From 34649f72b628c7c4966c167b8208f2595ca51251 Mon Sep 17 00:00:00 2001 From: Chris Metcalf Date: Thu, 23 Mar 2017 11:31:19 -0400 Subject: tile: prefer to __need_int_reg_t As part of some work in glibc to move away from the "__need" prefix, this commit breaks away the definitions of __int_reg_t, __uint_reg_t, __INT_REG_BITS, and __INT_REG_FMT to a separate "microheader". It is then included from to preserve the semantics of the previous header. For now, we continue to preserve the __need_int_reg_t semantics in as well, but anticipate that after a few years we can obsolete it. --- arch/tile/include/uapi/arch/abi.h | 49 +++---------------------- arch/tile/include/uapi/arch/intreg.h | 70 ++++++++++++++++++++++++++++++++++++ 2 files changed, 74 insertions(+), 45 deletions(-) create mode 100644 arch/tile/include/uapi/arch/intreg.h diff --git a/arch/tile/include/uapi/arch/abi.h b/arch/tile/include/uapi/arch/abi.h index c55a3d432644..328e62260272 100644 --- a/arch/tile/include/uapi/arch/abi.h +++ b/arch/tile/include/uapi/arch/abi.h @@ -20,58 +20,17 @@ #ifndef __ARCH_ABI_H__ -#if !defined __need_int_reg_t && !defined __DOXYGEN__ -# define __ARCH_ABI_H__ -# include -#endif - -/* Provide the basic machine types. */ -#ifndef __INT_REG_BITS - -/** Number of bits in a register. */ -#if defined __tilegx__ -# define __INT_REG_BITS 64 -#elif defined __tilepro__ -# define __INT_REG_BITS 32 -#elif !defined __need_int_reg_t +#ifndef __tile__ /* support uncommon use of arch headers in non-tile builds */ # include # define __INT_REG_BITS CHIP_WORD_SIZE() -#else -# error Unrecognized architecture with __need_int_reg_t -#endif - -#if __INT_REG_BITS == 64 - -#ifndef __ASSEMBLER__ -/** Unsigned type that can hold a register. */ -typedef unsigned long long __uint_reg_t; - -/** Signed type that can hold a register. */ -typedef long long __int_reg_t; -#endif - -/** String prefix to use for printf(). */ -#define __INT_REG_FMT "ll" - -#else - -#ifndef __ASSEMBLER__ -/** Unsigned type that can hold a register. */ -typedef unsigned long __uint_reg_t; - -/** Signed type that can hold a register. */ -typedef long __int_reg_t; -#endif - -/** String prefix to use for printf(). */ -#define __INT_REG_FMT "l" - #endif -#endif /* __INT_REG_BITS */ +#include +/* __need_int_reg_t is deprecated: just include */ #ifndef __need_int_reg_t +#define __ARCH_ABI_H__ #ifndef __ASSEMBLER__ /** Unsigned type that can hold a register. */ diff --git a/arch/tile/include/uapi/arch/intreg.h b/arch/tile/include/uapi/arch/intreg.h new file mode 100644 index 000000000000..1cf2fbf74306 --- /dev/null +++ b/arch/tile/include/uapi/arch/intreg.h @@ -0,0 +1,70 @@ +/* + * Copyright 2017 Tilera Corporation. All Rights Reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation, version 2. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/** + * @file + * + * Provide types and defines for the type that can hold a register, + * in the implementation namespace. + */ + +#ifndef __ARCH_INTREG_H__ +#define __ARCH_INTREG_H__ + +/* + * Get number of bits in a register. __INT_REG_BITS may be defined + * prior to including this header to force a particular bit width. + */ + +#ifndef __INT_REG_BITS +# if defined __tilegx__ +# define __INT_REG_BITS 64 +# elif defined __tilepro__ +# define __INT_REG_BITS 32 +# else +# error Unrecognized architecture +# endif +#endif + +#if __INT_REG_BITS == 64 + +# ifndef __ASSEMBLER__ +/** Unsigned type that can hold a register. */ +typedef unsigned long long __uint_reg_t; + +/** Signed type that can hold a register. */ +typedef long long __int_reg_t; +# endif + +/** String prefix to use for printf(). */ +# define __INT_REG_FMT "ll" + +#elif __INT_REG_BITS == 32 + +# ifndef __ASSEMBLER__ +/** Unsigned type that can hold a register. */ +typedef unsigned long __uint_reg_t; + +/** Signed type that can hold a register. */ +typedef long __int_reg_t; +# endif + +/** String prefix to use for printf(). */ +# define __INT_REG_FMT "l" + +#else +# error Unrecognized value of __INT_REG_BITS +#endif + +#endif /* !__ARCH_INTREG_H__ */ -- cgit v1.2.3-59-g8ed1b From 0af0bc38175d9859753a08f07af3aa767601265b Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 30 Mar 2017 13:54:50 +0200 Subject: mm, tile: drop arch_{add,remove}_memory these functions are unreachable because tile doesn't support memory hotplug becasuse it doesn't select ARCH_ENABLE_MEMORY_HOTPLUG nor it supports SPARSEMEM. This code hasn't been compiled for a while obviously because nobody has noticed that __add_pages has a different signature since 2009. Signed-off-by: Michal Hocko Signed-off-by: Chris Metcalf --- arch/tile/mm/init.c | 30 ------------------------------ 1 file changed, 30 deletions(-) diff --git a/arch/tile/mm/init.c b/arch/tile/mm/init.c index 3a97e4d7205c..5f757e04bcd2 100644 --- a/arch/tile/mm/init.c +++ b/arch/tile/mm/init.c @@ -857,36 +857,6 @@ void __init mem_init(void) #endif } -/* - * this is for the non-NUMA, single node SMP system case. - * Specifically, in the case of x86, we will always add - * memory to the highmem for now. - */ -#ifndef CONFIG_NEED_MULTIPLE_NODES -int arch_add_memory(u64 start, u64 size, bool for_device) -{ - struct pglist_data *pgdata = &contig_page_data; - struct zone *zone = pgdata->node_zones + MAX_NR_ZONES-1; - unsigned long start_pfn = start >> PAGE_SHIFT; - unsigned long nr_pages = size >> PAGE_SHIFT; - - return __add_pages(zone, start_pfn, nr_pages); -} - -int remove_memory(u64 start, u64 size) -{ - return -EINVAL; -} - -#ifdef CONFIG_MEMORY_HOTREMOVE -int arch_remove_memory(u64 start, u64 size) -{ - /* TODO */ - return -EBUSY; -} -#endif -#endif - struct kmem_cache *pgd_cache; void __init pgtable_cache_init(void) -- cgit v1.2.3-59-g8ed1b From c41e43c6faf68a9b70afdb0dfee45d196c27031b Mon Sep 17 00:00:00 2001 From: Andrey Smirnov Date: Fri, 21 Apr 2017 09:30:21 -0700 Subject: mtd: dataflash: Replace C99 types with their kernel counterparts No functional change intended. Cc: cphealy@gmail.com Cc: David Woodhouse Cc: Brian Norris Cc: Boris Brezillon Cc: Marek Vasut Cc: Richard Weinberger Cc: Cyrille Pitchen Cc: linux-kernel@vger.kernel.org Acked-by: Marek Vasut Signed-off-by: Andrey Smirnov Tested-by: Chris Healy Signed-off-by: Brian Norris --- drivers/mtd/devices/mtd_dataflash.c | 40 ++++++++++++++++++------------------- 1 file changed, 20 insertions(+), 20 deletions(-) diff --git a/drivers/mtd/devices/mtd_dataflash.c b/drivers/mtd/devices/mtd_dataflash.c index f9e9bd1cfaa0..a566231a9c79 100644 --- a/drivers/mtd/devices/mtd_dataflash.c +++ b/drivers/mtd/devices/mtd_dataflash.c @@ -84,7 +84,7 @@ struct dataflash { - uint8_t command[4]; + u8 command[4]; char name[24]; unsigned short page_offset; /* offset in flash address */ @@ -153,8 +153,8 @@ static int dataflash_erase(struct mtd_info *mtd, struct erase_info *instr) struct spi_transfer x = { }; struct spi_message msg; unsigned blocksize = priv->page_size << 3; - uint8_t *command; - uint32_t rem; + u8 *command; + u32 rem; pr_debug("%s: erase addr=0x%llx len 0x%llx\n", dev_name(&spi->dev), (long long)instr->addr, @@ -187,8 +187,8 @@ static int dataflash_erase(struct mtd_info *mtd, struct erase_info *instr) pageaddr = pageaddr << priv->page_offset; command[0] = do_block ? OP_ERASE_BLOCK : OP_ERASE_PAGE; - command[1] = (uint8_t)(pageaddr >> 16); - command[2] = (uint8_t)(pageaddr >> 8); + command[1] = (u8)(pageaddr >> 16); + command[2] = (u8)(pageaddr >> 8); command[3] = 0; pr_debug("ERASE %s: (%x) %x %x %x [%i]\n", @@ -239,7 +239,7 @@ static int dataflash_read(struct mtd_info *mtd, loff_t from, size_t len, struct spi_transfer x[2] = { }; struct spi_message msg; unsigned int addr; - uint8_t *command; + u8 *command; int status; pr_debug("%s: read 0x%x..0x%x\n", dev_name(&priv->spi->dev), @@ -271,9 +271,9 @@ static int dataflash_read(struct mtd_info *mtd, loff_t from, size_t len, * fewer "don't care" bytes. Both buffers stay unchanged. */ command[0] = OP_READ_CONTINUOUS; - command[1] = (uint8_t)(addr >> 16); - command[2] = (uint8_t)(addr >> 8); - command[3] = (uint8_t)(addr >> 0); + command[1] = (u8)(addr >> 16); + command[2] = (u8)(addr >> 8); + command[3] = (u8)(addr >> 0); /* plus 4 "don't care" bytes */ status = spi_sync(priv->spi, &msg); @@ -308,7 +308,7 @@ static int dataflash_write(struct mtd_info *mtd, loff_t to, size_t len, size_t remaining = len; u_char *writebuf = (u_char *) buf; int status = -EINVAL; - uint8_t *command; + u8 *command; pr_debug("%s: write 0x%x..0x%x\n", dev_name(&spi->dev), (unsigned)to, (unsigned)(to + len)); @@ -455,11 +455,11 @@ static int dataflash_get_otp_info(struct mtd_info *mtd, size_t len, } static ssize_t otp_read(struct spi_device *spi, unsigned base, - uint8_t *buf, loff_t off, size_t len) + u8 *buf, loff_t off, size_t len) { struct spi_message m; size_t l; - uint8_t *scratch; + u8 *scratch; struct spi_transfer t; int status; @@ -538,7 +538,7 @@ static int dataflash_write_user_otp(struct mtd_info *mtd, { struct spi_message m; const size_t l = 4 + 64; - uint8_t *scratch; + u8 *scratch; struct spi_transfer t; struct dataflash *priv = mtd->priv; int status; @@ -689,14 +689,14 @@ struct flash_info { /* JEDEC id has a high byte of zero plus three data bytes: * the manufacturer id, then a two byte device id. */ - uint32_t jedec_id; + u32 jedec_id; /* The size listed here is what works with OP_ERASE_PAGE. */ unsigned nr_pages; - uint16_t pagesize; - uint16_t pageoffset; + u16 pagesize; + u16 pageoffset; - uint16_t flags; + u16 flags; #define SUP_POW2PS 0x0002 /* supports 2^N byte pages */ #define IS_POW2PS 0x0001 /* uses 2^N byte pages */ }; @@ -739,9 +739,9 @@ static struct flash_info dataflash_data[] = { static struct flash_info *jedec_probe(struct spi_device *spi) { int tmp; - uint8_t code = OP_READ_ID; - uint8_t id[3]; - uint32_t jedec; + u8 code = OP_READ_ID; + u8 id[3]; + u32 jedec; struct flash_info *info; int status; -- cgit v1.2.3-59-g8ed1b From 41c9c6621afa22c86fe74cf07536fd21c7719ca6 Mon Sep 17 00:00:00 2001 From: Andrey Smirnov Date: Fri, 21 Apr 2017 09:30:22 -0700 Subject: mtd: dataflash: Improve coding style in jedec_probe() Change the following: - Replace indentation between type and name of local variable from tabs to spaces - Replace magic number 0x1F with CFI_MFR_ATMEL macro - Replace variable 'tmp' with 'ret' and 'i' where appropriate - Reformat multi-line comments and add newlines where appropriate No functional change intended. Cc: cphealy@gmail.com Cc: David Woodhouse Cc: Brian Norris Cc: Boris Brezillon Cc: Richard Weinberger Cc: Cyrille Pitchen Cc: Marek Vasut Cc: linux-kernel@vger.kernel.org Acked-by: Marek Vasut Tested-by: Chris Healy Signed-off-by: Andrey Smirnov Signed-off-by: Brian Norris --- drivers/mtd/devices/mtd_dataflash.c | 31 +++++++++++++++++-------------- 1 file changed, 17 insertions(+), 14 deletions(-) diff --git a/drivers/mtd/devices/mtd_dataflash.c b/drivers/mtd/devices/mtd_dataflash.c index a566231a9c79..5b7a8c36e4f7 100644 --- a/drivers/mtd/devices/mtd_dataflash.c +++ b/drivers/mtd/devices/mtd_dataflash.c @@ -82,6 +82,7 @@ #define OP_WRITE_SECURITY_REVC 0x9A #define OP_WRITE_SECURITY 0x9B /* revision D */ +#define CFI_MFR_ATMEL 0x1F struct dataflash { u8 command[4]; @@ -738,14 +739,15 @@ static struct flash_info dataflash_data[] = { static struct flash_info *jedec_probe(struct spi_device *spi) { - int tmp; - u8 code = OP_READ_ID; - u8 id[3]; - u32 jedec; - struct flash_info *info; + int ret, i; + u8 code = OP_READ_ID; + u8 id[3]; + u32 jedec; + struct flash_info *info; int status; - /* JEDEC also defines an optional "extended device information" + /* + * JEDEC also defines an optional "extended device information" * string for after vendor-specific data, after the three bytes * we use here. Supporting some chips might require using it. * @@ -753,13 +755,14 @@ static struct flash_info *jedec_probe(struct spi_device *spi) * That's not an error; only rev C and newer chips handle it, and * only Atmel sells these chips. */ - tmp = spi_write_then_read(spi, &code, 1, id, 3); - if (tmp < 0) { + ret = spi_write_then_read(spi, &code, 1, id, 3); + if (ret < 0) { pr_debug("%s: error %d reading JEDEC ID\n", - dev_name(&spi->dev), tmp); - return ERR_PTR(tmp); + dev_name(&spi->dev), ret); + return ERR_PTR(ret); } - if (id[0] != 0x1f) + + if (id[0] != CFI_MFR_ATMEL) return NULL; jedec = id[0]; @@ -768,9 +771,9 @@ static struct flash_info *jedec_probe(struct spi_device *spi) jedec = jedec << 8; jedec |= id[2]; - for (tmp = 0, info = dataflash_data; - tmp < ARRAY_SIZE(dataflash_data); - tmp++, info++) { + for (i = 0, info = dataflash_data; + i < ARRAY_SIZE(dataflash_data); + i++, info++) { if (info->jedec_id == jedec) { pr_debug("%s: OTP, sector protect%s\n", dev_name(&spi->dev), -- cgit v1.2.3-59-g8ed1b From 02f62864f6cebbbbff6bb611fddf78c1d05a9747 Mon Sep 17 00:00:00 2001 From: Andrey Smirnov Date: Fri, 21 Apr 2017 09:30:23 -0700 Subject: mtd: dataflash: Replace pr_debug, printk with dev_* functions Lion's share of calls to pr_debug in this driver follow the pattern of pr_debug("%s ", dev_name(), ), which should be semantically identical to dev_dbg(, "", ), so replace such occurencies to simplify the code. Convert the small minority of pr_debug that do not follow pattern from above to use dev_dbg as well, for the sake of consistency. Convert similar patter of printk(KERN_ERR, "%s: ...", dev_name(...), ...) to use dev_err instead. No functional change intended. Cc: cphealy@gmail.com Cc: David Woodhouse Cc: Brian Norris Cc: Boris Brezillon Cc: Marek Vasut Cc: Richard Weinberger Cc: Cyrille Pitchen Cc: linux-kernel@vger.kernel.org Reviewed-by: Marek Vasut Tested-by: Chris Healy Signed-off-by: Andrey Smirnov Signed-off-by: Brian Norris --- drivers/mtd/devices/mtd_dataflash.c | 74 +++++++++++++++++-------------------- 1 file changed, 33 insertions(+), 41 deletions(-) diff --git a/drivers/mtd/devices/mtd_dataflash.c b/drivers/mtd/devices/mtd_dataflash.c index 5b7a8c36e4f7..ccd1e024d343 100644 --- a/drivers/mtd/devices/mtd_dataflash.c +++ b/drivers/mtd/devices/mtd_dataflash.c @@ -130,8 +130,7 @@ static int dataflash_waitready(struct spi_device *spi) for (;;) { status = dataflash_status(spi); if (status < 0) { - pr_debug("%s: status %d?\n", - dev_name(&spi->dev), status); + dev_dbg(&spi->dev, "status %d?\n", status); status = 0; } @@ -157,9 +156,8 @@ static int dataflash_erase(struct mtd_info *mtd, struct erase_info *instr) u8 *command; u32 rem; - pr_debug("%s: erase addr=0x%llx len 0x%llx\n", - dev_name(&spi->dev), (long long)instr->addr, - (long long)instr->len); + dev_dbg(&spi->dev, "erase addr=0x%llx len 0x%llx\n", + (long long)instr->addr, (long long)instr->len); div_u64_rem(instr->len, priv->page_size, &rem); if (rem) @@ -192,7 +190,7 @@ static int dataflash_erase(struct mtd_info *mtd, struct erase_info *instr) command[2] = (u8)(pageaddr >> 8); command[3] = 0; - pr_debug("ERASE %s: (%x) %x %x %x [%i]\n", + dev_dbg(&spi->dev, "ERASE %s: (%x) %x %x %x [%i]\n", do_block ? "block" : "page", command[0], command[1], command[2], command[3], pageaddr); @@ -201,8 +199,8 @@ static int dataflash_erase(struct mtd_info *mtd, struct erase_info *instr) (void) dataflash_waitready(spi); if (status < 0) { - printk(KERN_ERR "%s: erase %x, err %d\n", - dev_name(&spi->dev), pageaddr, status); + dev_err(&spi->dev, "erase %x, err %d\n", + pageaddr, status); /* REVISIT: can retry instr->retries times; or * giveup and instr->fail_addr = instr->addr; */ @@ -243,8 +241,8 @@ static int dataflash_read(struct mtd_info *mtd, loff_t from, size_t len, u8 *command; int status; - pr_debug("%s: read 0x%x..0x%x\n", dev_name(&priv->spi->dev), - (unsigned)from, (unsigned)(from + len)); + dev_dbg(&priv->spi->dev, "read 0x%x..0x%x\n", + (unsigned int)from, (unsigned int)(from + len)); /* Calculate flash page/byte address */ addr = (((unsigned)from / priv->page_size) << priv->page_offset) @@ -252,7 +250,7 @@ static int dataflash_read(struct mtd_info *mtd, loff_t from, size_t len, command = priv->command; - pr_debug("READ: (%x) %x %x %x\n", + dev_dbg(&priv->spi->dev, "READ: (%x) %x %x %x\n", command[0], command[1], command[2], command[3]); spi_message_init(&msg); @@ -284,8 +282,7 @@ static int dataflash_read(struct mtd_info *mtd, loff_t from, size_t len, *retlen = msg.actual_length - 8; status = 0; } else - pr_debug("%s: read %x..%x --> %d\n", - dev_name(&priv->spi->dev), + dev_dbg(&priv->spi->dev, "read %x..%x --> %d\n", (unsigned)from, (unsigned)(from + len), status); return status; @@ -311,8 +308,8 @@ static int dataflash_write(struct mtd_info *mtd, loff_t to, size_t len, int status = -EINVAL; u8 *command; - pr_debug("%s: write 0x%x..0x%x\n", - dev_name(&spi->dev), (unsigned)to, (unsigned)(to + len)); + dev_dbg(&spi->dev, "write 0x%x..0x%x\n", + (unsigned int)to, (unsigned int)(to + len)); spi_message_init(&msg); @@ -329,7 +326,7 @@ static int dataflash_write(struct mtd_info *mtd, loff_t to, size_t len, mutex_lock(&priv->lock); while (remaining > 0) { - pr_debug("write @ %i:%i len=%i\n", + dev_dbg(&spi->dev, "write @ %i:%i len=%i\n", pageaddr, offset, writelen); /* REVISIT: @@ -357,13 +354,13 @@ static int dataflash_write(struct mtd_info *mtd, loff_t to, size_t len, command[2] = (addr & 0x0000FF00) >> 8; command[3] = 0; - pr_debug("TRANSFER: (%x) %x %x %x\n", + dev_dbg(&spi->dev, "TRANSFER: (%x) %x %x %x\n", command[0], command[1], command[2], command[3]); status = spi_sync(spi, &msg); if (status < 0) - pr_debug("%s: xfer %u -> %d\n", - dev_name(&spi->dev), addr, status); + dev_dbg(&spi->dev, "xfer %u -> %d\n", + addr, status); (void) dataflash_waitready(priv->spi); } @@ -375,7 +372,7 @@ static int dataflash_write(struct mtd_info *mtd, loff_t to, size_t len, command[2] = (addr & 0x0000FF00) >> 8; command[3] = (addr & 0x000000FF); - pr_debug("PROGRAM: (%x) %x %x %x\n", + dev_dbg(&spi->dev, "PROGRAM: (%x) %x %x %x\n", command[0], command[1], command[2], command[3]); x[1].tx_buf = writebuf; @@ -384,8 +381,8 @@ static int dataflash_write(struct mtd_info *mtd, loff_t to, size_t len, status = spi_sync(spi, &msg); spi_transfer_del(x + 1); if (status < 0) - pr_debug("%s: pgm %u/%u -> %d\n", - dev_name(&spi->dev), addr, writelen, status); + dev_dbg(&spi->dev, "pgm %u/%u -> %d\n", + addr, writelen, status); (void) dataflash_waitready(priv->spi); @@ -399,20 +396,20 @@ static int dataflash_write(struct mtd_info *mtd, loff_t to, size_t len, command[2] = (addr & 0x0000FF00) >> 8; command[3] = 0; - pr_debug("COMPARE: (%x) %x %x %x\n", + dev_dbg(&spi->dev, "COMPARE: (%x) %x %x %x\n", command[0], command[1], command[2], command[3]); status = spi_sync(spi, &msg); if (status < 0) - pr_debug("%s: compare %u -> %d\n", - dev_name(&spi->dev), addr, status); + dev_dbg(&spi->dev, "compare %u -> %d\n", + addr, status); status = dataflash_waitready(priv->spi); /* Check result of the compare operation */ if (status & (1 << 6)) { - printk(KERN_ERR "%s: compare page %u, err %d\n", - dev_name(&spi->dev), pageaddr, status); + dev_err(&spi->dev, "compare page %u, err %d\n", + pageaddr, status); remaining = 0; status = -EIO; break; @@ -757,8 +754,7 @@ static struct flash_info *jedec_probe(struct spi_device *spi) */ ret = spi_write_then_read(spi, &code, 1, id, 3); if (ret < 0) { - pr_debug("%s: error %d reading JEDEC ID\n", - dev_name(&spi->dev), ret); + dev_dbg(&spi->dev, "error %d reading JEDEC ID\n", ret); return ERR_PTR(ret); } @@ -775,16 +771,14 @@ static struct flash_info *jedec_probe(struct spi_device *spi) i < ARRAY_SIZE(dataflash_data); i++, info++) { if (info->jedec_id == jedec) { - pr_debug("%s: OTP, sector protect%s\n", - dev_name(&spi->dev), - (info->flags & SUP_POW2PS) - ? ", binary pagesize" : "" - ); + dev_dbg(&spi->dev, "OTP, sector protect%s\n", + (info->flags & SUP_POW2PS) ? + ", binary pagesize" : ""); if (info->flags & SUP_POW2PS) { status = dataflash_status(spi); if (status < 0) { - pr_debug("%s: status error %d\n", - dev_name(&spi->dev), status); + dev_dbg(&spi->dev, "status error %d\n", + status); return ERR_PTR(status); } if (status & 0x1) { @@ -848,8 +842,7 @@ static int dataflash_probe(struct spi_device *spi) */ status = dataflash_status(spi); if (status <= 0 || status == 0xff) { - pr_debug("%s: status error %d\n", - dev_name(&spi->dev), status); + dev_dbg(&spi->dev, "status error %d\n", status); if (status == 0 || status == 0xff) status = -ENODEV; return status; @@ -890,8 +883,7 @@ static int dataflash_probe(struct spi_device *spi) } if (status < 0) - pr_debug("%s: add_dataflash --> %d\n", dev_name(&spi->dev), - status); + dev_dbg(&spi->dev, "add_dataflash --> %d\n", status); return status; } @@ -901,7 +893,7 @@ static int dataflash_remove(struct spi_device *spi) struct dataflash *flash = spi_get_drvdata(spi); int status; - pr_debug("%s: remove\n", dev_name(&spi->dev)); + dev_dbg(&spi->dev, "remove\n"); status = mtd_device_unregister(&flash->mtd); if (status == 0) -- cgit v1.2.3-59-g8ed1b From a296a1bc3eb54382d2a61d47529e71c9d3bc615e Mon Sep 17 00:00:00 2001 From: Andrey Smirnov Date: Fri, 21 Apr 2017 09:30:24 -0700 Subject: mtd: dataflash: Get rid of loop counter in jedec_probe() "For" loop in jedec_probe can be simplified to not need counter 'i'. Convert the code and get rid of the variable. Cc: cphealy@gmail.com Cc: David Woodhouse Cc: Brian Norris Cc: Boris Brezillon Cc: Marek Vasut Cc: Richard Weinberger Cc: Cyrille Pitchen Cc: linux-kernel@vger.kernel.org Reviewed-by: Marek Vasut Tested-by: Chris Healy Signed-off-by: Andrey Smirnov Signed-off-by: Brian Norris --- drivers/mtd/devices/mtd_dataflash.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/mtd/devices/mtd_dataflash.c b/drivers/mtd/devices/mtd_dataflash.c index ccd1e024d343..2d3e4034b591 100644 --- a/drivers/mtd/devices/mtd_dataflash.c +++ b/drivers/mtd/devices/mtd_dataflash.c @@ -736,7 +736,7 @@ static struct flash_info dataflash_data[] = { static struct flash_info *jedec_probe(struct spi_device *spi) { - int ret, i; + int ret; u8 code = OP_READ_ID; u8 id[3]; u32 jedec; @@ -767,9 +767,9 @@ static struct flash_info *jedec_probe(struct spi_device *spi) jedec = jedec << 8; jedec |= id[2]; - for (i = 0, info = dataflash_data; - i < ARRAY_SIZE(dataflash_data); - i++, info++) { + for (info = dataflash_data; + info < dataflash_data + ARRAY_SIZE(dataflash_data); + info++) { if (info->jedec_id == jedec) { dev_dbg(&spi->dev, "OTP, sector protect%s\n", (info->flags & SUP_POW2PS) ? -- cgit v1.2.3-59-g8ed1b From 1da8869a428317a6d3cd8d47184cf87feb34a98b Mon Sep 17 00:00:00 2001 From: Andrey Smirnov Date: Fri, 21 Apr 2017 09:30:25 -0700 Subject: mtd: dataflash: Make use of "extened device information" In anticipation of supporting chips that need it, extend the size of struct flash_info's 'jedec_id' field to make room 2 byte of extended device information as well as add code to fetch this data during jedec_probe(). Cc: cphealy@gmail.com Cc: David Woodhouse Cc: Brian Norris Cc: Boris Brezillon Cc: Marek Vasut Cc: Richard Weinberger Cc: Cyrille Pitchen Cc: linux-kernel@vger.kernel.org Acked-by: Marek Vasut Tested-by: Chris Healy Signed-off-by: Andrey Smirnov Signed-off-by: Brian Norris --- drivers/mtd/devices/mtd_dataflash.c | 88 ++++++++++++++++++++++++------------- 1 file changed, 57 insertions(+), 31 deletions(-) diff --git a/drivers/mtd/devices/mtd_dataflash.c b/drivers/mtd/devices/mtd_dataflash.c index 2d3e4034b591..3f1a0fbe5a58 100644 --- a/drivers/mtd/devices/mtd_dataflash.c +++ b/drivers/mtd/devices/mtd_dataflash.c @@ -84,6 +84,9 @@ #define CFI_MFR_ATMEL 0x1F +#define DATAFLASH_SHIFT_EXTID 24 +#define DATAFLASH_SHIFT_ID 40 + struct dataflash { u8 command[4]; char name[24]; @@ -687,7 +690,7 @@ struct flash_info { /* JEDEC id has a high byte of zero plus three data bytes: * the manufacturer id, then a two byte device id. */ - u32 jedec_id; + u64 jedec_id; /* The size listed here is what works with OP_ERASE_PAGE. */ unsigned nr_pages; @@ -695,6 +698,7 @@ struct flash_info { u16 pageoffset; u16 flags; +#define SUP_EXTID 0x0004 /* supports extended ID data */ #define SUP_POW2PS 0x0002 /* supports 2^N byte pages */ #define IS_POW2PS 0x0001 /* uses 2^N byte pages */ }; @@ -734,42 +738,18 @@ static struct flash_info dataflash_data[] = { { "at45db642d", 0x1f2800, 8192, 1024, 10, SUP_POW2PS | IS_POW2PS}, }; -static struct flash_info *jedec_probe(struct spi_device *spi) +static struct flash_info *jedec_lookup(struct spi_device *spi, + u64 jedec, bool use_extid) { - int ret; - u8 code = OP_READ_ID; - u8 id[3]; - u32 jedec; struct flash_info *info; int status; - /* - * JEDEC also defines an optional "extended device information" - * string for after vendor-specific data, after the three bytes - * we use here. Supporting some chips might require using it. - * - * If the vendor ID isn't Atmel's (0x1f), assume this call failed. - * That's not an error; only rev C and newer chips handle it, and - * only Atmel sells these chips. - */ - ret = spi_write_then_read(spi, &code, 1, id, 3); - if (ret < 0) { - dev_dbg(&spi->dev, "error %d reading JEDEC ID\n", ret); - return ERR_PTR(ret); - } - - if (id[0] != CFI_MFR_ATMEL) - return NULL; - - jedec = id[0]; - jedec = jedec << 8; - jedec |= id[1]; - jedec = jedec << 8; - jedec |= id[2]; - for (info = dataflash_data; info < dataflash_data + ARRAY_SIZE(dataflash_data); info++) { + if (use_extid && !(info->flags & SUP_EXTID)) + continue; + if (info->jedec_id == jedec) { dev_dbg(&spi->dev, "OTP, sector protect%s\n", (info->flags & SUP_POW2PS) ? @@ -793,12 +773,58 @@ static struct flash_info *jedec_probe(struct spi_device *spi) } } + return ERR_PTR(-ENODEV); +} + +static struct flash_info *jedec_probe(struct spi_device *spi) +{ + int ret; + u8 code = OP_READ_ID; + u64 jedec; + u8 id[sizeof(jedec)] = {0}; + const unsigned int id_size = 5; + struct flash_info *info; + + /* + * JEDEC also defines an optional "extended device information" + * string for after vendor-specific data, after the three bytes + * we use here. Supporting some chips might require using it. + * + * If the vendor ID isn't Atmel's (0x1f), assume this call failed. + * That's not an error; only rev C and newer chips handle it, and + * only Atmel sells these chips. + */ + ret = spi_write_then_read(spi, &code, 1, id, id_size); + if (ret < 0) { + dev_dbg(&spi->dev, "error %d reading JEDEC ID\n", ret); + return ERR_PTR(ret); + } + + if (id[0] != CFI_MFR_ATMEL) + return NULL; + + jedec = be64_to_cpup((__be64 *)id); + + /* + * First, try to match device using extended device + * information + */ + info = jedec_lookup(spi, jedec >> DATAFLASH_SHIFT_EXTID, true); + if (!IS_ERR(info)) + return info; + /* + * If that fails, make another pass using regular ID + * information + */ + info = jedec_lookup(spi, jedec >> DATAFLASH_SHIFT_ID, false); + if (!IS_ERR(info)) + return info; /* * Treat other chips as errors ... we won't know the right page * size (it might be binary) even when we can tell which density * class is involved (legacy chip id scheme). */ - dev_warn(&spi->dev, "JEDEC id %06x not handled\n", jedec); + dev_warn(&spi->dev, "JEDEC id %016llx not handled\n", jedec); return ERR_PTR(-ENODEV); } -- cgit v1.2.3-59-g8ed1b From 67e4145ebf2c161d7404770461b8404f00a6d3bf Mon Sep 17 00:00:00 2001 From: Andrey Smirnov Date: Fri, 21 Apr 2017 09:30:26 -0700 Subject: mtd: dataflash: Add flash_info for AT45DB641E Cc: cphealy@gmail.com Cc: David Woodhouse Cc: Brian Norris Cc: Boris Brezillon Cc: Marek Vasut Cc: Richard Weinberger Cc: Cyrille Pitchen Cc: linux-kernel@vger.kernel.org Acked-by: Marek Vasut Tested-by: Chris Healy Signed-off-by: Andrey Smirnov Signed-off-by: Brian Norris --- drivers/mtd/devices/mtd_dataflash.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/mtd/devices/mtd_dataflash.c b/drivers/mtd/devices/mtd_dataflash.c index 3f1a0fbe5a58..5dc8bd042cc5 100644 --- a/drivers/mtd/devices/mtd_dataflash.c +++ b/drivers/mtd/devices/mtd_dataflash.c @@ -736,6 +736,9 @@ static struct flash_info dataflash_data[] = { { "AT45DB642x", 0x1f2800, 8192, 1056, 11, SUP_POW2PS}, { "at45db642d", 0x1f2800, 8192, 1024, 10, SUP_POW2PS | IS_POW2PS}, + + { "AT45DB641E", 0x1f28000100, 32768, 264, 9, SUP_EXTID | SUP_POW2PS}, + { "at45db641e", 0x1f28000100, 32768, 256, 8, SUP_EXTID | SUP_POW2PS | IS_POW2PS}, }; static struct flash_info *jedec_lookup(struct spi_device *spi, -- cgit v1.2.3-59-g8ed1b From 5dc17fa6fb7063c6bc8ea9f3183ec19ca68bbfd6 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 12 Apr 2017 17:34:31 +0200 Subject: mtd: mchp23k256: Add driver for this SPI SRAM device The Microchip 23k256 is a 32K Byte SRAM connected via SPI. Signed-off-by: Andrew Lunn Reviewed-by: Boris Brezillon Reviewed-by: Cyrille Pitchen [Brian: fixed copyright to be in this millenium] Signed-off-by: Brian Norris --- drivers/mtd/devices/Kconfig | 10 +++ drivers/mtd/devices/Makefile | 1 + drivers/mtd/devices/mchp23k256.c | 182 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 193 insertions(+) create mode 100644 drivers/mtd/devices/mchp23k256.c diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig index 58329d2dacd1..6def5445e03e 100644 --- a/drivers/mtd/devices/Kconfig +++ b/drivers/mtd/devices/Kconfig @@ -95,6 +95,16 @@ config MTD_M25P80 if you want to specify device partitioning or to use a device which doesn't support the JEDEC ID instruction. +config MTD_MCHP23K256 + tristate "Microchip 23K256 SRAM" + depends on SPI_MASTER + help + This enables access to Microchip 23K256 SRAM chips, using SPI. + + Set up your spi devices with the right board-specific + platform data, or a device tree description if you want to + specify device partitioning + config MTD_SPEAR_SMI tristate "SPEAR MTD NOR Support through SMI controller" depends on PLAT_SPEAR diff --git a/drivers/mtd/devices/Makefile b/drivers/mtd/devices/Makefile index 7912d3a0ee34..f0f767624cc6 100644 --- a/drivers/mtd/devices/Makefile +++ b/drivers/mtd/devices/Makefile @@ -12,6 +12,7 @@ obj-$(CONFIG_MTD_LART) += lart.o obj-$(CONFIG_MTD_BLOCK2MTD) += block2mtd.o obj-$(CONFIG_MTD_DATAFLASH) += mtd_dataflash.o obj-$(CONFIG_MTD_M25P80) += m25p80.o +obj-$(CONFIG_MTD_MCHP23K256) += mchp23k256.o obj-$(CONFIG_MTD_SPEAR_SMI) += spear_smi.o obj-$(CONFIG_MTD_SST25L) += sst25l.o obj-$(CONFIG_MTD_BCM47XXSFLASH) += bcm47xxsflash.o diff --git a/drivers/mtd/devices/mchp23k256.c b/drivers/mtd/devices/mchp23k256.c new file mode 100644 index 000000000000..e237db9f1bdb --- /dev/null +++ b/drivers/mtd/devices/mchp23k256.c @@ -0,0 +1,182 @@ +/* + * mchp23k256.c + * + * Driver for Microchip 23k256 SPI RAM chips + * + * Copyright © 2016 Andrew Lunn + * + * This code is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct mchp23k256_flash { + struct spi_device *spi; + struct mutex lock; + struct mtd_info mtd; +}; + +#define MCHP23K256_CMD_WRITE_STATUS 0x01 +#define MCHP23K256_CMD_WRITE 0x02 +#define MCHP23K256_CMD_READ 0x03 +#define MCHP23K256_MODE_SEQ BIT(6) + +#define to_mchp23k256_flash(x) container_of(x, struct mchp23k256_flash, mtd) + +static int mchp23k256_write(struct mtd_info *mtd, loff_t to, size_t len, + size_t *retlen, const unsigned char *buf) +{ + struct mchp23k256_flash *flash = to_mchp23k256_flash(mtd); + struct spi_transfer transfer[2] = {}; + struct spi_message message; + unsigned char command[3]; + + spi_message_init(&message); + + command[0] = MCHP23K256_CMD_WRITE; + command[1] = to >> 8; + command[2] = to; + + transfer[0].tx_buf = command; + transfer[0].len = sizeof(command); + spi_message_add_tail(&transfer[0], &message); + + transfer[1].tx_buf = buf; + transfer[1].len = len; + spi_message_add_tail(&transfer[1], &message); + + mutex_lock(&flash->lock); + + spi_sync(flash->spi, &message); + + if (retlen && message.actual_length > sizeof(command)) + *retlen += message.actual_length - sizeof(command); + + mutex_unlock(&flash->lock); + return 0; +} + +static int mchp23k256_read(struct mtd_info *mtd, loff_t from, size_t len, + size_t *retlen, unsigned char *buf) +{ + struct mchp23k256_flash *flash = to_mchp23k256_flash(mtd); + struct spi_transfer transfer[2] = {}; + struct spi_message message; + unsigned char command[3]; + + spi_message_init(&message); + + memset(&transfer, 0, sizeof(transfer)); + command[0] = MCHP23K256_CMD_READ; + command[1] = from >> 8; + command[2] = from; + + transfer[0].tx_buf = command; + transfer[0].len = sizeof(command); + spi_message_add_tail(&transfer[0], &message); + + transfer[1].rx_buf = buf; + transfer[1].len = len; + spi_message_add_tail(&transfer[1], &message); + + mutex_lock(&flash->lock); + + spi_sync(flash->spi, &message); + + if (retlen && message.actual_length > sizeof(command)) + *retlen += message.actual_length - sizeof(command); + + mutex_unlock(&flash->lock); + return 0; +} + +/* + * Set the device into sequential mode. This allows read/writes to the + * entire SRAM in a single operation + */ +static int mchp23k256_set_mode(struct spi_device *spi) +{ + struct spi_transfer transfer = {}; + struct spi_message message; + unsigned char command[2]; + + spi_message_init(&message); + + command[0] = MCHP23K256_CMD_WRITE_STATUS; + command[1] = MCHP23K256_MODE_SEQ; + + transfer.tx_buf = command; + transfer.len = sizeof(command); + spi_message_add_tail(&transfer, &message); + + return spi_sync(spi, &message); +} + +static int mchp23k256_probe(struct spi_device *spi) +{ + struct mchp23k256_flash *flash; + struct flash_platform_data *data; + int err; + + flash = devm_kzalloc(&spi->dev, sizeof(*flash), GFP_KERNEL); + if (!flash) + return -ENOMEM; + + flash->spi = spi; + mutex_init(&flash->lock); + spi_set_drvdata(spi, flash); + + err = mchp23k256_set_mode(spi); + if (err) + return err; + + data = dev_get_platdata(&spi->dev); + + flash->mtd.dev.parent = &spi->dev; + flash->mtd.type = MTD_RAM; + flash->mtd.flags = MTD_CAP_RAM; + flash->mtd.writesize = 1; + flash->mtd.size = SZ_32K; + flash->mtd._read = mchp23k256_read; + flash->mtd._write = mchp23k256_write; + + err = mtd_device_parse_register(&flash->mtd, NULL, NULL, + data ? data->parts : NULL, + data ? data->nr_parts : 0); + if (err) + return err; + + return 0; +} + +static int mchp23k256_remove(struct spi_device *spi) +{ + struct mchp23k256_flash *flash = spi_get_drvdata(spi); + + return mtd_device_unregister(&flash->mtd); +} + +static struct spi_driver mchp23k256_driver = { + .driver = { + .name = "mchp23k256", + }, + .probe = mchp23k256_probe, + .remove = mchp23k256_remove, +}; + +module_spi_driver(mchp23k256_driver); + +MODULE_DESCRIPTION("MTD SPI driver for MCHP23K256 RAM chips"); +MODULE_AUTHOR("Andrew Lunn "); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("spi:mchp23k256"); -- cgit v1.2.3-59-g8ed1b From a63be500c6663a98cedda15c1bb380e9a34349e8 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Thu, 4 May 2017 22:10:46 +0200 Subject: mtd: cfi_cmdset_0020: Drop unnecessary static Drop static on a local variable, when the variable is initialized before any use on every possible execution path through the function. The static has no benefit, and dropping it reduces the code size. The semantic patch that fixes this problem is as follows: (http://coccinelle.lip6.fr/) // @bad exists@ position p; identifier x; type T; @@ static T x@p; ... x = <+...x...+> @@ identifier x; expression e; type T; position p != bad.p; @@ -static T x@p; ... when != x when strict ?x = e; // The change in code size is indicates by the following output from the size command. before: text data bss dec hex filename 16671 48 16 16735 415f drivers/mtd/chips/cfi_cmdset_0020.o after: text data bss dec hex filename 16639 48 8 16695 4137 drivers/mtd/chips/cfi_cmdset_0020.o Signed-off-by: Julia Lawall Signed-off-by: Brian Norris --- drivers/mtd/chips/cfi_cmdset_0020.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/chips/cfi_cmdset_0020.c b/drivers/mtd/chips/cfi_cmdset_0020.c index 94d3eb42c4d5..7d342965f392 100644 --- a/drivers/mtd/chips/cfi_cmdset_0020.c +++ b/drivers/mtd/chips/cfi_cmdset_0020.c @@ -666,7 +666,7 @@ cfi_staa_writev(struct mtd_info *mtd, const struct kvec *vecs, size_t totlen = 0, thislen; int ret = 0; size_t buflen = 0; - static char *buffer; + char *buffer; if (!ECCBUF_SIZE) { /* We should fall back to a general writev implementation. -- cgit v1.2.3-59-g8ed1b From 6c51a52eeb58befd2e9be2ed7ee2c4c04139b336 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Thu, 4 May 2017 22:10:47 +0200 Subject: mtd: physmap_of: Drop unnecessary static Drop static on a local variable, when the variable is initialized before any use on every possible execution path through the function. The static has no benefit, and dropping it reduces the code size. The semantic patch that fixes this problem is as follows: (http://coccinelle.lip6.fr/) // @bad exists@ position p; identifier x; type T; @@ static T x@p; ... x = <+...x...+> @@ identifier x; expression e; type T; position p != bad.p; @@ -static T x@p; ... when != x when strict ?x = e; // The change in code size is indicates by the following output from the size command. before: text data bss dec hex filename 835 80 8 923 39b drivers/mtd/maps/physmap_of_gemini.o after: text data bss dec hex filename 823 80 0 903 387 drivers/mtd/maps/physmap_of_gemini.o Signed-off-by: Julia Lawall Signed-off-by: Brian Norris --- drivers/mtd/maps/physmap_of_gemini.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/maps/physmap_of_gemini.c b/drivers/mtd/maps/physmap_of_gemini.c index 9d371cd728ea..05b286b5289f 100644 --- a/drivers/mtd/maps/physmap_of_gemini.c +++ b/drivers/mtd/maps/physmap_of_gemini.c @@ -59,7 +59,7 @@ int of_flash_probe_gemini(struct platform_device *pdev, struct device_node *np, struct map_info *map) { - static struct regmap *rmap; + struct regmap *rmap; struct device *dev = &pdev->dev; u32 val; int ret; -- cgit v1.2.3-59-g8ed1b From 7699f1e358ec60958a153e365901cb1e7ca62e93 Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Tue, 2 May 2017 16:49:51 -0300 Subject: mtd: nand: Add Hisilicon machine dependency The Hisilicon NAND driver is only needed for a specific platform, so avoid cluttering the configuration. Signed-off-by: Ezequiel Garcia Signed-off-by: Boris Brezillon --- drivers/mtd/nand/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig index c3029528063b..effe767fc347 100644 --- a/drivers/mtd/nand/Kconfig +++ b/drivers/mtd/nand/Kconfig @@ -542,6 +542,7 @@ config MTD_NAND_SUNXI config MTD_NAND_HISI504 tristate "Support for NAND controller on Hisilicon SoC Hip04" + depends on ARCH_HISI || COMPILE_TEST depends on HAS_DMA help Enables support for NAND controller on Hisilicon SoC Hip04. -- cgit v1.2.3-59-g8ed1b From 6f9ad5f360e865cba263109cb186cb2e16dbdc8d Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Tue, 2 May 2017 16:49:52 -0300 Subject: mtd: nand: Add Mediatek machine dependency The Mediatek NAND driver is only needed for a specific platform, so avoid cluttering the configuration. Signed-off-by: Ezequiel Garcia Signed-off-by: Boris Brezillon --- drivers/mtd/nand/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig index effe767fc347..0bd2319d3035 100644 --- a/drivers/mtd/nand/Kconfig +++ b/drivers/mtd/nand/Kconfig @@ -556,6 +556,7 @@ config MTD_NAND_QCOM config MTD_NAND_MTK tristate "Support for NAND controller on MTK SoCs" + depends on ARCH_MEDIATEK || COMPILE_TEST depends on HAS_DMA help Enables support for NAND controller on MTK SoCs. -- cgit v1.2.3-59-g8ed1b From 0b2f93dc0099e3b8a739b8918eeb995e12520940 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 2 May 2017 12:29:13 +0200 Subject: mtd: nand: jz4780: Use mtd_set_ooblayout() to set the ooblayout The mtd_set_ooblayout() accesor has been added to hide internals of mtd_info and ease future refactoring. Call mtd_set_ooblayout() instead of directly accessing mtd->ooblayout. Signed-off-by: Boris Brezillon Acked-by: Harvey Hunt --- drivers/mtd/nand/jz4780_nand.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/nand/jz4780_nand.c b/drivers/mtd/nand/jz4780_nand.c index a39bb70175ee..8bc835f71b26 100644 --- a/drivers/mtd/nand/jz4780_nand.c +++ b/drivers/mtd/nand/jz4780_nand.c @@ -205,7 +205,7 @@ static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *de return -EINVAL; } - mtd->ooblayout = &nand_ooblayout_lp_ops; + mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops); return 0; } -- cgit v1.2.3-59-g8ed1b From 19d8ccc42b148d75284a3809f1eb1eba13a81677 Mon Sep 17 00:00:00 2001 From: Alexander Couzens Date: Tue, 2 May 2017 11:47:36 +0200 Subject: mtd: nand: davinci: set ECC algorithm explicitly for HW based ECC If ECC strength is 4bits/512bytes the algorithm of the ECC engine is BCH, otherwise (1bit/512bytes) Hamming is used. Signed-off-by: Alexander Couzens Signed-off-by: Boris Brezillon --- drivers/mtd/nand/davinci_nand.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/mtd/nand/davinci_nand.c b/drivers/mtd/nand/davinci_nand.c index 531c51991e57..7b26e53b95b1 100644 --- a/drivers/mtd/nand/davinci_nand.c +++ b/drivers/mtd/nand/davinci_nand.c @@ -771,11 +771,14 @@ static int nand_davinci_probe(struct platform_device *pdev) info->chip.ecc.hwctl = nand_davinci_hwctl_4bit; info->chip.ecc.bytes = 10; info->chip.ecc.options = NAND_ECC_GENERIC_ERASED_CHECK; + info->chip.ecc.algo = NAND_ECC_BCH; } else { + /* 1bit ecc hamming */ info->chip.ecc.calculate = nand_davinci_calculate_1bit; info->chip.ecc.correct = nand_davinci_correct_1bit; info->chip.ecc.hwctl = nand_davinci_hwctl_1bit; info->chip.ecc.bytes = 3; + info->chip.ecc.algo = NAND_ECC_HAMMING; } info->chip.ecc.size = 512; info->chip.ecc.strength = pdata->ecc_bits; -- cgit v1.2.3-59-g8ed1b From 6335b509b2b6fbe4cbeaef739434b40b8018df82 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Sat, 29 Apr 2017 10:52:34 +0200 Subject: mtd: nand: fsmc: reduce number of arguments of fsmc_nand_setup() In preparation for the introduction of support for using SDR timings exposed by the NAND flash instead of hard-coded timings, this commit reworks the fsmc_nand_setup() function to take a "struct fsmc_nand_data" as argument, which already contains the I/O registers base address, bank and bus width information. The timings is also currently contained in the "struct fsmc_nand_data", but we still pass it as a separate argument because the support for using SDR timings will pass a different value. Signed-off-by: Thomas Petazzoni Signed-off-by: Boris Brezillon --- drivers/mtd/nand/fsmc_nand.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) diff --git a/drivers/mtd/nand/fsmc_nand.c b/drivers/mtd/nand/fsmc_nand.c index cea50d2f218c..43108ddd7bdd 100644 --- a/drivers/mtd/nand/fsmc_nand.c +++ b/drivers/mtd/nand/fsmc_nand.c @@ -302,11 +302,13 @@ static void fsmc_cmd_ctrl(struct mtd_info *mtd, int cmd, unsigned int ctrl) * This routine initializes timing parameters related to NAND memory access in * FSMC registers */ -static void fsmc_nand_setup(void __iomem *regs, uint32_t bank, - uint32_t busw, struct fsmc_nand_timings *timings) +static void fsmc_nand_setup(struct fsmc_nand_data *host, + struct fsmc_nand_timings *timings) { uint32_t value = FSMC_DEVTYPE_NAND | FSMC_ENABLE | FSMC_WAITON; uint32_t tclr, tar, thiz, thold, twait, tset; + unsigned int bank = host->bank; + void __iomem *regs = host->regs_va; struct fsmc_nand_timings *tims; struct fsmc_nand_timings default_timings = { .tclr = FSMC_TCLR_1, @@ -318,7 +320,7 @@ static void fsmc_nand_setup(void __iomem *regs, uint32_t bank, }; if (timings) - tims = timings; + tims = host->dev_timings; else tims = &default_timings; @@ -329,7 +331,7 @@ static void fsmc_nand_setup(void __iomem *regs, uint32_t bank, twait = (tims->twait & FSMC_TWAIT_MASK) << FSMC_TWAIT_SHIFT; tset = (tims->tset & FSMC_TSET_MASK) << FSMC_TSET_SHIFT; - if (busw) + if (host->nand.options & NAND_BUSWIDTH_16) writel_relaxed(value | FSMC_DEVWID_16, FSMC_NAND_REG(regs, bank, PC)); else @@ -933,9 +935,7 @@ static int __init fsmc_nand_probe(struct platform_device *pdev) break; } - fsmc_nand_setup(host->regs_va, host->bank, - nand->options & NAND_BUSWIDTH_16, - host->dev_timings); + fsmc_nand_setup(host, host->dev_timings); if (AMBA_REV_BITS(host->pid) >= 8) { nand->ecc.read_page = fsmc_read_page_hwecc; @@ -1073,9 +1073,7 @@ static int fsmc_nand_resume(struct device *dev) struct fsmc_nand_data *host = dev_get_drvdata(dev); if (host) { clk_prepare_enable(host->clk); - fsmc_nand_setup(host->regs_va, host->bank, - host->nand.options & NAND_BUSWIDTH_16, - host->dev_timings); + fsmc_nand_setup(host, host->dev_timings); } return 0; } -- cgit v1.2.3-59-g8ed1b From d9fb0795718333e36f7e472d7d81b7b8efe347c8 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Sat, 29 Apr 2017 10:52:35 +0200 Subject: mtd: nand: fsmc: add support for SDR timings Until now, the fsmc_nand driver was either using controller timings specified in the Device Tree (through FSMC specific DT properties) or alternatively default/fallback timings. This commit implements support to use the timings advertised by the NAND chip itself, by implementing the ->setup_data_interface() hook. To preserve backward compatibility, if timings are specified in the Device Tree, we use the timings from the Device Tree (and don't implement ->setup_data_interface). Many thanks to Boris Brezillon for coming up with the logic to convert the NAND chip timings into the timings expected by the FSMC controller. Also, since the timings are now not only coming from the DT, the message warning that default timings will be used is removed. Signed-off-by: Thomas Petazzoni Signed-off-by: Boris Brezillon --- drivers/mtd/nand/fsmc_nand.c | 94 +++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 89 insertions(+), 5 deletions(-) diff --git a/drivers/mtd/nand/fsmc_nand.c b/drivers/mtd/nand/fsmc_nand.c index 43108ddd7bdd..442e4dff05ca 100644 --- a/drivers/mtd/nand/fsmc_nand.c +++ b/drivers/mtd/nand/fsmc_nand.c @@ -346,6 +346,88 @@ static void fsmc_nand_setup(struct fsmc_nand_data *host, FSMC_NAND_REG(regs, bank, ATTRIB)); } +static int fsmc_calc_timings(struct fsmc_nand_data *host, + const struct nand_sdr_timings *sdrt, + struct fsmc_nand_timings *tims) +{ + unsigned long hclk = clk_get_rate(host->clk); + unsigned long hclkn = NSEC_PER_SEC / hclk; + uint32_t thiz, thold, twait, tset; + + if (sdrt->tRC_min < 30000) + return -EOPNOTSUPP; + + tims->tar = DIV_ROUND_UP(sdrt->tAR_min / 1000, hclkn) - 1; + if (tims->tar > FSMC_TAR_MASK) + tims->tar = FSMC_TAR_MASK; + tims->tclr = DIV_ROUND_UP(sdrt->tCLR_min / 1000, hclkn) - 1; + if (tims->tclr > FSMC_TCLR_MASK) + tims->tclr = FSMC_TCLR_MASK; + + thiz = sdrt->tCS_min - sdrt->tWP_min; + tims->thiz = DIV_ROUND_UP(thiz / 1000, hclkn); + + thold = sdrt->tDH_min; + if (thold < sdrt->tCH_min) + thold = sdrt->tCH_min; + if (thold < sdrt->tCLH_min) + thold = sdrt->tCLH_min; + if (thold < sdrt->tWH_min) + thold = sdrt->tWH_min; + if (thold < sdrt->tALH_min) + thold = sdrt->tALH_min; + if (thold < sdrt->tREH_min) + thold = sdrt->tREH_min; + tims->thold = DIV_ROUND_UP(thold / 1000, hclkn); + if (tims->thold == 0) + tims->thold = 1; + else if (tims->thold > FSMC_THOLD_MASK) + tims->thold = FSMC_THOLD_MASK; + + twait = max(sdrt->tRP_min, sdrt->tWP_min); + tims->twait = DIV_ROUND_UP(twait / 1000, hclkn) - 1; + if (tims->twait == 0) + tims->twait = 1; + else if (tims->twait > FSMC_TWAIT_MASK) + tims->twait = FSMC_TWAIT_MASK; + + tset = max(sdrt->tCS_min - sdrt->tWP_min, + sdrt->tCEA_max - sdrt->tREA_max); + tims->tset = DIV_ROUND_UP(tset / 1000, hclkn) - 1; + if (tims->tset == 0) + tims->tset = 1; + else if (tims->tset > FSMC_TSET_MASK) + tims->tset = FSMC_TSET_MASK; + + return 0; +} + +static int fsmc_setup_data_interface(struct mtd_info *mtd, + const struct nand_data_interface *conf, + bool check_only) +{ + struct nand_chip *nand = mtd_to_nand(mtd); + struct fsmc_nand_data *host = nand_get_controller_data(nand); + struct fsmc_nand_timings tims; + const struct nand_sdr_timings *sdrt; + int ret; + + sdrt = nand_get_sdr_timings(conf); + if (IS_ERR(sdrt)) + return PTR_ERR(sdrt); + + ret = fsmc_calc_timings(host, sdrt, &tims); + if (ret) + return ret; + + if (check_only) + return 0; + + fsmc_nand_setup(host, &tims); + + return 0; +} + /* * fsmc_enable_hwecc - Enables Hardware ECC through FSMC registers */ @@ -798,10 +880,8 @@ static int fsmc_nand_probe_config_dt(struct platform_device *pdev, return -ENOMEM; ret = of_property_read_u8_array(np, "timings", (u8 *)host->dev_timings, sizeof(*host->dev_timings)); - if (ret) { - dev_info(&pdev->dev, "No timings in dts specified, using default timings!\n"); + if (ret) host->dev_timings = NULL; - } /* Set default NAND bank to 0 */ host->bank = 0; @@ -935,7 +1015,10 @@ static int __init fsmc_nand_probe(struct platform_device *pdev) break; } - fsmc_nand_setup(host, host->dev_timings); + if (host->dev_timings) + fsmc_nand_setup(host, host->dev_timings); + else + nand->setup_data_interface = fsmc_setup_data_interface; if (AMBA_REV_BITS(host->pid) >= 8) { nand->ecc.read_page = fsmc_read_page_hwecc; @@ -1073,7 +1156,8 @@ static int fsmc_nand_resume(struct device *dev) struct fsmc_nand_data *host = dev_get_drvdata(dev); if (host) { clk_prepare_enable(host->clk); - fsmc_nand_setup(host, host->dev_timings); + if (host->dev_timings) + fsmc_nand_setup(host, host->dev_timings); } return 0; } -- cgit v1.2.3-59-g8ed1b From 1debdb96643a3344e7c231d49e89d97078bc2c45 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Sat, 29 Apr 2017 10:52:36 +0200 Subject: mtd: nand: fsmc: remove default timings When timings are no longer provided by the Device Tree, we now use the SDR timings specified by the NAND flash, and such SDR timings are always provided. Therefore, it is no longer necessary to keep "default" timings in the fmsc driver. Signed-off-by: Thomas Petazzoni Signed-off-by: Boris Brezillon --- drivers/mtd/nand/fsmc_nand.c | 16 +--------------- 1 file changed, 1 insertion(+), 15 deletions(-) diff --git a/drivers/mtd/nand/fsmc_nand.c b/drivers/mtd/nand/fsmc_nand.c index 442e4dff05ca..f58c912fdf3b 100644 --- a/drivers/mtd/nand/fsmc_nand.c +++ b/drivers/mtd/nand/fsmc_nand.c @@ -303,26 +303,12 @@ static void fsmc_cmd_ctrl(struct mtd_info *mtd, int cmd, unsigned int ctrl) * FSMC registers */ static void fsmc_nand_setup(struct fsmc_nand_data *host, - struct fsmc_nand_timings *timings) + struct fsmc_nand_timings *tims) { uint32_t value = FSMC_DEVTYPE_NAND | FSMC_ENABLE | FSMC_WAITON; uint32_t tclr, tar, thiz, thold, twait, tset; unsigned int bank = host->bank; void __iomem *regs = host->regs_va; - struct fsmc_nand_timings *tims; - struct fsmc_nand_timings default_timings = { - .tclr = FSMC_TCLR_1, - .tar = FSMC_TAR_1, - .thiz = FSMC_THIZ_1, - .thold = FSMC_THOLD_4, - .twait = FSMC_TWAIT_6, - .tset = FSMC_TSET_0, - }; - - if (timings) - tims = host->dev_timings; - else - tims = &default_timings; tclr = (tims->tclr & FSMC_TCLR_MASK) << FSMC_TCLR_SHIFT; tar = (tims->tar & FSMC_TAR_MASK) << FSMC_TAR_SHIFT; -- cgit v1.2.3-59-g8ed1b From 85f94b5ef0eede10e7071f9e7e5b864ffad96d72 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Sat, 29 Apr 2017 11:06:42 +0200 Subject: dt-bindings: mtd: document new "on-die" nand-ecc-mode A number of NAND chips support a feature called on-die ECC, where the NAND chip itself is capable of doing error detection and correction. The new "on-die" value for nand-ecc-mode indicates that we want this functionality to be used. Signed-off-by: Thomas Petazzoni Acked-by: Rob Herring Reviewed-by: Richard Weinberger Signed-off-by: Boris Brezillon --- Documentation/devicetree/bindings/mtd/nand.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/mtd/nand.txt b/Documentation/devicetree/bindings/mtd/nand.txt index b05601600083..133f3813719c 100644 --- a/Documentation/devicetree/bindings/mtd/nand.txt +++ b/Documentation/devicetree/bindings/mtd/nand.txt @@ -21,7 +21,7 @@ Optional NAND chip properties: - nand-ecc-mode : String, operation mode of the NAND ecc mode. Supported values are: "none", "soft", "hw", "hw_syndrome", - "hw_oob_first". + "hw_oob_first", "on-die". Deprecated values: "soft_bch": use "soft" and nand-ecc-algo instead - nand-ecc-algo: string, algorithm of NAND ECC. -- cgit v1.2.3-59-g8ed1b From 785818fa8385fe55dab253e42a4c6728fca61333 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Sat, 29 Apr 2017 11:06:43 +0200 Subject: mtd: nand: add core support for on-die ECC A number of NAND flashes have a capability called "on-die ECC" where the NAND chip itself is capable of detecting and correcting errors. Linux already has support for using the ECC implementation of the NAND controller, or a software based ECC implementation, but not for using the ECC implementation of the NAND controller. However, such an implementation is sometimes useful in situations where the NAND controller provides ECC algorithms that are not strong enough for the NAND chip used on the system. A typical case is a NAND chip that requires a 4-bit ECC, while the NAND controller only provides a 1-bit ECC algorithm. This commit introduces the support for the NAND_ECC_ON_DIE ECC mode: - Parsing of the "on-die" value for the "nand-ecc-mode" Device Tree property - Handling NAND_ECC_ON_DIE case in nand_scan_tail(). The idea is that the vendor specific code for the NAND chip must implement ->read_page() and ->write_page(). It may optionally provide its own ->read_page_raw() and ->write_page_raw() as well. For OOB operation, we assume the standard operations are good enough, but they can be overridden by the vendor specific code if needed. Signed-off-by: Thomas Petazzoni Reviewed-by: Richard Weinberger Signed-off-by: Boris Brezillon --- drivers/mtd/nand/nand_base.c | 13 +++++++++++++ include/linux/mtd/nand.h | 1 + 2 files changed, 14 insertions(+) diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index d474378ed810..f49aecd3f1de 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -4177,6 +4177,7 @@ static const char * const nand_ecc_modes[] = { [NAND_ECC_HW] = "hw", [NAND_ECC_HW_SYNDROME] = "hw_syndrome", [NAND_ECC_HW_OOB_FIRST] = "hw_oob_first", + [NAND_ECC_ON_DIE] = "on-die", }; static int of_get_nand_ecc_mode(struct device_node *np) @@ -4717,6 +4718,18 @@ int nand_scan_tail(struct mtd_info *mtd) } break; + case NAND_ECC_ON_DIE: + if (!ecc->read_page || !ecc->write_page) { + WARN(1, "No ECC functions supplied; on-die ECC not possible\n"); + ret = -EINVAL; + goto err_free; + } + if (!ecc->read_oob) + ecc->read_oob = nand_read_oob_std; + if (!ecc->write_oob) + ecc->write_oob = nand_write_oob_std; + break; + case NAND_ECC_NONE: pr_warn("NAND_ECC_NONE selected by board driver. This is not recommended!\n"); ecc->read_page = nand_read_page_raw; diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 8f67b1581683..603522097ec9 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -116,6 +116,7 @@ typedef enum { NAND_ECC_HW, NAND_ECC_HW_SYNDROME, NAND_ECC_HW_OOB_FIRST, + NAND_ECC_ON_DIE, } nand_ecc_modes_t; enum nand_ecc_algo { -- cgit v1.2.3-59-g8ed1b From cc0f51ec111266f5d255e753bf3254ad411d5c12 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Sat, 29 Apr 2017 11:06:44 +0200 Subject: mtd: nand: export nand_{read,write}_page_raw() The nand_read_page_raw() and nand_write_page_raw() functions might be re-used by vendor-specific implementations of the read_page/write_page functions. Instead of having vendor-specific code duplicate this code, it is much better to export those functions and allow them to be re-used. Signed-off-by: Thomas Petazzoni Reviewed-by: Richard Weinberger Signed-off-by: Boris Brezillon --- drivers/mtd/nand/nand_base.c | 10 ++++++---- include/linux/mtd/nand.h | 8 ++++++++ 2 files changed, 14 insertions(+), 4 deletions(-) diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index f49aecd3f1de..0b3b1a88091a 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -1524,14 +1524,15 @@ EXPORT_SYMBOL(nand_check_erased_ecc_chunk); * * Not for syndrome calculating ECC controllers, which use a special oob layout. */ -static int nand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, - uint8_t *buf, int oob_required, int page) +int nand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, + uint8_t *buf, int oob_required, int page) { chip->read_buf(mtd, buf, mtd->writesize); if (oob_required) chip->read_buf(mtd, chip->oob_poi, mtd->oobsize); return 0; } +EXPORT_SYMBOL(nand_read_page_raw); /** * nand_read_page_raw_syndrome - [INTERN] read raw page data without ecc @@ -2469,8 +2470,8 @@ static int nand_read_oob(struct mtd_info *mtd, loff_t from, * * Not for syndrome calculating ECC controllers, which use a special oob layout. */ -static int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip, - const uint8_t *buf, int oob_required, int page) +int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip, + const uint8_t *buf, int oob_required, int page) { chip->write_buf(mtd, buf, mtd->writesize); if (oob_required) @@ -2478,6 +2479,7 @@ static int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip, return 0; } +EXPORT_SYMBOL(nand_write_page_raw); /** * nand_write_page_raw_syndrome - [INTERN] raw page write function diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 603522097ec9..7a01d2eb7443 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -1259,6 +1259,14 @@ int nand_read_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page); int nand_read_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip, int page); +/* Default read_page_raw implementation */ +int nand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, + uint8_t *buf, int oob_required, int page); + +/* Default write_page_raw implementation */ +int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip, + const uint8_t *buf, int oob_required, int page); + /* Reset and initialize a NAND device */ int nand_reset(struct nand_chip *chip, int chipnr); -- cgit v1.2.3-59-g8ed1b From c512f36b581862df20acef050c3e1a875166bd6f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 09:31:19 +0200 Subject: sunrpc: properly type argument to kxdreproc_t Pass struct rpc_request as the first argument instead of an untyped blob, and mark the data object as const. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton --- include/linux/sunrpc/xdr.h | 5 ++++- net/sunrpc/clnt.c | 3 ++- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 054c8cde18f3..290f189de200 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -17,6 +17,8 @@ #include #include +struct rpc_rqst; + /* * Buffer adjustment */ @@ -222,7 +224,8 @@ struct xdr_stream { /* * These are the xdr_stream style generic XDR encode and decode functions. */ -typedef void (*kxdreproc_t)(void *rqstp, struct xdr_stream *xdr, void *obj); +typedef void (*kxdreproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + const void *obj); typedef int (*kxdrdproc_t)(void *rqstp, struct xdr_stream *xdr, void *obj); extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index b5cb921775a0..9fee20dc0c80 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2476,7 +2476,8 @@ out_overflow: goto out_garbage; } -static void rpcproc_encode_null(void *rqstp, struct xdr_stream *xdr, void *obj) +static void rpcproc_encode_null(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + const void *obj) { } -- cgit v1.2.3-59-g8ed1b From 7d55f7febab6af865630ccb3a0fac9a144c459df Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 09:59:45 +0200 Subject: sunrpc: fix encoder callback prototypes Declare the p_encode callbacks with the proper prototype instead of casting to kxdreproc_t and losing all type safety. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton Acked-by: Trond Myklebust --- net/sunrpc/rpcb_clnt.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 5b30603596d0..d0269a39afdf 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -843,8 +843,9 @@ static void rpcb_getport_done(struct rpc_task *child, void *data) */ static void rpcb_enc_mapping(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct rpcbind_args *rpcb) + const void *data) { + const struct rpcbind_args *rpcb = data; __be32 *p; dprintk("RPC: %5u encoding PMAP_%s call (%u, %u, %d, %u)\n", @@ -917,8 +918,9 @@ static void encode_rpcb_string(struct xdr_stream *xdr, const char *string, } static void rpcb_enc_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct rpcbind_args *rpcb) + const void *data) { + const struct rpcbind_args *rpcb = data; __be32 *p; dprintk("RPC: %5u encoding RPCB_%s call (%u, %u, '%s', '%s')\n", @@ -992,7 +994,7 @@ out_fail: static struct rpc_procinfo rpcb_procedures2[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, - .p_encode = (kxdreproc_t)rpcb_enc_mapping, + .p_encode = rpcb_enc_mapping, .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_setres_sz, @@ -1002,7 +1004,7 @@ static struct rpc_procinfo rpcb_procedures2[] = { }, [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, - .p_encode = (kxdreproc_t)rpcb_enc_mapping, + .p_encode = rpcb_enc_mapping, .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_setres_sz, @@ -1012,7 +1014,7 @@ static struct rpc_procinfo rpcb_procedures2[] = { }, [RPCBPROC_GETPORT] = { .p_proc = RPCBPROC_GETPORT, - .p_encode = (kxdreproc_t)rpcb_enc_mapping, + .p_encode = rpcb_enc_mapping, .p_decode = (kxdrdproc_t)rpcb_dec_getport, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_getportres_sz, @@ -1025,7 +1027,7 @@ static struct rpc_procinfo rpcb_procedures2[] = { static struct rpc_procinfo rpcb_procedures3[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, - .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_encode = rpcb_enc_getaddr, .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, @@ -1035,7 +1037,7 @@ static struct rpc_procinfo rpcb_procedures3[] = { }, [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, - .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_encode = rpcb_enc_getaddr, .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, @@ -1045,7 +1047,7 @@ static struct rpc_procinfo rpcb_procedures3[] = { }, [RPCBPROC_GETADDR] = { .p_proc = RPCBPROC_GETADDR, - .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_encode = rpcb_enc_getaddr, .p_decode = (kxdrdproc_t)rpcb_dec_getaddr, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_getaddrres_sz, @@ -1058,7 +1060,7 @@ static struct rpc_procinfo rpcb_procedures3[] = { static struct rpc_procinfo rpcb_procedures4[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, - .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_encode = rpcb_enc_getaddr, .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, @@ -1068,7 +1070,7 @@ static struct rpc_procinfo rpcb_procedures4[] = { }, [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, - .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_encode = rpcb_enc_getaddr, .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, @@ -1078,7 +1080,7 @@ static struct rpc_procinfo rpcb_procedures4[] = { }, [RPCBPROC_GETADDR] = { .p_proc = RPCBPROC_GETADDR, - .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_encode = rpcb_enc_getaddr, .p_decode = (kxdrdproc_t)rpcb_dec_getaddr, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_getaddrres_sz, -- cgit v1.2.3-59-g8ed1b From bf96391e7b59a994c8aa72f5c425e3897ee799fa Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 09:34:04 +0200 Subject: lockd: fix encoder callback prototypes Declare the p_encode callbacks with the proper prototype instead of casting to kxdreproc_t and losing all type safety. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton Acked-by: Trond Myklebust --- fs/lockd/clnt4xdr.c | 22 +++++++++++++++------- fs/lockd/clntxdr.c | 22 +++++++++++++++------- fs/lockd/mon.c | 8 ++++---- 3 files changed, 34 insertions(+), 18 deletions(-) diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c index d3e40db28930..3cbad662120a 100644 --- a/fs/lockd/clnt4xdr.c +++ b/fs/lockd/clnt4xdr.c @@ -381,8 +381,9 @@ static void encode_nlm4_lock(struct xdr_stream *xdr, */ static void nlm4_xdr_enc_testargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -402,8 +403,9 @@ static void nlm4_xdr_enc_testargs(struct rpc_rqst *req, */ static void nlm4_xdr_enc_lockargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -424,8 +426,9 @@ static void nlm4_xdr_enc_lockargs(struct rpc_rqst *req, */ static void nlm4_xdr_enc_cancargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -442,8 +445,9 @@ static void nlm4_xdr_enc_cancargs(struct rpc_rqst *req, */ static void nlm4_xdr_enc_unlockargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -458,8 +462,10 @@ static void nlm4_xdr_enc_unlockargs(struct rpc_rqst *req, */ static void nlm4_xdr_enc_res(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_res *result) + const void *data) { + const struct nlm_res *result = data; + encode_cookie(xdr, &result->cookie); encode_nlm4_stat(xdr, result->status); } @@ -479,8 +485,10 @@ static void nlm4_xdr_enc_res(struct rpc_rqst *req, */ static void nlm4_xdr_enc_testres(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_res *result) + const void *data) { + const struct nlm_res *result = data; + encode_cookie(xdr, &result->cookie); encode_nlm4_stat(xdr, result->status); if (result->status == nlm_lck_denied) @@ -566,7 +574,7 @@ out: #define PROC(proc, argtype, restype) \ [NLMPROC_##proc] = { \ .p_proc = NLMPROC_##proc, \ - .p_encode = (kxdreproc_t)nlm4_xdr_enc_##argtype, \ + .p_encode = nlm4_xdr_enc_##argtype, \ .p_decode = (kxdrdproc_t)nlm4_xdr_dec_##restype, \ .p_arglen = NLM4_##argtype##_sz, \ .p_replen = NLM4_##restype##_sz, \ diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c index 3e9f7874b975..825c0fde8c80 100644 --- a/fs/lockd/clntxdr.c +++ b/fs/lockd/clntxdr.c @@ -374,8 +374,9 @@ static void encode_nlm_lock(struct xdr_stream *xdr, */ static void nlm_xdr_enc_testargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -395,8 +396,9 @@ static void nlm_xdr_enc_testargs(struct rpc_rqst *req, */ static void nlm_xdr_enc_lockargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -417,8 +419,9 @@ static void nlm_xdr_enc_lockargs(struct rpc_rqst *req, */ static void nlm_xdr_enc_cancargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -435,8 +438,9 @@ static void nlm_xdr_enc_cancargs(struct rpc_rqst *req, */ static void nlm_xdr_enc_unlockargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -451,8 +455,10 @@ static void nlm_xdr_enc_unlockargs(struct rpc_rqst *req, */ static void nlm_xdr_enc_res(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_res *result) + const void *data) { + const struct nlm_res *result = data; + encode_cookie(xdr, &result->cookie); encode_nlm_stat(xdr, result->status); } @@ -479,8 +485,10 @@ static void encode_nlm_testrply(struct xdr_stream *xdr, static void nlm_xdr_enc_testres(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_res *result) + const void *data) { + const struct nlm_res *result = data; + encode_cookie(xdr, &result->cookie); encode_nlm_stat(xdr, result->status); encode_nlm_testrply(xdr, result); @@ -564,7 +572,7 @@ out: #define PROC(proc, argtype, restype) \ [NLMPROC_##proc] = { \ .p_proc = NLMPROC_##proc, \ - .p_encode = (kxdreproc_t)nlm_xdr_enc_##argtype, \ + .p_encode = nlm_xdr_enc_##argtype, \ .p_decode = (kxdrdproc_t)nlm_xdr_dec_##restype, \ .p_arglen = NLM_##argtype##_sz, \ .p_replen = NLM_##restype##_sz, \ diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 19166d4a8d31..8043fd4b8a5c 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -476,14 +476,14 @@ static void encode_priv(struct xdr_stream *xdr, const struct nsm_args *argp) } static void nsm_xdr_enc_mon(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nsm_args *argp) + const void *argp) { encode_mon_id(xdr, argp); encode_priv(xdr, argp); } static void nsm_xdr_enc_unmon(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nsm_args *argp) + const void *argp) { encode_mon_id(xdr, argp); } @@ -532,7 +532,7 @@ static int nsm_xdr_dec_stat(struct rpc_rqst *rqstp, static struct rpc_procinfo nsm_procedures[] = { [NSMPROC_MON] = { .p_proc = NSMPROC_MON, - .p_encode = (kxdreproc_t)nsm_xdr_enc_mon, + .p_encode = nsm_xdr_enc_mon, .p_decode = (kxdrdproc_t)nsm_xdr_dec_stat_res, .p_arglen = SM_mon_sz, .p_replen = SM_monres_sz, @@ -541,7 +541,7 @@ static struct rpc_procinfo nsm_procedures[] = { }, [NSMPROC_UNMON] = { .p_proc = NSMPROC_UNMON, - .p_encode = (kxdreproc_t)nsm_xdr_enc_unmon, + .p_encode = nsm_xdr_enc_unmon, .p_decode = (kxdrdproc_t)nsm_xdr_dec_stat, .p_arglen = SM_mon_id_sz, .p_replen = SM_unmonres_sz, -- cgit v1.2.3-59-g8ed1b From 0096d39b9632706ca65a759a7024aef6b7833c6d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 10:01:49 +0200 Subject: nfs: fix encoder callback prototypes Declare the p_encode callbacks with the proper prototype instead of casting to kxdreproc_t and losing all type safety. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton Acked-by: Trond Myklebust --- fs/nfs/mount_clnt.c | 10 +-- fs/nfs/nfs2xdr.c | 49 ++++++++++---- fs/nfs/nfs3xdr.c | 83 ++++++++++++++++------- fs/nfs/nfs42xdr.c | 34 ++++++---- fs/nfs/nfs4xdr.c | 188 +++++++++++++++++++++++++++++++++------------------- 5 files changed, 242 insertions(+), 122 deletions(-) diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index 09b190015df4..f435d640d552 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -304,7 +304,7 @@ static void encode_mntdirpath(struct xdr_stream *xdr, const char *pathname) } static void mnt_xdr_enc_dirpath(struct rpc_rqst *req, struct xdr_stream *xdr, - const char *dirpath) + const void *dirpath) { encode_mntdirpath(xdr, dirpath); } @@ -467,7 +467,7 @@ static int mnt_xdr_dec_mountres3(struct rpc_rqst *req, static struct rpc_procinfo mnt_procedures[] = { [MOUNTPROC_MNT] = { .p_proc = MOUNTPROC_MNT, - .p_encode = (kxdreproc_t)mnt_xdr_enc_dirpath, + .p_encode = mnt_xdr_enc_dirpath, .p_decode = (kxdrdproc_t)mnt_xdr_dec_mountres, .p_arglen = MNT_enc_dirpath_sz, .p_replen = MNT_dec_mountres_sz, @@ -476,7 +476,7 @@ static struct rpc_procinfo mnt_procedures[] = { }, [MOUNTPROC_UMNT] = { .p_proc = MOUNTPROC_UMNT, - .p_encode = (kxdreproc_t)mnt_xdr_enc_dirpath, + .p_encode = mnt_xdr_enc_dirpath, .p_arglen = MNT_enc_dirpath_sz, .p_statidx = MOUNTPROC_UMNT, .p_name = "UMOUNT", @@ -486,7 +486,7 @@ static struct rpc_procinfo mnt_procedures[] = { static struct rpc_procinfo mnt3_procedures[] = { [MOUNTPROC3_MNT] = { .p_proc = MOUNTPROC3_MNT, - .p_encode = (kxdreproc_t)mnt_xdr_enc_dirpath, + .p_encode = mnt_xdr_enc_dirpath, .p_decode = (kxdrdproc_t)mnt_xdr_dec_mountres3, .p_arglen = MNT_enc_dirpath_sz, .p_replen = MNT_dec_mountres3_sz, @@ -495,7 +495,7 @@ static struct rpc_procinfo mnt3_procedures[] = { }, [MOUNTPROC3_UMNT] = { .p_proc = MOUNTPROC3_UMNT, - .p_encode = (kxdreproc_t)mnt_xdr_enc_dirpath, + .p_encode = mnt_xdr_enc_dirpath, .p_arglen = MNT_enc_dirpath_sz, .p_statidx = MOUNTPROC3_UMNT, .p_name = "UMOUNT", diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index b4e03ed8599d..8ecd58597228 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -568,8 +568,10 @@ out_default: static void nfs2_xdr_enc_fhandle(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_fh *fh) + const void *data) { + const struct nfs_fh *fh = data; + encode_fhandle(xdr, fh); } @@ -583,23 +585,29 @@ static void nfs2_xdr_enc_fhandle(struct rpc_rqst *req, */ static void nfs2_xdr_enc_sattrargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_sattrargs *args) + const void *data) { + const struct nfs_sattrargs *args = data; + encode_fhandle(xdr, args->fh); encode_sattr(xdr, args->sattr); } static void nfs2_xdr_enc_diropargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_diropargs *args) + const void *data) { + const struct nfs_diropargs *args = data; + encode_diropargs(xdr, args->fh, args->name, args->len); } static void nfs2_xdr_enc_readlinkargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_readlinkargs *args) + const void *data) { + const struct nfs_readlinkargs *args = data; + encode_fhandle(xdr, args->fh); prepare_reply_buffer(req, args->pages, args->pgbase, args->pglen, NFS_readlinkres_sz); @@ -632,8 +640,10 @@ static void encode_readargs(struct xdr_stream *xdr, static void nfs2_xdr_enc_readargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_pgio_args *args) + const void *data) { + const struct nfs_pgio_args *args = data; + encode_readargs(xdr, args); prepare_reply_buffer(req, args->pages, args->pgbase, args->count, NFS_readres_sz); @@ -672,8 +682,10 @@ static void encode_writeargs(struct xdr_stream *xdr, static void nfs2_xdr_enc_writeargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_pgio_args *args) + const void *data) { + const struct nfs_pgio_args *args = data; + encode_writeargs(xdr, args); xdr->buf->flags |= XDRBUF_WRITE; } @@ -688,16 +700,20 @@ static void nfs2_xdr_enc_writeargs(struct rpc_rqst *req, */ static void nfs2_xdr_enc_createargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_createargs *args) + const void *data) { + const struct nfs_createargs *args = data; + encode_diropargs(xdr, args->fh, args->name, args->len); encode_sattr(xdr, args->sattr); } static void nfs2_xdr_enc_removeargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_removeargs *args) + const void *data) { + const struct nfs_removeargs *args = data; + encode_diropargs(xdr, args->fh, args->name.name, args->name.len); } @@ -711,8 +727,9 @@ static void nfs2_xdr_enc_removeargs(struct rpc_rqst *req, */ static void nfs2_xdr_enc_renameargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_renameargs *args) + const void *data) { + const struct nfs_renameargs *args = data; const struct qstr *old = args->old_name; const struct qstr *new = args->new_name; @@ -730,8 +747,10 @@ static void nfs2_xdr_enc_renameargs(struct rpc_rqst *req, */ static void nfs2_xdr_enc_linkargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_linkargs *args) + const void *data) { + const struct nfs_linkargs *args = data; + encode_fhandle(xdr, args->fromfh); encode_diropargs(xdr, args->tofh, args->toname, args->tolen); } @@ -747,8 +766,10 @@ static void nfs2_xdr_enc_linkargs(struct rpc_rqst *req, */ static void nfs2_xdr_enc_symlinkargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_symlinkargs *args) + const void *data) { + const struct nfs_symlinkargs *args = data; + encode_diropargs(xdr, args->fromfh, args->fromname, args->fromlen); encode_path(xdr, args->pages, args->pathlen); encode_sattr(xdr, args->sattr); @@ -777,8 +798,10 @@ static void encode_readdirargs(struct xdr_stream *xdr, static void nfs2_xdr_enc_readdirargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_readdirargs *args) + const void *data) { + const struct nfs_readdirargs *args = data; + encode_readdirargs(xdr, args); prepare_reply_buffer(req, args->pages, 0, args->count, NFS_readdirres_sz); @@ -1118,7 +1141,7 @@ static int nfs_stat_to_errno(enum nfs_stat status) #define PROC(proc, argtype, restype, timer) \ [NFSPROC_##proc] = { \ .p_proc = NFSPROC_##proc, \ - .p_encode = (kxdreproc_t)nfs2_xdr_enc_##argtype, \ + .p_encode = nfs2_xdr_enc_##argtype, \ .p_decode = (kxdrdproc_t)nfs2_xdr_dec_##restype, \ .p_arglen = NFS_##argtype##_sz, \ .p_replen = NFS_##restype##_sz, \ diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 267126d32ec0..773150678633 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -846,8 +846,10 @@ static void encode_diropargs3(struct xdr_stream *xdr, const struct nfs_fh *fh, */ static void nfs3_xdr_enc_getattr3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_fh *fh) + const void *data) { + const struct nfs_fh *fh = data; + encode_nfs_fh3(xdr, fh); } @@ -884,8 +886,9 @@ static void encode_sattrguard3(struct xdr_stream *xdr, static void nfs3_xdr_enc_setattr3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_sattrargs *args) + const void *data) { + const struct nfs3_sattrargs *args = data; encode_nfs_fh3(xdr, args->fh); encode_sattr3(xdr, args->sattr); encode_sattrguard3(xdr, args); @@ -900,8 +903,10 @@ static void nfs3_xdr_enc_setattr3args(struct rpc_rqst *req, */ static void nfs3_xdr_enc_lookup3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_diropargs *args) + const void *data) { + const struct nfs3_diropargs *args = data; + encode_diropargs3(xdr, args->fh, args->name, args->len); } @@ -922,8 +927,10 @@ static void encode_access3args(struct xdr_stream *xdr, static void nfs3_xdr_enc_access3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_accessargs *args) + const void *data) { + const struct nfs3_accessargs *args = data; + encode_access3args(xdr, args); } @@ -936,8 +943,10 @@ static void nfs3_xdr_enc_access3args(struct rpc_rqst *req, */ static void nfs3_xdr_enc_readlink3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_readlinkargs *args) + const void *data) { + const struct nfs3_readlinkargs *args = data; + encode_nfs_fh3(xdr, args->fh); prepare_reply_buffer(req, args->pages, args->pgbase, args->pglen, NFS3_readlinkres_sz); @@ -966,8 +975,10 @@ static void encode_read3args(struct xdr_stream *xdr, static void nfs3_xdr_enc_read3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_pgio_args *args) + const void *data) { + const struct nfs_pgio_args *args = data; + encode_read3args(xdr, args); prepare_reply_buffer(req, args->pages, args->pgbase, args->count, NFS3_readres_sz); @@ -1008,8 +1019,10 @@ static void encode_write3args(struct xdr_stream *xdr, static void nfs3_xdr_enc_write3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_pgio_args *args) + const void *data) { + const struct nfs_pgio_args *args = data; + encode_write3args(xdr, args); xdr->buf->flags |= XDRBUF_WRITE; } @@ -1055,8 +1068,10 @@ static void encode_createhow3(struct xdr_stream *xdr, static void nfs3_xdr_enc_create3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_createargs *args) + const void *data) { + const struct nfs3_createargs *args = data; + encode_diropargs3(xdr, args->fh, args->name, args->len); encode_createhow3(xdr, args); } @@ -1071,8 +1086,10 @@ static void nfs3_xdr_enc_create3args(struct rpc_rqst *req, */ static void nfs3_xdr_enc_mkdir3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_mkdirargs *args) + const void *data) { + const struct nfs3_mkdirargs *args = data; + encode_diropargs3(xdr, args->fh, args->name, args->len); encode_sattr3(xdr, args->sattr); } @@ -1091,16 +1108,20 @@ static void nfs3_xdr_enc_mkdir3args(struct rpc_rqst *req, * }; */ static void encode_symlinkdata3(struct xdr_stream *xdr, - const struct nfs3_symlinkargs *args) + const void *data) { + const struct nfs3_symlinkargs *args = data; + encode_sattr3(xdr, args->sattr); encode_nfspath3(xdr, args->pages, args->pathlen); } static void nfs3_xdr_enc_symlink3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_symlinkargs *args) + const void *data) { + const struct nfs3_symlinkargs *args = data; + encode_diropargs3(xdr, args->fromfh, args->fromname, args->fromlen); encode_symlinkdata3(xdr, args); xdr->buf->flags |= XDRBUF_WRITE; @@ -1160,8 +1181,10 @@ static void encode_mknoddata3(struct xdr_stream *xdr, static void nfs3_xdr_enc_mknod3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_mknodargs *args) + const void *data) { + const struct nfs3_mknodargs *args = data; + encode_diropargs3(xdr, args->fh, args->name, args->len); encode_mknoddata3(xdr, args); } @@ -1175,8 +1198,10 @@ static void nfs3_xdr_enc_mknod3args(struct rpc_rqst *req, */ static void nfs3_xdr_enc_remove3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_removeargs *args) + const void *data) { + const struct nfs_removeargs *args = data; + encode_diropargs3(xdr, args->fh, args->name.name, args->name.len); } @@ -1190,8 +1215,9 @@ static void nfs3_xdr_enc_remove3args(struct rpc_rqst *req, */ static void nfs3_xdr_enc_rename3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_renameargs *args) + const void *data) { + const struct nfs_renameargs *args = data; const struct qstr *old = args->old_name; const struct qstr *new = args->new_name; @@ -1209,8 +1235,10 @@ static void nfs3_xdr_enc_rename3args(struct rpc_rqst *req, */ static void nfs3_xdr_enc_link3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_linkargs *args) + const void *data) { + const struct nfs3_linkargs *args = data; + encode_nfs_fh3(xdr, args->fromfh); encode_diropargs3(xdr, args->tofh, args->toname, args->tolen); } @@ -1240,8 +1268,10 @@ static void encode_readdir3args(struct xdr_stream *xdr, static void nfs3_xdr_enc_readdir3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_readdirargs *args) + const void *data) { + const struct nfs3_readdirargs *args = data; + encode_readdir3args(xdr, args); prepare_reply_buffer(req, args->pages, 0, args->count, NFS3_readdirres_sz); @@ -1280,8 +1310,10 @@ static void encode_readdirplus3args(struct xdr_stream *xdr, static void nfs3_xdr_enc_readdirplus3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_readdirargs *args) + const void *data) { + const struct nfs3_readdirargs *args = data; + encode_readdirplus3args(xdr, args); prepare_reply_buffer(req, args->pages, 0, args->count, NFS3_readdirres_sz); @@ -1310,8 +1342,10 @@ static void encode_commit3args(struct xdr_stream *xdr, static void nfs3_xdr_enc_commit3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_commitargs *args) + const void *data) { + const struct nfs_commitargs *args = data; + encode_commit3args(xdr, args); } @@ -1319,8 +1353,10 @@ static void nfs3_xdr_enc_commit3args(struct rpc_rqst *req, static void nfs3_xdr_enc_getacl3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_getaclargs *args) + const void *data) { + const struct nfs3_getaclargs *args = data; + encode_nfs_fh3(xdr, args->fh); encode_uint32(xdr, args->mask); if (args->mask & (NFS_ACL | NFS_DFACL)) @@ -1331,8 +1367,9 @@ static void nfs3_xdr_enc_getacl3args(struct rpc_rqst *req, static void nfs3_xdr_enc_setacl3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_setaclargs *args) + const void *data) { + const struct nfs3_setaclargs *args = data; unsigned int base; int error; @@ -2495,7 +2532,7 @@ static int nfs3_stat_to_errno(enum nfs_stat status) #define PROC(proc, argtype, restype, timer) \ [NFS3PROC_##proc] = { \ .p_proc = NFS3PROC_##proc, \ - .p_encode = (kxdreproc_t)nfs3_xdr_enc_##argtype##3args, \ + .p_encode = nfs3_xdr_enc_##argtype##3args, \ .p_decode = (kxdrdproc_t)nfs3_xdr_dec_##restype##3res, \ .p_arglen = NFS3_##argtype##args_sz, \ .p_replen = NFS3_##restype##res_sz, \ @@ -2538,7 +2575,7 @@ const struct rpc_version nfs_version3 = { static struct rpc_procinfo nfs3_acl_procedures[] = { [ACLPROC3_GETACL] = { .p_proc = ACLPROC3_GETACL, - .p_encode = (kxdreproc_t)nfs3_xdr_enc_getacl3args, + .p_encode = nfs3_xdr_enc_getacl3args, .p_decode = (kxdrdproc_t)nfs3_xdr_dec_getacl3res, .p_arglen = ACL3_getaclargs_sz, .p_replen = ACL3_getaclres_sz, @@ -2547,7 +2584,7 @@ static struct rpc_procinfo nfs3_acl_procedures[] = { }, [ACLPROC3_SETACL] = { .p_proc = ACLPROC3_SETACL, - .p_encode = (kxdreproc_t)nfs3_xdr_enc_setacl3args, + .p_encode = nfs3_xdr_enc_setacl3args, .p_decode = (kxdrdproc_t)nfs3_xdr_dec_setacl3res, .p_arglen = ACL3_setaclargs_sz, .p_replen = ACL3_setaclres_sz, diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index 528362f69cc1..0a1bd60a1f8e 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -112,7 +112,7 @@ decode_getattr_maxsz) static void encode_fallocate(struct xdr_stream *xdr, - struct nfs42_falloc_args *args) + const struct nfs42_falloc_args *args) { encode_nfs4_stateid(xdr, &args->falloc_stateid); encode_uint64(xdr, args->falloc_offset); @@ -120,7 +120,7 @@ static void encode_fallocate(struct xdr_stream *xdr, } static void encode_allocate(struct xdr_stream *xdr, - struct nfs42_falloc_args *args, + const struct nfs42_falloc_args *args, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_ALLOCATE, decode_allocate_maxsz, hdr); @@ -128,7 +128,7 @@ static void encode_allocate(struct xdr_stream *xdr, } static void encode_copy(struct xdr_stream *xdr, - struct nfs42_copy_args *args, + const struct nfs42_copy_args *args, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_COPY, decode_copy_maxsz, hdr); @@ -145,7 +145,7 @@ static void encode_copy(struct xdr_stream *xdr, } static void encode_deallocate(struct xdr_stream *xdr, - struct nfs42_falloc_args *args, + const struct nfs42_falloc_args *args, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_DEALLOCATE, decode_deallocate_maxsz, hdr); @@ -153,7 +153,7 @@ static void encode_deallocate(struct xdr_stream *xdr, } static void encode_seek(struct xdr_stream *xdr, - struct nfs42_seek_args *args, + const struct nfs42_seek_args *args, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_SEEK, decode_seek_maxsz, hdr); @@ -163,7 +163,7 @@ static void encode_seek(struct xdr_stream *xdr, } static void encode_layoutstats(struct xdr_stream *xdr, - struct nfs42_layoutstat_args *args, + const struct nfs42_layoutstat_args *args, struct nfs42_layoutstat_devinfo *devinfo, struct compound_hdr *hdr) { @@ -191,7 +191,7 @@ static void encode_layoutstats(struct xdr_stream *xdr, } static void encode_clone(struct xdr_stream *xdr, - struct nfs42_clone_args *args, + const struct nfs42_clone_args *args, struct compound_hdr *hdr) { __be32 *p; @@ -210,8 +210,9 @@ static void encode_clone(struct xdr_stream *xdr, */ static void nfs4_xdr_enc_allocate(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs42_falloc_args *args) + const void *data) { + const struct nfs42_falloc_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -225,7 +226,7 @@ static void nfs4_xdr_enc_allocate(struct rpc_rqst *req, } static void encode_copy_commit(struct xdr_stream *xdr, - struct nfs42_copy_args *args, + const struct nfs42_copy_args *args, struct compound_hdr *hdr) { __be32 *p; @@ -241,8 +242,9 @@ static void encode_copy_commit(struct xdr_stream *xdr, */ static void nfs4_xdr_enc_copy(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs42_copy_args *args) + const void *data) { + const struct nfs42_copy_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -262,8 +264,9 @@ static void nfs4_xdr_enc_copy(struct rpc_rqst *req, */ static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs42_falloc_args *args) + const void *data) { + const struct nfs42_falloc_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -281,8 +284,9 @@ static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req, */ static void nfs4_xdr_enc_seek(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs42_seek_args *args) + const void *data) { + const struct nfs42_seek_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -299,8 +303,9 @@ static void nfs4_xdr_enc_seek(struct rpc_rqst *req, */ static void nfs4_xdr_enc_layoutstats(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs42_layoutstat_args *args) + const void *data) { + const struct nfs42_layoutstat_args *args = data; int i; struct compound_hdr hdr = { @@ -321,8 +326,9 @@ static void nfs4_xdr_enc_layoutstats(struct rpc_rqst *req, */ static void nfs4_xdr_enc_clone(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs42_clone_args *args) + const void *data) { + const struct nfs42_clone_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 3aebfdc82b30..c5036ef770f9 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1651,7 +1651,8 @@ encode_restorefh(struct xdr_stream *xdr, struct compound_hdr *hdr) } static void -encode_setacl(struct xdr_stream *xdr, struct nfs_setaclargs *arg, struct compound_hdr *hdr) +encode_setacl(struct xdr_stream *xdr, const struct nfs_setaclargs *arg, + struct compound_hdr *hdr) { __be32 *p; @@ -1735,7 +1736,7 @@ static void encode_secinfo(struct xdr_stream *xdr, const struct qstr *name, stru #if defined(CONFIG_NFS_V4_1) /* NFSv4.1 operations */ static void encode_bind_conn_to_session(struct xdr_stream *xdr, - struct nfs41_bind_conn_to_session_args *args, + const struct nfs41_bind_conn_to_session_args *args, struct compound_hdr *hdr) { __be32 *p; @@ -1748,7 +1749,7 @@ static void encode_bind_conn_to_session(struct xdr_stream *xdr, *p = (args->use_conn_in_rdma_mode) ? cpu_to_be32(1) : cpu_to_be32(0); } -static void encode_op_map(struct xdr_stream *xdr, struct nfs4_op_map *op_map) +static void encode_op_map(struct xdr_stream *xdr, const struct nfs4_op_map *op_map) { unsigned int i; encode_uint32(xdr, NFS4_OP_MAP_NUM_WORDS); @@ -1757,7 +1758,7 @@ static void encode_op_map(struct xdr_stream *xdr, struct nfs4_op_map *op_map) } static void encode_exchange_id(struct xdr_stream *xdr, - struct nfs41_exchange_id_args *args, + const struct nfs41_exchange_id_args *args, struct compound_hdr *hdr) { __be32 *p; @@ -1809,7 +1810,7 @@ static void encode_exchange_id(struct xdr_stream *xdr, } static void encode_create_session(struct xdr_stream *xdr, - struct nfs41_create_session_args *args, + const struct nfs41_create_session_args *args, struct compound_hdr *hdr) { __be32 *p; @@ -1862,7 +1863,7 @@ static void encode_create_session(struct xdr_stream *xdr, } static void encode_destroy_session(struct xdr_stream *xdr, - struct nfs4_session *session, + const struct nfs4_session *session, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_DESTROY_SESSION, decode_destroy_session_maxsz, hdr); @@ -1878,7 +1879,7 @@ static void encode_destroy_clientid(struct xdr_stream *xdr, } static void encode_reclaim_complete(struct xdr_stream *xdr, - struct nfs41_reclaim_complete_args *args, + const struct nfs41_reclaim_complete_args *args, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_RECLAIM_COMPLETE, decode_reclaim_complete_maxsz, hdr); @@ -1974,7 +1975,7 @@ encode_layoutget(struct xdr_stream *xdr, static int encode_layoutcommit(struct xdr_stream *xdr, struct inode *inode, - struct nfs4_layoutcommit_args *args, + const struct nfs4_layoutcommit_args *args, struct compound_hdr *hdr) { __be32 *p; @@ -2044,7 +2045,7 @@ encode_secinfo_no_name(struct xdr_stream *xdr, } static void encode_test_stateid(struct xdr_stream *xdr, - struct nfs41_test_stateid_args *args, + const struct nfs41_test_stateid_args *args, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_TEST_STATEID, decode_test_stateid_maxsz, hdr); @@ -2053,7 +2054,7 @@ static void encode_test_stateid(struct xdr_stream *xdr, } static void encode_free_stateid(struct xdr_stream *xdr, - struct nfs41_free_stateid_args *args, + const struct nfs41_free_stateid_args *args, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_FREE_STATEID, decode_free_stateid_maxsz, hdr); @@ -2086,8 +2087,9 @@ static u32 nfs4_xdr_minorversion(const struct nfs4_sequence_args *args) * Encode an ACCESS request */ static void nfs4_xdr_enc_access(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_accessargs *args) + const void *data) { + const struct nfs4_accessargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2104,8 +2106,9 @@ static void nfs4_xdr_enc_access(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode LOOKUP request */ static void nfs4_xdr_enc_lookup(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_lookup_arg *args) + const void *data) { + const struct nfs4_lookup_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2124,8 +2127,9 @@ static void nfs4_xdr_enc_lookup(struct rpc_rqst *req, struct xdr_stream *xdr, */ static void nfs4_xdr_enc_lookup_root(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_lookup_root_arg *args) + const void *data) { + const struct nfs4_lookup_root_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2142,8 +2146,9 @@ static void nfs4_xdr_enc_lookup_root(struct rpc_rqst *req, * Encode REMOVE request */ static void nfs4_xdr_enc_remove(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_removeargs *args) + const void *data) { + const struct nfs_removeargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2159,8 +2164,9 @@ static void nfs4_xdr_enc_remove(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode RENAME request */ static void nfs4_xdr_enc_rename(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_renameargs *args) + const void *data) { + const struct nfs_renameargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2178,8 +2184,9 @@ static void nfs4_xdr_enc_rename(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode LINK request */ static void nfs4_xdr_enc_link(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_link_arg *args) + const void *data) { + const struct nfs4_link_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2199,8 +2206,9 @@ static void nfs4_xdr_enc_link(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode CREATE request */ static void nfs4_xdr_enc_create(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_create_arg *args) + const void *data) { + const struct nfs4_create_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2218,8 +2226,10 @@ static void nfs4_xdr_enc_create(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode SYMLINK request */ static void nfs4_xdr_enc_symlink(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_create_arg *args) + const void *data) { + const struct nfs4_create_arg *args = data; + nfs4_xdr_enc_create(req, xdr, args); } @@ -2227,8 +2237,9 @@ static void nfs4_xdr_enc_symlink(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode GETATTR request */ static void nfs4_xdr_enc_getattr(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_getattr_arg *args) + const void *data) { + const struct nfs4_getattr_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2244,8 +2255,9 @@ static void nfs4_xdr_enc_getattr(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode a CLOSE request */ static void nfs4_xdr_enc_close(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_closeargs *args) + const void *data) { + const struct nfs_closeargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2265,8 +2277,9 @@ static void nfs4_xdr_enc_close(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode an OPEN request */ static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_openargs *args) + const void *data) { + const struct nfs_openargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2287,8 +2300,9 @@ static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr, */ static void nfs4_xdr_enc_open_confirm(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_open_confirmargs *args) + const void *data) { + const struct nfs_open_confirmargs *args = data; struct compound_hdr hdr = { .nops = 0, }; @@ -2304,8 +2318,9 @@ static void nfs4_xdr_enc_open_confirm(struct rpc_rqst *req, */ static void nfs4_xdr_enc_open_noattr(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_openargs *args) + const void *data) { + const struct nfs_openargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2325,8 +2340,9 @@ static void nfs4_xdr_enc_open_noattr(struct rpc_rqst *req, */ static void nfs4_xdr_enc_open_downgrade(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_closeargs *args) + const void *data) { + const struct nfs_closeargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2344,8 +2360,9 @@ static void nfs4_xdr_enc_open_downgrade(struct rpc_rqst *req, * Encode a LOCK request */ static void nfs4_xdr_enc_lock(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_lock_args *args) + const void *data) { + const struct nfs_lock_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2361,8 +2378,9 @@ static void nfs4_xdr_enc_lock(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode a LOCKT request */ static void nfs4_xdr_enc_lockt(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_lockt_args *args) + const void *data) { + const struct nfs_lockt_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2378,8 +2396,9 @@ static void nfs4_xdr_enc_lockt(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode a LOCKU request */ static void nfs4_xdr_enc_locku(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_locku_args *args) + const void *data) { + const struct nfs_locku_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2393,8 +2412,9 @@ static void nfs4_xdr_enc_locku(struct rpc_rqst *req, struct xdr_stream *xdr, static void nfs4_xdr_enc_release_lockowner(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_release_lockowner_args *args) + const void *data) { + const struct nfs_release_lockowner_args *args = data; struct compound_hdr hdr = { .minorversion = 0, }; @@ -2408,8 +2428,9 @@ static void nfs4_xdr_enc_release_lockowner(struct rpc_rqst *req, * Encode a READLINK request */ static void nfs4_xdr_enc_readlink(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_readlink *args) + const void *data) { + const struct nfs4_readlink *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2428,8 +2449,9 @@ static void nfs4_xdr_enc_readlink(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode a READDIR request */ static void nfs4_xdr_enc_readdir(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_readdir_arg *args) + const void *data) { + const struct nfs4_readdir_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2451,8 +2473,9 @@ static void nfs4_xdr_enc_readdir(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode a READ request */ static void nfs4_xdr_enc_read(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_pgio_args *args) + const void *data) { + const struct nfs_pgio_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2472,8 +2495,9 @@ static void nfs4_xdr_enc_read(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode an SETATTR request */ static void nfs4_xdr_enc_setattr(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_setattrargs *args) + const void *data) { + const struct nfs_setattrargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2490,8 +2514,9 @@ static void nfs4_xdr_enc_setattr(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode a GETACL request */ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_getaclargs *args) + const void *data) { + const struct nfs_getaclargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2513,8 +2538,9 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode a WRITE request */ static void nfs4_xdr_enc_write(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_pgio_args *args) + const void *data) { + const struct nfs_pgio_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2533,8 +2559,9 @@ static void nfs4_xdr_enc_write(struct rpc_rqst *req, struct xdr_stream *xdr, * a COMMIT request */ static void nfs4_xdr_enc_commit(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_commitargs *args) + const void *data) { + const struct nfs_commitargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2550,8 +2577,9 @@ static void nfs4_xdr_enc_commit(struct rpc_rqst *req, struct xdr_stream *xdr, * FSINFO request */ static void nfs4_xdr_enc_fsinfo(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_fsinfo_arg *args) + const void *data) { + const struct nfs4_fsinfo_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2567,8 +2595,9 @@ static void nfs4_xdr_enc_fsinfo(struct rpc_rqst *req, struct xdr_stream *xdr, * a PATHCONF request */ static void nfs4_xdr_enc_pathconf(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_pathconf_arg *args) + const void *data) { + const struct nfs4_pathconf_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2585,8 +2614,9 @@ static void nfs4_xdr_enc_pathconf(struct rpc_rqst *req, struct xdr_stream *xdr, * a STATFS request */ static void nfs4_xdr_enc_statfs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_statfs_arg *args) + const void *data) { + const struct nfs4_statfs_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2604,8 +2634,9 @@ static void nfs4_xdr_enc_statfs(struct rpc_rqst *req, struct xdr_stream *xdr, */ static void nfs4_xdr_enc_server_caps(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_server_caps_arg *args) + const void *data) { + const struct nfs4_server_caps_arg *args = data; const u32 *bitmask = args->bitmask; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), @@ -2622,8 +2653,10 @@ static void nfs4_xdr_enc_server_caps(struct rpc_rqst *req, * a RENEW request */ static void nfs4_xdr_enc_renew(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_client *clp) + const void *data) + { + const struct nfs_client *clp = data; struct compound_hdr hdr = { .nops = 0, }; @@ -2638,8 +2671,9 @@ static void nfs4_xdr_enc_renew(struct rpc_rqst *req, struct xdr_stream *xdr, */ static void nfs4_xdr_enc_setclientid(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_setclientid *sc) + const void *data) { + const struct nfs4_setclientid *sc = data; struct compound_hdr hdr = { .nops = 0, }; @@ -2654,8 +2688,9 @@ static void nfs4_xdr_enc_setclientid(struct rpc_rqst *req, */ static void nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_setclientid_res *arg) + const void *data) { + const struct nfs4_setclientid_res *arg = data; struct compound_hdr hdr = { .nops = 0, }; @@ -2670,8 +2705,9 @@ static void nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req, */ static void nfs4_xdr_enc_delegreturn(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_delegreturnargs *args) + const void *data) { + const struct nfs4_delegreturnargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2692,8 +2728,9 @@ static void nfs4_xdr_enc_delegreturn(struct rpc_rqst *req, */ static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_fs_locations_arg *args) + const void *data) { + const struct nfs4_fs_locations_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2715,8 +2752,8 @@ static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req, } /* Set up reply kvec to capture returned fs_locations array. */ - xdr_inline_pages(&req->rq_rcv_buf, replen << 2, &args->page, - 0, PAGE_SIZE); + xdr_inline_pages(&req->rq_rcv_buf, replen << 2, + (struct page **)&args->page, 0, PAGE_SIZE); encode_nops(&hdr); } @@ -2725,8 +2762,9 @@ static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req, */ static void nfs4_xdr_enc_secinfo(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_secinfo_arg *args) + const void *data) { + const struct nfs4_secinfo_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2743,8 +2781,9 @@ static void nfs4_xdr_enc_secinfo(struct rpc_rqst *req, */ static void nfs4_xdr_enc_fsid_present(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_fsid_present_arg *args) + const void *data) { + const struct nfs4_fsid_present_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2764,8 +2803,9 @@ static void nfs4_xdr_enc_fsid_present(struct rpc_rqst *req, */ static void nfs4_xdr_enc_bind_conn_to_session(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs41_bind_conn_to_session_args *args) + const void *data) { + const struct nfs41_bind_conn_to_session_args *args = data; struct compound_hdr hdr = { .minorversion = args->client->cl_mvops->minor_version, }; @@ -2780,8 +2820,9 @@ static void nfs4_xdr_enc_bind_conn_to_session(struct rpc_rqst *req, */ static void nfs4_xdr_enc_exchange_id(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs41_exchange_id_args *args) + const void *data) { + const struct nfs41_exchange_id_args *args = data; struct compound_hdr hdr = { .minorversion = args->client->cl_mvops->minor_version, }; @@ -2796,8 +2837,9 @@ static void nfs4_xdr_enc_exchange_id(struct rpc_rqst *req, */ static void nfs4_xdr_enc_create_session(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs41_create_session_args *args) + const void *data) { + const struct nfs41_create_session_args *args = data; struct compound_hdr hdr = { .minorversion = args->client->cl_mvops->minor_version, }; @@ -2812,8 +2854,9 @@ static void nfs4_xdr_enc_create_session(struct rpc_rqst *req, */ static void nfs4_xdr_enc_destroy_session(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_session *session) + const void *data) { + const struct nfs4_session *session = data; struct compound_hdr hdr = { .minorversion = session->clp->cl_mvops->minor_version, }; @@ -2828,8 +2871,9 @@ static void nfs4_xdr_enc_destroy_session(struct rpc_rqst *req, */ static void nfs4_xdr_enc_destroy_clientid(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_client *clp) + const void *data) { + const struct nfs_client *clp = data; struct compound_hdr hdr = { .minorversion = clp->cl_mvops->minor_version, }; @@ -2843,8 +2887,9 @@ static void nfs4_xdr_enc_destroy_clientid(struct rpc_rqst *req, * a SEQUENCE request */ static void nfs4_xdr_enc_sequence(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_sequence_args *args) + const void *data) { + const struct nfs4_sequence_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(args), }; @@ -2859,8 +2904,9 @@ static void nfs4_xdr_enc_sequence(struct rpc_rqst *req, struct xdr_stream *xdr, */ static void nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_get_lease_time_args *args) + const void *data) { + const struct nfs4_get_lease_time_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->la_seq_args), }; @@ -2878,8 +2924,9 @@ static void nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req, */ static void nfs4_xdr_enc_reclaim_complete(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs41_reclaim_complete_args *args) + const void *data) { + const struct nfs41_reclaim_complete_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args) }; @@ -2895,8 +2942,9 @@ static void nfs4_xdr_enc_reclaim_complete(struct rpc_rqst *req, */ static void nfs4_xdr_enc_getdeviceinfo(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_getdeviceinfo_args *args) + const void *data) { + const struct nfs4_getdeviceinfo_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2919,8 +2967,9 @@ static void nfs4_xdr_enc_getdeviceinfo(struct rpc_rqst *req, */ static void nfs4_xdr_enc_layoutget(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_layoutget_args *args) + const void *data) { + const struct nfs4_layoutget_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2941,8 +2990,9 @@ static void nfs4_xdr_enc_layoutget(struct rpc_rqst *req, */ static void nfs4_xdr_enc_layoutcommit(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_layoutcommit_args *args) + const void *priv) { + const struct nfs4_layoutcommit_args *args = priv; struct nfs4_layoutcommit_data *data = container_of(args, struct nfs4_layoutcommit_data, args); struct compound_hdr hdr = { @@ -2962,8 +3012,9 @@ static void nfs4_xdr_enc_layoutcommit(struct rpc_rqst *req, */ static void nfs4_xdr_enc_layoutreturn(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_layoutreturn_args *args) + const void *data) { + const struct nfs4_layoutreturn_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2978,10 +3029,11 @@ static void nfs4_xdr_enc_layoutreturn(struct rpc_rqst *req, /* * Encode SECINFO_NO_NAME request */ -static int nfs4_xdr_enc_secinfo_no_name(struct rpc_rqst *req, +static void nfs4_xdr_enc_secinfo_no_name(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs41_secinfo_no_name_args *args) + const void *data) { + const struct nfs41_secinfo_no_name_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2991,7 +3043,6 @@ static int nfs4_xdr_enc_secinfo_no_name(struct rpc_rqst *req, encode_putrootfh(xdr, &hdr); encode_secinfo_no_name(xdr, args, &hdr); encode_nops(&hdr); - return 0; } /* @@ -2999,8 +3050,9 @@ static int nfs4_xdr_enc_secinfo_no_name(struct rpc_rqst *req, */ static void nfs4_xdr_enc_test_stateid(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs41_test_stateid_args *args) + const void *data) { + const struct nfs41_test_stateid_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -3016,8 +3068,9 @@ static void nfs4_xdr_enc_test_stateid(struct rpc_rqst *req, */ static void nfs4_xdr_enc_free_stateid(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs41_free_stateid_args *args) + const void *data) { + const struct nfs41_free_stateid_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -6364,8 +6417,9 @@ out: * Encode an SETACL request */ static void nfs4_xdr_enc_setacl(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_setaclargs *args) + const void *data) { + const struct nfs_setaclargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -7484,7 +7538,7 @@ nfs4_stat_to_errno(int stat) #define PROC(proc, argtype, restype) \ [NFSPROC4_CLNT_##proc] = { \ .p_proc = NFSPROC4_COMPOUND, \ - .p_encode = (kxdreproc_t)nfs4_xdr_##argtype, \ + .p_encode = nfs4_xdr_##argtype, \ .p_decode = (kxdrdproc_t)nfs4_xdr_##restype, \ .p_arglen = NFS4_##argtype##_sz, \ .p_replen = NFS4_##restype##_sz, \ -- cgit v1.2.3-59-g8ed1b From 1502c81b443d70f2e3009aef96428ffa94e2e29d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 14:47:53 +0200 Subject: nfsd: fix encoder callback prototypes Declare the p_encode callbacks with the proper prototype instead of casting to kxdreproc_t and losing all type safety. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton --- fs/nfsd/nfs4callback.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 0274db6e65d0..bede418237ee 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -468,7 +468,7 @@ static int decode_cb_sequence4res(struct xdr_stream *xdr, * NB: Without this zero space reservation, callbacks over krb5p fail */ static void nfs4_xdr_enc_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr, - void *__unused) + const void *__unused) { xdr_reserve_space(xdr, 0); } @@ -477,8 +477,9 @@ static void nfs4_xdr_enc_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr, * 20.2. Operation 4: CB_RECALL - Recall a Delegation */ static void nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfsd4_callback *cb) + const void *data) { + const struct nfsd4_callback *cb = data; const struct nfs4_delegation *dp = cb_to_delegation(cb); struct nfs4_cb_compound_hdr hdr = { .ident = cb->cb_clp->cl_cb_ident, @@ -585,8 +586,9 @@ static void encode_cb_layout4args(struct xdr_stream *xdr, static void nfs4_xdr_enc_cb_layout(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfsd4_callback *cb) + const void *data) { + const struct nfsd4_callback *cb = data; const struct nfs4_layout_stateid *ls = container_of(cb, struct nfs4_layout_stateid, ls_recall); struct nfs4_cb_compound_hdr hdr = { @@ -631,8 +633,9 @@ static void encode_stateowner(struct xdr_stream *xdr, struct nfs4_stateowner *so static void nfs4_xdr_enc_cb_notify_lock(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfsd4_callback *cb) + const void *data) { + const struct nfsd4_callback *cb = data; const struct nfsd4_blocked_lock *nbl = container_of(cb, struct nfsd4_blocked_lock, nbl_cb); struct nfs4_lockowner *lo = (struct nfs4_lockowner *)nbl->nbl_lock.fl_owner; @@ -682,7 +685,7 @@ static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp, #define PROC(proc, call, argtype, restype) \ [NFSPROC4_CLNT_##proc] = { \ .p_proc = NFSPROC4_CB_##call, \ - .p_encode = (kxdreproc_t)nfs4_xdr_enc_##argtype, \ + .p_encode = nfs4_xdr_enc_##argtype, \ .p_decode = (kxdrdproc_t)nfs4_xdr_dec_##restype, \ .p_arglen = NFS4_enc_##argtype##_sz, \ .p_replen = NFS4_dec_##restype##_sz, \ -- cgit v1.2.3-59-g8ed1b From 89daf3602310b46ddf1bea4873be737d8781fc39 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 14:54:06 +0200 Subject: sunrpc/auth_gss: nfsd: fix encoder callback prototypes Declare the p_encode callbacks with the proper prototype instead of casting to kxdreproc_t and losing all type safety. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton Acked-by: Trond Myklebust --- net/sunrpc/auth_gss/gss_rpc_upcall.c | 2 +- net/sunrpc/auth_gss/gss_rpc_xdr.c | 11 ++++++----- net/sunrpc/auth_gss/gss_rpc_xdr.h | 2 +- 3 files changed, 8 insertions(+), 7 deletions(-) diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index f0c6a8c78a56..45ab924da726 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -55,7 +55,7 @@ enum { #define PROC(proc, name) \ [GSSX_##proc] = { \ .p_proc = GSSX_##proc, \ - .p_encode = (kxdreproc_t)gssx_enc_##name, \ + .p_encode = gssx_enc_##name, \ .p_decode = (kxdrdproc_t)gssx_dec_##name, \ .p_arglen = GSSX_ARG_##name##_sz, \ .p_replen = GSSX_RES_##name##_sz, \ diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c index 25d9a9cf7b66..5e54f4743092 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.c +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c @@ -44,7 +44,7 @@ static int gssx_dec_bool(struct xdr_stream *xdr, u32 *v) } static int gssx_enc_buffer(struct xdr_stream *xdr, - gssx_buffer *buf) + const gssx_buffer *buf) { __be32 *p; @@ -56,7 +56,7 @@ static int gssx_enc_buffer(struct xdr_stream *xdr, } static int gssx_enc_in_token(struct xdr_stream *xdr, - struct gssp_in_token *in) + const struct gssp_in_token *in) { __be32 *p; @@ -130,7 +130,7 @@ static int gssx_dec_option(struct xdr_stream *xdr, } static int dummy_enc_opt_array(struct xdr_stream *xdr, - struct gssx_option_array *oa) + const struct gssx_option_array *oa) { __be32 *p; @@ -348,7 +348,7 @@ static int gssx_dec_status(struct xdr_stream *xdr, } static int gssx_enc_call_ctx(struct xdr_stream *xdr, - struct gssx_call_ctx *ctx) + const struct gssx_call_ctx *ctx) { struct gssx_option opt; __be32 *p; @@ -733,8 +733,9 @@ static int gssx_enc_cb(struct xdr_stream *xdr, struct gssx_cb *cb) void gssx_enc_accept_sec_context(struct rpc_rqst *req, struct xdr_stream *xdr, - struct gssx_arg_accept_sec_context *arg) + const void *data) { + const struct gssx_arg_accept_sec_context *arg = data; int err; err = gssx_enc_call_ctx(xdr, &arg->call_ctx); diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.h b/net/sunrpc/auth_gss/gss_rpc_xdr.h index 9d88c6239f01..87cd719ca0ad 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.h +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.h @@ -179,7 +179,7 @@ struct gssx_res_accept_sec_context { #define gssx_dec_init_sec_context NULL void gssx_enc_accept_sec_context(struct rpc_rqst *req, struct xdr_stream *xdr, - struct gssx_arg_accept_sec_context *args); + const void *data); int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp, struct xdr_stream *xdr, struct gssx_res_accept_sec_context *res); -- cgit v1.2.3-59-g8ed1b From 73c8dc133afb0cbe72a9234894ea72c2a0e71a73 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 14:58:11 +0200 Subject: sunrpc: properly type argument to kxdrdproc_t Pass struct rpc_request as the first argument instead of an untyped blob. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton Acked-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 3 ++- net/sunrpc/clnt.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 290f189de200..ed0fbf0d8d0f 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -226,7 +226,8 @@ struct xdr_stream { */ typedef void (*kxdreproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr, const void *obj); -typedef int (*kxdrdproc_t)(void *rqstp, struct xdr_stream *xdr, void *obj); +typedef int (*kxdrdproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + void *obj); extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p); extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 9fee20dc0c80..964d5c4a1b60 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2481,7 +2481,8 @@ static void rpcproc_encode_null(struct rpc_rqst *rqstp, struct xdr_stream *xdr, { } -static int rpcproc_decode_null(void *rqstp, struct xdr_stream *xdr, void *obj) +static int rpcproc_decode_null(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + void *obj) { return 0; } -- cgit v1.2.3-59-g8ed1b From 605d712fa89f16ed5266897ecda01dd1a74b8aa8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 15:00:29 +0200 Subject: sunrpc: fix decoder callback prototypes Declare the p_decode callbacks with the proper prototype instead of casting to kxdrdproc_t and losing all type safety. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton --- net/sunrpc/rpcb_clnt.c | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-) diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index d0269a39afdf..f67b9e2897b4 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -861,8 +861,9 @@ static void rpcb_enc_mapping(struct rpc_rqst *req, struct xdr_stream *xdr, } static int rpcb_dec_getport(struct rpc_rqst *req, struct xdr_stream *xdr, - struct rpcbind_args *rpcb) + void *data) { + struct rpcbind_args *rpcb = data; unsigned long port; __be32 *p; @@ -883,8 +884,9 @@ static int rpcb_dec_getport(struct rpc_rqst *req, struct xdr_stream *xdr, } static int rpcb_dec_set(struct rpc_rqst *req, struct xdr_stream *xdr, - unsigned int *boolp) + void *data) { + unsigned int *boolp = data; __be32 *p; p = xdr_inline_decode(xdr, 4); @@ -939,8 +941,9 @@ static void rpcb_enc_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr, } static int rpcb_dec_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr, - struct rpcbind_args *rpcb) + void *data) { + struct rpcbind_args *rpcb = data; struct sockaddr_storage address; struct sockaddr *sap = (struct sockaddr *)&address; __be32 *p; @@ -995,7 +998,7 @@ static struct rpc_procinfo rpcb_procedures2[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, .p_encode = rpcb_enc_mapping, - .p_decode = (kxdrdproc_t)rpcb_dec_set, + .p_decode = rpcb_dec_set, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_SET, @@ -1005,7 +1008,7 @@ static struct rpc_procinfo rpcb_procedures2[] = { [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, .p_encode = rpcb_enc_mapping, - .p_decode = (kxdrdproc_t)rpcb_dec_set, + .p_decode = rpcb_dec_set, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_UNSET, @@ -1015,7 +1018,7 @@ static struct rpc_procinfo rpcb_procedures2[] = { [RPCBPROC_GETPORT] = { .p_proc = RPCBPROC_GETPORT, .p_encode = rpcb_enc_mapping, - .p_decode = (kxdrdproc_t)rpcb_dec_getport, + .p_decode = rpcb_dec_getport, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_getportres_sz, .p_statidx = RPCBPROC_GETPORT, @@ -1028,7 +1031,7 @@ static struct rpc_procinfo rpcb_procedures3[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, .p_encode = rpcb_enc_getaddr, - .p_decode = (kxdrdproc_t)rpcb_dec_set, + .p_decode = rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_SET, @@ -1038,7 +1041,7 @@ static struct rpc_procinfo rpcb_procedures3[] = { [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, .p_encode = rpcb_enc_getaddr, - .p_decode = (kxdrdproc_t)rpcb_dec_set, + .p_decode = rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_UNSET, @@ -1048,7 +1051,7 @@ static struct rpc_procinfo rpcb_procedures3[] = { [RPCBPROC_GETADDR] = { .p_proc = RPCBPROC_GETADDR, .p_encode = rpcb_enc_getaddr, - .p_decode = (kxdrdproc_t)rpcb_dec_getaddr, + .p_decode = rpcb_dec_getaddr, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_getaddrres_sz, .p_statidx = RPCBPROC_GETADDR, @@ -1061,7 +1064,7 @@ static struct rpc_procinfo rpcb_procedures4[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, .p_encode = rpcb_enc_getaddr, - .p_decode = (kxdrdproc_t)rpcb_dec_set, + .p_decode = rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_SET, @@ -1071,7 +1074,7 @@ static struct rpc_procinfo rpcb_procedures4[] = { [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, .p_encode = rpcb_enc_getaddr, - .p_decode = (kxdrdproc_t)rpcb_dec_set, + .p_decode = rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_UNSET, @@ -1081,7 +1084,7 @@ static struct rpc_procinfo rpcb_procedures4[] = { [RPCBPROC_GETADDR] = { .p_proc = RPCBPROC_GETADDR, .p_encode = rpcb_enc_getaddr, - .p_decode = (kxdrdproc_t)rpcb_dec_getaddr, + .p_decode = rpcb_dec_getaddr, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_getaddrres_sz, .p_statidx = RPCBPROC_GETADDR, -- cgit v1.2.3-59-g8ed1b From 305c62417f2e5ff9e784ff7b52e493368373e2d7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 15:03:02 +0200 Subject: sunrpc/auth_gss: fix decoder callback prototypes Declare the p_decode callbacks with the proper prototype instead of casting to kxdrdproc_t and losing all type safety. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton Acked-by: Trond Myklebust --- net/sunrpc/auth_gss/gss_rpc_upcall.c | 2 +- net/sunrpc/auth_gss/gss_rpc_xdr.c | 3 ++- net/sunrpc/auth_gss/gss_rpc_xdr.h | 2 +- 3 files changed, 4 insertions(+), 3 deletions(-) diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index 45ab924da726..a80b8e607478 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -56,7 +56,7 @@ enum { [GSSX_##proc] = { \ .p_proc = GSSX_##proc, \ .p_encode = gssx_enc_##name, \ - .p_decode = (kxdrdproc_t)gssx_dec_##name, \ + .p_decode = gssx_dec_##name, \ .p_arglen = GSSX_ARG_##name##_sz, \ .p_replen = GSSX_RES_##name##_sz, \ .p_statidx = GSSX_##proc, \ diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c index 5e54f4743092..c4778cae58ef 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.c +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c @@ -790,8 +790,9 @@ done: int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct gssx_res_accept_sec_context *res) + void *data) { + struct gssx_res_accept_sec_context *res = data; u32 value_follows; int err; struct page *scratch; diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.h b/net/sunrpc/auth_gss/gss_rpc_xdr.h index 87cd719ca0ad..146c31032917 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.h +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.h @@ -182,7 +182,7 @@ void gssx_enc_accept_sec_context(struct rpc_rqst *req, const void *data); int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct gssx_res_accept_sec_context *res); + void *data); #define gssx_enc_release_handle NULL #define gssx_dec_release_handle NULL #define gssx_enc_get_mic NULL -- cgit v1.2.3-59-g8ed1b From d39916c48771597a3213758b6dc508b6b82083e4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 15:04:45 +0200 Subject: nfsd: fix decoder callback prototypes Declare the p_decode callbacks with the proper prototype instead of casting to kxdrdproc_t and losing all type safety. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton --- fs/nfsd/nfs4callback.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index bede418237ee..a2bedbd05b2b 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -513,8 +513,9 @@ static int nfs4_xdr_dec_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr, */ static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfsd4_callback *cb) + void *data) { + struct nfsd4_callback *cb = data; struct nfs4_cb_compound_hdr hdr; int status; @@ -604,8 +605,9 @@ static void nfs4_xdr_enc_cb_layout(struct rpc_rqst *req, static int nfs4_xdr_dec_cb_layout(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfsd4_callback *cb) + void *data) { + struct nfsd4_callback *cb = data; struct nfs4_cb_compound_hdr hdr; int status; @@ -662,8 +664,9 @@ static void nfs4_xdr_enc_cb_notify_lock(struct rpc_rqst *req, static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfsd4_callback *cb) + void *data) { + struct nfsd4_callback *cb = data; struct nfs4_cb_compound_hdr hdr; int status; @@ -686,7 +689,7 @@ static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp, [NFSPROC4_CLNT_##proc] = { \ .p_proc = NFSPROC4_CB_##call, \ .p_encode = nfs4_xdr_enc_##argtype, \ - .p_decode = (kxdrdproc_t)nfs4_xdr_dec_##restype, \ + .p_decode = nfs4_xdr_dec_##restype, \ .p_arglen = NFS4_enc_##argtype##_sz, \ .p_replen = NFS4_dec_##restype##_sz, \ .p_statidx = NFSPROC4_CB_##call, \ -- cgit v1.2.3-59-g8ed1b From 1fa2339123f596d0c7608670d9052805a90e92ca Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 15:06:20 +0200 Subject: lockd: fix decoder callback prototypes Declare the p_decode callbacks with the proper prototype instead of casting to kxdrdproc_t and losing all type safety. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton Acked-by: Trond Myklebust --- fs/lockd/clnt4xdr.c | 8 +++++--- fs/lockd/clntxdr.c | 8 +++++--- fs/lockd/mon.c | 10 ++++++---- 3 files changed, 16 insertions(+), 10 deletions(-) diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c index 3cbad662120a..f0ab7a99dd23 100644 --- a/fs/lockd/clnt4xdr.c +++ b/fs/lockd/clnt4xdr.c @@ -533,8 +533,9 @@ out: static int nlm4_xdr_dec_testres(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nlm_res *result) + void *data) { + struct nlm_res *result = data; int error; error = decode_cookie(xdr, &result->cookie); @@ -553,8 +554,9 @@ out: */ static int nlm4_xdr_dec_res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nlm_res *result) + void *data) { + struct nlm_res *result = data; int error; error = decode_cookie(xdr, &result->cookie); @@ -575,7 +577,7 @@ out: [NLMPROC_##proc] = { \ .p_proc = NLMPROC_##proc, \ .p_encode = nlm4_xdr_enc_##argtype, \ - .p_decode = (kxdrdproc_t)nlm4_xdr_dec_##restype, \ + .p_decode = nlm4_xdr_dec_##restype, \ .p_arglen = NLM4_##argtype##_sz, \ .p_replen = NLM4_##restype##_sz, \ .p_statidx = NLMPROC_##proc, \ diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c index 825c0fde8c80..17e7f08b3a22 100644 --- a/fs/lockd/clntxdr.c +++ b/fs/lockd/clntxdr.c @@ -531,8 +531,9 @@ out: static int nlm_xdr_dec_testres(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nlm_res *result) + void *data) { + struct nlm_res *result = data; int error; error = decode_cookie(xdr, &result->cookie); @@ -551,8 +552,9 @@ out: */ static int nlm_xdr_dec_res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nlm_res *result) + void *data) { + struct nlm_res *result = data; int error; error = decode_cookie(xdr, &result->cookie); @@ -573,7 +575,7 @@ out: [NLMPROC_##proc] = { \ .p_proc = NLMPROC_##proc, \ .p_encode = nlm_xdr_enc_##argtype, \ - .p_decode = (kxdrdproc_t)nlm_xdr_dec_##restype, \ + .p_decode = nlm_xdr_dec_##restype, \ .p_arglen = NLM_##argtype##_sz, \ .p_replen = NLM_##restype##_sz, \ .p_statidx = NLMPROC_##proc, \ diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 8043fd4b8a5c..80630f0347e1 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -490,8 +490,9 @@ static void nsm_xdr_enc_unmon(struct rpc_rqst *req, struct xdr_stream *xdr, static int nsm_xdr_dec_stat_res(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nsm_res *resp) + void *data) { + struct nsm_res *resp = data; __be32 *p; p = xdr_inline_decode(xdr, 4 + 4); @@ -507,8 +508,9 @@ static int nsm_xdr_dec_stat_res(struct rpc_rqst *rqstp, static int nsm_xdr_dec_stat(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nsm_res *resp) + void *data) { + struct nsm_res *resp = data; __be32 *p; p = xdr_inline_decode(xdr, 4); @@ -533,7 +535,7 @@ static struct rpc_procinfo nsm_procedures[] = { [NSMPROC_MON] = { .p_proc = NSMPROC_MON, .p_encode = nsm_xdr_enc_mon, - .p_decode = (kxdrdproc_t)nsm_xdr_dec_stat_res, + .p_decode = nsm_xdr_dec_stat_res, .p_arglen = SM_mon_sz, .p_replen = SM_monres_sz, .p_statidx = NSMPROC_MON, @@ -542,7 +544,7 @@ static struct rpc_procinfo nsm_procedures[] = { [NSMPROC_UNMON] = { .p_proc = NSMPROC_UNMON, .p_encode = nsm_xdr_enc_unmon, - .p_decode = (kxdrdproc_t)nsm_xdr_dec_stat, + .p_decode = nsm_xdr_dec_stat, .p_arglen = SM_mon_id_sz, .p_replen = SM_unmonres_sz, .p_statidx = NSMPROC_UNMON, -- cgit v1.2.3-59-g8ed1b From 18d9cff40010cb13cc57c36c982b273140b6b73e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 15:09:02 +0200 Subject: nfs: fix decoder callback prototypes Declare the p_decode callbacks with the proper prototype instead of casting to kxdrdproc_t and losing all type safety. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton Acked-by: Trond Myklebust --- fs/nfs/mount_clnt.c | 10 ++-- fs/nfs/nfs2xdr.c | 15 +++--- fs/nfs/nfs3xdr.c | 55 +++++++++++++-------- fs/nfs/nfs42xdr.c | 18 ++++--- fs/nfs/nfs4xdr.c | 137 ++++++++++++++++++++++++++++++++++------------------ 5 files changed, 151 insertions(+), 84 deletions(-) diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index f435d640d552..806657d65074 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -357,8 +357,9 @@ static int decode_fhandle(struct xdr_stream *xdr, struct mountres *res) static int mnt_xdr_dec_mountres(struct rpc_rqst *req, struct xdr_stream *xdr, - struct mountres *res) + void *data) { + struct mountres *res = data; int status; status = decode_status(xdr, res); @@ -449,8 +450,9 @@ static int decode_auth_flavors(struct xdr_stream *xdr, struct mountres *res) static int mnt_xdr_dec_mountres3(struct rpc_rqst *req, struct xdr_stream *xdr, - struct mountres *res) + void *data) { + struct mountres *res = data; int status; status = decode_fhs_status(xdr, res); @@ -468,7 +470,7 @@ static struct rpc_procinfo mnt_procedures[] = { [MOUNTPROC_MNT] = { .p_proc = MOUNTPROC_MNT, .p_encode = mnt_xdr_enc_dirpath, - .p_decode = (kxdrdproc_t)mnt_xdr_dec_mountres, + .p_decode = mnt_xdr_dec_mountres, .p_arglen = MNT_enc_dirpath_sz, .p_replen = MNT_dec_mountres_sz, .p_statidx = MOUNTPROC_MNT, @@ -487,7 +489,7 @@ static struct rpc_procinfo mnt3_procedures[] = { [MOUNTPROC3_MNT] = { .p_proc = MOUNTPROC3_MNT, .p_encode = mnt_xdr_enc_dirpath, - .p_decode = (kxdrdproc_t)mnt_xdr_dec_mountres3, + .p_decode = mnt_xdr_dec_mountres3, .p_arglen = MNT_enc_dirpath_sz, .p_replen = MNT_dec_mountres3_sz, .p_statidx = MOUNTPROC3_MNT, diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index 8ecd58597228..a299648ea321 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -832,13 +832,13 @@ out_default: } static int nfs2_xdr_dec_attrstat(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_fattr *result) + void *result) { return decode_attrstat(xdr, result, NULL); } static int nfs2_xdr_dec_diropres(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_diropok *result) + void *result) { return decode_diropres(xdr, result); } @@ -883,8 +883,9 @@ out_default: * }; */ static int nfs2_xdr_dec_readres(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_pgio_res *result) + void *data) { + struct nfs_pgio_res *result = data; enum nfs_stat status; int error; @@ -905,8 +906,10 @@ out_default: } static int nfs2_xdr_dec_writeres(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_pgio_res *result) + void *data) { + struct nfs_pgio_res *result = data; + /* All NFSv2 writes are "file sync" writes */ result->verf->committed = NFS_FILE_SYNC; return decode_attrstat(xdr, result->fattr, &result->op_status); @@ -1057,7 +1060,7 @@ out_overflow: } static int nfs2_xdr_dec_statfsres(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs2_fsstat *result) + void *result) { enum nfs_stat status; int error; @@ -1142,7 +1145,7 @@ static int nfs_stat_to_errno(enum nfs_stat status) [NFSPROC_##proc] = { \ .p_proc = NFSPROC_##proc, \ .p_encode = nfs2_xdr_enc_##argtype, \ - .p_decode = (kxdrdproc_t)nfs2_xdr_dec_##restype, \ + .p_decode = nfs2_xdr_dec_##restype, \ .p_arglen = NFS_##argtype##_sz, \ .p_replen = NFS_##restype##_sz, \ .p_timer = timer, \ diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 773150678633..cc272eb8be3e 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -1419,7 +1419,7 @@ static void nfs3_xdr_enc_setacl3args(struct rpc_rqst *req, */ static int nfs3_xdr_dec_getattr3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_fattr *result) + void *result) { enum nfs_stat status; int error; @@ -1456,7 +1456,7 @@ out_default: */ static int nfs3_xdr_dec_setattr3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_fattr *result) + void *result) { enum nfs_stat status; int error; @@ -1497,8 +1497,9 @@ out_status: */ static int nfs3_xdr_dec_lookup3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs3_diropres *result) + void *data) { + struct nfs3_diropres *result = data; enum nfs_stat status; int error; @@ -1544,8 +1545,9 @@ out_default: */ static int nfs3_xdr_dec_access3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs3_accessres *result) + void *data) { + struct nfs3_accessres *result = data; enum nfs_stat status; int error; @@ -1585,7 +1587,7 @@ out_default: */ static int nfs3_xdr_dec_readlink3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_fattr *result) + void *result) { enum nfs_stat status; int error; @@ -1663,8 +1665,9 @@ out_overflow: } static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_pgio_res *result) + void *data) { + struct nfs_pgio_res *result = data; enum nfs_stat status; int error; @@ -1736,8 +1739,9 @@ out_eio: } static int nfs3_xdr_dec_write3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_pgio_res *result) + void *data) { + struct nfs_pgio_res *result = data; enum nfs_stat status; int error; @@ -1801,8 +1805,9 @@ out: static int nfs3_xdr_dec_create3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs3_diropres *result) + void *data) { + struct nfs3_diropres *result = data; enum nfs_stat status; int error; @@ -1841,8 +1846,9 @@ out_default: */ static int nfs3_xdr_dec_remove3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_removeres *result) + void *data) { + struct nfs_removeres *result = data; enum nfs_stat status; int error; @@ -1882,8 +1888,9 @@ out_status: */ static int nfs3_xdr_dec_rename3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_renameres *result) + void *data) { + struct nfs_renameres *result = data; enum nfs_stat status; int error; @@ -1925,8 +1932,9 @@ out_status: * }; */ static int nfs3_xdr_dec_link3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs3_linkres *result) + void *data) { + struct nfs3_linkres *result = data; enum nfs_stat status; int error; @@ -2109,8 +2117,9 @@ out: static int nfs3_xdr_dec_readdir3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs3_readdirres *result) + void *data) { + struct nfs3_readdirres *result = data; enum nfs_stat status; int error; @@ -2177,8 +2186,9 @@ out_overflow: static int nfs3_xdr_dec_fsstat3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_fsstat *result) + void *data) { + struct nfs_fsstat *result = data; enum nfs_stat status; int error; @@ -2253,8 +2263,9 @@ out_overflow: static int nfs3_xdr_dec_fsinfo3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_fsinfo *result) + void *data) { + struct nfs_fsinfo *result = data; enum nfs_stat status; int error; @@ -2316,8 +2327,9 @@ out_overflow: static int nfs3_xdr_dec_pathconf3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_pathconf *result) + void *data) { + struct nfs_pathconf *result = data; enum nfs_stat status; int error; @@ -2357,8 +2369,9 @@ out_status: */ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_commitres *result) + void *data) { + struct nfs_commitres *result = data; enum nfs_stat status; int error; @@ -2426,7 +2439,7 @@ out: static int nfs3_xdr_dec_getacl3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs3_getaclres *result) + void *result) { enum nfs_stat status; int error; @@ -2445,7 +2458,7 @@ out_default: static int nfs3_xdr_dec_setacl3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_fattr *result) + void *result) { enum nfs_stat status; int error; @@ -2533,7 +2546,7 @@ static int nfs3_stat_to_errno(enum nfs_stat status) [NFS3PROC_##proc] = { \ .p_proc = NFS3PROC_##proc, \ .p_encode = nfs3_xdr_enc_##argtype##3args, \ - .p_decode = (kxdrdproc_t)nfs3_xdr_dec_##restype##3res, \ + .p_decode = nfs3_xdr_dec_##restype##3res, \ .p_arglen = NFS3_##argtype##args_sz, \ .p_replen = NFS3_##restype##res_sz, \ .p_timer = timer, \ @@ -2576,7 +2589,7 @@ static struct rpc_procinfo nfs3_acl_procedures[] = { [ACLPROC3_GETACL] = { .p_proc = ACLPROC3_GETACL, .p_encode = nfs3_xdr_enc_getacl3args, - .p_decode = (kxdrdproc_t)nfs3_xdr_dec_getacl3res, + .p_decode = nfs3_xdr_dec_getacl3res, .p_arglen = ACL3_getaclargs_sz, .p_replen = ACL3_getaclres_sz, .p_timer = 1, @@ -2585,7 +2598,7 @@ static struct rpc_procinfo nfs3_acl_procedures[] = { [ACLPROC3_SETACL] = { .p_proc = ACLPROC3_SETACL, .p_encode = nfs3_xdr_enc_setacl3args, - .p_decode = (kxdrdproc_t)nfs3_xdr_dec_setacl3res, + .p_decode = nfs3_xdr_dec_setacl3res, .p_arglen = ACL3_setaclargs_sz, .p_replen = ACL3_setaclres_sz, .p_timer = 0, diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index 0a1bd60a1f8e..5ee1b0f0d904 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -454,8 +454,9 @@ static int decode_clone(struct xdr_stream *xdr) */ static int nfs4_xdr_dec_allocate(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs42_falloc_res *res) + void *data) { + struct nfs42_falloc_res *res = data; struct compound_hdr hdr; int status; @@ -481,8 +482,9 @@ out: */ static int nfs4_xdr_dec_copy(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs42_copy_res *res) + void *data) { + struct nfs42_copy_res *res = data; struct compound_hdr hdr; int status; @@ -514,8 +516,9 @@ out: */ static int nfs4_xdr_dec_deallocate(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs42_falloc_res *res) + void *data) { + struct nfs42_falloc_res *res = data; struct compound_hdr hdr; int status; @@ -541,8 +544,9 @@ out: */ static int nfs4_xdr_dec_seek(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs42_seek_res *res) + void *data) { + struct nfs42_seek_res *res = data; struct compound_hdr hdr; int status; @@ -565,8 +569,9 @@ out: */ static int nfs4_xdr_dec_layoutstats(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs42_layoutstat_res *res) + void *data) { + struct nfs42_layoutstat_res *res = data; struct compound_hdr hdr; int status, i; @@ -595,8 +600,9 @@ out: */ static int nfs4_xdr_dec_clone(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs42_clone_res *res) + void *data) { + struct nfs42_clone_res *res = data; struct compound_hdr hdr; int status; diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index c5036ef770f9..797f3ce75286 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -6154,8 +6154,9 @@ int decode_layoutreturn(struct xdr_stream *xdr, */ static int nfs4_xdr_dec_open_downgrade(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_closeres *res) + void *data) { + struct nfs_closeres *res = data; struct compound_hdr hdr; int status; @@ -6183,8 +6184,9 @@ out: * Decode ACCESS response */ static int nfs4_xdr_dec_access(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_accessres *res) + void *data) { + struct nfs4_accessres *res = data; struct compound_hdr hdr; int status; @@ -6209,8 +6211,9 @@ out: * Decode LOOKUP response */ static int nfs4_xdr_dec_lookup(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_lookup_res *res) + void *data) { + struct nfs4_lookup_res *res = data; struct compound_hdr hdr; int status; @@ -6239,8 +6242,9 @@ out: */ static int nfs4_xdr_dec_lookup_root(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_lookup_res *res) + void *data) { + struct nfs4_lookup_res *res = data; struct compound_hdr hdr; int status; @@ -6265,8 +6269,9 @@ out: * Decode REMOVE response */ static int nfs4_xdr_dec_remove(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_removeres *res) + void *data) { + struct nfs_removeres *res = data; struct compound_hdr hdr; int status; @@ -6288,8 +6293,9 @@ out: * Decode RENAME response */ static int nfs4_xdr_dec_rename(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_renameres *res) + void *data) { + struct nfs_renameres *res = data; struct compound_hdr hdr; int status; @@ -6317,8 +6323,9 @@ out: * Decode LINK response */ static int nfs4_xdr_dec_link(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_link_res *res) + void *data) { + struct nfs4_link_res *res = data; struct compound_hdr hdr; int status; @@ -6356,8 +6363,9 @@ out: * Decode CREATE response */ static int nfs4_xdr_dec_create(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_create_res *res) + void *data) { + struct nfs4_create_res *res = data; struct compound_hdr hdr; int status; @@ -6385,7 +6393,7 @@ out: * Decode SYMLINK response */ static int nfs4_xdr_dec_symlink(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_create_res *res) + void *res) { return nfs4_xdr_dec_create(rqstp, xdr, res); } @@ -6394,8 +6402,9 @@ static int nfs4_xdr_dec_symlink(struct rpc_rqst *rqstp, struct xdr_stream *xdr, * Decode GETATTR response */ static int nfs4_xdr_dec_getattr(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_getattr_res *res) + void *data) { + struct nfs4_getattr_res *res = data; struct compound_hdr hdr; int status; @@ -6436,8 +6445,9 @@ static void nfs4_xdr_enc_setacl(struct rpc_rqst *req, struct xdr_stream *xdr, */ static int nfs4_xdr_dec_setacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_setaclres *res) + void *data) { + struct nfs_setaclres *res = data; struct compound_hdr hdr; int status; @@ -6460,8 +6470,9 @@ out: */ static int nfs4_xdr_dec_getacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_getaclres *res) + void *data) { + struct nfs_getaclres *res = data; struct compound_hdr hdr; int status; @@ -6488,8 +6499,9 @@ out: * Decode CLOSE response */ static int nfs4_xdr_dec_close(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_closeres *res) + void *data) { + struct nfs_closeres *res = data; struct compound_hdr hdr; int status; @@ -6522,8 +6534,9 @@ out: * Decode OPEN response */ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_openres *res) + void *data) { + struct nfs_openres *res = data; struct compound_hdr hdr; int status; @@ -6554,8 +6567,9 @@ out: */ static int nfs4_xdr_dec_open_confirm(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_open_confirmres *res) + void *data) { + struct nfs_open_confirmres *res = data; struct compound_hdr hdr; int status; @@ -6575,8 +6589,9 @@ out: */ static int nfs4_xdr_dec_open_noattr(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_openres *res) + void *data) { + struct nfs_openres *res = data; struct compound_hdr hdr; int status; @@ -6604,8 +6619,9 @@ out: */ static int nfs4_xdr_dec_setattr(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_setattrres *res) + void *data) { + struct nfs_setattrres *res = data; struct compound_hdr hdr; int status; @@ -6630,8 +6646,9 @@ out: * Decode LOCK response */ static int nfs4_xdr_dec_lock(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_lock_res *res) + void *data) { + struct nfs_lock_res *res = data; struct compound_hdr hdr; int status; @@ -6653,8 +6670,9 @@ out: * Decode LOCKT response */ static int nfs4_xdr_dec_lockt(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_lockt_res *res) + void *data) { + struct nfs_lockt_res *res = data; struct compound_hdr hdr; int status; @@ -6676,8 +6694,9 @@ out: * Decode LOCKU response */ static int nfs4_xdr_dec_locku(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_locku_res *res) + void *data) { + struct nfs_locku_res *res = data; struct compound_hdr hdr; int status; @@ -6712,8 +6731,9 @@ static int nfs4_xdr_dec_release_lockowner(struct rpc_rqst *rqstp, */ static int nfs4_xdr_dec_readlink(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_readlink_res *res) + void *data) { + struct nfs4_readlink_res *res = data; struct compound_hdr hdr; int status; @@ -6735,8 +6755,9 @@ out: * Decode READDIR response */ static int nfs4_xdr_dec_readdir(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_readdir_res *res) + void *data) { + struct nfs4_readdir_res *res = data; struct compound_hdr hdr; int status; @@ -6758,8 +6779,9 @@ out: * Decode Read response */ static int nfs4_xdr_dec_read(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_pgio_res *res) + void *data) { + struct nfs_pgio_res *res = data; struct compound_hdr hdr; int status; @@ -6784,8 +6806,9 @@ out: * Decode WRITE response */ static int nfs4_xdr_dec_write(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_pgio_res *res) + void *data) { + struct nfs_pgio_res *res = data; struct compound_hdr hdr; int status; @@ -6814,8 +6837,9 @@ out: * Decode COMMIT response */ static int nfs4_xdr_dec_commit(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_commitres *res) + void *data) { + struct nfs_commitres *res = data; struct compound_hdr hdr; int status; @@ -6838,8 +6862,9 @@ out: * Decode FSINFO response */ static int nfs4_xdr_dec_fsinfo(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_fsinfo_res *res) + void *data) { + struct nfs4_fsinfo_res *res = data; struct compound_hdr hdr; int status; @@ -6857,8 +6882,9 @@ static int nfs4_xdr_dec_fsinfo(struct rpc_rqst *req, struct xdr_stream *xdr, * Decode PATHCONF response */ static int nfs4_xdr_dec_pathconf(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_pathconf_res *res) + void *data) { + struct nfs4_pathconf_res *res = data; struct compound_hdr hdr; int status; @@ -6876,8 +6902,9 @@ static int nfs4_xdr_dec_pathconf(struct rpc_rqst *req, struct xdr_stream *xdr, * Decode STATFS response */ static int nfs4_xdr_dec_statfs(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_statfs_res *res) + void *data) { + struct nfs4_statfs_res *res = data; struct compound_hdr hdr; int status; @@ -6896,8 +6923,9 @@ static int nfs4_xdr_dec_statfs(struct rpc_rqst *req, struct xdr_stream *xdr, */ static int nfs4_xdr_dec_server_caps(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_server_caps_res *res) + void *data) { + struct nfs4_server_caps_res *res = data; struct compound_hdr hdr; int status; @@ -6935,8 +6963,9 @@ static int nfs4_xdr_dec_renew(struct rpc_rqst *rqstp, struct xdr_stream *xdr, */ static int nfs4_xdr_dec_setclientid(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_setclientid_res *res) + void *data) { + struct nfs4_setclientid_res *res = data; struct compound_hdr hdr; int status; @@ -6950,7 +6979,8 @@ static int nfs4_xdr_dec_setclientid(struct rpc_rqst *req, * Decode SETCLIENTID_CONFIRM response */ static int nfs4_xdr_dec_setclientid_confirm(struct rpc_rqst *req, - struct xdr_stream *xdr) + struct xdr_stream *xdr, + void *data) { struct compound_hdr hdr; int status; @@ -6966,8 +6996,9 @@ static int nfs4_xdr_dec_setclientid_confirm(struct rpc_rqst *req, */ static int nfs4_xdr_dec_delegreturn(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_delegreturnres *res) + void *data) { + struct nfs4_delegreturnres *res = data; struct compound_hdr hdr; int status; @@ -7001,8 +7032,9 @@ out: */ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_fs_locations_res *res) + void *data) { + struct nfs4_fs_locations_res *res = data; struct compound_hdr hdr; int status; @@ -7044,8 +7076,9 @@ out: */ static int nfs4_xdr_dec_secinfo(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_secinfo_res *res) + void *data) { + struct nfs4_secinfo_res *res = data; struct compound_hdr hdr; int status; @@ -7068,8 +7101,9 @@ out: */ static int nfs4_xdr_dec_fsid_present(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_fsid_present_res *res) + void *data) { + struct nfs4_fsid_present_res *res = data; struct compound_hdr hdr; int status; @@ -7129,7 +7163,7 @@ static int nfs4_xdr_dec_exchange_id(struct rpc_rqst *rqstp, */ static int nfs4_xdr_dec_create_session(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs41_create_session_res *res) + void *res) { struct compound_hdr hdr; int status; @@ -7177,7 +7211,7 @@ static int nfs4_xdr_dec_destroy_clientid(struct rpc_rqst *rqstp, */ static int nfs4_xdr_dec_sequence(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_sequence_res *res) + void *res) { struct compound_hdr hdr; int status; @@ -7193,8 +7227,9 @@ static int nfs4_xdr_dec_sequence(struct rpc_rqst *rqstp, */ static int nfs4_xdr_dec_get_lease_time(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_get_lease_time_res *res) + void *data) { + struct nfs4_get_lease_time_res *res = data; struct compound_hdr hdr; int status; @@ -7213,8 +7248,9 @@ static int nfs4_xdr_dec_get_lease_time(struct rpc_rqst *rqstp, */ static int nfs4_xdr_dec_reclaim_complete(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs41_reclaim_complete_res *res) + void *data) { + struct nfs41_reclaim_complete_res *res = data; struct compound_hdr hdr; int status; @@ -7231,8 +7267,9 @@ static int nfs4_xdr_dec_reclaim_complete(struct rpc_rqst *rqstp, */ static int nfs4_xdr_dec_getdeviceinfo(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_getdeviceinfo_res *res) + void *data) { + struct nfs4_getdeviceinfo_res *res = data; struct compound_hdr hdr; int status; @@ -7252,8 +7289,9 @@ out: */ static int nfs4_xdr_dec_layoutget(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_layoutget_res *res) + void *data) { + struct nfs4_layoutget_res *res = data; struct compound_hdr hdr; int status; @@ -7276,8 +7314,9 @@ out: */ static int nfs4_xdr_dec_layoutreturn(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_layoutreturn_res *res) + void *data) { + struct nfs4_layoutreturn_res *res = data; struct compound_hdr hdr; int status; @@ -7300,8 +7339,9 @@ out: */ static int nfs4_xdr_dec_layoutcommit(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_layoutcommit_res *res) + void *data) { + struct nfs4_layoutcommit_res *res = data; struct compound_hdr hdr; int status; @@ -7327,8 +7367,9 @@ out: */ static int nfs4_xdr_dec_secinfo_no_name(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_secinfo_res *res) + void *data) { + struct nfs4_secinfo_res *res = data; struct compound_hdr hdr; int status; @@ -7351,8 +7392,9 @@ out: */ static int nfs4_xdr_dec_test_stateid(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs41_test_stateid_res *res) + void *data) { + struct nfs41_test_stateid_res *res = data; struct compound_hdr hdr; int status; @@ -7372,8 +7414,9 @@ out: */ static int nfs4_xdr_dec_free_stateid(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs41_free_stateid_res *res) + void *data) { + struct nfs41_free_stateid_res *res = data; struct compound_hdr hdr; int status; @@ -7539,7 +7582,7 @@ nfs4_stat_to_errno(int stat) [NFSPROC4_CLNT_##proc] = { \ .p_proc = NFSPROC4_COMPOUND, \ .p_encode = nfs4_xdr_##argtype, \ - .p_decode = (kxdrdproc_t)nfs4_xdr_##restype, \ + .p_decode = nfs4_xdr_##restype, \ .p_arglen = NFS4_##argtype##_sz, \ .p_replen = NFS4_##restype##_sz, \ .p_statidx = NFSPROC4_CLNT_##proc, \ -- cgit v1.2.3-59-g8ed1b From f4dac4ade5ba4e84b1fb28ff52265f13aa833838 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 11 May 2017 09:22:18 +0200 Subject: nfs: don't cast callback decode/proc/encode routines Instead declare all functions with the proper methods signature. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton Acked-by: Trond Myklebust --- fs/nfs/callback.h | 27 ++++++---------- fs/nfs/callback_proc.c | 33 ++++++++++++------- fs/nfs/callback_xdr.c | 86 +++++++++++++++++++++++++++----------------------- 3 files changed, 77 insertions(+), 69 deletions(-) diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h index c701c308fac5..3dc54d7cb19c 100644 --- a/fs/nfs/callback.h +++ b/fs/nfs/callback.h @@ -114,8 +114,7 @@ struct cb_sequenceres { uint32_t csr_target_highestslotid; }; -extern __be32 nfs4_callback_sequence(struct cb_sequenceargs *args, - struct cb_sequenceres *res, +extern __be32 nfs4_callback_sequence(void *argp, void *resp, struct cb_process_state *cps); #define RCA4_TYPE_MASK_RDATA_DLG 0 @@ -134,15 +133,13 @@ struct cb_recallanyargs { uint32_t craa_type_mask; }; -extern __be32 nfs4_callback_recallany(struct cb_recallanyargs *args, - void *dummy, +extern __be32 nfs4_callback_recallany(void *argp, void *resp, struct cb_process_state *cps); struct cb_recallslotargs { uint32_t crsa_target_highest_slotid; }; -extern __be32 nfs4_callback_recallslot(struct cb_recallslotargs *args, - void *dummy, +extern __be32 nfs4_callback_recallslot(void *argp, void *resp, struct cb_process_state *cps); struct cb_layoutrecallargs { @@ -159,9 +156,8 @@ struct cb_layoutrecallargs { }; }; -extern __be32 nfs4_callback_layoutrecall( - struct cb_layoutrecallargs *args, - void *dummy, struct cb_process_state *cps); +extern __be32 nfs4_callback_layoutrecall(void *argp, void *resp, + struct cb_process_state *cps); struct cb_devicenotifyitem { uint32_t cbd_notify_type; @@ -175,9 +171,8 @@ struct cb_devicenotifyargs { struct cb_devicenotifyitem *devs; }; -extern __be32 nfs4_callback_devicenotify( - struct cb_devicenotifyargs *args, - void *dummy, struct cb_process_state *cps); +extern __be32 nfs4_callback_devicenotify(void *argp, void *resp, + struct cb_process_state *cps); struct cb_notify_lock_args { struct nfs_fh cbnl_fh; @@ -185,15 +180,13 @@ struct cb_notify_lock_args { bool cbnl_valid; }; -extern __be32 nfs4_callback_notify_lock(struct cb_notify_lock_args *args, - void *dummy, +extern __be32 nfs4_callback_notify_lock(void *argp, void *resp, struct cb_process_state *cps); #endif /* CONFIG_NFS_V4_1 */ extern int check_gss_callback_principal(struct nfs_client *, struct svc_rqst *); -extern __be32 nfs4_callback_getattr(struct cb_getattrargs *args, - struct cb_getattrres *res, +extern __be32 nfs4_callback_getattr(void *argp, void *resp, struct cb_process_state *cps); -extern __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy, +extern __be32 nfs4_callback_recall(void *argp, void *resp, struct cb_process_state *cps); #if IS_ENABLED(CONFIG_NFS_V4) extern int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt); diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index 52479f180ea1..5427cdf04c5a 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -19,10 +19,11 @@ #define NFSDBG_FACILITY NFSDBG_CALLBACK -__be32 nfs4_callback_getattr(struct cb_getattrargs *args, - struct cb_getattrres *res, +__be32 nfs4_callback_getattr(void *argp, void *resp, struct cb_process_state *cps) { + struct cb_getattrargs *args = argp; + struct cb_getattrres *res = resp; struct nfs_delegation *delegation; struct nfs_inode *nfsi; struct inode *inode; @@ -68,9 +69,10 @@ out: return res->status; } -__be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy, +__be32 nfs4_callback_recall(void *argp, void *resp, struct cb_process_state *cps) { + struct cb_recallargs *args = argp; struct inode *inode; __be32 res; @@ -324,9 +326,10 @@ static u32 do_callback_layoutrecall(struct nfs_client *clp, return initiate_bulk_draining(clp, args); } -__be32 nfs4_callback_layoutrecall(struct cb_layoutrecallargs *args, - void *dummy, struct cb_process_state *cps) +__be32 nfs4_callback_layoutrecall(void *argp, void *resp, + struct cb_process_state *cps) { + struct cb_layoutrecallargs *args = argp; u32 res = NFS4ERR_OP_NOT_IN_SESSION; if (cps->clp) @@ -345,9 +348,10 @@ static void pnfs_recall_all_layouts(struct nfs_client *clp) do_callback_layoutrecall(clp, &args); } -__be32 nfs4_callback_devicenotify(struct cb_devicenotifyargs *args, - void *dummy, struct cb_process_state *cps) +__be32 nfs4_callback_devicenotify(void *argp, void *resp, + struct cb_process_state *cps) { + struct cb_devicenotifyargs *args = argp; int i; __be32 res = 0; struct nfs_client *clp = cps->clp; @@ -469,10 +473,11 @@ out: return status; } -__be32 nfs4_callback_sequence(struct cb_sequenceargs *args, - struct cb_sequenceres *res, +__be32 nfs4_callback_sequence(void *argp, void *resp, struct cb_process_state *cps) { + struct cb_sequenceargs *args = argp; + struct cb_sequenceres *res = resp; struct nfs4_slot_table *tbl; struct nfs4_slot *slot; struct nfs_client *clp; @@ -571,9 +576,10 @@ validate_bitmap_values(unsigned long mask) return (mask & ~RCA4_TYPE_MASK_ALL) == 0; } -__be32 nfs4_callback_recallany(struct cb_recallanyargs *args, void *dummy, +__be32 nfs4_callback_recallany(void *argp, void *resp, struct cb_process_state *cps) { + struct cb_recallanyargs *args = argp; __be32 status; fmode_t flags = 0; @@ -606,9 +612,10 @@ out: } /* Reduce the fore channel's max_slots to the target value */ -__be32 nfs4_callback_recallslot(struct cb_recallslotargs *args, void *dummy, +__be32 nfs4_callback_recallslot(void *argp, void *resp, struct cb_process_state *cps) { + struct cb_recallslotargs *args = argp; struct nfs4_slot_table *fc_tbl; __be32 status; @@ -631,9 +638,11 @@ out: return status; } -__be32 nfs4_callback_notify_lock(struct cb_notify_lock_args *args, void *dummy, +__be32 nfs4_callback_notify_lock(void *argp, void *resp, struct cb_process_state *cps) { + struct cb_notify_lock_args *args = argp; + if (!cps->clp) /* set in cb_sequence */ return htonl(NFS4ERR_OP_NOT_IN_SESSION); diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index c14758e08d73..287c02202b25 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -43,16 +43,11 @@ /* Internal error code */ #define NFS4ERR_RESOURCE_HDR 11050 -typedef __be32 (*callback_process_op_t)(void *, void *, - struct cb_process_state *); -typedef __be32 (*callback_decode_arg_t)(struct svc_rqst *, struct xdr_stream *, void *); -typedef __be32 (*callback_encode_res_t)(struct svc_rqst *, struct xdr_stream *, void *); - - struct callback_op { - callback_process_op_t process_op; - callback_decode_arg_t decode_args; - callback_encode_res_t encode_res; + __be32 (*process_op)(void *, void *, struct cb_process_state *); + __be32 (*decode_args)(struct svc_rqst *, struct xdr_stream *, void *); + __be32 (*encode_res)(struct svc_rqst *, struct xdr_stream *, + const void *); long res_maxsize; }; @@ -184,8 +179,10 @@ static __be32 decode_op_hdr(struct xdr_stream *xdr, unsigned int *op) return 0; } -static __be32 decode_getattr_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, struct cb_getattrargs *args) +static __be32 decode_getattr_args(struct svc_rqst *rqstp, + struct xdr_stream *xdr, void *argp) { + struct cb_getattrargs *args = argp; __be32 status; status = decode_fh(xdr, &args->fh); @@ -194,8 +191,10 @@ static __be32 decode_getattr_args(struct svc_rqst *rqstp, struct xdr_stream *xdr return decode_bitmap(xdr, args->bitmap); } -static __be32 decode_recall_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, struct cb_recallargs *args) +static __be32 decode_recall_args(struct svc_rqst *rqstp, + struct xdr_stream *xdr, void *argp) { + struct cb_recallargs *args = argp; __be32 *p; __be32 status; @@ -217,9 +216,9 @@ static __be32 decode_layout_stateid(struct xdr_stream *xdr, nfs4_stateid *statei } static __be32 decode_layoutrecall_args(struct svc_rqst *rqstp, - struct xdr_stream *xdr, - struct cb_layoutrecallargs *args) + struct xdr_stream *xdr, void *argp) { + struct cb_layoutrecallargs *args = argp; __be32 *p; __be32 status = 0; uint32_t iomode; @@ -262,8 +261,9 @@ static __be32 decode_layoutrecall_args(struct svc_rqst *rqstp, static __be32 decode_devicenotify_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, - struct cb_devicenotifyargs *args) + void *argp) { + struct cb_devicenotifyargs *args = argp; __be32 *p; __be32 status = 0; u32 tmp; @@ -403,8 +403,9 @@ out: static __be32 decode_cb_sequence_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, - struct cb_sequenceargs *args) + void *argp) { + struct cb_sequenceargs *args = argp; __be32 *p; int i; __be32 status; @@ -450,8 +451,9 @@ out_free: static __be32 decode_recallany_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, - struct cb_recallanyargs *args) + void *argp) { + struct cb_recallanyargs *args = argp; uint32_t bitmap[2]; __be32 *p, status; @@ -469,8 +471,9 @@ static __be32 decode_recallany_args(struct svc_rqst *rqstp, static __be32 decode_recallslot_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, - struct cb_recallslotargs *args) + void *argp) { + struct cb_recallslotargs *args = argp; __be32 *p; p = read_buf(xdr, 4); @@ -510,8 +513,10 @@ static __be32 decode_lockowner(struct xdr_stream *xdr, struct cb_notify_lock_arg return 0; } -static __be32 decode_notify_lock_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, struct cb_notify_lock_args *args) +static __be32 decode_notify_lock_args(struct svc_rqst *rqstp, + struct xdr_stream *xdr, void *argp) { + struct cb_notify_lock_args *args = argp; __be32 status; status = decode_fh(xdr, &args->cbnl_fh); @@ -641,8 +646,10 @@ static __be32 encode_op_hdr(struct xdr_stream *xdr, uint32_t op, __be32 res) return 0; } -static __be32 encode_getattr_res(struct svc_rqst *rqstp, struct xdr_stream *xdr, const struct cb_getattrres *res) +static __be32 encode_getattr_res(struct svc_rqst *rqstp, struct xdr_stream *xdr, + const void *resp) { + const struct cb_getattrres *res = resp; __be32 *savep = NULL; __be32 status = res->status; @@ -683,8 +690,9 @@ static __be32 encode_sessionid(struct xdr_stream *xdr, static __be32 encode_cb_sequence_res(struct svc_rqst *rqstp, struct xdr_stream *xdr, - const struct cb_sequenceres *res) + const void *resp) { + const struct cb_sequenceres *res = resp; __be32 *p; __be32 status = res->csr_status; @@ -938,48 +946,46 @@ static struct callback_op callback_ops[] = { .res_maxsize = CB_OP_HDR_RES_MAXSZ, }, [OP_CB_GETATTR] = { - .process_op = (callback_process_op_t)nfs4_callback_getattr, - .decode_args = (callback_decode_arg_t)decode_getattr_args, - .encode_res = (callback_encode_res_t)encode_getattr_res, + .process_op = nfs4_callback_getattr, + .decode_args = decode_getattr_args, + .encode_res = encode_getattr_res, .res_maxsize = CB_OP_GETATTR_RES_MAXSZ, }, [OP_CB_RECALL] = { - .process_op = (callback_process_op_t)nfs4_callback_recall, - .decode_args = (callback_decode_arg_t)decode_recall_args, + .process_op = nfs4_callback_recall, + .decode_args = decode_recall_args, .res_maxsize = CB_OP_RECALL_RES_MAXSZ, }, #if defined(CONFIG_NFS_V4_1) [OP_CB_LAYOUTRECALL] = { - .process_op = (callback_process_op_t)nfs4_callback_layoutrecall, - .decode_args = - (callback_decode_arg_t)decode_layoutrecall_args, + .process_op = nfs4_callback_layoutrecall, + .decode_args = decode_layoutrecall_args, .res_maxsize = CB_OP_LAYOUTRECALL_RES_MAXSZ, }, [OP_CB_NOTIFY_DEVICEID] = { - .process_op = (callback_process_op_t)nfs4_callback_devicenotify, - .decode_args = - (callback_decode_arg_t)decode_devicenotify_args, + .process_op = nfs4_callback_devicenotify, + .decode_args = decode_devicenotify_args, .res_maxsize = CB_OP_DEVICENOTIFY_RES_MAXSZ, }, [OP_CB_SEQUENCE] = { - .process_op = (callback_process_op_t)nfs4_callback_sequence, - .decode_args = (callback_decode_arg_t)decode_cb_sequence_args, - .encode_res = (callback_encode_res_t)encode_cb_sequence_res, + .process_op = nfs4_callback_sequence, + .decode_args = decode_cb_sequence_args, + .encode_res = encode_cb_sequence_res, .res_maxsize = CB_OP_SEQUENCE_RES_MAXSZ, }, [OP_CB_RECALL_ANY] = { - .process_op = (callback_process_op_t)nfs4_callback_recallany, - .decode_args = (callback_decode_arg_t)decode_recallany_args, + .process_op = nfs4_callback_recallany, + .decode_args = decode_recallany_args, .res_maxsize = CB_OP_RECALLANY_RES_MAXSZ, }, [OP_CB_RECALL_SLOT] = { - .process_op = (callback_process_op_t)nfs4_callback_recallslot, - .decode_args = (callback_decode_arg_t)decode_recallslot_args, + .process_op = nfs4_callback_recallslot, + .decode_args = decode_recallslot_args, .res_maxsize = CB_OP_RECALLSLOT_RES_MAXSZ, }, [OP_CB_NOTIFY_LOCK] = { - .process_op = (callback_process_op_t)nfs4_callback_notify_lock, - .decode_args = (callback_decode_arg_t)decode_notify_lock_args, + .process_op = nfs4_callback_notify_lock, + .decode_args = decode_notify_lock_args, .res_maxsize = CB_OP_NOTIFY_LOCK_RES_MAXSZ, }, #endif /* CONFIG_NFS_V4_1 */ -- cgit v1.2.3-59-g8ed1b From cdfa31e93fd228e197cc5bb31f0156117cea2156 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 23:32:18 +0200 Subject: lockd: fix some weird indentation Remove double indentation of a few struct rpc_version and struct rpc_program instance. Signed-off-by: Christoph Hellwig Acked-by: Trond Myklebust --- fs/lockd/clntxdr.c | 22 +++++++++++----------- fs/lockd/mon.c | 16 ++++++++-------- 2 files changed, 19 insertions(+), 19 deletions(-) diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c index 17e7f08b3a22..bd8a976785ae 100644 --- a/fs/lockd/clntxdr.c +++ b/fs/lockd/clntxdr.c @@ -601,15 +601,15 @@ static struct rpc_procinfo nlm_procedures[] = { }; static const struct rpc_version nlm_version1 = { - .number = 1, - .nrprocs = ARRAY_SIZE(nlm_procedures), - .procs = nlm_procedures, + .number = 1, + .nrprocs = ARRAY_SIZE(nlm_procedures), + .procs = nlm_procedures, }; static const struct rpc_version nlm_version3 = { - .number = 3, - .nrprocs = ARRAY_SIZE(nlm_procedures), - .procs = nlm_procedures, + .number = 3, + .nrprocs = ARRAY_SIZE(nlm_procedures), + .procs = nlm_procedures, }; static const struct rpc_version *nlm_versions[] = { @@ -623,9 +623,9 @@ static const struct rpc_version *nlm_versions[] = { static struct rpc_stat nlm_rpc_stats; const struct rpc_program nlm_program = { - .name = "lockd", - .number = NLM_PROGRAM, - .nrvers = ARRAY_SIZE(nlm_versions), - .version = nlm_versions, - .stats = &nlm_rpc_stats, + .name = "lockd", + .number = NLM_PROGRAM, + .nrvers = ARRAY_SIZE(nlm_versions), + .version = nlm_versions, + .stats = &nlm_rpc_stats, }; diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 80630f0347e1..62424e929a7f 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -553,9 +553,9 @@ static struct rpc_procinfo nsm_procedures[] = { }; static const struct rpc_version nsm_version1 = { - .number = 1, - .nrprocs = ARRAY_SIZE(nsm_procedures), - .procs = nsm_procedures + .number = 1, + .nrprocs = ARRAY_SIZE(nsm_procedures), + .procs = nsm_procedures }; static const struct rpc_version *nsm_version[] = { @@ -565,9 +565,9 @@ static const struct rpc_version *nsm_version[] = { static struct rpc_stat nsm_stats; static const struct rpc_program nsm_program = { - .name = "statd", - .number = NSM_PROGRAM, - .nrvers = ARRAY_SIZE(nsm_version), - .version = nsm_version, - .stats = &nsm_stats + .name = "statd", + .number = NSM_PROGRAM, + .nrvers = ARRAY_SIZE(nsm_version), + .version = nsm_version, + .stats = &nsm_stats }; -- cgit v1.2.3-59-g8ed1b From 1c5876ddbdb401f814ef717394826e7dfb6704d4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 23:27:10 +0200 Subject: sunrpc: move p_count out of struct rpc_procinfo p_count is the only writeable memeber of struct rpc_procinfo, which is a good candidate to be const-ified as it contains function pointers. This patch moves it into out out struct rpc_procinfo, and into a separate writable array that is pointed to by struct rpc_version and indexed by p_statidx. Signed-off-by: Christoph Hellwig --- fs/lockd/clnt4xdr.c | 2 ++ fs/lockd/clntxdr.c | 4 ++++ fs/lockd/mon.c | 4 +++- fs/nfs/mount_clnt.c | 5 ++++- fs/nfs/nfs2xdr.c | 4 +++- fs/nfs/nfs3xdr.c | 6 +++++- fs/nfs/nfs4xdr.c | 4 +++- fs/nfsd/nfs4callback.c | 4 +++- include/linux/sunrpc/clnt.h | 2 +- net/sunrpc/auth_gss/gss_rpc_upcall.c | 3 ++- net/sunrpc/clnt.c | 6 ++++-- net/sunrpc/rpcb_clnt.c | 12 +++++++++--- net/sunrpc/stats.c | 3 +-- 13 files changed, 44 insertions(+), 15 deletions(-) diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c index f0ab7a99dd23..7c255d1d7c64 100644 --- a/fs/lockd/clnt4xdr.c +++ b/fs/lockd/clnt4xdr.c @@ -602,8 +602,10 @@ static struct rpc_procinfo nlm4_procedures[] = { PROC(GRANTED_RES, res, norep), }; +static unsigned int nlm_version4_counts[ARRAY_SIZE(nlm4_procedures)]; const struct rpc_version nlm_version4 = { .number = 4, .nrprocs = ARRAY_SIZE(nlm4_procedures), .procs = nlm4_procedures, + .counts = nlm_version4_counts, }; diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c index bd8a976785ae..39500c5743a5 100644 --- a/fs/lockd/clntxdr.c +++ b/fs/lockd/clntxdr.c @@ -600,16 +600,20 @@ static struct rpc_procinfo nlm_procedures[] = { PROC(GRANTED_RES, res, norep), }; +static unsigned int nlm_version1_counts[ARRAY_SIZE(nlm_procedures)]; static const struct rpc_version nlm_version1 = { .number = 1, .nrprocs = ARRAY_SIZE(nlm_procedures), .procs = nlm_procedures, + .counts = nlm_version1_counts, }; +static unsigned int nlm_version3_counts[ARRAY_SIZE(nlm_procedures)]; static const struct rpc_version nlm_version3 = { .number = 3, .nrprocs = ARRAY_SIZE(nlm_procedures), .procs = nlm_procedures, + .counts = nlm_version3_counts, }; static const struct rpc_version *nlm_versions[] = { diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 62424e929a7f..fe4ec82764fe 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -552,10 +552,12 @@ static struct rpc_procinfo nsm_procedures[] = { }, }; +static unsigned int nsm_version1_counts[ARRAY_SIZE(nsm_procedures)]; static const struct rpc_version nsm_version1 = { .number = 1, .nrprocs = ARRAY_SIZE(nsm_procedures), - .procs = nsm_procedures + .procs = nsm_procedures, + .counts = nsm_version1_counts, }; static const struct rpc_version *nsm_version[] = { diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index 806657d65074..d25914aa8bf9 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -504,17 +504,20 @@ static struct rpc_procinfo mnt3_procedures[] = { }, }; - +static unsigned int mnt_counts[ARRAY_SIZE(mnt_procedures)]; static const struct rpc_version mnt_version1 = { .number = 1, .nrprocs = ARRAY_SIZE(mnt_procedures), .procs = mnt_procedures, + .counts = mnt_counts, }; +static unsigned int mnt3_counts[ARRAY_SIZE(mnt_procedures)]; static const struct rpc_version mnt_version3 = { .number = 3, .nrprocs = ARRAY_SIZE(mnt3_procedures), .procs = mnt3_procedures, + .counts = mnt3_counts, }; static const struct rpc_version *mnt_version[] = { diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index a299648ea321..16b4526299c1 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -1170,8 +1170,10 @@ struct rpc_procinfo nfs_procedures[] = { PROC(STATFS, fhandle, statfsres, 0), }; +static unsigned int nfs_version2_counts[ARRAY_SIZE(nfs_procedures)]; const struct rpc_version nfs_version2 = { .number = 2, .nrprocs = ARRAY_SIZE(nfs_procedures), - .procs = nfs_procedures + .procs = nfs_procedures, + .counts = nfs_version2_counts, }; diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index cc272eb8be3e..a017ec5c7a9d 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -2578,10 +2578,12 @@ struct rpc_procinfo nfs3_procedures[] = { PROC(COMMIT, commit, commit, 5), }; +static unsigned int nfs_version3_counts[ARRAY_SIZE(nfs3_procedures)]; const struct rpc_version nfs_version3 = { .number = 3, .nrprocs = ARRAY_SIZE(nfs3_procedures), - .procs = nfs3_procedures + .procs = nfs3_procedures, + .counts = nfs_version3_counts, }; #ifdef CONFIG_NFS_V3_ACL @@ -2606,10 +2608,12 @@ static struct rpc_procinfo nfs3_acl_procedures[] = { }, }; +static unsigned int nfs3_acl_counts[ARRAY_SIZE(nfs3_acl_procedures)]; const struct rpc_version nfsacl_version3 = { .number = 3, .nrprocs = sizeof(nfs3_acl_procedures)/ sizeof(nfs3_acl_procedures[0]), .procs = nfs3_acl_procedures, + .counts = nfs3_acl_counts, }; #endif /* CONFIG_NFS_V3_ACL */ diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 797f3ce75286..40cf5529e65f 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -7661,10 +7661,12 @@ struct rpc_procinfo nfs4_procedures[] = { #endif /* CONFIG_NFS_V4_2 */ }; +static unsigned int nfs_version4_counts[ARRAY_SIZE(nfs4_procedures)]; const struct rpc_version nfs_version4 = { .number = 4, .nrprocs = ARRAY_SIZE(nfs4_procedures), - .procs = nfs4_procedures + .procs = nfs4_procedures, + .counts = nfs_version4_counts, }; /* diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index a2bedbd05b2b..afa961fe073c 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -705,6 +705,7 @@ static struct rpc_procinfo nfs4_cb_procedures[] = { PROC(CB_NOTIFY_LOCK, COMPOUND, cb_notify_lock, cb_notify_lock), }; +static unsigned int nfs4_cb_counts[ARRAY_SIZE(nfs4_cb_procedures)]; static struct rpc_version nfs_cb_version4 = { /* * Note on the callback rpc program version number: despite language in rfc @@ -715,7 +716,8 @@ static struct rpc_version nfs_cb_version4 = { */ .number = 1, .nrprocs = ARRAY_SIZE(nfs4_cb_procedures), - .procs = nfs4_cb_procedures + .procs = nfs4_cb_procedures, + .counts = nfs4_cb_counts, }; static const struct rpc_version *nfs_cb_version[] = { diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 6095ecba0dde..c75ba37151fe 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -88,6 +88,7 @@ struct rpc_version { u32 number; /* version number */ unsigned int nrprocs; /* number of procs */ struct rpc_procinfo * procs; /* procedure array */ + unsigned int *counts; /* call counts */ }; /* @@ -99,7 +100,6 @@ struct rpc_procinfo { kxdrdproc_t p_decode; /* XDR decode function */ unsigned int p_arglen; /* argument hdr length (u32) */ unsigned int p_replen; /* reply hdr length (u32) */ - unsigned int p_count; /* call count */ unsigned int p_timer; /* Which RTT timer to use */ u32 p_statidx; /* Which procedure to account */ const char * p_name; /* name of procedure */ diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index a80b8e607478..f8729b647605 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -364,11 +364,12 @@ void gssp_free_upcall_data(struct gssp_upcall_data *data) /* * Initialization stuff */ - +static unsigned int gssp_version1_counts[ARRAY_SIZE(gssp_procedures)]; static const struct rpc_version gssp_version1 = { .number = GSSPROXY_VERS_1, .nrprocs = ARRAY_SIZE(gssp_procedures), .procs = gssp_procedures, + .counts = gssp_version1_counts, }; static const struct rpc_version *gssp_version[] = { diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 964d5c4a1b60..f2d1f971247b 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1517,14 +1517,16 @@ static void call_start(struct rpc_task *task) { struct rpc_clnt *clnt = task->tk_client; + int idx = task->tk_msg.rpc_proc->p_statidx; dprintk("RPC: %5u call_start %s%d proc %s (%s)\n", task->tk_pid, clnt->cl_program->name, clnt->cl_vers, rpc_proc_name(task), (RPC_IS_ASYNC(task) ? "async" : "sync")); - /* Increment call count */ - task->tk_msg.rpc_proc->p_count++; + /* Increment call count (version might not be valid for ping) */ + if (clnt->cl_program->version[clnt->cl_vers]) + clnt->cl_program->version[clnt->cl_vers]->counts[idx]++; clnt->cl_stats->rpccnt++; task->tk_action = call_reserve; } diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index f67b9e2897b4..9d47b9d3bbee 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -1117,22 +1117,28 @@ static const struct rpcb_info rpcb_next_version6[] = { }, }; +static unsigned int rpcb_version2_counts[ARRAY_SIZE(rpcb_procedures2)]; static const struct rpc_version rpcb_version2 = { .number = RPCBVERS_2, .nrprocs = ARRAY_SIZE(rpcb_procedures2), - .procs = rpcb_procedures2 + .procs = rpcb_procedures2, + .counts = rpcb_version2_counts, }; +static unsigned int rpcb_version3_counts[ARRAY_SIZE(rpcb_procedures3)]; static const struct rpc_version rpcb_version3 = { .number = RPCBVERS_3, .nrprocs = ARRAY_SIZE(rpcb_procedures3), - .procs = rpcb_procedures3 + .procs = rpcb_procedures3, + .counts = rpcb_version3_counts, }; +static unsigned int rpcb_version4_counts[ARRAY_SIZE(rpcb_procedures4)]; static const struct rpc_version rpcb_version4 = { .number = RPCBVERS_4, .nrprocs = ARRAY_SIZE(rpcb_procedures4), - .procs = rpcb_procedures4 + .procs = rpcb_procedures4, + .counts = rpcb_version4_counts, }; static const struct rpc_version *rpcb_version[] = { diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c index caeb01ad2b5a..91c84d18bf9a 100644 --- a/net/sunrpc/stats.c +++ b/net/sunrpc/stats.c @@ -55,8 +55,7 @@ static int rpc_proc_show(struct seq_file *seq, void *v) { seq_printf(seq, "proc%u %u", vers->number, vers->nrprocs); for (j = 0; j < vers->nrprocs; j++) - seq_printf(seq, " %u", - vers->procs[j].p_count); + seq_printf(seq, " %u", vers->counts[j]); seq_putc(seq, '\n'); } return 0; -- cgit v1.2.3-59-g8ed1b From f700c72dd2f1f886f56788436b540aab95903c3f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 12 May 2017 15:51:24 +0200 Subject: nfs: use ARRAY_SIZE() in the nfsacl_version3 declaration Signed-off-by: Christoph Hellwig --- fs/nfs/nfs3xdr.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index a017ec5c7a9d..85ff1187e637 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -2611,8 +2611,7 @@ static struct rpc_procinfo nfs3_acl_procedures[] = { static unsigned int nfs3_acl_counts[ARRAY_SIZE(nfs3_acl_procedures)]; const struct rpc_version nfsacl_version3 = { .number = 3, - .nrprocs = sizeof(nfs3_acl_procedures)/ - sizeof(nfs3_acl_procedures[0]), + .nrprocs = ARRAY_SIZE(nfs3_acl_procedures), .procs = nfs3_acl_procedures, .counts = nfs3_acl_counts, }; -- cgit v1.2.3-59-g8ed1b From 499b4988109e91b76f231fb1b4f1e53ec3260686 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 12 May 2017 15:36:49 +0200 Subject: sunrpc: mark all struct rpc_procinfo instances as const struct rpc_procinfo contains function pointers, and marking it as constant avoids it being able to be used as an attach vector for code injections. Signed-off-by: Christoph Hellwig Acked-by: Trond Myklebust --- fs/lockd/clnt4xdr.c | 2 +- fs/lockd/clntxdr.c | 2 +- fs/lockd/mon.c | 2 +- fs/nfs/internal.h | 6 +++--- fs/nfs/mount_clnt.c | 4 ++-- fs/nfs/nfs2xdr.c | 2 +- fs/nfs/nfs3xdr.c | 4 ++-- fs/nfs/nfs4_fs.h | 2 +- fs/nfs/nfs4xdr.c | 2 +- fs/nfsd/nfs4callback.c | 2 +- include/linux/sunrpc/clnt.h | 4 ++-- include/linux/sunrpc/sched.h | 2 +- net/sunrpc/auth_gss/gss_rpc_upcall.c | 2 +- net/sunrpc/clnt.c | 4 ++-- net/sunrpc/rpcb_clnt.c | 19 ++++++++++--------- net/sunrpc/stats.c | 2 +- 16 files changed, 31 insertions(+), 30 deletions(-) diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c index 7c255d1d7c64..c349fc0f9b80 100644 --- a/fs/lockd/clnt4xdr.c +++ b/fs/lockd/clnt4xdr.c @@ -584,7 +584,7 @@ out: .p_name = #proc, \ } -static struct rpc_procinfo nlm4_procedures[] = { +static const struct rpc_procinfo nlm4_procedures[] = { PROC(TEST, testargs, testres), PROC(LOCK, lockargs, res), PROC(CANCEL, cancargs, res), diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c index 39500c5743a5..3b4724a6c4ee 100644 --- a/fs/lockd/clntxdr.c +++ b/fs/lockd/clntxdr.c @@ -582,7 +582,7 @@ out: .p_name = #proc, \ } -static struct rpc_procinfo nlm_procedures[] = { +static const struct rpc_procinfo nlm_procedures[] = { PROC(TEST, testargs, testres), PROC(LOCK, lockargs, res), PROC(CANCEL, cancargs, res), diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index fe4ec82764fe..9d8166c39c54 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -531,7 +531,7 @@ static int nsm_xdr_dec_stat(struct rpc_rqst *rqstp, #define SM_monres_sz 2 #define SM_unmonres_sz 1 -static struct rpc_procinfo nsm_procedures[] = { +static const struct rpc_procinfo nsm_procedures[] = { [NSMPROC_MON] = { .p_proc = NSMPROC_MON, .p_encode = nsm_xdr_enc_mon, diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index e9b4c3320e37..c21254924389 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -270,12 +270,12 @@ static inline bool nfs_match_open_context(const struct nfs_open_context *ctx1, } /* nfs2xdr.c */ -extern struct rpc_procinfo nfs_procedures[]; +extern const struct rpc_procinfo nfs_procedures[]; extern int nfs2_decode_dirent(struct xdr_stream *, struct nfs_entry *, int); /* nfs3xdr.c */ -extern struct rpc_procinfo nfs3_procedures[]; +extern const struct rpc_procinfo nfs3_procedures[]; extern int nfs3_decode_dirent(struct xdr_stream *, struct nfs_entry *, int); @@ -292,7 +292,7 @@ extern const u32 nfs41_maxgetdevinfo_overhead; /* nfs4proc.c */ #if IS_ENABLED(CONFIG_NFS_V4) -extern struct rpc_procinfo nfs4_procedures[]; +extern const struct rpc_procinfo nfs4_procedures[]; #endif #ifdef CONFIG_NFS_V4_SECURITY_LABEL diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index d25914aa8bf9..3efe946672be 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -466,7 +466,7 @@ static int mnt_xdr_dec_mountres3(struct rpc_rqst *req, return decode_auth_flavors(xdr, res); } -static struct rpc_procinfo mnt_procedures[] = { +static const struct rpc_procinfo mnt_procedures[] = { [MOUNTPROC_MNT] = { .p_proc = MOUNTPROC_MNT, .p_encode = mnt_xdr_enc_dirpath, @@ -485,7 +485,7 @@ static struct rpc_procinfo mnt_procedures[] = { }, }; -static struct rpc_procinfo mnt3_procedures[] = { +static const struct rpc_procinfo mnt3_procedures[] = { [MOUNTPROC3_MNT] = { .p_proc = MOUNTPROC3_MNT, .p_encode = mnt_xdr_enc_dirpath, diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index 16b4526299c1..c8a7e98c1371 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -1152,7 +1152,7 @@ static int nfs_stat_to_errno(enum nfs_stat status) .p_statidx = NFSPROC_##proc, \ .p_name = #proc, \ } -struct rpc_procinfo nfs_procedures[] = { +const struct rpc_procinfo nfs_procedures[] = { PROC(GETATTR, fhandle, attrstat, 1), PROC(SETATTR, sattrargs, attrstat, 0), PROC(LOOKUP, diropargs, diropres, 2), diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 85ff1187e637..670eddb3ae36 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -2554,7 +2554,7 @@ static int nfs3_stat_to_errno(enum nfs_stat status) .p_name = #proc, \ } -struct rpc_procinfo nfs3_procedures[] = { +const struct rpc_procinfo nfs3_procedures[] = { PROC(GETATTR, getattr, getattr, 1), PROC(SETATTR, setattr, setattr, 0), PROC(LOOKUP, lookup, lookup, 2), @@ -2587,7 +2587,7 @@ const struct rpc_version nfs_version3 = { }; #ifdef CONFIG_NFS_V3_ACL -static struct rpc_procinfo nfs3_acl_procedures[] = { +static const struct rpc_procinfo nfs3_acl_procedures[] = { [ACLPROC3_GETACL] = { .p_proc = ACLPROC3_GETACL, .p_encode = nfs3_xdr_enc_getacl3args, diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index af285cc27ccf..9b0cf3872722 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -493,7 +493,7 @@ static inline void nfs4_unregister_sysctl(void) #endif /* nfs4xdr.c */ -extern struct rpc_procinfo nfs4_procedures[]; +extern const struct rpc_procinfo nfs4_procedures[]; struct nfs4_mount_data; diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 40cf5529e65f..0f1f290c97cd 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -7594,7 +7594,7 @@ nfs4_stat_to_errno(int stat) .p_name = #proc, \ } -struct rpc_procinfo nfs4_procedures[] = { +const struct rpc_procinfo nfs4_procedures[] = { PROC(READ, enc_read, dec_read), PROC(WRITE, enc_write, dec_write), PROC(COMMIT, enc_commit, dec_commit), diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index afa961fe073c..ac10f78c0fb3 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -696,7 +696,7 @@ static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp, .p_name = #proc, \ } -static struct rpc_procinfo nfs4_cb_procedures[] = { +static const struct rpc_procinfo nfs4_cb_procedures[] = { PROC(CB_NULL, NULL, cb_null, cb_null), PROC(CB_RECALL, COMPOUND, cb_recall, cb_recall), #ifdef CONFIG_NFSD_PNFS diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index c75ba37151fe..55ef67bea06b 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -39,7 +39,7 @@ struct rpc_clnt { struct list_head cl_tasks; /* List of tasks */ spinlock_t cl_lock; /* spinlock */ struct rpc_xprt __rcu * cl_xprt; /* transport */ - struct rpc_procinfo * cl_procinfo; /* procedure info */ + const struct rpc_procinfo *cl_procinfo; /* procedure info */ u32 cl_prog, /* RPC program number */ cl_vers, /* RPC version number */ cl_maxproc; /* max procedure number */ @@ -87,7 +87,7 @@ struct rpc_program { struct rpc_version { u32 number; /* version number */ unsigned int nrprocs; /* number of procs */ - struct rpc_procinfo * procs; /* procedure array */ + const struct rpc_procinfo *procs; /* procedure array */ unsigned int *counts; /* call counts */ }; diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 7ba040c797ec..ed60253abd0a 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -22,7 +22,7 @@ */ struct rpc_procinfo; struct rpc_message { - struct rpc_procinfo * rpc_proc; /* Procedure information */ + const struct rpc_procinfo *rpc_proc; /* Procedure information */ void * rpc_argp; /* Arguments */ void * rpc_resp; /* Result */ struct rpc_cred * rpc_cred; /* Credentials */ diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index f8729b647605..46b295e4f2b8 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -63,7 +63,7 @@ enum { .p_name = #proc, \ } -static struct rpc_procinfo gssp_procedures[] = { +static const struct rpc_procinfo gssp_procedures[] = { PROC(INDICATE_MECHS, indicate_mechs), PROC(GET_CALL_CONTEXT, get_call_context), PROC(IMPORT_AND_CANON_NAME, import_and_canon_name), diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index f2d1f971247b..2e49d1f892b7 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1674,7 +1674,7 @@ call_allocate(struct rpc_task *task) unsigned int slack = task->tk_rqstp->rq_cred->cr_auth->au_cslack; struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; - struct rpc_procinfo *proc = task->tk_msg.rpc_proc; + const struct rpc_procinfo *proc = task->tk_msg.rpc_proc; int status; dprint_status(task); @@ -2489,7 +2489,7 @@ static int rpcproc_decode_null(struct rpc_rqst *rqstp, struct xdr_stream *xdr, return 0; } -static struct rpc_procinfo rpcproc_null = { +static const struct rpc_procinfo rpcproc_null = { .p_encode = rpcproc_encode_null, .p_decode = rpcproc_decode_null, }; diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 9d47b9d3bbee..ea0676f199c8 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -128,13 +128,13 @@ struct rpcbind_args { int r_status; }; -static struct rpc_procinfo rpcb_procedures2[]; -static struct rpc_procinfo rpcb_procedures3[]; -static struct rpc_procinfo rpcb_procedures4[]; +static const struct rpc_procinfo rpcb_procedures2[]; +static const struct rpc_procinfo rpcb_procedures3[]; +static const struct rpc_procinfo rpcb_procedures4[]; struct rpcb_info { u32 rpc_vers; - struct rpc_procinfo * rpc_proc; + const struct rpc_procinfo *rpc_proc; }; static const struct rpcb_info rpcb_next_version[]; @@ -620,7 +620,8 @@ int rpcb_v4_register(struct net *net, const u32 program, const u32 version, return -EAFNOSUPPORT; } -static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, struct rpcbind_args *map, struct rpc_procinfo *proc) +static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, + struct rpcbind_args *map, const struct rpc_procinfo *proc) { struct rpc_message msg = { .rpc_proc = proc, @@ -671,7 +672,7 @@ static struct rpc_clnt *rpcb_find_transport_owner(struct rpc_clnt *clnt) void rpcb_getport_async(struct rpc_task *task) { struct rpc_clnt *clnt; - struct rpc_procinfo *proc; + const struct rpc_procinfo *proc; u32 bind_version; struct rpc_xprt *xprt; struct rpc_clnt *rpcb_clnt; @@ -994,7 +995,7 @@ out_fail: * since the Linux kernel RPC code requires only these. */ -static struct rpc_procinfo rpcb_procedures2[] = { +static const struct rpc_procinfo rpcb_procedures2[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, .p_encode = rpcb_enc_mapping, @@ -1027,7 +1028,7 @@ static struct rpc_procinfo rpcb_procedures2[] = { }, }; -static struct rpc_procinfo rpcb_procedures3[] = { +static const struct rpc_procinfo rpcb_procedures3[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, .p_encode = rpcb_enc_getaddr, @@ -1060,7 +1061,7 @@ static struct rpc_procinfo rpcb_procedures3[] = { }, }; -static struct rpc_procinfo rpcb_procedures4[] = { +static const struct rpc_procinfo rpcb_procedures4[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, .p_encode = rpcb_enc_getaddr, diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c index 91c84d18bf9a..8b6c35ae1d57 100644 --- a/net/sunrpc/stats.c +++ b/net/sunrpc/stats.c @@ -191,7 +191,7 @@ void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats) EXPORT_SYMBOL_GPL(rpc_count_iostats); static void _print_name(struct seq_file *seq, unsigned int op, - struct rpc_procinfo *procs) + const struct rpc_procinfo *procs) { if (procs[op].p_name) seq_printf(seq, "\t%12s: ", procs[op].p_name); -- cgit v1.2.3-59-g8ed1b From 02be49f6b7afe3c4acb1bfdc76c0abe3f3a40f90 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 12 May 2017 15:58:06 +0200 Subject: nfsd4: const-ify nfs_cb_version4 Signed-off-by: Christoph Hellwig --- fs/nfsd/nfs4callback.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index ac10f78c0fb3..b45083c0f9ae 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -706,7 +706,7 @@ static const struct rpc_procinfo nfs4_cb_procedures[] = { }; static unsigned int nfs4_cb_counts[ARRAY_SIZE(nfs4_cb_procedures)]; -static struct rpc_version nfs_cb_version4 = { +static const struct rpc_version nfs_cb_version4 = { /* * Note on the callback rpc program version number: despite language in rfc * 5661 section 18.36.3 requiring servers to use 4 in this field, the -- cgit v1.2.3-59-g8ed1b From f7235b6bc56168302e1de8101a04b3d3061a0c82 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 17:59:13 +0200 Subject: nfsd: use named initializers in PROC() Signed-off-by: Christoph Hellwig --- fs/nfsd/nfs2acl.c | 22 +++++++++++----------- fs/nfsd/nfs3acl.c | 22 +++++++++++----------- fs/nfsd/nfs4proc.c | 10 +++++----- 3 files changed, 27 insertions(+), 27 deletions(-) diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 838f90f3f890..12933d07204c 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -345,17 +345,17 @@ static int nfsaclsvc_release_access(struct svc_rqst *rqstp, __be32 *p, #define nfsd3_voidres nfsd3_voidargs struct nfsd3_voidargs { int dummy; }; -#define PROC(name, argt, rest, relt, cache, respsize) \ - { (svc_procfunc) nfsacld_proc_##name, \ - (kxdrproc_t) nfsaclsvc_decode_##argt##args, \ - (kxdrproc_t) nfsaclsvc_encode_##rest##res, \ - (kxdrproc_t) nfsaclsvc_release_##relt, \ - sizeof(struct nfsd3_##argt##args), \ - sizeof(struct nfsd3_##rest##res), \ - 0, \ - cache, \ - respsize, \ - } +#define PROC(name, argt, rest, relt, cache, respsize) \ +{ \ + .pc_func = (svc_procfunc) nfsacld_proc_##name, \ + .pc_decode = (kxdrproc_t) nfsaclsvc_decode_##argt##args, \ + .pc_encode = (kxdrproc_t) nfsaclsvc_encode_##rest##res, \ + .pc_release = (kxdrproc_t) nfsaclsvc_release_##relt, \ + .pc_argsize = sizeof(struct nfsd3_##argt##args), \ + .pc_ressize = sizeof(struct nfsd3_##rest##res), \ + .pc_cachetype = cache, \ + .pc_xdrressize = respsize, \ +} #define ST 1 /* status*/ #define AT 21 /* attributes */ diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index dcb5f79076c0..db988a229b3a 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -237,17 +237,17 @@ static int nfs3svc_release_getacl(struct svc_rqst *rqstp, __be32 *p, #define nfsd3_voidres nfsd3_voidargs struct nfsd3_voidargs { int dummy; }; -#define PROC(name, argt, rest, relt, cache, respsize) \ - { (svc_procfunc) nfsd3_proc_##name, \ - (kxdrproc_t) nfs3svc_decode_##argt##args, \ - (kxdrproc_t) nfs3svc_encode_##rest##res, \ - (kxdrproc_t) nfs3svc_release_##relt, \ - sizeof(struct nfsd3_##argt##args), \ - sizeof(struct nfsd3_##rest##res), \ - 0, \ - cache, \ - respsize, \ - } +#define PROC(name, argt, rest, relt, cache, respsize) \ +{ \ + .pc_func = (svc_procfunc) nfsd3_proc_##name, \ + .pc_decode = (kxdrproc_t) nfs3svc_decode_##argt##args, \ + .pc_encode = (kxdrproc_t) nfs3svc_encode_##rest##res, \ + .pc_release = (kxdrproc_t) nfs3svc_release_##relt, \ + .pc_argsize = sizeof(struct nfsd3_##argt##args), \ + .pc_ressize = sizeof(struct nfsd3_##rest##res), \ + .pc_cachetype = cache, \ + .pc_xdrressize = respsize, \ +} #define ST 1 /* status*/ #define AT 21 /* attributes */ diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index c453a1998e00..695e17605b67 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1673,10 +1673,10 @@ static void svcxdr_init_encode(struct svc_rqst *rqstp, * COMPOUND call. */ static __be32 -nfsd4_proc_compound(struct svc_rqst *rqstp, - struct nfsd4_compoundargs *args, - struct nfsd4_compoundres *resp) +nfsd4_proc_compound(struct svc_rqst *rqstp, void *arg, void *res) { + struct nfsd4_compoundargs *args = arg; + struct nfsd4_compoundres *resp = res; struct nfsd4_op *op; struct nfsd4_operation *opdesc; struct nfsd4_compound_state *cstate = &resp->cstate; @@ -2518,7 +2518,7 @@ struct nfsd4_voidargs { int dummy; }; static struct svc_procedure nfsd_procedures4[2] = { [NFSPROC4_NULL] = { - .pc_func = (svc_procfunc) nfsd4_proc_null, + .pc_func = nfsd4_proc_null, .pc_encode = (kxdrproc_t) nfs4svc_encode_voidres, .pc_argsize = sizeof(struct nfsd4_voidargs), .pc_ressize = sizeof(struct nfsd4_voidres), @@ -2526,7 +2526,7 @@ static struct svc_procedure nfsd_procedures4[2] = { .pc_xdrressize = 1, }, [NFSPROC4_COMPOUND] = { - .pc_func = (svc_procfunc) nfsd4_proc_compound, + .pc_func = nfsd4_proc_compound, .pc_decode = (kxdrproc_t) nfs4svc_decode_compoundargs, .pc_encode = (kxdrproc_t) nfs4svc_encode_compoundres, .pc_argsize = sizeof(struct nfsd4_compoundargs), -- cgit v1.2.3-59-g8ed1b From 9482c9c15c29deb5e49ff475710f94dea0842328 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 18:03:06 +0200 Subject: nfsd: remove the unused PROC() macro in nfs3proc.c Signed-off-by: Christoph Hellwig --- fs/nfsd/nfs3proc.c | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 045c9081eabe..24e035190770 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -647,18 +647,6 @@ nfsd3_proc_commit(struct svc_rqst * rqstp, struct nfsd3_commitargs *argp, #define nfsd3_voidres nfsd3_voidargs struct nfsd3_voidargs { int dummy; }; -#define PROC(name, argt, rest, relt, cache, respsize) \ - { (svc_procfunc) nfsd3_proc_##name, \ - (kxdrproc_t) nfs3svc_decode_##argt##args, \ - (kxdrproc_t) nfs3svc_encode_##rest##res, \ - (kxdrproc_t) nfs3svc_release_##relt, \ - sizeof(struct nfsd3_##argt##args), \ - sizeof(struct nfsd3_##rest##res), \ - 0, \ - cache, \ - respsize, \ - } - #define ST 1 /* status*/ #define FH 17 /* filehandle with length */ #define AT 21 /* attributes */ -- cgit v1.2.3-59-g8ed1b From a6beb73272b4c0108e41bc7c7b5a447ae6c92863 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 17:35:49 +0200 Subject: sunrpc: properly type pc_func callbacks Drop the argp and resp arguments as they can trivially be derived from the rqstp argument. With that all functions now have the same prototype, and we can remove the unsafe casting to svc_procfunc as well as the svc_procfunc typedef itself. Signed-off-by: Christoph Hellwig --- fs/lockd/svc4proc.c | 118 ++++++++++++++++++++++------------- fs/lockd/svcproc.c | 118 ++++++++++++++++++++++------------- fs/nfs/callback_xdr.c | 7 ++- fs/nfsd/nfs2acl.c | 25 ++++---- fs/nfsd/nfs3acl.c | 15 ++--- fs/nfsd/nfs3proc.c | 151 ++++++++++++++++++++++++++------------------- fs/nfsd/nfs4proc.c | 9 +-- fs/nfsd/nfsproc.c | 104 +++++++++++++++++-------------- fs/nfsd/nfssvc.c | 2 +- include/linux/sunrpc/svc.h | 4 +- net/sunrpc/svc.c | 2 +- 11 files changed, 328 insertions(+), 227 deletions(-) diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 09c576f26c7b..3e4cba029d3d 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -62,7 +62,7 @@ no_locks: * NULL: Test for presence of service */ static __be32 -nlm4svc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) +nlm4svc_proc_null(struct svc_rqst *rqstp) { dprintk("lockd: NULL called\n"); return rpc_success; @@ -72,9 +72,9 @@ nlm4svc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) * TEST: Check for conflicting lock */ static __be32 -nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +__nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; __be32 rc = rpc_success; @@ -99,9 +99,15 @@ nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, } static __be32 -nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlm4svc_proc_test(struct svc_rqst *rqstp) { + return __nlm4svc_proc_test(rqstp, rqstp->rq_resp); +} + +static __be32 +__nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_res *resp) +{ + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; __be32 rc = rpc_success; @@ -141,9 +147,15 @@ nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, } static __be32 -nlm4svc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlm4svc_proc_lock(struct svc_rqst *rqstp) +{ + return __nlm4svc_proc_lock(rqstp, rqstp->rq_resp); +} + +static __be32 +__nlm4svc_proc_cancel(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; @@ -170,13 +182,19 @@ nlm4svc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp, return rpc_success; } +static __be32 +nlm4svc_proc_cancel(struct svc_rqst *rqstp) +{ + return __nlm4svc_proc_cancel(rqstp, rqstp->rq_resp); +} + /* * UNLOCK: release a lock */ static __be32 -nlm4svc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +__nlm4svc_proc_unlock(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; @@ -203,14 +221,21 @@ nlm4svc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp, return rpc_success; } +static __be32 +nlm4svc_proc_unlock(struct svc_rqst *rqstp) +{ + return __nlm4svc_proc_unlock(rqstp, rqstp->rq_resp); +} + /* * GRANTED: A server calls us to tell that a process' lock request * was granted */ static __be32 -nlm4svc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +__nlm4svc_proc_granted(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; + resp->cookie = argp->cookie; dprintk("lockd: GRANTED called\n"); @@ -219,6 +244,12 @@ nlm4svc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp, return rpc_success; } +static __be32 +nlm4svc_proc_granted(struct svc_rqst *rqstp) +{ + return __nlm4svc_proc_granted(rqstp, rqstp->rq_resp); +} + /* * This is the generic lockd callback for async RPC calls */ @@ -243,9 +274,10 @@ static const struct rpc_call_ops nlm4svc_callback_ops = { * because we send the callback before the reply proper. I hope this * doesn't break any clients. */ -static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args *argp, - __be32 (*func)(struct svc_rqst *, struct nlm_args *, struct nlm_res *)) +static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc, + __be32 (*func)(struct svc_rqst *, struct nlm_res *)) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_rqst *call; __be32 stat; @@ -261,7 +293,7 @@ static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args if (call == NULL) return rpc_system_err; - stat = func(rqstp, argp, &call->a_res); + stat = func(rqstp, &call->a_res); if (stat != 0) { nlmsvc_release_call(call); return stat; @@ -273,48 +305,44 @@ static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args return rpc_success; } -static __be32 nlm4svc_proc_test_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlm4svc_proc_test_msg(struct svc_rqst *rqstp) { dprintk("lockd: TEST_MSG called\n"); - return nlm4svc_callback(rqstp, NLMPROC_TEST_RES, argp, nlm4svc_proc_test); + return nlm4svc_callback(rqstp, NLMPROC_TEST_RES, __nlm4svc_proc_test); } -static __be32 nlm4svc_proc_lock_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlm4svc_proc_lock_msg(struct svc_rqst *rqstp) { dprintk("lockd: LOCK_MSG called\n"); - return nlm4svc_callback(rqstp, NLMPROC_LOCK_RES, argp, nlm4svc_proc_lock); + return nlm4svc_callback(rqstp, NLMPROC_LOCK_RES, __nlm4svc_proc_lock); } -static __be32 nlm4svc_proc_cancel_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlm4svc_proc_cancel_msg(struct svc_rqst *rqstp) { dprintk("lockd: CANCEL_MSG called\n"); - return nlm4svc_callback(rqstp, NLMPROC_CANCEL_RES, argp, nlm4svc_proc_cancel); + return nlm4svc_callback(rqstp, NLMPROC_CANCEL_RES, __nlm4svc_proc_cancel); } -static __be32 nlm4svc_proc_unlock_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlm4svc_proc_unlock_msg(struct svc_rqst *rqstp) { dprintk("lockd: UNLOCK_MSG called\n"); - return nlm4svc_callback(rqstp, NLMPROC_UNLOCK_RES, argp, nlm4svc_proc_unlock); + return nlm4svc_callback(rqstp, NLMPROC_UNLOCK_RES, __nlm4svc_proc_unlock); } -static __be32 nlm4svc_proc_granted_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlm4svc_proc_granted_msg(struct svc_rqst *rqstp) { dprintk("lockd: GRANTED_MSG called\n"); - return nlm4svc_callback(rqstp, NLMPROC_GRANTED_RES, argp, nlm4svc_proc_granted); + return nlm4svc_callback(rqstp, NLMPROC_GRANTED_RES, __nlm4svc_proc_granted); } /* * SHARE: create a DOS share or alter existing share. */ static __be32 -nlm4svc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlm4svc_proc_share(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; + struct nlm_res *resp = rqstp->rq_resp; struct nlm_host *host; struct nlm_file *file; @@ -345,9 +373,10 @@ nlm4svc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp, * UNSHARE: Release a DOS share. */ static __be32 -nlm4svc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlm4svc_proc_unshare(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; + struct nlm_res *resp = rqstp->rq_resp; struct nlm_host *host; struct nlm_file *file; @@ -378,22 +407,23 @@ nlm4svc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp, * NM_LOCK: Create an unmonitored lock */ static __be32 -nlm4svc_proc_nm_lock(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlm4svc_proc_nm_lock(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; + dprintk("lockd: NM_LOCK called\n"); argp->monitor = 0; /* just clean the monitor flag */ - return nlm4svc_proc_lock(rqstp, argp, resp); + return nlm4svc_proc_lock(rqstp); } /* * FREE_ALL: Release all locks and shares held by client */ static __be32 -nlm4svc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +nlm4svc_proc_free_all(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; /* Obtain client */ @@ -409,9 +439,10 @@ nlm4svc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp, * SM_NOTIFY: private callback from statd (not part of official NLM proto) */ static __be32 -nlm4svc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp, - void *resp) +nlm4svc_proc_sm_notify(struct svc_rqst *rqstp) { + struct nlm_reboot *argp = rqstp->rq_argp; + dprintk("lockd: SM_NOTIFY called\n"); if (!nlm_privileged_requester(rqstp)) { @@ -429,9 +460,10 @@ nlm4svc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp, * client sent a GRANTED_RES, let's remove the associated block */ static __be32 -nlm4svc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res *argp, - void *resp) +nlm4svc_proc_granted_res(struct svc_rqst *rqstp) { + struct nlm_res *argp = rqstp->rq_argp; + if (!nlmsvc_ops) return rpc_success; @@ -463,7 +495,7 @@ nlm4svc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res *argp, struct nlm_void { int dummy; }; #define PROC(name, xargt, xrest, argt, rest, respsize) \ - { .pc_func = (svc_procfunc) nlm4svc_proc_##name, \ + { .pc_func = nlm4svc_proc_##name, \ .pc_decode = (kxdrproc_t) nlm4svc_decode_##xargt, \ .pc_encode = (kxdrproc_t) nlm4svc_encode_##xrest, \ .pc_release = NULL, \ diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index fb26b9f522e7..3add50661fab 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -92,7 +92,7 @@ no_locks: * NULL: Test for presence of service */ static __be32 -nlmsvc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) +nlmsvc_proc_null(struct svc_rqst *rqstp) { dprintk("lockd: NULL called\n"); return rpc_success; @@ -102,9 +102,9 @@ nlmsvc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) * TEST: Check for conflicting lock */ static __be32 -nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +__nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; __be32 rc = rpc_success; @@ -130,9 +130,15 @@ nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, } static __be32 -nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlmsvc_proc_test(struct svc_rqst *rqstp) { + return __nlmsvc_proc_test(rqstp, rqstp->rq_resp); +} + +static __be32 +__nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_res *resp) +{ + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; __be32 rc = rpc_success; @@ -172,9 +178,15 @@ nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, } static __be32 -nlmsvc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlmsvc_proc_lock(struct svc_rqst *rqstp) +{ + return __nlmsvc_proc_lock(rqstp, rqstp->rq_resp); +} + +static __be32 +__nlmsvc_proc_cancel(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; struct net *net = SVC_NET(rqstp); @@ -202,13 +214,19 @@ nlmsvc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp, return rpc_success; } +static __be32 +nlmsvc_proc_cancel(struct svc_rqst *rqstp) +{ + return __nlmsvc_proc_cancel(rqstp, rqstp->rq_resp); +} + /* * UNLOCK: release a lock */ static __be32 -nlmsvc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +__nlmsvc_proc_unlock(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; struct net *net = SVC_NET(rqstp); @@ -236,14 +254,21 @@ nlmsvc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp, return rpc_success; } +static __be32 +nlmsvc_proc_unlock(struct svc_rqst *rqstp) +{ + return __nlmsvc_proc_unlock(rqstp, rqstp->rq_resp); +} + /* * GRANTED: A server calls us to tell that a process' lock request * was granted */ static __be32 -nlmsvc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +__nlmsvc_proc_granted(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; + resp->cookie = argp->cookie; dprintk("lockd: GRANTED called\n"); @@ -252,6 +277,12 @@ nlmsvc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp, return rpc_success; } +static __be32 +nlmsvc_proc_granted(struct svc_rqst *rqstp) +{ + return __nlmsvc_proc_granted(rqstp, rqstp->rq_resp); +} + /* * This is the generic lockd callback for async RPC calls */ @@ -284,9 +315,10 @@ static const struct rpc_call_ops nlmsvc_callback_ops = { * because we send the callback before the reply proper. I hope this * doesn't break any clients. */ -static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args *argp, - __be32 (*func)(struct svc_rqst *, struct nlm_args *, struct nlm_res *)) +static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc, + __be32 (*func)(struct svc_rqst *, struct nlm_res *)) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_rqst *call; __be32 stat; @@ -302,7 +334,7 @@ static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args if (call == NULL) return rpc_system_err; - stat = func(rqstp, argp, &call->a_res); + stat = func(rqstp, &call->a_res); if (stat != 0) { nlmsvc_release_call(call); return stat; @@ -314,50 +346,46 @@ static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args return rpc_success; } -static __be32 nlmsvc_proc_test_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlmsvc_proc_test_msg(struct svc_rqst *rqstp) { dprintk("lockd: TEST_MSG called\n"); - return nlmsvc_callback(rqstp, NLMPROC_TEST_RES, argp, nlmsvc_proc_test); + return nlmsvc_callback(rqstp, NLMPROC_TEST_RES, __nlmsvc_proc_test); } -static __be32 nlmsvc_proc_lock_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlmsvc_proc_lock_msg(struct svc_rqst *rqstp) { dprintk("lockd: LOCK_MSG called\n"); - return nlmsvc_callback(rqstp, NLMPROC_LOCK_RES, argp, nlmsvc_proc_lock); + return nlmsvc_callback(rqstp, NLMPROC_LOCK_RES, __nlmsvc_proc_lock); } -static __be32 nlmsvc_proc_cancel_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlmsvc_proc_cancel_msg(struct svc_rqst *rqstp) { dprintk("lockd: CANCEL_MSG called\n"); - return nlmsvc_callback(rqstp, NLMPROC_CANCEL_RES, argp, nlmsvc_proc_cancel); + return nlmsvc_callback(rqstp, NLMPROC_CANCEL_RES, __nlmsvc_proc_cancel); } static __be32 -nlmsvc_proc_unlock_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +nlmsvc_proc_unlock_msg(struct svc_rqst *rqstp) { dprintk("lockd: UNLOCK_MSG called\n"); - return nlmsvc_callback(rqstp, NLMPROC_UNLOCK_RES, argp, nlmsvc_proc_unlock); + return nlmsvc_callback(rqstp, NLMPROC_UNLOCK_RES, __nlmsvc_proc_unlock); } static __be32 -nlmsvc_proc_granted_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +nlmsvc_proc_granted_msg(struct svc_rqst *rqstp) { dprintk("lockd: GRANTED_MSG called\n"); - return nlmsvc_callback(rqstp, NLMPROC_GRANTED_RES, argp, nlmsvc_proc_granted); + return nlmsvc_callback(rqstp, NLMPROC_GRANTED_RES, __nlmsvc_proc_granted); } /* * SHARE: create a DOS share or alter existing share. */ static __be32 -nlmsvc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlmsvc_proc_share(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; + struct nlm_res *resp = rqstp->rq_resp; struct nlm_host *host; struct nlm_file *file; @@ -388,9 +416,10 @@ nlmsvc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp, * UNSHARE: Release a DOS share. */ static __be32 -nlmsvc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlmsvc_proc_unshare(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; + struct nlm_res *resp = rqstp->rq_resp; struct nlm_host *host; struct nlm_file *file; @@ -421,22 +450,23 @@ nlmsvc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp, * NM_LOCK: Create an unmonitored lock */ static __be32 -nlmsvc_proc_nm_lock(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlmsvc_proc_nm_lock(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; + dprintk("lockd: NM_LOCK called\n"); argp->monitor = 0; /* just clean the monitor flag */ - return nlmsvc_proc_lock(rqstp, argp, resp); + return nlmsvc_proc_lock(rqstp); } /* * FREE_ALL: Release all locks and shares held by client */ static __be32 -nlmsvc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +nlmsvc_proc_free_all(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; /* Obtain client */ @@ -452,9 +482,10 @@ nlmsvc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp, * SM_NOTIFY: private callback from statd (not part of official NLM proto) */ static __be32 -nlmsvc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp, - void *resp) +nlmsvc_proc_sm_notify(struct svc_rqst *rqstp) { + struct nlm_reboot *argp = rqstp->rq_argp; + dprintk("lockd: SM_NOTIFY called\n"); if (!nlm_privileged_requester(rqstp)) { @@ -472,9 +503,10 @@ nlmsvc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp, * client sent a GRANTED_RES, let's remove the associated block */ static __be32 -nlmsvc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res *argp, - void *resp) +nlmsvc_proc_granted_res(struct svc_rqst *rqstp) { + struct nlm_res *argp = rqstp->rq_argp; + if (!nlmsvc_ops) return rpc_success; @@ -505,7 +537,7 @@ nlmsvc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res *argp, struct nlm_void { int dummy; }; #define PROC(name, xargt, xrest, argt, rest, respsize) \ - { .pc_func = (svc_procfunc) nlmsvc_proc_##name, \ + { .pc_func = nlmsvc_proc_##name, \ .pc_decode = (kxdrproc_t) nlmsvc_decode_##xargt, \ .pc_encode = (kxdrproc_t) nlmsvc_encode_##xrest, \ .pc_release = NULL, \ diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 287c02202b25..5a14bdaa5986 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -53,7 +53,7 @@ struct callback_op { static struct callback_op callback_ops[]; -static __be32 nfs4_callback_null(struct svc_rqst *rqstp, void *argp, void *resp) +static __be32 nfs4_callback_null(struct svc_rqst *rqstp) { return htonl(NFS4_OK); } @@ -880,7 +880,7 @@ encode_hdr: /* * Decode, process and encode a COMPOUND */ -static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *resp) +static __be32 nfs4_callback_compound(struct svc_rqst *rqstp) { struct cb_compound_hdr_arg hdr_arg = { 0 }; struct cb_compound_hdr_res hdr_res = { NULL }; @@ -916,7 +916,8 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r while (status == 0 && nops != hdr_arg.nops) { status = process_op(nops, rqstp, &xdr_in, - argp, &xdr_out, resp, &cps); + rqstp->rq_argp, &xdr_out, rqstp->rq_resp, + &cps); nops++; } diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 12933d07204c..4b7f84fa1fa5 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -19,7 +19,7 @@ * NULL call. */ static __be32 -nfsacld_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) +nfsacld_proc_null(struct svc_rqst *rqstp) { return nfs_ok; } @@ -27,9 +27,10 @@ nfsacld_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) /* * Get the Access and/or Default ACL of a file. */ -static __be32 nfsacld_proc_getacl(struct svc_rqst * rqstp, - struct nfsd3_getaclargs *argp, struct nfsd3_getaclres *resp) +static __be32 nfsacld_proc_getacl(struct svc_rqst *rqstp) { + struct nfsd3_getaclargs *argp = rqstp->rq_argp; + struct nfsd3_getaclres *resp = rqstp->rq_resp; struct posix_acl *acl; struct inode *inode; svc_fh *fh; @@ -87,10 +88,10 @@ fail: /* * Set the Access and/or Default ACL of a file. */ -static __be32 nfsacld_proc_setacl(struct svc_rqst * rqstp, - struct nfsd3_setaclargs *argp, - struct nfsd_attrstat *resp) +static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp) { + struct nfsd3_setaclargs *argp = rqstp->rq_argp; + struct nfsd_attrstat *resp = rqstp->rq_resp; struct inode *inode; svc_fh *fh; __be32 nfserr = 0; @@ -141,9 +142,10 @@ out_errno: /* * Check file attributes */ -static __be32 nfsacld_proc_getattr(struct svc_rqst * rqstp, - struct nfsd_fhandle *argp, struct nfsd_attrstat *resp) +static __be32 nfsacld_proc_getattr(struct svc_rqst *rqstp) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + struct nfsd_attrstat *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: GETATTR %s\n", SVCFH_fmt(&argp->fh)); @@ -158,9 +160,10 @@ static __be32 nfsacld_proc_getattr(struct svc_rqst * rqstp, /* * Check file access */ -static __be32 nfsacld_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessargs *argp, - struct nfsd3_accessres *resp) +static __be32 nfsacld_proc_access(struct svc_rqst *rqstp) { + struct nfsd3_accessargs *argp = rqstp->rq_argp; + struct nfsd3_accessres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: ACCESS(2acl) %s 0x%x\n", @@ -347,7 +350,7 @@ struct nfsd3_voidargs { int dummy; }; #define PROC(name, argt, rest, relt, cache, respsize) \ { \ - .pc_func = (svc_procfunc) nfsacld_proc_##name, \ + .pc_func = nfsacld_proc_##name, \ .pc_decode = (kxdrproc_t) nfsaclsvc_decode_##argt##args, \ .pc_encode = (kxdrproc_t) nfsaclsvc_encode_##rest##res, \ .pc_release = (kxdrproc_t) nfsaclsvc_release_##relt, \ diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index db988a229b3a..5e42004035e0 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -18,7 +18,7 @@ * NULL call. */ static __be32 -nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) +nfsd3_proc_null(struct svc_rqst *rqstp) { return nfs_ok; } @@ -26,9 +26,10 @@ nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) /* * Get the Access and/or Default ACL of a file. */ -static __be32 nfsd3_proc_getacl(struct svc_rqst * rqstp, - struct nfsd3_getaclargs *argp, struct nfsd3_getaclres *resp) +static __be32 nfsd3_proc_getacl(struct svc_rqst *rqstp) { + struct nfsd3_getaclargs *argp = rqstp->rq_argp; + struct nfsd3_getaclres *resp = rqstp->rq_resp; struct posix_acl *acl; struct inode *inode; svc_fh *fh; @@ -80,10 +81,10 @@ fail: /* * Set the Access and/or Default ACL of a file. */ -static __be32 nfsd3_proc_setacl(struct svc_rqst * rqstp, - struct nfsd3_setaclargs *argp, - struct nfsd3_attrstat *resp) +static __be32 nfsd3_proc_setacl(struct svc_rqst *rqstp) { + struct nfsd3_setaclargs *argp = rqstp->rq_argp; + struct nfsd3_attrstat *resp = rqstp->rq_resp; struct inode *inode; svc_fh *fh; __be32 nfserr = 0; @@ -239,7 +240,7 @@ struct nfsd3_voidargs { int dummy; }; #define PROC(name, argt, rest, relt, cache, respsize) \ { \ - .pc_func = (svc_procfunc) nfsd3_proc_##name, \ + .pc_func = nfsd3_proc_##name, \ .pc_decode = (kxdrproc_t) nfs3svc_decode_##argt##args, \ .pc_encode = (kxdrproc_t) nfs3svc_encode_##rest##res, \ .pc_release = (kxdrproc_t) nfs3svc_release_##relt, \ diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 24e035190770..4a2bae07cfbf 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -31,7 +31,7 @@ static int nfs3_ftypes[] = { * NULL call. */ static __be32 -nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) +nfsd3_proc_null(struct svc_rqst *rqstp) { return nfs_ok; } @@ -40,9 +40,10 @@ nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) * Get a file's attributes */ static __be32 -nfsd3_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle *argp, - struct nfsd3_attrstat *resp) +nfsd3_proc_getattr(struct svc_rqst *rqstp) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + struct nfsd3_attrstat *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: GETATTR(3) %s\n", @@ -63,9 +64,10 @@ nfsd3_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle *argp, * Set a file's attributes */ static __be32 -nfsd3_proc_setattr(struct svc_rqst *rqstp, struct nfsd3_sattrargs *argp, - struct nfsd3_attrstat *resp) +nfsd3_proc_setattr(struct svc_rqst *rqstp) { + struct nfsd3_sattrargs *argp = rqstp->rq_argp; + struct nfsd3_attrstat *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: SETATTR(3) %s\n", @@ -81,9 +83,10 @@ nfsd3_proc_setattr(struct svc_rqst *rqstp, struct nfsd3_sattrargs *argp, * Look up a path name component */ static __be32 -nfsd3_proc_lookup(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp, - struct nfsd3_diropres *resp) +nfsd3_proc_lookup(struct svc_rqst *rqstp) { + struct nfsd3_diropargs *argp = rqstp->rq_argp; + struct nfsd3_diropres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: LOOKUP(3) %s %.*s\n", @@ -105,9 +108,10 @@ nfsd3_proc_lookup(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp, * Check file access */ static __be32 -nfsd3_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessargs *argp, - struct nfsd3_accessres *resp) +nfsd3_proc_access(struct svc_rqst *rqstp) { + struct nfsd3_accessargs *argp = rqstp->rq_argp; + struct nfsd3_accessres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: ACCESS(3) %s 0x%x\n", @@ -124,9 +128,10 @@ nfsd3_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessargs *argp, * Read a symlink. */ static __be32 -nfsd3_proc_readlink(struct svc_rqst *rqstp, struct nfsd3_readlinkargs *argp, - struct nfsd3_readlinkres *resp) +nfsd3_proc_readlink(struct svc_rqst *rqstp) { + struct nfsd3_readlinkargs *argp = rqstp->rq_argp; + struct nfsd3_readlinkres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: READLINK(3) %s\n", SVCFH_fmt(&argp->fh)); @@ -142,9 +147,10 @@ nfsd3_proc_readlink(struct svc_rqst *rqstp, struct nfsd3_readlinkargs *argp, * Read a portion of a file. */ static __be32 -nfsd3_proc_read(struct svc_rqst *rqstp, struct nfsd3_readargs *argp, - struct nfsd3_readres *resp) +nfsd3_proc_read(struct svc_rqst *rqstp) { + struct nfsd3_readargs *argp = rqstp->rq_argp; + struct nfsd3_readres *resp = rqstp->rq_resp; __be32 nfserr; u32 max_blocksize = svc_max_payload(rqstp); unsigned long cnt = min(argp->count, max_blocksize); @@ -179,9 +185,10 @@ nfsd3_proc_read(struct svc_rqst *rqstp, struct nfsd3_readargs *argp, * Write data to a file */ static __be32 -nfsd3_proc_write(struct svc_rqst *rqstp, struct nfsd3_writeargs *argp, - struct nfsd3_writeres *resp) +nfsd3_proc_write(struct svc_rqst *rqstp) { + struct nfsd3_writeargs *argp = rqstp->rq_argp; + struct nfsd3_writeres *resp = rqstp->rq_resp; __be32 nfserr; unsigned long cnt = argp->len; @@ -206,9 +213,10 @@ nfsd3_proc_write(struct svc_rqst *rqstp, struct nfsd3_writeargs *argp, * first reports about SunOS compatibility problems start to pour in... */ static __be32 -nfsd3_proc_create(struct svc_rqst *rqstp, struct nfsd3_createargs *argp, - struct nfsd3_diropres *resp) +nfsd3_proc_create(struct svc_rqst *rqstp) { + struct nfsd3_createargs *argp = rqstp->rq_argp; + struct nfsd3_diropres *resp = rqstp->rq_resp; svc_fh *dirfhp, *newfhp = NULL; struct iattr *attr; __be32 nfserr; @@ -243,9 +251,10 @@ nfsd3_proc_create(struct svc_rqst *rqstp, struct nfsd3_createargs *argp, * Make directory. This operation is not idempotent. */ static __be32 -nfsd3_proc_mkdir(struct svc_rqst *rqstp, struct nfsd3_createargs *argp, - struct nfsd3_diropres *resp) +nfsd3_proc_mkdir(struct svc_rqst *rqstp) { + struct nfsd3_createargs *argp = rqstp->rq_argp; + struct nfsd3_diropres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: MKDIR(3) %s %.*s\n", @@ -263,9 +272,10 @@ nfsd3_proc_mkdir(struct svc_rqst *rqstp, struct nfsd3_createargs *argp, } static __be32 -nfsd3_proc_symlink(struct svc_rqst *rqstp, struct nfsd3_symlinkargs *argp, - struct nfsd3_diropres *resp) +nfsd3_proc_symlink(struct svc_rqst *rqstp) { + struct nfsd3_symlinkargs *argp = rqstp->rq_argp; + struct nfsd3_diropres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: SYMLINK(3) %s %.*s -> %.*s\n", @@ -284,9 +294,10 @@ nfsd3_proc_symlink(struct svc_rqst *rqstp, struct nfsd3_symlinkargs *argp, * Make socket/fifo/device. */ static __be32 -nfsd3_proc_mknod(struct svc_rqst *rqstp, struct nfsd3_mknodargs *argp, - struct nfsd3_diropres *resp) +nfsd3_proc_mknod(struct svc_rqst *rqstp) { + struct nfsd3_mknodargs *argp = rqstp->rq_argp; + struct nfsd3_diropres *resp = rqstp->rq_resp; __be32 nfserr; int type; dev_t rdev = 0; @@ -321,9 +332,10 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp, struct nfsd3_mknodargs *argp, * Remove file/fifo/socket etc. */ static __be32 -nfsd3_proc_remove(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp, - struct nfsd3_attrstat *resp) +nfsd3_proc_remove(struct svc_rqst *rqstp) { + struct nfsd3_diropargs *argp = rqstp->rq_argp; + struct nfsd3_attrstat *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: REMOVE(3) %s %.*s\n", @@ -342,9 +354,10 @@ nfsd3_proc_remove(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp, * Remove a directory */ static __be32 -nfsd3_proc_rmdir(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp, - struct nfsd3_attrstat *resp) +nfsd3_proc_rmdir(struct svc_rqst *rqstp) { + struct nfsd3_diropargs *argp = rqstp->rq_argp; + struct nfsd3_attrstat *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: RMDIR(3) %s %.*s\n", @@ -359,9 +372,10 @@ nfsd3_proc_rmdir(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp, } static __be32 -nfsd3_proc_rename(struct svc_rqst *rqstp, struct nfsd3_renameargs *argp, - struct nfsd3_renameres *resp) +nfsd3_proc_rename(struct svc_rqst *rqstp) { + struct nfsd3_renameargs *argp = rqstp->rq_argp; + struct nfsd3_renameres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: RENAME(3) %s %.*s ->\n", @@ -381,9 +395,10 @@ nfsd3_proc_rename(struct svc_rqst *rqstp, struct nfsd3_renameargs *argp, } static __be32 -nfsd3_proc_link(struct svc_rqst *rqstp, struct nfsd3_linkargs *argp, - struct nfsd3_linkres *resp) +nfsd3_proc_link(struct svc_rqst *rqstp) { + struct nfsd3_linkargs *argp = rqstp->rq_argp; + struct nfsd3_linkres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: LINK(3) %s ->\n", @@ -404,9 +419,10 @@ nfsd3_proc_link(struct svc_rqst *rqstp, struct nfsd3_linkargs *argp, * Read a portion of a directory. */ static __be32 -nfsd3_proc_readdir(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp, - struct nfsd3_readdirres *resp) +nfsd3_proc_readdir(struct svc_rqst *rqstp) { + struct nfsd3_readdirargs *argp = rqstp->rq_argp; + struct nfsd3_readdirres *resp = rqstp->rq_resp; __be32 nfserr; int count; @@ -440,9 +456,10 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp, * For now, we choose to ignore the dircount parameter. */ static __be32 -nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp, - struct nfsd3_readdirres *resp) +nfsd3_proc_readdirplus(struct svc_rqst *rqstp) { + struct nfsd3_readdirargs *argp = rqstp->rq_argp; + struct nfsd3_readdirres *resp = rqstp->rq_resp; __be32 nfserr; int count = 0; loff_t offset; @@ -507,9 +524,10 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp, * Get file system stats */ static __be32 -nfsd3_proc_fsstat(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, - struct nfsd3_fsstatres *resp) +nfsd3_proc_fsstat(struct svc_rqst *rqstp) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + struct nfsd3_fsstatres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: FSSTAT(3) %s\n", @@ -524,9 +542,10 @@ nfsd3_proc_fsstat(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, * Get file system info */ static __be32 -nfsd3_proc_fsinfo(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, - struct nfsd3_fsinfores *resp) +nfsd3_proc_fsinfo(struct svc_rqst *rqstp) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + struct nfsd3_fsinfores *resp = rqstp->rq_resp; __be32 nfserr; u32 max_blocksize = svc_max_payload(rqstp); @@ -567,9 +586,10 @@ nfsd3_proc_fsinfo(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, * Get pathconf info for the specified file */ static __be32 -nfsd3_proc_pathconf(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, - struct nfsd3_pathconfres *resp) +nfsd3_proc_pathconf(struct svc_rqst *rqstp) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + struct nfsd3_pathconfres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: PATHCONF(3) %s\n", @@ -610,9 +630,10 @@ nfsd3_proc_pathconf(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, * Commit a file (range) to stable storage. */ static __be32 -nfsd3_proc_commit(struct svc_rqst * rqstp, struct nfsd3_commitargs *argp, - struct nfsd3_commitres *resp) +nfsd3_proc_commit(struct svc_rqst *rqstp) { + struct nfsd3_commitargs *argp = rqstp->rq_argp; + struct nfsd3_commitres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: COMMIT(3) %s %u@%Lu\n", @@ -655,7 +676,7 @@ struct nfsd3_voidargs { int dummy; }; static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_NULL] = { - .pc_func = (svc_procfunc) nfsd3_proc_null, + .pc_func = nfsd3_proc_null, .pc_encode = (kxdrproc_t) nfs3svc_encode_voidres, .pc_argsize = sizeof(struct nfsd3_voidargs), .pc_ressize = sizeof(struct nfsd3_voidres), @@ -663,7 +684,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST, }, [NFS3PROC_GETATTR] = { - .pc_func = (svc_procfunc) nfsd3_proc_getattr, + .pc_func = nfsd3_proc_getattr, .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_attrstatres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, @@ -673,7 +694,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+AT, }, [NFS3PROC_SETATTR] = { - .pc_func = (svc_procfunc) nfsd3_proc_setattr, + .pc_func = nfsd3_proc_setattr, .pc_decode = (kxdrproc_t) nfs3svc_decode_sattrargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, @@ -683,7 +704,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+WC, }, [NFS3PROC_LOOKUP] = { - .pc_func = (svc_procfunc) nfsd3_proc_lookup, + .pc_func = nfsd3_proc_lookup, .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_diropres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, @@ -693,7 +714,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+FH+pAT+pAT, }, [NFS3PROC_ACCESS] = { - .pc_func = (svc_procfunc) nfsd3_proc_access, + .pc_func = nfsd3_proc_access, .pc_decode = (kxdrproc_t) nfs3svc_decode_accessargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_accessres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, @@ -703,7 +724,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+pAT+1, }, [NFS3PROC_READLINK] = { - .pc_func = (svc_procfunc) nfsd3_proc_readlink, + .pc_func = nfsd3_proc_readlink, .pc_decode = (kxdrproc_t) nfs3svc_decode_readlinkargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readlinkres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, @@ -713,7 +734,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+pAT+1+NFS3_MAXPATHLEN/4, }, [NFS3PROC_READ] = { - .pc_func = (svc_procfunc) nfsd3_proc_read, + .pc_func = nfsd3_proc_read, .pc_decode = (kxdrproc_t) nfs3svc_decode_readargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, @@ -723,7 +744,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+pAT+4+NFSSVC_MAXBLKSIZE/4, }, [NFS3PROC_WRITE] = { - .pc_func = (svc_procfunc) nfsd3_proc_write, + .pc_func = nfsd3_proc_write, .pc_decode = (kxdrproc_t) nfs3svc_decode_writeargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_writeres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, @@ -733,7 +754,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+WC+4, }, [NFS3PROC_CREATE] = { - .pc_func = (svc_procfunc) nfsd3_proc_create, + .pc_func = nfsd3_proc_create, .pc_decode = (kxdrproc_t) nfs3svc_decode_createargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, @@ -743,7 +764,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+(1+FH+pAT)+WC, }, [NFS3PROC_MKDIR] = { - .pc_func = (svc_procfunc) nfsd3_proc_mkdir, + .pc_func = nfsd3_proc_mkdir, .pc_decode = (kxdrproc_t) nfs3svc_decode_mkdirargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, @@ -753,7 +774,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+(1+FH+pAT)+WC, }, [NFS3PROC_SYMLINK] = { - .pc_func = (svc_procfunc) nfsd3_proc_symlink, + .pc_func = nfsd3_proc_symlink, .pc_decode = (kxdrproc_t) nfs3svc_decode_symlinkargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, @@ -763,7 +784,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+(1+FH+pAT)+WC, }, [NFS3PROC_MKNOD] = { - .pc_func = (svc_procfunc) nfsd3_proc_mknod, + .pc_func = nfsd3_proc_mknod, .pc_decode = (kxdrproc_t) nfs3svc_decode_mknodargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, @@ -773,7 +794,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+(1+FH+pAT)+WC, }, [NFS3PROC_REMOVE] = { - .pc_func = (svc_procfunc) nfsd3_proc_remove, + .pc_func = nfsd3_proc_remove, .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, @@ -783,7 +804,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+WC, }, [NFS3PROC_RMDIR] = { - .pc_func = (svc_procfunc) nfsd3_proc_rmdir, + .pc_func = nfsd3_proc_rmdir, .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, @@ -793,7 +814,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+WC, }, [NFS3PROC_RENAME] = { - .pc_func = (svc_procfunc) nfsd3_proc_rename, + .pc_func = nfsd3_proc_rename, .pc_decode = (kxdrproc_t) nfs3svc_decode_renameargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_renameres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, @@ -803,7 +824,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+WC+WC, }, [NFS3PROC_LINK] = { - .pc_func = (svc_procfunc) nfsd3_proc_link, + .pc_func = nfsd3_proc_link, .pc_decode = (kxdrproc_t) nfs3svc_decode_linkargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_linkres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, @@ -813,7 +834,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+pAT+WC, }, [NFS3PROC_READDIR] = { - .pc_func = (svc_procfunc) nfsd3_proc_readdir, + .pc_func = nfsd3_proc_readdir, .pc_decode = (kxdrproc_t) nfs3svc_decode_readdirargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, @@ -822,7 +843,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_cachetype = RC_NOCACHE, }, [NFS3PROC_READDIRPLUS] = { - .pc_func = (svc_procfunc) nfsd3_proc_readdirplus, + .pc_func = nfsd3_proc_readdirplus, .pc_decode = (kxdrproc_t) nfs3svc_decode_readdirplusargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, @@ -831,7 +852,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_cachetype = RC_NOCACHE, }, [NFS3PROC_FSSTAT] = { - .pc_func = (svc_procfunc) nfsd3_proc_fsstat, + .pc_func = nfsd3_proc_fsstat, .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_fsstatres, .pc_argsize = sizeof(struct nfsd3_fhandleargs), @@ -840,7 +861,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+pAT+2*6+1, }, [NFS3PROC_FSINFO] = { - .pc_func = (svc_procfunc) nfsd3_proc_fsinfo, + .pc_func = nfsd3_proc_fsinfo, .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_fsinfores, .pc_argsize = sizeof(struct nfsd3_fhandleargs), @@ -849,7 +870,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+pAT+12, }, [NFS3PROC_PATHCONF] = { - .pc_func = (svc_procfunc) nfsd3_proc_pathconf, + .pc_func = nfsd3_proc_pathconf, .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_pathconfres, .pc_argsize = sizeof(struct nfsd3_fhandleargs), @@ -858,7 +879,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+pAT+6, }, [NFS3PROC_COMMIT] = { - .pc_func = (svc_procfunc) nfsd3_proc_commit, + .pc_func = nfsd3_proc_commit, .pc_decode = (kxdrproc_t) nfs3svc_decode_commitargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_commitres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 695e17605b67..7a0112bc3531 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1510,7 +1510,7 @@ out: * NULL call. */ static __be32 -nfsd4_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) +nfsd4_proc_null(struct svc_rqst *rqstp) { return nfs_ok; } @@ -1524,6 +1524,7 @@ static inline void nfsd4_increment_op_stats(u32 opnum) typedef __be32(*nfsd4op_func)(struct svc_rqst *, struct nfsd4_compound_state *, void *); typedef u32(*nfsd4op_rsize)(struct svc_rqst *, struct nfsd4_op *op); + typedef void(*stateid_setter)(struct nfsd4_compound_state *, void *); typedef void(*stateid_getter)(struct nfsd4_compound_state *, void *); @@ -1673,10 +1674,10 @@ static void svcxdr_init_encode(struct svc_rqst *rqstp, * COMPOUND call. */ static __be32 -nfsd4_proc_compound(struct svc_rqst *rqstp, void *arg, void *res) +nfsd4_proc_compound(struct svc_rqst *rqstp) { - struct nfsd4_compoundargs *args = arg; - struct nfsd4_compoundres *resp = res; + struct nfsd4_compoundargs *args = rqstp->rq_argp; + struct nfsd4_compoundres *resp = rqstp->rq_resp; struct nfsd4_op *op; struct nfsd4_operation *opdesc; struct nfsd4_compound_state *cstate = &resp->cstate; diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 03a7e9da4da0..448505b939db 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -17,7 +17,7 @@ typedef struct svc_buf svc_buf; static __be32 -nfsd_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) +nfsd_proc_null(struct svc_rqst *rqstp) { return nfs_ok; } @@ -39,9 +39,10 @@ nfsd_return_dirop(__be32 err, struct nfsd_diropres *resp) * N.B. After this call resp->fh needs an fh_put */ static __be32 -nfsd_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle *argp, - struct nfsd_attrstat *resp) +nfsd_proc_getattr(struct svc_rqst *rqstp) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + struct nfsd_attrstat *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: GETATTR %s\n", SVCFH_fmt(&argp->fh)); @@ -56,9 +57,10 @@ nfsd_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle *argp, * N.B. After this call resp->fh needs an fh_put */ static __be32 -nfsd_proc_setattr(struct svc_rqst *rqstp, struct nfsd_sattrargs *argp, - struct nfsd_attrstat *resp) +nfsd_proc_setattr(struct svc_rqst *rqstp) { + struct nfsd_sattrargs *argp = rqstp->rq_argp; + struct nfsd_attrstat *resp = rqstp->rq_resp; struct iattr *iap = &argp->attrs; struct svc_fh *fhp; __be32 nfserr; @@ -122,9 +124,10 @@ done: * N.B. After this call resp->fh needs an fh_put */ static __be32 -nfsd_proc_lookup(struct svc_rqst *rqstp, struct nfsd_diropargs *argp, - struct nfsd_diropres *resp) +nfsd_proc_lookup(struct svc_rqst *rqstp) { + struct nfsd_diropargs *argp = rqstp->rq_argp; + struct nfsd_diropres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: LOOKUP %s %.*s\n", @@ -142,9 +145,10 @@ nfsd_proc_lookup(struct svc_rqst *rqstp, struct nfsd_diropargs *argp, * Read a symlink. */ static __be32 -nfsd_proc_readlink(struct svc_rqst *rqstp, struct nfsd_readlinkargs *argp, - struct nfsd_readlinkres *resp) +nfsd_proc_readlink(struct svc_rqst *rqstp) { + struct nfsd_readlinkargs *argp = rqstp->rq_argp; + struct nfsd_readlinkres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: READLINK %s\n", SVCFH_fmt(&argp->fh)); @@ -162,9 +166,10 @@ nfsd_proc_readlink(struct svc_rqst *rqstp, struct nfsd_readlinkargs *argp, * N.B. After this call resp->fh needs an fh_put */ static __be32 -nfsd_proc_read(struct svc_rqst *rqstp, struct nfsd_readargs *argp, - struct nfsd_readres *resp) +nfsd_proc_read(struct svc_rqst *rqstp) { + struct nfsd_readargs *argp = rqstp->rq_argp; + struct nfsd_readres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: READ %s %d bytes at %d\n", @@ -200,9 +205,10 @@ nfsd_proc_read(struct svc_rqst *rqstp, struct nfsd_readargs *argp, * N.B. After this call resp->fh needs an fh_put */ static __be32 -nfsd_proc_write(struct svc_rqst *rqstp, struct nfsd_writeargs *argp, - struct nfsd_attrstat *resp) +nfsd_proc_write(struct svc_rqst *rqstp) { + struct nfsd_writeargs *argp = rqstp->rq_argp; + struct nfsd_attrstat *resp = rqstp->rq_resp; __be32 nfserr; unsigned long cnt = argp->len; @@ -222,9 +228,10 @@ nfsd_proc_write(struct svc_rqst *rqstp, struct nfsd_writeargs *argp, * N.B. After this call _both_ argp->fh and resp->fh need an fh_put */ static __be32 -nfsd_proc_create(struct svc_rqst *rqstp, struct nfsd_createargs *argp, - struct nfsd_diropres *resp) +nfsd_proc_create(struct svc_rqst *rqstp) { + struct nfsd_createargs *argp = rqstp->rq_argp; + struct nfsd_diropres *resp = rqstp->rq_resp; svc_fh *dirfhp = &argp->fh; svc_fh *newfhp = &resp->fh; struct iattr *attr = &argp->attrs; @@ -377,9 +384,9 @@ done: } static __be32 -nfsd_proc_remove(struct svc_rqst *rqstp, struct nfsd_diropargs *argp, - void *resp) +nfsd_proc_remove(struct svc_rqst *rqstp) { + struct nfsd_diropargs *argp = rqstp->rq_argp; __be32 nfserr; dprintk("nfsd: REMOVE %s %.*s\n", SVCFH_fmt(&argp->fh), @@ -392,9 +399,9 @@ nfsd_proc_remove(struct svc_rqst *rqstp, struct nfsd_diropargs *argp, } static __be32 -nfsd_proc_rename(struct svc_rqst *rqstp, struct nfsd_renameargs *argp, - void *resp) +nfsd_proc_rename(struct svc_rqst *rqstp) { + struct nfsd_renameargs *argp = rqstp->rq_argp; __be32 nfserr; dprintk("nfsd: RENAME %s %.*s -> \n", @@ -410,9 +417,9 @@ nfsd_proc_rename(struct svc_rqst *rqstp, struct nfsd_renameargs *argp, } static __be32 -nfsd_proc_link(struct svc_rqst *rqstp, struct nfsd_linkargs *argp, - void *resp) +nfsd_proc_link(struct svc_rqst *rqstp) { + struct nfsd_linkargs *argp = rqstp->rq_argp; __be32 nfserr; dprintk("nfsd: LINK %s ->\n", @@ -430,9 +437,9 @@ nfsd_proc_link(struct svc_rqst *rqstp, struct nfsd_linkargs *argp, } static __be32 -nfsd_proc_symlink(struct svc_rqst *rqstp, struct nfsd_symlinkargs *argp, - void *resp) +nfsd_proc_symlink(struct svc_rqst *rqstp) { + struct nfsd_symlinkargs *argp = rqstp->rq_argp; struct svc_fh newfh; __be32 nfserr; @@ -460,9 +467,10 @@ nfsd_proc_symlink(struct svc_rqst *rqstp, struct nfsd_symlinkargs *argp, * N.B. After this call resp->fh needs an fh_put */ static __be32 -nfsd_proc_mkdir(struct svc_rqst *rqstp, struct nfsd_createargs *argp, - struct nfsd_diropres *resp) +nfsd_proc_mkdir(struct svc_rqst *rqstp) { + struct nfsd_createargs *argp = rqstp->rq_argp; + struct nfsd_diropres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: MKDIR %s %.*s\n", SVCFH_fmt(&argp->fh), argp->len, argp->name); @@ -484,9 +492,9 @@ nfsd_proc_mkdir(struct svc_rqst *rqstp, struct nfsd_createargs *argp, * Remove a directory */ static __be32 -nfsd_proc_rmdir(struct svc_rqst *rqstp, struct nfsd_diropargs *argp, - void *resp) +nfsd_proc_rmdir(struct svc_rqst *rqstp) { + struct nfsd_diropargs *argp = rqstp->rq_argp; __be32 nfserr; dprintk("nfsd: RMDIR %s %.*s\n", SVCFH_fmt(&argp->fh), argp->len, argp->name); @@ -500,9 +508,10 @@ nfsd_proc_rmdir(struct svc_rqst *rqstp, struct nfsd_diropargs *argp, * Read a portion of a directory. */ static __be32 -nfsd_proc_readdir(struct svc_rqst *rqstp, struct nfsd_readdirargs *argp, - struct nfsd_readdirres *resp) +nfsd_proc_readdir(struct svc_rqst *rqstp) { + struct nfsd_readdirargs *argp = rqstp->rq_argp; + struct nfsd_readdirres *resp = rqstp->rq_resp; int count; __be32 nfserr; loff_t offset; @@ -540,9 +549,10 @@ nfsd_proc_readdir(struct svc_rqst *rqstp, struct nfsd_readdirargs *argp, * Get file system info */ static __be32 -nfsd_proc_statfs(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, - struct nfsd_statfsres *resp) +nfsd_proc_statfs(struct svc_rqst *rqstp) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + struct nfsd_statfsres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: STATFS %s\n", SVCFH_fmt(&argp->fh)); @@ -565,7 +575,7 @@ struct nfsd_void { int dummy; }; static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_NULL] = { - .pc_func = (svc_procfunc) nfsd_proc_null, + .pc_func = nfsd_proc_null, .pc_decode = (kxdrproc_t) nfssvc_decode_void, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_void), @@ -574,7 +584,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST, }, [NFSPROC_GETATTR] = { - .pc_func = (svc_procfunc) nfsd_proc_getattr, + .pc_func = nfsd_proc_getattr, .pc_decode = (kxdrproc_t) nfssvc_decode_fhandle, .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, .pc_release = (kxdrproc_t) nfssvc_release_fhandle, @@ -584,7 +594,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST+AT, }, [NFSPROC_SETATTR] = { - .pc_func = (svc_procfunc) nfsd_proc_setattr, + .pc_func = nfsd_proc_setattr, .pc_decode = (kxdrproc_t) nfssvc_decode_sattrargs, .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, .pc_release = (kxdrproc_t) nfssvc_release_fhandle, @@ -602,7 +612,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST, }, [NFSPROC_LOOKUP] = { - .pc_func = (svc_procfunc) nfsd_proc_lookup, + .pc_func = nfsd_proc_lookup, .pc_decode = (kxdrproc_t) nfssvc_decode_diropargs, .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, .pc_release = (kxdrproc_t) nfssvc_release_fhandle, @@ -612,7 +622,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST+FH+AT, }, [NFSPROC_READLINK] = { - .pc_func = (svc_procfunc) nfsd_proc_readlink, + .pc_func = nfsd_proc_readlink, .pc_decode = (kxdrproc_t) nfssvc_decode_readlinkargs, .pc_encode = (kxdrproc_t) nfssvc_encode_readlinkres, .pc_argsize = sizeof(struct nfsd_readlinkargs), @@ -621,7 +631,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST+1+NFS_MAXPATHLEN/4, }, [NFSPROC_READ] = { - .pc_func = (svc_procfunc) nfsd_proc_read, + .pc_func = nfsd_proc_read, .pc_decode = (kxdrproc_t) nfssvc_decode_readargs, .pc_encode = (kxdrproc_t) nfssvc_encode_readres, .pc_release = (kxdrproc_t) nfssvc_release_fhandle, @@ -639,7 +649,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST, }, [NFSPROC_WRITE] = { - .pc_func = (svc_procfunc) nfsd_proc_write, + .pc_func = nfsd_proc_write, .pc_decode = (kxdrproc_t) nfssvc_decode_writeargs, .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, .pc_release = (kxdrproc_t) nfssvc_release_fhandle, @@ -649,7 +659,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST+AT, }, [NFSPROC_CREATE] = { - .pc_func = (svc_procfunc) nfsd_proc_create, + .pc_func = nfsd_proc_create, .pc_decode = (kxdrproc_t) nfssvc_decode_createargs, .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, .pc_release = (kxdrproc_t) nfssvc_release_fhandle, @@ -659,7 +669,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST+FH+AT, }, [NFSPROC_REMOVE] = { - .pc_func = (svc_procfunc) nfsd_proc_remove, + .pc_func = nfsd_proc_remove, .pc_decode = (kxdrproc_t) nfssvc_decode_diropargs, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_diropargs), @@ -668,7 +678,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST, }, [NFSPROC_RENAME] = { - .pc_func = (svc_procfunc) nfsd_proc_rename, + .pc_func = nfsd_proc_rename, .pc_decode = (kxdrproc_t) nfssvc_decode_renameargs, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_renameargs), @@ -677,7 +687,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST, }, [NFSPROC_LINK] = { - .pc_func = (svc_procfunc) nfsd_proc_link, + .pc_func = nfsd_proc_link, .pc_decode = (kxdrproc_t) nfssvc_decode_linkargs, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_linkargs), @@ -686,7 +696,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST, }, [NFSPROC_SYMLINK] = { - .pc_func = (svc_procfunc) nfsd_proc_symlink, + .pc_func = nfsd_proc_symlink, .pc_decode = (kxdrproc_t) nfssvc_decode_symlinkargs, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_symlinkargs), @@ -695,7 +705,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST, }, [NFSPROC_MKDIR] = { - .pc_func = (svc_procfunc) nfsd_proc_mkdir, + .pc_func = nfsd_proc_mkdir, .pc_decode = (kxdrproc_t) nfssvc_decode_createargs, .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, .pc_release = (kxdrproc_t) nfssvc_release_fhandle, @@ -705,7 +715,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST+FH+AT, }, [NFSPROC_RMDIR] = { - .pc_func = (svc_procfunc) nfsd_proc_rmdir, + .pc_func = nfsd_proc_rmdir, .pc_decode = (kxdrproc_t) nfssvc_decode_diropargs, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_diropargs), @@ -714,7 +724,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST, }, [NFSPROC_READDIR] = { - .pc_func = (svc_procfunc) nfsd_proc_readdir, + .pc_func = nfsd_proc_readdir, .pc_decode = (kxdrproc_t) nfssvc_decode_readdirargs, .pc_encode = (kxdrproc_t) nfssvc_encode_readdirres, .pc_argsize = sizeof(struct nfsd_readdirargs), @@ -722,7 +732,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_cachetype = RC_NOCACHE, }, [NFSPROC_STATFS] = { - .pc_func = (svc_procfunc) nfsd_proc_statfs, + .pc_func = nfsd_proc_statfs, .pc_decode = (kxdrproc_t) nfssvc_decode_fhandle, .pc_encode = (kxdrproc_t) nfssvc_encode_statfsres, .pc_argsize = sizeof(struct nfsd_fhandle), diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 59979f0bbd4b..d64895fd8d25 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -827,7 +827,7 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) rqstp->rq_res.head[0].iov_len += sizeof(__be32); /* Now call the procedure handler, and encode NFS status. */ - nfserr = proc->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp); + nfserr = proc->pc_func(rqstp); nfserr = map_new_errors(rqstp->rq_vers, nfserr); if (nfserr == nfserr_dropit || test_bit(RQ_DROPME, &rqstp->rq_flags)) { dprintk("nfsd: Dropping request; may be revisited later\n"); diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 94631026f79c..5c222af2db41 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -418,9 +418,9 @@ struct svc_version { /* * RPC procedure info */ -typedef __be32 (*svc_procfunc)(struct svc_rqst *, void *argp, void *resp); struct svc_procedure { - svc_procfunc pc_func; /* process the request */ + /* process the request: */ + __be32 (*pc_func)(struct svc_rqst *); kxdrproc_t pc_decode; /* XDR decode args */ kxdrproc_t pc_encode; /* XDR encode result */ kxdrproc_t pc_release; /* XDR free result */ diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index bc0f5a0ecbdc..95335455ad38 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1281,7 +1281,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) if (xdr && !xdr(rqstp, argv->iov_base, rqstp->rq_argp)) goto err_garbage; - *statp = procp->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp); + *statp = procp->pc_func(rqstp); /* Encode reply */ if (*statp == rpc_drop_reply || -- cgit v1.2.3-59-g8ed1b From 8537488b5a2f33980e33f654b0a515304de2b267 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 18:48:24 +0200 Subject: sunrpc: properly type pc_release callbacks Drop the p and resp arguments as they are always NULL or can trivially be derived from the rqstp argument. With that all functions now have the same prototype, and we can remove the unsafe casting to kxdrproc_t. Signed-off-by: Christoph Hellwig --- fs/nfsd/nfs2acl.c | 22 +++++++++++----------- fs/nfsd/nfs3acl.c | 8 ++++---- fs/nfsd/nfs3proc.c | 36 ++++++++++++++++++------------------ fs/nfsd/nfs3xdr.c | 16 ++++++++-------- fs/nfsd/nfs4xdr.c | 4 +--- fs/nfsd/nfsproc.c | 14 +++++++------- fs/nfsd/nfsxdr.c | 8 ++++---- fs/nfsd/xdr.h | 2 +- fs/nfsd/xdr3.h | 6 ++---- fs/nfsd/xdr4.h | 2 +- include/linux/sunrpc/svc.h | 3 ++- net/sunrpc/svc.c | 8 ++++---- 12 files changed, 63 insertions(+), 66 deletions(-) diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 4b7f84fa1fa5..302441027f50 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -318,27 +318,27 @@ static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p, /* * XDR release functions */ -static int nfsaclsvc_release_getacl(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_getaclres *resp) +static void nfsaclsvc_release_getacl(struct svc_rqst *rqstp) { + struct nfsd3_getaclres *resp = rqstp->rq_resp; + fh_put(&resp->fh); posix_acl_release(resp->acl_access); posix_acl_release(resp->acl_default); - return 1; } -static int nfsaclsvc_release_attrstat(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_attrstat *resp) +static void nfsaclsvc_release_attrstat(struct svc_rqst *rqstp) { + struct nfsd_attrstat *resp = rqstp->rq_resp; + fh_put(&resp->fh); - return 1; } -static int nfsaclsvc_release_access(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_accessres *resp) +static void nfsaclsvc_release_access(struct svc_rqst *rqstp) { - fh_put(&resp->fh); - return 1; + struct nfsd3_accessres *resp = rqstp->rq_resp; + + fh_put(&resp->fh); } #define nfsaclsvc_decode_voidargs NULL @@ -353,7 +353,7 @@ struct nfsd3_voidargs { int dummy; }; .pc_func = nfsacld_proc_##name, \ .pc_decode = (kxdrproc_t) nfsaclsvc_decode_##argt##args, \ .pc_encode = (kxdrproc_t) nfsaclsvc_encode_##rest##res, \ - .pc_release = (kxdrproc_t) nfsaclsvc_release_##relt, \ + .pc_release = nfsaclsvc_release_##relt, \ .pc_argsize = sizeof(struct nfsd3_##argt##args), \ .pc_ressize = sizeof(struct nfsd3_##rest##res), \ .pc_cachetype = cache, \ diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 5e42004035e0..56cdff4e954c 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -223,13 +223,13 @@ static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p, /* * XDR release functions */ -static int nfs3svc_release_getacl(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_getaclres *resp) +static void nfs3svc_release_getacl(struct svc_rqst *rqstp) { + struct nfsd3_getaclres *resp = rqstp->rq_resp; + fh_put(&resp->fh); posix_acl_release(resp->acl_access); posix_acl_release(resp->acl_default); - return 1; } #define nfs3svc_decode_voidargs NULL @@ -243,7 +243,7 @@ struct nfsd3_voidargs { int dummy; }; .pc_func = nfsd3_proc_##name, \ .pc_decode = (kxdrproc_t) nfs3svc_decode_##argt##args, \ .pc_encode = (kxdrproc_t) nfs3svc_encode_##rest##res, \ - .pc_release = (kxdrproc_t) nfs3svc_release_##relt, \ + .pc_release = nfs3svc_release_##relt, \ .pc_argsize = sizeof(struct nfsd3_##argt##args), \ .pc_ressize = sizeof(struct nfsd3_##rest##res), \ .pc_cachetype = cache, \ diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 4a2bae07cfbf..f0cccc0768ce 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -687,7 +687,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_getattr, .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_attrstatres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_attrstatres), .pc_cachetype = RC_NOCACHE, @@ -697,7 +697,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_setattr, .pc_decode = (kxdrproc_t) nfs3svc_decode_sattrargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_sattrargs), .pc_ressize = sizeof(struct nfsd3_wccstatres), .pc_cachetype = RC_REPLBUFF, @@ -707,7 +707,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_lookup, .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_diropres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, + .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_diropargs), .pc_ressize = sizeof(struct nfsd3_diropres), .pc_cachetype = RC_NOCACHE, @@ -717,7 +717,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_access, .pc_decode = (kxdrproc_t) nfs3svc_decode_accessargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_accessres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_accessargs), .pc_ressize = sizeof(struct nfsd3_accessres), .pc_cachetype = RC_NOCACHE, @@ -727,7 +727,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_readlink, .pc_decode = (kxdrproc_t) nfs3svc_decode_readlinkargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readlinkres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readlinkargs), .pc_ressize = sizeof(struct nfsd3_readlinkres), .pc_cachetype = RC_NOCACHE, @@ -737,7 +737,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_read, .pc_decode = (kxdrproc_t) nfs3svc_decode_readargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readargs), .pc_ressize = sizeof(struct nfsd3_readres), .pc_cachetype = RC_NOCACHE, @@ -747,7 +747,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_write, .pc_decode = (kxdrproc_t) nfs3svc_decode_writeargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_writeres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_writeargs), .pc_ressize = sizeof(struct nfsd3_writeres), .pc_cachetype = RC_REPLBUFF, @@ -757,7 +757,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_create, .pc_decode = (kxdrproc_t) nfs3svc_decode_createargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, + .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_createargs), .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, @@ -767,7 +767,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_mkdir, .pc_decode = (kxdrproc_t) nfs3svc_decode_mkdirargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, + .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_mkdirargs), .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, @@ -777,7 +777,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_symlink, .pc_decode = (kxdrproc_t) nfs3svc_decode_symlinkargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, + .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_symlinkargs), .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, @@ -787,7 +787,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_mknod, .pc_decode = (kxdrproc_t) nfs3svc_decode_mknodargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, + .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_mknodargs), .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, @@ -797,7 +797,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_remove, .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_diropargs), .pc_ressize = sizeof(struct nfsd3_wccstatres), .pc_cachetype = RC_REPLBUFF, @@ -807,7 +807,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_rmdir, .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_diropargs), .pc_ressize = sizeof(struct nfsd3_wccstatres), .pc_cachetype = RC_REPLBUFF, @@ -817,7 +817,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_rename, .pc_decode = (kxdrproc_t) nfs3svc_decode_renameargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_renameres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, + .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_renameargs), .pc_ressize = sizeof(struct nfsd3_renameres), .pc_cachetype = RC_REPLBUFF, @@ -827,7 +827,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_link, .pc_decode = (kxdrproc_t) nfs3svc_decode_linkargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_linkres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, + .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_linkargs), .pc_ressize = sizeof(struct nfsd3_linkres), .pc_cachetype = RC_REPLBUFF, @@ -837,7 +837,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_readdir, .pc_decode = (kxdrproc_t) nfs3svc_decode_readdirargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readdirargs), .pc_ressize = sizeof(struct nfsd3_readdirres), .pc_cachetype = RC_NOCACHE, @@ -846,7 +846,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_readdirplus, .pc_decode = (kxdrproc_t) nfs3svc_decode_readdirplusargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readdirplusargs), .pc_ressize = sizeof(struct nfsd3_readdirres), .pc_cachetype = RC_NOCACHE, @@ -882,7 +882,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_commit, .pc_decode = (kxdrproc_t) nfs3svc_decode_commitargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_commitres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_commitargs), .pc_ressize = sizeof(struct nfsd3_commitres), .pc_cachetype = RC_NOCACHE, diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 12feac6ee2fd..7fd361a75287 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -1114,19 +1114,19 @@ nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p, /* * XDR release functions */ -int -nfs3svc_release_fhandle(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_attrstat *resp) +void +nfs3svc_release_fhandle(struct svc_rqst *rqstp) { + struct nfsd3_attrstat *resp = rqstp->rq_resp; + fh_put(&resp->fh); - return 1; } -int -nfs3svc_release_fhandle2(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_fhandle_pair *resp) +void +nfs3svc_release_fhandle2(struct svc_rqst *rqstp) { + struct nfsd3_fhandle_pair *resp = rqstp->rq_resp; + fh_put(&resp->fh1); fh_put(&resp->fh2); - return 1; } diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 26780d53a6f9..5aa847bdfc63 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -4543,9 +4543,8 @@ nfs4svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy) return xdr_ressize_check(rqstp, p); } -int nfsd4_release_compoundargs(void *rq, __be32 *p, void *resp) +void nfsd4_release_compoundargs(struct svc_rqst *rqstp) { - struct svc_rqst *rqstp = rq; struct nfsd4_compoundargs *args = rqstp->rq_argp; if (args->ops != args->iops) { @@ -4559,7 +4558,6 @@ int nfsd4_release_compoundargs(void *rq, __be32 *p, void *resp) args->to_free = tb->next; kfree(tb); } - return 1; } int diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 448505b939db..dc32e0f8480d 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -587,7 +587,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_func = nfsd_proc_getattr, .pc_decode = (kxdrproc_t) nfssvc_decode_fhandle, .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, - .pc_release = (kxdrproc_t) nfssvc_release_fhandle, + .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_NOCACHE, @@ -597,7 +597,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_func = nfsd_proc_setattr, .pc_decode = (kxdrproc_t) nfssvc_decode_sattrargs, .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, - .pc_release = (kxdrproc_t) nfssvc_release_fhandle, + .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_sattrargs), .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_REPLBUFF, @@ -615,7 +615,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_func = nfsd_proc_lookup, .pc_decode = (kxdrproc_t) nfssvc_decode_diropargs, .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, - .pc_release = (kxdrproc_t) nfssvc_release_fhandle, + .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_diropargs), .pc_ressize = sizeof(struct nfsd_diropres), .pc_cachetype = RC_NOCACHE, @@ -634,7 +634,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_func = nfsd_proc_read, .pc_decode = (kxdrproc_t) nfssvc_decode_readargs, .pc_encode = (kxdrproc_t) nfssvc_encode_readres, - .pc_release = (kxdrproc_t) nfssvc_release_fhandle, + .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_readargs), .pc_ressize = sizeof(struct nfsd_readres), .pc_cachetype = RC_NOCACHE, @@ -652,7 +652,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_func = nfsd_proc_write, .pc_decode = (kxdrproc_t) nfssvc_decode_writeargs, .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, - .pc_release = (kxdrproc_t) nfssvc_release_fhandle, + .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_writeargs), .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_REPLBUFF, @@ -662,7 +662,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_func = nfsd_proc_create, .pc_decode = (kxdrproc_t) nfssvc_decode_createargs, .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, - .pc_release = (kxdrproc_t) nfssvc_release_fhandle, + .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_createargs), .pc_ressize = sizeof(struct nfsd_diropres), .pc_cachetype = RC_REPLBUFF, @@ -708,7 +708,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_func = nfsd_proc_mkdir, .pc_decode = (kxdrproc_t) nfssvc_decode_createargs, .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, - .pc_release = (kxdrproc_t) nfssvc_release_fhandle, + .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_createargs), .pc_ressize = sizeof(struct nfsd_diropres), .pc_cachetype = RC_REPLBUFF, diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index 6a4947a3f4fa..de7b07ee489e 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -550,10 +550,10 @@ nfssvc_encode_entry(void *ccdv, const char *name, /* * XDR release functions */ -int -nfssvc_release_fhandle(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_fhandle *resp) +void +nfssvc_release_fhandle(struct svc_rqst *rqstp) { + struct nfsd_fhandle *resp = rqstp->rq_resp; + fh_put(&resp->fh); - return 1; } diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h index 4f0481d63804..2c21fa843fbf 100644 --- a/fs/nfsd/xdr.h +++ b/fs/nfsd/xdr.h @@ -164,7 +164,7 @@ int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *, struct nfsd_readdirres int nfssvc_encode_entry(void *, const char *name, int namlen, loff_t offset, u64 ino, unsigned int); -int nfssvc_release_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *); +void nfssvc_release_fhandle(struct svc_rqst *); /* Helper functions for NFSv2 ACL code */ __be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat); diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h index 335e04aaf7db..23fe456a223b 100644 --- a/fs/nfsd/xdr3.h +++ b/fs/nfsd/xdr3.h @@ -330,10 +330,8 @@ int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *, int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *, struct nfsd3_commitres *); -int nfs3svc_release_fhandle(struct svc_rqst *, __be32 *, - struct nfsd3_attrstat *); -int nfs3svc_release_fhandle2(struct svc_rqst *, __be32 *, - struct nfsd3_fhandle_pair *); +void nfs3svc_release_fhandle(struct svc_rqst *); +void nfs3svc_release_fhandle2(struct svc_rqst *); int nfs3svc_encode_entry(void *, const char *name, int namlen, loff_t offset, u64 ino, unsigned int); diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 8fda4abdf3b1..a158579d55a2 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -743,7 +743,7 @@ extern __be32 nfsd4_release_lockowner(struct svc_rqst *rqstp, struct nfsd4_compound_state *, struct nfsd4_release_lockowner *rlockowner); -extern int nfsd4_release_compoundargs(void *rq, __be32 *p, void *resp); +extern void nfsd4_release_compoundargs(struct svc_rqst *rqstp); extern __be32 nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *, struct nfsd4_delegreturn *dr); extern __be32 nfsd4_renew(struct svc_rqst *rqstp, diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 5c222af2db41..1381e1343640 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -423,7 +423,8 @@ struct svc_procedure { __be32 (*pc_func)(struct svc_rqst *); kxdrproc_t pc_decode; /* XDR decode args */ kxdrproc_t pc_encode; /* XDR encode result */ - kxdrproc_t pc_release; /* XDR free result */ + /* XDR free result: */ + void (*pc_release)(struct svc_rqst *); unsigned int pc_argsize; /* argument struct size */ unsigned int pc_ressize; /* result struct size */ unsigned int pc_count; /* call count */ diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 95335455ad38..4611cb7adc04 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1287,12 +1287,12 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) if (*statp == rpc_drop_reply || test_bit(RQ_DROPME, &rqstp->rq_flags)) { if (procp->pc_release) - procp->pc_release(rqstp, NULL, rqstp->rq_resp); + procp->pc_release(rqstp); goto dropit; } if (*statp == rpc_autherr_badcred) { if (procp->pc_release) - procp->pc_release(rqstp, NULL, rqstp->rq_resp); + procp->pc_release(rqstp); goto err_bad_auth; } if (*statp == rpc_success && @@ -1307,7 +1307,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) if (!versp->vs_dispatch(rqstp, statp)) { /* Release reply info */ if (procp->pc_release) - procp->pc_release(rqstp, NULL, rqstp->rq_resp); + procp->pc_release(rqstp); goto dropit; } } @@ -1318,7 +1318,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) /* Release reply info */ if (procp->pc_release) - procp->pc_release(rqstp, NULL, rqstp->rq_resp); + procp->pc_release(rqstp); if (procp->pc_encode == NULL) goto dropit; -- cgit v1.2.3-59-g8ed1b From 026fec7e7c4723b5f26a753bbcad69f68c8299d4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 19:01:48 +0200 Subject: sunrpc: properly type pc_decode callbacks Drop the argp argument as it can trivially be derived from the rqstp argument. With that all functions now have the same prototype, and we can remove the unsafe casting to kxdrproc_t. Signed-off-by: Christoph Hellwig --- fs/lockd/svc4proc.c | 2 +- fs/lockd/svcproc.c | 2 +- fs/lockd/xdr.c | 29 ++++++++++++------ fs/lockd/xdr4.c | 29 ++++++++++++------ fs/nfs/callback_xdr.c | 4 +-- fs/nfsd/nfs2acl.c | 21 +++++++------ fs/nfsd/nfs3acl.c | 11 +++---- fs/nfsd/nfs3proc.c | 42 +++++++++++++------------- fs/nfsd/nfs3xdr.c | 74 +++++++++++++++++++++++++++------------------- fs/nfsd/nfs4proc.c | 2 +- fs/nfsd/nfs4xdr.c | 4 ++- fs/nfsd/nfsproc.c | 36 +++++++++++----------- fs/nfsd/nfssvc.c | 5 ++-- fs/nfsd/nfsxdr.c | 53 ++++++++++++++++++++------------- fs/nfsd/xdr.h | 34 ++++++++------------- fs/nfsd/xdr3.h | 47 ++++++++++------------------- fs/nfsd/xdr4.h | 3 +- include/linux/lockd/xdr.h | 18 +++++------ include/linux/lockd/xdr4.h | 18 +++++------ include/linux/sunrpc/svc.h | 3 +- net/sunrpc/svc.c | 9 ++++-- 21 files changed, 237 insertions(+), 209 deletions(-) diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 3e4cba029d3d..804744f7528c 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -496,7 +496,7 @@ struct nlm_void { int dummy; }; #define PROC(name, xargt, xrest, argt, rest, respsize) \ { .pc_func = nlm4svc_proc_##name, \ - .pc_decode = (kxdrproc_t) nlm4svc_decode_##xargt, \ + .pc_decode = nlm4svc_decode_##xargt, \ .pc_encode = (kxdrproc_t) nlm4svc_encode_##xrest, \ .pc_release = NULL, \ .pc_argsize = sizeof(struct nlm_##argt), \ diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index 3add50661fab..204a698f7d41 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -538,7 +538,7 @@ struct nlm_void { int dummy; }; #define PROC(name, xargt, xrest, argt, rest, respsize) \ { .pc_func = nlmsvc_proc_##name, \ - .pc_decode = (kxdrproc_t) nlmsvc_decode_##xargt, \ + .pc_decode = nlmsvc_decode_##xargt, \ .pc_encode = (kxdrproc_t) nlmsvc_encode_##xrest, \ .pc_release = NULL, \ .pc_argsize = sizeof(struct nlm_##argt), \ diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c index 5b651daad518..b57af63fba56 100644 --- a/fs/lockd/xdr.c +++ b/fs/lockd/xdr.c @@ -182,8 +182,9 @@ nlm_encode_testres(__be32 *p, struct nlm_res *resp) * First, the server side XDR functions */ int -nlmsvc_decode_testargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlmsvc_decode_testargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!(p = nlm_decode_cookie(p, &argp->cookie))) @@ -207,8 +208,9 @@ nlmsvc_encode_testres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) } int -nlmsvc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlmsvc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!(p = nlm_decode_cookie(p, &argp->cookie))) @@ -227,8 +229,9 @@ nlmsvc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) } int -nlmsvc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlmsvc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!(p = nlm_decode_cookie(p, &argp->cookie))) @@ -243,8 +246,10 @@ nlmsvc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) } int -nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; + if (!(p = nlm_decode_cookie(p, &argp->cookie)) || !(p = nlm_decode_lock(p, &argp->lock))) return 0; @@ -253,8 +258,9 @@ nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) } int -nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; memset(lock, 0, sizeof(*lock)); @@ -293,8 +299,9 @@ nlmsvc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) } int -nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp) +nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; if (!(p = xdr_decode_string_inplace(p, &lock->caller, @@ -305,8 +312,10 @@ nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp) } int -nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp) +nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_reboot *argp = rqstp->rq_argp; + if (!(p = xdr_decode_string_inplace(p, &argp->mon, &argp->len, SM_MAXSTRLEN))) return 0; argp->state = ntohl(*p++); @@ -316,8 +325,10 @@ nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp) } int -nlmsvc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlmsvc_decode_res(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_argp; + if (!(p = nlm_decode_cookie(p, &resp->cookie))) return 0; resp->status = *p++; @@ -325,7 +336,7 @@ nlmsvc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) } int -nlmsvc_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nlmsvc_decode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_argsize_check(rqstp, p); } diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c index dfa4789cd460..46e18598a15c 100644 --- a/fs/lockd/xdr4.c +++ b/fs/lockd/xdr4.c @@ -179,8 +179,9 @@ nlm4_encode_testres(__be32 *p, struct nlm_res *resp) * First, the server side XDR functions */ int -nlm4svc_decode_testargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlm4svc_decode_testargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!(p = nlm4_decode_cookie(p, &argp->cookie))) @@ -204,8 +205,9 @@ nlm4svc_encode_testres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) } int -nlm4svc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlm4svc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!(p = nlm4_decode_cookie(p, &argp->cookie))) @@ -224,8 +226,9 @@ nlm4svc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) } int -nlm4svc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlm4svc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!(p = nlm4_decode_cookie(p, &argp->cookie))) @@ -240,8 +243,10 @@ nlm4svc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) } int -nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; + if (!(p = nlm4_decode_cookie(p, &argp->cookie)) || !(p = nlm4_decode_lock(p, &argp->lock))) return 0; @@ -250,8 +255,9 @@ nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) } int -nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; memset(lock, 0, sizeof(*lock)); @@ -290,8 +296,9 @@ nlm4svc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) } int -nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp) +nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; if (!(p = xdr_decode_string_inplace(p, &lock->caller, @@ -302,8 +309,10 @@ nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp) } int -nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp) +nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_reboot *argp = rqstp->rq_argp; + if (!(p = xdr_decode_string_inplace(p, &argp->mon, &argp->len, SM_MAXSTRLEN))) return 0; argp->state = ntohl(*p++); @@ -313,8 +322,10 @@ nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp } int -nlm4svc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlm4svc_decode_res(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_argp; + if (!(p = nlm4_decode_cookie(p, &resp->cookie))) return 0; resp->status = *p++; @@ -322,7 +333,7 @@ nlm4svc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) } int -nlm4svc_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nlm4svc_decode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_argsize_check(rqstp, p); } diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 5a14bdaa5986..23ecbf7a40c1 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -58,7 +58,7 @@ static __be32 nfs4_callback_null(struct svc_rqst *rqstp) return htonl(NFS4_OK); } -static int nfs4_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +static int nfs4_decode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_argsize_check(rqstp, p); } @@ -998,7 +998,7 @@ static struct callback_op callback_ops[] = { static struct svc_procedure nfs4_callback_procedures1[] = { [CB_NULL] = { .pc_func = nfs4_callback_null, - .pc_decode = (kxdrproc_t)nfs4_decode_void, + .pc_decode = nfs4_decode_void, .pc_encode = (kxdrproc_t)nfs4_encode_void, .pc_xdrressize = 1, }, diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 302441027f50..bcfdaa83ee6c 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -182,9 +182,10 @@ static __be32 nfsacld_proc_access(struct svc_rqst *rqstp) /* * XDR decode functions */ -static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_getaclargs *argp) +static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_getaclargs *argp = rqstp->rq_argp; + p = nfs2svc_decode_fh(p, &argp->fh); if (!p) return 0; @@ -194,9 +195,9 @@ static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p, } -static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_setaclargs *argp) +static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_setaclargs *argp = rqstp->rq_argp; struct kvec *head = rqstp->rq_arg.head; unsigned int base; int n; @@ -220,18 +221,20 @@ static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p, return (n > 0); } -static int nfsaclsvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_fhandle *argp) +static int nfsaclsvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + p = nfs2svc_decode_fh(p, &argp->fh); if (!p) return 0; return xdr_argsize_check(rqstp, p); } -static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_accessargs *argp) +static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_accessargs *argp = rqstp->rq_argp; + p = nfs2svc_decode_fh(p, &argp->fh); if (!p) return 0; @@ -351,7 +354,7 @@ struct nfsd3_voidargs { int dummy; }; #define PROC(name, argt, rest, relt, cache, respsize) \ { \ .pc_func = nfsacld_proc_##name, \ - .pc_decode = (kxdrproc_t) nfsaclsvc_decode_##argt##args, \ + .pc_decode = nfsaclsvc_decode_##argt##args, \ .pc_encode = (kxdrproc_t) nfsaclsvc_encode_##rest##res, \ .pc_release = nfsaclsvc_release_##relt, \ .pc_argsize = sizeof(struct nfsd3_##argt##args), \ diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 56cdff4e954c..4e68d6b5f409 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -124,9 +124,10 @@ out: /* * XDR decode functions */ -static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_getaclargs *args) +static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_getaclargs *args = rqstp->rq_argp; + p = nfs3svc_decode_fh(p, &args->fh); if (!p) return 0; @@ -136,9 +137,9 @@ static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p, } -static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_setaclargs *args) +static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_setaclargs *args = rqstp->rq_argp; struct kvec *head = rqstp->rq_arg.head; unsigned int base; int n; @@ -241,7 +242,7 @@ struct nfsd3_voidargs { int dummy; }; #define PROC(name, argt, rest, relt, cache, respsize) \ { \ .pc_func = nfsd3_proc_##name, \ - .pc_decode = (kxdrproc_t) nfs3svc_decode_##argt##args, \ + .pc_decode = nfs3svc_decode_##argt##args, \ .pc_encode = (kxdrproc_t) nfs3svc_encode_##rest##res, \ .pc_release = nfs3svc_release_##relt, \ .pc_argsize = sizeof(struct nfsd3_##argt##args), \ diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index f0cccc0768ce..ed83e8a9e7b4 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -685,7 +685,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_GETATTR] = { .pc_func = nfsd3_proc_getattr, - .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs, + .pc_decode = nfs3svc_decode_fhandleargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_attrstatres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_fhandleargs), @@ -695,7 +695,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_SETATTR] = { .pc_func = nfsd3_proc_setattr, - .pc_decode = (kxdrproc_t) nfs3svc_decode_sattrargs, + .pc_decode = nfs3svc_decode_sattrargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_sattrargs), @@ -705,7 +705,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_LOOKUP] = { .pc_func = nfsd3_proc_lookup, - .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs, + .pc_decode = nfs3svc_decode_diropargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_diropres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_diropargs), @@ -715,7 +715,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_ACCESS] = { .pc_func = nfsd3_proc_access, - .pc_decode = (kxdrproc_t) nfs3svc_decode_accessargs, + .pc_decode = nfs3svc_decode_accessargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_accessres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_accessargs), @@ -725,7 +725,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_READLINK] = { .pc_func = nfsd3_proc_readlink, - .pc_decode = (kxdrproc_t) nfs3svc_decode_readlinkargs, + .pc_decode = nfs3svc_decode_readlinkargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readlinkres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readlinkargs), @@ -735,7 +735,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_READ] = { .pc_func = nfsd3_proc_read, - .pc_decode = (kxdrproc_t) nfs3svc_decode_readargs, + .pc_decode = nfs3svc_decode_readargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readargs), @@ -745,7 +745,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_WRITE] = { .pc_func = nfsd3_proc_write, - .pc_decode = (kxdrproc_t) nfs3svc_decode_writeargs, + .pc_decode = nfs3svc_decode_writeargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_writeres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_writeargs), @@ -755,7 +755,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_CREATE] = { .pc_func = nfsd3_proc_create, - .pc_decode = (kxdrproc_t) nfs3svc_decode_createargs, + .pc_decode = nfs3svc_decode_createargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_createargs), @@ -765,7 +765,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_MKDIR] = { .pc_func = nfsd3_proc_mkdir, - .pc_decode = (kxdrproc_t) nfs3svc_decode_mkdirargs, + .pc_decode = nfs3svc_decode_mkdirargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_mkdirargs), @@ -775,7 +775,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_SYMLINK] = { .pc_func = nfsd3_proc_symlink, - .pc_decode = (kxdrproc_t) nfs3svc_decode_symlinkargs, + .pc_decode = nfs3svc_decode_symlinkargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_symlinkargs), @@ -785,7 +785,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_MKNOD] = { .pc_func = nfsd3_proc_mknod, - .pc_decode = (kxdrproc_t) nfs3svc_decode_mknodargs, + .pc_decode = nfs3svc_decode_mknodargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_mknodargs), @@ -795,7 +795,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_REMOVE] = { .pc_func = nfsd3_proc_remove, - .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs, + .pc_decode = nfs3svc_decode_diropargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_diropargs), @@ -805,7 +805,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_RMDIR] = { .pc_func = nfsd3_proc_rmdir, - .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs, + .pc_decode = nfs3svc_decode_diropargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_diropargs), @@ -815,7 +815,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_RENAME] = { .pc_func = nfsd3_proc_rename, - .pc_decode = (kxdrproc_t) nfs3svc_decode_renameargs, + .pc_decode = nfs3svc_decode_renameargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_renameres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_renameargs), @@ -825,7 +825,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_LINK] = { .pc_func = nfsd3_proc_link, - .pc_decode = (kxdrproc_t) nfs3svc_decode_linkargs, + .pc_decode = nfs3svc_decode_linkargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_linkres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_linkargs), @@ -835,7 +835,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_READDIR] = { .pc_func = nfsd3_proc_readdir, - .pc_decode = (kxdrproc_t) nfs3svc_decode_readdirargs, + .pc_decode = nfs3svc_decode_readdirargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readdirargs), @@ -844,7 +844,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_READDIRPLUS] = { .pc_func = nfsd3_proc_readdirplus, - .pc_decode = (kxdrproc_t) nfs3svc_decode_readdirplusargs, + .pc_decode = nfs3svc_decode_readdirplusargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readdirplusargs), @@ -853,7 +853,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_FSSTAT] = { .pc_func = nfsd3_proc_fsstat, - .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs, + .pc_decode = nfs3svc_decode_fhandleargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_fsstatres, .pc_argsize = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_fsstatres), @@ -862,7 +862,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_FSINFO] = { .pc_func = nfsd3_proc_fsinfo, - .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs, + .pc_decode = nfs3svc_decode_fhandleargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_fsinfores, .pc_argsize = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_fsinfores), @@ -871,7 +871,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_PATHCONF] = { .pc_func = nfsd3_proc_pathconf, - .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs, + .pc_decode = nfs3svc_decode_fhandleargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_pathconfres, .pc_argsize = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_pathconfres), @@ -880,7 +880,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_COMMIT] = { .pc_func = nfsd3_proc_commit, - .pc_decode = (kxdrproc_t) nfs3svc_decode_commitargs, + .pc_decode = nfs3svc_decode_commitargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_commitres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_commitargs), diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 7fd361a75287..be8bf8af9917 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -273,8 +273,10 @@ void fill_post_wcc(struct svc_fh *fhp) * XDR decode functions */ int -nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *args) +nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_fhandle *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; @@ -282,9 +284,10 @@ nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *a } int -nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_sattrargs *args) +nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_sattrargs *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; @@ -300,9 +303,10 @@ nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_diropargs *args) +nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_diropargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->fh)) || !(p = decode_filename(p, &args->name, &args->len))) return 0; @@ -311,9 +315,10 @@ nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_accessargs *args) +nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_accessargs *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; @@ -323,9 +328,9 @@ nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_readargs *args) +nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_readargs *args = rqstp->rq_argp; unsigned int len; int v; u32 max_blocksize = svc_max_payload(rqstp); @@ -356,9 +361,9 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_writeargs *args) +nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_writeargs *args = rqstp->rq_argp; unsigned int len, v, hdr, dlen; u32 max_blocksize = svc_max_payload(rqstp); struct kvec *head = rqstp->rq_arg.head; @@ -416,9 +421,10 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_createargs *args) +nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_createargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->fh)) || !(p = decode_filename(p, &args->name, &args->len))) return 0; @@ -438,10 +444,12 @@ nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p, return xdr_argsize_check(rqstp, p); } + int -nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_createargs *args) +nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_createargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->fh)) || !(p = decode_filename(p, &args->name, &args->len))) return 0; @@ -451,9 +459,9 @@ nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_symlinkargs *args) +nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_symlinkargs *args = rqstp->rq_argp; unsigned int len, avail; char *old, *new; struct kvec *vec; @@ -503,9 +511,10 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_mknodargs *args) +nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_mknodargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->fh)) || !(p = decode_filename(p, &args->name, &args->len))) return 0; @@ -525,9 +534,10 @@ nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_renameargs *args) +nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_renameargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->ffh)) || !(p = decode_filename(p, &args->fname, &args->flen)) || !(p = decode_fh(p, &args->tfh)) @@ -538,9 +548,10 @@ nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_readlinkargs *args) +nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_readlinkargs *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; @@ -552,9 +563,10 @@ nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_linkargs *args) +nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_linkargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->ffh)) || !(p = decode_fh(p, &args->tfh)) || !(p = decode_filename(p, &args->tname, &args->tlen))) @@ -564,9 +576,9 @@ nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_readdirargs *args) +nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_readdirargs *args = rqstp->rq_argp; p = decode_fh(p, &args->fh); if (!p) return 0; @@ -585,9 +597,9 @@ nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_readdirargs *args) +nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_readdirargs *args = rqstp->rq_argp; int len; u32 max_blocksize = svc_max_payload(rqstp); @@ -613,9 +625,9 @@ nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_commitargs *args) +nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_commitargs *args = rqstp->rq_argp; p = decode_fh(p, &args->fh); if (!p) return 0; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 7a0112bc3531..6ff434b77a9e 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -2528,7 +2528,7 @@ static struct svc_procedure nfsd_procedures4[2] = { }, [NFSPROC4_COMPOUND] = { .pc_func = nfsd4_proc_compound, - .pc_decode = (kxdrproc_t) nfs4svc_decode_compoundargs, + .pc_decode = nfs4svc_decode_compoundargs, .pc_encode = (kxdrproc_t) nfs4svc_encode_compoundres, .pc_argsize = sizeof(struct nfsd4_compoundargs), .pc_ressize = sizeof(struct nfsd4_compoundres), diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 5aa847bdfc63..3a7e117bd11e 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -4561,8 +4561,10 @@ void nfsd4_release_compoundargs(struct svc_rqst *rqstp) } int -nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compoundargs *args) +nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd4_compoundargs *args = rqstp->rq_argp; + if (rqstp->rq_arg.head[0].iov_len % 4) { /* client is nuts */ dprintk("%s: compound not properly padded! (peeraddr=%pISc xid=0x%x)", diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index dc32e0f8480d..d351d0ef6d34 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -576,7 +576,7 @@ struct nfsd_void { int dummy; }; static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_NULL] = { .pc_func = nfsd_proc_null, - .pc_decode = (kxdrproc_t) nfssvc_decode_void, + .pc_decode = nfssvc_decode_void, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_void), .pc_ressize = sizeof(struct nfsd_void), @@ -585,7 +585,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_GETATTR] = { .pc_func = nfsd_proc_getattr, - .pc_decode = (kxdrproc_t) nfssvc_decode_fhandle, + .pc_decode = nfssvc_decode_fhandle, .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_fhandle), @@ -595,7 +595,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_SETATTR] = { .pc_func = nfsd_proc_setattr, - .pc_decode = (kxdrproc_t) nfssvc_decode_sattrargs, + .pc_decode = nfssvc_decode_sattrargs, .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_sattrargs), @@ -604,7 +604,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST+AT, }, [NFSPROC_ROOT] = { - .pc_decode = (kxdrproc_t) nfssvc_decode_void, + .pc_decode = nfssvc_decode_void, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_void), .pc_ressize = sizeof(struct nfsd_void), @@ -613,7 +613,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_LOOKUP] = { .pc_func = nfsd_proc_lookup, - .pc_decode = (kxdrproc_t) nfssvc_decode_diropargs, + .pc_decode = nfssvc_decode_diropargs, .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_diropargs), @@ -623,7 +623,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_READLINK] = { .pc_func = nfsd_proc_readlink, - .pc_decode = (kxdrproc_t) nfssvc_decode_readlinkargs, + .pc_decode = nfssvc_decode_readlinkargs, .pc_encode = (kxdrproc_t) nfssvc_encode_readlinkres, .pc_argsize = sizeof(struct nfsd_readlinkargs), .pc_ressize = sizeof(struct nfsd_readlinkres), @@ -632,7 +632,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_READ] = { .pc_func = nfsd_proc_read, - .pc_decode = (kxdrproc_t) nfssvc_decode_readargs, + .pc_decode = nfssvc_decode_readargs, .pc_encode = (kxdrproc_t) nfssvc_encode_readres, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_readargs), @@ -641,7 +641,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST+AT+1+NFSSVC_MAXBLKSIZE_V2/4, }, [NFSPROC_WRITECACHE] = { - .pc_decode = (kxdrproc_t) nfssvc_decode_void, + .pc_decode = nfssvc_decode_void, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_void), .pc_ressize = sizeof(struct nfsd_void), @@ -650,7 +650,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_WRITE] = { .pc_func = nfsd_proc_write, - .pc_decode = (kxdrproc_t) nfssvc_decode_writeargs, + .pc_decode = nfssvc_decode_writeargs, .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_writeargs), @@ -660,7 +660,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_CREATE] = { .pc_func = nfsd_proc_create, - .pc_decode = (kxdrproc_t) nfssvc_decode_createargs, + .pc_decode = nfssvc_decode_createargs, .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_createargs), @@ -670,7 +670,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_REMOVE] = { .pc_func = nfsd_proc_remove, - .pc_decode = (kxdrproc_t) nfssvc_decode_diropargs, + .pc_decode = nfssvc_decode_diropargs, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_diropargs), .pc_ressize = sizeof(struct nfsd_void), @@ -679,7 +679,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_RENAME] = { .pc_func = nfsd_proc_rename, - .pc_decode = (kxdrproc_t) nfssvc_decode_renameargs, + .pc_decode = nfssvc_decode_renameargs, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_renameargs), .pc_ressize = sizeof(struct nfsd_void), @@ -688,7 +688,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_LINK] = { .pc_func = nfsd_proc_link, - .pc_decode = (kxdrproc_t) nfssvc_decode_linkargs, + .pc_decode = nfssvc_decode_linkargs, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_linkargs), .pc_ressize = sizeof(struct nfsd_void), @@ -697,7 +697,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_SYMLINK] = { .pc_func = nfsd_proc_symlink, - .pc_decode = (kxdrproc_t) nfssvc_decode_symlinkargs, + .pc_decode = nfssvc_decode_symlinkargs, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_symlinkargs), .pc_ressize = sizeof(struct nfsd_void), @@ -706,7 +706,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_MKDIR] = { .pc_func = nfsd_proc_mkdir, - .pc_decode = (kxdrproc_t) nfssvc_decode_createargs, + .pc_decode = nfssvc_decode_createargs, .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_createargs), @@ -716,7 +716,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_RMDIR] = { .pc_func = nfsd_proc_rmdir, - .pc_decode = (kxdrproc_t) nfssvc_decode_diropargs, + .pc_decode = nfssvc_decode_diropargs, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_diropargs), .pc_ressize = sizeof(struct nfsd_void), @@ -725,7 +725,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_READDIR] = { .pc_func = nfsd_proc_readdir, - .pc_decode = (kxdrproc_t) nfssvc_decode_readdirargs, + .pc_decode = nfssvc_decode_readdirargs, .pc_encode = (kxdrproc_t) nfssvc_encode_readdirres, .pc_argsize = sizeof(struct nfsd_readdirargs), .pc_ressize = sizeof(struct nfsd_readdirres), @@ -733,7 +733,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_STATFS] = { .pc_func = nfsd_proc_statfs, - .pc_decode = (kxdrproc_t) nfssvc_decode_fhandle, + .pc_decode = nfssvc_decode_fhandle, .pc_encode = (kxdrproc_t) nfssvc_encode_statfsres, .pc_argsize = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd_statfsres), diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index d64895fd8d25..3e00499d7ad7 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -801,9 +801,8 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) */ rqstp->rq_cachetype = proc->pc_cachetype; /* Decode arguments */ - xdr = proc->pc_decode; - if (xdr && !xdr(rqstp, (__be32*)rqstp->rq_arg.head[0].iov_base, - rqstp->rq_argp)) { + if (proc->pc_decode && + !proc->pc_decode(rqstp, (__be32*)rqstp->rq_arg.head[0].iov_base)) { dprintk("nfsd: failed to decode arguments!\n"); *statp = rpc_garbage_args; return 1; diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index de7b07ee489e..0957ceebe1aa 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -206,14 +206,16 @@ __be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *f * XDR decode functions */ int -nfssvc_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nfssvc_decode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_argsize_check(rqstp, p); } int -nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *args) +nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_fhandle *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; @@ -221,9 +223,10 @@ nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *ar } int -nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_sattrargs *args) +nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_sattrargs *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; @@ -233,9 +236,10 @@ nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_diropargs *args) +nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_diropargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->fh)) || !(p = decode_filename(p, &args->name, &args->len))) return 0; @@ -244,9 +248,9 @@ nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_readargs *args) +nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_readargs *args = rqstp->rq_argp; unsigned int len; int v; p = decode_fh(p, &args->fh); @@ -279,9 +283,9 @@ nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_writeargs *args) +nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_writeargs *args = rqstp->rq_argp; unsigned int len, hdr, dlen; struct kvec *head = rqstp->rq_arg.head; int v; @@ -335,9 +339,10 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_createargs *args) +nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_createargs *args = rqstp->rq_argp; + if ( !(p = decode_fh(p, &args->fh)) || !(p = decode_filename(p, &args->name, &args->len))) return 0; @@ -347,9 +352,10 @@ nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_renameargs *args) +nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_renameargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->ffh)) || !(p = decode_filename(p, &args->fname, &args->flen)) || !(p = decode_fh(p, &args->tfh)) @@ -360,8 +366,10 @@ nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readlinkargs *args) +nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_readlinkargs *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; @@ -373,9 +381,10 @@ nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readli } int -nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_linkargs *args) +nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_linkargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->ffh)) || !(p = decode_fh(p, &args->tfh)) || !(p = decode_filename(p, &args->tname, &args->tlen))) @@ -385,9 +394,10 @@ nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_symlinkargs *args) +nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_symlinkargs *args = rqstp->rq_argp; + if ( !(p = decode_fh(p, &args->ffh)) || !(p = decode_filename(p, &args->fname, &args->flen)) || !(p = decode_pathname(p, &args->tname, &args->tlen))) @@ -398,9 +408,10 @@ nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_readdirargs *args) +nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_readdirargs *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h index 2c21fa843fbf..8eeb752cf6f8 100644 --- a/fs/nfsd/xdr.h +++ b/fs/nfsd/xdr.h @@ -131,28 +131,18 @@ union nfsd_xdrstore { #define NFS2_SVC_XDRSIZE sizeof(union nfsd_xdrstore) -int nfssvc_decode_void(struct svc_rqst *, __be32 *, void *); -int nfssvc_decode_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *); -int nfssvc_decode_sattrargs(struct svc_rqst *, __be32 *, - struct nfsd_sattrargs *); -int nfssvc_decode_diropargs(struct svc_rqst *, __be32 *, - struct nfsd_diropargs *); -int nfssvc_decode_readargs(struct svc_rqst *, __be32 *, - struct nfsd_readargs *); -int nfssvc_decode_writeargs(struct svc_rqst *, __be32 *, - struct nfsd_writeargs *); -int nfssvc_decode_createargs(struct svc_rqst *, __be32 *, - struct nfsd_createargs *); -int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *, - struct nfsd_renameargs *); -int nfssvc_decode_readlinkargs(struct svc_rqst *, __be32 *, - struct nfsd_readlinkargs *); -int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *, - struct nfsd_linkargs *); -int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *, - struct nfsd_symlinkargs *); -int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *, - struct nfsd_readdirargs *); +int nfssvc_decode_void(struct svc_rqst *, __be32 *); +int nfssvc_decode_fhandle(struct svc_rqst *, __be32 *); +int nfssvc_decode_sattrargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_diropargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_readargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_writeargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_createargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_readlinkargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *); int nfssvc_encode_void(struct svc_rqst *, __be32 *, void *); int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *, struct nfsd_attrstat *); int nfssvc_encode_diropres(struct svc_rqst *, __be32 *, struct nfsd_diropres *); diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h index 23fe456a223b..f79be4c42e4a 100644 --- a/fs/nfsd/xdr3.h +++ b/fs/nfsd/xdr3.h @@ -269,37 +269,22 @@ union nfsd3_xdrstore { #define NFS3_SVC_XDRSIZE sizeof(union nfsd3_xdrstore) -int nfs3svc_decode_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *); -int nfs3svc_decode_sattrargs(struct svc_rqst *, __be32 *, - struct nfsd3_sattrargs *); -int nfs3svc_decode_diropargs(struct svc_rqst *, __be32 *, - struct nfsd3_diropargs *); -int nfs3svc_decode_accessargs(struct svc_rqst *, __be32 *, - struct nfsd3_accessargs *); -int nfs3svc_decode_readargs(struct svc_rqst *, __be32 *, - struct nfsd3_readargs *); -int nfs3svc_decode_writeargs(struct svc_rqst *, __be32 *, - struct nfsd3_writeargs *); -int nfs3svc_decode_createargs(struct svc_rqst *, __be32 *, - struct nfsd3_createargs *); -int nfs3svc_decode_mkdirargs(struct svc_rqst *, __be32 *, - struct nfsd3_createargs *); -int nfs3svc_decode_mknodargs(struct svc_rqst *, __be32 *, - struct nfsd3_mknodargs *); -int nfs3svc_decode_renameargs(struct svc_rqst *, __be32 *, - struct nfsd3_renameargs *); -int nfs3svc_decode_readlinkargs(struct svc_rqst *, __be32 *, - struct nfsd3_readlinkargs *); -int nfs3svc_decode_linkargs(struct svc_rqst *, __be32 *, - struct nfsd3_linkargs *); -int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *, - struct nfsd3_symlinkargs *); -int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *, - struct nfsd3_readdirargs *); -int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *, - struct nfsd3_readdirargs *); -int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *, - struct nfsd3_commitargs *); +int nfs3svc_decode_fhandle(struct svc_rqst *, __be32 *); +int nfs3svc_decode_sattrargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_diropargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_accessargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_readargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_writeargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_createargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_mkdirargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_mknodargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_renameargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_readlinkargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_linkargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *); int nfs3svc_encode_voidres(struct svc_rqst *, __be32 *, void *); int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *, struct nfsd3_attrstat *); diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index a158579d55a2..2a53c1233884 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -683,8 +683,7 @@ set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp) bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp); int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *, void *); -int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *, - struct nfsd4_compoundargs *); +int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *); int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *, struct nfsd4_compoundres *); __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32); diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index d39ed1cc5fbf..0416600844ce 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -95,19 +95,19 @@ struct nlm_reboot { */ #define NLMSVC_XDRSIZE sizeof(struct nlm_args) -int nlmsvc_decode_testargs(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlmsvc_decode_testargs(struct svc_rqst *, __be32 *); int nlmsvc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlmsvc_decode_lockargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_decode_cancargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_decode_unlockargs(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlmsvc_decode_lockargs(struct svc_rqst *, __be32 *); +int nlmsvc_decode_cancargs(struct svc_rqst *, __be32 *); +int nlmsvc_decode_unlockargs(struct svc_rqst *, __be32 *); int nlmsvc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlmsvc_decode_res(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlmsvc_decode_res(struct svc_rqst *, __be32 *); int nlmsvc_encode_void(struct svc_rqst *, __be32 *, void *); -int nlmsvc_decode_void(struct svc_rqst *, __be32 *, void *); -int nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlmsvc_decode_void(struct svc_rqst *, __be32 *); +int nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *); int nlmsvc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlmsvc_decode_notify(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_decode_reboot(struct svc_rqst *, __be32 *, struct nlm_reboot *); +int nlmsvc_decode_notify(struct svc_rqst *, __be32 *); +int nlmsvc_decode_reboot(struct svc_rqst *, __be32 *); /* int nlmclt_encode_testargs(struct rpc_rqst *, u32 *, struct nlm_args *); int nlmclt_encode_lockargs(struct rpc_rqst *, u32 *, struct nlm_args *); diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index e58c88b52ce1..951bbe31fdb8 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -23,19 +23,19 @@ -int nlm4svc_decode_testargs(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlm4svc_decode_testargs(struct svc_rqst *, __be32 *); int nlm4svc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlm4svc_decode_lockargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_decode_cancargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_decode_unlockargs(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlm4svc_decode_lockargs(struct svc_rqst *, __be32 *); +int nlm4svc_decode_cancargs(struct svc_rqst *, __be32 *); +int nlm4svc_decode_unlockargs(struct svc_rqst *, __be32 *); int nlm4svc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlm4svc_decode_res(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlm4svc_decode_res(struct svc_rqst *, __be32 *); int nlm4svc_encode_void(struct svc_rqst *, __be32 *, void *); -int nlm4svc_decode_void(struct svc_rqst *, __be32 *, void *); -int nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlm4svc_decode_void(struct svc_rqst *, __be32 *); +int nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *); int nlm4svc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlm4svc_decode_notify(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_decode_reboot(struct svc_rqst *, __be32 *, struct nlm_reboot *); +int nlm4svc_decode_notify(struct svc_rqst *, __be32 *); +int nlm4svc_decode_reboot(struct svc_rqst *, __be32 *); /* int nlmclt_encode_testargs(struct rpc_rqst *, u32 *, struct nlm_args *); int nlmclt_encode_lockargs(struct rpc_rqst *, u32 *, struct nlm_args *); diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 1381e1343640..047f04411dd4 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -421,7 +421,8 @@ struct svc_version { struct svc_procedure { /* process the request: */ __be32 (*pc_func)(struct svc_rqst *); - kxdrproc_t pc_decode; /* XDR decode args */ + /* XDR decode args: */ + int (*pc_decode)(struct svc_rqst *, __be32 *data); kxdrproc_t pc_encode; /* XDR encode result */ /* XDR free result: */ void (*pc_release)(struct svc_rqst *); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 4611cb7adc04..18024c1b9b7b 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1276,9 +1276,12 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) /* Call the function that processes the request. */ if (!versp->vs_dispatch) { - /* Decode arguments */ - xdr = procp->pc_decode; - if (xdr && !xdr(rqstp, argv->iov_base, rqstp->rq_argp)) + /* + * Decode arguments + * XXX: why do we ignore the return value? + */ + if (procp->pc_decode && + !procp->pc_decode(rqstp, argv->iov_base)) goto err_garbage; *statp = procp->pc_func(rqstp); -- cgit v1.2.3-59-g8ed1b From 63f8de37951a64cc24479eafd33085537e088075 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 19:42:02 +0200 Subject: sunrpc: properly type pc_encode callbacks Drop the resp argument as it can trivially be derived from the rqstp argument. With that all functions now have the same prototype, and we can remove the unsafe casting to kxdrproc_t. Signed-off-by: Christoph Hellwig Acked-by: Trond Myklebust --- fs/lockd/svc4proc.c | 2 +- fs/lockd/svcproc.c | 2 +- fs/lockd/xdr.c | 14 ++++++--- fs/lockd/xdr4.c | 14 ++++++--- fs/nfs/callback_xdr.c | 6 ++-- fs/nfsd/nfs2acl.c | 18 ++++++----- fs/nfsd/nfs3acl.c | 11 +++---- fs/nfsd/nfs3proc.c | 44 +++++++++++++-------------- fs/nfsd/nfs3xdr.c | 74 +++++++++++++++++++++++++++------------------- fs/nfsd/nfs4proc.c | 4 +-- fs/nfsd/nfs4xdr.c | 5 ++-- fs/nfsd/nfsproc.c | 36 +++++++++++----------- fs/nfsd/nfssvc.c | 5 +--- fs/nfsd/nfsxdr.c | 31 +++++++++++-------- fs/nfsd/xdr.h | 14 ++++----- fs/nfsd/xdr3.h | 45 ++++++++++------------------ fs/nfsd/xdr4.h | 5 ++-- include/linux/lockd/xdr.h | 8 ++--- include/linux/lockd/xdr4.h | 8 ++--- include/linux/sunrpc/svc.h | 3 +- net/sunrpc/svc.c | 6 ++-- 21 files changed, 185 insertions(+), 170 deletions(-) diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 804744f7528c..fed016155791 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -497,7 +497,7 @@ struct nlm_void { int dummy; }; #define PROC(name, xargt, xrest, argt, rest, respsize) \ { .pc_func = nlm4svc_proc_##name, \ .pc_decode = nlm4svc_decode_##xargt, \ - .pc_encode = (kxdrproc_t) nlm4svc_encode_##xrest, \ + .pc_encode = nlm4svc_encode_##xrest, \ .pc_release = NULL, \ .pc_argsize = sizeof(struct nlm_##argt), \ .pc_ressize = sizeof(struct nlm_##rest), \ diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index 204a698f7d41..14648b051eba 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -539,7 +539,7 @@ struct nlm_void { int dummy; }; #define PROC(name, xargt, xrest, argt, rest, respsize) \ { .pc_func = nlmsvc_proc_##name, \ .pc_decode = nlmsvc_decode_##xargt, \ - .pc_encode = (kxdrproc_t) nlmsvc_encode_##xrest, \ + .pc_encode = nlmsvc_encode_##xrest, \ .pc_release = NULL, \ .pc_argsize = sizeof(struct nlm_##argt), \ .pc_ressize = sizeof(struct nlm_##rest), \ diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c index b57af63fba56..442bbd0b0b29 100644 --- a/fs/lockd/xdr.c +++ b/fs/lockd/xdr.c @@ -200,8 +200,10 @@ nlmsvc_decode_testargs(struct svc_rqst *rqstp, __be32 *p) } int -nlmsvc_encode_testres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlmsvc_encode_testres(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_resp; + if (!(p = nlm_encode_testres(p, resp))) return 0; return xdr_ressize_check(rqstp, p); @@ -280,8 +282,10 @@ nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) } int -nlmsvc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlmsvc_encode_shareres(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_resp; + if (!(p = nlm_encode_cookie(p, &resp->cookie))) return 0; *p++ = resp->status; @@ -290,8 +294,10 @@ nlmsvc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) } int -nlmsvc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlmsvc_encode_res(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_resp; + if (!(p = nlm_encode_cookie(p, &resp->cookie))) return 0; *p++ = resp->status; @@ -342,7 +348,7 @@ nlmsvc_decode_void(struct svc_rqst *rqstp, __be32 *p) } int -nlmsvc_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nlmsvc_encode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_ressize_check(rqstp, p); } diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c index 46e18598a15c..2a0cd5679c49 100644 --- a/fs/lockd/xdr4.c +++ b/fs/lockd/xdr4.c @@ -197,8 +197,10 @@ nlm4svc_decode_testargs(struct svc_rqst *rqstp, __be32 *p) } int -nlm4svc_encode_testres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlm4svc_encode_testres(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_resp; + if (!(p = nlm4_encode_testres(p, resp))) return 0; return xdr_ressize_check(rqstp, p); @@ -277,8 +279,10 @@ nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) } int -nlm4svc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlm4svc_encode_shareres(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_resp; + if (!(p = nlm4_encode_cookie(p, &resp->cookie))) return 0; *p++ = resp->status; @@ -287,8 +291,10 @@ nlm4svc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) } int -nlm4svc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlm4svc_encode_res(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_resp; + if (!(p = nlm4_encode_cookie(p, &resp->cookie))) return 0; *p++ = resp->status; @@ -339,7 +345,7 @@ nlm4svc_decode_void(struct svc_rqst *rqstp, __be32 *p) } int -nlm4svc_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nlm4svc_encode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_ressize_check(rqstp, p); } diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 23ecbf7a40c1..acf75dc63e14 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -63,7 +63,7 @@ static int nfs4_decode_void(struct svc_rqst *rqstp, __be32 *p) return xdr_argsize_check(rqstp, p); } -static int nfs4_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +static int nfs4_encode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_ressize_check(rqstp, p); } @@ -999,12 +999,12 @@ static struct svc_procedure nfs4_callback_procedures1[] = { [CB_NULL] = { .pc_func = nfs4_callback_null, .pc_decode = nfs4_decode_void, - .pc_encode = (kxdrproc_t)nfs4_encode_void, + .pc_encode = nfs4_encode_void, .pc_xdrressize = 1, }, [CB_COMPOUND] = { .pc_func = nfs4_callback_compound, - .pc_encode = (kxdrproc_t)nfs4_encode_void, + .pc_encode = nfs4_encode_void, .pc_argsize = 256, .pc_ressize = 256, .pc_xdrressize = NFS4_CALLBACK_BUFSIZE, diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index bcfdaa83ee6c..fc6b179c8fff 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -251,15 +251,15 @@ static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p) * There must be an encoding function for void results so svc_process * will work properly. */ -static int nfsaclsvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy) +static int nfsaclsvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p) { return xdr_ressize_check(rqstp, p); } /* GETACL */ -static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_getaclres *resp) +static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_getaclres *resp = rqstp->rq_resp; struct dentry *dentry = resp->fh.fh_dentry; struct inode *inode; struct kvec *head = rqstp->rq_res.head; @@ -302,17 +302,19 @@ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p, return (n > 0); } -static int nfsaclsvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_attrstat *resp) +static int nfsaclsvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_attrstat *resp = rqstp->rq_resp; + p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat); return xdr_ressize_check(rqstp, p); } /* ACCESS */ -static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_accessres *resp) +static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_accessres *resp = rqstp->rq_resp; + p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat); *p++ = htonl(resp->access); return xdr_ressize_check(rqstp, p); @@ -355,7 +357,7 @@ struct nfsd3_voidargs { int dummy; }; { \ .pc_func = nfsacld_proc_##name, \ .pc_decode = nfsaclsvc_decode_##argt##args, \ - .pc_encode = (kxdrproc_t) nfsaclsvc_encode_##rest##res, \ + .pc_encode = nfsaclsvc_encode_##rest##res, \ .pc_release = nfsaclsvc_release_##relt, \ .pc_argsize = sizeof(struct nfsd3_##argt##args), \ .pc_ressize = sizeof(struct nfsd3_##rest##res), \ diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 4e68d6b5f409..9437b758cbfd 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -168,9 +168,9 @@ static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p) */ /* GETACL */ -static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_getaclres *resp) +static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_getaclres *resp = rqstp->rq_resp; struct dentry *dentry = resp->fh.fh_dentry; p = nfs3svc_encode_post_op_attr(rqstp, p, &resp->fh); @@ -213,9 +213,10 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p, } /* SETACL */ -static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_attrstat *resp) +static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_attrstat *resp = rqstp->rq_resp; + p = nfs3svc_encode_post_op_attr(rqstp, p, &resp->fh); return xdr_ressize_check(rqstp, p); @@ -243,7 +244,7 @@ struct nfsd3_voidargs { int dummy; }; { \ .pc_func = nfsd3_proc_##name, \ .pc_decode = nfs3svc_decode_##argt##args, \ - .pc_encode = (kxdrproc_t) nfs3svc_encode_##rest##res, \ + .pc_encode = nfs3svc_encode_##rest##res, \ .pc_release = nfs3svc_release_##relt, \ .pc_argsize = sizeof(struct nfsd3_##argt##args), \ .pc_ressize = sizeof(struct nfsd3_##rest##res), \ diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index ed83e8a9e7b4..17c90c41a3a6 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -677,7 +677,7 @@ struct nfsd3_voidargs { int dummy; }; static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_NULL] = { .pc_func = nfsd3_proc_null, - .pc_encode = (kxdrproc_t) nfs3svc_encode_voidres, + .pc_encode = nfs3svc_encode_voidres, .pc_argsize = sizeof(struct nfsd3_voidargs), .pc_ressize = sizeof(struct nfsd3_voidres), .pc_cachetype = RC_NOCACHE, @@ -686,7 +686,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_GETATTR] = { .pc_func = nfsd3_proc_getattr, .pc_decode = nfs3svc_decode_fhandleargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_attrstatres, + .pc_encode = nfs3svc_encode_attrstatres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_attrstatres), @@ -696,7 +696,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_SETATTR] = { .pc_func = nfsd3_proc_setattr, .pc_decode = nfs3svc_decode_sattrargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, + .pc_encode = nfs3svc_encode_wccstatres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_sattrargs), .pc_ressize = sizeof(struct nfsd3_wccstatres), @@ -706,7 +706,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_LOOKUP] = { .pc_func = nfsd3_proc_lookup, .pc_decode = nfs3svc_decode_diropargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_diropres, + .pc_encode = nfs3svc_encode_diropres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_diropargs), .pc_ressize = sizeof(struct nfsd3_diropres), @@ -716,7 +716,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_ACCESS] = { .pc_func = nfsd3_proc_access, .pc_decode = nfs3svc_decode_accessargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_accessres, + .pc_encode = nfs3svc_encode_accessres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_accessargs), .pc_ressize = sizeof(struct nfsd3_accessres), @@ -726,7 +726,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_READLINK] = { .pc_func = nfsd3_proc_readlink, .pc_decode = nfs3svc_decode_readlinkargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_readlinkres, + .pc_encode = nfs3svc_encode_readlinkres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readlinkargs), .pc_ressize = sizeof(struct nfsd3_readlinkres), @@ -736,7 +736,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_READ] = { .pc_func = nfsd3_proc_read, .pc_decode = nfs3svc_decode_readargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_readres, + .pc_encode = nfs3svc_encode_readres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readargs), .pc_ressize = sizeof(struct nfsd3_readres), @@ -746,7 +746,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_WRITE] = { .pc_func = nfsd3_proc_write, .pc_decode = nfs3svc_decode_writeargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_writeres, + .pc_encode = nfs3svc_encode_writeres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_writeargs), .pc_ressize = sizeof(struct nfsd3_writeres), @@ -756,7 +756,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_CREATE] = { .pc_func = nfsd3_proc_create, .pc_decode = nfs3svc_decode_createargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, + .pc_encode = nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_createargs), .pc_ressize = sizeof(struct nfsd3_createres), @@ -766,7 +766,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_MKDIR] = { .pc_func = nfsd3_proc_mkdir, .pc_decode = nfs3svc_decode_mkdirargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, + .pc_encode = nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_mkdirargs), .pc_ressize = sizeof(struct nfsd3_createres), @@ -776,7 +776,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_SYMLINK] = { .pc_func = nfsd3_proc_symlink, .pc_decode = nfs3svc_decode_symlinkargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, + .pc_encode = nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_symlinkargs), .pc_ressize = sizeof(struct nfsd3_createres), @@ -786,7 +786,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_MKNOD] = { .pc_func = nfsd3_proc_mknod, .pc_decode = nfs3svc_decode_mknodargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, + .pc_encode = nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_mknodargs), .pc_ressize = sizeof(struct nfsd3_createres), @@ -796,7 +796,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_REMOVE] = { .pc_func = nfsd3_proc_remove, .pc_decode = nfs3svc_decode_diropargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, + .pc_encode = nfs3svc_encode_wccstatres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_diropargs), .pc_ressize = sizeof(struct nfsd3_wccstatres), @@ -806,7 +806,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_RMDIR] = { .pc_func = nfsd3_proc_rmdir, .pc_decode = nfs3svc_decode_diropargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, + .pc_encode = nfs3svc_encode_wccstatres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_diropargs), .pc_ressize = sizeof(struct nfsd3_wccstatres), @@ -816,7 +816,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_RENAME] = { .pc_func = nfsd3_proc_rename, .pc_decode = nfs3svc_decode_renameargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_renameres, + .pc_encode = nfs3svc_encode_renameres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_renameargs), .pc_ressize = sizeof(struct nfsd3_renameres), @@ -826,7 +826,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_LINK] = { .pc_func = nfsd3_proc_link, .pc_decode = nfs3svc_decode_linkargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_linkres, + .pc_encode = nfs3svc_encode_linkres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_linkargs), .pc_ressize = sizeof(struct nfsd3_linkres), @@ -836,7 +836,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_READDIR] = { .pc_func = nfsd3_proc_readdir, .pc_decode = nfs3svc_decode_readdirargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres, + .pc_encode = nfs3svc_encode_readdirres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readdirargs), .pc_ressize = sizeof(struct nfsd3_readdirres), @@ -845,7 +845,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_READDIRPLUS] = { .pc_func = nfsd3_proc_readdirplus, .pc_decode = nfs3svc_decode_readdirplusargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres, + .pc_encode = nfs3svc_encode_readdirres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readdirplusargs), .pc_ressize = sizeof(struct nfsd3_readdirres), @@ -854,7 +854,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_FSSTAT] = { .pc_func = nfsd3_proc_fsstat, .pc_decode = nfs3svc_decode_fhandleargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_fsstatres, + .pc_encode = nfs3svc_encode_fsstatres, .pc_argsize = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_fsstatres), .pc_cachetype = RC_NOCACHE, @@ -863,7 +863,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_FSINFO] = { .pc_func = nfsd3_proc_fsinfo, .pc_decode = nfs3svc_decode_fhandleargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_fsinfores, + .pc_encode = nfs3svc_encode_fsinfores, .pc_argsize = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_fsinfores), .pc_cachetype = RC_NOCACHE, @@ -872,7 +872,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_PATHCONF] = { .pc_func = nfsd3_proc_pathconf, .pc_decode = nfs3svc_decode_fhandleargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_pathconfres, + .pc_encode = nfs3svc_encode_pathconfres, .pc_argsize = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_pathconfres), .pc_cachetype = RC_NOCACHE, @@ -881,7 +881,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_COMMIT] = { .pc_func = nfsd3_proc_commit, .pc_decode = nfs3svc_decode_commitargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_commitres, + .pc_encode = nfs3svc_encode_commitres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_commitargs), .pc_ressize = sizeof(struct nfsd3_commitres), diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index be8bf8af9917..349e355edc73 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -645,16 +645,17 @@ nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p) * will work properly. */ int -nfs3svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nfs3svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p) { return xdr_ressize_check(rqstp, p); } /* GETATTR */ int -nfs3svc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_attrstat *resp) +nfs3svc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_attrstat *resp = rqstp->rq_resp; + if (resp->status == 0) { lease_get_mtime(d_inode(resp->fh.fh_dentry), &resp->stat.mtime); @@ -665,18 +666,20 @@ nfs3svc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p, /* SETATTR, REMOVE, RMDIR */ int -nfs3svc_encode_wccstat(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_attrstat *resp) +nfs3svc_encode_wccstat(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_attrstat *resp = rqstp->rq_resp; + p = encode_wcc_data(rqstp, p, &resp->fh); return xdr_ressize_check(rqstp, p); } /* LOOKUP */ int -nfs3svc_encode_diropres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_diropres *resp) +nfs3svc_encode_diropres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_diropres *resp = rqstp->rq_resp; + if (resp->status == 0) { p = encode_fh(p, &resp->fh); p = encode_post_op_attr(rqstp, p, &resp->fh); @@ -687,9 +690,10 @@ nfs3svc_encode_diropres(struct svc_rqst *rqstp, __be32 *p, /* ACCESS */ int -nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_accessres *resp) +nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_accessres *resp = rqstp->rq_resp; + p = encode_post_op_attr(rqstp, p, &resp->fh); if (resp->status == 0) *p++ = htonl(resp->access); @@ -698,9 +702,10 @@ nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p, /* READLINK */ int -nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_readlinkres *resp) +nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_readlinkres *resp = rqstp->rq_resp; + p = encode_post_op_attr(rqstp, p, &resp->fh); if (resp->status == 0) { *p++ = htonl(resp->len); @@ -719,9 +724,10 @@ nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p, /* READ */ int -nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_readres *resp) +nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_readres *resp = rqstp->rq_resp; + p = encode_post_op_attr(rqstp, p, &resp->fh); if (resp->status == 0) { *p++ = htonl(resp->count); @@ -743,9 +749,9 @@ nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p, /* WRITE */ int -nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_writeres *resp) +nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_writeres *resp = rqstp->rq_resp; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); p = encode_wcc_data(rqstp, p, &resp->fh); @@ -760,9 +766,10 @@ nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p, /* CREATE, MKDIR, SYMLINK, MKNOD */ int -nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_diropres *resp) +nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_diropres *resp = rqstp->rq_resp; + if (resp->status == 0) { *p++ = xdr_one; p = encode_fh(p, &resp->fh); @@ -774,9 +781,10 @@ nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p, /* RENAME */ int -nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_renameres *resp) +nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_renameres *resp = rqstp->rq_resp; + p = encode_wcc_data(rqstp, p, &resp->ffh); p = encode_wcc_data(rqstp, p, &resp->tfh); return xdr_ressize_check(rqstp, p); @@ -784,9 +792,10 @@ nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p, /* LINK */ int -nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_linkres *resp) +nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_linkres *resp = rqstp->rq_resp; + p = encode_post_op_attr(rqstp, p, &resp->fh); p = encode_wcc_data(rqstp, p, &resp->tfh); return xdr_ressize_check(rqstp, p); @@ -794,9 +803,10 @@ nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p, /* READDIR */ int -nfs3svc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_readdirres *resp) +nfs3svc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_readdirres *resp = rqstp->rq_resp; + p = encode_post_op_attr(rqstp, p, &resp->fh); if (resp->status == 0) { @@ -1044,9 +1054,9 @@ nfs3svc_encode_entry_plus(void *cd, const char *name, /* FSSTAT */ int -nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_fsstatres *resp) +nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_fsstatres *resp = rqstp->rq_resp; struct kstatfs *s = &resp->stats; u64 bs = s->f_bsize; @@ -1066,9 +1076,10 @@ nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p, /* FSINFO */ int -nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_fsinfores *resp) +nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_fsinfores *resp = rqstp->rq_resp; + *p++ = xdr_zero; /* no post_op_attr */ if (resp->status == 0) { @@ -1090,9 +1101,10 @@ nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p, /* PATHCONF */ int -nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_pathconfres *resp) +nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_pathconfres *resp = rqstp->rq_resp; + *p++ = xdr_zero; /* no post_op_attr */ if (resp->status == 0) { @@ -1109,9 +1121,9 @@ nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p, /* COMMIT */ int -nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_commitres *resp) +nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_commitres *resp = rqstp->rq_resp; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); p = encode_wcc_data(rqstp, p, &resp->fh); diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 6ff434b77a9e..ad0622efae4e 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -2520,7 +2520,7 @@ struct nfsd4_voidargs { int dummy; }; static struct svc_procedure nfsd_procedures4[2] = { [NFSPROC4_NULL] = { .pc_func = nfsd4_proc_null, - .pc_encode = (kxdrproc_t) nfs4svc_encode_voidres, + .pc_encode = nfs4svc_encode_voidres, .pc_argsize = sizeof(struct nfsd4_voidargs), .pc_ressize = sizeof(struct nfsd4_voidres), .pc_cachetype = RC_NOCACHE, @@ -2529,7 +2529,7 @@ static struct svc_procedure nfsd_procedures4[2] = { [NFSPROC4_COMPOUND] = { .pc_func = nfsd4_proc_compound, .pc_decode = nfs4svc_decode_compoundargs, - .pc_encode = (kxdrproc_t) nfs4svc_encode_compoundres, + .pc_encode = nfs4svc_encode_compoundres, .pc_argsize = sizeof(struct nfsd4_compoundargs), .pc_ressize = sizeof(struct nfsd4_compoundres), .pc_release = nfsd4_release_compoundargs, diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 3a7e117bd11e..54e212e3541e 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -4538,7 +4538,7 @@ nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op) } int -nfs4svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nfs4svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p) { return xdr_ressize_check(rqstp, p); } @@ -4584,11 +4584,12 @@ nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p) } int -nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compoundres *resp) +nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p) { /* * All that remains is to write the tag and operation count... */ + struct nfsd4_compoundres *resp = rqstp->rq_resp; struct xdr_buf *buf = resp->xdr.buf; WARN_ON_ONCE(buf->len != buf->head[0].iov_len + buf->page_len + diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index d351d0ef6d34..0ef88d0e67d9 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -577,7 +577,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_NULL] = { .pc_func = nfsd_proc_null, .pc_decode = nfssvc_decode_void, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_void), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_NOCACHE, @@ -586,7 +586,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_GETATTR] = { .pc_func = nfsd_proc_getattr, .pc_decode = nfssvc_decode_fhandle, - .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, + .pc_encode = nfssvc_encode_attrstat, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd_attrstat), @@ -596,7 +596,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_SETATTR] = { .pc_func = nfsd_proc_setattr, .pc_decode = nfssvc_decode_sattrargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, + .pc_encode = nfssvc_encode_attrstat, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_sattrargs), .pc_ressize = sizeof(struct nfsd_attrstat), @@ -605,7 +605,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_ROOT] = { .pc_decode = nfssvc_decode_void, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_void), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_NOCACHE, @@ -614,7 +614,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_LOOKUP] = { .pc_func = nfsd_proc_lookup, .pc_decode = nfssvc_decode_diropargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, + .pc_encode = nfssvc_encode_diropres, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_diropargs), .pc_ressize = sizeof(struct nfsd_diropres), @@ -624,7 +624,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_READLINK] = { .pc_func = nfsd_proc_readlink, .pc_decode = nfssvc_decode_readlinkargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_readlinkres, + .pc_encode = nfssvc_encode_readlinkres, .pc_argsize = sizeof(struct nfsd_readlinkargs), .pc_ressize = sizeof(struct nfsd_readlinkres), .pc_cachetype = RC_NOCACHE, @@ -633,7 +633,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_READ] = { .pc_func = nfsd_proc_read, .pc_decode = nfssvc_decode_readargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_readres, + .pc_encode = nfssvc_encode_readres, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_readargs), .pc_ressize = sizeof(struct nfsd_readres), @@ -642,7 +642,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_WRITECACHE] = { .pc_decode = nfssvc_decode_void, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_void), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_NOCACHE, @@ -651,7 +651,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_WRITE] = { .pc_func = nfsd_proc_write, .pc_decode = nfssvc_decode_writeargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, + .pc_encode = nfssvc_encode_attrstat, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_writeargs), .pc_ressize = sizeof(struct nfsd_attrstat), @@ -661,7 +661,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_CREATE] = { .pc_func = nfsd_proc_create, .pc_decode = nfssvc_decode_createargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, + .pc_encode = nfssvc_encode_diropres, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_createargs), .pc_ressize = sizeof(struct nfsd_diropres), @@ -671,7 +671,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_REMOVE] = { .pc_func = nfsd_proc_remove, .pc_decode = nfssvc_decode_diropargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_diropargs), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_REPLSTAT, @@ -680,7 +680,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_RENAME] = { .pc_func = nfsd_proc_rename, .pc_decode = nfssvc_decode_renameargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_renameargs), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_REPLSTAT, @@ -689,7 +689,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_LINK] = { .pc_func = nfsd_proc_link, .pc_decode = nfssvc_decode_linkargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_linkargs), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_REPLSTAT, @@ -698,7 +698,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_SYMLINK] = { .pc_func = nfsd_proc_symlink, .pc_decode = nfssvc_decode_symlinkargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_symlinkargs), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_REPLSTAT, @@ -707,7 +707,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_MKDIR] = { .pc_func = nfsd_proc_mkdir, .pc_decode = nfssvc_decode_createargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, + .pc_encode = nfssvc_encode_diropres, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_createargs), .pc_ressize = sizeof(struct nfsd_diropres), @@ -717,7 +717,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_RMDIR] = { .pc_func = nfsd_proc_rmdir, .pc_decode = nfssvc_decode_diropargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_diropargs), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_REPLSTAT, @@ -726,7 +726,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_READDIR] = { .pc_func = nfsd_proc_readdir, .pc_decode = nfssvc_decode_readdirargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_readdirres, + .pc_encode = nfssvc_encode_readdirres, .pc_argsize = sizeof(struct nfsd_readdirargs), .pc_ressize = sizeof(struct nfsd_readdirres), .pc_cachetype = RC_NOCACHE, @@ -734,7 +734,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_STATFS] = { .pc_func = nfsd_proc_statfs, .pc_decode = nfssvc_decode_fhandle, - .pc_encode = (kxdrproc_t) nfssvc_encode_statfsres, + .pc_encode = nfssvc_encode_statfsres, .pc_argsize = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd_statfsres), .pc_cachetype = RC_NOCACHE, diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 3e00499d7ad7..555233664124 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -782,7 +782,6 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) { struct svc_procedure *proc; - kxdrproc_t xdr; __be32 nfserr; __be32 *nfserrp; @@ -841,9 +840,7 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) * For NFSv2, additional info is never returned in case of an error. */ if (!(nfserr && rqstp->rq_vers == 2)) { - xdr = proc->pc_encode; - if (xdr && !xdr(rqstp, nfserrp, - rqstp->rq_resp)) { + if (proc->pc_encode && !proc->pc_encode(rqstp, nfserrp)) { /* Failed to encode result. Release cache entry */ dprintk("nfsd: failed to encode result!\n"); nfsd_cache_update(rqstp, RC_NOCACHE, NULL); diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index 0957ceebe1aa..bb1998c5ae61 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -429,32 +429,35 @@ nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) * XDR encode functions */ int -nfssvc_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nfssvc_encode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_ressize_check(rqstp, p); } int -nfssvc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_attrstat *resp) +nfssvc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_attrstat *resp = rqstp->rq_resp; + p = encode_fattr(rqstp, p, &resp->fh, &resp->stat); return xdr_ressize_check(rqstp, p); } int -nfssvc_encode_diropres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_diropres *resp) +nfssvc_encode_diropres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_diropres *resp = rqstp->rq_resp; + p = encode_fh(p, &resp->fh); p = encode_fattr(rqstp, p, &resp->fh, &resp->stat); return xdr_ressize_check(rqstp, p); } int -nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_readlinkres *resp) +nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_readlinkres *resp = rqstp->rq_resp; + *p++ = htonl(resp->len); xdr_ressize_check(rqstp, p); rqstp->rq_res.page_len = resp->len; @@ -468,9 +471,10 @@ nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_readres *resp) +nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_readres *resp = rqstp->rq_resp; + p = encode_fattr(rqstp, p, &resp->fh, &resp->stat); *p++ = htonl(resp->count); xdr_ressize_check(rqstp, p); @@ -487,9 +491,10 @@ nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_readdirres *resp) +nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_readdirres *resp = rqstp->rq_resp; + xdr_ressize_check(rqstp, p); p = resp->buffer; *p++ = 0; /* no more entries */ @@ -500,9 +505,9 @@ nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_statfsres *resp) +nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_statfsres *resp = rqstp->rq_resp; struct kstatfs *stat = &resp->stats; *p++ = htonl(NFSSVC_MAXBLKSIZE_V2); /* max transfer size */ diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h index 8eeb752cf6f8..457ce45e5084 100644 --- a/fs/nfsd/xdr.h +++ b/fs/nfsd/xdr.h @@ -143,13 +143,13 @@ int nfssvc_decode_readlinkargs(struct svc_rqst *, __be32 *); int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *); int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *); int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *); -int nfssvc_encode_void(struct svc_rqst *, __be32 *, void *); -int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *, struct nfsd_attrstat *); -int nfssvc_encode_diropres(struct svc_rqst *, __be32 *, struct nfsd_diropres *); -int nfssvc_encode_readlinkres(struct svc_rqst *, __be32 *, struct nfsd_readlinkres *); -int nfssvc_encode_readres(struct svc_rqst *, __be32 *, struct nfsd_readres *); -int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *, struct nfsd_statfsres *); -int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *, struct nfsd_readdirres *); +int nfssvc_encode_void(struct svc_rqst *, __be32 *); +int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *); +int nfssvc_encode_diropres(struct svc_rqst *, __be32 *); +int nfssvc_encode_readlinkres(struct svc_rqst *, __be32 *); +int nfssvc_encode_readres(struct svc_rqst *, __be32 *); +int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *); +int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *); int nfssvc_encode_entry(void *, const char *name, int namlen, loff_t offset, u64 ino, unsigned int); diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h index f79be4c42e4a..80d7da620e91 100644 --- a/fs/nfsd/xdr3.h +++ b/fs/nfsd/xdr3.h @@ -285,35 +285,22 @@ int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *); int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *); int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *); int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *); -int nfs3svc_encode_voidres(struct svc_rqst *, __be32 *, void *); -int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *, - struct nfsd3_attrstat *); -int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *, - struct nfsd3_attrstat *); -int nfs3svc_encode_diropres(struct svc_rqst *, __be32 *, - struct nfsd3_diropres *); -int nfs3svc_encode_accessres(struct svc_rqst *, __be32 *, - struct nfsd3_accessres *); -int nfs3svc_encode_readlinkres(struct svc_rqst *, __be32 *, - struct nfsd3_readlinkres *); -int nfs3svc_encode_readres(struct svc_rqst *, __be32 *, struct nfsd3_readres *); -int nfs3svc_encode_writeres(struct svc_rqst *, __be32 *, struct nfsd3_writeres *); -int nfs3svc_encode_createres(struct svc_rqst *, __be32 *, - struct nfsd3_diropres *); -int nfs3svc_encode_renameres(struct svc_rqst *, __be32 *, - struct nfsd3_renameres *); -int nfs3svc_encode_linkres(struct svc_rqst *, __be32 *, - struct nfsd3_linkres *); -int nfs3svc_encode_readdirres(struct svc_rqst *, __be32 *, - struct nfsd3_readdirres *); -int nfs3svc_encode_fsstatres(struct svc_rqst *, __be32 *, - struct nfsd3_fsstatres *); -int nfs3svc_encode_fsinfores(struct svc_rqst *, __be32 *, - struct nfsd3_fsinfores *); -int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *, - struct nfsd3_pathconfres *); -int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *, - struct nfsd3_commitres *); +int nfs3svc_encode_voidres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *); +int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *); +int nfs3svc_encode_diropres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_accessres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_readlinkres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_readres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_writeres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_createres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_renameres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_linkres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_readdirres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_fsstatres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_fsinfores(struct svc_rqst *, __be32 *); +int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *); void nfs3svc_release_fhandle(struct svc_rqst *); void nfs3svc_release_fhandle2(struct svc_rqst *); diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 2a53c1233884..eb7f9239304f 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -682,10 +682,9 @@ set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp) bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp); -int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *, void *); +int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *); int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *); -int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *, - struct nfsd4_compoundres *); +int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *); __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32); void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *); void nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op); diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index 0416600844ce..7acbecc21a40 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -96,16 +96,16 @@ struct nlm_reboot { #define NLMSVC_XDRSIZE sizeof(struct nlm_args) int nlmsvc_decode_testargs(struct svc_rqst *, __be32 *); -int nlmsvc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlmsvc_encode_testres(struct svc_rqst *, __be32 *); int nlmsvc_decode_lockargs(struct svc_rqst *, __be32 *); int nlmsvc_decode_cancargs(struct svc_rqst *, __be32 *); int nlmsvc_decode_unlockargs(struct svc_rqst *, __be32 *); -int nlmsvc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlmsvc_encode_res(struct svc_rqst *, __be32 *); int nlmsvc_decode_res(struct svc_rqst *, __be32 *); -int nlmsvc_encode_void(struct svc_rqst *, __be32 *, void *); +int nlmsvc_encode_void(struct svc_rqst *, __be32 *); int nlmsvc_decode_void(struct svc_rqst *, __be32 *); int nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *); -int nlmsvc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlmsvc_encode_shareres(struct svc_rqst *, __be32 *); int nlmsvc_decode_notify(struct svc_rqst *, __be32 *); int nlmsvc_decode_reboot(struct svc_rqst *, __be32 *); /* diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index 951bbe31fdb8..bf1645609225 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -24,16 +24,16 @@ int nlm4svc_decode_testargs(struct svc_rqst *, __be32 *); -int nlm4svc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlm4svc_encode_testres(struct svc_rqst *, __be32 *); int nlm4svc_decode_lockargs(struct svc_rqst *, __be32 *); int nlm4svc_decode_cancargs(struct svc_rqst *, __be32 *); int nlm4svc_decode_unlockargs(struct svc_rqst *, __be32 *); -int nlm4svc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlm4svc_encode_res(struct svc_rqst *, __be32 *); int nlm4svc_decode_res(struct svc_rqst *, __be32 *); -int nlm4svc_encode_void(struct svc_rqst *, __be32 *, void *); +int nlm4svc_encode_void(struct svc_rqst *, __be32 *); int nlm4svc_decode_void(struct svc_rqst *, __be32 *); int nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *); -int nlm4svc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlm4svc_encode_shareres(struct svc_rqst *, __be32 *); int nlm4svc_decode_notify(struct svc_rqst *, __be32 *); int nlm4svc_decode_reboot(struct svc_rqst *, __be32 *); /* diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 047f04411dd4..6cfe41db7f31 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -423,7 +423,8 @@ struct svc_procedure { __be32 (*pc_func)(struct svc_rqst *); /* XDR decode args: */ int (*pc_decode)(struct svc_rqst *, __be32 *data); - kxdrproc_t pc_encode; /* XDR encode result */ + /* XDR encode result: */ + int (*pc_encode)(struct svc_rqst *, __be32 *data); /* XDR free result: */ void (*pc_release)(struct svc_rqst *); unsigned int pc_argsize; /* argument struct size */ diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 18024c1b9b7b..aa643a29fdc6 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1154,7 +1154,6 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) struct svc_version *versp = NULL; /* compiler food */ struct svc_procedure *procp = NULL; struct svc_serv *serv = rqstp->rq_server; - kxdrproc_t xdr; __be32 *statp; u32 prog, vers, proc; __be32 auth_stat, rpc_stat; @@ -1298,9 +1297,8 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) procp->pc_release(rqstp); goto err_bad_auth; } - if (*statp == rpc_success && - (xdr = procp->pc_encode) && - !xdr(rqstp, resv->iov_base+resv->iov_len, rqstp->rq_resp)) { + if (*statp == rpc_success && procp->pc_encode && + !procp->pc_encode(rqstp, resv->iov_base + resv->iov_len)) { dprintk("svc: failed to encode reply\n"); /* serv->sv_stats->rpcsystemerr++; */ *statp = rpc_system_err; -- cgit v1.2.3-59-g8ed1b From 35f297e5370bd511a171f7de0c5a31ee661f2e7e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 19:56:10 +0200 Subject: sunrpc: remove kxdrproc_t Remove the now unused typedef. Signed-off-by: Christoph Hellwig --- include/linux/sunrpc/xdr.h | 7 ------- 1 file changed, 7 deletions(-) diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index ed0fbf0d8d0f..261b48a2701d 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -34,13 +34,6 @@ struct xdr_netobj { u8 * data; }; -/* - * This is the legacy generic XDR function. rqstp is either a rpc_rqst - * (client side) or svc_rqst pointer (server side). - * Encode functions always assume there's enough room in the buffer. - */ -typedef int (*kxdrproc_t)(void *rqstp, __be32 *data, void *obj); - /* * Basic structure for transmission/reception of a client XDR message. * Features a header (for a linear buffer containing RPC headers -- cgit v1.2.3-59-g8ed1b From b60e985980948f65d9833e5be7adccb6df321368 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 20:03:15 +0200 Subject: nfsd4: properly type op_set_currentstateid callbacks Given the args union in struct nfsd4_op a name, and pass it to the op_set_currentstateid callbacks instead of using unsafe function pointer casts. Signed-off-by: Christoph Hellwig --- fs/nfsd/current_stateid.h | 12 ++++++++---- fs/nfsd/nfs4proc.c | 12 ++++++------ fs/nfsd/nfs4state.c | 20 ++++++++++++-------- fs/nfsd/xdr4.h | 2 +- 4 files changed, 27 insertions(+), 19 deletions(-) diff --git a/fs/nfsd/current_stateid.h b/fs/nfsd/current_stateid.h index 4123551208d8..3c80a7b5302d 100644 --- a/fs/nfsd/current_stateid.h +++ b/fs/nfsd/current_stateid.h @@ -8,10 +8,14 @@ extern void clear_current_stateid(struct nfsd4_compound_state *cstate); /* * functions to set current state id */ -extern void nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *); -extern void nfsd4_set_openstateid(struct nfsd4_compound_state *, struct nfsd4_open *); -extern void nfsd4_set_lockstateid(struct nfsd4_compound_state *, struct nfsd4_lock *); -extern void nfsd4_set_closestateid(struct nfsd4_compound_state *, struct nfsd4_close *); +extern void nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_set_openstateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_set_lockstateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_set_closestateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); /* * functions to consume current state id diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index ad0622efae4e..fa2c46f67f27 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1525,7 +1525,6 @@ typedef __be32(*nfsd4op_func)(struct svc_rqst *, struct nfsd4_compound_state *, void *); typedef u32(*nfsd4op_rsize)(struct svc_rqst *, struct nfsd4_op *op); -typedef void(*stateid_setter)(struct nfsd4_compound_state *, void *); typedef void(*stateid_getter)(struct nfsd4_compound_state *, void *); enum nfsd4_op_flags { @@ -1565,7 +1564,8 @@ struct nfsd4_operation { /* Try to get response size before operation */ nfsd4op_rsize op_rsize_bop; stateid_getter op_get_currentstateid; - stateid_setter op_set_currentstateid; + void (*op_set_currentstateid)(struct nfsd4_compound_state *, + union nfsd4_op_u *); }; static struct nfsd4_operation nfsd4_ops[]; @@ -2105,7 +2105,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_name = "OP_CLOSE", .op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize, .op_get_currentstateid = (stateid_getter)nfsd4_get_closestateid, - .op_set_currentstateid = (stateid_setter)nfsd4_set_closestateid, + .op_set_currentstateid = nfsd4_set_closestateid, }, [OP_COMMIT] = { .op_func = (nfsd4op_func)nfsd4_commit, @@ -2149,7 +2149,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LOCK", .op_rsize_bop = (nfsd4op_rsize)nfsd4_lock_rsize, - .op_set_currentstateid = (stateid_setter)nfsd4_set_lockstateid, + .op_set_currentstateid = nfsd4_set_lockstateid, }, [OP_LOCKT] = { .op_func = (nfsd4op_func)nfsd4_lockt, @@ -2185,7 +2185,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = OP_HANDLES_WRONGSEC | OP_MODIFIES_SOMETHING, .op_name = "OP_OPEN", .op_rsize_bop = (nfsd4op_rsize)nfsd4_open_rsize, - .op_set_currentstateid = (stateid_setter)nfsd4_set_openstateid, + .op_set_currentstateid = nfsd4_set_openstateid, }, [OP_OPEN_CONFIRM] = { .op_func = (nfsd4op_func)nfsd4_open_confirm, @@ -2199,7 +2199,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_name = "OP_OPEN_DOWNGRADE", .op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize, .op_get_currentstateid = (stateid_getter)nfsd4_get_opendowngradestateid, - .op_set_currentstateid = (stateid_setter)nfsd4_set_opendowngradestateid, + .op_set_currentstateid = nfsd4_set_opendowngradestateid, }, [OP_PUTFH] = { .op_func = (nfsd4op_func)nfsd4_putfh, diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 22002fb75a18..f9552357923e 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -7103,27 +7103,31 @@ clear_current_stateid(struct nfsd4_compound_state *cstate) * functions to set current state id */ void -nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *odp) +nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - put_stateid(cstate, &odp->od_stateid); + put_stateid(cstate, &u->open_downgrade.od_stateid); } void -nfsd4_set_openstateid(struct nfsd4_compound_state *cstate, struct nfsd4_open *open) +nfsd4_set_openstateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - put_stateid(cstate, &open->op_stateid); + put_stateid(cstate, &u->open.op_stateid); } void -nfsd4_set_closestateid(struct nfsd4_compound_state *cstate, struct nfsd4_close *close) +nfsd4_set_closestateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - put_stateid(cstate, &close->cl_stateid); + put_stateid(cstate, &u->close.cl_stateid); } void -nfsd4_set_lockstateid(struct nfsd4_compound_state *cstate, struct nfsd4_lock *lock) +nfsd4_set_lockstateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - put_stateid(cstate, &lock->lk_resp_stateid); + put_stateid(cstate, &u->lock.lk_resp_stateid); } /* diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index eb7f9239304f..b625f4aa1061 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -539,7 +539,7 @@ struct nfsd4_seek { struct nfsd4_op { int opnum; __be32 status; - union { + union nfsd4_op_u { struct nfsd4_access access; struct nfsd4_close close; struct nfsd4_commit commit; -- cgit v1.2.3-59-g8ed1b From 57832e7bd85a450e64dba19933d83b6577632066 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 20:37:33 +0200 Subject: nfsd4: properly type op_get_currentstateid callbacks Pass union nfsd4_op_u to the op_set_currentstateid callbacks instead of using unsafe function pointer casts. Signed-off-by: Christoph Hellwig --- fs/nfsd/current_stateid.h | 24 ++++++++++++++++-------- fs/nfsd/nfs4proc.c | 21 ++++++++++----------- fs/nfsd/nfs4state.c | 40 ++++++++++++++++++++++++---------------- 3 files changed, 50 insertions(+), 35 deletions(-) diff --git a/fs/nfsd/current_stateid.h b/fs/nfsd/current_stateid.h index 3c80a7b5302d..34075cee573a 100644 --- a/fs/nfsd/current_stateid.h +++ b/fs/nfsd/current_stateid.h @@ -20,13 +20,21 @@ extern void nfsd4_set_closestateid(struct nfsd4_compound_state *, /* * functions to consume current state id */ -extern void nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *); -extern void nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *, struct nfsd4_delegreturn *); -extern void nfsd4_get_freestateid(struct nfsd4_compound_state *, struct nfsd4_free_stateid *); -extern void nfsd4_get_setattrstateid(struct nfsd4_compound_state *, struct nfsd4_setattr *); -extern void nfsd4_get_closestateid(struct nfsd4_compound_state *, struct nfsd4_close *); -extern void nfsd4_get_lockustateid(struct nfsd4_compound_state *, struct nfsd4_locku *); -extern void nfsd4_get_readstateid(struct nfsd4_compound_state *, struct nfsd4_read *); -extern void nfsd4_get_writestateid(struct nfsd4_compound_state *, struct nfsd4_write *); +extern void nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_get_freestateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_get_setattrstateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_get_closestateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_get_lockustateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_get_readstateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_get_writestateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); #endif /* _NFSD4_CURRENT_STATE_H */ diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index fa2c46f67f27..4d724d3284b0 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1525,8 +1525,6 @@ typedef __be32(*nfsd4op_func)(struct svc_rqst *, struct nfsd4_compound_state *, void *); typedef u32(*nfsd4op_rsize)(struct svc_rqst *, struct nfsd4_op *op); -typedef void(*stateid_getter)(struct nfsd4_compound_state *, void *); - enum nfsd4_op_flags { ALLOWED_WITHOUT_FH = 1 << 0, /* No current filehandle required */ ALLOWED_ON_ABSENT_FS = 1 << 1, /* ops processed on absent fs */ @@ -1563,7 +1561,8 @@ struct nfsd4_operation { char *op_name; /* Try to get response size before operation */ nfsd4op_rsize op_rsize_bop; - stateid_getter op_get_currentstateid; + void (*op_get_currentstateid)(struct nfsd4_compound_state *, + union nfsd4_op_u *); void (*op_set_currentstateid)(struct nfsd4_compound_state *, union nfsd4_op_u *); }; @@ -2104,7 +2103,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_CLOSE", .op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize, - .op_get_currentstateid = (stateid_getter)nfsd4_get_closestateid, + .op_get_currentstateid = nfsd4_get_closestateid, .op_set_currentstateid = nfsd4_set_closestateid, }, [OP_COMMIT] = { @@ -2124,7 +2123,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_DELEGRETURN", .op_rsize_bop = nfsd4_only_status_rsize, - .op_get_currentstateid = (stateid_getter)nfsd4_get_delegreturnstateid, + .op_get_currentstateid = nfsd4_get_delegreturnstateid, }, [OP_GETATTR] = { .op_func = (nfsd4op_func)nfsd4_getattr, @@ -2161,7 +2160,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LOCKU", .op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize, - .op_get_currentstateid = (stateid_getter)nfsd4_get_lockustateid, + .op_get_currentstateid = nfsd4_get_lockustateid, }, [OP_LOOKUP] = { .op_func = (nfsd4op_func)nfsd4_lookup, @@ -2198,7 +2197,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_OPEN_DOWNGRADE", .op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize, - .op_get_currentstateid = (stateid_getter)nfsd4_get_opendowngradestateid, + .op_get_currentstateid = nfsd4_get_opendowngradestateid, .op_set_currentstateid = nfsd4_set_opendowngradestateid, }, [OP_PUTFH] = { @@ -2226,7 +2225,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_func = (nfsd4op_func)nfsd4_read, .op_name = "OP_READ", .op_rsize_bop = (nfsd4op_rsize)nfsd4_read_rsize, - .op_get_currentstateid = (stateid_getter)nfsd4_get_readstateid, + .op_get_currentstateid = nfsd4_get_readstateid, }, [OP_READDIR] = { .op_func = (nfsd4op_func)nfsd4_readdir, @@ -2282,7 +2281,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_name = "OP_SETATTR", .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_rsize_bop = (nfsd4op_rsize)nfsd4_setattr_rsize, - .op_get_currentstateid = (stateid_getter)nfsd4_get_setattrstateid, + .op_get_currentstateid = nfsd4_get_setattrstateid, }, [OP_SETCLIENTID] = { .op_func = (nfsd4op_func)nfsd4_setclientid, @@ -2308,7 +2307,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_WRITE", .op_rsize_bop = (nfsd4op_rsize)nfsd4_write_rsize, - .op_get_currentstateid = (stateid_getter)nfsd4_get_writestateid, + .op_get_currentstateid = nfsd4_get_writestateid, }, [OP_RELEASE_LOCKOWNER] = { .op_func = (nfsd4op_func)nfsd4_release_lockowner, @@ -2388,7 +2387,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_func = (nfsd4op_func)nfsd4_free_stateid, .op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING, .op_name = "OP_FREE_STATEID", - .op_get_currentstateid = (stateid_getter)nfsd4_get_freestateid, + .op_get_currentstateid = nfsd4_get_freestateid, .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, }, #ifdef CONFIG_NFSD_PNFS diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index f9552357923e..01ab21f8d34d 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -7135,49 +7135,57 @@ nfsd4_set_lockstateid(struct nfsd4_compound_state *cstate, */ void -nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *odp) +nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &odp->od_stateid); + get_stateid(cstate, &u->open_downgrade.od_stateid); } void -nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *cstate, struct nfsd4_delegreturn *drp) +nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &drp->dr_stateid); + get_stateid(cstate, &u->delegreturn.dr_stateid); } void -nfsd4_get_freestateid(struct nfsd4_compound_state *cstate, struct nfsd4_free_stateid *fsp) +nfsd4_get_freestateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &fsp->fr_stateid); + get_stateid(cstate, &u->free_stateid.fr_stateid); } void -nfsd4_get_setattrstateid(struct nfsd4_compound_state *cstate, struct nfsd4_setattr *setattr) +nfsd4_get_setattrstateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &setattr->sa_stateid); + get_stateid(cstate, &u->setattr.sa_stateid); } void -nfsd4_get_closestateid(struct nfsd4_compound_state *cstate, struct nfsd4_close *close) +nfsd4_get_closestateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &close->cl_stateid); + get_stateid(cstate, &u->close.cl_stateid); } void -nfsd4_get_lockustateid(struct nfsd4_compound_state *cstate, struct nfsd4_locku *locku) +nfsd4_get_lockustateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &locku->lu_stateid); + get_stateid(cstate, &u->locku.lu_stateid); } void -nfsd4_get_readstateid(struct nfsd4_compound_state *cstate, struct nfsd4_read *read) +nfsd4_get_readstateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &read->rd_stateid); + get_stateid(cstate, &u->read.rd_stateid); } void -nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, struct nfsd4_write *write) +nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &write->wr_stateid); + get_stateid(cstate, &u->write.wr_stateid); } -- cgit v1.2.3-59-g8ed1b From 1c1226385b44c1f66dafb3c56b68455ee565dbbf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 20:42:10 +0200 Subject: nfsd4: remove nfsd4op_rsize Except for a lot of unnecessary casts this typedef only has one user, so remove the casts and expand it in struct nfsd4_operation. Signed-off-by: Christoph Hellwig --- fs/nfsd/nfs4proc.c | 109 ++++++++++++++++++++++++++--------------------------- 1 file changed, 54 insertions(+), 55 deletions(-) diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 4d724d3284b0..0bd4b750262f 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1523,7 +1523,6 @@ static inline void nfsd4_increment_op_stats(u32 opnum) typedef __be32(*nfsd4op_func)(struct svc_rqst *, struct nfsd4_compound_state *, void *); -typedef u32(*nfsd4op_rsize)(struct svc_rqst *, struct nfsd4_op *op); enum nfsd4_op_flags { ALLOWED_WITHOUT_FH = 1 << 0, /* No current filehandle required */ @@ -1560,7 +1559,7 @@ struct nfsd4_operation { u32 op_flags; char *op_name; /* Try to get response size before operation */ - nfsd4op_rsize op_rsize_bop; + u32 (*op_rsize_bop)(struct svc_rqst *, struct nfsd4_op *); void (*op_get_currentstateid)(struct nfsd4_compound_state *, union nfsd4_op_u *); void (*op_set_currentstateid)(struct nfsd4_compound_state *, @@ -2096,13 +2095,13 @@ static struct nfsd4_operation nfsd4_ops[] = { [OP_ACCESS] = { .op_func = (nfsd4op_func)nfsd4_access, .op_name = "OP_ACCESS", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_access_rsize, + .op_rsize_bop = nfsd4_access_rsize, }, [OP_CLOSE] = { .op_func = (nfsd4op_func)nfsd4_close, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_CLOSE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize, + .op_rsize_bop = nfsd4_status_stateid_rsize, .op_get_currentstateid = nfsd4_get_closestateid, .op_set_currentstateid = nfsd4_set_closestateid, }, @@ -2110,13 +2109,13 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_func = (nfsd4op_func)nfsd4_commit, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_COMMIT", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_commit_rsize, + .op_rsize_bop = nfsd4_commit_rsize, }, [OP_CREATE] = { .op_func = (nfsd4op_func)nfsd4_create, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME | OP_CLEAR_STATEID, .op_name = "OP_CREATE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_create_rsize, + .op_rsize_bop = nfsd4_create_rsize, }, [OP_DELEGRETURN] = { .op_func = (nfsd4op_func)nfsd4_delegreturn, @@ -2134,69 +2133,69 @@ static struct nfsd4_operation nfsd4_ops[] = { [OP_GETFH] = { .op_func = (nfsd4op_func)nfsd4_getfh, .op_name = "OP_GETFH", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_getfh_rsize, + .op_rsize_bop = nfsd4_getfh_rsize, }, [OP_LINK] = { .op_func = (nfsd4op_func)nfsd4_link, .op_flags = ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_LINK", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_link_rsize, + .op_rsize_bop = nfsd4_link_rsize, }, [OP_LOCK] = { .op_func = (nfsd4op_func)nfsd4_lock, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LOCK", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_lock_rsize, + .op_rsize_bop = nfsd4_lock_rsize, .op_set_currentstateid = nfsd4_set_lockstateid, }, [OP_LOCKT] = { .op_func = (nfsd4op_func)nfsd4_lockt, .op_name = "OP_LOCKT", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_lock_rsize, + .op_rsize_bop = nfsd4_lock_rsize, }, [OP_LOCKU] = { .op_func = (nfsd4op_func)nfsd4_locku, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LOCKU", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize, + .op_rsize_bop = nfsd4_status_stateid_rsize, .op_get_currentstateid = nfsd4_get_lockustateid, }, [OP_LOOKUP] = { .op_func = (nfsd4op_func)nfsd4_lookup, .op_flags = OP_HANDLES_WRONGSEC | OP_CLEAR_STATEID, .op_name = "OP_LOOKUP", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_LOOKUPP] = { .op_func = (nfsd4op_func)nfsd4_lookupp, .op_flags = OP_HANDLES_WRONGSEC | OP_CLEAR_STATEID, .op_name = "OP_LOOKUPP", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_NVERIFY] = { .op_func = (nfsd4op_func)nfsd4_nverify, .op_name = "OP_NVERIFY", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_OPEN] = { .op_func = (nfsd4op_func)nfsd4_open, .op_flags = OP_HANDLES_WRONGSEC | OP_MODIFIES_SOMETHING, .op_name = "OP_OPEN", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_open_rsize, + .op_rsize_bop = nfsd4_open_rsize, .op_set_currentstateid = nfsd4_set_openstateid, }, [OP_OPEN_CONFIRM] = { .op_func = (nfsd4op_func)nfsd4_open_confirm, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_OPEN_CONFIRM", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize, + .op_rsize_bop = nfsd4_status_stateid_rsize, }, [OP_OPEN_DOWNGRADE] = { .op_func = (nfsd4op_func)nfsd4_open_downgrade, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_OPEN_DOWNGRADE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize, + .op_rsize_bop = nfsd4_status_stateid_rsize, .op_get_currentstateid = nfsd4_get_opendowngradestateid, .op_set_currentstateid = nfsd4_set_opendowngradestateid, }, @@ -2205,56 +2204,56 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID, .op_name = "OP_PUTFH", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_PUTPUBFH] = { .op_func = (nfsd4op_func)nfsd4_putrootfh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID, .op_name = "OP_PUTPUBFH", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_PUTROOTFH] = { .op_func = (nfsd4op_func)nfsd4_putrootfh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID, .op_name = "OP_PUTROOTFH", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_READ] = { .op_func = (nfsd4op_func)nfsd4_read, .op_name = "OP_READ", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_read_rsize, + .op_rsize_bop = nfsd4_read_rsize, .op_get_currentstateid = nfsd4_get_readstateid, }, [OP_READDIR] = { .op_func = (nfsd4op_func)nfsd4_readdir, .op_name = "OP_READDIR", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_readdir_rsize, + .op_rsize_bop = nfsd4_readdir_rsize, }, [OP_READLINK] = { .op_func = (nfsd4op_func)nfsd4_readlink, .op_name = "OP_READLINK", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_readlink_rsize, + .op_rsize_bop = nfsd4_readlink_rsize, }, [OP_REMOVE] = { .op_func = (nfsd4op_func)nfsd4_remove, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_REMOVE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_remove_rsize, + .op_rsize_bop = nfsd4_remove_rsize, }, [OP_RENAME] = { .op_func = (nfsd4op_func)nfsd4_rename, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_RENAME", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_rename_rsize, + .op_rsize_bop = nfsd4_rename_rsize, }, [OP_RENEW] = { .op_func = (nfsd4op_func)nfsd4_renew, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING, .op_name = "OP_RENEW", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_RESTOREFH] = { @@ -2262,25 +2261,25 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING, .op_name = "OP_RESTOREFH", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_SAVEFH] = { .op_func = (nfsd4op_func)nfsd4_savefh, .op_flags = OP_HANDLES_WRONGSEC | OP_MODIFIES_SOMETHING, .op_name = "OP_SAVEFH", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_SECINFO] = { .op_func = (nfsd4op_func)nfsd4_secinfo, .op_flags = OP_HANDLES_WRONGSEC, .op_name = "OP_SECINFO", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_secinfo_rsize, + .op_rsize_bop = nfsd4_secinfo_rsize, }, [OP_SETATTR] = { .op_func = (nfsd4op_func)nfsd4_setattr, .op_name = "OP_SETATTR", .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, - .op_rsize_bop = (nfsd4op_rsize)nfsd4_setattr_rsize, + .op_rsize_bop = nfsd4_setattr_rsize, .op_get_currentstateid = nfsd4_get_setattrstateid, }, [OP_SETCLIENTID] = { @@ -2288,25 +2287,25 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_SETCLIENTID", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_setclientid_rsize, + .op_rsize_bop = nfsd4_setclientid_rsize, }, [OP_SETCLIENTID_CONFIRM] = { .op_func = (nfsd4op_func)nfsd4_setclientid_confirm, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_SETCLIENTID_CONFIRM", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_VERIFY] = { .op_func = (nfsd4op_func)nfsd4_verify, .op_name = "OP_VERIFY", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_WRITE] = { .op_func = (nfsd4op_func)nfsd4_write, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_WRITE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_write_rsize, + .op_rsize_bop = nfsd4_write_rsize, .op_get_currentstateid = nfsd4_get_writestateid, }, [OP_RELEASE_LOCKOWNER] = { @@ -2314,7 +2313,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING, .op_name = "OP_RELEASE_LOCKOWNER", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, /* NFSv4.1 operations */ @@ -2323,97 +2322,97 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_EXCHANGE_ID", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_exchange_id_rsize, + .op_rsize_bop = nfsd4_exchange_id_rsize, }, [OP_BACKCHANNEL_CTL] = { .op_func = (nfsd4op_func)nfsd4_backchannel_ctl, .op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING, .op_name = "OP_BACKCHANNEL_CTL", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_BIND_CONN_TO_SESSION] = { .op_func = (nfsd4op_func)nfsd4_bind_conn_to_session, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_BIND_CONN_TO_SESSION", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_bind_conn_to_session_rsize, + .op_rsize_bop = nfsd4_bind_conn_to_session_rsize, }, [OP_CREATE_SESSION] = { .op_func = (nfsd4op_func)nfsd4_create_session, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_CREATE_SESSION", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_create_session_rsize, + .op_rsize_bop = nfsd4_create_session_rsize, }, [OP_DESTROY_SESSION] = { .op_func = (nfsd4op_func)nfsd4_destroy_session, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_DESTROY_SESSION", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_SEQUENCE] = { .op_func = (nfsd4op_func)nfsd4_sequence, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP, .op_name = "OP_SEQUENCE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_sequence_rsize, + .op_rsize_bop = nfsd4_sequence_rsize, }, [OP_DESTROY_CLIENTID] = { .op_func = (nfsd4op_func)nfsd4_destroy_clientid, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_DESTROY_CLIENTID", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_RECLAIM_COMPLETE] = { .op_func = (nfsd4op_func)nfsd4_reclaim_complete, .op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING, .op_name = "OP_RECLAIM_COMPLETE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_SECINFO_NO_NAME] = { .op_func = (nfsd4op_func)nfsd4_secinfo_no_name, .op_flags = OP_HANDLES_WRONGSEC, .op_name = "OP_SECINFO_NO_NAME", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_secinfo_rsize, + .op_rsize_bop = nfsd4_secinfo_rsize, }, [OP_TEST_STATEID] = { .op_func = (nfsd4op_func)nfsd4_test_stateid, .op_flags = ALLOWED_WITHOUT_FH, .op_name = "OP_TEST_STATEID", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_test_stateid_rsize, + .op_rsize_bop = nfsd4_test_stateid_rsize, }, [OP_FREE_STATEID] = { .op_func = (nfsd4op_func)nfsd4_free_stateid, .op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING, .op_name = "OP_FREE_STATEID", .op_get_currentstateid = nfsd4_get_freestateid, - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, #ifdef CONFIG_NFSD_PNFS [OP_GETDEVICEINFO] = { .op_func = (nfsd4op_func)nfsd4_getdeviceinfo, .op_flags = ALLOWED_WITHOUT_FH, .op_name = "OP_GETDEVICEINFO", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_getdeviceinfo_rsize, + .op_rsize_bop = nfsd4_getdeviceinfo_rsize, }, [OP_LAYOUTGET] = { .op_func = (nfsd4op_func)nfsd4_layoutget, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LAYOUTGET", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutget_rsize, + .op_rsize_bop = nfsd4_layoutget_rsize, }, [OP_LAYOUTCOMMIT] = { .op_func = (nfsd4op_func)nfsd4_layoutcommit, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LAYOUTCOMMIT", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutcommit_rsize, + .op_rsize_bop = nfsd4_layoutcommit_rsize, }, [OP_LAYOUTRETURN] = { .op_func = (nfsd4op_func)nfsd4_layoutreturn, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LAYOUTRETURN", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutreturn_rsize, + .op_rsize_bop = nfsd4_layoutreturn_rsize, }, #endif /* CONFIG_NFSD_PNFS */ @@ -2422,30 +2421,30 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_func = (nfsd4op_func)nfsd4_allocate, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_ALLOCATE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_DEALLOCATE] = { .op_func = (nfsd4op_func)nfsd4_deallocate, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_DEALLOCATE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_CLONE] = { .op_func = (nfsd4op_func)nfsd4_clone, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_CLONE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_COPY] = { .op_func = (nfsd4op_func)nfsd4_copy, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_COPY", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_copy_rsize, + .op_rsize_bop = nfsd4_copy_rsize, }, [OP_SEEK] = { .op_func = (nfsd4op_func)nfsd4_seek, .op_name = "OP_SEEK", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_seek_rsize, + .op_rsize_bop = nfsd4_seek_rsize, }, }; -- cgit v1.2.3-59-g8ed1b From eb69853da9459280d89876cfc3da11292e59f7af Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 20:58:35 +0200 Subject: nfsd4: properly type op_func callbacks Pass union nfsd4_op_u to the op_func callbacks instead of using unsafe function pointer casts. It also adds two missing structures to struct nfsd4_op.u to facilitate this. Signed-off-by: Christoph Hellwig --- fs/nfsd/nfs4proc.c | 234 ++++++++++++++++++++++++++++------------------------ fs/nfsd/nfs4state.c | 82 +++++++++++------- fs/nfsd/xdr4.h | 66 +++++++-------- 3 files changed, 209 insertions(+), 173 deletions(-) diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 0bd4b750262f..a947dcef5e4e 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -344,8 +344,9 @@ copy_clientid(clientid_t *clid, struct nfsd4_session *session) static __be32 nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_open *open) + union nfsd4_op_u *u) { + struct nfsd4_open *open = &u->open; __be32 status; struct svc_fh *resfh = NULL; struct net *net = SVC_NET(rqstp); @@ -467,14 +468,14 @@ out: */ static __be32 nfsd4_open_omfg(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_op *op) { - struct nfsd4_open *open = (struct nfsd4_open *)&op->u; + struct nfsd4_open *open = &op->u.open; if (!seqid_mutating_err(ntohl(op->status))) return op->status; if (nfsd4_has_session(cstate)) return op->status; open->op_xdr_error = op->status; - return nfsd4_open(rqstp, cstate, open); + return nfsd4_open(rqstp, cstate, &op->u); } /* @@ -482,19 +483,21 @@ static __be32 nfsd4_open_omfg(struct svc_rqst *rqstp, struct nfsd4_compound_stat */ static __be32 nfsd4_getfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct svc_fh **getfh) + union nfsd4_op_u *u) { if (!cstate->current_fh.fh_dentry) return nfserr_nofilehandle; - *getfh = &cstate->current_fh; + u->getfh = &cstate->current_fh; return nfs_ok; } static __be32 nfsd4_putfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_putfh *putfh) + union nfsd4_op_u *u) { + struct nfsd4_putfh *putfh = &u->putfh; + fh_put(&cstate->current_fh); cstate->current_fh.fh_handle.fh_size = putfh->pf_fhlen; memcpy(&cstate->current_fh.fh_handle.fh_base, putfh->pf_fhval, @@ -504,7 +507,7 @@ nfsd4_putfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_putrootfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - void *arg) + union nfsd4_op_u *u) { __be32 status; @@ -515,7 +518,7 @@ nfsd4_putrootfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_restorefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - void *arg) + union nfsd4_op_u *u) { if (!cstate->save_fh.fh_dentry) return nfserr_restorefh; @@ -530,7 +533,7 @@ nfsd4_restorefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_savefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - void *arg) + union nfsd4_op_u *u) { if (!cstate->current_fh.fh_dentry) return nfserr_nofilehandle; @@ -548,8 +551,10 @@ nfsd4_savefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, */ static __be32 nfsd4_access(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_access *access) + union nfsd4_op_u *u) { + struct nfsd4_access *access = &u->access; + if (access->ac_req_access & ~NFS3_ACCESS_FULL) return nfserr_inval; @@ -574,8 +579,10 @@ static void gen_boot_verifier(nfs4_verifier *verifier, struct net *net) static __be32 nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_commit *commit) + union nfsd4_op_u *u) { + struct nfsd4_commit *commit = &u->commit; + gen_boot_verifier(&commit->co_verf, SVC_NET(rqstp)); return nfsd_commit(rqstp, &cstate->current_fh, commit->co_offset, commit->co_count); @@ -583,8 +590,9 @@ nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_create *create) + union nfsd4_op_u *u) { + struct nfsd4_create *create = &u->create; struct svc_fh resfh; __be32 status; dev_t rdev; @@ -670,8 +678,9 @@ out: static __be32 nfsd4_getattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_getattr *getattr) + union nfsd4_op_u *u) { + struct nfsd4_getattr *getattr = &u->getattr; __be32 status; status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP); @@ -691,8 +700,9 @@ nfsd4_getattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_link(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_link *link) + union nfsd4_op_u *u) { + struct nfsd4_link *link = &u->link; __be32 status = nfserr_nofilehandle; if (!cstate->save_fh.fh_dentry) @@ -723,24 +733,25 @@ static __be32 nfsd4_do_lookupp(struct svc_rqst *rqstp, struct svc_fh *fh) static __be32 nfsd4_lookupp(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - void *arg) + union nfsd4_op_u *u) { return nfsd4_do_lookupp(rqstp, &cstate->current_fh); } static __be32 nfsd4_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_lookup *lookup) + union nfsd4_op_u *u) { return nfsd_lookup(rqstp, &cstate->current_fh, - lookup->lo_name, lookup->lo_len, + u->lookup.lo_name, u->lookup.lo_len, &cstate->current_fh); } static __be32 nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_read *read) + union nfsd4_op_u *u) { + struct nfsd4_read *read = &u->read; __be32 status; read->rd_filp = NULL; @@ -775,8 +786,9 @@ out: static __be32 nfsd4_readdir(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_readdir *readdir) + union nfsd4_op_u *u) { + struct nfsd4_readdir *readdir = &u->readdir; u64 cookie = readdir->rd_cookie; static const nfs4_verifier zeroverf; @@ -800,17 +812,18 @@ nfsd4_readdir(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_readlink(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_readlink *readlink) + union nfsd4_op_u *u) { - readlink->rl_rqstp = rqstp; - readlink->rl_fhp = &cstate->current_fh; + u->readlink.rl_rqstp = rqstp; + u->readlink.rl_fhp = &cstate->current_fh; return nfs_ok; } static __be32 nfsd4_remove(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_remove *remove) + union nfsd4_op_u *u) { + struct nfsd4_remove *remove = &u->remove; __be32 status; if (opens_in_grace(SVC_NET(rqstp))) @@ -826,8 +839,9 @@ nfsd4_remove(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_rename(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_rename *rename) + union nfsd4_op_u *u) { + struct nfsd4_rename *rename = &u->rename; __be32 status = nfserr_nofilehandle; if (!cstate->save_fh.fh_dentry) @@ -847,8 +861,9 @@ nfsd4_rename(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_secinfo *secinfo) + union nfsd4_op_u *u) { + struct nfsd4_secinfo *secinfo = &u->secinfo; struct svc_export *exp; struct dentry *dentry; __be32 err; @@ -876,11 +891,11 @@ nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_secinfo_no_name(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_secinfo_no_name *sin) + union nfsd4_op_u *u) { __be32 err; - switch (sin->sin_style) { + switch (u->secinfo_no_name.sin_style) { case NFS4_SECINFO_STYLE4_CURRENT_FH: break; case NFS4_SECINFO_STYLE4_PARENT: @@ -892,15 +907,16 @@ nfsd4_secinfo_no_name(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstat return nfserr_inval; } - sin->sin_exp = exp_get(cstate->current_fh.fh_export); + u->secinfo_no_name.sin_exp = exp_get(cstate->current_fh.fh_export); fh_put(&cstate->current_fh); return nfs_ok; } static __be32 nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_setattr *setattr) + union nfsd4_op_u *u) { + struct nfsd4_setattr *setattr = &u->setattr; __be32 status = nfs_ok; int err; @@ -960,8 +976,9 @@ static int fill_in_write_vector(struct kvec *vec, struct nfsd4_write *write) static __be32 nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_write *write) + union nfsd4_op_u *u) { + struct nfsd4_write *write = &u->write; stateid_t *stateid = &write->wr_stateid; struct file *filp = NULL; __be32 status = nfs_ok; @@ -1034,8 +1051,9 @@ out_put_src: static __be32 nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_clone *clone) + union nfsd4_op_u *u) { + struct nfsd4_clone *clone = &u->clone; struct file *src, *dst; __be32 status; @@ -1055,8 +1073,9 @@ out: static __be32 nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_copy *copy) + union nfsd4_op_u *u) { + struct nfsd4_copy *copy = &u->copy; struct file *src, *dst; __be32 status; ssize_t bytes; @@ -1111,23 +1130,24 @@ nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_allocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_fallocate *fallocate) + union nfsd4_op_u *u) { - return nfsd4_fallocate(rqstp, cstate, fallocate, 0); + return nfsd4_fallocate(rqstp, cstate, &u->allocate, 0); } static __be32 nfsd4_deallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_fallocate *fallocate) + union nfsd4_op_u *u) { - return nfsd4_fallocate(rqstp, cstate, fallocate, + return nfsd4_fallocate(rqstp, cstate, &u->deallocate, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE); } static __be32 nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_seek *seek) + union nfsd4_op_u *u) { + struct nfsd4_seek *seek = &u->seek; int whence; __be32 status; struct file *file; @@ -1232,21 +1252,21 @@ out_kfree: static __be32 nfsd4_nverify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_verify *verify) + union nfsd4_op_u *u) { __be32 status; - status = _nfsd4_verify(rqstp, cstate, verify); + status = _nfsd4_verify(rqstp, cstate, &u->verify); return status == nfserr_not_same ? nfs_ok : status; } static __be32 nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_verify *verify) + union nfsd4_op_u *u) { __be32 status; - status = _nfsd4_verify(rqstp, cstate, verify); + status = _nfsd4_verify(rqstp, cstate, &u->nverify); return status == nfserr_same ? nfs_ok : status; } @@ -1271,9 +1291,9 @@ nfsd4_layout_verify(struct svc_export *exp, unsigned int layout_type) static __be32 nfsd4_getdeviceinfo(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_getdeviceinfo *gdp) + struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct nfsd4_getdeviceinfo *gdp = &u->getdeviceinfo; const struct nfsd4_layout_ops *ops; struct nfsd4_deviceid_map *map; struct svc_export *exp; @@ -1317,9 +1337,9 @@ out: static __be32 nfsd4_layoutget(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_layoutget *lgp) + struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct nfsd4_layoutget *lgp = &u->layoutget; struct svc_fh *current_fh = &cstate->current_fh; const struct nfsd4_layout_ops *ops; struct nfs4_layout_stateid *ls; @@ -1397,9 +1417,9 @@ out: static __be32 nfsd4_layoutcommit(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_layoutcommit *lcp) + struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct nfsd4_layoutcommit *lcp = &u->layoutcommit; const struct nfsd4_layout_seg *seg = &lcp->lc_seg; struct svc_fh *current_fh = &cstate->current_fh; const struct nfsd4_layout_ops *ops; @@ -1461,9 +1481,9 @@ out: static __be32 nfsd4_layoutreturn(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_layoutreturn *lrp) + struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct nfsd4_layoutreturn *lrp = &u->layoutreturn; struct svc_fh *current_fh = &cstate->current_fh; __be32 nfserr; @@ -1521,9 +1541,6 @@ static inline void nfsd4_increment_op_stats(u32 opnum) nfsdstats.nfs4_opcount[opnum]++; } -typedef __be32(*nfsd4op_func)(struct svc_rqst *, struct nfsd4_compound_state *, - void *); - enum nfsd4_op_flags { ALLOWED_WITHOUT_FH = 1 << 0, /* No current filehandle required */ ALLOWED_ON_ABSENT_FS = 1 << 1, /* ops processed on absent fs */ @@ -1555,7 +1572,8 @@ enum nfsd4_op_flags { }; struct nfsd4_operation { - nfsd4op_func op_func; + __be32 (*op_func)(struct svc_rqst *, struct nfsd4_compound_state *, + union nfsd4_op_u *); u32 op_flags; char *op_name; /* Try to get response size before operation */ @@ -2093,12 +2111,12 @@ static inline u32 nfsd4_seek_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) static struct nfsd4_operation nfsd4_ops[] = { [OP_ACCESS] = { - .op_func = (nfsd4op_func)nfsd4_access, + .op_func = nfsd4_access, .op_name = "OP_ACCESS", .op_rsize_bop = nfsd4_access_rsize, }, [OP_CLOSE] = { - .op_func = (nfsd4op_func)nfsd4_close, + .op_func = nfsd4_close, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_CLOSE", .op_rsize_bop = nfsd4_status_stateid_rsize, @@ -2106,93 +2124,93 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_set_currentstateid = nfsd4_set_closestateid, }, [OP_COMMIT] = { - .op_func = (nfsd4op_func)nfsd4_commit, + .op_func = nfsd4_commit, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_COMMIT", .op_rsize_bop = nfsd4_commit_rsize, }, [OP_CREATE] = { - .op_func = (nfsd4op_func)nfsd4_create, + .op_func = nfsd4_create, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME | OP_CLEAR_STATEID, .op_name = "OP_CREATE", .op_rsize_bop = nfsd4_create_rsize, }, [OP_DELEGRETURN] = { - .op_func = (nfsd4op_func)nfsd4_delegreturn, + .op_func = nfsd4_delegreturn, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_DELEGRETURN", .op_rsize_bop = nfsd4_only_status_rsize, .op_get_currentstateid = nfsd4_get_delegreturnstateid, }, [OP_GETATTR] = { - .op_func = (nfsd4op_func)nfsd4_getattr, + .op_func = nfsd4_getattr, .op_flags = ALLOWED_ON_ABSENT_FS, .op_rsize_bop = nfsd4_getattr_rsize, .op_name = "OP_GETATTR", }, [OP_GETFH] = { - .op_func = (nfsd4op_func)nfsd4_getfh, + .op_func = nfsd4_getfh, .op_name = "OP_GETFH", .op_rsize_bop = nfsd4_getfh_rsize, }, [OP_LINK] = { - .op_func = (nfsd4op_func)nfsd4_link, + .op_func = nfsd4_link, .op_flags = ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_LINK", .op_rsize_bop = nfsd4_link_rsize, }, [OP_LOCK] = { - .op_func = (nfsd4op_func)nfsd4_lock, + .op_func = nfsd4_lock, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LOCK", .op_rsize_bop = nfsd4_lock_rsize, .op_set_currentstateid = nfsd4_set_lockstateid, }, [OP_LOCKT] = { - .op_func = (nfsd4op_func)nfsd4_lockt, + .op_func = nfsd4_lockt, .op_name = "OP_LOCKT", .op_rsize_bop = nfsd4_lock_rsize, }, [OP_LOCKU] = { - .op_func = (nfsd4op_func)nfsd4_locku, + .op_func = nfsd4_locku, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LOCKU", .op_rsize_bop = nfsd4_status_stateid_rsize, .op_get_currentstateid = nfsd4_get_lockustateid, }, [OP_LOOKUP] = { - .op_func = (nfsd4op_func)nfsd4_lookup, + .op_func = nfsd4_lookup, .op_flags = OP_HANDLES_WRONGSEC | OP_CLEAR_STATEID, .op_name = "OP_LOOKUP", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_LOOKUPP] = { - .op_func = (nfsd4op_func)nfsd4_lookupp, + .op_func = nfsd4_lookupp, .op_flags = OP_HANDLES_WRONGSEC | OP_CLEAR_STATEID, .op_name = "OP_LOOKUPP", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_NVERIFY] = { - .op_func = (nfsd4op_func)nfsd4_nverify, + .op_func = nfsd4_nverify, .op_name = "OP_NVERIFY", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_OPEN] = { - .op_func = (nfsd4op_func)nfsd4_open, + .op_func = nfsd4_open, .op_flags = OP_HANDLES_WRONGSEC | OP_MODIFIES_SOMETHING, .op_name = "OP_OPEN", .op_rsize_bop = nfsd4_open_rsize, .op_set_currentstateid = nfsd4_set_openstateid, }, [OP_OPEN_CONFIRM] = { - .op_func = (nfsd4op_func)nfsd4_open_confirm, + .op_func = nfsd4_open_confirm, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_OPEN_CONFIRM", .op_rsize_bop = nfsd4_status_stateid_rsize, }, [OP_OPEN_DOWNGRADE] = { - .op_func = (nfsd4op_func)nfsd4_open_downgrade, + .op_func = nfsd4_open_downgrade, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_OPEN_DOWNGRADE", .op_rsize_bop = nfsd4_status_stateid_rsize, @@ -2200,56 +2218,56 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_set_currentstateid = nfsd4_set_opendowngradestateid, }, [OP_PUTFH] = { - .op_func = (nfsd4op_func)nfsd4_putfh, + .op_func = nfsd4_putfh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID, .op_name = "OP_PUTFH", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_PUTPUBFH] = { - .op_func = (nfsd4op_func)nfsd4_putrootfh, + .op_func = nfsd4_putrootfh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID, .op_name = "OP_PUTPUBFH", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_PUTROOTFH] = { - .op_func = (nfsd4op_func)nfsd4_putrootfh, + .op_func = nfsd4_putrootfh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID, .op_name = "OP_PUTROOTFH", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_READ] = { - .op_func = (nfsd4op_func)nfsd4_read, + .op_func = nfsd4_read, .op_name = "OP_READ", .op_rsize_bop = nfsd4_read_rsize, .op_get_currentstateid = nfsd4_get_readstateid, }, [OP_READDIR] = { - .op_func = (nfsd4op_func)nfsd4_readdir, + .op_func = nfsd4_readdir, .op_name = "OP_READDIR", .op_rsize_bop = nfsd4_readdir_rsize, }, [OP_READLINK] = { - .op_func = (nfsd4op_func)nfsd4_readlink, + .op_func = nfsd4_readlink, .op_name = "OP_READLINK", .op_rsize_bop = nfsd4_readlink_rsize, }, [OP_REMOVE] = { - .op_func = (nfsd4op_func)nfsd4_remove, + .op_func = nfsd4_remove, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_REMOVE", .op_rsize_bop = nfsd4_remove_rsize, }, [OP_RENAME] = { - .op_func = (nfsd4op_func)nfsd4_rename, + .op_func = nfsd4_rename, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_RENAME", .op_rsize_bop = nfsd4_rename_rsize, }, [OP_RENEW] = { - .op_func = (nfsd4op_func)nfsd4_renew, + .op_func = nfsd4_renew, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING, .op_name = "OP_RENEW", @@ -2257,59 +2275,59 @@ static struct nfsd4_operation nfsd4_ops[] = { }, [OP_RESTOREFH] = { - .op_func = (nfsd4op_func)nfsd4_restorefh, + .op_func = nfsd4_restorefh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING, .op_name = "OP_RESTOREFH", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_SAVEFH] = { - .op_func = (nfsd4op_func)nfsd4_savefh, + .op_func = nfsd4_savefh, .op_flags = OP_HANDLES_WRONGSEC | OP_MODIFIES_SOMETHING, .op_name = "OP_SAVEFH", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_SECINFO] = { - .op_func = (nfsd4op_func)nfsd4_secinfo, + .op_func = nfsd4_secinfo, .op_flags = OP_HANDLES_WRONGSEC, .op_name = "OP_SECINFO", .op_rsize_bop = nfsd4_secinfo_rsize, }, [OP_SETATTR] = { - .op_func = (nfsd4op_func)nfsd4_setattr, + .op_func = nfsd4_setattr, .op_name = "OP_SETATTR", .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_rsize_bop = nfsd4_setattr_rsize, .op_get_currentstateid = nfsd4_get_setattrstateid, }, [OP_SETCLIENTID] = { - .op_func = (nfsd4op_func)nfsd4_setclientid, + .op_func = nfsd4_setclientid, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_SETCLIENTID", .op_rsize_bop = nfsd4_setclientid_rsize, }, [OP_SETCLIENTID_CONFIRM] = { - .op_func = (nfsd4op_func)nfsd4_setclientid_confirm, + .op_func = nfsd4_setclientid_confirm, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_SETCLIENTID_CONFIRM", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_VERIFY] = { - .op_func = (nfsd4op_func)nfsd4_verify, + .op_func = nfsd4_verify, .op_name = "OP_VERIFY", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_WRITE] = { - .op_func = (nfsd4op_func)nfsd4_write, + .op_func = nfsd4_write, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_WRITE", .op_rsize_bop = nfsd4_write_rsize, .op_get_currentstateid = nfsd4_get_writestateid, }, [OP_RELEASE_LOCKOWNER] = { - .op_func = (nfsd4op_func)nfsd4_release_lockowner, + .op_func = nfsd4_release_lockowner, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING, .op_name = "OP_RELEASE_LOCKOWNER", @@ -2318,72 +2336,72 @@ static struct nfsd4_operation nfsd4_ops[] = { /* NFSv4.1 operations */ [OP_EXCHANGE_ID] = { - .op_func = (nfsd4op_func)nfsd4_exchange_id, + .op_func = nfsd4_exchange_id, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_EXCHANGE_ID", .op_rsize_bop = nfsd4_exchange_id_rsize, }, [OP_BACKCHANNEL_CTL] = { - .op_func = (nfsd4op_func)nfsd4_backchannel_ctl, + .op_func = nfsd4_backchannel_ctl, .op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING, .op_name = "OP_BACKCHANNEL_CTL", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_BIND_CONN_TO_SESSION] = { - .op_func = (nfsd4op_func)nfsd4_bind_conn_to_session, + .op_func = nfsd4_bind_conn_to_session, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_BIND_CONN_TO_SESSION", .op_rsize_bop = nfsd4_bind_conn_to_session_rsize, }, [OP_CREATE_SESSION] = { - .op_func = (nfsd4op_func)nfsd4_create_session, + .op_func = nfsd4_create_session, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_CREATE_SESSION", .op_rsize_bop = nfsd4_create_session_rsize, }, [OP_DESTROY_SESSION] = { - .op_func = (nfsd4op_func)nfsd4_destroy_session, + .op_func = nfsd4_destroy_session, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_DESTROY_SESSION", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_SEQUENCE] = { - .op_func = (nfsd4op_func)nfsd4_sequence, + .op_func = nfsd4_sequence, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP, .op_name = "OP_SEQUENCE", .op_rsize_bop = nfsd4_sequence_rsize, }, [OP_DESTROY_CLIENTID] = { - .op_func = (nfsd4op_func)nfsd4_destroy_clientid, + .op_func = nfsd4_destroy_clientid, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_DESTROY_CLIENTID", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_RECLAIM_COMPLETE] = { - .op_func = (nfsd4op_func)nfsd4_reclaim_complete, + .op_func = nfsd4_reclaim_complete, .op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING, .op_name = "OP_RECLAIM_COMPLETE", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_SECINFO_NO_NAME] = { - .op_func = (nfsd4op_func)nfsd4_secinfo_no_name, + .op_func = nfsd4_secinfo_no_name, .op_flags = OP_HANDLES_WRONGSEC, .op_name = "OP_SECINFO_NO_NAME", .op_rsize_bop = nfsd4_secinfo_rsize, }, [OP_TEST_STATEID] = { - .op_func = (nfsd4op_func)nfsd4_test_stateid, + .op_func = nfsd4_test_stateid, .op_flags = ALLOWED_WITHOUT_FH, .op_name = "OP_TEST_STATEID", .op_rsize_bop = nfsd4_test_stateid_rsize, }, [OP_FREE_STATEID] = { - .op_func = (nfsd4op_func)nfsd4_free_stateid, + .op_func = nfsd4_free_stateid, .op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING, .op_name = "OP_FREE_STATEID", .op_get_currentstateid = nfsd4_get_freestateid, @@ -2391,25 +2409,25 @@ static struct nfsd4_operation nfsd4_ops[] = { }, #ifdef CONFIG_NFSD_PNFS [OP_GETDEVICEINFO] = { - .op_func = (nfsd4op_func)nfsd4_getdeviceinfo, + .op_func = nfsd4_getdeviceinfo, .op_flags = ALLOWED_WITHOUT_FH, .op_name = "OP_GETDEVICEINFO", .op_rsize_bop = nfsd4_getdeviceinfo_rsize, }, [OP_LAYOUTGET] = { - .op_func = (nfsd4op_func)nfsd4_layoutget, + .op_func = nfsd4_layoutget, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LAYOUTGET", .op_rsize_bop = nfsd4_layoutget_rsize, }, [OP_LAYOUTCOMMIT] = { - .op_func = (nfsd4op_func)nfsd4_layoutcommit, + .op_func = nfsd4_layoutcommit, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LAYOUTCOMMIT", .op_rsize_bop = nfsd4_layoutcommit_rsize, }, [OP_LAYOUTRETURN] = { - .op_func = (nfsd4op_func)nfsd4_layoutreturn, + .op_func = nfsd4_layoutreturn, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LAYOUTRETURN", .op_rsize_bop = nfsd4_layoutreturn_rsize, @@ -2418,31 +2436,31 @@ static struct nfsd4_operation nfsd4_ops[] = { /* NFSv4.2 operations */ [OP_ALLOCATE] = { - .op_func = (nfsd4op_func)nfsd4_allocate, + .op_func = nfsd4_allocate, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_ALLOCATE", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_DEALLOCATE] = { - .op_func = (nfsd4op_func)nfsd4_deallocate, + .op_func = nfsd4_deallocate, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_DEALLOCATE", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_CLONE] = { - .op_func = (nfsd4op_func)nfsd4_clone, + .op_func = nfsd4_clone, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_CLONE", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_COPY] = { - .op_func = (nfsd4op_func)nfsd4_copy, + .op_func = nfsd4_copy, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_COPY", .op_rsize_bop = nfsd4_copy_rsize, }, [OP_SEEK] = { - .op_func = (nfsd4op_func)nfsd4_seek, + .op_func = nfsd4_seek, .op_name = "OP_SEEK", .op_rsize_bop = nfsd4_seek_rsize, }, diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 01ab21f8d34d..0c04f81aa63b 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -2402,10 +2402,10 @@ static bool client_has_state(struct nfs4_client *clp) } __be32 -nfsd4_exchange_id(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_exchange_id *exid) +nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { + struct nfsd4_exchange_id *exid = &u->exchange_id; struct nfs4_client *conf, *new; struct nfs4_client *unconf = NULL; __be32 status; @@ -2698,9 +2698,9 @@ static __be32 nfsd4_check_cb_sec(struct nfsd4_cb_sec *cbs) __be32 nfsd4_create_session(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_create_session *cr_ses) + struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct nfsd4_create_session *cr_ses = &u->create_session; struct sockaddr *sa = svc_addr(rqstp); struct nfs4_client *conf, *unconf; struct nfs4_client *old = NULL; @@ -2824,8 +2824,11 @@ static __be32 nfsd4_map_bcts_dir(u32 *dir) return nfserr_inval; } -__be32 nfsd4_backchannel_ctl(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_backchannel_ctl *bc) +__be32 nfsd4_backchannel_ctl(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { + struct nfsd4_backchannel_ctl *bc = &u->backchannel_ctl; struct nfsd4_session *session = cstate->session; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); __be32 status; @@ -2845,8 +2848,9 @@ __be32 nfsd4_backchannel_ctl(struct svc_rqst *rqstp, struct nfsd4_compound_state __be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_bind_conn_to_session *bcts) + union nfsd4_op_u *u) { + struct nfsd4_bind_conn_to_session *bcts = &u->bind_conn_to_session; __be32 status; struct nfsd4_conn *conn; struct nfsd4_session *session; @@ -2886,10 +2890,10 @@ static bool nfsd4_compound_in_session(struct nfsd4_session *session, struct nfs4 } __be32 -nfsd4_destroy_session(struct svc_rqst *r, - struct nfsd4_compound_state *cstate, - struct nfsd4_destroy_session *sessionid) +nfsd4_destroy_session(struct svc_rqst *r, struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { + struct nfsd4_destroy_session *sessionid = &u->destroy_session; struct nfsd4_session *ses; __be32 status; int ref_held_by_me = 0; @@ -2983,10 +2987,10 @@ static bool nfsd4_request_too_big(struct svc_rqst *rqstp, } __be32 -nfsd4_sequence(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_sequence *seq) +nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { + struct nfsd4_sequence *seq = &u->sequence; struct nfsd4_compoundres *resp = rqstp->rq_resp; struct xdr_stream *xdr = &resp->xdr; struct nfsd4_session *session; @@ -3120,8 +3124,11 @@ nfsd4_sequence_done(struct nfsd4_compoundres *resp) } __be32 -nfsd4_destroy_clientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_destroy_clientid *dc) +nfsd4_destroy_clientid(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { + struct nfsd4_destroy_clientid *dc = &u->destroy_clientid; struct nfs4_client *conf, *unconf; struct nfs4_client *clp = NULL; __be32 status = 0; @@ -3161,8 +3168,10 @@ out: } __be32 -nfsd4_reclaim_complete(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_reclaim_complete *rc) +nfsd4_reclaim_complete(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct nfsd4_reclaim_complete *rc = &u->reclaim_complete; __be32 status = 0; if (rc->rca_one_fs) { @@ -3199,8 +3208,9 @@ out: __be32 nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_setclientid *setclid) + union nfsd4_op_u *u) { + struct nfsd4_setclientid *setclid = &u->setclientid; struct xdr_netobj clname = setclid->se_name; nfs4_verifier clverifier = setclid->se_verf; struct nfs4_client *conf, *new; @@ -3257,9 +3267,11 @@ out: __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_setclientid_confirm *setclientid_confirm) + struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { + struct nfsd4_setclientid_confirm *setclientid_confirm = + &u->setclientid_confirm; struct nfs4_client *conf, *unconf; struct nfs4_client *old = NULL; nfs4_verifier confirm = setclientid_confirm->sc_confirm; @@ -4506,8 +4518,9 @@ void nfsd4_cleanup_open_state(struct nfsd4_compound_state *cstate, __be32 nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - clientid_t *clid) + union nfsd4_op_u *u) { + clientid_t *clid = &u->renew; struct nfs4_client *clp; __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); @@ -4993,8 +5006,9 @@ out: */ __be32 nfsd4_test_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_test_stateid *test_stateid) + union nfsd4_op_u *u) { + struct nfsd4_test_stateid *test_stateid = &u->test_stateid; struct nfsd4_test_stateid_id *stateid; struct nfs4_client *cl = cstate->session->se_client; @@ -5033,8 +5047,9 @@ out: __be32 nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_free_stateid *free_stateid) + union nfsd4_op_u *u) { + struct nfsd4_free_stateid *free_stateid = &u->free_stateid; stateid_t *stateid = &free_stateid->fr_stateid; struct nfs4_stid *s; struct nfs4_delegation *dp; @@ -5162,8 +5177,9 @@ static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cs __be32 nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_open_confirm *oc) + union nfsd4_op_u *u) { + struct nfsd4_open_confirm *oc = &u->open_confirm; __be32 status; struct nfs4_openowner *oo; struct nfs4_ol_stateid *stp; @@ -5230,9 +5246,9 @@ static inline void nfs4_stateid_downgrade(struct nfs4_ol_stateid *stp, u32 to_ac __be32 nfsd4_open_downgrade(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_open_downgrade *od) + struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct nfsd4_open_downgrade *od = &u->open_downgrade; __be32 status; struct nfs4_ol_stateid *stp; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); @@ -5300,8 +5316,9 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s) */ __be32 nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_close *close) + union nfsd4_op_u *u) { + struct nfsd4_close *close = &u->close; __be32 status; struct nfs4_ol_stateid *stp; struct net *net = SVC_NET(rqstp); @@ -5330,8 +5347,9 @@ out: __be32 nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_delegreturn *dr) + union nfsd4_op_u *u) { + struct nfsd4_delegreturn *dr = &u->delegreturn; struct nfs4_delegation *dp; stateid_t *stateid = &dr->dr_stateid; struct nfs4_stid *s; @@ -5706,8 +5724,9 @@ out: */ __be32 nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_lock *lock) + union nfsd4_op_u *u) { + struct nfsd4_lock *lock = &u->lock; struct nfs4_openowner *open_sop = NULL; struct nfs4_lockowner *lock_sop = NULL; struct nfs4_ol_stateid *lock_stp = NULL; @@ -5939,8 +5958,9 @@ static __be32 nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct */ __be32 nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_lockt *lockt) + union nfsd4_op_u *u) { + struct nfsd4_lockt *lockt = &u->lockt; struct file_lock *file_lock = NULL; struct nfs4_lockowner *lo = NULL; __be32 status; @@ -6012,8 +6032,9 @@ out: __be32 nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_locku *locku) + union nfsd4_op_u *u) { + struct nfsd4_locku *locku = &u->locku; struct nfs4_ol_stateid *stp; struct file *filp = NULL; struct file_lock *file_lock = NULL; @@ -6119,8 +6140,9 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) __be32 nfsd4_release_lockowner(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_release_lockowner *rlockowner) + union nfsd4_op_u *u) { + struct nfsd4_release_lockowner *rlockowner = &u->release_lockowner; clientid_t *clid = &rlockowner->rl_clientid; struct nfs4_stateowner *sop; struct nfs4_lockowner *lo = NULL; diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index b625f4aa1061..72c6ad136107 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -577,6 +577,7 @@ struct nfsd4_op { struct nfsd4_bind_conn_to_session bind_conn_to_session; struct nfsd4_create_session create_session; struct nfsd4_destroy_session destroy_session; + struct nfsd4_destroy_clientid destroy_clientid; struct nfsd4_sequence sequence; struct nfsd4_reclaim_complete reclaim_complete; struct nfsd4_test_stateid test_stateid; @@ -585,6 +586,7 @@ struct nfsd4_op { struct nfsd4_layoutget layoutget; struct nfsd4_layoutcommit layoutcommit; struct nfsd4_layoutreturn layoutreturn; + struct nfsd4_secinfo_no_name secinfo_no_name; /* NFSv4.2 */ struct nfsd4_fallocate allocate; @@ -693,27 +695,26 @@ __be32 nfsd4_encode_fattr_to_buf(__be32 **p, int words, struct dentry *dentry, u32 *bmval, struct svc_rqst *, int ignore_crossmnt); extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_setclientid *setclid); + struct nfsd4_compound_state *, union nfsd4_op_u *u); extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_setclientid_confirm *setclientid_confirm); + struct nfsd4_compound_state *, union nfsd4_op_u *u); extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, struct nfsd4_exchange_id *); -extern __be32 nfsd4_backchannel_ctl(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_backchannel_ctl *); -extern __be32 nfsd4_bind_conn_to_session(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_bind_conn_to_session *); + struct nfsd4_compound_state *, union nfsd4_op_u *u); +extern __be32 nfsd4_backchannel_ctl(struct svc_rqst *, + struct nfsd4_compound_state *, union nfsd4_op_u *u); +extern __be32 nfsd4_bind_conn_to_session(struct svc_rqst *, + struct nfsd4_compound_state *, union nfsd4_op_u *u); extern __be32 nfsd4_create_session(struct svc_rqst *, - struct nfsd4_compound_state *, - struct nfsd4_create_session *); + struct nfsd4_compound_state *, union nfsd4_op_u *u); extern __be32 nfsd4_sequence(struct svc_rqst *, - struct nfsd4_compound_state *, - struct nfsd4_sequence *); + struct nfsd4_compound_state *, union nfsd4_op_u *u); extern void nfsd4_sequence_done(struct nfsd4_compoundres *resp); extern __be32 nfsd4_destroy_session(struct svc_rqst *, - struct nfsd4_compound_state *, - struct nfsd4_destroy_session *); -extern __be32 nfsd4_destroy_clientid(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_destroy_clientid *); -__be32 nfsd4_reclaim_complete(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_reclaim_complete *); + struct nfsd4_compound_state *, union nfsd4_op_u *u); +extern __be32 nfsd4_destroy_clientid(struct svc_rqst *, struct nfsd4_compound_state *, + union nfsd4_op_u *u); +__be32 nfsd4_reclaim_complete(struct svc_rqst *, struct nfsd4_compound_state *, + union nfsd4_op_u *u); extern __be32 nfsd4_process_open1(struct nfsd4_compound_state *, struct nfsd4_open *open, struct nfsd_net *nn); extern __be32 nfsd4_process_open2(struct svc_rqst *rqstp, @@ -722,34 +723,29 @@ extern void nfsd4_cstate_clear_replay(struct nfsd4_compound_state *cstate); extern void nfsd4_cleanup_open_state(struct nfsd4_compound_state *cstate, struct nfsd4_open *open); extern __be32 nfsd4_open_confirm(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, struct nfsd4_open_confirm *oc); -extern __be32 nfsd4_close(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_close *close); + struct nfsd4_compound_state *, union nfsd4_op_u *u); +extern __be32 nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *, + union nfsd4_op_u *u); extern __be32 nfsd4_open_downgrade(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_open_downgrade *od); + struct nfsd4_compound_state *, union nfsd4_op_u *u); extern __be32 nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *, - struct nfsd4_lock *lock); -extern __be32 nfsd4_lockt(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_lockt *lockt); -extern __be32 nfsd4_locku(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_locku *locku); + union nfsd4_op_u *u); +extern __be32 nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *, + union nfsd4_op_u *u); +extern __be32 nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *, + union nfsd4_op_u *u); extern __be32 nfsd4_release_lockowner(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_release_lockowner *rlockowner); + struct nfsd4_compound_state *, union nfsd4_op_u *u); extern void nfsd4_release_compoundargs(struct svc_rqst *rqstp); extern __be32 nfsd4_delegreturn(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, struct nfsd4_delegreturn *dr); -extern __be32 nfsd4_renew(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, clientid_t *clid); + struct nfsd4_compound_state *, union nfsd4_op_u *u); +extern __be32 nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *, + union nfsd4_op_u *u); extern __be32 nfsd4_test_stateid(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, struct nfsd4_test_stateid *test_stateid); + struct nfsd4_compound_state *, union nfsd4_op_u *); extern __be32 nfsd4_free_stateid(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, struct nfsd4_free_stateid *free_stateid); + struct nfsd4_compound_state *, union nfsd4_op_u *); extern void nfsd4_bump_seqid(struct nfsd4_compound_state *, __be32 nfserr); #endif -- cgit v1.2.3-59-g8ed1b From 7fd38af9cae6aef1dfd28a7d1bd214eb5ddb7d53 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 23:40:27 +0200 Subject: sunrpc: move pc_count out of struct svc_procinfo pc_count is the only writeable memeber of struct svc_procinfo, which is a good candidate to be const-ified as it contains function pointers. This patch moves it into out out struct svc_procinfo, and into a separate writable array that is pointed to by struct svc_version. Signed-off-by: Christoph Hellwig --- fs/lockd/svc.c | 6 ++++++ fs/nfs/callback_xdr.c | 4 ++++ fs/nfsd/nfs2acl.c | 2 ++ fs/nfsd/nfs3acl.c | 2 ++ fs/nfsd/nfs3proc.c | 2 ++ fs/nfsd/nfs4proc.c | 2 ++ fs/nfsd/nfsproc.c | 2 ++ include/linux/sunrpc/svc.h | 2 +- net/sunrpc/stats.c | 11 ++++++----- net/sunrpc/svc.c | 2 +- 10 files changed, 28 insertions(+), 7 deletions(-) diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 5d481e8a1b5d..cc6abe6280bc 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -739,23 +739,29 @@ module_exit(exit_nlm); /* * Define NLM program and procedures */ +static unsigned int nlmsvc_version1_count[17]; static struct svc_version nlmsvc_version1 = { .vs_vers = 1, .vs_nproc = 17, .vs_proc = nlmsvc_procedures, + .vs_count = nlmsvc_version1_count, .vs_xdrsize = NLMSVC_XDRSIZE, }; +static unsigned int nlmsvc_version3_count[24]; static struct svc_version nlmsvc_version3 = { .vs_vers = 3, .vs_nproc = 24, .vs_proc = nlmsvc_procedures, + .vs_count = nlmsvc_version3_count, .vs_xdrsize = NLMSVC_XDRSIZE, }; #ifdef CONFIG_LOCKD_V4 +static unsigned int nlmsvc_version4_count[24]; static struct svc_version nlmsvc_version4 = { .vs_vers = 4, .vs_nproc = 24, .vs_proc = nlmsvc_procedures4, + .vs_count = nlmsvc_version4_count, .vs_xdrsize = NLMSVC_XDRSIZE, }; #endif diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index acf75dc63e14..ecd46b8c0985 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -1011,20 +1011,24 @@ static struct svc_procedure nfs4_callback_procedures1[] = { } }; +static unsigned int nfs4_callback_count1[ARRAY_SIZE(nfs4_callback_procedures1)]; struct svc_version nfs4_callback_version1 = { .vs_vers = 1, .vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1), .vs_proc = nfs4_callback_procedures1, + .vs_count = nfs4_callback_count1, .vs_xdrsize = NFS4_CALLBACK_XDRSIZE, .vs_dispatch = NULL, .vs_hidden = true, .vs_need_cong_ctrl = true, }; +static unsigned int nfs4_callback_count4[ARRAY_SIZE(nfs4_callback_procedures1)]; struct svc_version nfs4_callback_version4 = { .vs_vers = 4, .vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1), .vs_proc = nfs4_callback_procedures1, + .vs_count = nfs4_callback_count4, .vs_xdrsize = NFS4_CALLBACK_XDRSIZE, .vs_dispatch = NULL, .vs_hidden = true, diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index fc6b179c8fff..026edfe73fd5 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -378,10 +378,12 @@ static struct svc_procedure nfsd_acl_procedures2[] = { PROC(access, access, access, access, RC_NOCACHE, ST+AT+1), }; +static unsigned int nfsd_acl_count2[ARRAY_SIZE(nfsd_acl_procedures2)]; struct svc_version nfsd_acl_version2 = { .vs_vers = 2, .vs_nproc = 5, .vs_proc = nfsd_acl_procedures2, + .vs_count = nfsd_acl_count2, .vs_dispatch = nfsd_dispatch, .vs_xdrsize = NFS3_SVC_XDRSIZE, }; diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 9437b758cbfd..73c0970ccefb 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -263,10 +263,12 @@ static struct svc_procedure nfsd_acl_procedures3[] = { PROC(setacl, setacl, setacl, fhandle, RC_NOCACHE, ST+pAT), }; +static unsigned int nfsd_acl_count3[ARRAY_SIZE(nfsd_acl_procedures3)]; struct svc_version nfsd_acl_version3 = { .vs_vers = 3, .vs_nproc = 3, .vs_proc = nfsd_acl_procedures3, + .vs_count = nfsd_acl_count3, .vs_dispatch = nfsd_dispatch, .vs_xdrsize = NFS3_SVC_XDRSIZE, }; diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 17c90c41a3a6..b5823802e278 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -890,10 +890,12 @@ static struct svc_procedure nfsd_procedures3[22] = { }, }; +static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures3)]; struct svc_version nfsd_version3 = { .vs_vers = 3, .vs_nproc = 22, .vs_proc = nfsd_procedures3, + .vs_count = nfsd_count3, .vs_dispatch = nfsd_dispatch, .vs_xdrsize = NFS3_SVC_XDRSIZE, }; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index a947dcef5e4e..bad5fec0ebc7 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -2554,10 +2554,12 @@ static struct svc_procedure nfsd_procedures4[2] = { }, }; +static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures4)]; struct svc_version nfsd_version4 = { .vs_vers = 4, .vs_nproc = 2, .vs_proc = nfsd_procedures4, + .vs_count = nfsd_count3, .vs_dispatch = nfsd_dispatch, .vs_xdrsize = NFS4_SVC_XDRSIZE, .vs_rpcb_optnl = true, diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 0ef88d0e67d9..44b157553733 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -743,10 +743,12 @@ static struct svc_procedure nfsd_procedures2[18] = { }; +static unsigned int nfsd_count2[ARRAY_SIZE(nfsd_procedures2)]; struct svc_version nfsd_version2 = { .vs_vers = 2, .vs_nproc = 18, .vs_proc = nfsd_procedures2, + .vs_count = nfsd_count2, .vs_dispatch = nfsd_dispatch, .vs_xdrsize = NFS2_SVC_XDRSIZE, }; diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 6cfe41db7f31..9f00384153f4 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -397,6 +397,7 @@ struct svc_version { u32 vs_vers; /* version number */ u32 vs_nproc; /* number of procedures */ struct svc_procedure * vs_proc; /* per-procedure info */ + unsigned int *vs_count; /* call counts */ u32 vs_xdrsize; /* xdrsize needed for this version */ /* Don't register with rpcbind */ @@ -429,7 +430,6 @@ struct svc_procedure { void (*pc_release)(struct svc_rqst *); unsigned int pc_argsize; /* argument struct size */ unsigned int pc_ressize; /* result struct size */ - unsigned int pc_count; /* call count */ unsigned int pc_cachetype; /* cache info (NFS) */ unsigned int pc_xdrressize; /* maximum size of XDR reply */ }; diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c index 8b6c35ae1d57..1e671333c3d5 100644 --- a/net/sunrpc/stats.c +++ b/net/sunrpc/stats.c @@ -77,9 +77,9 @@ static const struct file_operations rpc_proc_fops = { /* * Get RPC server stats */ -void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp) { +void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp) +{ const struct svc_program *prog = statp->program; - const struct svc_procedure *proc; const struct svc_version *vers; unsigned int i, j; @@ -98,11 +98,12 @@ void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp) { statp->rpcbadclnt); for (i = 0; i < prog->pg_nvers; i++) { - if (!(vers = prog->pg_vers[i]) || !(proc = vers->vs_proc)) + vers = prog->pg_vers[i]; + if (!vers) continue; seq_printf(seq, "proc%d %u", i, vers->vs_nproc); - for (j = 0; j < vers->vs_nproc; j++, proc++) - seq_printf(seq, " %u", proc->pc_count); + for (j = 0; j < vers->vs_nproc; j++) + seq_printf(seq, " %u", vers->vs_count[j]); seq_putc(seq, '\n'); } } diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index aa643a29fdc6..6452592194ac 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1261,7 +1261,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) svc_putnl(resv, RPC_SUCCESS); /* Bump per-procedure stats counter */ - procp->pc_count++; + versp->vs_count[proc]++; /* Initialize storage for argp and resp */ memset(rqstp->rq_argp, 0, procp->pc_argsize); -- cgit v1.2.3-59-g8ed1b From 860bda29b99afdc072a7a796fe81185f7ae85deb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 12 May 2017 16:11:49 +0200 Subject: sunrpc: mark all struct svc_procinfo instances as const struct svc_procinfo contains function pointers, and marking it as constant avoids it being able to be used as an attach vector for code injections. Signed-off-by: Christoph Hellwig --- fs/lockd/svc4proc.c | 2 +- fs/lockd/svcproc.c | 2 +- fs/nfs/callback_xdr.c | 2 +- fs/nfsd/nfs2acl.c | 2 +- fs/nfsd/nfs3acl.c | 2 +- fs/nfsd/nfs3proc.c | 2 +- fs/nfsd/nfs4proc.c | 2 +- fs/nfsd/nfsproc.c | 2 +- fs/nfsd/nfssvc.c | 4 ++-- include/linux/lockd/lockd.h | 4 ++-- include/linux/sunrpc/svc.h | 4 ++-- net/sunrpc/svc.c | 2 +- 12 files changed, 15 insertions(+), 15 deletions(-) diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index fed016155791..82925f17ec45 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -507,7 +507,7 @@ struct nlm_void { int dummy; }; #define No (1+1024/4) /* netobj */ #define St 1 /* status */ #define Rg 4 /* range (offset + length) */ -struct svc_procedure nlmsvc_procedures4[] = { +const struct svc_procedure nlmsvc_procedures4[] = { PROC(null, void, void, void, void, 1), PROC(test, testargs, testres, args, res, Ck+St+2+No+Rg), PROC(lock, lockargs, res, args, res, Ck+St), diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index 14648b051eba..07915162581d 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -551,7 +551,7 @@ struct nlm_void { int dummy; }; #define No (1+1024/4) /* Net Obj */ #define Rg 2 /* range - offset + size */ -struct svc_procedure nlmsvc_procedures[] = { +const struct svc_procedure nlmsvc_procedures[] = { PROC(null, void, void, void, void, 1), PROC(test, testargs, testres, args, res, Ck+St+2+No+Rg), PROC(lock, lockargs, res, args, res, Ck+St), diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index ecd46b8c0985..ae249f27297f 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -995,7 +995,7 @@ static struct callback_op callback_ops[] = { /* * Define NFS4 callback procedures */ -static struct svc_procedure nfs4_callback_procedures1[] = { +static const struct svc_procedure nfs4_callback_procedures1[] = { [CB_NULL] = { .pc_func = nfs4_callback_null, .pc_decode = nfs4_decode_void, diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 026edfe73fd5..c3f6b8a6b659 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -370,7 +370,7 @@ struct nfsd3_voidargs { int dummy; }; #define pAT (1+AT) /* post attributes - conditional */ #define ACL (1+NFS_ACL_MAX_ENTRIES*3) /* Access Control List */ -static struct svc_procedure nfsd_acl_procedures2[] = { +static const struct svc_procedure nfsd_acl_procedures2[] = { PROC(null, void, void, void, RC_NOCACHE, ST), PROC(getacl, getacl, getacl, getacl, RC_NOCACHE, ST+1+2*(1+ACL)), PROC(setacl, setacl, attrstat, attrstat, RC_NOCACHE, ST+AT), diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 73c0970ccefb..1a482ac9d4e9 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -257,7 +257,7 @@ struct nfsd3_voidargs { int dummy; }; #define pAT (1+AT) /* post attributes - conditional */ #define ACL (1+NFS_ACL_MAX_ENTRIES*3) /* Access Control List */ -static struct svc_procedure nfsd_acl_procedures3[] = { +static const struct svc_procedure nfsd_acl_procedures3[] = { PROC(null, void, void, void, RC_NOCACHE, ST), PROC(getacl, getacl, getacl, getacl, RC_NOCACHE, ST+1+2*(1+ACL)), PROC(setacl, setacl, setacl, fhandle, RC_NOCACHE, ST+pAT), diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index b5823802e278..96e0e6a2af51 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -674,7 +674,7 @@ struct nfsd3_voidargs { int dummy; }; #define pAT (1+AT) /* post attributes - conditional */ #define WC (7+pAT) /* WCC attributes */ -static struct svc_procedure nfsd_procedures3[22] = { +static const struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_NULL] = { .pc_func = nfsd3_proc_null, .pc_encode = nfs3svc_encode_voidres, diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index bad5fec0ebc7..a4d8aa3abc63 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -2533,7 +2533,7 @@ static const char *nfsd4_op_name(unsigned opnum) #define nfsd4_voidres nfsd4_voidargs struct nfsd4_voidargs { int dummy; }; -static struct svc_procedure nfsd_procedures4[2] = { +static const struct svc_procedure nfsd_procedures4[2] = { [NFSPROC4_NULL] = { .pc_func = nfsd4_proc_null, .pc_encode = nfs4svc_encode_voidres, diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 44b157553733..a68b686fda12 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -573,7 +573,7 @@ struct nfsd_void { int dummy; }; #define FH 8 /* filehandle */ #define AT 18 /* attributes */ -static struct svc_procedure nfsd_procedures2[18] = { +static const struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_NULL] = { .pc_func = nfsd_proc_null, .pc_decode = nfssvc_decode_void, diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 555233664124..379b310c445d 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -756,7 +756,7 @@ static __be32 map_new_errors(u32 vers, __be32 nfserr) * problem, we enforce these assumptions here: */ static bool nfs_request_too_big(struct svc_rqst *rqstp, - struct svc_procedure *proc) + const struct svc_procedure *proc) { /* * The ACL code has more careful bounds-checking and is not @@ -781,7 +781,7 @@ static bool nfs_request_too_big(struct svc_rqst *rqstp, int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) { - struct svc_procedure *proc; + const struct svc_procedure *proc; __be32 nfserr; __be32 *nfserrp; diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 41f7b6a04d69..3eca67728366 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -192,9 +192,9 @@ struct nlm_block { * Global variables */ extern const struct rpc_program nlm_program; -extern struct svc_procedure nlmsvc_procedures[]; +extern const struct svc_procedure nlmsvc_procedures[]; #ifdef CONFIG_LOCKD_V4 -extern struct svc_procedure nlmsvc_procedures4[]; +extern const struct svc_procedure nlmsvc_procedures4[]; #endif extern int nlmsvc_grace_period; extern unsigned long nlmsvc_timeout; diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 9f00384153f4..984e6b9c3043 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -237,7 +237,7 @@ struct svc_rqst { struct svc_serv * rq_server; /* RPC service definition */ struct svc_pool * rq_pool; /* thread pool */ - struct svc_procedure * rq_procinfo; /* procedure info */ + const struct svc_procedure *rq_procinfo;/* procedure info */ struct auth_ops * rq_authop; /* authentication flavour */ struct svc_cred rq_cred; /* auth info */ void * rq_xprt_ctxt; /* transport specific context ptr */ @@ -396,7 +396,7 @@ struct svc_program { struct svc_version { u32 vs_vers; /* version number */ u32 vs_nproc; /* number of procedures */ - struct svc_procedure * vs_proc; /* per-procedure info */ + const struct svc_procedure *vs_proc; /* per-procedure info */ unsigned int *vs_count; /* call counts */ u32 vs_xdrsize; /* xdrsize needed for this version */ diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 6452592194ac..049963d676a7 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1152,7 +1152,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) { struct svc_program *progp; struct svc_version *versp = NULL; /* compiler food */ - struct svc_procedure *procp = NULL; + const struct svc_procedure *procp = NULL; struct svc_serv *serv = rqstp->rq_server; __be32 *statp; u32 prog, vers, proc; -- cgit v1.2.3-59-g8ed1b From e9679189e34b25a1b9aa77fe37d331559d1544af Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 12 May 2017 16:21:37 +0200 Subject: sunrpc: mark all struct svc_version instances as const Signed-off-by: Christoph Hellwig Acked-by: Trond Myklebust --- fs/lockd/svc.c | 38 +++++++++++++++++++------------------- fs/nfs/callback.c | 2 +- fs/nfs/callback_xdr.c | 4 ++-- fs/nfs/internal.h | 4 ++-- fs/nfs/nfs4_fs.h | 4 ++-- fs/nfsd/nfs2acl.c | 14 +++++++------- fs/nfsd/nfs3acl.c | 14 +++++++------- fs/nfsd/nfs3proc.c | 14 +++++++------- fs/nfsd/nfs4proc.c | 2 +- fs/nfsd/nfsd.h | 6 +++--- fs/nfsd/nfsproc.c | 14 +++++++------- fs/nfsd/nfssvc.c | 8 ++++---- include/linux/sunrpc/svc.h | 2 +- net/sunrpc/svc.c | 4 ++-- 14 files changed, 65 insertions(+), 65 deletions(-) diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index cc6abe6280bc..726b6cecf430 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -740,32 +740,32 @@ module_exit(exit_nlm); * Define NLM program and procedures */ static unsigned int nlmsvc_version1_count[17]; -static struct svc_version nlmsvc_version1 = { - .vs_vers = 1, - .vs_nproc = 17, - .vs_proc = nlmsvc_procedures, - .vs_count = nlmsvc_version1_count, - .vs_xdrsize = NLMSVC_XDRSIZE, +static const struct svc_version nlmsvc_version1 = { + .vs_vers = 1, + .vs_nproc = 17, + .vs_proc = nlmsvc_procedures, + .vs_count = nlmsvc_version1_count, + .vs_xdrsize = NLMSVC_XDRSIZE, }; static unsigned int nlmsvc_version3_count[24]; -static struct svc_version nlmsvc_version3 = { - .vs_vers = 3, - .vs_nproc = 24, - .vs_proc = nlmsvc_procedures, - .vs_count = nlmsvc_version3_count, - .vs_xdrsize = NLMSVC_XDRSIZE, +static const struct svc_version nlmsvc_version3 = { + .vs_vers = 3, + .vs_nproc = 24, + .vs_proc = nlmsvc_procedures, + .vs_count = nlmsvc_version3_count, + .vs_xdrsize = NLMSVC_XDRSIZE, }; #ifdef CONFIG_LOCKD_V4 static unsigned int nlmsvc_version4_count[24]; -static struct svc_version nlmsvc_version4 = { - .vs_vers = 4, - .vs_nproc = 24, - .vs_proc = nlmsvc_procedures4, - .vs_count = nlmsvc_version4_count, - .vs_xdrsize = NLMSVC_XDRSIZE, +static const struct svc_version nlmsvc_version4 = { + .vs_vers = 4, + .vs_nproc = 24, + .vs_proc = nlmsvc_procedures4, + .vs_count = nlmsvc_version4_count, + .vs_xdrsize = NLMSVC_XDRSIZE, }; #endif -static struct svc_version * nlmsvc_version[] = { +static const struct svc_version *nlmsvc_version[] = { [1] = &nlmsvc_version1, [3] = &nlmsvc_version3, #ifdef CONFIG_LOCKD_V4 diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 73a1f928226c..34323877ec13 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -439,7 +439,7 @@ static int nfs_callback_authenticate(struct svc_rqst *rqstp) /* * Define NFS4 callback program */ -static struct svc_version *nfs4_callback_version[] = { +static const struct svc_version *nfs4_callback_version[] = { [1] = &nfs4_callback_version1, [4] = &nfs4_callback_version4, }; diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index ae249f27297f..01a430e51daa 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -1012,7 +1012,7 @@ static const struct svc_procedure nfs4_callback_procedures1[] = { }; static unsigned int nfs4_callback_count1[ARRAY_SIZE(nfs4_callback_procedures1)]; -struct svc_version nfs4_callback_version1 = { +const struct svc_version nfs4_callback_version1 = { .vs_vers = 1, .vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1), .vs_proc = nfs4_callback_procedures1, @@ -1024,7 +1024,7 @@ struct svc_version nfs4_callback_version1 = { }; static unsigned int nfs4_callback_count4[ARRAY_SIZE(nfs4_callback_procedures1)]; -struct svc_version nfs4_callback_version4 = { +const struct svc_version nfs4_callback_version4 = { .vs_vers = 4, .vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1), .vs_proc = nfs4_callback_procedures1, diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index c21254924389..9976d8498cf3 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -225,8 +225,8 @@ static inline void nfs_fs_proc_exit(void) #endif /* callback_xdr.c */ -extern struct svc_version nfs4_callback_version1; -extern struct svc_version nfs4_callback_version4; +extern const struct svc_version nfs4_callback_version1; +extern const struct svc_version nfs4_callback_version4; struct nfs_pageio_descriptor; /* pagelist.c */ diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 9b0cf3872722..40bd05f05e74 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -498,8 +498,8 @@ extern const struct rpc_procinfo nfs4_procedures[]; struct nfs4_mount_data; /* callback_xdr.c */ -extern struct svc_version nfs4_callback_version1; -extern struct svc_version nfs4_callback_version4; +extern const struct svc_version nfs4_callback_version1; +extern const struct svc_version nfs4_callback_version4; static inline void nfs4_stateid_copy(nfs4_stateid *dst, const nfs4_stateid *src) { diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index c3f6b8a6b659..6276ec8608b0 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -379,11 +379,11 @@ static const struct svc_procedure nfsd_acl_procedures2[] = { }; static unsigned int nfsd_acl_count2[ARRAY_SIZE(nfsd_acl_procedures2)]; -struct svc_version nfsd_acl_version2 = { - .vs_vers = 2, - .vs_nproc = 5, - .vs_proc = nfsd_acl_procedures2, - .vs_count = nfsd_acl_count2, - .vs_dispatch = nfsd_dispatch, - .vs_xdrsize = NFS3_SVC_XDRSIZE, +const struct svc_version nfsd_acl_version2 = { + .vs_vers = 2, + .vs_nproc = 5, + .vs_proc = nfsd_acl_procedures2, + .vs_count = nfsd_acl_count2, + .vs_dispatch = nfsd_dispatch, + .vs_xdrsize = NFS3_SVC_XDRSIZE, }; diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 1a482ac9d4e9..01976529f042 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -264,12 +264,12 @@ static const struct svc_procedure nfsd_acl_procedures3[] = { }; static unsigned int nfsd_acl_count3[ARRAY_SIZE(nfsd_acl_procedures3)]; -struct svc_version nfsd_acl_version3 = { - .vs_vers = 3, - .vs_nproc = 3, - .vs_proc = nfsd_acl_procedures3, - .vs_count = nfsd_acl_count3, - .vs_dispatch = nfsd_dispatch, - .vs_xdrsize = NFS3_SVC_XDRSIZE, +const struct svc_version nfsd_acl_version3 = { + .vs_vers = 3, + .vs_nproc = 3, + .vs_proc = nfsd_acl_procedures3, + .vs_count = nfsd_acl_count3, + .vs_dispatch = nfsd_dispatch, + .vs_xdrsize = NFS3_SVC_XDRSIZE, }; diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 96e0e6a2af51..2cb56a0d6625 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -891,11 +891,11 @@ static const struct svc_procedure nfsd_procedures3[22] = { }; static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures3)]; -struct svc_version nfsd_version3 = { - .vs_vers = 3, - .vs_nproc = 22, - .vs_proc = nfsd_procedures3, - .vs_count = nfsd_count3, - .vs_dispatch = nfsd_dispatch, - .vs_xdrsize = NFS3_SVC_XDRSIZE, +const struct svc_version nfsd_version3 = { + .vs_vers = 3, + .vs_nproc = 22, + .vs_proc = nfsd_procedures3, + .vs_dispatch = nfsd_dispatch, + .vs_count = nfsd_count3, + .vs_xdrsize = NFS3_SVC_XDRSIZE, }; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index a4d8aa3abc63..e814c1946f6e 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -2555,7 +2555,7 @@ static const struct svc_procedure nfsd_procedures4[2] = { }; static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures4)]; -struct svc_version nfsd_version4 = { +const struct svc_version nfsd_version4 = { .vs_vers = 4, .vs_nproc = 2, .vs_proc = nfsd_procedures4, diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index d96606801d47..b9c538ab7a59 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -60,7 +60,7 @@ struct readdir_cd { extern struct svc_program nfsd_program; -extern struct svc_version nfsd_version2, nfsd_version3, +extern const struct svc_version nfsd_version2, nfsd_version3, nfsd_version4; extern struct mutex nfsd_mutex; extern spinlock_t nfsd_drc_lock; @@ -86,12 +86,12 @@ void nfsd_destroy(struct net *net); #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) #ifdef CONFIG_NFSD_V2_ACL -extern struct svc_version nfsd_acl_version2; +extern const struct svc_version nfsd_acl_version2; #else #define nfsd_acl_version2 NULL #endif #ifdef CONFIG_NFSD_V3_ACL -extern struct svc_version nfsd_acl_version3; +extern const struct svc_version nfsd_acl_version3; #else #define nfsd_acl_version3 NULL #endif diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index a68b686fda12..5076ae2b8258 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -744,13 +744,13 @@ static const struct svc_procedure nfsd_procedures2[18] = { static unsigned int nfsd_count2[ARRAY_SIZE(nfsd_procedures2)]; -struct svc_version nfsd_version2 = { - .vs_vers = 2, - .vs_nproc = 18, - .vs_proc = nfsd_procedures2, - .vs_count = nfsd_count2, - .vs_dispatch = nfsd_dispatch, - .vs_xdrsize = NFS2_SVC_XDRSIZE, +const struct svc_version nfsd_version2 = { + .vs_vers = 2, + .vs_nproc = 18, + .vs_proc = nfsd_procedures2, + .vs_count = nfsd_count2, + .vs_dispatch = nfsd_dispatch, + .vs_xdrsize = NFS2_SVC_XDRSIZE, }; /* diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 379b310c445d..063ae7de2c12 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -68,14 +68,14 @@ unsigned long nfsd_drc_mem_used; #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) static struct svc_stat nfsd_acl_svcstats; -static struct svc_version * nfsd_acl_version[] = { +static const struct svc_version *nfsd_acl_version[] = { [2] = &nfsd_acl_version2, [3] = &nfsd_acl_version3, }; #define NFSD_ACL_MINVERS 2 #define NFSD_ACL_NRVERS ARRAY_SIZE(nfsd_acl_version) -static struct svc_version *nfsd_acl_versions[NFSD_ACL_NRVERS]; +static const struct svc_version *nfsd_acl_versions[NFSD_ACL_NRVERS]; static struct svc_program nfsd_acl_program = { .pg_prog = NFS_ACL_PROGRAM, @@ -92,7 +92,7 @@ static struct svc_stat nfsd_acl_svcstats = { }; #endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */ -static struct svc_version * nfsd_version[] = { +static const struct svc_version *nfsd_version[] = { [2] = &nfsd_version2, #if defined(CONFIG_NFSD_V3) [3] = &nfsd_version3, @@ -104,7 +104,7 @@ static struct svc_version * nfsd_version[] = { #define NFSD_MINVERS 2 #define NFSD_NRVERS ARRAY_SIZE(nfsd_version) -static struct svc_version *nfsd_versions[NFSD_NRVERS]; +static const struct svc_version *nfsd_versions[NFSD_NRVERS]; struct svc_program nfsd_program = { #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 984e6b9c3043..e85267899753 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -383,7 +383,7 @@ struct svc_program { unsigned int pg_lovers; /* lowest version */ unsigned int pg_hivers; /* highest version */ unsigned int pg_nvers; /* number of versions */ - struct svc_version ** pg_vers; /* version array */ + const struct svc_version **pg_vers; /* version array */ char * pg_name; /* service name */ char * pg_class; /* class name: services sharing authentication */ struct svc_stat * pg_stats; /* rpc statistics */ diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 049963d676a7..45b4f2d2e3bd 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1008,7 +1008,7 @@ int svc_register(const struct svc_serv *serv, struct net *net, const unsigned short port) { struct svc_program *progp; - struct svc_version *vers; + const struct svc_version *vers; unsigned int i; int error = 0; @@ -1151,7 +1151,7 @@ static int svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) { struct svc_program *progp; - struct svc_version *versp = NULL; /* compiler food */ + const struct svc_version *versp = NULL; /* compiler food */ const struct svc_procedure *procp = NULL; struct svc_serv *serv = rqstp->rq_server; __be32 *statp; -- cgit v1.2.3-59-g8ed1b From bb2a8b0cd116219777b99cb71fe9e24b31d3f521 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 23:46:47 +0200 Subject: nfsd4: const-ify nfsd4_ops nfsd4_ops contains function pointers, and marking it as constant avoids it being able to be used as an attach vector for code injections. Signed-off-by: Christoph Hellwig --- fs/nfsd/nfs4proc.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index e814c1946f6e..fe6cb5b6d31c 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1584,7 +1584,7 @@ struct nfsd4_operation { union nfsd4_op_u *); }; -static struct nfsd4_operation nfsd4_ops[]; +static const struct nfsd4_operation nfsd4_ops[]; static const char *nfsd4_op_name(unsigned opnum); @@ -1621,7 +1621,7 @@ static __be32 nfs41_check_op_ordering(struct nfsd4_compoundargs *args) return nfs_ok; } -static inline struct nfsd4_operation *OPDESC(struct nfsd4_op *op) +static inline const struct nfsd4_operation *OPDESC(struct nfsd4_op *op) { return &nfsd4_ops[op->opnum]; } @@ -1639,10 +1639,9 @@ static bool need_wrongsec_check(struct svc_rqst *rqstp) struct nfsd4_compoundargs *argp = rqstp->rq_argp; struct nfsd4_op *this = &argp->ops[resp->opcnt - 1]; struct nfsd4_op *next = &argp->ops[resp->opcnt]; - struct nfsd4_operation *thisd; - struct nfsd4_operation *nextd; + const struct nfsd4_operation *thisd = OPDESC(this); + const struct nfsd4_operation *nextd; - thisd = OPDESC(this); /* * Most ops check wronsec on our own; only the putfh-like ops * have special rules. @@ -1695,7 +1694,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) struct nfsd4_compoundargs *args = rqstp->rq_argp; struct nfsd4_compoundres *resp = rqstp->rq_resp; struct nfsd4_op *op; - struct nfsd4_operation *opdesc; + const struct nfsd4_operation *opdesc; struct nfsd4_compound_state *cstate = &resp->cstate; struct svc_fh *current_fh = &cstate->current_fh; struct svc_fh *save_fh = &cstate->save_fh; @@ -2109,7 +2108,7 @@ static inline u32 nfsd4_seek_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) return (op_encode_hdr_size + 3) * sizeof(__be32); } -static struct nfsd4_operation nfsd4_ops[] = { +static const struct nfsd4_operation nfsd4_ops[] = { [OP_ACCESS] = { .op_func = nfsd4_access, .op_name = "OP_ACCESS", -- cgit v1.2.3-59-g8ed1b From cfc5604c488ccd17936b69008af0c9ae050f4a08 Mon Sep 17 00:00:00 2001 From: Cyrille Pitchen Date: Tue, 25 Apr 2017 22:08:46 +0200 Subject: mtd: spi-nor: introduce SPI 1-2-2 and SPI 1-4-4 protocols This patch changes the prototype of spi_nor_scan(): its 3rd parameter is replaced by a 'struct spi_nor_hwcaps' pointer, which tells the spi-nor framework about the actual hardware capabilities supported by the SPI controller and its driver. Besides, this patch also introduces a new 'struct spi_nor_flash_parameter' telling the spi-nor framework about the hardware capabilities supported by the SPI flash memory and the associated settings required to use those hardware caps. Then, to improve the readability of spi_nor_scan(), the discovery of the memory settings and the memory initialization are now split into two dedicated functions. 1 - spi_nor_init_params() The spi_nor_init_params() function is responsible for initializing the 'struct spi_nor_flash_parameter'. Currently this structure is filled with legacy values but further patches will allow to override some parameter values dynamically, for instance by reading the JESD216 Serial Flash Discoverable Parameter (SFDP) tables from the SPI memory. The spi_nor_init_params() function only deals with the hardware capabilities of the SPI flash memory: especially it doesn't care about the hardware capabilities supported by the SPI controller. 2 - spi_nor_setup() The second function is called once the 'struct spi_nor_flash_parameter' has been initialized by spi_nor_init_params(). With both 'struct spi_nor_flash_parameter' and 'struct spi_nor_hwcaps', the new argument of spi_nor_scan(), spi_nor_setup() computes the best match between hardware caps supported by both the (Q)SPI memory and controller hence selecting the relevant settings for (Fast) Read and Page Program operations. Signed-off-by: Cyrille Pitchen Reviewed-by: Marek Vasut --- drivers/mtd/devices/m25p80.c | 21 +- drivers/mtd/spi-nor/aspeed-smc.c | 23 +- drivers/mtd/spi-nor/atmel-quadspi.c | 83 ++++--- drivers/mtd/spi-nor/cadence-quadspi.c | 18 +- drivers/mtd/spi-nor/fsl-quadspi.c | 6 +- drivers/mtd/spi-nor/hisi-sfc.c | 31 ++- drivers/mtd/spi-nor/intel-spi.c | 7 +- drivers/mtd/spi-nor/mtk-quadspi.c | 15 +- drivers/mtd/spi-nor/nxp-spifi.c | 22 +- drivers/mtd/spi-nor/spi-nor.c | 440 ++++++++++++++++++++++++++-------- drivers/mtd/spi-nor/stm32-quadspi.c | 27 ++- include/linux/mtd/spi-nor.h | 119 ++++++++- 12 files changed, 613 insertions(+), 199 deletions(-) diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c index c4df3b1bded0..07073f4ce0bd 100644 --- a/drivers/mtd/devices/m25p80.c +++ b/drivers/mtd/devices/m25p80.c @@ -111,14 +111,7 @@ static ssize_t m25p80_write(struct spi_nor *nor, loff_t to, size_t len, static inline unsigned int m25p80_rx_nbits(struct spi_nor *nor) { - switch (nor->flash_read) { - case SPI_NOR_DUAL: - return 2; - case SPI_NOR_QUAD: - return 4; - default: - return 0; - } + return spi_nor_get_protocol_data_nbits(nor->read_proto); } /* @@ -196,7 +189,11 @@ static int m25p_probe(struct spi_device *spi) struct flash_platform_data *data; struct m25p *flash; struct spi_nor *nor; - enum read_mode mode = SPI_NOR_NORMAL; + struct spi_nor_hwcaps hwcaps = { + .mask = SNOR_HWCAPS_READ | + SNOR_HWCAPS_READ_FAST | + SNOR_HWCAPS_PP, + }; char *flash_name; int ret; @@ -222,9 +219,9 @@ static int m25p_probe(struct spi_device *spi) flash->spi = spi; if (spi->mode & SPI_RX_QUAD) - mode = SPI_NOR_QUAD; + hwcaps.mask |= SNOR_HWCAPS_READ_1_1_4; else if (spi->mode & SPI_RX_DUAL) - mode = SPI_NOR_DUAL; + hwcaps.mask |= SNOR_HWCAPS_READ_1_1_2; if (data && data->name) nor->mtd.name = data->name; @@ -241,7 +238,7 @@ static int m25p_probe(struct spi_device *spi) else flash_name = spi->modalias; - ret = spi_nor_scan(nor, flash_name, mode); + ret = spi_nor_scan(nor, flash_name, &hwcaps); if (ret) return ret; diff --git a/drivers/mtd/spi-nor/aspeed-smc.c b/drivers/mtd/spi-nor/aspeed-smc.c index 56051d30f000..3f875c8d6339 100644 --- a/drivers/mtd/spi-nor/aspeed-smc.c +++ b/drivers/mtd/spi-nor/aspeed-smc.c @@ -585,14 +585,12 @@ static int aspeed_smc_chip_setup_finish(struct aspeed_smc_chip *chip) * TODO: Adjust clocks if fast read is supported and interpret * SPI-NOR flags to adjust controller settings. */ - switch (chip->nor.flash_read) { - case SPI_NOR_NORMAL: - cmd = CONTROL_COMMAND_MODE_NORMAL; - break; - case SPI_NOR_FAST: - cmd = CONTROL_COMMAND_MODE_FREAD; - break; - default: + if (chip->nor.read_proto == SNOR_PROTO_1_1_1) { + if (chip->nor.read_dummy == 0) + cmd = CONTROL_COMMAND_MODE_NORMAL; + else + cmd = CONTROL_COMMAND_MODE_FREAD; + } else { dev_err(chip->nor.dev, "unsupported SPI read mode\n"); return -EINVAL; } @@ -608,6 +606,11 @@ static int aspeed_smc_chip_setup_finish(struct aspeed_smc_chip *chip) static int aspeed_smc_setup_flash(struct aspeed_smc_controller *controller, struct device_node *np, struct resource *r) { + const struct spi_nor_hwcaps hwcaps = { + .mask = SNOR_HWCAPS_READ | + SNOR_HWCAPS_READ_FAST | + SNOR_HWCAPS_PP, + }; const struct aspeed_smc_info *info = controller->info; struct device *dev = controller->dev; struct device_node *child; @@ -671,11 +674,11 @@ static int aspeed_smc_setup_flash(struct aspeed_smc_controller *controller, break; /* - * TODO: Add support for SPI_NOR_QUAD and SPI_NOR_DUAL + * TODO: Add support for Dual and Quad SPI protocols * attach when board support is present as determined * by of property. */ - ret = spi_nor_scan(nor, NULL, SPI_NOR_NORMAL); + ret = spi_nor_scan(nor, NULL, &hwcaps); if (ret) break; diff --git a/drivers/mtd/spi-nor/atmel-quadspi.c b/drivers/mtd/spi-nor/atmel-quadspi.c index 47937d9beec6..ba76fa8f2031 100644 --- a/drivers/mtd/spi-nor/atmel-quadspi.c +++ b/drivers/mtd/spi-nor/atmel-quadspi.c @@ -275,14 +275,48 @@ static void atmel_qspi_debug_command(struct atmel_qspi *aq, static int atmel_qspi_run_command(struct atmel_qspi *aq, const struct atmel_qspi_command *cmd, - u32 ifr_tfrtyp, u32 ifr_width) + u32 ifr_tfrtyp, enum spi_nor_protocol proto) { u32 iar, icr, ifr, sr; int err = 0; iar = 0; icr = 0; - ifr = ifr_tfrtyp | ifr_width; + ifr = ifr_tfrtyp; + + /* Set the SPI protocol */ + switch (proto) { + case SNOR_PROTO_1_1_1: + ifr |= QSPI_IFR_WIDTH_SINGLE_BIT_SPI; + break; + + case SNOR_PROTO_1_1_2: + ifr |= QSPI_IFR_WIDTH_DUAL_OUTPUT; + break; + + case SNOR_PROTO_1_1_4: + ifr |= QSPI_IFR_WIDTH_QUAD_OUTPUT; + break; + + case SNOR_PROTO_1_2_2: + ifr |= QSPI_IFR_WIDTH_DUAL_IO; + break; + + case SNOR_PROTO_1_4_4: + ifr |= QSPI_IFR_WIDTH_QUAD_IO; + break; + + case SNOR_PROTO_2_2_2: + ifr |= QSPI_IFR_WIDTH_DUAL_CMD; + break; + + case SNOR_PROTO_4_4_4: + ifr |= QSPI_IFR_WIDTH_QUAD_CMD; + break; + + default: + return -EINVAL; + } /* Compute instruction parameters */ if (cmd->enable.bits.instruction) { @@ -434,7 +468,7 @@ static int atmel_qspi_read_reg(struct spi_nor *nor, u8 opcode, cmd.rx_buf = buf; cmd.buf_len = len; return atmel_qspi_run_command(aq, &cmd, QSPI_IFR_TFRTYP_TRSFR_READ, - QSPI_IFR_WIDTH_SINGLE_BIT_SPI); + nor->reg_proto); } static int atmel_qspi_write_reg(struct spi_nor *nor, u8 opcode, @@ -450,7 +484,7 @@ static int atmel_qspi_write_reg(struct spi_nor *nor, u8 opcode, cmd.tx_buf = buf; cmd.buf_len = len; return atmel_qspi_run_command(aq, &cmd, QSPI_IFR_TFRTYP_TRSFR_WRITE, - QSPI_IFR_WIDTH_SINGLE_BIT_SPI); + nor->reg_proto); } static ssize_t atmel_qspi_write(struct spi_nor *nor, loff_t to, size_t len, @@ -469,7 +503,7 @@ static ssize_t atmel_qspi_write(struct spi_nor *nor, loff_t to, size_t len, cmd.tx_buf = write_buf; cmd.buf_len = len; ret = atmel_qspi_run_command(aq, &cmd, QSPI_IFR_TFRTYP_TRSFR_WRITE_MEM, - QSPI_IFR_WIDTH_SINGLE_BIT_SPI); + nor->write_proto); return (ret < 0) ? ret : len; } @@ -484,7 +518,7 @@ static int atmel_qspi_erase(struct spi_nor *nor, loff_t offs) cmd.instruction = nor->erase_opcode; cmd.address = (u32)offs; return atmel_qspi_run_command(aq, &cmd, QSPI_IFR_TFRTYP_TRSFR_WRITE, - QSPI_IFR_WIDTH_SINGLE_BIT_SPI); + nor->reg_proto); } static ssize_t atmel_qspi_read(struct spi_nor *nor, loff_t from, size_t len, @@ -493,27 +527,8 @@ static ssize_t atmel_qspi_read(struct spi_nor *nor, loff_t from, size_t len, struct atmel_qspi *aq = nor->priv; struct atmel_qspi_command cmd; u8 num_mode_cycles, num_dummy_cycles; - u32 ifr_width; ssize_t ret; - switch (nor->flash_read) { - case SPI_NOR_NORMAL: - case SPI_NOR_FAST: - ifr_width = QSPI_IFR_WIDTH_SINGLE_BIT_SPI; - break; - - case SPI_NOR_DUAL: - ifr_width = QSPI_IFR_WIDTH_DUAL_OUTPUT; - break; - - case SPI_NOR_QUAD: - ifr_width = QSPI_IFR_WIDTH_QUAD_OUTPUT; - break; - - default: - return -EINVAL; - } - if (nor->read_dummy >= 2) { num_mode_cycles = 2; num_dummy_cycles = nor->read_dummy - 2; @@ -536,7 +551,7 @@ static ssize_t atmel_qspi_read(struct spi_nor *nor, loff_t from, size_t len, cmd.rx_buf = read_buf; cmd.buf_len = len; ret = atmel_qspi_run_command(aq, &cmd, QSPI_IFR_TFRTYP_TRSFR_READ_MEM, - ifr_width); + nor->read_proto); return (ret < 0) ? ret : len; } @@ -590,6 +605,20 @@ static irqreturn_t atmel_qspi_interrupt(int irq, void *dev_id) static int atmel_qspi_probe(struct platform_device *pdev) { + const struct spi_nor_hwcaps hwcaps = { + .mask = SNOR_HWCAPS_READ | + SNOR_HWCAPS_READ_FAST | + SNOR_HWCAPS_READ_1_1_2 | + SNOR_HWCAPS_READ_1_2_2 | + SNOR_HWCAPS_READ_2_2_2 | + SNOR_HWCAPS_READ_1_1_4 | + SNOR_HWCAPS_READ_1_4_4 | + SNOR_HWCAPS_READ_4_4_4 | + SNOR_HWCAPS_PP | + SNOR_HWCAPS_PP_1_1_4 | + SNOR_HWCAPS_PP_1_4_4 | + SNOR_HWCAPS_PP_4_4_4, + }; struct device_node *child, *np = pdev->dev.of_node; struct atmel_qspi *aq; struct resource *res; @@ -679,7 +708,7 @@ static int atmel_qspi_probe(struct platform_device *pdev) if (err) goto disable_clk; - err = spi_nor_scan(nor, NULL, SPI_NOR_QUAD); + err = spi_nor_scan(nor, NULL, &hwcaps); if (err) goto disable_clk; diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c index 9f8102de1b16..40096d73536c 100644 --- a/drivers/mtd/spi-nor/cadence-quadspi.c +++ b/drivers/mtd/spi-nor/cadence-quadspi.c @@ -855,15 +855,14 @@ static int cqspi_set_protocol(struct spi_nor *nor, const int read) f_pdata->data_width = CQSPI_INST_TYPE_SINGLE; if (read) { - switch (nor->flash_read) { - case SPI_NOR_NORMAL: - case SPI_NOR_FAST: + switch (nor->read_proto) { + case SNOR_PROTO_1_1_1: f_pdata->data_width = CQSPI_INST_TYPE_SINGLE; break; - case SPI_NOR_DUAL: + case SNOR_PROTO_1_1_2: f_pdata->data_width = CQSPI_INST_TYPE_DUAL; break; - case SPI_NOR_QUAD: + case SNOR_PROTO_1_1_4: f_pdata->data_width = CQSPI_INST_TYPE_QUAD; break; default: @@ -1069,6 +1068,13 @@ static void cqspi_controller_init(struct cqspi_st *cqspi) static int cqspi_setup_flash(struct cqspi_st *cqspi, struct device_node *np) { + const struct spi_nor_hwcaps hwcaps = { + .mask = SNOR_HWCAPS_READ | + SNOR_HWCAPS_READ_FAST | + SNOR_HWCAPS_READ_1_1_2 | + SNOR_HWCAPS_READ_1_1_4 | + SNOR_HWCAPS_PP, + }; struct platform_device *pdev = cqspi->pdev; struct device *dev = &pdev->dev; struct cqspi_flash_pdata *f_pdata; @@ -1123,7 +1129,7 @@ static int cqspi_setup_flash(struct cqspi_st *cqspi, struct device_node *np) goto err; } - ret = spi_nor_scan(nor, NULL, SPI_NOR_QUAD); + ret = spi_nor_scan(nor, NULL, &hwcaps); if (ret) goto err; diff --git a/drivers/mtd/spi-nor/fsl-quadspi.c b/drivers/mtd/spi-nor/fsl-quadspi.c index 1476135e0d50..f17d22435bfc 100644 --- a/drivers/mtd/spi-nor/fsl-quadspi.c +++ b/drivers/mtd/spi-nor/fsl-quadspi.c @@ -957,6 +957,10 @@ static void fsl_qspi_unprep(struct spi_nor *nor, enum spi_nor_ops ops) static int fsl_qspi_probe(struct platform_device *pdev) { + const struct spi_nor_hwcaps hwcaps = { + .mask = SNOR_HWCAPS_READ_1_1_4 | + SNOR_HWCAPS_PP, + }; struct device_node *np = pdev->dev.of_node; struct device *dev = &pdev->dev; struct fsl_qspi *q; @@ -1065,7 +1069,7 @@ static int fsl_qspi_probe(struct platform_device *pdev) /* set the chip address for READID */ fsl_qspi_set_base_addr(q, nor); - ret = spi_nor_scan(nor, NULL, SPI_NOR_QUAD); + ret = spi_nor_scan(nor, NULL, &hwcaps); if (ret) goto mutex_failed; diff --git a/drivers/mtd/spi-nor/hisi-sfc.c b/drivers/mtd/spi-nor/hisi-sfc.c index a286350627a6..d1106832b9d5 100644 --- a/drivers/mtd/spi-nor/hisi-sfc.c +++ b/drivers/mtd/spi-nor/hisi-sfc.c @@ -120,19 +120,24 @@ static inline int wait_op_finish(struct hifmc_host *host) (reg & FMC_INT_OP_DONE), 0, FMC_WAIT_TIMEOUT); } -static int get_if_type(enum read_mode flash_read) +static int get_if_type(enum spi_nor_protocol proto) { enum hifmc_iftype if_type; - switch (flash_read) { - case SPI_NOR_DUAL: + switch (proto) { + case SNOR_PROTO_1_1_2: if_type = IF_TYPE_DUAL; break; - case SPI_NOR_QUAD: + case SNOR_PROTO_1_2_2: + if_type = IF_TYPE_DIO; + break; + case SNOR_PROTO_1_1_4: if_type = IF_TYPE_QUAD; break; - case SPI_NOR_NORMAL: - case SPI_NOR_FAST: + case SNOR_PROTO_1_4_4: + if_type = IF_TYPE_QIO; + break; + case SNOR_PROTO_1_1_1: default: if_type = IF_TYPE_STD; break; @@ -253,7 +258,10 @@ static int hisi_spi_nor_dma_transfer(struct spi_nor *nor, loff_t start_off, writel(FMC_DMA_LEN_SET(len), host->regbase + FMC_DMA_LEN); reg = OP_CFG_FM_CS(priv->chipselect); - if_type = get_if_type(nor->flash_read); + if (op_type == FMC_OP_READ) + if_type = get_if_type(nor->read_proto); + else + if_type = get_if_type(nor->write_proto); reg |= OP_CFG_MEM_IF_TYPE(if_type); if (op_type == FMC_OP_READ) reg |= OP_CFG_DUMMY_NUM(nor->read_dummy >> 3); @@ -321,6 +329,13 @@ static ssize_t hisi_spi_nor_write(struct spi_nor *nor, loff_t to, static int hisi_spi_nor_register(struct device_node *np, struct hifmc_host *host) { + const struct spi_nor_hwcaps hwcaps = { + .mask = SNOR_HWCAPS_READ | + SNOR_HWCAPS_READ_FAST | + SNOR_HWCAPS_READ_1_1_2 | + SNOR_HWCAPS_READ_1_1_4 | + SNOR_HWCAPS_PP, + }; struct device *dev = host->dev; struct spi_nor *nor; struct hifmc_priv *priv; @@ -362,7 +377,7 @@ static int hisi_spi_nor_register(struct device_node *np, nor->read = hisi_spi_nor_read; nor->write = hisi_spi_nor_write; nor->erase = NULL; - ret = spi_nor_scan(nor, NULL, SPI_NOR_QUAD); + ret = spi_nor_scan(nor, NULL, &hwcaps); if (ret) return ret; diff --git a/drivers/mtd/spi-nor/intel-spi.c b/drivers/mtd/spi-nor/intel-spi.c index 986a3d020a3a..8a596bfeddff 100644 --- a/drivers/mtd/spi-nor/intel-spi.c +++ b/drivers/mtd/spi-nor/intel-spi.c @@ -715,6 +715,11 @@ static void intel_spi_fill_partition(struct intel_spi *ispi, struct intel_spi *intel_spi_probe(struct device *dev, struct resource *mem, const struct intel_spi_boardinfo *info) { + const struct spi_nor_hwcaps hwcaps = { + .mask = SNOR_HWCAPS_READ | + SNOR_HWCAPS_READ_FAST | + SNOR_HWCAPS_PP, + }; struct mtd_partition part; struct intel_spi *ispi; int ret; @@ -746,7 +751,7 @@ struct intel_spi *intel_spi_probe(struct device *dev, ispi->nor.write = intel_spi_write; ispi->nor.erase = intel_spi_erase; - ret = spi_nor_scan(&ispi->nor, NULL, SPI_NOR_NORMAL); + ret = spi_nor_scan(&ispi->nor, NULL, &hwcaps); if (ret) { dev_info(dev, "failed to locate the chip\n"); return ERR_PTR(ret); diff --git a/drivers/mtd/spi-nor/mtk-quadspi.c b/drivers/mtd/spi-nor/mtk-quadspi.c index b6377707ce32..8a20ec4991c8 100644 --- a/drivers/mtd/spi-nor/mtk-quadspi.c +++ b/drivers/mtd/spi-nor/mtk-quadspi.c @@ -123,20 +123,20 @@ static void mt8173_nor_set_read_mode(struct mt8173_nor *mt8173_nor) { struct spi_nor *nor = &mt8173_nor->nor; - switch (nor->flash_read) { - case SPI_NOR_FAST: + switch (nor->read_proto) { + case SNOR_PROTO_1_1_1: writeb(nor->read_opcode, mt8173_nor->base + MTK_NOR_PRGDATA3_REG); writeb(MTK_NOR_FAST_READ, mt8173_nor->base + MTK_NOR_CFG1_REG); break; - case SPI_NOR_DUAL: + case SNOR_PROTO_1_1_2: writeb(nor->read_opcode, mt8173_nor->base + MTK_NOR_PRGDATA3_REG); writeb(MTK_NOR_DUAL_READ_EN, mt8173_nor->base + MTK_NOR_DUAL_REG); break; - case SPI_NOR_QUAD: + case SNOR_PROTO_1_1_4: writeb(nor->read_opcode, mt8173_nor->base + MTK_NOR_PRGDATA4_REG); writeb(MTK_NOR_QUAD_READ_EN, mt8173_nor->base + @@ -408,6 +408,11 @@ static int mt8173_nor_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, static int mtk_nor_init(struct mt8173_nor *mt8173_nor, struct device_node *flash_node) { + const struct spi_nor_hwcaps hwcaps = { + .mask = SNOR_HWCAPS_READ_FAST | + SNOR_HWCAPS_READ_1_1_2 | + SNOR_HWCAPS_PP, + }; int ret; struct spi_nor *nor; @@ -426,7 +431,7 @@ static int mtk_nor_init(struct mt8173_nor *mt8173_nor, nor->write_reg = mt8173_nor_write_reg; nor->mtd.name = "mtk_nor"; /* initialized with NULL */ - ret = spi_nor_scan(nor, NULL, SPI_NOR_DUAL); + ret = spi_nor_scan(nor, NULL, &hwcaps); if (ret) return ret; diff --git a/drivers/mtd/spi-nor/nxp-spifi.c b/drivers/mtd/spi-nor/nxp-spifi.c index 73a14f40928b..15374216d4d9 100644 --- a/drivers/mtd/spi-nor/nxp-spifi.c +++ b/drivers/mtd/spi-nor/nxp-spifi.c @@ -240,13 +240,12 @@ static int nxp_spifi_erase(struct spi_nor *nor, loff_t offs) static int nxp_spifi_setup_memory_cmd(struct nxp_spifi *spifi) { - switch (spifi->nor.flash_read) { - case SPI_NOR_NORMAL: - case SPI_NOR_FAST: + switch (spifi->nor.read_proto) { + case SNOR_PROTO_1_1_1: spifi->mcmd = SPIFI_CMD_FIELDFORM_ALL_SERIAL; break; - case SPI_NOR_DUAL: - case SPI_NOR_QUAD: + case SNOR_PROTO_1_1_2: + case SNOR_PROTO_1_1_4: spifi->mcmd = SPIFI_CMD_FIELDFORM_QUAD_DUAL_DATA; break; default: @@ -274,7 +273,11 @@ static void nxp_spifi_dummy_id_read(struct spi_nor *nor) static int nxp_spifi_setup_flash(struct nxp_spifi *spifi, struct device_node *np) { - enum read_mode flash_read; + struct spi_nor_hwcaps hwcaps = { + .mask = SNOR_HWCAPS_READ | + SNOR_HWCAPS_READ_FAST | + SNOR_HWCAPS_PP, + }; u32 ctrl, property; u16 mode = 0; int ret; @@ -308,13 +311,12 @@ static int nxp_spifi_setup_flash(struct nxp_spifi *spifi, if (mode & SPI_RX_DUAL) { ctrl |= SPIFI_CTRL_DUAL; - flash_read = SPI_NOR_DUAL; + hwcaps.mask |= SNOR_HWCAPS_READ_1_1_2; } else if (mode & SPI_RX_QUAD) { ctrl &= ~SPIFI_CTRL_DUAL; - flash_read = SPI_NOR_QUAD; + hwcaps.mask |= SNOR_HWCAPS_READ_1_1_4; } else { ctrl |= SPIFI_CTRL_DUAL; - flash_read = SPI_NOR_NORMAL; } switch (mode & (SPI_CPHA | SPI_CPOL)) { @@ -351,7 +353,7 @@ static int nxp_spifi_setup_flash(struct nxp_spifi *spifi, */ nxp_spifi_dummy_id_read(&spifi->nor); - ret = spi_nor_scan(&spifi->nor, NULL, flash_read); + ret = spi_nor_scan(&spifi->nor, NULL, &hwcaps); if (ret) { dev_err(spifi->dev, "device scan failed\n"); return ret; diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index dea8c9cbadf0..e653806070a1 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -149,24 +149,6 @@ static int read_cr(struct spi_nor *nor) return val; } -/* - * Dummy Cycle calculation for different type of read. - * It can be used to support more commands with - * different dummy cycle requirements. - */ -static inline int spi_nor_read_dummy_cycles(struct spi_nor *nor) -{ - switch (nor->flash_read) { - case SPI_NOR_FAST: - case SPI_NOR_DUAL: - case SPI_NOR_QUAD: - return 8; - case SPI_NOR_NORMAL: - return 0; - } - return 0; -} - /* * Write status register 1 byte * Returns negative if error occurred. @@ -1460,30 +1442,6 @@ static int spansion_quad_enable(struct spi_nor *nor) return 0; } -static int set_quad_mode(struct spi_nor *nor, const struct flash_info *info) -{ - int status; - - switch (JEDEC_MFR(info)) { - case SNOR_MFR_MACRONIX: - status = macronix_quad_enable(nor); - if (status) { - dev_err(nor->dev, "Macronix quad-read not enabled\n"); - return -EINVAL; - } - return status; - case SNOR_MFR_MICRON: - return 0; - default: - status = spansion_quad_enable(nor); - if (status) { - dev_err(nor->dev, "Spansion quad-read not enabled\n"); - return -EINVAL; - } - return status; - } -} - static int spi_nor_check(struct spi_nor *nor) { if (!nor->dev || !nor->read || !nor->write || @@ -1536,8 +1494,323 @@ static int s3an_nor_scan(const struct flash_info *info, struct spi_nor *nor) return 0; } -int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode) +struct spi_nor_read_command { + u8 num_mode_clocks; + u8 num_wait_states; + u8 opcode; + enum spi_nor_protocol proto; +}; + +struct spi_nor_pp_command { + u8 opcode; + enum spi_nor_protocol proto; +}; + +enum spi_nor_read_command_index { + SNOR_CMD_READ, + SNOR_CMD_READ_FAST, + + /* Dual SPI */ + SNOR_CMD_READ_1_1_2, + SNOR_CMD_READ_1_2_2, + SNOR_CMD_READ_2_2_2, + + /* Quad SPI */ + SNOR_CMD_READ_1_1_4, + SNOR_CMD_READ_1_4_4, + SNOR_CMD_READ_4_4_4, + + SNOR_CMD_READ_MAX +}; + +enum spi_nor_pp_command_index { + SNOR_CMD_PP, + + /* Quad SPI */ + SNOR_CMD_PP_1_1_4, + SNOR_CMD_PP_1_4_4, + SNOR_CMD_PP_4_4_4, + + SNOR_CMD_PP_MAX +}; + +struct spi_nor_flash_parameter { + u64 size; + u32 page_size; + + struct spi_nor_hwcaps hwcaps; + struct spi_nor_read_command reads[SNOR_CMD_READ_MAX]; + struct spi_nor_pp_command page_programs[SNOR_CMD_PP_MAX]; + + int (*quad_enable)(struct spi_nor *nor); +}; + +static void +spi_nor_set_read_settings(struct spi_nor_read_command *read, + u8 num_mode_clocks, + u8 num_wait_states, + u8 opcode, + enum spi_nor_protocol proto) +{ + read->num_mode_clocks = num_mode_clocks; + read->num_wait_states = num_wait_states; + read->opcode = opcode; + read->proto = proto; +} + +static void +spi_nor_set_pp_settings(struct spi_nor_pp_command *pp, + u8 opcode, + enum spi_nor_protocol proto) +{ + pp->opcode = opcode; + pp->proto = proto; +} + +static int spi_nor_init_params(struct spi_nor *nor, + const struct flash_info *info, + struct spi_nor_flash_parameter *params) +{ + /* Set legacy flash parameters as default. */ + memset(params, 0, sizeof(*params)); + + /* Set SPI NOR sizes. */ + params->size = info->sector_size * info->n_sectors; + params->page_size = info->page_size; + + /* (Fast) Read settings. */ + params->hwcaps.mask |= SNOR_HWCAPS_READ; + spi_nor_set_read_settings(¶ms->reads[SNOR_CMD_READ], + 0, 0, SPINOR_OP_READ, + SNOR_PROTO_1_1_1); + + if (!(info->flags & SPI_NOR_NO_FR)) { + params->hwcaps.mask |= SNOR_HWCAPS_READ_FAST; + spi_nor_set_read_settings(¶ms->reads[SNOR_CMD_READ_FAST], + 0, 8, SPINOR_OP_READ_FAST, + SNOR_PROTO_1_1_1); + } + + if (info->flags & SPI_NOR_DUAL_READ) { + params->hwcaps.mask |= SNOR_HWCAPS_READ_1_1_2; + spi_nor_set_read_settings(¶ms->reads[SNOR_CMD_READ_1_1_2], + 0, 8, SPINOR_OP_READ_1_1_2, + SNOR_PROTO_1_1_2); + } + + if (info->flags & SPI_NOR_QUAD_READ) { + params->hwcaps.mask |= SNOR_HWCAPS_READ_1_1_4; + spi_nor_set_read_settings(¶ms->reads[SNOR_CMD_READ_1_1_4], + 0, 8, SPINOR_OP_READ_1_1_4, + SNOR_PROTO_1_1_4); + } + + /* Page Program settings. */ + params->hwcaps.mask |= SNOR_HWCAPS_PP; + spi_nor_set_pp_settings(¶ms->page_programs[SNOR_CMD_PP], + SPINOR_OP_PP, SNOR_PROTO_1_1_1); + + /* Select the procedure to set the Quad Enable bit. */ + if (params->hwcaps.mask & (SNOR_HWCAPS_READ_QUAD | + SNOR_HWCAPS_PP_QUAD)) { + switch (JEDEC_MFR(info)) { + case SNOR_MFR_MACRONIX: + params->quad_enable = macronix_quad_enable; + break; + + case SNOR_MFR_MICRON: + break; + + default: + params->quad_enable = spansion_quad_enable; + break; + } + } + + return 0; +} + +static int spi_nor_hwcaps2cmd(u32 hwcaps, const int table[][2], size_t size) +{ + size_t i; + + for (i = 0; i < size; i++) + if (table[i][0] == (int)hwcaps) + return table[i][1]; + + return -EINVAL; +} + +static int spi_nor_hwcaps_read2cmd(u32 hwcaps) +{ + static const int hwcaps_read2cmd[][2] = { + { SNOR_HWCAPS_READ, SNOR_CMD_READ }, + { SNOR_HWCAPS_READ_FAST, SNOR_CMD_READ_FAST }, + { SNOR_HWCAPS_READ_1_1_2, SNOR_CMD_READ_1_1_2 }, + { SNOR_HWCAPS_READ_1_2_2, SNOR_CMD_READ_1_2_2 }, + { SNOR_HWCAPS_READ_2_2_2, SNOR_CMD_READ_2_2_2 }, + { SNOR_HWCAPS_READ_1_1_4, SNOR_CMD_READ_1_1_4 }, + { SNOR_HWCAPS_READ_1_4_4, SNOR_CMD_READ_1_4_4 }, + { SNOR_HWCAPS_READ_4_4_4, SNOR_CMD_READ_4_4_4 }, + }; + + return spi_nor_hwcaps2cmd(hwcaps, hwcaps_read2cmd, + ARRAY_SIZE(hwcaps_read2cmd)); +} + +static int spi_nor_hwcaps_pp2cmd(u32 hwcaps) +{ + static const int hwcaps_pp2cmd[][2] = { + { SNOR_HWCAPS_PP, SNOR_CMD_PP }, + { SNOR_HWCAPS_PP_1_1_4, SNOR_CMD_PP_1_1_4 }, + { SNOR_HWCAPS_PP_1_4_4, SNOR_CMD_PP_1_4_4 }, + { SNOR_HWCAPS_PP_4_4_4, SNOR_CMD_PP_4_4_4 }, + }; + + return spi_nor_hwcaps2cmd(hwcaps, hwcaps_pp2cmd, + ARRAY_SIZE(hwcaps_pp2cmd)); +} + +static int spi_nor_select_read(struct spi_nor *nor, + const struct spi_nor_flash_parameter *params, + u32 shared_hwcaps) +{ + int cmd, best_match = fls(shared_hwcaps & SNOR_HWCAPS_READ_MASK) - 1; + const struct spi_nor_read_command *read; + + if (best_match < 0) + return -EINVAL; + + cmd = spi_nor_hwcaps_read2cmd(BIT(best_match)); + if (cmd < 0) + return -EINVAL; + + read = ¶ms->reads[cmd]; + nor->read_opcode = read->opcode; + nor->read_proto = read->proto; + + /* + * In the spi-nor framework, we don't need to make the difference + * between mode clock cycles and wait state clock cycles. + * Indeed, the value of the mode clock cycles is used by a QSPI + * flash memory to know whether it should enter or leave its 0-4-4 + * (Continuous Read / XIP) mode. + * eXecution In Place is out of the scope of the mtd sub-system. + * Hence we choose to merge both mode and wait state clock cycles + * into the so called dummy clock cycles. + */ + nor->read_dummy = read->num_mode_clocks + read->num_wait_states; + return 0; +} + +static int spi_nor_select_pp(struct spi_nor *nor, + const struct spi_nor_flash_parameter *params, + u32 shared_hwcaps) +{ + int cmd, best_match = fls(shared_hwcaps & SNOR_HWCAPS_PP_MASK) - 1; + const struct spi_nor_pp_command *pp; + + if (best_match < 0) + return -EINVAL; + + cmd = spi_nor_hwcaps_pp2cmd(BIT(best_match)); + if (cmd < 0) + return -EINVAL; + + pp = ¶ms->page_programs[cmd]; + nor->program_opcode = pp->opcode; + nor->write_proto = pp->proto; + return 0; +} + +static int spi_nor_select_erase(struct spi_nor *nor, + const struct flash_info *info) +{ + struct mtd_info *mtd = &nor->mtd; + +#ifdef CONFIG_MTD_SPI_NOR_USE_4K_SECTORS + /* prefer "small sector" erase if possible */ + if (info->flags & SECT_4K) { + nor->erase_opcode = SPINOR_OP_BE_4K; + mtd->erasesize = 4096; + } else if (info->flags & SECT_4K_PMC) { + nor->erase_opcode = SPINOR_OP_BE_4K_PMC; + mtd->erasesize = 4096; + } else +#endif + { + nor->erase_opcode = SPINOR_OP_SE; + mtd->erasesize = info->sector_size; + } + return 0; +} + +static int spi_nor_setup(struct spi_nor *nor, const struct flash_info *info, + const struct spi_nor_flash_parameter *params, + const struct spi_nor_hwcaps *hwcaps) +{ + u32 ignored_mask, shared_mask; + bool enable_quad_io; + int err; + + /* + * Keep only the hardware capabilities supported by both the SPI + * controller and the SPI flash memory. + */ + shared_mask = hwcaps->mask & params->hwcaps.mask; + + /* SPI n-n-n protocols are not supported yet. */ + ignored_mask = (SNOR_HWCAPS_READ_2_2_2 | + SNOR_HWCAPS_READ_4_4_4 | + SNOR_HWCAPS_PP_4_4_4); + if (shared_mask & ignored_mask) { + dev_dbg(nor->dev, + "SPI n-n-n protocols are not supported yet.\n"); + shared_mask &= ~ignored_mask; + } + + /* Select the (Fast) Read command. */ + err = spi_nor_select_read(nor, params, shared_mask); + if (err) { + dev_err(nor->dev, + "can't select read settings supported by both the SPI controller and memory.\n"); + return err; + } + + /* Select the Page Program command. */ + err = spi_nor_select_pp(nor, params, shared_mask); + if (err) { + dev_err(nor->dev, + "can't select write settings supported by both the SPI controller and memory.\n"); + return err; + } + + /* Select the Sector Erase command. */ + err = spi_nor_select_erase(nor, info); + if (err) { + dev_err(nor->dev, + "can't select erase settings supported by both the SPI controller and memory.\n"); + return err; + } + + /* Enable Quad I/O if needed. */ + enable_quad_io = (spi_nor_get_protocol_width(nor->read_proto) == 4 || + spi_nor_get_protocol_width(nor->write_proto) == 4); + if (enable_quad_io && params->quad_enable) { + err = params->quad_enable(nor); + if (err) { + dev_err(nor->dev, "quad mode not supported\n"); + return err; + } + } + + return 0; +} + +int spi_nor_scan(struct spi_nor *nor, const char *name, + const struct spi_nor_hwcaps *hwcaps) { + struct spi_nor_flash_parameter params; const struct flash_info *info = NULL; struct device *dev = nor->dev; struct mtd_info *mtd = &nor->mtd; @@ -1549,6 +1822,11 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode) if (ret) return ret; + /* Reset SPI protocol for all commands. */ + nor->reg_proto = SNOR_PROTO_1_1_1; + nor->read_proto = SNOR_PROTO_1_1_1; + nor->write_proto = SNOR_PROTO_1_1_1; + if (name) info = spi_nor_match_id(name); /* Try to auto-detect if chip name wasn't specified or not found */ @@ -1591,6 +1869,11 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode) if (info->flags & SPI_S3AN) nor->flags |= SNOR_F_READY_XSR_RDY; + /* Parse the Serial Flash Discoverable Parameters table. */ + ret = spi_nor_init_params(nor, info, ¶ms); + if (ret) + return ret; + /* * Atmel, SST, Intel/Numonyx, and others serial NOR tend to power up * with the software protection bits set @@ -1611,7 +1894,7 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode) mtd->type = MTD_NORFLASH; mtd->writesize = 1; mtd->flags = MTD_CAP_NORFLASH; - mtd->size = info->sector_size * info->n_sectors; + mtd->size = params.size; mtd->_erase = spi_nor_erase; mtd->_read = spi_nor_read; @@ -1642,75 +1925,38 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode) if (info->flags & NO_CHIP_ERASE) nor->flags |= SNOR_F_NO_OP_CHIP_ERASE; -#ifdef CONFIG_MTD_SPI_NOR_USE_4K_SECTORS - /* prefer "small sector" erase if possible */ - if (info->flags & SECT_4K) { - nor->erase_opcode = SPINOR_OP_BE_4K; - mtd->erasesize = 4096; - } else if (info->flags & SECT_4K_PMC) { - nor->erase_opcode = SPINOR_OP_BE_4K_PMC; - mtd->erasesize = 4096; - } else -#endif - { - nor->erase_opcode = SPINOR_OP_SE; - mtd->erasesize = info->sector_size; - } - if (info->flags & SPI_NOR_NO_ERASE) mtd->flags |= MTD_NO_ERASE; mtd->dev.parent = dev; - nor->page_size = info->page_size; + nor->page_size = params.page_size; mtd->writebufsize = nor->page_size; if (np) { /* If we were instantiated by DT, use it */ if (of_property_read_bool(np, "m25p,fast-read")) - nor->flash_read = SPI_NOR_FAST; + params.hwcaps.mask |= SNOR_HWCAPS_READ_FAST; else - nor->flash_read = SPI_NOR_NORMAL; + params.hwcaps.mask &= ~SNOR_HWCAPS_READ_FAST; } else { /* If we weren't instantiated by DT, default to fast-read */ - nor->flash_read = SPI_NOR_FAST; + params.hwcaps.mask |= SNOR_HWCAPS_READ_FAST; } /* Some devices cannot do fast-read, no matter what DT tells us */ if (info->flags & SPI_NOR_NO_FR) - nor->flash_read = SPI_NOR_NORMAL; - - /* Quad/Dual-read mode takes precedence over fast/normal */ - if (mode == SPI_NOR_QUAD && info->flags & SPI_NOR_QUAD_READ) { - ret = set_quad_mode(nor, info); - if (ret) { - dev_err(dev, "quad mode not supported\n"); - return ret; - } - nor->flash_read = SPI_NOR_QUAD; - } else if (mode == SPI_NOR_DUAL && info->flags & SPI_NOR_DUAL_READ) { - nor->flash_read = SPI_NOR_DUAL; - } - - /* Default commands */ - switch (nor->flash_read) { - case SPI_NOR_QUAD: - nor->read_opcode = SPINOR_OP_READ_1_1_4; - break; - case SPI_NOR_DUAL: - nor->read_opcode = SPINOR_OP_READ_1_1_2; - break; - case SPI_NOR_FAST: - nor->read_opcode = SPINOR_OP_READ_FAST; - break; - case SPI_NOR_NORMAL: - nor->read_opcode = SPINOR_OP_READ; - break; - default: - dev_err(dev, "No Read opcode defined\n"); - return -EINVAL; - } + params.hwcaps.mask &= ~SNOR_HWCAPS_READ_FAST; - nor->program_opcode = SPINOR_OP_PP; + /* + * Configure the SPI memory: + * - select op codes for (Fast) Read, Page Program and Sector Erase. + * - set the number of dummy cycles (mode cycles + wait states). + * - set the SPI protocols for register and memory accesses. + * - set the Quad Enable bit if needed (required by SPI x-y-4 protos). + */ + ret = spi_nor_setup(nor, info, ¶ms, hwcaps); + if (ret) + return ret; if (info->addr_width) nor->addr_width = info->addr_width; @@ -1732,8 +1978,6 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode) return -EINVAL; } - nor->read_dummy = spi_nor_read_dummy_cycles(nor); - if (info->flags & SPI_S3AN) { ret = s3an_nor_scan(info, nor); if (ret) diff --git a/drivers/mtd/spi-nor/stm32-quadspi.c b/drivers/mtd/spi-nor/stm32-quadspi.c index ae45f81b8cd3..1056e7408d2a 100644 --- a/drivers/mtd/spi-nor/stm32-quadspi.c +++ b/drivers/mtd/spi-nor/stm32-quadspi.c @@ -192,15 +192,15 @@ static void stm32_qspi_set_framemode(struct spi_nor *nor, cmd->framemode = CCR_IMODE_1; if (read) { - switch (nor->flash_read) { - case SPI_NOR_NORMAL: - case SPI_NOR_FAST: + switch (nor->read_proto) { + default: + case SNOR_PROTO_1_1_1: dmode = CCR_DMODE_1; break; - case SPI_NOR_DUAL: + case SNOR_PROTO_1_1_2: dmode = CCR_DMODE_2; break; - case SPI_NOR_QUAD: + case SNOR_PROTO_1_1_4: dmode = CCR_DMODE_4; break; } @@ -480,7 +480,12 @@ static void stm32_qspi_unprep(struct spi_nor *nor, enum spi_nor_ops ops) static int stm32_qspi_flash_setup(struct stm32_qspi *qspi, struct device_node *np) { - u32 width, flash_read, presc, cs_num, max_rate = 0; + struct spi_nor_hwcaps hwcaps = { + .mask = SNOR_HWCAPS_READ | + SNOR_HWCAPS_READ_FAST | + SNOR_HWCAPS_PP, + }; + u32 width, presc, cs_num, max_rate = 0; struct stm32_qspi_flash *flash; struct mtd_info *mtd; int ret; @@ -499,12 +504,10 @@ static int stm32_qspi_flash_setup(struct stm32_qspi *qspi, width = 1; if (width == 4) - flash_read = SPI_NOR_QUAD; + hwcaps.mask |= SNOR_HWCAPS_READ_1_1_4; else if (width == 2) - flash_read = SPI_NOR_DUAL; - else if (width == 1) - flash_read = SPI_NOR_NORMAL; - else + hwcaps.mask |= SNOR_HWCAPS_READ_1_1_2; + else if (width != 1) return -EINVAL; flash = &qspi->flash[cs_num]; @@ -539,7 +542,7 @@ static int stm32_qspi_flash_setup(struct stm32_qspi *qspi, */ flash->fsize = FSIZE_VAL(SZ_1K); - ret = spi_nor_scan(&flash->nor, NULL, flash_read); + ret = spi_nor_scan(&flash->nor, NULL, &hwcaps); if (ret) { dev_err(qspi->dev, "device scan failed\n"); return ret; diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index f2a718030476..60db1585f94c 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -119,13 +119,63 @@ /* Configuration Register bits. */ #define CR_QUAD_EN_SPAN BIT(1) /* Spansion Quad I/O */ -enum read_mode { - SPI_NOR_NORMAL = 0, - SPI_NOR_FAST, - SPI_NOR_DUAL, - SPI_NOR_QUAD, +/* Supported SPI protocols */ +#define SNOR_PROTO_INST_MASK GENMASK(23, 16) +#define SNOR_PROTO_INST_SHIFT 16 +#define SNOR_PROTO_INST(_nbits) \ + ((((unsigned long)(_nbits)) << SNOR_PROTO_INST_SHIFT) & \ + SNOR_PROTO_INST_MASK) + +#define SNOR_PROTO_ADDR_MASK GENMASK(15, 8) +#define SNOR_PROTO_ADDR_SHIFT 8 +#define SNOR_PROTO_ADDR(_nbits) \ + ((((unsigned long)(_nbits)) << SNOR_PROTO_ADDR_SHIFT) & \ + SNOR_PROTO_ADDR_MASK) + +#define SNOR_PROTO_DATA_MASK GENMASK(7, 0) +#define SNOR_PROTO_DATA_SHIFT 0 +#define SNOR_PROTO_DATA(_nbits) \ + ((((unsigned long)(_nbits)) << SNOR_PROTO_DATA_SHIFT) & \ + SNOR_PROTO_DATA_MASK) + +#define SNOR_PROTO_STR(_inst_nbits, _addr_nbits, _data_nbits) \ + (SNOR_PROTO_INST(_inst_nbits) | \ + SNOR_PROTO_ADDR(_addr_nbits) | \ + SNOR_PROTO_DATA(_data_nbits)) + +enum spi_nor_protocol { + SNOR_PROTO_1_1_1 = SNOR_PROTO_STR(1, 1, 1), + SNOR_PROTO_1_1_2 = SNOR_PROTO_STR(1, 1, 2), + SNOR_PROTO_1_1_4 = SNOR_PROTO_STR(1, 1, 4), + SNOR_PROTO_1_2_2 = SNOR_PROTO_STR(1, 2, 2), + SNOR_PROTO_1_4_4 = SNOR_PROTO_STR(1, 4, 4), + SNOR_PROTO_2_2_2 = SNOR_PROTO_STR(2, 2, 2), + SNOR_PROTO_4_4_4 = SNOR_PROTO_STR(4, 4, 4), }; +static inline u8 spi_nor_get_protocol_inst_nbits(enum spi_nor_protocol proto) +{ + return ((unsigned long)(proto & SNOR_PROTO_INST_MASK)) >> + SNOR_PROTO_INST_SHIFT; +} + +static inline u8 spi_nor_get_protocol_addr_nbits(enum spi_nor_protocol proto) +{ + return ((unsigned long)(proto & SNOR_PROTO_ADDR_MASK)) >> + SNOR_PROTO_ADDR_SHIFT; +} + +static inline u8 spi_nor_get_protocol_data_nbits(enum spi_nor_protocol proto) +{ + return ((unsigned long)(proto & SNOR_PROTO_DATA_MASK)) >> + SNOR_PROTO_DATA_SHIFT; +} + +static inline u8 spi_nor_get_protocol_width(enum spi_nor_protocol proto) +{ + return spi_nor_get_protocol_data_nbits(proto); +} + #define SPI_NOR_MAX_CMD_SIZE 8 enum spi_nor_ops { SPI_NOR_OPS_READ = 0, @@ -154,9 +204,11 @@ enum spi_nor_option_flags { * @read_opcode: the read opcode * @read_dummy: the dummy needed by the read operation * @program_opcode: the program opcode - * @flash_read: the mode of the read * @sst_write_second: used by the SST write operation * @flags: flag options for the current SPI-NOR (SNOR_F_*) + * @read_proto: the SPI protocol for read operations + * @write_proto: the SPI protocol for write operations + * @reg_proto the SPI protocol for read_reg/write_reg/erase operations * @cmd_buf: used by the write_reg * @prepare: [OPTIONAL] do some preparations for the * read/write/erase/lock/unlock operations @@ -185,7 +237,9 @@ struct spi_nor { u8 read_opcode; u8 read_dummy; u8 program_opcode; - enum read_mode flash_read; + enum spi_nor_protocol read_proto; + enum spi_nor_protocol write_proto; + enum spi_nor_protocol reg_proto; bool sst_write_second; u32 flags; u8 cmd_buf[SPI_NOR_MAX_CMD_SIZE]; @@ -219,11 +273,57 @@ static inline struct device_node *spi_nor_get_flash_node(struct spi_nor *nor) return mtd_get_of_node(&nor->mtd); } +/** + * struct spi_nor_hwcaps - Structure for describing the hardware capabilies + * supported by the SPI controller (bus master). + * @mask: the bitmask listing all the supported hw capabilies + */ +struct spi_nor_hwcaps { + u32 mask; +}; + +/* + *(Fast) Read capabilities. + * MUST be ordered by priority: the higher bit position, the higher priority. + * As a matter of performances, it is relevant to use Quad SPI protocols first, + * then Dual SPI protocols before Fast Read and lastly (Slow) Read. + */ +#define SNOR_HWCAPS_READ_MASK GENMASK(7, 0) +#define SNOR_HWCAPS_READ BIT(0) +#define SNOR_HWCAPS_READ_FAST BIT(1) + +#define SNOR_HWCAPS_READ_DUAL GENMASK(4, 2) +#define SNOR_HWCAPS_READ_1_1_2 BIT(2) +#define SNOR_HWCAPS_READ_1_2_2 BIT(3) +#define SNOR_HWCAPS_READ_2_2_2 BIT(4) + +#define SNOR_HWCAPS_READ_QUAD GENMASK(7, 5) +#define SNOR_HWCAPS_READ_1_1_4 BIT(5) +#define SNOR_HWCAPS_READ_1_4_4 BIT(6) +#define SNOR_HWCAPS_READ_4_4_4 BIT(7) + +/* + * Page Program capabilities. + * MUST be ordered by priority: the higher bit position, the higher priority. + * Like (Fast) Read capabilities, Quad SPI protocols are preferred to the + * legacy SPI 1-1-1 protocol. + * Note that Dual Page Programs are not supported because there is no existing + * JEDEC/SFDP standard to define them. Also at this moment no SPI flash memory + * implements such commands. + */ +#define SNOR_HWCAPS_PP_MASK GENMASK(19, 16) +#define SNOR_HWCAPS_PP BIT(16) + +#define SNOR_HWCAPS_PP_QUAD GENMASK(19, 17) +#define SNOR_HWCAPS_PP_1_1_4 BIT(17) +#define SNOR_HWCAPS_PP_1_4_4 BIT(18) +#define SNOR_HWCAPS_PP_4_4_4 BIT(19) + /** * spi_nor_scan() - scan the SPI NOR * @nor: the spi_nor structure * @name: the chip type name - * @mode: the read mode supported by the driver + * @hwcaps: the hardware capabilities supported by the controller driver * * The drivers can use this fuction to scan the SPI NOR. * In the scanning, it will try to get all the necessary information to @@ -233,6 +333,7 @@ static inline struct device_node *spi_nor_get_flash_node(struct spi_nor *nor) * * Return: 0 for success, others for failure. */ -int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode); +int spi_nor_scan(struct spi_nor *nor, const char *name, + const struct spi_nor_hwcaps *hwcaps); #endif -- cgit v1.2.3-59-g8ed1b From 138f5dc61b63c3e89dc133c4faed6b6d0a91b7fd Mon Sep 17 00:00:00 2001 From: Cyrille Pitchen Date: Tue, 25 Apr 2017 22:08:47 +0200 Subject: mtd: m25p80: add support of SPI 1-2-2 and 1-4-4 protocols Before this patch, m25p80_read() supported few SPI protocols: - regular SPI 1-1-1 - SPI Dual Output 1-1-2 - SPI Quad Output 1-1-4 On the other hand, m25p80_write() only supported SPI 1-1-1. This patch updates both m25p80_read() and m25p80_write() functions to let them support SPI 1-2-2 and SPI 1-4-4 protocols for Fast Read and Page Program SPI commands. It adopts a conservative approach to avoid regressions. Hence the new implementations try to be as close as possible to the old implementations, so the main differences are: - the tx_nbits values now being set properly for the spi_transfer structures carrying the (op code + address/dummy) bytes - and the spi_transfer structure being split into 2 spi_transfer structures when the numbers of I/O lines are different for op code and for address/dummy byte transfers on the SPI bus. Besides, the current spi-nor framework supports neither the SPI 2-2-2 nor the SPI 4-4-4 protocols. So, for now, we don't need to update the m25p80_{read|write}_reg() functions as SPI 1-1-1 is the only one possible protocol. Signed-off-by: Cyrille Pitchen Reviewed-by: Marek Vasut --- drivers/mtd/devices/m25p80.c | 102 +++++++++++++++++++++++++++++++++---------- 1 file changed, 79 insertions(+), 23 deletions(-) diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c index 07073f4ce0bd..00eea6fd379c 100644 --- a/drivers/mtd/devices/m25p80.c +++ b/drivers/mtd/devices/m25p80.c @@ -78,11 +78,17 @@ static ssize_t m25p80_write(struct spi_nor *nor, loff_t to, size_t len, { struct m25p *flash = nor->priv; struct spi_device *spi = flash->spi; - struct spi_transfer t[2] = {}; + unsigned int inst_nbits, addr_nbits, data_nbits, data_idx; + struct spi_transfer t[3] = {}; struct spi_message m; int cmd_sz = m25p_cmdsz(nor); ssize_t ret; + /* get transfer protocols. */ + inst_nbits = spi_nor_get_protocol_inst_nbits(nor->write_proto); + addr_nbits = spi_nor_get_protocol_addr_nbits(nor->write_proto); + data_nbits = spi_nor_get_protocol_data_nbits(nor->write_proto); + spi_message_init(&m); if (nor->program_opcode == SPINOR_OP_AAI_WP && nor->sst_write_second) @@ -92,12 +98,27 @@ static ssize_t m25p80_write(struct spi_nor *nor, loff_t to, size_t len, m25p_addr2cmd(nor, to, flash->command); t[0].tx_buf = flash->command; + t[0].tx_nbits = inst_nbits; t[0].len = cmd_sz; spi_message_add_tail(&t[0], &m); - t[1].tx_buf = buf; - t[1].len = len; - spi_message_add_tail(&t[1], &m); + /* split the op code and address bytes into two transfers if needed. */ + data_idx = 1; + if (addr_nbits != inst_nbits) { + t[0].len = 1; + + t[1].tx_buf = &flash->command[1]; + t[1].tx_nbits = addr_nbits; + t[1].len = cmd_sz - 1; + spi_message_add_tail(&t[1], &m); + + data_idx = 2; + } + + t[data_idx].tx_buf = buf; + t[data_idx].tx_nbits = data_nbits; + t[data_idx].len = len; + spi_message_add_tail(&t[data_idx], &m); ret = spi_sync(spi, &m); if (ret) @@ -109,11 +130,6 @@ static ssize_t m25p80_write(struct spi_nor *nor, loff_t to, size_t len, return ret; } -static inline unsigned int m25p80_rx_nbits(struct spi_nor *nor) -{ - return spi_nor_get_protocol_data_nbits(nor->read_proto); -} - /* * Read an address range from the nor chip. The address range * may be any size provided it is within the physical boundaries. @@ -123,13 +139,20 @@ static ssize_t m25p80_read(struct spi_nor *nor, loff_t from, size_t len, { struct m25p *flash = nor->priv; struct spi_device *spi = flash->spi; - struct spi_transfer t[2]; + unsigned int inst_nbits, addr_nbits, data_nbits, data_idx; + struct spi_transfer t[3]; struct spi_message m; unsigned int dummy = nor->read_dummy; ssize_t ret; + int cmd_sz; + + /* get transfer protocols. */ + inst_nbits = spi_nor_get_protocol_inst_nbits(nor->read_proto); + addr_nbits = spi_nor_get_protocol_addr_nbits(nor->read_proto); + data_nbits = spi_nor_get_protocol_data_nbits(nor->read_proto); /* convert the dummy cycles to the number of bytes */ - dummy /= 8; + dummy = (dummy * addr_nbits) / 8; if (spi_flash_read_supported(spi)) { struct spi_flash_read_message msg; @@ -142,10 +165,9 @@ static ssize_t m25p80_read(struct spi_nor *nor, loff_t from, size_t len, msg.read_opcode = nor->read_opcode; msg.addr_width = nor->addr_width; msg.dummy_bytes = dummy; - /* TODO: Support other combinations */ - msg.opcode_nbits = SPI_NBITS_SINGLE; - msg.addr_nbits = SPI_NBITS_SINGLE; - msg.data_nbits = m25p80_rx_nbits(nor); + msg.opcode_nbits = inst_nbits; + msg.addr_nbits = addr_nbits; + msg.data_nbits = data_nbits; ret = spi_flash_read(spi, &msg); if (ret < 0) @@ -160,20 +182,45 @@ static ssize_t m25p80_read(struct spi_nor *nor, loff_t from, size_t len, m25p_addr2cmd(nor, from, flash->command); t[0].tx_buf = flash->command; + t[0].tx_nbits = inst_nbits; t[0].len = m25p_cmdsz(nor) + dummy; spi_message_add_tail(&t[0], &m); - t[1].rx_buf = buf; - t[1].rx_nbits = m25p80_rx_nbits(nor); - t[1].len = min3(len, spi_max_transfer_size(spi), - spi_max_message_size(spi) - t[0].len); - spi_message_add_tail(&t[1], &m); + /* + * Set all dummy/mode cycle bits to avoid sending some manufacturer + * specific pattern, which might make the memory enter its Continuous + * Read mode by mistake. + * Based on the different mode cycle bit patterns listed and described + * in the JESD216B specification, the 0xff value works for all memories + * and all manufacturers. + */ + cmd_sz = t[0].len; + memset(flash->command + cmd_sz - dummy, 0xff, dummy); + + /* split the op code and address bytes into two transfers if needed. */ + data_idx = 1; + if (addr_nbits != inst_nbits) { + t[0].len = 1; + + t[1].tx_buf = &flash->command[1]; + t[1].tx_nbits = addr_nbits; + t[1].len = cmd_sz - 1; + spi_message_add_tail(&t[1], &m); + + data_idx = 2; + } + + t[data_idx].rx_buf = buf; + t[data_idx].rx_nbits = data_nbits; + t[data_idx].len = min3(len, spi_max_transfer_size(spi), + spi_max_message_size(spi) - cmd_sz); + spi_message_add_tail(&t[data_idx], &m); ret = spi_sync(spi, &m); if (ret) return ret; - ret = m.actual_length - m25p_cmdsz(nor) - dummy; + ret = m.actual_length - cmd_sz; if (ret < 0) return -EIO; return ret; @@ -218,11 +265,20 @@ static int m25p_probe(struct spi_device *spi) spi_set_drvdata(spi, flash); flash->spi = spi; - if (spi->mode & SPI_RX_QUAD) + if (spi->mode & SPI_RX_QUAD) { hwcaps.mask |= SNOR_HWCAPS_READ_1_1_4; - else if (spi->mode & SPI_RX_DUAL) + + if (spi->mode & SPI_TX_QUAD) + hwcaps.mask |= (SNOR_HWCAPS_READ_1_4_4 | + SNOR_HWCAPS_PP_1_1_4 | + SNOR_HWCAPS_PP_1_4_4); + } else if (spi->mode & SPI_RX_DUAL) { hwcaps.mask |= SNOR_HWCAPS_READ_1_1_2; + if (spi->mode & SPI_TX_DUAL) + hwcaps.mask |= SNOR_HWCAPS_READ_1_2_2; + } + if (data && data->name) nor->mtd.name = data->name; -- cgit v1.2.3-59-g8ed1b From 15f55331527b1422eae683477f8a31fdfae93316 Mon Sep 17 00:00:00 2001 From: Cyrille Pitchen Date: Tue, 25 Apr 2017 22:08:48 +0200 Subject: mtd: spi-nor: introduce Double Transfer Rate (DTR) SPI protocols This patch introduces support to Double Transfer Rate (DTR) SPI protocols. DTR is used only for Fast Read operations. According to manufacturer datasheets, whatever the number of I/O lines used during instruction (x) and address/mode/dummy (y) clock cycles, DTR is used only during data (z) clock cycles of SPI x-y-z protocols. Signed-off-by: Cyrille Pitchen Reviewed-by: Marek Vasut --- drivers/mtd/spi-nor/spi-nor.c | 10 +++++++++ include/linux/mtd/spi-nor.h | 48 +++++++++++++++++++++++++++++++++---------- 2 files changed, 47 insertions(+), 11 deletions(-) diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index e653806070a1..2062a3abba72 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -203,6 +203,10 @@ static inline u8 spi_nor_convert_3to4_read(u8 opcode) { SPINOR_OP_READ_1_2_2, SPINOR_OP_READ_1_2_2_4B }, { SPINOR_OP_READ_1_1_4, SPINOR_OP_READ_1_1_4_4B }, { SPINOR_OP_READ_1_4_4, SPINOR_OP_READ_1_4_4_4B }, + + { SPINOR_OP_READ_1_1_1_DTR, SPINOR_OP_READ_1_1_1_DTR_4B }, + { SPINOR_OP_READ_1_2_2_DTR, SPINOR_OP_READ_1_2_2_DTR_4B }, + { SPINOR_OP_READ_1_4_4_DTR, SPINOR_OP_READ_1_4_4_DTR_4B }, }; return spi_nor_convert_opcode(opcode, spi_nor_3to4_read, @@ -1509,16 +1513,19 @@ struct spi_nor_pp_command { enum spi_nor_read_command_index { SNOR_CMD_READ, SNOR_CMD_READ_FAST, + SNOR_CMD_READ_1_1_1_DTR, /* Dual SPI */ SNOR_CMD_READ_1_1_2, SNOR_CMD_READ_1_2_2, SNOR_CMD_READ_2_2_2, + SNOR_CMD_READ_1_2_2_DTR, /* Quad SPI */ SNOR_CMD_READ_1_1_4, SNOR_CMD_READ_1_4_4, SNOR_CMD_READ_4_4_4, + SNOR_CMD_READ_1_4_4_DTR, SNOR_CMD_READ_MAX }; @@ -1646,12 +1653,15 @@ static int spi_nor_hwcaps_read2cmd(u32 hwcaps) static const int hwcaps_read2cmd[][2] = { { SNOR_HWCAPS_READ, SNOR_CMD_READ }, { SNOR_HWCAPS_READ_FAST, SNOR_CMD_READ_FAST }, + { SNOR_HWCAPS_READ_1_1_1_DTR, SNOR_CMD_READ_1_1_1_DTR }, { SNOR_HWCAPS_READ_1_1_2, SNOR_CMD_READ_1_1_2 }, { SNOR_HWCAPS_READ_1_2_2, SNOR_CMD_READ_1_2_2 }, { SNOR_HWCAPS_READ_2_2_2, SNOR_CMD_READ_2_2_2 }, + { SNOR_HWCAPS_READ_1_2_2_DTR, SNOR_CMD_READ_1_2_2_DTR }, { SNOR_HWCAPS_READ_1_1_4, SNOR_CMD_READ_1_1_4 }, { SNOR_HWCAPS_READ_1_4_4, SNOR_CMD_READ_1_4_4 }, { SNOR_HWCAPS_READ_4_4_4, SNOR_CMD_READ_4_4_4 }, + { SNOR_HWCAPS_READ_1_4_4_DTR, SNOR_CMD_READ_1_4_4_DTR }, }; return spi_nor_hwcaps2cmd(hwcaps, hwcaps_read2cmd, diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 60db1585f94c..313dbe56f31a 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -73,6 +73,15 @@ #define SPINOR_OP_BE_32K_4B 0x5c /* Erase 32KiB block */ #define SPINOR_OP_SE_4B 0xdc /* Sector erase (usually 64KiB) */ +/* Double Transfer Rate opcodes - defined in JEDEC JESD216B. */ +#define SPINOR_OP_READ_1_1_1_DTR 0x0d +#define SPINOR_OP_READ_1_2_2_DTR 0xbd +#define SPINOR_OP_READ_1_4_4_DTR 0xed + +#define SPINOR_OP_READ_1_1_1_DTR_4B 0x0e +#define SPINOR_OP_READ_1_2_2_DTR_4B 0xbe +#define SPINOR_OP_READ_1_4_4_DTR_4B 0xee + /* Used for SST flashes only. */ #define SPINOR_OP_BP 0x02 /* Byte program */ #define SPINOR_OP_WRDI 0x04 /* Write disable */ @@ -138,10 +147,15 @@ ((((unsigned long)(_nbits)) << SNOR_PROTO_DATA_SHIFT) & \ SNOR_PROTO_DATA_MASK) +#define SNOR_PROTO_IS_DTR BIT(24) /* Double Transfer Rate */ + #define SNOR_PROTO_STR(_inst_nbits, _addr_nbits, _data_nbits) \ (SNOR_PROTO_INST(_inst_nbits) | \ SNOR_PROTO_ADDR(_addr_nbits) | \ SNOR_PROTO_DATA(_data_nbits)) +#define SNOR_PROTO_DTR(_inst_nbits, _addr_nbits, _data_nbits) \ + (SNOR_PROTO_IS_DTR | \ + SNOR_PROTO_STR(_inst_nbits, _addr_nbits, _data_nbits)) enum spi_nor_protocol { SNOR_PROTO_1_1_1 = SNOR_PROTO_STR(1, 1, 1), @@ -151,8 +165,17 @@ enum spi_nor_protocol { SNOR_PROTO_1_4_4 = SNOR_PROTO_STR(1, 4, 4), SNOR_PROTO_2_2_2 = SNOR_PROTO_STR(2, 2, 2), SNOR_PROTO_4_4_4 = SNOR_PROTO_STR(4, 4, 4), + + SNOR_PROTO_1_1_1_DTR = SNOR_PROTO_DTR(1, 1, 1), + SNOR_PROTO_1_2_2_DTR = SNOR_PROTO_DTR(1, 2, 2), + SNOR_PROTO_1_4_4_DTR = SNOR_PROTO_DTR(1, 4, 4), }; +static inline bool spi_nor_protocol_is_dtr(enum spi_nor_protocol proto) +{ + return !!(proto & SNOR_PROTO_IS_DTR); +} + static inline u8 spi_nor_get_protocol_inst_nbits(enum spi_nor_protocol proto) { return ((unsigned long)(proto & SNOR_PROTO_INST_MASK)) >> @@ -288,19 +311,22 @@ struct spi_nor_hwcaps { * As a matter of performances, it is relevant to use Quad SPI protocols first, * then Dual SPI protocols before Fast Read and lastly (Slow) Read. */ -#define SNOR_HWCAPS_READ_MASK GENMASK(7, 0) +#define SNOR_HWCAPS_READ_MASK GENMASK(10, 0) #define SNOR_HWCAPS_READ BIT(0) #define SNOR_HWCAPS_READ_FAST BIT(1) - -#define SNOR_HWCAPS_READ_DUAL GENMASK(4, 2) -#define SNOR_HWCAPS_READ_1_1_2 BIT(2) -#define SNOR_HWCAPS_READ_1_2_2 BIT(3) -#define SNOR_HWCAPS_READ_2_2_2 BIT(4) - -#define SNOR_HWCAPS_READ_QUAD GENMASK(7, 5) -#define SNOR_HWCAPS_READ_1_1_4 BIT(5) -#define SNOR_HWCAPS_READ_1_4_4 BIT(6) -#define SNOR_HWCAPS_READ_4_4_4 BIT(7) +#define SNOR_HWCAPS_READ_1_1_1_DTR BIT(2) + +#define SNOR_HWCAPS_READ_DUAL GENMASK(6, 3) +#define SNOR_HWCAPS_READ_1_1_2 BIT(3) +#define SNOR_HWCAPS_READ_1_2_2 BIT(4) +#define SNOR_HWCAPS_READ_2_2_2 BIT(5) +#define SNOR_HWCAPS_READ_1_2_2_DTR BIT(6) + +#define SNOR_HWCAPS_READ_QUAD GENMASK(10, 7) +#define SNOR_HWCAPS_READ_1_1_4 BIT(7) +#define SNOR_HWCAPS_READ_1_4_4 BIT(8) +#define SNOR_HWCAPS_READ_4_4_4 BIT(9) +#define SNOR_HWCAPS_READ_1_4_4_DTR BIT(10) /* * Page Program capabilities. -- cgit v1.2.3-59-g8ed1b From fe488a5e48c69204c3b1ad6fa3282e12dbfaabe7 Mon Sep 17 00:00:00 2001 From: Cyrille Pitchen Date: Tue, 25 Apr 2017 22:08:49 +0200 Subject: mtd: spi-nor: introduce Octo SPI protocols This patch starts adding support to Octo SPI protocols (SPI x-y-8). Op codes for Fast Read and/or Page Program operations using Octo SPI protocols are not known yet (no JEDEC specification has defined them yet) but we'd rather introduce the Octo SPI protocols now so it's done as it should be. Signed-off-by: Cyrille Pitchen Reviewed-by: Marek Vasut --- drivers/mtd/spi-nor/spi-nor.c | 22 +++++++++++++++++++++- include/linux/mtd/spi-nor.h | 26 +++++++++++++++++++++----- 2 files changed, 42 insertions(+), 6 deletions(-) diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 2062a3abba72..060a59e716be 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -1527,6 +1527,12 @@ enum spi_nor_read_command_index { SNOR_CMD_READ_4_4_4, SNOR_CMD_READ_1_4_4_DTR, + /* Octo SPI */ + SNOR_CMD_READ_1_1_8, + SNOR_CMD_READ_1_8_8, + SNOR_CMD_READ_8_8_8, + SNOR_CMD_READ_1_8_8_DTR, + SNOR_CMD_READ_MAX }; @@ -1538,6 +1544,11 @@ enum spi_nor_pp_command_index { SNOR_CMD_PP_1_4_4, SNOR_CMD_PP_4_4_4, + /* Octo SPI */ + SNOR_CMD_PP_1_1_8, + SNOR_CMD_PP_1_8_8, + SNOR_CMD_PP_8_8_8, + SNOR_CMD_PP_MAX }; @@ -1662,6 +1673,10 @@ static int spi_nor_hwcaps_read2cmd(u32 hwcaps) { SNOR_HWCAPS_READ_1_4_4, SNOR_CMD_READ_1_4_4 }, { SNOR_HWCAPS_READ_4_4_4, SNOR_CMD_READ_4_4_4 }, { SNOR_HWCAPS_READ_1_4_4_DTR, SNOR_CMD_READ_1_4_4_DTR }, + { SNOR_HWCAPS_READ_1_1_8, SNOR_CMD_READ_1_1_8 }, + { SNOR_HWCAPS_READ_1_8_8, SNOR_CMD_READ_1_8_8 }, + { SNOR_HWCAPS_READ_8_8_8, SNOR_CMD_READ_8_8_8 }, + { SNOR_HWCAPS_READ_1_8_8_DTR, SNOR_CMD_READ_1_8_8_DTR }, }; return spi_nor_hwcaps2cmd(hwcaps, hwcaps_read2cmd, @@ -1675,6 +1690,9 @@ static int spi_nor_hwcaps_pp2cmd(u32 hwcaps) { SNOR_HWCAPS_PP_1_1_4, SNOR_CMD_PP_1_1_4 }, { SNOR_HWCAPS_PP_1_4_4, SNOR_CMD_PP_1_4_4 }, { SNOR_HWCAPS_PP_4_4_4, SNOR_CMD_PP_4_4_4 }, + { SNOR_HWCAPS_PP_1_1_8, SNOR_CMD_PP_1_1_8 }, + { SNOR_HWCAPS_PP_1_8_8, SNOR_CMD_PP_1_8_8 }, + { SNOR_HWCAPS_PP_8_8_8, SNOR_CMD_PP_8_8_8 }, }; return spi_nor_hwcaps2cmd(hwcaps, hwcaps_pp2cmd, @@ -1772,7 +1790,9 @@ static int spi_nor_setup(struct spi_nor *nor, const struct flash_info *info, /* SPI n-n-n protocols are not supported yet. */ ignored_mask = (SNOR_HWCAPS_READ_2_2_2 | SNOR_HWCAPS_READ_4_4_4 | - SNOR_HWCAPS_PP_4_4_4); + SNOR_HWCAPS_READ_8_8_8 | + SNOR_HWCAPS_PP_4_4_4 | + SNOR_HWCAPS_PP_8_8_8); if (shared_mask & ignored_mask) { dev_dbg(nor->dev, "SPI n-n-n protocols are not supported yet.\n"); diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 313dbe56f31a..55faa2f07cca 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -161,14 +161,18 @@ enum spi_nor_protocol { SNOR_PROTO_1_1_1 = SNOR_PROTO_STR(1, 1, 1), SNOR_PROTO_1_1_2 = SNOR_PROTO_STR(1, 1, 2), SNOR_PROTO_1_1_4 = SNOR_PROTO_STR(1, 1, 4), + SNOR_PROTO_1_1_8 = SNOR_PROTO_STR(1, 1, 8), SNOR_PROTO_1_2_2 = SNOR_PROTO_STR(1, 2, 2), SNOR_PROTO_1_4_4 = SNOR_PROTO_STR(1, 4, 4), + SNOR_PROTO_1_8_8 = SNOR_PROTO_STR(1, 8, 8), SNOR_PROTO_2_2_2 = SNOR_PROTO_STR(2, 2, 2), SNOR_PROTO_4_4_4 = SNOR_PROTO_STR(4, 4, 4), + SNOR_PROTO_8_8_8 = SNOR_PROTO_STR(8, 8, 8), SNOR_PROTO_1_1_1_DTR = SNOR_PROTO_DTR(1, 1, 1), SNOR_PROTO_1_2_2_DTR = SNOR_PROTO_DTR(1, 2, 2), SNOR_PROTO_1_4_4_DTR = SNOR_PROTO_DTR(1, 4, 4), + SNOR_PROTO_1_8_8_DTR = SNOR_PROTO_DTR(1, 8, 8), }; static inline bool spi_nor_protocol_is_dtr(enum spi_nor_protocol proto) @@ -308,10 +312,11 @@ struct spi_nor_hwcaps { /* *(Fast) Read capabilities. * MUST be ordered by priority: the higher bit position, the higher priority. - * As a matter of performances, it is relevant to use Quad SPI protocols first, - * then Dual SPI protocols before Fast Read and lastly (Slow) Read. + * As a matter of performances, it is relevant to use Octo SPI protocols first, + * then Quad SPI protocols before Dual SPI protocols, Fast Read and lastly + * (Slow) Read. */ -#define SNOR_HWCAPS_READ_MASK GENMASK(10, 0) +#define SNOR_HWCAPS_READ_MASK GENMASK(14, 0) #define SNOR_HWCAPS_READ BIT(0) #define SNOR_HWCAPS_READ_FAST BIT(1) #define SNOR_HWCAPS_READ_1_1_1_DTR BIT(2) @@ -328,16 +333,22 @@ struct spi_nor_hwcaps { #define SNOR_HWCAPS_READ_4_4_4 BIT(9) #define SNOR_HWCAPS_READ_1_4_4_DTR BIT(10) +#define SNOR_HWCPAS_READ_OCTO GENMASK(14, 11) +#define SNOR_HWCAPS_READ_1_1_8 BIT(11) +#define SNOR_HWCAPS_READ_1_8_8 BIT(12) +#define SNOR_HWCAPS_READ_8_8_8 BIT(13) +#define SNOR_HWCAPS_READ_1_8_8_DTR BIT(14) + /* * Page Program capabilities. * MUST be ordered by priority: the higher bit position, the higher priority. - * Like (Fast) Read capabilities, Quad SPI protocols are preferred to the + * Like (Fast) Read capabilities, Octo/Quad SPI protocols are preferred to the * legacy SPI 1-1-1 protocol. * Note that Dual Page Programs are not supported because there is no existing * JEDEC/SFDP standard to define them. Also at this moment no SPI flash memory * implements such commands. */ -#define SNOR_HWCAPS_PP_MASK GENMASK(19, 16) +#define SNOR_HWCAPS_PP_MASK GENMASK(22, 16) #define SNOR_HWCAPS_PP BIT(16) #define SNOR_HWCAPS_PP_QUAD GENMASK(19, 17) @@ -345,6 +356,11 @@ struct spi_nor_hwcaps { #define SNOR_HWCAPS_PP_1_4_4 BIT(18) #define SNOR_HWCAPS_PP_4_4_4 BIT(19) +#define SNOR_HWCAPS_PP_OCTO GENMASK(22, 20) +#define SNOR_HWCAPS_PP_1_1_8 BIT(20) +#define SNOR_HWCAPS_PP_1_8_8 BIT(21) +#define SNOR_HWCAPS_PP_8_8_8 BIT(22) + /** * spi_nor_scan() - scan the SPI NOR * @nor: the spi_nor structure -- cgit v1.2.3-59-g8ed1b From ecca81f8cb54ce74f3d5d4ba77732a216173f7b1 Mon Sep 17 00:00:00 2001 From: Cyrille Pitchen Date: Thu, 4 May 2017 21:22:07 +0200 Subject: mtd: spi-nor: stm32-quadspi: fix compiler errors with COMPILE_TEST This patch fixes some compiler errors: - change format strings to use %zx for size_t - add missing #include Cc: Ludovic Barre Signed-off-by: Cyrille Pitchen --- drivers/mtd/spi-nor/stm32-quadspi.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/spi-nor/stm32-quadspi.c b/drivers/mtd/spi-nor/stm32-quadspi.c index 1056e7408d2a..86c0931543c5 100644 --- a/drivers/mtd/spi-nor/stm32-quadspi.c +++ b/drivers/mtd/spi-nor/stm32-quadspi.c @@ -19,6 +19,7 @@ #include #include #include +#include #define QUADSPI_CR 0x00 #define CR_EN BIT(0) @@ -375,7 +376,7 @@ static ssize_t stm32_qspi_read(struct spi_nor *nor, loff_t from, size_t len, struct stm32_qspi_cmd cmd; int err; - dev_dbg(qspi->dev, "read(%#.2x): buf:%p from:%#.8x len:%#x\n", + dev_dbg(qspi->dev, "read(%#.2x): buf:%p from:%#.8x len:%#zx\n", nor->read_opcode, buf, (u32)from, len); memset(&cmd, 0, sizeof(cmd)); @@ -402,7 +403,7 @@ static ssize_t stm32_qspi_write(struct spi_nor *nor, loff_t to, size_t len, struct stm32_qspi_cmd cmd; int err; - dev_dbg(dev, "write(%#.2x): buf:%p to:%#.8x len:%#x\n", + dev_dbg(dev, "write(%#.2x): buf:%p to:%#.8x len:%#zx\n", nor->program_opcode, buf, (u32)to, len); memset(&cmd, 0, sizeof(cmd)); -- cgit v1.2.3-59-g8ed1b From ddd0503e4d780607865950e14f215bf8660ed683 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Mon, 1 May 2017 18:13:00 -0700 Subject: mtd: spi-nor: stm32-quadspi: allow building with COMPILE_TEST Cc: Ludovic Barre Signed-off-by: Brian Norris Signed-off-by: Cyrille Pitchen --- drivers/mtd/spi-nor/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/spi-nor/Kconfig b/drivers/mtd/spi-nor/Kconfig index bfdfb1e72b38..293c8a4d1e49 100644 --- a/drivers/mtd/spi-nor/Kconfig +++ b/drivers/mtd/spi-nor/Kconfig @@ -108,7 +108,7 @@ config SPI_INTEL_SPI_PLATFORM config SPI_STM32_QUADSPI tristate "STM32 Quad SPI controller" - depends on ARCH_STM32 + depends on ARCH_STM32 || COMPILE_TEST help This enables support for the STM32 Quad SPI controller. We only connect the NOR to this controller. -- cgit v1.2.3-59-g8ed1b From 05d090f00203bdcf722b9cb6d5ac57c165e2c95c Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 5 May 2017 08:33:56 +0300 Subject: mtd: spi-nor: Potential oops on error path in quad_enable() Before commit cff959958832 ("mtd: spi-nor: introduce SPI 1-2-2 and SPI 1-4-4 protocols") then we treated 1 as -EINVAL in the caller but after that commit we changed to propagate the return. My static checker complains that it's eventually passed to an ERR_PTR() and later dereferenced, but I'm not totally certain if that's true. Regardless, returning 1 is wrong. Signed-off-by: Dan Carpenter Signed-off-by: Cyrille Pitchen --- drivers/mtd/spi-nor/spi-nor.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 060a59e716be..eef55b597ec7 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -1389,8 +1389,9 @@ static int macronix_quad_enable(struct spi_nor *nor) write_sr(nor, val | SR_QUAD_EN_MX); - if (spi_nor_wait_till_ready(nor)) - return 1; + ret = spi_nor_wait_till_ready(nor); + if (ret) + return ret; ret = read_sr(nor); if (!(ret > 0 && (ret & SR_QUAD_EN_MX))) { -- cgit v1.2.3-59-g8ed1b From 11e5890b5342c82eefbaa39aec4767ae21ae8803 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 10 Mar 2017 18:52:34 +0100 Subject: rtc: ds1307: convert driver to regmap This patch converts the ds1307 driver to using regmap. It's a rather big patch and I can test with DS3231 only. With this chip it's working fine. I'd appreciate if people with other supported hardware could test as well. Signed-off-by: Heiner Kallweit Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ds1307.c | 603 +++++++++++++++++------------------------------ 1 file changed, 221 insertions(+), 382 deletions(-) diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index 77339b3d50a1..94e13d703735 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -24,6 +24,7 @@ #include #include #include +#include /* * We can't determine type by probing, but if we expect pre-Linux code @@ -120,12 +121,11 @@ struct ds1307 { unsigned long flags; #define HAS_NVRAM 0 /* bit 0 == sysfs file active */ #define HAS_ALARM 1 /* bit 1 == irq claimed */ - struct i2c_client *client; + struct device *dev; + struct regmap *regmap; + const char *name; + int irq; struct rtc_device *rtc; - s32 (*read_block_data)(const struct i2c_client *client, u8 command, - u8 length, u8 *values); - s32 (*write_block_data)(const struct i2c_client *client, u8 command, - u8 length, const u8 *values); #ifdef CONFIG_COMMON_CLK struct clk_hw clks[2]; #endif @@ -137,11 +137,11 @@ struct chip_desc { u16 nvram_size; u16 trickle_charger_reg; u8 trickle_charger_setup; - u8 (*do_trickle_setup)(struct i2c_client *, uint32_t, bool); + u8 (*do_trickle_setup)(struct ds1307 *, uint32_t, + bool); }; -static u8 do_trickle_setup_ds1339(struct i2c_client *, - uint32_t ohms, bool diode); +static u8 do_trickle_setup_ds1339(struct ds1307 *, uint32_t ohms, bool diode); static struct chip_desc chips[last_ds_type] = { [ds_1307] = { @@ -280,136 +280,6 @@ static const struct acpi_device_id ds1307_acpi_ids[] = { MODULE_DEVICE_TABLE(acpi, ds1307_acpi_ids); #endif -/*----------------------------------------------------------------------*/ - -#define BLOCK_DATA_MAX_TRIES 10 - -static s32 ds1307_read_block_data_once(const struct i2c_client *client, - u8 command, u8 length, u8 *values) -{ - s32 i, data; - - for (i = 0; i < length; i++) { - data = i2c_smbus_read_byte_data(client, command + i); - if (data < 0) - return data; - values[i] = data; - } - return i; -} - -static s32 ds1307_read_block_data(const struct i2c_client *client, u8 command, - u8 length, u8 *values) -{ - u8 oldvalues[255]; - s32 ret; - int tries = 0; - - dev_dbg(&client->dev, "ds1307_read_block_data (length=%d)\n", length); - ret = ds1307_read_block_data_once(client, command, length, values); - if (ret < 0) - return ret; - do { - if (++tries > BLOCK_DATA_MAX_TRIES) { - dev_err(&client->dev, - "ds1307_read_block_data failed\n"); - return -EIO; - } - memcpy(oldvalues, values, length); - ret = ds1307_read_block_data_once(client, command, length, - values); - if (ret < 0) - return ret; - } while (memcmp(oldvalues, values, length)); - return length; -} - -static s32 ds1307_write_block_data(const struct i2c_client *client, u8 command, - u8 length, const u8 *values) -{ - u8 currvalues[255]; - int tries = 0; - - dev_dbg(&client->dev, "ds1307_write_block_data (length=%d)\n", length); - do { - s32 i, ret; - - if (++tries > BLOCK_DATA_MAX_TRIES) { - dev_err(&client->dev, - "ds1307_write_block_data failed\n"); - return -EIO; - } - for (i = 0; i < length; i++) { - ret = i2c_smbus_write_byte_data(client, command + i, - values[i]); - if (ret < 0) - return ret; - } - ret = ds1307_read_block_data_once(client, command, length, - currvalues); - if (ret < 0) - return ret; - } while (memcmp(currvalues, values, length)); - return length; -} - -/*----------------------------------------------------------------------*/ - -/* These RTC devices are not designed to be connected to a SMbus adapter. - SMbus limits block operations length to 32 bytes, whereas it's not - limited on I2C buses. As a result, accesses may exceed 32 bytes; - in that case, split them into smaller blocks */ - -static s32 ds1307_native_smbus_write_block_data(const struct i2c_client *client, - u8 command, u8 length, const u8 *values) -{ - u8 suboffset = 0; - - if (length <= I2C_SMBUS_BLOCK_MAX) { - s32 retval = i2c_smbus_write_i2c_block_data(client, - command, length, values); - if (retval < 0) - return retval; - return length; - } - - while (suboffset < length) { - s32 retval = i2c_smbus_write_i2c_block_data(client, - command + suboffset, - min(I2C_SMBUS_BLOCK_MAX, length - suboffset), - values + suboffset); - if (retval < 0) - return retval; - - suboffset += I2C_SMBUS_BLOCK_MAX; - } - return length; -} - -static s32 ds1307_native_smbus_read_block_data(const struct i2c_client *client, - u8 command, u8 length, u8 *values) -{ - u8 suboffset = 0; - - if (length <= I2C_SMBUS_BLOCK_MAX) - return i2c_smbus_read_i2c_block_data(client, - command, length, values); - - while (suboffset < length) { - s32 retval = i2c_smbus_read_i2c_block_data(client, - command + suboffset, - min(I2C_SMBUS_BLOCK_MAX, length - suboffset), - values + suboffset); - if (retval < 0) - return retval; - - suboffset += I2C_SMBUS_BLOCK_MAX; - } - return length; -} - -/*----------------------------------------------------------------------*/ - /* * The ds1337 and ds1339 both have two alarms, but we only use the first * one (with a "seconds" field). For ds1337 we expect nINTA is our alarm @@ -417,26 +287,25 @@ static s32 ds1307_native_smbus_read_block_data(const struct i2c_client *client, */ static irqreturn_t ds1307_irq(int irq, void *dev_id) { - struct i2c_client *client = dev_id; - struct ds1307 *ds1307 = i2c_get_clientdata(client); + struct ds1307 *ds1307 = dev_id; struct mutex *lock = &ds1307->rtc->ops_lock; - int stat, control; + int stat, control, ret; mutex_lock(lock); - stat = i2c_smbus_read_byte_data(client, DS1337_REG_STATUS); - if (stat < 0) + ret = regmap_read(ds1307->regmap, DS1337_REG_STATUS, &stat); + if (ret) goto out; if (stat & DS1337_BIT_A1I) { stat &= ~DS1337_BIT_A1I; - i2c_smbus_write_byte_data(client, DS1337_REG_STATUS, stat); + regmap_write(ds1307->regmap, DS1337_REG_STATUS, stat); - control = i2c_smbus_read_byte_data(client, DS1337_REG_CONTROL); - if (control < 0) + ret = regmap_read(ds1307->regmap, DS1337_REG_CONTROL, &control); + if (ret) goto out; control &= ~DS1337_BIT_A1IE; - i2c_smbus_write_byte_data(client, DS1337_REG_CONTROL, control); + regmap_write(ds1307->regmap, DS1337_REG_CONTROL, control); rtc_update_irq(ds1307->rtc, 1, RTC_AF | RTC_IRQF); } @@ -452,14 +321,13 @@ out: static int ds1307_get_time(struct device *dev, struct rtc_time *t) { struct ds1307 *ds1307 = dev_get_drvdata(dev); - int tmp; + int tmp, ret; /* read the RTC date and time registers all at once */ - tmp = ds1307->read_block_data(ds1307->client, - ds1307->offset, 7, ds1307->regs); - if (tmp != 7) { - dev_err(dev, "%s error %d\n", "read", tmp); - return -EIO; + ret = regmap_bulk_read(ds1307->regmap, ds1307->offset, ds1307->regs, 7); + if (ret) { + dev_err(dev, "%s error %d\n", "read", ret); + return ret; } dev_dbg(dev, "%s: %7ph\n", "read", ds1307->regs); @@ -580,9 +448,8 @@ static int ds1307_set_time(struct device *dev, struct rtc_time *t) dev_dbg(dev, "%s: %7ph\n", "write", buf); - result = ds1307->write_block_data(ds1307->client, - ds1307->offset, 7, buf); - if (result < 0) { + result = regmap_bulk_write(ds1307->regmap, ds1307->offset, buf, 7); + if (result) { dev_err(dev, "%s error %d\n", "write", result); return result; } @@ -591,19 +458,18 @@ static int ds1307_set_time(struct device *dev, struct rtc_time *t) static int ds1337_read_alarm(struct device *dev, struct rtc_wkalrm *t) { - struct i2c_client *client = to_i2c_client(dev); - struct ds1307 *ds1307 = i2c_get_clientdata(client); + struct ds1307 *ds1307 = dev_get_drvdata(dev); int ret; if (!test_bit(HAS_ALARM, &ds1307->flags)) return -EINVAL; /* read all ALARM1, ALARM2, and status registers at once */ - ret = ds1307->read_block_data(client, - DS1339_REG_ALARM1_SECS, 9, ds1307->regs); - if (ret != 9) { + ret = regmap_bulk_read(ds1307->regmap, DS1339_REG_ALARM1_SECS, + ds1307->regs, 9); + if (ret) { dev_err(dev, "%s error %d\n", "alarm read", ret); - return -EIO; + return ret; } dev_dbg(dev, "%s: %4ph, %3ph, %2ph\n", "alarm read", @@ -633,8 +499,7 @@ static int ds1337_read_alarm(struct device *dev, struct rtc_wkalrm *t) static int ds1337_set_alarm(struct device *dev, struct rtc_wkalrm *t) { - struct i2c_client *client = to_i2c_client(dev); - struct ds1307 *ds1307 = i2c_get_clientdata(client); + struct ds1307 *ds1307 = dev_get_drvdata(dev); unsigned char *buf = ds1307->regs; u8 control, status; int ret; @@ -649,11 +514,10 @@ static int ds1337_set_alarm(struct device *dev, struct rtc_wkalrm *t) t->enabled, t->pending); /* read current status of both alarms and the chip */ - ret = ds1307->read_block_data(client, - DS1339_REG_ALARM1_SECS, 9, buf); - if (ret != 9) { + ret = regmap_bulk_read(ds1307->regmap, DS1339_REG_ALARM1_SECS, buf, 9); + if (ret) { dev_err(dev, "%s error %d\n", "alarm write", ret); - return -EIO; + return ret; } control = ds1307->regs[7]; status = ds1307->regs[8]; @@ -676,9 +540,8 @@ static int ds1337_set_alarm(struct device *dev, struct rtc_wkalrm *t) buf[7] = control & ~(DS1337_BIT_A1IE | DS1337_BIT_A2IE); buf[8] = status & ~(DS1337_BIT_A1I | DS1337_BIT_A2I); - ret = ds1307->write_block_data(client, - DS1339_REG_ALARM1_SECS, 9, buf); - if (ret < 0) { + ret = regmap_bulk_write(ds1307->regmap, DS1339_REG_ALARM1_SECS, buf, 9); + if (ret) { dev_err(dev, "can't set alarm time\n"); return ret; } @@ -687,7 +550,7 @@ static int ds1337_set_alarm(struct device *dev, struct rtc_wkalrm *t) if (t->enabled) { dev_dbg(dev, "alarm IRQ armed\n"); buf[7] |= DS1337_BIT_A1IE; /* only ALARM1 is used */ - i2c_smbus_write_byte_data(client, DS1337_REG_CONTROL, buf[7]); + regmap_write(ds1307->regmap, DS1337_REG_CONTROL, buf[7]); } return 0; @@ -695,27 +558,22 @@ static int ds1337_set_alarm(struct device *dev, struct rtc_wkalrm *t) static int ds1307_alarm_irq_enable(struct device *dev, unsigned int enabled) { - struct i2c_client *client = to_i2c_client(dev); - struct ds1307 *ds1307 = i2c_get_clientdata(client); - int ret; + struct ds1307 *ds1307 = dev_get_drvdata(dev); + int control, ret; if (!test_bit(HAS_ALARM, &ds1307->flags)) return -ENOTTY; - ret = i2c_smbus_read_byte_data(client, DS1337_REG_CONTROL); - if (ret < 0) + ret = regmap_read(ds1307->regmap, DS1337_REG_CONTROL, &control); + if (ret) return ret; if (enabled) - ret |= DS1337_BIT_A1IE; + control |= DS1337_BIT_A1IE; else - ret &= ~DS1337_BIT_A1IE; - - ret = i2c_smbus_write_byte_data(client, DS1337_REG_CONTROL, ret); - if (ret < 0) - return ret; + control &= ~DS1337_BIT_A1IE; - return 0; + return regmap_write(ds1307->regmap, DS1337_REG_CONTROL, control); } static const struct rtc_class_ops ds13xx_rtc_ops = { @@ -752,31 +610,30 @@ static const struct rtc_class_ops ds13xx_rtc_ops = { static irqreturn_t mcp794xx_irq(int irq, void *dev_id) { - struct i2c_client *client = dev_id; - struct ds1307 *ds1307 = i2c_get_clientdata(client); + struct ds1307 *ds1307 = dev_id; struct mutex *lock = &ds1307->rtc->ops_lock; int reg, ret; mutex_lock(lock); /* Check and clear alarm 0 interrupt flag. */ - reg = i2c_smbus_read_byte_data(client, MCP794XX_REG_ALARM0_CTRL); - if (reg < 0) + ret = regmap_read(ds1307->regmap, MCP794XX_REG_ALARM0_CTRL, ®); + if (ret) goto out; if (!(reg & MCP794XX_BIT_ALMX_IF)) goto out; reg &= ~MCP794XX_BIT_ALMX_IF; - ret = i2c_smbus_write_byte_data(client, MCP794XX_REG_ALARM0_CTRL, reg); - if (ret < 0) + ret = regmap_write(ds1307->regmap, MCP794XX_REG_ALARM0_CTRL, reg); + if (ret) goto out; /* Disable alarm 0. */ - reg = i2c_smbus_read_byte_data(client, MCP794XX_REG_CONTROL); - if (reg < 0) + ret = regmap_read(ds1307->regmap, MCP794XX_REG_CONTROL, ®); + if (ret) goto out; reg &= ~MCP794XX_BIT_ALM0_EN; - ret = i2c_smbus_write_byte_data(client, MCP794XX_REG_CONTROL, reg); - if (ret < 0) + ret = regmap_write(ds1307->regmap, MCP794XX_REG_CONTROL, reg); + if (ret) goto out; rtc_update_irq(ds1307->rtc, 1, RTC_AF | RTC_IRQF); @@ -789,8 +646,7 @@ out: static int mcp794xx_read_alarm(struct device *dev, struct rtc_wkalrm *t) { - struct i2c_client *client = to_i2c_client(dev); - struct ds1307 *ds1307 = i2c_get_clientdata(client); + struct ds1307 *ds1307 = dev_get_drvdata(dev); u8 *regs = ds1307->regs; int ret; @@ -798,8 +654,8 @@ static int mcp794xx_read_alarm(struct device *dev, struct rtc_wkalrm *t) return -EINVAL; /* Read control and alarm 0 registers. */ - ret = ds1307->read_block_data(client, MCP794XX_REG_CONTROL, 10, regs); - if (ret < 0) + ret = regmap_bulk_read(ds1307->regmap, MCP794XX_REG_CONTROL, regs, 10); + if (ret) return ret; t->enabled = !!(regs[0] & MCP794XX_BIT_ALM0_EN); @@ -828,8 +684,7 @@ static int mcp794xx_read_alarm(struct device *dev, struct rtc_wkalrm *t) static int mcp794xx_set_alarm(struct device *dev, struct rtc_wkalrm *t) { - struct i2c_client *client = to_i2c_client(dev); - struct ds1307 *ds1307 = i2c_get_clientdata(client); + struct ds1307 *ds1307 = dev_get_drvdata(dev); unsigned char *regs = ds1307->regs; int ret; @@ -843,8 +698,8 @@ static int mcp794xx_set_alarm(struct device *dev, struct rtc_wkalrm *t) t->enabled, t->pending); /* Read control and alarm 0 registers. */ - ret = ds1307->read_block_data(client, MCP794XX_REG_CONTROL, 10, regs); - if (ret < 0) + ret = regmap_bulk_read(ds1307->regmap, MCP794XX_REG_CONTROL, regs, 10); + if (ret) return ret; /* Set alarm 0, using 24-hour and day-of-month modes. */ @@ -862,35 +717,34 @@ static int mcp794xx_set_alarm(struct device *dev, struct rtc_wkalrm *t) /* Disable interrupt. We will not enable until completely programmed */ regs[0] &= ~MCP794XX_BIT_ALM0_EN; - ret = ds1307->write_block_data(client, MCP794XX_REG_CONTROL, 10, regs); - if (ret < 0) + ret = regmap_bulk_write(ds1307->regmap, MCP794XX_REG_CONTROL, regs, 10); + if (ret) return ret; if (!t->enabled) return 0; regs[0] |= MCP794XX_BIT_ALM0_EN; - return i2c_smbus_write_byte_data(client, MCP794XX_REG_CONTROL, regs[0]); + return regmap_write(ds1307->regmap, MCP794XX_REG_CONTROL, regs[0]); } static int mcp794xx_alarm_irq_enable(struct device *dev, unsigned int enabled) { - struct i2c_client *client = to_i2c_client(dev); - struct ds1307 *ds1307 = i2c_get_clientdata(client); - int reg; + struct ds1307 *ds1307 = dev_get_drvdata(dev); + int reg, ret; if (!test_bit(HAS_ALARM, &ds1307->flags)) return -EINVAL; - reg = i2c_smbus_read_byte_data(client, MCP794XX_REG_CONTROL); - if (reg < 0) - return reg; + ret = regmap_read(ds1307->regmap, MCP794XX_REG_CONTROL, ®); + if (ret) + return ret; if (enabled) reg |= MCP794XX_BIT_ALM0_EN; else reg &= ~MCP794XX_BIT_ALM0_EN; - return i2c_smbus_write_byte_data(client, MCP794XX_REG_CONTROL, reg); + return regmap_write(ds1307->regmap, MCP794XX_REG_CONTROL, reg); } static const struct rtc_class_ops mcp794xx_rtc_ops = { @@ -908,17 +762,15 @@ ds1307_nvram_read(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { - struct i2c_client *client; struct ds1307 *ds1307; int result; - client = kobj_to_i2c_client(kobj); - ds1307 = i2c_get_clientdata(client); + ds1307 = dev_get_drvdata(kobj_to_dev(kobj)); - result = ds1307->read_block_data(client, ds1307->nvram_offset + off, - count, buf); - if (result < 0) - dev_err(&client->dev, "%s error %d\n", "nvram read", result); + result = regmap_bulk_read(ds1307->regmap, ds1307->nvram_offset + off, + buf, count); + if (result) + dev_err(ds1307->dev, "%s error %d\n", "nvram read", result); return result; } @@ -927,17 +779,15 @@ ds1307_nvram_write(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { - struct i2c_client *client; struct ds1307 *ds1307; int result; - client = kobj_to_i2c_client(kobj); - ds1307 = i2c_get_clientdata(client); + ds1307 = dev_get_drvdata(kobj_to_dev(kobj)); - result = ds1307->write_block_data(client, ds1307->nvram_offset + off, - count, buf); - if (result < 0) { - dev_err(&client->dev, "%s error %d\n", "nvram write", result); + result = regmap_bulk_write(ds1307->regmap, ds1307->nvram_offset + off, + buf, count); + if (result) { + dev_err(ds1307->dev, "%s error %d\n", "nvram write", result); return result; } return count; @@ -946,7 +796,7 @@ ds1307_nvram_write(struct file *filp, struct kobject *kobj, /*----------------------------------------------------------------------*/ -static u8 do_trickle_setup_ds1339(struct i2c_client *client, +static u8 do_trickle_setup_ds1339(struct ds1307 *ds1307, uint32_t ohms, bool diode) { u8 setup = (diode) ? DS1307_TRICKLE_CHARGER_DIODE : @@ -963,14 +813,14 @@ static u8 do_trickle_setup_ds1339(struct i2c_client *client, setup |= DS1307_TRICKLE_CHARGER_4K_OHM; break; default: - dev_warn(&client->dev, + dev_warn(ds1307->dev, "Unsupported ohm value %u in dt\n", ohms); return 0; } return setup; } -static void ds1307_trickle_init(struct i2c_client *client, +static void ds1307_trickle_init(struct ds1307 *ds1307, struct chip_desc *chip) { uint32_t ohms = 0; @@ -978,11 +828,12 @@ static void ds1307_trickle_init(struct i2c_client *client, if (!chip->do_trickle_setup) goto out; - if (device_property_read_u32(&client->dev, "trickle-resistor-ohms", &ohms)) + if (device_property_read_u32(ds1307->dev, "trickle-resistor-ohms", + &ohms)) goto out; - if (device_property_read_bool(&client->dev, "trickle-diode-disable")) + if (device_property_read_bool(ds1307->dev, "trickle-diode-disable")) diode = false; - chip->trickle_charger_setup = chip->do_trickle_setup(client, + chip->trickle_charger_setup = chip->do_trickle_setup(ds1307, ohms, diode); out: return; @@ -1009,13 +860,10 @@ static int ds3231_hwmon_read_temp(struct device *dev, s32 *mC) s16 temp; int ret; - ret = ds1307->read_block_data(ds1307->client, DS3231_REG_TEMPERATURE, - sizeof(temp_buf), temp_buf); - if (ret < 0) + ret = regmap_bulk_read(ds1307->regmap, DS3231_REG_TEMPERATURE, + temp_buf, sizeof(temp_buf)); + if (ret) return ret; - if (ret != sizeof(temp_buf)) - return -EIO; - /* * Temperature is represented as a 10-bit code with a resolution of * 0.25 degree celsius and encoded in two's complement format. @@ -1055,12 +903,11 @@ static void ds1307_hwmon_register(struct ds1307 *ds1307) if (ds1307->type != ds_3231) return; - dev = devm_hwmon_device_register_with_groups(&ds1307->client->dev, - ds1307->client->name, + dev = devm_hwmon_device_register_with_groups(ds1307->dev, ds1307->name, ds1307, ds3231_hwmon_groups); if (IS_ERR(dev)) { - dev_warn(&ds1307->client->dev, - "unable to register hwmon device %ld\n", PTR_ERR(dev)); + dev_warn(ds1307->dev, "unable to register hwmon device %ld\n", + PTR_ERR(dev)); } } @@ -1099,23 +946,20 @@ static int ds3231_clk_sqw_rates[] = { static int ds1337_write_control(struct ds1307 *ds1307, u8 mask, u8 value) { - struct i2c_client *client = ds1307->client; struct mutex *lock = &ds1307->rtc->ops_lock; int control; int ret; mutex_lock(lock); - control = i2c_smbus_read_byte_data(client, DS1337_REG_CONTROL); - if (control < 0) { - ret = control; + ret = regmap_read(ds1307->regmap, DS1337_REG_CONTROL, &control); + if (ret) goto out; - } control &= ~mask; control |= value; - ret = i2c_smbus_write_byte_data(client, DS1337_REG_CONTROL, control); + ret = regmap_write(ds1307->regmap, DS1337_REG_CONTROL, control); out: mutex_unlock(lock); @@ -1126,12 +970,12 @@ static unsigned long ds3231_clk_sqw_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) { struct ds1307 *ds1307 = clk_sqw_to_ds1307(hw); - int control; + int control, ret; int rate_sel = 0; - control = i2c_smbus_read_byte_data(ds1307->client, DS1337_REG_CONTROL); - if (control < 0) - return control; + ret = regmap_read(ds1307->regmap, DS1337_REG_CONTROL, &control); + if (ret) + return ret; if (control & DS1337_BIT_RS1) rate_sel += 1; if (control & DS1337_BIT_RS2) @@ -1195,11 +1039,11 @@ static void ds3231_clk_sqw_unprepare(struct clk_hw *hw) static int ds3231_clk_sqw_is_prepared(struct clk_hw *hw) { struct ds1307 *ds1307 = clk_sqw_to_ds1307(hw); - int control; + int control, ret; - control = i2c_smbus_read_byte_data(ds1307->client, DS1337_REG_CONTROL); - if (control < 0) - return control; + ret = regmap_read(ds1307->regmap, DS1337_REG_CONTROL, &control); + if (ret) + return ret; return !(control & DS1337_BIT_INTCN); } @@ -1221,25 +1065,22 @@ static unsigned long ds3231_clk_32khz_recalc_rate(struct clk_hw *hw, static int ds3231_clk_32khz_control(struct ds1307 *ds1307, bool enable) { - struct i2c_client *client = ds1307->client; struct mutex *lock = &ds1307->rtc->ops_lock; int status; int ret; mutex_lock(lock); - status = i2c_smbus_read_byte_data(client, DS1337_REG_STATUS); - if (status < 0) { - ret = status; + ret = regmap_read(ds1307->regmap, DS1337_REG_STATUS, &status); + if (ret) goto out; - } if (enable) status |= DS3231_BIT_EN32KHZ; else status &= ~DS3231_BIT_EN32KHZ; - ret = i2c_smbus_write_byte_data(client, DS1337_REG_STATUS, status); + ret = regmap_write(ds1307->regmap, DS1337_REG_STATUS, status); out: mutex_unlock(lock); @@ -1263,11 +1104,11 @@ static void ds3231_clk_32khz_unprepare(struct clk_hw *hw) static int ds3231_clk_32khz_is_prepared(struct clk_hw *hw) { struct ds1307 *ds1307 = clk_32khz_to_ds1307(hw); - int status; + int status, ret; - status = i2c_smbus_read_byte_data(ds1307->client, DS1337_REG_STATUS); - if (status < 0) - return status; + ret = regmap_read(ds1307->regmap, DS1337_REG_STATUS, &status); + if (ret) + return ret; return !!(status & DS3231_BIT_EN32KHZ); } @@ -1292,18 +1133,17 @@ static struct clk_init_data ds3231_clks_init[] = { static int ds3231_clks_register(struct ds1307 *ds1307) { - struct i2c_client *client = ds1307->client; - struct device_node *node = client->dev.of_node; + struct device_node *node = ds1307->dev->of_node; struct clk_onecell_data *onecell; int i; - onecell = devm_kzalloc(&client->dev, sizeof(*onecell), GFP_KERNEL); + onecell = devm_kzalloc(ds1307->dev, sizeof(*onecell), GFP_KERNEL); if (!onecell) return -ENOMEM; onecell->clk_num = ARRAY_SIZE(ds3231_clks_init); - onecell->clks = devm_kcalloc(&client->dev, onecell->clk_num, - sizeof(onecell->clks[0]), GFP_KERNEL); + onecell->clks = devm_kcalloc(ds1307->dev, onecell->clk_num, + sizeof(onecell->clks[0]), GFP_KERNEL); if (!onecell->clks) return -ENOMEM; @@ -1322,8 +1162,8 @@ static int ds3231_clks_register(struct ds1307 *ds1307) &init.name); ds1307->clks[i].init = &init; - onecell->clks[i] = devm_clk_register(&client->dev, - &ds1307->clks[i]); + onecell->clks[i] = devm_clk_register(ds1307->dev, + &ds1307->clks[i]); if (IS_ERR(onecell->clks[i])) return PTR_ERR(onecell->clks[i]); } @@ -1345,8 +1185,8 @@ static void ds1307_clks_register(struct ds1307 *ds1307) ret = ds3231_clks_register(ds1307); if (ret) { - dev_warn(&ds1307->client->dev, - "unable to register clock device %d\n", ret); + dev_warn(ds1307->dev, "unable to register clock device %d\n", + ret); } } @@ -1358,6 +1198,12 @@ static void ds1307_clks_register(struct ds1307 *ds1307) #endif /* CONFIG_COMMON_CLK */ +static const struct regmap_config regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .max_register = 0x12, +}; + static int ds1307_probe(struct i2c_client *client, const struct i2c_device_id *id) { @@ -1365,7 +1211,6 @@ static int ds1307_probe(struct i2c_client *client, int err = -ENODEV; int tmp, wday; struct chip_desc *chip; - struct i2c_adapter *adapter = to_i2c_adapter(client->dev.parent); bool want_irq = false; bool ds1307_can_wakeup_device = false; unsigned char *buf; @@ -1382,17 +1227,22 @@ static int ds1307_probe(struct i2c_client *client, }; const struct rtc_class_ops *rtc_ops = &ds13xx_rtc_ops; - if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA) - && !i2c_check_functionality(adapter, I2C_FUNC_SMBUS_I2C_BLOCK)) - return -EIO; - ds1307 = devm_kzalloc(&client->dev, sizeof(struct ds1307), GFP_KERNEL); if (!ds1307) return -ENOMEM; - i2c_set_clientdata(client, ds1307); + dev_set_drvdata(&client->dev, ds1307); + ds1307->dev = &client->dev; + ds1307->name = client->name; + ds1307->irq = client->irq; + + ds1307->regmap = devm_regmap_init_i2c(client, ®map_config); + if (IS_ERR(ds1307->regmap)) { + dev_err(ds1307->dev, "regmap allocation failed\n"); + return PTR_ERR(ds1307->regmap); + } - ds1307->client = client; + i2c_set_clientdata(client, ds1307); if (client->dev.of_node) { ds1307->type = (enum ds_type) @@ -1405,7 +1255,7 @@ static int ds1307_probe(struct i2c_client *client, const struct acpi_device_id *acpi_id; acpi_id = acpi_match_device(ACPI_PTR(ds1307_acpi_ids), - &client->dev); + ds1307->dev); if (!acpi_id) return -ENODEV; chip = &chips[acpi_id->driver_data]; @@ -1413,27 +1263,21 @@ static int ds1307_probe(struct i2c_client *client, } if (!pdata) - ds1307_trickle_init(client, chip); + ds1307_trickle_init(ds1307, chip); else if (pdata->trickle_charger_setup) chip->trickle_charger_setup = pdata->trickle_charger_setup; if (chip->trickle_charger_setup && chip->trickle_charger_reg) { - dev_dbg(&client->dev, "writing trickle charger info 0x%x to 0x%x\n", + dev_dbg(ds1307->dev, + "writing trickle charger info 0x%x to 0x%x\n", DS13XX_TRICKLE_CHARGER_MAGIC | chip->trickle_charger_setup, chip->trickle_charger_reg); - i2c_smbus_write_byte_data(client, chip->trickle_charger_reg, + regmap_write(ds1307->regmap, chip->trickle_charger_reg, DS13XX_TRICKLE_CHARGER_MAGIC | chip->trickle_charger_setup); } buf = ds1307->regs; - if (i2c_check_functionality(adapter, I2C_FUNC_SMBUS_I2C_BLOCK)) { - ds1307->read_block_data = ds1307_native_smbus_read_block_data; - ds1307->write_block_data = ds1307_native_smbus_write_block_data; - } else { - ds1307->read_block_data = ds1307_read_block_data; - ds1307->write_block_data = ds1307_write_block_data; - } #ifdef CONFIG_OF /* @@ -1459,11 +1303,10 @@ static int ds1307_probe(struct i2c_client *client, case ds_1339: case ds_3231: /* get registers that the "rtc" read below won't read... */ - tmp = ds1307->read_block_data(ds1307->client, - DS1337_REG_CONTROL, 2, buf); - if (tmp != 2) { - dev_dbg(&client->dev, "read error %d\n", tmp); - err = -EIO; + err = regmap_bulk_read(ds1307->regmap, DS1337_REG_CONTROL, + buf, 2); + if (err) { + dev_dbg(ds1307->dev, "read error %d\n", err); goto exit; } @@ -1477,8 +1320,8 @@ static int ds1307_probe(struct i2c_client *client, * For some variants, be sure alarms can trigger when we're * running on Vbackup (BBSQI/BBSQW) */ - if (chip->alarm && (ds1307->client->irq > 0 || - ds1307_can_wakeup_device)) { + if (chip->alarm && (ds1307->irq > 0 || + ds1307_can_wakeup_device)) { ds1307->regs[0] |= DS1337_BIT_INTCN | bbsqi_bitpos[ds1307->type]; ds1307->regs[0] &= ~(DS1337_BIT_A2IE | DS1337_BIT_A1IE); @@ -1486,50 +1329,49 @@ static int ds1307_probe(struct i2c_client *client, want_irq = true; } - i2c_smbus_write_byte_data(client, DS1337_REG_CONTROL, - ds1307->regs[0]); + regmap_write(ds1307->regmap, DS1337_REG_CONTROL, + ds1307->regs[0]); /* oscillator fault? clear flag, and warn */ if (ds1307->regs[1] & DS1337_BIT_OSF) { - i2c_smbus_write_byte_data(client, DS1337_REG_STATUS, - ds1307->regs[1] & ~DS1337_BIT_OSF); - dev_warn(&client->dev, "SET TIME!\n"); + regmap_write(ds1307->regmap, DS1337_REG_STATUS, + ds1307->regs[1] & ~DS1337_BIT_OSF); + dev_warn(ds1307->dev, "SET TIME!\n"); } break; case rx_8025: - tmp = i2c_smbus_read_i2c_block_data(ds1307->client, - RX8025_REG_CTRL1 << 4 | 0x08, 2, buf); - if (tmp != 2) { - dev_dbg(&client->dev, "read error %d\n", tmp); - err = -EIO; + err = regmap_bulk_read(ds1307->regmap, + RX8025_REG_CTRL1 << 4 | 0x08, buf, 2); + if (err) { + dev_dbg(ds1307->dev, "read error %d\n", err); goto exit; } /* oscillator off? turn it on, so clock can tick. */ if (!(ds1307->regs[1] & RX8025_BIT_XST)) { ds1307->regs[1] |= RX8025_BIT_XST; - i2c_smbus_write_byte_data(client, - RX8025_REG_CTRL2 << 4 | 0x08, - ds1307->regs[1]); - dev_warn(&client->dev, + regmap_write(ds1307->regmap, + RX8025_REG_CTRL2 << 4 | 0x08, + ds1307->regs[1]); + dev_warn(ds1307->dev, "oscillator stop detected - SET TIME!\n"); } if (ds1307->regs[1] & RX8025_BIT_PON) { ds1307->regs[1] &= ~RX8025_BIT_PON; - i2c_smbus_write_byte_data(client, - RX8025_REG_CTRL2 << 4 | 0x08, - ds1307->regs[1]); - dev_warn(&client->dev, "power-on detected\n"); + regmap_write(ds1307->regmap, + RX8025_REG_CTRL2 << 4 | 0x08, + ds1307->regs[1]); + dev_warn(ds1307->dev, "power-on detected\n"); } if (ds1307->regs[1] & RX8025_BIT_VDET) { ds1307->regs[1] &= ~RX8025_BIT_VDET; - i2c_smbus_write_byte_data(client, - RX8025_REG_CTRL2 << 4 | 0x08, - ds1307->regs[1]); - dev_warn(&client->dev, "voltage drop detected\n"); + regmap_write(ds1307->regmap, + RX8025_REG_CTRL2 << 4 | 0x08, + ds1307->regs[1]); + dev_warn(ds1307->dev, "voltage drop detected\n"); } /* make sure we are running in 24hour mode */ @@ -1537,16 +1379,15 @@ static int ds1307_probe(struct i2c_client *client, u8 hour; /* switch to 24 hour mode */ - i2c_smbus_write_byte_data(client, - RX8025_REG_CTRL1 << 4 | 0x08, - ds1307->regs[0] | - RX8025_BIT_2412); - - tmp = i2c_smbus_read_i2c_block_data(ds1307->client, - RX8025_REG_CTRL1 << 4 | 0x08, 2, buf); - if (tmp != 2) { - dev_dbg(&client->dev, "read error %d\n", tmp); - err = -EIO; + regmap_write(ds1307->regmap, + RX8025_REG_CTRL1 << 4 | 0x08, + ds1307->regs[0] | RX8025_BIT_2412); + + err = regmap_bulk_read(ds1307->regmap, + RX8025_REG_CTRL1 << 4 | 0x08, + buf, 2); + if (err) { + dev_dbg(ds1307->dev, "read error %d\n", err); goto exit; } @@ -1557,9 +1398,8 @@ static int ds1307_probe(struct i2c_client *client, if (ds1307->regs[DS1307_REG_HOUR] & DS1307_BIT_PM) hour += 12; - i2c_smbus_write_byte_data(client, - DS1307_REG_HOUR << 4 | 0x08, - hour); + regmap_write(ds1307->regmap, + DS1307_REG_HOUR << 4 | 0x08, hour); } break; case ds_1388: @@ -1567,7 +1407,7 @@ static int ds1307_probe(struct i2c_client *client, break; case mcp794xx: rtc_ops = &mcp794xx_rtc_ops; - if (ds1307->client->irq > 0 && chip->alarm) { + if (ds1307->irq > 0 && chip->alarm) { irq_handler = mcp794xx_irq; want_irq = true; } @@ -1578,10 +1418,9 @@ static int ds1307_probe(struct i2c_client *client, read_rtc: /* read RTC registers */ - tmp = ds1307->read_block_data(ds1307->client, ds1307->offset, 8, buf); - if (tmp != 8) { - dev_dbg(&client->dev, "read error %d\n", tmp); - err = -EIO; + err = regmap_bulk_read(ds1307->regmap, ds1307->offset, buf, 8); + if (err) { + dev_dbg(ds1307->dev, "read error %d\n", err); goto exit; } @@ -1597,56 +1436,55 @@ read_rtc: case m41t00: /* clock halted? turn it on, so clock can tick. */ if (tmp & DS1307_BIT_CH) { - i2c_smbus_write_byte_data(client, DS1307_REG_SECS, 0); - dev_warn(&client->dev, "SET TIME!\n"); + regmap_write(ds1307->regmap, DS1307_REG_SECS, 0); + dev_warn(ds1307->dev, "SET TIME!\n"); goto read_rtc; } break; case ds_1338: /* clock halted? turn it on, so clock can tick. */ if (tmp & DS1307_BIT_CH) - i2c_smbus_write_byte_data(client, DS1307_REG_SECS, 0); + regmap_write(ds1307->regmap, DS1307_REG_SECS, 0); /* oscillator fault? clear flag, and warn */ if (ds1307->regs[DS1307_REG_CONTROL] & DS1338_BIT_OSF) { - i2c_smbus_write_byte_data(client, DS1307_REG_CONTROL, - ds1307->regs[DS1307_REG_CONTROL] - & ~DS1338_BIT_OSF); - dev_warn(&client->dev, "SET TIME!\n"); + regmap_write(ds1307->regmap, DS1307_REG_CONTROL, + ds1307->regs[DS1307_REG_CONTROL] & + ~DS1338_BIT_OSF); + dev_warn(ds1307->dev, "SET TIME!\n"); goto read_rtc; } break; case ds_1340: /* clock halted? turn it on, so clock can tick. */ if (tmp & DS1340_BIT_nEOSC) - i2c_smbus_write_byte_data(client, DS1307_REG_SECS, 0); + regmap_write(ds1307->regmap, DS1307_REG_SECS, 0); - tmp = i2c_smbus_read_byte_data(client, DS1340_REG_FLAG); - if (tmp < 0) { - dev_dbg(&client->dev, "read error %d\n", tmp); - err = -EIO; + err = regmap_read(ds1307->regmap, DS1340_REG_FLAG, &tmp); + if (err) { + dev_dbg(ds1307->dev, "read error %d\n", err); goto exit; } /* oscillator fault? clear flag, and warn */ if (tmp & DS1340_BIT_OSF) { - i2c_smbus_write_byte_data(client, DS1340_REG_FLAG, 0); - dev_warn(&client->dev, "SET TIME!\n"); + regmap_write(ds1307->regmap, DS1340_REG_FLAG, 0); + dev_warn(ds1307->dev, "SET TIME!\n"); } break; case mcp794xx: /* make sure that the backup battery is enabled */ if (!(ds1307->regs[DS1307_REG_WDAY] & MCP794XX_BIT_VBATEN)) { - i2c_smbus_write_byte_data(client, DS1307_REG_WDAY, - ds1307->regs[DS1307_REG_WDAY] - | MCP794XX_BIT_VBATEN); + regmap_write(ds1307->regmap, DS1307_REG_WDAY, + ds1307->regs[DS1307_REG_WDAY] | + MCP794XX_BIT_VBATEN); } /* clock halted? turn it on, so clock can tick. */ if (!(tmp & MCP794XX_BIT_ST)) { - i2c_smbus_write_byte_data(client, DS1307_REG_SECS, - MCP794XX_BIT_ST); - dev_warn(&client->dev, "SET TIME!\n"); + regmap_write(ds1307->regmap, DS1307_REG_SECS, + MCP794XX_BIT_ST); + dev_warn(ds1307->dev, "SET TIME!\n"); goto read_rtc; } @@ -1680,16 +1518,15 @@ read_rtc: tmp = 0; if (ds1307->regs[DS1307_REG_HOUR] & DS1307_BIT_PM) tmp += 12; - i2c_smbus_write_byte_data(client, - ds1307->offset + DS1307_REG_HOUR, - bin2bcd(tmp)); + regmap_write(ds1307->regmap, ds1307->offset + DS1307_REG_HOUR, + bin2bcd(tmp)); } /* * Some IPs have weekday reset value = 0x1 which might not correct * hence compute the wday using the current date/month/year values */ - ds1307_get_time(&client->dev, &tm); + ds1307_get_time(ds1307->dev, &tm); wday = tm.tm_wday; timestamp = rtc_tm_to_time64(&tm); rtc_time64_to_tm(timestamp, &tm); @@ -1700,51 +1537,53 @@ read_rtc: * timestamp */ if (wday != tm.tm_wday) { - wday = i2c_smbus_read_byte_data(client, MCP794XX_REG_WEEKDAY); + regmap_read(ds1307->regmap, MCP794XX_REG_WEEKDAY, &wday); wday = wday & ~MCP794XX_REG_WEEKDAY_WDAY_MASK; wday = wday | (tm.tm_wday + 1); - i2c_smbus_write_byte_data(client, MCP794XX_REG_WEEKDAY, wday); + regmap_write(ds1307->regmap, MCP794XX_REG_WEEKDAY, wday); } if (want_irq) { - device_set_wakeup_capable(&client->dev, true); + device_set_wakeup_capable(ds1307->dev, true); set_bit(HAS_ALARM, &ds1307->flags); } - ds1307->rtc = devm_rtc_device_register(&client->dev, client->name, + ds1307->rtc = devm_rtc_device_register(ds1307->dev, ds1307->name, rtc_ops, THIS_MODULE); if (IS_ERR(ds1307->rtc)) { return PTR_ERR(ds1307->rtc); } - if (ds1307_can_wakeup_device && ds1307->client->irq <= 0) { + if (ds1307_can_wakeup_device && ds1307->irq <= 0) { /* Disable request for an IRQ */ want_irq = false; - dev_info(&client->dev, "'wakeup-source' is set, request for an IRQ is disabled!\n"); + dev_info(ds1307->dev, + "'wakeup-source' is set, request for an IRQ is disabled!\n"); /* We cannot support UIE mode if we do not have an IRQ line */ ds1307->rtc->uie_unsupported = 1; } if (want_irq) { - err = devm_request_threaded_irq(&client->dev, - client->irq, NULL, irq_handler, + err = devm_request_threaded_irq(ds1307->dev, + ds1307->irq, NULL, irq_handler, IRQF_SHARED | IRQF_ONESHOT, - ds1307->rtc->name, client); + ds1307->rtc->name, ds1307); if (err) { client->irq = 0; - device_set_wakeup_capable(&client->dev, false); + device_set_wakeup_capable(ds1307->dev, false); clear_bit(HAS_ALARM, &ds1307->flags); - dev_err(&client->dev, "unable to request IRQ!\n"); + dev_err(ds1307->dev, "unable to request IRQ!\n"); } else - dev_dbg(&client->dev, "got IRQ %d\n", client->irq); + dev_dbg(ds1307->dev, "got IRQ %d\n", client->irq); } if (chip->nvram_size) { - ds1307->nvram = devm_kzalloc(&client->dev, + ds1307->nvram = devm_kzalloc(ds1307->dev, sizeof(struct bin_attribute), GFP_KERNEL); if (!ds1307->nvram) { - dev_err(&client->dev, "cannot allocate memory for nvram sysfs\n"); + dev_err(ds1307->dev, + "cannot allocate memory for nvram sysfs\n"); } else { ds1307->nvram->attr.name = "nvram"; @@ -1757,15 +1596,15 @@ read_rtc: ds1307->nvram->size = chip->nvram_size; ds1307->nvram_offset = chip->nvram_offset; - err = sysfs_create_bin_file(&client->dev.kobj, + err = sysfs_create_bin_file(&ds1307->dev->kobj, ds1307->nvram); if (err) { - dev_err(&client->dev, + dev_err(ds1307->dev, "unable to create sysfs file: %s\n", ds1307->nvram->attr.name); } else { set_bit(HAS_NVRAM, &ds1307->flags); - dev_info(&client->dev, "%zu bytes nvram\n", + dev_info(ds1307->dev, "%zu bytes nvram\n", ds1307->nvram->size); } } @@ -1785,7 +1624,7 @@ static int ds1307_remove(struct i2c_client *client) struct ds1307 *ds1307 = i2c_get_clientdata(client); if (test_and_clear_bit(HAS_NVRAM, &ds1307->flags)) - sysfs_remove_bin_file(&client->dev.kobj, ds1307->nvram); + sysfs_remove_bin_file(&ds1307->dev->kobj, ds1307->nvram); return 0; } -- cgit v1.2.3-59-g8ed1b From 289d72afddf83440117c35d864bf0c6309c1d011 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 25 Apr 2017 15:57:08 +0530 Subject: thermal: cpu_cooling: Avoid accessing potentially freed structures After the lock is dropped, it is possible that the cpufreq_dev gets freed before we call get_level() and that can cause kernel to crash. Drop the lock after we are done using the structure. Cc: 4.2+ # 4.2+ Fixes: 02373d7c69b4 ("thermal: cpu_cooling: fix lockdep problems in cpu_cooling") Signed-off-by: Viresh Kumar Reviewed-by: Lukasz Luba Tested-by: Lukasz Luba Signed-off-by: Eduardo Valentin --- drivers/thermal/cpu_cooling.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index 69d0f430b2d1..be29489dd247 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -153,8 +153,10 @@ unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq) mutex_lock(&cooling_list_lock); list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) { if (cpumask_test_cpu(cpu, &cpufreq_dev->allowed_cpus)) { + unsigned long level = get_level(cpufreq_dev, freq); + mutex_unlock(&cooling_list_lock); - return get_level(cpufreq_dev, freq); + return level; } } mutex_unlock(&cooling_list_lock); -- cgit v1.2.3-59-g8ed1b From fb8ea3082169612933b5cd14f30415e81f926f7b Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 25 Apr 2017 15:57:09 +0530 Subject: thermal: cpu_cooling: rearrange globals Just to make it look better. Signed-off-by: Viresh Kumar Reviewed-by: Lukasz Luba Tested-by: Lukasz Luba Signed-off-by: Eduardo Valentin --- drivers/thermal/cpu_cooling.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index be29489dd247..ce94aafed25d 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -105,8 +105,8 @@ struct cpufreq_cooling_device { struct device *cpu_dev; get_static_t plat_get_static_power; }; -static DEFINE_IDA(cpufreq_ida); +static DEFINE_IDA(cpufreq_ida); static DEFINE_MUTEX(cooling_list_lock); static LIST_HEAD(cpufreq_dev_list); -- cgit v1.2.3-59-g8ed1b From 1dea432a671aa87068c28194a6a602a6f358f749 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 25 Apr 2017 15:57:10 +0530 Subject: thermal: cpu_cooling: Name cpufreq cooling devices as cpufreq_cdev Objects of "struct cpufreq_cooling_device" are named a bit inconsistently. Lets use cpufreq_cdev everywhere. Also note that the lists containing such devices is renamed similarly too. Signed-off-by: Viresh Kumar Reviewed-by: Lukasz Luba Tested-by: Lukasz Luba Signed-off-by: Eduardo Valentin --- drivers/thermal/cpu_cooling.c | 248 +++++++++++++++++++++--------------------- 1 file changed, 124 insertions(+), 124 deletions(-) diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index ce94aafed25d..80a46a80817b 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -108,27 +108,27 @@ struct cpufreq_cooling_device { static DEFINE_IDA(cpufreq_ida); static DEFINE_MUTEX(cooling_list_lock); -static LIST_HEAD(cpufreq_dev_list); +static LIST_HEAD(cpufreq_cdev_list); /* Below code defines functions to be used for cpufreq as cooling device */ /** * get_level: Find the level for a particular frequency - * @cpufreq_dev: cpufreq_dev for which the property is required + * @cpufreq_cdev: cpufreq_cdev for which the property is required * @freq: Frequency * * Return: level on success, THERMAL_CSTATE_INVALID on error. */ -static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_dev, +static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_cdev, unsigned int freq) { unsigned long level; - for (level = 0; level <= cpufreq_dev->max_level; level++) { - if (freq == cpufreq_dev->freq_table[level]) + for (level = 0; level <= cpufreq_cdev->max_level; level++) { + if (freq == cpufreq_cdev->freq_table[level]) return level; - if (freq > cpufreq_dev->freq_table[level]) + if (freq > cpufreq_cdev->freq_table[level]) break; } @@ -148,12 +148,12 @@ static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_dev, */ unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq) { - struct cpufreq_cooling_device *cpufreq_dev; + struct cpufreq_cooling_device *cpufreq_cdev; mutex_lock(&cooling_list_lock); - list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) { - if (cpumask_test_cpu(cpu, &cpufreq_dev->allowed_cpus)) { - unsigned long level = get_level(cpufreq_dev, freq); + list_for_each_entry(cpufreq_cdev, &cpufreq_cdev_list, node) { + if (cpumask_test_cpu(cpu, &cpufreq_cdev->allowed_cpus)) { + unsigned long level = get_level(cpufreq_cdev, freq); mutex_unlock(&cooling_list_lock); return level; @@ -183,14 +183,14 @@ static int cpufreq_thermal_notifier(struct notifier_block *nb, { struct cpufreq_policy *policy = data; unsigned long clipped_freq; - struct cpufreq_cooling_device *cpufreq_dev; + struct cpufreq_cooling_device *cpufreq_cdev; if (event != CPUFREQ_ADJUST) return NOTIFY_DONE; mutex_lock(&cooling_list_lock); - list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) { - if (!cpumask_test_cpu(policy->cpu, &cpufreq_dev->allowed_cpus)) + list_for_each_entry(cpufreq_cdev, &cpufreq_cdev_list, node) { + if (!cpumask_test_cpu(policy->cpu, &cpufreq_cdev->allowed_cpus)) continue; /* @@ -204,7 +204,7 @@ static int cpufreq_thermal_notifier(struct notifier_block *nb, * But, if clipped_freq is greater than policy->max, we don't * need to do anything. */ - clipped_freq = cpufreq_dev->clipped_freq; + clipped_freq = cpufreq_cdev->clipped_freq; if (policy->max > clipped_freq) cpufreq_verify_within_limits(policy, 0, clipped_freq); @@ -217,11 +217,11 @@ static int cpufreq_thermal_notifier(struct notifier_block *nb, /** * build_dyn_power_table() - create a dynamic power to frequency table - * @cpufreq_device: the cpufreq cooling device in which to store the table + * @cpufreq_cdev: the cpufreq cooling device in which to store the table * @capacitance: dynamic power coefficient for these cpus * * Build a dynamic power to frequency table for this cpu and store it - * in @cpufreq_device. This table will be used in cpu_power_to_freq() and + * in @cpufreq_cdev. This table will be used in cpu_power_to_freq() and * cpu_freq_to_power() to convert between power and frequency * efficiently. Power is stored in mW, frequency in KHz. The * resulting table is in ascending order. @@ -230,7 +230,7 @@ static int cpufreq_thermal_notifier(struct notifier_block *nb, * -ENOMEM if we run out of memory or -EAGAIN if an OPP was * added/enabled while the function was executing. */ -static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device, +static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_cdev, u32 capacitance) { struct power_table *power_table; @@ -239,10 +239,10 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device, int num_opps = 0, cpu, i, ret = 0; unsigned long freq; - for_each_cpu(cpu, &cpufreq_device->allowed_cpus) { + for_each_cpu(cpu, &cpufreq_cdev->allowed_cpus) { dev = get_cpu_device(cpu); if (!dev) { - dev_warn(&cpufreq_device->cool_dev->device, + dev_warn(&cpufreq_cdev->cool_dev->device, "No cpu device for cpu %d\n", cpu); continue; } @@ -295,9 +295,9 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device, goto free_power_table; } - cpufreq_device->cpu_dev = dev; - cpufreq_device->dyn_power_table = power_table; - cpufreq_device->dyn_power_table_entries = i; + cpufreq_cdev->cpu_dev = dev; + cpufreq_cdev->dyn_power_table = power_table; + cpufreq_cdev->dyn_power_table_entries = i; return 0; @@ -307,26 +307,26 @@ free_power_table: return ret; } -static u32 cpu_freq_to_power(struct cpufreq_cooling_device *cpufreq_device, +static u32 cpu_freq_to_power(struct cpufreq_cooling_device *cpufreq_cdev, u32 freq) { int i; - struct power_table *pt = cpufreq_device->dyn_power_table; + struct power_table *pt = cpufreq_cdev->dyn_power_table; - for (i = 1; i < cpufreq_device->dyn_power_table_entries; i++) + for (i = 1; i < cpufreq_cdev->dyn_power_table_entries; i++) if (freq < pt[i].frequency) break; return pt[i - 1].power; } -static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_device, +static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_cdev, u32 power) { int i; - struct power_table *pt = cpufreq_device->dyn_power_table; + struct power_table *pt = cpufreq_cdev->dyn_power_table; - for (i = 1; i < cpufreq_device->dyn_power_table_entries; i++) + for (i = 1; i < cpufreq_cdev->dyn_power_table_entries; i++) if (power < pt[i].power) break; @@ -335,37 +335,37 @@ static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_device, /** * get_load() - get load for a cpu since last updated - * @cpufreq_device: &struct cpufreq_cooling_device for this cpu + * @cpufreq_cdev: &struct cpufreq_cooling_device for this cpu * @cpu: cpu number - * @cpu_idx: index of the cpu in cpufreq_device->allowed_cpus + * @cpu_idx: index of the cpu in cpufreq_cdev->allowed_cpus * * Return: The average load of cpu @cpu in percentage since this * function was last called. */ -static u32 get_load(struct cpufreq_cooling_device *cpufreq_device, int cpu, +static u32 get_load(struct cpufreq_cooling_device *cpufreq_cdev, int cpu, int cpu_idx) { u32 load; u64 now, now_idle, delta_time, delta_idle; now_idle = get_cpu_idle_time(cpu, &now, 0); - delta_idle = now_idle - cpufreq_device->time_in_idle[cpu_idx]; - delta_time = now - cpufreq_device->time_in_idle_timestamp[cpu_idx]; + delta_idle = now_idle - cpufreq_cdev->time_in_idle[cpu_idx]; + delta_time = now - cpufreq_cdev->time_in_idle_timestamp[cpu_idx]; if (delta_time <= delta_idle) load = 0; else load = div64_u64(100 * (delta_time - delta_idle), delta_time); - cpufreq_device->time_in_idle[cpu_idx] = now_idle; - cpufreq_device->time_in_idle_timestamp[cpu_idx] = now; + cpufreq_cdev->time_in_idle[cpu_idx] = now_idle; + cpufreq_cdev->time_in_idle_timestamp[cpu_idx] = now; return load; } /** * get_static_power() - calculate the static power consumed by the cpus - * @cpufreq_device: struct &cpufreq_cooling_device for this cpu cdev + * @cpufreq_cdev: struct &cpufreq_cooling_device for this cpu cdev * @tz: thermal zone device in which we're operating * @freq: frequency in KHz * @power: pointer in which to store the calculated static power @@ -378,25 +378,24 @@ static u32 get_load(struct cpufreq_cooling_device *cpufreq_device, int cpu, * * Return: 0 on success, -E* on failure. */ -static int get_static_power(struct cpufreq_cooling_device *cpufreq_device, +static int get_static_power(struct cpufreq_cooling_device *cpufreq_cdev, struct thermal_zone_device *tz, unsigned long freq, u32 *power) { struct dev_pm_opp *opp; unsigned long voltage; - struct cpumask *cpumask = &cpufreq_device->allowed_cpus; + struct cpumask *cpumask = &cpufreq_cdev->allowed_cpus; unsigned long freq_hz = freq * 1000; - if (!cpufreq_device->plat_get_static_power || - !cpufreq_device->cpu_dev) { + if (!cpufreq_cdev->plat_get_static_power || !cpufreq_cdev->cpu_dev) { *power = 0; return 0; } - opp = dev_pm_opp_find_freq_exact(cpufreq_device->cpu_dev, freq_hz, + opp = dev_pm_opp_find_freq_exact(cpufreq_cdev->cpu_dev, freq_hz, true); if (IS_ERR(opp)) { - dev_warn_ratelimited(cpufreq_device->cpu_dev, + dev_warn_ratelimited(cpufreq_cdev->cpu_dev, "Failed to find OPP for frequency %lu: %ld\n", freq_hz, PTR_ERR(opp)); return -EINVAL; @@ -406,31 +405,31 @@ static int get_static_power(struct cpufreq_cooling_device *cpufreq_device, dev_pm_opp_put(opp); if (voltage == 0) { - dev_err_ratelimited(cpufreq_device->cpu_dev, + dev_err_ratelimited(cpufreq_cdev->cpu_dev, "Failed to get voltage for frequency %lu\n", freq_hz); return -EINVAL; } - return cpufreq_device->plat_get_static_power(cpumask, tz->passive_delay, - voltage, power); + return cpufreq_cdev->plat_get_static_power(cpumask, tz->passive_delay, + voltage, power); } /** * get_dynamic_power() - calculate the dynamic power - * @cpufreq_device: &cpufreq_cooling_device for this cdev + * @cpufreq_cdev: &cpufreq_cooling_device for this cdev * @freq: current frequency * * Return: the dynamic power consumed by the cpus described by - * @cpufreq_device. + * @cpufreq_cdev. */ -static u32 get_dynamic_power(struct cpufreq_cooling_device *cpufreq_device, +static u32 get_dynamic_power(struct cpufreq_cooling_device *cpufreq_cdev, unsigned long freq) { u32 raw_cpu_power; - raw_cpu_power = cpu_freq_to_power(cpufreq_device, freq); - return (raw_cpu_power * cpufreq_device->last_load) / 100; + raw_cpu_power = cpu_freq_to_power(cpufreq_cdev, freq); + return (raw_cpu_power * cpufreq_cdev->last_load) / 100; } /* cpufreq cooling device callback functions are defined below */ @@ -448,9 +447,9 @@ static u32 get_dynamic_power(struct cpufreq_cooling_device *cpufreq_device, static int cpufreq_get_max_state(struct thermal_cooling_device *cdev, unsigned long *state) { - struct cpufreq_cooling_device *cpufreq_device = cdev->devdata; + struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata; - *state = cpufreq_device->max_level; + *state = cpufreq_cdev->max_level; return 0; } @@ -467,9 +466,9 @@ static int cpufreq_get_max_state(struct thermal_cooling_device *cdev, static int cpufreq_get_cur_state(struct thermal_cooling_device *cdev, unsigned long *state) { - struct cpufreq_cooling_device *cpufreq_device = cdev->devdata; + struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata; - *state = cpufreq_device->cpufreq_state; + *state = cpufreq_cdev->cpufreq_state; return 0; } @@ -487,21 +486,21 @@ static int cpufreq_get_cur_state(struct thermal_cooling_device *cdev, static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev, unsigned long state) { - struct cpufreq_cooling_device *cpufreq_device = cdev->devdata; - unsigned int cpu = cpumask_any(&cpufreq_device->allowed_cpus); + struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata; + unsigned int cpu = cpumask_any(&cpufreq_cdev->allowed_cpus); unsigned int clip_freq; /* Request state should be less than max_level */ - if (WARN_ON(state > cpufreq_device->max_level)) + if (WARN_ON(state > cpufreq_cdev->max_level)) return -EINVAL; /* Check if the old cooling action is same as new cooling action */ - if (cpufreq_device->cpufreq_state == state) + if (cpufreq_cdev->cpufreq_state == state) return 0; - clip_freq = cpufreq_device->freq_table[state]; - cpufreq_device->cpufreq_state = state; - cpufreq_device->clipped_freq = clip_freq; + clip_freq = cpufreq_cdev->freq_table[state]; + cpufreq_cdev->cpufreq_state = state; + cpufreq_cdev->clipped_freq = clip_freq; cpufreq_update_policy(cpu); @@ -538,10 +537,10 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev, unsigned long freq; int i = 0, cpu, ret; u32 static_power, dynamic_power, total_load = 0; - struct cpufreq_cooling_device *cpufreq_device = cdev->devdata; + struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata; u32 *load_cpu = NULL; - cpu = cpumask_any_and(&cpufreq_device->allowed_cpus, cpu_online_mask); + cpu = cpumask_any_and(&cpufreq_cdev->allowed_cpus, cpu_online_mask); /* * All the CPUs are offline, thus the requested power by @@ -555,16 +554,16 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev, freq = cpufreq_quick_get(cpu); if (trace_thermal_power_cpu_get_power_enabled()) { - u32 ncpus = cpumask_weight(&cpufreq_device->allowed_cpus); + u32 ncpus = cpumask_weight(&cpufreq_cdev->allowed_cpus); load_cpu = kcalloc(ncpus, sizeof(*load_cpu), GFP_KERNEL); } - for_each_cpu(cpu, &cpufreq_device->allowed_cpus) { + for_each_cpu(cpu, &cpufreq_cdev->allowed_cpus) { u32 load; if (cpu_online(cpu)) - load = get_load(cpufreq_device, cpu, i); + load = get_load(cpufreq_cdev, cpu, i); else load = 0; @@ -575,10 +574,10 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev, i++; } - cpufreq_device->last_load = total_load; + cpufreq_cdev->last_load = total_load; - dynamic_power = get_dynamic_power(cpufreq_device, freq); - ret = get_static_power(cpufreq_device, tz, freq, &static_power); + dynamic_power = get_dynamic_power(cpufreq_cdev, freq); + ret = get_static_power(cpufreq_cdev, tz, freq, &static_power); if (ret) { kfree(load_cpu); return ret; @@ -586,7 +585,7 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev, if (load_cpu) { trace_thermal_power_cpu_get_power( - &cpufreq_device->allowed_cpus, + &cpufreq_cdev->allowed_cpus, freq, load_cpu, i, dynamic_power, static_power); kfree(load_cpu); @@ -619,12 +618,12 @@ static int cpufreq_state2power(struct thermal_cooling_device *cdev, cpumask_var_t cpumask; u32 static_power, dynamic_power; int ret; - struct cpufreq_cooling_device *cpufreq_device = cdev->devdata; + struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata; if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) return -ENOMEM; - cpumask_and(cpumask, &cpufreq_device->allowed_cpus, cpu_online_mask); + cpumask_and(cpumask, &cpufreq_cdev->allowed_cpus, cpu_online_mask); num_cpus = cpumask_weight(cpumask); /* None of our cpus are online, so no power */ @@ -634,14 +633,14 @@ static int cpufreq_state2power(struct thermal_cooling_device *cdev, goto out; } - freq = cpufreq_device->freq_table[state]; + freq = cpufreq_cdev->freq_table[state]; if (!freq) { ret = -EINVAL; goto out; } - dynamic_power = cpu_freq_to_power(cpufreq_device, freq) * num_cpus; - ret = get_static_power(cpufreq_device, tz, freq, &static_power); + dynamic_power = cpu_freq_to_power(cpufreq_cdev, freq) * num_cpus; + ret = get_static_power(cpufreq_cdev, tz, freq, &static_power); if (ret) goto out; @@ -679,24 +678,24 @@ static int cpufreq_power2state(struct thermal_cooling_device *cdev, int ret; s32 dyn_power; u32 last_load, normalised_power, static_power; - struct cpufreq_cooling_device *cpufreq_device = cdev->devdata; + struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata; - cpu = cpumask_any_and(&cpufreq_device->allowed_cpus, cpu_online_mask); + cpu = cpumask_any_and(&cpufreq_cdev->allowed_cpus, cpu_online_mask); /* None of our cpus are online */ if (cpu >= nr_cpu_ids) return -ENODEV; cur_freq = cpufreq_quick_get(cpu); - ret = get_static_power(cpufreq_device, tz, cur_freq, &static_power); + ret = get_static_power(cpufreq_cdev, tz, cur_freq, &static_power); if (ret) return ret; dyn_power = power - static_power; dyn_power = dyn_power > 0 ? dyn_power : 0; - last_load = cpufreq_device->last_load ?: 1; + last_load = cpufreq_cdev->last_load ?: 1; normalised_power = (dyn_power * 100) / last_load; - target_freq = cpu_power_to_freq(cpufreq_device, normalised_power); + target_freq = cpu_power_to_freq(cpufreq_cdev, normalised_power); *state = cpufreq_cooling_get_level(cpu, target_freq); if (*state == THERMAL_CSTATE_INVALID) { @@ -706,7 +705,7 @@ static int cpufreq_power2state(struct thermal_cooling_device *cdev, return -EINVAL; } - trace_thermal_power_cpu_limit(&cpufreq_device->allowed_cpus, + trace_thermal_power_cpu_limit(&cpufreq_cdev->allowed_cpus, target_freq, *state, power); return 0; } @@ -771,7 +770,7 @@ __cpufreq_cooling_register(struct device_node *np, { struct cpufreq_policy *policy; struct thermal_cooling_device *cool_dev; - struct cpufreq_cooling_device *cpufreq_dev; + struct cpufreq_cooling_device *cpufreq_cdev; char dev_name[THERMAL_NAME_LENGTH]; struct cpufreq_frequency_table *pos, *table; cpumask_var_t temp_mask; @@ -798,49 +797,49 @@ __cpufreq_cooling_register(struct device_node *np, goto put_policy; } - cpufreq_dev = kzalloc(sizeof(*cpufreq_dev), GFP_KERNEL); - if (!cpufreq_dev) { + cpufreq_cdev = kzalloc(sizeof(*cpufreq_cdev), GFP_KERNEL); + if (!cpufreq_cdev) { cool_dev = ERR_PTR(-ENOMEM); goto put_policy; } num_cpus = cpumask_weight(clip_cpus); - cpufreq_dev->time_in_idle = kcalloc(num_cpus, - sizeof(*cpufreq_dev->time_in_idle), + cpufreq_cdev->time_in_idle = kcalloc(num_cpus, + sizeof(*cpufreq_cdev->time_in_idle), GFP_KERNEL); - if (!cpufreq_dev->time_in_idle) { + if (!cpufreq_cdev->time_in_idle) { cool_dev = ERR_PTR(-ENOMEM); goto free_cdev; } - cpufreq_dev->time_in_idle_timestamp = - kcalloc(num_cpus, sizeof(*cpufreq_dev->time_in_idle_timestamp), + cpufreq_cdev->time_in_idle_timestamp = + kcalloc(num_cpus, sizeof(*cpufreq_cdev->time_in_idle_timestamp), GFP_KERNEL); - if (!cpufreq_dev->time_in_idle_timestamp) { + if (!cpufreq_cdev->time_in_idle_timestamp) { cool_dev = ERR_PTR(-ENOMEM); goto free_time_in_idle; } /* Find max levels */ cpufreq_for_each_valid_entry(pos, table) - cpufreq_dev->max_level++; + cpufreq_cdev->max_level++; - cpufreq_dev->freq_table = kmalloc(sizeof(*cpufreq_dev->freq_table) * - cpufreq_dev->max_level, GFP_KERNEL); - if (!cpufreq_dev->freq_table) { + cpufreq_cdev->freq_table = kmalloc(sizeof(*cpufreq_cdev->freq_table) * + cpufreq_cdev->max_level, GFP_KERNEL); + if (!cpufreq_cdev->freq_table) { cool_dev = ERR_PTR(-ENOMEM); goto free_time_in_idle_timestamp; } /* max_level is an index, not a counter */ - cpufreq_dev->max_level--; + cpufreq_cdev->max_level--; - cpumask_copy(&cpufreq_dev->allowed_cpus, clip_cpus); + cpumask_copy(&cpufreq_cdev->allowed_cpus, clip_cpus); if (capacitance) { - cpufreq_dev->plat_get_static_power = plat_static_func; + cpufreq_cdev->plat_get_static_power = plat_static_func; - ret = build_dyn_power_table(cpufreq_dev, capacitance); + ret = build_dyn_power_table(cpufreq_cdev, capacitance); if (ret) { cool_dev = ERR_PTR(ret); goto free_table; @@ -856,12 +855,12 @@ __cpufreq_cooling_register(struct device_node *np, cool_dev = ERR_PTR(ret); goto free_power_table; } - cpufreq_dev->id = ret; + cpufreq_cdev->id = ret; /* Fill freq-table in descending order of frequencies */ - for (i = 0, freq = -1; i <= cpufreq_dev->max_level; i++) { + for (i = 0, freq = -1; i <= cpufreq_cdev->max_level; i++) { freq = find_next_max(table, freq); - cpufreq_dev->freq_table[i] = freq; + cpufreq_cdev->freq_table[i] = freq; /* Warn for duplicate entries */ if (!freq) @@ -871,20 +870,21 @@ __cpufreq_cooling_register(struct device_node *np, } snprintf(dev_name, sizeof(dev_name), "thermal-cpufreq-%d", - cpufreq_dev->id); + cpufreq_cdev->id); - cool_dev = thermal_of_cooling_device_register(np, dev_name, cpufreq_dev, + cool_dev = thermal_of_cooling_device_register(np, dev_name, + cpufreq_cdev, cooling_ops); if (IS_ERR(cool_dev)) goto remove_ida; - cpufreq_dev->clipped_freq = cpufreq_dev->freq_table[0]; - cpufreq_dev->cool_dev = cool_dev; + cpufreq_cdev->clipped_freq = cpufreq_cdev->freq_table[0]; + cpufreq_cdev->cool_dev = cool_dev; mutex_lock(&cooling_list_lock); /* Register the notifier for first cpufreq cooling device */ - first = list_empty(&cpufreq_dev_list); - list_add(&cpufreq_dev->node, &cpufreq_dev_list); + first = list_empty(&cpufreq_cdev_list); + list_add(&cpufreq_cdev->node, &cpufreq_cdev_list); mutex_unlock(&cooling_list_lock); if (first) @@ -894,17 +894,17 @@ __cpufreq_cooling_register(struct device_node *np, goto put_policy; remove_ida: - ida_simple_remove(&cpufreq_ida, cpufreq_dev->id); + ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id); free_power_table: - kfree(cpufreq_dev->dyn_power_table); + kfree(cpufreq_cdev->dyn_power_table); free_table: - kfree(cpufreq_dev->freq_table); + kfree(cpufreq_cdev->freq_table); free_time_in_idle_timestamp: - kfree(cpufreq_dev->time_in_idle_timestamp); + kfree(cpufreq_cdev->time_in_idle_timestamp); free_time_in_idle: - kfree(cpufreq_dev->time_in_idle); + kfree(cpufreq_cdev->time_in_idle); free_cdev: - kfree(cpufreq_dev); + kfree(cpufreq_cdev); put_policy: cpufreq_cpu_put(policy); free_cpumask: @@ -1029,30 +1029,30 @@ EXPORT_SYMBOL(of_cpufreq_power_cooling_register); */ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev) { - struct cpufreq_cooling_device *cpufreq_dev; + struct cpufreq_cooling_device *cpufreq_cdev; bool last; if (!cdev) return; - cpufreq_dev = cdev->devdata; + cpufreq_cdev = cdev->devdata; mutex_lock(&cooling_list_lock); - list_del(&cpufreq_dev->node); + list_del(&cpufreq_cdev->node); /* Unregister the notifier for the last cpufreq cooling device */ - last = list_empty(&cpufreq_dev_list); + last = list_empty(&cpufreq_cdev_list); mutex_unlock(&cooling_list_lock); if (last) cpufreq_unregister_notifier(&thermal_cpufreq_notifier_block, CPUFREQ_POLICY_NOTIFIER); - thermal_cooling_device_unregister(cpufreq_dev->cool_dev); - ida_simple_remove(&cpufreq_ida, cpufreq_dev->id); - kfree(cpufreq_dev->dyn_power_table); - kfree(cpufreq_dev->time_in_idle_timestamp); - kfree(cpufreq_dev->time_in_idle); - kfree(cpufreq_dev->freq_table); - kfree(cpufreq_dev); + thermal_cooling_device_unregister(cpufreq_cdev->cool_dev); + ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id); + kfree(cpufreq_cdev->dyn_power_table); + kfree(cpufreq_cdev->time_in_idle_timestamp); + kfree(cpufreq_cdev->time_in_idle); + kfree(cpufreq_cdev->freq_table); + kfree(cpufreq_cdev); } EXPORT_SYMBOL_GPL(cpufreq_cooling_unregister); -- cgit v1.2.3-59-g8ed1b From 04bdbdf93cedc728ceff6af175fcce2bedfdd25f Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 25 Apr 2017 15:57:11 +0530 Subject: thermal: cpu_cooling: replace cool_dev with cdev Objects of "struct thermal_cooling_device" are named a bit inconsistently. Lets use cdev everywhere. Signed-off-by: Viresh Kumar Reviewed-by: Lukasz Luba Tested-by: Lukasz Luba Signed-off-by: Eduardo Valentin --- drivers/thermal/cpu_cooling.c | 37 ++++++++++++++++++------------------- 1 file changed, 18 insertions(+), 19 deletions(-) diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index 80a46a80817b..f1e784c22c5a 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -65,7 +65,7 @@ struct power_table { * struct cpufreq_cooling_device - data for cooling device with cpufreq * @id: unique integer value corresponding to each cpufreq_cooling_device * registered. - * @cool_dev: thermal_cooling_device pointer to keep track of the + * @cdev: thermal_cooling_device pointer to keep track of the * registered cooling device. * @cpufreq_state: integer value representing the current state of cpufreq * cooling devices. @@ -90,7 +90,7 @@ struct power_table { */ struct cpufreq_cooling_device { int id; - struct thermal_cooling_device *cool_dev; + struct thermal_cooling_device *cdev; unsigned int cpufreq_state; unsigned int clipped_freq; unsigned int max_level; @@ -242,7 +242,7 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_cdev, for_each_cpu(cpu, &cpufreq_cdev->allowed_cpus) { dev = get_cpu_device(cpu); if (!dev) { - dev_warn(&cpufreq_cdev->cool_dev->device, + dev_warn(&cpufreq_cdev->cdev->device, "No cpu device for cpu %d\n", cpu); continue; } @@ -769,7 +769,7 @@ __cpufreq_cooling_register(struct device_node *np, get_static_t plat_static_func) { struct cpufreq_policy *policy; - struct thermal_cooling_device *cool_dev; + struct thermal_cooling_device *cdev; struct cpufreq_cooling_device *cpufreq_cdev; char dev_name[THERMAL_NAME_LENGTH]; struct cpufreq_frequency_table *pos, *table; @@ -786,20 +786,20 @@ __cpufreq_cooling_register(struct device_node *np, policy = cpufreq_cpu_get(cpumask_first(temp_mask)); if (!policy) { pr_debug("%s: CPUFreq policy not found\n", __func__); - cool_dev = ERR_PTR(-EPROBE_DEFER); + cdev = ERR_PTR(-EPROBE_DEFER); goto free_cpumask; } table = policy->freq_table; if (!table) { pr_debug("%s: CPUFreq table not found\n", __func__); - cool_dev = ERR_PTR(-ENODEV); + cdev = ERR_PTR(-ENODEV); goto put_policy; } cpufreq_cdev = kzalloc(sizeof(*cpufreq_cdev), GFP_KERNEL); if (!cpufreq_cdev) { - cool_dev = ERR_PTR(-ENOMEM); + cdev = ERR_PTR(-ENOMEM); goto put_policy; } @@ -808,7 +808,7 @@ __cpufreq_cooling_register(struct device_node *np, sizeof(*cpufreq_cdev->time_in_idle), GFP_KERNEL); if (!cpufreq_cdev->time_in_idle) { - cool_dev = ERR_PTR(-ENOMEM); + cdev = ERR_PTR(-ENOMEM); goto free_cdev; } @@ -816,7 +816,7 @@ __cpufreq_cooling_register(struct device_node *np, kcalloc(num_cpus, sizeof(*cpufreq_cdev->time_in_idle_timestamp), GFP_KERNEL); if (!cpufreq_cdev->time_in_idle_timestamp) { - cool_dev = ERR_PTR(-ENOMEM); + cdev = ERR_PTR(-ENOMEM); goto free_time_in_idle; } @@ -827,7 +827,7 @@ __cpufreq_cooling_register(struct device_node *np, cpufreq_cdev->freq_table = kmalloc(sizeof(*cpufreq_cdev->freq_table) * cpufreq_cdev->max_level, GFP_KERNEL); if (!cpufreq_cdev->freq_table) { - cool_dev = ERR_PTR(-ENOMEM); + cdev = ERR_PTR(-ENOMEM); goto free_time_in_idle_timestamp; } @@ -841,7 +841,7 @@ __cpufreq_cooling_register(struct device_node *np, ret = build_dyn_power_table(cpufreq_cdev, capacitance); if (ret) { - cool_dev = ERR_PTR(ret); + cdev = ERR_PTR(ret); goto free_table; } @@ -852,7 +852,7 @@ __cpufreq_cooling_register(struct device_node *np, ret = ida_simple_get(&cpufreq_ida, 0, 0, GFP_KERNEL); if (ret < 0) { - cool_dev = ERR_PTR(ret); + cdev = ERR_PTR(ret); goto free_power_table; } cpufreq_cdev->id = ret; @@ -872,14 +872,13 @@ __cpufreq_cooling_register(struct device_node *np, snprintf(dev_name, sizeof(dev_name), "thermal-cpufreq-%d", cpufreq_cdev->id); - cool_dev = thermal_of_cooling_device_register(np, dev_name, - cpufreq_cdev, - cooling_ops); - if (IS_ERR(cool_dev)) + cdev = thermal_of_cooling_device_register(np, dev_name, cpufreq_cdev, + cooling_ops); + if (IS_ERR(cdev)) goto remove_ida; cpufreq_cdev->clipped_freq = cpufreq_cdev->freq_table[0]; - cpufreq_cdev->cool_dev = cool_dev; + cpufreq_cdev->cdev = cdev; mutex_lock(&cooling_list_lock); /* Register the notifier for first cpufreq cooling device */ @@ -909,7 +908,7 @@ put_policy: cpufreq_cpu_put(policy); free_cpumask: free_cpumask_var(temp_mask); - return cool_dev; + return cdev; } /** @@ -1047,7 +1046,7 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev) cpufreq_unregister_notifier(&thermal_cpufreq_notifier_block, CPUFREQ_POLICY_NOTIFIER); - thermal_cooling_device_unregister(cpufreq_cdev->cool_dev); + thermal_cooling_device_unregister(cpufreq_cdev->cdev); ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id); kfree(cpufreq_cdev->dyn_power_table); kfree(cpufreq_cdev->time_in_idle_timestamp); -- cgit v1.2.3-59-g8ed1b From 3e08b2df12983159ea2d9a1aa2b2bc601093b3cb Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 25 Apr 2017 15:57:12 +0530 Subject: thermal: cpu_cooling: remove cpufreq_cooling_get_level() There is only one user of cpufreq_cooling_get_level() and that already has pointer to the cpufreq_cdev structure. It can directly call get_level() instead and we can get rid of cpufreq_cooling_get_level(). Signed-off-by: Viresh Kumar Reviewed-by: Lukasz Luba Tested-by: Lukasz Luba Signed-off-by: Eduardo Valentin --- drivers/thermal/cpu_cooling.c | 33 +-------------------------------- include/linux/cpu_cooling.h | 6 ------ 2 files changed, 1 insertion(+), 38 deletions(-) diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index f1e784c22c5a..1f4b6a719d05 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -135,37 +135,6 @@ static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_cdev, return THERMAL_CSTATE_INVALID; } -/** - * cpufreq_cooling_get_level - for a given cpu, return the cooling level. - * @cpu: cpu for which the level is required - * @freq: the frequency of interest - * - * This function will match the cooling level corresponding to the - * requested @freq and return it. - * - * Return: The matched cooling level on success or THERMAL_CSTATE_INVALID - * otherwise. - */ -unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq) -{ - struct cpufreq_cooling_device *cpufreq_cdev; - - mutex_lock(&cooling_list_lock); - list_for_each_entry(cpufreq_cdev, &cpufreq_cdev_list, node) { - if (cpumask_test_cpu(cpu, &cpufreq_cdev->allowed_cpus)) { - unsigned long level = get_level(cpufreq_cdev, freq); - - mutex_unlock(&cooling_list_lock); - return level; - } - } - mutex_unlock(&cooling_list_lock); - - pr_err("%s: cpu:%d not part of any cooling device\n", __func__, cpu); - return THERMAL_CSTATE_INVALID; -} -EXPORT_SYMBOL_GPL(cpufreq_cooling_get_level); - /** * cpufreq_thermal_notifier - notifier callback for cpufreq policy change. * @nb: struct notifier_block * with callback info. @@ -697,7 +666,7 @@ static int cpufreq_power2state(struct thermal_cooling_device *cdev, normalised_power = (dyn_power * 100) / last_load; target_freq = cpu_power_to_freq(cpufreq_cdev, normalised_power); - *state = cpufreq_cooling_get_level(cpu, target_freq); + *state = get_level(cpufreq_cdev, target_freq); if (*state == THERMAL_CSTATE_INVALID) { dev_err_ratelimited(&cdev->device, "Failed to convert %dKHz for cpu %d into a cdev state\n", diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index c156f5082758..96c5e4c2f9c8 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -82,7 +82,6 @@ of_cpufreq_power_cooling_register(struct device_node *np, */ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev); -unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq); #else /* !CONFIG_CPU_THERMAL */ static inline struct thermal_cooling_device * cpufreq_cooling_register(const struct cpumask *clip_cpus) @@ -117,11 +116,6 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev) { return; } -static inline -unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq) -{ - return THERMAL_CSTATE_INVALID; -} #endif /* CONFIG_CPU_THERMAL */ #endif /* __CPU_COOLING_H__ */ -- cgit v1.2.3-59-g8ed1b From 18f301c934db0f7bae4e7c12e941bce11d67aec5 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 25 Apr 2017 15:57:13 +0530 Subject: thermal: cpu_cooling: get rid of a variable in cpufreq_set_cur_state() 'cpu' is used at only one place and there is no need to keep a separate variable for it. Signed-off-by: Viresh Kumar Reviewed-by: Lukasz Luba Tested-by: Lukasz Luba Signed-off-by: Eduardo Valentin --- drivers/thermal/cpu_cooling.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index 1f4b6a719d05..002b48dc6bea 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -456,7 +456,6 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev, unsigned long state) { struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata; - unsigned int cpu = cpumask_any(&cpufreq_cdev->allowed_cpus); unsigned int clip_freq; /* Request state should be less than max_level */ @@ -471,7 +470,7 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev, cpufreq_cdev->cpufreq_state = state; cpufreq_cdev->clipped_freq = clip_freq; - cpufreq_update_policy(cpu); + cpufreq_update_policy(cpumask_any(&cpufreq_cdev->allowed_cpus)); return 0; } -- cgit v1.2.3-59-g8ed1b From 4d753aa7b6279e4b7d338947a434689962f430d1 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 25 Apr 2017 15:57:14 +0530 Subject: thermal: cpu_cooling: use cpufreq_policy to register cooling device The CPU cooling driver uses the cpufreq policy, to get clip_cpus, the frequency table, etc. Most of the callers of CPU cooling driver's registration routines have the cpufreq policy with them, but they only pass the policy->related_cpus cpumask. The __cpufreq_cooling_register() routine then gets the policy by itself and uses it. It would be much better if the callers can pass the policy instead directly. This also fixes a basic design flaw, where the policy can be freed while the CPU cooling driver is still active. Signed-off-by: Viresh Kumar Reviewed-by: Lukasz Luba Tested-by: Lukasz Luba Signed-off-by: Eduardo Valentin --- drivers/cpufreq/arm_big_little.c | 2 +- drivers/cpufreq/cpufreq-dt.c | 2 +- drivers/cpufreq/dbx500-cpufreq.c | 2 +- drivers/cpufreq/mt8173-cpufreq.c | 4 +- drivers/cpufreq/qoriq-cpufreq.c | 3 +- drivers/thermal/cpu_cooling.c | 61 ++++++++-------------- drivers/thermal/imx_thermal.c | 22 ++++++-- drivers/thermal/ti-soc-thermal/ti-thermal-common.c | 22 +++++--- include/linux/cpu_cooling.h | 26 ++++----- 9 files changed, 74 insertions(+), 70 deletions(-) diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c index 418042201e6d..ea6d62547b10 100644 --- a/drivers/cpufreq/arm_big_little.c +++ b/drivers/cpufreq/arm_big_little.c @@ -540,7 +540,7 @@ static void bL_cpufreq_ready(struct cpufreq_policy *policy) &power_coefficient); cdev[cur_cluster] = of_cpufreq_power_cooling_register(np, - policy->related_cpus, power_coefficient, NULL); + policy, power_coefficient, NULL); if (IS_ERR(cdev[cur_cluster])) { dev_err(cpu_dev, "running cpufreq without cooling device: %ld\n", diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index c943787d761e..fef3c2160691 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -326,7 +326,7 @@ static void cpufreq_ready(struct cpufreq_policy *policy) &power_coefficient); priv->cdev = of_cpufreq_power_cooling_register(np, - policy->related_cpus, power_coefficient, NULL); + policy, power_coefficient, NULL); if (IS_ERR(priv->cdev)) { dev_err(priv->cpu_dev, "running cpufreq without cooling device: %ld\n", diff --git a/drivers/cpufreq/dbx500-cpufreq.c b/drivers/cpufreq/dbx500-cpufreq.c index 3575b82210ba..4ee0431579c1 100644 --- a/drivers/cpufreq/dbx500-cpufreq.c +++ b/drivers/cpufreq/dbx500-cpufreq.c @@ -43,7 +43,7 @@ static int dbx500_cpufreq_exit(struct cpufreq_policy *policy) static void dbx500_cpufreq_ready(struct cpufreq_policy *policy) { - cdev = cpufreq_cooling_register(policy->cpus); + cdev = cpufreq_cooling_register(policy); if (IS_ERR(cdev)) pr_err("Failed to register cooling device %ld\n", PTR_ERR(cdev)); else diff --git a/drivers/cpufreq/mt8173-cpufreq.c b/drivers/cpufreq/mt8173-cpufreq.c index fd1886faf33a..f9f00fb4bc3a 100644 --- a/drivers/cpufreq/mt8173-cpufreq.c +++ b/drivers/cpufreq/mt8173-cpufreq.c @@ -320,9 +320,7 @@ static void mtk_cpufreq_ready(struct cpufreq_policy *policy) of_property_read_u32(np, DYNAMIC_POWER, &capacitance); info->cdev = of_cpufreq_power_cooling_register(np, - policy->related_cpus, - capacitance, - NULL); + policy, capacitance, NULL); if (IS_ERR(info->cdev)) { dev_err(info->cpu_dev, diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c index e2ea433a5f9c..4ada55b8856e 100644 --- a/drivers/cpufreq/qoriq-cpufreq.c +++ b/drivers/cpufreq/qoriq-cpufreq.c @@ -278,8 +278,7 @@ static void qoriq_cpufreq_ready(struct cpufreq_policy *policy) struct device_node *np = of_get_cpu_node(policy->cpu, NULL); if (of_find_property(np, "#cooling-cells", NULL)) { - cpud->cdev = of_cpufreq_cooling_register(np, - policy->related_cpus); + cpud->cdev = of_cpufreq_cooling_register(np, policy); if (IS_ERR(cpud->cdev) && PTR_ERR(cpud->cdev) != -ENOSYS) { pr_err("cpu%d is not running as cooling device: %ld\n", diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index 002b48dc6bea..58e58065b650 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -717,7 +717,7 @@ static unsigned int find_next_max(struct cpufreq_frequency_table *table, /** * __cpufreq_cooling_register - helper function to create cpufreq cooling device * @np: a valid struct device_node to the cooling device device tree node - * @clip_cpus: cpumask of cpus where the frequency constraints will happen. + * @policy: cpufreq policy * Normally this should be same as cpufreq policy->related_cpus. * @capacitance: dynamic power coefficient for these cpus * @plat_static_func: function to calculate the static power consumed by these @@ -733,45 +733,34 @@ static unsigned int find_next_max(struct cpufreq_frequency_table *table, */ static struct thermal_cooling_device * __cpufreq_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus, u32 capacitance, + struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func) { - struct cpufreq_policy *policy; struct thermal_cooling_device *cdev; struct cpufreq_cooling_device *cpufreq_cdev; char dev_name[THERMAL_NAME_LENGTH]; struct cpufreq_frequency_table *pos, *table; - cpumask_var_t temp_mask; unsigned int freq, i, num_cpus; int ret; struct thermal_cooling_device_ops *cooling_ops; bool first; - if (!alloc_cpumask_var(&temp_mask, GFP_KERNEL)) - return ERR_PTR(-ENOMEM); - - cpumask_and(temp_mask, clip_cpus, cpu_online_mask); - policy = cpufreq_cpu_get(cpumask_first(temp_mask)); - if (!policy) { - pr_debug("%s: CPUFreq policy not found\n", __func__); - cdev = ERR_PTR(-EPROBE_DEFER); - goto free_cpumask; + if (IS_ERR_OR_NULL(policy)) { + pr_err("%s: cpufreq policy isn't valid: %p", __func__, policy); + return ERR_PTR(-EINVAL); } table = policy->freq_table; if (!table) { pr_debug("%s: CPUFreq table not found\n", __func__); - cdev = ERR_PTR(-ENODEV); - goto put_policy; + return ERR_PTR(-ENODEV); } cpufreq_cdev = kzalloc(sizeof(*cpufreq_cdev), GFP_KERNEL); - if (!cpufreq_cdev) { - cdev = ERR_PTR(-ENOMEM); - goto put_policy; - } + if (!cpufreq_cdev) + return ERR_PTR(-ENOMEM); - num_cpus = cpumask_weight(clip_cpus); + num_cpus = cpumask_weight(policy->related_cpus); cpufreq_cdev->time_in_idle = kcalloc(num_cpus, sizeof(*cpufreq_cdev->time_in_idle), GFP_KERNEL); @@ -802,7 +791,7 @@ __cpufreq_cooling_register(struct device_node *np, /* max_level is an index, not a counter */ cpufreq_cdev->max_level--; - cpumask_copy(&cpufreq_cdev->allowed_cpus, clip_cpus); + cpumask_copy(&cpufreq_cdev->allowed_cpus, policy->related_cpus); if (capacitance) { cpufreq_cdev->plat_get_static_power = plat_static_func; @@ -858,7 +847,7 @@ __cpufreq_cooling_register(struct device_node *np, cpufreq_register_notifier(&thermal_cpufreq_notifier_block, CPUFREQ_POLICY_NOTIFIER); - goto put_policy; + return cdev; remove_ida: ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id); @@ -872,16 +861,12 @@ free_time_in_idle: kfree(cpufreq_cdev->time_in_idle); free_cdev: kfree(cpufreq_cdev); -put_policy: - cpufreq_cpu_put(policy); -free_cpumask: - free_cpumask_var(temp_mask); return cdev; } /** * cpufreq_cooling_register - function to create cpufreq cooling device. - * @clip_cpus: cpumask of cpus where the frequency constraints will happen. + * @policy: cpufreq policy * * This interface function registers the cpufreq cooling device with the name * "thermal-cpufreq-%x". This api can support multiple instances of cpufreq @@ -891,16 +876,16 @@ free_cpumask: * on failure, it returns a corresponding ERR_PTR(). */ struct thermal_cooling_device * -cpufreq_cooling_register(const struct cpumask *clip_cpus) +cpufreq_cooling_register(struct cpufreq_policy *policy) { - return __cpufreq_cooling_register(NULL, clip_cpus, 0, NULL); + return __cpufreq_cooling_register(NULL, policy, 0, NULL); } EXPORT_SYMBOL_GPL(cpufreq_cooling_register); /** * of_cpufreq_cooling_register - function to create cpufreq cooling device. * @np: a valid struct device_node to the cooling device device tree node - * @clip_cpus: cpumask of cpus where the frequency constraints will happen. + * @policy: cpufreq policy * * This interface function registers the cpufreq cooling device with the name * "thermal-cpufreq-%x". This api can support multiple instances of cpufreq @@ -912,18 +897,18 @@ EXPORT_SYMBOL_GPL(cpufreq_cooling_register); */ struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus) + struct cpufreq_policy *policy) { if (!np) return ERR_PTR(-EINVAL); - return __cpufreq_cooling_register(np, clip_cpus, 0, NULL); + return __cpufreq_cooling_register(np, policy, 0, NULL); } EXPORT_SYMBOL_GPL(of_cpufreq_cooling_register); /** * cpufreq_power_cooling_register() - create cpufreq cooling device with power extensions - * @clip_cpus: cpumask of cpus where the frequency constraints will happen + * @policy: cpufreq policy * @capacitance: dynamic power coefficient for these cpus * @plat_static_func: function to calculate the static power consumed by these * cpus (optional) @@ -943,10 +928,10 @@ EXPORT_SYMBOL_GPL(of_cpufreq_cooling_register); * on failure, it returns a corresponding ERR_PTR(). */ struct thermal_cooling_device * -cpufreq_power_cooling_register(const struct cpumask *clip_cpus, u32 capacitance, +cpufreq_power_cooling_register(struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func) { - return __cpufreq_cooling_register(NULL, clip_cpus, capacitance, + return __cpufreq_cooling_register(NULL, policy, capacitance, plat_static_func); } EXPORT_SYMBOL(cpufreq_power_cooling_register); @@ -954,7 +939,7 @@ EXPORT_SYMBOL(cpufreq_power_cooling_register); /** * of_cpufreq_power_cooling_register() - create cpufreq cooling device with power extensions * @np: a valid struct device_node to the cooling device device tree node - * @clip_cpus: cpumask of cpus where the frequency constraints will happen + * @policy: cpufreq policy * @capacitance: dynamic power coefficient for these cpus * @plat_static_func: function to calculate the static power consumed by these * cpus (optional) @@ -976,14 +961,14 @@ EXPORT_SYMBOL(cpufreq_power_cooling_register); */ struct thermal_cooling_device * of_cpufreq_power_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus, + struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func) { if (!np) return ERR_PTR(-EINVAL); - return __cpufreq_cooling_register(np, clip_cpus, capacitance, + return __cpufreq_cooling_register(np, policy, capacitance, plat_static_func); } EXPORT_SYMBOL(of_cpufreq_power_cooling_register); diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c index fb648a45754e..f7ec39f46ee4 100644 --- a/drivers/thermal/imx_thermal.c +++ b/drivers/thermal/imx_thermal.c @@ -8,6 +8,7 @@ */ #include +#include #include #include #include @@ -88,6 +89,7 @@ static struct thermal_soc_data thermal_imx6sx_data = { }; struct imx_thermal_data { + struct cpufreq_policy *policy; struct thermal_zone_device *tz; struct thermal_cooling_device *cdev; enum thermal_device_mode mode; @@ -525,13 +527,18 @@ static int imx_thermal_probe(struct platform_device *pdev) regmap_write(map, MISC0 + REG_SET, MISC0_REFTOP_SELBIASOFF); regmap_write(map, TEMPSENSE0 + REG_SET, TEMPSENSE0_POWER_DOWN); - data->cdev = cpufreq_cooling_register(cpu_present_mask); + data->policy = cpufreq_cpu_get(0); + if (!data->policy) { + pr_debug("%s: CPUFreq policy not found\n", __func__); + return -EPROBE_DEFER; + } + + data->cdev = cpufreq_cooling_register(data->policy); if (IS_ERR(data->cdev)) { ret = PTR_ERR(data->cdev); - if (ret != -EPROBE_DEFER) - dev_err(&pdev->dev, - "failed to register cpufreq cooling device: %d\n", - ret); + dev_err(&pdev->dev, + "failed to register cpufreq cooling device: %d\n", ret); + cpufreq_cpu_put(data->policy); return ret; } @@ -542,6 +549,7 @@ static int imx_thermal_probe(struct platform_device *pdev) dev_err(&pdev->dev, "failed to get thermal clk: %d\n", ret); cpufreq_cooling_unregister(data->cdev); + cpufreq_cpu_put(data->policy); return ret; } @@ -556,6 +564,7 @@ static int imx_thermal_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "failed to enable thermal clk: %d\n", ret); cpufreq_cooling_unregister(data->cdev); + cpufreq_cpu_put(data->policy); return ret; } @@ -571,6 +580,7 @@ static int imx_thermal_probe(struct platform_device *pdev) "failed to register thermal zone device %d\n", ret); clk_disable_unprepare(data->thermal_clk); cpufreq_cooling_unregister(data->cdev); + cpufreq_cpu_put(data->policy); return ret; } @@ -599,6 +609,7 @@ static int imx_thermal_probe(struct platform_device *pdev) clk_disable_unprepare(data->thermal_clk); thermal_zone_device_unregister(data->tz); cpufreq_cooling_unregister(data->cdev); + cpufreq_cpu_put(data->policy); return ret; } @@ -620,6 +631,7 @@ static int imx_thermal_remove(struct platform_device *pdev) thermal_zone_device_unregister(data->tz); cpufreq_cooling_unregister(data->cdev); + cpufreq_cpu_put(data->policy); return 0; } diff --git a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c index 02790f69e26c..c211a8e4a210 100644 --- a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c +++ b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include @@ -37,6 +38,7 @@ /* common data structures */ struct ti_thermal_data { + struct cpufreq_policy *policy; struct thermal_zone_device *ti_thermal; struct thermal_zone_device *pcb_tz; struct thermal_cooling_device *cool_dev; @@ -247,15 +249,19 @@ int ti_thermal_register_cpu_cooling(struct ti_bandgap *bgp, int id) if (!data) return -EINVAL; + data->policy = cpufreq_cpu_get(0); + if (!data->policy) { + pr_debug("%s: CPUFreq policy not found\n", __func__); + return -EPROBE_DEFER; + } + /* Register cooling device */ - data->cool_dev = cpufreq_cooling_register(cpu_present_mask); + data->cool_dev = cpufreq_cooling_register(data->policy); if (IS_ERR(data->cool_dev)) { int ret = PTR_ERR(data->cool_dev); - - if (ret != -EPROBE_DEFER) - dev_err(bgp->dev, - "Failed to register cpu cooling device %d\n", - ret); + dev_err(bgp->dev, "Failed to register cpu cooling device %d\n", + ret); + cpufreq_cpu_put(data->policy); return ret; } @@ -270,8 +276,10 @@ int ti_thermal_unregister_cpu_cooling(struct ti_bandgap *bgp, int id) data = ti_bandgap_get_sensor_data(bgp, id); - if (data) + if (data) { cpufreq_cooling_unregister(data->cool_dev); + cpufreq_cpu_put(data->policy); + } return 0; } diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index 96c5e4c2f9c8..d4292ebc5c8b 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -28,47 +28,49 @@ #include #include +struct cpufreq_policy; + typedef int (*get_static_t)(cpumask_t *cpumask, int interval, unsigned long voltage, u32 *power); #ifdef CONFIG_CPU_THERMAL /** * cpufreq_cooling_register - function to create cpufreq cooling device. - * @clip_cpus: cpumask of cpus where the frequency constraints will happen + * @policy: cpufreq policy. */ struct thermal_cooling_device * -cpufreq_cooling_register(const struct cpumask *clip_cpus); +cpufreq_cooling_register(struct cpufreq_policy *policy); struct thermal_cooling_device * -cpufreq_power_cooling_register(const struct cpumask *clip_cpus, +cpufreq_power_cooling_register(struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func); /** * of_cpufreq_cooling_register - create cpufreq cooling device based on DT. * @np: a valid struct device_node to the cooling device device tree node. - * @clip_cpus: cpumask of cpus where the frequency constraints will happen + * @policy: cpufreq policy. */ #ifdef CONFIG_THERMAL_OF struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus); + struct cpufreq_policy *policy); struct thermal_cooling_device * of_cpufreq_power_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus, + struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func); #else static inline struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus) + struct cpufreq_policy *policy) { return ERR_PTR(-ENOSYS); } static inline struct thermal_cooling_device * of_cpufreq_power_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus, + struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func) { @@ -84,12 +86,12 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev); #else /* !CONFIG_CPU_THERMAL */ static inline struct thermal_cooling_device * -cpufreq_cooling_register(const struct cpumask *clip_cpus) +cpufreq_cooling_register(struct cpufreq_policy *policy) { return ERR_PTR(-ENOSYS); } static inline struct thermal_cooling_device * -cpufreq_power_cooling_register(const struct cpumask *clip_cpus, +cpufreq_power_cooling_register(struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func) { return NULL; @@ -97,14 +99,14 @@ cpufreq_power_cooling_register(const struct cpumask *clip_cpus, static inline struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus) + struct cpufreq_policy *policy) { return ERR_PTR(-ENOSYS); } static inline struct thermal_cooling_device * of_cpufreq_power_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus, + struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func) { -- cgit v1.2.3-59-g8ed1b From 55d852931319d2e3ccde86cd426405231ce6c6ac Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 25 Apr 2017 15:57:15 +0530 Subject: cpufreq: create cpufreq_table_count_valid_entries() We need such a routine at two places already, lets create one. Signed-off-by: Viresh Kumar Reviewed-by: Lukasz Luba Tested-by: Lukasz Luba Signed-off-by: Eduardo Valentin --- drivers/cpufreq/cpufreq_stats.c | 13 ++++--------- drivers/thermal/cpu_cooling.c | 22 +++++++++------------- include/linux/cpufreq.h | 14 ++++++++++++++ 3 files changed, 27 insertions(+), 22 deletions(-) diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c index f570ead62454..9c3d319dc129 100644 --- a/drivers/cpufreq/cpufreq_stats.c +++ b/drivers/cpufreq/cpufreq_stats.c @@ -170,11 +170,10 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy) unsigned int i = 0, count = 0, ret = -ENOMEM; struct cpufreq_stats *stats; unsigned int alloc_size; - struct cpufreq_frequency_table *pos, *table; + struct cpufreq_frequency_table *pos; - /* We need cpufreq table for creating stats table */ - table = policy->freq_table; - if (unlikely(!table)) + count = cpufreq_table_count_valid_entries(policy); + if (!count) return; /* stats already initialized */ @@ -185,10 +184,6 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy) if (!stats) return; - /* Find total allocation size */ - cpufreq_for_each_valid_entry(pos, table) - count++; - alloc_size = count * sizeof(int) + count * sizeof(u64); alloc_size += count * count * sizeof(int); @@ -205,7 +200,7 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy) stats->max_state = count; /* Find valid-unique entries */ - cpufreq_for_each_valid_entry(pos, table) + cpufreq_for_each_valid_entry(pos, policy->freq_table) if (freq_table_get_index(stats, pos->frequency) == -1) stats->freq_table[i++] = pos->frequency; diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index 58e58065b650..55ff45c1e917 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -739,7 +739,6 @@ __cpufreq_cooling_register(struct device_node *np, struct thermal_cooling_device *cdev; struct cpufreq_cooling_device *cpufreq_cdev; char dev_name[THERMAL_NAME_LENGTH]; - struct cpufreq_frequency_table *pos, *table; unsigned int freq, i, num_cpus; int ret; struct thermal_cooling_device_ops *cooling_ops; @@ -750,9 +749,10 @@ __cpufreq_cooling_register(struct device_node *np, return ERR_PTR(-EINVAL); } - table = policy->freq_table; - if (!table) { - pr_debug("%s: CPUFreq table not found\n", __func__); + i = cpufreq_table_count_valid_entries(policy); + if (!i) { + pr_debug("%s: CPUFreq table not found or has no valid entries\n", + __func__); return ERR_PTR(-ENODEV); } @@ -777,20 +777,16 @@ __cpufreq_cooling_register(struct device_node *np, goto free_time_in_idle; } - /* Find max levels */ - cpufreq_for_each_valid_entry(pos, table) - cpufreq_cdev->max_level++; + /* max_level is an index, not a counter */ + cpufreq_cdev->max_level = i - 1; - cpufreq_cdev->freq_table = kmalloc(sizeof(*cpufreq_cdev->freq_table) * - cpufreq_cdev->max_level, GFP_KERNEL); + cpufreq_cdev->freq_table = kmalloc(sizeof(*cpufreq_cdev->freq_table) * i, + GFP_KERNEL); if (!cpufreq_cdev->freq_table) { cdev = ERR_PTR(-ENOMEM); goto free_time_in_idle_timestamp; } - /* max_level is an index, not a counter */ - cpufreq_cdev->max_level--; - cpumask_copy(&cpufreq_cdev->allowed_cpus, policy->related_cpus); if (capacitance) { @@ -816,7 +812,7 @@ __cpufreq_cooling_register(struct device_node *np, /* Fill freq-table in descending order of frequencies */ for (i = 0, freq = -1; i <= cpufreq_cdev->max_level; i++) { - freq = find_next_max(table, freq); + freq = find_next_max(policy->freq_table, freq); cpufreq_cdev->freq_table[i] = freq; /* Warn for duplicate entries */ diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index a5ce0bbeadb5..eb9abfadaeac 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -862,6 +862,20 @@ static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy, return -EINVAL; } } + +static inline int cpufreq_table_count_valid_entries(const struct cpufreq_policy *policy) +{ + struct cpufreq_frequency_table *pos; + int count = 0; + + if (unlikely(!policy->freq_table)) + return 0; + + cpufreq_for_each_valid_entry(pos, policy->freq_table) + count++; + + return count; +} #else static inline int cpufreq_boost_trigger_state(int state) { -- cgit v1.2.3-59-g8ed1b From b12b6519496bb07b0845ed50eee1ca75c3b7fa81 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 25 Apr 2017 15:57:16 +0530 Subject: thermal: cpu_cooling: store cpufreq policy The cpufreq policy can be used by the cpu_cooling driver, lets store it in the cpufreq_cooling_device structure. Signed-off-by: Viresh Kumar Reviewed-by: Lukasz Luba Tested-by: Lukasz Luba Signed-off-by: Eduardo Valentin --- drivers/thermal/cpu_cooling.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index 55ff45c1e917..7dddc7443f5d 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -67,6 +67,7 @@ struct power_table { * registered. * @cdev: thermal_cooling_device pointer to keep track of the * registered cooling device. + * @policy: cpufreq policy. * @cpufreq_state: integer value representing the current state of cpufreq * cooling devices. * @clipped_freq: integer value representing the absolute value of the clipped @@ -91,6 +92,7 @@ struct power_table { struct cpufreq_cooling_device { int id; struct thermal_cooling_device *cdev; + struct cpufreq_policy *policy; unsigned int cpufreq_state; unsigned int clipped_freq; unsigned int max_level; @@ -760,6 +762,7 @@ __cpufreq_cooling_register(struct device_node *np, if (!cpufreq_cdev) return ERR_PTR(-ENOMEM); + cpufreq_cdev->policy = policy; num_cpus = cpumask_weight(policy->related_cpus); cpufreq_cdev->time_in_idle = kcalloc(num_cpus, sizeof(*cpufreq_cdev->time_in_idle), -- cgit v1.2.3-59-g8ed1b From 02bacb21c6575ce408645ddb22fef44940d10257 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 25 Apr 2017 15:57:17 +0530 Subject: thermal: cpu_cooling: OPPs are registered for all CPUs The OPPs are registered for all CPUs of a cpufreq policy now and we don't need to run the loop in build_dyn_power_table(). Just check for the policy->cpu and we should be fine. Signed-off-by: Viresh Kumar Reviewed-by: Lukasz Luba Tested-by: Lukasz Luba Signed-off-by: Eduardo Valentin --- drivers/thermal/cpu_cooling.c | 26 +++++++++++--------------- 1 file changed, 11 insertions(+), 15 deletions(-) diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index 7dddc7443f5d..ce387f62c93e 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -83,7 +83,7 @@ struct power_table { * @dyn_power_table: array of struct power_table for frequency to power * conversion, sorted in ascending order. * @dyn_power_table_entries: number of entries in the @dyn_power_table array - * @cpu_dev: the first cpu_device from @allowed_cpus that has OPPs registered + * @cpu_dev: the cpu_device of policy->cpu. * @plat_get_static_power: callback to calculate the static power * * This structure is required for keeping information of each registered @@ -207,24 +207,20 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_cdev, struct power_table *power_table; struct dev_pm_opp *opp; struct device *dev = NULL; - int num_opps = 0, cpu, i, ret = 0; + int num_opps = 0, cpu = cpufreq_cdev->policy->cpu, i, ret = 0; unsigned long freq; - for_each_cpu(cpu, &cpufreq_cdev->allowed_cpus) { - dev = get_cpu_device(cpu); - if (!dev) { - dev_warn(&cpufreq_cdev->cdev->device, - "No cpu device for cpu %d\n", cpu); - continue; - } - - num_opps = dev_pm_opp_get_opp_count(dev); - if (num_opps > 0) - break; - else if (num_opps < 0) - return num_opps; + dev = get_cpu_device(cpu); + if (unlikely(!dev)) { + dev_warn(&cpufreq_cdev->cdev->device, + "No cpu device for cpu %d\n", cpu); + return -ENODEV; } + num_opps = dev_pm_opp_get_opp_count(dev); + if (num_opps < 0) + return num_opps; + if (num_opps == 0) return -EINVAL; -- cgit v1.2.3-59-g8ed1b From ba76dd9ddd4046ece873444c2256e09afbd5d32e Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 25 Apr 2017 15:57:18 +0530 Subject: thermal: cpu_cooling: get rid of 'allowed_cpus' 'allowed_cpus' is a copy of policy->related_cpus and can be replaced by it directly. At some places we are only concerned about online CPUs and policy->cpus can be used there. Signed-off-by: Viresh Kumar Reviewed-by: Lukasz Luba Tested-by: Lukasz Luba Signed-off-by: Eduardo Valentin --- drivers/thermal/cpu_cooling.c | 81 +++++++++++++------------------------------ 1 file changed, 25 insertions(+), 56 deletions(-) diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index ce387f62c93e..94e7121817bf 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -74,7 +74,6 @@ struct power_table { * frequency. * @max_level: maximum cooling level. One less than total number of valid * cpufreq frequencies. - * @allowed_cpus: all the cpus involved for this cpufreq_cooling_device. * @node: list_head to link all cpufreq_cooling_device together. * @last_load: load measured by the latest call to cpufreq_get_requested_power() * @time_in_idle: previous reading of the absolute time that this cpu was idle @@ -97,7 +96,6 @@ struct cpufreq_cooling_device { unsigned int clipped_freq; unsigned int max_level; unsigned int *freq_table; /* In descending order */ - struct cpumask allowed_cpus; struct list_head node; u32 last_load; u64 *time_in_idle; @@ -161,7 +159,11 @@ static int cpufreq_thermal_notifier(struct notifier_block *nb, mutex_lock(&cooling_list_lock); list_for_each_entry(cpufreq_cdev, &cpufreq_cdev_list, node) { - if (!cpumask_test_cpu(policy->cpu, &cpufreq_cdev->allowed_cpus)) + /* + * A new copy of the policy is sent to the notifier and can't + * compare that directly. + */ + if (policy->cpu != cpufreq_cdev->policy->cpu) continue; /* @@ -304,7 +306,7 @@ static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_cdev, * get_load() - get load for a cpu since last updated * @cpufreq_cdev: &struct cpufreq_cooling_device for this cpu * @cpu: cpu number - * @cpu_idx: index of the cpu in cpufreq_cdev->allowed_cpus + * @cpu_idx: index of the cpu in time_in_idle* * * Return: The average load of cpu @cpu in percentage since this * function was last called. @@ -351,7 +353,7 @@ static int get_static_power(struct cpufreq_cooling_device *cpufreq_cdev, { struct dev_pm_opp *opp; unsigned long voltage; - struct cpumask *cpumask = &cpufreq_cdev->allowed_cpus; + struct cpumask *cpumask = cpufreq_cdev->policy->related_cpus; unsigned long freq_hz = freq * 1000; if (!cpufreq_cdev->plat_get_static_power || !cpufreq_cdev->cpu_dev) { @@ -468,7 +470,7 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev, cpufreq_cdev->cpufreq_state = state; cpufreq_cdev->clipped_freq = clip_freq; - cpufreq_update_policy(cpumask_any(&cpufreq_cdev->allowed_cpus)); + cpufreq_update_policy(cpufreq_cdev->policy->cpu); return 0; } @@ -504,28 +506,18 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev, int i = 0, cpu, ret; u32 static_power, dynamic_power, total_load = 0; struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata; + struct cpufreq_policy *policy = cpufreq_cdev->policy; u32 *load_cpu = NULL; - cpu = cpumask_any_and(&cpufreq_cdev->allowed_cpus, cpu_online_mask); - - /* - * All the CPUs are offline, thus the requested power by - * the cdev is 0 - */ - if (cpu >= nr_cpu_ids) { - *power = 0; - return 0; - } - - freq = cpufreq_quick_get(cpu); + freq = cpufreq_quick_get(policy->cpu); if (trace_thermal_power_cpu_get_power_enabled()) { - u32 ncpus = cpumask_weight(&cpufreq_cdev->allowed_cpus); + u32 ncpus = cpumask_weight(policy->related_cpus); load_cpu = kcalloc(ncpus, sizeof(*load_cpu), GFP_KERNEL); } - for_each_cpu(cpu, &cpufreq_cdev->allowed_cpus) { + for_each_cpu(cpu, policy->related_cpus) { u32 load; if (cpu_online(cpu)) @@ -550,9 +542,9 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev, } if (load_cpu) { - trace_thermal_power_cpu_get_power( - &cpufreq_cdev->allowed_cpus, - freq, load_cpu, i, dynamic_power, static_power); + trace_thermal_power_cpu_get_power(policy->related_cpus, freq, + load_cpu, i, dynamic_power, + static_power); kfree(load_cpu); } @@ -581,38 +573,22 @@ static int cpufreq_state2power(struct thermal_cooling_device *cdev, unsigned long state, u32 *power) { unsigned int freq, num_cpus; - cpumask_var_t cpumask; u32 static_power, dynamic_power; int ret; struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata; - if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) - return -ENOMEM; - - cpumask_and(cpumask, &cpufreq_cdev->allowed_cpus, cpu_online_mask); - num_cpus = cpumask_weight(cpumask); - - /* None of our cpus are online, so no power */ - if (num_cpus == 0) { - *power = 0; - ret = 0; - goto out; - } + num_cpus = cpumask_weight(cpufreq_cdev->policy->cpus); freq = cpufreq_cdev->freq_table[state]; - if (!freq) { - ret = -EINVAL; - goto out; - } + if (!freq) + return -EINVAL; dynamic_power = cpu_freq_to_power(cpufreq_cdev, freq) * num_cpus; ret = get_static_power(cpufreq_cdev, tz, freq, &static_power); if (ret) - goto out; + return ret; *power = static_power + dynamic_power; -out: - free_cpumask_var(cpumask); return ret; } @@ -640,19 +616,14 @@ static int cpufreq_power2state(struct thermal_cooling_device *cdev, struct thermal_zone_device *tz, u32 power, unsigned long *state) { - unsigned int cpu, cur_freq, target_freq; + unsigned int cur_freq, target_freq; int ret; s32 dyn_power; u32 last_load, normalised_power, static_power; struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata; + struct cpufreq_policy *policy = cpufreq_cdev->policy; - cpu = cpumask_any_and(&cpufreq_cdev->allowed_cpus, cpu_online_mask); - - /* None of our cpus are online */ - if (cpu >= nr_cpu_ids) - return -ENODEV; - - cur_freq = cpufreq_quick_get(cpu); + cur_freq = cpufreq_quick_get(policy->cpu); ret = get_static_power(cpufreq_cdev, tz, cur_freq, &static_power); if (ret) return ret; @@ -667,12 +638,12 @@ static int cpufreq_power2state(struct thermal_cooling_device *cdev, if (*state == THERMAL_CSTATE_INVALID) { dev_err_ratelimited(&cdev->device, "Failed to convert %dKHz for cpu %d into a cdev state\n", - target_freq, cpu); + target_freq, policy->cpu); return -EINVAL; } - trace_thermal_power_cpu_limit(&cpufreq_cdev->allowed_cpus, - target_freq, *state, power); + trace_thermal_power_cpu_limit(policy->related_cpus, target_freq, *state, + power); return 0; } @@ -786,8 +757,6 @@ __cpufreq_cooling_register(struct device_node *np, goto free_time_in_idle_timestamp; } - cpumask_copy(&cpufreq_cdev->allowed_cpus, policy->related_cpus); - if (capacitance) { cpufreq_cdev->plat_get_static_power = plat_static_func; -- cgit v1.2.3-59-g8ed1b From 349d39dc57396e3e9f39170905ff8d626eea9e44 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 25 Apr 2017 15:57:19 +0530 Subject: thermal: cpu_cooling: merge frequency and power tables The cpu_cooling driver keeps two tables: - freq_table: table of frequencies in descending order, built from policy->freq_table. - power_table: table of frequencies and power in ascending order, built from OPP table. If the OPPs are used for the CPU device then both these tables are actually built using the OPP core and should have the same frequency entries. And there is no need to keep separate tables for this. Lets merge them both. Note that the new table is in descending order of frequencies and so the 'for' loops were required to be fixed at few places to make it work. Signed-off-by: Viresh Kumar Reviewed-by: Lukasz Luba Tested-by: Lukasz Luba Signed-off-by: Eduardo Valentin --- drivers/thermal/cpu_cooling.c | 153 ++++++++++++++++++------------------------ 1 file changed, 67 insertions(+), 86 deletions(-) diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index 94e7121817bf..67ec52d5f7fc 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -49,14 +49,14 @@ */ /** - * struct power_table - frequency to power conversion + * struct freq_table - frequency table along with power entries * @frequency: frequency in KHz * @power: power in mW * * This structure is built when the cooling device registers and helps - * in translating frequency to power and viceversa. + * in translating frequency to power and vice versa. */ -struct power_table { +struct freq_table { u32 frequency; u32 power; }; @@ -79,9 +79,6 @@ struct power_table { * @time_in_idle: previous reading of the absolute time that this cpu was idle * @time_in_idle_timestamp: wall time of the last invocation of * get_cpu_idle_time_us() - * @dyn_power_table: array of struct power_table for frequency to power - * conversion, sorted in ascending order. - * @dyn_power_table_entries: number of entries in the @dyn_power_table array * @cpu_dev: the cpu_device of policy->cpu. * @plat_get_static_power: callback to calculate the static power * @@ -95,13 +92,11 @@ struct cpufreq_cooling_device { unsigned int cpufreq_state; unsigned int clipped_freq; unsigned int max_level; - unsigned int *freq_table; /* In descending order */ + struct freq_table *freq_table; /* In descending order */ struct list_head node; u32 last_load; u64 *time_in_idle; u64 *time_in_idle_timestamp; - struct power_table *dyn_power_table; - int dyn_power_table_entries; struct device *cpu_dev; get_static_t plat_get_static_power; }; @@ -125,10 +120,10 @@ static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_cdev, unsigned long level; for (level = 0; level <= cpufreq_cdev->max_level; level++) { - if (freq == cpufreq_cdev->freq_table[level]) + if (freq == cpufreq_cdev->freq_table[level].frequency) return level; - if (freq > cpufreq_cdev->freq_table[level]) + if (freq > cpufreq_cdev->freq_table[level].frequency) break; } @@ -189,28 +184,25 @@ static int cpufreq_thermal_notifier(struct notifier_block *nb, } /** - * build_dyn_power_table() - create a dynamic power to frequency table - * @cpufreq_cdev: the cpufreq cooling device in which to store the table + * update_freq_table() - Update the freq table with power numbers + * @cpufreq_cdev: the cpufreq cooling device in which to update the table * @capacitance: dynamic power coefficient for these cpus * - * Build a dynamic power to frequency table for this cpu and store it - * in @cpufreq_cdev. This table will be used in cpu_power_to_freq() and - * cpu_freq_to_power() to convert between power and frequency - * efficiently. Power is stored in mW, frequency in KHz. The - * resulting table is in ascending order. + * Update the freq table with power numbers. This table will be used in + * cpu_power_to_freq() and cpu_freq_to_power() to convert between power and + * frequency efficiently. Power is stored in mW, frequency in KHz. The + * resulting table is in descending order. * * Return: 0 on success, -EINVAL if there are no OPPs for any CPUs, - * -ENOMEM if we run out of memory or -EAGAIN if an OPP was - * added/enabled while the function was executing. + * or -ENOMEM if we run out of memory. */ -static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_cdev, - u32 capacitance) +static int update_freq_table(struct cpufreq_cooling_device *cpufreq_cdev, + u32 capacitance) { - struct power_table *power_table; + struct freq_table *freq_table = cpufreq_cdev->freq_table; struct dev_pm_opp *opp; struct device *dev = NULL; - int num_opps = 0, cpu = cpufreq_cdev->policy->cpu, i, ret = 0; - unsigned long freq; + int num_opps = 0, cpu = cpufreq_cdev->policy->cpu, i; dev = get_cpu_device(cpu); if (unlikely(!dev)) { @@ -223,25 +215,32 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_cdev, if (num_opps < 0) return num_opps; - if (num_opps == 0) + /* + * The cpufreq table is also built from the OPP table and so the count + * should match. + */ + if (num_opps != cpufreq_cdev->max_level + 1) { + dev_warn(dev, "Number of OPPs not matching with max_levels\n"); return -EINVAL; + } - power_table = kcalloc(num_opps, sizeof(*power_table), GFP_KERNEL); - if (!power_table) - return -ENOMEM; - - for (freq = 0, i = 0; - opp = dev_pm_opp_find_freq_ceil(dev, &freq), !IS_ERR(opp); - freq++, i++) { - u32 freq_mhz, voltage_mv; + for (i = 0; i <= cpufreq_cdev->max_level; i++) { + unsigned long freq = freq_table[i].frequency * 1000; + u32 freq_mhz = freq_table[i].frequency / 1000; u64 power; + u32 voltage_mv; - if (i >= num_opps) { - ret = -EAGAIN; - goto free_power_table; + /* + * Find ceil frequency as 'freq' may be slightly lower than OPP + * freq due to truncation while converting to kHz. + */ + opp = dev_pm_opp_find_freq_ceil(dev, &freq); + if (IS_ERR(opp)) { + dev_err(dev, "failed to get opp for %lu frequency\n", + freq); + return -EINVAL; } - freq_mhz = freq / 1000000; voltage_mv = dev_pm_opp_get_voltage(opp) / 1000; dev_pm_opp_put(opp); @@ -252,54 +251,39 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_cdev, power = (u64)capacitance * freq_mhz * voltage_mv * voltage_mv; do_div(power, 1000000000); - /* frequency is stored in power_table in KHz */ - power_table[i].frequency = freq / 1000; - /* power is stored in mW */ - power_table[i].power = power; - } - - if (i != num_opps) { - ret = PTR_ERR(opp); - goto free_power_table; + freq_table[i].power = power; } cpufreq_cdev->cpu_dev = dev; - cpufreq_cdev->dyn_power_table = power_table; - cpufreq_cdev->dyn_power_table_entries = i; return 0; - -free_power_table: - kfree(power_table); - - return ret; } static u32 cpu_freq_to_power(struct cpufreq_cooling_device *cpufreq_cdev, u32 freq) { int i; - struct power_table *pt = cpufreq_cdev->dyn_power_table; + struct freq_table *freq_table = cpufreq_cdev->freq_table; - for (i = 1; i < cpufreq_cdev->dyn_power_table_entries; i++) - if (freq < pt[i].frequency) + for (i = 1; i <= cpufreq_cdev->max_level; i++) + if (freq > freq_table[i].frequency) break; - return pt[i - 1].power; + return freq_table[i - 1].power; } static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_cdev, u32 power) { int i; - struct power_table *pt = cpufreq_cdev->dyn_power_table; + struct freq_table *freq_table = cpufreq_cdev->freq_table; - for (i = 1; i < cpufreq_cdev->dyn_power_table_entries; i++) - if (power < pt[i].power) + for (i = 1; i <= cpufreq_cdev->max_level; i++) + if (power > freq_table[i].power) break; - return pt[i - 1].frequency; + return freq_table[i - 1].frequency; } /** @@ -466,7 +450,7 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev, if (cpufreq_cdev->cpufreq_state == state) return 0; - clip_freq = cpufreq_cdev->freq_table[state]; + clip_freq = cpufreq_cdev->freq_table[state].frequency; cpufreq_cdev->cpufreq_state = state; cpufreq_cdev->clipped_freq = clip_freq; @@ -579,7 +563,7 @@ static int cpufreq_state2power(struct thermal_cooling_device *cdev, num_cpus = cpumask_weight(cpufreq_cdev->policy->cpus); - freq = cpufreq_cdev->freq_table[state]; + freq = cpufreq_cdev->freq_table[state].frequency; if (!freq) return -EINVAL; @@ -757,31 +741,20 @@ __cpufreq_cooling_register(struct device_node *np, goto free_time_in_idle_timestamp; } - if (capacitance) { - cpufreq_cdev->plat_get_static_power = plat_static_func; - - ret = build_dyn_power_table(cpufreq_cdev, capacitance); - if (ret) { - cdev = ERR_PTR(ret); - goto free_table; - } - - cooling_ops = &cpufreq_power_cooling_ops; - } else { - cooling_ops = &cpufreq_cooling_ops; - } - ret = ida_simple_get(&cpufreq_ida, 0, 0, GFP_KERNEL); if (ret < 0) { cdev = ERR_PTR(ret); - goto free_power_table; + goto free_table; } cpufreq_cdev->id = ret; + snprintf(dev_name, sizeof(dev_name), "thermal-cpufreq-%d", + cpufreq_cdev->id); + /* Fill freq-table in descending order of frequencies */ for (i = 0, freq = -1; i <= cpufreq_cdev->max_level; i++) { freq = find_next_max(policy->freq_table, freq); - cpufreq_cdev->freq_table[i] = freq; + cpufreq_cdev->freq_table[i].frequency = freq; /* Warn for duplicate entries */ if (!freq) @@ -790,15 +763,26 @@ __cpufreq_cooling_register(struct device_node *np, pr_debug("%s: freq:%u KHz\n", __func__, freq); } - snprintf(dev_name, sizeof(dev_name), "thermal-cpufreq-%d", - cpufreq_cdev->id); + if (capacitance) { + cpufreq_cdev->plat_get_static_power = plat_static_func; + + ret = update_freq_table(cpufreq_cdev, capacitance); + if (ret) { + cdev = ERR_PTR(ret); + goto remove_ida; + } + + cooling_ops = &cpufreq_power_cooling_ops; + } else { + cooling_ops = &cpufreq_cooling_ops; + } cdev = thermal_of_cooling_device_register(np, dev_name, cpufreq_cdev, cooling_ops); if (IS_ERR(cdev)) goto remove_ida; - cpufreq_cdev->clipped_freq = cpufreq_cdev->freq_table[0]; + cpufreq_cdev->clipped_freq = cpufreq_cdev->freq_table[0].frequency; cpufreq_cdev->cdev = cdev; mutex_lock(&cooling_list_lock); @@ -815,8 +799,6 @@ __cpufreq_cooling_register(struct device_node *np, remove_ida: ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id); -free_power_table: - kfree(cpufreq_cdev->dyn_power_table); free_table: kfree(cpufreq_cdev->freq_table); free_time_in_idle_timestamp: @@ -965,7 +947,6 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev) thermal_cooling_device_unregister(cpufreq_cdev->cdev); ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id); - kfree(cpufreq_cdev->dyn_power_table); kfree(cpufreq_cdev->time_in_idle_timestamp); kfree(cpufreq_cdev->time_in_idle); kfree(cpufreq_cdev->freq_table); -- cgit v1.2.3-59-g8ed1b From 81ee14da1051ee87c243b9a0e55d83f1aa274b76 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 25 Apr 2017 15:57:20 +0530 Subject: thermal: cpu_cooling: create structure for idle time stats We keep two arrays for idle time stats and allocate memory for them separately. It would be much easier to follow if we create an array of idle stats structure instead and allocate it once. Signed-off-by: Viresh Kumar Reviewed-by: Lukasz Luba Tested-by: Lukasz Luba Signed-off-by: Eduardo Valentin --- drivers/thermal/cpu_cooling.c | 53 ++++++++++++++++++++----------------------- 1 file changed, 25 insertions(+), 28 deletions(-) diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index 67ec52d5f7fc..11735dba1456 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -61,6 +61,16 @@ struct freq_table { u32 power; }; +/** + * struct time_in_idle - Idle time stats + * @time: previous reading of the absolute time that this cpu was idle + * @timestamp: wall time of the last invocation of get_cpu_idle_time_us() + */ +struct time_in_idle { + u64 time; + u64 timestamp; +}; + /** * struct cpufreq_cooling_device - data for cooling device with cpufreq * @id: unique integer value corresponding to each cpufreq_cooling_device @@ -76,9 +86,7 @@ struct freq_table { * cpufreq frequencies. * @node: list_head to link all cpufreq_cooling_device together. * @last_load: load measured by the latest call to cpufreq_get_requested_power() - * @time_in_idle: previous reading of the absolute time that this cpu was idle - * @time_in_idle_timestamp: wall time of the last invocation of - * get_cpu_idle_time_us() + * @idle_time: idle time stats * @cpu_dev: the cpu_device of policy->cpu. * @plat_get_static_power: callback to calculate the static power * @@ -95,8 +103,7 @@ struct cpufreq_cooling_device { struct freq_table *freq_table; /* In descending order */ struct list_head node; u32 last_load; - u64 *time_in_idle; - u64 *time_in_idle_timestamp; + struct time_in_idle *idle_time; struct device *cpu_dev; get_static_t plat_get_static_power; }; @@ -300,18 +307,19 @@ static u32 get_load(struct cpufreq_cooling_device *cpufreq_cdev, int cpu, { u32 load; u64 now, now_idle, delta_time, delta_idle; + struct time_in_idle *idle_time = &cpufreq_cdev->idle_time[cpu_idx]; now_idle = get_cpu_idle_time(cpu, &now, 0); - delta_idle = now_idle - cpufreq_cdev->time_in_idle[cpu_idx]; - delta_time = now - cpufreq_cdev->time_in_idle_timestamp[cpu_idx]; + delta_idle = now_idle - idle_time->time; + delta_time = now - idle_time->timestamp; if (delta_time <= delta_idle) load = 0; else load = div64_u64(100 * (delta_time - delta_idle), delta_time); - cpufreq_cdev->time_in_idle[cpu_idx] = now_idle; - cpufreq_cdev->time_in_idle_timestamp[cpu_idx] = now; + idle_time->time = now_idle; + idle_time->timestamp = now; return load; } @@ -715,22 +723,14 @@ __cpufreq_cooling_register(struct device_node *np, cpufreq_cdev->policy = policy; num_cpus = cpumask_weight(policy->related_cpus); - cpufreq_cdev->time_in_idle = kcalloc(num_cpus, - sizeof(*cpufreq_cdev->time_in_idle), - GFP_KERNEL); - if (!cpufreq_cdev->time_in_idle) { + cpufreq_cdev->idle_time = kcalloc(num_cpus, + sizeof(*cpufreq_cdev->idle_time), + GFP_KERNEL); + if (!cpufreq_cdev->idle_time) { cdev = ERR_PTR(-ENOMEM); goto free_cdev; } - cpufreq_cdev->time_in_idle_timestamp = - kcalloc(num_cpus, sizeof(*cpufreq_cdev->time_in_idle_timestamp), - GFP_KERNEL); - if (!cpufreq_cdev->time_in_idle_timestamp) { - cdev = ERR_PTR(-ENOMEM); - goto free_time_in_idle; - } - /* max_level is an index, not a counter */ cpufreq_cdev->max_level = i - 1; @@ -738,7 +738,7 @@ __cpufreq_cooling_register(struct device_node *np, GFP_KERNEL); if (!cpufreq_cdev->freq_table) { cdev = ERR_PTR(-ENOMEM); - goto free_time_in_idle_timestamp; + goto free_idle_time; } ret = ida_simple_get(&cpufreq_ida, 0, 0, GFP_KERNEL); @@ -801,10 +801,8 @@ remove_ida: ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id); free_table: kfree(cpufreq_cdev->freq_table); -free_time_in_idle_timestamp: - kfree(cpufreq_cdev->time_in_idle_timestamp); -free_time_in_idle: - kfree(cpufreq_cdev->time_in_idle); +free_idle_time: + kfree(cpufreq_cdev->idle_time); free_cdev: kfree(cpufreq_cdev); return cdev; @@ -947,8 +945,7 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev) thermal_cooling_device_unregister(cpufreq_cdev->cdev); ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id); - kfree(cpufreq_cdev->time_in_idle_timestamp); - kfree(cpufreq_cdev->time_in_idle); + kfree(cpufreq_cdev->idle_time); kfree(cpufreq_cdev->freq_table); kfree(cpufreq_cdev); } -- cgit v1.2.3-59-g8ed1b From da27f69d6a4eaf7bdaaad9d9e1b997a1c8f186aa Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 25 Apr 2017 15:57:21 +0530 Subject: thermal: cpu_cooling: get_level() can't fail The frequency passed to get_level() is returned by cpu_power_to_freq() and it is guaranteed that get_level() can't fail. Get rid of error code. Signed-off-by: Viresh Kumar Reviewed-by: Lukasz Luba Tested-by: Lukasz Luba Signed-off-by: Eduardo Valentin --- drivers/thermal/cpu_cooling.c | 20 +++++--------------- 1 file changed, 5 insertions(+), 15 deletions(-) diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index 11735dba1456..2c2d76ac04c3 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -119,22 +119,19 @@ static LIST_HEAD(cpufreq_cdev_list); * @cpufreq_cdev: cpufreq_cdev for which the property is required * @freq: Frequency * - * Return: level on success, THERMAL_CSTATE_INVALID on error. + * Return: level corresponding to the frequency. */ static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_cdev, unsigned int freq) { + struct freq_table *freq_table = cpufreq_cdev->freq_table; unsigned long level; - for (level = 0; level <= cpufreq_cdev->max_level; level++) { - if (freq == cpufreq_cdev->freq_table[level].frequency) - return level; - - if (freq > cpufreq_cdev->freq_table[level].frequency) + for (level = 1; level <= cpufreq_cdev->max_level; level++) + if (freq > freq_table[level].frequency) break; - } - return THERMAL_CSTATE_INVALID; + return level - 1; } /** @@ -627,13 +624,6 @@ static int cpufreq_power2state(struct thermal_cooling_device *cdev, target_freq = cpu_power_to_freq(cpufreq_cdev, normalised_power); *state = get_level(cpufreq_cdev, target_freq); - if (*state == THERMAL_CSTATE_INVALID) { - dev_err_ratelimited(&cdev->device, - "Failed to convert %dKHz for cpu %d into a cdev state\n", - target_freq, policy->cpu); - return -EINVAL; - } - trace_thermal_power_cpu_limit(policy->related_cpus, target_freq, *state, power); return 0; -- cgit v1.2.3-59-g8ed1b From 53ca1ece60a719e23f686c647cb05d9e12a31974 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 25 Apr 2017 15:57:22 +0530 Subject: thermal: cpu_cooling: don't store cpu_dev in cpufreq_cdev 'cpu_dev' is used by only one function, get_static_power(), and it wouldn't be time consuming to get the cpu device structure within it. This would help removing cpu_dev from struct cpufreq_cooling_device. Signed-off-by: Viresh Kumar Reviewed-by: Lukasz Luba Tested-by: Lukasz Luba Signed-off-by: Eduardo Valentin --- drivers/thermal/cpu_cooling.c | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index 2c2d76ac04c3..bfa9731e7cdb 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -87,7 +87,6 @@ struct time_in_idle { * @node: list_head to link all cpufreq_cooling_device together. * @last_load: load measured by the latest call to cpufreq_get_requested_power() * @idle_time: idle time stats - * @cpu_dev: the cpu_device of policy->cpu. * @plat_get_static_power: callback to calculate the static power * * This structure is required for keeping information of each registered @@ -104,7 +103,6 @@ struct cpufreq_cooling_device { struct list_head node; u32 last_load; struct time_in_idle *idle_time; - struct device *cpu_dev; get_static_t plat_get_static_power; }; @@ -259,8 +257,6 @@ static int update_freq_table(struct cpufreq_cooling_device *cpufreq_cdev, freq_table[i].power = power; } - cpufreq_cdev->cpu_dev = dev; - return 0; } @@ -342,19 +338,22 @@ static int get_static_power(struct cpufreq_cooling_device *cpufreq_cdev, { struct dev_pm_opp *opp; unsigned long voltage; - struct cpumask *cpumask = cpufreq_cdev->policy->related_cpus; + struct cpufreq_policy *policy = cpufreq_cdev->policy; + struct cpumask *cpumask = policy->related_cpus; unsigned long freq_hz = freq * 1000; + struct device *dev; - if (!cpufreq_cdev->plat_get_static_power || !cpufreq_cdev->cpu_dev) { + if (!cpufreq_cdev->plat_get_static_power) { *power = 0; return 0; } - opp = dev_pm_opp_find_freq_exact(cpufreq_cdev->cpu_dev, freq_hz, - true); + dev = get_cpu_device(policy->cpu); + WARN_ON(!dev); + + opp = dev_pm_opp_find_freq_exact(dev, freq_hz, true); if (IS_ERR(opp)) { - dev_warn_ratelimited(cpufreq_cdev->cpu_dev, - "Failed to find OPP for frequency %lu: %ld\n", + dev_warn_ratelimited(dev, "Failed to find OPP for frequency %lu: %ld\n", freq_hz, PTR_ERR(opp)); return -EINVAL; } @@ -363,8 +362,7 @@ static int get_static_power(struct cpufreq_cooling_device *cpufreq_cdev, dev_pm_opp_put(opp); if (voltage == 0) { - dev_err_ratelimited(cpufreq_cdev->cpu_dev, - "Failed to get voltage for frequency %lu\n", + dev_err_ratelimited(dev, "Failed to get voltage for frequency %lu\n", freq_hz); return -EINVAL; } -- cgit v1.2.3-59-g8ed1b From cb1b631864ad7e34324ceccb73d0226dd00ad90d Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 25 Apr 2017 15:57:23 +0530 Subject: thermal: cpu_cooling: 'freq' can't be zero in cpufreq_state2power() The frequency table shouldn't have any zero frequency entries and so such a check isn't required. Though it would be better to make sure 'state' is within limits. Signed-off-by: Viresh Kumar Reviewed-by: Lukasz Luba Tested-by: Lukasz Luba Signed-off-by: Eduardo Valentin --- drivers/thermal/cpu_cooling.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index bfa9731e7cdb..9cbf7bdbeb7a 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -564,12 +564,13 @@ static int cpufreq_state2power(struct thermal_cooling_device *cdev, int ret; struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata; + /* Request state should be less than max_level */ + if (WARN_ON(state > cpufreq_cdev->max_level)) + return -EINVAL; + num_cpus = cpumask_weight(cpufreq_cdev->policy->cpus); freq = cpufreq_cdev->freq_table[state].frequency; - if (!freq) - return -EINVAL; - dynamic_power = cpu_freq_to_power(cpufreq_cdev, freq) * num_cpus; ret = get_static_power(cpufreq_cdev, tz, freq, &static_power); if (ret) -- cgit v1.2.3-59-g8ed1b From d72b4015839cca333a8e0108b1739a50f03d2acc Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 25 Apr 2017 15:57:24 +0530 Subject: thermal: cpu_cooling: Rearrange struct cpufreq_cooling_device This shrinks the size of the structure on arm64 by 8 bytes by avoiding padding of 4 bytes at two places. Also add missing doc comment for freq_table Signed-off-by: Viresh Kumar Reviewed-by: Lukasz Luba Tested-by: Lukasz Luba Signed-off-by: Eduardo Valentin --- drivers/thermal/cpu_cooling.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index 9cbf7bdbeb7a..1305020790b2 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -75,17 +75,18 @@ struct time_in_idle { * struct cpufreq_cooling_device - data for cooling device with cpufreq * @id: unique integer value corresponding to each cpufreq_cooling_device * registered. - * @cdev: thermal_cooling_device pointer to keep track of the - * registered cooling device. - * @policy: cpufreq policy. + * @last_load: load measured by the latest call to cpufreq_get_requested_power() * @cpufreq_state: integer value representing the current state of cpufreq * cooling devices. * @clipped_freq: integer value representing the absolute value of the clipped * frequency. * @max_level: maximum cooling level. One less than total number of valid * cpufreq frequencies. + * @freq_table: Freq table in descending order of frequencies + * @cdev: thermal_cooling_device pointer to keep track of the + * registered cooling device. + * @policy: cpufreq policy. * @node: list_head to link all cpufreq_cooling_device together. - * @last_load: load measured by the latest call to cpufreq_get_requested_power() * @idle_time: idle time stats * @plat_get_static_power: callback to calculate the static power * @@ -94,14 +95,14 @@ struct time_in_idle { */ struct cpufreq_cooling_device { int id; - struct thermal_cooling_device *cdev; - struct cpufreq_policy *policy; + u32 last_load; unsigned int cpufreq_state; unsigned int clipped_freq; unsigned int max_level; struct freq_table *freq_table; /* In descending order */ + struct thermal_cooling_device *cdev; + struct cpufreq_policy *policy; struct list_head node; - u32 last_load; struct time_in_idle *idle_time; get_static_t plat_get_static_power; }; -- cgit v1.2.3-59-g8ed1b From f19b1a1735f7453c35031ed5ca3883f20176dde6 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 23 May 2017 12:33:06 +0530 Subject: thermal: cpu_cooling: Replace kmalloc with kmalloc_array Checkpatch reports following: WARNING: Prefer kmalloc_array over kmalloc with multiply + cpufreq_cdev->freq_table = kmalloc(sizeof(*cpufreq_cdev->freq_table) * i, Fix that. Signed-off-by: Viresh Kumar Signed-off-by: Eduardo Valentin --- drivers/thermal/cpu_cooling.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index 1305020790b2..908a8014cf76 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -724,8 +724,9 @@ __cpufreq_cooling_register(struct device_node *np, /* max_level is an index, not a counter */ cpufreq_cdev->max_level = i - 1; - cpufreq_cdev->freq_table = kmalloc(sizeof(*cpufreq_cdev->freq_table) * i, - GFP_KERNEL); + cpufreq_cdev->freq_table = kmalloc_array(i, + sizeof(*cpufreq_cdev->freq_table), + GFP_KERNEL); if (!cpufreq_cdev->freq_table) { cdev = ERR_PTR(-ENOMEM); goto free_idle_time; -- cgit v1.2.3-59-g8ed1b From 4a78cc644eed3cf2dae00c3a959910a86c140fd6 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 26 May 2017 17:10:15 +0200 Subject: mtd: nand: Make sure drivers not supporting SET/GET_FEATURES return -ENOTSUPP A lot of drivers are providing their own ->cmdfunc(), and most of the time this implementation does not support all possible NAND operations. But since ->cmdfunc() cannot return an error code, the core has no way to know that the operation it requested is not supported. This is a problem we cannot address for all kind of operations with the current design, but we can prevent these silent failures for the GET/SET FEATURES operation by overloading the default ->onfi_{set,get}_features() methods with one returning -ENOTSUPP. Reported-by: Chris Packham Signed-off-by: Boris Brezillon Tested-by: Chris Packham --- drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c | 2 ++ drivers/mtd/nand/cafe_nand.c | 2 ++ drivers/mtd/nand/denali.c | 2 ++ drivers/mtd/nand/docg4.c | 2 ++ drivers/mtd/nand/fsl_elbc_nand.c | 2 ++ drivers/mtd/nand/fsl_ifc_nand.c | 2 ++ drivers/mtd/nand/hisi504_nand.c | 2 ++ drivers/mtd/nand/mpc5121_nfc.c | 2 ++ drivers/mtd/nand/nand_base.c | 19 +++++++++++++++++++ drivers/mtd/nand/pxa3xx_nand.c | 2 ++ drivers/mtd/nand/qcom_nandc.c | 2 ++ drivers/mtd/nand/sh_flctl.c | 2 ++ drivers/mtd/nand/vf610_nfc.c | 2 ++ drivers/staging/mt29f_spinand/mt29f_spinand.c | 2 ++ include/linux/mtd/nand.h | 5 +++++ 15 files changed, 50 insertions(+) diff --git a/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c b/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c index f1da4ea88f2c..54bac5b73f0a 100644 --- a/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c +++ b/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c @@ -392,6 +392,8 @@ int bcm47xxnflash_ops_bcm4706_init(struct bcm47xxnflash *b47n) b47n->nand_chip.read_byte = bcm47xxnflash_ops_bcm4706_read_byte; b47n->nand_chip.read_buf = bcm47xxnflash_ops_bcm4706_read_buf; b47n->nand_chip.write_buf = bcm47xxnflash_ops_bcm4706_write_buf; + b47n->nand_chip.onfi_set_features = nand_onfi_get_set_features_notsupp; + b47n->nand_chip.onfi_get_features = nand_onfi_get_set_features_notsupp; nand_chip->chip_delay = 50; b47n->nand_chip.bbt_options = NAND_BBT_USE_FLASH; diff --git a/drivers/mtd/nand/cafe_nand.c b/drivers/mtd/nand/cafe_nand.c index d40c32d311d8..2fd733eba0a3 100644 --- a/drivers/mtd/nand/cafe_nand.c +++ b/drivers/mtd/nand/cafe_nand.c @@ -654,6 +654,8 @@ static int cafe_nand_probe(struct pci_dev *pdev, cafe->nand.read_buf = cafe_read_buf; cafe->nand.write_buf = cafe_write_buf; cafe->nand.select_chip = cafe_select_chip; + cafe->nand.onfi_set_features = nand_onfi_get_set_features_notsupp; + cafe->nand.onfi_get_features = nand_onfi_get_set_features_notsupp; cafe->nand.chip_delay = 0; diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c index 16634df2e39a..b3c99d98fdee 100644 --- a/drivers/mtd/nand/denali.c +++ b/drivers/mtd/nand/denali.c @@ -1531,6 +1531,8 @@ int denali_init(struct denali_nand_info *denali) chip->cmdfunc = denali_cmdfunc; chip->read_byte = denali_read_byte; chip->waitfunc = denali_waitfunc; + chip->onfi_set_features = nand_onfi_get_set_features_notsupp; + chip->onfi_get_features = nand_onfi_get_set_features_notsupp; /* * scan for NAND devices attached to the controller diff --git a/drivers/mtd/nand/docg4.c b/drivers/mtd/nand/docg4.c index 7af2a3cd949e..a27a84fbfb84 100644 --- a/drivers/mtd/nand/docg4.c +++ b/drivers/mtd/nand/docg4.c @@ -1260,6 +1260,8 @@ static void __init init_mtd_structs(struct mtd_info *mtd) nand->read_buf = docg4_read_buf; nand->write_buf = docg4_write_buf16; nand->erase = docg4_erase_block; + nand->onfi_set_features = nand_onfi_get_set_features_notsupp; + nand->onfi_get_features = nand_onfi_get_set_features_notsupp; nand->ecc.read_page = docg4_read_page; nand->ecc.write_page = docg4_write_page; nand->ecc.read_page_raw = docg4_read_page_raw; diff --git a/drivers/mtd/nand/fsl_elbc_nand.c b/drivers/mtd/nand/fsl_elbc_nand.c index 113f76e59937..b9ac16f05057 100644 --- a/drivers/mtd/nand/fsl_elbc_nand.c +++ b/drivers/mtd/nand/fsl_elbc_nand.c @@ -775,6 +775,8 @@ static int fsl_elbc_chip_init(struct fsl_elbc_mtd *priv) chip->select_chip = fsl_elbc_select_chip; chip->cmdfunc = fsl_elbc_cmdfunc; chip->waitfunc = fsl_elbc_wait; + chip->onfi_set_features = nand_onfi_get_set_features_notsupp; + chip->onfi_get_features = nand_onfi_get_set_features_notsupp; chip->bbt_td = &bbt_main_descr; chip->bbt_md = &bbt_mirror_descr; diff --git a/drivers/mtd/nand/fsl_ifc_nand.c b/drivers/mtd/nand/fsl_ifc_nand.c index d1570f512f0b..89e14daeaba6 100644 --- a/drivers/mtd/nand/fsl_ifc_nand.c +++ b/drivers/mtd/nand/fsl_ifc_nand.c @@ -831,6 +831,8 @@ static int fsl_ifc_chip_init(struct fsl_ifc_mtd *priv) chip->select_chip = fsl_ifc_select_chip; chip->cmdfunc = fsl_ifc_cmdfunc; chip->waitfunc = fsl_ifc_wait; + chip->onfi_set_features = nand_onfi_get_set_features_notsupp; + chip->onfi_get_features = nand_onfi_get_set_features_notsupp; chip->bbt_td = &bbt_main_descr; chip->bbt_md = &bbt_mirror_descr; diff --git a/drivers/mtd/nand/hisi504_nand.c b/drivers/mtd/nand/hisi504_nand.c index e40364eeb556..530caa80b1b6 100644 --- a/drivers/mtd/nand/hisi504_nand.c +++ b/drivers/mtd/nand/hisi504_nand.c @@ -764,6 +764,8 @@ static int hisi_nfc_probe(struct platform_device *pdev) chip->write_buf = hisi_nfc_write_buf; chip->read_buf = hisi_nfc_read_buf; chip->chip_delay = HINFC504_CHIP_DELAY; + chip->onfi_set_features = nand_onfi_get_set_features_notsupp; + chip->onfi_get_features = nand_onfi_get_set_features_notsupp; hisi_nfc_host_init(host); diff --git a/drivers/mtd/nand/mpc5121_nfc.c b/drivers/mtd/nand/mpc5121_nfc.c index 6d6eaed2d20c..0e86fb6277c3 100644 --- a/drivers/mtd/nand/mpc5121_nfc.c +++ b/drivers/mtd/nand/mpc5121_nfc.c @@ -708,6 +708,8 @@ static int mpc5121_nfc_probe(struct platform_device *op) chip->read_buf = mpc5121_nfc_read_buf; chip->write_buf = mpc5121_nfc_write_buf; chip->select_chip = mpc5121_nfc_select_chip; + chip->onfi_set_features = nand_onfi_get_set_features_notsupp; + chip->onfi_get_features = nand_onfi_get_set_features_notsupp; chip->bbt_options = NAND_BBT_USE_FLASH; chip->ecc.mode = NAND_ECC_SOFT; chip->ecc.algo = NAND_ECC_HAMMING; diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index 0b3b1a88091a..ed08e3946727 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -3420,6 +3420,25 @@ static int nand_onfi_get_features(struct mtd_info *mtd, struct nand_chip *chip, return 0; } +/** + * nand_onfi_get_set_features_notsupp - set/get features stub returning + * -ENOTSUPP + * @mtd: MTD device structure + * @chip: nand chip info structure + * @addr: feature address. + * @subfeature_param: the subfeature parameters, a four bytes array. + * + * Should be used by NAND controller drivers that do not support the SET/GET + * FEATURES operations. + */ +int nand_onfi_get_set_features_notsupp(struct mtd_info *mtd, + struct nand_chip *chip, int addr, + u8 *subfeature_param) +{ + return -ENOTSUPP; +} +EXPORT_SYMBOL(nand_onfi_get_set_features_notsupp); + /** * nand_suspend - [MTD Interface] Suspend the NAND flash * @mtd: MTD device structure diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c index 649ba8200832..74dae4bbdac8 100644 --- a/drivers/mtd/nand/pxa3xx_nand.c +++ b/drivers/mtd/nand/pxa3xx_nand.c @@ -1812,6 +1812,8 @@ static int alloc_nand_resource(struct platform_device *pdev) chip->write_buf = pxa3xx_nand_write_buf; chip->options |= NAND_NO_SUBPAGE_WRITE; chip->cmdfunc = nand_cmdfunc; + chip->onfi_set_features = nand_onfi_get_set_features_notsupp; + chip->onfi_get_features = nand_onfi_get_set_features_notsupp; } nand_hw_control_init(chip->controller); diff --git a/drivers/mtd/nand/qcom_nandc.c b/drivers/mtd/nand/qcom_nandc.c index 57d483ac5765..88af7145a51a 100644 --- a/drivers/mtd/nand/qcom_nandc.c +++ b/drivers/mtd/nand/qcom_nandc.c @@ -2008,6 +2008,8 @@ static int qcom_nand_host_init(struct qcom_nand_controller *nandc, chip->read_byte = qcom_nandc_read_byte; chip->read_buf = qcom_nandc_read_buf; chip->write_buf = qcom_nandc_write_buf; + chip->onfi_set_features = nand_onfi_get_set_features_notsupp; + chip->onfi_get_features = nand_onfi_get_set_features_notsupp; /* * the bad block marker is readable only when we read the last codeword diff --git a/drivers/mtd/nand/sh_flctl.c b/drivers/mtd/nand/sh_flctl.c index 442ce619b3b6..891ac7b99305 100644 --- a/drivers/mtd/nand/sh_flctl.c +++ b/drivers/mtd/nand/sh_flctl.c @@ -1183,6 +1183,8 @@ static int flctl_probe(struct platform_device *pdev) nand->read_buf = flctl_read_buf; nand->select_chip = flctl_select_chip; nand->cmdfunc = flctl_cmdfunc; + nand->onfi_set_features = nand_onfi_get_set_features_notsupp; + nand->onfi_get_features = nand_onfi_get_set_features_notsupp; if (pdata->flcmncr_val & SEL_16BIT) nand->options |= NAND_BUSWIDTH_16; diff --git a/drivers/mtd/nand/vf610_nfc.c b/drivers/mtd/nand/vf610_nfc.c index 3ea4bb19e12d..744ab10e8962 100644 --- a/drivers/mtd/nand/vf610_nfc.c +++ b/drivers/mtd/nand/vf610_nfc.c @@ -703,6 +703,8 @@ static int vf610_nfc_probe(struct platform_device *pdev) chip->read_buf = vf610_nfc_read_buf; chip->write_buf = vf610_nfc_write_buf; chip->select_chip = vf610_nfc_select_chip; + chip->onfi_set_features = nand_onfi_get_set_features_notsupp; + chip->onfi_get_features = nand_onfi_get_set_features_notsupp; chip->options |= NAND_NO_SUBPAGE_WRITE; diff --git a/drivers/staging/mt29f_spinand/mt29f_spinand.c b/drivers/staging/mt29f_spinand/mt29f_spinand.c index e389009fca42..a4e3ae8f0c85 100644 --- a/drivers/staging/mt29f_spinand/mt29f_spinand.c +++ b/drivers/staging/mt29f_spinand/mt29f_spinand.c @@ -915,6 +915,8 @@ static int spinand_probe(struct spi_device *spi_nand) chip->waitfunc = spinand_wait; chip->options |= NAND_CACHEPRG; chip->select_chip = spinand_select_chip; + chip->onfi_set_features = nand_onfi_get_set_features_notsupp; + chip->onfi_get_features = nand_onfi_get_set_features_notsupp; mtd = nand_to_mtd(chip); diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 7a01d2eb7443..28f7dd9177e9 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -1259,6 +1259,11 @@ int nand_read_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page); int nand_read_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip, int page); +/* Stub used by drivers that do not support GET/SET FEATURES operations */ +int nand_onfi_get_set_features_notsupp(struct mtd_info *mtd, + struct nand_chip *chip, int addr, + u8 *subfeature_param); + /* Default read_page_raw implementation */ int nand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, uint8_t *buf, int oob_required, int page); -- cgit v1.2.3-59-g8ed1b From 8066360744743fb7f2dee1e2041fc9fc92f9d6b5 Mon Sep 17 00:00:00 2001 From: David Lowe Date: Sat, 22 Apr 2017 18:28:00 +0100 Subject: rtc: rtc-ds1307: enable support for mcp794xx as a wakeup source without IRQ This patch extends the fixes for ds1337, ds1339, ds3231 in commit 8bc2a40730ec ("rtc: ds1307: add support for the DT property 'wakeup-source'") to mcp794xx devices, so that those parts can similarly be used as a wakeup source without an IRQ to the processor. Tested on Raspberry Pi ZeroW with MCP79400. Signed-off-by: David Lowe Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ds1307.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index 94e13d703735..a264938500af 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -1407,7 +1407,8 @@ static int ds1307_probe(struct i2c_client *client, break; case mcp794xx: rtc_ops = &mcp794xx_rtc_ops; - if (ds1307->irq > 0 && chip->alarm) { + if (chip->alarm && (ds1307->irq > 0 || + ds1307_can_wakeup_device)) { irq_handler = mcp794xx_irq; want_irq = true; } -- cgit v1.2.3-59-g8ed1b From 2de9261c18c2b09a8025872bb470853dc8db726c Mon Sep 17 00:00:00 2001 From: Gary Bisson Date: Tue, 25 Apr 2017 16:45:14 +0200 Subject: rtc: m41t80: fix SQWE override when setting an alarm Currently setting an alarm clears the SQWE bit which means that the clock output is disabled no matter its previous state. Signed-off-by: Gary Bisson Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-m41t80.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/rtc/rtc-m41t80.c b/drivers/rtc/rtc-m41t80.c index 5ec4653022ff..b0749645aa48 100644 --- a/drivers/rtc/rtc-m41t80.c +++ b/drivers/rtc/rtc-m41t80.c @@ -332,6 +332,9 @@ static int m41t80_set_alarm(struct device *dev, struct rtc_wkalrm *alrm) return err; } + /* Keep SQWE bit value */ + alarmvals[0] |= (ret & M41T80_ALMON_SQWE); + ret = i2c_smbus_read_byte_data(client, M41T80_REG_FLAGS); if (ret < 0) return ret; -- cgit v1.2.3-59-g8ed1b From 0f546b058b86ea2f661cc7a6e931cee5a29959ef Mon Sep 17 00:00:00 2001 From: Gary Bisson Date: Tue, 25 Apr 2017 16:45:15 +0200 Subject: rtc: m41t80: fix SQW dividers override when setting a date This patch is only relevant for RTC with the SQ_ALT feature which means the clock output frequency divider is stored in the weekday register. Current implementation discards the previous dividers value and clear them as soon as the time is set. Signed-off-by: Gary Bisson Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-m41t80.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/rtc/rtc-m41t80.c b/drivers/rtc/rtc-m41t80.c index b0749645aa48..1e8ba7a469ac 100644 --- a/drivers/rtc/rtc-m41t80.c +++ b/drivers/rtc/rtc-m41t80.c @@ -227,6 +227,7 @@ static int m41t80_get_datetime(struct i2c_client *client, /* Sets the given date and time to the real time clock. */ static int m41t80_set_datetime(struct i2c_client *client, struct rtc_time *tm) { + struct m41t80_data *clientdata = i2c_get_clientdata(client); unsigned char buf[8]; int err, flags; @@ -242,6 +243,17 @@ static int m41t80_set_datetime(struct i2c_client *client, struct rtc_time *tm) buf[M41T80_REG_YEAR] = bin2bcd(tm->tm_year - 100); buf[M41T80_REG_WDAY] = tm->tm_wday; + /* If the square wave output is controlled in the weekday register */ + if (clientdata->features & M41T80_FEATURE_SQ_ALT) { + int val; + + val = i2c_smbus_read_byte_data(client, M41T80_REG_WDAY); + if (val < 0) + return val; + + buf[M41T80_REG_WDAY] |= (val & 0xf0); + } + err = i2c_smbus_write_i2c_block_data(client, M41T80_REG_SSEC, sizeof(buf), buf); if (err < 0) { -- cgit v1.2.3-59-g8ed1b From 17e296eb35dc5b15511ffa4ef5de67e53cb5a284 Mon Sep 17 00:00:00 2001 From: Gary Bisson Date: Tue, 25 Apr 2017 16:45:16 +0200 Subject: rtc: m41t80: remove sqw sysfs entry In order to use the proper clock framework to control this feature. Signed-off-by: Gary Bisson Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-m41t80.c | 88 ------------------------------------------------ 1 file changed, 88 deletions(-) diff --git a/drivers/rtc/rtc-m41t80.c b/drivers/rtc/rtc-m41t80.c index 1e8ba7a469ac..6145bc164162 100644 --- a/drivers/rtc/rtc-m41t80.c +++ b/drivers/rtc/rtc-m41t80.c @@ -446,96 +446,8 @@ static ssize_t flags_show(struct device *dev, } static DEVICE_ATTR_RO(flags); -static ssize_t sqwfreq_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct i2c_client *client = to_i2c_client(dev); - struct m41t80_data *clientdata = i2c_get_clientdata(client); - int val, reg_sqw; - - if (!(clientdata->features & M41T80_FEATURE_SQ)) - return -EINVAL; - - reg_sqw = M41T80_REG_SQW; - if (clientdata->features & M41T80_FEATURE_SQ_ALT) - reg_sqw = M41T80_REG_WDAY; - val = i2c_smbus_read_byte_data(client, reg_sqw); - if (val < 0) - return val; - val = (val >> 4) & 0xf; - switch (val) { - case 0: - break; - case 1: - val = 32768; - break; - default: - val = 32768 >> val; - } - return sprintf(buf, "%d\n", val); -} - -static ssize_t sqwfreq_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct i2c_client *client = to_i2c_client(dev); - struct m41t80_data *clientdata = i2c_get_clientdata(client); - int almon, sqw, reg_sqw, rc; - unsigned long val; - - rc = kstrtoul(buf, 0, &val); - if (rc < 0) - return rc; - - if (!(clientdata->features & M41T80_FEATURE_SQ)) - return -EINVAL; - - if (val) { - if (!is_power_of_2(val)) - return -EINVAL; - val = ilog2(val); - if (val == 15) - val = 1; - else if (val < 14) - val = 15 - val; - else - return -EINVAL; - } - /* disable SQW, set SQW frequency & re-enable */ - almon = i2c_smbus_read_byte_data(client, M41T80_REG_ALARM_MON); - if (almon < 0) - return almon; - reg_sqw = M41T80_REG_SQW; - if (clientdata->features & M41T80_FEATURE_SQ_ALT) - reg_sqw = M41T80_REG_WDAY; - sqw = i2c_smbus_read_byte_data(client, reg_sqw); - if (sqw < 0) - return sqw; - sqw = (sqw & 0x0f) | (val << 4); - - rc = i2c_smbus_write_byte_data(client, M41T80_REG_ALARM_MON, - almon & ~M41T80_ALMON_SQWE); - if (rc < 0) - return rc; - - if (val) { - rc = i2c_smbus_write_byte_data(client, reg_sqw, sqw); - if (rc < 0) - return rc; - - rc = i2c_smbus_write_byte_data(client, M41T80_REG_ALARM_MON, - almon | M41T80_ALMON_SQWE); - if (rc < 0) - return rc; - } - return count; -} -static DEVICE_ATTR_RW(sqwfreq); - static struct attribute *attrs[] = { &dev_attr_flags.attr, - &dev_attr_sqwfreq.attr, NULL, }; -- cgit v1.2.3-59-g8ed1b From 1373e77b4f108929caa448bb23f341a4af774cad Mon Sep 17 00:00:00 2001 From: Gary Bisson Date: Tue, 25 Apr 2017 16:45:17 +0200 Subject: rtc: m41t80: add clock provider support Some devices supported by the m41t80 driver have a programmable square-wave output signal (see M41T80_FEATURE_SQ). This enables to use this feature as a clock provider of common clock framework. Signed-off-by: Gary Bisson Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-m41t80.c | 172 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 172 insertions(+) diff --git a/drivers/rtc/rtc-m41t80.c b/drivers/rtc/rtc-m41t80.c index 6145bc164162..8940e9e43ea0 100644 --- a/drivers/rtc/rtc-m41t80.c +++ b/drivers/rtc/rtc-m41t80.c @@ -16,6 +16,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include +#include #include #include #include @@ -53,6 +54,8 @@ #define M41T80_ALARM_REG_SIZE \ (M41T80_REG_ALARM_SEC + 1 - M41T80_REG_ALARM_MON) +#define M41T80_SQW_MAX_FREQ 32768 + #define M41T80_SEC_ST BIT(7) /* ST: Stop Bit */ #define M41T80_ALMON_AFE BIT(7) /* AFE: AF Enable Bit */ #define M41T80_ALMON_SQWE BIT(6) /* SQWE: SQW Enable Bit */ @@ -147,7 +150,11 @@ MODULE_DEVICE_TABLE(of, m41t80_of_match); struct m41t80_data { unsigned long features; + struct i2c_client *client; struct rtc_device *rtc; +#ifdef CONFIG_COMMON_CLK + struct clk_hw sqw; +#endif }; static irqreturn_t m41t80_handle_irq(int irq, void *dev_id) @@ -455,6 +462,166 @@ static struct attribute_group attr_group = { .attrs = attrs, }; +#ifdef CONFIG_COMMON_CLK +#define sqw_to_m41t80_data(_hw) container_of(_hw, struct m41t80_data, sqw) + +static unsigned long m41t80_sqw_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct m41t80_data *m41t80 = sqw_to_m41t80_data(hw); + struct i2c_client *client = m41t80->client; + int reg_sqw = (m41t80->features & M41T80_FEATURE_SQ_ALT) ? + M41T80_REG_WDAY : M41T80_REG_SQW; + int ret = i2c_smbus_read_byte_data(client, reg_sqw); + unsigned long val = M41T80_SQW_MAX_FREQ; + + if (ret < 0) + return 0; + + ret >>= 4; + if (ret == 0) + val = 0; + else if (ret > 1) + val = val / (1 << ret); + + return val; +} + +static long m41t80_sqw_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *prate) +{ + int i, freq = M41T80_SQW_MAX_FREQ; + + if (freq <= rate) + return freq; + + for (i = 2; i <= ilog2(M41T80_SQW_MAX_FREQ); i++) { + freq /= 1 << i; + if (freq <= rate) + return freq; + } + + return 0; +} + +static int m41t80_sqw_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct m41t80_data *m41t80 = sqw_to_m41t80_data(hw); + struct i2c_client *client = m41t80->client; + int reg_sqw = (m41t80->features & M41T80_FEATURE_SQ_ALT) ? + M41T80_REG_WDAY : M41T80_REG_SQW; + int reg, ret, val = 0; + + if (rate) { + if (!is_power_of_2(rate)) + return -EINVAL; + val = ilog2(rate); + if (val == ilog2(M41T80_SQW_MAX_FREQ)) + val = 1; + else if (val < (ilog2(M41T80_SQW_MAX_FREQ) - 1)) + val = ilog2(M41T80_SQW_MAX_FREQ) - val; + else + return -EINVAL; + } + + reg = i2c_smbus_read_byte_data(client, reg_sqw); + if (reg < 0) + return reg; + + reg = (reg & 0x0f) | (val << 4); + + ret = i2c_smbus_write_byte_data(client, reg_sqw, reg); + if (ret < 0) + return ret; + + return -EINVAL; +} + +static int m41t80_sqw_control(struct clk_hw *hw, bool enable) +{ + struct m41t80_data *m41t80 = sqw_to_m41t80_data(hw); + struct i2c_client *client = m41t80->client; + int ret = i2c_smbus_read_byte_data(client, M41T80_REG_ALARM_MON); + + if (ret < 0) + return ret; + + if (enable) + ret |= M41T80_ALMON_SQWE; + else + ret &= ~M41T80_ALMON_SQWE; + + return i2c_smbus_write_byte_data(client, M41T80_REG_ALARM_MON, ret); +} + +static int m41t80_sqw_prepare(struct clk_hw *hw) +{ + return m41t80_sqw_control(hw, 1); +} + +static void m41t80_sqw_unprepare(struct clk_hw *hw) +{ + m41t80_sqw_control(hw, 0); +} + +static int m41t80_sqw_is_prepared(struct clk_hw *hw) +{ + struct m41t80_data *m41t80 = sqw_to_m41t80_data(hw); + struct i2c_client *client = m41t80->client; + int ret = i2c_smbus_read_byte_data(client, M41T80_REG_ALARM_MON); + + if (ret < 0) + return ret; + + return !!(ret & M41T80_ALMON_SQWE); +} + +static const struct clk_ops m41t80_sqw_ops = { + .prepare = m41t80_sqw_prepare, + .unprepare = m41t80_sqw_unprepare, + .is_prepared = m41t80_sqw_is_prepared, + .recalc_rate = m41t80_sqw_recalc_rate, + .round_rate = m41t80_sqw_round_rate, + .set_rate = m41t80_sqw_set_rate, +}; + +static struct clk *m41t80_sqw_register_clk(struct m41t80_data *m41t80) +{ + struct i2c_client *client = m41t80->client; + struct device_node *node = client->dev.of_node; + struct clk *clk; + struct clk_init_data init; + int ret; + + /* First disable the clock */ + ret = i2c_smbus_read_byte_data(client, M41T80_REG_ALARM_MON); + if (ret < 0) + return ERR_PTR(ret); + ret = i2c_smbus_write_byte_data(client, M41T80_REG_ALARM_MON, + ret & ~(M41T80_ALMON_SQWE)); + if (ret < 0) + return ERR_PTR(ret); + + init.name = "m41t80-sqw"; + init.ops = &m41t80_sqw_ops; + init.flags = 0; + init.parent_names = NULL; + init.num_parents = 0; + m41t80->sqw.init = &init; + + /* optional override of the clockname */ + of_property_read_string(node, "clock-output-names", &init.name); + + /* register the clock */ + clk = clk_register(&client->dev, &m41t80->sqw); + if (!IS_ERR(clk)) + of_clk_add_provider(node, of_clk_src_simple_get, clk); + + return clk; +} +#endif + #ifdef CONFIG_RTC_DRV_M41T80_WDT /* ***************************************************************************** @@ -772,6 +939,7 @@ static int m41t80_probe(struct i2c_client *client, if (!m41t80_data) return -ENOMEM; + m41t80_data->client = client; if (client->dev.of_node) m41t80_data->features = (unsigned long) of_device_get_match_data(&client->dev); @@ -863,6 +1031,10 @@ static int m41t80_probe(struct i2c_client *client, return rc; } } +#endif +#ifdef CONFIG_COMMON_CLK + if (m41t80_data->features & M41T80_FEATURE_SQ) + m41t80_sqw_register_clk(m41t80_data); #endif return 0; } -- cgit v1.2.3-59-g8ed1b From 6dc1cf6f932bb0ea4d8f5e913a0a401ecacd2f03 Mon Sep 17 00:00:00 2001 From: Vaibhav Jain Date: Fri, 19 May 2017 15:35:09 +0530 Subject: rtc: opal: Handle disabled TPO in opal_get_tpo_time() On PowerNV platform when Timed-Power-On(TPO) is disabled, read of stored TPO yields value with all date components set to '0' inside opal_get_tpo_time(). The function opal_to_tm() then converts it to an offset from year 1900 yielding alarm-time == "1900-00-01 00:00:00". This causes problems with __rtc_read_alarm() that expecting an offset from "1970-00-01 00:00:00" and returned alarm-time results in a -ve value for time64_t. Which ultimately results in this error reported in kernel logs with a seemingly garbage value: "rtc rtc0: invalid alarm value: -2-1--1041528741 2005511117:71582844:32" We fix this by explicitly handling the case of all alarm date-time components being '0' inside opal_get_tpo_time() and returning -ENOENT in such a case. This signals generic rtc that no alarm is set and it bails out from the alarm initialization flow without reporting the above error. Signed-off-by: Vaibhav Jain Reported-by: Steve Best Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-opal.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/rtc/rtc-opal.c b/drivers/rtc/rtc-opal.c index ea20f627dabe..2d84e2a28772 100644 --- a/drivers/rtc/rtc-opal.c +++ b/drivers/rtc/rtc-opal.c @@ -142,6 +142,16 @@ static int opal_get_tpo_time(struct device *dev, struct rtc_wkalrm *alarm) y_m_d = be32_to_cpu(__y_m_d); h_m_s_ms = ((u64)be32_to_cpu(__h_m) << 32); + + /* check if no alarm is set */ + if (y_m_d == 0 && h_m_s_ms == 0) { + pr_debug("No alarm is set\n"); + rc = -ENOENT; + goto exit; + } else { + pr_debug("Alarm set to %x %llx\n", y_m_d, h_m_s_ms); + } + opal_to_tm(y_m_d, h_m_s_ms, &alarm->time); exit: -- cgit v1.2.3-59-g8ed1b From da96aea0ed177105cb13ee83b328f6c61e061d3f Mon Sep 17 00:00:00 2001 From: Vaibhav Jain Date: Fri, 19 May 2017 22:18:55 +0530 Subject: rtc: interface: Validate alarm-time before handling rollover In function __rtc_read_alarm() its possible for an alarm time-stamp to be invalid even after replacing missing components with current time-stamp. The condition 'alarm->time.tm_year < 70' will trigger this case and will cause the call to 'rtc_tm_to_time64(&alarm->time)' return a negative value for variable t_alm. While handling alarm rollover this negative t_alm (assumed to seconds offset from '1970-01-01 00:00:00') is converted back to rtc_time via rtc_time64_to_tm() which results in this error log with seemingly garbage values: "rtc rtc0: invalid alarm value: -2-1--1041528741 2005511117:71582844:32" This error was generated when the rtc driver (rtc-opal in this case) returned an alarm time-stamp of '00-00-00 00:00:00' to indicate that the alarm is disabled. Though I have submitted a separate fix for the rtc-opal driver, this issue may potentially impact other existing/future rtc drivers. To fix this issue the patch validates the alarm time-stamp just after filling up the missing datetime components and if rtc_valid_tm() still reports it to be invalid then bails out of the function without handling the rollover. Reported-by: Steve Best Signed-off-by: Vaibhav Jain Signed-off-by: Alexandre Belloni --- drivers/rtc/interface.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index fc0fa7577636..8cec9a02c0b8 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -227,6 +227,13 @@ int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) missing = year; } + /* Can't proceed if alarm is still invalid after replacing + * missing fields. + */ + err = rtc_valid_tm(&alarm->time); + if (err) + goto done; + /* with luck, no rollover is needed */ t_now = rtc_tm_to_time64(&now); t_alm = rtc_tm_to_time64(&alarm->time); @@ -278,9 +285,9 @@ int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) dev_warn(&rtc->dev, "alarm rollover not handled\n"); } -done: err = rtc_valid_tm(&alarm->time); +done: if (err) { dev_warn(&rtc->dev, "invalid alarm value: %d-%d-%d %d:%d:%d\n", alarm->time.tm_year + 1900, alarm->time.tm_mon + 1, -- cgit v1.2.3-59-g8ed1b From a21512c1698d8106bcece0d24ff590dc92682678 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 18 May 2017 22:25:56 -0300 Subject: rtc.txt: standardize document format Each text file under Documentation follows a different format. Some doesn't even have titles! Change its representation to follow the adopted standard, using ReST markups for it to be parseable by Sphinx: - adjust identation of the titles; - mark a table as such; - don't capitalize chapter names. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Alexandre Belloni --- Documentation/rtc.txt | 44 +++++++++++++++++++++++--------------------- 1 file changed, 23 insertions(+), 21 deletions(-) diff --git a/Documentation/rtc.txt b/Documentation/rtc.txt index ddc366026e00..47feb4414b7e 100644 --- a/Documentation/rtc.txt +++ b/Documentation/rtc.txt @@ -1,6 +1,6 @@ - - Real Time Clock (RTC) Drivers for Linux - ======================================= +======================================= +Real Time Clock (RTC) Drivers for Linux +======================================= When Linux developers talk about a "Real Time Clock", they usually mean something that tracks wall clock time and is battery backed so that it @@ -32,8 +32,8 @@ only issue an alarm up to 24 hours in the future, other hardware may be able to schedule one any time in the upcoming century. - Old PC/AT-Compatible driver: /dev/rtc - -------------------------------------- +Old PC/AT-Compatible driver: /dev/rtc +-------------------------------------- All PCs (even Alpha machines) have a Real Time Clock built into them. Usually they are built into the chipset of the computer, but some may @@ -105,8 +105,8 @@ that will be using this driver. See the code at the end of this document. (The original /dev/rtc driver was written by Paul Gortmaker.) - New portable "RTC Class" drivers: /dev/rtcN - -------------------------------------------- +New portable "RTC Class" drivers: /dev/rtcN +-------------------------------------------- Because Linux supports many non-ACPI and non-PC platforms, some of which have more than one RTC style clock, it needed a more portable solution @@ -136,35 +136,37 @@ a high functionality RTC is integrated into the SOC. That system might read the system clock from the discrete RTC, but use the integrated one for all other tasks, because of its greater functionality. -SYSFS INTERFACE +SYSFS interface --------------- The sysfs interface under /sys/class/rtc/rtcN provides access to various rtc attributes without requiring the use of ioctls. All dates and times are in the RTC's timezone, rather than in system time. -date: RTC-provided date -hctosys: 1 if the RTC provided the system time at boot via the +================ ============================================================== +date RTC-provided date +hctosys 1 if the RTC provided the system time at boot via the CONFIG_RTC_HCTOSYS kernel option, 0 otherwise -max_user_freq: The maximum interrupt rate an unprivileged user may request +max_user_freq The maximum interrupt rate an unprivileged user may request from this RTC. -name: The name of the RTC corresponding to this sysfs directory -since_epoch: The number of seconds since the epoch according to the RTC -time: RTC-provided time -wakealarm: The time at which the clock will generate a system wakeup +name The name of the RTC corresponding to this sysfs directory +since_epoch The number of seconds since the epoch according to the RTC +time RTC-provided time +wakealarm The time at which the clock will generate a system wakeup event. This is a one shot wakeup event, so must be reset - after wake if a daily wakeup is required. Format is seconds since - the epoch by default, or if there's a leading +, seconds in the - future, or if there is a leading +=, seconds ahead of the current - alarm. -offset: The amount which the rtc clock has been adjusted in firmware. + after wake if a daily wakeup is required. Format is seconds + since the epoch by default, or if there's a leading +, seconds + in the future, or if there is a leading +=, seconds ahead of + the current alarm. +offset The amount which the rtc clock has been adjusted in firmware. Visible only if the driver supports clock offset adjustment. The unit is parts per billion, i.e. The number of clock ticks which are added to or removed from the rtc's base clock per billion ticks. A positive value makes a day pass more slowly, longer, and a negative value makes a day pass more quickly. +================ ============================================================== -IOCTL INTERFACE +IOCTL interface --------------- The ioctl() calls supported by /dev/rtc are also supported by the RTC class -- cgit v1.2.3-59-g8ed1b From 2d7b56378d32b0cf006f8944cbba4046df45dd25 Mon Sep 17 00:00:00 2001 From: Caesar Wang Date: Wed, 31 May 2017 10:14:23 +0800 Subject: drm/rockchip: gem: add the lacks lock and trivial changes As the allocation and free buffer that need to add mutex lock for drm mm, but it lacks the locking on error path in rockchip_gem_iommu_map(). Also, the trivial changes like The comment should be placed in the kerneldoc and unused blank line. Signed-off-by: Caesar Wang Reviewed-by: Mark Yao Signed-off-by: Mark Yao Link: http://patchwork.freedesktop.org/patch/msgid/1496196863-25738-1-git-send-email-wxt@rock-chips.com --- drivers/gpu/drm/rockchip/rockchip_drm_drv.h | 2 +- drivers/gpu/drm/rockchip/rockchip_drm_gem.c | 5 +++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.h b/drivers/gpu/drm/rockchip/rockchip_drm_drv.h index a48fcce3f5f6..4a7a3107d874 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.h +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.h @@ -45,13 +45,13 @@ struct rockchip_crtc_state { * * @crtc: array of enabled CRTCs, used to map from "pipe" to drm_crtc. * @num_pipe: number of pipes for this device. + * @mm_lock: protect drm_mm on multi-threads. */ struct rockchip_drm_private { struct drm_fb_helper fbdev_helper; struct drm_gem_object *fbdev_bo; struct drm_atomic_state *state; struct iommu_domain *domain; - /* protect drm_mm on multi-threads */ struct mutex mm_lock; struct drm_mm mm; struct list_head psr_list; diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c index df9e57064f19..b74ac717e56a 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c @@ -29,12 +29,11 @@ static int rockchip_gem_iommu_map(struct rockchip_gem_object *rk_obj) ssize_t ret; mutex_lock(&private->mm_lock); - ret = drm_mm_insert_node_generic(&private->mm, &rk_obj->mm, rk_obj->base.size, PAGE_SIZE, 0, 0); - mutex_unlock(&private->mm_lock); + if (ret < 0) { DRM_ERROR("out of I/O virtual memory: %zd\n", ret); return ret; @@ -56,7 +55,9 @@ static int rockchip_gem_iommu_map(struct rockchip_gem_object *rk_obj) return 0; err_remove_node: + mutex_lock(&private->mm_lock); drm_mm_remove_node(&rk_obj->mm); + mutex_unlock(&private->mm_lock); return ret; } -- cgit v1.2.3-59-g8ed1b From 9748e1d87573c94191442d6bd0307f523e5cd8b8 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Sat, 29 Apr 2017 11:06:45 +0200 Subject: mtd: nand: add support for Micron on-die ECC Now that the core NAND subsystem has support for on-die ECC, this commit brings the necessary code to support on-die ECC on Micron NANDs. In micron_nand_init(), we detect if the Micron NAND chip supports on-die ECC mode, by checking a number of conditions: - It must be an ONFI NAND - It must be a SLC NAND - Enabling *and* disabling on-die ECC must work - The on-die ECC must be correcting 4 bits per 512 bytes of data. Some Micron NAND chips have an on-die ECC able to correct 8 bits per 512 bytes of data, but they work slightly differently and therefore we don't support them in this patch. Then, if the on-die ECC cannot be disabled (some Micron NAND have on-die ECC forcefully enabled), we bail out, as we don't support such NANDs. Indeed, the implementation of raw_read()/raw_write() make the assumption that on-die ECC can be disabled. Support for Micron NANDs with on-die ECC forcefully enabled can easily be added, but in the absence of such HW for testing, we preferred to simply bail out. If the on-die ECC is supported, and requested in the Device Tree, then it is indeed enabled, by using custom implementations of the ->read_page(), ->read_page_raw(), ->write_page() and ->write_page_raw() operation to properly handle the on-die ECC. In the non-raw functions, we need to enable the internal ECC engine before issuing the NAND_CMD_READ0 or NAND_CMD_SEQIN commands, which is why we set the NAND_ECC_CUSTOM_PAGE_ACCESS option at initialization time (it asks the NAND core to let the NAND driver issue those commands). Signed-off-by: Thomas Petazzoni Signed-off-by: Boris Brezillon --- drivers/mtd/nand/nand_micron.c | 216 +++++++++++++++++++++++++++++++++++++++++ include/linux/mtd/nand.h | 2 + 2 files changed, 218 insertions(+) diff --git a/drivers/mtd/nand/nand_micron.c b/drivers/mtd/nand/nand_micron.c index 877011069251..9993f8ead1e2 100644 --- a/drivers/mtd/nand/nand_micron.c +++ b/drivers/mtd/nand/nand_micron.c @@ -17,6 +17,12 @@ #include +/* + * Special Micron status bit that indicates when the block has been + * corrected by on-die ECC and should be rewritten + */ +#define NAND_STATUS_WRITE_RECOMMENDED BIT(3) + struct nand_onfi_vendor_micron { u8 two_plane_read; u8 read_cache; @@ -66,9 +72,191 @@ static int micron_nand_onfi_init(struct nand_chip *chip) return 0; } +static int micron_nand_on_die_ooblayout_ecc(struct mtd_info *mtd, int section, + struct mtd_oob_region *oobregion) +{ + if (section >= 4) + return -ERANGE; + + oobregion->offset = (section * 16) + 8; + oobregion->length = 8; + + return 0; +} + +static int micron_nand_on_die_ooblayout_free(struct mtd_info *mtd, int section, + struct mtd_oob_region *oobregion) +{ + if (section >= 4) + return -ERANGE; + + oobregion->offset = (section * 16) + 2; + oobregion->length = 6; + + return 0; +} + +static const struct mtd_ooblayout_ops micron_nand_on_die_ooblayout_ops = { + .ecc = micron_nand_on_die_ooblayout_ecc, + .free = micron_nand_on_die_ooblayout_free, +}; + +static int micron_nand_on_die_ecc_setup(struct nand_chip *chip, bool enable) +{ + u8 feature[ONFI_SUBFEATURE_PARAM_LEN] = { 0, }; + + if (enable) + feature[0] |= ONFI_FEATURE_ON_DIE_ECC_EN; + + return chip->onfi_set_features(nand_to_mtd(chip), chip, + ONFI_FEATURE_ON_DIE_ECC, feature); +} + +static int +micron_nand_read_page_on_die_ecc(struct mtd_info *mtd, struct nand_chip *chip, + uint8_t *buf, int oob_required, + int page) +{ + int status; + int max_bitflips = 0; + + micron_nand_on_die_ecc_setup(chip, true); + + chip->cmdfunc(mtd, NAND_CMD_READ0, 0x00, page); + chip->cmdfunc(mtd, NAND_CMD_STATUS, -1, -1); + status = chip->read_byte(mtd); + if (status & NAND_STATUS_FAIL) + mtd->ecc_stats.failed++; + /* + * The internal ECC doesn't tell us the number of bitflips + * that have been corrected, but tells us if it recommends to + * rewrite the block. If it's the case, then we pretend we had + * a number of bitflips equal to the ECC strength, which will + * hint the NAND core to rewrite the block. + */ + else if (status & NAND_STATUS_WRITE_RECOMMENDED) + max_bitflips = chip->ecc.strength; + + chip->cmdfunc(mtd, NAND_CMD_READ0, -1, -1); + + nand_read_page_raw(mtd, chip, buf, oob_required, page); + + micron_nand_on_die_ecc_setup(chip, false); + + return max_bitflips; +} + +static int +micron_nand_write_page_on_die_ecc(struct mtd_info *mtd, struct nand_chip *chip, + const uint8_t *buf, int oob_required, + int page) +{ + micron_nand_on_die_ecc_setup(chip, true); + + chip->cmdfunc(mtd, NAND_CMD_SEQIN, 0x00, page); + nand_write_page_raw(mtd, chip, buf, oob_required, page); + chip->cmdfunc(mtd, NAND_CMD_PAGEPROG, -1, -1); + + micron_nand_on_die_ecc_setup(chip, false); + + return 0; +} + +static int +micron_nand_read_page_raw_on_die_ecc(struct mtd_info *mtd, + struct nand_chip *chip, + uint8_t *buf, int oob_required, + int page) +{ + chip->cmdfunc(mtd, NAND_CMD_READ0, 0x00, page); + nand_read_page_raw(mtd, chip, buf, oob_required, page); + + return 0; +} + +static int +micron_nand_write_page_raw_on_die_ecc(struct mtd_info *mtd, + struct nand_chip *chip, + const uint8_t *buf, int oob_required, + int page) +{ + chip->cmdfunc(mtd, NAND_CMD_SEQIN, 0x00, page); + nand_write_page_raw(mtd, chip, buf, oob_required, page); + chip->cmdfunc(mtd, NAND_CMD_PAGEPROG, -1, -1); + + return 0; +} + +enum { + /* The NAND flash doesn't support on-die ECC */ + MICRON_ON_DIE_UNSUPPORTED, + + /* + * The NAND flash supports on-die ECC and it can be + * enabled/disabled by a set features command. + */ + MICRON_ON_DIE_SUPPORTED, + + /* + * The NAND flash supports on-die ECC, and it cannot be + * disabled. + */ + MICRON_ON_DIE_MANDATORY, +}; + +/* + * Try to detect if the NAND support on-die ECC. To do this, we enable + * the feature, and read back if it has been enabled as expected. We + * also check if it can be disabled, because some Micron NANDs do not + * allow disabling the on-die ECC and we don't support such NANDs for + * now. + * + * This function also has the side effect of disabling on-die ECC if + * it had been left enabled by the firmware/bootloader. + */ +static int micron_supports_on_die_ecc(struct nand_chip *chip) +{ + u8 feature[ONFI_SUBFEATURE_PARAM_LEN] = { 0, }; + int ret; + + if (chip->onfi_version == 0) + return MICRON_ON_DIE_UNSUPPORTED; + + if (chip->bits_per_cell != 1) + return MICRON_ON_DIE_UNSUPPORTED; + + ret = micron_nand_on_die_ecc_setup(chip, true); + if (ret) + return MICRON_ON_DIE_UNSUPPORTED; + + chip->onfi_get_features(nand_to_mtd(chip), chip, + ONFI_FEATURE_ON_DIE_ECC, feature); + if ((feature[0] & ONFI_FEATURE_ON_DIE_ECC_EN) == 0) + return MICRON_ON_DIE_UNSUPPORTED; + + ret = micron_nand_on_die_ecc_setup(chip, false); + if (ret) + return MICRON_ON_DIE_UNSUPPORTED; + + chip->onfi_get_features(nand_to_mtd(chip), chip, + ONFI_FEATURE_ON_DIE_ECC, feature); + if (feature[0] & ONFI_FEATURE_ON_DIE_ECC_EN) + return MICRON_ON_DIE_MANDATORY; + + /* + * Some Micron NANDs have an on-die ECC of 4/512, some other + * 8/512. We only support the former. + */ + if (chip->onfi_params.ecc_bits != 4) + return MICRON_ON_DIE_UNSUPPORTED; + + return MICRON_ON_DIE_SUPPORTED; +} + static int micron_nand_init(struct nand_chip *chip) { struct mtd_info *mtd = nand_to_mtd(chip); + int ondie; int ret; ret = micron_nand_onfi_init(chip); @@ -78,6 +266,34 @@ static int micron_nand_init(struct nand_chip *chip) if (mtd->writesize == 2048) chip->bbt_options |= NAND_BBT_SCAN2NDPAGE; + ondie = micron_supports_on_die_ecc(chip); + + if (ondie == MICRON_ON_DIE_MANDATORY) { + pr_err("On-die ECC forcefully enabled, not supported\n"); + return -EINVAL; + } + + if (chip->ecc.mode == NAND_ECC_ON_DIE) { + if (ondie == MICRON_ON_DIE_UNSUPPORTED) { + pr_err("On-die ECC selected but not supported\n"); + return -EINVAL; + } + + chip->ecc.options = NAND_ECC_CUSTOM_PAGE_ACCESS; + chip->ecc.bytes = 8; + chip->ecc.size = 512; + chip->ecc.strength = 4; + chip->ecc.algo = NAND_ECC_BCH; + chip->ecc.read_page = micron_nand_read_page_on_die_ecc; + chip->ecc.write_page = micron_nand_write_page_on_die_ecc; + chip->ecc.read_page_raw = + micron_nand_read_page_raw_on_die_ecc; + chip->ecc.write_page_raw = + micron_nand_write_page_raw_on_die_ecc; + + mtd_set_ooblayout(mtd, µn_nand_on_die_ooblayout_ops); + } + return 0; } diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 28f7dd9177e9..893d0ce08030 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -258,6 +258,8 @@ struct nand_chip; /* Vendor-specific feature address (Micron) */ #define ONFI_FEATURE_ADDR_READ_RETRY 0x89 +#define ONFI_FEATURE_ON_DIE_ECC 0x90 +#define ONFI_FEATURE_ON_DIE_ECC_EN BIT(3) /* ONFI subfeature parameters length */ #define ONFI_SUBFEATURE_PARAM_LEN 4 -- cgit v1.2.3-59-g8ed1b From 838ff7b333263abc9e7e026bb225ed66511f450f Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Sat, 29 Apr 2017 11:06:46 +0200 Subject: mtd: nand: fsmc_nand: handle on-die ECC case This commit adjusts the fsmc_nand driver so that it accepts the NAND_ECC_ON_DIE case. It simply does nothing in this case, since both the ECC operations and OOB layout will be defined by the NAND chip code rather than by the NAND controller code. Signed-off-by: Thomas Petazzoni Reviewed-by: Richard Weinberger Signed-off-by: Boris Brezillon --- drivers/mtd/nand/fsmc_nand.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/mtd/nand/fsmc_nand.c b/drivers/mtd/nand/fsmc_nand.c index f58c912fdf3b..de57554b8c4f 100644 --- a/drivers/mtd/nand/fsmc_nand.c +++ b/drivers/mtd/nand/fsmc_nand.c @@ -1055,6 +1055,9 @@ static int __init fsmc_nand_probe(struct platform_device *pdev) break; } + case NAND_ECC_ON_DIE: + break; + default: dev_err(&pdev->dev, "Unsupported ECC mode!\n"); goto err_probe; -- cgit v1.2.3-59-g8ed1b From 086567f12e1188c57e061a53825a5eff5a7923a0 Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Fri, 21 Apr 2017 12:51:07 +0200 Subject: mtd: nand: Optimize checking of erased buffers If we see ~0UL in flash, there's no need for hweight, and no need to check number of bitflips. So this should be net win. Signed-off-by: Pavel Machek Signed-off-by: Boris Brezillon --- drivers/mtd/nand/nand_base.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index ed08e3946727..79d98c9fa8a7 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -1421,7 +1421,10 @@ static int nand_check_erased_buf(void *buf, int len, int bitflips_threshold) for (; len >= sizeof(long); len -= sizeof(long), bitmap += sizeof(long)) { - weight = hweight_long(*((unsigned long *)bitmap)); + unsigned long d = *((unsigned long *)bitmap); + if (d == ~0UL) + continue; + weight = hweight_long(d); bitflips += BITS_PER_LONG - weight; if (unlikely(bitflips > bitflips_threshold)) return -EBADMSG; -- cgit v1.2.3-59-g8ed1b From 6b7ee72149a4a6963e361c5324cea2961f17989a Mon Sep 17 00:00:00 2001 From: Stefan Agner Date: Fri, 21 Apr 2017 18:23:34 -0700 Subject: mtd: nand: gpmi: unify clock handling Add device specific list of clocks required, and handle all clocks in a single for loop. This avoids further code duplication when adding i.MX 7 support. Signed-off-by: Stefan Agner Reviewed-by: Marek Vasut Signed-off-by: Boris Brezillon --- drivers/mtd/nand/gpmi-nand/gpmi-nand.c | 41 +++++++++++++++------------------- drivers/mtd/nand/gpmi-nand/gpmi-nand.h | 2 ++ 2 files changed, 20 insertions(+), 23 deletions(-) diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c index d52139635b67..c8bbf5da2ab8 100644 --- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c +++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c @@ -82,6 +82,10 @@ static int gpmi_ooblayout_free(struct mtd_info *mtd, int section, return 0; } +static const char * const gpmi_clks_for_mx2x[] = { + "gpmi_io", +}; + static const struct mtd_ooblayout_ops gpmi_ooblayout_ops = { .ecc = gpmi_ooblayout_ecc, .free = gpmi_ooblayout_free, @@ -91,24 +95,36 @@ static const struct gpmi_devdata gpmi_devdata_imx23 = { .type = IS_MX23, .bch_max_ecc_strength = 20, .max_chain_delay = 16, + .clks = gpmi_clks_for_mx2x, + .clks_count = ARRAY_SIZE(gpmi_clks_for_mx2x), }; static const struct gpmi_devdata gpmi_devdata_imx28 = { .type = IS_MX28, .bch_max_ecc_strength = 20, .max_chain_delay = 16, + .clks = gpmi_clks_for_mx2x, + .clks_count = ARRAY_SIZE(gpmi_clks_for_mx2x), +}; + +static const char * const gpmi_clks_for_mx6[] = { + "gpmi_io", "gpmi_apb", "gpmi_bch", "gpmi_bch_apb", "per1_bch", }; static const struct gpmi_devdata gpmi_devdata_imx6q = { .type = IS_MX6Q, .bch_max_ecc_strength = 40, .max_chain_delay = 12, + .clks = gpmi_clks_for_mx6, + .clks_count = ARRAY_SIZE(gpmi_clks_for_mx6), }; static const struct gpmi_devdata gpmi_devdata_imx6sx = { .type = IS_MX6SX, .bch_max_ecc_strength = 62, .max_chain_delay = 12, + .clks = gpmi_clks_for_mx6, + .clks_count = ARRAY_SIZE(gpmi_clks_for_mx6), }; static irqreturn_t bch_irq(int irq, void *cookie) @@ -599,35 +615,14 @@ acquire_err: return -EINVAL; } -static char *extra_clks_for_mx6q[GPMI_CLK_MAX] = { - "gpmi_apb", "gpmi_bch", "gpmi_bch_apb", "per1_bch", -}; - static int gpmi_get_clks(struct gpmi_nand_data *this) { struct resources *r = &this->resources; - char **extra_clks = NULL; struct clk *clk; int err, i; - /* The main clock is stored in the first. */ - r->clock[0] = devm_clk_get(this->dev, "gpmi_io"); - if (IS_ERR(r->clock[0])) { - err = PTR_ERR(r->clock[0]); - goto err_clock; - } - - /* Get extra clocks */ - if (GPMI_IS_MX6(this)) - extra_clks = extra_clks_for_mx6q; - if (!extra_clks) - return 0; - - for (i = 1; i < GPMI_CLK_MAX; i++) { - if (extra_clks[i - 1] == NULL) - break; - - clk = devm_clk_get(this->dev, extra_clks[i - 1]); + for (i = 0; i < this->devdata->clks_count; i++) { + clk = devm_clk_get(this->dev, this->devdata->clks[i]); if (IS_ERR(clk)) { err = PTR_ERR(clk); goto err_clock; diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.h b/drivers/mtd/nand/gpmi-nand/gpmi-nand.h index 4e49a1f5fa27..8879c4eff25e 100644 --- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.h +++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.h @@ -130,6 +130,8 @@ struct gpmi_devdata { enum gpmi_type type; int bch_max_ecc_strength; int max_chain_delay; /* See the async EDO mode */ + const char * const *clks; + const int clks_count; }; struct gpmi_nand_data { -- cgit v1.2.3-59-g8ed1b From b4af694f1c51f035f70fe964e4859bd9dbaa52b8 Mon Sep 17 00:00:00 2001 From: Stefan Agner Date: Fri, 21 Apr 2017 18:23:35 -0700 Subject: mtd: nand: gpmi: add i.MX 7 SoC support Add support for i.MX 7 SoC. The i.MX 7 has a slightly different clock architecture requiring only two clocks to be referenced. The IP is slightly different compared to i.MX 6, but currently none of this differences are in use, therefore reuse GPMI_IS_MX6. Signed-off-by: Stefan Agner Reviewed-by: Marek Vasut Signed-off-by: Boris Brezillon --- drivers/mtd/nand/gpmi-nand/gpmi-nand.c | 15 +++++++++++++++ drivers/mtd/nand/gpmi-nand/gpmi-nand.h | 7 +++++-- 2 files changed, 20 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c index c8bbf5da2ab8..9b777be633a9 100644 --- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c +++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c @@ -127,6 +127,18 @@ static const struct gpmi_devdata gpmi_devdata_imx6sx = { .clks_count = ARRAY_SIZE(gpmi_clks_for_mx6), }; +static const char * const gpmi_clks_for_mx7d[] = { + "gpmi_io", "gpmi_bch_apb", +}; + +static const struct gpmi_devdata gpmi_devdata_imx7d = { + .type = IS_MX7D, + .bch_max_ecc_strength = 62, + .max_chain_delay = 12, + .clks = gpmi_clks_for_mx7d, + .clks_count = ARRAY_SIZE(gpmi_clks_for_mx7d), +}; + static irqreturn_t bch_irq(int irq, void *cookie) { struct gpmi_nand_data *this = cookie; @@ -2071,6 +2083,9 @@ static const struct of_device_id gpmi_nand_id_table[] = { }, { .compatible = "fsl,imx6sx-gpmi-nand", .data = &gpmi_devdata_imx6sx, + }, { + .compatible = "fsl,imx7d-gpmi-nand", + .data = &gpmi_devdata_imx7d, }, {} }; MODULE_DEVICE_TABLE(of, gpmi_nand_id_table); diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.h b/drivers/mtd/nand/gpmi-nand/gpmi-nand.h index 8879c4eff25e..e88a45a62ab6 100644 --- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.h +++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.h @@ -123,7 +123,8 @@ enum gpmi_type { IS_MX23, IS_MX28, IS_MX6Q, - IS_MX6SX + IS_MX6SX, + IS_MX7D, }; struct gpmi_devdata { @@ -307,6 +308,8 @@ void gpmi_copy_bits(u8 *dst, size_t dst_bit_off, #define GPMI_IS_MX28(x) ((x)->devdata->type == IS_MX28) #define GPMI_IS_MX6Q(x) ((x)->devdata->type == IS_MX6Q) #define GPMI_IS_MX6SX(x) ((x)->devdata->type == IS_MX6SX) +#define GPMI_IS_MX7D(x) ((x)->devdata->type == IS_MX7D) -#define GPMI_IS_MX6(x) (GPMI_IS_MX6Q(x) || GPMI_IS_MX6SX(x)) +#define GPMI_IS_MX6(x) (GPMI_IS_MX6Q(x) || GPMI_IS_MX6SX(x) || \ + GPMI_IS_MX7D(x)) #endif -- cgit v1.2.3-59-g8ed1b From d7e578c8118113789b7abd2977e208c64d6f8465 Mon Sep 17 00:00:00 2001 From: Stefan Agner Date: Fri, 21 Apr 2017 18:23:36 -0700 Subject: mtd: gpmi: document current clock requirements The clock requirements are completely missing, add the clocks currently required by the driver. Signed-off-by: Stefan Agner Acked-by: Rob Herring Signed-off-by: Boris Brezillon --- Documentation/devicetree/bindings/mtd/gpmi-nand.txt | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/mtd/gpmi-nand.txt b/Documentation/devicetree/bindings/mtd/gpmi-nand.txt index d02acaff3c35..b289ef3c1b7e 100644 --- a/Documentation/devicetree/bindings/mtd/gpmi-nand.txt +++ b/Documentation/devicetree/bindings/mtd/gpmi-nand.txt @@ -4,7 +4,12 @@ The GPMI nand controller provides an interface to control the NAND flash chips. Required properties: - - compatible : should be "fsl,-gpmi-nand" + - compatible : should be "fsl,-gpmi-nand", chip can be: + * imx23 + * imx28 + * imx6q + * imx6sx + * imx7d - reg : should contain registers location and length for gpmi and bch. - reg-names: Should contain the reg names "gpmi-nand" and "bch" - interrupts : BCH interrupt number. @@ -13,6 +18,13 @@ Required properties: and GPMI DMA channel ID. Refer to dma.txt and fsl-mxs-dma.txt for details. - dma-names: Must be "rx-tx". + - clocks : clocks phandle and clock specifier corresponding to each clock + specified in clock-names. + - clock-names : The "gpmi_io" clock is always required. Which clocks are + exactly required depends on chip: + * imx23/imx28 : "gpmi_io" + * imx6q/sx : "gpmi_io", "gpmi_apb", "gpmi_bch", "gpmi_bch_apb", "per1_bch" + * imx7d : "gpmi_io", "gpmi_bch_apb" Optional properties: - nand-on-flash-bbt: boolean to enable on flash bbt option if not -- cgit v1.2.3-59-g8ed1b From 4d02423e9afe6c46142ce98bbcaf5167316dbfbf Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Mon, 10 Apr 2017 10:35:17 +0200 Subject: mtd: nand: gpmi: Fix gpmi_nand_init() error path The GPMI driver is wrongly assuming that nand_release() can safely be called on an uninitialized/unregistered NAND device. Add a new err_nand_cleanup label in the error path and only execute if nand_scan_tail() succeeded. Note that we now call nand_cleanup() instead of nand_release() (nand_release() is actually grouping the mtd_device_unregister() and nand_cleanup() in one call) because there's no point in trying to unregister a device that has never been registered. Signed-off-by: Boris Brezillon Reviewed-by: Marek Vasut Acked-by: Han Xu Reviewed-by: Marek Vasut --- drivers/mtd/nand/gpmi-nand/gpmi-nand.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c index 9b777be633a9..f7ac81e44ce7 100644 --- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c +++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c @@ -2055,18 +2055,20 @@ static int gpmi_nand_init(struct gpmi_nand_data *this) ret = nand_boot_init(this); if (ret) - goto err_out; + goto err_nand_cleanup; ret = chip->scan_bbt(mtd); if (ret) - goto err_out; + goto err_nand_cleanup; ret = mtd_device_register(mtd, NULL, 0); if (ret) - goto err_out; + goto err_nand_cleanup; return 0; +err_nand_cleanup: + nand_cleanup(chip); err_out: - gpmi_nand_exit(this); + gpmi_free_dma_buffer(this); return ret; } -- cgit v1.2.3-59-g8ed1b From ebb528d97830731b5fce27a72191e4fb94a4e66d Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Mon, 10 Apr 2017 10:35:18 +0200 Subject: mtd: nand: gpmi: Kill gpmi_nand_exit() The only user of gpmi_nand_exit() is gpmi_nand_remove(). Move its content to the caller. Signed-off-by: Boris Brezillon Reviewed-by: Marek Vasut Acked-by: Han Xu --- drivers/mtd/nand/gpmi-nand/gpmi-nand.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c index f7ac81e44ce7..50f8d4a1b983 100644 --- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c +++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c @@ -1936,12 +1936,6 @@ static int gpmi_set_geometry(struct gpmi_nand_data *this) return gpmi_alloc_dma_buffer(this); } -static void gpmi_nand_exit(struct gpmi_nand_data *this) -{ - nand_release(nand_to_mtd(&this->nand)); - gpmi_free_dma_buffer(this); -} - static int gpmi_init_last(struct gpmi_nand_data *this) { struct nand_chip *chip = &this->nand; @@ -2141,7 +2135,8 @@ static int gpmi_nand_remove(struct platform_device *pdev) { struct gpmi_nand_data *this = platform_get_drvdata(pdev); - gpmi_nand_exit(this); + nand_release(nand_to_mtd(&this->nand)); + gpmi_free_dma_buffer(this); release_resources(this); return 0; } -- cgit v1.2.3-59-g8ed1b From 104e442a67cfba4d0cc982384761befb917fb6a1 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 16 Mar 2017 09:35:58 +0100 Subject: mtd: nand: Pass the CS line to ->setup_data_interface() Some NAND controllers can assign different NAND timings to different CS lines. Pass the CS line information to ->setup_data_interface() so that the NAND controller driver knows which CS line is concerned by the setup_data_interface() request. Signed-off-by: Boris Brezillon --- drivers/mtd/nand/fsmc_nand.c | 7 +++---- drivers/mtd/nand/mxc_nand.c | 12 +++++------- drivers/mtd/nand/nand_base.c | 22 +++++++++++++--------- drivers/mtd/nand/s3c2410.c | 5 ++--- drivers/mtd/nand/sunxi_nand.c | 7 +++---- drivers/mtd/nand/tango_nand.c | 7 +++---- include/linux/mtd/nand.h | 12 ++++++++---- 7 files changed, 37 insertions(+), 35 deletions(-) diff --git a/drivers/mtd/nand/fsmc_nand.c b/drivers/mtd/nand/fsmc_nand.c index de57554b8c4f..9d8b051d3187 100644 --- a/drivers/mtd/nand/fsmc_nand.c +++ b/drivers/mtd/nand/fsmc_nand.c @@ -388,9 +388,8 @@ static int fsmc_calc_timings(struct fsmc_nand_data *host, return 0; } -static int fsmc_setup_data_interface(struct mtd_info *mtd, - const struct nand_data_interface *conf, - bool check_only) +static int fsmc_setup_data_interface(struct mtd_info *mtd, int csline, + const struct nand_data_interface *conf) { struct nand_chip *nand = mtd_to_nand(mtd); struct fsmc_nand_data *host = nand_get_controller_data(nand); @@ -406,7 +405,7 @@ static int fsmc_setup_data_interface(struct mtd_info *mtd, if (ret) return ret; - if (check_only) + if (csline == NAND_DATA_IFACE_CHECK_ONLY) return 0; fsmc_nand_setup(host, &tims); diff --git a/drivers/mtd/nand/mxc_nand.c b/drivers/mtd/nand/mxc_nand.c index 61ca020c5272..a764d5ca7536 100644 --- a/drivers/mtd/nand/mxc_nand.c +++ b/drivers/mtd/nand/mxc_nand.c @@ -152,9 +152,8 @@ struct mxc_nand_devtype_data { void (*select_chip)(struct mtd_info *mtd, int chip); int (*correct_data)(struct mtd_info *mtd, u_char *dat, u_char *read_ecc, u_char *calc_ecc); - int (*setup_data_interface)(struct mtd_info *mtd, - const struct nand_data_interface *conf, - bool check_only); + int (*setup_data_interface)(struct mtd_info *mtd, int csline, + const struct nand_data_interface *conf); /* * On i.MX21 the CONFIG2:INT bit cannot be read if interrupts are masked @@ -1015,9 +1014,8 @@ static void preset_v1(struct mtd_info *mtd) writew(0x4, NFC_V1_V2_WRPROT); } -static int mxc_nand_v2_setup_data_interface(struct mtd_info *mtd, - const struct nand_data_interface *conf, - bool check_only) +static int mxc_nand_v2_setup_data_interface(struct mtd_info *mtd, int csline, + const struct nand_data_interface *conf) { struct nand_chip *nand_chip = mtd_to_nand(mtd); struct mxc_nand_host *host = nand_get_controller_data(nand_chip); @@ -1075,7 +1073,7 @@ static int mxc_nand_v2_setup_data_interface(struct mtd_info *mtd, return -EINVAL; } - if (check_only) + if (csline == NAND_DATA_IFACE_CHECK_ONLY) return 0; ret = clk_set_rate(host->clk, rate); diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index 79d98c9fa8a7..3317acf0ce04 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -1042,12 +1042,13 @@ static int nand_wait(struct mtd_info *mtd, struct nand_chip *chip) /** * nand_reset_data_interface - Reset data interface and timings * @chip: The NAND chip + * @chipnr: Internal die id * * Reset the Data interface and timings to ONFI mode 0. * * Returns 0 for success or negative error code otherwise. */ -static int nand_reset_data_interface(struct nand_chip *chip) +static int nand_reset_data_interface(struct nand_chip *chip, int chipnr) { struct mtd_info *mtd = nand_to_mtd(chip); const struct nand_data_interface *conf; @@ -1071,7 +1072,7 @@ static int nand_reset_data_interface(struct nand_chip *chip) */ conf = nand_get_default_data_interface(); - ret = chip->setup_data_interface(mtd, conf, false); + ret = chip->setup_data_interface(mtd, chipnr, conf); if (ret) pr_err("Failed to configure data interface to SDR timing mode 0\n"); @@ -1081,6 +1082,7 @@ static int nand_reset_data_interface(struct nand_chip *chip) /** * nand_setup_data_interface - Setup the best data interface and timings * @chip: The NAND chip + * @chipnr: Internal die id * * Find and configure the best data interface and NAND timings supported by * the chip and the driver. @@ -1090,7 +1092,7 @@ static int nand_reset_data_interface(struct nand_chip *chip) * * Returns 0 for success or negative error code otherwise. */ -static int nand_setup_data_interface(struct nand_chip *chip) +static int nand_setup_data_interface(struct nand_chip *chip, int chipnr) { struct mtd_info *mtd = nand_to_mtd(chip); int ret; @@ -1114,7 +1116,7 @@ static int nand_setup_data_interface(struct nand_chip *chip) goto err; } - ret = chip->setup_data_interface(mtd, chip->data_interface, false); + ret = chip->setup_data_interface(mtd, chipnr, chip->data_interface); err: return ret; } @@ -1165,8 +1167,10 @@ static int nand_init_data_interface(struct nand_chip *chip) if (ret) continue; - ret = chip->setup_data_interface(mtd, chip->data_interface, - true); + /* Pass -1 to only */ + ret = chip->setup_data_interface(mtd, + NAND_DATA_IFACE_CHECK_ONLY, + chip->data_interface); if (!ret) { chip->onfi_timing_mode_default = mode; break; @@ -1193,7 +1197,7 @@ int nand_reset(struct nand_chip *chip, int chipnr) struct mtd_info *mtd = nand_to_mtd(chip); int ret; - ret = nand_reset_data_interface(chip); + ret = nand_reset_data_interface(chip, chipnr); if (ret) return ret; @@ -1206,7 +1210,7 @@ int nand_reset(struct nand_chip *chip, int chipnr) chip->select_chip(mtd, -1); chip->select_chip(mtd, chipnr); - ret = nand_setup_data_interface(chip); + ret = nand_setup_data_interface(chip, chipnr); chip->select_chip(mtd, -1); if (ret) return ret; @@ -4396,7 +4400,7 @@ int nand_scan_ident(struct mtd_info *mtd, int maxchips, * For the other dies, nand_reset() will automatically switch to the * best mode for us. */ - ret = nand_setup_data_interface(chip); + ret = nand_setup_data_interface(chip, 0); if (ret) return ret; diff --git a/drivers/mtd/nand/s3c2410.c b/drivers/mtd/nand/s3c2410.c index f0b030d44f71..9e0c849607b9 100644 --- a/drivers/mtd/nand/s3c2410.c +++ b/drivers/mtd/nand/s3c2410.c @@ -812,9 +812,8 @@ static int s3c2410_nand_add_partition(struct s3c2410_nand_info *info, return -ENODEV; } -static int s3c2410_nand_setup_data_interface(struct mtd_info *mtd, - const struct nand_data_interface *conf, - bool check_only) +static int s3c2410_nand_setup_data_interface(struct mtd_info *mtd, int csline, + const struct nand_data_interface *conf) { struct s3c2410_nand_info *info = s3c2410_nand_mtd_toinfo(mtd); struct s3c2410_platform_nand *pdata = info->platform; diff --git a/drivers/mtd/nand/sunxi_nand.c b/drivers/mtd/nand/sunxi_nand.c index 118a26fff368..9c2dbe352c43 100644 --- a/drivers/mtd/nand/sunxi_nand.c +++ b/drivers/mtd/nand/sunxi_nand.c @@ -1592,9 +1592,8 @@ static int _sunxi_nand_lookup_timing(const s32 *lut, int lut_size, u32 duration, #define sunxi_nand_lookup_timing(l, p, c) \ _sunxi_nand_lookup_timing(l, ARRAY_SIZE(l), p, c) -static int sunxi_nfc_setup_data_interface(struct mtd_info *mtd, - const struct nand_data_interface *conf, - bool check_only) +static int sunxi_nfc_setup_data_interface(struct mtd_info *mtd, int csline, + const struct nand_data_interface *conf) { struct nand_chip *nand = mtd_to_nand(mtd); struct sunxi_nand_chip *chip = to_sunxi_nand(nand); @@ -1707,7 +1706,7 @@ static int sunxi_nfc_setup_data_interface(struct mtd_info *mtd, return tRHW; } - if (check_only) + if (csline == NAND_DATA_IFACE_CHECK_ONLY) return 0; /* diff --git a/drivers/mtd/nand/tango_nand.c b/drivers/mtd/nand/tango_nand.c index 05b6e1065203..85e0d97593e8 100644 --- a/drivers/mtd/nand/tango_nand.c +++ b/drivers/mtd/nand/tango_nand.c @@ -476,9 +476,8 @@ static u32 to_ticks(int kHz, int ps) return DIV_ROUND_UP_ULL((u64)kHz * ps, NSEC_PER_SEC); } -static int tango_set_timings(struct mtd_info *mtd, - const struct nand_data_interface *conf, - bool check_only) +static int tango_set_timings(struct mtd_info *mtd, int csline, + const struct nand_data_interface *conf) { const struct nand_sdr_timings *sdr = nand_get_sdr_timings(conf); struct nand_chip *chip = mtd_to_nand(mtd); @@ -490,7 +489,7 @@ static int tango_set_timings(struct mtd_info *mtd, if (IS_ERR(sdr)) return PTR_ERR(sdr); - if (check_only) + if (csline == NAND_DATA_IFACE_CHECK_ONLY) return 0; Trdy = to_ticks(kHz, sdr->tCEA_max - sdr->tREA_max); diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 893d0ce08030..9de3686e738c 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -107,6 +107,8 @@ int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len); #define NAND_STATUS_READY 0x40 #define NAND_STATUS_WP 0x80 +#define NAND_DATA_IFACE_CHECK_ONLY -1 + /* * Constants for ECC_MODES */ @@ -818,7 +820,10 @@ struct nand_manufacturer_ops { * @read_retries: [INTERN] the number of read retry modes supported * @onfi_set_features: [REPLACEABLE] set the features for ONFI nand * @onfi_get_features: [REPLACEABLE] get the features for ONFI nand - * @setup_data_interface: [OPTIONAL] setup the data interface and timing + * @setup_data_interface: [OPTIONAL] setup the data interface and timing. If + * chipnr is set to %NAND_DATA_IFACE_CHECK_ONLY this + * means the configuration should not be applied but + * only checked. * @bbt: [INTERN] bad block table pointer * @bbt_td: [REPLACEABLE] bad block table descriptor for flash * lookup. @@ -862,9 +867,8 @@ struct nand_chip { int (*onfi_get_features)(struct mtd_info *mtd, struct nand_chip *chip, int feature_addr, uint8_t *subfeature_para); int (*setup_read_retry)(struct mtd_info *mtd, int retry_mode); - int (*setup_data_interface)(struct mtd_info *mtd, - const struct nand_data_interface *conf, - bool check_only); + int (*setup_data_interface)(struct mtd_info *mtd, int chipnr, + const struct nand_data_interface *conf); int chip_delay; -- cgit v1.2.3-59-g8ed1b From f9ce2eddf1769a2cf93e87332c55063537e69119 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 16 Mar 2017 09:35:59 +0100 Subject: mtd: nand: atmel: Add ->setup_data_interface() hooks The NAND controller IP can adapt the NAND controller timings dynamically. Implement the ->setup_data_interface() hook to support this feature. Note that it's not supported on at91rm9200 because this SoC has a completely different SMC block, which is not supported yet. Signed-off-by: Boris Brezillon --- drivers/mtd/nand/Kconfig | 1 + drivers/mtd/nand/atmel/nand-controller.c | 329 ++++++++++++++++++++++++++++++- 2 files changed, 328 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig index 0bd2319d3035..dbfa72d61d5a 100644 --- a/drivers/mtd/nand/Kconfig +++ b/drivers/mtd/nand/Kconfig @@ -308,6 +308,7 @@ config MTD_NAND_CS553X config MTD_NAND_ATMEL tristate "Support for NAND Flash / SmartMedia on AT91" depends on ARCH_AT91 + select MFD_ATMEL_SMC help Enables support for NAND Flash / Smart Media Card interface on Atmel AT91 processors. diff --git a/drivers/mtd/nand/atmel/nand-controller.c b/drivers/mtd/nand/atmel/nand-controller.c index 3b2446896147..ee32909f7943 100644 --- a/drivers/mtd/nand/atmel/nand-controller.c +++ b/drivers/mtd/nand/atmel/nand-controller.c @@ -57,6 +57,7 @@ #include #include #include +#include #include #include #include @@ -151,6 +152,8 @@ struct atmel_nand_cs { void __iomem *virt; dma_addr_t dma; } io; + + struct atmel_smc_cs_conf smcconf; }; struct atmel_nand { @@ -196,6 +199,8 @@ struct atmel_nand_controller_ops { void (*nand_init)(struct atmel_nand_controller *nc, struct atmel_nand *nand); int (*ecc_init)(struct atmel_nand *nand); + int (*setup_data_interface)(struct atmel_nand *nand, int csline, + const struct nand_data_interface *conf); }; struct atmel_nand_controller_caps { @@ -1175,6 +1180,295 @@ static int atmel_hsmc_nand_ecc_init(struct atmel_nand *nand) return 0; } +static int atmel_smc_nand_prepare_smcconf(struct atmel_nand *nand, + const struct nand_data_interface *conf, + struct atmel_smc_cs_conf *smcconf) +{ + u32 ncycles, totalcycles, timeps, mckperiodps; + struct atmel_nand_controller *nc; + int ret; + + nc = to_nand_controller(nand->base.controller); + + /* DDR interface not supported. */ + if (conf->type != NAND_SDR_IFACE) + return -ENOTSUPP; + + /* + * tRC < 30ns implies EDO mode. This controller does not support this + * mode. + */ + if (conf->timings.sdr.tRC_min < 30) + return -ENOTSUPP; + + atmel_smc_cs_conf_init(smcconf); + + mckperiodps = NSEC_PER_SEC / clk_get_rate(nc->mck); + mckperiodps *= 1000; + + /* + * Set write pulse timing. This one is easy to extract: + * + * NWE_PULSE = tWP + */ + ncycles = DIV_ROUND_UP(conf->timings.sdr.tWP_min, mckperiodps); + totalcycles = ncycles; + ret = atmel_smc_cs_conf_set_pulse(smcconf, ATMEL_SMC_NWE_SHIFT, + ncycles); + if (ret) + return ret; + + /* + * The write setup timing depends on the operation done on the NAND. + * All operations goes through the same data bus, but the operation + * type depends on the address we are writing to (ALE/CLE address + * lines). + * Since we have no way to differentiate the different operations at + * the SMC level, we must consider the worst case (the biggest setup + * time among all operation types): + * + * NWE_SETUP = max(tCLS, tCS, tALS, tDS) - NWE_PULSE + */ + timeps = max3(conf->timings.sdr.tCLS_min, conf->timings.sdr.tCS_min, + conf->timings.sdr.tALS_min); + timeps = max(timeps, conf->timings.sdr.tDS_min); + ncycles = DIV_ROUND_UP(timeps, mckperiodps); + ncycles = ncycles > totalcycles ? ncycles - totalcycles : 0; + totalcycles += ncycles; + ret = atmel_smc_cs_conf_set_setup(smcconf, ATMEL_SMC_NWE_SHIFT, + ncycles); + if (ret) + return ret; + + /* + * As for the write setup timing, the write hold timing depends on the + * operation done on the NAND: + * + * NWE_HOLD = max(tCLH, tCH, tALH, tDH, tWH) + */ + timeps = max3(conf->timings.sdr.tCLH_min, conf->timings.sdr.tCH_min, + conf->timings.sdr.tALH_min); + timeps = max3(timeps, conf->timings.sdr.tDH_min, + conf->timings.sdr.tWH_min); + ncycles = DIV_ROUND_UP(timeps, mckperiodps); + totalcycles += ncycles; + + /* + * The write cycle timing is directly matching tWC, but is also + * dependent on the other timings on the setup and hold timings we + * calculated earlier, which gives: + * + * NWE_CYCLE = max(tWC, NWE_SETUP + NWE_PULSE + NWE_HOLD) + */ + ncycles = DIV_ROUND_UP(conf->timings.sdr.tWC_min, mckperiodps); + ncycles = max(totalcycles, ncycles); + ret = atmel_smc_cs_conf_set_cycle(smcconf, ATMEL_SMC_NWE_SHIFT, + ncycles); + if (ret) + return ret; + + /* + * We don't want the CS line to be toggled between each byte/word + * transfer to the NAND. The only way to guarantee that is to have the + * NCS_{WR,RD}_{SETUP,HOLD} timings set to 0, which in turn means: + * + * NCS_WR_PULSE = NWE_CYCLE + */ + ret = atmel_smc_cs_conf_set_pulse(smcconf, ATMEL_SMC_NCS_WR_SHIFT, + ncycles); + if (ret) + return ret; + + /* + * As for the write setup timing, the read hold timing depends on the + * operation done on the NAND: + * + * NRD_HOLD = max(tREH, tRHOH) + */ + timeps = max(conf->timings.sdr.tREH_min, conf->timings.sdr.tRHOH_min); + ncycles = DIV_ROUND_UP(timeps, mckperiodps); + totalcycles = ncycles; + + /* + * TDF = tRHZ - NRD_HOLD + */ + ncycles = DIV_ROUND_UP(conf->timings.sdr.tRHZ_max, mckperiodps); + ncycles -= totalcycles; + + /* + * In ONFI 4.0 specs, tRHZ has been increased to support EDO NANDs and + * we might end up with a config that does not fit in the TDF field. + * Just take the max value in this case and hope that the NAND is more + * tolerant than advertised. + */ + if (ncycles > ATMEL_SMC_MODE_TDF_MAX) + ncycles = ATMEL_SMC_MODE_TDF_MAX; + else if (ncycles < ATMEL_SMC_MODE_TDF_MIN) + ncycles = ATMEL_SMC_MODE_TDF_MIN; + + smcconf->mode |= ATMEL_SMC_MODE_TDF(ncycles) | + ATMEL_SMC_MODE_TDFMODE_OPTIMIZED; + + /* + * Read pulse timing directly matches tRP: + * + * NRD_PULSE = tRP + */ + ncycles = DIV_ROUND_UP(conf->timings.sdr.tRP_min, mckperiodps); + totalcycles += ncycles; + ret = atmel_smc_cs_conf_set_pulse(smcconf, ATMEL_SMC_NRD_SHIFT, + ncycles); + if (ret) + return ret; + + /* + * The write cycle timing is directly matching tWC, but is also + * dependent on the setup and hold timings we calculated earlier, + * which gives: + * + * NRD_CYCLE = max(tRC, NRD_PULSE + NRD_HOLD) + * + * NRD_SETUP is always 0. + */ + ncycles = DIV_ROUND_UP(conf->timings.sdr.tRC_min, mckperiodps); + ncycles = max(totalcycles, ncycles); + ret = atmel_smc_cs_conf_set_cycle(smcconf, ATMEL_SMC_NRD_SHIFT, + ncycles); + if (ret) + return ret; + + /* + * We don't want the CS line to be toggled between each byte/word + * transfer from the NAND. The only way to guarantee that is to have + * the NCS_{WR,RD}_{SETUP,HOLD} timings set to 0, which in turn means: + * + * NCS_RD_PULSE = NRD_CYCLE + */ + ret = atmel_smc_cs_conf_set_pulse(smcconf, ATMEL_SMC_NCS_RD_SHIFT, + ncycles); + if (ret) + return ret; + + /* Txxx timings are directly matching tXXX ones. */ + ncycles = DIV_ROUND_UP(conf->timings.sdr.tCLR_min, mckperiodps); + ret = atmel_smc_cs_conf_set_timing(smcconf, + ATMEL_HSMC_TIMINGS_TCLR_SHIFT, + ncycles); + if (ret) + return ret; + + ncycles = DIV_ROUND_UP(conf->timings.sdr.tADL_min, mckperiodps); + ret = atmel_smc_cs_conf_set_timing(smcconf, + ATMEL_HSMC_TIMINGS_TADL_SHIFT, + ncycles); + if (ret) + return ret; + + ncycles = DIV_ROUND_UP(conf->timings.sdr.tAR_min, mckperiodps); + ret = atmel_smc_cs_conf_set_timing(smcconf, + ATMEL_HSMC_TIMINGS_TAR_SHIFT, + ncycles); + if (ret) + return ret; + + ncycles = DIV_ROUND_UP(conf->timings.sdr.tRR_min, mckperiodps); + ret = atmel_smc_cs_conf_set_timing(smcconf, + ATMEL_HSMC_TIMINGS_TRR_SHIFT, + ncycles); + if (ret) + return ret; + + ncycles = DIV_ROUND_UP(conf->timings.sdr.tWB_max, mckperiodps); + ret = atmel_smc_cs_conf_set_timing(smcconf, + ATMEL_HSMC_TIMINGS_TWB_SHIFT, + ncycles); + if (ret) + return ret; + + /* Attach the CS line to the NFC logic. */ + smcconf->timings |= ATMEL_HSMC_TIMINGS_NFSEL; + + /* Set the appropriate data bus width. */ + if (nand->base.options & NAND_BUSWIDTH_16) + smcconf->mode |= ATMEL_SMC_MODE_DBW_16; + + /* Operate in NRD/NWE READ/WRITEMODE. */ + smcconf->mode |= ATMEL_SMC_MODE_READMODE_NRD | + ATMEL_SMC_MODE_WRITEMODE_NWE; + + return 0; +} + +static int atmel_smc_nand_setup_data_interface(struct atmel_nand *nand, + int csline, + const struct nand_data_interface *conf) +{ + struct atmel_nand_controller *nc; + struct atmel_smc_cs_conf smcconf; + struct atmel_nand_cs *cs; + int ret; + + nc = to_nand_controller(nand->base.controller); + + ret = atmel_smc_nand_prepare_smcconf(nand, conf, &smcconf); + if (ret) + return ret; + + if (csline == NAND_DATA_IFACE_CHECK_ONLY) + return 0; + + cs = &nand->cs[csline]; + cs->smcconf = smcconf; + atmel_smc_cs_conf_apply(nc->smc, cs->id, &cs->smcconf); + + return 0; +} + +static int atmel_hsmc_nand_setup_data_interface(struct atmel_nand *nand, + int csline, + const struct nand_data_interface *conf) +{ + struct atmel_nand_controller *nc; + struct atmel_smc_cs_conf smcconf; + struct atmel_nand_cs *cs; + int ret; + + nc = to_nand_controller(nand->base.controller); + + ret = atmel_smc_nand_prepare_smcconf(nand, conf, &smcconf); + if (ret) + return ret; + + if (csline == NAND_DATA_IFACE_CHECK_ONLY) + return 0; + + cs = &nand->cs[csline]; + cs->smcconf = smcconf; + + if (cs->rb.type == ATMEL_NAND_NATIVE_RB) + cs->smcconf.timings |= ATMEL_HSMC_TIMINGS_RBNSEL(cs->rb.id); + + atmel_hsmc_cs_conf_apply(nc->smc, cs->id, &cs->smcconf); + + return 0; +} + +static int atmel_nand_setup_data_interface(struct mtd_info *mtd, int csline, + const struct nand_data_interface *conf) +{ + struct nand_chip *chip = mtd_to_nand(mtd); + struct atmel_nand *nand = to_atmel_nand(chip); + struct atmel_nand_controller *nc; + + nc = to_nand_controller(nand->base.controller); + + if (csline >= nand->numcs || + (csline < 0 && csline != NAND_DATA_IFACE_CHECK_ONLY)) + return -EINVAL; + + return nc->caps->ops->setup_data_interface(nand, csline, conf); +} + static void atmel_nand_init(struct atmel_nand_controller *nc, struct atmel_nand *nand) { @@ -1192,6 +1486,9 @@ static void atmel_nand_init(struct atmel_nand_controller *nc, chip->write_buf = atmel_nand_write_buf; chip->select_chip = atmel_nand_select_chip; + if (nc->mck && nc->caps->ops->setup_data_interface) + chip->setup_data_interface = atmel_nand_setup_data_interface; + /* Some NANDs require a longer delay than the default one (20us). */ chip->chip_delay = 40; @@ -1677,6 +1974,12 @@ static int atmel_nand_controller_init(struct atmel_nand_controller *nc, if (nc->caps->legacy_of_bindings) return 0; + nc->mck = of_clk_get(dev->parent->of_node, 0); + if (IS_ERR(nc->mck)) { + dev_err(dev, "Failed to retrieve MCK clk\n"); + return PTR_ERR(nc->mck); + } + np = of_parse_phandle(dev->parent->of_node, "atmel,smc", 0); if (!np) { dev_err(dev, "Missing or invalid atmel,smc property\n"); @@ -1983,6 +2286,7 @@ static const struct atmel_nand_controller_ops atmel_hsmc_nc_ops = { .remove = atmel_hsmc_nand_controller_remove, .ecc_init = atmel_hsmc_nand_ecc_init, .nand_init = atmel_hsmc_nand_init, + .setup_data_interface = atmel_hsmc_nand_setup_data_interface, }; static const struct atmel_nand_controller_caps atmel_sama5_nc_caps = { @@ -2037,7 +2341,14 @@ atmel_smc_nand_controller_remove(struct atmel_nand_controller *nc) return 0; } -static const struct atmel_nand_controller_ops atmel_smc_nc_ops = { +/* + * The SMC reg layout of at91rm9200 is completely different which prevents us + * from re-using atmel_smc_nand_setup_data_interface() for the + * ->setup_data_interface() hook. + * At this point, there's no support for the at91rm9200 SMC IP, so we leave + * ->setup_data_interface() unassigned. + */ +static const struct atmel_nand_controller_ops at91rm9200_nc_ops = { .probe = atmel_smc_nand_controller_probe, .remove = atmel_smc_nand_controller_remove, .ecc_init = atmel_nand_ecc_init, @@ -2045,6 +2356,20 @@ static const struct atmel_nand_controller_ops atmel_smc_nc_ops = { }; static const struct atmel_nand_controller_caps atmel_rm9200_nc_caps = { + .ale_offs = BIT(21), + .cle_offs = BIT(22), + .ops = &at91rm9200_nc_ops, +}; + +static const struct atmel_nand_controller_ops atmel_smc_nc_ops = { + .probe = atmel_smc_nand_controller_probe, + .remove = atmel_smc_nand_controller_remove, + .ecc_init = atmel_nand_ecc_init, + .nand_init = atmel_smc_nand_init, + .setup_data_interface = atmel_smc_nand_setup_data_interface, +}; + +static const struct atmel_nand_controller_caps atmel_sam9260_nc_caps = { .ale_offs = BIT(21), .cle_offs = BIT(22), .ops = &atmel_smc_nc_ops, @@ -2093,7 +2418,7 @@ static const struct of_device_id atmel_nand_controller_of_ids[] = { }, { .compatible = "atmel,at91sam9260-nand-controller", - .data = &atmel_rm9200_nc_caps, + .data = &atmel_sam9260_nc_caps, }, { .compatible = "atmel,at91sam9261-nand-controller", -- cgit v1.2.3-59-g8ed1b From 6e532afaca8ed41107fa0a551d7b2db99a869540 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 16 Mar 2017 09:36:00 +0100 Subject: mtd: nand: atmel: Add PM ops Provide a ->resume() hook to make sure the NAND timings are correctly restored by resetting all chips connected to the controller. Signed-off-by: Boris Brezillon --- drivers/mtd/nand/atmel/nand-controller.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/mtd/nand/atmel/nand-controller.c b/drivers/mtd/nand/atmel/nand-controller.c index ee32909f7943..846c555e470b 100644 --- a/drivers/mtd/nand/atmel/nand-controller.c +++ b/drivers/mtd/nand/atmel/nand-controller.c @@ -2506,6 +2506,24 @@ static int atmel_nand_controller_remove(struct platform_device *pdev) return nc->caps->ops->remove(nc); } +static int atmel_nand_controller_resume(struct device *dev) +{ + struct atmel_nand_controller *nc = dev_get_drvdata(dev); + struct atmel_nand *nand; + + list_for_each_entry(nand, &nc->chips, node) { + int i; + + for (i = 0; i < nand->numcs; i++) + nand_reset(&nand->base, i); + } + + return 0; +} + +static SIMPLE_DEV_PM_OPS(atmel_nand_controller_pm_ops, NULL, + atmel_nand_controller_resume); + static struct platform_driver atmel_nand_controller_driver = { .driver = { .name = "atmel-nand-controller", -- cgit v1.2.3-59-g8ed1b From 0b4773fd1649e0d418275557723a7ef54f769dc9 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 16 May 2017 00:17:41 +0200 Subject: mtd: nand: Drop unused cached programming support Cached programming is always skipped, so drop the associated code until we decide to really support it. Signed-off-by: Boris Brezillon --- drivers/mtd/nand/nand_base.c | 38 ++++++++++++-------------------------- 1 file changed, 12 insertions(+), 26 deletions(-) diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index 3317acf0ce04..561f70e05c88 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -2724,7 +2724,7 @@ static int nand_write_page_syndrome(struct mtd_info *mtd, */ static int nand_write_page(struct mtd_info *mtd, struct nand_chip *chip, uint32_t offset, int data_len, const uint8_t *buf, - int oob_required, int page, int cached, int raw) + int oob_required, int page, int raw) { int status, subpage; @@ -2750,31 +2750,19 @@ static int nand_write_page(struct mtd_info *mtd, struct nand_chip *chip, if (status < 0) return status; + if (nand_standard_page_accessors(&chip->ecc)) + chip->cmdfunc(mtd, NAND_CMD_PAGEPROG, -1, -1); + status = chip->waitfunc(mtd, chip); /* - * Cached progamming disabled for now. Not sure if it's worth the - * trouble. The speed gain is not very impressive. (2.3->2.6Mib/s). + * See if operation failed and additional status checks are + * available. */ - cached = 0; - - if (!cached || !NAND_HAS_CACHEPROG(chip)) { - - if (nand_standard_page_accessors(&chip->ecc)) - chip->cmdfunc(mtd, NAND_CMD_PAGEPROG, -1, -1); - status = chip->waitfunc(mtd, chip); - /* - * See if operation failed and additional status checks are - * available. - */ - if ((status & NAND_STATUS_FAIL) && (chip->errstat)) - status = chip->errstat(mtd, chip, FL_WRITING, status, - page); + if ((status & NAND_STATUS_FAIL) && (chip->errstat)) + status = chip->errstat(mtd, chip, FL_WRITING, status, + page); - if (status & NAND_STATUS_FAIL) - return -EIO; - } else { - chip->cmdfunc(mtd, NAND_CMD_CACHEDPROG, -1, -1); - status = chip->waitfunc(mtd, chip); - } + if (status & NAND_STATUS_FAIL) + return -EIO; return 0; } @@ -2881,7 +2869,6 @@ static int nand_do_write_ops(struct mtd_info *mtd, loff_t to, while (1) { int bytes = mtd->writesize; - int cached = writelen > bytes && page != blockmask; uint8_t *wbuf = buf; int use_bufpoi; int part_pagewr = (column || writelen < mtd->writesize); @@ -2899,7 +2886,6 @@ static int nand_do_write_ops(struct mtd_info *mtd, loff_t to, if (use_bufpoi) { pr_debug("%s: using write bounce buffer for buf@%p\n", __func__, buf); - cached = 0; if (part_pagewr) bytes = min_t(int, bytes - column, writelen); chip->pagebuf = -1; @@ -2918,7 +2904,7 @@ static int nand_do_write_ops(struct mtd_info *mtd, loff_t to, } ret = nand_write_page(mtd, chip, column, bytes, wbuf, - oob_required, page, cached, + oob_required, page, (ops->mode == MTD_OPS_RAW)); if (ret) break; -- cgit v1.2.3-59-g8ed1b From 7d135bcced20be2b50128432c5426a7278ec4f6d Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sat, 6 May 2017 18:03:33 +0200 Subject: mtd: nand: Drop the ->errstat() hook The ->errstat() hook is no longer implemented NAND controller drivers. Get rid of it before someone starts abusing it. Signed-off-by: Boris Brezillon --- drivers/mtd/nand/nand_base.c | 16 ---------------- include/linux/mtd/nand.h | 5 ----- 2 files changed, 21 deletions(-) diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index 561f70e05c88..df613125795b 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -2753,14 +2753,6 @@ static int nand_write_page(struct mtd_info *mtd, struct nand_chip *chip, if (nand_standard_page_accessors(&chip->ecc)) chip->cmdfunc(mtd, NAND_CMD_PAGEPROG, -1, -1); status = chip->waitfunc(mtd, chip); - /* - * See if operation failed and additional status checks are - * available. - */ - if ((status & NAND_STATUS_FAIL) && (chip->errstat)) - status = chip->errstat(mtd, chip, FL_WRITING, status, - page); - if (status & NAND_STATUS_FAIL) return -EIO; @@ -3220,14 +3212,6 @@ int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr, status = chip->erase(mtd, page & chip->pagemask); - /* - * See if operation failed and additional status checks are - * available - */ - if ((status & NAND_STATUS_FAIL) && (chip->errstat)) - status = chip->errstat(mtd, chip, FL_ERASING, - status, page); - /* See if block erase succeeded */ if (status & NAND_STATUS_FAIL) { pr_debug("%s: failed erase, page 0x%08x\n", diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 9de3686e738c..8b3607bde1b5 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -834,9 +834,6 @@ struct nand_manufacturer_ops { * structure which is shared among multiple independent * devices. * @priv: [OPTIONAL] pointer to private chip data - * @errstat: [OPTIONAL] hardware specific function to perform - * additional error status checks (determine if errors are - * correctable). * @manufacturer: [INTERN] Contains manufacturer information */ @@ -860,8 +857,6 @@ struct nand_chip { int(*waitfunc)(struct mtd_info *mtd, struct nand_chip *this); int (*erase)(struct mtd_info *mtd, int page); int (*scan_bbt)(struct mtd_info *mtd); - int (*errstat)(struct mtd_info *mtd, struct nand_chip *this, int state, - int status, int page); int (*onfi_set_features)(struct mtd_info *mtd, struct nand_chip *chip, int feature_addr, uint8_t *subfeature_para); int (*onfi_get_features)(struct mtd_info *mtd, struct nand_chip *chip, -- cgit v1.2.3-59-g8ed1b From 2de85e73360104d3582363dcebdcdd7dc20431be Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 16 May 2017 00:23:45 +0200 Subject: mtd: nand: sunxi: Actually use DMA for subpage reads ecc->read_subpage is set to sunxi_nfc_hw_ecc_read_subpage_dma when ->dmac != NULL, but is then unconditionally overwritten in the common init path. Remove this extra assignment to allow usage of the DMA operation when possible. Signed-off-by: Boris Brezillon --- drivers/mtd/nand/sunxi_nand.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mtd/nand/sunxi_nand.c b/drivers/mtd/nand/sunxi_nand.c index 9c2dbe352c43..9a46d1db9211 100644 --- a/drivers/mtd/nand/sunxi_nand.c +++ b/drivers/mtd/nand/sunxi_nand.c @@ -1921,7 +1921,6 @@ static int sunxi_nand_hw_ecc_ctrl_init(struct mtd_info *mtd, ecc->write_subpage = sunxi_nfc_hw_ecc_write_subpage; ecc->read_oob_raw = nand_read_oob_std; ecc->write_oob_raw = nand_write_oob_std; - ecc->read_subpage = sunxi_nfc_hw_ecc_read_subpage; return 0; } -- cgit v1.2.3-59-g8ed1b From df5586d7bf6cce421ed48e9b2a88a8bdaa4fd9d0 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 16 May 2017 00:23:46 +0200 Subject: mtd: nand: sunxi: Remove unneeded ->cmdfunc(NAND_CMD_READ0, 0, page) The core already sends the NAND_CMD_READ0 for us. Duplicating this call in the driver is useless and introduces a perf penalty. Signed-off-by: Boris Brezillon --- drivers/mtd/nand/sunxi_nand.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mtd/nand/sunxi_nand.c b/drivers/mtd/nand/sunxi_nand.c index 9a46d1db9211..d0b6f8f9f297 100644 --- a/drivers/mtd/nand/sunxi_nand.c +++ b/drivers/mtd/nand/sunxi_nand.c @@ -1301,7 +1301,6 @@ static int sunxi_nfc_hw_ecc_read_subpage(struct mtd_info *mtd, sunxi_nfc_hw_ecc_enable(mtd); - chip->cmdfunc(mtd, NAND_CMD_READ0, 0, page); for (i = data_offs / ecc->size; i < DIV_ROUND_UP(data_offs + readlen, ecc->size); i++) { int data_off = i * ecc->size; -- cgit v1.2.3-59-g8ed1b From a186493237a9d8559997c2f97c33c4716d602fd2 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Wed, 17 May 2017 10:47:50 +0200 Subject: mtd: nand: tango: Fix incorrect use of SEQIN command SEQIN is supposed to be used when one wants to start programming a page. What we want here is just to change the column within the page, which is done with the RNDIN command. Fixes: 6956e2385a16 ("mtd: nand: add tango NAND flash controller support") Cc: stable@vger.kernel.org Signed-off-by: Boris Brezillon Acked-by: Marc Gonzalez --- drivers/mtd/nand/tango_nand.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/nand/tango_nand.c b/drivers/mtd/nand/tango_nand.c index 85e0d97593e8..201979f0c1bd 100644 --- a/drivers/mtd/nand/tango_nand.c +++ b/drivers/mtd/nand/tango_nand.c @@ -332,7 +332,7 @@ static void aux_write(struct nand_chip *chip, const u8 **buf, int len, int *pos) if (!*buf) { /* skip over "len" bytes */ - chip->cmdfunc(mtd, NAND_CMD_SEQIN, *pos, -1); + chip->cmdfunc(mtd, NAND_CMD_RNDIN, *pos, -1); } else { tango_write_buf(mtd, *buf, len); *buf += len; -- cgit v1.2.3-59-g8ed1b From 41145649f4acb30249b636b945053db50c9331c5 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 16 May 2017 18:27:49 +0200 Subject: mtd: nand: Wait for PAGEPROG to finish in drivers setting NAND_ECC_CUSTOM_PAGE_ACCESS Drivers setting NAND_ECC_CUSTOM_PAGE_ACCESS are supposed to handle the full read/write page sequence, and waiting for a page to actually be programmed is part of this write-page sequence. This is also what is done in ->write_oob_xxx() hooks, so let's do that in ->write_page_xxx() as well to make it consistent. Signed-off-by: Boris Brezillon --- drivers/mtd/nand/atmel/nand-controller.c | 6 +++++- drivers/mtd/nand/nand_base.c | 10 ++++++---- drivers/mtd/nand/nand_micron.c | 10 ++++++++-- drivers/mtd/nand/tango_nand.c | 13 ++++++++++++- 4 files changed, 31 insertions(+), 8 deletions(-) diff --git a/drivers/mtd/nand/atmel/nand-controller.c b/drivers/mtd/nand/atmel/nand-controller.c index 846c555e470b..6055831c953f 100644 --- a/drivers/mtd/nand/atmel/nand-controller.c +++ b/drivers/mtd/nand/atmel/nand-controller.c @@ -917,7 +917,7 @@ static int atmel_hsmc_nand_pmecc_write_pg(struct nand_chip *chip, struct mtd_info *mtd = nand_to_mtd(chip); struct atmel_nand *nand = to_atmel_nand(chip); struct atmel_hsmc_nand_controller *nc; - int ret; + int ret, status; nc = to_hsmc_nand_controller(chip->controller); @@ -959,6 +959,10 @@ static int atmel_hsmc_nand_pmecc_write_pg(struct nand_chip *chip, dev_err(nc->base.dev, "Failed to program NAND page (err = %d)\n", ret); + status = chip->waitfunc(mtd, chip); + if (status & NAND_STATUS_FAIL) + return -EIO; + return ret; } diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index df613125795b..4b4fea4a3d1f 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -2750,11 +2750,13 @@ static int nand_write_page(struct mtd_info *mtd, struct nand_chip *chip, if (status < 0) return status; - if (nand_standard_page_accessors(&chip->ecc)) + if (nand_standard_page_accessors(&chip->ecc)) { chip->cmdfunc(mtd, NAND_CMD_PAGEPROG, -1, -1); - status = chip->waitfunc(mtd, chip); - if (status & NAND_STATUS_FAIL) - return -EIO; + + status = chip->waitfunc(mtd, chip); + if (status & NAND_STATUS_FAIL) + return -EIO; + } return 0; } diff --git a/drivers/mtd/nand/nand_micron.c b/drivers/mtd/nand/nand_micron.c index 9993f8ead1e2..c30ab60f8e1b 100644 --- a/drivers/mtd/nand/nand_micron.c +++ b/drivers/mtd/nand/nand_micron.c @@ -151,15 +151,18 @@ micron_nand_write_page_on_die_ecc(struct mtd_info *mtd, struct nand_chip *chip, const uint8_t *buf, int oob_required, int page) { + int status; + micron_nand_on_die_ecc_setup(chip, true); chip->cmdfunc(mtd, NAND_CMD_SEQIN, 0x00, page); nand_write_page_raw(mtd, chip, buf, oob_required, page); chip->cmdfunc(mtd, NAND_CMD_PAGEPROG, -1, -1); + status = chip->waitfunc(mtd, chip); micron_nand_on_die_ecc_setup(chip, false); - return 0; + return status & NAND_STATUS_FAIL ? -EIO : 0; } static int @@ -180,11 +183,14 @@ micron_nand_write_page_raw_on_die_ecc(struct mtd_info *mtd, const uint8_t *buf, int oob_required, int page) { + int status; + chip->cmdfunc(mtd, NAND_CMD_SEQIN, 0x00, page); nand_write_page_raw(mtd, chip, buf, oob_required, page); chip->cmdfunc(mtd, NAND_CMD_PAGEPROG, -1, -1); + status = chip->waitfunc(mtd, chip); - return 0; + return status & NAND_STATUS_FAIL ? -EIO : 0; } enum { diff --git a/drivers/mtd/nand/tango_nand.c b/drivers/mtd/nand/tango_nand.c index 201979f0c1bd..dddc4fa7beb6 100644 --- a/drivers/mtd/nand/tango_nand.c +++ b/drivers/mtd/nand/tango_nand.c @@ -295,7 +295,7 @@ static int tango_write_page(struct mtd_info *mtd, struct nand_chip *chip, const u8 *buf, int oob_required, int page) { struct tango_nfc *nfc = to_tango_nfc(chip->controller); - int err, len = mtd->writesize; + int err, status, len = mtd->writesize; /* Calling tango_write_oob() would send PAGEPROG twice */ if (oob_required) @@ -306,6 +306,10 @@ static int tango_write_page(struct mtd_info *mtd, struct nand_chip *chip, if (err) return err; + status = chip->waitfunc(mtd, chip); + if (status & NAND_STATUS_FAIL) + return -EIO; + return 0; } @@ -423,9 +427,16 @@ static int tango_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, static int tango_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip, const u8 *buf, int oob_required, int page) { + int status; + chip->cmdfunc(mtd, NAND_CMD_SEQIN, 0, page); raw_write(chip, buf, chip->oob_poi); chip->cmdfunc(mtd, NAND_CMD_PAGEPROG, -1, -1); + + status = chip->waitfunc(mtd, chip); + if (status & NAND_STATUS_FAIL) + return -EIO; + return 0; } -- cgit v1.2.3-59-g8ed1b From 2165c4a1f71a04c7ea6493f18740a3afd4e47e4f Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 16 May 2017 18:35:45 +0200 Subject: mtd: nand: Support 'EXIT GET STATUS' command in nand_command[_lp]() READ0 is sometimes used to exit GET STATUS mode. When this is the case no address cycles are requested, and we can use this information to detect that READSTART should not be issued after READ0 or that we shouldn't wait for the chip to be ready. Signed-off-by: Boris Brezillon Tested-by: Thomas Petazzoni --- drivers/mtd/nand/nand_base.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index 4b4fea4a3d1f..58a97e30b3f4 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -753,6 +753,16 @@ static void nand_command(struct mtd_info *mtd, unsigned int command, return; /* This applies to read commands */ + case NAND_CMD_READ0: + /* + * READ0 is sometimes used to exit GET STATUS mode. When this + * is the case no address cycles are requested, and we can use + * this information to detect that we should not wait for the + * device to be ready. + */ + if (column == -1 && page_addr == -1) + return; + default: /* * If we don't have access to the busy pin, we apply the given @@ -887,6 +897,15 @@ static void nand_command_lp(struct mtd_info *mtd, unsigned int command, return; case NAND_CMD_READ0: + /* + * READ0 is sometimes used to exit GET STATUS mode. When this + * is the case no address cycles are requested, and we can use + * this information to detect that READSTART should not be + * issued. + */ + if (column == -1 && page_addr == -1) + return; + chip->cmd_ctrl(mtd, NAND_CMD_READSTART, NAND_NCE | NAND_CLE | NAND_CTRL_CHANGE); chip->cmd_ctrl(mtd, NAND_CMD_NONE, -- cgit v1.2.3-59-g8ed1b From 79e0348c4e24fd1affdcf055e0269755580e0fcc Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 25 May 2017 13:50:20 +0900 Subject: mtd: nand: check ecc->total sanity in nand_scan_tail Drivers are supposed to set correct ecc->{size,strength,bytes} before calling nand_scan_tail(), but it does not complain about ecc->total bigger than oobsize. In this case, chip->scan_bbt() crashes due to memory corruption, but it is hard to debug. It would be kind to fail it earlier with a clear message. Signed-off-by: Masahiro Yamada Signed-off-by: Boris Brezillon --- drivers/mtd/nand/nand_base.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index 58a97e30b3f4..2404bb046b69 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -4789,6 +4789,11 @@ int nand_scan_tail(struct mtd_info *mtd) goto err_free; } ecc->total = ecc->steps * ecc->bytes; + if (ecc->total > mtd->oobsize) { + WARN(1, "Total number of ECC bytes exceeded oobsize\n"); + ret = -EINVAL; + goto err_free; + } /* * The number of bytes available for a client to place data into -- cgit v1.2.3-59-g8ed1b From 05b6c2313e91ac65915bde5e55bc6f194bfe22f3 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 31 May 2017 10:19:26 +0200 Subject: mtd: nand: atmel: mark resume function __maybe_unused The newly added suspend/resume support causes a harmless warning: drivers/mtd/nand/atmel/nand-controller.c:2513:12: error: 'atmel_nand_controller_resume' defined but not used [-Werror=unused-function] This shuts up the warning with a __maybe_unused annotation. Fixes: b107007a7114 ("mtd: nand: atmel: Add PM ops") Signed-off-by: Arnd Bergmann Signed-off-by: Boris Brezillon --- drivers/mtd/nand/atmel/nand-controller.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/nand/atmel/nand-controller.c b/drivers/mtd/nand/atmel/nand-controller.c index 6055831c953f..d24e67b95167 100644 --- a/drivers/mtd/nand/atmel/nand-controller.c +++ b/drivers/mtd/nand/atmel/nand-controller.c @@ -2510,7 +2510,7 @@ static int atmel_nand_controller_remove(struct platform_device *pdev) return nc->caps->ops->remove(nc); } -static int atmel_nand_controller_resume(struct device *dev) +static __maybe_unused int atmel_nand_controller_resume(struct device *dev) { struct atmel_nand_controller *nc = dev_get_drvdata(dev); struct atmel_nand *nand; -- cgit v1.2.3-59-g8ed1b From 2968698ba03187b09e84fbc709f0b5d19ddd94ff Mon Sep 17 00:00:00 2001 From: Xiaolei Li Date: Wed, 31 May 2017 16:26:38 +0800 Subject: mtd: nand: mediatek: update DT bindings Add MT2712 NAND Flash Controller dt bindings documentation. Signed-off-by: Xiaolei Li Reviewed-by: Matthias Brugger Signed-off-by: Boris Brezillon --- Documentation/devicetree/bindings/mtd/mtk-nand.txt | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/mtd/mtk-nand.txt b/Documentation/devicetree/bindings/mtd/mtk-nand.txt index 069c192ed5c2..dbf9e054c11c 100644 --- a/Documentation/devicetree/bindings/mtd/mtk-nand.txt +++ b/Documentation/devicetree/bindings/mtd/mtk-nand.txt @@ -12,7 +12,8 @@ tree nodes. The first part of NFC is NAND Controller Interface (NFI) HW. Required NFI properties: -- compatible: Should be "mediatek,mtxxxx-nfc". +- compatible: Should be one of "mediatek,mt2701-nfc", + "mediatek,mt2712-nfc". - reg: Base physical address and size of NFI. - interrupts: Interrupts of NFI. - clocks: NFI required clocks. @@ -141,7 +142,7 @@ Example: ============== Required BCH properties: -- compatible: Should be "mediatek,mtxxxx-ecc". +- compatible: Should be one of "mediatek,mt2701-ecc", "mediatek,mt2712-ecc". - reg: Base physical address and size of ECC. - interrupts: Interrupts of ECC. - clocks: ECC required clocks. -- cgit v1.2.3-59-g8ed1b From 582212ceb9bcd9ef0808497a8e066c4eef442e19 Mon Sep 17 00:00:00 2001 From: Xiaolei Li Date: Wed, 31 May 2017 16:26:39 +0800 Subject: mtd: nand: mediatek: refine register NFI_PAGEFMT setting The register NFI_PAGEFMT is always 32 bits length, so it is better to do register program using writel() compare with writew(). Signed-off-by: Xiaolei Li Signed-off-by: Boris Brezillon --- drivers/mtd/nand/mtk_nand.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/nand/mtk_nand.c b/drivers/mtd/nand/mtk_nand.c index 6c517c682939..c28f4b7025bf 100644 --- a/drivers/mtd/nand/mtk_nand.c +++ b/drivers/mtd/nand/mtk_nand.c @@ -408,7 +408,7 @@ static int mtk_nfc_hw_runtime_config(struct mtd_info *mtd) fmt |= mtk_nand->fdm.reg_size << PAGEFMT_FDM_SHIFT; fmt |= mtk_nand->fdm.ecc_size << PAGEFMT_FDM_ECC_SHIFT; - nfi_writew(nfc, fmt, NFI_PAGEFMT); + nfi_writel(nfc, fmt, NFI_PAGEFMT); nfc->ecc_cfg.strength = chip->ecc.strength; nfc->ecc_cfg.len = chip->ecc.size + mtk_nand->fdm.ecc_size; @@ -1009,7 +1009,7 @@ static inline void mtk_nfc_hw_init(struct mtk_nfc *nfc) * 0 : poll the status of the busy/ready signal after [7:4]*16 cycles. */ nfi_writew(nfc, 0xf1, NFI_CNRNB); - nfi_writew(nfc, PAGEFMT_8K_16K, NFI_PAGEFMT); + nfi_writel(nfc, PAGEFMT_8K_16K, NFI_PAGEFMT); mtk_nfc_hw_reset(nfc); -- cgit v1.2.3-59-g8ed1b From 7ec4a37c5d71f0a0bfeb1346d4e832a090ca292d Mon Sep 17 00:00:00 2001 From: Xiaolei Li Date: Wed, 31 May 2017 16:26:40 +0800 Subject: mtd: nand: mediatek: add support for different MTK NAND FLASH Controller IP ECC strength and spare size supported may be different among MTK NAND FLASH Controller IPs. This patch contains changes as following: (1) add new struct mtk_nfc_caps to support different spare size. (2) add new struct mtk_ecc_caps to support different ecc strength. (3) remove ECC_CNFG_xBIT define, use a for loop to do ecc strength config. (4) remove PAGEFMT_SPARE_ define, use a for loop to do spare format config. (5) malloc ecc->eccdata buffer according to max ecc strength of this IP. Signed-off-by: Xiaolei Li Signed-off-by: Boris Brezillon --- drivers/mtd/nand/mtk_ecc.c | 181 ++++++++++++++++++-------------------------- drivers/mtd/nand/mtk_ecc.h | 2 +- drivers/mtd/nand/mtk_nand.c | 169 +++++++++++++++++++---------------------- 3 files changed, 153 insertions(+), 199 deletions(-) diff --git a/drivers/mtd/nand/mtk_ecc.c b/drivers/mtd/nand/mtk_ecc.c index dbf256217b3e..ae513038b34f 100644 --- a/drivers/mtd/nand/mtk_ecc.c +++ b/drivers/mtd/nand/mtk_ecc.c @@ -33,26 +33,6 @@ #define ECC_ENCCON (0x00) #define ECC_ENCCNFG (0x04) -#define ECC_CNFG_4BIT (0) -#define ECC_CNFG_6BIT (1) -#define ECC_CNFG_8BIT (2) -#define ECC_CNFG_10BIT (3) -#define ECC_CNFG_12BIT (4) -#define ECC_CNFG_14BIT (5) -#define ECC_CNFG_16BIT (6) -#define ECC_CNFG_18BIT (7) -#define ECC_CNFG_20BIT (8) -#define ECC_CNFG_22BIT (9) -#define ECC_CNFG_24BIT (0xa) -#define ECC_CNFG_28BIT (0xb) -#define ECC_CNFG_32BIT (0xc) -#define ECC_CNFG_36BIT (0xd) -#define ECC_CNFG_40BIT (0xe) -#define ECC_CNFG_44BIT (0xf) -#define ECC_CNFG_48BIT (0x10) -#define ECC_CNFG_52BIT (0x11) -#define ECC_CNFG_56BIT (0x12) -#define ECC_CNFG_60BIT (0x13) #define ECC_MODE_SHIFT (5) #define ECC_MS_SHIFT (16) #define ECC_ENCDIADDR (0x08) @@ -66,7 +46,6 @@ #define DEC_CNFG_CORRECT (0x3 << 12) #define ECC_DECIDLE (0x10C) #define ECC_DECENUM0 (0x114) -#define ERR_MASK (0x3f) #define ECC_DECDONE (0x124) #define ECC_DECIRQ_EN (0x200) #define ECC_DECIRQ_STA (0x204) @@ -78,8 +57,15 @@ #define ECC_IRQ_REG(op) ((op) == ECC_ENCODE ? \ ECC_ENCIRQ_EN : ECC_DECIRQ_EN) +struct mtk_ecc_caps { + u32 err_mask; + const u8 *ecc_strength; + u8 num_ecc_strength; +}; + struct mtk_ecc { struct device *dev; + const struct mtk_ecc_caps *caps; void __iomem *regs; struct clk *clk; @@ -87,7 +73,13 @@ struct mtk_ecc { struct mutex lock; u32 sectors; - u8 eccdata[112]; + u8 *eccdata; +}; + +/* ecc strength that mt2701 supports */ +static const u8 ecc_strength_mt2701[] = { + 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 28, 32, 36, + 40, 44, 48, 52, 56, 60 }; static inline void mtk_ecc_wait_idle(struct mtk_ecc *ecc, @@ -136,77 +128,24 @@ static irqreturn_t mtk_ecc_irq(int irq, void *id) return IRQ_HANDLED; } -static void mtk_ecc_config(struct mtk_ecc *ecc, struct mtk_ecc_config *config) +static int mtk_ecc_config(struct mtk_ecc *ecc, struct mtk_ecc_config *config) { - u32 ecc_bit = ECC_CNFG_4BIT, dec_sz, enc_sz; - u32 reg; - - switch (config->strength) { - case 4: - ecc_bit = ECC_CNFG_4BIT; - break; - case 6: - ecc_bit = ECC_CNFG_6BIT; - break; - case 8: - ecc_bit = ECC_CNFG_8BIT; - break; - case 10: - ecc_bit = ECC_CNFG_10BIT; - break; - case 12: - ecc_bit = ECC_CNFG_12BIT; - break; - case 14: - ecc_bit = ECC_CNFG_14BIT; - break; - case 16: - ecc_bit = ECC_CNFG_16BIT; - break; - case 18: - ecc_bit = ECC_CNFG_18BIT; - break; - case 20: - ecc_bit = ECC_CNFG_20BIT; - break; - case 22: - ecc_bit = ECC_CNFG_22BIT; - break; - case 24: - ecc_bit = ECC_CNFG_24BIT; - break; - case 28: - ecc_bit = ECC_CNFG_28BIT; - break; - case 32: - ecc_bit = ECC_CNFG_32BIT; - break; - case 36: - ecc_bit = ECC_CNFG_36BIT; - break; - case 40: - ecc_bit = ECC_CNFG_40BIT; - break; - case 44: - ecc_bit = ECC_CNFG_44BIT; - break; - case 48: - ecc_bit = ECC_CNFG_48BIT; - break; - case 52: - ecc_bit = ECC_CNFG_52BIT; - break; - case 56: - ecc_bit = ECC_CNFG_56BIT; - break; - case 60: - ecc_bit = ECC_CNFG_60BIT; - break; - default: - dev_err(ecc->dev, "invalid strength %d, default to 4 bits\n", + u32 ecc_bit, dec_sz, enc_sz; + u32 reg, i; + + for (i = 0; i < ecc->caps->num_ecc_strength; i++) { + if (ecc->caps->ecc_strength[i] == config->strength) + break; + } + + if (i == ecc->caps->num_ecc_strength) { + dev_err(ecc->dev, "invalid ecc strength %d\n", config->strength); + return -EINVAL; } + ecc_bit = i; + if (config->op == ECC_ENCODE) { /* configure ECC encoder (in bits) */ enc_sz = config->len << 3; @@ -232,6 +171,8 @@ static void mtk_ecc_config(struct mtk_ecc *ecc, struct mtk_ecc_config *config) if (config->sectors) ecc->sectors = 1 << (config->sectors - 1); } + + return 0; } void mtk_ecc_get_stats(struct mtk_ecc *ecc, struct mtk_ecc_stats *stats, @@ -247,8 +188,8 @@ void mtk_ecc_get_stats(struct mtk_ecc *ecc, struct mtk_ecc_stats *stats, offset = (i >> 2) << 2; err = readl(ecc->regs + ECC_DECENUM0 + offset); err = err >> ((i % 4) * 8); - err &= ERR_MASK; - if (err == ERR_MASK) { + err &= ecc->caps->err_mask; + if (err == ecc->caps->err_mask) { /* uncorrectable errors */ stats->failed++; continue; @@ -322,7 +263,11 @@ int mtk_ecc_enable(struct mtk_ecc *ecc, struct mtk_ecc_config *config) } mtk_ecc_wait_idle(ecc, op); - mtk_ecc_config(ecc, config); + + ret = mtk_ecc_config(ecc, config); + if (ret) + return ret; + writew(ECC_OP_ENABLE, ecc->regs + ECC_CTL_REG(op)); init_completion(&ecc->done); @@ -409,37 +354,66 @@ timeout: } EXPORT_SYMBOL(mtk_ecc_encode); -void mtk_ecc_adjust_strength(u32 *p) +void mtk_ecc_adjust_strength(struct mtk_ecc *ecc, u32 *p) { - u32 ecc[] = {4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 28, 32, 36, - 40, 44, 48, 52, 56, 60}; + const u8 *ecc_strength = ecc->caps->ecc_strength; int i; - for (i = 0; i < ARRAY_SIZE(ecc); i++) { - if (*p <= ecc[i]) { + for (i = 0; i < ecc->caps->num_ecc_strength; i++) { + if (*p <= ecc_strength[i]) { if (!i) - *p = ecc[i]; - else if (*p != ecc[i]) - *p = ecc[i - 1]; + *p = ecc_strength[i]; + else if (*p != ecc_strength[i]) + *p = ecc_strength[i - 1]; return; } } - *p = ecc[ARRAY_SIZE(ecc) - 1]; + *p = ecc_strength[ecc->caps->num_ecc_strength - 1]; } EXPORT_SYMBOL(mtk_ecc_adjust_strength); +static const struct mtk_ecc_caps mtk_ecc_caps_mt2701 = { + .err_mask = 0x3f, + .ecc_strength = ecc_strength_mt2701, + .num_ecc_strength = 20, +}; + +static const struct of_device_id mtk_ecc_dt_match[] = { + { + .compatible = "mediatek,mt2701-ecc", + .data = &mtk_ecc_caps_mt2701, + }, + {}, +}; + static int mtk_ecc_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct mtk_ecc *ecc; struct resource *res; + const struct of_device_id *of_ecc_id = NULL; + u32 max_eccdata_size; int irq, ret; ecc = devm_kzalloc(dev, sizeof(*ecc), GFP_KERNEL); if (!ecc) return -ENOMEM; + of_ecc_id = of_match_device(mtk_ecc_dt_match, &pdev->dev); + if (!of_ecc_id) + return -ENODEV; + + ecc->caps = of_ecc_id->data; + + max_eccdata_size = ecc->caps->num_ecc_strength - 1; + max_eccdata_size = ecc->caps->ecc_strength[max_eccdata_size]; + max_eccdata_size = (max_eccdata_size * ECC_PARITY_BITS + 7) >> 3; + max_eccdata_size = round_up(max_eccdata_size, 4); + ecc->eccdata = devm_kzalloc(dev, max_eccdata_size, GFP_KERNEL); + if (!ecc->eccdata) + return -ENOMEM; + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); ecc->regs = devm_ioremap_resource(dev, res); if (IS_ERR(ecc->regs)) { @@ -508,11 +482,6 @@ static int mtk_ecc_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(mtk_ecc_pm_ops, mtk_ecc_suspend, mtk_ecc_resume); #endif -static const struct of_device_id mtk_ecc_dt_match[] = { - { .compatible = "mediatek,mt2701-ecc" }, - {}, -}; - MODULE_DEVICE_TABLE(of, mtk_ecc_dt_match); static struct platform_driver mtk_ecc_driver = { diff --git a/drivers/mtd/nand/mtk_ecc.h b/drivers/mtd/nand/mtk_ecc.h index cbeba5cd1c13..d245c14f1b80 100644 --- a/drivers/mtd/nand/mtk_ecc.h +++ b/drivers/mtd/nand/mtk_ecc.h @@ -42,7 +42,7 @@ void mtk_ecc_get_stats(struct mtk_ecc *, struct mtk_ecc_stats *, int); int mtk_ecc_wait_done(struct mtk_ecc *, enum mtk_ecc_operation); int mtk_ecc_enable(struct mtk_ecc *, struct mtk_ecc_config *); void mtk_ecc_disable(struct mtk_ecc *); -void mtk_ecc_adjust_strength(u32 *); +void mtk_ecc_adjust_strength(struct mtk_ecc *ecc, u32 *p); struct mtk_ecc *of_mtk_ecc_get(struct device_node *); void mtk_ecc_release(struct mtk_ecc *); diff --git a/drivers/mtd/nand/mtk_nand.c b/drivers/mtd/nand/mtk_nand.c index c28f4b7025bf..e428669f41f1 100644 --- a/drivers/mtd/nand/mtk_nand.c +++ b/drivers/mtd/nand/mtk_nand.c @@ -24,6 +24,7 @@ #include #include #include +#include #include "mtk_ecc.h" /* NAND controller register definition */ @@ -38,23 +39,6 @@ #define NFI_PAGEFMT (0x04) #define PAGEFMT_FDM_ECC_SHIFT (12) #define PAGEFMT_FDM_SHIFT (8) -#define PAGEFMT_SPARE_16 (0) -#define PAGEFMT_SPARE_26 (1) -#define PAGEFMT_SPARE_27 (2) -#define PAGEFMT_SPARE_28 (3) -#define PAGEFMT_SPARE_32 (4) -#define PAGEFMT_SPARE_36 (5) -#define PAGEFMT_SPARE_40 (6) -#define PAGEFMT_SPARE_44 (7) -#define PAGEFMT_SPARE_48 (8) -#define PAGEFMT_SPARE_49 (9) -#define PAGEFMT_SPARE_50 (0xa) -#define PAGEFMT_SPARE_51 (0xb) -#define PAGEFMT_SPARE_52 (0xc) -#define PAGEFMT_SPARE_62 (0xd) -#define PAGEFMT_SPARE_63 (0xe) -#define PAGEFMT_SPARE_64 (0xf) -#define PAGEFMT_SPARE_SHIFT (4) #define PAGEFMT_SEC_SEL_512 BIT(2) #define PAGEFMT_512_2K (0) #define PAGEFMT_2K_4K (1) @@ -115,6 +99,13 @@ #define MTK_RESET_TIMEOUT (1000000) #define MTK_MAX_SECTOR (16) #define MTK_NAND_MAX_NSELS (2) +#define MTK_NFC_MIN_SPARE (16) + +struct mtk_nfc_caps { + const u8 *spare_size; + u8 num_spare_size; + u8 pageformat_spare_shift; +}; struct mtk_nfc_bad_mark_ctl { void (*bm_swap)(struct mtd_info *, u8 *buf, int raw); @@ -155,6 +146,7 @@ struct mtk_nfc { struct mtk_ecc *ecc; struct device *dev; + const struct mtk_nfc_caps *caps; void __iomem *regs; struct completion done; @@ -163,6 +155,15 @@ struct mtk_nfc { u8 *buffer; }; +/* + * supported spare size of each IP. + * order should be the same with the spare size bitfiled defination of + * register NFI_PAGEFMT. + */ +static const u8 spare_size_mt2701[] = { + 16, 26, 27, 28, 32, 36, 40, 44, 48, 49, 50, 51, 52, 62, 63, 64 +}; + static inline struct mtk_nfc_nand_chip *to_mtk_nand(struct nand_chip *nand) { return container_of(nand, struct mtk_nfc_nand_chip, nand); @@ -308,7 +309,7 @@ static int mtk_nfc_hw_runtime_config(struct mtd_info *mtd) struct nand_chip *chip = mtd_to_nand(mtd); struct mtk_nfc_nand_chip *mtk_nand = to_mtk_nand(chip); struct mtk_nfc *nfc = nand_get_controller_data(chip); - u32 fmt, spare; + u32 fmt, spare, i; if (!mtd->writesize) return 0; @@ -352,60 +353,18 @@ static int mtk_nfc_hw_runtime_config(struct mtd_info *mtd) if (chip->ecc.size == 1024) spare >>= 1; - switch (spare) { - case 16: - fmt |= (PAGEFMT_SPARE_16 << PAGEFMT_SPARE_SHIFT); - break; - case 26: - fmt |= (PAGEFMT_SPARE_26 << PAGEFMT_SPARE_SHIFT); - break; - case 27: - fmt |= (PAGEFMT_SPARE_27 << PAGEFMT_SPARE_SHIFT); - break; - case 28: - fmt |= (PAGEFMT_SPARE_28 << PAGEFMT_SPARE_SHIFT); - break; - case 32: - fmt |= (PAGEFMT_SPARE_32 << PAGEFMT_SPARE_SHIFT); - break; - case 36: - fmt |= (PAGEFMT_SPARE_36 << PAGEFMT_SPARE_SHIFT); - break; - case 40: - fmt |= (PAGEFMT_SPARE_40 << PAGEFMT_SPARE_SHIFT); - break; - case 44: - fmt |= (PAGEFMT_SPARE_44 << PAGEFMT_SPARE_SHIFT); - break; - case 48: - fmt |= (PAGEFMT_SPARE_48 << PAGEFMT_SPARE_SHIFT); - break; - case 49: - fmt |= (PAGEFMT_SPARE_49 << PAGEFMT_SPARE_SHIFT); - break; - case 50: - fmt |= (PAGEFMT_SPARE_50 << PAGEFMT_SPARE_SHIFT); - break; - case 51: - fmt |= (PAGEFMT_SPARE_51 << PAGEFMT_SPARE_SHIFT); - break; - case 52: - fmt |= (PAGEFMT_SPARE_52 << PAGEFMT_SPARE_SHIFT); - break; - case 62: - fmt |= (PAGEFMT_SPARE_62 << PAGEFMT_SPARE_SHIFT); - break; - case 63: - fmt |= (PAGEFMT_SPARE_63 << PAGEFMT_SPARE_SHIFT); - break; - case 64: - fmt |= (PAGEFMT_SPARE_64 << PAGEFMT_SPARE_SHIFT); - break; - default: - dev_err(nfc->dev, "invalid spare per sector %d\n", spare); + for (i = 0; i < nfc->caps->num_spare_size; i++) { + if (nfc->caps->spare_size[i] == spare) + break; + } + + if (i == nfc->caps->num_spare_size) { + dev_err(nfc->dev, "invalid spare size %d\n", spare); return -EINVAL; } + fmt |= i << nfc->caps->pageformat_spare_shift; + fmt |= mtk_nand->fdm.reg_size << PAGEFMT_FDM_SHIFT; fmt |= mtk_nand->fdm.ecc_size << PAGEFMT_FDM_ECC_SHIFT; nfi_writel(nfc, fmt, NFI_PAGEFMT); @@ -1131,12 +1090,12 @@ static void mtk_nfc_set_bad_mark_ctl(struct mtk_nfc_bad_mark_ctl *bm_ctl, } } -static void mtk_nfc_set_spare_per_sector(u32 *sps, struct mtd_info *mtd) +static int mtk_nfc_set_spare_per_sector(u32 *sps, struct mtd_info *mtd) { struct nand_chip *nand = mtd_to_nand(mtd); - u32 spare[] = {16, 26, 27, 28, 32, 36, 40, 44, - 48, 49, 50, 51, 52, 62, 63, 64}; - u32 eccsteps, i; + struct mtk_nfc *nfc = nand_get_controller_data(nand); + const u8 *spare = nfc->caps->spare_size; + u32 eccsteps, i, closest_spare = 0; eccsteps = mtd->writesize / nand->ecc.size; *sps = mtd->oobsize / eccsteps; @@ -1144,28 +1103,31 @@ static void mtk_nfc_set_spare_per_sector(u32 *sps, struct mtd_info *mtd) if (nand->ecc.size == 1024) *sps >>= 1; - for (i = 0; i < ARRAY_SIZE(spare); i++) { - if (*sps <= spare[i]) { - if (!i) - *sps = spare[i]; - else if (*sps != spare[i]) - *sps = spare[i - 1]; - break; + if (*sps < MTK_NFC_MIN_SPARE) + return -EINVAL; + + for (i = 0; i < nfc->caps->num_spare_size; i++) { + if (*sps >= spare[i] && spare[i] >= spare[closest_spare]) { + closest_spare = i; + if (*sps == spare[i]) + break; } } - if (i >= ARRAY_SIZE(spare)) - *sps = spare[ARRAY_SIZE(spare) - 1]; + *sps = spare[closest_spare]; if (nand->ecc.size == 1024) *sps <<= 1; + + return 0; } static int mtk_nfc_ecc_init(struct device *dev, struct mtd_info *mtd) { struct nand_chip *nand = mtd_to_nand(mtd); + struct mtk_nfc *nfc = nand_get_controller_data(nand); u32 spare; - int free; + int free, ret; /* support only ecc hw mode */ if (nand->ecc.mode != NAND_ECC_HW) { @@ -1194,7 +1156,9 @@ static int mtk_nfc_ecc_init(struct device *dev, struct mtd_info *mtd) nand->ecc.size = 1024; } - mtk_nfc_set_spare_per_sector(&spare, mtd); + ret = mtk_nfc_set_spare_per_sector(&spare, mtd); + if (ret) + return ret; /* calculate oob bytes except ecc parity data */ free = ((nand->ecc.strength * ECC_PARITY_BITS) + 7) >> 3; @@ -1214,7 +1178,7 @@ static int mtk_nfc_ecc_init(struct device *dev, struct mtd_info *mtd) } } - mtk_ecc_adjust_strength(&nand->ecc.strength); + mtk_ecc_adjust_strength(nfc->ecc, &nand->ecc.strength); dev_info(dev, "eccsize %d eccstrength %d\n", nand->ecc.size, nand->ecc.strength); @@ -1312,7 +1276,10 @@ static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc, return -EINVAL; } - mtk_nfc_set_spare_per_sector(&chip->spare_per_sector, mtd); + ret = mtk_nfc_set_spare_per_sector(&chip->spare_per_sector, mtd); + if (ret) + return ret; + mtk_nfc_set_fdm(&chip->fdm, mtd); mtk_nfc_set_bad_mark_ctl(&chip->bad_mark, mtd); @@ -1354,12 +1321,28 @@ static int mtk_nfc_nand_chips_init(struct device *dev, struct mtk_nfc *nfc) return 0; } +static const struct mtk_nfc_caps mtk_nfc_caps_mt2701 = { + .spare_size = spare_size_mt2701, + .num_spare_size = 16, + .pageformat_spare_shift = 4, +}; + +static const struct of_device_id mtk_nfc_id_table[] = { + { + .compatible = "mediatek,mt2701-nfc", + .data = &mtk_nfc_caps_mt2701, + }, + {} +}; +MODULE_DEVICE_TABLE(of, mtk_nfc_id_table); + static int mtk_nfc_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct device_node *np = dev->of_node; struct mtk_nfc *nfc; struct resource *res; + const struct of_device_id *of_nfc_id = NULL; int ret, irq; nfc = devm_kzalloc(dev, sizeof(*nfc), GFP_KERNEL); @@ -1423,6 +1406,14 @@ static int mtk_nfc_probe(struct platform_device *pdev) goto clk_disable; } + of_nfc_id = of_match_device(mtk_nfc_id_table, &pdev->dev); + if (!of_nfc_id) { + ret = -ENODEV; + goto clk_disable; + } + + nfc->caps = of_nfc_id->data; + platform_set_drvdata(pdev, nfc); ret = mtk_nfc_nand_chips_init(dev, nfc); @@ -1503,12 +1494,6 @@ static int mtk_nfc_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(mtk_nfc_pm_ops, mtk_nfc_suspend, mtk_nfc_resume); #endif -static const struct of_device_id mtk_nfc_id_table[] = { - { .compatible = "mediatek,mt2701-nfc" }, - {} -}; -MODULE_DEVICE_TABLE(of, mtk_nfc_id_table); - static struct platform_driver mtk_nfc_driver = { .probe = mtk_nfc_probe, .remove = mtk_nfc_remove, -- cgit v1.2.3-59-g8ed1b From 30ee809e980b07f467fca3e7ee16e8d034cf41af Mon Sep 17 00:00:00 2001 From: Xiaolei Li Date: Wed, 31 May 2017 16:26:41 +0800 Subject: mtd: nand: mediatek: add support for MT2712 NAND FLASH Controller MT2712 NAND FLASH Controller is similar to MT2701 except those following: (1) MT2712 supports up to 148B spare size per 1KB size sector (the same with 74B spare size per 512B size sector). There are three new spare format: 61, 67, 74. (2) MT2712 supports up to 80 bit ecc strength. There are three new ecc strength level: 68, 72, 80. (3) MT2712 ECC encode parity data register's start offset is 0x300, and different with 0x10 of MT2701. (4) MT2712 improves ecc irq function. When ECC works in ECC_NFI_MODE, MT2701 will generate ecc irq number the same with ecc steps during page read. However, MT2712 can only generate one ecc irq. Changes of this patch are: (1) add two new variables named pg_irq_sel, encode_parity_reg0 in struct mtk_ecc_caps. (2) add new bitfield ECC_PG_IRQ_SEL for register ECC_IRQ_REG. (3) add ecc strength array of mt2712. (4) add spare size array of mt2712. (5) add mt2712 nfc and ecc device compatiable and data. Signed-off-by: Xiaolei Li Signed-off-by: Boris Brezillon --- drivers/mtd/nand/mtk_ecc.c | 39 +++++++++++++++++++++++++++++++++++---- drivers/mtd/nand/mtk_nand.c | 14 ++++++++++++++ 2 files changed, 49 insertions(+), 4 deletions(-) diff --git a/drivers/mtd/nand/mtk_ecc.c b/drivers/mtd/nand/mtk_ecc.c index ae513038b34f..4958121cb827 100644 --- a/drivers/mtd/nand/mtk_ecc.c +++ b/drivers/mtd/nand/mtk_ecc.c @@ -28,6 +28,7 @@ #define ECC_IDLE_MASK BIT(0) #define ECC_IRQ_EN BIT(0) +#define ECC_PG_IRQ_SEL BIT(1) #define ECC_OP_ENABLE (1) #define ECC_OP_DISABLE (0) @@ -37,7 +38,6 @@ #define ECC_MS_SHIFT (16) #define ECC_ENCDIADDR (0x08) #define ECC_ENCIDLE (0x0C) -#define ECC_ENCPAR(x) (0x10 + (x) * sizeof(u32)) #define ECC_ENCIRQ_EN (0x80) #define ECC_ENCIRQ_STA (0x84) #define ECC_DECCON (0x100) @@ -61,6 +61,8 @@ struct mtk_ecc_caps { u32 err_mask; const u8 *ecc_strength; u8 num_ecc_strength; + u32 encode_parity_reg0; + int pg_irq_sel; }; struct mtk_ecc { @@ -76,12 +78,17 @@ struct mtk_ecc { u8 *eccdata; }; -/* ecc strength that mt2701 supports */ +/* ecc strength that each IP supports */ static const u8 ecc_strength_mt2701[] = { 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 28, 32, 36, 40, 44, 48, 52, 56, 60 }; +static const u8 ecc_strength_mt2712[] = { + 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 28, 32, 36, + 40, 44, 48, 52, 56, 60, 68, 72, 80 +}; + static inline void mtk_ecc_wait_idle(struct mtk_ecc *ecc, enum mtk_ecc_operation op) { @@ -254,6 +261,7 @@ EXPORT_SYMBOL(of_mtk_ecc_get); int mtk_ecc_enable(struct mtk_ecc *ecc, struct mtk_ecc_config *config) { enum mtk_ecc_operation op = config->op; + u16 reg_val; int ret; ret = mutex_lock_interruptible(&ecc->lock); @@ -271,7 +279,15 @@ int mtk_ecc_enable(struct mtk_ecc *ecc, struct mtk_ecc_config *config) writew(ECC_OP_ENABLE, ecc->regs + ECC_CTL_REG(op)); init_completion(&ecc->done); - writew(ECC_IRQ_EN, ecc->regs + ECC_IRQ_REG(op)); + reg_val = ECC_IRQ_EN; + /* + * For ECC_NFI_MODE, if ecc->caps->pg_irq_sel is 1, then it + * means this chip can only generate one ecc irq during page + * read / write. If is 0, generate one ecc irq each ecc step. + */ + if ((ecc->caps->pg_irq_sel) && (config->mode == ECC_NFI_MODE)) + reg_val |= ECC_PG_IRQ_SEL; + writew(reg_val, ecc->regs + ECC_IRQ_REG(op)); return 0; } @@ -341,7 +357,9 @@ int mtk_ecc_encode(struct mtk_ecc *ecc, struct mtk_ecc_config *config, len = (config->strength * ECC_PARITY_BITS + 7) >> 3; /* write the parity bytes generated by the ECC back to temp buffer */ - __ioread32_copy(ecc->eccdata, ecc->regs + ECC_ENCPAR(0), round_up(len, 4)); + __ioread32_copy(ecc->eccdata, + ecc->regs + ecc->caps->encode_parity_reg0, + round_up(len, 4)); /* copy into possibly unaligned OOB region with actual length */ memcpy(data + bytes, ecc->eccdata, len); @@ -377,12 +395,25 @@ static const struct mtk_ecc_caps mtk_ecc_caps_mt2701 = { .err_mask = 0x3f, .ecc_strength = ecc_strength_mt2701, .num_ecc_strength = 20, + .encode_parity_reg0 = 0x10, + .pg_irq_sel = 0, +}; + +static const struct mtk_ecc_caps mtk_ecc_caps_mt2712 = { + .err_mask = 0x7f, + .ecc_strength = ecc_strength_mt2712, + .num_ecc_strength = 23, + .encode_parity_reg0 = 0x300, + .pg_irq_sel = 1, }; static const struct of_device_id mtk_ecc_dt_match[] = { { .compatible = "mediatek,mt2701-ecc", .data = &mtk_ecc_caps_mt2701, + }, { + .compatible = "mediatek,mt2712-ecc", + .data = &mtk_ecc_caps_mt2712, }, {}, }; diff --git a/drivers/mtd/nand/mtk_nand.c b/drivers/mtd/nand/mtk_nand.c index e428669f41f1..4d9ee278b9a0 100644 --- a/drivers/mtd/nand/mtk_nand.c +++ b/drivers/mtd/nand/mtk_nand.c @@ -164,6 +164,11 @@ static const u8 spare_size_mt2701[] = { 16, 26, 27, 28, 32, 36, 40, 44, 48, 49, 50, 51, 52, 62, 63, 64 }; +static const u8 spare_size_mt2712[] = { + 16, 26, 27, 28, 32, 36, 40, 44, 48, 49, 50, 51, 52, 62, 61, 63, 64, 67, + 74 +}; + static inline struct mtk_nfc_nand_chip *to_mtk_nand(struct nand_chip *nand) { return container_of(nand, struct mtk_nfc_nand_chip, nand); @@ -1327,10 +1332,19 @@ static const struct mtk_nfc_caps mtk_nfc_caps_mt2701 = { .pageformat_spare_shift = 4, }; +static const struct mtk_nfc_caps mtk_nfc_caps_mt2712 = { + .spare_size = spare_size_mt2712, + .num_spare_size = 19, + .pageformat_spare_shift = 16, +}; + static const struct of_device_id mtk_nfc_id_table[] = { { .compatible = "mediatek,mt2701-nfc", .data = &mtk_nfc_caps_mt2701, + }, { + .compatible = "mediatek,mt2712-nfc", + .data = &mtk_nfc_caps_mt2712, }, {} }; -- cgit v1.2.3-59-g8ed1b From 4db4d35ebda390b5287d758fdd51b26c24fbc26b Mon Sep 17 00:00:00 2001 From: Chris Packham Date: Thu, 25 May 2017 11:49:12 +1200 Subject: mtd: mchp23k256: Add OF device ID table This allows registering of this device via a Device Tree. Signed-off-by: Chris Packham Reviewed-by: Andrew Lunn Tested-by: Andrew Lunn Acked-by: Boris Brezillon Acked-by: Rob Herring Signed-off-by: Brian Norris --- .../devicetree/bindings/mtd/microchip,mchp23k256.txt | 18 ++++++++++++++++++ drivers/mtd/devices/mchp23k256.c | 8 ++++++++ 2 files changed, 26 insertions(+) create mode 100644 Documentation/devicetree/bindings/mtd/microchip,mchp23k256.txt diff --git a/Documentation/devicetree/bindings/mtd/microchip,mchp23k256.txt b/Documentation/devicetree/bindings/mtd/microchip,mchp23k256.txt new file mode 100644 index 000000000000..25e5ad38b0f0 --- /dev/null +++ b/Documentation/devicetree/bindings/mtd/microchip,mchp23k256.txt @@ -0,0 +1,18 @@ +* MTD SPI driver for Microchip 23K256 (and similar) serial SRAM + +Required properties: +- #address-cells, #size-cells : Must be present if the device has sub-nodes + representing partitions. +- compatible : Must be "microchip,mchp23k256" +- reg : Chip-Select number +- spi-max-frequency : Maximum frequency of the SPI bus the chip can operate at + +Example: + + spi-sram@0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "microchip,mchp23k256"; + reg = <0>; + spi-max-frequency = <20000000>; + }; diff --git a/drivers/mtd/devices/mchp23k256.c b/drivers/mtd/devices/mchp23k256.c index e237db9f1bdb..9d8306a15833 100644 --- a/drivers/mtd/devices/mchp23k256.c +++ b/drivers/mtd/devices/mchp23k256.c @@ -19,6 +19,7 @@ #include #include #include +#include struct mchp23k256_flash { struct spi_device *spi; @@ -166,9 +167,16 @@ static int mchp23k256_remove(struct spi_device *spi) return mtd_device_unregister(&flash->mtd); } +static const struct of_device_id mchp23k256_of_table[] = { + { .compatible = "microchip,mchp23k256" }, + {} +}; +MODULE_DEVICE_TABLE(of, mchp23k256_of_table); + static struct spi_driver mchp23k256_driver = { .driver = { .name = "mchp23k256", + .of_match_table = of_match_ptr(mchp23k256_of_table), }, .probe = mchp23k256_probe, .remove = mchp23k256_remove, -- cgit v1.2.3-59-g8ed1b From 44225c9c79ae288b5f1668dc5dda7ba9f87995f1 Mon Sep 17 00:00:00 2001 From: Chris Packham Date: Thu, 25 May 2017 11:49:13 +1200 Subject: mtd: mchp23k256: switch to mtd_device_register() Use mtd_device_register() instead of mtd_device_parse_register() to eliminate two unused parameters. Signed-off-by: Chris Packham Reviewed-by: Andrew Lunn Tested-by: Andrew Lunn Acked-by: Boris Brezillon Signed-off-by: Brian Norris --- drivers/mtd/devices/mchp23k256.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/devices/mchp23k256.c b/drivers/mtd/devices/mchp23k256.c index 9d8306a15833..2542f5b8b63f 100644 --- a/drivers/mtd/devices/mchp23k256.c +++ b/drivers/mtd/devices/mchp23k256.c @@ -151,9 +151,8 @@ static int mchp23k256_probe(struct spi_device *spi) flash->mtd._read = mchp23k256_read; flash->mtd._write = mchp23k256_write; - err = mtd_device_parse_register(&flash->mtd, NULL, NULL, - data ? data->parts : NULL, - data ? data->nr_parts : 0); + err = mtd_device_register(&flash->mtd, data ? data->parts : NULL, + data ? data->nr_parts : 0); if (err) return err; -- cgit v1.2.3-59-g8ed1b From 77a73f3caece06d1d17268f43ec39c5779e6ce24 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Fri, 2 Jun 2017 13:57:03 +0200 Subject: rtc: sysfs: make name uniform The name sysfs attribute is not useful in its current form because of all the drivers: - 3 are using the feature correctly - 2 are clearly misusing it - 60 are using driver.name, either directly or indirectly - 46 are using pdev->name - 8 are using client->name - 31 are using a variation of driver.name (addition or removal of rtc-, -rtc, _rtc, rtc_) Make it uniform and use the driver name and the device name. Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-sysfs.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-sysfs.c b/drivers/rtc/rtc-sysfs.c index 1218d5d4224d..e364550eb9a7 100644 --- a/drivers/rtc/rtc-sysfs.c +++ b/drivers/rtc/rtc-sysfs.c @@ -27,7 +27,8 @@ static ssize_t name_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "%s\n", to_rtc_device(dev)->name); + return sprintf(buf, "%s %s\n", dev_driver_string(dev->parent), + dev_name(dev->parent)); } static DEVICE_ATTR_RO(name); -- cgit v1.2.3-59-g8ed1b From 9f8606533b961b06c258cf4804e3379aa14c5951 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Fri, 2 Jun 2017 14:01:37 +0200 Subject: rtc: dev: remove rtc->name from debug message rtc->name is superfluous here because the rtc is already registered at that point and its name has already been printed. Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-dev.c b/drivers/rtc/rtc-dev.c index e81a8711fea7..794bc4fa4937 100644 --- a/drivers/rtc/rtc-dev.c +++ b/drivers/rtc/rtc-dev.c @@ -464,7 +464,7 @@ void rtc_dev_prepare(struct rtc_device *rtc) return; if (rtc->id >= RTC_DEV_MAX) { - dev_dbg(&rtc->dev, "%s: too many RTC devices\n", rtc->name); + dev_dbg(&rtc->dev, "too many RTC devices\n"); return; } -- cgit v1.2.3-59-g8ed1b From f09e706992bd031f0d94b77e40074e7fea5c89a9 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Fri, 2 Jun 2017 14:03:39 +0200 Subject: rtc: pcf8563: avoid using rtc->name pcf8563->rtc->name is a copy of pcf8563_driver.driver.name, use it instead Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-pcf8563.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-pcf8563.c b/drivers/rtc/rtc-pcf8563.c index 1227ceab61ee..cea6ea4df970 100644 --- a/drivers/rtc/rtc-pcf8563.c +++ b/drivers/rtc/rtc-pcf8563.c @@ -606,7 +606,7 @@ static int pcf8563_probe(struct i2c_client *client, err = devm_request_threaded_irq(&client->dev, client->irq, NULL, pcf8563_irq, IRQF_SHARED|IRQF_ONESHOT|IRQF_TRIGGER_FALLING, - pcf8563->rtc->name, client); + pcf8563_driver.driver.name, client); if (err) { dev_err(&client->dev, "unable to request IRQ %d\n", client->irq); -- cgit v1.2.3-59-g8ed1b From 4b9e2a0c0591d2789a43414b8299466800873aea Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Fri, 2 Jun 2017 14:13:21 +0200 Subject: rtc: ds1307: avoid using rtc-name ds1307->rtc->name is a copy of ds1307->name, use it instead. Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ds1307.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index a264938500af..16ace2fb0c0a 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -1567,7 +1567,7 @@ read_rtc: err = devm_request_threaded_irq(ds1307->dev, ds1307->irq, NULL, irq_handler, IRQF_SHARED | IRQF_ONESHOT, - ds1307->rtc->name, ds1307); + ds1307->name, ds1307); if (err) { client->irq = 0; device_set_wakeup_capable(ds1307->dev, false); -- cgit v1.2.3-59-g8ed1b From 5c82a6ae0242416cfead597bb2b42aa3481a0ba7 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Fri, 2 Jun 2017 14:15:15 +0200 Subject: rtc: remove rtc_device.name rtc->name is only used in messages were it is superfluous. Remove it completely from the structure. Signed-off-by: Alexandre Belloni --- drivers/rtc/class.c | 7 +++---- include/linux/rtc.h | 1 - 2 files changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index 5fb439897fe1..543c64cd3df0 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -224,7 +224,6 @@ struct rtc_device *rtc_device_register(const char *name, struct device *dev, rtc->pie_timer.function = rtc_pie_update_irq; rtc->pie_enabled = 0; - strlcpy(rtc->name, name, RTC_DEVICE_NAME_SIZE); dev_set_name(&rtc->dev, "rtc%d", id); /* Check to see if there is an ALARM already set in hw */ @@ -238,20 +237,20 @@ struct rtc_device *rtc_device_register(const char *name, struct device *dev, err = cdev_device_add(&rtc->char_dev, &rtc->dev); if (err) { dev_warn(&rtc->dev, "%s: failed to add char device %d:%d\n", - rtc->name, MAJOR(rtc->dev.devt), rtc->id); + name, MAJOR(rtc->dev.devt), rtc->id); /* This will free both memory and the ID */ put_device(&rtc->dev); goto exit; } else { - dev_dbg(&rtc->dev, "%s: dev (%d:%d)\n", rtc->name, + dev_dbg(&rtc->dev, "%s: dev (%d:%d)\n", name, MAJOR(rtc->dev.devt), rtc->id); } rtc_proc_add_device(rtc); dev_info(dev, "rtc core: registered %s as %s\n", - rtc->name, dev_name(&rtc->dev)); + name, dev_name(&rtc->dev)); return rtc; diff --git a/include/linux/rtc.h b/include/linux/rtc.h index b693adac853b..d354f56e0cf5 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -116,7 +116,6 @@ struct rtc_device { struct module *owner; int id; - char name[RTC_DEVICE_NAME_SIZE]; const struct rtc_class_ops *ops; struct mutex ops_lock; -- cgit v1.2.3-59-g8ed1b From 2f071ff175ea221710d583222b55f915d90901f0 Mon Sep 17 00:00:00 2001 From: Chris Packham Date: Fri, 2 Jun 2017 15:21:18 +1200 Subject: mtd: mchp23k256: add partitioning support Setting the of_node for the mtd device allows the generic mtd code to setup the partitions. [Editorial note (Brian): patch still pending on fixing up the "aligned to eraseblock" partition sanity check, given that this SRAM has no eraseblocks.] Signed-off-by: Chris Packham Reviewed-by: Andrew Lunn Tested-by: Andrew Lunn Signed-off-by: Brian Norris --- drivers/mtd/devices/mchp23k256.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/mtd/devices/mchp23k256.c b/drivers/mtd/devices/mchp23k256.c index 2542f5b8b63f..3e5feb454644 100644 --- a/drivers/mtd/devices/mchp23k256.c +++ b/drivers/mtd/devices/mchp23k256.c @@ -143,6 +143,7 @@ static int mchp23k256_probe(struct spi_device *spi) data = dev_get_platdata(&spi->dev); + mtd_set_of_node(&flash->mtd, spi->dev.of_node); flash->mtd.dev.parent = &spi->dev; flash->mtd.type = MTD_RAM; flash->mtd.flags = MTD_CAP_RAM; -- cgit v1.2.3-59-g8ed1b From 4379075a870b8de43a9ecd5b46884953234fc669 Mon Sep 17 00:00:00 2001 From: Chris Packham Date: Fri, 2 Jun 2017 15:21:19 +1200 Subject: mtd: mchp23k256: Add support for mchp23lcv1024 The mchp23lcv1024 is similar to the mchp23k256, the differences (from a software point of view) are the capacity of the chip and the size of the addresses used. There is no way to detect the specific chip so we must be told via a Device Tree or default to mchp23k256 when device tree is not used. Signed-off-by: Chris Packham Reviewed-by: Andrew Lunn Acked-by: Rob Herring Signed-off-by: Brian Norris --- .../bindings/mtd/microchip,mchp23k256.txt | 2 +- drivers/mtd/devices/mchp23k256.c | 66 ++++++++++++++++++---- 2 files changed, 57 insertions(+), 11 deletions(-) diff --git a/Documentation/devicetree/bindings/mtd/microchip,mchp23k256.txt b/Documentation/devicetree/bindings/mtd/microchip,mchp23k256.txt index 25e5ad38b0f0..7328eb92a03c 100644 --- a/Documentation/devicetree/bindings/mtd/microchip,mchp23k256.txt +++ b/Documentation/devicetree/bindings/mtd/microchip,mchp23k256.txt @@ -3,7 +3,7 @@ Required properties: - #address-cells, #size-cells : Must be present if the device has sub-nodes representing partitions. -- compatible : Must be "microchip,mchp23k256" +- compatible : Must be one of "microchip,mchp23k256" or "microchip,mchp23lcv1024" - reg : Chip-Select number - spi-max-frequency : Maximum frequency of the SPI bus the chip can operate at diff --git a/drivers/mtd/devices/mchp23k256.c b/drivers/mtd/devices/mchp23k256.c index 3e5feb454644..8956b7dcc984 100644 --- a/drivers/mtd/devices/mchp23k256.c +++ b/drivers/mtd/devices/mchp23k256.c @@ -21,10 +21,18 @@ #include #include +#define MAX_CMD_SIZE 4 + +struct mchp23_caps { + u8 addr_width; + unsigned int size; +}; + struct mchp23k256_flash { struct spi_device *spi; struct mutex lock; struct mtd_info mtd; + const struct mchp23_caps *caps; }; #define MCHP23K256_CMD_WRITE_STATUS 0x01 @@ -34,22 +42,40 @@ struct mchp23k256_flash { #define to_mchp23k256_flash(x) container_of(x, struct mchp23k256_flash, mtd) +static void mchp23k256_addr2cmd(struct mchp23k256_flash *flash, + unsigned int addr, u8 *cmd) +{ + int i; + + /* + * Address is sent in big endian (MSB first) and we skip + * the first entry of the cmd array which contains the cmd + * opcode. + */ + for (i = flash->caps->addr_width; i > 0; i--, addr >>= 8) + cmd[i] = addr; +} + +static int mchp23k256_cmdsz(struct mchp23k256_flash *flash) +{ + return 1 + flash->caps->addr_width; +} + static int mchp23k256_write(struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen, const unsigned char *buf) { struct mchp23k256_flash *flash = to_mchp23k256_flash(mtd); struct spi_transfer transfer[2] = {}; struct spi_message message; - unsigned char command[3]; + unsigned char command[MAX_CMD_SIZE]; spi_message_init(&message); command[0] = MCHP23K256_CMD_WRITE; - command[1] = to >> 8; - command[2] = to; + mchp23k256_addr2cmd(flash, to, command); transfer[0].tx_buf = command; - transfer[0].len = sizeof(command); + transfer[0].len = mchp23k256_cmdsz(flash); spi_message_add_tail(&transfer[0], &message); transfer[1].tx_buf = buf; @@ -73,17 +99,16 @@ static int mchp23k256_read(struct mtd_info *mtd, loff_t from, size_t len, struct mchp23k256_flash *flash = to_mchp23k256_flash(mtd); struct spi_transfer transfer[2] = {}; struct spi_message message; - unsigned char command[3]; + unsigned char command[MAX_CMD_SIZE]; spi_message_init(&message); memset(&transfer, 0, sizeof(transfer)); command[0] = MCHP23K256_CMD_READ; - command[1] = from >> 8; - command[2] = from; + mchp23k256_addr2cmd(flash, from, command); transfer[0].tx_buf = command; - transfer[0].len = sizeof(command); + transfer[0].len = mchp23k256_cmdsz(flash); spi_message_add_tail(&transfer[0], &message); transfer[1].rx_buf = buf; @@ -123,6 +148,16 @@ static int mchp23k256_set_mode(struct spi_device *spi) return spi_sync(spi, &message); } +static const struct mchp23_caps mchp23k256_caps = { + .size = SZ_32K, + .addr_width = 2, +}; + +static const struct mchp23_caps mchp23lcv1024_caps = { + .size = SZ_128K, + .addr_width = 3, +}; + static int mchp23k256_probe(struct spi_device *spi) { struct mchp23k256_flash *flash; @@ -143,12 +178,16 @@ static int mchp23k256_probe(struct spi_device *spi) data = dev_get_platdata(&spi->dev); + flash->caps = of_device_get_match_data(&spi->dev); + if (!flash->caps) + flash->caps = &mchp23k256_caps; + mtd_set_of_node(&flash->mtd, spi->dev.of_node); flash->mtd.dev.parent = &spi->dev; flash->mtd.type = MTD_RAM; flash->mtd.flags = MTD_CAP_RAM; flash->mtd.writesize = 1; - flash->mtd.size = SZ_32K; + flash->mtd.size = flash->caps->size; flash->mtd._read = mchp23k256_read; flash->mtd._write = mchp23k256_write; @@ -168,7 +207,14 @@ static int mchp23k256_remove(struct spi_device *spi) } static const struct of_device_id mchp23k256_of_table[] = { - { .compatible = "microchip,mchp23k256" }, + { + .compatible = "microchip,mchp23k256", + .data = &mchp23k256_caps, + }, + { + .compatible = "microchip,mchp23lcv1024", + .data = &mchp23lcv1024_caps, + }, {} }; MODULE_DEVICE_TABLE(of, mchp23k256_of_table); -- cgit v1.2.3-59-g8ed1b From c46adf0976eacadd60920da5b8bf8e27299183bd Mon Sep 17 00:00:00 2001 From: Xiaolei Li Date: Thu, 1 Jun 2017 17:01:19 +0800 Subject: mtd: subpagetest: fix wrong written check in function write_eraseblock2 Write size in function write_eraseblock2 is subpgsize * k. It is wrong to check whether written is equal to subpgsize after each mtd_write. Signed-off-by: Xiaolei Li Reviewed-by: Richard Weinberger Acked-by: Boris Brezillon Signed-off-by: Brian Norris --- drivers/mtd/tests/subpagetest.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/tests/subpagetest.c b/drivers/mtd/tests/subpagetest.c index aecc6ce5a9e1..fa2519ad2435 100644 --- a/drivers/mtd/tests/subpagetest.c +++ b/drivers/mtd/tests/subpagetest.c @@ -102,7 +102,7 @@ static int write_eraseblock2(int ebnum) if (unlikely(err || written != subpgsize * k)) { pr_err("error: write failed at %#llx\n", (long long)addr); - if (written != subpgsize) { + if (written != subpgsize * k) { pr_err(" write size: %#x\n", subpgsize * k); pr_err(" written: %#08zx\n", -- cgit v1.2.3-59-g8ed1b From fb418240ecbd721a1237da592c075993c1709955 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 9 May 2017 16:46:04 -0500 Subject: target: remove dead code Local variable _ret_ is assigned to a constant value and it is never updated again. Remove this variable and the dead code it guards. Addresses-Coverity-ID: 140761 Signed-off-by: Gustavo A. R. Silva Reviewed-by: Tyrel Datwyler Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_rd.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c index 20253d04103f..d12967690054 100644 --- a/drivers/target/target_core_rd.c +++ b/drivers/target/target_core_rd.c @@ -554,7 +554,7 @@ static ssize_t rd_set_configfs_dev_params(struct se_device *dev, struct rd_dev *rd_dev = RD_DEV(dev); char *orig, *ptr, *opts; substring_t args[MAX_OPT_ARGS]; - int ret = 0, arg, token; + int arg, token; opts = kstrdup(page, GFP_KERNEL); if (!opts) @@ -589,7 +589,7 @@ static ssize_t rd_set_configfs_dev_params(struct se_device *dev, } kfree(orig); - return (!ret) ? count : ret; + return count; } static ssize_t rd_show_configfs_dev_params(struct se_device *dev, char *b) -- cgit v1.2.3-59-g8ed1b From 12bdcbd539c6327c09da0503c674733cb2d82cb5 Mon Sep 17 00:00:00 2001 From: Byungchul Park Date: Fri, 12 May 2017 09:42:56 +0900 Subject: vhost/scsi: Don't reinvent the wheel but use existing llist API Although llist provides proper APIs, they are not used. Make them used. Signed-off-by: Byungchul Park Acked-by: Nicholas Bellinger Signed-off-by: Nicholas Bellinger --- drivers/vhost/scsi.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index fd6c8b66f06f..679f8960db4b 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -496,14 +496,12 @@ static void vhost_scsi_evt_work(struct vhost_work *work) struct vhost_scsi *vs = container_of(work, struct vhost_scsi, vs_event_work); struct vhost_virtqueue *vq = &vs->vqs[VHOST_SCSI_VQ_EVT].vq; - struct vhost_scsi_evt *evt; + struct vhost_scsi_evt *evt, *t; struct llist_node *llnode; mutex_lock(&vq->mutex); llnode = llist_del_all(&vs->vs_event_list); - while (llnode) { - evt = llist_entry(llnode, struct vhost_scsi_evt, list); - llnode = llist_next(llnode); + llist_for_each_entry_safe(evt, t, llnode, list) { vhost_scsi_do_evt_work(vs, evt); vhost_scsi_free_evt(vs, evt); } @@ -529,10 +527,7 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work) bitmap_zero(signal, VHOST_SCSI_MAX_VQ); llnode = llist_del_all(&vs->vs_completion_list); - while (llnode) { - cmd = llist_entry(llnode, struct vhost_scsi_cmd, - tvc_completion_list); - llnode = llist_next(llnode); + llist_for_each_entry(cmd, llnode, tvc_completion_list) { se_cmd = &cmd->tvc_se_cmd; pr_debug("%s tv_cmd %p resid %u status %#02x\n", __func__, -- cgit v1.2.3-59-g8ed1b From 464fd6419c68bc6b1697e02f46b6d3dd57dfed28 Mon Sep 17 00:00:00 2001 From: Michael Cyr Date: Tue, 16 May 2017 17:49:21 -0500 Subject: ibmvscsis: Enable Logical Partition Migration Support Changes to support a new mechanism from phyp to better synchronize the logical partition migration (LPM) of the client partition. This includes a new VIOCTL to register that we support this new functionality, and 2 new Transport Event types, and finally another new VIOCTL to let phyp know once we're ready for the Suspend. Signed-off-by: Michael Cyr Signed-off-by: Bryant G. Ly Signed-off-by: Nicholas Bellinger --- drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c | 148 ++++++++++++++++++++++++++++--- drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h | 25 +++++- drivers/scsi/ibmvscsi_tgt/libsrp.h | 5 +- 3 files changed, 162 insertions(+), 16 deletions(-) diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c index abf6026645dd..35710524d059 100644 --- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c +++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c @@ -155,6 +155,9 @@ static long ibmvscsis_unregister_command_q(struct scsi_info *vscsi) qrc = h_free_crq(vscsi->dds.unit_id); switch (qrc) { case H_SUCCESS: + spin_lock_bh(&vscsi->intr_lock); + vscsi->flags &= ~PREP_FOR_SUSPEND_FLAGS; + spin_unlock_bh(&vscsi->intr_lock); break; case H_HARDWARE: @@ -422,6 +425,9 @@ static void ibmvscsis_disconnect(struct work_struct *work) new_state = vscsi->new_state; vscsi->new_state = 0; + vscsi->flags |= DISCONNECT_SCHEDULED; + vscsi->flags &= ~SCHEDULE_DISCONNECT; + pr_debug("disconnect: flags 0x%x, state 0x%hx\n", vscsi->flags, vscsi->state); @@ -802,6 +808,13 @@ static long ibmvscsis_establish_new_q(struct scsi_info *vscsi) long rc = ADAPT_SUCCESS; uint format; + rc = h_vioctl(vscsi->dds.unit_id, H_ENABLE_PREPARE_FOR_SUSPEND, 30000, + 0, 0, 0, 0); + if (rc == H_SUCCESS) + vscsi->flags |= PREP_FOR_SUSPEND_ENABLED; + else if (rc != H_NOT_FOUND) + pr_err("Error from Enable Prepare for Suspend: %ld\n", rc); + vscsi->flags &= PRESERVE_FLAG_FIELDS; vscsi->rsp_q_timer.timer_pops = 0; vscsi->debit = 0; @@ -950,6 +963,63 @@ static void ibmvscsis_free_cmd_resources(struct scsi_info *vscsi, } } +/** + * ibmvscsis_ready_for_suspend() - Helper function to call VIOCTL + * @vscsi: Pointer to our adapter structure + * @idle: Indicates whether we were called from adapter_idle. This + * is important to know if we need to do a disconnect, since if + * we're called from adapter_idle, we're still processing the + * current disconnect, so we can't just call post_disconnect. + * + * This function is called when the adapter is idle when phyp has sent + * us a Prepare for Suspend Transport Event. + * + * EXECUTION ENVIRONMENT: + * Process or interrupt environment called with interrupt lock held + */ +static long ibmvscsis_ready_for_suspend(struct scsi_info *vscsi, bool idle) +{ + long rc = 0; + struct viosrp_crq *crq; + + /* See if there is a Resume event in the queue */ + crq = vscsi->cmd_q.base_addr + vscsi->cmd_q.index; + + pr_debug("ready_suspend: flags 0x%x, state 0x%hx crq_valid:%x\n", + vscsi->flags, vscsi->state, (int)crq->valid); + + if (!(vscsi->flags & PREP_FOR_SUSPEND_ABORTED) && !(crq->valid)) { + rc = h_vioctl(vscsi->dds.unit_id, H_READY_FOR_SUSPEND, 0, 0, 0, + 0, 0); + if (rc) { + pr_err("Ready for Suspend Vioctl failed: %ld\n", rc); + rc = 0; + } + } else if (((vscsi->flags & PREP_FOR_SUSPEND_OVERWRITE) && + (vscsi->flags & PREP_FOR_SUSPEND_ABORTED)) || + ((crq->valid) && ((crq->valid != VALID_TRANS_EVENT) || + (crq->format != RESUME_FROM_SUSP)))) { + if (idle) { + vscsi->state = ERR_DISCONNECT_RECONNECT; + ibmvscsis_reset_queue(vscsi); + rc = -1; + } else if (vscsi->state == CONNECTED) { + ibmvscsis_post_disconnect(vscsi, + ERR_DISCONNECT_RECONNECT, 0); + } + + vscsi->flags &= ~PREP_FOR_SUSPEND_OVERWRITE; + + if ((crq->valid) && ((crq->valid != VALID_TRANS_EVENT) || + (crq->format != RESUME_FROM_SUSP))) + pr_err("Invalid element in CRQ after Prepare for Suspend"); + } + + vscsi->flags &= ~(PREP_FOR_SUSPEND_PENDING | PREP_FOR_SUSPEND_ABORTED); + + return rc; +} + /** * ibmvscsis_trans_event() - Handle a Transport Event * @vscsi: Pointer to our adapter structure @@ -974,18 +1044,8 @@ static long ibmvscsis_trans_event(struct scsi_info *vscsi, case PARTNER_FAILED: case PARTNER_DEREGISTER: ibmvscsis_delete_client_info(vscsi, true); - break; - - default: - rc = ERROR; - dev_err(&vscsi->dev, "trans_event: invalid format %d\n", - (uint)crq->format); - ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT, - RESPONSE_Q_DOWN); - break; - } - - if (rc == ADAPT_SUCCESS) { + if (crq->format == MIGRATED) + vscsi->flags &= ~PREP_FOR_SUSPEND_OVERWRITE; switch (vscsi->state) { case NO_QUEUE: case ERR_DISCONNECTED: @@ -1034,6 +1094,60 @@ static long ibmvscsis_trans_event(struct scsi_info *vscsi, vscsi->flags |= (RESPONSE_Q_DOWN | TRANS_EVENT); break; } + break; + + case PREPARE_FOR_SUSPEND: + pr_debug("Prep for Suspend, crq status = 0x%x\n", + (int)crq->status); + switch (vscsi->state) { + case ERR_DISCONNECTED: + case WAIT_CONNECTION: + case CONNECTED: + ibmvscsis_ready_for_suspend(vscsi, false); + break; + case SRP_PROCESSING: + vscsi->resume_state = vscsi->state; + vscsi->flags |= PREP_FOR_SUSPEND_PENDING; + if (crq->status == CRQ_ENTRY_OVERWRITTEN) + vscsi->flags |= PREP_FOR_SUSPEND_OVERWRITE; + ibmvscsis_post_disconnect(vscsi, WAIT_IDLE, 0); + break; + case NO_QUEUE: + case UNDEFINED: + case UNCONFIGURING: + case WAIT_ENABLED: + case ERR_DISCONNECT: + case ERR_DISCONNECT_RECONNECT: + case WAIT_IDLE: + pr_err("Invalid state for Prepare for Suspend Trans Event: 0x%x\n", + vscsi->state); + break; + } + break; + + case RESUME_FROM_SUSP: + pr_debug("Resume from Suspend, crq status = 0x%x\n", + (int)crq->status); + if (vscsi->flags & PREP_FOR_SUSPEND_PENDING) { + vscsi->flags |= PREP_FOR_SUSPEND_ABORTED; + } else { + if ((crq->status == CRQ_ENTRY_OVERWRITTEN) || + (vscsi->flags & PREP_FOR_SUSPEND_OVERWRITE)) { + ibmvscsis_post_disconnect(vscsi, + ERR_DISCONNECT_RECONNECT, + 0); + vscsi->flags &= ~PREP_FOR_SUSPEND_OVERWRITE; + } + } + break; + + default: + rc = ERROR; + dev_err(&vscsi->dev, "trans_event: invalid format %d\n", + (uint)crq->format); + ibmvscsis_post_disconnect(vscsi, ERR_DISCONNECT, + RESPONSE_Q_DOWN); + break; } rc = vscsi->flags & SCHEDULE_DISCONNECT; @@ -1201,6 +1315,7 @@ static struct ibmvscsis_cmd *ibmvscsis_get_free_cmd(struct scsi_info *vscsi) static void ibmvscsis_adapter_idle(struct scsi_info *vscsi) { int free_qs = false; + long rc = 0; pr_debug("adapter_idle: flags 0x%x, state 0x%hx\n", vscsi->flags, vscsi->state); @@ -1240,7 +1355,14 @@ static void ibmvscsis_adapter_idle(struct scsi_info *vscsi) vscsi->rsp_q_timer.timer_pops = 0; vscsi->debit = 0; vscsi->credit = 0; - if (vscsi->flags & TRANS_EVENT) { + if (vscsi->flags & PREP_FOR_SUSPEND_PENDING) { + vscsi->state = vscsi->resume_state; + vscsi->resume_state = 0; + rc = ibmvscsis_ready_for_suspend(vscsi, true); + vscsi->flags &= ~DISCONNECT_SCHEDULED; + if (rc) + break; + } else if (vscsi->flags & TRANS_EVENT) { vscsi->state = WAIT_CONNECTION; vscsi->flags &= PRESERVE_FLAG_FIELDS; } else { diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h index b4391a8de456..cc96c2731134 100644 --- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h +++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.h @@ -262,6 +262,14 @@ struct scsi_info { #define DISCONNECT_SCHEDULED 0x00800 /* remove function is sleeping */ #define CFG_SLEEPING 0x01000 + /* Register for Prepare for Suspend Transport Events */ +#define PREP_FOR_SUSPEND_ENABLED 0x02000 + /* Prepare for Suspend event sent */ +#define PREP_FOR_SUSPEND_PENDING 0x04000 + /* Resume from Suspend event sent */ +#define PREP_FOR_SUSPEND_ABORTED 0x08000 + /* Prepare for Suspend event overwrote another CRQ entry */ +#define PREP_FOR_SUSPEND_OVERWRITE 0x10000 u32 flags; /* adapter lock */ spinlock_t intr_lock; @@ -272,6 +280,7 @@ struct scsi_info { /* used in crq, to tag what iu the response is for */ u64 empty_iu_tag; uint new_state; + uint resume_state; /* control block for the response queue timer */ struct timer_cb rsp_q_timer; /* keep last client to enable proper accounting */ @@ -324,8 +333,13 @@ struct scsi_info { #define TARGET_STOP(VSCSI) (long)(((VSCSI)->state & DONT_PROCESS_STATE) | \ ((VSCSI)->flags & BLOCK)) +#define PREP_FOR_SUSPEND_FLAGS (PREP_FOR_SUSPEND_ENABLED | \ + PREP_FOR_SUSPEND_PENDING | \ + PREP_FOR_SUSPEND_ABORTED | \ + PREP_FOR_SUSPEND_OVERWRITE) + /* flag bit that are not reset during disconnect */ -#define PRESERVE_FLAG_FIELDS 0 +#define PRESERVE_FLAG_FIELDS (PREP_FOR_SUSPEND_FLAGS) #define vio_iu(IUE) ((union viosrp_iu *)((IUE)->sbuf->buf)) @@ -333,8 +347,15 @@ struct scsi_info { #define WRITE_CMD(cdb) (((cdb)[0] & 0x1F) == 0xA) #ifndef H_GET_PARTNER_INFO -#define H_GET_PARTNER_INFO 0x0000000000000008LL +#define H_GET_PARTNER_INFO 0x0000000000000008LL +#endif +#ifndef H_ENABLE_PREPARE_FOR_SUSPEND +#define H_ENABLE_PREPARE_FOR_SUSPEND 0x000000000000001DLL #endif +#ifndef H_READY_FOR_SUSPEND +#define H_READY_FOR_SUSPEND 0x000000000000001ELL +#endif + #define h_copy_rdma(l, sa, sb, da, db) \ plpar_hcall_norets(H_COPY_RDMA, l, sa, sb, da, db) diff --git a/drivers/scsi/ibmvscsi_tgt/libsrp.h b/drivers/scsi/ibmvscsi_tgt/libsrp.h index 4696f331453e..9fec55b36322 100644 --- a/drivers/scsi/ibmvscsi_tgt/libsrp.h +++ b/drivers/scsi/ibmvscsi_tgt/libsrp.h @@ -30,10 +30,13 @@ enum srp_trans_event { UNUSED_FORMAT = 0, PARTNER_FAILED = 1, PARTNER_DEREGISTER = 2, - MIGRATED = 6 + MIGRATED = 6, + PREPARE_FOR_SUSPEND = 9, + RESUME_FROM_SUSP = 0xA }; enum srp_status { + CRQ_ENTRY_OVERWRITTEN = 0x20, HEADER_DESCRIPTOR = 0xF1, PING = 0xF5, PING_RESPONSE = 0xF6 -- cgit v1.2.3-59-g8ed1b From 2237498f0b5c74768f688ebaf16eab2c708d5fdb Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Tue, 11 Apr 2017 22:21:47 -0700 Subject: target/iblock: Convert WRITE_SAME to blkdev_issue_zeroout The people who are actively using iblock_execute_write_same_direct() are doing so in the context of ESX VAAI BlockZero, together with EXTENDED_COPY and COMPARE_AND_WRITE primitives. In practice though I've not seen any users of IBLOCK WRITE_SAME for anything other than VAAI BlockZero, so just using blkdev_issue_zeroout() when available, and falling back to iblock_execute_write_same() if the WRITE_SAME buffer contains anything other than zeros should be OK. (Hook up max_write_zeroes_sectors to signal LBPRZ feature bit in target_configure_unmap_from_queue - nab) Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Cc: Christoph Hellwig Cc: Mike Christie Cc: Hannes Reinecke Cc: Jens Axboe Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_device.c | 2 +- drivers/target/target_core_iblock.c | 44 +++++++++++++++++++++++-------------- 2 files changed, 28 insertions(+), 18 deletions(-) diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 8add07f387f9..a5762e601fa1 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -851,7 +851,7 @@ bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib, attrib->unmap_granularity = q->limits.discard_granularity / block_size; attrib->unmap_granularity_alignment = q->limits.discard_alignment / block_size; - attrib->unmap_zeroes_data = 0; + attrib->unmap_zeroes_data = (q->limits.max_write_zeroes_sectors); return true; } EXPORT_SYMBOL(target_configure_unmap_from_queue); diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index bb069ebe4aa6..b2044133d747 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -86,6 +86,7 @@ static int iblock_configure_device(struct se_device *dev) struct block_device *bd = NULL; struct blk_integrity *bi; fmode_t mode; + unsigned int max_write_zeroes_sectors; int ret = -ENOMEM; if (!(ib_dev->ibd_flags & IBDF_HAS_UDEV_PATH)) { @@ -129,7 +130,11 @@ static int iblock_configure_device(struct se_device *dev) * Enable write same emulation for IBLOCK and use 0xFFFF as * the smaller WRITE_SAME(10) only has a two-byte block count. */ - dev->dev_attrib.max_write_same_len = 0xFFFF; + max_write_zeroes_sectors = bdev_write_zeroes_sectors(bd); + if (max_write_zeroes_sectors) + dev->dev_attrib.max_write_same_len = max_write_zeroes_sectors; + else + dev->dev_attrib.max_write_same_len = 0xFFFF; if (blk_queue_nonrot(q)) dev->dev_attrib.is_nonrot = 1; @@ -415,28 +420,31 @@ iblock_execute_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb) } static sense_reason_t -iblock_execute_write_same_direct(struct block_device *bdev, struct se_cmd *cmd) +iblock_execute_zero_out(struct block_device *bdev, struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; struct scatterlist *sg = &cmd->t_data_sg[0]; - struct page *page = NULL; - int ret; + unsigned char *buf, zero = 0x00, *p = &zero; + int rc, ret; - if (sg->offset) { - page = alloc_page(GFP_KERNEL); - if (!page) - return TCM_OUT_OF_RESOURCES; - sg_copy_to_buffer(sg, cmd->t_data_nents, page_address(page), - dev->dev_attrib.block_size); - } + buf = kmap(sg_page(sg)) + sg->offset; + if (!buf) + return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; + /* + * Fall back to block_execute_write_same() slow-path if + * incoming WRITE_SAME payload does not contain zeros. + */ + rc = memcmp(buf, p, cmd->data_length); + kunmap(sg_page(sg)); + + if (rc) + return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - ret = blkdev_issue_write_same(bdev, + ret = blkdev_issue_zeroout(bdev, target_to_linux_sector(dev, cmd->t_task_lba), target_to_linux_sector(dev, sbc_get_write_same_sectors(cmd)), - GFP_KERNEL, page ? page : sg_page(sg)); - if (page) - __free_page(page); + GFP_KERNEL, false); if (ret) return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; @@ -472,8 +480,10 @@ iblock_execute_write_same(struct se_cmd *cmd) return TCM_INVALID_CDB_FIELD; } - if (bdev_write_same(bdev)) - return iblock_execute_write_same_direct(bdev, cmd); + if (bdev_write_zeroes_sectors(bdev)) { + if (!iblock_execute_zero_out(bdev, cmd)) + return 0; + } ibr = kzalloc(sizeof(struct iblock_req), GFP_KERNEL); if (!ibr) -- cgit v1.2.3-59-g8ed1b From c17cd24959cdb12c855dc61e20c36fa25f21f3d3 Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Thu, 1 Jun 2017 03:10:53 -0700 Subject: target/configfs: Kill se_device->dev_link_magic Instead of using a hardcoded magic value in se_device when verifying a target config_item symlink source during target_fabric_port_link(), go ahead and use target_core_dev_item_ops directly instead. Reviewed-by: Christoph Hellwig Cc: Mike Christie Cc: Hannes Reinecke Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_configfs.c | 6 +++++- drivers/target/target_core_device.c | 1 - drivers/target/target_core_fabric_configfs.c | 12 +++++++----- include/target/target_core_base.h | 2 -- 4 files changed, 12 insertions(+), 9 deletions(-) diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index 0326607e5ab8..9b8abd55c21c 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -2236,7 +2236,11 @@ static void target_core_dev_release(struct config_item *item) target_free_device(dev); } -static struct configfs_item_operations target_core_dev_item_ops = { +/* + * Used in target_core_fabric_configfs.c to verify valid se_device symlink + * within target_fabric_port_link() + */ +struct configfs_item_operations target_core_dev_item_ops = { .release = target_core_dev_release, }; diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index a5762e601fa1..e4771cec108c 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -756,7 +756,6 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name) if (!dev) return NULL; - dev->dev_link_magic = SE_DEV_LINK_MAGIC; dev->se_hba = hba; dev->transport = hba->backend->ops; dev->prot_length = sizeof(struct t10_pi_tuple); diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c index d1e6cab8e3d3..2cbaecd1669d 100644 --- a/drivers/target/target_core_fabric_configfs.c +++ b/drivers/target/target_core_fabric_configfs.c @@ -620,6 +620,8 @@ static struct configfs_attribute *target_fabric_port_attrs[] = { NULL, }; +extern struct configfs_item_operations target_core_dev_item_ops; + static int target_fabric_port_link( struct config_item *lun_ci, struct config_item *se_dev_ci) @@ -628,16 +630,16 @@ static int target_fabric_port_link( struct se_lun *lun = container_of(to_config_group(lun_ci), struct se_lun, lun_group); struct se_portal_group *se_tpg; - struct se_device *dev = - container_of(to_config_group(se_dev_ci), struct se_device, dev_group); + struct se_device *dev; struct target_fabric_configfs *tf; int ret; - if (dev->dev_link_magic != SE_DEV_LINK_MAGIC) { - pr_err("Bad dev->dev_link_magic, not a valid se_dev_ci pointer:" - " %p to struct se_device: %p\n", se_dev_ci, dev); + if (!se_dev_ci->ci_type || + se_dev_ci->ci_type->ct_item_ops != &target_core_dev_item_ops) { + pr_err("Bad se_dev_ci, not a valid se_dev_ci pointer: %p\n", se_dev_ci); return -EFAULT; } + dev = container_of(to_config_group(se_dev_ci), struct se_device, dev_group); if (!(dev->dev_flags & DF_CONFIGURED)) { pr_err("se_device not configured yet, cannot port link\n"); diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 0c1dce2ac6f0..c3c14d053122 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -746,8 +746,6 @@ struct se_dev_stat_grps { }; struct se_device { -#define SE_DEV_LINK_MAGIC 0xfeeddeef - u32 dev_link_magic; /* RELATIVE TARGET PORT IDENTIFER Counter */ u16 dev_rpti_counter; /* Used for SAM Task Attribute ordering */ -- cgit v1.2.3-59-g8ed1b From 9ae0e9ade56f23765366d2cfad24e65f28df977d Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Thu, 1 Jun 2017 03:11:18 -0700 Subject: target/configfs: Kill se_lun->lun_link_magic Instead of using a hardcoded magic value in se_lun when verifying a target config_item symlink source during target_fabric_mappedlun_link(), go ahead and use target_fabric_port_item_ops directly instead. Reviewed-by: Christoph Hellwig Cc: Mike Christie Cc: Hannes Reinecke Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_fabric_configfs.c | 13 ++++++++----- drivers/target/target_core_tpg.c | 1 - include/target/target_core_base.h | 2 -- 3 files changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c index 2cbaecd1669d..e9e917cc6441 100644 --- a/drivers/target/target_core_fabric_configfs.c +++ b/drivers/target/target_core_fabric_configfs.c @@ -65,6 +65,8 @@ static void target_fabric_setup_##_name##_cit(struct target_fabric_configfs *tf) pr_debug("Setup generic %s\n", __stringify(_name)); \ } +static struct configfs_item_operations target_fabric_port_item_ops; + /* Start of tfc_tpg_mappedlun_cit */ static int target_fabric_mappedlun_link( @@ -72,19 +74,20 @@ static int target_fabric_mappedlun_link( struct config_item *lun_ci) { struct se_dev_entry *deve; - struct se_lun *lun = container_of(to_config_group(lun_ci), - struct se_lun, lun_group); + struct se_lun *lun; struct se_lun_acl *lacl = container_of(to_config_group(lun_acl_ci), struct se_lun_acl, se_lun_group); struct se_portal_group *se_tpg; struct config_item *nacl_ci, *tpg_ci, *tpg_ci_s, *wwn_ci, *wwn_ci_s; bool lun_access_ro; - if (lun->lun_link_magic != SE_LUN_LINK_MAGIC) { - pr_err("Bad lun->lun_link_magic, not a valid lun_ci pointer:" - " %p to struct lun: %p\n", lun_ci, lun); + if (!lun_ci->ci_type || + lun_ci->ci_type->ct_item_ops != &target_fabric_port_item_ops) { + pr_err("Bad lun_ci, not a valid lun_ci pointer: %p\n", lun_ci); return -EFAULT; } + lun = container_of(to_config_group(lun_ci), struct se_lun, lun_group); + /* * Ensure that the source port exists */ diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c index 310d9e55c6eb..36913734c6bc 100644 --- a/drivers/target/target_core_tpg.c +++ b/drivers/target/target_core_tpg.c @@ -576,7 +576,6 @@ struct se_lun *core_tpg_alloc_lun( return ERR_PTR(-ENOMEM); } lun->unpacked_lun = unpacked_lun; - lun->lun_link_magic = SE_LUN_LINK_MAGIC; atomic_set(&lun->lun_acl_count, 0); init_completion(&lun->lun_ref_comp); init_completion(&lun->lun_shutdown_comp); diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index c3c14d053122..47d9f381209f 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -701,8 +701,6 @@ struct scsi_port_stats { struct se_lun { u64 unpacked_lun; -#define SE_LUN_LINK_MAGIC 0xffff7771 - u32 lun_link_magic; bool lun_shutdown; bool lun_access_ro; u32 lun_index; -- cgit v1.2.3-59-g8ed1b From eceb4459df4a5b6127ae479280168847b9780b25 Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Thu, 1 Jun 2017 20:21:33 -0700 Subject: iscsi-target: Avoid holding ->tpg_state_lock during param update As originally reported by Jia-Ju, iscsit_tpg_enable_portal_group() holds iscsi_portal_group->tpg_state_lock while updating AUTHMETHOD via iscsi_update_param_value(), which performs a GFP_KERNEL allocation. However, since iscsit_tpg_enable_portal_group() is already protected by iscsit_get_tpg() -> iscsi_portal_group->tpg_access_lock in it's parent caller, ->tpg_state_lock only needs to be held when setting TPG_STATE_ACTIVE. Reported-by: Jia-Ju Bai Reviewed-by: Jia-Ju Bai Signed-off-by: Nicholas Bellinger --- drivers/target/iscsi/iscsi_target_tpg.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c index 2e7e08dbda48..abaabbaebd88 100644 --- a/drivers/target/iscsi/iscsi_target_tpg.c +++ b/drivers/target/iscsi/iscsi_target_tpg.c @@ -311,11 +311,9 @@ int iscsit_tpg_enable_portal_group(struct iscsi_portal_group *tpg) struct iscsi_tiqn *tiqn = tpg->tpg_tiqn; int ret; - spin_lock(&tpg->tpg_state_lock); if (tpg->tpg_state == TPG_STATE_ACTIVE) { pr_err("iSCSI target portal group: %hu is already" " active, ignoring request.\n", tpg->tpgt); - spin_unlock(&tpg->tpg_state_lock); return -EINVAL; } /* @@ -324,10 +322,8 @@ int iscsit_tpg_enable_portal_group(struct iscsi_portal_group *tpg) * is enforced (as per default), and remove the NONE option. */ param = iscsi_find_param_from_key(AUTHMETHOD, tpg->param_list); - if (!param) { - spin_unlock(&tpg->tpg_state_lock); + if (!param) return -EINVAL; - } if (tpg->tpg_attrib.authentication) { if (!strcmp(param->value, NONE)) { @@ -341,6 +337,7 @@ int iscsit_tpg_enable_portal_group(struct iscsi_portal_group *tpg) goto err; } + spin_lock(&tpg->tpg_state_lock); tpg->tpg_state = TPG_STATE_ACTIVE; spin_unlock(&tpg->tpg_state_lock); @@ -353,7 +350,6 @@ int iscsit_tpg_enable_portal_group(struct iscsi_portal_group *tpg) return 0; err: - spin_unlock(&tpg->tpg_state_lock); return ret; } -- cgit v1.2.3-59-g8ed1b From d45e5316e6a5071dbfe44bae04a89a3ba75e1ea9 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sat, 10 Jun 2017 12:09:05 +0200 Subject: mtd: nand: fsl_ifc: fix handing of bit flips in erased pages If we see unrecoverable ECC error, we need to count number of bitflips from all-ones and report correctable/uncorrectable according to that. Otherwise we report ECC failed on erased flash with single bit error. Signed-off-by: Pavel Machek Reported-by: Darwin Dingel Acked-by: Darwin Dingel Signed-off-by: Boris Brezillon --- drivers/mtd/nand/fsl_ifc_nand.c | 77 ++++++++++++++++++++++------------------- 1 file changed, 42 insertions(+), 35 deletions(-) diff --git a/drivers/mtd/nand/fsl_ifc_nand.c b/drivers/mtd/nand/fsl_ifc_nand.c index 89e14daeaba6..d1c4538f870f 100644 --- a/drivers/mtd/nand/fsl_ifc_nand.c +++ b/drivers/mtd/nand/fsl_ifc_nand.c @@ -171,34 +171,6 @@ static void set_addr(struct mtd_info *mtd, int column, int page_addr, int oob) ifc_nand_ctrl->index += mtd->writesize; } -static int is_blank(struct mtd_info *mtd, unsigned int bufnum) -{ - struct nand_chip *chip = mtd_to_nand(mtd); - struct fsl_ifc_mtd *priv = nand_get_controller_data(chip); - u8 __iomem *addr = priv->vbase + bufnum * (mtd->writesize * 2); - u32 __iomem *mainarea = (u32 __iomem *)addr; - u8 __iomem *oob = addr + mtd->writesize; - struct mtd_oob_region oobregion = { }; - int i, section = 0; - - for (i = 0; i < mtd->writesize / 4; i++) { - if (__raw_readl(&mainarea[i]) != 0xffffffff) - return 0; - } - - mtd_ooblayout_ecc(mtd, section++, &oobregion); - while (oobregion.length) { - for (i = 0; i < oobregion.length; i++) { - if (__raw_readb(&oob[oobregion.offset + i]) != 0xff) - return 0; - } - - mtd_ooblayout_ecc(mtd, section++, &oobregion); - } - - return 1; -} - /* returns nonzero if entire page is blank */ static int check_read_ecc(struct mtd_info *mtd, struct fsl_ifc_ctrl *ctrl, u32 *eccstat, unsigned int bufnum) @@ -274,16 +246,14 @@ static void fsl_ifc_run_command(struct mtd_info *mtd) if (errors == 15) { /* * Uncorrectable error. - * OK only if the whole page is blank. + * We'll check for blank pages later. * * We disable ECCER reporting due to... * erratum IFC-A002770 -- so report it now if we * see an uncorrectable error in ECCSTAT. */ - if (!is_blank(mtd, bufnum)) - ctrl->nand_stat |= - IFC_NAND_EVTER_STAT_ECCER; - break; + ctrl->nand_stat |= IFC_NAND_EVTER_STAT_ECCER; + continue; } mtd->ecc_stats.corrected += errors; @@ -678,6 +648,39 @@ static int fsl_ifc_wait(struct mtd_info *mtd, struct nand_chip *chip) return nand_fsr | NAND_STATUS_WP; } +/* + * The controller does not check for bitflips in erased pages, + * therefore software must check instead. + */ +static int check_erased_page(struct nand_chip *chip, u8 *buf) +{ + struct mtd_info *mtd = nand_to_mtd(chip); + u8 *ecc = chip->oob_poi; + const int ecc_size = chip->ecc.bytes; + const int pkt_size = chip->ecc.size; + int i, res, bitflips = 0; + struct mtd_oob_region oobregion = { }; + + mtd_ooblayout_ecc(mtd, 0, &oobregion); + ecc += oobregion.offset; + + for (i = 0; i < chip->ecc.steps; ++i) { + res = nand_check_erased_ecc_chunk(buf, pkt_size, ecc, ecc_size, + NULL, 0, + chip->ecc.strength); + if (res < 0) + mtd->ecc_stats.failed++; + else + mtd->ecc_stats.corrected += res; + + bitflips = max(res, bitflips); + buf += pkt_size; + ecc += ecc_size; + } + + return bitflips; +} + static int fsl_ifc_read_page(struct mtd_info *mtd, struct nand_chip *chip, uint8_t *buf, int oob_required, int page) { @@ -689,8 +692,12 @@ static int fsl_ifc_read_page(struct mtd_info *mtd, struct nand_chip *chip, if (oob_required) fsl_ifc_read_buf(mtd, chip->oob_poi, mtd->oobsize); - if (ctrl->nand_stat & IFC_NAND_EVTER_STAT_ECCER) - dev_err(priv->dev, "NAND Flash ECC Uncorrectable Error\n"); + if (ctrl->nand_stat & IFC_NAND_EVTER_STAT_ECCER) { + if (!oob_required) + fsl_ifc_read_buf(mtd, chip->oob_poi, mtd->oobsize); + + return check_erased_page(chip, buf); + } if (ctrl->nand_stat != IFC_NAND_EVTER_STAT_OPC) mtd->ecc_stats.failed++; -- cgit v1.2.3-59-g8ed1b From 3762a33b007b63e058eb600eccf0bcd097d386f5 Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Thu, 1 Jun 2017 16:28:15 +0530 Subject: mtd: nand: orion: Handle return value of clk_prepare_enable clk_prepare_enable() can fail here and we must check its return value. Signed-off-by: Arvind Yadav Signed-off-by: Boris Brezillon --- drivers/mtd/nand/orion_nand.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/nand/orion_nand.c b/drivers/mtd/nand/orion_nand.c index f8e463a97b9e..209170ed2b76 100644 --- a/drivers/mtd/nand/orion_nand.c +++ b/drivers/mtd/nand/orion_nand.c @@ -166,7 +166,11 @@ static int __init orion_nand_probe(struct platform_device *pdev) } } - clk_prepare_enable(info->clk); + ret = clk_prepare_enable(info->clk); + if (ret) { + dev_err(&pdev->dev, "failed to prepare clock!\n"); + return ret; + } ret = nand_scan(mtd, 1); if (ret) -- cgit v1.2.3-59-g8ed1b From d816f6b6375901a5090018961c5ab631784538ea Mon Sep 17 00:00:00 2001 From: Matthias Lange Date: Mon, 5 Jun 2017 11:33:51 +0200 Subject: mtd: nand: gpmi: Fix typo in data structure name This makes it easier to grep. Signed-off-by: Matthias Lange Signed-off-by: Boris Brezillon --- drivers/mtd/nand/gpmi-nand/gpmi-lib.c | 4 ++-- drivers/mtd/nand/gpmi-nand/gpmi-nand.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-lib.c b/drivers/mtd/nand/gpmi-nand/gpmi-lib.c index 141bd70a49c2..57ff0518bbda 100644 --- a/drivers/mtd/nand/gpmi-nand/gpmi-lib.c +++ b/drivers/mtd/nand/gpmi-nand/gpmi-lib.c @@ -26,7 +26,7 @@ #include "gpmi-regs.h" #include "bch-regs.h" -static struct timing_threshod timing_default_threshold = { +static struct timing_threshold timing_default_threshold = { .max_data_setup_cycles = (BM_GPMI_TIMING0_DATA_SETUP >> BP_GPMI_TIMING0_DATA_SETUP), .internal_data_setup_in_ns = 0, @@ -329,7 +329,7 @@ static unsigned int ns_to_cycles(unsigned int time, static int gpmi_nfc_compute_hardware_timing(struct gpmi_nand_data *this, struct gpmi_nfc_hardware_timing *hw) { - struct timing_threshod *nfc = &timing_default_threshold; + struct timing_threshold *nfc = &timing_default_threshold; struct resources *r = &this->resources; struct nand_chip *nand = &this->nand; struct nand_timing target = this->timing; diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.h b/drivers/mtd/nand/gpmi-nand/gpmi-nand.h index e88a45a62ab6..9df0ad64e7e0 100644 --- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.h +++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.h @@ -234,7 +234,7 @@ struct gpmi_nfc_hardware_timing { }; /** - * struct timing_threshod - Timing threshold + * struct timing_threshold - Timing threshold * @max_data_setup_cycles: The maximum number of data setup cycles that * can be expressed in the hardware. * @internal_data_setup_in_ns: The time, in ns, that the NFC hardware requires @@ -256,7 +256,7 @@ struct gpmi_nfc_hardware_timing { * progress, this is the clock frequency during * the most recent I/O transaction. */ -struct timing_threshod { +struct timing_threshold { const unsigned int max_chip_count; const unsigned int max_data_setup_cycles; const unsigned int internal_data_setup_in_ns; -- cgit v1.2.3-59-g8ed1b From f82c3232d1906bc8754e0b33ce39d09d08cb60c3 Mon Sep 17 00:00:00 2001 From: Matthias Lange Date: Mon, 5 Jun 2017 11:34:38 +0200 Subject: mtd: nand: gpmi: fix typo in comment Signed-off-by: Matthias Lange Signed-off-by: Boris Brezillon --- drivers/mtd/nand/gpmi-nand/gpmi-lib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-lib.c b/drivers/mtd/nand/gpmi-nand/gpmi-lib.c index 57ff0518bbda..97787246af41 100644 --- a/drivers/mtd/nand/gpmi-nand/gpmi-lib.c +++ b/drivers/mtd/nand/gpmi-nand/gpmi-lib.c @@ -932,7 +932,7 @@ static int enable_edo_mode(struct gpmi_nand_data *this, int mode) nand->select_chip(mtd, 0); - /* [1] send SET FEATURE commond to NAND */ + /* [1] send SET FEATURE command to NAND */ feature[0] = mode; ret = nand->onfi_set_features(mtd, nand, ONFI_FEATURE_ADDR_TIMING_MODE, feature); -- cgit v1.2.3-59-g8ed1b From 2b8c92b4e7265e271cd070a1a5dd1ab2766e516b Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 6 Jun 2017 08:21:40 +0900 Subject: mtd: nand: denali_dt: clean up resource ioremap No need to use two struct resource pointers. Just reuse one. Signed-off-by: Masahiro Yamada Signed-off-by: Boris Brezillon --- drivers/mtd/nand/denali_dt.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/mtd/nand/denali_dt.c b/drivers/mtd/nand/denali_dt.c index df9ef36cc2ce..b48430fe3cd4 100644 --- a/drivers/mtd/nand/denali_dt.c +++ b/drivers/mtd/nand/denali_dt.c @@ -49,7 +49,7 @@ MODULE_DEVICE_TABLE(of, denali_nand_dt_ids); static int denali_dt_probe(struct platform_device *pdev) { - struct resource *denali_reg, *nand_data; + struct resource *res; struct denali_dt *dt; const struct denali_dt_data *data; struct denali_nand_info *denali; @@ -74,15 +74,13 @@ static int denali_dt_probe(struct platform_device *pdev) return denali->irq; } - denali_reg = platform_get_resource_byname(pdev, IORESOURCE_MEM, - "denali_reg"); - denali->flash_reg = devm_ioremap_resource(&pdev->dev, denali_reg); + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "denali_reg"); + denali->flash_reg = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(denali->flash_reg)) return PTR_ERR(denali->flash_reg); - nand_data = platform_get_resource_byname(pdev, IORESOURCE_MEM, - "nand_data"); - denali->flash_mem = devm_ioremap_resource(&pdev->dev, nand_data); + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nand_data"); + denali->flash_mem = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(denali->flash_mem)) return PTR_ERR(denali->flash_mem); -- cgit v1.2.3-59-g8ed1b From df8b97024e6d28e98066696619e2084bbda4e40e Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 6 Jun 2017 08:21:41 +0900 Subject: mtd: nand: denali: use BIT() and GENMASK() for register macros Use BIT() and GENMASK() for register field macros. This will make it easier to compare the macros with the register description in the Denali User's Guide. Signed-off-by: Masahiro Yamada Signed-off-by: Boris Brezillon --- drivers/mtd/nand/denali.h | 244 ++++++++++++++++++++++------------------------ 1 file changed, 119 insertions(+), 125 deletions(-) diff --git a/drivers/mtd/nand/denali.h b/drivers/mtd/nand/denali.h index ec004850652a..37833535a7a3 100644 --- a/drivers/mtd/nand/denali.h +++ b/drivers/mtd/nand/denali.h @@ -24,273 +24,267 @@ #include #define DEVICE_RESET 0x0 -#define DEVICE_RESET__BANK0 0x0001 -#define DEVICE_RESET__BANK1 0x0002 -#define DEVICE_RESET__BANK2 0x0004 -#define DEVICE_RESET__BANK3 0x0008 +#define DEVICE_RESET__BANK(bank) BIT(bank) #define TRANSFER_SPARE_REG 0x10 -#define TRANSFER_SPARE_REG__FLAG 0x0001 +#define TRANSFER_SPARE_REG__FLAG BIT(0) #define LOAD_WAIT_CNT 0x20 -#define LOAD_WAIT_CNT__VALUE 0xffff +#define LOAD_WAIT_CNT__VALUE GENMASK(15, 0) #define PROGRAM_WAIT_CNT 0x30 -#define PROGRAM_WAIT_CNT__VALUE 0xffff +#define PROGRAM_WAIT_CNT__VALUE GENMASK(15, 0) #define ERASE_WAIT_CNT 0x40 -#define ERASE_WAIT_CNT__VALUE 0xffff +#define ERASE_WAIT_CNT__VALUE GENMASK(15, 0) #define INT_MON_CYCCNT 0x50 -#define INT_MON_CYCCNT__VALUE 0xffff +#define INT_MON_CYCCNT__VALUE GENMASK(15, 0) #define RB_PIN_ENABLED 0x60 -#define RB_PIN_ENABLED__BANK0 0x0001 -#define RB_PIN_ENABLED__BANK1 0x0002 -#define RB_PIN_ENABLED__BANK2 0x0004 -#define RB_PIN_ENABLED__BANK3 0x0008 +#define RB_PIN_ENABLED__BANK(bank) BIT(bank) #define MULTIPLANE_OPERATION 0x70 -#define MULTIPLANE_OPERATION__FLAG 0x0001 +#define MULTIPLANE_OPERATION__FLAG BIT(0) #define MULTIPLANE_READ_ENABLE 0x80 -#define MULTIPLANE_READ_ENABLE__FLAG 0x0001 +#define MULTIPLANE_READ_ENABLE__FLAG BIT(0) #define COPYBACK_DISABLE 0x90 -#define COPYBACK_DISABLE__FLAG 0x0001 +#define COPYBACK_DISABLE__FLAG BIT(0) #define CACHE_WRITE_ENABLE 0xa0 -#define CACHE_WRITE_ENABLE__FLAG 0x0001 +#define CACHE_WRITE_ENABLE__FLAG BIT(0) #define CACHE_READ_ENABLE 0xb0 -#define CACHE_READ_ENABLE__FLAG 0x0001 +#define CACHE_READ_ENABLE__FLAG BIT(0) #define PREFETCH_MODE 0xc0 -#define PREFETCH_MODE__PREFETCH_EN 0x0001 -#define PREFETCH_MODE__PREFETCH_BURST_LENGTH 0xfff0 +#define PREFETCH_MODE__PREFETCH_EN BIT(0) +#define PREFETCH_MODE__PREFETCH_BURST_LENGTH GENMASK(15, 4) #define CHIP_ENABLE_DONT_CARE 0xd0 -#define CHIP_EN_DONT_CARE__FLAG 0x01 +#define CHIP_EN_DONT_CARE__FLAG BIT(0) #define ECC_ENABLE 0xe0 -#define ECC_ENABLE__FLAG 0x0001 +#define ECC_ENABLE__FLAG BIT(0) #define GLOBAL_INT_ENABLE 0xf0 -#define GLOBAL_INT_EN_FLAG 0x01 +#define GLOBAL_INT_EN_FLAG BIT(0) #define WE_2_RE 0x100 -#define WE_2_RE__VALUE 0x003f +#define WE_2_RE__VALUE GENMASK(5, 0) #define ADDR_2_DATA 0x110 -#define ADDR_2_DATA__VALUE 0x003f +#define ADDR_2_DATA__VALUE GENMASK(5, 0) #define RE_2_WE 0x120 -#define RE_2_WE__VALUE 0x003f +#define RE_2_WE__VALUE GENMASK(5, 0) #define ACC_CLKS 0x130 -#define ACC_CLKS__VALUE 0x000f +#define ACC_CLKS__VALUE GENMASK(3, 0) #define NUMBER_OF_PLANES 0x140 -#define NUMBER_OF_PLANES__VALUE 0x0007 +#define NUMBER_OF_PLANES__VALUE GENMASK(2, 0) #define PAGES_PER_BLOCK 0x150 -#define PAGES_PER_BLOCK__VALUE 0xffff +#define PAGES_PER_BLOCK__VALUE GENMASK(15, 0) #define DEVICE_WIDTH 0x160 -#define DEVICE_WIDTH__VALUE 0x0003 +#define DEVICE_WIDTH__VALUE GENMASK(1, 0) #define DEVICE_MAIN_AREA_SIZE 0x170 -#define DEVICE_MAIN_AREA_SIZE__VALUE 0xffff +#define DEVICE_MAIN_AREA_SIZE__VALUE GENMASK(15, 0) #define DEVICE_SPARE_AREA_SIZE 0x180 -#define DEVICE_SPARE_AREA_SIZE__VALUE 0xffff +#define DEVICE_SPARE_AREA_SIZE__VALUE GENMASK(15, 0) #define TWO_ROW_ADDR_CYCLES 0x190 -#define TWO_ROW_ADDR_CYCLES__FLAG 0x0001 +#define TWO_ROW_ADDR_CYCLES__FLAG BIT(0) #define MULTIPLANE_ADDR_RESTRICT 0x1a0 -#define MULTIPLANE_ADDR_RESTRICT__FLAG 0x0001 +#define MULTIPLANE_ADDR_RESTRICT__FLAG BIT(0) #define ECC_CORRECTION 0x1b0 -#define ECC_CORRECTION__VALUE 0x001f +#define ECC_CORRECTION__VALUE GENMASK(4, 0) #define READ_MODE 0x1c0 -#define READ_MODE__VALUE 0x000f +#define READ_MODE__VALUE GENMASK(3, 0) #define WRITE_MODE 0x1d0 -#define WRITE_MODE__VALUE 0x000f +#define WRITE_MODE__VALUE GENMASK(3, 0) #define COPYBACK_MODE 0x1e0 -#define COPYBACK_MODE__VALUE 0x000f +#define COPYBACK_MODE__VALUE GENMASK(3, 0) #define RDWR_EN_LO_CNT 0x1f0 -#define RDWR_EN_LO_CNT__VALUE 0x001f +#define RDWR_EN_LO_CNT__VALUE GENMASK(4, 0) #define RDWR_EN_HI_CNT 0x200 -#define RDWR_EN_HI_CNT__VALUE 0x001f +#define RDWR_EN_HI_CNT__VALUE GENMASK(4, 0) #define MAX_RD_DELAY 0x210 -#define MAX_RD_DELAY__VALUE 0x000f +#define MAX_RD_DELAY__VALUE GENMASK(3, 0) #define CS_SETUP_CNT 0x220 -#define CS_SETUP_CNT__VALUE 0x001f +#define CS_SETUP_CNT__VALUE GENMASK(4, 0) #define SPARE_AREA_SKIP_BYTES 0x230 -#define SPARE_AREA_SKIP_BYTES__VALUE 0x003f +#define SPARE_AREA_SKIP_BYTES__VALUE GENMASK(5, 0) #define SPARE_AREA_MARKER 0x240 -#define SPARE_AREA_MARKER__VALUE 0xffff +#define SPARE_AREA_MARKER__VALUE GENMASK(15, 0) #define DEVICES_CONNECTED 0x250 -#define DEVICES_CONNECTED__VALUE 0x0007 +#define DEVICES_CONNECTED__VALUE GENMASK(2, 0) #define DIE_MASK 0x260 -#define DIE_MASK__VALUE 0x00ff +#define DIE_MASK__VALUE GENMASK(7, 0) #define FIRST_BLOCK_OF_NEXT_PLANE 0x270 -#define FIRST_BLOCK_OF_NEXT_PLANE__VALUE 0xffff +#define FIRST_BLOCK_OF_NEXT_PLANE__VALUE GENMASK(15, 0) #define WRITE_PROTECT 0x280 -#define WRITE_PROTECT__FLAG 0x0001 +#define WRITE_PROTECT__FLAG BIT(0) #define RE_2_RE 0x290 -#define RE_2_RE__VALUE 0x003f +#define RE_2_RE__VALUE GENMASK(5, 0) #define MANUFACTURER_ID 0x300 -#define MANUFACTURER_ID__VALUE 0x00ff +#define MANUFACTURER_ID__VALUE GENMASK(7, 0) #define DEVICE_ID 0x310 -#define DEVICE_ID__VALUE 0x00ff +#define DEVICE_ID__VALUE GENMASK(7, 0) #define DEVICE_PARAM_0 0x320 -#define DEVICE_PARAM_0__VALUE 0x00ff +#define DEVICE_PARAM_0__VALUE GENMASK(7, 0) #define DEVICE_PARAM_1 0x330 -#define DEVICE_PARAM_1__VALUE 0x00ff +#define DEVICE_PARAM_1__VALUE GENMASK(7, 0) #define DEVICE_PARAM_2 0x340 -#define DEVICE_PARAM_2__VALUE 0x00ff +#define DEVICE_PARAM_2__VALUE GENMASK(7, 0) #define LOGICAL_PAGE_DATA_SIZE 0x350 -#define LOGICAL_PAGE_DATA_SIZE__VALUE 0xffff +#define LOGICAL_PAGE_DATA_SIZE__VALUE GENMASK(15, 0) #define LOGICAL_PAGE_SPARE_SIZE 0x360 -#define LOGICAL_PAGE_SPARE_SIZE__VALUE 0xffff +#define LOGICAL_PAGE_SPARE_SIZE__VALUE GENMASK(15, 0) #define REVISION 0x370 -#define REVISION__VALUE 0xffff +#define REVISION__VALUE GENMASK(15, 0) #define ONFI_DEVICE_FEATURES 0x380 -#define ONFI_DEVICE_FEATURES__VALUE 0x003f +#define ONFI_DEVICE_FEATURES__VALUE GENMASK(5, 0) #define ONFI_OPTIONAL_COMMANDS 0x390 -#define ONFI_OPTIONAL_COMMANDS__VALUE 0x003f +#define ONFI_OPTIONAL_COMMANDS__VALUE GENMASK(5, 0) #define ONFI_TIMING_MODE 0x3a0 -#define ONFI_TIMING_MODE__VALUE 0x003f +#define ONFI_TIMING_MODE__VALUE GENMASK(5, 0) #define ONFI_PGM_CACHE_TIMING_MODE 0x3b0 -#define ONFI_PGM_CACHE_TIMING_MODE__VALUE 0x003f +#define ONFI_PGM_CACHE_TIMING_MODE__VALUE GENMASK(5, 0) #define ONFI_DEVICE_NO_OF_LUNS 0x3c0 -#define ONFI_DEVICE_NO_OF_LUNS__NO_OF_LUNS 0x00ff -#define ONFI_DEVICE_NO_OF_LUNS__ONFI_DEVICE 0x0100 +#define ONFI_DEVICE_NO_OF_LUNS__NO_OF_LUNS GENMASK(7, 0) +#define ONFI_DEVICE_NO_OF_LUNS__ONFI_DEVICE BIT(8) #define ONFI_DEVICE_NO_OF_BLOCKS_PER_LUN_L 0x3d0 -#define ONFI_DEVICE_NO_OF_BLOCKS_PER_LUN_L__VALUE 0xffff +#define ONFI_DEVICE_NO_OF_BLOCKS_PER_LUN_L__VALUE GENMASK(15, 0) #define ONFI_DEVICE_NO_OF_BLOCKS_PER_LUN_U 0x3e0 -#define ONFI_DEVICE_NO_OF_BLOCKS_PER_LUN_U__VALUE 0xffff - -#define FEATURES 0x3f0 -#define FEATURES__N_BANKS 0x0003 -#define FEATURES__ECC_MAX_ERR 0x003c -#define FEATURES__DMA 0x0040 -#define FEATURES__CMD_DMA 0x0080 -#define FEATURES__PARTITION 0x0100 -#define FEATURES__XDMA_SIDEBAND 0x0200 -#define FEATURES__GPREG 0x0400 -#define FEATURES__INDEX_ADDR 0x0800 +#define ONFI_DEVICE_NO_OF_BLOCKS_PER_LUN_U__VALUE GENMASK(15, 0) + +#define FEATURES 0x3f0 +#define FEATURES__N_BANKS GENMASK(1, 0) +#define FEATURES__ECC_MAX_ERR GENMASK(5, 2) +#define FEATURES__DMA BIT(6) +#define FEATURES__CMD_DMA BIT(7) +#define FEATURES__PARTITION BIT(8) +#define FEATURES__XDMA_SIDEBAND BIT(9) +#define FEATURES__GPREG BIT(10) +#define FEATURES__INDEX_ADDR BIT(11) #define TRANSFER_MODE 0x400 -#define TRANSFER_MODE__VALUE 0x0003 +#define TRANSFER_MODE__VALUE GENMASK(1, 0) -#define INTR_STATUS(__bank) (0x410 + ((__bank) * 0x50)) -#define INTR_EN(__bank) (0x420 + ((__bank) * 0x50)) +#define INTR_STATUS(bank) (0x410 + (bank) * 0x50) +#define INTR_EN(bank) (0x420 + (bank) * 0x50) /* bit[1:0] is used differently depending on IP version */ -#define INTR__ECC_UNCOR_ERR 0x0001 /* new IP */ -#define INTR__ECC_TRANSACTION_DONE 0x0001 /* old IP */ -#define INTR__ECC_ERR 0x0002 /* old IP */ -#define INTR__DMA_CMD_COMP 0x0004 -#define INTR__TIME_OUT 0x0008 -#define INTR__PROGRAM_FAIL 0x0010 -#define INTR__ERASE_FAIL 0x0020 -#define INTR__LOAD_COMP 0x0040 -#define INTR__PROGRAM_COMP 0x0080 -#define INTR__ERASE_COMP 0x0100 -#define INTR__PIPE_CPYBCK_CMD_COMP 0x0200 -#define INTR__LOCKED_BLK 0x0400 -#define INTR__UNSUP_CMD 0x0800 -#define INTR__INT_ACT 0x1000 -#define INTR__RST_COMP 0x2000 -#define INTR__PIPE_CMD_ERR 0x4000 -#define INTR__PAGE_XFER_INC 0x8000 - -#define PAGE_CNT(__bank) (0x430 + ((__bank) * 0x50)) -#define ERR_PAGE_ADDR(__bank) (0x440 + ((__bank) * 0x50)) -#define ERR_BLOCK_ADDR(__bank) (0x450 + ((__bank) * 0x50)) +#define INTR__ECC_UNCOR_ERR BIT(0) /* new IP */ +#define INTR__ECC_TRANSACTION_DONE BIT(0) /* old IP */ +#define INTR__ECC_ERR BIT(1) /* old IP */ +#define INTR__DMA_CMD_COMP BIT(2) +#define INTR__TIME_OUT BIT(3) +#define INTR__PROGRAM_FAIL BIT(4) +#define INTR__ERASE_FAIL BIT(5) +#define INTR__LOAD_COMP BIT(6) +#define INTR__PROGRAM_COMP BIT(7) +#define INTR__ERASE_COMP BIT(8) +#define INTR__PIPE_CPYBCK_CMD_COMP BIT(9) +#define INTR__LOCKED_BLK BIT(10) +#define INTR__UNSUP_CMD BIT(11) +#define INTR__INT_ACT BIT(12) +#define INTR__RST_COMP BIT(13) +#define INTR__PIPE_CMD_ERR BIT(14) +#define INTR__PAGE_XFER_INC BIT(15) + +#define PAGE_CNT(bank) (0x430 + (bank) * 0x50) +#define ERR_PAGE_ADDR(bank) (0x440 + (bank) * 0x50) +#define ERR_BLOCK_ADDR(bank) (0x450 + (bank) * 0x50) #define ECC_THRESHOLD 0x600 -#define ECC_THRESHOLD__VALUE 0x03ff +#define ECC_THRESHOLD__VALUE GENMASK(9, 0) #define ECC_ERROR_BLOCK_ADDRESS 0x610 -#define ECC_ERROR_BLOCK_ADDRESS__VALUE 0xffff +#define ECC_ERROR_BLOCK_ADDRESS__VALUE GENMASK(15, 0) #define ECC_ERROR_PAGE_ADDRESS 0x620 -#define ECC_ERROR_PAGE_ADDRESS__VALUE 0x0fff -#define ECC_ERROR_PAGE_ADDRESS__BANK 0xf000 +#define ECC_ERROR_PAGE_ADDRESS__VALUE GENMASK(11, 0) +#define ECC_ERROR_PAGE_ADDRESS__BANK GENMASK(15, 12) #define ECC_ERROR_ADDRESS 0x630 -#define ECC_ERROR_ADDRESS__OFFSET 0x0fff -#define ECC_ERROR_ADDRESS__SECTOR_NR 0xf000 +#define ECC_ERROR_ADDRESS__OFFSET GENMASK(11, 0) +#define ECC_ERROR_ADDRESS__SECTOR_NR GENMASK(15, 12) #define ERR_CORRECTION_INFO 0x640 -#define ERR_CORRECTION_INFO__BYTEMASK 0x00ff -#define ERR_CORRECTION_INFO__DEVICE_NR 0x0f00 -#define ERR_CORRECTION_INFO__ERROR_TYPE 0x4000 -#define ERR_CORRECTION_INFO__LAST_ERR_INFO 0x8000 +#define ERR_CORRECTION_INFO__BYTEMASK GENMASK(7, 0) +#define ERR_CORRECTION_INFO__DEVICE_NR GENMASK(11, 8) +#define ERR_CORRECTION_INFO__ERROR_TYPE BIT(14) +#define ERR_CORRECTION_INFO__LAST_ERR_INFO BIT(15) #define ECC_COR_INFO(bank) (0x650 + (bank) / 2 * 0x10) #define ECC_COR_INFO__SHIFT(bank) ((bank) % 2 * 8) -#define ECC_COR_INFO__MAX_ERRORS 0x007f -#define ECC_COR_INFO__UNCOR_ERR 0x0080 +#define ECC_COR_INFO__MAX_ERRORS GENMASK(6, 0) +#define ECC_COR_INFO__UNCOR_ERR BIT(7) #define DMA_ENABLE 0x700 -#define DMA_ENABLE__FLAG 0x0001 +#define DMA_ENABLE__FLAG BIT(0) #define IGNORE_ECC_DONE 0x710 -#define IGNORE_ECC_DONE__FLAG 0x0001 +#define IGNORE_ECC_DONE__FLAG BIT(0) #define DMA_INTR 0x720 #define DMA_INTR_EN 0x730 -#define DMA_INTR__TARGET_ERROR 0x0001 -#define DMA_INTR__DESC_COMP_CHANNEL0 0x0002 -#define DMA_INTR__DESC_COMP_CHANNEL1 0x0004 -#define DMA_INTR__DESC_COMP_CHANNEL2 0x0008 -#define DMA_INTR__DESC_COMP_CHANNEL3 0x0010 -#define DMA_INTR__MEMCOPY_DESC_COMP 0x0020 +#define DMA_INTR__TARGET_ERROR BIT(0) +#define DMA_INTR__DESC_COMP_CHANNEL0 BIT(1) +#define DMA_INTR__DESC_COMP_CHANNEL1 BIT(2) +#define DMA_INTR__DESC_COMP_CHANNEL2 BIT(3) +#define DMA_INTR__DESC_COMP_CHANNEL3 BIT(4) +#define DMA_INTR__MEMCOPY_DESC_COMP BIT(5) #define TARGET_ERR_ADDR_LO 0x740 -#define TARGET_ERR_ADDR_LO__VALUE 0xffff +#define TARGET_ERR_ADDR_LO__VALUE GENMASK(15, 0) #define TARGET_ERR_ADDR_HI 0x750 -#define TARGET_ERR_ADDR_HI__VALUE 0xffff +#define TARGET_ERR_ADDR_HI__VALUE GENMASK(15, 0) #define CHNL_ACTIVE 0x760 -#define CHNL_ACTIVE__CHANNEL0 0x0001 -#define CHNL_ACTIVE__CHANNEL1 0x0002 -#define CHNL_ACTIVE__CHANNEL2 0x0004 -#define CHNL_ACTIVE__CHANNEL3 0x0008 +#define CHNL_ACTIVE__CHANNEL0 BIT(0) +#define CHNL_ACTIVE__CHANNEL1 BIT(1) +#define CHNL_ACTIVE__CHANNEL2 BIT(2) +#define CHNL_ACTIVE__CHANNEL3 BIT(3) #define FAIL 1 /*failed flag*/ #define PASS 0 /*success flag*/ -- cgit v1.2.3-59-g8ed1b From 2c8f8afa7f92acb07641bf95b940d384ed1d0294 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 7 Jun 2017 20:52:10 +0900 Subject: mtd: nand: add generic helpers to check, match, maximize ECC settings Driver are responsible for setting up ECC parameters correctly. Those include: - Check if ECC parameters specified (usually by DT) are valid - Meet the chip's ECC requirement - Maximize ECC strength if NAND_ECC_MAXIMIZE flag is set The logic can be generalized by factoring out common code. This commit adds 3 helpers to the NAND framework: nand_check_ecc_caps - Check if preset step_size and strength are valid nand_match_ecc_req - Match the chip's requirement nand_maximize_ecc - Maximize the ECC strength To use the helpers above, a driver needs to provide: - Data array of supported ECC step size and strength - A hook that calculates ECC bytes from the combination of step_size and strength. By using those helpers, code duplication among drivers will be reduced. Signed-off-by: Masahiro Yamada Signed-off-by: Boris Brezillon --- drivers/mtd/nand/nand_base.c | 220 +++++++++++++++++++++++++++++++++++++++++++ include/linux/mtd/nand.h | 33 +++++++ 2 files changed, 253 insertions(+) diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index 2404bb046b69..85edac9b2bb5 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -4523,6 +4523,226 @@ static int nand_set_ecc_soft_ops(struct mtd_info *mtd) } } +/** + * nand_check_ecc_caps - check the sanity of preset ECC settings + * @chip: nand chip info structure + * @caps: ECC caps info structure + * @oobavail: OOB size that the ECC engine can use + * + * When ECC step size and strength are already set, check if they are supported + * by the controller and the calculated ECC bytes fit within the chip's OOB. + * On success, the calculated ECC bytes is set. + */ +int nand_check_ecc_caps(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail) +{ + struct mtd_info *mtd = nand_to_mtd(chip); + const struct nand_ecc_step_info *stepinfo; + int preset_step = chip->ecc.size; + int preset_strength = chip->ecc.strength; + int nsteps, ecc_bytes; + int i, j; + + if (WARN_ON(oobavail < 0)) + return -EINVAL; + + if (!preset_step || !preset_strength) + return -ENODATA; + + nsteps = mtd->writesize / preset_step; + + for (i = 0; i < caps->nstepinfos; i++) { + stepinfo = &caps->stepinfos[i]; + + if (stepinfo->stepsize != preset_step) + continue; + + for (j = 0; j < stepinfo->nstrengths; j++) { + if (stepinfo->strengths[j] != preset_strength) + continue; + + ecc_bytes = caps->calc_ecc_bytes(preset_step, + preset_strength); + if (WARN_ON_ONCE(ecc_bytes < 0)) + return ecc_bytes; + + if (ecc_bytes * nsteps > oobavail) { + pr_err("ECC (step, strength) = (%d, %d) does not fit in OOB", + preset_step, preset_strength); + return -ENOSPC; + } + + chip->ecc.bytes = ecc_bytes; + + return 0; + } + } + + pr_err("ECC (step, strength) = (%d, %d) not supported on this controller", + preset_step, preset_strength); + + return -ENOTSUPP; +} +EXPORT_SYMBOL_GPL(nand_check_ecc_caps); + +/** + * nand_match_ecc_req - meet the chip's requirement with least ECC bytes + * @chip: nand chip info structure + * @caps: ECC engine caps info structure + * @oobavail: OOB size that the ECC engine can use + * + * If a chip's ECC requirement is provided, try to meet it with the least + * number of ECC bytes (i.e. with the largest number of OOB-free bytes). + * On success, the chosen ECC settings are set. + */ +int nand_match_ecc_req(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail) +{ + struct mtd_info *mtd = nand_to_mtd(chip); + const struct nand_ecc_step_info *stepinfo; + int req_step = chip->ecc_step_ds; + int req_strength = chip->ecc_strength_ds; + int req_corr, step_size, strength, nsteps, ecc_bytes, ecc_bytes_total; + int best_step, best_strength, best_ecc_bytes; + int best_ecc_bytes_total = INT_MAX; + int i, j; + + if (WARN_ON(oobavail < 0)) + return -EINVAL; + + /* No information provided by the NAND chip */ + if (!req_step || !req_strength) + return -ENOTSUPP; + + /* number of correctable bits the chip requires in a page */ + req_corr = mtd->writesize / req_step * req_strength; + + for (i = 0; i < caps->nstepinfos; i++) { + stepinfo = &caps->stepinfos[i]; + step_size = stepinfo->stepsize; + + for (j = 0; j < stepinfo->nstrengths; j++) { + strength = stepinfo->strengths[j]; + + /* + * If both step size and strength are smaller than the + * chip's requirement, it is not easy to compare the + * resulted reliability. + */ + if (step_size < req_step && strength < req_strength) + continue; + + if (mtd->writesize % step_size) + continue; + + nsteps = mtd->writesize / step_size; + + ecc_bytes = caps->calc_ecc_bytes(step_size, strength); + if (WARN_ON_ONCE(ecc_bytes < 0)) + continue; + ecc_bytes_total = ecc_bytes * nsteps; + + if (ecc_bytes_total > oobavail || + strength * nsteps < req_corr) + continue; + + /* + * We assume the best is to meet the chip's requrement + * with the least number of ECC bytes. + */ + if (ecc_bytes_total < best_ecc_bytes_total) { + best_ecc_bytes_total = ecc_bytes_total; + best_step = step_size; + best_strength = strength; + best_ecc_bytes = ecc_bytes; + } + } + } + + if (best_ecc_bytes_total == INT_MAX) + return -ENOTSUPP; + + chip->ecc.size = best_step; + chip->ecc.strength = best_strength; + chip->ecc.bytes = best_ecc_bytes; + + return 0; +} +EXPORT_SYMBOL_GPL(nand_match_ecc_req); + +/** + * nand_maximize_ecc - choose the max ECC strength available + * @chip: nand chip info structure + * @caps: ECC engine caps info structure + * @oobavail: OOB size that the ECC engine can use + * + * Choose the max ECC strength that is supported on the controller, and can fit + * within the chip's OOB. On success, the chosen ECC settings are set. + */ +int nand_maximize_ecc(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail) +{ + struct mtd_info *mtd = nand_to_mtd(chip); + const struct nand_ecc_step_info *stepinfo; + int step_size, strength, nsteps, ecc_bytes, corr; + int best_corr = 0; + int best_step = 0; + int best_strength, best_ecc_bytes; + int i, j; + + if (WARN_ON(oobavail < 0)) + return -EINVAL; + + for (i = 0; i < caps->nstepinfos; i++) { + stepinfo = &caps->stepinfos[i]; + step_size = stepinfo->stepsize; + + /* If chip->ecc.size is already set, respect it */ + if (chip->ecc.size && step_size != chip->ecc.size) + continue; + + for (j = 0; j < stepinfo->nstrengths; j++) { + strength = stepinfo->strengths[j]; + + if (mtd->writesize % step_size) + continue; + + nsteps = mtd->writesize / step_size; + + ecc_bytes = caps->calc_ecc_bytes(step_size, strength); + if (WARN_ON_ONCE(ecc_bytes < 0)) + continue; + + if (ecc_bytes * nsteps > oobavail) + continue; + + corr = strength * nsteps; + + /* + * If the number of correctable bits is the same, + * bigger step_size has more reliability. + */ + if (corr > best_corr || + (corr == best_corr && step_size > best_step)) { + best_corr = corr; + best_step = step_size; + best_strength = strength; + best_ecc_bytes = ecc_bytes; + } + } + } + + if (!best_corr) + return -ENOTSUPP; + + chip->ecc.size = best_step; + chip->ecc.strength = best_strength; + chip->ecc.bytes = best_ecc_bytes; + + return 0; +} +EXPORT_SYMBOL_GPL(nand_maximize_ecc); + /* * Check if the chip configuration meet the datasheet requirements. diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 8b3607bde1b5..568f53e812cd 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -481,6 +481,30 @@ static inline void nand_hw_control_init(struct nand_hw_control *nfc) init_waitqueue_head(&nfc->wq); } +/** + * struct nand_ecc_step_info - ECC step information of ECC engine + * @stepsize: data bytes per ECC step + * @strengths: array of supported strengths + * @nstrengths: number of supported strengths + */ +struct nand_ecc_step_info { + int stepsize; + const int *strengths; + int nstrengths; +}; + +/** + * struct nand_ecc_caps - capability of ECC engine + * @stepinfos: array of ECC step information + * @nstepinfos: number of ECC step information + * @calc_ecc_bytes: driver's hook to calculate ECC bytes per step + */ +struct nand_ecc_caps { + const struct nand_ecc_step_info *stepinfos; + int nstepinfos; + int (*calc_ecc_bytes)(int step_size, int strength); +}; + /** * struct nand_ecc_ctrl - Control structure for ECC * @mode: ECC mode @@ -1246,6 +1270,15 @@ int nand_check_erased_ecc_chunk(void *data, int datalen, void *extraoob, int extraooblen, int threshold); +int nand_check_ecc_caps(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail); + +int nand_match_ecc_req(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail); + +int nand_maximize_ecc(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail); + /* Default write_oob implementation */ int nand_write_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page); -- cgit v1.2.3-59-g8ed1b From a03c60178c181767ecfb26fb311a88742d228118 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 7 Jun 2017 20:52:11 +0900 Subject: mtd: nand: add a shorthand to generate nand_ecc_caps structure struct nand_ecc_caps was designed as flexible as possible to support multiple stepsizes (like sunxi_nand.c). So, we need to write multiple arrays even for the simplest case. I guess many controllers support a single stepsize, so here is a shorthand macro for the case. It allows to describe like ... NAND_ECC_CAPS_SINGLE(denali_pci_ecc_caps, denali_calc_ecc_bytes, 512, 8, 15); ... instead of static const int denali_pci_ecc_strengths[] = {8, 15}; static const struct nand_ecc_step_info denali_pci_ecc_stepinfo = { .stepsize = 512, .strengths = denali_pci_ecc_strengths, .nstrengths = ARRAY_SIZE(denali_pci_ecc_strengths), }; static const struct nand_ecc_caps denali_pci_ecc_caps = { .stepinfos = &denali_pci_ecc_stepinfo, .nstepinfos = 1, .calc_ecc_bytes = denali_calc_ecc_bytes, }; Signed-off-by: Masahiro Yamada Signed-off-by: Boris Brezillon --- include/linux/mtd/nand.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 568f53e812cd..dc8fbc033442 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -505,6 +505,20 @@ struct nand_ecc_caps { int (*calc_ecc_bytes)(int step_size, int strength); }; +/* a shorthand to generate struct nand_ecc_caps with only one ECC stepsize */ +#define NAND_ECC_CAPS_SINGLE(__name, __calc, __step, ...) \ +static const int __name##_strengths[] = { __VA_ARGS__ }; \ +static const struct nand_ecc_step_info __name##_stepinfo = { \ + .stepsize = __step, \ + .strengths = __name##_strengths, \ + .nstrengths = ARRAY_SIZE(__name##_strengths), \ +}; \ +static const struct nand_ecc_caps __name = { \ + .stepinfos = &__name##_stepinfo, \ + .nstepinfos = 1, \ + .calc_ecc_bytes = __calc, \ +} + /** * struct nand_ecc_ctrl - Control structure for ECC * @mode: ECC mode -- cgit v1.2.3-59-g8ed1b From 7de117fd5bfe0d84e50714ef5dcf5f3cec7f0eef Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 7 Jun 2017 20:52:12 +0900 Subject: mtd: nand: denali: avoid hard-coding ECC step, strength, bytes This driver was originally written for the Intel MRST platform with several platform-specific parameters hard-coded. Currently, the ECC settings are hard-coded as follows: #define ECC_SECTOR_SIZE 512 #define ECC_8BITS 14 #define ECC_15BITS 26 Therefore, the driver can only support two cases. - ecc.size = 512, ecc.strength = 8 --> ecc.bytes = 14 - ecc.size = 512, ecc.strength = 15 --> ecc.bytes = 26 However, these are actually customizable parameters, for example, UniPhier platform supports the following: - ecc.size = 1024, ecc.strength = 8 --> ecc.bytes = 14 - ecc.size = 1024, ecc.strength = 16 --> ecc.bytes = 28 - ecc.size = 1024, ecc.strength = 24 --> ecc.bytes = 42 So, we need to handle the ECC parameters in a more generic manner. Fortunately, the Denali User's Guide explains how to calculate the ecc.bytes. The formula is: ecc.bytes = 2 * CEIL(13 * ecc.strength / 16) (for ecc.size = 512) ecc.bytes = 2 * CEIL(14 * ecc.strength / 16) (for ecc.size = 1024) For DT platforms, it would be reasonable to allow DT to specify ECC strength by either "nand-ecc-strength" or "nand-ecc-maximize". If none of them is specified, the driver will try to meet the chip's ECC requirement. For PCI platforms, the max ECC strength is used to keep the original behavior. Newer versions of this IP need ecc.size and ecc.steps explicitly set up via the following registers: CFG_DATA_BLOCK_SIZE (0x6b0) CFG_LAST_DATA_BLOCK_SIZE (0x6c0) CFG_NUM_DATA_BLOCKS (0x6d0) For older IP versions, write accesses to these registers are just ignored. Signed-off-by: Masahiro Yamada Acked-by: Rob Herring Signed-off-by: Boris Brezillon --- .../devicetree/bindings/mtd/denali-nand.txt | 7 ++ drivers/mtd/nand/denali.c | 87 +++++++++++++--------- drivers/mtd/nand/denali.h | 12 ++- drivers/mtd/nand/denali_dt.c | 5 ++ drivers/mtd/nand/denali_pci.c | 4 + 5 files changed, 78 insertions(+), 37 deletions(-) diff --git a/Documentation/devicetree/bindings/mtd/denali-nand.txt b/Documentation/devicetree/bindings/mtd/denali-nand.txt index e593bbeb2115..b7742a7363ea 100644 --- a/Documentation/devicetree/bindings/mtd/denali-nand.txt +++ b/Documentation/devicetree/bindings/mtd/denali-nand.txt @@ -7,6 +7,13 @@ Required properties: - reg-names: Should contain the reg names "nand_data" and "denali_reg" - interrupts : The interrupt number. +Optional properties: + - nand-ecc-step-size: see nand.txt for details. If present, the value must be + 512 for "altr,socfpga-denali-nand" + - nand-ecc-strength: see nand.txt for details. Valid values are: + 8, 15 for "altr,socfpga-denali-nand" + - nand-ecc-maximize: see nand.txt for details + The device tree may optionally contain sub-nodes describing partitions of the address space. See partition.txt for more detail. diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c index b3c99d98fdee..2d3d9875dfaa 100644 --- a/drivers/mtd/nand/denali.c +++ b/drivers/mtd/nand/denali.c @@ -886,8 +886,6 @@ static int denali_hw_ecc_fixup(struct mtd_info *mtd, return max_bitflips; } -#define ECC_SECTOR_SIZE 512 - #define ECC_SECTOR(x) (((x) & ECC_ERROR_ADDRESS__SECTOR_NR) >> 12) #define ECC_BYTE(x) (((x) & ECC_ERROR_ADDRESS__OFFSET)) #define ECC_CORRECTION_VALUE(x) ((x) & ERR_CORRECTION_INFO__BYTEMASK) @@ -899,6 +897,7 @@ static int denali_sw_ecc_fixup(struct mtd_info *mtd, struct denali_nand_info *denali, unsigned long *uncor_ecc_flags, uint8_t *buf) { + unsigned int ecc_size = denali->nand.ecc.size; unsigned int bitflips = 0; unsigned int max_bitflips = 0; uint32_t err_addr, err_cor_info; @@ -928,9 +927,9 @@ static int denali_sw_ecc_fixup(struct mtd_info *mtd, * an erased sector. */ *uncor_ecc_flags |= BIT(err_sector); - } else if (err_byte < ECC_SECTOR_SIZE) { + } else if (err_byte < ecc_size) { /* - * If err_byte is larger than ECC_SECTOR_SIZE, means error + * If err_byte is larger than ecc_size, means error * happened in OOB, so we ignore it. It's no need for * us to correct it err_device is represented the NAND * error bits are happened in if there are more than @@ -939,7 +938,7 @@ static int denali_sw_ecc_fixup(struct mtd_info *mtd, int offset; unsigned int flips_in_byte; - offset = (err_sector * ECC_SECTOR_SIZE + err_byte) * + offset = (err_sector * ecc_size + err_byte) * denali->devnum + err_device; /* correct the ECC error */ @@ -1345,13 +1344,39 @@ static void denali_hw_init(struct denali_nand_info *denali) denali_irq_init(denali); } -/* - * Althogh controller spec said SLC ECC is forceb to be 4bit, - * but denali controller in MRST only support 15bit and 8bit ECC - * correction - */ -#define ECC_8BITS 14 -#define ECC_15BITS 26 +int denali_calc_ecc_bytes(int step_size, int strength) +{ + /* BCH code. Denali requires ecc.bytes to be multiple of 2 */ + return DIV_ROUND_UP(strength * fls(step_size * 8), 16) * 2; +} +EXPORT_SYMBOL(denali_calc_ecc_bytes); + +static int denali_ecc_setup(struct mtd_info *mtd, struct nand_chip *chip, + struct denali_nand_info *denali) +{ + int oobavail = mtd->oobsize - denali->bbtskipbytes; + int ret; + + /* + * If .size and .strength are already set (usually by DT), + * check if they are supported by this controller. + */ + if (chip->ecc.size && chip->ecc.strength) + return nand_check_ecc_caps(chip, denali->ecc_caps, oobavail); + + /* + * We want .size and .strength closest to the chip's requirement + * unless NAND_ECC_MAXIMIZE is requested. + */ + if (!(chip->ecc.options & NAND_ECC_MAXIMIZE)) { + ret = nand_match_ecc_req(chip, denali->ecc_caps, oobavail); + if (!ret) + return 0; + } + + /* Max ECC strength is the last thing we can do */ + return nand_maximize_ecc(chip, denali->ecc_caps, oobavail); +} static int denali_ooblayout_ecc(struct mtd_info *mtd, int section, struct mtd_oob_region *oobregion) @@ -1588,34 +1613,26 @@ int denali_init(struct denali_nand_info *denali) /* no subpage writes on denali */ chip->options |= NAND_NO_SUBPAGE_WRITE; - /* - * Denali Controller only support 15bit and 8bit ECC in MRST, - * so just let controller do 15bit ECC for MLC and 8bit ECC for - * SLC if possible. - * */ - if (!nand_is_slc(chip) && - (mtd->oobsize > (denali->bbtskipbytes + - ECC_15BITS * (mtd->writesize / - ECC_SECTOR_SIZE)))) { - /* if MLC OOB size is large enough, use 15bit ECC*/ - chip->ecc.strength = 15; - chip->ecc.bytes = ECC_15BITS; - iowrite32(15, denali->flash_reg + ECC_CORRECTION); - } else if (mtd->oobsize < (denali->bbtskipbytes + - ECC_8BITS * (mtd->writesize / - ECC_SECTOR_SIZE))) { - pr_err("Your NAND chip OOB is not large enough to contain 8bit ECC correction codes"); + ret = denali_ecc_setup(mtd, chip, denali); + if (ret) { + dev_err(denali->dev, "Failed to setup ECC settings.\n"); goto failed_req_irq; - } else { - chip->ecc.strength = 8; - chip->ecc.bytes = ECC_8BITS; - iowrite32(8, denali->flash_reg + ECC_CORRECTION); } + dev_dbg(denali->dev, + "chosen ECC settings: step=%d, strength=%d, bytes=%d\n", + chip->ecc.size, chip->ecc.strength, chip->ecc.bytes); + + iowrite32(chip->ecc.strength, denali->flash_reg + ECC_CORRECTION); + + iowrite32(chip->ecc.size, denali->flash_reg + CFG_DATA_BLOCK_SIZE); + iowrite32(chip->ecc.size, denali->flash_reg + CFG_LAST_DATA_BLOCK_SIZE); + /* chip->ecc.steps is set by nand_scan_tail(); not available here */ + iowrite32(mtd->writesize / chip->ecc.size, + denali->flash_reg + CFG_NUM_DATA_BLOCKS); + mtd_set_ooblayout(mtd, &denali_ooblayout_ops); - /* override the default read operations */ - chip->ecc.size = ECC_SECTOR_SIZE; chip->ecc.read_page = denali_read_page; chip->ecc.read_page_raw = denali_read_page_raw; chip->ecc.write_page = denali_write_page; diff --git a/drivers/mtd/nand/denali.h b/drivers/mtd/nand/denali.h index 37833535a7a3..a06ed741b550 100644 --- a/drivers/mtd/nand/denali.h +++ b/drivers/mtd/nand/denali.h @@ -259,6 +259,14 @@ #define ECC_COR_INFO__MAX_ERRORS GENMASK(6, 0) #define ECC_COR_INFO__UNCOR_ERR BIT(7) +#define CFG_DATA_BLOCK_SIZE 0x6b0 + +#define CFG_LAST_DATA_BLOCK_SIZE 0x6c0 + +#define CFG_NUM_DATA_BLOCKS 0x6d0 + +#define CFG_META_DATA_SIZE 0x6e0 + #define DMA_ENABLE 0x700 #define DMA_ENABLE__FLAG BIT(0) @@ -301,8 +309,6 @@ #define MODE_10 0x08000000 #define MODE_11 0x0C000000 -#define ECC_SECTOR_SIZE 512 - struct nand_buf { int head; int tail; @@ -337,11 +343,13 @@ struct denali_nand_info { int max_banks; unsigned int revision; unsigned int caps; + const struct nand_ecc_caps *ecc_caps; }; #define DENALI_CAP_HW_ECC_FIXUP BIT(0) #define DENALI_CAP_DMA_64BIT BIT(1) +int denali_calc_ecc_bytes(int step_size, int strength); extern int denali_init(struct denali_nand_info *denali); extern void denali_remove(struct denali_nand_info *denali); diff --git a/drivers/mtd/nand/denali_dt.c b/drivers/mtd/nand/denali_dt.c index b48430fe3cd4..bd1aa4cf4457 100644 --- a/drivers/mtd/nand/denali_dt.c +++ b/drivers/mtd/nand/denali_dt.c @@ -32,10 +32,14 @@ struct denali_dt { struct denali_dt_data { unsigned int revision; unsigned int caps; + const struct nand_ecc_caps *ecc_caps; }; +NAND_ECC_CAPS_SINGLE(denali_socfpga_ecc_caps, denali_calc_ecc_bytes, + 512, 8, 15); static const struct denali_dt_data denali_socfpga_data = { .caps = DENALI_CAP_HW_ECC_FIXUP, + .ecc_caps = &denali_socfpga_ecc_caps, }; static const struct of_device_id denali_nand_dt_ids[] = { @@ -64,6 +68,7 @@ static int denali_dt_probe(struct platform_device *pdev) if (data) { denali->revision = data->revision; denali->caps = data->caps; + denali->ecc_caps = data->ecc_caps; } denali->platform = DT; diff --git a/drivers/mtd/nand/denali_pci.c b/drivers/mtd/nand/denali_pci.c index ac843238b77e..37dc0934c24c 100644 --- a/drivers/mtd/nand/denali_pci.c +++ b/drivers/mtd/nand/denali_pci.c @@ -27,6 +27,8 @@ static const struct pci_device_id denali_pci_ids[] = { }; MODULE_DEVICE_TABLE(pci, denali_pci_ids); +NAND_ECC_CAPS_SINGLE(denali_pci_ecc_caps, denali_calc_ecc_bytes, 512, 8, 15); + static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) { int ret; @@ -65,6 +67,8 @@ static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) pci_set_master(dev); denali->dev = &dev->dev; denali->irq = dev->irq; + denali->ecc_caps = &denali_pci_ecc_caps; + denali->nand.ecc.options |= NAND_ECC_MAXIMIZE; ret = pci_request_regions(dev, DENALI_NAND_NAME); if (ret) { -- cgit v1.2.3-59-g8ed1b From 0615e7ad5d52594d12d67aa987d1fd98164e2f64 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 7 Jun 2017 20:52:13 +0900 Subject: mtd: nand: denali: remove Toshiba and Hynix specific fixup code The Denali IP can automatically detect device parameters such as page size, oob size, device width, etc. and this driver currently relies on it. However, this hardware function is known to be problematic. [1] Due to a hardware bug, various misdetected cases were reported. That is why get_toshiba_nand_para() and get_hynix_nand_para() exist to fix-up the misdetected parameters. It is not realistic to add a new NAND device to the *black list* every time we are hit by a misdetected case. We would never be able to guarantee that all cases are covered. [2] Because this feature is unreliable, it is disabled on some platforms. The nand_scan_ident() detects device parameters in a more tested way. The hardware should not set the device parameter registers in a different, unreliable way. Instead, set the parameters from the nand_scan_ident() back to the registers. Signed-off-by: Masahiro Yamada Signed-off-by: Boris Brezillon --- drivers/mtd/nand/denali.c | 40 ++++++---------------------------------- 1 file changed, 6 insertions(+), 34 deletions(-) diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c index 2d3d9875dfaa..2b4618bb8d72 100644 --- a/drivers/mtd/nand/denali.c +++ b/drivers/mtd/nand/denali.c @@ -337,36 +337,6 @@ static void get_samsung_nand_para(struct denali_nand_info *denali, } } -static void get_toshiba_nand_para(struct denali_nand_info *denali) -{ - /* - * Workaround to fix a controller bug which reports a wrong - * spare area size for some kind of Toshiba NAND device - */ - if ((ioread32(denali->flash_reg + DEVICE_MAIN_AREA_SIZE) == 4096) && - (ioread32(denali->flash_reg + DEVICE_SPARE_AREA_SIZE) == 64)) - iowrite32(216, denali->flash_reg + DEVICE_SPARE_AREA_SIZE); -} - -static void get_hynix_nand_para(struct denali_nand_info *denali, - uint8_t device_id) -{ - switch (device_id) { - case 0xD5: /* Hynix H27UAG8T2A, H27UBG8U5A or H27UCG8VFA */ - case 0xD7: /* Hynix H27UDG8VEM, H27UCG8UDM or H27UCG8V5A */ - iowrite32(128, denali->flash_reg + PAGES_PER_BLOCK); - iowrite32(4096, denali->flash_reg + DEVICE_MAIN_AREA_SIZE); - iowrite32(224, denali->flash_reg + DEVICE_SPARE_AREA_SIZE); - iowrite32(0, denali->flash_reg + DEVICE_WIDTH); - break; - default: - dev_warn(denali->dev, - "Unknown Hynix NAND (Device ID: 0x%x).\n" - "Will use default parameter values instead.\n", - device_id); - } -} - /* * determines how many NAND chips are connected to the controller. Note for * Intel CE4100 devices we don't support more than one device. @@ -453,10 +423,6 @@ static uint16_t denali_nand_timing_set(struct denali_nand_info *denali) return FAIL; } else if (maf_id == 0xEC) { /* Samsung NAND */ get_samsung_nand_para(denali, device_id); - } else if (maf_id == 0x98) { /* Toshiba NAND */ - get_toshiba_nand_para(denali); - } else if (maf_id == 0xAD) { /* Hynix NAND */ - get_hynix_nand_para(denali, device_id); } dev_info(denali->dev, @@ -1624,6 +1590,12 @@ int denali_init(struct denali_nand_info *denali) chip->ecc.size, chip->ecc.strength, chip->ecc.bytes); iowrite32(chip->ecc.strength, denali->flash_reg + ECC_CORRECTION); + iowrite32(mtd->erasesize / mtd->writesize, + denali->flash_reg + PAGES_PER_BLOCK); + iowrite32(chip->options & NAND_BUSWIDTH_16 ? 1 : 0, + denali->flash_reg + DEVICE_WIDTH); + iowrite32(mtd->writesize, denali->flash_reg + DEVICE_MAIN_AREA_SIZE); + iowrite32(mtd->oobsize, denali->flash_reg + DEVICE_SPARE_AREA_SIZE); iowrite32(chip->ecc.size, denali->flash_reg + CFG_DATA_BLOCK_SIZE); iowrite32(chip->ecc.size, denali->flash_reg + CFG_LAST_DATA_BLOCK_SIZE); -- cgit v1.2.3-59-g8ed1b From 91300dd67baec4f046aa76e3a2e8222d15cc76e9 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 7 Jun 2017 20:52:14 +0900 Subject: mtd: nand: denali_dt: add compatible strings for UniPhier SoC variants Add two compatible strings for UniPhier SoC family. "socionext,uniphier-denali-nand-v5a" is used on UniPhier sLD3, LD4, Pro4, sLD8. "socionext,uniphier-denali-nand-v5b" is used on UniPhier Pro5, PXs2, LD6b, LD11, LD20. Signed-off-by: Masahiro Yamada Acked-by: Rob Herring Signed-off-by: Boris Brezillon --- .../devicetree/bindings/mtd/denali-nand.txt | 6 ++++++ drivers/mtd/nand/denali_dt.c | 25 ++++++++++++++++++++++ 2 files changed, 31 insertions(+) diff --git a/Documentation/devicetree/bindings/mtd/denali-nand.txt b/Documentation/devicetree/bindings/mtd/denali-nand.txt index b7742a7363ea..504291d2e5c2 100644 --- a/Documentation/devicetree/bindings/mtd/denali-nand.txt +++ b/Documentation/devicetree/bindings/mtd/denali-nand.txt @@ -3,6 +3,8 @@ Required properties: - compatible : should be one of the following: "altr,socfpga-denali-nand" - for Altera SOCFPGA + "socionext,uniphier-denali-nand-v5a" - for Socionext UniPhier (v5a) + "socionext,uniphier-denali-nand-v5b" - for Socionext UniPhier (v5b) - reg : should contain registers location and length for data and reg. - reg-names: Should contain the reg names "nand_data" and "denali_reg" - interrupts : The interrupt number. @@ -10,8 +12,12 @@ Required properties: Optional properties: - nand-ecc-step-size: see nand.txt for details. If present, the value must be 512 for "altr,socfpga-denali-nand" + 1024 for "socionext,uniphier-denali-nand-v5a" + 1024 for "socionext,uniphier-denali-nand-v5b" - nand-ecc-strength: see nand.txt for details. Valid values are: 8, 15 for "altr,socfpga-denali-nand" + 8, 16, 24 for "socionext,uniphier-denali-nand-v5a" + 8, 16 for "socionext,uniphier-denali-nand-v5b" - nand-ecc-maximize: see nand.txt for details The device tree may optionally contain sub-nodes describing partitions of the diff --git a/drivers/mtd/nand/denali_dt.c b/drivers/mtd/nand/denali_dt.c index bd1aa4cf4457..be598230c108 100644 --- a/drivers/mtd/nand/denali_dt.c +++ b/drivers/mtd/nand/denali_dt.c @@ -42,11 +42,36 @@ static const struct denali_dt_data denali_socfpga_data = { .ecc_caps = &denali_socfpga_ecc_caps, }; +NAND_ECC_CAPS_SINGLE(denali_uniphier_v5a_ecc_caps, denali_calc_ecc_bytes, + 1024, 8, 16, 24); +static const struct denali_dt_data denali_uniphier_v5a_data = { + .caps = DENALI_CAP_HW_ECC_FIXUP | + DENALI_CAP_DMA_64BIT, + .ecc_caps = &denali_uniphier_v5a_ecc_caps, +}; + +NAND_ECC_CAPS_SINGLE(denali_uniphier_v5b_ecc_caps, denali_calc_ecc_bytes, + 1024, 8, 16); +static const struct denali_dt_data denali_uniphier_v5b_data = { + .revision = 0x0501, + .caps = DENALI_CAP_HW_ECC_FIXUP | + DENALI_CAP_DMA_64BIT, + .ecc_caps = &denali_uniphier_v5b_ecc_caps, +}; + static const struct of_device_id denali_nand_dt_ids[] = { { .compatible = "altr,socfpga-denali-nand", .data = &denali_socfpga_data, }, + { + .compatible = "socionext,uniphier-denali-nand-v5a", + .data = &denali_uniphier_v5a_data, + }, + { + .compatible = "socionext,uniphier-denali-nand-v5b", + .data = &denali_uniphier_v5b_data, + }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, denali_nand_dt_ids); -- cgit v1.2.3-59-g8ed1b From 0527eb372301bfd9b84160adb6c132b443ae3013 Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Tue, 2 May 2017 19:35:37 +0530 Subject: pwm: tegra: Set maximum pwm clock source per SoC tapeout The PWM hardware IP is taped-out with different maximum frequency on different SoCs. From HW team: Before Tegra186, it is 48 MHz. In Tegra186, it is 102 MHz. Add support to limit the clock source frequency to the maximum IP supported frequency. Provide these values via SoC chipdata. Signed-off-by: Laxman Dewangan Acked-by: Jon Hunter Signed-off-by: Thierry Reding --- drivers/pwm/pwm-tegra.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/drivers/pwm/pwm-tegra.c b/drivers/pwm/pwm-tegra.c index 8c6ed556db28..e9b33f09ff09 100644 --- a/drivers/pwm/pwm-tegra.c +++ b/drivers/pwm/pwm-tegra.c @@ -41,6 +41,9 @@ struct tegra_pwm_soc { unsigned int num_channels; + + /* Maximum IP frequency for given SoCs */ + unsigned long max_frequency; }; struct tegra_pwm_chip { @@ -201,7 +204,18 @@ static int tegra_pwm_probe(struct platform_device *pdev) if (IS_ERR(pwm->clk)) return PTR_ERR(pwm->clk); - /* Read PWM clock rate from source */ + /* Set maximum frequency of the IP */ + ret = clk_set_rate(pwm->clk, pwm->soc->max_frequency); + if (ret < 0) { + dev_err(&pdev->dev, "Failed to set max frequency: %d\n", ret); + return ret; + } + + /* + * The requested and configured frequency may differ due to + * clock register resolutions. Get the configured frequency + * so that PWM period can be calculated more accurately. + */ pwm->clk_rate = clk_get_rate(pwm->clk); pwm->rst = devm_reset_control_get(&pdev->dev, "pwm"); @@ -273,10 +287,12 @@ static int tegra_pwm_resume(struct device *dev) static const struct tegra_pwm_soc tegra20_pwm_soc = { .num_channels = 4, + .max_frequency = 48000000UL, }; static const struct tegra_pwm_soc tegra186_pwm_soc = { .num_channels = 1, + .max_frequency = 102000000UL, }; static const struct of_device_id tegra_pwm_of_match[] = { -- cgit v1.2.3-59-g8ed1b From a247f7236d06f504e57637b8ec124fc1af226d08 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 13 Jun 2017 14:59:14 +0200 Subject: udf: Remove unused UDF_DEFAULT_BLOCKSIZE The define is unused. Remove it. Signed-off-by: Jan Kara --- fs/udf/super.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/fs/udf/super.c b/fs/udf/super.c index 14b4bc1f6801..462ac2e9258c 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -73,8 +73,6 @@ #define VDS_POS_TERMINATING_DESC 6 #define VDS_POS_LENGTH 7 -#define UDF_DEFAULT_BLOCKSIZE 2048 - #define VSD_FIRST_SECTOR_OFFSET 32768 #define VSD_MAX_SECTOR_OFFSET 0x800000 -- cgit v1.2.3-59-g8ed1b From d690694be93332cf7a91a6024b0598601f5f993a Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Tue, 13 Jun 2017 14:58:42 +0200 Subject: mtd: nand: atmel: drop unused include The Atmel NAND driver doesn't used anything from linux/platform_data/atmel.h, stop including it. Signed-off-by: Alexandre Belloni Signed-off-by: Boris Brezillon --- drivers/mtd/nand/atmel/nand-controller.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mtd/nand/atmel/nand-controller.c b/drivers/mtd/nand/atmel/nand-controller.c index d24e67b95167..d922a88e407f 100644 --- a/drivers/mtd/nand/atmel/nand-controller.c +++ b/drivers/mtd/nand/atmel/nand-controller.c @@ -65,7 +65,6 @@ #include #include #include -#include #include #include "pmecc.h" -- cgit v1.2.3-59-g8ed1b From 7d57e5e933674c116e46f30eee7629c20f9073da Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Tue, 13 Jun 2017 09:22:57 -0600 Subject: vfio/pci: Add Intel XXV710 to hidden INTx devices XXV710 has the same broken INTx behavior as the rest of the X/XL710 series, the interrupt status register is not wired to report pending INTx interrupts, thus we never associate the interrupt to the device. Extend the device IDs to include these so that we hide that the device supports INTx at all to the user. Reported-by: Stefan Assmann Signed-off-by: Alex Williamson Acked-by: Jesse Brandeburg --- drivers/vfio/pci/vfio_pci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 324c52e3a1a4..063c1ce6fa42 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -195,11 +195,11 @@ static bool vfio_pci_nointx(struct pci_dev *pdev) switch (pdev->vendor) { case PCI_VENDOR_ID_INTEL: switch (pdev->device) { - /* All i40e (XL710/X710) 10/20/40GbE NICs */ + /* All i40e (XL710/X710/XXV710) 10/20/25/40GbE NICs */ case 0x1572: case 0x1574: case 0x1580 ... 0x1581: - case 0x1583 ... 0x1589: + case 0x1583 ... 0x158b: case 0x37d0 ... 0x37d2: return true; default: -- cgit v1.2.3-59-g8ed1b From 7b3a10df1d4bd8a83934897442370221b4cd631b Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 18 May 2017 10:34:31 +0300 Subject: vfio: Use ERR_CAST() instead of open coding it It's a small cleanup to use ERR_CAST() here. Signed-off-by: Dan Carpenter Signed-off-by: Alex Williamson --- drivers/vfio/vfio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 561084ab387f..6a49485eb49d 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -382,7 +382,7 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group) if (IS_ERR(dev)) { vfio_free_group_minor(minor); vfio_group_unlock_and_free(group); - return (struct vfio_group *)dev; /* ERR_PTR */ + return ERR_CAST(dev); } group->minor = minor; -- cgit v1.2.3-59-g8ed1b From 1eeef2d7483a7e3f8d2dd2a5b9939b3b814dc549 Mon Sep 17 00:00:00 2001 From: Chris Packham Date: Fri, 9 Jun 2017 15:58:31 +1200 Subject: mtd: handle partitioning on devices with 0 erasesize erasesize is meaningful for flash devices but for SRAM there is no concept of an erase block so erasesize is set to 0. When partitioning these devices instead of ensuring partitions fall on erasesize boundaries we ensure they fall on writesize boundaries. Helped-by: Boris Brezillon Signed-off-by: Chris Packham Acked-by: Boris Brezillon Signed-off-by: Brian Norris --- drivers/mtd/mtdpart.c | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index ea5e5307f667..2e152e53ace0 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -393,8 +393,12 @@ static struct mtd_part *allocate_partition(struct mtd_info *master, const struct mtd_partition *part, int partno, uint64_t cur_offset) { + int wr_alignment = (master->flags & MTD_NO_ERASE) ? master->writesize: + master->erasesize; struct mtd_part *slave; + u32 remainder; char *name; + u64 tmp; /* allocate the partition structure */ slave = kzalloc(sizeof(*slave), GFP_KERNEL); @@ -499,10 +503,11 @@ static struct mtd_part *allocate_partition(struct mtd_info *master, if (slave->offset == MTDPART_OFS_APPEND) slave->offset = cur_offset; if (slave->offset == MTDPART_OFS_NXTBLK) { + tmp = cur_offset; slave->offset = cur_offset; - if (mtd_mod_by_eb(cur_offset, master) != 0) { - /* Round up to next erasesize */ - slave->offset = (mtd_div_by_eb(cur_offset, master) + 1) * master->erasesize; + remainder = do_div(tmp, wr_alignment); + if (remainder) { + slave->offset += wr_alignment - remainder; printk(KERN_NOTICE "Moving partition %d: " "0x%012llx -> 0x%012llx\n", partno, (unsigned long long)cur_offset, (unsigned long long)slave->offset); @@ -567,19 +572,22 @@ static struct mtd_part *allocate_partition(struct mtd_info *master, slave->mtd.erasesize = master->erasesize; } - if ((slave->mtd.flags & MTD_WRITEABLE) && - mtd_mod_by_eb(slave->offset, &slave->mtd)) { + tmp = slave->offset; + remainder = do_div(tmp, wr_alignment); + if ((slave->mtd.flags & MTD_WRITEABLE) && remainder) { /* Doesn't start on a boundary of major erase size */ /* FIXME: Let it be writable if it is on a boundary of * _minor_ erase size though */ slave->mtd.flags &= ~MTD_WRITEABLE; - printk(KERN_WARNING"mtd: partition \"%s\" doesn't start on an erase block boundary -- force read-only\n", + printk(KERN_WARNING"mtd: partition \"%s\" doesn't start on an erase/write block boundary -- force read-only\n", part->name); } - if ((slave->mtd.flags & MTD_WRITEABLE) && - mtd_mod_by_eb(slave->mtd.size, &slave->mtd)) { + + tmp = slave->mtd.size; + remainder = do_div(tmp, wr_alignment); + if ((slave->mtd.flags & MTD_WRITEABLE) && remainder) { slave->mtd.flags &= ~MTD_WRITEABLE; - printk(KERN_WARNING"mtd: partition \"%s\" doesn't end on an erase block -- force read-only\n", + printk(KERN_WARNING"mtd: partition \"%s\" doesn't end on an erase/write block -- force read-only\n", part->name); } -- cgit v1.2.3-59-g8ed1b From 9795e0e8ac0d6a3ee092f1b555b284b57feef99e Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 13 Jun 2017 15:54:58 +0200 Subject: udf: Fix races with i_size changes during readpage __udf_adinicb_readpage() uses i_size several times. When truncate changes i_size while the function is running, it can observe several different values and thus e.g. expose uninitialized parts of page to userspace. Also use i_size_read() in the function since it does not hold inode_lock. Since i_size is guaranteed to be small, this cannot really cause any issues even on 32-bit archs but let's be careful. CC: stable@vger.kernel.org Fixes: 9c2fc0de1a6e638fe58c354a463f544f42a90a09 Signed-off-by: Jan Kara --- fs/udf/file.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/fs/udf/file.c b/fs/udf/file.c index f5eb2d5b3bac..e06d2c15749a 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -43,10 +43,15 @@ static void __udf_adinicb_readpage(struct page *page) struct inode *inode = page->mapping->host; char *kaddr; struct udf_inode_info *iinfo = UDF_I(inode); + loff_t isize = i_size_read(inode); + /* + * We have to be careful here as truncate can change i_size under us. + * So just sample it once and use the same value everywhere. + */ kaddr = kmap_atomic(page); - memcpy(kaddr, iinfo->i_ext.i_data + iinfo->i_lenEAttr, inode->i_size); - memset(kaddr + inode->i_size, 0, PAGE_SIZE - inode->i_size); + memcpy(kaddr, iinfo->i_ext.i_data + iinfo->i_lenEAttr, isize); + memset(kaddr + isize, 0, PAGE_SIZE - isize); flush_dcache_page(page); SetPageUptodate(page); kunmap_atomic(kaddr); -- cgit v1.2.3-59-g8ed1b From 146c4ad6ec034a1fbfbf90ba76cb69b6504c374a Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 13 Jun 2017 16:08:52 +0200 Subject: udf: Use i_size_read() in udf_adinicb_writepage() We don't hold inode_lock in udf_adinicb_writepage() so use i_size_read() to get i_size. This cannot cause real problems is i_size is guaranteed to be small but let's be careful. Signed-off-by: Jan Kara --- fs/udf/file.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/udf/file.c b/fs/udf/file.c index e06d2c15749a..356c2bf148a5 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -76,7 +76,8 @@ static int udf_adinicb_writepage(struct page *page, BUG_ON(!PageLocked(page)); kaddr = kmap_atomic(page); - memcpy(iinfo->i_ext.i_data + iinfo->i_lenEAttr, kaddr, inode->i_size); + memcpy(iinfo->i_ext.i_data + iinfo->i_lenEAttr, kaddr, + i_size_read(inode)); SetPageUptodate(page); kunmap_atomic(kaddr); mark_inode_dirty(inode); -- cgit v1.2.3-59-g8ed1b From f2e95355891153f66d4156bf3a142c6489cd78c6 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 13 Jun 2017 16:20:25 +0200 Subject: udf: Fix deadlock between writeback and udf_setsize() udf_setsize() called truncate_setsize() with i_data_sem held. Thus truncate_pagecache() called from truncate_setsize() could lock a page under i_data_sem which can deadlock as page lock ranks below i_data_sem - e. g. writeback can hold page lock and try to acquire i_data_sem to map a block. Fix the problem by moving truncate_setsize() calls from under i_data_sem. It is safe for us to change i_size without holding i_data_sem as all the places that depend on i_size being stable already hold inode_lock. CC: stable@vger.kernel.org Fixes: 7e49b6f2480cb9a9e7322a91592e56a5c85361f5 Signed-off-by: Jan Kara --- fs/udf/inode.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 98c510e17203..18fdb9d90812 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1222,8 +1222,8 @@ int udf_setsize(struct inode *inode, loff_t newsize) return err; } set_size: - truncate_setsize(inode, newsize); up_write(&iinfo->i_data_sem); + truncate_setsize(inode, newsize); } else { if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { down_write(&iinfo->i_data_sem); @@ -1240,9 +1240,9 @@ set_size: udf_get_block); if (err) return err; + truncate_setsize(inode, newsize); down_write(&iinfo->i_data_sem); udf_clear_extent_cache(inode); - truncate_setsize(inode, newsize); udf_truncate_extents(inode); up_write(&iinfo->i_data_sem); } -- cgit v1.2.3-59-g8ed1b From 3c399fa40fd13c5749386695e71f5f747a634f21 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 14 Jun 2017 09:51:20 +0200 Subject: udf: Use time64_to_tm for timestamp conversion UDF on-disk time stamp is stored in a form very similar to struct tm. Use time64_to_tm() for conversion of seconds since epoch to year, month, ... format and then just copy this as necessary to UDF on-disk structure to simplify the code. Signed-off-by: Jan Kara --- fs/udf/udftime.c | 45 +++++++++++---------------------------------- 1 file changed, 11 insertions(+), 34 deletions(-) diff --git a/fs/udf/udftime.c b/fs/udf/udftime.c index 77c331f1a770..b9dadc7e5c35 100644 --- a/fs/udf/udftime.c +++ b/fs/udf/udftime.c @@ -38,6 +38,7 @@ #include #include +#include #define EPOCH_YEAR 1970 @@ -81,9 +82,6 @@ static time_t year_seconds[MAX_YEAR_SECONDS] = { /*2038*/ SPY(68, 17, 0) }; -#define SECS_PER_HOUR (60 * 60) -#define SECS_PER_DAY (SECS_PER_HOUR * 24) - struct timespec * udf_disk_stamp_to_time(struct timespec *dest, struct timestamp src) { @@ -119,9 +117,9 @@ udf_disk_stamp_to_time(struct timespec *dest, struct timestamp src) struct timestamp * udf_time_to_disk_stamp(struct timestamp *dest, struct timespec ts) { - long int days, rem, y; - const unsigned short int *ip; + long seconds; int16_t offset; + struct tm tm; offset = -sys_tz.tz_minuteswest; @@ -130,35 +128,14 @@ udf_time_to_disk_stamp(struct timestamp *dest, struct timespec ts) dest->typeAndTimezone = cpu_to_le16(0x1000 | (offset & 0x0FFF)); - ts.tv_sec += offset * 60; - days = ts.tv_sec / SECS_PER_DAY; - rem = ts.tv_sec % SECS_PER_DAY; - dest->hour = rem / SECS_PER_HOUR; - rem %= SECS_PER_HOUR; - dest->minute = rem / 60; - dest->second = rem % 60; - y = 1970; - -#define DIV(a, b) ((a) / (b) - ((a) % (b) < 0)) -#define LEAPS_THRU_END_OF(y) (DIV (y, 4) - DIV (y, 100) + DIV (y, 400)) - - while (days < 0 || days >= (__isleap(y) ? 366 : 365)) { - long int yg = y + days / 365 - (days % 365 < 0); - - /* Adjust DAYS and Y to match the guessed year. */ - days -= ((yg - y) * 365 - + LEAPS_THRU_END_OF(yg - 1) - - LEAPS_THRU_END_OF(y - 1)); - y = yg; - } - dest->year = cpu_to_le16(y); - ip = __mon_yday[__isleap(y)]; - for (y = 11; days < (long int)ip[y]; --y) - continue; - days -= ip[y]; - dest->month = y + 1; - dest->day = days + 1; - + seconds = ts.tv_sec + offset * 60; + time64_to_tm(seconds, 0, &tm); + dest->year = cpu_to_le16(tm.tm_year + 1900); + dest->month = tm.tm_mon + 1; + dest->day = tm.tm_mday; + dest->hour = tm.tm_hour; + dest->minute = tm.tm_min; + dest->second = tm.tm_sec; dest->centiseconds = ts.tv_nsec / 10000000; dest->hundredsOfMicroseconds = (ts.tv_nsec / 1000 - dest->centiseconds * 10000) / 100; -- cgit v1.2.3-59-g8ed1b From fd3cfad374d452ebe0a2f87f37c2ceeea7e0d134 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 14 Jun 2017 10:42:48 +0200 Subject: udf: Convert udf_disk_stamp_to_time() to use mktime64() Convert udf_disk_stamp_to_time() to use mktime64() to simplify the code. As a bonus we get working timestamp conversion for dates before epoch and after 2038 (both of which are allowed by UDF standard). Signed-off-by: Jan Kara --- fs/udf/udftime.c | 53 ++--------------------------------------------------- 1 file changed, 2 insertions(+), 51 deletions(-) diff --git a/fs/udf/udftime.c b/fs/udf/udftime.c index b9dadc7e5c35..14626b34d13e 100644 --- a/fs/udf/udftime.c +++ b/fs/udf/udftime.c @@ -40,52 +40,9 @@ #include #include -#define EPOCH_YEAR 1970 - -#ifndef __isleap -/* Nonzero if YEAR is a leap year (every 4 years, - except every 100th isn't, and every 400th is). */ -#define __isleap(year) \ - ((year) % 4 == 0 && ((year) % 100 != 0 || (year) % 400 == 0)) -#endif - -/* How many days come before each month (0-12). */ -static const unsigned short int __mon_yday[2][13] = { - /* Normal years. */ - {0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365}, - /* Leap years. */ - {0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366} -}; - -#define MAX_YEAR_SECONDS 69 -#define SPD 0x15180 /*3600*24 */ -#define SPY(y, l, s) (SPD * (365 * y + l) + s) - -static time_t year_seconds[MAX_YEAR_SECONDS] = { -/*1970*/ SPY(0, 0, 0), SPY(1, 0, 0), SPY(2, 0, 0), SPY(3, 1, 0), -/*1974*/ SPY(4, 1, 0), SPY(5, 1, 0), SPY(6, 1, 0), SPY(7, 2, 0), -/*1978*/ SPY(8, 2, 0), SPY(9, 2, 0), SPY(10, 2, 0), SPY(11, 3, 0), -/*1982*/ SPY(12, 3, 0), SPY(13, 3, 0), SPY(14, 3, 0), SPY(15, 4, 0), -/*1986*/ SPY(16, 4, 0), SPY(17, 4, 0), SPY(18, 4, 0), SPY(19, 5, 0), -/*1990*/ SPY(20, 5, 0), SPY(21, 5, 0), SPY(22, 5, 0), SPY(23, 6, 0), -/*1994*/ SPY(24, 6, 0), SPY(25, 6, 0), SPY(26, 6, 0), SPY(27, 7, 0), -/*1998*/ SPY(28, 7, 0), SPY(29, 7, 0), SPY(30, 7, 0), SPY(31, 8, 0), -/*2002*/ SPY(32, 8, 0), SPY(33, 8, 0), SPY(34, 8, 0), SPY(35, 9, 0), -/*2006*/ SPY(36, 9, 0), SPY(37, 9, 0), SPY(38, 9, 0), SPY(39, 10, 0), -/*2010*/ SPY(40, 10, 0), SPY(41, 10, 0), SPY(42, 10, 0), SPY(43, 11, 0), -/*2014*/ SPY(44, 11, 0), SPY(45, 11, 0), SPY(46, 11, 0), SPY(47, 12, 0), -/*2018*/ SPY(48, 12, 0), SPY(49, 12, 0), SPY(50, 12, 0), SPY(51, 13, 0), -/*2022*/ SPY(52, 13, 0), SPY(53, 13, 0), SPY(54, 13, 0), SPY(55, 14, 0), -/*2026*/ SPY(56, 14, 0), SPY(57, 14, 0), SPY(58, 14, 0), SPY(59, 15, 0), -/*2030*/ SPY(60, 15, 0), SPY(61, 15, 0), SPY(62, 15, 0), SPY(63, 16, 0), -/*2034*/ SPY(64, 16, 0), SPY(65, 16, 0), SPY(66, 16, 0), SPY(67, 17, 0), -/*2038*/ SPY(68, 17, 0) -}; - struct timespec * udf_disk_stamp_to_time(struct timespec *dest, struct timestamp src) { - int yday; u16 typeAndTimezone = le16_to_cpu(src.typeAndTimezone); u16 year = le16_to_cpu(src.year); uint8_t type = typeAndTimezone >> 12; @@ -100,15 +57,9 @@ udf_disk_stamp_to_time(struct timespec *dest, struct timestamp src) } else offset = 0; - if ((year < EPOCH_YEAR) || - (year >= EPOCH_YEAR + MAX_YEAR_SECONDS)) { - return NULL; - } - dest->tv_sec = year_seconds[year - EPOCH_YEAR]; + dest->tv_sec = mktime64(year, src.month, src.day, src.hour, src.minute, + src.second); dest->tv_sec -= offset * 60; - - yday = ((__mon_yday[__isleap(year)][src.month - 1]) + src.day - 1); - dest->tv_sec += (((yday * 24) + src.hour) * 60 + src.minute) * 60 + src.second; dest->tv_nsec = 1000 * (src.centiseconds * 10000 + src.hundredsOfMicroseconds * 100 + src.microseconds); return dest; -- cgit v1.2.3-59-g8ed1b From 08cfe9f08109ad7ebe2248d483c683adbb1c9448 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 14 Jun 2017 17:40:55 +0200 Subject: mdacon: align code in mda_detect properly This is just a whitespace cleanup. The code was a mess having multiple commands on one line like: scr_writew(0xAA55, p); if (scr_readw(p) == 0xAA55) count++; Indent that properly and make it nicer for reading. Signed-off-by: Jiri Slaby Cc: Tomi Valkeinen Signed-off-by: Bartlomiej Zolnierkiewicz --- drivers/video/console/mdacon.c | 60 ++++++++++++++++++++++++------------------ 1 file changed, 35 insertions(+), 25 deletions(-) diff --git a/drivers/video/console/mdacon.c b/drivers/video/console/mdacon.c index ec192a1bf297..424af6bdb408 100644 --- a/drivers/video/console/mdacon.c +++ b/drivers/video/console/mdacon.c @@ -208,10 +208,17 @@ static int mda_detect(void) p = (u16 *) mda_vram_base; q = (u16 *) (mda_vram_base + 0x01000); - p_save = scr_readw(p); q_save = scr_readw(q); + p_save = scr_readw(p); + q_save = scr_readw(q); + + scr_writew(0xAA55, p); + if (scr_readw(p) == 0xAA55) + count++; + + scr_writew(0x55AA, p); + if (scr_readw(p) == 0x55AA) + count++; - scr_writew(0xAA55, p); if (scr_readw(p) == 0xAA55) count++; - scr_writew(0x55AA, p); if (scr_readw(p) == 0x55AA) count++; scr_writew(p_save, p); if (count != 2) { @@ -220,13 +227,18 @@ static int mda_detect(void) /* check if we have 4K or 8K */ - scr_writew(0xA55A, q); scr_writew(0x0000, p); - if (scr_readw(q) == 0xA55A) count++; + scr_writew(0xA55A, q); + scr_writew(0x0000, p); + if (scr_readw(q) == 0xA55A) + count++; - scr_writew(0x5AA5, q); scr_writew(0x0000, p); - if (scr_readw(q) == 0x5AA5) count++; + scr_writew(0x5AA5, q); + scr_writew(0x0000, p); + if (scr_readw(q) == 0x5AA5) + count++; - scr_writew(p_save, p); scr_writew(q_save, q); + scr_writew(p_save, p); + scr_writew(q_save, q); if (count == 4) { mda_vram_len = 0x02000; @@ -240,14 +252,12 @@ static int mda_detect(void) /* Edward: These two mess `tests' mess up my cursor on bootup */ /* cursor low register */ - if (! test_mda_b(0x66, 0x0f)) { + if (!test_mda_b(0x66, 0x0f)) return 0; - } /* cursor low register */ - if (! test_mda_b(0x99, 0x0f)) { + if (!test_mda_b(0x99, 0x0f)) return 0; - } #endif /* See if the card is a Hercules, by checking whether the vsync @@ -257,25 +267,25 @@ static int mda_detect(void) p_save = q_save = inb_p(mda_status_port) & MDA_STATUS_VSYNC; - for (count=0; count < 50000 && p_save == q_save; count++) { + for (count = 0; count < 50000 && p_save == q_save; count++) { q_save = inb(mda_status_port) & MDA_STATUS_VSYNC; udelay(2); } if (p_save != q_save) { switch (inb_p(mda_status_port) & 0x70) { - case 0x10: - mda_type = TYPE_HERCPLUS; - mda_type_name = "HerculesPlus"; - break; - case 0x50: - mda_type = TYPE_HERCCOLOR; - mda_type_name = "HerculesColor"; - break; - default: - mda_type = TYPE_HERC; - mda_type_name = "Hercules"; - break; + case 0x10: + mda_type = TYPE_HERCPLUS; + mda_type_name = "HerculesPlus"; + break; + case 0x50: + mda_type = TYPE_HERCCOLOR; + mda_type_name = "HerculesColor"; + break; + default: + mda_type = TYPE_HERC; + mda_type_name = "Hercules"; + break; } } -- cgit v1.2.3-59-g8ed1b From 734f13b11d6fcc4947e75f0e11baf29cb3e161eb Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 14 Jun 2017 17:40:56 +0200 Subject: mdacon: make mda_vram_base u16 * Given every user of mda_vram_base expects a pointer, let mda_vram_base be a pointer to u16. The offset calculation in mda_detect had to be adjusted by / 2 (due to different pointer arithmetic now). We introduce a cast to a value returned from VGA_MAP_MEM. But I will change VGA_MAP_MEM to return a pointer later too. But vgacon needs a similar change first. Signed-off-by: Jiri Slaby Cc: Tomi Valkeinen Signed-off-by: Bartlomiej Zolnierkiewicz --- drivers/video/console/mdacon.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/video/console/mdacon.c b/drivers/video/console/mdacon.c index 424af6bdb408..3ec2b178bb88 100644 --- a/drivers/video/console/mdacon.c +++ b/drivers/video/console/mdacon.c @@ -48,7 +48,7 @@ static DEFINE_SPINLOCK(mda_lock); /* description of the hardware layout */ -static unsigned long mda_vram_base; /* Base of video memory */ +static u16 *mda_vram_base; /* Base of video memory */ static unsigned long mda_vram_len; /* Size of video memory */ static unsigned int mda_num_columns; /* Number of text columns */ static unsigned int mda_num_lines; /* Number of text lines */ @@ -205,8 +205,8 @@ static int mda_detect(void) /* do a memory check */ - p = (u16 *) mda_vram_base; - q = (u16 *) (mda_vram_base + 0x01000); + p = mda_vram_base; + q = mda_vram_base + 0x01000 / 2; p_save = scr_readw(p); q_save = scr_readw(q); @@ -323,7 +323,7 @@ static const char *mdacon_startup(void) mda_num_lines = 25; mda_vram_len = 0x01000; - mda_vram_base = VGA_MAP_MEM(0xb0000, mda_vram_len); + mda_vram_base = (u16 *)VGA_MAP_MEM(0xb0000, mda_vram_len); mda_index_port = 0x3b4; mda_value_port = 0x3b5; @@ -420,7 +420,7 @@ static void mdacon_invert_region(struct vc_data *c, u16 *p, int count) } } -#define MDA_ADDR(x,y) ((u16 *) mda_vram_base + (y)*mda_num_columns + (x)) +#define MDA_ADDR(x, y) (mda_vram_base + (y)*mda_num_columns + (x)) static void mdacon_putc(struct vc_data *c, int ch, int y, int x) { @@ -463,7 +463,7 @@ static int mdacon_blank(struct vc_data *c, int blank, int mode_switch) { if (mda_type == TYPE_MDA) { if (blank) - scr_memsetw((void *)mda_vram_base, + scr_memsetw(mda_vram_base, mda_convert_attr(c->vc_video_erase_char), c->vc_screenbuf_size); /* Tell console.c that it has to restore the screen itself */ -- cgit v1.2.3-59-g8ed1b From 927f7a17eb2ecc9b5a3b31a297f08f221b1f531c Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 14 Jun 2017 17:40:56 +0200 Subject: mdacon: replace MDA_ADDR macro by inline function MDA_ADDR is one of those macros which could be an inline function. So convert MDA_ADDR to mda_addr. Note that we take x and y as unsigned now. But they are absolute coordinates, so this is no problem. Signed-off-by: Jiri Slaby Cc: Tomi Valkeinen Signed-off-by: Bartlomiej Zolnierkiewicz --- drivers/video/console/mdacon.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/drivers/video/console/mdacon.c b/drivers/video/console/mdacon.c index 3ec2b178bb88..d0d427a2f1a3 100644 --- a/drivers/video/console/mdacon.c +++ b/drivers/video/console/mdacon.c @@ -420,17 +420,20 @@ static void mdacon_invert_region(struct vc_data *c, u16 *p, int count) } } -#define MDA_ADDR(x, y) (mda_vram_base + (y)*mda_num_columns + (x)) +static inline u16 *mda_addr(unsigned int x, unsigned int y) +{ + return mda_vram_base + y * mda_num_columns + x; +} static void mdacon_putc(struct vc_data *c, int ch, int y, int x) { - scr_writew(mda_convert_attr(ch), MDA_ADDR(x, y)); + scr_writew(mda_convert_attr(ch), mda_addr(x, y)); } static void mdacon_putcs(struct vc_data *c, const unsigned short *s, int count, int y, int x) { - u16 *dest = MDA_ADDR(x, y); + u16 *dest = mda_addr(x, y); for (; count > 0; count--) { scr_writew(mda_convert_attr(scr_readw(s++)), dest++); @@ -440,7 +443,7 @@ static void mdacon_putcs(struct vc_data *c, const unsigned short *s, static void mdacon_clear(struct vc_data *c, int y, int x, int height, int width) { - u16 *dest = MDA_ADDR(x, y); + u16 *dest = mda_addr(x, y); u16 eattr = mda_convert_attr(c->vc_video_erase_char); if (width <= 0 || height <= 0) @@ -512,16 +515,16 @@ static bool mdacon_scroll(struct vc_data *c, unsigned int t, unsigned int b, switch (dir) { case SM_UP: - scr_memmovew(MDA_ADDR(0,t), MDA_ADDR(0,t+lines), + scr_memmovew(mda_addr(0, t), mda_addr(0, t + lines), (b-t-lines)*mda_num_columns*2); - scr_memsetw(MDA_ADDR(0,b-lines), eattr, + scr_memsetw(mda_addr(0, b - lines), eattr, lines*mda_num_columns*2); break; case SM_DOWN: - scr_memmovew(MDA_ADDR(0,t+lines), MDA_ADDR(0,t), + scr_memmovew(mda_addr(0, t + lines), mda_addr(0, t), (b-t-lines)*mda_num_columns*2); - scr_memsetw(MDA_ADDR(0,t), eattr, lines*mda_num_columns*2); + scr_memsetw(mda_addr(0, t), eattr, lines*mda_num_columns*2); break; } -- cgit v1.2.3-59-g8ed1b From ac5b52d2a2980fe34474e23037b02485c61538a3 Mon Sep 17 00:00:00 2001 From: Karim Eshapa Date: Wed, 14 Jun 2017 17:40:56 +0200 Subject: video: fbdev: omap2: omapfb: displays: panel-dsi-cm: Use time comparison kernel macro. Use time_before_eq() kernel macro for time comparison. Signed-off-by: Karim Eshapa Cc: tomi.valkeinen@ti.com Cc: peter.ujfalusi@ti.com Cc: tj@kernel.org Cc: mingo@kernel.org [b.zolnierkie: patch description fixup] Signed-off-by: Bartlomiej Zolnierkiewicz --- drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c index fd2b372d0264..7f20bc267234 100644 --- a/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c +++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c @@ -100,7 +100,7 @@ static void hw_guard_wait(struct panel_drv_data *ddata) { unsigned long wait = ddata->hw_guard_end - jiffies; - if ((long)wait > 0 && wait <= ddata->hw_guard_wait) { + if ((long)wait > 0 && time_before_eq(wait, ddata->hw_guard_wait)) { set_current_state(TASK_UNINTERRUPTIBLE); schedule_timeout(wait); } -- cgit v1.2.3-59-g8ed1b From 86388d835e7f98a227e83530fa9b4953193df43a Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Wed, 14 Jun 2017 17:40:56 +0200 Subject: video: fbdev: pxafb: Handle return value of clk_prepare_enable clk_prepare_enable() can fail here and we must check its return value. Signed-off-by: Arvind Yadav Signed-off-by: Bartlomiej Zolnierkiewicz --- drivers/video/fbdev/pxafb.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/video/fbdev/pxafb.c b/drivers/video/fbdev/pxafb.c index b21a89b03fb4..c3d49e13643c 100644 --- a/drivers/video/fbdev/pxafb.c +++ b/drivers/video/fbdev/pxafb.c @@ -1436,7 +1436,10 @@ static void pxafb_enable_controller(struct pxafb_info *fbi) pr_debug("reg_lccr3 0x%08x\n", (unsigned int) fbi->reg_lccr3); /* enable LCD controller clock */ - clk_prepare_enable(fbi->clk); + if (clk_prepare_enable(fbi->clk)) { + pr_err("%s: Failed to prepare clock\n", __func__); + return; + } if (fbi->lccr0 & LCCR0_LCDT) return; -- cgit v1.2.3-59-g8ed1b From b543849350d90849719e63ded1b71bc0ee6d9d73 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 14 Jun 2017 17:40:57 +0200 Subject: omapfb: Use sysfs_match_string() helper Use sysfs_match_string() helper instead of open coded variant. Signed-off-by: Andy Shevchenko Cc: Tomi Valkeinen Signed-off-by: Bartlomiej Zolnierkiewicz --- drivers/video/fbdev/omap2/omapfb/dss/manager-sysfs.c | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) diff --git a/drivers/video/fbdev/omap2/omapfb/dss/manager-sysfs.c b/drivers/video/fbdev/omap2/omapfb/dss/manager-sysfs.c index 9e2a67fdf4d2..44b96af4ef4e 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/manager-sysfs.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/manager-sysfs.c @@ -182,22 +182,16 @@ static ssize_t manager_trans_key_type_show(struct omap_overlay_manager *mgr, static ssize_t manager_trans_key_type_store(struct omap_overlay_manager *mgr, const char *buf, size_t size) { - enum omap_dss_trans_key_type key_type; struct omap_overlay_manager_info info; int r; - for (key_type = OMAP_DSS_COLOR_KEY_GFX_DST; - key_type < ARRAY_SIZE(trans_key_type_str); key_type++) { - if (sysfs_streq(buf, trans_key_type_str[key_type])) - break; - } - - if (key_type == ARRAY_SIZE(trans_key_type_str)) - return -EINVAL; + r = sysfs_match_string(trans_key_type_str, buf); + if (r < 0) + return r; mgr->get_manager_info(mgr, &info); - info.trans_key_type = key_type; + info.trans_key_type = r; r = mgr->set_manager_info(mgr, &info); if (r) -- cgit v1.2.3-59-g8ed1b From 0e25884bbe246d68f1a928a3d5a682ab01a58c83 Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Wed, 14 Jun 2017 17:40:57 +0200 Subject: video: fbdev: sh_mobile_lcdcfb: constify sh_mobile_lcdc_bl_ops. File size before: text data bss dec hex filename 17525 952 0 18477 482d drivers/video/fbdev/sh_mobile_lcdcfb.o File size After adding 'const': text data bss dec hex filename 17557 920 0 18477 482d drivers/video/fbdev/sh_mobile_lcdcfb.o Signed-off-by: Arvind Yadav Cc: geert+renesas@glider.be Cc: keescook@chromium.org Signed-off-by: Bartlomiej Zolnierkiewicz --- drivers/video/fbdev/sh_mobile_lcdcfb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/video/fbdev/sh_mobile_lcdcfb.c b/drivers/video/fbdev/sh_mobile_lcdcfb.c index 885ee3a563aa..c3a46506e47e 100644 --- a/drivers/video/fbdev/sh_mobile_lcdcfb.c +++ b/drivers/video/fbdev/sh_mobile_lcdcfb.c @@ -2301,7 +2301,7 @@ static int sh_mobile_lcdc_check_fb(struct backlight_device *bdev, return (info->bl_dev == bdev); } -static struct backlight_ops sh_mobile_lcdc_bl_ops = { +static const struct backlight_ops sh_mobile_lcdc_bl_ops = { .options = BL_CORE_SUSPENDRESUME, .update_status = sh_mobile_lcdc_update_bl, .get_brightness = sh_mobile_lcdc_get_brightness, -- cgit v1.2.3-59-g8ed1b From a8feae09110675e77022b6f04ac6d308e842d75d Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 14 Jun 2017 17:40:57 +0200 Subject: uvesafb: Fix continuation printks without KERN_LEVEL to pr_cont, neatening Linus recently broke the printk without KERN_CONT behavior. Fix it for uvesafb. While there, convert printk(KERN_ to pr_. Add pr_fmt and remove the embedded prefixes. Miscellanea: o Coalesce formats and realign arguments o Add a missing space to a format when coalescing. Signed-off-by: Joe Perches Cc: Michal Januszewski Signed-off-by: Bartlomiej Zolnierkiewicz --- drivers/video/fbdev/uvesafb.c | 148 ++++++++++++++++++------------------------ 1 file changed, 62 insertions(+), 86 deletions(-) diff --git a/drivers/video/fbdev/uvesafb.c b/drivers/video/fbdev/uvesafb.c index 98af9e02959b..dc0e8d90d9cc 100644 --- a/drivers/video/fbdev/uvesafb.c +++ b/drivers/video/fbdev/uvesafb.c @@ -5,6 +5,9 @@ * Loosely based upon the vesafb driver. * */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include #include #include @@ -149,8 +152,8 @@ static int uvesafb_exec(struct uvesafb_ktask *task) * allowed by connector. */ if (sizeof(*m) + len > CONNECTOR_MAX_MSG_SIZE) { - printk(KERN_WARNING "uvesafb: message too long (%d), " - "can't execute task\n", (int)(sizeof(*m) + len)); + pr_warn("message too long (%d), can't execute task\n", + (int)(sizeof(*m) + len)); return -E2BIG; } @@ -198,10 +201,8 @@ static int uvesafb_exec(struct uvesafb_ktask *task) */ err = uvesafb_helper_start(); if (err) { - printk(KERN_ERR "uvesafb: failed to execute %s\n", - v86d_path); - printk(KERN_ERR "uvesafb: make sure that the v86d " - "helper is installed and executable\n"); + pr_err("failed to execute %s\n", v86d_path); + pr_err("make sure that the v86d helper is installed and executable\n"); } else { v86d_started = 1; err = cn_netlink_send(m, 0, 0, gfp_any()); @@ -375,9 +376,8 @@ static u8 *uvesafb_vbe_state_save(struct uvesafb_par *par) err = uvesafb_exec(task); if (err || (task->t.regs.eax & 0xffff) != 0x004f) { - printk(KERN_WARNING "uvesafb: VBE get state call " - "failed (eax=0x%x, err=%d)\n", - task->t.regs.eax, err); + pr_warn("VBE get state call failed (eax=0x%x, err=%d)\n", + task->t.regs.eax, err); kfree(state); state = NULL; } @@ -407,9 +407,8 @@ static void uvesafb_vbe_state_restore(struct uvesafb_par *par, u8 *state_buf) err = uvesafb_exec(task); if (err || (task->t.regs.eax & 0xffff) != 0x004f) - printk(KERN_WARNING "uvesafb: VBE state restore call " - "failed (eax=0x%x, err=%d)\n", - task->t.regs.eax, err); + pr_warn("VBE state restore call failed (eax=0x%x, err=%d)\n", + task->t.regs.eax, err); uvesafb_free(task); } @@ -427,24 +426,22 @@ static int uvesafb_vbe_getinfo(struct uvesafb_ktask *task, err = uvesafb_exec(task); if (err || (task->t.regs.eax & 0xffff) != 0x004f) { - printk(KERN_ERR "uvesafb: Getting VBE info block failed " - "(eax=0x%x, err=%d)\n", (u32)task->t.regs.eax, - err); + pr_err("Getting VBE info block failed (eax=0x%x, err=%d)\n", + (u32)task->t.regs.eax, err); return -EINVAL; } if (par->vbe_ib.vbe_version < 0x0200) { - printk(KERN_ERR "uvesafb: Sorry, pre-VBE 2.0 cards are " - "not supported.\n"); + pr_err("Sorry, pre-VBE 2.0 cards are not supported\n"); return -EINVAL; } if (!par->vbe_ib.mode_list_ptr) { - printk(KERN_ERR "uvesafb: Missing mode list!\n"); + pr_err("Missing mode list!\n"); return -EINVAL; } - printk(KERN_INFO "uvesafb: "); + pr_info(""); /* * Convert string pointers and the mode list pointer into @@ -452,23 +449,24 @@ static int uvesafb_vbe_getinfo(struct uvesafb_ktask *task, * video adapter and its vendor. */ if (par->vbe_ib.oem_vendor_name_ptr) - printk("%s, ", + pr_cont("%s, ", ((char *)task->buf) + par->vbe_ib.oem_vendor_name_ptr); if (par->vbe_ib.oem_product_name_ptr) - printk("%s, ", + pr_cont("%s, ", ((char *)task->buf) + par->vbe_ib.oem_product_name_ptr); if (par->vbe_ib.oem_product_rev_ptr) - printk("%s, ", + pr_cont("%s, ", ((char *)task->buf) + par->vbe_ib.oem_product_rev_ptr); if (par->vbe_ib.oem_string_ptr) - printk("OEM: %s, ", + pr_cont("OEM: %s, ", ((char *)task->buf) + par->vbe_ib.oem_string_ptr); - printk("VBE v%d.%d\n", ((par->vbe_ib.vbe_version & 0xff00) >> 8), - par->vbe_ib.vbe_version & 0xff); + pr_cont("VBE v%d.%d\n", + (par->vbe_ib.vbe_version & 0xff00) >> 8, + par->vbe_ib.vbe_version & 0xff); return 0; } @@ -507,8 +505,7 @@ static int uvesafb_vbe_getmodes(struct uvesafb_ktask *task, err = uvesafb_exec(task); if (err || (task->t.regs.eax & 0xffff) != 0x004f) { - printk(KERN_WARNING "uvesafb: Getting mode info block " - "for mode 0x%x failed (eax=0x%x, err=%d)\n", + pr_warn("Getting mode info block for mode 0x%x failed (eax=0x%x, err=%d)\n", *mode, (u32)task->t.regs.eax, err); mode++; par->vbe_modes_cnt--; @@ -569,23 +566,20 @@ static int uvesafb_vbe_getpmi(struct uvesafb_ktask *task, + task->t.regs.edi); par->pmi_start = (u8 *)par->pmi_base + par->pmi_base[1]; par->pmi_pal = (u8 *)par->pmi_base + par->pmi_base[2]; - printk(KERN_INFO "uvesafb: protected mode interface info at " - "%04x:%04x\n", - (u16)task->t.regs.es, (u16)task->t.regs.edi); - printk(KERN_INFO "uvesafb: pmi: set display start = %p, " - "set palette = %p\n", par->pmi_start, - par->pmi_pal); + pr_info("protected mode interface info at %04x:%04x\n", + (u16)task->t.regs.es, (u16)task->t.regs.edi); + pr_info("pmi: set display start = %p, set palette = %p\n", + par->pmi_start, par->pmi_pal); if (par->pmi_base[3]) { - printk(KERN_INFO "uvesafb: pmi: ports = "); + pr_info("pmi: ports ="); for (i = par->pmi_base[3]/2; par->pmi_base[i] != 0xffff; i++) - printk("%x ", par->pmi_base[i]); - printk("\n"); + pr_cont(" %x", par->pmi_base[i]); + pr_cont("\n"); if (par->pmi_base[i] != 0xffff) { - printk(KERN_INFO "uvesafb: can't handle memory" - " requests, pmi disabled\n"); + pr_info("can't handle memory requests, pmi disabled\n"); par->ypan = par->pmi_setpal = 0; } } @@ -634,17 +628,13 @@ static int uvesafb_vbe_getedid(struct uvesafb_ktask *task, struct fb_info *info) return -EINVAL; if ((task->t.regs.ebx & 0x3) == 3) { - printk(KERN_INFO "uvesafb: VBIOS/hardware supports both " - "DDC1 and DDC2 transfers\n"); + pr_info("VBIOS/hardware supports both DDC1 and DDC2 transfers\n"); } else if ((task->t.regs.ebx & 0x3) == 2) { - printk(KERN_INFO "uvesafb: VBIOS/hardware supports DDC2 " - "transfers\n"); + pr_info("VBIOS/hardware supports DDC2 transfers\n"); } else if ((task->t.regs.ebx & 0x3) == 1) { - printk(KERN_INFO "uvesafb: VBIOS/hardware supports DDC1 " - "transfers\n"); + pr_info("VBIOS/hardware supports DDC1 transfers\n"); } else { - printk(KERN_INFO "uvesafb: VBIOS/hardware doesn't support " - "DDC transfers\n"); + pr_info("VBIOS/hardware doesn't support DDC transfers\n"); return -EINVAL; } @@ -718,14 +708,12 @@ static void uvesafb_vbe_getmonspecs(struct uvesafb_ktask *task, } if (info->monspecs.gtf) - printk(KERN_INFO - "uvesafb: monitor limits: vf = %d Hz, hf = %d kHz, " - "clk = %d MHz\n", info->monspecs.vfmax, + pr_info("monitor limits: vf = %d Hz, hf = %d kHz, clk = %d MHz\n", + info->monspecs.vfmax, (int)(info->monspecs.hfmax / 1000), (int)(info->monspecs.dclkmax / 1000000)); else - printk(KERN_INFO "uvesafb: no monitor limits have been set, " - "default refresh rate will be used\n"); + pr_info("no monitor limits have been set, default refresh rate will be used\n"); /* Add VBE modes to the modelist. */ for (i = 0; i < par->vbe_modes_cnt; i++) { @@ -779,8 +767,7 @@ static void uvesafb_vbe_getstatesize(struct uvesafb_ktask *task, err = uvesafb_exec(task); if (err || (task->t.regs.eax & 0xffff) != 0x004f) { - printk(KERN_WARNING "uvesafb: VBE state buffer size " - "cannot be determined (eax=0x%x, err=%d)\n", + pr_warn("VBE state buffer size cannot be determined (eax=0x%x, err=%d)\n", task->t.regs.eax, err); par->vbe_state_size = 0; return; @@ -815,8 +802,7 @@ static int uvesafb_vbe_init(struct fb_info *info) if (par->pmi_setpal || par->ypan) { if (__supported_pte_mask & _PAGE_NX) { par->pmi_setpal = par->ypan = 0; - printk(KERN_WARNING "uvesafb: NX protection is active, " - "better not use the PMI.\n"); + pr_warn("NX protection is active, better not use the PMI\n"); } else { uvesafb_vbe_getpmi(task, par); } @@ -859,8 +845,7 @@ static int uvesafb_vbe_init_mode(struct fb_info *info) goto gotmode; } } - printk(KERN_INFO "uvesafb: requested VBE mode 0x%x is " - "unavailable\n", vbemode); + pr_info("requested VBE mode 0x%x is unavailable\n", vbemode); vbemode = 0; } @@ -1181,8 +1166,8 @@ static int uvesafb_open(struct fb_info *info, int user) if (!cnt && par->vbe_state_size) { buf = uvesafb_vbe_state_save(par); if (IS_ERR(buf)) { - printk(KERN_WARNING "uvesafb: save hardware state" - "failed, error code is %ld!\n", PTR_ERR(buf)); + pr_warn("save hardware state failed, error code is %ld!\n", + PTR_ERR(buf)); } else { par->vbe_state_orig = buf; } @@ -1293,17 +1278,16 @@ setmode: * use our own timings. Try again with the default timings. */ if (crtc != NULL) { - printk(KERN_WARNING "uvesafb: mode switch failed " - "(eax=0x%x, err=%d). Trying again with " - "default timings.\n", task->t.regs.eax, err); + pr_warn("mode switch failed (eax=0x%x, err=%d) - trying again with default timings\n", + task->t.regs.eax, err); uvesafb_reset(task); kfree(crtc); crtc = NULL; info->var.pixclock = 0; goto setmode; } else { - printk(KERN_ERR "uvesafb: mode switch failed (eax=" - "0x%x, err=%d)\n", task->t.regs.eax, err); + pr_err("mode switch failed (eax=0x%x, err=%d)\n", + task->t.regs.eax, err); err = -EINVAL; goto out; } @@ -1510,13 +1494,11 @@ static void uvesafb_init_info(struct fb_info *info, struct vbe_mode_ib *mode) mode->bytes_per_scan_line; if (par->ypan && info->var.yres_virtual > info->var.yres) { - printk(KERN_INFO "uvesafb: scrolling: %s " - "using protected mode interface, " - "yres_virtual=%d\n", + pr_info("scrolling: %s using protected mode interface, yres_virtual=%d\n", (par->ypan > 1) ? "ywrap" : "ypan", info->var.yres_virtual); } else { - printk(KERN_INFO "uvesafb: scrolling: redraw\n"); + pr_info("scrolling: redraw\n"); info->var.yres_virtual = info->var.yres; par->ypan = 0; } @@ -1704,7 +1686,7 @@ static int uvesafb_probe(struct platform_device *dev) err = uvesafb_vbe_init(info); if (err) { - printk(KERN_ERR "uvesafb: vbe_init() failed with %d\n", err); + pr_err("vbe_init() failed with %d\n", err); goto out; } @@ -1726,15 +1708,15 @@ static int uvesafb_probe(struct platform_device *dev) uvesafb_init_info(info, mode); if (!request_region(0x3c0, 32, "uvesafb")) { - printk(KERN_ERR "uvesafb: request region 0x3c0-0x3e0 failed\n"); + pr_err("request region 0x3c0-0x3e0 failed\n"); err = -EIO; goto out_mode; } if (!request_mem_region(info->fix.smem_start, info->fix.smem_len, "uvesafb")) { - printk(KERN_ERR "uvesafb: cannot reserve video memory at " - "0x%lx\n", info->fix.smem_start); + pr_err("cannot reserve video memory at 0x%lx\n", + info->fix.smem_start); err = -EIO; goto out_reg; } @@ -1743,10 +1725,8 @@ static int uvesafb_probe(struct platform_device *dev) uvesafb_ioremap(info); if (!info->screen_base) { - printk(KERN_ERR - "uvesafb: abort, cannot ioremap 0x%x bytes of video " - "memory at 0x%lx\n", - info->fix.smem_len, info->fix.smem_start); + pr_err("abort, cannot ioremap 0x%x bytes of video memory at 0x%lx\n", + info->fix.smem_len, info->fix.smem_start); err = -EIO; goto out_mem; } @@ -1754,16 +1734,14 @@ static int uvesafb_probe(struct platform_device *dev) platform_set_drvdata(dev, info); if (register_framebuffer(info) < 0) { - printk(KERN_ERR - "uvesafb: failed to register framebuffer device\n"); + pr_err("failed to register framebuffer device\n"); err = -EINVAL; goto out_unmap; } - printk(KERN_INFO "uvesafb: framebuffer at 0x%lx, mapped to 0x%p, " - "using %dk, total %dk\n", info->fix.smem_start, - info->screen_base, info->fix.smem_len/1024, - par->vbe_ib.total_memory * 64); + pr_info("framebuffer at 0x%lx, mapped to 0x%p, using %dk, total %dk\n", + info->fix.smem_start, info->screen_base, + info->fix.smem_len / 1024, par->vbe_ib.total_memory * 64); fb_info(info, "%s frame buffer device\n", info->fix.id); err = sysfs_create_group(&dev->dev.kobj, &uvesafb_dev_attgrp); @@ -1871,8 +1849,7 @@ static int uvesafb_setup(char *options) else if (this_opt[0] >= '0' && this_opt[0] <= '9') { mode_option = this_opt; } else { - printk(KERN_WARNING - "uvesafb: unrecognized option %s\n", this_opt); + pr_warn("unrecognized option %s\n", this_opt); } } @@ -1931,8 +1908,7 @@ static int uvesafb_init(void) err = driver_create_file(&uvesafb_driver.driver, &driver_attr_v86d); if (err) { - printk(KERN_WARNING "uvesafb: failed to register " - "attributes\n"); + pr_warn("failed to register attributes\n"); err = 0; } } -- cgit v1.2.3-59-g8ed1b From e297a783e41560b44e3c14f38e420cba518113b8 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 7 Jun 2017 19:58:56 -0400 Subject: random: add wait_for_random_bytes() API This enables users of get_random_{bytes,u32,u64,int,long} to wait until the pool is ready before using this function, in case they actually want to have reliable randomness. Signed-off-by: Jason A. Donenfeld Signed-off-by: Theodore Ts'o --- drivers/char/random.c | 41 +++++++++++++++++++++++++++++++---------- include/linux/random.h | 1 + 2 files changed, 32 insertions(+), 10 deletions(-) diff --git a/drivers/char/random.c b/drivers/char/random.c index 01a260f67437..3853dd4f92e7 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -851,11 +851,6 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r) } } -static inline void crng_wait_ready(void) -{ - wait_event_interruptible(crng_init_wait, crng_ready()); -} - static void _extract_crng(struct crng_state *crng, __u8 out[CHACHA20_BLOCK_SIZE]) { @@ -1477,7 +1472,10 @@ static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf, * number of good random numbers, suitable for key generation, seeding * TCP sequence numbers, etc. It does not rely on the hardware random * number generator. For random bytes direct from the hardware RNG - * (when available), use get_random_bytes_arch(). + * (when available), use get_random_bytes_arch(). In order to ensure + * that the randomness provided by this function is okay, the function + * wait_for_random_bytes() should be called and return 0 at least once + * at any point prior. */ void get_random_bytes(void *buf, int nbytes) { @@ -1506,6 +1504,24 @@ void get_random_bytes(void *buf, int nbytes) } EXPORT_SYMBOL(get_random_bytes); +/* + * Wait for the urandom pool to be seeded and thus guaranteed to supply + * cryptographically secure random numbers. This applies to: the /dev/urandom + * device, the get_random_bytes function, and the get_random_{u32,u64,int,long} + * family of functions. Using any of these functions without first calling + * this function forfeits the guarantee of security. + * + * Returns: 0 if the urandom pool has been seeded. + * -ERESTARTSYS if the function was interrupted by a signal. + */ +int wait_for_random_bytes(void) +{ + if (likely(crng_ready())) + return 0; + return wait_event_interruptible(crng_init_wait, crng_ready()); +} +EXPORT_SYMBOL(wait_for_random_bytes); + /* * Add a callback function that will be invoked when the nonblocking * pool is initialised. @@ -1860,6 +1876,8 @@ const struct file_operations urandom_fops = { SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count, unsigned int, flags) { + int ret; + if (flags & ~(GRND_NONBLOCK|GRND_RANDOM)) return -EINVAL; @@ -1872,9 +1890,9 @@ SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count, if (!crng_ready()) { if (flags & GRND_NONBLOCK) return -EAGAIN; - crng_wait_ready(); - if (signal_pending(current)) - return -ERESTARTSYS; + ret = wait_for_random_bytes(); + if (unlikely(ret)) + return ret; } return urandom_read(NULL, buf, count, NULL); } @@ -2035,7 +2053,10 @@ static rwlock_t batched_entropy_reset_lock = __RW_LOCK_UNLOCKED(batched_entropy_ /* * Get a random word for internal kernel use only. The quality of the random * number is either as good as RDRAND or as good as /dev/urandom, with the - * goal of being quite fast and not depleting entropy. + * goal of being quite fast and not depleting entropy. In order to ensure + * that the randomness provided by this function is okay, the function + * wait_for_random_bytes() should be called and return 0 at least once + * at any point prior. */ static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u64); u64 get_random_u64(void) diff --git a/include/linux/random.h b/include/linux/random.h index ed5c3838780d..e29929347c95 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -34,6 +34,7 @@ extern void add_input_randomness(unsigned int type, unsigned int code, extern void add_interrupt_randomness(int irq, int irq_flags) __latent_entropy; extern void get_random_bytes(void *buf, int nbytes); +extern int wait_for_random_bytes(void); extern int add_random_ready_callback(struct random_ready_callback *rdy); extern void del_random_ready_callback(struct random_ready_callback *rdy); extern void get_random_bytes_arch(void *buf, int nbytes); -- cgit v1.2.3-59-g8ed1b From da9ba564bd683374b8d319756f312821b8265b06 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 7 Jun 2017 20:05:02 -0400 Subject: random: add get_random_{bytes,u32,u64,int,long,once}_wait family These functions are simple convenience wrappers that call wait_for_random_bytes before calling the respective get_random_* function. Signed-off-by: Jason A. Donenfeld Signed-off-by: Theodore Ts'o --- include/linux/net.h | 2 ++ include/linux/once.h | 2 ++ include/linux/random.h | 25 +++++++++++++++++++++++++ 3 files changed, 29 insertions(+) diff --git a/include/linux/net.h b/include/linux/net.h index abcfa46a2bd9..dda2cc939a53 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -274,6 +274,8 @@ do { \ #define net_get_random_once(buf, nbytes) \ get_random_once((buf), (nbytes)) +#define net_get_random_once_wait(buf, nbytes) \ + get_random_once_wait((buf), (nbytes)) int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); diff --git a/include/linux/once.h b/include/linux/once.h index 285f12cb40e6..9c98aaa87cbc 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -53,5 +53,7 @@ void __do_once_done(bool *done, struct static_key *once_key, #define get_random_once(buf, nbytes) \ DO_ONCE(get_random_bytes, (buf), (nbytes)) +#define get_random_once_wait(buf, nbytes) \ + DO_ONCE(get_random_bytes_wait, (buf), (nbytes)) \ #endif /* _LINUX_ONCE_H */ diff --git a/include/linux/random.h b/include/linux/random.h index e29929347c95..4aecc339558d 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -58,6 +58,31 @@ static inline unsigned long get_random_long(void) #endif } +/* Calls wait_for_random_bytes() and then calls get_random_bytes(buf, nbytes). + * Returns the result of the call to wait_for_random_bytes. */ +static inline int get_random_bytes_wait(void *buf, int nbytes) +{ + int ret = wait_for_random_bytes(); + if (unlikely(ret)) + return ret; + get_random_bytes(buf, nbytes); + return 0; +} + +#define declare_get_random_var_wait(var) \ + static inline int get_random_ ## var ## _wait(var *out) { \ + int ret = wait_for_random_bytes(); \ + if (unlikely(ret)) \ + return ret; \ + *out = get_random_ ## var(); \ + return 0; \ + } +declare_get_random_var_wait(u32) +declare_get_random_var_wait(u64) +declare_get_random_var_wait(int) +declare_get_random_var_wait(long) +#undef declare_get_random_var + unsigned long randomize_page(unsigned long start, unsigned long range); u32 prandom_u32(void); -- cgit v1.2.3-59-g8ed1b From 51b0817b0d23d51223575eff14629b3602a93cd4 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 7 Jun 2017 20:42:50 -0400 Subject: cifs: use get_random_u32 for 32-bit lock random Using get_random_u32 here is faster, more fitting of the use case, and just as cryptographically secure. It also has the benefit of providing better randomness at early boot, which is sometimes when this is used. Signed-off-by: Jason A. Donenfeld Cc: Steve French Signed-off-by: Theodore Ts'o --- fs/cifs/cifsfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 9a1667e0e8d6..fe0c8dcc7dc7 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1359,7 +1359,7 @@ init_cifs(void) spin_lock_init(&cifs_tcp_ses_lock); spin_lock_init(&GlobalMid_Lock); - get_random_bytes(&cifs_lock_secret, sizeof(cifs_lock_secret)); + cifs_lock_secret = get_random_u32(); if (cifs_max_pending < 2) { cifs_max_pending = 2; -- cgit v1.2.3-59-g8ed1b From 6787ab81b29115b6d2e7d17fe8a8017da66197d6 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 7 Jun 2017 22:34:26 -0400 Subject: iscsi: ensure RNG is seeded before use It's not safe to use weak random data here, especially for the challenge response randomness. Since we're always in process context, it's safe to simply wait until we have enough randomness to carry out the authentication correctly. While we're at it, we clean up a small memleak during an error condition. Signed-off-by: Jason A. Donenfeld Cc: "Nicholas A. Bellinger" Cc: Lee Duncan Cc: Chris Leech Signed-off-by: Theodore Ts'o --- drivers/target/iscsi/iscsi_target_auth.c | 14 +++++++++++--- drivers/target/iscsi/iscsi_target_login.c | 22 ++++++++++++++-------- 2 files changed, 25 insertions(+), 11 deletions(-) diff --git a/drivers/target/iscsi/iscsi_target_auth.c b/drivers/target/iscsi/iscsi_target_auth.c index 903b667f8e01..f9bc8ec6fb6b 100644 --- a/drivers/target/iscsi/iscsi_target_auth.c +++ b/drivers/target/iscsi/iscsi_target_auth.c @@ -47,18 +47,21 @@ static void chap_binaryhex_to_asciihex(char *dst, char *src, int src_len) } } -static void chap_gen_challenge( +static int chap_gen_challenge( struct iscsi_conn *conn, int caller, char *c_str, unsigned int *c_len) { + int ret; unsigned char challenge_asciihex[CHAP_CHALLENGE_LENGTH * 2 + 1]; struct iscsi_chap *chap = conn->auth_protocol; memset(challenge_asciihex, 0, CHAP_CHALLENGE_LENGTH * 2 + 1); - get_random_bytes(chap->challenge, CHAP_CHALLENGE_LENGTH); + ret = get_random_bytes_wait(chap->challenge, CHAP_CHALLENGE_LENGTH); + if (unlikely(ret)) + return ret; chap_binaryhex_to_asciihex(challenge_asciihex, chap->challenge, CHAP_CHALLENGE_LENGTH); /* @@ -69,6 +72,7 @@ static void chap_gen_challenge( pr_debug("[%s] Sending CHAP_C=0x%s\n\n", (caller) ? "server" : "client", challenge_asciihex); + return 0; } static int chap_check_algorithm(const char *a_str) @@ -143,6 +147,7 @@ static struct iscsi_chap *chap_server_open( case CHAP_DIGEST_UNKNOWN: default: pr_err("Unsupported CHAP_A value\n"); + kfree(conn->auth_protocol); return NULL; } @@ -156,7 +161,10 @@ static struct iscsi_chap *chap_server_open( /* * Generate Challenge. */ - chap_gen_challenge(conn, 1, aic_str, aic_len); + if (chap_gen_challenge(conn, 1, aic_str, aic_len) < 0) { + kfree(conn->auth_protocol); + return NULL; + } return chap; } diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 66238477137b..5ef028c11738 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -245,22 +245,26 @@ int iscsi_check_for_session_reinstatement(struct iscsi_conn *conn) return 0; } -static void iscsi_login_set_conn_values( +static int iscsi_login_set_conn_values( struct iscsi_session *sess, struct iscsi_conn *conn, __be16 cid) { + int ret; conn->sess = sess; conn->cid = be16_to_cpu(cid); /* * Generate a random Status sequence number (statsn) for the new * iSCSI connection. */ - get_random_bytes(&conn->stat_sn, sizeof(u32)); + ret = get_random_bytes_wait(&conn->stat_sn, sizeof(u32)); + if (unlikely(ret)) + return ret; mutex_lock(&auth_id_lock); conn->auth_id = iscsit_global->auth_id++; mutex_unlock(&auth_id_lock); + return 0; } __printf(2, 3) int iscsi_change_param_sprintf( @@ -306,7 +310,11 @@ static int iscsi_login_zero_tsih_s1( return -ENOMEM; } - iscsi_login_set_conn_values(sess, conn, pdu->cid); + ret = iscsi_login_set_conn_values(sess, conn, pdu->cid); + if (unlikely(ret)) { + kfree(sess); + return ret; + } sess->init_task_tag = pdu->itt; memcpy(&sess->isid, pdu->isid, 6); sess->exp_cmd_sn = be32_to_cpu(pdu->cmdsn); @@ -497,8 +505,7 @@ static int iscsi_login_non_zero_tsih_s1( { struct iscsi_login_req *pdu = (struct iscsi_login_req *)buf; - iscsi_login_set_conn_values(NULL, conn, pdu->cid); - return 0; + return iscsi_login_set_conn_values(NULL, conn, pdu->cid); } /* @@ -554,9 +561,8 @@ static int iscsi_login_non_zero_tsih_s2( atomic_set(&sess->session_continuation, 1); spin_unlock_bh(&sess->conn_lock); - iscsi_login_set_conn_values(sess, conn, pdu->cid); - - if (iscsi_copy_param_list(&conn->param_list, + if (iscsi_login_set_conn_values(sess, conn, pdu->cid) < 0 || + iscsi_copy_param_list(&conn->param_list, conn->tpg->param_list, 0) < 0) { iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR, ISCSI_LOGIN_STATUS_NO_RESOURCES); -- cgit v1.2.3-59-g8ed1b From ae5b806a3d3c23d9d3b57aecbe687a0bd82ab086 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 7 Jun 2017 22:44:54 -0400 Subject: ceph: ensure RNG is seeded before using Ceph uses the RNG for various nonce generations, and it shouldn't accept using bad randomness. So, we wait for the RNG to be properly seeded. We do this by calling wait_for_random_bytes() in a function that is certainly called in process context, early on, so that all subsequent calls to get_random_bytes are necessarily acceptable. Signed-off-by: Jason A. Donenfeld Cc: Ilya Dryomov Cc: "Yan, Zheng" Cc: Sage Weil Signed-off-by: Theodore Ts'o --- net/ceph/ceph_common.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 4fd02831beed..26ab58665f77 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -611,7 +611,11 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private) { struct ceph_client *client; struct ceph_entity_addr *myaddr = NULL; - int err = -ENOMEM; + int err; + + err = wait_for_random_bytes(); + if (err < 0) + return ERR_PTR(err); client = kzalloc(sizeof(*client), GFP_KERNEL); if (client == NULL) -- cgit v1.2.3-59-g8ed1b From d48ad080ec0101c2cca92926bed64993ab565c3d Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 7 Jun 2017 22:47:13 -0400 Subject: rhashtable: use get_random_u32 for hash_rnd This is much faster and just as secure. It also has the added benefit of probably returning better randomness at early-boot on systems with architectural RNGs. Signed-off-by: Jason A. Donenfeld Cc: Thomas Graf Cc: Herbert Xu Signed-off-by: Theodore Ts'o --- lib/rhashtable.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/rhashtable.c b/lib/rhashtable.c index d9e7274a04cd..a1eb7c947f46 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -235,7 +235,7 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht, INIT_LIST_HEAD(&tbl->walkers); - get_random_bytes(&tbl->hash_rnd, sizeof(tbl->hash_rnd)); + tbl->hash_rnd = get_random_u32(); for (i = 0; i < nbuckets; i++) INIT_RHT_NULLS_HEAD(tbl->buckets[i], ht, i); -- cgit v1.2.3-59-g8ed1b From b3d0f7895d1251f0af0dd38410e7be3e52be4a1d Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 7 Jun 2017 23:00:05 -0400 Subject: net/neighbor: use get_random_u32 for 32-bit hash random Using get_random_u32 here is faster, more fitting of the use case, and just as cryptographically secure. It also has the benefit of providing better randomness at early boot, which is when many of these structures are assigned. Signed-off-by: Jason A. Donenfeld Cc: David Miller Signed-off-by: Theodore Ts'o --- net/core/neighbour.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index d274f81fcc2c..9784133b0cdb 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -312,8 +312,7 @@ out_entries: static void neigh_get_hash_rnd(u32 *x) { - get_random_bytes(x, sizeof(*x)); - *x |= 1; + *x = get_random_u32() | 1; } static struct neigh_hash_table *neigh_hash_alloc(unsigned int shift) -- cgit v1.2.3-59-g8ed1b From 7aed9f72c3c70bdc18e72ec086c1a0eafdcd273f Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 7 Jun 2017 23:01:20 -0400 Subject: net/route: use get_random_int for random counter Using get_random_int here is faster, more fitting of the use case, and just as cryptographically secure. It also has the benefit of providing better randomness at early boot, which is when many of these structures are assigned. Also, semantically, it's not really proper to have been assigning an atomic_t in this way before, even if in practice it works fine. Signed-off-by: Jason A. Donenfeld Cc: David Miller Signed-off-by: Theodore Ts'o --- net/ipv4/route.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 655d9eebe43e..11e001a42094 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2936,8 +2936,7 @@ static __net_init int rt_genid_init(struct net *net) { atomic_set(&net->ipv4.rt_genid, 0); atomic_set(&net->fnhe_genid, 0); - get_random_bytes(&net->ipv4.dev_addr_genid, - sizeof(net->ipv4.dev_addr_genid)); + atomic_set(&net->ipv4.dev_addr_genid, get_random_int()); return 0; } -- cgit v1.2.3-59-g8ed1b From d06bfd1989fe97623b32d6df4ffa6e4338c99dc8 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 7 Jun 2017 23:06:55 -0400 Subject: random: warn when kernel uses unseeded randomness This enables an important dmesg notification about when drivers have used the crng without it being seeded first. Prior, these errors would occur silently, and so there hasn't been a great way of diagnosing these types of bugs for obscure setups. By adding this as a config option, we can leave it on by default, so that we learn where these issues happen, in the field, will still allowing some people to turn it off, if they really know what they're doing and do not want the log entries. However, we don't leave it _completely_ by default. An earlier version of this patch simply had `default y`. I'd really love that, but it turns out, this problem with unseeded randomness being used is really quite present and is going to take a long time to fix. Thus, as a compromise between log-messages-for-all and nobody-knows, this is `default y`, except it is also `depends on DEBUG_KERNEL`. This will ensure that the curious see the messages while others don't have to. Signed-off-by: Jason A. Donenfeld Signed-off-by: Theodore Ts'o --- drivers/char/random.c | 15 +++++++++++++-- lib/Kconfig.debug | 16 ++++++++++++++++ 2 files changed, 29 insertions(+), 2 deletions(-) diff --git a/drivers/char/random.c b/drivers/char/random.c index 3853dd4f92e7..fa5bbd5a7ca0 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -288,7 +288,6 @@ #define SEC_XFER_SIZE 512 #define EXTRACT_SIZE 10 -#define DEBUG_RANDOM_BOOT 0 #define LONGS(x) (((x) + sizeof(unsigned long) - 1)/sizeof(unsigned long)) @@ -1481,7 +1480,7 @@ void get_random_bytes(void *buf, int nbytes) { __u8 tmp[CHACHA20_BLOCK_SIZE]; -#if DEBUG_RANDOM_BOOT > 0 +#ifdef CONFIG_WARN_UNSEEDED_RANDOM if (!crng_ready()) printk(KERN_NOTICE "random: %pF get_random_bytes called " "with crng_init = %d\n", (void *) _RET_IP_, crng_init); @@ -2075,6 +2074,12 @@ u64 get_random_u64(void) return ret; #endif +#ifdef CONFIG_WARN_UNSEEDED_RANDOM + if (!crng_ready()) + printk(KERN_NOTICE "random: %pF get_random_u64 called " + "with crng_init = %d\n", (void *) _RET_IP_, crng_init); +#endif + batch = &get_cpu_var(batched_entropy_u64); if (use_lock) read_lock_irqsave(&batched_entropy_reset_lock, flags); @@ -2101,6 +2106,12 @@ u32 get_random_u32(void) if (arch_get_random_int(&ret)) return ret; +#ifdef CONFIG_WARN_UNSEEDED_RANDOM + if (!crng_ready()) + printk(KERN_NOTICE "random: %pF get_random_u32 called " + "with crng_init = %d\n", (void *) _RET_IP_, crng_init); +#endif + batch = &get_cpu_var(batched_entropy_u32); if (use_lock) read_lock_irqsave(&batched_entropy_reset_lock, flags); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index e4587ebe52c7..c4159605bfbf 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1209,6 +1209,22 @@ config STACKTRACE It is also used by various kernel debugging features that require stack trace generation. +config WARN_UNSEEDED_RANDOM + bool "Warn when kernel uses unseeded randomness" + default y + depends on DEBUG_KERNEL + help + Some parts of the kernel contain bugs relating to their use of + cryptographically secure random numbers before it's actually possible + to generate those numbers securely. This setting ensures that these + flaws don't go unnoticed, by enabling a message, should this ever + occur. This will allow people with obscure setups to know when things + are going wrong, so that they might contact developers about fixing + it. + + Say Y here, unless you simply do not care about using unseeded + randomness and do not want a potential warning message in your logs. + config DEBUG_KOBJECT bool "kobject debugging" depends on DEBUG_KERNEL -- cgit v1.2.3-59-g8ed1b From b21ff825d6b7fa7122f9c4455f9a0f157b9fb225 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 13 Jun 2017 22:45:35 +0900 Subject: mtd: nand: denali: set NAND_ECC_CUSTOM_PAGE_ACCESS The denali_cmdfunc() actually does nothing valuable for NAND_CMD_{PAGEPROG,READ0,SEQIN}. For NAND_CMD_{READ0,SEQIN}, it copies "page" to "denali->page", then denali_read_page(_raw) compares them just for the sanity check. (Inconsistently, this check is missing from denali_write_page(_raw).) The Denali controller is equipped with high level read/write interface, so let's skip unneeded call of cmdfunc(). If NAND_ECC_CUSTOM_PAGE_ACCESS is set, nand_write_page() will not call ->waitfunc hook. So, ->write_page(_raw) hooks should directly return -EIO on failure. The error handling of page writes will be much simpler. Signed-off-by: Masahiro Yamada Signed-off-by: Boris Brezillon --- drivers/mtd/nand/denali.c | 41 ++++++++++++----------------------------- drivers/mtd/nand/denali.h | 1 - 2 files changed, 12 insertions(+), 30 deletions(-) diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c index 2b4618bb8d72..7133a33b4ad3 100644 --- a/drivers/mtd/nand/denali.c +++ b/drivers/mtd/nand/denali.c @@ -998,13 +998,16 @@ static void denali_setup_dma(struct denali_nand_info *denali, int op) * configuration details. */ static int write_page(struct mtd_info *mtd, struct nand_chip *chip, - const uint8_t *buf, bool raw_xfer) + const uint8_t *buf, int page, bool raw_xfer) { struct denali_nand_info *denali = mtd_to_denali(mtd); dma_addr_t addr = denali->buf.dma_buf; size_t size = mtd->writesize + mtd->oobsize; uint32_t irq_status; uint32_t irq_mask = INTR__DMA_CMD_COMP | INTR__PROGRAM_FAIL; + int ret = 0; + + denali->page = page; /* * if it is a raw xfer, we want to disable ecc and send the spare area. @@ -1036,13 +1039,13 @@ static int write_page(struct mtd_info *mtd, struct nand_chip *chip, if (irq_status == 0) { dev_err(denali->dev, "timeout on write_page (type = %d)\n", raw_xfer); - denali->status = NAND_STATUS_FAIL; + ret = -EIO; } denali_enable_dma(denali, false); dma_sync_single_for_cpu(denali->dev, addr, size, DMA_TO_DEVICE); - return 0; + return ret; } /* NAND core entry points */ @@ -1059,7 +1062,7 @@ static int denali_write_page(struct mtd_info *mtd, struct nand_chip *chip, * for regular page writes, we let HW handle all the ECC * data written to the device. */ - return write_page(mtd, chip, buf, false); + return write_page(mtd, chip, buf, page, false); } /* @@ -1075,7 +1078,7 @@ static int denali_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip, * for raw page writes, we want to disable ECC and simply write * whatever data is in the buffer. */ - return write_page(mtd, chip, buf, true); + return write_page(mtd, chip, buf, page, true); } static int denali_write_oob(struct mtd_info *mtd, struct nand_chip *chip, @@ -1105,12 +1108,7 @@ static int denali_read_page(struct mtd_info *mtd, struct nand_chip *chip, unsigned long uncor_ecc_flags = 0; int stat = 0; - if (page != denali->page) { - dev_err(denali->dev, - "IN %s: page %d is not equal to denali->page %d", - __func__, page, denali->page); - BUG(); - } + denali->page = page; setup_ecc_for_xfer(denali, true, false); @@ -1154,12 +1152,7 @@ static int denali_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, size_t size = mtd->writesize + mtd->oobsize; uint32_t irq_mask = INTR__DMA_CMD_COMP; - if (page != denali->page) { - dev_err(denali->dev, - "IN %s: page %d is not equal to denali->page %d", - __func__, page, denali->page); - BUG(); - } + denali->page = page; setup_ecc_for_xfer(denali, false, true); denali_enable_dma(denali, true); @@ -1204,12 +1197,7 @@ static void denali_select_chip(struct mtd_info *mtd, int chip) static int denali_waitfunc(struct mtd_info *mtd, struct nand_chip *chip) { - struct denali_nand_info *denali = mtd_to_denali(mtd); - int status = denali->status; - - denali->status = 0; - - return status; + return 0; } static int denali_erase(struct mtd_info *mtd, int page) @@ -1238,8 +1226,6 @@ static void denali_cmdfunc(struct mtd_info *mtd, unsigned int cmd, int col, int i; switch (cmd) { - case NAND_CMD_PAGEPROG: - break; case NAND_CMD_STATUS: read_status(denali); break; @@ -1259,10 +1245,6 @@ static void denali_cmdfunc(struct mtd_info *mtd, unsigned int cmd, int col, write_byte_to_buf(denali, id); } break; - case NAND_CMD_READ0: - case NAND_CMD_SEQIN: - denali->page = page; - break; case NAND_CMD_RESET: reset_bank(denali); break; @@ -1605,6 +1587,7 @@ int denali_init(struct denali_nand_info *denali) mtd_set_ooblayout(mtd, &denali_ooblayout_ops); + chip->ecc.options |= NAND_ECC_CUSTOM_PAGE_ACCESS; chip->ecc.read_page = denali_read_page; chip->ecc.read_page_raw = denali_read_page_raw; chip->ecc.write_page = denali_write_page; diff --git a/drivers/mtd/nand/denali.h b/drivers/mtd/nand/denali.h index a06ed741b550..352d8328b94a 100644 --- a/drivers/mtd/nand/denali.h +++ b/drivers/mtd/nand/denali.h @@ -323,7 +323,6 @@ struct nand_buf { struct denali_nand_info { struct nand_chip nand; int flash_bank; /* currently selected chip */ - int status; int platform; struct nand_buf buf; struct device *dev; -- cgit v1.2.3-59-g8ed1b From 959e9f2ae9dac4821d7da354a37272650febebbe Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 13 Jun 2017 22:45:36 +0900 Subject: mtd: nand: denali: remove unneeded find_valid_banks() The function find_valid_banks() issues the Read ID (0x90) command, then compares the first byte (Manufacturer ID) of each bank with the one of bank0. This is equivalent to what nand_scan_ident() does. The number of chips is detected there, so this is unneeded. What is worse for find_valid_banks() is that, if multiple chips are connected to INTEL_CE4100 platform, it crashes the kernel by BUG(). This is what we should avoid. This function is just harmful and unneeded. Signed-off-by: Masahiro Yamada Signed-off-by: Boris Brezillon --- drivers/mtd/nand/denali.c | 47 ----------------------------------------------- drivers/mtd/nand/denali.h | 1 - 2 files changed, 48 deletions(-) diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c index 7133a33b4ad3..122df4c6126d 100644 --- a/drivers/mtd/nand/denali.c +++ b/drivers/mtd/nand/denali.c @@ -337,51 +337,6 @@ static void get_samsung_nand_para(struct denali_nand_info *denali, } } -/* - * determines how many NAND chips are connected to the controller. Note for - * Intel CE4100 devices we don't support more than one device. - */ -static void find_valid_banks(struct denali_nand_info *denali) -{ - uint32_t id[denali->max_banks]; - int i; - - denali->total_used_banks = 1; - for (i = 0; i < denali->max_banks; i++) { - index_addr(denali, MODE_11 | (i << 24) | 0, 0x90); - index_addr(denali, MODE_11 | (i << 24) | 1, 0); - index_addr_read_data(denali, MODE_11 | (i << 24) | 2, &id[i]); - - dev_dbg(denali->dev, - "Return 1st ID for bank[%d]: %x\n", i, id[i]); - - if (i == 0) { - if (!(id[i] & 0x0ff)) - break; /* WTF? */ - } else { - if ((id[i] & 0x0ff) == (id[0] & 0x0ff)) - denali->total_used_banks++; - else - break; - } - } - - if (denali->platform == INTEL_CE4100) { - /* - * Platform limitations of the CE4100 device limit - * users to a single chip solution for NAND. - * Multichip support is not enabled. - */ - if (denali->total_used_banks != 1) { - dev_err(denali->dev, - "Sorry, Intel CE4100 only supports a single NAND device.\n"); - BUG(); - } - } - dev_dbg(denali->dev, - "denali->total_used_banks: %d\n", denali->total_used_banks); -} - /* * Use the configuration feature register to determine the maximum number of * banks that the hardware supports. @@ -439,8 +394,6 @@ static uint16_t denali_nand_timing_set(struct denali_nand_info *denali) ioread32(denali->flash_reg + RDWR_EN_HI_CNT), ioread32(denali->flash_reg + CS_SETUP_CNT)); - find_valid_banks(denali); - /* * If the user specified to override the default timings * with a specific ONFI mode, we apply those changes here. diff --git a/drivers/mtd/nand/denali.h b/drivers/mtd/nand/denali.h index 352d8328b94a..0e4a8965f6f1 100644 --- a/drivers/mtd/nand/denali.h +++ b/drivers/mtd/nand/denali.h @@ -326,7 +326,6 @@ struct denali_nand_info { int platform; struct nand_buf buf; struct device *dev; - int total_used_banks; int page; void __iomem *flash_reg; /* Register Interface */ void __iomem *flash_mem; /* Host Data/Command Interface */ -- cgit v1.2.3-59-g8ed1b From 1bb88666775e50fdef1d915d395eca9267bd3ab1 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 13 Jun 2017 22:45:37 +0900 Subject: mtd: nand: denali: handle timing parameters by setup_data_interface() Handling timing parameters in a driver's own way should be avoided because it duplicates efforts of drivers/mtd/nand/nand_timings.c Besides, this driver hard-codes Intel specific parameters such as CLK_X=5, CLK_MULTI=4. Taking a certain device (Samsung K9WAG08U1A) into account by get_samsung_nand_para() is weird as well. Now, the core framework provides .setup_data_interface() hook, which handles timing parameters in a generic manner. While I am working on this, I found even more issues in the current code, so fixed the following as well: - In recent IP versions, WE_2_RE and TWHR2 share the same register. Likewise for ADDR_2_DATA and TCWAW, CS_SETUP_CNT and TWB. When updating one, the other must be masked. Otherwise, the other will be set to 0, then timing settings will be broken. - The recent IP release expanded the ADDR_2_DATA to 7-bit wide. This register is related to tADL. As commit 74a332e78e8f ("mtd: nand: timings: Fix tADL_min for ONFI 4.0 chips") addressed, the ONFi 4.0 increased the minimum of tADL to 400 nsec. This may not fit in the 6-bit ADDR_2_DATA in older versions. Check the IP revision and handle this correctly, otherwise the register value would wrap around. Signed-off-by: Masahiro Yamada Signed-off-by: Boris Brezillon --- drivers/mtd/nand/denali.c | 345 +++++++++++++++--------------------------- drivers/mtd/nand/denali.h | 26 ++-- drivers/mtd/nand/denali_dt.c | 3 +- drivers/mtd/nand/denali_pci.c | 6 +- 4 files changed, 139 insertions(+), 241 deletions(-) diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c index 122df4c6126d..ca2b6b8850ba 100644 --- a/drivers/mtd/nand/denali.c +++ b/drivers/mtd/nand/denali.c @@ -28,17 +28,6 @@ MODULE_LICENSE("GPL"); -/* - * We define a module parameter that allows the user to override - * the hardware and decide what timing mode should be used. - */ -#define NAND_DEFAULT_TIMINGS -1 - -static int onfi_timing_mode = NAND_DEFAULT_TIMINGS; -module_param(onfi_timing_mode, int, S_IRUGO); -MODULE_PARM_DESC(onfi_timing_mode, - "Overrides default ONFI setting. -1 indicates use default timings"); - #define DENALI_NAND_NAME "denali-nand" /* @@ -63,10 +52,12 @@ MODULE_PARM_DESC(onfi_timing_mode, #define CHIP_SELECT_INVALID -1 /* - * This macro divides two integers and rounds fractional values up - * to the nearest integer value. + * The bus interface clock, clk_x, is phase aligned with the core clock. The + * clk_x is an integral multiple N of the core clk. The value N is configured + * at IP delivery time, and its available value is 4, 5, or 6. We need to align + * to the largest value to make it work with any possible configuration. */ -#define CEIL_DIV(X, Y) (((X)%(Y)) ? ((X)/(Y)+1) : ((X)/(Y))) +#define DENALI_CLK_X_MULT 6 /* * this macro allows us to convert from an MTD structure to our own @@ -195,148 +186,6 @@ static uint16_t denali_nand_reset(struct denali_nand_info *denali) return PASS; } -/* - * this routine calculates the ONFI timing values for a given mode and - * programs the clocking register accordingly. The mode is determined by - * the get_onfi_nand_para routine. - */ -static void nand_onfi_timing_set(struct denali_nand_info *denali, - uint16_t mode) -{ - uint16_t Trea[6] = {40, 30, 25, 20, 20, 16}; - uint16_t Trp[6] = {50, 25, 17, 15, 12, 10}; - uint16_t Treh[6] = {30, 15, 15, 10, 10, 7}; - uint16_t Trc[6] = {100, 50, 35, 30, 25, 20}; - uint16_t Trhoh[6] = {0, 15, 15, 15, 15, 15}; - uint16_t Trloh[6] = {0, 0, 0, 0, 5, 5}; - uint16_t Tcea[6] = {100, 45, 30, 25, 25, 25}; - uint16_t Tadl[6] = {200, 100, 100, 100, 70, 70}; - uint16_t Trhw[6] = {200, 100, 100, 100, 100, 100}; - uint16_t Trhz[6] = {200, 100, 100, 100, 100, 100}; - uint16_t Twhr[6] = {120, 80, 80, 60, 60, 60}; - uint16_t Tcs[6] = {70, 35, 25, 25, 20, 15}; - - uint16_t data_invalid_rhoh, data_invalid_rloh, data_invalid; - uint16_t dv_window = 0; - uint16_t en_lo, en_hi; - uint16_t acc_clks; - uint16_t addr_2_data, re_2_we, re_2_re, we_2_re, cs_cnt; - - en_lo = CEIL_DIV(Trp[mode], CLK_X); - en_hi = CEIL_DIV(Treh[mode], CLK_X); -#if ONFI_BLOOM_TIME - if ((en_hi * CLK_X) < (Treh[mode] + 2)) - en_hi++; -#endif - - if ((en_lo + en_hi) * CLK_X < Trc[mode]) - en_lo += CEIL_DIV((Trc[mode] - (en_lo + en_hi) * CLK_X), CLK_X); - - if ((en_lo + en_hi) < CLK_MULTI) - en_lo += CLK_MULTI - en_lo - en_hi; - - while (dv_window < 8) { - data_invalid_rhoh = en_lo * CLK_X + Trhoh[mode]; - - data_invalid_rloh = (en_lo + en_hi) * CLK_X + Trloh[mode]; - - data_invalid = data_invalid_rhoh < data_invalid_rloh ? - data_invalid_rhoh : data_invalid_rloh; - - dv_window = data_invalid - Trea[mode]; - - if (dv_window < 8) - en_lo++; - } - - acc_clks = CEIL_DIV(Trea[mode], CLK_X); - - while (acc_clks * CLK_X - Trea[mode] < 3) - acc_clks++; - - if (data_invalid - acc_clks * CLK_X < 2) - dev_warn(denali->dev, "%s, Line %d: Warning!\n", - __FILE__, __LINE__); - - addr_2_data = CEIL_DIV(Tadl[mode], CLK_X); - re_2_we = CEIL_DIV(Trhw[mode], CLK_X); - re_2_re = CEIL_DIV(Trhz[mode], CLK_X); - we_2_re = CEIL_DIV(Twhr[mode], CLK_X); - cs_cnt = CEIL_DIV((Tcs[mode] - Trp[mode]), CLK_X); - if (cs_cnt == 0) - cs_cnt = 1; - - if (Tcea[mode]) { - while (cs_cnt * CLK_X + Trea[mode] < Tcea[mode]) - cs_cnt++; - } - -#if MODE5_WORKAROUND - if (mode == 5) - acc_clks = 5; -#endif - - /* Sighting 3462430: Temporary hack for MT29F128G08CJABAWP:B */ - if (ioread32(denali->flash_reg + MANUFACTURER_ID) == 0 && - ioread32(denali->flash_reg + DEVICE_ID) == 0x88) - acc_clks = 6; - - iowrite32(acc_clks, denali->flash_reg + ACC_CLKS); - iowrite32(re_2_we, denali->flash_reg + RE_2_WE); - iowrite32(re_2_re, denali->flash_reg + RE_2_RE); - iowrite32(we_2_re, denali->flash_reg + WE_2_RE); - iowrite32(addr_2_data, denali->flash_reg + ADDR_2_DATA); - iowrite32(en_lo, denali->flash_reg + RDWR_EN_LO_CNT); - iowrite32(en_hi, denali->flash_reg + RDWR_EN_HI_CNT); - iowrite32(cs_cnt, denali->flash_reg + CS_SETUP_CNT); -} - -/* queries the NAND device to see what ONFI modes it supports. */ -static uint16_t get_onfi_nand_para(struct denali_nand_info *denali) -{ - int i; - - /* - * we needn't to do a reset here because driver has already - * reset all the banks before - */ - if (!(ioread32(denali->flash_reg + ONFI_TIMING_MODE) & - ONFI_TIMING_MODE__VALUE)) - return FAIL; - - for (i = 5; i > 0; i--) { - if (ioread32(denali->flash_reg + ONFI_TIMING_MODE) & - (0x01 << i)) - break; - } - - nand_onfi_timing_set(denali, i); - - /* - * By now, all the ONFI devices we know support the page cache - * rw feature. So here we enable the pipeline_rw_ahead feature - */ - /* iowrite32(1, denali->flash_reg + CACHE_WRITE_ENABLE); */ - /* iowrite32(1, denali->flash_reg + CACHE_READ_ENABLE); */ - - return PASS; -} - -static void get_samsung_nand_para(struct denali_nand_info *denali, - uint8_t device_id) -{ - if (device_id == 0xd3) { /* Samsung K9WAG08U1A */ - /* Set timing register values according to datasheet */ - iowrite32(5, denali->flash_reg + ACC_CLKS); - iowrite32(20, denali->flash_reg + RE_2_WE); - iowrite32(12, denali->flash_reg + WE_2_RE); - iowrite32(14, denali->flash_reg + ADDR_2_DATA); - iowrite32(3, denali->flash_reg + RDWR_EN_LO_CNT); - iowrite32(2, denali->flash_reg + RDWR_EN_HI_CNT); - iowrite32(2, denali->flash_reg + CS_SETUP_CNT); - } -} - /* * Use the configuration feature register to determine the maximum number of * banks that the hardware supports. @@ -352,58 +201,6 @@ static void detect_max_banks(struct denali_nand_info *denali) denali->max_banks <<= 1; } -static uint16_t denali_nand_timing_set(struct denali_nand_info *denali) -{ - uint16_t status = PASS; - uint32_t id_bytes[8], addr; - uint8_t maf_id, device_id; - int i; - - /* - * Use read id method to get device ID and other params. - * For some NAND chips, controller can't report the correct - * device ID by reading from DEVICE_ID register - */ - addr = MODE_11 | BANK(denali->flash_bank); - index_addr(denali, addr | 0, 0x90); - index_addr(denali, addr | 1, 0); - for (i = 0; i < 8; i++) - index_addr_read_data(denali, addr | 2, &id_bytes[i]); - maf_id = id_bytes[0]; - device_id = id_bytes[1]; - - if (ioread32(denali->flash_reg + ONFI_DEVICE_NO_OF_LUNS) & - ONFI_DEVICE_NO_OF_LUNS__ONFI_DEVICE) { /* ONFI 1.0 NAND */ - if (FAIL == get_onfi_nand_para(denali)) - return FAIL; - } else if (maf_id == 0xEC) { /* Samsung NAND */ - get_samsung_nand_para(denali, device_id); - } - - dev_info(denali->dev, - "Dump timing register values:\n" - "acc_clks: %d, re_2_we: %d, re_2_re: %d\n" - "we_2_re: %d, addr_2_data: %d, rdwr_en_lo_cnt: %d\n" - "rdwr_en_hi_cnt: %d, cs_setup_cnt: %d\n", - ioread32(denali->flash_reg + ACC_CLKS), - ioread32(denali->flash_reg + RE_2_WE), - ioread32(denali->flash_reg + RE_2_RE), - ioread32(denali->flash_reg + WE_2_RE), - ioread32(denali->flash_reg + ADDR_2_DATA), - ioread32(denali->flash_reg + RDWR_EN_LO_CNT), - ioread32(denali->flash_reg + RDWR_EN_HI_CNT), - ioread32(denali->flash_reg + CS_SETUP_CNT)); - - /* - * If the user specified to override the default timings - * with a specific ONFI mode, we apply those changes here. - */ - if (onfi_timing_mode != NAND_DEFAULT_TIMINGS) - nand_onfi_timing_set(denali, onfi_timing_mode); - - return status; -} - static void denali_set_intr_modes(struct denali_nand_info *denali, uint16_t INT_ENABLE) { @@ -1209,7 +1006,121 @@ static void denali_cmdfunc(struct mtd_info *mtd, unsigned int cmd, int col, break; } } -/* end NAND core entry points */ + +#define DIV_ROUND_DOWN_ULL(ll, d) \ + ({ unsigned long long _tmp = (ll); do_div(_tmp, d); _tmp; }) + +static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr, + const struct nand_data_interface *conf) +{ + struct denali_nand_info *denali = mtd_to_denali(mtd); + const struct nand_sdr_timings *timings; + unsigned long t_clk; + int acc_clks, re_2_we, re_2_re, we_2_re, addr_2_data; + int rdwr_en_lo, rdwr_en_hi, rdwr_en_lo_hi, cs_setup; + int addr_2_data_mask; + uint32_t tmp; + + timings = nand_get_sdr_timings(conf); + if (IS_ERR(timings)) + return PTR_ERR(timings); + + /* clk_x period in picoseconds */ + t_clk = DIV_ROUND_DOWN_ULL(1000000000000ULL, denali->clk_x_rate); + if (!t_clk) + return -EINVAL; + + if (chipnr == NAND_DATA_IFACE_CHECK_ONLY) + return 0; + + /* tREA -> ACC_CLKS */ + acc_clks = DIV_ROUND_UP(timings->tREA_max, t_clk); + acc_clks = min_t(int, acc_clks, ACC_CLKS__VALUE); + + tmp = ioread32(denali->flash_reg + ACC_CLKS); + tmp &= ~ACC_CLKS__VALUE; + tmp |= acc_clks; + iowrite32(tmp, denali->flash_reg + ACC_CLKS); + + /* tRWH -> RE_2_WE */ + re_2_we = DIV_ROUND_UP(timings->tRHW_min, t_clk); + re_2_we = min_t(int, re_2_we, RE_2_WE__VALUE); + + tmp = ioread32(denali->flash_reg + RE_2_WE); + tmp &= ~RE_2_WE__VALUE; + tmp |= re_2_we; + iowrite32(tmp, denali->flash_reg + RE_2_WE); + + /* tRHZ -> RE_2_RE */ + re_2_re = DIV_ROUND_UP(timings->tRHZ_max, t_clk); + re_2_re = min_t(int, re_2_re, RE_2_RE__VALUE); + + tmp = ioread32(denali->flash_reg + RE_2_RE); + tmp &= ~RE_2_RE__VALUE; + tmp |= re_2_re; + iowrite32(tmp, denali->flash_reg + RE_2_RE); + + /* tWHR -> WE_2_RE */ + we_2_re = DIV_ROUND_UP(timings->tWHR_min, t_clk); + we_2_re = min_t(int, we_2_re, TWHR2_AND_WE_2_RE__WE_2_RE); + + tmp = ioread32(denali->flash_reg + TWHR2_AND_WE_2_RE); + tmp &= ~TWHR2_AND_WE_2_RE__WE_2_RE; + tmp |= we_2_re; + iowrite32(tmp, denali->flash_reg + TWHR2_AND_WE_2_RE); + + /* tADL -> ADDR_2_DATA */ + + /* for older versions, ADDR_2_DATA is only 6 bit wide */ + addr_2_data_mask = TCWAW_AND_ADDR_2_DATA__ADDR_2_DATA; + if (denali->revision < 0x0501) + addr_2_data_mask >>= 1; + + addr_2_data = DIV_ROUND_UP(timings->tADL_min, t_clk); + addr_2_data = min_t(int, addr_2_data, addr_2_data_mask); + + tmp = ioread32(denali->flash_reg + TCWAW_AND_ADDR_2_DATA); + tmp &= ~addr_2_data_mask; + tmp |= addr_2_data; + iowrite32(tmp, denali->flash_reg + TCWAW_AND_ADDR_2_DATA); + + /* tREH, tWH -> RDWR_EN_HI_CNT */ + rdwr_en_hi = DIV_ROUND_UP(max(timings->tREH_min, timings->tWH_min), + t_clk); + rdwr_en_hi = min_t(int, rdwr_en_hi, RDWR_EN_HI_CNT__VALUE); + + tmp = ioread32(denali->flash_reg + RDWR_EN_HI_CNT); + tmp &= ~RDWR_EN_HI_CNT__VALUE; + tmp |= rdwr_en_hi; + iowrite32(tmp, denali->flash_reg + RDWR_EN_HI_CNT); + + /* tRP, tWP -> RDWR_EN_LO_CNT */ + rdwr_en_lo = DIV_ROUND_UP(max(timings->tRP_min, timings->tWP_min), + t_clk); + rdwr_en_lo_hi = DIV_ROUND_UP(max(timings->tRC_min, timings->tWC_min), + t_clk); + rdwr_en_lo_hi = max(rdwr_en_lo_hi, DENALI_CLK_X_MULT); + rdwr_en_lo = max(rdwr_en_lo, rdwr_en_lo_hi - rdwr_en_hi); + rdwr_en_lo = min_t(int, rdwr_en_lo, RDWR_EN_LO_CNT__VALUE); + + tmp = ioread32(denali->flash_reg + RDWR_EN_LO_CNT); + tmp &= ~RDWR_EN_LO_CNT__VALUE; + tmp |= rdwr_en_lo; + iowrite32(tmp, denali->flash_reg + RDWR_EN_LO_CNT); + + /* tCS, tCEA -> CS_SETUP_CNT */ + cs_setup = max3((int)DIV_ROUND_UP(timings->tCS_min, t_clk) - rdwr_en_lo, + (int)DIV_ROUND_UP(timings->tCEA_max, t_clk) - acc_clks, + 0); + cs_setup = min_t(int, cs_setup, CS_SETUP_CNT__VALUE); + + tmp = ioread32(denali->flash_reg + CS_SETUP_CNT); + tmp &= ~CS_SETUP_CNT__VALUE; + tmp |= cs_setup; + iowrite32(tmp, denali->flash_reg + CS_SETUP_CNT); + + return 0; +} /* Initialization code to bring the device up to a known good state */ static void denali_hw_init(struct denali_nand_info *denali) @@ -1241,7 +1152,6 @@ static void denali_hw_init(struct denali_nand_info *denali) /* Should set value for these registers when init */ iowrite32(0, denali->flash_reg + TWO_ROW_ADDR_CYCLES); iowrite32(1, denali->flash_reg + ECC_ENABLE); - denali_nand_timing_set(denali); denali_irq_init(denali); } @@ -1416,17 +1326,6 @@ int denali_init(struct denali_nand_info *denali) struct mtd_info *mtd = nand_to_mtd(chip); int ret; - if (denali->platform == INTEL_CE4100) { - /* - * Due to a silicon limitation, we can only support - * ONFI timing mode 1 and below. - */ - if (onfi_timing_mode < -1 || onfi_timing_mode > 1) { - pr_err("Intel CE4100 only supports ONFI timing mode 1 or below\n"); - return -EINVAL; - } - } - /* allocate a temporary buffer for nand_scan_ident() */ denali->buf.buf = devm_kzalloc(denali->dev, PAGE_SIZE, GFP_DMA | GFP_KERNEL); @@ -1460,6 +1359,10 @@ int denali_init(struct denali_nand_info *denali) chip->onfi_set_features = nand_onfi_get_set_features_notsupp; chip->onfi_get_features = nand_onfi_get_set_features_notsupp; + /* clk rate info is needed for setup_data_interface */ + if (denali->clk_x_rate) + chip->setup_data_interface = denali_setup_data_interface; + /* * scan for NAND devices attached to the controller * this is the first stage in a two step process to register diff --git a/drivers/mtd/nand/denali.h b/drivers/mtd/nand/denali.h index 0e4a8965f6f1..fb473895a79d 100644 --- a/drivers/mtd/nand/denali.h +++ b/drivers/mtd/nand/denali.h @@ -72,11 +72,14 @@ #define GLOBAL_INT_ENABLE 0xf0 #define GLOBAL_INT_EN_FLAG BIT(0) -#define WE_2_RE 0x100 -#define WE_2_RE__VALUE GENMASK(5, 0) +#define TWHR2_AND_WE_2_RE 0x100 +#define TWHR2_AND_WE_2_RE__WE_2_RE GENMASK(5, 0) +#define TWHR2_AND_WE_2_RE__TWHR2 GENMASK(13, 8) -#define ADDR_2_DATA 0x110 -#define ADDR_2_DATA__VALUE GENMASK(5, 0) +#define TCWAW_AND_ADDR_2_DATA 0x110 +/* The width of ADDR_2_DATA is 6 bit for old IP, 7 bit for new IP */ +#define TCWAW_AND_ADDR_2_DATA__ADDR_2_DATA GENMASK(6, 0) +#define TCWAW_AND_ADDR_2_DATA__TCWAW GENMASK(13, 8) #define RE_2_WE 0x120 #define RE_2_WE__VALUE GENMASK(5, 0) @@ -128,6 +131,7 @@ #define CS_SETUP_CNT 0x220 #define CS_SETUP_CNT__VALUE GENMASK(4, 0) +#define CS_SETUP_CNT__TWB GENMASK(17, 12) #define SPARE_AREA_SKIP_BYTES 0x230 #define SPARE_AREA_SKIP_BYTES__VALUE GENMASK(5, 0) @@ -294,16 +298,8 @@ #define CHNL_ACTIVE__CHANNEL2 BIT(2) #define CHNL_ACTIVE__CHANNEL3 BIT(3) -#define FAIL 1 /*failed flag*/ #define PASS 0 /*success flag*/ -#define CLK_X 5 -#define CLK_MULTI 4 - -#define ONFI_BLOOM_TIME 1 -#define MODE5_WORKAROUND 0 - - #define MODE_00 0x00000000 #define MODE_01 0x04000000 #define MODE_10 0x08000000 @@ -316,14 +312,10 @@ struct nand_buf { dma_addr_t dma_buf; }; -#define INTEL_CE4100 1 -#define INTEL_MRST 2 -#define DT 3 - struct denali_nand_info { struct nand_chip nand; + unsigned long clk_x_rate; /* bus interface clock rate */ int flash_bank; /* currently selected chip */ - int platform; struct nand_buf buf; struct device *dev; int page; diff --git a/drivers/mtd/nand/denali_dt.c b/drivers/mtd/nand/denali_dt.c index be598230c108..ebcce50f4005 100644 --- a/drivers/mtd/nand/denali_dt.c +++ b/drivers/mtd/nand/denali_dt.c @@ -96,7 +96,6 @@ static int denali_dt_probe(struct platform_device *pdev) denali->ecc_caps = data->ecc_caps; } - denali->platform = DT; denali->dev = &pdev->dev; denali->irq = platform_get_irq(pdev, 0); if (denali->irq < 0) { @@ -121,6 +120,8 @@ static int denali_dt_probe(struct platform_device *pdev) } clk_prepare_enable(dt->clk); + denali->clk_x_rate = clk_get_rate(dt->clk); + ret = denali_init(denali); if (ret) goto out_disable_clk; diff --git a/drivers/mtd/nand/denali_pci.c b/drivers/mtd/nand/denali_pci.c index 37dc0934c24c..6217525c1000 100644 --- a/drivers/mtd/nand/denali_pci.c +++ b/drivers/mtd/nand/denali_pci.c @@ -19,6 +19,9 @@ #define DENALI_NAND_NAME "denali-nand-pci" +#define INTEL_CE4100 1 +#define INTEL_MRST 2 + /* List of platforms this NAND controller has be integrated into */ static const struct pci_device_id denali_pci_ids[] = { { PCI_VDEVICE(INTEL, 0x0701), INTEL_CE4100 }, @@ -47,13 +50,11 @@ static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) } if (id->driver_data == INTEL_CE4100) { - denali->platform = INTEL_CE4100; mem_base = pci_resource_start(dev, 0); mem_len = pci_resource_len(dev, 1); csr_base = pci_resource_start(dev, 1); csr_len = pci_resource_len(dev, 1); } else { - denali->platform = INTEL_MRST; csr_base = pci_resource_start(dev, 0); csr_len = pci_resource_len(dev, 0); mem_base = pci_resource_start(dev, 1); @@ -69,6 +70,7 @@ static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) denali->irq = dev->irq; denali->ecc_caps = &denali_pci_ecc_caps; denali->nand.ecc.options |= NAND_ECC_MAXIMIZE; + denali->clk_x_rate = 200000000; /* 200 MHz */ ret = pci_request_regions(dev, DENALI_NAND_NAME); if (ret) { -- cgit v1.2.3-59-g8ed1b From c19e31d0a32dd3ee555a536414104acf86b9a884 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 13 Jun 2017 22:45:38 +0900 Subject: mtd: nand: denali: rework interrupt handling Simplify the interrupt handling and fix issues: - The register field view of INTR_EN / INTR_STATUS is different among IP versions. The global macro DENALI_IRQ_ALL is hard-coded for Intel platforms. The interrupt mask should be determined at run-time depending on the running platform. - wait_for_irq() loops do {} while() until interested flags are asserted. The logic can be simplified. - The spin_lock() guard seems too complex (and suspicious in a race condition if wait_for_completion_timeout() bails out by timeout). - denali->complete is reused again and again, but reinit_completion() is missing. Add it. Re-work the code to make it more robust and easier to handle. While we are here, also rename the jump label "failed_req_irq" to more appropriate "disable_irq". Signed-off-by: Masahiro Yamada Signed-off-by: Boris Brezillon --- drivers/mtd/nand/denali.c | 317 +++++++++++++++++----------------------------- drivers/mtd/nand/denali.h | 1 + 2 files changed, 117 insertions(+), 201 deletions(-) diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c index ca2b6b8850ba..2acdc5f42a00 100644 --- a/drivers/mtd/nand/denali.c +++ b/drivers/mtd/nand/denali.c @@ -30,27 +30,14 @@ MODULE_LICENSE("GPL"); #define DENALI_NAND_NAME "denali-nand" -/* - * We define a macro here that combines all interrupts this driver uses into - * a single constant value, for convenience. - */ -#define DENALI_IRQ_ALL (INTR__DMA_CMD_COMP | \ - INTR__ECC_TRANSACTION_DONE | \ - INTR__ECC_ERR | \ - INTR__PROGRAM_FAIL | \ - INTR__LOAD_COMP | \ - INTR__PROGRAM_COMP | \ - INTR__TIME_OUT | \ - INTR__ERASE_FAIL | \ - INTR__RST_COMP | \ - INTR__ERASE_COMP) - /* * indicates whether or not the internal value for the flash bank is * valid or not */ #define CHIP_SELECT_INVALID -1 +#define DENALI_NR_BANKS 4 + /* * The bus interface clock, clk_x, is phase aligned with the core clock. The * clk_x is an integral multiple N of the core clk. The value N is configured @@ -85,14 +72,6 @@ static inline struct denali_nand_info *mtd_to_denali(struct mtd_info *mtd) */ #define BANK(x) ((x) << 24) -/* forward declarations */ -static void clear_interrupts(struct denali_nand_info *denali); -static uint32_t wait_for_irq(struct denali_nand_info *denali, - uint32_t irq_mask); -static void denali_irq_enable(struct denali_nand_info *denali, - uint32_t int_mask); -static uint32_t read_interrupt_status(struct denali_nand_info *denali); - /* * Certain operations for the denali NAND controller use an indexed mode to * read/write data. The operation is performed by writing the address value @@ -143,22 +122,6 @@ static void read_status(struct denali_nand_info *denali) write_byte_to_buf(denali, 0); } -/* resets a specific device connected to the core */ -static void reset_bank(struct denali_nand_info *denali) -{ - uint32_t irq_status; - uint32_t irq_mask = INTR__RST_COMP | INTR__TIME_OUT; - - clear_interrupts(denali); - - iowrite32(1 << denali->flash_bank, denali->flash_reg + DEVICE_RESET); - - irq_status = wait_for_irq(denali, irq_mask); - - if (irq_status & INTR__TIME_OUT) - dev_err(denali->dev, "reset bank failed.\n"); -} - /* Reset the flash controller */ static uint16_t denali_nand_reset(struct denali_nand_info *denali) { @@ -201,169 +164,124 @@ static void detect_max_banks(struct denali_nand_info *denali) denali->max_banks <<= 1; } -static void denali_set_intr_modes(struct denali_nand_info *denali, - uint16_t INT_ENABLE) +static void denali_enable_irq(struct denali_nand_info *denali) { - if (INT_ENABLE) - iowrite32(1, denali->flash_reg + GLOBAL_INT_ENABLE); - else - iowrite32(0, denali->flash_reg + GLOBAL_INT_ENABLE); -} + int i; -/* - * validation function to verify that the controlling software is making - * a valid request - */ -static inline bool is_flash_bank_valid(int flash_bank) -{ - return flash_bank >= 0 && flash_bank < 4; + for (i = 0; i < DENALI_NR_BANKS; i++) + iowrite32(U32_MAX, denali->flash_reg + INTR_EN(i)); + iowrite32(GLOBAL_INT_EN_FLAG, denali->flash_reg + GLOBAL_INT_ENABLE); } -static void denali_irq_init(struct denali_nand_info *denali) +static void denali_disable_irq(struct denali_nand_info *denali) { - uint32_t int_mask; int i; - /* Disable global interrupts */ - denali_set_intr_modes(denali, false); - - int_mask = DENALI_IRQ_ALL; - - /* Clear all status bits */ - for (i = 0; i < denali->max_banks; ++i) - iowrite32(0xFFFF, denali->flash_reg + INTR_STATUS(i)); - - denali_irq_enable(denali, int_mask); + for (i = 0; i < DENALI_NR_BANKS; i++) + iowrite32(0, denali->flash_reg + INTR_EN(i)); + iowrite32(0, denali->flash_reg + GLOBAL_INT_ENABLE); } -static void denali_irq_cleanup(int irqnum, struct denali_nand_info *denali) +static void denali_clear_irq(struct denali_nand_info *denali, + int bank, uint32_t irq_status) { - denali_set_intr_modes(denali, false); + /* write one to clear bits */ + iowrite32(irq_status, denali->flash_reg + INTR_STATUS(bank)); } -static void denali_irq_enable(struct denali_nand_info *denali, - uint32_t int_mask) +static void denali_clear_irq_all(struct denali_nand_info *denali) { int i; - for (i = 0; i < denali->max_banks; ++i) - iowrite32(int_mask, denali->flash_reg + INTR_EN(i)); + for (i = 0; i < DENALI_NR_BANKS; i++) + denali_clear_irq(denali, i, U32_MAX); } -/* - * This function only returns when an interrupt that this driver cares about - * occurs. This is to reduce the overhead of servicing interrupts - */ -static inline uint32_t denali_irq_detected(struct denali_nand_info *denali) +static irqreturn_t denali_isr(int irq, void *dev_id) { - return read_interrupt_status(denali) & DENALI_IRQ_ALL; -} + struct denali_nand_info *denali = dev_id; + irqreturn_t ret = IRQ_NONE; + uint32_t irq_status; + int i; -/* Interrupts are cleared by writing a 1 to the appropriate status bit */ -static inline void clear_interrupt(struct denali_nand_info *denali, - uint32_t irq_mask) -{ - uint32_t intr_status_reg; + spin_lock(&denali->irq_lock); - intr_status_reg = INTR_STATUS(denali->flash_bank); + for (i = 0; i < DENALI_NR_BANKS; i++) { + irq_status = ioread32(denali->flash_reg + INTR_STATUS(i)); + if (irq_status) + ret = IRQ_HANDLED; - iowrite32(irq_mask, denali->flash_reg + intr_status_reg); -} + denali_clear_irq(denali, i, irq_status); -static void clear_interrupts(struct denali_nand_info *denali) -{ - uint32_t status; + if (i != denali->flash_bank) + continue; + + denali->irq_status |= irq_status; - spin_lock_irq(&denali->irq_lock); + if (denali->irq_status & denali->irq_mask) + complete(&denali->complete); + } - status = read_interrupt_status(denali); - clear_interrupt(denali, status); + spin_unlock(&denali->irq_lock); - denali->irq_status = 0x0; - spin_unlock_irq(&denali->irq_lock); + return ret; } -static uint32_t read_interrupt_status(struct denali_nand_info *denali) +static void denali_reset_irq(struct denali_nand_info *denali) { - uint32_t intr_status_reg; - - intr_status_reg = INTR_STATUS(denali->flash_bank); + unsigned long flags; - return ioread32(denali->flash_reg + intr_status_reg); + spin_lock_irqsave(&denali->irq_lock, flags); + denali->irq_status = 0; + denali->irq_mask = 0; + spin_unlock_irqrestore(&denali->irq_lock, flags); } -/* - * This is the interrupt service routine. It handles all interrupts - * sent to this device. Note that on CE4100, this is a shared interrupt. - */ -static irqreturn_t denali_isr(int irq, void *dev_id) +static uint32_t denali_wait_for_irq(struct denali_nand_info *denali, + uint32_t irq_mask) { - struct denali_nand_info *denali = dev_id; + unsigned long time_left, flags; uint32_t irq_status; - irqreturn_t result = IRQ_NONE; - spin_lock(&denali->irq_lock); + spin_lock_irqsave(&denali->irq_lock, flags); - /* check to see if a valid NAND chip has been selected. */ - if (is_flash_bank_valid(denali->flash_bank)) { - /* - * check to see if controller generated the interrupt, - * since this is a shared interrupt - */ - irq_status = denali_irq_detected(denali); - if (irq_status != 0) { - /* handle interrupt */ - /* first acknowledge it */ - clear_interrupt(denali, irq_status); - /* - * store the status in the device context for someone - * to read - */ - denali->irq_status |= irq_status; - /* notify anyone who cares that it happened */ - complete(&denali->complete); - /* tell the OS that we've handled this */ - result = IRQ_HANDLED; - } + irq_status = denali->irq_status; + + if (irq_mask & irq_status) { + /* return immediately if the IRQ has already happened. */ + spin_unlock_irqrestore(&denali->irq_lock, flags); + return irq_status; } - spin_unlock(&denali->irq_lock); - return result; + + denali->irq_mask = irq_mask; + reinit_completion(&denali->complete); + spin_unlock_irqrestore(&denali->irq_lock, flags); + + time_left = wait_for_completion_timeout(&denali->complete, + msecs_to_jiffies(1000)); + if (!time_left) { + dev_err(denali->dev, "timeout while waiting for irq 0x%x\n", + denali->irq_mask); + return 0; + } + + return denali->irq_status; } -static uint32_t wait_for_irq(struct denali_nand_info *denali, uint32_t irq_mask) +/* resets a specific device connected to the core */ +static void reset_bank(struct denali_nand_info *denali) { - unsigned long comp_res; - uint32_t intr_status; - unsigned long timeout = msecs_to_jiffies(1000); + uint32_t irq_status; - do { - comp_res = - wait_for_completion_timeout(&denali->complete, timeout); - spin_lock_irq(&denali->irq_lock); - intr_status = denali->irq_status; - - if (intr_status & irq_mask) { - denali->irq_status &= ~irq_mask; - spin_unlock_irq(&denali->irq_lock); - /* our interrupt was detected */ - break; - } + denali_reset_irq(denali); - /* - * these are not the interrupts you are looking for - - * need to wait again - */ - spin_unlock_irq(&denali->irq_lock); - } while (comp_res != 0); + iowrite32(1 << denali->flash_bank, denali->flash_reg + DEVICE_RESET); - if (comp_res == 0) { - /* timeout */ - pr_err("timeout occurred, status = 0x%x, mask = 0x%x\n", - intr_status, irq_mask); + irq_status = denali_wait_for_irq(denali, + INTR__RST_COMP | INTR__TIME_OUT); - intr_status = 0; - } - return intr_status; + if (!(irq_status & INTR__RST_COMP)) + dev_err(denali->dev, "reset bank failed.\n"); } /* @@ -397,7 +315,7 @@ static int denali_send_pipeline_cmd(struct denali_nand_info *denali, setup_ecc_for_xfer(denali, ecc_en, transfer_spare); - clear_interrupts(denali); + denali_reset_irq(denali); addr = BANK(denali->flash_bank) | denali->page; @@ -479,9 +397,9 @@ static int write_oob_data(struct mtd_info *mtd, uint8_t *buf, int page) write_data_to_flash_mem(denali, buf, mtd->oobsize); /* wait for operation to complete */ - irq_status = wait_for_irq(denali, irq_mask); + irq_status = denali_wait_for_irq(denali, irq_mask); - if (irq_status == 0) { + if (!(irq_status & INTR__PROGRAM_COMP)) { dev_err(denali->dev, "OOB write failed\n"); status = -EIO; } @@ -510,9 +428,9 @@ static void read_oob_data(struct mtd_info *mtd, uint8_t *buf, int page) * can always use status0 bit as the * mask is identical for each bank. */ - irq_status = wait_for_irq(denali, irq_mask); + irq_status = denali_wait_for_irq(denali, irq_mask); - if (irq_status == 0) + if (!(irq_status & INTR__LOAD_COMP)) dev_err(denali->dev, "page on OOB timeout %d\n", denali->page); @@ -620,9 +538,9 @@ static int denali_sw_ecc_fixup(struct mtd_info *mtd, unsigned int err_byte, err_sector, err_device; uint8_t err_cor_value; unsigned int prev_sector = 0; + uint32_t irq_status; - /* read the ECC errors. we'll ignore them for now */ - denali_set_intr_modes(denali, false); + denali_reset_irq(denali); do { err_addr = ioread32(denali->flash_reg + ECC_ERROR_ADDRESS); @@ -674,10 +592,9 @@ static int denali_sw_ecc_fixup(struct mtd_info *mtd, * ECC_TRANSACTION_DONE interrupt, so here just wait for * a while for this interrupt */ - while (!(read_interrupt_status(denali) & INTR__ECC_TRANSACTION_DONE)) - cpu_relax(); - clear_interrupts(denali); - denali_set_intr_modes(denali, true); + irq_status = denali_wait_for_irq(denali, INTR__ECC_TRANSACTION_DONE); + if (!(irq_status & INTR__ECC_TRANSACTION_DONE)) + return -EIO; return max_bitflips; } @@ -778,15 +695,14 @@ static int write_page(struct mtd_info *mtd, struct nand_chip *chip, dma_sync_single_for_device(denali->dev, addr, size, DMA_TO_DEVICE); - clear_interrupts(denali); + denali_reset_irq(denali); denali_enable_dma(denali, true); denali_setup_dma(denali, DENALI_WRITE); /* wait for operation to complete */ - irq_status = wait_for_irq(denali, irq_mask); - - if (irq_status == 0) { + irq_status = denali_wait_for_irq(denali, irq_mask); + if (!(irq_status & INTR__DMA_CMD_COMP)) { dev_err(denali->dev, "timeout on write_page (type = %d)\n", raw_xfer); ret = -EIO; @@ -865,11 +781,11 @@ static int denali_read_page(struct mtd_info *mtd, struct nand_chip *chip, denali_enable_dma(denali, true); dma_sync_single_for_device(denali->dev, addr, size, DMA_FROM_DEVICE); - clear_interrupts(denali); + denali_reset_irq(denali); denali_setup_dma(denali, DENALI_READ); /* wait for operation to complete */ - irq_status = wait_for_irq(denali, irq_mask); + irq_status = denali_wait_for_irq(denali, irq_mask); dma_sync_single_for_cpu(denali->dev, addr, size, DMA_FROM_DEVICE); @@ -901,6 +817,7 @@ static int denali_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, dma_addr_t addr = denali->buf.dma_buf; size_t size = mtd->writesize + mtd->oobsize; uint32_t irq_mask = INTR__DMA_CMD_COMP; + uint32_t irq_status; denali->page = page; @@ -909,11 +826,13 @@ static int denali_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, dma_sync_single_for_device(denali->dev, addr, size, DMA_FROM_DEVICE); - clear_interrupts(denali); + denali_reset_irq(denali); denali_setup_dma(denali, DENALI_READ); /* wait for operation to complete */ - wait_for_irq(denali, irq_mask); + irq_status = denali_wait_for_irq(denali, irq_mask); + if (irq_status & INTR__DMA_CMD_COMP) + return -ETIMEDOUT; dma_sync_single_for_cpu(denali->dev, addr, size, DMA_FROM_DEVICE); @@ -940,9 +859,7 @@ static void denali_select_chip(struct mtd_info *mtd, int chip) { struct denali_nand_info *denali = mtd_to_denali(mtd); - spin_lock_irq(&denali->irq_lock); denali->flash_bank = chip; - spin_unlock_irq(&denali->irq_lock); } static int denali_waitfunc(struct mtd_info *mtd, struct nand_chip *chip) @@ -953,19 +870,19 @@ static int denali_waitfunc(struct mtd_info *mtd, struct nand_chip *chip) static int denali_erase(struct mtd_info *mtd, int page) { struct denali_nand_info *denali = mtd_to_denali(mtd); - uint32_t cmd, irq_status; - clear_interrupts(denali); + denali_reset_irq(denali); /* setup page read request for access type */ cmd = MODE_10 | BANK(denali->flash_bank) | page; index_addr(denali, cmd, 0x1); /* wait for erase to complete or failure to occur */ - irq_status = wait_for_irq(denali, INTR__ERASE_COMP | INTR__ERASE_FAIL); + irq_status = denali_wait_for_irq(denali, + INTR__ERASE_COMP | INTR__ERASE_FAIL); - return irq_status & INTR__ERASE_FAIL ? NAND_STATUS_FAIL : PASS; + return irq_status & INTR__ERASE_COMP ? 0 : NAND_STATUS_FAIL; } static void denali_cmdfunc(struct mtd_info *mtd, unsigned int cmd, int col, @@ -1152,7 +1069,6 @@ static void denali_hw_init(struct denali_nand_info *denali) /* Should set value for these registers when init */ iowrite32(0, denali->flash_reg + TWO_ROW_ADDR_CYCLES); iowrite32(1, denali->flash_reg + ECC_ENABLE); - denali_irq_init(denali); } int denali_calc_ecc_bytes(int step_size, int strength) @@ -1264,9 +1180,6 @@ static void denali_drv_init(struct denali_nand_info *denali) /* indicate that MTD has not selected a valid bank yet */ denali->flash_bank = CHIP_SELECT_INVALID; - - /* initialize our irq_status variable to indicate no interrupts */ - denali->irq_status = 0; } static int denali_multidev_fixup(struct denali_nand_info *denali) @@ -1336,6 +1249,8 @@ int denali_init(struct denali_nand_info *denali) denali_hw_init(denali); denali_drv_init(denali); + denali_clear_irq_all(denali); + /* Request IRQ after all the hardware initialization is finished */ ret = devm_request_irq(denali->dev, denali->irq, denali_isr, IRQF_SHARED, DENALI_NAND_NAME, denali); @@ -1344,8 +1259,8 @@ int denali_init(struct denali_nand_info *denali) return ret; } - /* now that our ISR is registered, we can enable interrupts */ - denali_set_intr_modes(denali, true); + denali_enable_irq(denali); + nand_set_flash_node(chip, denali->dev->of_node); /* Fallback to the default name if DT did not give "label" property */ if (!mtd->name) @@ -1370,7 +1285,7 @@ int denali_init(struct denali_nand_info *denali) */ ret = nand_scan_ident(mtd, denali->max_banks, NULL); if (ret) - goto failed_req_irq; + goto disable_irq; /* allocate the right size buffer now */ devm_kfree(denali->dev, denali->buf.buf); @@ -1379,7 +1294,7 @@ int denali_init(struct denali_nand_info *denali) GFP_KERNEL); if (!denali->buf.buf) { ret = -ENOMEM; - goto failed_req_irq; + goto disable_irq; } ret = dma_set_mask(denali->dev, @@ -1387,7 +1302,7 @@ int denali_init(struct denali_nand_info *denali) 64 : 32)); if (ret) { dev_err(denali->dev, "No usable DMA configuration\n"); - goto failed_req_irq; + goto disable_irq; } denali->buf.dma_buf = dma_map_single(denali->dev, denali->buf.buf, @@ -1396,7 +1311,7 @@ int denali_init(struct denali_nand_info *denali) if (dma_mapping_error(denali->dev, denali->buf.dma_buf)) { dev_err(denali->dev, "Failed to map DMA buffer\n"); ret = -EIO; - goto failed_req_irq; + goto disable_irq; } /* @@ -1420,7 +1335,7 @@ int denali_init(struct denali_nand_info *denali) ret = denali_ecc_setup(mtd, chip, denali); if (ret) { dev_err(denali->dev, "Failed to setup ECC settings.\n"); - goto failed_req_irq; + goto disable_irq; } dev_dbg(denali->dev, @@ -1454,21 +1369,21 @@ int denali_init(struct denali_nand_info *denali) ret = denali_multidev_fixup(denali); if (ret) - goto failed_req_irq; + goto disable_irq; ret = nand_scan_tail(mtd); if (ret) - goto failed_req_irq; + goto disable_irq; ret = mtd_device_register(mtd, NULL, 0); if (ret) { dev_err(denali->dev, "Failed to register MTD: %d\n", ret); - goto failed_req_irq; + goto disable_irq; } return 0; -failed_req_irq: - denali_irq_cleanup(denali->irq, denali); +disable_irq: + denali_disable_irq(denali); return ret; } @@ -1486,7 +1401,7 @@ void denali_remove(struct denali_nand_info *denali) int bufsize = mtd->writesize + mtd->oobsize; nand_release(mtd); - denali_irq_cleanup(denali->irq, denali); + denali_disable_irq(denali); dma_unmap_single(denali->dev, denali->buf.dma_buf, bufsize, DMA_BIDIRECTIONAL); } diff --git a/drivers/mtd/nand/denali.h b/drivers/mtd/nand/denali.h index fb473895a79d..a0ac0f84f8b5 100644 --- a/drivers/mtd/nand/denali.h +++ b/drivers/mtd/nand/denali.h @@ -325,6 +325,7 @@ struct denali_nand_info { /* elements used by ISR */ struct completion complete; spinlock_t irq_lock; + uint32_t irq_mask; uint32_t irq_status; int irq; -- cgit v1.2.3-59-g8ed1b From fa6134e5457d3177b82b35fa4004505f2571150a Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 13 Jun 2017 22:45:39 +0900 Subject: mtd: nand: denali: switch over to cmd_ctrl instead of cmdfunc The NAND_CMD_SET_FEATURES support is missing from denali_cmdfunc(). We also see /* TODO: Read OOB data */ comment. It would be possible to add more commands along with the current implementation, but having ->cmd_ctrl() seems a better approach from the discussion with Boris [1]. Rely on the default ->cmdfunc() from the framework and implement the driver's own ->cmd_ctrl(). This transition also fixes NAND_CMD_STATUS and NAND_CMD_PARAM handling. NAND_CMD_STATUS was just faked by the register read, so the only valid bit was the WP bit. NAND_CMD_PARAM was completely broken; not only the command sent on the bus was NAND_CMD_STATUS instead of NAND_CMD_PARAM, but also the driver was only reading 8 bytes, while the parameter page contains several hundreds of bytes. Also add ->write_byte(), which is needed for write direction commands, ->read/write_buf(16), which will be used some commits later. ->read_word() is not used for now, but the core may call it in the future. Now, this driver can drop nand_onfi_get_set_features_notsupp(). [1] https://lkml.org/lkml/2017/3/15/97 Signed-off-by: Masahiro Yamada Signed-off-by: Boris Brezillon --- drivers/mtd/nand/denali.c | 232 ++++++++++++++++++++++++---------------------- drivers/mtd/nand/denali.h | 2 - 2 files changed, 123 insertions(+), 111 deletions(-) diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c index 2acdc5f42a00..8091ba0916cc 100644 --- a/drivers/mtd/nand/denali.c +++ b/drivers/mtd/nand/denali.c @@ -85,43 +85,6 @@ static void index_addr(struct denali_nand_info *denali, iowrite32(data, denali->flash_mem + 0x10); } -/* Perform an indexed read of the device */ -static void index_addr_read_data(struct denali_nand_info *denali, - uint32_t address, uint32_t *pdata) -{ - iowrite32(address, denali->flash_mem); - *pdata = ioread32(denali->flash_mem + 0x10); -} - -/* - * We need to buffer some data for some of the NAND core routines. - * The operations manage buffering that data. - */ -static void reset_buf(struct denali_nand_info *denali) -{ - denali->buf.head = denali->buf.tail = 0; -} - -static void write_byte_to_buf(struct denali_nand_info *denali, uint8_t byte) -{ - denali->buf.buf[denali->buf.tail++] = byte; -} - -/* reads the status of the device */ -static void read_status(struct denali_nand_info *denali) -{ - uint32_t cmd; - - /* initialize the data buffer to store status */ - reset_buf(denali); - - cmd = ioread32(denali->flash_reg + WRITE_PROTECT); - if (cmd) - write_byte_to_buf(denali, NAND_STATUS_WP); - else - write_byte_to_buf(denali, 0); -} - /* Reset the flash controller */ static uint16_t denali_nand_reset(struct denali_nand_info *denali) { @@ -268,20 +231,16 @@ static uint32_t denali_wait_for_irq(struct denali_nand_info *denali, return denali->irq_status; } -/* resets a specific device connected to the core */ -static void reset_bank(struct denali_nand_info *denali) +static uint32_t denali_check_irq(struct denali_nand_info *denali) { + unsigned long flags; uint32_t irq_status; - denali_reset_irq(denali); - - iowrite32(1 << denali->flash_bank, denali->flash_reg + DEVICE_RESET); - - irq_status = denali_wait_for_irq(denali, - INTR__RST_COMP | INTR__TIME_OUT); + spin_lock_irqsave(&denali->irq_lock, flags); + irq_status = denali->irq_status; + spin_unlock_irqrestore(&denali->irq_lock, flags); - if (!(irq_status & INTR__RST_COMP)) - dev_err(denali->dev, "reset bank failed.\n"); + return irq_status; } /* @@ -302,6 +261,105 @@ static void setup_ecc_for_xfer(struct denali_nand_info *denali, bool ecc_en, iowrite32(transfer_spare_flag, denali->flash_reg + TRANSFER_SPARE_REG); } +static void denali_read_buf(struct mtd_info *mtd, uint8_t *buf, int len) +{ + struct denali_nand_info *denali = mtd_to_denali(mtd); + int i; + + iowrite32(MODE_11 | BANK(denali->flash_bank) | 2, denali->flash_mem); + + for (i = 0; i < len; i++) + buf[i] = ioread32(denali->flash_mem + 0x10); +} + +static void denali_write_buf(struct mtd_info *mtd, const uint8_t *buf, int len) +{ + struct denali_nand_info *denali = mtd_to_denali(mtd); + int i; + + iowrite32(MODE_11 | BANK(denali->flash_bank) | 2, denali->flash_mem); + + for (i = 0; i < len; i++) + iowrite32(buf[i], denali->flash_mem + 0x10); +} + +static void denali_read_buf16(struct mtd_info *mtd, uint8_t *buf, int len) +{ + struct denali_nand_info *denali = mtd_to_denali(mtd); + uint16_t *buf16 = (uint16_t *)buf; + int i; + + iowrite32(MODE_11 | BANK(denali->flash_bank) | 2, denali->flash_mem); + + for (i = 0; i < len / 2; i++) + buf16[i] = ioread32(denali->flash_mem + 0x10); +} + +static void denali_write_buf16(struct mtd_info *mtd, const uint8_t *buf, + int len) +{ + struct denali_nand_info *denali = mtd_to_denali(mtd); + const uint16_t *buf16 = (const uint16_t *)buf; + int i; + + iowrite32(MODE_11 | BANK(denali->flash_bank) | 2, denali->flash_mem); + + for (i = 0; i < len / 2; i++) + iowrite32(buf16[i], denali->flash_mem + 0x10); +} + +static uint8_t denali_read_byte(struct mtd_info *mtd) +{ + uint8_t byte; + + denali_read_buf(mtd, &byte, 1); + + return byte; +} + +static void denali_write_byte(struct mtd_info *mtd, uint8_t byte) +{ + denali_write_buf(mtd, &byte, 1); +} + +static uint16_t denali_read_word(struct mtd_info *mtd) +{ + uint16_t word; + + denali_read_buf16(mtd, (uint8_t *)&word, 2); + + return word; +} + +static void denali_cmd_ctrl(struct mtd_info *mtd, int dat, unsigned int ctrl) +{ + struct denali_nand_info *denali = mtd_to_denali(mtd); + uint32_t type; + + if (ctrl & NAND_CLE) + type = 0; + else if (ctrl & NAND_ALE) + type = 1; + else + return; + + /* + * Some commands are followed by chip->dev_ready or chip->waitfunc. + * irq_status must be cleared here to catch the R/B# interrupt later. + */ + if (ctrl & NAND_CTRL_CHANGE) + denali_reset_irq(denali); + + index_addr(denali, MODE_11 | BANK(denali->flash_bank) | type, dat); +} + +static int denali_dev_ready(struct mtd_info *mtd) +{ + struct denali_nand_info *denali = mtd_to_denali(mtd); + + return !!(denali_check_irq(denali) & INTR__INT_ACT); +} + /* * sends a pipeline command operation to the controller. See the Denali NAND * controller's user guide for more information (section 4.2.3.6). @@ -844,17 +902,6 @@ static int denali_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, return 0; } -static uint8_t denali_read_byte(struct mtd_info *mtd) -{ - struct denali_nand_info *denali = mtd_to_denali(mtd); - uint8_t result = 0xff; - - if (denali->buf.head < denali->buf.tail) - result = denali->buf.buf[denali->buf.head++]; - - return result; -} - static void denali_select_chip(struct mtd_info *mtd, int chip) { struct denali_nand_info *denali = mtd_to_denali(mtd); @@ -864,7 +911,13 @@ static void denali_select_chip(struct mtd_info *mtd, int chip) static int denali_waitfunc(struct mtd_info *mtd, struct nand_chip *chip) { - return 0; + struct denali_nand_info *denali = mtd_to_denali(mtd); + uint32_t irq_status; + + /* R/B# pin transitioned from low to high? */ + irq_status = denali_wait_for_irq(denali, INTR__INT_ACT); + + return irq_status & INTR__INT_ACT ? 0 : NAND_STATUS_FAIL; } static int denali_erase(struct mtd_info *mtd, int page) @@ -885,45 +938,6 @@ static int denali_erase(struct mtd_info *mtd, int page) return irq_status & INTR__ERASE_COMP ? 0 : NAND_STATUS_FAIL; } -static void denali_cmdfunc(struct mtd_info *mtd, unsigned int cmd, int col, - int page) -{ - struct denali_nand_info *denali = mtd_to_denali(mtd); - uint32_t addr, id; - int i; - - switch (cmd) { - case NAND_CMD_STATUS: - read_status(denali); - break; - case NAND_CMD_READID: - case NAND_CMD_PARAM: - reset_buf(denali); - /* - * sometimes ManufactureId read from register is not right - * e.g. some of Micron MT29F32G08QAA MLC NAND chips - * So here we send READID cmd to NAND insteand - */ - addr = MODE_11 | BANK(denali->flash_bank); - index_addr(denali, addr | 0, 0x90); - index_addr(denali, addr | 1, col); - for (i = 0; i < 8; i++) { - index_addr_read_data(denali, addr | 2, &id); - write_byte_to_buf(denali, id); - } - break; - case NAND_CMD_RESET: - reset_bank(denali); - break; - case NAND_CMD_READOOB: - /* TODO: Read OOB data */ - break; - default: - pr_err(": unsupported command received 0x%x\n", cmd); - break; - } -} - #define DIV_ROUND_DOWN_ULL(ll, d) \ ({ unsigned long long _tmp = (ll); do_div(_tmp, d); _tmp; }) @@ -1239,12 +1253,6 @@ int denali_init(struct denali_nand_info *denali) struct mtd_info *mtd = nand_to_mtd(chip); int ret; - /* allocate a temporary buffer for nand_scan_ident() */ - denali->buf.buf = devm_kzalloc(denali->dev, PAGE_SIZE, - GFP_DMA | GFP_KERNEL); - if (!denali->buf.buf) - return -ENOMEM; - mtd->dev.parent = denali->dev; denali_hw_init(denali); denali_drv_init(denali); @@ -1268,11 +1276,12 @@ int denali_init(struct denali_nand_info *denali) /* register the driver with the NAND core subsystem */ chip->select_chip = denali_select_chip; - chip->cmdfunc = denali_cmdfunc; chip->read_byte = denali_read_byte; + chip->write_byte = denali_write_byte; + chip->read_word = denali_read_word; + chip->cmd_ctrl = denali_cmd_ctrl; + chip->dev_ready = denali_dev_ready; chip->waitfunc = denali_waitfunc; - chip->onfi_set_features = nand_onfi_get_set_features_notsupp; - chip->onfi_get_features = nand_onfi_get_set_features_notsupp; /* clk rate info is needed for setup_data_interface */ if (denali->clk_x_rate) @@ -1287,8 +1296,6 @@ int denali_init(struct denali_nand_info *denali) if (ret) goto disable_irq; - /* allocate the right size buffer now */ - devm_kfree(denali->dev, denali->buf.buf); denali->buf.buf = devm_kzalloc(denali->dev, mtd->writesize + mtd->oobsize, GFP_KERNEL); @@ -1358,6 +1365,13 @@ int denali_init(struct denali_nand_info *denali) mtd_set_ooblayout(mtd, &denali_ooblayout_ops); + if (chip->options & NAND_BUSWIDTH_16) { + chip->read_buf = denali_read_buf16; + chip->write_buf = denali_write_buf16; + } else { + chip->read_buf = denali_read_buf; + chip->write_buf = denali_write_buf; + } chip->ecc.options |= NAND_ECC_CUSTOM_PAGE_ACCESS; chip->ecc.read_page = denali_read_page; chip->ecc.read_page_raw = denali_read_page_raw; diff --git a/drivers/mtd/nand/denali.h b/drivers/mtd/nand/denali.h index a0ac0f84f8b5..a84d8784ee98 100644 --- a/drivers/mtd/nand/denali.h +++ b/drivers/mtd/nand/denali.h @@ -306,8 +306,6 @@ #define MODE_11 0x0C000000 struct nand_buf { - int head; - int tail; uint8_t *buf; dma_addr_t dma_buf; }; -- cgit v1.2.3-59-g8ed1b From f486287d2372422d68768c88fe54e80a48aee8ec Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 13 Jun 2017 22:45:40 +0900 Subject: mtd: nand: denali: fix bank reset function to detect the number of chips The nand_scan_ident() iterates over maxchips, and calls nand_reset() for each. This driver currently passes the maximum number of banks (=chip selects) supported by the controller as maxchips. So, maxchips is typically 4 or 8. Usually, less number of NAND chips are connected to the controller. This can be a problem for ONFi devices. Now, this driver implements ->setup_data_interface() hook, so nand_setup_data_interface() issues Set Features (0xEF) command, which waits until the chip returns R/B# response. If no chip there, we know it never happens, but the driver still ends up with waiting for a long time. It will finally bail-out with timeout error and the driver will work with existing chips, but unnecessary wait will give a bad user experience. The denali_nand_reset() polls the INTR__RST_COMP and INTR__TIME_OUT bits, but they are always set even if not NAND chip is connected to that bank. To know the chip existence, INTR__INT_ACT bit must be checked; this flag is set only when R/B# is toggled. Since the Reset (0xFF) command toggles the R/B# pin, this can be used to know the actual number of chips, and update denali->max_banks. Signed-off-by: Masahiro Yamada Signed-off-by: Boris Brezillon --- drivers/mtd/nand/denali.c | 52 +++++++++++++++++++++-------------------------- 1 file changed, 23 insertions(+), 29 deletions(-) diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c index 8091ba0916cc..3169ba58c58a 100644 --- a/drivers/mtd/nand/denali.c +++ b/drivers/mtd/nand/denali.c @@ -85,33 +85,6 @@ static void index_addr(struct denali_nand_info *denali, iowrite32(data, denali->flash_mem + 0x10); } -/* Reset the flash controller */ -static uint16_t denali_nand_reset(struct denali_nand_info *denali) -{ - int i; - - for (i = 0; i < denali->max_banks; i++) - iowrite32(INTR__RST_COMP | INTR__TIME_OUT, - denali->flash_reg + INTR_STATUS(i)); - - for (i = 0; i < denali->max_banks; i++) { - iowrite32(1 << i, denali->flash_reg + DEVICE_RESET); - while (!(ioread32(denali->flash_reg + INTR_STATUS(i)) & - (INTR__RST_COMP | INTR__TIME_OUT))) - cpu_relax(); - if (ioread32(denali->flash_reg + INTR_STATUS(i)) & - INTR__TIME_OUT) - dev_dbg(denali->dev, - "NAND Reset operation timed out on bank %d\n", i); - } - - for (i = 0; i < denali->max_banks; i++) - iowrite32(INTR__RST_COMP | INTR__TIME_OUT, - denali->flash_reg + INTR_STATUS(i)); - - return PASS; -} - /* * Use the configuration feature register to determine the maximum number of * banks that the hardware supports. @@ -1053,7 +1026,28 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr, return 0; } -/* Initialization code to bring the device up to a known good state */ +static void denali_reset_banks(struct denali_nand_info *denali) +{ + int i; + + denali_clear_irq_all(denali); + + for (i = 0; i < denali->max_banks; i++) { + iowrite32(1 << i, denali->flash_reg + DEVICE_RESET); + while (!(ioread32(denali->flash_reg + INTR_STATUS(i)) & + (INTR__RST_COMP | INTR__TIME_OUT))) + cpu_relax(); + if (!(ioread32(denali->flash_reg + INTR_STATUS(i)) & + INTR__INT_ACT)) + break; + } + + dev_dbg(denali->dev, "%d chips connected\n", i); + denali->max_banks = i; + + denali_clear_irq_all(denali); +} + static void denali_hw_init(struct denali_nand_info *denali) { /* @@ -1073,7 +1067,7 @@ static void denali_hw_init(struct denali_nand_info *denali) denali->bbtskipbytes = ioread32(denali->flash_reg + SPARE_AREA_SKIP_BYTES); detect_max_banks(denali); - denali_nand_reset(denali); + denali_reset_banks(denali); iowrite32(0x0F, denali->flash_reg + RB_PIN_ENABLED); iowrite32(CHIP_EN_DONT_CARE__FLAG, denali->flash_reg + CHIP_ENABLE_DONT_CARE); -- cgit v1.2.3-59-g8ed1b From d49f5790278d18fd6b8e474397d9abfdf29a48f2 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 13 Jun 2017 22:45:41 +0900 Subject: mtd: nand: denali: use interrupt instead of polling for bank reset The current bank reset implementation polls the INTR_STATUS register until interested bits are set. This is not good because: - polling simply wastes time-slice of the thread - The while() loop may continue eternally if no bit is set, for example, due to the controller problem. The denali_wait_for_irq() uses wait_for_completion_timeout(), which is safer. We can use interrupt by moving the denali_reset_bank() call below the interrupt setup. Signed-off-by: Masahiro Yamada Signed-off-by: Boris Brezillon --- drivers/mtd/nand/denali.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c index 3169ba58c58a..31d987d26e12 100644 --- a/drivers/mtd/nand/denali.c +++ b/drivers/mtd/nand/denali.c @@ -1028,24 +1028,25 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr, static void denali_reset_banks(struct denali_nand_info *denali) { + u32 irq_status; int i; - denali_clear_irq_all(denali); - for (i = 0; i < denali->max_banks; i++) { - iowrite32(1 << i, denali->flash_reg + DEVICE_RESET); - while (!(ioread32(denali->flash_reg + INTR_STATUS(i)) & - (INTR__RST_COMP | INTR__TIME_OUT))) - cpu_relax(); - if (!(ioread32(denali->flash_reg + INTR_STATUS(i)) & - INTR__INT_ACT)) + denali->flash_bank = i; + + denali_reset_irq(denali); + + iowrite32(DEVICE_RESET__BANK(i), + denali->flash_reg + DEVICE_RESET); + + irq_status = denali_wait_for_irq(denali, + INTR__RST_COMP | INTR__INT_ACT | INTR__TIME_OUT); + if (!(irq_status & INTR__INT_ACT)) break; } dev_dbg(denali->dev, "%d chips connected\n", i); denali->max_banks = i; - - denali_clear_irq_all(denali); } static void denali_hw_init(struct denali_nand_info *denali) @@ -1067,7 +1068,6 @@ static void denali_hw_init(struct denali_nand_info *denali) denali->bbtskipbytes = ioread32(denali->flash_reg + SPARE_AREA_SKIP_BYTES); detect_max_banks(denali); - denali_reset_banks(denali); iowrite32(0x0F, denali->flash_reg + RB_PIN_ENABLED); iowrite32(CHIP_EN_DONT_CARE__FLAG, denali->flash_reg + CHIP_ENABLE_DONT_CARE); @@ -1185,9 +1185,6 @@ static void denali_drv_init(struct denali_nand_info *denali) * element that might be access shared data (interrupt status) */ spin_lock_init(&denali->irq_lock); - - /* indicate that MTD has not selected a valid bank yet */ - denali->flash_bank = CHIP_SELECT_INVALID; } static int denali_multidev_fixup(struct denali_nand_info *denali) @@ -1262,6 +1259,9 @@ int denali_init(struct denali_nand_info *denali) } denali_enable_irq(denali); + denali_reset_banks(denali); + + denali->flash_bank = CHIP_SELECT_INVALID; nand_set_flash_node(chip, denali->dev->of_node); /* Fallback to the default name if DT did not give "label" property */ -- cgit v1.2.3-59-g8ed1b From 2291cb89680637f8f965371973273be312f2cede Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 13 Jun 2017 22:45:42 +0900 Subject: mtd: nand: denali: propagate page to helpers via function argument This driver stores the currently addressed page into denali->page, which is later read out by helper functions. While I am tackling on this driver, I often missed to insert "denali->page = page;" where needed. This makes page_read/write callbacks to get access to a wrong page, which is a bug hard to figure out. Instead, I'd rather pass the page via function argument because the compiler's prototype checks will help to detect bugs. For the same reason, propagate dma_addr to the DMA helpers instead of denali->buf.dma_buf . Signed-off-by: Masahiro Yamada Signed-off-by: Boris Brezillon --- drivers/mtd/nand/denali.c | 58 ++++++++++++++++++++--------------------------- drivers/mtd/nand/denali.h | 1 - 2 files changed, 24 insertions(+), 35 deletions(-) diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c index 31d987d26e12..24849f6bb37b 100644 --- a/drivers/mtd/nand/denali.c +++ b/drivers/mtd/nand/denali.c @@ -337,7 +337,7 @@ static int denali_dev_ready(struct mtd_info *mtd) * sends a pipeline command operation to the controller. See the Denali NAND * controller's user guide for more information (section 4.2.3.6). */ -static int denali_send_pipeline_cmd(struct denali_nand_info *denali, +static int denali_send_pipeline_cmd(struct denali_nand_info *denali, int page, bool ecc_en, bool transfer_spare, int access_type, int op) { @@ -348,7 +348,7 @@ static int denali_send_pipeline_cmd(struct denali_nand_info *denali, denali_reset_irq(denali); - addr = BANK(denali->flash_bank) | denali->page; + addr = BANK(denali->flash_bank) | page; if (op == DENALI_WRITE && access_type != SPARE_ACCESS) { cmd = MODE_01 | addr; @@ -421,9 +421,7 @@ static int write_oob_data(struct mtd_info *mtd, uint8_t *buf, int page) uint32_t irq_mask = INTR__PROGRAM_COMP | INTR__PROGRAM_FAIL; int status = 0; - denali->page = page; - - if (denali_send_pipeline_cmd(denali, false, false, SPARE_ACCESS, + if (denali_send_pipeline_cmd(denali, page, false, false, SPARE_ACCESS, DENALI_WRITE) == PASS) { write_data_to_flash_mem(denali, buf, mtd->oobsize); @@ -448,9 +446,7 @@ static void read_oob_data(struct mtd_info *mtd, uint8_t *buf, int page) uint32_t irq_mask = INTR__LOAD_COMP; uint32_t irq_status, addr, cmd; - denali->page = page; - - if (denali_send_pipeline_cmd(denali, false, true, SPARE_ACCESS, + if (denali_send_pipeline_cmd(denali, page, false, true, SPARE_ACCESS, DENALI_READ) == PASS) { read_data_from_flash_mem(denali, buf, mtd->oobsize); @@ -462,8 +458,7 @@ static void read_oob_data(struct mtd_info *mtd, uint8_t *buf, int page) irq_status = denali_wait_for_irq(denali, irq_mask); if (!(irq_status & INTR__LOAD_COMP)) - dev_err(denali->dev, "page on OOB timeout %d\n", - denali->page); + dev_err(denali->dev, "page on OOB timeout %d\n", page); /* * We set the device back to MAIN_ACCESS here as I observed @@ -472,7 +467,7 @@ static void read_oob_data(struct mtd_info *mtd, uint8_t *buf, int page) * is reliable (according to the MTD test infrastructure) * if you are in MAIN_ACCESS. */ - addr = BANK(denali->flash_bank) | denali->page; + addr = BANK(denali->flash_bank) | page; cmd = MODE_10 | addr; index_addr(denali, cmd, MAIN_ACCESS); } @@ -637,13 +632,13 @@ static void denali_enable_dma(struct denali_nand_info *denali, bool en) ioread32(denali->flash_reg + DMA_ENABLE); } -static void denali_setup_dma64(struct denali_nand_info *denali, int op) +static void denali_setup_dma64(struct denali_nand_info *denali, + dma_addr_t dma_addr, int page, int op) { uint32_t mode; const int page_count = 1; - uint64_t addr = denali->buf.dma_buf; - mode = MODE_10 | BANK(denali->flash_bank) | denali->page; + mode = MODE_10 | BANK(denali->flash_bank) | page; /* DMA is a three step process */ @@ -654,41 +649,42 @@ static void denali_setup_dma64(struct denali_nand_info *denali, int op) index_addr(denali, mode, 0x01002000 | (64 << 16) | op | page_count); /* 2. set memory low address */ - index_addr(denali, mode, addr); + index_addr(denali, mode, dma_addr); /* 3. set memory high address */ - index_addr(denali, mode, addr >> 32); + index_addr(denali, mode, (uint64_t)dma_addr >> 32); } -static void denali_setup_dma32(struct denali_nand_info *denali, int op) +static void denali_setup_dma32(struct denali_nand_info *denali, + dma_addr_t dma_addr, int page, int op) { uint32_t mode; const int page_count = 1; - uint32_t addr = denali->buf.dma_buf; mode = MODE_10 | BANK(denali->flash_bank); /* DMA is a four step process */ /* 1. setup transfer type and # of pages */ - index_addr(denali, mode | denali->page, 0x2000 | op | page_count); + index_addr(denali, mode | page, 0x2000 | op | page_count); /* 2. set memory high address bits 23:8 */ - index_addr(denali, mode | ((addr >> 16) << 8), 0x2200); + index_addr(denali, mode | ((dma_addr >> 16) << 8), 0x2200); /* 3. set memory low address bits 23:8 */ - index_addr(denali, mode | ((addr & 0xffff) << 8), 0x2300); + index_addr(denali, mode | ((dma_addr & 0xffff) << 8), 0x2300); /* 4. interrupt when complete, burst len = 64 bytes */ index_addr(denali, mode | 0x14000, 0x2400); } -static void denali_setup_dma(struct denali_nand_info *denali, int op) +static void denali_setup_dma(struct denali_nand_info *denali, + dma_addr_t dma_addr, int page, int op) { if (denali->caps & DENALI_CAP_DMA_64BIT) - denali_setup_dma64(denali, op); + denali_setup_dma64(denali, dma_addr, page, op); else - denali_setup_dma32(denali, op); + denali_setup_dma32(denali, dma_addr, page, op); } /* @@ -705,8 +701,6 @@ static int write_page(struct mtd_info *mtd, struct nand_chip *chip, uint32_t irq_mask = INTR__DMA_CMD_COMP | INTR__PROGRAM_FAIL; int ret = 0; - denali->page = page; - /* * if it is a raw xfer, we want to disable ecc and send the spare area. * !raw_xfer - enable ecc @@ -729,7 +723,7 @@ static int write_page(struct mtd_info *mtd, struct nand_chip *chip, denali_reset_irq(denali); denali_enable_dma(denali, true); - denali_setup_dma(denali, DENALI_WRITE); + denali_setup_dma(denali, addr, page, DENALI_WRITE); /* wait for operation to complete */ irq_status = denali_wait_for_irq(denali, irq_mask); @@ -805,15 +799,13 @@ static int denali_read_page(struct mtd_info *mtd, struct nand_chip *chip, unsigned long uncor_ecc_flags = 0; int stat = 0; - denali->page = page; - setup_ecc_for_xfer(denali, true, false); denali_enable_dma(denali, true); dma_sync_single_for_device(denali->dev, addr, size, DMA_FROM_DEVICE); denali_reset_irq(denali); - denali_setup_dma(denali, DENALI_READ); + denali_setup_dma(denali, addr, page, DENALI_READ); /* wait for operation to complete */ irq_status = denali_wait_for_irq(denali, irq_mask); @@ -832,7 +824,7 @@ static int denali_read_page(struct mtd_info *mtd, struct nand_chip *chip, return stat; if (uncor_ecc_flags) { - read_oob_data(mtd, chip->oob_poi, denali->page); + read_oob_data(mtd, chip->oob_poi, page); stat = denali_check_erased_page(mtd, chip, buf, uncor_ecc_flags, stat); @@ -850,15 +842,13 @@ static int denali_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, uint32_t irq_mask = INTR__DMA_CMD_COMP; uint32_t irq_status; - denali->page = page; - setup_ecc_for_xfer(denali, false, true); denali_enable_dma(denali, true); dma_sync_single_for_device(denali->dev, addr, size, DMA_FROM_DEVICE); denali_reset_irq(denali); - denali_setup_dma(denali, DENALI_READ); + denali_setup_dma(denali, addr, page, DENALI_READ); /* wait for operation to complete */ irq_status = denali_wait_for_irq(denali, irq_mask); diff --git a/drivers/mtd/nand/denali.h b/drivers/mtd/nand/denali.h index a84d8784ee98..ad2223d179d0 100644 --- a/drivers/mtd/nand/denali.h +++ b/drivers/mtd/nand/denali.h @@ -316,7 +316,6 @@ struct denali_nand_info { int flash_bank; /* currently selected chip */ struct nand_buf buf; struct device *dev; - int page; void __iomem *flash_reg; /* Register Interface */ void __iomem *flash_mem; /* Host Data/Command Interface */ -- cgit v1.2.3-59-g8ed1b From 00fc615fd671877cd6e52b556a9d097223b6804e Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 13 Jun 2017 22:45:43 +0900 Subject: mtd: nand: denali: merge struct nand_buf into struct denali_nand_info Now struct nand_buf has only two members, so I see no reason for the separation. Signed-off-by: Masahiro Yamada Signed-off-by: Boris Brezillon --- drivers/mtd/nand/denali.c | 29 ++++++++++++++--------------- drivers/mtd/nand/denali.h | 8 ++------ 2 files changed, 16 insertions(+), 21 deletions(-) diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c index 24849f6bb37b..4ba8ad610381 100644 --- a/drivers/mtd/nand/denali.c +++ b/drivers/mtd/nand/denali.c @@ -695,7 +695,7 @@ static int write_page(struct mtd_info *mtd, struct nand_chip *chip, const uint8_t *buf, int page, bool raw_xfer) { struct denali_nand_info *denali = mtd_to_denali(mtd); - dma_addr_t addr = denali->buf.dma_buf; + dma_addr_t addr = denali->dma_addr; size_t size = mtd->writesize + mtd->oobsize; uint32_t irq_status; uint32_t irq_mask = INTR__DMA_CMD_COMP | INTR__PROGRAM_FAIL; @@ -709,11 +709,11 @@ static int write_page(struct mtd_info *mtd, struct nand_chip *chip, setup_ecc_for_xfer(denali, !raw_xfer, raw_xfer); /* copy buffer into DMA buffer */ - memcpy(denali->buf.buf, buf, mtd->writesize); + memcpy(denali->buf, buf, mtd->writesize); if (raw_xfer) { /* transfer the data to the spare area */ - memcpy(denali->buf.buf + mtd->writesize, + memcpy(denali->buf + mtd->writesize, chip->oob_poi, mtd->oobsize); } @@ -790,7 +790,7 @@ static int denali_read_page(struct mtd_info *mtd, struct nand_chip *chip, uint8_t *buf, int oob_required, int page) { struct denali_nand_info *denali = mtd_to_denali(mtd); - dma_addr_t addr = denali->buf.dma_buf; + dma_addr_t addr = denali->dma_addr; size_t size = mtd->writesize + mtd->oobsize; uint32_t irq_status; uint32_t irq_mask = denali->caps & DENALI_CAP_HW_ECC_FIXUP ? @@ -812,7 +812,7 @@ static int denali_read_page(struct mtd_info *mtd, struct nand_chip *chip, dma_sync_single_for_cpu(denali->dev, addr, size, DMA_FROM_DEVICE); - memcpy(buf, denali->buf.buf, mtd->writesize); + memcpy(buf, denali->buf, mtd->writesize); if (denali->caps & DENALI_CAP_HW_ECC_FIXUP) stat = denali_hw_ecc_fixup(mtd, denali, &uncor_ecc_flags); @@ -837,7 +837,7 @@ static int denali_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, uint8_t *buf, int oob_required, int page) { struct denali_nand_info *denali = mtd_to_denali(mtd); - dma_addr_t addr = denali->buf.dma_buf; + dma_addr_t addr = denali->dma_addr; size_t size = mtd->writesize + mtd->oobsize; uint32_t irq_mask = INTR__DMA_CMD_COMP; uint32_t irq_status; @@ -859,8 +859,8 @@ static int denali_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, denali_enable_dma(denali, false); - memcpy(buf, denali->buf.buf, mtd->writesize); - memcpy(chip->oob_poi, denali->buf.buf + mtd->writesize, mtd->oobsize); + memcpy(buf, denali->buf, mtd->writesize); + memcpy(chip->oob_poi, denali->buf + mtd->writesize, mtd->oobsize); return 0; } @@ -1280,10 +1280,9 @@ int denali_init(struct denali_nand_info *denali) if (ret) goto disable_irq; - denali->buf.buf = devm_kzalloc(denali->dev, - mtd->writesize + mtd->oobsize, - GFP_KERNEL); - if (!denali->buf.buf) { + denali->buf = devm_kzalloc(denali->dev, mtd->writesize + mtd->oobsize, + GFP_KERNEL); + if (!denali->buf) { ret = -ENOMEM; goto disable_irq; } @@ -1296,10 +1295,10 @@ int denali_init(struct denali_nand_info *denali) goto disable_irq; } - denali->buf.dma_buf = dma_map_single(denali->dev, denali->buf.buf, + denali->dma_addr = dma_map_single(denali->dev, denali->buf, mtd->writesize + mtd->oobsize, DMA_BIDIRECTIONAL); - if (dma_mapping_error(denali->dev, denali->buf.dma_buf)) { + if (dma_mapping_error(denali->dev, denali->dma_addr)) { dev_err(denali->dev, "Failed to map DMA buffer\n"); ret = -EIO; goto disable_irq; @@ -1400,7 +1399,7 @@ void denali_remove(struct denali_nand_info *denali) nand_release(mtd); denali_disable_irq(denali); - dma_unmap_single(denali->dev, denali->buf.dma_buf, bufsize, + dma_unmap_single(denali->dev, denali->dma_addr, bufsize, DMA_BIDIRECTIONAL); } EXPORT_SYMBOL(denali_remove); diff --git a/drivers/mtd/nand/denali.h b/drivers/mtd/nand/denali.h index ad2223d179d0..1b991d3016f8 100644 --- a/drivers/mtd/nand/denali.h +++ b/drivers/mtd/nand/denali.h @@ -305,16 +305,10 @@ #define MODE_10 0x08000000 #define MODE_11 0x0C000000 -struct nand_buf { - uint8_t *buf; - dma_addr_t dma_buf; -}; - struct denali_nand_info { struct nand_chip nand; unsigned long clk_x_rate; /* bus interface clock rate */ int flash_bank; /* currently selected chip */ - struct nand_buf buf; struct device *dev; void __iomem *flash_reg; /* Register Interface */ void __iomem *flash_mem; /* Host Data/Command Interface */ @@ -326,6 +320,8 @@ struct denali_nand_info { uint32_t irq_status; int irq; + void *buf; + dma_addr_t dma_addr; int devnum; /* represent how many nands connected */ int bbtskipbytes; int max_banks; -- cgit v1.2.3-59-g8ed1b From 96a376bd93bb76945fce61e2e17ddc7f152b31c6 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 13 Jun 2017 22:45:44 +0900 Subject: mtd: nand: denali: use flag instead of register macro for direction It is not a good idea to re-use macros that represent a specific register bit field for the transfer direction. It is true that bit 8 indicates the direction for the MAP10 pipeline operation and the data DMA operation, but this is not valid across the IP. Use a simple flag (write: 1, read: 0) for the direction. Signed-off-by: Masahiro Yamada Signed-off-by: Boris Brezillon --- drivers/mtd/nand/denali.c | 36 +++++++++++++++++------------------- 1 file changed, 17 insertions(+), 19 deletions(-) diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c index 4ba8ad610381..3b7d2f81aa5b 100644 --- a/drivers/mtd/nand/denali.c +++ b/drivers/mtd/nand/denali.c @@ -63,9 +63,6 @@ static inline struct denali_nand_info *mtd_to_denali(struct mtd_info *mtd) #define MAIN_ACCESS 0x42 #define MAIN_SPARE_ACCESS 0x43 -#define DENALI_READ 0 -#define DENALI_WRITE 0x100 - /* * this is a helper macro that allows us to * format the bank into the proper bits for the controller @@ -339,7 +336,7 @@ static int denali_dev_ready(struct mtd_info *mtd) */ static int denali_send_pipeline_cmd(struct denali_nand_info *denali, int page, bool ecc_en, bool transfer_spare, - int access_type, int op) + int access_type, int write) { int status = PASS; uint32_t addr, cmd; @@ -350,17 +347,17 @@ static int denali_send_pipeline_cmd(struct denali_nand_info *denali, int page, addr = BANK(denali->flash_bank) | page; - if (op == DENALI_WRITE && access_type != SPARE_ACCESS) { + if (write && access_type != SPARE_ACCESS) { cmd = MODE_01 | addr; iowrite32(cmd, denali->flash_mem); - } else if (op == DENALI_WRITE && access_type == SPARE_ACCESS) { + } else if (write && access_type == SPARE_ACCESS) { /* read spare area */ cmd = MODE_10 | addr; index_addr(denali, cmd, access_type); cmd = MODE_01 | addr; iowrite32(cmd, denali->flash_mem); - } else if (op == DENALI_READ) { + } else { /* setup page read request for access type */ cmd = MODE_10 | addr; index_addr(denali, cmd, access_type); @@ -422,7 +419,7 @@ static int write_oob_data(struct mtd_info *mtd, uint8_t *buf, int page) int status = 0; if (denali_send_pipeline_cmd(denali, page, false, false, SPARE_ACCESS, - DENALI_WRITE) == PASS) { + 1) == PASS) { write_data_to_flash_mem(denali, buf, mtd->oobsize); /* wait for operation to complete */ @@ -447,7 +444,7 @@ static void read_oob_data(struct mtd_info *mtd, uint8_t *buf, int page) uint32_t irq_status, addr, cmd; if (denali_send_pipeline_cmd(denali, page, false, true, SPARE_ACCESS, - DENALI_READ) == PASS) { + 0) == PASS) { read_data_from_flash_mem(denali, buf, mtd->oobsize); /* @@ -633,7 +630,7 @@ static void denali_enable_dma(struct denali_nand_info *denali, bool en) } static void denali_setup_dma64(struct denali_nand_info *denali, - dma_addr_t dma_addr, int page, int op) + dma_addr_t dma_addr, int page, int write) { uint32_t mode; const int page_count = 1; @@ -646,7 +643,8 @@ static void denali_setup_dma64(struct denali_nand_info *denali, * 1. setup transfer type, interrupt when complete, * burst len = 64 bytes, the number of pages */ - index_addr(denali, mode, 0x01002000 | (64 << 16) | op | page_count); + index_addr(denali, mode, + 0x01002000 | (64 << 16) | (write << 8) | page_count); /* 2. set memory low address */ index_addr(denali, mode, dma_addr); @@ -656,7 +654,7 @@ static void denali_setup_dma64(struct denali_nand_info *denali, } static void denali_setup_dma32(struct denali_nand_info *denali, - dma_addr_t dma_addr, int page, int op) + dma_addr_t dma_addr, int page, int write) { uint32_t mode; const int page_count = 1; @@ -666,7 +664,7 @@ static void denali_setup_dma32(struct denali_nand_info *denali, /* DMA is a four step process */ /* 1. setup transfer type and # of pages */ - index_addr(denali, mode | page, 0x2000 | op | page_count); + index_addr(denali, mode | page, 0x2000 | (write << 8) | page_count); /* 2. set memory high address bits 23:8 */ index_addr(denali, mode | ((dma_addr >> 16) << 8), 0x2200); @@ -679,12 +677,12 @@ static void denali_setup_dma32(struct denali_nand_info *denali, } static void denali_setup_dma(struct denali_nand_info *denali, - dma_addr_t dma_addr, int page, int op) + dma_addr_t dma_addr, int page, int write) { if (denali->caps & DENALI_CAP_DMA_64BIT) - denali_setup_dma64(denali, dma_addr, page, op); + denali_setup_dma64(denali, dma_addr, page, write); else - denali_setup_dma32(denali, dma_addr, page, op); + denali_setup_dma32(denali, dma_addr, page, write); } /* @@ -723,7 +721,7 @@ static int write_page(struct mtd_info *mtd, struct nand_chip *chip, denali_reset_irq(denali); denali_enable_dma(denali, true); - denali_setup_dma(denali, addr, page, DENALI_WRITE); + denali_setup_dma(denali, addr, page, 1); /* wait for operation to complete */ irq_status = denali_wait_for_irq(denali, irq_mask); @@ -805,7 +803,7 @@ static int denali_read_page(struct mtd_info *mtd, struct nand_chip *chip, dma_sync_single_for_device(denali->dev, addr, size, DMA_FROM_DEVICE); denali_reset_irq(denali); - denali_setup_dma(denali, addr, page, DENALI_READ); + denali_setup_dma(denali, addr, page, 0); /* wait for operation to complete */ irq_status = denali_wait_for_irq(denali, irq_mask); @@ -848,7 +846,7 @@ static int denali_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, dma_sync_single_for_device(denali->dev, addr, size, DMA_FROM_DEVICE); denali_reset_irq(denali); - denali_setup_dma(denali, addr, page, DENALI_READ); + denali_setup_dma(denali, addr, page, 0); /* wait for operation to complete */ irq_status = denali_wait_for_irq(denali, irq_mask); -- cgit v1.2.3-59-g8ed1b From 26d266e10e5eb59cfbcc47922655dc3149e1bd59 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 13 Jun 2017 22:45:45 +0900 Subject: mtd: nand: denali: fix raw and oob accessors for syndrome page layout The Denali IP adopts the syndrome page layout; payload and ECC are interleaved, with BBM area always placed at the beginning of OOB. The figure below shows the page organization for ecc->steps == 2: |----------------| |-----------| | | | | | | | | | Payload0 | | | | | | | | | | | | | | | |----------------| | in-band | | ECC0 | | area | |----------------| | | | | | | | | | | | Payload1 | | | | | | | | | | | |----------------| |-----------| | BBM | | | |----------------| | | |Payload1 (cont.)| | | |----------------| |out-of-band| | ECC1 | | area | |----------------| | | | OOB free | | | |----------------| |-----------| The current raw / oob accessors do not take that into consideration, so in-band and out-of-band data are transferred as stored in the device. In the case above, in-band: Payload0 + ECC0 + Payload1(partial) out-of-band: BBM + Payload1(cont.) + ECC1 + OOB-free This is wrong. As the comment block of struct nand_ecc_ctrl says, driver callbacks must hide the specific layout used by the hardware and always return contiguous in-band and out-of-band data. The current implementation is completely screwed-up, so read/write callbacks must be re-worked. Also, it is reasonable to support PIO transfer in case DMA may not work for some reasons. Actually, the Data DMA may not be equipped depending on the configuration of the RTL. This can be checked by reading the bit 4 of the FEATURES register. Even if the controller has the DMA support, dma_set_mask() and dma_map_single() could fail. In either case, the driver can fall back to the PIO transfer. Slower access would be better than giving up. Signed-off-by: Masahiro Yamada Signed-off-by: Boris Brezillon --- drivers/mtd/nand/denali.c | 610 ++++++++++++++++++++++++++-------------------- drivers/mtd/nand/denali.h | 3 +- 2 files changed, 344 insertions(+), 269 deletions(-) diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c index 3b7d2f81aa5b..ed0044c560e5 100644 --- a/drivers/mtd/nand/denali.c +++ b/drivers/mtd/nand/denali.c @@ -55,14 +55,6 @@ static inline struct denali_nand_info *mtd_to_denali(struct mtd_info *mtd) return container_of(mtd_to_nand(mtd), struct denali_nand_info, nand); } -/* - * These constants are defined by the driver to enable common driver - * configuration options. - */ -#define SPARE_ACCESS 0x41 -#define MAIN_ACCESS 0x42 -#define MAIN_SPARE_ACCESS 0x43 - /* * this is a helper macro that allows us to * format the bank into the proper bits for the controller @@ -330,146 +322,6 @@ static int denali_dev_ready(struct mtd_info *mtd) return !!(denali_check_irq(denali) & INTR__INT_ACT); } -/* - * sends a pipeline command operation to the controller. See the Denali NAND - * controller's user guide for more information (section 4.2.3.6). - */ -static int denali_send_pipeline_cmd(struct denali_nand_info *denali, int page, - bool ecc_en, bool transfer_spare, - int access_type, int write) -{ - int status = PASS; - uint32_t addr, cmd; - - setup_ecc_for_xfer(denali, ecc_en, transfer_spare); - - denali_reset_irq(denali); - - addr = BANK(denali->flash_bank) | page; - - if (write && access_type != SPARE_ACCESS) { - cmd = MODE_01 | addr; - iowrite32(cmd, denali->flash_mem); - } else if (write && access_type == SPARE_ACCESS) { - /* read spare area */ - cmd = MODE_10 | addr; - index_addr(denali, cmd, access_type); - - cmd = MODE_01 | addr; - iowrite32(cmd, denali->flash_mem); - } else { - /* setup page read request for access type */ - cmd = MODE_10 | addr; - index_addr(denali, cmd, access_type); - - cmd = MODE_01 | addr; - iowrite32(cmd, denali->flash_mem); - } - return status; -} - -/* helper function that simply writes a buffer to the flash */ -static int write_data_to_flash_mem(struct denali_nand_info *denali, - const uint8_t *buf, int len) -{ - uint32_t *buf32; - int i; - - /* - * verify that the len is a multiple of 4. - * see comment in read_data_from_flash_mem() - */ - BUG_ON((len % 4) != 0); - - /* write the data to the flash memory */ - buf32 = (uint32_t *)buf; - for (i = 0; i < len / 4; i++) - iowrite32(*buf32++, denali->flash_mem + 0x10); - return i * 4; /* intent is to return the number of bytes read */ -} - -/* helper function that simply reads a buffer from the flash */ -static int read_data_from_flash_mem(struct denali_nand_info *denali, - uint8_t *buf, int len) -{ - uint32_t *buf32; - int i; - - /* - * we assume that len will be a multiple of 4, if not it would be nice - * to know about it ASAP rather than have random failures... - * This assumption is based on the fact that this function is designed - * to be used to read flash pages, which are typically multiples of 4. - */ - BUG_ON((len % 4) != 0); - - /* transfer the data from the flash */ - buf32 = (uint32_t *)buf; - for (i = 0; i < len / 4; i++) - *buf32++ = ioread32(denali->flash_mem + 0x10); - return i * 4; /* intent is to return the number of bytes read */ -} - -/* writes OOB data to the device */ -static int write_oob_data(struct mtd_info *mtd, uint8_t *buf, int page) -{ - struct denali_nand_info *denali = mtd_to_denali(mtd); - uint32_t irq_status; - uint32_t irq_mask = INTR__PROGRAM_COMP | INTR__PROGRAM_FAIL; - int status = 0; - - if (denali_send_pipeline_cmd(denali, page, false, false, SPARE_ACCESS, - 1) == PASS) { - write_data_to_flash_mem(denali, buf, mtd->oobsize); - - /* wait for operation to complete */ - irq_status = denali_wait_for_irq(denali, irq_mask); - - if (!(irq_status & INTR__PROGRAM_COMP)) { - dev_err(denali->dev, "OOB write failed\n"); - status = -EIO; - } - } else { - dev_err(denali->dev, "unable to send pipeline command\n"); - status = -EIO; - } - return status; -} - -/* reads OOB data from the device */ -static void read_oob_data(struct mtd_info *mtd, uint8_t *buf, int page) -{ - struct denali_nand_info *denali = mtd_to_denali(mtd); - uint32_t irq_mask = INTR__LOAD_COMP; - uint32_t irq_status, addr, cmd; - - if (denali_send_pipeline_cmd(denali, page, false, true, SPARE_ACCESS, - 0) == PASS) { - read_data_from_flash_mem(denali, buf, mtd->oobsize); - - /* - * wait for command to be accepted - * can always use status0 bit as the - * mask is identical for each bank. - */ - irq_status = denali_wait_for_irq(denali, irq_mask); - - if (!(irq_status & INTR__LOAD_COMP)) - dev_err(denali->dev, "page on OOB timeout %d\n", page); - - /* - * We set the device back to MAIN_ACCESS here as I observed - * instability with the controller if you do a block erase - * and the last transaction was a SPARE_ACCESS. Block erase - * is reliable (according to the MTD test infrastructure) - * if you are in MAIN_ACCESS. - */ - addr = BANK(denali->flash_bank) | page; - cmd = MODE_10 | addr; - index_addr(denali, cmd, MAIN_ACCESS); - } -} - static int denali_check_erased_page(struct mtd_info *mtd, struct nand_chip *chip, uint8_t *buf, unsigned long uncor_ecc_flags, @@ -685,144 +537,303 @@ static void denali_setup_dma(struct denali_nand_info *denali, denali_setup_dma32(denali, dma_addr, page, write); } -/* - * writes a page. user specifies type, and this function handles the - * configuration details. - */ -static int write_page(struct mtd_info *mtd, struct nand_chip *chip, - const uint8_t *buf, int page, bool raw_xfer) +static int denali_pio_read(struct denali_nand_info *denali, void *buf, + size_t size, int page, int raw) { - struct denali_nand_info *denali = mtd_to_denali(mtd); - dma_addr_t addr = denali->dma_addr; - size_t size = mtd->writesize + mtd->oobsize; - uint32_t irq_status; - uint32_t irq_mask = INTR__DMA_CMD_COMP | INTR__PROGRAM_FAIL; - int ret = 0; + uint32_t addr = BANK(denali->flash_bank) | page; + uint32_t *buf32 = (uint32_t *)buf; + uint32_t irq_status, ecc_err_mask; + int i; - /* - * if it is a raw xfer, we want to disable ecc and send the spare area. - * !raw_xfer - enable ecc - * raw_xfer - transfer spare - */ - setup_ecc_for_xfer(denali, !raw_xfer, raw_xfer); + if (denali->caps & DENALI_CAP_HW_ECC_FIXUP) + ecc_err_mask = INTR__ECC_UNCOR_ERR; + else + ecc_err_mask = INTR__ECC_ERR; - /* copy buffer into DMA buffer */ - memcpy(denali->buf, buf, mtd->writesize); + denali_reset_irq(denali); - if (raw_xfer) { - /* transfer the data to the spare area */ - memcpy(denali->buf + mtd->writesize, - chip->oob_poi, - mtd->oobsize); - } + iowrite32(MODE_01 | addr, denali->flash_mem); + for (i = 0; i < size / 4; i++) + *buf32++ = ioread32(denali->flash_mem + 0x10); + + irq_status = denali_wait_for_irq(denali, INTR__PAGE_XFER_INC); + if (!(irq_status & INTR__PAGE_XFER_INC)) + return -EIO; - dma_sync_single_for_device(denali->dev, addr, size, DMA_TO_DEVICE); + return irq_status & ecc_err_mask ? -EBADMSG : 0; +} + +static int denali_pio_write(struct denali_nand_info *denali, + const void *buf, size_t size, int page, int raw) +{ + uint32_t addr = BANK(denali->flash_bank) | page; + const uint32_t *buf32 = (uint32_t *)buf; + uint32_t irq_status; + int i; denali_reset_irq(denali); + + iowrite32(MODE_01 | addr, denali->flash_mem); + for (i = 0; i < size / 4; i++) + iowrite32(*buf32++, denali->flash_mem + 0x10); + + irq_status = denali_wait_for_irq(denali, + INTR__PROGRAM_COMP | INTR__PROGRAM_FAIL); + if (!(irq_status & INTR__PROGRAM_COMP)) + return -EIO; + + return 0; +} + +static int denali_pio_xfer(struct denali_nand_info *denali, void *buf, + size_t size, int page, int raw, int write) +{ + if (write) + return denali_pio_write(denali, buf, size, page, raw); + else + return denali_pio_read(denali, buf, size, page, raw); +} + +static int denali_dma_xfer(struct denali_nand_info *denali, void *buf, + size_t size, int page, int raw, int write) +{ + dma_addr_t dma_addr = denali->dma_addr; + uint32_t irq_mask, irq_status, ecc_err_mask; + enum dma_data_direction dir = write ? DMA_TO_DEVICE : DMA_FROM_DEVICE; + int ret = 0; + + dma_sync_single_for_device(denali->dev, dma_addr, size, dir); + + if (write) { + /* + * INTR__PROGRAM_COMP is never asserted for the DMA transfer. + * We can use INTR__DMA_CMD_COMP instead. This flag is asserted + * when the page program is completed. + */ + irq_mask = INTR__DMA_CMD_COMP | INTR__PROGRAM_FAIL; + ecc_err_mask = 0; + } else if (denali->caps & DENALI_CAP_HW_ECC_FIXUP) { + irq_mask = INTR__DMA_CMD_COMP; + ecc_err_mask = INTR__ECC_UNCOR_ERR; + } else { + irq_mask = INTR__DMA_CMD_COMP; + ecc_err_mask = INTR__ECC_ERR; + } + denali_enable_dma(denali, true); - denali_setup_dma(denali, addr, page, 1); + denali_reset_irq(denali); + denali_setup_dma(denali, dma_addr, page, write); /* wait for operation to complete */ irq_status = denali_wait_for_irq(denali, irq_mask); - if (!(irq_status & INTR__DMA_CMD_COMP)) { - dev_err(denali->dev, "timeout on write_page (type = %d)\n", - raw_xfer); + if (!(irq_status & INTR__DMA_CMD_COMP)) ret = -EIO; - } + else if (irq_status & ecc_err_mask) + ret = -EBADMSG; denali_enable_dma(denali, false); - dma_sync_single_for_cpu(denali->dev, addr, size, DMA_TO_DEVICE); + dma_sync_single_for_cpu(denali->dev, dma_addr, size, dir); return ret; } -/* NAND core entry points */ - -/* - * this is the callback that the NAND core calls to write a page. Since - * writing a page with ECC or without is similar, all the work is done - * by write_page above. - */ -static int denali_write_page(struct mtd_info *mtd, struct nand_chip *chip, - const uint8_t *buf, int oob_required, int page) +static int denali_data_xfer(struct denali_nand_info *denali, void *buf, + size_t size, int page, int raw, int write) { - /* - * for regular page writes, we let HW handle all the ECC - * data written to the device. - */ - return write_page(mtd, chip, buf, page, false); + setup_ecc_for_xfer(denali, !raw, raw); + + if (denali->dma_avail) + return denali_dma_xfer(denali, buf, size, page, raw, write); + else + return denali_pio_xfer(denali, buf, size, page, raw, write); } -/* - * This is the callback that the NAND core calls to write a page without ECC. - * raw access is similar to ECC page writes, so all the work is done in the - * write_page() function above. - */ -static int denali_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip, - const uint8_t *buf, int oob_required, - int page) +static void denali_oob_xfer(struct mtd_info *mtd, struct nand_chip *chip, + int page, int write) { - /* - * for raw page writes, we want to disable ECC and simply write - * whatever data is in the buffer. - */ - return write_page(mtd, chip, buf, page, true); + struct denali_nand_info *denali = mtd_to_denali(mtd); + unsigned int start_cmd = write ? NAND_CMD_SEQIN : NAND_CMD_READ0; + unsigned int rnd_cmd = write ? NAND_CMD_RNDIN : NAND_CMD_RNDOUT; + int writesize = mtd->writesize; + int oobsize = mtd->oobsize; + uint8_t *bufpoi = chip->oob_poi; + int ecc_steps = chip->ecc.steps; + int ecc_size = chip->ecc.size; + int ecc_bytes = chip->ecc.bytes; + int oob_skip = denali->bbtskipbytes; + size_t size = writesize + oobsize; + int i, pos, len; + + /* BBM at the beginning of the OOB area */ + chip->cmdfunc(mtd, start_cmd, writesize, page); + if (write) + chip->write_buf(mtd, bufpoi, oob_skip); + else + chip->read_buf(mtd, bufpoi, oob_skip); + bufpoi += oob_skip; + + /* OOB ECC */ + for (i = 0; i < ecc_steps; i++) { + pos = ecc_size + i * (ecc_size + ecc_bytes); + len = ecc_bytes; + + if (pos >= writesize) + pos += oob_skip; + else if (pos + len > writesize) + len = writesize - pos; + + chip->cmdfunc(mtd, rnd_cmd, pos, -1); + if (write) + chip->write_buf(mtd, bufpoi, len); + else + chip->read_buf(mtd, bufpoi, len); + bufpoi += len; + if (len < ecc_bytes) { + len = ecc_bytes - len; + chip->cmdfunc(mtd, rnd_cmd, writesize + oob_skip, -1); + if (write) + chip->write_buf(mtd, bufpoi, len); + else + chip->read_buf(mtd, bufpoi, len); + bufpoi += len; + } + } + + /* OOB free */ + len = oobsize - (bufpoi - chip->oob_poi); + chip->cmdfunc(mtd, rnd_cmd, size - len, -1); + if (write) + chip->write_buf(mtd, bufpoi, len); + else + chip->read_buf(mtd, bufpoi, len); } -static int denali_write_oob(struct mtd_info *mtd, struct nand_chip *chip, - int page) +static int denali_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, + uint8_t *buf, int oob_required, int page) { - return write_oob_data(mtd, chip->oob_poi, page); + struct denali_nand_info *denali = mtd_to_denali(mtd); + int writesize = mtd->writesize; + int oobsize = mtd->oobsize; + int ecc_steps = chip->ecc.steps; + int ecc_size = chip->ecc.size; + int ecc_bytes = chip->ecc.bytes; + void *dma_buf = denali->buf; + int oob_skip = denali->bbtskipbytes; + size_t size = writesize + oobsize; + int ret, i, pos, len; + + ret = denali_data_xfer(denali, dma_buf, size, page, 1, 0); + if (ret) + return ret; + + /* Arrange the buffer for syndrome payload/ecc layout */ + if (buf) { + for (i = 0; i < ecc_steps; i++) { + pos = i * (ecc_size + ecc_bytes); + len = ecc_size; + + if (pos >= writesize) + pos += oob_skip; + else if (pos + len > writesize) + len = writesize - pos; + + memcpy(buf, dma_buf + pos, len); + buf += len; + if (len < ecc_size) { + len = ecc_size - len; + memcpy(buf, dma_buf + writesize + oob_skip, + len); + buf += len; + } + } + } + + if (oob_required) { + uint8_t *oob = chip->oob_poi; + + /* BBM at the beginning of the OOB area */ + memcpy(oob, dma_buf + writesize, oob_skip); + oob += oob_skip; + + /* OOB ECC */ + for (i = 0; i < ecc_steps; i++) { + pos = ecc_size + i * (ecc_size + ecc_bytes); + len = ecc_bytes; + + if (pos >= writesize) + pos += oob_skip; + else if (pos + len > writesize) + len = writesize - pos; + + memcpy(oob, dma_buf + pos, len); + oob += len; + if (len < ecc_bytes) { + len = ecc_bytes - len; + memcpy(oob, dma_buf + writesize + oob_skip, + len); + oob += len; + } + } + + /* OOB free */ + len = oobsize - (oob - chip->oob_poi); + memcpy(oob, dma_buf + size - len, len); + } + + return 0; } static int denali_read_oob(struct mtd_info *mtd, struct nand_chip *chip, int page) { - read_oob_data(mtd, chip->oob_poi, page); + denali_oob_xfer(mtd, chip, page, 0); return 0; } -static int denali_read_page(struct mtd_info *mtd, struct nand_chip *chip, - uint8_t *buf, int oob_required, int page) +static int denali_write_oob(struct mtd_info *mtd, struct nand_chip *chip, + int page) { struct denali_nand_info *denali = mtd_to_denali(mtd); - dma_addr_t addr = denali->dma_addr; - size_t size = mtd->writesize + mtd->oobsize; - uint32_t irq_status; - uint32_t irq_mask = denali->caps & DENALI_CAP_HW_ECC_FIXUP ? - INTR__DMA_CMD_COMP | INTR__ECC_UNCOR_ERR : - INTR__ECC_TRANSACTION_DONE | INTR__ECC_ERR; - unsigned long uncor_ecc_flags = 0; - int stat = 0; + int status; - setup_ecc_for_xfer(denali, true, false); + denali_reset_irq(denali); - denali_enable_dma(denali, true); - dma_sync_single_for_device(denali->dev, addr, size, DMA_FROM_DEVICE); + denali_oob_xfer(mtd, chip, page, 1); - denali_reset_irq(denali); - denali_setup_dma(denali, addr, page, 0); + chip->cmdfunc(mtd, NAND_CMD_PAGEPROG, -1, -1); + status = chip->waitfunc(mtd, chip); - /* wait for operation to complete */ - irq_status = denali_wait_for_irq(denali, irq_mask); + return status & NAND_STATUS_FAIL ? -EIO : 0; +} + +static int denali_read_page(struct mtd_info *mtd, struct nand_chip *chip, + uint8_t *buf, int oob_required, int page) +{ + struct denali_nand_info *denali = mtd_to_denali(mtd); + unsigned long uncor_ecc_flags = 0; + int stat = 0; + int ret; - dma_sync_single_for_cpu(denali->dev, addr, size, DMA_FROM_DEVICE); + ret = denali_data_xfer(denali, denali->buf, mtd->writesize, page, 0, 0); + if (ret && ret != -EBADMSG) + return ret; memcpy(buf, denali->buf, mtd->writesize); if (denali->caps & DENALI_CAP_HW_ECC_FIXUP) stat = denali_hw_ecc_fixup(mtd, denali, &uncor_ecc_flags); - else if (irq_status & INTR__ECC_ERR) + else if (ret == -EBADMSG) stat = denali_sw_ecc_fixup(mtd, denali, &uncor_ecc_flags, buf); - denali_enable_dma(denali, false); if (stat < 0) return stat; if (uncor_ecc_flags) { - read_oob_data(mtd, chip->oob_poi, page); + ret = denali_read_oob(mtd, chip, page); + if (ret) + return ret; stat = denali_check_erased_page(mtd, chip, buf, uncor_ecc_flags, stat); @@ -831,36 +842,93 @@ static int denali_read_page(struct mtd_info *mtd, struct nand_chip *chip, return stat; } -static int denali_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, - uint8_t *buf, int oob_required, int page) +static int denali_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip, + const uint8_t *buf, int oob_required, int page) { struct denali_nand_info *denali = mtd_to_denali(mtd); - dma_addr_t addr = denali->dma_addr; - size_t size = mtd->writesize + mtd->oobsize; - uint32_t irq_mask = INTR__DMA_CMD_COMP; - uint32_t irq_status; - - setup_ecc_for_xfer(denali, false, true); - denali_enable_dma(denali, true); + int writesize = mtd->writesize; + int oobsize = mtd->oobsize; + int ecc_steps = chip->ecc.steps; + int ecc_size = chip->ecc.size; + int ecc_bytes = chip->ecc.bytes; + void *dma_buf = denali->buf; + int oob_skip = denali->bbtskipbytes; + size_t size = writesize + oobsize; + int i, pos, len; - dma_sync_single_for_device(denali->dev, addr, size, DMA_FROM_DEVICE); + /* + * Fill the buffer with 0xff first except the full page transfer. + * This simplifies the logic. + */ + if (!buf || !oob_required) + memset(dma_buf, 0xff, size); + + /* Arrange the buffer for syndrome payload/ecc layout */ + if (buf) { + for (i = 0; i < ecc_steps; i++) { + pos = i * (ecc_size + ecc_bytes); + len = ecc_size; + + if (pos >= writesize) + pos += oob_skip; + else if (pos + len > writesize) + len = writesize - pos; + + memcpy(dma_buf + pos, buf, len); + buf += len; + if (len < ecc_size) { + len = ecc_size - len; + memcpy(dma_buf + writesize + oob_skip, buf, + len); + buf += len; + } + } + } - denali_reset_irq(denali); - denali_setup_dma(denali, addr, page, 0); + if (oob_required) { + const uint8_t *oob = chip->oob_poi; + + /* BBM at the beginning of the OOB area */ + memcpy(dma_buf + writesize, oob, oob_skip); + oob += oob_skip; + + /* OOB ECC */ + for (i = 0; i < ecc_steps; i++) { + pos = ecc_size + i * (ecc_size + ecc_bytes); + len = ecc_bytes; + + if (pos >= writesize) + pos += oob_skip; + else if (pos + len > writesize) + len = writesize - pos; + + memcpy(dma_buf + pos, oob, len); + oob += len; + if (len < ecc_bytes) { + len = ecc_bytes - len; + memcpy(dma_buf + writesize + oob_skip, oob, + len); + oob += len; + } + } - /* wait for operation to complete */ - irq_status = denali_wait_for_irq(denali, irq_mask); - if (irq_status & INTR__DMA_CMD_COMP) - return -ETIMEDOUT; + /* OOB free */ + len = oobsize - (oob - chip->oob_poi); + memcpy(dma_buf + size - len, oob, len); + } - dma_sync_single_for_cpu(denali->dev, addr, size, DMA_FROM_DEVICE); + return denali_data_xfer(denali, dma_buf, size, page, 1, 1); +} - denali_enable_dma(denali, false); +static int denali_write_page(struct mtd_info *mtd, struct nand_chip *chip, + const uint8_t *buf, int oob_required, int page) +{ + struct denali_nand_info *denali = mtd_to_denali(mtd); - memcpy(buf, denali->buf, mtd->writesize); - memcpy(chip->oob_poi, denali->buf + mtd->writesize, mtd->oobsize); + memcpy(denali->buf, buf, mtd->writesize); - return 0; + return denali_data_xfer(denali, denali->buf, mtd->writesize, page, + 0, 1); } static void denali_select_chip(struct mtd_info *mtd, int chip) @@ -1285,21 +1353,29 @@ int denali_init(struct denali_nand_info *denali) goto disable_irq; } - ret = dma_set_mask(denali->dev, - DMA_BIT_MASK(denali->caps & DENALI_CAP_DMA_64BIT ? - 64 : 32)); - if (ret) { - dev_err(denali->dev, "No usable DMA configuration\n"); - goto disable_irq; + if (ioread32(denali->flash_reg + FEATURES) & FEATURES__DMA) + denali->dma_avail = 1; + + if (denali->dma_avail) { + int dma_bit = denali->caps & DENALI_CAP_DMA_64BIT ? 64 : 32; + + ret = dma_set_mask(denali->dev, DMA_BIT_MASK(dma_bit)); + if (ret) { + dev_info(denali->dev, + "Failed to set DMA mask. Disabling DMA.\n"); + denali->dma_avail = 0; + } } - denali->dma_addr = dma_map_single(denali->dev, denali->buf, - mtd->writesize + mtd->oobsize, - DMA_BIDIRECTIONAL); - if (dma_mapping_error(denali->dev, denali->dma_addr)) { - dev_err(denali->dev, "Failed to map DMA buffer\n"); - ret = -EIO; - goto disable_irq; + if (denali->dma_avail) { + denali->dma_addr = dma_map_single(denali->dev, denali->buf, + mtd->writesize + mtd->oobsize, + DMA_BIDIRECTIONAL); + if (dma_mapping_error(denali->dev, denali->dma_addr)) { + dev_info(denali->dev, + "Failed to map DMA buffer. Disabling DMA.\n"); + denali->dma_avail = 0; + }; } /* diff --git a/drivers/mtd/nand/denali.h b/drivers/mtd/nand/denali.h index 1b991d3016f8..f5da52f09e34 100644 --- a/drivers/mtd/nand/denali.h +++ b/drivers/mtd/nand/denali.h @@ -298,8 +298,6 @@ #define CHNL_ACTIVE__CHANNEL2 BIT(2) #define CHNL_ACTIVE__CHANNEL3 BIT(3) -#define PASS 0 /*success flag*/ - #define MODE_00 0x00000000 #define MODE_01 0x04000000 #define MODE_10 0x08000000 @@ -322,6 +320,7 @@ struct denali_nand_info { void *buf; dma_addr_t dma_addr; + int dma_avail; int devnum; /* represent how many nands connected */ int bbtskipbytes; int max_banks; -- cgit v1.2.3-59-g8ed1b From 57a4d8b5f6482718f17c08f2cdfea085b1d3c12a Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 13 Jun 2017 22:45:46 +0900 Subject: mtd: nand: denali: support hardware-assisted erased page detection Recent versions of this IP support automatic erased page detection. If an erased page is detected on reads, the controller does not set INTR__ECC_UNCOR_ERR, but INTR__ERASED_PAGE. The detection of erased pages is based on the number of zeros in a page; if the number of zeros is less than the value in the field ERASED_THRESHOLD, the page is assumed as erased. Please note ERASED_THRESHOLD specifies the number of zeros in a _page_ instead of an ECC chunk. Moreover, the controller does not provide a way to know the actual number of bitflips. Actually, an erased page (all 0xff) is not an ECC correctable pattern on the Denali ECC engine. In other words, there may be overlap between the following two: [1] a bit pattern reachable from a valid payload + ECC pattern within ecc.strength bitflips [2] a bit pattern reachable from an erased state (all 0xff) within ecc.strength bitflips So, this feature may intercept ECC correctable patterns, then replace [1] with [2]. After all, this feature can work safely only when ECC_THRESHOLD == 1, i.e. detect erased pages without any bitflips. This should be the case most of the time. If there is a bitflip or more, the driver will fallback to the software method by using nand_check_erased_ecc_chunk(). Strangely enough, the driver still has to fill the buffer with 0xff in case of INTR__ERASED_PAGE because the ECC correction engine has already manipulated the data in the buffer before it judges erased pages. Signed-off-by: Masahiro Yamada Signed-off-by: Boris Brezillon --- drivers/mtd/nand/denali.c | 9 ++++++++- drivers/mtd/nand/denali.h | 5 +++++ 2 files changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c index ed0044c560e5..e8d8e6c6f45e 100644 --- a/drivers/mtd/nand/denali.c +++ b/drivers/mtd/nand/denali.c @@ -560,6 +560,9 @@ static int denali_pio_read(struct denali_nand_info *denali, void *buf, if (!(irq_status & INTR__PAGE_XFER_INC)) return -EIO; + if (irq_status & INTR__ERASED_PAGE) + memset(buf, 0xff, size); + return irq_status & ecc_err_mask ? -EBADMSG : 0; } @@ -635,6 +638,9 @@ static int denali_dma_xfer(struct denali_nand_info *denali, void *buf, denali_enable_dma(denali, false); dma_sync_single_for_cpu(denali->dev, dma_addr, size, dir); + if (irq_status & INTR__ERASED_PAGE) + memset(buf, 0xff, size); + return ret; } @@ -1406,7 +1412,8 @@ int denali_init(struct denali_nand_info *denali) "chosen ECC settings: step=%d, strength=%d, bytes=%d\n", chip->ecc.size, chip->ecc.strength, chip->ecc.bytes); - iowrite32(chip->ecc.strength, denali->flash_reg + ECC_CORRECTION); + iowrite32(MAKE_ECC_CORRECTION(chip->ecc.strength, 1), + denali->flash_reg + ECC_CORRECTION); iowrite32(mtd->erasesize / mtd->writesize, denali->flash_reg + PAGES_PER_BLOCK); iowrite32(chip->options & NAND_BUSWIDTH_16 ? 1 : 0, diff --git a/drivers/mtd/nand/denali.h b/drivers/mtd/nand/denali.h index f5da52f09e34..657a794af695 100644 --- a/drivers/mtd/nand/denali.h +++ b/drivers/mtd/nand/denali.h @@ -110,6 +110,10 @@ #define ECC_CORRECTION 0x1b0 #define ECC_CORRECTION__VALUE GENMASK(4, 0) +#define ECC_CORRECTION__ERASE_THRESHOLD GENMASK(31, 16) +#define MAKE_ECC_CORRECTION(val, thresh) \ + (((val) & (ECC_CORRECTION__VALUE)) | \ + (((thresh) << 16) & (ECC_CORRECTION__ERASE_THRESHOLD))) #define READ_MODE 0x1c0 #define READ_MODE__VALUE GENMASK(3, 0) @@ -233,6 +237,7 @@ #define INTR__RST_COMP BIT(13) #define INTR__PIPE_CMD_ERR BIT(14) #define INTR__PAGE_XFER_INC BIT(15) +#define INTR__ERASED_PAGE BIT(16) #define PAGE_CNT(bank) (0x430 + (bank) * 0x50) #define ERR_PAGE_ADDR(bank) (0x440 + (bank) * 0x50) -- cgit v1.2.3-59-g8ed1b From 997cde2a222091270ce0c276e567b68e5615f577 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 13 Jun 2017 22:45:47 +0900 Subject: mtd: nand: denali: skip driver internal bounce buffer when possible For ecc->read_page() and ecc->write_page(), it is possible to call dma_map_single() against the given buffer. This bypasses the driver internal bounce buffer and save the memcpy(). Signed-off-by: Masahiro Yamada Signed-off-by: Boris Brezillon --- drivers/mtd/nand/denali.c | 38 ++++++++++++-------------------------- 1 file changed, 12 insertions(+), 26 deletions(-) diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c index e8d8e6c6f45e..ec5fc8da5f9a 100644 --- a/drivers/mtd/nand/denali.c +++ b/drivers/mtd/nand/denali.c @@ -600,12 +600,16 @@ static int denali_pio_xfer(struct denali_nand_info *denali, void *buf, static int denali_dma_xfer(struct denali_nand_info *denali, void *buf, size_t size, int page, int raw, int write) { - dma_addr_t dma_addr = denali->dma_addr; + dma_addr_t dma_addr; uint32_t irq_mask, irq_status, ecc_err_mask; enum dma_data_direction dir = write ? DMA_TO_DEVICE : DMA_FROM_DEVICE; int ret = 0; - dma_sync_single_for_device(denali->dev, dma_addr, size, dir); + dma_addr = dma_map_single(denali->dev, buf, size, dir); + if (dma_mapping_error(denali->dev, dma_addr)) { + dev_dbg(denali->dev, "Failed to DMA-map buffer. Trying PIO.\n"); + return denali_pio_xfer(denali, buf, size, page, raw, write); + } if (write) { /* @@ -636,7 +640,7 @@ static int denali_dma_xfer(struct denali_nand_info *denali, void *buf, ret = -EBADMSG; denali_enable_dma(denali, false); - dma_sync_single_for_cpu(denali->dev, dma_addr, size, dir); + dma_unmap_single(denali->dev, dma_addr, size, dir); if (irq_status & INTR__ERASED_PAGE) memset(buf, 0xff, size); @@ -822,12 +826,10 @@ static int denali_read_page(struct mtd_info *mtd, struct nand_chip *chip, int stat = 0; int ret; - ret = denali_data_xfer(denali, denali->buf, mtd->writesize, page, 0, 0); + ret = denali_data_xfer(denali, buf, mtd->writesize, page, 0, 0); if (ret && ret != -EBADMSG) return ret; - memcpy(buf, denali->buf, mtd->writesize); - if (denali->caps & DENALI_CAP_HW_ECC_FIXUP) stat = denali_hw_ecc_fixup(mtd, denali, &uncor_ecc_flags); else if (ret == -EBADMSG) @@ -931,10 +933,8 @@ static int denali_write_page(struct mtd_info *mtd, struct nand_chip *chip, { struct denali_nand_info *denali = mtd_to_denali(mtd); - memcpy(denali->buf, buf, mtd->writesize); - - return denali_data_xfer(denali, denali->buf, mtd->writesize, page, - 0, 1); + return denali_data_xfer(denali, (void *)buf, mtd->writesize, + page, 0, 1); } static void denali_select_chip(struct mtd_info *mtd, int chip) @@ -1374,14 +1374,8 @@ int denali_init(struct denali_nand_info *denali) } if (denali->dma_avail) { - denali->dma_addr = dma_map_single(denali->dev, denali->buf, - mtd->writesize + mtd->oobsize, - DMA_BIDIRECTIONAL); - if (dma_mapping_error(denali->dev, denali->dma_addr)) { - dev_info(denali->dev, - "Failed to map DMA buffer. Disabling DMA.\n"); - denali->dma_avail = 0; - }; + chip->options |= NAND_USE_BOUNCE_BUFFER; + chip->buf_align = 16; } /* @@ -1471,16 +1465,8 @@ EXPORT_SYMBOL(denali_init); void denali_remove(struct denali_nand_info *denali) { struct mtd_info *mtd = nand_to_mtd(&denali->nand); - /* - * Pre-compute DMA buffer size to avoid any problems in case - * nand_release() ever changes in a way that mtd->writesize and - * mtd->oobsize are not reliable after this call. - */ - int bufsize = mtd->writesize + mtd->oobsize; nand_release(mtd); denali_disable_irq(denali); - dma_unmap_single(denali->dev, denali->dma_addr, bufsize, - DMA_BIDIRECTIONAL); } EXPORT_SYMBOL(denali_remove); -- cgit v1.2.3-59-g8ed1b From 7d370b2c255612569818134ae0a6d0e46eabfe8b Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 13 Jun 2017 22:45:48 +0900 Subject: mtd: nand: denali: use non-managed kmalloc() for DMA buffer As Russell and Lars stated in the discussion [1], using devm_k*alloc() with DMA is not a good idea. Let's use kmalloc (not kzalloc because no need for zero-out). Also, allocate the buffer as late as possible because it must be freed for any error that follows. [1] https://lkml.org/lkml/2017/3/8/693 Signed-off-by: Masahiro Yamada Cc: Russell King Cc: Lars-Peter Clausen Acked-by: Robin Murphy Signed-off-by: Boris Brezillon --- drivers/mtd/nand/denali.c | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c index ec5fc8da5f9a..bb2da2fd069e 100644 --- a/drivers/mtd/nand/denali.c +++ b/drivers/mtd/nand/denali.c @@ -23,6 +23,7 @@ #include #include #include +#include #include "denali.h" @@ -1352,13 +1353,6 @@ int denali_init(struct denali_nand_info *denali) if (ret) goto disable_irq; - denali->buf = devm_kzalloc(denali->dev, mtd->writesize + mtd->oobsize, - GFP_KERNEL); - if (!denali->buf) { - ret = -ENOMEM; - goto disable_irq; - } - if (ioread32(denali->flash_reg + FEATURES) & FEATURES__DMA) denali->dma_avail = 1; @@ -1443,17 +1437,30 @@ int denali_init(struct denali_nand_info *denali) if (ret) goto disable_irq; + /* + * This buffer is DMA-mapped by denali_{read,write}_page_raw. Do not + * use devm_kmalloc() because the memory allocated by devm_ does not + * guarantee DMA-safe alignment. + */ + denali->buf = kmalloc(mtd->writesize + mtd->oobsize, GFP_KERNEL); + if (!denali->buf) { + ret = -ENOMEM; + goto disable_irq; + } + ret = nand_scan_tail(mtd); if (ret) - goto disable_irq; + goto free_buf; ret = mtd_device_register(mtd, NULL, 0); if (ret) { dev_err(denali->dev, "Failed to register MTD: %d\n", ret); - goto disable_irq; + goto free_buf; } return 0; +free_buf: + kfree(denali->buf); disable_irq: denali_disable_irq(denali); @@ -1467,6 +1474,7 @@ void denali_remove(struct denali_nand_info *denali) struct mtd_info *mtd = nand_to_mtd(&denali->nand); nand_release(mtd); + kfree(denali->buf); denali_disable_irq(denali); } EXPORT_SYMBOL(denali_remove); -- cgit v1.2.3-59-g8ed1b From 777f2d49e8e9fbb5d00f54c496877220b6e6ff6c Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 13 Jun 2017 22:45:49 +0900 Subject: mtd: nand: denali: enable bad block table scan Now this driver is ready to remove NAND_SKIP_BBTSCAN. The BBT descriptors in denali.c are equivalent to the ones in nand_bbt.c. There is no need to duplicate the equivalent structures. The with-oob decriptors do not work for this driver anyway. The bbt_pattern (offs = 8) and the version (veroffs = 12) area overlaps the ECC area. Set NAND_BBT_NO_OOB flag to use the no_oob variant of the BBT descriptors. Signed-off-by: Masahiro Yamada Signed-off-by: Boris Brezillon --- drivers/mtd/nand/denali.c | 31 ++----------------------------- 1 file changed, 2 insertions(+), 29 deletions(-) diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c index bb2da2fd069e..5ac3eb07c6d6 100644 --- a/drivers/mtd/nand/denali.c +++ b/drivers/mtd/nand/denali.c @@ -1211,29 +1211,6 @@ static const struct mtd_ooblayout_ops denali_ooblayout_ops = { .free = denali_ooblayout_free, }; -static uint8_t bbt_pattern[] = {'B', 'b', 't', '0' }; -static uint8_t mirror_pattern[] = {'1', 't', 'b', 'B' }; - -static struct nand_bbt_descr bbt_main_descr = { - .options = NAND_BBT_LASTBLOCK | NAND_BBT_CREATE | NAND_BBT_WRITE - | NAND_BBT_2BIT | NAND_BBT_VERSION | NAND_BBT_PERCHIP, - .offs = 8, - .len = 4, - .veroffs = 12, - .maxblocks = 4, - .pattern = bbt_pattern, -}; - -static struct nand_bbt_descr bbt_mirror_descr = { - .options = NAND_BBT_LASTBLOCK | NAND_BBT_CREATE | NAND_BBT_WRITE - | NAND_BBT_2BIT | NAND_BBT_VERSION | NAND_BBT_PERCHIP, - .offs = 8, - .len = 4, - .veroffs = 12, - .maxblocks = 4, - .pattern = mirror_pattern, -}; - /* initialize driver data structures */ static void denali_drv_init(struct denali_nand_info *denali) { @@ -1378,13 +1355,9 @@ int denali_init(struct denali_nand_info *denali) * bad block management. */ - /* Bad block management */ - chip->bbt_td = &bbt_main_descr; - chip->bbt_md = &bbt_mirror_descr; - - /* skip the scan for now until we have OOB read and write support */ chip->bbt_options |= NAND_BBT_USE_FLASH; - chip->options |= NAND_SKIP_BBTSCAN; + chip->bbt_options |= NAND_BBT_NO_OOB; + chip->ecc.mode = NAND_ECC_HW_SYNDROME; /* no subpage writes on denali */ -- cgit v1.2.3-59-g8ed1b From 0d3a966d2b34f449df7859fa39e3db5b71da2bfa Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 16 Jun 2017 14:36:39 +0900 Subject: mtd: nand: denali: avoid magic numbers and rename for clarification Introduce some macros and helpers to avoid magic numbers and rename macros/functions for clarification. - We see '| 2' in several places. This means Data Cycle in MAP11 mode. The Denali User's Guide says bit[1:0] of MAP11 is like follows: b'00 = Command Cycle b'01 = Address Cycle b'10 = Data Cycle So, this commit added DENALI_MAP11_{CMD,ADDR,DATA} macros. - We see 'denali->flash_mem + 0x10' in several places, but 0x10 is a magic number. Actually, this accesses the data port of the Host Data/Command Interface. So, this commit added DENALI_HOST_DATA. On the other hand, 'denali->flash_mem' gets access to the address port, so DENALI_HOST_ADDR was also added. - We see 'index_addr(denali, cmd, 0x1)' in denali_erase(), but 0x1 is a magic number. 0x1 means the erase operation. Replace 0x1 with DENALI_ERASE. - Rename index_addr() to denali_host_write() for clarification - Denali User's Guide says MAP{00,01,10,11} for access mode. Match the macros with terminology in the IP document. - Rename struct members as follows: flash_bank -> active_bank (currently selected bank) flash_reg -> reg (base address of registers) flash_mem -> host (base address of host interface) devnum -> devs_per_cs (devices connected in parallel) bbtskipbytes -> oob_skip_bytes (number of bytes to skip in OOB) Signed-off-by: Masahiro Yamada Signed-off-by: Boris Brezillon --- drivers/mtd/nand/denali.c | 247 +++++++++++++++++++++--------------------- drivers/mtd/nand/denali.h | 15 +-- drivers/mtd/nand/denali_dt.c | 12 +- drivers/mtd/nand/denali_pci.c | 16 +-- 4 files changed, 144 insertions(+), 146 deletions(-) diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c index 5ac3eb07c6d6..d723be352148 100644 --- a/drivers/mtd/nand/denali.c +++ b/drivers/mtd/nand/denali.c @@ -31,12 +31,26 @@ MODULE_LICENSE("GPL"); #define DENALI_NAND_NAME "denali-nand" -/* - * indicates whether or not the internal value for the flash bank is - * valid or not - */ -#define CHIP_SELECT_INVALID -1 +/* Host Data/Command Interface */ +#define DENALI_HOST_ADDR 0x00 +#define DENALI_HOST_DATA 0x10 + +#define DENALI_MAP00 (0 << 26) /* direct access to buffer */ +#define DENALI_MAP01 (1 << 26) /* read/write pages in PIO */ +#define DENALI_MAP10 (2 << 26) /* high-level control plane */ +#define DENALI_MAP11 (3 << 26) /* direct controller access */ + +/* MAP11 access cycle type */ +#define DENALI_MAP11_CMD ((DENALI_MAP11) | 0) /* command cycle */ +#define DENALI_MAP11_ADDR ((DENALI_MAP11) | 1) /* address cycle */ +#define DENALI_MAP11_DATA ((DENALI_MAP11) | 2) /* data cycle */ + +/* MAP10 commands */ +#define DENALI_ERASE 0x01 + +#define DENALI_BANK(denali) ((denali)->active_bank << 24) +#define DENALI_INVALID_BANK -1 #define DENALI_NR_BANKS 4 /* @@ -56,23 +70,11 @@ static inline struct denali_nand_info *mtd_to_denali(struct mtd_info *mtd) return container_of(mtd_to_nand(mtd), struct denali_nand_info, nand); } -/* - * this is a helper macro that allows us to - * format the bank into the proper bits for the controller - */ -#define BANK(x) ((x) << 24) - -/* - * Certain operations for the denali NAND controller use an indexed mode to - * read/write data. The operation is performed by writing the address value - * of the command to the device memory followed by the data. This function - * abstracts this common operation. - */ -static void index_addr(struct denali_nand_info *denali, - uint32_t address, uint32_t data) +static void denali_host_write(struct denali_nand_info *denali, + uint32_t addr, uint32_t data) { - iowrite32(address, denali->flash_mem); - iowrite32(data, denali->flash_mem + 0x10); + iowrite32(addr, denali->host + DENALI_HOST_ADDR); + iowrite32(data, denali->host + DENALI_HOST_DATA); } /* @@ -81,7 +83,7 @@ static void index_addr(struct denali_nand_info *denali, */ static void detect_max_banks(struct denali_nand_info *denali) { - uint32_t features = ioread32(denali->flash_reg + FEATURES); + uint32_t features = ioread32(denali->reg + FEATURES); denali->max_banks = 1 << (features & FEATURES__N_BANKS); @@ -95,8 +97,8 @@ static void denali_enable_irq(struct denali_nand_info *denali) int i; for (i = 0; i < DENALI_NR_BANKS; i++) - iowrite32(U32_MAX, denali->flash_reg + INTR_EN(i)); - iowrite32(GLOBAL_INT_EN_FLAG, denali->flash_reg + GLOBAL_INT_ENABLE); + iowrite32(U32_MAX, denali->reg + INTR_EN(i)); + iowrite32(GLOBAL_INT_EN_FLAG, denali->reg + GLOBAL_INT_ENABLE); } static void denali_disable_irq(struct denali_nand_info *denali) @@ -104,15 +106,15 @@ static void denali_disable_irq(struct denali_nand_info *denali) int i; for (i = 0; i < DENALI_NR_BANKS; i++) - iowrite32(0, denali->flash_reg + INTR_EN(i)); - iowrite32(0, denali->flash_reg + GLOBAL_INT_ENABLE); + iowrite32(0, denali->reg + INTR_EN(i)); + iowrite32(0, denali->reg + GLOBAL_INT_ENABLE); } static void denali_clear_irq(struct denali_nand_info *denali, int bank, uint32_t irq_status) { /* write one to clear bits */ - iowrite32(irq_status, denali->flash_reg + INTR_STATUS(bank)); + iowrite32(irq_status, denali->reg + INTR_STATUS(bank)); } static void denali_clear_irq_all(struct denali_nand_info *denali) @@ -133,13 +135,13 @@ static irqreturn_t denali_isr(int irq, void *dev_id) spin_lock(&denali->irq_lock); for (i = 0; i < DENALI_NR_BANKS; i++) { - irq_status = ioread32(denali->flash_reg + INTR_STATUS(i)); + irq_status = ioread32(denali->reg + INTR_STATUS(i)); if (irq_status) ret = IRQ_HANDLED; denali_clear_irq(denali, i, irq_status); - if (i != denali->flash_bank) + if (i != denali->active_bank) continue; denali->irq_status |= irq_status; @@ -220,8 +222,8 @@ static void setup_ecc_for_xfer(struct denali_nand_info *denali, bool ecc_en, transfer_spare_flag = transfer_spare ? TRANSFER_SPARE_REG__FLAG : 0; /* Enable spare area/ECC per user's request. */ - iowrite32(ecc_en_flag, denali->flash_reg + ECC_ENABLE); - iowrite32(transfer_spare_flag, denali->flash_reg + TRANSFER_SPARE_REG); + iowrite32(ecc_en_flag, denali->reg + ECC_ENABLE); + iowrite32(transfer_spare_flag, denali->reg + TRANSFER_SPARE_REG); } static void denali_read_buf(struct mtd_info *mtd, uint8_t *buf, int len) @@ -229,10 +231,11 @@ static void denali_read_buf(struct mtd_info *mtd, uint8_t *buf, int len) struct denali_nand_info *denali = mtd_to_denali(mtd); int i; - iowrite32(MODE_11 | BANK(denali->flash_bank) | 2, denali->flash_mem); + iowrite32(DENALI_MAP11_DATA | DENALI_BANK(denali), + denali->host + DENALI_HOST_ADDR); for (i = 0; i < len; i++) - buf[i] = ioread32(denali->flash_mem + 0x10); + buf[i] = ioread32(denali->host + DENALI_HOST_DATA); } static void denali_write_buf(struct mtd_info *mtd, const uint8_t *buf, int len) @@ -240,10 +243,11 @@ static void denali_write_buf(struct mtd_info *mtd, const uint8_t *buf, int len) struct denali_nand_info *denali = mtd_to_denali(mtd); int i; - iowrite32(MODE_11 | BANK(denali->flash_bank) | 2, denali->flash_mem); + iowrite32(DENALI_MAP11_DATA | DENALI_BANK(denali), + denali->host + DENALI_HOST_ADDR); for (i = 0; i < len; i++) - iowrite32(buf[i], denali->flash_mem + 0x10); + iowrite32(buf[i], denali->host + DENALI_HOST_DATA); } static void denali_read_buf16(struct mtd_info *mtd, uint8_t *buf, int len) @@ -252,10 +256,11 @@ static void denali_read_buf16(struct mtd_info *mtd, uint8_t *buf, int len) uint16_t *buf16 = (uint16_t *)buf; int i; - iowrite32(MODE_11 | BANK(denali->flash_bank) | 2, denali->flash_mem); + iowrite32(DENALI_MAP11_DATA | DENALI_BANK(denali), + denali->host + DENALI_HOST_ADDR); for (i = 0; i < len / 2; i++) - buf16[i] = ioread32(denali->flash_mem + 0x10); + buf16[i] = ioread32(denali->host + DENALI_HOST_DATA); } static void denali_write_buf16(struct mtd_info *mtd, const uint8_t *buf, @@ -265,10 +270,11 @@ static void denali_write_buf16(struct mtd_info *mtd, const uint8_t *buf, const uint16_t *buf16 = (const uint16_t *)buf; int i; - iowrite32(MODE_11 | BANK(denali->flash_bank) | 2, denali->flash_mem); + iowrite32(DENALI_MAP11_DATA | DENALI_BANK(denali), + denali->host + DENALI_HOST_ADDR); for (i = 0; i < len / 2; i++) - iowrite32(buf16[i], denali->flash_mem + 0x10); + iowrite32(buf16[i], denali->host + DENALI_HOST_DATA); } static uint8_t denali_read_byte(struct mtd_info *mtd) @@ -300,9 +306,9 @@ static void denali_cmd_ctrl(struct mtd_info *mtd, int dat, unsigned int ctrl) uint32_t type; if (ctrl & NAND_CLE) - type = 0; + type = DENALI_MAP11_CMD; else if (ctrl & NAND_ALE) - type = 1; + type = DENALI_MAP11_ADDR; else return; @@ -313,7 +319,7 @@ static void denali_cmd_ctrl(struct mtd_info *mtd, int dat, unsigned int ctrl) if (ctrl & NAND_CTRL_CHANGE) denali_reset_irq(denali); - index_addr(denali, MODE_11 | BANK(denali->flash_bank) | type, dat); + denali_host_write(denali, DENALI_BANK(denali) | type, dat); } static int denali_dev_ready(struct mtd_info *mtd) @@ -366,11 +372,11 @@ static int denali_hw_ecc_fixup(struct mtd_info *mtd, unsigned long *uncor_ecc_flags) { struct nand_chip *chip = mtd_to_nand(mtd); - int bank = denali->flash_bank; + int bank = denali->active_bank; uint32_t ecc_cor; unsigned int max_bitflips; - ecc_cor = ioread32(denali->flash_reg + ECC_COR_INFO(bank)); + ecc_cor = ioread32(denali->reg + ECC_COR_INFO(bank)); ecc_cor >>= ECC_COR_INFO__SHIFT(bank); if (ecc_cor & ECC_COR_INFO__UNCOR_ERR) { @@ -419,11 +425,11 @@ static int denali_sw_ecc_fixup(struct mtd_info *mtd, denali_reset_irq(denali); do { - err_addr = ioread32(denali->flash_reg + ECC_ERROR_ADDRESS); + err_addr = ioread32(denali->reg + ECC_ERROR_ADDRESS); err_sector = ECC_SECTOR(err_addr); err_byte = ECC_BYTE(err_addr); - err_cor_info = ioread32(denali->flash_reg + ERR_CORRECTION_INFO); + err_cor_info = ioread32(denali->reg + ERR_CORRECTION_INFO); err_cor_value = ECC_CORRECTION_VALUE(err_cor_info); err_device = ECC_ERR_DEVICE(err_cor_info); @@ -449,7 +455,7 @@ static int denali_sw_ecc_fixup(struct mtd_info *mtd, unsigned int flips_in_byte; offset = (err_sector * ecc_size + err_byte) * - denali->devnum + err_device; + denali->devs_per_cs + err_device; /* correct the ECC error */ flips_in_byte = hweight8(buf[offset] ^ err_cor_value); @@ -478,8 +484,8 @@ static int denali_sw_ecc_fixup(struct mtd_info *mtd, /* programs the controller to either enable/disable DMA transfers */ static void denali_enable_dma(struct denali_nand_info *denali, bool en) { - iowrite32(en ? DMA_ENABLE__FLAG : 0, denali->flash_reg + DMA_ENABLE); - ioread32(denali->flash_reg + DMA_ENABLE); + iowrite32(en ? DMA_ENABLE__FLAG : 0, denali->reg + DMA_ENABLE); + ioread32(denali->reg + DMA_ENABLE); } static void denali_setup_dma64(struct denali_nand_info *denali, @@ -488,7 +494,7 @@ static void denali_setup_dma64(struct denali_nand_info *denali, uint32_t mode; const int page_count = 1; - mode = MODE_10 | BANK(denali->flash_bank) | page; + mode = DENALI_MAP10 | DENALI_BANK(denali) | page; /* DMA is a three step process */ @@ -496,14 +502,14 @@ static void denali_setup_dma64(struct denali_nand_info *denali, * 1. setup transfer type, interrupt when complete, * burst len = 64 bytes, the number of pages */ - index_addr(denali, mode, - 0x01002000 | (64 << 16) | (write << 8) | page_count); + denali_host_write(denali, mode, + 0x01002000 | (64 << 16) | (write << 8) | page_count); /* 2. set memory low address */ - index_addr(denali, mode, dma_addr); + denali_host_write(denali, mode, dma_addr); /* 3. set memory high address */ - index_addr(denali, mode, (uint64_t)dma_addr >> 32); + denali_host_write(denali, mode, (uint64_t)dma_addr >> 32); } static void denali_setup_dma32(struct denali_nand_info *denali, @@ -512,21 +518,22 @@ static void denali_setup_dma32(struct denali_nand_info *denali, uint32_t mode; const int page_count = 1; - mode = MODE_10 | BANK(denali->flash_bank); + mode = DENALI_MAP10 | DENALI_BANK(denali); /* DMA is a four step process */ /* 1. setup transfer type and # of pages */ - index_addr(denali, mode | page, 0x2000 | (write << 8) | page_count); + denali_host_write(denali, mode | page, + 0x2000 | (write << 8) | page_count); /* 2. set memory high address bits 23:8 */ - index_addr(denali, mode | ((dma_addr >> 16) << 8), 0x2200); + denali_host_write(denali, mode | ((dma_addr >> 16) << 8), 0x2200); /* 3. set memory low address bits 23:8 */ - index_addr(denali, mode | ((dma_addr & 0xffff) << 8), 0x2300); + denali_host_write(denali, mode | ((dma_addr & 0xffff) << 8), 0x2300); /* 4. interrupt when complete, burst len = 64 bytes */ - index_addr(denali, mode | 0x14000, 0x2400); + denali_host_write(denali, mode | 0x14000, 0x2400); } static void denali_setup_dma(struct denali_nand_info *denali, @@ -541,7 +548,7 @@ static void denali_setup_dma(struct denali_nand_info *denali, static int denali_pio_read(struct denali_nand_info *denali, void *buf, size_t size, int page, int raw) { - uint32_t addr = BANK(denali->flash_bank) | page; + uint32_t addr = DENALI_BANK(denali) | page; uint32_t *buf32 = (uint32_t *)buf; uint32_t irq_status, ecc_err_mask; int i; @@ -553,9 +560,9 @@ static int denali_pio_read(struct denali_nand_info *denali, void *buf, denali_reset_irq(denali); - iowrite32(MODE_01 | addr, denali->flash_mem); + iowrite32(DENALI_MAP01 | addr, denali->host + DENALI_HOST_ADDR); for (i = 0; i < size / 4; i++) - *buf32++ = ioread32(denali->flash_mem + 0x10); + *buf32++ = ioread32(denali->host + DENALI_HOST_DATA); irq_status = denali_wait_for_irq(denali, INTR__PAGE_XFER_INC); if (!(irq_status & INTR__PAGE_XFER_INC)) @@ -570,16 +577,16 @@ static int denali_pio_read(struct denali_nand_info *denali, void *buf, static int denali_pio_write(struct denali_nand_info *denali, const void *buf, size_t size, int page, int raw) { - uint32_t addr = BANK(denali->flash_bank) | page; + uint32_t addr = DENALI_BANK(denali) | page; const uint32_t *buf32 = (uint32_t *)buf; uint32_t irq_status; int i; denali_reset_irq(denali); - iowrite32(MODE_01 | addr, denali->flash_mem); + iowrite32(DENALI_MAP01 | addr, denali->host + DENALI_HOST_ADDR); for (i = 0; i < size / 4; i++) - iowrite32(*buf32++, denali->flash_mem + 0x10); + iowrite32(*buf32++, denali->host + DENALI_HOST_DATA); irq_status = denali_wait_for_irq(denali, INTR__PROGRAM_COMP | INTR__PROGRAM_FAIL); @@ -672,7 +679,7 @@ static void denali_oob_xfer(struct mtd_info *mtd, struct nand_chip *chip, int ecc_steps = chip->ecc.steps; int ecc_size = chip->ecc.size; int ecc_bytes = chip->ecc.bytes; - int oob_skip = denali->bbtskipbytes; + int oob_skip = denali->oob_skip_bytes; size_t size = writesize + oobsize; int i, pos, len; @@ -730,7 +737,7 @@ static int denali_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, int ecc_size = chip->ecc.size; int ecc_bytes = chip->ecc.bytes; void *dma_buf = denali->buf; - int oob_skip = denali->bbtskipbytes; + int oob_skip = denali->oob_skip_bytes; size_t size = writesize + oobsize; int ret, i, pos, len; @@ -861,7 +868,7 @@ static int denali_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip, int ecc_size = chip->ecc.size; int ecc_bytes = chip->ecc.bytes; void *dma_buf = denali->buf; - int oob_skip = denali->bbtskipbytes; + int oob_skip = denali->oob_skip_bytes; size_t size = writesize + oobsize; int i, pos, len; @@ -942,7 +949,7 @@ static void denali_select_chip(struct mtd_info *mtd, int chip) { struct denali_nand_info *denali = mtd_to_denali(mtd); - denali->flash_bank = chip; + denali->active_bank = chip; } static int denali_waitfunc(struct mtd_info *mtd, struct nand_chip *chip) @@ -959,13 +966,12 @@ static int denali_waitfunc(struct mtd_info *mtd, struct nand_chip *chip) static int denali_erase(struct mtd_info *mtd, int page) { struct denali_nand_info *denali = mtd_to_denali(mtd); - uint32_t cmd, irq_status; + uint32_t irq_status; denali_reset_irq(denali); - /* setup page read request for access type */ - cmd = MODE_10 | BANK(denali->flash_bank) | page; - index_addr(denali, cmd, 0x1); + denali_host_write(denali, DENALI_MAP10 | DENALI_BANK(denali) | page, + DENALI_ERASE); /* wait for erase to complete or failure to occur */ irq_status = denali_wait_for_irq(denali, @@ -1004,37 +1010,37 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr, acc_clks = DIV_ROUND_UP(timings->tREA_max, t_clk); acc_clks = min_t(int, acc_clks, ACC_CLKS__VALUE); - tmp = ioread32(denali->flash_reg + ACC_CLKS); + tmp = ioread32(denali->reg + ACC_CLKS); tmp &= ~ACC_CLKS__VALUE; tmp |= acc_clks; - iowrite32(tmp, denali->flash_reg + ACC_CLKS); + iowrite32(tmp, denali->reg + ACC_CLKS); /* tRWH -> RE_2_WE */ re_2_we = DIV_ROUND_UP(timings->tRHW_min, t_clk); re_2_we = min_t(int, re_2_we, RE_2_WE__VALUE); - tmp = ioread32(denali->flash_reg + RE_2_WE); + tmp = ioread32(denali->reg + RE_2_WE); tmp &= ~RE_2_WE__VALUE; tmp |= re_2_we; - iowrite32(tmp, denali->flash_reg + RE_2_WE); + iowrite32(tmp, denali->reg + RE_2_WE); /* tRHZ -> RE_2_RE */ re_2_re = DIV_ROUND_UP(timings->tRHZ_max, t_clk); re_2_re = min_t(int, re_2_re, RE_2_RE__VALUE); - tmp = ioread32(denali->flash_reg + RE_2_RE); + tmp = ioread32(denali->reg + RE_2_RE); tmp &= ~RE_2_RE__VALUE; tmp |= re_2_re; - iowrite32(tmp, denali->flash_reg + RE_2_RE); + iowrite32(tmp, denali->reg + RE_2_RE); /* tWHR -> WE_2_RE */ we_2_re = DIV_ROUND_UP(timings->tWHR_min, t_clk); we_2_re = min_t(int, we_2_re, TWHR2_AND_WE_2_RE__WE_2_RE); - tmp = ioread32(denali->flash_reg + TWHR2_AND_WE_2_RE); + tmp = ioread32(denali->reg + TWHR2_AND_WE_2_RE); tmp &= ~TWHR2_AND_WE_2_RE__WE_2_RE; tmp |= we_2_re; - iowrite32(tmp, denali->flash_reg + TWHR2_AND_WE_2_RE); + iowrite32(tmp, denali->reg + TWHR2_AND_WE_2_RE); /* tADL -> ADDR_2_DATA */ @@ -1046,20 +1052,20 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr, addr_2_data = DIV_ROUND_UP(timings->tADL_min, t_clk); addr_2_data = min_t(int, addr_2_data, addr_2_data_mask); - tmp = ioread32(denali->flash_reg + TCWAW_AND_ADDR_2_DATA); + tmp = ioread32(denali->reg + TCWAW_AND_ADDR_2_DATA); tmp &= ~addr_2_data_mask; tmp |= addr_2_data; - iowrite32(tmp, denali->flash_reg + TCWAW_AND_ADDR_2_DATA); + iowrite32(tmp, denali->reg + TCWAW_AND_ADDR_2_DATA); /* tREH, tWH -> RDWR_EN_HI_CNT */ rdwr_en_hi = DIV_ROUND_UP(max(timings->tREH_min, timings->tWH_min), t_clk); rdwr_en_hi = min_t(int, rdwr_en_hi, RDWR_EN_HI_CNT__VALUE); - tmp = ioread32(denali->flash_reg + RDWR_EN_HI_CNT); + tmp = ioread32(denali->reg + RDWR_EN_HI_CNT); tmp &= ~RDWR_EN_HI_CNT__VALUE; tmp |= rdwr_en_hi; - iowrite32(tmp, denali->flash_reg + RDWR_EN_HI_CNT); + iowrite32(tmp, denali->reg + RDWR_EN_HI_CNT); /* tRP, tWP -> RDWR_EN_LO_CNT */ rdwr_en_lo = DIV_ROUND_UP(max(timings->tRP_min, timings->tWP_min), @@ -1070,10 +1076,10 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr, rdwr_en_lo = max(rdwr_en_lo, rdwr_en_lo_hi - rdwr_en_hi); rdwr_en_lo = min_t(int, rdwr_en_lo, RDWR_EN_LO_CNT__VALUE); - tmp = ioread32(denali->flash_reg + RDWR_EN_LO_CNT); + tmp = ioread32(denali->reg + RDWR_EN_LO_CNT); tmp &= ~RDWR_EN_LO_CNT__VALUE; tmp |= rdwr_en_lo; - iowrite32(tmp, denali->flash_reg + RDWR_EN_LO_CNT); + iowrite32(tmp, denali->reg + RDWR_EN_LO_CNT); /* tCS, tCEA -> CS_SETUP_CNT */ cs_setup = max3((int)DIV_ROUND_UP(timings->tCS_min, t_clk) - rdwr_en_lo, @@ -1081,10 +1087,10 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr, 0); cs_setup = min_t(int, cs_setup, CS_SETUP_CNT__VALUE); - tmp = ioread32(denali->flash_reg + CS_SETUP_CNT); + tmp = ioread32(denali->reg + CS_SETUP_CNT); tmp &= ~CS_SETUP_CNT__VALUE; tmp |= cs_setup; - iowrite32(tmp, denali->flash_reg + CS_SETUP_CNT); + iowrite32(tmp, denali->reg + CS_SETUP_CNT); return 0; } @@ -1095,12 +1101,12 @@ static void denali_reset_banks(struct denali_nand_info *denali) int i; for (i = 0; i < denali->max_banks; i++) { - denali->flash_bank = i; + denali->active_bank = i; denali_reset_irq(denali); iowrite32(DEVICE_RESET__BANK(i), - denali->flash_reg + DEVICE_RESET); + denali->reg + DEVICE_RESET); irq_status = denali_wait_for_irq(denali, INTR__RST_COMP | INTR__INT_ACT | INTR__TIME_OUT); @@ -1119,8 +1125,7 @@ static void denali_hw_init(struct denali_nand_info *denali) * override it. */ if (!denali->revision) - denali->revision = - swab16(ioread32(denali->flash_reg + REVISION)); + denali->revision = swab16(ioread32(denali->reg + REVISION)); /* * tell driver how many bit controller will skip before @@ -1128,18 +1133,16 @@ static void denali_hw_init(struct denali_nand_info *denali) * set by firmware. So we read this value out. * if this value is 0, just let it be. */ - denali->bbtskipbytes = ioread32(denali->flash_reg + - SPARE_AREA_SKIP_BYTES); + denali->oob_skip_bytes = ioread32(denali->reg + SPARE_AREA_SKIP_BYTES); detect_max_banks(denali); - iowrite32(0x0F, denali->flash_reg + RB_PIN_ENABLED); - iowrite32(CHIP_EN_DONT_CARE__FLAG, - denali->flash_reg + CHIP_ENABLE_DONT_CARE); + iowrite32(0x0F, denali->reg + RB_PIN_ENABLED); + iowrite32(CHIP_EN_DONT_CARE__FLAG, denali->reg + CHIP_ENABLE_DONT_CARE); - iowrite32(0xffff, denali->flash_reg + SPARE_AREA_MARKER); + iowrite32(0xffff, denali->reg + SPARE_AREA_MARKER); /* Should set value for these registers when init */ - iowrite32(0, denali->flash_reg + TWO_ROW_ADDR_CYCLES); - iowrite32(1, denali->flash_reg + ECC_ENABLE); + iowrite32(0, denali->reg + TWO_ROW_ADDR_CYCLES); + iowrite32(1, denali->reg + ECC_ENABLE); } int denali_calc_ecc_bytes(int step_size, int strength) @@ -1152,7 +1155,7 @@ EXPORT_SYMBOL(denali_calc_ecc_bytes); static int denali_ecc_setup(struct mtd_info *mtd, struct nand_chip *chip, struct denali_nand_info *denali) { - int oobavail = mtd->oobsize - denali->bbtskipbytes; + int oobavail = mtd->oobsize - denali->oob_skip_bytes; int ret; /* @@ -1185,7 +1188,7 @@ static int denali_ooblayout_ecc(struct mtd_info *mtd, int section, if (section) return -ERANGE; - oobregion->offset = denali->bbtskipbytes; + oobregion->offset = denali->oob_skip_bytes; oobregion->length = chip->ecc.total; return 0; @@ -1200,7 +1203,7 @@ static int denali_ooblayout_free(struct mtd_info *mtd, int section, if (section) return -ERANGE; - oobregion->offset = chip->ecc.total + denali->bbtskipbytes; + oobregion->offset = chip->ecc.total + denali->oob_skip_bytes; oobregion->length = mtd->oobsize - oobregion->offset; return 0; @@ -1239,23 +1242,23 @@ static int denali_multidev_fixup(struct denali_nand_info *denali) * In this case, the core framework knows nothing about this fact, * so we should tell it the _logical_ pagesize and anything necessary. */ - denali->devnum = ioread32(denali->flash_reg + DEVICES_CONNECTED); + denali->devs_per_cs = ioread32(denali->reg + DEVICES_CONNECTED); /* * On some SoCs, DEVICES_CONNECTED is not auto-detected. * For those, DEVICES_CONNECTED is left to 0. Set 1 if it is the case. */ - if (denali->devnum == 0) { - denali->devnum = 1; - iowrite32(1, denali->flash_reg + DEVICES_CONNECTED); + if (denali->devs_per_cs == 0) { + denali->devs_per_cs = 1; + iowrite32(1, denali->reg + DEVICES_CONNECTED); } - if (denali->devnum == 1) + if (denali->devs_per_cs == 1) return 0; - if (denali->devnum != 2) { + if (denali->devs_per_cs != 2) { dev_err(denali->dev, "unsupported number of devices %d\n", - denali->devnum); + denali->devs_per_cs); return -EINVAL; } @@ -1273,7 +1276,7 @@ static int denali_multidev_fixup(struct denali_nand_info *denali) chip->ecc.size <<= 1; chip->ecc.bytes <<= 1; chip->ecc.strength <<= 1; - denali->bbtskipbytes <<= 1; + denali->oob_skip_bytes <<= 1; return 0; } @@ -1301,7 +1304,7 @@ int denali_init(struct denali_nand_info *denali) denali_enable_irq(denali); denali_reset_banks(denali); - denali->flash_bank = CHIP_SELECT_INVALID; + denali->active_bank = DENALI_INVALID_BANK; nand_set_flash_node(chip, denali->dev->of_node); /* Fallback to the default name if DT did not give "label" property */ @@ -1330,7 +1333,7 @@ int denali_init(struct denali_nand_info *denali) if (ret) goto disable_irq; - if (ioread32(denali->flash_reg + FEATURES) & FEATURES__DMA) + if (ioread32(denali->reg + FEATURES) & FEATURES__DMA) denali->dma_avail = 1; if (denali->dma_avail) { @@ -1374,19 +1377,19 @@ int denali_init(struct denali_nand_info *denali) chip->ecc.size, chip->ecc.strength, chip->ecc.bytes); iowrite32(MAKE_ECC_CORRECTION(chip->ecc.strength, 1), - denali->flash_reg + ECC_CORRECTION); + denali->reg + ECC_CORRECTION); iowrite32(mtd->erasesize / mtd->writesize, - denali->flash_reg + PAGES_PER_BLOCK); + denali->reg + PAGES_PER_BLOCK); iowrite32(chip->options & NAND_BUSWIDTH_16 ? 1 : 0, - denali->flash_reg + DEVICE_WIDTH); - iowrite32(mtd->writesize, denali->flash_reg + DEVICE_MAIN_AREA_SIZE); - iowrite32(mtd->oobsize, denali->flash_reg + DEVICE_SPARE_AREA_SIZE); + denali->reg + DEVICE_WIDTH); + iowrite32(mtd->writesize, denali->reg + DEVICE_MAIN_AREA_SIZE); + iowrite32(mtd->oobsize, denali->reg + DEVICE_SPARE_AREA_SIZE); - iowrite32(chip->ecc.size, denali->flash_reg + CFG_DATA_BLOCK_SIZE); - iowrite32(chip->ecc.size, denali->flash_reg + CFG_LAST_DATA_BLOCK_SIZE); + iowrite32(chip->ecc.size, denali->reg + CFG_DATA_BLOCK_SIZE); + iowrite32(chip->ecc.size, denali->reg + CFG_LAST_DATA_BLOCK_SIZE); /* chip->ecc.steps is set by nand_scan_tail(); not available here */ iowrite32(mtd->writesize / chip->ecc.size, - denali->flash_reg + CFG_NUM_DATA_BLOCKS); + denali->reg + CFG_NUM_DATA_BLOCKS); mtd_set_ooblayout(mtd, &denali_ooblayout_ops); diff --git a/drivers/mtd/nand/denali.h b/drivers/mtd/nand/denali.h index 657a794af695..237cc706b0fb 100644 --- a/drivers/mtd/nand/denali.h +++ b/drivers/mtd/nand/denali.h @@ -303,18 +303,13 @@ #define CHNL_ACTIVE__CHANNEL2 BIT(2) #define CHNL_ACTIVE__CHANNEL3 BIT(3) -#define MODE_00 0x00000000 -#define MODE_01 0x04000000 -#define MODE_10 0x08000000 -#define MODE_11 0x0C000000 - struct denali_nand_info { struct nand_chip nand; unsigned long clk_x_rate; /* bus interface clock rate */ - int flash_bank; /* currently selected chip */ + int active_bank; /* currently selected bank */ struct device *dev; - void __iomem *flash_reg; /* Register Interface */ - void __iomem *flash_mem; /* Host Data/Command Interface */ + void __iomem *reg; /* Register Interface */ + void __iomem *host; /* Host Data/Command Interface */ /* elements used by ISR */ struct completion complete; @@ -326,8 +321,8 @@ struct denali_nand_info { void *buf; dma_addr_t dma_addr; int dma_avail; - int devnum; /* represent how many nands connected */ - int bbtskipbytes; + int devs_per_cs; /* devices connected in parallel */ + int oob_skip_bytes; int max_banks; unsigned int revision; unsigned int caps; diff --git a/drivers/mtd/nand/denali_dt.c b/drivers/mtd/nand/denali_dt.c index ebcce50f4005..47f398edf18f 100644 --- a/drivers/mtd/nand/denali_dt.c +++ b/drivers/mtd/nand/denali_dt.c @@ -104,14 +104,14 @@ static int denali_dt_probe(struct platform_device *pdev) } res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "denali_reg"); - denali->flash_reg = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(denali->flash_reg)) - return PTR_ERR(denali->flash_reg); + denali->reg = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(denali->reg)) + return PTR_ERR(denali->reg); res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nand_data"); - denali->flash_mem = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(denali->flash_mem)) - return PTR_ERR(denali->flash_mem); + denali->host = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(denali->host)) + return PTR_ERR(denali->host); dt->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(dt->clk)) { diff --git a/drivers/mtd/nand/denali_pci.c b/drivers/mtd/nand/denali_pci.c index 6217525c1000..81370c79aa48 100644 --- a/drivers/mtd/nand/denali_pci.c +++ b/drivers/mtd/nand/denali_pci.c @@ -78,14 +78,14 @@ static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) return ret; } - denali->flash_reg = ioremap_nocache(csr_base, csr_len); - if (!denali->flash_reg) { + denali->reg = ioremap_nocache(csr_base, csr_len); + if (!denali->reg) { dev_err(&dev->dev, "Spectra: Unable to remap memory region\n"); return -ENOMEM; } - denali->flash_mem = ioremap_nocache(mem_base, mem_len); - if (!denali->flash_mem) { + denali->host = ioremap_nocache(mem_base, mem_len); + if (!denali->host) { dev_err(&dev->dev, "Spectra: ioremap_nocache failed!"); ret = -ENOMEM; goto failed_remap_reg; @@ -100,9 +100,9 @@ static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) return 0; failed_remap_mem: - iounmap(denali->flash_mem); + iounmap(denali->host); failed_remap_reg: - iounmap(denali->flash_reg); + iounmap(denali->reg); return ret; } @@ -112,8 +112,8 @@ static void denali_pci_remove(struct pci_dev *dev) struct denali_nand_info *denali = pci_get_drvdata(dev); denali_remove(denali); - iounmap(denali->flash_reg); - iounmap(denali->flash_mem); + iounmap(denali->reg); + iounmap(denali->host); } static struct pci_driver denali_pci_driver = { -- cgit v1.2.3-59-g8ed1b From d1ab0da84dcbac30a9039ccef72d69bf0a68bfc7 Mon Sep 17 00:00:00 2001 From: Prabhakar Kushwaha Date: Fri, 9 Jun 2017 16:27:21 +0530 Subject: mtd: nand: ifc: Initialize SRAM for all version >= 1.0 All IFC version >= 1.0 use 28nm technology for SRAM. Here SRAM has a requirement to initialize before any read operation performed for avoiding ECC Error. So update condition check to initialize SRAM for all IFC version >= 1.0.0 Signed-off-by: Prabhakar Kushwaha Signed-off-by: Boris Brezillon --- drivers/mtd/nand/fsl_ifc_nand.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/nand/fsl_ifc_nand.c b/drivers/mtd/nand/fsl_ifc_nand.c index d1c4538f870f..59408ec2c69f 100644 --- a/drivers/mtd/nand/fsl_ifc_nand.c +++ b/drivers/mtd/nand/fsl_ifc_nand.c @@ -913,7 +913,7 @@ static int fsl_ifc_chip_init(struct fsl_ifc_mtd *priv) chip->ecc.algo = NAND_ECC_HAMMING; } - if (ctrl->version == FSL_IFC_VERSION_1_1_0) + if (ctrl->version >= FSL_IFC_VERSION_1_1_0) fsl_ifc_sram_init(priv); return 0; -- cgit v1.2.3-59-g8ed1b From df1d178879f53d7f790d4bc372aa0fc5d5423328 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Tue, 23 May 2017 07:30:19 +0200 Subject: dt-bindings: mtd: make partitions doc a bit more generic MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently the only documented partitioning is "fixed-partitions" but there are more methods in use that we may want to support in the future. Mention them and make it clear Fixed Partitions are just a single case. Signed-off-by: Brian Norris Signed-off-by: Rafał Miłecki Acked-by: Rob Herring --- .../devicetree/bindings/mtd/partition.txt | 32 ++++++++++++++++++---- 1 file changed, 26 insertions(+), 6 deletions(-) diff --git a/Documentation/devicetree/bindings/mtd/partition.txt b/Documentation/devicetree/bindings/mtd/partition.txt index 81a224da63be..36f3b769a626 100644 --- a/Documentation/devicetree/bindings/mtd/partition.txt +++ b/Documentation/devicetree/bindings/mtd/partition.txt @@ -1,29 +1,49 @@ -Representing flash partitions in devicetree +Flash partitions in device tree +=============================== -Partitions can be represented by sub-nodes of an mtd device. This can be used +Flash devices can be partitioned into one or more functional ranges (e.g. "boot +code", "nvram", "kernel"). + +Different devices may be partitioned in a different ways. Some may use a fixed +flash layout set at production time. Some may use on-flash table that describes +the geometry and naming/purpose of each functional region. It is also possible +to see these methods mixed. + +To assist system software in locating partitions, we allow describing which +method is used for a given flash device. To describe the method there should be +a subnode of the flash device that is named 'partitions'. It must have a +'compatible' property, which is used to identify the method to use. + +We currently only document a binding for fixed layouts. + + +Fixed Partitions +================ + +Partitions can be represented by sub-nodes of a flash device. This can be used on platforms which have strong conventions about which portions of a flash are used for what purposes, but which don't use an on-flash partition table such as RedBoot. -The partition table should be a subnode of the mtd node and should be named +The partition table should be a subnode of the flash node and should be named 'partitions'. This node should have the following property: - compatible : (required) must be "fixed-partitions" Partitions are then defined in subnodes of the partitions node. -For backwards compatibility partitions as direct subnodes of the mtd device are +For backwards compatibility partitions as direct subnodes of the flash device are supported. This use is discouraged. NOTE: also for backwards compatibility, direct subnodes that have a compatible string are not considered partitions, as they may be used for other bindings. #address-cells & #size-cells must both be present in the partitions subnode of the -mtd device. There are two valid values for both: +flash device. There are two valid values for both: <1>: for partitions that require a single 32-bit cell to represent their size/address (aka the value is below 4 GiB) <2>: for partitions that require two 32-bit cells to represent their size/address (aka the value is 4 GiB or greater). Required properties: -- reg : The partition's offset and size within the mtd bank. +- reg : The partition's offset and size within the flash Optional properties: - label : The label / name for this partition. If omitted, the label is taken -- cgit v1.2.3-59-g8ed1b From 01f9c7240a900d5676a8496496f2974dd36996b1 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Tue, 23 May 2017 07:30:20 +0200 Subject: mtd: partitions: factor out code calling parser MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This code is going to be reused for parsers matched using OF so let's factor it out to make this easier. Signed-off-by: Brian Norris Signed-off-by: Rafał Miłecki Acked-by: Brian Norris --- drivers/mtd/mtdpart.c | 33 ++++++++++++++++++++++++--------- 1 file changed, 24 insertions(+), 9 deletions(-) diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index 2e152e53ace0..7ececd3d7799 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -807,6 +807,27 @@ static const char * const default_mtd_part_types[] = { NULL }; +static int mtd_part_do_parse(struct mtd_part_parser *parser, + struct mtd_info *master, + struct mtd_partitions *pparts, + struct mtd_part_parser_data *data) +{ + int ret; + + ret = (*parser->parse_fn)(master, &pparts->parts, data); + pr_debug("%s: parser %s: %i\n", master->name, parser->name, ret); + if (ret <= 0) + return ret; + + pr_notice("%d %s partitions found on MTD device %s\n", ret, + parser->name, master->name); + + pparts->nr_parts = ret; + pparts->parser = parser; + + return ret; +} + /** * parse_mtd_partitions - parse MTD partitions * @master: the master partition (describes whole MTD device) @@ -847,16 +868,10 @@ int parse_mtd_partitions(struct mtd_info *master, const char *const *types, parser ? parser->name : NULL); if (!parser) continue; - ret = (*parser->parse_fn)(master, &pparts->parts, data); - pr_debug("%s: parser %s: %i\n", - master->name, parser->name, ret); - if (ret > 0) { - printk(KERN_NOTICE "%d %s partitions found on MTD device %s\n", - ret, parser->name, master->name); - pparts->nr_parts = ret; - pparts->parser = parser; + ret = mtd_part_do_parse(parser, master, pparts, data); + /* Found partitions! */ + if (ret > 0) return 0; - } mtd_part_parser_put(parser); /* * Stash the first error we see; only report it if no parser -- cgit v1.2.3-59-g8ed1b From 0cbef932bd82857823c0e52b08218b0c9920a475 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Wed, 21 Jun 2017 00:18:43 +0930 Subject: spi-nor: Add Winbond w25m512jv Similar to the other ones, different size. The "JV" suffix is in the datasheet, I haven't seen mentions of a different one. The datasheet indicates DUAL and QUAD are supported. http://www.winbond.com/resource-files/w25m512jv%20revc%2001062017.pdf Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Joel Stanley Signed-off-by: Cyrille Pitchen --- drivers/mtd/spi-nor/spi-nor.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index eef55b597ec7..43de5adafcb7 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -1146,6 +1146,8 @@ static const struct flash_info spi_nor_ids[] = { { "w25q80bl", INFO(0xef4014, 0, 64 * 1024, 16, SECT_4K) }, { "w25q128", INFO(0xef4018, 0, 64 * 1024, 256, SECT_4K) }, { "w25q256", INFO(0xef4019, 0, 64 * 1024, 512, SECT_4K) }, + { "w25m512jv", INFO(0xef7119, 0, 64 * 1024, 1024, + SECT_4K | SPI_NOR_QUAD_READ | SPI_NOR_DUAL_READ) }, /* Catalyst / On Semiconductor -- non-JEDEC */ { "cat25c11", CAT25_INFO( 16, 8, 16, 1, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) }, -- cgit v1.2.3-59-g8ed1b From f993c123b461ff47c10edfee65465fe651d0521f Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Fri, 16 Jun 2017 15:05:17 +0530 Subject: mtd: spi-nor: cqspi: make of_device_ids const of_device_ids are not supposed to change at runtime. All functions working with of_device_ids provided by work with const of_device_ids. So mark the non-const structs as const. Signed-off-by: Arvind Yadav Reviewed-by: Marek Vasut Signed-off-by: Cyrille Pitchen --- drivers/mtd/spi-nor/cadence-quadspi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c index 40096d73536c..d315c326e72f 100644 --- a/drivers/mtd/spi-nor/cadence-quadspi.c +++ b/drivers/mtd/spi-nor/cadence-quadspi.c @@ -1283,7 +1283,7 @@ static const struct dev_pm_ops cqspi__dev_pm_ops = { #define CQSPI_DEV_PM_OPS NULL #endif -static struct of_device_id const cqspi_dt_ids[] = { +static const struct of_device_id const cqspi_dt_ids[] = { {.compatible = "cdns,qspi-nor",}, { /* end of table */ } }; -- cgit v1.2.3-59-g8ed1b From ce398a8141b485e4c97bd313c4c06cb6f64a22d7 Mon Sep 17 00:00:00 2001 From: Cédric Le Goater Date: Wed, 19 Apr 2017 16:00:19 +0200 Subject: mtd: spi-nor: Add support for Macronix mx66l1g45g spi flash MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These modules are used on the OpenPOWER Witherspoon systems to hold the POWER9 host firmware image. The SPI_NOR_DUAL_READ flags is added for the Aspeed SoCs which do not support QUAD reads. Signed-off-by: Cédric Le Goater Reviewed-by: Marek Vasut Signed-off-by: Cyrille Pitchen --- drivers/mtd/spi-nor/spi-nor.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 43de5adafcb7..032cb13c8135 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -1012,6 +1012,7 @@ static const struct flash_info spi_nor_ids[] = { { "mx25u25635f", INFO(0xc22539, 0, 64 * 1024, 512, SECT_4K | SPI_NOR_4B_OPCODES) }, { "mx25l25655e", INFO(0xc22619, 0, 64 * 1024, 512, 0) }, { "mx66l51235l", INFO(0xc2201a, 0, 64 * 1024, 1024, SPI_NOR_QUAD_READ) }, + { "mx66l1g45g", INFO(0xc2201b, 0, 64 * 1024, 2048, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) }, { "mx66l1g55g", INFO(0xc2261b, 0, 64 * 1024, 2048, SPI_NOR_QUAD_READ) }, /* Micron */ -- cgit v1.2.3-59-g8ed1b From d7c9ade2e31dbae4deaa8a5198107ecde4c56968 Mon Sep 17 00:00:00 2001 From: Cédric Le Goater Date: Wed, 19 Apr 2017 16:00:20 +0200 Subject: mtd: spi-nor: add Dual and Quad read mode support to some flash devices MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These devices are used on OpenPOWER systems. The SPI_NOR_DUAL_READ flags is added for the Aspeed SoCs which do not support QUAD reads. Signed-off-by: Cédric Le Goater Reviewed-by: Marek Vasut Signed-off-by: Cyrille Pitchen --- drivers/mtd/spi-nor/spi-nor.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 032cb13c8135..040ab5d7ac05 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -1008,10 +1008,10 @@ static const struct flash_info spi_nor_ids[] = { { "mx25u6435f", INFO(0xc22537, 0, 64 * 1024, 128, SECT_4K) }, { "mx25l12805d", INFO(0xc22018, 0, 64 * 1024, 256, 0) }, { "mx25l12855e", INFO(0xc22618, 0, 64 * 1024, 256, 0) }, - { "mx25l25635e", INFO(0xc22019, 0, 64 * 1024, 512, 0) }, + { "mx25l25635e", INFO(0xc22019, 0, 64 * 1024, 512, SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) }, { "mx25u25635f", INFO(0xc22539, 0, 64 * 1024, 512, SECT_4K | SPI_NOR_4B_OPCODES) }, { "mx25l25655e", INFO(0xc22619, 0, 64 * 1024, 512, 0) }, - { "mx66l51235l", INFO(0xc2201a, 0, 64 * 1024, 1024, SPI_NOR_QUAD_READ) }, + { "mx66l51235l", INFO(0xc2201a, 0, 64 * 1024, 1024, SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) }, { "mx66l1g45g", INFO(0xc2201b, 0, 64 * 1024, 2048, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) }, { "mx66l1g55g", INFO(0xc2261b, 0, 64 * 1024, 2048, SPI_NOR_QUAD_READ) }, @@ -1023,7 +1023,7 @@ static const struct flash_info spi_nor_ids[] = { { "n25q064a", INFO(0x20bb17, 0, 64 * 1024, 128, SECT_4K | SPI_NOR_QUAD_READ) }, { "n25q128a11", INFO(0x20bb18, 0, 64 * 1024, 256, SECT_4K | SPI_NOR_QUAD_READ) }, { "n25q128a13", INFO(0x20ba18, 0, 64 * 1024, 256, SECT_4K | SPI_NOR_QUAD_READ) }, - { "n25q256a", INFO(0x20ba19, 0, 64 * 1024, 512, SECT_4K | SPI_NOR_QUAD_READ) }, + { "n25q256a", INFO(0x20ba19, 0, 64 * 1024, 512, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) }, { "n25q256ax1", INFO(0x20bb19, 0, 64 * 1024, 512, SECT_4K | SPI_NOR_QUAD_READ) }, { "n25q512a", INFO(0x20bb20, 0, 64 * 1024, 1024, SECT_4K | USE_FSR | SPI_NOR_QUAD_READ) }, { "n25q512ax3", INFO(0x20ba20, 0, 64 * 1024, 1024, SECT_4K | USE_FSR | SPI_NOR_QUAD_READ) }, @@ -1146,7 +1146,7 @@ static const struct flash_info spi_nor_ids[] = { { "w25q80", INFO(0xef5014, 0, 64 * 1024, 16, SECT_4K) }, { "w25q80bl", INFO(0xef4014, 0, 64 * 1024, 16, SECT_4K) }, { "w25q128", INFO(0xef4018, 0, 64 * 1024, 256, SECT_4K) }, - { "w25q256", INFO(0xef4019, 0, 64 * 1024, 512, SECT_4K) }, + { "w25q256", INFO(0xef4019, 0, 64 * 1024, 512, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) }, { "w25m512jv", INFO(0xef7119, 0, 64 * 1024, 1024, SECT_4K | SPI_NOR_QUAD_READ | SPI_NOR_DUAL_READ) }, -- cgit v1.2.3-59-g8ed1b From a9f127bb5f92379ecb135a66bb89f8403e998d96 Mon Sep 17 00:00:00 2001 From: Cédric Le Goater Date: Thu, 20 Apr 2017 13:56:34 +0200 Subject: mtd: spi-nor: aspeed: remove dummies from keep mask MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is no need to keep the dummy bytes in the control register if the command mode is not kept also. This could lead to an inconsistent setting : normal read mode (command 0x3) and dummy bytes. It is to be noted that the HW allows such a configuration. Signed-off-by: Cédric Le Goater Reviewed-by: Marek Vasut Signed-off-by: Cyrille Pitchen --- drivers/mtd/spi-nor/aspeed-smc.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/mtd/spi-nor/aspeed-smc.c b/drivers/mtd/spi-nor/aspeed-smc.c index 3f875c8d6339..d76663b369db 100644 --- a/drivers/mtd/spi-nor/aspeed-smc.c +++ b/drivers/mtd/spi-nor/aspeed-smc.c @@ -180,8 +180,7 @@ struct aspeed_smc_controller { #define CONTROL_KEEP_MASK \ (CONTROL_AAF_MODE | CONTROL_CE_INACTIVE_MASK | CONTROL_CLK_DIV4 | \ - CONTROL_IO_DUMMY_MASK | CONTROL_CLOCK_FREQ_SEL_MASK | \ - CONTROL_LSB_FIRST | CONTROL_CLOCK_MODE_3) + CONTROL_CLOCK_FREQ_SEL_MASK | CONTROL_LSB_FIRST | CONTROL_CLOCK_MODE_3) /* * The Segment Register uses a 8MB unit to encode the start address -- cgit v1.2.3-59-g8ed1b From e6f0acb2f0da89625aefc84b448f457b9161436b Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Thu, 15 Jun 2017 10:54:23 -0700 Subject: bridge: Fix panel-bridge error return on !panel. ERR_PTR() needs a negative errno argument. Signed-off-by: Eric Anholt Signed-off-by: Archit Taneja Link: http://patchwork.freedesktop.org/patch/msgid/20170615175423.17954-1-eric@anholt.net --- drivers/gpu/drm/bridge/panel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/bridge/panel.c b/drivers/gpu/drm/bridge/panel.c index 99f9a4beb859..67fe19e5a9c6 100644 --- a/drivers/gpu/drm/bridge/panel.c +++ b/drivers/gpu/drm/bridge/panel.c @@ -161,7 +161,7 @@ struct drm_bridge *drm_panel_bridge_add(struct drm_panel *panel, int ret; if (!panel) - return ERR_PTR(EINVAL); + return ERR_PTR(-EINVAL); panel_bridge = devm_kzalloc(panel->dev, sizeof(*panel_bridge), GFP_KERNEL); -- cgit v1.2.3-59-g8ed1b From 7ef0e5e16d18a38af489bea7193ba3b2be31ee58 Mon Sep 17 00:00:00 2001 From: Cédric Le Goater Date: Thu, 20 Apr 2017 13:56:36 +0200 Subject: mtd: spi-nor: aspeed: configure chip window on AHB bus MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The segment registers of the SMC controller provide a way to configure the mapping windows of the chips on the AHB bus. The settings are required to be correct when the controller operates in Command mode, which is the case for DMAs and the LPC mapping. This tries to set the segment registers of each chip depending on the size of the flash device and depending on the previous segment settings, in order to have a contiguous window across multiple chips. Unfortunately, the AST2500 SPI controller has a bug and it is not possible to configure a full 128MB window for a chip of the same size. The window size needs to be restricted to 120MB. This issue only applies to CE0. Signed-off-by: Cédric Le Goater Reviewed-by: Marek Vasut Signed-off-by: Cyrille Pitchen --- drivers/mtd/spi-nor/aspeed-smc.c | 157 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 154 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/spi-nor/aspeed-smc.c b/drivers/mtd/spi-nor/aspeed-smc.c index d76663b369db..0106357421bd 100644 --- a/drivers/mtd/spi-nor/aspeed-smc.c +++ b/drivers/mtd/spi-nor/aspeed-smc.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #define DEVICE_NAME "aspeed-smc" @@ -97,6 +98,7 @@ struct aspeed_smc_chip { struct aspeed_smc_controller *controller; void __iomem *ctl; /* control register */ void __iomem *ahb_base; /* base of chip window */ + u32 ahb_window_size; /* chip mapping window size */ u32 ctl_val[smc_max]; /* control settings */ enum aspeed_smc_flash_type type; /* what type of flash */ struct spi_nor nor; @@ -109,6 +111,7 @@ struct aspeed_smc_controller { const struct aspeed_smc_info *info; /* type info of controller */ void __iomem *regs; /* controller registers */ void __iomem *ahb_base; /* per-chip windows resource */ + u32 ahb_window_size; /* full mapping window size */ struct aspeed_smc_chip *chips[0]; /* pointers to attached chips */ }; @@ -193,6 +196,10 @@ struct aspeed_smc_controller { #define SEGMENT_ADDR_REG0 0x30 #define SEGMENT_ADDR_START(_r) ((((_r) >> 16) & 0xFF) << 23) #define SEGMENT_ADDR_END(_r) ((((_r) >> 24) & 0xFF) << 23) +#define SEGMENT_ADDR_VALUE(start, end) \ + (((((start) >> 23) & 0xFF) << 16) | ((((end) >> 23) & 0xFF) << 24)) +#define SEGMENT_ADDR_REG(controller, cs) \ + ((controller)->regs + SEGMENT_ADDR_REG0 + (cs) * 4) /* * In user mode all data bytes read or written to the chip decode address @@ -438,8 +445,7 @@ static void __iomem *aspeed_smc_chip_base(struct aspeed_smc_chip *chip, u32 reg; if (controller->info->nce > 1) { - reg = readl(controller->regs + SEGMENT_ADDR_REG0 + - chip->cs * 4); + reg = readl(SEGMENT_ADDR_REG(controller, chip->cs)); if (SEGMENT_ADDR_START(reg) >= SEGMENT_ADDR_END(reg)) return NULL; @@ -450,6 +456,146 @@ static void __iomem *aspeed_smc_chip_base(struct aspeed_smc_chip *chip, return controller->ahb_base + offset; } +static u32 aspeed_smc_ahb_base_phy(struct aspeed_smc_controller *controller) +{ + u32 seg0_val = readl(SEGMENT_ADDR_REG(controller, 0)); + + return SEGMENT_ADDR_START(seg0_val); +} + +static u32 chip_set_segment(struct aspeed_smc_chip *chip, u32 cs, u32 start, + u32 size) +{ + struct aspeed_smc_controller *controller = chip->controller; + void __iomem *seg_reg; + u32 seg_oldval, seg_newval, ahb_base_phy, end; + + ahb_base_phy = aspeed_smc_ahb_base_phy(controller); + + seg_reg = SEGMENT_ADDR_REG(controller, cs); + seg_oldval = readl(seg_reg); + + /* + * If the chip size is not specified, use the default segment + * size, but take into account the possible overlap with the + * previous segment + */ + if (!size) + size = SEGMENT_ADDR_END(seg_oldval) - start; + + /* + * The segment cannot exceed the maximum window size of the + * controller. + */ + if (start + size > ahb_base_phy + controller->ahb_window_size) { + size = ahb_base_phy + controller->ahb_window_size - start; + dev_warn(chip->nor.dev, "CE%d window resized to %dMB", + cs, size >> 20); + } + + end = start + size; + seg_newval = SEGMENT_ADDR_VALUE(start, end); + writel(seg_newval, seg_reg); + + /* + * Restore default value if something goes wrong. The chip + * might have set some bogus value and we would loose access + * to the chip. + */ + if (seg_newval != readl(seg_reg)) { + dev_err(chip->nor.dev, "CE%d window invalid", cs); + writel(seg_oldval, seg_reg); + start = SEGMENT_ADDR_START(seg_oldval); + end = SEGMENT_ADDR_END(seg_oldval); + size = end - start; + } + + dev_info(chip->nor.dev, "CE%d window [ 0x%.8x - 0x%.8x ] %dMB", + cs, start, end, size >> 20); + + return size; +} + +/* + * The segment register defines the mapping window on the AHB bus and + * it needs to be configured depending on the chip size. The segment + * register of the following CE also needs to be tuned in order to + * provide a contiguous window across multiple chips. + * + * This is expected to be called in increasing CE order + */ +static u32 aspeed_smc_chip_set_segment(struct aspeed_smc_chip *chip) +{ + struct aspeed_smc_controller *controller = chip->controller; + u32 ahb_base_phy, start; + u32 size = chip->nor.mtd.size; + + /* + * Each controller has a chip size limit for direct memory + * access + */ + if (size > controller->info->maxsize) + size = controller->info->maxsize; + + /* + * The AST2400 SPI controller only handles one chip and does + * not have segment registers. Let's use the chip size for the + * AHB window. + */ + if (controller->info == &spi_2400_info) + goto out; + + /* + * The AST2500 SPI controller has a HW bug when the CE0 chip + * size reaches 128MB. Enforce a size limit of 120MB to + * prevent the controller from using bogus settings in the + * segment register. + */ + if (chip->cs == 0 && controller->info == &spi_2500_info && + size == SZ_128M) { + size = 120 << 20; + dev_info(chip->nor.dev, + "CE%d window resized to %dMB (AST2500 HW quirk)", + chip->cs, size >> 20); + } + + ahb_base_phy = aspeed_smc_ahb_base_phy(controller); + + /* + * As a start address for the current segment, use the default + * start address if we are handling CE0 or use the previous + * segment ending address + */ + if (chip->cs) { + u32 prev = readl(SEGMENT_ADDR_REG(controller, chip->cs - 1)); + + start = SEGMENT_ADDR_END(prev); + } else { + start = ahb_base_phy; + } + + size = chip_set_segment(chip, chip->cs, start, size); + + /* Update chip base address on the AHB bus */ + chip->ahb_base = controller->ahb_base + (start - ahb_base_phy); + + /* + * Now, make sure the next segment does not overlap with the + * current one we just configured, even if there is no + * available chip. That could break access in Command Mode. + */ + if (chip->cs < controller->info->nce - 1) + chip_set_segment(chip, chip->cs + 1, start + size, 0); + +out: + if (size < chip->nor.mtd.size) + dev_warn(chip->nor.dev, + "CE%d window too small for chip %dMB", + chip->cs, (u32)chip->nor.mtd.size >> 20); + + return size; +} + static void aspeed_smc_chip_enable_write(struct aspeed_smc_chip *chip) { struct aspeed_smc_controller *controller = chip->controller; @@ -523,7 +669,7 @@ static int aspeed_smc_chip_setup_init(struct aspeed_smc_chip *chip, */ chip->ahb_base = aspeed_smc_chip_base(chip, res); if (!chip->ahb_base) { - dev_warn(chip->nor.dev, "CE segment window closed.\n"); + dev_warn(chip->nor.dev, "CE%d window closed", chip->cs); return -EINVAL; } @@ -570,6 +716,9 @@ static int aspeed_smc_chip_setup_finish(struct aspeed_smc_chip *chip) if (chip->nor.addr_width == 4 && info->set_4b) info->set_4b(chip); + /* This is for direct AHB access when using Command Mode. */ + chip->ahb_window_size = aspeed_smc_chip_set_segment(chip); + /* * base mode has not been optimized yet. use it for writes. */ @@ -733,6 +882,8 @@ static int aspeed_smc_probe(struct platform_device *pdev) if (IS_ERR(controller->ahb_base)) return PTR_ERR(controller->ahb_base); + controller->ahb_window_size = resource_size(res); + ret = aspeed_smc_setup_flash(controller, np, res); if (ret) dev_err(dev, "Aspeed SMC probe failed %d\n", ret); -- cgit v1.2.3-59-g8ed1b From fe496e23b74852cbb2df7e0a6e26752131c41bb6 Mon Sep 17 00:00:00 2001 From: Tom Rini Date: Wed, 21 Jun 2017 08:22:06 -0400 Subject: dt-bindings: mtd: elm: Correct compatible string requirement The binding says that the compatible string must be "ti,am33xx-elm" but the code checks only for, and all functioning users set, this as "ti,am3352-elm" so correct the binding. Cc: David Woodhouse Cc: Brian Norris Cc: Boris Brezillon Cc: Marek Vasut Cc: Richard Weinberger Cc: Cyrille Pitchen Cc: Rob Herring Cc: Mark Rutland Signed-off-by: Tom Rini Signed-off-by: Boris Brezillon --- Documentation/devicetree/bindings/mtd/elm.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/mtd/elm.txt b/Documentation/devicetree/bindings/mtd/elm.txt index 8c1528c421d4..59ddc61c1076 100644 --- a/Documentation/devicetree/bindings/mtd/elm.txt +++ b/Documentation/devicetree/bindings/mtd/elm.txt @@ -1,7 +1,7 @@ Error location module Required properties: -- compatible: Must be "ti,am33xx-elm" +- compatible: Must be "ti,am3352-elm" - reg: physical base address and size of the registers map. - interrupts: Interrupt number for the elm. -- cgit v1.2.3-59-g8ed1b From a7adb70a73b7cb220f4515745d2671d2226e0097 Mon Sep 17 00:00:00 2001 From: Tom Rini Date: Wed, 21 Jun 2017 08:14:54 -0400 Subject: dt-bindings: gpmc: Correct location of generic gpmc binding The binding bus/ti-gpmc.txt has been moved to memory-controllers/omap-gpmc.txt. Update all references to this in order to make reading and understanding a given binding easier. Cc: David Woodhouse Cc: Brian Norris Cc:Boris Brezillon Cc: Marek Vasut Cc: Richard Weinberger Cc: Cyrille Pitchen Cc: Rob Herring Cc: Mark Rutland Signed-off-by: Tom Rini Signed-off-by: Boris Brezillon --- Documentation/devicetree/bindings/mtd/gpmc-nand.txt | 2 +- Documentation/devicetree/bindings/mtd/gpmc-nor.txt | 4 ++-- Documentation/devicetree/bindings/mtd/gpmc-onenand.txt | 2 +- Documentation/devicetree/bindings/net/gpmc-eth.txt | 4 ++-- 4 files changed, 6 insertions(+), 6 deletions(-) diff --git a/Documentation/devicetree/bindings/mtd/gpmc-nand.txt b/Documentation/devicetree/bindings/mtd/gpmc-nand.txt index 174f68c26c1b..dd559045593d 100644 --- a/Documentation/devicetree/bindings/mtd/gpmc-nand.txt +++ b/Documentation/devicetree/bindings/mtd/gpmc-nand.txt @@ -5,7 +5,7 @@ the GPMC controller with a name of "nand". All timing relevant properties as well as generic gpmc child properties are explained in a separate documents - please refer to -Documentation/devicetree/bindings/bus/ti-gpmc.txt +Documentation/devicetree/bindings/memory-controllers/omap-gpmc.txt For NAND specific properties such as ECC modes or bus width, please refer to Documentation/devicetree/bindings/mtd/nand.txt diff --git a/Documentation/devicetree/bindings/mtd/gpmc-nor.txt b/Documentation/devicetree/bindings/mtd/gpmc-nor.txt index 4828c17bb784..131d3a74d0bd 100644 --- a/Documentation/devicetree/bindings/mtd/gpmc-nor.txt +++ b/Documentation/devicetree/bindings/mtd/gpmc-nor.txt @@ -5,7 +5,7 @@ child nodes of the GPMC controller with a name of "nor". All timing relevant properties as well as generic GPMC child properties are explained in a separate documents. Please refer to -Documentation/devicetree/bindings/bus/ti-gpmc.txt +Documentation/devicetree/bindings/memory-controllers/omap-gpmc.txt Required properties: - bank-width: Width of NOR flash in bytes. GPMC supports 8-bit and @@ -28,7 +28,7 @@ Required properties: Optional properties: - gpmc,XXX Additional GPMC timings and settings parameters. See - Documentation/devicetree/bindings/bus/ti-gpmc.txt + Documentation/devicetree/bindings/memory-controllers/omap-gpmc.txt Optional properties for partition table parsing: - #address-cells: should be set to 1 diff --git a/Documentation/devicetree/bindings/mtd/gpmc-onenand.txt b/Documentation/devicetree/bindings/mtd/gpmc-onenand.txt index 5d8fa527c496..b6e8bfd024f4 100644 --- a/Documentation/devicetree/bindings/mtd/gpmc-onenand.txt +++ b/Documentation/devicetree/bindings/mtd/gpmc-onenand.txt @@ -5,7 +5,7 @@ the GPMC controller with a name of "onenand". All timing relevant properties as well as generic gpmc child properties are explained in a separate documents - please refer to -Documentation/devicetree/bindings/bus/ti-gpmc.txt +Documentation/devicetree/bindings/memory-controllers/omap-gpmc.txt Required properties: diff --git a/Documentation/devicetree/bindings/net/gpmc-eth.txt b/Documentation/devicetree/bindings/net/gpmc-eth.txt index ace4a64b3695..f7da3d73ca1b 100644 --- a/Documentation/devicetree/bindings/net/gpmc-eth.txt +++ b/Documentation/devicetree/bindings/net/gpmc-eth.txt @@ -9,7 +9,7 @@ the GPMC controller with an "ethernet" name. All timing relevant properties as well as generic GPMC child properties are explained in a separate documents. Please refer to -Documentation/devicetree/bindings/bus/ti-gpmc.txt +Documentation/devicetree/bindings/memory-controllers/omap-gpmc.txt For the properties relevant to the ethernet controller connected to the GPMC refer to the binding documentation of the device. For example, the documentation @@ -43,7 +43,7 @@ Required properties: Optional properties: - gpmc,XXX Additional GPMC timings and settings parameters. See - Documentation/devicetree/bindings/bus/ti-gpmc.txt + Documentation/devicetree/bindings/memory-controllers/omap-gpmc.txt Example: -- cgit v1.2.3-59-g8ed1b From a57ce439505da3801e264656a3bdf746505c77ec Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 21 Jun 2017 18:23:11 +0900 Subject: MAINTAINERS: add entry for Denali NAND controller driver The Denali NAND controller driver (drivers/mtd/nand/denali*) has been largely reworked by me. Add myself as its maintainer now. Signed-off-by: Masahiro Yamada Signed-off-by: Boris Brezillon --- MAINTAINERS | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index f7d568b8f133..4abec10fe630 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3888,6 +3888,12 @@ M: Pali Rohár S: Maintained F: drivers/platform/x86/dell-wmi.c +DENALI NAND DRIVER +M: Masahiro Yamada +L: linux-mtd@lists.infradead.org +S: Supported +F: drivers/mtd/nand/denali* + DESIGNWARE USB2 DRD IP DRIVER M: John Youn L: linux-usb@vger.kernel.org -- cgit v1.2.3-59-g8ed1b From 08263a9ae664b24fa777d20b365601534842b236 Mon Sep 17 00:00:00 2001 From: Rafał Miłecki Date: Wed, 21 Jun 2017 08:26:42 +0200 Subject: mtd: partitions: add helper for deleting partition MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are two similar functions handling deletion. One handles single partition and another the whole MTD flash device. They share (duplicate) some code so it makes sense to add a small helper for that part. Function del_mtd_partitions has been moved a bit to keep all deleting stuff together. Signed-off-by: Rafał Miłecki Signed-off-by: Brian Norris --- drivers/mtd/mtdpart.c | 75 +++++++++++++++++++++++++++++---------------------- 1 file changed, 43 insertions(+), 32 deletions(-) diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index 7ececd3d7799..bcec72148d0b 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -363,32 +363,6 @@ static inline void free_partition(struct mtd_part *p) kfree(p); } -/* - * This function unregisters and destroy all slave MTD objects which are - * attached to the given master MTD object. - */ - -int del_mtd_partitions(struct mtd_info *master) -{ - struct mtd_part *slave, *next; - int ret, err = 0; - - mutex_lock(&mtd_partitions_mutex); - list_for_each_entry_safe(slave, next, &mtd_partitions, list) - if (slave->master == master) { - ret = del_mtd_device(&slave->mtd); - if (ret < 0) { - err = ret; - continue; - } - list_del(&slave->list); - free_partition(slave); - } - mutex_unlock(&mtd_partitions_mutex); - - return err; -} - static struct mtd_part *allocate_partition(struct mtd_info *master, const struct mtd_partition *part, int partno, uint64_t cur_offset) @@ -675,6 +649,48 @@ int mtd_add_partition(struct mtd_info *master, const char *name, } EXPORT_SYMBOL_GPL(mtd_add_partition); +/** + * __mtd_del_partition - delete MTD partition + * + * @priv: internal MTD struct for partition to be deleted + * + * This function must be called with the partitions mutex locked. + */ +static int __mtd_del_partition(struct mtd_part *priv) +{ + int err; + + err = del_mtd_device(&priv->mtd); + if (err) + return err; + + list_del(&priv->list); + free_partition(priv); + + return 0; +} + +/* + * This function unregisters and destroy all slave MTD objects which are + * attached to the given master MTD object. + */ +int del_mtd_partitions(struct mtd_info *master) +{ + struct mtd_part *slave, *next; + int ret, err = 0; + + mutex_lock(&mtd_partitions_mutex); + list_for_each_entry_safe(slave, next, &mtd_partitions, list) + if (slave->master == master) { + ret = __mtd_del_partition(slave); + if (ret < 0) + err = ret; + } + mutex_unlock(&mtd_partitions_mutex); + + return err; +} + int mtd_del_partition(struct mtd_info *master, int partno) { struct mtd_part *slave, *next; @@ -686,12 +702,7 @@ int mtd_del_partition(struct mtd_info *master, int partno) (slave->mtd.index == partno)) { sysfs_remove_files(&slave->mtd.dev.kobj, mtd_partition_attrs); - ret = del_mtd_device(&slave->mtd); - if (ret < 0) - break; - - list_del(&slave->list); - free_partition(slave); + ret = __mtd_del_partition(slave); break; } mutex_unlock(&mtd_partitions_mutex); -- cgit v1.2.3-59-g8ed1b From c5ceaba74083daf619bdb34d4871e297a177eebf Mon Sep 17 00:00:00 2001 From: Rafał Miłecki Date: Wed, 21 Jun 2017 08:26:43 +0200 Subject: mtd: partitions: remove sysfs files when deleting all master's partitions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When support for sysfs "offset" file was added it missed to update the del_mtd_partitions function. It deletes partitions just like mtd_del_partition does so both should also take care of removing sysfs files. This change moves sysfs_remove_files call to the shared function to fix this issue. Fixes: a62c24d755291 ("mtd: part: Add sysfs variable for offset of partition") Cc: Dan Ehrenberg Signed-off-by: Rafał Miłecki Signed-off-by: Brian Norris --- drivers/mtd/mtdpart.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index bcec72148d0b..9434050accc7 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -660,6 +660,8 @@ static int __mtd_del_partition(struct mtd_part *priv) { int err; + sysfs_remove_files(&priv->mtd.dev.kobj, mtd_partition_attrs); + err = del_mtd_device(&priv->mtd); if (err) return err; @@ -700,8 +702,6 @@ int mtd_del_partition(struct mtd_info *master, int partno) list_for_each_entry_safe(slave, next, &mtd_partitions, list) if ((slave->master == master) && (slave->mtd.index == partno)) { - sysfs_remove_files(&slave->mtd.dev.kobj, - mtd_partition_attrs); ret = __mtd_del_partition(slave); break; } -- cgit v1.2.3-59-g8ed1b From 0a9d72b69da6d8dae1abd7990c6c4c749846ef3e Mon Sep 17 00:00:00 2001 From: Rafał Miłecki Date: Wed, 21 Jun 2017 08:26:44 +0200 Subject: mtd: partitions: rename "master" to the "parent" where appropriate MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This prepares mtd subsystem for the new feature: subpartitions. In some cases flash device partition can be a container with extra subpartitions (volumes). So far there was a flat structure implemented. One master (flash device) could be partitioned into few partitions. Every partition got its master and it was enough to get things running. To support subpartitions we need to store pointer to the parent for each partition. This is required to implement more natural tree structure and handle all recursion and offsets calculation. To make code consistent this patch renamed "master" to the "parent" in places where we can be dealing with subpartitions. Signed-off-by: Rafał Miłecki Signed-off-by: Brian Norris --- drivers/mtd/mtdpart.c | 204 ++++++++++++++++++++++++++------------------------ 1 file changed, 105 insertions(+), 99 deletions(-) diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index 9434050accc7..208822040735 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -37,10 +37,16 @@ static LIST_HEAD(mtd_partitions); static DEFINE_MUTEX(mtd_partitions_mutex); -/* Our partition node structure */ +/** + * struct mtd_part - our partition node structure + * + * @mtd: struct holding partition details + * @parent: parent mtd - flash device or another partition + * @offset: partition offset relative to the *flash device* + */ struct mtd_part { struct mtd_info mtd; - struct mtd_info *master; + struct mtd_info *parent; uint64_t offset; struct list_head list; }; @@ -67,15 +73,15 @@ static int part_read(struct mtd_info *mtd, loff_t from, size_t len, struct mtd_ecc_stats stats; int res; - stats = part->master->ecc_stats; - res = part->master->_read(part->master, from + part->offset, len, + stats = part->parent->ecc_stats; + res = part->parent->_read(part->parent, from + part->offset, len, retlen, buf); if (unlikely(mtd_is_eccerr(res))) mtd->ecc_stats.failed += - part->master->ecc_stats.failed - stats.failed; + part->parent->ecc_stats.failed - stats.failed; else mtd->ecc_stats.corrected += - part->master->ecc_stats.corrected - stats.corrected; + part->parent->ecc_stats.corrected - stats.corrected; return res; } @@ -84,7 +90,7 @@ static int part_point(struct mtd_info *mtd, loff_t from, size_t len, { struct mtd_part *part = mtd_to_part(mtd); - return part->master->_point(part->master, from + part->offset, len, + return part->parent->_point(part->parent, from + part->offset, len, retlen, virt, phys); } @@ -92,7 +98,7 @@ static int part_unpoint(struct mtd_info *mtd, loff_t from, size_t len) { struct mtd_part *part = mtd_to_part(mtd); - return part->master->_unpoint(part->master, from + part->offset, len); + return part->parent->_unpoint(part->parent, from + part->offset, len); } static unsigned long part_get_unmapped_area(struct mtd_info *mtd, @@ -103,7 +109,7 @@ static unsigned long part_get_unmapped_area(struct mtd_info *mtd, struct mtd_part *part = mtd_to_part(mtd); offset += part->offset; - return part->master->_get_unmapped_area(part->master, len, offset, + return part->parent->_get_unmapped_area(part->parent, len, offset, flags); } @@ -132,7 +138,7 @@ static int part_read_oob(struct mtd_info *mtd, loff_t from, return -EINVAL; } - res = part->master->_read_oob(part->master, from + part->offset, ops); + res = part->parent->_read_oob(part->parent, from + part->offset, ops); if (unlikely(res)) { if (mtd_is_bitflip(res)) mtd->ecc_stats.corrected++; @@ -146,7 +152,7 @@ static int part_read_user_prot_reg(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen, u_char *buf) { struct mtd_part *part = mtd_to_part(mtd); - return part->master->_read_user_prot_reg(part->master, from, len, + return part->parent->_read_user_prot_reg(part->parent, from, len, retlen, buf); } @@ -154,7 +160,7 @@ static int part_get_user_prot_info(struct mtd_info *mtd, size_t len, size_t *retlen, struct otp_info *buf) { struct mtd_part *part = mtd_to_part(mtd); - return part->master->_get_user_prot_info(part->master, len, retlen, + return part->parent->_get_user_prot_info(part->parent, len, retlen, buf); } @@ -162,7 +168,7 @@ static int part_read_fact_prot_reg(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen, u_char *buf) { struct mtd_part *part = mtd_to_part(mtd); - return part->master->_read_fact_prot_reg(part->master, from, len, + return part->parent->_read_fact_prot_reg(part->parent, from, len, retlen, buf); } @@ -170,7 +176,7 @@ static int part_get_fact_prot_info(struct mtd_info *mtd, size_t len, size_t *retlen, struct otp_info *buf) { struct mtd_part *part = mtd_to_part(mtd); - return part->master->_get_fact_prot_info(part->master, len, retlen, + return part->parent->_get_fact_prot_info(part->parent, len, retlen, buf); } @@ -178,7 +184,7 @@ static int part_write(struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen, const u_char *buf) { struct mtd_part *part = mtd_to_part(mtd); - return part->master->_write(part->master, to + part->offset, len, + return part->parent->_write(part->parent, to + part->offset, len, retlen, buf); } @@ -186,7 +192,7 @@ static int part_panic_write(struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen, const u_char *buf) { struct mtd_part *part = mtd_to_part(mtd); - return part->master->_panic_write(part->master, to + part->offset, len, + return part->parent->_panic_write(part->parent, to + part->offset, len, retlen, buf); } @@ -199,14 +205,14 @@ static int part_write_oob(struct mtd_info *mtd, loff_t to, return -EINVAL; if (ops->datbuf && to + ops->len > mtd->size) return -EINVAL; - return part->master->_write_oob(part->master, to + part->offset, ops); + return part->parent->_write_oob(part->parent, to + part->offset, ops); } static int part_write_user_prot_reg(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen, u_char *buf) { struct mtd_part *part = mtd_to_part(mtd); - return part->master->_write_user_prot_reg(part->master, from, len, + return part->parent->_write_user_prot_reg(part->parent, from, len, retlen, buf); } @@ -214,14 +220,14 @@ static int part_lock_user_prot_reg(struct mtd_info *mtd, loff_t from, size_t len) { struct mtd_part *part = mtd_to_part(mtd); - return part->master->_lock_user_prot_reg(part->master, from, len); + return part->parent->_lock_user_prot_reg(part->parent, from, len); } static int part_writev(struct mtd_info *mtd, const struct kvec *vecs, unsigned long count, loff_t to, size_t *retlen) { struct mtd_part *part = mtd_to_part(mtd); - return part->master->_writev(part->master, vecs, count, + return part->parent->_writev(part->parent, vecs, count, to + part->offset, retlen); } @@ -231,7 +237,7 @@ static int part_erase(struct mtd_info *mtd, struct erase_info *instr) int ret; instr->addr += part->offset; - ret = part->master->_erase(part->master, instr); + ret = part->parent->_erase(part->parent, instr); if (ret) { if (instr->fail_addr != MTD_FAIL_ADDR_UNKNOWN) instr->fail_addr -= part->offset; @@ -257,51 +263,51 @@ EXPORT_SYMBOL_GPL(mtd_erase_callback); static int part_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len) { struct mtd_part *part = mtd_to_part(mtd); - return part->master->_lock(part->master, ofs + part->offset, len); + return part->parent->_lock(part->parent, ofs + part->offset, len); } static int part_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len) { struct mtd_part *part = mtd_to_part(mtd); - return part->master->_unlock(part->master, ofs + part->offset, len); + return part->parent->_unlock(part->parent, ofs + part->offset, len); } static int part_is_locked(struct mtd_info *mtd, loff_t ofs, uint64_t len) { struct mtd_part *part = mtd_to_part(mtd); - return part->master->_is_locked(part->master, ofs + part->offset, len); + return part->parent->_is_locked(part->parent, ofs + part->offset, len); } static void part_sync(struct mtd_info *mtd) { struct mtd_part *part = mtd_to_part(mtd); - part->master->_sync(part->master); + part->parent->_sync(part->parent); } static int part_suspend(struct mtd_info *mtd) { struct mtd_part *part = mtd_to_part(mtd); - return part->master->_suspend(part->master); + return part->parent->_suspend(part->parent); } static void part_resume(struct mtd_info *mtd) { struct mtd_part *part = mtd_to_part(mtd); - part->master->_resume(part->master); + part->parent->_resume(part->parent); } static int part_block_isreserved(struct mtd_info *mtd, loff_t ofs) { struct mtd_part *part = mtd_to_part(mtd); ofs += part->offset; - return part->master->_block_isreserved(part->master, ofs); + return part->parent->_block_isreserved(part->parent, ofs); } static int part_block_isbad(struct mtd_info *mtd, loff_t ofs) { struct mtd_part *part = mtd_to_part(mtd); ofs += part->offset; - return part->master->_block_isbad(part->master, ofs); + return part->parent->_block_isbad(part->parent, ofs); } static int part_block_markbad(struct mtd_info *mtd, loff_t ofs) @@ -310,7 +316,7 @@ static int part_block_markbad(struct mtd_info *mtd, loff_t ofs) int res; ofs += part->offset; - res = part->master->_block_markbad(part->master, ofs); + res = part->parent->_block_markbad(part->parent, ofs); if (!res) mtd->ecc_stats.badblocks++; return res; @@ -319,13 +325,13 @@ static int part_block_markbad(struct mtd_info *mtd, loff_t ofs) static int part_get_device(struct mtd_info *mtd) { struct mtd_part *part = mtd_to_part(mtd); - return part->master->_get_device(part->master); + return part->parent->_get_device(part->parent); } static void part_put_device(struct mtd_info *mtd) { struct mtd_part *part = mtd_to_part(mtd); - part->master->_put_device(part->master); + part->parent->_put_device(part->parent); } static int part_ooblayout_ecc(struct mtd_info *mtd, int section, @@ -333,7 +339,7 @@ static int part_ooblayout_ecc(struct mtd_info *mtd, int section, { struct mtd_part *part = mtd_to_part(mtd); - return mtd_ooblayout_ecc(part->master, section, oobregion); + return mtd_ooblayout_ecc(part->parent, section, oobregion); } static int part_ooblayout_free(struct mtd_info *mtd, int section, @@ -341,7 +347,7 @@ static int part_ooblayout_free(struct mtd_info *mtd, int section, { struct mtd_part *part = mtd_to_part(mtd); - return mtd_ooblayout_free(part->master, section, oobregion); + return mtd_ooblayout_free(part->parent, section, oobregion); } static const struct mtd_ooblayout_ops part_ooblayout_ops = { @@ -353,7 +359,7 @@ static int part_max_bad_blocks(struct mtd_info *mtd, loff_t ofs, size_t len) { struct mtd_part *part = mtd_to_part(mtd); - return part->master->_max_bad_blocks(part->master, + return part->parent->_max_bad_blocks(part->parent, ofs + part->offset, len); } @@ -363,12 +369,12 @@ static inline void free_partition(struct mtd_part *p) kfree(p); } -static struct mtd_part *allocate_partition(struct mtd_info *master, +static struct mtd_part *allocate_partition(struct mtd_info *parent, const struct mtd_partition *part, int partno, uint64_t cur_offset) { - int wr_alignment = (master->flags & MTD_NO_ERASE) ? master->writesize: - master->erasesize; + int wr_alignment = (parent->flags & MTD_NO_ERASE) ? parent->writesize: + parent->erasesize; struct mtd_part *slave; u32 remainder; char *name; @@ -379,25 +385,25 @@ static struct mtd_part *allocate_partition(struct mtd_info *master, name = kstrdup(part->name, GFP_KERNEL); if (!name || !slave) { printk(KERN_ERR"memory allocation error while creating partitions for \"%s\"\n", - master->name); + parent->name); kfree(name); kfree(slave); return ERR_PTR(-ENOMEM); } /* set up the MTD object for this partition */ - slave->mtd.type = master->type; - slave->mtd.flags = master->flags & ~part->mask_flags; + slave->mtd.type = parent->type; + slave->mtd.flags = parent->flags & ~part->mask_flags; slave->mtd.size = part->size; - slave->mtd.writesize = master->writesize; - slave->mtd.writebufsize = master->writebufsize; - slave->mtd.oobsize = master->oobsize; - slave->mtd.oobavail = master->oobavail; - slave->mtd.subpage_sft = master->subpage_sft; - slave->mtd.pairing = master->pairing; + slave->mtd.writesize = parent->writesize; + slave->mtd.writebufsize = parent->writebufsize; + slave->mtd.oobsize = parent->oobsize; + slave->mtd.oobavail = parent->oobavail; + slave->mtd.subpage_sft = parent->subpage_sft; + slave->mtd.pairing = parent->pairing; slave->mtd.name = name; - slave->mtd.owner = master->owner; + slave->mtd.owner = parent->owner; /* NOTE: Historically, we didn't arrange MTDs as a tree out of * concern for showing the same data in multiple partitions. @@ -408,70 +414,70 @@ static struct mtd_part *allocate_partition(struct mtd_info *master, * distinguish between the master and the partition in sysfs. */ slave->mtd.dev.parent = IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER) ? - &master->dev : - master->dev.parent; + &parent->dev : + parent->dev.parent; slave->mtd.dev.of_node = part->of_node; slave->mtd._read = part_read; slave->mtd._write = part_write; - if (master->_panic_write) + if (parent->_panic_write) slave->mtd._panic_write = part_panic_write; - if (master->_point && master->_unpoint) { + if (parent->_point && parent->_unpoint) { slave->mtd._point = part_point; slave->mtd._unpoint = part_unpoint; } - if (master->_get_unmapped_area) + if (parent->_get_unmapped_area) slave->mtd._get_unmapped_area = part_get_unmapped_area; - if (master->_read_oob) + if (parent->_read_oob) slave->mtd._read_oob = part_read_oob; - if (master->_write_oob) + if (parent->_write_oob) slave->mtd._write_oob = part_write_oob; - if (master->_read_user_prot_reg) + if (parent->_read_user_prot_reg) slave->mtd._read_user_prot_reg = part_read_user_prot_reg; - if (master->_read_fact_prot_reg) + if (parent->_read_fact_prot_reg) slave->mtd._read_fact_prot_reg = part_read_fact_prot_reg; - if (master->_write_user_prot_reg) + if (parent->_write_user_prot_reg) slave->mtd._write_user_prot_reg = part_write_user_prot_reg; - if (master->_lock_user_prot_reg) + if (parent->_lock_user_prot_reg) slave->mtd._lock_user_prot_reg = part_lock_user_prot_reg; - if (master->_get_user_prot_info) + if (parent->_get_user_prot_info) slave->mtd._get_user_prot_info = part_get_user_prot_info; - if (master->_get_fact_prot_info) + if (parent->_get_fact_prot_info) slave->mtd._get_fact_prot_info = part_get_fact_prot_info; - if (master->_sync) + if (parent->_sync) slave->mtd._sync = part_sync; - if (!partno && !master->dev.class && master->_suspend && - master->_resume) { + if (!partno && !parent->dev.class && parent->_suspend && + parent->_resume) { slave->mtd._suspend = part_suspend; slave->mtd._resume = part_resume; } - if (master->_writev) + if (parent->_writev) slave->mtd._writev = part_writev; - if (master->_lock) + if (parent->_lock) slave->mtd._lock = part_lock; - if (master->_unlock) + if (parent->_unlock) slave->mtd._unlock = part_unlock; - if (master->_is_locked) + if (parent->_is_locked) slave->mtd._is_locked = part_is_locked; - if (master->_block_isreserved) + if (parent->_block_isreserved) slave->mtd._block_isreserved = part_block_isreserved; - if (master->_block_isbad) + if (parent->_block_isbad) slave->mtd._block_isbad = part_block_isbad; - if (master->_block_markbad) + if (parent->_block_markbad) slave->mtd._block_markbad = part_block_markbad; - if (master->_max_bad_blocks) + if (parent->_max_bad_blocks) slave->mtd._max_bad_blocks = part_max_bad_blocks; - if (master->_get_device) + if (parent->_get_device) slave->mtd._get_device = part_get_device; - if (master->_put_device) + if (parent->_put_device) slave->mtd._put_device = part_put_device; slave->mtd._erase = part_erase; - slave->master = master; + slave->parent = parent; slave->offset = part->offset; if (slave->offset == MTDPART_OFS_APPEND) @@ -489,25 +495,25 @@ static struct mtd_part *allocate_partition(struct mtd_info *master, } if (slave->offset == MTDPART_OFS_RETAIN) { slave->offset = cur_offset; - if (master->size - slave->offset >= slave->mtd.size) { - slave->mtd.size = master->size - slave->offset + if (parent->size - slave->offset >= slave->mtd.size) { + slave->mtd.size = parent->size - slave->offset - slave->mtd.size; } else { printk(KERN_ERR "mtd partition \"%s\" doesn't have enough space: %#llx < %#llx, disabled\n", - part->name, master->size - slave->offset, + part->name, parent->size - slave->offset, slave->mtd.size); /* register to preserve ordering */ goto out_register; } } if (slave->mtd.size == MTDPART_SIZ_FULL) - slave->mtd.size = master->size - slave->offset; + slave->mtd.size = parent->size - slave->offset; printk(KERN_NOTICE "0x%012llx-0x%012llx : \"%s\"\n", (unsigned long long)slave->offset, (unsigned long long)(slave->offset + slave->mtd.size), slave->mtd.name); /* let's do some sanity checks */ - if (slave->offset >= master->size) { + if (slave->offset >= parent->size) { /* let's register it anyway to preserve ordering */ slave->offset = 0; slave->mtd.size = 0; @@ -515,16 +521,16 @@ static struct mtd_part *allocate_partition(struct mtd_info *master, part->name); goto out_register; } - if (slave->offset + slave->mtd.size > master->size) { - slave->mtd.size = master->size - slave->offset; + if (slave->offset + slave->mtd.size > parent->size) { + slave->mtd.size = parent->size - slave->offset; printk(KERN_WARNING"mtd: partition \"%s\" extends beyond the end of device \"%s\" -- size truncated to %#llx\n", - part->name, master->name, (unsigned long long)slave->mtd.size); + part->name, parent->name, (unsigned long long)slave->mtd.size); } - if (master->numeraseregions > 1) { + if (parent->numeraseregions > 1) { /* Deal with variable erase size stuff */ - int i, max = master->numeraseregions; + int i, max = parent->numeraseregions; u64 end = slave->offset + slave->mtd.size; - struct mtd_erase_region_info *regions = master->eraseregions; + struct mtd_erase_region_info *regions = parent->eraseregions; /* Find the first erase regions which is part of this * partition. */ @@ -543,7 +549,7 @@ static struct mtd_part *allocate_partition(struct mtd_info *master, BUG_ON(slave->mtd.erasesize == 0); } else { /* Single erase size */ - slave->mtd.erasesize = master->erasesize; + slave->mtd.erasesize = parent->erasesize; } tmp = slave->offset; @@ -566,17 +572,17 @@ static struct mtd_part *allocate_partition(struct mtd_info *master, } mtd_set_ooblayout(&slave->mtd, &part_ooblayout_ops); - slave->mtd.ecc_step_size = master->ecc_step_size; - slave->mtd.ecc_strength = master->ecc_strength; - slave->mtd.bitflip_threshold = master->bitflip_threshold; + slave->mtd.ecc_step_size = parent->ecc_step_size; + slave->mtd.ecc_strength = parent->ecc_strength; + slave->mtd.bitflip_threshold = parent->bitflip_threshold; - if (master->_block_isbad) { + if (parent->_block_isbad) { uint64_t offs = 0; while (offs < slave->mtd.size) { - if (mtd_block_isreserved(master, offs + slave->offset)) + if (mtd_block_isreserved(parent, offs + slave->offset)) slave->mtd.ecc_stats.bbtblocks++; - else if (mtd_block_isbad(master, offs + slave->offset)) + else if (mtd_block_isbad(parent, offs + slave->offset)) slave->mtd.ecc_stats.badblocks++; offs += slave->mtd.erasesize; } @@ -610,7 +616,7 @@ static int mtd_add_partition_attrs(struct mtd_part *new) return ret; } -int mtd_add_partition(struct mtd_info *master, const char *name, +int mtd_add_partition(struct mtd_info *parent, const char *name, long long offset, long long length) { struct mtd_partition part; @@ -623,7 +629,7 @@ int mtd_add_partition(struct mtd_info *master, const char *name, return -EINVAL; if (length == MTDPART_SIZ_FULL) - length = master->size - offset; + length = parent->size - offset; if (length <= 0) return -EINVAL; @@ -633,7 +639,7 @@ int mtd_add_partition(struct mtd_info *master, const char *name, part.size = length; part.offset = offset; - new = allocate_partition(master, &part, -1, offset); + new = allocate_partition(parent, &part, -1, offset); if (IS_ERR(new)) return PTR_ERR(new); @@ -683,7 +689,7 @@ int del_mtd_partitions(struct mtd_info *master) mutex_lock(&mtd_partitions_mutex); list_for_each_entry_safe(slave, next, &mtd_partitions, list) - if (slave->master == master) { + if (slave->parent == master) { ret = __mtd_del_partition(slave); if (ret < 0) err = ret; @@ -700,7 +706,7 @@ int mtd_del_partition(struct mtd_info *master, int partno) mutex_lock(&mtd_partitions_mutex); list_for_each_entry_safe(slave, next, &mtd_partitions, list) - if ((slave->master == master) && + if ((slave->parent == master) && (slave->mtd.index == partno)) { ret = __mtd_del_partition(slave); break; @@ -933,6 +939,6 @@ uint64_t mtd_get_device_size(const struct mtd_info *mtd) if (!mtd_is_partition(mtd)) return mtd->size; - return mtd_to_part(mtd)->master->size; + return mtd_to_part(mtd)->parent->size; } EXPORT_SYMBOL_GPL(mtd_get_device_size); -- cgit v1.2.3-59-g8ed1b From 97519dc52b44af054d7654776e78eaa211cf1842 Mon Sep 17 00:00:00 2001 From: Rafał Miłecki Date: Wed, 21 Jun 2017 08:26:45 +0200 Subject: mtd: partitions: add support for subpartitions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some flash device partitions can be containers with extra subpartitions (volumes). All callbacks are already capable of this additional level of indirection. This patch makes sure we always display subpartitions using a tree structure and takes care of deleting subpartitions when parent gets removed. Signed-off-by: Rafał Miłecki Signed-off-by: Brian Norris --- drivers/mtd/mtdpart.c | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-) diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index 208822040735..c0d464d192ee 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -413,7 +413,7 @@ static struct mtd_part *allocate_partition(struct mtd_info *parent, * parent conditional on that option. Note, this is a way to * distinguish between the master and the partition in sysfs. */ - slave->mtd.dev.parent = IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER) ? + slave->mtd.dev.parent = IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER) || mtd_is_partition(parent) ? &parent->dev : parent->dev.parent; slave->mtd.dev.of_node = part->of_node; @@ -664,8 +664,17 @@ EXPORT_SYMBOL_GPL(mtd_add_partition); */ static int __mtd_del_partition(struct mtd_part *priv) { + struct mtd_part *child, *next; int err; + list_for_each_entry_safe(child, next, &mtd_partitions, list) { + if (child->parent == &priv->mtd) { + err = __mtd_del_partition(child); + if (err) + return err; + } + } + sysfs_remove_files(&priv->mtd.dev.kobj, mtd_partition_attrs); err = del_mtd_device(&priv->mtd); @@ -680,16 +689,16 @@ static int __mtd_del_partition(struct mtd_part *priv) /* * This function unregisters and destroy all slave MTD objects which are - * attached to the given master MTD object. + * attached to the given MTD object. */ -int del_mtd_partitions(struct mtd_info *master) +int del_mtd_partitions(struct mtd_info *mtd) { struct mtd_part *slave, *next; int ret, err = 0; mutex_lock(&mtd_partitions_mutex); list_for_each_entry_safe(slave, next, &mtd_partitions, list) - if (slave->parent == master) { + if (slave->parent == mtd) { ret = __mtd_del_partition(slave); if (ret < 0) err = ret; @@ -699,14 +708,14 @@ int del_mtd_partitions(struct mtd_info *master) return err; } -int mtd_del_partition(struct mtd_info *master, int partno) +int mtd_del_partition(struct mtd_info *mtd, int partno) { struct mtd_part *slave, *next; int ret = -EINVAL; mutex_lock(&mtd_partitions_mutex); list_for_each_entry_safe(slave, next, &mtd_partitions, list) - if ((slave->parent == master) && + if ((slave->parent == mtd) && (slave->mtd.index == partno)) { ret = __mtd_del_partition(slave); break; @@ -939,6 +948,6 @@ uint64_t mtd_get_device_size(const struct mtd_info *mtd) if (!mtd_is_partition(mtd)) return mtd->size; - return mtd_to_part(mtd)->parent->size; + return mtd_get_device_size(mtd_to_part(mtd)->parent); } EXPORT_SYMBOL_GPL(mtd_get_device_size); -- cgit v1.2.3-59-g8ed1b From 1a0915be192606fee64830b9c5d70b7ed59426b6 Mon Sep 17 00:00:00 2001 From: Rafał Miłecki Date: Wed, 21 Jun 2017 08:26:46 +0200 Subject: mtd: partitions: add support for partition parsers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some devices have partitions that are kind of containers with extra subpartitions / volumes instead of e.g. a simple filesystem data. To support such cases we need to first create normal flash device partitions and then take care of these special ones. It's very common case for home routers. Depending on the vendor there are formats like TRX, Seama, TP-Link, WRGG & more. All of them are used to embed few partitions into a single one / single firmware file. Ideally all vendors would use some well documented / standardized format like UBI (and some probably start doing so), but there are still countless devices on the market using these poor vendor specific formats. This patch extends MTD subsystem by allowing to specify list of parsers that should be tried for a given partition. Supporting such poor formats is highly unlikely to be the top priority so these changes try to minimize maintenance cost to the minimum. It reuses existing code for these new parsers and just adds a one property and one new function. This implementation requires setting partition parsers in a flash parser. A proper change of bcm47xxpart will follow and in the future we will hopefully also find a solution for doing it with ofpart ("fixed-partitions"). Signed-off-by: Rafał Miłecki Signed-off-by: Brian Norris --- drivers/mtd/mtdpart.c | 31 +++++++++++++++++++++++++++++++ include/linux/mtd/partitions.h | 7 +++++++ 2 files changed, 38 insertions(+) diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index c0d464d192ee..2ad9493703f9 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -369,6 +369,35 @@ static inline void free_partition(struct mtd_part *p) kfree(p); } +/** + * mtd_parse_part - parse MTD partition looking for subpartitions + * + * @slave: part that is supposed to be a container and should be parsed + * @types: NULL-terminated array with names of partition parsers to try + * + * Some partitions are kind of containers with extra subpartitions (volumes). + * There can be various formats of such containers. This function tries to use + * specified parsers to analyze given partition and registers found + * subpartitions on success. + */ +static int mtd_parse_part(struct mtd_part *slave, const char *const *types) +{ + struct mtd_partitions parsed; + int err; + + err = parse_mtd_partitions(&slave->mtd, types, &parsed, NULL); + if (err) + return err; + else if (!parsed.nr_parts) + return -ENOENT; + + err = add_mtd_partitions(&slave->mtd, parsed.parts, parsed.nr_parts); + + mtd_part_parser_cleanup(&parsed); + + return err; +} + static struct mtd_part *allocate_partition(struct mtd_info *parent, const struct mtd_partition *part, int partno, uint64_t cur_offset) @@ -758,6 +787,8 @@ int add_mtd_partitions(struct mtd_info *master, add_mtd_device(&slave->mtd); mtd_add_partition_attrs(slave); + if (parts[i].types) + mtd_parse_part(slave, parts[i].types); cur_offset = slave->offset + slave->mtd.size; } diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index 06df1e06b6e0..c4beb70dacbd 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -20,6 +20,12 @@ * * For each partition, these fields are available: * name: string that will be used to label the partition's MTD device. + * types: some partitions can be containers using specific format to describe + * embedded subpartitions / volumes. E.g. many home routers use "firmware" + * partition that contains at least kernel and rootfs. In such case an + * extra parser is needed that will detect these dynamic partitions and + * report them to the MTD subsystem. If set this property stores an array + * of parser names to use when looking for subpartitions. * size: the partition size; if defined as MTDPART_SIZ_FULL, the partition * will extend to the end of the master MTD device. * offset: absolute starting position within the master MTD device; if @@ -38,6 +44,7 @@ struct mtd_partition { const char *name; /* identifier string */ + const char *const *types; /* names of parsers to use if any */ uint64_t size; /* partition size */ uint64_t offset; /* offset within the master MTD space */ uint32_t mask_flags; /* master MTD flags to mask out for this partition */ -- cgit v1.2.3-59-g8ed1b From 99352afe8f169c95b294b6b9a8d0e18cd9e3c2a0 Mon Sep 17 00:00:00 2001 From: Rafał Miłecki Date: Wed, 21 Jun 2017 08:26:47 +0200 Subject: mtd: extract TRX parser out of bcm47xxpart into a separated module MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This makes TRX parsing code reusable with other platforms and parsers. Please note this patch doesn't really change anything in the existing code, just moves it. There is still some place for improvement (e.g. working on non-hacky method of checking rootfs format) but it's not really a subject of this change. Signed-off-by: Rafał Miłecki Signed-off-by: Brian Norris --- drivers/mtd/Kconfig | 4 ++ drivers/mtd/Makefile | 1 + drivers/mtd/bcm47xxpart.c | 99 ++---------------------------- drivers/mtd/parsers/Kconfig | 8 +++ drivers/mtd/parsers/Makefile | 1 + drivers/mtd/parsers/parser_trx.c | 126 +++++++++++++++++++++++++++++++++++++++ 6 files changed, 145 insertions(+), 94 deletions(-) create mode 100644 drivers/mtd/parsers/Kconfig create mode 100644 drivers/mtd/parsers/Makefile create mode 100644 drivers/mtd/parsers/parser_trx.c diff --git a/drivers/mtd/Kconfig b/drivers/mtd/Kconfig index e83a279f1217..5a2d71729b9a 100644 --- a/drivers/mtd/Kconfig +++ b/drivers/mtd/Kconfig @@ -155,6 +155,10 @@ config MTD_BCM47XX_PARTS This provides partitions parser for devices based on BCM47xx boards. +menu "Partition parsers" +source "drivers/mtd/parsers/Kconfig" +endmenu + comment "User Modules And Translation Layers" # diff --git a/drivers/mtd/Makefile b/drivers/mtd/Makefile index 99bb9a1f6e16..151d60df303a 100644 --- a/drivers/mtd/Makefile +++ b/drivers/mtd/Makefile @@ -13,6 +13,7 @@ obj-$(CONFIG_MTD_AFS_PARTS) += afs.o obj-$(CONFIG_MTD_AR7_PARTS) += ar7part.o obj-$(CONFIG_MTD_BCM63XX_PARTS) += bcm63xxpart.o obj-$(CONFIG_MTD_BCM47XX_PARTS) += bcm47xxpart.o +obj-y += parsers/ # 'Users' - code which presents functionality to userspace. obj-$(CONFIG_MTD_BLKDEVS) += mtd_blkdevs.o diff --git a/drivers/mtd/bcm47xxpart.c b/drivers/mtd/bcm47xxpart.c index d10fa6c8f074..fe2581d9d882 100644 --- a/drivers/mtd/bcm47xxpart.c +++ b/drivers/mtd/bcm47xxpart.c @@ -43,7 +43,8 @@ #define ML_MAGIC2 0x26594131 #define TRX_MAGIC 0x30524448 #define SHSQ_MAGIC 0x71736873 /* shsq (weird ZTE H218N endianness) */ -#define UBI_EC_MAGIC 0x23494255 /* UBI# */ + +static const char * const trx_types[] = { "trx", NULL }; struct trx_header { uint32_t magic; @@ -62,89 +63,6 @@ static void bcm47xxpart_add_part(struct mtd_partition *part, const char *name, part->mask_flags = mask_flags; } -static const char *bcm47xxpart_trx_data_part_name(struct mtd_info *master, - size_t offset) -{ - uint32_t buf; - size_t bytes_read; - int err; - - err = mtd_read(master, offset, sizeof(buf), &bytes_read, - (uint8_t *)&buf); - if (err && !mtd_is_bitflip(err)) { - pr_err("mtd_read error while parsing (offset: 0x%X): %d\n", - offset, err); - goto out_default; - } - - if (buf == UBI_EC_MAGIC) - return "ubi"; - -out_default: - return "rootfs"; -} - -static int bcm47xxpart_parse_trx(struct mtd_info *master, - struct mtd_partition *trx, - struct mtd_partition *parts, - size_t parts_len) -{ - struct trx_header header; - size_t bytes_read; - int curr_part = 0; - int i, err; - - if (parts_len < 3) { - pr_warn("No enough space to add TRX partitions!\n"); - return -ENOMEM; - } - - err = mtd_read(master, trx->offset, sizeof(header), &bytes_read, - (uint8_t *)&header); - if (err && !mtd_is_bitflip(err)) { - pr_err("mtd_read error while reading TRX header: %d\n", err); - return err; - } - - i = 0; - - /* We have LZMA loader if offset[2] points to sth */ - if (header.offset[2]) { - bcm47xxpart_add_part(&parts[curr_part++], "loader", - trx->offset + header.offset[i], 0); - i++; - } - - if (header.offset[i]) { - bcm47xxpart_add_part(&parts[curr_part++], "linux", - trx->offset + header.offset[i], 0); - i++; - } - - if (header.offset[i]) { - size_t offset = trx->offset + header.offset[i]; - const char *name = bcm47xxpart_trx_data_part_name(master, - offset); - - bcm47xxpart_add_part(&parts[curr_part++], name, offset, 0); - i++; - } - - /* - * Assume that every partition ends at the beginning of the one it is - * followed by. - */ - for (i = 0; i < curr_part; i++) { - u64 next_part_offset = (i < curr_part - 1) ? - parts[i + 1].offset : - trx->offset + trx->size; - - parts[i].size = next_part_offset - parts[i].offset; - } - - return curr_part; -} - /** * bcm47xxpart_bootpartition - gets index of TRX partition used by bootloader * @@ -362,17 +280,10 @@ static int bcm47xxpart_parse(struct mtd_info *master, for (i = 0; i < trx_num; i++) { struct mtd_partition *trx = &parts[trx_parts[i]]; - if (i == bcm47xxpart_bootpartition()) { - int num_parts; - - num_parts = bcm47xxpart_parse_trx(master, trx, - parts + curr_part, - BCM47XXPART_MAX_PARTS - curr_part); - if (num_parts > 0) - curr_part += num_parts; - } else { + if (i == bcm47xxpart_bootpartition()) + trx->types = trx_types; + else trx->name = "failsafe"; - } } *pparts = parts; diff --git a/drivers/mtd/parsers/Kconfig b/drivers/mtd/parsers/Kconfig new file mode 100644 index 000000000000..d206b3c533bc --- /dev/null +++ b/drivers/mtd/parsers/Kconfig @@ -0,0 +1,8 @@ +config MTD_PARSER_TRX + tristate "Parser for TRX format partitions" + depends on MTD && (BCM47XX || ARCH_BCM_5301X || COMPILE_TEST) + help + TRX is a firmware format used by Broadcom on their devices. It + may contain up to 3/4 partitions (depending on the version). + This driver will parse TRX header and report at least two partitions: + kernel and rootfs. diff --git a/drivers/mtd/parsers/Makefile b/drivers/mtd/parsers/Makefile new file mode 100644 index 000000000000..4d9024e0be3b --- /dev/null +++ b/drivers/mtd/parsers/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_MTD_PARSER_TRX) += parser_trx.o diff --git a/drivers/mtd/parsers/parser_trx.c b/drivers/mtd/parsers/parser_trx.c new file mode 100644 index 000000000000..e805108afd31 --- /dev/null +++ b/drivers/mtd/parsers/parser_trx.c @@ -0,0 +1,126 @@ +/* + * Parser for TRX format partitions + * + * Copyright (C) 2012 - 2017 Rafał Miłecki + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include +#include +#include +#include + +#define TRX_PARSER_MAX_PARTS 4 + +/* Magics */ +#define TRX_MAGIC 0x30524448 +#define UBI_EC_MAGIC 0x23494255 /* UBI# */ + +struct trx_header { + uint32_t magic; + uint32_t length; + uint32_t crc32; + uint16_t flags; + uint16_t version; + uint32_t offset[3]; +} __packed; + +static const char *parser_trx_data_part_name(struct mtd_info *master, + size_t offset) +{ + uint32_t buf; + size_t bytes_read; + int err; + + err = mtd_read(master, offset, sizeof(buf), &bytes_read, + (uint8_t *)&buf); + if (err && !mtd_is_bitflip(err)) { + pr_err("mtd_read error while parsing (offset: 0x%X): %d\n", + offset, err); + goto out_default; + } + + if (buf == UBI_EC_MAGIC) + return "ubi"; + +out_default: + return "rootfs"; +} + +static int parser_trx_parse(struct mtd_info *mtd, + const struct mtd_partition **pparts, + struct mtd_part_parser_data *data) +{ + struct mtd_partition *parts; + struct mtd_partition *part; + struct trx_header trx; + size_t bytes_read; + uint8_t curr_part = 0, i = 0; + int err; + + parts = kzalloc(sizeof(struct mtd_partition) * TRX_PARSER_MAX_PARTS, + GFP_KERNEL); + if (!parts) + return -ENOMEM; + + err = mtd_read(mtd, 0, sizeof(trx), &bytes_read, (uint8_t *)&trx); + if (err) { + pr_err("MTD reading error: %d\n", err); + kfree(parts); + return err; + } + + if (trx.magic != TRX_MAGIC) { + kfree(parts); + return -ENOENT; + } + + /* We have LZMA loader if there is address in offset[2] */ + if (trx.offset[2]) { + part = &parts[curr_part++]; + part->name = "loader"; + part->offset = trx.offset[i]; + i++; + } + + if (trx.offset[i]) { + part = &parts[curr_part++]; + part->name = "linux"; + part->offset = trx.offset[i]; + i++; + } + + if (trx.offset[i]) { + part = &parts[curr_part++]; + part->name = parser_trx_data_part_name(mtd, trx.offset[i]); + part->offset = trx.offset[i]; + i++; + } + + /* + * Assume that every partition ends at the beginning of the one it is + * followed by. + */ + for (i = 0; i < curr_part; i++) { + u64 next_part_offset = (i < curr_part - 1) ? + parts[i + 1].offset : mtd->size; + + parts[i].size = next_part_offset - parts[i].offset; + } + + *pparts = parts; + return i; +}; + +static struct mtd_part_parser mtd_parser_trx = { + .parse_fn = parser_trx_parse, + .name = "trx", +}; +module_mtd_part_parser(mtd_parser_trx); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Parser for TRX format partitions"); -- cgit v1.2.3-59-g8ed1b From 6eab81e6358730fd566e2c069d7be2309713ac3a Mon Sep 17 00:00:00 2001 From: Cyrille Pitchen Date: Tue, 13 Jun 2017 21:46:24 +0200 Subject: MAINTAINERS: Update SPI NOR subsystem git repositories SPI NOR branches are now hosted on MTD repos, spi-nor/next is on l2-mtd and spi-nor/fixes is on linux-mtd. Signed-off-by: Cyrille Pitchen Acked-by: Marek Vasut Signed-off-by: Brian Norris --- MAINTAINERS | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 9e984645c4b0..16d536082a59 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12122,7 +12122,8 @@ M: Marek Vasut L: linux-mtd@lists.infradead.org W: http://www.linux-mtd.infradead.org/ Q: http://patchwork.ozlabs.org/project/linux-mtd/list/ -T: git git://github.com/spi-nor/linux.git +T: git git://git.infradead.org/linux-mtd.git spi-nor/fixes +T: git git://git.infradead.org/l2-mtd.git spi-nor/next S: Maintained F: drivers/mtd/spi-nor/ F: include/linux/mtd/spi-nor.h -- cgit v1.2.3-59-g8ed1b From 54930dfeb46e978b447af0fb8ab4e181c1bf9d7a Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Thu, 22 Jun 2017 16:35:04 -0400 Subject: reiserfs: don't preallocate blocks for extended attributes Most extended attributes will fit in a single block. More importantly, we drop the reference to the inode while holding the transaction open so the preallocated blocks aren't released. As a result, the inode may be evicted before it's removed from the transaction's prealloc list which can cause memory corruption. Signed-off-by: Jeff Mahoney Signed-off-by: Jan Kara --- fs/reiserfs/bitmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/reiserfs/bitmap.c b/fs/reiserfs/bitmap.c index dc198bc64c61..a6f39fe2b664 100644 --- a/fs/reiserfs/bitmap.c +++ b/fs/reiserfs/bitmap.c @@ -1128,7 +1128,7 @@ static int determine_prealloc_size(reiserfs_blocknr_hint_t * hint) hint->prealloc_size = 0; if (!hint->formatted_node && hint->preallocate) { - if (S_ISREG(hint->inode->i_mode) + if (S_ISREG(hint->inode->i_mode) && !IS_PRIVATE(hint->inode) && hint->inode->i_size >= REISERFS_SB(hint->th->t_super)->s_alloc_options. preallocmin * hint->inode->i_sb->s_blocksize) -- cgit v1.2.3-59-g8ed1b From 08db141b5313ac2f64b844fb5725b8d81744b417 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Thu, 22 Jun 2017 16:47:34 -0400 Subject: reiserfs: fix race in prealloc discard The main loop in __discard_prealloc is protected by the reiserfs write lock which is dropped across schedules like the BKL it replaced. The problem is that it checks the value, calls a routine that schedules, and then adjusts the state. As a result, two threads that are calling reiserfs_prealloc_discard at the same time can race when one calls reiserfs_free_prealloc_block, the lock is dropped, and the other calls reiserfs_free_prealloc_block with the same block number. In the right circumstances, it can cause the prealloc count to go negative. Signed-off-by: Jeff Mahoney Signed-off-by: Jan Kara --- fs/reiserfs/bitmap.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/fs/reiserfs/bitmap.c b/fs/reiserfs/bitmap.c index a6f39fe2b664..edc8ef78b63f 100644 --- a/fs/reiserfs/bitmap.c +++ b/fs/reiserfs/bitmap.c @@ -513,9 +513,17 @@ static void __discard_prealloc(struct reiserfs_transaction_handle *th, "inode has negative prealloc blocks count."); #endif while (ei->i_prealloc_count > 0) { - reiserfs_free_prealloc_block(th, inode, ei->i_prealloc_block); - ei->i_prealloc_block++; + b_blocknr_t block_to_free; + + /* + * reiserfs_free_prealloc_block can drop the write lock, + * which could allow another caller to free the same block. + * We can protect against it by modifying the prealloc + * state before calling it. + */ + block_to_free = ei->i_prealloc_block++; ei->i_prealloc_count--; + reiserfs_free_prealloc_block(th, inode, block_to_free); dirty = 1; } if (dirty) -- cgit v1.2.3-59-g8ed1b From 58de51ca77e2166262b043b0ff93290b184a2364 Mon Sep 17 00:00:00 2001 From: Rafał Miłecki Date: Fri, 23 Jun 2017 07:07:14 +0200 Subject: mtd: parsers: trx: fix pr_err format for printing offset MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This fixes following warning: include/linux/kern_levels.h:4:18: warning: format '%X' expects argument of type 'unsigned int', but argument 2 has type 'size_t {aka long unsigned int}' [-Wformat=] Signed-off-by: Rafał Miłecki Signed-off-by: Brian Norris --- drivers/mtd/parsers/parser_trx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/parsers/parser_trx.c b/drivers/mtd/parsers/parser_trx.c index e805108afd31..df360a75e1eb 100644 --- a/drivers/mtd/parsers/parser_trx.c +++ b/drivers/mtd/parsers/parser_trx.c @@ -39,7 +39,7 @@ static const char *parser_trx_data_part_name(struct mtd_info *master, err = mtd_read(master, offset, sizeof(buf), &bytes_read, (uint8_t *)&buf); if (err && !mtd_is_bitflip(err)) { - pr_err("mtd_read error while parsing (offset: 0x%X): %d\n", + pr_err("mtd_read error while parsing (offset: 0x%zX): %d\n", offset, err); goto out_default; } -- cgit v1.2.3-59-g8ed1b From c169e3d3c049d93929a92f909a4b80ba0f85a3c3 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Thu, 22 Jun 2017 14:09:18 -0700 Subject: mtd: partitions: fixup some allocate_partition() whitespace Some recent patches caused churn around this area, and checkpatch noticed the existing issues. Signed-off-by: Brian Norris --- drivers/mtd/mtdpart.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index 2ad9493703f9..5736b0c90b33 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -402,7 +402,7 @@ static struct mtd_part *allocate_partition(struct mtd_info *parent, const struct mtd_partition *part, int partno, uint64_t cur_offset) { - int wr_alignment = (parent->flags & MTD_NO_ERASE) ? parent->writesize: + int wr_alignment = (parent->flags & MTD_NO_ERASE) ? parent->writesize : parent->erasesize; struct mtd_part *slave; u32 remainder; @@ -480,8 +480,8 @@ static struct mtd_part *allocate_partition(struct mtd_info *parent, slave->mtd._sync = part_sync; if (!partno && !parent->dev.class && parent->_suspend && parent->_resume) { - slave->mtd._suspend = part_suspend; - slave->mtd._resume = part_resume; + slave->mtd._suspend = part_suspend; + slave->mtd._resume = part_resume; } if (parent->_writev) slave->mtd._writev = part_writev; -- cgit v1.2.3-59-g8ed1b From 0ec7769a98b00866e37740328d65cba6594d178d Mon Sep 17 00:00:00 2001 From: Vaibhav Jain Date: Wed, 31 May 2017 18:39:01 +0530 Subject: rtc: opal: Implement rtc_class_ops.alarm_irq_enable callback Provide an implementation of the callback rtc_class_ops.alarm_irq_enable for rtc-opal driver. This callback is called when the wake alarm is disabled via the command: 'echo 0 > /sys/class/rtc/rtc0/wakealarm' Without this the Timed-Power-On(TPO) config remains set even when its disabled by the above command and FSP will still force machine boot at previously configured alarm time. The callback is implemented as function opal_tpo_alarm_irq_enable() which calls opal_set_tpo_time() with alarm.enabled == 0. A branch is added to opal_set_tpo_time() to handle this case by passing y_m_d == h_m_s_ms == 0 to opal as arguments for opal_tpo_write() call. Signed-off-by: Vaibhav Jain Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-opal.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-opal.c b/drivers/rtc/rtc-opal.c index 2d84e2a28772..e2a946c0e667 100644 --- a/drivers/rtc/rtc-opal.c +++ b/drivers/rtc/rtc-opal.c @@ -167,7 +167,14 @@ static int opal_set_tpo_time(struct device *dev, struct rtc_wkalrm *alarm) u32 y_m_d = 0; int token, rc; - tm_to_opal(&alarm->time, &y_m_d, &h_m_s_ms); + /* if alarm is enabled */ + if (alarm->enabled) { + tm_to_opal(&alarm->time, &y_m_d, &h_m_s_ms); + pr_debug("Alarm set to %x %llx\n", y_m_d, h_m_s_ms); + + } else { + pr_debug("Alarm getting disabled\n"); + } token = opal_async_get_token_interruptible(); if (token < 0) { @@ -200,6 +207,18 @@ exit: return rc; } +int opal_tpo_alarm_irq_enable(struct device *dev, unsigned int enabled) +{ + struct rtc_wkalrm alarm = { .enabled = 0 }; + + /* + * TPO is automatically enabled when opal_set_tpo_time() is called with + * non-zero rtc-time. We only handle disable case which needs to be + * explicitly told to opal. + */ + return enabled ? 0 : opal_set_tpo_time(dev, &alarm); +} + static struct rtc_class_ops opal_rtc_ops = { .read_time = opal_get_rtc_time, .set_time = opal_set_rtc_time, @@ -215,6 +234,7 @@ static int opal_rtc_probe(struct platform_device *pdev) device_set_wakeup_capable(&pdev->dev, true); opal_rtc_ops.read_alarm = opal_get_tpo_time; opal_rtc_ops.set_alarm = opal_set_tpo_time; + opal_rtc_ops.alarm_irq_enable = opal_tpo_alarm_irq_enable; } rtc = devm_rtc_device_register(&pdev->dev, DRVNAME, &opal_rtc_ops, -- cgit v1.2.3-59-g8ed1b From fe6d94fe66b50c10c94911e525ad680a8f2dfc21 Mon Sep 17 00:00:00 2001 From: "Diaz de Grenu, Jose" Date: Thu, 11 May 2017 17:38:39 +0200 Subject: rtc: mxc: remove unused variable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This variable was never used. With GCC 6.2, we get the following warning: drivers/rtc/rtc-mxc.c:44:18: warning: ‘PIE_BIT_DEF’ defined but not used [-Wunused-const-variable=] static const u32 PIE_BIT_DEF[MAX_PIE_NUM][2] = { Signed-off-by: Diaz de Grenu, Jose Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-mxc.c | 11 ----------- 1 file changed, 11 deletions(-) diff --git a/drivers/rtc/rtc-mxc.c b/drivers/rtc/rtc-mxc.c index 77319122642a..401f46d8f21b 100644 --- a/drivers/rtc/rtc-mxc.c +++ b/drivers/rtc/rtc-mxc.c @@ -43,17 +43,6 @@ #define MAX_PIE_NUM 9 #define MAX_PIE_FREQ 512 -static const u32 PIE_BIT_DEF[MAX_PIE_NUM][2] = { - { 2, RTC_2HZ_BIT }, - { 4, RTC_SAM0_BIT }, - { 8, RTC_SAM1_BIT }, - { 16, RTC_SAM2_BIT }, - { 32, RTC_SAM3_BIT }, - { 64, RTC_SAM4_BIT }, - { 128, RTC_SAM5_BIT }, - { 256, RTC_SAM6_BIT }, - { MAX_PIE_FREQ, RTC_SAM7_BIT }, -}; #define MXC_RTC_TIME 0 #define MXC_RTC_ALARM 1 -- cgit v1.2.3-59-g8ed1b From 8768e7b3e3677fb51bf3ed5ceef174f40be4c287 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 16 Jun 2017 21:28:02 +0200 Subject: rtc: s3c: Jump to central exit point on getting src clock error In other error paths in probe, centralized exit point was used so make this consistent. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-s3c.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c index d44fb34df8fe..c5aa7a35d07f 100644 --- a/drivers/rtc/rtc-s3c.c +++ b/drivers/rtc/rtc-s3c.c @@ -510,8 +510,7 @@ static int s3c_rtc_probe(struct platform_device *pdev) else dev_dbg(&pdev->dev, "probe deferred due to missing rtc src clk\n"); - clk_disable_unprepare(info->rtc_clk); - return ret; + goto err_src_clk; } clk_prepare_enable(info->rtc_src_clk); } @@ -575,6 +574,7 @@ static int s3c_rtc_probe(struct platform_device *pdev) if (info->data->needs_src_clk) clk_disable_unprepare(info->rtc_src_clk); +err_src_clk: clk_disable_unprepare(info->rtc_clk); return ret; -- cgit v1.2.3-59-g8ed1b From fc1afe60535eeb433648ebf80e23868cc6dd4fca Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 16 Jun 2017 21:28:03 +0200 Subject: rtc: s3c: Minor white-space cleanups Minor cleanups to make the code easier to read. No functional changes. 1. Remove one space before labels as this is nowadays mostly preferred. 2. Fix indentation of arguments in function calls. 3. Split structure member declaration. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-s3c.c | 47 +++++++++++++++++++++++------------------------ 1 file changed, 23 insertions(+), 24 deletions(-) diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c index c5aa7a35d07f..2b503dab7957 100644 --- a/drivers/rtc/rtc-s3c.c +++ b/drivers/rtc/rtc-s3c.c @@ -49,7 +49,8 @@ struct s3c_rtc { spinlock_t pie_lock; spinlock_t alarm_clk_lock; - int ticnt_save, ticnt_en_save; + int ticnt_save; + int ticnt_en_save; bool wake_en; }; @@ -169,7 +170,7 @@ static int s3c_rtc_gettime(struct device *dev, struct rtc_time *rtc_tm) s3c_rtc_enable_clk(info); - retry_get_time: +retry_get_time: rtc_tm->tm_min = readb(info->base + S3C2410_RTCMIN); rtc_tm->tm_hour = readb(info->base + S3C2410_RTCHOUR); rtc_tm->tm_mday = readb(info->base + S3C2410_RTCDATE); @@ -199,8 +200,8 @@ static int s3c_rtc_gettime(struct device *dev, struct rtc_time *rtc_tm) rtc_tm->tm_year += 100; dev_dbg(dev, "read time %04d.%02d.%02d %02d:%02d:%02d\n", - 1900 + rtc_tm->tm_year, rtc_tm->tm_mon, rtc_tm->tm_mday, - rtc_tm->tm_hour, rtc_tm->tm_min, rtc_tm->tm_sec); + 1900 + rtc_tm->tm_year, rtc_tm->tm_mon, rtc_tm->tm_mday, + rtc_tm->tm_hour, rtc_tm->tm_min, rtc_tm->tm_sec); rtc_tm->tm_mon -= 1; @@ -213,8 +214,8 @@ static int s3c_rtc_settime(struct device *dev, struct rtc_time *tm) int year = tm->tm_year - 100; dev_dbg(dev, "set time %04d.%02d.%02d %02d:%02d:%02d\n", - 1900 + tm->tm_year, tm->tm_mon, tm->tm_mday, - tm->tm_hour, tm->tm_min, tm->tm_sec); + 1900 + tm->tm_year, tm->tm_mon, tm->tm_mday, + tm->tm_hour, tm->tm_min, tm->tm_sec); /* we get around y2k by simply not supporting it */ @@ -259,9 +260,9 @@ static int s3c_rtc_getalarm(struct device *dev, struct rtc_wkalrm *alrm) alrm->enabled = (alm_en & S3C2410_RTCALM_ALMEN) ? 1 : 0; dev_dbg(dev, "read alarm %d, %04d.%02d.%02d %02d:%02d:%02d\n", - alm_en, - 1900 + alm_tm->tm_year, alm_tm->tm_mon, alm_tm->tm_mday, - alm_tm->tm_hour, alm_tm->tm_min, alm_tm->tm_sec); + alm_en, + 1900 + alm_tm->tm_year, alm_tm->tm_mon, alm_tm->tm_mday, + alm_tm->tm_hour, alm_tm->tm_min, alm_tm->tm_sec); /* decode the alarm enable field */ if (alm_en & S3C2410_RTCALM_SECEN) @@ -295,9 +296,9 @@ static int s3c_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm) int year = tm->tm_year - 100; dev_dbg(dev, "s3c_rtc_setalarm: %d, %04d.%02d.%02d %02d:%02d:%02d\n", - alrm->enabled, - 1900 + tm->tm_year, tm->tm_mon + 1, tm->tm_mday, - tm->tm_hour, tm->tm_min, tm->tm_sec); + alrm->enabled, + 1900 + tm->tm_year, tm->tm_mon + 1, tm->tm_mday, + tm->tm_hour, tm->tm_min, tm->tm_sec); s3c_rtc_enable_clk(info); @@ -378,8 +379,7 @@ static void s3c24xx_rtc_enable(struct s3c_rtc *info) dev_info(info->dev, "rtc disabled, re-enabling\n"); tmp = readw(info->base + S3C2410_RTCCON); - writew(tmp | S3C2410_RTCCON_RTCEN, - info->base + S3C2410_RTCCON); + writew(tmp | S3C2410_RTCCON_RTCEN, info->base + S3C2410_RTCCON); } if (con & S3C2410_RTCCON_CNTSEL) { @@ -387,7 +387,7 @@ static void s3c24xx_rtc_enable(struct s3c_rtc *info) tmp = readw(info->base + S3C2410_RTCCON); writew(tmp & ~S3C2410_RTCCON_CNTSEL, - info->base + S3C2410_RTCCON); + info->base + S3C2410_RTCCON); } if (con & S3C2410_RTCCON_CLKRST) { @@ -395,7 +395,7 @@ static void s3c24xx_rtc_enable(struct s3c_rtc *info) tmp = readw(info->base + S3C2410_RTCCON); writew(tmp & ~S3C2410_RTCCON_CLKRST, - info->base + S3C2410_RTCCON); + info->base + S3C2410_RTCCON); } } @@ -481,7 +481,7 @@ static int s3c_rtc_probe(struct platform_device *pdev) } dev_dbg(&pdev->dev, "s3c2410_rtc: tick irq %d, alarm irq %d\n", - info->irq_tick, info->irq_alarm); + info->irq_tick, info->irq_alarm); /* get the memory region */ res = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -520,7 +520,7 @@ static int s3c_rtc_probe(struct platform_device *pdev) info->data->enable(info); dev_dbg(&pdev->dev, "s3c2410_rtc: RTCCON=%02x\n", - readw(info->base + S3C2410_RTCCON)); + readw(info->base + S3C2410_RTCCON)); device_init_wakeup(&pdev->dev, 1); @@ -540,7 +540,7 @@ static int s3c_rtc_probe(struct platform_device *pdev) /* register RTC and exit */ info->rtc = devm_rtc_device_register(&pdev->dev, "s3c", &s3c_rtcops, - THIS_MODULE); + THIS_MODULE); if (IS_ERR(info->rtc)) { dev_err(&pdev->dev, "cannot attach rtc\n"); ret = PTR_ERR(info->rtc); @@ -548,14 +548,14 @@ static int s3c_rtc_probe(struct platform_device *pdev) } ret = devm_request_irq(&pdev->dev, info->irq_alarm, s3c_rtc_alarmirq, - 0, "s3c2410-rtc alarm", info); + 0, "s3c2410-rtc alarm", info); if (ret) { dev_err(&pdev->dev, "IRQ%d error %d\n", info->irq_alarm, ret); goto err_nortc; } ret = devm_request_irq(&pdev->dev, info->irq_tick, s3c_rtc_tickirq, - 0, "s3c2410-rtc tick", info); + 0, "s3c2410-rtc tick", info); if (ret) { dev_err(&pdev->dev, "IRQ%d error %d\n", info->irq_tick, ret); goto err_nortc; @@ -568,7 +568,7 @@ static int s3c_rtc_probe(struct platform_device *pdev) return 0; - err_nortc: +err_nortc: if (info->data->disable) info->data->disable(info); @@ -747,8 +747,7 @@ static void s3c6410_rtc_restore_tick_cnt(struct s3c_rtc *info) writel(info->ticnt_save, info->base + S3C2410_TICNT); if (info->ticnt_en_save) { con = readw(info->base + S3C2410_RTCCON); - writew(con | info->ticnt_en_save, - info->base + S3C2410_RTCCON); + writew(con | info->ticnt_en_save, info->base + S3C2410_RTCCON); } } -- cgit v1.2.3-59-g8ed1b From 21df6fed0db35cf4382734126bd206b6c750e17c Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 16 Jun 2017 21:28:04 +0200 Subject: rtc: s3c: Drop unneeded cast to void pointer There is no need for casting to void pointer for of_device_id data. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-s3c.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c index 2b503dab7957..bfc8660ff1e7 100644 --- a/drivers/rtc/rtc-s3c.c +++ b/drivers/rtc/rtc-s3c.c @@ -801,19 +801,19 @@ static struct s3c_rtc_data const s3c6410_rtc_data = { static const struct of_device_id s3c_rtc_dt_match[] = { { .compatible = "samsung,s3c2410-rtc", - .data = (void *)&s3c2410_rtc_data, + .data = &s3c2410_rtc_data, }, { .compatible = "samsung,s3c2416-rtc", - .data = (void *)&s3c2416_rtc_data, + .data = &s3c2416_rtc_data, }, { .compatible = "samsung,s3c2443-rtc", - .data = (void *)&s3c2443_rtc_data, + .data = &s3c2443_rtc_data, }, { .compatible = "samsung,s3c6410-rtc", - .data = (void *)&s3c6410_rtc_data, + .data = &s3c6410_rtc_data, }, { .compatible = "samsung,exynos3250-rtc", - .data = (void *)&s3c6410_rtc_data, + .data = &s3c6410_rtc_data, }, { /* sentinel */ }, }; -- cgit v1.2.3-59-g8ed1b From 6b72086d8594febb9e9d63cfb29d950da17e8f06 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 16 Jun 2017 21:28:05 +0200 Subject: rtc: s3c: Do not remove const from rodata memory All instances of struct s3c_rtc_data are in fact static const thus put in rodata so we should not drop the const while getting the pointer to them. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-s3c.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c index bfc8660ff1e7..c666b95fb8d7 100644 --- a/drivers/rtc/rtc-s3c.c +++ b/drivers/rtc/rtc-s3c.c @@ -41,7 +41,7 @@ struct s3c_rtc { struct clk *rtc_src_clk; bool clk_disabled; - struct s3c_rtc_data *data; + const struct s3c_rtc_data *data; int irq_alarm; int irq_tick; @@ -437,12 +437,12 @@ static int s3c_rtc_remove(struct platform_device *pdev) static const struct of_device_id s3c_rtc_dt_match[]; -static struct s3c_rtc_data *s3c_rtc_get_data(struct platform_device *pdev) +static const struct s3c_rtc_data *s3c_rtc_get_data(struct platform_device *pdev) { const struct of_device_id *match; match = of_match_node(s3c_rtc_dt_match, pdev->dev.of_node); - return (struct s3c_rtc_data *)match->data; + return match->data; } static int s3c_rtc_probe(struct platform_device *pdev) -- cgit v1.2.3-59-g8ed1b From 9903f68af6ca9d9b25f5c50bfedd2e0cb899f848 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 16 Jun 2017 21:28:06 +0200 Subject: rtc: s3c: Handle clock prepare failures in probe clk_prepare_enable() can fail so handle such case. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-s3c.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c index c666b95fb8d7..0cb2f27a30b4 100644 --- a/drivers/rtc/rtc-s3c.c +++ b/drivers/rtc/rtc-s3c.c @@ -498,7 +498,9 @@ static int s3c_rtc_probe(struct platform_device *pdev) dev_dbg(&pdev->dev, "probe deferred due to missing rtc clk\n"); return ret; } - clk_prepare_enable(info->rtc_clk); + ret = clk_prepare_enable(info->rtc_clk); + if (ret) + return ret; if (info->data->needs_src_clk) { info->rtc_src_clk = devm_clk_get(&pdev->dev, "rtc_src"); @@ -512,7 +514,9 @@ static int s3c_rtc_probe(struct platform_device *pdev) "probe deferred due to missing rtc src clk\n"); goto err_src_clk; } - clk_prepare_enable(info->rtc_src_clk); + ret = clk_prepare_enable(info->rtc_src_clk); + if (ret) + goto err_src_clk; } /* check to see if everything is setup correctly */ -- cgit v1.2.3-59-g8ed1b From 498bcf313985c76c4572d8ce885a6480728d28f9 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 16 Jun 2017 21:28:07 +0200 Subject: rtc: s3c: Handle clock enable failures clk_enable() can fail so handle such case. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-s3c.c | 72 ++++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 57 insertions(+), 15 deletions(-) diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c index 0cb2f27a30b4..a8992c227f61 100644 --- a/drivers/rtc/rtc-s3c.c +++ b/drivers/rtc/rtc-s3c.c @@ -68,18 +68,32 @@ struct s3c_rtc_data { void (*disable) (struct s3c_rtc *info); }; -static void s3c_rtc_enable_clk(struct s3c_rtc *info) +static int s3c_rtc_enable_clk(struct s3c_rtc *info) { unsigned long irq_flags; + int ret = 0; spin_lock_irqsave(&info->alarm_clk_lock, irq_flags); + if (info->clk_disabled) { - clk_enable(info->rtc_clk); - if (info->data->needs_src_clk) - clk_enable(info->rtc_src_clk); + ret = clk_enable(info->rtc_clk); + if (ret) + goto out; + + if (info->data->needs_src_clk) { + ret = clk_enable(info->rtc_src_clk); + if (ret) { + clk_disable(info->rtc_clk); + goto out; + } + } info->clk_disabled = false; } + +out: spin_unlock_irqrestore(&info->alarm_clk_lock, irq_flags); + + return ret; } static void s3c_rtc_disable_clk(struct s3c_rtc *info) @@ -122,10 +136,13 @@ static int s3c_rtc_setaie(struct device *dev, unsigned int enabled) { struct s3c_rtc *info = dev_get_drvdata(dev); unsigned int tmp; + int ret; dev_dbg(info->dev, "%s: aie=%d\n", __func__, enabled); - s3c_rtc_enable_clk(info); + ret = s3c_rtc_enable_clk(info); + if (ret) + return ret; tmp = readb(info->base + S3C2410_RTCALM) & ~S3C2410_RTCALM_ALMEN; @@ -136,10 +153,13 @@ static int s3c_rtc_setaie(struct device *dev, unsigned int enabled) s3c_rtc_disable_clk(info); - if (enabled) - s3c_rtc_enable_clk(info); - else + if (enabled) { + ret = s3c_rtc_enable_clk(info); + if (ret) + return ret; + } else { s3c_rtc_disable_clk(info); + } return 0; } @@ -147,10 +167,14 @@ static int s3c_rtc_setaie(struct device *dev, unsigned int enabled) /* Set RTC frequency */ static int s3c_rtc_setfreq(struct s3c_rtc *info, int freq) { + int ret; + if (!is_power_of_2(freq)) return -EINVAL; - s3c_rtc_enable_clk(info); + ret = s3c_rtc_enable_clk(info); + if (ret) + return ret; spin_lock_irq(&info->pie_lock); if (info->data->set_freq) @@ -167,8 +191,11 @@ static int s3c_rtc_gettime(struct device *dev, struct rtc_time *rtc_tm) { struct s3c_rtc *info = dev_get_drvdata(dev); unsigned int have_retried = 0; + int ret; - s3c_rtc_enable_clk(info); + ret = s3c_rtc_enable_clk(info); + if (ret) + return ret; retry_get_time: rtc_tm->tm_min = readb(info->base + S3C2410_RTCMIN); @@ -212,6 +239,7 @@ static int s3c_rtc_settime(struct device *dev, struct rtc_time *tm) { struct s3c_rtc *info = dev_get_drvdata(dev); int year = tm->tm_year - 100; + int ret; dev_dbg(dev, "set time %04d.%02d.%02d %02d:%02d:%02d\n", 1900 + tm->tm_year, tm->tm_mon, tm->tm_mday, @@ -224,7 +252,9 @@ static int s3c_rtc_settime(struct device *dev, struct rtc_time *tm) return -EINVAL; } - s3c_rtc_enable_clk(info); + ret = s3c_rtc_enable_clk(info); + if (ret) + return ret; writeb(bin2bcd(tm->tm_sec), info->base + S3C2410_RTCSEC); writeb(bin2bcd(tm->tm_min), info->base + S3C2410_RTCMIN); @@ -243,8 +273,11 @@ static int s3c_rtc_getalarm(struct device *dev, struct rtc_wkalrm *alrm) struct s3c_rtc *info = dev_get_drvdata(dev); struct rtc_time *alm_tm = &alrm->time; unsigned int alm_en; + int ret; - s3c_rtc_enable_clk(info); + ret = s3c_rtc_enable_clk(info); + if (ret) + return ret; alm_tm->tm_sec = readb(info->base + S3C2410_ALMSEC); alm_tm->tm_min = readb(info->base + S3C2410_ALMMIN); @@ -293,6 +326,7 @@ static int s3c_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm) struct s3c_rtc *info = dev_get_drvdata(dev); struct rtc_time *tm = &alrm->time; unsigned int alrm_en; + int ret; int year = tm->tm_year - 100; dev_dbg(dev, "s3c_rtc_setalarm: %d, %04d.%02d.%02d %02d:%02d:%02d\n", @@ -300,7 +334,9 @@ static int s3c_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm) 1900 + tm->tm_year, tm->tm_mon + 1, tm->tm_mday, tm->tm_hour, tm->tm_min, tm->tm_sec); - s3c_rtc_enable_clk(info); + ret = s3c_rtc_enable_clk(info); + if (ret) + return ret; alrm_en = readb(info->base + S3C2410_RTCALM) & S3C2410_RTCALM_ALMEN; writeb(0x00, info->base + S3C2410_RTCALM); @@ -349,8 +385,11 @@ static int s3c_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm) static int s3c_rtc_proc(struct device *dev, struct seq_file *seq) { struct s3c_rtc *info = dev_get_drvdata(dev); + int ret; - s3c_rtc_enable_clk(info); + ret = s3c_rtc_enable_clk(info); + if (ret) + return ret; if (info->data->enable_tick) info->data->enable_tick(info, seq); @@ -589,8 +628,11 @@ err_src_clk: static int s3c_rtc_suspend(struct device *dev) { struct s3c_rtc *info = dev_get_drvdata(dev); + int ret; - s3c_rtc_enable_clk(info); + ret = s3c_rtc_enable_clk(info); + if (ret) + return ret; /* save TICNT for anyone using periodic interrupts */ if (info->data->save_tick_cnt) -- cgit v1.2.3-59-g8ed1b From ee0981be7704589635de23cc32556399c86653a8 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sun, 18 Jun 2017 22:55:28 +0200 Subject: rtc: ds1307: Add support for Epson RX8130CE Add support for yet another RTC chip, Epson RX8130CE. This time around, the chip has slightly permutated registers and also the register starts at 0x10 instead of 0x0 . So far, we only support the RTC and NVRAM parts of the chip, Alarm and Timer is not supported. Signed-off-by: Marek Vasut Cc: Alexandre Belloni Cc: Arnd Bergmann Cc: Felipe Balbi Cc: Nishanth Menon Cc: Tony Lindgren Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ds1307.c | 175 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 175 insertions(+) diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index 16ace2fb0c0a..3cbb7636b405 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -44,6 +44,7 @@ enum ds_type { m41t00, mcp794xx, rx_8025, + rx_8130, last_ds_type /* always last */ /* rs5c372 too? different address... */ }; @@ -169,6 +170,12 @@ static struct chip_desc chips[last_ds_type] = { [ds_3231] = { .alarm = 1, }, + [rx_8130] = { + .alarm = 1, + /* this is battery backed SRAM */ + .nvram_offset = 0x20, + .nvram_size = 4, /* 32bit (4 word x 8 bit) */ + }, [mcp794xx] = { .alarm = 1, /* this is battery backed SRAM */ @@ -192,6 +199,7 @@ static const struct i2c_device_id ds1307_id[] = { { "pt7c4338", ds_1307 }, { "rx8025", rx_8025 }, { "isl12057", ds_1337 }, + { "rx8130", rx_8130 }, { } }; MODULE_DEVICE_TABLE(i2c, ds1307_id); @@ -586,6 +594,165 @@ static const struct rtc_class_ops ds13xx_rtc_ops = { /*----------------------------------------------------------------------*/ +/* + * Alarm support for rx8130 devices. + */ + +#define RX8130_REG_ALARM_MIN 0x07 +#define RX8130_REG_ALARM_HOUR 0x08 +#define RX8130_REG_ALARM_WEEK_OR_DAY 0x09 +#define RX8130_REG_EXTENSION 0x0c +#define RX8130_REG_EXTENSION_WADA (1 << 3) +#define RX8130_REG_FLAG 0x0d +#define RX8130_REG_FLAG_AF (1 << 3) +#define RX8130_REG_CONTROL0 0x0e +#define RX8130_REG_CONTROL0_AIE (1 << 3) + +static irqreturn_t rx8130_irq(int irq, void *dev_id) +{ + struct ds1307 *ds1307 = dev_id; + struct mutex *lock = &ds1307->rtc->ops_lock; + u8 ctl[3]; + int ret; + + mutex_lock(lock); + + /* Read control registers. */ + ret = regmap_bulk_read(ds1307->regmap, RX8130_REG_EXTENSION, ctl, 3); + if (ret < 0) + goto out; + if (!(ctl[1] & RX8130_REG_FLAG_AF)) + goto out; + ctl[1] &= ~RX8130_REG_FLAG_AF; + ctl[2] &= ~RX8130_REG_CONTROL0_AIE; + + ret = regmap_bulk_write(ds1307->regmap, RX8130_REG_EXTENSION, ctl, 3); + if (ret < 0) + goto out; + + rtc_update_irq(ds1307->rtc, 1, RTC_AF | RTC_IRQF); + +out: + mutex_unlock(lock); + + return IRQ_HANDLED; +} + +static int rx8130_read_alarm(struct device *dev, struct rtc_wkalrm *t) +{ + struct ds1307 *ds1307 = dev_get_drvdata(dev); + u8 ald[3], ctl[3]; + int ret; + + if (!test_bit(HAS_ALARM, &ds1307->flags)) + return -EINVAL; + + /* Read alarm registers. */ + ret = regmap_bulk_read(ds1307->regmap, RX8130_REG_ALARM_MIN, ald, 3); + if (ret < 0) + return ret; + + /* Read control registers. */ + ret = regmap_bulk_read(ds1307->regmap, RX8130_REG_EXTENSION, ctl, 3); + if (ret < 0) + return ret; + + t->enabled = !!(ctl[2] & RX8130_REG_CONTROL0_AIE); + t->pending = !!(ctl[1] & RX8130_REG_FLAG_AF); + + /* Report alarm 0 time assuming 24-hour and day-of-month modes. */ + t->time.tm_sec = -1; + t->time.tm_min = bcd2bin(ald[0] & 0x7f); + t->time.tm_hour = bcd2bin(ald[1] & 0x7f); + t->time.tm_wday = -1; + t->time.tm_mday = bcd2bin(ald[2] & 0x7f); + t->time.tm_mon = -1; + t->time.tm_year = -1; + t->time.tm_yday = -1; + t->time.tm_isdst = -1; + + dev_dbg(dev, "%s, sec=%d min=%d hour=%d wday=%d mday=%d mon=%d enabled=%d\n", + __func__, t->time.tm_sec, t->time.tm_min, t->time.tm_hour, + t->time.tm_wday, t->time.tm_mday, t->time.tm_mon, t->enabled); + + return 0; +} + +static int rx8130_set_alarm(struct device *dev, struct rtc_wkalrm *t) +{ + struct ds1307 *ds1307 = dev_get_drvdata(dev); + u8 ald[3], ctl[3]; + int ret; + + if (!test_bit(HAS_ALARM, &ds1307->flags)) + return -EINVAL; + + dev_dbg(dev, "%s, sec=%d min=%d hour=%d wday=%d mday=%d mon=%d " + "enabled=%d pending=%d\n", __func__, + t->time.tm_sec, t->time.tm_min, t->time.tm_hour, + t->time.tm_wday, t->time.tm_mday, t->time.tm_mon, + t->enabled, t->pending); + + /* Read control registers. */ + ret = regmap_bulk_read(ds1307->regmap, RX8130_REG_EXTENSION, ctl, 3); + if (ret < 0) + return ret; + + ctl[0] &= ~RX8130_REG_EXTENSION_WADA; + ctl[1] |= RX8130_REG_FLAG_AF; + ctl[2] &= ~RX8130_REG_CONTROL0_AIE; + + ret = regmap_bulk_write(ds1307->regmap, RX8130_REG_EXTENSION, ctl, 3); + if (ret < 0) + return ret; + + /* Hardware alarm precision is 1 minute! */ + ald[0] = bin2bcd(t->time.tm_min); + ald[1] = bin2bcd(t->time.tm_hour); + ald[2] = bin2bcd(t->time.tm_mday); + + ret = regmap_bulk_write(ds1307->regmap, RX8130_REG_ALARM_MIN, ald, 3); + if (ret < 0) + return ret; + + if (!t->enabled) + return 0; + + ctl[2] |= RX8130_REG_CONTROL0_AIE; + + return regmap_bulk_write(ds1307->regmap, RX8130_REG_EXTENSION, ctl, 3); +} + +static int rx8130_alarm_irq_enable(struct device *dev, unsigned int enabled) +{ + struct ds1307 *ds1307 = dev_get_drvdata(dev); + int ret, reg; + + if (!test_bit(HAS_ALARM, &ds1307->flags)) + return -EINVAL; + + ret = regmap_read(ds1307->regmap, RX8130_REG_CONTROL0, ®); + if (ret < 0) + return ret; + + if (enabled) + reg |= RX8130_REG_CONTROL0_AIE; + else + reg &= ~RX8130_REG_CONTROL0_AIE; + + return regmap_write(ds1307->regmap, RX8130_REG_CONTROL0, reg); +} + +static const struct rtc_class_ops rx8130_rtc_ops = { + .read_time = ds1307_get_time, + .set_time = ds1307_set_time, + .read_alarm = rx8130_read_alarm, + .set_alarm = rx8130_set_alarm, + .alarm_irq_enable = rx8130_alarm_irq_enable, +}; + +/*----------------------------------------------------------------------*/ + /* * Alarm support for mcp794xx devices. */ @@ -1402,6 +1569,14 @@ static int ds1307_probe(struct i2c_client *client, DS1307_REG_HOUR << 4 | 0x08, hour); } break; + case rx_8130: + ds1307->offset = 0x10; /* Seconds starts at 0x10 */ + rtc_ops = &rx8130_rtc_ops; + if (chip->alarm && ds1307->irq > 0) { + irq_handler = rx8130_irq; + want_irq = true; + } + break; case ds_1388: ds1307->offset = 1; /* Seconds starts at 1 */ break; -- cgit v1.2.3-59-g8ed1b From 188986c70e09f0f3cd88e6fe14c89e439474e3ec Mon Sep 17 00:00:00 2001 From: Xiaolei Li Date: Fri, 23 Jun 2017 15:12:24 +0800 Subject: mtd: nand: mtk: fix incorrect register setting order about ecc irq Currently, we trigger ECC HW before setting ecc irq. It is incorrect. Because ECC starts working once the register ECC_CTL_REG is set as ECC_OP_ENABLE. And this may lead an abnormal behavior of ecc irq. So, should enable ecc irq at first, then trigger ECC. Fixes: 1d6b1e464950 ("mtd: mediatek: driver for MTK Smart Device") Signed-off-by: Xiaolei Li Signed-off-by: Boris Brezillon --- drivers/mtd/nand/mtk_ecc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/nand/mtk_ecc.c b/drivers/mtd/nand/mtk_ecc.c index 4958121cb827..a855a4e5cc35 100644 --- a/drivers/mtd/nand/mtk_ecc.c +++ b/drivers/mtd/nand/mtk_ecc.c @@ -276,8 +276,6 @@ int mtk_ecc_enable(struct mtk_ecc *ecc, struct mtk_ecc_config *config) if (ret) return ret; - writew(ECC_OP_ENABLE, ecc->regs + ECC_CTL_REG(op)); - init_completion(&ecc->done); reg_val = ECC_IRQ_EN; /* @@ -289,6 +287,8 @@ int mtk_ecc_enable(struct mtk_ecc *ecc, struct mtk_ecc_config *config) reg_val |= ECC_PG_IRQ_SEL; writew(reg_val, ecc->regs + ECC_IRQ_REG(op)); + writew(ECC_OP_ENABLE, ecc->regs + ECC_CTL_REG(op)); + return 0; } EXPORT_SYMBOL(mtk_ecc_enable); -- cgit v1.2.3-59-g8ed1b From 88404312556c10e4bcd1aeeb75b1b7e9e3226160 Mon Sep 17 00:00:00 2001 From: Xiaolei Li Date: Fri, 23 Jun 2017 15:12:25 +0800 Subject: mtd: nand: mtk: disable ecc irq when writing page with hwecc Currently, ecc encode irq is enabled when writing page with hwecc, but we actually do not wait for this irq done. Because NFI and ECC work in parallel, nfi irq and ecc irq almost come together. Now, there are two steps to check whether page data are totally written. First, wait for nfi irq INTR_AHB_DONE. This is to ensure all data in RAM are received by NFI. Second, polling the register NFI_ADDRCNTR till all data include ecc parity data runtime generated by ECC are sent to NAND device. So, it is redunant to enable ecc irq without waiting for it. Signed-off-by: Xiaolei Li Signed-off-by: Boris Brezillon --- drivers/mtd/nand/mtk_ecc.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/drivers/mtd/nand/mtk_ecc.c b/drivers/mtd/nand/mtk_ecc.c index a855a4e5cc35..00ce22e0eaf0 100644 --- a/drivers/mtd/nand/mtk_ecc.c +++ b/drivers/mtd/nand/mtk_ecc.c @@ -276,16 +276,18 @@ int mtk_ecc_enable(struct mtk_ecc *ecc, struct mtk_ecc_config *config) if (ret) return ret; - init_completion(&ecc->done); - reg_val = ECC_IRQ_EN; - /* - * For ECC_NFI_MODE, if ecc->caps->pg_irq_sel is 1, then it - * means this chip can only generate one ecc irq during page - * read / write. If is 0, generate one ecc irq each ecc step. - */ - if ((ecc->caps->pg_irq_sel) && (config->mode == ECC_NFI_MODE)) - reg_val |= ECC_PG_IRQ_SEL; - writew(reg_val, ecc->regs + ECC_IRQ_REG(op)); + if (config->mode != ECC_NFI_MODE || op != ECC_ENCODE) { + init_completion(&ecc->done); + reg_val = ECC_IRQ_EN; + /* + * For ECC_NFI_MODE, if ecc->caps->pg_irq_sel is 1, then it + * means this chip can only generate one ecc irq during page + * read / write. If is 0, generate one ecc irq each ecc step. + */ + if (ecc->caps->pg_irq_sel && config->mode == ECC_NFI_MODE) + reg_val |= ECC_PG_IRQ_SEL; + writew(reg_val, ecc->regs + ECC_IRQ_REG(op)); + } writew(ECC_OP_ENABLE, ecc->regs + ECC_CTL_REG(op)); -- cgit v1.2.3-59-g8ed1b From 777a8d92dfca26e63b0fe7ea9889618291512f1d Mon Sep 17 00:00:00 2001 From: Xiaolei Li Date: Fri, 23 Jun 2017 15:12:26 +0800 Subject: mtd: nand: mtk: remove unneeded mtk_nfc_hw_init from mtk_nfc_resume chip->select_chip will do nfc runtime configuration. There is no need to do mtk_nfc_hw_init before it. Signed-off-by: Xiaolei Li Signed-off-by: Boris Brezillon --- drivers/mtd/nand/mtk_nand.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/mtd/nand/mtk_nand.c b/drivers/mtd/nand/mtk_nand.c index 4d9ee278b9a0..d51c58e61812 100644 --- a/drivers/mtd/nand/mtk_nand.c +++ b/drivers/mtd/nand/mtk_nand.c @@ -1490,8 +1490,6 @@ static int mtk_nfc_resume(struct device *dev) if (ret) return ret; - mtk_nfc_hw_init(nfc); - /* reset NAND chip if VCC was powered off */ list_for_each_entry(chip, &nfc->chips, node) { nand = &chip->nand; -- cgit v1.2.3-59-g8ed1b From c4ec13543e322d4cc68eb6018f5a8a8858d0053a Mon Sep 17 00:00:00 2001 From: Xiaolei Li Date: Fri, 23 Jun 2017 15:12:27 +0800 Subject: mtd: nand: mtk: remove unneeded mtk_ecc_hw_init from mtk_ecc_resume There is no need to add mtk_ecc_hw_init during ecc resume, because there always takes mtk_ecc_wait_idle in the function mtk_ecc_enable. Signed-off-by: Xiaolei Li Signed-off-by: Boris Brezillon --- drivers/mtd/nand/mtk_ecc.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/mtd/nand/mtk_ecc.c b/drivers/mtd/nand/mtk_ecc.c index 00ce22e0eaf0..f38e2bb1953e 100644 --- a/drivers/mtd/nand/mtk_ecc.c +++ b/drivers/mtd/nand/mtk_ecc.c @@ -507,8 +507,6 @@ static int mtk_ecc_resume(struct device *dev) return ret; } - mtk_ecc_hw_init(ecc); - return 0; } -- cgit v1.2.3-59-g8ed1b From edfee3619c4955be38d414f25bd4f6c5c1b029ba Mon Sep 17 00:00:00 2001 From: Xiaolei Li Date: Fri, 23 Jun 2017 15:12:28 +0800 Subject: mtd: nand: mtk: add ->setup_data_interface() hook Currently, we use the fixed ACC timing 0x10804211. This is not the best setting for each case. Actually, MTK NAND controller can adapt ACC timings dynamically according to nfi clock frequence. Implement the ->setup_data_interface() hook to optimize driver performance. Signed-off-by: Xiaolei Li Signed-off-by: Boris Brezillon --- drivers/mtd/nand/mtk_nand.c | 90 +++++++++++++++++++++++++++++++++++++-------- 1 file changed, 75 insertions(+), 15 deletions(-) diff --git a/drivers/mtd/nand/mtk_nand.c b/drivers/mtd/nand/mtk_nand.c index d51c58e61812..f7ae99464375 100644 --- a/drivers/mtd/nand/mtk_nand.c +++ b/drivers/mtd/nand/mtk_nand.c @@ -100,11 +100,15 @@ #define MTK_MAX_SECTOR (16) #define MTK_NAND_MAX_NSELS (2) #define MTK_NFC_MIN_SPARE (16) +#define ACCTIMING(tpoecs, tprecs, tc2r, tw2r, twh, twst, trlt) \ + ((tpoecs) << 28 | (tprecs) << 22 | (tc2r) << 16 | \ + (tw2r) << 12 | (twh) << 8 | (twst) << 4 | (trlt)) struct mtk_nfc_caps { const u8 *spare_size; u8 num_spare_size; u8 pageformat_spare_shift; + u8 nfi_clk_div; }; struct mtk_nfc_bad_mark_ctl { @@ -495,6 +499,74 @@ static void mtk_nfc_write_buf(struct mtd_info *mtd, const u8 *buf, int len) mtk_nfc_write_byte(mtd, buf[i]); } +static int mtk_nfc_setup_data_interface(struct mtd_info *mtd, int csline, + const struct nand_data_interface *conf) +{ + struct mtk_nfc *nfc = nand_get_controller_data(mtd_to_nand(mtd)); + const struct nand_sdr_timings *timings; + u32 rate, tpoecs, tprecs, tc2r, tw2r, twh, twst, trlt; + + timings = nand_get_sdr_timings(conf); + if (IS_ERR(timings)) + return -ENOTSUPP; + + if (csline == NAND_DATA_IFACE_CHECK_ONLY) + return 0; + + rate = clk_get_rate(nfc->clk.nfi_clk); + /* There is a frequency divider in some IPs */ + rate /= nfc->caps->nfi_clk_div; + + /* turn clock rate into KHZ */ + rate /= 1000; + + tpoecs = max(timings->tALH_min, timings->tCLH_min) / 1000; + tpoecs = DIV_ROUND_UP(tpoecs * rate, 1000000); + tpoecs &= 0xf; + + tprecs = max(timings->tCLS_min, timings->tALS_min) / 1000; + tprecs = DIV_ROUND_UP(tprecs * rate, 1000000); + tprecs &= 0x3f; + + /* sdr interface has no tCR which means CE# low to RE# low */ + tc2r = 0; + + tw2r = timings->tWHR_min / 1000; + tw2r = DIV_ROUND_UP(tw2r * rate, 1000000); + tw2r = DIV_ROUND_UP(tw2r - 1, 2); + tw2r &= 0xf; + + twh = max(timings->tREH_min, timings->tWH_min) / 1000; + twh = DIV_ROUND_UP(twh * rate, 1000000) - 1; + twh &= 0xf; + + twst = timings->tWP_min / 1000; + twst = DIV_ROUND_UP(twst * rate, 1000000) - 1; + twst &= 0xf; + + trlt = max(timings->tREA_max, timings->tRP_min) / 1000; + trlt = DIV_ROUND_UP(trlt * rate, 1000000) - 1; + trlt &= 0xf; + + /* + * ACCON: access timing control register + * ------------------------------------- + * 31:28: tpoecs, minimum required time for CS post pulling down after + * accessing the device + * 27:22: tprecs, minimum required time for CS pre pulling down before + * accessing the device + * 21:16: tc2r, minimum required time from NCEB low to NREB low + * 15:12: tw2r, minimum required time from NWEB high to NREB low. + * 11:08: twh, write enable hold time + * 07:04: twst, write wait states + * 03:00: trlt, read wait states + */ + trlt = ACCTIMING(tpoecs, tprecs, tc2r, tw2r, twh, twst, trlt); + nfi_writel(nfc, trlt, NFI_ACCCON); + + return 0; +} + static int mtk_nfc_sector_encode(struct nand_chip *chip, u8 *data) { struct mtk_nfc *nfc = nand_get_controller_data(chip); @@ -951,21 +1023,6 @@ static int mtk_nfc_read_oob_std(struct mtd_info *mtd, struct nand_chip *chip, static inline void mtk_nfc_hw_init(struct mtk_nfc *nfc) { - /* - * ACCON: access timing control register - * ------------------------------------- - * 31:28: minimum required time for CS post pulling down after accessing - * the device - * 27:22: minimum required time for CS pre pulling down before accessing - * the device - * 21:16: minimum required time from NCEB low to NREB low - * 15:12: minimum required time from NWEB high to NREB low. - * 11:08: write enable hold time - * 07:04: write wait states - * 03:00: read wait states - */ - nfi_writel(nfc, 0x10804211, NFI_ACCCON); - /* * CNRNB: nand ready/busy register * ------------------------------- @@ -1240,6 +1297,7 @@ static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc, nand->read_byte = mtk_nfc_read_byte; nand->read_buf = mtk_nfc_read_buf; nand->cmd_ctrl = mtk_nfc_cmd_ctrl; + nand->setup_data_interface = mtk_nfc_setup_data_interface; /* set default mode in case dt entry is missing */ nand->ecc.mode = NAND_ECC_HW; @@ -1330,12 +1388,14 @@ static const struct mtk_nfc_caps mtk_nfc_caps_mt2701 = { .spare_size = spare_size_mt2701, .num_spare_size = 16, .pageformat_spare_shift = 4, + .nfi_clk_div = 1, }; static const struct mtk_nfc_caps mtk_nfc_caps_mt2712 = { .spare_size = spare_size_mt2712, .num_spare_size = 19, .pageformat_spare_shift = 16, + .nfi_clk_div = 2, }; static const struct of_device_id mtk_nfc_id_table[] = { -- cgit v1.2.3-59-g8ed1b From 62d02fd1f807bf5a259a242c483c9fb98a242630 Mon Sep 17 00:00:00 2001 From: Chuanxiao Dong Date: Mon, 26 Jun 2017 15:20:49 +0800 Subject: drm/i915/gvt: Fix possible recursive locking issue vfio_unpin_pages will hold a read semaphore however it is already hold in the same thread by vfio ioctl. It will cause below warning: [ 5102.127454] ============================================ [ 5102.133379] WARNING: possible recursive locking detected [ 5102.139304] 4.12.0-rc4+ #3 Not tainted [ 5102.143483] -------------------------------------------- [ 5102.149407] qemu-system-x86/1620 is trying to acquire lock: [ 5102.155624] (&container->group_lock){++++++}, at: [] vfio_unpin_pages+0x96/0xf0 [ 5102.165626] but task is already holding lock: [ 5102.172134] (&container->group_lock){++++++}, at: [] vfio_fops_unl_ioctl+0x5f/0x280 [ 5102.182522] other info that might help us debug this: [ 5102.189806] Possible unsafe locking scenario: [ 5102.196411] CPU0 [ 5102.199136] ---- [ 5102.201861] lock(&container->group_lock); [ 5102.206527] lock(&container->group_lock); [ 5102.211191] *** DEADLOCK *** [ 5102.217796] May be due to missing lock nesting notation [ 5102.225370] 3 locks held by qemu-system-x86/1620: [ 5102.230618] #0: (&container->group_lock){++++++}, at: [] vfio_fops_unl_ioctl+0x5f/0x280 [ 5102.241482] #1: (&(&iommu->notifier)->rwsem){++++..}, at: [] __blocking_notifier_call_chain+0x35/0x70 [ 5102.253713] #2: (&vgpu->vdev.cache_lock){+.+...}, at: [] intel_vgpu_iommu_notifier+0x77/0x120 [ 5102.265163] stack backtrace: [ 5102.270022] CPU: 5 PID: 1620 Comm: qemu-system-x86 Not tainted 4.12.0-rc4+ #3 [ 5102.277991] Hardware name: Intel Corporation S1200RP/S1200RP, BIOS S1200RP.86B.03.01.APER.061220151418 06/12/2015 [ 5102.289445] Call Trace: [ 5102.292175] dump_stack+0x85/0xc7 [ 5102.295871] validate_chain.isra.21+0x9da/0xaf0 [ 5102.300925] __lock_acquire+0x405/0x820 [ 5102.305202] lock_acquire+0xc7/0x220 [ 5102.309191] ? vfio_unpin_pages+0x96/0xf0 [ 5102.313666] down_read+0x2b/0x50 [ 5102.317259] ? vfio_unpin_pages+0x96/0xf0 [ 5102.321732] vfio_unpin_pages+0x96/0xf0 [ 5102.326024] intel_vgpu_iommu_notifier+0xe5/0x120 [ 5102.331283] notifier_call_chain+0x4a/0x70 [ 5102.335851] __blocking_notifier_call_chain+0x4d/0x70 [ 5102.341490] blocking_notifier_call_chain+0x16/0x20 [ 5102.346935] vfio_iommu_type1_ioctl+0x87b/0x920 [ 5102.351994] vfio_fops_unl_ioctl+0x81/0x280 [ 5102.356660] ? __fget+0xf0/0x210 [ 5102.360261] do_vfs_ioctl+0x93/0x6a0 [ 5102.364247] ? __fget+0x111/0x210 [ 5102.367942] SyS_ioctl+0x41/0x70 [ 5102.371542] entry_SYSCALL_64_fastpath+0x1f/0xbe put the vfio_unpin_pages in a workqueue can fix this. v2: - use for style instead of do{}while(1). (Zhenyu) v3: - rename gvt_cache_mark to gvt_cache_mark_remove. (Zhenyu) Fixes: 659643f7d814 ("drm/i915/gvt/kvmgt: add vfio/mdev support to KVMGT") Signed-off-by: Chuanxiao Dong Cc: Zhenyu Wang Cc: stable@vger.kernel.org # v4.10+ Signed-off-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/gvt.h | 3 +++ drivers/gpu/drm/i915/gvt/kvmgt.c | 55 ++++++++++++++++++++++++++++++++-------- 2 files changed, 48 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index 930732e5c780..8b5876d63624 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -183,6 +183,9 @@ struct intel_vgpu { struct kvm *kvm; struct work_struct release_work; atomic_t released; + struct work_struct unpin_work; + spinlock_t unpin_lock; /* To protect unpin_list */ + struct list_head unpin_list; } vdev; #endif }; diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 1ae0b4083ce1..56a8d6a7d9c6 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -78,6 +78,7 @@ struct gvt_dma { struct rb_node node; gfn_t gfn; unsigned long iova; + struct list_head list; }; static inline bool handle_valid(unsigned long handle) @@ -166,6 +167,7 @@ static void gvt_cache_add(struct intel_vgpu *vgpu, gfn_t gfn, new->gfn = gfn; new->iova = iova; + INIT_LIST_HEAD(&new->list); mutex_lock(&vgpu->vdev.cache_lock); while (*link) { @@ -197,26 +199,52 @@ static void __gvt_cache_remove_entry(struct intel_vgpu *vgpu, kfree(entry); } -static void gvt_cache_remove(struct intel_vgpu *vgpu, gfn_t gfn) +static void intel_vgpu_unpin_work(struct work_struct *work) { + struct intel_vgpu *vgpu = container_of(work, struct intel_vgpu, + vdev.unpin_work); struct device *dev = mdev_dev(vgpu->vdev.mdev); struct gvt_dma *this; - unsigned long g1; - int rc; + unsigned long gfn; + + for (;;) { + spin_lock(&vgpu->vdev.unpin_lock); + if (list_empty(&vgpu->vdev.unpin_list)) { + spin_unlock(&vgpu->vdev.unpin_lock); + break; + } + this = list_first_entry(&vgpu->vdev.unpin_list, + struct gvt_dma, list); + list_del(&this->list); + spin_unlock(&vgpu->vdev.unpin_lock); + + gfn = this->gfn; + vfio_unpin_pages(dev, &gfn, 1); + kfree(this); + } +} + +static bool gvt_cache_mark_remove(struct intel_vgpu *vgpu, gfn_t gfn) +{ + struct gvt_dma *this; mutex_lock(&vgpu->vdev.cache_lock); this = __gvt_cache_find(vgpu, gfn); if (!this) { mutex_unlock(&vgpu->vdev.cache_lock); - return; + return false; } - - g1 = gfn; gvt_dma_unmap_iova(vgpu, this->iova); - rc = vfio_unpin_pages(dev, &g1, 1); - WARN_ON(rc != 1); - __gvt_cache_remove_entry(vgpu, this); + /* remove this from rb tree */ + rb_erase(&this->node, &vgpu->vdev.cache); mutex_unlock(&vgpu->vdev.cache_lock); + + /* put this to the unpin_list */ + spin_lock(&vgpu->vdev.unpin_lock); + list_move_tail(&this->list, &vgpu->vdev.unpin_list); + spin_unlock(&vgpu->vdev.unpin_lock); + + return true; } static void gvt_cache_init(struct intel_vgpu *vgpu) @@ -453,6 +481,9 @@ static int intel_vgpu_create(struct kobject *kobj, struct mdev_device *mdev) } INIT_WORK(&vgpu->vdev.release_work, intel_vgpu_release_work); + INIT_WORK(&vgpu->vdev.unpin_work, intel_vgpu_unpin_work); + spin_lock_init(&vgpu->vdev.unpin_lock); + INIT_LIST_HEAD(&vgpu->vdev.unpin_list); vgpu->vdev.mdev = mdev; mdev_set_drvdata(mdev, vgpu); @@ -482,6 +513,7 @@ static int intel_vgpu_iommu_notifier(struct notifier_block *nb, struct intel_vgpu *vgpu = container_of(nb, struct intel_vgpu, vdev.iommu_notifier); + bool sched_unmap = false; if (action == VFIO_IOMMU_NOTIFY_DMA_UNMAP) { struct vfio_iommu_type1_dma_unmap *unmap = data; @@ -491,7 +523,10 @@ static int intel_vgpu_iommu_notifier(struct notifier_block *nb, end_gfn = gfn + unmap->size / PAGE_SIZE; while (gfn < end_gfn) - gvt_cache_remove(vgpu, gfn++); + sched_unmap |= gvt_cache_mark_remove(vgpu, gfn++); + + if (sched_unmap) + schedule_work(&vgpu->vdev.unpin_work); } return NOTIFY_OK; -- cgit v1.2.3-59-g8ed1b From f16bd3dda2c8bf6699e808cd9cc540cfab10e60e Mon Sep 17 00:00:00 2001 From: Chuanxiao Dong Date: Mon, 26 Jun 2017 15:20:50 +0800 Subject: drm/i915/gvt: Fix inconsistent locks holding sequence There are two kinds of locking sequence. One is in the thread which is started by vfio ioctl to do the iommu unmapping. The locking sequence is: down_read(&group_lock) ----> mutex_lock(&cached_lock) The other is in the vfio release thread which will unpin all the cached pages. The lock sequence is: mutex_lock(&cached_lock) ---> down_read(&group_lock) And, the cache_lock is used to protect the rb tree of the cache node and doing vfio unpin doesn't require this lock. Move the vfio unpin out of the cache_lock protected region. v2: - use for style instead of do{}while(1). (Zhenyu) Fixes: f30437c5e7bf ("drm/i915/gvt: add KVMGT support") Signed-off-by: Chuanxiao Dong Cc: Zhenyu Wang Cc: stable@vger.kernel.org # v4.10+ Signed-off-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/kvmgt.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 56a8d6a7d9c6..75a6e1d8af0d 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -260,16 +260,20 @@ static void gvt_cache_destroy(struct intel_vgpu *vgpu) struct device *dev = mdev_dev(vgpu->vdev.mdev); unsigned long gfn; - mutex_lock(&vgpu->vdev.cache_lock); - while ((node = rb_first(&vgpu->vdev.cache))) { + for (;;) { + mutex_lock(&vgpu->vdev.cache_lock); + node = rb_first(&vgpu->vdev.cache); + if (!node) { + mutex_unlock(&vgpu->vdev.cache_lock); + break; + } dma = rb_entry(node, struct gvt_dma, node); gvt_dma_unmap_iova(vgpu, dma->iova); gfn = dma->gfn; - - vfio_unpin_pages(dev, &gfn, 1); __gvt_cache_remove_entry(vgpu, dma); + mutex_unlock(&vgpu->vdev.cache_lock); + vfio_unpin_pages(dev, &gfn, 1); } - mutex_unlock(&vgpu->vdev.cache_lock); } static struct intel_vgpu_type *intel_gvt_find_vgpu_type(struct intel_gvt *gvt, -- cgit v1.2.3-59-g8ed1b From 38cb266ad1a24e037220dc563ab46364595b17b6 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Fri, 23 Jun 2017 14:00:13 -0600 Subject: DRM: Fix an incorrectly formatted table The "supported input formats" table in dw_hdmi.h was incorrectly formatted, using "+" signs where "|" needs to be. That, in turn, causes the PDF build to fail. Fixes: def23aa7e982 ("drm: bridge: dw-hdmi: Switch to V4L bus format and encodings") Signed-off-by: Jonathan Corbet Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/20170623140013.0703107a@lwn.net --- include/drm/bridge/dw_hdmi.h | 70 ++++++++++++++++++++++---------------------- 1 file changed, 35 insertions(+), 35 deletions(-) diff --git a/include/drm/bridge/dw_hdmi.h b/include/drm/bridge/dw_hdmi.h index 4c8d4c81a0e8..182f83283e24 100644 --- a/include/drm/bridge/dw_hdmi.h +++ b/include/drm/bridge/dw_hdmi.h @@ -22,56 +22,56 @@ struct dw_hdmi; * 48bit bus. * * +----------------------+----------------------------------+------------------------------+ - * + Format Name + Format Code + Encodings + + * | Format Name | Format Code | Encodings | * +----------------------+----------------------------------+------------------------------+ - * + RGB 4:4:4 8bit + ``MEDIA_BUS_FMT_RGB888_1X24`` + ``V4L2_YCBCR_ENC_DEFAULT`` + + * | RGB 4:4:4 8bit | ``MEDIA_BUS_FMT_RGB888_1X24`` | ``V4L2_YCBCR_ENC_DEFAULT`` | * +----------------------+----------------------------------+------------------------------+ - * + RGB 4:4:4 10bits + ``MEDIA_BUS_FMT_RGB101010_1X30`` + ``V4L2_YCBCR_ENC_DEFAULT`` + + * | RGB 4:4:4 10bits | ``MEDIA_BUS_FMT_RGB101010_1X30`` | ``V4L2_YCBCR_ENC_DEFAULT`` | * +----------------------+----------------------------------+------------------------------+ - * + RGB 4:4:4 12bits + ``MEDIA_BUS_FMT_RGB121212_1X36`` + ``V4L2_YCBCR_ENC_DEFAULT`` + + * | RGB 4:4:4 12bits | ``MEDIA_BUS_FMT_RGB121212_1X36`` | ``V4L2_YCBCR_ENC_DEFAULT`` | * +----------------------+----------------------------------+------------------------------+ - * + RGB 4:4:4 16bits + ``MEDIA_BUS_FMT_RGB161616_1X48`` + ``V4L2_YCBCR_ENC_DEFAULT`` + + * | RGB 4:4:4 16bits | ``MEDIA_BUS_FMT_RGB161616_1X48`` | ``V4L2_YCBCR_ENC_DEFAULT`` | * +----------------------+----------------------------------+------------------------------+ - * + YCbCr 4:4:4 8bit + ``MEDIA_BUS_FMT_YUV8_1X24`` + ``V4L2_YCBCR_ENC_601`` + - * + + + or ``V4L2_YCBCR_ENC_709`` + - * + + + or ``V4L2_YCBCR_ENC_XV601`` + - * + + + or ``V4L2_YCBCR_ENC_XV709`` + + * | YCbCr 4:4:4 8bit | ``MEDIA_BUS_FMT_YUV8_1X24`` | ``V4L2_YCBCR_ENC_601`` | + * | | | or ``V4L2_YCBCR_ENC_709`` | + * | | | or ``V4L2_YCBCR_ENC_XV601`` | + * | | | or ``V4L2_YCBCR_ENC_XV709`` | * +----------------------+----------------------------------+------------------------------+ - * + YCbCr 4:4:4 10bits + ``MEDIA_BUS_FMT_YUV10_1X30`` + ``V4L2_YCBCR_ENC_601`` + - * + + + or ``V4L2_YCBCR_ENC_709`` + - * + + + or ``V4L2_YCBCR_ENC_XV601`` + - * + + + or ``V4L2_YCBCR_ENC_XV709`` + + * | YCbCr 4:4:4 10bits | ``MEDIA_BUS_FMT_YUV10_1X30`` | ``V4L2_YCBCR_ENC_601`` | + * | | | or ``V4L2_YCBCR_ENC_709`` | + * | | | or ``V4L2_YCBCR_ENC_XV601`` | + * | | | or ``V4L2_YCBCR_ENC_XV709`` | * +----------------------+----------------------------------+------------------------------+ - * + YCbCr 4:4:4 12bits + ``MEDIA_BUS_FMT_YUV12_1X36`` + ``V4L2_YCBCR_ENC_601`` + - * + + + or ``V4L2_YCBCR_ENC_709`` + - * + + + or ``V4L2_YCBCR_ENC_XV601`` + - * + + + or ``V4L2_YCBCR_ENC_XV709`` + + * | YCbCr 4:4:4 12bits | ``MEDIA_BUS_FMT_YUV12_1X36`` | ``V4L2_YCBCR_ENC_601`` | + * | | | or ``V4L2_YCBCR_ENC_709`` | + * | | | or ``V4L2_YCBCR_ENC_XV601`` | + * | | | or ``V4L2_YCBCR_ENC_XV709`` | * +----------------------+----------------------------------+------------------------------+ - * + YCbCr 4:4:4 16bits + ``MEDIA_BUS_FMT_YUV16_1X48`` + ``V4L2_YCBCR_ENC_601`` + - * + + + or ``V4L2_YCBCR_ENC_709`` + - * + + + or ``V4L2_YCBCR_ENC_XV601`` + - * + + + or ``V4L2_YCBCR_ENC_XV709`` + + * | YCbCr 4:4:4 16bits | ``MEDIA_BUS_FMT_YUV16_1X48`` | ``V4L2_YCBCR_ENC_601`` | + * | | | or ``V4L2_YCBCR_ENC_709`` | + * | | | or ``V4L2_YCBCR_ENC_XV601`` | + * | | | or ``V4L2_YCBCR_ENC_XV709`` | * +----------------------+----------------------------------+------------------------------+ - * + YCbCr 4:2:2 8bit + ``MEDIA_BUS_FMT_UYVY8_1X16`` + ``V4L2_YCBCR_ENC_601`` + - * + + + or ``V4L2_YCBCR_ENC_709`` + + * | YCbCr 4:2:2 8bit | ``MEDIA_BUS_FMT_UYVY8_1X16`` | ``V4L2_YCBCR_ENC_601`` | + * | | | or ``V4L2_YCBCR_ENC_709`` | * +----------------------+----------------------------------+------------------------------+ - * + YCbCr 4:2:2 10bits + ``MEDIA_BUS_FMT_UYVY10_1X20`` + ``V4L2_YCBCR_ENC_601`` + - * + + + or ``V4L2_YCBCR_ENC_709`` + + * | YCbCr 4:2:2 10bits | ``MEDIA_BUS_FMT_UYVY10_1X20`` | ``V4L2_YCBCR_ENC_601`` | + * | | | or ``V4L2_YCBCR_ENC_709`` | * +----------------------+----------------------------------+------------------------------+ - * + YCbCr 4:2:2 12bits + ``MEDIA_BUS_FMT_UYVY12_1X24`` + ``V4L2_YCBCR_ENC_601`` + - * + + + or ``V4L2_YCBCR_ENC_709`` + + * | YCbCr 4:2:2 12bits | ``MEDIA_BUS_FMT_UYVY12_1X24`` | ``V4L2_YCBCR_ENC_601`` | + * | | | or ``V4L2_YCBCR_ENC_709`` | * +----------------------+----------------------------------+------------------------------+ - * + YCbCr 4:2:0 8bit + ``MEDIA_BUS_FMT_UYYVYY8_0_5X24`` + ``V4L2_YCBCR_ENC_601`` + - * + + + or ``V4L2_YCBCR_ENC_709`` + + * | YCbCr 4:2:0 8bit | ``MEDIA_BUS_FMT_UYYVYY8_0_5X24`` | ``V4L2_YCBCR_ENC_601`` | + * | | | or ``V4L2_YCBCR_ENC_709`` | * +----------------------+----------------------------------+------------------------------+ - * + YCbCr 4:2:0 10bits + ``MEDIA_BUS_FMT_UYYVYY10_0_5X30``+ ``V4L2_YCBCR_ENC_601`` + - * + + + or ``V4L2_YCBCR_ENC_709`` + + * | YCbCr 4:2:0 10bits | ``MEDIA_BUS_FMT_UYYVYY10_0_5X30``| ``V4L2_YCBCR_ENC_601`` | + * | | | or ``V4L2_YCBCR_ENC_709`` | * +----------------------+----------------------------------+------------------------------+ - * + YCbCr 4:2:0 12bits + ``MEDIA_BUS_FMT_UYYVYY12_0_5X36``+ ``V4L2_YCBCR_ENC_601`` + - * + + + or ``V4L2_YCBCR_ENC_709`` + + * | YCbCr 4:2:0 12bits | ``MEDIA_BUS_FMT_UYYVYY12_0_5X36``| ``V4L2_YCBCR_ENC_601`` | + * | | | or ``V4L2_YCBCR_ENC_709`` | * +----------------------+----------------------------------+------------------------------+ - * + YCbCr 4:2:0 16bits + ``MEDIA_BUS_FMT_UYYVYY16_0_5X48``+ ``V4L2_YCBCR_ENC_601`` + - * + + + or ``V4L2_YCBCR_ENC_709`` + + * | YCbCr 4:2:0 16bits | ``MEDIA_BUS_FMT_UYYVYY16_0_5X48``| ``V4L2_YCBCR_ENC_601`` | + * | | | or ``V4L2_YCBCR_ENC_709`` | * +----------------------+----------------------------------+------------------------------+ */ -- cgit v1.2.3-59-g8ed1b From af18ba48420e39833ccaedfe98b98fdef040c6eb Mon Sep 17 00:00:00 2001 From: Alexander Sverdlin Date: Thu, 22 Jun 2017 13:20:36 +0200 Subject: mtd: spi-nor: Add support for mx66u51235f This chip supports stateless 4-byte opcodes, dual and quad read and uniform 4K-byte erase. Signed-off-by: Alexander Sverdlin Signed-off-by: Cyrille Pitchen --- drivers/mtd/spi-nor/spi-nor.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 040ab5d7ac05..2659bbad5b9a 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -1012,6 +1012,7 @@ static const struct flash_info spi_nor_ids[] = { { "mx25u25635f", INFO(0xc22539, 0, 64 * 1024, 512, SECT_4K | SPI_NOR_4B_OPCODES) }, { "mx25l25655e", INFO(0xc22619, 0, 64 * 1024, 512, 0) }, { "mx66l51235l", INFO(0xc2201a, 0, 64 * 1024, 1024, SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) }, + { "mx66u51235f", INFO(0xc2253a, 0, 64 * 1024, 1024, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ | SPI_NOR_4B_OPCODES) }, { "mx66l1g45g", INFO(0xc2201b, 0, 64 * 1024, 2048, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) }, { "mx66l1g55g", INFO(0xc2261b, 0, 64 * 1024, 2048, SPI_NOR_QUAD_READ) }, -- cgit v1.2.3-59-g8ed1b From d8b494a32889eae6eebb71bb4de3e14025026fe5 Mon Sep 17 00:00:00 2001 From: Harry Chou Date: Fri, 23 Jun 2017 03:58:11 +0800 Subject: mtd: spi-nor: Add support for Spansion S25FL064L It's an 8 MiB flash with 4 KiB erase sectors. Signed-off-by: Harry Chou Signed-off-by: Cyrille Pitchen --- drivers/mtd/spi-nor/spi-nor.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 2659bbad5b9a..1413828ff1fb 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -1064,6 +1064,7 @@ static const struct flash_info spi_nor_ids[] = { { "s25fl164k", INFO(0x014017, 0, 64 * 1024, 128, SECT_4K) }, { "s25fl204k", INFO(0x014013, 0, 64 * 1024, 8, SECT_4K | SPI_NOR_DUAL_READ) }, { "s25fl208k", INFO(0x014014, 0, 64 * 1024, 16, SECT_4K | SPI_NOR_DUAL_READ) }, + { "s25fl064l", INFO(0x016017, 0, 64 * 1024, 128, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ | SPI_NOR_4B_OPCODES) }, /* SST -- large erase sizes are "overlays", "sectors" are 4K */ { "sst25vf040b", INFO(0xbf258d, 0, 64 * 1024, 8, SECT_4K | SST_WRITE) }, -- cgit v1.2.3-59-g8ed1b From 3fde00a014ed1b0716a1d73fdebd96188e2ff6fe Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 26 Jun 2017 14:15:02 -0700 Subject: dt-bindings: Document the Broadcom STB wake-up timer node Document the binding for the Broadcom STB SoCs wake-up timer node allowing the system to generate alarms and exit low power states. Acked-by: Rob Herring Signed-off-by: Florian Fainelli Signed-off-by: Alexandre Belloni --- .../bindings/rtc/brcm,brcmstb-waketimer.txt | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) create mode 100644 Documentation/devicetree/bindings/rtc/brcm,brcmstb-waketimer.txt diff --git a/Documentation/devicetree/bindings/rtc/brcm,brcmstb-waketimer.txt b/Documentation/devicetree/bindings/rtc/brcm,brcmstb-waketimer.txt new file mode 100644 index 000000000000..1d990bcc0baf --- /dev/null +++ b/Documentation/devicetree/bindings/rtc/brcm,brcmstb-waketimer.txt @@ -0,0 +1,22 @@ +Broadcom STB wake-up Timer + +The Broadcom STB wake-up timer provides a 27Mhz resolution timer, with the +ability to wake up the system from low-power suspend/standby modes. + +Required properties: +- compatible : should contain "brcm,brcmstb-waketimer" +- reg : the register start and length for the WKTMR block +- interrupts : The TIMER interrupt +- interrupt-parent: The phandle to the Always-On (AON) Power Management (PM) L2 + interrupt controller node +- clocks : The phandle to the UPG fixed clock (27Mhz domain) + +Example: + +waketimer@f0411580 { + compatible = "brcm,brcmstb-waketimer"; + reg = <0xf0411580 0x14>; + interrupts = <0x3>; + interrupt-parent = <&aon_pm_l2_intc>; + clocks = <&upg_fixed>; +}; -- cgit v1.2.3-59-g8ed1b From 295a0d0b55269fce2290a7aebfcc8c2525866c33 Mon Sep 17 00:00:00 2001 From: Xiong Zhang Date: Tue, 20 Jun 2017 11:37:22 +0800 Subject: drm/i915/gvt: Set initial PORT_CLK_SEL vreg for BDW On BDW, when host physical screen and guest virtual screen aren't on the same DDI port, guest i915 driver prints the following error and stop running. [ 6.775873] BUG: unable to handle kernel NULL pointer dereference at 0000000000000068 [ 6.775928] IP: intel_ddi_clock_get+0x81/0x430 [i915] [ 6.776206] Call Trace: [ 6.776233] ? vgpu_read32+0x4f/0x100 [i915] [ 6.776264] intel_ddi_get_config+0x11c/0x230 [i915] [ 6.776298] intel_modeset_setup_hw_state+0x313/0xd40 [i915] [ 6.776334] intel_modeset_init+0xe49/0x18d0 [i915] [ 6.776368] ? vgpu_write32+0x53/0x100 [i915] [ 6.776731] ? intel_i2c_reset+0x42/0x50 [i915] [ 6.777085] ? intel_setup_gmbus+0x32a/0x350 [i915] [ 6.777427] i915_driver_load+0xabc/0x14d0 [i915] [ 6.777768] i915_pci_probe+0x4f/0x70 [i915] The null pointer is guest intel_crtc_state->shared_dpll which is setted in haswell_get_ddi_pll(). When guest and host screen are on different DDI port, host driver won't set PORT_CLK_SET(guest_port), so haswell_get_ddi_pll() will return null and don't set pipe_config->shared_dpll, once the following program refernce this structure, it will print the above error. This patch set the initial val of guest PORT_CLK_SEL(guest_port) to LCPLL_810. And guest i915 driver will reset this value according to guest screen mode. Signed-off-by: Xiong Zhang Signed-off-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/display.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c index e0261fcc5b50..818e94907c3b 100644 --- a/drivers/gpu/drm/i915/gvt/display.c +++ b/drivers/gpu/drm/i915/gvt/display.c @@ -197,6 +197,12 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST | (PORT_B << TRANS_DDI_PORT_SHIFT) | TRANS_DDI_FUNC_ENABLE); + if (IS_BROADWELL(dev_priv)) { + vgpu_vreg(vgpu, PORT_CLK_SEL(PORT_B)) &= + ~PORT_CLK_SEL_MASK; + vgpu_vreg(vgpu, PORT_CLK_SEL(PORT_B)) |= + PORT_CLK_SEL_LCPLL_810; + } vgpu_vreg(vgpu, DDI_BUF_CTL(PORT_B)) |= DDI_BUF_CTL_ENABLE; vgpu_vreg(vgpu, DDI_BUF_CTL(PORT_B)) &= ~DDI_BUF_IS_IDLE; vgpu_vreg(vgpu, SDEISR) |= SDE_PORTB_HOTPLUG_CPT; @@ -211,6 +217,12 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST | (PORT_C << TRANS_DDI_PORT_SHIFT) | TRANS_DDI_FUNC_ENABLE); + if (IS_BROADWELL(dev_priv)) { + vgpu_vreg(vgpu, PORT_CLK_SEL(PORT_C)) &= + ~PORT_CLK_SEL_MASK; + vgpu_vreg(vgpu, PORT_CLK_SEL(PORT_C)) |= + PORT_CLK_SEL_LCPLL_810; + } vgpu_vreg(vgpu, DDI_BUF_CTL(PORT_C)) |= DDI_BUF_CTL_ENABLE; vgpu_vreg(vgpu, DDI_BUF_CTL(PORT_C)) &= ~DDI_BUF_IS_IDLE; vgpu_vreg(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDIC_DETECTED; @@ -225,6 +237,12 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) (TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST | (PORT_D << TRANS_DDI_PORT_SHIFT) | TRANS_DDI_FUNC_ENABLE); + if (IS_BROADWELL(dev_priv)) { + vgpu_vreg(vgpu, PORT_CLK_SEL(PORT_D)) &= + ~PORT_CLK_SEL_MASK; + vgpu_vreg(vgpu, PORT_CLK_SEL(PORT_D)) |= + PORT_CLK_SEL_LCPLL_810; + } vgpu_vreg(vgpu, DDI_BUF_CTL(PORT_D)) |= DDI_BUF_CTL_ENABLE; vgpu_vreg(vgpu, DDI_BUF_CTL(PORT_D)) &= ~DDI_BUF_IS_IDLE; vgpu_vreg(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDID_DETECTED; -- cgit v1.2.3-59-g8ed1b From 75e64ff2c2f5ce1ae5b47b2f372fe5b9dc99f5a9 Mon Sep 17 00:00:00 2001 From: Xiong Zhang Date: Wed, 28 Jun 2017 02:03:16 +0800 Subject: drm/i915/gvt: Don't read ADPA_CRT_HOTPLUG_MONITOR from host When host connects a crt screen, linux guest will detect two screens: crt and dp. This is wrong as linux guest has only one dp. In order to avoid guest get host crt screen, we should set ADPA_CRT_HOTPLUG_MONITOR to none. But MMIO_RO(PCH_ADPA) prevent from that. So MMIO_DH should be used instead of MMIO_RO. v2: Clear its staus to none at initialize, so guest don't get host crt.(Zhangyu) v3: SKL doesn't have this register, limit it to pre_skl.(xiong) Signed-off-by: Xiong Zhang Signed-off-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/display.c | 4 ++++ drivers/gpu/drm/i915/gvt/handlers.c | 2 +- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c index 818e94907c3b..2deb05f618fb 100644 --- a/drivers/gpu/drm/i915/gvt/display.c +++ b/drivers/gpu/drm/i915/gvt/display.c @@ -262,6 +262,10 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) vgpu_vreg(vgpu, DDI_BUF_CTL(PORT_A)) |= DDI_INIT_DISPLAY_DETECTED; } + + /* Clear host CRT status, so guest couldn't detect this host CRT. */ + if (IS_BROADWELL(dev_priv)) + vgpu_vreg(vgpu, PCH_ADPA) &= ~ADPA_CRT_HOTPLUG_MONITOR_MASK; } static void clean_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num) diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 0ffd69654592..437a35f41b62 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -1905,7 +1905,7 @@ static int init_generic_mmio_info(struct intel_gvt *gvt) MMIO_F(_PCH_DPD_AUX_CH_CTL, 6 * 4, 0, 0, 0, D_PRE_SKL, NULL, dp_aux_ch_ctl_mmio_write); - MMIO_RO(PCH_ADPA, D_ALL, 0, ADPA_CRT_HOTPLUG_MONITOR_MASK, NULL, pch_adpa_mmio_write); + MMIO_DH(PCH_ADPA, D_PRE_SKL, NULL, pch_adpa_mmio_write); MMIO_DH(_PCH_TRANSACONF, D_ALL, NULL, transconf_mmio_write); MMIO_DH(_PCH_TRANSBCONF, D_ALL, NULL, transconf_mmio_write); -- cgit v1.2.3-59-g8ed1b From 170748db2deb2dedcb405ae091dbc74a478842e5 Mon Sep 17 00:00:00 2001 From: Bibby Hsieh Date: Tue, 24 Jan 2017 12:40:58 +0800 Subject: drm/mediatek: Support UYVY and YUYV format for overlay MT8173 overlay can support UYVY and YUYV format, we add the format in DRM driver. Signed-off-by: Bibby Hsieh Reviewed-by: Daniel Kurtz Signed-off-by: CK Hu --- drivers/gpu/drm/mediatek/mtk_disp_ovl.c | 7 +++++++ drivers/gpu/drm/mediatek/mtk_drm_plane.c | 2 ++ 2 files changed, 9 insertions(+) diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c index a14d7d64d7b1..35bc5babdbf7 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c @@ -42,9 +42,12 @@ #define OVL_RDMA_MEM_GMC 0x40402020 #define OVL_CON_BYTE_SWAP BIT(24) +#define OVL_CON_MTX_YUV_TO_RGB (6 << 16) #define OVL_CON_CLRFMT_RGB (1 << 12) #define OVL_CON_CLRFMT_RGBA8888 (2 << 12) #define OVL_CON_CLRFMT_ARGB8888 (3 << 12) +#define OVL_CON_CLRFMT_UYVY (4 << 12) +#define OVL_CON_CLRFMT_YUYV (5 << 12) #define OVL_CON_CLRFMT_RGB565(ovl) ((ovl)->data->fmt_rgb565_is_0 ? \ 0 : OVL_CON_CLRFMT_RGB) #define OVL_CON_CLRFMT_RGB888(ovl) ((ovl)->data->fmt_rgb565_is_0 ? \ @@ -176,6 +179,10 @@ static unsigned int ovl_fmt_convert(struct mtk_disp_ovl *ovl, unsigned int fmt) case DRM_FORMAT_XBGR8888: case DRM_FORMAT_ABGR8888: return OVL_CON_CLRFMT_RGBA8888 | OVL_CON_BYTE_SWAP; + case DRM_FORMAT_UYVY: + return OVL_CON_CLRFMT_UYVY | OVL_CON_MTX_YUV_TO_RGB; + case DRM_FORMAT_YUYV: + return OVL_CON_CLRFMT_YUYV | OVL_CON_MTX_YUV_TO_RGB; } } diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c index e405e89ed5e5..1a59b9ab4aa8 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c @@ -28,6 +28,8 @@ static const u32 formats[] = { DRM_FORMAT_XRGB8888, DRM_FORMAT_ARGB8888, DRM_FORMAT_RGB565, + DRM_FORMAT_UYVY, + DRM_FORMAT_YUYV, }; static void mtk_plane_reset(struct drm_plane *plane) -- cgit v1.2.3-59-g8ed1b From 446b8c542f8551b368dab1ff3539beb3aedb5928 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Fri, 17 Mar 2017 18:00:23 +0100 Subject: drm/mediatek: use platform_register_drivers Use platform_register_drivers instead of open coding the iteration over component platform drivers in the mtk_drm_drv and mtk_hdmi modules. Signed-off-by: Philipp Zabel Signed-off-by: CK Hu --- drivers/gpu/drm/mediatek/mtk_drm_drv.c | 27 ++++----------------------- drivers/gpu/drm/mediatek/mtk_hdmi.c | 27 ++++----------------------- 2 files changed, 8 insertions(+), 46 deletions(-) diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index f6c8ec4c7dbc..3754c3ffdcf2 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -576,33 +576,14 @@ static struct platform_driver * const mtk_drm_drivers[] = { static int __init mtk_drm_init(void) { - int ret; - int i; - - for (i = 0; i < ARRAY_SIZE(mtk_drm_drivers); i++) { - ret = platform_driver_register(mtk_drm_drivers[i]); - if (ret < 0) { - pr_err("Failed to register %s driver: %d\n", - mtk_drm_drivers[i]->driver.name, ret); - goto err; - } - } - - return 0; - -err: - while (--i >= 0) - platform_driver_unregister(mtk_drm_drivers[i]); - - return ret; + return platform_register_drivers(mtk_drm_drivers, + ARRAY_SIZE(mtk_drm_drivers)); } static void __exit mtk_drm_exit(void) { - int i; - - for (i = ARRAY_SIZE(mtk_drm_drivers) - 1; i >= 0; i--) - platform_driver_unregister(mtk_drm_drivers[i]); + platform_unregister_drivers(mtk_drm_drivers, + ARRAY_SIZE(mtk_drm_drivers)); } module_init(mtk_drm_init); diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c index 0a4ffd724146..71eb4fbbfc85 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c @@ -1778,33 +1778,14 @@ static struct platform_driver * const mtk_hdmi_drivers[] = { static int __init mtk_hdmitx_init(void) { - int ret; - int i; - - for (i = 0; i < ARRAY_SIZE(mtk_hdmi_drivers); i++) { - ret = platform_driver_register(mtk_hdmi_drivers[i]); - if (ret < 0) { - pr_err("Failed to register %s driver: %d\n", - mtk_hdmi_drivers[i]->driver.name, ret); - goto err; - } - } - - return 0; - -err: - while (--i >= 0) - platform_driver_unregister(mtk_hdmi_drivers[i]); - - return ret; + return platform_register_drivers(mtk_hdmi_drivers, + ARRAY_SIZE(mtk_hdmi_drivers)); } static void __exit mtk_hdmitx_exit(void) { - int i; - - for (i = ARRAY_SIZE(mtk_hdmi_drivers) - 1; i >= 0; i--) - platform_driver_unregister(mtk_hdmi_drivers[i]); + platform_unregister_drivers(mtk_hdmi_drivers, + ARRAY_SIZE(mtk_hdmi_drivers)); } module_init(mtk_hdmitx_init); -- cgit v1.2.3-59-g8ed1b From afd89636f1846ec2c340de894dac103cd336fcee Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 11 Apr 2017 14:44:19 +0100 Subject: drm/mediatek: re-phrase DRM_INFO error message The current message contains a spelling mistake and is not easily parsable. Re-phrase it to be more understandable. Signed-off-by: Colin Ian King Signed-off-by: CK Hu --- drivers/gpu/drm/mediatek/mtk_dsi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index b5cc6e12334c..97253c8f813b 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -930,7 +930,7 @@ static u32 mtk_dsi_recv_cnt(u8 type, u8 *read_data) DRM_INFO("type is 0x02, try again\n"); break; default: - DRM_INFO("type(0x%x) cannot be non-recognite\n", type); + DRM_INFO("type(0x%x) not recognized\n", type); break; } -- cgit v1.2.3-59-g8ed1b From 4a3bfb5c24306aa129c0de32e5d1ffb553a60a7c Mon Sep 17 00:00:00 2001 From: Christophe Jaillet Date: Fri, 9 Jun 2017 21:27:12 +0200 Subject: drm/mediatek: check for memory allocation failure If 'devm_kmalloc_array' returns NULL, we should return -ENOMEM as already done a few lines above instead of deferencing a NULL pointer a few lines below. Signed-off-by: Christophe JAILLET Reviewed-by: Matthias Brugger Signed-off-by: CK Hu --- drivers/gpu/drm/mediatek/mtk_drm_crtc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index 6582e1f56d37..cb32c9369f3a 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -559,6 +559,8 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev, mtk_crtc->ddp_comp = devm_kmalloc_array(dev, mtk_crtc->ddp_comp_nr, sizeof(*mtk_crtc->ddp_comp), GFP_KERNEL); + if (!mtk_crtc->ddp_comp) + return -ENOMEM; mtk_crtc->mutex = mtk_disp_mutex_get(priv->mutex_dev, pipe); if (IS_ERR(mtk_crtc->mutex)) { -- cgit v1.2.3-59-g8ed1b From 5ac5895a84d92bd2b3db490f8ee242ccb4d77e96 Mon Sep 17 00:00:00 2001 From: "yt.shen@mediatek.com" Date: Fri, 16 Jun 2017 22:02:16 +0800 Subject: drm/mediatek: separate color module to fixup error memory reallocation Previous patch (c5f228ef6c drm/mediatek: add *driver_data for different hardware settings) calls devm_kfree() and then devm_kzalloc() to reallocate color module data structure. But this reallocation cannnot guarantee the new address is unchanged, but the caller will use the old address, which is wrong. Fix it by separate color module from general components, this patch separate color module to independent files, like mtk_disp_ovl.c and mtk_disp_rdma.c do Fixes: c5f228ef6ccd ("drm/mediatek: add *driver_data for different hardware settings") Signed-off-by: YT Shen Tested-by: Bibby Hsieh Signed-off-by: CK Hu --- drivers/gpu/drm/mediatek/Makefile | 3 +- drivers/gpu/drm/mediatek/mtk_disp_color.c | 176 ++++++++++++++++++++++++++++ drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c | 80 +------------ drivers/gpu/drm/mediatek/mtk_drm_drv.c | 6 +- drivers/gpu/drm/mediatek/mtk_drm_drv.h | 1 + 5 files changed, 185 insertions(+), 81 deletions(-) create mode 100644 drivers/gpu/drm/mediatek/mtk_disp_color.c diff --git a/drivers/gpu/drm/mediatek/Makefile b/drivers/gpu/drm/mediatek/Makefile index bf2e5be1ab30..e37b55a23a65 100644 --- a/drivers/gpu/drm/mediatek/Makefile +++ b/drivers/gpu/drm/mediatek/Makefile @@ -1,4 +1,5 @@ -mediatek-drm-y := mtk_disp_ovl.o \ +mediatek-drm-y := mtk_disp_color.o \ + mtk_disp_ovl.o \ mtk_disp_rdma.o \ mtk_drm_crtc.o \ mtk_drm_ddp.o \ diff --git a/drivers/gpu/drm/mediatek/mtk_disp_color.c b/drivers/gpu/drm/mediatek/mtk_disp_color.c new file mode 100644 index 000000000000..ef79a6d55646 --- /dev/null +++ b/drivers/gpu/drm/mediatek/mtk_disp_color.c @@ -0,0 +1,176 @@ +/* + * Copyright (c) 2017 MediaTek Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include +#include +#include +#include +#include +#include + +#include "mtk_drm_crtc.h" +#include "mtk_drm_ddp_comp.h" + +#define DISP_COLOR_CFG_MAIN 0x0400 +#define DISP_COLOR_START_MT2701 0x0f00 +#define DISP_COLOR_START_MT8173 0x0c00 +#define DISP_COLOR_START(comp) ((comp)->data->color_offset) +#define DISP_COLOR_WIDTH(comp) (DISP_COLOR_START(comp) + 0x50) +#define DISP_COLOR_HEIGHT(comp) (DISP_COLOR_START(comp) + 0x54) + +#define COLOR_BYPASS_ALL BIT(7) +#define COLOR_SEQ_SEL BIT(13) + +struct mtk_disp_color_data { + unsigned int color_offset; +}; + +/** + * struct mtk_disp_color - DISP_COLOR driver structure + * @ddp_comp - structure containing type enum and hardware resources + * @crtc - associated crtc to report irq events to + */ +struct mtk_disp_color { + struct mtk_ddp_comp ddp_comp; + struct drm_crtc *crtc; + const struct mtk_disp_color_data *data; +}; + +static inline struct mtk_disp_color *comp_to_color(struct mtk_ddp_comp *comp) +{ + return container_of(comp, struct mtk_disp_color, ddp_comp); +} + +static void mtk_color_config(struct mtk_ddp_comp *comp, unsigned int w, + unsigned int h, unsigned int vrefresh, + unsigned int bpc) +{ + struct mtk_disp_color *color = comp_to_color(comp); + + writel(w, comp->regs + DISP_COLOR_WIDTH(color)); + writel(h, comp->regs + DISP_COLOR_HEIGHT(color)); +} + +static void mtk_color_start(struct mtk_ddp_comp *comp) +{ + struct mtk_disp_color *color = comp_to_color(comp); + + writel(COLOR_BYPASS_ALL | COLOR_SEQ_SEL, + comp->regs + DISP_COLOR_CFG_MAIN); + writel(0x1, comp->regs + DISP_COLOR_START(color)); +} + +static const struct mtk_ddp_comp_funcs mtk_disp_color_funcs = { + .config = mtk_color_config, + .start = mtk_color_start, +}; + +static int mtk_disp_color_bind(struct device *dev, struct device *master, + void *data) +{ + struct mtk_disp_color *priv = dev_get_drvdata(dev); + struct drm_device *drm_dev = data; + int ret; + + ret = mtk_ddp_comp_register(drm_dev, &priv->ddp_comp); + if (ret < 0) { + dev_err(dev, "Failed to register component %s: %d\n", + dev->of_node->full_name, ret); + return ret; + } + + return 0; +} + +static void mtk_disp_color_unbind(struct device *dev, struct device *master, + void *data) +{ + struct mtk_disp_color *priv = dev_get_drvdata(dev); + struct drm_device *drm_dev = data; + + mtk_ddp_comp_unregister(drm_dev, &priv->ddp_comp); +} + +static const struct component_ops mtk_disp_color_component_ops = { + .bind = mtk_disp_color_bind, + .unbind = mtk_disp_color_unbind, +}; + +static int mtk_disp_color_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct mtk_disp_color *priv; + int comp_id; + int ret; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + comp_id = mtk_ddp_comp_get_id(dev->of_node, MTK_DISP_COLOR); + if (comp_id < 0) { + dev_err(dev, "Failed to identify by alias: %d\n", comp_id); + return comp_id; + } + + ret = mtk_ddp_comp_init(dev, dev->of_node, &priv->ddp_comp, comp_id, + &mtk_disp_color_funcs); + if (ret) { + dev_err(dev, "Failed to initialize component: %d\n", ret); + return ret; + } + + priv->data = of_device_get_match_data(dev); + + platform_set_drvdata(pdev, priv); + + ret = component_add(dev, &mtk_disp_color_component_ops); + if (ret) + dev_err(dev, "Failed to add component: %d\n", ret); + + return ret; +} + +static int mtk_disp_color_remove(struct platform_device *pdev) +{ + component_del(&pdev->dev, &mtk_disp_color_component_ops); + + return 0; +} + +static const struct mtk_disp_color_data mt2701_color_driver_data = { + .color_offset = DISP_COLOR_START_MT2701, +}; + +static const struct mtk_disp_color_data mt8173_color_driver_data = { + .color_offset = DISP_COLOR_START_MT8173, +}; + +static const struct of_device_id mtk_disp_color_driver_dt_match[] = { + { .compatible = "mediatek,mt2701-disp-color", + .data = &mt2701_color_driver_data}, + { .compatible = "mediatek,mt8173-disp-color", + .data = &mt8173_color_driver_data}, + {}, +}; +MODULE_DEVICE_TABLE(of, mtk_disp_color_driver_dt_match); + +struct platform_driver mtk_disp_color_driver = { + .probe = mtk_disp_color_probe, + .remove = mtk_disp_color_remove, + .driver = { + .name = "mediatek-disp-color", + .owner = THIS_MODULE, + .of_match_table = mtk_disp_color_driver_dt_match, + }, +}; diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c index 8b52416b6e41..07d7ea2268ef 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c @@ -38,13 +38,6 @@ #define DISP_REG_UFO_START 0x0000 -#define DISP_COLOR_CFG_MAIN 0x0400 -#define DISP_COLOR_START_MT2701 0x0f00 -#define DISP_COLOR_START_MT8173 0x0c00 -#define DISP_COLOR_START(comp) ((comp)->data->color_offset) -#define DISP_COLOR_WIDTH(comp) (DISP_COLOR_START(comp) + 0x50) -#define DISP_COLOR_HEIGHT(comp) (DISP_COLOR_START(comp) + 0x54) - #define DISP_AAL_EN 0x0000 #define DISP_AAL_SIZE 0x0030 @@ -55,9 +48,6 @@ #define LUT_10BIT_MASK 0x03ff -#define COLOR_BYPASS_ALL BIT(7) -#define COLOR_SEQ_SEL BIT(13) - #define OD_RELAYMODE BIT(0) #define UFO_BYPASS BIT(2) @@ -82,20 +72,6 @@ #define DITHER_ADD_LSHIFT_G(x) (((x) & 0x7) << 4) #define DITHER_ADD_RSHIFT_G(x) (((x) & 0x7) << 0) -struct mtk_disp_color_data { - unsigned int color_offset; -}; - -struct mtk_disp_color { - struct mtk_ddp_comp ddp_comp; - const struct mtk_disp_color_data *data; -}; - -static inline struct mtk_disp_color *comp_to_color(struct mtk_ddp_comp *comp) -{ - return container_of(comp, struct mtk_disp_color, ddp_comp); -} - void mtk_dither_set(struct mtk_ddp_comp *comp, unsigned int bpc, unsigned int CFG) { @@ -119,25 +95,6 @@ void mtk_dither_set(struct mtk_ddp_comp *comp, unsigned int bpc, } } -static void mtk_color_config(struct mtk_ddp_comp *comp, unsigned int w, - unsigned int h, unsigned int vrefresh, - unsigned int bpc) -{ - struct mtk_disp_color *color = comp_to_color(comp); - - writel(w, comp->regs + DISP_COLOR_WIDTH(color)); - writel(h, comp->regs + DISP_COLOR_HEIGHT(color)); -} - -static void mtk_color_start(struct mtk_ddp_comp *comp) -{ - struct mtk_disp_color *color = comp_to_color(comp); - - writel(COLOR_BYPASS_ALL | COLOR_SEQ_SEL, - comp->regs + DISP_COLOR_CFG_MAIN); - writel(0x1, comp->regs + DISP_COLOR_START(color)); -} - static void mtk_od_config(struct mtk_ddp_comp *comp, unsigned int w, unsigned int h, unsigned int vrefresh, unsigned int bpc) @@ -229,11 +186,6 @@ static const struct mtk_ddp_comp_funcs ddp_gamma = { .stop = mtk_gamma_stop, }; -static const struct mtk_ddp_comp_funcs ddp_color = { - .config = mtk_color_config, - .start = mtk_color_start, -}; - static const struct mtk_ddp_comp_funcs ddp_od = { .config = mtk_od_config, .start = mtk_od_start, @@ -268,8 +220,8 @@ struct mtk_ddp_comp_match { static const struct mtk_ddp_comp_match mtk_ddp_matches[DDP_COMPONENT_ID_MAX] = { [DDP_COMPONENT_AAL] = { MTK_DISP_AAL, 0, &ddp_aal }, [DDP_COMPONENT_BLS] = { MTK_DISP_BLS, 0, NULL }, - [DDP_COMPONENT_COLOR0] = { MTK_DISP_COLOR, 0, &ddp_color }, - [DDP_COMPONENT_COLOR1] = { MTK_DISP_COLOR, 1, &ddp_color }, + [DDP_COMPONENT_COLOR0] = { MTK_DISP_COLOR, 0, NULL }, + [DDP_COMPONENT_COLOR1] = { MTK_DISP_COLOR, 1, NULL }, [DDP_COMPONENT_DPI0] = { MTK_DPI, 0, NULL }, [DDP_COMPONENT_DSI0] = { MTK_DSI, 0, NULL }, [DDP_COMPONENT_DSI1] = { MTK_DSI, 1, NULL }, @@ -286,22 +238,6 @@ static const struct mtk_ddp_comp_match mtk_ddp_matches[DDP_COMPONENT_ID_MAX] = { [DDP_COMPONENT_WDMA1] = { MTK_DISP_WDMA, 1, NULL }, }; -static const struct mtk_disp_color_data mt2701_color_driver_data = { - .color_offset = DISP_COLOR_START_MT2701, -}; - -static const struct mtk_disp_color_data mt8173_color_driver_data = { - .color_offset = DISP_COLOR_START_MT8173, -}; - -static const struct of_device_id mtk_disp_color_driver_dt_match[] = { - { .compatible = "mediatek,mt2701-disp-color", - .data = &mt2701_color_driver_data}, - { .compatible = "mediatek,mt8173-disp-color", - .data = &mt8173_color_driver_data}, - {}, -}; - int mtk_ddp_comp_get_id(struct device_node *node, enum mtk_ddp_comp_type comp_type) { @@ -324,23 +260,11 @@ int mtk_ddp_comp_init(struct device *dev, struct device_node *node, enum mtk_ddp_comp_type type; struct device_node *larb_node; struct platform_device *larb_pdev; - const struct of_device_id *match; - struct mtk_disp_color *color; if (comp_id < 0 || comp_id >= DDP_COMPONENT_ID_MAX) return -EINVAL; type = mtk_ddp_matches[comp_id].type; - if (type == MTK_DISP_COLOR) { - devm_kfree(dev, comp); - color = devm_kzalloc(dev, sizeof(*color), GFP_KERNEL); - if (!color) - return -ENOMEM; - - match = of_match_node(mtk_disp_color_driver_dt_match, node); - color->data = match->data; - comp = &color->ddp_comp; - } comp->id = comp_id; comp->funcs = funcs ?: mtk_ddp_matches[comp_id].funcs; diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index 3754c3ffdcf2..41d2cffe953e 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -439,11 +439,12 @@ static int mtk_drm_probe(struct platform_device *pdev) private->comp_node[comp_id] = of_node_get(node); /* - * Currently only the OVL, RDMA, DSI, and DPI blocks have + * Currently only the COLOR, OVL, RDMA, DSI, and DPI blocks have * separate component platform drivers and initialize their own * DDP component structure. The others are initialized here. */ - if (comp_type == MTK_DISP_OVL || + if (comp_type == MTK_DISP_COLOR || + comp_type == MTK_DISP_OVL || comp_type == MTK_DISP_RDMA || comp_type == MTK_DSI || comp_type == MTK_DPI) { @@ -566,6 +567,7 @@ static struct platform_driver mtk_drm_platform_driver = { static struct platform_driver * const mtk_drm_drivers[] = { &mtk_ddp_driver, + &mtk_disp_color_driver, &mtk_disp_ovl_driver, &mtk_disp_rdma_driver, &mtk_dpi_driver, diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.h b/drivers/gpu/drm/mediatek/mtk_drm_drv.h index aef8747d810b..c3378c452c0a 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.h +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.h @@ -59,6 +59,7 @@ struct mtk_drm_private { }; extern struct platform_driver mtk_ddp_driver; +extern struct platform_driver mtk_disp_color_driver; extern struct platform_driver mtk_disp_ovl_driver; extern struct platform_driver mtk_disp_rdma_driver; extern struct platform_driver mtk_dpi_driver; -- cgit v1.2.3-59-g8ed1b From 12597988319c8943531c7b2183580231b08b7471 Mon Sep 17 00:00:00 2001 From: Matt Redfearn Date: Mon, 15 May 2017 10:46:35 +0100 Subject: MIPS: Sort MIPS Kconfig Alphabetically. Sort the entries in config MIPS alphabetically so as to make entries easier to find. Signed-off-by: Matt Redfearn Cc: James Hogan Cc: linux-mips@linux-mips.org Cc: linux-kernel@vger.kernel.org Patchwork: https://patchwork.linux-mips.org/patch/16068/ Signed-off-by: Ralf Baechle --- arch/mips/Kconfig | 98 +++++++++++++++++++++++++++---------------------------- 1 file changed, 49 insertions(+), 49 deletions(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 2828ecde133d..0b15978c0f88 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -1,75 +1,75 @@ config MIPS bool default y - select ARCH_SUPPORTS_UPROBES + select ARCH_BINFMT_ELF_STATE + select ARCH_CLOCKSOURCE_DATA + select ARCH_DISCARD_MEMBLOCK + select ARCH_HAS_ELF_RANDOMIZE + select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO - select ARCH_USE_CMPXCHG_LOCKREF if 64BIT + select ARCH_SUPPORTS_UPROBES select ARCH_USE_BUILTIN_BSWAP - select HAVE_CONTEXT_TRACKING - select HAVE_GENERIC_DMA_COHERENT - select HAVE_IDE - select HAVE_IRQ_EXIT_ON_IRQ_STACK - select HAVE_OPROFILE - select HAVE_PERF_EVENTS - select PERF_USE_VMALLOC + select ARCH_USE_CMPXCHG_LOCKREF if 64BIT + select ARCH_WANT_IPC_PARSE_VERSION + select BUILDTIME_EXTABLE_SORT + select CLONE_BACKWARDS + select CPU_PM if CPU_IDLE + select GENERIC_ATOMIC64 if !64BIT + select GENERIC_CLOCKEVENTS + select GENERIC_CMOS_UPDATE + select GENERIC_CPU_AUTOPROBE + select GENERIC_IRQ_PROBE + select GENERIC_IRQ_SHOW + select GENERIC_PCI_IOMAP + select GENERIC_SCHED_CLOCK if !CAVIUM_OCTEON_SOC + select GENERIC_SMP_IDLE_THREAD + select GENERIC_TIME_VSYSCALL + select HANDLE_DOMAIN_IRQ + select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS if MMU select HAVE_ARCH_MMAP_RND_COMPAT_BITS if MMU && COMPAT select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK + select HAVE_ARCH_TRANSPARENT_HUGEPAGE if CPU_SUPPORTS_HUGEPAGES && 64BIT select HAVE_CBPF_JIT if !CPU_MICROMIPS - select HAVE_FUNCTION_TRACER + select HAVE_CC_STACKPROTECTOR + select HAVE_CONTEXT_TRACKING + select HAVE_COPY_THREAD_TLS + select HAVE_C_RECORDMCOUNT + select HAVE_DEBUG_KMEMLEAK + select HAVE_DEBUG_STACKOVERFLOW + select HAVE_DMA_API_DEBUG + select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE + select HAVE_EXIT_THREAD select HAVE_FTRACE_MCOUNT_RECORD - select HAVE_C_RECORDMCOUNT select HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FUNCTION_TRACER + select HAVE_GENERIC_DMA_COHERENT + select HAVE_IDE + select HAVE_IRQ_EXIT_ON_IRQ_STACK + select HAVE_IRQ_TIME_ACCOUNTING select HAVE_KPROBES select HAVE_KRETPROBES - select HAVE_SYSCALL_TRACEPOINTS - select HAVE_DEBUG_KMEMLEAK - select HAVE_SYSCALL_TRACEPOINTS - select ARCH_HAS_ELF_RANDOMIZE - select HAVE_ARCH_TRANSPARENT_HUGEPAGE if CPU_SUPPORTS_HUGEPAGES && 64BIT - select RTC_LIB if !MACH_LOONGSON64 - select GENERIC_ATOMIC64 if !64BIT - select HAVE_DMA_CONTIGUOUS - select HAVE_DMA_API_DEBUG - select GENERIC_IRQ_PROBE - select GENERIC_IRQ_SHOW - select GENERIC_PCI_IOMAP - select HAVE_ARCH_JUMP_LABEL - select ARCH_WANT_IPC_PARSE_VERSION - select IRQ_FORCED_THREADING select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP - select ARCH_DISCARD_MEMBLOCK - select GENERIC_SMP_IDLE_THREAD - select BUILDTIME_EXTABLE_SORT - select GENERIC_CPU_AUTOPROBE - select GENERIC_CLOCKEVENTS - select GENERIC_SCHED_CLOCK if !CAVIUM_OCTEON_SOC - select GENERIC_CMOS_UPDATE select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI - select VIRT_TO_BUS - select MODULES_USE_ELF_REL if MODULES + select HAVE_OPROFILE + select HAVE_PERF_EVENTS + select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_SYSCALL_TRACEPOINTS + select HAVE_SYSCALL_TRACEPOINTS + select HAVE_VIRT_CPU_ACCOUNTING_GEN + select IRQ_FORCED_THREADING select MODULES_USE_ELF_RELA if MODULES && 64BIT - select CLONE_BACKWARDS - select HAVE_DEBUG_STACKOVERFLOW - select HAVE_CC_STACKPROTECTOR - select CPU_PM if CPU_IDLE - select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST - select ARCH_BINFMT_ELF_STATE + select MODULES_USE_ELF_REL if MODULES + select PERF_USE_VMALLOC + select RTC_LIB if !MACH_LOONGSON64 select SYSCTL_EXCEPTION_TRACE - select HAVE_VIRT_CPU_ACCOUNTING_GEN - select HAVE_IRQ_TIME_ACCOUNTING - select GENERIC_TIME_VSYSCALL - select ARCH_CLOCKSOURCE_DATA - select HANDLE_DOMAIN_IRQ - select HAVE_EXIT_THREAD - select HAVE_REGS_AND_STACK_ACCESS_API - select HAVE_COPY_THREAD_TLS + select VIRT_TO_BUS menu "Machine selection" -- cgit v1.2.3-59-g8ed1b From 59baa24d8710add3689124fb2a232bac2decae9a Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 8 Jun 2017 18:10:13 +0200 Subject: MIPS: defconfig: Cleanup from old Kconfig options Remove old, dead Kconfig options (in order appearing in this commit): - EXPERIMENTAL is gone since v3.9; - INET_LRO: commit 7bbf3cae65b6 ("ipv4: Remove inet_lro library"); - MTD_CONCAT: commit f53fdebcc3e1 ("mtd: drop MTD_CONCAT from Kconfig entirely"); - MTD_CHAR: commit 660685d9d1b4 ("mtd: merge mtdchar module with mtdcore"); - NETDEV_1000 and NETDEV_10000: commit f860b0522f65 ("drivers/net: Kconfig and Makefile cleanup"); NET_ETHERNET should be replaced with just ETHERNET but that is separate change; - MISC_DEVICES: commit 7c5763b8453a ("drivers: misc: Remove MISC_DEVICES config option"); - HID_SUPPORT: commit 1f41a6a99476 ("HID: Fix the generic Kconfig options"); - BT_L2CAP and BT_SCO: commit f1e91e1640d8 ("Bluetooth: Always compile SCO and L2CAP in Bluetooth Core"); - DEBUG_ERRORS: commit b025a3f836d1 ("ARM: 6876/1: Kconfig.debug: Remove unused CONFIG_DEBUG_ERRORS"); - USB_DEVICE_CLASS: commit 007bab91324e ("USB: remove CONFIG_USB_DEVICE_CLASS"); - RCU_CPU_STALL_DETECTOR: commit a00e0d714fbd ("rcu: Remove conditional compilation for RCU CPU stall warnings"); - IP_NF_QUEUE: commit 3dd6664fac7e ("netfilter: remove unused "config IP_NF_QUEUE""); - IP_NF_TARGET_ULOG: commit d4da843e6fad ("netfilter: kill remnants of ulog targets"); - IP6_NF_QUEUE: commit d16cf20e2f2f ("netfilter: remove ip_queue support"); - IP6_NF_TARGET_LOG: commit 6939c33a757b ("netfilter: merge ipt_LOG and ip6_LOG into xt_LOG"); - USB_LED: commit a335aaf3125c ("usb: misc: remove outdated USB LED driver"); - MMC_UNSAFE_RESUME: commit 2501c9179dff ("mmc: core: Use MMC_UNSAFE_RESUME as default behavior"); - AUTOFS_FS: commit 561c5cf9236a ("staging: Remove autofs3"); - VIDEO_OUTPUT_CONTROL: commit f167a64e9d67 ("video / output: Drop display output class support"); - USB_LIBUSUAL: commit f61870ee6f8c ("usb: remove libusual"); - CRYPTO_ZLIB: 110492183c4b ("crypto: compress - remove unused pcomp interface"); - BLK_DEV_UB: commit 68a5059ecf82 ("block: remove the deprecated ub driver"); Signed-off-by: Krzysztof Kozlowski Cc: Arnd Bergmann Cc: Florian Fainelli Cc: linux-kernel@vger.kernel.org Cc: bcm-kernel-feedback-list@broadcom.com Cc: linux-mips@linux-mips.org Cc: linux-arm-kernel@lists.infradead.org Patchwork: https://patchwork.linux-mips.org/patch/16342/ Signed-off-by: Ralf Baechle --- arch/mips/configs/ar7_defconfig | 6 ------ arch/mips/configs/ath79_defconfig | 2 -- arch/mips/configs/bcm63xx_defconfig | 7 ------- arch/mips/configs/bigsur_defconfig | 4 ---- arch/mips/configs/bmips_be_defconfig | 1 - arch/mips/configs/capcella_defconfig | 4 ---- arch/mips/configs/cavium_octeon_defconfig | 1 - arch/mips/configs/ci20_defconfig | 1 - arch/mips/configs/cobalt_defconfig | 8 -------- arch/mips/configs/decstation_defconfig | 1 - arch/mips/configs/e55_defconfig | 2 -- arch/mips/configs/fuloong2e_defconfig | 11 ----------- arch/mips/configs/gpr_defconfig | 8 -------- arch/mips/configs/ip22_defconfig | 11 ----------- arch/mips/configs/ip27_defconfig | 5 ----- arch/mips/configs/ip28_defconfig | 5 ----- arch/mips/configs/ip32_defconfig | 8 -------- arch/mips/configs/jazz_defconfig | 6 ------ arch/mips/configs/jmr3927_defconfig | 7 ------- arch/mips/configs/lasat_defconfig | 5 ----- arch/mips/configs/lemote2f_defconfig | 12 ------------ arch/mips/configs/loongson3_defconfig | 3 --- arch/mips/configs/malta_kvm_defconfig | 1 - arch/mips/configs/malta_kvm_guest_defconfig | 1 - arch/mips/configs/malta_qemu_32r6_defconfig | 1 - arch/mips/configs/maltaaprp_defconfig | 2 -- arch/mips/configs/maltasmvp_defconfig | 1 - arch/mips/configs/maltasmvp_eva_defconfig | 2 -- arch/mips/configs/maltaup_defconfig | 2 -- arch/mips/configs/markeins_defconfig | 4 ---- arch/mips/configs/mips_paravirt_defconfig | 1 - arch/mips/configs/mpc30x_defconfig | 5 ----- arch/mips/configs/msp71xx_defconfig | 2 -- arch/mips/configs/mtx1_defconfig | 11 ----------- arch/mips/configs/nlm_xlp_defconfig | 5 ----- arch/mips/configs/nlm_xlr_defconfig | 9 --------- arch/mips/configs/pnx8335_stb225_defconfig | 7 ------- arch/mips/configs/qi_lb60_defconfig | 3 --- arch/mips/configs/rb532_defconfig | 6 ------ arch/mips/configs/rbtx49xx_defconfig | 7 ------- arch/mips/configs/rm200_defconfig | 8 -------- arch/mips/configs/rt305x_defconfig | 2 -- arch/mips/configs/sb1250_swarm_defconfig | 1 - arch/mips/configs/tb0219_defconfig | 6 ------ arch/mips/configs/tb0226_defconfig | 7 ------- arch/mips/configs/tb0287_defconfig | 5 ----- arch/mips/configs/workpad_defconfig | 4 ---- 47 files changed, 221 deletions(-) diff --git a/arch/mips/configs/ar7_defconfig b/arch/mips/configs/ar7_defconfig index 320772caf054..92fca3c42eac 100644 --- a/arch/mips/configs/ar7_defconfig +++ b/arch/mips/configs/ar7_defconfig @@ -3,7 +3,6 @@ CONFIG_HIGH_RES_TIMERS=y CONFIG_HZ_100=y CONFIG_KEXEC=y # CONFIG_SECCOMP is not set -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_KERNEL_LZMA=y CONFIG_SYSVIPC=y @@ -41,7 +40,6 @@ CONFIG_SYN_COOKIES=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_INET_DIAG is not set CONFIG_TCP_CONG_ADVANCED=y # CONFIG_TCP_CONG_BIC is not set @@ -86,7 +84,6 @@ CONFIG_MAC80211_RC_DEFAULT_PID=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FIRMWARE_IN_KERNEL is not set CONFIG_MTD=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_INTELEXT=y @@ -99,8 +96,6 @@ CONFIG_FIXED_PHY=y CONFIG_NET_ETHERNET=y CONFIG_MII=y CONFIG_CPMAC=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set CONFIG_PPP=m CONFIG_PPP_MULTILINK=y CONFIG_PPP_FILTER=y @@ -142,7 +137,6 @@ CONFIG_BSD_DISKLABEL=y # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y CONFIG_DEBUG_FS=y -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="rootfstype=squashfs,jffs2" CONFIG_CRYPTO=y diff --git a/arch/mips/configs/ath79_defconfig b/arch/mips/configs/ath79_defconfig index 134879c1310a..25ed914933e5 100644 --- a/arch/mips/configs/ath79_defconfig +++ b/arch/mips/configs/ath79_defconfig @@ -7,7 +7,6 @@ CONFIG_ATH79_MACH_PB44=y CONFIG_ATH79_MACH_UBNT_XM=y CONFIG_HZ_100=y # CONFIG_SECCOMP is not set -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_HIGH_RES_TIMERS=y @@ -35,7 +34,6 @@ CONFIG_IP_ADVANCED_ROUTER=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set CONFIG_CFG80211=m CONFIG_MAC80211=m diff --git a/arch/mips/configs/bcm63xx_defconfig b/arch/mips/configs/bcm63xx_defconfig index 5599a9f1e3c6..131b350f014f 100644 --- a/arch/mips/configs/bcm63xx_defconfig +++ b/arch/mips/configs/bcm63xx_defconfig @@ -5,7 +5,6 @@ CONFIG_BCM63XX_CPU_6348=y CONFIG_BCM63XX_CPU_6358=y CONFIG_NO_HZ=y # CONFIG_SECCOMP is not set -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set # CONFIG_SWAP is not set CONFIG_TINY_RCU=y @@ -33,7 +32,6 @@ CONFIG_INET=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_INET_DIAG is not set # CONFIG_IPV6 is not set CONFIG_CFG80211=y @@ -50,13 +48,10 @@ CONFIG_MTD_CFI_INTELEXT=y CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_PHYSMAP=y # CONFIG_BLK_DEV is not set -# CONFIG_MISC_DEVICES is not set CONFIG_NETDEVICES=y CONFIG_BCM63XX_PHY=y CONFIG_NET_ETHERNET=y CONFIG_BCM63XX_ENET=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set CONFIG_B43=y # CONFIG_B43_PHY_LP is not set # CONFIG_INPUT is not set @@ -70,7 +65,6 @@ CONFIG_SERIAL_BCM63XX_CONSOLE=y # CONFIG_HWMON is not set # CONFIG_VGA_ARB is not set CONFIG_USB=y -# CONFIG_USB_DEVICE_CLASS is not set CONFIG_USB_EHCI_HCD=y # CONFIG_USB_EHCI_TT_NEWSCHED is not set CONFIG_USB_OHCI_HCD=y @@ -84,7 +78,6 @@ CONFIG_LEDS_TRIGGER_DEFAULT_ON=y CONFIG_PROC_KCORE=y # CONFIG_NETWORK_FILESYSTEMS is not set CONFIG_MAGIC_SYSRQ=y -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="console=ttyS0,115200" # CONFIG_CRYPTO_HW is not set diff --git a/arch/mips/configs/bigsur_defconfig b/arch/mips/configs/bigsur_defconfig index d20b09d77b53..a55009edbb29 100644 --- a/arch/mips/configs/bigsur_defconfig +++ b/arch/mips/configs/bigsur_defconfig @@ -4,7 +4,6 @@ CONFIG_SMP=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_HZ_1000=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_BSD_PROCESS_ACCT=y @@ -60,7 +59,6 @@ CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m CONFIG_INET_XFRM_MODE_TRANSPORT=m CONFIG_INET_XFRM_MODE_TUNNEL=m -# CONFIG_INET_LRO is not set CONFIG_TCP_MD5SIG=y CONFIG_IPV6_ROUTER_PREF=y CONFIG_IPV6_ROUTE_INFO=y @@ -182,7 +180,6 @@ CONFIG_QUOTA=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set CONFIG_QFMT_V2=m -CONFIG_AUTOFS_FS=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_ISO9660_FS=m @@ -284,7 +281,6 @@ CONFIG_CRYPTO_SEED=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_ZLIB=m CONFIG_CRYPTO_LZO=m CONFIG_CRC_T10DIF=m CONFIG_CRC7=m diff --git a/arch/mips/configs/bmips_be_defconfig b/arch/mips/configs/bmips_be_defconfig index acf7785c4cdb..a7072a14d396 100644 --- a/arch/mips/configs/bmips_be_defconfig +++ b/arch/mips/configs/bmips_be_defconfig @@ -23,7 +23,6 @@ CONFIG_INET=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_INET_DIAG is not set CONFIG_CFG80211=y CONFIG_NL80211_TESTMODE=y diff --git a/arch/mips/configs/capcella_defconfig b/arch/mips/configs/capcella_defconfig index 2924ba34a01b..bd80b5c852dd 100644 --- a/arch/mips/configs/capcella_defconfig +++ b/arch/mips/configs/capcella_defconfig @@ -1,6 +1,5 @@ CONFIG_MACH_VR41XX=y CONFIG_ZAO_CAPCELLA=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set @@ -46,8 +45,6 @@ CONFIG_SMSC_PHY=m CONFIG_NET_ETHERNET=y CONFIG_NET_PCI=y CONFIG_8139TOO=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set # CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set @@ -59,7 +56,6 @@ CONFIG_SERIAL_VR41XX_CONSOLE=y CONFIG_GPIO_VR41XX=y # CONFIG_HWMON is not set # CONFIG_VGA_CONSOLE is not set -# CONFIG_HID_SUPPORT is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_VR41XX=y diff --git a/arch/mips/configs/cavium_octeon_defconfig b/arch/mips/configs/cavium_octeon_defconfig index d4fda41f00ba..e5b18f1a31a0 100644 --- a/arch/mips/configs/cavium_octeon_defconfig +++ b/arch/mips/configs/cavium_octeon_defconfig @@ -42,7 +42,6 @@ CONFIG_IP_MROUTE=y CONFIG_IP_PIMSM_V1=y CONFIG_IP_PIMSM_V2=y CONFIG_SYN_COOKIES=y -# CONFIG_INET_LRO is not set CONFIG_IPV6=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y diff --git a/arch/mips/configs/ci20_defconfig b/arch/mips/configs/ci20_defconfig index 43e0ba24470c..b42cfa7865f9 100644 --- a/arch/mips/configs/ci20_defconfig +++ b/arch/mips/configs/ci20_defconfig @@ -41,7 +41,6 @@ CONFIG_INET=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_INET_DIAG is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set diff --git a/arch/mips/configs/cobalt_defconfig b/arch/mips/configs/cobalt_defconfig index 23b66934e18d..a9066f300665 100644 --- a/arch/mips/configs/cobalt_defconfig +++ b/arch/mips/configs/cobalt_defconfig @@ -1,5 +1,4 @@ CONFIG_MIPS_COBALT=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_RELAY=y @@ -15,17 +14,14 @@ CONFIG_XFRM_USER=y CONFIG_NET_KEY=y CONFIG_NET_KEY_MIGRATE=y CONFIG_INET=y -# CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_MTD=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLKDEVS=y CONFIG_MTD_JEDECPROBE=y CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_PHYSMAP=y CONFIG_BLK_DEV_LOOP=y -# CONFIG_MISC_DEVICES is not set CONFIG_RAID_ATTRS=y CONFIG_BLK_DEV_SD=y # CONFIG_SCSI_LOWLEVEL is not set @@ -36,8 +32,6 @@ CONFIG_NET_ETHERNET=y CONFIG_NET_TULIP=y CONFIG_DE2104X=y CONFIG_TULIP=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set # CONFIG_INPUT_MOUSEDEV is not set CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_KEYBOARD is not set @@ -56,7 +50,6 @@ CONFIG_FB_COBALT=y # CONFIG_VGA_CONSOLE is not set CONFIG_HID=m CONFIG_USB=m -# CONFIG_USB_DEVICE_CLASS is not set CONFIG_USB_EHCI_HCD=m # CONFIG_USB_EHCI_TT_NEWSCHED is not set CONFIG_USB_OHCI_HCD=m @@ -84,6 +77,5 @@ CONFIG_NFS_V3_ACL=y CONFIG_NFSD=y CONFIG_NFSD_V3=y CONFIG_NFSD_V3_ACL=y -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_CRC16=y CONFIG_LIBCRC32C=y diff --git a/arch/mips/configs/decstation_defconfig b/arch/mips/configs/decstation_defconfig index 2b6cb41d5715..e149f78901f8 100644 --- a/arch/mips/configs/decstation_defconfig +++ b/arch/mips/configs/decstation_defconfig @@ -1,6 +1,5 @@ CONFIG_MACH_DECSTATION=y CONFIG_CPU_R3000=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set diff --git a/arch/mips/configs/e55_defconfig b/arch/mips/configs/e55_defconfig index e94d266c4b97..c3ac0209457c 100644 --- a/arch/mips/configs/e55_defconfig +++ b/arch/mips/configs/e55_defconfig @@ -1,6 +1,5 @@ CONFIG_MACH_VR41XX=y CONFIG_CASIO_E55=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set @@ -28,7 +27,6 @@ CONFIG_SERIAL_VR41XX_CONSOLE=y CONFIG_GPIO_VR41XX=y # CONFIG_HWMON is not set # CONFIG_VGA_CONSOLE is not set -# CONFIG_HID_SUPPORT is not set # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_VR41XX=y diff --git a/arch/mips/configs/fuloong2e_defconfig b/arch/mips/configs/fuloong2e_defconfig index 87435897fd50..499f51498ecb 100644 --- a/arch/mips/configs/fuloong2e_defconfig +++ b/arch/mips/configs/fuloong2e_defconfig @@ -3,7 +3,6 @@ CONFIG_64BIT=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_PREEMPT_VOLUNTARY=y -CONFIG_EXPERIMENTAL=y CONFIG_LOCALVERSION="-fuloong2e" # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y @@ -47,7 +46,6 @@ CONFIG_NET_IPGRE=m CONFIG_NET_IPGRE_BROADCAST=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_LRO is not set # CONFIG_INET_DIAG is not set # CONFIG_IPV6 is not set CONFIG_NETFILTER=y @@ -79,7 +77,6 @@ CONFIG_NETFILTER_XT_MATCH_STRING=m CONFIG_NETFILTER_XT_MATCH_TCPMSS=m CONFIG_NETFILTER_XT_MATCH_TIME=m CONFIG_NETFILTER_XT_MATCH_U32=m -CONFIG_IP_NF_QUEUE=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_ADDRTYPE=m CONFIG_IP_NF_MATCH_AH=m @@ -88,7 +85,6 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_LOG=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_ECN=m CONFIG_IP_NF_TARGET_TTL=m @@ -101,7 +97,6 @@ CONFIG_NET_9P=m CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_FW_LOADER=m CONFIG_MTD=m -CONFIG_MTD_CHAR=m CONFIG_MTD_BLOCK=m CONFIG_MTD_CFI=m CONFIG_MTD_JEDECPROBE=m @@ -163,7 +158,6 @@ CONFIG_I2C=m CONFIG_I2C_CHARDEV=m CONFIG_I2C_VIAPRO=m # CONFIG_HWMON is not set -CONFIG_VIDEO_OUTPUT_CONTROL=m CONFIG_FB=y CONFIG_FB_RADEON=y # CONFIG_FB_RADEON_I2C is not set @@ -184,7 +178,6 @@ CONFIG_USB_KBD=y CONFIG_USB_MOUSE=y CONFIG_USB=y CONFIG_USB_ANNOUNCE_NEW_DEVICES=y -# CONFIG_USB_DEVICE_CLASS is not set CONFIG_USB_OTG_WHITELIST=y CONFIG_USB_WUSB_CBAF=m CONFIG_USB_C67X00_HCD=m @@ -201,7 +194,6 @@ CONFIG_USB_TMC=m CONFIG_USB_STORAGE=y CONFIG_USB_STORAGE_ONETOUCH=y CONFIG_USB_STORAGE_CYPRESS_ATACB=y -CONFIG_USB_LIBUSUAL=y CONFIG_USB_SEVSEG=m CONFIG_USB_ISIGHTFW=m CONFIG_UIO=m @@ -215,7 +207,6 @@ CONFIG_EXT4_FS=m CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y CONFIG_REISERFS_FS=m -CONFIG_AUTOFS_FS=y CONFIG_AUTOFS4_FS=y CONFIG_FUSE_FS=y CONFIG_ISO9660_FS=m @@ -256,8 +247,6 @@ CONFIG_NLS_ISO8859_1=y CONFIG_NLS_UTF8=y # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_DEBUG_FS=y -# CONFIG_RCU_CPU_STALL_DETECTOR is not set -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_AUTHENC=m CONFIG_CRYPTO_CCM=m diff --git a/arch/mips/configs/gpr_defconfig b/arch/mips/configs/gpr_defconfig index e24feb0633aa..b1911816337c 100644 --- a/arch/mips/configs/gpr_defconfig +++ b/arch/mips/configs/gpr_defconfig @@ -2,7 +2,6 @@ CONFIG_MIPS_ALCHEMY=y CONFIG_MIPS_GPR=y CONFIG_HIGH_RES_TIMERS=y CONFIG_PREEMPT_VOLUNTARY=y -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -59,7 +58,6 @@ CONFIG_NETFILTER_XT_MATCH_REALM=m CONFIG_NETFILTER_XT_MATCH_STATISTIC=m CONFIG_NETFILTER_XT_MATCH_STRING=m CONFIG_NETFILTER_XT_MATCH_TCPMSS=m -CONFIG_IP_NF_QUEUE=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_ADDRTYPE=m CONFIG_IP_NF_MATCH_AH=m @@ -68,7 +66,6 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_LOG=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_ECN=m CONFIG_IP_NF_TARGET_TTL=m @@ -166,7 +163,6 @@ CONFIG_YAM=m CONFIG_CFG80211=y CONFIG_MAC80211=y CONFIG_MTD=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_INTELEXT=y @@ -200,8 +196,6 @@ CONFIG_SMSC_PHY=m CONFIG_NET_ETHERNET=y CONFIG_MII=y CONFIG_MIPS_AU1X00_ENET=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set CONFIG_ATH_COMMON=y CONFIG_ATH_DEBUG=y CONFIG_ATH5K=y @@ -286,14 +280,12 @@ CONFIG_USB_HIDDEV=y CONFIG_USB_KBD=m CONFIG_USB_MOUSE=m CONFIG_USB=y -# CONFIG_USB_DEVICE_CLASS is not set CONFIG_USB_MON=y CONFIG_USB_EHCI_HCD=y CONFIG_USB_EHCI_ROOT_HUB_TT=y CONFIG_USB_OHCI_HCD=y CONFIG_USB_OHCI_HCD_PLATFORM=y CONFIG_USB_STORAGE=m -CONFIG_USB_LIBUSUAL=y CONFIG_USB_SERIAL=y CONFIG_USB_EZUSB=y CONFIG_USB_SERIAL_GENERIC=y diff --git a/arch/mips/configs/ip22_defconfig b/arch/mips/configs/ip22_defconfig index ec8e9684296d..83e8fe2064aa 100644 --- a/arch/mips/configs/ip22_defconfig +++ b/arch/mips/configs/ip22_defconfig @@ -4,7 +4,6 @@ CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_HZ_1000=y CONFIG_PREEMPT_VOLUNTARY=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y @@ -46,7 +45,6 @@ CONFIG_INET_IPCOMP=m CONFIG_INET_XFRM_MODE_TRANSPORT=m CONFIG_INET_XFRM_MODE_TUNNEL=m CONFIG_INET_XFRM_MODE_BEET=m -# CONFIG_INET_LRO is not set CONFIG_TCP_MD5SIG=y CONFIG_IPV6_ROUTER_PREF=y CONFIG_IPV6_ROUTE_INFO=y @@ -139,7 +137,6 @@ CONFIG_IP_VS_SED=m CONFIG_IP_VS_NQ=m CONFIG_IP_VS_FTP=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_IP_NF_QUEUE=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_ADDRTYPE=m CONFIG_IP_NF_MATCH_AH=m @@ -148,7 +145,6 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_LOG=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m @@ -163,7 +159,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_IP6_NF_QUEUE=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -174,7 +169,6 @@ CONFIG_IP6_NF_MATCH_IPV6HEADER=m CONFIG_IP6_NF_MATCH_MH=m CONFIG_IP6_NF_MATCH_RT=m CONFIG_IP6_NF_TARGET_HL=m -CONFIG_IP6_NF_TARGET_LOG=m CONFIG_IP6_NF_FILTER=m CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_MANGLE=m @@ -215,7 +209,6 @@ CONFIG_RFKILL=m CONFIG_CONNECTOR=m CONFIG_CDROM_PKTCDVD=m CONFIG_ATA_OVER_ETH=m -# CONFIG_MISC_DEVICES is not set CONFIG_RAID_ATTRS=m CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y @@ -245,8 +238,6 @@ CONFIG_MDIO_BITBANG=m CONFIG_NET_ETHERNET=y CONFIG_SMC91X=m CONFIG_SGISEEQ=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set CONFIG_HOSTAP=m CONFIG_INPUT_MOUSEDEV=m CONFIG_MOUSE_PS2=m @@ -286,7 +277,6 @@ CONFIG_QUOTA=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set CONFIG_QFMT_V2=m -CONFIG_AUTOFS_FS=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_ISO9660_FS=m @@ -355,7 +345,6 @@ CONFIG_NLS_KOI8_U=m CONFIG_NLS_UTF8=m CONFIG_DLM=m CONFIG_DEBUG_MEMORY_INIT=y -# CONFIG_RCU_CPU_STALL_DETECTOR is not set CONFIG_KEYS=y CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_NULL=m diff --git a/arch/mips/configs/ip27_defconfig b/arch/mips/configs/ip27_defconfig index e582069b44fd..a0d593248668 100644 --- a/arch/mips/configs/ip27_defconfig +++ b/arch/mips/configs/ip27_defconfig @@ -5,7 +5,6 @@ CONFIG_SMP=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_HZ_1000=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_IKCONFIG=y @@ -104,7 +103,6 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m CONFIG_BLK_DEV_OSD=m CONFIG_CDROM_PKTCDVD=m CONFIG_ATA_OVER_ETH=m -# CONFIG_MISC_DEVICES is not set CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y @@ -325,7 +323,6 @@ CONFIG_XFS_POSIX_ACL=y CONFIG_BTRFS_FS=m CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_QUOTA_NETLINK_INTERFACE=y -CONFIG_AUTOFS_FS=m CONFIG_FUSE_FS=m CONFIG_CUSE=m CONFIG_FSCACHE=m @@ -342,7 +339,6 @@ CONFIG_NFS_V3=y CONFIG_RPCSEC_GSS_KRB5=y CONFIG_PARTITION_ADVANCED=y CONFIG_DLM=m -# CONFIG_RCU_CPU_STALL_DETECTOR is not set CONFIG_KEYS=y CONFIG_SECURITYFS=y CONFIG_CRYPTO_FIPS=y @@ -378,7 +374,6 @@ CONFIG_CRYPTO_SEED=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_ZLIB=m CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_DEV_HIFN_795X=m CONFIG_CRC_T10DIF=m diff --git a/arch/mips/configs/ip28_defconfig b/arch/mips/configs/ip28_defconfig index 4dbf6269b3f9..d0a4c2cfacf8 100644 --- a/arch/mips/configs/ip28_defconfig +++ b/arch/mips/configs/ip28_defconfig @@ -1,7 +1,6 @@ CONFIG_SGI_IP28=y CONFIG_ARC_CONSOLE=y CONFIG_PREEMPT_VOLUNTARY=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y @@ -35,10 +34,8 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set CONFIG_TCP_MD5SIG=y # CONFIG_IPV6 is not set -# CONFIG_MISC_DEVICES is not set CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y @@ -48,8 +45,6 @@ CONFIG_NETDEVICES=y CONFIG_DUMMY=m CONFIG_NET_ETHERNET=y CONFIG_SGISEEQ=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set # CONFIG_MOUSE_PS2_ALPS is not set # CONFIG_MOUSE_PS2_SYNAPTICS is not set CONFIG_VT_HW_CONSOLE_BINDING=y diff --git a/arch/mips/configs/ip32_defconfig b/arch/mips/configs/ip32_defconfig index f9af98f63cff..1e26e58b9dc3 100644 --- a/arch/mips/configs/ip32_defconfig +++ b/arch/mips/configs/ip32_defconfig @@ -1,6 +1,5 @@ CONFIG_SGI_IP32=y # CONFIG_SECCOMP is not set -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_BSD_PROCESS_ACCT=y @@ -38,7 +37,6 @@ CONFIG_NET_IPGRE=m CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m -# CONFIG_INET_LRO is not set CONFIG_TCP_CONG_ADVANCED=y CONFIG_TCP_MD5SIG=y CONFIG_INET6_AH=m @@ -76,8 +74,6 @@ CONFIG_NET_TULIP=y CONFIG_DE2104X=m CONFIG_TULIP=m CONFIG_TULIP_MMIO=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set CONFIG_INPUT_EVDEV=m # CONFIG_SERIO_I8042 is not set CONFIG_SERIO_MACEPS2=y @@ -87,7 +83,6 @@ CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_HW_RANDOM=y CONFIG_WATCHDOG=y -CONFIG_VIDEO_OUTPUT_CONTROL=y CONFIG_FB=y CONFIG_FIRMWARE_EDID=y CONFIG_FB_GBE=y @@ -117,7 +112,6 @@ CONFIG_EXT3_FS_SECURITY=y CONFIG_QUOTA=y CONFIG_QFMT_V1=m CONFIG_QFMT_V2=m -CONFIG_AUTOFS_FS=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_ISO9660_FS=m @@ -178,8 +172,6 @@ CONFIG_NLS_KOI8_R=m CONFIG_NLS_KOI8_U=m CONFIG_NLS_UTF8=m CONFIG_MAGIC_SYSRQ=y -# CONFIG_RCU_CPU_STALL_DETECTOR is not set -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_KEYS=y CONFIG_CRYPTO_NULL=y CONFIG_CRYPTO_CBC=y diff --git a/arch/mips/configs/jazz_defconfig b/arch/mips/configs/jazz_defconfig index 3019fce63cd3..9ad1c94376c8 100644 --- a/arch/mips/configs/jazz_defconfig +++ b/arch/mips/configs/jazz_defconfig @@ -1,7 +1,6 @@ CONFIG_MACH_JAZZ=y CONFIG_OLIVETTI_M700=y CONFIG_PREEMPT_VOLUNTARY=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_BSD_PROCESS_ACCT=y @@ -85,7 +84,6 @@ CONFIG_NETFILTER_XT_MATCH_STATISTIC=m CONFIG_NETFILTER_XT_MATCH_STRING=m CONFIG_NETFILTER_XT_MATCH_TCPMSS=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_IP_NF_QUEUE=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_ADDRTYPE=m CONFIG_IP_NF_MATCH_AH=m @@ -94,7 +92,6 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_LOG=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m @@ -109,7 +106,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_IP6_NF_QUEUE=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -120,7 +116,6 @@ CONFIG_IP6_NF_MATCH_IPV6HEADER=m CONFIG_IP6_NF_MATCH_MH=m CONFIG_IP6_NF_MATCH_RT=m CONFIG_IP6_NF_TARGET_HL=m -CONFIG_IP6_NF_TARGET_LOG=m CONFIG_IP6_NF_FILTER=m CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_MANGLE=m @@ -276,7 +271,6 @@ CONFIG_REISERFS_FS_POSIX_ACL=y CONFIG_REISERFS_FS_SECURITY=y CONFIG_XFS_FS=m CONFIG_XFS_QUOTA=y -CONFIG_AUTOFS_FS=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_ISO9660_FS=m diff --git a/arch/mips/configs/jmr3927_defconfig b/arch/mips/configs/jmr3927_defconfig index 9bc08f275120..af12281a5c33 100644 --- a/arch/mips/configs/jmr3927_defconfig +++ b/arch/mips/configs/jmr3927_defconfig @@ -18,23 +18,18 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_INET_DIAG is not set # CONFIG_IPV6 is not set CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y CONFIG_MTD_CFI=y CONFIG_MTD_JEDECPROBE=y CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_PHYSMAP=y -# CONFIG_MISC_DEVICES is not set CONFIG_NETDEVICES=y CONFIG_NET_ETHERNET=y CONFIG_NET_PCI=y CONFIG_TC35815=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set @@ -58,5 +53,3 @@ CONFIG_PROC_KCORE=y # CONFIG_MISC_FILESYSTEMS is not set CONFIG_NFS_FS=y CONFIG_ROOT_NFS=y -# CONFIG_RCU_CPU_STALL_DETECTOR is not set -CONFIG_SYSCTL_SYSCALL_CHECK=y diff --git a/arch/mips/configs/lasat_defconfig b/arch/mips/configs/lasat_defconfig index e620a2c3eba4..947a35c7c46c 100644 --- a/arch/mips/configs/lasat_defconfig +++ b/arch/mips/configs/lasat_defconfig @@ -5,7 +5,6 @@ CONFIG_DS1603=y CONFIG_LASAT_SYSCTL=y CONFIG_HZ_1000=y # CONFIG_SECCOMP is not set -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_EXPERT=y @@ -31,7 +30,6 @@ CONFIG_INET=y # CONFIG_INET_DIAG is not set # CONFIG_IPV6 is not set CONFIG_MTD=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_AMDSTD=y @@ -44,8 +42,6 @@ CONFIG_NETDEVICES=y CONFIG_NET_ETHERNET=y CONFIG_NET_PCI=y CONFIG_PCNET32=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set # CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set @@ -56,7 +52,6 @@ CONFIG_SERIAL_8250_CONSOLE=y # CONFIG_SERIAL_8250_PCI is not set # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set -# CONFIG_HID_SUPPORT is not set # CONFIG_USB_SUPPORT is not set CONFIG_EXT2_FS=y CONFIG_EXT3_FS=y diff --git a/arch/mips/configs/lemote2f_defconfig b/arch/mips/configs/lemote2f_defconfig index 8df80c6383f2..1ec8ed8d05d1 100644 --- a/arch/mips/configs/lemote2f_defconfig +++ b/arch/mips/configs/lemote2f_defconfig @@ -7,7 +7,6 @@ CONFIG_HIGH_RES_TIMERS=y CONFIG_PREEMPT=y CONFIG_KEXEC=y # CONFIG_SECCOMP is not set -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_BSD_PROCESS_ACCT=y @@ -83,8 +82,6 @@ CONFIG_NET_SCHED=y CONFIG_NET_EMATCH=y CONFIG_NET_CLS_ACT=y CONFIG_BT=m -CONFIG_BT_L2CAP=y -CONFIG_BT_SCO=y CONFIG_BT_RFCOMM=m CONFIG_BT_RFCOMM_TTY=y CONFIG_BT_BNEP=m @@ -142,7 +139,6 @@ CONFIG_8139TOO=y # CONFIG_8139TOO_PIO is not set CONFIG_R8169=y CONFIG_R8169_VLAN=y -# CONFIG_NETDEV_10000 is not set CONFIG_USB_USBNET=m CONFIG_USB_NET_CDC_EEM=m CONFIG_NETCONSOLE=m @@ -205,7 +201,6 @@ CONFIG_USB_ZR364XX=m CONFIG_USB_STKWEBCAM=m CONFIG_USB_S2255=m # CONFIG_RADIO_ADAPTERS is not set -CONFIG_VIDEO_OUTPUT_CONTROL=y CONFIG_FB=y CONFIG_FIRMWARE_EDID=y CONFIG_FB_MODE_HELPERS=y @@ -290,7 +285,6 @@ CONFIG_HID_WACOM=m CONFIG_HID_ZEROPLUS=m CONFIG_ZEROPLUS_FF=y CONFIG_USB=y -# CONFIG_USB_DEVICE_CLASS is not set CONFIG_USB_DYNAMIC_MINORS=y CONFIG_USB_OTG_WHITELIST=y CONFIG_USB_MON=y @@ -313,10 +307,8 @@ CONFIG_USB_STORAGE_SDDR09=m CONFIG_USB_STORAGE_SDDR55=m CONFIG_USB_STORAGE_JUMPSHOT=m CONFIG_USB_STORAGE_ALAUDA=m -CONFIG_USB_LIBUSUAL=y CONFIG_USB_SERIAL=m CONFIG_USB_SERIAL_GENERIC=y -CONFIG_USB_LED=m CONFIG_USB_GADGET=m CONFIG_USB_GADGET_M66592=y CONFIG_MMC=m @@ -341,7 +333,6 @@ CONFIG_XFS_POSIX_ACL=y CONFIG_BTRFS_FS=m CONFIG_QUOTA=y CONFIG_QFMT_V2=m -CONFIG_AUTOFS_FS=m CONFIG_AUTOFS4_FS=m CONFIG_FSCACHE=m CONFIG_CACHEFILES=m @@ -407,8 +398,6 @@ CONFIG_PRINTK_TIME=y CONFIG_FRAME_WARN=1024 CONFIG_STRIP_ASM_SYMS=y CONFIG_DEBUG_FS=y -# CONFIG_RCU_CPU_STALL_DETECTOR is not set -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_KEYS=y CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_NULL=m @@ -446,6 +435,5 @@ CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_DEFLATE=m -CONFIG_CRYPTO_ZLIB=m CONFIG_CRYPTO_LZO=m CONFIG_CRC_T10DIF=y diff --git a/arch/mips/configs/loongson3_defconfig b/arch/mips/configs/loongson3_defconfig index 7f95c4b3ab2c..324dfee23dfb 100644 --- a/arch/mips/configs/loongson3_defconfig +++ b/arch/mips/configs/loongson3_defconfig @@ -95,7 +95,6 @@ CONFIG_IP_NF_MATCH_ECN=m CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_ECN=m CONFIG_IP_NF_TARGET_TTL=m @@ -252,7 +251,6 @@ CONFIG_MEDIA_USB_SUPPORT=y CONFIG_USB_VIDEO_CLASS=m CONFIG_DRM=y CONFIG_DRM_RADEON=y -CONFIG_VIDEO_OUTPUT_CONTROL=y CONFIG_FB_RADEON=y CONFIG_LCD_CLASS_DEVICE=y CONFIG_LCD_PLATFORM=m @@ -335,7 +333,6 @@ CONFIG_STRIP_ASM_SYMS=y CONFIG_MAGIC_SYSRQ=y # CONFIG_SCHED_DEBUG is not set # CONFIG_DEBUG_PREEMPT is not set -# CONFIG_RCU_CPU_STALL_VERBOSE is not set # CONFIG_FTRACE is not set CONFIG_SECURITY=y CONFIG_SECURITYFS=y diff --git a/arch/mips/configs/malta_kvm_defconfig b/arch/mips/configs/malta_kvm_defconfig index e233f878afef..80ecd94ed126 100644 --- a/arch/mips/configs/malta_kvm_defconfig +++ b/arch/mips/configs/malta_kvm_defconfig @@ -133,7 +133,6 @@ CONFIG_IP_NF_MATCH_ECN=m CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_CLUSTERIP=m CONFIG_IP_NF_TARGET_ECN=m diff --git a/arch/mips/configs/malta_kvm_guest_defconfig b/arch/mips/configs/malta_kvm_guest_defconfig index fbe085c328ab..35ad1f8d1a79 100644 --- a/arch/mips/configs/malta_kvm_guest_defconfig +++ b/arch/mips/configs/malta_kvm_guest_defconfig @@ -132,7 +132,6 @@ CONFIG_IP_NF_MATCH_ECN=m CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_CLUSTERIP=m CONFIG_IP_NF_TARGET_ECN=m diff --git a/arch/mips/configs/malta_qemu_32r6_defconfig b/arch/mips/configs/malta_qemu_32r6_defconfig index cbf37dd0c490..77145ecaa23b 100644 --- a/arch/mips/configs/malta_qemu_32r6_defconfig +++ b/arch/mips/configs/malta_qemu_32r6_defconfig @@ -42,7 +42,6 @@ CONFIG_SYN_COOKIES=y CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m -# CONFIG_INET_LRO is not set CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m diff --git a/arch/mips/configs/maltaaprp_defconfig b/arch/mips/configs/maltaaprp_defconfig index 35f6ba260df8..cc2687cfdc13 100644 --- a/arch/mips/configs/maltaaprp_defconfig +++ b/arch/mips/configs/maltaaprp_defconfig @@ -43,7 +43,6 @@ CONFIG_SYN_COOKIES=y CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m -# CONFIG_INET_LRO is not set CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m @@ -135,7 +134,6 @@ CONFIG_HW_RANDOM=y CONFIG_POWER_RESET=y CONFIG_POWER_RESET_SYSCON=y # CONFIG_HWMON is not set -CONFIG_VIDEO_OUTPUT_CONTROL=m CONFIG_FB=y CONFIG_FIRMWARE_EDID=y CONFIG_FB_MATROX=y diff --git a/arch/mips/configs/maltasmvp_defconfig b/arch/mips/configs/maltasmvp_defconfig index 900f14543eeb..55b68b981b05 100644 --- a/arch/mips/configs/maltasmvp_defconfig +++ b/arch/mips/configs/maltasmvp_defconfig @@ -46,7 +46,6 @@ CONFIG_SYN_COOKIES=y CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m -# CONFIG_INET_LRO is not set CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m diff --git a/arch/mips/configs/maltasmvp_eva_defconfig b/arch/mips/configs/maltasmvp_eva_defconfig index 8e2738b5e180..5ca590cf1635 100644 --- a/arch/mips/configs/maltasmvp_eva_defconfig +++ b/arch/mips/configs/maltasmvp_eva_defconfig @@ -47,7 +47,6 @@ CONFIG_SYN_COOKIES=y CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m -# CONFIG_INET_LRO is not set CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m @@ -140,7 +139,6 @@ CONFIG_HW_RANDOM=y CONFIG_POWER_RESET=y CONFIG_POWER_RESET_SYSCON=y # CONFIG_HWMON is not set -CONFIG_VIDEO_OUTPUT_CONTROL=m CONFIG_FB=y CONFIG_FIRMWARE_EDID=y CONFIG_FB_MATROX=y diff --git a/arch/mips/configs/maltaup_defconfig b/arch/mips/configs/maltaup_defconfig index 6dc4e309a691..7ea7c0ba2666 100644 --- a/arch/mips/configs/maltaup_defconfig +++ b/arch/mips/configs/maltaup_defconfig @@ -42,7 +42,6 @@ CONFIG_SYN_COOKIES=y CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m -# CONFIG_INET_LRO is not set CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m @@ -134,7 +133,6 @@ CONFIG_HW_RANDOM=y CONFIG_POWER_RESET=y CONFIG_POWER_RESET_SYSCON=y # CONFIG_HWMON is not set -CONFIG_VIDEO_OUTPUT_CONTROL=m CONFIG_FB=y CONFIG_FIRMWARE_EDID=y CONFIG_FB_MATROX=y diff --git a/arch/mips/configs/markeins_defconfig b/arch/mips/configs/markeins_defconfig index 0f08e4623ee4..43ce6576ab1c 100644 --- a/arch/mips/configs/markeins_defconfig +++ b/arch/mips/configs/markeins_defconfig @@ -1,7 +1,6 @@ CONFIG_NEC_MARKEINS=y CONFIG_HZ_1000=y CONFIG_PREEMPT=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_BSD_PROCESS_ACCT=y @@ -92,7 +91,6 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_LOG=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m @@ -117,7 +115,6 @@ CONFIG_IP6_NF_MATCH_IPV6HEADER=m CONFIG_IP6_NF_MATCH_MH=m CONFIG_IP6_NF_MATCH_RT=m CONFIG_IP6_NF_TARGET_HL=m -CONFIG_IP6_NF_TARGET_LOG=m CONFIG_IP6_NF_FILTER=m CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_MANGLE=m @@ -125,7 +122,6 @@ CONFIG_IP6_NF_RAW=m CONFIG_FW_LOADER=m CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_AMDSTD=y diff --git a/arch/mips/configs/mips_paravirt_defconfig b/arch/mips/configs/mips_paravirt_defconfig index 84cfcb4bf2ea..accf0db1dc6f 100644 --- a/arch/mips/configs/mips_paravirt_defconfig +++ b/arch/mips/configs/mips_paravirt_defconfig @@ -39,7 +39,6 @@ CONFIG_IP_MROUTE=y CONFIG_IP_PIMSM_V1=y CONFIG_IP_PIMSM_V2=y CONFIG_SYN_COOKIES=y -# CONFIG_INET_LRO is not set CONFIG_IPV6=y # CONFIG_WIRELESS is not set CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" diff --git a/arch/mips/configs/mpc30x_defconfig b/arch/mips/configs/mpc30x_defconfig index a2c045fab6c5..3486b034f726 100644 --- a/arch/mips/configs/mpc30x_defconfig +++ b/arch/mips/configs/mpc30x_defconfig @@ -1,6 +1,5 @@ CONFIG_MACH_VR41XX=y CONFIG_VICTOR_MPC30X=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_RELAY=y @@ -31,8 +30,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_ATA=y CONFIG_PATA_LEGACY=y CONFIG_NETDEVICES=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set CONFIG_USB_PEGASUS=m # CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set @@ -45,13 +42,11 @@ CONFIG_SERIAL_VR41XX_CONSOLE=y CONFIG_GPIO_VR41XX=y # CONFIG_HWMON is not set # CONFIG_VGA_CONSOLE is not set -# CONFIG_HID_SUPPORT is not set CONFIG_USB=m CONFIG_USB_OHCI_HCD=m CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_VR41XX=y CONFIG_EXT2_FS=y -CONFIG_AUTOFS_FS=y CONFIG_AUTOFS4_FS=y CONFIG_PROC_KCORE=y CONFIG_CONFIGFS_FS=m diff --git a/arch/mips/configs/msp71xx_defconfig b/arch/mips/configs/msp71xx_defconfig index 201edfb2637d..3c8c16b10732 100644 --- a/arch/mips/configs/msp71xx_defconfig +++ b/arch/mips/configs/msp71xx_defconfig @@ -2,7 +2,6 @@ CONFIG_PMC_MSP=y CONFIG_PMC_MSP7120_GW=y CONFIG_CPU_MIPS32_R2=y CONFIG_PREEMPT=y -CONFIG_EXPERIMENTAL=y CONFIG_LOCALVERSION="-pmc" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y @@ -38,7 +37,6 @@ CONFIG_BRIDGE=y # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FW_LOADER is not set CONFIG_MTD=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_AMDSTD=y diff --git a/arch/mips/configs/mtx1_defconfig b/arch/mips/configs/mtx1_defconfig index f3f60056bc27..4011f1869e72 100644 --- a/arch/mips/configs/mtx1_defconfig +++ b/arch/mips/configs/mtx1_defconfig @@ -1,7 +1,6 @@ CONFIG_MIPS_ALCHEMY=y CONFIG_MIPS_MTX1=y CONFIG_PREEMPT_VOLUNTARY=y -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -81,7 +80,6 @@ CONFIG_NETFILTER_XT_MATCH_REALM=m CONFIG_NETFILTER_XT_MATCH_STATISTIC=m CONFIG_NETFILTER_XT_MATCH_STRING=m CONFIG_NETFILTER_XT_MATCH_TCPMSS=m -CONFIG_IP_NF_QUEUE=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_ADDRTYPE=m CONFIG_IP_NF_MATCH_AH=m @@ -90,7 +88,6 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_LOG=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_ECN=m CONFIG_IP_NF_TARGET_TTL=m @@ -98,7 +95,6 @@ CONFIG_IP_NF_RAW=m CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m -CONFIG_IP6_NF_QUEUE=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -108,7 +104,6 @@ CONFIG_IP6_NF_MATCH_HL=m CONFIG_IP6_NF_MATCH_IPV6HEADER=m CONFIG_IP6_NF_MATCH_RT=m CONFIG_IP6_NF_TARGET_HL=m -CONFIG_IP6_NF_TARGET_LOG=m CONFIG_IP6_NF_FILTER=m CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_MANGLE=m @@ -225,8 +220,6 @@ CONFIG_TOSHIBA_FIR=m CONFIG_VLSI_FIR=m CONFIG_MCS_FIR=m CONFIG_BT=m -CONFIG_BT_L2CAP=y -CONFIG_BT_SCO=y CONFIG_BT_RFCOMM=m CONFIG_BT_RFCOMM_TTY=y CONFIG_BT_BNEP=m @@ -246,7 +239,6 @@ CONFIG_BT_HCIBTUART=m CONFIG_BT_HCIVHCI=m CONFIG_CONNECTOR=m CONFIG_MTD=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_INTELEXT=y @@ -257,7 +249,6 @@ CONFIG_MTD_PHYSMAP=y CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=65536 -# CONFIG_MISC_DEVICES is not set CONFIG_SCSI=m CONFIG_BLK_DEV_SD=m CONFIG_CHR_DEV_SG=m @@ -596,7 +587,6 @@ CONFIG_USB_STORAGE_SDDR55=m CONFIG_USB_STORAGE_JUMPSHOT=m CONFIG_USB_STORAGE_ALAUDA=m CONFIG_USB_STORAGE_KARMA=m -CONFIG_USB_LIBUSUAL=y CONFIG_USB_MDC800=m CONFIG_USB_MICROTEK=m CONFIG_USB_SERIAL=m @@ -640,7 +630,6 @@ CONFIG_USB_ADUTUX=m CONFIG_USB_RIO500=m CONFIG_USB_LEGOTOWER=m CONFIG_USB_LCD=m -CONFIG_USB_LED=m CONFIG_USB_CYPRESS_CY7C63=m CONFIG_USB_CYTHERM=m CONFIG_USB_IDMOUSE=m diff --git a/arch/mips/configs/nlm_xlp_defconfig b/arch/mips/configs/nlm_xlp_defconfig index 07d01827a973..5720ce23e9aa 100644 --- a/arch/mips/configs/nlm_xlp_defconfig +++ b/arch/mips/configs/nlm_xlp_defconfig @@ -6,7 +6,6 @@ CONFIG_KSM=y CONFIG_DEFAULT_MMAP_MIN_ADDR=65536 CONFIG_SMP=y # CONFIG_SECCOMP is not set -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -183,14 +182,12 @@ CONFIG_IP_VS_SED=m CONFIG_IP_VS_NQ=m CONFIG_IP_VS_FTP=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_IP_NF_QUEUE=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m @@ -317,7 +314,6 @@ CONFIG_DEVTMPFS_MOUNT=y CONFIG_CONNECTOR=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_ADV_OPTIONS=y @@ -607,7 +603,6 @@ CONFIG_CRYPTO_SEED=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_ZLIB=m CONFIG_CRYPTO_LZO=m CONFIG_CRC_CCITT=m CONFIG_CRC7=m diff --git a/arch/mips/configs/nlm_xlr_defconfig b/arch/mips/configs/nlm_xlr_defconfig index f59969acb724..fea56c535d92 100644 --- a/arch/mips/configs/nlm_xlr_defconfig +++ b/arch/mips/configs/nlm_xlr_defconfig @@ -7,7 +7,6 @@ CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_PREEMPT_VOLUNTARY=y CONFIG_KEXEC=y -CONFIG_EXPERIMENTAL=y CONFIG_CROSS_COMPILE="" # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y @@ -163,7 +162,6 @@ CONFIG_IP_VS_SED=m CONFIG_IP_VS_NQ=m CONFIG_IP_VS_FTP=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_IP_NF_QUEUE=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -171,7 +169,6 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_LOG=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m @@ -186,7 +183,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_IP6_NF_QUEUE=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -197,7 +193,6 @@ CONFIG_IP6_NF_MATCH_IPV6HEADER=m CONFIG_IP6_NF_MATCH_MH=m CONFIG_IP6_NF_MATCH_RT=m CONFIG_IP6_NF_TARGET_HL=m -CONFIG_IP6_NF_TARGET_LOG=m CONFIG_IP6_NF_FILTER=m CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_MANGLE=m @@ -308,7 +303,6 @@ CONFIG_BLK_DEV_OSD=m CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=65536 CONFIG_CDROM_PKTCDVD=y -CONFIG_MISC_DEVICES=y CONFIG_RAID_ATTRS=m CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y @@ -369,7 +363,6 @@ CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_DS1374=y # CONFIG_HWMON is not set # CONFIG_VGA_CONSOLE is not set -# CONFIG_HID_SUPPORT is not set # CONFIG_USB_SUPPORT is not set CONFIG_UIO=y CONFIG_UIO_PDRV=m @@ -522,7 +515,6 @@ CONFIG_SCHEDSTATS=y CONFIG_TIMER_STATS=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_MEMORY_INIT=y -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_SCHED_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_KGDB=y @@ -568,7 +560,6 @@ CONFIG_CRYPTO_SEED=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_ZLIB=m CONFIG_CRYPTO_LZO=m CONFIG_CRC_CCITT=m CONFIG_CRC7=m diff --git a/arch/mips/configs/pnx8335_stb225_defconfig b/arch/mips/configs/pnx8335_stb225_defconfig index c887066ecc2a..81b5eb89446c 100644 --- a/arch/mips/configs/pnx8335_stb225_defconfig +++ b/arch/mips/configs/pnx8335_stb225_defconfig @@ -5,7 +5,6 @@ CONFIG_HIGH_RES_TIMERS=y CONFIG_HZ_128=y CONFIG_PREEMPT_VOLUNTARY=y # CONFIG_SECCOMP is not set -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set # CONFIG_SWAP is not set CONFIG_SYSVIPC=y @@ -27,12 +26,10 @@ CONFIG_IP_MULTICAST=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_INET_AH=y -# CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_ADV_OPTIONS=y @@ -41,15 +38,12 @@ CONFIG_MTD_CFI_GEOMETRY=y CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_PHYSMAP=y CONFIG_BLK_DEV_LOOP=y -# CONFIG_MISC_DEVICES is not set CONFIG_BLK_DEV_SD=y # CONFIG_SCSI_LOWLEVEL is not set CONFIG_ATA=y CONFIG_NETDEVICES=y CONFIG_NET_ETHERNET=y CONFIG_MII=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set # CONFIG_INPUT_MOUSEDEV is not set CONFIG_INPUT_EVDEV=m CONFIG_INPUT_EVBUG=m @@ -94,4 +88,3 @@ CONFIG_NLS_ASCII=m CONFIG_NLS_ISO8859_1=m CONFIG_NLS_ISO8859_15=m CONFIG_NLS_UTF8=m -CONFIG_SYSCTL_SYSCALL_CHECK=y diff --git a/arch/mips/configs/qi_lb60_defconfig b/arch/mips/configs/qi_lb60_defconfig index d7bb8cce1068..3f1333517405 100644 --- a/arch/mips/configs/qi_lb60_defconfig +++ b/arch/mips/configs/qi_lb60_defconfig @@ -34,7 +34,6 @@ CONFIG_IP_MROUTE_MULTIPLE_TABLES=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_INET_DIAG is not set CONFIG_TCP_CONG_ADVANCED=y # CONFIG_TCP_CONG_BIC is not set @@ -109,7 +108,6 @@ CONFIG_USB_GADGET_DEBUG=y CONFIG_USB_ETH=y # CONFIG_USB_ETH_RNDIS is not set CONFIG_MMC=y -CONFIG_MMC_UNSAFE_RESUME=y # CONFIG_MMC_BLOCK_BOUNCE is not set CONFIG_MMC_JZ4740=y CONFIG_RTC_CLASS=y @@ -183,7 +181,6 @@ CONFIG_PANIC_ON_OOPS=y # CONFIG_FTRACE is not set CONFIG_KGDB=y CONFIG_RUNTIME_DEBUG=y -CONFIG_CRYPTO_ZLIB=y # CONFIG_CRYPTO_ANSI_CPRNG is not set CONFIG_FONTS=y CONFIG_FONT_SUN8x16=y diff --git a/arch/mips/configs/rb532_defconfig b/arch/mips/configs/rb532_defconfig index 5d9d708e12e5..6fa56c6e53f5 100644 --- a/arch/mips/configs/rb532_defconfig +++ b/arch/mips/configs/rb532_defconfig @@ -3,7 +3,6 @@ CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_HZ_100=y # CONFIG_SECCOMP is not set -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_BSD_PROCESS_ACCT=y @@ -39,7 +38,6 @@ CONFIG_SYN_COOKIES=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set CONFIG_INET_DIAG=m CONFIG_TCP_CONG_ADVANCED=y CONFIG_TCP_CONG_CUBIC=m @@ -114,7 +112,6 @@ CONFIG_NET_CLS_IND=y CONFIG_HAMRADIO=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_MTD=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_BLOCK2MTD=y CONFIG_MTD_NAND=y @@ -129,8 +126,6 @@ CONFIG_NET_ETHERNET=y CONFIG_KORINA=y CONFIG_NET_PCI=y CONFIG_VIA_RHINE=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set CONFIG_ATMEL=m CONFIG_PPP=m CONFIG_PPP_MULTILINK=y @@ -183,7 +178,6 @@ CONFIG_BSD_DISKLABEL=y CONFIG_STRIP_ASM_SYMS=y CONFIG_CRYPTO=y CONFIG_CRYPTO_TEST=m -CONFIG_CRYPTO_ZLIB=y # CONFIG_CRYPTO_HW is not set CONFIG_CRC16=m CONFIG_LIBCRC32C=m diff --git a/arch/mips/configs/rbtx49xx_defconfig b/arch/mips/configs/rbtx49xx_defconfig index 43d55e5abacb..fb195e29e449 100644 --- a/arch/mips/configs/rbtx49xx_defconfig +++ b/arch/mips/configs/rbtx49xx_defconfig @@ -31,12 +31,10 @@ CONFIG_IP_PNP=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=m CONFIG_MTD_BLOCK_RO=m CONFIG_MTD_CFI=y @@ -50,7 +48,6 @@ CONFIG_MTD_NAND_TXX9NDFMC=m CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=8192 -# CONFIG_MISC_DEVICES is not set CONFIG_IDE=y CONFIG_BLK_DEV_IDE_TX4938=y CONFIG_BLK_DEV_IDE_TX4939=y @@ -60,8 +57,6 @@ CONFIG_SMC91X=y CONFIG_NE2000=y CONFIG_NET_PCI=y CONFIG_TC35815=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set # CONFIG_WLAN is not set # CONFIG_INPUT is not set # CONFIG_SERIO is not set @@ -108,5 +103,3 @@ CONFIG_NFS_V3=y CONFIG_ROOT_NFS=y CONFIG_STRIP_ASM_SYMS=y CONFIG_DEBUG_FS=y -# CONFIG_RCU_CPU_STALL_DETECTOR is not set -CONFIG_SYSCTL_SYSCALL_CHECK=y diff --git a/arch/mips/configs/rm200_defconfig b/arch/mips/configs/rm200_defconfig index c2b4e3f33a73..99679e514042 100644 --- a/arch/mips/configs/rm200_defconfig +++ b/arch/mips/configs/rm200_defconfig @@ -3,7 +3,6 @@ CONFIG_CPU_LITTLE_ENDIAN=y CONFIG_ARC_CONSOLE=y CONFIG_HZ_1000=y CONFIG_PREEMPT_VOLUNTARY=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_BSD_PROCESS_ACCT=y @@ -94,7 +93,6 @@ CONFIG_NETFILTER_XT_MATCH_STATISTIC=m CONFIG_NETFILTER_XT_MATCH_STRING=m CONFIG_NETFILTER_XT_MATCH_TCPMSS=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_IP_NF_QUEUE=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_ADDRTYPE=m CONFIG_IP_NF_MATCH_AH=m @@ -103,7 +101,6 @@ CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_LOG=m -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_NF_NAT=m CONFIG_IP_NF_TARGET_MASQUERADE=m CONFIG_IP_NF_TARGET_NETMAP=m @@ -118,7 +115,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_IP6_NF_QUEUE=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -129,7 +125,6 @@ CONFIG_IP6_NF_MATCH_IPV6HEADER=m CONFIG_IP6_NF_MATCH_MH=m CONFIG_IP6_NF_MATCH_RT=m CONFIG_IP6_NF_TARGET_HL=m -CONFIG_IP6_NF_TARGET_LOG=m CONFIG_IP6_NF_FILTER=m CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP6_NF_MANGLE=m @@ -214,7 +209,6 @@ CONFIG_BLK_DEV_LOOP=m CONFIG_BLK_DEV_CRYPTOLOOP=m CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_SX8=m -CONFIG_BLK_DEV_UB=m CONFIG_BLK_DEV_RAM=m CONFIG_CDROM_PKTCDVD=m CONFIG_ATA_OVER_ETH=m @@ -353,7 +347,6 @@ CONFIG_USB_SERIAL_OMNINET=m CONFIG_USB_RIO500=m CONFIG_USB_LEGOTOWER=m CONFIG_USB_LCD=m -CONFIG_USB_LED=m CONFIG_USB_CYTHERM=m CONFIG_USB_SISUSBVGA=m CONFIG_USB_LD=m @@ -366,7 +359,6 @@ CONFIG_REISERFS_FS_POSIX_ACL=y CONFIG_REISERFS_FS_SECURITY=y CONFIG_XFS_FS=m CONFIG_XFS_QUOTA=y -CONFIG_AUTOFS_FS=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_ISO9660_FS=m diff --git a/arch/mips/configs/rt305x_defconfig b/arch/mips/configs/rt305x_defconfig index d14ae2fa7d13..c695b7b1c4ae 100644 --- a/arch/mips/configs/rt305x_defconfig +++ b/arch/mips/configs/rt305x_defconfig @@ -5,7 +5,6 @@ CONFIG_CPU_MIPS32_R2=y # CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HZ_100=y # CONFIG_SECCOMP is not set -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_HIGH_RES_TIMERS=y @@ -44,7 +43,6 @@ CONFIG_SYN_COOKIES=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_INET_DIAG is not set CONFIG_TCP_CONG_ADVANCED=y # CONFIG_TCP_CONG_BIC is not set diff --git a/arch/mips/configs/sb1250_swarm_defconfig b/arch/mips/configs/sb1250_swarm_defconfig index 7fca09fedb59..c724bdd6a7e6 100644 --- a/arch/mips/configs/sb1250_swarm_defconfig +++ b/arch/mips/configs/sb1250_swarm_defconfig @@ -4,7 +4,6 @@ CONFIG_64BIT=y CONFIG_SMP=y CONFIG_HIGH_RES_TIMERS=y CONFIG_HZ_1000=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=15 CONFIG_CGROUPS=y diff --git a/arch/mips/configs/tb0219_defconfig b/arch/mips/configs/tb0219_defconfig index 11f51505d562..4041597e3170 100644 --- a/arch/mips/configs/tb0219_defconfig +++ b/arch/mips/configs/tb0219_defconfig @@ -1,6 +1,5 @@ CONFIG_MACH_VR41XX=y CONFIG_TANBAC_TB0219=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_SYSFS_DEPRECATED_V2=y @@ -31,7 +30,6 @@ CONFIG_SYN_COOKIES=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set CONFIG_NETWORK_SECMARK=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" @@ -40,7 +38,6 @@ CONFIG_BLK_DEV_LOOP=m CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_XIP=y -# CONFIG_MISC_DEVICES is not set CONFIG_NETDEVICES=y CONFIG_PHYLIB=m CONFIG_MARVELL_PHY=m @@ -57,7 +54,6 @@ CONFIG_VIA_RHINE=y CONFIG_VIA_RHINE_MMIO=y CONFIG_R8169=y CONFIG_VIA_VELOCITY=y -# CONFIG_NETDEV_10000 is not set # CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set @@ -70,7 +66,6 @@ CONFIG_SERIAL_VR41XX_CONSOLE=y CONFIG_GPIO_TB0219=y # CONFIG_HWMON is not set # CONFIG_VGA_CONSOLE is not set -# CONFIG_HID_SUPPORT is not set CONFIG_USB=m CONFIG_USB_MON=m CONFIG_USB_EHCI_HCD=m @@ -91,6 +86,5 @@ CONFIG_NFS_V3=y CONFIG_ROOT_NFS=y CONFIG_NFSD=y CONFIG_NFSD_V3=y -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="cca=3 mem=64M console=ttyVR0,115200 ip=any root=/dev/nfs" diff --git a/arch/mips/configs/tb0226_defconfig b/arch/mips/configs/tb0226_defconfig index 9327b3af32cd..565f0441c50d 100644 --- a/arch/mips/configs/tb0226_defconfig +++ b/arch/mips/configs/tb0226_defconfig @@ -1,6 +1,5 @@ CONFIG_MACH_VR41XX=y CONFIG_TANBAC_TB0226=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_SYSFS_DEPRECATED_V2=y @@ -29,7 +28,6 @@ CONFIG_SYN_COOKIES=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set CONFIG_NETWORK_SECMARK=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" @@ -37,7 +35,6 @@ CONFIG_BLK_DEV_LOOP=m CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_XIP=y -# CONFIG_MISC_DEVICES is not set CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_SCSI_MULTI_LUN=y @@ -49,8 +46,6 @@ CONFIG_NETDEVICES=y CONFIG_NET_ETHERNET=y CONFIG_NET_PCI=y CONFIG_E100=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set CONFIG_USB_CATC=m CONFIG_USB_KAWETH=m CONFIG_USB_PEGASUS=m @@ -66,7 +61,6 @@ CONFIG_SERIAL_VR41XX_CONSOLE=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set # CONFIG_VGA_CONSOLE is not set -# CONFIG_HID_SUPPORT is not set CONFIG_USB=y CONFIG_USB_EHCI_HCD=y # CONFIG_USB_EHCI_TT_NEWSCHED is not set @@ -87,7 +81,6 @@ CONFIG_NFS_V3=y CONFIG_ROOT_NFS=y CONFIG_NFSD=m CONFIG_NFSD_V3=y -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="cca=3 mem=32M console=ttyVR0,115200" CONFIG_CRC32=m diff --git a/arch/mips/configs/tb0287_defconfig b/arch/mips/configs/tb0287_defconfig index a967289b7970..a702be602fb9 100644 --- a/arch/mips/configs/tb0287_defconfig +++ b/arch/mips/configs/tb0287_defconfig @@ -1,5 +1,4 @@ CONFIG_MACH_VR41XX=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_SYSFS_DEPRECATED_V2=y @@ -31,7 +30,6 @@ CONFIG_SYN_COOKIES=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set CONFIG_TCP_CONG_ADVANCED=y CONFIG_TCP_CONG_BIC=y CONFIG_TCP_CONG_CUBIC=m @@ -43,7 +41,6 @@ CONFIG_BLK_DEV_LOOP=m CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_XIP=y -# CONFIG_MISC_DEVICES is not set CONFIG_BLK_DEV_SD=y CONFIG_SCSI_SCAN_ASYNC=y # CONFIG_SCSI_LOWLEVEL is not set @@ -64,7 +61,6 @@ CONFIG_VIA_RHINE=y CONFIG_VIA_RHINE_MMIO=y CONFIG_R8169=y CONFIG_VIA_VELOCITY=y -# CONFIG_NETDEV_10000 is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -76,7 +72,6 @@ CONFIG_SERIAL_VR41XX_CONSOLE=y CONFIG_GPIO_VR41XX=y # CONFIG_HWMON is not set CONFIG_MFD_SM501=y -CONFIG_VIDEO_OUTPUT_CONTROL=m CONFIG_FB=y CONFIG_FB_SM501=y # CONFIG_VGA_CONSOLE is not set diff --git a/arch/mips/configs/workpad_defconfig b/arch/mips/configs/workpad_defconfig index ee4b2be43c44..a84eac409c9c 100644 --- a/arch/mips/configs/workpad_defconfig +++ b/arch/mips/configs/workpad_defconfig @@ -1,6 +1,5 @@ CONFIG_MACH_VR41XX=y CONFIG_IBM_WORKPAD=y -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set @@ -28,13 +27,10 @@ CONFIG_IP_MULTICAST=y # CONFIG_IPV6 is not set CONFIG_NETWORK_SECMARK=y CONFIG_BLK_DEV_RAM=m -# CONFIG_MISC_DEVICES is not set CONFIG_IDE=y CONFIG_BLK_DEV_IDECS=m CONFIG_IDE_GENERIC=y CONFIG_NETDEVICES=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set CONFIG_NET_PCMCIA=y CONFIG_PCMCIA_3C589=m CONFIG_PCMCIA_3C574=m -- cgit v1.2.3-59-g8ed1b From 315e9c767d9a4668ad68cde1b57a14f916c90668 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 27 Jun 2017 17:34:19 +0200 Subject: mtd: spi-nor: cqspi: remove duplicate const The variable was already marked 'const' before the previous patch, but the qualifier was in an unusual place, and now the extra 'const' causes a harmless warning: drivers/mtd/spi-nor/cadence-quadspi.c:1286:34: error: duplicate 'const' declaration specifier [-Werror=duplicate-decl-specifier] This removes the other 'const' instead. Fixes: f993c123b461 ("mtd: spi-nor: cqspi: make of_device_ids const") Signed-off-by: Arnd Bergmann Signed-off-by: Cyrille Pitchen --- drivers/mtd/spi-nor/cadence-quadspi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c index d315c326e72f..53c7d8e0327a 100644 --- a/drivers/mtd/spi-nor/cadence-quadspi.c +++ b/drivers/mtd/spi-nor/cadence-quadspi.c @@ -1283,7 +1283,7 @@ static const struct dev_pm_ops cqspi__dev_pm_ops = { #define CQSPI_DEV_PM_OPS NULL #endif -static const struct of_device_id const cqspi_dt_ids[] = { +static const struct of_device_id cqspi_dt_ids[] = { {.compatible = "cdns,qspi-nor",}, { /* end of table */ } }; -- cgit v1.2.3-59-g8ed1b From 9447332ffacceeb49467ae5314887a30f6c0aaa9 Mon Sep 17 00:00:00 2001 From: Cyrille Pitchen Date: Mon, 26 Jun 2017 15:09:59 +0200 Subject: mtd: st_spi_fsm: remove SPINOR_OP_RDSR2 and use SPINOR_OP_RDCR instead The 35h instruction op code has two aliases/macro definitions: - SPINOR_OP_RDCR from include/linux/mtd/spi-nor.h - SPINOR_OP_RDSR2 from drivers/mtd/devices/serial_flash_cmds.h Actually, some manufacturers name the associated internal register Status Register 2 whereas other manufacturers name it Configuration Register hence the two different macros for the very same instruction op code. Since the spi-nor.h file is the reference file for all SPI NOR instruction op codes, this patch removes the definition of the SPINOR_OP_RDSR2 macro. Also the SPINOR_OP_RDSR2 macro will be associated to another instruction op code in a further patch so we need to avoid a conflict defining this macro twice. Indeed the JESD216 rev B specification, defining the SFDP tables, also refers to the 3Eh and 3Fh instruction op codes to write/read the Status Register 2 on some SPI NOR flash memories, the 35h op code still being used to read the Configuration Register/Status Register 2 on other memories. Signed-off-by: Cyrille Pitchen Acked-by: Marek Vasut --- drivers/mtd/devices/serial_flash_cmds.h | 1 - drivers/mtd/devices/st_spi_fsm.c | 4 ++-- 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/devices/serial_flash_cmds.h b/drivers/mtd/devices/serial_flash_cmds.h index 8b81e15105dd..eba125c9f23f 100644 --- a/drivers/mtd/devices/serial_flash_cmds.h +++ b/drivers/mtd/devices/serial_flash_cmds.h @@ -13,7 +13,6 @@ #define _MTD_SERIAL_FLASH_CMDS_H /* Generic Flash Commands/OPCODEs */ -#define SPINOR_OP_RDSR2 0x35 #define SPINOR_OP_WRVCR 0x81 #define SPINOR_OP_RDVCR 0x85 diff --git a/drivers/mtd/devices/st_spi_fsm.c b/drivers/mtd/devices/st_spi_fsm.c index 804313a33f2b..21afd94cd904 100644 --- a/drivers/mtd/devices/st_spi_fsm.c +++ b/drivers/mtd/devices/st_spi_fsm.c @@ -1445,7 +1445,7 @@ static int stfsm_s25fl_config(struct stfsm *fsm) } /* Check status of 'QE' bit, update if required. */ - stfsm_read_status(fsm, SPINOR_OP_RDSR2, &cr1, 1); + stfsm_read_status(fsm, SPINOR_OP_RDCR, &cr1, 1); data_pads = ((fsm->stfsm_seq_read.seq_cfg >> 16) & 0x3) + 1; if (data_pads == 4) { if (!(cr1 & STFSM_S25FL_CONFIG_QE)) { @@ -1490,7 +1490,7 @@ static int stfsm_w25q_config(struct stfsm *fsm) return ret; /* Check status of 'QE' bit, update if required. */ - stfsm_read_status(fsm, SPINOR_OP_RDSR2, &sr2, 1); + stfsm_read_status(fsm, SPINOR_OP_RDCR, &sr2, 1); data_pads = ((fsm->stfsm_seq_read.seq_cfg >> 16) & 0x3) + 1; if (data_pads == 4) { if (!(sr2 & W25Q_STATUS_QE)) { -- cgit v1.2.3-59-g8ed1b From 351b0940d473146923711bc943fc881354a4c1f3 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Thu, 30 Mar 2017 11:37:44 -0700 Subject: MIPS: module: Ensure we always clean up r_mips_hi16_list If we hit an error whilst processing a reloc then we would return early from apply_relocate & potentially not free entries in r_mips_hi16_list, thereby leaking memory. Fix this by ensuring that we always run the code to free r_mipps_hi16_list when errors occur. Signed-off-by: Paul Burton Fixes: 861667dc82f5 ("MIPS: Fix race condition in module relocation code.") Fixes: 04211a574641 ("MIPS: Bail on unsupported module relocs") Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/15831/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/module.c | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-) diff --git a/arch/mips/kernel/module.c b/arch/mips/kernel/module.c index 94627a3a6a0d..ddcfb59593b6 100644 --- a/arch/mips/kernel/module.c +++ b/arch/mips/kernel/module.c @@ -251,7 +251,7 @@ int apply_relocate(Elf_Shdr *sechdrs, const char *strtab, u32 *location; unsigned int i, type; Elf_Addr v; - int res; + int err = 0; pr_debug("Applying relocate section %u to %u\n", relsec, sechdrs[relsec].sh_info); @@ -270,7 +270,8 @@ int apply_relocate(Elf_Shdr *sechdrs, const char *strtab, continue; pr_warn("%s: Unknown symbol %s\n", me->name, strtab + sym->st_name); - return -ENOENT; + err = -ENOENT; + goto out; } type = ELF_MIPS_R_TYPE(rel[i]); @@ -283,29 +284,32 @@ int apply_relocate(Elf_Shdr *sechdrs, const char *strtab, if (!handler) { pr_err("%s: Unknown relocation type %u\n", me->name, type); - return -EINVAL; + err = -EINVAL; + goto out; } v = sym->st_value; - res = handler(me, location, v); - if (res) - return res; + err = handler(me, location, v); + if (err) + goto out; } +out: /* - * Normally the hi16 list should be deallocated at this point. A + * Normally the hi16 list should be deallocated at this point. A * malformed binary however could contain a series of R_MIPS_HI16 - * relocations not followed by a R_MIPS_LO16 relocation. In that - * case, free up the list and return an error. + * relocations not followed by a R_MIPS_LO16 relocation, or if we hit + * an error processing a reloc we might have gotten here before + * reaching the R_MIPS_LO16. In either case, free up the list and + * return an error. */ if (me->arch.r_mips_hi16_list) { free_relocation_chain(me->arch.r_mips_hi16_list); me->arch.r_mips_hi16_list = NULL; - - return -ENOEXEC; + err = err ?: -ENOEXEC; } - return 0; + return err; } /* Given an address, look for it in the module exception tables. */ -- cgit v1.2.3-59-g8ed1b From 430d0b88943afffd0da6d98799bf0afb008fd13f Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Thu, 30 Mar 2017 11:37:45 -0700 Subject: MIPS: module: Unify rel & rela reloc handling The module load code has previously had entirely separate implementations for rel & rela style relocs, which unnecessarily duplicates a whole lot of code. Unify the implementations of both types of reloc, sharing the bulk of the code. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/15832/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/module.h | 8 +- arch/mips/kernel/Makefile | 1 - arch/mips/kernel/module-rela.c | 202 ----------------------------------------- arch/mips/kernel/module.c | 195 ++++++++++++++++++++++++++++++--------- 4 files changed, 154 insertions(+), 252 deletions(-) delete mode 100644 arch/mips/kernel/module-rela.c diff --git a/arch/mips/include/asm/module.h b/arch/mips/include/asm/module.h index 702c273e67a9..e51add184717 100644 --- a/arch/mips/include/asm/module.h +++ b/arch/mips/include/asm/module.h @@ -47,8 +47,8 @@ typedef struct { #define Elf_Mips_Rel Elf32_Rel #define Elf_Mips_Rela Elf32_Rela -#define ELF_MIPS_R_SYM(rel) ELF32_R_SYM(rel.r_info) -#define ELF_MIPS_R_TYPE(rel) ELF32_R_TYPE(rel.r_info) +#define ELF_MIPS_R_SYM(rel) ELF32_R_SYM((rel).r_info) +#define ELF_MIPS_R_TYPE(rel) ELF32_R_TYPE((rel).r_info) #endif @@ -65,8 +65,8 @@ typedef struct { #define Elf_Mips_Rel Elf64_Mips_Rel #define Elf_Mips_Rela Elf64_Mips_Rela -#define ELF_MIPS_R_SYM(rel) (rel.r_sym) -#define ELF_MIPS_R_TYPE(rel) (rel.r_type) +#define ELF_MIPS_R_SYM(rel) ((rel).r_sym) +#define ELF_MIPS_R_TYPE(rel) ((rel).r_type) #endif diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile index 9a0e37b92ce0..f0edd7e8a0b7 100644 --- a/arch/mips/kernel/Makefile +++ b/arch/mips/kernel/Makefile @@ -31,7 +31,6 @@ obj-$(CONFIG_SYNC_R4K) += sync-r4k.o obj-$(CONFIG_DEBUG_FS) += segment.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_MODULES) += module.o -obj-$(CONFIG_MODULES_USE_ELF_RELA) += module-rela.o obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o obj-$(CONFIG_FUNCTION_TRACER) += mcount.o ftrace.o diff --git a/arch/mips/kernel/module-rela.c b/arch/mips/kernel/module-rela.c deleted file mode 100644 index 781168834456..000000000000 --- a/arch/mips/kernel/module-rela.c +++ /dev/null @@ -1,202 +0,0 @@ -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - * Copyright (C) 2001 Rusty Russell. - * Copyright (C) 2003, 2004 Ralf Baechle (ralf@linux-mips.org) - * Copyright (C) 2005 Thiemo Seufer - * Copyright (C) 2015 Imagination Technologies Ltd. - */ - -#include -#include -#include -#include - -extern int apply_r_mips_none(struct module *me, u32 *location, Elf_Addr v); - -static int apply_r_mips_32_rela(struct module *me, u32 *location, Elf_Addr v) -{ - *location = v; - - return 0; -} - -static int apply_r_mips_26_rela(struct module *me, u32 *location, Elf_Addr v) -{ - if (v % 4) { - pr_err("module %s: dangerous R_MIPS_26 RELA relocation\n", - me->name); - return -ENOEXEC; - } - - if ((v & 0xf0000000) != (((unsigned long)location + 4) & 0xf0000000)) { - pr_err("module %s: relocation overflow\n", me->name); - return -ENOEXEC; - } - - *location = (*location & ~0x03ffffff) | ((v >> 2) & 0x03ffffff); - - return 0; -} - -static int apply_r_mips_hi16_rela(struct module *me, u32 *location, Elf_Addr v) -{ - *location = (*location & 0xffff0000) | - ((((long long) v + 0x8000LL) >> 16) & 0xffff); - - return 0; -} - -static int apply_r_mips_lo16_rela(struct module *me, u32 *location, Elf_Addr v) -{ - *location = (*location & 0xffff0000) | (v & 0xffff); - - return 0; -} - -static int apply_r_mips_pc_rela(struct module *me, u32 *location, Elf_Addr v, - unsigned bits) -{ - unsigned long mask = GENMASK(bits - 1, 0); - unsigned long se_bits; - long offset; - - if (v % 4) { - pr_err("module %s: dangerous R_MIPS_PC%u RELA relocation\n", - me->name, bits); - return -ENOEXEC; - } - - offset = ((long)v - (long)location) >> 2; - - /* check the sign bit onwards are identical - ie. we didn't overflow */ - se_bits = (offset & BIT(bits - 1)) ? ~0ul : 0; - if ((offset & ~mask) != (se_bits & ~mask)) { - pr_err("module %s: relocation overflow\n", me->name); - return -ENOEXEC; - } - - *location = (*location & ~mask) | (offset & mask); - - return 0; -} - -static int apply_r_mips_pc16_rela(struct module *me, u32 *location, Elf_Addr v) -{ - return apply_r_mips_pc_rela(me, location, v, 16); -} - -static int apply_r_mips_pc21_rela(struct module *me, u32 *location, Elf_Addr v) -{ - return apply_r_mips_pc_rela(me, location, v, 21); -} - -static int apply_r_mips_pc26_rela(struct module *me, u32 *location, Elf_Addr v) -{ - return apply_r_mips_pc_rela(me, location, v, 26); -} - -static int apply_r_mips_64_rela(struct module *me, u32 *location, Elf_Addr v) -{ - *(Elf_Addr *)location = v; - - return 0; -} - -static int apply_r_mips_higher_rela(struct module *me, u32 *location, - Elf_Addr v) -{ - *location = (*location & 0xffff0000) | - ((((long long) v + 0x80008000LL) >> 32) & 0xffff); - - return 0; -} - -static int apply_r_mips_highest_rela(struct module *me, u32 *location, - Elf_Addr v) -{ - *location = (*location & 0xffff0000) | - ((((long long) v + 0x800080008000LL) >> 48) & 0xffff); - - return 0; -} - -static int (*reloc_handlers_rela[]) (struct module *me, u32 *location, - Elf_Addr v) = { - [R_MIPS_NONE] = apply_r_mips_none, - [R_MIPS_32] = apply_r_mips_32_rela, - [R_MIPS_26] = apply_r_mips_26_rela, - [R_MIPS_HI16] = apply_r_mips_hi16_rela, - [R_MIPS_LO16] = apply_r_mips_lo16_rela, - [R_MIPS_PC16] = apply_r_mips_pc16_rela, - [R_MIPS_64] = apply_r_mips_64_rela, - [R_MIPS_HIGHER] = apply_r_mips_higher_rela, - [R_MIPS_HIGHEST] = apply_r_mips_highest_rela, - [R_MIPS_PC21_S2] = apply_r_mips_pc21_rela, - [R_MIPS_PC26_S2] = apply_r_mips_pc26_rela, -}; - -int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, - unsigned int symindex, unsigned int relsec, - struct module *me) -{ - Elf_Mips_Rela *rel = (void *) sechdrs[relsec].sh_addr; - int (*handler)(struct module *me, u32 *location, Elf_Addr v); - Elf_Sym *sym; - u32 *location; - unsigned int i, type; - Elf_Addr v; - int res; - - pr_debug("Applying relocate section %u to %u\n", relsec, - sechdrs[relsec].sh_info); - - for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) { - /* This is where to make the change */ - location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr - + rel[i].r_offset; - /* This is the symbol it is referring to */ - sym = (Elf_Sym *)sechdrs[symindex].sh_addr - + ELF_MIPS_R_SYM(rel[i]); - if (sym->st_value >= -MAX_ERRNO) { - /* Ignore unresolved weak symbol */ - if (ELF_ST_BIND(sym->st_info) == STB_WEAK) - continue; - pr_warn("%s: Unknown symbol %s\n", - me->name, strtab + sym->st_name); - return -ENOENT; - } - - type = ELF_MIPS_R_TYPE(rel[i]); - - if (type < ARRAY_SIZE(reloc_handlers_rela)) - handler = reloc_handlers_rela[type]; - else - handler = NULL; - - if (!handler) { - pr_err("%s: Unknown relocation type %u\n", - me->name, type); - return -EINVAL; - } - - v = sym->st_value + rel[i].r_addend; - res = handler(me, location, v); - if (res) - return res; - } - - return 0; -} diff --git a/arch/mips/kernel/module.c b/arch/mips/kernel/module.c index ddcfb59593b6..b250eb0c4fc1 100644 --- a/arch/mips/kernel/module.c +++ b/arch/mips/kernel/module.c @@ -53,22 +53,25 @@ void *module_alloc(unsigned long size) } #endif -int apply_r_mips_none(struct module *me, u32 *location, Elf_Addr v) +static int apply_r_mips_none(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela) { return 0; } -static int apply_r_mips_32_rel(struct module *me, u32 *location, Elf_Addr v) +static int apply_r_mips_32(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela) { - *location += v; + *location = base + v; return 0; } -static int apply_r_mips_26_rel(struct module *me, u32 *location, Elf_Addr v) +static int apply_r_mips_26(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela) { if (v % 4) { - pr_err("module %s: dangerous R_MIPS_26 REL relocation\n", + pr_err("module %s: dangerous R_MIPS_26 relocation\n", me->name); return -ENOEXEC; } @@ -80,15 +83,22 @@ static int apply_r_mips_26_rel(struct module *me, u32 *location, Elf_Addr v) } *location = (*location & ~0x03ffffff) | - ((*location + (v >> 2)) & 0x03ffffff); + ((base + (v >> 2)) & 0x03ffffff); return 0; } -static int apply_r_mips_hi16_rel(struct module *me, u32 *location, Elf_Addr v) +static int apply_r_mips_hi16(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela) { struct mips_hi16 *n; + if (rela) { + *location = (*location & 0xffff0000) | + ((((long long) v + 0x8000LL) >> 16) & 0xffff); + return 0; + } + /* * We cannot relocate this one now because we don't know the value of * the carry we need to add. Save the information, and let LO16 do the @@ -117,12 +127,18 @@ static void free_relocation_chain(struct mips_hi16 *l) } } -static int apply_r_mips_lo16_rel(struct module *me, u32 *location, Elf_Addr v) +static int apply_r_mips_lo16(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela) { - unsigned long insnlo = *location; + unsigned long insnlo = base; struct mips_hi16 *l; Elf_Addr val, vallo; + if (rela) { + *location = (*location & 0xffff0000) | (v & 0xffff); + return 0; + } + /* Sign extend the addend we extract from the lo insn. */ vallo = ((insnlo & 0xffff) ^ 0x8000) - 0x8000; @@ -178,26 +194,26 @@ out_danger: free_relocation_chain(l); me->arch.r_mips_hi16_list = NULL; - pr_err("module %s: dangerous R_MIPS_LO16 REL relocation\n", me->name); + pr_err("module %s: dangerous R_MIPS_LO16 relocation\n", me->name); return -ENOEXEC; } -static int apply_r_mips_pc_rel(struct module *me, u32 *location, Elf_Addr v, - unsigned bits) +static int apply_r_mips_pc(struct module *me, u32 *location, u32 base, + Elf_Addr v, unsigned int bits) { unsigned long mask = GENMASK(bits - 1, 0); unsigned long se_bits; long offset; if (v % 4) { - pr_err("module %s: dangerous R_MIPS_PC%u REL relocation\n", + pr_err("module %s: dangerous R_MIPS_PC%u relocation\n", me->name, bits); return -ENOEXEC; } - /* retrieve & sign extend implicit addend */ - offset = *location & mask; + /* retrieve & sign extend implicit addend if any */ + offset = base & mask; offset |= (offset & BIT(bits - 1)) ? ~mask : 0; offset += ((long)v - (long)location) >> 2; @@ -214,56 +230,121 @@ static int apply_r_mips_pc_rel(struct module *me, u32 *location, Elf_Addr v, return 0; } -static int apply_r_mips_pc16_rel(struct module *me, u32 *location, Elf_Addr v) +static int apply_r_mips_pc16(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela) { - return apply_r_mips_pc_rel(me, location, v, 16); + return apply_r_mips_pc(me, location, base, v, 16); } -static int apply_r_mips_pc21_rel(struct module *me, u32 *location, Elf_Addr v) +static int apply_r_mips_pc21(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela) { - return apply_r_mips_pc_rel(me, location, v, 21); + return apply_r_mips_pc(me, location, base, v, 21); } -static int apply_r_mips_pc26_rel(struct module *me, u32 *location, Elf_Addr v) +static int apply_r_mips_pc26(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela) { - return apply_r_mips_pc_rel(me, location, v, 26); + return apply_r_mips_pc(me, location, base, v, 26); } -static int (*reloc_handlers_rel[]) (struct module *me, u32 *location, - Elf_Addr v) = { +static int apply_r_mips_64(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela) +{ + if (WARN_ON(!rela)) + return -EINVAL; + + *(Elf_Addr *)location = v; + + return 0; +} + +static int apply_r_mips_higher(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela) +{ + if (WARN_ON(!rela)) + return -EINVAL; + + *location = (*location & 0xffff0000) | + ((((long long)v + 0x80008000LL) >> 32) & 0xffff); + + return 0; +} + +static int apply_r_mips_highest(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela) +{ + if (WARN_ON(!rela)) + return -EINVAL; + + *location = (*location & 0xffff0000) | + ((((long long)v + 0x800080008000LL) >> 48) & 0xffff); + + return 0; +} + +/** + * reloc_handler() - Apply a particular relocation to a module + * @me: the module to apply the reloc to + * @location: the address at which the reloc is to be applied + * @base: the existing value at location for REL-style; 0 for RELA-style + * @v: the value of the reloc, with addend for RELA-style + * + * Each implemented reloc_handler function applies a particular type of + * relocation to the module @me. Relocs that may be found in either REL or RELA + * variants can be handled by making use of the @base & @v parameters which are + * set to values which abstract the difference away from the particular reloc + * implementations. + * + * Return: 0 upon success, else -ERRNO + */ +typedef int (*reloc_handler)(struct module *me, u32 *location, + u32 base, Elf_Addr v, bool rela); + +/* The handlers for known reloc types */ +static reloc_handler reloc_handlers[] = { [R_MIPS_NONE] = apply_r_mips_none, - [R_MIPS_32] = apply_r_mips_32_rel, - [R_MIPS_26] = apply_r_mips_26_rel, - [R_MIPS_HI16] = apply_r_mips_hi16_rel, - [R_MIPS_LO16] = apply_r_mips_lo16_rel, - [R_MIPS_PC16] = apply_r_mips_pc16_rel, - [R_MIPS_PC21_S2] = apply_r_mips_pc21_rel, - [R_MIPS_PC26_S2] = apply_r_mips_pc26_rel, + [R_MIPS_32] = apply_r_mips_32, + [R_MIPS_26] = apply_r_mips_26, + [R_MIPS_HI16] = apply_r_mips_hi16, + [R_MIPS_LO16] = apply_r_mips_lo16, + [R_MIPS_PC16] = apply_r_mips_pc16, + [R_MIPS_64] = apply_r_mips_64, + [R_MIPS_HIGHER] = apply_r_mips_higher, + [R_MIPS_HIGHEST] = apply_r_mips_highest, + [R_MIPS_PC21_S2] = apply_r_mips_pc21, + [R_MIPS_PC26_S2] = apply_r_mips_pc26, }; -int apply_relocate(Elf_Shdr *sechdrs, const char *strtab, - unsigned int symindex, unsigned int relsec, - struct module *me) +static int __apply_relocate(Elf_Shdr *sechdrs, const char *strtab, + unsigned int symindex, unsigned int relsec, + struct module *me, bool rela) { - Elf_Mips_Rel *rel = (void *) sechdrs[relsec].sh_addr; - int (*handler)(struct module *me, u32 *location, Elf_Addr v); + union { + Elf_Mips_Rel *rel; + Elf_Mips_Rela *rela; + } r; + reloc_handler handler; Elf_Sym *sym; - u32 *location; + u32 *location, base; unsigned int i, type; Elf_Addr v; int err = 0; + size_t reloc_sz; pr_debug("Applying relocate section %u to %u\n", relsec, sechdrs[relsec].sh_info); + r.rel = (void *)sechdrs[relsec].sh_addr; + reloc_sz = rela ? sizeof(*r.rela) : sizeof(*r.rel); me->arch.r_mips_hi16_list = NULL; - for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) { + for (i = 0; i < sechdrs[relsec].sh_size / reloc_sz; i++) { /* This is where to make the change */ location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr - + rel[i].r_offset; + + r.rel->r_offset; /* This is the symbol it is referring to */ sym = (Elf_Sym *)sechdrs[symindex].sh_addr - + ELF_MIPS_R_SYM(rel[i]); + + ELF_MIPS_R_SYM(*r.rel); if (sym->st_value >= -MAX_ERRNO) { /* Ignore unresolved weak symbol */ if (ELF_ST_BIND(sym->st_info) == STB_WEAK) @@ -274,10 +355,9 @@ int apply_relocate(Elf_Shdr *sechdrs, const char *strtab, goto out; } - type = ELF_MIPS_R_TYPE(rel[i]); - - if (type < ARRAY_SIZE(reloc_handlers_rel)) - handler = reloc_handlers_rel[type]; + type = ELF_MIPS_R_TYPE(*r.rel); + if (type < ARRAY_SIZE(reloc_handlers)) + handler = reloc_handlers[type]; else handler = NULL; @@ -288,8 +368,17 @@ int apply_relocate(Elf_Shdr *sechdrs, const char *strtab, goto out; } - v = sym->st_value; - err = handler(me, location, v); + if (rela) { + v = sym->st_value + r.rela->r_addend; + base = 0; + r.rela = &r.rela[1]; + } else { + v = sym->st_value; + base = *location; + r.rel = &r.rel[1]; + } + + err = handler(me, location, base, v, rela); if (err) goto out; } @@ -312,6 +401,22 @@ out: return err; } +int apply_relocate(Elf_Shdr *sechdrs, const char *strtab, + unsigned int symindex, unsigned int relsec, + struct module *me) +{ + return __apply_relocate(sechdrs, strtab, symindex, relsec, me, false); +} + +#ifdef CONFIG_MODULES_USE_ELF_RELA +int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, + unsigned int symindex, unsigned int relsec, + struct module *me) +{ + return __apply_relocate(sechdrs, strtab, symindex, relsec, me, true); +} +#endif /* CONFIG_MODULES_USE_ELF_RELA */ + /* Given an address, look for it in the module exception tables. */ const struct exception_table_entry *search_module_dbetables(unsigned long addr) { -- cgit v1.2.3-59-g8ed1b From ce807d5f67ed309a6f357b88cc93185d89e921d3 Mon Sep 17 00:00:00 2001 From: David Daney Date: Tue, 13 Jun 2017 15:28:43 -0700 Subject: MIPS: Optimize uasm insn lookup. Instead of doing a linear search through the insn_table for each instruction, use the opcode as direct index into the table. This will give constant time lookup performance as the number of supported opcodes increases. Make the tables const as they are only ever read. For uasm-mips.c sort the table alphabetically, and remove duplicate entries, uasm-micromips.c was already sorted and duplicate free. There is a small savings in object size as struct insn loses a field: $ size arch/mips/mm/uasm-mips.o arch/mips/mm/uasm-mips.o.save text data bss dec hex filename 10040 0 0 10040 2738 arch/mips/mm/uasm-mips.o 9240 1120 0 10360 2878 arch/mips/mm/uasm-mips.o.save Signed-off-by: David Daney Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Matt Redfearn Cc: netdev@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16365/ Signed-off-by: Ralf Baechle --- arch/mips/mm/uasm-micromips.c | 188 ++++++++++++++++++------------------ arch/mips/mm/uasm-mips.c | 217 +++++++++++++++++++++--------------------- arch/mips/mm/uasm.c | 3 +- 3 files changed, 199 insertions(+), 209 deletions(-) diff --git a/arch/mips/mm/uasm-micromips.c b/arch/mips/mm/uasm-micromips.c index 277cf52d80e1..c28ff53c8da0 100644 --- a/arch/mips/mm/uasm-micromips.c +++ b/arch/mips/mm/uasm-micromips.c @@ -40,93 +40,92 @@ #include "uasm.c" -static struct insn insn_table_MM[] = { - { insn_addu, M(mm_pool32a_op, 0, 0, 0, 0, mm_addu32_op), RT | RS | RD }, - { insn_addiu, M(mm_addiu32_op, 0, 0, 0, 0, 0), RT | RS | SIMM }, - { insn_and, M(mm_pool32a_op, 0, 0, 0, 0, mm_and_op), RT | RS | RD }, - { insn_andi, M(mm_andi32_op, 0, 0, 0, 0, 0), RT | RS | UIMM }, - { insn_beq, M(mm_beq32_op, 0, 0, 0, 0, 0), RS | RT | BIMM }, - { insn_beql, 0, 0 }, - { insn_bgez, M(mm_pool32i_op, mm_bgez_op, 0, 0, 0, 0), RS | BIMM }, - { insn_bgezl, 0, 0 }, - { insn_bltz, M(mm_pool32i_op, mm_bltz_op, 0, 0, 0, 0), RS | BIMM }, - { insn_bltzl, 0, 0 }, - { insn_bne, M(mm_bne32_op, 0, 0, 0, 0, 0), RT | RS | BIMM }, - { insn_cache, M(mm_pool32b_op, 0, 0, mm_cache_func, 0, 0), RT | RS | SIMM }, - { insn_cfc1, M(mm_pool32f_op, 0, 0, 0, mm_cfc1_op, mm_32f_73_op), RT | RS }, - { insn_cfcmsa, M(mm_pool32s_op, 0, msa_cfc_op, 0, 0, mm_32s_elm_op), RD | RE }, - { insn_ctc1, M(mm_pool32f_op, 0, 0, 0, mm_ctc1_op, mm_32f_73_op), RT | RS }, - { insn_ctcmsa, M(mm_pool32s_op, 0, msa_ctc_op, 0, 0, mm_32s_elm_op), RD | RE }, - { insn_daddu, 0, 0 }, - { insn_daddiu, 0, 0 }, - { insn_di, M(mm_pool32a_op, 0, 0, 0, mm_di_op, mm_pool32axf_op), RS }, - { insn_divu, M(mm_pool32a_op, 0, 0, 0, mm_divu_op, mm_pool32axf_op), RT | RS }, - { insn_dmfc0, 0, 0 }, - { insn_dmtc0, 0, 0 }, - { insn_dsll, 0, 0 }, - { insn_dsll32, 0, 0 }, - { insn_dsra, 0, 0 }, - { insn_dsrl, 0, 0 }, - { insn_dsrl32, 0, 0 }, - { insn_drotr, 0, 0 }, - { insn_drotr32, 0, 0 }, - { insn_dsubu, 0, 0 }, - { insn_eret, M(mm_pool32a_op, 0, 0, 0, mm_eret_op, mm_pool32axf_op), 0 }, - { insn_ins, M(mm_pool32a_op, 0, 0, 0, 0, mm_ins_op), RT | RS | RD | RE }, - { insn_ext, M(mm_pool32a_op, 0, 0, 0, 0, mm_ext_op), RT | RS | RD | RE }, - { insn_j, M(mm_j32_op, 0, 0, 0, 0, 0), JIMM }, - { insn_jal, M(mm_jal32_op, 0, 0, 0, 0, 0), JIMM }, - { insn_jalr, M(mm_pool32a_op, 0, 0, 0, mm_jalr_op, mm_pool32axf_op), RT | RS }, - { insn_jr, M(mm_pool32a_op, 0, 0, 0, mm_jalr_op, mm_pool32axf_op), RS }, - { insn_lb, M(mm_lb32_op, 0, 0, 0, 0, 0), RT | RS | SIMM }, - { insn_ld, 0, 0 }, - { insn_lh, M(mm_lh32_op, 0, 0, 0, 0, 0), RS | RS | SIMM }, - { insn_ll, M(mm_pool32c_op, 0, 0, (mm_ll_func << 1), 0, 0), RS | RT | SIMM }, - { insn_lld, 0, 0 }, - { insn_lui, M(mm_pool32i_op, mm_lui_op, 0, 0, 0, 0), RS | SIMM }, - { insn_lw, M(mm_lw32_op, 0, 0, 0, 0, 0), RT | RS | SIMM }, - { insn_mfc0, M(mm_pool32a_op, 0, 0, 0, mm_mfc0_op, mm_pool32axf_op), RT | RS | RD }, - { insn_mfhi, M(mm_pool32a_op, 0, 0, 0, mm_mfhi32_op, mm_pool32axf_op), RS }, - { insn_mflo, M(mm_pool32a_op, 0, 0, 0, mm_mflo32_op, mm_pool32axf_op), RS }, - { insn_mtc0, M(mm_pool32a_op, 0, 0, 0, mm_mtc0_op, mm_pool32axf_op), RT | RS | RD }, - { insn_mthi, M(mm_pool32a_op, 0, 0, 0, mm_mthi32_op, mm_pool32axf_op), RS }, - { insn_mtlo, M(mm_pool32a_op, 0, 0, 0, mm_mtlo32_op, mm_pool32axf_op), RS }, - { insn_mul, M(mm_pool32a_op, 0, 0, 0, 0, mm_mul_op), RT | RS | RD }, - { insn_or, M(mm_pool32a_op, 0, 0, 0, 0, mm_or32_op), RT | RS | RD }, - { insn_ori, M(mm_ori32_op, 0, 0, 0, 0, 0), RT | RS | UIMM }, - { insn_pref, M(mm_pool32c_op, 0, 0, (mm_pref_func << 1), 0, 0), RT | RS | SIMM }, - { insn_rfe, 0, 0 }, - { insn_sc, M(mm_pool32c_op, 0, 0, (mm_sc_func << 1), 0, 0), RT | RS | SIMM }, - { insn_scd, 0, 0 }, - { insn_sd, 0, 0 }, - { insn_sll, M(mm_pool32a_op, 0, 0, 0, 0, mm_sll32_op), RT | RS | RD }, - { insn_sllv, M(mm_pool32a_op, 0, 0, 0, 0, mm_sllv32_op), RT | RS | RD }, - { insn_slt, M(mm_pool32a_op, 0, 0, 0, 0, mm_slt_op), RT | RS | RD }, - { insn_sltiu, M(mm_sltiu32_op, 0, 0, 0, 0, 0), RT | RS | SIMM }, - { insn_sltu, M(mm_pool32a_op, 0, 0, 0, 0, mm_sltu_op), RT | RS | RD }, - { insn_sra, M(mm_pool32a_op, 0, 0, 0, 0, mm_sra_op), RT | RS | RD }, - { insn_srl, M(mm_pool32a_op, 0, 0, 0, 0, mm_srl32_op), RT | RS | RD }, - { insn_srlv, M(mm_pool32a_op, 0, 0, 0, 0, mm_srlv32_op), RT | RS | RD }, - { insn_rotr, M(mm_pool32a_op, 0, 0, 0, 0, mm_rotr_op), RT | RS | RD }, - { insn_subu, M(mm_pool32a_op, 0, 0, 0, 0, mm_subu32_op), RT | RS | RD }, - { insn_sw, M(mm_sw32_op, 0, 0, 0, 0, 0), RT | RS | SIMM }, - { insn_sync, M(mm_pool32a_op, 0, 0, 0, mm_sync_op, mm_pool32axf_op), RS }, - { insn_tlbp, M(mm_pool32a_op, 0, 0, 0, mm_tlbp_op, mm_pool32axf_op), 0 }, - { insn_tlbr, M(mm_pool32a_op, 0, 0, 0, mm_tlbr_op, mm_pool32axf_op), 0 }, - { insn_tlbwi, M(mm_pool32a_op, 0, 0, 0, mm_tlbwi_op, mm_pool32axf_op), 0 }, - { insn_tlbwr, M(mm_pool32a_op, 0, 0, 0, mm_tlbwr_op, mm_pool32axf_op), 0 }, - { insn_wait, M(mm_pool32a_op, 0, 0, 0, mm_wait_op, mm_pool32axf_op), SCIMM }, - { insn_wsbh, M(mm_pool32a_op, 0, 0, 0, mm_wsbh_op, mm_pool32axf_op), RT | RS }, - { insn_xor, M(mm_pool32a_op, 0, 0, 0, 0, mm_xor32_op), RT | RS | RD }, - { insn_xori, M(mm_xori32_op, 0, 0, 0, 0, 0), RT | RS | UIMM }, - { insn_dins, 0, 0 }, - { insn_dinsm, 0, 0 }, - { insn_syscall, M(mm_pool32a_op, 0, 0, 0, mm_syscall_op, mm_pool32axf_op), SCIMM}, - { insn_bbit0, 0, 0 }, - { insn_bbit1, 0, 0 }, - { insn_lwx, 0, 0 }, - { insn_ldx, 0, 0 }, - { insn_invalid, 0, 0 } +static const struct insn const insn_table_MM[insn_invalid] = { + [insn_addu] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_addu32_op), RT | RS | RD}, + [insn_addiu] = {M(mm_addiu32_op, 0, 0, 0, 0, 0), RT | RS | SIMM}, + [insn_and] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_and_op), RT | RS | RD}, + [insn_andi] = {M(mm_andi32_op, 0, 0, 0, 0, 0), RT | RS | UIMM}, + [insn_beq] = {M(mm_beq32_op, 0, 0, 0, 0, 0), RS | RT | BIMM}, + [insn_beql] = {0, 0}, + [insn_bgez] = {M(mm_pool32i_op, mm_bgez_op, 0, 0, 0, 0), RS | BIMM}, + [insn_bgezl] = {0, 0}, + [insn_bltz] = {M(mm_pool32i_op, mm_bltz_op, 0, 0, 0, 0), RS | BIMM}, + [insn_bltzl] = {0, 0}, + [insn_bne] = {M(mm_bne32_op, 0, 0, 0, 0, 0), RT | RS | BIMM}, + [insn_cache] = {M(mm_pool32b_op, 0, 0, mm_cache_func, 0, 0), RT | RS | SIMM}, + [insn_cfc1] = {M(mm_pool32f_op, 0, 0, 0, mm_cfc1_op, mm_32f_73_op), RT | RS}, + [insn_cfcmsa] = {M(mm_pool32s_op, 0, msa_cfc_op, 0, 0, mm_32s_elm_op), RD | RE}, + [insn_ctc1] = {M(mm_pool32f_op, 0, 0, 0, mm_ctc1_op, mm_32f_73_op), RT | RS}, + [insn_ctcmsa] = {M(mm_pool32s_op, 0, msa_ctc_op, 0, 0, mm_32s_elm_op), RD | RE}, + [insn_daddu] = {0, 0}, + [insn_daddiu] = {0, 0}, + [insn_di] = {M(mm_pool32a_op, 0, 0, 0, mm_di_op, mm_pool32axf_op), RS}, + [insn_divu] = {M(mm_pool32a_op, 0, 0, 0, mm_divu_op, mm_pool32axf_op), RT | RS}, + [insn_dmfc0] = {0, 0}, + [insn_dmtc0] = {0, 0}, + [insn_dsll] = {0, 0}, + [insn_dsll32] = {0, 0}, + [insn_dsra] = {0, 0}, + [insn_dsrl] = {0, 0}, + [insn_dsrl32] = {0, 0}, + [insn_drotr] = {0, 0}, + [insn_drotr32] = {0, 0}, + [insn_dsubu] = {0, 0}, + [insn_eret] = {M(mm_pool32a_op, 0, 0, 0, mm_eret_op, mm_pool32axf_op), 0}, + [insn_ins] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_ins_op), RT | RS | RD | RE}, + [insn_ext] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_ext_op), RT | RS | RD | RE}, + [insn_j] = {M(mm_j32_op, 0, 0, 0, 0, 0), JIMM}, + [insn_jal] = {M(mm_jal32_op, 0, 0, 0, 0, 0), JIMM}, + [insn_jalr] = {M(mm_pool32a_op, 0, 0, 0, mm_jalr_op, mm_pool32axf_op), RT | RS}, + [insn_jr] = {M(mm_pool32a_op, 0, 0, 0, mm_jalr_op, mm_pool32axf_op), RS}, + [insn_lb] = {M(mm_lb32_op, 0, 0, 0, 0, 0), RT | RS | SIMM}, + [insn_ld] = {0, 0}, + [insn_lh] = {M(mm_lh32_op, 0, 0, 0, 0, 0), RS | RS | SIMM}, + [insn_ll] = {M(mm_pool32c_op, 0, 0, (mm_ll_func << 1), 0, 0), RS | RT | SIMM}, + [insn_lld] = {0, 0}, + [insn_lui] = {M(mm_pool32i_op, mm_lui_op, 0, 0, 0, 0), RS | SIMM}, + [insn_lw] = {M(mm_lw32_op, 0, 0, 0, 0, 0), RT | RS | SIMM}, + [insn_mfc0] = {M(mm_pool32a_op, 0, 0, 0, mm_mfc0_op, mm_pool32axf_op), RT | RS | RD}, + [insn_mfhi] = {M(mm_pool32a_op, 0, 0, 0, mm_mfhi32_op, mm_pool32axf_op), RS}, + [insn_mflo] = {M(mm_pool32a_op, 0, 0, 0, mm_mflo32_op, mm_pool32axf_op), RS}, + [insn_mtc0] = {M(mm_pool32a_op, 0, 0, 0, mm_mtc0_op, mm_pool32axf_op), RT | RS | RD}, + [insn_mthi] = {M(mm_pool32a_op, 0, 0, 0, mm_mthi32_op, mm_pool32axf_op), RS}, + [insn_mtlo] = {M(mm_pool32a_op, 0, 0, 0, mm_mtlo32_op, mm_pool32axf_op), RS}, + [insn_mul] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_mul_op), RT | RS | RD}, + [insn_or] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_or32_op), RT | RS | RD}, + [insn_ori] = {M(mm_ori32_op, 0, 0, 0, 0, 0), RT | RS | UIMM}, + [insn_pref] = {M(mm_pool32c_op, 0, 0, (mm_pref_func << 1), 0, 0), RT | RS | SIMM}, + [insn_rfe] = {0, 0}, + [insn_sc] = {M(mm_pool32c_op, 0, 0, (mm_sc_func << 1), 0, 0), RT | RS | SIMM}, + [insn_scd] = {0, 0}, + [insn_sd] = {0, 0}, + [insn_sll] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_sll32_op), RT | RS | RD}, + [insn_sllv] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_sllv32_op), RT | RS | RD}, + [insn_slt] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_slt_op), RT | RS | RD}, + [insn_sltiu] = {M(mm_sltiu32_op, 0, 0, 0, 0, 0), RT | RS | SIMM}, + [insn_sltu] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_sltu_op), RT | RS | RD}, + [insn_sra] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_sra_op), RT | RS | RD}, + [insn_srl] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_srl32_op), RT | RS | RD}, + [insn_srlv] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_srlv32_op), RT | RS | RD}, + [insn_rotr] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_rotr_op), RT | RS | RD}, + [insn_subu] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_subu32_op), RT | RS | RD}, + [insn_sw] = {M(mm_sw32_op, 0, 0, 0, 0, 0), RT | RS | SIMM}, + [insn_sync] = {M(mm_pool32a_op, 0, 0, 0, mm_sync_op, mm_pool32axf_op), RS}, + [insn_tlbp] = {M(mm_pool32a_op, 0, 0, 0, mm_tlbp_op, mm_pool32axf_op), 0}, + [insn_tlbr] = {M(mm_pool32a_op, 0, 0, 0, mm_tlbr_op, mm_pool32axf_op), 0}, + [insn_tlbwi] = {M(mm_pool32a_op, 0, 0, 0, mm_tlbwi_op, mm_pool32axf_op), 0}, + [insn_tlbwr] = {M(mm_pool32a_op, 0, 0, 0, mm_tlbwr_op, mm_pool32axf_op), 0}, + [insn_wait] = {M(mm_pool32a_op, 0, 0, 0, mm_wait_op, mm_pool32axf_op), SCIMM}, + [insn_wsbh] = {M(mm_pool32a_op, 0, 0, 0, mm_wsbh_op, mm_pool32axf_op), RT | RS}, + [insn_xor] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_xor32_op), RT | RS | RD}, + [insn_xori] = {M(mm_xori32_op, 0, 0, 0, 0, 0), RT | RS | UIMM}, + [insn_dins] = {0, 0}, + [insn_dinsm] = {0, 0}, + [insn_syscall] = {M(mm_pool32a_op, 0, 0, 0, mm_syscall_op, mm_pool32axf_op), SCIMM}, + [insn_bbit0] = {0, 0}, + [insn_bbit1] = {0, 0}, + [insn_lwx] = {0, 0}, + [insn_ldx] = {0, 0}, }; #undef M @@ -156,20 +155,17 @@ static inline u32 build_jimm(u32 arg) */ static void build_insn(u32 **buf, enum opcode opc, ...) { - struct insn *ip = NULL; - unsigned int i; + const struct insn *ip; va_list ap; u32 op; - for (i = 0; insn_table_MM[i].opcode != insn_invalid; i++) - if (insn_table_MM[i].opcode == opc) { - ip = &insn_table_MM[i]; - break; - } - - if (!ip || (opc == insn_daddiu && r4k_daddiu_bug())) + if (opc < 0 || opc >= insn_invalid || + (opc == insn_daddiu && r4k_daddiu_bug()) || + (insn_table_MM[opc].match == 0 && insn_table_MM[opc].fields == 0)) panic("Unsupported Micro-assembler instruction %d", opc); + ip = &insn_table_MM[opc]; + op = ip->match; va_start(ap, opc); if (ip->fields & RS) { diff --git a/arch/mips/mm/uasm-mips.c b/arch/mips/mm/uasm-mips.c index 2277499fe6ae..f3937e315ba8 100644 --- a/arch/mips/mm/uasm-mips.c +++ b/arch/mips/mm/uasm-mips.c @@ -48,126 +48,124 @@ #include "uasm.c" -static struct insn insn_table[] = { - { insn_addiu, M(addiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_addu, M(spec_op, 0, 0, 0, 0, addu_op), RS | RT | RD }, - { insn_andi, M(andi_op, 0, 0, 0, 0, 0), RS | RT | UIMM }, - { insn_and, M(spec_op, 0, 0, 0, 0, and_op), RS | RT | RD }, - { insn_bbit0, M(lwc2_op, 0, 0, 0, 0, 0), RS | RT | BIMM }, - { insn_bbit1, M(swc2_op, 0, 0, 0, 0, 0), RS | RT | BIMM }, - { insn_beql, M(beql_op, 0, 0, 0, 0, 0), RS | RT | BIMM }, - { insn_beq, M(beq_op, 0, 0, 0, 0, 0), RS | RT | BIMM }, - { insn_bgezl, M(bcond_op, 0, bgezl_op, 0, 0, 0), RS | BIMM }, - { insn_bgez, M(bcond_op, 0, bgez_op, 0, 0, 0), RS | BIMM }, - { insn_bltzl, M(bcond_op, 0, bltzl_op, 0, 0, 0), RS | BIMM }, - { insn_bltz, M(bcond_op, 0, bltz_op, 0, 0, 0), RS | BIMM }, - { insn_bne, M(bne_op, 0, 0, 0, 0, 0), RS | RT | BIMM }, +static const struct insn const insn_table[insn_invalid] = { + [insn_addiu] = {M(addiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_addu] = {M(spec_op, 0, 0, 0, 0, addu_op), RS | RT | RD}, + [insn_and] = {M(spec_op, 0, 0, 0, 0, and_op), RS | RT | RD}, + [insn_andi] = {M(andi_op, 0, 0, 0, 0, 0), RS | RT | UIMM}, + [insn_bbit0] = {M(lwc2_op, 0, 0, 0, 0, 0), RS | RT | BIMM}, + [insn_bbit1] = {M(swc2_op, 0, 0, 0, 0, 0), RS | RT | BIMM}, + [insn_beq] = {M(beq_op, 0, 0, 0, 0, 0), RS | RT | BIMM}, + [insn_beql] = {M(beql_op, 0, 0, 0, 0, 0), RS | RT | BIMM}, + [insn_bgez] = {M(bcond_op, 0, bgez_op, 0, 0, 0), RS | BIMM}, + [insn_bgezl] = {M(bcond_op, 0, bgezl_op, 0, 0, 0), RS | BIMM}, + [insn_bltz] = {M(bcond_op, 0, bltz_op, 0, 0, 0), RS | BIMM}, + [insn_bltzl] = {M(bcond_op, 0, bltzl_op, 0, 0, 0), RS | BIMM}, + [insn_bne] = {M(bne_op, 0, 0, 0, 0, 0), RS | RT | BIMM}, #ifndef CONFIG_CPU_MIPSR6 - { insn_cache, M(cache_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, + [insn_cache] = {M(cache_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, #else - { insn_cache, M6(spec3_op, 0, 0, 0, cache6_op), RS | RT | SIMM9 }, + [insn_cache] = {M6(spec3_op, 0, 0, 0, cache6_op), RS | RT | SIMM9}, #endif - { insn_cfc1, M(cop1_op, cfc_op, 0, 0, 0, 0), RT | RD }, - { insn_cfcmsa, M(msa_op, 0, msa_cfc_op, 0, 0, msa_elm_op), RD | RE }, - { insn_ctc1, M(cop1_op, ctc_op, 0, 0, 0, 0), RT | RD }, - { insn_ctcmsa, M(msa_op, 0, msa_ctc_op, 0, 0, msa_elm_op), RD | RE }, - { insn_daddiu, M(daddiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_daddu, M(spec_op, 0, 0, 0, 0, daddu_op), RS | RT | RD }, - { insn_dinsm, M(spec3_op, 0, 0, 0, 0, dinsm_op), RS | RT | RD | RE }, - { insn_di, M(cop0_op, mfmc0_op, 0, 12, 0, 0), RT }, - { insn_dins, M(spec3_op, 0, 0, 0, 0, dins_op), RS | RT | RD | RE }, - { insn_divu, M(spec_op, 0, 0, 0, 0, divu_op), RS | RT }, - { insn_dmfc0, M(cop0_op, dmfc_op, 0, 0, 0, 0), RT | RD | SET}, - { insn_dmtc0, M(cop0_op, dmtc_op, 0, 0, 0, 0), RT | RD | SET}, - { insn_drotr32, M(spec_op, 1, 0, 0, 0, dsrl32_op), RT | RD | RE }, - { insn_drotr, M(spec_op, 1, 0, 0, 0, dsrl_op), RT | RD | RE }, - { insn_dsll32, M(spec_op, 0, 0, 0, 0, dsll32_op), RT | RD | RE }, - { insn_dsll, M(spec_op, 0, 0, 0, 0, dsll_op), RT | RD | RE }, - { insn_dsra, M(spec_op, 0, 0, 0, 0, dsra_op), RT | RD | RE }, - { insn_dsrl32, M(spec_op, 0, 0, 0, 0, dsrl32_op), RT | RD | RE }, - { insn_dsrl, M(spec_op, 0, 0, 0, 0, dsrl_op), RT | RD | RE }, - { insn_dsubu, M(spec_op, 0, 0, 0, 0, dsubu_op), RS | RT | RD }, - { insn_eret, M(cop0_op, cop_op, 0, 0, 0, eret_op), 0 }, - { insn_ext, M(spec3_op, 0, 0, 0, 0, ext_op), RS | RT | RD | RE }, - { insn_ins, M(spec3_op, 0, 0, 0, 0, ins_op), RS | RT | RD | RE }, - { insn_j, M(j_op, 0, 0, 0, 0, 0), JIMM }, - { insn_jal, M(jal_op, 0, 0, 0, 0, 0), JIMM }, - { insn_jalr, M(spec_op, 0, 0, 0, 0, jalr_op), RS | RD }, - { insn_j, M(j_op, 0, 0, 0, 0, 0), JIMM }, + [insn_cfc1] = {M(cop1_op, cfc_op, 0, 0, 0, 0), RT | RD}, + [insn_cfcmsa] = {M(msa_op, 0, msa_cfc_op, 0, 0, msa_elm_op), RD | RE}, + [insn_ctc1] = {M(cop1_op, ctc_op, 0, 0, 0, 0), RT | RD}, + [insn_ctcmsa] = {M(msa_op, 0, msa_ctc_op, 0, 0, msa_elm_op), RD | RE}, + [insn_daddiu] = {M(daddiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_daddu] = {M(spec_op, 0, 0, 0, 0, daddu_op), RS | RT | RD}, + [insn_di] = {M(cop0_op, mfmc0_op, 0, 12, 0, 0), RT}, + [insn_dins] = {M(spec3_op, 0, 0, 0, 0, dins_op), RS | RT | RD | RE}, + [insn_dinsm] = {M(spec3_op, 0, 0, 0, 0, dinsm_op), RS | RT | RD | RE}, + [insn_divu] = {M(spec_op, 0, 0, 0, 0, divu_op), RS | RT}, + [insn_dmfc0] = {M(cop0_op, dmfc_op, 0, 0, 0, 0), RT | RD | SET}, + [insn_dmtc0] = {M(cop0_op, dmtc_op, 0, 0, 0, 0), RT | RD | SET}, + [insn_drotr] = {M(spec_op, 1, 0, 0, 0, dsrl_op), RT | RD | RE}, + [insn_drotr32] = {M(spec_op, 1, 0, 0, 0, dsrl32_op), RT | RD | RE}, + [insn_dsll] = {M(spec_op, 0, 0, 0, 0, dsll_op), RT | RD | RE}, + [insn_dsll32] = {M(spec_op, 0, 0, 0, 0, dsll32_op), RT | RD | RE}, + [insn_dsra] = {M(spec_op, 0, 0, 0, 0, dsra_op), RT | RD | RE}, + [insn_dsrl] = {M(spec_op, 0, 0, 0, 0, dsrl_op), RT | RD | RE}, + [insn_dsrl32] = {M(spec_op, 0, 0, 0, 0, dsrl32_op), RT | RD | RE}, + [insn_dsubu] = {M(spec_op, 0, 0, 0, 0, dsubu_op), RS | RT | RD}, + [insn_eret] = {M(cop0_op, cop_op, 0, 0, 0, eret_op), 0}, + [insn_ext] = {M(spec3_op, 0, 0, 0, 0, ext_op), RS | RT | RD | RE}, + [insn_ins] = {M(spec3_op, 0, 0, 0, 0, ins_op), RS | RT | RD | RE}, + [insn_j] = {M(j_op, 0, 0, 0, 0, 0), JIMM}, + [insn_jal] = {M(jal_op, 0, 0, 0, 0, 0), JIMM}, + [insn_jalr] = {M(spec_op, 0, 0, 0, 0, jalr_op), RS | RD}, #ifndef CONFIG_CPU_MIPSR6 - { insn_jr, M(spec_op, 0, 0, 0, 0, jr_op), RS }, + [insn_jr] = {M(spec_op, 0, 0, 0, 0, jr_op), RS}, #else - { insn_jr, M(spec_op, 0, 0, 0, 0, jalr_op), RS }, + [insn_jr] = {M(spec_op, 0, 0, 0, 0, jalr_op), RS}, #endif - { insn_lb, M(lb_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_ld, M(ld_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_ldx, M(spec3_op, 0, 0, 0, ldx_op, lx_op), RS | RT | RD }, - { insn_lh, M(lh_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_lhu, M(lhu_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, + [insn_lb] = {M(lb_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_ld] = {M(ld_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_lddir] = {M(lwc2_op, 0, 0, 0, lddir_op, mult_op), RS | RT | RD}, + [insn_ldpte] = {M(lwc2_op, 0, 0, 0, ldpte_op, mult_op), RS | RD}, + [insn_ldx] = {M(spec3_op, 0, 0, 0, ldx_op, lx_op), RS | RT | RD}, + [insn_lh] = {M(lh_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_lhu] = {M(lhu_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, #ifndef CONFIG_CPU_MIPSR6 - { insn_lld, M(lld_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_ll, M(ll_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, + [insn_ll] = {M(ll_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_lld] = {M(lld_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, #else - { insn_lld, M6(spec3_op, 0, 0, 0, lld6_op), RS | RT | SIMM9 }, - { insn_ll, M6(spec3_op, 0, 0, 0, ll6_op), RS | RT | SIMM9 }, + [insn_ll] = {M6(spec3_op, 0, 0, 0, ll6_op), RS | RT | SIMM9}, + [insn_lld] = {M6(spec3_op, 0, 0, 0, lld6_op), RS | RT | SIMM9}, #endif - { insn_lui, M(lui_op, 0, 0, 0, 0, 0), RT | SIMM }, - { insn_lw, M(lw_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_lwx, M(spec3_op, 0, 0, 0, lwx_op, lx_op), RS | RT | RD }, - { insn_mfc0, M(cop0_op, mfc_op, 0, 0, 0, 0), RT | RD | SET}, - { insn_mfhc0, M(cop0_op, mfhc0_op, 0, 0, 0, 0), RT | RD | SET}, - { insn_mfhi, M(spec_op, 0, 0, 0, 0, mfhi_op), RD }, - { insn_mflo, M(spec_op, 0, 0, 0, 0, mflo_op), RD }, - { insn_mtc0, M(cop0_op, mtc_op, 0, 0, 0, 0), RT | RD | SET}, - { insn_mthc0, M(cop0_op, mthc0_op, 0, 0, 0, 0), RT | RD | SET}, - { insn_mthi, M(spec_op, 0, 0, 0, 0, mthi_op), RS }, - { insn_mtlo, M(spec_op, 0, 0, 0, 0, mtlo_op), RS }, + [insn_lui] = {M(lui_op, 0, 0, 0, 0, 0), RT | SIMM}, + [insn_lw] = {M(lw_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_lwx] = {M(spec3_op, 0, 0, 0, lwx_op, lx_op), RS | RT | RD}, + [insn_mfc0] = {M(cop0_op, mfc_op, 0, 0, 0, 0), RT | RD | SET}, + [insn_mfhc0] = {M(cop0_op, mfhc0_op, 0, 0, 0, 0), RT | RD | SET}, + [insn_mfhi] = {M(spec_op, 0, 0, 0, 0, mfhi_op), RD}, + [insn_mflo] = {M(spec_op, 0, 0, 0, 0, mflo_op), RD}, + [insn_mtc0] = {M(cop0_op, mtc_op, 0, 0, 0, 0), RT | RD | SET}, + [insn_mthc0] = {M(cop0_op, mthc0_op, 0, 0, 0, 0), RT | RD | SET}, + [insn_mthi] = {M(spec_op, 0, 0, 0, 0, mthi_op), RS}, + [insn_mtlo] = {M(spec_op, 0, 0, 0, 0, mtlo_op), RS}, #ifndef CONFIG_CPU_MIPSR6 - { insn_mul, M(spec2_op, 0, 0, 0, 0, mul_op), RS | RT | RD}, + [insn_mul] = {M(spec2_op, 0, 0, 0, 0, mul_op), RS | RT | RD}, #else - { insn_mul, M(spec_op, 0, 0, 0, mult_mul_op, mult_op), RS | RT | RD}, + [insn_mul] = {M(spec_op, 0, 0, 0, mult_mul_op, mult_op), RS | RT | RD}, #endif - { insn_ori, M(ori_op, 0, 0, 0, 0, 0), RS | RT | UIMM }, - { insn_or, M(spec_op, 0, 0, 0, 0, or_op), RS | RT | RD }, + [insn_or] = {M(spec_op, 0, 0, 0, 0, or_op), RS | RT | RD}, + [insn_ori] = {M(ori_op, 0, 0, 0, 0, 0), RS | RT | UIMM}, #ifndef CONFIG_CPU_MIPSR6 - { insn_pref, M(pref_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, + [insn_pref] = {M(pref_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, #else - { insn_pref, M6(spec3_op, 0, 0, 0, pref6_op), RS | RT | SIMM9 }, + [insn_pref] = {M6(spec3_op, 0, 0, 0, pref6_op), RS | RT | SIMM9}, #endif - { insn_rfe, M(cop0_op, cop_op, 0, 0, 0, rfe_op), 0 }, - { insn_rotr, M(spec_op, 1, 0, 0, 0, srl_op), RT | RD | RE }, + [insn_rfe] = {M(cop0_op, cop_op, 0, 0, 0, rfe_op), 0}, + [insn_rotr] = {M(spec_op, 1, 0, 0, 0, srl_op), RT | RD | RE}, #ifndef CONFIG_CPU_MIPSR6 - { insn_scd, M(scd_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_sc, M(sc_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, + [insn_sc] = {M(sc_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_scd] = {M(scd_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, #else - { insn_scd, M6(spec3_op, 0, 0, 0, scd6_op), RS | RT | SIMM9 }, - { insn_sc, M6(spec3_op, 0, 0, 0, sc6_op), RS | RT | SIMM9 }, + [insn_sc] = {M6(spec3_op, 0, 0, 0, sc6_op), RS | RT | SIMM9}, + [insn_scd] = {M6(spec3_op, 0, 0, 0, scd6_op), RS | RT | SIMM9}, #endif - { insn_sd, M(sd_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_sll, M(spec_op, 0, 0, 0, 0, sll_op), RT | RD | RE }, - { insn_sllv, M(spec_op, 0, 0, 0, 0, sllv_op), RS | RT | RD }, - { insn_slt, M(spec_op, 0, 0, 0, 0, slt_op), RS | RT | RD }, - { insn_sltiu, M(sltiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_sltu, M(spec_op, 0, 0, 0, 0, sltu_op), RS | RT | RD }, - { insn_sra, M(spec_op, 0, 0, 0, 0, sra_op), RT | RD | RE }, - { insn_srl, M(spec_op, 0, 0, 0, 0, srl_op), RT | RD | RE }, - { insn_srlv, M(spec_op, 0, 0, 0, 0, srlv_op), RS | RT | RD }, - { insn_subu, M(spec_op, 0, 0, 0, 0, subu_op), RS | RT | RD }, - { insn_sw, M(sw_op, 0, 0, 0, 0, 0), RS | RT | SIMM }, - { insn_sync, M(spec_op, 0, 0, 0, 0, sync_op), RE }, - { insn_syscall, M(spec_op, 0, 0, 0, 0, syscall_op), SCIMM}, - { insn_tlbp, M(cop0_op, cop_op, 0, 0, 0, tlbp_op), 0 }, - { insn_tlbr, M(cop0_op, cop_op, 0, 0, 0, tlbr_op), 0 }, - { insn_tlbwi, M(cop0_op, cop_op, 0, 0, 0, tlbwi_op), 0 }, - { insn_tlbwr, M(cop0_op, cop_op, 0, 0, 0, tlbwr_op), 0 }, - { insn_wait, M(cop0_op, cop_op, 0, 0, 0, wait_op), SCIMM }, - { insn_wsbh, M(spec3_op, 0, 0, 0, wsbh_op, bshfl_op), RT | RD }, - { insn_xori, M(xori_op, 0, 0, 0, 0, 0), RS | RT | UIMM }, - { insn_xor, M(spec_op, 0, 0, 0, 0, xor_op), RS | RT | RD }, - { insn_yield, M(spec3_op, 0, 0, 0, 0, yield_op), RS | RD }, - { insn_ldpte, M(lwc2_op, 0, 0, 0, ldpte_op, mult_op), RS | RD }, - { insn_lddir, M(lwc2_op, 0, 0, 0, lddir_op, mult_op), RS | RT | RD }, - { insn_invalid, 0, 0 } + [insn_sd] = {M(sd_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_sll] = {M(spec_op, 0, 0, 0, 0, sll_op), RT | RD | RE}, + [insn_sllv] = {M(spec_op, 0, 0, 0, 0, sllv_op), RS | RT | RD}, + [insn_slt] = {M(spec_op, 0, 0, 0, 0, slt_op), RS | RT | RD}, + [insn_sltiu] = {M(sltiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_sltu] = {M(spec_op, 0, 0, 0, 0, sltu_op), RS | RT | RD}, + [insn_sra] = {M(spec_op, 0, 0, 0, 0, sra_op), RT | RD | RE}, + [insn_srl] = {M(spec_op, 0, 0, 0, 0, srl_op), RT | RD | RE}, + [insn_srlv] = {M(spec_op, 0, 0, 0, 0, srlv_op), RS | RT | RD}, + [insn_subu] = {M(spec_op, 0, 0, 0, 0, subu_op), RS | RT | RD}, + [insn_sw] = {M(sw_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_sync] = {M(spec_op, 0, 0, 0, 0, sync_op), RE}, + [insn_syscall] = {M(spec_op, 0, 0, 0, 0, syscall_op), SCIMM}, + [insn_tlbp] = {M(cop0_op, cop_op, 0, 0, 0, tlbp_op), 0}, + [insn_tlbr] = {M(cop0_op, cop_op, 0, 0, 0, tlbr_op), 0}, + [insn_tlbwi] = {M(cop0_op, cop_op, 0, 0, 0, tlbwi_op), 0}, + [insn_tlbwr] = {M(cop0_op, cop_op, 0, 0, 0, tlbwr_op), 0}, + [insn_wait] = {M(cop0_op, cop_op, 0, 0, 0, wait_op), SCIMM}, + [insn_wsbh] = {M(spec3_op, 0, 0, 0, wsbh_op, bshfl_op), RT | RD}, + [insn_xor] = {M(spec_op, 0, 0, 0, 0, xor_op), RS | RT | RD}, + [insn_xori] = {M(xori_op, 0, 0, 0, 0, 0), RS | RT | UIMM}, + [insn_yield] = {M(spec3_op, 0, 0, 0, 0, yield_op), RS | RD}, }; #undef M @@ -196,20 +194,17 @@ static inline u32 build_jimm(u32 arg) */ static void build_insn(u32 **buf, enum opcode opc, ...) { - struct insn *ip = NULL; - unsigned int i; + const struct insn *ip; va_list ap; u32 op; - for (i = 0; insn_table[i].opcode != insn_invalid; i++) - if (insn_table[i].opcode == opc) { - ip = &insn_table[i]; - break; - } - - if (!ip || (opc == insn_daddiu && r4k_daddiu_bug())) + if (opc < 0 || opc >= insn_invalid || + (opc == insn_daddiu && r4k_daddiu_bug()) || + (insn_table[opc].match == 0 && insn_table[opc].fields == 0)) panic("Unsupported Micro-assembler instruction %d", opc); + ip = &insn_table[opc]; + op = ip->match; va_start(ap, opc); if (ip->fields & RS) diff --git a/arch/mips/mm/uasm.c b/arch/mips/mm/uasm.c index 730363b59bac..f23ed85a0d6c 100644 --- a/arch/mips/mm/uasm.c +++ b/arch/mips/mm/uasm.c @@ -46,7 +46,6 @@ enum fields { #define SIMM9_MASK 0x1ff enum opcode { - insn_invalid, insn_addiu, insn_addu, insn_and, insn_andi, insn_bbit0, insn_bbit1, insn_beq, insn_beql, insn_bgez, insn_bgezl, insn_bltz, insn_bltzl, insn_bne, insn_cache, insn_cfc1, insn_cfcmsa, insn_ctc1, insn_ctcmsa, @@ -62,10 +61,10 @@ enum opcode { insn_srlv, insn_subu, insn_sw, insn_sync, insn_syscall, insn_tlbp, insn_tlbr, insn_tlbwi, insn_tlbwr, insn_wait, insn_wsbh, insn_xor, insn_xori, insn_yield, insn_lddir, insn_ldpte, insn_lhu, + insn_invalid /* insn_invalid must be last */ }; struct insn { - enum opcode opcode; u32 match; enum fields fields; }; -- cgit v1.2.3-59-g8ed1b From 1f22d599c9849898ef9e3229434b87438278cccc Mon Sep 17 00:00:00 2001 From: David Daney Date: Tue, 13 Jun 2017 15:28:44 -0700 Subject: MIPS: Correctly define DBSHFL type instruction opcodes. DSHD was incorrectly classified as being BSHFL, and DSHD was missing altogether. Signed-off-by: David Daney Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Matt Redfearn Cc: netdev@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16366/ Signed-off-by: Ralf Baechle --- arch/mips/include/uapi/asm/inst.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/arch/mips/include/uapi/asm/inst.h b/arch/mips/include/uapi/asm/inst.h index b5e46ae872d3..e5f538584b8e 100644 --- a/arch/mips/include/uapi/asm/inst.h +++ b/arch/mips/include/uapi/asm/inst.h @@ -276,11 +276,18 @@ enum lx_func { */ enum bshfl_func { wsbh_op = 0x2, - dshd_op = 0x5, seb_op = 0x10, seh_op = 0x18, }; +/* + * DBSHFL opcodes + */ +enum dbshfl_func { + dsbh_op = 0x2, + dshd_op = 0x5, +}; + /* * MSA minor opcodes. */ -- cgit v1.2.3-59-g8ed1b From dc190129f1c16e025a42a9c3717de7ed47fc6e2f Mon Sep 17 00:00:00 2001 From: David Daney Date: Tue, 13 Jun 2017 15:28:45 -0700 Subject: MIPS: Add some instructions to uasm. Follow on patches for eBPF JIT require these additional instructions: insn_bgtz, insn_blez, insn_break, insn_ddivu, insn_dmultu, insn_dsbh, insn_dshd, insn_dsllv, insn_dsra32, insn_dsrav, insn_dsrlv, insn_lbu, insn_movn, insn_movz, insn_multu, insn_nor, insn_sb, insn_sh, insn_slti, insn_dinsu, insn_lwu ... so, add them. Sort the insn_* enumeration values alphabetically. Signed-off-by: David Daney Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Matt Redfearn Cc: netdev@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16367/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/uasm.h | 30 +++++++++++++++++++++++ arch/mips/mm/uasm-mips.c | 21 ++++++++++++++++ arch/mips/mm/uasm.c | 58 ++++++++++++++++++++++++++++++++++---------- 3 files changed, 96 insertions(+), 13 deletions(-) diff --git a/arch/mips/include/asm/uasm.h b/arch/mips/include/asm/uasm.h index 3748f4d120a5..59dae37f6b8d 100644 --- a/arch/mips/include/asm/uasm.h +++ b/arch/mips/include/asm/uasm.h @@ -72,9 +72,12 @@ Ip_u1u2s3(_beq); Ip_u1u2s3(_beql); Ip_u1s2(_bgez); Ip_u1s2(_bgezl); +Ip_u1s2(_bgtz); +Ip_u1s2(_blez); Ip_u1s2(_bltz); Ip_u1s2(_bltzl); Ip_u1u2s3(_bne); +Ip_u1(_break); Ip_u2s3u1(_cache); Ip_u1u2(_cfc1); Ip_u2u1(_cfcmsa); @@ -82,19 +85,28 @@ Ip_u1u2(_ctc1); Ip_u2u1(_ctcmsa); Ip_u2u1s3(_daddiu); Ip_u3u1u2(_daddu); +Ip_u1u2(_ddivu); Ip_u1(_di); Ip_u2u1msbu3(_dins); Ip_u2u1msbu3(_dinsm); +Ip_u2u1msbu3(_dinsu); Ip_u1u2(_divu); Ip_u1u2u3(_dmfc0); Ip_u1u2u3(_dmtc0); +Ip_u1u2(_dmultu); Ip_u2u1u3(_drotr); Ip_u2u1u3(_drotr32); +Ip_u2u1(_dsbh); +Ip_u2u1(_dshd); Ip_u2u1u3(_dsll); Ip_u2u1u3(_dsll32); +Ip_u3u2u1(_dsllv); Ip_u2u1u3(_dsra); +Ip_u2u1u3(_dsra32); +Ip_u3u2u1(_dsrav); Ip_u2u1u3(_dsrl); Ip_u2u1u3(_dsrl32); +Ip_u3u2u1(_dsrlv); Ip_u3u1u2(_dsubu); Ip_0(_eret); Ip_u2u1msbu3(_ext); @@ -104,6 +116,7 @@ Ip_u1(_jal); Ip_u2u1(_jalr); Ip_u1(_jr); Ip_u2s3u1(_lb); +Ip_u2s3u1(_lbu); Ip_u2s3u1(_ld); Ip_u3u1u2(_ldx); Ip_u2s3u1(_lh); @@ -112,27 +125,35 @@ Ip_u2s3u1(_ll); Ip_u2s3u1(_lld); Ip_u1s2(_lui); Ip_u2s3u1(_lw); +Ip_u2s3u1(_lwu); Ip_u3u1u2(_lwx); Ip_u1u2u3(_mfc0); Ip_u1u2u3(_mfhc0); Ip_u1(_mfhi); Ip_u1(_mflo); +Ip_u3u1u2(_movn); +Ip_u3u1u2(_movz); Ip_u1u2u3(_mtc0); Ip_u1u2u3(_mthc0); Ip_u1(_mthi); Ip_u1(_mtlo); Ip_u3u1u2(_mul); +Ip_u1u2(_multu); +Ip_u3u1u2(_nor); Ip_u3u1u2(_or); Ip_u2u1u3(_ori); Ip_u2s3u1(_pref); Ip_0(_rfe); Ip_u2u1u3(_rotr); +Ip_u2s3u1(_sb); Ip_u2s3u1(_sc); Ip_u2s3u1(_scd); Ip_u2s3u1(_sd); +Ip_u2s3u1(_sh); Ip_u2u1u3(_sll); Ip_u3u2u1(_sllv); Ip_s3s1s2(_slt); +Ip_u2u1s3(_slti); Ip_u2u1s3(_sltiu); Ip_u3u1u2(_sltu); Ip_u2u1u3(_sra); @@ -248,6 +269,15 @@ static inline void uasm_i_dsrl_safe(u32 **p, unsigned int a1, uasm_i_dsrl32(p, a1, a2, a3 - 32); } +static inline void uasm_i_dsra_safe(u32 **p, unsigned int a1, + unsigned int a2, unsigned int a3) +{ + if (a3 < 32) + uasm_i_dsra(p, a1, a2, a3); + else + uasm_i_dsra32(p, a1, a2, a3 - 32); +} + /* Handle relocations. */ struct uasm_reloc { u32 *addr; diff --git a/arch/mips/mm/uasm-mips.c b/arch/mips/mm/uasm-mips.c index f3937e315ba8..3f74f6c1f065 100644 --- a/arch/mips/mm/uasm-mips.c +++ b/arch/mips/mm/uasm-mips.c @@ -59,9 +59,12 @@ static const struct insn const insn_table[insn_invalid] = { [insn_beql] = {M(beql_op, 0, 0, 0, 0, 0), RS | RT | BIMM}, [insn_bgez] = {M(bcond_op, 0, bgez_op, 0, 0, 0), RS | BIMM}, [insn_bgezl] = {M(bcond_op, 0, bgezl_op, 0, 0, 0), RS | BIMM}, + [insn_bgtz] = {M(bgtz_op, 0, 0, 0, 0, 0), RS | BIMM}, + [insn_blez] = {M(blez_op, 0, 0, 0, 0, 0), RS | BIMM}, [insn_bltz] = {M(bcond_op, 0, bltz_op, 0, 0, 0), RS | BIMM}, [insn_bltzl] = {M(bcond_op, 0, bltzl_op, 0, 0, 0), RS | BIMM}, [insn_bne] = {M(bne_op, 0, 0, 0, 0, 0), RS | RT | BIMM}, + [insn_break] = {M(spec_op, 0, 0, 0, 0, break_op), SCIMM}, #ifndef CONFIG_CPU_MIPSR6 [insn_cache] = {M(cache_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, #else @@ -73,19 +76,28 @@ static const struct insn const insn_table[insn_invalid] = { [insn_ctcmsa] = {M(msa_op, 0, msa_ctc_op, 0, 0, msa_elm_op), RD | RE}, [insn_daddiu] = {M(daddiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, [insn_daddu] = {M(spec_op, 0, 0, 0, 0, daddu_op), RS | RT | RD}, + [insn_ddivu] = {M(spec_op, 0, 0, 0, 0, ddivu_op), RS | RT}, [insn_di] = {M(cop0_op, mfmc0_op, 0, 12, 0, 0), RT}, [insn_dins] = {M(spec3_op, 0, 0, 0, 0, dins_op), RS | RT | RD | RE}, [insn_dinsm] = {M(spec3_op, 0, 0, 0, 0, dinsm_op), RS | RT | RD | RE}, + [insn_dinsu] = {M(spec3_op, 0, 0, 0, 0, dinsu_op), RS | RT | RD | RE}, [insn_divu] = {M(spec_op, 0, 0, 0, 0, divu_op), RS | RT}, [insn_dmfc0] = {M(cop0_op, dmfc_op, 0, 0, 0, 0), RT | RD | SET}, [insn_dmtc0] = {M(cop0_op, dmtc_op, 0, 0, 0, 0), RT | RD | SET}, + [insn_dmultu] = {M(spec_op, 0, 0, 0, 0, dmultu_op), RS | RT}, [insn_drotr] = {M(spec_op, 1, 0, 0, 0, dsrl_op), RT | RD | RE}, [insn_drotr32] = {M(spec_op, 1, 0, 0, 0, dsrl32_op), RT | RD | RE}, + [insn_dsbh] = {M(spec3_op, 0, 0, 0, dsbh_op, dbshfl_op), RT | RD}, + [insn_dshd] = {M(spec3_op, 0, 0, 0, dshd_op, dbshfl_op), RT | RD}, [insn_dsll] = {M(spec_op, 0, 0, 0, 0, dsll_op), RT | RD | RE}, [insn_dsll32] = {M(spec_op, 0, 0, 0, 0, dsll32_op), RT | RD | RE}, + [insn_dsllv] = {M(spec_op, 0, 0, 0, 0, dsllv_op), RS | RT | RD}, [insn_dsra] = {M(spec_op, 0, 0, 0, 0, dsra_op), RT | RD | RE}, + [insn_dsra32] = {M(spec_op, 0, 0, 0, 0, dsra32_op), RT | RD | RE}, + [insn_dsrav] = {M(spec_op, 0, 0, 0, 0, dsrav_op), RS | RT | RD}, [insn_dsrl] = {M(spec_op, 0, 0, 0, 0, dsrl_op), RT | RD | RE}, [insn_dsrl32] = {M(spec_op, 0, 0, 0, 0, dsrl32_op), RT | RD | RE}, + [insn_dsrlv] = {M(spec_op, 0, 0, 0, 0, dsrlv_op), RS | RT | RD}, [insn_dsubu] = {M(spec_op, 0, 0, 0, 0, dsubu_op), RS | RT | RD}, [insn_eret] = {M(cop0_op, cop_op, 0, 0, 0, eret_op), 0}, [insn_ext] = {M(spec3_op, 0, 0, 0, 0, ext_op), RS | RT | RD | RE}, @@ -99,6 +111,7 @@ static const struct insn const insn_table[insn_invalid] = { [insn_jr] = {M(spec_op, 0, 0, 0, 0, jalr_op), RS}, #endif [insn_lb] = {M(lb_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_lbu] = {M(lbu_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, [insn_ld] = {M(ld_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, [insn_lddir] = {M(lwc2_op, 0, 0, 0, lddir_op, mult_op), RS | RT | RD}, [insn_ldpte] = {M(lwc2_op, 0, 0, 0, ldpte_op, mult_op), RS | RD}, @@ -114,11 +127,14 @@ static const struct insn const insn_table[insn_invalid] = { #endif [insn_lui] = {M(lui_op, 0, 0, 0, 0, 0), RT | SIMM}, [insn_lw] = {M(lw_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_lwu] = {M(lwu_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, [insn_lwx] = {M(spec3_op, 0, 0, 0, lwx_op, lx_op), RS | RT | RD}, [insn_mfc0] = {M(cop0_op, mfc_op, 0, 0, 0, 0), RT | RD | SET}, [insn_mfhc0] = {M(cop0_op, mfhc0_op, 0, 0, 0, 0), RT | RD | SET}, [insn_mfhi] = {M(spec_op, 0, 0, 0, 0, mfhi_op), RD}, [insn_mflo] = {M(spec_op, 0, 0, 0, 0, mflo_op), RD}, + [insn_movn] = {M(spec_op, 0, 0, 0, 0, movn_op), RS | RT | RD}, + [insn_movz] = {M(spec_op, 0, 0, 0, 0, movz_op), RS | RT | RD}, [insn_mtc0] = {M(cop0_op, mtc_op, 0, 0, 0, 0), RT | RD | SET}, [insn_mthc0] = {M(cop0_op, mthc0_op, 0, 0, 0, 0), RT | RD | SET}, [insn_mthi] = {M(spec_op, 0, 0, 0, 0, mthi_op), RS}, @@ -128,6 +144,8 @@ static const struct insn const insn_table[insn_invalid] = { #else [insn_mul] = {M(spec_op, 0, 0, 0, mult_mul_op, mult_op), RS | RT | RD}, #endif + [insn_multu] = {M(spec_op, 0, 0, 0, 0, multu_op), RS | RT}, + [insn_nor] = {M(spec_op, 0, 0, 0, 0, nor_op), RS | RT | RD}, [insn_or] = {M(spec_op, 0, 0, 0, 0, or_op), RS | RT | RD}, [insn_ori] = {M(ori_op, 0, 0, 0, 0, 0), RS | RT | UIMM}, #ifndef CONFIG_CPU_MIPSR6 @@ -137,6 +155,7 @@ static const struct insn const insn_table[insn_invalid] = { #endif [insn_rfe] = {M(cop0_op, cop_op, 0, 0, 0, rfe_op), 0}, [insn_rotr] = {M(spec_op, 1, 0, 0, 0, srl_op), RT | RD | RE}, + [insn_sb] = {M(sb_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, #ifndef CONFIG_CPU_MIPSR6 [insn_sc] = {M(sc_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, [insn_scd] = {M(scd_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, @@ -145,9 +164,11 @@ static const struct insn const insn_table[insn_invalid] = { [insn_scd] = {M6(spec3_op, 0, 0, 0, scd6_op), RS | RT | SIMM9}, #endif [insn_sd] = {M(sd_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, + [insn_sh] = {M(sh_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, [insn_sll] = {M(spec_op, 0, 0, 0, 0, sll_op), RT | RD | RE}, [insn_sllv] = {M(spec_op, 0, 0, 0, 0, sllv_op), RS | RT | RD}, [insn_slt] = {M(spec_op, 0, 0, 0, 0, slt_op), RS | RT | RD}, + [insn_slti] = {M(slti_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, [insn_sltiu] = {M(sltiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM}, [insn_sltu] = {M(spec_op, 0, 0, 0, 0, sltu_op), RS | RT | RD}, [insn_sra] = {M(spec_op, 0, 0, 0, 0, sra_op), RT | RD | RE}, diff --git a/arch/mips/mm/uasm.c b/arch/mips/mm/uasm.c index f23ed85a0d6c..57570c0649b4 100644 --- a/arch/mips/mm/uasm.c +++ b/arch/mips/mm/uasm.c @@ -47,20 +47,24 @@ enum fields { enum opcode { insn_addiu, insn_addu, insn_and, insn_andi, insn_bbit0, insn_bbit1, - insn_beq, insn_beql, insn_bgez, insn_bgezl, insn_bltz, insn_bltzl, - insn_bne, insn_cache, insn_cfc1, insn_cfcmsa, insn_ctc1, insn_ctcmsa, - insn_daddiu, insn_daddu, insn_di, insn_dins, insn_dinsm, insn_divu, - insn_dmfc0, insn_dmtc0, insn_drotr, insn_drotr32, insn_dsll, - insn_dsll32, insn_dsra, insn_dsrl, insn_dsrl32, insn_dsubu, insn_eret, - insn_ext, insn_ins, insn_j, insn_jal, insn_jalr, insn_jr, insn_lb, - insn_ld, insn_ldx, insn_lh, insn_ll, insn_lld, insn_lui, insn_lw, - insn_lwx, insn_mfc0, insn_mfhc0, insn_mfhi, insn_mflo, insn_mtc0, - insn_mthc0, insn_mthi, insn_mtlo, insn_mul, insn_or, insn_ori, - insn_pref, insn_rfe, insn_rotr, insn_sc, insn_scd, insn_sd, insn_sll, - insn_sllv, insn_slt, insn_sltiu, insn_sltu, insn_sra, insn_srl, + insn_beq, insn_beql, insn_bgez, insn_bgezl, insn_bgtz, insn_blez, + insn_bltz, insn_bltzl, insn_bne, insn_break, insn_cache, insn_cfc1, + insn_cfcmsa, insn_ctc1, insn_ctcmsa, insn_daddiu, insn_daddu, insn_ddivu, + insn_di, insn_dins, insn_dinsm, insn_dinsu, insn_divu, insn_dmfc0, + insn_dmtc0, insn_dmultu, insn_drotr, insn_drotr32, insn_dsbh, insn_dshd, + insn_dsll, insn_dsll32, insn_dsllv, insn_dsra, insn_dsra32, insn_dsrav, + insn_dsrl, insn_dsrl32, insn_dsrlv, insn_dsubu, insn_eret, insn_ext, + insn_ins, insn_j, insn_jal, insn_jalr, insn_jr, insn_lb, insn_lbu, + insn_ld, insn_lddir, insn_ldpte, insn_ldx, insn_lh, insn_lhu, + insn_ll, insn_lld, insn_lui, insn_lw, insn_lwu, insn_lwx, insn_mfc0, + insn_mfhc0, insn_mfhi, insn_mflo, insn_movn, insn_movz, insn_mtc0, + insn_mthc0, insn_mthi, insn_mtlo, insn_mul, insn_multu, insn_nor, + insn_or, insn_ori, insn_pref, insn_rfe, insn_rotr, insn_sb, + insn_sc, insn_scd, insn_sd, insn_sh, insn_sll, insn_sllv, + insn_slt, insn_slti, insn_sltiu, insn_sltu, insn_sra, insn_srl, insn_srlv, insn_subu, insn_sw, insn_sync, insn_syscall, insn_tlbp, insn_tlbr, insn_tlbwi, insn_tlbwr, insn_wait, insn_wsbh, insn_xor, - insn_xori, insn_yield, insn_lddir, insn_ldpte, insn_lhu, + insn_xori, insn_yield, insn_invalid /* insn_invalid must be last */ }; @@ -214,6 +218,13 @@ Ip_u2u1msbu3(op) \ } \ UASM_EXPORT_SYMBOL(uasm_i##op); +#define I_u2u1msb32msb3(op) \ +Ip_u2u1msbu3(op) \ +{ \ + build_insn(buf, insn##op, b, a, c+d-33, c-32); \ +} \ +UASM_EXPORT_SYMBOL(uasm_i##op); + #define I_u2u1msbdu3(op) \ Ip_u2u1msbu3(op) \ { \ @@ -264,25 +275,36 @@ I_u1u2s3(_beq) I_u1u2s3(_beql) I_u1s2(_bgez) I_u1s2(_bgezl) +I_u1s2(_bgtz) +I_u1s2(_blez) I_u1s2(_bltz) I_u1s2(_bltzl) I_u1u2s3(_bne) +I_u1(_break) I_u2s3u1(_cache) I_u1u2(_cfc1) I_u2u1(_cfcmsa) I_u1u2(_ctc1) I_u2u1(_ctcmsa) +I_u1u2(_ddivu) I_u1u2u3(_dmfc0) I_u1u2u3(_dmtc0) +I_u1u2(_dmultu) I_u2u1s3(_daddiu) I_u3u1u2(_daddu) I_u1(_di); I_u1u2(_divu) +I_u2u1(_dsbh); +I_u2u1(_dshd); I_u2u1u3(_dsll) I_u2u1u3(_dsll32) +I_u3u2u1(_dsllv) I_u2u1u3(_dsra) +I_u2u1u3(_dsra32) +I_u3u2u1(_dsrav) I_u2u1u3(_dsrl) I_u2u1u3(_dsrl32) +I_u3u2u1(_dsrlv) I_u2u1u3(_drotr) I_u2u1u3(_drotr32) I_u3u1u2(_dsubu) @@ -294,6 +316,7 @@ I_u1(_jal) I_u2u1(_jalr) I_u1(_jr) I_u2s3u1(_lb) +I_u2s3u1(_lbu) I_u2s3u1(_ld) I_u2s3u1(_lh) I_u2s3u1(_lhu) @@ -301,8 +324,11 @@ I_u2s3u1(_ll) I_u2s3u1(_lld) I_u1s2(_lui) I_u2s3u1(_lw) +I_u2s3u1(_lwu) I_u1u2u3(_mfc0) I_u1u2u3(_mfhc0) +I_u3u1u2(_movn) +I_u3u1u2(_movz) I_u1(_mfhi) I_u1(_mflo) I_u1u2u3(_mtc0) @@ -310,15 +336,20 @@ I_u1u2u3(_mthc0) I_u1(_mthi) I_u1(_mtlo) I_u3u1u2(_mul) -I_u2u1u3(_ori) +I_u1u2(_multu) +I_u3u1u2(_nor) I_u3u1u2(_or) +I_u2u1u3(_ori) I_0(_rfe) +I_u2s3u1(_sb) I_u2s3u1(_sc) I_u2s3u1(_scd) I_u2s3u1(_sd) +I_u2s3u1(_sh) I_u2u1u3(_sll) I_u3u2u1(_sllv) I_s3s1s2(_slt) +I_u2u1s3(_slti) I_u2u1s3(_sltiu) I_u3u1u2(_sltu) I_u2u1u3(_sra) @@ -339,6 +370,7 @@ I_u2u1u3(_xori) I_u2u1(_yield) I_u2u1msbu3(_dins); I_u2u1msb32u3(_dinsm); +I_u2u1msb32msb3(_dinsu); I_u1(_syscall); I_u1u2s3(_bbit0); I_u1u2s3(_bbit1); -- cgit v1.2.3-59-g8ed1b From f381bf6d82f032b7410185b35d000ea370ac706b Mon Sep 17 00:00:00 2001 From: David Daney Date: Tue, 13 Jun 2017 15:28:46 -0700 Subject: MIPS: Add support for eBPF JIT. Since the eBPF machine has 64-bit registers, we only support this in 64-bit kernels. As of the writing of this commit log test-bpf is showing: test_bpf: Summary: 316 PASSED, 0 FAILED, [308/308 JIT'ed] All current test cases are successfully compiled. Many examples in samples/bpf are usable, specifically tracex5 which uses tail calls works. Signed-off-by: David Daney Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Markos Chandras Cc: Matt Redfearn Cc: netdev@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16369/ Signed-off-by: Ralf Baechle --- arch/mips/Kconfig | 12 +++++++++++- arch/mips/net/Makefile | 3 ++- 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 0b15978c0f88..9891a1285f25 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -33,7 +33,8 @@ config MIPS select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE if CPU_SUPPORTS_HUGEPAGES && 64BIT - select HAVE_CBPF_JIT if !CPU_MICROMIPS + select HAVE_CBPF_JIT if (!64BIT && !CPU_MICROMIPS) + select HAVE_EBPF_JIT if (64BIT && !CPU_MICROMIPS) select HAVE_CC_STACKPROTECTOR select HAVE_CONTEXT_TRACKING select HAVE_COPY_THREAD_TLS @@ -1178,6 +1179,15 @@ config SYS_SUPPORTS_RELOCATABLE The platform must provide plat_get_fdt() if it selects CONFIG_USE_OF to allow access to command line and entropy sources. +config MIPS_CBPF_JIT + def_bool y + depends on BPF_JIT && HAVE_CBPF_JIT + +config MIPS_EBPF_JIT + def_bool y + depends on BPF_JIT && HAVE_EBPF_JIT + + # # Endianness selection. Sufficiently obscure so many users don't know what to # answer,so we try hard to limit the available choices. Also the use of a diff --git a/arch/mips/net/Makefile b/arch/mips/net/Makefile index 8c2771401f54..47d678416715 100644 --- a/arch/mips/net/Makefile +++ b/arch/mips/net/Makefile @@ -1,3 +1,4 @@ # MIPS networking code -obj-$(CONFIG_BPF_JIT) += bpf_jit.o bpf_jit_asm.o +obj-$(CONFIG_MIPS_CBPF_JIT) += bpf_jit.o bpf_jit_asm.o +obj-$(CONFIG_MIPS_EBPF_JIT) += ebpf_jit.o -- cgit v1.2.3-59-g8ed1b From 669c4092225f0ed5df12ebee654581b558a5e3ed Mon Sep 17 00:00:00 2001 From: David Daney Date: Tue, 13 Jun 2017 15:28:47 -0700 Subject: MIPS: Give __secure_computing() access to syscall arguments. KProbes of __seccomp_filter() are not very useful without access to the syscall arguments. Do what x86 does, and populate a struct seccomp_data to be passed to __secure_computing(). This allows samples/bpf/tracex5 to extract a sensible trace. Signed-off-by: David Daney Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Matt Redfearn Cc: netdev@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16368/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/ptrace.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index 6931fe722a0b..ba3b1f771256 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -868,8 +868,26 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall) tracehook_report_syscall_entry(regs)) return -1; - if (secure_computing(NULL) == -1) - return -1; +#ifdef CONFIG_SECCOMP + if (unlikely(test_thread_flag(TIF_SECCOMP))) { + int ret, i; + struct seccomp_data sd; + + sd.nr = syscall; + sd.arch = syscall_get_arch(); + for (i = 0; i < 6; i++) { + unsigned long v, r; + + r = mips_get_syscall_arg(&v, current, regs, i); + sd.args[i] = r ? 0 : v; + } + sd.instruction_pointer = KSTK_EIP(current); + + ret = __secure_computing(&sd); + if (ret == -1) + return ret; + } +#endif if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_enter(regs, regs->regs[2]); -- cgit v1.2.3-59-g8ed1b From 498e9ade6593887397844eb8ac9d811252f7239e Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Tue, 13 Jun 2017 10:01:08 -0700 Subject: MIPS: Perform post-DMA cache flushes on systems with MAARs Recent CPUs from Imagination Technologies such as the I6400 or P6600 are able to speculatively fetch data from memory into caches. This means that if used in a system with non-coherent DMA they require that caches be invalidated after a device performs DMA, and before the CPU reads the DMA'd data, in order to ensure that stale values weren't speculatively prefetched. Such CPUs also introduced Memory Accessibility Attribute Registers (MAARs) in order to control the regions in which they are allowed to speculate. Thus we can use the presence of MAARs as a good indication that the CPU requires the above cache maintenance. Use the presence of MAARs to determine the result of cpu_needs_post_dma_flush() in the default case, in order to handle these recent CPUs correctly. Note that the return type of cpu_needs_post_dma_flush() is changed to bool, such that it's clearer what's happening when cpu_has_maar is cast to bool for the return value. If this patch were backported to a pre-v4.7 kernel then MIPS_CPU_MAAR was 1ull<<34, so when cast to an int we would incorrectly return 0. It so happens that MIPS_CPU_MAAR is currently 1ull<<30, so when truncated to an int gives a non-zero value anyway, but even so the implicit conversion from long long int to bool makes it clearer to understand what will happen than the implicit conversion from long long int to int would. The bool return type also fits this usage better semantically, so seems like an all-round win. Thanks to Ed for spotting the issue for pre-v4.7 kernels & suggesting the return type change. Signed-off-by: Paul Burton Reviewed-by: Bryan O'Donoghue Tested-by: Bryan O'Donoghue Cc: Ed Blake Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16363/ Signed-off-by: Ralf Baechle --- arch/mips/mm/dma-default.c | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-) diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c index fe8df14b6169..e08598c70b3e 100644 --- a/arch/mips/mm/dma-default.c +++ b/arch/mips/mm/dma-default.c @@ -68,12 +68,25 @@ static inline struct page *dma_addr_to_page(struct device *dev, * systems and only the R10000 and R12000 are used in such systems, the * SGI IP28 Indigo² rsp. SGI IP32 aka O2. */ -static inline int cpu_needs_post_dma_flush(struct device *dev) +static inline bool cpu_needs_post_dma_flush(struct device *dev) { - return !plat_device_is_coherent(dev) && - (boot_cpu_type() == CPU_R10000 || - boot_cpu_type() == CPU_R12000 || - boot_cpu_type() == CPU_BMIPS5000); + if (plat_device_is_coherent(dev)) + return false; + + switch (boot_cpu_type()) { + case CPU_R10000: + case CPU_R12000: + case CPU_BMIPS5000: + return true; + + default: + /* + * Presence of MAARs suggests that the CPU supports + * speculatively prefetching data, and therefore requires + * the post-DMA flush/invalidate. + */ + return cpu_has_maar; + } } static gfp_t massage_gfp_flags(const struct device *dev, gfp_t gfp) -- cgit v1.2.3-59-g8ed1b From 859aeb1b0dd1b9c6ff3d78f6cb913a73af9da247 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 2 Jun 2017 12:39:04 -0700 Subject: MIPS: Probe the I6500 CPU Introduce the I6500 PRID & probe it just the same way as I6400. The MIPS I6500 is the latest in Imagination Technologies' I-Class range of CPUs, with a focus on scalability & heterogeneity. It introduces the notion of multiple clusters to the MIPS Coherent Processing System, allowing for a far higher total number of cores & threads in a system when compared with its predecessors. Clusters don't need to be identical, and may contain differing numbers of cores & IOCUs, or cores with differing properties. This patch alone adds the basic support for booting Linux on an I6500 CPU without support for any of its new functionality, for which support will be introduced in further patches. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16190/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/cpu-type.h | 1 + arch/mips/include/asm/cpu.h | 3 ++- arch/mips/kernel/cpu-probe.c | 5 +++++ arch/mips/mm/c-r4k.c | 2 ++ 4 files changed, 10 insertions(+), 1 deletion(-) diff --git a/arch/mips/include/asm/cpu-type.h b/arch/mips/include/asm/cpu-type.h index bdd6dc18e65c..175fe565f4e1 100644 --- a/arch/mips/include/asm/cpu-type.h +++ b/arch/mips/include/asm/cpu-type.h @@ -84,6 +84,7 @@ static inline int __pure __get_cpu_type(const int cpu_type) #ifdef CONFIG_SYS_HAS_CPU_MIPS64_R6 case CPU_I6400: + case CPU_I6500: case CPU_P6600: #endif diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h index 98f59307e6a3..3069359b0120 100644 --- a/arch/mips/include/asm/cpu.h +++ b/arch/mips/include/asm/cpu.h @@ -124,6 +124,7 @@ #define PRID_IMP_P5600 0xa800 #define PRID_IMP_I6400 0xa900 #define PRID_IMP_M6250 0xab00 +#define PRID_IMP_I6500 0xb000 /* * These are the PRID's for when 23:16 == PRID_COMP_SIBYTE @@ -322,7 +323,7 @@ enum cpu_type_enum { */ CPU_5KC, CPU_5KE, CPU_20KC, CPU_25KF, CPU_SB1, CPU_SB1A, CPU_LOONGSON2, CPU_LOONGSON3, CPU_CAVIUM_OCTEON, CPU_CAVIUM_OCTEON_PLUS, - CPU_CAVIUM_OCTEON2, CPU_CAVIUM_OCTEON3, CPU_XLR, CPU_XLP, + CPU_CAVIUM_OCTEON2, CPU_CAVIUM_OCTEON3, CPU_XLR, CPU_XLP, CPU_I6500, CPU_QEMU_GENERIC, diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index 1aba27786bd5..353ade2c130a 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -564,6 +564,7 @@ static int set_ftlb_enable(struct cpuinfo_mips *c, enum ftlb_flags flags) back_to_back_c0_hazard(); break; case CPU_I6400: + case CPU_I6500: /* There's no way to disable the FTLB */ if (!(flags & FTLB_EN)) return 1; @@ -1635,6 +1636,10 @@ static inline void cpu_probe_mips(struct cpuinfo_mips *c, unsigned int cpu) c->cputype = CPU_I6400; __cpu_name[cpu] = "MIPS I6400"; break; + case PRID_IMP_I6500: + c->cputype = CPU_I6500; + __cpu_name[cpu] = "MIPS I6500"; + break; case PRID_IMP_M5150: c->cputype = CPU_M5150; __cpu_name[cpu] = "MIPS M5150"; diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index 3fe99cb271a9..81d6a15c93d0 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -1453,6 +1453,7 @@ static void probe_pcache(void) case CPU_20KC: case CPU_25KF: case CPU_I6400: + case CPU_I6500: case CPU_SB1: case CPU_SB1A: case CPU_XLR: @@ -1512,6 +1513,7 @@ static void probe_pcache(void) case CPU_ALCHEMY: case CPU_I6400: + case CPU_I6500: c->icache.flags |= MIPS_CACHE_IC_F_DC; break; -- cgit v1.2.3-59-g8ed1b From 736add2412a7740d9d8b56fb83440e94b01bc1b4 Mon Sep 17 00:00:00 2001 From: Marcin Nowakowski Date: Tue, 13 Jun 2017 11:23:39 +0200 Subject: MIPS: perf: add I6500 handling Add a definition of the perf registers for the new I6500 core. Since I6500 has the same event definitions as I6400, re-use the existing i6400 map structures by renaming them to a slightly more generic 'i6x00_***_map'. Signed-off-by: Marcin Nowakowski Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16362/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/perf_event_mipsxx.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c index f3e301f95aef..9e6c74bf66c4 100644 --- a/arch/mips/kernel/perf_event_mipsxx.c +++ b/arch/mips/kernel/perf_event_mipsxx.c @@ -814,7 +814,7 @@ static const struct mips_perf_event mipsxxcore_event_map2 [PERF_COUNT_HW_BRANCH_MISSES] = { 0x27, CNTR_ODD, T }, }; -static const struct mips_perf_event i6400_event_map[PERF_COUNT_HW_MAX] = { +static const struct mips_perf_event i6x00_event_map[PERF_COUNT_HW_MAX] = { [PERF_COUNT_HW_CPU_CYCLES] = { 0x00, CNTR_EVEN | CNTR_ODD }, [PERF_COUNT_HW_INSTRUCTIONS] = { 0x01, CNTR_EVEN | CNTR_ODD }, /* These only count dcache, not icache */ @@ -1014,7 +1014,7 @@ static const struct mips_perf_event mipsxxcore_cache_map2 }, }; -static const struct mips_perf_event i6400_cache_map +static const struct mips_perf_event i6x00_cache_map [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = { @@ -1610,6 +1610,7 @@ static const struct mips_perf_event *mipsxx_pmu_map_raw_event(u64 config) #endif break; case CPU_I6400: + case CPU_I6500: /* 8-bit event numbers */ base_id = config & 0xff; raw_event.cntr_mask = CNTR_EVEN | CNTR_ODD; @@ -1770,8 +1771,13 @@ init_hw_perf_events(void) break; case CPU_I6400: mipspmu.name = "mips/I6400"; - mipspmu.general_event_map = &i6400_event_map; - mipspmu.cache_event_map = &i6400_cache_map; + mipspmu.general_event_map = &i6x00_event_map; + mipspmu.cache_event_map = &i6x00_cache_map; + break; + case CPU_I6500: + mipspmu.name = "mips/I6500"; + mipspmu.general_event_map = &i6x00_event_map; + mipspmu.cache_event_map = &i6x00_cache_map; break; case CPU_1004K: mipspmu.name = "mips/1004K"; -- cgit v1.2.3-59-g8ed1b From 2ec420b26f7b6ff332393f0bb5a7d245f7ad87f0 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Wed, 31 May 2017 16:19:47 +0100 Subject: MIPS: Fix mips_atomic_set() retry condition The inline asm retry check in the MIPS_ATOMIC_SET operation of the sysmips system call has been backwards since commit f1e39a4a616c ("MIPS: Rewrite sysmips(MIPS_ATOMIC_SET, ...) in C with inline assembler") merged in v2.6.32, resulting in the non R10000_LLSC_WAR case retrying until the operation was inatomic, before returning the new value that was probably just written multiple times instead of the old value. Invert the branch condition to fix that particular issue. Fixes: f1e39a4a616c ("MIPS: Rewrite sysmips(MIPS_ATOMIC_SET, ...) in C with inline assembler") Signed-off-by: James Hogan Cc: linux-mips@linux-mips.org Cc: stable@vger.kernel.org Patchwork: https://patchwork.linux-mips.org/patch/16148/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/syscall.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index 1dfa7f5796c7..95e1b300ac0d 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -134,7 +134,7 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new) "1: ll %[old], (%[addr]) \n" " move %[tmp], %[new] \n" "2: sc %[tmp], (%[addr]) \n" - " bnez %[tmp], 4f \n" + " beqz %[tmp], 4f \n" "3: \n" " .insn \n" " .subsection 2 \n" -- cgit v1.2.3-59-g8ed1b From 49955d84cd9ccdca5a16a495e448e1a06fad9e49 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Wed, 31 May 2017 16:19:48 +0100 Subject: MIPS: Save static registers before sysmips The MIPS sysmips system call handler may return directly from the MIPS_ATOMIC_SET case (mips_atomic_set()) to syscall_exit. This path restores the static (callee saved) registers, however they won't have been saved on entry to the system call. Use the save_static_function() macro to create a __sys_sysmips wrapper function which saves the static registers before calling sys_sysmips, so that the correct static register state is restored by syscall_exit. Fixes: f1e39a4a616c ("MIPS: Rewrite sysmips(MIPS_ATOMIC_SET, ...) in C with inline assembler") Signed-off-by: James Hogan Cc: linux-mips@linux-mips.org Cc: stable@vger.kernel.org Patchwork: https://patchwork.linux-mips.org/patch/16149/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/scall32-o32.S | 2 +- arch/mips/kernel/scall64-64.S | 2 +- arch/mips/kernel/scall64-n32.S | 2 +- arch/mips/kernel/scall64-o32.S | 2 +- arch/mips/kernel/syscall.c | 6 ++++++ 5 files changed, 10 insertions(+), 4 deletions(-) diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index 80ed68b2c95e..27c2f90eeb21 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -371,7 +371,7 @@ EXPORT(sys_call_table) PTR sys_writev PTR sys_cacheflush PTR sys_cachectl - PTR sys_sysmips + PTR __sys_sysmips PTR sys_ni_syscall /* 4150 */ PTR sys_getsid PTR sys_fdatasync diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S index 49765b44aa9b..65d5aeeb9bdb 100644 --- a/arch/mips/kernel/scall64-64.S +++ b/arch/mips/kernel/scall64-64.S @@ -311,7 +311,7 @@ EXPORT(sys_call_table) PTR sys_sched_getaffinity PTR sys_cacheflush PTR sys_cachectl - PTR sys_sysmips + PTR __sys_sysmips PTR sys_io_setup /* 5200 */ PTR sys_io_destroy PTR sys_io_getevents diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 90bad2d1b2d3..cbf190ef9e8a 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -302,7 +302,7 @@ EXPORT(sysn32_call_table) PTR compat_sys_sched_getaffinity PTR sys_cacheflush PTR sys_cachectl - PTR sys_sysmips + PTR __sys_sysmips PTR compat_sys_io_setup /* 6200 */ PTR sys_io_destroy PTR compat_sys_io_getevents diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 2dd70bd104e1..c30bc520885f 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -371,7 +371,7 @@ EXPORT(sys32_call_table) PTR compat_sys_writev PTR sys_cacheflush PTR sys_cachectl - PTR sys_sysmips + PTR __sys_sysmips PTR sys_ni_syscall /* 4150 */ PTR sys_getsid PTR sys_fdatasync diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index 95e1b300ac0d..3e5d82e744ac 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -192,6 +192,12 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new) unreachable(); } +/* + * mips_atomic_set() normally returns directly via syscall_exit potentially + * clobbering static registers, so be sure to preserve them. + */ +save_static_function(sys_sysmips); + SYSCALL_DEFINE3(sysmips, long, cmd, long, arg1, long, arg2) { switch (cmd) { -- cgit v1.2.3-59-g8ed1b From 4915e1b043d6286928207b1f6968197b50407294 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Wed, 31 May 2017 16:19:49 +0100 Subject: MIPS: Fix mips_atomic_set() with EVA EVA linked loads (LLE) and conditional stores (SCE) should be used on EVA kernels for the MIPS_ATOMIC_SET operation of the sysmips system call, or else the atomic set will apply to the kernel view of the virtual address space (potentially unmapped on EVA kernels) rather than the user view (TLB mapped). Signed-off-by: James Hogan Cc: linux-mips@linux-mips.org Cc: # 3.15.x- Patchwork: https://patchwork.linux-mips.org/patch/16151/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/syscall.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index 3e5d82e744ac..863f958c126c 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -29,6 +29,7 @@ #include #include +#include #include #include #include @@ -131,9 +132,11 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new) __asm__ __volatile__ ( " .set "MIPS_ISA_ARCH_LEVEL" \n" " li %[err], 0 \n" - "1: ll %[old], (%[addr]) \n" + "1: \n" + user_ll("%[old]", "(%[addr])") " move %[tmp], %[new] \n" - "2: sc %[tmp], (%[addr]) \n" + "2: \n" + user_sc("%[tmp]", "(%[addr])") " beqz %[tmp], 4f \n" "3: \n" " .insn \n" -- cgit v1.2.3-59-g8ed1b From 203e090ade7357101e40a3d3aad3af77653da8df Mon Sep 17 00:00:00 2001 From: James Hogan Date: Wed, 31 May 2017 16:19:50 +0100 Subject: MIPS: Branch straight to ll in mips_atomic_set() Adjust the atomic loop in the MIPS_ATOMIC_SET operation of the sysmips system call to branch straight back to the linked load rather than jumping via a different subsection (whose purpose remains a mystery to me). Signed-off-by: James Hogan Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16150/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/syscall.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index 863f958c126c..58c6f634b550 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -137,13 +137,9 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new) " move %[tmp], %[new] \n" "2: \n" user_sc("%[tmp]", "(%[addr])") - " beqz %[tmp], 4f \n" + " beqz %[tmp], 1b \n" "3: \n" " .insn \n" - " .subsection 2 \n" - "4: b 1b \n" - " .previous \n" - " \n" " .section .fixup,\"ax\" \n" "5: li %[err], %[efault] \n" " j 3b \n" -- cgit v1.2.3-59-g8ed1b From efe4a1acdc2c70da9025cf405112667e5580a572 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 2 Jun 2017 12:29:58 -0700 Subject: MIPS: SEAD-3: Remove GIC timer from DT The SEAD-3 board doesn't & never has configured the GIC frequency. Remove the timer node from the DT in order to avoid attempting to probe the GIC clocksource/clockevent driver which will produce error messages such as these during boot: [ 0.000000] GIC frequency not specified. [ 0.000000] Failed to initialize '/interrupt-controller@1b1c0000/timer': -22 [ 0.000000] clocksource_probe: no matching clocksources found Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16188/ Signed-off-by: Ralf Baechle --- arch/mips/boot/dts/mti/sead3.dts | 5 ----- 1 file changed, 5 deletions(-) diff --git a/arch/mips/boot/dts/mti/sead3.dts b/arch/mips/boot/dts/mti/sead3.dts index b112879a5d9d..1bf58f841bbb 100644 --- a/arch/mips/boot/dts/mti/sead3.dts +++ b/arch/mips/boot/dts/mti/sead3.dts @@ -54,11 +54,6 @@ * controller & should be probed first. */ interrupt-parent = <&cpu_intc>; - - timer { - compatible = "mti,gic-timer"; - interrupts = ; - }; }; ehci@1b200000 { -- cgit v1.2.3-59-g8ed1b From 571b7e69f7f775c531ffaf73ae476b1e46150f41 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 2 Jun 2017 12:29:51 -0700 Subject: MIPS: generic/yamon-dt: Pull YAMON DT shim code out of SEAD-3 board In preparation for supporting other YAMON-using boards (Malta) & sharing code to translate information from YAMON into device tree properties, pull the code doing so for the kernel command line, system memory & serial configuration out of the SEAD-3 board code. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16181/ Signed-off-by: Ralf Baechle --- arch/mips/generic/Kconfig | 8 ++ arch/mips/generic/Makefile | 1 + arch/mips/generic/board-sead3.c | 178 +----------------------------------- arch/mips/generic/yamon-dt.c | 190 +++++++++++++++++++++++++++++++++++++++ arch/mips/include/asm/yamon-dt.h | 48 ++++++++++ 5 files changed, 251 insertions(+), 174 deletions(-) create mode 100644 arch/mips/generic/yamon-dt.c create mode 100644 arch/mips/include/asm/yamon-dt.h diff --git a/arch/mips/generic/Kconfig b/arch/mips/generic/Kconfig index a606b3f9196c..446b7c68133d 100644 --- a/arch/mips/generic/Kconfig +++ b/arch/mips/generic/Kconfig @@ -9,9 +9,17 @@ config LEGACY_BOARDS kernel is booted without being provided with an FDT via the UHI boot protocol. +config YAMON_DT_SHIM + bool + help + Select this from your board if the board uses the YAMON bootloader + and you wish to include code which helps translate various + YAMON-provided environment variables into a device tree properties. + config LEGACY_BOARD_SEAD3 bool "Support MIPS SEAD-3 boards" select LEGACY_BOARDS + select YAMON_DT_SHIM help Enable this to include support for booting on MIPS SEAD-3 FPGA-based development boards, which boot using a legacy boot protocol. diff --git a/arch/mips/generic/Makefile b/arch/mips/generic/Makefile index acb9b6d62b16..56b3ea565ed9 100644 --- a/arch/mips/generic/Makefile +++ b/arch/mips/generic/Makefile @@ -12,5 +12,6 @@ obj-y += init.o obj-y += irq.o obj-y += proc.o +obj-$(CONFIG_YAMON_DT_SHIM) += yamon-dt.o obj-$(CONFIG_LEGACY_BOARD_SEAD3) += board-sead3.o obj-$(CONFIG_KEXEC) += kexec.o diff --git a/arch/mips/generic/board-sead3.c b/arch/mips/generic/board-sead3.c index f4ae0584a33b..63fdc98738ba 100644 --- a/arch/mips/generic/board-sead3.c +++ b/arch/mips/generic/board-sead3.c @@ -17,6 +17,7 @@ #include #include #include +#include #define SEAD_CONFIG CKSEG1ADDR(0x1b100110) #define SEAD_CONFIG_GIC_PRESENT BIT(1) @@ -33,98 +34,6 @@ static __init bool sead3_detect(void) return (rev & MIPS_REVISION_MACHINE) == MIPS_REVISION_MACHINE_SEAD3; } -static __init int append_cmdline(void *fdt) -{ - int err, chosen_off; - - /* find or add chosen node */ - chosen_off = fdt_path_offset(fdt, "/chosen"); - if (chosen_off == -FDT_ERR_NOTFOUND) - chosen_off = fdt_path_offset(fdt, "/chosen@0"); - if (chosen_off == -FDT_ERR_NOTFOUND) - chosen_off = fdt_add_subnode(fdt, 0, "chosen"); - if (chosen_off < 0) { - pr_err("Unable to find or add DT chosen node: %d\n", - chosen_off); - return chosen_off; - } - - err = fdt_setprop_string(fdt, chosen_off, "bootargs", fw_getcmdline()); - if (err) { - pr_err("Unable to set bootargs property: %d\n", err); - return err; - } - - return 0; -} - -static __init int append_memory(void *fdt) -{ - unsigned long phys_memsize, memsize; - __be32 mem_array[2]; - int err, mem_off; - char *var; - - /* find memory size from the bootloader environment */ - var = fw_getenv("memsize"); - if (var) { - err = kstrtoul(var, 0, &phys_memsize); - if (err) { - pr_err("Failed to read memsize env variable '%s'\n", - var); - return -EINVAL; - } - } else { - pr_warn("The bootloader didn't provide memsize: defaulting to 32MB\n"); - phys_memsize = 32 << 20; - } - - /* default to using all available RAM */ - memsize = phys_memsize; - - /* allow the user to override the usable memory */ - var = strstr(arcs_cmdline, "memsize="); - if (var) - memsize = memparse(var + strlen("memsize="), NULL); - - /* if the user says there's more RAM than we thought, believe them */ - phys_memsize = max_t(unsigned long, phys_memsize, memsize); - - /* find or add a memory node */ - mem_off = fdt_path_offset(fdt, "/memory"); - if (mem_off == -FDT_ERR_NOTFOUND) - mem_off = fdt_add_subnode(fdt, 0, "memory"); - if (mem_off < 0) { - pr_err("Unable to find or add memory DT node: %d\n", mem_off); - return mem_off; - } - - err = fdt_setprop_string(fdt, mem_off, "device_type", "memory"); - if (err) { - pr_err("Unable to set memory node device_type: %d\n", err); - return err; - } - - mem_array[0] = 0; - mem_array[1] = cpu_to_be32(phys_memsize); - err = fdt_setprop(fdt, mem_off, "reg", mem_array, sizeof(mem_array)); - if (err) { - pr_err("Unable to set memory regs property: %d\n", err); - return err; - } - - mem_array[0] = 0; - mem_array[1] = cpu_to_be32(memsize); - err = fdt_setprop(fdt, mem_off, "linux,usable-memory", - mem_array, sizeof(mem_array)); - if (err) { - pr_err("Unable to set linux,usable-memory property: %d\n", err); - return err; - } - - return 0; -} - static __init int remove_gic(void *fdt) { const unsigned int cpu_ehci_int = 2; @@ -214,85 +123,6 @@ static __init int remove_gic(void *fdt) return 0; } -static __init int serial_config(void *fdt) -{ - const char *yamontty, *mode_var; - char mode_var_name[9], path[18], parity; - unsigned int uart, baud, stop_bits; - bool hw_flow; - int chosen_off, err; - - yamontty = fw_getenv("yamontty"); - if (!yamontty || !strcmp(yamontty, "tty0")) { - uart = 0; - } else if (!strcmp(yamontty, "tty1")) { - uart = 1; - } else { - pr_warn("yamontty environment variable '%s' invalid\n", - yamontty); - uart = 0; - } - - baud = stop_bits = 0; - parity = 0; - hw_flow = false; - - snprintf(mode_var_name, sizeof(mode_var_name), "modetty%u", uart); - mode_var = fw_getenv(mode_var_name); - if (mode_var) { - while (mode_var[0] >= '0' && mode_var[0] <= '9') { - baud *= 10; - baud += mode_var[0] - '0'; - mode_var++; - } - if (mode_var[0] == ',') - mode_var++; - if (mode_var[0]) - parity = mode_var[0]; - if (mode_var[0] == ',') - mode_var++; - if (mode_var[0]) - stop_bits = mode_var[0] - '0'; - if (mode_var[0] == ',') - mode_var++; - if (!strcmp(mode_var, "hw")) - hw_flow = true; - } - - if (!baud) - baud = 38400; - - if (parity != 'e' && parity != 'n' && parity != 'o') - parity = 'n'; - - if (stop_bits != 7 && stop_bits != 8) - stop_bits = 8; - - WARN_ON(snprintf(path, sizeof(path), "uart%u:%u%c%u%s", - uart, baud, parity, stop_bits, - hw_flow ? "r" : "") >= sizeof(path)); - - /* find or add chosen node */ - chosen_off = fdt_path_offset(fdt, "/chosen"); - if (chosen_off == -FDT_ERR_NOTFOUND) - chosen_off = fdt_path_offset(fdt, "/chosen@0"); - if (chosen_off == -FDT_ERR_NOTFOUND) - chosen_off = fdt_add_subnode(fdt, 0, "chosen"); - if (chosen_off < 0) { - pr_err("Unable to find or add DT chosen node: %d\n", - chosen_off); - return chosen_off; - } - - err = fdt_setprop_string(fdt, chosen_off, "stdout-path", path); - if (err) { - pr_err("Unable to set stdout-path property: %d\n", err); - return err; - } - - return 0; -} - static __init const void *sead3_fixup_fdt(const void *fdt, const void *match_data) { @@ -311,11 +141,11 @@ static __init const void *sead3_fixup_fdt(const void *fdt, if (err) panic("Unable to open FDT: %d", err); - err = append_cmdline(fdt_buf); + err = yamon_dt_append_cmdline(fdt_buf); if (err) panic("Unable to patch FDT: %d", err); - err = append_memory(fdt_buf); + err = yamon_dt_append_memory(fdt_buf); if (err) panic("Unable to patch FDT: %d", err); @@ -323,7 +153,7 @@ static __init const void *sead3_fixup_fdt(const void *fdt, if (err) panic("Unable to patch FDT: %d", err); - err = serial_config(fdt_buf); + err = yamon_dt_serial_config(fdt_buf); if (err) panic("Unable to patch FDT: %d", err); diff --git a/arch/mips/generic/yamon-dt.c b/arch/mips/generic/yamon-dt.c new file mode 100644 index 000000000000..9a0c8da5a796 --- /dev/null +++ b/arch/mips/generic/yamon-dt.c @@ -0,0 +1,190 @@ +/* + * Copyright (C) 2016 Imagination Technologies + * Author: Paul Burton + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#define pr_fmt(fmt) "yamon-dt: " fmt + +#include +#include +#include +#include +#include + +#include + +__init int yamon_dt_append_cmdline(void *fdt) +{ + int err, chosen_off; + + /* find or add chosen node */ + chosen_off = fdt_path_offset(fdt, "/chosen"); + if (chosen_off == -FDT_ERR_NOTFOUND) + chosen_off = fdt_path_offset(fdt, "/chosen@0"); + if (chosen_off == -FDT_ERR_NOTFOUND) + chosen_off = fdt_add_subnode(fdt, 0, "chosen"); + if (chosen_off < 0) { + pr_err("Unable to find or add DT chosen node: %d\n", + chosen_off); + return chosen_off; + } + + err = fdt_setprop_string(fdt, chosen_off, "bootargs", fw_getcmdline()); + if (err) { + pr_err("Unable to set bootargs property: %d\n", err); + return err; + } + + return 0; +} + +__init int yamon_dt_append_memory(void *fdt) +{ + unsigned long phys_memsize, memsize; + __be32 mem_array[2]; + int err, mem_off; + char *var; + + /* find memory size from the bootloader environment */ + var = fw_getenv("memsize"); + if (var) { + err = kstrtoul(var, 0, &phys_memsize); + if (err) { + pr_err("Failed to read memsize env variable '%s'\n", + var); + return -EINVAL; + } + } else { + pr_warn("The bootloader didn't provide memsize: defaulting to 32MB\n"); + phys_memsize = 32 << 20; + } + + /* default to using all available RAM */ + memsize = phys_memsize; + + /* allow the user to override the usable memory */ + var = strstr(arcs_cmdline, "memsize="); + if (var) + memsize = memparse(var + strlen("memsize="), NULL); + + /* if the user says there's more RAM than we thought, believe them */ + phys_memsize = max_t(unsigned long, phys_memsize, memsize); + + /* find or add a memory node */ + mem_off = fdt_path_offset(fdt, "/memory"); + if (mem_off == -FDT_ERR_NOTFOUND) + mem_off = fdt_add_subnode(fdt, 0, "memory"); + if (mem_off < 0) { + pr_err("Unable to find or add memory DT node: %d\n", mem_off); + return mem_off; + } + + err = fdt_setprop_string(fdt, mem_off, "device_type", "memory"); + if (err) { + pr_err("Unable to set memory node device_type: %d\n", err); + return err; + } + + mem_array[0] = 0; + mem_array[1] = cpu_to_be32(phys_memsize); + err = fdt_setprop(fdt, mem_off, "reg", mem_array, sizeof(mem_array)); + if (err) { + pr_err("Unable to set memory regs property: %d\n", err); + return err; + } + + mem_array[0] = 0; + mem_array[1] = cpu_to_be32(memsize); + err = fdt_setprop(fdt, mem_off, "linux,usable-memory", + mem_array, sizeof(mem_array)); + if (err) { + pr_err("Unable to set linux,usable-memory property: %d\n", err); + return err; + } + + return 0; +} + +__init int yamon_dt_serial_config(void *fdt) +{ + const char *yamontty, *mode_var; + char mode_var_name[9], path[18], parity; + unsigned int uart, baud, stop_bits; + bool hw_flow; + int chosen_off, err; + + yamontty = fw_getenv("yamontty"); + if (!yamontty || !strcmp(yamontty, "tty0")) { + uart = 0; + } else if (!strcmp(yamontty, "tty1")) { + uart = 1; + } else { + pr_warn("yamontty environment variable '%s' invalid\n", + yamontty); + uart = 0; + } + + baud = stop_bits = 0; + parity = 0; + hw_flow = false; + + snprintf(mode_var_name, sizeof(mode_var_name), "modetty%u", uart); + mode_var = fw_getenv(mode_var_name); + if (mode_var) { + while (mode_var[0] >= '0' && mode_var[0] <= '9') { + baud *= 10; + baud += mode_var[0] - '0'; + mode_var++; + } + if (mode_var[0] == ',') + mode_var++; + if (mode_var[0]) + parity = mode_var[0]; + if (mode_var[0] == ',') + mode_var++; + if (mode_var[0]) + stop_bits = mode_var[0] - '0'; + if (mode_var[0] == ',') + mode_var++; + if (!strcmp(mode_var, "hw")) + hw_flow = true; + } + + if (!baud) + baud = 38400; + + if (parity != 'e' && parity != 'n' && parity != 'o') + parity = 'n'; + + if (stop_bits != 7 && stop_bits != 8) + stop_bits = 8; + + WARN_ON(snprintf(path, sizeof(path), "uart%u:%u%c%u%s", + uart, baud, parity, stop_bits, + hw_flow ? "r" : "") >= sizeof(path)); + + /* find or add chosen node */ + chosen_off = fdt_path_offset(fdt, "/chosen"); + if (chosen_off == -FDT_ERR_NOTFOUND) + chosen_off = fdt_path_offset(fdt, "/chosen@0"); + if (chosen_off == -FDT_ERR_NOTFOUND) + chosen_off = fdt_add_subnode(fdt, 0, "chosen"); + if (chosen_off < 0) { + pr_err("Unable to find or add DT chosen node: %d\n", + chosen_off); + return chosen_off; + } + + err = fdt_setprop_string(fdt, chosen_off, "stdout-path", path); + if (err) { + pr_err("Unable to set stdout-path property: %d\n", err); + return err; + } + + return 0; +} diff --git a/arch/mips/include/asm/yamon-dt.h b/arch/mips/include/asm/yamon-dt.h new file mode 100644 index 000000000000..3f3367de4836 --- /dev/null +++ b/arch/mips/include/asm/yamon-dt.h @@ -0,0 +1,48 @@ +/* + * Copyright (C) 2016 Imagination Technologies + * Author: Paul Burton + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#ifndef __MIPS_ASM_YAMON_DT_H__ +#define __MIPS_ASM_YAMON_DT_H__ + +/** + * yamon_dt_append_cmdline() - Append YAMON-provided command line to /chosen + * @fdt: the FDT blob + * + * Write the YAMON-provided command line to the bootargs property of the + * /chosen node in @fdt. + * + * Return: 0 on success, else -errno + */ +extern __init int yamon_dt_append_cmdline(void *fdt); + +/** + * yamon_dt_append_memory() - Append YAMON-provided memory info to /memory + * @fdt: the FDT blob + * + * Generate a /memory node in @fdt based upon memory size information provided + * by YAMON in its environment. + * + * Return: 0 on success, else -errno + */ +extern __init int yamon_dt_append_memory(void *fdt); + +/** + * yamon_dt_serial_config() - Append YAMON-provided serial config to /chosen + * @fdt: the FDT blob + * + * Generate a stdout-path property in the /chosen node of @fdt, based upon + * information provided in the YAMON environment about the UART configuration + * of the system. + * + * Return: 0 on success, else -errno + */ +extern __init int yamon_dt_serial_config(void *fdt); + +#endif /* __MIPS_ASM_YAMON_DT_H__ */ -- cgit v1.2.3-59-g8ed1b From f41d2430bbd6b64ee934915a1856fa406677d55e Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 2 Jun 2017 12:29:52 -0700 Subject: MIPS: generic/yamon-dt: Support > 256MB of RAM YAMON can expose more than 256MB of RAM to Linux on Malta by passing an ememsize environment variable with the full size, but the kernel then needs to be careful to choose the corresponding physical memory regions, avoiding the IO memory window. This is platform dependent, and on Malta it also depends on the memory layout which varies between system controllers. Extend yamon_dt_amend_memory() to generically handle this by taking [e]memsize bytes of memory from an array of memory regions passed in as a new parameter. Board code provides this array as appropriate depending on its own memory map. [paul.burton@imgtec.com: SEAD-3 supports 384MB DDR from 0] Signed-off-by: James Hogan Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16182/ Signed-off-by: Ralf Baechle --- arch/mips/generic/board-sead3.c | 17 +++++++- arch/mips/generic/yamon-dt.c | 92 +++++++++++++++++++++++++++++++--------- arch/mips/include/asm/yamon-dt.h | 22 ++++++++-- 3 files changed, 106 insertions(+), 25 deletions(-) diff --git a/arch/mips/generic/board-sead3.c b/arch/mips/generic/board-sead3.c index 63fdc98738ba..97186a3a5d21 100644 --- a/arch/mips/generic/board-sead3.c +++ b/arch/mips/generic/board-sead3.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -26,6 +27,15 @@ #define MIPS_REVISION_MACHINE (0xf << 4) #define MIPS_REVISION_MACHINE_SEAD3 (0x4 << 4) +/* + * Maximum 384MB RAM at physical address 0, preceding any I/O. + */ +static struct yamon_mem_region mem_regions[] __initdata = { + /* start size */ + { 0, SZ_256M + SZ_128M }, + {} +}; + static __init bool sead3_detect(void) { uint32_t rev; @@ -34,6 +44,11 @@ static __init bool sead3_detect(void) return (rev & MIPS_REVISION_MACHINE) == MIPS_REVISION_MACHINE_SEAD3; } +static __init int append_memory(void *fdt) +{ + return yamon_dt_append_memory(fdt, mem_regions); +} + static __init int remove_gic(void *fdt) { const unsigned int cpu_ehci_int = 2; @@ -145,7 +160,7 @@ static __init const void *sead3_fixup_fdt(const void *fdt, if (err) panic("Unable to patch FDT: %d", err); - err = yamon_dt_append_memory(fdt_buf); + err = append_memory(fdt_buf); if (err) panic("Unable to patch FDT: %d", err); diff --git a/arch/mips/generic/yamon-dt.c b/arch/mips/generic/yamon-dt.c index 9a0c8da5a796..8e36a5baaa7e 100644 --- a/arch/mips/generic/yamon-dt.c +++ b/arch/mips/generic/yamon-dt.c @@ -17,6 +17,9 @@ #include #include +#include + +#define MAX_MEM_ARRAY_ENTRIES 2 __init int yamon_dt_append_cmdline(void *fdt) { @@ -43,23 +46,64 @@ __init int yamon_dt_append_cmdline(void *fdt) return 0; } -__init int yamon_dt_append_memory(void *fdt) +static unsigned int __init gen_fdt_mem_array( + const struct yamon_mem_region *regions, + __be32 *mem_array, + unsigned int max_entries, + unsigned long memsize) +{ + const struct yamon_mem_region *mr; + unsigned long size; + unsigned int entries = 0; + + for (mr = regions; mr->size && memsize; ++mr) { + if (entries >= max_entries) { + pr_warn("Number of regions exceeds max %u\n", + max_entries); + break; + } + + /* How much of the remaining RAM fits in the next region? */ + size = min_t(unsigned long, memsize, mr->size); + memsize -= size; + + /* Emit a memory region */ + *(mem_array++) = cpu_to_be32(mr->start); + *(mem_array++) = cpu_to_be32(size); + ++entries; + + /* Discard the next mr->discard bytes */ + memsize -= min_t(unsigned long, memsize, mr->discard); + } + return entries; +} + +__init int yamon_dt_append_memory(void *fdt, + const struct yamon_mem_region *regions) { unsigned long phys_memsize, memsize; - __be32 mem_array[2]; - int err, mem_off; - char *var; + __be32 mem_array[2 * MAX_MEM_ARRAY_ENTRIES]; + unsigned int mem_entries; + int i, err, mem_off; + char *var, param_name[10], *var_names[] = { + "ememsize", "memsize", + }; /* find memory size from the bootloader environment */ - var = fw_getenv("memsize"); - if (var) { + for (i = 0; i < ARRAY_SIZE(var_names); i++) { + var = fw_getenv(var_names[i]); + if (!var) + continue; + err = kstrtoul(var, 0, &phys_memsize); - if (err) { - pr_err("Failed to read memsize env variable '%s'\n", - var); - return -EINVAL; - } - } else { + if (!err) + break; + + pr_warn("Failed to read the '%s' env variable '%s'\n", + var_names[i], var); + } + + if (!phys_memsize) { pr_warn("The bootloader didn't provide memsize: defaulting to 32MB\n"); phys_memsize = 32 << 20; } @@ -68,9 +112,14 @@ __init int yamon_dt_append_memory(void *fdt) memsize = phys_memsize; /* allow the user to override the usable memory */ - var = strstr(arcs_cmdline, "memsize="); - if (var) - memsize = memparse(var + strlen("memsize="), NULL); + for (i = 0; i < ARRAY_SIZE(var_names); i++) { + snprintf(param_name, sizeof(param_name), "%s=", var_names[i]); + var = strstr(arcs_cmdline, param_name); + if (!var) + continue; + + memsize = memparse(var + strlen(param_name), NULL); + } /* if the user says there's more RAM than we thought, believe them */ phys_memsize = max_t(unsigned long, phys_memsize, memsize); @@ -90,18 +139,19 @@ __init int yamon_dt_append_memory(void *fdt) return err; } - mem_array[0] = 0; - mem_array[1] = cpu_to_be32(phys_memsize); - err = fdt_setprop(fdt, mem_off, "reg", mem_array, sizeof(mem_array)); + mem_entries = gen_fdt_mem_array(regions, mem_array, + MAX_MEM_ARRAY_ENTRIES, phys_memsize); + err = fdt_setprop(fdt, mem_off, "reg", + mem_array, mem_entries * 2 * sizeof(mem_array[0])); if (err) { pr_err("Unable to set memory regs property: %d\n", err); return err; } - mem_array[0] = 0; - mem_array[1] = cpu_to_be32(memsize); + mem_entries = gen_fdt_mem_array(regions, mem_array, + MAX_MEM_ARRAY_ENTRIES, memsize); err = fdt_setprop(fdt, mem_off, "linux,usable-memory", - mem_array, sizeof(mem_array)); + mem_array, mem_entries * 2 * sizeof(mem_array[0])); if (err) { pr_err("Unable to set linux,usable-memory property: %d\n", err); return err; diff --git a/arch/mips/include/asm/yamon-dt.h b/arch/mips/include/asm/yamon-dt.h index 3f3367de4836..485cfe3e45e1 100644 --- a/arch/mips/include/asm/yamon-dt.h +++ b/arch/mips/include/asm/yamon-dt.h @@ -11,6 +11,20 @@ #ifndef __MIPS_ASM_YAMON_DT_H__ #define __MIPS_ASM_YAMON_DT_H__ +#include + +/** + * struct yamon_mem_region - Represents a contiguous range of physical RAM. + * @start: Start physical address. + * @size: Maximum size of region. + * @discard: Length of additional memory to discard after the region. + */ +struct yamon_mem_region { + phys_addr_t start; + phys_addr_t size; + phys_addr_t discard; +}; + /** * yamon_dt_append_cmdline() - Append YAMON-provided command line to /chosen * @fdt: the FDT blob @@ -24,14 +38,16 @@ extern __init int yamon_dt_append_cmdline(void *fdt); /** * yamon_dt_append_memory() - Append YAMON-provided memory info to /memory - * @fdt: the FDT blob + * @fdt: the FDT blob + * @regions: zero size terminated array of physical memory regions * * Generate a /memory node in @fdt based upon memory size information provided - * by YAMON in its environment. + * by YAMON in its environment and the @regions array. * * Return: 0 on success, else -errno */ -extern __init int yamon_dt_append_memory(void *fdt); +extern __init int yamon_dt_append_memory(void *fdt, + const struct yamon_mem_region *regions); /** * yamon_dt_serial_config() - Append YAMON-provided serial config to /chosen -- cgit v1.2.3-59-g8ed1b From c3d62fc6a058d1024f3ad0525a251e9d6c5203ed Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 2 Jun 2017 12:29:53 -0700 Subject: MIPS: generic/yamon-dt: Use serial* rather than uart* aliases Name aliases in the SEAD-3 device tree serial0 & serial1, rather than uart0 & uart1. This allows the core serial code to make use of the aliases to ensure that the UARTs are consistently numbered as expected rather than having the numbering depend upon probe order. When translating YAMON-provided serial configuration to a device tree stdout-path property adjust accordingly, such that we continue to reference a valid alias. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16183/ Signed-off-by: Ralf Baechle --- arch/mips/boot/dts/mti/sead3.dts | 6 +++--- arch/mips/generic/yamon-dt.c | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/mips/boot/dts/mti/sead3.dts b/arch/mips/boot/dts/mti/sead3.dts index 1bf58f841bbb..f327791cbcb5 100644 --- a/arch/mips/boot/dts/mti/sead3.dts +++ b/arch/mips/boot/dts/mti/sead3.dts @@ -14,12 +14,12 @@ interrupt-parent = <&gic>; chosen { - stdout-path = "uart1:115200"; + stdout-path = "serial1:115200"; }; aliases { - uart0 = &uart0; - uart1 = &uart1; + serial0 = &uart0; + serial1 = &uart1; }; cpus { diff --git a/arch/mips/generic/yamon-dt.c b/arch/mips/generic/yamon-dt.c index 8e36a5baaa7e..6077bca9b364 100644 --- a/arch/mips/generic/yamon-dt.c +++ b/arch/mips/generic/yamon-dt.c @@ -163,7 +163,7 @@ __init int yamon_dt_append_memory(void *fdt, __init int yamon_dt_serial_config(void *fdt) { const char *yamontty, *mode_var; - char mode_var_name[9], path[18], parity; + char mode_var_name[9], path[20], parity; unsigned int uart, baud, stop_bits; bool hw_flow; int chosen_off, err; @@ -214,7 +214,7 @@ __init int yamon_dt_serial_config(void *fdt) if (stop_bits != 7 && stop_bits != 8) stop_bits = 8; - WARN_ON(snprintf(path, sizeof(path), "uart%u:%u%c%u%s", + WARN_ON(snprintf(path, sizeof(path), "serial%u:%u%c%u%s", uart, baud, parity, stop_bits, hw_flow ? "r" : "") >= sizeof(path)); -- cgit v1.2.3-59-g8ed1b From e889dfca12ce95cdeaa50f66d1f33ad8fed4ca58 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 2 Jun 2017 12:29:54 -0700 Subject: MIPS: generic: Abstract FDT fixup application Introduce an apply_mips_fdt_fixups() function which can apply fixups to an FDT based upon an array of fixup descriptions. This abstracts that functionality such that legacy board code can apply FDT fixups without requiring lots of duplication. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16184/ Signed-off-by: Ralf Baechle --- arch/mips/generic/board-sead3.c | 33 +++++++++++---------------------- arch/mips/generic/init.c | 27 +++++++++++++++++++++++++++ arch/mips/include/asm/machine.h | 31 +++++++++++++++++++++++++++++++ 3 files changed, 69 insertions(+), 22 deletions(-) diff --git a/arch/mips/generic/board-sead3.c b/arch/mips/generic/board-sead3.c index 97186a3a5d21..39e11bd249cf 100644 --- a/arch/mips/generic/board-sead3.c +++ b/arch/mips/generic/board-sead3.c @@ -138,6 +138,14 @@ static __init int remove_gic(void *fdt) return 0; } +static const struct mips_fdt_fixup sead3_fdt_fixups[] __initconst = { + { yamon_dt_append_cmdline, "append command line" }, + { append_memory, "append memory" }, + { remove_gic, "remove GIC when not present" }, + { yamon_dt_serial_config, "append serial configuration" }, + { }, +}; + static __init const void *sead3_fixup_fdt(const void *fdt, const void *match_data) { @@ -152,29 +160,10 @@ static __init const void *sead3_fixup_fdt(const void *fdt, fw_init_cmdline(); - err = fdt_open_into(fdt, fdt_buf, sizeof(fdt_buf)); - if (err) - panic("Unable to open FDT: %d", err); - - err = yamon_dt_append_cmdline(fdt_buf); - if (err) - panic("Unable to patch FDT: %d", err); - - err = append_memory(fdt_buf); - if (err) - panic("Unable to patch FDT: %d", err); - - err = remove_gic(fdt_buf); - if (err) - panic("Unable to patch FDT: %d", err); - - err = yamon_dt_serial_config(fdt_buf); - if (err) - panic("Unable to patch FDT: %d", err); - - err = fdt_pack(fdt_buf); + err = apply_mips_fdt_fixups(fdt_buf, sizeof(fdt_buf), + fdt, sead3_fdt_fixups); if (err) - panic("Unable to pack FDT: %d\n", err); + panic("Unable to fixup FDT: %d", err); return fdt_buf; } diff --git a/arch/mips/generic/init.c b/arch/mips/generic/init.c index 4af619215410..4a9a1edbfb29 100644 --- a/arch/mips/generic/init.c +++ b/arch/mips/generic/init.c @@ -122,6 +122,33 @@ void __init device_tree_init(void) err = register_up_smp_ops(); } +int __init apply_mips_fdt_fixups(void *fdt_out, size_t fdt_out_size, + const void *fdt_in, + const struct mips_fdt_fixup *fixups) +{ + int err; + + err = fdt_open_into(fdt_in, fdt_out, fdt_out_size); + if (err) { + pr_err("Failed to open FDT\n"); + return err; + } + + for (; fixups->apply; fixups++) { + err = fixups->apply(fdt_out); + if (err) { + pr_err("Failed to apply FDT fixup \"%s\"\n", + fixups->description); + return err; + } + } + + err = fdt_pack(fdt_out); + if (err) + pr_err("Failed to pack FDT\n"); + return err; +} + void __init plat_time_init(void) { struct device_node *np; diff --git a/arch/mips/include/asm/machine.h b/arch/mips/include/asm/machine.h index 6b444cd9526f..ecb6c7335484 100644 --- a/arch/mips/include/asm/machine.h +++ b/arch/mips/include/asm/machine.h @@ -60,4 +60,35 @@ mips_machine_is_compatible(const struct mips_machine *mach, const void *fdt) return NULL; } +/** + * struct mips_fdt_fixup - Describe a fixup to apply to an FDT + * @apply: applies the fixup to @fdt, returns zero on success else -errno + * @description: a short description of the fixup + * + * Describes a fixup applied to an FDT blob by the @apply function. The + * @description field provides a short description of the fixup intended for + * use in error messages if the @apply function returns non-zero. + */ +struct mips_fdt_fixup { + int (*apply)(void *fdt); + const char *description; +}; + +/** + * apply_mips_fdt_fixups() - apply fixups to an FDT blob + * @fdt_out: buffer in which to place the fixed-up FDT + * @fdt_out_size: the size of the @fdt_out buffer + * @fdt_in: the FDT blob + * @fixups: pointer to an array of fixups to be applied + * + * Loop through the array of fixups pointed to by @fixups, calling the apply + * function on each until either one returns an error or we reach the end of + * the list as indicated by an entry with a NULL apply field. + * + * Return: zero on success, else -errno + */ +extern int __init apply_mips_fdt_fixups(void *fdt_out, size_t fdt_out_size, + const void *fdt_in, + const struct mips_fdt_fixup *fixups); + #endif /* __MIPS_ASM_MACHINE_H__ */ -- cgit v1.2.3-59-g8ed1b From ae7ce6b1e0a98132e2ecb2f64ebaa8c535b6b9f5 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 2 Jun 2017 12:29:55 -0700 Subject: MIPS: generic: Set RTC_ALWAYS_BCD to 0 Drivers for the mc146818 RTC generally check control registers to determine whether a value is encoded as binary or as a binary coded decimal. Setting RTC_ALWAYS_BCD to 1 effectively bypasses these checks and causes drivers to always expect binary coded decimal values, regardless of control register values. This does not seem like a sane default - defaulting to 0 allows the drivers to check control registers to determine encoding type & allows the driver to work generically with both binary & BCD encodings. Set this in mach-generic/mc146818rtc.h such that the generic kernel, or platforms which don't provide a custom mc146818rtc.h, can have an RTC driver which works with both encodings. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16185/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/mach-generic/mc146818rtc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/include/asm/mach-generic/mc146818rtc.h b/arch/mips/include/asm/mach-generic/mc146818rtc.h index 0b9a942f079d..9c72e540ff56 100644 --- a/arch/mips/include/asm/mach-generic/mc146818rtc.h +++ b/arch/mips/include/asm/mach-generic/mc146818rtc.h @@ -27,7 +27,7 @@ static inline void CMOS_WRITE(unsigned char data, unsigned long addr) outb_p(data, RTC_PORT(1)); } -#define RTC_ALWAYS_BCD 1 +#define RTC_ALWAYS_BCD 0 #ifndef mc146818_decode_year #define mc146818_decode_year(year) ((year) < 70 ? (year) + 2000 : (year) + 1900) -- cgit v1.2.3-59-g8ed1b From 032a469b1e6ef02209308a5b107c10beb4b12fb6 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 2 Jun 2017 12:29:56 -0700 Subject: MIPS: generic: Add a MAINTAINERS entry Add an entry to MAINTAINERS for the generic platform code, such that relevant people, starting with myself, can be CC'd on patches. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16186/ Signed-off-by: Ralf Baechle --- MAINTAINERS | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 09b5ab6a8a5c..bcf2d258c0dd 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8489,6 +8489,12 @@ F: Documentation/devicetree/bindings/mips/ F: Documentation/mips/ F: arch/mips/ +MIPS GENERIC PLATFORM +M: Paul Burton +L: linux-mips@linux-mips.org +S: Supported +F: arch/mips/generic/ + MIPS/LOONGSON1 ARCHITECTURE M: Keguang Zhang L: linux-mips@linux-mips.org -- cgit v1.2.3-59-g8ed1b From fbdc674ba33c3791b315a546019e570e3e94e599 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 2 Jun 2017 12:29:57 -0700 Subject: MIPS: SEAD-3: Set interrupt-parent per-device, not at root node The SEAD-3 board may be configured with or without a MIPS Global Interrupt Controller (GIC). Because of this we have a device tree with a default case of a GIC present, and code to fixup the device tree based upon a configuration register that indicates the presence of the GIC. In order to keep this DT fixup code simple, the interrupt-parent property was specified at the root node of the SEAD-3 DT, allowing the fixup code to simply change this property to the phandle of the CPU interrupt controller if a GIC is not present & affect all interrupt-using devices at once. This however causes a problem if we do have a GIC & the device tree is used as-is, because the interrupt-parent property of the root node applies to the CPU interrupt controller node. This causes a cycle when of_irq_init() attempts to probe interrupt controllers in order and boots fail due to a lack of configured interrupts, with this message printed on the kernel console: [ 0.000000] OF: of_irq_init: children remain, but no parents Fix this by removing the interrupt-parent property from the DT root node & instead setting it for each device which uses interrupts, ensuring that the CPU interrupt controller node has no interrupt-parent & allowing of_irq_init() to identify it as the root interrupt controller. Signed-off-by: Paul Burton Reported-by: Keng Koh Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16187/ Signed-off-by: Ralf Baechle --- arch/mips/boot/dts/mti/sead3.dts | 5 ++++- arch/mips/generic/board-sead3.c | 26 ++++++++++++++++++++------ 2 files changed, 24 insertions(+), 7 deletions(-) diff --git a/arch/mips/boot/dts/mti/sead3.dts b/arch/mips/boot/dts/mti/sead3.dts index f327791cbcb5..cabe256f9a68 100644 --- a/arch/mips/boot/dts/mti/sead3.dts +++ b/arch/mips/boot/dts/mti/sead3.dts @@ -11,7 +11,6 @@ #size-cells = <1>; compatible = "mti,sead-3"; model = "MIPS SEAD-3"; - interrupt-parent = <&gic>; chosen { stdout-path = "serial1:115200"; @@ -60,6 +59,7 @@ compatible = "generic-ehci"; reg = <0x1b200000 0x1000>; + interrupt-parent = <&gic>; interrupts = <0>; /* GIC 0 or CPU 6 */ has-transaction-translator; @@ -222,6 +222,7 @@ clock-frequency = <14745600>; + interrupt-parent = <&gic>; interrupts = <3>; /* GIC 3 or CPU 4 */ no-loopback-test; @@ -236,6 +237,7 @@ clock-frequency = <14745600>; + interrupt-parent = <&gic>; interrupts = <2>; /* GIC 2 or CPU 4 */ no-loopback-test; @@ -246,6 +248,7 @@ reg = <0x1f010000 0x10000>; reg-io-width = <4>; + interrupt-parent = <&gic>; interrupts = <0>; /* GIC 0 or CPU 6 */ phy-mode = "mii"; diff --git a/arch/mips/generic/board-sead3.c b/arch/mips/generic/board-sead3.c index 39e11bd249cf..f109a6b9fdd0 100644 --- a/arch/mips/generic/board-sead3.c +++ b/arch/mips/generic/board-sead3.c @@ -87,14 +87,16 @@ static __init int remove_gic(void *fdt) return -EINVAL; } - err = fdt_setprop_u32(fdt, 0, "interrupt-parent", cpu_phandle); - if (err) { - pr_err("unable to set root interrupt-parent: %d\n", err); - return err; - } - uart_off = fdt_node_offset_by_compatible(fdt, -1, "ns16550a"); while (uart_off >= 0) { + err = fdt_setprop_u32(fdt, uart_off, "interrupt-parent", + cpu_phandle); + if (err) { + pr_warn("unable to set UART interrupt-parent: %d\n", + err); + return err; + } + err = fdt_setprop_u32(fdt, uart_off, "interrupts", cpu_uart_int); if (err) { @@ -117,6 +119,12 @@ static __init int remove_gic(void *fdt) return eth_off; } + err = fdt_setprop_u32(fdt, eth_off, "interrupt-parent", cpu_phandle); + if (err) { + pr_err("unable to set ethernet interrupt-parent: %d\n", err); + return err; + } + err = fdt_setprop_u32(fdt, eth_off, "interrupts", cpu_eth_int); if (err) { pr_err("unable to set ethernet interrupts property: %d\n", err); @@ -129,6 +137,12 @@ static __init int remove_gic(void *fdt) return ehci_off; } + err = fdt_setprop_u32(fdt, ehci_off, "interrupt-parent", cpu_phandle); + if (err) { + pr_err("unable to set EHCI interrupt-parent: %d\n", err); + return err; + } + err = fdt_setprop_u32(fdt, ehci_off, "interrupts", cpu_ehci_int); if (err) { pr_err("unable to set EHCI interrupts property: %d\n", err); -- cgit v1.2.3-59-g8ed1b From d3f616346def161cfb0e4153692713f066755639 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 2 Jun 2017 12:29:59 -0700 Subject: MIPS: SEAD-3: Fix GIC interrupt specifiers The various interrupt specifiers in the device tree are not in a valid format for the MIPS GIC interrupt controller binding. Where each interrupt should provide 3 values - GIC_LOCAL or GIC_SHARED, the pin number & the type of interrupt - the device tree was only providing the pin number. This causes interrupts for those devices to not be used when a GIC is present. SEAD-3 systems without a GIC are unaffected since the DT fixup code generates interrupt specifiers that are valid for the CPU interrupt controller. Fix this by adding the GIC_SHARED & IRQ_TYPE_LEVEL_HIGH values to each interrupt specifier. Signed-off-by: Paul Burton Fixes: c11e3b48dbc3 ("MIPS: SEAD3: Probe UARTs using DT") Fixes: a34e93882de4 ("MIPS: SEAD3: Probe ethernet controller using DT") Fixes: 7afd2a5aec2e ("MIPS: SEAD3: Probe EHCI controller using DT") Cc: linux-mips@linux-mips.org Cc: stable@vger.kernel.org # v4.9+ Patchwork: https://patchwork.linux-mips.org/patch/16189/ Signed-off-by: Ralf Baechle --- arch/mips/boot/dts/mti/sead3.dts | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/mips/boot/dts/mti/sead3.dts b/arch/mips/boot/dts/mti/sead3.dts index cabe256f9a68..4f8bc83c2960 100644 --- a/arch/mips/boot/dts/mti/sead3.dts +++ b/arch/mips/boot/dts/mti/sead3.dts @@ -60,7 +60,7 @@ reg = <0x1b200000 0x1000>; interrupt-parent = <&gic>; - interrupts = <0>; /* GIC 0 or CPU 6 */ + interrupts = ; /* GIC 0 or CPU 6 */ has-transaction-translator; }; @@ -223,7 +223,7 @@ clock-frequency = <14745600>; interrupt-parent = <&gic>; - interrupts = <3>; /* GIC 3 or CPU 4 */ + interrupts = ; /* GIC 3 or CPU 4 */ no-loopback-test; }; @@ -238,7 +238,7 @@ clock-frequency = <14745600>; interrupt-parent = <&gic>; - interrupts = <2>; /* GIC 2 or CPU 4 */ + interrupts = ; /* GIC 2 or CPU 4 */ no-loopback-test; }; @@ -249,7 +249,7 @@ reg-io-width = <4>; interrupt-parent = <&gic>; - interrupts = <0>; /* GIC 0 or CPU 6 */ + interrupts = ; /* GIC 0 or CPU 6 */ phy-mode = "mii"; smsc,irq-push-pull; -- cgit v1.2.3-59-g8ed1b From 0a00024d7a779b283db2a02130ffa46f47634d0c Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Thu, 22 Jun 2017 23:06:48 +0800 Subject: MIPS: Loongson: Add Loongson-3A R3 basic support Loongson-3A R3 is very similar to Loongson-3A R2. All Loongson-3 CPU family: Code-name Brand-name PRId Loongson-3A R1 Loongson-3A1000 0x6305 Loongson-3A R2 Loongson-3A2000 0x6308 Loongson-3A R3 Loongson-3A3000 0x6309 Loongson-3B R1 Loongson-3B1000 0x6306 Loongson-3B R2 Loongson-3B1500 0x6307 Signed-off-by: Huacai Chen Cc: John Crispin Cc: Steven J . Hill Cc: Fuxin Zhang Cc: Zhangjin Wu Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16585/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/cpu.h | 1 + arch/mips/kernel/cpu-probe.c | 6 ++++++ arch/mips/loongson64/common/env.c | 1 + arch/mips/loongson64/loongson-3/smp.c | 5 +++-- drivers/platform/mips/cpu_hwmon.c | 17 +++++++++++++---- 5 files changed, 24 insertions(+), 6 deletions(-) diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h index 3069359b0120..53b8b1f49084 100644 --- a/arch/mips/include/asm/cpu.h +++ b/arch/mips/include/asm/cpu.h @@ -248,6 +248,7 @@ #define PRID_REV_LOONGSON3B_R1 0x0006 #define PRID_REV_LOONGSON3B_R2 0x0007 #define PRID_REV_LOONGSON3A_R2 0x0008 +#define PRID_REV_LOONGSON3A_R3 0x0009 /* * Older processors used to encode processor version and revision in two diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index 353ade2c130a..09462bba629f 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -1836,6 +1836,12 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) set_elf_platform(cpu, "loongson3a"); set_isa(c, MIPS_CPU_ISA_M64R2); break; + case PRID_REV_LOONGSON3A_R3: + c->cputype = CPU_LOONGSON3; + __cpu_name[cpu] = "ICT Loongson-3"; + set_elf_platform(cpu, "loongson3a"); + set_isa(c, MIPS_CPU_ISA_M64R2); + break; } decode_configs(c); diff --git a/arch/mips/loongson64/common/env.c b/arch/mips/loongson64/common/env.c index 6afa21850267..4707abfe9d64 100644 --- a/arch/mips/loongson64/common/env.c +++ b/arch/mips/loongson64/common/env.c @@ -193,6 +193,7 @@ void __init prom_init_env(void) break; case PRID_REV_LOONGSON3A_R1: case PRID_REV_LOONGSON3A_R2: + case PRID_REV_LOONGSON3A_R3: cpu_clock_freq = 900000000; break; case PRID_REV_LOONGSON3B_R1: diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/loongson-3/smp.c index 64659fc73940..1629743ba96a 100644 --- a/arch/mips/loongson64/loongson-3/smp.c +++ b/arch/mips/loongson64/loongson-3/smp.c @@ -503,7 +503,7 @@ static void loongson3a_r1_play_dead(int *state_addr) : "a1"); } -static void loongson3a_r2_play_dead(int *state_addr) +static void loongson3a_r2r3_play_dead(int *state_addr) { register int val; register long cpuid, core, node, count; @@ -664,8 +664,9 @@ void play_dead(void) (void *)CKSEG1ADDR((unsigned long)loongson3a_r1_play_dead); break; case PRID_REV_LOONGSON3A_R2: + case PRID_REV_LOONGSON3A_R3: play_dead_at_ckseg1 = - (void *)CKSEG1ADDR((unsigned long)loongson3a_r2_play_dead); + (void *)CKSEG1ADDR((unsigned long)loongson3a_r2r3_play_dead); break; case PRID_REV_LOONGSON3B_R1: case PRID_REV_LOONGSON3B_R2: diff --git a/drivers/platform/mips/cpu_hwmon.c b/drivers/platform/mips/cpu_hwmon.c index 4300a558d0f3..46ab7d86ae1c 100644 --- a/drivers/platform/mips/cpu_hwmon.c +++ b/drivers/platform/mips/cpu_hwmon.c @@ -17,14 +17,23 @@ */ int loongson3_cpu_temp(int cpu) { - u32 reg; + u32 reg, prid_rev; reg = LOONGSON_CHIPTEMP(cpu); - if ((read_c0_prid() & PRID_REV_MASK) == PRID_REV_LOONGSON3A_R1) + prid_rev = read_c0_prid() & PRID_REV_MASK; + switch (prid_rev) { + case PRID_REV_LOONGSON3A_R1: reg = (reg >> 8) & 0xff; - else + break; + case PRID_REV_LOONGSON3A_R2: + case PRID_REV_LOONGSON3B_R1: + case PRID_REV_LOONGSON3B_R2: reg = ((reg >> 8) & 0xff) - 100; - + break; + case PRID_REV_LOONGSON3A_R3: + reg = (reg & 0xffff)*731/0x4000 - 273; + break; + } return (int)reg * 1000; } -- cgit v1.2.3-59-g8ed1b From 06eb8a56af23ae32e90fdd6b27fec30930364b52 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 19 Jun 2017 14:00:40 -0400 Subject: sunrpc: Disable splice for krb5i Running a multi-threaded 8KB fio test (70/30 mix), three or four out of twelve of the jobs fail when using krb5i. The failure is an EIO on a read. Troubleshooting confirmed the EIO results when the client fails to verify the MIC of an NFS READ reply. Bruce suggested the problem could be due to the data payload changing between the time the reply's MIC was computed on the server and the time the reply was actually sent. krb5p gets around this problem by disabling RQ_SPLICE_OK. Use the same mechanism for krb5i RPCs. "iozone -i0 -i1 -s128m -y1k -az -I", export is tmpfs, mount is sec=krb5i,vers=3,proto=rdma. The important numbers are the read / reread column. Here's without the RQ_SPLICE_OK patch: kB reclen write rewrite read reread 131072 1 7546 7929 8396 8267 131072 2 14375 14600 15843 15639 131072 4 19280 19248 21303 21410 131072 8 32350 31772 35199 34883 131072 16 36748 37477 49365 51706 131072 32 55669 56059 57475 57389 131072 64 74599 75190 74903 75550 131072 128 99810 101446 102828 102724 131072 256 122042 122612 124806 125026 131072 512 137614 138004 141412 141267 131072 1024 146601 148774 151356 151409 131072 2048 180684 181727 293140 292840 131072 4096 206907 207658 552964 549029 131072 8192 223982 224360 454493 473469 131072 16384 228927 228390 654734 632607 And here's with it: kB reclen write rewrite read reread 131072 1 7700 7365 7958 8011 131072 2 13211 13303 14937 14414 131072 4 19001 19265 20544 20657 131072 8 30883 31097 34255 33566 131072 16 36868 34908 51499 49944 131072 32 56428 55535 58710 56952 131072 64 73507 74676 75619 74378 131072 128 100324 101442 103276 102736 131072 256 122517 122995 124639 124150 131072 512 137317 139007 140530 140830 131072 1024 146807 148923 151246 151072 131072 2048 179656 180732 292631 292034 131072 4096 206216 208583 543355 541951 131072 8192 223738 224273 494201 489372 131072 16384 229313 229840 691719 668427 I would say that there is not much difference in this test. For good measure, here's the same test with sec=krb5p: kB reclen write rewrite read reread 131072 1 5982 5881 6137 6218 131072 2 10216 10252 10850 10932 131072 4 12236 12575 15375 15526 131072 8 15461 15462 23821 22351 131072 16 25677 25811 27529 27640 131072 32 31903 32354 34063 33857 131072 64 42989 43188 45635 45561 131072 128 52848 53210 56144 56141 131072 256 59123 59214 62691 62933 131072 512 63140 63277 66887 67025 131072 1024 65255 65299 69213 69140 131072 2048 76454 76555 133767 133862 131072 4096 84726 84883 251925 250702 131072 8192 89491 89482 270821 276085 131072 16384 91572 91597 361768 336868 BugLink: https://bugzilla.linux-nfs.org/show_bug.cgi?id=307 Signed-off-by: Chuck Lever Reviewed-by: Jeff Layton Signed-off-by: J. Bruce Fields --- net/sunrpc/auth_gss/svcauth_gss.c | 8 ++++++++ net/sunrpc/svc.c | 2 +- 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index a54a7a3d28f5..7b1ee5a0b03c 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -838,6 +838,14 @@ unwrap_integ_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct g struct xdr_netobj mic; struct xdr_buf integ_buf; + /* NFS READ normally uses splice to send data in-place. However + * the data in cache can change after the reply's MIC is computed + * but before the RPC reply is sent. To prevent the client from + * rejecting the server-computed MIC in this somewhat rare case, + * do not use splice with the GSS integrity service. + */ + clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); + /* Did we already verify the signature on the original pass through? */ if (rqstp->rq_deferred) return 0; diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 45b4f2d2e3bd..85ce0db5b0a6 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1165,7 +1165,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) if (argv->iov_len < 6*4) goto err_short_len; - /* Will be turned off only in gss privacy case: */ + /* Will be turned off by GSS integrity and privacy services */ set_bit(RQ_SPLICE_OK, &rqstp->rq_flags); /* Will be turned off only when NFSv4 Sessions are used */ set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); -- cgit v1.2.3-59-g8ed1b From 91a08eae7979417bf10c98f149c6ea28e6632114 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 23 Jun 2017 17:17:15 -0400 Subject: svcrdma: Squelch disconnection messages The server displays "svcrdma: failed to post Send WR (-107)" in the kernel log when the client disconnects. This could flood the server's log, so remove the message. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- net/sunrpc/xprtrdma/svc_rdma_sendto.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 1736337f3a55..5ba6d915c906 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -313,13 +313,17 @@ static int svc_rdma_dma_map_buf(struct svcxprt_rdma *rdma, dma_addr = ib_dma_map_page(dev, virt_to_page(base), offset, len, DMA_TO_DEVICE); if (ib_dma_mapping_error(dev, dma_addr)) - return -EIO; + goto out_maperr; ctxt->sge[sge_no].addr = dma_addr; ctxt->sge[sge_no].length = len; ctxt->sge[sge_no].lkey = rdma->sc_pd->local_dma_lkey; svc_rdma_count_mappings(rdma, ctxt); return 0; + +out_maperr: + pr_err("svcrdma: failed to map buffer\n"); + return -EIO; } static int svc_rdma_dma_map_page(struct svcxprt_rdma *rdma, @@ -334,13 +338,17 @@ static int svc_rdma_dma_map_page(struct svcxprt_rdma *rdma, dma_addr = ib_dma_map_page(dev, page, offset, len, DMA_TO_DEVICE); if (ib_dma_mapping_error(dev, dma_addr)) - return -EIO; + goto out_maperr; ctxt->sge[sge_no].addr = dma_addr; ctxt->sge[sge_no].length = len; ctxt->sge[sge_no].lkey = rdma->sc_pd->local_dma_lkey; svc_rdma_count_mappings(rdma, ctxt); return 0; + +out_maperr: + pr_err("svcrdma: failed to map page\n"); + return -EIO; } /** @@ -547,7 +555,6 @@ static int svc_rdma_send_reply_msg(struct svcxprt_rdma *rdma, return 0; err: - pr_err("svcrdma: failed to post Send WR (%d)\n", ret); svc_rdma_unmap_dma(ctxt); svc_rdma_put_context(ctxt, 1); return ret; -- cgit v1.2.3-59-g8ed1b From 107c1d0a991abe632a051de697c5acc33c03fd96 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 23 Jun 2017 17:17:24 -0400 Subject: svcrdma: Avoid Send Queue overflow Sanity case: Catch the case where more Work Requests are being posted to the Send Queue than there are Send Queue Entries. This might happen if a client sends a chunk with more segments than there are SQEs for the transport. The server can't send that reply, so the transport will deadlock unless the client drops the RPC. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- net/sunrpc/xprtrdma/svc_rdma_rw.c | 5 +++++ net/sunrpc/xprtrdma/svc_rdma_sendto.c | 2 +- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index 0cf620277693..3b35364d9a6b 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -232,6 +232,9 @@ static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc) struct ib_cqe *cqe; int ret; + if (cc->cc_sqecount > rdma->sc_sq_depth) + return -EINVAL; + first_wr = NULL; cqe = &cc->cc_cqe; list_for_each(tmp, &cc->cc_rwctxts) { @@ -425,6 +428,7 @@ static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info, * * Returns a non-negative number of bytes the chunk consumed, or * %-E2BIG if the payload was larger than the Write chunk, + * %-EINVAL if client provided too many segments, * %-ENOMEM if rdma_rw context pool was exhausted, * %-ENOTCONN if posting failed (connection is lost), * %-EIO if rdma_rw initialization failed (DMA mapping, etc). @@ -465,6 +469,7 @@ out_err: * * Returns a non-negative number of bytes the chunk consumed, or * %-E2BIG if the payload was larger than the Reply chunk, + * %-EINVAL if client provided too many segments, * %-ENOMEM if rdma_rw context pool was exhausted, * %-ENOTCONN if posting failed (connection is lost), * %-EIO if rdma_rw initialization failed (DMA mapping, etc). diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 5ba6d915c906..19fd01e4b690 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -684,7 +684,7 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) return 0; err2: - if (ret != -E2BIG) + if (ret != -E2BIG || ret != -EINVAL) goto err1; ret = svc_rdma_post_recv(rdma, GFP_KERNEL); -- cgit v1.2.3-59-g8ed1b From a80a32341fbabd4276165a9ce4fa4c80168c0bef Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 23 Jun 2017 17:17:35 -0400 Subject: svcrdma: Remove svc_rdma_marshal.c svc_rdma_marshal.c has one remaining exported function -- svc_rdma_xdr_decode_req -- and it has a single call site. Take the same approach as the sendto path, and move this function into the source file where it is called. This is a refactoring change only. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 3 - net/sunrpc/xprtrdma/Makefile | 4 +- net/sunrpc/xprtrdma/svc_rdma_marshal.c | 168 -------------------------------- net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 126 ++++++++++++++++++++++++ 4 files changed, 128 insertions(+), 173 deletions(-) delete mode 100644 net/sunrpc/xprtrdma/svc_rdma_marshal.c diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index f3787d800ba4..3ca991657889 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -185,9 +185,6 @@ extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp, struct xdr_buf *rcvbuf); -/* svc_rdma_marshal.c */ -extern int svc_rdma_xdr_decode_req(struct xdr_buf *); - /* svc_rdma_recvfrom.c */ extern int svc_rdma_recvfrom(struct svc_rqst *); extern int rdma_read_chunk_lcl(struct svcxprt_rdma *, struct svc_rqst *, diff --git a/net/sunrpc/xprtrdma/Makefile b/net/sunrpc/xprtrdma/Makefile index c1ae8142ab73..b8213ddce2f2 100644 --- a/net/sunrpc/xprtrdma/Makefile +++ b/net/sunrpc/xprtrdma/Makefile @@ -3,6 +3,6 @@ obj-$(CONFIG_SUNRPC_XPRT_RDMA) += rpcrdma.o rpcrdma-y := transport.o rpc_rdma.o verbs.o \ fmr_ops.o frwr_ops.o \ svc_rdma.o svc_rdma_backchannel.o svc_rdma_transport.o \ - svc_rdma_marshal.o svc_rdma_sendto.o svc_rdma_recvfrom.o \ - svc_rdma_rw.o module.o + svc_rdma_sendto.o svc_rdma_recvfrom.o svc_rdma_rw.o \ + module.o rpcrdma-$(CONFIG_SUNRPC_BACKCHANNEL) += backchannel.o diff --git a/net/sunrpc/xprtrdma/svc_rdma_marshal.c b/net/sunrpc/xprtrdma/svc_rdma_marshal.c deleted file mode 100644 index bdcf7d85a3dc..000000000000 --- a/net/sunrpc/xprtrdma/svc_rdma_marshal.c +++ /dev/null @@ -1,168 +0,0 @@ -/* - * Copyright (c) 2016 Oracle. All rights reserved. - * Copyright (c) 2005-2006 Network Appliance, Inc. All rights reserved. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the BSD-type - * license below: - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * - * Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials provided - * with the distribution. - * - * Neither the name of the Network Appliance, Inc. nor the names of - * its contributors may be used to endorse or promote products - * derived from this software without specific prior written - * permission. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - * Author: Tom Tucker - */ - -#include -#include -#include -#include -#include - -#define RPCDBG_FACILITY RPCDBG_SVCXPRT - -static __be32 *xdr_check_read_list(__be32 *p, __be32 *end) -{ - __be32 *next; - - while (*p++ != xdr_zero) { - next = p + rpcrdma_readchunk_maxsz - 1; - if (next > end) - return NULL; - p = next; - } - return p; -} - -static __be32 *xdr_check_write_list(__be32 *p, __be32 *end) -{ - __be32 *next; - - while (*p++ != xdr_zero) { - next = p + 1 + be32_to_cpup(p) * rpcrdma_segment_maxsz; - if (next > end) - return NULL; - p = next; - } - return p; -} - -static __be32 *xdr_check_reply_chunk(__be32 *p, __be32 *end) -{ - __be32 *next; - - if (*p++ != xdr_zero) { - next = p + 1 + be32_to_cpup(p) * rpcrdma_segment_maxsz; - if (next > end) - return NULL; - p = next; - } - return p; -} - -/** - * svc_rdma_xdr_decode_req - Parse incoming RPC-over-RDMA header - * @rq_arg: Receive buffer - * - * On entry, xdr->head[0].iov_base points to first byte in the - * RPC-over-RDMA header. - * - * On successful exit, head[0] points to first byte past the - * RPC-over-RDMA header. For RDMA_MSG, this is the RPC message. - * The length of the RPC-over-RDMA header is returned. - */ -int svc_rdma_xdr_decode_req(struct xdr_buf *rq_arg) -{ - __be32 *p, *end, *rdma_argp; - unsigned int hdr_len; - - /* Verify that there's enough bytes for header + something */ - if (rq_arg->len <= RPCRDMA_HDRLEN_ERR) - goto out_short; - - rdma_argp = rq_arg->head[0].iov_base; - if (*(rdma_argp + 1) != rpcrdma_version) - goto out_version; - - switch (*(rdma_argp + 3)) { - case rdma_msg: - case rdma_nomsg: - break; - - case rdma_done: - goto out_drop; - - case rdma_error: - goto out_drop; - - default: - goto out_proc; - } - - end = (__be32 *)((unsigned long)rdma_argp + rq_arg->len); - p = xdr_check_read_list(rdma_argp + 4, end); - if (!p) - goto out_inval; - p = xdr_check_write_list(p, end); - if (!p) - goto out_inval; - p = xdr_check_reply_chunk(p, end); - if (!p) - goto out_inval; - if (p > end) - goto out_inval; - - rq_arg->head[0].iov_base = p; - hdr_len = (unsigned long)p - (unsigned long)rdma_argp; - rq_arg->head[0].iov_len -= hdr_len; - return hdr_len; - -out_short: - dprintk("svcrdma: header too short = %d\n", rq_arg->len); - return -EINVAL; - -out_version: - dprintk("svcrdma: bad xprt version: %u\n", - be32_to_cpup(rdma_argp + 1)); - return -EPROTONOSUPPORT; - -out_drop: - dprintk("svcrdma: dropping RDMA_DONE/ERROR message\n"); - return 0; - -out_proc: - dprintk("svcrdma: bad rdma procedure (%u)\n", - be32_to_cpup(rdma_argp + 3)); - return -EINVAL; - -out_inval: - dprintk("svcrdma: failed to parse transport header\n"); - return -EINVAL; -} diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 27a99bf5b1a6..55ad335bbef1 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -1,4 +1,5 @@ /* + * Copyright (c) 2016, 2017 Oracle. All rights reserved. * Copyright (c) 2014 Open Grid Computing, Inc. All rights reserved. * Copyright (c) 2005-2006 Network Appliance, Inc. All rights reserved. * @@ -40,6 +41,7 @@ * Author: Tom Tucker */ +#include #include #include #include @@ -115,6 +117,130 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp, rqstp->rq_arg.tail[0].iov_len = 0; } +static __be32 *xdr_check_read_list(__be32 *p, __be32 *end) +{ + __be32 *next; + + while (*p++ != xdr_zero) { + next = p + rpcrdma_readchunk_maxsz - 1; + if (next > end) + return NULL; + p = next; + } + return p; +} + +static __be32 *xdr_check_write_list(__be32 *p, __be32 *end) +{ + __be32 *next; + + while (*p++ != xdr_zero) { + next = p + 1 + be32_to_cpup(p) * rpcrdma_segment_maxsz; + if (next > end) + return NULL; + p = next; + } + return p; +} + +static __be32 *xdr_check_reply_chunk(__be32 *p, __be32 *end) +{ + __be32 *next; + + if (*p++ != xdr_zero) { + next = p + 1 + be32_to_cpup(p) * rpcrdma_segment_maxsz; + if (next > end) + return NULL; + p = next; + } + return p; +} + +/* On entry, xdr->head[0].iov_base points to first byte in the + * RPC-over-RDMA header. + * + * On successful exit, head[0] points to first byte past the + * RPC-over-RDMA header. For RDMA_MSG, this is the RPC message. + * The length of the RPC-over-RDMA header is returned. + * + * Assumptions: + * - The transport header is entirely contained in the head iovec. + */ +static int svc_rdma_xdr_decode_req(struct xdr_buf *rq_arg) +{ + __be32 *p, *end, *rdma_argp; + unsigned int hdr_len; + char *proc; + + /* Verify that there's enough bytes for header + something */ + if (rq_arg->len <= RPCRDMA_HDRLEN_ERR) + goto out_short; + + rdma_argp = rq_arg->head[0].iov_base; + if (*(rdma_argp + 1) != rpcrdma_version) + goto out_version; + + switch (*(rdma_argp + 3)) { + case rdma_msg: + proc = "RDMA_MSG"; + break; + case rdma_nomsg: + proc = "RDMA_NOMSG"; + break; + + case rdma_done: + goto out_drop; + + case rdma_error: + goto out_drop; + + default: + goto out_proc; + } + + end = (__be32 *)((unsigned long)rdma_argp + rq_arg->len); + p = xdr_check_read_list(rdma_argp + 4, end); + if (!p) + goto out_inval; + p = xdr_check_write_list(p, end); + if (!p) + goto out_inval; + p = xdr_check_reply_chunk(p, end); + if (!p) + goto out_inval; + if (p > end) + goto out_inval; + + rq_arg->head[0].iov_base = p; + hdr_len = (unsigned long)p - (unsigned long)rdma_argp; + rq_arg->head[0].iov_len -= hdr_len; + dprintk("svcrdma: received %s request for XID 0x%08x, hdr_len=%u\n", + proc, be32_to_cpup(rdma_argp), hdr_len); + return hdr_len; + +out_short: + dprintk("svcrdma: header too short = %d\n", rq_arg->len); + return -EINVAL; + +out_version: + dprintk("svcrdma: bad xprt version: %u\n", + be32_to_cpup(rdma_argp + 1)); + return -EPROTONOSUPPORT; + +out_drop: + dprintk("svcrdma: dropping RDMA_DONE/ERROR message\n"); + return 0; + +out_proc: + dprintk("svcrdma: bad rdma procedure (%u)\n", + be32_to_cpup(rdma_argp + 3)); + return -EINVAL; + +out_inval: + dprintk("svcrdma: failed to parse transport header\n"); + return -EINVAL; +} + /* Issue an RDMA_READ using the local lkey to map the data sink */ int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, -- cgit v1.2.3-59-g8ed1b From e77340e00300df9b6591d686f186eea60c67206f Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 23 Jun 2017 17:17:44 -0400 Subject: svcrdma: Improve Read chunk sanity checking Identify malformed transport headers and unsupported chunk combinations as early as possible. - Reject RPC-over-RDMA messages that contain more than one Read chunk, since this implementation currently does not support more than one per RPC transaction. - Ensure that segment lengths are not crazy. - Remove the segment count check. With a 1KB inline threshold, the largest number of Read segments that can be conveyed is about 40 (for a RDMA_NOMSG Call message). This is nowhere near RPCSVC_MAXPAGES. As far as I can tell, that was just a sanity check and does not enforce an implementation limit. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 55 ++++++++++++++++++++++----------- 1 file changed, 37 insertions(+), 18 deletions(-) diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 55ad335bbef1..885ad9503ee0 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -117,15 +117,47 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp, rqstp->rq_arg.tail[0].iov_len = 0; } -static __be32 *xdr_check_read_list(__be32 *p, __be32 *end) +/* This accommodates the largest possible Position-Zero + * Read chunk or Reply chunk, in one segment. + */ +#define MAX_BYTES_SPECIAL_SEG ((u32)((RPCSVC_MAXPAGES + 2) << PAGE_SHIFT)) + +/* Sanity check the Read list. + * + * Implementation limits: + * - This implementation supports only one Read chunk. + * + * Sanity checks: + * - Read list does not overflow buffer. + * - Segment size limited by largest NFS data payload. + * + * The segment count is limited to how many segments can + * fit in the transport header without overflowing the + * buffer. That's about 40 Read segments for a 1KB inline + * threshold. + * + * Returns pointer to the following Write list. + */ +static __be32 *xdr_check_read_list(__be32 *p, const __be32 *end) { - __be32 *next; + u32 position; + bool first; + first = true; while (*p++ != xdr_zero) { - next = p + rpcrdma_readchunk_maxsz - 1; - if (next > end) + if (first) { + position = be32_to_cpup(p++); + first = false; + } else if (be32_to_cpup(p++) != position) { + return NULL; + } + p++; /* handle */ + if (be32_to_cpup(p++) > MAX_BYTES_SPECIAL_SEG) + return NULL; + p += 2; /* offset */ + + if (p > end) return NULL; - p = next; } return p; } @@ -478,16 +510,6 @@ int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt, return ret; } -static unsigned int -rdma_rcl_chunk_count(struct rpcrdma_read_chunk *ch) -{ - unsigned int count; - - for (count = 0; ch->rc_discrim != xdr_zero; ch++) - count++; - return count; -} - /* If there was additional inline content, append it to the end of arg.pages. * Tail copy has to be done after the reader function has determined how many * pages are needed for RDMA READ. @@ -567,9 +589,6 @@ static int rdma_read_chunks(struct svcxprt_rdma *xprt, if (!ch) return 0; - if (rdma_rcl_chunk_count(ch) > RPCSVC_MAXPAGES) - return -EINVAL; - /* The request is completed when the RDMA_READs complete. The * head context keeps all the pages that comprise the * request. -- cgit v1.2.3-59-g8ed1b From 3c22f326074d2306041b0c5c9df516464349564d Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 23 Jun 2017 17:17:52 -0400 Subject: svcrdma: Improve Write chunk sanity checking Identify malformed transport headers and unsupported chunk combinations as early as possible. - Reject RPC-over-RDMA messages that contain more than one Write chunk, since this implementation does not support more than one per message. - Ensure that segment lengths are not crazy. - Ensure that the chunk's segment count is not crazy. With a 1KB inline threshold, the largest number of Write segments that can be conveyed is about 60 (for a RDMA_NOMSG Reply message). Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 52 +++++++++++++++++++++++++++++---- 1 file changed, 47 insertions(+), 5 deletions(-) diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 885ad9503ee0..cf8be18f297a 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -117,6 +117,11 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp, rqstp->rq_arg.tail[0].iov_len = 0; } +/* This accommodates the largest possible Write chunk, + * in one segment. + */ +#define MAX_BYTES_WRITE_SEG ((u32)(RPCSVC_MAXPAGES << PAGE_SHIFT)) + /* This accommodates the largest possible Position-Zero * Read chunk or Reply chunk, in one segment. */ @@ -162,15 +167,52 @@ static __be32 *xdr_check_read_list(__be32 *p, const __be32 *end) return p; } -static __be32 *xdr_check_write_list(__be32 *p, __be32 *end) +/* The segment count is limited to how many segments can + * fit in the transport header without overflowing the + * buffer. That's about 60 Write segments for a 1KB inline + * threshold. + */ +static __be32 *xdr_check_write_chunk(__be32 *p, const __be32 *end, + u32 maxlen) { - __be32 *next; + u32 i, segcount; + + segcount = be32_to_cpup(p++); + for (i = 0; i < segcount; i++) { + p++; /* handle */ + if (be32_to_cpup(p++) > maxlen) + return NULL; + p += 2; /* offset */ + + if (p > end) + return NULL; + } + + return p; +} +/* Sanity check the Write list. + * + * Implementation limits: + * - This implementation supports only one Write chunk. + * + * Sanity checks: + * - Write list does not overflow buffer. + * - Segment size limited by largest NFS data payload. + * + * Returns pointer to the following Reply chunk. + */ +static __be32 *xdr_check_write_list(__be32 *p, const __be32 *end) +{ + u32 chcount; + + chcount = 0; while (*p++ != xdr_zero) { - next = p + 1 + be32_to_cpup(p) * rpcrdma_segment_maxsz; - if (next > end) + p = xdr_check_write_chunk(p, end, MAX_BYTES_WRITE_SEG); + if (!p) + return NULL; + if (chcount++ > 1) return NULL; - p = next; } return p; } -- cgit v1.2.3-59-g8ed1b From ca5c76aba7502d52a6019358ec04bd4d734037d7 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 23 Jun 2017 17:18:00 -0400 Subject: svcrdma: Improve Reply chunk sanity checking Identify malformed transport headers and unsupported chunk combinations as early as possible. - Ensure that segment lengths are not crazy. - Ensure that the Reply chunk's segment count is not crazy. With a 1KB inline threshold, the largest number of Write segments that can be conveyed is about 60 (for a RDMA_NOMSG Reply message). Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index cf8be18f297a..b48089314f85 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -217,15 +217,20 @@ static __be32 *xdr_check_write_list(__be32 *p, const __be32 *end) return p; } -static __be32 *xdr_check_reply_chunk(__be32 *p, __be32 *end) +/* Sanity check the Reply chunk. + * + * Sanity checks: + * - Reply chunk does not overflow buffer. + * - Segment size limited by largest NFS data payload. + * + * Returns pointer to the following RPC header. + */ +static __be32 *xdr_check_reply_chunk(__be32 *p, const __be32 *end) { - __be32 *next; - if (*p++ != xdr_zero) { - next = p + 1 + be32_to_cpup(p) * rpcrdma_segment_maxsz; - if (next > end) + p = xdr_check_write_chunk(p, end, MAX_BYTES_SPECIAL_SEG); + if (!p) return NULL; - p = next; } return p; } -- cgit v1.2.3-59-g8ed1b From 2d6491a56c76f2d6c22aaa710e2a4d04ad41529b Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 23 Jun 2017 17:18:08 -0400 Subject: svcrdma: Don't account for Receive queue "starvation" >From what I can tell, calling ->recvfrom when there is no work to do is a normal part of operation. This is the only way svc_recv can tell when there is no more data ready to receive on the transport. Neither the TCP nor the UDP transport implementations have a "starve" metric. The cost of receive starvation accounting is bumping an atomic, which results in extra (IMO unnecessary) bus traffic between CPU sockets, while holding a spin lock. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 21 ++++++--------------- 1 file changed, 6 insertions(+), 15 deletions(-) diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index b48089314f85..1452bd02d857 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -844,9 +844,9 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) struct svc_xprt *xprt = rqstp->rq_xprt; struct svcxprt_rdma *rdma_xprt = container_of(xprt, struct svcxprt_rdma, sc_xprt); - struct svc_rdma_op_ctxt *ctxt = NULL; + struct svc_rdma_op_ctxt *ctxt; struct rpcrdma_msg *rmsgp; - int ret = 0; + int ret; dprintk("svcrdma: rqstp=%p\n", rqstp); @@ -863,21 +863,13 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) struct svc_rdma_op_ctxt, list); list_del(&ctxt->list); } else { - atomic_inc(&rdma_stat_rq_starve); + /* No new incoming requests, terminate the loop */ clear_bit(XPT_DATA, &xprt->xpt_flags); - ctxt = NULL; + spin_unlock(&rdma_xprt->sc_rq_dto_lock); + return 0; } spin_unlock(&rdma_xprt->sc_rq_dto_lock); - if (!ctxt) { - /* This is the EAGAIN path. The svc_recv routine will - * return -EAGAIN, the nfsd thread will go to call into - * svc_recv again and we shouldn't be on the active - * transport list - */ - if (test_bit(XPT_CLOSE, &xprt->xpt_flags)) - goto defer; - goto out; - } + dprintk("svcrdma: processing ctxt=%p on xprt=%p, rqstp=%p\n", ctxt, rdma_xprt, rqstp); atomic_inc(&rdma_stat_recv); @@ -920,7 +912,6 @@ complete: + rqstp->rq_arg.page_len + rqstp->rq_arg.tail[0].iov_len; svc_rdma_put_context(ctxt, 0); - out: dprintk("svcrdma: ret=%d, rq_arg.len=%u, " "rq_arg.head[0].iov_base=%p, rq_arg.head[0].iov_len=%zd\n", ret, rqstp->rq_arg.len, -- cgit v1.2.3-59-g8ed1b From 811642d8d8a82c0cce8dc2debfdaf23c5a144839 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 19 Jun 2017 09:10:32 -0600 Subject: vfio: Fix group release deadlock If vfio_iommu_group_notifier() acquires a group reference and that reference becomes the last reference to the group, then vfio_group_put introduces a deadlock code path where we're trying to unregister from the iommu notifier chain from within a callout of that chain. Use a work_struct to release this reference asynchronously. Signed-off-by: Alex Williamson Reviewed-by: Eric Auger Tested-by: Eric Auger Cc: stable@vger.kernel.org --- drivers/vfio/vfio.c | 37 ++++++++++++++++++++++++++++++++++++- 1 file changed, 36 insertions(+), 1 deletion(-) diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 6a49485eb49d..54dd2fbf83d9 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -423,6 +423,34 @@ static void vfio_group_put(struct vfio_group *group) kref_put_mutex(&group->kref, vfio_group_release, &vfio.group_lock); } +struct vfio_group_put_work { + struct work_struct work; + struct vfio_group *group; +}; + +static void vfio_group_put_bg(struct work_struct *work) +{ + struct vfio_group_put_work *do_work; + + do_work = container_of(work, struct vfio_group_put_work, work); + + vfio_group_put(do_work->group); + kfree(do_work); +} + +static void vfio_group_schedule_put(struct vfio_group *group) +{ + struct vfio_group_put_work *do_work; + + do_work = kmalloc(sizeof(*do_work), GFP_KERNEL); + if (WARN_ON(!do_work)) + return; + + INIT_WORK(&do_work->work, vfio_group_put_bg); + do_work->group = group; + schedule_work(&do_work->work); +} + /* Assume group_lock or group reference is held */ static void vfio_group_get(struct vfio_group *group) { @@ -762,7 +790,14 @@ static int vfio_iommu_group_notifier(struct notifier_block *nb, break; } - vfio_group_put(group); + /* + * If we're the last reference to the group, the group will be + * released, which includes unregistering the iommu group notifier. + * We hold a read-lock on that notifier list, unregistering needs + * a write-lock... deadlock. Release our reference asynchronously + * to avoid that situation. + */ + vfio_group_schedule_put(group); return NOTIFY_OK; } -- cgit v1.2.3-59-g8ed1b From e323369b2e204da4dc771bbddceef986f4bf85d5 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Wed, 28 Jun 2017 13:49:52 -0600 Subject: kvm-vfio: Decouple only when we match a group Unset-KVM and decrement-assignment only when we find the group in our list. Otherwise we can get out of sync if the user triggers this for groups that aren't currently on our list. Signed-off-by: Alex Williamson Reviewed-by: Alexey Kardashevskiy Reviewed-by: Eric Auger Tested-by: Eric Auger Acked-by: Paolo Bonzini Cc: stable@vger.kernel.org --- virt/kvm/vfio.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c index 37d9118fd84b..6e002d0f3191 100644 --- a/virt/kvm/vfio.c +++ b/virt/kvm/vfio.c @@ -246,21 +246,20 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg) continue; list_del(&kvg->node); + kvm_arch_end_assignment(dev->kvm); +#ifdef CONFIG_SPAPR_TCE_IOMMU + kvm_spapr_tce_release_vfio_group(dev->kvm, + kvg->vfio_group); +#endif + kvm_vfio_group_set_kvm(kvg->vfio_group, NULL); kvm_vfio_group_put_external_user(kvg->vfio_group); kfree(kvg); ret = 0; break; } - kvm_arch_end_assignment(dev->kvm); - mutex_unlock(&kv->lock); -#ifdef CONFIG_SPAPR_TCE_IOMMU - kvm_spapr_tce_release_vfio_group(dev->kvm, vfio_group); -#endif - kvm_vfio_group_set_kvm(vfio_group, NULL); - kvm_vfio_group_put_external_user(vfio_group); kvm_vfio_update_coherency(dev); -- cgit v1.2.3-59-g8ed1b From 5d6dee80a1e94cc284d03e06d930e60e8d3ecf7d Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Wed, 28 Jun 2017 13:50:05 -0600 Subject: vfio: New external user group/file match At the point where the kvm-vfio pseudo device wants to release its vfio group reference, we can't always acquire a new reference to make that happen. The group can be in a state where we wouldn't allow a new reference to be added. This new helper function allows a caller to match a file to a group to facilitate this. Given a file and group, report if they match. Thus the caller needs to already have a group reference to match to the file. This allows the deletion of a group without acquiring a new reference. Signed-off-by: Alex Williamson Reviewed-by: Eric Auger Reviewed-by: Paolo Bonzini Tested-by: Eric Auger Cc: stable@vger.kernel.org --- drivers/vfio/vfio.c | 9 +++++++++ include/linux/vfio.h | 2 ++ virt/kvm/vfio.c | 27 +++++++++++++++++++-------- 3 files changed, 30 insertions(+), 8 deletions(-) diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 54dd2fbf83d9..7597a377eb4e 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -1776,6 +1776,15 @@ void vfio_group_put_external_user(struct vfio_group *group) } EXPORT_SYMBOL_GPL(vfio_group_put_external_user); +bool vfio_external_group_match_file(struct vfio_group *test_group, + struct file *filep) +{ + struct vfio_group *group = filep->private_data; + + return (filep->f_op == &vfio_group_fops) && (group == test_group); +} +EXPORT_SYMBOL_GPL(vfio_external_group_match_file); + int vfio_external_user_iommu_id(struct vfio_group *group) { return iommu_group_id(group->iommu_group); diff --git a/include/linux/vfio.h b/include/linux/vfio.h index edf9b2cad277..9b34d0af5d27 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -97,6 +97,8 @@ extern void vfio_unregister_iommu_driver( */ extern struct vfio_group *vfio_group_get_external_user(struct file *filep); extern void vfio_group_put_external_user(struct vfio_group *group); +extern bool vfio_external_group_match_file(struct vfio_group *group, + struct file *filep); extern int vfio_external_user_iommu_id(struct vfio_group *group); extern long vfio_external_check_extension(struct vfio_group *group, unsigned long arg); diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c index 6e002d0f3191..d99850c462a1 100644 --- a/virt/kvm/vfio.c +++ b/virt/kvm/vfio.c @@ -51,6 +51,22 @@ static struct vfio_group *kvm_vfio_group_get_external_user(struct file *filep) return vfio_group; } +static bool kvm_vfio_external_group_match_file(struct vfio_group *group, + struct file *filep) +{ + bool ret, (*fn)(struct vfio_group *, struct file *); + + fn = symbol_get(vfio_external_group_match_file); + if (!fn) + return false; + + ret = fn(group, filep); + + symbol_put(vfio_external_group_match_file); + + return ret; +} + static void kvm_vfio_group_put_external_user(struct vfio_group *vfio_group) { void (*fn)(struct vfio_group *); @@ -231,18 +247,13 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg) if (!f.file) return -EBADF; - vfio_group = kvm_vfio_group_get_external_user(f.file); - fdput(f); - - if (IS_ERR(vfio_group)) - return PTR_ERR(vfio_group); - ret = -ENOENT; mutex_lock(&kv->lock); list_for_each_entry(kvg, &kv->group_list, node) { - if (kvg->vfio_group != vfio_group) + if (!kvm_vfio_external_group_match_file(kvg->vfio_group, + f.file)) continue; list_del(&kvg->node); @@ -260,7 +271,7 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg) mutex_unlock(&kv->lock); - kvm_vfio_group_put_external_user(vfio_group); + fdput(f); kvm_vfio_update_coherency(dev); -- cgit v1.2.3-59-g8ed1b From b392ee07999aa1f19b3a845fad47ec4275341f71 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Thu, 22 Jun 2017 23:06:50 +0800 Subject: MIPS: Loongson: Add NMI handler support Signed-off-by: Huacai Chen Cc: John Crispin Cc: Steven J . Hill Cc: Fuxin Zhang Cc: Zhangjin Wu Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16587/ Signed-off-by: Ralf Baechle --- arch/mips/loongson64/common/init.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/arch/mips/loongson64/common/init.c b/arch/mips/loongson64/common/init.c index 9b987fe98b5b..6ef17120722f 100644 --- a/arch/mips/loongson64/common/init.c +++ b/arch/mips/loongson64/common/init.c @@ -10,13 +10,25 @@ #include #include +#include #include +#include #include /* Loongson CPU address windows config space base address */ unsigned long __maybe_unused _loongson_addrwincfg_base; +static void __init mips_nmi_setup(void) +{ + void *base; + extern char except_vec_nmi; + + base = (void *)(CAC_BASE + 0x380); + memcpy(base, &except_vec_nmi, 0x80); + flush_icache_range((unsigned long)base, (unsigned long)base + 0x80); +} + void __init prom_init(void) { #ifdef CONFIG_CPU_SUPPORTS_ADDRWINCFG @@ -40,6 +52,7 @@ void __init prom_init(void) /*init the uart base address */ prom_init_uart_base(); register_smp_ops(&loongson3_smp_ops); + board_nmi_handler_setup = mips_nmi_setup; } void __init prom_free_prom_memory(void) -- cgit v1.2.3-59-g8ed1b From 99b0b5a3a1e994247e7533de0fd7e4d13ead0ddd Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Thu, 22 Jun 2017 23:06:51 +0800 Subject: MIPS: Loongson-3: Support 4 packages in CPU Hwmon driver Loongson-3 machines may have as many as 4 physical packages. Signed-off-by: Huacai Chen Cc: John Crispin Cc: Steven J . Hill Cc: Fuxin Zhang Cc: Zhangjin Wu Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16588/ Signed-off-by: Ralf Baechle --- drivers/platform/mips/cpu_hwmon.c | 119 +++++++++++++++++++------------------- 1 file changed, 58 insertions(+), 61 deletions(-) diff --git a/drivers/platform/mips/cpu_hwmon.c b/drivers/platform/mips/cpu_hwmon.c index 46ab7d86ae1c..322de58eebaf 100644 --- a/drivers/platform/mips/cpu_hwmon.c +++ b/drivers/platform/mips/cpu_hwmon.c @@ -37,6 +37,7 @@ int loongson3_cpu_temp(int cpu) return (int)reg * 1000; } +static int nr_packages; static struct device *cpu_hwmon_dev; static ssize_t get_hwmon_name(struct device *dev, @@ -60,88 +61,74 @@ static ssize_t get_hwmon_name(struct device *dev, return sprintf(buf, "cpu-hwmon\n"); } -static ssize_t get_cpu0_temp(struct device *dev, +static ssize_t get_cpu_temp(struct device *dev, struct device_attribute *attr, char *buf); -static ssize_t get_cpu1_temp(struct device *dev, - struct device_attribute *attr, char *buf); -static ssize_t cpu0_temp_label(struct device *dev, - struct device_attribute *attr, char *buf); -static ssize_t cpu1_temp_label(struct device *dev, +static ssize_t cpu_temp_label(struct device *dev, struct device_attribute *attr, char *buf); -static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, get_cpu0_temp, NULL, 1); -static SENSOR_DEVICE_ATTR(temp1_label, S_IRUGO, cpu0_temp_label, NULL, 1); -static SENSOR_DEVICE_ATTR(temp2_input, S_IRUGO, get_cpu1_temp, NULL, 2); -static SENSOR_DEVICE_ATTR(temp2_label, S_IRUGO, cpu1_temp_label, NULL, 2); - -static const struct attribute *hwmon_cputemp1[] = { - &sensor_dev_attr_temp1_input.dev_attr.attr, - &sensor_dev_attr_temp1_label.dev_attr.attr, - NULL -}; - -static const struct attribute *hwmon_cputemp2[] = { - &sensor_dev_attr_temp2_input.dev_attr.attr, - &sensor_dev_attr_temp2_label.dev_attr.attr, - NULL +static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, get_cpu_temp, NULL, 1); +static SENSOR_DEVICE_ATTR(temp1_label, S_IRUGO, cpu_temp_label, NULL, 1); +static SENSOR_DEVICE_ATTR(temp2_input, S_IRUGO, get_cpu_temp, NULL, 2); +static SENSOR_DEVICE_ATTR(temp2_label, S_IRUGO, cpu_temp_label, NULL, 2); +static SENSOR_DEVICE_ATTR(temp3_input, S_IRUGO, get_cpu_temp, NULL, 3); +static SENSOR_DEVICE_ATTR(temp3_label, S_IRUGO, cpu_temp_label, NULL, 3); +static SENSOR_DEVICE_ATTR(temp4_input, S_IRUGO, get_cpu_temp, NULL, 4); +static SENSOR_DEVICE_ATTR(temp4_label, S_IRUGO, cpu_temp_label, NULL, 4); + +static const struct attribute *hwmon_cputemp[4][3] = { + { + &sensor_dev_attr_temp1_input.dev_attr.attr, + &sensor_dev_attr_temp1_label.dev_attr.attr, + NULL + }, + { + &sensor_dev_attr_temp2_input.dev_attr.attr, + &sensor_dev_attr_temp2_label.dev_attr.attr, + NULL + }, + { + &sensor_dev_attr_temp3_input.dev_attr.attr, + &sensor_dev_attr_temp3_label.dev_attr.attr, + NULL + }, + { + &sensor_dev_attr_temp4_input.dev_attr.attr, + &sensor_dev_attr_temp4_label.dev_attr.attr, + NULL + } }; -static ssize_t cpu0_temp_label(struct device *dev, +static ssize_t cpu_temp_label(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "CPU 0 Temperature\n"); + int id = (to_sensor_dev_attr(attr))->index - 1; + return sprintf(buf, "CPU %d Temperature\n", id); } -static ssize_t cpu1_temp_label(struct device *dev, +static ssize_t get_cpu_temp(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "CPU 1 Temperature\n"); -} - -static ssize_t get_cpu0_temp(struct device *dev, - struct device_attribute *attr, char *buf) -{ - int value = loongson3_cpu_temp(0); - return sprintf(buf, "%d\n", value); -} - -static ssize_t get_cpu1_temp(struct device *dev, - struct device_attribute *attr, char *buf) -{ - int value = loongson3_cpu_temp(1); + int id = (to_sensor_dev_attr(attr))->index - 1; + int value = loongson3_cpu_temp(id); return sprintf(buf, "%d\n", value); } static int create_sysfs_cputemp_files(struct kobject *kobj) { - int ret; - - ret = sysfs_create_files(kobj, hwmon_cputemp1); - if (ret) - goto sysfs_create_temp1_fail; - - if (loongson_sysconf.nr_cpus <= loongson_sysconf.cores_per_package) - return 0; - - ret = sysfs_create_files(kobj, hwmon_cputemp2); - if (ret) - goto sysfs_create_temp2_fail; + int i, ret = 0; - return 0; + for (i=0; ikobj, hwmon_cputemp1); + int i; - if (loongson_sysconf.nr_cpus > loongson_sysconf.cores_per_package) - sysfs_remove_files(&cpu_hwmon_dev->kobj, hwmon_cputemp2); + for (i=0; i temp_max) + temp_max = value; + } + + if (temp_max <= CPU_THERMAL_THRESHOLD) schedule_delayed_work(&thermal_work, msecs_to_jiffies(5000)); else orderly_poweroff(true); @@ -169,6 +163,9 @@ static int __init loongson_hwmon_init(void) goto fail_hwmon_device_register; } + nr_packages = loongson_sysconf.nr_cpus / + loongson_sysconf.cores_per_package; + ret = sysfs_create_group(&cpu_hwmon_dev->kobj, &cpu_hwmon_attribute_group); if (ret) { -- cgit v1.2.3-59-g8ed1b From e1b88ca8d72193e48bac026b19b8c686cc7fea25 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Thu, 22 Jun 2017 23:06:52 +0800 Subject: MIPS: Loongson-3: IRQ balancing for PCI devices IRQ0 (HPET), IRQ1 (Keyboard), IRQ2 (Cascade), IRQ7 (SCI), IRQ8 (RTC) and IRQ12 (Mouse) are handled by core-0 locally. Other PCI IRQs (3, 4, 5, 6, 14, 15) are balanced by all cores from Node-0. This can improve I/O performance significantly. Signed-off-by: Huacai Chen Cc: John Crispin Cc: Steven J . Hill Cc: Fuxin Zhang Cc: Zhangjin Wu Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16589/ Signed-off-by: Ralf Baechle --- arch/mips/loongson64/loongson-3/irq.c | 19 +++++++++++++++++-- arch/mips/loongson64/loongson-3/smp.c | 18 +++++++++++++++++- 2 files changed, 34 insertions(+), 3 deletions(-) diff --git a/arch/mips/loongson64/loongson-3/irq.c b/arch/mips/loongson64/loongson-3/irq.c index 548f759454dc..2e6e205ed9b9 100644 --- a/arch/mips/loongson64/loongson-3/irq.c +++ b/arch/mips/loongson64/loongson-3/irq.c @@ -9,17 +9,32 @@ #include "smp.h" +extern void loongson3_send_irq_by_ipi(int cpu, int irqs); unsigned int ht_irq[] = {0, 1, 3, 4, 5, 6, 7, 8, 12, 14, 15}; +unsigned int local_irq = 1<<0 | 1<<1 | 1<<2 | 1<<7 | 1<<8 | 1<<12; static void ht_irqdispatch(void) { - unsigned int i, irq; + unsigned int i, irq, irq0, irq1; + static unsigned int dest_cpu = 0; irq = LOONGSON_HT1_INT_VECTOR(0); LOONGSON_HT1_INT_VECTOR(0) = irq; /* Acknowledge the IRQs */ + irq0 = irq & local_irq; /* handled by local core */ + irq1 = irq & ~local_irq; /* balanced by other cores */ + + if (dest_cpu == 0 || !cpu_online(dest_cpu)) + irq0 |= irq1; + else + loongson3_send_irq_by_ipi(dest_cpu, irq1); + + dest_cpu = dest_cpu + 1; + if (dest_cpu >= num_possible_cpus() || cpu_data[dest_cpu].package > 0) + dest_cpu = 0; + for (i = 0; i < ARRAY_SIZE(ht_irq); i++) { - if (irq & (0x1 << ht_irq[i])) + if (irq0 & (0x1 << ht_irq[i])) do_IRQ(ht_irq[i]); } } diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/loongson-3/smp.c index 1629743ba96a..b7a355c3c408 100644 --- a/arch/mips/loongson64/loongson-3/smp.c +++ b/arch/mips/loongson64/loongson-3/smp.c @@ -254,13 +254,21 @@ loongson3_send_ipi_mask(const struct cpumask *mask, unsigned int action) loongson3_ipi_write32((u32)action, ipi_set0_regs[cpu_logical_map(i)]); } +#define IPI_IRQ_OFFSET 6 + +void loongson3_send_irq_by_ipi(int cpu, int irqs) +{ + loongson3_ipi_write32(irqs << IPI_IRQ_OFFSET, ipi_set0_regs[cpu_logical_map(cpu)]); +} + void loongson3_ipi_interrupt(struct pt_regs *regs) { int i, cpu = smp_processor_id(); - unsigned int action, c0count; + unsigned int action, c0count, irqs; /* Load the ipi register to figure out what we're supposed to do */ action = loongson3_ipi_read32(ipi_status0_regs[cpu_logical_map(cpu)]); + irqs = action >> IPI_IRQ_OFFSET; /* Clear the ipi register to clear the interrupt */ loongson3_ipi_write32((u32)action, ipi_clear0_regs[cpu_logical_map(cpu)]); @@ -282,6 +290,14 @@ void loongson3_ipi_interrupt(struct pt_regs *regs) core0_c0count[i] = c0count; __wbflush(); /* Let others see the result ASAP */ } + + if (irqs) { + int irq; + while ((irq = ffs(irqs))) { + do_IRQ(irq-1); + irqs &= ~(1<<(irq-1)); + } + } } #define MAX_LOOPS 800 -- cgit v1.2.3-59-g8ed1b From ecc38a0968ec3e0605079e49d276d9a4186abdb7 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Thu, 22 Jun 2017 23:06:53 +0800 Subject: MIPS: Loongson-3: support irq_set_affinity() in i8259 chip With this patch we can set irq affinity via procfs, so as to improve network performance. Signed-off-by: Huacai Chen Cc: John Crispin Cc: Steven J . Hill Cc: Fuxin Zhang Cc: Zhangjin Wu Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16590/ Signed-off-by: Ralf Baechle --- arch/mips/loongson64/loongson-3/irq.c | 67 ++++++++++++++++++++++++++++------- 1 file changed, 54 insertions(+), 13 deletions(-) diff --git a/arch/mips/loongson64/loongson-3/irq.c b/arch/mips/loongson64/loongson-3/irq.c index 2e6e205ed9b9..7202e52cd046 100644 --- a/arch/mips/loongson64/loongson-3/irq.c +++ b/arch/mips/loongson64/loongson-3/irq.c @@ -10,32 +10,68 @@ #include "smp.h" extern void loongson3_send_irq_by_ipi(int cpu, int irqs); + +unsigned int irq_cpu[16] = {[0 ... 15] = -1}; unsigned int ht_irq[] = {0, 1, 3, 4, 5, 6, 7, 8, 12, 14, 15}; unsigned int local_irq = 1<<0 | 1<<1 | 1<<2 | 1<<7 | 1<<8 | 1<<12; +int plat_set_irq_affinity(struct irq_data *d, const struct cpumask *affinity, + bool force) +{ + unsigned int cpu; + struct cpumask new_affinity; + + /* I/O devices are connected on package-0 */ + cpumask_copy(&new_affinity, affinity); + for_each_cpu(cpu, affinity) + if (cpu_data[cpu].package > 0) + cpumask_clear_cpu(cpu, &new_affinity); + + if (cpumask_empty(&new_affinity)) + return -EINVAL; + + cpumask_copy(d->common->affinity, &new_affinity); + + return IRQ_SET_MASK_OK_NOCOPY; +} + static void ht_irqdispatch(void) { - unsigned int i, irq, irq0, irq1; - static unsigned int dest_cpu = 0; + unsigned int i, irq; + struct irq_data *irqd; + struct cpumask affinity; irq = LOONGSON_HT1_INT_VECTOR(0); LOONGSON_HT1_INT_VECTOR(0) = irq; /* Acknowledge the IRQs */ - irq0 = irq & local_irq; /* handled by local core */ - irq1 = irq & ~local_irq; /* balanced by other cores */ + for (i = 0; i < ARRAY_SIZE(ht_irq); i++) { + if (!(irq & (0x1 << ht_irq[i]))) + continue; - if (dest_cpu == 0 || !cpu_online(dest_cpu)) - irq0 |= irq1; - else - loongson3_send_irq_by_ipi(dest_cpu, irq1); + /* handled by local core */ + if (local_irq & (0x1 << ht_irq[i])) { + do_IRQ(ht_irq[i]); + continue; + } - dest_cpu = dest_cpu + 1; - if (dest_cpu >= num_possible_cpus() || cpu_data[dest_cpu].package > 0) - dest_cpu = 0; + irqd = irq_get_irq_data(ht_irq[i]); + cpumask_and(&affinity, irqd->common->affinity, cpu_active_mask); + if (cpumask_empty(&affinity)) { + do_IRQ(ht_irq[i]); + continue; + } - for (i = 0; i < ARRAY_SIZE(ht_irq); i++) { - if (irq0 & (0x1 << ht_irq[i])) + irq_cpu[ht_irq[i]] = cpumask_next(irq_cpu[ht_irq[i]], &affinity); + if (irq_cpu[ht_irq[i]] >= nr_cpu_ids) + irq_cpu[ht_irq[i]] = cpumask_first(&affinity); + + if (irq_cpu[ht_irq[i]] == 0) { do_IRQ(ht_irq[i]); + continue; + } + + /* balanced by other cores */ + loongson3_send_irq_by_ipi(irq_cpu[ht_irq[i]], (0x1 << ht_irq[i])); } } @@ -135,11 +171,16 @@ void irq_router_init(void) void __init mach_init_irq(void) { + struct irq_chip *chip; + clear_c0_status(ST0_IM | ST0_BEV); irq_router_init(); mips_cpu_irq_init(); init_i8259_irqs(); + chip = irq_get_chip(I8259A_IRQ_BASE); + chip->irq_set_affinity = plat_set_irq_affinity; + irq_set_chip_and_handler(LOONGSON_UART_IRQ, &loongson_irq_chip, handle_level_irq); -- cgit v1.2.3-59-g8ed1b From b9c4dc2cf9af62bc0d2d8504c15175aeac49ad53 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Thu, 22 Jun 2017 23:06:54 +0800 Subject: MIPS: Loogson: Make enum loongson_cpu_type more clear Sort enum loongson_cpu_type in a more reasonable manner, this makes the CPU names more clear and extensible. Those already defined enum values are renamed to Legacy_* for compatibility. Signed-off-by: Huacai Chen Cc: John Crispin Cc: Steven J . Hill Cc: Fuxin Zhang Cc: Zhangjin Wu Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16591/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/mach-loongson64/boot_param.h | 22 ++++++++++++++++------ arch/mips/loongson64/common/env.c | 11 ++++++++--- 2 files changed, 24 insertions(+), 9 deletions(-) diff --git a/arch/mips/include/asm/mach-loongson64/boot_param.h b/arch/mips/include/asm/mach-loongson64/boot_param.h index d3f3258b7cd4..9f9bb9c53785 100644 --- a/arch/mips/include/asm/mach-loongson64/boot_param.h +++ b/arch/mips/include/asm/mach-loongson64/boot_param.h @@ -27,12 +27,22 @@ struct efi_memory_map_loongson { } __packed; enum loongson_cpu_type { - Loongson_2E = 0, - Loongson_2F = 1, - Loongson_3A = 2, - Loongson_3B = 3, - Loongson_1A = 4, - Loongson_1B = 5 + Legacy_2E = 0x0, + Legacy_2F = 0x1, + Legacy_3A = 0x2, + Legacy_3B = 0x3, + Legacy_1A = 0x4, + Legacy_1B = 0x5, + Legacy_2G = 0x6, + Legacy_2H = 0x7, + Loongson_1A = 0x100, + Loongson_1B = 0x101, + Loongson_2E = 0x200, + Loongson_2F = 0x201, + Loongson_2G = 0x202, + Loongson_2H = 0x203, + Loongson_3A = 0x300, + Loongson_3B = 0x301 }; /* diff --git a/arch/mips/loongson64/common/env.c b/arch/mips/loongson64/common/env.c index 4707abfe9d64..1e8a955ae5a8 100644 --- a/arch/mips/loongson64/common/env.c +++ b/arch/mips/loongson64/common/env.c @@ -90,7 +90,9 @@ void __init prom_init_env(void) cpu_clock_freq = ecpu->cpu_clock_freq; loongson_sysconf.cputype = ecpu->cputype; - if (ecpu->cputype == Loongson_3A) { + switch (ecpu->cputype) { + case Legacy_3A: + case Loongson_3A: loongson_sysconf.cores_per_node = 4; loongson_sysconf.cores_per_package = 4; smp_group[0] = 0x900000003ff01000; @@ -111,7 +113,9 @@ void __init prom_init_env(void) loongson_freqctrl[3] = 0x900030001fe001d0; loongson_sysconf.ht_control_base = 0x90000EFDFB000000; loongson_sysconf.workarounds = WORKAROUND_CPUFREQ; - } else if (ecpu->cputype == Loongson_3B) { + break; + case Legacy_3B: + case Loongson_3B: loongson_sysconf.cores_per_node = 4; /* One chip has 2 nodes */ loongson_sysconf.cores_per_package = 8; smp_group[0] = 0x900000003ff01000; @@ -132,7 +136,8 @@ void __init prom_init_env(void) loongson_freqctrl[3] = 0x900060001fe001d0; loongson_sysconf.ht_control_base = 0x90001EFDFB000000; loongson_sysconf.workarounds = WORKAROUND_CPUHOTPLUG; - } else { + break; + default: loongson_sysconf.cores_per_node = 1; loongson_sysconf.cores_per_package = 1; loongson_chipcfg[0] = 0x900000001fe00180; -- cgit v1.2.3-59-g8ed1b From 296a7624f5b292af610d728e7e347fda341a985e Mon Sep 17 00:00:00 2001 From: Miodrag Dinic Date: Mon, 19 Jun 2017 17:50:08 +0200 Subject: MIPS: cmdline: Add support for 'memmap' parameter Implement support for parsing 'memmap' kernel command line parameter. This patch covers parsing of the following two formats for 'memmap' parameter values: - nn[KMG]@ss[KMG] - nn[KMG]$ss[KMG] ([KMG] = K M or G (kilo, mega, giga)) These two allowed formats for parameter value are already documented in file kernel-parameters.txt in Documentation/admin-guide folder. Some architectures already support them, but Mips did not prior to this patch. Excerpt from Documentation/admin-guide/kernel-parameters.txt: memmap=nn[KMG]@ss[KMG] [KNL] Force usage of a specific region of memory. Region of memory to be used is from ss to ss+nn. memmap=nn[KMG]$ss[KMG] Mark specific memory as reserved. Region of memory to be reserved is from ss to ss+nn. Example: Exclude memory from 0x18690000-0x1869ffff memmap=64K$0x18690000 or memmap=0x10000$0x18690000 There is no need to update this documentation file with respect to this patch. Signed-off-by: Miodrag Dinic Signed-off-by: Goran Ferenc Signed-off-by: Aleksandar Markovic Cc: James.Hogan@imgtec.com Cc: Paul.Burton@imgtec.com Cc: Raghu.Gandham@imgtec.com Cc: Leonid.Yegoshin@imgtec.com Cc: Douglas.Leung@imgtec.com Cc: Petar.Jovanovic@imgtec.com Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16508/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/setup.c | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 01d1dbde5fbf..fe3939726765 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -670,6 +670,46 @@ static int __init early_parse_mem(char *p) } early_param("mem", early_parse_mem); +static int __init early_parse_memmap(char *p) +{ + char *oldp; + u64 start_at, mem_size; + + if (!p) + return -EINVAL; + + if (!strncmp(p, "exactmap", 8)) { + pr_err("\"memmap=exactmap\" invalid on MIPS\n"); + return 0; + } + + oldp = p; + mem_size = memparse(p, &p); + if (p == oldp) + return -EINVAL; + + if (*p == '@') { + start_at = memparse(p+1, &p); + add_memory_region(start_at, mem_size, BOOT_MEM_RAM); + } else if (*p == '#') { + pr_err("\"memmap=nn#ss\" (force ACPI data) invalid on MIPS\n"); + return -EINVAL; + } else if (*p == '$') { + start_at = memparse(p+1, &p); + add_memory_region(start_at, mem_size, BOOT_MEM_RESERVED); + } else { + pr_err("\"memmap\" invalid format!\n"); + return -EINVAL; + } + + if (*p == '\0') { + usermem = 1; + return 0; + } else + return -EINVAL; +} +early_param("memmap", early_parse_memmap); + #ifdef CONFIG_PROC_VMCORE unsigned long setup_elfcorehdr, setup_elfcorehdr_size; static int __init early_parse_elfcorehdr(char *p) -- cgit v1.2.3-59-g8ed1b From 21855a6e5b44999fb9f5493cc2c8c9eed5f32876 Mon Sep 17 00:00:00 2001 From: Miodrag Dinic Date: Mon, 19 Jun 2017 17:50:09 +0200 Subject: MIPS: build: Fix "-modd-spreg" switch usage when compiling for mips32r6 Add "-modd-spreg" when compiling the kernel for mips32r6 target. This makes sure the kernel builds properly even with toolchains that use "-mno-odd-spreg" by default. This is the case with Android gcc. Prior to this patch, kernel builds using gcc for Android failed with following error messages, if target architecture is set to mips32r6: arch/mips/kernel/r4k_switch.S: Assembler messages: .../r4k_switch.S:210: Error: float register should be even, was 1 .../r4k_switch.S:212: Error: float register should be even, was 3 .../r4k_switch.S:214: Error: float register should be even, was 5 .../r4k_switch.S:216: Error: float register should be even, was 7 .../r4k_switch.S:218: Error: float register should be even, was 9 .../r4k_switch.S:220: Error: float register should be even, was 11 .../r4k_switch.S:222: Error: float register should be even, was 13 .../r4k_switch.S:224: Error: float register should be even, was 15 .../r4k_switch.S:226: Error: float register should be even, was 17 .../r4k_switch.S:228: Error: float register should be even, was 19 .../r4k_switch.S:230: Error: float register should be even, was 21 .../r4k_switch.S:232: Error: float register should be even, was 23 .../r4k_switch.S:234: Error: float register should be even, was 25 .../r4k_switch.S:236: Error: float register should be even, was 27 .../r4k_switch.S:238: Error: float register should be even, was 29 .../r4k_switch.S:240: Error: float register should be even, was 31 make[2]: *** [arch/mips/kernel/r4k_switch.o] Error 1 Signed-off-by: Miodrag Dinic Signed-off-by: Goran Ferenc Signed-off-by: Aleksandar Markovic Cc: James.Hogan@imgtec.com Cc: Paul.Burton@imgtec.com Cc: Raghu.Gandham@imgtec.com Cc: Leonid.Yegoshin@imgtec.com Cc: Douglas.Leung@imgtec.com Cc: Petar.Jovanovic@imgtec.com Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16509/ Signed-off-by: Ralf Baechle --- arch/mips/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/Makefile b/arch/mips/Makefile index 02a1787c888c..04343625b929 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -160,7 +160,7 @@ cflags-$(CONFIG_CPU_MIPS32_R1) += $(call cc-option,-march=mips32,-mips32 -U_MIPS -Wa,-mips32 -Wa,--trap cflags-$(CONFIG_CPU_MIPS32_R2) += $(call cc-option,-march=mips32r2,-mips32r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS32) \ -Wa,-mips32r2 -Wa,--trap -cflags-$(CONFIG_CPU_MIPS32_R6) += -march=mips32r6 -Wa,--trap +cflags-$(CONFIG_CPU_MIPS32_R6) += -march=mips32r6 -Wa,--trap -modd-spreg cflags-$(CONFIG_CPU_MIPS64_R1) += $(call cc-option,-march=mips64,-mips64 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) \ -Wa,-mips64 -Wa,--trap cflags-$(CONFIG_CPU_MIPS64_R2) += $(call cc-option,-march=mips64r2,-mips64r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) \ -- cgit v1.2.3-59-g8ed1b From 3daf281f2ce3b80cc1abf04f355f066e37f69451 Mon Sep 17 00:00:00 2001 From: Leonid Yegoshin Date: Mon, 19 Jun 2017 17:50:10 +0200 Subject: MIPS: R6: Fix PREF instruction usage by memcpy for MIPS R6 Disable usage of PREF instruction usage by memcpy for MIPS R6. MIPS R6 redefines PREF instruction with smaller offset than ordinary MIPS. However, the memcpy code uses PREF instruction with offsets bigger than +-256 bytes. Malta kernels already disable usage of PREF for memcpy. This was found during adaptation of MIPS R6 for virtual board used by Android emulator. Signed-off-by: Leonid Yegoshin Signed-off-by: Miodrag Dinic Signed-off-by: Goran Ferenc Signed-off-by: Aleksandar Markovic Cc: James.Hogan@imgtec.com Cc: Paul.Burton@imgtec.com Cc: Raghu.Gandham@imgtec.com Cc: Leonid.Yegoshin@imgtec.com Cc: Douglas.Leung@imgtec.com Cc: Petar.Jovanovic@imgtec.com Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16510/ Signed-off-by: Ralf Baechle --- arch/mips/lib/memcpy.S | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/mips/lib/memcpy.S b/arch/mips/lib/memcpy.S index 3114a2ed1f4e..03e3304d6ae5 100644 --- a/arch/mips/lib/memcpy.S +++ b/arch/mips/lib/memcpy.S @@ -28,6 +28,9 @@ #ifdef CONFIG_MIPS_MALTA #undef CONFIG_CPU_HAS_PREFETCH #endif +#ifdef CONFIG_CPU_MIPSR6 +#undef CONFIG_CPU_HAS_PREFETCH +#endif #include #include -- cgit v1.2.3-59-g8ed1b From 3f88ec633362efa454ca4ea289d4ad91cd44a976 Mon Sep 17 00:00:00 2001 From: Miodrag Dinic Date: Mon, 19 Jun 2017 17:50:11 +0200 Subject: MIPS: unaligned: Add DSP lwx & lhx missaligned access support Add handling of missaligned access for DSP load instructions lwx & lhx. Since DSP instructions share SPECIAL3 opcode with other non-DSP instructions, necessary logic was inserted for distinguishing between instructions with SPECIAL3 opcode. For that purpose, the instruction format for DSP instructions is added to arch/mips/include/uapi/asm/inst.h. Signed-off-by: Miodrag Dinic Signed-off-by: Aleksandar Markovic Cc: James.Hogan@imgtec.com Cc: Paul.Burton@imgtec.com Cc: Raghu.Gandham@imgtec.com Cc: Leonid.Yegoshin@imgtec.com Cc: Douglas.Leung@imgtec.com Cc: Petar.Jovanovic@imgtec.com Cc: Goran.Ferenc@imgtec.com Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16511/ Signed-off-by: Ralf Baechle --- arch/mips/include/uapi/asm/inst.h | 11 +++ arch/mips/kernel/unaligned.c | 174 ++++++++++++++++++++++---------------- 2 files changed, 111 insertions(+), 74 deletions(-) diff --git a/arch/mips/include/uapi/asm/inst.h b/arch/mips/include/uapi/asm/inst.h index e5f538584b8e..d61897535926 100644 --- a/arch/mips/include/uapi/asm/inst.h +++ b/arch/mips/include/uapi/asm/inst.h @@ -762,6 +762,16 @@ struct msa_mi10_format { /* MSA MI10 */ ;)))))) }; +struct dsp_format { /* SPEC3 DSP format instructions */ + __BITFIELD_FIELD(unsigned int opcode : 6, + __BITFIELD_FIELD(unsigned int base : 5, + __BITFIELD_FIELD(unsigned int index : 5, + __BITFIELD_FIELD(unsigned int rd : 5, + __BITFIELD_FIELD(unsigned int op : 5, + __BITFIELD_FIELD(unsigned int func : 6, + ;)))))) +}; + struct spec3_format { /* SPEC3 */ __BITFIELD_FIELD(unsigned int opcode:6, __BITFIELD_FIELD(unsigned int rs:5, @@ -1053,6 +1063,7 @@ union mips_instruction { struct b_format b_format; struct ps_format ps_format; struct v_format v_format; + struct dsp_format dsp_format; struct spec3_format spec3_format; struct fb_format fb_format; struct fp0_format fp0_format; diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c index f806ee56e639..67946bb98dd0 100644 --- a/arch/mips/kernel/unaligned.c +++ b/arch/mips/kernel/unaligned.c @@ -939,88 +939,114 @@ static void emulate_load_store_insn(struct pt_regs *regs, * The remaining opcodes are the ones that are really of * interest. */ -#ifdef CONFIG_EVA case spec3_op: - /* - * we can land here only from kernel accessing user memory, - * so we need to "switch" the address limit to user space, so - * address check can work properly. - */ - seg = get_fs(); - set_fs(USER_DS); - switch (insn.spec3_format.func) { - case lhe_op: - if (!access_ok(VERIFY_READ, addr, 2)) { - set_fs(seg); - goto sigbus; - } - LoadHWE(addr, value, res); - if (res) { - set_fs(seg); - goto fault; - } - compute_return_epc(regs); - regs->regs[insn.spec3_format.rt] = value; - break; - case lwe_op: - if (!access_ok(VERIFY_READ, addr, 4)) { - set_fs(seg); - goto sigbus; + if (insn.dsp_format.func == lx_op) { + switch (insn.dsp_format.op) { + case lwx_op: + if (!access_ok(VERIFY_READ, addr, 4)) + goto sigbus; + LoadW(addr, value, res); + if (res) + goto fault; + compute_return_epc(regs); + regs->regs[insn.dsp_format.rd] = value; + break; + case lhx_op: + if (!access_ok(VERIFY_READ, addr, 2)) + goto sigbus; + LoadHW(addr, value, res); + if (res) + goto fault; + compute_return_epc(regs); + regs->regs[insn.dsp_format.rd] = value; + break; + default: + goto sigill; } + } +#ifdef CONFIG_EVA + else { + /* + * we can land here only from kernel accessing user + * memory, so we need to "switch" the address limit to + * user space, so that address check can work properly. + */ + seg = get_fs(); + set_fs(USER_DS); + switch (insn.spec3_format.func) { + case lhe_op: + if (!access_ok(VERIFY_READ, addr, 2)) { + set_fs(seg); + goto sigbus; + } + LoadHWE(addr, value, res); + if (res) { + set_fs(seg); + goto fault; + } + compute_return_epc(regs); + regs->regs[insn.spec3_format.rt] = value; + break; + case lwe_op: + if (!access_ok(VERIFY_READ, addr, 4)) { + set_fs(seg); + goto sigbus; + } LoadWE(addr, value, res); - if (res) { - set_fs(seg); - goto fault; - } - compute_return_epc(regs); - regs->regs[insn.spec3_format.rt] = value; - break; - case lhue_op: - if (!access_ok(VERIFY_READ, addr, 2)) { - set_fs(seg); - goto sigbus; - } - LoadHWUE(addr, value, res); - if (res) { - set_fs(seg); - goto fault; - } - compute_return_epc(regs); - regs->regs[insn.spec3_format.rt] = value; - break; - case she_op: - if (!access_ok(VERIFY_WRITE, addr, 2)) { - set_fs(seg); - goto sigbus; - } - compute_return_epc(regs); - value = regs->regs[insn.spec3_format.rt]; - StoreHWE(addr, value, res); - if (res) { - set_fs(seg); - goto fault; - } - break; - case swe_op: - if (!access_ok(VERIFY_WRITE, addr, 4)) { - set_fs(seg); - goto sigbus; - } - compute_return_epc(regs); - value = regs->regs[insn.spec3_format.rt]; - StoreWE(addr, value, res); - if (res) { + if (res) { + set_fs(seg); + goto fault; + } + compute_return_epc(regs); + regs->regs[insn.spec3_format.rt] = value; + break; + case lhue_op: + if (!access_ok(VERIFY_READ, addr, 2)) { + set_fs(seg); + goto sigbus; + } + LoadHWUE(addr, value, res); + if (res) { + set_fs(seg); + goto fault; + } + compute_return_epc(regs); + regs->regs[insn.spec3_format.rt] = value; + break; + case she_op: + if (!access_ok(VERIFY_WRITE, addr, 2)) { + set_fs(seg); + goto sigbus; + } + compute_return_epc(regs); + value = regs->regs[insn.spec3_format.rt]; + StoreHWE(addr, value, res); + if (res) { + set_fs(seg); + goto fault; + } + break; + case swe_op: + if (!access_ok(VERIFY_WRITE, addr, 4)) { + set_fs(seg); + goto sigbus; + } + compute_return_epc(regs); + value = regs->regs[insn.spec3_format.rt]; + StoreWE(addr, value, res); + if (res) { + set_fs(seg); + goto fault; + } + break; + default: set_fs(seg); - goto fault; + goto sigill; } - break; - default: set_fs(seg); - goto sigill; } - set_fs(seg); - break; #endif + break; case lh_op: if (!access_ok(VERIFY_READ, addr, 2)) goto sigbus; -- cgit v1.2.3-59-g8ed1b From 6b1e76297c4ad4b906fdf054460e4e56914f6e34 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 9 Jun 2017 17:26:33 -0700 Subject: MIPS: cmpxchg: Unify R10000_LLSC_WAR & non-R10000_LLSC_WAR cases Prior to this patch the xchg & cmpxchg functions have duplicated code which is for all intents & purposes identical apart from use of a branch-likely instruction in the R10000_LLSC_WAR case & a regular branch instruction in the non-R10000_LLSC_WAR case. This patch removes the duplication, declaring a __scbeqz macro to select the branch instruction suitable for use when checking the result of an sc instruction & making use of it to unify the 2 cases. In __xchg_u{32,64}() this means writing the branch in asm, where it was previously being done in C as a do...while loop for the non-R10000_LLSC_WAR case. As this is a single instruction, and adds consistency with the R10000_LLSC_WAR cases & the cmpxchg() code, this seems worthwhile. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16348/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/cmpxchg.h | 80 ++++++++++++----------------------------- 1 file changed, 22 insertions(+), 58 deletions(-) diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h index b71ab4a5fd50..0582c01d229d 100644 --- a/arch/mips/include/asm/cmpxchg.h +++ b/arch/mips/include/asm/cmpxchg.h @@ -13,44 +13,38 @@ #include #include +/* + * Using a branch-likely instruction to check the result of an sc instruction + * works around a bug present in R10000 CPUs prior to revision 3.0 that could + * cause ll-sc sequences to execute non-atomically. + */ +#if R10000_LLSC_WAR +# define __scbeqz "beqzl" +#else +# define __scbeqz "beqz" +#endif + static inline unsigned long __xchg_u32(volatile int * m, unsigned int val) { __u32 retval; smp_mb__before_llsc(); - if (kernel_uses_llsc && R10000_LLSC_WAR) { + if (kernel_uses_llsc) { unsigned long dummy; __asm__ __volatile__( - " .set arch=r4000 \n" + " .set " MIPS_ISA_ARCH_LEVEL " \n" "1: ll %0, %3 # xchg_u32 \n" " .set mips0 \n" " move %2, %z4 \n" - " .set arch=r4000 \n" + " .set " MIPS_ISA_ARCH_LEVEL " \n" " sc %2, %1 \n" - " beqzl %2, 1b \n" + "\t" __scbeqz " %2, 1b \n" " .set mips0 \n" : "=&r" (retval), "=" GCC_OFF_SMALL_ASM() (*m), "=&r" (dummy) : GCC_OFF_SMALL_ASM() (*m), "Jr" (val) : "memory"); - } else if (kernel_uses_llsc) { - unsigned long dummy; - - do { - __asm__ __volatile__( - " .set "MIPS_ISA_ARCH_LEVEL" \n" - " ll %0, %3 # xchg_u32 \n" - " .set mips0 \n" - " move %2, %z4 \n" - " .set "MIPS_ISA_ARCH_LEVEL" \n" - " sc %2, %1 \n" - " .set mips0 \n" - : "=&r" (retval), "=" GCC_OFF_SMALL_ASM() (*m), - "=&r" (dummy) - : GCC_OFF_SMALL_ASM() (*m), "Jr" (val) - : "memory"); - } while (unlikely(!dummy)); } else { unsigned long flags; @@ -72,34 +66,19 @@ static inline __u64 __xchg_u64(volatile __u64 * m, __u64 val) smp_mb__before_llsc(); - if (kernel_uses_llsc && R10000_LLSC_WAR) { + if (kernel_uses_llsc) { unsigned long dummy; __asm__ __volatile__( - " .set arch=r4000 \n" + " .set " MIPS_ISA_ARCH_LEVEL " \n" "1: lld %0, %3 # xchg_u64 \n" " move %2, %z4 \n" " scd %2, %1 \n" - " beqzl %2, 1b \n" + "\t" __scbeqz " %2, 1b \n" " .set mips0 \n" : "=&r" (retval), "=" GCC_OFF_SMALL_ASM() (*m), "=&r" (dummy) : GCC_OFF_SMALL_ASM() (*m), "Jr" (val) : "memory"); - } else if (kernel_uses_llsc) { - unsigned long dummy; - - do { - __asm__ __volatile__( - " .set "MIPS_ISA_ARCH_LEVEL" \n" - " lld %0, %3 # xchg_u64 \n" - " move %2, %z4 \n" - " scd %2, %1 \n" - " .set mips0 \n" - : "=&r" (retval), "=" GCC_OFF_SMALL_ASM() (*m), - "=&r" (dummy) - : GCC_OFF_SMALL_ASM() (*m), "Jr" (val) - : "memory"); - } while (unlikely(!dummy)); } else { unsigned long flags; @@ -142,24 +121,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz ({ \ __typeof(*(m)) __ret; \ \ - if (kernel_uses_llsc && R10000_LLSC_WAR) { \ - __asm__ __volatile__( \ - " .set push \n" \ - " .set noat \n" \ - " .set arch=r4000 \n" \ - "1: " ld " %0, %2 # __cmpxchg_asm \n" \ - " bne %0, %z3, 2f \n" \ - " .set mips0 \n" \ - " move $1, %z4 \n" \ - " .set arch=r4000 \n" \ - " " st " $1, %1 \n" \ - " beqzl $1, 1b \n" \ - "2: \n" \ - " .set pop \n" \ - : "=&r" (__ret), "=" GCC_OFF_SMALL_ASM() (*m) \ - : GCC_OFF_SMALL_ASM() (*m), "Jr" (old), "Jr" (new) \ - : "memory"); \ - } else if (kernel_uses_llsc) { \ + if (kernel_uses_llsc) { \ __asm__ __volatile__( \ " .set push \n" \ " .set noat \n" \ @@ -170,7 +132,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz " move $1, %z4 \n" \ " .set "MIPS_ISA_ARCH_LEVEL" \n" \ " " st " $1, %1 \n" \ - " beqz $1, 1b \n" \ + "\t" __scbeqz " $1, 1b \n" \ " .set pop \n" \ "2: \n" \ : "=&r" (__ret), "=" GCC_OFF_SMALL_ASM() (*m) \ @@ -245,4 +207,6 @@ extern void __cmpxchg_called_with_bad_pointer(void); #define cmpxchg64(ptr, o, n) cmpxchg64_local((ptr), (o), (n)) #endif +#undef __scbeqz + #endif /* __ASM_CMPXCHG_H */ -- cgit v1.2.3-59-g8ed1b From 5154f3b4194910a4216866e7535c37e5bcb17800 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 9 Jun 2017 17:26:34 -0700 Subject: MIPS: cmpxchg: Pull xchg() asm into a macro Use a macro to generate the 32 & 64 bit variants of the backing code for xchg(), much as is already done for cmpxchg(). This removes the duplication that could previously be found in __xchg_u32() & __xchg_u64(). Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16349/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/cmpxchg.h | 81 +++++++++++++++++------------------------ 1 file changed, 33 insertions(+), 48 deletions(-) diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h index 0582c01d229d..a19359649b60 100644 --- a/arch/mips/include/asm/cmpxchg.h +++ b/arch/mips/include/asm/cmpxchg.h @@ -24,36 +24,43 @@ # define __scbeqz "beqz" #endif +#define __xchg_asm(ld, st, m, val) \ +({ \ + __typeof(*(m)) __ret; \ + \ + if (kernel_uses_llsc) { \ + __asm__ __volatile__( \ + " .set push \n" \ + " .set noat \n" \ + " .set " MIPS_ISA_ARCH_LEVEL " \n" \ + "1: " ld " %0, %2 # __xchg_asm \n" \ + " .set mips0 \n" \ + " move $1, %z3 \n" \ + " .set " MIPS_ISA_ARCH_LEVEL " \n" \ + " " st " $1, %1 \n" \ + "\t" __scbeqz " $1, 1b \n" \ + " .set pop \n" \ + : "=&r" (__ret), "=" GCC_OFF_SMALL_ASM() (*m) \ + : GCC_OFF_SMALL_ASM() (*m), "Jr" (val) \ + : "memory"); \ + } else { \ + unsigned long __flags; \ + \ + raw_local_irq_save(__flags); \ + __ret = *m; \ + *m = val; \ + raw_local_irq_restore(__flags); \ + } \ + \ + __ret; \ +}) + static inline unsigned long __xchg_u32(volatile int * m, unsigned int val) { __u32 retval; smp_mb__before_llsc(); - - if (kernel_uses_llsc) { - unsigned long dummy; - - __asm__ __volatile__( - " .set " MIPS_ISA_ARCH_LEVEL " \n" - "1: ll %0, %3 # xchg_u32 \n" - " .set mips0 \n" - " move %2, %z4 \n" - " .set " MIPS_ISA_ARCH_LEVEL " \n" - " sc %2, %1 \n" - "\t" __scbeqz " %2, 1b \n" - " .set mips0 \n" - : "=&r" (retval), "=" GCC_OFF_SMALL_ASM() (*m), "=&r" (dummy) - : GCC_OFF_SMALL_ASM() (*m), "Jr" (val) - : "memory"); - } else { - unsigned long flags; - - raw_local_irq_save(flags); - retval = *m; - *m = val; - raw_local_irq_restore(flags); /* implies memory barrier */ - } - + retval = __xchg_asm("ll", "sc", m, val); smp_llsc_mb(); return retval; @@ -65,29 +72,7 @@ static inline __u64 __xchg_u64(volatile __u64 * m, __u64 val) __u64 retval; smp_mb__before_llsc(); - - if (kernel_uses_llsc) { - unsigned long dummy; - - __asm__ __volatile__( - " .set " MIPS_ISA_ARCH_LEVEL " \n" - "1: lld %0, %3 # xchg_u64 \n" - " move %2, %z4 \n" - " scd %2, %1 \n" - "\t" __scbeqz " %2, 1b \n" - " .set mips0 \n" - : "=&r" (retval), "=" GCC_OFF_SMALL_ASM() (*m), "=&r" (dummy) - : GCC_OFF_SMALL_ASM() (*m), "Jr" (val) - : "memory"); - } else { - unsigned long flags; - - raw_local_irq_save(flags); - retval = *m; - *m = val; - raw_local_irq_restore(flags); /* implies memory barrier */ - } - + retval = __xchg_asm("lld", "scd", m, val); smp_llsc_mb(); return retval; -- cgit v1.2.3-59-g8ed1b From 77299db802d4a7ae43f7ca246adbff0420bc9f5a Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 9 Jun 2017 17:26:35 -0700 Subject: MIPS: cmpxchg: Use __compiletime_error() for bad cmpxchg() pointers Our cmpxchg() implementation relies upon generating a call to a function which doesn't really exist (__cmpxchg_called_with_bad_pointer) to create a link failure in cases where cmpxchg() is called with a pointer to a value of an unsupported size. The __compiletime_error macro can be used to decorate a function such that a call to it generates a compile-time, rather than a link-time, error. This patch uses __compiletime_error to cause bad cmpxchg() calls to error out at compile time rather than link time, allowing errors to occur more quickly & making it easier to spot where the problem comes from. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16350/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/cmpxchg.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h index a19359649b60..ee0214e00ab1 100644 --- a/arch/mips/include/asm/cmpxchg.h +++ b/arch/mips/include/asm/cmpxchg.h @@ -137,10 +137,17 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz }) /* - * This function doesn't exist, so you'll get a linker error - * if something tries to do an invalid cmpxchg(). + * This function doesn't exist, so if it is called you'll either: + * + * - Get an error at compile-time due to __compiletime_error, if supported by + * your compiler. + * + * or: + * + * - Get an error at link-time due to the call to the missing function. */ -extern void __cmpxchg_called_with_bad_pointer(void); +extern void __cmpxchg_called_with_bad_pointer(void) + __compiletime_error("Bad argument size for cmpxchg"); #define __cmpxchg(ptr, old, new, pre_barrier, post_barrier) \ ({ \ -- cgit v1.2.3-59-g8ed1b From d15dc68c1143e249c36612c15bf4e930637b47c3 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 9 Jun 2017 17:26:36 -0700 Subject: MIPS: cmpxchg: Error out on unsupported xchg() calls xchg() has up until now simply returned the x parameter in cases where it is called with a pointer to a value of an unsupported size. This will often cause the calling code to hit a failure path, presuming that the value of x differs from the content of the memory pointed at by ptr, but we can do better by producing a compile-time or link-time error such that unsupported calls to xchg() are detectable earlier than runtime. This patch does this in the same was as is already done for cmpxchg(), using a call to a missing function annotated with __compiletime_error(). Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16351/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/cmpxchg.h | 32 +++++++++++++++++--------------- 1 file changed, 17 insertions(+), 15 deletions(-) diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h index ee0214e00ab1..fe652c3e5d8c 100644 --- a/arch/mips/include/asm/cmpxchg.h +++ b/arch/mips/include/asm/cmpxchg.h @@ -24,6 +24,21 @@ # define __scbeqz "beqz" #endif +/* + * These functions doesn't exist, so if they are called you'll either: + * + * - Get an error at compile-time due to __compiletime_error, if supported by + * your compiler. + * + * or: + * + * - Get an error at link-time due to the call to the missing function. + */ +extern void __cmpxchg_called_with_bad_pointer(void) + __compiletime_error("Bad argument size for cmpxchg"); +extern unsigned long __xchg_called_with_bad_pointer(void) + __compiletime_error("Bad argument size for xchg"); + #define __xchg_asm(ld, st, m, val) \ ({ \ __typeof(*(m)) __ret; \ @@ -89,9 +104,9 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz return __xchg_u32(ptr, x); case 8: return __xchg_u64(ptr, x); + default: + return __xchg_called_with_bad_pointer(); } - - return x; } #define xchg(ptr, x) \ @@ -136,19 +151,6 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz __ret; \ }) -/* - * This function doesn't exist, so if it is called you'll either: - * - * - Get an error at compile-time due to __compiletime_error, if supported by - * your compiler. - * - * or: - * - * - Get an error at link-time due to the call to the missing function. - */ -extern void __cmpxchg_called_with_bad_pointer(void) - __compiletime_error("Bad argument size for cmpxchg"); - #define __cmpxchg(ptr, old, new, pre_barrier, post_barrier) \ ({ \ __typeof__(ptr) __ptr = (ptr); \ -- cgit v1.2.3-59-g8ed1b From 62c6081dca75d6bec1198ed5a1ae50968b323a8c Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 9 Jun 2017 17:26:37 -0700 Subject: MIPS: cmpxchg: Drop __xchg_u{32,64} functions The __xchg_u32() & __xchg_u64() functions now add very little value. This patch therefore removes them, by: - Moving memory barriers out of them & into xchg(), which also removes the duplication & readies us to support xchg_relaxed() if we wish to. - Calling __xchg_asm() directly from __xchg(). - Performing the check for CONFIG_64BIT being enabled in the size=8 case of __xchg(). Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16352/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/cmpxchg.h | 48 +++++++++++++++-------------------------- 1 file changed, 17 insertions(+), 31 deletions(-) diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h index fe652c3e5d8c..e9c1e97bc29d 100644 --- a/arch/mips/include/asm/cmpxchg.h +++ b/arch/mips/include/asm/cmpxchg.h @@ -70,40 +70,18 @@ extern unsigned long __xchg_called_with_bad_pointer(void) __ret; \ }) -static inline unsigned long __xchg_u32(volatile int * m, unsigned int val) -{ - __u32 retval; - - smp_mb__before_llsc(); - retval = __xchg_asm("ll", "sc", m, val); - smp_llsc_mb(); - - return retval; -} - -#ifdef CONFIG_64BIT -static inline __u64 __xchg_u64(volatile __u64 * m, __u64 val) -{ - __u64 retval; - - smp_mb__before_llsc(); - retval = __xchg_asm("lld", "scd", m, val); - smp_llsc_mb(); - - return retval; -} -#else -extern __u64 __xchg_u64_unsupported_on_32bit_kernels(volatile __u64 * m, __u64 val); -#define __xchg_u64 __xchg_u64_unsupported_on_32bit_kernels -#endif - static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size) { switch (size) { case 4: - return __xchg_u32(ptr, x); + return __xchg_asm("ll", "sc", (volatile u32 *)ptr, x); + case 8: - return __xchg_u64(ptr, x); + if (!IS_ENABLED(CONFIG_64BIT)) + return __xchg_called_with_bad_pointer(); + + return __xchg_asm("lld", "scd", (volatile u64 *)ptr, x); + default: return __xchg_called_with_bad_pointer(); } @@ -111,10 +89,18 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz #define xchg(ptr, x) \ ({ \ + __typeof__(*(ptr)) __res; \ + \ BUILD_BUG_ON(sizeof(*(ptr)) & ~0xc); \ \ - ((__typeof__(*(ptr))) \ - __xchg((unsigned long)(x), (ptr), sizeof(*(ptr)))); \ + smp_mb__before_llsc(); \ + \ + __res = (__typeof__(*(ptr))) \ + __xchg((unsigned long)(x), (ptr), sizeof(*(ptr))); \ + \ + smp_llsc_mb(); \ + \ + __res; \ }) #define __cmpxchg_asm(ld, st, m, old, new) \ -- cgit v1.2.3-59-g8ed1b From 8263db4d7768448cb06adbbdd14c613a1ea09830 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 9 Jun 2017 17:26:38 -0700 Subject: MIPS: cmpxchg: Implement __cmpxchg() as a function Replace the macro definition of __cmpxchg() with an inline function, which is easier to read & modify. The cmpxchg() & cmpxchg_local() macros are adjusted to call the new __cmpxchg() function. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16353/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/cmpxchg.h | 59 ++++++++++++++++++++++------------------- 1 file changed, 32 insertions(+), 27 deletions(-) diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h index e9c1e97bc29d..516cb66f066b 100644 --- a/arch/mips/include/asm/cmpxchg.h +++ b/arch/mips/include/asm/cmpxchg.h @@ -34,7 +34,7 @@ * * - Get an error at link-time due to the call to the missing function. */ -extern void __cmpxchg_called_with_bad_pointer(void) +extern unsigned long __cmpxchg_called_with_bad_pointer(void) __compiletime_error("Bad argument size for cmpxchg"); extern unsigned long __xchg_called_with_bad_pointer(void) __compiletime_error("Bad argument size for xchg"); @@ -137,38 +137,43 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz __ret; \ }) -#define __cmpxchg(ptr, old, new, pre_barrier, post_barrier) \ +static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, + unsigned long new, unsigned int size) +{ + switch (size) { + case 4: + return __cmpxchg_asm("ll", "sc", (volatile u32 *)ptr, old, new); + + case 8: + /* lld/scd are only available for MIPS64 */ + if (!IS_ENABLED(CONFIG_64BIT)) + return __cmpxchg_called_with_bad_pointer(); + + return __cmpxchg_asm("lld", "scd", (volatile u64 *)ptr, old, new); + + default: + return __cmpxchg_called_with_bad_pointer(); + } +} + +#define cmpxchg_local(ptr, old, new) \ + ((__typeof__(*(ptr))) \ + __cmpxchg((ptr), \ + (unsigned long)(__typeof__(*(ptr)))(old), \ + (unsigned long)(__typeof__(*(ptr)))(new), \ + sizeof(*(ptr)))) + +#define cmpxchg(ptr, old, new) \ ({ \ - __typeof__(ptr) __ptr = (ptr); \ - __typeof__(*(ptr)) __old = (old); \ - __typeof__(*(ptr)) __new = (new); \ - __typeof__(*(ptr)) __res = 0; \ - \ - pre_barrier; \ - \ - switch (sizeof(*(__ptr))) { \ - case 4: \ - __res = __cmpxchg_asm("ll", "sc", __ptr, __old, __new); \ - break; \ - case 8: \ - if (sizeof(long) == 8) { \ - __res = __cmpxchg_asm("lld", "scd", __ptr, \ - __old, __new); \ - break; \ - } \ - default: \ - __cmpxchg_called_with_bad_pointer(); \ - break; \ - } \ + __typeof__(*(ptr)) __res; \ \ - post_barrier; \ + smp_mb__before_llsc(); \ + __res = cmpxchg_local((ptr), (old), (new)); \ + smp_llsc_mb(); \ \ __res; \ }) -#define cmpxchg(ptr, old, new) __cmpxchg(ptr, old, new, smp_mb__before_llsc(), smp_llsc_mb()) -#define cmpxchg_local(ptr, old, new) __cmpxchg(ptr, old, new, , ) - #ifdef CONFIG_64BIT #define cmpxchg64_local(ptr, o, n) \ ({ \ -- cgit v1.2.3-59-g8ed1b From b70eb30056dc84568f3d32440d9be6a558025843 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 9 Jun 2017 17:26:39 -0700 Subject: MIPS: cmpxchg: Implement 1 byte & 2 byte xchg() Implement 1 & 2 byte xchg() using read-modify-write atop a 4 byte cmpxchg(). This allows us to support these atomic operations despite the MIPS ISA only providing for 4 & 8 byte atomic operations. This is required in order to support queued spinlocks (qspinlock) in a later patch, since these make use of a 2 byte xchg() in their slow path. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16354/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/cmpxchg.h | 9 +++++-- arch/mips/kernel/Makefile | 2 +- arch/mips/kernel/cmpxchg.c | 52 +++++++++++++++++++++++++++++++++++++++++ 3 files changed, 60 insertions(+), 3 deletions(-) create mode 100644 arch/mips/kernel/cmpxchg.c diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h index 516cb66f066b..a633bf845689 100644 --- a/arch/mips/include/asm/cmpxchg.h +++ b/arch/mips/include/asm/cmpxchg.h @@ -70,9 +70,16 @@ extern unsigned long __xchg_called_with_bad_pointer(void) __ret; \ }) +extern unsigned long __xchg_small(volatile void *ptr, unsigned long val, + unsigned int size); + static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size) { switch (size) { + case 1: + case 2: + return __xchg_small(ptr, x, size); + case 4: return __xchg_asm("ll", "sc", (volatile u32 *)ptr, x); @@ -91,8 +98,6 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz ({ \ __typeof__(*(ptr)) __res; \ \ - BUILD_BUG_ON(sizeof(*(ptr)) & ~0xc); \ - \ smp_mb__before_llsc(); \ \ __res = (__typeof__(*(ptr))) \ diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile index f0edd7e8a0b7..46c0581256f1 100644 --- a/arch/mips/kernel/Makefile +++ b/arch/mips/kernel/Makefile @@ -4,7 +4,7 @@ extra-y := head.o vmlinux.lds -obj-y += cpu-probe.o branch.o elf.o entry.o genex.o idle.o irq.o \ +obj-y += cmpxchg.o cpu-probe.o branch.o elf.o entry.o genex.o idle.o irq.o \ process.o prom.o ptrace.o reset.o setup.o signal.o \ syscall.o time.o topology.o traps.o unaligned.o watch.o \ vdso.o cacheinfo.o diff --git a/arch/mips/kernel/cmpxchg.c b/arch/mips/kernel/cmpxchg.c new file mode 100644 index 000000000000..5acfbf9fb2c5 --- /dev/null +++ b/arch/mips/kernel/cmpxchg.c @@ -0,0 +1,52 @@ +/* + * Copyright (C) 2017 Imagination Technologies + * Author: Paul Burton + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include +#include + +unsigned long __xchg_small(volatile void *ptr, unsigned long val, unsigned int size) +{ + u32 old32, new32, load32, mask; + volatile u32 *ptr32; + unsigned int shift; + + /* Check that ptr is naturally aligned */ + WARN_ON((unsigned long)ptr & (size - 1)); + + /* Mask value to the correct size. */ + mask = GENMASK((size * BITS_PER_BYTE) - 1, 0); + val &= mask; + + /* + * Calculate a shift & mask that correspond to the value we wish to + * exchange within the naturally aligned 4 byte integerthat includes + * it. + */ + shift = (unsigned long)ptr & 0x3; + if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) + shift ^= sizeof(u32) - size; + shift *= BITS_PER_BYTE; + mask <<= shift; + + /* + * Calculate a pointer to the naturally aligned 4 byte integer that + * includes our byte of interest, and load its value. + */ + ptr32 = (volatile u32 *)((unsigned long)ptr & ~0x3); + load32 = *ptr32; + + do { + old32 = load32; + new32 = (load32 & ~mask) | (val << shift); + load32 = cmpxchg(ptr32, old32, new32); + } while (load32 != old32); + + return (load32 & mask) >> shift; +} -- cgit v1.2.3-59-g8ed1b From 3ba7f44d2b19166b34031db48ce613d1bddbd384 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 9 Jun 2017 17:26:40 -0700 Subject: MIPS: cmpxchg: Implement 1 byte & 2 byte cmpxchg() Implement support for 1 & 2 byte cmpxchg() using read-modify-write atop a 4 byte cmpxchg(). This allows us to support these atomic operations despite the MIPS ISA only providing 4 & 8 byte atomic operations. This is required in order to support queued rwlocks (qrwlock) in a later patch, since these make use of a 1 byte cmpxchg() in their slow path. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16355/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/cmpxchg.h | 7 +++++ arch/mips/kernel/cmpxchg.c | 57 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 64 insertions(+) diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h index a633bf845689..a633f61c5545 100644 --- a/arch/mips/include/asm/cmpxchg.h +++ b/arch/mips/include/asm/cmpxchg.h @@ -142,10 +142,17 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz __ret; \ }) +extern unsigned long __cmpxchg_small(volatile void *ptr, unsigned long old, + unsigned long new, unsigned int size); + static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, unsigned int size) { switch (size) { + case 1: + case 2: + return __cmpxchg_small(ptr, old, new, size); + case 4: return __cmpxchg_asm("ll", "sc", (volatile u32 *)ptr, old, new); diff --git a/arch/mips/kernel/cmpxchg.c b/arch/mips/kernel/cmpxchg.c index 5acfbf9fb2c5..7730f1d3434f 100644 --- a/arch/mips/kernel/cmpxchg.c +++ b/arch/mips/kernel/cmpxchg.c @@ -50,3 +50,60 @@ unsigned long __xchg_small(volatile void *ptr, unsigned long val, unsigned int s return (load32 & mask) >> shift; } + +unsigned long __cmpxchg_small(volatile void *ptr, unsigned long old, + unsigned long new, unsigned int size) +{ + u32 mask, old32, new32, load32; + volatile u32 *ptr32; + unsigned int shift; + u8 load; + + /* Check that ptr is naturally aligned */ + WARN_ON((unsigned long)ptr & (size - 1)); + + /* Mask inputs to the correct size. */ + mask = GENMASK((size * BITS_PER_BYTE) - 1, 0); + old &= mask; + new &= mask; + + /* + * Calculate a shift & mask that correspond to the value we wish to + * compare & exchange within the naturally aligned 4 byte integer + * that includes it. + */ + shift = (unsigned long)ptr & 0x3; + if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) + shift ^= sizeof(u32) - size; + shift *= BITS_PER_BYTE; + mask <<= shift; + + /* + * Calculate a pointer to the naturally aligned 4 byte integer that + * includes our byte of interest, and load its value. + */ + ptr32 = (volatile u32 *)((unsigned long)ptr & ~0x3); + load32 = *ptr32; + + while (true) { + /* + * Ensure the byte we want to exchange matches the expected + * old value, and if not then bail. + */ + load = (load32 & mask) >> shift; + if (load != old) + return load; + + /* + * Calculate the old & new values of the naturally aligned + * 4 byte integer that include the byte we want to exchange. + * Attempt to exchange the old value for the new value, and + * return if we succeed. + */ + old32 = (load32 & ~mask) | (old << shift); + new32 = (load32 & ~mask) | (new << shift); + load32 = cmpxchg(ptr32, old32, new32); + if (load32 == old32) + return old; + } +} -- cgit v1.2.3-59-g8ed1b From 4843cf8d3be4d45f609c865698b63374ae935042 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 9 Jun 2017 17:26:41 -0700 Subject: MIPS: cmpxchg: Rearrange __xchg() arguments to match xchg() The __xchg() function declares its first 2 arguments in reverse order compared to the xchg() macro, which is confusing & serves no purpose. Reorder the arguments such that __xchg() & xchg() match. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16356/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/cmpxchg.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h index a633f61c5545..903f3bf48419 100644 --- a/arch/mips/include/asm/cmpxchg.h +++ b/arch/mips/include/asm/cmpxchg.h @@ -73,7 +73,8 @@ extern unsigned long __xchg_called_with_bad_pointer(void) extern unsigned long __xchg_small(volatile void *ptr, unsigned long val, unsigned int size); -static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size) +static inline unsigned long __xchg(volatile void *ptr, unsigned long x, + int size) { switch (size) { case 1: @@ -101,7 +102,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz smp_mb__before_llsc(); \ \ __res = (__typeof__(*(ptr))) \ - __xchg((unsigned long)(x), (ptr), sizeof(*(ptr))); \ + __xchg((ptr), (unsigned long)(x), sizeof(*(ptr))); \ \ smp_llsc_mb(); \ \ -- cgit v1.2.3-59-g8ed1b From 25da4e9dedbfa1630cc87903dcced5b249b936ef Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 9 Jun 2017 17:26:42 -0700 Subject: MIPS: Use queued read/write locks (qrwlock) This patch switches MIPS to make use of generically implemented queued read/write locks, rather than the custom implementation used previously. This allows us to drop a whole load of inline assembly, share more generic code, and is also a performance win. Results from running the AIM7 short workload on a MIPS Creator Ci40 (ie. 2 core 2 thread interAptiv CPU clocked at 546MHz) with v4.12-rc4 pistachio_defconfig, with ftrace disabled due to a current bug, and both with & without use of queued rwlocks & spinlocks: Forks | v4.12-rc4 | +qlocks | Change -------|-----------|----------|-------- 10 | 52630.32 | 53316.31 | +1.01% 20 | 51777.80 | 52623.15 | +1.02% 30 | 51645.92 | 52517.26 | +1.02% 40 | 51634.88 | 52419.89 | +1.02% 50 | 51506.75 | 52307.81 | +1.02% 60 | 51500.74 | 52322.72 | +1.02% 70 | 51434.81 | 52288.60 | +1.02% 80 | 51423.22 | 52434.85 | +1.02% 90 | 51428.65 | 52410.10 | +1.02% The kernels used for these tests also had my "MIPS: Hardcode cpu_has_* where known at compile time due to ISA" patch applied, which allows the kernel_uses_llsc checks in cmpxchg() & xchg() to be optimised away at compile time. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16357/ Signed-off-by: Ralf Baechle --- arch/mips/Kconfig | 1 + arch/mips/include/asm/Kbuild | 1 + arch/mips/include/asm/spinlock.h | 216 +-------------------------------- arch/mips/include/asm/spinlock_types.h | 10 +- 4 files changed, 4 insertions(+), 224 deletions(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 9891a1285f25..7c2a64b32179 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -11,6 +11,7 @@ config MIPS select ARCH_SUPPORTS_UPROBES select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF if 64BIT + select ARCH_USE_QUEUED_RWLOCKS select ARCH_WANT_IPC_PARSE_VERSION select BUILDTIME_EXTABLE_SORT select CLONE_BACKWARDS diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild index 2535c7b4c482..ae6cb47e9d22 100644 --- a/arch/mips/include/asm/Kbuild +++ b/arch/mips/include/asm/Kbuild @@ -12,6 +12,7 @@ generic-y += mm-arch-hooks.h generic-y += parport.h generic-y += percpu.h generic-y += preempt.h +generic-y += qrwlock.h generic-y += sections.h generic-y += segment.h generic-y += serial.h diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h index a8df44d60607..3e7afff196cd 100644 --- a/arch/mips/include/asm/spinlock.h +++ b/arch/mips/include/asm/spinlock.h @@ -13,6 +13,7 @@ #include #include +#include #include #include @@ -220,221 +221,6 @@ static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock) return tmp; } -/* - * Read-write spinlocks, allowing multiple readers but only one writer. - * - * NOTE! it is quite common to have readers in interrupts but no interrupt - * writers. For those circumstances we can "mix" irq-safe locks - any writer - * needs to get a irq-safe write-lock, but readers can get non-irqsafe - * read-locks. - */ - -/* - * read_can_lock - would read_trylock() succeed? - * @lock: the rwlock in question. - */ -#define arch_read_can_lock(rw) ((rw)->lock >= 0) - -/* - * write_can_lock - would write_trylock() succeed? - * @lock: the rwlock in question. - */ -#define arch_write_can_lock(rw) (!(rw)->lock) - -static inline void arch_read_lock(arch_rwlock_t *rw) -{ - unsigned int tmp; - - if (R10000_LLSC_WAR) { - __asm__ __volatile__( - " .set noreorder # arch_read_lock \n" - "1: ll %1, %2 \n" - " bltz %1, 1b \n" - " addu %1, 1 \n" - " sc %1, %0 \n" - " beqzl %1, 1b \n" - " nop \n" - " .set reorder \n" - : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp) - : GCC_OFF_SMALL_ASM() (rw->lock) - : "memory"); - } else { - do { - __asm__ __volatile__( - "1: ll %1, %2 # arch_read_lock \n" - " bltz %1, 1b \n" - " addu %1, 1 \n" - "2: sc %1, %0 \n" - : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp) - : GCC_OFF_SMALL_ASM() (rw->lock) - : "memory"); - } while (unlikely(!tmp)); - } - - smp_llsc_mb(); -} - -static inline void arch_read_unlock(arch_rwlock_t *rw) -{ - unsigned int tmp; - - smp_mb__before_llsc(); - - if (R10000_LLSC_WAR) { - __asm__ __volatile__( - "1: ll %1, %2 # arch_read_unlock \n" - " addiu %1, -1 \n" - " sc %1, %0 \n" - " beqzl %1, 1b \n" - : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp) - : GCC_OFF_SMALL_ASM() (rw->lock) - : "memory"); - } else { - do { - __asm__ __volatile__( - "1: ll %1, %2 # arch_read_unlock \n" - " addiu %1, -1 \n" - " sc %1, %0 \n" - : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp) - : GCC_OFF_SMALL_ASM() (rw->lock) - : "memory"); - } while (unlikely(!tmp)); - } -} - -static inline void arch_write_lock(arch_rwlock_t *rw) -{ - unsigned int tmp; - - if (R10000_LLSC_WAR) { - __asm__ __volatile__( - " .set noreorder # arch_write_lock \n" - "1: ll %1, %2 \n" - " bnez %1, 1b \n" - " lui %1, 0x8000 \n" - " sc %1, %0 \n" - " beqzl %1, 1b \n" - " nop \n" - " .set reorder \n" - : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp) - : GCC_OFF_SMALL_ASM() (rw->lock) - : "memory"); - } else { - do { - __asm__ __volatile__( - "1: ll %1, %2 # arch_write_lock \n" - " bnez %1, 1b \n" - " lui %1, 0x8000 \n" - "2: sc %1, %0 \n" - : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp) - : GCC_OFF_SMALL_ASM() (rw->lock) - : "memory"); - } while (unlikely(!tmp)); - } - - smp_llsc_mb(); -} - -static inline void arch_write_unlock(arch_rwlock_t *rw) -{ - smp_mb__before_llsc(); - - __asm__ __volatile__( - " # arch_write_unlock \n" - " sw $0, %0 \n" - : "=m" (rw->lock) - : "m" (rw->lock) - : "memory"); -} - -static inline int arch_read_trylock(arch_rwlock_t *rw) -{ - unsigned int tmp; - int ret; - - if (R10000_LLSC_WAR) { - __asm__ __volatile__( - " .set noreorder # arch_read_trylock \n" - " li %2, 0 \n" - "1: ll %1, %3 \n" - " bltz %1, 2f \n" - " addu %1, 1 \n" - " sc %1, %0 \n" - " .set reorder \n" - " beqzl %1, 1b \n" - " nop \n" - __WEAK_LLSC_MB - " li %2, 1 \n" - "2: \n" - : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret) - : GCC_OFF_SMALL_ASM() (rw->lock) - : "memory"); - } else { - __asm__ __volatile__( - " .set noreorder # arch_read_trylock \n" - " li %2, 0 \n" - "1: ll %1, %3 \n" - " bltz %1, 2f \n" - " addu %1, 1 \n" - " sc %1, %0 \n" - " beqz %1, 1b \n" - " nop \n" - " .set reorder \n" - __WEAK_LLSC_MB - " li %2, 1 \n" - "2: .insn \n" - : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret) - : GCC_OFF_SMALL_ASM() (rw->lock) - : "memory"); - } - - return ret; -} - -static inline int arch_write_trylock(arch_rwlock_t *rw) -{ - unsigned int tmp; - int ret; - - if (R10000_LLSC_WAR) { - __asm__ __volatile__( - " .set noreorder # arch_write_trylock \n" - " li %2, 0 \n" - "1: ll %1, %3 \n" - " bnez %1, 2f \n" - " lui %1, 0x8000 \n" - " sc %1, %0 \n" - " beqzl %1, 1b \n" - " nop \n" - __WEAK_LLSC_MB - " li %2, 1 \n" - " .set reorder \n" - "2: \n" - : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret) - : GCC_OFF_SMALL_ASM() (rw->lock) - : "memory"); - } else { - do { - __asm__ __volatile__( - " ll %1, %3 # arch_write_trylock \n" - " li %2, 0 \n" - " bnez %1, 2f \n" - " lui %1, 0x8000 \n" - " sc %1, %0 \n" - " li %2, 1 \n" - "2: .insn \n" - : "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), - "=&r" (ret) - : GCC_OFF_SMALL_ASM() (rw->lock) - : "memory"); - } while (unlikely(!tmp)); - - smp_llsc_mb(); - } - - return ret; -} - #define arch_read_lock_flags(lock, flags) arch_read_lock(lock) #define arch_write_lock_flags(lock, flags) arch_write_lock(lock) diff --git a/arch/mips/include/asm/spinlock_types.h b/arch/mips/include/asm/spinlock_types.h index 9b2528e612c0..3d38bfad9b49 100644 --- a/arch/mips/include/asm/spinlock_types.h +++ b/arch/mips/include/asm/spinlock_types.h @@ -1,10 +1,6 @@ #ifndef _ASM_SPINLOCK_TYPES_H #define _ASM_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H -# error "please don't include this file directly" -#endif - #include #include @@ -28,10 +24,6 @@ typedef union { #define __ARCH_SPIN_LOCK_UNLOCKED { .lock = 0 } -typedef struct { - volatile unsigned int lock; -} arch_rwlock_t; - -#define __ARCH_RW_LOCK_UNLOCKED { 0 } +#include #endif -- cgit v1.2.3-59-g8ed1b From 0b17c9670590148656645be57f62f279f0d3ad52 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 9 Jun 2017 17:26:43 -0700 Subject: MIPS: Use queued spinlocks (qspinlock) This patch switches MIPS to make use of generically implemented queued spinlocks, rather than the ticket spinlocks used previously. This allows us to drop a whole load of inline assembly, share more generic code, and is also a performance win. Results from running the AIM7 short workload on a MIPS Creator Ci40 (ie. 2 core 2 thread interAptiv CPU clocked at 546MHz) with v4.12-rc4 pistachio_defconfig, with ftrace disabled due to a current bug, and both with & without use of queued rwlocks & spinlocks: Forks | v4.12-rc4 | +qlocks | Change -------|-----------|----------|-------- 10 | 52630.32 | 53316.31 | +1.01% 20 | 51777.80 | 52623.15 | +1.02% 30 | 51645.92 | 52517.26 | +1.02% 40 | 51634.88 | 52419.89 | +1.02% 50 | 51506.75 | 52307.81 | +1.02% 60 | 51500.74 | 52322.72 | +1.02% 70 | 51434.81 | 52288.60 | +1.02% 80 | 51423.22 | 52434.85 | +1.02% 90 | 51428.65 | 52410.10 | +1.02% The kernels used for these tests also had my "MIPS: Hardcode cpu_has_* where known at compile time due to ISA" patch applied, which allows the kernel_uses_llsc checks in cmpxchg() & xchg() to be optimised away at compile time. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16358/ Signed-off-by: Ralf Baechle --- arch/mips/Kconfig | 1 + arch/mips/include/asm/Kbuild | 1 + arch/mips/include/asm/spinlock.h | 210 +-------------------------------- arch/mips/include/asm/spinlock_types.h | 24 +--- 4 files changed, 4 insertions(+), 232 deletions(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 7c2a64b32179..ef1cb20cfbb3 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -12,6 +12,7 @@ config MIPS select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF if 64BIT select ARCH_USE_QUEUED_RWLOCKS + select ARCH_USE_QUEUED_SPINLOCKS select ARCH_WANT_IPC_PARSE_VERSION select BUILDTIME_EXTABLE_SORT select CLONE_BACKWARDS diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild index ae6cb47e9d22..7c8aab23bce8 100644 --- a/arch/mips/include/asm/Kbuild +++ b/arch/mips/include/asm/Kbuild @@ -13,6 +13,7 @@ generic-y += parport.h generic-y += percpu.h generic-y += preempt.h generic-y += qrwlock.h +generic-y += qspinlock.h generic-y += sections.h generic-y += segment.h generic-y += serial.h diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h index 3e7afff196cd..a7d21da16b6a 100644 --- a/arch/mips/include/asm/spinlock.h +++ b/arch/mips/include/asm/spinlock.h @@ -9,217 +9,9 @@ #ifndef _ASM_SPINLOCK_H #define _ASM_SPINLOCK_H -#include - -#include #include #include -#include -#include - -/* - * Your basic SMP spinlocks, allowing only a single CPU anywhere - * - * Simple spin lock operations. There are two variants, one clears IRQ's - * on the local processor, one does not. - * - * These are fair FIFO ticket locks - * - * (the type definitions are in asm/spinlock_types.h) - */ - - -/* - * Ticket locks are conceptually two parts, one indicating the current head of - * the queue, and the other indicating the current tail. The lock is acquired - * by atomically noting the tail and incrementing it by one (thus adding - * ourself to the queue and noting our position), then waiting until the head - * becomes equal to the the initial value of the tail. - */ - -static inline int arch_spin_is_locked(arch_spinlock_t *lock) -{ - u32 counters = ACCESS_ONCE(lock->lock); - - return ((counters >> 16) ^ counters) & 0xffff; -} - -static inline int arch_spin_value_unlocked(arch_spinlock_t lock) -{ - return lock.h.serving_now == lock.h.ticket; -} - -#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) - -static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) -{ - u16 owner = READ_ONCE(lock->h.serving_now); - smp_rmb(); - for (;;) { - arch_spinlock_t tmp = READ_ONCE(*lock); - - if (tmp.h.serving_now == tmp.h.ticket || - tmp.h.serving_now != owner) - break; - - cpu_relax(); - } - smp_acquire__after_ctrl_dep(); -} - -static inline int arch_spin_is_contended(arch_spinlock_t *lock) -{ - u32 counters = ACCESS_ONCE(lock->lock); - - return (((counters >> 16) - counters) & 0xffff) > 1; -} -#define arch_spin_is_contended arch_spin_is_contended - -static inline void arch_spin_lock(arch_spinlock_t *lock) -{ - int my_ticket; - int tmp; - int inc = 0x10000; - - if (R10000_LLSC_WAR) { - __asm__ __volatile__ ( - " .set push # arch_spin_lock \n" - " .set noreorder \n" - " \n" - "1: ll %[ticket], %[ticket_ptr] \n" - " addu %[my_ticket], %[ticket], %[inc] \n" - " sc %[my_ticket], %[ticket_ptr] \n" - " beqzl %[my_ticket], 1b \n" - " nop \n" - " srl %[my_ticket], %[ticket], 16 \n" - " andi %[ticket], %[ticket], 0xffff \n" - " bne %[ticket], %[my_ticket], 4f \n" - " subu %[ticket], %[my_ticket], %[ticket] \n" - "2: \n" - " .subsection 2 \n" - "4: andi %[ticket], %[ticket], 0xffff \n" - " sll %[ticket], 5 \n" - " \n" - "6: bnez %[ticket], 6b \n" - " subu %[ticket], 1 \n" - " \n" - " lhu %[ticket], %[serving_now_ptr] \n" - " beq %[ticket], %[my_ticket], 2b \n" - " subu %[ticket], %[my_ticket], %[ticket] \n" - " b 4b \n" - " subu %[ticket], %[ticket], 1 \n" - " .previous \n" - " .set pop \n" - : [ticket_ptr] "+" GCC_OFF_SMALL_ASM() (lock->lock), - [serving_now_ptr] "+m" (lock->h.serving_now), - [ticket] "=&r" (tmp), - [my_ticket] "=&r" (my_ticket) - : [inc] "r" (inc)); - } else { - __asm__ __volatile__ ( - " .set push # arch_spin_lock \n" - " .set noreorder \n" - " \n" - "1: ll %[ticket], %[ticket_ptr] \n" - " addu %[my_ticket], %[ticket], %[inc] \n" - " sc %[my_ticket], %[ticket_ptr] \n" - " beqz %[my_ticket], 1b \n" - " srl %[my_ticket], %[ticket], 16 \n" - " andi %[ticket], %[ticket], 0xffff \n" - " bne %[ticket], %[my_ticket], 4f \n" - " subu %[ticket], %[my_ticket], %[ticket] \n" - "2: .insn \n" - " .subsection 2 \n" - "4: andi %[ticket], %[ticket], 0xffff \n" - " sll %[ticket], 5 \n" - " \n" - "6: bnez %[ticket], 6b \n" - " subu %[ticket], 1 \n" - " \n" - " lhu %[ticket], %[serving_now_ptr] \n" - " beq %[ticket], %[my_ticket], 2b \n" - " subu %[ticket], %[my_ticket], %[ticket] \n" - " b 4b \n" - " subu %[ticket], %[ticket], 1 \n" - " .previous \n" - " .set pop \n" - : [ticket_ptr] "+" GCC_OFF_SMALL_ASM() (lock->lock), - [serving_now_ptr] "+m" (lock->h.serving_now), - [ticket] "=&r" (tmp), - [my_ticket] "=&r" (my_ticket) - : [inc] "r" (inc)); - } - - smp_llsc_mb(); -} - -static inline void arch_spin_unlock(arch_spinlock_t *lock) -{ - unsigned int serving_now = lock->h.serving_now + 1; - wmb(); - lock->h.serving_now = (u16)serving_now; - nudge_writes(); -} - -static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock) -{ - int tmp, tmp2, tmp3; - int inc = 0x10000; - - if (R10000_LLSC_WAR) { - __asm__ __volatile__ ( - " .set push # arch_spin_trylock \n" - " .set noreorder \n" - " \n" - "1: ll %[ticket], %[ticket_ptr] \n" - " srl %[my_ticket], %[ticket], 16 \n" - " andi %[now_serving], %[ticket], 0xffff \n" - " bne %[my_ticket], %[now_serving], 3f \n" - " addu %[ticket], %[ticket], %[inc] \n" - " sc %[ticket], %[ticket_ptr] \n" - " beqzl %[ticket], 1b \n" - " li %[ticket], 1 \n" - "2: \n" - " .subsection 2 \n" - "3: b 2b \n" - " li %[ticket], 0 \n" - " .previous \n" - " .set pop \n" - : [ticket_ptr] "+" GCC_OFF_SMALL_ASM() (lock->lock), - [ticket] "=&r" (tmp), - [my_ticket] "=&r" (tmp2), - [now_serving] "=&r" (tmp3) - : [inc] "r" (inc)); - } else { - __asm__ __volatile__ ( - " .set push # arch_spin_trylock \n" - " .set noreorder \n" - " \n" - "1: ll %[ticket], %[ticket_ptr] \n" - " srl %[my_ticket], %[ticket], 16 \n" - " andi %[now_serving], %[ticket], 0xffff \n" - " bne %[my_ticket], %[now_serving], 3f \n" - " addu %[ticket], %[ticket], %[inc] \n" - " sc %[ticket], %[ticket_ptr] \n" - " beqz %[ticket], 1b \n" - " li %[ticket], 1 \n" - "2: .insn \n" - " .subsection 2 \n" - "3: b 2b \n" - " li %[ticket], 0 \n" - " .previous \n" - " .set pop \n" - : [ticket_ptr] "+" GCC_OFF_SMALL_ASM() (lock->lock), - [ticket] "=&r" (tmp), - [my_ticket] "=&r" (tmp2), - [now_serving] "=&r" (tmp3) - : [inc] "r" (inc)); - } - - smp_llsc_mb(); - - return tmp; -} +#include #define arch_read_lock_flags(lock, flags) arch_read_lock(lock) #define arch_write_lock_flags(lock, flags) arch_write_lock(lock) diff --git a/arch/mips/include/asm/spinlock_types.h b/arch/mips/include/asm/spinlock_types.h index 3d38bfad9b49..177e722eb96c 100644 --- a/arch/mips/include/asm/spinlock_types.h +++ b/arch/mips/include/asm/spinlock_types.h @@ -1,29 +1,7 @@ #ifndef _ASM_SPINLOCK_TYPES_H #define _ASM_SPINLOCK_TYPES_H -#include - -#include - -typedef union { - /* - * bits 0..15 : serving_now - * bits 16..31 : ticket - */ - u32 lock; - struct { -#ifdef __BIG_ENDIAN - u16 ticket; - u16 serving_now; -#else - u16 serving_now; - u16 ticket; -#endif - } h; -} arch_spinlock_t; - -#define __ARCH_SPIN_LOCK_UNLOCKED { .lock = 0 } - +#include #include #endif -- cgit v1.2.3-59-g8ed1b From 13769ebad0c42738831787e27c7c7f982e7da579 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Fri, 16 Jun 2017 00:05:08 +0100 Subject: MIPS: math-emu: Prevent wrong ISA mode instruction emulation Terminate FPU emulation immediately whenever an ISA mode switch has been observed. This is so that we do not interpret machine code in the wrong mode, for example when a regular MIPS FPU instruction has been placed in a delay slot of a jump that switches into the MIPS16 mode, as with the following code (taken from a GCC test suite case): 00400650 : 400650: 3c020100 lui v0,0x100 400654: 03e00008 jr ra 400658: 44c2f800 ctc1 v0,c1_fcsr 40065c: 00000000 nop [...] 004012d0 <__libc_csu_init>: 4012d0: f000 6a02 li v0,2 4012d4: f150 0b1c la v1,3f9430 <_DYNAMIC-0x6df0> 4012d8: f400 3240 sll v0,16 4012dc: e269 addu v0,v1 4012de: 659a move gp,v0 4012e0: f00c 64f6 save a0-a2,48,ra,s0-s1 4012e4: 673c move s1,gp 4012e6: f010 9978 lw v1,-32744(s1) 4012ea: d204 sw v0,16(sp) 4012ec: eb40 jalr v1 4012ee: 653b move t9,v1 4012f0: f010 997c lw v1,-32740(s1) 4012f4: f030 9920 lw s1,-32736(s1) 4012f8: e32f subu v1,s1 4012fa: 326b sra v0,v1,2 4012fc: d206 sw v0,24(sp) 4012fe: 220c beqz v0,401318 <__libc_csu_init+0x48> 401300: 6800 li s0,0 401302: 99e0 lw a3,0(s1) 401304: 4801 addiu s0,1 401306: 960e lw a2,56(sp) 401308: 4904 addiu s1,4 40130a: 950d lw a1,52(sp) 40130c: 940c lw a0,48(sp) 40130e: ef40 jalr a3 401310: 653f move t9,a3 401312: 9206 lw v0,24(sp) 401314: ea0a cmp v0,s0 401316: 61f5 btnez 401302 <__libc_csu_init+0x32> 401318: 6476 restore 48,ra,s0-s1 40131a: e8a0 jrc ra Here `set_fast_math' is called from `40130e' (`40130f' with the ISA bit) and emulation triggers for the CTC1 instruction. As it is in a jump delay slot emulation continues from `401312' (`401313' with the ISA bit). However we have no path to handle MIPS16 FPU code emulation, because there are no MIPS16 FPU instructions. So the default emulation path is taken, interpreting a 32-bit word fetched by `get_user' from `401313' as a regular MIPS instruction, which is: 401313: f5ea0a92 sdc1 $f10,2706(t7) This makes the FPU emulator proceed with the supposed SDC1 instruction and consequently makes the program considered here terminate with SIGSEGV. A similar although less severe issue exists with pure-microMIPS processors in the case where similarly an FPU instruction is emulated in a delay slot of a register jump that (incorrectly) switches into the regular MIPS mode. A subsequent instruction fetch from the jump's target is supposed to cause an Address Error exception, however instead we proceed with regular MIPS FPU emulation. For simplicity then, always terminate the emulation loop whenever a mode change is detected, denoted by an ISA mode bit flip. As from commit 377cb1b6c16a ("MIPS: Disable MIPS16/microMIPS crap for platforms not supporting these ASEs.") the result of `get_isa16_mode' can be hardcoded to 0, so we need to examine the ISA mode bit by hand. This complements commit 102cedc32a6e ("MIPS: microMIPS: Floating point support.") which added JALX decoding to FPU emulation. Fixes: 102cedc32a6e ("MIPS: microMIPS: Floating point support.") Signed-off-by: Maciej W. Rozycki Cc: James Hogan Cc: linux-mips@linux-mips.org Cc: stable@vger.kernel.org # 3.9+ Patchwork: https://patchwork.linux-mips.org/patch/16393/ Signed-off-by: Ralf Baechle --- arch/mips/math-emu/cp1emu.c | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c index f12fde10c8ad..261915265942 100644 --- a/arch/mips/math-emu/cp1emu.c +++ b/arch/mips/math-emu/cp1emu.c @@ -2524,6 +2524,35 @@ dcopuop: return 0; } +/* + * Emulate FPU instructions. + * + * If we use FPU hardware, then we have been typically called to handle + * an unimplemented operation, such as where an operand is a NaN or + * denormalized. In that case exit the emulation loop after a single + * iteration so as to let hardware execute any subsequent instructions. + * + * If we have no FPU hardware or it has been disabled, then continue + * emulating floating-point instructions until one of these conditions + * has occurred: + * + * - a non-FPU instruction has been encountered, + * + * - an attempt to emulate has ended with a signal, + * + * - the ISA mode has been switched. + * + * We need to terminate the emulation loop if we got switched to the + * MIPS16 mode, whether supported or not, so that we do not attempt + * to emulate a MIPS16 instruction as a regular MIPS FPU instruction. + * Similarly if we got switched to the microMIPS mode and only the + * regular MIPS mode is supported, so that we do not attempt to emulate + * a microMIPS instruction as a regular MIPS FPU instruction. Or if + * we got switched to the regular MIPS mode and only the microMIPS mode + * is supported, so that we do not attempt to emulate a regular MIPS + * instruction that should cause an Address Error exception instead. + * For simplicity we always terminate upon an ISA mode switch. + */ int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx, int has_fpu, void *__user *fault_addr) { @@ -2609,6 +2638,15 @@ int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx, break; if (sig) break; + /* + * We have to check for the ISA bit explicitly here, + * because `get_isa16_mode' may return 0 if support + * for code compression has been globally disabled, + * or otherwise we may produce the wrong signal or + * even proceed successfully where we must not. + */ + if ((xcp->cp0_epc ^ prevepc) & 0x1) + break; cond_resched(); } while (xcp->cp0_epc > prevepc); -- cgit v1.2.3-59-g8ed1b From a9db101b735a9d49295326ae41f610f6da62b08c Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Fri, 16 Jun 2017 00:06:19 +0100 Subject: MIPS: Actually decode JALX in `__compute_return_epc_for_insn' Complement commit fb6883e5809c ("MIPS: microMIPS: Support handling of delay slots.") and actually decode the regular MIPS JALX major instruction opcode, the handling of which has been added with the said commit for EPC calculation in `__compute_return_epc_for_insn'. Fixes: fb6883e5809c ("MIPS: microMIPS: Support handling of delay slots.") Signed-off-by: Maciej W. Rozycki Cc: James Hogan Cc: linux-mips@linux-mips.org Cc: stable@vger.kernel.org # 3.9+ Patchwork: https://patchwork.linux-mips.org/patch/16394/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/branch.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c index f702a459a830..40cc3def36a4 100644 --- a/arch/mips/kernel/branch.c +++ b/arch/mips/kernel/branch.c @@ -556,6 +556,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, /* * These are unconditional and in j_format. */ + case jalx_op: case jal_op: regs->regs[31] = regs->cp0_epc + 8; case j_op: -- cgit v1.2.3-59-g8ed1b From 11a3799dbeb620bf0400b1fda5cc2c6bea55f20a Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Fri, 16 Jun 2017 00:07:34 +0100 Subject: MIPS: Fix unaligned PC interpretation in `compute_return_epc' Fix a regression introduced with commit fb6883e5809c ("MIPS: microMIPS: Support handling of delay slots.") and defer to `__compute_return_epc' if the ISA bit is set in EPC with non-MIPS16, non-microMIPS hardware, which will then arrange for a SIGBUS due to an unaligned instruction reference. Returning EPC here is never correct as the API defines this function's result to be either a negative error code on failure or one of 0 and BRANCH_LIKELY_TAKEN on success. Fixes: fb6883e5809c ("MIPS: microMIPS: Support handling of delay slots.") Signed-off-by: Maciej W. Rozycki Cc: James Hogan Cc: linux-mips@linux-mips.org Cc: stable@vger.kernel.org # 3.9+ Patchwork: https://patchwork.linux-mips.org/patch/16395/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/branch.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/arch/mips/include/asm/branch.h b/arch/mips/include/asm/branch.h index de781cf54bc7..da80878f2c0d 100644 --- a/arch/mips/include/asm/branch.h +++ b/arch/mips/include/asm/branch.h @@ -74,10 +74,7 @@ static inline int compute_return_epc(struct pt_regs *regs) return __microMIPS_compute_return_epc(regs); if (cpu_has_mips16) return __MIPS16e_compute_return_epc(regs); - return regs->cp0_epc; - } - - if (!delay_slot(regs)) { + } else if (!delay_slot(regs)) { regs->cp0_epc += 4; return 0; } -- cgit v1.2.3-59-g8ed1b From 7b82c1058ac1f8f8b9f2b8786b1f710a57a870a8 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Fri, 16 Jun 2017 00:08:29 +0100 Subject: MIPS: Send SIGILL for BPOSGE32 in `__compute_return_epc_for_insn' Fix commit e50c0a8fa60d ("Support the MIPS32 / MIPS64 DSP ASE.") and send SIGILL rather than SIGBUS whenever an unimplemented BPOSGE32 DSP ASE instruction has been encountered in `__compute_return_epc_for_insn' as our Reserved Instruction exception handler would in response to an attempt to actually execute the instruction. Sending SIGBUS only makes sense for the unaligned PC case, since moved to `__compute_return_epc'. Adjust function documentation accordingly, correct formatting and use `pr_info' rather than `printk' as the other exit path already does. Fixes: e50c0a8fa60d ("Support the MIPS32 / MIPS64 DSP ASE.") Signed-off-by: Maciej W. Rozycki Cc: James Hogan Cc: linux-mips@linux-mips.org Cc: stable@vger.kernel.org # 2.6.14+ Patchwork: https://patchwork.linux-mips.org/patch/16396/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/branch.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c index 40cc3def36a4..81b5608acd5c 100644 --- a/arch/mips/kernel/branch.c +++ b/arch/mips/kernel/branch.c @@ -399,7 +399,7 @@ int __MIPS16e_compute_return_epc(struct pt_regs *regs) * * @regs: Pointer to pt_regs * @insn: branch instruction to decode - * @returns: -EFAULT on error and forces SIGBUS, and on success + * @returns: -EFAULT on error and forces SIGILL, and on success * returns 0 or BRANCH_LIKELY_TAKEN as appropriate after * evaluating the branch. * @@ -832,8 +832,9 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, return ret; sigill_dsp: - printk("%s: DSP branch but not DSP ASE - sending SIGBUS.\n", current->comm); - force_sig(SIGBUS, current); + pr_info("%s: DSP branch but not DSP ASE - sending SIGILL.\n", + current->comm); + force_sig(SIGILL, current); return -EFAULT; sigill_r6: pr_info("%s: R2 branch but r2-to-r6 emulator is not preset - sending SIGILL.\n", -- cgit v1.2.3-59-g8ed1b From 1f4edde422961397cf4470b347958c13c6a740bb Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Fri, 16 Jun 2017 00:09:23 +0100 Subject: MIPS: Rename `sigill_r6' to `sigill_r2r6' in `__compute_return_epc_for_insn' Use the more accurate `sigill_r2r6' name for the label used in the case of sending SIGILL in the absence of the instruction emulator for an earlier ISA level instruction that has been removed as from the R6 ISA, so that the `sigill_r6' name is freed for the situation where an R6 instruction is not supposed to be interpreted, because the executing processor does not support the R6 ISA. Signed-off-by: Maciej W. Rozycki Cc: James Hogan Cc: linux-mips@linux-mips.org Cc: stable@vger.kernel.org # 3.19+ Patchwork: https://patchwork.linux-mips.org/patch/16397/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/branch.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c index 81b5608acd5c..df5c32b38408 100644 --- a/arch/mips/kernel/branch.c +++ b/arch/mips/kernel/branch.c @@ -431,7 +431,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, /* Fall through */ case jr_op: if (NO_R6EMU && insn.r_format.func == jr_op) - goto sigill_r6; + goto sigill_r2r6; regs->cp0_epc = regs->regs[insn.r_format.rs]; break; } @@ -446,7 +446,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, switch (insn.i_format.rt) { case bltzl_op: if (NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case bltz_op: if ((long)regs->regs[insn.i_format.rs] < 0) { epc = epc + 4 + (insn.i_format.simmediate << 2); @@ -459,7 +459,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case bgezl_op: if (NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case bgez_op: if ((long)regs->regs[insn.i_format.rs] >= 0) { epc = epc + 4 + (insn.i_format.simmediate << 2); @@ -574,7 +574,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, */ case beql_op: if (NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case beq_op: if (regs->regs[insn.i_format.rs] == regs->regs[insn.i_format.rt]) { @@ -588,7 +588,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case bnel_op: if (NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case bne_op: if (regs->regs[insn.i_format.rs] != regs->regs[insn.i_format.rt]) { @@ -602,7 +602,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case blezl_op: /* not really i_format */ if (!insn.i_format.rt && NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case blez_op: /* * Compact branches for R6 for the @@ -637,7 +637,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case bgtzl_op: if (!insn.i_format.rt && NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case bgtz_op: /* * Compact branches for R6 for the @@ -836,7 +836,7 @@ sigill_dsp: current->comm); force_sig(SIGILL, current); return -EFAULT; -sigill_r6: +sigill_r2r6: pr_info("%s: R2 branch but r2-to-r6 emulator is not preset - sending SIGILL.\n", current->comm); force_sig(SIGILL, current); -- cgit v1.2.3-59-g8ed1b From fef40be6da856afead4177aaa9d869a66fb3381f Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Fri, 16 Jun 2017 00:12:53 +0100 Subject: MIPS: Send SIGILL for linked branches in `__compute_return_epc_for_insn' Fix commit 319824eabc3f ("MIPS: kernel: branch: Do not emulate the branch likelies on MIPS R6") and also send SIGILL rather than returning -SIGILL for BLTZAL, BLTZALL, BGEZAL and BGEZALL instruction encodings no longer supported in R6, except where emulated. Returning -SIGILL is never correct as the API defines this function's result upon error to be -EFAULT and a signal actually issued. Fixes: 319824eabc3f ("MIPS: kernel: branch: Do not emulate the branch likelies on MIPS R6") Signed-off-by: Maciej W. Rozycki Cc: James Hogan Cc: linux-mips@linux-mips.org Cc: stable@vger.kernel.org # 3.19+ Patchwork: https://patchwork.linux-mips.org/patch/16398/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/branch.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c index df5c32b38408..64c8360e3d62 100644 --- a/arch/mips/kernel/branch.c +++ b/arch/mips/kernel/branch.c @@ -473,10 +473,8 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case bltzal_op: case bltzall_op: if (NO_R6EMU && (insn.i_format.rs || - insn.i_format.rt == bltzall_op)) { - ret = -SIGILL; - break; - } + insn.i_format.rt == bltzall_op)) + goto sigill_r2r6; regs->regs[31] = epc + 8; /* * OK we are here either because we hit a NAL @@ -507,10 +505,8 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case bgezal_op: case bgezall_op: if (NO_R6EMU && (insn.i_format.rs || - insn.i_format.rt == bgezall_op)) { - ret = -SIGILL; - break; - } + insn.i_format.rt == bgezall_op)) + goto sigill_r2r6; regs->regs[31] = epc + 8; /* * OK we are here either because we hit a BAL -- cgit v1.2.3-59-g8ed1b From a60b1a5bf88a250f1a77977c0224e502c901c77b Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Fri, 16 Jun 2017 00:14:12 +0100 Subject: MIPS: Send SIGILL for R6 branches in `__compute_return_epc_for_insn' Fix: * commit 8467ca0122e2 ("MIPS: Emulate the new MIPS R6 branch compact (BC) instruction"), * commit 84fef630127a ("MIPS: Emulate the new MIPS R6 BALC instruction"), * commit 69b9a2fd05a3 ("MIPS: Emulate the new MIPS R6 BEQZC and JIC instructions"), * commit 28d6f93d201d ("MIPS: Emulate the new MIPS R6 BNEZC and JIALC instructions"), * commit c893ce38b265 ("MIPS: Emulate the new MIPS R6 BOVC, BEQC and BEQZALC instructions") and send SIGILL rather than returning -SIGILL for R6 branch and jump instructions. Returning -SIGILL is never correct as the API defines this function's result upon error to be -EFAULT and a signal actually issued. Fixes: 8467ca0122e2 ("MIPS: Emulate the new MIPS R6 branch compact (BC) instruction") Fixes: 84fef630127a ("MIPS: Emulate the new MIPS R6 BALC instruction") Fixes: 69b9a2fd05a3 ("MIPS: Emulate the new MIPS R6 BEQZC and JIC instructions") Fixes: 28d6f93d201d ("MIPS: Emulate the new MIPS R6 BNEZC and JIALC instructions") Fixes: c893ce38b265 ("MIPS: Emulate the new MIPS R6 BOVC, BEQC and BEQZALC instructions") Signed-off-by: Maciej W. Rozycki Cc: James Hogan Cc: linux-mips@linux-mips.org Cc: stable@vger.kernel.org # 3.19+ Patchwork: https://patchwork.linux-mips.org/patch/16399/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/branch.c | 35 +++++++++++++++-------------------- 1 file changed, 15 insertions(+), 20 deletions(-) diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c index 64c8360e3d62..6d536e5581e1 100644 --- a/arch/mips/kernel/branch.c +++ b/arch/mips/kernel/branch.c @@ -771,35 +771,27 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, #else case bc6_op: /* Only valid for MIPS R6 */ - if (!cpu_has_mips_r6) { - ret = -SIGILL; - break; - } + if (!cpu_has_mips_r6) + goto sigill_r6; regs->cp0_epc += 8; break; case balc6_op: - if (!cpu_has_mips_r6) { - ret = -SIGILL; - break; - } + if (!cpu_has_mips_r6) + goto sigill_r6; /* Compact branch: BALC */ regs->regs[31] = epc + 4; epc += 4 + (insn.i_format.simmediate << 2); regs->cp0_epc = epc; break; case pop66_op: - if (!cpu_has_mips_r6) { - ret = -SIGILL; - break; - } + if (!cpu_has_mips_r6) + goto sigill_r6; /* Compact branch: BEQZC || JIC */ regs->cp0_epc += 8; break; case pop76_op: - if (!cpu_has_mips_r6) { - ret = -SIGILL; - break; - } + if (!cpu_has_mips_r6) + goto sigill_r6; /* Compact branch: BNEZC || JIALC */ if (!insn.i_format.rs) { /* JIALC: set $31/ra */ @@ -811,10 +803,8 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case pop10_op: case pop30_op: /* Only valid for MIPS R6 */ - if (!cpu_has_mips_r6) { - ret = -SIGILL; - break; - } + if (!cpu_has_mips_r6) + goto sigill_r6; /* * Compact branches: * bovc, beqc, beqzalc, bnvc, bnec, bnezlac @@ -837,6 +827,11 @@ sigill_r2r6: current->comm); force_sig(SIGILL, current); return -EFAULT; +sigill_r6: + pr_info("%s: R6 branch but no MIPSr6 ISA support - sending SIGILL.\n", + current->comm); + force_sig(SIGILL, current); + return -EFAULT; } EXPORT_SYMBOL_GPL(__compute_return_epc_for_insn); -- cgit v1.2.3-59-g8ed1b From 27fe2200dad2de8207a694024a7b9037dff1b280 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Fri, 16 Jun 2017 00:15:22 +0100 Subject: MIPS: Fix a typo: s/preset/present/ in r2-to-r6 emulation error message This is a user-visible message, so we want it to be spelled correctly. Fixes: 5f9f41c474be ("MIPS: kernel: Prepare the JR instruction for emulation on MIPS R6") Signed-off-by: Maciej W. Rozycki Cc: James Hogan Cc: linux-mips@linux-mips.org Cc: stable@vger.kernel.org # 3.19+ Patchwork: https://patchwork.linux-mips.org/patch/16400/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/branch.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c index 6d536e5581e1..e53379c689b2 100644 --- a/arch/mips/kernel/branch.c +++ b/arch/mips/kernel/branch.c @@ -823,7 +823,7 @@ sigill_dsp: force_sig(SIGILL, current); return -EFAULT; sigill_r2r6: - pr_info("%s: R2 branch but r2-to-r6 emulator is not preset - sending SIGILL.\n", + pr_info("%s: R2 branch but r2-to-r6 emulator is not present - sending SIGILL.\n", current->comm); force_sig(SIGILL, current); return -EFAULT; -- cgit v1.2.3-59-g8ed1b From 70f743d141d3b14ca904581dfd1bd50dbe685c4f Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Fri, 16 Jun 2017 00:16:15 +0100 Subject: MIPS: math-emu: For MFHC1/MTHC1 also return SIGILL right away Update commit 1ac944007bed ("MIPS: math-emu: Add mfhc1 & mthc1 support.") and like done throughout `cop1Emulate' for other cases also for the MFHC1 and MTHC1 instructions return SIGILL right away rather than jumping to a single `return' statement. Signed-off-by: Maciej W. Rozycki Cc: James Hogan Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16401/ Signed-off-by: Ralf Baechle --- arch/mips/math-emu/cp1emu.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c index 261915265942..f08a7b4facb9 100644 --- a/arch/mips/math-emu/cp1emu.c +++ b/arch/mips/math-emu/cp1emu.c @@ -1142,7 +1142,7 @@ emul: case mfhc_op: if (!cpu_has_mips_r2_r6) - goto sigill; + return SIGILL; /* copregister rd -> gpr[rt] */ if (MIPSInst_RT(ir) != 0) { @@ -1153,7 +1153,7 @@ emul: case mthc_op: if (!cpu_has_mips_r2_r6) - goto sigill; + return SIGILL; /* copregister rd <- gpr[rt] */ SITOHREG(xcp->regs[MIPSInst_RT(ir)], MIPSInst_RD(ir)); @@ -1376,7 +1376,6 @@ branch_common: xcp->regs[MIPSInst_RS(ir)]; break; default: -sigill: return SIGILL; } -- cgit v1.2.3-59-g8ed1b From f259fe295ef07aafadf3316f58c4ac4eddfeccf1 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Fri, 16 Jun 2017 00:18:11 +0100 Subject: MIPS: Use `pr_debug' for messages from `__compute_return_epc_for_insn' Reduce the log level for branch emulation error messages issued before sending SIGILL by `__compute_return_epc_for_insn' as these are triggered by user software and are not an event that would normally require any attention. The same signal sent from elsewhere does not actually leave any trace in the kernel log at all. Signed-off-by: Maciej W. Rozycki Cc: James Hogan Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16402/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/branch.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c index e53379c689b2..b79ed9af9886 100644 --- a/arch/mips/kernel/branch.c +++ b/arch/mips/kernel/branch.c @@ -818,18 +818,18 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, return ret; sigill_dsp: - pr_info("%s: DSP branch but not DSP ASE - sending SIGILL.\n", - current->comm); + pr_debug("%s: DSP branch but not DSP ASE - sending SIGILL.\n", + current->comm); force_sig(SIGILL, current); return -EFAULT; sigill_r2r6: - pr_info("%s: R2 branch but r2-to-r6 emulator is not present - sending SIGILL.\n", - current->comm); + pr_debug("%s: R2 branch but r2-to-r6 emulator is not present - sending SIGILL.\n", + current->comm); force_sig(SIGILL, current); return -EFAULT; sigill_r6: - pr_info("%s: R6 branch but no MIPSr6 ISA support - sending SIGILL.\n", - current->comm); + pr_debug("%s: R6 branch but no MIPSr6 ISA support - sending SIGILL.\n", + current->comm); force_sig(SIGILL, current); return -EFAULT; } -- cgit v1.2.3-59-g8ed1b From 9b03d8abe06d92195712fd489b2e8983de27fa68 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 2 Jun 2017 14:48:49 -0700 Subject: MIPS: Skip IPI setup if we only have 1 CPU If we're running on a system with only 1 possible CPU then it makes no sense to reserve or initialise IPIs since we'll never use them. Avoid doing so. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16192/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/smp.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index aba1afb64b62..770d4d1516cb 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -335,6 +335,9 @@ int mips_smp_ipi_free(const struct cpumask *mask) static int __init mips_smp_ipi_init(void) { + if (num_possible_cpus() == 1) + return 0; + mips_smp_ipi_allocate(cpu_possible_mask); call_desc = irq_to_desc(call_virq); -- cgit v1.2.3-59-g8ed1b From 516db1c61f3fd4328361699a2c74781ab1dbf84c Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 2 Jun 2017 14:48:50 -0700 Subject: MIPS: CM: Avoid per-core locking with CM3 & higher CM3 provides a GCR_CL_OTHER register per VP, rather than only per core. This means that we don't need to prevent other VPs within a core from racing with code that makes use of the core-other register region. Reduce locking overhead by demoting the per-core spinlock providing protection for CM2.5 & lower to a per-CPU/per-VP spinlock for CM3 & higher. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16193/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/mips-cm.c | 38 ++++++++++++++++++++++++++++++++------ 1 file changed, 32 insertions(+), 6 deletions(-) diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c index 659e6d3ae335..99bb74dd12ce 100644 --- a/arch/mips/kernel/mips-cm.c +++ b/arch/mips/kernel/mips-cm.c @@ -265,15 +265,34 @@ void mips_cm_lock_other(unsigned int core, unsigned int vp) u32 val; preempt_disable(); - curr_core = current_cpu_data.core; - spin_lock_irqsave(&per_cpu(cm_core_lock, curr_core), - per_cpu(cm_core_lock_flags, curr_core)); if (mips_cm_revision() >= CM_REV_CM3) { val = core << CM3_GCR_Cx_OTHER_CORE_SHF; val |= vp << CM3_GCR_Cx_OTHER_VP_SHF; + + /* + * We need to disable interrupts in SMP systems in order to + * ensure that we don't interrupt the caller with code which + * may modify the redirect register. We do so here in a + * slightly obscure way by using a spin lock, since this has + * the neat property of also catching any nested uses of + * mips_cm_lock_other() leading to a deadlock or a nice warning + * with lockdep enabled. + */ + spin_lock_irqsave(this_cpu_ptr(&cm_core_lock), + *this_cpu_ptr(&cm_core_lock_flags)); } else { BUG_ON(vp != 0); + + /* + * We only have a GCR_CL_OTHER per core in systems with + * CM 2.5 & older, so have to ensure other VP(E)s don't + * race with us. + */ + curr_core = current_cpu_data.core; + spin_lock_irqsave(&per_cpu(cm_core_lock, curr_core), + per_cpu(cm_core_lock_flags, curr_core)); + val = core << CM_GCR_Cx_OTHER_CORENUM_SHF; } @@ -288,10 +307,17 @@ void mips_cm_lock_other(unsigned int core, unsigned int vp) void mips_cm_unlock_other(void) { - unsigned curr_core = current_cpu_data.core; + unsigned int curr_core; + + if (mips_cm_revision() < CM_REV_CM3) { + curr_core = current_cpu_data.core; + spin_unlock_irqrestore(&per_cpu(cm_core_lock, curr_core), + per_cpu(cm_core_lock_flags, curr_core)); + } else { + spin_unlock_irqrestore(this_cpu_ptr(&cm_core_lock), + *this_cpu_ptr(&cm_core_lock_flags)); + } - spin_unlock_irqrestore(&per_cpu(cm_core_lock, curr_core), - per_cpu(cm_core_lock_flags, curr_core)); preempt_enable(); } -- cgit v1.2.3-59-g8ed1b From 2f93a60c3d829da07764eafd922beb40e7317aa3 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 2 Jun 2017 14:48:51 -0700 Subject: MIPS: CM: WARN on attempt to lock invalid VP, not BUG Rather than using BUG_ON in the case of an invalid attempt to lock access to a non-zero VP on a pre-CM3 system, use WARN_ON so that we have even the slightest chance of recovery. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16194/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/mips-cm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c index 99bb74dd12ce..cb0c57f860d4 100644 --- a/arch/mips/kernel/mips-cm.c +++ b/arch/mips/kernel/mips-cm.c @@ -282,7 +282,7 @@ void mips_cm_lock_other(unsigned int core, unsigned int vp) spin_lock_irqsave(this_cpu_ptr(&cm_core_lock), *this_cpu_ptr(&cm_core_lock_flags)); } else { - BUG_ON(vp != 0); + WARN_ON(vp != 0); /* * We only have a GCR_CL_OTHER per core in systems with -- cgit v1.2.3-59-g8ed1b From c8b7712c34d0604e2540608731bd5e9202c1139e Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 2 Jun 2017 14:48:52 -0700 Subject: MIPS: CPS: Select CONFIG_SYS_SUPPORTS_SCHED_SMT for MIPSr6 Prior to MIPSr6 multithreading is only supported if CONFIG_MIPS_MT_SMP is enabled, so CONFIG_MIPS_MT_SMP selects CONFIG_SYS_SUPPORTS_SCHED_SMT. With MIPSr6 the CONFIG_MIPS_CPS SMP implementation always supports multithreading, so have it select CONFIG_SYS_SUPPORTS_SCHED_SMT in order to allow the scheduler to make better informed decisions on multithreaded MIPSr6 systems (for example those using I6400 or I6500 CPUs). Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16195/ Signed-off-by: Ralf Baechle --- arch/mips/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index ef1cb20cfbb3..a986116dabb5 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -2381,6 +2381,7 @@ config MIPS_CPS select SMP select SYNC_R4K if (CEVT_R4K || CSRC_R4K) select SYS_SUPPORTS_HOTPLUG_CPU + select SYS_SUPPORTS_SCHED_SMT if CPU_MIPSR6 select SYS_SUPPORTS_SMP select WEAK_ORDERING help -- cgit v1.2.3-59-g8ed1b From 5570ba2ee920de4e7760a2802b842771845b2c32 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 2 Jun 2017 14:48:53 -0700 Subject: MIPS: CPS: Prevent multi-core with dcache aliasing Systems using the MIPS Coherence Manager (CM) cannot support multi-core SMP with dcache aliasing. This is because CPU caches are VIPT, but interventions in CM-based systems provide only the physical address to remote caches. This means that interventions may behave incorrectly in the presence of an aliasing dcache, since the physical address used when handling an intervention may lead to operation on an aliased cache line rather than the correct line. Prevent us from running into this issue by refusing to boot secondary cores in systems where dcache aliasing may occur. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16196/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/smp-cps.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index 36954ddd0b9f..90ecd099c4b0 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -142,9 +142,11 @@ static void __init cps_prepare_cpus(unsigned int max_cpus) /* Warn the user if the CCA prevents multi-core */ ncores = mips_cm_numcores(); - if (cca_unsuitable && ncores > 1) { - pr_warn("Using only one core due to unsuitable CCA 0x%x\n", - cca); + if ((cca_unsuitable || cpu_has_dc_aliases) && ncores > 1) { + pr_warn("Using only one core due to %s%s%s\n", + cca_unsuitable ? "unsuitable CCA" : "", + (cca_unsuitable && cpu_has_dc_aliases) ? " & " : "", + cpu_has_dc_aliases ? "dcache aliasing" : ""); for_each_present_cpu(c) { if (cpu_data[c].core) -- cgit v1.2.3-59-g8ed1b From 4ad755c9e39c0eeae16f96b97602f1954f582c66 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 2 Jun 2017 14:48:54 -0700 Subject: MIPS: CPS: Handle cores not powering down more gracefully If we get into a state where a core that ought to power down isn't doing so then the current result is that another CPU gets stuck inside cps_cpu_die() waiting for CPU that ought to be powering down to do so. The best case scenario is that we then trigger RCU stall messages or lockup messages, but neither makes it particularly clear what's happening. Handle this more gracefully by introducing a timeout beyond which we warn the user that the core didn't power down & stop waiting for it. This at least allows the CPU running cps_cpu_die() to continue normally, and hopefully presuming the CPU that powered back up is doing nothing harmful the system will continue functioning as normal. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16197/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/smp-cps.c | 27 ++++++++++++++++++++++++--- 1 file changed, 24 insertions(+), 3 deletions(-) diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index 90ecd099c4b0..f832e99ad4c3 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -490,6 +490,7 @@ static void cps_cpu_die(unsigned int cpu) { unsigned core = cpu_data[cpu].core; unsigned int vpe_id = cpu_vpe_id(&cpu_data[cpu]); + ktime_t fail_time; unsigned stat; int err; @@ -516,6 +517,7 @@ static void cps_cpu_die(unsigned int cpu) * state, the latter happening when a JTAG probe is connected * in which case the CPC will refuse to power down the core. */ + fail_time = ktime_add_ms(ktime_get(), 2000); do { mips_cm_lock_other(core, 0); mips_cpc_lock_other(core); @@ -523,9 +525,28 @@ static void cps_cpu_die(unsigned int cpu) stat &= CPC_Cx_STAT_CONF_SEQSTATE_MSK; mips_cpc_unlock_other(); mips_cm_unlock_other(); - } while (stat != CPC_Cx_STAT_CONF_SEQSTATE_D0 && - stat != CPC_Cx_STAT_CONF_SEQSTATE_D2 && - stat != CPC_Cx_STAT_CONF_SEQSTATE_U2); + + if (stat == CPC_Cx_STAT_CONF_SEQSTATE_D0 || + stat == CPC_Cx_STAT_CONF_SEQSTATE_D2 || + stat == CPC_Cx_STAT_CONF_SEQSTATE_U2) + break; + + /* + * The core ought to have powered down, but didn't & + * now we don't really know what state it's in. It's + * likely that its _pwr_up pin has been wired to logic + * 1 & it powered back up as soon as we powered it + * down... + * + * The best we can do is warn the user & continue in + * the hope that the core is doing nothing harmful & + * might behave properly if we online it later. + */ + if (WARN(ktime_after(ktime_get(), fail_time), + "CPU%u hasn't powered down, seq. state %u\n", + cpu, stat >> CPC_Cx_STAT_CONF_SEQSTATE_SHF)) + break; + } while (1); /* Indicate the core is powered off */ bitmap_clear(core_power, core, 1); -- cgit v1.2.3-59-g8ed1b From fa7a3b4a7217b40bf58c4f38e5ee573b43a8aa2f Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 2 Jun 2017 14:48:55 -0700 Subject: MIPS: CPS: Handle spurious VP starts more gracefully On pre-r6 systems with the MT ASE the CPS SMP code included checks to halt the VPE running mips_cps_boot_vpes() if its bit in the struct core_boot_config vpe_mask field is clear. This was largely done in order to allow us to start arbitrary VPEs within a core despite the fact that hardware is typically configured to run only VPE0 after powering up a core. VPE0 would start the desired other VPEs, halt itself, and the fact that VPE0 started would be largely hidden & irrelevant. In MIPSr6 multithreading we have control over which VPs start executing when a core powers up via the cores CPC registers accessed remotely through the redirect block. For this reason the MIPSr6 multithreading path in mips_cps_boot_vpes() hasn't bothered up until now to handle halting the VP running it. However it is possible to power up cores entirely in hardware by using a pwr_up pin associated with the core. Unfortunately some systems wire this pin to a logic 1, which means that it is possible for a core to power up at a point that software doesn't expect. The result is that we generally go execute the kernel on a CPU that ought not to be running & the results can be unpredictable. Handle this case by stopping VPs that we don't expect to be running in mips_cps_boot_vpes() - with this change even if a core powers up it will do nothing useful & all VPs within it will stop running before they proceed to run general kernel code & do any damage. Ideally we would produce some sort of warning here, but given the stage of core bringup this happens at that would be non-trivial. We also will only hit this if a core starts up after being offlined via hotplug, and when that happens we will already produce a warning that the CPU didn't power down in cps_cpu_die() which seems sufficient. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16198/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/cps-vec.S | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S index a00e87b0256d..b849fe6aad94 100644 --- a/arch/mips/kernel/cps-vec.S +++ b/arch/mips/kernel/cps-vec.S @@ -22,6 +22,7 @@ #define GCR_CL_COHERENCE_OFS 0x2008 #define GCR_CL_ID_OFS 0x2028 +#define CPC_CL_VC_STOP_OFS 0x2020 #define CPC_CL_VC_RUN_OFS 0x2028 .extern mips_cm_base @@ -376,8 +377,12 @@ LEAF(mips_cps_boot_vpes) PTR_LI t2, UNCAC_BASE PTR_ADD t1, t1, t2 - /* Set VC_RUN to the VPE mask */ + /* Start any other VPs that ought to be running */ PTR_S ta2, CPC_CL_VC_RUN_OFS(t1) + + /* Ensure this VP stops running if it shouldn't be */ + not ta2 + PTR_S ta2, CPC_CL_VC_STOP_OFS(t1) ehb #elif defined(CONFIG_MIPS_MT) -- cgit v1.2.3-59-g8ed1b From e7bc8557428f069eaa613b3676ea6931c0f7fe43 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 2 Jun 2017 15:38:01 -0700 Subject: MIPS: Add CPU shared FTLB feature detection Some systems share FTLB RAMs or entries between sibling CPUs (ie. hardware threads, or VP(E)s, within a core). These properties require kernel handling in various places. As a start this patch introduces cpu_has_shared_ftlb_ram & cpu_has_shared_ftlb_entries feature macros which we set appropriately for I6400 & I6500 CPUs. Further patches will make use of these macros as appropriate. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16202/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/cpu-features.h | 41 ++++++++++++++++++++++++++++++++++++ arch/mips/include/asm/cpu.h | 4 ++++ arch/mips/kernel/cpu-probe.c | 11 ++++++++++ 3 files changed, 56 insertions(+) diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h index 494d38274142..d6ea8e7c5107 100644 --- a/arch/mips/include/asm/cpu-features.h +++ b/arch/mips/include/asm/cpu-features.h @@ -487,6 +487,47 @@ # define cpu_has_perf (cpu_data[0].options & MIPS_CPU_PERF) #endif +#if defined(CONFIG_SMP) && defined(__mips_isa_rev) && (__mips_isa_rev >= 6) +/* + * Some systems share FTLB RAMs between threads within a core (siblings in + * kernel parlance). This means that FTLB entries may become invalid at almost + * any point when an entry is evicted due to a sibling thread writing an entry + * to the shared FTLB RAM. + * + * This is only relevant to SMP systems, and the only systems that exhibit this + * property implement MIPSr6 or higher so we constrain support for this to + * kernels that will run on such systems. + */ +# ifndef cpu_has_shared_ftlb_ram +# define cpu_has_shared_ftlb_ram \ + (current_cpu_data.options & MIPS_CPU_SHARED_FTLB_RAM) +# endif + +/* + * Some systems take this a step further & share FTLB entries between siblings. + * This is implemented as TLB writes happening as usual, but if an entry + * written by a sibling exists in the shared FTLB for a translation which would + * otherwise cause a TLB refill exception then the CPU will use the entry + * written by its sibling rather than triggering a refill & writing a matching + * TLB entry for itself. + * + * This is naturally only valid if a TLB entry is known to be suitable for use + * on all siblings in a CPU, and so it only takes effect when MMIDs are in use + * rather than ASIDs or when a TLB entry is marked global. + */ +# ifndef cpu_has_shared_ftlb_entries +# define cpu_has_shared_ftlb_entries \ + (current_cpu_data.options & MIPS_CPU_SHARED_FTLB_ENTRIES) +# endif +#endif /* SMP && __mips_isa_rev >= 6 */ + +#ifndef cpu_has_shared_ftlb_ram +# define cpu_has_shared_ftlb_ram 0 +#endif +#ifndef cpu_has_shared_ftlb_entries +# define cpu_has_shared_ftlb_entries 0 +#endif + /* * Guest capabilities */ diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h index 53b8b1f49084..ce798594c868 100644 --- a/arch/mips/include/asm/cpu.h +++ b/arch/mips/include/asm/cpu.h @@ -418,6 +418,10 @@ enum cpu_type_enum { #define MIPS_CPU_GUESTID MBIT_ULL(51) /* CPU uses VZ ASE GuestID feature */ #define MIPS_CPU_DRG MBIT_ULL(52) /* CPU has VZ Direct Root to Guest (DRG) */ #define MIPS_CPU_UFR MBIT_ULL(53) /* CPU supports User mode FR switching */ +#define MIPS_CPU_SHARED_FTLB_RAM \ + MBIT_ULL(54) /* CPU shares FTLB RAM with another */ +#define MIPS_CPU_SHARED_FTLB_ENTRIES \ + MBIT_ULL(55) /* CPU shares FTLB entries with another */ /* * CPU ASE encodings diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index 09462bba629f..3f0d43ce994a 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -1653,6 +1653,17 @@ static inline void cpu_probe_mips(struct cpuinfo_mips *c, unsigned int cpu) decode_configs(c); spram_config(); + + switch (__get_cpu_type(c->cputype)) { + case CPU_I6500: + c->options |= MIPS_CPU_SHARED_FTLB_ENTRIES; + /* fall-through */ + case CPU_I6400: + c->options |= MIPS_CPU_SHARED_FTLB_RAM; + /* fall-through */ + default: + break; + } } static inline void cpu_probe_alchemy(struct cpuinfo_mips *c, unsigned int cpu) -- cgit v1.2.3-59-g8ed1b From f39878cc5b09c75d35eaf52131e920b872e3feb4 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 2 Jun 2017 15:38:02 -0700 Subject: MIPS: Handle tlbex-tlbp race condition In systems where there are multiple actors updating the TLB, the potential exists for a race condition wherein a CPU hits a TLB exception but by the time it reaches a TLBP instruction the affected TLB entry may have been replaced. This can happen if, for example, a CPU shares the TLB between hardware threads (VPs) within a core and one of them replaces the entry that another has just taken a TLB exception for. We handle this race in the case of the Hardware Table Walker (HTW) being the other actor already, but didn't take into account the potential for multiple threads racing. Include the code for aborting TLB exception handling in affected multi-threaded systems, those being the I6400 & I6500 CPUs which share TLB entries between VPs. In the case of using RiXi without dedicated exceptions we have never handled this race even for HTW. This patch adds WARN()s to these cases which ought never to be hit because all CPUs with either HTW or shared FTLB RAMs also include dedicated RiXi exceptions, but the WARN()s will ensure this is always the case. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16203/ Signed-off-by: Ralf Baechle --- arch/mips/mm/tlbex.c | 38 +++++++++++++++++++++++++++++++++++++- 1 file changed, 37 insertions(+), 1 deletion(-) diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index ed1c5297547a..e6499209b81c 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -2015,6 +2015,26 @@ static void build_r3000_tlb_modify_handler(void) } #endif /* CONFIG_MIPS_PGD_C0_CONTEXT */ +static bool cpu_has_tlbex_tlbp_race(void) +{ + /* + * When a Hardware Table Walker is running it can replace TLB entries + * at any time, leading to a race between it & the CPU. + */ + if (cpu_has_htw) + return true; + + /* + * If the CPU shares FTLB RAM with its siblings then our entry may be + * replaced at any time by a sibling performing a write to the FTLB. + */ + if (cpu_has_shared_ftlb_ram) + return true; + + /* In all other cases there ought to be no race condition to handle */ + return false; +} + /* * R4000 style TLB load/store/modify handlers. */ @@ -2051,7 +2071,7 @@ build_r4000_tlbchange_handler_head(u32 **p, struct uasm_label **l, iPTE_LW(p, wr.r1, wr.r2); /* get even pte */ if (!m4kc_tlbp_war()) { build_tlb_probe_entry(p); - if (cpu_has_htw) { + if (cpu_has_tlbex_tlbp_race()) { /* race condition happens, leaving */ uasm_i_ehb(p); uasm_i_mfc0(p, wr.r3, C0_INDEX); @@ -2125,6 +2145,14 @@ static void build_r4000_tlb_load_handler(void) } uasm_i_nop(&p); + /* + * Warn if something may race with us & replace the TLB entry + * before we read it here. Everything with such races should + * also have dedicated RiXi exception handlers, so this + * shouldn't be hit. + */ + WARN(cpu_has_tlbex_tlbp_race(), "Unhandled race in RiXi path"); + uasm_i_tlbr(&p); switch (current_cpu_type()) { @@ -2192,6 +2220,14 @@ static void build_r4000_tlb_load_handler(void) } uasm_i_nop(&p); + /* + * Warn if something may race with us & replace the TLB entry + * before we read it here. Everything with such races should + * also have dedicated RiXi exception handlers, so this + * shouldn't be hit. + */ + WARN(cpu_has_tlbex_tlbp_race(), "Unhandled race in RiXi path"); + uasm_i_tlbr(&p); switch (current_cpu_type()) { -- cgit v1.2.3-59-g8ed1b From cebf8c0f4f4e378f5e82606023b92ffbb1ad6048 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 2 Jun 2017 15:38:03 -0700 Subject: MIPS: Allow storing pgd in C0_CONTEXT for MIPSr6 CONFIG_MIPS_PGD_C0_CONTEXT, which allows a pointer to the page directory to be stored in the cop0 Context register when enabled, was previously only allowed for MIPSr2. MIPSr6 is just as able to make use of it, so allow it there too. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16204/ Signed-off-by: Ralf Baechle --- arch/mips/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index a986116dabb5..609986e8b21e 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -2073,7 +2073,7 @@ config CPU_SUPPORTS_UNCACHED_ACCELERATED bool config MIPS_PGD_C0_CONTEXT bool - default y if 64BIT && CPU_MIPSR2 && !CPU_XLP + default y if 64BIT && (CPU_MIPSR2 || CPU_MIPSR6) && !CPU_XLP # # Set to y for ptrace access to watch registers. -- cgit v1.2.3-59-g8ed1b From 5f930860e70a4761f026d3e3a9f7787eac3c4f60 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 2 Jun 2017 15:38:04 -0700 Subject: MIPS: Use current_cpu_type() in m4kc_tlbp_war() Use current_cpu_type() to check for 4Kc processors instead of checking the PRID directly. This will allow for the 4Kc case to be optimised out of kernels that can't run on 4KC processors, thanks to __get_cpu_type() and its unreachable() call. Signed-off-by: Paul Burton Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16205/ Signed-off-by: Ralf Baechle --- arch/mips/mm/tlbex.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index e6499209b81c..5aadc69c8ce3 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -153,8 +153,7 @@ static int scratchpad_offset(int i) */ static int m4kc_tlbp_war(void) { - return (current_cpu_data.processor_id & 0xffff00) == - (PRID_COMP_MIPS | PRID_IMP_4KC); + return current_cpu_type() == CPU_4KC; } /* Handle labels (which must be positive integers). */ -- cgit v1.2.3-59-g8ed1b From 8ec7f15b8cca4f790df5cdf33f26e2926d4ee2fd Mon Sep 17 00:00:00 2001 From: Goran Ferenc Date: Wed, 28 Jun 2017 17:55:28 +0200 Subject: MIPS: VDSO: Fix conversions in do_monotonic()/do_monotonic_coarse() Fix incorrect calculation in do_monotonic() and do_monotonic_coarse() function that in turn caused incorrect values returned by the vdso version of system call clock_gettime() on mips64 if its system clock ID parameter was CLOCK_MONOTONIC or CLOCK_MONOTONIC_COARSE. Consider these variables and their types on mips32 and mips64: tk->wall_to_monotonic.tv_sec s64, s64 (kernel/vdso.c) vdso_data.wall_to_mono_sec u32, u32 (kernel/vdso.c) to_mono_sec u32, u32 (vdso/gettimeofday.c) ts->tv_sec s32, s64 (vdso/gettimeofday.c) For mips64 case, u32 vdso_data.wall_to_mono_sec variable is updated from the 64-bit signed variable tk->wall_to_monotonic.tv_sec (kernel/vdso.c:76) which is a negative number holding the time passed from 1970-01-01 to the time boot started. This 64-bit signed value is currently around 47+ years, in seconds. For instance, let this value be: -1489757461 or 11111111111111111111111111111111 10100111001101000001101011101011 By updating 32-bit vdso_data.wall_to_mono_sec variable, we lose upper 32 bits (signed 1's). to_mono_sec variable is a parameter of do_monotonic() and do_monotonic_coarse() functions which holds vdso_data.wall_to_mono_sec value. Its value needs to be added (or subtracted considering it holds negative value from the tk->wall_to_monotonic.tv_sec) to the current time passed from 1970-01-01 (ts->tv_sec), which is again something like 47+ years, but increased by the time passed from the boot to the current time. ts->tv_sec is 32-bit long in case of 32-bit architecture and 64-bit long in case of 64-bit architecture. Consider the update of ts->tv_sec (vdso/gettimeofday.c:55 & 167): ts->tv_sec += to_mono_sec; mips32 case: This update will be performed correctly, since both ts->tv_sec and to_mono_sec are 32-bit long and the sign in to_mono_sec is preserved. Implicit conversion from u32 to s32 will be done correctly. mips64 case: This update will be wrong, since the implicit conversion will not be done correctly. The reason is that the conversion will be from u32 to s64. This is because to_mono_sec is 32-bit long for both mips32 and mips64 cases and s64..33 bits of converted to_mono_sec variable will be zeros. So, in order to make MIPS64 implementation work properly for MONOTONIC and MONOTONIC_COARSE clock ids on mips64, the size of wall_to_mono_sec variable in mips_vdso_data union and respective parameters in do_monotonic() and do_monotonic_coarse() functions should be changed from u32 to u64. Because of consistency, this size change from u32 and u64 is also done for wall_to_mono_nsec variable and corresponding function parameters. As far as similar situations for other architectures are concerned, let's take a look at arm. Arm has two distinct vdso_data structures for 32-bit & 64-bit cases, and arm's wall_to_mono_sec and wall_to_mono_nsec are u32 for 32-bit and u64 for 64-bit cases. On the other hand, MIPS has only one structure (mips_vdso_data), hence the need for changing the size of above mentioned parameters. Signed-off-by: Goran Ferenc Signed-off-by: Miodrag Dinic Signed-off-by: Aleksandar Markovic Cc: Douglas Leung Cc: James Hogan Cc: Paul Burton Cc: Petar Jovanovic Cc: Raghu Gandham Cc: linux-mips@linux-mips.org Cc: linux-kernel@vger.kernel.org Patchwork: https://patchwork.linux-mips.org/patch/16638/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/vdso.h | 4 ++-- arch/mips/vdso/gettimeofday.c | 8 ++++---- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/mips/include/asm/vdso.h b/arch/mips/include/asm/vdso.h index 8f4ca5dd992b..b7cd6cf77b83 100644 --- a/arch/mips/include/asm/vdso.h +++ b/arch/mips/include/asm/vdso.h @@ -79,8 +79,8 @@ union mips_vdso_data { struct { u64 xtime_sec; u64 xtime_nsec; - u32 wall_to_mono_sec; - u32 wall_to_mono_nsec; + u64 wall_to_mono_sec; + u64 wall_to_mono_nsec; u32 seq_count; u32 cs_shift; u8 clock_mode; diff --git a/arch/mips/vdso/gettimeofday.c b/arch/mips/vdso/gettimeofday.c index ce89c9e294f9..fd7d433970bf 100644 --- a/arch/mips/vdso/gettimeofday.c +++ b/arch/mips/vdso/gettimeofday.c @@ -39,8 +39,8 @@ static __always_inline int do_monotonic_coarse(struct timespec *ts, const union mips_vdso_data *data) { u32 start_seq; - u32 to_mono_sec; - u32 to_mono_nsec; + u64 to_mono_sec; + u64 to_mono_nsec; do { start_seq = vdso_data_read_begin(data); @@ -148,8 +148,8 @@ static __always_inline int do_monotonic(struct timespec *ts, { u32 start_seq; u64 ns; - u32 to_mono_sec; - u32 to_mono_nsec; + u64 to_mono_sec; + u64 to_mono_nsec; do { start_seq = vdso_data_read_begin(data); -- cgit v1.2.3-59-g8ed1b From 180902e08f051f72c89ffa366f4e4f7a8e9c753e Mon Sep 17 00:00:00 2001 From: Goran Ferenc Date: Wed, 28 Jun 2017 17:55:29 +0200 Subject: MIPS: VDSO: Add implementation of clock_gettime() fallback This patch adds clock_gettime_fallback() function that wraps assembly invocation of clock_gettime() syscall using __NR_clock_gettime. This function is used if pure VDSO implementation of clock_gettime() does not succeed for any reason. For example, it is called if the clkid parameter of clock_gettime() is not one of the clkids listed in the switch-case block of the function __vdso_clock_gettime() (one such case for clkid is CLOCK_BOOTIME). If syscall invocation via __NR_clock_gettime fails, register a3 will be set. So, after the syscall, register a3 is tested and the return value is negated if it's set. Signed-off-by: Goran Ferenc Signed-off-by: Miodrag Dinic Signed-off-by: Aleksandar Markovic Cc: Douglas Leung Cc: James Hogan Cc: Paul Burton Cc: Petar Jovanovic Cc: Raghu Gandham Cc: linux-mips@linux-mips.org Cc: linux-kernel@vger.kernel.org Patchwork: https://patchwork.linux-mips.org/patch/16639/ Signed-off-by: Ralf Baechle --- arch/mips/vdso/gettimeofday.c | 25 ++++++++++++++++++++++--- 1 file changed, 22 insertions(+), 3 deletions(-) diff --git a/arch/mips/vdso/gettimeofday.c b/arch/mips/vdso/gettimeofday.c index fd7d433970bf..5f6337545ee2 100644 --- a/arch/mips/vdso/gettimeofday.c +++ b/arch/mips/vdso/gettimeofday.c @@ -20,6 +20,24 @@ #include #include +static __always_inline long clock_gettime_fallback(clockid_t _clkid, + struct timespec *_ts) +{ + register struct timespec *ts asm("a1") = _ts; + register clockid_t clkid asm("a0") = _clkid; + register long ret asm("v0"); + register long nr asm("v0") = __NR_clock_gettime; + register long error asm("a3"); + + asm volatile( + " syscall\n" + : "=r" (ret), "=r" (error) + : "r" (clkid), "r" (ts), "r" (nr) + : "memory"); + + return error ? -ret : ret; +} + static __always_inline int do_realtime_coarse(struct timespec *ts, const union mips_vdso_data *data) { @@ -207,7 +225,7 @@ int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) int __vdso_clock_gettime(clockid_t clkid, struct timespec *ts) { const union mips_vdso_data *data = get_vdso_data(); - int ret; + int ret = -1; switch (clkid) { case CLOCK_REALTIME_COARSE: @@ -223,10 +241,11 @@ int __vdso_clock_gettime(clockid_t clkid, struct timespec *ts) ret = do_monotonic(ts, data); break; default: - ret = -ENOSYS; break; } - /* If we return -ENOSYS libc should fall back to a syscall. */ + if (ret) + ret = clock_gettime_fallback(clkid, ts); + return ret; } -- cgit v1.2.3-59-g8ed1b From 0b523a85e134d41f57ddd8c5193bd9f0a5e20b0d Mon Sep 17 00:00:00 2001 From: Goran Ferenc Date: Wed, 28 Jun 2017 17:55:30 +0200 Subject: MIPS: VDSO: Add implementation of gettimeofday() fallback This patch adds gettimeofday_fallback() function that wraps assembly invocation of gettimeofday() syscall using __NR_gettimeofday. This function is used if pure VDSO implementation gettimeofday() does not succeed for any reason. Its imeplementation is enclosed in "#ifdef CONFIG_MIPS_CLOCK_VSYSCALL" to be in sync with the similar arrangement for __vdso_gettimeofday(). If syscall invocation via __NR_gettimeofday fails, register a3 will be set. So, after the syscall, register a3 is tested and the return valuem is negated if it's set. Signed-off-by: Goran Ferenc Signed-off-by: Miodrag Dinic Signed-off-by: Aleksandar Markovic Cc: Douglas Leung Cc: James Hogan Cc: Paul Burton Cc: Petar Jovanovic Cc: Raghu Gandham Cc: linux-mips@linux-mips.org Cc: linux-kernel@vger.kernel.org Patchwork: https://patchwork.linux-mips.org/patch/16640/ Signed-off-by: Ralf Baechle --- arch/mips/vdso/gettimeofday.c | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) diff --git a/arch/mips/vdso/gettimeofday.c b/arch/mips/vdso/gettimeofday.c index 5f6337545ee2..23305bf6c7a2 100644 --- a/arch/mips/vdso/gettimeofday.c +++ b/arch/mips/vdso/gettimeofday.c @@ -20,6 +20,28 @@ #include #include +#ifdef CONFIG_MIPS_CLOCK_VSYSCALL + +static __always_inline long gettimeofday_fallback(struct timeval *_tv, + struct timezone *_tz) +{ + register struct timezone *tz asm("a1") = _tz; + register struct timeval *tv asm("a0") = _tv; + register long ret asm("v0"); + register long nr asm("v0") = __NR_gettimeofday; + register long error asm("a3"); + + asm volatile( + " syscall\n" + : "=r" (ret), "=r" (error) + : "r" (tv), "r" (tz), "r" (nr) + : "memory"); + + return error ? -ret : ret; +} + +#endif + static __always_inline long clock_gettime_fallback(clockid_t _clkid, struct timespec *_ts) { @@ -205,7 +227,7 @@ int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) ret = do_realtime(&ts, data); if (ret) - return ret; + return gettimeofday_fallback(tv, tz); if (tv) { tv->tv_sec = ts.tv_sec; -- cgit v1.2.3-59-g8ed1b From bdb94f6e824d5bd1577c3f80cbe0c6b4beab5a5c Mon Sep 17 00:00:00 2001 From: Aleksandar Markovic Date: Wed, 28 Jun 2017 17:55:31 +0200 Subject: MIPS: VDSO: Fix a mismatch between comment and preprocessor constant Sync the comment with its preprocessor constant counterpart. Signed-off-by: Aleksandar Markovic Cc: James Hogan Cc: Miodrag Dinic Cc: Paul Burton Cc: Petar Jovanovic Cc: Raghu Gandham Cc: linux-mips@linux-mips.org Cc: linux-kernel@vger.kernel.org Patchwork: https://patchwork.linux-mips.org/patch/16641/ Signed-off-by: Ralf Baechle --- arch/mips/vdso/gettimeofday.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/vdso/gettimeofday.c b/arch/mips/vdso/gettimeofday.c index 23305bf6c7a2..974276e828b2 100644 --- a/arch/mips/vdso/gettimeofday.c +++ b/arch/mips/vdso/gettimeofday.c @@ -242,7 +242,7 @@ int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) return 0; } -#endif /* CONFIG_CLKSRC_MIPS_GIC */ +#endif /* CONFIG_MIPS_CLOCK_VSYSCALL */ int __vdso_clock_gettime(clockid_t clkid, struct timespec *ts) { -- cgit v1.2.3-59-g8ed1b From 0d76d6e1eede5f2aa13695cb4c9d763bb3555e3e Mon Sep 17 00:00:00 2001 From: Willy WOLFF Date: Sat, 24 Jun 2017 14:06:03 +0100 Subject: thermal: fix source code documentation for parameters Some parameters are not documented, or not present at all, in thermal governors code. Signed-off-by: Willy Wolff Signed-off-by: Zhang Rui --- drivers/thermal/fair_share.c | 1 + drivers/thermal/step_wise.c | 3 +-- drivers/thermal/user_space.c | 3 ++- 3 files changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/thermal/fair_share.c b/drivers/thermal/fair_share.c index 68bd1b569118..d3469fbc5207 100644 --- a/drivers/thermal/fair_share.c +++ b/drivers/thermal/fair_share.c @@ -71,6 +71,7 @@ static long get_target_state(struct thermal_zone_device *tz, /** * fair_share_throttle - throttles devices associated with the given zone * @tz - thermal_zone_device + * @trip - trip point index * * Throttling Logic: This uses three parameters to calculate the new * throttle state of the cooling devices associated with the given zone. diff --git a/drivers/thermal/step_wise.c b/drivers/thermal/step_wise.c index bcef2e7c4ec9..be95826631b7 100644 --- a/drivers/thermal/step_wise.c +++ b/drivers/thermal/step_wise.c @@ -186,8 +186,7 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip) /** * step_wise_throttle - throttles devices associated with the given zone * @tz - thermal_zone_device - * @trip - the trip point - * @trip_type - type of the trip point + * @trip - trip point index * * Throttling Logic: This uses the trend of the thermal zone to throttle. * If the thermal zone is 'heating up' this throttles all the cooling diff --git a/drivers/thermal/user_space.c b/drivers/thermal/user_space.c index c908150c268d..8e92a06ef48a 100644 --- a/drivers/thermal/user_space.c +++ b/drivers/thermal/user_space.c @@ -24,12 +24,13 @@ #include #include + #include "thermal_core.h" /** * notify_user_space - Notifies user space about thermal events * @tz - thermal_zone_device - * @trip - Trip point index + * @trip - trip point index * * This function notifies the user space through UEvents. */ -- cgit v1.2.3-59-g8ed1b From 86326031e3d4dec828d966c19fe9fe1371d0a0a8 Mon Sep 17 00:00:00 2001 From: Sumeet Pawnikar Date: Tue, 30 May 2017 23:14:58 +0530 Subject: Thermal/int340x: Fix few typos and kernel-doc style This patch fix the few typos in function header of acpi_parse_trt. Also, fix the typo in kernel debug message for acpi_parse_art. Signed-off-by: Sumeet Pawnikar Signed-off-by: Zhang Rui --- drivers/thermal/int340x_thermal/acpi_thermal_rel.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/thermal/int340x_thermal/acpi_thermal_rel.c b/drivers/thermal/int340x_thermal/acpi_thermal_rel.c index 2c2ec7666eb1..51ceb80212a7 100644 --- a/drivers/thermal/int340x_thermal/acpi_thermal_rel.c +++ b/drivers/thermal/int340x_thermal/acpi_thermal_rel.c @@ -62,8 +62,8 @@ static int acpi_thermal_rel_release(struct inode *inode, struct file *file) * acpi_parse_trt - Thermal Relationship Table _TRT for passive cooling * * @handle: ACPI handle of the device contains _TRT - * @art_count: the number of valid entries resulted from parsing _TRT - * @artp: pointer to pointer of array of art entries in parsing result + * @trt_count: the number of valid entries resulted from parsing _TRT + * @trtp: pointer to pointer of array of _TRT entries in parsing result * @create_dev: whether to create platform devices for target and source * */ @@ -208,7 +208,7 @@ int acpi_parse_art(acpi_handle handle, int *art_count, struct art **artp, if (art->target) { result = acpi_bus_get_device(art->target, &adev); if (result) - pr_warn("Failed to get source ACPI device\n"); + pr_warn("Failed to get target ACPI device\n"); } } -- cgit v1.2.3-59-g8ed1b From 4ca0e75e46b6ee408bdc334fff449323d476812c Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Tue, 6 Jun 2017 16:00:41 -0700 Subject: thermal: int340x: check for sensor when PTYP is missing For INT3403 sensor PTYP field is mandatory. But some platforms didn't have this field for sensors. This cause load failure for int3403 driver. This change checks for the presence of _TMP method and if present, then treats this device as a sensor. Signed-off-by: Srinivas Pandruvada Signed-off-by: Zhang Rui --- drivers/thermal/int340x_thermal/int3403_thermal.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/thermal/int340x_thermal/int3403_thermal.c b/drivers/thermal/int340x_thermal/int3403_thermal.c index c4890c9437eb..8a7f24dd9315 100644 --- a/drivers/thermal/int340x_thermal/int3403_thermal.c +++ b/drivers/thermal/int340x_thermal/int3403_thermal.c @@ -238,8 +238,16 @@ static int int3403_add(struct platform_device *pdev) status = acpi_evaluate_integer(priv->adev->handle, "PTYP", NULL, &priv->type); if (ACPI_FAILURE(status)) { - result = -EINVAL; - goto err; + unsigned long long tmp; + + status = acpi_evaluate_integer(priv->adev->handle, "_TMP", + NULL, &tmp); + if (ACPI_FAILURE(status)) { + result = -EINVAL; + goto err; + } else { + priv->type = INT3403_TYPE_SENSOR; + } } platform_set_drvdata(pdev, priv); -- cgit v1.2.3-59-g8ed1b From 5cd82b757795228516bf60a0552d1a40fa8adeb2 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Tue, 13 Jun 2017 10:15:26 +0800 Subject: drm/i915/gvt: Make function dpy_reg_mmio_readx safe The dpy_reg_mmio_read_x functions directly copy 4 bytes data to the target address with considering the length. If may cause the target memory corrupted if the requested length less than 4 bytes. Fix it for safety even we already have some checking to avoid this happen. And for convince, the 3 functions are merged. Signed-off-by: Changbin Du Signed-off-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/handlers.c | 35 +++++++++++++++++++---------------- 1 file changed, 19 insertions(+), 16 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 437a35f41b62..a9114aa1eddb 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -366,21 +366,24 @@ static int lcpll_ctl_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, static int dpy_reg_mmio_read(struct intel_vgpu *vgpu, unsigned int offset, void *p_data, unsigned int bytes) { - *(u32 *)p_data = (1 << 17); - return 0; -} - -static int dpy_reg_mmio_read_2(struct intel_vgpu *vgpu, unsigned int offset, - void *p_data, unsigned int bytes) -{ - *(u32 *)p_data = 3; - return 0; -} + switch (offset) { + case 0xe651c: + case 0xe661c: + case 0xe671c: + case 0xe681c: + vgpu_vreg(vgpu, offset) = 1 << 17; + break; + case 0xe6c04: + vgpu_vreg(vgpu, offset) = 0x3; + break; + case 0xe6e1c: + vgpu_vreg(vgpu, offset) = 0x2f << 16; + break; + default: + return -EINVAL; + } -static int dpy_reg_mmio_read_3(struct intel_vgpu *vgpu, unsigned int offset, - void *p_data, unsigned int bytes) -{ - *(u32 *)p_data = (0x2f << 16); + read_vreg(vgpu, offset, p_data, bytes); return 0; } @@ -1991,8 +1994,8 @@ static int init_generic_mmio_info(struct intel_gvt *gvt) MMIO_DH(0xe661c, D_ALL, dpy_reg_mmio_read, NULL); MMIO_DH(0xe671c, D_ALL, dpy_reg_mmio_read, NULL); MMIO_DH(0xe681c, D_ALL, dpy_reg_mmio_read, NULL); - MMIO_DH(0xe6c04, D_ALL, dpy_reg_mmio_read_2, NULL); - MMIO_DH(0xe6e1c, D_ALL, dpy_reg_mmio_read_3, NULL); + MMIO_DH(0xe6c04, D_ALL, dpy_reg_mmio_read, NULL); + MMIO_DH(0xe6e1c, D_ALL, dpy_reg_mmio_read, NULL); MMIO_RO(PCH_PORT_HOTPLUG, D_ALL, 0, PORTA_HOTPLUG_STATUS_MASK -- cgit v1.2.3-59-g8ed1b From 138b87fa43b629ed14429e2e056fe4d5ef132921 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Thu, 29 Jun 2017 15:37:20 +0300 Subject: drm: vblank: Fix vblank timestamp update MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 3fcdcb270936 ("drm/vblank: Switch to bool in_vblank_irq in get_vblank_timestamp") inverted a condition by mistake that resulted in vblank timestamps always being 0 on hardware without a vblank counter. Fix it. Fixes: 3fcdcb270936 ("drm/vblank: Switch to bool in_vblank_irq in get_vblank_timestamp") Suggested-by: Ville Syrjälä Signed-off-by: Laurent Pinchart Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/20170629123720.27173-1-laurent.pinchart+renesas@ideasonboard.com --- drivers/gpu/drm/drm_vblank.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_vblank.c b/drivers/gpu/drm/drm_vblank.c index 463e4d81fb0d..e9f33cd805dd 100644 --- a/drivers/gpu/drm/drm_vblank.c +++ b/drivers/gpu/drm/drm_vblank.c @@ -242,7 +242,7 @@ static void drm_update_vblank_count(struct drm_device *dev, unsigned int pipe, * Otherwise reinitialize delayed at next vblank interrupt and assign 0 * for now, to mark the vblanktimestamp as invalid. */ - if (!rc && in_vblank_irq) + if (!rc && !in_vblank_irq) t_vblank = (struct timeval) {0, 0}; store_vblank(dev, pipe, diff, &t_vblank, cur_vblank); -- cgit v1.2.3-59-g8ed1b From 3859a271a003aba01e45b85c9d8b355eb7bf25f9 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 28 Oct 2016 01:22:25 -0700 Subject: randstruct: Mark various structs for randomization This marks many critical kernel structures for randomization. These are structures that have been targeted in the past in security exploits, or contain functions pointers, pointers to function pointer tables, lists, workqueues, ref-counters, credentials, permissions, or are otherwise sensitive. This initial list was extracted from Brad Spengler/PaX Team's code in the last public patch of grsecurity/PaX based on my understanding of the code. Changes or omissions from the original code are mine and don't reflect the original grsecurity/PaX code. Left out of this list is task_struct, which requires special handling and will be covered in a subsequent patch. Signed-off-by: Kees Cook --- arch/x86/include/asm/processor.h | 2 +- fs/mount.h | 4 ++-- fs/namei.c | 2 +- fs/proc/internal.h | 6 +++--- include/linux/binfmts.h | 4 ++-- include/linux/cdev.h | 2 +- include/linux/cred.h | 4 ++-- include/linux/dcache.h | 2 +- include/linux/fs.h | 17 +++++++++-------- include/linux/fs_struct.h | 2 +- include/linux/ipc.h | 2 +- include/linux/ipc_namespace.h | 2 +- include/linux/key-type.h | 4 ++-- include/linux/kmod.h | 2 +- include/linux/kobject.h | 2 +- include/linux/lsm_hooks.h | 4 ++-- include/linux/mm_types.h | 4 ++-- include/linux/module.h | 4 ++-- include/linux/mount.h | 2 +- include/linux/msg.h | 2 +- include/linux/path.h | 2 +- include/linux/pid_namespace.h | 2 +- include/linux/proc_ns.h | 2 +- include/linux/sched.h | 2 +- include/linux/sched/signal.h | 2 +- include/linux/sem.h | 2 +- include/linux/shm.h | 2 +- include/linux/sysctl.h | 2 +- include/linux/tty.h | 2 +- include/linux/tty_driver.h | 4 ++-- include/linux/user_namespace.h | 2 +- include/linux/utsname.h | 2 +- include/net/af_unix.h | 2 +- include/net/neighbour.h | 2 +- include/net/net_namespace.h | 2 +- include/net/sock.h | 2 +- kernel/futex.c | 4 ++-- security/keys/internal.h | 2 +- 38 files changed, 57 insertions(+), 56 deletions(-) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 3cada998a402..e2335edb9fc5 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -129,7 +129,7 @@ struct cpuinfo_x86 { /* Index into per_cpu list: */ u16 cpu_index; u32 microcode; -}; +} __randomize_layout; struct cpuid_regs { u32 eax, ebx, ecx, edx; diff --git a/fs/mount.h b/fs/mount.h index bf1fda6eed8f..e406b286fba1 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -16,7 +16,7 @@ struct mnt_namespace { u64 event; unsigned int mounts; /* # of mounts in the namespace */ unsigned int pending_mounts; -}; +} __randomize_layout; struct mnt_pcp { int mnt_count; @@ -68,7 +68,7 @@ struct mount { struct hlist_head mnt_pins; struct fs_pin mnt_umount; struct dentry *mnt_ex_mountpoint; -}; +} __randomize_layout; #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */ diff --git a/fs/namei.c b/fs/namei.c index 6571a5f5112e..1764620ac383 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -524,7 +524,7 @@ struct nameidata { struct inode *link_inode; unsigned root_seq; int dfd; -}; +} __randomize_layout; static void set_nameidata(struct nameidata *p, int dfd, struct filename *name) { diff --git a/fs/proc/internal.h b/fs/proc/internal.h index c5ae09b6c726..07b16318223f 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -51,7 +51,7 @@ struct proc_dir_entry { spinlock_t pde_unload_lock; /* proc_fops checks and pde_users bumps */ u8 namelen; char name[]; -}; +} __randomize_layout; union proc_op { int (*proc_get_link)(struct dentry *, struct path *); @@ -70,7 +70,7 @@ struct proc_inode { struct list_head sysctl_inodes; const struct proc_ns_operations *ns_ops; struct inode vfs_inode; -}; +} __randomize_layout; /* * General functions @@ -279,7 +279,7 @@ struct proc_maps_private { #ifdef CONFIG_NUMA struct mempolicy *task_mempolicy; #endif -}; +} __randomize_layout; struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode); diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 05488da3aee9..3ae9013eeaaa 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -46,7 +46,7 @@ struct linux_binprm { unsigned interp_flags; unsigned interp_data; unsigned long loader, exec; -}; +} __randomize_layout; #define BINPRM_FLAGS_ENFORCE_NONDUMP_BIT 0 #define BINPRM_FLAGS_ENFORCE_NONDUMP (1 << BINPRM_FLAGS_ENFORCE_NONDUMP_BIT) @@ -81,7 +81,7 @@ struct linux_binfmt { int (*load_shlib)(struct file *); int (*core_dump)(struct coredump_params *cprm); unsigned long min_coredump; /* minimal dump size */ -}; +} __randomize_layout; extern void __register_binfmt(struct linux_binfmt *fmt, int insert); diff --git a/include/linux/cdev.h b/include/linux/cdev.h index 408bc09ce497..cb28eb21e3ca 100644 --- a/include/linux/cdev.h +++ b/include/linux/cdev.h @@ -17,7 +17,7 @@ struct cdev { struct list_head list; dev_t dev; unsigned int count; -}; +} __randomize_layout; void cdev_init(struct cdev *, const struct file_operations *); diff --git a/include/linux/cred.h b/include/linux/cred.h index b03e7d049a64..82c8a9e1aabb 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -31,7 +31,7 @@ struct group_info { atomic_t usage; int ngroups; kgid_t gid[0]; -}; +} __randomize_layout; /** * get_group_info - Get a reference to a group info structure @@ -145,7 +145,7 @@ struct cred { struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */ struct group_info *group_info; /* supplementary groups for euid/fsgid */ struct rcu_head rcu; /* RCU deletion hook */ -}; +} __randomize_layout; extern void __put_cred(struct cred *); extern void exit_creds(struct task_struct *); diff --git a/include/linux/dcache.h b/include/linux/dcache.h index d2e38dc6172c..7eb262e13d3c 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -113,7 +113,7 @@ struct dentry { struct hlist_bl_node d_in_lookup_hash; /* only for in-lookup ones */ struct rcu_head d_rcu; } d_u; -}; +} __randomize_layout; /* * dentry->d_lock spinlock nesting subclasses: diff --git a/include/linux/fs.h b/include/linux/fs.h index 803e5a9b2654..8f28143486c4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -275,7 +275,7 @@ struct kiocb { void (*ki_complete)(struct kiocb *iocb, long ret, long ret2); void *private; int ki_flags; -}; +} __randomize_layout; static inline bool is_sync_kiocb(struct kiocb *kiocb) { @@ -392,7 +392,7 @@ struct address_space { gfp_t gfp_mask; /* implicit gfp mask for allocations */ struct list_head private_list; /* ditto */ void *private_data; /* ditto */ -} __attribute__((aligned(sizeof(long)))); +} __attribute__((aligned(sizeof(long)))) __randomize_layout; /* * On most architectures that alignment is already the case; but * must be enforced here for CRIS, to let the least significant bit @@ -435,7 +435,7 @@ struct block_device { int bd_fsfreeze_count; /* Mutex for freeze */ struct mutex bd_fsfreeze_mutex; -}; +} __randomize_layout; /* * Radix-tree tags, for tagging dirty and writeback pages within the pagecache @@ -653,7 +653,7 @@ struct inode { #endif void *i_private; /* fs or device private pointer */ -}; +} __randomize_layout; static inline unsigned int i_blocksize(const struct inode *node) { @@ -868,7 +868,8 @@ struct file { struct list_head f_tfile_llink; #endif /* #ifdef CONFIG_EPOLL */ struct address_space *f_mapping; -} __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ +} __randomize_layout + __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ struct file_handle { __u32 handle_bytes; @@ -1005,7 +1006,7 @@ struct file_lock { int state; /* state of grant or error if -ve */ } afs; } fl_u; -}; +} __randomize_layout; struct file_lock_context { spinlock_t flc_lock; @@ -1404,7 +1405,7 @@ struct super_block { spinlock_t s_inode_wblist_lock; struct list_head s_inodes_wb; /* writeback inodes */ -}; +} __randomize_layout; /* Helper functions so that in most cases filesystems will * not need to deal directly with kuid_t and kgid_t and can @@ -1690,7 +1691,7 @@ struct file_operations { u64); ssize_t (*dedupe_file_range)(struct file *, u64, u64, struct file *, u64); -}; +} __randomize_layout; struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index 0efc3e62843a..7a026240cbb1 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -12,7 +12,7 @@ struct fs_struct { int umask; int in_exec; struct path root, pwd; -}; +} __randomize_layout; extern struct kmem_cache *fs_cachep; diff --git a/include/linux/ipc.h b/include/linux/ipc.h index 71fd92d81b26..ea0eb0b5f98c 100644 --- a/include/linux/ipc.h +++ b/include/linux/ipc.h @@ -20,6 +20,6 @@ struct kern_ipc_perm { umode_t mode; unsigned long seq; void *security; -} ____cacheline_aligned_in_smp; +} ____cacheline_aligned_in_smp __randomize_layout; #endif /* _LINUX_IPC_H */ diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index 848e5796400e..65327ee0936b 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -61,7 +61,7 @@ struct ipc_namespace { struct ucounts *ucounts; struct ns_common ns; -}; +} __randomize_layout; extern struct ipc_namespace init_ipc_ns; extern spinlock_t mq_lock; diff --git a/include/linux/key-type.h b/include/linux/key-type.h index 8496cf64575c..9520fc3c3b9a 100644 --- a/include/linux/key-type.h +++ b/include/linux/key-type.h @@ -45,7 +45,7 @@ struct key_preparsed_payload { size_t datalen; /* Raw datalen */ size_t quotalen; /* Quota length for proposed payload */ time_t expiry; /* Expiry time of key */ -}; +} __randomize_layout; typedef int (*request_key_actor_t)(struct key_construction *key, const char *op, void *aux); @@ -158,7 +158,7 @@ struct key_type { /* internal fields */ struct list_head link; /* link in types list */ struct lock_class_key lock_class; /* key->sem lock class */ -}; +} __randomize_layout; extern struct key_type key_type_keyring; diff --git a/include/linux/kmod.h b/include/linux/kmod.h index c4e441e00db5..655082c88fd9 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -64,7 +64,7 @@ struct subprocess_info { int (*init)(struct subprocess_info *info, struct cred *new); void (*cleanup)(struct subprocess_info *info); void *data; -}; +} __randomize_layout; extern int call_usermodehelper(const char *path, char **argv, char **envp, int wait); diff --git a/include/linux/kobject.h b/include/linux/kobject.h index ca85cb80e99a..084513350317 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -172,7 +172,7 @@ struct kset { spinlock_t list_lock; struct kobject kobj; const struct kset_uevent_ops *uevent_ops; -}; +} __randomize_layout; extern void kset_init(struct kset *kset); extern int __must_check kset_register(struct kset *kset); diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 080f34e66017..565163fc9ad4 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1876,7 +1876,7 @@ struct security_hook_heads { struct list_head audit_rule_match; struct list_head audit_rule_free; #endif /* CONFIG_AUDIT */ -}; +} __randomize_layout; /* * Security module hook list structure. @@ -1887,7 +1887,7 @@ struct security_hook_list { struct list_head *head; union security_list_options hook; char *lsm; -}; +} __randomize_layout; /* * Initializing a security_hook_list structure takes diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 45cdb27791a3..ff151814a02d 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -342,7 +342,7 @@ struct vm_area_struct { struct mempolicy *vm_policy; /* NUMA policy for the VMA */ #endif struct vm_userfaultfd_ctx vm_userfaultfd_ctx; -}; +} __randomize_layout; struct core_thread { struct task_struct *task; @@ -500,7 +500,7 @@ struct mm_struct { atomic_long_t hugetlb_usage; #endif struct work_struct async_put_work; -}; +} __randomize_layout; extern struct mm_struct init_mm; diff --git a/include/linux/module.h b/include/linux/module.h index 21f56393602f..d93111d7def6 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -45,7 +45,7 @@ struct module_kobject { struct kobject *drivers_dir; struct module_param_attrs *mp; struct completion *kobj_completion; -}; +} __randomize_layout; struct module_attribute { struct attribute attr; @@ -475,7 +475,7 @@ struct module { ctor_fn_t *ctors; unsigned int num_ctors; #endif -} ____cacheline_aligned; +} ____cacheline_aligned __randomize_layout; #ifndef MODULE_ARCH_INIT #define MODULE_ARCH_INIT {} #endif diff --git a/include/linux/mount.h b/include/linux/mount.h index 8e0352af06b7..1ce85e6fd95f 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -67,7 +67,7 @@ struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ struct super_block *mnt_sb; /* pointer to superblock */ int mnt_flags; -}; +} __randomize_layout; struct file; /* forward dec */ struct path; diff --git a/include/linux/msg.h b/include/linux/msg.h index f3f302f9c197..a001305f5a79 100644 --- a/include/linux/msg.h +++ b/include/linux/msg.h @@ -29,7 +29,7 @@ struct msg_queue { struct list_head q_messages; struct list_head q_receivers; struct list_head q_senders; -}; +} __randomize_layout; /* Helper routines for sys_msgsnd and sys_msgrcv */ extern long do_msgsnd(int msqid, long mtype, void __user *mtext, diff --git a/include/linux/path.h b/include/linux/path.h index d1372186f431..cde895cc4af4 100644 --- a/include/linux/path.h +++ b/include/linux/path.h @@ -7,7 +7,7 @@ struct vfsmount; struct path { struct vfsmount *mnt; struct dentry *dentry; -}; +} __randomize_layout; extern void path_get(const struct path *); extern void path_put(const struct path *); diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index c2a989dee876..b09136f88cf4 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -52,7 +52,7 @@ struct pid_namespace { int hide_pid; int reboot; /* group exit code if this pidns was rebooted */ struct ns_common ns; -}; +} __randomize_layout; extern struct pid_namespace init_pid_ns; diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index 58ab28d81fc2..06844b54dfc1 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -21,7 +21,7 @@ struct proc_ns_operations { int (*install)(struct nsproxy *nsproxy, struct ns_common *ns); struct user_namespace *(*owner)(struct ns_common *ns); struct ns_common *(*get_parent)(struct ns_common *ns); -}; +} __randomize_layout; extern const struct proc_ns_operations netns_operations; extern const struct proc_ns_operations utsns_operations; diff --git a/include/linux/sched.h b/include/linux/sched.h index 2b69fc650201..f833254fce00 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -408,7 +408,7 @@ struct sched_rt_entity { /* rq "owned" by this entity/group: */ struct rt_rq *my_q; #endif -}; +} __randomize_layout; struct sched_dl_entity { struct rb_node rb_node; diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index c06d63b3a583..2a0dd40b15db 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -222,7 +222,7 @@ struct signal_struct { struct mutex cred_guard_mutex; /* guard against foreign influences on * credential calculations * (notably. ptrace) */ -}; +} __randomize_layout; /* * Bits in flags field of signal_struct. diff --git a/include/linux/sem.h b/include/linux/sem.h index 9edec926e9d9..23bcbdfad4a6 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -21,7 +21,7 @@ struct sem_array { int sem_nsems; /* no. of semaphores in array */ int complex_count; /* pending complex operations */ unsigned int use_global_lock;/* >0: global lock required */ -}; +} __randomize_layout; #ifdef CONFIG_SYSVIPC diff --git a/include/linux/shm.h b/include/linux/shm.h index 04e881829625..0fb7061ec54c 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -22,7 +22,7 @@ struct shmid_kernel /* private to the kernel */ /* The task created the shm object. NULL if the task is dead. */ struct task_struct *shm_creator; struct list_head shm_clist; /* list by creator */ -}; +} __randomize_layout; /* shm_mode upper byte flags */ #define SHM_DEST 01000 /* segment will be destroyed on last detach */ diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 80d07816def0..9ddeef2c03e2 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -117,7 +117,7 @@ struct ctl_table struct ctl_table_poll *poll; void *extra1; void *extra2; -}; +} __randomize_layout; struct ctl_node { struct rb_node node; diff --git a/include/linux/tty.h b/include/linux/tty.h index d07cd2105a6c..73f8d0977bb0 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -333,7 +333,7 @@ struct tty_struct { /* If the tty has a pending do_SAK, queue it here - akpm */ struct work_struct SAK_work; struct tty_port *port; -}; +} __randomize_layout; /* Each of a tty's open files has private_data pointing to tty_file_private */ struct tty_file_private { diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index b742b5e47cc2..00b2213f6a35 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -291,7 +291,7 @@ struct tty_operations { void (*poll_put_char)(struct tty_driver *driver, int line, char ch); #endif const struct file_operations *proc_fops; -}; +} __randomize_layout; struct tty_driver { int magic; /* magic number for this structure */ @@ -325,7 +325,7 @@ struct tty_driver { const struct tty_operations *ops; struct list_head tty_drivers; -}; +} __randomize_layout; extern struct list_head tty_drivers; diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 32354b4b4b2b..b3575ce29148 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -66,7 +66,7 @@ struct user_namespace { #endif struct ucounts *ucounts; int ucount_max[UCOUNT_COUNTS]; -}; +} __randomize_layout; struct ucounts { struct hlist_node node; diff --git a/include/linux/utsname.h b/include/linux/utsname.h index 60f0bb83b313..da826ed059cf 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -26,7 +26,7 @@ struct uts_namespace { struct user_namespace *user_ns; struct ucounts *ucounts; struct ns_common ns; -}; +} __randomize_layout; extern struct uts_namespace init_uts_ns; #ifdef CONFIG_UTS_NS diff --git a/include/net/af_unix.h b/include/net/af_unix.h index fd60eccb59a6..64e2a1e24a2c 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -36,7 +36,7 @@ struct unix_skb_parms { u32 secid; /* Security ID */ #endif u32 consumed; -}; +} __randomize_layout; #define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb)) diff --git a/include/net/neighbour.h b/include/net/neighbour.h index e4dd3a214034..a62959d2b3f7 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -155,7 +155,7 @@ struct neighbour { struct rcu_head rcu; struct net_device *dev; u8 primary_key[0]; -}; +} __randomize_layout; struct neigh_ops { int family; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index fe80bb48ab1f..a224196d16ac 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -147,7 +147,7 @@ struct net { #endif struct sock *diag_nlsk; atomic_t fnhe_genid; -}; +} __randomize_layout; #include diff --git a/include/net/sock.h b/include/net/sock.h index f33e3d134e0b..d349297db9e9 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1113,7 +1113,7 @@ struct proto { atomic_t socks; #endif int (*diag_destroy)(struct sock *sk, int err); -}; +} __randomize_layout; int proto_register(struct proto *prot, int alloc_slab); void proto_unregister(struct proto *prot); diff --git a/kernel/futex.c b/kernel/futex.c index 357348a6cf6b..5616511abf39 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -212,7 +212,7 @@ struct futex_pi_state { atomic_t refcount; union futex_key key; -}; +} __randomize_layout; /** * struct futex_q - The hashed futex queue entry, one per waiting task @@ -246,7 +246,7 @@ struct futex_q { struct rt_mutex_waiter *rt_waiter; union futex_key *requeue_pi_key; u32 bitset; -}; +} __randomize_layout; static const struct futex_q futex_q_init = { /* list gets initialized in queue_me()*/ diff --git a/security/keys/internal.h b/security/keys/internal.h index c0f8682eba69..6494954e9980 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -197,7 +197,7 @@ struct request_key_auth { void *callout_info; size_t callout_len; pid_t pid; -}; +} __randomize_layout; extern struct key_type key_type_request_key_auth; extern struct key *request_key_auth_new(struct key *target, -- cgit v1.2.3-59-g8ed1b From 29e48ce87f1eaaa4b1fe3d9af90c586ac2d1fb74 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 5 Apr 2017 22:43:33 -0700 Subject: task_struct: Allow randomized layout This marks most of the layout of task_struct as randomizable, but leaves thread_info and scheduler state untouched at the start, and thread_struct untouched at the end. Other parts of the kernel use unnamed structures, but the 0-day builder using gcc-4.4 blows up on static initializers. Officially, it's documented as only working on gcc 4.6 and later, which further confuses me: https://gcc.gnu.org/wiki/C11Status The structure layout randomization already requires gcc 4.7, but instead of depending on the plugin being enabled, just check the gcc versions for wider build testing. At Linus's suggestion, the marking is hidden in a macro to reduce how ugly it looks. Additionally, indenting is left unchanged since it would make things harder to read. Randomization of task_struct is modified from Brad Spengler/PaX Team's code in the last public patch of grsecurity/PaX based on my understanding of the code. Changes or omissions from the original code are mine and don't reflect the original grsecurity/PaX code. Cc: Linus Torvalds Signed-off-by: Kees Cook --- include/linux/compiler-gcc.h | 13 ++++++++++++- include/linux/compiler.h | 5 +++++ include/linux/sched.h | 14 ++++++++++++++ 3 files changed, 31 insertions(+), 1 deletion(-) diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 7deaae3dc87d..c4a66c036692 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -231,6 +231,7 @@ #endif /* GCC_VERSION >= 40500 */ #if GCC_VERSION >= 40600 + /* * When used with Link Time Optimization, gcc can optimize away C functions or * variables which are referenced only from assembly code. __visible tells the @@ -238,7 +239,17 @@ * this. */ #define __visible __attribute__((externally_visible)) -#endif + +/* + * RANDSTRUCT_PLUGIN wants to use an anonymous struct, but it is only + * possible since GCC 4.6. To provide as much build testing coverage + * as possible, this is used for all GCC 4.6+ builds, and not just on + * RANDSTRUCT_PLUGIN builds. + */ +#define randomized_struct_fields_start struct { +#define randomized_struct_fields_end } __randomize_layout; + +#endif /* GCC_VERSION >= 40600 */ #if GCC_VERSION >= 40900 && !defined(__CHECKER__) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 55ee9ee814f8..0b4ac3e8c63e 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -456,6 +456,11 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s # define __no_randomize_layout #endif +#ifndef randomized_struct_fields_start +# define randomized_struct_fields_start +# define randomized_struct_fields_end +#endif + /* * Tell gcc if a function is cold. The compiler will assume any path * directly leading to the call is unlikely. diff --git a/include/linux/sched.h b/include/linux/sched.h index f833254fce00..e2ad3531e7fe 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -490,6 +490,13 @@ struct task_struct { #endif /* -1 unrunnable, 0 runnable, >0 stopped: */ volatile long state; + + /* + * This begins the randomizable portion of task_struct. Only + * scheduling-critical items should be added above here. + */ + randomized_struct_fields_start + void *stack; atomic_t usage; /* Per task flags (PF_*), defined further below: */ @@ -1051,6 +1058,13 @@ struct task_struct { /* Used by LSM modules for access restriction: */ void *security; #endif + + /* + * New fields for task_struct should be added above here, so that + * they are included in the randomized portion of task_struct. + */ + randomized_struct_fields_end + /* CPU-specific state of this task: */ struct thread_struct thread; -- cgit v1.2.3-59-g8ed1b From 8acdf5055974e49d337d51ac7011449cfd7b7d05 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 28 Oct 2016 00:45:16 -0700 Subject: randstruct: opt-out externally exposed function pointer structs Some function pointer structures are used externally to the kernel, like the paravirt structures. These should never be randomized, so mark them as such, in preparation for enabling randstruct's automatic selection of all-function-pointer structures. These markings are verbatim from Brad Spengler/PaX Team's code in the last public patch of grsecurity/PaX based on my understanding of the code. Changes or omissions from the original code are mine and don't reflect the original grsecurity/PaX code. Signed-off-by: Kees Cook --- arch/arm/include/asm/cacheflush.h | 2 +- arch/x86/include/asm/paravirt_types.h | 16 ++++++++-------- 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index d69bebf697e7..74504b154256 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -116,7 +116,7 @@ struct cpu_cache_fns { void (*dma_unmap_area)(const void *, size_t, int); void (*dma_flush_range)(const void *, const void *); -}; +} __no_randomize_layout; /* * Select the calling method diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 7465d6fe336f..96c7e3cf43fa 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -83,7 +83,7 @@ struct pv_init_ops { */ unsigned (*patch)(u8 type, u16 clobber, void *insnbuf, unsigned long addr, unsigned len); -}; +} __no_randomize_layout; struct pv_lazy_ops { @@ -91,12 +91,12 @@ struct pv_lazy_ops { void (*enter)(void); void (*leave)(void); void (*flush)(void); -}; +} __no_randomize_layout; struct pv_time_ops { unsigned long long (*sched_clock)(void); unsigned long long (*steal_clock)(int cpu); -}; +} __no_randomize_layout; struct pv_cpu_ops { /* hooks for various privileged instructions */ @@ -175,7 +175,7 @@ struct pv_cpu_ops { void (*start_context_switch)(struct task_struct *prev); void (*end_context_switch)(struct task_struct *next); -}; +} __no_randomize_layout; struct pv_irq_ops { /* @@ -198,7 +198,7 @@ struct pv_irq_ops { #ifdef CONFIG_X86_64 void (*adjust_exception_frame)(void); #endif -}; +} __no_randomize_layout; struct pv_mmu_ops { unsigned long (*read_cr2)(void); @@ -306,7 +306,7 @@ struct pv_mmu_ops { an mfn. We can tell which is which from the index. */ void (*set_fixmap)(unsigned /* enum fixed_addresses */ idx, phys_addr_t phys, pgprot_t flags); -}; +} __no_randomize_layout; struct arch_spinlock; #ifdef CONFIG_SMP @@ -323,7 +323,7 @@ struct pv_lock_ops { void (*kick)(int cpu); struct paravirt_callee_save vcpu_is_preempted; -}; +} __no_randomize_layout; /* This contains all the paravirt structures: we get a convenient * number for each function using the offset which we use to indicate @@ -335,7 +335,7 @@ struct paravirt_patch_template { struct pv_irq_ops pv_irq_ops; struct pv_mmu_ops pv_mmu_ops; struct pv_lock_ops pv_lock_ops; -}; +} __no_randomize_layout; extern struct pv_info pv_info; extern struct pv_init_ops pv_init_ops; -- cgit v1.2.3-59-g8ed1b From e3bdc8d7623d5875403ad40443e7b049ae200fcd Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Tue, 6 Jun 2017 15:12:37 +0530 Subject: thermal: imx: Handle return value of clk_prepare_enable clk_prepare_enable() can fail here and we must check its return value. Signed-off-by: Arvind Yadav Signed-off-by: Eduardo Valentin --- drivers/thermal/imx_thermal.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c index f7ec39f46ee4..4798b4b1fd77 100644 --- a/drivers/thermal/imx_thermal.c +++ b/drivers/thermal/imx_thermal.c @@ -660,8 +660,11 @@ static int imx_thermal_resume(struct device *dev) { struct imx_thermal_data *data = dev_get_drvdata(dev); struct regmap *map = data->tempmon; + int ret; - clk_prepare_enable(data->thermal_clk); + ret = clk_prepare_enable(data->thermal_clk); + if (ret) + return ret; /* Enabled thermal sensor after resume */ regmap_write(map, TEMPSENSE0 + REG_CLR, TEMPSENSE0_POWER_DOWN); regmap_write(map, TEMPSENSE0 + REG_SET, TEMPSENSE0_MEASURE_TEMP); -- cgit v1.2.3-59-g8ed1b From 919054fdfc8adf58c5512fe9872eb53ea0f5525d Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Tue, 6 Jun 2017 15:04:46 +0530 Subject: thermal: hisilicon: Handle return value of clk_prepare_enable clk_prepare_enable() can fail here and we must check its return value. Signed-off-by: Arvind Yadav Signed-off-by: Eduardo Valentin --- drivers/thermal/hisi_thermal.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/thermal/hisi_thermal.c b/drivers/thermal/hisi_thermal.c index f6429666a1cf..9c3ce341eb97 100644 --- a/drivers/thermal/hisi_thermal.c +++ b/drivers/thermal/hisi_thermal.c @@ -397,8 +397,11 @@ static int hisi_thermal_suspend(struct device *dev) static int hisi_thermal_resume(struct device *dev) { struct hisi_thermal_data *data = dev_get_drvdata(dev); + int ret; - clk_prepare_enable(data->clk); + ret = clk_prepare_enable(data->clk); + if (ret) + return ret; data->irq_enabled = true; hisi_thermal_enable_bind_irq_sensor(data); -- cgit v1.2.3-59-g8ed1b From 1fe3854a83b580727c9464b37b62ba77ead1d6f6 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 14 Jun 2017 12:13:27 +0300 Subject: thermal: bcm2835: fix an error code in probe() This causes a static checker because we're passing a valid pointer to PTR_ERR(). "err" is already the correct error code, so we can just delete this line. Fixes: bcb7dd9ef206 ("thermal: bcm2835: add thermal driver for bcm2835 SoC") Acked-by: Stefan Wahren Signed-off-by: Dan Carpenter Signed-off-by: Eduardo Valentin --- drivers/thermal/broadcom/bcm2835_thermal.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/thermal/broadcom/bcm2835_thermal.c b/drivers/thermal/broadcom/bcm2835_thermal.c index 0ecf80890c84..e6863c841662 100644 --- a/drivers/thermal/broadcom/bcm2835_thermal.c +++ b/drivers/thermal/broadcom/bcm2835_thermal.c @@ -245,7 +245,6 @@ static int bcm2835_thermal_probe(struct platform_device *pdev) */ err = tz->ops->get_trip_temp(tz, 0, &trip_temp); if (err < 0) { - err = PTR_ERR(tz); dev_err(&pdev->dev, "Not able to read trip_temp: %d\n", err); -- cgit v1.2.3-59-g8ed1b From 4086d90cffb8f48400d51fbab575fe50458512e3 Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Thu, 29 Jun 2017 13:59:54 +0200 Subject: drm/atomic: Add missing drm_atomic_state_clear to atomic_remove_fb All atomic state should be cleared when drm_modeset_backoff() is called, because it drops all locks and the state becomes invalid. The call to drm_atomic_state_clear was missing in atomic_remove_fb, so add the missing call there. Signed-off-by: Maarten Lankhorst Link: http://patchwork.freedesktop.org/patch/msgid/20170629115954.26029-1-maarten.lankhorst@linux.intel.com Reviewed-by: Daniel Vetter Fixes: db8f6403e88a ("drm: Convert drm_framebuffer_remove to atomic, v4.") Cc: stable@vger.kernel.org # v4.12-rc1+ --- drivers/gpu/drm/drm_framebuffer.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c index fc8ef42203ec..b3ef4f1c2630 100644 --- a/drivers/gpu/drm/drm_framebuffer.c +++ b/drivers/gpu/drm/drm_framebuffer.c @@ -832,6 +832,7 @@ unlock: drm_atomic_clean_old_fb(dev, plane_mask, ret); if (ret == -EDEADLK) { + drm_atomic_state_clear(state); drm_modeset_backoff(&ctx); goto retry; } -- cgit v1.2.3-59-g8ed1b From 81667e9c8ad827365f2d1e8b924caf062a19c593 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 3 Jul 2017 13:54:28 +0300 Subject: mtd: nand: mtk: release lock on error path We only want to hold the lock on the success path, not this error path. Fixes: 7ec4a37c5d71 ("mtd: nand: mediatek: add support for different MTK NAND FLASH Controller IP") Signed-off-by: Dan Carpenter Signed-off-by: Boris Brezillon --- drivers/mtd/nand/mtk_ecc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/nand/mtk_ecc.c b/drivers/mtd/nand/mtk_ecc.c index f38e2bb1953e..6c3a4aab0b48 100644 --- a/drivers/mtd/nand/mtk_ecc.c +++ b/drivers/mtd/nand/mtk_ecc.c @@ -273,8 +273,10 @@ int mtk_ecc_enable(struct mtk_ecc *ecc, struct mtk_ecc_config *config) mtk_ecc_wait_idle(ecc, op); ret = mtk_ecc_config(ecc, config); - if (ret) + if (ret) { + mutex_unlock(&ecc->lock); return ret; + } if (config->mode != ECC_NFI_MODE || op != ECC_ENCODE) { init_completion(&ecc->done); -- cgit v1.2.3-59-g8ed1b From ce3f7163e4ce8fd583dcb36b6ee6b81fd1b419ae Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Mon, 26 Jun 2017 23:30:51 +0300 Subject: drm/i915: Disable MSI for all pre-gen5 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We have pretty clear evidence that MSIs are getting lost on g4x and somehow the interrupt logic doesn't seem to recover from that state even if we try hard to clear the IIR. Disabling IER around the normal IIR clearing in the irq handler isn't sufficient to avoid this, so the problem really seems to be further up the interrupt chain. This should guarantee that there's always an edge if any IIR bits are set after the interrupt handler is done, which should normally guarantee that the CPU interrupt is generated. That approach seems to work perfectly on VLV/CHV, but apparently not on g4x. MSI is documented to be broken on 965gm at least. The chipset spec says MSI is defeatured because interrupts can be delayed or lost, which fits well with what we're seeing on g4x. Previously we've already disabled GMBUS interrupts on g4x because somehow GMBUS manages to raise legacy interrupts even when MSI is enabled. Since there's such widespread MSI breakahge all over in the pre-gen5 land let's just give up on MSI on these platforms. Seqno reporting might be negatively affected by this since the legcy interrupts aren't guaranteed to be ordered with the seqno writes, whereas MSI interrupts may be? But an occasioanlly missed seqno seems like a small price to pay for generally working interrupts. Cc: stable@vger.kernel.org Cc: Diego Viola Tested-by: Diego Viola Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=101261 Signed-off-by: Ville Syrjälä Link: http://patchwork.freedesktop.org/patch/msgid/20170626203051.28480-1-ville.syrjala@linux.intel.com Reviewed-by: Daniel Vetter (cherry picked from commit e38c2da01f76cca82b59ca612529b81df82a7cc7) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_drv.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index ee2325b180e7..fc307e03943c 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1132,10 +1132,12 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv) * and the registers being closely associated. * * According to chipset errata, on the 965GM, MSI interrupts may - * be lost or delayed, but we use them anyways to avoid - * stuck interrupts on some machines. + * be lost or delayed, and was defeatured. MSI interrupts seem to + * get lost on g4x as well, and interrupt delivery seems to stay + * properly dead afterwards. So we'll just disable them for all + * pre-gen5 chipsets. */ - if (!IS_I945G(dev_priv) && !IS_I945GM(dev_priv)) { + if (INTEL_GEN(dev_priv) >= 5) { if (pci_enable_msi(pdev) < 0) DRM_DEBUG_DRIVER("can't enable MSI"); } -- cgit v1.2.3-59-g8ed1b From 1a13a2ec3eb360c80e1ea88b9b7616fa64d4e278 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Tue, 27 Jun 2017 07:38:54 +0200 Subject: drm/i915: Fix an error checking test 'dma_buf_vmap' returns NULL on error, not an error pointer. Fixes: 6cca22ede8a4 ("drm/i915: Add some mock tests for dmabuf interop") Signed-off-by: Christophe JAILLET Link: http://patchwork.freedesktop.org/patch/msgid/20170627053854.21152-1-christophe.jaillet@wanadoo.fr Reviewed-by: Chris Wilson Signed-off-by: Chris Wilson (cherry picked from commit 7c3f5317b8c2828ab10e8cf87c8ab5232d1966d0) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c index d15cc9d3a5cd..89dc25a5a53b 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c @@ -246,9 +246,9 @@ static int igt_dmabuf_export_vmap(void *arg) i915_gem_object_put(obj); ptr = dma_buf_vmap(dmabuf); - if (IS_ERR(ptr)) { - err = PTR_ERR(ptr); - pr_err("dma_buf_vmap failed with err=%d\n", err); + if (!ptr) { + pr_err("dma_buf_vmap failed\n"); + err = -ENOMEM; goto out; } -- cgit v1.2.3-59-g8ed1b From 9c75b185274b7766fe69c2e73607c1ed780b284b Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Wed, 28 Jun 2017 18:06:05 -0300 Subject: drm/i915: reintroduce VLV/CHV PFI programming power domain workaround MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are still cases on these platforms where an attempt is made to configure the CDCLK while the power domain is off, like when coming back from a suspend. So the workaround below is still needed. This effectively reverts commit 63ff30442519 ("drm/i915: Nuke the VLV/CHV PFI programming power domain workaround"). Cc: stable@vger.kernel.org Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=101517 Suggested-by: Ville Syrjälä Signed-off-by: Gabriel Krisman Bertazi Link: http://patchwork.freedesktop.org/patch/msgid/20170628210605.4994-1-krisman@collabora.co.uk Reviewed-by: Ville Syrjälä Signed-off-by: Ville Syrjälä (cherry picked from commit 886015a0ad43c7fc034b23ea4614ba39162f9ddd) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_cdclk.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c index b8914db7d2e1..1241e5891b29 100644 --- a/drivers/gpu/drm/i915/intel_cdclk.c +++ b/drivers/gpu/drm/i915/intel_cdclk.c @@ -491,6 +491,14 @@ static void vlv_set_cdclk(struct drm_i915_private *dev_priv, int cdclk = cdclk_state->cdclk; u32 val, cmd; + /* There are cases where we can end up here with power domains + * off and a CDCLK frequency other than the minimum, like when + * issuing a modeset without actually changing any display after + * a system suspend. So grab the PIPE-A domain, which covers + * the HW blocks needed for the following programming. + */ + intel_display_power_get(dev_priv, POWER_DOMAIN_PIPE_A); + if (cdclk >= 320000) /* jump to highest voltage for 400MHz too */ cmd = 2; else if (cdclk == 266667) @@ -549,6 +557,8 @@ static void vlv_set_cdclk(struct drm_i915_private *dev_priv, intel_update_cdclk(dev_priv); vlv_program_pfi_credits(dev_priv); + + intel_display_power_put(dev_priv, POWER_DOMAIN_PIPE_A); } static void chv_set_cdclk(struct drm_i915_private *dev_priv, @@ -568,6 +578,14 @@ static void chv_set_cdclk(struct drm_i915_private *dev_priv, return; } + /* There are cases where we can end up here with power domains + * off and a CDCLK frequency other than the minimum, like when + * issuing a modeset without actually changing any display after + * a system suspend. So grab the PIPE-A domain, which covers + * the HW blocks needed for the following programming. + */ + intel_display_power_get(dev_priv, POWER_DOMAIN_PIPE_A); + /* * Specs are full of misinformation, but testing on actual * hardware has shown that we just need to write the desired @@ -590,6 +608,8 @@ static void chv_set_cdclk(struct drm_i915_private *dev_priv, intel_update_cdclk(dev_priv); vlv_program_pfi_credits(dev_priv); + + intel_display_power_put(dev_priv, POWER_DOMAIN_PIPE_A); } static int bdw_calc_cdclk(int max_pixclk) -- cgit v1.2.3-59-g8ed1b From 4ec654bf3a63d503e3c5336eade5c369ae17db56 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 29 Jun 2017 16:04:25 +0100 Subject: drm/i915: Avoid undefined behaviour of "u32 >> 32" When computing a hash for looking up relocation target handles in an execbuf, we start with a large size for the hashtable and proceed to halve it until the allocation succeeds. The final attempt is with an order of 0 (i.e. a single element). This means that we then pass bits=0 to hash_32() which then computes "hash >> (32 - 0)" to lookup the single element. Right shifting a value by the width of the operand is undefined, so limit the smallest hash table we use to order 1. v2: Keep the retry allocation flag for the final pass Fixes: 4ff4b44cbb70 ("drm/i915: Store a direct lookup from object handle to vma") Signed-off-by: Chris Wilson Cc: Joonas Lahtinen Cc: Tvrtko Ursulin Reviewed-by: Tvrtko Ursulin Link: http://patchwork.freedesktop.org/patch/msgid/20170629150425.27508-1-chris@chris-wilson.co.uk (cherry picked from commit 4d470f7359c4bf22518baa30700ad45649371a22) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 38 +++++++++++++++++++----------- 1 file changed, 24 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 9337446f1068..054b2e54cdaf 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -288,20 +288,26 @@ static int eb_create(struct i915_execbuffer *eb) * direct lookup. */ do { + unsigned int flags; + + /* While we can still reduce the allocation size, don't + * raise a warning and allow the allocation to fail. + * On the last pass though, we want to try as hard + * as possible to perform the allocation and warn + * if it fails. + */ + flags = GFP_TEMPORARY; + if (size > 1) + flags |= __GFP_NORETRY | __GFP_NOWARN; + eb->buckets = kzalloc(sizeof(struct hlist_head) << size, - GFP_TEMPORARY | - __GFP_NORETRY | - __GFP_NOWARN); + flags); if (eb->buckets) break; } while (--size); - if (unlikely(!eb->buckets)) { - eb->buckets = kzalloc(sizeof(struct hlist_head), - GFP_TEMPORARY); - if (unlikely(!eb->buckets)) - return -ENOMEM; - } + if (unlikely(!size)) + return -ENOMEM; eb->lut_size = size; } else { @@ -452,7 +458,7 @@ eb_add_vma(struct i915_execbuffer *eb, return err; } - if (eb->lut_size >= 0) { + if (eb->lut_size > 0) { vma->exec_handle = entry->handle; hlist_add_head(&vma->exec_node, &eb->buckets[hash_32(entry->handle, @@ -894,7 +900,7 @@ static void eb_release_vmas(const struct i915_execbuffer *eb) static void eb_reset_vmas(const struct i915_execbuffer *eb) { eb_release_vmas(eb); - if (eb->lut_size >= 0) + if (eb->lut_size > 0) memset(eb->buckets, 0, sizeof(struct hlist_head) << eb->lut_size); } @@ -903,7 +909,7 @@ static void eb_destroy(const struct i915_execbuffer *eb) { GEM_BUG_ON(eb->reloc_cache.rq); - if (eb->lut_size >= 0) + if (eb->lut_size > 0) kfree(eb->buckets); } @@ -2180,8 +2186,11 @@ i915_gem_do_execbuffer(struct drm_device *dev, } } - if (eb_create(&eb)) - return -ENOMEM; + err = eb_create(&eb); + if (err) + goto err_out_fence; + + GEM_BUG_ON(!eb.lut_size); /* * Take a local wakeref for preparing to dispatch the execbuf as @@ -2340,6 +2349,7 @@ err_unlock: err_rpm: intel_runtime_pm_put(eb.i915); eb_destroy(&eb); +err_out_fence: if (out_fence_fd != -1) put_unused_fd(out_fence_fd); err_in_fence: -- cgit v1.2.3-59-g8ed1b From 2347728934b501b07bea8b1b6e8fa27a56dc098f Mon Sep 17 00:00:00 2001 From: Rodrigo Vivi Date: Mon, 19 Jun 2017 14:21:47 -0700 Subject: drm/i915/cfl: Fix Workarounds. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit During the review of Coffee Lake workarounds Mika pointed out that WaDisableKillLogic and GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC should be removed from CFL and with that I should carry the rv-b. However when doing the v2 I removed another Workaround that should remain because although not mentioned by spec the history of hangs around it advocates on its favor. On some follow-up patches I continued operating on the wrong workardound, but Ville noticed that, so here is the fix for the current CFL code that is upstream already. Fixes: 46c26662d2f ("drm/i915/cfl: Introduce Coffee Lake workarounds.") Cc: Ville Syrjälä Cc: Dhinakaran Pandiyan Cc: Mika Kuoppala Signed-off-by: Rodrigo Vivi Reviewed-by: Dhinakaran Pandiyan (cherry picked from commit 98eed3d1ade53596e1c8785e049f03da4480a820) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_engine_cs.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index a4487c5b7e37..5b4de719bec3 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -821,9 +821,10 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine) I915_WRITE(BDW_SCRATCH1, I915_READ(BDW_SCRATCH1) | GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE); - /* WaDisableKillLogic:bxt,skl,kbl,cfl */ - I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | - ECOCHK_DIS_TLB); + /* WaDisableKillLogic:bxt,skl,kbl */ + if (!IS_COFFEELAKE(dev_priv)) + I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | + ECOCHK_DIS_TLB); /* WaClearFlowControlGpgpuContextSave:skl,bxt,kbl,glk,cfl */ /* WaDisablePartialInstShootdown:skl,bxt,kbl,glk,cfl */ @@ -894,10 +895,9 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine) WA_SET_BIT_MASKED(HDC_CHICKEN0, HDC_FORCE_NON_COHERENT); - /* WaDisableHDCInvalidation:skl,bxt,kbl */ - if (!IS_COFFEELAKE(dev_priv)) - I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | - BDW_DISABLE_HDC_INVALIDATION); + /* WaDisableHDCInvalidation:skl,bxt,kbl,cfl */ + I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | + BDW_DISABLE_HDC_INVALIDATION); /* WaDisableSamplerPowerBypassForSOPingPong:skl,bxt,kbl,cfl */ if (IS_SKYLAKE(dev_priv) || -- cgit v1.2.3-59-g8ed1b From c379b897ba1a7f786419e8c36a3438ce856f016a Mon Sep 17 00:00:00 2001 From: "Navare, Manasi D" Date: Thu, 29 Jun 2017 18:14:01 -0700 Subject: drm/i915/cnl: Fix the CURSOR_COEFF_MASK used in DDI Vswing Programming The Cursor Coeff is lower 6 bits in the PORT_TX_DW4 register and hence the CURSOR_COEFF_MASK should be (0x3F << 0) Fixes: 04416108ccea ("drm/i915/cnl: Add registers related to voltage swing sequences.") Signed-off-by: Manasi Navare Reviewed-by: Rodrigo Vivi Signed-off-by: Rodrigo Vivi Link: http://patchwork.freedesktop.org/patch/msgid/1498785241-21138-1-git-send-email-manasi.d.navare@intel.com (cherry picked from commit fcace3b9b727e25ffa3f7ad2c96e76b8584a9f3e) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_reg.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index c8647cfa81ba..64cc674b652a 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -1802,7 +1802,7 @@ enum skl_disp_power_wells { #define POST_CURSOR_2(x) ((x) << 6) #define POST_CURSOR_2_MASK (0x3F << 6) #define CURSOR_COEFF(x) ((x) << 0) -#define CURSOR_COEFF_MASK (0x3F << 6) +#define CURSOR_COEFF_MASK (0x3F << 0) #define _CNL_PORT_TX_DW5_GRP_AE 0x162354 #define _CNL_PORT_TX_DW5_GRP_B 0x1623D4 -- cgit v1.2.3-59-g8ed1b From 04941829b0049d2446c7042ab9686dd057d809a6 Mon Sep 17 00:00:00 2001 From: "sagar.a.kamble@intel.com" Date: Tue, 27 Jun 2017 23:09:41 +0530 Subject: drm/i915: Hold RPM wakelock while initializing OA buffer OA buffer initialization involves access to HW registers to set the OA base, head and tail. Ensure device is awake while setting these. With this, all oa.ops are covered under RPM and forcewake wakelock. Cc: Lionel Landwerlin Signed-off-by: Sagar Arun Kamble Reviewed-by: Lionel Landwerlin Signed-off-by: Maarten Lankhorst Link: http://patchwork.freedesktop.org/patch/msgid/1498585181-23048-1-git-send-email-sagar.a.kamble@intel.com Fixes: d79651522e89c ("drm/i915: Enable i915 perf stream for Haswell OA unit") Cc: # v4.11+ (cherry picked from commit 987f8c444aa2c33d98e7030d0c5f0a5325cc84ea) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_perf.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 38c44407bafc..9cd22f83b0cf 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -2067,10 +2067,6 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, return ret; } - ret = alloc_oa_buffer(dev_priv); - if (ret) - goto err_oa_buf_alloc; - /* PRM - observability performance counters: * * OACONTROL, performance counter enable, note: @@ -2086,6 +2082,10 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, intel_runtime_pm_get(dev_priv); intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL); + ret = alloc_oa_buffer(dev_priv); + if (ret) + goto err_oa_buf_alloc; + ret = dev_priv->perf.oa.ops.enable_metric_set(dev_priv); if (ret) goto err_enable; @@ -2097,11 +2097,11 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, return 0; err_enable: - intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); - intel_runtime_pm_put(dev_priv); free_oa_buffer(dev_priv); err_oa_buf_alloc: + intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); + intel_runtime_pm_put(dev_priv); if (stream->ctx) oa_put_render_ctx_id(stream); -- cgit v1.2.3-59-g8ed1b From 3950c95e2c39b998abcc9702005b5ba7c7f70d32 Mon Sep 17 00:00:00 2001 From: "H. Nikolaus Schaller" Date: Mon, 3 Jul 2017 18:37:10 +0200 Subject: power: supply: twl4030-charger: move irq allocation to just before irqs are enabled And initialize workers and notifiers as soon as possible. This avoids a potential race if irqs are enabled and triggered too early before the worker is properly set up. Suggested-by: Grygorii Strashko Signed-off-by: H. Nikolaus Schaller Signed-off-by: Sebastian Reichel --- drivers/power/supply/twl4030_charger.c | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) diff --git a/drivers/power/supply/twl4030_charger.c b/drivers/power/supply/twl4030_charger.c index 3de802f169a1..9fad387e5081 100644 --- a/drivers/power/supply/twl4030_charger.c +++ b/drivers/power/supply/twl4030_charger.c @@ -980,12 +980,27 @@ static int twl4030_bci_probe(struct platform_device *pdev) platform_set_drvdata(pdev, bci); + INIT_WORK(&bci->work, twl4030_bci_usb_work); + INIT_DELAYED_WORK(&bci->current_worker, twl4030_current_worker); + bci->channel_vac = devm_iio_channel_get(&pdev->dev, "vac"); if (IS_ERR(bci->channel_vac)) { bci->channel_vac = NULL; dev_warn(&pdev->dev, "could not request vac iio channel"); } + if (bci->dev->of_node) { + struct device_node *phynode; + + phynode = of_find_compatible_node(bci->dev->of_node->parent, + NULL, "ti,twl4030-usb"); + if (phynode) { + bci->usb_nb.notifier_call = twl4030_bci_usb_ncb; + bci->transceiver = devm_usb_get_phy_by_node( + bci->dev, phynode, &bci->usb_nb); + } + } + bci->ac = devm_power_supply_register(&pdev->dev, &twl4030_bci_ac_desc, NULL); if (IS_ERR(bci->ac)) { @@ -1019,20 +1034,6 @@ static int twl4030_bci_probe(struct platform_device *pdev) return ret; } - INIT_WORK(&bci->work, twl4030_bci_usb_work); - INIT_DELAYED_WORK(&bci->current_worker, twl4030_current_worker); - - bci->usb_nb.notifier_call = twl4030_bci_usb_ncb; - if (bci->dev->of_node) { - struct device_node *phynode; - - phynode = of_find_compatible_node(bci->dev->of_node->parent, - NULL, "ti,twl4030-usb"); - if (phynode) - bci->transceiver = devm_usb_get_phy_by_node( - bci->dev, phynode, &bci->usb_nb); - } - /* Enable interrupts now. */ reg = ~(u32)(TWL4030_ICHGLOW | TWL4030_ICHGEOC | TWL4030_TBATOR2 | TWL4030_TBATOR1 | TWL4030_BATSTS); -- cgit v1.2.3-59-g8ed1b From 7bb5a650f3471e4052e1692b29b0f3d3ca099c47 Mon Sep 17 00:00:00 2001 From: "H. Nikolaus Schaller" Date: Mon, 3 Jul 2017 18:37:11 +0200 Subject: power: supply: twl4030-charger: add deferred probing for phy and iio This fixes an issue if both this twl4030_charger driver and phy-twl4030-usb are compiled as modules and loaded in random order. It has been observed on GTA04 and OpenPandora devices that in worst case the boot process hangs and in best case the AC detection fails with a warning. Therefore we add deferred probing checks for the usb_phy and the iio channel for AC detection. Signed-off-by: H. Nikolaus Schaller Signed-off-by: Sebastian Reichel --- drivers/power/supply/twl4030_charger.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/power/supply/twl4030_charger.c b/drivers/power/supply/twl4030_charger.c index 9fad387e5081..9dff1b4b85fc 100644 --- a/drivers/power/supply/twl4030_charger.c +++ b/drivers/power/supply/twl4030_charger.c @@ -985,8 +985,12 @@ static int twl4030_bci_probe(struct platform_device *pdev) bci->channel_vac = devm_iio_channel_get(&pdev->dev, "vac"); if (IS_ERR(bci->channel_vac)) { + ret = PTR_ERR(bci->channel_vac); + if (ret == -EPROBE_DEFER) + return ret; /* iio not ready */ + dev_warn(&pdev->dev, "could not request vac iio channel (%d)", + ret); bci->channel_vac = NULL; - dev_warn(&pdev->dev, "could not request vac iio channel"); } if (bci->dev->of_node) { @@ -998,6 +1002,14 @@ static int twl4030_bci_probe(struct platform_device *pdev) bci->usb_nb.notifier_call = twl4030_bci_usb_ncb; bci->transceiver = devm_usb_get_phy_by_node( bci->dev, phynode, &bci->usb_nb); + if (IS_ERR(bci->transceiver)) { + ret = PTR_ERR(bci->transceiver); + if (ret == -EPROBE_DEFER) + return ret; /* phy not ready */ + dev_warn(&pdev->dev, "could not request transceiver (%d)", + ret); + bci->transceiver = NULL; + } } } -- cgit v1.2.3-59-g8ed1b From 468138d78510688fb5476f98d23f11ac6a63229a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 2 May 2017 19:52:17 -0400 Subject: binfmt_flat: flat_{get,put}_addr_from_rp() should be able to fail on MMU targets EFAULT is possible here. Make both return 0 or error, passing what used to be the return value of flat_get_addr_from_rp() by reference. Signed-off-by: Al Viro --- arch/arm/include/asm/flat.h | 25 +++++++++++++++++++++--- arch/blackfin/include/asm/flat.h | 25 ++++++++++++++---------- arch/blackfin/kernel/flat.c | 13 ++++++------- arch/c6x/include/asm/flat.h | 15 +++++++++++++-- arch/h8300/include/asm/flat.h | 24 +++++++++++++++++------ arch/m32r/include/asm/flat.h | 19 ++++++++----------- arch/m68k/include/asm/flat.h | 23 +++++++++++++++++++--- arch/microblaze/include/asm/flat.h | 34 ++++++++++++++++----------------- arch/sh/include/asm/flat.h | 15 +++++++++++++-- arch/xtensa/include/asm/flat.h | 15 +++++++++++++-- fs/binfmt_flat.c | 39 +++++++++++++++++++++----------------- include/linux/flat.h | 2 +- 12 files changed, 168 insertions(+), 81 deletions(-) diff --git a/arch/arm/include/asm/flat.h b/arch/arm/include/asm/flat.h index acf1d14b89a6..29d3a1524bce 100644 --- a/arch/arm/include/asm/flat.h +++ b/arch/arm/include/asm/flat.h @@ -5,12 +5,31 @@ #ifndef __ARM_FLAT_H__ #define __ARM_FLAT_H__ +#include + #define flat_argvp_envp_on_stack() 1 #define flat_old_ram_flag(flags) (flags) #define flat_reloc_valid(reloc, size) ((reloc) <= (size)) -#define flat_get_addr_from_rp(rp, relval, flags, persistent) \ - ({ unsigned long __val; __get_user_unaligned(__val, rp); __val; }) -#define flat_put_addr_at_rp(rp, val, relval) __put_user_unaligned(val, rp) + +static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags, + u32 *addr, u32 *persistent) +{ +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + return copy_from_user(addr, rp, 4) ? -EFAULT : 0; +#else + return get_user(*addr, rp); +#endif +} + +static inline int flat_put_addr_at_rp(u32 __user *rp, u32 addr, u32 rel) +{ +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + return copy_to_user(rp, &addr, 4) ? -EFAULT : 0; +#else + return put_user(addr, rp); +#endif +} + #define flat_get_relocate_addr(rel) (rel) #define flat_set_persistent(relval, p) 0 diff --git a/arch/blackfin/include/asm/flat.h b/arch/blackfin/include/asm/flat.h index c1314c56dd18..296d7f56fbfd 100644 --- a/arch/blackfin/include/asm/flat.h +++ b/arch/blackfin/include/asm/flat.h @@ -14,23 +14,28 @@ #define flat_argvp_envp_on_stack() 0 #define flat_old_ram_flag(flags) (flags) -extern unsigned long bfin_get_addr_from_rp (unsigned long *ptr, - unsigned long relval, - unsigned long flags, - unsigned long *persistent); +extern unsigned long bfin_get_addr_from_rp (u32 *ptr, u32 relval, + u32 flags, u32 *persistent); -extern void bfin_put_addr_at_rp(unsigned long *ptr, unsigned long addr, - unsigned long relval); +extern void bfin_put_addr_at_rp(u32 *ptr, u32 addr, u32 relval); /* The amount by which a relocation can exceed the program image limits without being regarded as an error. */ #define flat_reloc_valid(reloc, size) ((reloc) <= (size)) -#define flat_get_addr_from_rp(rp, relval, flags, persistent) \ - bfin_get_addr_from_rp(rp, relval, flags, persistent) -#define flat_put_addr_at_rp(rp, val, relval) \ - bfin_put_addr_at_rp(rp, val, relval) +static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags, + u32 *addr, u32 *persistent) +{ + *addr = bfin_get_addr_from_rp(rp, relval, flags, persistent); + return 0; +} + +static inline int flat_put_addr_at_rp(u32 __user *rp, u32 val, u32 relval) +{ + bfin_put_addr_at_rp(rp, val, relval); + return 0; +} /* Convert a relocation entry into an address. */ static inline unsigned long diff --git a/arch/blackfin/kernel/flat.c b/arch/blackfin/kernel/flat.c index b5b658449616..d29ab6a2e909 100644 --- a/arch/blackfin/kernel/flat.c +++ b/arch/blackfin/kernel/flat.c @@ -13,14 +13,14 @@ #define FLAT_BFIN_RELOC_TYPE_16H_BIT 1 #define FLAT_BFIN_RELOC_TYPE_32_BIT 2 -unsigned long bfin_get_addr_from_rp(unsigned long *ptr, - unsigned long relval, - unsigned long flags, - unsigned long *persistent) +unsigned long bfin_get_addr_from_rp(u32 *ptr, + u32 relval, + u32 flags, + u32 *persistent) { unsigned short *usptr = (unsigned short *)ptr; int type = (relval >> 26) & 7; - unsigned long val; + u32 val; switch (type) { case FLAT_BFIN_RELOC_TYPE_16_BIT: @@ -59,8 +59,7 @@ EXPORT_SYMBOL(bfin_get_addr_from_rp); * Insert the address ADDR into the symbol reference at RP; * RELVAL is the raw relocation-table entry from which RP is derived */ -void bfin_put_addr_at_rp(unsigned long *ptr, unsigned long addr, - unsigned long relval) +void bfin_put_addr_at_rp(u32 *ptr, u32 addr, u32 relval) { unsigned short *usptr = (unsigned short *)ptr; int type = (relval >> 26) & 7; diff --git a/arch/c6x/include/asm/flat.h b/arch/c6x/include/asm/flat.h index a1858bd5f6c8..6f1feb00bd52 100644 --- a/arch/c6x/include/asm/flat.h +++ b/arch/c6x/include/asm/flat.h @@ -1,11 +1,22 @@ #ifndef __ASM_C6X_FLAT_H #define __ASM_C6X_FLAT_H +#include + #define flat_argvp_envp_on_stack() 0 #define flat_old_ram_flag(flags) (flags) #define flat_reloc_valid(reloc, size) ((reloc) <= (size)) -#define flat_get_addr_from_rp(rp, relval, flags, p) get_unaligned(rp) -#define flat_put_addr_at_rp(rp, val, relval) put_unaligned(val, rp) +static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags, + u32 *addr, u32 *persistent) +{ + *addr = get_unaligned((__force u32 *)rp); + return 0; +} +static inline int flat_put_addr_at_rp(u32 __user *rp, u32 addr, u32 rel) +{ + put_unaligned(addr, (__force u32 *)rp); + return 0; +} #define flat_get_relocate_addr(rel) (rel) #define flat_set_persistent(relval, p) 0 diff --git a/arch/h8300/include/asm/flat.h b/arch/h8300/include/asm/flat.h index a4898eccf2bf..18d024251738 100644 --- a/arch/h8300/include/asm/flat.h +++ b/arch/h8300/include/asm/flat.h @@ -5,6 +5,8 @@ #ifndef __H8300_FLAT_H__ #define __H8300_FLAT_H__ +#include + #define flat_argvp_envp_on_stack() 1 #define flat_old_ram_flag(flags) 1 #define flat_reloc_valid(reloc, size) ((reloc) <= (size)) @@ -18,11 +20,21 @@ */ #define flat_get_relocate_addr(rel) (rel & ~0x00000001) -#define flat_get_addr_from_rp(rp, relval, flags, persistent) \ - ({(void)persistent; \ - get_unaligned(rp) & (((flags) & FLAT_FLAG_GOTPIC) ? \ - 0xffffffff : 0x00ffffff); }) -#define flat_put_addr_at_rp(rp, addr, rel) \ - put_unaligned(((*(char *)(rp)) << 24) | ((addr) & 0x00ffffff), (rp)) +static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags, + u32 *addr, u32 *persistent) +{ + u32 val = get_unaligned((__force u32 *)rp); + if (!(flags & FLAT_FLAG_GOTPIC) + val &= 0x00ffffff; + *addr = val; + return 0; +} + +static inline int flat_put_addr_at_rp(u32 __user *rp, u32 addr, u32 rel) +{ + u32 *p = (__force u32 *)rp; + put_unaligned((addr & 0x00ffffff) | (*(char *)p << 24), p); + return 0; +} #endif /* __H8300_FLAT_H__ */ diff --git a/arch/m32r/include/asm/flat.h b/arch/m32r/include/asm/flat.h index 5d711c4688fb..455ce7ddbf14 100644 --- a/arch/m32r/include/asm/flat.h +++ b/arch/m32r/include/asm/flat.h @@ -17,11 +17,6 @@ #define flat_set_persistent(relval, p) 0 #define flat_reloc_valid(reloc, size) \ (((reloc) - textlen_for_m32r_lo16_data) <= (size)) -#define flat_get_addr_from_rp(rp, relval, flags, persistent) \ - m32r_flat_get_addr_from_rp(rp, relval, (text_len) ) - -#define flat_put_addr_at_rp(rp, addr, relval) \ - m32r_flat_put_addr_at_rp(rp, addr, relval) /* Convert a relocation entry into an address. */ static inline unsigned long @@ -57,9 +52,9 @@ flat_get_relocate_addr (unsigned long relval) static unsigned long textlen_for_m32r_lo16_data = 0; -static inline unsigned long m32r_flat_get_addr_from_rp (unsigned long *rp, - unsigned long relval, - unsigned long textlen) +static inline unsigned long m32r_flat_get_addr_from_rp (u32 *rp, + u32 relval, + u32 textlen) { unsigned int reloc = flat_m32r_get_reloc_type (relval); textlen_for_m32r_lo16_data = 0; @@ -100,9 +95,7 @@ static inline unsigned long m32r_flat_get_addr_from_rp (unsigned long *rp, return ~0; /* bogus value */ } -static inline void m32r_flat_put_addr_at_rp (unsigned long *rp, - unsigned long addr, - unsigned long relval) +static inline void flat_put_addr_at_rp(u32 *rp, u32 addr, u32 relval) { unsigned int reloc = flat_m32r_get_reloc_type (relval); if (reloc & 0xf0) { @@ -142,4 +135,8 @@ static inline void m32r_flat_put_addr_at_rp (unsigned long *rp, } } +// kludge - text_len is a local variable in the only user. +#define flat_get_addr_from_rp(rp, relval, flags, addr, persistent) \ + (m32r_flat_get_addr_from_rp(rp, relval, text_len), 0) + #endif /* __ASM_M32R_FLAT_H */ diff --git a/arch/m68k/include/asm/flat.h b/arch/m68k/include/asm/flat.h index 00c392b0cabd..48b62790fe70 100644 --- a/arch/m68k/include/asm/flat.h +++ b/arch/m68k/include/asm/flat.h @@ -5,12 +5,29 @@ #ifndef __M68KNOMMU_FLAT_H__ #define __M68KNOMMU_FLAT_H__ +#include + #define flat_argvp_envp_on_stack() 1 #define flat_old_ram_flag(flags) (flags) #define flat_reloc_valid(reloc, size) ((reloc) <= (size)) -#define flat_get_addr_from_rp(rp, relval, flags, p) \ - ({ unsigned long __val; __get_user_unaligned(__val, rp); __val; }) -#define flat_put_addr_at_rp(rp, val, relval) __put_user_unaligned(val, rp) +static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags, + u32 *addr, u32 *persistent) +{ +#ifdef CONFIG_CPU_HAS_NO_UNALIGNED + return copy_from_user(addr, rp, 4) ? -EFAULT : 0; +#else + return get_user(*addr, rp); +#endif +} + +static inline int flat_put_addr_at_rp(u32 __user *rp, u32 addr, u32 rel) +{ +#ifdef CONFIG_CPU_HAS_NO_UNALIGNED + return copy_to_user(rp, &addr, 4) ? -EFAULT : 0; +#else + return put_user(addr, rp); +#endif +} #define flat_get_relocate_addr(rel) (rel) static inline int flat_set_persistent(unsigned long relval, diff --git a/arch/microblaze/include/asm/flat.h b/arch/microblaze/include/asm/flat.h index 6847c1512c7b..f23c3d266bae 100644 --- a/arch/microblaze/include/asm/flat.h +++ b/arch/microblaze/include/asm/flat.h @@ -32,29 +32,27 @@ * reference */ -static inline unsigned long -flat_get_addr_from_rp(unsigned long *rp, unsigned long relval, - unsigned long flags, unsigned long *persistent) +static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags, + u32 *addr, u32 *persistent) { - unsigned long addr; - (void)flags; + u32 *p = (__force u32 *)rp; /* Is it a split 64/32 reference? */ if (relval & 0x80000000) { /* Grab the two halves of the reference */ - unsigned long val_hi, val_lo; + u32 val_hi, val_lo; - val_hi = get_unaligned(rp); - val_lo = get_unaligned(rp+1); + val_hi = get_unaligned(p); + val_lo = get_unaligned(p+1); /* Crack the address out */ - addr = ((val_hi & 0xffff) << 16) + (val_lo & 0xffff); + *addr = ((val_hi & 0xffff) << 16) + (val_lo & 0xffff); } else { /* Get the address straight out */ - addr = get_unaligned(rp); + *addr = get_unaligned(p); } - return addr; + return 0; } /* @@ -63,25 +61,27 @@ flat_get_addr_from_rp(unsigned long *rp, unsigned long relval, */ static inline void -flat_put_addr_at_rp(unsigned long *rp, unsigned long addr, unsigned long relval) +flat_put_addr_at_rp(u32 __user *rp, u32 addr, u32 relval) { + u32 *p = (__force u32 *)rp; /* Is this a split 64/32 reloc? */ if (relval & 0x80000000) { /* Get the two "halves" */ - unsigned long val_hi = get_unaligned(rp); - unsigned long val_lo = get_unaligned(rp + 1); + unsigned long val_hi = get_unaligned(p); + unsigned long val_lo = get_unaligned(p + 1); /* insert the address */ val_hi = (val_hi & 0xffff0000) | addr >> 16; val_lo = (val_lo & 0xffff0000) | (addr & 0xffff); /* store the two halves back into memory */ - put_unaligned(val_hi, rp); - put_unaligned(val_lo, rp+1); + put_unaligned(val_hi, p); + put_unaligned(val_lo, p+1); } else { /* Put it straight in, no messing around */ - put_unaligned(addr, rp); + put_unaligned(addr, p); } + return 0; } #define flat_get_relocate_addr(rel) (rel & 0x7fffffff) diff --git a/arch/sh/include/asm/flat.h b/arch/sh/include/asm/flat.h index 5d84df5e27f6..275fcae23539 100644 --- a/arch/sh/include/asm/flat.h +++ b/arch/sh/include/asm/flat.h @@ -12,11 +12,22 @@ #ifndef __ASM_SH_FLAT_H #define __ASM_SH_FLAT_H +#include + #define flat_argvp_envp_on_stack() 0 #define flat_old_ram_flag(flags) (flags) #define flat_reloc_valid(reloc, size) ((reloc) <= (size)) -#define flat_get_addr_from_rp(rp, relval, flags, p) get_unaligned(rp) -#define flat_put_addr_at_rp(rp, val, relval) put_unaligned(val,rp) +static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags, + u32 *addr, u32 *persistent) +{ + *addr = get_unaligned((__force u32 *)rp); + return 0; +} +static inline int flat_put_addr_at_rp(u32 __user *rp, u32 addr, u32 rel) +{ + put_unaligned(addr, (__force u32 *)rp); + return 0; +} #define flat_get_relocate_addr(rel) (rel) #define flat_set_persistent(relval, p) ({ (void)p; 0; }) diff --git a/arch/xtensa/include/asm/flat.h b/arch/xtensa/include/asm/flat.h index 94c44abf15e4..60e0d6a45795 100644 --- a/arch/xtensa/include/asm/flat.h +++ b/arch/xtensa/include/asm/flat.h @@ -1,11 +1,22 @@ #ifndef __ASM_XTENSA_FLAT_H #define __ASM_XTENSA_FLAT_H +#include + #define flat_argvp_envp_on_stack() 0 #define flat_old_ram_flag(flags) (flags) #define flat_reloc_valid(reloc, size) ((reloc) <= (size)) -#define flat_get_addr_from_rp(rp, relval, flags, p) get_unaligned(rp) -#define flat_put_addr_at_rp(rp, val, relval ) put_unaligned(val, rp) +static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags, + u32 *addr, u32 *persistent) +{ + *addr = get_unaligned((__force u32 *)rp); + return 0; +} +static inline int flat_put_addr_at_rp(u32 __user *rp, u32 addr, u32 rel) +{ + put_unaligned(addr, (__force u32 *)rp); + return 0; +} #define flat_get_relocate_addr(rel) (rel) #define flat_set_persistent(relval, p) 0 diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 2edcefc0a294..69ec23daa25e 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -422,9 +422,9 @@ static int load_flat_file(struct linux_binprm *bprm, { struct flat_hdr *hdr; unsigned long textpos, datapos, realdatastart; - unsigned long text_len, data_len, bss_len, stack_len, full_data, flags; + u32 text_len, data_len, bss_len, stack_len, full_data, flags; unsigned long len, memp, memp_size, extra, rlim; - unsigned long __user *reloc, *rp; + u32 __user *reloc, *rp; struct inode *inode; int i, rev, relocs; loff_t fpos; @@ -596,13 +596,13 @@ static int load_flat_file(struct linux_binprm *bprm, goto err; } - reloc = (unsigned long __user *) + reloc = (u32 __user *) (datapos + (ntohl(hdr->reloc_start) - text_len)); memp = realdatastart; memp_size = len; } else { - len = text_len + data_len + extra + MAX_SHARED_LIBS * sizeof(unsigned long); + len = text_len + data_len + extra + MAX_SHARED_LIBS * sizeof(u32); len = PAGE_ALIGN(len); textpos = vm_mmap(NULL, 0, len, PROT_READ | PROT_EXEC | PROT_WRITE, MAP_PRIVATE, 0); @@ -618,10 +618,10 @@ static int load_flat_file(struct linux_binprm *bprm, realdatastart = textpos + ntohl(hdr->data_start); datapos = ALIGN(realdatastart + - MAX_SHARED_LIBS * sizeof(unsigned long), + MAX_SHARED_LIBS * sizeof(u32), FLAT_DATA_ALIGN); - reloc = (unsigned long __user *) + reloc = (u32 __user *) (datapos + (ntohl(hdr->reloc_start) - text_len)); memp = textpos; memp_size = len; @@ -694,7 +694,7 @@ static int load_flat_file(struct linux_binprm *bprm, ret = result; pr_err("Unable to read code+data+bss, errno %d\n", ret); vm_munmap(textpos, text_len + data_len + extra + - MAX_SHARED_LIBS * sizeof(unsigned long)); + MAX_SHARED_LIBS * sizeof(u32)); goto err; } } @@ -754,8 +754,8 @@ static int load_flat_file(struct linux_binprm *bprm, * image. */ if (flags & FLAT_FLAG_GOTPIC) { - for (rp = (unsigned long __user *)datapos; ; rp++) { - unsigned long addr, rp_val; + for (rp = (u32 __user *)datapos; ; rp++) { + u32 addr, rp_val; if (get_user(rp_val, rp)) return -EFAULT; if (rp_val == 0xffffffff) @@ -784,9 +784,9 @@ static int load_flat_file(struct linux_binprm *bprm, * __start to address 4 so that is okay). */ if (rev > OLD_FLAT_VERSION) { - unsigned long __maybe_unused persistent = 0; + u32 __maybe_unused persistent = 0; for (i = 0; i < relocs; i++) { - unsigned long addr, relval; + u32 addr, relval; /* * Get the address of the pointer to be @@ -799,15 +799,18 @@ static int load_flat_file(struct linux_binprm *bprm, if (flat_set_persistent(relval, &persistent)) continue; addr = flat_get_relocate_addr(relval); - rp = (unsigned long __user *)calc_reloc(addr, libinfo, id, 1); - if (rp == (unsigned long __user *)RELOC_FAILED) { + rp = (u32 __user *)calc_reloc(addr, libinfo, id, 1); + if (rp == (u32 __user *)RELOC_FAILED) { ret = -ENOEXEC; goto err; } /* Get the pointer's value. */ - addr = flat_get_addr_from_rp(rp, relval, flags, - &persistent); + ret = flat_get_addr_from_rp(rp, relval, flags, + &addr, &persistent); + if (unlikely(ret)) + goto err; + if (addr != 0) { /* * Do the relocation. PIC relocs in the data section are @@ -822,12 +825,14 @@ static int load_flat_file(struct linux_binprm *bprm, } /* Write back the relocated pointer. */ - flat_put_addr_at_rp(rp, addr, relval); + ret = flat_put_addr_at_rp(rp, addr, relval); + if (unlikely(ret)) + goto err; } } } else { for (i = 0; i < relocs; i++) { - unsigned long relval; + u32 relval; if (get_user(relval, reloc + i)) return -EFAULT; relval = ntohl(relval); diff --git a/include/linux/flat.h b/include/linux/flat.h index 2c1eb15c4ba4..7d542dfd0def 100644 --- a/include/linux/flat.h +++ b/include/linux/flat.h @@ -9,8 +9,8 @@ #ifndef _LINUX_FLAT_H #define _LINUX_FLAT_H -#include #include +#include /* * While it would be nice to keep this header clean, users of older -- cgit v1.2.3-59-g8ed1b From 3170d8d226c2053355f3946b4b5ded4c006fe6d4 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 2 May 2017 20:06:33 -0400 Subject: kill {__,}{get,put}_user_unaligned() no users left Signed-off-by: Al Viro --- arch/arm/include/asm/uaccess.h | 7 - arch/arm64/include/asm/uaccess.h | 4 - arch/ia64/include/asm/uaccess.h | 36 ----- arch/m68k/include/asm/uaccess.h | 7 - arch/mips/include/asm/uaccess.h | 277 -------------------------------- arch/parisc/include/asm/uaccess.h | 1 - arch/powerpc/include/asm/uaccess.h | 3 - arch/s390/include/asm/uaccess.h | 3 - arch/sparc/include/asm/uaccess_64.h | 1 - arch/tile/include/asm/uaccess.h | 1 - arch/x86/include/asm/uaccess.h | 3 - include/asm-generic/uaccess-unaligned.h | 26 --- 12 files changed, 369 deletions(-) delete mode 100644 include/asm-generic/uaccess-unaligned.h diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 2577405d082d..0726091a8964 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -17,13 +17,6 @@ #include #include -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS -#include -#else -#define __get_user_unaligned __get_user -#define __put_user_unaligned __put_user -#endif - #include /* diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 7b8a04789cef..f2b465e129de 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -254,8 +254,6 @@ do { \ (void)0; \ }) -#define __get_user_unaligned __get_user - #define get_user(x, ptr) \ ({ \ __typeof__(*(ptr)) __user *__p = (ptr); \ @@ -320,8 +318,6 @@ do { \ (void)0; \ }) -#define __put_user_unaligned __put_user - #define put_user(x, ptr) \ ({ \ __typeof__(*(ptr)) __user *__p = (ptr); \ diff --git a/arch/ia64/include/asm/uaccess.h b/arch/ia64/include/asm/uaccess.h index 82a7646c4416..a217bcfe6700 100644 --- a/arch/ia64/include/asm/uaccess.h +++ b/arch/ia64/include/asm/uaccess.h @@ -87,42 +87,6 @@ static inline int __access_ok(const void __user *p, unsigned long size) #define __put_user(x, ptr) __put_user_nocheck((__typeof__(*(ptr))) (x), (ptr), sizeof(*(ptr))) #define __get_user(x, ptr) __get_user_nocheck((x), (ptr), sizeof(*(ptr))) -extern long __put_user_unaligned_unknown (void); - -#define __put_user_unaligned(x, ptr) \ -({ \ - long __ret; \ - switch (sizeof(*(ptr))) { \ - case 1: __ret = __put_user((x), (ptr)); break; \ - case 2: __ret = (__put_user((x), (u8 __user *)(ptr))) \ - | (__put_user((x) >> 8, ((u8 __user *)(ptr) + 1))); break; \ - case 4: __ret = (__put_user((x), (u16 __user *)(ptr))) \ - | (__put_user((x) >> 16, ((u16 __user *)(ptr) + 1))); break; \ - case 8: __ret = (__put_user((x), (u32 __user *)(ptr))) \ - | (__put_user((x) >> 32, ((u32 __user *)(ptr) + 1))); break; \ - default: __ret = __put_user_unaligned_unknown(); \ - } \ - __ret; \ -}) - -extern long __get_user_unaligned_unknown (void); - -#define __get_user_unaligned(x, ptr) \ -({ \ - long __ret; \ - switch (sizeof(*(ptr))) { \ - case 1: __ret = __get_user((x), (ptr)); break; \ - case 2: __ret = (__get_user((x), (u8 __user *)(ptr))) \ - | (__get_user((x) >> 8, ((u8 __user *)(ptr) + 1))); break; \ - case 4: __ret = (__get_user((x), (u16 __user *)(ptr))) \ - | (__get_user((x) >> 16, ((u16 __user *)(ptr) + 1))); break; \ - case 8: __ret = (__get_user((x), (u32 __user *)(ptr))) \ - | (__get_user((x) >> 32, ((u32 __user *)(ptr) + 1))); break; \ - default: __ret = __get_user_unaligned_unknown(); \ - } \ - __ret; \ -}) - #ifdef ASM_SUPPORTED struct __large_struct { unsigned long buf[100]; }; # define __m(x) (*(struct __large_struct __user *)(x)) diff --git a/arch/m68k/include/asm/uaccess.h b/arch/m68k/include/asm/uaccess.h index 67b3481d6020..63ba18e4c9a2 100644 --- a/arch/m68k/include/asm/uaccess.h +++ b/arch/m68k/include/asm/uaccess.h @@ -3,11 +3,4 @@ #else #include #endif - #include -#ifdef CONFIG_CPU_HAS_NO_UNALIGNED -#include -#else -#define __get_user_unaligned(x, ptr) __get_user((x), (ptr)) -#define __put_user_unaligned(x, ptr) __put_user((x), (ptr)) -#endif diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h index 99e629a590a5..c5fc42429ce8 100644 --- a/arch/mips/include/asm/uaccess.h +++ b/arch/mips/include/asm/uaccess.h @@ -496,283 +496,6 @@ do { \ extern void __put_user_unknown(void); -/* - * ul{b,h,w} are macros and there are no equivalent macros for EVA. - * EVA unaligned access is handled in the ADE exception handler. - */ -#ifndef CONFIG_EVA -/* - * put_user_unaligned: - Write a simple value into user space. - * @x: Value to copy to user space. - * @ptr: Destination address, in user space. - * - * Context: User context only. This function may sleep if pagefaults are - * enabled. - * - * This macro copies a single simple value from kernel space to user - * space. It supports simple types like char and int, but not larger - * data types like structures or arrays. - * - * @ptr must have pointer-to-simple-variable type, and @x must be assignable - * to the result of dereferencing @ptr. - * - * Returns zero on success, or -EFAULT on error. - */ -#define put_user_unaligned(x,ptr) \ - __put_user_unaligned_check((x),(ptr),sizeof(*(ptr))) - -/* - * get_user_unaligned: - Get a simple variable from user space. - * @x: Variable to store result. - * @ptr: Source address, in user space. - * - * Context: User context only. This function may sleep if pagefaults are - * enabled. - * - * This macro copies a single simple variable from user space to kernel - * space. It supports simple types like char and int, but not larger - * data types like structures or arrays. - * - * @ptr must have pointer-to-simple-variable type, and the result of - * dereferencing @ptr must be assignable to @x without a cast. - * - * Returns zero on success, or -EFAULT on error. - * On error, the variable @x is set to zero. - */ -#define get_user_unaligned(x,ptr) \ - __get_user_unaligned_check((x),(ptr),sizeof(*(ptr))) - -/* - * __put_user_unaligned: - Write a simple value into user space, with less checking. - * @x: Value to copy to user space. - * @ptr: Destination address, in user space. - * - * Context: User context only. This function may sleep if pagefaults are - * enabled. - * - * This macro copies a single simple value from kernel space to user - * space. It supports simple types like char and int, but not larger - * data types like structures or arrays. - * - * @ptr must have pointer-to-simple-variable type, and @x must be assignable - * to the result of dereferencing @ptr. - * - * Caller must check the pointer with access_ok() before calling this - * function. - * - * Returns zero on success, or -EFAULT on error. - */ -#define __put_user_unaligned(x,ptr) \ - __put_user_unaligned_nocheck((x),(ptr),sizeof(*(ptr))) - -/* - * __get_user_unaligned: - Get a simple variable from user space, with less checking. - * @x: Variable to store result. - * @ptr: Source address, in user space. - * - * Context: User context only. This function may sleep if pagefaults are - * enabled. - * - * This macro copies a single simple variable from user space to kernel - * space. It supports simple types like char and int, but not larger - * data types like structures or arrays. - * - * @ptr must have pointer-to-simple-variable type, and the result of - * dereferencing @ptr must be assignable to @x without a cast. - * - * Caller must check the pointer with access_ok() before calling this - * function. - * - * Returns zero on success, or -EFAULT on error. - * On error, the variable @x is set to zero. - */ -#define __get_user_unaligned(x,ptr) \ - __get_user_unaligned_nocheck((x),(ptr),sizeof(*(ptr))) - -/* - * Yuck. We need two variants, one for 64bit operation and one - * for 32 bit mode and old iron. - */ -#ifdef CONFIG_32BIT -#define __GET_USER_UNALIGNED_DW(val, ptr) \ - __get_user_unaligned_asm_ll32(val, ptr) -#endif -#ifdef CONFIG_64BIT -#define __GET_USER_UNALIGNED_DW(val, ptr) \ - __get_user_unaligned_asm(val, "uld", ptr) -#endif - -extern void __get_user_unaligned_unknown(void); - -#define __get_user_unaligned_common(val, size, ptr) \ -do { \ - switch (size) { \ - case 1: __get_data_asm(val, "lb", ptr); break; \ - case 2: __get_data_unaligned_asm(val, "ulh", ptr); break; \ - case 4: __get_data_unaligned_asm(val, "ulw", ptr); break; \ - case 8: __GET_USER_UNALIGNED_DW(val, ptr); break; \ - default: __get_user_unaligned_unknown(); break; \ - } \ -} while (0) - -#define __get_user_unaligned_nocheck(x,ptr,size) \ -({ \ - int __gu_err; \ - \ - __get_user_unaligned_common((x), size, ptr); \ - __gu_err; \ -}) - -#define __get_user_unaligned_check(x,ptr,size) \ -({ \ - int __gu_err = -EFAULT; \ - const __typeof__(*(ptr)) __user * __gu_ptr = (ptr); \ - \ - if (likely(access_ok(VERIFY_READ, __gu_ptr, size))) \ - __get_user_unaligned_common((x), size, __gu_ptr); \ - \ - __gu_err; \ -}) - -#define __get_data_unaligned_asm(val, insn, addr) \ -{ \ - long __gu_tmp; \ - \ - __asm__ __volatile__( \ - "1: " insn " %1, %3 \n" \ - "2: \n" \ - " .insn \n" \ - " .section .fixup,\"ax\" \n" \ - "3: li %0, %4 \n" \ - " move %1, $0 \n" \ - " j 2b \n" \ - " .previous \n" \ - " .section __ex_table,\"a\" \n" \ - " "__UA_ADDR "\t1b, 3b \n" \ - " "__UA_ADDR "\t1b + 4, 3b \n" \ - " .previous \n" \ - : "=r" (__gu_err), "=r" (__gu_tmp) \ - : "0" (0), "o" (__m(addr)), "i" (-EFAULT)); \ - \ - (val) = (__typeof__(*(addr))) __gu_tmp; \ -} - -/* - * Get a long long 64 using 32 bit registers. - */ -#define __get_user_unaligned_asm_ll32(val, addr) \ -{ \ - unsigned long long __gu_tmp; \ - \ - __asm__ __volatile__( \ - "1: ulw %1, (%3) \n" \ - "2: ulw %D1, 4(%3) \n" \ - " move %0, $0 \n" \ - "3: \n" \ - " .insn \n" \ - " .section .fixup,\"ax\" \n" \ - "4: li %0, %4 \n" \ - " move %1, $0 \n" \ - " move %D1, $0 \n" \ - " j 3b \n" \ - " .previous \n" \ - " .section __ex_table,\"a\" \n" \ - " " __UA_ADDR " 1b, 4b \n" \ - " " __UA_ADDR " 1b + 4, 4b \n" \ - " " __UA_ADDR " 2b, 4b \n" \ - " " __UA_ADDR " 2b + 4, 4b \n" \ - " .previous \n" \ - : "=r" (__gu_err), "=&r" (__gu_tmp) \ - : "0" (0), "r" (addr), "i" (-EFAULT)); \ - (val) = (__typeof__(*(addr))) __gu_tmp; \ -} - -/* - * Yuck. We need two variants, one for 64bit operation and one - * for 32 bit mode and old iron. - */ -#ifdef CONFIG_32BIT -#define __PUT_USER_UNALIGNED_DW(ptr) __put_user_unaligned_asm_ll32(ptr) -#endif -#ifdef CONFIG_64BIT -#define __PUT_USER_UNALIGNED_DW(ptr) __put_user_unaligned_asm("usd", ptr) -#endif - -#define __put_user_unaligned_common(ptr, size) \ -do { \ - switch (size) { \ - case 1: __put_data_asm("sb", ptr); break; \ - case 2: __put_user_unaligned_asm("ush", ptr); break; \ - case 4: __put_user_unaligned_asm("usw", ptr); break; \ - case 8: __PUT_USER_UNALIGNED_DW(ptr); break; \ - default: __put_user_unaligned_unknown(); break; \ -} while (0) - -#define __put_user_unaligned_nocheck(x,ptr,size) \ -({ \ - __typeof__(*(ptr)) __pu_val; \ - int __pu_err = 0; \ - \ - __pu_val = (x); \ - __put_user_unaligned_common(ptr, size); \ - __pu_err; \ -}) - -#define __put_user_unaligned_check(x,ptr,size) \ -({ \ - __typeof__(*(ptr)) __user *__pu_addr = (ptr); \ - __typeof__(*(ptr)) __pu_val = (x); \ - int __pu_err = -EFAULT; \ - \ - if (likely(access_ok(VERIFY_WRITE, __pu_addr, size))) \ - __put_user_unaligned_common(__pu_addr, size); \ - \ - __pu_err; \ -}) - -#define __put_user_unaligned_asm(insn, ptr) \ -{ \ - __asm__ __volatile__( \ - "1: " insn " %z2, %3 # __put_user_unaligned_asm\n" \ - "2: \n" \ - " .insn \n" \ - " .section .fixup,\"ax\" \n" \ - "3: li %0, %4 \n" \ - " j 2b \n" \ - " .previous \n" \ - " .section __ex_table,\"a\" \n" \ - " " __UA_ADDR " 1b, 3b \n" \ - " .previous \n" \ - : "=r" (__pu_err) \ - : "0" (0), "Jr" (__pu_val), "o" (__m(ptr)), \ - "i" (-EFAULT)); \ -} - -#define __put_user_unaligned_asm_ll32(ptr) \ -{ \ - __asm__ __volatile__( \ - "1: sw %2, (%3) # __put_user_unaligned_asm_ll32 \n" \ - "2: sw %D2, 4(%3) \n" \ - "3: \n" \ - " .insn \n" \ - " .section .fixup,\"ax\" \n" \ - "4: li %0, %4 \n" \ - " j 3b \n" \ - " .previous \n" \ - " .section __ex_table,\"a\" \n" \ - " " __UA_ADDR " 1b, 4b \n" \ - " " __UA_ADDR " 1b + 4, 4b \n" \ - " " __UA_ADDR " 2b, 4b \n" \ - " " __UA_ADDR " 2b + 4, 4b \n" \ - " .previous" \ - : "=r" (__pu_err) \ - : "0" (0), "r" (__pu_val), "r" (ptr), \ - "i" (-EFAULT)); \ -} - -extern void __put_user_unaligned_unknown(void); -#endif - /* * We're generating jump to subroutines which will be outside the range of * jump instructions diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 6b113f39f30c..d24091e1907a 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -6,7 +6,6 @@ */ #include #include -#include #include #include diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 5c0d8a8cdae5..9e7b08bbde5b 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -90,9 +90,6 @@ #define __put_user_inatomic(x, ptr) \ __put_user_nosleep((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr))) -#define __get_user_unaligned __get_user -#define __put_user_unaligned __put_user - extern long __put_user_bad(void); /* diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index 78f3f093d143..fad9df965ec2 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -249,9 +249,6 @@ int __put_user_bad(void) __attribute__((noreturn)); int __get_user_bad(void) __attribute__((noreturn)); -#define __put_user_unaligned __put_user -#define __get_user_unaligned __get_user - unsigned long __must_check raw_copy_in_user(void __user *to, const void __user *from, unsigned long n); diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h index 6096d671aa63..b5f976ee7510 100644 --- a/arch/sparc/include/asm/uaccess_64.h +++ b/arch/sparc/include/asm/uaccess_64.h @@ -9,7 +9,6 @@ #include #include #include -#include #include #include diff --git a/arch/tile/include/asm/uaccess.h b/arch/tile/include/asm/uaccess.h index a803f6bb4d92..7f777411d1d6 100644 --- a/arch/tile/include/asm/uaccess.h +++ b/arch/tile/include/asm/uaccess.h @@ -19,7 +19,6 @@ * User space memory access functions */ #include -#include #include #include diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 68766b276d9e..fd91722315c8 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -535,9 +535,6 @@ struct __large_struct { unsigned long buf[100]; }; #define __put_user(x, ptr) \ __put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr))) -#define __get_user_unaligned __get_user -#define __put_user_unaligned __put_user - /* * {get|put}_user_try and catch * diff --git a/include/asm-generic/uaccess-unaligned.h b/include/asm-generic/uaccess-unaligned.h deleted file mode 100644 index 67deb898f0c5..000000000000 --- a/include/asm-generic/uaccess-unaligned.h +++ /dev/null @@ -1,26 +0,0 @@ -#ifndef __ASM_GENERIC_UACCESS_UNALIGNED_H -#define __ASM_GENERIC_UACCESS_UNALIGNED_H - -/* - * This macro should be used instead of __get_user() when accessing - * values at locations that are not known to be aligned. - */ -#define __get_user_unaligned(x, ptr) \ -({ \ - __typeof__ (*(ptr)) __x; \ - __copy_from_user(&__x, (ptr), sizeof(*(ptr))) ? -EFAULT : 0; \ - (x) = __x; \ -}) - - -/* - * This macro should be used instead of __put_user() when accessing - * values at locations that are not known to be aligned. - */ -#define __put_user_unaligned(x, ptr) \ -({ \ - __typeof__ (*(ptr)) __x = (x); \ - __copy_to_user((ptr), &__x, sizeof(*(ptr))) ? -EFAULT : 0; \ -}) - -#endif /* __ASM_GENERIC_UACCESS_UNALIGNED_H */ -- cgit v1.2.3-59-g8ed1b From 526c9e971f4fdec4cab41b531405e211afb1d82a Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Tue, 4 Jul 2017 17:47:22 +0200 Subject: video: fbdev: fsl-diu-fb: constify mfb_template and fsl_diu_match. File size before: text data bss dec hex filename 2469 1552 24 4045 fcd drivers/video/fbdev/fsl-diu-fb.o File size after adding 'const': text data bss dec hex filename 3821 200 24 4045 fcd drivers/video/fbdev/fsl-diu-fb.o Signed-off-by: Arvind Yadav Cc: Timur Tabi Signed-off-by: Bartlomiej Zolnierkiewicz --- drivers/video/fbdev/fsl-diu-fb.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/video/fbdev/fsl-diu-fb.c b/drivers/video/fbdev/fsl-diu-fb.c index ca3d6b366471..25abbcf38913 100644 --- a/drivers/video/fbdev/fsl-diu-fb.c +++ b/drivers/video/fbdev/fsl-diu-fb.c @@ -388,7 +388,7 @@ struct fsl_diu_data { /* Determine the DMA address of a member of the fsl_diu_data structure */ #define DMA_ADDR(p, f) ((p)->dma_addr + offsetof(struct fsl_diu_data, f)) -static struct mfb_info mfb_template[] = { +static const struct mfb_info mfb_template[] = { { .index = PLANE0, .id = "Panel0", @@ -1868,7 +1868,7 @@ static int __init fsl_diu_setup(char *options) } #endif -static struct of_device_id fsl_diu_match[] = { +static const struct of_device_id fsl_diu_match[] = { #ifdef CONFIG_PPC_MPC512x { .compatible = "fsl,mpc5121-diu", -- cgit v1.2.3-59-g8ed1b From 6af574e826740bf17663b48ba3f8fadb81d2113f Mon Sep 17 00:00:00 2001 From: Alexey Khoroshilov Date: Tue, 4 Jul 2017 17:47:23 +0200 Subject: vmlfb: Fix error handling in cr_pll_init() There is an error path, where iomemory is left mapped. Found by Linux Driver Verification project (linuxtesting.org). Signed-off-by: Alexey Khoroshilov Cc: Alan Hourihane Signed-off-by: Bartlomiej Zolnierkiewicz --- drivers/video/fbdev/vermilion/cr_pll.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/video/fbdev/vermilion/cr_pll.c b/drivers/video/fbdev/vermilion/cr_pll.c index ebc6e6e0dd0f..ba105c876bed 100644 --- a/drivers/video/fbdev/vermilion/cr_pll.c +++ b/drivers/video/fbdev/vermilion/cr_pll.c @@ -185,6 +185,7 @@ static int __init cr_pll_init(void) if (err) { printk(KERN_ERR "Carillo Ranch failed to initialize vml_sys.\n"); + iounmap(mch_regs_base); pci_dev_put(mch_dev); return err; } -- cgit v1.2.3-59-g8ed1b From 5ffe80c1fa1ac5b0b5c47503452d2f155fcc2702 Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Tue, 4 Jul 2017 17:47:23 +0200 Subject: omapfb: panel-dsi-cm: constify dsicm_attr_group File size before: text data bss dec hex filename 4657 464 0 5121 1401 drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.o File size after adding 'const': text data bss dec hex filename 4713 400 0 5113 13f9 drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.o Signed-off-by: Arvind Yadav Cc: Tomi Valkeinen Signed-off-by: Bartlomiej Zolnierkiewicz --- drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c index 7f20bc267234..bef431530090 100644 --- a/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c +++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c @@ -559,7 +559,7 @@ static struct attribute *dsicm_attrs[] = { NULL, }; -static struct attribute_group dsicm_attr_group = { +static const struct attribute_group dsicm_attr_group = { .attrs = dsicm_attrs, }; -- cgit v1.2.3-59-g8ed1b From 62bffe325f08517eb57963bf0907701fffaab57c Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Tue, 4 Jul 2017 17:47:23 +0200 Subject: fbdev: omapfb: constify ctrl_caps, color_caps, panel_attr_grp and ctrl_attr_grp File size before: text data bss dec hex filename 13007 1536 156 14699 396b drivers/video/fbdev/omap/omapfb_main.o File size after adding 'const': text data bss dec hex filename 13135 1408 156 14699 396b drivers/video/fbdev/omap/omapfb_main.o Signed-off-by: Arvind Yadav Cc: Tomi Valkeinen Signed-off-by: Bartlomiej Zolnierkiewicz --- drivers/video/fbdev/omap/omapfb_main.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/video/fbdev/omap/omapfb_main.c b/drivers/video/fbdev/omap/omapfb_main.c index f4cbfb3b8a09..3479a47a3082 100644 --- a/drivers/video/fbdev/omap/omapfb_main.c +++ b/drivers/video/fbdev/omap/omapfb_main.c @@ -62,7 +62,7 @@ struct caps_table_struct { const char *name; }; -static struct caps_table_struct ctrl_caps[] = { +static const struct caps_table_struct ctrl_caps[] = { { OMAPFB_CAPS_MANUAL_UPDATE, "manual update" }, { OMAPFB_CAPS_TEARSYNC, "tearing synchronization" }, { OMAPFB_CAPS_PLANE_RELOCATE_MEM, "relocate plane memory" }, @@ -74,7 +74,7 @@ static struct caps_table_struct ctrl_caps[] = { { OMAPFB_CAPS_SET_BACKLIGHT, "backlight setting" }, }; -static struct caps_table_struct color_caps[] = { +static const struct caps_table_struct color_caps[] = { { 1 << OMAPFB_COLOR_RGB565, "RGB565", }, { 1 << OMAPFB_COLOR_YUV422, "YUV422", }, { 1 << OMAPFB_COLOR_YUV420, "YUV420", }, @@ -1384,7 +1384,7 @@ static struct attribute *panel_attrs[] = { NULL, }; -static struct attribute_group panel_attr_grp = { +static const struct attribute_group panel_attr_grp = { .name = "panel", .attrs = panel_attrs, }; @@ -1406,7 +1406,7 @@ static struct attribute *ctrl_attrs[] = { NULL, }; -static struct attribute_group ctrl_attr_grp = { +static const struct attribute_group ctrl_attr_grp = { .name = "ctrl", .attrs = ctrl_attrs, }; -- cgit v1.2.3-59-g8ed1b From dd7d958ae9126b2d4a96e41340579049afebd2bf Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 4 Jul 2017 17:47:23 +0200 Subject: video: fbdev: aty: remove useless variable assignments in aty_var_to_crtc() Value assigned to variable vdisplay at line 990 is overwritten at line 1039 before it can be used. Also, variable assignment at line 987 is the same as at line 1039. This makes such variable assignments useless. Remove these variable assignments and the code related. Addresses-Covertity-ID: 1226900 Signed-off-by: Gustavo A. R. Silva Signed-off-by: Bartlomiej Zolnierkiewicz --- drivers/video/fbdev/aty/atyfb_base.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c index 11026e726b68..3142d7f7020f 100644 --- a/drivers/video/fbdev/aty/atyfb_base.c +++ b/drivers/video/fbdev/aty/atyfb_base.c @@ -984,12 +984,6 @@ static int aty_var_to_crtc(const struct fb_info *info, v_total <<= 1; } - vdisplay = yres; -#ifdef CONFIG_FB_ATY_GENERIC_LCD - if ((par->lcd_table != 0) && (crtc->lcd_gen_cntl & LCD_ON)) - vdisplay = par->lcd_height; -#endif - v_disp--; v_sync_strt--; v_sync_end--; -- cgit v1.2.3-59-g8ed1b From 360772f26407b759ec3a91dda81fdbc74b7f7f2c Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 4 Jul 2017 17:47:23 +0200 Subject: video: fbdev: matrox: the list iterator can't be NULL My static checker is complaining because we check "drv" for NULL and then we dereference it to get the next item in the list. It can't be NULL so we can remove this check. Signed-off-by: Dan Carpenter Signed-off-by: Bartlomiej Zolnierkiewicz --- drivers/video/fbdev/matrox/matroxfb_base.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/video/fbdev/matrox/matroxfb_base.c b/drivers/video/fbdev/matrox/matroxfb_base.c index 11eb094396ae..f6a0b9af97a9 100644 --- a/drivers/video/fbdev/matrox/matroxfb_base.c +++ b/drivers/video/fbdev/matrox/matroxfb_base.c @@ -2001,7 +2001,7 @@ static void matroxfb_register_device(struct matrox_fb_info* minfo) { for (drv = matroxfb_driver_l(matroxfb_driver_list.next); drv != matroxfb_driver_l(&matroxfb_driver_list); drv = matroxfb_driver_l(drv->node.next)) { - if (drv && drv->probe) { + if (drv->probe) { void *p = drv->probe(minfo); if (p) { minfo->drivers_data[i] = p; -- cgit v1.2.3-59-g8ed1b From ffb07550c76f70b8fa5e57352e7e299f4811f0a0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 27 Jun 2017 19:32:04 -0400 Subject: copy_msghdr_from_user(): get rid of field-by-field copyin Signed-off-by: Al Viro --- net/socket.c | 31 ++++++++++++++----------------- 1 file changed, 14 insertions(+), 17 deletions(-) diff --git a/net/socket.c b/net/socket.c index c2564eb25c6b..af33d929135a 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1870,22 +1870,18 @@ static int copy_msghdr_from_user(struct msghdr *kmsg, struct sockaddr __user **save_addr, struct iovec **iov) { - struct sockaddr __user *uaddr; - struct iovec __user *uiov; - size_t nr_segs; + struct user_msghdr msg; ssize_t err; - if (!access_ok(VERIFY_READ, umsg, sizeof(*umsg)) || - __get_user(uaddr, &umsg->msg_name) || - __get_user(kmsg->msg_namelen, &umsg->msg_namelen) || - __get_user(uiov, &umsg->msg_iov) || - __get_user(nr_segs, &umsg->msg_iovlen) || - __get_user(kmsg->msg_control, &umsg->msg_control) || - __get_user(kmsg->msg_controllen, &umsg->msg_controllen) || - __get_user(kmsg->msg_flags, &umsg->msg_flags)) + if (copy_from_user(&msg, umsg, sizeof(*umsg))) return -EFAULT; - if (!uaddr) + kmsg->msg_control = msg.msg_control; + kmsg->msg_controllen = msg.msg_controllen; + kmsg->msg_flags = msg.msg_flags; + + kmsg->msg_namelen = msg.msg_namelen; + if (!msg.msg_name) kmsg->msg_namelen = 0; if (kmsg->msg_namelen < 0) @@ -1895,11 +1891,11 @@ static int copy_msghdr_from_user(struct msghdr *kmsg, kmsg->msg_namelen = sizeof(struct sockaddr_storage); if (save_addr) - *save_addr = uaddr; + *save_addr = msg.msg_name; - if (uaddr && kmsg->msg_namelen) { + if (msg.msg_name && kmsg->msg_namelen) { if (!save_addr) { - err = move_addr_to_kernel(uaddr, kmsg->msg_namelen, + err = move_addr_to_kernel(msg.msg_name, kmsg->msg_namelen, kmsg->msg_name); if (err < 0) return err; @@ -1909,12 +1905,13 @@ static int copy_msghdr_from_user(struct msghdr *kmsg, kmsg->msg_namelen = 0; } - if (nr_segs > UIO_MAXIOV) + if (msg.msg_iovlen > UIO_MAXIOV) return -EMSGSIZE; kmsg->msg_iocb = NULL; - return import_iovec(save_addr ? READ : WRITE, uiov, nr_segs, + return import_iovec(save_addr ? READ : WRITE, + msg.msg_iov, msg.msg_iovlen, UIO_FASTIOV, iov, &kmsg->msg_iter); } -- cgit v1.2.3-59-g8ed1b From 5da028a8af38eced330332d5ae51c212e9e86242 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 27 Jun 2017 18:24:21 -0400 Subject: get_compat_msghdr(): get rid of field-by-field copyin Signed-off-by: Al Viro --- net/compat.c | 31 ++++++++++++++----------------- 1 file changed, 14 insertions(+), 17 deletions(-) diff --git a/net/compat.c b/net/compat.c index aba929e5250f..dba5e222a0e5 100644 --- a/net/compat.c +++ b/net/compat.c @@ -37,21 +37,16 @@ int get_compat_msghdr(struct msghdr *kmsg, struct sockaddr __user **save_addr, struct iovec **iov) { - compat_uptr_t uaddr, uiov, tmp3; - compat_size_t nr_segs; + struct compat_msghdr msg; ssize_t err; - if (!access_ok(VERIFY_READ, umsg, sizeof(*umsg)) || - __get_user(uaddr, &umsg->msg_name) || - __get_user(kmsg->msg_namelen, &umsg->msg_namelen) || - __get_user(uiov, &umsg->msg_iov) || - __get_user(nr_segs, &umsg->msg_iovlen) || - __get_user(tmp3, &umsg->msg_control) || - __get_user(kmsg->msg_controllen, &umsg->msg_controllen) || - __get_user(kmsg->msg_flags, &umsg->msg_flags)) + if (copy_from_user(&msg, umsg, sizeof(*umsg))) return -EFAULT; - if (!uaddr) + kmsg->msg_flags = msg.msg_flags; + kmsg->msg_namelen = msg.msg_namelen; + + if (!msg.msg_name) kmsg->msg_namelen = 0; if (kmsg->msg_namelen < 0) @@ -59,14 +54,16 @@ int get_compat_msghdr(struct msghdr *kmsg, if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) kmsg->msg_namelen = sizeof(struct sockaddr_storage); - kmsg->msg_control = compat_ptr(tmp3); + + kmsg->msg_control = compat_ptr(msg.msg_control); + kmsg->msg_controllen = msg.msg_controllen; if (save_addr) - *save_addr = compat_ptr(uaddr); + *save_addr = compat_ptr(msg.msg_name); - if (uaddr && kmsg->msg_namelen) { + if (msg.msg_name && kmsg->msg_namelen) { if (!save_addr) { - err = move_addr_to_kernel(compat_ptr(uaddr), + err = move_addr_to_kernel(compat_ptr(msg.msg_name), kmsg->msg_namelen, kmsg->msg_name); if (err < 0) @@ -77,13 +74,13 @@ int get_compat_msghdr(struct msghdr *kmsg, kmsg->msg_namelen = 0; } - if (nr_segs > UIO_MAXIOV) + if (msg.msg_iovlen > UIO_MAXIOV) return -EMSGSIZE; kmsg->msg_iocb = NULL; return compat_import_iovec(save_addr ? READ : WRITE, - compat_ptr(uiov), nr_segs, + compat_ptr(msg.msg_iov), msg.msg_iovlen, UIO_FASTIOV, iov, &kmsg->msg_iter); } -- cgit v1.2.3-59-g8ed1b From f8f8a727eab1c5b78c3703a461565b042979cc79 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 27 Jun 2017 18:34:53 -0400 Subject: get_compat_bpf_fprog(): don't copyin field-by-field Signed-off-by: Al Viro --- net/compat.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/net/compat.c b/net/compat.c index dba5e222a0e5..6ded6c821d7a 100644 --- a/net/compat.c +++ b/net/compat.c @@ -313,15 +313,15 @@ struct sock_fprog __user *get_compat_bpf_fprog(char __user *optval) { struct compat_sock_fprog __user *fprog32 = (struct compat_sock_fprog __user *)optval; struct sock_fprog __user *kfprog = compat_alloc_user_space(sizeof(struct sock_fprog)); - compat_uptr_t ptr; - u16 len; - - if (!access_ok(VERIFY_READ, fprog32, sizeof(*fprog32)) || - !access_ok(VERIFY_WRITE, kfprog, sizeof(struct sock_fprog)) || - __get_user(len, &fprog32->len) || - __get_user(ptr, &fprog32->filter) || - __put_user(len, &kfprog->len) || - __put_user(compat_ptr(ptr), &kfprog->filter)) + struct compat_sock_fprog f32; + struct sock_fprog f; + + if (copy_from_user(&f32, fprog32, sizeof(*fprog32))) + return NULL; + memset(&f, 0, sizeof(f)); + f.len = f32.len; + f.filter = compat_ptr(f32.filter); + if (copy_to_user(kfprog, &f, sizeof(struct sock_fprog))) return NULL; return kfprog; -- cgit v1.2.3-59-g8ed1b From ecebcd4da6cde7bfcde62d06488faba164b70b37 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Tue, 4 Jul 2017 13:16:41 -0600 Subject: docs: Do not include from kernel/rcu/srcu.c That file went away with commit bd8cc5a062f4 (srcu: Remove Classic SRCU) during the 4.13 merge window, leading to errors like: Error: Cannot open file ./kernel/rcu/srcu.c during the docs build. Reported-by: Linus Torvalds Signed-off-by: Jonathan Corbet --- Documentation/driver-api/basics.rst | 3 --- 1 file changed, 3 deletions(-) diff --git a/Documentation/driver-api/basics.rst b/Documentation/driver-api/basics.rst index 472e7a664d13..ab82250c7727 100644 --- a/Documentation/driver-api/basics.rst +++ b/Documentation/driver-api/basics.rst @@ -106,9 +106,6 @@ Kernel utility functions .. kernel-doc:: kernel/sys.c :export: -.. kernel-doc:: kernel/rcu/srcu.c - :export: - .. kernel-doc:: kernel/rcu/tree.c :export: -- cgit v1.2.3-59-g8ed1b From 8d1630f13754f1435d3ea7078829121c52f38d15 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Tue, 23 May 2017 13:37:05 +0100 Subject: MIPS: MIPS16e2: Identify ASE presence Identify the presence of the MIPS16e2 ASE as per the architecture specification[1], by checking for CP0 Config5.CA2 bit being 1[2]. References: [1] "MIPS32 Architecture for Programmers: MIPS16e2 Application-Specific Extension Technical Reference Manual", Imagination Technologies Ltd., Document Number: MD01172, Revision 01.00, April 26, 2016, Section 1.2 "Software Detection of the ASE", p. 5 [2] "MIPS32 interAptiv Multiprocessing System Software User's Manual", Imagination Technologies Ltd., Document Number: MD00904, Revision 02.01, June 15, 2016, Section 2.2.1.6 "Device Configuration 5 -- Config5 (CP0 Register 16, Select 5)", pp. 71-72 Signed-off-by: Maciej W. Rozycki Reviewed-by: James Hogan Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16094/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/cpu-features.h | 3 +++ arch/mips/include/asm/cpu.h | 1 + arch/mips/include/asm/mipsregs.h | 1 + arch/mips/kernel/cpu-probe.c | 2 ++ 4 files changed, 7 insertions(+) diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h index d6ea8e7c5107..8baa9033b181 100644 --- a/arch/mips/include/asm/cpu-features.h +++ b/arch/mips/include/asm/cpu-features.h @@ -138,6 +138,9 @@ #ifndef cpu_has_mips16 #define cpu_has_mips16 (cpu_data[0].ases & MIPS_ASE_MIPS16) #endif +#ifndef cpu_has_mips16e2 +#define cpu_has_mips16e2 (cpu_data[0].ases & MIPS_ASE_MIPS16E2) +#endif #ifndef cpu_has_mdmx #define cpu_has_mdmx (cpu_data[0].ases & MIPS_ASE_MDMX) #endif diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h index ce798594c868..d0c152b989f8 100644 --- a/arch/mips/include/asm/cpu.h +++ b/arch/mips/include/asm/cpu.h @@ -436,5 +436,6 @@ enum cpu_type_enum { #define MIPS_ASE_VZ 0x00000080 /* Virtualization ASE */ #define MIPS_ASE_MSA 0x00000100 /* MIPS SIMD Architecture */ #define MIPS_ASE_DSP3 0x00000200 /* Signal Processing ASE Rev 3*/ +#define MIPS_ASE_MIPS16E2 0x00000400 /* MIPS16e2 */ #endif /* _ASM_CPU_H */ diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index 6875b69f59f7..dbb0eceda2c6 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -652,6 +652,7 @@ #define MIPS_CONF5_SBRI (_ULCAST_(1) << 6) #define MIPS_CONF5_FRE (_ULCAST_(1) << 8) #define MIPS_CONF5_UFE (_ULCAST_(1) << 9) +#define MIPS_CONF5_CA2 (_ULCAST_(1) << 14) #define MIPS_CONF5_MSAEN (_ULCAST_(1) << 27) #define MIPS_CONF5_EVA (_ULCAST_(1) << 28) #define MIPS_CONF5_CV (_ULCAST_(1) << 29) diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index 3f0d43ce994a..d08afc7dc507 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -845,6 +845,8 @@ static inline unsigned int decode_config5(struct cpuinfo_mips *c) c->options |= MIPS_CPU_MVH; if (cpu_has_mips_r6 && (config5 & MIPS_CONF5_VP)) c->options |= MIPS_CPU_VP; + if (config5 & MIPS_CONF5_CA2) + c->ases |= MIPS_ASE_MIPS16E2; return config5 & MIPS_CONF_M; } -- cgit v1.2.3-59-g8ed1b From f3235d32075137e277a2e4ea0d7cef2b59480f4a Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Tue, 23 May 2017 13:38:19 +0100 Subject: MIPS: MIPS16e2: Subdecode extended LWSP/SWSP instructions Implement extended LWSP/SWSP instruction subdecoding for the purpose of unaligned GP-relative memory access emulation. With the introduction of the MIPS16e2 ASE[1] the previously must-be-zero 3-bit field at bits 7..5 of the extended encodings of the instructions selected with the LWSP and SWSP major opcodes has become a `sel' field, acting as an opcode extension for additional operations. In both cases the `sel' value of 0 has retained the original operation, that is: LW rx, offset(sp) and: SW rx, offset(sp) for LWSP and SWSP respectively. In hardware predating the MIPS16e2 ASE other values may or may not have been decoded, architecturally yielding unpredictable results, and in our unaligned memory access emulation we have treated the 3-bit field as a don't-care, that is effectively making all the possible encodings of the field alias to the architecturally defined encoding of 0. For the non-zero values of the `sel' field the MIPS16e2 ASE has in particular defined these GP-relative operations: LW rx, offset(gp) # sel = 1 LH rx, offset(gp) # sel = 2 LHU rx, offset(gp) # sel = 4 and SW rx, offset(gp) # sel = 1 SH rx, offset(gp) # sel = 2 for LWSP and SWSP respectively, which will trap with an Address Error exception if the effective address calculated is not naturally-aligned for the operation requested. These operations have been selected for unaligned access emulation, for consistency with the corresponding regular MIPS and microMIPS operations. For other non-zero values of the `sel' field the MIPS16e2 ASE has defined further operations, which however either never trap with an Address Error exception, such as LWL or GP-relative SB, or are not supposed to be emulated, such as LL or SC. These operations have been selected to exclude from unaligned access emulation, should an Address Error exception ever happen with them. Subdecode the `sel' field in unaligned access emulation then for the extended encodings of the instructions selected with the LWSP and SWSP major opcodes, whenever support for the MIPS16e2 ASE has been detected in hardware, and either emulate the operation requested or send SIGBUS to the originating process, according to the selection described above. For hardware implementing the MIPS16 ASE, however lacking MIPS16e2 ASE support retain the original interpretation of the `sel' field. The effects of this change are illustrated with the following user program: $ cat mips16e2-test.c #include #include int main(void) { int64_t scratch[16] = { 0 }; int32_t *tmp0, *tmp1, *tmp2; int i; scratch[0] = 0xc8c7c6c5c4c3c2c1; scratch[1] = 0xd0cfcecdcccbcac9; asm volatile( "move %0, $sp\n\t" "move %1, $gp\n\t" "move $sp, %4\n\t" "addiu %2, %4, 8\n\t" "move $gp, %2\n\t" "lw %2, 2($sp)\n\t" "sw %2, 16(%4)\n\t" "lw %2, 2($gp)\n\t" "sw %2, 24(%4)\n\t" "lw %2, 1($sp)\n\t" "sw %2, 32(%4)\n\t" "lh %2, 1($gp)\n\t" "sw %2, 40(%4)\n\t" "lw %2, 3($sp)\n\t" "sw %2, 48(%4)\n\t" "lhu %2, 3($gp)\n\t" "sw %2, 56(%4)\n\t" "lw %2, 0(%4)\n\t" "sw %2, 66($sp)\n\t" "lw %2, 8(%4)\n\t" "sw %2, 82($gp)\n\t" "lw %2, 0(%4)\n\t" "sw %2, 97($sp)\n\t" "lw %2, 8(%4)\n\t" "sh %2, 113($gp)\n\t" "move $gp, %1\n\t" "move $sp, %0" : "=&d" (tmp0), "=&d" (tmp1), "=&d" (tmp2), "=m" (scratch) : "d" (scratch)); for (i = 0; i < sizeof(scratch) / sizeof(*scratch); i += 2) printf("%016" PRIx64 "\t%016" PRIx64 "\n", scratch[i], scratch[i + 1]); return 0; } $ to be compiled with: $ gcc -mips16 -mips32r2 -Wa,-mmips16e2 -o mips16e2-test mips16e2-test.c $ With 74Kf hardware, which does not implement the MIPS16e2 ASE, this program produces the following output: $ ./mips16e2-test c8c7c6c5c4c3c2c1 d0cfcecdcccbcac9 00000000c6c5c4c3 00000000c6c5c4c3 00000000c5c4c3c2 00000000c5c4c3c2 00000000c7c6c5c4 00000000c7c6c5c4 0000c4c3c2c10000 0000000000000000 0000cccbcac90000 0000000000000000 000000c4c3c2c100 0000000000000000 000000cccbcac900 0000000000000000 $ regardless of whether the change has been applied or not. With the change not applied and interAptive MR2 hardware[2], which does implement the MIPS16e2 ASE, it produces the following output: $ ./mips16e2-test c8c7c6c5c4c3c2c1 d0cfcecdcccbcac9 00000000c6c5c4c3 00000000cecdcccb 00000000c5c4c3c2 00000000cdcccbca 00000000c7c6c5c4 00000000cfcecdcc 0000c4c3c2c10000 0000000000000000 0000000000000000 0000cccbcac90000 000000c4c3c2c100 0000000000000000 0000000000000000 000000cccbcac900 $ which shows that for GP-relative operations the correct trapping address calculated from $gp has been obtained from the CP0 BadVAddr register and so has data from the source operand, however masking and extension has not been applied for halfword operations. With the change applied and interAptive MR2 hardware the program produces the following output: $ ./mips16e2-test c8c7c6c5c4c3c2c1 d0cfcecdcccbcac9 00000000c6c5c4c3 00000000cecdcccb 00000000c5c4c3c2 00000000ffffcbca 00000000c7c6c5c4 000000000000cdcc 0000c4c3c2c10000 0000000000000000 0000000000000000 0000cccbcac90000 000000c4c3c2c100 0000000000000000 0000000000000000 0000000000cac900 $ as expected. References: [1] "MIPS32 Architecture for Programmers: MIPS16e2 Application-Specific Extension Technical Reference Manual", Imagination Technologies Ltd., Document Number: MD01172, Revision 01.00, April 26, 2016 [2] "MIPS32 interAptiv Multiprocessing System Software User's Manual", Imagination Technologies Ltd., Document Number: MD00904, Revision 02.01, June 15, 2016, Chapter 24 "MIPS16e Application-Specific Extension to the MIPS32 Instruction Set", pp. 871-883 Signed-off-by: Maciej W. Rozycki Reviewed-by: James Hogan Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16095/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/unaligned.c | 39 +++++++++++++++++++++++++++++++++++++-- 1 file changed, 37 insertions(+), 2 deletions(-) diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c index 67946bb98dd0..5eaf2578ac04 100644 --- a/arch/mips/kernel/unaligned.c +++ b/arch/mips/kernel/unaligned.c @@ -2010,6 +2010,8 @@ static void emulate_load_store_MIPS16e(struct pt_regs *regs, void __user * addr) u16 __user *pc16; unsigned long origpc; union mips16e_instruction mips16inst, oldinst; + unsigned int opcode; + int extended = 0; origpc = regs->cp0_epc; orig31 = regs->regs[31]; @@ -2022,6 +2024,7 @@ static void emulate_load_store_MIPS16e(struct pt_regs *regs, void __user * addr) /* skip EXTEND instruction */ if (mips16inst.ri.opcode == MIPS16e_extend_op) { + extended = 1; pc16++; __get_user(mips16inst.full, pc16); } else if (delay_slot(regs)) { @@ -2034,7 +2037,8 @@ static void emulate_load_store_MIPS16e(struct pt_regs *regs, void __user * addr) goto sigbus; } - switch (mips16inst.ri.opcode) { + opcode = mips16inst.ri.opcode; + switch (opcode) { case MIPS16e_i64_op: /* I64 or RI64 instruction */ switch (mips16inst.i64.func) { /* I64/RI64 func field check */ case MIPS16e_ldpc_func: @@ -2054,9 +2058,40 @@ static void emulate_load_store_MIPS16e(struct pt_regs *regs, void __user * addr) goto sigbus; case MIPS16e_swsp_op: + reg = reg16to32[mips16inst.ri.rx]; + if (extended && cpu_has_mips16e2) + switch (mips16inst.ri.imm >> 5) { + case 0: /* SWSP */ + case 1: /* SWGP */ + break; + case 2: /* SHGP */ + opcode = MIPS16e_sh_op; + break; + default: + goto sigbus; + } + break; + case MIPS16e_lwpc_op: + reg = reg16to32[mips16inst.ri.rx]; + break; + case MIPS16e_lwsp_op: reg = reg16to32[mips16inst.ri.rx]; + if (extended && cpu_has_mips16e2) + switch (mips16inst.ri.imm >> 5) { + case 0: /* LWSP */ + case 1: /* LWGP */ + break; + case 2: /* LHGP */ + opcode = MIPS16e_lh_op; + break; + case 4: /* LHUGP */ + opcode = MIPS16e_lhu_op; + break; + default: + goto sigbus; + } break; case MIPS16e_i8_op: @@ -2070,7 +2105,7 @@ static void emulate_load_store_MIPS16e(struct pt_regs *regs, void __user * addr) break; } - switch (mips16inst.ri.opcode) { + switch (opcode) { case MIPS16e_lb_op: case MIPS16e_lbu_op: -- cgit v1.2.3-59-g8ed1b From b82ce24426a4071da9529d726057e4e642948667 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 4 Jul 2017 12:21:12 +0800 Subject: crypto: sha1-ssse3 - Disable avx2 It has been reported that sha1-avx2 can cause page faults by reading beyond the end of the input. This patch disables it until it can be fixed. Cc: Fixes: 7c1da8d0d046 ("crypto: sha - SHA1 transform x86_64 AVX2") Reported-by: Jan Stancek Signed-off-by: Herbert Xu --- arch/x86/crypto/sha1_ssse3_glue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c index fc61739150e7..f960a043cdeb 100644 --- a/arch/x86/crypto/sha1_ssse3_glue.c +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -201,7 +201,7 @@ asmlinkage void sha1_transform_avx2(u32 *digest, const char *data, static bool avx2_usable(void) { - if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2) + if (false && avx_usable() && boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_BMI1) && boot_cpu_has(X86_FEATURE_BMI2)) return true; -- cgit v1.2.3-59-g8ed1b From 74a1eb565c3f4ca55af2db8dc42c31ae311a79c0 Mon Sep 17 00:00:00 2001 From: Priyalee Kushwaha Date: Sat, 3 Jun 2017 10:21:24 -0700 Subject: platform/x86: intel_telemetry_debugfs: fix oops when load/unload module This fixes an oops found while testing load/unload of the intel_telemetry_debugfs module. module_init uses register_pm_notifier for PM callbacks, but unregister_pm_notifier was missing from module_exit. [ 97.481860] BUG: unable to handle kernel paging request at ffffffffa006f010 [ 97.489742] IP: blocking_notifier_chain_register+0x3a/0xa0 [ 97.495898] PGD 2e0a067 [ 97.495899] PUD 2e0b063 [ 97.498737] PMD 179e29067 [ 97.501573] PTE 0 [ 97.508423] Oops: 0000 1 PREEMPT SMP [ 97.512724] Modules linked in: intel_telemetry_debugfs intel_rapl gpio_keys dwc3 udc_core intel_telemetry_pltdrv intel_punit_ipc intel_telemetry_core rtc_cmos efivars x86_pkg_temp_thermal iwlwifi snd_hda_codec_hdmi soc_button_array btusb cfg80211 btrtl mei_me hci_uart btbcm mei btintel i915 bluetooth intel_pmc_ipc snd_hda_intel spi_pxa2xx_platform snd_hda_codec dwc3_pci snd_hda_core tpm_tis tpm_tis_core tpm efivarfs [ 97.558453] CPU: 0 PID: 889 Comm: modprobe Not tainted 4.11.0-rc6-intel-dev-bkc #1 [ 97.566950] Hardware name: Intel Corp. Joule DVT3/SDS, BIOS GTPP181A.X64.0143.B30.1701132137 01/13/2017 [ 97.577518] task: ffff8801793a21c0 task.stack: ffff8801793f0000 [ 97.584162] RIP: 0010:blocking_notifier_chain_register+0x3a/0xa0 [ 97.590903] RSP: 0018:ffff8801793f3c58 EFLAGS: 00010286 [ 97.596802] RAX: ffffffffa006f000 RBX: ffffffff81e3ea20 RCX: 0000000000000000 [ 97.604812] RDX: ffff880179eaf210 RSI: ffffffffa0131000 RDI: ffffffff81e3ea20 [ 97.612821] RBP: ffff8801793f3c68 R08: 0000000000000006 R09: 000000000000005c [ 97.620847] R10: 0000000000000000 R11: 0000000000000006 R12: ffffffffa0131000 [ 97.628855] R13: 0000000000000000 R14: ffff880176e35f48 R15: ffff8801793f3ea8 [ 97.636865] FS: 00007f7eeba07700(0000) GS:ffff88017fc00000(0000) knlGS:0000000000000000 [ 97.645948] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 97.652423] CR2: ffffffffa006f010 CR3: 00000001775ef000 CR4: 00000000003406f0 [ 97.660423] Call Trace: [ 97.663166] ? 0xffffffffa0031000 [ 97.666885] register_pm_notifier+0x18/0x20 [ 97.671581] telemetry_debugfs_init+0x92/0x1000 Signed-off-by: Priyalee Kushwaha Signed-off-by: Andy Shevchenko Signed-off-by: Darren Hart (VMware) --- drivers/platform/x86/intel_telemetry_debugfs.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/drivers/platform/x86/intel_telemetry_debugfs.c b/drivers/platform/x86/intel_telemetry_debugfs.c index ef29f18b1951..4cc2f4ea0a25 100644 --- a/drivers/platform/x86/intel_telemetry_debugfs.c +++ b/drivers/platform/x86/intel_telemetry_debugfs.c @@ -97,11 +97,9 @@ } \ } -#ifdef CONFIG_PM_SLEEP static u8 suspend_prep_ok; static u32 suspend_shlw_ctr_temp, suspend_deep_ctr_temp; static u64 suspend_shlw_res_temp, suspend_deep_res_temp; -#endif struct telemetry_susp_stats { u32 shlw_swake_ctr; @@ -807,7 +805,6 @@ static const struct file_operations telem_ioss_trc_verb_ops = { .release = single_release, }; -#ifdef CONFIG_PM_SLEEP static int pm_suspend_prep_cb(void) { struct telemetry_evtlog evtlog[TELEM_MAX_OS_ALLOCATED_EVENTS]; @@ -937,7 +934,6 @@ static int pm_notification(struct notifier_block *this, static struct notifier_block pm_notifier = { .notifier_call = pm_notification, }; -#endif /* CONFIG_PM_SLEEP */ static int __init telemetry_debugfs_init(void) { @@ -960,14 +956,13 @@ static int __init telemetry_debugfs_init(void) if (err < 0) return -EINVAL; - -#ifdef CONFIG_PM_SLEEP register_pm_notifier(&pm_notifier); -#endif /* CONFIG_PM_SLEEP */ debugfs_conf->telemetry_dbg_dir = debugfs_create_dir("telemetry", NULL); - if (!debugfs_conf->telemetry_dbg_dir) - return -ENOMEM; + if (!debugfs_conf->telemetry_dbg_dir) { + err = -ENOMEM; + goto out_pm; + } f = debugfs_create_file("pss_info", S_IFREG | S_IRUGO, debugfs_conf->telemetry_dbg_dir, NULL, @@ -1014,6 +1009,8 @@ static int __init telemetry_debugfs_init(void) out: debugfs_remove_recursive(debugfs_conf->telemetry_dbg_dir); debugfs_conf->telemetry_dbg_dir = NULL; +out_pm: + unregister_pm_notifier(&pm_notifier); return err; } @@ -1022,6 +1019,7 @@ static void __exit telemetry_debugfs_exit(void) { debugfs_remove_recursive(debugfs_conf->telemetry_dbg_dir); debugfs_conf->telemetry_dbg_dir = NULL; + unregister_pm_notifier(&pm_notifier); } late_initcall(telemetry_debugfs_init); -- cgit v1.2.3-59-g8ed1b From 7a3a51ab9467fb634dcfcd18eade61f418f540dd Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 30 Jun 2017 10:52:18 +0300 Subject: platform/x86: intel_telemetry_debugfs: fix some error codes in init There are bunch of "goto out;" paths where we don't set the error code. Signed-off-by: Dan Carpenter Signed-off-by: Andy Shevchenko --- drivers/platform/x86/intel_telemetry_debugfs.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/platform/x86/intel_telemetry_debugfs.c b/drivers/platform/x86/intel_telemetry_debugfs.c index 4cc2f4ea0a25..b8be058a8754 100644 --- a/drivers/platform/x86/intel_telemetry_debugfs.c +++ b/drivers/platform/x86/intel_telemetry_debugfs.c @@ -938,7 +938,7 @@ static struct notifier_block pm_notifier = { static int __init telemetry_debugfs_init(void) { const struct x86_cpu_id *id; - int err = -ENOMEM; + int err; struct dentry *f; /* Only APL supported for now */ @@ -958,11 +958,10 @@ static int __init telemetry_debugfs_init(void) register_pm_notifier(&pm_notifier); + err = -ENOMEM; debugfs_conf->telemetry_dbg_dir = debugfs_create_dir("telemetry", NULL); - if (!debugfs_conf->telemetry_dbg_dir) { - err = -ENOMEM; + if (!debugfs_conf->telemetry_dbg_dir) goto out_pm; - } f = debugfs_create_file("pss_info", S_IFREG | S_IRUGO, debugfs_conf->telemetry_dbg_dir, NULL, -- cgit v1.2.3-59-g8ed1b From bc8c47abd486014aae543ecdea59554f098df9df Mon Sep 17 00:00:00 2001 From: Rajneesh Bhardwaj Date: Fri, 23 Jun 2017 22:22:35 +0530 Subject: platform/x86: intel_telemetry: Add debugfs entry for S0ix residency This adds a debugfs consumer for the exported kernel API intel_pmc_read_s0ix_residency. This debugfs entry reads S0ix residency directly from the PMC hardware counters. TEST: - echo freeze > /sys/power/state - Wake the system, read the S0ix residency i.e. cat /sys/kernel/debug/telemetry/s0ix_residency_usec Signed-off-by: Shanth Murthy Signed-off-by: Rajneesh Bhardwaj Signed-off-by: Andy Shevchenko --- drivers/platform/x86/intel_telemetry_debugfs.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/drivers/platform/x86/intel_telemetry_debugfs.c b/drivers/platform/x86/intel_telemetry_debugfs.c index b8be058a8754..cd21df982abd 100644 --- a/drivers/platform/x86/intel_telemetry_debugfs.c +++ b/drivers/platform/x86/intel_telemetry_debugfs.c @@ -710,6 +710,24 @@ static const struct file_operations telem_socstate_ops = { .release = single_release, }; +static int telem_s0ix_res_get(void *data, u64 *val) +{ + u64 s0ix_total_res; + int ret; + + ret = intel_pmc_s0ix_counter_read(&s0ix_total_res); + if (ret) { + pr_err("Failed to read S0ix residency"); + return ret; + } + + *val = s0ix_total_res; + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(telem_s0ix_fops, telem_s0ix_res_get, NULL, "%llu\n"); + static int telem_pss_trc_verb_show(struct seq_file *s, void *unused) { u32 verbosity; @@ -987,6 +1005,14 @@ static int __init telemetry_debugfs_init(void) goto out; } + f = debugfs_create_file("s0ix_residency_usec", S_IFREG | S_IRUGO, + debugfs_conf->telemetry_dbg_dir, + NULL, &telem_s0ix_fops); + if (!f) { + pr_err("s0ix_residency_usec debugfs register failed\n"); + goto out; + } + f = debugfs_create_file("pss_trace_verbosity", S_IFREG | S_IRUGO, debugfs_conf->telemetry_dbg_dir, NULL, &telem_pss_trc_verb_ops); -- cgit v1.2.3-59-g8ed1b From 0df4b805cbccbe3f8378f49c415adb2fcffdd3dc Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Sat, 1 Jul 2017 08:20:18 +0200 Subject: platform/x86: ideapad-laptop: Add IdeaPad V510-15IKB to no_hw_rfkill Like other Lenovo models the IdeaPad V510-15IKB does not have an hw rfkill switch. This results in hard-blocked radios after boot, resulting in always blocked radios rendering them unusable. Add the IdeaPad V510-15IKB to the no_hw_rfkill DMI list and allows using the built-in radios. Signed-off-by: Sven Eckelmann Signed-off-by: Andy Shevchenko --- drivers/platform/x86/ideapad-laptop.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index 527e5d9ab9bf..f23e4ad7c564 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -915,6 +915,13 @@ static const struct dmi_system_id no_hw_rfkill_list[] = { DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo V310-15ISK"), }, }, + { + .ident = "Lenovo V510-15IKB", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo V510-15IKB"), + }, + }, { .ident = "Lenovo ideapad 310-15IKB", .matches = { -- cgit v1.2.3-59-g8ed1b From 710c059c248a24609051f5a3dd1d8468cdc675b0 Mon Sep 17 00:00:00 2001 From: Yang Jiaxun Date: Tue, 4 Jul 2017 14:39:19 +0000 Subject: platform/x86: ideapad-laptop: Add several models to no_hw_rfkill Some Lenovo ideapad models do not have hardware rfkill switches, but trying to read the rfkill switches through the ideapad-laptop module. It caused to always reported blocking breaking wifi. Fix it by adding those models to no_hw_rfkill_list. Signed-off-by: Yang Jiaxun Signed-off-by: Andy Shevchenko --- drivers/platform/x86/ideapad-laptop.c | 70 +++++++++++++++++++++++++++++++++++ 1 file changed, 70 insertions(+) diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index f23e4ad7c564..993366a48d5d 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -908,6 +908,27 @@ static const struct dmi_system_id no_hw_rfkill_list[] = { DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo G50-30"), }, }, + { + .ident = "Lenovo V310-14IKB", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo V310-14IKB"), + }, + }, + { + .ident = "Lenovo V310-14ISK", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo V310-14ISK"), + }, + }, + { + .ident = "Lenovo V310-15IKB", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo V310-15IKB"), + }, + }, { .ident = "Lenovo V310-15ISK", .matches = { @@ -922,6 +943,41 @@ static const struct dmi_system_id no_hw_rfkill_list[] = { DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo V510-15IKB"), }, }, + { + .ident = "Lenovo ideapad 300-15IBR", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad 300-15IBR"), + }, + }, + { + .ident = "Lenovo ideapad 300-15IKB", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad 300-15IKB"), + }, + }, + { + .ident = "Lenovo ideapad 300S-11IBR", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad 300S-11BR"), + }, + }, + { + .ident = "Lenovo ideapad 310-15ABR", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad 310-15ABR"), + }, + }, + { + .ident = "Lenovo ideapad 310-15IAP", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad 310-15IAP"), + }, + }, { .ident = "Lenovo ideapad 310-15IKB", .matches = { @@ -929,6 +985,20 @@ static const struct dmi_system_id no_hw_rfkill_list[] = { DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad 310-15IKB"), }, }, + { + .ident = "Lenovo ideapad 310-15ISK", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad 310-15ISK"), + }, + }, + { + .ident = "Lenovo ideapad Y700-14ISK", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad Y700-14ISK"), + }, + }, { .ident = "Lenovo ideapad Y700-15ACZ", .matches = { -- cgit v1.2.3-59-g8ed1b From 5e8f42aa49d9c8686f5ca56a1734767c476c62d5 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 4 Jul 2017 18:34:39 +0300 Subject: platform/x86: ideapad-laptop: Fix indentation in DMI table There are couple of places where 8 spaces are used instead of tabs. Replace former by latter. No functional change intended. Signed-off-by: Andy Shevchenko --- drivers/platform/x86/ideapad-laptop.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index 993366a48d5d..603fc6050971 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -932,8 +932,8 @@ static const struct dmi_system_id no_hw_rfkill_list[] = { { .ident = "Lenovo V310-15ISK", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo V310-15ISK"), + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo V310-15ISK"), }, }, { @@ -981,8 +981,8 @@ static const struct dmi_system_id no_hw_rfkill_list[] = { { .ident = "Lenovo ideapad 310-15IKB", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad 310-15IKB"), + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad 310-15IKB"), }, }, { -- cgit v1.2.3-59-g8ed1b From c4f07ecee22ec720936eb58e7c63b89a1e86bf32 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Mon, 26 Jun 2017 14:15:03 -0700 Subject: rtc: brcmstb-waketimer: Add Broadcom STB wake-timer This adds support for the Broadcom STB wake-timer which is a timer in the chip's 27Mhz clock domain that offers the ability to wake the system (wake-up source) from suspend states (S2, S3, S5). It is supported using the rtc framework allowing us to configure alarms for system wake-up. Signed-off-by: Brian Norris Signed-off-by: Markus Mayer Signed-off-by: Florian Fainelli Signed-off-by: Arnd Bergmann Signed-off-by: Alexandre Belloni --- drivers/rtc/Kconfig | 11 ++ drivers/rtc/Makefile | 1 + drivers/rtc/rtc-brcmstb-waketimer.c | 330 ++++++++++++++++++++++++++++++++++++ 3 files changed, 342 insertions(+) create mode 100644 drivers/rtc/rtc-brcmstb-waketimer.c diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index 8d3b95728326..8e1aa67fe533 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -197,6 +197,17 @@ config RTC_DRV_AC100 This driver can also be built as a module. If so, the module will be called rtc-ac100. +config RTC_DRV_BRCMSTB + tristate "Broadcom STB wake-timer" + depends on ARCH_BRCMSTB || BMIPS_GENERIC || COMPILE_TEST + default ARCH_BRCMSTB || BMIPS_GENERIC + help + If you say yes here you get support for the wake-timer found on + Broadcom STB SoCs (BCM7xxx). + + This driver can also be built as a module. If so, the module will + be called rtc-brcmstb-waketimer. + config RTC_DRV_AS3722 tristate "ams AS3722 RTC driver" depends on MFD_AS3722 diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile index 13857d2fce09..df89cac1f9ae 100644 --- a/drivers/rtc/Makefile +++ b/drivers/rtc/Makefile @@ -36,6 +36,7 @@ obj-$(CONFIG_RTC_DRV_AT91RM9200)+= rtc-at91rm9200.o obj-$(CONFIG_RTC_DRV_AT91SAM9) += rtc-at91sam9.o obj-$(CONFIG_RTC_DRV_AU1XXX) += rtc-au1xxx.o obj-$(CONFIG_RTC_DRV_BFIN) += rtc-bfin.o +obj-$(CONFIG_RTC_DRV_BRCMSTB) += rtc-brcmstb-waketimer.o obj-$(CONFIG_RTC_DRV_BQ32K) += rtc-bq32k.o obj-$(CONFIG_RTC_DRV_BQ4802) += rtc-bq4802.o obj-$(CONFIG_RTC_DRV_CMOS) += rtc-cmos.o diff --git a/drivers/rtc/rtc-brcmstb-waketimer.c b/drivers/rtc/rtc-brcmstb-waketimer.c new file mode 100644 index 000000000000..796ac792a381 --- /dev/null +++ b/drivers/rtc/rtc-brcmstb-waketimer.c @@ -0,0 +1,330 @@ +/* + * Copyright © 2014-2017 Broadcom + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct brcmstb_waketmr { + struct rtc_device *rtc; + struct device *dev; + void __iomem *base; + int irq; + struct notifier_block reboot_notifier; + struct clk *clk; + u32 rate; +}; + +#define BRCMSTB_WKTMR_EVENT 0x00 +#define BRCMSTB_WKTMR_COUNTER 0x04 +#define BRCMSTB_WKTMR_ALARM 0x08 +#define BRCMSTB_WKTMR_PRESCALER 0x0C +#define BRCMSTB_WKTMR_PRESCALER_VAL 0x10 + +#define BRCMSTB_WKTMR_DEFAULT_FREQ 27000000 + +static inline void brcmstb_waketmr_clear_alarm(struct brcmstb_waketmr *timer) +{ + writel_relaxed(1, timer->base + BRCMSTB_WKTMR_EVENT); + (void)readl_relaxed(timer->base + BRCMSTB_WKTMR_EVENT); +} + +static void brcmstb_waketmr_set_alarm(struct brcmstb_waketmr *timer, + unsigned int secs) +{ + brcmstb_waketmr_clear_alarm(timer); + + writel_relaxed(secs + 1, timer->base + BRCMSTB_WKTMR_ALARM); +} + +static irqreturn_t brcmstb_waketmr_irq(int irq, void *data) +{ + struct brcmstb_waketmr *timer = data; + + pm_wakeup_event(timer->dev, 0); + + return IRQ_HANDLED; +} + +struct wktmr_time { + u32 sec; + u32 pre; +}; + +static void wktmr_read(struct brcmstb_waketmr *timer, + struct wktmr_time *t) +{ + u32 tmp; + + do { + t->sec = readl_relaxed(timer->base + BRCMSTB_WKTMR_COUNTER); + tmp = readl_relaxed(timer->base + BRCMSTB_WKTMR_PRESCALER_VAL); + } while (tmp >= timer->rate); + + t->pre = timer->rate - tmp; +} + +static int brcmstb_waketmr_prepare_suspend(struct brcmstb_waketmr *timer) +{ + struct device *dev = timer->dev; + int ret = 0; + + if (device_may_wakeup(dev)) { + ret = enable_irq_wake(timer->irq); + if (ret) { + dev_err(dev, "failed to enable wake-up interrupt\n"); + return ret; + } + } + + return ret; +} + +/* If enabled as a wakeup-source, arm the timer when powering off */ +static int brcmstb_waketmr_reboot(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct brcmstb_waketmr *timer; + + timer = container_of(nb, struct brcmstb_waketmr, reboot_notifier); + + /* Set timer for cold boot */ + if (action == SYS_POWER_OFF) + brcmstb_waketmr_prepare_suspend(timer); + + return NOTIFY_DONE; +} + +static int brcmstb_waketmr_gettime(struct device *dev, + struct rtc_time *tm) +{ + struct brcmstb_waketmr *timer = dev_get_drvdata(dev); + struct wktmr_time now; + + wktmr_read(timer, &now); + + rtc_time_to_tm(now.sec, tm); + + return 0; +} + +static int brcmstb_waketmr_settime(struct device *dev, + struct rtc_time *tm) +{ + struct brcmstb_waketmr *timer = dev_get_drvdata(dev); + time64_t sec; + + sec = rtc_tm_to_time64(tm); + + if (sec > U32_MAX || sec < 0) + return -EINVAL; + + writel_relaxed(sec, timer->base + BRCMSTB_WKTMR_COUNTER); + + return 0; +} + +static int brcmstb_waketmr_getalarm(struct device *dev, + struct rtc_wkalrm *alarm) +{ + struct brcmstb_waketmr *timer = dev_get_drvdata(dev); + time64_t sec; + u32 reg; + + sec = readl_relaxed(timer->base + BRCMSTB_WKTMR_ALARM); + if (sec != 0) { + /* Alarm is enabled */ + alarm->enabled = 1; + rtc_time64_to_tm(sec, &alarm->time); + } + + reg = readl_relaxed(timer->base + BRCMSTB_WKTMR_EVENT); + alarm->pending = !!(reg & 1); + + return 0; +} + +static int brcmstb_waketmr_setalarm(struct device *dev, + struct rtc_wkalrm *alarm) +{ + struct brcmstb_waketmr *timer = dev_get_drvdata(dev); + time64_t sec; + + if (alarm->enabled) + sec = rtc_tm_to_time64(&alarm->time); + else + sec = 0; + + if (sec > U32_MAX || sec < 0) + return -EINVAL; + + brcmstb_waketmr_set_alarm(timer, sec); + + return 0; +} + +/* + * Does not do much but keep the RTC class happy. We always support + * alarms. + */ +static int brcmstb_waketmr_alarm_enable(struct device *dev, + unsigned int enabled) +{ + return 0; +} + +static const struct rtc_class_ops brcmstb_waketmr_ops = { + .read_time = brcmstb_waketmr_gettime, + .set_time = brcmstb_waketmr_settime, + .read_alarm = brcmstb_waketmr_getalarm, + .set_alarm = brcmstb_waketmr_setalarm, + .alarm_irq_enable = brcmstb_waketmr_alarm_enable, +}; + +static int brcmstb_waketmr_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct brcmstb_waketmr *timer; + struct resource *res; + int ret; + + timer = devm_kzalloc(dev, sizeof(*timer), GFP_KERNEL); + if (!timer) + return -ENOMEM; + + platform_set_drvdata(pdev, timer); + timer->dev = dev; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + timer->base = devm_ioremap_resource(dev, res); + if (IS_ERR(timer->base)) + return PTR_ERR(timer->base); + + /* + * Set wakeup capability before requesting wakeup interrupt, so we can + * process boot-time "wakeups" (e.g., from S5 soft-off) + */ + device_set_wakeup_capable(dev, true); + device_wakeup_enable(dev); + + timer->irq = platform_get_irq(pdev, 0); + if (timer->irq < 0) + return -ENODEV; + + timer->clk = devm_clk_get(dev, NULL); + if (!IS_ERR(timer->clk)) { + ret = clk_prepare_enable(timer->clk); + if (ret) + return ret; + timer->rate = clk_get_rate(timer->clk); + if (!timer->rate) + timer->rate = BRCMSTB_WKTMR_DEFAULT_FREQ; + } else { + timer->rate = BRCMSTB_WKTMR_DEFAULT_FREQ; + timer->clk = NULL; + } + + ret = devm_request_irq(dev, timer->irq, brcmstb_waketmr_irq, 0, + "brcmstb-waketimer", timer); + if (ret < 0) + return ret; + + timer->reboot_notifier.notifier_call = brcmstb_waketmr_reboot; + register_reboot_notifier(&timer->reboot_notifier); + + timer->rtc = rtc_device_register("brcmstb-waketmr", dev, + &brcmstb_waketmr_ops, THIS_MODULE); + if (IS_ERR(timer->rtc)) { + dev_err(dev, "unable to register device\n"); + unregister_reboot_notifier(&timer->reboot_notifier); + return PTR_ERR(timer->rtc); + } + + dev_info(dev, "registered, with irq %d\n", timer->irq); + + return ret; +} + +static int brcmstb_waketmr_remove(struct platform_device *pdev) +{ + struct brcmstb_waketmr *timer = dev_get_drvdata(&pdev->dev); + + unregister_reboot_notifier(&timer->reboot_notifier); + rtc_device_unregister(timer->rtc); + + return 0; +} + +#ifdef CONFIG_PM_SLEEP +static int brcmstb_waketmr_suspend(struct device *dev) +{ + struct brcmstb_waketmr *timer = dev_get_drvdata(dev); + + return brcmstb_waketmr_prepare_suspend(timer); +} + +static int brcmstb_waketmr_resume(struct device *dev) +{ + struct brcmstb_waketmr *timer = dev_get_drvdata(dev); + int ret; + + if (!device_may_wakeup(dev)) + return 0; + + ret = disable_irq_wake(timer->irq); + + brcmstb_waketmr_clear_alarm(timer); + + return ret; +} +#endif /* CONFIG_PM_SLEEP */ + +static SIMPLE_DEV_PM_OPS(brcmstb_waketmr_pm_ops, + brcmstb_waketmr_suspend, brcmstb_waketmr_resume); + +static const struct of_device_id brcmstb_waketmr_of_match[] = { + { .compatible = "brcm,brcmstb-waketimer" }, + { /* sentinel */ }, +}; + +static struct platform_driver brcmstb_waketmr_driver = { + .probe = brcmstb_waketmr_probe, + .remove = brcmstb_waketmr_remove, + .driver = { + .name = "brcmstb-waketimer", + .pm = &brcmstb_waketmr_pm_ops, + .of_match_table = of_match_ptr(brcmstb_waketmr_of_match), + } +}; +module_platform_driver(brcmstb_waketmr_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Brian Norris"); +MODULE_AUTHOR("Markus Mayer"); +MODULE_DESCRIPTION("Wake-up timer driver for STB chips"); -- cgit v1.2.3-59-g8ed1b From 078f3f6452c8be74fd406733f99f2cb0d9c50efc Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 5 Jun 2017 17:57:29 +0200 Subject: rtc: ds1307: use regmap_update_bits where applicable After the switch to regmap we can now make use of regmap_update_bits to simplify read/modify/write ops. Signed-off-by: Heiner Kallweit Reviewed-by: Linus Walleij Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ds1307.c | 82 ++++++++++++------------------------------------ 1 file changed, 20 insertions(+), 62 deletions(-) diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index 3cbb7636b405..9b4106a7e8e4 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -297,7 +297,7 @@ static irqreturn_t ds1307_irq(int irq, void *dev_id) { struct ds1307 *ds1307 = dev_id; struct mutex *lock = &ds1307->rtc->ops_lock; - int stat, control, ret; + int stat, ret; mutex_lock(lock); ret = regmap_read(ds1307->regmap, DS1337_REG_STATUS, &stat); @@ -308,13 +308,11 @@ static irqreturn_t ds1307_irq(int irq, void *dev_id) stat &= ~DS1337_BIT_A1I; regmap_write(ds1307->regmap, DS1337_REG_STATUS, stat); - ret = regmap_read(ds1307->regmap, DS1337_REG_CONTROL, &control); + ret = regmap_update_bits(ds1307->regmap, DS1337_REG_CONTROL, + DS1337_BIT_A1IE, 0); if (ret) goto out; - control &= ~DS1337_BIT_A1IE; - regmap_write(ds1307->regmap, DS1337_REG_CONTROL, control); - rtc_update_irq(ds1307->rtc, 1, RTC_AF | RTC_IRQF); } @@ -567,21 +565,13 @@ static int ds1337_set_alarm(struct device *dev, struct rtc_wkalrm *t) static int ds1307_alarm_irq_enable(struct device *dev, unsigned int enabled) { struct ds1307 *ds1307 = dev_get_drvdata(dev); - int control, ret; if (!test_bit(HAS_ALARM, &ds1307->flags)) return -ENOTTY; - ret = regmap_read(ds1307->regmap, DS1337_REG_CONTROL, &control); - if (ret) - return ret; - - if (enabled) - control |= DS1337_BIT_A1IE; - else - control &= ~DS1337_BIT_A1IE; - - return regmap_write(ds1307->regmap, DS1337_REG_CONTROL, control); + return regmap_update_bits(ds1307->regmap, DS1337_REG_CONTROL, + DS1337_BIT_A1IE, + enabled ? DS1337_BIT_A1IE : 0); } static const struct rtc_class_ops ds13xx_rtc_ops = { @@ -795,11 +785,8 @@ static irqreturn_t mcp794xx_irq(int irq, void *dev_id) goto out; /* Disable alarm 0. */ - ret = regmap_read(ds1307->regmap, MCP794XX_REG_CONTROL, ®); - if (ret) - goto out; - reg &= ~MCP794XX_BIT_ALM0_EN; - ret = regmap_write(ds1307->regmap, MCP794XX_REG_CONTROL, reg); + ret = regmap_update_bits(ds1307->regmap, MCP794XX_REG_CONTROL, + MCP794XX_BIT_ALM0_EN, 0); if (ret) goto out; @@ -897,21 +884,13 @@ static int mcp794xx_set_alarm(struct device *dev, struct rtc_wkalrm *t) static int mcp794xx_alarm_irq_enable(struct device *dev, unsigned int enabled) { struct ds1307 *ds1307 = dev_get_drvdata(dev); - int reg, ret; if (!test_bit(HAS_ALARM, &ds1307->flags)) return -EINVAL; - ret = regmap_read(ds1307->regmap, MCP794XX_REG_CONTROL, ®); - if (ret) - return ret; - - if (enabled) - reg |= MCP794XX_BIT_ALM0_EN; - else - reg &= ~MCP794XX_BIT_ALM0_EN; - - return regmap_write(ds1307->regmap, MCP794XX_REG_CONTROL, reg); + return regmap_update_bits(ds1307->regmap, MCP794XX_REG_CONTROL, + MCP794XX_BIT_ALM0_EN, + enabled ? MCP794XX_BIT_ALM0_EN : 0); } static const struct rtc_class_ops mcp794xx_rtc_ops = { @@ -1114,20 +1093,11 @@ static int ds3231_clk_sqw_rates[] = { static int ds1337_write_control(struct ds1307 *ds1307, u8 mask, u8 value) { struct mutex *lock = &ds1307->rtc->ops_lock; - int control; int ret; mutex_lock(lock); - - ret = regmap_read(ds1307->regmap, DS1337_REG_CONTROL, &control); - if (ret) - goto out; - - control &= ~mask; - control |= value; - - ret = regmap_write(ds1307->regmap, DS1337_REG_CONTROL, control); -out: + ret = regmap_update_bits(ds1307->regmap, DS1337_REG_CONTROL, + mask, value); mutex_unlock(lock); return ret; @@ -1233,22 +1203,12 @@ static unsigned long ds3231_clk_32khz_recalc_rate(struct clk_hw *hw, static int ds3231_clk_32khz_control(struct ds1307 *ds1307, bool enable) { struct mutex *lock = &ds1307->rtc->ops_lock; - int status; int ret; mutex_lock(lock); - - ret = regmap_read(ds1307->regmap, DS1337_REG_STATUS, &status); - if (ret) - goto out; - - if (enable) - status |= DS3231_BIT_EN32KHZ; - else - status &= ~DS3231_BIT_EN32KHZ; - - ret = regmap_write(ds1307->regmap, DS1337_REG_STATUS, status); -out: + ret = regmap_update_bits(ds1307->regmap, DS1337_REG_STATUS, + DS3231_BIT_EN32KHZ, + enable ? DS3231_BIT_EN32KHZ : 0); mutex_unlock(lock); return ret; @@ -1712,12 +1672,10 @@ read_rtc: * If different then set the wday which we computed using * timestamp */ - if (wday != tm.tm_wday) { - regmap_read(ds1307->regmap, MCP794XX_REG_WEEKDAY, &wday); - wday = wday & ~MCP794XX_REG_WEEKDAY_WDAY_MASK; - wday = wday | (tm.tm_wday + 1); - regmap_write(ds1307->regmap, MCP794XX_REG_WEEKDAY, wday); - } + if (wday != tm.tm_wday) + regmap_update_bits(ds1307->regmap, MCP794XX_REG_WEEKDAY, + MCP794XX_REG_WEEKDAY_WDAY_MASK, + tm.tm_wday + 1); if (want_irq) { device_set_wakeup_capable(ds1307->dev, true); -- cgit v1.2.3-59-g8ed1b From e03c78ac2d7709b7556a9b8dd584e2969c6fce67 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 18 May 2017 02:14:57 +0900 Subject: um: Use printk instead of printf in make_uml_dir Since this function will be called after printk buffer initialized, use printk as other functions do. Signed-off-by: Masami Hiramatsu Signed-off-by: Richard Weinberger --- arch/um/os-Linux/umid.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/arch/um/os-Linux/umid.c b/arch/um/os-Linux/umid.c index c1dc89261f67..37cfaba47aa6 100644 --- a/arch/um/os-Linux/umid.c +++ b/arch/um/os-Linux/umid.c @@ -35,8 +35,9 @@ static int __init make_uml_dir(void) err = -ENOENT; if (home == NULL) { - printk(UM_KERN_ERR "make_uml_dir : no value in " - "environment for $HOME\n"); + printk(UM_KERN_ERR + "%s: no value in environment for $HOME\n", + __func__); goto err; } strlcpy(dir, home, sizeof(dir)); @@ -50,13 +51,15 @@ static int __init make_uml_dir(void) err = -ENOMEM; uml_dir = malloc(strlen(dir) + 1); if (uml_dir == NULL) { - printf("make_uml_dir : malloc failed, errno = %d\n", errno); + printk(UM_KERN_ERR "%s : malloc failed, errno = %d\n", + __func__, errno); goto err; } strcpy(uml_dir, dir); if ((mkdir(uml_dir, 0777) < 0) && (errno != EEXIST)) { - printf("Failed to mkdir '%s': %s\n", uml_dir, strerror(errno)); + printk(UM_KERN_ERR "Failed to mkdir '%s': %s\n", + uml_dir, strerror(errno)); err = -errno; goto err_free; } -- cgit v1.2.3-59-g8ed1b From f7887ee11082b468517f31ae315b474eaa48b843 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 18 May 2017 02:16:05 +0900 Subject: um: Add os_info() for pre-boot information messages Add os_info() for printing out pre-boot information level messages in stderr. The messages via os_info() are suppressed by "quiet" kernel command line. Signed-off-by: Masami Hiramatsu Signed-off-by: Richard Weinberger --- arch/um/include/shared/os.h | 2 ++ arch/um/os-Linux/util.c | 25 +++++++++++++++++++++++++ 2 files changed, 27 insertions(+) diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h index cd1fa97776c3..9e95bcebaf9b 100644 --- a/arch/um/include/shared/os.h +++ b/arch/um/include/shared/os.h @@ -242,6 +242,8 @@ extern void setup_hostinfo(char *buf, int len); extern void os_dump_core(void) __attribute__ ((noreturn)); extern void um_early_printk(const char *s, unsigned int n); extern void os_fix_helper_signals(void); +extern void os_info(const char *fmt, ...) + __attribute__ ((format (printf, 1, 2))); /* time.c */ extern void os_idle_sleep(unsigned long long nsecs); diff --git a/arch/um/os-Linux/util.c b/arch/um/os-Linux/util.c index faee55ef6d2f..c9bad1bca108 100644 --- a/arch/um/os-Linux/util.c +++ b/arch/um/os-Linux/util.c @@ -13,6 +13,7 @@ #include #include #include +#include #include void stack_protections(unsigned long address) @@ -152,3 +153,27 @@ void um_early_printk(const char *s, unsigned int n) { printf("%.*s", n, s); } + +static int quiet_info; + +static int __init quiet_cmd_param(char *str, int *add) +{ + quiet_info = 1; + return 0; +} + +__uml_setup("quiet", quiet_cmd_param, +"quiet\n" +" Turns off information messages during boot.\n\n"); + +void os_info(const char *fmt, ...) +{ + va_list list; + + if (quiet_info) + return; + + va_start(list, fmt); + vfprintf(stderr, fmt, list); + va_end(list); +} -- cgit v1.2.3-59-g8ed1b From d3878bb8003009d148cd787e1a2d74cff914a7b2 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 18 May 2017 02:17:14 +0900 Subject: um: Use os_info for the messages on normal path Use os_info() for printing out the messages on the normal execution path. Signed-off-by: Masami Hiramatsu Signed-off-by: Richard Weinberger --- arch/um/kernel/um_arch.c | 8 ++++---- arch/um/os-Linux/main.c | 3 +-- arch/um/os-Linux/mem.c | 18 +++++++++--------- arch/um/os-Linux/start_up.c | 26 ++++++++++++++------------ 4 files changed, 28 insertions(+), 27 deletions(-) diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 64a1fd06f3fd..5df91d845a0d 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -289,8 +289,8 @@ int __init linux_main(int argc, char **argv) diff = UML_ROUND_UP(brk_start) - UML_ROUND_UP(&_end); if (diff > 1024 * 1024) { - printf("Adding %ld bytes to physical memory to account for " - "exec-shield gap\n", diff); + os_info("Adding %ld bytes to physical memory to account for " + "exec-shield gap\n", diff); physmem_size += UML_ROUND_UP(brk_start) - UML_ROUND_UP(&_end); } @@ -330,8 +330,8 @@ int __init linux_main(int argc, char **argv) end_vm = start_vm + virtmem_size; if (virtmem_size < physmem_size) - printf("Kernel virtual memory size shrunk to %lu bytes\n", - virtmem_size); + os_info("Kernel virtual memory size shrunk to %lu bytes\n", + virtmem_size); os_flush_stdout(); diff --git a/arch/um/os-Linux/main.c b/arch/um/os-Linux/main.c index 9d499de87e63..f880dcd6ecc9 100644 --- a/arch/um/os-Linux/main.c +++ b/arch/um/os-Linux/main.c @@ -184,14 +184,13 @@ int __init main(int argc, char **argv, char **envp) */ unblock_signals(); + os_info("\n"); /* Reboot */ if (ret) { - printf("\n"); execvp(new_argv[0], new_argv); perror("Failed to exec kernel"); ret = 1; } - printf("\n"); return uml_exitcode; } diff --git a/arch/um/os-Linux/mem.c b/arch/um/os-Linux/mem.c index 8b1767668515..a7f6023301cd 100644 --- a/arch/um/os-Linux/mem.c +++ b/arch/um/os-Linux/mem.c @@ -25,13 +25,13 @@ static int __init check_tmpfs(const char *dir) { struct statfs st; - printf("Checking if %s is on tmpfs...", dir); + os_info("Checking if %s is on tmpfs...", dir); if (statfs(dir, &st) < 0) { - printf("%s\n", strerror(errno)); + os_info("%s\n", strerror(errno)); } else if (st.f_type != TMPFS_MAGIC) { - printf("no\n"); + os_info("no\n"); } else { - printf("OK\n"); + os_info("OK\n"); return 0; } return -1; @@ -61,18 +61,18 @@ static char * __init choose_tempdir(void) int i; const char *dir; - printf("Checking environment variables for a tempdir..."); + os_info("Checking environment variables for a tempdir..."); for (i = 0; vars[i]; i++) { dir = getenv(vars[i]); if ((dir != NULL) && (*dir != '\0')) { - printf("%s\n", dir); + os_info("%s\n", dir); if (check_tmpfs(dir) >= 0) goto done; else goto warn; } } - printf("none found\n"); + os_info("none found\n"); for (i = 0; tmpfs_dirs[i]; i++) { dir = tmpfs_dirs[i]; @@ -194,7 +194,7 @@ void __init check_tmpexec(void) addr = mmap(NULL, UM_KERN_PAGE_SIZE, PROT_READ | PROT_WRITE | PROT_EXEC, MAP_PRIVATE, fd, 0); - printf("Checking PROT_EXEC mmap in %s...", tempdir); + os_info("Checking PROT_EXEC mmap in %s...", tempdir); if (addr == MAP_FAILED) { err = errno; printf("%s\n", strerror(err)); @@ -203,7 +203,7 @@ void __init check_tmpexec(void) printf("%s must be not mounted noexec\n", tempdir); exit(1); } - printf("OK\n"); + os_info("OK\n"); munmap(addr, UM_KERN_PAGE_SIZE); close(fd); diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c index 22a358ef1b0c..f16e001998e5 100644 --- a/arch/um/os-Linux/start_up.c +++ b/arch/um/os-Linux/start_up.c @@ -166,7 +166,7 @@ static void __init check_sysemu(void) unsigned long regs[MAX_REG_NR]; int pid, n, status, count=0; - non_fatal("Checking syscall emulation patch for ptrace..."); + os_info("Checking syscall emulation patch for ptrace..."); sysemu_supported = 0; pid = start_ptraced_child(); @@ -199,10 +199,10 @@ static void __init check_sysemu(void) goto fail_stopped; sysemu_supported = 1; - non_fatal("OK\n"); + os_info("OK\n"); set_using_sysemu(!force_sysemu_disabled); - non_fatal("Checking advanced syscall emulation patch for ptrace..."); + os_info("Checking advanced syscall emulation patch for ptrace..."); pid = start_ptraced_child(); if ((ptrace(PTRACE_OLDSETOPTIONS, pid, 0, @@ -244,7 +244,7 @@ static void __init check_sysemu(void) goto fail_stopped; sysemu_supported = 2; - non_fatal("OK\n"); + os_info("OK\n"); if (!force_sysemu_disabled) set_using_sysemu(sysemu_supported); @@ -260,7 +260,7 @@ static void __init check_ptrace(void) { int pid, syscall, n, status; - non_fatal("Checking that ptrace can change system call numbers..."); + os_info("Checking that ptrace can change system call numbers..."); pid = start_ptraced_child(); if ((ptrace(PTRACE_OLDSETOPTIONS, pid, 0, @@ -292,7 +292,7 @@ static void __init check_ptrace(void) } } stop_ptraced_child(pid, 0, 1); - non_fatal("OK\n"); + os_info("OK\n"); check_sysemu(); } @@ -308,15 +308,17 @@ static void __init check_coredump_limit(void) return; } - printf("Core dump limits :\n\tsoft - "); + os_info("Core dump limits :\n\tsoft - "); if (lim.rlim_cur == RLIM_INFINITY) - printf("NONE\n"); - else printf("%lu\n", lim.rlim_cur); + os_info("NONE\n"); + else + os_info("%llu\n", (unsigned long long)lim.rlim_cur); - printf("\thard - "); + os_info("\thard - "); if (lim.rlim_max == RLIM_INFINITY) - printf("NONE\n"); - else printf("%lu\n", lim.rlim_max); + os_info("NONE\n"); + else + os_info("%llu\n", (unsigned long long)lim.rlim_max); } void __init os_early_checks(void) -- cgit v1.2.3-59-g8ed1b From 721ccae88d04f7e9334fde4cbb3eecfaa70a31ac Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 18 May 2017 02:18:22 +0900 Subject: um: Add os_warn() for pre-boot warning/error messages Add os_warn() for printing out pre-boot warning/error messages in stderr. The messages via os_warn() are not suppressed by quiet option. Signed-off-by: Masami Hiramatsu Signed-off-by: Richard Weinberger --- arch/um/include/shared/os.h | 2 ++ arch/um/os-Linux/util.c | 9 +++++++++ 2 files changed, 11 insertions(+) diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h index 9e95bcebaf9b..574e03fc7ba2 100644 --- a/arch/um/include/shared/os.h +++ b/arch/um/include/shared/os.h @@ -244,6 +244,8 @@ extern void um_early_printk(const char *s, unsigned int n); extern void os_fix_helper_signals(void); extern void os_info(const char *fmt, ...) __attribute__ ((format (printf, 1, 2))); +extern void os_warn(const char *fmt, ...) + __attribute__ ((format (printf, 1, 2))); /* time.c */ extern void os_idle_sleep(unsigned long long nsecs); diff --git a/arch/um/os-Linux/util.c b/arch/um/os-Linux/util.c index c9bad1bca108..8cc8b2617a67 100644 --- a/arch/um/os-Linux/util.c +++ b/arch/um/os-Linux/util.c @@ -177,3 +177,12 @@ void os_info(const char *fmt, ...) vfprintf(stderr, fmt, list); va_end(list); } + +void os_warn(const char *fmt, ...) +{ + va_list list; + + va_start(list, fmt); + vfprintf(stderr, fmt, list); + va_end(list); +} -- cgit v1.2.3-59-g8ed1b From 0936d4f3d5a3d5daf453bc341f02ba4e68cfe40e Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 18 May 2017 02:19:31 +0900 Subject: um: Use os_warn to print out pre-boot warning/error messages Use os_warn() instead of printf/fprintf to print out pre-boot warning/error messages to stderr. Note that the help message and version message are kept to print out to stdout, because user explicitly specifies those options to get such information. Signed-off-by: Masami Hiramatsu Signed-off-by: Richard Weinberger --- arch/um/kernel/physmem.c | 10 +++++----- arch/um/kernel/um_arch.c | 8 +++++--- arch/um/kernel/umid.c | 4 ++-- arch/um/os-Linux/execvp.c | 2 +- arch/um/os-Linux/main.c | 6 +++--- arch/um/os-Linux/mem.c | 10 +++++----- arch/um/os-Linux/start_up.c | 2 +- arch/um/os-Linux/umid.c | 8 ++++---- 8 files changed, 26 insertions(+), 24 deletions(-) diff --git a/arch/um/kernel/physmem.c b/arch/um/kernel/physmem.c index 4c9861b421fd..f02596e9931d 100644 --- a/arch/um/kernel/physmem.c +++ b/arch/um/kernel/physmem.c @@ -89,8 +89,8 @@ void __init setup_physmem(unsigned long start, unsigned long reserve_end, offset = uml_reserved - uml_physmem; map_size = len - offset; if(map_size <= 0) { - printf("Too few physical memory! Needed=%d, given=%d\n", - offset, len); + os_warn("Too few physical memory! Needed=%lu, given=%lu\n", + offset, len); exit(1); } @@ -99,9 +99,9 @@ void __init setup_physmem(unsigned long start, unsigned long reserve_end, err = os_map_memory((void *) uml_reserved, physmem_fd, offset, map_size, 1, 1, 1); if (err < 0) { - printf("setup_physmem - mapping %ld bytes of memory at 0x%p " - "failed - errno = %d\n", map_size, - (void *) uml_reserved, err); + os_warn("setup_physmem - mapping %ld bytes of memory at 0x%p " + "failed - errno = %d\n", map_size, + (void *) uml_reserved, err); exit(1); } diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 5df91d845a0d..9c5d111f46be 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -34,7 +34,7 @@ static char __initdata command_line[COMMAND_LINE_SIZE] = { 0 }; static void __init add_arg(char *arg) { if (strlen(command_line) + strlen(arg) + 1 > COMMAND_LINE_SIZE) { - printf("add_arg: Too many command line arguments!\n"); + os_warn("add_arg: Too many command line arguments!\n"); exit(1); } if (strlen(command_line) > 0) @@ -126,6 +126,7 @@ static const char *usage_string = static int __init uml_version_setup(char *line, int *add) { + /* Explicitly use printf() to show version in stdout */ printf("%s\n", init_utsname()->release); exit(0); @@ -154,8 +155,8 @@ __uml_setup("root=", uml_root_setup, static int __init no_skas_debug_setup(char *line, int *add) { - printf("'debug' is not necessary to gdb UML in skas mode - run \n"); - printf("'gdb linux'\n"); + os_warn("'debug' is not necessary to gdb UML in skas mode - run\n"); + os_warn("'gdb linux'\n"); return 0; } @@ -171,6 +172,7 @@ static int __init Usage(char *line, int *add) printf(usage_string, init_utsname()->release); p = &__uml_help_start; + /* Explicitly use printf() to show help in stdout */ while (p < &__uml_help_end) { printf("%s", *p); p++; diff --git a/arch/um/kernel/umid.c b/arch/um/kernel/umid.c index f6cc3bd61781..10bf4aca529f 100644 --- a/arch/um/kernel/umid.c +++ b/arch/um/kernel/umid.c @@ -16,14 +16,14 @@ static int __init set_umid_arg(char *name, int *add) int err; if (umid_inited) { - printf("umid already set\n"); + os_warn("umid already set\n"); return 0; } *add = 0; err = set_umid(name); if (err == -EEXIST) - printf("umid '%s' already in use\n", name); + os_warn("umid '%s' already in use\n", name); else if (!err) umid_inited = 1; diff --git a/arch/um/os-Linux/execvp.c b/arch/um/os-Linux/execvp.c index 8fb25ca07c46..84a0777c2a45 100644 --- a/arch/um/os-Linux/execvp.c +++ b/arch/um/os-Linux/execvp.c @@ -136,7 +136,7 @@ int main(int argc, char**argv) int ret; argc--; if (!argc) { - fprintf(stderr, "Not enough arguments\n"); + os_warn("Not enough arguments\n"); return 1; } argv++; diff --git a/arch/um/os-Linux/main.c b/arch/um/os-Linux/main.c index f880dcd6ecc9..5f970ece5ac3 100644 --- a/arch/um/os-Linux/main.c +++ b/arch/um/os-Linux/main.c @@ -74,8 +74,8 @@ static void install_fatal_handler(int sig) action.sa_restorer = NULL; action.sa_handler = last_ditch_exit; if (sigaction(sig, &action, NULL) < 0) { - printf("failed to install handler for signal %d - errno = %d\n", - sig, errno); + os_warn("failed to install handler for signal %d " + "- errno = %d\n", sig, errno); exit(1); } } @@ -175,7 +175,7 @@ int __init main(int argc, char **argv, char **envp) /* disable SIGIO for the fds and set SIGIO to be ignored */ err = deactivate_all_fds(); if (err) - printf("deactivate_all_fds failed, errno = %d\n", -err); + os_warn("deactivate_all_fds failed, errno = %d\n", -err); /* * Let any pending signals fire now. This ensures diff --git a/arch/um/os-Linux/mem.c b/arch/um/os-Linux/mem.c index a7f6023301cd..e162a95ad7dd 100644 --- a/arch/um/os-Linux/mem.c +++ b/arch/um/os-Linux/mem.c @@ -82,7 +82,7 @@ static char * __init choose_tempdir(void) dir = fallback_dir; warn: - printf("Warning: tempdir %s is not on tmpfs\n", dir); + os_warn("Warning: tempdir %s is not on tmpfs\n", dir); done: /* Make a copy since getenv results may not remain valid forever. */ return strdup(dir); @@ -100,7 +100,7 @@ static int __init make_tempfile(const char *template) if (tempdir == NULL) { tempdir = choose_tempdir(); if (tempdir == NULL) { - fprintf(stderr, "Failed to choose tempdir: %s\n", + os_warn("Failed to choose tempdir: %s\n", strerror(errno)); return -1; } @@ -125,7 +125,7 @@ static int __init make_tempfile(const char *template) strcat(tempname, template); fd = mkstemp(tempname); if (fd < 0) { - fprintf(stderr, "open - cannot create %s: %s\n", tempname, + os_warn("open - cannot create %s: %s\n", tempname, strerror(errno)); goto out; } @@ -197,10 +197,10 @@ void __init check_tmpexec(void) os_info("Checking PROT_EXEC mmap in %s...", tempdir); if (addr == MAP_FAILED) { err = errno; - printf("%s\n", strerror(err)); + os_warn("%s\n", strerror(err)); close(fd); if (err == EPERM) - printf("%s must be not mounted noexec\n", tempdir); + os_warn("%s must be not mounted noexec\n", tempdir); exit(1); } os_info("OK\n"); diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c index f16e001998e5..b1b6b75c5b17 100644 --- a/arch/um/os-Linux/start_up.c +++ b/arch/um/os-Linux/start_up.c @@ -351,7 +351,7 @@ int __init parse_iomem(char *str, int *add) driver = str; file = strchr(str,','); if (file == NULL) { - fprintf(stderr, "parse_iomem : failed to parse iomem\n"); + os_warn("parse_iomem : failed to parse iomem\n"); goto out; } *file = '\0'; diff --git a/arch/um/os-Linux/umid.c b/arch/um/os-Linux/umid.c index 37cfaba47aa6..998fbb445458 100644 --- a/arch/um/os-Linux/umid.c +++ b/arch/um/os-Linux/umid.c @@ -354,7 +354,7 @@ char *get_umid(void) static int __init set_uml_dir(char *name, int *add) { if (*name == '\0') { - printf("uml_dir can't be an empty string\n"); + os_warn("uml_dir can't be an empty string\n"); return 0; } @@ -365,7 +365,7 @@ static int __init set_uml_dir(char *name, int *add) uml_dir = malloc(strlen(name) + 2); if (uml_dir == NULL) { - printf("Failed to malloc uml_dir - error = %d\n", errno); + os_warn("Failed to malloc uml_dir - error = %d\n", errno); /* * Return 0 here because do_initcalls doesn't look at @@ -390,8 +390,8 @@ static void remove_umid_dir(void) sprintf(dir, "%s%s", uml_dir, umid); err = remove_files_and_dir(dir); if (err) - printf("remove_umid_dir - remove_files_and_dir failed with " - "err = %d\n", err); + os_warn("%s - remove_files_and_dir failed with err = %d\n", + __func__, err); } __uml_exitcall(remove_umid_dir); -- cgit v1.2.3-59-g8ed1b From 745a600cf1a6230f5e3910c340dcb312b718e114 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 18 May 2017 02:20:39 +0900 Subject: um: console: Ignore console= option Ignore linux kernel's console= option at uml's console option handler. Since uml's con= option is only for setting up new console, and Linux kernel's console= option specify to which console kernel output its message, we can use both option for different purpose. Signed-off-by: Masami Hiramatsu Signed-off-by: Richard Weinberger --- arch/um/drivers/stdio_console.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/um/drivers/stdio_console.c b/arch/um/drivers/stdio_console.c index 7b361f36ca96..c90817b04da9 100644 --- a/arch/um/drivers/stdio_console.c +++ b/arch/um/drivers/stdio_console.c @@ -192,6 +192,9 @@ __uml_exitcall(console_exit); static int console_chan_setup(char *str) { + if (!strncmp(str, "sole=", 5)) /* console= option specifies tty */ + return 0; + line_setup(vt_conf, MAX_TTYS, &def_conf, str, "console"); return 1; } -- cgit v1.2.3-59-g8ed1b From f44f1e7da7c8e3f4575d5d61c4df978496903fcc Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 23 May 2017 17:32:31 -0700 Subject: um: Avoid longjmp/setjmp symbol clashes with libpthread.a Building a statically linked UML kernel on a Centos 6.9 host resulted in the following linking failure (GCC 4.4, glibc-2.12): /usr/lib/gcc/x86_64-redhat-linux/4.4.7/../../../../lib64/libpthread.a(libpthread.o): In function `siglongjmp': (.text+0x8490): multiple definition of `longjmp' arch/x86/um/built-in.o:/local/users/fainelli/openwrt/trunk/build_dir/target-x86_64_musl/linux-uml/linux-4.4.69/arch/x86/um/setjmp_64.S:44: first defined here /usr/lib/gcc/x86_64-redhat-linux/4.4.7/../../../../lib64/libpthread.a(libpthread.o): In function `sem_open': (.text+0x77cd): warning: the use of `mktemp' is dangerous, better use `mkstemp' collect2: ld returned 1 exit status make[4]: *** [vmlinux] Error 1 Adopt a solution similar to the one done for vmap where we define longjmp/setjmp to be kernel_longjmp/setjmp. In the process, make sure we do rename the functions in arch/x86/um/setjmp_*.S accordingly. Fixes: a7df4716d195 ("um: link with -lpthread") Signed-off-by: Florian Fainelli Signed-off-by: Richard Weinberger --- arch/um/Makefile | 4 ++++ arch/x86/um/setjmp_32.S | 16 ++++++++-------- arch/x86/um/setjmp_64.S | 16 ++++++++-------- 3 files changed, 20 insertions(+), 16 deletions(-) diff --git a/arch/um/Makefile b/arch/um/Makefile index 0ca46ededfc7..6ca4f66085c1 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -59,10 +59,14 @@ KBUILD_CPPFLAGS += -I$(srctree)/$(HOST_DIR)/um # Same things for in6addr_loopback and mktime - found in libc. For these two we # only get link-time error, luckily. # +# -Dlongjmp=kernel_longjmp prevents anything from referencing the libpthread.a +# embedded copy of longjmp, same thing for setjmp. +# # These apply to USER_CFLAGS to. KBUILD_CFLAGS += $(CFLAGS) $(CFLAGS-y) -D__arch_um__ \ $(ARCH_INCLUDE) $(MODE_INCLUDE) -Dvmap=kernel_vmap \ + -Dlongjmp=kernel_longjmp -Dsetjmp=kernel_setjmp \ -Din6addr_loopback=kernel_in6addr_loopback \ -Din6addr_any=kernel_in6addr_any -Dstrrchr=kernel_strrchr diff --git a/arch/x86/um/setjmp_32.S b/arch/x86/um/setjmp_32.S index b766792c9933..39053192918d 100644 --- a/arch/x86/um/setjmp_32.S +++ b/arch/x86/um/setjmp_32.S @@ -16,9 +16,9 @@ .text .align 4 - .globl setjmp - .type setjmp, @function -setjmp: + .globl kernel_setjmp + .type kernel_setjmp, @function +kernel_setjmp: #ifdef _REGPARM movl %eax,%edx #else @@ -35,13 +35,13 @@ setjmp: movl %ecx,20(%edx) # Return address ret - .size setjmp,.-setjmp + .size kernel_setjmp,.-kernel_setjmp .text .align 4 - .globl longjmp - .type longjmp, @function -longjmp: + .globl kernel_longjmp + .type kernel_longjmp, @function +kernel_longjmp: #ifdef _REGPARM xchgl %eax,%edx #else @@ -55,4 +55,4 @@ longjmp: movl 16(%edx),%edi jmp *20(%edx) - .size longjmp,.-longjmp + .size kernel_longjmp,.-kernel_longjmp diff --git a/arch/x86/um/setjmp_64.S b/arch/x86/um/setjmp_64.S index 45f547b4043e..c56942e1a38c 100644 --- a/arch/x86/um/setjmp_64.S +++ b/arch/x86/um/setjmp_64.S @@ -18,9 +18,9 @@ .text .align 4 - .globl setjmp - .type setjmp, @function -setjmp: + .globl kernel_setjmp + .type kernel_setjmp, @function +kernel_setjmp: pop %rsi # Return address, and adjust the stack xorl %eax,%eax # Return value movq %rbx,(%rdi) @@ -34,13 +34,13 @@ setjmp: movq %rsi,56(%rdi) # Return address ret - .size setjmp,.-setjmp + .size kernel_setjmp,.-kernel_setjmp .text .align 4 - .globl longjmp - .type longjmp, @function -longjmp: + .globl kernel_longjmp + .type kernel_longjmp, @function +kernel_longjmp: movl %esi,%eax # Return value (int) movq (%rdi),%rbx movq 8(%rdi),%rsp @@ -51,4 +51,4 @@ longjmp: movq 48(%rdi),%r15 jmp *56(%rdi) - .size longjmp,.-longjmp + .size kernel_longjmp,.-kernel_longjmp -- cgit v1.2.3-59-g8ed1b From 0a987645672ebde7844a9c0732a5a25f3d4bb6c6 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 25 May 2017 11:36:26 -0700 Subject: um: Allow building and running on older hosts Commit a78ff1112263 ("um: add extended processor state save/restore support") and b6024b21fec8 ("um: extend fpstate to _xstate to support YMM registers") forced the use of the x86 FP _xstate and PTRACE_GETREGSET/SETREGSET. On older hosts, we would neither be able to build UML nor run it anymore with these two commits applied because we don't have definitions for struct _xstate nor these two ptrace requests. We can determine at build time which fp context structure to check against, just like we can keep using the old i387 fp save/restore if PTRACE_GETRESET/SETREGSET are not defined. Fixes: a78ff1112263 ("um: add extended processor state save/restore support") Fixes: b6024b21fec8 ("um: extend fpstate to _xstate to support YMM registers") Signed-off-by: Florian Fainelli Signed-off-by: Richard Weinberger --- arch/x86/um/os-Linux/registers.c | 12 ++++++++---- arch/x86/um/user-offsets.c | 4 ++++ 2 files changed, 12 insertions(+), 4 deletions(-) diff --git a/arch/x86/um/os-Linux/registers.c b/arch/x86/um/os-Linux/registers.c index 00f54a91bb4b..28775f55bde2 100644 --- a/arch/x86/um/os-Linux/registers.c +++ b/arch/x86/um/os-Linux/registers.c @@ -26,6 +26,7 @@ int save_i387_registers(int pid, unsigned long *fp_regs) int save_fp_registers(int pid, unsigned long *fp_regs) { +#ifdef PTRACE_GETREGSET struct iovec iov; if (have_xstate_support) { @@ -34,9 +35,9 @@ int save_fp_registers(int pid, unsigned long *fp_regs) if (ptrace(PTRACE_GETREGSET, pid, NT_X86_XSTATE, &iov) < 0) return -errno; return 0; - } else { + } else +#endif return save_i387_registers(pid, fp_regs); - } } int restore_i387_registers(int pid, unsigned long *fp_regs) @@ -48,6 +49,7 @@ int restore_i387_registers(int pid, unsigned long *fp_regs) int restore_fp_registers(int pid, unsigned long *fp_regs) { +#ifdef PTRACE_SETREGSET struct iovec iov; if (have_xstate_support) { @@ -56,9 +58,9 @@ int restore_fp_registers(int pid, unsigned long *fp_regs) if (ptrace(PTRACE_SETREGSET, pid, NT_X86_XSTATE, &iov) < 0) return -errno; return 0; - } else { + } else +#endif return restore_i387_registers(pid, fp_regs); - } } #ifdef __i386__ @@ -122,6 +124,7 @@ int put_fp_registers(int pid, unsigned long *regs) void arch_init_registers(int pid) { +#ifdef PTRACE_GETREGSET struct _xstate fp_regs; struct iovec iov; @@ -129,6 +132,7 @@ void arch_init_registers(int pid) iov.iov_len = sizeof(struct _xstate); if (ptrace(PTRACE_GETREGSET, pid, NT_X86_XSTATE, &iov) == 0) have_xstate_support = 1; +#endif } #endif diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c index cb3c22370cf5..8af0fb5d2780 100644 --- a/arch/x86/um/user-offsets.c +++ b/arch/x86/um/user-offsets.c @@ -50,7 +50,11 @@ void foo(void) DEFINE(HOST_GS, GS); DEFINE(HOST_ORIG_AX, ORIG_EAX); #else +#if defined(PTRACE_GETREGSET) && defined(PTRACE_SETREGSET) DEFINE(HOST_FP_SIZE, sizeof(struct _xstate) / sizeof(unsigned long)); +#else + DEFINE(HOST_FP_SIZE, sizeof(struct _fpstate) / sizeof(unsigned long)); +#endif DEFINE_LONGS(HOST_BX, RBX); DEFINE_LONGS(HOST_CX, RCX); DEFINE_LONGS(HOST_DI, RDI); -- cgit v1.2.3-59-g8ed1b From 1bcbfbfdeb0091036db7a32e1cd31b49cce5983a Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Wed, 24 May 2017 15:42:15 -0600 Subject: um: add dummy ioremap and iounmap functions The user mode architecture does not provide ioremap or iounmap, and because of this, the arch won't build when the functions are used in some core libraries. I have designs to use these functions in scatterlist.c where they'd almost certainly never be called on the um architecture but it does need to compile. Signed-off-by: Logan Gunthorpe Signed-off-by: Stephen Bates Signed-off-by: Richard Weinberger --- arch/um/include/asm/io.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 arch/um/include/asm/io.h diff --git a/arch/um/include/asm/io.h b/arch/um/include/asm/io.h new file mode 100644 index 000000000000..8f35d574f35b --- /dev/null +++ b/arch/um/include/asm/io.h @@ -0,0 +1,17 @@ +#ifndef _ASM_UM_IO_H +#define _ASM_UM_IO_H + +#define ioremap ioremap +static inline void __iomem *ioremap(phys_addr_t offset, size_t size) +{ + return (void __iomem *)(unsigned long)offset; +} + +#define iounmap iounmap +static inline void iounmap(void __iomem *addr) +{ +} + +#include + +#endif -- cgit v1.2.3-59-g8ed1b From 4afb9996a254a8ec33801f4b33992d45670164b2 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 13 Jun 2017 16:47:55 -0700 Subject: ubifs: require key for truncate(2) of encrypted file Currently, filesystems allow truncate(2) on an encrypted file without the encryption key. However, it's impossible to correctly handle the case where the size being truncated to is not a multiple of the filesystem block size, because that would require decrypting the final block, zeroing the part beyond i_size, then encrypting the block. As other modifications to encrypted file contents are prohibited without the key, just prohibit truncate(2) as well, making it fail with ENOKEY. Signed-off-by: Eric Biggers Signed-off-by: Richard Weinberger --- fs/ubifs/file.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 2cda3d67e2d0..ee3ff4c6bf4a 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1284,6 +1284,14 @@ int ubifs_setattr(struct dentry *dentry, struct iattr *attr) if (err) return err; + if (ubifs_crypt_is_encrypted(inode) && (attr->ia_valid & ATTR_SIZE)) { + err = fscrypt_get_encryption_info(inode); + if (err) + return err; + if (!fscrypt_has_encryption_key(inode)) + return -ENOKEY; + } + if ((attr->ia_valid & ATTR_SIZE) && attr->ia_size < inode->i_size) /* Truncation to a smaller size */ err = do_truncation(c, inode, attr); -- cgit v1.2.3-59-g8ed1b From af65936a7a5bb8ec1d05b2a7670f84ca2014628d Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 22 May 2017 17:39:44 -0700 Subject: ubifs: don't bother checking for encryption key in ->mmap() Since only an open file can be mmap'ed, and we only allow open()ing an encrypted file when its key is available, there is no need to check for the key again before permitting each mmap(). Signed-off-by: Eric Biggers Acked-by: Richard Weinberger Signed-off-by: Richard Weinberger --- fs/ubifs/file.c | 9 --------- 1 file changed, 9 deletions(-) diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index ee3ff4c6bf4a..c1d352842ee2 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1615,15 +1615,6 @@ static const struct vm_operations_struct ubifs_file_vm_ops = { static int ubifs_file_mmap(struct file *file, struct vm_area_struct *vma) { int err; - struct inode *inode = file->f_mapping->host; - - if (ubifs_crypt_is_encrypted(inode)) { - err = fscrypt_get_encryption_info(inode); - if (err) - return -EACCES; - if (!fscrypt_has_encryption_key(inode)) - return -ENOKEY; - } err = generic_file_mmap(file, vma); if (err) -- cgit v1.2.3-59-g8ed1b From da55b1ad4b29b6ab44d5dc8ea8306260246d2699 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 3 Jul 2017 07:59:26 -0500 Subject: PM / devfreq: rk3399_dmc: fix error return code in rk3399_dmcfreq_probe() platform_get_irq() returns an error code, but the rk3399_dmc driver ignores it and always returns -EINVAL. This is not correct, and prevents -EPROBE_DEFER from being propagated properly. Notice that platform_get_irq() no longer returns 0 on error: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=e330b9a6bb35dc7097a4f02cb1ae7b6f96df92af Print and propagate the return value of platform_get_irq on failure. Reviewed-by: Chanwoo Choi Signed-off-by: Gustavo A. R. Silva Signed-off-by: MyungJoo Ham --- drivers/devfreq/rk3399_dmc.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/devfreq/rk3399_dmc.c b/drivers/devfreq/rk3399_dmc.c index 40a2499730fc..1b89ebbad02c 100644 --- a/drivers/devfreq/rk3399_dmc.c +++ b/drivers/devfreq/rk3399_dmc.c @@ -336,8 +336,9 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); if (irq < 0) { - dev_err(&pdev->dev, "Cannot get the dmc interrupt resource\n"); - return -EINVAL; + dev_err(&pdev->dev, + "Cannot get the dmc interrupt resource: %d\n", irq); + return irq; } data = devm_kzalloc(dev, sizeof(struct rk3399_dmcfreq), GFP_KERNEL); if (!data) -- cgit v1.2.3-59-g8ed1b From 9e578b37505018622dfafc40eed7cd78ff2af221 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 3 Jul 2017 07:47:38 -0500 Subject: PM / devfreq: tegra: fix error return code in tegra_devfreq_probe() platform_get_irq() returns an error code, but the tegra-devfreq driver ignores it and always returns -ENODEV. This is not correct, and prevents -EPROBE_DEFER from being propagated properly. Notice that platform_get_irq() no longer returns 0 on error: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=e330b9a6bb35dc7097a4f02cb1ae7b6f96df92af Print and propagate the return value of platform_get_irq on failure. Reviewed-by: Chanwoo Choi Signed-off-by: Gustavo A. R. Silva Signed-off-by: MyungJoo Ham --- drivers/devfreq/tegra-devfreq.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/devfreq/tegra-devfreq.c b/drivers/devfreq/tegra-devfreq.c index 214fff96fa4a..ae712159246f 100644 --- a/drivers/devfreq/tegra-devfreq.c +++ b/drivers/devfreq/tegra-devfreq.c @@ -688,9 +688,9 @@ static int tegra_devfreq_probe(struct platform_device *pdev) } irq = platform_get_irq(pdev, 0); - if (irq <= 0) { - dev_err(&pdev->dev, "Failed to get IRQ\n"); - return -ENODEV; + if (irq < 0) { + dev_err(&pdev->dev, "Failed to get IRQ: %d\n", irq); + return irq; } platform_set_drvdata(pdev, tegra); -- cgit v1.2.3-59-g8ed1b From 37d644aa01c092686af8a96f34df93c74e55b480 Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Mon, 3 Jul 2017 15:40:04 +0530 Subject: PM / devfreq: constify attribute_group structures. attribute_groups are not supposed to change at runtime. All functions working with attribute_groups provided by work with const attribute_group. So mark the non-const structs as const. File size before: text data bss dec hex filename 621 176 0 797 31d drivers/devfreq/governor_userspace.o File size After adding 'const': text data bss dec hex filename 670 144 0 814 32e drivers/devfreq/governor_userspace.o Signed-off-by: Arvind Yadav Reviewed-by: Chanwoo Choi Signed-off-by: MyungJoo Ham --- drivers/devfreq/governor_userspace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/devfreq/governor_userspace.c b/drivers/devfreq/governor_userspace.c index 176976068bcd..77028c27593c 100644 --- a/drivers/devfreq/governor_userspace.c +++ b/drivers/devfreq/governor_userspace.c @@ -86,7 +86,7 @@ static struct attribute *dev_entries[] = { &dev_attr_set_freq.attr, NULL, }; -static struct attribute_group dev_attr_group = { +static const struct attribute_group dev_attr_group = { .name = "userspace", .attrs = dev_entries, }; -- cgit v1.2.3-59-g8ed1b From df8f4c6c0275216498340a64c7d2674377bd3e78 Mon Sep 17 00:00:00 2001 From: Ulrich Hecht Date: Thu, 27 Apr 2017 16:37:43 +0200 Subject: dt-bindings: pwm: Add R-Car M3-W device tree bindings Add device tree bindings for the PWM controller found on R-Car M3-W SoCs. Signed-off-by: Ulrich Hecht Reviewed-by: Geert Uytterhoeven Reviewed-by: Simon Horman Acked-by: Rob Herring Signed-off-by: Thierry Reding --- Documentation/devicetree/bindings/pwm/renesas,pwm-rcar.txt | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/pwm/renesas,pwm-rcar.txt b/Documentation/devicetree/bindings/pwm/renesas,pwm-rcar.txt index d6de64335022..7e94b802395d 100644 --- a/Documentation/devicetree/bindings/pwm/renesas,pwm-rcar.txt +++ b/Documentation/devicetree/bindings/pwm/renesas,pwm-rcar.txt @@ -8,6 +8,7 @@ Required Properties: - "renesas,pwm-r8a7791": for R-Car M2-W - "renesas,pwm-r8a7794": for R-Car E2 - "renesas,pwm-r8a7795": for R-Car H3 + - "renesas,pwm-r8a7796": for R-Car M3-W - reg: base address and length of the registers block for the PWM. - #pwm-cells: should be 2. See pwm.txt in this directory for a description of the cells format. -- cgit v1.2.3-59-g8ed1b From d7f673d8a0776f3f791fd795b409060ba808b62a Mon Sep 17 00:00:00 2001 From: Fabrice GASNIER Date: Wed, 14 Jun 2017 17:13:16 +0200 Subject: dt-bindings: pwm: Update STM32 timers clock names Clock name has been updated during driver/DT binding review: https://lkml.org/lkml/2016/12/13/718 Update DT binding doc to reflect this. Fixes: cd9a99c2f8e8 (dt-bindings: pwm: Add STM32 bindings) Signed-off-by: Fabrice Gasnier Acked-by: Rob Herring Signed-off-by: Thierry Reding --- Documentation/devicetree/bindings/pwm/pwm-stm32.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/pwm/pwm-stm32.txt b/Documentation/devicetree/bindings/pwm/pwm-stm32.txt index 6dd040363e5e..3e6d55018d7a 100644 --- a/Documentation/devicetree/bindings/pwm/pwm-stm32.txt +++ b/Documentation/devicetree/bindings/pwm/pwm-stm32.txt @@ -24,7 +24,7 @@ Example: compatible = "st,stm32-timers"; reg = <0x40010000 0x400>; clocks = <&rcc 0 160>; - clock-names = "clk_int"; + clock-names = "int"; pwm { compatible = "st,stm32-pwm"; -- cgit v1.2.3-59-g8ed1b From 0e1921dcd825004551bd4dd2df99697641434a52 Mon Sep 17 00:00:00 2001 From: Markus Elfring Date: Tue, 16 May 2017 11:40:09 +0200 Subject: pwm: bfin: Remove unneeded error message Omit an extra message for a memory allocation failure in this function. This issue was detected by using the Coccinelle software. Link: http://events.linuxfoundation.org/sites/events/files/slides/LCJ16-Refactor_Strings-WSang_0.pdf Signed-off-by: Markus Elfring Signed-off-by: Thierry Reding --- drivers/pwm/pwm-bfin.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/pwm/pwm-bfin.c b/drivers/pwm/pwm-bfin.c index d2ed0a2a18e8..a9a88137f2cb 100644 --- a/drivers/pwm/pwm-bfin.c +++ b/drivers/pwm/pwm-bfin.c @@ -118,10 +118,8 @@ static int bfin_pwm_probe(struct platform_device *pdev) int ret; pwm = devm_kzalloc(&pdev->dev, sizeof(*pwm), GFP_KERNEL); - if (!pwm) { - dev_err(&pdev->dev, "failed to allocate memory\n"); + if (!pwm) return -ENOMEM; - } platform_set_drvdata(pdev, pwm); -- cgit v1.2.3-59-g8ed1b From c571123c8a94cfbc88e70be4e8883529181417ce Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sat, 17 Jun 2017 12:26:44 -0300 Subject: pwm: Standardize document format Each text file under Documentation follows a different format. Some don't even have titles! Change its representation to follow the adopted standard, using ReST markup for it to be parseable by Sphinx: - mark document title; - mark literal blocks; - better format the parameters. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Thierry Reding --- Documentation/pwm.txt | 46 ++++++++++++++++++++++++++++------------------ 1 file changed, 28 insertions(+), 18 deletions(-) diff --git a/Documentation/pwm.txt b/Documentation/pwm.txt index 789b27c6ec99..8fbf0aa3ba2d 100644 --- a/Documentation/pwm.txt +++ b/Documentation/pwm.txt @@ -1,4 +1,6 @@ +====================================== Pulse Width Modulation (PWM) interface +====================================== This provides an overview about the Linux PWM interface @@ -16,7 +18,7 @@ Users of the legacy PWM API use unique IDs to refer to PWM devices. Instead of referring to a PWM device via its unique ID, board setup code should instead register a static mapping that can be used to match PWM -consumers to providers, as given in the following example: +consumers to providers, as given in the following example:: static struct pwm_lookup board_pwm_lookup[] = { PWM_LOOKUP("tegra-pwm", 0, "pwm-backlight", NULL, @@ -40,9 +42,9 @@ New users should use the pwm_get() function and pass to it the consumer device or a consumer name. pwm_put() is used to free the PWM device. Managed variants of these functions, devm_pwm_get() and devm_pwm_put(), also exist. -After being requested, a PWM has to be configured using: +After being requested, a PWM has to be configured using:: -int pwm_apply_state(struct pwm_device *pwm, struct pwm_state *state); + int pwm_apply_state(struct pwm_device *pwm, struct pwm_state *state); This API controls both the PWM period/duty_cycle config and the enable/disable state. @@ -72,11 +74,14 @@ interface is provided to use the PWMs from userspace. It is exposed at pwmchipN, where N is the base of the PWM chip. Inside the directory you will find: -npwm - The number of PWM channels this chip supports (read-only). + npwm + The number of PWM channels this chip supports (read-only). -export - Exports a PWM channel for use with sysfs (write-only). + export + Exports a PWM channel for use with sysfs (write-only). -unexport - Unexports a PWM channel from sysfs (write-only). + unexport + Unexports a PWM channel from sysfs (write-only). The PWM channels are numbered using a per-chip index from 0 to npwm-1. @@ -84,21 +89,26 @@ When a PWM channel is exported a pwmX directory will be created in the pwmchipN directory it is associated with, where X is the number of the channel that was exported. The following properties will then be available: -period - The total period of the PWM signal (read/write). - Value is in nanoseconds and is the sum of the active and inactive - time of the PWM. + period + The total period of the PWM signal (read/write). + Value is in nanoseconds and is the sum of the active and inactive + time of the PWM. -duty_cycle - The active time of the PWM signal (read/write). - Value is in nanoseconds and must be less than the period. + duty_cycle + The active time of the PWM signal (read/write). + Value is in nanoseconds and must be less than the period. -polarity - Changes the polarity of the PWM signal (read/write). - Writes to this property only work if the PWM chip supports changing - the polarity. The polarity can only be changed if the PWM is not - enabled. Value is the string "normal" or "inversed". + polarity + Changes the polarity of the PWM signal (read/write). + Writes to this property only work if the PWM chip supports changing + the polarity. The polarity can only be changed if the PWM is not + enabled. Value is the string "normal" or "inversed". -enable - Enable/disable the PWM signal (read/write). - 0 - disabled - 1 - enabled + enable + Enable/disable the PWM signal (read/write). + + - 0 - disabled + - 1 - enabled Implementing a PWM driver ------------------------- -- cgit v1.2.3-59-g8ed1b From 93c292ef3cbb46db78853763fc4d9a5b9dfb97d5 Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Tue, 23 May 2017 18:05:03 +0200 Subject: pwm: Silently error out on EPROBE_DEFER MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In of_pwm_get(), if we fail to get the PWM chip due to probe deferal, we shouldn't print an error message. Just be silent in this case. Signed-off-by: Jerome Brunet Reviewed-by: Andreas Färber Signed-off-by: Thierry Reding --- drivers/pwm/core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c index a0860b30bd93..1581f6ab1b1f 100644 --- a/drivers/pwm/core.c +++ b/drivers/pwm/core.c @@ -678,7 +678,9 @@ struct pwm_device *of_pwm_get(struct device_node *np, const char *con_id) pc = of_node_to_pwmchip(args.np); if (IS_ERR(pc)) { - pr_err("%s(): PWM chip not found\n", __func__); + if (PTR_ERR(pc) != -EPROBE_DEFER) + pr_err("%s(): PWM chip not found\n", __func__); + pwm = ERR_CAST(pc); goto put; } -- cgit v1.2.3-59-g8ed1b From c034a6fda0179a85cd571c386ed6748188b0a79c Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Tue, 13 Jun 2017 15:26:41 +0530 Subject: pwm: hibvt: Constify hibvt_pwm_ops File size before: text data bss dec hex filename 1510 296 0 1806 70e drivers/pwm/pwm-hibvt.o File size After adding 'const': text data bss dec hex filename 1606 192 0 1798 706 drivers/pwm/pwm-hibvt.o Signed-off-by: Arvind Yadav Signed-off-by: Thierry Reding --- drivers/pwm/pwm-hibvt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pwm/pwm-hibvt.c b/drivers/pwm/pwm-hibvt.c index d0e8f8542626..8dadc58d6cdf 100644 --- a/drivers/pwm/pwm-hibvt.c +++ b/drivers/pwm/pwm-hibvt.c @@ -165,7 +165,7 @@ static int hibvt_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, return 0; } -static struct pwm_ops hibvt_pwm_ops = { +static const struct pwm_ops hibvt_pwm_ops = { .get_state = hibvt_pwm_get_state, .apply = hibvt_pwm_apply, -- cgit v1.2.3-59-g8ed1b From 93e0dfb2c52f9cb7a7899156475b4e7b0bee7de3 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Tue, 30 May 2017 21:32:07 +0200 Subject: pwm: sun4i: Improve hardware read out Implement .get_state instead of only reading the polarity at probe time. This allows to get the proper state, period and duty cycle. Signed-off-by: Alexandre Belloni Reviewed-by: Chen-Yu Tsai Acked-by: Maxime Ripard Signed-off-by: Thierry Reding --- drivers/pwm/pwm-sun4i.c | 65 ++++++++++++++++++++++++++++++++++--------------- 1 file changed, 46 insertions(+), 19 deletions(-) diff --git a/drivers/pwm/pwm-sun4i.c b/drivers/pwm/pwm-sun4i.c index 1284ffa05921..175a69245a8a 100644 --- a/drivers/pwm/pwm-sun4i.c +++ b/drivers/pwm/pwm-sun4i.c @@ -44,6 +44,10 @@ #define PWM_DTY_MASK GENMASK(15, 0) +#define PWM_REG_PRD(reg) ((((reg) >> 16) & PWM_PRD_MASK) + 1) +#define PWM_REG_DTY(reg) ((reg) & PWM_DTY_MASK) +#define PWM_REG_PRESCAL(reg, chan) (((reg) >> ((chan) * PWMCH_OFFSET)) & PWM_PRESCAL_MASK) + #define BIT_CH(bit, chan) ((bit) << ((chan) * PWMCH_OFFSET)) static const u32 prescaler_table[] = { @@ -96,6 +100,46 @@ static inline void sun4i_pwm_writel(struct sun4i_pwm_chip *chip, writel(val, chip->base + offset); } +static void sun4i_pwm_get_state(struct pwm_chip *chip, + struct pwm_device *pwm, + struct pwm_state *state) +{ + struct sun4i_pwm_chip *sun4i_pwm = to_sun4i_pwm_chip(chip); + u64 clk_rate, tmp; + u32 val; + unsigned int prescaler; + + clk_rate = clk_get_rate(sun4i_pwm->clk); + + val = sun4i_pwm_readl(sun4i_pwm, PWM_CTRL_REG); + + if ((val == PWM_PRESCAL_MASK) && sun4i_pwm->data->has_prescaler_bypass) + prescaler = 1; + else + prescaler = prescaler_table[PWM_REG_PRESCAL(val, pwm->hwpwm)]; + + if (prescaler == 0) + return; + + if (val & BIT_CH(PWM_ACT_STATE, pwm->hwpwm)) + state->polarity = PWM_POLARITY_NORMAL; + else + state->polarity = PWM_POLARITY_INVERSED; + + if (val & BIT_CH(PWM_CLK_GATING | PWM_EN, pwm->hwpwm)) + state->enabled = true; + else + state->enabled = false; + + val = sun4i_pwm_readl(sun4i_pwm, PWM_CH_PRD(pwm->hwpwm)); + + tmp = prescaler * NSEC_PER_SEC * PWM_REG_DTY(val); + state->duty_cycle = DIV_ROUND_CLOSEST_ULL(tmp, clk_rate); + + tmp = prescaler * NSEC_PER_SEC * PWM_REG_PRD(val); + state->period = DIV_ROUND_CLOSEST_ULL(tmp, clk_rate); +} + static int sun4i_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, int duty_ns, int period_ns) { @@ -257,6 +301,7 @@ static const struct pwm_ops sun4i_pwm_ops = { .set_polarity = sun4i_pwm_set_polarity, .enable = sun4i_pwm_enable, .disable = sun4i_pwm_disable, + .get_state = sun4i_pwm_get_state, .owner = THIS_MODULE, }; @@ -316,8 +361,7 @@ static int sun4i_pwm_probe(struct platform_device *pdev) { struct sun4i_pwm_chip *pwm; struct resource *res; - u32 val; - int i, ret; + int ret; const struct of_device_id *match; match = of_match_device(sun4i_pwm_dt_ids, &pdev->dev); @@ -353,24 +397,7 @@ static int sun4i_pwm_probe(struct platform_device *pdev) platform_set_drvdata(pdev, pwm); - ret = clk_prepare_enable(pwm->clk); - if (ret) { - dev_err(&pdev->dev, "failed to enable PWM clock\n"); - goto clk_error; - } - - val = sun4i_pwm_readl(pwm, PWM_CTRL_REG); - for (i = 0; i < pwm->chip.npwm; i++) - if (!(val & BIT_CH(PWM_ACT_STATE, i))) - pwm_set_polarity(&pwm->chip.pwms[i], - PWM_POLARITY_INVERSED); - clk_disable_unprepare(pwm->clk); - return 0; - -clk_error: - pwmchip_remove(&pwm->chip); - return ret; } static int sun4i_pwm_remove(struct platform_device *pdev) -- cgit v1.2.3-59-g8ed1b From c32c5c50d4fe156da1ecd32f2a16c1b8fcfba392 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Tue, 30 May 2017 21:32:08 +0200 Subject: pwm: sun4i: Switch to atomic PWM Switch the driver to atomic PWM. This makes it easier to wait a proper amount of time when changing the duty cycle before disabling the channel (main use case is switching the duty cycle to 0 before disabling). Signed-off-by: Alexandre Belloni Acked-by: Maxime Ripard Signed-off-by: Thierry Reding --- drivers/pwm/pwm-sun4i.c | 166 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 166 insertions(+) diff --git a/drivers/pwm/pwm-sun4i.c b/drivers/pwm/pwm-sun4i.c index 175a69245a8a..cd8737d0804f 100644 --- a/drivers/pwm/pwm-sun4i.c +++ b/drivers/pwm/pwm-sun4i.c @@ -8,8 +8,10 @@ #include #include +#include #include #include +#include #include #include #include @@ -81,6 +83,8 @@ struct sun4i_pwm_chip { void __iomem *base; spinlock_t ctrl_lock; const struct sun4i_pwm_data *data; + unsigned long next_period[2]; + bool needs_delay[2]; }; static inline struct sun4i_pwm_chip *to_sun4i_pwm_chip(struct pwm_chip *chip) @@ -140,6 +144,167 @@ static void sun4i_pwm_get_state(struct pwm_chip *chip, state->period = DIV_ROUND_CLOSEST_ULL(tmp, clk_rate); } +static int sun4i_pwm_calculate(struct sun4i_pwm_chip *sun4i_pwm, + struct pwm_state *state, + u32 *dty, u32 *prd, unsigned int *prsclr) +{ + u64 clk_rate, div = 0; + unsigned int pval, prescaler = 0; + + clk_rate = clk_get_rate(sun4i_pwm->clk); + + if (sun4i_pwm->data->has_prescaler_bypass) { + /* First, test without any prescaler when available */ + prescaler = PWM_PRESCAL_MASK; + pval = 1; + /* + * When not using any prescaler, the clock period in nanoseconds + * is not an integer so round it half up instead of + * truncating to get less surprising values. + */ + div = clk_rate * state->period + NSEC_PER_SEC / 2; + do_div(div, NSEC_PER_SEC); + if (div - 1 > PWM_PRD_MASK) + prescaler = 0; + } + + if (prescaler == 0) { + /* Go up from the first divider */ + for (prescaler = 0; prescaler < PWM_PRESCAL_MASK; prescaler++) { + if (!prescaler_table[prescaler]) + continue; + pval = prescaler_table[prescaler]; + div = clk_rate; + do_div(div, pval); + div = div * state->period; + do_div(div, NSEC_PER_SEC); + if (div - 1 <= PWM_PRD_MASK) + break; + } + + if (div - 1 > PWM_PRD_MASK) + return -EINVAL; + } + + *prd = div; + div *= state->duty_cycle; + do_div(div, state->period); + *dty = div; + *prsclr = prescaler; + + div = (u64)pval * NSEC_PER_SEC * *prd; + state->period = DIV_ROUND_CLOSEST_ULL(div, clk_rate); + + div = (u64)pval * NSEC_PER_SEC * *dty; + state->duty_cycle = DIV_ROUND_CLOSEST_ULL(div, clk_rate); + + return 0; +} + +static int sun4i_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, + struct pwm_state *state) +{ + struct sun4i_pwm_chip *sun4i_pwm = to_sun4i_pwm_chip(chip); + struct pwm_state cstate; + u32 ctrl; + int ret; + unsigned int delay_us; + unsigned long now; + + pwm_get_state(pwm, &cstate); + + if (!cstate.enabled) { + ret = clk_prepare_enable(sun4i_pwm->clk); + if (ret) { + dev_err(chip->dev, "failed to enable PWM clock\n"); + return ret; + } + } + + spin_lock(&sun4i_pwm->ctrl_lock); + ctrl = sun4i_pwm_readl(sun4i_pwm, PWM_CTRL_REG); + + if ((cstate.period != state->period) || + (cstate.duty_cycle != state->duty_cycle)) { + u32 period, duty, val; + unsigned int prescaler; + + ret = sun4i_pwm_calculate(sun4i_pwm, state, + &duty, &period, &prescaler); + if (ret) { + dev_err(chip->dev, "period exceeds the maximum value\n"); + spin_unlock(&sun4i_pwm->ctrl_lock); + if (!cstate.enabled) + clk_disable_unprepare(sun4i_pwm->clk); + return ret; + } + + if (PWM_REG_PRESCAL(ctrl, pwm->hwpwm) != prescaler) { + /* Prescaler changed, the clock has to be gated */ + ctrl &= ~BIT_CH(PWM_CLK_GATING, pwm->hwpwm); + sun4i_pwm_writel(sun4i_pwm, ctrl, PWM_CTRL_REG); + + ctrl &= ~BIT_CH(PWM_PRESCAL_MASK, pwm->hwpwm); + ctrl |= BIT_CH(prescaler, pwm->hwpwm); + } + + val = (duty & PWM_DTY_MASK) | PWM_PRD(period); + sun4i_pwm_writel(sun4i_pwm, val, PWM_CH_PRD(pwm->hwpwm)); + sun4i_pwm->next_period[pwm->hwpwm] = jiffies + + usecs_to_jiffies(cstate.period / 1000 + 1); + sun4i_pwm->needs_delay[pwm->hwpwm] = true; + } + + if (state->polarity != PWM_POLARITY_NORMAL) + ctrl &= ~BIT_CH(PWM_ACT_STATE, pwm->hwpwm); + else + ctrl |= BIT_CH(PWM_ACT_STATE, pwm->hwpwm); + + ctrl |= BIT_CH(PWM_CLK_GATING, pwm->hwpwm); + if (state->enabled) { + ctrl |= BIT_CH(PWM_EN, pwm->hwpwm); + } else if (!sun4i_pwm->needs_delay[pwm->hwpwm]) { + ctrl &= ~BIT_CH(PWM_EN, pwm->hwpwm); + ctrl &= ~BIT_CH(PWM_CLK_GATING, pwm->hwpwm); + } + + sun4i_pwm_writel(sun4i_pwm, ctrl, PWM_CTRL_REG); + + spin_unlock(&sun4i_pwm->ctrl_lock); + + if (state->enabled) + return 0; + + if (!sun4i_pwm->needs_delay[pwm->hwpwm]) { + clk_disable_unprepare(sun4i_pwm->clk); + return 0; + } + + /* We need a full period to elapse before disabling the channel. */ + now = jiffies; + if (sun4i_pwm->needs_delay[pwm->hwpwm] && + time_before(now, sun4i_pwm->next_period[pwm->hwpwm])) { + delay_us = jiffies_to_usecs(sun4i_pwm->next_period[pwm->hwpwm] - + now); + if ((delay_us / 500) > MAX_UDELAY_MS) + msleep(delay_us / 1000 + 1); + else + usleep_range(delay_us, delay_us * 2); + } + sun4i_pwm->needs_delay[pwm->hwpwm] = false; + + spin_lock(&sun4i_pwm->ctrl_lock); + ctrl = sun4i_pwm_readl(sun4i_pwm, PWM_CTRL_REG); + ctrl &= ~BIT_CH(PWM_CLK_GATING, pwm->hwpwm); + ctrl &= ~BIT_CH(PWM_EN, pwm->hwpwm); + sun4i_pwm_writel(sun4i_pwm, ctrl, PWM_CTRL_REG); + spin_unlock(&sun4i_pwm->ctrl_lock); + + clk_disable_unprepare(sun4i_pwm->clk); + + return 0; +} + static int sun4i_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, int duty_ns, int period_ns) { @@ -301,6 +466,7 @@ static const struct pwm_ops sun4i_pwm_ops = { .set_polarity = sun4i_pwm_set_polarity, .enable = sun4i_pwm_enable, .disable = sun4i_pwm_disable, + .apply = sun4i_pwm_apply, .get_state = sun4i_pwm_get_state, .owner = THIS_MODULE, }; -- cgit v1.2.3-59-g8ed1b From a054c4d68408cdbb260ba9384415fb53edb29d7a Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Tue, 30 May 2017 21:32:09 +0200 Subject: pwm: sun4i: Drop legacy callbacks Remove the legacy callbacks .enable(), .disable(), .set_polarity() and .config(). Signed-off-by: Alexandre Belloni Acked-by: Chen-Yu Tsai Acked-by: Maxime Ripard Signed-off-by: Thierry Reding --- drivers/pwm/pwm-sun4i.c | 160 ------------------------------------------------ 1 file changed, 160 deletions(-) diff --git a/drivers/pwm/pwm-sun4i.c b/drivers/pwm/pwm-sun4i.c index cd8737d0804f..6d23f1d1c9b7 100644 --- a/drivers/pwm/pwm-sun4i.c +++ b/drivers/pwm/pwm-sun4i.c @@ -305,167 +305,7 @@ static int sun4i_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, return 0; } -static int sun4i_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm, - int duty_ns, int period_ns) -{ - struct sun4i_pwm_chip *sun4i_pwm = to_sun4i_pwm_chip(chip); - u32 prd, dty, val, clk_gate; - u64 clk_rate, div = 0; - unsigned int prescaler = 0; - int err; - - clk_rate = clk_get_rate(sun4i_pwm->clk); - - if (sun4i_pwm->data->has_prescaler_bypass) { - /* First, test without any prescaler when available */ - prescaler = PWM_PRESCAL_MASK; - /* - * When not using any prescaler, the clock period in nanoseconds - * is not an integer so round it half up instead of - * truncating to get less surprising values. - */ - div = clk_rate * period_ns + NSEC_PER_SEC / 2; - do_div(div, NSEC_PER_SEC); - if (div - 1 > PWM_PRD_MASK) - prescaler = 0; - } - - if (prescaler == 0) { - /* Go up from the first divider */ - for (prescaler = 0; prescaler < PWM_PRESCAL_MASK; prescaler++) { - if (!prescaler_table[prescaler]) - continue; - div = clk_rate; - do_div(div, prescaler_table[prescaler]); - div = div * period_ns; - do_div(div, NSEC_PER_SEC); - if (div - 1 <= PWM_PRD_MASK) - break; - } - - if (div - 1 > PWM_PRD_MASK) { - dev_err(chip->dev, "period exceeds the maximum value\n"); - return -EINVAL; - } - } - - prd = div; - div *= duty_ns; - do_div(div, period_ns); - dty = div; - - err = clk_prepare_enable(sun4i_pwm->clk); - if (err) { - dev_err(chip->dev, "failed to enable PWM clock\n"); - return err; - } - - spin_lock(&sun4i_pwm->ctrl_lock); - val = sun4i_pwm_readl(sun4i_pwm, PWM_CTRL_REG); - - if (sun4i_pwm->data->has_rdy && (val & PWM_RDY(pwm->hwpwm))) { - spin_unlock(&sun4i_pwm->ctrl_lock); - clk_disable_unprepare(sun4i_pwm->clk); - return -EBUSY; - } - - clk_gate = val & BIT_CH(PWM_CLK_GATING, pwm->hwpwm); - if (clk_gate) { - val &= ~BIT_CH(PWM_CLK_GATING, pwm->hwpwm); - sun4i_pwm_writel(sun4i_pwm, val, PWM_CTRL_REG); - } - - val = sun4i_pwm_readl(sun4i_pwm, PWM_CTRL_REG); - val &= ~BIT_CH(PWM_PRESCAL_MASK, pwm->hwpwm); - val |= BIT_CH(prescaler, pwm->hwpwm); - sun4i_pwm_writel(sun4i_pwm, val, PWM_CTRL_REG); - - val = (dty & PWM_DTY_MASK) | PWM_PRD(prd); - sun4i_pwm_writel(sun4i_pwm, val, PWM_CH_PRD(pwm->hwpwm)); - - if (clk_gate) { - val = sun4i_pwm_readl(sun4i_pwm, PWM_CTRL_REG); - val |= clk_gate; - sun4i_pwm_writel(sun4i_pwm, val, PWM_CTRL_REG); - } - - spin_unlock(&sun4i_pwm->ctrl_lock); - clk_disable_unprepare(sun4i_pwm->clk); - - return 0; -} - -static int sun4i_pwm_set_polarity(struct pwm_chip *chip, struct pwm_device *pwm, - enum pwm_polarity polarity) -{ - struct sun4i_pwm_chip *sun4i_pwm = to_sun4i_pwm_chip(chip); - u32 val; - int ret; - - ret = clk_prepare_enable(sun4i_pwm->clk); - if (ret) { - dev_err(chip->dev, "failed to enable PWM clock\n"); - return ret; - } - - spin_lock(&sun4i_pwm->ctrl_lock); - val = sun4i_pwm_readl(sun4i_pwm, PWM_CTRL_REG); - - if (polarity != PWM_POLARITY_NORMAL) - val &= ~BIT_CH(PWM_ACT_STATE, pwm->hwpwm); - else - val |= BIT_CH(PWM_ACT_STATE, pwm->hwpwm); - - sun4i_pwm_writel(sun4i_pwm, val, PWM_CTRL_REG); - - spin_unlock(&sun4i_pwm->ctrl_lock); - clk_disable_unprepare(sun4i_pwm->clk); - - return 0; -} - -static int sun4i_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm) -{ - struct sun4i_pwm_chip *sun4i_pwm = to_sun4i_pwm_chip(chip); - u32 val; - int ret; - - ret = clk_prepare_enable(sun4i_pwm->clk); - if (ret) { - dev_err(chip->dev, "failed to enable PWM clock\n"); - return ret; - } - - spin_lock(&sun4i_pwm->ctrl_lock); - val = sun4i_pwm_readl(sun4i_pwm, PWM_CTRL_REG); - val |= BIT_CH(PWM_EN, pwm->hwpwm); - val |= BIT_CH(PWM_CLK_GATING, pwm->hwpwm); - sun4i_pwm_writel(sun4i_pwm, val, PWM_CTRL_REG); - spin_unlock(&sun4i_pwm->ctrl_lock); - - return 0; -} - -static void sun4i_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm) -{ - struct sun4i_pwm_chip *sun4i_pwm = to_sun4i_pwm_chip(chip); - u32 val; - - spin_lock(&sun4i_pwm->ctrl_lock); - val = sun4i_pwm_readl(sun4i_pwm, PWM_CTRL_REG); - val &= ~BIT_CH(PWM_EN, pwm->hwpwm); - val &= ~BIT_CH(PWM_CLK_GATING, pwm->hwpwm); - sun4i_pwm_writel(sun4i_pwm, val, PWM_CTRL_REG); - spin_unlock(&sun4i_pwm->ctrl_lock); - - clk_disable_unprepare(sun4i_pwm->clk); -} - static const struct pwm_ops sun4i_pwm_ops = { - .config = sun4i_pwm_config, - .set_polarity = sun4i_pwm_set_polarity, - .enable = sun4i_pwm_enable, - .disable = sun4i_pwm_disable, .apply = sun4i_pwm_apply, .get_state = sun4i_pwm_get_state, .owner = THIS_MODULE, -- cgit v1.2.3-59-g8ed1b From d396b20a1e88ca2cabf7ec99c6c2138902aff1f3 Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Thu, 8 Jun 2017 14:24:15 +0200 Subject: pwm: meson: Add compatible for the gxbb ao PWMs On the gxbb (and gxl) family, the PWMs of the AO domain require a specific compatible because the possible input clocks are different from the EE PWMs input clocks. Since the number of possible input clocks is also different, the 'num_parents' field is added to all the Meson PWM data. Acked-by: Neil Armstrong Signed-off-by: Jerome Brunet Reviewed-by: Kevin Hilman Signed-off-by: Thierry Reding --- drivers/pwm/pwm-meson.c | 32 +++++++++++++++++++++++++++++--- 1 file changed, 29 insertions(+), 3 deletions(-) diff --git a/drivers/pwm/pwm-meson.c b/drivers/pwm/pwm-meson.c index 045ef9fa6fe3..defc27d880f3 100644 --- a/drivers/pwm/pwm-meson.c +++ b/drivers/pwm/pwm-meson.c @@ -103,6 +103,7 @@ struct meson_pwm_channel { struct meson_pwm_data { const char * const *parent_names; + unsigned int num_parents; }; struct meson_pwm { @@ -381,6 +382,7 @@ static const char * const pwm_meson8b_parent_names[] = { static const struct meson_pwm_data pwm_meson8b_data = { .parent_names = pwm_meson8b_parent_names, + .num_parents = ARRAY_SIZE(pwm_meson8b_parent_names), }; static const char * const pwm_gxbb_parent_names[] = { @@ -389,11 +391,35 @@ static const char * const pwm_gxbb_parent_names[] = { static const struct meson_pwm_data pwm_gxbb_data = { .parent_names = pwm_gxbb_parent_names, + .num_parents = ARRAY_SIZE(pwm_gxbb_parent_names), +}; + +/* + * Only the 2 first inputs of the GXBB AO PWMs are valid + * The last 2 are grounded + */ +static const char * const pwm_gxbb_ao_parent_names[] = { + "xtal", "clk81" +}; + +static const struct meson_pwm_data pwm_gxbb_ao_data = { + .parent_names = pwm_gxbb_ao_parent_names, + .num_parents = ARRAY_SIZE(pwm_gxbb_ao_parent_names), }; static const struct of_device_id meson_pwm_matches[] = { - { .compatible = "amlogic,meson8b-pwm", .data = &pwm_meson8b_data }, - { .compatible = "amlogic,meson-gxbb-pwm", .data = &pwm_gxbb_data }, + { + .compatible = "amlogic,meson8b-pwm", + .data = &pwm_meson8b_data + }, + { + .compatible = "amlogic,meson-gxbb-pwm", + .data = &pwm_gxbb_data + }, + { + .compatible = "amlogic,meson-gxbb-ao-pwm", + .data = &pwm_gxbb_ao_data + }, {}, }; MODULE_DEVICE_TABLE(of, meson_pwm_matches); @@ -417,7 +443,7 @@ static int meson_pwm_init_channels(struct meson_pwm *meson, init.ops = &clk_mux_ops; init.flags = CLK_IS_BASIC; init.parent_names = meson->data->parent_names; - init.num_parents = 1 << MISC_CLK_SEL_WIDTH; + init.num_parents = meson->data->num_parents; channel->mux.reg = meson->base + REG_MISC_AB; channel->mux.shift = mux_reg_shifts[i]; -- cgit v1.2.3-59-g8ed1b From 6ede2b7df92f4f8da1abfa831a038688fcf409ea Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 5 Jul 2017 13:02:27 -0700 Subject: ALSA: opl4: Move inline before return type Make the code like the rest of the kernel. Signed-off-by: Joe Perches Acked-by: Clemens Ladisch Signed-off-by: Takashi Iwai --- sound/drivers/opl4/opl4_lib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/drivers/opl4/opl4_lib.c b/sound/drivers/opl4/opl4_lib.c index bc345d564f8d..db76a5bf2bd2 100644 --- a/sound/drivers/opl4/opl4_lib.c +++ b/sound/drivers/opl4/opl4_lib.c @@ -29,7 +29,7 @@ MODULE_AUTHOR("Clemens Ladisch "); MODULE_DESCRIPTION("OPL4 driver"); MODULE_LICENSE("GPL"); -static void inline snd_opl4_wait(struct snd_opl4 *opl4) +static inline void snd_opl4_wait(struct snd_opl4 *opl4) { int timeout = 10; while ((inb(opl4->fm_port) & OPL4_STATUS_BUSY) && --timeout > 0) -- cgit v1.2.3-59-g8ed1b From f35157417215ec138c920320c746fdb3e04ef1d5 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 4 Jul 2017 17:25:02 +0100 Subject: Provide a function to create a NUL-terminated string from unterminated data Provide a function, kmemdup_nul(), that will create a NUL-terminated string from an unterminated character array where the length is known in advance. This is better than kstrndup() in situations where we already know the string length as the strnlen() in kstrndup() is superfluous. Signed-off-by: David Howells Signed-off-by: Al Viro --- include/linux/string.h | 1 + mm/util.c | 24 ++++++++++++++++++++++++ 2 files changed, 25 insertions(+) diff --git a/include/linux/string.h b/include/linux/string.h index 537918f8a98e..3dd944cfe171 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -131,6 +131,7 @@ extern char *kstrdup(const char *s, gfp_t gfp) __malloc; extern const char *kstrdup_const(const char *s, gfp_t gfp); extern char *kstrndup(const char *s, size_t len, gfp_t gfp); extern void *kmemdup(const void *src, size_t len, gfp_t gfp); +extern char *kmemdup_nul(const char *s, size_t len, gfp_t gfp); extern char **argv_split(gfp_t gfp, const char *str, int *argcp); extern void argv_free(char **argv); diff --git a/mm/util.c b/mm/util.c index 26be6407abd7..21ddf90f883d 100644 --- a/mm/util.c +++ b/mm/util.c @@ -83,6 +83,8 @@ EXPORT_SYMBOL(kstrdup_const); * @s: the string to duplicate * @max: read at most @max chars from @s * @gfp: the GFP mask used in the kmalloc() call when allocating memory + * + * Note: Use kmemdup_nul() instead if the size is known exactly. */ char *kstrndup(const char *s, size_t max, gfp_t gfp) { @@ -120,6 +122,28 @@ void *kmemdup(const void *src, size_t len, gfp_t gfp) } EXPORT_SYMBOL(kmemdup); +/** + * kmemdup_nul - Create a NUL-terminated string from unterminated data + * @s: The data to stringify + * @len: The size of the data + * @gfp: the GFP mask used in the kmalloc() call when allocating memory + */ +char *kmemdup_nul(const char *s, size_t len, gfp_t gfp) +{ + char *buf; + + if (!s) + return NULL; + + buf = kmalloc_track_caller(len + 1, gfp); + if (buf) { + memcpy(buf, s, len); + buf[len] = '\0'; + } + return buf; +} +EXPORT_SYMBOL(kmemdup_nul); + /** * memdup_user - duplicate memory region from user space * -- cgit v1.2.3-59-g8ed1b From dd111b31e951c4ffb3a525b51b11d240118693c1 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 4 Jul 2017 17:25:09 +0100 Subject: VFS: Clean up whitespace in fs/namespace.c and fs/super.c Clean up line terminal whitespace in fs/namespace.c and fs/super.c. Signed-off-by: David Howells Signed-off-by: Al Viro --- fs/namespace.c | 4 ++-- fs/super.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/namespace.c b/fs/namespace.c index 5a4438445bf7..544ab84642eb 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1656,7 +1656,7 @@ out_unlock: namespace_unlock(); } -/* +/* * Is the caller allowed to modify his namespace? */ static inline bool may_mount(void) @@ -2210,7 +2210,7 @@ static int do_loopback(struct path *path, const char *old_name, err = -EINVAL; if (mnt_ns_loop(old_path.dentry)) - goto out; + goto out; mp = lock_mount(path); err = PTR_ERR(mp); diff --git a/fs/super.c b/fs/super.c index adb0c0de428c..dfb56a9665d8 100644 --- a/fs/super.c +++ b/fs/super.c @@ -508,7 +508,7 @@ retry: return ERR_PTR(-ENOMEM); goto retry; } - + err = set(s, data); if (err) { spin_unlock(&sb_lock); @@ -771,7 +771,7 @@ restart: spin_unlock(&sb_lock); return NULL; } - + struct super_block *user_get_super(dev_t dev) { struct super_block *sb; -- cgit v1.2.3-59-g8ed1b From ee416bcdba9975065de571e09de1f7ebfde2156a Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 4 Jul 2017 17:25:16 +0100 Subject: VFS: Make get_filesystem() return the affected filesystem Make get_filesystem() return a pointer to the filesystem on which it just got a ref. Suggested-by: Rasmus Villemoes Signed-off-by: David Howells Signed-off-by: Al Viro --- fs/filesystems.c | 3 ++- include/linux/fs.h | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/filesystems.c b/fs/filesystems.c index cac75547d35c..591e52d23ed4 100644 --- a/fs/filesystems.c +++ b/fs/filesystems.c @@ -33,9 +33,10 @@ static struct file_system_type *file_systems; static DEFINE_RWLOCK(file_systems_lock); /* WARNING: This can be used only if we _already_ own a reference */ -void get_filesystem(struct file_system_type *fs) +struct file_system_type *get_filesystem(struct file_system_type *fs) { __module_get(fs->owner); + return fs; } void put_filesystem(struct file_system_type *fs) diff --git a/include/linux/fs.h b/include/linux/fs.h index 803e5a9b2654..bc0c054894b9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2956,7 +2956,7 @@ extern int generic_block_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len, get_block_t *get_block); -extern void get_filesystem(struct file_system_type *fs); +extern struct file_system_type *get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern struct super_block *get_super(struct block_device *); -- cgit v1.2.3-59-g8ed1b From cdf01226b26e98c79c13b335fbe0cbbbe850cf44 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 4 Jul 2017 17:25:22 +0100 Subject: VFS: Provide empty name qstr Provide an empty name (ie. "") qstr for general use. Signed-off-by: David Howells Signed-off-by: Al Viro --- fs/dcache.c | 8 ++++++-- fs/gfs2/dir.c | 3 +-- fs/namei.c | 3 +-- fs/nsfs.c | 3 +-- fs/pipe.c | 3 +-- include/linux/dcache.h | 5 +++++ 6 files changed, 15 insertions(+), 10 deletions(-) diff --git a/fs/dcache.c b/fs/dcache.c index a9f995f6859e..95efb7b2bf84 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -90,6 +90,11 @@ EXPORT_SYMBOL(rename_lock); static struct kmem_cache *dentry_cache __read_mostly; +const struct qstr empty_name = QSTR_INIT("", 0); +EXPORT_SYMBOL(empty_name); +const struct qstr slash_name = QSTR_INIT("/", 1); +EXPORT_SYMBOL(slash_name); + /* * This is the single most critical data structure when it comes * to the dcache: the hashtable for lookups. Somebody should try @@ -1578,8 +1583,7 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) */ dentry->d_iname[DNAME_INLINE_LEN-1] = 0; if (unlikely(!name)) { - static const struct qstr anon = QSTR_INIT("/", 1); - name = &anon; + name = &slash_name; dname = dentry->d_iname; } else if (name->len > DNAME_INLINE_LEN-1) { size_t size = offsetof(struct external_name, name[1]); diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index 79113219be5f..a5dfff6a033e 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -872,7 +872,6 @@ static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh, struct buffer_head *bh; struct gfs2_leaf *leaf; struct gfs2_dirent *dent; - struct qstr name = { .name = "" }; struct timespec tv = current_time(inode); error = gfs2_alloc_blocks(ip, &bn, &n, 0, NULL); @@ -896,7 +895,7 @@ static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh, leaf->lf_sec = cpu_to_be64(tv.tv_sec); memset(leaf->lf_reserved2, 0, sizeof(leaf->lf_reserved2)); dent = (struct gfs2_dirent *)(leaf+1); - gfs2_qstr2dirent(&name, bh->b_size - sizeof(struct gfs2_leaf), dent); + gfs2_qstr2dirent(&empty_name, bh->b_size - sizeof(struct gfs2_leaf), dent); *pbh = bh; return leaf; } diff --git a/fs/namei.c b/fs/namei.c index 6571a5f5112e..0d35760fee00 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3400,7 +3400,6 @@ out: struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag) { - static const struct qstr name = QSTR_INIT("/", 1); struct dentry *child = NULL; struct inode *dir = dentry->d_inode; struct inode *inode; @@ -3414,7 +3413,7 @@ struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag) if (!dir->i_op->tmpfile) goto out_err; error = -ENOMEM; - child = d_alloc(dentry, &name); + child = d_alloc(dentry, &slash_name); if (unlikely(!child)) goto out_err; error = dir->i_op->tmpfile(dir, child, mode); diff --git a/fs/nsfs.c b/fs/nsfs.c index f3db56e83dd2..08127a2b8559 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -53,7 +53,6 @@ static void nsfs_evict(struct inode *inode) static void *__ns_get_path(struct path *path, struct ns_common *ns) { struct vfsmount *mnt = nsfs_mnt; - struct qstr qname = { .name = "", }; struct dentry *dentry; struct inode *inode; unsigned long d; @@ -85,7 +84,7 @@ slow: inode->i_fop = &ns_file_operations; inode->i_private = ns; - dentry = d_alloc_pseudo(mnt->mnt_sb, &qname); + dentry = d_alloc_pseudo(mnt->mnt_sb, &empty_name); if (!dentry) { iput(inode); return ERR_PTR(-ENOMEM); diff --git a/fs/pipe.c b/fs/pipe.c index 73b84baf58f8..97e5be897753 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -739,13 +739,12 @@ int create_pipe_files(struct file **res, int flags) struct inode *inode = get_pipe_inode(); struct file *f; struct path path; - static struct qstr name = { .name = "" }; if (!inode) return -ENFILE; err = -ENOMEM; - path.dentry = d_alloc_pseudo(pipe_mnt->mnt_sb, &name); + path.dentry = d_alloc_pseudo(pipe_mnt->mnt_sb, &empty_name); if (!path.dentry) goto err_inode; path.mnt = mntget(pipe_mnt); diff --git a/include/linux/dcache.h b/include/linux/dcache.h index d2e38dc6172c..3f65a4fa72ed 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -55,6 +55,11 @@ struct qstr { #define QSTR_INIT(n,l) { { { .len = l } }, .name = n } +extern const char empty_string[]; +extern const struct qstr empty_name; +extern const char slash_string[]; +extern const struct qstr slash_name; + struct dentry_stat_t { long nr_dentry; long nr_unused; -- cgit v1.2.3-59-g8ed1b From c3d98ea08291ca26144780f601e1fd39e4f20f7e Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 5 Jul 2017 16:24:09 +0100 Subject: VFS: Don't use save/replace_mount_options if not using generic_show_options btrfs, debugfs, reiserfs and tracefs call save_mount_options() and reiserfs calls replace_mount_options(), but they then implement their own ->show_options() methods and don't touch s_options, rendering the saved options unnecessary. I'm trying to eliminate s_options to make it easier to implement a context-based mount where the mount options can be passed individually over a file descriptor. Remove the calls to save/replace_mount_options() call in these cases. Signed-off-by: David Howells cc: Chris Mason cc: Greg Kroah-Hartman cc: Steven Rostedt cc: linux-btrfs@vger.kernel.org cc: reiserfs-devel@vger.kernel.org Signed-off-by: Al Viro --- fs/btrfs/super.c | 1 - fs/debugfs/inode.c | 2 -- fs/reiserfs/super.c | 4 ---- fs/tracefs/inode.c | 2 -- 4 files changed, 9 deletions(-) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 4f1cdd5058f1..8e9758b3eb23 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1164,7 +1164,6 @@ static int btrfs_fill_super(struct super_block *sb, goto fail_close; } - save_mount_options(sb, data); cleancache_init_fs(sb); sb->s_flags |= MS_ACTIVE; return 0; diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index e892ae7d89f8..0dc9e9c0e0f8 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -203,8 +203,6 @@ static int debug_fill_super(struct super_block *sb, void *data, int silent) struct debugfs_fs_info *fsi; int err; - save_mount_options(sb, data); - fsi = kzalloc(sizeof(struct debugfs_fs_info), GFP_KERNEL); sb->s_fs_info = fsi; if (!fsi) { diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 685f1e056998..306e4e9d172d 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -1599,8 +1599,6 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) } out_ok_unlocked: - if (new_opts) - replace_mount_options(s, new_opts); return 0; out_err_unlock: @@ -1916,8 +1914,6 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) char *qf_names[REISERFS_MAXQUOTAS] = {}; unsigned int qfmt = 0; - save_mount_options(s, data); - sbi = kzalloc(sizeof(struct reiserfs_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 328e89c2cf83..bea8ad876bf9 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -270,8 +270,6 @@ static int trace_fill_super(struct super_block *sb, void *data, int silent) struct tracefs_fs_info *fsi; int err; - save_mount_options(sb, data); - fsi = kzalloc(sizeof(struct tracefs_fs_info), GFP_KERNEL); sb->s_fs_info = fsi; if (!fsi) { -- cgit v1.2.3-59-g8ed1b From 4a25220d4e43bb2461823dbc7eb1502a34087958 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 5 Jul 2017 16:24:18 +0100 Subject: hugetlbfs: Implement show_options Implement the show_options superblock op for hugetlbfs as part of a bid to get rid of s_options and generic_show_options() to make it easier to implement a context-based mount where the mount options can be passed individually over a file descriptor. Note that the uid and gid should possibly be displayed relative to the viewer's user namespace. Signed-off-by: David Howells cc: Nadia Yvette Chambers Signed-off-by: Al Viro --- fs/hugetlbfs/inode.c | 70 +++++++++++++++++++++++++++++++++++++++---------- include/linux/hugetlb.h | 3 +++ 2 files changed, 59 insertions(+), 14 deletions(-) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index d44f5456eb9b..99b3b9836575 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -46,13 +46,13 @@ static const struct inode_operations hugetlbfs_dir_inode_operations; static const struct inode_operations hugetlbfs_inode_operations; struct hugetlbfs_config { - kuid_t uid; - kgid_t gid; - umode_t mode; - long max_hpages; - long nr_inodes; - struct hstate *hstate; - long min_hpages; + struct hstate *hstate; + long max_hpages; + long nr_inodes; + long min_hpages; + kuid_t uid; + kgid_t gid; + umode_t mode; }; struct hugetlbfs_inode_info { @@ -851,6 +851,46 @@ static int hugetlbfs_migrate_page(struct address_space *mapping, return MIGRATEPAGE_SUCCESS; } +/* + * Display the mount options in /proc/mounts. + */ +static int hugetlbfs_show_options(struct seq_file *m, struct dentry *root) +{ + struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(root->d_sb); + struct hugepage_subpool *spool = sbinfo->spool; + unsigned long hpage_size = huge_page_size(sbinfo->hstate); + unsigned hpage_shift = huge_page_shift(sbinfo->hstate); + char mod; + + if (!uid_eq(sbinfo->uid, GLOBAL_ROOT_UID)) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, sbinfo->uid)); + if (!gid_eq(sbinfo->gid, GLOBAL_ROOT_GID)) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, sbinfo->gid)); + if (sbinfo->mode != 0755) + seq_printf(m, ",mode=%o", sbinfo->mode); + if (sbinfo->max_inodes != -1) + seq_printf(m, ",nr_inodes=%lu", sbinfo->max_inodes); + + hpage_size /= 1024; + mod = 'K'; + if (hpage_size >= 1024) { + hpage_size /= 1024; + mod = 'M'; + } + seq_printf(m, ",pagesize=%lu%c", hpage_size, mod); + if (spool) { + if (spool->max_hpages != -1) + seq_printf(m, ",size=%llu", + (unsigned long long)spool->max_hpages << hpage_shift); + if (spool->min_hpages != -1) + seq_printf(m, ",min_size=%llu", + (unsigned long long)spool->min_hpages << hpage_shift); + } + return 0; +} + static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb); @@ -1008,19 +1048,19 @@ static const struct super_operations hugetlbfs_ops = { .evict_inode = hugetlbfs_evict_inode, .statfs = hugetlbfs_statfs, .put_super = hugetlbfs_put_super, - .show_options = generic_show_options, + .show_options = hugetlbfs_show_options, }; -enum { NO_SIZE, SIZE_STD, SIZE_PERCENT }; +enum hugetlbfs_size_type { NO_SIZE, SIZE_STD, SIZE_PERCENT }; /* * Convert size option passed from command line to number of huge pages * in the pool specified by hstate. Size option could be in bytes * (val_type == SIZE_STD) or percentage of the pool (val_type == SIZE_PERCENT). */ -static long long +static long hugetlbfs_size_to_hpages(struct hstate *h, unsigned long long size_opt, - int val_type) + enum hugetlbfs_size_type val_type) { if (val_type == NO_SIZE) return -1; @@ -1042,7 +1082,7 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig) substring_t args[MAX_OPT_ARGS]; int option; unsigned long long max_size_opt = 0, min_size_opt = 0; - int max_val_type = NO_SIZE, min_val_type = NO_SIZE; + enum hugetlbfs_size_type max_val_type = NO_SIZE, min_val_type = NO_SIZE; if (!options) return 0; @@ -1156,8 +1196,6 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent) struct hugetlbfs_config config; struct hugetlbfs_sb_info *sbinfo; - save_mount_options(sb, data); - config.max_hpages = -1; /* No limit on size by default */ config.nr_inodes = -1; /* No limit on number of inodes by default */ config.uid = current_fsuid(); @@ -1178,6 +1216,10 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent) sbinfo->max_inodes = config.nr_inodes; sbinfo->free_inodes = config.nr_inodes; sbinfo->spool = NULL; + sbinfo->uid = config.uid; + sbinfo->gid = config.gid; + sbinfo->mode = config.mode; + /* * Allocate and initialize subpool if maximum or minimum size is * specified. Any needed reservations (for minimim size) are taken diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index b857fc8cc2ec..3b6eeaad2f77 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -262,6 +262,9 @@ struct hugetlbfs_sb_info { spinlock_t stat_lock; struct hstate *hstate; struct hugepage_subpool *spool; + kuid_t uid; + kgid_t gid; + umode_t mode; }; static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) -- cgit v1.2.3-59-g8ed1b From d86efb0df98afe0acdda7ed94963684c3fa7cccd Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 5 Jul 2017 16:24:27 +0100 Subject: omfs: Implement show_options Implement the show_options superblock op for omfs as part of a bid to get rid of s_options and generic_show_options() to make it easier to implement a context-based mount where the mount options can be passed individually over a file descriptor. Note that the uid and gid should possibly be displayed relative to the viewer's user namespace. Signed-off-by: David Howells cc: Bob Copeland cc: linux-karma-devel@lists.sourceforge.net Signed-off-by: Al Viro --- fs/omfs/inode.c | 33 ++++++++++++++++++++++++++++++--- 1 file changed, 30 insertions(+), 3 deletions(-) diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c index 8c9034ee7383..ee14af9e26f2 100644 --- a/fs/omfs/inode.c +++ b/fs/omfs/inode.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include "omfs.h" @@ -290,12 +291,40 @@ static int omfs_statfs(struct dentry *dentry, struct kstatfs *buf) return 0; } +/* + * Display the mount options in /proc/mounts. + */ +static int omfs_show_options(struct seq_file *m, struct dentry *root) +{ + struct omfs_sb_info *sbi = OMFS_SB(root->d_sb); + umode_t cur_umask = current_umask(); + + if (!uid_eq(sbi->s_uid, current_uid())) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, sbi->s_uid)); + if (!gid_eq(sbi->s_gid, current_gid())) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, sbi->s_gid)); + + if (sbi->s_dmask == sbi->s_fmask) { + if (sbi->s_fmask != cur_umask) + seq_printf(m, ",umask=%o", sbi->s_fmask); + } else { + if (sbi->s_dmask != cur_umask) + seq_printf(m, ",dmask=%o", sbi->s_dmask); + if (sbi->s_fmask != cur_umask) + seq_printf(m, ",fmask=%o", sbi->s_fmask); + } + + return 0; +} + static const struct super_operations omfs_sops = { .write_inode = omfs_write_inode, .evict_inode = omfs_evict_inode, .put_super = omfs_put_super, .statfs = omfs_statfs, - .show_options = generic_show_options, + .show_options = omfs_show_options, }; /* @@ -434,8 +463,6 @@ static int omfs_fill_super(struct super_block *sb, void *data, int silent) struct inode *root; int ret = -EINVAL; - save_mount_options(sb, (char *) data); - sbi = kzalloc(sizeof(struct omfs_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; -- cgit v1.2.3-59-g8ed1b From 349d743895e2371bda9a02a5b465b50cc24d2825 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 5 Jul 2017 16:24:34 +0100 Subject: pstore: Implement show_options Implement the show_options superblock op for pstore as part of a bid to get rid of s_options and generic_show_options() to make it easier to implement a context-based mount where the mount options can be passed individually over a file descriptor. Signed-off-by: David Howells cc: Kees Cook cc: Anton Vorontsov cc: Colin Cross cc: Tony Luck Signed-off-by: Al Viro --- fs/pstore/inode.c | 14 +++++++++++--- fs/pstore/internal.h | 3 +++ fs/pstore/platform.c | 2 +- 3 files changed, 15 insertions(+), 4 deletions(-) diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index 792a4e5f9226..913e839ac1f5 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -283,6 +283,16 @@ static void parse_options(char *options) } } +/* + * Display the mount options in /proc/mounts. + */ +static int pstore_show_options(struct seq_file *m, struct dentry *root) +{ + if (kmsg_bytes != PSTORE_DEFAULT_KMSG_BYTES) + seq_printf(m, ",kmsg_bytes=%lu", kmsg_bytes); + return 0; +} + static int pstore_remount(struct super_block *sb, int *flags, char *data) { sync_filesystem(sb); @@ -296,7 +306,7 @@ static const struct super_operations pstore_ops = { .drop_inode = generic_delete_inode, .evict_inode = pstore_evict_inode, .remount_fs = pstore_remount, - .show_options = generic_show_options, + .show_options = pstore_show_options, }; static struct super_block *pstore_sb; @@ -448,8 +458,6 @@ static int pstore_fill_super(struct super_block *sb, void *data, int silent) { struct inode *inode; - save_mount_options(sb, data); - pstore_sb = sb; sb->s_maxbytes = MAX_LFS_FILESIZE; diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h index c416e653dc4f..4d5913130580 100644 --- a/fs/pstore/internal.h +++ b/fs/pstore/internal.h @@ -5,6 +5,9 @@ #include #include +#define PSTORE_DEFAULT_KMSG_BYTES 10240 +extern unsigned long kmsg_bytes; + #ifdef CONFIG_PSTORE_FTRACE extern void pstore_register_ftrace(void); extern void pstore_unregister_ftrace(void); diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index d468eec9b8a6..6640df40908d 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -99,7 +99,7 @@ static char *big_oops_buf; static size_t big_oops_buf_sz; /* How much of the console log to snapshot */ -static unsigned long kmsg_bytes = 10240; +unsigned long kmsg_bytes = PSTORE_DEFAULT_KMSG_BYTES; void pstore_set_kmsg_bytes(int bytes) { -- cgit v1.2.3-59-g8ed1b From 604ecf4288933dec3c235ed1ee575a154670c882 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 5 Jul 2017 16:24:42 +0100 Subject: ramfs: Implement show_options Implement the show_options superblock op for ramfs as part of a bid to get rid of s_options and generic_show_options() to make it easier to implement a context-based mount where the mount options can be passed individually over a file descriptor. Signed-off-by: David Howells Signed-off-by: Al Viro --- fs/ramfs/inode.c | 32 +++++++++++++++++++++----------- 1 file changed, 21 insertions(+), 11 deletions(-) diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index 26e45863e499..11201b2d06b9 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -38,6 +38,14 @@ #include #include "internal.h" +struct ramfs_mount_opts { + umode_t mode; +}; + +struct ramfs_fs_info { + struct ramfs_mount_opts mount_opts; +}; + #define RAMFS_DEFAULT_MODE 0755 static const struct super_operations ramfs_ops; @@ -149,14 +157,22 @@ static const struct inode_operations ramfs_dir_inode_operations = { .rename = simple_rename, }; +/* + * Display the mount options in /proc/mounts. + */ +static int ramfs_show_options(struct seq_file *m, struct dentry *root) +{ + struct ramfs_fs_info *fsi = root->d_sb->s_fs_info; + + if (fsi->mount_opts.mode != RAMFS_DEFAULT_MODE) + seq_printf(m, ",mode=%o", fsi->mount_opts.mode); + return 0; +} + static const struct super_operations ramfs_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, - .show_options = generic_show_options, -}; - -struct ramfs_mount_opts { - umode_t mode; + .show_options = ramfs_show_options, }; enum { @@ -169,10 +185,6 @@ static const match_table_t tokens = { {Opt_err, NULL} }; -struct ramfs_fs_info { - struct ramfs_mount_opts mount_opts; -}; - static int ramfs_parse_options(char *data, struct ramfs_mount_opts *opts) { substring_t args[MAX_OPT_ARGS]; @@ -211,8 +223,6 @@ int ramfs_fill_super(struct super_block *sb, void *data, int silent) struct inode *inode; int err; - save_mount_options(sb, data); - fsi = kzalloc(sizeof(struct ramfs_fs_info), GFP_KERNEL); sb->s_fs_info = fsi; if (!fsi) -- cgit v1.2.3-59-g8ed1b From 4cc7c1864bbd4cf80f6bdc8ba3217de5aa5f4688 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 5 Jul 2017 16:24:49 +0100 Subject: bpf: Implement show_options Implement the show_options superblock op for bpf as part of a bid to get rid of s_options and generic_show_options() to make it easier to implement a context-based mount where the mount options can be passed individually over a file descriptor. Signed-off-by: David Howells cc: Alexei Starovoitov cc: Daniel Borkmann cc: netdev@vger.kernel.org Signed-off-by: Al Viro --- kernel/bpf/inode.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 9bbd33497d3d..e833ed914358 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -377,10 +377,22 @@ static void bpf_evict_inode(struct inode *inode) bpf_any_put(inode->i_private, type); } +/* + * Display the mount options in /proc/mounts. + */ +static int bpf_show_options(struct seq_file *m, struct dentry *root) +{ + umode_t mode = d_inode(root)->i_mode & S_IALLUGO & ~S_ISVTX; + + if (mode != S_IRWXUGO) + seq_printf(m, ",mode=%o", mode); + return 0; +} + static const struct super_operations bpf_super_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, - .show_options = generic_show_options, + .show_options = bpf_show_options, .evict_inode = bpf_evict_inode, }; @@ -434,8 +446,6 @@ static int bpf_fill_super(struct super_block *sb, void *data, int silent) struct inode *inode; int ret; - save_mount_options(sb, data); - ret = bpf_parse_options(data, &opts); if (ret) return ret; -- cgit v1.2.3-59-g8ed1b From 8517bb1f19679bf2bf6c29a98b7a4f3a78629554 Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Thu, 8 Jun 2017 14:24:14 +0200 Subject: dt-bindings: pwm: meson: Add compatible for gxbb ao PWMs Add compatible string to properly handle the PWMs found in the AO domain of the gxbb (and gxl) family. Acked-by: Neil Armstrong Signed-off-by: Jerome Brunet Acked-by: Rob Herring Signed-off-by: Thierry Reding --- Documentation/devicetree/bindings/pwm/pwm-meson.txt | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/pwm/pwm-meson.txt b/Documentation/devicetree/bindings/pwm/pwm-meson.txt index 5376a4468cb6..5b07bebbf6f7 100644 --- a/Documentation/devicetree/bindings/pwm/pwm-meson.txt +++ b/Documentation/devicetree/bindings/pwm/pwm-meson.txt @@ -2,7 +2,9 @@ Amlogic Meson PWM Controller ============================ Required properties: -- compatible: Shall contain "amlogic,meson8b-pwm" or "amlogic,meson-gxbb-pwm". +- compatible: Shall contain "amlogic,meson8b-pwm" + or "amlogic,meson-gxbb-pwm" + or "amlogic,meson-gxbb-ao-pwm" - #pwm-cells: Should be 3. See pwm.txt in this directory for a description of the cells format. -- cgit v1.2.3-59-g8ed1b From 99c621d704cf1c4eb74c3c42e674edf3df64f92d Mon Sep 17 00:00:00 2001 From: Michael Sartain Date: Wed, 5 Jul 2017 22:07:15 -0600 Subject: tracing: Add saved_tgids file to show cached pid to tgid mappings Export the cached pid / tgid mappings in debugfs tracing saved_tgids file. This allows user apps to translate the pids from a trace to their respective thread group. Example saved_tgids file with pid / tgid values separated by ' ': # cat saved_tgids 1048 1048 1047 1047 7 7 1049 1047 1054 1047 1053 1047 Link: http://lkml.kernel.org/r/20170630004023.064965233@goodmis.org Link: http://lkml.kernel.org/r/20170706040713.unwkumbta5menygi@mikesart-cos Reviewed-by: Joel Fernandes Signed-off-by: Michael Sartain Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 73 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 73 insertions(+) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 00e2e4169b1e..f079a8ca1117 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4688,6 +4688,76 @@ static const struct file_operations tracing_readme_fops = { .llseek = generic_file_llseek, }; +static void *saved_tgids_next(struct seq_file *m, void *v, loff_t *pos) +{ + int *ptr = v; + + if (*pos || m->count) + ptr++; + + (*pos)++; + + for (; ptr <= &tgid_map[PID_MAX_DEFAULT]; ptr++) { + if (trace_find_tgid(*ptr)) + return ptr; + } + + return NULL; +} + +static void *saved_tgids_start(struct seq_file *m, loff_t *pos) +{ + void *v; + loff_t l = 0; + + if (!tgid_map) + return NULL; + + v = &tgid_map[0]; + while (l <= *pos) { + v = saved_tgids_next(m, v, &l); + if (!v) + return NULL; + } + + return v; +} + +static void saved_tgids_stop(struct seq_file *m, void *v) +{ +} + +static int saved_tgids_show(struct seq_file *m, void *v) +{ + int pid = (int *)v - tgid_map; + + seq_printf(m, "%d %d\n", pid, trace_find_tgid(pid)); + return 0; +} + +static const struct seq_operations tracing_saved_tgids_seq_ops = { + .start = saved_tgids_start, + .stop = saved_tgids_stop, + .next = saved_tgids_next, + .show = saved_tgids_show, +}; + +static int tracing_saved_tgids_open(struct inode *inode, struct file *filp) +{ + if (tracing_disabled) + return -ENODEV; + + return seq_open(filp, &tracing_saved_tgids_seq_ops); +} + + +static const struct file_operations tracing_saved_tgids_fops = { + .open = tracing_saved_tgids_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + static void *saved_cmdlines_next(struct seq_file *m, void *v, loff_t *pos) { unsigned int *ptr = v; @@ -7920,6 +7990,9 @@ static __init int tracer_init_tracefs(void) trace_create_file("saved_cmdlines_size", 0644, d_tracer, NULL, &tracing_saved_cmdlines_size_fops); + trace_create_file("saved_tgids", 0444, d_tracer, + NULL, &tracing_saved_tgids_fops); + trace_eval_init(); trace_create_eval_file(d_tracer); -- cgit v1.2.3-59-g8ed1b From fd7b2be8cbcf6cd6d9c9e843ffff36fb91388e51 Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Thu, 8 Jun 2017 14:24:16 +0200 Subject: pwm: meson: Improve PWM calculation precision When using input clocks with high rates, such as clk81 (166MHz), the fin_ns = NSEC_PER_SEC / fin_freq can introduce a significant error. Ex: fin_freq = 166666667, NSEC_PER_SEC = 1000000000 fin_ns = 5,9999999 which is, of course, rounded down to 5. This introduces an error of ~20% on the period requested from the PWM. This patch uses ps instead of ns (and 64 bit integers) to perform the calculation. This should give a good enough precision. Fixes: 211ed630753d ("pwm: Add support for Meson PWM Controller") Signed-off-by: Jerome Brunet Acked-by: Neil Armstrong Signed-off-by: Thierry Reding squash! pwm: meson: Improve pwm calculation precision --- drivers/pwm/pwm-meson.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/drivers/pwm/pwm-meson.c b/drivers/pwm/pwm-meson.c index defc27d880f3..cb845edfe2b4 100644 --- a/drivers/pwm/pwm-meson.c +++ b/drivers/pwm/pwm-meson.c @@ -163,7 +163,8 @@ static int meson_pwm_calc(struct meson_pwm *meson, unsigned int duty, unsigned int period) { unsigned int pre_div, cnt, duty_cnt; - unsigned long fin_freq = -1, fin_ns; + unsigned long fin_freq = -1; + u64 fin_ps; if (~(meson->inverter_mask >> id) & 0x1) duty = period - duty; @@ -179,13 +180,15 @@ static int meson_pwm_calc(struct meson_pwm *meson, } dev_dbg(meson->chip.dev, "fin_freq: %lu Hz\n", fin_freq); - fin_ns = NSEC_PER_SEC / fin_freq; + fin_ps = (u64)NSEC_PER_SEC * 1000; + do_div(fin_ps, fin_freq); /* Calc pre_div with the period */ for (pre_div = 0; pre_div < MISC_CLK_DIV_MASK; pre_div++) { - cnt = DIV_ROUND_CLOSEST(period, fin_ns * (pre_div + 1)); - dev_dbg(meson->chip.dev, "fin_ns=%lu pre_div=%u cnt=%u\n", - fin_ns, pre_div, cnt); + cnt = DIV_ROUND_CLOSEST_ULL((u64)period * 1000, + fin_ps * (pre_div + 1)); + dev_dbg(meson->chip.dev, "fin_ps=%llu pre_div=%u cnt=%u\n", + fin_ps, pre_div, cnt); if (cnt <= 0xffff) break; } @@ -208,7 +211,8 @@ static int meson_pwm_calc(struct meson_pwm *meson, channel->lo = cnt; } else { /* Then check is we can have the duty with the same pre_div */ - duty_cnt = DIV_ROUND_CLOSEST(duty, fin_ns * (pre_div + 1)); + duty_cnt = DIV_ROUND_CLOSEST_ULL((u64)duty * 1000, + fin_ps * (pre_div + 1)); if (duty_cnt > 0xffff) { dev_err(meson->chip.dev, "unable to get duty cycle\n"); return -EINVAL; -- cgit v1.2.3-59-g8ed1b From e47866a177cf0baba1d714fa93cb762f25bd6cef Mon Sep 17 00:00:00 2001 From: Nick Vaccaro Date: Fri, 23 Jun 2017 14:52:47 -0700 Subject: pwm: cros-ec: Fix transposed param settings The __cros_ec_pwm_get_duty() routine was transposing the insize and outsize fields when calling cros_ec_cmd_xfer_status(). The original code worked without error due to size of the two particular parameter blocks passed to cros_ec_cmd_xfer_status(), so this change is not fixing an actual runtime problem, just correcting the calling usage. Signed-off-by: Nick Vaccaro Reviewed-by: Brian Norris Signed-off-by: Thierry Reding --- drivers/pwm/pwm-cros-ec.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/pwm/pwm-cros-ec.c b/drivers/pwm/pwm-cros-ec.c index f6ca4e8c6253..9c13694eaa24 100644 --- a/drivers/pwm/pwm-cros-ec.c +++ b/drivers/pwm/pwm-cros-ec.c @@ -75,8 +75,8 @@ static int __cros_ec_pwm_get_duty(struct cros_ec_device *ec, u8 index, msg->version = 0; msg->command = EC_CMD_PWM_GET_DUTY; - msg->insize = sizeof(*params); - msg->outsize = sizeof(*resp); + msg->insize = sizeof(*resp); + msg->outsize = sizeof(*params); params->pwm_type = EC_PWM_TYPE_GENERIC; params->index = index; -- cgit v1.2.3-59-g8ed1b From c2d42edb528af75890cf73658e86e6dc9ac2b22b Mon Sep 17 00:00:00 2001 From: Allen Hubbe Date: Tue, 27 Dec 2016 19:12:27 -0500 Subject: NTB: ntb_test: modprobe on remote host Signed-off-by: Allen Hubbe Acked-by: Logan Gunthorpe Signed-off-by: Jon Mason --- tools/testing/selftests/ntb/ntb_test.sh | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/ntb/ntb_test.sh b/tools/testing/selftests/ntb/ntb_test.sh index 13f5198ba0ee..1ee8ea350f65 100755 --- a/tools/testing/selftests/ntb/ntb_test.sh +++ b/tools/testing/selftests/ntb/ntb_test.sh @@ -85,6 +85,10 @@ set -e function _modprobe() { modprobe "$@" + + if [[ "$REMOTE_HOST" != "" ]]; then + ssh "$REMOTE_HOST" modprobe "$@" + fi } function split_remote() -- cgit v1.2.3-59-g8ed1b From 7c49c9855a890ce32ea08f01366ecb221a027ad8 Mon Sep 17 00:00:00 2001 From: Allen Hubbe Date: Tue, 27 Dec 2016 19:12:28 -0500 Subject: NTB: ntb_test: add parameter for doorbell bitmask If the test attempts to clear doorbell bits that are invalid for the hardware, then the test will fail. Provide a parameter to specify the doorbell bits to clear. Set default doorbell bits that work for XEON. Signed-off-by: Allen Hubbe Acked-by: Logan Gunthorpe Signed-off-by: Jon Mason --- tools/testing/selftests/ntb/ntb_test.sh | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/ntb/ntb_test.sh b/tools/testing/selftests/ntb/ntb_test.sh index 1ee8ea350f65..1c12b5855e4f 100755 --- a/tools/testing/selftests/ntb/ntb_test.sh +++ b/tools/testing/selftests/ntb/ntb_test.sh @@ -18,6 +18,7 @@ LIST_DEVS=FALSE DEBUGFS=${DEBUGFS-/sys/kernel/debug} +DB_BITMASK=0x7FFF PERF_RUN_ORDER=32 MAX_MW_SIZE=0 RUN_DMA_TESTS= @@ -38,6 +39,7 @@ function show_help() echo "be highly recommended." echo echo "Options:" + echo " -b BITMASK doorbell clear bitmask for ntb_tool" echo " -C don't cleanup ntb modules on exit" echo " -d run dma tests" echo " -h show this help message" @@ -52,8 +54,9 @@ function show_help() function parse_args() { OPTIND=0 - while getopts "Cdhlm:r:p:w:" opt; do + while getopts "b:Cdhlm:r:p:w:" opt; do case "$opt" in + b) DB_BITMASK=${OPTARG} ;; C) DONT_CLEANUP=1 ;; d) RUN_DMA_TESTS=1 ;; h) show_help; exit 0 ;; @@ -158,7 +161,7 @@ function doorbell_test() echo "Running db tests on: $(basename $LOC) / $(basename $REM)" - write_file "c 0xFFFFFFFF" "$REM/db" + write_file "c $DB_BITMASK" "$REM/db" for ((i=1; i <= 8; i++)); do let DB=$(read_file "$REM/db") || true -- cgit v1.2.3-59-g8ed1b From 60934b200ddd62187b149a7f32cc0f160c08a7ed Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Wed, 14 Dec 2016 02:49:13 +0300 Subject: NTB: Make link-state API being declared first Since link operations are usually performed before memory window access operations, it's logically better to declare link-related API before any of MW/Doorbell/Scratchpad methods. Signed-off-by: Serge Semin Signed-off-by: Jon Mason --- include/linux/ntb.h | 137 ++++++++++++++++++++++++++-------------------------- 1 file changed, 69 insertions(+), 68 deletions(-) diff --git a/include/linux/ntb.h b/include/linux/ntb.h index de87ceac110e..d7ab3e1ec88f 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -179,13 +179,13 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) /** * struct ntb_ctx_ops - ntb device operations + * @link_is_up: See ntb_link_is_up(). + * @link_enable: See ntb_link_enable(). + * @link_disable: See ntb_link_disable(). * @mw_count: See ntb_mw_count(). * @mw_get_range: See ntb_mw_get_range(). * @mw_set_trans: See ntb_mw_set_trans(). * @mw_clear_trans: See ntb_mw_clear_trans(). - * @link_is_up: See ntb_link_is_up(). - * @link_enable: See ntb_link_enable(). - * @link_disable: See ntb_link_disable(). * @db_is_unsafe: See ntb_db_is_unsafe(). * @db_valid_mask: See ntb_db_valid_mask(). * @db_vector_count: See ntb_db_vector_count(). @@ -212,6 +212,12 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) * @peer_spad_write: See ntb_peer_spad_write(). */ struct ntb_dev_ops { + int (*link_is_up)(struct ntb_dev *ntb, + enum ntb_speed *speed, enum ntb_width *width); + int (*link_enable)(struct ntb_dev *ntb, + enum ntb_speed max_speed, enum ntb_width max_width); + int (*link_disable)(struct ntb_dev *ntb); + int (*mw_count)(struct ntb_dev *ntb); int (*mw_get_range)(struct ntb_dev *ntb, int idx, phys_addr_t *base, resource_size_t *size, @@ -220,12 +226,6 @@ struct ntb_dev_ops { dma_addr_t addr, resource_size_t size); int (*mw_clear_trans)(struct ntb_dev *ntb, int idx); - int (*link_is_up)(struct ntb_dev *ntb, - enum ntb_speed *speed, enum ntb_width *width); - int (*link_enable)(struct ntb_dev *ntb, - enum ntb_speed max_speed, enum ntb_width max_width); - int (*link_disable)(struct ntb_dev *ntb); - int (*db_is_unsafe)(struct ntb_dev *ntb); u64 (*db_valid_mask)(struct ntb_dev *ntb); int (*db_vector_count)(struct ntb_dev *ntb); @@ -265,13 +265,14 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops) { /* commented callbacks are not required: */ return + ops->link_is_up && + ops->link_enable && + ops->link_disable && ops->mw_count && ops->mw_get_range && ops->mw_set_trans && /* ops->mw_clear_trans && */ - ops->link_is_up && - ops->link_enable && - ops->link_disable && + /* ops->db_is_unsafe && */ ops->db_valid_mask && @@ -440,6 +441,62 @@ void ntb_link_event(struct ntb_dev *ntb); */ void ntb_db_event(struct ntb_dev *ntb, int vector); +/** + * ntb_link_is_up() - get the current ntb link state + * @ntb: NTB device context. + * @speed: OUT - The link speed expressed as PCIe generation number. + * @width: OUT - The link width expressed as the number of PCIe lanes. + * + * Get the current state of the ntb link. It is recommended to query the link + * state once after every link event. It is safe to query the link state in + * the context of the link event callback. + * + * Return: One if the link is up, zero if the link is down, otherwise a + * negative value indicating the error number. + */ +static inline int ntb_link_is_up(struct ntb_dev *ntb, + enum ntb_speed *speed, enum ntb_width *width) +{ + return ntb->ops->link_is_up(ntb, speed, width); +} + +/** + * ntb_link_enable() - enable the link on the secondary side of the ntb + * @ntb: NTB device context. + * @max_speed: The maximum link speed expressed as PCIe generation number. + * @max_width: The maximum link width expressed as the number of PCIe lanes. + * + * Enable the link on the secondary side of the ntb. This can only be done + * from the primary side of the ntb in primary or b2b topology. The ntb device + * should train the link to its maximum speed and width, or the requested speed + * and width, whichever is smaller, if supported. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_link_enable(struct ntb_dev *ntb, + enum ntb_speed max_speed, + enum ntb_width max_width) +{ + return ntb->ops->link_enable(ntb, max_speed, max_width); +} + +/** + * ntb_link_disable() - disable the link on the secondary side of the ntb + * @ntb: NTB device context. + * + * Disable the link on the secondary side of the ntb. This can only be + * done from the primary side of the ntb in primary or b2b topology. The ntb + * device should disable the link. Returning from this call must indicate that + * a barrier has passed, though with no more writes may pass in either + * direction across the link, except if this call returns an error number. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_link_disable(struct ntb_dev *ntb) +{ + return ntb->ops->link_disable(ntb); +} + /** * ntb_mw_count() - get the number of memory windows * @ntb: NTB device context. @@ -516,62 +573,6 @@ static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int idx) return ntb->ops->mw_clear_trans(ntb, idx); } -/** - * ntb_link_is_up() - get the current ntb link state - * @ntb: NTB device context. - * @speed: OUT - The link speed expressed as PCIe generation number. - * @width: OUT - The link width expressed as the number of PCIe lanes. - * - * Get the current state of the ntb link. It is recommended to query the link - * state once after every link event. It is safe to query the link state in - * the context of the link event callback. - * - * Return: One if the link is up, zero if the link is down, otherwise a - * negative value indicating the error number. - */ -static inline int ntb_link_is_up(struct ntb_dev *ntb, - enum ntb_speed *speed, enum ntb_width *width) -{ - return ntb->ops->link_is_up(ntb, speed, width); -} - -/** - * ntb_link_enable() - enable the link on the secondary side of the ntb - * @ntb: NTB device context. - * @max_speed: The maximum link speed expressed as PCIe generation number. - * @max_width: The maximum link width expressed as the number of PCIe lanes. - * - * Enable the link on the secondary side of the ntb. This can only be done - * from the primary side of the ntb in primary or b2b topology. The ntb device - * should train the link to its maximum speed and width, or the requested speed - * and width, whichever is smaller, if supported. - * - * Return: Zero on success, otherwise an error number. - */ -static inline int ntb_link_enable(struct ntb_dev *ntb, - enum ntb_speed max_speed, - enum ntb_width max_width) -{ - return ntb->ops->link_enable(ntb, max_speed, max_width); -} - -/** - * ntb_link_disable() - disable the link on the secondary side of the ntb - * @ntb: NTB device context. - * - * Disable the link on the secondary side of the ntb. This can only be - * done from the primary side of the ntb in primary or b2b topology. The ntb - * device should disable the link. Returning from this call must indicate that - * a barrier has passed, though with no more writes may pass in either - * direction across the link, except if this call returns an error number. - * - * Return: Zero on success, otherwise an error number. - */ -static inline int ntb_link_disable(struct ntb_dev *ntb) -{ - return ntb->ops->link_disable(ntb); -} - /** * ntb_db_is_unsafe() - check if it is safe to use hardware doorbell * @ntb: NTB device context. -- cgit v1.2.3-59-g8ed1b From 1e5301196a88961b02fe43c73a952f78b2c84712 Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Wed, 14 Dec 2016 02:49:14 +0300 Subject: NTB: Add indexed ports NTB API There is some NTB hardware, which can combine more than just two domains over NTB. For instance, some IDT PCIe-switches can have NTB-functions activated on more than two-ports. The different domains are distinguished by ports they are connected to. So the new port-related methods are added to the NTB API: ntb_port_number() - return local port ntb_peer_port_count() - return number of peers local port can connect to ntb_peer_port_number(pdix) - return port number by it index ntb_peer_port_idx(port) - return port index by it number Current test-drivers aren't changed much. They still support two-ports devices for the time being while multi-ports hardware drivers aren't added. By default port-related API is declared for two-ports hardware. So corresponding hardware drivers won't need to implement it. Signed-off-by: Serge Semin Signed-off-by: Jon Mason --- drivers/ntb/ntb.c | 54 ++++++++++++++ drivers/ntb/ntb_transport.c | 6 ++ drivers/ntb/test/ntb_perf.c | 4 ++ drivers/ntb/test/ntb_pingpong.c | 6 ++ drivers/ntb/test/ntb_tool.c | 5 ++ include/linux/ntb.h | 156 ++++++++++++++++++++++++++++++++++++++++ 6 files changed, 231 insertions(+) diff --git a/drivers/ntb/ntb.c b/drivers/ntb/ntb.c index 2e2530743831..1e92e52813aa 100644 --- a/drivers/ntb/ntb.c +++ b/drivers/ntb/ntb.c @@ -191,6 +191,60 @@ void ntb_db_event(struct ntb_dev *ntb, int vector) } EXPORT_SYMBOL(ntb_db_event); +int ntb_default_port_number(struct ntb_dev *ntb) +{ + switch (ntb->topo) { + case NTB_TOPO_PRI: + case NTB_TOPO_B2B_USD: + return NTB_PORT_PRI_USD; + case NTB_TOPO_SEC: + case NTB_TOPO_B2B_DSD: + return NTB_PORT_SEC_DSD; + default: + break; + } + + return -EINVAL; +} +EXPORT_SYMBOL(ntb_default_port_number); + +int ntb_default_peer_port_count(struct ntb_dev *ntb) +{ + return NTB_DEF_PEER_CNT; +} +EXPORT_SYMBOL(ntb_default_peer_port_count); + +int ntb_default_peer_port_number(struct ntb_dev *ntb, int pidx) +{ + if (pidx != NTB_DEF_PEER_IDX) + return -EINVAL; + + switch (ntb->topo) { + case NTB_TOPO_PRI: + case NTB_TOPO_B2B_USD: + return NTB_PORT_SEC_DSD; + case NTB_TOPO_SEC: + case NTB_TOPO_B2B_DSD: + return NTB_PORT_PRI_USD; + default: + break; + } + + return -EINVAL; +} +EXPORT_SYMBOL(ntb_default_peer_port_number); + +int ntb_default_peer_port_idx(struct ntb_dev *ntb, int port) +{ + int peer_port = ntb_default_peer_port_number(ntb, NTB_DEF_PEER_IDX); + + if (peer_port == -EINVAL || port != peer_port) + return -EINVAL; + + return 0; +} +EXPORT_SYMBOL(ntb_default_peer_port_idx); + static int ntb_probe(struct device *dev) { struct ntb_dev *ntb; diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index 10e5bf460139..cc6ae35109b1 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -95,6 +95,9 @@ MODULE_PARM_DESC(use_dma, "Use DMA engine to perform large data copy"); static struct dentry *nt_debugfs_dir; +/* Only two-ports NTB devices are supported */ +#define PIDX NTB_DEF_PEER_IDX + struct ntb_queue_entry { /* ntb_queue list reference */ struct list_head entry; @@ -1064,6 +1067,9 @@ static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev) dev_dbg(&ndev->dev, "scratchpad is unsafe, proceed anyway...\n"); + if (ntb_peer_port_count(ndev) != NTB_DEF_PEER_CNT) + dev_warn(&ndev->dev, "Multi-port NTB devices unsupported\n"); + node = dev_to_node(&ndev->dev); nt = kzalloc_node(sizeof(*nt), GFP_KERNEL, node); diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c index 5cab2831ce99..e52cc4eace90 100644 --- a/drivers/ntb/test/ntb_perf.c +++ b/drivers/ntb/test/ntb_perf.c @@ -76,6 +76,7 @@ #define DMA_RETRIES 20 #define SZ_4G (1ULL << 32) #define MAX_SEG_ORDER 20 /* no larger than 1M for kmalloc buffer */ +#define PIDX NTB_DEF_PEER_IDX MODULE_LICENSE(DRIVER_LICENSE); MODULE_VERSION(DRIVER_VERSION); @@ -766,6 +767,9 @@ static int perf_probe(struct ntb_client *client, struct ntb_dev *ntb) return -EIO; } + if (ntb_peer_port_count(ntb) != NTB_DEF_PEER_CNT) + dev_warn(&ntb->dev, "Multi-port NTB devices unsupported\n"); + node = dev_to_node(&pdev->dev); perf = kzalloc_node(sizeof(*perf), GFP_KERNEL, node); diff --git a/drivers/ntb/test/ntb_pingpong.c b/drivers/ntb/test/ntb_pingpong.c index 435861189d97..12f8b40cb11a 100644 --- a/drivers/ntb/test/ntb_pingpong.c +++ b/drivers/ntb/test/ntb_pingpong.c @@ -90,6 +90,9 @@ static unsigned long db_init = 0x7; module_param(db_init, ulong, 0644); MODULE_PARM_DESC(db_init, "Initial doorbell bits to ring on the peer"); +/* Only two-ports NTB devices are supported */ +#define PIDX NTB_DEF_PEER_IDX + struct pp_ctx { struct ntb_dev *ntb; u64 db_bits; @@ -230,6 +233,9 @@ static int pp_probe(struct ntb_client *client, } } + if (ntb_peer_port_count(ntb) != NTB_DEF_PEER_CNT) + dev_warn(&ntb->dev, "multi-port NTB is unsupported\n"); + pp = kmalloc(sizeof(*pp), GFP_KERNEL); if (!pp) { rc = -ENOMEM; diff --git a/drivers/ntb/test/ntb_tool.c b/drivers/ntb/test/ntb_tool.c index 61bf2ef87e0e..690862d90411 100644 --- a/drivers/ntb/test/ntb_tool.c +++ b/drivers/ntb/test/ntb_tool.c @@ -120,6 +120,8 @@ MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESCRIPTION); #define MAX_MWS 16 +/* Only two-ports devices are supported */ +#define PIDX NTB_DEF_PEER_IDX static struct dentry *tool_dbgfs; @@ -919,6 +921,9 @@ static int tool_probe(struct ntb_client *self, struct ntb_dev *ntb) if (ntb_spad_is_unsafe(ntb)) dev_dbg(&ntb->dev, "scratchpad is unsafe\n"); + if (ntb_peer_port_count(ntb) != NTB_DEF_PEER_CNT) + dev_warn(&ntb->dev, "multi-port NTB is unsupported\n"); + tc = kzalloc(sizeof(*tc), GFP_KERNEL); if (!tc) { rc = -ENOMEM; diff --git a/include/linux/ntb.h b/include/linux/ntb.h index d7ab3e1ec88f..d23483bae6f3 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -139,6 +139,20 @@ enum ntb_width { NTB_WIDTH_32 = 32, }; +/** + * enum ntb_default_port - NTB default port number + * @NTB_PORT_PRI_USD: Default port of the NTB_TOPO_PRI/NTB_TOPO_B2B_USD + * topologies + * @NTB_PORT_SEC_DSD: Default port of the NTB_TOPO_SEC/NTB_TOPO_B2B_DSD + * topologies + */ +enum ntb_default_port { + NTB_PORT_PRI_USD, + NTB_PORT_SEC_DSD +}; +#define NTB_DEF_PEER_CNT (1) +#define NTB_DEF_PEER_IDX (0) + /** * struct ntb_client_ops - ntb client operations * @probe: Notify client of a new device. @@ -179,6 +193,10 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) /** * struct ntb_ctx_ops - ntb device operations + * @port_number: See ntb_port_number(). + * @peer_port_count: See ntb_peer_port_count(). + * @peer_port_number: See ntb_peer_port_number(). + * @peer_port_idx: See ntb_peer_port_idx(). * @link_is_up: See ntb_link_is_up(). * @link_enable: See ntb_link_enable(). * @link_disable: See ntb_link_disable(). @@ -212,6 +230,11 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) * @peer_spad_write: See ntb_peer_spad_write(). */ struct ntb_dev_ops { + int (*port_number)(struct ntb_dev *ntb); + int (*peer_port_count)(struct ntb_dev *ntb); + int (*peer_port_number)(struct ntb_dev *ntb, int pidx); + int (*peer_port_idx)(struct ntb_dev *ntb, int port); + int (*link_is_up)(struct ntb_dev *ntb, enum ntb_speed *speed, enum ntb_width *width); int (*link_enable)(struct ntb_dev *ntb, @@ -265,6 +288,9 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops) { /* commented callbacks are not required: */ return + !ops->peer_port_count == !ops->port_number && + !ops->peer_port_number == !ops->port_number && + !ops->peer_port_idx == !ops->port_number && ops->link_is_up && ops->link_enable && ops->link_disable && @@ -441,6 +467,136 @@ void ntb_link_event(struct ntb_dev *ntb); */ void ntb_db_event(struct ntb_dev *ntb, int vector); +/** + * ntb_default_port_number() - get the default local port number + * @ntb: NTB device context. + * + * If hardware driver doesn't specify port_number() callback method, the NTB + * is considered with just two ports. So this method returns default local + * port number in compliance with topology. + * + * NOTE Don't call this method directly. The ntb_port_number() function should + * be used instead. + * + * Return: the default local port number + */ +int ntb_default_port_number(struct ntb_dev *ntb); + +/** + * ntb_default_port_count() - get the default number of peer device ports + * @ntb: NTB device context. + * + * By default hardware driver supports just one peer device. + * + * NOTE Don't call this method directly. The ntb_peer_port_count() function + * should be used instead. + * + * Return: the default number of peer ports + */ +int ntb_default_peer_port_count(struct ntb_dev *ntb); + +/** + * ntb_default_peer_port_number() - get the default peer port by given index + * @ntb: NTB device context. + * @idx: Peer port index (should not differ from zero). + * + * By default hardware driver supports just one peer device, so this method + * shall return the corresponding value from enum ntb_default_port. + * + * NOTE Don't call this method directly. The ntb_peer_port_number() function + * should be used instead. + * + * Return: the peer device port or negative value indicating an error + */ +int ntb_default_peer_port_number(struct ntb_dev *ntb, int pidx); + +/** + * ntb_default_peer_port_idx() - get the default peer device port index by + * given port number + * @ntb: NTB device context. + * @port: Peer port number (should be one of enum ntb_default_port). + * + * By default hardware driver supports just one peer device, so while + * specified port-argument indicates peer port from enum ntb_default_port, + * the return value shall be zero. + * + * NOTE Don't call this method directly. The ntb_peer_port_idx() function + * should be used instead. + * + * Return: the peer port index or negative value indicating an error + */ +int ntb_default_peer_port_idx(struct ntb_dev *ntb, int port); + +/** + * ntb_port_number() - get the local port number + * @ntb: NTB device context. + * + * Hardware must support at least simple two-ports ntb connection + * + * Return: the local port number + */ +static inline int ntb_port_number(struct ntb_dev *ntb) +{ + if (!ntb->ops->port_number) + return ntb_default_port_number(ntb); + + return ntb->ops->port_number(ntb); +} + +/** + * ntb_peer_port_count() - get the number of peer device ports + * @ntb: NTB device context. + * + * Hardware may support an access to memory of several remote domains + * over multi-port NTB devices. This method returns the number of peers, + * local device can have shared memory with. + * + * Return: the number of peer ports + */ +static inline int ntb_peer_port_count(struct ntb_dev *ntb) +{ + if (!ntb->ops->peer_port_count) + return ntb_default_peer_port_count(ntb); + + return ntb->ops->peer_port_count(ntb); +} + +/** + * ntb_peer_port_number() - get the peer port by given index + * @ntb: NTB device context. + * @pidx: Peer port index. + * + * Peer ports are continuously enumerated by NTB API logic, so this method + * lets to retrieve port real number by its index. + * + * Return: the peer device port or negative value indicating an error + */ +static inline int ntb_peer_port_number(struct ntb_dev *ntb, int pidx) +{ + if (!ntb->ops->peer_port_number) + return ntb_default_peer_port_number(ntb, pidx); + + return ntb->ops->peer_port_number(ntb, pidx); +} + +/** + * ntb_peer_port_idx() - get the peer device port index by given port number + * @ntb: NTB device context. + * @port: Peer port number. + * + * Inverse operation of ntb_peer_port_number(), so one can get port index + * by specified port number. + * + * Return: the peer port index or negative value indicating an error + */ +static inline int ntb_peer_port_idx(struct ntb_dev *ntb, int port) +{ + if (!ntb->ops->peer_port_idx) + return ntb_default_peer_port_idx(ntb, port); + + return ntb->ops->peer_port_idx(ntb, port); +} + /** * ntb_link_is_up() - get the current ntb link state * @ntb: NTB device context. -- cgit v1.2.3-59-g8ed1b From 4e8c11b7fd29f70eb7af43bae908297689f2c3da Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Wed, 14 Dec 2016 02:49:15 +0300 Subject: NTB: Alter link-state API to support multi-port devices Multi-port devices permit the NTB connections between multiple domains, so a local device can have NTB link being up with one peer and being down with another. NTB link-state API is appropriately altered to return a bitfield of the link-states between the local device and possible peers. Signed-off-by: Serge Semin Acked-by: Allen Hubbe Signed-off-by: Jon Mason --- drivers/ntb/hw/amd/ntb_hw_amd.c | 2 +- drivers/ntb/hw/intel/ntb_hw_intel.c | 2 +- include/linux/ntb.h | 31 ++++++++++++++++--------------- 3 files changed, 18 insertions(+), 17 deletions(-) diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.c b/drivers/ntb/hw/amd/ntb_hw_amd.c index 019a158e1128..e71ab4c1fe0e 100644 --- a/drivers/ntb/hw/amd/ntb_hw_amd.c +++ b/drivers/ntb/hw/amd/ntb_hw_amd.c @@ -212,7 +212,7 @@ static int amd_link_is_up(struct amd_ntb_dev *ndev) return 0; } -static int amd_ntb_link_is_up(struct ntb_dev *ntb, +static u64 amd_ntb_link_is_up(struct ntb_dev *ntb, enum ntb_speed *speed, enum ntb_width *width) { diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.c b/drivers/ntb/hw/intel/ntb_hw_intel.c index 7b3b6fd63d7d..6b25bf816f28 100644 --- a/drivers/ntb/hw/intel/ntb_hw_intel.c +++ b/drivers/ntb/hw/intel/ntb_hw_intel.c @@ -1171,7 +1171,7 @@ static int intel_ntb_mw_set_trans(struct ntb_dev *ntb, int idx, return 0; } -static int intel_ntb_link_is_up(struct ntb_dev *ntb, +static u64 intel_ntb_link_is_up(struct ntb_dev *ntb, enum ntb_speed *speed, enum ntb_width *width) { diff --git a/include/linux/ntb.h b/include/linux/ntb.h index d23483bae6f3..b2b2924f5f43 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -235,7 +235,7 @@ struct ntb_dev_ops { int (*peer_port_number)(struct ntb_dev *ntb, int pidx); int (*peer_port_idx)(struct ntb_dev *ntb, int port); - int (*link_is_up)(struct ntb_dev *ntb, + u64 (*link_is_up)(struct ntb_dev *ntb, enum ntb_speed *speed, enum ntb_width *width); int (*link_enable)(struct ntb_dev *ntb, enum ntb_speed max_speed, enum ntb_width max_width); @@ -607,25 +607,26 @@ static inline int ntb_peer_port_idx(struct ntb_dev *ntb, int port) * state once after every link event. It is safe to query the link state in * the context of the link event callback. * - * Return: One if the link is up, zero if the link is down, otherwise a - * negative value indicating the error number. + * Return: bitfield of indexed ports link state: bit is set/cleared if the + * link is up/down respectively. */ -static inline int ntb_link_is_up(struct ntb_dev *ntb, +static inline u64 ntb_link_is_up(struct ntb_dev *ntb, enum ntb_speed *speed, enum ntb_width *width) { return ntb->ops->link_is_up(ntb, speed, width); } /** - * ntb_link_enable() - enable the link on the secondary side of the ntb + * ntb_link_enable() - enable the local port ntb connection * @ntb: NTB device context. * @max_speed: The maximum link speed expressed as PCIe generation number. * @max_width: The maximum link width expressed as the number of PCIe lanes. * - * Enable the link on the secondary side of the ntb. This can only be done - * from the primary side of the ntb in primary or b2b topology. The ntb device - * should train the link to its maximum speed and width, or the requested speed - * and width, whichever is smaller, if supported. + * Enable the NTB/PCIe link on the local or remote (for bridge-to-bridge + * topology) side of the bridge. If it's supported the ntb device should train + * the link to its maximum speed and width, or the requested speed and width, + * whichever is smaller. Some hardware doesn't support PCIe link training, so + * the last two arguments will be ignored then. * * Return: Zero on success, otherwise an error number. */ @@ -637,14 +638,14 @@ static inline int ntb_link_enable(struct ntb_dev *ntb, } /** - * ntb_link_disable() - disable the link on the secondary side of the ntb + * ntb_link_disable() - disable the local port ntb connection * @ntb: NTB device context. * - * Disable the link on the secondary side of the ntb. This can only be - * done from the primary side of the ntb in primary or b2b topology. The ntb - * device should disable the link. Returning from this call must indicate that - * a barrier has passed, though with no more writes may pass in either - * direction across the link, except if this call returns an error number. + * Disable the link on the local or remote (for b2b topology) of the ntb. + * The ntb device should disable the link. Returning from this call must + * indicate that a barrier has passed, though with no more writes may pass in + * either direction across the link, except if this call returns an error + * number. * * Return: Zero on success, otherwise an error number. */ -- cgit v1.2.3-59-g8ed1b From 443b9a14ecbe811071467d54d6f2f1182835cc4d Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Wed, 11 Jan 2017 03:11:33 +0300 Subject: NTB: Alter MW API to support multi-ports devices Multi-port NTB devices permit to share a memory between all accessible peers. Memory Windows API is altered to correspondingly initialize and map memory windows for such devices: ntb_mw_count(pidx); - number of inbound memory windows, which can be allocated for shared buffer with specified peer device. ntb_mw_get_align(pidx, widx); - get alignment and size restriction parameters to properly allocate inbound memory region. ntb_peer_mw_count(); - get number of outbound memory windows. ntb_peer_mw_get_addr(widx); - get mapping address of an outbound memory window If hardware supports inbound translation configured on the local ntb port: ntb_mw_set_trans(pidx, widx); - set translation address of allocated inbound memory window so a peer device could access it. ntb_mw_clear_trans(pidx, widx); - clear the translation address of an inbound memory window. If hardware supports outbound translation configured on the peer ntb port: ntb_peer_mw_set_trans(pidx, widx); - set translation address of a memory window retrieved from a peer device ntb_peer_mw_clear_trans(pidx, widx); - clear the translation address of an outbound memory window Signed-off-by: Serge Semin Acked-by: Allen Hubbe Signed-off-by: Jon Mason --- drivers/ntb/hw/amd/ntb_hw_amd.c | 68 +++++++++--- drivers/ntb/hw/intel/ntb_hw_intel.c | 90 ++++++++++++---- drivers/ntb/ntb.c | 2 + drivers/ntb/ntb_transport.c | 21 +++- drivers/ntb/test/ntb_perf.c | 17 ++- drivers/ntb/test/ntb_tool.c | 43 +++++--- include/linux/ntb.h | 208 ++++++++++++++++++++++++++++-------- 7 files changed, 342 insertions(+), 107 deletions(-) diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.c b/drivers/ntb/hw/amd/ntb_hw_amd.c index e71ab4c1fe0e..bcefe1df9ce3 100644 --- a/drivers/ntb/hw/amd/ntb_hw_amd.c +++ b/drivers/ntb/hw/amd/ntb_hw_amd.c @@ -5,6 +5,7 @@ * GPL LICENSE SUMMARY * * Copyright (C) 2016 Advanced Micro Devices, Inc. All Rights Reserved. + * Copyright (C) 2016 T-Platforms. All Rights Reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -13,6 +14,7 @@ * BSD LICENSE * * Copyright (C) 2016 Advanced Micro Devices, Inc. All Rights Reserved. + * Copyright (C) 2016 T-Platforms. All Rights Reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions @@ -79,40 +81,42 @@ static int ndev_mw_to_bar(struct amd_ntb_dev *ndev, int idx) return 1 << idx; } -static int amd_ntb_mw_count(struct ntb_dev *ntb) +static int amd_ntb_mw_count(struct ntb_dev *ntb, int pidx) { + if (pidx != NTB_DEF_PEER_IDX) + return -EINVAL; + return ntb_ndev(ntb)->mw_count; } -static int amd_ntb_mw_get_range(struct ntb_dev *ntb, int idx, - phys_addr_t *base, - resource_size_t *size, - resource_size_t *align, - resource_size_t *align_size) +static int amd_ntb_mw_get_align(struct ntb_dev *ntb, int pidx, int idx, + resource_size_t *addr_align, + resource_size_t *size_align, + resource_size_t *size_max) { struct amd_ntb_dev *ndev = ntb_ndev(ntb); int bar; + if (pidx != NTB_DEF_PEER_IDX) + return -EINVAL; + bar = ndev_mw_to_bar(ndev, idx); if (bar < 0) return bar; - if (base) - *base = pci_resource_start(ndev->ntb.pdev, bar); - - if (size) - *size = pci_resource_len(ndev->ntb.pdev, bar); + if (addr_align) + *addr_align = SZ_4K; - if (align) - *align = SZ_4K; + if (size_align) + *size_align = 1; - if (align_size) - *align_size = 1; + if (size_max) + *size_max = pci_resource_len(ndev->ntb.pdev, bar); return 0; } -static int amd_ntb_mw_set_trans(struct ntb_dev *ntb, int idx, +static int amd_ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int idx, dma_addr_t addr, resource_size_t size) { struct amd_ntb_dev *ndev = ntb_ndev(ntb); @@ -122,6 +126,9 @@ static int amd_ntb_mw_set_trans(struct ntb_dev *ntb, int idx, u64 base_addr, limit, reg_val; int bar; + if (pidx != NTB_DEF_PEER_IDX) + return -EINVAL; + bar = ndev_mw_to_bar(ndev, idx); if (bar < 0) return bar; @@ -284,6 +291,31 @@ static int amd_ntb_link_disable(struct ntb_dev *ntb) return 0; } +static int amd_ntb_peer_mw_count(struct ntb_dev *ntb) +{ + /* The same as for inbound MWs */ + return ntb_ndev(ntb)->mw_count; +} + +static int amd_ntb_peer_mw_get_addr(struct ntb_dev *ntb, int idx, + phys_addr_t *base, resource_size_t *size) +{ + struct amd_ntb_dev *ndev = ntb_ndev(ntb); + int bar; + + bar = ndev_mw_to_bar(ndev, idx); + if (bar < 0) + return bar; + + if (base) + *base = pci_resource_start(ndev->ntb.pdev, bar); + + if (size) + *size = pci_resource_len(ndev->ntb.pdev, bar); + + return 0; +} + static u64 amd_ntb_db_valid_mask(struct ntb_dev *ntb) { return ntb_ndev(ntb)->db_valid_mask; @@ -431,8 +463,10 @@ static int amd_ntb_peer_spad_write(struct ntb_dev *ntb, static const struct ntb_dev_ops amd_ntb_ops = { .mw_count = amd_ntb_mw_count, - .mw_get_range = amd_ntb_mw_get_range, + .mw_get_align = amd_ntb_mw_get_align, .mw_set_trans = amd_ntb_mw_set_trans, + .peer_mw_count = amd_ntb_peer_mw_count, + .peer_mw_get_addr = amd_ntb_peer_mw_get_addr, .link_is_up = amd_ntb_link_is_up, .link_enable = amd_ntb_link_enable, .link_disable = amd_ntb_link_disable, diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.c b/drivers/ntb/hw/intel/ntb_hw_intel.c index 6b25bf816f28..a9b4ed4d7b52 100644 --- a/drivers/ntb/hw/intel/ntb_hw_intel.c +++ b/drivers/ntb/hw/intel/ntb_hw_intel.c @@ -6,6 +6,7 @@ * * Copyright(c) 2012 Intel Corporation. All rights reserved. * Copyright (C) 2015 EMC Corporation. All Rights Reserved. + * Copyright (C) 2016 T-Platforms. All Rights Reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -15,6 +16,7 @@ * * Copyright(c) 2012 Intel Corporation. All rights reserved. * Copyright (C) 2015 EMC Corporation. All Rights Reserved. + * Copyright (C) 2016 T-Platforms. All Rights Reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions @@ -1035,20 +1037,26 @@ static void ndev_deinit_debugfs(struct intel_ntb_dev *ndev) debugfs_remove_recursive(ndev->debugfs_dir); } -static int intel_ntb_mw_count(struct ntb_dev *ntb) +static int intel_ntb_mw_count(struct ntb_dev *ntb, int pidx) { + if (pidx != NTB_DEF_PEER_IDX) + return -EINVAL; + return ntb_ndev(ntb)->mw_count; } -static int intel_ntb_mw_get_range(struct ntb_dev *ntb, int idx, - phys_addr_t *base, - resource_size_t *size, - resource_size_t *align, - resource_size_t *align_size) +static int intel_ntb_mw_get_align(struct ntb_dev *ntb, int pidx, int idx, + resource_size_t *addr_align, + resource_size_t *size_align, + resource_size_t *size_max) { struct intel_ntb_dev *ndev = ntb_ndev(ntb); + resource_size_t bar_size, mw_size; int bar; + if (pidx != NTB_DEF_PEER_IDX) + return -EINVAL; + if (idx >= ndev->b2b_idx && !ndev->b2b_off) idx += 1; @@ -1056,24 +1064,26 @@ static int intel_ntb_mw_get_range(struct ntb_dev *ntb, int idx, if (bar < 0) return bar; - if (base) - *base = pci_resource_start(ndev->ntb.pdev, bar) + - (idx == ndev->b2b_idx ? ndev->b2b_off : 0); + bar_size = pci_resource_len(ndev->ntb.pdev, bar); - if (size) - *size = pci_resource_len(ndev->ntb.pdev, bar) - - (idx == ndev->b2b_idx ? ndev->b2b_off : 0); + if (idx == ndev->b2b_idx) + mw_size = bar_size - ndev->b2b_off; + else + mw_size = bar_size; + + if (addr_align) + *addr_align = pci_resource_len(ndev->ntb.pdev, bar); - if (align) - *align = pci_resource_len(ndev->ntb.pdev, bar); + if (size_align) + *size_align = 1; - if (align_size) - *align_size = 1; + if (size_max) + *size_max = mw_size; return 0; } -static int intel_ntb_mw_set_trans(struct ntb_dev *ntb, int idx, +static int intel_ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int idx, dma_addr_t addr, resource_size_t size) { struct intel_ntb_dev *ndev = ntb_ndev(ntb); @@ -1083,6 +1093,9 @@ static int intel_ntb_mw_set_trans(struct ntb_dev *ntb, int idx, u64 base, limit, reg_val; int bar; + if (pidx != NTB_DEF_PEER_IDX) + return -EINVAL; + if (idx >= ndev->b2b_idx && !ndev->b2b_off) idx += 1; @@ -1249,6 +1262,36 @@ static int intel_ntb_link_disable(struct ntb_dev *ntb) return 0; } +static int intel_ntb_peer_mw_count(struct ntb_dev *ntb) +{ + /* Numbers of inbound and outbound memory windows match */ + return ntb_ndev(ntb)->mw_count; +} + +static int intel_ntb_peer_mw_get_addr(struct ntb_dev *ntb, int idx, + phys_addr_t *base, resource_size_t *size) +{ + struct intel_ntb_dev *ndev = ntb_ndev(ntb); + int bar; + + if (idx >= ndev->b2b_idx && !ndev->b2b_off) + idx += 1; + + bar = ndev_mw_to_bar(ndev, idx); + if (bar < 0) + return bar; + + if (base) + *base = pci_resource_start(ndev->ntb.pdev, bar) + + (idx == ndev->b2b_idx ? ndev->b2b_off : 0); + + if (size) + *size = pci_resource_len(ndev->ntb.pdev, bar) - + (idx == ndev->b2b_idx ? ndev->b2b_off : 0); + + return 0; +} + static int intel_ntb_db_is_unsafe(struct ntb_dev *ntb) { return ndev_ignore_unsafe(ntb_ndev(ntb), NTB_UNSAFE_DB); @@ -1902,7 +1945,7 @@ static int intel_ntb3_link_enable(struct ntb_dev *ntb, return 0; } -static int intel_ntb3_mw_set_trans(struct ntb_dev *ntb, int idx, +static int intel_ntb3_mw_set_trans(struct ntb_dev *ntb, int pidx, int idx, dma_addr_t addr, resource_size_t size) { struct intel_ntb_dev *ndev = ntb_ndev(ntb); @@ -1912,6 +1955,9 @@ static int intel_ntb3_mw_set_trans(struct ntb_dev *ntb, int idx, u64 base, limit, reg_val; int bar; + if (pidx != NTB_DEF_PEER_IDX) + return -EINVAL; + if (idx >= ndev->b2b_idx && !ndev->b2b_off) idx += 1; @@ -2906,8 +2952,10 @@ static const struct intel_ntb_xlat_reg skx_sec_xlat = { /* operations for primary side of local ntb */ static const struct ntb_dev_ops intel_ntb_ops = { .mw_count = intel_ntb_mw_count, - .mw_get_range = intel_ntb_mw_get_range, + .mw_get_align = intel_ntb_mw_get_align, .mw_set_trans = intel_ntb_mw_set_trans, + .peer_mw_count = intel_ntb_peer_mw_count, + .peer_mw_get_addr = intel_ntb_peer_mw_get_addr, .link_is_up = intel_ntb_link_is_up, .link_enable = intel_ntb_link_enable, .link_disable = intel_ntb_link_disable, @@ -2932,8 +2980,10 @@ static const struct ntb_dev_ops intel_ntb_ops = { static const struct ntb_dev_ops intel_ntb3_ops = { .mw_count = intel_ntb_mw_count, - .mw_get_range = intel_ntb_mw_get_range, + .mw_get_align = intel_ntb_mw_get_align, .mw_set_trans = intel_ntb3_mw_set_trans, + .peer_mw_count = intel_ntb_peer_mw_count, + .peer_mw_get_addr = intel_ntb_peer_mw_get_addr, .link_is_up = intel_ntb_link_is_up, .link_enable = intel_ntb3_link_enable, .link_disable = intel_ntb_link_disable, diff --git a/drivers/ntb/ntb.c b/drivers/ntb/ntb.c index 1e92e52813aa..2551bb2ff4a4 100644 --- a/drivers/ntb/ntb.c +++ b/drivers/ntb/ntb.c @@ -5,6 +5,7 @@ * GPL LICENSE SUMMARY * * Copyright (C) 2015 EMC Corporation. All Rights Reserved. + * Copyright (C) 2016 T-Platforms. All Rights Reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -18,6 +19,7 @@ * BSD LICENSE * * Copyright (C) 2015 EMC Corporation. All Rights Reserved. + * Copyright (C) 2016 T-Platforms. All Rights Reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index cc6ae35109b1..771b469cebf0 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -673,7 +673,7 @@ static void ntb_free_mw(struct ntb_transport_ctx *nt, int num_mw) if (!mw->virt_addr) return; - ntb_mw_clear_trans(nt->ndev, num_mw); + ntb_mw_clear_trans(nt->ndev, PIDX, num_mw); dma_free_coherent(&pdev->dev, mw->buff_size, mw->virt_addr, mw->dma_addr); mw->xlat_size = 0; @@ -730,7 +730,8 @@ static int ntb_set_mw(struct ntb_transport_ctx *nt, int num_mw, } /* Notify HW the memory location of the receive buffer */ - rc = ntb_mw_set_trans(nt->ndev, num_mw, mw->dma_addr, mw->xlat_size); + rc = ntb_mw_set_trans(nt->ndev, PIDX, num_mw, mw->dma_addr, + mw->xlat_size); if (rc) { dev_err(&pdev->dev, "Unable to set mw%d translation", num_mw); ntb_free_mw(nt, num_mw); @@ -1058,7 +1059,12 @@ static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev) int node; int rc, i; - mw_count = ntb_mw_count(ndev); + mw_count = ntb_mw_count(ndev, PIDX); + + if (!ndev->ops->mw_set_trans) { + dev_err(&ndev->dev, "Inbound MW based NTB API is required\n"); + return -EINVAL; + } if (ntb_db_is_unsafe(ndev)) dev_dbg(&ndev->dev, @@ -1100,8 +1106,13 @@ static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev) for (i = 0; i < mw_count; i++) { mw = &nt->mw_vec[i]; - rc = ntb_mw_get_range(ndev, i, &mw->phys_addr, &mw->phys_size, - &mw->xlat_align, &mw->xlat_align_size); + rc = ntb_mw_get_align(ndev, PIDX, i, &mw->xlat_align, + &mw->xlat_align_size, NULL); + if (rc) + goto err1; + + rc = ntb_peer_mw_get_addr(ndev, i, &mw->phys_addr, + &mw->phys_size); if (rc) goto err1; diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c index e52cc4eace90..7f89cceaf350 100644 --- a/drivers/ntb/test/ntb_perf.c +++ b/drivers/ntb/test/ntb_perf.c @@ -455,7 +455,7 @@ static void perf_free_mw(struct perf_ctx *perf) if (!mw->virt_addr) return; - ntb_mw_clear_trans(perf->ntb, 0); + ntb_mw_clear_trans(perf->ntb, PIDX, 0); dma_free_coherent(&pdev->dev, mw->buf_size, mw->virt_addr, mw->dma_addr); mw->xlat_size = 0; @@ -491,7 +491,7 @@ static int perf_set_mw(struct perf_ctx *perf, resource_size_t size) mw->buf_size = 0; } - rc = ntb_mw_set_trans(perf->ntb, 0, mw->dma_addr, mw->xlat_size); + rc = ntb_mw_set_trans(perf->ntb, PIDX, 0, mw->dma_addr, mw->xlat_size); if (rc) { dev_err(&perf->ntb->dev, "Unable to set mw0 translation\n"); perf_free_mw(perf); @@ -562,8 +562,12 @@ static int perf_setup_mw(struct ntb_dev *ntb, struct perf_ctx *perf) mw = &perf->mw; - rc = ntb_mw_get_range(ntb, 0, &mw->phys_addr, &mw->phys_size, - &mw->xlat_align, &mw->xlat_align_size); + rc = ntb_mw_get_align(ntb, PIDX, 0, &mw->xlat_align, + &mw->xlat_align_size, NULL); + if (rc) + return rc; + + rc = ntb_peer_mw_get_addr(ntb, 0, &mw->phys_addr, &mw->phys_size); if (rc) return rc; @@ -767,6 +771,11 @@ static int perf_probe(struct ntb_client *client, struct ntb_dev *ntb) return -EIO; } + if (!ntb->ops->mw_set_trans) { + dev_err(&ntb->dev, "Need inbound MW based NTB API\n"); + return -EINVAL; + } + if (ntb_peer_port_count(ntb) != NTB_DEF_PEER_CNT) dev_warn(&ntb->dev, "Multi-port NTB devices unsupported\n"); diff --git a/drivers/ntb/test/ntb_tool.c b/drivers/ntb/test/ntb_tool.c index 690862d90411..cb692473d457 100644 --- a/drivers/ntb/test/ntb_tool.c +++ b/drivers/ntb/test/ntb_tool.c @@ -119,7 +119,8 @@ MODULE_VERSION(DRIVER_VERSION); MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESCRIPTION); -#define MAX_MWS 16 +/* It is rare to have hadrware with greater than six MWs */ +#define MAX_MWS 6 /* Only two-ports devices are supported */ #define PIDX NTB_DEF_PEER_IDX @@ -670,28 +671,27 @@ static int tool_setup_mw(struct tool_ctx *tc, int idx, size_t req_size) { int rc; struct tool_mw *mw = &tc->mws[idx]; - phys_addr_t base; - resource_size_t size, align, align_size; + resource_size_t size, align_addr, align_size; char buf[16]; if (mw->peer) return 0; - rc = ntb_mw_get_range(tc->ntb, idx, &base, &size, &align, - &align_size); + rc = ntb_mw_get_align(tc->ntb, PIDX, idx, &align_addr, + &align_size, &size); if (rc) return rc; mw->size = min_t(resource_size_t, req_size, size); - mw->size = round_up(mw->size, align); + mw->size = round_up(mw->size, align_addr); mw->size = round_up(mw->size, align_size); mw->peer = dma_alloc_coherent(&tc->ntb->pdev->dev, mw->size, &mw->peer_dma, GFP_KERNEL); - if (!mw->peer) + if (!mw->peer || !IS_ALIGNED(mw->peer_dma, align_addr)) return -ENOMEM; - rc = ntb_mw_set_trans(tc->ntb, idx, mw->peer_dma, mw->size); + rc = ntb_mw_set_trans(tc->ntb, PIDX, idx, mw->peer_dma, mw->size); if (rc) goto err_free_dma; @@ -718,7 +718,7 @@ static void tool_free_mw(struct tool_ctx *tc, int idx) struct tool_mw *mw = &tc->mws[idx]; if (mw->peer) { - ntb_mw_clear_trans(tc->ntb, idx); + ntb_mw_clear_trans(tc->ntb, PIDX, idx); dma_free_coherent(&tc->ntb->pdev->dev, mw->size, mw->peer, mw->peer_dma); @@ -744,8 +744,9 @@ static ssize_t tool_peer_mw_trans_read(struct file *filep, phys_addr_t base; resource_size_t mw_size; - resource_size_t align; + resource_size_t align_addr; resource_size_t align_size; + resource_size_t max_size; buf_size = min_t(size_t, size, 512); @@ -753,8 +754,9 @@ static ssize_t tool_peer_mw_trans_read(struct file *filep, if (!buf) return -ENOMEM; - ntb_mw_get_range(mw->tc->ntb, mw->idx, - &base, &mw_size, &align, &align_size); + ntb_mw_get_align(mw->tc->ntb, PIDX, mw->idx, + &align_addr, &align_size, &max_size); + ntb_peer_mw_get_addr(mw->tc->ntb, mw->idx, &base, &mw_size); off += scnprintf(buf + off, buf_size - off, "Peer MW %d Information:\n", mw->idx); @@ -769,12 +771,16 @@ static ssize_t tool_peer_mw_trans_read(struct file *filep, off += scnprintf(buf + off, buf_size - off, "Alignment \t%lld\n", - (unsigned long long)align); + (unsigned long long)align_addr); off += scnprintf(buf + off, buf_size - off, "Size Alignment \t%lld\n", (unsigned long long)align_size); + off += scnprintf(buf + off, buf_size - off, + "Size Max \t%lld\n", + (unsigned long long)max_size); + off += scnprintf(buf + off, buf_size - off, "Ready \t%c\n", (mw->peer) ? 'Y' : 'N'); @@ -829,8 +835,7 @@ static int tool_init_mw(struct tool_ctx *tc, int idx) phys_addr_t base; int rc; - rc = ntb_mw_get_range(tc->ntb, idx, &base, &mw->win_size, - NULL, NULL); + rc = ntb_peer_mw_get_addr(tc->ntb, idx, &base, &mw->win_size); if (rc) return rc; @@ -915,6 +920,12 @@ static int tool_probe(struct ntb_client *self, struct ntb_dev *ntb) int rc; int i; + if (!ntb->ops->mw_set_trans) { + dev_dbg(&ntb->dev, "need inbound MW based NTB API\n"); + rc = -EINVAL; + goto err_tc; + } + if (ntb_db_is_unsafe(ntb)) dev_dbg(&ntb->dev, "doorbell is unsafe\n"); @@ -933,7 +944,7 @@ static int tool_probe(struct ntb_client *self, struct ntb_dev *ntb) tc->ntb = ntb; init_waitqueue_head(&tc->link_wq); - tc->mw_count = min(ntb_mw_count(tc->ntb), MAX_MWS); + tc->mw_count = min(ntb_mw_count(tc->ntb, PIDX), MAX_MWS); for (i = 0; i < tc->mw_count; i++) { rc = tool_init_mw(tc, i); if (rc) diff --git a/include/linux/ntb.h b/include/linux/ntb.h index b2b2924f5f43..2ea83f91a236 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -5,6 +5,7 @@ * GPL LICENSE SUMMARY * * Copyright (C) 2015 EMC Corporation. All Rights Reserved. + * Copyright (C) 2016 T-Platforms. All Rights Reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -18,6 +19,7 @@ * BSD LICENSE * * Copyright (C) 2015 EMC Corporation. All Rights Reserved. + * Copyright (C) 2016 T-Platforms. All Rights Reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions @@ -201,9 +203,13 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) * @link_enable: See ntb_link_enable(). * @link_disable: See ntb_link_disable(). * @mw_count: See ntb_mw_count(). - * @mw_get_range: See ntb_mw_get_range(). + * @mw_get_align: See ntb_mw_get_align(). * @mw_set_trans: See ntb_mw_set_trans(). * @mw_clear_trans: See ntb_mw_clear_trans(). + * @peer_mw_count: See ntb_peer_mw_count(). + * @peer_mw_get_addr: See ntb_peer_mw_get_addr(). + * @peer_mw_set_trans: See ntb_peer_mw_set_trans(). + * @peer_mw_clear_trans:See ntb_peer_mw_clear_trans(). * @db_is_unsafe: See ntb_db_is_unsafe(). * @db_valid_mask: See ntb_db_valid_mask(). * @db_vector_count: See ntb_db_vector_count(). @@ -241,13 +247,20 @@ struct ntb_dev_ops { enum ntb_speed max_speed, enum ntb_width max_width); int (*link_disable)(struct ntb_dev *ntb); - int (*mw_count)(struct ntb_dev *ntb); - int (*mw_get_range)(struct ntb_dev *ntb, int idx, - phys_addr_t *base, resource_size_t *size, - resource_size_t *align, resource_size_t *align_size); - int (*mw_set_trans)(struct ntb_dev *ntb, int idx, + int (*mw_count)(struct ntb_dev *ntb, int pidx); + int (*mw_get_align)(struct ntb_dev *ntb, int pidx, int widx, + resource_size_t *addr_align, + resource_size_t *size_align, + resource_size_t *size_max); + int (*mw_set_trans)(struct ntb_dev *ntb, int pidx, int widx, dma_addr_t addr, resource_size_t size); - int (*mw_clear_trans)(struct ntb_dev *ntb, int idx); + int (*mw_clear_trans)(struct ntb_dev *ntb, int pidx, int widx); + int (*peer_mw_count)(struct ntb_dev *ntb); + int (*peer_mw_get_addr)(struct ntb_dev *ntb, int widx, + phys_addr_t *base, resource_size_t *size); + int (*peer_mw_set_trans)(struct ntb_dev *ntb, int pidx, int widx, + u64 addr, resource_size_t size); + int (*peer_mw_clear_trans)(struct ntb_dev *ntb, int pidx, int widx); int (*db_is_unsafe)(struct ntb_dev *ntb); u64 (*db_valid_mask)(struct ntb_dev *ntb); @@ -295,9 +308,13 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops) ops->link_enable && ops->link_disable && ops->mw_count && - ops->mw_get_range && - ops->mw_set_trans && + ops->mw_get_align && + (ops->mw_set_trans || + ops->peer_mw_set_trans) && /* ops->mw_clear_trans && */ + ops->peer_mw_count && + ops->peer_mw_get_addr && + /* ops->peer_mw_clear_trans && */ /* ops->db_is_unsafe && */ ops->db_valid_mask && @@ -655,79 +672,180 @@ static inline int ntb_link_disable(struct ntb_dev *ntb) } /** - * ntb_mw_count() - get the number of memory windows + * ntb_mw_count() - get the number of inbound memory windows, which could + * be created for a specified peer device * @ntb: NTB device context. + * @pidx: Port index of peer device. * * Hardware and topology may support a different number of memory windows. + * Moreover different peer devices can support different number of memory + * windows. Simply speaking this method returns the number of possible inbound + * memory windows to share with specified peer device. * * Return: the number of memory windows. */ -static inline int ntb_mw_count(struct ntb_dev *ntb) +static inline int ntb_mw_count(struct ntb_dev *ntb, int pidx) { - return ntb->ops->mw_count(ntb); + return ntb->ops->mw_count(ntb, pidx); } /** - * ntb_mw_get_range() - get the range of a memory window + * ntb_mw_get_align() - get the restriction parameters of inbound memory window * @ntb: NTB device context. - * @idx: Memory window number. - * @base: OUT - the base address for mapping the memory window - * @size: OUT - the size for mapping the memory window - * @align: OUT - the base alignment for translating the memory window - * @align_size: OUT - the size alignment for translating the memory window - * - * Get the range of a memory window. NULL may be given for any output - * parameter if the value is not needed. The base and size may be used for - * mapping the memory window, to access the peer memory. The alignment and - * size may be used for translating the memory window, for the peer to access - * memory on the local system. - * - * Return: Zero on success, otherwise an error number. + * @pidx: Port index of peer device. + * @widx: Memory window index. + * @addr_align: OUT - the base alignment for translating the memory window + * @size_align: OUT - the size alignment for translating the memory window + * @size_max: OUT - the maximum size of the memory window + * + * Get the alignments of an inbound memory window with specified index. + * NULL may be given for any output parameter if the value is not needed. + * The alignment and size parameters may be used for allocation of proper + * shared memory. + * + * Return: Zero on success, otherwise a negative error number. */ -static inline int ntb_mw_get_range(struct ntb_dev *ntb, int idx, - phys_addr_t *base, resource_size_t *size, - resource_size_t *align, resource_size_t *align_size) +static inline int ntb_mw_get_align(struct ntb_dev *ntb, int pidx, int widx, + resource_size_t *addr_align, + resource_size_t *size_align, + resource_size_t *size_max) { - return ntb->ops->mw_get_range(ntb, idx, base, size, - align, align_size); + return ntb->ops->mw_get_align(ntb, pidx, widx, addr_align, size_align, + size_max); } /** - * ntb_mw_set_trans() - set the translation of a memory window + * ntb_mw_set_trans() - set the translation of an inbound memory window * @ntb: NTB device context. - * @idx: Memory window number. - * @addr: The dma address local memory to expose to the peer. + * @pidx: Port index of peer device. + * @widx: Memory window index. + * @addr: The dma address of local memory to expose to the peer. * @size: The size of the local memory to expose to the peer. * * Set the translation of a memory window. The peer may access local memory * through the window starting at the address, up to the size. The address - * must be aligned to the alignment specified by ntb_mw_get_range(). The size - * must be aligned to the size alignment specified by ntb_mw_get_range(). + * and size must be aligned in compliance with restrictions of + * ntb_mw_get_align(). The region size should not exceed the size_max parameter + * of that method. + * + * This method may not be implemented due to the hardware specific memory + * windows interface. * * Return: Zero on success, otherwise an error number. */ -static inline int ntb_mw_set_trans(struct ntb_dev *ntb, int idx, +static inline int ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx, dma_addr_t addr, resource_size_t size) { - return ntb->ops->mw_set_trans(ntb, idx, addr, size); + if (!ntb->ops->mw_set_trans) + return 0; + + return ntb->ops->mw_set_trans(ntb, pidx, widx, addr, size); } /** - * ntb_mw_clear_trans() - clear the translation of a memory window + * ntb_mw_clear_trans() - clear the translation address of an inbound memory + * window * @ntb: NTB device context. - * @idx: Memory window number. + * @pidx: Port index of peer device. + * @widx: Memory window index. * - * Clear the translation of a memory window. The peer may no longer access - * local memory through the window. + * Clear the translation of an inbound memory window. The peer may no longer + * access local memory through the window. * * Return: Zero on success, otherwise an error number. */ -static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int idx) +static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int pidx, int widx) { if (!ntb->ops->mw_clear_trans) - return ntb->ops->mw_set_trans(ntb, idx, 0, 0); + return ntb_mw_set_trans(ntb, pidx, widx, 0, 0); + + return ntb->ops->mw_clear_trans(ntb, pidx, widx); +} + +/** + * ntb_peer_mw_count() - get the number of outbound memory windows, which could + * be mapped to access a shared memory + * @ntb: NTB device context. + * + * Hardware and topology may support a different number of memory windows. + * This method returns the number of outbound memory windows supported by + * local device. + * + * Return: the number of memory windows. + */ +static inline int ntb_peer_mw_count(struct ntb_dev *ntb) +{ + return ntb->ops->peer_mw_count(ntb); +} + +/** + * ntb_peer_mw_get_addr() - get map address of an outbound memory window + * @ntb: NTB device context. + * @widx: Memory window index (within ntb_peer_mw_count() return value). + * @base: OUT - the base address of mapping region. + * @size: OUT - the size of mapping region. + * + * Get base and size of memory region to map. NULL may be given for any output + * parameter if the value is not needed. The base and size may be used for + * mapping the memory window, to access the peer memory. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_peer_mw_get_addr(struct ntb_dev *ntb, int widx, + phys_addr_t *base, resource_size_t *size) +{ + return ntb->ops->peer_mw_get_addr(ntb, widx, base, size); +} + +/** + * ntb_peer_mw_set_trans() - set a translation address of a memory window + * retrieved from a peer device + * @ntb: NTB device context. + * @pidx: Port index of peer device the translation address received from. + * @widx: Memory window index. + * @addr: The dma address of the shared memory to access. + * @size: The size of the shared memory to access. + * + * Set the translation of an outbound memory window. The local device may + * access shared memory allocated by a peer device sent the address. + * + * This method may not be implemented due to the hardware specific memory + * windows interface, so a translation address can be only set on the side, + * where shared memory (inbound memory windows) is allocated. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx, + u64 addr, resource_size_t size) +{ + if (!ntb->ops->peer_mw_set_trans) + return 0; + + return ntb->ops->peer_mw_set_trans(ntb, pidx, widx, addr, size); +} + +/** + * ntb_peer_mw_clear_trans() - clear the translation address of an outbound + * memory window + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * @widx: Memory window index. + * + * Clear the translation of a outbound memory window. The local device may no + * longer access a shared memory through the window. + * + * This method may not be implemented due to the hardware specific memory + * windows interface. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_mw_clear_trans(struct ntb_dev *ntb, int pidx, + int widx) +{ + if (!ntb->ops->peer_mw_clear_trans) + return ntb_peer_mw_set_trans(ntb, pidx, widx, 0, 0); - return ntb->ops->mw_clear_trans(ntb, idx); + return ntb->ops->peer_mw_clear_trans(ntb, pidx, widx); } /** -- cgit v1.2.3-59-g8ed1b From d67288a39584daad11edee9b03d53264ba147453 Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Wed, 11 Jan 2017 03:13:20 +0300 Subject: NTB: Alter Scratchpads API to support multi-ports devices Even though there is no any real NTB hardware, which would have both more than two ports and Scratchpad registers, it is logically correct to have Scratchpad API accepting a peer port index as well. Intel/AMD drivers utilize Primary and Secondary topology to split Scratchpad between connected root devices. Since port-index API introduced, Intel/AMD NTB hardware drivers can use device port to determine which Scratchpad registers actually belong to local and peer devices. The same approach can be used if some potential hardware in future will be multi-port and have some set of Scratchpads. Here are the brief of changes in the API: ntb_spad_count() - return number of Scratchpads per each port ntb_peer_spad_addr(pidx, sidx) - address of Scratchpad register of the peer device with pidx-index ntb_peer_spad_read(pidx, sidx) - read specified Scratchpad register of the peer with pidx-index ntb_peer_spad_write(pidx, sidx) - write data to Scratchpad register of the peer with pidx-index Since there is hardware which doesn't support Scratchpad registers, the corresponding API methods are now made optional. Signed-off-by: Serge Semin Acked-by: Allen Hubbe Signed-off-by: Jon Mason --- drivers/ntb/hw/amd/ntb_hw_amd.c | 14 +++---- drivers/ntb/hw/intel/ntb_hw_intel.c | 14 +++---- drivers/ntb/ntb_transport.c | 15 ++++---- drivers/ntb/test/ntb_perf.c | 6 +-- drivers/ntb/test/ntb_pingpong.c | 8 +++- drivers/ntb/test/ntb_tool.c | 21 +++++++++-- include/linux/ntb.h | 73 +++++++++++++++++++++++-------------- 7 files changed, 94 insertions(+), 57 deletions(-) diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.c b/drivers/ntb/hw/amd/ntb_hw_amd.c index bcefe1df9ce3..891beb9f26c2 100644 --- a/drivers/ntb/hw/amd/ntb_hw_amd.c +++ b/drivers/ntb/hw/amd/ntb_hw_amd.c @@ -432,30 +432,30 @@ static int amd_ntb_spad_write(struct ntb_dev *ntb, return 0; } -static u32 amd_ntb_peer_spad_read(struct ntb_dev *ntb, int idx) +static u32 amd_ntb_peer_spad_read(struct ntb_dev *ntb, int pidx, int sidx) { struct amd_ntb_dev *ndev = ntb_ndev(ntb); void __iomem *mmio = ndev->self_mmio; u32 offset; - if (idx < 0 || idx >= ndev->spad_count) + if (sidx < 0 || sidx >= ndev->spad_count) return -EINVAL; - offset = ndev->peer_spad + (idx << 2); + offset = ndev->peer_spad + (sidx << 2); return readl(mmio + AMD_SPAD_OFFSET + offset); } -static int amd_ntb_peer_spad_write(struct ntb_dev *ntb, - int idx, u32 val) +static int amd_ntb_peer_spad_write(struct ntb_dev *ntb, int pidx, + int sidx, u32 val) { struct amd_ntb_dev *ndev = ntb_ndev(ntb); void __iomem *mmio = ndev->self_mmio; u32 offset; - if (idx < 0 || idx >= ndev->spad_count) + if (sidx < 0 || sidx >= ndev->spad_count) return -EINVAL; - offset = ndev->peer_spad + (idx << 2); + offset = ndev->peer_spad + (sidx << 2); writel(val, mmio + AMD_SPAD_OFFSET + offset); return 0; diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.c b/drivers/ntb/hw/intel/ntb_hw_intel.c index a9b4ed4d7b52..e00aa39a4544 100644 --- a/drivers/ntb/hw/intel/ntb_hw_intel.c +++ b/drivers/ntb/hw/intel/ntb_hw_intel.c @@ -1409,30 +1409,30 @@ static int intel_ntb_spad_write(struct ntb_dev *ntb, ndev->self_reg->spad); } -static int intel_ntb_peer_spad_addr(struct ntb_dev *ntb, int idx, +static int intel_ntb_peer_spad_addr(struct ntb_dev *ntb, int pidx, int sidx, phys_addr_t *spad_addr) { struct intel_ntb_dev *ndev = ntb_ndev(ntb); - return ndev_spad_addr(ndev, idx, spad_addr, ndev->peer_addr, + return ndev_spad_addr(ndev, sidx, spad_addr, ndev->peer_addr, ndev->peer_reg->spad); } -static u32 intel_ntb_peer_spad_read(struct ntb_dev *ntb, int idx) +static u32 intel_ntb_peer_spad_read(struct ntb_dev *ntb, int pidx, int sidx) { struct intel_ntb_dev *ndev = ntb_ndev(ntb); - return ndev_spad_read(ndev, idx, + return ndev_spad_read(ndev, sidx, ndev->peer_mmio + ndev->peer_reg->spad); } -static int intel_ntb_peer_spad_write(struct ntb_dev *ntb, - int idx, u32 val) +static int intel_ntb_peer_spad_write(struct ntb_dev *ntb, int pidx, + int sidx, u32 val) { struct intel_ntb_dev *ndev = ntb_ndev(ntb); - return ndev_spad_write(ndev, idx, val, + return ndev_spad_write(ndev, sidx, val, ndev->peer_mmio + ndev->peer_reg->spad); } diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index 771b469cebf0..9a03c5871efe 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -862,17 +862,17 @@ static void ntb_transport_link_work(struct work_struct *work) size = max_mw_size; spad = MW0_SZ_HIGH + (i * 2); - ntb_peer_spad_write(ndev, spad, upper_32_bits(size)); + ntb_peer_spad_write(ndev, PIDX, spad, upper_32_bits(size)); spad = MW0_SZ_LOW + (i * 2); - ntb_peer_spad_write(ndev, spad, lower_32_bits(size)); + ntb_peer_spad_write(ndev, PIDX, spad, lower_32_bits(size)); } - ntb_peer_spad_write(ndev, NUM_MWS, nt->mw_count); + ntb_peer_spad_write(ndev, PIDX, NUM_MWS, nt->mw_count); - ntb_peer_spad_write(ndev, NUM_QPS, nt->qp_count); + ntb_peer_spad_write(ndev, PIDX, NUM_QPS, nt->qp_count); - ntb_peer_spad_write(ndev, VERSION, NTB_TRANSPORT_VERSION); + ntb_peer_spad_write(ndev, PIDX, VERSION, NTB_TRANSPORT_VERSION); /* Query the remote side for its info */ val = ntb_spad_read(ndev, VERSION); @@ -948,7 +948,7 @@ static void ntb_qp_link_work(struct work_struct *work) val = ntb_spad_read(nt->ndev, QP_LINKS); - ntb_peer_spad_write(nt->ndev, QP_LINKS, val | BIT(qp->qp_num)); + ntb_peer_spad_write(nt->ndev, PIDX, QP_LINKS, val | BIT(qp->qp_num)); /* query remote spad for qp ready bits */ dev_dbg_ratelimited(&pdev->dev, "Remote QP link status = %x\n", val); @@ -2108,8 +2108,7 @@ void ntb_transport_link_down(struct ntb_transport_qp *qp) val = ntb_spad_read(qp->ndev, QP_LINKS); - ntb_peer_spad_write(qp->ndev, QP_LINKS, - val & ~BIT(qp->qp_num)); + ntb_peer_spad_write(qp->ndev, PIDX, QP_LINKS, val & ~BIT(qp->qp_num)); if (qp->link_is_up) ntb_send_link_down(qp); diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c index 7f89cceaf350..42756a98a728 100644 --- a/drivers/ntb/test/ntb_perf.c +++ b/drivers/ntb/test/ntb_perf.c @@ -518,9 +518,9 @@ static void perf_link_work(struct work_struct *work) if (max_mw_size && size > max_mw_size) size = max_mw_size; - ntb_peer_spad_write(ndev, MW_SZ_HIGH, upper_32_bits(size)); - ntb_peer_spad_write(ndev, MW_SZ_LOW, lower_32_bits(size)); - ntb_peer_spad_write(ndev, VERSION, PERF_VERSION); + ntb_peer_spad_write(ndev, PIDX, MW_SZ_HIGH, upper_32_bits(size)); + ntb_peer_spad_write(ndev, PIDX, MW_SZ_LOW, lower_32_bits(size)); + ntb_peer_spad_write(ndev, PIDX, VERSION, PERF_VERSION); /* now read what peer wrote */ val = ntb_spad_read(ndev, VERSION); diff --git a/drivers/ntb/test/ntb_pingpong.c b/drivers/ntb/test/ntb_pingpong.c index 12f8b40cb11a..938a18bcfc3f 100644 --- a/drivers/ntb/test/ntb_pingpong.c +++ b/drivers/ntb/test/ntb_pingpong.c @@ -138,7 +138,7 @@ static void pp_ping(unsigned long ctx) "Ping bits %#llx read %#x write %#x\n", db_bits, spad_rd, spad_wr); - ntb_peer_spad_write(pp->ntb, 0, spad_wr); + ntb_peer_spad_write(pp->ntb, PIDX, 0, spad_wr); ntb_peer_db_set(pp->ntb, db_bits); ntb_db_clear_mask(pp->ntb, db_mask); @@ -225,6 +225,12 @@ static int pp_probe(struct ntb_client *client, } } + if (ntb_spad_count(ntb) < 1) { + dev_dbg(&ntb->dev, "no enough scratchpads\n"); + rc = -EINVAL; + goto err_pp; + } + if (ntb_spad_is_unsafe(ntb)) { dev_dbg(&ntb->dev, "scratchpad is unsafe\n"); if (!unsafe) { diff --git a/drivers/ntb/test/ntb_tool.c b/drivers/ntb/test/ntb_tool.c index cb692473d457..f002bf48a08d 100644 --- a/drivers/ntb/test/ntb_tool.c +++ b/drivers/ntb/test/ntb_tool.c @@ -462,13 +462,22 @@ static TOOL_FOPS_RDWR(tool_spad_fops, tool_spad_read, tool_spad_write); +static u32 ntb_tool_peer_spad_read(struct ntb_dev *ntb, int sidx) +{ + return ntb_peer_spad_read(ntb, PIDX, sidx); +} + static ssize_t tool_peer_spad_read(struct file *filep, char __user *ubuf, size_t size, loff_t *offp) { struct tool_ctx *tc = filep->private_data; - return tool_spadfn_read(tc, ubuf, size, offp, - tc->ntb->ops->peer_spad_read); + return tool_spadfn_read(tc, ubuf, size, offp, ntb_tool_peer_spad_read); +} + +static int ntb_tool_peer_spad_write(struct ntb_dev *ntb, int sidx, u32 val) +{ + return ntb_peer_spad_write(ntb, PIDX, sidx, val); } static ssize_t tool_peer_spad_write(struct file *filep, const char __user *ubuf, @@ -477,7 +486,7 @@ static ssize_t tool_peer_spad_write(struct file *filep, const char __user *ubuf, struct tool_ctx *tc = filep->private_data; return tool_spadfn_write(tc, ubuf, size, offp, - tc->ntb->ops->peer_spad_write); + ntb_tool_peer_spad_write); } static TOOL_FOPS_RDWR(tool_peer_spad_fops, @@ -926,6 +935,12 @@ static int tool_probe(struct ntb_client *self, struct ntb_dev *ntb) goto err_tc; } + if (ntb_spad_count(ntb) < 1) { + dev_dbg(&ntb->dev, "no enough scratchpads\n"); + rc = -EINVAL; + goto err_tc; + } + if (ntb_db_is_unsafe(ntb)) dev_dbg(&ntb->dev, "doorbell is unsafe\n"); diff --git a/include/linux/ntb.h b/include/linux/ntb.h index 2ea83f91a236..4e3cd56af732 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -288,13 +288,14 @@ struct ntb_dev_ops { int (*spad_is_unsafe)(struct ntb_dev *ntb); int (*spad_count)(struct ntb_dev *ntb); - u32 (*spad_read)(struct ntb_dev *ntb, int idx); - int (*spad_write)(struct ntb_dev *ntb, int idx, u32 val); + u32 (*spad_read)(struct ntb_dev *ntb, int sidx); + int (*spad_write)(struct ntb_dev *ntb, int sidx, u32 val); - int (*peer_spad_addr)(struct ntb_dev *ntb, int idx, + int (*peer_spad_addr)(struct ntb_dev *ntb, int pidx, int sidx, phys_addr_t *spad_addr); - u32 (*peer_spad_read)(struct ntb_dev *ntb, int idx); - int (*peer_spad_write)(struct ntb_dev *ntb, int idx, u32 val); + u32 (*peer_spad_read)(struct ntb_dev *ntb, int pidx, int sidx); + int (*peer_spad_write)(struct ntb_dev *ntb, int pidx, int sidx, + u32 val); }; static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops) @@ -335,13 +336,12 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops) /* ops->peer_db_read_mask && */ /* ops->peer_db_set_mask && */ /* ops->peer_db_clear_mask && */ - /* ops->spad_is_unsafe && */ - ops->spad_count && - ops->spad_read && - ops->spad_write && - /* ops->peer_spad_addr && */ - /* ops->peer_spad_read && */ - ops->peer_spad_write && + /* !ops->spad_is_unsafe == !ops->spad_count && */ + !ops->spad_read == !ops->spad_count && + !ops->spad_write == !ops->spad_count && + /* !ops->peer_spad_addr == !ops->spad_count && */ + /* !ops->peer_spad_read == !ops->spad_count && */ + !ops->peer_spad_write == !ops->spad_count && 1; } @@ -1176,47 +1176,58 @@ static inline int ntb_spad_is_unsafe(struct ntb_dev *ntb) * @ntb: NTB device context. * * Hardware and topology may support a different number of scratchpads. + * Although it must be the same for all ports per NTB device. * * Return: the number of scratchpads. */ static inline int ntb_spad_count(struct ntb_dev *ntb) { + if (!ntb->ops->spad_count) + return 0; + return ntb->ops->spad_count(ntb); } /** * ntb_spad_read() - read the local scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @sidx: Scratchpad index. * * Read the local scratchpad register, and return the value. * * Return: The value of the local scratchpad register. */ -static inline u32 ntb_spad_read(struct ntb_dev *ntb, int idx) +static inline u32 ntb_spad_read(struct ntb_dev *ntb, int sidx) { - return ntb->ops->spad_read(ntb, idx); + if (!ntb->ops->spad_read) + return ~(u32)0; + + return ntb->ops->spad_read(ntb, sidx); } /** * ntb_spad_write() - write the local scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @sidx: Scratchpad index. * @val: Scratchpad value. * * Write the value to the local scratchpad register. * * Return: Zero on success, otherwise an error number. */ -static inline int ntb_spad_write(struct ntb_dev *ntb, int idx, u32 val) +static inline int ntb_spad_write(struct ntb_dev *ntb, int sidx, u32 val) { - return ntb->ops->spad_write(ntb, idx, val); + if (!ntb->ops->spad_write) + return -EINVAL; + + return ntb->ops->spad_write(ntb, sidx, val); } /** * ntb_peer_spad_addr() - address of the peer scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @pidx: Port index of peer device. + * @sidx: Scratchpad index. * @spad_addr: OUT - The address of the peer scratchpad register. * * Return the address of the peer doorbell register. This may be used, for @@ -1224,45 +1235,51 @@ static inline int ntb_spad_write(struct ntb_dev *ntb, int idx, u32 val) * * Return: Zero on success, otherwise an error number. */ -static inline int ntb_peer_spad_addr(struct ntb_dev *ntb, int idx, +static inline int ntb_peer_spad_addr(struct ntb_dev *ntb, int pidx, int sidx, phys_addr_t *spad_addr) { if (!ntb->ops->peer_spad_addr) return -EINVAL; - return ntb->ops->peer_spad_addr(ntb, idx, spad_addr); + return ntb->ops->peer_spad_addr(ntb, pidx, sidx, spad_addr); } /** * ntb_peer_spad_read() - read the peer scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @pidx: Port index of peer device. + * @sidx: Scratchpad index. * * Read the peer scratchpad register, and return the value. * * Return: The value of the local scratchpad register. */ -static inline u32 ntb_peer_spad_read(struct ntb_dev *ntb, int idx) +static inline u32 ntb_peer_spad_read(struct ntb_dev *ntb, int pidx, int sidx) { if (!ntb->ops->peer_spad_read) - return 0; + return ~(u32)0; - return ntb->ops->peer_spad_read(ntb, idx); + return ntb->ops->peer_spad_read(ntb, pidx, sidx); } /** * ntb_peer_spad_write() - write the peer scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @pidx: Port index of peer device. + * @sidx: Scratchpad index. * @val: Scratchpad value. * * Write the value to the peer scratchpad register. * * Return: Zero on success, otherwise an error number. */ -static inline int ntb_peer_spad_write(struct ntb_dev *ntb, int idx, u32 val) +static inline int ntb_peer_spad_write(struct ntb_dev *ntb, int pidx, int sidx, + u32 val) { - return ntb->ops->peer_spad_write(ntb, idx, val); + if (!ntb->ops->peer_spad_write) + return -EINVAL; + + return ntb->ops->peer_spad_write(ntb, pidx, sidx, val); } #endif -- cgit v1.2.3-59-g8ed1b From bc3e49adc279c5505d6df8dd8c7fca45d6d3d21a Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Tue, 20 Dec 2016 12:48:20 +0300 Subject: NTB: Add Messaging NTB API Some IDT NTB-capable PCIe-switches have message registers to communicate with peer devices. This patch adds new NTB API callback methods, which can be used to utilize these registers functionality: ntb_msg_count(); - get number of message registers ntb_msg_inbits(); - get bitfield of inbound message registers status ntb_msg_outbits(); - get bitfield of outbound message registers status ntb_msg_read_sts(); - read the inbound and outbound message registers status ntb_msg_clear_sts(); - clear status bits of message registers ntb_msg_set_mask(); - mask interrupts raised by status bits of message registers. ntb_msg_clear_mask(); - clear interrupts mask bits of message registers ntb_msg_read(midx, *pidx); - read message register with specified index, additionally getting peer port index which data received from ntb_msg_write(midx, pidx); - write data to the specified message register sending it to the passed peer device connected over a pidx port ntb_msg_event(); - notify driver context of a new message event Of course there is hardware which doesn't support Message registers, so this API is made optional. Signed-off-by: Serge Semin Acked-by: Allen Hubbe Signed-off-by: Jon Mason --- drivers/ntb/ntb.c | 13 ++++ include/linux/ntb.h | 205 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 218 insertions(+) diff --git a/drivers/ntb/ntb.c b/drivers/ntb/ntb.c index 2551bb2ff4a4..03b80d89b980 100644 --- a/drivers/ntb/ntb.c +++ b/drivers/ntb/ntb.c @@ -193,6 +193,19 @@ void ntb_db_event(struct ntb_dev *ntb, int vector) } EXPORT_SYMBOL(ntb_db_event); +void ntb_msg_event(struct ntb_dev *ntb) +{ + unsigned long irqflags; + + spin_lock_irqsave(&ntb->ctx_lock, irqflags); + { + if (ntb->ctx_ops && ntb->ctx_ops->msg_event) + ntb->ctx_ops->msg_event(ntb->ctx); + } + spin_unlock_irqrestore(&ntb->ctx_lock, irqflags); +} +EXPORT_SYMBOL(ntb_msg_event); + int ntb_default_port_number(struct ntb_dev *ntb) { switch (ntb->topo) { diff --git a/include/linux/ntb.h b/include/linux/ntb.h index 4e3cd56af732..d59688f91618 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -178,10 +178,12 @@ static inline int ntb_client_ops_is_valid(const struct ntb_client_ops *ops) * struct ntb_ctx_ops - ntb driver context operations * @link_event: See ntb_link_event(). * @db_event: See ntb_db_event(). + * @msg_event: See ntb_msg_event(). */ struct ntb_ctx_ops { void (*link_event)(void *ctx); void (*db_event)(void *ctx, int db_vector); + void (*msg_event)(void *ctx); }; static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) @@ -190,6 +192,7 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) return /* ops->link_event && */ /* ops->db_event && */ + /* ops->msg_event && */ 1; } @@ -234,6 +237,15 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) * @peer_spad_addr: See ntb_peer_spad_addr(). * @peer_spad_read: See ntb_peer_spad_read(). * @peer_spad_write: See ntb_peer_spad_write(). + * @msg_count: See ntb_msg_count(). + * @msg_inbits: See ntb_msg_inbits(). + * @msg_outbits: See ntb_msg_outbits(). + * @msg_read_sts: See ntb_msg_read_sts(). + * @msg_clear_sts: See ntb_msg_clear_sts(). + * @msg_set_mask: See ntb_msg_set_mask(). + * @msg_clear_mask: See ntb_msg_clear_mask(). + * @msg_read: See ntb_msg_read(). + * @msg_write: See ntb_msg_write(). */ struct ntb_dev_ops { int (*port_number)(struct ntb_dev *ntb); @@ -296,6 +308,16 @@ struct ntb_dev_ops { u32 (*peer_spad_read)(struct ntb_dev *ntb, int pidx, int sidx); int (*peer_spad_write)(struct ntb_dev *ntb, int pidx, int sidx, u32 val); + + int (*msg_count)(struct ntb_dev *ntb); + u64 (*msg_inbits)(struct ntb_dev *ntb); + u64 (*msg_outbits)(struct ntb_dev *ntb); + u64 (*msg_read_sts)(struct ntb_dev *ntb); + int (*msg_clear_sts)(struct ntb_dev *ntb, u64 sts_bits); + int (*msg_set_mask)(struct ntb_dev *ntb, u64 mask_bits); + int (*msg_clear_mask)(struct ntb_dev *ntb, u64 mask_bits); + int (*msg_read)(struct ntb_dev *ntb, int midx, int *pidx, u32 *msg); + int (*msg_write)(struct ntb_dev *ntb, int midx, int pidx, u32 msg); }; static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops) @@ -342,6 +364,15 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops) /* !ops->peer_spad_addr == !ops->spad_count && */ /* !ops->peer_spad_read == !ops->spad_count && */ !ops->peer_spad_write == !ops->spad_count && + + !ops->msg_inbits == !ops->msg_count && + !ops->msg_outbits == !ops->msg_count && + !ops->msg_read_sts == !ops->msg_count && + !ops->msg_clear_sts == !ops->msg_count && + /* !ops->msg_set_mask == !ops->msg_count && */ + /* !ops->msg_clear_mask == !ops->msg_count && */ + !ops->msg_read == !ops->msg_count && + !ops->msg_write == !ops->msg_count && 1; } @@ -484,6 +515,18 @@ void ntb_link_event(struct ntb_dev *ntb); */ void ntb_db_event(struct ntb_dev *ntb, int vector); +/** + * ntb_msg_event() - notify driver context of a message event + * @ntb: NTB device context. + * + * Notify the driver context of a message event. If hardware supports + * message registers, this event indicates, that a new message arrived in + * some incoming message register or last sent message couldn't be delivered. + * The events can be masked/unmasked by the methods ntb_msg_set_mask() and + * ntb_msg_clear_mask(). + */ +void ntb_msg_event(struct ntb_dev *ntb); + /** * ntb_default_port_number() - get the default local port number * @ntb: NTB device context. @@ -1282,4 +1325,166 @@ static inline int ntb_peer_spad_write(struct ntb_dev *ntb, int pidx, int sidx, return ntb->ops->peer_spad_write(ntb, pidx, sidx, val); } +/** + * ntb_msg_count() - get the number of message registers + * @ntb: NTB device context. + * + * Hardware may support a different number of message registers. + * + * Return: the number of message registers. + */ +static inline int ntb_msg_count(struct ntb_dev *ntb) +{ + if (!ntb->ops->msg_count) + return 0; + + return ntb->ops->msg_count(ntb); +} + +/** + * ntb_msg_inbits() - get a bitfield of inbound message registers status + * @ntb: NTB device context. + * + * The method returns the bitfield of status and mask registers, which related + * to inbound message registers. + * + * Return: bitfield of inbound message registers. + */ +static inline u64 ntb_msg_inbits(struct ntb_dev *ntb) +{ + if (!ntb->ops->msg_inbits) + return 0; + + return ntb->ops->msg_inbits(ntb); +} + +/** + * ntb_msg_outbits() - get a bitfield of outbound message registers status + * @ntb: NTB device context. + * + * The method returns the bitfield of status and mask registers, which related + * to outbound message registers. + * + * Return: bitfield of outbound message registers. + */ +static inline u64 ntb_msg_outbits(struct ntb_dev *ntb) +{ + if (!ntb->ops->msg_outbits) + return 0; + + return ntb->ops->msg_outbits(ntb); +} + +/** + * ntb_msg_read_sts() - read the message registers status + * @ntb: NTB device context. + * + * Read the status of message register. Inbound and outbound message registers + * related bits can be filtered by masks retrieved from ntb_msg_inbits() and + * ntb_msg_outbits(). + * + * Return: status bits of message registers + */ +static inline u64 ntb_msg_read_sts(struct ntb_dev *ntb) +{ + if (!ntb->ops->msg_read_sts) + return 0; + + return ntb->ops->msg_read_sts(ntb); +} + +/** + * ntb_msg_clear_sts() - clear status bits of message registers + * @ntb: NTB device context. + * @sts_bits: Status bits to clear. + * + * Clear bits in the status register. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_clear_sts(struct ntb_dev *ntb, u64 sts_bits) +{ + if (!ntb->ops->msg_clear_sts) + return -EINVAL; + + return ntb->ops->msg_clear_sts(ntb, sts_bits); +} + +/** + * ntb_msg_set_mask() - set mask of message register status bits + * @ntb: NTB device context. + * @mask_bits: Mask bits. + * + * Mask the message registers status bits from raising the message event. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_set_mask(struct ntb_dev *ntb, u64 mask_bits) +{ + if (!ntb->ops->msg_set_mask) + return -EINVAL; + + return ntb->ops->msg_set_mask(ntb, mask_bits); +} + +/** + * ntb_msg_clear_mask() - clear message registers mask + * @ntb: NTB device context. + * @mask_bits: Mask bits to clear. + * + * Clear bits in the message events mask register. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_clear_mask(struct ntb_dev *ntb, u64 mask_bits) +{ + if (!ntb->ops->msg_clear_mask) + return -EINVAL; + + return ntb->ops->msg_clear_mask(ntb, mask_bits); +} + +/** + * ntb_msg_read() - read message register with specified index + * @ntb: NTB device context. + * @midx: Message register index + * @pidx: OUT - Port index of peer device a message retrieved from + * @msg: OUT - Data + * + * Read data from the specified message register. Source port index of a + * message is retrieved as well. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_read(struct ntb_dev *ntb, int midx, int *pidx, + u32 *msg) +{ + if (!ntb->ops->msg_read) + return -EINVAL; + + return ntb->ops->msg_read(ntb, midx, pidx, msg); +} + +/** + * ntb_msg_write() - write data to the specified message register + * @ntb: NTB device context. + * @midx: Message register index + * @pidx: Port index of peer device a message being sent to + * @msg: Data to send + * + * Send data to a specified peer device using the defined message register. + * Message event can be raised if the midx registers isn't empty while + * calling this method and the corresponding interrupt isn't masked. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_write(struct ntb_dev *ntb, int midx, int pidx, + u32 msg) +{ + if (!ntb->ops->msg_write) + return -EINVAL; + + return ntb->ops->msg_write(ntb, midx, pidx, msg); +} + #endif -- cgit v1.2.3-59-g8ed1b From cdcca896aee19e338adf3000512cade4befa5c69 Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Wed, 14 Dec 2016 02:49:19 +0300 Subject: NTB: Add new Memory Windows API documentation Since the new API slightly changes the way a typical NTB client driver works, the documentation file needs to be appropriately updated. Signed-off-by: Serge Semin Acked-by: Allen Hubbe Signed-off-by: Jon Mason --- Documentation/ntb.txt | 99 ++++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 91 insertions(+), 8 deletions(-) diff --git a/Documentation/ntb.txt b/Documentation/ntb.txt index 1d9bbabb6c79..a5af4f0159f3 100644 --- a/Documentation/ntb.txt +++ b/Documentation/ntb.txt @@ -1,14 +1,16 @@ # NTB Drivers NTB (Non-Transparent Bridge) is a type of PCI-Express bridge chip that connects -the separate memory systems of two computers to the same PCI-Express fabric. -Existing NTB hardware supports a common feature set, including scratchpad -registers, doorbell registers, and memory translation windows. Scratchpad -registers are read-and-writable registers that are accessible from either side -of the device, so that peers can exchange a small amount of information at a -fixed address. Doorbell registers provide a way for peers to send interrupt -events. Memory windows allow translated read and write access to the peer -memory. +the separate memory systems of two or more computers to the same PCI-Express +fabric. Existing NTB hardware supports a common feature set: doorbell +registers and memory translation windows, as well as non common features like +scratchpad and message registers. Scratchpad registers are read-and-writable +registers that are accessible from either side of the device, so that peers can +exchange a small amount of information at a fixed address. Message registers can +be utilized for the same purpose. Additionally they are provided with with +special status bits to make sure the information isn't rewritten by another +peer. Doorbell registers provide a way for peers to send interrupt events. +Memory windows allow translated read and write access to the peer memory. ## NTB Core Driver (ntb) @@ -26,6 +28,87 @@ as ntb hardware, or hardware drivers, are inserted and removed. The registration uses the Linux Device framework, so it should feel familiar to anyone who has written a pci driver. +### NTB Typical client driver implementation + +Primary purpose of NTB is to share some peace of memory between at least two +systems. So the NTB device features like Scratchpad/Message registers are +mainly used to perform the proper memory window initialization. Typically +there are two types of memory window interfaces supported by the NTB API: +inbound translation configured on the local ntb port and outbound translation +configured by the peer, on the peer ntb port. The first type is +depicted on the next figure + +Inbound translation: + Memory: Local NTB Port: Peer NTB Port: Peer MMIO: + ____________ + | dma-mapped |-ntb_mw_set_trans(addr) | + | memory | _v____________ | ______________ + | (addr) |<======| MW xlat addr |<====| MW base addr |<== memory-mapped IO + |------------| |--------------| | |--------------| + +So typical scenario of the first type memory window initialization looks: +1) allocate a memory region, 2) put translated address to NTB config, +3) somehow notify a peer device of performed initialization, 4) peer device +maps corresponding outbound memory window so to have access to the shared +memory region. + +The second type of interface, that implies the shared windows being +initialized by a peer device, is depicted on the figure: + +Outbound translation: + Memory: Local NTB Port: Peer NTB Port: Peer MMIO: + ____________ ______________ + | dma-mapped | | | MW base addr |<== memory-mapped IO + | memory | | |--------------| + | (addr) |<===================| MW xlat addr |<-ntb_peer_mw_set_trans(addr) + |------------| | |--------------| + +Typical scenario of the second type interface initialization would be: +1) allocate a memory region, 2) somehow deliver a translated address to a peer +device, 3) peer puts the translated address to NTB config, 4) peer device maps +outbound memory window so to have access to the shared memory region. + +As one can see the described scenarios can be combined in one portable +algorithm. + Local device: + 1) Allocate memory for a shared window + 2) Initialize memory window by translated address of the allocated region + (it may fail if local memory window initialization is unsupported) + 3) Send the translated address and memory window index to a peer device + Peer device: + 1) Initialize memory window with retrieved address of the allocated + by another device memory region (it may fail if peer memory window + initialization is unsupported) + 2) Map outbound memory window + +In accordance with this scenario, the NTB Memory Window API can be used as +follows: + Local device: + 1) ntb_mw_count(pidx) - retrieve number of memory ranges, which can + be allocated for memory windows between local device and peer device + of port with specified index. + 2) ntb_get_align(pidx, midx) - retrieve parameters restricting the + shared memory region alignment and size. Then memory can be properly + allocated. + 3) Allocate physically contiguous memory region in compliance with + restrictions retrieved in 2). + 4) ntb_mw_set_trans(pidx, midx) - try to set translation address of + the memory window with specified index for the defined peer device + (it may fail if local translated address setting is not supported) + 5) Send translated base address (usually together with memory window + number) to the peer device using, for instance, scratchpad or message + registers. + Peer device: + 1) ntb_peer_mw_set_trans(pidx, midx) - try to set received from other + device (related to pidx) translated address for specified memory + window. It may fail if retrieved address, for instance, exceeds + maximum possible address or isn't properly aligned. + 2) ntb_peer_mw_get_addr(widx) - retrieve MMIO address to map the memory + window so to have an access to the shared memory. + +Also it is worth to note, that method ntb_mw_count(pidx) should return the +same value as ntb_peer_mw_count() on the peer with port index - pidx. + ### NTB Transport Client (ntb\_transport) and NTB Netdev (ntb\_netdev) The primary client for NTB is the Transport client, used in tandem with NTB -- cgit v1.2.3-59-g8ed1b From 85dce3aaae98a8440f4a1a2404bcbab890574b46 Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Wed, 14 Dec 2016 02:49:20 +0300 Subject: NTB: Add PCIe Gen4 link speed Signed-off-by: Serge Semin Acked-by: Allen Hubbe Signed-off-by: Jon Mason --- include/linux/ntb.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/linux/ntb.h b/include/linux/ntb.h index d59688f91618..a6f569727845 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -108,6 +108,7 @@ static inline char *ntb_topo_string(enum ntb_topo topo) * @NTB_SPEED_GEN1: Link is trained to gen1 speed. * @NTB_SPEED_GEN2: Link is trained to gen2 speed. * @NTB_SPEED_GEN3: Link is trained to gen3 speed. + * @NTB_SPEED_GEN4: Link is trained to gen4 speed. */ enum ntb_speed { NTB_SPEED_AUTO = -1, @@ -115,6 +116,7 @@ enum ntb_speed { NTB_SPEED_GEN1 = 1, NTB_SPEED_GEN2 = 2, NTB_SPEED_GEN3 = 3, + NTB_SPEED_GEN4 = 4 }; /** -- cgit v1.2.3-59-g8ed1b From 3c69f5d6731c43a5b6b9e78b385948e8d76460be Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Tue, 20 Dec 2016 12:50:09 +0300 Subject: NTB: Add ntb.h comments Signed-off-by: Serge Semin Acked-by: Allen Hubbe Signed-off-by: Jon Mason --- include/linux/ntb.h | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git a/include/linux/ntb.h b/include/linux/ntb.h index a6f569727845..609e232c00da 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -326,12 +326,17 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops) { /* commented callbacks are not required: */ return + /* Port operations are required for multiport devices */ !ops->peer_port_count == !ops->port_number && !ops->peer_port_number == !ops->port_number && !ops->peer_port_idx == !ops->port_number && + + /* Link operations are required */ ops->link_is_up && ops->link_enable && ops->link_disable && + + /* One or both MW interfaces should be developed */ ops->mw_count && ops->mw_get_align && (ops->mw_set_trans || @@ -341,12 +346,11 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops) ops->peer_mw_get_addr && /* ops->peer_mw_clear_trans && */ + /* Doorbell operations are mostly required */ /* ops->db_is_unsafe && */ ops->db_valid_mask && - /* both set, or both unset */ - (!ops->db_vector_count == !ops->db_vector_mask) && - + (!ops->db_vector_count == !ops->db_vector_mask) && ops->db_read && /* ops->db_set && */ ops->db_clear && @@ -360,6 +364,8 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops) /* ops->peer_db_read_mask && */ /* ops->peer_db_set_mask && */ /* ops->peer_db_clear_mask && */ + + /* Scrachpads interface is optional */ /* !ops->spad_is_unsafe == !ops->spad_count && */ !ops->spad_read == !ops->spad_count && !ops->spad_write == !ops->spad_count && @@ -367,6 +373,7 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops) /* !ops->peer_spad_read == !ops->spad_count && */ !ops->peer_spad_write == !ops->spad_count && + /* Messaging interface is optional */ !ops->msg_inbits == !ops->msg_count && !ops->msg_outbits == !ops->msg_count && !ops->msg_read_sts == !ops->msg_count && @@ -387,13 +394,12 @@ struct ntb_client { struct device_driver drv; const struct ntb_client_ops ops; }; - #define drv_ntb_client(__drv) container_of((__drv), struct ntb_client, drv) /** * struct ntb_device - ntb device * @dev: Linux device object. - * @pdev: Pci device entry of the ntb. + * @pdev: PCI device entry of the ntb. * @topo: Detected topology of the ntb. * @ops: See &ntb_dev_ops. * @ctx: See &ntb_ctx_ops. @@ -414,7 +420,6 @@ struct ntb_dev { /* block unregister until device is fully released */ struct completion released; }; - #define dev_ntb(__dev) container_of((__dev), struct ntb_dev, dev) /** @@ -511,7 +516,7 @@ void ntb_link_event(struct ntb_dev *ntb); * multiple interrupt vectors for doorbells, the vector number indicates which * vector received the interrupt. The vector number is relative to the first * vector used for doorbells, starting at zero, and must be less than - ** ntb_db_vector_count(). The driver may call ntb_db_read() to check which + * ntb_db_vector_count(). The driver may call ntb_db_read() to check which * doorbell bits need service, and ntb_db_vector_mask() to determine which of * those bits are associated with the vector number. */ -- cgit v1.2.3-59-g8ed1b From 0f9bfb979a5fae2936afa128c04f29ab5e07a9ad Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Tue, 10 Jan 2017 17:33:36 -0700 Subject: ntb_hw_amd: Style fixes: open code macros that just obfuscate code As per a comments in [1] by Greg Kroah-Hartman, the ndev_* macros should be cleaned up. This makes it more clear what's actually going on when reading the code. [1] http://www.spinics.net/lists/linux-pci/msg56904.html Signed-off-by: Logan Gunthorpe Signed-off-by: Jon Mason --- drivers/ntb/hw/amd/ntb_hw_amd.c | 55 ++++++++++++++++++++++------------------- drivers/ntb/hw/amd/ntb_hw_amd.h | 3 --- 2 files changed, 29 insertions(+), 29 deletions(-) diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.c b/drivers/ntb/hw/amd/ntb_hw_amd.c index 891beb9f26c2..f0788aae05c9 100644 --- a/drivers/ntb/hw/amd/ntb_hw_amd.c +++ b/drivers/ntb/hw/amd/ntb_hw_amd.c @@ -133,7 +133,7 @@ static int amd_ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int idx, if (bar < 0) return bar; - mw_size = pci_resource_len(ndev->ntb.pdev, bar); + mw_size = pci_resource_len(ntb->pdev, bar); /* make sure the range fits in the usable mw size */ if (size > mw_size) @@ -142,7 +142,7 @@ static int amd_ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int idx, mmio = ndev->self_mmio; peer_mmio = ndev->peer_mmio; - base_addr = pci_resource_start(ndev->ntb.pdev, bar); + base_addr = pci_resource_start(ntb->pdev, bar); if (bar != 1) { xlat_reg = AMD_BAR23XLAT_OFFSET + ((bar - 2) << 2); @@ -232,7 +232,7 @@ static u64 amd_ntb_link_is_up(struct ntb_dev *ntb, if (width) *width = NTB_LNK_STA_WIDTH(ndev->lnk_sta); - dev_dbg(ndev_dev(ndev), "link is up.\n"); + dev_dbg(&ntb->pdev->dev, "link is up.\n"); ret = 1; } else { @@ -241,7 +241,7 @@ static u64 amd_ntb_link_is_up(struct ntb_dev *ntb, if (width) *width = NTB_WIDTH_NONE; - dev_dbg(ndev_dev(ndev), "link is down.\n"); + dev_dbg(&ntb->pdev->dev, "link is down.\n"); } return ret; @@ -261,7 +261,7 @@ static int amd_ntb_link_enable(struct ntb_dev *ntb, if (ndev->ntb.topo == NTB_TOPO_SEC) return -EINVAL; - dev_dbg(ndev_dev(ndev), "Enabling Link.\n"); + dev_dbg(&ntb->pdev->dev, "Enabling Link.\n"); ntb_ctl = readl(mmio + AMD_CNTL_OFFSET); ntb_ctl |= (PMM_REG_CTL | SMM_REG_CTL); @@ -282,7 +282,7 @@ static int amd_ntb_link_disable(struct ntb_dev *ntb) if (ndev->ntb.topo == NTB_TOPO_SEC) return -EINVAL; - dev_dbg(ndev_dev(ndev), "Enabling Link.\n"); + dev_dbg(&ntb->pdev->dev, "Enabling Link.\n"); ntb_ctl = readl(mmio + AMD_CNTL_OFFSET); ntb_ctl &= ~(PMM_REG_CTL | SMM_REG_CTL); @@ -500,18 +500,19 @@ static void amd_ack_smu(struct amd_ntb_dev *ndev, u32 bit) static void amd_handle_event(struct amd_ntb_dev *ndev, int vec) { void __iomem *mmio = ndev->self_mmio; + struct device *dev = &ndev->ntb.pdev->dev; u32 status; status = readl(mmio + AMD_INTSTAT_OFFSET); if (!(status & AMD_EVENT_INTMASK)) return; - dev_dbg(ndev_dev(ndev), "status = 0x%x and vec = %d\n", status, vec); + dev_dbg(dev, "status = 0x%x and vec = %d\n", status, vec); status &= AMD_EVENT_INTMASK; switch (status) { case AMD_PEER_FLUSH_EVENT: - dev_info(ndev_dev(ndev), "Flush is done.\n"); + dev_info(dev, "Flush is done.\n"); break; case AMD_PEER_RESET_EVENT: amd_ack_smu(ndev, AMD_PEER_RESET_EVENT); @@ -537,7 +538,7 @@ static void amd_handle_event(struct amd_ntb_dev *ndev, int vec) status = readl(mmio + AMD_PMESTAT_OFFSET); /* check if this is WAKEUP event */ if (status & 0x1) - dev_info(ndev_dev(ndev), "Wakeup is done.\n"); + dev_info(dev, "Wakeup is done.\n"); amd_ack_smu(ndev, AMD_PEER_D0_EVENT); @@ -546,14 +547,14 @@ static void amd_handle_event(struct amd_ntb_dev *ndev, int vec) AMD_LINK_HB_TIMEOUT); break; default: - dev_info(ndev_dev(ndev), "event status = 0x%x.\n", status); + dev_info(dev, "event status = 0x%x.\n", status); break; } } static irqreturn_t ndev_interrupt(struct amd_ntb_dev *ndev, int vec) { - dev_dbg(ndev_dev(ndev), "vec %d\n", vec); + dev_dbg(&ndev->ntb.pdev->dev, "vec %d\n", vec); if (vec > (AMD_DB_CNT - 1) || (ndev->msix_vec_count == 1)) amd_handle_event(ndev, vec); @@ -575,7 +576,7 @@ static irqreturn_t ndev_irq_isr(int irq, void *dev) { struct amd_ntb_dev *ndev = dev; - return ndev_interrupt(ndev, irq - ndev_pdev(ndev)->irq); + return ndev_interrupt(ndev, irq - ndev->ntb.pdev->irq); } static int ndev_init_isr(struct amd_ntb_dev *ndev, @@ -584,7 +585,7 @@ static int ndev_init_isr(struct amd_ntb_dev *ndev, struct pci_dev *pdev; int rc, i, msix_count, node; - pdev = ndev_pdev(ndev); + pdev = ndev->ntb.pdev; node = dev_to_node(&pdev->dev); @@ -626,7 +627,7 @@ static int ndev_init_isr(struct amd_ntb_dev *ndev, goto err_msix_request; } - dev_dbg(ndev_dev(ndev), "Using msix interrupts\n"); + dev_dbg(&pdev->dev, "Using msix interrupts\n"); ndev->db_count = msix_min; ndev->msix_vec_count = msix_max; return 0; @@ -653,7 +654,7 @@ err_msix_vec_alloc: if (rc) goto err_msi_request; - dev_dbg(ndev_dev(ndev), "Using msi interrupts\n"); + dev_dbg(&pdev->dev, "Using msi interrupts\n"); ndev->db_count = 1; ndev->msix_vec_count = 1; return 0; @@ -670,7 +671,7 @@ err_msi_enable: if (rc) goto err_intx_request; - dev_dbg(ndev_dev(ndev), "Using intx interrupts\n"); + dev_dbg(&pdev->dev, "Using intx interrupts\n"); ndev->db_count = 1; ndev->msix_vec_count = 1; return 0; @@ -685,7 +686,7 @@ static void ndev_deinit_isr(struct amd_ntb_dev *ndev) void __iomem *mmio = ndev->self_mmio; int i; - pdev = ndev_pdev(ndev); + pdev = ndev->ntb.pdev; /* Mask all doorbell interrupts */ ndev->db_mask = ndev->db_valid_mask; @@ -811,7 +812,8 @@ static void ndev_init_debugfs(struct amd_ntb_dev *ndev) ndev->debugfs_info = NULL; } else { ndev->debugfs_dir = - debugfs_create_dir(ndev_name(ndev), debugfs_dir); + debugfs_create_dir(pci_name(ndev->ntb.pdev), + debugfs_dir); if (!ndev->debugfs_dir) ndev->debugfs_info = NULL; else @@ -846,7 +848,7 @@ static int amd_poll_link(struct amd_ntb_dev *ndev) reg = readl(mmio + AMD_SIDEINFO_OFFSET); reg &= NTB_LIN_STA_ACTIVE_BIT; - dev_dbg(ndev_dev(ndev), "%s: reg_val = 0x%x.\n", __func__, reg); + dev_dbg(&ndev->ntb.pdev->dev, "%s: reg_val = 0x%x.\n", __func__, reg); if (reg == ndev->cntl_sta) return 0; @@ -928,7 +930,8 @@ static int amd_init_ntb(struct amd_ntb_dev *ndev) break; default: - dev_err(ndev_dev(ndev), "AMD NTB does not support B2B mode.\n"); + dev_err(&ndev->ntb.pdev->dev, + "AMD NTB does not support B2B mode.\n"); return -EINVAL; } @@ -957,10 +960,10 @@ static int amd_init_dev(struct amd_ntb_dev *ndev) struct pci_dev *pdev; int rc = 0; - pdev = ndev_pdev(ndev); + pdev = ndev->ntb.pdev; ndev->ntb.topo = amd_get_topo(ndev); - dev_dbg(ndev_dev(ndev), "AMD NTB topo is %s\n", + dev_dbg(&pdev->dev, "AMD NTB topo is %s\n", ntb_topo_string(ndev->ntb.topo)); rc = amd_init_ntb(ndev); @@ -969,7 +972,7 @@ static int amd_init_dev(struct amd_ntb_dev *ndev) rc = amd_init_isr(ndev); if (rc) { - dev_err(ndev_dev(ndev), "fail to init isr.\n"); + dev_err(&pdev->dev, "fail to init isr.\n"); return rc; } @@ -1007,7 +1010,7 @@ static int amd_ntb_init_pci(struct amd_ntb_dev *ndev, rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); if (rc) goto err_dma_mask; - dev_warn(ndev_dev(ndev), "Cannot DMA highmem\n"); + dev_warn(&pdev->dev, "Cannot DMA highmem\n"); } rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); @@ -1015,7 +1018,7 @@ static int amd_ntb_init_pci(struct amd_ntb_dev *ndev, rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); if (rc) goto err_dma_mask; - dev_warn(ndev_dev(ndev), "Cannot DMA consistent highmem\n"); + dev_warn(&pdev->dev, "Cannot DMA consistent highmem\n"); } ndev->self_mmio = pci_iomap(pdev, 0, 0); @@ -1038,7 +1041,7 @@ err_pci_enable: static void amd_ntb_deinit_pci(struct amd_ntb_dev *ndev) { - struct pci_dev *pdev = ndev_pdev(ndev); + struct pci_dev *pdev = ndev->ntb.pdev; pci_iounmap(pdev, ndev->self_mmio); diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.h b/drivers/ntb/hw/amd/ntb_hw_amd.h index 13d73ed94a52..8f3617a46292 100644 --- a/drivers/ntb/hw/amd/ntb_hw_amd.h +++ b/drivers/ntb/hw/amd/ntb_hw_amd.h @@ -211,9 +211,6 @@ struct amd_ntb_dev { struct dentry *debugfs_info; }; -#define ndev_pdev(ndev) ((ndev)->ntb.pdev) -#define ndev_name(ndev) pci_name(ndev_pdev(ndev)) -#define ndev_dev(ndev) (&ndev_pdev(ndev)->dev) #define ntb_ndev(__ntb) container_of(__ntb, struct amd_ntb_dev, ntb) #define hb_ndev(__work) container_of(__work, struct amd_ntb_dev, hb_timer.work) -- cgit v1.2.3-59-g8ed1b From 48ea02184a9d000f877f901951d37843b26d26ad Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Tue, 10 Jan 2017 17:33:37 -0700 Subject: ntb_hw_intel: Style fixes: open code macros that just obfuscate code As per a comments in [1] by Greg Kroah-Hartman, the ndev_* macros should be cleaned up. This makes it more clear what's actually going on when reading the code. [1] http://www.spinics.net/lists/linux-pci/msg56904.html Signed-off-by: Logan Gunthorpe Signed-off-by: Jon Mason --- drivers/ntb/hw/intel/ntb_hw_intel.c | 192 ++++++++++++++++++------------------ drivers/ntb/hw/intel/ntb_hw_intel.h | 3 - 2 files changed, 95 insertions(+), 100 deletions(-) diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.c b/drivers/ntb/hw/intel/ntb_hw_intel.c index e00aa39a4544..2557e2c05b90 100644 --- a/drivers/ntb/hw/intel/ntb_hw_intel.c +++ b/drivers/ntb/hw/intel/ntb_hw_intel.c @@ -272,12 +272,12 @@ static inline int ndev_db_addr(struct intel_ntb_dev *ndev, if (db_addr) { *db_addr = reg_addr + reg; - dev_dbg(ndev_dev(ndev), "Peer db addr %llx\n", *db_addr); + dev_dbg(&ndev->ntb.pdev->dev, "Peer db addr %llx\n", *db_addr); } if (db_size) { *db_size = ndev->reg->db_size; - dev_dbg(ndev_dev(ndev), "Peer db size %llx\n", *db_size); + dev_dbg(&ndev->ntb.pdev->dev, "Peer db size %llx\n", *db_size); } return 0; @@ -370,7 +370,8 @@ static inline int ndev_spad_addr(struct intel_ntb_dev *ndev, int idx, if (spad_addr) { *spad_addr = reg_addr + reg + (idx << 2); - dev_dbg(ndev_dev(ndev), "Peer spad addr %llx\n", *spad_addr); + dev_dbg(&ndev->ntb.pdev->dev, "Peer spad addr %llx\n", + *spad_addr); } return 0; @@ -411,7 +412,7 @@ static irqreturn_t ndev_interrupt(struct intel_ntb_dev *ndev, int vec) if ((ndev->hwerr_flags & NTB_HWERR_MSIX_VECTOR32_BAD) && (vec == 31)) vec_mask |= ndev->db_link_mask; - dev_dbg(ndev_dev(ndev), "vec %d vec_mask %llx\n", vec, vec_mask); + dev_dbg(&ndev->ntb.pdev->dev, "vec %d vec_mask %llx\n", vec, vec_mask); ndev->last_ts = jiffies; @@ -430,7 +431,7 @@ static irqreturn_t ndev_vec_isr(int irq, void *dev) { struct intel_ntb_vec *nvec = dev; - dev_dbg(ndev_dev(nvec->ndev), "irq: %d nvec->num: %d\n", + dev_dbg(&nvec->ndev->ntb.pdev->dev, "irq: %d nvec->num: %d\n", irq, nvec->num); return ndev_interrupt(nvec->ndev, nvec->num); @@ -440,7 +441,7 @@ static irqreturn_t ndev_irq_isr(int irq, void *dev) { struct intel_ntb_dev *ndev = dev; - return ndev_interrupt(ndev, irq - ndev_pdev(ndev)->irq); + return ndev_interrupt(ndev, irq - ndev->ntb.pdev->irq); } static int ndev_init_isr(struct intel_ntb_dev *ndev, @@ -450,7 +451,7 @@ static int ndev_init_isr(struct intel_ntb_dev *ndev, struct pci_dev *pdev; int rc, i, msix_count, node; - pdev = ndev_pdev(ndev); + pdev = ndev->ntb.pdev; node = dev_to_node(&pdev->dev); @@ -489,7 +490,7 @@ static int ndev_init_isr(struct intel_ntb_dev *ndev, goto err_msix_request; } - dev_dbg(ndev_dev(ndev), "Using %d msix interrupts\n", msix_count); + dev_dbg(&pdev->dev, "Using %d msix interrupts\n", msix_count); ndev->db_vec_count = msix_count; ndev->db_vec_shift = msix_shift; return 0; @@ -517,7 +518,7 @@ err_msix_vec_alloc: if (rc) goto err_msi_request; - dev_dbg(ndev_dev(ndev), "Using msi interrupts\n"); + dev_dbg(&pdev->dev, "Using msi interrupts\n"); ndev->db_vec_count = 1; ndev->db_vec_shift = total_shift; return 0; @@ -535,7 +536,7 @@ err_msi_enable: if (rc) goto err_intx_request; - dev_dbg(ndev_dev(ndev), "Using intx interrupts\n"); + dev_dbg(&pdev->dev, "Using intx interrupts\n"); ndev->db_vec_count = 1; ndev->db_vec_shift = total_shift; return 0; @@ -549,7 +550,7 @@ static void ndev_deinit_isr(struct intel_ntb_dev *ndev) struct pci_dev *pdev; int i; - pdev = ndev_pdev(ndev); + pdev = ndev->ntb.pdev; /* Mask all doorbell interrupts */ ndev->db_mask = ndev->db_valid_mask; @@ -746,7 +747,7 @@ static ssize_t ndev_ntb_debugfs_read(struct file *filp, char __user *ubuf, union { u64 v64; u32 v32; u16 v16; u8 v8; } u; ndev = filp->private_data; - pdev = ndev_pdev(ndev); + pdev = ndev->ntb.pdev; mmio = ndev->self_mmio; buf_size = min(count, 0x800ul); @@ -1021,7 +1022,8 @@ static void ndev_init_debugfs(struct intel_ntb_dev *ndev) ndev->debugfs_info = NULL; } else { ndev->debugfs_dir = - debugfs_create_dir(ndev_name(ndev), debugfs_dir); + debugfs_create_dir(pci_name(ndev->ntb.pdev), + debugfs_dir); if (!ndev->debugfs_dir) ndev->debugfs_info = NULL; else @@ -1219,13 +1221,13 @@ static int intel_ntb_link_enable(struct ntb_dev *ntb, if (ndev->ntb.topo == NTB_TOPO_SEC) return -EINVAL; - dev_dbg(ndev_dev(ndev), + dev_dbg(&ntb->pdev->dev, "Enabling link with max_speed %d max_width %d\n", max_speed, max_width); if (max_speed != NTB_SPEED_AUTO) - dev_dbg(ndev_dev(ndev), "ignoring max_speed %d\n", max_speed); + dev_dbg(&ntb->pdev->dev, "ignoring max_speed %d\n", max_speed); if (max_width != NTB_WIDTH_AUTO) - dev_dbg(ndev_dev(ndev), "ignoring max_width %d\n", max_width); + dev_dbg(&ntb->pdev->dev, "ignoring max_width %d\n", max_width); ntb_ctl = ioread32(ndev->self_mmio + ndev->reg->ntb_ctl); ntb_ctl &= ~(NTB_CTL_DISABLE | NTB_CTL_CFG_LOCK); @@ -1248,7 +1250,7 @@ static int intel_ntb_link_disable(struct ntb_dev *ntb) if (ndev->ntb.topo == NTB_TOPO_SEC) return -EINVAL; - dev_dbg(ndev_dev(ndev), "Disabling link\n"); + dev_dbg(&ntb->pdev->dev, "Disabling link\n"); /* Bring NTB link down */ ntb_cntl = ioread32(ndev->self_mmio + ndev->reg->ntb_ctl); @@ -1485,30 +1487,33 @@ static int atom_link_is_err(struct intel_ntb_dev *ndev) static inline enum ntb_topo atom_ppd_topo(struct intel_ntb_dev *ndev, u32 ppd) { + struct device *dev = &ndev->ntb.pdev->dev; + switch (ppd & ATOM_PPD_TOPO_MASK) { case ATOM_PPD_TOPO_B2B_USD: - dev_dbg(ndev_dev(ndev), "PPD %d B2B USD\n", ppd); + dev_dbg(dev, "PPD %d B2B USD\n", ppd); return NTB_TOPO_B2B_USD; case ATOM_PPD_TOPO_B2B_DSD: - dev_dbg(ndev_dev(ndev), "PPD %d B2B DSD\n", ppd); + dev_dbg(dev, "PPD %d B2B DSD\n", ppd); return NTB_TOPO_B2B_DSD; case ATOM_PPD_TOPO_PRI_USD: case ATOM_PPD_TOPO_PRI_DSD: /* accept bogus PRI_DSD */ case ATOM_PPD_TOPO_SEC_USD: case ATOM_PPD_TOPO_SEC_DSD: /* accept bogus SEC_DSD */ - dev_dbg(ndev_dev(ndev), "PPD %d non B2B disabled\n", ppd); + dev_dbg(dev, "PPD %d non B2B disabled\n", ppd); return NTB_TOPO_NONE; } - dev_dbg(ndev_dev(ndev), "PPD %d invalid\n", ppd); + dev_dbg(dev, "PPD %d invalid\n", ppd); return NTB_TOPO_NONE; } static void atom_link_hb(struct work_struct *work) { struct intel_ntb_dev *ndev = hb_ndev(work); + struct device *dev = &ndev->ntb.pdev->dev; unsigned long poll_ts; void __iomem *mmio; u32 status32; @@ -1546,30 +1551,30 @@ static void atom_link_hb(struct work_struct *work) /* Clear AER Errors, write to clear */ status32 = ioread32(mmio + ATOM_ERRCORSTS_OFFSET); - dev_dbg(ndev_dev(ndev), "ERRCORSTS = %x\n", status32); + dev_dbg(dev, "ERRCORSTS = %x\n", status32); status32 &= PCI_ERR_COR_REP_ROLL; iowrite32(status32, mmio + ATOM_ERRCORSTS_OFFSET); /* Clear unexpected electrical idle event in LTSSM, write to clear */ status32 = ioread32(mmio + ATOM_LTSSMERRSTS0_OFFSET); - dev_dbg(ndev_dev(ndev), "LTSSMERRSTS0 = %x\n", status32); + dev_dbg(dev, "LTSSMERRSTS0 = %x\n", status32); status32 |= ATOM_LTSSMERRSTS0_UNEXPECTEDEI; iowrite32(status32, mmio + ATOM_LTSSMERRSTS0_OFFSET); /* Clear DeSkew Buffer error, write to clear */ status32 = ioread32(mmio + ATOM_DESKEWSTS_OFFSET); - dev_dbg(ndev_dev(ndev), "DESKEWSTS = %x\n", status32); + dev_dbg(dev, "DESKEWSTS = %x\n", status32); status32 |= ATOM_DESKEWSTS_DBERR; iowrite32(status32, mmio + ATOM_DESKEWSTS_OFFSET); status32 = ioread32(mmio + ATOM_IBSTERRRCRVSTS0_OFFSET); - dev_dbg(ndev_dev(ndev), "IBSTERRRCRVSTS0 = %x\n", status32); + dev_dbg(dev, "IBSTERRRCRVSTS0 = %x\n", status32); status32 &= ATOM_IBIST_ERR_OFLOW; iowrite32(status32, mmio + ATOM_IBSTERRRCRVSTS0_OFFSET); /* Releases the NTB state machine to allow the link to retrain */ status32 = ioread32(mmio + ATOM_LTSSMSTATEJMP_OFFSET); - dev_dbg(ndev_dev(ndev), "LTSSMSTATEJMP = %x\n", status32); + dev_dbg(dev, "LTSSMSTATEJMP = %x\n", status32); status32 &= ~ATOM_LTSSMSTATEJMP_FORCEDETECT; iowrite32(status32, mmio + ATOM_LTSSMSTATEJMP_OFFSET); @@ -1742,11 +1747,11 @@ static int skx_setup_b2b_mw(struct intel_ntb_dev *ndev, int b2b_bar; u8 bar_sz; - pdev = ndev_pdev(ndev); + pdev = ndev->ntb.pdev; mmio = ndev->self_mmio; if (ndev->b2b_idx == UINT_MAX) { - dev_dbg(ndev_dev(ndev), "not using b2b mw\n"); + dev_dbg(&pdev->dev, "not using b2b mw\n"); b2b_bar = 0; ndev->b2b_off = 0; } else { @@ -1754,24 +1759,21 @@ static int skx_setup_b2b_mw(struct intel_ntb_dev *ndev, if (b2b_bar < 0) return -EIO; - dev_dbg(ndev_dev(ndev), "using b2b mw bar %d\n", b2b_bar); + dev_dbg(&pdev->dev, "using b2b mw bar %d\n", b2b_bar); bar_size = pci_resource_len(ndev->ntb.pdev, b2b_bar); - dev_dbg(ndev_dev(ndev), "b2b bar size %#llx\n", bar_size); + dev_dbg(&pdev->dev, "b2b bar size %#llx\n", bar_size); if (b2b_mw_share && ((bar_size >> 1) >= XEON_B2B_MIN_SIZE)) { - dev_dbg(ndev_dev(ndev), - "b2b using first half of bar\n"); + dev_dbg(&pdev->dev, "b2b using first half of bar\n"); ndev->b2b_off = bar_size >> 1; } else if (bar_size >= XEON_B2B_MIN_SIZE) { - dev_dbg(ndev_dev(ndev), - "b2b using whole bar\n"); + dev_dbg(&pdev->dev, "b2b using whole bar\n"); ndev->b2b_off = 0; --ndev->mw_count; } else { - dev_dbg(ndev_dev(ndev), - "b2b bar size is too small\n"); + dev_dbg(&pdev->dev, "b2b bar size is too small\n"); return -EIO; } } @@ -1781,7 +1783,7 @@ static int skx_setup_b2b_mw(struct intel_ntb_dev *ndev, * except disable or halve the size of the b2b secondary bar. */ pci_read_config_byte(pdev, SKX_IMBAR1SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "IMBAR1SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "IMBAR1SZ %#x\n", bar_sz); if (b2b_bar == 1) { if (ndev->b2b_off) bar_sz -= 1; @@ -1791,10 +1793,10 @@ static int skx_setup_b2b_mw(struct intel_ntb_dev *ndev, pci_write_config_byte(pdev, SKX_EMBAR1SZ_OFFSET, bar_sz); pci_read_config_byte(pdev, SKX_EMBAR1SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "EMBAR1SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "EMBAR1SZ %#x\n", bar_sz); pci_read_config_byte(pdev, SKX_IMBAR2SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "IMBAR2SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "IMBAR2SZ %#x\n", bar_sz); if (b2b_bar == 2) { if (ndev->b2b_off) bar_sz -= 1; @@ -1804,7 +1806,7 @@ static int skx_setup_b2b_mw(struct intel_ntb_dev *ndev, pci_write_config_byte(pdev, SKX_EMBAR2SZ_OFFSET, bar_sz); pci_read_config_byte(pdev, SKX_EMBAR2SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "EMBAR2SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "EMBAR2SZ %#x\n", bar_sz); /* SBAR01 hit by first part of the b2b bar */ if (b2b_bar == 0) @@ -1820,12 +1822,12 @@ static int skx_setup_b2b_mw(struct intel_ntb_dev *ndev, bar_addr = addr->bar2_addr64 + (b2b_bar == 1 ? ndev->b2b_off : 0); iowrite64(bar_addr, mmio + SKX_IMBAR1XLMT_OFFSET); bar_addr = ioread64(mmio + SKX_IMBAR1XLMT_OFFSET); - dev_dbg(ndev_dev(ndev), "IMBAR1XLMT %#018llx\n", bar_addr); + dev_dbg(&pdev->dev, "IMBAR1XLMT %#018llx\n", bar_addr); bar_addr = addr->bar4_addr64 + (b2b_bar == 2 ? ndev->b2b_off : 0); iowrite64(bar_addr, mmio + SKX_IMBAR2XLMT_OFFSET); bar_addr = ioread64(mmio + SKX_IMBAR2XLMT_OFFSET); - dev_dbg(ndev_dev(ndev), "IMBAR2XLMT %#018llx\n", bar_addr); + dev_dbg(&pdev->dev, "IMBAR2XLMT %#018llx\n", bar_addr); /* zero incoming translation addrs */ iowrite64(0, mmio + SKX_IMBAR1XBASE_OFFSET); @@ -1895,7 +1897,7 @@ static int skx_init_dev(struct intel_ntb_dev *ndev) u8 ppd; int rc; - pdev = ndev_pdev(ndev); + pdev = ndev->ntb.pdev; ndev->reg = &skx_reg; @@ -1904,7 +1906,7 @@ static int skx_init_dev(struct intel_ntb_dev *ndev) return -EIO; ndev->ntb.topo = xeon_ppd_topo(ndev, ppd); - dev_dbg(ndev_dev(ndev), "ppd %#x topo %s\n", ppd, + dev_dbg(&pdev->dev, "ppd %#x topo %s\n", ppd, ntb_topo_string(ndev->ntb.topo)); if (ndev->ntb.topo == NTB_TOPO_NONE) return -EINVAL; @@ -1928,14 +1930,14 @@ static int intel_ntb3_link_enable(struct ntb_dev *ntb, ndev = container_of(ntb, struct intel_ntb_dev, ntb); - dev_dbg(ndev_dev(ndev), + dev_dbg(&ntb->pdev->dev, "Enabling link with max_speed %d max_width %d\n", max_speed, max_width); if (max_speed != NTB_SPEED_AUTO) - dev_dbg(ndev_dev(ndev), "ignoring max_speed %d\n", max_speed); + dev_dbg(&ntb->pdev->dev, "ignoring max_speed %d\n", max_speed); if (max_width != NTB_WIDTH_AUTO) - dev_dbg(ndev_dev(ndev), "ignoring max_width %d\n", max_width); + dev_dbg(&ntb->pdev->dev, "ignoring max_width %d\n", max_width); ntb_ctl = ioread32(ndev->self_mmio + ndev->reg->ntb_ctl); ntb_ctl &= ~(NTB_CTL_DISABLE | NTB_CTL_CFG_LOCK); @@ -1999,7 +2001,7 @@ static int intel_ntb3_mw_set_trans(struct ntb_dev *ntb, int pidx, int idx, return -EIO; } - dev_dbg(ndev_dev(ndev), "BAR %d IMBARXBASE: %#Lx\n", bar, reg_val); + dev_dbg(&ntb->pdev->dev, "BAR %d IMBARXBASE: %#Lx\n", bar, reg_val); /* set and verify setting the limit */ iowrite64(limit, mmio + limit_reg); @@ -2010,7 +2012,7 @@ static int intel_ntb3_mw_set_trans(struct ntb_dev *ntb, int pidx, int idx, return -EIO; } - dev_dbg(ndev_dev(ndev), "BAR %d IMBARXLMT: %#Lx\n", bar, reg_val); + dev_dbg(&ntb->pdev->dev, "BAR %d IMBARXLMT: %#Lx\n", bar, reg_val); /* setup the EP */ limit_reg = ndev->xlat_reg->bar2_limit + (idx * 0x10) + 0x4000; @@ -2031,7 +2033,7 @@ static int intel_ntb3_mw_set_trans(struct ntb_dev *ntb, int pidx, int idx, return -EIO; } - dev_dbg(ndev_dev(ndev), "BAR %d EMBARXLMT: %#Lx\n", bar, reg_val); + dev_dbg(&ntb->pdev->dev, "BAR %d EMBARXLMT: %#Lx\n", bar, reg_val); return 0; } @@ -2138,7 +2140,7 @@ static inline enum ntb_topo xeon_ppd_topo(struct intel_ntb_dev *ndev, u8 ppd) static inline int xeon_ppd_bar4_split(struct intel_ntb_dev *ndev, u8 ppd) { if (ppd & XEON_PPD_SPLIT_BAR_MASK) { - dev_dbg(ndev_dev(ndev), "PPD %d split bar\n", ppd); + dev_dbg(&ndev->ntb.pdev->dev, "PPD %d split bar\n", ppd); return 1; } return 0; @@ -2168,11 +2170,11 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, int b2b_bar; u8 bar_sz; - pdev = ndev_pdev(ndev); + pdev = ndev->ntb.pdev; mmio = ndev->self_mmio; if (ndev->b2b_idx == UINT_MAX) { - dev_dbg(ndev_dev(ndev), "not using b2b mw\n"); + dev_dbg(&pdev->dev, "not using b2b mw\n"); b2b_bar = 0; ndev->b2b_off = 0; } else { @@ -2180,24 +2182,21 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, if (b2b_bar < 0) return -EIO; - dev_dbg(ndev_dev(ndev), "using b2b mw bar %d\n", b2b_bar); + dev_dbg(&pdev->dev, "using b2b mw bar %d\n", b2b_bar); bar_size = pci_resource_len(ndev->ntb.pdev, b2b_bar); - dev_dbg(ndev_dev(ndev), "b2b bar size %#llx\n", bar_size); + dev_dbg(&pdev->dev, "b2b bar size %#llx\n", bar_size); if (b2b_mw_share && XEON_B2B_MIN_SIZE <= bar_size >> 1) { - dev_dbg(ndev_dev(ndev), - "b2b using first half of bar\n"); + dev_dbg(&pdev->dev, "b2b using first half of bar\n"); ndev->b2b_off = bar_size >> 1; } else if (XEON_B2B_MIN_SIZE <= bar_size) { - dev_dbg(ndev_dev(ndev), - "b2b using whole bar\n"); + dev_dbg(&pdev->dev, "b2b using whole bar\n"); ndev->b2b_off = 0; --ndev->mw_count; } else { - dev_dbg(ndev_dev(ndev), - "b2b bar size is too small\n"); + dev_dbg(&pdev->dev, "b2b bar size is too small\n"); return -EIO; } } @@ -2209,7 +2208,7 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, * offsets are not in a consistent order (bar5sz comes after ppd, odd). */ pci_read_config_byte(pdev, XEON_PBAR23SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "PBAR23SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "PBAR23SZ %#x\n", bar_sz); if (b2b_bar == 2) { if (ndev->b2b_off) bar_sz -= 1; @@ -2218,11 +2217,11 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, } pci_write_config_byte(pdev, XEON_SBAR23SZ_OFFSET, bar_sz); pci_read_config_byte(pdev, XEON_SBAR23SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "SBAR23SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "SBAR23SZ %#x\n", bar_sz); if (!ndev->bar4_split) { pci_read_config_byte(pdev, XEON_PBAR45SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "PBAR45SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "PBAR45SZ %#x\n", bar_sz); if (b2b_bar == 4) { if (ndev->b2b_off) bar_sz -= 1; @@ -2231,10 +2230,10 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, } pci_write_config_byte(pdev, XEON_SBAR45SZ_OFFSET, bar_sz); pci_read_config_byte(pdev, XEON_SBAR45SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "SBAR45SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "SBAR45SZ %#x\n", bar_sz); } else { pci_read_config_byte(pdev, XEON_PBAR4SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "PBAR4SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "PBAR4SZ %#x\n", bar_sz); if (b2b_bar == 4) { if (ndev->b2b_off) bar_sz -= 1; @@ -2243,10 +2242,10 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, } pci_write_config_byte(pdev, XEON_SBAR4SZ_OFFSET, bar_sz); pci_read_config_byte(pdev, XEON_SBAR4SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "SBAR4SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "SBAR4SZ %#x\n", bar_sz); pci_read_config_byte(pdev, XEON_PBAR5SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "PBAR5SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "PBAR5SZ %#x\n", bar_sz); if (b2b_bar == 5) { if (ndev->b2b_off) bar_sz -= 1; @@ -2255,7 +2254,7 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, } pci_write_config_byte(pdev, XEON_SBAR5SZ_OFFSET, bar_sz); pci_read_config_byte(pdev, XEON_SBAR5SZ_OFFSET, &bar_sz); - dev_dbg(ndev_dev(ndev), "SBAR5SZ %#x\n", bar_sz); + dev_dbg(&pdev->dev, "SBAR5SZ %#x\n", bar_sz); } /* SBAR01 hit by first part of the b2b bar */ @@ -2272,7 +2271,7 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, else return -EIO; - dev_dbg(ndev_dev(ndev), "SBAR01 %#018llx\n", bar_addr); + dev_dbg(&pdev->dev, "SBAR01 %#018llx\n", bar_addr); iowrite64(bar_addr, mmio + XEON_SBAR0BASE_OFFSET); /* Other SBAR are normally hit by the PBAR xlat, except for b2b bar. @@ -2283,26 +2282,26 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, bar_addr = addr->bar2_addr64 + (b2b_bar == 2 ? ndev->b2b_off : 0); iowrite64(bar_addr, mmio + XEON_SBAR23BASE_OFFSET); bar_addr = ioread64(mmio + XEON_SBAR23BASE_OFFSET); - dev_dbg(ndev_dev(ndev), "SBAR23 %#018llx\n", bar_addr); + dev_dbg(&pdev->dev, "SBAR23 %#018llx\n", bar_addr); if (!ndev->bar4_split) { bar_addr = addr->bar4_addr64 + (b2b_bar == 4 ? ndev->b2b_off : 0); iowrite64(bar_addr, mmio + XEON_SBAR45BASE_OFFSET); bar_addr = ioread64(mmio + XEON_SBAR45BASE_OFFSET); - dev_dbg(ndev_dev(ndev), "SBAR45 %#018llx\n", bar_addr); + dev_dbg(&pdev->dev, "SBAR45 %#018llx\n", bar_addr); } else { bar_addr = addr->bar4_addr32 + (b2b_bar == 4 ? ndev->b2b_off : 0); iowrite32(bar_addr, mmio + XEON_SBAR4BASE_OFFSET); bar_addr = ioread32(mmio + XEON_SBAR4BASE_OFFSET); - dev_dbg(ndev_dev(ndev), "SBAR4 %#010llx\n", bar_addr); + dev_dbg(&pdev->dev, "SBAR4 %#010llx\n", bar_addr); bar_addr = addr->bar5_addr32 + (b2b_bar == 5 ? ndev->b2b_off : 0); iowrite32(bar_addr, mmio + XEON_SBAR5BASE_OFFSET); bar_addr = ioread32(mmio + XEON_SBAR5BASE_OFFSET); - dev_dbg(ndev_dev(ndev), "SBAR5 %#010llx\n", bar_addr); + dev_dbg(&pdev->dev, "SBAR5 %#010llx\n", bar_addr); } /* setup incoming bar limits == base addrs (zero length windows) */ @@ -2310,26 +2309,26 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, bar_addr = addr->bar2_addr64 + (b2b_bar == 2 ? ndev->b2b_off : 0); iowrite64(bar_addr, mmio + XEON_SBAR23LMT_OFFSET); bar_addr = ioread64(mmio + XEON_SBAR23LMT_OFFSET); - dev_dbg(ndev_dev(ndev), "SBAR23LMT %#018llx\n", bar_addr); + dev_dbg(&pdev->dev, "SBAR23LMT %#018llx\n", bar_addr); if (!ndev->bar4_split) { bar_addr = addr->bar4_addr64 + (b2b_bar == 4 ? ndev->b2b_off : 0); iowrite64(bar_addr, mmio + XEON_SBAR45LMT_OFFSET); bar_addr = ioread64(mmio + XEON_SBAR45LMT_OFFSET); - dev_dbg(ndev_dev(ndev), "SBAR45LMT %#018llx\n", bar_addr); + dev_dbg(&pdev->dev, "SBAR45LMT %#018llx\n", bar_addr); } else { bar_addr = addr->bar4_addr32 + (b2b_bar == 4 ? ndev->b2b_off : 0); iowrite32(bar_addr, mmio + XEON_SBAR4LMT_OFFSET); bar_addr = ioread32(mmio + XEON_SBAR4LMT_OFFSET); - dev_dbg(ndev_dev(ndev), "SBAR4LMT %#010llx\n", bar_addr); + dev_dbg(&pdev->dev, "SBAR4LMT %#010llx\n", bar_addr); bar_addr = addr->bar5_addr32 + (b2b_bar == 5 ? ndev->b2b_off : 0); iowrite32(bar_addr, mmio + XEON_SBAR5LMT_OFFSET); bar_addr = ioread32(mmio + XEON_SBAR5LMT_OFFSET); - dev_dbg(ndev_dev(ndev), "SBAR5LMT %#05llx\n", bar_addr); + dev_dbg(&pdev->dev, "SBAR5LMT %#05llx\n", bar_addr); } /* zero incoming translation addrs */ @@ -2355,23 +2354,23 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, bar_addr = peer_addr->bar2_addr64; iowrite64(bar_addr, mmio + XEON_PBAR23XLAT_OFFSET); bar_addr = ioread64(mmio + XEON_PBAR23XLAT_OFFSET); - dev_dbg(ndev_dev(ndev), "PBAR23XLAT %#018llx\n", bar_addr); + dev_dbg(&pdev->dev, "PBAR23XLAT %#018llx\n", bar_addr); if (!ndev->bar4_split) { bar_addr = peer_addr->bar4_addr64; iowrite64(bar_addr, mmio + XEON_PBAR45XLAT_OFFSET); bar_addr = ioread64(mmio + XEON_PBAR45XLAT_OFFSET); - dev_dbg(ndev_dev(ndev), "PBAR45XLAT %#018llx\n", bar_addr); + dev_dbg(&pdev->dev, "PBAR45XLAT %#018llx\n", bar_addr); } else { bar_addr = peer_addr->bar4_addr32; iowrite32(bar_addr, mmio + XEON_PBAR4XLAT_OFFSET); bar_addr = ioread32(mmio + XEON_PBAR4XLAT_OFFSET); - dev_dbg(ndev_dev(ndev), "PBAR4XLAT %#010llx\n", bar_addr); + dev_dbg(&pdev->dev, "PBAR4XLAT %#010llx\n", bar_addr); bar_addr = peer_addr->bar5_addr32; iowrite32(bar_addr, mmio + XEON_PBAR5XLAT_OFFSET); bar_addr = ioread32(mmio + XEON_PBAR5XLAT_OFFSET); - dev_dbg(ndev_dev(ndev), "PBAR5XLAT %#010llx\n", bar_addr); + dev_dbg(&pdev->dev, "PBAR5XLAT %#010llx\n", bar_addr); } /* set the translation offset for b2b registers */ @@ -2389,7 +2388,7 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, return -EIO; /* B2B_XLAT_OFFSET is 64bit, but can only take 32bit writes */ - dev_dbg(ndev_dev(ndev), "B2BXLAT %#018llx\n", bar_addr); + dev_dbg(&pdev->dev, "B2BXLAT %#018llx\n", bar_addr); iowrite32(bar_addr, mmio + XEON_B2B_XLAT_OFFSETL); iowrite32(bar_addr >> 32, mmio + XEON_B2B_XLAT_OFFSETU); @@ -2408,6 +2407,7 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, static int xeon_init_ntb(struct intel_ntb_dev *ndev) { + struct device *dev = &ndev->ntb.pdev->dev; int rc; u32 ntb_ctl; @@ -2423,7 +2423,7 @@ static int xeon_init_ntb(struct intel_ntb_dev *ndev) switch (ndev->ntb.topo) { case NTB_TOPO_PRI: if (ndev->hwerr_flags & NTB_HWERR_SDOORBELL_LOCKUP) { - dev_err(ndev_dev(ndev), "NTB Primary config disabled\n"); + dev_err(dev, "NTB Primary config disabled\n"); return -EINVAL; } @@ -2441,7 +2441,7 @@ static int xeon_init_ntb(struct intel_ntb_dev *ndev) case NTB_TOPO_SEC: if (ndev->hwerr_flags & NTB_HWERR_SDOORBELL_LOCKUP) { - dev_err(ndev_dev(ndev), "NTB Secondary config disabled\n"); + dev_err(dev, "NTB Secondary config disabled\n"); return -EINVAL; } /* use half the spads for the peer */ @@ -2466,18 +2466,17 @@ static int xeon_init_ntb(struct intel_ntb_dev *ndev) ndev->b2b_idx = b2b_mw_idx; if (ndev->b2b_idx >= ndev->mw_count) { - dev_dbg(ndev_dev(ndev), + dev_dbg(dev, "b2b_mw_idx %d invalid for mw_count %u\n", b2b_mw_idx, ndev->mw_count); return -EINVAL; } - dev_dbg(ndev_dev(ndev), - "setting up b2b mw idx %d means %d\n", + dev_dbg(dev, "setting up b2b mw idx %d means %d\n", b2b_mw_idx, ndev->b2b_idx); } else if (ndev->hwerr_flags & NTB_HWERR_B2BDOORBELL_BIT14) { - dev_warn(ndev_dev(ndev), "Reduce doorbell count by 1\n"); + dev_warn(dev, "Reduce doorbell count by 1\n"); ndev->db_count -= 1; } @@ -2518,7 +2517,7 @@ static int xeon_init_dev(struct intel_ntb_dev *ndev) u8 ppd; int rc, mem; - pdev = ndev_pdev(ndev); + pdev = ndev->ntb.pdev; switch (pdev->device) { /* There is a Xeon hardware errata related to writes to SDOORBELL or @@ -2594,14 +2593,14 @@ static int xeon_init_dev(struct intel_ntb_dev *ndev) return -EIO; ndev->ntb.topo = xeon_ppd_topo(ndev, ppd); - dev_dbg(ndev_dev(ndev), "ppd %#x topo %s\n", ppd, + dev_dbg(&pdev->dev, "ppd %#x topo %s\n", ppd, ntb_topo_string(ndev->ntb.topo)); if (ndev->ntb.topo == NTB_TOPO_NONE) return -EINVAL; if (ndev->ntb.topo != NTB_TOPO_SEC) { ndev->bar4_split = xeon_ppd_bar4_split(ndev, ppd); - dev_dbg(ndev_dev(ndev), "ppd %#x bar4_split %d\n", + dev_dbg(&pdev->dev, "ppd %#x bar4_split %d\n", ppd, ndev->bar4_split); } else { /* This is a way for transparent BAR to figure out if we are @@ -2611,7 +2610,7 @@ static int xeon_init_dev(struct intel_ntb_dev *ndev) mem = pci_select_bars(pdev, IORESOURCE_MEM); ndev->bar4_split = hweight32(mem) == HSX_SPLIT_BAR_MW_COUNT + 1; - dev_dbg(ndev_dev(ndev), "mem %#x bar4_split %d\n", + dev_dbg(&pdev->dev, "mem %#x bar4_split %d\n", mem, ndev->bar4_split); } @@ -2648,7 +2647,7 @@ static int intel_ntb_init_pci(struct intel_ntb_dev *ndev, struct pci_dev *pdev) rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); if (rc) goto err_dma_mask; - dev_warn(ndev_dev(ndev), "Cannot DMA highmem\n"); + dev_warn(&pdev->dev, "Cannot DMA highmem\n"); } rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); @@ -2656,7 +2655,7 @@ static int intel_ntb_init_pci(struct intel_ntb_dev *ndev, struct pci_dev *pdev) rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); if (rc) goto err_dma_mask; - dev_warn(ndev_dev(ndev), "Cannot DMA consistent highmem\n"); + dev_warn(&pdev->dev, "Cannot DMA consistent highmem\n"); } ndev->self_mmio = pci_iomap(pdev, 0, 0); @@ -2682,7 +2681,7 @@ err_pci_enable: static void intel_ntb_deinit_pci(struct intel_ntb_dev *ndev) { - struct pci_dev *pdev = ndev_pdev(ndev); + struct pci_dev *pdev = ndev->ntb.pdev; if (ndev->peer_mmio && ndev->peer_mmio != ndev->self_mmio) pci_iounmap(pdev, ndev->peer_mmio); @@ -3058,4 +3057,3 @@ static void __exit intel_ntb_pci_driver_exit(void) debugfs_remove_recursive(debugfs_dir); } module_exit(intel_ntb_pci_driver_exit); - diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.h b/drivers/ntb/hw/intel/ntb_hw_intel.h index f2cf8a783f1e..2d6c38afb128 100644 --- a/drivers/ntb/hw/intel/ntb_hw_intel.h +++ b/drivers/ntb/hw/intel/ntb_hw_intel.h @@ -382,9 +382,6 @@ struct intel_ntb_dev { struct dentry *debugfs_info; }; -#define ndev_pdev(ndev) ((ndev)->ntb.pdev) -#define ndev_name(ndev) pci_name(ndev_pdev(ndev)) -#define ndev_dev(ndev) (&ndev_pdev(ndev)->dev) #define ntb_ndev(__ntb) container_of(__ntb, struct intel_ntb_dev, ntb) #define hb_ndev(__work) container_of(__work, struct intel_ntb_dev, \ hb_timer.work) -- cgit v1.2.3-59-g8ed1b From bf2a952d31d2cd28bb3454f15645a76fda70addd Mon Sep 17 00:00:00 2001 From: Serge Semin Date: Wed, 12 Apr 2017 15:44:45 +0300 Subject: NTB: Add IDT 89HPESxNTx PCIe-switches support IDT 89HPESxNTx device series is PCIe-switches, which support Non-Transparent bridging between domains connected to the device ports. Since new NTB API exposes multi-port interface and messaging API, the IDT NT-functions can be now supported in the kernel. This driver adds the following functionality: 1) Multi-port NTB API to have information of possible NT-functions activated in compliance with available device ports. 2) Memory windows of direct and look up table based address translation with all possible combinations of BARs setup. 3) Traditional doorbell NTB API. 4) One-on-one messaging NTB API. There are some IDT PCIe-switch setups, which must be done before any of the NTB peers started. It can be performed either by system BIOS via IDT SMBus-slave interface or by pre-initialized IDT PCIe-switch EEPROM: 1) NT-functions of corresponding ports must be activated using SWPARTxCTL and SWPORTxCTL registers. 2) BAR0 must be configured to expose NT-function configuration registers map. 3) The rest of the BARs must have at least one memory window configured, otherwise the driver will just return an error. Temperature sensor of IDT PCIe-switches can be also optionally activated by BIOS or EEPROM. (See IDT documentations for details of how the pre-initialization can be done) Signed-off-by: Serge Semin Acked-by: Allen Hubbe Signed-off-by: Jon Mason --- MAINTAINERS | 6 + drivers/ntb/hw/Kconfig | 1 + drivers/ntb/hw/Makefile | 1 + drivers/ntb/hw/idt/Kconfig | 31 + drivers/ntb/hw/idt/Makefile | 1 + drivers/ntb/hw/idt/ntb_hw_idt.c | 2712 +++++++++++++++++++++++++++++++++++++++ drivers/ntb/hw/idt/ntb_hw_idt.h | 1149 +++++++++++++++++ 7 files changed, 3901 insertions(+) create mode 100644 drivers/ntb/hw/idt/Kconfig create mode 100644 drivers/ntb/hw/idt/Makefile create mode 100644 drivers/ntb/hw/idt/ntb_hw_idt.c create mode 100644 drivers/ntb/hw/idt/ntb_hw_idt.h diff --git a/MAINTAINERS b/MAINTAINERS index 767e9d202adf..66f7649fad95 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9122,6 +9122,12 @@ F: include/linux/ntb.h F: include/linux/ntb_transport.h F: tools/testing/selftests/ntb/ +NTB IDT DRIVER +M: Serge Semin +L: linux-ntb@googlegroups.com +S: Supported +F: drivers/ntb/hw/idt/ + NTB INTEL DRIVER M: Jon Mason M: Dave Jiang diff --git a/drivers/ntb/hw/Kconfig b/drivers/ntb/hw/Kconfig index 7116472b4625..a89243c9fdd3 100644 --- a/drivers/ntb/hw/Kconfig +++ b/drivers/ntb/hw/Kconfig @@ -1,2 +1,3 @@ source "drivers/ntb/hw/amd/Kconfig" +source "drivers/ntb/hw/idt/Kconfig" source "drivers/ntb/hw/intel/Kconfig" diff --git a/drivers/ntb/hw/Makefile b/drivers/ntb/hw/Makefile index 532e0859b4a1..87332c3905f0 100644 --- a/drivers/ntb/hw/Makefile +++ b/drivers/ntb/hw/Makefile @@ -1,2 +1,3 @@ obj-$(CONFIG_NTB_AMD) += amd/ +obj-$(CONFIG_NTB_IDT) += idt/ obj-$(CONFIG_NTB_INTEL) += intel/ diff --git a/drivers/ntb/hw/idt/Kconfig b/drivers/ntb/hw/idt/Kconfig new file mode 100644 index 000000000000..b360e5613b9f --- /dev/null +++ b/drivers/ntb/hw/idt/Kconfig @@ -0,0 +1,31 @@ +config NTB_IDT + tristate "IDT PCIe-switch Non-Transparent Bridge support" + depends on PCI + help + This driver supports NTB of cappable IDT PCIe-switches. + + Some of the pre-initializations must be made before IDT PCIe-switch + exposes it NT-functions correctly. It should be done by either proper + initialisation of EEPROM connected to master smbus of the switch or + by BIOS using slave-SMBus interface changing corresponding registers + value. Evidently it must be done before PCI bus enumeration is + finished in Linux kernel. + + First of all partitions must be activated and properly assigned to all + the ports with NT-functions intended to be activated (see SWPARTxCTL + and SWPORTxCTL registers). Then all NT-function BARs must be enabled + with chosen valid aperture. For memory windows related BARs the + aperture settings shall determine the maximum size of memory windows + accepted by a BAR. Note that BAR0 must map PCI configuration space + registers. + + It's worth to note, that since a part of this driver relies on the + BAR settings of peer NT-functions, the BAR setups can't be done over + kernel PCI fixups. That's why the alternative pre-initialization + techniques like BIOS using SMBus interface or EEPROM should be + utilized. Additionally if one needs to have temperature sensor + information printed to system log, the corresponding registers must + be initialized within BIOS/EEPROM as well. + + If unsure, say N. + diff --git a/drivers/ntb/hw/idt/Makefile b/drivers/ntb/hw/idt/Makefile new file mode 100644 index 000000000000..a102cf154be0 --- /dev/null +++ b/drivers/ntb/hw/idt/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_NTB_IDT) += ntb_hw_idt.o diff --git a/drivers/ntb/hw/idt/ntb_hw_idt.c b/drivers/ntb/hw/idt/ntb_hw_idt.c new file mode 100644 index 000000000000..d44d7ef38fe8 --- /dev/null +++ b/drivers/ntb/hw/idt/ntb_hw_idt.c @@ -0,0 +1,2712 @@ +/* + * This file is provided under a GPLv2 license. When using or + * redistributing this file, you may do so under that license. + * + * GPL LICENSE SUMMARY + * + * Copyright (C) 2016 T-Platforms All Rights Reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General + * Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, one can be found http://www.gnu.org/licenses/. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + * IDT PCIe-switch NTB Linux driver + * + * Contact Information: + * Serge Semin , + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "ntb_hw_idt.h" + +#define NTB_NAME "ntb_hw_idt" +#define NTB_DESC "IDT PCI-E Non-Transparent Bridge Driver" +#define NTB_VER "2.0" +#define NTB_IRQNAME "ntb_irq_idt" + +MODULE_DESCRIPTION(NTB_DESC); +MODULE_VERSION(NTB_VER); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("T-platforms"); + +/* + * NT Endpoint registers table simplifying a loop access to the functionally + * related registers + */ +static const struct idt_ntb_regs ntdata_tbl = { + { {IDT_NT_BARSETUP0, IDT_NT_BARLIMIT0, + IDT_NT_BARLTBASE0, IDT_NT_BARUTBASE0}, + {IDT_NT_BARSETUP1, IDT_NT_BARLIMIT1, + IDT_NT_BARLTBASE1, IDT_NT_BARUTBASE1}, + {IDT_NT_BARSETUP2, IDT_NT_BARLIMIT2, + IDT_NT_BARLTBASE2, IDT_NT_BARUTBASE2}, + {IDT_NT_BARSETUP3, IDT_NT_BARLIMIT3, + IDT_NT_BARLTBASE3, IDT_NT_BARUTBASE3}, + {IDT_NT_BARSETUP4, IDT_NT_BARLIMIT4, + IDT_NT_BARLTBASE4, IDT_NT_BARUTBASE4}, + {IDT_NT_BARSETUP5, IDT_NT_BARLIMIT5, + IDT_NT_BARLTBASE5, IDT_NT_BARUTBASE5} }, + { {IDT_NT_INMSG0, IDT_NT_OUTMSG0, IDT_NT_INMSGSRC0}, + {IDT_NT_INMSG1, IDT_NT_OUTMSG1, IDT_NT_INMSGSRC1}, + {IDT_NT_INMSG2, IDT_NT_OUTMSG2, IDT_NT_INMSGSRC2}, + {IDT_NT_INMSG3, IDT_NT_OUTMSG3, IDT_NT_INMSGSRC3} } +}; + +/* + * NT Endpoint ports data table with the corresponding pcie command, link + * status, control and BAR-related registers + */ +static const struct idt_ntb_port portdata_tbl[IDT_MAX_NR_PORTS] = { +/*0*/ { IDT_SW_NTP0_PCIECMDSTS, IDT_SW_NTP0_PCIELCTLSTS, + IDT_SW_NTP0_NTCTL, + IDT_SW_SWPORT0CTL, IDT_SW_SWPORT0STS, + { {IDT_SW_NTP0_BARSETUP0, IDT_SW_NTP0_BARLIMIT0, + IDT_SW_NTP0_BARLTBASE0, IDT_SW_NTP0_BARUTBASE0}, + {IDT_SW_NTP0_BARSETUP1, IDT_SW_NTP0_BARLIMIT1, + IDT_SW_NTP0_BARLTBASE1, IDT_SW_NTP0_BARUTBASE1}, + {IDT_SW_NTP0_BARSETUP2, IDT_SW_NTP0_BARLIMIT2, + IDT_SW_NTP0_BARLTBASE2, IDT_SW_NTP0_BARUTBASE2}, + {IDT_SW_NTP0_BARSETUP3, IDT_SW_NTP0_BARLIMIT3, + IDT_SW_NTP0_BARLTBASE3, IDT_SW_NTP0_BARUTBASE3}, + {IDT_SW_NTP0_BARSETUP4, IDT_SW_NTP0_BARLIMIT4, + IDT_SW_NTP0_BARLTBASE4, IDT_SW_NTP0_BARUTBASE4}, + {IDT_SW_NTP0_BARSETUP5, IDT_SW_NTP0_BARLIMIT5, + IDT_SW_NTP0_BARLTBASE5, IDT_SW_NTP0_BARUTBASE5} } }, +/*1*/ {0}, +/*2*/ { IDT_SW_NTP2_PCIECMDSTS, IDT_SW_NTP2_PCIELCTLSTS, + IDT_SW_NTP2_NTCTL, + IDT_SW_SWPORT2CTL, IDT_SW_SWPORT2STS, + { {IDT_SW_NTP2_BARSETUP0, IDT_SW_NTP2_BARLIMIT0, + IDT_SW_NTP2_BARLTBASE0, IDT_SW_NTP2_BARUTBASE0}, + {IDT_SW_NTP2_BARSETUP1, IDT_SW_NTP2_BARLIMIT1, + IDT_SW_NTP2_BARLTBASE1, IDT_SW_NTP2_BARUTBASE1}, + {IDT_SW_NTP2_BARSETUP2, IDT_SW_NTP2_BARLIMIT2, + IDT_SW_NTP2_BARLTBASE2, IDT_SW_NTP2_BARUTBASE2}, + {IDT_SW_NTP2_BARSETUP3, IDT_SW_NTP2_BARLIMIT3, + IDT_SW_NTP2_BARLTBASE3, IDT_SW_NTP2_BARUTBASE3}, + {IDT_SW_NTP2_BARSETUP4, IDT_SW_NTP2_BARLIMIT4, + IDT_SW_NTP2_BARLTBASE4, IDT_SW_NTP2_BARUTBASE4}, + {IDT_SW_NTP2_BARSETUP5, IDT_SW_NTP2_BARLIMIT5, + IDT_SW_NTP2_BARLTBASE5, IDT_SW_NTP2_BARUTBASE5} } }, +/*3*/ {0}, +/*4*/ { IDT_SW_NTP4_PCIECMDSTS, IDT_SW_NTP4_PCIELCTLSTS, + IDT_SW_NTP4_NTCTL, + IDT_SW_SWPORT4CTL, IDT_SW_SWPORT4STS, + { {IDT_SW_NTP4_BARSETUP0, IDT_SW_NTP4_BARLIMIT0, + IDT_SW_NTP4_BARLTBASE0, IDT_SW_NTP4_BARUTBASE0}, + {IDT_SW_NTP4_BARSETUP1, IDT_SW_NTP4_BARLIMIT1, + IDT_SW_NTP4_BARLTBASE1, IDT_SW_NTP4_BARUTBASE1}, + {IDT_SW_NTP4_BARSETUP2, IDT_SW_NTP4_BARLIMIT2, + IDT_SW_NTP4_BARLTBASE2, IDT_SW_NTP4_BARUTBASE2}, + {IDT_SW_NTP4_BARSETUP3, IDT_SW_NTP4_BARLIMIT3, + IDT_SW_NTP4_BARLTBASE3, IDT_SW_NTP4_BARUTBASE3}, + {IDT_SW_NTP4_BARSETUP4, IDT_SW_NTP4_BARLIMIT4, + IDT_SW_NTP4_BARLTBASE4, IDT_SW_NTP4_BARUTBASE4}, + {IDT_SW_NTP4_BARSETUP5, IDT_SW_NTP4_BARLIMIT5, + IDT_SW_NTP4_BARLTBASE5, IDT_SW_NTP4_BARUTBASE5} } }, +/*5*/ {0}, +/*6*/ { IDT_SW_NTP6_PCIECMDSTS, IDT_SW_NTP6_PCIELCTLSTS, + IDT_SW_NTP6_NTCTL, + IDT_SW_SWPORT6CTL, IDT_SW_SWPORT6STS, + { {IDT_SW_NTP6_BARSETUP0, IDT_SW_NTP6_BARLIMIT0, + IDT_SW_NTP6_BARLTBASE0, IDT_SW_NTP6_BARUTBASE0}, + {IDT_SW_NTP6_BARSETUP1, IDT_SW_NTP6_BARLIMIT1, + IDT_SW_NTP6_BARLTBASE1, IDT_SW_NTP6_BARUTBASE1}, + {IDT_SW_NTP6_BARSETUP2, IDT_SW_NTP6_BARLIMIT2, + IDT_SW_NTP6_BARLTBASE2, IDT_SW_NTP6_BARUTBASE2}, + {IDT_SW_NTP6_BARSETUP3, IDT_SW_NTP6_BARLIMIT3, + IDT_SW_NTP6_BARLTBASE3, IDT_SW_NTP6_BARUTBASE3}, + {IDT_SW_NTP6_BARSETUP4, IDT_SW_NTP6_BARLIMIT4, + IDT_SW_NTP6_BARLTBASE4, IDT_SW_NTP6_BARUTBASE4}, + {IDT_SW_NTP6_BARSETUP5, IDT_SW_NTP6_BARLIMIT5, + IDT_SW_NTP6_BARLTBASE5, IDT_SW_NTP6_BARUTBASE5} } }, +/*7*/ {0}, +/*8*/ { IDT_SW_NTP8_PCIECMDSTS, IDT_SW_NTP8_PCIELCTLSTS, + IDT_SW_NTP8_NTCTL, + IDT_SW_SWPORT8CTL, IDT_SW_SWPORT8STS, + { {IDT_SW_NTP8_BARSETUP0, IDT_SW_NTP8_BARLIMIT0, + IDT_SW_NTP8_BARLTBASE0, IDT_SW_NTP8_BARUTBASE0}, + {IDT_SW_NTP8_BARSETUP1, IDT_SW_NTP8_BARLIMIT1, + IDT_SW_NTP8_BARLTBASE1, IDT_SW_NTP8_BARUTBASE1}, + {IDT_SW_NTP8_BARSETUP2, IDT_SW_NTP8_BARLIMIT2, + IDT_SW_NTP8_BARLTBASE2, IDT_SW_NTP8_BARUTBASE2}, + {IDT_SW_NTP8_BARSETUP3, IDT_SW_NTP8_BARLIMIT3, + IDT_SW_NTP8_BARLTBASE3, IDT_SW_NTP8_BARUTBASE3}, + {IDT_SW_NTP8_BARSETUP4, IDT_SW_NTP8_BARLIMIT4, + IDT_SW_NTP8_BARLTBASE4, IDT_SW_NTP8_BARUTBASE4}, + {IDT_SW_NTP8_BARSETUP5, IDT_SW_NTP8_BARLIMIT5, + IDT_SW_NTP8_BARLTBASE5, IDT_SW_NTP8_BARUTBASE5} } }, +/*9*/ {0}, +/*10*/ {0}, +/*11*/ {0}, +/*12*/ { IDT_SW_NTP12_PCIECMDSTS, IDT_SW_NTP12_PCIELCTLSTS, + IDT_SW_NTP12_NTCTL, + IDT_SW_SWPORT12CTL, IDT_SW_SWPORT12STS, + { {IDT_SW_NTP12_BARSETUP0, IDT_SW_NTP12_BARLIMIT0, + IDT_SW_NTP12_BARLTBASE0, IDT_SW_NTP12_BARUTBASE0}, + {IDT_SW_NTP12_BARSETUP1, IDT_SW_NTP12_BARLIMIT1, + IDT_SW_NTP12_BARLTBASE1, IDT_SW_NTP12_BARUTBASE1}, + {IDT_SW_NTP12_BARSETUP2, IDT_SW_NTP12_BARLIMIT2, + IDT_SW_NTP12_BARLTBASE2, IDT_SW_NTP12_BARUTBASE2}, + {IDT_SW_NTP12_BARSETUP3, IDT_SW_NTP12_BARLIMIT3, + IDT_SW_NTP12_BARLTBASE3, IDT_SW_NTP12_BARUTBASE3}, + {IDT_SW_NTP12_BARSETUP4, IDT_SW_NTP12_BARLIMIT4, + IDT_SW_NTP12_BARLTBASE4, IDT_SW_NTP12_BARUTBASE4}, + {IDT_SW_NTP12_BARSETUP5, IDT_SW_NTP12_BARLIMIT5, + IDT_SW_NTP12_BARLTBASE5, IDT_SW_NTP12_BARUTBASE5} } }, +/*13*/ {0}, +/*14*/ {0}, +/*15*/ {0}, +/*16*/ { IDT_SW_NTP16_PCIECMDSTS, IDT_SW_NTP16_PCIELCTLSTS, + IDT_SW_NTP16_NTCTL, + IDT_SW_SWPORT16CTL, IDT_SW_SWPORT16STS, + { {IDT_SW_NTP16_BARSETUP0, IDT_SW_NTP16_BARLIMIT0, + IDT_SW_NTP16_BARLTBASE0, IDT_SW_NTP16_BARUTBASE0}, + {IDT_SW_NTP16_BARSETUP1, IDT_SW_NTP16_BARLIMIT1, + IDT_SW_NTP16_BARLTBASE1, IDT_SW_NTP16_BARUTBASE1}, + {IDT_SW_NTP16_BARSETUP2, IDT_SW_NTP16_BARLIMIT2, + IDT_SW_NTP16_BARLTBASE2, IDT_SW_NTP16_BARUTBASE2}, + {IDT_SW_NTP16_BARSETUP3, IDT_SW_NTP16_BARLIMIT3, + IDT_SW_NTP16_BARLTBASE3, IDT_SW_NTP16_BARUTBASE3}, + {IDT_SW_NTP16_BARSETUP4, IDT_SW_NTP16_BARLIMIT4, + IDT_SW_NTP16_BARLTBASE4, IDT_SW_NTP16_BARUTBASE4}, + {IDT_SW_NTP16_BARSETUP5, IDT_SW_NTP16_BARLIMIT5, + IDT_SW_NTP16_BARLTBASE5, IDT_SW_NTP16_BARUTBASE5} } }, +/*17*/ {0}, +/*18*/ {0}, +/*19*/ {0}, +/*20*/ { IDT_SW_NTP20_PCIECMDSTS, IDT_SW_NTP20_PCIELCTLSTS, + IDT_SW_NTP20_NTCTL, + IDT_SW_SWPORT20CTL, IDT_SW_SWPORT20STS, + { {IDT_SW_NTP20_BARSETUP0, IDT_SW_NTP20_BARLIMIT0, + IDT_SW_NTP20_BARLTBASE0, IDT_SW_NTP20_BARUTBASE0}, + {IDT_SW_NTP20_BARSETUP1, IDT_SW_NTP20_BARLIMIT1, + IDT_SW_NTP20_BARLTBASE1, IDT_SW_NTP20_BARUTBASE1}, + {IDT_SW_NTP20_BARSETUP2, IDT_SW_NTP20_BARLIMIT2, + IDT_SW_NTP20_BARLTBASE2, IDT_SW_NTP20_BARUTBASE2}, + {IDT_SW_NTP20_BARSETUP3, IDT_SW_NTP20_BARLIMIT3, + IDT_SW_NTP20_BARLTBASE3, IDT_SW_NTP20_BARUTBASE3}, + {IDT_SW_NTP20_BARSETUP4, IDT_SW_NTP20_BARLIMIT4, + IDT_SW_NTP20_BARLTBASE4, IDT_SW_NTP20_BARUTBASE4}, + {IDT_SW_NTP20_BARSETUP5, IDT_SW_NTP20_BARLIMIT5, + IDT_SW_NTP20_BARLTBASE5, IDT_SW_NTP20_BARUTBASE5} } }, +/*21*/ {0}, +/*22*/ {0}, +/*23*/ {0} +}; + +/* + * IDT PCIe-switch partitions table with the corresponding control, status + * and messages control registers + */ +static const struct idt_ntb_part partdata_tbl[IDT_MAX_NR_PARTS] = { +/*0*/ { IDT_SW_SWPART0CTL, IDT_SW_SWPART0STS, + {IDT_SW_SWP0MSGCTL0, IDT_SW_SWP0MSGCTL1, + IDT_SW_SWP0MSGCTL2, IDT_SW_SWP0MSGCTL3} }, +/*1*/ { IDT_SW_SWPART1CTL, IDT_SW_SWPART1STS, + {IDT_SW_SWP1MSGCTL0, IDT_SW_SWP1MSGCTL1, + IDT_SW_SWP1MSGCTL2, IDT_SW_SWP1MSGCTL3} }, +/*2*/ { IDT_SW_SWPART2CTL, IDT_SW_SWPART2STS, + {IDT_SW_SWP2MSGCTL0, IDT_SW_SWP2MSGCTL1, + IDT_SW_SWP2MSGCTL2, IDT_SW_SWP2MSGCTL3} }, +/*3*/ { IDT_SW_SWPART3CTL, IDT_SW_SWPART3STS, + {IDT_SW_SWP3MSGCTL0, IDT_SW_SWP3MSGCTL1, + IDT_SW_SWP3MSGCTL2, IDT_SW_SWP3MSGCTL3} }, +/*4*/ { IDT_SW_SWPART4CTL, IDT_SW_SWPART4STS, + {IDT_SW_SWP4MSGCTL0, IDT_SW_SWP4MSGCTL1, + IDT_SW_SWP4MSGCTL2, IDT_SW_SWP4MSGCTL3} }, +/*5*/ { IDT_SW_SWPART5CTL, IDT_SW_SWPART5STS, + {IDT_SW_SWP5MSGCTL0, IDT_SW_SWP5MSGCTL1, + IDT_SW_SWP5MSGCTL2, IDT_SW_SWP5MSGCTL3} }, +/*6*/ { IDT_SW_SWPART6CTL, IDT_SW_SWPART6STS, + {IDT_SW_SWP6MSGCTL0, IDT_SW_SWP6MSGCTL1, + IDT_SW_SWP6MSGCTL2, IDT_SW_SWP6MSGCTL3} }, +/*7*/ { IDT_SW_SWPART7CTL, IDT_SW_SWPART7STS, + {IDT_SW_SWP7MSGCTL0, IDT_SW_SWP7MSGCTL1, + IDT_SW_SWP7MSGCTL2, IDT_SW_SWP7MSGCTL3} } +}; + +/* + * DebugFS directory to place the driver debug file + */ +static struct dentry *dbgfs_topdir; + +/*============================================================================= + * 1. IDT PCIe-switch registers IO-functions + * + * Beside ordinary configuration space registers IDT PCIe-switch expose + * global configuration registers, which are used to determine state of other + * device ports as well as being notified of some switch-related events. + * Additionally all the configuration space registers of all the IDT + * PCIe-switch functions are mapped to the Global Address space, so each + * function can determine a configuration of any other PCI-function. + * Functions declared in this chapter are created to encapsulate access + * to configuration and global registers, so the driver code just need to + * provide IDT NTB hardware descriptor and a register address. + *============================================================================= + */ + +/* + * idt_nt_write() - PCI configuration space registers write method + * @ndev: IDT NTB hardware driver descriptor + * @reg: Register to write data to + * @data: Value to write to the register + * + * IDT PCIe-switch registers are all Little endian. + */ +static void idt_nt_write(struct idt_ntb_dev *ndev, + const unsigned int reg, const u32 data) +{ + /* + * It's obvious bug to request a register exceeding the maximum possible + * value as well as to have it unaligned. + */ + if (WARN_ON(reg > IDT_REG_PCI_MAX || !IS_ALIGNED(reg, IDT_REG_ALIGN))) + return; + + /* Just write the value to the specified register */ + iowrite32(data, ndev->cfgspc + (ptrdiff_t)reg); +} + +/* + * idt_nt_read() - PCI configuration space registers read method + * @ndev: IDT NTB hardware driver descriptor + * @reg: Register to write data to + * + * IDT PCIe-switch Global configuration registers are all Little endian. + * + * Return: register value + */ +static u32 idt_nt_read(struct idt_ntb_dev *ndev, const unsigned int reg) +{ + /* + * It's obvious bug to request a register exceeding the maximum possible + * value as well as to have it unaligned. + */ + if (WARN_ON(reg > IDT_REG_PCI_MAX || !IS_ALIGNED(reg, IDT_REG_ALIGN))) + return ~0; + + /* Just read the value from the specified register */ + return ioread32(ndev->cfgspc + (ptrdiff_t)reg); +} + +/* + * idt_sw_write() - Global registers write method + * @ndev: IDT NTB hardware driver descriptor + * @reg: Register to write data to + * @data: Value to write to the register + * + * IDT PCIe-switch Global configuration registers are all Little endian. + */ +static void idt_sw_write(struct idt_ntb_dev *ndev, + const unsigned int reg, const u32 data) +{ + unsigned long irqflags; + + /* + * It's obvious bug to request a register exceeding the maximum possible + * value as well as to have it unaligned. + */ + if (WARN_ON(reg > IDT_REG_SW_MAX || !IS_ALIGNED(reg, IDT_REG_ALIGN))) + return; + + /* Lock GASA registers operations */ + spin_lock_irqsave(&ndev->gasa_lock, irqflags); + /* Set the global register address */ + iowrite32((u32)reg, ndev->cfgspc + (ptrdiff_t)IDT_NT_GASAADDR); + /* Put the new value of the register */ + iowrite32(data, ndev->cfgspc + (ptrdiff_t)IDT_NT_GASADATA); + /* Make sure the PCIe transactions are executed */ + mmiowb(); + /* Unlock GASA registers operations */ + spin_unlock_irqrestore(&ndev->gasa_lock, irqflags); +} + +/* + * idt_sw_read() - Global registers read method + * @ndev: IDT NTB hardware driver descriptor + * @reg: Register to write data to + * + * IDT PCIe-switch Global configuration registers are all Little endian. + * + * Return: register value + */ +static u32 idt_sw_read(struct idt_ntb_dev *ndev, const unsigned int reg) +{ + unsigned long irqflags; + u32 data; + + /* + * It's obvious bug to request a register exceeding the maximum possible + * value as well as to have it unaligned. + */ + if (WARN_ON(reg > IDT_REG_SW_MAX || !IS_ALIGNED(reg, IDT_REG_ALIGN))) + return ~0; + + /* Lock GASA registers operations */ + spin_lock_irqsave(&ndev->gasa_lock, irqflags); + /* Set the global register address */ + iowrite32((u32)reg, ndev->cfgspc + (ptrdiff_t)IDT_NT_GASAADDR); + /* Get the data of the register (read ops acts as MMIO barrier) */ + data = ioread32(ndev->cfgspc + (ptrdiff_t)IDT_NT_GASADATA); + /* Unlock GASA registers operations */ + spin_unlock_irqrestore(&ndev->gasa_lock, irqflags); + + return data; +} + +/* + * idt_reg_set_bits() - set bits of a passed register + * @ndev: IDT NTB hardware driver descriptor + * @reg: Register to change bits of + * @reg_lock: Register access spin lock + * @valid_mask: Mask of valid bits + * @set_bits: Bitmask to set + * + * Helper method to check whether a passed bitfield is valid and set + * corresponding bits of a register. + * + * WARNING! Make sure the passed register isn't accessed over plane + * idt_nt_write() method (read method is ok to be used concurrently). + * + * Return: zero on success, negative error on invalid bitmask. + */ +static inline int idt_reg_set_bits(struct idt_ntb_dev *ndev, unsigned int reg, + spinlock_t *reg_lock, + u64 valid_mask, u64 set_bits) +{ + unsigned long irqflags; + u32 data; + + if (set_bits & ~(u64)valid_mask) + return -EINVAL; + + /* Lock access to the register unless the change is written back */ + spin_lock_irqsave(reg_lock, irqflags); + data = idt_nt_read(ndev, reg) | (u32)set_bits; + idt_nt_write(ndev, reg, data); + /* Unlock the register */ + spin_unlock_irqrestore(reg_lock, irqflags); + + return 0; +} + +/* + * idt_reg_clear_bits() - clear bits of a passed register + * @ndev: IDT NTB hardware driver descriptor + * @reg: Register to change bits of + * @reg_lock: Register access spin lock + * @set_bits: Bitmask to clear + * + * Helper method to check whether a passed bitfield is valid and clear + * corresponding bits of a register. + * + * NOTE! Invalid bits are always considered cleared so it's not an error + * to clear them over. + * + * WARNING! Make sure the passed register isn't accessed over plane + * idt_nt_write() method (read method is ok to use concurrently). + */ +static inline void idt_reg_clear_bits(struct idt_ntb_dev *ndev, + unsigned int reg, spinlock_t *reg_lock, + u64 clear_bits) +{ + unsigned long irqflags; + u32 data; + + /* Lock access to the register unless the change is written back */ + spin_lock_irqsave(reg_lock, irqflags); + data = idt_nt_read(ndev, reg) & ~(u32)clear_bits; + idt_nt_write(ndev, reg, data); + /* Unlock the register */ + spin_unlock_irqrestore(reg_lock, irqflags); +} + +/*=========================================================================== + * 2. Ports operations + * + * IDT PCIe-switches can have from 3 up to 8 ports with possible + * NT-functions enabled. So all the possible ports need to be scanned looking + * for NTB activated. NTB API will have enumerated only the ports with NTB. + *=========================================================================== + */ + +/* + * idt_scan_ports() - scan IDT PCIe-switch ports collecting info in the tables + * @ndev: Pointer to the PCI device descriptor + * + * Return: zero on success, otherwise a negative error number. + */ +static int idt_scan_ports(struct idt_ntb_dev *ndev) +{ + unsigned char pidx, port, part; + u32 data, portsts, partsts; + + /* Retrieve the local port number */ + data = idt_nt_read(ndev, IDT_NT_PCIELCAP); + ndev->port = GET_FIELD(PCIELCAP_PORTNUM, data); + + /* Retrieve the local partition number */ + portsts = idt_sw_read(ndev, portdata_tbl[ndev->port].sts); + ndev->part = GET_FIELD(SWPORTxSTS_SWPART, portsts); + + /* Initialize port/partition -> index tables with invalid values */ + memset(ndev->port_idx_map, -EINVAL, sizeof(ndev->port_idx_map)); + memset(ndev->part_idx_map, -EINVAL, sizeof(ndev->part_idx_map)); + + /* + * Walk over all the possible ports checking whether any of them has + * NT-function activated + */ + ndev->peer_cnt = 0; + for (pidx = 0; pidx < ndev->swcfg->port_cnt; pidx++) { + port = ndev->swcfg->ports[pidx]; + /* Skip local port */ + if (port == ndev->port) + continue; + + /* Read the port status register to get it partition */ + portsts = idt_sw_read(ndev, portdata_tbl[port].sts); + part = GET_FIELD(SWPORTxSTS_SWPART, portsts); + + /* Retrieve the partition status */ + partsts = idt_sw_read(ndev, partdata_tbl[part].sts); + /* Check if partition state is active and port has NTB */ + if (IS_FLD_SET(SWPARTxSTS_STATE, partsts, ACT) && + (IS_FLD_SET(SWPORTxSTS_MODE, portsts, NT) || + IS_FLD_SET(SWPORTxSTS_MODE, portsts, USNT) || + IS_FLD_SET(SWPORTxSTS_MODE, portsts, USNTDMA) || + IS_FLD_SET(SWPORTxSTS_MODE, portsts, NTDMA))) { + /* Save the port and partition numbers */ + ndev->peers[ndev->peer_cnt].port = port; + ndev->peers[ndev->peer_cnt].part = part; + /* Fill in the port/partition -> index tables */ + ndev->port_idx_map[port] = ndev->peer_cnt; + ndev->part_idx_map[part] = ndev->peer_cnt; + ndev->peer_cnt++; + } + } + + dev_dbg(&ndev->ntb.pdev->dev, "Local port: %hhu, num of peers: %hhu\n", + ndev->port, ndev->peer_cnt); + + /* It's useless to have this driver loaded if there is no any peer */ + if (ndev->peer_cnt == 0) { + dev_warn(&ndev->ntb.pdev->dev, "No active peer found\n"); + return -ENODEV; + } + + return 0; +} + +/* + * idt_ntb_port_number() - get the local port number + * @ntb: NTB device context. + * + * Return: the local port number + */ +static int idt_ntb_port_number(struct ntb_dev *ntb) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + return ndev->port; +} + +/* + * idt_ntb_peer_port_count() - get the number of peer ports + * @ntb: NTB device context. + * + * Return the count of detected peer NT-functions. + * + * Return: number of peer ports + */ +static int idt_ntb_peer_port_count(struct ntb_dev *ntb) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + return ndev->peer_cnt; +} + +/* + * idt_ntb_peer_port_number() - get peer port by given index + * @ntb: NTB device context. + * @pidx: Peer port index. + * + * Return: peer port or negative error + */ +static int idt_ntb_peer_port_number(struct ntb_dev *ntb, int pidx) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + if (pidx < 0 || ndev->peer_cnt <= pidx) + return -EINVAL; + + /* Return the detected NT-function port number */ + return ndev->peers[pidx].port; +} + +/* + * idt_ntb_peer_port_idx() - get peer port index by given port number + * @ntb: NTB device context. + * @port: Peer port number. + * + * Internal port -> index table is pre-initialized with -EINVAL values, + * so we just need to return it value + * + * Return: peer NT-function port index or negative error + */ +static int idt_ntb_peer_port_idx(struct ntb_dev *ntb, int port) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + if (port < 0 || IDT_MAX_NR_PORTS <= port) + return -EINVAL; + + return ndev->port_idx_map[port]; +} + +/*=========================================================================== + * 3. Link status operations + * There is no any ready-to-use method to have peer ports notified if NTB + * link is set up or got down. Instead global signal can be used instead. + * In case if any one of ports changes local NTB link state, it sends + * global signal and clears corresponding global state bit. Then all the ports + * receive a notification of that, so to make client driver being aware of + * possible NTB link change. + * Additionally each of active NT-functions is subscribed to PCIe-link + * state changes of peer ports. + *=========================================================================== + */ + +static void idt_ntb_local_link_disable(struct idt_ntb_dev *ndev); + +/* + * idt_init_link() - Initialize NTB link state notification subsystem + * @ndev: IDT NTB hardware driver descriptor + * + * Function performs the basic initialization of some global registers + * needed to enable IRQ-based notifications of PCIe Link Up/Down and + * Global Signal events. + * NOTE Since it's not possible to determine when all the NTB peer drivers are + * unloaded as well as have those registers accessed concurrently, we must + * preinitialize them with the same value and leave it uncleared on local + * driver unload. + */ +static void idt_init_link(struct idt_ntb_dev *ndev) +{ + u32 part_mask, port_mask, se_mask; + unsigned char pidx; + + /* Initialize spin locker of Mapping Table access registers */ + spin_lock_init(&ndev->mtbl_lock); + + /* Walk over all detected peers collecting port and partition masks */ + port_mask = ~BIT(ndev->port); + part_mask = ~BIT(ndev->part); + for (pidx = 0; pidx < ndev->peer_cnt; pidx++) { + port_mask &= ~BIT(ndev->peers[pidx].port); + part_mask &= ~BIT(ndev->peers[pidx].part); + } + + /* Clean the Link Up/Down and GLobal Signal status registers */ + idt_sw_write(ndev, IDT_SW_SELINKUPSTS, (u32)-1); + idt_sw_write(ndev, IDT_SW_SELINKDNSTS, (u32)-1); + idt_sw_write(ndev, IDT_SW_SEGSIGSTS, (u32)-1); + + /* Unmask NT-activated partitions to receive Global Switch events */ + idt_sw_write(ndev, IDT_SW_SEPMSK, part_mask); + + /* Enable PCIe Link Up events of NT-activated ports */ + idt_sw_write(ndev, IDT_SW_SELINKUPMSK, port_mask); + + /* Enable PCIe Link Down events of NT-activated ports */ + idt_sw_write(ndev, IDT_SW_SELINKDNMSK, port_mask); + + /* Unmask NT-activated partitions to receive Global Signal events */ + idt_sw_write(ndev, IDT_SW_SEGSIGMSK, part_mask); + + /* Unmask Link Up/Down and Global Switch Events */ + se_mask = ~(IDT_SEMSK_LINKUP | IDT_SEMSK_LINKDN | IDT_SEMSK_GSIGNAL); + idt_sw_write(ndev, IDT_SW_SEMSK, se_mask); + + dev_dbg(&ndev->ntb.pdev->dev, "NTB link status events initialized"); +} + +/* + * idt_deinit_link() - deinitialize link subsystem + * @ndev: IDT NTB hardware driver descriptor + * + * Just disable the link back. + */ +static void idt_deinit_link(struct idt_ntb_dev *ndev) +{ + /* Disable the link */ + idt_ntb_local_link_disable(ndev); + + dev_dbg(&ndev->ntb.pdev->dev, "NTB link status events deinitialized"); +} + +/* + * idt_se_isr() - switch events ISR + * @ndev: IDT NTB hardware driver descriptor + * @ntint_sts: NT-function interrupt status + * + * This driver doesn't support IDT PCIe-switch dynamic reconfigurations, + * Failover capability, etc, so switch events are utilized to notify of + * PCIe and NTB link events. + * The method is called from PCIe ISR bottom-half routine. + */ +static void idt_se_isr(struct idt_ntb_dev *ndev, u32 ntint_sts) +{ + u32 sests; + + /* Read Switch Events status */ + sests = idt_sw_read(ndev, IDT_SW_SESTS); + + /* Clean the Link Up/Down and Global Signal status registers */ + idt_sw_write(ndev, IDT_SW_SELINKUPSTS, (u32)-1); + idt_sw_write(ndev, IDT_SW_SELINKDNSTS, (u32)-1); + idt_sw_write(ndev, IDT_SW_SEGSIGSTS, (u32)-1); + + /* Clean the corresponding interrupt bit */ + idt_nt_write(ndev, IDT_NT_NTINTSTS, IDT_NTINTSTS_SEVENT); + + dev_dbg(&ndev->ntb.pdev->dev, "SE IRQ detected %#08x (SESTS %#08x)", + ntint_sts, sests); + + /* Notify the client driver of possible link state change */ + ntb_link_event(&ndev->ntb); +} + +/* + * idt_ntb_local_link_enable() - enable the local NTB link. + * @ndev: IDT NTB hardware driver descriptor + * + * In order to enable the NTB link we need: + * - enable Completion TLPs translation + * - initialize mapping table to enable the Request ID translation + * - notify peers of NTB link state change + */ +static void idt_ntb_local_link_enable(struct idt_ntb_dev *ndev) +{ + u32 reqid, mtbldata = 0; + unsigned long irqflags; + + /* Enable the ID protection and Completion TLPs translation */ + idt_nt_write(ndev, IDT_NT_NTCTL, IDT_NTCTL_CPEN); + + /* Retrieve the current Requester ID (Bus:Device:Function) */ + reqid = idt_nt_read(ndev, IDT_NT_REQIDCAP); + + /* + * Set the corresponding NT Mapping table entry of port partition index + * with the data to perform the Request ID translation + */ + mtbldata = SET_FIELD(NTMTBLDATA_REQID, 0, reqid) | + SET_FIELD(NTMTBLDATA_PART, 0, ndev->part) | + IDT_NTMTBLDATA_VALID; + spin_lock_irqsave(&ndev->mtbl_lock, irqflags); + idt_nt_write(ndev, IDT_NT_NTMTBLADDR, ndev->part); + idt_nt_write(ndev, IDT_NT_NTMTBLDATA, mtbldata); + mmiowb(); + spin_unlock_irqrestore(&ndev->mtbl_lock, irqflags); + + /* Notify the peers by setting and clearing the global signal bit */ + idt_nt_write(ndev, IDT_NT_NTGSIGNAL, IDT_NTGSIGNAL_SET); + idt_sw_write(ndev, IDT_SW_SEGSIGSTS, (u32)1 << ndev->part); +} + +/* + * idt_ntb_local_link_disable() - disable the local NTB link. + * @ndev: IDT NTB hardware driver descriptor + * + * In order to enable the NTB link we need: + * - disable Completion TLPs translation + * - clear corresponding mapping table entry + * - notify peers of NTB link state change + */ +static void idt_ntb_local_link_disable(struct idt_ntb_dev *ndev) +{ + unsigned long irqflags; + + /* Disable Completion TLPs translation */ + idt_nt_write(ndev, IDT_NT_NTCTL, 0); + + /* Clear the corresponding NT Mapping table entry */ + spin_lock_irqsave(&ndev->mtbl_lock, irqflags); + idt_nt_write(ndev, IDT_NT_NTMTBLADDR, ndev->part); + idt_nt_write(ndev, IDT_NT_NTMTBLDATA, 0); + mmiowb(); + spin_unlock_irqrestore(&ndev->mtbl_lock, irqflags); + + /* Notify the peers by setting and clearing the global signal bit */ + idt_nt_write(ndev, IDT_NT_NTGSIGNAL, IDT_NTGSIGNAL_SET); + idt_sw_write(ndev, IDT_SW_SEGSIGSTS, (u32)1 << ndev->part); +} + +/* + * idt_ntb_local_link_is_up() - test wethter local NTB link is up + * @ndev: IDT NTB hardware driver descriptor + * + * Local link is up under the following conditions: + * - Bus mastering is enabled + * - NTCTL has Completion TLPs translation enabled + * - Mapping table permits Request TLPs translation + * NOTE: We don't need to check PCIe link state since it's obviously + * up while we are able to communicate with IDT PCIe-switch + * + * Return: true if link is up, otherwise false + */ +static bool idt_ntb_local_link_is_up(struct idt_ntb_dev *ndev) +{ + unsigned long irqflags; + u32 data; + + /* Read the local Bus Master Enable status */ + data = idt_nt_read(ndev, IDT_NT_PCICMDSTS); + if (!(data & IDT_PCICMDSTS_BME)) + return false; + + /* Read the local Completion TLPs translation enable status */ + data = idt_nt_read(ndev, IDT_NT_NTCTL); + if (!(data & IDT_NTCTL_CPEN)) + return false; + + /* Read Mapping table entry corresponding to the local partition */ + spin_lock_irqsave(&ndev->mtbl_lock, irqflags); + idt_nt_write(ndev, IDT_NT_NTMTBLADDR, ndev->part); + data = idt_nt_read(ndev, IDT_NT_NTMTBLDATA); + spin_unlock_irqrestore(&ndev->mtbl_lock, irqflags); + + return !!(data & IDT_NTMTBLDATA_VALID); +} + +/* + * idt_ntb_peer_link_is_up() - test whether peer NTB link is up + * @ndev: IDT NTB hardware driver descriptor + * @pidx: Peer port index + * + * Peer link is up under the following conditions: + * - PCIe link is up + * - Bus mastering is enabled + * - NTCTL has Completion TLPs translation enabled + * - Mapping table permits Request TLPs translation + * + * Return: true if link is up, otherwise false + */ +static bool idt_ntb_peer_link_is_up(struct idt_ntb_dev *ndev, int pidx) +{ + unsigned long irqflags; + unsigned char port; + u32 data; + + /* Retrieve the device port number */ + port = ndev->peers[pidx].port; + + /* Check whether PCIe link is up */ + data = idt_sw_read(ndev, portdata_tbl[port].sts); + if (!(data & IDT_SWPORTxSTS_LINKUP)) + return false; + + /* Check whether bus mastering is enabled on the peer port */ + data = idt_sw_read(ndev, portdata_tbl[port].pcicmdsts); + if (!(data & IDT_PCICMDSTS_BME)) + return false; + + /* Check if Completion TLPs translation is enabled on the peer port */ + data = idt_sw_read(ndev, portdata_tbl[port].ntctl); + if (!(data & IDT_NTCTL_CPEN)) + return false; + + /* Read Mapping table entry corresponding to the peer partition */ + spin_lock_irqsave(&ndev->mtbl_lock, irqflags); + idt_nt_write(ndev, IDT_NT_NTMTBLADDR, ndev->peers[pidx].part); + data = idt_nt_read(ndev, IDT_NT_NTMTBLDATA); + spin_unlock_irqrestore(&ndev->mtbl_lock, irqflags); + + return !!(data & IDT_NTMTBLDATA_VALID); +} + +/* + * idt_ntb_link_is_up() - get the current ntb link state (NTB API callback) + * @ntb: NTB device context. + * @speed: OUT - The link speed expressed as PCIe generation number. + * @width: OUT - The link width expressed as the number of PCIe lanes. + * + * Get the bitfield of NTB link states for all peer ports + * + * Return: bitfield of indexed ports link state: bit is set/cleared if the + * link is up/down respectively. + */ +static u64 idt_ntb_link_is_up(struct ntb_dev *ntb, + enum ntb_speed *speed, enum ntb_width *width) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + unsigned char pidx; + u64 status; + u32 data; + + /* Retrieve the local link speed and width */ + if (speed != NULL || width != NULL) { + data = idt_nt_read(ndev, IDT_NT_PCIELCTLSTS); + if (speed != NULL) + *speed = GET_FIELD(PCIELCTLSTS_CLS, data); + if (width != NULL) + *width = GET_FIELD(PCIELCTLSTS_NLW, data); + } + + /* If local NTB link isn't up then all the links are considered down */ + if (!idt_ntb_local_link_is_up(ndev)) + return 0; + + /* Collect all the peer ports link states into the bitfield */ + status = 0; + for (pidx = 0; pidx < ndev->peer_cnt; pidx++) { + if (idt_ntb_peer_link_is_up(ndev, pidx)) + status |= ((u64)1 << pidx); + } + + return status; +} + +/* + * idt_ntb_link_enable() - enable local port ntb link (NTB API callback) + * @ntb: NTB device context. + * @max_speed: The maximum link speed expressed as PCIe generation number. + * @max_width: The maximum link width expressed as the number of PCIe lanes. + * + * Enable just local NTB link. PCIe link parameters are ignored. + * + * Return: always zero. + */ +static int idt_ntb_link_enable(struct ntb_dev *ntb, enum ntb_speed speed, + enum ntb_width width) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + /* Just enable the local NTB link */ + idt_ntb_local_link_enable(ndev); + + dev_dbg(&ndev->ntb.pdev->dev, "Local NTB link enabled"); + + return 0; +} + +/* + * idt_ntb_link_disable() - disable local port ntb link (NTB API callback) + * @ntb: NTB device context. + * + * Disable just local NTB link. + * + * Return: always zero. + */ +static int idt_ntb_link_disable(struct ntb_dev *ntb) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + /* Just disable the local NTB link */ + idt_ntb_local_link_disable(ndev); + + dev_dbg(&ndev->ntb.pdev->dev, "Local NTB link disabled"); + + return 0; +} + +/*============================================================================= + * 4. Memory Window operations + * + * IDT PCIe-switches have two types of memory windows: MWs with direct + * address translation and MWs with LUT based translation. The first type of + * MWs is simple map of corresponding BAR address space to a memory space + * of specified target port. So it implemets just ont-to-one mapping. Lookup + * table in its turn can map one BAR address space to up to 24 different + * memory spaces of different ports. + * NT-functions BARs can be turned on to implement either direct or lookup + * table based address translations, so: + * BAR0 - NT configuration registers space/direct address translation + * BAR1 - direct address translation/upper address of BAR0x64 + * BAR2 - direct address translation/Lookup table with either 12 or 24 entries + * BAR3 - direct address translation/upper address of BAR2x64 + * BAR4 - direct address translation/Lookup table with either 12 or 24 entries + * BAR5 - direct address translation/upper address of BAR4x64 + * Additionally BAR2 and BAR4 can't have 24-entries LUT enabled at the same + * time. Since the BARs setup can be rather complicated this driver implements + * a scanning algorithm to have all the possible memory windows configuration + * covered. + * + * NOTE 1 BAR setup must be done before Linux kernel enumerated NT-function + * of any port, so this driver would have memory windows configurations fixed. + * In this way all initializations must be performed either by platform BIOS + * or using EEPROM connected to IDT PCIe-switch master SMBus. + * + * NOTE 2 This driver expects BAR0 mapping NT-function configuration space. + * Easy calculation can give us an upper boundary of 29 possible memory windows + * per each NT-function if all the BARs are of 32bit type. + *============================================================================= + */ + +/* + * idt_get_mw_count() - get memory window count + * @mw_type: Memory window type + * + * Return: number of memory windows with respect to the BAR type + */ +static inline unsigned char idt_get_mw_count(enum idt_mw_type mw_type) +{ + switch (mw_type) { + case IDT_MW_DIR: + return 1; + case IDT_MW_LUT12: + return 12; + case IDT_MW_LUT24: + return 24; + default: + break; + } + + return 0; +} + +/* + * idt_get_mw_name() - get memory window name + * @mw_type: Memory window type + * + * Return: pointer to a string with name + */ +static inline char *idt_get_mw_name(enum idt_mw_type mw_type) +{ + switch (mw_type) { + case IDT_MW_DIR: + return "DIR "; + case IDT_MW_LUT12: + return "LUT12"; + case IDT_MW_LUT24: + return "LUT24"; + default: + break; + } + + return "unknown"; +} + +/* + * idt_scan_mws() - scan memory windows of the port + * @ndev: IDT NTB hardware driver descriptor + * @port: Port to get number of memory windows for + * @mw_cnt: Out - number of memory windows + * + * It walks over BAR setup registers of the specified port and determines + * the memory windows parameters if any activated. + * + * Return: array of memory windows + */ +static struct idt_mw_cfg *idt_scan_mws(struct idt_ntb_dev *ndev, int port, + unsigned char *mw_cnt) +{ + struct idt_mw_cfg mws[IDT_MAX_NR_MWS], *ret_mws; + const struct idt_ntb_bar *bars; + enum idt_mw_type mw_type; + unsigned char widx, bidx, en_cnt; + bool bar_64bit = false; + int aprt_size; + u32 data; + + /* Retrieve the array of the BARs registers */ + bars = portdata_tbl[port].bars; + + /* Scan all the BARs belonging to the port */ + *mw_cnt = 0; + for (bidx = 0; bidx < IDT_BAR_CNT; bidx += 1 + bar_64bit) { + /* Read BARSETUP register value */ + data = idt_sw_read(ndev, bars[bidx].setup); + + /* Skip disabled BARs */ + if (!(data & IDT_BARSETUP_EN)) { + bar_64bit = false; + continue; + } + + /* Skip next BARSETUP if current one has 64bit addressing */ + bar_64bit = IS_FLD_SET(BARSETUP_TYPE, data, 64); + + /* Skip configuration space mapping BARs */ + if (data & IDT_BARSETUP_MODE_CFG) + continue; + + /* Retrieve MW type/entries count and aperture size */ + mw_type = GET_FIELD(BARSETUP_ATRAN, data); + en_cnt = idt_get_mw_count(mw_type); + aprt_size = (u64)1 << GET_FIELD(BARSETUP_SIZE, data); + + /* Save configurations of all available memory windows */ + for (widx = 0; widx < en_cnt; widx++, (*mw_cnt)++) { + /* + * IDT can expose a limited number of MWs, so it's bug + * to have more than the driver expects + */ + if (*mw_cnt >= IDT_MAX_NR_MWS) + return ERR_PTR(-EINVAL); + + /* Save basic MW info */ + mws[*mw_cnt].type = mw_type; + mws[*mw_cnt].bar = bidx; + mws[*mw_cnt].idx = widx; + /* It's always DWORD aligned */ + mws[*mw_cnt].addr_align = IDT_TRANS_ALIGN; + /* DIR and LUT approachs differently configure MWs */ + if (mw_type == IDT_MW_DIR) + mws[*mw_cnt].size_max = aprt_size; + else if (mw_type == IDT_MW_LUT12) + mws[*mw_cnt].size_max = aprt_size / 16; + else + mws[*mw_cnt].size_max = aprt_size / 32; + mws[*mw_cnt].size_align = (mw_type == IDT_MW_DIR) ? + IDT_DIR_SIZE_ALIGN : mws[*mw_cnt].size_max; + } + } + + /* Allocate memory for memory window descriptors */ + ret_mws = devm_kcalloc(&ndev->ntb.pdev->dev, *mw_cnt, + sizeof(*ret_mws), GFP_KERNEL); + if (IS_ERR_OR_NULL(ret_mws)) + return ERR_PTR(-ENOMEM); + + /* Copy the info of detected memory windows */ + memcpy(ret_mws, mws, (*mw_cnt)*sizeof(*ret_mws)); + + return ret_mws; +} + +/* + * idt_init_mws() - initialize memory windows subsystem + * @ndev: IDT NTB hardware driver descriptor + * + * Scan BAR setup registers of local and peer ports to determine the + * outbound and inbound memory windows parameters + * + * Return: zero on success, otherwise a negative error number + */ +static int idt_init_mws(struct idt_ntb_dev *ndev) +{ + struct idt_ntb_peer *peer; + unsigned char pidx; + + /* Scan memory windows of the local port */ + ndev->mws = idt_scan_mws(ndev, ndev->port, &ndev->mw_cnt); + if (IS_ERR(ndev->mws)) { + dev_err(&ndev->ntb.pdev->dev, + "Failed to scan mws of local port %hhu", ndev->port); + return PTR_ERR(ndev->mws); + } + + /* Scan memory windows of the peer ports */ + for (pidx = 0; pidx < ndev->peer_cnt; pidx++) { + peer = &ndev->peers[pidx]; + peer->mws = idt_scan_mws(ndev, peer->port, &peer->mw_cnt); + if (IS_ERR(peer->mws)) { + dev_err(&ndev->ntb.pdev->dev, + "Failed to scan mws of port %hhu", peer->port); + return PTR_ERR(peer->mws); + } + } + + /* Initialize spin locker of the LUT registers */ + spin_lock_init(&ndev->lut_lock); + + dev_dbg(&ndev->ntb.pdev->dev, "Outbound and inbound MWs initialized"); + + return 0; +} + +/* + * idt_ntb_mw_count() - number of inbound memory windows (NTB API callback) + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * + * The value is returned for the specified peer, so generally speaking it can + * be different for different port depending on the IDT PCIe-switch + * initialization. + * + * Return: the number of memory windows. + */ +static int idt_ntb_mw_count(struct ntb_dev *ntb, int pidx) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + if (pidx < 0 || ndev->peer_cnt <= pidx) + return -EINVAL; + + return ndev->peers[pidx].mw_cnt; +} + +/* + * idt_ntb_mw_get_align() - inbound memory window parameters (NTB API callback) + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * @widx: Memory window index. + * @addr_align: OUT - the base alignment for translating the memory window + * @size_align: OUT - the size alignment for translating the memory window + * @size_max: OUT - the maximum size of the memory window + * + * The peer memory window parameters have already been determined, so just + * return the corresponding values, which mustn't change within session. + * + * Return: Zero on success, otherwise a negative error number. + */ +static int idt_ntb_mw_get_align(struct ntb_dev *ntb, int pidx, int widx, + resource_size_t *addr_align, + resource_size_t *size_align, + resource_size_t *size_max) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + struct idt_ntb_peer *peer; + + if (pidx < 0 || ndev->peer_cnt <= pidx) + return -EINVAL; + + peer = &ndev->peers[pidx]; + + if (widx < 0 || peer->mw_cnt <= widx) + return -EINVAL; + + if (addr_align != NULL) + *addr_align = peer->mws[widx].addr_align; + + if (size_align != NULL) + *size_align = peer->mws[widx].size_align; + + if (size_max != NULL) + *size_max = peer->mws[widx].size_max; + + return 0; +} + +/* + * idt_ntb_peer_mw_count() - number of outbound memory windows + * (NTB API callback) + * @ntb: NTB device context. + * + * Outbound memory windows parameters have been determined based on the + * BAR setup registers value, which are mostly constants within one session. + * + * Return: the number of memory windows. + */ +static int idt_ntb_peer_mw_count(struct ntb_dev *ntb) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + return ndev->mw_cnt; +} + +/* + * idt_ntb_peer_mw_get_addr() - get map address of an outbound memory window + * (NTB API callback) + * @ntb: NTB device context. + * @widx: Memory window index (within ntb_peer_mw_count() return value). + * @base: OUT - the base address of mapping region. + * @size: OUT - the size of mapping region. + * + * Return just parameters of BAR resources mapping. Size reflects just the size + * of the resource + * + * Return: Zero on success, otherwise a negative error number. + */ +static int idt_ntb_peer_mw_get_addr(struct ntb_dev *ntb, int widx, + phys_addr_t *base, resource_size_t *size) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + if (widx < 0 || ndev->mw_cnt <= widx) + return -EINVAL; + + /* Mapping address is just properly shifted BAR resource start */ + if (base != NULL) + *base = pci_resource_start(ntb->pdev, ndev->mws[widx].bar) + + ndev->mws[widx].idx * ndev->mws[widx].size_max; + + /* Mapping size has already been calculated at MWs scanning */ + if (size != NULL) + *size = ndev->mws[widx].size_max; + + return 0; +} + +/* + * idt_ntb_peer_mw_set_trans() - set a translation address of a memory window + * (NTB API callback) + * @ntb: NTB device context. + * @pidx: Port index of peer device the translation address received from. + * @widx: Memory window index. + * @addr: The dma address of the shared memory to access. + * @size: The size of the shared memory to access. + * + * The Direct address translation and LUT base translation is initialized a + * bit differenet. Although the parameters restriction are now determined by + * the same code. + * + * Return: Zero on success, otherwise an error number. + */ +static int idt_ntb_peer_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx, + u64 addr, resource_size_t size) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + struct idt_mw_cfg *mw_cfg; + u32 data = 0, lutoff = 0; + + if (pidx < 0 || ndev->peer_cnt <= pidx) + return -EINVAL; + + if (widx < 0 || ndev->mw_cnt <= widx) + return -EINVAL; + + /* + * Retrieve the memory window config to make sure the passed arguments + * fit it restrictions + */ + mw_cfg = &ndev->mws[widx]; + if (!IS_ALIGNED(addr, mw_cfg->addr_align)) + return -EINVAL; + if (!IS_ALIGNED(size, mw_cfg->size_align) || size > mw_cfg->size_max) + return -EINVAL; + + /* DIR and LUT based translations are initialized differently */ + if (mw_cfg->type == IDT_MW_DIR) { + const struct idt_ntb_bar *bar = &ntdata_tbl.bars[mw_cfg->bar]; + u64 limit; + /* Set destination partition of translation */ + data = idt_nt_read(ndev, bar->setup); + data = SET_FIELD(BARSETUP_TPART, data, ndev->peers[pidx].part); + idt_nt_write(ndev, bar->setup, data); + /* Set translation base address */ + idt_nt_write(ndev, bar->ltbase, (u32)addr); + idt_nt_write(ndev, bar->utbase, (u32)(addr >> 32)); + /* Set the custom BAR aperture limit */ + limit = pci_resource_start(ntb->pdev, mw_cfg->bar) + size; + idt_nt_write(ndev, bar->limit, (u32)limit); + if (IS_FLD_SET(BARSETUP_TYPE, data, 64)) + idt_nt_write(ndev, (bar + 1)->limit, (limit >> 32)); + } else { + unsigned long irqflags; + /* Initialize corresponding LUT entry */ + lutoff = SET_FIELD(LUTOFFSET_INDEX, 0, mw_cfg->idx) | + SET_FIELD(LUTOFFSET_BAR, 0, mw_cfg->bar); + data = SET_FIELD(LUTUDATA_PART, 0, ndev->peers[pidx].part) | + IDT_LUTUDATA_VALID; + spin_lock_irqsave(&ndev->lut_lock, irqflags); + idt_nt_write(ndev, IDT_NT_LUTOFFSET, lutoff); + idt_nt_write(ndev, IDT_NT_LUTLDATA, (u32)addr); + idt_nt_write(ndev, IDT_NT_LUTMDATA, (u32)(addr >> 32)); + idt_nt_write(ndev, IDT_NT_LUTUDATA, data); + mmiowb(); + spin_unlock_irqrestore(&ndev->lut_lock, irqflags); + /* Limit address isn't specified since size is fixed for LUT */ + } + + return 0; +} + +/* + * idt_ntb_peer_mw_clear_trans() - clear the outbound MW translation address + * (NTB API callback) + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * @widx: Memory window index. + * + * It effectively disables the translation over the specified outbound MW. + * + * Return: Zero on success, otherwise an error number. + */ +static int idt_ntb_peer_mw_clear_trans(struct ntb_dev *ntb, int pidx, + int widx) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + struct idt_mw_cfg *mw_cfg; + + if (pidx < 0 || ndev->peer_cnt <= pidx) + return -EINVAL; + + if (widx < 0 || ndev->mw_cnt <= widx) + return -EINVAL; + + mw_cfg = &ndev->mws[widx]; + + /* DIR and LUT based translations are initialized differently */ + if (mw_cfg->type == IDT_MW_DIR) { + const struct idt_ntb_bar *bar = &ntdata_tbl.bars[mw_cfg->bar]; + u32 data; + /* Read BARSETUP to check BAR type */ + data = idt_nt_read(ndev, bar->setup); + /* Disable translation by specifying zero BAR limit */ + idt_nt_write(ndev, bar->limit, 0); + if (IS_FLD_SET(BARSETUP_TYPE, data, 64)) + idt_nt_write(ndev, (bar + 1)->limit, 0); + } else { + unsigned long irqflags; + u32 lutoff; + /* Clear the corresponding LUT entry up */ + lutoff = SET_FIELD(LUTOFFSET_INDEX, 0, mw_cfg->idx) | + SET_FIELD(LUTOFFSET_BAR, 0, mw_cfg->bar); + spin_lock_irqsave(&ndev->lut_lock, irqflags); + idt_nt_write(ndev, IDT_NT_LUTOFFSET, lutoff); + idt_nt_write(ndev, IDT_NT_LUTLDATA, 0); + idt_nt_write(ndev, IDT_NT_LUTMDATA, 0); + idt_nt_write(ndev, IDT_NT_LUTUDATA, 0); + mmiowb(); + spin_unlock_irqrestore(&ndev->lut_lock, irqflags); + } + + return 0; +} + +/*============================================================================= + * 5. Doorbell operations + * + * Doorbell functionality of IDT PCIe-switches is pretty unusual. First of + * all there is global doorbell register which state can by changed by any + * NT-function of the IDT device in accordance with global permissions. These + * permissions configs are not supported by NTB API, so it must be done by + * either BIOS or EEPROM settings. In the same way the state of the global + * doorbell is reflected to the NT-functions local inbound doorbell registers. + * It can lead to situations when client driver sets some peer doorbell bits + * and get them bounced back to local inbound doorbell if permissions are + * granted. + * Secondly there is just one IRQ vector for Doorbell, Message, Temperature + * and Switch events, so if client driver left any of Doorbell bits set and + * some other event occurred, the driver will be notified of Doorbell event + * again. + *============================================================================= + */ + +/* + * idt_db_isr() - doorbell event ISR + * @ndev: IDT NTB hardware driver descriptor + * @ntint_sts: NT-function interrupt status + * + * Doorbell event happans when DBELL bit of NTINTSTS switches from 0 to 1. + * It happens only when unmasked doorbell bits are set to ones on completely + * zeroed doorbell register. + * The method is called from PCIe ISR bottom-half routine. + */ +static void idt_db_isr(struct idt_ntb_dev *ndev, u32 ntint_sts) +{ + /* + * Doorbell IRQ status will be cleaned only when client + * driver unsets all the doorbell bits. + */ + dev_dbg(&ndev->ntb.pdev->dev, "DB IRQ detected %#08x", ntint_sts); + + /* Notify the client driver of possible doorbell state change */ + ntb_db_event(&ndev->ntb, 0); +} + +/* + * idt_ntb_db_valid_mask() - get a mask of doorbell bits supported by the ntb + * (NTB API callback) + * @ntb: NTB device context. + * + * IDT PCIe-switches expose just one Doorbell register of DWORD size. + * + * Return: A mask of doorbell bits supported by the ntb. + */ +static u64 idt_ntb_db_valid_mask(struct ntb_dev *ntb) +{ + return IDT_DBELL_MASK; +} + +/* + * idt_ntb_db_read() - read the local doorbell register (NTB API callback) + * @ntb: NTB device context. + * + * There is just on inbound doorbell register of each NT-function, so + * this method return it value. + * + * Return: The bits currently set in the local doorbell register. + */ +static u64 idt_ntb_db_read(struct ntb_dev *ntb) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + return idt_nt_read(ndev, IDT_NT_INDBELLSTS); +} + +/* + * idt_ntb_db_clear() - clear bits in the local doorbell register + * (NTB API callback) + * @ntb: NTB device context. + * @db_bits: Doorbell bits to clear. + * + * Clear bits of inbound doorbell register by writing ones to it. + * + * NOTE! Invalid bits are always considered cleared so it's not an error + * to clear them over. + * + * Return: always zero as success. + */ +static int idt_ntb_db_clear(struct ntb_dev *ntb, u64 db_bits) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + idt_nt_write(ndev, IDT_NT_INDBELLSTS, (u32)db_bits); + + return 0; +} + +/* + * idt_ntb_db_read_mask() - read the local doorbell mask (NTB API callback) + * @ntb: NTB device context. + * + * Each inbound doorbell bit can be masked from generating IRQ by setting + * the corresponding bit in inbound doorbell mask. So this method returns + * the value of the register. + * + * Return: The bits currently set in the local doorbell mask register. + */ +static u64 idt_ntb_db_read_mask(struct ntb_dev *ntb) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + return idt_nt_read(ndev, IDT_NT_INDBELLMSK); +} + +/* + * idt_ntb_db_set_mask() - set bits in the local doorbell mask + * (NTB API callback) + * @ntb: NTB device context. + * @db_bits: Doorbell mask bits to set. + * + * The inbound doorbell register mask value must be read, then OR'ed with + * passed field and only then set back. + * + * Return: zero on success, negative error if invalid argument passed. + */ +static int idt_ntb_db_set_mask(struct ntb_dev *ntb, u64 db_bits) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + return idt_reg_set_bits(ndev, IDT_NT_INDBELLMSK, &ndev->db_mask_lock, + IDT_DBELL_MASK, db_bits); +} + +/* + * idt_ntb_db_clear_mask() - clear bits in the local doorbell mask + * (NTB API callback) + * @ntb: NTB device context. + * @db_bits: Doorbell bits to clear. + * + * The method just clears the set bits up in accordance with the passed + * bitfield. IDT PCIe-switch shall generate an interrupt if there hasn't + * been any unmasked bit set before current unmasking. Otherwise IRQ won't + * be generated since there is only one IRQ vector for all doorbells. + * + * Return: always zero as success + */ +static int idt_ntb_db_clear_mask(struct ntb_dev *ntb, u64 db_bits) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + idt_reg_clear_bits(ndev, IDT_NT_INDBELLMSK, &ndev->db_mask_lock, + db_bits); + + return 0; +} + +/* + * idt_ntb_peer_db_set() - set bits in the peer doorbell register + * (NTB API callback) + * @ntb: NTB device context. + * @db_bits: Doorbell bits to set. + * + * IDT PCIe-switches exposes local outbound doorbell register to change peer + * inbound doorbell register state. + * + * Return: zero on success, negative error if invalid argument passed. + */ +static int idt_ntb_peer_db_set(struct ntb_dev *ntb, u64 db_bits) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + if (db_bits & ~(u64)IDT_DBELL_MASK) + return -EINVAL; + + idt_nt_write(ndev, IDT_NT_OUTDBELLSET, (u32)db_bits); + return 0; +} + +/*============================================================================= + * 6. Messaging operations + * + * Each NT-function of IDT PCIe-switch has four inbound and four outbound + * message registers. Each outbound message register can be connected to one or + * even more than one peer inbound message registers by setting global + * configurations. Since NTB API permits one-on-one message registers mapping + * only, the driver acts in according with that restriction. + *============================================================================= + */ + +/* + * idt_init_msg() - initialize messaging interface + * @ndev: IDT NTB hardware driver descriptor + * + * Just initialize the message registers routing tables locker. + */ +static void idt_init_msg(struct idt_ntb_dev *ndev) +{ + unsigned char midx; + + /* Init the messages routing table lockers */ + for (midx = 0; midx < IDT_MSG_CNT; midx++) + spin_lock_init(&ndev->msg_locks[midx]); + + dev_dbg(&ndev->ntb.pdev->dev, "NTB Messaging initialized"); +} + +/* + * idt_msg_isr() - message event ISR + * @ndev: IDT NTB hardware driver descriptor + * @ntint_sts: NT-function interrupt status + * + * Message event happens when MSG bit of NTINTSTS switches from 0 to 1. + * It happens only when unmasked message status bits are set to ones on + * completely zeroed message status register. + * The method is called from PCIe ISR bottom-half routine. + */ +static void idt_msg_isr(struct idt_ntb_dev *ndev, u32 ntint_sts) +{ + /* + * Message IRQ status will be cleaned only when client + * driver unsets all the message status bits. + */ + dev_dbg(&ndev->ntb.pdev->dev, "Message IRQ detected %#08x", ntint_sts); + + /* Notify the client driver of possible message status change */ + ntb_msg_event(&ndev->ntb); +} + +/* + * idt_ntb_msg_count() - get the number of message registers (NTB API callback) + * @ntb: NTB device context. + * + * IDT PCIe-switches support four message registers. + * + * Return: the number of message registers. + */ +static int idt_ntb_msg_count(struct ntb_dev *ntb) +{ + return IDT_MSG_CNT; +} + +/* + * idt_ntb_msg_inbits() - get a bitfield of inbound message registers status + * (NTB API callback) + * @ntb: NTB device context. + * + * NT message status register is shared between inbound and outbound message + * registers status + * + * Return: bitfield of inbound message registers. + */ +static u64 idt_ntb_msg_inbits(struct ntb_dev *ntb) +{ + return (u64)IDT_INMSG_MASK; +} + +/* + * idt_ntb_msg_outbits() - get a bitfield of outbound message registers status + * (NTB API callback) + * @ntb: NTB device context. + * + * NT message status register is shared between inbound and outbound message + * registers status + * + * Return: bitfield of outbound message registers. + */ +static u64 idt_ntb_msg_outbits(struct ntb_dev *ntb) +{ + return (u64)IDT_OUTMSG_MASK; +} + +/* + * idt_ntb_msg_read_sts() - read the message registers status (NTB API callback) + * @ntb: NTB device context. + * + * IDT PCIe-switches expose message status registers to notify drivers of + * incoming data and failures in case if peer message register isn't freed. + * + * Return: status bits of message registers + */ +static u64 idt_ntb_msg_read_sts(struct ntb_dev *ntb) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + return idt_nt_read(ndev, IDT_NT_MSGSTS); +} + +/* + * idt_ntb_msg_clear_sts() - clear status bits of message registers + * (NTB API callback) + * @ntb: NTB device context. + * @sts_bits: Status bits to clear. + * + * Clear bits in the status register by writing ones. + * + * NOTE! Invalid bits are always considered cleared so it's not an error + * to clear them over. + * + * Return: always zero as success. + */ +static int idt_ntb_msg_clear_sts(struct ntb_dev *ntb, u64 sts_bits) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + idt_nt_write(ndev, IDT_NT_MSGSTS, sts_bits); + + return 0; +} + +/* + * idt_ntb_msg_set_mask() - set mask of message register status bits + * (NTB API callback) + * @ntb: NTB device context. + * @mask_bits: Mask bits. + * + * Mask the message status bits from raising an IRQ. + * + * Return: zero on success, negative error if invalid argument passed. + */ +static int idt_ntb_msg_set_mask(struct ntb_dev *ntb, u64 mask_bits) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + return idt_reg_set_bits(ndev, IDT_NT_MSGSTSMSK, &ndev->msg_mask_lock, + IDT_MSG_MASK, mask_bits); +} + +/* + * idt_ntb_msg_clear_mask() - clear message registers mask + * (NTB API callback) + * @ntb: NTB device context. + * @mask_bits: Mask bits. + * + * Clear mask of message status bits IRQs. + * + * Return: always zero as success. + */ +static int idt_ntb_msg_clear_mask(struct ntb_dev *ntb, u64 mask_bits) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + idt_reg_clear_bits(ndev, IDT_NT_MSGSTSMSK, &ndev->msg_mask_lock, + mask_bits); + + return 0; +} + +/* + * idt_ntb_msg_read() - read message register with specified index + * (NTB API callback) + * @ntb: NTB device context. + * @midx: Message register index + * @pidx: OUT - Port index of peer device a message retrieved from + * @msg: OUT - Data + * + * Read data from the specified message register and source register. + * + * Return: zero on success, negative error if invalid argument passed. + */ +static int idt_ntb_msg_read(struct ntb_dev *ntb, int midx, int *pidx, u32 *msg) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + + if (midx < 0 || IDT_MSG_CNT <= midx) + return -EINVAL; + + /* Retrieve source port index of the message */ + if (pidx != NULL) { + u32 srcpart; + + srcpart = idt_nt_read(ndev, ntdata_tbl.msgs[midx].src); + *pidx = ndev->part_idx_map[srcpart]; + + /* Sanity check partition index (for initial case) */ + if (*pidx == -EINVAL) + *pidx = 0; + } + + /* Retrieve data of the corresponding message register */ + if (msg != NULL) + *msg = idt_nt_read(ndev, ntdata_tbl.msgs[midx].in); + + return 0; +} + +/* + * idt_ntb_msg_write() - write data to the specified message register + * (NTB API callback) + * @ntb: NTB device context. + * @midx: Message register index + * @pidx: Port index of peer device a message being sent to + * @msg: Data to send + * + * Just try to send data to a peer. Message status register should be + * checked by client driver. + * + * Return: zero on success, negative error if invalid argument passed. + */ +static int idt_ntb_msg_write(struct ntb_dev *ntb, int midx, int pidx, u32 msg) +{ + struct idt_ntb_dev *ndev = to_ndev_ntb(ntb); + unsigned long irqflags; + u32 swpmsgctl = 0; + + if (midx < 0 || IDT_MSG_CNT <= midx) + return -EINVAL; + + if (pidx < 0 || ndev->peer_cnt <= pidx) + return -EINVAL; + + /* Collect the routing information */ + swpmsgctl = SET_FIELD(SWPxMSGCTL_REG, 0, midx) | + SET_FIELD(SWPxMSGCTL_PART, 0, ndev->peers[pidx].part); + + /* Lock the messages routing table of the specified register */ + spin_lock_irqsave(&ndev->msg_locks[midx], irqflags); + /* Set the route and send the data */ + idt_sw_write(ndev, partdata_tbl[ndev->part].msgctl[midx], swpmsgctl); + idt_nt_write(ndev, ntdata_tbl.msgs[midx].out, msg); + mmiowb(); + /* Unlock the messages routing table */ + spin_unlock_irqrestore(&ndev->msg_locks[midx], irqflags); + + /* Client driver shall check the status register */ + return 0; +} + +/*============================================================================= + * 7. Temperature sensor operations + * + * IDT PCIe-switch has an embedded temperature sensor, which can be used to + * warn a user-space of possible chip overheating. Since workload temperature + * can be different on different platforms, temperature thresholds as well as + * general sensor settings must be setup in the framework of BIOS/EEPROM + * initializations. It includes the actual sensor enabling as well. + *============================================================================= + */ + +/* + * idt_read_temp() - read temperature from chip sensor + * @ntb: NTB device context. + * @val: OUT - integer value of temperature + * @frac: OUT - fraction + */ +static void idt_read_temp(struct idt_ntb_dev *ndev, unsigned char *val, + unsigned char *frac) +{ + u32 data; + + /* Read the data from TEMP field of the TMPSTS register */ + data = idt_sw_read(ndev, IDT_SW_TMPSTS); + data = GET_FIELD(TMPSTS_TEMP, data); + /* TEMP field has one fractional bit and seven integer bits */ + *val = data >> 1; + *frac = ((data & 0x1) ? 5 : 0); +} + +/* + * idt_temp_isr() - temperature sensor alarm events ISR + * @ndev: IDT NTB hardware driver descriptor + * @ntint_sts: NT-function interrupt status + * + * It handles events of temperature crossing alarm thresholds. Since reading + * of TMPALARM register clears it up, the function doesn't analyze the + * read value, instead the current temperature value just warningly printed to + * log. + * The method is called from PCIe ISR bottom-half routine. + */ +static void idt_temp_isr(struct idt_ntb_dev *ndev, u32 ntint_sts) +{ + unsigned char val, frac; + + /* Read the current temperature value */ + idt_read_temp(ndev, &val, &frac); + + /* Read the temperature alarm to clean the alarm status out */ + /*(void)idt_sw_read(ndev, IDT_SW_TMPALARM);*/ + + /* Clean the corresponding interrupt bit */ + idt_nt_write(ndev, IDT_NT_NTINTSTS, IDT_NTINTSTS_TMPSENSOR); + + dev_dbg(&ndev->ntb.pdev->dev, + "Temp sensor IRQ detected %#08x", ntint_sts); + + /* Print temperature value to log */ + dev_warn(&ndev->ntb.pdev->dev, "Temperature %hhu.%hhu", val, frac); +} + +/*============================================================================= + * 8. ISRs related operations + * + * IDT PCIe-switch has strangely developed IRQ system. There is just one + * interrupt vector for doorbell and message registers. So the hardware driver + * can't determine actual source of IRQ if, for example, message event happened + * while any of unmasked doorbell is still set. The similar situation may be if + * switch or temperature sensor events pop up. The difference is that SEVENT + * and TMPSENSOR bits of NT interrupt status register can be cleaned by + * IRQ handler so a next interrupt request won't have false handling of + * corresponding events. + * The hardware driver has only bottom-half handler of the IRQ, since if any + * of events happened the device won't raise it again before the last one is + * handled by clearing of corresponding NTINTSTS bit. + *============================================================================= + */ + +static irqreturn_t idt_thread_isr(int irq, void *devid); + +/* + * idt_init_isr() - initialize PCIe interrupt handler + * @ndev: IDT NTB hardware driver descriptor + * + * Return: zero on success, otherwise a negative error number. + */ +static int idt_init_isr(struct idt_ntb_dev *ndev) +{ + struct pci_dev *pdev = ndev->ntb.pdev; + u32 ntint_mask; + int ret; + + /* Allocate just one interrupt vector for the ISR */ + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI | PCI_IRQ_LEGACY); + if (ret != 1) { + dev_err(&pdev->dev, "Failed to allocate IRQ vector"); + return ret; + } + + /* Retrieve the IRQ vector */ + ret = pci_irq_vector(pdev, 0); + if (ret < 0) { + dev_err(&pdev->dev, "Failed to get IRQ vector"); + goto err_free_vectors; + } + + /* Set the IRQ handler */ + ret = devm_request_threaded_irq(&pdev->dev, ret, NULL, idt_thread_isr, + IRQF_ONESHOT, NTB_IRQNAME, ndev); + if (ret != 0) { + dev_err(&pdev->dev, "Failed to set MSI IRQ handler, %d", ret); + goto err_free_vectors; + } + + /* Unmask Message/Doorbell/SE/Temperature interrupts */ + ntint_mask = idt_nt_read(ndev, IDT_NT_NTINTMSK) & ~IDT_NTINTMSK_ALL; + idt_nt_write(ndev, IDT_NT_NTINTMSK, ntint_mask); + + /* From now on the interrupts are enabled */ + dev_dbg(&pdev->dev, "NTB interrupts initialized"); + + return 0; + +err_free_vectors: + pci_free_irq_vectors(pdev); + + return ret; +} + + +/* + * idt_deinit_ist() - deinitialize PCIe interrupt handler + * @ndev: IDT NTB hardware driver descriptor + * + * Disable corresponding interrupts and free allocated IRQ vectors. + */ +static void idt_deinit_isr(struct idt_ntb_dev *ndev) +{ + struct pci_dev *pdev = ndev->ntb.pdev; + u32 ntint_mask; + + /* Mask interrupts back */ + ntint_mask = idt_nt_read(ndev, IDT_NT_NTINTMSK) | IDT_NTINTMSK_ALL; + idt_nt_write(ndev, IDT_NT_NTINTMSK, ntint_mask); + + /* Manually free IRQ otherwise PCI free irq vectors will fail */ + devm_free_irq(&pdev->dev, pci_irq_vector(pdev, 0), ndev); + + /* Free allocated IRQ vectors */ + pci_free_irq_vectors(pdev); + + dev_dbg(&pdev->dev, "NTB interrupts deinitialized"); +} + +/* + * idt_thread_isr() - NT function interrupts handler + * @irq: IRQ number + * @devid: Custom buffer + * + * It reads current NT interrupts state register and handles all the event + * it declares. + * The method is bottom-half routine of actual default PCIe IRQ handler. + */ +static irqreturn_t idt_thread_isr(int irq, void *devid) +{ + struct idt_ntb_dev *ndev = devid; + bool handled = false; + u32 ntint_sts; + + /* Read the NT interrupts status register */ + ntint_sts = idt_nt_read(ndev, IDT_NT_NTINTSTS); + + /* Handle messaging interrupts */ + if (ntint_sts & IDT_NTINTSTS_MSG) { + idt_msg_isr(ndev, ntint_sts); + handled = true; + } + + /* Handle doorbell interrupts */ + if (ntint_sts & IDT_NTINTSTS_DBELL) { + idt_db_isr(ndev, ntint_sts); + handled = true; + } + + /* Handle switch event interrupts */ + if (ntint_sts & IDT_NTINTSTS_SEVENT) { + idt_se_isr(ndev, ntint_sts); + handled = true; + } + + /* Handle temperature sensor interrupt */ + if (ntint_sts & IDT_NTINTSTS_TMPSENSOR) { + idt_temp_isr(ndev, ntint_sts); + handled = true; + } + + dev_dbg(&ndev->ntb.pdev->dev, "IDT IRQs 0x%08x handled", ntint_sts); + + return handled ? IRQ_HANDLED : IRQ_NONE; +} + +/*=========================================================================== + * 9. NTB hardware driver initialization + *=========================================================================== + */ + +/* + * NTB API operations + */ +static const struct ntb_dev_ops idt_ntb_ops = { + .port_number = idt_ntb_port_number, + .peer_port_count = idt_ntb_peer_port_count, + .peer_port_number = idt_ntb_peer_port_number, + .peer_port_idx = idt_ntb_peer_port_idx, + .link_is_up = idt_ntb_link_is_up, + .link_enable = idt_ntb_link_enable, + .link_disable = idt_ntb_link_disable, + .mw_count = idt_ntb_mw_count, + .mw_get_align = idt_ntb_mw_get_align, + .peer_mw_count = idt_ntb_peer_mw_count, + .peer_mw_get_addr = idt_ntb_peer_mw_get_addr, + .peer_mw_set_trans = idt_ntb_peer_mw_set_trans, + .peer_mw_clear_trans = idt_ntb_peer_mw_clear_trans, + .db_valid_mask = idt_ntb_db_valid_mask, + .db_read = idt_ntb_db_read, + .db_clear = idt_ntb_db_clear, + .db_read_mask = idt_ntb_db_read_mask, + .db_set_mask = idt_ntb_db_set_mask, + .db_clear_mask = idt_ntb_db_clear_mask, + .peer_db_set = idt_ntb_peer_db_set, + .msg_count = idt_ntb_msg_count, + .msg_inbits = idt_ntb_msg_inbits, + .msg_outbits = idt_ntb_msg_outbits, + .msg_read_sts = idt_ntb_msg_read_sts, + .msg_clear_sts = idt_ntb_msg_clear_sts, + .msg_set_mask = idt_ntb_msg_set_mask, + .msg_clear_mask = idt_ntb_msg_clear_mask, + .msg_read = idt_ntb_msg_read, + .msg_write = idt_ntb_msg_write +}; + +/* + * idt_register_device() - register IDT NTB device + * @ndev: IDT NTB hardware driver descriptor + * + * Return: zero on success, otherwise a negative error number. + */ +static int idt_register_device(struct idt_ntb_dev *ndev) +{ + int ret; + + /* Initialize the rest of NTB device structure and register it */ + ndev->ntb.ops = &idt_ntb_ops; + ndev->ntb.topo = NTB_TOPO_PRI; + + ret = ntb_register_device(&ndev->ntb); + if (ret != 0) { + dev_err(&ndev->ntb.pdev->dev, "Failed to register NTB device"); + return ret; + } + + dev_dbg(&ndev->ntb.pdev->dev, "NTB device successfully registered"); + + return 0; +} + +/* + * idt_unregister_device() - unregister IDT NTB device + * @ndev: IDT NTB hardware driver descriptor + */ +static void idt_unregister_device(struct idt_ntb_dev *ndev) +{ + /* Just unregister the NTB device */ + ntb_unregister_device(&ndev->ntb); + + dev_dbg(&ndev->ntb.pdev->dev, "NTB device unregistered"); +} + +/*============================================================================= + * 10. DebugFS node initialization + *============================================================================= + */ + +static ssize_t idt_dbgfs_info_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *offp); + +/* + * Driver DebugFS info file operations + */ +static const struct file_operations idt_dbgfs_info_ops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = idt_dbgfs_info_read +}; + +/* + * idt_dbgfs_info_read() - DebugFS read info node callback + * @file: File node descriptor. + * @ubuf: User-space buffer to put data to + * @count: Size of the buffer + * @offp: Offset within the buffer + */ +static ssize_t idt_dbgfs_info_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *offp) +{ + struct idt_ntb_dev *ndev = filp->private_data; + unsigned char temp, frac, idx, pidx, cnt; + ssize_t ret = 0, off = 0; + unsigned long irqflags; + enum ntb_speed speed; + enum ntb_width width; + char *strbuf; + size_t size; + u32 data; + + /* Lets limit the buffer size the way the Intel/AMD drivers do */ + size = min_t(size_t, count, 0x1000U); + + /* Allocate the memory for the buffer */ + strbuf = kmalloc(size, GFP_KERNEL); + if (strbuf == NULL) + return -ENOMEM; + + /* Put the data into the string buffer */ + off += scnprintf(strbuf + off, size - off, + "\n\t\tIDT NTB device Information:\n\n"); + + /* General local device configurations */ + off += scnprintf(strbuf + off, size - off, + "Local Port %hhu, Partition %hhu\n", ndev->port, ndev->part); + + /* Peer ports information */ + off += scnprintf(strbuf + off, size - off, "Peers:\n"); + for (idx = 0; idx < ndev->peer_cnt; idx++) { + off += scnprintf(strbuf + off, size - off, + "\t%hhu. Port %hhu, Partition %hhu\n", + idx, ndev->peers[idx].port, ndev->peers[idx].part); + } + + /* Links status */ + data = idt_ntb_link_is_up(&ndev->ntb, &speed, &width); + off += scnprintf(strbuf + off, size - off, + "NTB link status\t- 0x%08x, ", data); + off += scnprintf(strbuf + off, size - off, "PCIe Gen %d x%d lanes\n", + speed, width); + + /* Mapping table entries */ + off += scnprintf(strbuf + off, size - off, "NTB Mapping Table:\n"); + for (idx = 0; idx < IDT_MTBL_ENTRY_CNT; idx++) { + spin_lock_irqsave(&ndev->mtbl_lock, irqflags); + idt_nt_write(ndev, IDT_NT_NTMTBLADDR, idx); + data = idt_nt_read(ndev, IDT_NT_NTMTBLDATA); + spin_unlock_irqrestore(&ndev->mtbl_lock, irqflags); + + /* Print valid entries only */ + if (data & IDT_NTMTBLDATA_VALID) { + off += scnprintf(strbuf + off, size - off, + "\t%hhu. Partition %d, Requester ID 0x%04x\n", + idx, GET_FIELD(NTMTBLDATA_PART, data), + GET_FIELD(NTMTBLDATA_REQID, data)); + } + } + off += scnprintf(strbuf + off, size - off, "\n"); + + /* Outbound memory windows information */ + off += scnprintf(strbuf + off, size - off, + "Outbound Memory Windows:\n"); + for (idx = 0; idx < ndev->mw_cnt; idx += cnt) { + data = ndev->mws[idx].type; + cnt = idt_get_mw_count(data); + + /* Print Memory Window information */ + if (data == IDT_MW_DIR) + off += scnprintf(strbuf + off, size - off, + "\t%hhu.\t", idx); + else + off += scnprintf(strbuf + off, size - off, + "\t%hhu-%hhu.\t", idx, idx + cnt - 1); + + off += scnprintf(strbuf + off, size - off, "%s BAR%hhu, ", + idt_get_mw_name(data), ndev->mws[idx].bar); + + off += scnprintf(strbuf + off, size - off, + "Address align 0x%08llx, ", ndev->mws[idx].addr_align); + + off += scnprintf(strbuf + off, size - off, + "Size align 0x%08llx, Size max %llu\n", + ndev->mws[idx].size_align, ndev->mws[idx].size_max); + } + + /* Inbound memory windows information */ + for (pidx = 0; pidx < ndev->peer_cnt; pidx++) { + off += scnprintf(strbuf + off, size - off, + "Inbound Memory Windows for peer %hhu (Port %hhu):\n", + pidx, ndev->peers[pidx].port); + + /* Print Memory Windows information */ + for (idx = 0; idx < ndev->peers[pidx].mw_cnt; idx += cnt) { + data = ndev->peers[pidx].mws[idx].type; + cnt = idt_get_mw_count(data); + + if (data == IDT_MW_DIR) + off += scnprintf(strbuf + off, size - off, + "\t%hhu.\t", idx); + else + off += scnprintf(strbuf + off, size - off, + "\t%hhu-%hhu.\t", idx, idx + cnt - 1); + + off += scnprintf(strbuf + off, size - off, + "%s BAR%hhu, ", idt_get_mw_name(data), + ndev->peers[pidx].mws[idx].bar); + + off += scnprintf(strbuf + off, size - off, + "Address align 0x%08llx, ", + ndev->peers[pidx].mws[idx].addr_align); + + off += scnprintf(strbuf + off, size - off, + "Size align 0x%08llx, Size max %llu\n", + ndev->peers[pidx].mws[idx].size_align, + ndev->peers[pidx].mws[idx].size_max); + } + } + off += scnprintf(strbuf + off, size - off, "\n"); + + /* Doorbell information */ + data = idt_sw_read(ndev, IDT_SW_GDBELLSTS); + off += scnprintf(strbuf + off, size - off, + "Global Doorbell state\t- 0x%08x\n", data); + data = idt_ntb_db_read(&ndev->ntb); + off += scnprintf(strbuf + off, size - off, + "Local Doorbell state\t- 0x%08x\n", data); + data = idt_nt_read(ndev, IDT_NT_INDBELLMSK); + off += scnprintf(strbuf + off, size - off, + "Local Doorbell mask\t- 0x%08x\n", data); + off += scnprintf(strbuf + off, size - off, "\n"); + + /* Messaging information */ + off += scnprintf(strbuf + off, size - off, + "Message event valid\t- 0x%08x\n", IDT_MSG_MASK); + data = idt_ntb_msg_read_sts(&ndev->ntb); + off += scnprintf(strbuf + off, size - off, + "Message event status\t- 0x%08x\n", data); + data = idt_nt_read(ndev, IDT_NT_MSGSTSMSK); + off += scnprintf(strbuf + off, size - off, + "Message event mask\t- 0x%08x\n", data); + off += scnprintf(strbuf + off, size - off, + "Message data:\n"); + for (idx = 0; idx < IDT_MSG_CNT; idx++) { + int src; + (void)idt_ntb_msg_read(&ndev->ntb, idx, &src, &data); + off += scnprintf(strbuf + off, size - off, + "\t%hhu. 0x%08x from peer %hhu (Port %hhu)\n", + idx, data, src, ndev->peers[src].port); + } + off += scnprintf(strbuf + off, size - off, "\n"); + + /* Current temperature */ + idt_read_temp(ndev, &temp, &frac); + off += scnprintf(strbuf + off, size - off, + "Switch temperature\t\t- %hhu.%hhuC\n", temp, frac); + + /* Copy the buffer to the User Space */ + ret = simple_read_from_buffer(ubuf, count, offp, strbuf, off); + kfree(strbuf); + + return ret; +} + +/* + * idt_init_dbgfs() - initialize DebugFS node + * @ndev: IDT NTB hardware driver descriptor + * + * Return: zero on success, otherwise a negative error number. + */ +static int idt_init_dbgfs(struct idt_ntb_dev *ndev) +{ + char devname[64]; + + /* If the top directory is not created then do nothing */ + if (IS_ERR_OR_NULL(dbgfs_topdir)) { + dev_info(&ndev->ntb.pdev->dev, "Top DebugFS directory absent"); + return PTR_ERR(dbgfs_topdir); + } + + /* Create the info file node */ + snprintf(devname, 64, "info:%s", pci_name(ndev->ntb.pdev)); + ndev->dbgfs_info = debugfs_create_file(devname, 0400, dbgfs_topdir, + ndev, &idt_dbgfs_info_ops); + if (IS_ERR(ndev->dbgfs_info)) { + dev_dbg(&ndev->ntb.pdev->dev, "Failed to create DebugFS node"); + return PTR_ERR(ndev->dbgfs_info); + } + + dev_dbg(&ndev->ntb.pdev->dev, "NTB device DebugFS node created"); + + return 0; +} + +/* + * idt_deinit_dbgfs() - deinitialize DebugFS node + * @ndev: IDT NTB hardware driver descriptor + * + * Just discard the info node from DebugFS + */ +static void idt_deinit_dbgfs(struct idt_ntb_dev *ndev) +{ + debugfs_remove(ndev->dbgfs_info); + + dev_dbg(&ndev->ntb.pdev->dev, "NTB device DebugFS node discarded"); +} + +/*============================================================================= + * 11. Basic PCIe device initialization + *============================================================================= + */ + +/* + * idt_check_setup() - Check whether the IDT PCIe-swtich is properly + * pre-initialized + * @pdev: Pointer to the PCI device descriptor + * + * Return: zero on success, otherwise a negative error number. + */ +static int idt_check_setup(struct pci_dev *pdev) +{ + u32 data; + int ret; + + /* Read the BARSETUP0 */ + ret = pci_read_config_dword(pdev, IDT_NT_BARSETUP0, &data); + if (ret != 0) { + dev_err(&pdev->dev, + "Failed to read BARSETUP0 config register"); + return ret; + } + + /* Check whether the BAR0 register is enabled to be of config space */ + if (!(data & IDT_BARSETUP_EN) || !(data & IDT_BARSETUP_MODE_CFG)) { + dev_err(&pdev->dev, "BAR0 doesn't map config space"); + return -EINVAL; + } + + /* Configuration space BAR0 must have certain size */ + if ((data & IDT_BARSETUP_SIZE_MASK) != IDT_BARSETUP_SIZE_CFG) { + dev_err(&pdev->dev, "Invalid size of config space"); + return -EINVAL; + } + + dev_dbg(&pdev->dev, "NTB device pre-initialized correctly"); + + return 0; +} + +/* + * Create the IDT PCIe-switch driver descriptor + * @pdev: Pointer to the PCI device descriptor + * @id: IDT PCIe-device configuration + * + * It just allocates a memory for IDT PCIe-switch device structure and + * initializes some commonly used fields. + * + * No need of release method, since managed device resource is used for + * memory allocation. + * + * Return: pointer to the descriptor, otherwise a negative error number. + */ +static struct idt_ntb_dev *idt_create_dev(struct pci_dev *pdev, + const struct pci_device_id *id) +{ + struct idt_ntb_dev *ndev; + + /* Allocate memory for the IDT PCIe-device descriptor */ + ndev = devm_kzalloc(&pdev->dev, sizeof(*ndev), GFP_KERNEL); + if (IS_ERR_OR_NULL(ndev)) { + dev_err(&pdev->dev, "Memory allocation failed for descriptor"); + return ERR_PTR(-ENOMEM); + } + + /* Save the IDT PCIe-switch ports configuration */ + ndev->swcfg = (struct idt_89hpes_cfg *)id->driver_data; + /* Save the PCI-device pointer inside the NTB device structure */ + ndev->ntb.pdev = pdev; + + /* Initialize spin locker of Doorbell, Message and GASA registers */ + spin_lock_init(&ndev->db_mask_lock); + spin_lock_init(&ndev->msg_mask_lock); + spin_lock_init(&ndev->gasa_lock); + + dev_info(&pdev->dev, "IDT %s discovered", ndev->swcfg->name); + + dev_dbg(&pdev->dev, "NTB device descriptor created"); + + return ndev; +} + +/* + * idt_init_pci() - initialize the basic PCI-related subsystem + * @ndev: Pointer to the IDT PCIe-switch driver descriptor + * + * Managed device resources will be freed automatically in case of failure or + * driver detachment. + * + * Return: zero on success, otherwise negative error number. + */ +static int idt_init_pci(struct idt_ntb_dev *ndev) +{ + struct pci_dev *pdev = ndev->ntb.pdev; + int ret; + + /* Initialize the bit mask of DMA */ + ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); + if (ret != 0) { + ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + if (ret != 0) { + dev_err(&pdev->dev, "Failed to set DMA bit mask\n"); + return ret; + } + dev_warn(&pdev->dev, "Cannot set DMA highmem bit mask\n"); + } + ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); + if (ret != 0) { + ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); + if (ret != 0) { + dev_err(&pdev->dev, + "Failed to set consistent DMA bit mask\n"); + return ret; + } + dev_warn(&pdev->dev, + "Cannot set consistent DMA highmem bit mask\n"); + } + + /* + * Enable the device advanced error reporting. It's not critical to + * have AER disabled in the kernel. + */ + ret = pci_enable_pcie_error_reporting(pdev); + if (ret != 0) + dev_warn(&pdev->dev, "PCIe AER capability disabled\n"); + else /* Cleanup uncorrectable error status before getting to init */ + pci_cleanup_aer_uncorrect_error_status(pdev); + + /* First enable the PCI device */ + ret = pcim_enable_device(pdev); + if (ret != 0) { + dev_err(&pdev->dev, "Failed to enable PCIe device\n"); + goto err_disable_aer; + } + + /* + * Enable the bus mastering, which effectively enables MSI IRQs and + * Request TLPs translation + */ + pci_set_master(pdev); + + /* Request all BARs resources and map BAR0 only */ + ret = pcim_iomap_regions_request_all(pdev, 1, NTB_NAME); + if (ret != 0) { + dev_err(&pdev->dev, "Failed to request resources\n"); + goto err_clear_master; + } + + /* Retrieve virtual address of BAR0 - PCI configuration space */ + ndev->cfgspc = pcim_iomap_table(pdev)[0]; + + /* Put the IDT driver data pointer to the PCI-device private pointer */ + pci_set_drvdata(pdev, ndev); + + dev_dbg(&pdev->dev, "NT-function PCIe interface initialized"); + + return 0; + +err_clear_master: + pci_clear_master(pdev); +err_disable_aer: + (void)pci_disable_pcie_error_reporting(pdev); + + return ret; +} + +/* + * idt_deinit_pci() - deinitialize the basic PCI-related subsystem + * @ndev: Pointer to the IDT PCIe-switch driver descriptor + * + * Managed resources will be freed on the driver detachment + */ +static void idt_deinit_pci(struct idt_ntb_dev *ndev) +{ + struct pci_dev *pdev = ndev->ntb.pdev; + + /* Clean up the PCI-device private data pointer */ + pci_set_drvdata(pdev, NULL); + + /* Clear the bus master disabling the Request TLPs translation */ + pci_clear_master(pdev); + + /* Disable the AER capability */ + (void)pci_disable_pcie_error_reporting(pdev); + + dev_dbg(&pdev->dev, "NT-function PCIe interface cleared"); +} + +/*=========================================================================== + * 12. PCI bus callback functions + *=========================================================================== + */ + +/* + * idt_pci_probe() - PCI device probe callback + * @pdev: Pointer to PCI device structure + * @id: PCIe device custom descriptor + * + * Return: zero on success, otherwise negative error number + */ +static int idt_pci_probe(struct pci_dev *pdev, + const struct pci_device_id *id) +{ + struct idt_ntb_dev *ndev; + int ret; + + /* Check whether IDT PCIe-switch is properly pre-initialized */ + ret = idt_check_setup(pdev); + if (ret != 0) + return ret; + + /* Allocate the memory for IDT NTB device data */ + ndev = idt_create_dev(pdev, id); + if (IS_ERR_OR_NULL(ndev)) + return PTR_ERR(ndev); + + /* Initialize the basic PCI subsystem of the device */ + ret = idt_init_pci(ndev); + if (ret != 0) + return ret; + + /* Scan ports of the IDT PCIe-switch */ + (void)idt_scan_ports(ndev); + + /* Initialize NTB link events subsystem */ + idt_init_link(ndev); + + /* Initialize MWs subsystem */ + ret = idt_init_mws(ndev); + if (ret != 0) + goto err_deinit_link; + + /* Initialize Messaging subsystem */ + idt_init_msg(ndev); + + /* Initialize IDT interrupts handler */ + ret = idt_init_isr(ndev); + if (ret != 0) + goto err_deinit_link; + + /* Register IDT NTB devices on the NTB bus */ + ret = idt_register_device(ndev); + if (ret != 0) + goto err_deinit_isr; + + /* Initialize DebugFS info node */ + (void)idt_init_dbgfs(ndev); + + /* IDT PCIe-switch NTB driver is finally initialized */ + dev_info(&pdev->dev, "IDT NTB device is ready"); + + /* May the force be with us... */ + return 0; + +err_deinit_isr: + idt_deinit_isr(ndev); +err_deinit_link: + idt_deinit_link(ndev); + idt_deinit_pci(ndev); + + return ret; +} + +/* + * idt_pci_probe() - PCI device remove callback + * @pdev: Pointer to PCI device structure + */ +static void idt_pci_remove(struct pci_dev *pdev) +{ + struct idt_ntb_dev *ndev = pci_get_drvdata(pdev); + + /* Deinit the DebugFS node */ + idt_deinit_dbgfs(ndev); + + /* Unregister NTB device */ + idt_unregister_device(ndev); + + /* Stop the interrupts handling */ + idt_deinit_isr(ndev); + + /* Deinitialize link event subsystem */ + idt_deinit_link(ndev); + + /* Deinit basic PCI subsystem */ + idt_deinit_pci(ndev); + + /* IDT PCIe-switch NTB driver is finally initialized */ + dev_info(&pdev->dev, "IDT NTB device is removed"); + + /* Sayonara... */ +} + +/* + * IDT PCIe-switch models ports configuration structures + */ +static struct idt_89hpes_cfg idt_89hpes24nt6ag2_config = { + .name = "89HPES24NT6AG2", + .port_cnt = 6, .ports = {0, 2, 4, 6, 8, 12} +}; +static struct idt_89hpes_cfg idt_89hpes32nt8ag2_config = { + .name = "89HPES32NT8AG2", + .port_cnt = 8, .ports = {0, 2, 4, 6, 8, 12, 16, 20} +}; +static struct idt_89hpes_cfg idt_89hpes32nt8bg2_config = { + .name = "89HPES32NT8BG2", + .port_cnt = 8, .ports = {0, 2, 4, 6, 8, 12, 16, 20} +}; +static struct idt_89hpes_cfg idt_89hpes12nt12g2_config = { + .name = "89HPES12NT12G2", + .port_cnt = 3, .ports = {0, 8, 16} +}; +static struct idt_89hpes_cfg idt_89hpes16nt16g2_config = { + .name = "89HPES16NT16G2", + .port_cnt = 4, .ports = {0, 8, 12, 16} +}; +static struct idt_89hpes_cfg idt_89hpes24nt24g2_config = { + .name = "89HPES24NT24G2", + .port_cnt = 8, .ports = {0, 2, 4, 6, 8, 12, 16, 20} +}; +static struct idt_89hpes_cfg idt_89hpes32nt24ag2_config = { + .name = "89HPES32NT24AG2", + .port_cnt = 8, .ports = {0, 2, 4, 6, 8, 12, 16, 20} +}; +static struct idt_89hpes_cfg idt_89hpes32nt24bg2_config = { + .name = "89HPES32NT24BG2", + .port_cnt = 8, .ports = {0, 2, 4, 6, 8, 12, 16, 20} +}; + +/* + * PCI-ids table of the supported IDT PCIe-switch devices + */ +static const struct pci_device_id idt_pci_tbl[] = { + {IDT_PCI_DEVICE_IDS(89HPES24NT6AG2, idt_89hpes24nt6ag2_config)}, + {IDT_PCI_DEVICE_IDS(89HPES32NT8AG2, idt_89hpes32nt8ag2_config)}, + {IDT_PCI_DEVICE_IDS(89HPES32NT8BG2, idt_89hpes32nt8bg2_config)}, + {IDT_PCI_DEVICE_IDS(89HPES12NT12G2, idt_89hpes12nt12g2_config)}, + {IDT_PCI_DEVICE_IDS(89HPES16NT16G2, idt_89hpes16nt16g2_config)}, + {IDT_PCI_DEVICE_IDS(89HPES24NT24G2, idt_89hpes24nt24g2_config)}, + {IDT_PCI_DEVICE_IDS(89HPES32NT24AG2, idt_89hpes32nt24ag2_config)}, + {IDT_PCI_DEVICE_IDS(89HPES32NT24BG2, idt_89hpes32nt24bg2_config)}, + {0} +}; +MODULE_DEVICE_TABLE(pci, idt_pci_tbl); + +/* + * IDT PCIe-switch NT-function device driver structure definition + */ +static struct pci_driver idt_pci_driver = { + .name = KBUILD_MODNAME, + .probe = idt_pci_probe, + .remove = idt_pci_remove, + .id_table = idt_pci_tbl, +}; + +static int __init idt_pci_driver_init(void) +{ + pr_info("%s %s\n", NTB_DESC, NTB_VER); + + /* Create the top DebugFS directory if the FS is initialized */ + if (debugfs_initialized()) + dbgfs_topdir = debugfs_create_dir(KBUILD_MODNAME, NULL); + + /* Register the NTB hardware driver to handle the PCI device */ + return pci_register_driver(&idt_pci_driver); +} +module_init(idt_pci_driver_init); + +static void __exit idt_pci_driver_exit(void) +{ + /* Unregister the NTB hardware driver */ + pci_unregister_driver(&idt_pci_driver); + + /* Discard the top DebugFS directory */ + debugfs_remove_recursive(dbgfs_topdir); +} +module_exit(idt_pci_driver_exit); + diff --git a/drivers/ntb/hw/idt/ntb_hw_idt.h b/drivers/ntb/hw/idt/ntb_hw_idt.h new file mode 100644 index 000000000000..856fd182f6f4 --- /dev/null +++ b/drivers/ntb/hw/idt/ntb_hw_idt.h @@ -0,0 +1,1149 @@ +/* + * This file is provided under a GPLv2 license. When using or + * redistributing this file, you may do so under that license. + * + * GPL LICENSE SUMMARY + * + * Copyright (C) 2016 T-Platforms All Rights Reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General + * Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, one can be found http://www.gnu.org/licenses/. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + * IDT PCIe-switch NTB Linux driver + * + * Contact Information: + * Serge Semin , + */ + +#ifndef NTB_HW_IDT_H +#define NTB_HW_IDT_H + +#include +#include +#include +#include +#include +#include + + +/* + * Macro is used to create the struct pci_device_id that matches + * the supported IDT PCIe-switches + * @devname: Capitalized name of the particular device + * @data: Variable passed to the driver of the particular device + */ +#define IDT_PCI_DEVICE_IDS(devname, data) \ + .vendor = PCI_VENDOR_ID_IDT, .device = PCI_DEVICE_ID_IDT_##devname, \ + .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, \ + .class = (PCI_CLASS_BRIDGE_OTHER << 8), .class_mask = (0xFFFF00), \ + .driver_data = (kernel_ulong_t)&data + +/* + * IDT PCIe-switches device IDs + */ +#define PCI_DEVICE_ID_IDT_89HPES24NT6AG2 0x8091 +#define PCI_DEVICE_ID_IDT_89HPES32NT8AG2 0x808F +#define PCI_DEVICE_ID_IDT_89HPES32NT8BG2 0x8088 +#define PCI_DEVICE_ID_IDT_89HPES12NT12G2 0x8092 +#define PCI_DEVICE_ID_IDT_89HPES16NT16G2 0x8090 +#define PCI_DEVICE_ID_IDT_89HPES24NT24G2 0x808E +#define PCI_DEVICE_ID_IDT_89HPES32NT24AG2 0x808C +#define PCI_DEVICE_ID_IDT_89HPES32NT24BG2 0x808A + +/* + * NT-function Configuration Space registers + * NOTE 1) The IDT PCIe-switch internal data is little-endian + * so it must be taken into account in the driver + * internals. + * 2) Additionally the registers should be accessed either + * with byte-enables corresponding to their native size or + * the size of one DWORD + * + * So to simplify the driver code, there is only DWORD-sized read/write + * operations utilized. + */ +/* PCI Express Configuration Space */ +/* PCI Express command/status register (DWORD) */ +#define IDT_NT_PCICMDSTS 0x00004U +/* PCI Express Device Capabilities (DWORD) */ +#define IDT_NT_PCIEDCAP 0x00044U +/* PCI Express Device Control/Status (WORD+WORD) */ +#define IDT_NT_PCIEDCTLSTS 0x00048U +/* PCI Express Link Capabilities (DWORD) */ +#define IDT_NT_PCIELCAP 0x0004CU +/* PCI Express Link Control/Status (WORD+WORD) */ +#define IDT_NT_PCIELCTLSTS 0x00050U +/* PCI Express Device Capabilities 2 (DWORD) */ +#define IDT_NT_PCIEDCAP2 0x00064U +/* PCI Express Device Control 2 (WORD+WORD) */ +#define IDT_NT_PCIEDCTL2 0x00068U +/* PCI Power Management Control and Status (DWORD) */ +#define IDT_NT_PMCSR 0x000C4U +/*==========================================*/ +/* IDT Proprietary NT-port-specific registers */ +/* NT-function main control registers */ +/* NT Endpoint Control (DWORD) */ +#define IDT_NT_NTCTL 0x00400U +/* NT Endpoint Interrupt Status/Mask (DWORD) */ +#define IDT_NT_NTINTSTS 0x00404U +#define IDT_NT_NTINTMSK 0x00408U +/* NT Endpoint Signal Data (DWORD) */ +#define IDT_NT_NTSDATA 0x0040CU +/* NT Endpoint Global Signal (DWORD) */ +#define IDT_NT_NTGSIGNAL 0x00410U +/* Internal Error Reporting Mask 0/1 (DWORD) */ +#define IDT_NT_NTIERRORMSK0 0x00414U +#define IDT_NT_NTIERRORMSK1 0x00418U +/* Doorbel registers */ +/* NT Outbound Doorbell Set (DWORD) */ +#define IDT_NT_OUTDBELLSET 0x00420U +/* NT Inbound Doorbell Status/Mask (DWORD) */ +#define IDT_NT_INDBELLSTS 0x00428U +#define IDT_NT_INDBELLMSK 0x0042CU +/* Message registers */ +/* Outbound Message N (DWORD) */ +#define IDT_NT_OUTMSG0 0x00430U +#define IDT_NT_OUTMSG1 0x00434U +#define IDT_NT_OUTMSG2 0x00438U +#define IDT_NT_OUTMSG3 0x0043CU +/* Inbound Message N (DWORD) */ +#define IDT_NT_INMSG0 0x00440U +#define IDT_NT_INMSG1 0x00444U +#define IDT_NT_INMSG2 0x00448U +#define IDT_NT_INMSG3 0x0044CU +/* Inbound Message Source N (DWORD) */ +#define IDT_NT_INMSGSRC0 0x00450U +#define IDT_NT_INMSGSRC1 0x00454U +#define IDT_NT_INMSGSRC2 0x00458U +#define IDT_NT_INMSGSRC3 0x0045CU +/* Message Status (DWORD) */ +#define IDT_NT_MSGSTS 0x00460U +/* Message Status Mask (DWORD) */ +#define IDT_NT_MSGSTSMSK 0x00464U +/* BAR-setup registers */ +/* BAR N Setup/Limit Address/Lower and Upper Translated Base Address (DWORD) */ +#define IDT_NT_BARSETUP0 0x00470U +#define IDT_NT_BARLIMIT0 0x00474U +#define IDT_NT_BARLTBASE0 0x00478U +#define IDT_NT_BARUTBASE0 0x0047CU +#define IDT_NT_BARSETUP1 0x00480U +#define IDT_NT_BARLIMIT1 0x00484U +#define IDT_NT_BARLTBASE1 0x00488U +#define IDT_NT_BARUTBASE1 0x0048CU +#define IDT_NT_BARSETUP2 0x00490U +#define IDT_NT_BARLIMIT2 0x00494U +#define IDT_NT_BARLTBASE2 0x00498U +#define IDT_NT_BARUTBASE2 0x0049CU +#define IDT_NT_BARSETUP3 0x004A0U +#define IDT_NT_BARLIMIT3 0x004A4U +#define IDT_NT_BARLTBASE3 0x004A8U +#define IDT_NT_BARUTBASE3 0x004ACU +#define IDT_NT_BARSETUP4 0x004B0U +#define IDT_NT_BARLIMIT4 0x004B4U +#define IDT_NT_BARLTBASE4 0x004B8U +#define IDT_NT_BARUTBASE4 0x004BCU +#define IDT_NT_BARSETUP5 0x004C0U +#define IDT_NT_BARLIMIT5 0x004C4U +#define IDT_NT_BARLTBASE5 0x004C8U +#define IDT_NT_BARUTBASE5 0x004CCU +/* NT mapping table registers */ +/* NT Mapping Table Address/Status/Data (DWORD) */ +#define IDT_NT_NTMTBLADDR 0x004D0U +#define IDT_NT_NTMTBLSTS 0x004D4U +#define IDT_NT_NTMTBLDATA 0x004D8U +/* Requester ID (Bus:Device:Function) Capture (DWORD) */ +#define IDT_NT_REQIDCAP 0x004DCU +/* Memory Windows Lookup table registers */ +/* Lookup Table Offset/Lower, Middle and Upper data (DWORD) */ +#define IDT_NT_LUTOFFSET 0x004E0U +#define IDT_NT_LUTLDATA 0x004E4U +#define IDT_NT_LUTMDATA 0x004E8U +#define IDT_NT_LUTUDATA 0x004ECU +/* NT Endpoint Uncorrectable/Correctable Errors Emulation registers (DWORD) */ +#define IDT_NT_NTUEEM 0x004F0U +#define IDT_NT_NTCEEM 0x004F4U +/* Global Address Space Access/Data registers (DWARD) */ +#define IDT_NT_GASAADDR 0x00FF8U +#define IDT_NT_GASADATA 0x00FFCU + +/* + * IDT PCIe-switch Global Configuration and Status registers + */ +/* Port N Configuration register in global space */ +/* PCI Express command/status and link control/status registers (WORD+WORD) */ +#define IDT_SW_NTP0_PCIECMDSTS 0x01004U +#define IDT_SW_NTP0_PCIELCTLSTS 0x01050U +/* NT-function control register (DWORD) */ +#define IDT_SW_NTP0_NTCTL 0x01400U +/* BAR setup/limit/base address registers (DWORD) */ +#define IDT_SW_NTP0_BARSETUP0 0x01470U +#define IDT_SW_NTP0_BARLIMIT0 0x01474U +#define IDT_SW_NTP0_BARLTBASE0 0x01478U +#define IDT_SW_NTP0_BARUTBASE0 0x0147CU +#define IDT_SW_NTP0_BARSETUP1 0x01480U +#define IDT_SW_NTP0_BARLIMIT1 0x01484U +#define IDT_SW_NTP0_BARLTBASE1 0x01488U +#define IDT_SW_NTP0_BARUTBASE1 0x0148CU +#define IDT_SW_NTP0_BARSETUP2 0x01490U +#define IDT_SW_NTP0_BARLIMIT2 0x01494U +#define IDT_SW_NTP0_BARLTBASE2 0x01498U +#define IDT_SW_NTP0_BARUTBASE2 0x0149CU +#define IDT_SW_NTP0_BARSETUP3 0x014A0U +#define IDT_SW_NTP0_BARLIMIT3 0x014A4U +#define IDT_SW_NTP0_BARLTBASE3 0x014A8U +#define IDT_SW_NTP0_BARUTBASE3 0x014ACU +#define IDT_SW_NTP0_BARSETUP4 0x014B0U +#define IDT_SW_NTP0_BARLIMIT4 0x014B4U +#define IDT_SW_NTP0_BARLTBASE4 0x014B8U +#define IDT_SW_NTP0_BARUTBASE4 0x014BCU +#define IDT_SW_NTP0_BARSETUP5 0x014C0U +#define IDT_SW_NTP0_BARLIMIT5 0x014C4U +#define IDT_SW_NTP0_BARLTBASE5 0x014C8U +#define IDT_SW_NTP0_BARUTBASE5 0x014CCU +/* PCI Express command/status and link control/status registers (WORD+WORD) */ +#define IDT_SW_NTP2_PCIECMDSTS 0x05004U +#define IDT_SW_NTP2_PCIELCTLSTS 0x05050U +/* NT-function control register (DWORD) */ +#define IDT_SW_NTP2_NTCTL 0x05400U +/* BAR setup/limit/base address registers (DWORD) */ +#define IDT_SW_NTP2_BARSETUP0 0x05470U +#define IDT_SW_NTP2_BARLIMIT0 0x05474U +#define IDT_SW_NTP2_BARLTBASE0 0x05478U +#define IDT_SW_NTP2_BARUTBASE0 0x0547CU +#define IDT_SW_NTP2_BARSETUP1 0x05480U +#define IDT_SW_NTP2_BARLIMIT1 0x05484U +#define IDT_SW_NTP2_BARLTBASE1 0x05488U +#define IDT_SW_NTP2_BARUTBASE1 0x0548CU +#define IDT_SW_NTP2_BARSETUP2 0x05490U +#define IDT_SW_NTP2_BARLIMIT2 0x05494U +#define IDT_SW_NTP2_BARLTBASE2 0x05498U +#define IDT_SW_NTP2_BARUTBASE2 0x0549CU +#define IDT_SW_NTP2_BARSETUP3 0x054A0U +#define IDT_SW_NTP2_BARLIMIT3 0x054A4U +#define IDT_SW_NTP2_BARLTBASE3 0x054A8U +#define IDT_SW_NTP2_BARUTBASE3 0x054ACU +#define IDT_SW_NTP2_BARSETUP4 0x054B0U +#define IDT_SW_NTP2_BARLIMIT4 0x054B4U +#define IDT_SW_NTP2_BARLTBASE4 0x054B8U +#define IDT_SW_NTP2_BARUTBASE4 0x054BCU +#define IDT_SW_NTP2_BARSETUP5 0x054C0U +#define IDT_SW_NTP2_BARLIMIT5 0x054C4U +#define IDT_SW_NTP2_BARLTBASE5 0x054C8U +#define IDT_SW_NTP2_BARUTBASE5 0x054CCU +/* PCI Express command/status and link control/status registers (WORD+WORD) */ +#define IDT_SW_NTP4_PCIECMDSTS 0x09004U +#define IDT_SW_NTP4_PCIELCTLSTS 0x09050U +/* NT-function control register (DWORD) */ +#define IDT_SW_NTP4_NTCTL 0x09400U +/* BAR setup/limit/base address registers (DWORD) */ +#define IDT_SW_NTP4_BARSETUP0 0x09470U +#define IDT_SW_NTP4_BARLIMIT0 0x09474U +#define IDT_SW_NTP4_BARLTBASE0 0x09478U +#define IDT_SW_NTP4_BARUTBASE0 0x0947CU +#define IDT_SW_NTP4_BARSETUP1 0x09480U +#define IDT_SW_NTP4_BARLIMIT1 0x09484U +#define IDT_SW_NTP4_BARLTBASE1 0x09488U +#define IDT_SW_NTP4_BARUTBASE1 0x0948CU +#define IDT_SW_NTP4_BARSETUP2 0x09490U +#define IDT_SW_NTP4_BARLIMIT2 0x09494U +#define IDT_SW_NTP4_BARLTBASE2 0x09498U +#define IDT_SW_NTP4_BARUTBASE2 0x0949CU +#define IDT_SW_NTP4_BARSETUP3 0x094A0U +#define IDT_SW_NTP4_BARLIMIT3 0x094A4U +#define IDT_SW_NTP4_BARLTBASE3 0x094A8U +#define IDT_SW_NTP4_BARUTBASE3 0x094ACU +#define IDT_SW_NTP4_BARSETUP4 0x094B0U +#define IDT_SW_NTP4_BARLIMIT4 0x094B4U +#define IDT_SW_NTP4_BARLTBASE4 0x094B8U +#define IDT_SW_NTP4_BARUTBASE4 0x094BCU +#define IDT_SW_NTP4_BARSETUP5 0x094C0U +#define IDT_SW_NTP4_BARLIMIT5 0x094C4U +#define IDT_SW_NTP4_BARLTBASE5 0x094C8U +#define IDT_SW_NTP4_BARUTBASE5 0x094CCU +/* PCI Express command/status and link control/status registers (WORD+WORD) */ +#define IDT_SW_NTP6_PCIECMDSTS 0x0D004U +#define IDT_SW_NTP6_PCIELCTLSTS 0x0D050U +/* NT-function control register (DWORD) */ +#define IDT_SW_NTP6_NTCTL 0x0D400U +/* BAR setup/limit/base address registers (DWORD) */ +#define IDT_SW_NTP6_BARSETUP0 0x0D470U +#define IDT_SW_NTP6_BARLIMIT0 0x0D474U +#define IDT_SW_NTP6_BARLTBASE0 0x0D478U +#define IDT_SW_NTP6_BARUTBASE0 0x0D47CU +#define IDT_SW_NTP6_BARSETUP1 0x0D480U +#define IDT_SW_NTP6_BARLIMIT1 0x0D484U +#define IDT_SW_NTP6_BARLTBASE1 0x0D488U +#define IDT_SW_NTP6_BARUTBASE1 0x0D48CU +#define IDT_SW_NTP6_BARSETUP2 0x0D490U +#define IDT_SW_NTP6_BARLIMIT2 0x0D494U +#define IDT_SW_NTP6_BARLTBASE2 0x0D498U +#define IDT_SW_NTP6_BARUTBASE2 0x0D49CU +#define IDT_SW_NTP6_BARSETUP3 0x0D4A0U +#define IDT_SW_NTP6_BARLIMIT3 0x0D4A4U +#define IDT_SW_NTP6_BARLTBASE3 0x0D4A8U +#define IDT_SW_NTP6_BARUTBASE3 0x0D4ACU +#define IDT_SW_NTP6_BARSETUP4 0x0D4B0U +#define IDT_SW_NTP6_BARLIMIT4 0x0D4B4U +#define IDT_SW_NTP6_BARLTBASE4 0x0D4B8U +#define IDT_SW_NTP6_BARUTBASE4 0x0D4BCU +#define IDT_SW_NTP6_BARSETUP5 0x0D4C0U +#define IDT_SW_NTP6_BARLIMIT5 0x0D4C4U +#define IDT_SW_NTP6_BARLTBASE5 0x0D4C8U +#define IDT_SW_NTP6_BARUTBASE5 0x0D4CCU +/* PCI Express command/status and link control/status registers (WORD+WORD) */ +#define IDT_SW_NTP8_PCIECMDSTS 0x11004U +#define IDT_SW_NTP8_PCIELCTLSTS 0x11050U +/* NT-function control register (DWORD) */ +#define IDT_SW_NTP8_NTCTL 0x11400U +/* BAR setup/limit/base address registers (DWORD) */ +#define IDT_SW_NTP8_BARSETUP0 0x11470U +#define IDT_SW_NTP8_BARLIMIT0 0x11474U +#define IDT_SW_NTP8_BARLTBASE0 0x11478U +#define IDT_SW_NTP8_BARUTBASE0 0x1147CU +#define IDT_SW_NTP8_BARSETUP1 0x11480U +#define IDT_SW_NTP8_BARLIMIT1 0x11484U +#define IDT_SW_NTP8_BARLTBASE1 0x11488U +#define IDT_SW_NTP8_BARUTBASE1 0x1148CU +#define IDT_SW_NTP8_BARSETUP2 0x11490U +#define IDT_SW_NTP8_BARLIMIT2 0x11494U +#define IDT_SW_NTP8_BARLTBASE2 0x11498U +#define IDT_SW_NTP8_BARUTBASE2 0x1149CU +#define IDT_SW_NTP8_BARSETUP3 0x114A0U +#define IDT_SW_NTP8_BARLIMIT3 0x114A4U +#define IDT_SW_NTP8_BARLTBASE3 0x114A8U +#define IDT_SW_NTP8_BARUTBASE3 0x114ACU +#define IDT_SW_NTP8_BARSETUP4 0x114B0U +#define IDT_SW_NTP8_BARLIMIT4 0x114B4U +#define IDT_SW_NTP8_BARLTBASE4 0x114B8U +#define IDT_SW_NTP8_BARUTBASE4 0x114BCU +#define IDT_SW_NTP8_BARSETUP5 0x114C0U +#define IDT_SW_NTP8_BARLIMIT5 0x114C4U +#define IDT_SW_NTP8_BARLTBASE5 0x114C8U +#define IDT_SW_NTP8_BARUTBASE5 0x114CCU +/* PCI Express command/status and link control/status registers (WORD+WORD) */ +#define IDT_SW_NTP12_PCIECMDSTS 0x19004U +#define IDT_SW_NTP12_PCIELCTLSTS 0x19050U +/* NT-function control register (DWORD) */ +#define IDT_SW_NTP12_NTCTL 0x19400U +/* BAR setup/limit/base address registers (DWORD) */ +#define IDT_SW_NTP12_BARSETUP0 0x19470U +#define IDT_SW_NTP12_BARLIMIT0 0x19474U +#define IDT_SW_NTP12_BARLTBASE0 0x19478U +#define IDT_SW_NTP12_BARUTBASE0 0x1947CU +#define IDT_SW_NTP12_BARSETUP1 0x19480U +#define IDT_SW_NTP12_BARLIMIT1 0x19484U +#define IDT_SW_NTP12_BARLTBASE1 0x19488U +#define IDT_SW_NTP12_BARUTBASE1 0x1948CU +#define IDT_SW_NTP12_BARSETUP2 0x19490U +#define IDT_SW_NTP12_BARLIMIT2 0x19494U +#define IDT_SW_NTP12_BARLTBASE2 0x19498U +#define IDT_SW_NTP12_BARUTBASE2 0x1949CU +#define IDT_SW_NTP12_BARSETUP3 0x194A0U +#define IDT_SW_NTP12_BARLIMIT3 0x194A4U +#define IDT_SW_NTP12_BARLTBASE3 0x194A8U +#define IDT_SW_NTP12_BARUTBASE3 0x194ACU +#define IDT_SW_NTP12_BARSETUP4 0x194B0U +#define IDT_SW_NTP12_BARLIMIT4 0x194B4U +#define IDT_SW_NTP12_BARLTBASE4 0x194B8U +#define IDT_SW_NTP12_BARUTBASE4 0x194BCU +#define IDT_SW_NTP12_BARSETUP5 0x194C0U +#define IDT_SW_NTP12_BARLIMIT5 0x194C4U +#define IDT_SW_NTP12_BARLTBASE5 0x194C8U +#define IDT_SW_NTP12_BARUTBASE5 0x194CCU +/* PCI Express command/status and link control/status registers (WORD+WORD) */ +#define IDT_SW_NTP16_PCIECMDSTS 0x21004U +#define IDT_SW_NTP16_PCIELCTLSTS 0x21050U +/* NT-function control register (DWORD) */ +#define IDT_SW_NTP16_NTCTL 0x21400U +/* BAR setup/limit/base address registers (DWORD) */ +#define IDT_SW_NTP16_BARSETUP0 0x21470U +#define IDT_SW_NTP16_BARLIMIT0 0x21474U +#define IDT_SW_NTP16_BARLTBASE0 0x21478U +#define IDT_SW_NTP16_BARUTBASE0 0x2147CU +#define IDT_SW_NTP16_BARSETUP1 0x21480U +#define IDT_SW_NTP16_BARLIMIT1 0x21484U +#define IDT_SW_NTP16_BARLTBASE1 0x21488U +#define IDT_SW_NTP16_BARUTBASE1 0x2148CU +#define IDT_SW_NTP16_BARSETUP2 0x21490U +#define IDT_SW_NTP16_BARLIMIT2 0x21494U +#define IDT_SW_NTP16_BARLTBASE2 0x21498U +#define IDT_SW_NTP16_BARUTBASE2 0x2149CU +#define IDT_SW_NTP16_BARSETUP3 0x214A0U +#define IDT_SW_NTP16_BARLIMIT3 0x214A4U +#define IDT_SW_NTP16_BARLTBASE3 0x214A8U +#define IDT_SW_NTP16_BARUTBASE3 0x214ACU +#define IDT_SW_NTP16_BARSETUP4 0x214B0U +#define IDT_SW_NTP16_BARLIMIT4 0x214B4U +#define IDT_SW_NTP16_BARLTBASE4 0x214B8U +#define IDT_SW_NTP16_BARUTBASE4 0x214BCU +#define IDT_SW_NTP16_BARSETUP5 0x214C0U +#define IDT_SW_NTP16_BARLIMIT5 0x214C4U +#define IDT_SW_NTP16_BARLTBASE5 0x214C8U +#define IDT_SW_NTP16_BARUTBASE5 0x214CCU +/* PCI Express command/status and link control/status registers (WORD+WORD) */ +#define IDT_SW_NTP20_PCIECMDSTS 0x29004U +#define IDT_SW_NTP20_PCIELCTLSTS 0x29050U +/* NT-function control register (DWORD) */ +#define IDT_SW_NTP20_NTCTL 0x29400U +/* BAR setup/limit/base address registers (DWORD) */ +#define IDT_SW_NTP20_BARSETUP0 0x29470U +#define IDT_SW_NTP20_BARLIMIT0 0x29474U +#define IDT_SW_NTP20_BARLTBASE0 0x29478U +#define IDT_SW_NTP20_BARUTBASE0 0x2947CU +#define IDT_SW_NTP20_BARSETUP1 0x29480U +#define IDT_SW_NTP20_BARLIMIT1 0x29484U +#define IDT_SW_NTP20_BARLTBASE1 0x29488U +#define IDT_SW_NTP20_BARUTBASE1 0x2948CU +#define IDT_SW_NTP20_BARSETUP2 0x29490U +#define IDT_SW_NTP20_BARLIMIT2 0x29494U +#define IDT_SW_NTP20_BARLTBASE2 0x29498U +#define IDT_SW_NTP20_BARUTBASE2 0x2949CU +#define IDT_SW_NTP20_BARSETUP3 0x294A0U +#define IDT_SW_NTP20_BARLIMIT3 0x294A4U +#define IDT_SW_NTP20_BARLTBASE3 0x294A8U +#define IDT_SW_NTP20_BARUTBASE3 0x294ACU +#define IDT_SW_NTP20_BARSETUP4 0x294B0U +#define IDT_SW_NTP20_BARLIMIT4 0x294B4U +#define IDT_SW_NTP20_BARLTBASE4 0x294B8U +#define IDT_SW_NTP20_BARUTBASE4 0x294BCU +#define IDT_SW_NTP20_BARSETUP5 0x294C0U +#define IDT_SW_NTP20_BARLIMIT5 0x294C4U +#define IDT_SW_NTP20_BARLTBASE5 0x294C8U +#define IDT_SW_NTP20_BARUTBASE5 0x294CCU +/* IDT PCIe-switch control register (DWORD) */ +#define IDT_SW_CTL 0x3E000U +/* Boot Configuration Vector Status (DWORD) */ +#define IDT_SW_BCVSTS 0x3E004U +/* Port Clocking Mode (DWORD) */ +#define IDT_SW_PCLKMODE 0x3E008U +/* Reset Drain Delay (DWORD) */ +#define IDT_SW_RDRAINDELAY 0x3E080U +/* Port Operating Mode Change Drain Delay (DWORD) */ +#define IDT_SW_POMCDELAY 0x3E084U +/* Side Effect Delay (DWORD) */ +#define IDT_SW_SEDELAY 0x3E088U +/* Upstream Secondary Bus Reset Delay (DWORD) */ +#define IDT_SW_SSBRDELAY 0x3E08CU +/* Switch partition N Control/Status/Failover registers */ +#define IDT_SW_SWPART0CTL 0x3E100U +#define IDT_SW_SWPART0STS 0x3E104U +#define IDT_SW_SWPART0FCTL 0x3E108U +#define IDT_SW_SWPART1CTL 0x3E120U +#define IDT_SW_SWPART1STS 0x3E124U +#define IDT_SW_SWPART1FCTL 0x3E128U +#define IDT_SW_SWPART2CTL 0x3E140U +#define IDT_SW_SWPART2STS 0x3E144U +#define IDT_SW_SWPART2FCTL 0x3E148U +#define IDT_SW_SWPART3CTL 0x3E160U +#define IDT_SW_SWPART3STS 0x3E164U +#define IDT_SW_SWPART3FCTL 0x3E168U +#define IDT_SW_SWPART4CTL 0x3E180U +#define IDT_SW_SWPART4STS 0x3E184U +#define IDT_SW_SWPART4FCTL 0x3E188U +#define IDT_SW_SWPART5CTL 0x3E1A0U +#define IDT_SW_SWPART5STS 0x3E1A4U +#define IDT_SW_SWPART5FCTL 0x3E1A8U +#define IDT_SW_SWPART6CTL 0x3E1C0U +#define IDT_SW_SWPART6STS 0x3E1C4U +#define IDT_SW_SWPART6FCTL 0x3E1C8U +#define IDT_SW_SWPART7CTL 0x3E1E0U +#define IDT_SW_SWPART7STS 0x3E1E4U +#define IDT_SW_SWPART7FCTL 0x3E1E8U +/* Switch port N control and status registers */ +#define IDT_SW_SWPORT0CTL 0x3E200U +#define IDT_SW_SWPORT0STS 0x3E204U +#define IDT_SW_SWPORT0FCTL 0x3E208U +#define IDT_SW_SWPORT2CTL 0x3E240U +#define IDT_SW_SWPORT2STS 0x3E244U +#define IDT_SW_SWPORT2FCTL 0x3E248U +#define IDT_SW_SWPORT4CTL 0x3E280U +#define IDT_SW_SWPORT4STS 0x3E284U +#define IDT_SW_SWPORT4FCTL 0x3E288U +#define IDT_SW_SWPORT6CTL 0x3E2C0U +#define IDT_SW_SWPORT6STS 0x3E2C4U +#define IDT_SW_SWPORT6FCTL 0x3E2C8U +#define IDT_SW_SWPORT8CTL 0x3E300U +#define IDT_SW_SWPORT8STS 0x3E304U +#define IDT_SW_SWPORT8FCTL 0x3E308U +#define IDT_SW_SWPORT12CTL 0x3E380U +#define IDT_SW_SWPORT12STS 0x3E384U +#define IDT_SW_SWPORT12FCTL 0x3E388U +#define IDT_SW_SWPORT16CTL 0x3E400U +#define IDT_SW_SWPORT16STS 0x3E404U +#define IDT_SW_SWPORT16FCTL 0x3E408U +#define IDT_SW_SWPORT20CTL 0x3E480U +#define IDT_SW_SWPORT20STS 0x3E484U +#define IDT_SW_SWPORT20FCTL 0x3E488U +/* Switch Event registers */ +/* Switch Event Status/Mask/Partition mask (DWORD) */ +#define IDT_SW_SESTS 0x3EC00U +#define IDT_SW_SEMSK 0x3EC04U +#define IDT_SW_SEPMSK 0x3EC08U +/* Switch Event Link Up/Down Status/Mask (DWORD) */ +#define IDT_SW_SELINKUPSTS 0x3EC0CU +#define IDT_SW_SELINKUPMSK 0x3EC10U +#define IDT_SW_SELINKDNSTS 0x3EC14U +#define IDT_SW_SELINKDNMSK 0x3EC18U +/* Switch Event Fundamental Reset Status/Mask (DWORD) */ +#define IDT_SW_SEFRSTSTS 0x3EC1CU +#define IDT_SW_SEFRSTMSK 0x3EC20U +/* Switch Event Hot Reset Status/Mask (DWORD) */ +#define IDT_SW_SEHRSTSTS 0x3EC24U +#define IDT_SW_SEHRSTMSK 0x3EC28U +/* Switch Event Failover Mask (DWORD) */ +#define IDT_SW_SEFOVRMSK 0x3EC2CU +/* Switch Event Global Signal Status/Mask (DWORD) */ +#define IDT_SW_SEGSIGSTS 0x3EC30U +#define IDT_SW_SEGSIGMSK 0x3EC34U +/* NT Global Doorbell Status (DWORD) */ +#define IDT_SW_GDBELLSTS 0x3EC3CU +/* Switch partition N message M control (msgs routing table) (DWORD) */ +#define IDT_SW_SWP0MSGCTL0 0x3EE00U +#define IDT_SW_SWP1MSGCTL0 0x3EE04U +#define IDT_SW_SWP2MSGCTL0 0x3EE08U +#define IDT_SW_SWP3MSGCTL0 0x3EE0CU +#define IDT_SW_SWP4MSGCTL0 0x3EE10U +#define IDT_SW_SWP5MSGCTL0 0x3EE14U +#define IDT_SW_SWP6MSGCTL0 0x3EE18U +#define IDT_SW_SWP7MSGCTL0 0x3EE1CU +#define IDT_SW_SWP0MSGCTL1 0x3EE20U +#define IDT_SW_SWP1MSGCTL1 0x3EE24U +#define IDT_SW_SWP2MSGCTL1 0x3EE28U +#define IDT_SW_SWP3MSGCTL1 0x3EE2CU +#define IDT_SW_SWP4MSGCTL1 0x3EE30U +#define IDT_SW_SWP5MSGCTL1 0x3EE34U +#define IDT_SW_SWP6MSGCTL1 0x3EE38U +#define IDT_SW_SWP7MSGCTL1 0x3EE3CU +#define IDT_SW_SWP0MSGCTL2 0x3EE40U +#define IDT_SW_SWP1MSGCTL2 0x3EE44U +#define IDT_SW_SWP2MSGCTL2 0x3EE48U +#define IDT_SW_SWP3MSGCTL2 0x3EE4CU +#define IDT_SW_SWP4MSGCTL2 0x3EE50U +#define IDT_SW_SWP5MSGCTL2 0x3EE54U +#define IDT_SW_SWP6MSGCTL2 0x3EE58U +#define IDT_SW_SWP7MSGCTL2 0x3EE5CU +#define IDT_SW_SWP0MSGCTL3 0x3EE60U +#define IDT_SW_SWP1MSGCTL3 0x3EE64U +#define IDT_SW_SWP2MSGCTL3 0x3EE68U +#define IDT_SW_SWP3MSGCTL3 0x3EE6CU +#define IDT_SW_SWP4MSGCTL3 0x3EE70U +#define IDT_SW_SWP5MSGCTL3 0x3EE74U +#define IDT_SW_SWP6MSGCTL3 0x3EE78U +#define IDT_SW_SWP7MSGCTL3 0x3EE7CU +/* SMBus Status and Control registers (DWORD) */ +#define IDT_SW_SMBUSSTS 0x3F188U +#define IDT_SW_SMBUSCTL 0x3F18CU +/* Serial EEPROM Interface (DWORD) */ +#define IDT_SW_EEPROMINTF 0x3F190U +/* MBus I/O Expander Address N (DWORD) */ +#define IDT_SW_IOEXPADDR0 0x3F198U +#define IDT_SW_IOEXPADDR1 0x3F19CU +#define IDT_SW_IOEXPADDR2 0x3F1A0U +#define IDT_SW_IOEXPADDR3 0x3F1A4U +#define IDT_SW_IOEXPADDR4 0x3F1A8U +#define IDT_SW_IOEXPADDR5 0x3F1ACU +/* General Purpose Events Control and Status registers (DWORD) */ +#define IDT_SW_GPECTL 0x3F1B0U +#define IDT_SW_GPESTS 0x3F1B4U +/* Temperature sensor Control/Status/Alarm/Adjustment/Slope registers */ +#define IDT_SW_TMPCTL 0x3F1D4U +#define IDT_SW_TMPSTS 0x3F1D8U +#define IDT_SW_TMPALARM 0x3F1DCU +#define IDT_SW_TMPADJ 0x3F1E0U +#define IDT_SW_TSSLOPE 0x3F1E4U +/* SMBus Configuration Block header log (DWORD) */ +#define IDT_SW_SMBUSCBHL 0x3F1E8U + +/* + * Common registers related constants + * @IDT_REG_ALIGN: Registers alignment used in the driver + * @IDT_REG_PCI_MAX: Maximum PCI configuration space register value + * @IDT_REG_SW_MAX: Maximum global register value + */ +#define IDT_REG_ALIGN 4 +#define IDT_REG_PCI_MAX 0x00FFFU +#define IDT_REG_SW_MAX 0x3FFFFU + +/* + * PCICMDSTS register fields related constants + * @IDT_PCICMDSTS_IOAE: I/O access enable + * @IDT_PCICMDSTS_MAE: Memory access enable + * @IDT_PCICMDSTS_BME: Bus master enable + */ +#define IDT_PCICMDSTS_IOAE 0x00000001U +#define IDT_PCICMDSTS_MAE 0x00000002U +#define IDT_PCICMDSTS_BME 0x00000004U + +/* + * PCIEDCAP register fields related constants + * @IDT_PCIEDCAP_MPAYLOAD_MASK: Maximum payload size mask + * @IDT_PCIEDCAP_MPAYLOAD_FLD: Maximum payload size field offset + * @IDT_PCIEDCAP_MPAYLOAD_S128: Max supported payload size of 128 bytes + * @IDT_PCIEDCAP_MPAYLOAD_S256: Max supported payload size of 256 bytes + * @IDT_PCIEDCAP_MPAYLOAD_S512: Max supported payload size of 512 bytes + * @IDT_PCIEDCAP_MPAYLOAD_S1024: Max supported payload size of 1024 bytes + * @IDT_PCIEDCAP_MPAYLOAD_S2048: Max supported payload size of 2048 bytes + */ +#define IDT_PCIEDCAP_MPAYLOAD_MASK 0x00000007U +#define IDT_PCIEDCAP_MPAYLOAD_FLD 0 +#define IDT_PCIEDCAP_MPAYLOAD_S128 0x00000000U +#define IDT_PCIEDCAP_MPAYLOAD_S256 0x00000001U +#define IDT_PCIEDCAP_MPAYLOAD_S512 0x00000002U +#define IDT_PCIEDCAP_MPAYLOAD_S1024 0x00000003U +#define IDT_PCIEDCAP_MPAYLOAD_S2048 0x00000004U + +/* + * PCIEDCTLSTS registers fields related constants + * @IDT_PCIEDCTL_MPS_MASK: Maximum payload size mask + * @IDT_PCIEDCTL_MPS_FLD: MPS field offset + * @IDT_PCIEDCTL_MPS_S128: Max payload size of 128 bytes + * @IDT_PCIEDCTL_MPS_S256: Max payload size of 256 bytes + * @IDT_PCIEDCTL_MPS_S512: Max payload size of 512 bytes + * @IDT_PCIEDCTL_MPS_S1024: Max payload size of 1024 bytes + * @IDT_PCIEDCTL_MPS_S2048: Max payload size of 2048 bytes + * @IDT_PCIEDCTL_MPS_S4096: Max payload size of 4096 bytes + */ +#define IDT_PCIEDCTLSTS_MPS_MASK 0x000000E0U +#define IDT_PCIEDCTLSTS_MPS_FLD 5 +#define IDT_PCIEDCTLSTS_MPS_S128 0x00000000U +#define IDT_PCIEDCTLSTS_MPS_S256 0x00000020U +#define IDT_PCIEDCTLSTS_MPS_S512 0x00000040U +#define IDT_PCIEDCTLSTS_MPS_S1024 0x00000060U +#define IDT_PCIEDCTLSTS_MPS_S2048 0x00000080U +#define IDT_PCIEDCTLSTS_MPS_S4096 0x000000A0U + +/* + * PCIELCAP register fields related constants + * @IDT_PCIELCAP_PORTNUM_MASK: Port number field mask + * @IDT_PCIELCAP_PORTNUM_FLD: Port number field offset + */ +#define IDT_PCIELCAP_PORTNUM_MASK 0xFF000000U +#define IDT_PCIELCAP_PORTNUM_FLD 24 + +/* + * PCIELCTLSTS registers fields related constants + * @IDT_PCIELSTS_CLS_MASK: Current link speed mask + * @IDT_PCIELSTS_CLS_FLD: Current link speed field offset + * @IDT_PCIELSTS_NLW_MASK: Negotiated link width mask + * @IDT_PCIELSTS_NLW_FLD: Negotiated link width field offset + * @IDT_PCIELSTS_SCLK_COM: Common slot clock configuration + */ +#define IDT_PCIELCTLSTS_CLS_MASK 0x000F0000U +#define IDT_PCIELCTLSTS_CLS_FLD 16 +#define IDT_PCIELCTLSTS_NLW_MASK 0x03F00000U +#define IDT_PCIELCTLSTS_NLW_FLD 20 +#define IDT_PCIELCTLSTS_SCLK_COM 0x10000000U + +/* + * NTCTL register fields related constants + * @IDT_NTCTL_IDPROTDIS: ID Protection check disable (disable MTBL) + * @IDT_NTCTL_CPEN: Completion enable + * @IDT_NTCTL_RNS: Request no snoop processing (if MTBL disabled) + * @IDT_NTCTL_ATP: Address type processing (if MTBL disabled) + */ +#define IDT_NTCTL_IDPROTDIS 0x00000001U +#define IDT_NTCTL_CPEN 0x00000002U +#define IDT_NTCTL_RNS 0x00000004U +#define IDT_NTCTL_ATP 0x00000008U + +/* + * NTINTSTS register fields related constants + * @IDT_NTINTSTS_MSG: Message interrupt bit + * @IDT_NTINTSTS_DBELL: Doorbell interrupt bit + * @IDT_NTINTSTS_SEVENT: Switch Event interrupt bit + * @IDT_NTINTSTS_TMPSENSOR: Temperature sensor interrupt bit + */ +#define IDT_NTINTSTS_MSG 0x00000001U +#define IDT_NTINTSTS_DBELL 0x00000002U +#define IDT_NTINTSTS_SEVENT 0x00000008U +#define IDT_NTINTSTS_TMPSENSOR 0x00000080U + +/* + * NTINTMSK register fields related constants + * @IDT_NTINTMSK_MSG: Message interrupt mask bit + * @IDT_NTINTMSK_DBELL: Doorbell interrupt mask bit + * @IDT_NTINTMSK_SEVENT: Switch Event interrupt mask bit + * @IDT_NTINTMSK_TMPSENSOR: Temperature sensor interrupt mask bit + * @IDT_NTINTMSK_ALL: All the useful interrupts mask + */ +#define IDT_NTINTMSK_MSG 0x00000001U +#define IDT_NTINTMSK_DBELL 0x00000002U +#define IDT_NTINTMSK_SEVENT 0x00000008U +#define IDT_NTINTMSK_TMPSENSOR 0x00000080U +#define IDT_NTINTMSK_ALL \ + (IDT_NTINTMSK_MSG | IDT_NTINTMSK_DBELL | \ + IDT_NTINTMSK_SEVENT | IDT_NTINTMSK_TMPSENSOR) + +/* + * NTGSIGNAL register fields related constants + * @IDT_NTGSIGNAL_SET: Set global signal of the local partition + */ +#define IDT_NTGSIGNAL_SET 0x00000001U + +/* + * BARSETUP register fields related constants + * @IDT_BARSETUP_TYPE_MASK: Mask of the TYPE field + * @IDT_BARSETUP_TYPE_32: 32-bit addressing BAR + * @IDT_BARSETUP_TYPE_64: 64-bit addressing BAR + * @IDT_BARSETUP_PREF: Value of the BAR prefetchable field + * @IDT_BARSETUP_SIZE_MASK: Mask of the SIZE field + * @IDT_BARSETUP_SIZE_FLD: SIZE field offset + * @IDT_BARSETUP_SIZE_CFG: SIZE field value in case of config space MODE + * @IDT_BARSETUP_MODE_CFG: Configuration space BAR mode + * @IDT_BARSETUP_ATRAN_MASK: ATRAN field mask + * @IDT_BARSETUP_ATRAN_FLD: ATRAN field offset + * @IDT_BARSETUP_ATRAN_DIR: Direct address translation memory window + * @IDT_BARSETUP_ATRAN_LUT12: 12-entry lookup table + * @IDT_BARSETUP_ATRAN_LUT24: 24-entry lookup table + * @IDT_BARSETUP_TPART_MASK: TPART field mask + * @IDT_BARSETUP_TPART_FLD: TPART field offset + * @IDT_BARSETUP_EN: BAR enable bit + */ +#define IDT_BARSETUP_TYPE_MASK 0x00000006U +#define IDT_BARSETUP_TYPE_FLD 0 +#define IDT_BARSETUP_TYPE_32 0x00000000U +#define IDT_BARSETUP_TYPE_64 0x00000004U +#define IDT_BARSETUP_PREF 0x00000008U +#define IDT_BARSETUP_SIZE_MASK 0x000003F0U +#define IDT_BARSETUP_SIZE_FLD 4 +#define IDT_BARSETUP_SIZE_CFG 0x000000C0U +#define IDT_BARSETUP_MODE_CFG 0x00000400U +#define IDT_BARSETUP_ATRAN_MASK 0x00001800U +#define IDT_BARSETUP_ATRAN_FLD 11 +#define IDT_BARSETUP_ATRAN_DIR 0x00000000U +#define IDT_BARSETUP_ATRAN_LUT12 0x00000800U +#define IDT_BARSETUP_ATRAN_LUT24 0x00001000U +#define IDT_BARSETUP_TPART_MASK 0x0000E000U +#define IDT_BARSETUP_TPART_FLD 13 +#define IDT_BARSETUP_EN 0x80000000U + +/* + * NTMTBLDATA register fields related constants + * @IDT_NTMTBLDATA_VALID: Set the MTBL entry being valid + * @IDT_NTMTBLDATA_REQID_MASK: Bus:Device:Function field mask + * @IDT_NTMTBLDATA_REQID_FLD: Bus:Device:Function field offset + * @IDT_NTMTBLDATA_PART_MASK: Partition field mask + * @IDT_NTMTBLDATA_PART_FLD: Partition field offset + * @IDT_NTMTBLDATA_ATP_TRANS: Enable AT field translation on request TLPs + * @IDT_NTMTBLDATA_CNS_INV: Enable No Snoop attribute inversion of + * Completion TLPs + * @IDT_NTMTBLDATA_RNS_INV: Enable No Snoop attribute inversion of + * Request TLPs + */ +#define IDT_NTMTBLDATA_VALID 0x00000001U +#define IDT_NTMTBLDATA_REQID_MASK 0x0001FFFEU +#define IDT_NTMTBLDATA_REQID_FLD 1 +#define IDT_NTMTBLDATA_PART_MASK 0x000E0000U +#define IDT_NTMTBLDATA_PART_FLD 17 +#define IDT_NTMTBLDATA_ATP_TRANS 0x20000000U +#define IDT_NTMTBLDATA_CNS_INV 0x40000000U +#define IDT_NTMTBLDATA_RNS_INV 0x80000000U + +/* + * REQIDCAP register fields related constants + * @IDT_REQIDCAP_REQID_MASK: Request ID field mask + * @IDT_REQIDCAP_REQID_FLD: Request ID field offset + */ +#define IDT_REQIDCAP_REQID_MASK 0x0000FFFFU +#define IDT_REQIDCAP_REQID_FLD 0 + +/* + * LUTOFFSET register fields related constants + * @IDT_LUTOFFSET_INDEX_MASK: Lookup table index field mask + * @IDT_LUTOFFSET_INDEX_FLD: Lookup table index field offset + * @IDT_LUTOFFSET_BAR_MASK: Lookup table BAR select field mask + * @IDT_LUTOFFSET_BAR_FLD: Lookup table BAR select field offset + */ +#define IDT_LUTOFFSET_INDEX_MASK 0x0000001FU +#define IDT_LUTOFFSET_INDEX_FLD 0 +#define IDT_LUTOFFSET_BAR_MASK 0x00000700U +#define IDT_LUTOFFSET_BAR_FLD 8 + +/* + * LUTUDATA register fields related constants + * @IDT_LUTUDATA_PART_MASK: Partition field mask + * @IDT_LUTUDATA_PART_FLD: Partition field offset + * @IDT_LUTUDATA_VALID: Lookup table entry valid bit + */ +#define IDT_LUTUDATA_PART_MASK 0x0000000FU +#define IDT_LUTUDATA_PART_FLD 0 +#define IDT_LUTUDATA_VALID 0x80000000U + +/* + * SWPARTxSTS register fields related constants + * @IDT_SWPARTxSTS_SCI: Switch partition state change initiated + * @IDT_SWPARTxSTS_SCC: Switch partition state change completed + * @IDT_SWPARTxSTS_STATE_MASK: Switch partition state mask + * @IDT_SWPARTxSTS_STATE_FLD: Switch partition state field offset + * @IDT_SWPARTxSTS_STATE_DIS: Switch partition disabled + * @IDT_SWPARTxSTS_STATE_ACT: Switch partition enabled + * @IDT_SWPARTxSTS_STATE_RES: Switch partition in reset + * @IDT_SWPARTxSTS_US: Switch partition has upstream port + * @IDT_SWPARTxSTS_USID_MASK: Switch partition upstream port ID mask + * @IDT_SWPARTxSTS_USID_FLD: Switch partition upstream port ID field offset + * @IDT_SWPARTxSTS_NT: Upstream port has NT function + * @IDT_SWPARTxSTS_DMA: Upstream port has DMA function + */ +#define IDT_SWPARTxSTS_SCI 0x00000001U +#define IDT_SWPARTxSTS_SCC 0x00000002U +#define IDT_SWPARTxSTS_STATE_MASK 0x00000060U +#define IDT_SWPARTxSTS_STATE_FLD 5 +#define IDT_SWPARTxSTS_STATE_DIS 0x00000000U +#define IDT_SWPARTxSTS_STATE_ACT 0x00000020U +#define IDT_SWPARTxSTS_STATE_RES 0x00000060U +#define IDT_SWPARTxSTS_US 0x00000100U +#define IDT_SWPARTxSTS_USID_MASK 0x00003E00U +#define IDT_SWPARTxSTS_USID_FLD 9 +#define IDT_SWPARTxSTS_NT 0x00004000U +#define IDT_SWPARTxSTS_DMA 0x00008000U + +/* + * SWPORTxSTS register fields related constants + * @IDT_SWPORTxSTS_OMCI: Operation mode change initiated + * @IDT_SWPORTxSTS_OMCC: Operation mode change completed + * @IDT_SWPORTxSTS_LINKUP: Link up status + * @IDT_SWPORTxSTS_DS: Port lanes behave as downstream lanes + * @IDT_SWPORTxSTS_MODE_MASK: Port mode field mask + * @IDT_SWPORTxSTS_MODE_FLD: Port mode field offset + * @IDT_SWPORTxSTS_MODE_DIS: Port mode - disabled + * @IDT_SWPORTxSTS_MODE_DS: Port mode - downstream switch port + * @IDT_SWPORTxSTS_MODE_US: Port mode - upstream switch port + * @IDT_SWPORTxSTS_MODE_NT: Port mode - NT function + * @IDT_SWPORTxSTS_MODE_USNT: Port mode - upstream switch port with NTB + * @IDT_SWPORTxSTS_MODE_UNAT: Port mode - unattached + * @IDT_SWPORTxSTS_MODE_USDMA: Port mode - upstream switch port with DMA + * @IDT_SWPORTxSTS_MODE_USNTDMA:Port mode - upstream port with NTB and DMA + * @IDT_SWPORTxSTS_MODE_NTDMA: Port mode - NT function with DMA + * @IDT_SWPORTxSTS_SWPART_MASK: Port partition field mask + * @IDT_SWPORTxSTS_SWPART_FLD: Port partition field offset + * @IDT_SWPORTxSTS_DEVNUM_MASK: Port device number field mask + * @IDT_SWPORTxSTS_DEVNUM_FLD: Port device number field offset + */ +#define IDT_SWPORTxSTS_OMCI 0x00000001U +#define IDT_SWPORTxSTS_OMCC 0x00000002U +#define IDT_SWPORTxSTS_LINKUP 0x00000010U +#define IDT_SWPORTxSTS_DS 0x00000020U +#define IDT_SWPORTxSTS_MODE_MASK 0x000003C0U +#define IDT_SWPORTxSTS_MODE_FLD 6 +#define IDT_SWPORTxSTS_MODE_DIS 0x00000000U +#define IDT_SWPORTxSTS_MODE_DS 0x00000040U +#define IDT_SWPORTxSTS_MODE_US 0x00000080U +#define IDT_SWPORTxSTS_MODE_NT 0x000000C0U +#define IDT_SWPORTxSTS_MODE_USNT 0x00000100U +#define IDT_SWPORTxSTS_MODE_UNAT 0x00000140U +#define IDT_SWPORTxSTS_MODE_USDMA 0x00000180U +#define IDT_SWPORTxSTS_MODE_USNTDMA 0x000001C0U +#define IDT_SWPORTxSTS_MODE_NTDMA 0x00000200U +#define IDT_SWPORTxSTS_SWPART_MASK 0x00001C00U +#define IDT_SWPORTxSTS_SWPART_FLD 10 +#define IDT_SWPORTxSTS_DEVNUM_MASK 0x001F0000U +#define IDT_SWPORTxSTS_DEVNUM_FLD 16 + +/* + * SEMSK register fields related constants + * @IDT_SEMSK_LINKUP: Link Up event mask bit + * @IDT_SEMSK_LINKDN: Link Down event mask bit + * @IDT_SEMSK_GSIGNAL: Global Signal event mask bit + */ +#define IDT_SEMSK_LINKUP 0x00000001U +#define IDT_SEMSK_LINKDN 0x00000002U +#define IDT_SEMSK_GSIGNAL 0x00000020U + +/* + * SWPxMSGCTL register fields related constants + * @IDT_SWPxMSGCTL_REG_MASK: Register select field mask + * @IDT_SWPxMSGCTL_REG_FLD: Register select field offset + * @IDT_SWPxMSGCTL_PART_MASK: Partition select field mask + * @IDT_SWPxMSGCTL_PART_FLD: Partition select field offset + */ +#define IDT_SWPxMSGCTL_REG_MASK 0x00000003U +#define IDT_SWPxMSGCTL_REG_FLD 0 +#define IDT_SWPxMSGCTL_PART_MASK 0x00000070U +#define IDT_SWPxMSGCTL_PART_FLD 4 + +/* + * TMPSTS register fields related constants + * @IDT_TMPSTS_TEMP_MASK: Current temperature field mask + * @IDT_TMPSTS_TEMP_FLD: Current temperature field offset + */ +#define IDT_TMPSTS_TEMP_MASK 0x000000FFU +#define IDT_TMPSTS_TEMP_FLD 0 + +/* + * Helper macro to get/set the corresponding field value + * @GET_FIELD: Retrieve the value of the corresponding field + * @SET_FIELD: Set the specified field up + * @IS_FLD_SET: Check whether a field is set with value + */ +#define GET_FIELD(field, data) \ + (((u32)(data) & IDT_ ##field## _MASK) >> IDT_ ##field## _FLD) +#define SET_FIELD(field, data, value) \ + (((u32)(data) & ~IDT_ ##field## _MASK) | \ + ((u32)(value) << IDT_ ##field## _FLD)) +#define IS_FLD_SET(field, data, value) \ + (((u32)(data) & IDT_ ##field## _MASK) == IDT_ ##field## _ ##value) + +/* + * Useful registers masks: + * @IDT_DBELL_MASK: Doorbell bits mask + * @IDT_OUTMSG_MASK: Out messages status bits mask + * @IDT_INMSG_MASK: In messages status bits mask + * @IDT_MSG_MASK: Any message status bits mask + */ +#define IDT_DBELL_MASK ((u32)0xFFFFFFFFU) +#define IDT_OUTMSG_MASK ((u32)0x0000000FU) +#define IDT_INMSG_MASK ((u32)0x000F0000U) +#define IDT_MSG_MASK (IDT_INMSG_MASK | IDT_OUTMSG_MASK) + +/* + * Number of IDT NTB resources: + * @IDT_MSG_CNT: Number of Message registers + * @IDT_BAR_CNT: Number of BARs of each port + * @IDT_MTBL_ENTRY_CNT: Number mapping table entries + */ +#define IDT_MSG_CNT 4 +#define IDT_BAR_CNT 6 +#define IDT_MTBL_ENTRY_CNT 64 + +/* + * General IDT PCIe-switch constant + * @IDT_MAX_NR_PORTS: Maximum number of ports per IDT PCIe-switch + * @IDT_MAX_NR_PARTS: Maximum number of partitions per IDT PCIe-switch + * @IDT_MAX_NR_PEERS: Maximum number of NT-peers per IDT PCIe-switch + * @IDT_MAX_NR_MWS: Maximum number of Memory Widows + * @IDT_PCIE_REGSIZE: Size of the registers in bytes + * @IDT_TRANS_ALIGN: Alignment of translated base address + * @IDT_DIR_SIZE_ALIGN: Alignment of size setting for direct translated MWs. + * Even though the lower 10 bits are reserved, they are + * treated by IDT as one's so basically there is no any + * alignment of size limit for DIR address translation. + */ +#define IDT_MAX_NR_PORTS 24 +#define IDT_MAX_NR_PARTS 8 +#define IDT_MAX_NR_PEERS 8 +#define IDT_MAX_NR_MWS 29 +#define IDT_PCIE_REGSIZE 4 +#define IDT_TRANS_ALIGN 4 +#define IDT_DIR_SIZE_ALIGN 1 + +/* + * IDT Memory Windows type. Depending on the device settings, IDT supports + * Direct Address Translation MW registers and Lookup Table registers + * @IDT_MW_DIR: Direct address translation + * @IDT_MW_LUT12: 12-entry lookup table entry + * @IDT_MW_LUT24: 24-entry lookup table entry + * + * NOTE These values are exactly the same as one of the BARSETUP ATRAN field + */ +enum idt_mw_type { + IDT_MW_DIR = 0x0, + IDT_MW_LUT12 = 0x1, + IDT_MW_LUT24 = 0x2 +}; + +/* + * IDT PCIe-switch model private data + * @name: Device name + * @port_cnt: Total number of NT endpoint ports + * @ports: Port ids + */ +struct idt_89hpes_cfg { + char *name; + unsigned char port_cnt; + unsigned char ports[]; +}; + +/* + * Memory window configuration structure + * @type: Type of the memory window (direct address translation or lookup + * table) + * + * @bar: PCIe BAR the memory window referenced to + * @idx: Index of the memory window within the BAR + * + * @addr_align: Alignment of translated address + * @size_align: Alignment of memory window size + * @size_max: Maximum size of memory window + */ +struct idt_mw_cfg { + enum idt_mw_type type; + + unsigned char bar; + unsigned char idx; + + u64 addr_align; + u64 size_align; + u64 size_max; +}; + +/* + * Description structure of peer IDT NT-functions: + * @port: NT-function port + * @part: NT-function partition + * + * @mw_cnt: Number of memory windows supported by NT-function + * @mws: Array of memory windows descriptors + */ +struct idt_ntb_peer { + unsigned char port; + unsigned char part; + + unsigned char mw_cnt; + struct idt_mw_cfg *mws; +}; + +/* + * Description structure of local IDT NT-function: + * @ntb: Linux NTB-device description structure + * @swcfg: Pointer to the structure of local IDT PCIe-switch + * specific cofnfigurations + * + * @port: Local NT-function port + * @part: Local NT-function partition + * + * @peer_cnt: Number of peers with activated NTB-function + * @peers: Array of peers descripting structures + * @port_idx_map: Map of port number -> peer index + * @part_idx_map: Map of partition number -> peer index + * + * @mtbl_lock: Mapping table access lock + * + * @mw_cnt: Number of memory windows supported by NT-function + * @mws: Array of memory windows descriptors + * @lut_lock: Lookup table access lock + * + * @msg_locks: Message registers mapping table lockers + * + * @cfgspc: Virtual address of the memory mapped configuration + * space of the NT-function + * @db_mask_lock: Doorbell mask register lock + * @msg_mask_lock: Message mask register lock + * @gasa_lock: GASA registers access lock + * + * @dbgfs_info: DebugFS info node + */ +struct idt_ntb_dev { + struct ntb_dev ntb; + struct idt_89hpes_cfg *swcfg; + + unsigned char port; + unsigned char part; + + unsigned char peer_cnt; + struct idt_ntb_peer peers[IDT_MAX_NR_PEERS]; + char port_idx_map[IDT_MAX_NR_PORTS]; + char part_idx_map[IDT_MAX_NR_PARTS]; + + spinlock_t mtbl_lock; + + unsigned char mw_cnt; + struct idt_mw_cfg *mws; + spinlock_t lut_lock; + + spinlock_t msg_locks[IDT_MSG_CNT]; + + void __iomem *cfgspc; + spinlock_t db_mask_lock; + spinlock_t msg_mask_lock; + spinlock_t gasa_lock; + + struct dentry *dbgfs_info; +}; +#define to_ndev_ntb(__ntb) container_of(__ntb, struct idt_ntb_dev, ntb) + +/* + * Descriptor of the IDT PCIe-switch BAR resources + * @setup: BAR setup register + * @limit: BAR limit register + * @ltbase: Lower translated base address + * @utbase: Upper translated base address + */ +struct idt_ntb_bar { + unsigned int setup; + unsigned int limit; + unsigned int ltbase; + unsigned int utbase; +}; + +/* + * Descriptor of the IDT PCIe-switch message resources + * @in: Inbound message register + * @out: Outbound message register + * @src: Source of inbound message register + */ +struct idt_ntb_msg { + unsigned int in; + unsigned int out; + unsigned int src; +}; + +/* + * Descriptor of the IDT PCIe-switch NT-function specific parameters in the + * PCI Configuration Space + * @bars: BARs related registers + * @msgs: Messaging related registers + */ +struct idt_ntb_regs { + struct idt_ntb_bar bars[IDT_BAR_CNT]; + struct idt_ntb_msg msgs[IDT_MSG_CNT]; +}; + +/* + * Descriptor of the IDT PCIe-switch port specific parameters in the + * Global Configuration Space + * @pcicmdsts: PCI command/status register + * @pcielctlsts: PCIe link control/status + * + * @ctl: Port control register + * @sts: Port status register + * + * @bars: BARs related registers + */ +struct idt_ntb_port { + unsigned int pcicmdsts; + unsigned int pcielctlsts; + unsigned int ntctl; + + unsigned int ctl; + unsigned int sts; + + struct idt_ntb_bar bars[IDT_BAR_CNT]; +}; + +/* + * Descriptor of the IDT PCIe-switch partition specific parameters. + * @ctl: Partition control register in the Global Address Space + * @sts: Partition status register in the Global Address Space + * @msgctl: Messages control registers + */ +struct idt_ntb_part { + unsigned int ctl; + unsigned int sts; + unsigned int msgctl[IDT_MSG_CNT]; +}; + +#endif /* NTB_HW_IDT_H */ -- cgit v1.2.3-59-g8ed1b From e9410ff810f330d41dd69aecdd46fd7d4bb9c983 Mon Sep 17 00:00:00 2001 From: Gary R Hook Date: Tue, 9 May 2017 09:33:17 -0500 Subject: ntb: Add a module option to control affinity of DMA channels The DMA channel(s)/memory used to transfer data to an NTB device may not be required to be on the same node as the device. Add a module parameter that allows any candidate channel (aside from node assocation) and allocated memory to be used. Signed-off-by: Gary R Hook Acked-by: Dave Jiang Signed-off-by: Jon Mason --- drivers/ntb/test/ntb_perf.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c index 42756a98a728..0ec9f56f6999 100644 --- a/drivers/ntb/test/ntb_perf.c +++ b/drivers/ntb/test/ntb_perf.c @@ -101,6 +101,10 @@ static bool use_dma; /* default to 0 */ module_param(use_dma, bool, 0644); MODULE_PARM_DESC(use_dma, "Using DMA engine to measure performance"); +static bool on_node = true; /* default to 1 */ +module_param(on_node, bool, 0644); +MODULE_PARM_DESC(on_node, "Run threads only on NTB device node (default: true)"); + struct perf_mw { phys_addr_t phys_addr; resource_size_t phys_size; @@ -345,6 +349,10 @@ static int perf_move_data(struct pthr_ctx *pctx, char __iomem *dst, char *src, static bool perf_dma_filter_fn(struct dma_chan *chan, void *node) { + /* Is the channel required to be on the same node as the device? */ + if (!on_node) + return true; + return dev_to_node(&chan->dev->device) == (int)(unsigned long)node; } @@ -362,7 +370,7 @@ static int ntb_perf_thread(void *data) pr_debug("kthread %s starting...\n", current->comm); - node = dev_to_node(&pdev->dev); + node = on_node ? dev_to_node(&pdev->dev) : NUMA_NO_NODE; if (use_dma && !pctx->dma_chan) { dma_cap_mask_t dma_mask; @@ -682,7 +690,8 @@ static ssize_t debugfs_run_write(struct file *filp, const char __user *ubuf, pr_info("Fix run_order to %u\n", run_order); } - node = dev_to_node(&perf->ntb->pdev->dev); + node = on_node ? dev_to_node(&perf->ntb->pdev->dev) + : NUMA_NO_NODE; atomic_set(&perf->tdone, 0); /* launch kernel thread */ @@ -779,8 +788,7 @@ static int perf_probe(struct ntb_client *client, struct ntb_dev *ntb) if (ntb_peer_port_count(ntb) != NTB_DEF_PEER_CNT) dev_warn(&ntb->dev, "Multi-port NTB devices unsupported\n"); - node = dev_to_node(&pdev->dev); - + node = on_node ? dev_to_node(&pdev->dev) : NUMA_NO_NODE; perf = kzalloc_node(sizeof(*perf), GFP_KERNEL, node); if (!perf) { rc = -ENOMEM; -- cgit v1.2.3-59-g8ed1b From 0b93a6dbec96be880a3d58a683669b4a75beee1d Mon Sep 17 00:00:00 2001 From: Gary R Hook Date: Tue, 9 May 2017 09:33:28 -0500 Subject: ntb: Remove debug-fs variables from the context structure The Debug FS entries manage themselves; we don't need to hang onto them in the context structure. Signed-off-by: Gary R Hook Acked-by: Dave Jiang Signed-off-by: Jon Mason --- drivers/ntb/test/ntb_perf.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c index 0ec9f56f6999..60e0dd320aef 100644 --- a/drivers/ntb/test/ntb_perf.c +++ b/drivers/ntb/test/ntb_perf.c @@ -140,9 +140,6 @@ struct perf_ctx { bool link_is_up; struct delayed_work link_work; wait_queue_head_t link_wq; - struct dentry *debugfs_node_dir; - struct dentry *debugfs_run; - struct dentry *debugfs_threads; u8 perf_threads; /* mutex ensures only one set of threads run at once */ struct mutex run_mutex; @@ -737,6 +734,9 @@ static const struct file_operations ntb_perf_debugfs_run = { static int perf_debugfs_setup(struct perf_ctx *perf) { struct pci_dev *pdev = perf->ntb->pdev; + struct dentry *debugfs_node_dir; + struct dentry *debugfs_run; + struct dentry *debugfs_threads; if (!debugfs_initialized()) return -ENODEV; @@ -747,21 +747,21 @@ static int perf_debugfs_setup(struct perf_ctx *perf) return -ENODEV; } - perf->debugfs_node_dir = debugfs_create_dir(pci_name(pdev), - perf_debugfs_dir); - if (!perf->debugfs_node_dir) + debugfs_node_dir = debugfs_create_dir(pci_name(pdev), + perf_debugfs_dir); + if (!debugfs_node_dir) return -ENODEV; - perf->debugfs_run = debugfs_create_file("run", S_IRUSR | S_IWUSR, - perf->debugfs_node_dir, perf, - &ntb_perf_debugfs_run); - if (!perf->debugfs_run) + debugfs_run = debugfs_create_file("run", S_IRUSR | S_IWUSR, + debugfs_node_dir, perf, + &ntb_perf_debugfs_run); + if (!debugfs_run) return -ENODEV; - perf->debugfs_threads = debugfs_create_u8("threads", S_IRUSR | S_IWUSR, - perf->debugfs_node_dir, - &perf->perf_threads); - if (!perf->debugfs_threads) + debugfs_threads = debugfs_create_u8("threads", S_IRUSR | S_IWUSR, + debugfs_node_dir, + &perf->perf_threads); + if (!debugfs_threads) return -ENODEV; return 0; -- cgit v1.2.3-59-g8ed1b From 8407dd6c16c0d92432323c0ce8daecd13e424703 Mon Sep 17 00:00:00 2001 From: Gary R Hook Date: Tue, 9 May 2017 09:33:36 -0500 Subject: ntb: Add more debugfs support for ntb_perf testing options The ntb_perf tool uses module parameters to control the characteristics of its test. Enable the changing of these options through debugfs, and eliminating the need to unload and reload the module to make changes and run additional tests. Add a new module parameter that forces the DMA channel selection onto the same node as the NTB device (default: true). - seg_order: Size of the NTB memory window; power of 2. - run_order: Size of the data buffer; power of 2. - use_dma: Use DMA or memcpy? Default: 0. - on_node: Only use DMA channel(s) on the NTB node. Default: true. Signed-off-by: Gary R Hook Acked-by: Dave Jiang Signed-off-by: Jon Mason --- drivers/ntb/test/ntb_perf.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c index 60e0dd320aef..6fdddf86269e 100644 --- a/drivers/ntb/test/ntb_perf.c +++ b/drivers/ntb/test/ntb_perf.c @@ -737,6 +737,10 @@ static int perf_debugfs_setup(struct perf_ctx *perf) struct dentry *debugfs_node_dir; struct dentry *debugfs_run; struct dentry *debugfs_threads; + struct dentry *debugfs_seg_order; + struct dentry *debugfs_run_order; + struct dentry *debugfs_use_dma; + struct dentry *debugfs_on_node; if (!debugfs_initialized()) return -ENODEV; @@ -764,6 +768,30 @@ static int perf_debugfs_setup(struct perf_ctx *perf) if (!debugfs_threads) return -ENODEV; + debugfs_seg_order = debugfs_create_u32("seg_order", 0600, + debugfs_node_dir, + &seg_order); + if (!debugfs_seg_order) + return -ENODEV; + + debugfs_run_order = debugfs_create_u32("run_order", 0600, + debugfs_node_dir, + &run_order); + if (!debugfs_run_order) + return -ENODEV; + + debugfs_use_dma = debugfs_create_bool("use_dma", 0600, + debugfs_node_dir, + &use_dma); + if (!debugfs_use_dma) + return -ENODEV; + + debugfs_on_node = debugfs_create_bool("on_node", 0600, + debugfs_node_dir, + &on_node); + if (!debugfs_on_node) + return -ENODEV; + return 0; } -- cgit v1.2.3-59-g8ed1b From 32e0f5bfa5aa2a74264160e0990df3af125ca6e2 Mon Sep 17 00:00:00 2001 From: Gary R Hook Date: Mon, 15 May 2017 10:33:27 -0500 Subject: ntb: Add error path/handling to Debug FS entry creation If a failure occurs when creating Debug FS entries, unroll all of the work that's been done. Signed-off-by: Gary R Hook Acked-by: Dave Jiang Signed-off-by: Jon Mason --- drivers/ntb/test/ntb_perf.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c index 6fdddf86269e..759f772fa00c 100644 --- a/drivers/ntb/test/ntb_perf.c +++ b/drivers/ntb/test/ntb_perf.c @@ -745,6 +745,7 @@ static int perf_debugfs_setup(struct perf_ctx *perf) if (!debugfs_initialized()) return -ENODEV; + /* Assumpion: only one NTB device in the system */ if (!perf_debugfs_dir) { perf_debugfs_dir = debugfs_create_dir(KBUILD_MODNAME, NULL); if (!perf_debugfs_dir) @@ -754,45 +755,50 @@ static int perf_debugfs_setup(struct perf_ctx *perf) debugfs_node_dir = debugfs_create_dir(pci_name(pdev), perf_debugfs_dir); if (!debugfs_node_dir) - return -ENODEV; + goto err; debugfs_run = debugfs_create_file("run", S_IRUSR | S_IWUSR, debugfs_node_dir, perf, &ntb_perf_debugfs_run); if (!debugfs_run) - return -ENODEV; + goto err; debugfs_threads = debugfs_create_u8("threads", S_IRUSR | S_IWUSR, debugfs_node_dir, &perf->perf_threads); if (!debugfs_threads) - return -ENODEV; + goto err; debugfs_seg_order = debugfs_create_u32("seg_order", 0600, debugfs_node_dir, &seg_order); if (!debugfs_seg_order) - return -ENODEV; + goto err; debugfs_run_order = debugfs_create_u32("run_order", 0600, debugfs_node_dir, &run_order); if (!debugfs_run_order) - return -ENODEV; + goto err; debugfs_use_dma = debugfs_create_bool("use_dma", 0600, debugfs_node_dir, &use_dma); if (!debugfs_use_dma) - return -ENODEV; + goto err; debugfs_on_node = debugfs_create_bool("on_node", 0600, debugfs_node_dir, &on_node); if (!debugfs_on_node) - return -ENODEV; + goto err; return 0; + +err: + debugfs_remove_recursive(perf_debugfs_dir); + perf_debugfs_dir = NULL; + return -ENODEV; } static int perf_probe(struct ntb_client *client, struct ntb_dev *ntb) -- cgit v1.2.3-59-g8ed1b From 854b1dd9c39d8c8c8647a44de47ef18506ae11f9 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Mon, 5 Jun 2017 14:00:51 -0600 Subject: ntb_netdev: set the net_device's parent At present, ntb_netdev devices end up under /sys/devices/virtual/net completely unconnected to the ntb trees below them. This patch sets the parent of the net_device (using SET_NETDEV_DEV) to the client_dev device. This results in a better connected sysfs path for the network device: /sys/devices/pci0000:00/0000:00:03.0/0000:03:00.1/0000:03:00.1/ntb_netdev0/net/eth2 Signed-off-by: Logan Gunthorpe Acked-by: Allen Hubbe Signed-off-by: Jon Mason --- drivers/net/ntb_netdev.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c index 4daf3d0926a8..0250aa9ae2cb 100644 --- a/drivers/net/ntb_netdev.c +++ b/drivers/net/ntb_netdev.c @@ -418,6 +418,8 @@ static int ntb_netdev_probe(struct device *client_dev) if (!ndev) return -ENOMEM; + SET_NETDEV_DEV(ndev, client_dev); + dev = netdev_priv(ndev); dev->ndev = ndev; dev->pdev = pdev; -- cgit v1.2.3-59-g8ed1b From e48585dec2bd0183436437995e30d20dfa92f6aa Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 5 Jun 2017 17:57:33 +0200 Subject: rtc: ds1307: factor out century bit handling The driver has lots of places with chip-specific code what doesn't necessarily facilitate maintenance. Let's describe chip-specific differences in century bit handling in struct chip_desc to improve this. Signed-off-by: Heiner Kallweit Reviewed-by: Linus Walleij Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ds1307.c | 73 ++++++++++++++++++------------------------------ 1 file changed, 27 insertions(+), 46 deletions(-) diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index 9b4106a7e8e4..922675281b7a 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -136,6 +136,9 @@ struct chip_desc { unsigned alarm:1; u16 nvram_offset; u16 nvram_size; + u8 century_reg; + u8 century_enable_bit; + u8 century_bit; u16 trickle_charger_reg; u8 trickle_charger_setup; u8 (*do_trickle_setup)(struct ds1307 *, uint32_t, @@ -151,6 +154,8 @@ static struct chip_desc chips[last_ds_type] = { }, [ds_1337] = { .alarm = 1, + .century_reg = DS1307_REG_MONTH, + .century_bit = DS1337_BIT_CENTURY, }, [ds_1338] = { .nvram_offset = 8, @@ -158,10 +163,15 @@ static struct chip_desc chips[last_ds_type] = { }, [ds_1339] = { .alarm = 1, + .century_reg = DS1307_REG_MONTH, + .century_bit = DS1337_BIT_CENTURY, .trickle_charger_reg = 0x10, .do_trickle_setup = &do_trickle_setup_ds1339, }, [ds_1340] = { + .century_reg = DS1307_REG_HOUR, + .century_enable_bit = DS1340_BIT_CENTURY_EN, + .century_bit = DS1340_BIT_CENTURY, .trickle_charger_reg = 0x08, }, [ds_1388] = { @@ -169,6 +179,8 @@ static struct chip_desc chips[last_ds_type] = { }, [ds_3231] = { .alarm = 1, + .century_reg = DS1307_REG_MONTH, + .century_bit = DS1337_BIT_CENTURY, }, [rx_8130] = { .alarm = 1, @@ -328,6 +340,7 @@ static int ds1307_get_time(struct device *dev, struct rtc_time *t) { struct ds1307 *ds1307 = dev_get_drvdata(dev); int tmp, ret; + const struct chip_desc *chip = &chips[ds1307->type]; /* read the RTC date and time registers all at once */ ret = regmap_bulk_read(ds1307->regmap, ds1307->offset, ds1307->regs, 7); @@ -355,22 +368,9 @@ static int ds1307_get_time(struct device *dev, struct rtc_time *t) t->tm_mon = bcd2bin(tmp) - 1; t->tm_year = bcd2bin(ds1307->regs[DS1307_REG_YEAR]) + 100; -#ifdef CONFIG_RTC_DRV_DS1307_CENTURY - switch (ds1307->type) { - case ds_1337: - case ds_1339: - case ds_3231: - if (ds1307->regs[DS1307_REG_MONTH] & DS1337_BIT_CENTURY) - t->tm_year += 100; - break; - case ds_1340: - if (ds1307->regs[DS1307_REG_HOUR] & DS1340_BIT_CENTURY) - t->tm_year += 100; - break; - default: - break; - } -#endif + if (ds1307->regs[chip->century_reg] & chip->century_bit && + IS_ENABLED(CONFIG_RTC_DRV_DS1307_CENTURY)) + t->tm_year += 100; dev_dbg(dev, "%s secs=%d, mins=%d, " "hours=%d, mday=%d, mon=%d, year=%d, wday=%d\n", @@ -385,6 +385,7 @@ static int ds1307_get_time(struct device *dev, struct rtc_time *t) static int ds1307_set_time(struct device *dev, struct rtc_time *t) { struct ds1307 *ds1307 = dev_get_drvdata(dev); + const struct chip_desc *chip = &chips[ds1307->type]; int result; int tmp; u8 *buf = ds1307->regs; @@ -395,24 +396,14 @@ static int ds1307_set_time(struct device *dev, struct rtc_time *t) t->tm_hour, t->tm_mday, t->tm_mon, t->tm_year, t->tm_wday); -#ifdef CONFIG_RTC_DRV_DS1307_CENTURY if (t->tm_year < 100) return -EINVAL; - switch (ds1307->type) { - case ds_1337: - case ds_1339: - case ds_3231: - case ds_1340: - if (t->tm_year > 299) - return -EINVAL; - default: - if (t->tm_year > 199) - return -EINVAL; - break; - } +#ifdef CONFIG_RTC_DRV_DS1307_CENTURY + if (t->tm_year > (chip->century_bit ? 299 : 199)) + return -EINVAL; #else - if (t->tm_year < 100 || t->tm_year > 199) + if (t->tm_year > 199) return -EINVAL; #endif @@ -427,19 +418,12 @@ static int ds1307_set_time(struct device *dev, struct rtc_time *t) tmp = t->tm_year - 100; buf[DS1307_REG_YEAR] = bin2bcd(tmp); - switch (ds1307->type) { - case ds_1337: - case ds_1339: - case ds_3231: - if (t->tm_year > 199) - buf[DS1307_REG_MONTH] |= DS1337_BIT_CENTURY; - break; - case ds_1340: - buf[DS1307_REG_HOUR] |= DS1340_BIT_CENTURY_EN; - if (t->tm_year > 199) - buf[DS1307_REG_HOUR] |= DS1340_BIT_CENTURY; - break; - case mcp794xx: + if (chip->century_enable_bit) + buf[chip->century_reg] |= chip->century_enable_bit; + if (t->tm_year > 199 && chip->century_bit) + buf[chip->century_reg] |= chip->century_bit; + + if (ds1307->type == mcp794xx) { /* * these bits were cleared when preparing the date/time * values and need to be set again before writing the @@ -447,9 +431,6 @@ static int ds1307_set_time(struct device *dev, struct rtc_time *t) */ buf[DS1307_REG_SECS] |= MCP794XX_BIT_ST; buf[DS1307_REG_WDAY] |= MCP794XX_BIT_VBATEN; - break; - default: - break; } dev_dbg(dev, "%s: %7ph\n", "write", buf); -- cgit v1.2.3-59-g8ed1b From ac05fba39cc5a959e5d9ca24a059d884db0118a5 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 30 May 2017 09:53:30 +0200 Subject: rtc: gemini: Add optional clock handling This makes the Gemini optionally take two clock references to the PCLK and EXTCLK. As we are adding a clock framework to the Gemini platform we need to make sure that we get the right references. Acked-by: Hans Ulli Kroll Signed-off-by: Linus Walleij Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-gemini.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/drivers/rtc/rtc-gemini.c b/drivers/rtc/rtc-gemini.c index 5279390bb42d..cf766e01832a 100644 --- a/drivers/rtc/rtc-gemini.c +++ b/drivers/rtc/rtc-gemini.c @@ -26,6 +26,7 @@ #include #include #include +#include #define DRV_NAME "rtc-gemini" @@ -38,6 +39,8 @@ struct gemini_rtc { struct rtc_device *rtc_dev; void __iomem *rtc_base; int rtc_irq; + struct clk *pclk; + struct clk *extclk; }; enum gemini_rtc_offsets { @@ -127,6 +130,27 @@ static int gemini_rtc_probe(struct platform_device *pdev) return -ENOMEM; platform_set_drvdata(pdev, rtc); + rtc->pclk = devm_clk_get(dev, "PCLK"); + if (IS_ERR(rtc->pclk)) { + dev_err(dev, "could not get PCLK\n"); + } else { + ret = clk_prepare_enable(rtc->pclk); + if (ret) { + dev_err(dev, "failed to enable PCLK\n"); + return ret; + } + } + rtc->extclk = devm_clk_get(dev, "EXTCLK"); + if (IS_ERR(rtc->extclk)) { + dev_err(dev, "could not get EXTCLK\n"); + } else { + ret = clk_prepare_enable(rtc->extclk); + if (ret) { + dev_err(dev, "failed to enable EXTCLK\n"); + return ret; + } + } + res = platform_get_resource(pdev, IORESOURCE_IRQ, 0); if (!res) return -ENODEV; @@ -156,6 +180,10 @@ static int gemini_rtc_remove(struct platform_device *pdev) { struct gemini_rtc *rtc = platform_get_drvdata(pdev); + if (!IS_ERR(rtc->extclk)) + clk_disable_unprepare(rtc->extclk); + if (!IS_ERR(rtc->pclk)) + clk_disable_unprepare(rtc->pclk); rtc_device_unregister(rtc->rtc_dev); return 0; -- cgit v1.2.3-59-g8ed1b From 7f1e988dffbd808ad17f22b6b88a9aa42ebe739a Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 30 May 2017 09:53:31 +0200 Subject: rtc: gemini: Augment DT bindings for Faraday The Gemini RTC is actually a standard IP block from Faraday Technology called FTRTC010. Rename the bindings, add the generic compatible string and add definitions for the two available clocks. Cc: devicetree@vger.kernel.org Cc: Po-Yu Chuang Acked-by: Rob Herring Signed-off-by: Linus Walleij Signed-off-by: Alexandre Belloni --- .../devicetree/bindings/rtc/cortina,gemini.txt | 14 ----------- .../devicetree/bindings/rtc/faraday,ftrtc010.txt | 28 ++++++++++++++++++++++ 2 files changed, 28 insertions(+), 14 deletions(-) delete mode 100644 Documentation/devicetree/bindings/rtc/cortina,gemini.txt create mode 100644 Documentation/devicetree/bindings/rtc/faraday,ftrtc010.txt diff --git a/Documentation/devicetree/bindings/rtc/cortina,gemini.txt b/Documentation/devicetree/bindings/rtc/cortina,gemini.txt deleted file mode 100644 index 4ce4e794ddbb..000000000000 --- a/Documentation/devicetree/bindings/rtc/cortina,gemini.txt +++ /dev/null @@ -1,14 +0,0 @@ -* Cortina Systems Gemini RTC - -Gemini SoC real-time clock. - -Required properties: -- compatible : Should be "cortina,gemini-rtc" - -Examples: - -rtc@45000000 { - compatible = "cortina,gemini-rtc"; - reg = <0x45000000 0x100>; - interrupts = <17 IRQ_TYPE_LEVEL_HIGH>; -}; diff --git a/Documentation/devicetree/bindings/rtc/faraday,ftrtc010.txt b/Documentation/devicetree/bindings/rtc/faraday,ftrtc010.txt new file mode 100644 index 000000000000..e3938f5e0b6c --- /dev/null +++ b/Documentation/devicetree/bindings/rtc/faraday,ftrtc010.txt @@ -0,0 +1,28 @@ +* Faraday Technology FTRTC010 Real Time Clock + +This RTC appears in for example the Storlink Gemini family of +SoCs. + +Required properties: +- compatible : Should be one of: + "faraday,ftrtc010" + "cortina,gemini-rtc", "faraday,ftrtc010" + +Optional properties: +- clocks: when present should contain clock references to the + PCLK and EXTCLK clocks. Faraday calls the later CLK1HZ and + says the clock should be 1 Hz, but implementers actually seem + to choose different clocks here, like Cortina who chose + 32768 Hz (a typical low-power clock). +- clock-names: should name the clocks "PCLK" and "EXTCLK" + respectively. + +Examples: + +rtc@45000000 { + compatible = "cortina,gemini-rtc"; + reg = <0x45000000 0x100>; + interrupts = <17 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&foo 0>, <&foo 1>; + clock-names = "PCLK", "EXTCLK"; +}; -- cgit v1.2.3-59-g8ed1b From 1d61d2592c1f70d74112ed1ee8f182694dc43c48 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 30 May 2017 09:53:32 +0200 Subject: rtc: gemini/ftrtc010: rename driver and symbols The Gemini RTC is actually a generic IP block from Faraday Technology names FTRTC010. Rename the driver file and all symbols to match this IP name. The relationship can be clearly seen in the U-Boot driver posted by Po-Yu Chuang for the Faraday A320 board: https://lists.denx.de/pipermail/u-boot/2009-September/061326.html Remove the dependency on ARCH_GEMINI but select the driver for ARCH_GEMINI so we get a smooth transition. The IP block is synthsized on different silicon and architectures. Cc: Po-Yu Chuang Acked-by: Hans Ulli Kroll Signed-off-by: Linus Walleij Signed-off-by: Alexandre Belloni --- MAINTAINERS | 2 +- drivers/rtc/Kconfig | 10 +-- drivers/rtc/Makefile | 2 +- drivers/rtc/rtc-ftrtc010.c | 208 +++++++++++++++++++++++++++++++++++++++++++++ drivers/rtc/rtc-gemini.c | 207 -------------------------------------------- 5 files changed, 215 insertions(+), 214 deletions(-) create mode 100644 drivers/rtc/rtc-ftrtc010.c delete mode 100644 drivers/rtc/rtc-gemini.c diff --git a/MAINTAINERS b/MAINTAINERS index f7d568b8f133..c6f0f412b32e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1226,7 +1226,7 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) T: git git://github.com/ulli-kroll/linux.git S: Maintained F: arch/arm/mach-gemini/ -F: drivers/rtc/rtc-gemini.c +F: drivers/rtc/rtc-ftrtc010.c ARM/CSR SIRFPRIMA2 MACHINE SUPPORT M: Barry Song diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index 8e1aa67fe533..0e5044cd84dd 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -1495,16 +1495,16 @@ config RTC_DRV_ARMADA38X This driver can also be built as a module. If so, the module will be called armada38x-rtc. -config RTC_DRV_GEMINI - tristate "Gemini SoC RTC" - depends on ARCH_GEMINI || COMPILE_TEST +config RTC_DRV_FTRTC010 + tristate "Faraday Technology FTRTC010 RTC" depends on HAS_IOMEM + default ARCH_GEMINI help If you say Y here you will get support for the - RTC found on Gemini SoC's. + Faraday Technolog FTRTC010 found on e.g. Gemini SoC's. This driver can also be built as a module. If so, the module - will be called rtc-gemini. + will be called rtc-ftrtc010. config RTC_DRV_PS3 tristate "PS3 RTC" diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile index df89cac1f9ae..4050fc8b9271 100644 --- a/drivers/rtc/Makefile +++ b/drivers/rtc/Makefile @@ -68,7 +68,7 @@ obj-$(CONFIG_RTC_DRV_EFI) += rtc-efi.o obj-$(CONFIG_RTC_DRV_EM3027) += rtc-em3027.o obj-$(CONFIG_RTC_DRV_EP93XX) += rtc-ep93xx.o obj-$(CONFIG_RTC_DRV_FM3130) += rtc-fm3130.o -obj-$(CONFIG_RTC_DRV_GEMINI) += rtc-gemini.o +obj-$(CONFIG_RTC_DRV_FTRTC010) += rtc-ftrtc010.o obj-$(CONFIG_RTC_DRV_GENERIC) += rtc-generic.o obj-$(CONFIG_RTC_DRV_HID_SENSOR_TIME) += rtc-hid-sensor-time.o obj-$(CONFIG_RTC_DRV_HYM8563) += rtc-hym8563.o diff --git a/drivers/rtc/rtc-ftrtc010.c b/drivers/rtc/rtc-ftrtc010.c new file mode 100644 index 000000000000..af8d6beae20c --- /dev/null +++ b/drivers/rtc/rtc-ftrtc010.c @@ -0,0 +1,208 @@ +/* + * Faraday Technology FTRTC010 driver + * + * Copyright (C) 2009 Janos Laube + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Original code for older kernel 2.6.15 are from Stormlinksemi + * first update from Janos Laube for > 2.6.29 kernels + * + * checkpatch fixes and usage of rtc-lib code + * Hans Ulli Kroll + */ + +#include +#include +#include +#include +#include +#include +#include + +#define DRV_NAME "rtc-ftrtc010" + +MODULE_AUTHOR("Hans Ulli Kroll "); +MODULE_DESCRIPTION("RTC driver for Gemini SoC"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:" DRV_NAME); + +struct ftrtc010_rtc { + struct rtc_device *rtc_dev; + void __iomem *rtc_base; + int rtc_irq; + struct clk *pclk; + struct clk *extclk; +}; + +enum ftrtc010_rtc_offsets { + FTRTC010_RTC_SECOND = 0x00, + FTRTC010_RTC_MINUTE = 0x04, + FTRTC010_RTC_HOUR = 0x08, + FTRTC010_RTC_DAYS = 0x0C, + FTRTC010_RTC_ALARM_SECOND = 0x10, + FTRTC010_RTC_ALARM_MINUTE = 0x14, + FTRTC010_RTC_ALARM_HOUR = 0x18, + FTRTC010_RTC_RECORD = 0x1C, + FTRTC010_RTC_CR = 0x20, +}; + +static irqreturn_t ftrtc010_rtc_interrupt(int irq, void *dev) +{ + return IRQ_HANDLED; +} + +/* + * Looks like the RTC in the Gemini SoC is (totaly) broken + * We can't read/write directly the time from RTC registers. + * We must do some "offset" calculation to get the real time + * + * This FIX works pretty fine and Stormlinksemi aka Cortina-Networks does + * the same thing, without the rtc-lib.c calls. + */ + +static int ftrtc010_rtc_read_time(struct device *dev, struct rtc_time *tm) +{ + struct ftrtc010_rtc *rtc = dev_get_drvdata(dev); + + unsigned int days, hour, min, sec; + unsigned long offset, time; + + sec = readl(rtc->rtc_base + FTRTC010_RTC_SECOND); + min = readl(rtc->rtc_base + FTRTC010_RTC_MINUTE); + hour = readl(rtc->rtc_base + FTRTC010_RTC_HOUR); + days = readl(rtc->rtc_base + FTRTC010_RTC_DAYS); + offset = readl(rtc->rtc_base + FTRTC010_RTC_RECORD); + + time = offset + days * 86400 + hour * 3600 + min * 60 + sec; + + rtc_time_to_tm(time, tm); + + return 0; +} + +static int ftrtc010_rtc_set_time(struct device *dev, struct rtc_time *tm) +{ + struct ftrtc010_rtc *rtc = dev_get_drvdata(dev); + unsigned int sec, min, hour, day; + unsigned long offset, time; + + if (tm->tm_year >= 2148) /* EPOCH Year + 179 */ + return -EINVAL; + + rtc_tm_to_time(tm, &time); + + sec = readl(rtc->rtc_base + FTRTC010_RTC_SECOND); + min = readl(rtc->rtc_base + FTRTC010_RTC_MINUTE); + hour = readl(rtc->rtc_base + FTRTC010_RTC_HOUR); + day = readl(rtc->rtc_base + FTRTC010_RTC_DAYS); + + offset = time - (day * 86400 + hour * 3600 + min * 60 + sec); + + writel(offset, rtc->rtc_base + FTRTC010_RTC_RECORD); + writel(0x01, rtc->rtc_base + FTRTC010_RTC_CR); + + return 0; +} + +static const struct rtc_class_ops ftrtc010_rtc_ops = { + .read_time = ftrtc010_rtc_read_time, + .set_time = ftrtc010_rtc_set_time, +}; + +static int ftrtc010_rtc_probe(struct platform_device *pdev) +{ + struct ftrtc010_rtc *rtc; + struct device *dev = &pdev->dev; + struct resource *res; + int ret; + + rtc = devm_kzalloc(&pdev->dev, sizeof(*rtc), GFP_KERNEL); + if (unlikely(!rtc)) + return -ENOMEM; + platform_set_drvdata(pdev, rtc); + + rtc->pclk = devm_clk_get(dev, "PCLK"); + if (IS_ERR(rtc->pclk)) { + dev_err(dev, "could not get PCLK\n"); + } else { + ret = clk_prepare_enable(rtc->pclk); + if (ret) { + dev_err(dev, "failed to enable PCLK\n"); + return ret; + } + } + rtc->extclk = devm_clk_get(dev, "EXTCLK"); + if (IS_ERR(rtc->extclk)) { + dev_err(dev, "could not get EXTCLK\n"); + } else { + ret = clk_prepare_enable(rtc->extclk); + if (ret) { + dev_err(dev, "failed to enable EXTCLK\n"); + return ret; + } + } + + res = platform_get_resource(pdev, IORESOURCE_IRQ, 0); + if (!res) + return -ENODEV; + + rtc->rtc_irq = res->start; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) + return -ENODEV; + + rtc->rtc_base = devm_ioremap(dev, res->start, + resource_size(res)); + if (!rtc->rtc_base) + return -ENOMEM; + + ret = devm_request_irq(dev, rtc->rtc_irq, ftrtc010_rtc_interrupt, + IRQF_SHARED, pdev->name, dev); + if (unlikely(ret)) + return ret; + + rtc->rtc_dev = rtc_device_register(pdev->name, dev, + &ftrtc010_rtc_ops, THIS_MODULE); + return PTR_ERR_OR_ZERO(rtc->rtc_dev); +} + +static int ftrtc010_rtc_remove(struct platform_device *pdev) +{ + struct ftrtc010_rtc *rtc = platform_get_drvdata(pdev); + + if (!IS_ERR(rtc->extclk)) + clk_disable_unprepare(rtc->extclk); + if (!IS_ERR(rtc->pclk)) + clk_disable_unprepare(rtc->pclk); + rtc_device_unregister(rtc->rtc_dev); + + return 0; +} + +static const struct of_device_id ftrtc010_rtc_dt_match[] = { + { .compatible = "cortina,gemini-rtc" }, + { .compatible = "faraday,ftrtc010" }, + { } +}; +MODULE_DEVICE_TABLE(of, ftrtc010_rtc_dt_match); + +static struct platform_driver ftrtc010_rtc_driver = { + .driver = { + .name = DRV_NAME, + .of_match_table = ftrtc010_rtc_dt_match, + }, + .probe = ftrtc010_rtc_probe, + .remove = ftrtc010_rtc_remove, +}; + +module_platform_driver_probe(ftrtc010_rtc_driver, ftrtc010_rtc_probe); diff --git a/drivers/rtc/rtc-gemini.c b/drivers/rtc/rtc-gemini.c deleted file mode 100644 index cf766e01832a..000000000000 --- a/drivers/rtc/rtc-gemini.c +++ /dev/null @@ -1,207 +0,0 @@ -/* - * Gemini OnChip RTC - * - * Copyright (C) 2009 Janos Laube - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * Original code for older kernel 2.6.15 are from Stormlinksemi - * first update from Janos Laube for > 2.6.29 kernels - * - * checkpatch fixes and usage of rtc-lib code - * Hans Ulli Kroll - */ - -#include -#include -#include -#include -#include -#include -#include - -#define DRV_NAME "rtc-gemini" - -MODULE_AUTHOR("Hans Ulli Kroll "); -MODULE_DESCRIPTION("RTC driver for Gemini SoC"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform:" DRV_NAME); - -struct gemini_rtc { - struct rtc_device *rtc_dev; - void __iomem *rtc_base; - int rtc_irq; - struct clk *pclk; - struct clk *extclk; -}; - -enum gemini_rtc_offsets { - GEMINI_RTC_SECOND = 0x00, - GEMINI_RTC_MINUTE = 0x04, - GEMINI_RTC_HOUR = 0x08, - GEMINI_RTC_DAYS = 0x0C, - GEMINI_RTC_ALARM_SECOND = 0x10, - GEMINI_RTC_ALARM_MINUTE = 0x14, - GEMINI_RTC_ALARM_HOUR = 0x18, - GEMINI_RTC_RECORD = 0x1C, - GEMINI_RTC_CR = 0x20 -}; - -static irqreturn_t gemini_rtc_interrupt(int irq, void *dev) -{ - return IRQ_HANDLED; -} - -/* - * Looks like the RTC in the Gemini SoC is (totaly) broken - * We can't read/write directly the time from RTC registers. - * We must do some "offset" calculation to get the real time - * - * This FIX works pretty fine and Stormlinksemi aka Cortina-Networks does - * the same thing, without the rtc-lib.c calls. - */ - -static int gemini_rtc_read_time(struct device *dev, struct rtc_time *tm) -{ - struct gemini_rtc *rtc = dev_get_drvdata(dev); - - unsigned int days, hour, min, sec; - unsigned long offset, time; - - sec = readl(rtc->rtc_base + GEMINI_RTC_SECOND); - min = readl(rtc->rtc_base + GEMINI_RTC_MINUTE); - hour = readl(rtc->rtc_base + GEMINI_RTC_HOUR); - days = readl(rtc->rtc_base + GEMINI_RTC_DAYS); - offset = readl(rtc->rtc_base + GEMINI_RTC_RECORD); - - time = offset + days * 86400 + hour * 3600 + min * 60 + sec; - - rtc_time_to_tm(time, tm); - - return 0; -} - -static int gemini_rtc_set_time(struct device *dev, struct rtc_time *tm) -{ - struct gemini_rtc *rtc = dev_get_drvdata(dev); - unsigned int sec, min, hour, day; - unsigned long offset, time; - - if (tm->tm_year >= 2148) /* EPOCH Year + 179 */ - return -EINVAL; - - rtc_tm_to_time(tm, &time); - - sec = readl(rtc->rtc_base + GEMINI_RTC_SECOND); - min = readl(rtc->rtc_base + GEMINI_RTC_MINUTE); - hour = readl(rtc->rtc_base + GEMINI_RTC_HOUR); - day = readl(rtc->rtc_base + GEMINI_RTC_DAYS); - - offset = time - (day * 86400 + hour * 3600 + min * 60 + sec); - - writel(offset, rtc->rtc_base + GEMINI_RTC_RECORD); - writel(0x01, rtc->rtc_base + GEMINI_RTC_CR); - - return 0; -} - -static const struct rtc_class_ops gemini_rtc_ops = { - .read_time = gemini_rtc_read_time, - .set_time = gemini_rtc_set_time, -}; - -static int gemini_rtc_probe(struct platform_device *pdev) -{ - struct gemini_rtc *rtc; - struct device *dev = &pdev->dev; - struct resource *res; - int ret; - - rtc = devm_kzalloc(&pdev->dev, sizeof(*rtc), GFP_KERNEL); - if (unlikely(!rtc)) - return -ENOMEM; - platform_set_drvdata(pdev, rtc); - - rtc->pclk = devm_clk_get(dev, "PCLK"); - if (IS_ERR(rtc->pclk)) { - dev_err(dev, "could not get PCLK\n"); - } else { - ret = clk_prepare_enable(rtc->pclk); - if (ret) { - dev_err(dev, "failed to enable PCLK\n"); - return ret; - } - } - rtc->extclk = devm_clk_get(dev, "EXTCLK"); - if (IS_ERR(rtc->extclk)) { - dev_err(dev, "could not get EXTCLK\n"); - } else { - ret = clk_prepare_enable(rtc->extclk); - if (ret) { - dev_err(dev, "failed to enable EXTCLK\n"); - return ret; - } - } - - res = platform_get_resource(pdev, IORESOURCE_IRQ, 0); - if (!res) - return -ENODEV; - - rtc->rtc_irq = res->start; - - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) - return -ENODEV; - - rtc->rtc_base = devm_ioremap(dev, res->start, - resource_size(res)); - if (!rtc->rtc_base) - return -ENOMEM; - - ret = devm_request_irq(dev, rtc->rtc_irq, gemini_rtc_interrupt, - IRQF_SHARED, pdev->name, dev); - if (unlikely(ret)) - return ret; - - rtc->rtc_dev = rtc_device_register(pdev->name, dev, - &gemini_rtc_ops, THIS_MODULE); - return PTR_ERR_OR_ZERO(rtc->rtc_dev); -} - -static int gemini_rtc_remove(struct platform_device *pdev) -{ - struct gemini_rtc *rtc = platform_get_drvdata(pdev); - - if (!IS_ERR(rtc->extclk)) - clk_disable_unprepare(rtc->extclk); - if (!IS_ERR(rtc->pclk)) - clk_disable_unprepare(rtc->pclk); - rtc_device_unregister(rtc->rtc_dev); - - return 0; -} - -static const struct of_device_id gemini_rtc_dt_match[] = { - { .compatible = "cortina,gemini-rtc" }, - { } -}; -MODULE_DEVICE_TABLE(of, gemini_rtc_dt_match); - -static struct platform_driver gemini_rtc_driver = { - .driver = { - .name = DRV_NAME, - .of_match_table = gemini_rtc_dt_match, - }, - .probe = gemini_rtc_probe, - .remove = gemini_rtc_remove, -}; - -module_platform_driver_probe(gemini_rtc_driver, gemini_rtc_probe); -- cgit v1.2.3-59-g8ed1b From d0a67c372df410b579197ea818596001fe20070d Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 23 Jun 2017 11:29:00 +0300 Subject: rtc: rtc-nuc900: fix loop timeout test We should change this post-op to a pre-op because we want the loop to exit with "timeout" set to zero. Fixes: 0a89b55364e0 ("nuc900/rtc: change the waiting for device ready implement") Signed-off-by: Dan Carpenter Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-nuc900.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-nuc900.c b/drivers/rtc/rtc-nuc900.c index b1b6b3041bfb..4ed81117cf5f 100644 --- a/drivers/rtc/rtc-nuc900.c +++ b/drivers/rtc/rtc-nuc900.c @@ -93,7 +93,7 @@ static int *check_rtc_access_enable(struct nuc900_rtc *nuc900_rtc) __raw_writel(AERPOWERON, nuc900_rtc->rtc_reg + REG_RTC_AER); while (!(__raw_readl(nuc900_rtc->rtc_reg + REG_RTC_AER) & AERRWENB) - && timeout--) + && --timeout) mdelay(1); if (!timeout) -- cgit v1.2.3-59-g8ed1b From c35c4195f919a077ce106ec84cfcecbb0b67db30 Mon Sep 17 00:00:00 2001 From: Kirill Esipov Date: Wed, 28 Jun 2017 14:29:09 +0300 Subject: rtc: ds3232: add temperature support DS3232/DS3234 has the temperature registers with a resolution of 0.25 degree celsius. This enables to get the value through hwmon. # cat /sys/class/hwmon/hwmon0/temp1_input 37250 Signed-off-by: Kirill Esipov Signed-off-by: Alexandre Belloni --- drivers/rtc/Kconfig | 8 ++++ drivers/rtc/rtc-ds3232.c | 119 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 127 insertions(+) diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index 0e5044cd84dd..d0e4b4a1c2a1 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -802,6 +802,14 @@ config RTC_DRV_DS3232 This driver can also be built as a module. If so, the module will be called rtc-ds3232. +config RTC_DRV_DS3232_HWMON + bool "HWMON support for Dallas/Maxim DS3232/DS3234" + depends on RTC_DRV_DS3232 && HWMON && !(RTC_DRV_DS3232=y && HWMON=m) + default y + help + Say Y here if you want to expose temperature sensor data on + rtc-ds3232 + config RTC_DRV_PCF2127 tristate "NXP PCF2127" depends on RTC_I2C_AND_SPI diff --git a/drivers/rtc/rtc-ds3232.c b/drivers/rtc/rtc-ds3232.c index deff431a37c4..0550f7ba464f 100644 --- a/drivers/rtc/rtc-ds3232.c +++ b/drivers/rtc/rtc-ds3232.c @@ -22,6 +22,7 @@ #include #include #include +#include #define DS3232_REG_SECONDS 0x00 #define DS3232_REG_MINUTES 0x01 @@ -46,6 +47,8 @@ # define DS3232_REG_SR_A2F 0x02 # define DS3232_REG_SR_A1F 0x01 +#define DS3232_REG_TEMPERATURE 0x11 + struct ds3232 { struct device *dev; struct regmap *regmap; @@ -275,6 +278,120 @@ static int ds3232_update_alarm(struct device *dev, unsigned int enabled) return ret; } +/* + * Temperature sensor support for ds3232/ds3234 devices. + * A user-initiated temperature conversion is not started by this function, + * so the temperature is updated once every 64 seconds. + */ +static int ds3232_hwmon_read_temp(struct device *dev, long int *mC) +{ + struct ds3232 *ds3232 = dev_get_drvdata(dev); + u8 temp_buf[2]; + s16 temp; + int ret; + + ret = regmap_bulk_read(ds3232->regmap, DS3232_REG_TEMPERATURE, temp_buf, + sizeof(temp_buf)); + if (ret < 0) + return ret; + + /* + * Temperature is represented as a 10-bit code with a resolution of + * 0.25 degree celsius and encoded in two's complement format. + */ + temp = (temp_buf[0] << 8) | temp_buf[1]; + temp >>= 6; + *mC = temp * 250; + + return 0; +} + +static umode_t ds3232_hwmon_is_visible(const void *data, + enum hwmon_sensor_types type, + u32 attr, int channel) +{ + if (type != hwmon_temp) + return 0; + + switch (attr) { + case hwmon_temp_input: + return 0444; + default: + return 0; + } +} + +static int ds3232_hwmon_read(struct device *dev, + enum hwmon_sensor_types type, + u32 attr, int channel, long *temp) +{ + int err; + + switch (attr) { + case hwmon_temp_input: + err = ds3232_hwmon_read_temp(dev, temp); + break; + default: + err = -EOPNOTSUPP; + break; + } + + return err; +} + +static u32 ds3232_hwmon_chip_config[] = { + HWMON_C_REGISTER_TZ, + 0 +}; + +static const struct hwmon_channel_info ds3232_hwmon_chip = { + .type = hwmon_chip, + .config = ds3232_hwmon_chip_config, +}; + +static u32 ds3232_hwmon_temp_config[] = { + HWMON_T_INPUT, + 0 +}; + +static const struct hwmon_channel_info ds3232_hwmon_temp = { + .type = hwmon_temp, + .config = ds3232_hwmon_temp_config, +}; + +static const struct hwmon_channel_info *ds3232_hwmon_info[] = { + &ds3232_hwmon_chip, + &ds3232_hwmon_temp, + NULL +}; + +static const struct hwmon_ops ds3232_hwmon_hwmon_ops = { + .is_visible = ds3232_hwmon_is_visible, + .read = ds3232_hwmon_read, +}; + +static const struct hwmon_chip_info ds3232_hwmon_chip_info = { + .ops = &ds3232_hwmon_hwmon_ops, + .info = ds3232_hwmon_info, +}; + +static void ds3232_hwmon_register(struct device *dev, const char *name) +{ + struct ds3232 *ds3232 = dev_get_drvdata(dev); + struct device *hwmon_dev; + + if (!IS_ENABLED(CONFIG_RTC_DRV_DS3232_HWMON)) + return; + + hwmon_dev = devm_hwmon_device_register_with_info(dev, name, ds3232, + &ds3232_hwmon_chip_info, + NULL); + if (IS_ERR(hwmon_dev)) { + dev_err(dev, "unable to register hwmon device %ld\n", + PTR_ERR(hwmon_dev)); + } +} + static int ds3232_alarm_irq_enable(struct device *dev, unsigned int enabled) { struct ds3232 *ds3232 = dev_get_drvdata(dev); @@ -366,6 +483,8 @@ static int ds3232_probe(struct device *dev, struct regmap *regmap, int irq, if (ds3232->irq > 0) device_init_wakeup(dev, 1); + ds3232_hwmon_register(dev, name); + ds3232->rtc = devm_rtc_device_register(dev, name, &ds3232_rtc_ops, THIS_MODULE); if (IS_ERR(ds3232->rtc)) -- cgit v1.2.3-59-g8ed1b From 300a7735becf55f7fd18f8cd3dc3b945a0cab712 Mon Sep 17 00:00:00 2001 From: Sean Nyekjaer Date: Thu, 8 Jun 2017 12:36:54 +0200 Subject: rtc: ds1307: add ds1308 variant The ds1308 variant is very similar to the already supported ds1338 variant, it have more debug registers and a square wave clock output. Signed-off-by: Sean Nyekjaer Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ds1307.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index 922675281b7a..57ea25400ecd 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -34,6 +34,7 @@ */ enum ds_type { ds_1307, + ds_1308, ds_1337, ds_1338, ds_1339, @@ -152,6 +153,10 @@ static struct chip_desc chips[last_ds_type] = { .nvram_offset = 8, .nvram_size = 56, }, + [ds_1308] = { + .nvram_offset = 8, + .nvram_size = 56, + }, [ds_1337] = { .alarm = 1, .century_reg = DS1307_REG_MONTH, @@ -198,6 +203,7 @@ static struct chip_desc chips[last_ds_type] = { static const struct i2c_device_id ds1307_id[] = { { "ds1307", ds_1307 }, + { "ds1308", ds_1308 }, { "ds1337", ds_1337 }, { "ds1338", ds_1338 }, { "ds1339", ds_1339 }, @@ -222,6 +228,10 @@ static const struct of_device_id ds1307_of_match[] = { .compatible = "dallas,ds1307", .data = (void *)ds_1307 }, + { + .compatible = "dallas,ds1308", + .data = (void *)ds_1308 + }, { .compatible = "dallas,ds1337", .data = (void *)ds_1337 @@ -282,6 +292,7 @@ MODULE_DEVICE_TABLE(of, ds1307_of_match); #ifdef CONFIG_ACPI static const struct acpi_device_id ds1307_acpi_ids[] = { { .id = "DS1307", .driver_data = ds_1307 }, + { .id = "DS1308", .driver_data = ds_1308 }, { .id = "DS1337", .driver_data = ds_1337 }, { .id = "DS1338", .driver_data = ds_1338 }, { .id = "DS1339", .driver_data = ds_1339 }, @@ -1558,6 +1569,7 @@ read_rtc: goto read_rtc; } break; + case ds_1308: case ds_1338: /* clock halted? turn it on, so clock can tick. */ if (tmp & DS1307_BIT_CH) -- cgit v1.2.3-59-g8ed1b From d2be279bcd8055ddfd92cc5f5d305eb3651e059b Mon Sep 17 00:00:00 2001 From: Amelie Delaunay Date: Thu, 6 Jul 2017 10:47:44 +0200 Subject: dt-bindings: rtc: stm32: add support for STM32H7 This patch documents support for STM32H7 Real Time Clock. It introduces a new compatible and rework clock definitions. On STM32H7 we have a 'pclk' clock for register access, in addition to the 'rtc_ck' clock. Acked-by: Rob Herring Signed-off-by: Amelie Delaunay Signed-off-by: Alexandre Belloni --- .../devicetree/bindings/rtc/st,stm32-rtc.txt | 32 ++++++++++++++++++---- 1 file changed, 27 insertions(+), 5 deletions(-) diff --git a/Documentation/devicetree/bindings/rtc/st,stm32-rtc.txt b/Documentation/devicetree/bindings/rtc/st,stm32-rtc.txt index e2837b951237..0a4c371a9b7a 100644 --- a/Documentation/devicetree/bindings/rtc/st,stm32-rtc.txt +++ b/Documentation/devicetree/bindings/rtc/st,stm32-rtc.txt @@ -1,17 +1,25 @@ STM32 Real Time Clock Required properties: -- compatible: "st,stm32-rtc". +- compatible: can be either "st,stm32-rtc" or "st,stm32h7-rtc", depending on + the device is compatible with stm32(f4/f7) or stm32h7. - reg: address range of rtc register set. -- clocks: reference to the clock entry ck_rtc. +- clocks: can use up to two clocks, depending on part used: + - "rtc_ck": RTC clock source. + It is required on stm32(f4/f7) and stm32h7. + - "pclk": RTC APB interface clock. + It is not present on stm32(f4/f7). + It is required on stm32h7. +- clock-names: must be "rtc_ck" and "pclk". + It is required only on stm32h7. - interrupt-parent: phandle for the interrupt controller. - interrupts: rtc alarm interrupt. - st,syscfg: phandle for pwrcfg, mandatory to disable/enable backup domain (RTC registers) write protection. -Optional properties (to override default ck_rtc parent clock): -- assigned-clocks: reference to the ck_rtc clock entry. -- assigned-clock-parents: phandle of the new parent clock of ck_rtc. +Optional properties (to override default rtc_ck parent clock): +- assigned-clocks: reference to the rtc_ck clock entry. +- assigned-clock-parents: phandle of the new parent clock of rtc_ck. Example: @@ -25,3 +33,17 @@ Example: interrupts = <17 1>; st,syscfg = <&pwrcfg>; }; + + rtc: rtc@58004000 { + compatible = "st,stm32h7-rtc"; + reg = <0x58004000 0x400>; + clocks = <&rcc RTCAPB_CK>, <&rcc RTC_CK>; + clock-names = "pclk", "rtc_ck"; + assigned-clocks = <&rcc RTC_CK>; + assigned-clock-parents = <&rcc LSE_CK>; + interrupt-parent = <&exti>; + interrupts = <17 1>; + interrupt-names = "alarm"; + st,syscfg = <&pwrcfg>; + status = "disabled"; + }; -- cgit v1.2.3-59-g8ed1b From 9a6757eadc14f01385fd41fe3906dc22dcdb919e Mon Sep 17 00:00:00 2001 From: Amelie Delaunay Date: Thu, 6 Jul 2017 10:47:45 +0200 Subject: rtc: stm32: add STM32H7 RTC support This patch adds support for STM32H7 RTC. On STM32H7, the RTC bus interface clock (APB clock) needs to be enabled. Signed-off-by: Amelie Delaunay Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-stm32.c | 82 +++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 65 insertions(+), 17 deletions(-) diff --git a/drivers/rtc/rtc-stm32.c b/drivers/rtc/rtc-stm32.c index bd57eb1029e1..3a5c3d7d0c77 100644 --- a/drivers/rtc/rtc-stm32.c +++ b/drivers/rtc/rtc-stm32.c @@ -94,11 +94,17 @@ /* STM32_PWR_CR bit field */ #define PWR_CR_DBP BIT(8) +struct stm32_rtc_data { + bool has_pclk; +}; + struct stm32_rtc { struct rtc_device *rtc_dev; void __iomem *base; struct regmap *dbp; - struct clk *ck_rtc; + struct stm32_rtc_data *data; + struct clk *pclk; + struct clk *rtc_ck; int irq_alarm; }; @@ -122,9 +128,9 @@ static int stm32_rtc_enter_init_mode(struct stm32_rtc *rtc) writel_relaxed(isr, rtc->base + STM32_RTC_ISR); /* - * It takes around 2 ck_rtc clock cycles to enter in + * It takes around 2 rtc_ck clock cycles to enter in * initialization phase mode (and have INITF flag set). As - * slowest ck_rtc frequency may be 32kHz and highest should be + * slowest rtc_ck frequency may be 32kHz and highest should be * 1MHz, we poll every 10 us with a timeout of 100ms. */ return readl_relaxed_poll_timeout_atomic( @@ -153,7 +159,7 @@ static int stm32_rtc_wait_sync(struct stm32_rtc *rtc) /* * Wait for RSF to be set to ensure the calendar registers are - * synchronised, it takes around 2 ck_rtc clock cycles + * synchronised, it takes around 2 rtc_ck clock cycles */ return readl_relaxed_poll_timeout_atomic(rtc->base + STM32_RTC_ISR, isr, @@ -456,7 +462,7 @@ static int stm32_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm) /* * Poll Alarm write flag to be sure that Alarm update is allowed: it - * takes around 2 ck_rtc clock cycles + * takes around 2 rtc_ck clock cycles */ ret = readl_relaxed_poll_timeout_atomic(rtc->base + STM32_RTC_ISR, isr, @@ -490,8 +496,17 @@ static const struct rtc_class_ops stm32_rtc_ops = { .alarm_irq_enable = stm32_rtc_alarm_irq_enable, }; +static const struct stm32_rtc_data stm32_rtc_data = { + .has_pclk = false, +}; + +static const struct stm32_rtc_data stm32h7_rtc_data = { + .has_pclk = true, +}; + static const struct of_device_id stm32_rtc_of_match[] = { - { .compatible = "st,stm32-rtc" }, + { .compatible = "st,stm32-rtc", .data = &stm32_rtc_data }, + { .compatible = "st,stm32h7-rtc", .data = &stm32h7_rtc_data }, {} }; MODULE_DEVICE_TABLE(of, stm32_rtc_of_match); @@ -503,7 +518,7 @@ static int stm32_rtc_init(struct platform_device *pdev, unsigned int rate; int ret = 0; - rate = clk_get_rate(rtc->ck_rtc); + rate = clk_get_rate(rtc->rtc_ck); /* Find prediv_a and prediv_s to obtain the 1Hz calendar clock */ pred_a_max = STM32_RTC_PRER_PRED_A >> STM32_RTC_PRER_PRED_A_SHIFT; @@ -524,7 +539,7 @@ static int stm32_rtc_init(struct platform_device *pdev, pred_a = pred_a_max; pred_s = (rate / (pred_a + 1)) - 1; - dev_warn(&pdev->dev, "ck_rtc is %s\n", + dev_warn(&pdev->dev, "rtc_ck is %s\n", (rate < ((pred_a + 1) * (pred_s + 1))) ? "fast" : "slow"); } @@ -561,6 +576,7 @@ static int stm32_rtc_probe(struct platform_device *pdev) { struct stm32_rtc *rtc; struct resource *res; + const struct of_device_id *match; int ret; rtc = devm_kzalloc(&pdev->dev, sizeof(*rtc), GFP_KERNEL); @@ -579,15 +595,34 @@ static int stm32_rtc_probe(struct platform_device *pdev) return PTR_ERR(rtc->dbp); } - rtc->ck_rtc = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(rtc->ck_rtc)) { - dev_err(&pdev->dev, "no ck_rtc clock"); - return PTR_ERR(rtc->ck_rtc); + match = of_match_device(stm32_rtc_of_match, &pdev->dev); + rtc->data = (struct stm32_rtc_data *)match->data; + + if (!rtc->data->has_pclk) { + rtc->pclk = NULL; + rtc->rtc_ck = devm_clk_get(&pdev->dev, NULL); + } else { + rtc->pclk = devm_clk_get(&pdev->dev, "pclk"); + if (IS_ERR(rtc->pclk)) { + dev_err(&pdev->dev, "no pclk clock"); + return PTR_ERR(rtc->pclk); + } + rtc->rtc_ck = devm_clk_get(&pdev->dev, "rtc_ck"); + } + if (IS_ERR(rtc->rtc_ck)) { + dev_err(&pdev->dev, "no rtc_ck clock"); + return PTR_ERR(rtc->rtc_ck); + } + + if (rtc->data->has_pclk) { + ret = clk_prepare_enable(rtc->pclk); + if (ret) + return ret; } - ret = clk_prepare_enable(rtc->ck_rtc); + ret = clk_prepare_enable(rtc->rtc_ck); if (ret) - return ret; + goto err; regmap_update_bits(rtc->dbp, PWR_CR, PWR_CR_DBP, PWR_CR_DBP); @@ -595,7 +630,7 @@ static int stm32_rtc_probe(struct platform_device *pdev) * After a system reset, RTC_ISR.INITS flag can be read to check if * the calendar has been initalized or not. INITS flag is reset by a * power-on reset (no vbat, no power-supply). It is not reset if - * ck_rtc parent clock has changed (so RTC prescalers need to be + * rtc_ck parent clock has changed (so RTC prescalers need to be * changed). That's why we cannot rely on this flag to know if RTC * init has to be done. */ @@ -646,7 +681,9 @@ static int stm32_rtc_probe(struct platform_device *pdev) return 0; err: - clk_disable_unprepare(rtc->ck_rtc); + if (rtc->data->has_pclk) + clk_disable_unprepare(rtc->pclk); + clk_disable_unprepare(rtc->rtc_ck); regmap_update_bits(rtc->dbp, PWR_CR, PWR_CR_DBP, 0); @@ -667,7 +704,9 @@ static int stm32_rtc_remove(struct platform_device *pdev) writel_relaxed(cr, rtc->base + STM32_RTC_CR); stm32_rtc_wpr_lock(rtc); - clk_disable_unprepare(rtc->ck_rtc); + clk_disable_unprepare(rtc->rtc_ck); + if (rtc->data->has_pclk) + clk_disable_unprepare(rtc->pclk); /* Enable backup domain write protection */ regmap_update_bits(rtc->dbp, PWR_CR, PWR_CR_DBP, 0); @@ -682,6 +721,9 @@ static int stm32_rtc_suspend(struct device *dev) { struct stm32_rtc *rtc = dev_get_drvdata(dev); + if (rtc->data->has_pclk) + clk_disable_unprepare(rtc->pclk); + if (device_may_wakeup(dev)) return enable_irq_wake(rtc->irq_alarm); @@ -693,6 +735,12 @@ static int stm32_rtc_resume(struct device *dev) struct stm32_rtc *rtc = dev_get_drvdata(dev); int ret = 0; + if (rtc->data->has_pclk) { + ret = clk_prepare_enable(rtc->pclk); + if (ret) + return ret; + } + ret = stm32_rtc_wait_sync(rtc); if (ret < 0) return ret; -- cgit v1.2.3-59-g8ed1b From f59627810e18d4435051d982b5d05cab18c6e653 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 22 Jun 2017 20:03:51 +0100 Subject: Btrfs: incremental send, fix invalid path for link commands In some scenarios an incremental send stream can contain link commands with an invalid target path. Such scenarios happen after moving some directory inode A, renaming a regular file inode B into the old name of inode A and finally creating a new hard link for inode B at directory inode A. Consider the following example scenario where this issue happens. Parent snapshot: . (ino 256) | |--- dir1/ (ino 257) | |--- dir2/ (ino 258) | |--- dir3/ (ino 259) | |--- file1 (ino 261) | |--- dir4/ (ino 262) | |--- dir5/ (ino 260) Send snapshot: . (ino 256) | |--- dir1/ (ino 257) |--- dir2/ (ino 258) | |--- dir3/ (ino 259) | |--- dir4 (ino 261) | |--- dir6/ (ino 263) |--- dir44/ (ino 262) |--- file11 (ino 261) |--- dir55/ (ino 260) When attempting to apply the corresponding incremental send stream, a link command contains an invalid target path which makes the receiver fail. The following is the verbose output of the btrfs receive command: receiving snapshot mysnap2 uuid=90076fe6-5ba6-e64a-9321-9279670ed16b (...) utimes utimes dir1 utimes dir1/dir2/dir3 utimes rename dir1/dir2/dir3/dir4 -> o262-7-0 link dir1/dir2/dir3/dir4 -> dir1/dir2/dir3/file1 link dir1/dir2/dir3/dir4/file11 -> dir1/dir2/dir3/file1 ERROR: link dir1/dir2/dir3/dir4/file11 -> dir1/dir2/dir3/file1 failed: Not a directory The following steps happen during the computation of the incremental send stream the lead to this issue: 1) When processing inode 261, we orphanize inode 262 due to a name/location collision with one of the new hard links for inode 261 (created in the second step below). 2) We create one of the 2 new hard links for inode 261, the one whose location is at "dir1/dir2/dir3/dir4". 3) We then attempt to create the other new hard link for inode 261, which has inode 262 as its parent directory. Because the path for this new hard link was computed before we started processing the new references (hard links), it reflects the old name/location of inode 262, that is, it does not account for the orphanization step that happened when we started processing the new references for inode 261, whence it is no longer valid, causing the receiver to fail. So fix this issue by recomputing the full path of new references if we ended up orphanizing other inodes which are directories. A test case for fstests follows soon. Signed-off-by: Filipe Manana --- fs/btrfs/send.c | 81 ++++++++++++++++++++++++++++++++++++--------------------- 1 file changed, 51 insertions(+), 30 deletions(-) diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index e937c10b8287..7eaccfb72b47 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1856,7 +1856,7 @@ out: */ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen, const char *name, int name_len, - u64 *who_ino, u64 *who_gen) + u64 *who_ino, u64 *who_gen, u64 *who_mode) { int ret = 0; u64 gen; @@ -1905,7 +1905,7 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen, if (other_inode > sctx->send_progress || is_waiting_for_move(sctx, other_inode)) { ret = get_inode_info(sctx->parent_root, other_inode, NULL, - who_gen, NULL, NULL, NULL, NULL); + who_gen, who_mode, NULL, NULL, NULL); if (ret < 0) goto out; @@ -3683,6 +3683,36 @@ out: return ret; } +static int update_ref_path(struct send_ctx *sctx, struct recorded_ref *ref) +{ + int ret; + struct fs_path *new_path; + + /* + * Our reference's name member points to its full_path member string, so + * we use here a new path. + */ + new_path = fs_path_alloc(); + if (!new_path) + return -ENOMEM; + + ret = get_cur_path(sctx, ref->dir, ref->dir_gen, new_path); + if (ret < 0) { + fs_path_free(new_path); + return ret; + } + ret = fs_path_add(new_path, ref->name, ref->name_len); + if (ret < 0) { + fs_path_free(new_path); + return ret; + } + + fs_path_free(ref->full_path); + set_ref_path(ref, new_path); + + return 0; +} + /* * This does all the move/link/unlink/rmdir magic. */ @@ -3696,10 +3726,12 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) struct fs_path *valid_path = NULL; u64 ow_inode = 0; u64 ow_gen; + u64 ow_mode; int did_overwrite = 0; int is_orphan = 0; u64 last_dir_ino_rm = 0; bool can_rename = true; + bool orphanized_dir = false; bool orphanized_ancestor = false; btrfs_debug(fs_info, "process_recorded_refs %llu", sctx->cur_ino); @@ -3798,7 +3830,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) */ ret = will_overwrite_ref(sctx, cur->dir, cur->dir_gen, cur->name, cur->name_len, - &ow_inode, &ow_gen); + &ow_inode, &ow_gen, &ow_mode); if (ret < 0) goto out; if (ret) { @@ -3815,6 +3847,8 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) cur->full_path); if (ret < 0) goto out; + if (S_ISDIR(ow_mode)) + orphanized_dir = true; /* * If ow_inode has its rename operation delayed @@ -3920,6 +3954,18 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) if (ret < 0) goto out; } else { + /* + * We might have previously orphanized an inode + * which is an ancestor of our current inode, + * so our reference's full path, which was + * computed before any such orphanizations, must + * be updated. + */ + if (orphanized_dir) { + ret = update_ref_path(sctx, cur); + if (ret < 0) + goto out; + } ret = send_link(sctx, cur->full_path, valid_path); if (ret < 0) @@ -3990,34 +4036,9 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) * ancestor inode. */ if (orphanized_ancestor) { - struct fs_path *new_path; - - /* - * Our reference's name member points to - * its full_path member string, so we - * use here a new path. - */ - new_path = fs_path_alloc(); - if (!new_path) { - ret = -ENOMEM; - goto out; - } - ret = get_cur_path(sctx, cur->dir, - cur->dir_gen, - new_path); - if (ret < 0) { - fs_path_free(new_path); - goto out; - } - ret = fs_path_add(new_path, - cur->name, - cur->name_len); - if (ret < 0) { - fs_path_free(new_path); + ret = update_ref_path(sctx, cur); + if (ret < 0) goto out; - } - fs_path_free(cur->full_path); - set_ref_path(cur, new_path); } ret = send_unlink(sctx, cur->full_path); if (ret < 0) -- cgit v1.2.3-59-g8ed1b From 24e52b11e0ca788513b945a87b57cc0522a92933 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 6 Jul 2017 15:31:46 +0100 Subject: Btrfs: incremental send, fix invalid memory access When doing an incremental send, while processing an extent that changed between the parent and send snapshots and that extent was an inline extent in the parent snapshot, it's possible to access a memory region beyond the end of leaf if the inline extent is very small and it is the first item in a leaf. An example scenario is described below. The send snapshot has the following leaf: leaf 33865728 items 33 free space 773 generation 46 owner 5 fs uuid ab7090d8-dafd-4fb9-9246-723b6d2e2fb7 chunk uuid 2d16478c-c704-4ab9-b574-68bff2281b1f (...) item 14 key (335 EXTENT_DATA 0) itemoff 3052 itemsize 53 generation 36 type 1 (regular) extent data disk byte 12791808 nr 4096 extent data offset 0 nr 4096 ram 4096 extent compression 0 (none) item 15 key (335 EXTENT_DATA 8192) itemoff 2999 itemsize 53 generation 36 type 1 (regular) extent data disk byte 138170368 nr 225280 extent data offset 0 nr 225280 ram 225280 extent compression 0 (none) (...) And the parent snapshot has the following leaf: leaf 31272960 items 17 free space 17 generation 31 owner 5 fs uuid ab7090d8-dafd-4fb9-9246-723b6d2e2fb7 chunk uuid 2d16478c-c704-4ab9-b574-68bff2281b1f item 0 key (335 EXTENT_DATA 0) itemoff 3951 itemsize 44 generation 31 type 0 (inline) inline extent data size 23 ram_bytes 613 compression 1 (zlib) (...) When computing the send stream, it is detected that the extent of inode 335, at file offset 0, and at fs/btrfs/send.c:is_extent_unchanged() we grab the leaf from the parent snapshot and access the inline extent item. However, before jumping to the 'out' label, we access the 'offset' and 'disk_bytenr' fields of the extent item, which should not be done for inline extents since the inlined data starts at the offset of the 'disk_bytenr' field and can be very small. For example accessing the 'offset' field of the file extent item results in the following trace: [ 599.705368] general protection fault: 0000 [#1] PREEMPT SMP [ 599.706296] Modules linked in: btrfs psmouse i2c_piix4 ppdev acpi_cpufreq serio_raw parport_pc i2c_core evdev tpm_tis tpm_tis_core sg pcspkr parport tpm button su$ [ 599.709340] CPU: 7 PID: 5283 Comm: btrfs Not tainted 4.10.0-rc8-btrfs-next-46+ #1 [ 599.709340] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.1-0-gb3ef39f-prebuilt.qemu-project.org 04/01/2014 [ 599.709340] task: ffff88023eedd040 task.stack: ffffc90006658000 [ 599.709340] RIP: 0010:read_extent_buffer+0xdb/0xf4 [btrfs] [ 599.709340] RSP: 0018:ffffc9000665ba00 EFLAGS: 00010286 [ 599.709340] RAX: db73880000000000 RBX: 0000000000000000 RCX: 0000000000000001 [ 599.709340] RDX: ffffc9000665ba60 RSI: db73880000000000 RDI: ffffc9000665ba5f [ 599.709340] RBP: ffffc9000665ba30 R08: 0000000000000001 R09: ffff88020dc5e098 [ 599.709340] R10: 0000000000001000 R11: 0000160000000000 R12: 6db6db6db6db6db7 [ 599.709340] R13: ffff880000000000 R14: 0000000000000000 R15: ffff88020dc5e088 [ 599.709340] FS: 00007f519555a8c0(0000) GS:ffff88023f3c0000(0000) knlGS:0000000000000000 [ 599.709340] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 599.709340] CR2: 00007f1411afd000 CR3: 0000000235f8e000 CR4: 00000000000006e0 [ 599.709340] Call Trace: [ 599.709340] btrfs_get_token_64+0x93/0xce [btrfs] [ 599.709340] ? printk+0x48/0x50 [ 599.709340] btrfs_get_64+0xb/0xd [btrfs] [ 599.709340] process_extent+0x3a1/0x1106 [btrfs] [ 599.709340] ? btree_read_extent_buffer_pages+0x5/0xef [btrfs] [ 599.709340] changed_cb+0xb03/0xb3d [btrfs] [ 599.709340] ? btrfs_get_token_32+0x7a/0xcc [btrfs] [ 599.709340] btrfs_compare_trees+0x432/0x53d [btrfs] [ 599.709340] ? process_extent+0x1106/0x1106 [btrfs] [ 599.709340] btrfs_ioctl_send+0x960/0xe26 [btrfs] [ 599.709340] btrfs_ioctl+0x181b/0x1fed [btrfs] [ 599.709340] ? trace_hardirqs_on_caller+0x150/0x1ac [ 599.709340] vfs_ioctl+0x21/0x38 [ 599.709340] ? vfs_ioctl+0x21/0x38 [ 599.709340] do_vfs_ioctl+0x611/0x645 [ 599.709340] ? rcu_read_unlock+0x5b/0x5d [ 599.709340] ? __fget+0x6d/0x79 [ 599.709340] SyS_ioctl+0x57/0x7b [ 599.709340] entry_SYSCALL_64_fastpath+0x18/0xad [ 599.709340] RIP: 0033:0x7f51945eec47 [ 599.709340] RSP: 002b:00007ffc21c13e98 EFLAGS: 00000202 ORIG_RAX: 0000000000000010 [ 599.709340] RAX: ffffffffffffffda RBX: ffffffff81096459 RCX: 00007f51945eec47 [ 599.709340] RDX: 00007ffc21c13f20 RSI: 0000000040489426 RDI: 0000000000000004 [ 599.709340] RBP: ffffc9000665bf98 R08: 00007f519450d700 R09: 00007f519450d700 [ 599.709340] R10: 00007f519450d9d0 R11: 0000000000000202 R12: 0000000000000046 [ 599.709340] R13: ffffc9000665bf78 R14: 0000000000000000 R15: 00007f5195574040 [ 599.709340] ? trace_hardirqs_off_caller+0x43/0xb1 [ 599.709340] Code: 29 f0 49 39 d8 4c 0f 47 c3 49 03 81 58 01 00 00 44 89 c1 4c 01 c2 4c 29 c3 48 c1 f8 03 49 0f af c4 48 c1 e0 0c 4c 01 e8 48 01 c6 a4 31 f6 4$ [ 599.709340] RIP: read_extent_buffer+0xdb/0xf4 [btrfs] RSP: ffffc9000665ba00 [ 599.762057] ---[ end trace fe00d7af61b9f49e ]--- This is because the 'offset' field starts at an offset of 37 bytes (offsetof(struct btrfs_file_extent_item, offset)), has a length of 8 bytes and therefore attemping to read it causes a 1 byte access beyond the end of the leaf, as the first item's content in a leaf is located at the tail of the leaf, the item size is 44 bytes and the offset of that field plus its length (37 + 8 = 45) goes beyond the item's size by 1 byte. So fix this by accessing the 'offset' and 'disk_bytenr' fields after jumping to the 'out' label if we are processing an inline extent. We move the reading operation of the 'disk_bytenr' field too because we have the same problem as for the 'offset' field explained above when the inline data is less then 8 bytes. The access to the 'generation' field is also moved but just for the sake of grouping access to all the fields. Fixes: e1cbfd7bf6da ("Btrfs: send, fix file hole not being preserved due to inline extent") Cc: # v4.12+ Signed-off-by: Filipe Manana --- fs/btrfs/send.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 7eaccfb72b47..b082210df9c8 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -5270,15 +5270,12 @@ static int is_extent_unchanged(struct send_ctx *sctx, goto out; } - right_disknr = btrfs_file_extent_disk_bytenr(eb, ei); if (right_type == BTRFS_FILE_EXTENT_INLINE) { right_len = btrfs_file_extent_inline_len(eb, slot, ei); right_len = PAGE_ALIGN(right_len); } else { right_len = btrfs_file_extent_num_bytes(eb, ei); } - right_offset = btrfs_file_extent_offset(eb, ei); - right_gen = btrfs_file_extent_generation(eb, ei); /* * Are we at extent 8? If yes, we know the extent is changed. @@ -5303,6 +5300,10 @@ static int is_extent_unchanged(struct send_ctx *sctx, goto out; } + right_disknr = btrfs_file_extent_disk_bytenr(eb, ei); + right_offset = btrfs_file_extent_offset(eb, ei); + right_gen = btrfs_file_extent_generation(eb, ei); + left_offset_fixed = left_offset; if (key.offset < ekey->offset) { /* Fix the right offset for 2a and 7. */ -- cgit v1.2.3-59-g8ed1b From 4edfc5406ac9d3b59f770dd7436fdcfd5d593216 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 1 Jul 2017 12:15:22 +0200 Subject: platform/x86: silead_dmi: Add touchscreen info for I.T.Works TW891 2-in-1 Add touchscreen info for I.T.Works TW891 2-in-1. Signed-off-by: Hans de Goede Signed-off-by: Darren Hart (VMware) --- drivers/platform/x86/silead_dmi.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/drivers/platform/x86/silead_dmi.c b/drivers/platform/x86/silead_dmi.c index 3cd3bdfe51df..f9e840aa5592 100644 --- a/drivers/platform/x86/silead_dmi.c +++ b/drivers/platform/x86/silead_dmi.c @@ -122,6 +122,20 @@ static const struct silead_ts_dmi_data pov_mobii_wintab_p800w_data = { .properties = pov_mobii_wintab_p800w_props, }; +static const struct property_entry itworks_tw891_props[] = { + PROPERTY_ENTRY_U32("touchscreen-size-x", 1600), + PROPERTY_ENTRY_U32("touchscreen-size-y", 890), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), + PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), + PROPERTY_ENTRY_STRING("firmware-name", "gsl3670-itworks-tw891.fw"), + { } +}; + +static const struct silead_ts_dmi_data itworks_tw891_data = { + .acpi_name = "MSSL1680:00", + .properties = itworks_tw891_props, +}; + static const struct dmi_system_id silead_ts_dmi_table[] = { { /* CUBE iwork8 Air */ @@ -187,6 +201,14 @@ static const struct dmi_system_id silead_ts_dmi_table[] = { DMI_MATCH(DMI_BIOS_DATE, "08/22/2014"), }, }, + { + /* I.T.Works TW891 */ + .driver_data = (void *)&itworks_tw891_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "To be filled by O.E.M."), + DMI_MATCH(DMI_PRODUCT_NAME, "TW891"), + }, + }, { }, }; -- cgit v1.2.3-59-g8ed1b From 12f66e4a0f7b5624901ba4301210e026c9ddf78d Mon Sep 17 00:00:00 2001 From: Jiang Yi Date: Fri, 2 Jun 2017 11:45:09 +0800 Subject: target: reject COMPARE_AND_WRITE if emulate_caw is not set In struct se_dev_attrib, there is a field emulate_caw exposed as a /sys/kernel/config/target/core/$HBA/$DEV/attrib/. If this field is set zero, it means the corresponding struct se_device does not support the scsi cmd COMPARE_AND_WRITE In function sbc_parse_cdb(), go ahead and reject scsi COMPARE_AND_WRITE if emulate_caw is not set, because it has been explicitly disabled from user-space. (Make pr_err ratelimited - nab) Signed-off-by: Jiang Yi Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_sbc.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index 4316f7b65fb7..ff4a6ec30adf 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -1005,6 +1005,12 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) break; } case COMPARE_AND_WRITE: + if (!dev->dev_attrib.emulate_caw) { + pr_err_ratelimited("se_device %s/%s (vpd_unit_serial %s) reject" + " COMPARE_AND_WRITE\n", dev->se_hba->backend->ops->name, + dev->dev_group.cg_item.ci_name, dev->t10_wwn.unit_serial); + return TCM_UNSUPPORTED_SCSI_OPCODE; + } sectors = cdb[13]; /* * Currently enforce COMPARE_AND_WRITE for a single sector -- cgit v1.2.3-59-g8ed1b From eeb64d239ea664592ff8f1bce5546209a6593df5 Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Sat, 3 Jun 2017 06:41:03 -0700 Subject: target: Add support for TMR percpu reference counting This patch introduces TMR percpu reference counting using se_lun->lun_ref in transport_lookup_tmr_lun(), following how existing non TMR per se_lun reference counting works within transport_lookup_cmd_lun(). It also adds explicit transport_lun_remove_cmd() calls to drop the reference in the three tmr related locations that invoke transport_cmd_check_stop_to_fabric(); - target_tmr_work() during normal ->queue_tm_rsp() - target_complete_tmr_failure() during error ->queue_tm_rsp() - transport_generic_handle_tmr() during early failure Also, note the exception paths in transport_generic_free_cmd() and transport_cmd_finish_abort() already check SCF_SE_LUN_CMD, and will invoke transport_lun_remove_cmd() when necessary. Reviewed-by: Himanshu Madhani Reviewed-by: Quinn Tran Cc: Mike Christie Cc: Hannes Reinecke Cc: Christoph Hellwig Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_device.c | 14 ++++++++++---- drivers/target/target_core_transport.c | 3 +++ 2 files changed, 13 insertions(+), 4 deletions(-) diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index e4771cec108c..bf7a57953fa4 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -168,11 +168,20 @@ int transport_lookup_tmr_lun(struct se_cmd *se_cmd, u64 unpacked_lun) rcu_read_lock(); deve = target_nacl_find_deve(nacl, unpacked_lun); if (deve) { - se_cmd->se_lun = rcu_dereference(deve->se_lun); se_lun = rcu_dereference(deve->se_lun); + + if (!percpu_ref_tryget_live(&se_lun->lun_ref)) { + se_lun = NULL; + goto out_unlock; + } + + se_cmd->se_lun = rcu_dereference(deve->se_lun); se_cmd->pr_res_key = deve->pr_res_key; se_cmd->orig_fe_lun = unpacked_lun; + se_cmd->se_cmd_flags |= SCF_SE_LUN_CMD; + se_cmd->lun_ref_active = true; } +out_unlock: rcu_read_unlock(); if (!se_lun) { @@ -182,9 +191,6 @@ int transport_lookup_tmr_lun(struct se_cmd *se_cmd, u64 unpacked_lun) unpacked_lun); return -ENODEV; } - /* - * XXX: Add percpu se_lun->lun_ref reference count for TMR - */ se_cmd->se_dev = rcu_dereference_raw(se_lun->lun_se_dev); se_tmr->tmr_dev = rcu_dereference_raw(se_lun->lun_se_dev); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index f1b3a46bdcaf..97a01f48068b 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1590,6 +1590,7 @@ static void target_complete_tmr_failure(struct work_struct *work) se_cmd->se_tmr_req->response = TMR_LUN_DOES_NOT_EXIST; se_cmd->se_tfo->queue_tm_rsp(se_cmd); + transport_lun_remove_cmd(se_cmd); transport_cmd_check_stop_to_fabric(se_cmd); } @@ -3201,6 +3202,7 @@ static void target_tmr_work(struct work_struct *work) cmd->se_tfo->queue_tm_rsp(cmd); check_stop: + transport_lun_remove_cmd(cmd); transport_cmd_check_stop_to_fabric(cmd); } @@ -3223,6 +3225,7 @@ int transport_generic_handle_tmr( pr_warn_ratelimited("handle_tmr caught CMD_T_ABORTED TMR %d" "ref_tag: %llu tag: %llu\n", cmd->se_tmr_req->function, cmd->se_tmr_req->ref_task_tag, cmd->tag); + transport_lun_remove_cmd(cmd); transport_cmd_check_stop_to_fabric(cmd); return 0; } -- cgit v1.2.3-59-g8ed1b From 5465e7d3b99bbaa823ae4f8e538543e7d6cdc530 Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Sat, 3 Jun 2017 06:55:50 -0700 Subject: target: Add TARGET_SCF_LOOKUP_LUN_FROM_TAG support for ABORT_TASK This patch introduces support in target_submit_tmr() for locating a unpacked_lun from an existing se_cmd->tag during ABORT_TASK. When TARGET_SCF_LOOKUP_LUN_FROM_TAG is set, target_submit_tmr() will do the extra lookup via target_lookup_lun_from_tag() and subsequently invoke transport_lookup_tmr_lun() so a proper percpu se_lun->lun_ref is taken before workqueue dispatch into se_device->tmr_wq happens. Aside from the extra target_lookup_lun_from_tag(), the existing code-path remains unchanged. Reviewed-by: Himanshu Madhani Reviewed-by: Quinn Tran Cc: Mike Christie Cc: Hannes Reinecke Cc: Christoph Hellwig Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_transport.c | 53 ++++++++++++++++++++++++++++------ include/target/target_core_base.h | 3 +- 2 files changed, 46 insertions(+), 10 deletions(-) diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 97a01f48068b..e045803921f8 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1594,6 +1594,29 @@ static void target_complete_tmr_failure(struct work_struct *work) transport_cmd_check_stop_to_fabric(se_cmd); } +static bool target_lookup_lun_from_tag(struct se_session *se_sess, u64 tag, + u64 *unpacked_lun) +{ + struct se_cmd *se_cmd; + unsigned long flags; + bool ret = false; + + spin_lock_irqsave(&se_sess->sess_cmd_lock, flags); + list_for_each_entry(se_cmd, &se_sess->sess_cmd_list, se_cmd_list) { + if (se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) + continue; + + if (se_cmd->tag == tag) { + *unpacked_lun = se_cmd->orig_fe_lun; + ret = true; + break; + } + } + spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); + + return ret; +} + /** * target_submit_tmr - lookup unpacked lun and submit uninitialized se_cmd * for TMR CDBs @@ -1641,19 +1664,31 @@ int target_submit_tmr(struct se_cmd *se_cmd, struct se_session *se_sess, core_tmr_release_req(se_cmd->se_tmr_req); return ret; } + /* + * If this is ABORT_TASK with no explicit fabric provided LUN, + * go ahead and search active session tags for a match to figure + * out unpacked_lun for the original se_cmd. + */ + if (tm_type == TMR_ABORT_TASK && (flags & TARGET_SCF_LOOKUP_LUN_FROM_TAG)) { + if (!target_lookup_lun_from_tag(se_sess, tag, &unpacked_lun)) + goto failure; + } ret = transport_lookup_tmr_lun(se_cmd, unpacked_lun); - if (ret) { - /* - * For callback during failure handling, push this work off - * to process context with TMR_LUN_DOES_NOT_EXIST status. - */ - INIT_WORK(&se_cmd->work, target_complete_tmr_failure); - schedule_work(&se_cmd->work); - return 0; - } + if (ret) + goto failure; + transport_generic_handle_tmr(se_cmd); return 0; + + /* + * For callback during failure handling, push this work off + * to process context with TMR_LUN_DOES_NOT_EXIST status. + */ +failure: + INIT_WORK(&se_cmd->work, target_complete_tmr_failure); + schedule_work(&se_cmd->work); + return 0; } EXPORT_SYMBOL(target_submit_tmr); diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 47d9f381209f..f835528e424e 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -188,7 +188,8 @@ enum target_sc_flags_table { TARGET_SCF_BIDI_OP = 0x01, TARGET_SCF_ACK_KREF = 0x02, TARGET_SCF_UNKNOWN_SIZE = 0x04, - TARGET_SCF_USE_CPUID = 0x08, + TARGET_SCF_USE_CPUID = 0x08, + TARGET_SCF_LOOKUP_LUN_FROM_TAG = 0x10, }; /* fabric independent task management function values */ -- cgit v1.2.3-59-g8ed1b From eb5ae2335a84cccf45ec01602bc300c3e70486d0 Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Sat, 3 Jun 2017 07:07:21 -0700 Subject: qla2xxx: Convert QLA_TGT_ABTS to TARGET_SCF_LOOKUP_LUN_FROM_TAG Following Himanshu's earlier patch to drop the redundant tag lookup within __qlt_24xx_handle_abts(), go ahead and drop this now QLA_TGT_ABTS can use TARGET_SCF_LOOKUP_LUN_FROM_TAG and have target_submit_tmr() do this from common code. Reviewed-by: Himanshu Madhani Acked-by: Himanshu Madhani Reviewed-by: Quinn Tran Cc: Mike Christie Cc: Hannes Reinecke Cc: Christoph Hellwig Signed-off-by: Nicholas Bellinger --- drivers/scsi/qla2xxx/qla_target.c | 39 +++++++++----------------------------- drivers/scsi/qla2xxx/tcm_qla2xxx.c | 4 +++- 2 files changed, 12 insertions(+), 31 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 0e03ca2ab3e5..401e245477d4 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1847,38 +1847,13 @@ static int __qlt_24xx_handle_abts(struct scsi_qla_host *vha, struct abts_recv_from_24xx *abts, struct fc_port *sess) { struct qla_hw_data *ha = vha->hw; - struct se_session *se_sess = sess->se_sess; struct qla_tgt_mgmt_cmd *mcmd; - struct se_cmd *se_cmd; - u32 lun = 0; int rc; - bool found_lun = false; - unsigned long flags; - - spin_lock_irqsave(&se_sess->sess_cmd_lock, flags); - list_for_each_entry(se_cmd, &se_sess->sess_cmd_list, se_cmd_list) { - struct qla_tgt_cmd *cmd = - container_of(se_cmd, struct qla_tgt_cmd, se_cmd); - if (se_cmd->tag == abts->exchange_addr_to_abort) { - lun = cmd->unpacked_lun; - found_lun = true; - break; - } - } - spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); - /* cmd not in LIO lists, look in qla list */ - if (!found_lun) { - if (abort_cmd_for_tag(vha, abts->exchange_addr_to_abort)) { - /* send TASK_ABORT response immediately */ - qlt_24xx_send_abts_resp(vha, abts, FCP_TMF_CMPL, false); - return 0; - } else { - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf081, - "unable to find cmd in driver or LIO for tag 0x%x\n", - abts->exchange_addr_to_abort); - return -ENOENT; - } + if (abort_cmd_for_tag(vha, abts->exchange_addr_to_abort)) { + /* send TASK_ABORT response immediately */ + qlt_24xx_send_abts_resp(vha, abts, FCP_TMF_CMPL, false); + return 0; } ql_dbg(ql_dbg_tgt_mgt, vha, 0xf00f, @@ -1899,7 +1874,11 @@ static int __qlt_24xx_handle_abts(struct scsi_qla_host *vha, mcmd->reset_count = vha->hw->chip_reset; mcmd->tmr_func = QLA_TGT_ABTS; - rc = ha->tgt.tgt_ops->handle_tmr(mcmd, lun, mcmd->tmr_func, + /* + * LUN is looked up by target-core internally based on the passed + * abts->exchange_addr_to_abort tag. + */ + rc = ha->tgt.tgt_ops->handle_tmr(mcmd, 0, mcmd->tmr_func, abts->exchange_addr_to_abort); if (rc != 0) { ql_dbg(ql_dbg_tgt_mgt, vha, 0xf052, diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index 7443e4efa3ae..75aeb9fdfd06 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -601,11 +601,13 @@ static int tcm_qla2xxx_handle_tmr(struct qla_tgt_mgmt_cmd *mcmd, uint32_t lun, struct fc_port *sess = mcmd->sess; struct se_cmd *se_cmd = &mcmd->se_cmd; int transl_tmr_func = 0; + int flags = TARGET_SCF_ACK_KREF; switch (tmr_func) { case QLA_TGT_ABTS: pr_debug("%ld: ABTS received\n", sess->vha->host_no); transl_tmr_func = TMR_ABORT_TASK; + flags |= TARGET_SCF_LOOKUP_LUN_FROM_TAG; break; case QLA_TGT_2G_ABORT_TASK: pr_debug("%ld: 2G Abort Task received\n", sess->vha->host_no); @@ -638,7 +640,7 @@ static int tcm_qla2xxx_handle_tmr(struct qla_tgt_mgmt_cmd *mcmd, uint32_t lun, } return target_submit_tmr(se_cmd, sess->se_sess, NULL, lun, mcmd, - transl_tmr_func, GFP_ATOMIC, tag, TARGET_SCF_ACK_KREF); + transl_tmr_func, GFP_ATOMIC, tag, flags); } static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd) -- cgit v1.2.3-59-g8ed1b From 3e182db787714b373d4b1a1fd7dba4a581e8e406 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 23 May 2017 16:48:22 -0700 Subject: target: Use symbolic value for WRITE_VERIFY_16 Now that a symbolic value has been introduced for WRITE_VERIFY_16, use it. This patch does not change any functionality. References: commit c2d26f18dcbc ("target: Add WRITE_VERIFY_16") Signed-off-by: Bart Van Assche Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Cc: Bryant G. Ly Cc: Andy Grover Cc: David Disseldorp Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_device.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index bf7a57953fa4..6403f44e6104 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -1131,7 +1131,7 @@ passthrough_parse_cdb(struct se_cmd *cmd, case WRITE_16: case WRITE_VERIFY: case WRITE_VERIFY_12: - case 0x8e: /* WRITE_VERIFY_16 */ + case WRITE_VERIFY_16: case COMPARE_AND_WRITE: case XDWRITEREAD_10: cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB; -- cgit v1.2.3-59-g8ed1b From 9f2f342892e15f8600939ec8d06caf963ccff880 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 23 May 2017 16:48:23 -0700 Subject: target: Remove se_device.dev_list The last user of se_device.dev_list was removed through commit 0fd97ccf45be ("target: kill struct se_subsystem_dev"). Hence also remove se_device.dev_list. Signed-off-by: Bart Van Assche Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Cc: Andy Grover Cc: David Disseldorp Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_device.c | 1 - include/target/target_core_base.h | 2 -- 2 files changed, 3 deletions(-) diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 6403f44e6104..1f54b397bd57 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -767,7 +767,6 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name) dev->prot_length = sizeof(struct t10_pi_tuple); dev->hba_index = hba->hba_index; - INIT_LIST_HEAD(&dev->dev_list); INIT_LIST_HEAD(&dev->dev_sep_list); INIT_LIST_HEAD(&dev->dev_tmr_list); INIT_LIST_HEAD(&dev->delayed_cmd_list); diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index f835528e424e..a3af69fcf75e 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -816,8 +816,6 @@ struct se_device { unsigned char udev_path[SE_UDEV_PATH_LEN]; /* Pointer to template of function pointers for transport */ const struct target_backend_ops *transport; - /* Linked list for struct se_hba struct se_device list */ - struct list_head dev_list; struct se_lun xcopy_lun; /* Protection Information */ int prot_length; -- cgit v1.2.3-59-g8ed1b From f2b72d6a8eed0eb02e6346886514a27df1efe827 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 23 May 2017 16:48:24 -0700 Subject: target: Fix transport_init_se_cmd() Avoid that aborting a command before it has been submitted onto a workqueue triggers the following warning: INFO: trying to register non-static key. the code is fine but needs lockdep annotation. turning off the locking correctness validator. CPU: 3 PID: 46 Comm: kworker/u8:1 Not tainted 4.12.0-rc2-dbg+ #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.0.0-prebuilt.qemu-project.org 04/01/2014 Workqueue: tmr-iblock target_tmr_work [target_core_mod] Call Trace: dump_stack+0x86/0xcf register_lock_class+0xe8/0x570 __lock_acquire+0xa1/0x11d0 lock_acquire+0x59/0x80 flush_work+0x42/0x2b0 __cancel_work_timer+0x10c/0x180 cancel_work_sync+0xb/0x10 core_tmr_lun_reset+0x352/0x740 [target_core_mod] target_tmr_work+0xd6/0x130 [target_core_mod] process_one_work+0x1ca/0x3f0 worker_thread+0x49/0x3b0 kthread+0x109/0x140 ret_from_fork+0x31/0x40 Signed-off-by: Bart Van Assche Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: David Disseldorp Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_transport.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index e045803921f8..d601616b9f12 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1239,6 +1239,7 @@ void transport_init_se_cmd( init_completion(&cmd->t_transport_stop_comp); init_completion(&cmd->cmd_wait_comp); spin_lock_init(&cmd->t_state_lock); + INIT_WORK(&cmd->work, NULL); kref_init(&cmd->cmd_kref); cmd->se_tfo = tfo; -- cgit v1.2.3-59-g8ed1b From a85d667e58bddf73be84d1981b41eaac985ed216 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 23 May 2017 16:48:27 -0700 Subject: target: Use {get,put}_unaligned_be*() instead of open coding these functions Introduce the function get_unaligned_be24(). Use {get,put}_unaligned_be*() where appropriate. This patch does not change any functionality. Signed-off-by: Bart Van Assche Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Cc: Andy Grover Cc: David Disseldorp Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_alua.c | 8 +-- drivers/target/target_core_device.c | 8 +-- drivers/target/target_core_fabric_lib.c | 6 +- drivers/target/target_core_pr.c | 99 +++++++-------------------------- drivers/target/target_core_pscsi.c | 20 +++---- drivers/target/target_core_sbc.c | 59 +++++--------------- drivers/target/target_core_spc.c | 42 +++++++------- drivers/target/target_core_xcopy.c | 4 +- include/target/target_core_backend.h | 8 +++ 9 files changed, 83 insertions(+), 171 deletions(-) diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c index fc4a9c303d55..a91b7c25ffd4 100644 --- a/drivers/target/target_core_alua.c +++ b/drivers/target/target_core_alua.c @@ -205,8 +205,8 @@ target_emulate_report_target_port_groups(struct se_cmd *cmd) /* * TARGET PORT GROUP */ - buf[off++] = ((tg_pt_gp->tg_pt_gp_id >> 8) & 0xff); - buf[off++] = (tg_pt_gp->tg_pt_gp_id & 0xff); + put_unaligned_be16(tg_pt_gp->tg_pt_gp_id, &buf[off]); + off += 2; off++; /* Skip over Reserved */ /* @@ -235,8 +235,8 @@ target_emulate_report_target_port_groups(struct se_cmd *cmd) /* * Set RELATIVE TARGET PORT IDENTIFIER */ - buf[off++] = ((lun->lun_rtpi >> 8) & 0xff); - buf[off++] = (lun->lun_rtpi & 0xff); + put_unaligned_be16(lun->lun_rtpi, &buf[off]); + off += 2; rd_len += 4; } spin_unlock(&tg_pt_gp->tg_pt_gp_lock); diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 1f54b397bd57..11c80c47b9d3 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -1091,19 +1091,19 @@ passthrough_parse_cdb(struct se_cmd *cmd, TRANSPORT_FLAG_PASSTHROUGH_PGR)) { if (cdb[0] == PERSISTENT_RESERVE_IN) { cmd->execute_cmd = target_scsi3_emulate_pr_in; - size = (cdb[7] << 8) + cdb[8]; + size = get_unaligned_be16(&cdb[7]); return target_cmd_size_check(cmd, size); } if (cdb[0] == PERSISTENT_RESERVE_OUT) { cmd->execute_cmd = target_scsi3_emulate_pr_out; - size = (cdb[7] << 8) + cdb[8]; + size = get_unaligned_be16(&cdb[7]); return target_cmd_size_check(cmd, size); } if (cdb[0] == RELEASE || cdb[0] == RELEASE_10) { cmd->execute_cmd = target_scsi2_reservation_release; if (cdb[0] == RELEASE_10) - size = (cdb[7] << 8) | cdb[8]; + size = get_unaligned_be16(&cdb[7]); else size = cmd->data_length; return target_cmd_size_check(cmd, size); @@ -1111,7 +1111,7 @@ passthrough_parse_cdb(struct se_cmd *cmd, if (cdb[0] == RESERVE || cdb[0] == RESERVE_10) { cmd->execute_cmd = target_scsi2_reservation_reserve; if (cdb[0] == RESERVE_10) - size = (cdb[7] << 8) | cdb[8]; + size = get_unaligned_be16(&cdb[7]); else size = cmd->data_length; return target_cmd_size_check(cmd, size); diff --git a/drivers/target/target_core_fabric_lib.c b/drivers/target/target_core_fabric_lib.c index cb6497ce4b61..508da345b73f 100644 --- a/drivers/target/target_core_fabric_lib.c +++ b/drivers/target/target_core_fabric_lib.c @@ -34,6 +34,7 @@ #include #include #include +#include #include @@ -216,8 +217,7 @@ static int iscsi_get_pr_transport_id( if (padding != 0) len += padding; - buf[2] = ((len >> 8) & 0xff); - buf[3] = (len & 0xff); + put_unaligned_be16(len, &buf[2]); /* * Increment value for total payload + header length for * full status descriptor @@ -306,7 +306,7 @@ static char *iscsi_parse_pr_out_transport_id( */ if (out_tid_len) { /* The shift works thanks to integer promotion rules */ - add_len = (buf[2] << 8) | buf[3]; + add_len = get_unaligned_be16(&buf[2]); tid_len = strlen(&buf[4]); tid_len += 4; /* Add four bytes for iSCSI Transport ID header */ diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index 129ca572673c..9921d4d6bb41 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -1562,10 +1562,7 @@ core_scsi3_decode_spec_i_port( * first extract TransportID Parameter Data Length, and make sure * the value matches up to the SCSI expected data transfer length. */ - tpdl = (buf[24] & 0xff) << 24; - tpdl |= (buf[25] & 0xff) << 16; - tpdl |= (buf[26] & 0xff) << 8; - tpdl |= buf[27] & 0xff; + tpdl = get_unaligned_be32(&buf[24]); if ((tpdl + 28) != cmd->data_length) { pr_err("SPC-3 PR: Illegal tpdl: %u + 28 byte header" @@ -3221,12 +3218,8 @@ core_scsi3_emulate_pro_register_and_move(struct se_cmd *cmd, u64 res_key, goto out_put_pr_reg; } - rtpi = (buf[18] & 0xff) << 8; - rtpi |= buf[19] & 0xff; - tid_len = (buf[20] & 0xff) << 24; - tid_len |= (buf[21] & 0xff) << 16; - tid_len |= (buf[22] & 0xff) << 8; - tid_len |= buf[23] & 0xff; + rtpi = get_unaligned_be16(&buf[18]); + tid_len = get_unaligned_be32(&buf[20]); transport_kunmap_data_sg(cmd); buf = NULL; @@ -3552,16 +3545,6 @@ out_put_pr_reg: return ret; } -static unsigned long long core_scsi3_extract_reservation_key(unsigned char *cdb) -{ - unsigned int __v1, __v2; - - __v1 = (cdb[0] << 24) | (cdb[1] << 16) | (cdb[2] << 8) | cdb[3]; - __v2 = (cdb[4] << 24) | (cdb[5] << 16) | (cdb[6] << 8) | cdb[7]; - - return ((unsigned long long)__v2) | (unsigned long long)__v1 << 32; -} - /* * See spc4r17 section 6.14 Table 170 */ @@ -3619,8 +3602,8 @@ target_scsi3_emulate_pr_out(struct se_cmd *cmd) /* * From PERSISTENT_RESERVE_OUT parameter list (payload) */ - res_key = core_scsi3_extract_reservation_key(&buf[0]); - sa_res_key = core_scsi3_extract_reservation_key(&buf[8]); + res_key = get_unaligned_be64(&buf[0]); + sa_res_key = get_unaligned_be64(&buf[8]); /* * REGISTER_AND_MOVE uses a different SA parameter list containing * SCSI TransportIDs. @@ -3734,10 +3717,7 @@ core_scsi3_pri_read_keys(struct se_cmd *cmd) if (!buf) return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - buf[0] = ((dev->t10_pr.pr_generation >> 24) & 0xff); - buf[1] = ((dev->t10_pr.pr_generation >> 16) & 0xff); - buf[2] = ((dev->t10_pr.pr_generation >> 8) & 0xff); - buf[3] = (dev->t10_pr.pr_generation & 0xff); + put_unaligned_be32(dev->t10_pr.pr_generation, buf); spin_lock(&dev->t10_pr.registration_lock); list_for_each_entry(pr_reg, &dev->t10_pr.registration_list, @@ -3749,23 +3729,13 @@ core_scsi3_pri_read_keys(struct se_cmd *cmd) if ((add_len + 8) > (cmd->data_length - 8)) break; - buf[off++] = ((pr_reg->pr_res_key >> 56) & 0xff); - buf[off++] = ((pr_reg->pr_res_key >> 48) & 0xff); - buf[off++] = ((pr_reg->pr_res_key >> 40) & 0xff); - buf[off++] = ((pr_reg->pr_res_key >> 32) & 0xff); - buf[off++] = ((pr_reg->pr_res_key >> 24) & 0xff); - buf[off++] = ((pr_reg->pr_res_key >> 16) & 0xff); - buf[off++] = ((pr_reg->pr_res_key >> 8) & 0xff); - buf[off++] = (pr_reg->pr_res_key & 0xff); - + put_unaligned_be64(pr_reg->pr_res_key, &buf[off]); + off += 8; add_len += 8; } spin_unlock(&dev->t10_pr.registration_lock); - buf[4] = ((add_len >> 24) & 0xff); - buf[5] = ((add_len >> 16) & 0xff); - buf[6] = ((add_len >> 8) & 0xff); - buf[7] = (add_len & 0xff); + put_unaligned_be32(add_len, &buf[4]); transport_kunmap_data_sg(cmd); @@ -3796,10 +3766,7 @@ core_scsi3_pri_read_reservation(struct se_cmd *cmd) if (!buf) return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - buf[0] = ((dev->t10_pr.pr_generation >> 24) & 0xff); - buf[1] = ((dev->t10_pr.pr_generation >> 16) & 0xff); - buf[2] = ((dev->t10_pr.pr_generation >> 8) & 0xff); - buf[3] = (dev->t10_pr.pr_generation & 0xff); + put_unaligned_be32(dev->t10_pr.pr_generation, &buf[0]); spin_lock(&dev->dev_reservation_lock); pr_reg = dev->dev_pr_res_holder; @@ -3807,10 +3774,7 @@ core_scsi3_pri_read_reservation(struct se_cmd *cmd) /* * Set the hardcoded Additional Length */ - buf[4] = ((add_len >> 24) & 0xff); - buf[5] = ((add_len >> 16) & 0xff); - buf[6] = ((add_len >> 8) & 0xff); - buf[7] = (add_len & 0xff); + put_unaligned_be32(add_len, &buf[4]); if (cmd->data_length < 22) goto err; @@ -3837,14 +3801,7 @@ core_scsi3_pri_read_reservation(struct se_cmd *cmd) else pr_res_key = pr_reg->pr_res_key; - buf[8] = ((pr_res_key >> 56) & 0xff); - buf[9] = ((pr_res_key >> 48) & 0xff); - buf[10] = ((pr_res_key >> 40) & 0xff); - buf[11] = ((pr_res_key >> 32) & 0xff); - buf[12] = ((pr_res_key >> 24) & 0xff); - buf[13] = ((pr_res_key >> 16) & 0xff); - buf[14] = ((pr_res_key >> 8) & 0xff); - buf[15] = (pr_res_key & 0xff); + put_unaligned_be64(pr_res_key, &buf[8]); /* * Set the SCOPE and TYPE */ @@ -3882,8 +3839,7 @@ core_scsi3_pri_report_capabilities(struct se_cmd *cmd) if (!buf) return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - buf[0] = ((add_len >> 8) & 0xff); - buf[1] = (add_len & 0xff); + put_unaligned_be16(add_len, &buf[0]); buf[2] |= 0x10; /* CRH: Compatible Reservation Hanlding bit. */ buf[2] |= 0x08; /* SIP_C: Specify Initiator Ports Capable bit */ buf[2] |= 0x04; /* ATP_C: All Target Ports Capable bit */ @@ -3947,10 +3903,7 @@ core_scsi3_pri_read_full_status(struct se_cmd *cmd) if (!buf) return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - buf[0] = ((dev->t10_pr.pr_generation >> 24) & 0xff); - buf[1] = ((dev->t10_pr.pr_generation >> 16) & 0xff); - buf[2] = ((dev->t10_pr.pr_generation >> 8) & 0xff); - buf[3] = (dev->t10_pr.pr_generation & 0xff); + put_unaligned_be32(dev->t10_pr.pr_generation, &buf[0]); spin_lock(&dev->dev_reservation_lock); if (dev->dev_pr_res_holder) { @@ -3992,14 +3945,8 @@ core_scsi3_pri_read_full_status(struct se_cmd *cmd) /* * Set RESERVATION KEY */ - buf[off++] = ((pr_reg->pr_res_key >> 56) & 0xff); - buf[off++] = ((pr_reg->pr_res_key >> 48) & 0xff); - buf[off++] = ((pr_reg->pr_res_key >> 40) & 0xff); - buf[off++] = ((pr_reg->pr_res_key >> 32) & 0xff); - buf[off++] = ((pr_reg->pr_res_key >> 24) & 0xff); - buf[off++] = ((pr_reg->pr_res_key >> 16) & 0xff); - buf[off++] = ((pr_reg->pr_res_key >> 8) & 0xff); - buf[off++] = (pr_reg->pr_res_key & 0xff); + put_unaligned_be64(pr_reg->pr_res_key, &buf[off]); + off += 8; off += 4; /* Skip Over Reserved area */ /* @@ -4041,8 +3988,8 @@ core_scsi3_pri_read_full_status(struct se_cmd *cmd) if (!pr_reg->pr_reg_all_tg_pt) { u16 sep_rtpi = pr_reg->tg_pt_sep_rtpi; - buf[off++] = ((sep_rtpi >> 8) & 0xff); - buf[off++] = (sep_rtpi & 0xff); + put_unaligned_be16(sep_rtpi, &buf[off]); + off += 2; } else off += 2; /* Skip over RELATIVE TARGET PORT IDENTIFIER */ @@ -4062,10 +4009,7 @@ core_scsi3_pri_read_full_status(struct se_cmd *cmd) /* * Set the ADDITIONAL DESCRIPTOR LENGTH */ - buf[off++] = ((desc_len >> 24) & 0xff); - buf[off++] = ((desc_len >> 16) & 0xff); - buf[off++] = ((desc_len >> 8) & 0xff); - buf[off++] = (desc_len & 0xff); + put_unaligned_be32(desc_len, &buf[off]); /* * Size of full desctipor header minus TransportID * containing $FABRIC_MOD specific) initiator device/port @@ -4082,10 +4026,7 @@ core_scsi3_pri_read_full_status(struct se_cmd *cmd) /* * Set ADDITIONAL_LENGTH */ - buf[4] = ((add_len >> 24) & 0xff); - buf[5] = ((add_len >> 16) & 0xff); - buf[6] = ((add_len >> 8) & 0xff); - buf[7] = (add_len & 0xff); + put_unaligned_be32(add_len, &buf[4]); transport_kunmap_data_sg(cmd); diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 3e4abb13f8ea..e0be4aa38328 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -168,7 +168,7 @@ static void pscsi_tape_read_blocksize(struct se_device *dev, /* * If MODE_SENSE still returns zero, set the default value to 1024. */ - sdev->sector_size = (buf[9] << 16) | (buf[10] << 8) | (buf[11]); + sdev->sector_size = get_unaligned_be24(&buf[9]); out_free: if (!sdev->sector_size) sdev->sector_size = 1024; @@ -209,8 +209,7 @@ pscsi_get_inquiry_vpd_serial(struct scsi_device *sdev, struct t10_wwn *wwn) cdb[0] = INQUIRY; cdb[1] = 0x01; /* Query VPD */ cdb[2] = 0x80; /* Unit Serial Number */ - cdb[3] = (INQUIRY_VPD_SERIAL_LEN >> 8) & 0xff; - cdb[4] = (INQUIRY_VPD_SERIAL_LEN & 0xff); + put_unaligned_be16(INQUIRY_VPD_SERIAL_LEN, &cdb[3]); ret = scsi_execute_req(sdev, cdb, DMA_FROM_DEVICE, buf, INQUIRY_VPD_SERIAL_LEN, NULL, HZ, 1, NULL); @@ -245,8 +244,7 @@ pscsi_get_inquiry_vpd_device_ident(struct scsi_device *sdev, cdb[0] = INQUIRY; cdb[1] = 0x01; /* Query VPD */ cdb[2] = 0x83; /* Device Identifier */ - cdb[3] = (INQUIRY_VPD_DEVICE_IDENTIFIER_LEN >> 8) & 0xff; - cdb[4] = (INQUIRY_VPD_DEVICE_IDENTIFIER_LEN & 0xff); + put_unaligned_be16(INQUIRY_VPD_DEVICE_IDENTIFIER_LEN, &cdb[3]); ret = scsi_execute_req(sdev, cdb, DMA_FROM_DEVICE, buf, INQUIRY_VPD_DEVICE_IDENTIFIER_LEN, @@ -254,7 +252,7 @@ pscsi_get_inquiry_vpd_device_ident(struct scsi_device *sdev, if (ret) goto out; - page_len = (buf[2] << 8) | buf[3]; + page_len = get_unaligned_be16(&buf[2]); while (page_len > 0) { /* Grab a pointer to the Identification descriptor */ page_83 = &buf[off]; @@ -669,19 +667,17 @@ after_mode_sense: } if (cdb[0] == MODE_SELECT) - bdl = (buf[3]); + bdl = buf[3]; else - bdl = (buf[6] << 8) | (buf[7]); + bdl = get_unaligned_be16(&buf[6]); if (!bdl) goto after_mode_select; if (cdb[0] == MODE_SELECT) - blocksize = (buf[9] << 16) | (buf[10] << 8) | - (buf[11]); + blocksize = get_unaligned_be24(&buf[9]); else - blocksize = (buf[13] << 16) | (buf[14] << 8) | - (buf[15]); + blocksize = get_unaligned_be24(&buf[13]); sd->sector_size = blocksize; } diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index ff4a6ec30adf..ca42fba882db 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -71,14 +71,8 @@ sbc_emulate_readcapacity(struct se_cmd *cmd) else blocks = (u32)blocks_long; - buf[0] = (blocks >> 24) & 0xff; - buf[1] = (blocks >> 16) & 0xff; - buf[2] = (blocks >> 8) & 0xff; - buf[3] = blocks & 0xff; - buf[4] = (dev->dev_attrib.block_size >> 24) & 0xff; - buf[5] = (dev->dev_attrib.block_size >> 16) & 0xff; - buf[6] = (dev->dev_attrib.block_size >> 8) & 0xff; - buf[7] = dev->dev_attrib.block_size & 0xff; + put_unaligned_be32(blocks, &buf[0]); + put_unaligned_be32(dev->dev_attrib.block_size, &buf[4]); rbuf = transport_kmap_data_sg(cmd); if (rbuf) { @@ -102,18 +96,8 @@ sbc_emulate_readcapacity_16(struct se_cmd *cmd) unsigned long long blocks = dev->transport->get_blocks(dev); memset(buf, 0, sizeof(buf)); - buf[0] = (blocks >> 56) & 0xff; - buf[1] = (blocks >> 48) & 0xff; - buf[2] = (blocks >> 40) & 0xff; - buf[3] = (blocks >> 32) & 0xff; - buf[4] = (blocks >> 24) & 0xff; - buf[5] = (blocks >> 16) & 0xff; - buf[6] = (blocks >> 8) & 0xff; - buf[7] = blocks & 0xff; - buf[8] = (dev->dev_attrib.block_size >> 24) & 0xff; - buf[9] = (dev->dev_attrib.block_size >> 16) & 0xff; - buf[10] = (dev->dev_attrib.block_size >> 8) & 0xff; - buf[11] = dev->dev_attrib.block_size & 0xff; + put_unaligned_be64(blocks, &buf[0]); + put_unaligned_be32(dev->dev_attrib.block_size, &buf[8]); /* * Set P_TYPE and PROT_EN bits for DIF support */ @@ -134,8 +118,8 @@ sbc_emulate_readcapacity_16(struct se_cmd *cmd) if (dev->transport->get_alignment_offset_lbas) { u16 lalba = dev->transport->get_alignment_offset_lbas(dev); - buf[14] = (lalba >> 8) & 0x3f; - buf[15] = lalba & 0xff; + + put_unaligned_be16(lalba, &buf[14]); } /* @@ -262,18 +246,17 @@ static inline u32 transport_get_sectors_6(unsigned char *cdb) static inline u32 transport_get_sectors_10(unsigned char *cdb) { - return (u32)(cdb[7] << 8) + cdb[8]; + return get_unaligned_be16(&cdb[7]); } static inline u32 transport_get_sectors_12(unsigned char *cdb) { - return (u32)(cdb[6] << 24) + (cdb[7] << 16) + (cdb[8] << 8) + cdb[9]; + return get_unaligned_be32(&cdb[6]); } static inline u32 transport_get_sectors_16(unsigned char *cdb) { - return (u32)(cdb[10] << 24) + (cdb[11] << 16) + - (cdb[12] << 8) + cdb[13]; + return get_unaligned_be32(&cdb[10]); } /* @@ -281,29 +264,23 @@ static inline u32 transport_get_sectors_16(unsigned char *cdb) */ static inline u32 transport_get_sectors_32(unsigned char *cdb) { - return (u32)(cdb[28] << 24) + (cdb[29] << 16) + - (cdb[30] << 8) + cdb[31]; + return get_unaligned_be32(&cdb[28]); } static inline u32 transport_lba_21(unsigned char *cdb) { - return ((cdb[1] & 0x1f) << 16) | (cdb[2] << 8) | cdb[3]; + return get_unaligned_be24(&cdb[1]) & 0x1fffff; } static inline u32 transport_lba_32(unsigned char *cdb) { - return (cdb[2] << 24) | (cdb[3] << 16) | (cdb[4] << 8) | cdb[5]; + return get_unaligned_be32(&cdb[2]); } static inline unsigned long long transport_lba_64(unsigned char *cdb) { - unsigned int __v1, __v2; - - __v1 = (cdb[2] << 24) | (cdb[3] << 16) | (cdb[4] << 8) | cdb[5]; - __v2 = (cdb[6] << 24) | (cdb[7] << 16) | (cdb[8] << 8) | cdb[9]; - - return ((unsigned long long)__v2) | (unsigned long long)__v1 << 32; + return get_unaligned_be64(&cdb[2]); } /* @@ -311,12 +288,7 @@ static inline unsigned long long transport_lba_64(unsigned char *cdb) */ static inline unsigned long long transport_lba_64_ext(unsigned char *cdb) { - unsigned int __v1, __v2; - - __v1 = (cdb[12] << 24) | (cdb[13] << 16) | (cdb[14] << 8) | cdb[15]; - __v2 = (cdb[16] << 24) | (cdb[17] << 16) | (cdb[18] << 8) | cdb[19]; - - return ((unsigned long long)__v2) | (unsigned long long)__v1 << 32; + return get_unaligned_be64(&cdb[12]); } static sense_reason_t @@ -1051,8 +1023,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops) cmd->t_task_cdb[1] & 0x1f); return TCM_INVALID_CDB_FIELD; } - size = (cdb[10] << 24) | (cdb[11] << 16) | - (cdb[12] << 8) | cdb[13]; + size = get_unaligned_be32(&cdb[10]); break; case SYNCHRONIZE_CACHE: case SYNCHRONIZE_CACHE_16: diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c index 2a91ed3ef380..f59ac7671031 100644 --- a/drivers/target/target_core_spc.c +++ b/drivers/target/target_core_spc.c @@ -287,8 +287,8 @@ check_t10_vend_desc: /* Skip over Obsolete field in RTPI payload * in Table 472 */ off += 2; - buf[off++] = ((lun->lun_rtpi >> 8) & 0xff); - buf[off++] = (lun->lun_rtpi & 0xff); + put_unaligned_be16(lun->lun_rtpi, &buf[off]); + off += 2; len += 8; /* Header size + Designation descriptor */ /* * Target port group identifier, see spc4r17 @@ -316,8 +316,8 @@ check_t10_vend_desc: off++; /* Skip over Reserved */ buf[off++] = 4; /* DESIGNATOR LENGTH */ off += 2; /* Skip over Reserved Field */ - buf[off++] = ((tg_pt_gp_id >> 8) & 0xff); - buf[off++] = (tg_pt_gp_id & 0xff); + put_unaligned_be16(tg_pt_gp_id, &buf[off]); + off += 2; len += 8; /* Header size + Designation descriptor */ /* * Logical Unit Group identifier, see spc4r17 @@ -343,8 +343,8 @@ check_lu_gp: off++; /* Skip over Reserved */ buf[off++] = 4; /* DESIGNATOR LENGTH */ off += 2; /* Skip over Reserved Field */ - buf[off++] = ((lu_gp_id >> 8) & 0xff); - buf[off++] = (lu_gp_id & 0xff); + put_unaligned_be16(lu_gp_id, &buf[off]); + off += 2; len += 8; /* Header size + Designation descriptor */ /* * SCSI name string designator, see spc4r17 @@ -431,8 +431,7 @@ check_scsi_name: /* Header size + Designation descriptor */ len += (scsi_target_len + 4); } - buf[2] = ((len >> 8) & 0xff); - buf[3] = (len & 0xff); /* Page Length for VPD 0x83 */ + put_unaligned_be16(len, &buf[2]); /* Page Length for VPD 0x83 */ return 0; } EXPORT_SYMBOL(spc_emulate_evpd_83); @@ -1288,7 +1287,7 @@ spc_parse_cdb(struct se_cmd *cmd, unsigned int *size) cmd->execute_cmd = spc_emulate_modeselect; break; case MODE_SELECT_10: - *size = (cdb[7] << 8) + cdb[8]; + *size = get_unaligned_be16(&cdb[7]); cmd->execute_cmd = spc_emulate_modeselect; break; case MODE_SENSE: @@ -1296,25 +1295,25 @@ spc_parse_cdb(struct se_cmd *cmd, unsigned int *size) cmd->execute_cmd = spc_emulate_modesense; break; case MODE_SENSE_10: - *size = (cdb[7] << 8) + cdb[8]; + *size = get_unaligned_be16(&cdb[7]); cmd->execute_cmd = spc_emulate_modesense; break; case LOG_SELECT: case LOG_SENSE: - *size = (cdb[7] << 8) + cdb[8]; + *size = get_unaligned_be16(&cdb[7]); break; case PERSISTENT_RESERVE_IN: - *size = (cdb[7] << 8) + cdb[8]; + *size = get_unaligned_be16(&cdb[7]); cmd->execute_cmd = target_scsi3_emulate_pr_in; break; case PERSISTENT_RESERVE_OUT: - *size = (cdb[7] << 8) + cdb[8]; + *size = get_unaligned_be16(&cdb[7]); cmd->execute_cmd = target_scsi3_emulate_pr_out; break; case RELEASE: case RELEASE_10: if (cdb[0] == RELEASE_10) - *size = (cdb[7] << 8) | cdb[8]; + *size = get_unaligned_be16(&cdb[7]); else *size = cmd->data_length; @@ -1327,7 +1326,7 @@ spc_parse_cdb(struct se_cmd *cmd, unsigned int *size) * Assume the passthrough or $FABRIC_MOD will tell us about it. */ if (cdb[0] == RESERVE_10) - *size = (cdb[7] << 8) | cdb[8]; + *size = get_unaligned_be16(&cdb[7]); else *size = cmd->data_length; @@ -1338,7 +1337,7 @@ spc_parse_cdb(struct se_cmd *cmd, unsigned int *size) cmd->execute_cmd = spc_emulate_request_sense; break; case INQUIRY: - *size = (cdb[3] << 8) + cdb[4]; + *size = get_unaligned_be16(&cdb[3]); /* * Do implicit HEAD_OF_QUEUE processing for INQUIRY. @@ -1349,7 +1348,7 @@ spc_parse_cdb(struct se_cmd *cmd, unsigned int *size) break; case SECURITY_PROTOCOL_IN: case SECURITY_PROTOCOL_OUT: - *size = (cdb[6] << 24) | (cdb[7] << 16) | (cdb[8] << 8) | cdb[9]; + *size = get_unaligned_be32(&cdb[6]); break; case EXTENDED_COPY: *size = get_unaligned_be32(&cdb[10]); @@ -1361,19 +1360,18 @@ spc_parse_cdb(struct se_cmd *cmd, unsigned int *size) break; case READ_ATTRIBUTE: case WRITE_ATTRIBUTE: - *size = (cdb[10] << 24) | (cdb[11] << 16) | - (cdb[12] << 8) | cdb[13]; + *size = get_unaligned_be32(&cdb[10]); break; case RECEIVE_DIAGNOSTIC: case SEND_DIAGNOSTIC: - *size = (cdb[3] << 8) | cdb[4]; + *size = get_unaligned_be16(&cdb[3]); break; case WRITE_BUFFER: - *size = (cdb[6] << 16) + (cdb[7] << 8) + cdb[8]; + *size = get_unaligned_be24(&cdb[6]); break; case REPORT_LUNS: cmd->execute_cmd = spc_emulate_report_luns; - *size = (cdb[6] << 24) | (cdb[7] << 16) | (cdb[8] << 8) | cdb[9]; + *size = get_unaligned_be32(&cdb[6]); /* * Do implicit HEAD_OF_QUEUE processing for REPORT_LUNS * See spc4r17 section 5.3 diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c index cac5a20a4de0..f12cf0c12531 100644 --- a/drivers/target/target_core_xcopy.c +++ b/drivers/target/target_core_xcopy.c @@ -311,9 +311,7 @@ static int target_xcopy_parse_segdesc_02(struct se_cmd *se_cmd, struct xcopy_op (unsigned long long)xop->dst_lba); if (dc != 0) { - xop->dbl = (desc[29] & 0xff) << 16; - xop->dbl |= (desc[30] & 0xff) << 8; - xop->dbl |= desc[31] & 0xff; + xop->dbl = get_unaligned_be24(&desc[29]); pr_debug("XCOPY seg desc 0x02: DC=1 w/ dbl: %u\n", xop->dbl); } diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index e475531565fd..b76071161cdc 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -2,6 +2,7 @@ #define TARGET_CORE_BACKEND_H #include +#include #include #define TRANSPORT_FLAG_PASSTHROUGH 0x1 @@ -109,4 +110,11 @@ sector_t target_to_linux_sector(struct se_device *dev, sector_t lb); bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib, struct request_queue *q); + +/* Only use get_unaligned_be24() if reading p - 1 is allowed. */ +static inline uint32_t get_unaligned_be24(const uint8_t *const p) +{ + return get_unaligned_be32(p - 1) & 0xffffffU; +} + #endif /* TARGET_CORE_BACKEND_H */ -- cgit v1.2.3-59-g8ed1b From d877d7275be34ad70ce92bcbb4bb36cec77ed004 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 23 May 2017 16:48:29 -0700 Subject: target: Fix a deadlock between the XCOPY code and iSCSI session shutdown Move the code for parsing an XCOPY command from the context of the iSCSI receiver thread to the context of the XCOPY workqueue. Keep the simple XCOPY checks in the context of the iSCSI receiver thread. Move the code for allocating and freeing struct xcopy_op from the code that parses an XCOPY command to its caller. This patch fixes the following deadlock: ====================================================== [ INFO: possible circular locking dependency detected ] 4.10.0-rc7-dbg+ #1 Not tainted ------------------------------------------------------- rmdir/13321 is trying to acquire lock: (&sess->cmdsn_mutex){+.+.+.}, at: [] iscsit_free_all_ooo_cmdsns+0x2d/0xb0 [iscsi_target_mod] but task is already holding lock: (&sb->s_type->i_mutex_key#14){++++++}, at: [] vfs_rmdir+0x50/0x140 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&sb->s_type->i_mutex_key#14){++++++}: lock_acquire+0x71/0x90 down_write+0x3f/0x70 configfs_depend_item+0x3a/0xb0 [configfs] target_depend_item+0x13/0x20 [target_core_mod] target_xcopy_locate_se_dev_e4+0xdd/0x1a0 [target_core_mod] target_do_xcopy+0x34b/0x970 [target_core_mod] __target_execute_cmd+0x22/0xa0 [target_core_mod] target_execute_cmd+0x233/0x2c0 [target_core_mod] iscsit_execute_cmd+0x208/0x270 [iscsi_target_mod] iscsit_sequence_cmd+0x10b/0x190 [iscsi_target_mod] iscsit_get_rx_pdu+0x37d/0xcd0 [iscsi_target_mod] iscsi_target_rx_thread+0x6e/0xa0 [iscsi_target_mod] kthread+0x102/0x140 ret_from_fork+0x31/0x40 -> #0 (&sess->cmdsn_mutex){+.+.+.}: __lock_acquire+0x10e6/0x1260 lock_acquire+0x71/0x90 mutex_lock_nested+0x5f/0x670 iscsit_free_all_ooo_cmdsns+0x2d/0xb0 [iscsi_target_mod] iscsit_close_session+0xac/0x200 [iscsi_target_mod] lio_tpg_close_session+0x9f/0xb0 [iscsi_target_mod] target_shutdown_sessions+0xc3/0xd0 [target_core_mod] core_tpg_del_initiator_node_acl+0x91/0x140 [target_core_mod] target_fabric_nacl_base_release+0x20/0x30 [target_core_mod] config_item_release+0x5a/0xc0 [configfs] config_item_put+0x1d/0x1f [configfs] configfs_rmdir+0x1a6/0x300 [configfs] vfs_rmdir+0xb7/0x140 do_rmdir+0x1f4/0x200 SyS_rmdir+0x11/0x20 entry_SYSCALL_64_fastpath+0x23/0xc6 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&sb->s_type->i_mutex_key#14); lock(&sess->cmdsn_mutex); lock(&sb->s_type->i_mutex_key#14); lock(&sess->cmdsn_mutex); *** DEADLOCK *** 3 locks held by rmdir/13321: #0: (sb_writers#10){.+.+.+}, at: [] mnt_want_write+0x1f/0x50 #1: (&default_group_class[depth - 1]#2/1){+.+.+.}, at: [] do_rmdir+0x15e/0x200 #2: (&sb->s_type->i_mutex_key#14){++++++}, at: [] vfs_rmdir+0x50/0x140 stack backtrace: CPU: 2 PID: 13321 Comm: rmdir Not tainted 4.10.0-rc7-dbg+ #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.0.0-prebuilt.qemu-project.org 04/01/2014 Call Trace: dump_stack+0x86/0xc3 print_circular_bug+0x1c7/0x220 __lock_acquire+0x10e6/0x1260 lock_acquire+0x71/0x90 mutex_lock_nested+0x5f/0x670 iscsit_free_all_ooo_cmdsns+0x2d/0xb0 [iscsi_target_mod] iscsit_close_session+0xac/0x200 [iscsi_target_mod] lio_tpg_close_session+0x9f/0xb0 [iscsi_target_mod] target_shutdown_sessions+0xc3/0xd0 [target_core_mod] core_tpg_del_initiator_node_acl+0x91/0x140 [target_core_mod] target_fabric_nacl_base_release+0x20/0x30 [target_core_mod] config_item_release+0x5a/0xc0 [configfs] config_item_put+0x1d/0x1f [configfs] configfs_rmdir+0x1a6/0x300 [configfs] vfs_rmdir+0xb7/0x140 do_rmdir+0x1f4/0x200 SyS_rmdir+0x11/0x20 entry_SYSCALL_64_fastpath+0x23/0xc6 Signed-off-by: Bart Van Assche Cc: Hannes Reinecke Cc: Christoph Hellwig Cc: Andy Grover Cc: David Disseldorp Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_xcopy.c | 110 +++++++++++++++++++++++-------------- 1 file changed, 69 insertions(+), 41 deletions(-) diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c index f12cf0c12531..56738a41e346 100644 --- a/drivers/target/target_core_xcopy.c +++ b/drivers/target/target_core_xcopy.c @@ -40,6 +40,8 @@ static struct workqueue_struct *xcopy_wq = NULL; +static sense_reason_t target_parse_xcopy_cmd(struct xcopy_op *xop); + static int target_xcopy_gen_naa_ieee(struct se_device *dev, unsigned char *buf) { int off = 0; @@ -779,13 +781,24 @@ static int target_xcopy_write_destination( static void target_xcopy_do_work(struct work_struct *work) { struct xcopy_op *xop = container_of(work, struct xcopy_op, xop_work); - struct se_device *src_dev = xop->src_dev, *dst_dev = xop->dst_dev; struct se_cmd *ec_cmd = xop->xop_se_cmd; - sector_t src_lba = xop->src_lba, dst_lba = xop->dst_lba, end_lba; + struct se_device *src_dev, *dst_dev; + sector_t src_lba, dst_lba, end_lba; unsigned int max_sectors; - int rc; - unsigned short nolb = xop->nolb, cur_nolb, max_nolb, copied_nolb = 0; + int rc = 0; + unsigned short nolb, cur_nolb, max_nolb, copied_nolb = 0; + + if (target_parse_xcopy_cmd(xop) != TCM_NO_SENSE) + goto err_free; + if (WARN_ON_ONCE(!xop->src_dev) || WARN_ON_ONCE(!xop->dst_dev)) + goto err_free; + + src_dev = xop->src_dev; + dst_dev = xop->dst_dev; + src_lba = xop->src_lba; + dst_lba = xop->dst_lba; + nolb = xop->nolb; end_lba = src_lba + nolb; /* * Break up XCOPY I/O into hw_max_sectors sized I/O based on the @@ -853,6 +866,8 @@ static void target_xcopy_do_work(struct work_struct *work) out: xcopy_pt_undepend_remotedev(xop); + +err_free: kfree(xop); /* * Don't override an error scsi status if it has already been set @@ -865,48 +880,22 @@ out: target_complete_cmd(ec_cmd, ec_cmd->scsi_status); } -sense_reason_t target_do_xcopy(struct se_cmd *se_cmd) +/* + * Returns TCM_NO_SENSE upon success or a sense code != TCM_NO_SENSE if parsing + * fails. + */ +static sense_reason_t target_parse_xcopy_cmd(struct xcopy_op *xop) { - struct se_device *dev = se_cmd->se_dev; - struct xcopy_op *xop = NULL; + struct se_cmd *se_cmd = xop->xop_se_cmd; unsigned char *p = NULL, *seg_desc; - unsigned int list_id, list_id_usage, sdll, inline_dl, sa; + unsigned int list_id, list_id_usage, sdll, inline_dl; sense_reason_t ret = TCM_INVALID_PARAMETER_LIST; int rc; unsigned short tdll; - if (!dev->dev_attrib.emulate_3pc) { - pr_err("EXTENDED_COPY operation explicitly disabled\n"); - return TCM_UNSUPPORTED_SCSI_OPCODE; - } - - sa = se_cmd->t_task_cdb[1] & 0x1f; - if (sa != 0x00) { - pr_err("EXTENDED_COPY(LID4) not supported\n"); - return TCM_UNSUPPORTED_SCSI_OPCODE; - } - - if (se_cmd->data_length == 0) { - target_complete_cmd(se_cmd, SAM_STAT_GOOD); - return TCM_NO_SENSE; - } - if (se_cmd->data_length < XCOPY_HDR_LEN) { - pr_err("XCOPY parameter truncation: length %u < hdr_len %u\n", - se_cmd->data_length, XCOPY_HDR_LEN); - return TCM_PARAMETER_LIST_LENGTH_ERROR; - } - - xop = kzalloc(sizeof(struct xcopy_op), GFP_KERNEL); - if (!xop) { - pr_err("Unable to allocate xcopy_op\n"); - return TCM_OUT_OF_RESOURCES; - } - xop->xop_se_cmd = se_cmd; - p = transport_kmap_data_sg(se_cmd); if (!p) { pr_err("transport_kmap_data_sg() failed in target_do_xcopy\n"); - kfree(xop); return TCM_OUT_OF_RESOURCES; } @@ -975,18 +964,57 @@ sense_reason_t target_do_xcopy(struct se_cmd *se_cmd) pr_debug("XCOPY: Processed %d target descriptors, length: %u\n", rc, rc * XCOPY_TARGET_DESC_LEN); transport_kunmap_data_sg(se_cmd); - - INIT_WORK(&xop->xop_work, target_xcopy_do_work); - queue_work(xcopy_wq, &xop->xop_work); return TCM_NO_SENSE; out: if (p) transport_kunmap_data_sg(se_cmd); - kfree(xop); return ret; } +sense_reason_t target_do_xcopy(struct se_cmd *se_cmd) +{ + struct se_device *dev = se_cmd->se_dev; + struct xcopy_op *xop; + unsigned int sa; + + if (!dev->dev_attrib.emulate_3pc) { + pr_err("EXTENDED_COPY operation explicitly disabled\n"); + return TCM_UNSUPPORTED_SCSI_OPCODE; + } + + sa = se_cmd->t_task_cdb[1] & 0x1f; + if (sa != 0x00) { + pr_err("EXTENDED_COPY(LID4) not supported\n"); + return TCM_UNSUPPORTED_SCSI_OPCODE; + } + + if (se_cmd->data_length == 0) { + target_complete_cmd(se_cmd, SAM_STAT_GOOD); + return TCM_NO_SENSE; + } + if (se_cmd->data_length < XCOPY_HDR_LEN) { + pr_err("XCOPY parameter truncation: length %u < hdr_len %u\n", + se_cmd->data_length, XCOPY_HDR_LEN); + return TCM_PARAMETER_LIST_LENGTH_ERROR; + } + + xop = kzalloc(sizeof(struct xcopy_op), GFP_KERNEL); + if (!xop) + goto err; + xop->xop_se_cmd = se_cmd; + INIT_WORK(&xop->xop_work, target_xcopy_do_work); + if (WARN_ON_ONCE(!queue_work(xcopy_wq, &xop->xop_work))) + goto free; + return TCM_NO_SENSE; + +free: + kfree(xop); + +err: + return TCM_OUT_OF_RESOURCES; +} + static sense_reason_t target_rcr_operating_parameters(struct se_cmd *se_cmd) { unsigned char *p; -- cgit v1.2.3-59-g8ed1b From 13fdd4458ed1b808946fd7baba657b6a51d3c72b Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 23 May 2017 16:48:35 -0700 Subject: IB/srpt: Make a debug statement in srpt_abort_cmd() more informative Do not only report the state of the I/O context before srpt_abort_cmd() was called but also the new state assigned by srpt_abort_cmd() Signed-off-by: Bart Van Assche Reviewed-by: Hannes Reinecke Cc: Doug Ledford Cc: Christoph Hellwig Cc: Andy Grover Cc: David Disseldorp Signed-off-by: Nicholas Bellinger --- drivers/infiniband/ulp/srpt/ib_srpt.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 1ced0731c140..402275be0931 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -1157,8 +1157,8 @@ static int srpt_abort_cmd(struct srpt_send_ioctx *ioctx) } spin_unlock_irqrestore(&ioctx->spinlock, flags); - pr_debug("Aborting cmd with state %d and tag %lld\n", state, - ioctx->cmd.tag); + pr_debug("Aborting cmd with state %d -> %d and tag %lld\n", state, + ioctx->state, ioctx->cmd.tag); switch (state) { case SRPT_STATE_NEW: -- cgit v1.2.3-59-g8ed1b From 9f4ab18ac51dc87345a9cbd2527e6acf7a0a9335 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 23 May 2017 16:48:36 -0700 Subject: xen/scsiback: Fix a TMR related use-after-free scsiback_release_cmd() must not dereference se_cmd->se_tmr_req because that memory is freed by target_free_cmd_mem() before scsiback_release_cmd() is called. Fix this use-after-free by inlining struct scsiback_tmr into struct vscsibk_pend. Signed-off-by: Bart Van Assche Reviewed-by: Juergen Gross Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: David Disseldorp Cc: xen-devel@lists.xenproject.org Cc: # 3.18+ Signed-off-by: Nicholas Bellinger --- drivers/xen/xen-scsiback.c | 33 +++++++++------------------------ 1 file changed, 9 insertions(+), 24 deletions(-) diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index d6950e0802b7..980f32817305 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -134,9 +134,7 @@ struct vscsibk_pend { struct page *pages[VSCSI_MAX_GRANTS]; struct se_cmd se_cmd; -}; -struct scsiback_tmr { atomic_t tmr_complete; wait_queue_head_t tmr_wait; }; @@ -599,26 +597,20 @@ static void scsiback_device_action(struct vscsibk_pend *pending_req, struct scsiback_tpg *tpg = pending_req->v2p->tpg; struct scsiback_nexus *nexus = tpg->tpg_nexus; struct se_cmd *se_cmd = &pending_req->se_cmd; - struct scsiback_tmr *tmr; u64 unpacked_lun = pending_req->v2p->lun; int rc, err = FAILED; - tmr = kzalloc(sizeof(struct scsiback_tmr), GFP_KERNEL); - if (!tmr) { - target_put_sess_cmd(se_cmd); - goto err; - } - - init_waitqueue_head(&tmr->tmr_wait); + init_waitqueue_head(&pending_req->tmr_wait); rc = target_submit_tmr(&pending_req->se_cmd, nexus->tvn_se_sess, &pending_req->sense_buffer[0], - unpacked_lun, tmr, act, GFP_KERNEL, + unpacked_lun, NULL, act, GFP_KERNEL, tag, TARGET_SCF_ACK_KREF); if (rc) goto err; - wait_event(tmr->tmr_wait, atomic_read(&tmr->tmr_complete)); + wait_event(pending_req->tmr_wait, + atomic_read(&pending_req->tmr_complete)); err = (se_cmd->se_tmr_req->response == TMR_FUNCTION_COMPLETE) ? SUCCESS : FAILED; @@ -626,9 +618,8 @@ static void scsiback_device_action(struct vscsibk_pend *pending_req, scsiback_do_resp_with_sense(NULL, err, 0, pending_req); transport_generic_free_cmd(&pending_req->se_cmd, 1); return; + err: - if (tmr) - kfree(tmr); scsiback_do_resp_with_sense(NULL, err, 0, pending_req); } @@ -1389,12 +1380,6 @@ static int scsiback_check_stop_free(struct se_cmd *se_cmd) static void scsiback_release_cmd(struct se_cmd *se_cmd) { struct se_session *se_sess = se_cmd->se_sess; - struct se_tmr_req *se_tmr = se_cmd->se_tmr_req; - - if (se_tmr && se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) { - struct scsiback_tmr *tmr = se_tmr->fabric_tmr_ptr; - kfree(tmr); - } percpu_ida_free(&se_sess->sess_tag_pool, se_cmd->map_tag); } @@ -1455,11 +1440,11 @@ static int scsiback_queue_status(struct se_cmd *se_cmd) static void scsiback_queue_tm_rsp(struct se_cmd *se_cmd) { - struct se_tmr_req *se_tmr = se_cmd->se_tmr_req; - struct scsiback_tmr *tmr = se_tmr->fabric_tmr_ptr; + struct vscsibk_pend *pending_req = container_of(se_cmd, + struct vscsibk_pend, se_cmd); - atomic_set(&tmr->tmr_complete, 1); - wake_up(&tmr->tmr_wait); + atomic_set(&pending_req->tmr_complete, 1); + wake_up(&pending_req->tmr_wait); } static void scsiback_aborted_task(struct se_cmd *se_cmd) -- cgit v1.2.3-59-g8ed1b From e3eac12442c2678d64b655e9768bda1be65e0b68 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 23 May 2017 16:48:37 -0700 Subject: xen/scsiback: Replace a waitqueue and a counter by a completion This patch simplifies the implementation of the scsiback driver but does not change its behavior. Signed-off-by: Bart Van Assche Reviewed-by: Juergen Gross Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: David Disseldorp Cc: xen-devel@lists.xenproject.org Signed-off-by: Nicholas Bellinger --- drivers/xen/xen-scsiback.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index 980f32817305..4cb33a0916a8 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -135,8 +135,7 @@ struct vscsibk_pend { struct se_cmd se_cmd; - atomic_t tmr_complete; - wait_queue_head_t tmr_wait; + struct completion tmr_done; }; #define VSCSI_DEFAULT_SESSION_TAGS 128 @@ -600,7 +599,7 @@ static void scsiback_device_action(struct vscsibk_pend *pending_req, u64 unpacked_lun = pending_req->v2p->lun; int rc, err = FAILED; - init_waitqueue_head(&pending_req->tmr_wait); + init_completion(&pending_req->tmr_done); rc = target_submit_tmr(&pending_req->se_cmd, nexus->tvn_se_sess, &pending_req->sense_buffer[0], @@ -609,8 +608,7 @@ static void scsiback_device_action(struct vscsibk_pend *pending_req, if (rc) goto err; - wait_event(pending_req->tmr_wait, - atomic_read(&pending_req->tmr_complete)); + wait_for_completion(&pending_req->tmr_done); err = (se_cmd->se_tmr_req->response == TMR_FUNCTION_COMPLETE) ? SUCCESS : FAILED; @@ -1443,8 +1441,7 @@ static void scsiback_queue_tm_rsp(struct se_cmd *se_cmd) struct vscsibk_pend *pending_req = container_of(se_cmd, struct vscsibk_pend, se_cmd); - atomic_set(&pending_req->tmr_complete, 1); - wake_up(&pending_req->tmr_wait); + complete(&pending_req->tmr_done); } static void scsiback_aborted_task(struct se_cmd *se_cmd) -- cgit v1.2.3-59-g8ed1b From af90e84d1f535827f4c593436a807b1efa9f6f2b Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 23 May 2017 16:48:38 -0700 Subject: xen/scsiback: Make TMF processing slightly faster Target drivers must guarantee that struct se_cmd and struct se_tmr_req exist as long as target_tmr_work() is in progress. Since the last access by the LIO core is a call to .check_stop_free() and since the Xen scsiback .check_stop_free() drops a reference to the TMF, it is already guaranteed that the struct se_cmd that corresponds to the TMF exists as long as target_tmr_work() is in progress. Hence change the second argument of transport_generic_free_cmd() from 1 into 0. Signed-off-by: Bart Van Assche Reviewed-by: Juergen Gross Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: David Disseldorp Cc: xen-devel@lists.xenproject.org Signed-off-by: Nicholas Bellinger --- drivers/xen/xen-scsiback.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index 4cb33a0916a8..7bc88fd43cfc 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -614,7 +614,7 @@ static void scsiback_device_action(struct vscsibk_pend *pending_req, SUCCESS : FAILED; scsiback_do_resp_with_sense(NULL, err, 0, pending_req); - transport_generic_free_cmd(&pending_req->se_cmd, 1); + transport_generic_free_cmd(&pending_req->se_cmd, 0); return; err: -- cgit v1.2.3-59-g8ed1b From 03db016a1bf2d35f41c08aad2ca4f4f18eeda4be Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Fri, 2 Jun 2017 23:33:56 -0700 Subject: iscsi-target: Kill left-over iscsi_target_do_cleanup With commit 25cdda95fda7 in place to address the initial login PDU asynchronous socket close OOPs, go ahead and kill off the left-over iscsi_target_do_cleanup() and ->login_cleanup_work. Reported-by: Mike Christie Cc: Mike Christie Signed-off-by: Nicholas Bellinger --- drivers/target/iscsi/iscsi_target_nego.c | 24 ------------------------ include/target/iscsi/iscsi_target_core.h | 1 - 2 files changed, 25 deletions(-) diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c index 6f88b31242b0..96df63f1f795 100644 --- a/drivers/target/iscsi/iscsi_target_nego.c +++ b/drivers/target/iscsi/iscsi_target_nego.c @@ -655,28 +655,6 @@ err: iscsit_deaccess_np(np, tpg, tpg_np); } -static void iscsi_target_do_cleanup(struct work_struct *work) -{ - struct iscsi_conn *conn = container_of(work, - struct iscsi_conn, login_cleanup_work.work); - struct sock *sk = conn->sock->sk; - struct iscsi_login *login = conn->login; - struct iscsi_np *np = login->np; - struct iscsi_portal_group *tpg = conn->tpg; - struct iscsi_tpg_np *tpg_np = conn->tpg_np; - - pr_debug("Entering iscsi_target_do_cleanup\n"); - - cancel_delayed_work_sync(&conn->login_work); - conn->orig_state_change(sk); - - iscsi_target_restore_sock_callbacks(conn); - iscsi_target_login_drop(conn, login); - iscsit_deaccess_np(np, tpg, tpg_np); - - pr_debug("iscsi_target_do_cleanup done()\n"); -} - static void iscsi_target_sk_state_change(struct sock *sk) { struct iscsi_conn *conn; @@ -1082,7 +1060,6 @@ int iscsi_target_locate_portal( int sessiontype = 0, ret = 0, tag_num, tag_size; INIT_DELAYED_WORK(&conn->login_work, iscsi_target_do_login_rx); - INIT_DELAYED_WORK(&conn->login_cleanup_work, iscsi_target_do_cleanup); iscsi_target_set_sock_callbacks(conn); login->np = np; @@ -1331,7 +1308,6 @@ int iscsi_target_start_negotiation( if (ret < 0) { cancel_delayed_work_sync(&conn->login_work); - cancel_delayed_work_sync(&conn->login_cleanup_work); iscsi_target_restore_sock_callbacks(conn); iscsi_remove_failed_auth_entry(conn); } diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index 5f17fb770477..7948fc68286b 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -560,7 +560,6 @@ struct iscsi_conn { #define LOGIN_FLAGS_INITIAL_PDU 8 unsigned long login_flags; struct delayed_work login_work; - struct delayed_work login_cleanup_work; struct iscsi_login *login; struct timer_list nopin_timer; struct timer_list nopin_response_timer; -- cgit v1.2.3-59-g8ed1b From c00e6220231542c6409780a3e9bfa44be7d94f3a Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 23 May 2017 16:48:28 -0700 Subject: target: Introduce a function that shows the command state Introduce target_show_cmd() and use it where appropriate. If transport_wait_for_tasks() takes too long, make it show the state of the command it is waiting for. (Add missing brackets around multi-line conditions - nab) Signed-off-by: Bart Van Assche Cc: Hannes Reinecke Cc: Christoph Hellwig Cc: Andy Grover Cc: David Disseldorp Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_tmr.c | 18 ++--- drivers/target/target_core_transport.c | 122 +++++++++++++++++++++++++++++---- include/target/target_core_fabric.h | 1 + 3 files changed, 114 insertions(+), 27 deletions(-) diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c index 13f47bf4d16b..e22847bd79b9 100644 --- a/drivers/target/target_core_tmr.c +++ b/drivers/target/target_core_tmr.c @@ -355,20 +355,10 @@ static void core_tmr_drain_state_list( cmd = list_entry(drain_task_list.next, struct se_cmd, state_list); list_del_init(&cmd->state_list); - pr_debug("LUN_RESET: %s cmd: %p" - " ITT/CmdSN: 0x%08llx/0x%08x, i_state: %d, t_state: %d" - "cdb: 0x%02x\n", - (preempt_and_abort_list) ? "Preempt" : "", cmd, - cmd->tag, 0, - cmd->se_tfo->get_cmd_state(cmd), cmd->t_state, - cmd->t_task_cdb[0]); - pr_debug("LUN_RESET: ITT[0x%08llx] - pr_res_key: 0x%016Lx" - " -- CMD_T_ACTIVE: %d" - " CMD_T_STOP: %d CMD_T_SENT: %d\n", - cmd->tag, cmd->pr_res_key, - (cmd->transport_state & CMD_T_ACTIVE) != 0, - (cmd->transport_state & CMD_T_STOP) != 0, - (cmd->transport_state & CMD_T_SENT) != 0); + target_show_cmd("LUN_RESET: ", cmd); + pr_debug("LUN_RESET: ITT[0x%08llx] - %s pr_res_key: 0x%016Lx\n", + cmd->tag, (preempt_and_abort_list) ? "preempt" : "", + cmd->pr_res_key); /* * If the command may be queued onto a workqueue cancel it now. diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index d601616b9f12..a5ecec8f3996 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1704,15 +1704,9 @@ void transport_generic_request_failure(struct se_cmd *cmd, if (transport_check_aborted_status(cmd, 1)) return; - pr_debug("-----[ Storage Engine Exception for cmd: %p ITT: 0x%08llx" - " CDB: 0x%02x\n", cmd, cmd->tag, cmd->t_task_cdb[0]); - pr_debug("-----[ i_state: %d t_state: %d sense_reason: %d\n", - cmd->se_tfo->get_cmd_state(cmd), - cmd->t_state, sense_reason); - pr_debug("-----[ CMD_T_ACTIVE: %d CMD_T_STOP: %d CMD_T_SENT: %d\n", - (cmd->transport_state & CMD_T_ACTIVE) != 0, - (cmd->transport_state & CMD_T_STOP) != 0, - (cmd->transport_state & CMD_T_SENT) != 0); + pr_debug("-----[ Storage Engine Exception; sense_reason %d\n", + sense_reason); + target_show_cmd("-----[ ", cmd); /* * For SAM Task Attribute emulation for failed struct se_cmd @@ -2705,6 +2699,108 @@ int target_put_sess_cmd(struct se_cmd *se_cmd) } EXPORT_SYMBOL(target_put_sess_cmd); +static const char *data_dir_name(enum dma_data_direction d) +{ + switch (d) { + case DMA_BIDIRECTIONAL: return "BIDI"; + case DMA_TO_DEVICE: return "WRITE"; + case DMA_FROM_DEVICE: return "READ"; + case DMA_NONE: return "NONE"; + } + + return "(?)"; +} + +static const char *cmd_state_name(enum transport_state_table t) +{ + switch (t) { + case TRANSPORT_NO_STATE: return "NO_STATE"; + case TRANSPORT_NEW_CMD: return "NEW_CMD"; + case TRANSPORT_WRITE_PENDING: return "WRITE_PENDING"; + case TRANSPORT_PROCESSING: return "PROCESSING"; + case TRANSPORT_COMPLETE: return "COMPLETE"; + case TRANSPORT_ISTATE_PROCESSING: + return "ISTATE_PROCESSING"; + case TRANSPORT_COMPLETE_QF_WP: return "COMPLETE_QF_WP"; + case TRANSPORT_COMPLETE_QF_OK: return "COMPLETE_QF_OK"; + case TRANSPORT_COMPLETE_QF_ERR: return "COMPLETE_QF_ERR"; + } + + return "(?)"; +} + +static void target_append_str(char **str, const char *txt) +{ + char *prev = *str; + + *str = *str ? kasprintf(GFP_ATOMIC, "%s,%s", *str, txt) : + kstrdup(txt, GFP_ATOMIC); + kfree(prev); +} + +/* + * Convert a transport state bitmask into a string. The caller is + * responsible for freeing the returned pointer. + */ +static char *target_ts_to_str(u32 ts) +{ + char *str = NULL; + + if (ts & CMD_T_ABORTED) + target_append_str(&str, "aborted"); + if (ts & CMD_T_ACTIVE) + target_append_str(&str, "active"); + if (ts & CMD_T_COMPLETE) + target_append_str(&str, "complete"); + if (ts & CMD_T_SENT) + target_append_str(&str, "sent"); + if (ts & CMD_T_STOP) + target_append_str(&str, "stop"); + if (ts & CMD_T_FABRIC_STOP) + target_append_str(&str, "fabric_stop"); + + return str; +} + +static const char *target_tmf_name(enum tcm_tmreq_table tmf) +{ + switch (tmf) { + case TMR_ABORT_TASK: return "ABORT_TASK"; + case TMR_ABORT_TASK_SET: return "ABORT_TASK_SET"; + case TMR_CLEAR_ACA: return "CLEAR_ACA"; + case TMR_CLEAR_TASK_SET: return "CLEAR_TASK_SET"; + case TMR_LUN_RESET: return "LUN_RESET"; + case TMR_TARGET_WARM_RESET: return "TARGET_WARM_RESET"; + case TMR_TARGET_COLD_RESET: return "TARGET_COLD_RESET"; + case TMR_UNKNOWN: break; + } + return "(?)"; +} + +void target_show_cmd(const char *pfx, struct se_cmd *cmd) +{ + char *ts_str = target_ts_to_str(cmd->transport_state); + const u8 *cdb = cmd->t_task_cdb; + struct se_tmr_req *tmf = cmd->se_tmr_req; + + if (!(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)) { + pr_debug("%scmd %#02x:%#02x with tag %#llx dir %s i_state %d t_state %s len %d refcnt %d transport_state %s\n", + pfx, cdb[0], cdb[1], cmd->tag, + data_dir_name(cmd->data_direction), + cmd->se_tfo->get_cmd_state(cmd), + cmd_state_name(cmd->t_state), cmd->data_length, + kref_read(&cmd->cmd_kref), ts_str); + } else { + pr_debug("%stmf %s with tag %#llx ref_task_tag %#llx i_state %d t_state %s refcnt %d transport_state %s\n", + pfx, target_tmf_name(tmf->function), cmd->tag, + tmf->ref_task_tag, cmd->se_tfo->get_cmd_state(cmd), + cmd_state_name(cmd->t_state), + kref_read(&cmd->cmd_kref), ts_str); + } + kfree(ts_str); +} +EXPORT_SYMBOL(target_show_cmd); + /* target_sess_cmd_list_set_waiting - Flag all commands in * sess_cmd_list to complete cmd_wait_comp. Set * sess_tearing_down so no more commands are queued. @@ -2849,13 +2945,13 @@ __transport_wait_for_tasks(struct se_cmd *cmd, bool fabric_stop, cmd->transport_state |= CMD_T_STOP; - pr_debug("wait_for_tasks: Stopping %p ITT: 0x%08llx i_state: %d," - " t_state: %d, CMD_T_STOP\n", cmd, cmd->tag, - cmd->se_tfo->get_cmd_state(cmd), cmd->t_state); + target_show_cmd("wait_for_tasks: Stopping ", cmd); spin_unlock_irqrestore(&cmd->t_state_lock, *flags); - wait_for_completion(&cmd->t_transport_stop_comp); + while (!wait_for_completion_timeout(&cmd->t_transport_stop_comp, + 180 * HZ)) + target_show_cmd("wait for tasks: ", cmd); spin_lock_irqsave(&cmd->t_state_lock, *flags); cmd->transport_state &= ~(CMD_T_ACTIVE | CMD_T_STOP); diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h index d7dd1427fe0d..33d2e3e5773c 100644 --- a/include/target/target_core_fabric.h +++ b/include/target/target_core_fabric.h @@ -160,6 +160,7 @@ int target_get_sess_cmd(struct se_cmd *, bool); int target_put_sess_cmd(struct se_cmd *); void target_sess_cmd_list_set_waiting(struct se_session *); void target_wait_for_sess_cmds(struct se_session *); +void target_show_cmd(const char *pfx, struct se_cmd *cmd); int core_alua_check_nonop_delay(struct se_cmd *); -- cgit v1.2.3-59-g8ed1b From f33f79f3d0e5caf04dd889cd7cf636261970f009 Mon Sep 17 00:00:00 2001 From: Hui Wang Date: Fri, 7 Jul 2017 12:08:29 +0800 Subject: ALSA: hda/realtek - change the location for one of two front microphones On this Lenovo machine, there are two front mics, and both of them are assigned the same name "Mic", but pulseaudio can't support two mics with the same name, as a workaround, we change the location for one of them, then the driver will assign "Front Mic" and "Mic" for them. Cc: stable@vger.kernel.org Signed-off-by: Hui Wang Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index cd6987b5c6d9..e2116d2ea529 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5179,6 +5179,7 @@ enum { ALC233_FIXUP_ASUS_MIC_NO_PRESENCE, ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE, ALC233_FIXUP_LENOVO_MULTI_CODECS, + ALC294_FIXUP_LENOVO_MIC_LOCATION, }; static const struct hda_fixup alc269_fixups[] = { @@ -5962,6 +5963,18 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc233_alc662_fixup_lenovo_dual_codecs, }, + [ALC294_FIXUP_LENOVO_MIC_LOCATION] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + /* Change the mic location from front to right, otherwise there are + two front mics with the same name, pulseaudio can't handle them. + This is just a temporary workaround, after applying this fixup, + there will be one "Front Mic" and one "Mic" in this machine. + */ + { 0x1a, 0x04a19040 }, + { } + }, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -6143,6 +6156,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x2233, "Thinkpad", ALC292_FIXUP_TPT460), SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), + SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION), SND_PCI_QUIRK(0x17aa, 0x3112, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI), SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), -- cgit v1.2.3-59-g8ed1b From 4d3895d5ea43cf40fd707692263c6f0988fe8d70 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 23 May 2017 16:48:39 -0700 Subject: target/tcm_loop: Merge struct tcm_loop_cmd and struct tcm_loop_tmr This patch simplifies the tcm_loop implementation but does not change any functionality. Signed-off-by: Bart Van Assche Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: David Disseldorp Signed-off-by: Nicholas Bellinger --- drivers/target/loopback/tcm_loop.c | 22 ++++++++-------------- drivers/target/loopback/tcm_loop.h | 7 ++----- 2 files changed, 10 insertions(+), 19 deletions(-) diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c index 5091b31b3e56..79776b447b15 100644 --- a/drivers/target/loopback/tcm_loop.c +++ b/drivers/target/loopback/tcm_loop.c @@ -221,7 +221,6 @@ static int tcm_loop_issue_tmr(struct tcm_loop_tpg *tl_tpg, struct se_portal_group *se_tpg; struct tcm_loop_nexus *tl_nexus; struct tcm_loop_cmd *tl_cmd = NULL; - struct tcm_loop_tmr *tl_tmr = NULL; int ret = TMR_FUNCTION_FAILED, rc; /* @@ -240,12 +239,7 @@ static int tcm_loop_issue_tmr(struct tcm_loop_tpg *tl_tpg, return ret; } - tl_tmr = kzalloc(sizeof(struct tcm_loop_tmr), GFP_KERNEL); - if (!tl_tmr) { - pr_err("Unable to allocate memory for tl_tmr\n"); - goto release; - } - init_waitqueue_head(&tl_tmr->tl_tmr_wait); + init_waitqueue_head(&tl_cmd->tl_tmr_wait); se_cmd = &tl_cmd->tl_se_cmd; se_tpg = &tl_tpg->tl_se_tpg; @@ -257,7 +251,7 @@ static int tcm_loop_issue_tmr(struct tcm_loop_tpg *tl_tpg, DMA_NONE, TCM_SIMPLE_TAG, &tl_cmd->tl_sense_buf[0]); - rc = core_tmr_alloc_req(se_cmd, tl_tmr, tmr, GFP_KERNEL); + rc = core_tmr_alloc_req(se_cmd, NULL, tmr, GFP_KERNEL); if (rc < 0) goto release; @@ -276,7 +270,7 @@ static int tcm_loop_issue_tmr(struct tcm_loop_tpg *tl_tpg, * tcm_loop_queue_tm_rsp() to wake us up. */ transport_generic_handle_tmr(se_cmd); - wait_event(tl_tmr->tl_tmr_wait, atomic_read(&tl_tmr->tmr_complete)); + wait_event(tl_cmd->tl_tmr_wait, atomic_read(&tl_cmd->tmr_complete)); /* * The TMR LUN_RESET has completed, check the response status and * then release allocations. @@ -287,7 +281,6 @@ release: transport_generic_free_cmd(se_cmd, 1); else kmem_cache_free(tcm_loop_cmd_cache, tl_cmd); - kfree(tl_tmr); return ret; } @@ -669,14 +662,15 @@ static int tcm_loop_queue_status(struct se_cmd *se_cmd) static void tcm_loop_queue_tm_rsp(struct se_cmd *se_cmd) { - struct se_tmr_req *se_tmr = se_cmd->se_tmr_req; - struct tcm_loop_tmr *tl_tmr = se_tmr->fabric_tmr_ptr; + struct tcm_loop_cmd *tl_cmd = container_of(se_cmd, + struct tcm_loop_cmd, tl_se_cmd); + /* * The SCSI EH thread will be sleeping on se_tmr->tl_tmr_wait, go ahead * and wake up the wait_queue_head_t in tcm_loop_device_reset() */ - atomic_set(&tl_tmr->tmr_complete, 1); - wake_up(&tl_tmr->tl_tmr_wait); + atomic_set(&tl_cmd->tmr_complete, 1); + wake_up(&tl_cmd->tl_tmr_wait); } static void tcm_loop_aborted_task(struct se_cmd *se_cmd) diff --git a/drivers/target/loopback/tcm_loop.h b/drivers/target/loopback/tcm_loop.h index a8a230b4e6b5..21340781568b 100644 --- a/drivers/target/loopback/tcm_loop.h +++ b/drivers/target/loopback/tcm_loop.h @@ -16,13 +16,10 @@ struct tcm_loop_cmd { /* The TCM I/O descriptor that is accessed via container_of() */ struct se_cmd tl_se_cmd; struct work_struct work; - /* Sense buffer that will be mapped into outgoing status */ - unsigned char tl_sense_buf[TRANSPORT_SENSE_BUFFER]; -}; - -struct tcm_loop_tmr { atomic_t tmr_complete; wait_queue_head_t tl_tmr_wait; + /* Sense buffer that will be mapped into outgoing status */ + unsigned char tl_sense_buf[TRANSPORT_SENSE_BUFFER]; }; struct tcm_loop_nexus { -- cgit v1.2.3-59-g8ed1b From d17203c41185a05ecd4d1fc647f16b17ab1b27ae Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 23 May 2017 16:48:40 -0700 Subject: target/tcm_loop: Replace a waitqueue and a counter by a completion This patch simplifies the implementation of the tcm_loop driver but does not change its behavior. Signed-off-by: Bart Van Assche Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: David Disseldorp Signed-off-by: Nicholas Bellinger --- drivers/target/loopback/tcm_loop.c | 12 ++++-------- drivers/target/loopback/tcm_loop.h | 3 +-- 2 files changed, 5 insertions(+), 10 deletions(-) diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c index 79776b447b15..27f912747113 100644 --- a/drivers/target/loopback/tcm_loop.c +++ b/drivers/target/loopback/tcm_loop.c @@ -239,7 +239,7 @@ static int tcm_loop_issue_tmr(struct tcm_loop_tpg *tl_tpg, return ret; } - init_waitqueue_head(&tl_cmd->tl_tmr_wait); + init_completion(&tl_cmd->tmr_done); se_cmd = &tl_cmd->tl_se_cmd; se_tpg = &tl_tpg->tl_se_tpg; @@ -270,7 +270,7 @@ static int tcm_loop_issue_tmr(struct tcm_loop_tpg *tl_tpg, * tcm_loop_queue_tm_rsp() to wake us up. */ transport_generic_handle_tmr(se_cmd); - wait_event(tl_cmd->tl_tmr_wait, atomic_read(&tl_cmd->tmr_complete)); + wait_for_completion(&tl_cmd->tmr_done); /* * The TMR LUN_RESET has completed, check the response status and * then release allocations. @@ -665,12 +665,8 @@ static void tcm_loop_queue_tm_rsp(struct se_cmd *se_cmd) struct tcm_loop_cmd *tl_cmd = container_of(se_cmd, struct tcm_loop_cmd, tl_se_cmd); - /* - * The SCSI EH thread will be sleeping on se_tmr->tl_tmr_wait, go ahead - * and wake up the wait_queue_head_t in tcm_loop_device_reset() - */ - atomic_set(&tl_cmd->tmr_complete, 1); - wake_up(&tl_cmd->tl_tmr_wait); + /* Wake up tcm_loop_issue_tmr(). */ + complete(&tl_cmd->tmr_done); } static void tcm_loop_aborted_task(struct se_cmd *se_cmd) diff --git a/drivers/target/loopback/tcm_loop.h b/drivers/target/loopback/tcm_loop.h index 21340781568b..3acc43c05117 100644 --- a/drivers/target/loopback/tcm_loop.h +++ b/drivers/target/loopback/tcm_loop.h @@ -16,8 +16,7 @@ struct tcm_loop_cmd { /* The TCM I/O descriptor that is accessed via container_of() */ struct se_cmd tl_se_cmd; struct work_struct work; - atomic_t tmr_complete; - wait_queue_head_t tl_tmr_wait; + struct completion tmr_done; /* Sense buffer that will be mapped into outgoing status */ unsigned char tl_sense_buf[TRANSPORT_SENSE_BUFFER]; }; -- cgit v1.2.3-59-g8ed1b From 75f141aaf48e13812b4fee914a66f6fce28b543f Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 23 May 2017 16:48:41 -0700 Subject: target/tcm_loop: Use target_submit_tmr() instead of open-coding this function Use target_submit_tmr() instead of open-coding this function. The only functional change is that TMFs are now added to sess_cmd_list, something the current code does not do. This behavior change is a bug fix because it makes LUN RESETs wait for other TMFs that are in progress for the same LUN. Signed-off-by: Bart Van Assche Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: David Disseldorp Signed-off-by: Nicholas Bellinger --- drivers/target/loopback/tcm_loop.c | 32 +++----------------------------- 1 file changed, 3 insertions(+), 29 deletions(-) diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c index 27f912747113..8cf556b4c5ca 100644 --- a/drivers/target/loopback/tcm_loop.c +++ b/drivers/target/loopback/tcm_loop.c @@ -218,7 +218,6 @@ static int tcm_loop_issue_tmr(struct tcm_loop_tpg *tl_tpg, { struct se_cmd *se_cmd = NULL; struct se_session *se_sess; - struct se_portal_group *se_tpg; struct tcm_loop_nexus *tl_nexus; struct tcm_loop_cmd *tl_cmd = NULL; int ret = TMR_FUNCTION_FAILED, rc; @@ -242,40 +241,15 @@ static int tcm_loop_issue_tmr(struct tcm_loop_tpg *tl_tpg, init_completion(&tl_cmd->tmr_done); se_cmd = &tl_cmd->tl_se_cmd; - se_tpg = &tl_tpg->tl_se_tpg; se_sess = tl_tpg->tl_nexus->se_sess; - /* - * Initialize struct se_cmd descriptor from target_core_mod infrastructure - */ - transport_init_se_cmd(se_cmd, se_tpg->se_tpg_tfo, se_sess, 0, - DMA_NONE, TCM_SIMPLE_TAG, - &tl_cmd->tl_sense_buf[0]); - rc = core_tmr_alloc_req(se_cmd, NULL, tmr, GFP_KERNEL); + rc = target_submit_tmr(se_cmd, se_sess, tl_cmd->tl_sense_buf, lun, + NULL, tmr, GFP_KERNEL, task, 0 /*flags*/); if (rc < 0) goto release; - - if (tmr == TMR_ABORT_TASK) - se_cmd->se_tmr_req->ref_task_tag = task; - - /* - * Locate the underlying TCM struct se_lun - */ - if (transport_lookup_tmr_lun(se_cmd, lun) < 0) { - ret = TMR_LUN_DOES_NOT_EXIST; - goto release; - } - /* - * Queue the TMR to TCM Core and sleep waiting for - * tcm_loop_queue_tm_rsp() to wake us up. - */ - transport_generic_handle_tmr(se_cmd); wait_for_completion(&tl_cmd->tmr_done); - /* - * The TMR LUN_RESET has completed, check the response status and - * then release allocations. - */ ret = se_cmd->se_tmr_req->response; + release: if (se_cmd) transport_generic_free_cmd(se_cmd, 1); -- cgit v1.2.3-59-g8ed1b From 4c1f0e65397f4e5768b955c32489d5b4b6b92a90 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 23 May 2017 16:48:42 -0700 Subject: target/tcm_loop: Make TMF processing slightly faster Target drivers must guarantee that struct se_cmd and struct se_tmr_req exist as long as target_tmr_work() is in progress. This is why the tcm_loop driver today passes 1 as second argument to transport_generic_free_cmd() from inside the TMF code. Instead of making the TMF code wait, make the TMF code obtain two references (SCF_ACK_KREF) and drop one reference from inside the .check_stop_free() callback. Signed-off-by: Bart Van Assche Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: David Disseldorp Signed-off-by: Nicholas Bellinger --- drivers/target/loopback/tcm_loop.c | 25 +++++++++---------------- 1 file changed, 9 insertions(+), 16 deletions(-) diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c index 8cf556b4c5ca..b6a913e38b30 100644 --- a/drivers/target/loopback/tcm_loop.c +++ b/drivers/target/loopback/tcm_loop.c @@ -51,19 +51,7 @@ static int tcm_loop_queue_status(struct se_cmd *se_cmd); */ static int tcm_loop_check_stop_free(struct se_cmd *se_cmd) { - /* - * Do not release struct se_cmd's containing a valid TMR - * pointer. These will be released directly in tcm_loop_device_reset() - * with transport_generic_free_cmd(). - */ - if (se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) - return 0; - /* - * Release the struct se_cmd, which will make a callback to release - * struct tcm_loop_cmd * in tcm_loop_deallocate_core_cmd() - */ - transport_generic_free_cmd(se_cmd, 0); - return 1; + return transport_generic_free_cmd(se_cmd, 0); } static void tcm_loop_release_cmd(struct se_cmd *se_cmd) @@ -244,18 +232,23 @@ static int tcm_loop_issue_tmr(struct tcm_loop_tpg *tl_tpg, se_sess = tl_tpg->tl_nexus->se_sess; rc = target_submit_tmr(se_cmd, se_sess, tl_cmd->tl_sense_buf, lun, - NULL, tmr, GFP_KERNEL, task, 0 /*flags*/); + NULL, tmr, GFP_KERNEL, task, + TARGET_SCF_ACK_KREF); if (rc < 0) goto release; wait_for_completion(&tl_cmd->tmr_done); ret = se_cmd->se_tmr_req->response; + target_put_sess_cmd(se_cmd); + +out: + return ret; release: if (se_cmd) - transport_generic_free_cmd(se_cmd, 1); + transport_generic_free_cmd(se_cmd, 0); else kmem_cache_free(tcm_loop_cmd_cache, tl_cmd); - return ret; + goto out; } static int tcm_loop_abort_task(struct scsi_cmnd *sc) -- cgit v1.2.3-59-g8ed1b From 4412a67131a037fa1d032bcd50270e9d336a775d Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 23 May 2017 16:48:43 -0700 Subject: target/iscsi: Remove second argument of __iscsit_free_cmd() Initialize .data_direction to DMA_NONE in iscsit_allocate_cmd() such that the second argument of __iscsit_free_cmd() can be left out. Note: this patch causes the first part of __iscsit_free_cmd() no longer to be skipped for TMFs. That's fine since no data segments are associated with TMFs. Signed-off-by: Bart Van Assche Reviewed-by: Hannes Reinecke Cc: Christoph Hellwig Cc: Andy Grover Cc: David Disseldorp Signed-off-by: Nicholas Bellinger --- drivers/target/iscsi/iscsi_target.c | 4 +--- drivers/target/iscsi/iscsi_target_util.c | 29 +++++++++++++---------------- drivers/target/iscsi/iscsi_target_util.h | 2 +- 3 files changed, 15 insertions(+), 20 deletions(-) diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 3fdca2cdd8da..735d4ff2d0ce 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -488,15 +488,13 @@ EXPORT_SYMBOL(iscsit_queue_rsp); void iscsit_aborted_task(struct iscsi_conn *conn, struct iscsi_cmd *cmd) { - bool scsi_cmd = (cmd->iscsi_opcode == ISCSI_OP_SCSI_CMD); - spin_lock_bh(&conn->cmd_lock); if (!list_empty(&cmd->i_conn_node) && !(cmd->se_cmd.transport_state & CMD_T_FABRIC_STOP)) list_del_init(&cmd->i_conn_node); spin_unlock_bh(&conn->cmd_lock); - __iscsit_free_cmd(cmd, scsi_cmd, true); + __iscsit_free_cmd(cmd, true); } EXPORT_SYMBOL(iscsit_aborted_task); diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index 7d3e2fcc26a0..41b9e7cc08b8 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -167,6 +167,7 @@ struct iscsi_cmd *iscsit_allocate_cmd(struct iscsi_conn *conn, int state) cmd->se_cmd.map_tag = tag; cmd->conn = conn; + cmd->data_direction = DMA_NONE; INIT_LIST_HEAD(&cmd->i_conn_node); INIT_LIST_HEAD(&cmd->datain_list); INIT_LIST_HEAD(&cmd->cmd_r2t_list); @@ -711,19 +712,16 @@ void iscsit_release_cmd(struct iscsi_cmd *cmd) } EXPORT_SYMBOL(iscsit_release_cmd); -void __iscsit_free_cmd(struct iscsi_cmd *cmd, bool scsi_cmd, - bool check_queues) +void __iscsit_free_cmd(struct iscsi_cmd *cmd, bool check_queues) { struct iscsi_conn *conn = cmd->conn; - if (scsi_cmd) { - if (cmd->data_direction == DMA_TO_DEVICE) { - iscsit_stop_dataout_timer(cmd); - iscsit_free_r2ts_from_list(cmd); - } - if (cmd->data_direction == DMA_FROM_DEVICE) - iscsit_free_all_datain_reqs(cmd); + if (cmd->data_direction == DMA_TO_DEVICE) { + iscsit_stop_dataout_timer(cmd); + iscsit_free_r2ts_from_list(cmd); } + if (cmd->data_direction == DMA_FROM_DEVICE) + iscsit_free_all_datain_reqs(cmd); if (conn && check_queues) { iscsit_remove_cmd_from_immediate_queue(cmd, conn); @@ -738,23 +736,22 @@ void iscsit_free_cmd(struct iscsi_cmd *cmd, bool shutdown) { struct se_cmd *se_cmd = NULL; int rc; - bool op_scsi = false; + /* * Determine if a struct se_cmd is associated with * this struct iscsi_cmd. */ switch (cmd->iscsi_opcode) { case ISCSI_OP_SCSI_CMD: - op_scsi = true; /* * Fallthrough */ case ISCSI_OP_SCSI_TMFUNC: se_cmd = &cmd->se_cmd; - __iscsit_free_cmd(cmd, op_scsi, shutdown); + __iscsit_free_cmd(cmd, shutdown); rc = transport_generic_free_cmd(se_cmd, shutdown); if (!rc && shutdown && se_cmd->se_sess) { - __iscsit_free_cmd(cmd, op_scsi, shutdown); + __iscsit_free_cmd(cmd, shutdown); target_put_sess_cmd(se_cmd); } break; @@ -766,18 +763,18 @@ void iscsit_free_cmd(struct iscsi_cmd *cmd, bool shutdown) */ if (cmd->se_cmd.se_tfo != NULL) { se_cmd = &cmd->se_cmd; - __iscsit_free_cmd(cmd, true, shutdown); + __iscsit_free_cmd(cmd, shutdown); rc = transport_generic_free_cmd(&cmd->se_cmd, shutdown); if (!rc && shutdown && se_cmd->se_sess) { - __iscsit_free_cmd(cmd, true, shutdown); + __iscsit_free_cmd(cmd, shutdown); target_put_sess_cmd(se_cmd); } break; } /* Fall-through */ default: - __iscsit_free_cmd(cmd, false, shutdown); + __iscsit_free_cmd(cmd, shutdown); iscsit_release_cmd(cmd); break; } diff --git a/drivers/target/iscsi/iscsi_target_util.h b/drivers/target/iscsi/iscsi_target_util.h index 9e4197af8708..425160565d0c 100644 --- a/drivers/target/iscsi/iscsi_target_util.h +++ b/drivers/target/iscsi/iscsi_target_util.h @@ -37,7 +37,7 @@ extern void iscsit_remove_cmd_from_tx_queues(struct iscsi_cmd *, struct iscsi_co extern bool iscsit_conn_all_queues_empty(struct iscsi_conn *); extern void iscsit_free_queue_reqs_for_conn(struct iscsi_conn *); extern void iscsit_release_cmd(struct iscsi_cmd *); -extern void __iscsit_free_cmd(struct iscsi_cmd *, bool, bool); +extern void __iscsit_free_cmd(struct iscsi_cmd *, bool); extern void iscsit_free_cmd(struct iscsi_cmd *, bool); extern int iscsit_check_session_usage_count(struct iscsi_session *); extern void iscsit_dec_session_usage_count(struct iscsi_session *); -- cgit v1.2.3-59-g8ed1b From d1c26857cdec3e3bdb5cf7179411f6ce8cc0834c Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 23 May 2017 16:48:44 -0700 Subject: target/iscsi: Simplify iscsit_free_cmd() Since .se_tfo is only set if a command has been submitted to the LIO core, check .se_tfo instead of .iscsi_opcode. Since __iscsit_free_cmd() only affects SCSI commands but not TMFs, calling that function for TMFs does not change behavior. This patch does not change the behavior of iscsit_free_cmd(). Signed-off-by: Bart Van Assche Cc: Hannes Reinecke Cc: Christoph Hellwig Cc: Andy Grover Cc: David Disseldorp Signed-off-by: Nicholas Bellinger --- drivers/target/iscsi/iscsi_target_util.c | 39 ++++---------------------------- 1 file changed, 4 insertions(+), 35 deletions(-) diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index 41b9e7cc08b8..1e36f83b5961 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -734,49 +734,18 @@ void __iscsit_free_cmd(struct iscsi_cmd *cmd, bool check_queues) void iscsit_free_cmd(struct iscsi_cmd *cmd, bool shutdown) { - struct se_cmd *se_cmd = NULL; + struct se_cmd *se_cmd = cmd->se_cmd.se_tfo ? &cmd->se_cmd : NULL; int rc; - /* - * Determine if a struct se_cmd is associated with - * this struct iscsi_cmd. - */ - switch (cmd->iscsi_opcode) { - case ISCSI_OP_SCSI_CMD: - /* - * Fallthrough - */ - case ISCSI_OP_SCSI_TMFUNC: - se_cmd = &cmd->se_cmd; - __iscsit_free_cmd(cmd, shutdown); + __iscsit_free_cmd(cmd, shutdown); + if (se_cmd) { rc = transport_generic_free_cmd(se_cmd, shutdown); if (!rc && shutdown && se_cmd->se_sess) { __iscsit_free_cmd(cmd, shutdown); target_put_sess_cmd(se_cmd); } - break; - case ISCSI_OP_REJECT: - /* - * Handle special case for REJECT when iscsi_add_reject*() has - * overwritten the original iscsi_opcode assignment, and the - * associated cmd->se_cmd needs to be released. - */ - if (cmd->se_cmd.se_tfo != NULL) { - se_cmd = &cmd->se_cmd; - __iscsit_free_cmd(cmd, shutdown); - - rc = transport_generic_free_cmd(&cmd->se_cmd, shutdown); - if (!rc && shutdown && se_cmd->se_sess) { - __iscsit_free_cmd(cmd, shutdown); - target_put_sess_cmd(se_cmd); - } - break; - } - /* Fall-through */ - default: - __iscsit_free_cmd(cmd, shutdown); + } else { iscsit_release_cmd(cmd); - break; } } EXPORT_SYMBOL(iscsit_free_cmd); -- cgit v1.2.3-59-g8ed1b From 8fa4011e0dd9423f1226f2f9769a1cf25c264468 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 23 May 2017 16:48:45 -0700 Subject: target/iscsi: Remove dead code from iscsit_process_scsi_cmd() If an iSCSI command is rejected before iscsit_process_scsi_cmd() is called, .reject_reason is set but iscsit_process_scsi_cmd() is not called. This means that the "if (cmd->reject_reason) ..." code in this function can be removed without changing the behavior of this function. Signed-off-by: Bart Van Assche Cc: Hannes Reinecke Cc: Christoph Hellwig Cc: Andy Grover Cc: David Disseldorp Signed-off-by: Nicholas Bellinger --- drivers/target/iscsi/iscsi_target.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 735d4ff2d0ce..74e4975dd1b1 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -1249,12 +1249,8 @@ int iscsit_process_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, * execution. These exceptions are processed in CmdSN order using * iscsit_check_received_cmdsn() in iscsit_get_immediate_data() below. */ - if (cmd->sense_reason) { - if (cmd->reject_reason) - return 0; - + if (cmd->sense_reason) return 1; - } /* * Call directly into transport_generic_new_cmd() to perform * the backend memory allocation. -- cgit v1.2.3-59-g8ed1b From e9447a46e9fba006ff9b0f4e40a4e38bf2d788db Mon Sep 17 00:00:00 2001 From: "Bryant G. Ly" Date: Tue, 6 Jun 2017 15:45:49 -0500 Subject: ibmvscsis: Use tpgt passed in by user ibmvscsis always returned 0 for the tpg/tag, since it did not parse the value passed in by the user. When functions like ALUA members exports the value, it will be incorrect because targetcli/rtslib starts the tpg numbering at 1. Signed-off-by: Bryant G. Ly Signed-off-by: Mike Christie Signed-off-by: Nicholas Bellinger --- drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c index 35710524d059..522d547d9fea 100644 --- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c +++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c @@ -3914,8 +3914,16 @@ static struct se_portal_group *ibmvscsis_make_tpg(struct se_wwn *wwn, { struct ibmvscsis_tport *tport = container_of(wwn, struct ibmvscsis_tport, tport_wwn); + u16 tpgt; int rc; + if (strstr(name, "tpgt_") != name) + return ERR_PTR(-EINVAL); + rc = kstrtou16(name + 5, 0, &tpgt); + if (rc) + return ERR_PTR(rc); + tport->tport_tpgt = tpgt; + tport->releasing = false; rc = core_tpg_register(&tport->tport_wwn, &tport->se_tpg, -- cgit v1.2.3-59-g8ed1b From 9a8bb60650b3d6994bd19a3200941f029c95a7a0 Mon Sep 17 00:00:00 2001 From: "Bryant G. Ly" Date: Tue, 6 Jun 2017 09:28:48 -0500 Subject: tcmu: Support emulate_write_cache This will enable the toggling of write_cache in tcmu through targetcli-fb Signed-off-by: Bryant G. Ly Reviewed-By: Mike Christie Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_user.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index beb5f098f32d..0c797cc69d9e 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -1290,6 +1290,8 @@ static int tcmu_configure_device(struct se_device *dev) /* Other attributes can be configured in userspace */ if (!dev->dev_attrib.hw_max_sectors) dev->dev_attrib.hw_max_sectors = 128; + if (!dev->dev_attrib.emulate_write_cache) + dev->dev_attrib.emulate_write_cache = 0; dev->dev_attrib.hw_queue_depth = 128; /* @@ -1546,6 +1548,32 @@ static ssize_t tcmu_cmd_time_out_store(struct config_item *item, const char *pag } CONFIGFS_ATTR(tcmu_, cmd_time_out); +static ssize_t tcmu_emulate_write_cache_show(struct config_item *item, + char *page) +{ + struct se_dev_attrib *da = container_of(to_config_group(item), + struct se_dev_attrib, da_group); + + return snprintf(page, PAGE_SIZE, "%i\n", da->emulate_write_cache); +} + +static ssize_t tcmu_emulate_write_cache_store(struct config_item *item, + const char *page, size_t count) +{ + struct se_dev_attrib *da = container_of(to_config_group(item), + struct se_dev_attrib, da_group); + int val; + int ret; + + ret = kstrtouint(page, 0, &val); + if (ret < 0) + return ret; + + da->emulate_write_cache = val; + return count; +} +CONFIGFS_ATTR(tcmu_, emulate_write_cache); + static struct configfs_attribute **tcmu_attrs; static struct target_backend_ops tcmu_ops = { @@ -1682,6 +1710,8 @@ static int __init tcmu_module_init(void) tcmu_attrs[i] = passthrough_attrib_attrs[i]; } tcmu_attrs[i] = &tcmu_attr_cmd_time_out; + i++; + tcmu_attrs[i] = &tcmu_attr_emulate_write_cache; tcmu_ops.tb_dev_attrib_attrs = tcmu_attrs; ret = transport_backend_register(&tcmu_ops); -- cgit v1.2.3-59-g8ed1b From 1068be7bd4b05ca41a6a8de724f52a9c87861412 Mon Sep 17 00:00:00 2001 From: "Bryant G. Ly" Date: Tue, 6 Jun 2017 09:28:49 -0500 Subject: tcmu: Add netlink for device reconfiguration This gives tcmu the ability to handle events that can cause reconfiguration, such as resize, path changes, write_cache, etc... Signed-off-by: Bryant G. Ly Reviewed-By: Mike Christie Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_user.c | 12 ++++++++++++ include/uapi/linux/target_core_user.h | 1 + 2 files changed, 13 insertions(+) diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 0c797cc69d9e..ae918222284b 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -1562,6 +1562,7 @@ static ssize_t tcmu_emulate_write_cache_store(struct config_item *item, { struct se_dev_attrib *da = container_of(to_config_group(item), struct se_dev_attrib, da_group); + struct tcmu_dev *udev = TCMU_DEV(da->da_dev); int val; int ret; @@ -1570,6 +1571,17 @@ static ssize_t tcmu_emulate_write_cache_store(struct config_item *item, return ret; da->emulate_write_cache = val; + + /* Check if device has been configured before */ + if (tcmu_dev_configured(udev)) { + ret = tcmu_netlink_event(TCMU_CMD_RECONFIG_DEVICE, + udev->uio_info.name, + udev->uio_info.uio_dev->minor); + if (ret) { + pr_err("Unable to reconfigure device\n"); + return ret; + } + } return count; } CONFIGFS_ATTR(tcmu_, emulate_write_cache); diff --git a/include/uapi/linux/target_core_user.h b/include/uapi/linux/target_core_user.h index af17b4154ef6..403a61faada0 100644 --- a/include/uapi/linux/target_core_user.h +++ b/include/uapi/linux/target_core_user.h @@ -130,6 +130,7 @@ enum tcmu_genl_cmd { TCMU_CMD_UNSPEC, TCMU_CMD_ADDED_DEVICE, TCMU_CMD_REMOVED_DEVICE, + TCMU_CMD_RECONFIG_DEVICE, __TCMU_CMD_MAX, }; #define TCMU_CMD_MAX (__TCMU_CMD_MAX - 1) -- cgit v1.2.3-59-g8ed1b From 801fc54d5d943e8a6a6bc26bc94fb9b90938ff68 Mon Sep 17 00:00:00 2001 From: "Bryant G. Ly" Date: Tue, 6 Jun 2017 09:28:50 -0500 Subject: tcmu: Make dev_size configurable via userspace Allow tcmu backstores to be able to set the device size after it has been configured via set attribute. Part of support in userspace to support certain backstores changing device size. Signed-off-by: Bryant G. Ly Reviewed-By: Mike Christie Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_user.c | 59 +++++++++++++++++++++++++++++++++++---- 1 file changed, 54 insertions(+), 5 deletions(-) diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index ae918222284b..c8c84b71dc91 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -1548,6 +1548,44 @@ static ssize_t tcmu_cmd_time_out_store(struct config_item *item, const char *pag } CONFIGFS_ATTR(tcmu_, cmd_time_out); +static ssize_t tcmu_dev_size_show(struct config_item *item, char *page) +{ + struct se_dev_attrib *da = container_of(to_config_group(item), + struct se_dev_attrib, da_group); + struct tcmu_dev *udev = TCMU_DEV(da->da_dev); + + return snprintf(page, PAGE_SIZE, "%zu\n", udev->dev_size); +} + +static ssize_t tcmu_dev_size_store(struct config_item *item, const char *page, + size_t count) +{ + struct se_dev_attrib *da = container_of(to_config_group(item), + struct se_dev_attrib, da_group); + struct tcmu_dev *udev = TCMU_DEV(da->da_dev); + unsigned long val; + int ret; + + ret = kstrtoul(page, 0, &val); + if (ret < 0) + return ret; + udev->dev_size = val; + + /* Check if device has been configured before */ + if (tcmu_dev_configured(udev)) { + ret = tcmu_netlink_event(TCMU_CMD_RECONFIG_DEVICE, + udev->uio_info.name, + udev->uio_info.uio_dev->minor); + if (ret) { + pr_err("Unable to reconfigure device\n"); + return ret; + } + } + + return count; +} +CONFIGFS_ATTR(tcmu_, dev_size); + static ssize_t tcmu_emulate_write_cache_show(struct config_item *item, char *page) { @@ -1586,6 +1624,13 @@ static ssize_t tcmu_emulate_write_cache_store(struct config_item *item, } CONFIGFS_ATTR(tcmu_, emulate_write_cache); +struct configfs_attribute *tcmu_attrib_attrs[] = { + &tcmu_attr_cmd_time_out, + &tcmu_attr_dev_size, + &tcmu_attr_emulate_write_cache, + NULL, +}; + static struct configfs_attribute **tcmu_attrs; static struct target_backend_ops tcmu_ops = { @@ -1685,7 +1730,7 @@ static int unmap_thread_fn(void *data) static int __init tcmu_module_init(void) { - int ret, i, len = 0; + int ret, i, k, len = 0; BUILD_BUG_ON((sizeof(struct tcmu_cmd_entry) % TCMU_OP_ALIGN_SIZE) != 0); @@ -1710,7 +1755,10 @@ static int __init tcmu_module_init(void) for (i = 0; passthrough_attrib_attrs[i] != NULL; i++) { len += sizeof(struct configfs_attribute *); } - len += sizeof(struct configfs_attribute *) * 2; + for (i = 0; tcmu_attrib_attrs[i] != NULL; i++) { + len += sizeof(struct configfs_attribute *); + } + len += sizeof(struct configfs_attribute *); tcmu_attrs = kzalloc(len, GFP_KERNEL); if (!tcmu_attrs) { @@ -1721,9 +1769,10 @@ static int __init tcmu_module_init(void) for (i = 0; passthrough_attrib_attrs[i] != NULL; i++) { tcmu_attrs[i] = passthrough_attrib_attrs[i]; } - tcmu_attrs[i] = &tcmu_attr_cmd_time_out; - i++; - tcmu_attrs[i] = &tcmu_attr_emulate_write_cache; + for (k = 0; tcmu_attrib_attrs[k] != NULL; k++) { + tcmu_attrs[i] = tcmu_attrib_attrs[k]; + i++; + } tcmu_ops.tb_dev_attrib_attrs = tcmu_attrs; ret = transport_backend_register(&tcmu_ops); -- cgit v1.2.3-59-g8ed1b From ee01825220f01c0befea25f08325962fa9374ee2 Mon Sep 17 00:00:00 2001 From: "Bryant G. Ly" Date: Tue, 6 Jun 2017 09:28:51 -0500 Subject: tcmu: Make dev_config configurable This allows for userspace to change the device path after it has been created. Thus giving the user the ability to change the path. The use case for this is to allow for virtual optical to have media change. Signed-off-by: Bryant G. Ly Reviewed-By: Mike Christie Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_user.c | 41 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index c8c84b71dc91..7c6475731895 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -1548,6 +1548,46 @@ static ssize_t tcmu_cmd_time_out_store(struct config_item *item, const char *pag } CONFIGFS_ATTR(tcmu_, cmd_time_out); +static ssize_t tcmu_dev_path_show(struct config_item *item, char *page) +{ + struct se_dev_attrib *da = container_of(to_config_group(item), + struct se_dev_attrib, da_group); + struct tcmu_dev *udev = TCMU_DEV(da->da_dev); + + return snprintf(page, PAGE_SIZE, "%s\n", udev->dev_config); +} + +static ssize_t tcmu_dev_path_store(struct config_item *item, const char *page, + size_t count) +{ + struct se_dev_attrib *da = container_of(to_config_group(item), + struct se_dev_attrib, da_group); + struct tcmu_dev *udev = TCMU_DEV(da->da_dev); + char *copy = NULL; + int ret; + + copy = kstrdup(page, GFP_KERNEL); + if (!copy) { + kfree(copy); + return -EINVAL; + } + strlcpy(udev->dev_config, copy, TCMU_CONFIG_LEN); + + /* Check if device has been configured before */ + if (tcmu_dev_configured(udev)) { + ret = tcmu_netlink_event(TCMU_CMD_RECONFIG_DEVICE, + udev->uio_info.name, + udev->uio_info.uio_dev->minor); + if (ret) { + pr_err("Unable to reconfigure device\n"); + return ret; + } + } + + return count; +} +CONFIGFS_ATTR(tcmu_, dev_path); + static ssize_t tcmu_dev_size_show(struct config_item *item, char *page) { struct se_dev_attrib *da = container_of(to_config_group(item), @@ -1626,6 +1666,7 @@ CONFIGFS_ATTR(tcmu_, emulate_write_cache); struct configfs_attribute *tcmu_attrib_attrs[] = { &tcmu_attr_cmd_time_out, + &tcmu_attr_dev_path, &tcmu_attr_dev_size, &tcmu_attr_emulate_write_cache, NULL, -- cgit v1.2.3-59-g8ed1b From 8a45885c1514cdae2ee64b5ac03ffc00a1a8a9d7 Mon Sep 17 00:00:00 2001 From: "Bryant G. Ly" Date: Tue, 6 Jun 2017 09:28:52 -0500 Subject: tcmu: Add Type of reconfig into netlink This patch adds more info about the attribute being changed, so that usersapce can easily figure out what is happening. Signed-off-by: Bryant G. Ly Reviewed-By: Mike Christie Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_user.c | 20 ++++++++++++++------ include/uapi/linux/target_core_user.h | 8 ++++++++ 2 files changed, 22 insertions(+), 6 deletions(-) diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 7c6475731895..afc1fd6bacaf 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -1176,7 +1176,8 @@ static int tcmu_release(struct uio_info *info, struct inode *inode) return 0; } -static int tcmu_netlink_event(enum tcmu_genl_cmd cmd, const char *name, int minor) +static int tcmu_netlink_event(enum tcmu_genl_cmd cmd, const char *name, + int minor, int type) { struct sk_buff *skb; void *msg_header; @@ -1198,6 +1199,10 @@ static int tcmu_netlink_event(enum tcmu_genl_cmd cmd, const char *name, int mino if (ret < 0) goto free_skb; + ret = nla_put_u32(skb, TCMU_ATTR_TYPE, type); + if (ret < 0) + goto free_skb; + genlmsg_end(skb, msg_header); ret = genlmsg_multicast_allns(&tcmu_genl_family, skb, 0, @@ -1301,7 +1306,7 @@ static int tcmu_configure_device(struct se_device *dev) kref_get(&udev->kref); ret = tcmu_netlink_event(TCMU_CMD_ADDED_DEVICE, udev->uio_info.name, - udev->uio_info.uio_dev->minor); + udev->uio_info.uio_dev->minor, NO_RECONFIG); if (ret) goto err_netlink; @@ -1383,7 +1388,7 @@ static void tcmu_free_device(struct se_device *dev) if (tcmu_dev_configured(udev)) { tcmu_netlink_event(TCMU_CMD_REMOVED_DEVICE, udev->uio_info.name, - udev->uio_info.uio_dev->minor); + udev->uio_info.uio_dev->minor, NO_RECONFIG); uio_unregister_device(&udev->uio_info); } @@ -1577,7 +1582,8 @@ static ssize_t tcmu_dev_path_store(struct config_item *item, const char *page, if (tcmu_dev_configured(udev)) { ret = tcmu_netlink_event(TCMU_CMD_RECONFIG_DEVICE, udev->uio_info.name, - udev->uio_info.uio_dev->minor); + udev->uio_info.uio_dev->minor, + CONFIG_PATH); if (ret) { pr_err("Unable to reconfigure device\n"); return ret; @@ -1615,7 +1621,8 @@ static ssize_t tcmu_dev_size_store(struct config_item *item, const char *page, if (tcmu_dev_configured(udev)) { ret = tcmu_netlink_event(TCMU_CMD_RECONFIG_DEVICE, udev->uio_info.name, - udev->uio_info.uio_dev->minor); + udev->uio_info.uio_dev->minor, + CONFIG_SIZE); if (ret) { pr_err("Unable to reconfigure device\n"); return ret; @@ -1654,7 +1661,8 @@ static ssize_t tcmu_emulate_write_cache_store(struct config_item *item, if (tcmu_dev_configured(udev)) { ret = tcmu_netlink_event(TCMU_CMD_RECONFIG_DEVICE, udev->uio_info.name, - udev->uio_info.uio_dev->minor); + udev->uio_info.uio_dev->minor, + CONFIG_WRITECACHE); if (ret) { pr_err("Unable to reconfigure device\n"); return ret; diff --git a/include/uapi/linux/target_core_user.h b/include/uapi/linux/target_core_user.h index 403a61faada0..5b00e3500005 100644 --- a/include/uapi/linux/target_core_user.h +++ b/include/uapi/linux/target_core_user.h @@ -139,8 +139,16 @@ enum tcmu_genl_attr { TCMU_ATTR_UNSPEC, TCMU_ATTR_DEVICE, TCMU_ATTR_MINOR, + TCMU_ATTR_TYPE, __TCMU_ATTR_MAX, }; #define TCMU_ATTR_MAX (__TCMU_ATTR_MAX - 1) +enum tcmu_reconfig_types { + NO_RECONFIG, + CONFIG_PATH, + CONFIG_SIZE, + CONFIG_WRITECACHE, +}; + #endif -- cgit v1.2.3-59-g8ed1b From 1d6ef276594a781686058802996e09c8550fd767 Mon Sep 17 00:00:00 2001 From: Jiang Yi Date: Sun, 25 Jun 2017 12:28:50 -0700 Subject: target: Fix COMPARE_AND_WRITE caw_sem leak during se_cmd quiesce This patch addresses a COMPARE_AND_WRITE se_device->caw_sem leak, that would be triggered during normal se_cmd shutdown or abort via __transport_wait_for_tasks(). This would occur because target_complete_cmd() would catch this early and do complete_all(&cmd->t_transport_stop_comp), but since target_complete_ok_work() or target_complete_failure_work() are never called to invoke se_cmd->transport_complete_callback(), the COMPARE_AND_WRITE specific callbacks never release caw_sem. To address this special case, go ahead and release caw_sem directly from target_complete_cmd(). (Remove '&& success' from check, to release caw_sem regardless of scsi_status - nab) Signed-off-by: Jiang Yi Cc: # 3.14+ Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_transport.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index a5ecec8f3996..28de421e3220 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -730,6 +730,15 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status) if (cmd->transport_state & CMD_T_ABORTED || cmd->transport_state & CMD_T_STOP) { spin_unlock_irqrestore(&cmd->t_state_lock, flags); + /* + * If COMPARE_AND_WRITE was stopped by __transport_wait_for_tasks(), + * release se_device->caw_sem obtained by sbc_compare_and_write() + * since target_complete_ok_work() or target_complete_failure_work() + * won't be called to invoke the normal CAW completion callbacks. + */ + if (cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) { + up(&dev->caw_sem); + } complete_all(&cmd->t_transport_stop_comp); return; } else if (!success) { -- cgit v1.2.3-59-g8ed1b From 07932a023af3cd728390ffdaeffb78e357123181 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Thu, 15 Jun 2017 15:05:31 +0800 Subject: tcmu: Fix module removal due to stuck unmap_thread thread again Because the unmap code just after the schdule() returned may take a long time and if the kthread_stop() is fired just when in this routine, the module removal maybe stuck too. Signed-off-by: Xiubo Li Reviewed-by: Mike Christie Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_user.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index afc1fd6bacaf..a60a66d61146 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -1707,7 +1707,7 @@ static int unmap_thread_fn(void *data) struct page *page; int i; - while (1) { + while (!kthread_should_stop()) { DEFINE_WAIT(__wait); prepare_to_wait(&unmap_wait, &__wait, TASK_INTERRUPTIBLE); -- cgit v1.2.3-59-g8ed1b From 5821783bcaa94f4a00d65effb3fb8937b08cb2ae Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 13 Jun 2017 14:29:09 +0100 Subject: tcmu: make array tcmu_attrib_attrs static const The array tcmu_attrib_attrs does not need to be in global scope, so make it static. Cleans up sparse warning: "symbol 'tcmu_attrib_attrs' was not declared. Should it be static?" Signed-off-by: Colin Ian King Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_user.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index a60a66d61146..6322269d9e85 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -1672,7 +1672,7 @@ static ssize_t tcmu_emulate_write_cache_store(struct config_item *item, } CONFIGFS_ATTR(tcmu_, emulate_write_cache); -struct configfs_attribute *tcmu_attrib_attrs[] = { +static struct configfs_attribute *tcmu_attrib_attrs[] = { &tcmu_attr_cmd_time_out, &tcmu_attr_dev_path, &tcmu_attr_dev_size, -- cgit v1.2.3-59-g8ed1b From fce50a2fa4e9c6e103915c351b6d4a98661341d6 Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Thu, 29 Jun 2017 22:21:31 -0700 Subject: iser-target: Avoid isert_conn->cm_id dereference in isert_login_recv_done This patch fixes a NULL pointer dereference in isert_login_recv_done() of isert_conn->cm_id due to isert_cma_handler() -> isert_connect_error() resetting isert_conn->cm_id = NULL during a failed login attempt. As per Sagi, we will always see the completion of all recv wrs posted on the qp (given that we assigned a ->done handler), this is a FLUSH error completion, we just don't get to verify that because we deref NULL before. The issue here, was the assumption that dereferencing the connection cm_id is always safe, which is not true since: commit 4a579da2586bd3b79b025947ea24ede2bbfede62 Author: Sagi Grimberg Date: Sun Mar 29 15:52:04 2015 +0300 iser-target: Fix possible deadlock in RDMA_CM connection error As I see it, we have a direct reference to the isert_device from isert_conn which is the one-liner fix that we actually need like we do in isert_rdma_read_done() and isert_rdma_write_done(). Reported-by: Andrea Righi Tested-by: Andrea Righi Reviewed-by: Sagi Grimberg Cc: # 3.10+ Signed-off-by: Nicholas Bellinger --- drivers/infiniband/ulp/isert/ib_isert.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index fcbed35e95a8..0e662656ef42 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -1452,7 +1452,7 @@ static void isert_login_recv_done(struct ib_cq *cq, struct ib_wc *wc) { struct isert_conn *isert_conn = wc->qp->qp_context; - struct ib_device *ib_dev = isert_conn->cm_id->device; + struct ib_device *ib_dev = isert_conn->device->ib_device; if (unlikely(wc->status != IB_WC_SUCCESS)) { isert_print_wc(wc, "login recv"); -- cgit v1.2.3-59-g8ed1b From 5f572526a18418258bfa137e3353656c25439500 Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Fri, 30 Jun 2017 00:08:13 -0700 Subject: qla2xxx: Fix incorrect tcm_qla2xxx_free_cmd use during TMR ABORT This patch drops two incorrect usages of tcm_qla2xxx_free_cmd() during TMR ABORT within tcm_qla2xxx_handle_data_work() and tcm_qla2xxx_aborted_task(), which where attempting to dispatch into workqueue context to do tcm_qla2xxx_complete_free() and subsequently invoke transport_generic_free_cmd(). This is incorrect because during TMR ABORT target-core will drop the outstanding se_cmd->cmd_kref references once it has quiesced the se_cmd via transport_wait_for_tasks(), and in the case of qla2xxx it should not attempt to do it's own transport_generic_free_cmd() once the abort has occured. As reported by Pascal, this was originally manifesting as a BUG_ON(cmd->cmd_in_wq) in qlt_free_cmd() during TMR ABORT, with a LIO backend that had sufficently high enough WRITE latency to trigger a host side TMR ABORT_TASK. In addition, for the case in tcm_qla2xxx_write_pending_status() and tcm_qla2xxx_handle_data_work() that waits for outstanding FCP WRITE data transfer to complete before preceeding with a TMR ABORT, avoid se_cmd->t_transport_stop_comp that is already used by transport_wait_for_tasks() and use a qla2xxx internal struct completion instead. Reported-by: Pascal de Bruijn Tested-by: Pascal de Bruijn Acked-by: Himanshu Madhani Cc: Quinn Tran Cc: # 3.10+ Signed-off-by: Nicholas Bellinger --- drivers/scsi/qla2xxx/qla_target.c | 4 ++++ drivers/scsi/qla2xxx/qla_target.h | 1 + drivers/scsi/qla2xxx/tcm_qla2xxx.c | 36 +++--------------------------------- 3 files changed, 8 insertions(+), 33 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 401e245477d4..8f8ece900801 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -4079,6 +4079,8 @@ static struct qla_tgt_cmd *qlt_get_tag(scsi_qla_host_t *vha, cmd = &((struct qla_tgt_cmd *)se_sess->sess_cmd_map)[tag]; memset(cmd, 0, sizeof(struct qla_tgt_cmd)); + init_completion(&cmd->write_pending_abort_comp); + memcpy(&cmd->atio, atio, sizeof(*atio)); cmd->state = QLA_TGT_STATE_NEW; cmd->tgt = vha->vha_tgt.qla_tgt; @@ -5083,6 +5085,8 @@ qlt_alloc_qfull_cmd(struct scsi_qla_host *vha, qlt_incr_num_pend_cmds(vha); INIT_LIST_HEAD(&cmd->cmd_list); + init_completion(&cmd->write_pending_abort_comp); + memcpy(&cmd->atio, atio, sizeof(*atio)); cmd->tgt = vha->vha_tgt.qla_tgt; diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h index d64420251194..939e93c5d3ae 100644 --- a/drivers/scsi/qla2xxx/qla_target.h +++ b/drivers/scsi/qla2xxx/qla_target.h @@ -868,6 +868,7 @@ struct qla_tgt_cmd { unsigned char sense_buffer[TRANSPORT_SENSE_BUFFER]; spinlock_t cmd_lock; + struct completion write_pending_abort_comp; /* to save extra sess dereferences */ unsigned int conf_compl_supported:1; unsigned int sg_mapped:1; diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index 75aeb9fdfd06..8c1bf9b14bb2 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -415,6 +415,7 @@ static int tcm_qla2xxx_write_pending(struct se_cmd *se_cmd) static int tcm_qla2xxx_write_pending_status(struct se_cmd *se_cmd) { + struct qla_tgt_cmd *cmd = container_of(se_cmd, struct qla_tgt_cmd, se_cmd); unsigned long flags; /* * Check for WRITE_PENDING status to determine if we need to wait for @@ -424,8 +425,7 @@ static int tcm_qla2xxx_write_pending_status(struct se_cmd *se_cmd) if (se_cmd->t_state == TRANSPORT_WRITE_PENDING || se_cmd->t_state == TRANSPORT_COMPLETE_QF_WP) { spin_unlock_irqrestore(&se_cmd->t_state_lock, flags); - wait_for_completion_timeout(&se_cmd->t_transport_stop_comp, - 50); + wait_for_completion(&cmd->write_pending_abort_comp); return 0; } spin_unlock_irqrestore(&se_cmd->t_state_lock, flags); @@ -501,7 +501,6 @@ static int tcm_qla2xxx_handle_cmd(scsi_qla_host_t *vha, struct qla_tgt_cmd *cmd, static void tcm_qla2xxx_handle_data_work(struct work_struct *work) { struct qla_tgt_cmd *cmd = container_of(work, struct qla_tgt_cmd, work); - unsigned long flags; /* * Ensure that the complete FCP WRITE payload has been received. @@ -509,17 +508,6 @@ static void tcm_qla2xxx_handle_data_work(struct work_struct *work) */ cmd->cmd_in_wq = 0; - spin_lock_irqsave(&cmd->cmd_lock, flags); - cmd->data_work = 1; - if (cmd->aborted) { - cmd->data_work_free = 1; - spin_unlock_irqrestore(&cmd->cmd_lock, flags); - - tcm_qla2xxx_free_cmd(cmd); - return; - } - spin_unlock_irqrestore(&cmd->cmd_lock, flags); - cmd->vha->tgt_counters.qla_core_ret_ctio++; if (!cmd->write_data_transferred) { /* @@ -527,7 +515,7 @@ static void tcm_qla2xxx_handle_data_work(struct work_struct *work) * waiting upon completion in tcm_qla2xxx_write_pending_status() */ if (cmd->se_cmd.transport_state & CMD_T_ABORTED) { - complete(&cmd->se_cmd.t_transport_stop_comp); + complete(&cmd->write_pending_abort_comp); return; } @@ -753,31 +741,13 @@ static void tcm_qla2xxx_queue_tm_rsp(struct se_cmd *se_cmd) qlt_xmit_tm_rsp(mcmd); } -#define DATA_WORK_NOT_FREE(_cmd) (_cmd->data_work && !_cmd->data_work_free) static void tcm_qla2xxx_aborted_task(struct se_cmd *se_cmd) { struct qla_tgt_cmd *cmd = container_of(se_cmd, struct qla_tgt_cmd, se_cmd); - unsigned long flags; if (qlt_abort_cmd(cmd)) return; - - spin_lock_irqsave(&cmd->cmd_lock, flags); - if ((cmd->state == QLA_TGT_STATE_NEW)|| - ((cmd->state == QLA_TGT_STATE_DATA_IN) && - DATA_WORK_NOT_FREE(cmd))) { - cmd->data_work_free = 1; - spin_unlock_irqrestore(&cmd->cmd_lock, flags); - /* - * cmd has not reached fw, Use this trigger to free it. - */ - tcm_qla2xxx_free_cmd(cmd); - return; - } - spin_unlock_irqrestore(&cmd->cmd_lock, flags); - return; - } static void tcm_qla2xxx_clear_sess_lookup(struct tcm_qla2xxx_lport *, -- cgit v1.2.3-59-g8ed1b From 2d76443e02f260d7a5bd0ede1851ae5534f0c68d Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Mon, 12 Jun 2017 01:34:28 -0500 Subject: tcmu: reconfigure netlink attr changes 1. TCMU_ATTR_TYPE is too generic when it describes only the reconfiguration type, so rename to TCMU_ATTR_RECONFIG_TYPE. 2. Only return the reconfig type when it is a TCMU_CMD_RECONFIG_DEVICE command. 3. CONFIG_* type is not needed. We can pass the value along with an ATTR to userspace, so it does not need to read sysfs/configfs. 4. Fix leak in tcmu_dev_path_store and rename to dev_config to reflect it is more than just a path that can be changed. 6. Don't update kernel struct value if netlink sending fails. Signed-off-by: Mike Christie Reviewed-by: "Bryant G. Ly" Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_user.c | 73 +++++++++++++++++++++-------------- include/uapi/linux/target_core_user.h | 12 ++---- 2 files changed, 48 insertions(+), 37 deletions(-) diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 6322269d9e85..ca5b081295db 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -1177,7 +1177,8 @@ static int tcmu_release(struct uio_info *info, struct inode *inode) } static int tcmu_netlink_event(enum tcmu_genl_cmd cmd, const char *name, - int minor, int type) + int minor, int reconfig_attr, + const void *reconfig_data) { struct sk_buff *skb; void *msg_header; @@ -1199,9 +1200,27 @@ static int tcmu_netlink_event(enum tcmu_genl_cmd cmd, const char *name, if (ret < 0) goto free_skb; - ret = nla_put_u32(skb, TCMU_ATTR_TYPE, type); - if (ret < 0) - goto free_skb; + if (cmd == TCMU_CMD_RECONFIG_DEVICE) { + switch (reconfig_attr) { + case TCMU_ATTR_DEV_CFG: + ret = nla_put_string(skb, reconfig_attr, reconfig_data); + break; + case TCMU_ATTR_DEV_SIZE: + ret = nla_put_u64_64bit(skb, reconfig_attr, + *((u64 *)reconfig_data), + TCMU_ATTR_PAD); + break; + case TCMU_ATTR_WRITECACHE: + ret = nla_put_u8(skb, reconfig_attr, + *((u8 *)reconfig_data)); + break; + default: + BUG(); + } + + if (ret < 0) + goto free_skb; + } genlmsg_end(skb, msg_header); @@ -1306,7 +1325,7 @@ static int tcmu_configure_device(struct se_device *dev) kref_get(&udev->kref); ret = tcmu_netlink_event(TCMU_CMD_ADDED_DEVICE, udev->uio_info.name, - udev->uio_info.uio_dev->minor, NO_RECONFIG); + udev->uio_info.uio_dev->minor, 0, NULL); if (ret) goto err_netlink; @@ -1388,7 +1407,7 @@ static void tcmu_free_device(struct se_device *dev) if (tcmu_dev_configured(udev)) { tcmu_netlink_event(TCMU_CMD_REMOVED_DEVICE, udev->uio_info.name, - udev->uio_info.uio_dev->minor, NO_RECONFIG); + udev->uio_info.uio_dev->minor, 0, NULL); uio_unregister_device(&udev->uio_info); } @@ -1553,7 +1572,7 @@ static ssize_t tcmu_cmd_time_out_store(struct config_item *item, const char *pag } CONFIGFS_ATTR(tcmu_, cmd_time_out); -static ssize_t tcmu_dev_path_show(struct config_item *item, char *page) +static ssize_t tcmu_dev_config_show(struct config_item *item, char *page) { struct se_dev_attrib *da = container_of(to_config_group(item), struct se_dev_attrib, da_group); @@ -1562,37 +1581,34 @@ static ssize_t tcmu_dev_path_show(struct config_item *item, char *page) return snprintf(page, PAGE_SIZE, "%s\n", udev->dev_config); } -static ssize_t tcmu_dev_path_store(struct config_item *item, const char *page, - size_t count) +static ssize_t tcmu_dev_config_store(struct config_item *item, const char *page, + size_t count) { struct se_dev_attrib *da = container_of(to_config_group(item), struct se_dev_attrib, da_group); struct tcmu_dev *udev = TCMU_DEV(da->da_dev); - char *copy = NULL; - int ret; + int ret, len; - copy = kstrdup(page, GFP_KERNEL); - if (!copy) { - kfree(copy); + len = strlen(page); + if (!len || len > TCMU_CONFIG_LEN - 1) return -EINVAL; - } - strlcpy(udev->dev_config, copy, TCMU_CONFIG_LEN); /* Check if device has been configured before */ if (tcmu_dev_configured(udev)) { ret = tcmu_netlink_event(TCMU_CMD_RECONFIG_DEVICE, udev->uio_info.name, udev->uio_info.uio_dev->minor, - CONFIG_PATH); + TCMU_ATTR_DEV_CFG, page); if (ret) { pr_err("Unable to reconfigure device\n"); return ret; } } + strlcpy(udev->dev_config, page, TCMU_CONFIG_LEN); return count; } -CONFIGFS_ATTR(tcmu_, dev_path); +CONFIGFS_ATTR(tcmu_, dev_config); static ssize_t tcmu_dev_size_show(struct config_item *item, char *page) { @@ -1609,26 +1625,25 @@ static ssize_t tcmu_dev_size_store(struct config_item *item, const char *page, struct se_dev_attrib *da = container_of(to_config_group(item), struct se_dev_attrib, da_group); struct tcmu_dev *udev = TCMU_DEV(da->da_dev); - unsigned long val; + u64 val; int ret; - ret = kstrtoul(page, 0, &val); + ret = kstrtou64(page, 0, &val); if (ret < 0) return ret; - udev->dev_size = val; /* Check if device has been configured before */ if (tcmu_dev_configured(udev)) { ret = tcmu_netlink_event(TCMU_CMD_RECONFIG_DEVICE, udev->uio_info.name, udev->uio_info.uio_dev->minor, - CONFIG_SIZE); + TCMU_ATTR_DEV_SIZE, &val); if (ret) { pr_err("Unable to reconfigure device\n"); return ret; } } - + udev->dev_size = val; return count; } CONFIGFS_ATTR(tcmu_, dev_size); @@ -1648,33 +1663,33 @@ static ssize_t tcmu_emulate_write_cache_store(struct config_item *item, struct se_dev_attrib *da = container_of(to_config_group(item), struct se_dev_attrib, da_group); struct tcmu_dev *udev = TCMU_DEV(da->da_dev); - int val; + u8 val; int ret; - ret = kstrtouint(page, 0, &val); + ret = kstrtou8(page, 0, &val); if (ret < 0) return ret; - da->emulate_write_cache = val; - /* Check if device has been configured before */ if (tcmu_dev_configured(udev)) { ret = tcmu_netlink_event(TCMU_CMD_RECONFIG_DEVICE, udev->uio_info.name, udev->uio_info.uio_dev->minor, - CONFIG_WRITECACHE); + TCMU_ATTR_WRITECACHE, &val); if (ret) { pr_err("Unable to reconfigure device\n"); return ret; } } + + da->emulate_write_cache = val; return count; } CONFIGFS_ATTR(tcmu_, emulate_write_cache); static struct configfs_attribute *tcmu_attrib_attrs[] = { &tcmu_attr_cmd_time_out, - &tcmu_attr_dev_path, + &tcmu_attr_dev_config, &tcmu_attr_dev_size, &tcmu_attr_emulate_write_cache, NULL, diff --git a/include/uapi/linux/target_core_user.h b/include/uapi/linux/target_core_user.h index 5b00e3500005..4bfc9a1b635c 100644 --- a/include/uapi/linux/target_core_user.h +++ b/include/uapi/linux/target_core_user.h @@ -139,16 +139,12 @@ enum tcmu_genl_attr { TCMU_ATTR_UNSPEC, TCMU_ATTR_DEVICE, TCMU_ATTR_MINOR, - TCMU_ATTR_TYPE, + TCMU_ATTR_PAD, + TCMU_ATTR_DEV_CFG, + TCMU_ATTR_DEV_SIZE, + TCMU_ATTR_WRITECACHE, __TCMU_ATTR_MAX, }; #define TCMU_ATTR_MAX (__TCMU_ATTR_MAX - 1) -enum tcmu_reconfig_types { - NO_RECONFIG, - CONFIG_PATH, - CONFIG_SIZE, - CONFIG_WRITECACHE, -}; - #endif -- cgit v1.2.3-59-g8ed1b From 926347061ef1f4d3873829fd1960c6e4b965aa9f Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 23 Jun 2017 01:18:12 -0500 Subject: target: break up free_device callback With this patch free_device is now used to free what is allocated in the alloc_device callback and destroy_device tears down the resources that are setup in the configure_device callback. This patch will be needed in the next patch where tcmu needs to be able to look up the device in the destroy callback. Signed-off-by: Mike Christie Reviewed-by: Bart Van Assche Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_device.c | 2 ++ drivers/target/target_core_file.c | 7 ++++++- drivers/target/target_core_iblock.c | 8 ++++++-- drivers/target/target_core_pscsi.c | 7 ++++++- drivers/target/target_core_rd.c | 7 ++++++- drivers/target/target_core_user.c | 12 +++++++++--- include/target/target_core_backend.h | 1 + 7 files changed, 36 insertions(+), 8 deletions(-) diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 11c80c47b9d3..16a701fed66b 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -974,6 +974,8 @@ void target_free_device(struct se_device *dev) if (dev->dev_flags & DF_CONFIGURED) { destroy_workqueue(dev->tmr_wq); + dev->transport->destroy_device(dev); + mutex_lock(&g_device_mutex); list_del(&dev->g_dev_node); mutex_unlock(&g_device_mutex); diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index 73b8f93a5fef..50f235580546 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -236,6 +236,11 @@ static void fd_dev_call_rcu(struct rcu_head *p) } static void fd_free_device(struct se_device *dev) +{ + call_rcu(&dev->rcu_head, fd_dev_call_rcu); +} + +static void fd_destroy_device(struct se_device *dev) { struct fd_dev *fd_dev = FD_DEV(dev); @@ -243,7 +248,6 @@ static void fd_free_device(struct se_device *dev) filp_close(fd_dev->fd_file, NULL); fd_dev->fd_file = NULL; } - call_rcu(&dev->rcu_head, fd_dev_call_rcu); } static int fd_do_rw(struct se_cmd *cmd, struct file *fd, @@ -826,6 +830,7 @@ static const struct target_backend_ops fileio_ops = { .detach_hba = fd_detach_hba, .alloc_device = fd_alloc_device, .configure_device = fd_configure_device, + .destroy_device = fd_destroy_device, .free_device = fd_free_device, .parse_cdb = fd_parse_cdb, .set_configfs_dev_params = fd_set_configfs_dev_params, diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index b2044133d747..a5e16f715392 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -189,6 +189,11 @@ static void iblock_dev_call_rcu(struct rcu_head *p) } static void iblock_free_device(struct se_device *dev) +{ + call_rcu(&dev->rcu_head, iblock_dev_call_rcu); +} + +static void iblock_destroy_device(struct se_device *dev) { struct iblock_dev *ib_dev = IBLOCK_DEV(dev); @@ -196,8 +201,6 @@ static void iblock_free_device(struct se_device *dev) blkdev_put(ib_dev->ibd_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL); if (ib_dev->ibd_bio_set != NULL) bioset_free(ib_dev->ibd_bio_set); - - call_rcu(&dev->rcu_head, iblock_dev_call_rcu); } static unsigned long long iblock_emulate_read_cap_with_block_size( @@ -858,6 +861,7 @@ static const struct target_backend_ops iblock_ops = { .detach_hba = iblock_detach_hba, .alloc_device = iblock_alloc_device, .configure_device = iblock_configure_device, + .destroy_device = iblock_destroy_device, .free_device = iblock_free_device, .parse_cdb = iblock_parse_cdb, .set_configfs_dev_params = iblock_set_configfs_dev_params, diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index e0be4aa38328..7d944b23aeee 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -563,6 +563,11 @@ static void pscsi_dev_call_rcu(struct rcu_head *p) } static void pscsi_free_device(struct se_device *dev) +{ + call_rcu(&dev->rcu_head, pscsi_dev_call_rcu); +} + +static void pscsi_destroy_device(struct se_device *dev) { struct pscsi_dev_virt *pdv = PSCSI_DEV(dev); struct pscsi_hba_virt *phv = dev->se_hba->hba_ptr; @@ -592,7 +597,6 @@ static void pscsi_free_device(struct se_device *dev) pdv->pdv_sd = NULL; } - call_rcu(&dev->rcu_head, pscsi_dev_call_rcu); } static void pscsi_transport_complete(struct se_cmd *cmd, struct scatterlist *sg, @@ -1084,6 +1088,7 @@ static const struct target_backend_ops pscsi_ops = { .pmode_enable_hba = pscsi_pmode_enable_hba, .alloc_device = pscsi_alloc_device, .configure_device = pscsi_configure_device, + .destroy_device = pscsi_destroy_device, .free_device = pscsi_free_device, .transport_complete = pscsi_transport_complete, .parse_cdb = pscsi_parse_cdb, diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c index d12967690054..a6e8106abd6f 100644 --- a/drivers/target/target_core_rd.c +++ b/drivers/target/target_core_rd.c @@ -338,11 +338,15 @@ static void rd_dev_call_rcu(struct rcu_head *p) } static void rd_free_device(struct se_device *dev) +{ + call_rcu(&dev->rcu_head, rd_dev_call_rcu); +} + +static void rd_destroy_device(struct se_device *dev) { struct rd_dev *rd_dev = RD_DEV(dev); rd_release_device_space(rd_dev); - call_rcu(&dev->rcu_head, rd_dev_call_rcu); } static struct rd_dev_sg_table *rd_get_sg_table(struct rd_dev *rd_dev, u32 page) @@ -651,6 +655,7 @@ static const struct target_backend_ops rd_mcp_ops = { .detach_hba = rd_detach_hba, .alloc_device = rd_alloc_device, .configure_device = rd_configure_device, + .destroy_device = rd_destroy_device, .free_device = rd_free_device, .parse_cdb = rd_parse_cdb, .set_configfs_dev_params = rd_set_configfs_dev_params, diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index ca5b081295db..e58127b8db8a 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -1379,6 +1379,14 @@ static void tcmu_blocks_release(struct tcmu_dev *udev) } static void tcmu_free_device(struct se_device *dev) +{ + struct tcmu_dev *udev = TCMU_DEV(dev); + + /* release ref from init */ + kref_put(&udev->kref, tcmu_dev_kref_release); +} + +static void tcmu_destroy_device(struct se_device *dev) { struct tcmu_dev *udev = TCMU_DEV(dev); struct tcmu_cmd *cmd; @@ -1411,9 +1419,6 @@ static void tcmu_free_device(struct se_device *dev) uio_unregister_device(&udev->uio_info); } - - /* release ref from init */ - kref_put(&udev->kref, tcmu_dev_kref_release); } enum { @@ -1705,6 +1710,7 @@ static struct target_backend_ops tcmu_ops = { .detach_hba = tcmu_detach_hba, .alloc_device = tcmu_alloc_device, .configure_device = tcmu_configure_device, + .destroy_device = tcmu_destroy_device, .free_device = tcmu_free_device, .parse_cdb = tcmu_parse_cdb, .set_configfs_dev_params = tcmu_set_configfs_dev_params, diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index b76071161cdc..3dbcacd7e8d7 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -30,6 +30,7 @@ struct target_backend_ops { struct se_device *(*alloc_device)(struct se_hba *, const char *); int (*configure_device)(struct se_device *); + void (*destroy_device)(struct se_device *); void (*free_device)(struct se_device *device); ssize_t (*set_configfs_dev_params)(struct se_device *, -- cgit v1.2.3-59-g8ed1b From 0a5eee647b78e53da05e081362f42a11b4b674eb Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 23 Jun 2017 01:18:13 -0500 Subject: target: use idr for se_device dev index In the next patches we will add tcmu netlink support that allows userspace to send commands to target_core_user. To execute operations on a se_device/tcmu_dev we need to be able to look up a dev by any old id. This patch replaces the se_device->dev_index with a idr created id. The next patches will also remove the g_device_list and replace it with the idr. Signed-off-by: Mike Christie Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_device.c | 30 ++++++++++++++++++++++++++---- include/target/target_core_base.h | 1 - 2 files changed, 26 insertions(+), 5 deletions(-) diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 16a701fed66b..f10dfe7b1d54 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -51,6 +51,7 @@ DEFINE_MUTEX(g_device_mutex); LIST_HEAD(g_device_list); +static DEFINE_IDR(devices_idr); static struct se_hba *lun0_hba; /* not static, needed by tpg.c */ @@ -882,7 +883,7 @@ EXPORT_SYMBOL(target_to_linux_sector); int target_configure_device(struct se_device *dev) { struct se_hba *hba = dev->se_hba; - int ret; + int ret, id; if (dev->dev_flags & DF_CONFIGURED) { pr_err("se_dev->se_dev_ptr already set for storage" @@ -890,9 +891,26 @@ int target_configure_device(struct se_device *dev) return -EEXIST; } + /* + * Add early so modules like tcmu can use during its + * configuration. + */ + mutex_lock(&g_device_mutex); + /* + * Use cyclic to try and avoid collisions with devices + * that were recently removed. + */ + id = idr_alloc_cyclic(&devices_idr, dev, 0, INT_MAX, GFP_KERNEL); + mutex_unlock(&g_device_mutex); + if (id < 0) { + ret = -ENOMEM; + goto out; + } + dev->dev_index = id; + ret = dev->transport->configure_device(dev); if (ret) - goto out; + goto out_free_index; /* * XXX: there is not much point to have two different values here.. */ @@ -907,12 +925,11 @@ int target_configure_device(struct se_device *dev) dev->dev_attrib.hw_block_size); dev->dev_attrib.optimal_sectors = dev->dev_attrib.hw_max_sectors; - dev->dev_index = scsi_get_new_index(SCSI_DEVICE_INDEX); dev->creation_time = get_jiffies_64(); ret = core_setup_alua(dev); if (ret) - goto out; + goto out_free_index; /* * Startup the struct se_device processing thread @@ -960,6 +977,10 @@ int target_configure_device(struct se_device *dev) out_free_alua: core_alua_free_lu_gp_mem(dev); +out_free_index: + mutex_lock(&g_device_mutex); + idr_remove(&devices_idr, dev->dev_index); + mutex_unlock(&g_device_mutex); out: se_release_vpd_for_dev(dev); return ret; @@ -977,6 +998,7 @@ void target_free_device(struct se_device *dev) dev->transport->destroy_device(dev); mutex_lock(&g_device_mutex); + idr_remove(&devices_idr, dev->dev_index); list_del(&dev->g_dev_node); mutex_unlock(&g_device_mutex); diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index a3af69fcf75e..51a92f17352c 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -219,7 +219,6 @@ enum tcm_tmrsp_table { */ typedef enum { SCSI_INST_INDEX, - SCSI_DEVICE_INDEX, SCSI_AUTH_INTR_INDEX, SCSI_INDEX_TYPE_MAX } scsi_index_t; -- cgit v1.2.3-59-g8ed1b From 85441e6b8c97964a6da72135dc21f708adbdc4d8 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 23 Jun 2017 01:18:14 -0500 Subject: target: add helper to find se_device by dev_index This adds a helper to find a se_device by dev_index. It will be used in the next patches so tcmu's netlink interface can execute commands on specific devices. Signed-off-by: Mike Christie Reviewed-by: Bart Van Assche Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_device.c | 24 ++++++++++++++++++++++++ include/target/target_core_backend.h | 2 ++ 2 files changed, 26 insertions(+) diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index f10dfe7b1d54..de1131612ddc 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -880,6 +880,30 @@ sector_t target_to_linux_sector(struct se_device *dev, sector_t lb) } EXPORT_SYMBOL(target_to_linux_sector); +/** + * target_find_device - find a se_device by its dev_index + * @id: dev_index + * @do_depend: true if caller needs target_depend_item to be done + * + * If do_depend is true, the caller must do a target_undepend_item + * when finished using the device. + * + * If do_depend is false, the caller must be called in a configfs + * callback or during removal. + */ +struct se_device *target_find_device(int id, bool do_depend) +{ + struct se_device *dev; + + mutex_lock(&g_device_mutex); + dev = idr_find(&devices_idr, id); + if (dev && do_depend && target_depend_item(&dev->dev_group.cg_item)) + dev = NULL; + mutex_unlock(&g_device_mutex); + return dev; +} +EXPORT_SYMBOL(target_find_device); + int target_configure_device(struct se_device *dev) { struct se_hba *hba = dev->se_hba; diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index 3dbcacd7e8d7..1f2b7007f2df 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -106,6 +106,8 @@ bool target_lun_is_rdonly(struct se_cmd *); sense_reason_t passthrough_parse_cdb(struct se_cmd *cmd, sense_reason_t (*exec_cmd)(struct se_cmd *cmd)); +struct se_device *target_find_device(int id, bool do_depend); + bool target_sense_desc_format(struct se_device *dev); sector_t target_to_linux_sector(struct se_device *dev, sector_t lb); bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib, -- cgit v1.2.3-59-g8ed1b From b3af66e24393f03ef81db17a11387d9e6174bd01 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 23 Jun 2017 01:18:15 -0500 Subject: tcmu: perfom device add, del and reconfig synchronously This makes the device add, del reconfig operations sync. It fixes the issue where for add and reconfig, we do not know if userspace successfully completely the operation, so we leave invalid kernel structs or report incorrect status for the config/reconfig operations. Signed-off-by: Mike Christie Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_user.c | 213 ++++++++++++++++++++++++++++++---- include/uapi/linux/target_core_user.h | 7 ++ 2 files changed, 200 insertions(+), 20 deletions(-) diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index e58127b8db8a..e080cd1a8fde 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -87,6 +87,8 @@ /* Default maximum of the global data blocks(512K * PAGE_SIZE) */ #define TCMU_GLOBAL_MAX_BLOCKS (512 * 1024) +static u8 tcmu_kern_cmd_reply_supported; + static struct device *tcmu_root_device; struct tcmu_hba { @@ -95,6 +97,13 @@ struct tcmu_hba { #define TCMU_CONFIG_LEN 256 +struct tcmu_nl_cmd { + /* wake up thread waiting for reply */ + struct completion complete; + int cmd; + int status; +}; + struct tcmu_dev { struct list_head node; struct kref kref; @@ -135,6 +144,11 @@ struct tcmu_dev { struct timer_list timeout; unsigned int cmd_time_out; + spinlock_t nl_cmd_lock; + struct tcmu_nl_cmd curr_nl_cmd; + /* wake up threads waiting on curr_nl_cmd */ + wait_queue_head_t nl_cmd_wq; + char dev_config[TCMU_CONFIG_LEN]; }; @@ -178,16 +192,128 @@ static const struct genl_multicast_group tcmu_mcgrps[] = { [TCMU_MCGRP_CONFIG] = { .name = "config", }, }; +static struct nla_policy tcmu_attr_policy[TCMU_ATTR_MAX+1] = { + [TCMU_ATTR_DEVICE] = { .type = NLA_STRING }, + [TCMU_ATTR_MINOR] = { .type = NLA_U32 }, + [TCMU_ATTR_CMD_STATUS] = { .type = NLA_S32 }, + [TCMU_ATTR_DEVICE_ID] = { .type = NLA_U32 }, + [TCMU_ATTR_SUPP_KERN_CMD_REPLY] = { .type = NLA_U8 }, +}; + +static int tcmu_genl_cmd_done(struct genl_info *info, int completed_cmd) +{ + struct se_device *dev; + struct tcmu_dev *udev; + struct tcmu_nl_cmd *nl_cmd; + int dev_id, rc, ret = 0; + bool is_removed = (completed_cmd == TCMU_CMD_REMOVED_DEVICE); + + if (!info->attrs[TCMU_ATTR_CMD_STATUS] || + !info->attrs[TCMU_ATTR_DEVICE_ID]) { + printk(KERN_ERR "TCMU_ATTR_CMD_STATUS or TCMU_ATTR_DEVICE_ID not set, doing nothing\n"); + return -EINVAL; + } + + dev_id = nla_get_u32(info->attrs[TCMU_ATTR_DEVICE_ID]); + rc = nla_get_s32(info->attrs[TCMU_ATTR_CMD_STATUS]); + + dev = target_find_device(dev_id, !is_removed); + if (!dev) { + printk(KERN_ERR "tcmu nl cmd %u/%u completion could not find device with dev id %u.\n", + completed_cmd, rc, dev_id); + return -ENODEV; + } + udev = TCMU_DEV(dev); + + spin_lock(&udev->nl_cmd_lock); + nl_cmd = &udev->curr_nl_cmd; + + pr_debug("genl cmd done got id %d curr %d done %d rc %d\n", dev_id, + nl_cmd->cmd, completed_cmd, rc); + + if (nl_cmd->cmd != completed_cmd) { + printk(KERN_ERR "Mismatched commands (Expecting reply for %d. Current %d).\n", + completed_cmd, nl_cmd->cmd); + ret = -EINVAL; + } else { + nl_cmd->status = rc; + } + + spin_unlock(&udev->nl_cmd_lock); + if (!is_removed) + target_undepend_item(&dev->dev_group.cg_item); + if (!ret) + complete(&nl_cmd->complete); + return ret; +} + +static int tcmu_genl_rm_dev_done(struct sk_buff *skb, struct genl_info *info) +{ + return tcmu_genl_cmd_done(info, TCMU_CMD_REMOVED_DEVICE); +} + +static int tcmu_genl_add_dev_done(struct sk_buff *skb, struct genl_info *info) +{ + return tcmu_genl_cmd_done(info, TCMU_CMD_ADDED_DEVICE); +} + +static int tcmu_genl_reconfig_dev_done(struct sk_buff *skb, + struct genl_info *info) +{ + return tcmu_genl_cmd_done(info, TCMU_CMD_RECONFIG_DEVICE); +} + +static int tcmu_genl_set_features(struct sk_buff *skb, struct genl_info *info) +{ + if (info->attrs[TCMU_ATTR_SUPP_KERN_CMD_REPLY]) { + tcmu_kern_cmd_reply_supported = + nla_get_u8(info->attrs[TCMU_ATTR_SUPP_KERN_CMD_REPLY]); + printk(KERN_INFO "tcmu daemon: command reply support %u.\n", + tcmu_kern_cmd_reply_supported); + } + + return 0; +} + +static const struct genl_ops tcmu_genl_ops[] = { + { + .cmd = TCMU_CMD_SET_FEATURES, + .flags = GENL_ADMIN_PERM, + .policy = tcmu_attr_policy, + .doit = tcmu_genl_set_features, + }, + { + .cmd = TCMU_CMD_ADDED_DEVICE_DONE, + .flags = GENL_ADMIN_PERM, + .policy = tcmu_attr_policy, + .doit = tcmu_genl_add_dev_done, + }, + { + .cmd = TCMU_CMD_REMOVED_DEVICE_DONE, + .flags = GENL_ADMIN_PERM, + .policy = tcmu_attr_policy, + .doit = tcmu_genl_rm_dev_done, + }, + { + .cmd = TCMU_CMD_RECONFIG_DEVICE_DONE, + .flags = GENL_ADMIN_PERM, + .policy = tcmu_attr_policy, + .doit = tcmu_genl_reconfig_dev_done, + }, +}; + /* Our generic netlink family */ static struct genl_family tcmu_genl_family __ro_after_init = { .module = THIS_MODULE, .hdrsize = 0, .name = "TCM-USER", - .version = 1, + .version = 2, .maxattr = TCMU_ATTR_MAX, .mcgrps = tcmu_mcgrps, .n_mcgrps = ARRAY_SIZE(tcmu_mcgrps), .netnsok = true, + .ops = tcmu_genl_ops, + .n_ops = ARRAY_SIZE(tcmu_genl_ops), }; #define tcmu_cmd_set_dbi_cur(cmd, index) ((cmd)->dbi_cur = (index)) @@ -989,6 +1115,9 @@ static struct se_device *tcmu_alloc_device(struct se_hba *hba, const char *name) setup_timer(&udev->timeout, tcmu_device_timedout, (unsigned long)udev); + init_waitqueue_head(&udev->nl_cmd_wq); + spin_lock_init(&udev->nl_cmd_lock); + return &udev->se_dev; } @@ -1176,9 +1305,54 @@ static int tcmu_release(struct uio_info *info, struct inode *inode) return 0; } -static int tcmu_netlink_event(enum tcmu_genl_cmd cmd, const char *name, - int minor, int reconfig_attr, - const void *reconfig_data) +static void tcmu_init_genl_cmd_reply(struct tcmu_dev *udev, int cmd) +{ + struct tcmu_nl_cmd *nl_cmd = &udev->curr_nl_cmd; + + if (!tcmu_kern_cmd_reply_supported) + return; +relock: + spin_lock(&udev->nl_cmd_lock); + + if (nl_cmd->cmd != TCMU_CMD_UNSPEC) { + spin_unlock(&udev->nl_cmd_lock); + pr_debug("sleeping for open nl cmd\n"); + wait_event(udev->nl_cmd_wq, (nl_cmd->cmd == TCMU_CMD_UNSPEC)); + goto relock; + } + + memset(nl_cmd, 0, sizeof(*nl_cmd)); + nl_cmd->cmd = cmd; + init_completion(&nl_cmd->complete); + + spin_unlock(&udev->nl_cmd_lock); +} + +static int tcmu_wait_genl_cmd_reply(struct tcmu_dev *udev) +{ + struct tcmu_nl_cmd *nl_cmd = &udev->curr_nl_cmd; + int ret; + DEFINE_WAIT(__wait); + + if (!tcmu_kern_cmd_reply_supported) + return 0; + + pr_debug("sleeping for nl reply\n"); + wait_for_completion(&nl_cmd->complete); + + spin_lock(&udev->nl_cmd_lock); + nl_cmd->cmd = TCMU_CMD_UNSPEC; + ret = nl_cmd->status; + nl_cmd->status = 0; + spin_unlock(&udev->nl_cmd_lock); + + wake_up_all(&udev->nl_cmd_wq); + + return ret;; +} + +static int tcmu_netlink_event(struct tcmu_dev *udev, enum tcmu_genl_cmd cmd, + int reconfig_attr, const void *reconfig_data) { struct sk_buff *skb; void *msg_header; @@ -1192,11 +1366,15 @@ static int tcmu_netlink_event(enum tcmu_genl_cmd cmd, const char *name, if (!msg_header) goto free_skb; - ret = nla_put_string(skb, TCMU_ATTR_DEVICE, name); + ret = nla_put_string(skb, TCMU_ATTR_DEVICE, udev->uio_info.name); if (ret < 0) goto free_skb; - ret = nla_put_u32(skb, TCMU_ATTR_MINOR, minor); + ret = nla_put_u32(skb, TCMU_ATTR_MINOR, udev->uio_info.uio_dev->minor); + if (ret < 0) + goto free_skb; + + ret = nla_put_u32(skb, TCMU_ATTR_DEVICE_ID, udev->se_dev.dev_index); if (ret < 0) goto free_skb; @@ -1224,12 +1402,15 @@ static int tcmu_netlink_event(enum tcmu_genl_cmd cmd, const char *name, genlmsg_end(skb, msg_header); + tcmu_init_genl_cmd_reply(udev, cmd); + ret = genlmsg_multicast_allns(&tcmu_genl_family, skb, 0, TCMU_MCGRP_CONFIG, GFP_KERNEL); - /* We don't care if no one is listening */ if (ret == -ESRCH) ret = 0; + if (!ret) + ret = tcmu_wait_genl_cmd_reply(udev); return ret; free_skb: @@ -1324,8 +1505,7 @@ static int tcmu_configure_device(struct se_device *dev) */ kref_get(&udev->kref); - ret = tcmu_netlink_event(TCMU_CMD_ADDED_DEVICE, udev->uio_info.name, - udev->uio_info.uio_dev->minor, 0, NULL); + ret = tcmu_netlink_event(udev, TCMU_CMD_ADDED_DEVICE, 0, NULL); if (ret) goto err_netlink; @@ -1414,8 +1594,7 @@ static void tcmu_destroy_device(struct se_device *dev) tcmu_blocks_release(udev); if (tcmu_dev_configured(udev)) { - tcmu_netlink_event(TCMU_CMD_REMOVED_DEVICE, udev->uio_info.name, - udev->uio_info.uio_dev->minor, 0, NULL); + tcmu_netlink_event(udev, TCMU_CMD_REMOVED_DEVICE, 0, NULL); uio_unregister_device(&udev->uio_info); } @@ -1600,9 +1779,7 @@ static ssize_t tcmu_dev_config_store(struct config_item *item, const char *page, /* Check if device has been configured before */ if (tcmu_dev_configured(udev)) { - ret = tcmu_netlink_event(TCMU_CMD_RECONFIG_DEVICE, - udev->uio_info.name, - udev->uio_info.uio_dev->minor, + ret = tcmu_netlink_event(udev, TCMU_CMD_RECONFIG_DEVICE, TCMU_ATTR_DEV_CFG, page); if (ret) { pr_err("Unable to reconfigure device\n"); @@ -1639,9 +1816,7 @@ static ssize_t tcmu_dev_size_store(struct config_item *item, const char *page, /* Check if device has been configured before */ if (tcmu_dev_configured(udev)) { - ret = tcmu_netlink_event(TCMU_CMD_RECONFIG_DEVICE, - udev->uio_info.name, - udev->uio_info.uio_dev->minor, + ret = tcmu_netlink_event(udev, TCMU_CMD_RECONFIG_DEVICE, TCMU_ATTR_DEV_SIZE, &val); if (ret) { pr_err("Unable to reconfigure device\n"); @@ -1677,9 +1852,7 @@ static ssize_t tcmu_emulate_write_cache_store(struct config_item *item, /* Check if device has been configured before */ if (tcmu_dev_configured(udev)) { - ret = tcmu_netlink_event(TCMU_CMD_RECONFIG_DEVICE, - udev->uio_info.name, - udev->uio_info.uio_dev->minor, + ret = tcmu_netlink_event(udev, TCMU_CMD_RECONFIG_DEVICE, TCMU_ATTR_WRITECACHE, &val); if (ret) { pr_err("Unable to reconfigure device\n"); diff --git a/include/uapi/linux/target_core_user.h b/include/uapi/linux/target_core_user.h index 4bfc9a1b635c..24a1c4ec2248 100644 --- a/include/uapi/linux/target_core_user.h +++ b/include/uapi/linux/target_core_user.h @@ -131,6 +131,10 @@ enum tcmu_genl_cmd { TCMU_CMD_ADDED_DEVICE, TCMU_CMD_REMOVED_DEVICE, TCMU_CMD_RECONFIG_DEVICE, + TCMU_CMD_ADDED_DEVICE_DONE, + TCMU_CMD_REMOVED_DEVICE_DONE, + TCMU_CMD_RECONFIG_DEVICE_DONE, + TCMU_CMD_SET_FEATURES, __TCMU_CMD_MAX, }; #define TCMU_CMD_MAX (__TCMU_CMD_MAX - 1) @@ -143,6 +147,9 @@ enum tcmu_genl_attr { TCMU_ATTR_DEV_CFG, TCMU_ATTR_DEV_SIZE, TCMU_ATTR_WRITECACHE, + TCMU_ATTR_CMD_STATUS, + TCMU_ATTR_DEVICE_ID, + TCMU_ATTR_SUPP_KERN_CMD_REPLY, __TCMU_ATTR_MAX, }; #define TCMU_ATTR_MAX (__TCMU_ATTR_MAX - 1) -- cgit v1.2.3-59-g8ed1b From b1943fd454d1a2e2c8018a2f79a7023893619439 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 23 Jun 2017 01:18:16 -0500 Subject: target: add helper to iterate over devices This adds a wrapper around idr_for_each so the xcopy code can loop over the devices in the next patch. Signed-off-by: Mike Christie Reviewed-by: Bart Van Assche Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_device.c | 45 +++++++++++++++++++++++++++++++++++ drivers/target/target_core_internal.h | 2 ++ 2 files changed, 47 insertions(+) diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index de1131612ddc..bd32a0c65961 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -904,6 +904,51 @@ struct se_device *target_find_device(int id, bool do_depend) } EXPORT_SYMBOL(target_find_device); +struct devices_idr_iter { + int (*fn)(struct se_device *dev, void *data); + void *data; +}; + +static int target_devices_idr_iter(int id, void *p, void *data) +{ + struct devices_idr_iter *iter = data; + struct se_device *dev = p; + + /* + * We add the device early to the idr, so it can be used + * by backend modules during configuration. We do not want + * to allow other callers to access partially setup devices, + * so we skip them here. + */ + if (!(dev->dev_flags & DF_CONFIGURED)) + return 0; + + return iter->fn(dev, iter->data); +} + +/** + * target_for_each_device - iterate over configured devices + * @fn: iterator function + * @data: pointer to data that will be passed to fn + * + * fn must return 0 to continue looping over devices. non-zero will break + * from the loop and return that value to the caller. + */ +int target_for_each_device(int (*fn)(struct se_device *dev, void *data), + void *data) +{ + struct devices_idr_iter iter; + int ret; + + iter.fn = fn; + iter.data = data; + + mutex_lock(&g_device_mutex); + ret = idr_for_each(&devices_idr, target_devices_idr_iter, &iter); + mutex_unlock(&g_device_mutex); + return ret; +} + int target_configure_device(struct se_device *dev) { struct se_hba *hba = dev->se_hba; diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h index 0912de7c0cf8..1d3ac0238568 100644 --- a/drivers/target/target_core_internal.h +++ b/drivers/target/target_core_internal.h @@ -87,6 +87,8 @@ void core_dev_release_virtual_lun0(void); struct se_device *target_alloc_device(struct se_hba *hba, const char *name); int target_configure_device(struct se_device *dev); void target_free_device(struct se_device *); +int target_for_each_device(int (*fn)(struct se_device *dev, void *data), + void *data); /* target_core_configfs.c */ void target_setup_backend_cits(struct target_backend *); -- cgit v1.2.3-59-g8ed1b From 6906d008b4b06e42cad393ac25bec76fbf31fabd Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 23 Jun 2017 01:18:17 -0500 Subject: xcopy: loop over devices using idr helper This converts the xcopy code to use the idr helper. The next patch will drop the g_device_list and make g_device_mutex local to the target_core_device.c file. Signed-off-by: Mike Christie Reviewed-by: Bart Van Assche Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_xcopy.c | 70 ++++++++++++++++++++++---------------- 1 file changed, 41 insertions(+), 29 deletions(-) diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c index 56738a41e346..9ee89e00cd77 100644 --- a/drivers/target/target_core_xcopy.c +++ b/drivers/target/target_core_xcopy.c @@ -55,48 +55,60 @@ static int target_xcopy_gen_naa_ieee(struct se_device *dev, unsigned char *buf) return 0; } -static int target_xcopy_locate_se_dev_e4(const unsigned char *dev_wwn, - struct se_device **found_dev) +struct xcopy_dev_search_info { + const unsigned char *dev_wwn; + struct se_device *found_dev; +}; + +static int target_xcopy_locate_se_dev_e4_iter(struct se_device *se_dev, + void *data) { - struct se_device *se_dev; + struct xcopy_dev_search_info *info = data; unsigned char tmp_dev_wwn[XCOPY_NAA_IEEE_REGEX_LEN]; int rc; - mutex_lock(&g_device_mutex); - list_for_each_entry(se_dev, &g_device_list, g_dev_node) { + if (!se_dev->dev_attrib.emulate_3pc) + return 0; - if (!se_dev->dev_attrib.emulate_3pc) - continue; + memset(&tmp_dev_wwn[0], 0, XCOPY_NAA_IEEE_REGEX_LEN); + target_xcopy_gen_naa_ieee(se_dev, &tmp_dev_wwn[0]); - memset(&tmp_dev_wwn[0], 0, XCOPY_NAA_IEEE_REGEX_LEN); - target_xcopy_gen_naa_ieee(se_dev, &tmp_dev_wwn[0]); + rc = memcmp(&tmp_dev_wwn[0], info->dev_wwn, XCOPY_NAA_IEEE_REGEX_LEN); + if (rc != 0) + return 0; - rc = memcmp(&tmp_dev_wwn[0], dev_wwn, XCOPY_NAA_IEEE_REGEX_LEN); - if (rc != 0) - continue; + info->found_dev = se_dev; + pr_debug("XCOPY 0xe4: located se_dev: %p\n", se_dev); - *found_dev = se_dev; - pr_debug("XCOPY 0xe4: located se_dev: %p\n", se_dev); + rc = target_depend_item(&se_dev->dev_group.cg_item); + if (rc != 0) { + pr_err("configfs_depend_item attempt failed: %d for se_dev: %p\n", + rc, se_dev); + return rc; + } - rc = target_depend_item(&se_dev->dev_group.cg_item); - if (rc != 0) { - pr_err("configfs_depend_item attempt failed:" - " %d for se_dev: %p\n", rc, se_dev); - mutex_unlock(&g_device_mutex); - return rc; - } + pr_debug("Called configfs_depend_item for se_dev: %p se_dev->se_dev_group: %p\n", + se_dev, &se_dev->dev_group); + return 1; +} + +static int target_xcopy_locate_se_dev_e4(const unsigned char *dev_wwn, + struct se_device **found_dev) +{ + struct xcopy_dev_search_info info; + int ret; - pr_debug("Called configfs_depend_item for se_dev: %p" - " se_dev->se_dev_group: %p\n", se_dev, - &se_dev->dev_group); + memset(&info, 0, sizeof(info)); + info.dev_wwn = dev_wwn; - mutex_unlock(&g_device_mutex); + ret = target_for_each_device(target_xcopy_locate_se_dev_e4_iter, &info); + if (ret == 1) { + *found_dev = info.found_dev; return 0; + } else { + pr_debug_ratelimited("Unable to locate 0xe4 descriptor for EXTENDED_COPY\n"); + return -EINVAL; } - mutex_unlock(&g_device_mutex); - - pr_debug_ratelimited("Unable to locate 0xe4 descriptor for EXTENDED_COPY\n"); - return -EINVAL; } static int target_xcopy_parse_tiddesc_e4(struct se_cmd *se_cmd, struct xcopy_op *xop, -- cgit v1.2.3-59-g8ed1b From be50f538e9a5081c61a78faf58c5591c94064633 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 23 Jun 2017 01:18:18 -0500 Subject: target: remove g_device_list g_device_list is no longer needed because we now use the idr code for lookups and seaches. Signed-off-by: Mike Christie Reviewed-by: Bart Van Assche Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_device.c | 30 ++++++++++++------------------ drivers/target/target_core_internal.h | 3 --- include/target/target_core_base.h | 1 - 3 files changed, 12 insertions(+), 22 deletions(-) diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index bd32a0c65961..3ae8fbf01bdf 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -49,8 +49,8 @@ #include "target_core_pr.h" #include "target_core_ua.h" -DEFINE_MUTEX(g_device_mutex); -LIST_HEAD(g_device_list); +DEFINE_MUTEX(device_mutex); +LIST_HEAD(device_list); static DEFINE_IDR(devices_idr); static struct se_hba *lun0_hba; @@ -773,7 +773,6 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name) INIT_LIST_HEAD(&dev->delayed_cmd_list); INIT_LIST_HEAD(&dev->state_list); INIT_LIST_HEAD(&dev->qf_cmd_list); - INIT_LIST_HEAD(&dev->g_dev_node); spin_lock_init(&dev->execute_task_lock); spin_lock_init(&dev->delayed_cmd_lock); spin_lock_init(&dev->dev_reservation_lock); @@ -895,11 +894,11 @@ struct se_device *target_find_device(int id, bool do_depend) { struct se_device *dev; - mutex_lock(&g_device_mutex); + mutex_lock(&device_mutex); dev = idr_find(&devices_idr, id); if (dev && do_depend && target_depend_item(&dev->dev_group.cg_item)) dev = NULL; - mutex_unlock(&g_device_mutex); + mutex_unlock(&device_mutex); return dev; } EXPORT_SYMBOL(target_find_device); @@ -943,9 +942,9 @@ int target_for_each_device(int (*fn)(struct se_device *dev, void *data), iter.fn = fn; iter.data = data; - mutex_lock(&g_device_mutex); + mutex_lock(&device_mutex); ret = idr_for_each(&devices_idr, target_devices_idr_iter, &iter); - mutex_unlock(&g_device_mutex); + mutex_unlock(&device_mutex); return ret; } @@ -964,13 +963,13 @@ int target_configure_device(struct se_device *dev) * Add early so modules like tcmu can use during its * configuration. */ - mutex_lock(&g_device_mutex); + mutex_lock(&device_mutex); /* * Use cyclic to try and avoid collisions with devices * that were recently removed. */ id = idr_alloc_cyclic(&devices_idr, dev, 0, INT_MAX, GFP_KERNEL); - mutex_unlock(&g_device_mutex); + mutex_unlock(&device_mutex); if (id < 0) { ret = -ENOMEM; goto out; @@ -1036,10 +1035,6 @@ int target_configure_device(struct se_device *dev) hba->dev_count++; spin_unlock(&hba->device_lock); - mutex_lock(&g_device_mutex); - list_add_tail(&dev->g_dev_node, &g_device_list); - mutex_unlock(&g_device_mutex); - dev->dev_flags |= DF_CONFIGURED; return 0; @@ -1047,9 +1042,9 @@ int target_configure_device(struct se_device *dev) out_free_alua: core_alua_free_lu_gp_mem(dev); out_free_index: - mutex_lock(&g_device_mutex); + mutex_lock(&device_mutex); idr_remove(&devices_idr, dev->dev_index); - mutex_unlock(&g_device_mutex); + mutex_unlock(&device_mutex); out: se_release_vpd_for_dev(dev); return ret; @@ -1066,10 +1061,9 @@ void target_free_device(struct se_device *dev) dev->transport->destroy_device(dev); - mutex_lock(&g_device_mutex); + mutex_lock(&device_mutex); idr_remove(&devices_idr, dev->dev_index); - list_del(&dev->g_dev_node); - mutex_unlock(&g_device_mutex); + mutex_unlock(&device_mutex); spin_lock(&hba->device_lock); hba->dev_count--; diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h index 1d3ac0238568..f30e8ac13386 100644 --- a/drivers/target/target_core_internal.h +++ b/drivers/target/target_core_internal.h @@ -56,9 +56,6 @@ struct target_fabric_configfs { extern struct t10_alua_lu_gp *default_lu_gp; /* target_core_device.c */ -extern struct mutex g_device_mutex; -extern struct list_head g_device_list; - int core_alloc_rtpi(struct se_lun *lun, struct se_device *dev); struct se_dev_entry *core_get_se_deve_from_rtpi(struct se_node_acl *, u16); void target_pr_kref_release(struct kref *); diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 51a92f17352c..516764febeb7 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -796,7 +796,6 @@ struct se_device { struct list_head delayed_cmd_list; struct list_head state_list; struct list_head qf_cmd_list; - struct list_head g_dev_node; /* Pointer to associated SE HBA */ struct se_hba *se_hba; /* T10 Inquiry and VPD WWN Information */ -- cgit v1.2.3-59-g8ed1b From 531283ff7593f7059ced43c725d90cec3e5af549 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 23 Jun 2017 01:18:19 -0500 Subject: tcmu: drop configured check in destroy destroy_device is only called if we have successfully run configure_device, so drop the duplicate tcmu_dev_configured check. Signed-off-by: Mike Christie Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_user.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index e080cd1a8fde..d10aa0ac0918 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -1593,11 +1593,9 @@ static void tcmu_destroy_device(struct se_device *dev) tcmu_blocks_release(udev); - if (tcmu_dev_configured(udev)) { - tcmu_netlink_event(udev, TCMU_CMD_REMOVED_DEVICE, 0, NULL); + tcmu_netlink_event(udev, TCMU_CMD_REMOVED_DEVICE, 0, NULL); - uio_unregister_device(&udev->uio_info); - } + uio_unregister_device(&udev->uio_info); } enum { -- cgit v1.2.3-59-g8ed1b From 9260695d65590f4711d1166eadbfcb0acfa0625a Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 23 Jun 2017 01:18:20 -0500 Subject: tcmu: fix multiple uio open/close sequences If the uio device is open and closed multiple times, the kref count will be off due to tcmu_release getting called multiple times for each close. This patch integrates Wenji Tang's patch to add a kref_get on open that now matches the kref_put done on tcmu_release and adds a kref_put in tcmu_destroy_device to match the kref_get done in succesful tcmu_configure_device calls. Signed-off-by: Mike Christie Cc: Wenji Tang Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_user.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index d10aa0ac0918..1e69b1b32558 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -1269,6 +1269,7 @@ static int tcmu_open(struct uio_info *info, struct inode *inode) return -EBUSY; udev->inode = inode; + kref_get(&udev->kref); pr_debug("open\n"); @@ -1300,7 +1301,7 @@ static int tcmu_release(struct uio_info *info, struct inode *inode) clear_bit(TCMU_DEV_BIT_OPEN, &udev->flags); pr_debug("close\n"); - /* release ref from configure */ + /* release ref from open */ kref_put(&udev->kref, tcmu_dev_kref_release); return 0; } @@ -1596,6 +1597,9 @@ static void tcmu_destroy_device(struct se_device *dev) tcmu_netlink_event(udev, TCMU_CMD_REMOVED_DEVICE, 0, NULL); uio_unregister_device(&udev->uio_info); + + /* release ref from configure */ + kref_put(&udev->kref, tcmu_dev_kref_release); } enum { -- cgit v1.2.3-59-g8ed1b From 9d62bc0e6d79b11e3298e831358155930fb8f5e3 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Fri, 30 Jun 2017 16:14:16 +0800 Subject: tcmu: Fix flushing cmd entry dcache page When feeding the tcmu's cmd ring, we need to flush the dcache page for the cmd entry to make sure these kernel stores are visible to user space mappings of that page. For the none PAD cmd entry, this will be flushed at the end of the tcmu_queue_cmd_ring(). Signed-off-by: Xiubo Li Reviewed-by: Mike Christie Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_user.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 1e69b1b32558..a8ff6b5fdec8 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -825,21 +825,21 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd) size_t pad_size = head_to_end(cmd_head, udev->cmdr_size); entry = (void *) mb + CMDR_OFF + cmd_head; - tcmu_flush_dcache_range(entry, sizeof(*entry)); tcmu_hdr_set_op(&entry->hdr.len_op, TCMU_OP_PAD); tcmu_hdr_set_len(&entry->hdr.len_op, pad_size); entry->hdr.cmd_id = 0; /* not used for PAD */ entry->hdr.kflags = 0; entry->hdr.uflags = 0; + tcmu_flush_dcache_range(entry, sizeof(*entry)); UPDATE_HEAD(mb->cmd_head, pad_size, udev->cmdr_size); + tcmu_flush_dcache_range(mb, sizeof(*mb)); cmd_head = mb->cmd_head % udev->cmdr_size; /* UAM */ WARN_ON(cmd_head != 0); } entry = (void *) mb + CMDR_OFF + cmd_head; - tcmu_flush_dcache_range(entry, sizeof(*entry)); tcmu_hdr_set_op(&entry->hdr.len_op, TCMU_OP_CMD); entry->hdr.cmd_id = tcmu_cmd->cmd_id; entry->hdr.kflags = 0; -- cgit v1.2.3-59-g8ed1b From c82ff239ecf27dd5eddc91540f50321547a2d311 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 4 Jul 2017 09:44:19 +0100 Subject: target: make device_mutex and device_list static Variables device_mutex and device_list static are local to the source, so make them static. Cleans up sparse warnings: "symbol 'device_list' was not declared. Should it be static?" "symbol 'device_mutex' was not declared. Should it be static?" Signed-off-by: Colin Ian King Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_device.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 3ae8fbf01bdf..bbcef3bc66c8 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -49,8 +49,8 @@ #include "target_core_pr.h" #include "target_core_ua.h" -DEFINE_MUTEX(device_mutex); -LIST_HEAD(device_list); +static DEFINE_MUTEX(device_mutex); +static LIST_HEAD(device_list); static DEFINE_IDR(devices_idr); static struct se_hba *lun0_hba; -- cgit v1.2.3-59-g8ed1b From 9fe36984501035f2878aa10d83e79bfc07b7ad7e Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Wed, 31 May 2017 15:52:38 -0500 Subject: target: do not require a transport_complete for SCF_TRANSPORT_TASK_SENSE tcmu needs to pass raw sense to target_complete_cmd, but a a transport_complete callout is akward to implement for it. This moves the check for SCF_TRANSPORT_TASK_SENSE so any backend can pass sense. Signed-off-by: Mike Christie Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_transport.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 28de421e3220..a8f943e325eb 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -719,9 +719,9 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status) dev->transport->transport_complete(cmd, cmd->t_data_sg, transport_get_sense_buffer(cmd)); - if (cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) - success = 1; } + if (cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) + success = 1; /* * Check for case where an explicit ABORT_TASK has been received -- cgit v1.2.3-59-g8ed1b From c6d66aba98a39cfed206c5c61f0a604ba09b26ce Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Wed, 31 May 2017 15:52:39 -0500 Subject: target: add helper to copy sense to se_cmd buffer This adds a helper to copy sense from backend module buffer to the se_cmd's sense buffer. Signed-off-by: Mike Christie Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_transport.c | 18 ++++++++++++++++++ include/target/target_core_backend.h | 2 ++ 2 files changed, 20 insertions(+) diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index a8f943e325eb..341025a3cbb7 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -704,6 +704,24 @@ static unsigned char *transport_get_sense_buffer(struct se_cmd *cmd) return cmd->sense_buffer; } +void transport_copy_sense_to_cmd(struct se_cmd *cmd, unsigned char *sense) +{ + unsigned char *cmd_sense_buf; + unsigned long flags; + + spin_lock_irqsave(&cmd->t_state_lock, flags); + cmd_sense_buf = transport_get_sense_buffer(cmd); + if (!cmd_sense_buf) { + spin_unlock_irqrestore(&cmd->t_state_lock, flags); + return; + } + + cmd->se_cmd_flags |= SCF_TRANSPORT_TASK_SENSE; + memcpy(cmd_sense_buf, sense, cmd->scsi_sense_length); + spin_unlock_irqrestore(&cmd->t_state_lock, flags); +} +EXPORT_SYMBOL(transport_copy_sense_to_cmd); + void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status) { struct se_device *dev = cmd->se_dev; diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index 1f2b7007f2df..3757f5f54e03 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -73,6 +73,8 @@ void target_backend_unregister(const struct target_backend_ops *); void target_complete_cmd(struct se_cmd *, u8); void target_complete_cmd_with_length(struct se_cmd *, u8, int); +void transport_copy_sense_to_cmd(struct se_cmd *, unsigned char *); + sense_reason_t spc_parse_cdb(struct se_cmd *cmd, unsigned int *size); sense_reason_t spc_emulate_report_luns(struct se_cmd *cmd); sense_reason_t spc_emulate_inquiry_std(struct se_cmd *, unsigned char *); -- cgit v1.2.3-59-g8ed1b From 406f74c20dc258f8258b64d16d159c3fff06a506 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Wed, 31 May 2017 15:52:40 -0500 Subject: tcmu: fix sense handling during completion We were just copying the sense to the cmd sense_buffer and did not implement a transport_complete or set the SCF_TRANSPORT_TASK_SENSE, so the sense was ignored. Signed-off-by: Mike Christie Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_user.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index a8ff6b5fdec8..cbbfba0c1352 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -956,8 +956,7 @@ static void tcmu_handle_completion(struct tcmu_cmd *cmd, struct tcmu_cmd_entry * cmd->se_cmd); entry->rsp.scsi_status = SAM_STAT_CHECK_CONDITION; } else if (entry->rsp.scsi_status == SAM_STAT_CHECK_CONDITION) { - memcpy(se_cmd->sense_buffer, entry->rsp.sense_buffer, - se_cmd->scsi_sense_length); + transport_copy_sense_to_cmd(se_cmd, entry->rsp.sense_buffer); } else if (se_cmd->se_cmd_flags & SCF_BIDI) { /* Get Data-In buffer before clean up */ gather_data_area(udev, cmd, true); -- cgit v1.2.3-59-g8ed1b From dce6ce8cfb842c333094c3eb2e3ea66b1edb02ad Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Wed, 31 May 2017 15:52:41 -0500 Subject: pscsi: finish cmd processing from pscsi_req_done This patch performs the pscsi_transport_complete operations from pscsi_req_done. It looks like the only difference the transport_complete callout provides is that it is called under t_state_lock which seems to only be needed for the SCF_TRANSPORT_TASK_SENSE bit handling. We can now use transport_copy_sense_to_cmd to handle the se_cmd sense bits, and we can then drop the code where we have to copy the request info to the pscsi_plugin_task for transport_complete use. Signed-off-by: Mike Christie Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_pscsi.c | 38 ++++++++++++++++---------------------- drivers/target/target_core_pscsi.h | 4 ---- 2 files changed, 16 insertions(+), 26 deletions(-) diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 7d944b23aeee..fb40f64072f6 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -599,12 +599,11 @@ static void pscsi_destroy_device(struct se_device *dev) } } -static void pscsi_transport_complete(struct se_cmd *cmd, struct scatterlist *sg, - unsigned char *sense_buffer) +static void pscsi_complete_cmd(struct se_cmd *cmd, u8 scsi_status, + unsigned char *req_sense) { struct pscsi_dev_virt *pdv = PSCSI_DEV(cmd->se_dev); struct scsi_device *sd = pdv->pdv_sd; - int result; struct pscsi_plugin_task *pt = cmd->priv; unsigned char *cdb; /* @@ -615,7 +614,6 @@ static void pscsi_transport_complete(struct se_cmd *cmd, struct scatterlist *sg, return; cdb = &pt->pscsi_cdb[0]; - result = pt->pscsi_result; /* * Hack to make sure that Write-Protect modepage is set if R/O mode is * forced. @@ -624,7 +622,7 @@ static void pscsi_transport_complete(struct se_cmd *cmd, struct scatterlist *sg, goto after_mode_sense; if (((cdb[0] == MODE_SENSE) || (cdb[0] == MODE_SENSE_10)) && - (status_byte(result) << 1) == SAM_STAT_GOOD) { + scsi_status == SAM_STAT_GOOD) { bool read_only = target_lun_is_rdonly(cmd); if (read_only) { @@ -659,12 +657,12 @@ after_mode_sense: * storage engine. */ if (((cdb[0] == MODE_SELECT) || (cdb[0] == MODE_SELECT_10)) && - (status_byte(result) << 1) == SAM_STAT_GOOD) { + scsi_status == SAM_STAT_GOOD) { unsigned char *buf; u16 bdl; u32 blocksize; - buf = sg_virt(&sg[0]); + buf = sg_virt(&cmd->t_data_sg[0]); if (!buf) { pr_err("Unable to get buf for scatterlist\n"); goto after_mode_select; @@ -687,10 +685,8 @@ after_mode_sense: } after_mode_select: - if (sense_buffer && (status_byte(result) & CHECK_CONDITION)) { - memcpy(sense_buffer, pt->pscsi_sense, TRANSPORT_SENSE_BUFFER); - cmd->se_cmd_flags |= SCF_TRANSPORT_TASK_SENSE; - } + if (scsi_status == SAM_STAT_CHECK_CONDITION) + transport_copy_sense_to_cmd(cmd, req_sense); } enum { @@ -1049,30 +1045,29 @@ static void pscsi_req_done(struct request *req, int uptodate) { struct se_cmd *cmd = req->end_io_data; struct pscsi_plugin_task *pt = cmd->priv; + int result = scsi_req(req)->result; + u8 scsi_status = status_byte(result) << 1; - pt->pscsi_result = scsi_req(req)->result; - pt->pscsi_resid = scsi_req(req)->resid_len; - - cmd->scsi_status = status_byte(pt->pscsi_result) << 1; - if (cmd->scsi_status) { + if (scsi_status) { pr_debug("PSCSI Status Byte exception at cmd: %p CDB:" " 0x%02x Result: 0x%08x\n", cmd, pt->pscsi_cdb[0], - pt->pscsi_result); + result); } - switch (host_byte(pt->pscsi_result)) { + pscsi_complete_cmd(cmd, scsi_status, scsi_req(req)->sense); + + switch (host_byte(result)) { case DID_OK: - target_complete_cmd(cmd, cmd->scsi_status); + target_complete_cmd(cmd, scsi_status); break; default: pr_debug("PSCSI Host Byte exception at cmd: %p CDB:" " 0x%02x Result: 0x%08x\n", cmd, pt->pscsi_cdb[0], - pt->pscsi_result); + result); target_complete_cmd(cmd, SAM_STAT_CHECK_CONDITION); break; } - memcpy(pt->pscsi_sense, scsi_req(req)->sense, TRANSPORT_SENSE_BUFFER); __blk_put_request(req->q, req); kfree(pt); } @@ -1090,7 +1085,6 @@ static const struct target_backend_ops pscsi_ops = { .configure_device = pscsi_configure_device, .destroy_device = pscsi_destroy_device, .free_device = pscsi_free_device, - .transport_complete = pscsi_transport_complete, .parse_cdb = pscsi_parse_cdb, .set_configfs_dev_params = pscsi_set_configfs_dev_params, .show_configfs_dev_params = pscsi_show_configfs_dev_params, diff --git a/drivers/target/target_core_pscsi.h b/drivers/target/target_core_pscsi.h index 8a02fa47c7e8..b86fb0e1b783 100644 --- a/drivers/target/target_core_pscsi.h +++ b/drivers/target/target_core_pscsi.h @@ -23,10 +23,6 @@ struct scsi_device; struct Scsi_Host; struct pscsi_plugin_task { - unsigned char pscsi_sense[TRANSPORT_SENSE_BUFFER]; - int pscsi_direction; - int pscsi_result; - u32 pscsi_resid; unsigned char pscsi_cdb[0]; } ____cacheline_aligned; -- cgit v1.2.3-59-g8ed1b From 1a444175486026c1a280507f8d82094909acddd2 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Wed, 31 May 2017 15:52:42 -0500 Subject: target: remove transport_complete transport_complete is no longer used, so drop the code. Signed-off-by: Mike Christie Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_transport.c | 6 ------ include/target/target_core_backend.h | 4 ---- 2 files changed, 10 deletions(-) diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 341025a3cbb7..b9122a56784e 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -732,12 +732,6 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status) spin_lock_irqsave(&cmd->t_state_lock, flags); - - if (dev && dev->transport->transport_complete) { - dev->transport->transport_complete(cmd, - cmd->t_data_sg, - transport_get_sense_buffer(cmd)); - } if (cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) success = 1; diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index 3757f5f54e03..e150e391878b 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -37,10 +37,6 @@ struct target_backend_ops { const char *, ssize_t); ssize_t (*show_configfs_dev_params)(struct se_device *, char *); - void (*transport_complete)(struct se_cmd *cmd, - struct scatterlist *, - unsigned char *); - sense_reason_t (*parse_cdb)(struct se_cmd *cmd); u32 (*get_device_type)(struct se_device *); sector_t (*get_blocks)(struct se_device *); -- cgit v1.2.3-59-g8ed1b From 402242c904432207515e3ccb4126ff0dcfba89ca Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Wed, 31 May 2017 15:52:43 -0500 Subject: target: fix SAM_STAT_BUSY/TASK_SET_FULL handling If the scsi status was not SAM_STAT_GOOD or there was no transport sense, we would ignore the scsi status and do a generic not ready LUN communication failure check condition failure. The problem is that LUN COMM failure is treated as a hard error sometimes and will cause apps to get IO errors instead of the OS's SCSI layer retrying. For example, the tcmu daemon will return SAM_STAT_QUEUE_FULL when memory runs low and can still make progress but wants the initiator to reduce the work load. Windows will fail this error directly the app instead of retrying. This patch is based on Nick's "target/iblock: Use -EAGAIN/-ENOMEM to propigate SAM BUSY/TASK_SET_FULL" patch here: http://comments.gmane.org/gmane.linux.scsi.target.devel/11301 but instead of only setting SAM_STAT_GOOD, SAM_STAT_TASK_SET_FULL and SAM_STAT_BUSY as success, it sets all non check condition status as success so they are passed back to the initiator, so passthrough type backends can return all SCSI status codes. Since only passthrough uses this, I was not sure if we wanted to add checks for non-passthrough and specific codes. Signed-off-by: Mike Christie Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_transport.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index b9122a56784e..8735243edf04 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -725,15 +725,23 @@ EXPORT_SYMBOL(transport_copy_sense_to_cmd); void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status) { struct se_device *dev = cmd->se_dev; - int success = scsi_status == GOOD; + int success; unsigned long flags; cmd->scsi_status = scsi_status; - spin_lock_irqsave(&cmd->t_state_lock, flags); - if (cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) + switch (cmd->scsi_status) { + case SAM_STAT_CHECK_CONDITION: + if (cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) + success = 1; + else + success = 0; + break; + default: success = 1; + break; + } /* * Check for case where an explicit ABORT_TASK has been received -- cgit v1.2.3-59-g8ed1b From e5dc9a7055c98bcd7b03f9735d5f2ec2b7f0d897 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 28 Jun 2017 14:58:56 +0900 Subject: target: Use macro for WRITE_VERIFY_32 operation codes Add WRITE_VERIFY_32 definition to scsi prototypes and use this macro definition isntead of the hard coded value. (Drop WRITE_VERIFY_16 that's already part of another patch - nab) Signed-off-by: Damien Le Moal Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_device.c | 2 +- include/scsi/scsi_proto.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index bbcef3bc66c8..1c7c57a3c52e 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -1226,7 +1226,7 @@ passthrough_parse_cdb(struct se_cmd *cmd, switch (get_unaligned_be16(&cdb[8])) { case READ_32: case WRITE_32: - case 0x0c: /* WRITE_VERIFY_32 */ + case WRITE_VERIFY_32: case XDWRITEREAD_32: cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB; break; diff --git a/include/scsi/scsi_proto.h b/include/scsi/scsi_proto.h index ce78ec8e367d..5e3fe037938e 100644 --- a/include/scsi/scsi_proto.h +++ b/include/scsi/scsi_proto.h @@ -161,6 +161,7 @@ #define READ_32 0x09 #define VERIFY_32 0x0a #define WRITE_32 0x0b +#define WRITE_VERIFY_32 0x0c #define WRITE_SAME_32 0x0d /* Values for T10/04-262r7 */ -- cgit v1.2.3-59-g8ed1b From 016a5fec19e191ed1d45f75d8bfbefdec3f2dada Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 28 Jun 2017 14:58:57 +0900 Subject: target: pscsi: Introduce TYPE_ZBC support TYPE_ZBC host managed zoned block devices are also block devices despite the non-standard device type (14h). Handle them similarly to regular TYPE_DISK devices. Signed-off-by: Damien Le Moal Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_pscsi.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index fb40f64072f6..b71d22ebc9bf 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -382,7 +382,7 @@ static int pscsi_create_type_disk(struct se_device *dev, struct scsi_device *sd) spin_unlock_irq(sh->host_lock); /* * Claim exclusive struct block_device access to struct scsi_device - * for TYPE_DISK using supplied udev_path + * for TYPE_DISK and TYPE_ZBC using supplied udev_path */ bd = blkdev_get_by_path(dev->udev_path, FMODE_WRITE|FMODE_READ|FMODE_EXCL, pdv); @@ -400,8 +400,9 @@ static int pscsi_create_type_disk(struct se_device *dev, struct scsi_device *sd) return ret; } - pr_debug("CORE_PSCSI[%d] - Added TYPE_DISK for %d:%d:%d:%llu\n", - phv->phv_host_id, sh->host_no, sd->channel, sd->id, sd->lun); + pr_debug("CORE_PSCSI[%d] - Added TYPE_%s for %d:%d:%d:%llu\n", + phv->phv_host_id, sd->type == TYPE_DISK ? "DISK" : "ZBC", + sh->host_no, sd->channel, sd->id, sd->lun); return 0; } @@ -520,6 +521,7 @@ static int pscsi_configure_device(struct se_device *dev) */ switch (sd->type) { case TYPE_DISK: + case TYPE_ZBC: ret = pscsi_create_type_disk(dev, sd); break; default: @@ -576,9 +578,11 @@ static void pscsi_destroy_device(struct se_device *dev) if (sd) { /* * Release exclusive pSCSI internal struct block_device claim for - * struct scsi_device with TYPE_DISK from pscsi_create_type_disk() + * struct scsi_device with TYPE_DISK or TYPE_ZBC + * from pscsi_create_type_disk() */ - if ((sd->type == TYPE_DISK) && pdv->pdv_bd) { + if ((sd->type == TYPE_DISK || sd->type == TYPE_ZBC) && + pdv->pdv_bd) { blkdev_put(pdv->pdv_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL); pdv->pdv_bd = NULL; @@ -1000,7 +1004,8 @@ pscsi_execute_cmd(struct se_cmd *cmd) req->end_io_data = cmd; scsi_req(req)->cmd_len = scsi_command_size(pt->pscsi_cdb); scsi_req(req)->cmd = &pt->pscsi_cdb[0]; - if (pdv->pdv_sd->type == TYPE_DISK) + if (pdv->pdv_sd->type == TYPE_DISK || + pdv->pdv_sd->type == TYPE_ZBC) req->timeout = PS_TIMEOUT_DISK; else req->timeout = PS_TIMEOUT_OTHER; -- cgit v1.2.3-59-g8ed1b From 22e19c8d062cc19832cde13225cbc6e5283cd969 Mon Sep 17 00:00:00 2001 From: Thomas Meyer Date: Thu, 6 Jul 2017 00:31:14 +0200 Subject: um: userspace - be more verbose in ptrace set regs error When ptrace fails to set GP/FP regs for the target process, log the error before crashing the UML kernel. Signed-off-by: Thomas Meyer Signed-off-by: Richard Weinberger --- arch/um/os-Linux/skas/process.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c index 03b3c4cc7735..31c9be2c2bdd 100644 --- a/arch/um/os-Linux/skas/process.c +++ b/arch/um/os-Linux/skas/process.c @@ -323,11 +323,17 @@ void userspace(struct uml_pt_regs *regs) * fail. In this case, there is nothing to do but * just kill the process. */ - if (ptrace(PTRACE_SETREGS, pid, 0, regs->gp)) + if (ptrace(PTRACE_SETREGS, pid, 0, regs->gp)) { + printk(UM_KERN_ERR "userspace - ptrace set regs " + "failed, errno = %d\n", errno); fatal_sigsegv(); + } - if (put_fp_registers(pid, regs->fp)) + if (put_fp_registers(pid, regs->fp)) { + printk(UM_KERN_ERR "userspace - ptrace set fp regs " + "failed, errno = %d\n", errno); fatal_sigsegv(); + } /* Now we set local_using_sysemu to be used for one loop */ local_using_sysemu = get_using_sysemu(); -- cgit v1.2.3-59-g8ed1b From 171fa6928bcdf72372f98884b0abb93ad9b2e673 Mon Sep 17 00:00:00 2001 From: Thomas Meyer Date: Thu, 6 Jul 2017 00:32:33 +0200 Subject: um: stub-data.h: remove superfluous include Signed-off-by: Thomas Meyer Signed-off-by: Richard Weinberger --- arch/um/include/shared/skas/stub-data.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/um/include/shared/skas/stub-data.h b/arch/um/include/shared/skas/stub-data.h index a9deece956bf..13f404e1262b 100644 --- a/arch/um/include/shared/skas/stub-data.h +++ b/arch/um/include/shared/skas/stub-data.h @@ -8,8 +8,6 @@ #ifndef __STUB_DATA_H #define __STUB_DATA_H -#include - struct stub_data { unsigned long offset; int fd; -- cgit v1.2.3-59-g8ed1b From 88af23381ac3a04e35974d9ece422c2b6ebe7775 Mon Sep 17 00:00:00 2001 From: Thomas Meyer Date: Thu, 6 Jul 2017 00:34:04 +0200 Subject: um: Add kerneldoc for segv_handler Signed-off-by: Thomas Meyer Signed-off-by: Richard Weinberger --- arch/um/kernel/trap.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 59158871b9fc..4e6fcb32620f 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -183,6 +183,16 @@ void fatal_sigsegv(void) os_dump_core(); } +/** + * segv_handler() - the SIGSEGV handler + * @sig: the signal number + * @unused_si: the signal info struct; unused in this handler + * @regs: the ptrace register information + * + * The handler first extracts the faultinfo from the UML ptrace regs struct. + * If the userfault did not happen in an UML userspace process, bad_segv is called. + * Otherwise the signal did happen in a cloned userspace process, handle it. + */ void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs) { struct faultinfo * fi = UPT_FAULTINFO(regs); -- cgit v1.2.3-59-g8ed1b From e90998302682c41df4813da1ae019c8db79775f5 Mon Sep 17 00:00:00 2001 From: Thomas Meyer Date: Thu, 6 Jul 2017 00:34:05 +0200 Subject: um: Add kerneldoc for userspace_tramp() and start_userspace() Also use correct function name spelling (stub_segv_handler) for better grepping Signed-off-by: Thomas Meyer Signed-off-by: Richard Weinberger --- arch/um/os-Linux/skas/process.c | 31 ++++++++++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-) diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c index 31c9be2c2bdd..819d68656673 100644 --- a/arch/um/os-Linux/skas/process.c +++ b/arch/um/os-Linux/skas/process.c @@ -108,7 +108,7 @@ static void get_skas_faultinfo(int pid, struct faultinfo *fi) wait_stub_done(pid); /* - * faultinfo is prepared by the stub-segv-handler at start of + * faultinfo is prepared by the stub_segv_handler at start of * the stub stack page. We just have to copy it. */ memcpy(fi, (void *)current_stub_stack(), sizeof(*fi)); @@ -175,6 +175,21 @@ static void handle_trap(int pid, struct uml_pt_regs *regs, extern char __syscall_stub_start[]; +/** + * userspace_tramp() - userspace trampoline + * @stack: pointer to the new userspace stack page, can be NULL, if? FIXME: + * + * The userspace trampoline is used to setup a new userspace process in start_userspace() after it was clone()'ed. + * This function will run on a temporary stack page. + * It ptrace()'es itself, then + * Two pages are mapped into the userspace address space: + * - STUB_CODE (with EXEC), which contains the skas stub code + * - STUB_DATA (with R/W), which contains a data page that is used to transfer certain data between the UML userspace process and the UML kernel. + * Also for the userspace process a SIGSEGV handler is installed to catch pagefaults in the userspace process. + * And last the process stops itself to give control to the UML kernel for this userspace process. + * + * Return: Always zero, otherwise the current userspace process is ended with non null exit() call + */ static int userspace_tramp(void *stack) { void *addr; @@ -236,12 +251,24 @@ static int userspace_tramp(void *stack) int userspace_pid[NR_CPUS]; +/** + * start_userspace() - prepare a new userspace process + * @stub_stack: pointer to the stub stack. Can be NULL, if? FIXME: + * + * Setups a new temporary stack page that is used while userspace_tramp() runs + * Clones the kernel process into a new userspace process, with FDs only. + * + * Return: When positive: the process id of the new userspace process, + * when negative: an error number. + * FIXME: can PIDs become negative?! + */ int start_userspace(unsigned long stub_stack) { void *stack; unsigned long sp; int pid, status, n, flags, err; + /* setup a temporary stack page */ stack = mmap(NULL, UM_KERN_PAGE_SIZE, PROT_READ | PROT_WRITE | PROT_EXEC, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); @@ -252,10 +279,12 @@ int start_userspace(unsigned long stub_stack) return err; } + /* set stack pointer to the end of the stack page, so it can grow downwards */ sp = (unsigned long) stack + UM_KERN_PAGE_SIZE - sizeof(void *); flags = CLONE_FILES | SIGCHLD; + /* clone into new userspace process */ pid = clone(userspace_tramp, (void *) sp, flags, (void *) stub_stack); if (pid < 0) { err = -errno; -- cgit v1.2.3-59-g8ed1b From 0e4524a5d341e719e8ee9ee7db5d58e2c5a4c10e Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Thu, 6 Jul 2017 14:44:28 +0200 Subject: KVM: mark vcpu->pid pointer as rcu protected We do use rcu to protect the pid pointer. Mark it as such and adopt all code to use the proper access methods. This was detected by sparse. "virt/kvm/kvm_main.c:2248:15: error: incompatible types in comparison expression (different address spaces)" Signed-off-by: Christian Borntraeger Reviewed-by: Paolo Bonzini --- include/linux/kvm_host.h | 2 +- virt/kvm/kvm_main.c | 15 +++++++++++---- 2 files changed, 12 insertions(+), 5 deletions(-) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 0b50e7b35ed4..bcd37b855c66 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -234,7 +234,7 @@ struct kvm_vcpu { int guest_fpu_loaded, guest_xcr0_loaded; struct swait_queue_head wq; - struct pid *pid; + struct pid __rcu *pid; int sigset_active; sigset_t sigset; struct kvm_vcpu_stat stat; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 19f0ecb9b93e..fc2d58312fd5 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -293,7 +293,12 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_init); void kvm_vcpu_uninit(struct kvm_vcpu *vcpu) { - put_pid(vcpu->pid); + /* + * no need for rcu_read_lock as VCPU_RUN is the only place that + * will change the vcpu->pid pointer and on uninit all file + * descriptors are already gone. + */ + put_pid(rcu_dereference_protected(vcpu->pid, 1)); kvm_arch_vcpu_uninit(vcpu); free_page((unsigned long)vcpu->run); } @@ -2551,13 +2556,14 @@ static long kvm_vcpu_ioctl(struct file *filp, if (r) return r; switch (ioctl) { - case KVM_RUN: + case KVM_RUN: { + struct pid *oldpid; r = -EINVAL; if (arg) goto out; - if (unlikely(vcpu->pid != current->pids[PIDTYPE_PID].pid)) { + oldpid = rcu_access_pointer(vcpu->pid); + if (unlikely(oldpid != current->pids[PIDTYPE_PID].pid)) { /* The thread running this VCPU changed. */ - struct pid *oldpid = vcpu->pid; struct pid *newpid = get_task_pid(current, PIDTYPE_PID); rcu_assign_pointer(vcpu->pid, newpid); @@ -2568,6 +2574,7 @@ static long kvm_vcpu_ioctl(struct file *filp, r = kvm_arch_vcpu_ioctl_run(vcpu, vcpu->run); trace_kvm_userspace_exit(vcpu->run->exit_reason, r); break; + } case KVM_GET_REGS: { struct kvm_regs *kvm_regs; -- cgit v1.2.3-59-g8ed1b From d1bec20facd6eae17cb2f39ebbf443c95c650490 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Thu, 6 Jul 2017 11:41:58 +0200 Subject: rtc: class separate device allocation from registration Create rtc_allocate_device to allocate memory for a struct rtc_device and initialize it. Signed-off-by: Alexandre Belloni --- drivers/rtc/class.c | 63 +++++++++++++++++++++++++++++++---------------------- 1 file changed, 37 insertions(+), 26 deletions(-) diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index 543c64cd3df0..fb39c1334d7b 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -150,6 +150,41 @@ static SIMPLE_DEV_PM_OPS(rtc_class_dev_pm_ops, rtc_suspend, rtc_resume); #define RTC_CLASS_DEV_PM_OPS NULL #endif +static struct rtc_device *rtc_allocate_device(void) +{ + struct rtc_device *rtc; + + rtc = kzalloc(sizeof(*rtc), GFP_KERNEL); + if (!rtc) + return NULL; + + device_initialize(&rtc->dev); + + rtc->irq_freq = 1; + rtc->max_user_freq = 64; + rtc->dev.class = rtc_class; + rtc->dev.groups = rtc_get_dev_attribute_groups(); + rtc->dev.release = rtc_device_release; + + mutex_init(&rtc->ops_lock); + spin_lock_init(&rtc->irq_lock); + spin_lock_init(&rtc->irq_task_lock); + init_waitqueue_head(&rtc->irq_queue); + + /* Init timerqueue */ + timerqueue_init_head(&rtc->timerqueue); + INIT_WORK(&rtc->irqwork, rtc_timer_do_work); + /* Init aie timer */ + rtc_timer_init(&rtc->aie_timer, rtc_aie_update_irq, (void *)rtc); + /* Init uie timer */ + rtc_timer_init(&rtc->uie_rtctimer, rtc_uie_update_irq, (void *)rtc); + /* Init pie timer */ + hrtimer_init(&rtc->pie_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + rtc->pie_timer.function = rtc_pie_update_irq; + rtc->pie_enabled = 0; + + return rtc; +} /** * rtc_device_register - register w/ RTC class @@ -189,40 +224,16 @@ struct rtc_device *rtc_device_register(const char *name, struct device *dev, } } - rtc = kzalloc(sizeof(struct rtc_device), GFP_KERNEL); - if (rtc == NULL) { + rtc = rtc_allocate_device(); + if (!rtc) { err = -ENOMEM; goto exit_ida; } - device_initialize(&rtc->dev); - rtc->id = id; rtc->ops = ops; rtc->owner = owner; - rtc->irq_freq = 1; - rtc->max_user_freq = 64; rtc->dev.parent = dev; - rtc->dev.class = rtc_class; - rtc->dev.groups = rtc_get_dev_attribute_groups(); - rtc->dev.release = rtc_device_release; - - mutex_init(&rtc->ops_lock); - spin_lock_init(&rtc->irq_lock); - spin_lock_init(&rtc->irq_task_lock); - init_waitqueue_head(&rtc->irq_queue); - - /* Init timerqueue */ - timerqueue_init_head(&rtc->timerqueue); - INIT_WORK(&rtc->irqwork, rtc_timer_do_work); - /* Init aie timer */ - rtc_timer_init(&rtc->aie_timer, rtc_aie_update_irq, (void *)rtc); - /* Init uie timer */ - rtc_timer_init(&rtc->uie_rtctimer, rtc_uie_update_irq, (void *)rtc); - /* Init pie timer */ - hrtimer_init(&rtc->pie_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - rtc->pie_timer.function = rtc_pie_update_irq; - rtc->pie_enabled = 0; dev_set_name(&rtc->dev, "rtc%d", id); -- cgit v1.2.3-59-g8ed1b From b91336df8ac2f5d15a2132074ba596580526db1d Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Thu, 6 Jul 2017 11:41:59 +0200 Subject: rtc: class separate id allocation from registration Create rtc_device_get_id to allocate the id for an RTC. Signed-off-by: Alexandre Belloni --- drivers/rtc/class.c | 44 +++++++++++++++++++++++++------------------- 1 file changed, 25 insertions(+), 19 deletions(-) diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index fb39c1334d7b..93ce88e1b1cb 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -186,6 +186,27 @@ static struct rtc_device *rtc_allocate_device(void) return rtc; } +static int rtc_device_get_id(struct device *dev) +{ + int of_id = -1, id = -1; + + if (dev->of_node) + of_id = of_alias_get_id(dev->of_node, "rtc"); + else if (dev->parent && dev->parent->of_node) + of_id = of_alias_get_id(dev->parent->of_node, "rtc"); + + if (of_id >= 0) { + id = ida_simple_get(&rtc_ida, of_id, of_id + 1, GFP_KERNEL); + if (id < 0) + dev_warn(dev, "/aliases ID %d not available\n", of_id); + } + + if (id < 0) + id = ida_simple_get(&rtc_ida, 0, 0, GFP_KERNEL); + + return id; +} + /** * rtc_device_register - register w/ RTC class * @dev: the device to register @@ -201,27 +222,12 @@ struct rtc_device *rtc_device_register(const char *name, struct device *dev, { struct rtc_device *rtc; struct rtc_wkalrm alrm; - int of_id = -1, id = -1, err; - - if (dev->of_node) - of_id = of_alias_get_id(dev->of_node, "rtc"); - else if (dev->parent && dev->parent->of_node) - of_id = of_alias_get_id(dev->parent->of_node, "rtc"); - - if (of_id >= 0) { - id = ida_simple_get(&rtc_ida, of_id, of_id + 1, - GFP_KERNEL); - if (id < 0) - dev_warn(dev, "/aliases ID %d not available\n", - of_id); - } + int id, err; + id = rtc_device_get_id(dev); if (id < 0) { - id = ida_simple_get(&rtc_ida, 0, 0, GFP_KERNEL); - if (id < 0) { - err = id; - goto exit; - } + err = id; + goto exit; } rtc = rtc_allocate_device(); -- cgit v1.2.3-59-g8ed1b From 3068a254d5519cd5116f61297462da6d1aa84c20 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Thu, 6 Jul 2017 11:42:00 +0200 Subject: rtc: introduce new registration method Introduce rtc_register_device() to register an already allocated and initialized struct rtc_device. It automatically sets up the owner and the two steps allocation/registration will allow to remove race conditions in the IRQ handling of some driver. It also allows to properly extend the core without adding more arguments to rtc_device_register(). Signed-off-by: Alexandre Belloni --- drivers/rtc/class.c | 84 +++++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/rtc.h | 7 +++++ 2 files changed, 91 insertions(+) diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index 93ce88e1b1cb..58e2a05765bb 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -150,6 +150,7 @@ static SIMPLE_DEV_PM_OPS(rtc_class_dev_pm_ops, rtc_suspend, rtc_resume); #define RTC_CLASS_DEV_PM_OPS NULL #endif +/* Ensure the caller will set the id before releasing the device */ static struct rtc_device *rtc_allocate_device(void) { struct rtc_device *rtc; @@ -372,6 +373,89 @@ void devm_rtc_device_unregister(struct device *dev, struct rtc_device *rtc) } EXPORT_SYMBOL_GPL(devm_rtc_device_unregister); +static void devm_rtc_release_device(struct device *dev, void *res) +{ + struct rtc_device *rtc = *(struct rtc_device **)res; + + if (rtc->registered) + rtc_device_unregister(rtc); + else + put_device(&rtc->dev); +} + +struct rtc_device *devm_rtc_allocate_device(struct device *dev) +{ + struct rtc_device **ptr, *rtc; + int id, err; + + id = rtc_device_get_id(dev); + if (id < 0) + return ERR_PTR(id); + + ptr = devres_alloc(devm_rtc_release_device, sizeof(*ptr), GFP_KERNEL); + if (!ptr) { + err = -ENOMEM; + goto exit_ida; + } + + rtc = rtc_allocate_device(); + if (!rtc) { + err = -ENOMEM; + goto exit_devres; + } + + *ptr = rtc; + devres_add(dev, ptr); + + rtc->id = id; + rtc->dev.parent = dev; + dev_set_name(&rtc->dev, "rtc%d", id); + + return rtc; + +exit_devres: + devres_free(ptr); +exit_ida: + ida_simple_remove(&rtc_ida, id); + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(devm_rtc_allocate_device); + +int __rtc_register_device(struct module *owner, struct rtc_device *rtc) +{ + struct rtc_wkalrm alrm; + int err; + + if (!rtc->ops) + return -EINVAL; + + rtc->owner = owner; + + /* Check to see if there is an ALARM already set in hw */ + err = __rtc_read_alarm(rtc, &alrm); + if (!err && !rtc_valid_tm(&alrm.time)) + rtc_initialize_alarm(rtc, &alrm); + + rtc_dev_prepare(rtc); + + err = cdev_device_add(&rtc->char_dev, &rtc->dev); + if (err) + dev_warn(rtc->dev.parent, "failed to add char device %d:%d\n", + MAJOR(rtc->dev.devt), rtc->id); + else + dev_dbg(rtc->dev.parent, "char device (%d:%d)\n", + MAJOR(rtc->dev.devt), rtc->id); + + rtc_proc_add_device(rtc); + + rtc->registered = true; + dev_info(rtc->dev.parent, "registered as %s\n", + dev_name(&rtc->dev)); + + return 0; +} +EXPORT_SYMBOL_GPL(__rtc_register_device); + static int __init rtc_init(void) { rtc_class = class_create(THIS_MODULE, "rtc"); diff --git a/include/linux/rtc.h b/include/linux/rtc.h index d354f56e0cf5..8e4a5f44f59e 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -142,6 +142,8 @@ struct rtc_device { /* Some hardware can't support UIE mode */ int uie_unsupported; + bool registered; + #ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL struct work_struct uie_task; struct timer_list uie_timer; @@ -163,6 +165,8 @@ extern struct rtc_device *devm_rtc_device_register(struct device *dev, const char *name, const struct rtc_class_ops *ops, struct module *owner); +struct rtc_device *devm_rtc_allocate_device(struct device *dev); +int __rtc_register_device(struct module *owner, struct rtc_device *rtc); extern void rtc_device_unregister(struct rtc_device *rtc); extern void devm_rtc_device_unregister(struct device *dev, struct rtc_device *rtc); @@ -218,6 +222,9 @@ static inline bool is_leap_year(unsigned int year) return (!(year % 4) && (year % 100)) || !(year % 400); } +#define rtc_register_device(device) \ + __rtc_register_device(THIS_MODULE, device) + #ifdef CONFIG_RTC_HCTOSYS_DEVICE extern int rtc_hctosys_ret; #else -- cgit v1.2.3-59-g8ed1b From 735ae2056b3c7296bb188d079c020f606a679c4a Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Thu, 6 Jul 2017 11:42:01 +0200 Subject: rtc: at91rm9200: remove race condition While highly unlikely, it is possible to get an interrupt as soon as it is requested. In that case, at91_rtc_interrupt() will be called with rtc == NULL. Solve that by using devm_rtc_allocate_device/rtc_register_device. Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-at91rm9200.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/rtc/rtc-at91rm9200.c b/drivers/rtc/rtc-at91rm9200.c index b60fd477778f..e221b78b6f10 100644 --- a/drivers/rtc/rtc-at91rm9200.c +++ b/drivers/rtc/rtc-at91rm9200.c @@ -409,6 +409,11 @@ static int __init at91_rtc_probe(struct platform_device *pdev) return -ENOMEM; } + rtc = devm_rtc_allocate_device(&pdev->dev); + if (IS_ERR(rtc)) + return PTR_ERR(rtc); + platform_set_drvdata(pdev, rtc); + sclk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(sclk)) return PTR_ERR(sclk); @@ -441,13 +446,10 @@ static int __init at91_rtc_probe(struct platform_device *pdev) if (!device_can_wakeup(&pdev->dev)) device_init_wakeup(&pdev->dev, 1); - rtc = devm_rtc_device_register(&pdev->dev, pdev->name, - &at91_rtc_ops, THIS_MODULE); - if (IS_ERR(rtc)) { - ret = PTR_ERR(rtc); + rtc->ops = &at91_rtc_ops; + ret = rtc_register_device(rtc); + if (ret) goto err_clk; - } - platform_set_drvdata(pdev, rtc); /* enable SECEV interrupt in order to initialize at91_rtc_upd_rdy * completion. -- cgit v1.2.3-59-g8ed1b From 697e5a47aa12cdab6f2a8b284cc923cdf704eafc Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Thu, 6 Jul 2017 11:42:02 +0200 Subject: rtc: add generic nvmem support Many RTCs have an on board non volatile storage. It can be battery backed RAM or an EEPROM. Use the nvmem subsystem to export it to both userspace and in-kernel consumers. This stays compatible with the previous (non documented) ABI that was using /sys/class/rtc/rtcx/device/nvram to export that memory. But will warn about the deprecation. Signed-off-by: Alexandre Belloni --- Documentation/rtc.txt | 2 + drivers/rtc/Kconfig | 8 ++++ drivers/rtc/Makefile | 1 + drivers/rtc/class.c | 4 ++ drivers/rtc/nvmem.c | 113 +++++++++++++++++++++++++++++++++++++++++++++++++ drivers/rtc/rtc-core.h | 8 ++++ include/linux/rtc.h | 7 +++ 7 files changed, 143 insertions(+) create mode 100644 drivers/rtc/nvmem.c diff --git a/Documentation/rtc.txt b/Documentation/rtc.txt index 47feb4414b7e..c0c977445fb9 100644 --- a/Documentation/rtc.txt +++ b/Documentation/rtc.txt @@ -164,6 +164,8 @@ offset The amount which the rtc clock has been adjusted in firmware. which are added to or removed from the rtc's base clock per billion ticks. A positive value makes a day pass more slowly, longer, and a negative value makes a day pass more quickly. +*/nvmem The non volatile storage exported as a raw file, as described + in Documentation/nvmem/nvmem.txt ================ ============================================================== IOCTL interface diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index d0e4b4a1c2a1..72419ac2c52a 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -77,6 +77,14 @@ config RTC_DEBUG Say yes here to enable debugging support in the RTC framework and individual RTC drivers. +config RTC_NVMEM + bool "RTC non volatile storage support" + select NVMEM + default RTC_CLASS + help + Say yes here to add support for the non volatile (often battery + backed) storage present on RTCs. + comment "RTC interfaces" config RTC_INTF_SYSFS diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile index 4050fc8b9271..acd366b41c85 100644 --- a/drivers/rtc/Makefile +++ b/drivers/rtc/Makefile @@ -15,6 +15,7 @@ ifdef CONFIG_RTC_DRV_EFI rtc-core-y += rtc-efi-platform.o endif +rtc-core-$(CONFIG_RTC_NVMEM) += nvmem.o rtc-core-$(CONFIG_RTC_INTF_DEV) += rtc-dev.o rtc-core-$(CONFIG_RTC_INTF_PROC) += rtc-proc.o rtc-core-$(CONFIG_RTC_INTF_SYSFS) += rtc-sysfs.o diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index 58e2a05765bb..2ed970d61da1 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -290,6 +290,8 @@ EXPORT_SYMBOL_GPL(rtc_device_register); */ void rtc_device_unregister(struct rtc_device *rtc) { + rtc_nvmem_unregister(rtc); + mutex_lock(&rtc->ops_lock); /* * Remove innards of this RTC, then disable it, before @@ -448,6 +450,8 @@ int __rtc_register_device(struct module *owner, struct rtc_device *rtc) rtc_proc_add_device(rtc); + rtc_nvmem_register(rtc); + rtc->registered = true; dev_info(rtc->dev.parent, "registered as %s\n", dev_name(&rtc->dev)); diff --git a/drivers/rtc/nvmem.c b/drivers/rtc/nvmem.c new file mode 100644 index 000000000000..8567b4ed9ac6 --- /dev/null +++ b/drivers/rtc/nvmem.c @@ -0,0 +1,113 @@ +/* + * RTC subsystem, nvmem interface + * + * Copyright (C) 2017 Alexandre Belloni + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include + +#include "rtc-core.h" + +/* + * Deprecated ABI compatibility, this should be removed at some point + */ + +static const char nvram_warning[] = "Deprecated ABI, please use nvmem"; + +static ssize_t +rtc_nvram_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, + char *buf, loff_t off, size_t count) +{ + struct rtc_device *rtc = attr->private; + + dev_warn_once(kobj_to_dev(kobj), nvram_warning); + + return nvmem_device_read(rtc->nvmem, off, count, buf); +} + +static ssize_t +rtc_nvram_write(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, + char *buf, loff_t off, size_t count) +{ + struct rtc_device *rtc = attr->private; + + dev_warn_once(kobj_to_dev(kobj), nvram_warning); + + return nvmem_device_write(rtc->nvmem, off, count, buf); +} + +static int rtc_nvram_register(struct rtc_device *rtc) +{ + int err; + + rtc->nvram = devm_kzalloc(rtc->dev.parent, + sizeof(struct bin_attribute), + GFP_KERNEL); + if (!rtc->nvram) + return -ENOMEM; + + rtc->nvram->attr.name = "nvram"; + rtc->nvram->attr.mode = 0644; + rtc->nvram->private = rtc; + + sysfs_bin_attr_init(rtc->nvram); + + rtc->nvram->read = rtc_nvram_read; + rtc->nvram->write = rtc_nvram_write; + rtc->nvram->size = rtc->nvmem_config->size; + + err = sysfs_create_bin_file(&rtc->dev.parent->kobj, + rtc->nvram); + if (err) { + devm_kfree(rtc->dev.parent, rtc->nvram); + rtc->nvram = NULL; + } + + return err; +} + +static void rtc_nvram_unregister(struct rtc_device *rtc) +{ + sysfs_remove_bin_file(&rtc->dev.parent->kobj, rtc->nvram); +} + +/* + * New ABI, uses nvmem + */ +void rtc_nvmem_register(struct rtc_device *rtc) +{ + if (!rtc->nvmem_config) + return; + + rtc->nvmem_config->dev = &rtc->dev; + rtc->nvmem_config->owner = rtc->owner; + rtc->nvmem = nvmem_register(rtc->nvmem_config); + if (IS_ERR_OR_NULL(rtc->nvmem)) + return; + + /* Register the old ABI */ + if (rtc->nvram_old_abi) + rtc_nvram_register(rtc); +} + +void rtc_nvmem_unregister(struct rtc_device *rtc) +{ + if (IS_ERR_OR_NULL(rtc->nvmem)) + return; + + /* unregister the old ABI */ + if (rtc->nvram) + rtc_nvram_unregister(rtc); + + nvmem_unregister(rtc->nvmem); +} diff --git a/drivers/rtc/rtc-core.h b/drivers/rtc/rtc-core.h index 7a4ed2f7c7d7..ecab76a3207c 100644 --- a/drivers/rtc/rtc-core.h +++ b/drivers/rtc/rtc-core.h @@ -45,3 +45,11 @@ static inline const struct attribute_group **rtc_get_dev_attribute_groups(void) return NULL; } #endif + +#ifdef CONFIG_RTC_NVMEM +void rtc_nvmem_register(struct rtc_device *rtc); +void rtc_nvmem_unregister(struct rtc_device *rtc); +#else +static inline void rtc_nvmem_register(struct rtc_device *rtc) {} +static inline void rtc_nvmem_unregister(struct rtc_device *rtc) {} +#endif diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 8e4a5f44f59e..d53ecdc060cf 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -14,6 +14,7 @@ #include #include +#include #include extern int rtc_month_days(unsigned int month, unsigned int year); @@ -144,6 +145,12 @@ struct rtc_device { bool registered; + struct nvmem_config *nvmem_config; + struct nvmem_device *nvmem; + /* Old ABI support */ + bool nvram_old_abi; + struct bin_attribute *nvram; + #ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL struct work_struct uie_task; struct timer_list uie_timer; -- cgit v1.2.3-59-g8ed1b From 7133eca19505defed19b1337f46b2cd5f7608814 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Thu, 6 Jul 2017 11:42:03 +0200 Subject: rtc: rv8803: switch to rtc_register_device This removes a possible race condition and allows for further improvement of the driver. Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-rv8803.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/rtc/rtc-rv8803.c b/drivers/rtc/rtc-rv8803.c index 9ad97ab29866..209edbb03971 100644 --- a/drivers/rtc/rtc-rv8803.c +++ b/drivers/rtc/rtc-rv8803.c @@ -577,6 +577,11 @@ static int rv8803_probe(struct i2c_client *client, if (flags & RV8803_FLAG_AF) dev_warn(&client->dev, "An alarm maybe have been missed.\n"); + rv8803->rtc = devm_rtc_allocate_device(&client->dev); + if (IS_ERR(rv8803->rtc)) { + return PTR_ERR(rv8803->rtc); + } + if (client->irq > 0) { err = devm_request_threaded_irq(&client->dev, client->irq, NULL, rv8803_handle_irq, @@ -592,12 +597,10 @@ static int rv8803_probe(struct i2c_client *client, } } - rv8803->rtc = devm_rtc_device_register(&client->dev, client->name, - &rv8803_rtc_ops, THIS_MODULE); - if (IS_ERR(rv8803->rtc)) { - dev_err(&client->dev, "unable to register the class device\n"); - return PTR_ERR(rv8803->rtc); - } + rv8803->rtc->ops = &rv8803_rtc_ops; + err = rtc_register_device(rv8803->rtc); + if (err) + return err; err = rv8803_write_reg(rv8803->client, RV8803_EXT, RV8803_EXT_WADA); if (err) -- cgit v1.2.3-59-g8ed1b From 16d70a78b45a65c88a3c614ebadbf2589f6f8efe Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Thu, 6 Jul 2017 11:42:04 +0200 Subject: rtc: rv8803: use generic nvmem support Instead of adding a binary sysfs attribute from the driver (which suffers from a race condition as the attribute appears after the device), use the core to register an nvmem device. Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-rv8803.c | 51 +++++++++++++++++++----------------------------- 1 file changed, 20 insertions(+), 31 deletions(-) diff --git a/drivers/rtc/rtc-rv8803.c b/drivers/rtc/rtc-rv8803.c index 209edbb03971..10474ab7887d 100644 --- a/drivers/rtc/rtc-rv8803.c +++ b/drivers/rtc/rtc-rv8803.c @@ -68,6 +68,7 @@ struct rv8803_data { struct mutex flags_lock; u8 ctrl; enum rv8803_type type; + struct nvmem_config nvmem_cfg; }; static int rv8803_read_reg(const struct i2c_client *client, u8 reg) @@ -460,48 +461,32 @@ static int rv8803_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) } } -static ssize_t rv8803_nvram_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, - char *buf, loff_t off, size_t count) +static int rv8803_nvram_write(void *priv, unsigned int offset, void *val, + size_t bytes) { - struct device *dev = kobj_to_dev(kobj); - struct i2c_client *client = to_i2c_client(dev); int ret; - ret = rv8803_write_reg(client, RV8803_RAM, buf[0]); + ret = rv8803_write_reg(priv, RV8803_RAM, *(u8 *)val); if (ret) return ret; - return 1; + return 0; } -static ssize_t rv8803_nvram_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, - char *buf, loff_t off, size_t count) +static int rv8803_nvram_read(void *priv, unsigned int offset, + void *val, size_t bytes) { - struct device *dev = kobj_to_dev(kobj); - struct i2c_client *client = to_i2c_client(dev); int ret; - ret = rv8803_read_reg(client, RV8803_RAM); + ret = rv8803_read_reg(priv, RV8803_RAM); if (ret < 0) return ret; - buf[0] = ret; + *(u8 *)val = ret; - return 1; + return 0; } -static struct bin_attribute rv8803_nvram_attr = { - .attr = { - .name = "nvram", - .mode = S_IRUGO | S_IWUSR, - }, - .size = 1, - .read = rv8803_nvram_read, - .write = rv8803_nvram_write, -}; - static struct rtc_class_ops rv8803_rtc_ops = { .read_time = rv8803_get_time, .set_time = rv8803_set_time, @@ -597,7 +582,17 @@ static int rv8803_probe(struct i2c_client *client, } } + rv8803->nvmem_cfg.name = "rv8803_nvram", + rv8803->nvmem_cfg.word_size = 1, + rv8803->nvmem_cfg.stride = 1, + rv8803->nvmem_cfg.size = 1, + rv8803->nvmem_cfg.reg_read = rv8803_nvram_read, + rv8803->nvmem_cfg.reg_write = rv8803_nvram_write, + rv8803->nvmem_cfg.priv = client; + rv8803->rtc->ops = &rv8803_rtc_ops; + rv8803->rtc->nvmem_config = &rv8803->nvmem_cfg; + rv8803->rtc->nvram_old_abi = true; err = rtc_register_device(rv8803->rtc); if (err) return err; @@ -612,10 +607,6 @@ static int rv8803_probe(struct i2c_client *client, return err; } - err = device_create_bin_file(&client->dev, &rv8803_nvram_attr); - if (err) - return err; - rv8803->rtc->max_user_freq = 1; return 0; @@ -623,8 +614,6 @@ static int rv8803_probe(struct i2c_client *client, static int rv8803_remove(struct i2c_client *client) { - device_remove_bin_file(&client->dev, &rv8803_nvram_attr); - return 0; } -- cgit v1.2.3-59-g8ed1b From 2a52482ffb1a65249049eaec9e3560a1e79abf3d Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Thu, 6 Jul 2017 11:42:05 +0200 Subject: rtc: rv8803: remove rv8803_remove rv8803_remove() is now empty, remove it. Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-rv8803.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/rtc/rtc-rv8803.c b/drivers/rtc/rtc-rv8803.c index 10474ab7887d..aae2576741a6 100644 --- a/drivers/rtc/rtc-rv8803.c +++ b/drivers/rtc/rtc-rv8803.c @@ -612,11 +612,6 @@ static int rv8803_probe(struct i2c_client *client, return 0; } -static int rv8803_remove(struct i2c_client *client) -{ - return 0; -} - static const struct i2c_device_id rv8803_id[] = { { "rv8803", rv_8803 }, { "rx8900", rx_8900 }, @@ -643,7 +638,6 @@ static struct i2c_driver rv8803_driver = { .of_match_table = of_match_ptr(rv8803_of_match), }, .probe = rv8803_probe, - .remove = rv8803_remove, .id_table = rv8803_id, }; module_i2c_driver(rv8803_driver); -- cgit v1.2.3-59-g8ed1b From 69b119a642b7e143be08f9cbabca7bc910f5720d Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Thu, 6 Jul 2017 11:42:06 +0200 Subject: rtc: ds1307: switch to rtc_register_device This removes a possible race condition and crash and allows for further improvement of the driver. Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ds1307.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index 57ea25400ecd..6f94f20326fb 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -1674,8 +1674,8 @@ read_rtc: device_set_wakeup_capable(ds1307->dev, true); set_bit(HAS_ALARM, &ds1307->flags); } - ds1307->rtc = devm_rtc_device_register(ds1307->dev, ds1307->name, - rtc_ops, THIS_MODULE); + + ds1307->rtc = devm_rtc_allocate_device(ds1307->dev); if (IS_ERR(ds1307->rtc)) { return PTR_ERR(ds1307->rtc); } @@ -1737,6 +1737,11 @@ read_rtc: } } + ds1307->rtc->ops = rtc_ops; + err = rtc_register_device(ds1307->rtc); + if (err) + return err; + ds1307_hwmon_register(ds1307); ds1307_clks_register(ds1307); -- cgit v1.2.3-59-g8ed1b From abc925f72c666042bf49fbf590bed01e5dbc2c97 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Thu, 6 Jul 2017 11:42:07 +0200 Subject: rtc: ds1307: use generic nvmem Instead of adding a binary sysfs attribute from the driver (which suffers from a race condition as the attribute appears after the device), use the core to register an nvmem device. Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ds1307.c | 88 ++++++++++++------------------------------------ 1 file changed, 22 insertions(+), 66 deletions(-) diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index 6f94f20326fb..76652566cc31 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -118,7 +118,7 @@ struct ds1307 { u8 offset; /* register's offset */ u8 regs[11]; u16 nvram_offset; - struct bin_attribute *nvram; + struct nvmem_config nvmem_cfg; enum ds_type type; unsigned long flags; #define HAS_NVRAM 0 /* bit 0 == sysfs file active */ @@ -895,43 +895,24 @@ static const struct rtc_class_ops mcp794xx_rtc_ops = { /*----------------------------------------------------------------------*/ -static ssize_t -ds1307_nvram_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, - char *buf, loff_t off, size_t count) +static int ds1307_nvram_read(void *priv, unsigned int offset, void *val, + size_t bytes) { - struct ds1307 *ds1307; - int result; - - ds1307 = dev_get_drvdata(kobj_to_dev(kobj)); + struct ds1307 *ds1307 = priv; - result = regmap_bulk_read(ds1307->regmap, ds1307->nvram_offset + off, - buf, count); - if (result) - dev_err(ds1307->dev, "%s error %d\n", "nvram read", result); - return result; + return regmap_bulk_read(ds1307->regmap, ds1307->nvram_offset + offset, + val, bytes); } -static ssize_t -ds1307_nvram_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, - char *buf, loff_t off, size_t count) +static int ds1307_nvram_write(void *priv, unsigned int offset, void *val, + size_t bytes) { - struct ds1307 *ds1307; - int result; + struct ds1307 *ds1307 = priv; - ds1307 = dev_get_drvdata(kobj_to_dev(kobj)); - - result = regmap_bulk_write(ds1307->regmap, ds1307->nvram_offset + off, - buf, count); - if (result) { - dev_err(ds1307->dev, "%s error %d\n", "nvram write", result); - return result; - } - return count; + return regmap_bulk_write(ds1307->regmap, ds1307->nvram_offset + offset, + val, bytes); } - /*----------------------------------------------------------------------*/ static u8 do_trickle_setup_ds1339(struct ds1307 *ds1307, @@ -1704,37 +1685,17 @@ read_rtc: } if (chip->nvram_size) { - - ds1307->nvram = devm_kzalloc(ds1307->dev, - sizeof(struct bin_attribute), - GFP_KERNEL); - if (!ds1307->nvram) { - dev_err(ds1307->dev, - "cannot allocate memory for nvram sysfs\n"); - } else { - - ds1307->nvram->attr.name = "nvram"; - ds1307->nvram->attr.mode = S_IRUGO | S_IWUSR; - - sysfs_bin_attr_init(ds1307->nvram); - - ds1307->nvram->read = ds1307_nvram_read; - ds1307->nvram->write = ds1307_nvram_write; - ds1307->nvram->size = chip->nvram_size; - ds1307->nvram_offset = chip->nvram_offset; - - err = sysfs_create_bin_file(&ds1307->dev->kobj, - ds1307->nvram); - if (err) { - dev_err(ds1307->dev, - "unable to create sysfs file: %s\n", - ds1307->nvram->attr.name); - } else { - set_bit(HAS_NVRAM, &ds1307->flags); - dev_info(ds1307->dev, "%zu bytes nvram\n", - ds1307->nvram->size); - } - } + ds1307->nvmem_cfg.name = "ds1307_nvram"; + ds1307->nvmem_cfg.word_size = 1; + ds1307->nvmem_cfg.stride = 1; + ds1307->nvmem_cfg.size = chip->nvram_size; + ds1307->nvmem_cfg.reg_read = ds1307_nvram_read; + ds1307->nvmem_cfg.reg_write = ds1307_nvram_write; + ds1307->nvmem_cfg.priv = ds1307; + ds1307->nvram_offset = chip->nvram_offset; + + ds1307->rtc->nvmem_config = &ds1307->nvmem_cfg; + ds1307->rtc->nvram_old_abi = true; } ds1307->rtc->ops = rtc_ops; @@ -1753,11 +1714,6 @@ exit: static int ds1307_remove(struct i2c_client *client) { - struct ds1307 *ds1307 = i2c_get_clientdata(client); - - if (test_and_clear_bit(HAS_NVRAM, &ds1307->flags)) - sysfs_remove_bin_file(&ds1307->dev->kobj, ds1307->nvram); - return 0; } -- cgit v1.2.3-59-g8ed1b From bed8e280476fc8652f4105fe430e10fcf4032392 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Thu, 6 Jul 2017 11:42:08 +0200 Subject: rtc: ds1307: remove ds1307_remove ds1307_remove() is now empty, remove it Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ds1307.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index 76652566cc31..4fac49e55d47 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -1712,11 +1712,6 @@ exit: return err; } -static int ds1307_remove(struct i2c_client *client) -{ - return 0; -} - static struct i2c_driver ds1307_driver = { .driver = { .name = "rtc-ds1307", @@ -1724,7 +1719,6 @@ static struct i2c_driver ds1307_driver = { .acpi_match_table = ACPI_PTR(ds1307_acpi_ids), }, .probe = ds1307_probe, - .remove = ds1307_remove, .id_table = ds1307_id, }; -- cgit v1.2.3-59-g8ed1b From eaf260ac04d9b4cf9f458d5c97555bfff2da526e Mon Sep 17 00:00:00 2001 From: Joel Fernandes Date: Thu, 6 Jul 2017 16:00:21 -0700 Subject: tracing: Treat recording comm for idle task as a success Currently we stop recording comm for non-idle tasks when switching from/to idle task since we treat that as a record failure. Fix that by treat recording of comm for idle task as a success. Link: http://lkml.kernel.org/r/20170706230023.17942-1-joelaf@google.com Cc: kernel-team@android.com Cc: Ingo Molnar Reported-by: Michael Sartain Signed-off-by: Joel Fernandes Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f079a8ca1117..6722d86f2af5 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1916,7 +1916,11 @@ static int trace_save_cmdline(struct task_struct *tsk) { unsigned pid, idx; - if (!tsk->pid || unlikely(tsk->pid > PID_MAX_DEFAULT)) + /* treat recording of idle task as a success */ + if (!tsk->pid) + return 1; + + if (unlikely(tsk->pid > PID_MAX_DEFAULT)) return 0; /* -- cgit v1.2.3-59-g8ed1b From bd45d34d25720a820021c8ea45de5cd607eace64 Mon Sep 17 00:00:00 2001 From: Joel Fernandes Date: Thu, 6 Jul 2017 16:00:22 -0700 Subject: tracing: Treat recording tgid for idle task as a success Currently we stop recording tgid for non-idle tasks when switching from/to idle task since we treat that as a record failure. Fix that by treat recording of tgid for idle task as a success. Link: http://lkml.kernel.org/r/20170706230023.17942-2-joelaf@google.com Cc: kernel-team@android.com Cc: Ingo Molnar Reported-by: Michael Sartain Signed-off-by: Joel Fernandes Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 6722d86f2af5..aee11e3a394f 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2006,7 +2006,11 @@ int trace_find_tgid(int pid) static int trace_save_tgid(struct task_struct *tsk) { - if (unlikely(!tgid_map || !tsk->pid || tsk->pid > PID_MAX_DEFAULT)) + /* treat recording of idle task as a success */ + if (!tsk->pid) + return 1; + + if (unlikely(!tgid_map || tsk->pid > PID_MAX_DEFAULT)) return 0; tgid_map[tsk->pid] = tsk->tgid; -- cgit v1.2.3-59-g8ed1b From 29b1a8ad7df4528b862a79e3d5fb0936f4d199c7 Mon Sep 17 00:00:00 2001 From: Joel Fernandes Date: Thu, 6 Jul 2017 16:00:23 -0700 Subject: tracing: Attempt to record other information even if some fail In recent patches where we record comm and tgid at the same time, we skip continuing to record if any fail. Fix that by trying to record as many things as we can even if some couldn't be recorded. If any information isn't recorded, then we don't set trace_taskinfo_save as before. Link: http://lkml.kernel.org/r/20170706230023.17942-3-joelaf@google.com Cc: kernel-team@android.com Cc: Ingo Molnar Signed-off-by: Joel Fernandes Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 32 ++++++++++++++++++++++++-------- 1 file changed, 24 insertions(+), 8 deletions(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index aee11e3a394f..92af8fd1429b 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2037,11 +2037,20 @@ static bool tracing_record_taskinfo_skip(int flags) */ void tracing_record_taskinfo(struct task_struct *task, int flags) { + bool done; + if (tracing_record_taskinfo_skip(flags)) return; - if ((flags & TRACE_RECORD_CMDLINE) && !trace_save_cmdline(task)) - return; - if ((flags & TRACE_RECORD_TGID) && !trace_save_tgid(task)) + + /* + * Record as much task information as possible. If some fail, continue + * to try to record the others. + */ + done = !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(task); + done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(task); + + /* If recording any information failed, retry again soon. */ + if (!done) return; __this_cpu_write(trace_taskinfo_save, false); @@ -2058,15 +2067,22 @@ void tracing_record_taskinfo(struct task_struct *task, int flags) void tracing_record_taskinfo_sched_switch(struct task_struct *prev, struct task_struct *next, int flags) { + bool done; + if (tracing_record_taskinfo_skip(flags)) return; - if ((flags & TRACE_RECORD_CMDLINE) && - (!trace_save_cmdline(prev) || !trace_save_cmdline(next))) - return; + /* + * Record as much task information as possible. If some fail, continue + * to try to record the others. + */ + done = !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(prev); + done &= !(flags & TRACE_RECORD_CMDLINE) || trace_save_cmdline(next); + done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(prev); + done &= !(flags & TRACE_RECORD_TGID) || trace_save_tgid(next); - if ((flags & TRACE_RECORD_TGID) && - (!trace_save_tgid(prev) || !trace_save_tgid(next))) + /* If recording any information failed, retry again soon. */ + if (!done) return; __this_cpu_write(trace_taskinfo_save, false); -- cgit v1.2.3-59-g8ed1b From 5535f800b0e1533e5f3a1428f6ef25eb29eccc0f Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Thu, 6 Jul 2017 20:31:11 +0200 Subject: KVM: use rcu access function for irq routing irq routing is rcu protected. Use the proper access functions. Found by sparse virt/kvm/irqchip.c:233:13: warning: incorrect type in assignment (different address spaces) virt/kvm/irqchip.c:233:13: expected struct kvm_irq_routing_table *old virt/kvm/irqchip.c:233:13: got struct kvm_irq_routing_table [noderef] *irq_routing Signed-off-by: Christian Borntraeger Reviewed-by: Paolo Bonzini --- virt/kvm/irqchip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c index 31e40c9e81df..b1286c4e0712 100644 --- a/virt/kvm/irqchip.c +++ b/virt/kvm/irqchip.c @@ -230,7 +230,7 @@ int kvm_set_irq_routing(struct kvm *kvm, } mutex_lock(&kvm->irq_lock); - old = kvm->irq_routing; + old = rcu_dereference_protected(kvm->irq_routing, 1); rcu_assign_pointer(kvm->irq_routing, new); kvm_irq_routing_update(kvm); kvm_arch_irq_routing_update(kvm); -- cgit v1.2.3-59-g8ed1b From 4a12f95177280a660bda99e81838919b1cc6a91a Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Fri, 7 Jul 2017 10:51:38 +0200 Subject: KVM: mark kvm->busses as rcu protected mark kvm->busses as rcu protected and use the correct access function everywhere. found by sparse virt/kvm/kvm_main.c:3490:15: error: incompatible types in comparison expression (different address spaces) virt/kvm/kvm_main.c:3509:15: error: incompatible types in comparison expression (different address spaces) virt/kvm/kvm_main.c:3561:15: error: incompatible types in comparison expression (different address spaces) virt/kvm/kvm_main.c:3644:15: error: incompatible types in comparison expression (different address spaces) Signed-off-by: Christian Borntraeger --- include/linux/kvm_host.h | 8 +++++++- virt/kvm/eventfd.c | 8 +++++--- virt/kvm/kvm_main.c | 17 ++++++++++------- 3 files changed, 22 insertions(+), 11 deletions(-) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index bcd37b855c66..6a164f9eb02c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -404,7 +404,7 @@ struct kvm { int last_boosted_vcpu; struct list_head vm_list; struct mutex lock; - struct kvm_io_bus *buses[KVM_NR_BUSES]; + struct kvm_io_bus __rcu *buses[KVM_NR_BUSES]; #ifdef CONFIG_HAVE_KVM_EVENTFD struct { spinlock_t lock; @@ -473,6 +473,12 @@ struct kvm { #define vcpu_err(vcpu, fmt, ...) \ kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) +static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx) +{ + return srcu_dereference_check(kvm->buses[idx], &kvm->srcu, + lockdep_is_held(&kvm->slots_lock)); +} + static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) { /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu, in case diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index a8d540398bbd..d016aadd5fbb 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -825,7 +825,7 @@ static int kvm_assign_ioeventfd_idx(struct kvm *kvm, if (ret < 0) goto unlock_fail; - kvm->buses[bus_idx]->ioeventfd_count++; + kvm_get_bus(kvm, bus_idx)->ioeventfd_count++; list_add_tail(&p->list, &kvm->ioeventfds); mutex_unlock(&kvm->slots_lock); @@ -848,6 +848,7 @@ kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx, { struct _ioeventfd *p, *tmp; struct eventfd_ctx *eventfd; + struct kvm_io_bus *bus; int ret = -ENOENT; eventfd = eventfd_ctx_fdget(args->fd); @@ -870,8 +871,9 @@ kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx, continue; kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev); - if (kvm->buses[bus_idx]) - kvm->buses[bus_idx]->ioeventfd_count--; + bus = kvm_get_bus(kvm, bus_idx); + if (bus) + bus->ioeventfd_count--; ioeventfd_release(p); ret = 0; break; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index fc2d58312fd5..d76e822f8929 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -679,8 +679,8 @@ static struct kvm *kvm_create_vm(unsigned long type) if (init_srcu_struct(&kvm->irq_srcu)) goto out_err_no_irq_srcu; for (i = 0; i < KVM_NR_BUSES; i++) { - kvm->buses[i] = kzalloc(sizeof(struct kvm_io_bus), - GFP_KERNEL); + rcu_assign_pointer(kvm->buses[i], + kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL)); if (!kvm->buses[i]) goto out_err; } @@ -705,7 +705,7 @@ out_err_no_srcu: hardware_disable_all(); out_err_no_disable: for (i = 0; i < KVM_NR_BUSES; i++) - kfree(kvm->buses[i]); + kfree(rcu_access_pointer(kvm->buses[i])); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) kvm_free_memslots(kvm, kvm->memslots[i]); kvm_arch_free_vm(kvm); @@ -740,8 +740,11 @@ static void kvm_destroy_vm(struct kvm *kvm) spin_unlock(&kvm_lock); kvm_free_irq_routing(kvm); for (i = 0; i < KVM_NR_BUSES; i++) { - if (kvm->buses[i]) - kvm_io_bus_destroy(kvm->buses[i]); + struct kvm_io_bus *bus; + + bus = rcu_dereference_protected(kvm->buses[i], 1); + if (bus) + kvm_io_bus_destroy(bus); kvm->buses[i] = NULL; } kvm_coalesced_mmio_free(kvm); @@ -3570,7 +3573,7 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, { struct kvm_io_bus *new_bus, *bus; - bus = kvm->buses[bus_idx]; + bus = kvm_get_bus(kvm, bus_idx); if (!bus) return -ENOMEM; @@ -3599,7 +3602,7 @@ void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, int i; struct kvm_io_bus *new_bus, *bus; - bus = kvm->buses[bus_idx]; + bus = kvm_get_bus(kvm, bus_idx); if (!bus) return; -- cgit v1.2.3-59-g8ed1b From a80cf7b5f4149753d5f19c872a47e66195b167d4 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Thu, 6 Jul 2017 16:17:14 +0200 Subject: KVM: mark memory slots as rcu we access the memslots array via srcu. Mark it as such and use the right access functions also for the freeing of memory slots. Found by sparse: ./include/linux/kvm_host.h:565:16: error: incompatible types in comparison expression (different address spaces) Signed-off-by: Christian Borntraeger Reviewed-by: Paolo Bonzini --- include/linux/kvm_host.h | 2 +- virt/kvm/kvm_main.c | 6 ++++-- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 6a164f9eb02c..b3ca77a96b2d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -390,7 +390,7 @@ struct kvm { spinlock_t mmu_lock; struct mutex slots_lock; struct mm_struct *mm; /* userspace tied to this vm */ - struct kvm_memslots *memslots[KVM_ADDRESS_SPACE_NUM]; + struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM]; struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; /* diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index d76e822f8929..6e6d4edf0e92 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -707,7 +707,8 @@ out_err_no_disable: for (i = 0; i < KVM_NR_BUSES; i++) kfree(rcu_access_pointer(kvm->buses[i])); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) - kvm_free_memslots(kvm, kvm->memslots[i]); + kvm_free_memslots(kvm, + rcu_dereference_protected(kvm->memslots[i], 1)); kvm_arch_free_vm(kvm); mmdrop(current->mm); return ERR_PTR(r); @@ -756,7 +757,8 @@ static void kvm_destroy_vm(struct kvm *kvm) kvm_arch_destroy_vm(kvm); kvm_destroy_devices(kvm); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) - kvm_free_memslots(kvm, kvm->memslots[i]); + kvm_free_memslots(kvm, + rcu_dereference_protected(kvm->memslots[i], 1)); cleanup_srcu_struct(&kvm->irq_srcu); cleanup_srcu_struct(&kvm->srcu); kvm_arch_free_vm(kvm); -- cgit v1.2.3-59-g8ed1b From 20e2b791796bd68816fa115f12be5320de2b8021 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 6 Jul 2017 12:34:40 +0200 Subject: ALSA: msnd: Optimize / harden DSP and MIDI loops The ISA msnd drivers have loops fetching the ring-buffer head, tail and size values inside the loops. Such codes are inefficient and fragile. This patch optimizes it, and also adds the sanity check to avoid the endless loops. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=196131 Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=196133 Signed-off-by: Takashi Iwai --- sound/isa/msnd/msnd_midi.c | 30 +++++++++++++++--------------- sound/isa/msnd/msnd_pinnacle.c | 23 ++++++++++++----------- 2 files changed, 27 insertions(+), 26 deletions(-) diff --git a/sound/isa/msnd/msnd_midi.c b/sound/isa/msnd/msnd_midi.c index 912b5a9ccbab..013d8d1170fe 100644 --- a/sound/isa/msnd/msnd_midi.c +++ b/sound/isa/msnd/msnd_midi.c @@ -120,24 +120,24 @@ void snd_msndmidi_input_read(void *mpuv) unsigned long flags; struct snd_msndmidi *mpu = mpuv; void *pwMIDQData = mpu->dev->mappedbase + MIDQ_DATA_BUFF; + u16 head, tail, size; spin_lock_irqsave(&mpu->input_lock, flags); - while (readw(mpu->dev->MIDQ + JQS_wTail) != - readw(mpu->dev->MIDQ + JQS_wHead)) { - u16 wTmp, val; - val = readw(pwMIDQData + 2 * readw(mpu->dev->MIDQ + JQS_wHead)); - - if (test_bit(MSNDMIDI_MODE_BIT_INPUT_TRIGGER, - &mpu->mode)) - snd_rawmidi_receive(mpu->substream_input, - (unsigned char *)&val, 1); - - wTmp = readw(mpu->dev->MIDQ + JQS_wHead) + 1; - if (wTmp > readw(mpu->dev->MIDQ + JQS_wSize)) - writew(0, mpu->dev->MIDQ + JQS_wHead); - else - writew(wTmp, mpu->dev->MIDQ + JQS_wHead); + head = readw(mpu->dev->MIDQ + JQS_wHead); + tail = readw(mpu->dev->MIDQ + JQS_wTail); + size = readw(mpu->dev->MIDQ + JQS_wSize); + if (head > size || tail > size) + goto out; + while (head != tail) { + unsigned char val = readw(pwMIDQData + 2 * head); + + if (test_bit(MSNDMIDI_MODE_BIT_INPUT_TRIGGER, &mpu->mode)) + snd_rawmidi_receive(mpu->substream_input, &val, 1); + if (++head > size) + head = 0; + writew(head, mpu->dev->MIDQ + JQS_wHead); } + out: spin_unlock_irqrestore(&mpu->input_lock, flags); } EXPORT_SYMBOL(snd_msndmidi_input_read); diff --git a/sound/isa/msnd/msnd_pinnacle.c b/sound/isa/msnd/msnd_pinnacle.c index ad4897337df5..fc4fb1904aef 100644 --- a/sound/isa/msnd/msnd_pinnacle.c +++ b/sound/isa/msnd/msnd_pinnacle.c @@ -170,23 +170,24 @@ static irqreturn_t snd_msnd_interrupt(int irq, void *dev_id) { struct snd_msnd *chip = dev_id; void *pwDSPQData = chip->mappedbase + DSPQ_DATA_BUFF; + u16 head, tail, size; /* Send ack to DSP */ /* inb(chip->io + HP_RXL); */ /* Evaluate queued DSP messages */ - while (readw(chip->DSPQ + JQS_wTail) != readw(chip->DSPQ + JQS_wHead)) { - u16 wTmp; - - snd_msnd_eval_dsp_msg(chip, - readw(pwDSPQData + 2 * readw(chip->DSPQ + JQS_wHead))); - - wTmp = readw(chip->DSPQ + JQS_wHead) + 1; - if (wTmp > readw(chip->DSPQ + JQS_wSize)) - writew(0, chip->DSPQ + JQS_wHead); - else - writew(wTmp, chip->DSPQ + JQS_wHead); + head = readw(chip->DSPQ + JQS_wHead); + tail = readw(chip->DSPQ + JQS_wTail); + size = readw(chip->DSPQ + JQS_wSize); + if (head > size || tail > size) + goto out; + while (head != tail) { + snd_msnd_eval_dsp_msg(chip, readw(pwDSPQData + 2 * head)); + if (++head > size) + head = 0; + writew(head, chip->DSPQ + JQS_wHead); } + out: /* Send ack to DSP */ inb(chip->io + HP_RXL); return IRQ_HANDLED; -- cgit v1.2.3-59-g8ed1b From 564d8a2cf3abf16575af48bdc3e86e92ee8a617d Mon Sep 17 00:00:00 2001 From: Mario Kleiner Date: Fri, 7 Jul 2017 04:57:04 +0200 Subject: drm/radeon: Fix eDP for single-display iMac10,1 (v2) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The late 2009, 27 inch Apple iMac10,1 has an internal eDP display and an external Mini- Displayport output, driven by a DCE-3.2, RV730 Radeon Mobility HD-4670. The machine worked fine in a dual-display setup with eDP panel + externally connected HDMI or DVI-D digital display sink, connected via MiniDP to DVI or HDMI adapter. However, booting the machine single-display with only eDP panel results in a completely black display - even backlight powering off, as soon as the radeon modesetting driver loads. This patch fixes the single dispay eDP case by assigning encoders based on dig->linkb, similar to DCE-4+. While this should not be generally necessary (Alex: "...atom on normal boards should be able to handle any mapping."), Apple seems to use some special routing here. One remaining problem not solved by this patch is that an external Minidisplayport->DP sink does still not work on iMac10,1, whereas external DVI and HDMI sinks continue to work. The problem affects at least all tested kernels since Linux 3.13 - didn't test earlier kernels, so backporting to stable probably makes sense. v2: With the original patch from 2016, Alex was worried it will break other DCE3.2 systems. Use dmi_match() to apply this special encoder assignment only for the Apple iMac 10,1 from late 2009. Signed-off-by: Mario Kleiner Cc: Alex Deucher Cc: Michel Dänzer Cc: Signed-off-by: Alex Deucher --- drivers/gpu/drm/radeon/atombios_encoders.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c index fa4f8f008e4d..e67ed383e11b 100644 --- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -31,6 +31,7 @@ #include "radeon_asic.h" #include "atom.h" #include +#include extern int atom_debug; @@ -2184,9 +2185,17 @@ int radeon_atom_pick_dig_encoder(struct drm_encoder *encoder, int fe_idx) goto assigned; } - /* on DCE32 and encoder can driver any block so just crtc id */ + /* + * On DCE32 any encoder can drive any block so usually just use crtc id, + * but Apple thinks different at least on iMac10,1, so there use linkb, + * otherwise the internal eDP panel will stay dark. + */ if (ASIC_IS_DCE32(rdev)) { - enc_idx = radeon_crtc->crtc_id; + if (dmi_match(DMI_PRODUCT_NAME, "iMac10,1")) + enc_idx = (dig->linkb) ? 1 : 0; + else + enc_idx = radeon_crtc->crtc_id; + goto assigned; } -- cgit v1.2.3-59-g8ed1b From b77a5372076984d33731a8da0fd52fc718f62a23 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 6 Jul 2017 17:19:02 -0500 Subject: platform/x86: fujitsu-laptop: add NULL check on devm_kzalloc() return value Check return value from call to devm_kzalloc() in order to prevent a NULL pointer dereference. This issue was detected using Coccinelle and the following semantic patch: @@ expression x; identifier fld; @@ * x = devm_kzalloc(...); ... when != x == NULL x->fld Signed-off-by: Gustavo A. R. Silva Reviewed-by: Jonathan Woithe Signed-off-by: Darren Hart (VMware) --- drivers/platform/x86/fujitsu-laptop.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/platform/x86/fujitsu-laptop.c b/drivers/platform/x86/fujitsu-laptop.c index c1a852847d02..9a1034bec0fc 100644 --- a/drivers/platform/x86/fujitsu-laptop.c +++ b/drivers/platform/x86/fujitsu-laptop.c @@ -695,6 +695,9 @@ static int acpi_fujitsu_laptop_leds_register(struct acpi_device *device) if (call_fext_func(device, FUNC_LEDS, 0x0, 0x0, 0x0) & LOGOLAMP_POWERON) { led = devm_kzalloc(&device->dev, sizeof(*led), GFP_KERNEL); + if (!led) + return -ENOMEM; + led->name = "fujitsu::logolamp"; led->brightness_set_blocking = logolamp_set; led->brightness_get = logolamp_get; @@ -707,6 +710,9 @@ static int acpi_fujitsu_laptop_leds_register(struct acpi_device *device) FUNC_LEDS, 0x0, 0x0, 0x0) & KEYBOARD_LAMPS) && (call_fext_func(device, FUNC_BUTTONS, 0x0, 0x0, 0x0) == 0x0)) { led = devm_kzalloc(&device->dev, sizeof(*led), GFP_KERNEL); + if (!led) + return -ENOMEM; + led->name = "fujitsu::kblamps"; led->brightness_set_blocking = kblamps_set; led->brightness_get = kblamps_get; @@ -723,6 +729,9 @@ static int acpi_fujitsu_laptop_leds_register(struct acpi_device *device) */ if (call_fext_func(device, FUNC_BUTTONS, 0x0, 0x0, 0x0) & BIT(24)) { led = devm_kzalloc(&device->dev, sizeof(*led), GFP_KERNEL); + if (!led) + return -ENOMEM; + led->name = "fujitsu::radio_led"; led->brightness_set_blocking = radio_led_set; led->brightness_get = radio_led_get; @@ -741,6 +750,9 @@ static int acpi_fujitsu_laptop_leds_register(struct acpi_device *device) (call_fext_func(device, FUNC_LEDS, 0x2, ECO_LED, 0x0) != UNSUPPORTED_CMD)) { led = devm_kzalloc(&device->dev, sizeof(*led), GFP_KERNEL); + if (!led) + return -ENOMEM; + led->name = "fujitsu::eco_led"; led->brightness_set_blocking = eco_led_set; led->brightness_get = eco_led_get; -- cgit v1.2.3-59-g8ed1b From 7f56c30bd0a232822aca38d288da475613bdff9b Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Fri, 7 Jul 2017 15:37:38 -0600 Subject: vfio: Remove unnecessary uses of vfio_container.group_lock The original intent of vfio_container.group_lock is to protect vfio_container.group_list, however over time it's become a crutch to prevent changes in container composition any time we call into the iommu driver backend. This introduces problems when we start to have more complex interactions, for example when a user's DMA unmap request triggers a notification to an mdev vendor driver, who responds by attempting to unpin mappings within that request, re-entering the iommu backend. We incorrectly assume that the use of read-locks here allow for this nested locking behavior, but a poorly timed write-lock could in fact trigger a deadlock. The current use of group_lock seems to fall into the trap of locking code, not data. Correct that by removing uses of group_lock that are not directly related to group_list. Note that the vfio type1 iommu backend has its own mutex, vfio_iommu.lock, which it uses to protect itself for each of these interfaces anyway. The group_lock appears to be a redundancy for these interfaces and type1 even goes so far as to release its mutex to allow for exactly the re-entrant code path above. Reported-by: Chuanxiao Dong Signed-off-by: Alex Williamson Acked-by: Alexey Kardashevskiy Cc: stable@vger.kernel.org # v4.10+ --- drivers/vfio/vfio.c | 38 -------------------------------------- 1 file changed, 38 deletions(-) diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 7597a377eb4e..330d50582f40 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -1175,15 +1175,11 @@ static long vfio_fops_unl_ioctl(struct file *filep, ret = vfio_ioctl_set_iommu(container, arg); break; default: - down_read(&container->group_lock); - driver = container->iommu_driver; data = container->iommu_data; if (driver) /* passthrough all unrecognized ioctls */ ret = driver->ops->ioctl(data, cmd, arg); - - up_read(&container->group_lock); } return ret; @@ -1237,15 +1233,11 @@ static ssize_t vfio_fops_read(struct file *filep, char __user *buf, struct vfio_iommu_driver *driver; ssize_t ret = -EINVAL; - down_read(&container->group_lock); - driver = container->iommu_driver; if (likely(driver && driver->ops->read)) ret = driver->ops->read(container->iommu_data, buf, count, ppos); - up_read(&container->group_lock); - return ret; } @@ -1256,15 +1248,11 @@ static ssize_t vfio_fops_write(struct file *filep, const char __user *buf, struct vfio_iommu_driver *driver; ssize_t ret = -EINVAL; - down_read(&container->group_lock); - driver = container->iommu_driver; if (likely(driver && driver->ops->write)) ret = driver->ops->write(container->iommu_data, buf, count, ppos); - up_read(&container->group_lock); - return ret; } @@ -1274,14 +1262,10 @@ static int vfio_fops_mmap(struct file *filep, struct vm_area_struct *vma) struct vfio_iommu_driver *driver; int ret = -EINVAL; - down_read(&container->group_lock); - driver = container->iommu_driver; if (likely(driver && driver->ops->mmap)) ret = driver->ops->mmap(container->iommu_data, vma); - up_read(&container->group_lock); - return ret; } @@ -1993,8 +1977,6 @@ int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, int npage, goto err_pin_pages; container = group->container; - down_read(&container->group_lock); - driver = container->iommu_driver; if (likely(driver && driver->ops->pin_pages)) ret = driver->ops->pin_pages(container->iommu_data, user_pfn, @@ -2002,7 +1984,6 @@ int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, int npage, else ret = -ENOTTY; - up_read(&container->group_lock); vfio_group_try_dissolve_container(group); err_pin_pages: @@ -2042,8 +2023,6 @@ int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn, int npage) goto err_unpin_pages; container = group->container; - down_read(&container->group_lock); - driver = container->iommu_driver; if (likely(driver && driver->ops->unpin_pages)) ret = driver->ops->unpin_pages(container->iommu_data, user_pfn, @@ -2051,7 +2030,6 @@ int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn, int npage) else ret = -ENOTTY; - up_read(&container->group_lock); vfio_group_try_dissolve_container(group); err_unpin_pages: @@ -2073,8 +2051,6 @@ static int vfio_register_iommu_notifier(struct vfio_group *group, return -EINVAL; container = group->container; - down_read(&container->group_lock); - driver = container->iommu_driver; if (likely(driver && driver->ops->register_notifier)) ret = driver->ops->register_notifier(container->iommu_data, @@ -2082,7 +2058,6 @@ static int vfio_register_iommu_notifier(struct vfio_group *group, else ret = -ENOTTY; - up_read(&container->group_lock); vfio_group_try_dissolve_container(group); return ret; @@ -2100,8 +2075,6 @@ static int vfio_unregister_iommu_notifier(struct vfio_group *group, return -EINVAL; container = group->container; - down_read(&container->group_lock); - driver = container->iommu_driver; if (likely(driver && driver->ops->unregister_notifier)) ret = driver->ops->unregister_notifier(container->iommu_data, @@ -2109,7 +2082,6 @@ static int vfio_unregister_iommu_notifier(struct vfio_group *group, else ret = -ENOTTY; - up_read(&container->group_lock); vfio_group_try_dissolve_container(group); return ret; @@ -2127,7 +2099,6 @@ static int vfio_register_group_notifier(struct vfio_group *group, unsigned long *events, struct notifier_block *nb) { - struct vfio_container *container; int ret; bool set_kvm = false; @@ -2145,9 +2116,6 @@ static int vfio_register_group_notifier(struct vfio_group *group, if (ret) return -EINVAL; - container = group->container; - down_read(&container->group_lock); - ret = blocking_notifier_chain_register(&group->notifier, nb); /* @@ -2158,7 +2126,6 @@ static int vfio_register_group_notifier(struct vfio_group *group, blocking_notifier_call_chain(&group->notifier, VFIO_GROUP_NOTIFY_SET_KVM, group->kvm); - up_read(&container->group_lock); vfio_group_try_dissolve_container(group); return ret; @@ -2167,19 +2134,14 @@ static int vfio_register_group_notifier(struct vfio_group *group, static int vfio_unregister_group_notifier(struct vfio_group *group, struct notifier_block *nb) { - struct vfio_container *container; int ret; ret = vfio_group_add_container_user(group); if (ret) return -EINVAL; - container = group->container; - down_read(&container->group_lock); - ret = blocking_notifier_chain_unregister(&group->notifier, nb); - up_read(&container->group_lock); vfio_group_try_dissolve_container(group); return ret; -- cgit v1.2.3-59-g8ed1b From b9504247a6eb2bd68e3f620ca1f3fbe7309123ea Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 25 Jun 2017 20:22:57 +0200 Subject: mtd: Fix check in mtd_unpoint() The code checks that ->_point is not NULL, but we should actually check ->_unpoint value which is dereferenced a few lines after the check. Signed-off-by: Boris Brezillon Signed-off-by: Brian Norris --- drivers/mtd/mtdcore.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index 1517da3ddd7d..956382cea256 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -991,7 +991,7 @@ EXPORT_SYMBOL_GPL(mtd_point); /* We probably shouldn't allow XIP if the unpoint isn't a NULL */ int mtd_unpoint(struct mtd_info *mtd, loff_t from, size_t len) { - if (!mtd->_point) + if (!mtd->_unpoint) return -EOPNOTSUPP; if (from < 0 || from >= mtd->size || len > mtd->size - from) return -EINVAL; -- cgit v1.2.3-59-g8ed1b From 3941dae15ed90437396389e8bb7d2d5b3e63ba4a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 20 Apr 2017 16:43:12 -0400 Subject: drm_dp_aux_dev: switch to read_iter/write_iter Signed-off-by: Al Viro --- drivers/gpu/drm/drm_dp_aux_dev.c | 109 +++++++++++++++++---------------------- 1 file changed, 46 insertions(+), 63 deletions(-) diff --git a/drivers/gpu/drm/drm_dp_aux_dev.c b/drivers/gpu/drm/drm_dp_aux_dev.c index ec1ed94b2390..d34e5096887a 100644 --- a/drivers/gpu/drm/drm_dp_aux_dev.c +++ b/drivers/gpu/drm/drm_dp_aux_dev.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include #include @@ -140,101 +141,83 @@ static loff_t auxdev_llseek(struct file *file, loff_t offset, int whence) return fixed_size_llseek(file, offset, whence, AUX_MAX_OFFSET); } -static ssize_t auxdev_read(struct file *file, char __user *buf, size_t count, - loff_t *offset) +static ssize_t auxdev_read_iter(struct kiocb *iocb, struct iov_iter *to) { - size_t bytes_pending, num_bytes_processed = 0; - struct drm_dp_aux_dev *aux_dev = file->private_data; + struct drm_dp_aux_dev *aux_dev = iocb->ki_filp->private_data; + loff_t pos = iocb->ki_pos; ssize_t res = 0; if (!atomic_inc_not_zero(&aux_dev->usecount)) return -ENODEV; - bytes_pending = min((loff_t)count, AUX_MAX_OFFSET - (*offset)); - - if (!access_ok(VERIFY_WRITE, buf, bytes_pending)) { - res = -EFAULT; - goto out; - } + iov_iter_truncate(to, AUX_MAX_OFFSET - pos); - while (bytes_pending > 0) { - uint8_t localbuf[DP_AUX_MAX_PAYLOAD_BYTES]; - ssize_t todo = min_t(size_t, bytes_pending, sizeof(localbuf)); + while (iov_iter_count(to)) { + uint8_t buf[DP_AUX_MAX_PAYLOAD_BYTES]; + ssize_t todo = min(iov_iter_count(to), sizeof(buf)); if (signal_pending(current)) { - res = num_bytes_processed ? - num_bytes_processed : -ERESTARTSYS; - goto out; + res = -ERESTARTSYS; + break; } - res = drm_dp_dpcd_read(aux_dev->aux, *offset, localbuf, todo); - if (res <= 0) { - res = num_bytes_processed ? num_bytes_processed : res; - goto out; - } - if (__copy_to_user(buf + num_bytes_processed, localbuf, res)) { - res = num_bytes_processed ? - num_bytes_processed : -EFAULT; - goto out; + res = drm_dp_dpcd_read(aux_dev->aux, pos, buf, todo); + if (res <= 0) + break; + + if (copy_to_iter(buf, res, to) != res) { + res = -EFAULT; + break; } - bytes_pending -= res; - *offset += res; - num_bytes_processed += res; - res = num_bytes_processed; + + pos += res; } -out: + if (pos != iocb->ki_pos) + res = pos - iocb->ki_pos; + iocb->ki_pos = pos; + atomic_dec(&aux_dev->usecount); wake_up_atomic_t(&aux_dev->usecount); return res; } -static ssize_t auxdev_write(struct file *file, const char __user *buf, - size_t count, loff_t *offset) +static ssize_t auxdev_write_iter(struct kiocb *iocb, struct iov_iter *from) { - size_t bytes_pending, num_bytes_processed = 0; - struct drm_dp_aux_dev *aux_dev = file->private_data; + struct drm_dp_aux_dev *aux_dev = iocb->ki_filp->private_data; + loff_t pos = iocb->ki_pos; ssize_t res = 0; if (!atomic_inc_not_zero(&aux_dev->usecount)) return -ENODEV; - bytes_pending = min((loff_t)count, AUX_MAX_OFFSET - *offset); - - if (!access_ok(VERIFY_READ, buf, bytes_pending)) { - res = -EFAULT; - goto out; - } + iov_iter_truncate(from, AUX_MAX_OFFSET - pos); - while (bytes_pending > 0) { - uint8_t localbuf[DP_AUX_MAX_PAYLOAD_BYTES]; - ssize_t todo = min_t(size_t, bytes_pending, sizeof(localbuf)); + while (iov_iter_count(from)) { + uint8_t buf[DP_AUX_MAX_PAYLOAD_BYTES]; + ssize_t todo = min(iov_iter_count(from), sizeof(buf)); if (signal_pending(current)) { - res = num_bytes_processed ? - num_bytes_processed : -ERESTARTSYS; - goto out; + res = -ERESTARTSYS; + break; } - if (__copy_from_user(localbuf, - buf + num_bytes_processed, todo)) { - res = num_bytes_processed ? - num_bytes_processed : -EFAULT; - goto out; + if (!copy_from_iter_full(buf, todo, from)) { + res = -EFAULT; + break; } - res = drm_dp_dpcd_write(aux_dev->aux, *offset, localbuf, todo); - if (res <= 0) { - res = num_bytes_processed ? num_bytes_processed : res; - goto out; - } - bytes_pending -= res; - *offset += res; - num_bytes_processed += res; - res = num_bytes_processed; + res = drm_dp_dpcd_write(aux_dev->aux, pos, buf, todo); + if (res <= 0) + break; + + pos += res; } -out: + if (pos != iocb->ki_pos) + res = pos - iocb->ki_pos; + iocb->ki_pos = pos; + atomic_dec(&aux_dev->usecount); wake_up_atomic_t(&aux_dev->usecount); return res; @@ -251,8 +234,8 @@ static int auxdev_release(struct inode *inode, struct file *file) static const struct file_operations auxdev_fops = { .owner = THIS_MODULE, .llseek = auxdev_llseek, - .read = auxdev_read, - .write = auxdev_write, + .read_iter = auxdev_read_iter, + .write_iter = auxdev_write_iter, .open = auxdev_open, .release = auxdev_release, }; -- cgit v1.2.3-59-g8ed1b From 799ce1dbb9bba56ff21733838a05070787fdcde5 Mon Sep 17 00:00:00 2001 From: Tommy Nguyen Date: Sun, 9 Jul 2017 10:25:43 +0100 Subject: befs: add kernel-doc formatting for befs_bt_read_super() fs/befs/TODO mentions some comments needing conversion to Kernel-Doc formatting. This patch changes the comment describing befs_bt_read_super(). Signed-off-by: Tommy Nguyen Signed-off-by: Luis de Bethencourt --- fs/befs/btree.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/fs/befs/btree.c b/fs/befs/btree.c index d509887c580c..1b7e0f7128d6 100644 --- a/fs/befs/btree.c +++ b/fs/befs/btree.c @@ -120,18 +120,15 @@ static int befs_compare_strings(const void *key1, int keylen1, const void *key2, int keylen2); /** - * befs_bt_read_super - read in btree superblock convert to cpu byteorder - * @sb: Filesystem superblock - * @ds: Datastream to read from - * @sup: Buffer in which to place the btree superblock + * befs_bt_read_super() - read in btree superblock convert to cpu byteorder + * @sb: Filesystem superblock + * @ds: Datastream to read from + * @sup: Buffer in which to place the btree superblock * * Calls befs_read_datastream to read in the btree superblock and * makes sure it is in cpu byteorder, byteswapping if necessary. - * - * On success, returns BEFS_OK and *@sup contains the btree superblock, - * in cpu byte order. - * - * On failure, BEFS_ERR is returned. + * Return: BEFS_OK on success and if *@sup contains the btree superblock in cpu + * byte order. Otherwise return BEFS_ERR on error. */ static int befs_bt_read_super(struct super_block *sb, const befs_data_stream *ds, -- cgit v1.2.3-59-g8ed1b From fca18a47cf3eb8425ec19c2dfc374f3d04f5219f Mon Sep 17 00:00:00 2001 From: "Naveen N. Rao" Date: Sat, 8 Jul 2017 00:27:30 +0530 Subject: trace/kprobes: Sanitize derived event names When we derive event names, convert some expected symbols (such as ':' used to specify module:name and '.' present in some symbols) into underscores so that the event name is not rejected. Before this patch: # echo 'p kobject_example:foo_store' > kprobe_events trace_kprobe: Failed to allocate trace_probe.(-22) -sh: write error: Invalid argument After this patch: # echo 'p kobject_example:foo_store' > kprobe_events # cat kprobe_events p:kprobes/p_kobject_example_foo_store_0 kobject_example:foo_store Link: http://lkml.kernel.org/r/66c189e09e71361aba91dd4a5bd146a1b62a7a51.1499453040.git.naveen.n.rao@linux.vnet.ibm.com Acked-by: Masami Hiramatsu Signed-off-by: Naveen N. Rao Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_kprobe.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index c129fca6ec99..44fd819aa33d 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -598,6 +598,14 @@ static struct notifier_block trace_kprobe_module_nb = { .priority = 1 /* Invoked after kprobe module callback */ }; +/* Convert certain expected symbols into '_' when generating event names */ +static inline void sanitize_event_name(char *name) +{ + while (*name++ != '\0') + if (*name == ':' || *name == '.') + *name = '_'; +} + static int create_trace_kprobe(int argc, char **argv) { /* @@ -740,6 +748,7 @@ static int create_trace_kprobe(int argc, char **argv) else snprintf(buf, MAX_EVENT_NAME_LEN, "%c_0x%p", is_return ? 'r' : 'p', addr); + sanitize_event_name(buf); event = buf; } tk = alloc_trace_kprobe(group, event, addr, symbol, offset, maxactive, -- cgit v1.2.3-59-g8ed1b From f7181e5aaab58d81c5453887e39a1e1041f6bb1a Mon Sep 17 00:00:00 2001 From: "Naveen N. Rao" Date: Sat, 8 Jul 2017 00:27:31 +0530 Subject: selftests/ftrace: Update multiple kprobes test for powerpc KPROBES_ON_FTRACE is only available on powerpc64le. Update comment to clarify this. Also, we should use an offset of 8 to ensure that the probe does not fall on ftrace location. The current offset of 4 will fall before the function local entry point and won't fire, while an offset of 12 or 16 will fall on ftrace location. Offset 8 is currently guaranteed to not be the ftrace location. Link: http://lkml.kernel.org/r/3d32e8fa076070e83527476fdfa3a747bb9a1a3a.1499453040.git.naveen.n.rao@linux.vnet.ibm.com Acked-by: Masami Hiramatsu Signed-off-by: Naveen N. Rao Signed-off-by: Steven Rostedt (VMware) --- tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc index f4d1ff785d67..2a1cb9908746 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc @@ -2,10 +2,10 @@ # description: Register/unregister many kprobe events # ftrace fentry skip size depends on the machine architecture. -# Currently HAVE_KPROBES_ON_FTRACE defined on x86 and powerpc +# Currently HAVE_KPROBES_ON_FTRACE defined on x86 and powerpc64le case `uname -m` in x86_64|i[3456]86) OFFS=5;; - ppc*) OFFS=4;; + ppc64le) OFFS=8;; *) OFFS=0;; esac -- cgit v1.2.3-59-g8ed1b From ff431b1390cbf8764f8550b8e427eb28d4a6328e Mon Sep 17 00:00:00 2001 From: "Naveen N. Rao" Date: Sat, 8 Jul 2017 00:27:32 +0530 Subject: selftests/ftrace: Add a test to probe module functions Add a kprobes test to ensure that we are able to add a probe on a module function using 'p :' format, with/without having to specify a probe name. Link: http://lkml.kernel.org/r/2d8087e25a7ad9206f3e2b7b4bb0c3c86eaa38af.1499453040.git.naveen.n.rao@linux.vnet.ibm.com Suggested-by: Masami Hiramatsu Acked-by: Masami Hiramatsu Signed-off-by: Naveen N. Rao Signed-off-by: Steven Rostedt (VMware) --- .../ftrace/test.d/kprobe/kprobe_module.tc | 28 ++++++++++++++++++++++ 1 file changed, 28 insertions(+) create mode 100644 tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc new file mode 100644 index 000000000000..6d634e4b7680 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_module.tc @@ -0,0 +1,28 @@ +#!/bin/sh +# description: Kprobe dynamic event - probing module + +[ -f kprobe_events ] || exit_unsupported # this is configurable + +disable_events +echo > kprobe_events + +:;: "Add an event on a module function without specifying event name" ;: + +MOD=`lsmod | head -n 2 | tail -n 1 | cut -f1 -d" "` +FUNC=`grep -m 1 ".* t .*\\[$MOD\\]" /proc/kallsyms | xargs | cut -f3 -d" "` +[ "x" != "x$MOD" -a "y" != "y$FUNC" ] || exit_unresolved +echo "p $MOD:$FUNC" > kprobe_events +PROBE_NAME=`echo $MOD:$FUNC | tr ".:" "_"` +test -d events/kprobes/p_${PROBE_NAME}_0 || exit_failure + +:;: "Add an event on a module function with new event name" ;: + +echo "p:event1 $MOD:$FUNC" > kprobe_events +test -d events/kprobes/event1 || exit_failure + +:;: "Add an event on a module function with new event and group name" ;: + +echo "p:kprobes1/event1 $MOD:$FUNC" > kprobe_events +test -d events/kprobes1/event1 || exit_failure + +echo > kprobe_events -- cgit v1.2.3-59-g8ed1b From 8cb0bc9e3f863f3e77522d02443a75c0e45a6ed0 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Sat, 8 Jul 2017 00:27:33 +0530 Subject: selftests/ftrace: Add a testcase for kprobe event naming Add a testcase for kprobe event naming. This testcase checks whether the kprobe events can automatically ganerate its event name on normal function and dot-suffixed function. Also it checks whether the kprobe events can correctly define new event with given event name and group name. Link: http://lkml.kernel.org/r/61ae96fd1fcd14ee652c8b6525c218b8661bb0d2.1499453040.git.naveen.n.rao@linux.vnet.ibm.com Signed-off-by: Masami Hiramatsu [Updated tests to use vfs_read and symbols with '.isra.', added check for kprobe_events and a command to clear it on exit, various additional checks and tests] Signed-off-by: Naveen N. Rao Signed-off-by: Steven Rostedt (VMware) --- .../ftrace/test.d/kprobe/kprobe_eventname.tc | 36 ++++++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc new file mode 100644 index 000000000000..b9302cc82c12 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc @@ -0,0 +1,36 @@ +#!/bin/sh +# description: Kprobe event auto/manual naming + +[ -f kprobe_events ] || exit_unsupported # this is configurable + +disable_events +echo > kprobe_events + +:;: "Add an event on function without name" ;: + +FUNC=`grep " [tT] .*vfs_read$" /proc/kallsyms | tail -n 1 | cut -f 3 -d " "` +[ "x" != "x$FUNC" ] || exit_unresolved +echo "p $FUNC" > kprobe_events +PROBE_NAME=`echo $FUNC | tr ".:" "_"` +test -d events/kprobes/p_${PROBE_NAME}_0 || exit_failure + +:;: "Add an event on function with new name" ;: + +echo "p:event1 $FUNC" > kprobe_events +test -d events/kprobes/event1 || exit_failure + +:;: "Add an event on function with new name and group" ;: + +echo "p:kprobes2/event2 $FUNC" > kprobe_events +test -d events/kprobes2/event2 || exit_failure + +:;: "Add an event on dot function without name" ;: + +FUNC=`grep -m 10 " [tT] .*\.isra\..*$" /proc/kallsyms | tail -n 1 | cut -f 3 -d " "` +[ "x" != "x$FUNC" ] || exit_unresolved +echo "p $FUNC" > kprobe_events +EVENT=`grep $FUNC kprobe_events | cut -f 1 -d " " | cut -f 2 -d:` +[ "x" != "x$EVENT" ] || exit_failure +test -d events/$EVENT || exit_failure + +echo > kprobe_events -- cgit v1.2.3-59-g8ed1b From 87ebb94e28ccac00bacba0d6a0dac0aac5b9c63b Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:33 +0900 Subject: kbuild: remove useless $(gen) variable in Makefile.headersinst We have no true case for the $(if $(gen), ...) conditional. Drop it to simplify the gendir calculation. Signed-off-by: Masahiro Yamada --- scripts/Makefile.headersinst | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/scripts/Makefile.headersinst b/scripts/Makefile.headersinst index c583a1e1bd3c..4e9287bfdf28 100644 --- a/scripts/Makefile.headersinst +++ b/scripts/Makefile.headersinst @@ -39,9 +39,6 @@ skip-inst := $(if $(filter %/uapi,$(obj)),1) ifeq ($(skip-inst),) -# generated header directory -gen := $(if $(gen),$(gen),$(subst include/,include/generated/,$(obj))) - # Kbuild file is optional kbuild-file := $(srctree)/$(obj)/Kbuild -include $(kbuild-file) @@ -53,7 +50,7 @@ endif installdir := $(INSTALL_HDR_PATH)/$(subst uapi/,,$(_dst)) -gendir := $(objtree)/$(gen) +gendir := $(objtree)/$(subst include/,include/generated/,$(obj)) header-files := $(notdir $(wildcard $(srcdir)/*.h)) header-files += $(notdir $(wildcard $(srcdir)/*.agh)) header-files := $(filter-out $(no-export-headers), $(header-files)) -- cgit v1.2.3-59-g8ed1b From 0f042eea0a4a4fb1b1999784d745a47c0bb2c2f9 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:34 +0900 Subject: kbuild: fix comment about dst of headers_{install, check}_all Commit 61562f981e92 ("uapi: export all arch specifics directories") changed the dst from asm- to arch- for headers_install_all or headers_check_all. Update the comment. Signed-off-by: Masahiro Yamada --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 06ef9947cf7c..ce5875628740 100644 --- a/Makefile +++ b/Makefile @@ -1133,7 +1133,7 @@ firmware_install: #Default location for installed headers export INSTALL_HDR_PATH = $(objtree)/usr -# If we do an all arch process set dst to asm-$(hdr-arch) +# If we do an all arch process set dst to include/arch-$(hdr-arch) hdr-dst = $(if $(KBUILD_HEADERS), dst=include/arch-$(hdr-arch), dst=include) PHONY += archheaders -- cgit v1.2.3-59-g8ed1b From a8ff49a1d92da4eb566d026adc43946852975129 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:35 +0900 Subject: kbuild: pass dst= to Makefile.headersinst from top Makefile We can always pass dst= from the top Makefile. This will simplify the logic in Makefile.headersinst. Signed-off-by: Masahiro Yamada --- Makefile | 4 ++-- scripts/Makefile.headersinst | 8 ++------ 2 files changed, 4 insertions(+), 8 deletions(-) diff --git a/Makefile b/Makefile index ce5875628740..70c414b15859 100644 --- a/Makefile +++ b/Makefile @@ -1154,7 +1154,7 @@ PHONY += headers_install headers_install: __headers $(if $(wildcard $(srctree)/arch/$(hdr-arch)/include/uapi/asm/Kbuild),, \ $(error Headers not exportable for the $(SRCARCH) architecture)) - $(Q)$(MAKE) $(hdr-inst)=include/uapi + $(Q)$(MAKE) $(hdr-inst)=include/uapi dst=include $(Q)$(MAKE) $(hdr-inst)=arch/$(hdr-arch)/include/uapi $(hdr-dst) PHONY += headers_check_all @@ -1163,7 +1163,7 @@ headers_check_all: headers_install_all PHONY += headers_check headers_check: headers_install - $(Q)$(MAKE) $(hdr-inst)=include/uapi HDRCHECK=1 + $(Q)$(MAKE) $(hdr-inst)=include/uapi dst=include HDRCHECK=1 $(Q)$(MAKE) $(hdr-inst)=arch/$(hdr-arch)/include/uapi $(hdr-dst) HDRCHECK=1 # --------------------------------------------------------------------------- diff --git a/scripts/Makefile.headersinst b/scripts/Makefile.headersinst index 4e9287bfdf28..e9147f05ea77 100644 --- a/scripts/Makefile.headersinst +++ b/scripts/Makefile.headersinst @@ -23,15 +23,12 @@ subdirs := $(patsubst $(srcdir)/%/,%,\ $(filter-out $(srcdir)/,\ $(sort $(dir $(wildcard $(srcdir)/*/))))) -# caller may set destination dir (when installing to asm/) -_dst := $(if $(dst),$(dst),$(obj)) - # Recursion __headers: $(subdirs) .PHONY: $(subdirs) $(subdirs): - $(Q)$(MAKE) $(hdr-inst)=$(obj)/$@ dst=$(_dst)/$@ + $(Q)$(MAKE) $(hdr-inst)=$(obj)/$@ dst=$(dst)/$@ # Skip header install/check for include/uapi and arch/$(hdr-arch)/include/uapi. # We have only sub-directories there. @@ -48,8 +45,7 @@ ifneq ($(wildcard $(old-kbuild-file)),) include $(old-kbuild-file) endif -installdir := $(INSTALL_HDR_PATH)/$(subst uapi/,,$(_dst)) - +installdir := $(INSTALL_HDR_PATH)/$(dst) gendir := $(objtree)/$(subst include/,include/generated/,$(obj)) header-files := $(notdir $(wildcard $(srcdir)/*.h)) header-files += $(notdir $(wildcard $(srcdir)/*.agh)) -- cgit v1.2.3-59-g8ed1b From 7a7e98f4b341fc56cb352fd2bacfaecbc3f988fc Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:36 +0900 Subject: arm64: move generic-y of exported headers to uapi/asm/Kbuild Since commit fcc8487d477a ("uapi: export all headers under uapi directories"), all (and only) headers under uapi directories are exported, but asm-generic wrappers are still exceptions. To complete de-coupling the uapi from kernel headers, move generic-y of exported headers to uapi/asm/Kbuild. With this change, "make headers_install" will just need to parse uapi/asm/Kbuild to build up exported headers. For arm64, "generic-y += kvm_para.h" is doubled in asm/Kbuild and uapi/asm/Kbuild. So, the one in the former can be simply removed. Signed-off-by: Masahiro Yamada Acked-by: Catalin Marinas --- arch/arm64/include/asm/Kbuild | 17 ----------------- arch/arm64/include/uapi/asm/Kbuild | 16 ++++++++++++++++ 2 files changed, 16 insertions(+), 17 deletions(-) diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index a7a97a608033..f81c7b685fc6 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -6,41 +6,24 @@ generic-y += dma.h generic-y += dma-contiguous.h generic-y += early_ioremap.h generic-y += emergency-restart.h -generic-y += errno.h generic-y += hw_irq.h -generic-y += ioctl.h -generic-y += ioctls.h -generic-y += ipcbuf.h generic-y += irq_regs.h generic-y += kdebug.h generic-y += kmap_types.h -generic-y += kvm_para.h generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h -generic-y += mman.h -generic-y += msgbuf.h generic-y += msi.h -generic-y += poll.h generic-y += preempt.h -generic-y += resource.h generic-y += rwsem.h generic-y += segment.h -generic-y += sembuf.h generic-y += serial.h generic-y += set_memory.h -generic-y += shmbuf.h generic-y += simd.h generic-y += sizes.h -generic-y += socket.h -generic-y += sockios.h -generic-y += swab.h generic-y += switch_to.h -generic-y += termbits.h -generic-y += termios.h generic-y += trace_clock.h -generic-y += types.h generic-y += unaligned.h generic-y += user.h generic-y += vga.h diff --git a/arch/arm64/include/uapi/asm/Kbuild b/arch/arm64/include/uapi/asm/Kbuild index 13a97aa2285f..fc28bd95c6d3 100644 --- a/arch/arm64/include/uapi/asm/Kbuild +++ b/arch/arm64/include/uapi/asm/Kbuild @@ -1,4 +1,20 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += errno.h +generic-y += ioctl.h +generic-y += ioctls.h +generic-y += ipcbuf.h generic-y += kvm_para.h +generic-y += mman.h +generic-y += msgbuf.h +generic-y += poll.h +generic-y += resource.h +generic-y += sembuf.h +generic-y += shmbuf.h +generic-y += socket.h +generic-y += sockios.h +generic-y += swab.h +generic-y += termbits.h +generic-y += termios.h +generic-y += types.h -- cgit v1.2.3-59-g8ed1b From ae884913ac1a76366f84561a5e89f483365c0fb7 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:37 +0900 Subject: ARM: move generic-y of exported headers to uapi/asm/Kbuild Since commit fcc8487d477a ("uapi: export all headers under uapi directories"), all (and only) headers under uapi directories are exported, but asm-generic wrappers are still exceptions. To complete de-coupling the uapi from kernel headers, move generic-y of exported headers to uapi/asm/Kbuild. With this change, "make headers_install" will just need to parse uapi/asm/Kbuild to build up exported headers. Signed-off-by: Masahiro Yamada --- arch/arm/include/asm/Kbuild | 16 ---------------- arch/arm/include/uapi/asm/Kbuild | 14 ++++++++++++++ 2 files changed, 14 insertions(+), 16 deletions(-) diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild index d8360501c082..721ab5ecfb9b 100644 --- a/arch/arm/include/asm/Kbuild +++ b/arch/arm/include/asm/Kbuild @@ -1,39 +1,23 @@ - - -generic-y += bitsperlong.h generic-y += clkdev.h generic-y += current.h generic-y += early_ioremap.h generic-y += emergency-restart.h -generic-y += errno.h generic-y += exec.h generic-y += extable.h -generic-y += ioctl.h -generic-y += ipcbuf.h generic-y += irq_regs.h generic-y += kdebug.h generic-y += local.h generic-y += local64.h generic-y += mm-arch-hooks.h -generic-y += msgbuf.h generic-y += msi.h -generic-y += param.h generic-y += parport.h -generic-y += poll.h generic-y += preempt.h -generic-y += resource.h generic-y += rwsem.h generic-y += seccomp.h generic-y += segment.h -generic-y += sembuf.h generic-y += serial.h -generic-y += shmbuf.h generic-y += simd.h generic-y += sizes.h -generic-y += socket.h -generic-y += sockios.h -generic-y += termbits.h -generic-y += termios.h generic-y += timex.h generic-y += trace_clock.h generic-y += unaligned.h diff --git a/arch/arm/include/uapi/asm/Kbuild b/arch/arm/include/uapi/asm/Kbuild index 5fb3368e70cb..8e17fe80b55b 100644 --- a/arch/arm/include/uapi/asm/Kbuild +++ b/arch/arm/include/uapi/asm/Kbuild @@ -5,4 +5,18 @@ generated-y += unistd-common.h generated-y += unistd-oabi.h generated-y += unistd-eabi.h +generic-y += bitsperlong.h +generic-y += errno.h +generic-y += ioctl.h +generic-y += ipcbuf.h +generic-y += msgbuf.h +generic-y += param.h +generic-y += poll.h +generic-y += resource.h +generic-y += sembuf.h +generic-y += shmbuf.h generic-y += siginfo.h +generic-y += socket.h +generic-y += sockios.h +generic-y += termbits.h +generic-y += termios.h -- cgit v1.2.3-59-g8ed1b From 3e4f9376659d8646302a317848ffb3a12101aa89 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:38 +0900 Subject: arc: move generic-y of exported headers to uapi/asm/Kbuild Since commit fcc8487d477a ("uapi: export all headers under uapi directories"), all (and only) headers under uapi directories are exported, but asm-generic wrappers are still exceptions. To complete de-coupling the uapi from kernel headers, move generic-y of exported headers to uapi/asm/Kbuild. With this change, "make headers_install" will just need to parse uapi/asm/Kbuild to build up exported headers. Signed-off-by: Masahiro Yamada --- arch/arc/include/asm/Kbuild | 24 ------------------------ arch/arc/include/uapi/asm/Kbuild | 24 ++++++++++++++++++++++++ 2 files changed, 24 insertions(+), 24 deletions(-) diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild index 3e74ca5e6402..353dae386b2f 100644 --- a/arch/arc/include/asm/Kbuild +++ b/arch/arc/include/asm/Kbuild @@ -1,51 +1,27 @@ -generic-y += auxvec.h -generic-y += bitsperlong.h generic-y += bugs.h generic-y += clkdev.h generic-y += device.h generic-y += div64.h generic-y += emergency-restart.h -generic-y += errno.h generic-y += extable.h generic-y += fb.h -generic-y += fcntl.h generic-y += ftrace.h generic-y += hardirq.h generic-y += hw_irq.h -generic-y += ioctl.h -generic-y += ioctls.h -generic-y += ipcbuf.h generic-y += irq_regs.h generic-y += irq_work.h generic-y += kmap_types.h -generic-y += kvm_para.h generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h -generic-y += mman.h -generic-y += msgbuf.h generic-y += msi.h -generic-y += param.h generic-y += parport.h generic-y += pci.h generic-y += percpu.h -generic-y += poll.h -generic-y += posix_types.h generic-y += preempt.h -generic-y += resource.h -generic-y += sembuf.h -generic-y += shmbuf.h -generic-y += socket.h -generic-y += sockios.h -generic-y += stat.h -generic-y += statfs.h -generic-y += termbits.h -generic-y += termios.h generic-y += topology.h generic-y += trace_clock.h -generic-y += types.h -generic-y += ucontext.h generic-y += user.h generic-y += vga.h generic-y += word-at-a-time.h diff --git a/arch/arc/include/uapi/asm/Kbuild b/arch/arc/include/uapi/asm/Kbuild index b55fc2ae1e8c..fa6d0ff4ff89 100644 --- a/arch/arc/include/uapi/asm/Kbuild +++ b/arch/arc/include/uapi/asm/Kbuild @@ -1,4 +1,28 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += auxvec.h +generic-y += bitsperlong.h +generic-y += errno.h +generic-y += fcntl.h +generic-y += ioctl.h +generic-y += ioctls.h +generic-y += ipcbuf.h +generic-y += kvm_para.h +generic-y += mman.h +generic-y += msgbuf.h +generic-y += param.h +generic-y += poll.h +generic-y += posix_types.h +generic-y += resource.h +generic-y += sembuf.h +generic-y += shmbuf.h generic-y += siginfo.h +generic-y += socket.h +generic-y += sockios.h +generic-y += stat.h +generic-y += statfs.h +generic-y += termbits.h +generic-y += termios.h +generic-y += types.h +generic-y += ucontext.h -- cgit v1.2.3-59-g8ed1b From 6b4be36250b7fd14f717a61ae3e72f4ba6bdfe04 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:39 +0900 Subject: blackfin: move generic-y of exported headers to uapi/asm/Kbuild Since commit fcc8487d477a ("uapi: export all headers under uapi directories"), all (and only) headers under uapi directories are exported, but asm-generic wrappers are still exceptions. To complete de-coupling the uapi from kernel headers, move generic-y of exported headers to uapi/asm/Kbuild. With this change, "make headers_install" will just need to parse uapi/asm/Kbuild to build up exported headers. Also, move "generic-y += kprobes.h" up in order to keep the entries sorted. Signed-off-by: Masahiro Yamada --- arch/blackfin/include/asm/Kbuild | 24 +----------------------- arch/blackfin/include/uapi/asm/Kbuild | 22 ++++++++++++++++++++++ 2 files changed, 23 insertions(+), 23 deletions(-) diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild index dc4ef9ac1e83..fe736973630f 100644 --- a/arch/blackfin/include/asm/Kbuild +++ b/arch/blackfin/include/asm/Kbuild @@ -1,50 +1,28 @@ - -generic-y += auxvec.h -generic-y += bitsperlong.h generic-y += bugs.h generic-y += current.h generic-y += device.h generic-y += div64.h generic-y += emergency-restart.h -generic-y += errno.h generic-y += extable.h generic-y += fb.h generic-y += futex.h generic-y += hw_irq.h -generic-y += ioctl.h -generic-y += ipcbuf.h generic-y += irq_regs.h generic-y += irq_work.h generic-y += kdebug.h generic-y += kmap_types.h -generic-y += kvm_para.h +generic-y += kprobes.h generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h -generic-y += mman.h -generic-y += msgbuf.h -generic-y += param.h generic-y += percpu.h generic-y += pgalloc.h generic-y += preempt.h -generic-y += resource.h -generic-y += sembuf.h generic-y += serial.h -generic-y += setup.h -generic-y += shmbuf.h -generic-y += shmparam.h -generic-y += socket.h -generic-y += sockios.h -generic-y += statfs.h -generic-y += termbits.h -generic-y += termios.h generic-y += topology.h generic-y += trace_clock.h -generic-y += types.h -generic-y += ucontext.h generic-y += unaligned.h generic-y += user.h generic-y += word-at-a-time.h generic-y += xor.h -generic-y += kprobes.h diff --git a/arch/blackfin/include/uapi/asm/Kbuild b/arch/blackfin/include/uapi/asm/Kbuild index b15bf6bc0e94..aa624b4ab655 100644 --- a/arch/blackfin/include/uapi/asm/Kbuild +++ b/arch/blackfin/include/uapi/asm/Kbuild @@ -1,2 +1,24 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm + +generic-y += auxvec.h +generic-y += bitsperlong.h +generic-y += errno.h +generic-y += ioctl.h +generic-y += ipcbuf.h +generic-y += kvm_para.h +generic-y += mman.h +generic-y += msgbuf.h +generic-y += param.h +generic-y += resource.h +generic-y += sembuf.h +generic-y += setup.h +generic-y += shmbuf.h +generic-y += shmparam.h +generic-y += socket.h +generic-y += sockios.h +generic-y += statfs.h +generic-y += termbits.h +generic-y += termios.h +generic-y += types.h +generic-y += ucontext.h -- cgit v1.2.3-59-g8ed1b From 97b81556f656594b343d516158ea305d4e0dcae5 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:40 +0900 Subject: c6x: move generic-y of exported headers to uapi/asm/Kbuild Since commit fcc8487d477a ("uapi: export all headers under uapi directories"), all (and only) headers under uapi directories are exported, but asm-generic wrappers are still exceptions. To complete de-coupling the uapi from kernel headers, move generic-y of exported headers to uapi/asm/Kbuild. With this change, "make headers_install" will just need to parse uapi/asm/Kbuild to build up exported headers. Also, move "generic-y += kprobes.h" up in order to keep the entries sorted. Signed-off-by: Masahiro Yamada --- arch/c6x/include/asm/Kbuild | 28 +--------------------------- arch/c6x/include/uapi/asm/Kbuild | 25 +++++++++++++++++++++++++ 2 files changed, 26 insertions(+), 27 deletions(-) diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild index a3c8d05c4cc7..d717329c8cf9 100644 --- a/arch/c6x/include/asm/Kbuild +++ b/arch/c6x/include/asm/Kbuild @@ -1,8 +1,5 @@ - generic-y += atomic.h -generic-y += auxvec.h generic-y += barrier.h -generic-y += bitsperlong.h generic-y += bugs.h generic-y += clkdev.h generic-y += current.h @@ -10,55 +7,32 @@ generic-y += device.h generic-y += div64.h generic-y += dma.h generic-y += emergency-restart.h -generic-y += errno.h generic-y += exec.h generic-y += extable.h generic-y += fb.h -generic-y += fcntl.h generic-y += futex.h generic-y += hw_irq.h generic-y += io.h -generic-y += ioctl.h -generic-y += ioctls.h -generic-y += ipcbuf.h generic-y += irq_regs.h generic-y += irq_work.h generic-y += kdebug.h generic-y += kmap_types.h +generic-y += kprobes.h generic-y += local.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h -generic-y += mman.h generic-y += mmu.h generic-y += mmu_context.h -generic-y += msgbuf.h -generic-y += param.h generic-y += pci.h generic-y += percpu.h generic-y += pgalloc.h -generic-y += poll.h -generic-y += posix_types.h generic-y += preempt.h -generic-y += resource.h generic-y += segment.h -generic-y += sembuf.h generic-y += serial.h -generic-y += shmbuf.h -generic-y += shmparam.h -generic-y += signal.h -generic-y += socket.h -generic-y += sockios.h -generic-y += stat.h -generic-y += statfs.h -generic-y += termbits.h -generic-y += termios.h generic-y += tlbflush.h generic-y += topology.h generic-y += trace_clock.h -generic-y += types.h -generic-y += ucontext.h generic-y += user.h generic-y += vga.h generic-y += word-at-a-time.h generic-y += xor.h -generic-y += kprobes.h diff --git a/arch/c6x/include/uapi/asm/Kbuild b/arch/c6x/include/uapi/asm/Kbuild index 1c44d3b3eba0..67ee896a76a7 100644 --- a/arch/c6x/include/uapi/asm/Kbuild +++ b/arch/c6x/include/uapi/asm/Kbuild @@ -1,5 +1,30 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += auxvec.h +generic-y += bitsperlong.h +generic-y += errno.h +generic-y += fcntl.h +generic-y += ioctl.h +generic-y += ioctls.h +generic-y += ipcbuf.h generic-y += kvm_para.h +generic-y += mman.h +generic-y += msgbuf.h +generic-y += param.h +generic-y += poll.h +generic-y += posix_types.h +generic-y += resource.h +generic-y += sembuf.h +generic-y += shmbuf.h +generic-y += shmparam.h generic-y += siginfo.h +generic-y += signal.h +generic-y += socket.h +generic-y += sockios.h +generic-y += stat.h +generic-y += statfs.h +generic-y += termbits.h +generic-y += termios.h +generic-y += types.h +generic-y += ucontext.h -- cgit v1.2.3-59-g8ed1b From c6ec85cefb476e4ab914d18951fa4c04d96b3bb6 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:41 +0900 Subject: cris: move generic-y of exported headers to uapi/asm/Kbuild Since commit fcc8487d477a ("uapi: export all headers under uapi directories"), all (and only) headers under uapi directories are exported, but asm-generic wrappers are still exceptions. To complete de-coupling the uapi from kernel headers, move generic-y of exported headers to uapi/asm/Kbuild. With this change, "make headers_install" will just need to parse uapi/asm/Kbuild to build up exported headers. Also, move "generic-y += kprobes.h", "generic-y += emergency-restart.h" up in order to keep the entries sorted. Signed-off-by: Masahiro Yamada --- arch/cris/include/asm/Kbuild | 21 ++------------------- arch/cris/include/uapi/asm/Kbuild | 17 +++++++++++++++++ 2 files changed, 19 insertions(+), 19 deletions(-) diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild index acc5781100c2..460349cb147f 100644 --- a/arch/cris/include/asm/Kbuild +++ b/arch/cris/include/asm/Kbuild @@ -1,48 +1,31 @@ generic-y += atomic.h -generic-y += auxvec.h generic-y += barrier.h -generic-y += bitsperlong.h generic-y += clkdev.h generic-y += cmpxchg.h generic-y += current.h generic-y += device.h generic-y += div64.h -generic-y += errno.h +generic-y += emergency-restart.h generic-y += exec.h generic-y += extable.h -generic-y += emergency-restart.h -generic-y += fcntl.h generic-y += futex.h generic-y += hardirq.h -generic-y += ioctl.h -generic-y += ipcbuf.h generic-y += irq_regs.h generic-y += irq_work.h generic-y += kdebug.h generic-y += kmap_types.h -generic-y += kvm_para.h +generic-y += kprobes.h generic-y += linkage.h generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h -generic-y += mman.h generic-y += module.h -generic-y += msgbuf.h generic-y += percpu.h -generic-y += poll.h generic-y += preempt.h -generic-y += resource.h generic-y += sections.h -generic-y += sembuf.h -generic-y += shmbuf.h -generic-y += socket.h -generic-y += sockios.h -generic-y += statfs.h generic-y += topology.h generic-y += trace_clock.h -generic-y += types.h generic-y += vga.h generic-y += word-at-a-time.h generic-y += xor.h -generic-y += kprobes.h diff --git a/arch/cris/include/uapi/asm/Kbuild b/arch/cris/include/uapi/asm/Kbuild index b55fc2ae1e8c..3687b54bb18e 100644 --- a/arch/cris/include/uapi/asm/Kbuild +++ b/arch/cris/include/uapi/asm/Kbuild @@ -1,4 +1,21 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += auxvec.h +generic-y += bitsperlong.h +generic-y += errno.h +generic-y += fcntl.h +generic-y += ioctl.h +generic-y += ipcbuf.h +generic-y += kvm_para.h +generic-y += mman.h +generic-y += msgbuf.h +generic-y += poll.h +generic-y += resource.h +generic-y += sembuf.h +generic-y += shmbuf.h generic-y += siginfo.h +generic-y += socket.h +generic-y += sockios.h +generic-y += statfs.h +generic-y += types.h -- cgit v1.2.3-59-g8ed1b From c26e2c0c6d2728377d7219095676dc372a421c1c Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:42 +0900 Subject: h8300: move generic-y of exported headers to uapi/asm/Kbuild Since commit fcc8487d477a ("uapi: export all headers under uapi directories"), all (and only) headers under uapi directories are exported, but asm-generic wrappers are still exceptions. To complete de-coupling the uapi from kernel headers, move generic-y of exported headers to uapi/asm/Kbuild. With this change, "make headers_install" will just need to parse uapi/asm/Kbuild to build up exported headers. Also, move "generic-y += kprobes.h" and "generic-y += trace_clock.h" in order to keep the entries sorted. Signed-off-by: Masahiro Yamada --- arch/h8300/include/asm/Kbuild | 30 ++---------------------------- arch/h8300/include/uapi/asm/Kbuild | 26 ++++++++++++++++++++++++++ 2 files changed, 28 insertions(+), 28 deletions(-) diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild index 99c824608a31..bc077491d299 100644 --- a/arch/h8300/include/asm/Kbuild +++ b/arch/h8300/include/asm/Kbuild @@ -1,5 +1,4 @@ generic-y += asm-offsets.h -generic-y += auxvec.h generic-y += barrier.h generic-y += bugs.h generic-y += cacheflush.h @@ -11,66 +10,41 @@ generic-y += device.h generic-y += div64.h generic-y += dma.h generic-y += emergency-restart.h -generic-y += errno.h generic-y += exec.h generic-y += extable.h generic-y += fb.h -generic-y += fcntl.h generic-y += ftrace.h generic-y += futex.h generic-y += hardirq.h generic-y += hash.h generic-y += hw_irq.h -generic-y += ioctl.h -generic-y += ioctls.h -generic-y += ipcbuf.h generic-y += irq_regs.h generic-y += irq_work.h generic-y += kdebug.h generic-y += kmap_types.h -generic-y += kvm_para.h +generic-y += kprobes.h generic-y += linkage.h generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h -generic-y += mman.h generic-y += mmu.h generic-y += mmu_context.h generic-y += module.h -generic-y += msgbuf.h -generic-y += param.h generic-y += parport.h generic-y += percpu.h generic-y += pgalloc.h -generic-y += poll.h -generic-y += posix_types.h generic-y += preempt.h -generic-y += resource.h generic-y += scatterlist.h generic-y += sections.h -generic-y += sembuf.h generic-y += serial.h -generic-y += setup.h -generic-y += shmbuf.h -generic-y += shmparam.h generic-y += sizes.h -generic-y += socket.h -generic-y += sockios.h generic-y += spinlock.h -generic-y += stat.h -generic-y += statfs.h -generic-y += swab.h -generic-y += termbits.h -generic-y += termios.h generic-y += timex.h generic-y += tlbflush.h -generic-y += trace_clock.h generic-y += topology.h -generic-y += types.h -generic-y += ucontext.h +generic-y += trace_clock.h generic-y += unaligned.h generic-y += vga.h generic-y += word-at-a-time.h generic-y += xor.h -generic-y += kprobes.h diff --git a/arch/h8300/include/uapi/asm/Kbuild b/arch/h8300/include/uapi/asm/Kbuild index b55fc2ae1e8c..187aed820e71 100644 --- a/arch/h8300/include/uapi/asm/Kbuild +++ b/arch/h8300/include/uapi/asm/Kbuild @@ -1,4 +1,30 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += auxvec.h +generic-y += errno.h +generic-y += fcntl.h +generic-y += ioctl.h +generic-y += ioctls.h +generic-y += ipcbuf.h +generic-y += kvm_para.h +generic-y += mman.h +generic-y += msgbuf.h +generic-y += param.h +generic-y += poll.h +generic-y += posix_types.h +generic-y += resource.h +generic-y += sembuf.h +generic-y += setup.h +generic-y += shmbuf.h +generic-y += shmparam.h generic-y += siginfo.h +generic-y += socket.h +generic-y += sockios.h +generic-y += stat.h +generic-y += statfs.h +generic-y += swab.h +generic-y += termbits.h +generic-y += termios.h +generic-y += types.h +generic-y += ucontext.h -- cgit v1.2.3-59-g8ed1b From e4c694a3b07de1f193387121c7cae717ff7f4483 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:43 +0900 Subject: hexagon: move generic-y of exported headers to uapi/asm/Kbuild Since commit fcc8487d477a ("uapi: export all headers under uapi directories"), all (and only) headers under uapi directories are exported, but asm-generic wrappers are still exceptions. To complete de-coupling the uapi from kernel headers, move generic-y of exported headers to uapi/asm/Kbuild. With this change, "make headers_install" will just need to parse uapi/asm/Kbuild to build up exported headers. Also, move "generic-y += kprobes.h" up in order to keep the entries sorted. Signed-off-by: Masahiro Yamada --- arch/hexagon/include/asm/Kbuild | 24 +----------------------- arch/hexagon/include/uapi/asm/Kbuild | 22 ++++++++++++++++++++++ 2 files changed, 23 insertions(+), 23 deletions(-) diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild index 0fc9cb04e6ad..34013683d123 100644 --- a/arch/hexagon/include/asm/Kbuild +++ b/arch/hexagon/include/asm/Kbuild @@ -1,4 +1,3 @@ -generic-y += auxvec.h generic-y += barrier.h generic-y += bug.h generic-y += bugs.h @@ -7,53 +6,32 @@ generic-y += current.h generic-y += device.h generic-y += div64.h generic-y += emergency-restart.h -generic-y += errno.h generic-y += extable.h generic-y += fb.h -generic-y += fcntl.h generic-y += ftrace.h generic-y += hardirq.h generic-y += hw_irq.h -generic-y += ioctl.h -generic-y += ioctls.h generic-y += iomap.h -generic-y += ipcbuf.h generic-y += irq_regs.h generic-y += irq_work.h generic-y += kdebug.h generic-y += kmap_types.h +generic-y += kprobes.h generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h -generic-y += mman.h -generic-y += msgbuf.h generic-y += pci.h generic-y += percpu.h -generic-y += poll.h -generic-y += posix_types.h generic-y += preempt.h -generic-y += resource.h generic-y += rwsem.h generic-y += sections.h generic-y += segment.h -generic-y += sembuf.h generic-y += serial.h -generic-y += shmbuf.h -generic-y += shmparam.h generic-y += sizes.h -generic-y += socket.h -generic-y += sockios.h -generic-y += stat.h -generic-y += statfs.h -generic-y += termbits.h -generic-y += termios.h generic-y += topology.h generic-y += trace_clock.h -generic-y += types.h -generic-y += ucontext.h generic-y += unaligned.h generic-y += vga.h generic-y += word-at-a-time.h generic-y += xor.h -generic-y += kprobes.h diff --git a/arch/hexagon/include/uapi/asm/Kbuild b/arch/hexagon/include/uapi/asm/Kbuild index b55fc2ae1e8c..cb5df3aad3a8 100644 --- a/arch/hexagon/include/uapi/asm/Kbuild +++ b/arch/hexagon/include/uapi/asm/Kbuild @@ -1,4 +1,26 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += auxvec.h +generic-y += errno.h +generic-y += fcntl.h +generic-y += ioctl.h +generic-y += ioctls.h +generic-y += ipcbuf.h +generic-y += mman.h +generic-y += msgbuf.h +generic-y += poll.h +generic-y += posix_types.h +generic-y += resource.h +generic-y += sembuf.h +generic-y += shmbuf.h +generic-y += shmparam.h generic-y += siginfo.h +generic-y += socket.h +generic-y += sockios.h +generic-y += stat.h +generic-y += statfs.h +generic-y += termbits.h +generic-y += termios.h +generic-y += types.h +generic-y += ucontext.h -- cgit v1.2.3-59-g8ed1b From e18e340fd171fbb9bd38125c3d0ba5d3fd3ddfb9 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:44 +0900 Subject: ia64: remove redundant generic-y += kvm_para.h from asm/Kbuild "generic-y += kvm_para.h" is doubled in asm/Kbuild and uapi/asm/Kbuild. The one in the former should be simply removed because kvm_para.h is exported. Signed-off-by: Masahiro Yamada --- arch/ia64/include/asm/Kbuild | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild index 502a91d8dbbd..1d7641f891e1 100644 --- a/arch/ia64/include/asm/Kbuild +++ b/arch/ia64/include/asm/Kbuild @@ -1,8 +1,6 @@ - generic-y += clkdev.h generic-y += exec.h generic-y += irq_work.h -generic-y += kvm_para.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += preempt.h -- cgit v1.2.3-59-g8ed1b From e64f6ead4b8a0d096ca47cf3e3f4ace070476c2b Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:45 +0900 Subject: m32r: move generic-y of exported headers to uapi/asm/Kbuild Since commit fcc8487d477a ("uapi: export all headers under uapi directories"), all (and only) headers under uapi directories are exported, but asm-generic wrappers are still exceptions. To complete de-coupling the uapi from kernel headers, move generic-y of exported headers to uapi/asm/Kbuild. With this change, "make headers_install" will just need to parse uapi/asm/Kbuild to build up exported headers. Also, move "generic-y += kprobes.h" up in order to keep the entries sorted. Signed-off-by: Masahiro Yamada --- arch/m32r/include/asm/Kbuild | 4 +--- arch/m32r/include/uapi/asm/Kbuild | 3 ++- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild index c000ffac8586..7e11b125c35e 100644 --- a/arch/m32r/include/asm/Kbuild +++ b/arch/m32r/include/asm/Kbuild @@ -1,10 +1,9 @@ - generic-y += clkdev.h generic-y += current.h generic-y += exec.h generic-y += extable.h generic-y += irq_work.h -generic-y += kvm_para.h +generic-y += kprobes.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += module.h @@ -12,4 +11,3 @@ generic-y += preempt.h generic-y += sections.h generic-y += trace_clock.h generic-y += word-at-a-time.h -generic-y += kprobes.h diff --git a/arch/m32r/include/uapi/asm/Kbuild b/arch/m32r/include/uapi/asm/Kbuild index c94ee54210bc..1c44d3b3eba0 100644 --- a/arch/m32r/include/uapi/asm/Kbuild +++ b/arch/m32r/include/uapi/asm/Kbuild @@ -1,4 +1,5 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm -generic-y += siginfo.h +generic-y += kvm_para.h +generic-y += siginfo.h -- cgit v1.2.3-59-g8ed1b From 5608e72dfde31a6c2e051092f7aac026794971b8 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:46 +0900 Subject: m68k: move generic-y of exported headers to uapi/asm/Kbuild Since commit fcc8487d477a ("uapi: export all headers under uapi directories"), all (and only) headers under uapi directories are exported, but asm-generic wrappers are still exceptions. To complete de-coupling the uapi from kernel headers, move generic-y of exported headers to uapi/asm/Kbuild. With this change, "make headers_install" will just need to parse uapi/asm/Kbuild to build up exported headers. For m68k, "generic-y += termios.h" is doubled in asm/Kbuild and uapi/asm/Kbuild. So, the one in the former can be simply removed. Also, move "generic-y += kprobes.h" up in order to keep the entries sorted. Signed-off-by: Masahiro Yamada Acked-by: Geert Uytterhoeven --- arch/m68k/include/asm/Kbuild | 13 +------------ arch/m68k/include/uapi/asm/Kbuild | 10 ++++++++++ 2 files changed, 11 insertions(+), 12 deletions(-) diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index 5ecf4e47b2e2..59d6d0d38f67 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -1,36 +1,25 @@ generic-y += barrier.h -generic-y += bitsperlong.h generic-y += clkdev.h generic-y += device.h generic-y += emergency-restart.h -generic-y += errno.h generic-y += exec.h generic-y += extable.h generic-y += futex.h generic-y += hw_irq.h -generic-y += ioctl.h -generic-y += ipcbuf.h generic-y += irq_regs.h generic-y += irq_work.h generic-y += kdebug.h generic-y += kmap_types.h -generic-y += kvm_para.h +generic-y += kprobes.h generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h -generic-y += mman.h generic-y += percpu.h generic-y += preempt.h -generic-y += resource.h generic-y += sections.h -generic-y += shmparam.h generic-y += spinlock.h -generic-y += statfs.h -generic-y += termios.h generic-y += topology.h generic-y += trace_clock.h -generic-y += types.h generic-y += word-at-a-time.h generic-y += xor.h -generic-y += kprobes.h diff --git a/arch/m68k/include/uapi/asm/Kbuild b/arch/m68k/include/uapi/asm/Kbuild index 68b45cc87e2c..3717b64a620d 100644 --- a/arch/m68k/include/uapi/asm/Kbuild +++ b/arch/m68k/include/uapi/asm/Kbuild @@ -2,11 +2,21 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += auxvec.h +generic-y += bitsperlong.h +generic-y += errno.h +generic-y += ioctl.h +generic-y += ipcbuf.h +generic-y += kvm_para.h +generic-y += mman.h generic-y += msgbuf.h +generic-y += resource.h generic-y += sembuf.h generic-y += shmbuf.h +generic-y += shmparam.h generic-y += siginfo.h generic-y += socket.h generic-y += sockios.h +generic-y += statfs.h generic-y += termbits.h generic-y += termios.h +generic-y += types.h -- cgit v1.2.3-59-g8ed1b From d4442e42e5de2314084d0cca0d0eab08daac21af Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:47 +0900 Subject: metag: move generic-y of exported headers to uapi/asm/Kbuild Since commit fcc8487d477a ("uapi: export all headers under uapi directories"), all (and only) headers under uapi directories are exported, but asm-generic wrappers are still exceptions. To complete de-coupling the uapi from kernel headers, move generic-y of exported headers to uapi/asm/Kbuild. With this change, "make headers_install" will just need to parse uapi/asm/Kbuild to build up exported headers. Also, move "generic-y += kprobes.h" up in order to keep the entries sorted. Signed-off-by: Masahiro Yamada --- arch/metag/include/asm/Kbuild | 26 +------------------------- arch/metag/include/uapi/asm/Kbuild | 24 ++++++++++++++++++++++++ 2 files changed, 25 insertions(+), 25 deletions(-) diff --git a/arch/metag/include/asm/Kbuild b/arch/metag/include/asm/Kbuild index 8f940553a579..3fba97ed9bb2 100644 --- a/arch/metag/include/asm/Kbuild +++ b/arch/metag/include/asm/Kbuild @@ -1,58 +1,34 @@ -generic-y += auxvec.h -generic-y += bitsperlong.h generic-y += bugs.h generic-y += clkdev.h generic-y += current.h generic-y += device.h generic-y += dma.h generic-y += emergency-restart.h -generic-y += errno.h generic-y += exec.h generic-y += extable.h generic-y += fb.h -generic-y += fcntl.h generic-y += futex.h generic-y += hardirq.h generic-y += hw_irq.h -generic-y += ioctl.h -generic-y += ioctls.h -generic-y += ipcbuf.h generic-y += irq_regs.h generic-y += irq_work.h generic-y += kdebug.h generic-y += kmap_types.h -generic-y += kvm_para.h +generic-y += kprobes.h generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h -generic-y += msgbuf.h -generic-y += param.h generic-y += pci.h generic-y += percpu.h -generic-y += poll.h -generic-y += posix_types.h generic-y += preempt.h generic-y += sections.h -generic-y += sembuf.h generic-y += serial.h -generic-y += shmbuf.h -generic-y += shmparam.h -generic-y += signal.h -generic-y += socket.h -generic-y += sockios.h -generic-y += stat.h -generic-y += statfs.h generic-y += switch_to.h -generic-y += termbits.h -generic-y += termios.h generic-y += timex.h generic-y += trace_clock.h -generic-y += types.h -generic-y += ucontext.h generic-y += unaligned.h generic-y += user.h generic-y += vga.h generic-y += word-at-a-time.h generic-y += xor.h -generic-y += kprobes.h diff --git a/arch/metag/include/uapi/asm/Kbuild b/arch/metag/include/uapi/asm/Kbuild index b29731ebd7a9..6ac763d9a3e3 100644 --- a/arch/metag/include/uapi/asm/Kbuild +++ b/arch/metag/include/uapi/asm/Kbuild @@ -1,6 +1,30 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += auxvec.h +generic-y += bitsperlong.h +generic-y += errno.h +generic-y += fcntl.h +generic-y += ioctl.h +generic-y += ioctls.h +generic-y += ipcbuf.h +generic-y += kvm_para.h generic-y += mman.h +generic-y += msgbuf.h +generic-y += param.h +generic-y += poll.h +generic-y += posix_types.h generic-y += resource.h +generic-y += sembuf.h generic-y += setup.h +generic-y += shmbuf.h +generic-y += shmparam.h +generic-y += signal.h +generic-y += socket.h +generic-y += sockios.h +generic-y += stat.h +generic-y += statfs.h +generic-y += termbits.h +generic-y += termios.h +generic-y += types.h +generic-y += ucontext.h -- cgit v1.2.3-59-g8ed1b From 9ffd93852fc66f2bdf61a574db107f106e9fb2ff Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:48 +0900 Subject: microblaze: move generic-y of exported headers to uapi/asm/Kbuild Since commit fcc8487d477a ("uapi: export all headers under uapi directories"), all (and only) headers under uapi directories are exported, but asm-generic wrappers are still exceptions. To complete de-coupling the uapi from kernel headers, move generic-y of exported headers to uapi/asm/Kbuild. With this change, "make headers_install" will just need to parse uapi/asm/Kbuild to build up exported headers. For microblaze, "generic-y += siginfo.h" is doubled in asm/Kbuild and uapi/asm/Kbuild. So, the one in the former can be simply removed. Signed-off-by: Masahiro Yamada --- arch/microblaze/include/asm/Kbuild | 25 ------------------------- arch/microblaze/include/uapi/asm/Kbuild | 25 ++++++++++++++++++++++++- 2 files changed, 24 insertions(+), 26 deletions(-) diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index 83a4ef3a2495..9d66f7793841 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -1,22 +1,15 @@ - generic-y += barrier.h generic-y += bitops.h -generic-y += bitsperlong.h generic-y += bug.h generic-y += bugs.h generic-y += clkdev.h generic-y += device.h generic-y += div64.h generic-y += emergency-restart.h -generic-y += errno.h generic-y += exec.h generic-y += extable.h generic-y += fb.h -generic-y += fcntl.h generic-y += hardirq.h -generic-y += ioctl.h -generic-y += ioctls.h -generic-y += ipcbuf.h generic-y += irq_regs.h generic-y += irq_work.h generic-y += kdebug.h @@ -27,31 +20,13 @@ generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h -generic-y += mman.h -generic-y += msgbuf.h -generic-y += param.h generic-y += parport.h generic-y += percpu.h -generic-y += poll.h generic-y += preempt.h -generic-y += resource.h -generic-y += sembuf.h generic-y += serial.h -generic-y += shmbuf.h -generic-y += shmparam.h -generic-y += siginfo.h -generic-y += signal.h -generic-y += socket.h -generic-y += sockios.h -generic-y += stat.h -generic-y += statfs.h -generic-y += swab.h generic-y += syscalls.h -generic-y += termbits.h -generic-y += termios.h generic-y += topology.h generic-y += trace_clock.h -generic-y += ucontext.h generic-y += vga.h generic-y += word-at-a-time.h generic-y += xor.h diff --git a/arch/microblaze/include/uapi/asm/Kbuild b/arch/microblaze/include/uapi/asm/Kbuild index cb6784f4a427..e77a596f3f1e 100644 --- a/arch/microblaze/include/uapi/asm/Kbuild +++ b/arch/microblaze/include/uapi/asm/Kbuild @@ -1,5 +1,28 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm -generic-y += types.h +generic-y += bitsperlong.h +generic-y += errno.h +generic-y += fcntl.h +generic-y += ioctl.h +generic-y += ioctls.h +generic-y += ipcbuf.h +generic-y += mman.h +generic-y += msgbuf.h +generic-y += param.h +generic-y += poll.h +generic-y += resource.h +generic-y += sembuf.h +generic-y += shmbuf.h +generic-y += shmparam.h generic-y += siginfo.h +generic-y += signal.h +generic-y += socket.h +generic-y += sockios.h +generic-y += stat.h +generic-y += statfs.h +generic-y += swab.h +generic-y += termbits.h +generic-y += termios.h +generic-y += types.h +generic-y += ucontext.h -- cgit v1.2.3-59-g8ed1b From c96396f0780e3b217f5194538e6dcd3c22d00122 Mon Sep 17 00:00:00 2001 From: Benjamin Gaignard Date: Mon, 19 Jun 2017 11:36:20 +0200 Subject: tools: timer: add rtctest_setdate This tool allow to set directly the time and date to a RTC device. Unlike other tools isn't doens't use "struct timeval" or "time_t" so it is safe for 32bits platforms when testing for y2038/2106 bug. Signed-off-by: Benjamin Gaignard Signed-off-by: Alexandre Belloni --- tools/testing/selftests/timers/Makefile | 2 +- tools/testing/selftests/timers/rtctest_setdate.c | 86 ++++++++++++++++++++++++ 2 files changed, 87 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/timers/rtctest_setdate.c diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile index 5fa1d7e9a915..54481f17518a 100644 --- a/tools/testing/selftests/timers/Makefile +++ b/tools/testing/selftests/timers/Makefile @@ -9,7 +9,7 @@ TEST_GEN_PROGS = posix_timers nanosleep nsleep-lat set-timer-lat mqueue-lat \ TEST_GEN_PROGS_EXTENDED = alarmtimer-suspend valid-adjtimex adjtick change_skew \ skew_consistency clocksource-switch leap-a-day \ - leapcrash set-tai set-2038 set-tz + leapcrash set-tai set-2038 set-tz rtctest_setdate include ../lib.mk diff --git a/tools/testing/selftests/timers/rtctest_setdate.c b/tools/testing/selftests/timers/rtctest_setdate.c new file mode 100644 index 000000000000..2cb78489eca4 --- /dev/null +++ b/tools/testing/selftests/timers/rtctest_setdate.c @@ -0,0 +1,86 @@ +/* Real Time Clock Driver Test + * by: Benjamin Gaignard (benjamin.gaignard@linaro.org) + * + * To build + * gcc rtctest_setdate.c -o rtctest_setdate + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static const char default_time[] = "00:00:00"; + +int main(int argc, char **argv) +{ + int fd, retval; + struct rtc_time new, current; + const char *rtc, *date; + const char *time = default_time; + + switch (argc) { + case 4: + time = argv[3]; + /* FALLTHROUGH */ + case 3: + date = argv[2]; + rtc = argv[1]; + break; + default: + fprintf(stderr, "usage: rtctest_setdate [HH:MM:SS]\n"); + return 1; + } + + fd = open(rtc, O_RDONLY); + if (fd == -1) { + perror(rtc); + exit(errno); + } + + sscanf(date, "%d-%d-%d", &new.tm_mday, &new.tm_mon, &new.tm_year); + new.tm_mon -= 1; + new.tm_year -= 1900; + sscanf(time, "%d:%d:%d", &new.tm_hour, &new.tm_min, &new.tm_sec); + + fprintf(stderr, "Test will set RTC date/time to %d-%d-%d, %02d:%02d:%02d.\n", + new.tm_mday, new.tm_mon + 1, new.tm_year + 1900, + new.tm_hour, new.tm_min, new.tm_sec); + + /* Write the new date in RTC */ + retval = ioctl(fd, RTC_SET_TIME, &new); + if (retval == -1) { + perror("RTC_SET_TIME ioctl"); + close(fd); + exit(errno); + } + + /* Read back */ + retval = ioctl(fd, RTC_RD_TIME, ¤t); + if (retval == -1) { + perror("RTC_RD_TIME ioctl"); + exit(errno); + } + + fprintf(stderr, "\n\nCurrent RTC date/time is %d-%d-%d, %02d:%02d:%02d.\n", + current.tm_mday, current.tm_mon + 1, current.tm_year + 1900, + current.tm_hour, current.tm_min, current.tm_sec); + + close(fd); + return 0; +} -- cgit v1.2.3-59-g8ed1b From 69c31226fc9f887dcd5c27a91f5cc0f244a6953e Mon Sep 17 00:00:00 2001 From: Benjamin Gaignard Date: Mon, 19 Jun 2017 11:36:21 +0200 Subject: rtc: rtctest: add check for problematic dates Some dates could be problematic because they reach the limits of RTC hardware capabilities. This patch add various of them but since it will change RTC date it will be activated only when 'd' args is set. Signed-off-by: Benjamin Gaignard Signed-off-by: Alexandre Belloni --- tools/testing/selftests/timers/rtctest.c | 128 ++++++++++++++++++++++++++++++- 1 file changed, 124 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/timers/rtctest.c b/tools/testing/selftests/timers/rtctest.c index 4230d3052e5d..f61170f7b024 100644 --- a/tools/testing/selftests/timers/rtctest.c +++ b/tools/testing/selftests/timers/rtctest.c @@ -21,6 +21,9 @@ #include #include +#ifndef ARRAY_SIZE +# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif /* * This expects the new RTC class driver framework, working with @@ -29,23 +32,84 @@ */ static const char default_rtc[] = "/dev/rtc0"; +static struct rtc_time cutoff_dates[] = { + { + .tm_year = 70, /* 1970 -1900 */ + .tm_mday = 1, + }, + /* signed time_t 19/01/2038 3:14:08 */ + { + .tm_year = 138, + .tm_mday = 19, + }, + { + .tm_year = 138, + .tm_mday = 20, + }, + { + .tm_year = 199, /* 2099 -1900 */ + .tm_mday = 1, + }, + { + .tm_year = 200, /* 2100 -1900 */ + .tm_mday = 1, + }, + /* unsigned time_t 07/02/2106 7:28:15*/ + { + .tm_year = 205, + .tm_mon = 1, + .tm_mday = 7, + }, + { + .tm_year = 206, + .tm_mon = 1, + .tm_mday = 8, + }, + /* signed time on 64bit in nanoseconds 12/04/2262 01:47:16*/ + { + .tm_year = 362, + .tm_mon = 3, + .tm_mday = 12, + }, + { + .tm_year = 362, /* 2262 -1900 */ + .tm_mon = 3, + .tm_mday = 13, + }, +}; + +static int compare_dates(struct rtc_time *a, struct rtc_time *b) +{ + if (a->tm_year != b->tm_year || + a->tm_mon != b->tm_mon || + a->tm_mday != b->tm_mday || + a->tm_hour != b->tm_hour || + a->tm_min != b->tm_min || + ((b->tm_sec - a->tm_sec) > 1)) + return 1; + + return 0; +} int main(int argc, char **argv) { - int i, fd, retval, irqcount = 0; + int i, fd, retval, irqcount = 0, dangerous = 0; unsigned long tmp, data; struct rtc_time rtc_tm; const char *rtc = default_rtc; struct timeval start, end, diff; switch (argc) { + case 3: + if (*argv[2] == 'd') + dangerous = 1; case 2: rtc = argv[1]; /* FALLTHROUGH */ case 1: break; default: - fprintf(stderr, "usage: rtctest [rtcdev]\n"); + fprintf(stderr, "usage: rtctest [rtcdev] [d]\n"); return 1; } @@ -202,7 +266,7 @@ test_PIE: /* not all RTCs support periodic IRQs */ if (errno == EINVAL) { fprintf(stderr, "\nNo periodic IRQ support\n"); - goto done; + goto test_DATE; } perror("RTC_IRQP_READ ioctl"); exit(errno); @@ -221,7 +285,7 @@ test_PIE: if (errno == EINVAL) { fprintf(stderr, "\n...Periodic IRQ rate is fixed\n"); - goto done; + goto test_DATE; } perror("RTC_IRQP_SET ioctl"); exit(errno); @@ -269,6 +333,62 @@ test_PIE: } } +test_DATE: + if (!dangerous) + goto done; + + fprintf(stderr, "\nTesting problematic dates\n"); + + for (i = 0; i < ARRAY_SIZE(cutoff_dates); i++) { + struct rtc_time current; + + /* Write the new date in RTC */ + retval = ioctl(fd, RTC_SET_TIME, &cutoff_dates[i]); + if (retval == -1) { + perror("RTC_SET_TIME ioctl"); + close(fd); + exit(errno); + } + + /* Read back */ + retval = ioctl(fd, RTC_RD_TIME, ¤t); + if (retval == -1) { + perror("RTC_RD_TIME ioctl"); + exit(errno); + } + + if(compare_dates(&cutoff_dates[i], ¤t)) { + fprintf(stderr,"Setting date %d failed\n", + cutoff_dates[i].tm_year + 1900); + goto done; + } + + cutoff_dates[i].tm_sec += 5; + + /* Write the new alarm in RTC */ + retval = ioctl(fd, RTC_ALM_SET, &cutoff_dates[i]); + if (retval == -1) { + perror("RTC_ALM_SET ioctl"); + close(fd); + exit(errno); + } + + /* Read back */ + retval = ioctl(fd, RTC_ALM_READ, ¤t); + if (retval == -1) { + perror("RTC_ALM_READ ioctl"); + exit(errno); + } + + if(compare_dates(&cutoff_dates[i], ¤t)) { + fprintf(stderr,"Setting alarm %d failed\n", + cutoff_dates[i].tm_year + 1900); + goto done; + } + + fprintf(stderr, "Setting year %d is OK \n", + cutoff_dates[i].tm_year + 1900); + } done: fprintf(stderr, "\n\n\t\t\t *** Test complete ***\n"); -- cgit v1.2.3-59-g8ed1b From f4b82d39e40fc9c3493826abb49c64c37c7025b9 Mon Sep 17 00:00:00 2001 From: Benjamin Gaignard Date: Mon, 19 Jun 2017 11:36:22 +0200 Subject: rtc: st-lpc: make it robust against y2038/2106 bug Make driver use u64 variables and functions to be sure that it will support dates after year 2038. Signed-off-by: Benjamin Gaignard Acked-by: Patrice Chotard Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-st-lpc.c | 19 ++++++++----------- 1 file changed, 8 insertions(+), 11 deletions(-) diff --git a/drivers/rtc/rtc-st-lpc.c b/drivers/rtc/rtc-st-lpc.c index 74c0a336ceea..82b0af159a28 100644 --- a/drivers/rtc/rtc-st-lpc.c +++ b/drivers/rtc/rtc-st-lpc.c @@ -99,7 +99,7 @@ static int st_rtc_read_time(struct device *dev, struct rtc_time *tm) lpt = ((unsigned long long)lpt_msb << 32) | lpt_lsb; do_div(lpt, rtc->clkrate); - rtc_time_to_tm(lpt, tm); + rtc_time64_to_tm(lpt, tm); return 0; } @@ -107,13 +107,10 @@ static int st_rtc_read_time(struct device *dev, struct rtc_time *tm) static int st_rtc_set_time(struct device *dev, struct rtc_time *tm) { struct st_rtc *rtc = dev_get_drvdata(dev); - unsigned long long lpt; - unsigned long secs, flags; - int ret; + unsigned long long lpt, secs; + unsigned long flags; - ret = rtc_tm_to_time(tm, &secs); - if (ret) - return ret; + secs = rtc_tm_to_time64(tm); lpt = (unsigned long long)secs * rtc->clkrate; @@ -161,13 +158,13 @@ static int st_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *t) { struct st_rtc *rtc = dev_get_drvdata(dev); struct rtc_time now; - unsigned long now_secs; - unsigned long alarm_secs; + unsigned long long now_secs; + unsigned long long alarm_secs; unsigned long long lpa; st_rtc_read_time(dev, &now); - rtc_tm_to_time(&now, &now_secs); - rtc_tm_to_time(&t->time, &alarm_secs); + now_secs = rtc_tm_to_time64(&now); + alarm_secs = rtc_tm_to_time64(&t->time); /* Invalid alarm time */ if (now_secs > alarm_secs) -- cgit v1.2.3-59-g8ed1b From 49aac8204da5f344f52ed9b3eb8736ca7a60c4a8 Mon Sep 17 00:00:00 2001 From: Oleksandr Andrushchenko Date: Thu, 29 Jun 2017 00:20:19 -0700 Subject: Input: xen-kbdfront - add multi-touch support Extend xen_kbdfront to provide multi-touch support to unprivileged domains. Signed-off-by: Oleksandr Andrushchenko [dtor: factor out various sub-protocols - multitouch, single touch, keys] Signed-off-by: Dmitry Torokhov --- drivers/input/misc/xen-kbdfront.c | 219 +++++++++++++++++++++++++++++++------- 1 file changed, 179 insertions(+), 40 deletions(-) diff --git a/drivers/input/misc/xen-kbdfront.c b/drivers/input/misc/xen-kbdfront.c index eb770613a9bd..fa130e7b734c 100644 --- a/drivers/input/misc/xen-kbdfront.c +++ b/drivers/input/misc/xen-kbdfront.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -34,11 +35,14 @@ struct xenkbd_info { struct input_dev *kbd; struct input_dev *ptr; + struct input_dev *mtouch; struct xenkbd_page *page; int gref; int irq; struct xenbus_device *xbdev; char phys[32]; + /* current MT slot/contact ID we are injecting events in */ + int mtouch_cur_contact_id; }; enum { KPARAM_X, KPARAM_Y, KPARAM_CNT }; @@ -56,6 +60,112 @@ static void xenkbd_disconnect_backend(struct xenkbd_info *); * to do that. */ +static void xenkbd_handle_motion_event(struct xenkbd_info *info, + struct xenkbd_motion *motion) +{ + input_report_rel(info->ptr, REL_X, motion->rel_x); + input_report_rel(info->ptr, REL_Y, motion->rel_y); + if (motion->rel_z) + input_report_rel(info->ptr, REL_WHEEL, -motion->rel_z); + input_sync(info->ptr); +} + +static void xenkbd_handle_position_event(struct xenkbd_info *info, + struct xenkbd_position *pos) +{ + input_report_abs(info->ptr, ABS_X, pos->abs_x); + input_report_abs(info->ptr, ABS_Y, pos->abs_y); + if (pos->rel_z) + input_report_rel(info->ptr, REL_WHEEL, -pos->rel_z); + input_sync(info->ptr); +} + +static void xenkbd_handle_key_event(struct xenkbd_info *info, + struct xenkbd_key *key) +{ + struct input_dev *dev; + + if (test_bit(key->keycode, info->ptr->keybit)) { + dev = info->ptr; + } else if (test_bit(key->keycode, info->kbd->keybit)) { + dev = info->kbd; + } else { + pr_warn("unhandled keycode 0x%x\n", key->keycode); + return; + } + + input_report_key(dev, key->keycode, key->pressed); + input_sync(dev); +} + +static void xenkbd_handle_mt_event(struct xenkbd_info *info, + struct xenkbd_mtouch *mtouch) +{ + if (unlikely(!info->mtouch)) + return; + + if (mtouch->contact_id != info->mtouch_cur_contact_id) { + info->mtouch_cur_contact_id = mtouch->contact_id; + input_mt_slot(info->mtouch, mtouch->contact_id); + } + + switch (mtouch->event_type) { + case XENKBD_MT_EV_DOWN: + input_mt_report_slot_state(info->mtouch, MT_TOOL_FINGER, true); + /* fall through */ + + case XENKBD_MT_EV_MOTION: + input_report_abs(info->mtouch, ABS_MT_POSITION_X, + mtouch->u.pos.abs_x); + input_report_abs(info->mtouch, ABS_MT_POSITION_Y, + mtouch->u.pos.abs_y); + break; + + case XENKBD_MT_EV_SHAPE: + input_report_abs(info->mtouch, ABS_MT_TOUCH_MAJOR, + mtouch->u.shape.major); + input_report_abs(info->mtouch, ABS_MT_TOUCH_MINOR, + mtouch->u.shape.minor); + break; + + case XENKBD_MT_EV_ORIENT: + input_report_abs(info->mtouch, ABS_MT_ORIENTATION, + mtouch->u.orientation); + break; + + case XENKBD_MT_EV_UP: + input_mt_report_slot_state(info->mtouch, MT_TOOL_FINGER, false); + break; + + case XENKBD_MT_EV_SYN: + input_mt_sync_frame(info->mtouch); + input_sync(info->mtouch); + break; + } +} + +static void xenkbd_handle_event(struct xenkbd_info *info, + union xenkbd_in_event *event) +{ + switch (event->type) { + case XENKBD_TYPE_MOTION: + xenkbd_handle_motion_event(info, &event->motion); + break; + + case XENKBD_TYPE_KEY: + xenkbd_handle_key_event(info, &event->key); + break; + + case XENKBD_TYPE_POS: + xenkbd_handle_position_event(info, &event->pos); + break; + + case XENKBD_TYPE_MTOUCH: + xenkbd_handle_mt_event(info, &event->mtouch); + break; + } +} + static irqreturn_t input_handler(int rq, void *dev_id) { struct xenkbd_info *info = dev_id; @@ -66,44 +176,8 @@ static irqreturn_t input_handler(int rq, void *dev_id) if (prod == page->in_cons) return IRQ_HANDLED; rmb(); /* ensure we see ring contents up to prod */ - for (cons = page->in_cons; cons != prod; cons++) { - union xenkbd_in_event *event; - struct input_dev *dev; - event = &XENKBD_IN_RING_REF(page, cons); - - dev = info->ptr; - switch (event->type) { - case XENKBD_TYPE_MOTION: - input_report_rel(dev, REL_X, event->motion.rel_x); - input_report_rel(dev, REL_Y, event->motion.rel_y); - if (event->motion.rel_z) - input_report_rel(dev, REL_WHEEL, - -event->motion.rel_z); - break; - case XENKBD_TYPE_KEY: - dev = NULL; - if (test_bit(event->key.keycode, info->kbd->keybit)) - dev = info->kbd; - if (test_bit(event->key.keycode, info->ptr->keybit)) - dev = info->ptr; - if (dev) - input_report_key(dev, event->key.keycode, - event->key.pressed); - else - pr_warn("unhandled keycode 0x%x\n", - event->key.keycode); - break; - case XENKBD_TYPE_POS: - input_report_abs(dev, ABS_X, event->pos.abs_x); - input_report_abs(dev, ABS_Y, event->pos.abs_y); - if (event->pos.rel_z) - input_report_rel(dev, REL_WHEEL, - -event->pos.rel_z); - break; - } - if (dev) - input_sync(dev); - } + for (cons = page->in_cons; cons != prod; cons++) + xenkbd_handle_event(info, &XENKBD_IN_RING_REF(page, cons)); mb(); /* ensure we got ring contents */ page->in_cons = cons; notify_remote_via_irq(info->irq); @@ -115,9 +189,9 @@ static int xenkbd_probe(struct xenbus_device *dev, const struct xenbus_device_id *id) { int ret, i; - unsigned int abs; + unsigned int abs, touch; struct xenkbd_info *info; - struct input_dev *kbd, *ptr; + struct input_dev *kbd, *ptr, *mtouch; info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) { @@ -152,6 +226,17 @@ static int xenkbd_probe(struct xenbus_device *dev, } } + touch = xenbus_read_unsigned(dev->nodename, + XENKBD_FIELD_FEAT_MTOUCH, 0); + if (touch) { + ret = xenbus_write(XBT_NIL, dev->nodename, + XENKBD_FIELD_REQ_MTOUCH, "1"); + if (ret) { + pr_warn("xenkbd: can't request multi-touch"); + touch = 0; + } + } + /* keyboard */ kbd = input_allocate_device(); if (!kbd) @@ -208,6 +293,58 @@ static int xenkbd_probe(struct xenbus_device *dev, } info->ptr = ptr; + /* multi-touch device */ + if (touch) { + int num_cont, width, height; + + mtouch = input_allocate_device(); + if (!mtouch) + goto error_nomem; + + num_cont = xenbus_read_unsigned(info->xbdev->nodename, + XENKBD_FIELD_MT_NUM_CONTACTS, + 1); + width = xenbus_read_unsigned(info->xbdev->nodename, + XENKBD_FIELD_MT_WIDTH, + XENFB_WIDTH); + height = xenbus_read_unsigned(info->xbdev->nodename, + XENKBD_FIELD_MT_HEIGHT, + XENFB_HEIGHT); + + mtouch->name = "Xen Virtual Multi-touch"; + mtouch->phys = info->phys; + mtouch->id.bustype = BUS_PCI; + mtouch->id.vendor = 0x5853; + mtouch->id.product = 0xfffd; + + input_set_abs_params(mtouch, ABS_MT_TOUCH_MAJOR, + 0, 255, 0, 0); + input_set_abs_params(mtouch, ABS_MT_POSITION_X, + 0, width, 0, 0); + input_set_abs_params(mtouch, ABS_MT_POSITION_Y, + 0, height, 0, 0); + input_set_abs_params(mtouch, ABS_MT_PRESSURE, + 0, 255, 0, 0); + + ret = input_mt_init_slots(mtouch, num_cont, INPUT_MT_DIRECT); + if (ret) { + input_free_device(mtouch); + xenbus_dev_fatal(info->xbdev, ret, + "input_mt_init_slots"); + goto error; + } + + ret = input_register_device(mtouch); + if (ret) { + input_free_device(mtouch); + xenbus_dev_fatal(info->xbdev, ret, + "input_register_device(mtouch)"); + goto error; + } + info->mtouch_cur_contact_id = -1; + info->mtouch = mtouch; + } + ret = xenkbd_connect_backend(dev, info); if (ret < 0) goto error; @@ -240,6 +377,8 @@ static int xenkbd_remove(struct xenbus_device *dev) input_unregister_device(info->kbd); if (info->ptr) input_unregister_device(info->ptr); + if (info->mtouch) + input_unregister_device(info->mtouch); free_page((unsigned long)info->page); kfree(info); return 0; -- cgit v1.2.3-59-g8ed1b From 0f107573da417c7f5c6d3a0160ebacc3adb019c4 Mon Sep 17 00:00:00 2001 From: Joseph Lo Date: Sun, 2 Jul 2017 13:38:31 -0700 Subject: Input: gpio_keys - handle the missing key press event in resume phase The GPIO key press event might be missed in the resume phase, if the key had been released before the system had been resumed to the stage that it could capture the press event. So we simulate the wakeup key press event in case the key had been released by the time we got interrupt handler to run. Signed-off-by: Joseph Lo Signed-off-by: Enric Balletbo i Serra Signed-off-by: Dmitry Torokhov --- drivers/input/keyboard/gpio_keys.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/drivers/input/keyboard/gpio_keys.c b/drivers/input/keyboard/gpio_keys.c index da3d362f21b1..a047b9af8369 100644 --- a/drivers/input/keyboard/gpio_keys.c +++ b/drivers/input/keyboard/gpio_keys.c @@ -48,6 +48,7 @@ struct gpio_button_data { spinlock_t lock; bool disabled; bool key_pressed; + bool suspended; }; struct gpio_keys_drvdata { @@ -396,8 +397,20 @@ static irqreturn_t gpio_keys_gpio_isr(int irq, void *dev_id) BUG_ON(irq != bdata->irq); - if (bdata->button->wakeup) + if (bdata->button->wakeup) { + const struct gpio_keys_button *button = bdata->button; + pm_stay_awake(bdata->input->dev.parent); + if (bdata->suspended && + (button->type == 0 || button->type == EV_KEY)) { + /* + * Simulate wakeup key press in case the key has + * already released by the time we got interrupt + * handler to run. + */ + input_report_key(bdata->input, button->code, 1); + } + } mod_delayed_work(system_wq, &bdata->work, @@ -855,6 +868,7 @@ static int __maybe_unused gpio_keys_suspend(struct device *dev) struct gpio_button_data *bdata = &ddata->data[i]; if (bdata->button->wakeup) enable_irq_wake(bdata->irq); + bdata->suspended = true; } } else { mutex_lock(&input->mutex); @@ -878,6 +892,7 @@ static int __maybe_unused gpio_keys_resume(struct device *dev) struct gpio_button_data *bdata = &ddata->data[i]; if (bdata->button->wakeup) disable_irq_wake(bdata->irq); + bdata->suspended = false; } } else { mutex_lock(&input->mutex); -- cgit v1.2.3-59-g8ed1b From de8c5221aa003935d6d31becf5850b247dff14a1 Mon Sep 17 00:00:00 2001 From: "Bryant G. Ly" Date: Fri, 7 Jul 2017 14:20:00 -0500 Subject: tcmu: Fix dev_config_store Currently when there is a reconfig, the uio_info->name does not get updated to reflect the change in the dev_config name change. On restart tcmu-runner there will be a mismatch between the dev_config string in uio and the tcmu structure that contains the string. When this occurs it'll reload the one in uio and you lose the reconfigured device path. v2: Created a helper function for the updating of uio_info Signed-off-by: Bryant G. Ly Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_user.c | 32 ++++++++++++++++++++++++-------- 1 file changed, 24 insertions(+), 8 deletions(-) diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index cbbfba0c1352..2f1fa927682e 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -1418,19 +1418,14 @@ free_skb: return ret; } -static int tcmu_configure_device(struct se_device *dev) +static int tcmu_update_uio_info(struct tcmu_dev *udev) { - struct tcmu_dev *udev = TCMU_DEV(dev); struct tcmu_hba *hba = udev->hba->hba_ptr; struct uio_info *info; - struct tcmu_mailbox *mb; - size_t size; - size_t used; - int ret = 0; + size_t size, used; char *str; info = &udev->uio_info; - size = snprintf(NULL, 0, "tcm-user/%u/%s/%s", hba->host_id, udev->name, udev->dev_config); size += 1; /* for \0 */ @@ -1439,12 +1434,27 @@ static int tcmu_configure_device(struct se_device *dev) return -ENOMEM; used = snprintf(str, size, "tcm-user/%u/%s", hba->host_id, udev->name); - if (udev->dev_config[0]) snprintf(str + used, size - used, "/%s", udev->dev_config); info->name = str; + return 0; +} + +static int tcmu_configure_device(struct se_device *dev) +{ + struct tcmu_dev *udev = TCMU_DEV(dev); + struct uio_info *info; + struct tcmu_mailbox *mb; + int ret = 0; + + ret = tcmu_update_uio_info(udev); + if (ret) + return ret; + + info = &udev->uio_info; + udev->mb_addr = vzalloc(CMDR_SIZE); if (!udev->mb_addr) { ret = -ENOMEM; @@ -1786,6 +1796,12 @@ static ssize_t tcmu_dev_config_store(struct config_item *item, const char *page, pr_err("Unable to reconfigure device\n"); return ret; } + strlcpy(udev->dev_config, page, TCMU_CONFIG_LEN); + + ret = tcmu_update_uio_info(udev); + if (ret) + return ret; + return count; } strlcpy(udev->dev_config, page, TCMU_CONFIG_LEN); -- cgit v1.2.3-59-g8ed1b From 388fe6996bf658146e70c0df986981eae4be0385 Mon Sep 17 00:00:00 2001 From: Tang Wenji Date: Sat, 8 Jul 2017 11:15:44 +0800 Subject: target: Fix cmd size for PR-OUT in passthrough_parse_cdb The cmd size should be 4bytes form byte5 to byte8 when CDB opcode is PERSISTENT_RESERVE_OUT in SPC3 and SPC4 (Also fix up the same in spc_parse_cdb - MNC) Signed-off-by: Tang Wenji Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_device.c | 2 +- drivers/target/target_core_spc.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 1c7c57a3c52e..e8dd6da164b2 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -1183,7 +1183,7 @@ passthrough_parse_cdb(struct se_cmd *cmd, } if (cdb[0] == PERSISTENT_RESERVE_OUT) { cmd->execute_cmd = target_scsi3_emulate_pr_out; - size = get_unaligned_be16(&cdb[7]); + size = get_unaligned_be32(&cdb[5]); return target_cmd_size_check(cmd, size); } diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c index f59ac7671031..cb0461a10808 100644 --- a/drivers/target/target_core_spc.c +++ b/drivers/target/target_core_spc.c @@ -1307,7 +1307,7 @@ spc_parse_cdb(struct se_cmd *cmd, unsigned int *size) cmd->execute_cmd = target_scsi3_emulate_pr_in; break; case PERSISTENT_RESERVE_OUT: - *size = get_unaligned_be16(&cdb[7]); + *size = get_unaligned_be32(&cdb[5]); cmd->execute_cmd = target_scsi3_emulate_pr_out; break; case RELEASE: -- cgit v1.2.3-59-g8ed1b From 7ee0031786dc3762f61d0ec9171bb75d56a5ac76 Mon Sep 17 00:00:00 2001 From: Tang Wenji Date: Sat, 8 Jul 2017 11:28:25 +0800 Subject: target: Fix return sense reason in target_scsi3_emulate_pr_out The sense reason should be TCM_PARAMETER_LIST_LENGTH_ERROR when parmeter length error. Also the cdb[1] & 0x1f has been assigned to local variable sa, so use sa instead of it. Signed-off-by: Tang Wenji Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_pr.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index 9921d4d6bb41..6d5def64db61 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -3585,7 +3585,7 @@ target_scsi3_emulate_pr_out(struct se_cmd *cmd) if (cmd->data_length < 24) { pr_warn("SPC-PR: Received PR OUT parameter list" " length too small: %u\n", cmd->data_length); - return TCM_INVALID_PARAMETER_LIST; + return TCM_PARAMETER_LIST_LENGTH_ERROR; } /* @@ -3629,7 +3629,7 @@ target_scsi3_emulate_pr_out(struct se_cmd *cmd) /* * SPEC_I_PT=1 is only valid for Service action: REGISTER */ - if (spec_i_pt && ((cdb[1] & 0x1f) != PRO_REGISTER)) + if (spec_i_pt && (sa != PRO_REGISTER)) return TCM_INVALID_PARAMETER_LIST; /* @@ -3641,11 +3641,11 @@ target_scsi3_emulate_pr_out(struct se_cmd *cmd) * the sense key set to ILLEGAL REQUEST, and the additional sense * code set to PARAMETER LIST LENGTH ERROR. */ - if (!spec_i_pt && ((cdb[1] & 0x1f) != PRO_REGISTER_AND_MOVE) && + if (!spec_i_pt && (sa != PRO_REGISTER_AND_MOVE) && (cmd->data_length != 24)) { pr_warn("SPC-PR: Received PR OUT illegal parameter" " list length: %u\n", cmd->data_length); - return TCM_INVALID_PARAMETER_LIST; + return TCM_PARAMETER_LIST_LENGTH_ERROR; } /* @@ -3685,7 +3685,7 @@ target_scsi3_emulate_pr_out(struct se_cmd *cmd) break; default: pr_err("Unknown PERSISTENT_RESERVE_OUT service" - " action: 0x%02x\n", cdb[1] & 0x1f); + " action: 0x%02x\n", sa); return TCM_INVALID_CDB_FIELD; } -- cgit v1.2.3-59-g8ed1b From 7581d5ca2bb269cfc2ce2d0cb489aac513167f6b Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 22 Jun 2017 17:02:11 +0100 Subject: drm/i915/fbdev: Check for existence of ifbdev->vma before operations Commit fabef825626d ("drm/i915: Drop struct_mutex around frontbuffer flushes") adds a dependency to ifbdev->vma when flushing the framebufer, but the checks are only against the existence of the ifbdev->fb and not against ifbdev->vma. This leaves a window of opportunity where we may try to operate on the fbdev prior to it being probed (thanks to asynchronous booting). Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=101534 Fixes: fabef825626d ("drm/i915: Drop struct_mutex around frontbuffer flushes") Signed-off-by: Chris Wilson Cc: Joonas Lahtinen Cc: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/20170622160211.783-1-chris@chris-wilson.co.uk Reviewed-by: Tvrtko Ursulin Cc: stable@vger.kernel.org (cherry picked from commit 15727ed0d944ce1dec8b9e1082dd3df29a0fdf44) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_fbdev.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index 03347c6ae599..0c4cde6b2e6f 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -535,13 +535,14 @@ static void intel_fbdev_destroy(struct intel_fbdev *ifbdev) drm_fb_helper_fini(&ifbdev->helper); - if (ifbdev->fb) { + if (ifbdev->vma) { mutex_lock(&ifbdev->helper.dev->struct_mutex); intel_unpin_fb_vma(ifbdev->vma); mutex_unlock(&ifbdev->helper.dev->struct_mutex); + } + if (ifbdev->fb) drm_framebuffer_remove(&ifbdev->fb->base); - } kfree(ifbdev); } @@ -765,7 +766,7 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous struct intel_fbdev *ifbdev = dev_priv->fbdev; struct fb_info *info; - if (!ifbdev || !ifbdev->fb) + if (!ifbdev || !ifbdev->vma) return; info = ifbdev->helper.fbdev; @@ -812,7 +813,7 @@ void intel_fbdev_output_poll_changed(struct drm_device *dev) { struct intel_fbdev *ifbdev = to_i915(dev)->fbdev; - if (ifbdev && ifbdev->fb) + if (ifbdev && ifbdev->vma) drm_fb_helper_hotplug_event(&ifbdev->helper); } @@ -824,7 +825,7 @@ void intel_fbdev_restore_mode(struct drm_device *dev) return; intel_fbdev_sync(ifbdev); - if (!ifbdev->fb) + if (!ifbdev->vma) return; if (drm_fb_helper_restore_fbdev_mode_unlocked(&ifbdev->helper) == 0) -- cgit v1.2.3-59-g8ed1b From 7e988b103d0d52190244517edc76e649071284bb Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Fri, 7 Jul 2017 15:49:00 +0200 Subject: KVM: use correct accessor function for __kvm_memslots kvm memslots are protected by srcu and not by rcu. We must use srcu_dereference_check instead of rcu_dereference_check. Signed-off-by: Christian Borntraeger Suggested-by: Paolo Bonzini --- include/linux/kvm_host.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index b3ca77a96b2d..648b34cabb38 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -568,9 +568,8 @@ void kvm_put_kvm(struct kvm *kvm); static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id) { - return rcu_dereference_check(kvm->memslots[as_id], - srcu_read_lock_held(&kvm->srcu) - || lockdep_is_held(&kvm->slots_lock)); + return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu, + lockdep_is_held(&kvm->slots_lock)); } static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) -- cgit v1.2.3-59-g8ed1b From 1e2a516e89fc412a754327522ab271b42f99c6b4 Mon Sep 17 00:00:00 2001 From: Balbir Singh Date: Thu, 29 Jun 2017 21:57:26 +1000 Subject: powerpc/kexec: Fix radix to hash kexec due to IAMR/AMOR This patch fixes a crash seen while doing a kexec from radix mode to hash mode. Key 0 is special in hash and used in the RPN by default, we set the key values to 0 today. In radix mode key 0 is used to control supervisor<->user access. In hash key 0 is used by default, so the first instruction after the switch causes a crash on kexec. Commit 3b10d0095a1e ("powerpc/mm/radix: Prevent kernel execution of user space") introduced the setting of IAMR and AMOR values to prevent execution of user mode instructions from supervisor mode. We need to clean up these SPR's on kexec. Fixes: 3b10d0095a1e ("powerpc/mm/radix: Prevent kernel execution of user space") Cc: stable@vger.kernel.org # v4.10+ Reported-by: Benjamin Herrenschmidt Signed-off-by: Balbir Singh Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/misc_64.S | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index c119044cad0d..8ac0bd2bddb0 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -614,6 +614,18 @@ _GLOBAL(kexec_sequence) li r0,0 std r0,16(r1) +BEGIN_FTR_SECTION + /* + * This is the best time to turn AMR/IAMR off. + * key 0 is used in radix for supervisor<->user + * protection, but on hash key 0 is reserved + * ideally we want to enter with a clean state. + * NOTE, we rely on r0 being 0 from above. + */ + mtspr SPRN_IAMR,r0 + mtspr SPRN_AMOR,r0 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) + /* save regs for local vars on new stack. * yes, we won't go back, but ... */ -- cgit v1.2.3-59-g8ed1b From 1c0eaf0f56d6128af7f0f252855173fcee85d202 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Fri, 30 Jun 2017 17:37:32 -0500 Subject: powerpc/powernv: Tell OPAL about our MMU mode on POWER9 That will allow OPAL to configure the CPU in an optimal way. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Michael Neuling Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/opal-api.h | 9 +++++++++ arch/powerpc/platforms/powernv/opal.c | 19 +++++++++++++++++-- arch/powerpc/platforms/powernv/setup.c | 11 ++++++++++- 3 files changed, 36 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h index ef930ba500f9..3130a73652c7 100644 --- a/arch/powerpc/include/asm/opal-api.h +++ b/arch/powerpc/include/asm/opal-api.h @@ -876,6 +876,15 @@ struct OpalIoPhb4ErrorData { enum { OPAL_REINIT_CPUS_HILE_BE = (1 << 0), OPAL_REINIT_CPUS_HILE_LE = (1 << 1), + + /* These two define the base MMU mode of the host on P9 + * + * On P9 Nimbus DD2.0 and Cumlus (and later), KVM can still + * create hash guests in "radix" mode with care (full core + * switch only). + */ + OPAL_REINIT_CPUS_MMU_HASH = (1 << 2), + OPAL_REINIT_CPUS_MMU_RADIX = (1 << 3), }; typedef struct oppanel_line { diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 59684b4af4d1..9b87abb178f0 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -59,6 +59,8 @@ static struct task_struct *kopald_tsk; void opal_configure_cores(void) { + u64 reinit_flags = 0; + /* Do the actual re-init, This will clobber all FPRs, VRs, etc... * * It will preserve non volatile GPRs and HSPRG0/1. It will @@ -66,11 +68,24 @@ void opal_configure_cores(void) * but it might clobber a bunch. */ #ifdef __BIG_ENDIAN__ - opal_reinit_cpus(OPAL_REINIT_CPUS_HILE_BE); + reinit_flags |= OPAL_REINIT_CPUS_HILE_BE; #else - opal_reinit_cpus(OPAL_REINIT_CPUS_HILE_LE); + reinit_flags |= OPAL_REINIT_CPUS_HILE_LE; #endif + /* + * POWER9 always support running hash: + * ie. Host hash supports hash guests + * Host radix supports hash/radix guests + */ + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + reinit_flags |= OPAL_REINIT_CPUS_MMU_HASH; + if (early_radix_enabled()) + reinit_flags |= OPAL_REINIT_CPUS_MMU_RADIX; + } + + opal_reinit_cpus(reinit_flags); + /* Restore some bits */ if (cur_cpu_spec->cpu_restore) cur_cpu_spec->cpu_restore(); diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 2dc7e5fb86c3..897aa1400eb8 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -225,6 +225,8 @@ static void pnv_kexec_wait_secondaries_down(void) static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) { + u64 reinit_flags; + if (xive_enabled()) xive_kexec_teardown_cpu(secondary); else @@ -254,8 +256,15 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) * We might be running as little-endian - now that interrupts * are disabled, reset the HILE bit to big-endian so we don't * take interrupts in the wrong endian later + * + * We reinit to enable both radix and hash on P9 to ensure + * the mode used by the next kernel is always supported. */ - opal_reinit_cpus(OPAL_REINIT_CPUS_HILE_BE); + reinit_flags = OPAL_REINIT_CPUS_HILE_BE; + if (cpu_has_feature(CPU_FTR_ARCH_300)) + reinit_flags |= OPAL_REINIT_CPUS_MMU_RADIX | + OPAL_REINIT_CPUS_MMU_HASH; + opal_reinit_cpus(reinit_flags); } } #endif /* CONFIG_KEXEC_CORE */ -- cgit v1.2.3-59-g8ed1b From c6bb0b8d426a8cf865ca9c8a532cc3a2927cfceb Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Sat, 8 Jul 2017 07:45:32 -0500 Subject: powerpc/mm/radix: Properly clear process table entry On radix, the process table entry we want to clear when destroying a context is entry 0, not entry 1. This has no *immediate* consequence on Power9, but it can cause other bugs to become worse. Fixes: 7e381c0ff618 ("powerpc/mm/radix: Add mmu context handling callback for radix") Cc: stable@vger.kernel.org # v4.7+ Signed-off-by: Benjamin Herrenschmidt Reviewed-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- arch/powerpc/mm/mmu_context_book3s64.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c index 71de2c6d88f3..ceff76262c7e 100644 --- a/arch/powerpc/mm/mmu_context_book3s64.c +++ b/arch/powerpc/mm/mmu_context_book3s64.c @@ -223,9 +223,15 @@ void destroy_context(struct mm_struct *mm) mm->context.cop_lockp = NULL; #endif /* CONFIG_PPC_ICSWX */ - if (radix_enabled()) - process_tb[mm->context.id].prtb1 = 0; - else + if (radix_enabled()) { + /* + * Radix doesn't have a valid bit in the process table + * entries. However we know that at least P9 implementation + * will avoid caching an entry with an invalid RTS field, + * and 0 is invalid. So this will do. + */ + process_tb[mm->context.id].prtb0 = 0; + } else subpage_prot_free(mm); destroy_pagetable_page(mm); __destroy_context(mm->context.id); -- cgit v1.2.3-59-g8ed1b From 3a6a04706fd08eb5677fdfc086e26fcd5eb154f4 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Fri, 7 Jul 2017 16:12:16 -0500 Subject: powerpc/mm/radix: Synchronize updates to the process table When writing to the process table, we need to ensure the store is visible to a subsequent access by the MMU. We assume we never have the PID active while doing the update, so a ptesync/isync pair should hopefully be a big enough hammer for our purpose. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Michael Ellerman --- arch/powerpc/mm/mmu_context_book3s64.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c index ceff76262c7e..abed1fe6992f 100644 --- a/arch/powerpc/mm/mmu_context_book3s64.c +++ b/arch/powerpc/mm/mmu_context_book3s64.c @@ -138,6 +138,14 @@ static int radix__init_new_context(struct mm_struct *mm) rts_field = radix__get_tree_size(); process_tb[index].prtb0 = cpu_to_be64(rts_field | __pa(mm->pgd) | RADIX_PGD_INDEX_SIZE); + /* + * Order the above store with subsequent update of the PID + * register (at which point HW can start loading/caching + * the entry) and the corresponding load by the MMU from + * the L2 cache. + */ + asm volatile("ptesync;isync" : : : "memory"); + mm->context.npu_context = NULL; return index; -- cgit v1.2.3-59-g8ed1b From 42a6e0996084972574e0a2b23e7326b78b0f64c5 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 10 Jul 2017 13:22:50 +0200 Subject: nvmem: include linux/err.h from header The new support for nvmem devices from the rtc layer caused a build error in some configurations: include/linux/nvmem-provider.h: In function 'nvmem_register': include/linux/nvmem-provider.h:51:9: error: implicit declaration of function 'ERR_PTR' [-Werror=implicit-function-declaration] This adds the missing include to ensure we can always include the header. Fixes: 697e5a47aa12 ("rtc: add generic nvmem support") Signed-off-by: Arnd Bergmann Acked-by: Srinivas Kandagatla Signed-off-by: Alexandre Belloni --- include/linux/nvmem-provider.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index cd93416d762e..497706f5adca 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -12,6 +12,9 @@ #ifndef _LINUX_NVMEM_PROVIDER_H #define _LINUX_NVMEM_PROVIDER_H +#include +#include + struct nvmem_device; struct nvmem_cell_info; typedef int (*nvmem_reg_read_t)(void *priv, unsigned int offset, -- cgit v1.2.3-59-g8ed1b From b49defe83659cefbb1763d541e779da32594ab10 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Fri, 30 Jun 2017 13:25:45 +0200 Subject: kvm: avoid unused variable warning for UP builds The uniprocessor version of smp_call_function_many does not evaluate all of its argument, and the compiler emits a warning about "wait" being unused. This breaks the build on architectures for which "-Werror" is enabled by default. Work around it by moving the invocation of smp_call_function_many to its own inline function. Reported-by: Paul Mackerras Cc: stable@vger.kernel.org Fixes: 7a97cec26b94c909f4cbad2dc3186af3e457a522 Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 19f0ecb9b93e..0d796c9a6482 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -187,12 +187,23 @@ static void ack_flush(void *_completed) { } +static inline bool kvm_kick_many_cpus(const struct cpumask *cpus, bool wait) +{ + if (unlikely(!cpus)) + cpus = cpu_online_mask; + + if (cpumask_empty(cpus)) + return false; + + smp_call_function_many(cpus, ack_flush, NULL, wait); + return true; +} + bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req) { int i, cpu, me; cpumask_var_t cpus; - bool called = true; - bool wait = req & KVM_REQUEST_WAIT; + bool called; struct kvm_vcpu *vcpu; zalloc_cpumask_var(&cpus, GFP_ATOMIC); @@ -207,14 +218,9 @@ bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req) if (cpus != NULL && cpu != -1 && cpu != me && kvm_request_needs_ipi(vcpu, req)) - cpumask_set_cpu(cpu, cpus); + __cpumask_set_cpu(cpu, cpus); } - if (unlikely(cpus == NULL)) - smp_call_function_many(cpu_online_mask, ack_flush, NULL, wait); - else if (!cpumask_empty(cpus)) - smp_call_function_many(cpus, ack_flush, NULL, wait); - else - called = false; + called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT)); put_cpu(); free_cpumask_var(cpus); return called; -- cgit v1.2.3-59-g8ed1b From 70bcd708dfd1de453905212c9c5c755b1844772b Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 5 Jul 2017 12:38:06 +0200 Subject: KVM: vmx: expose more information for KVM_INTERNAL_ERROR_DELIVERY_EV exits This exit ended up being reported, but the currently exposed data does not provide much of a starting point for debugging. In the reported case, the vmexit was an EPT misconfiguration (MMIO access). Let userspace report ethe exit qualification and, if relevant, the GPA. Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index f76efad248ab..7592a18ecc1c 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -8418,9 +8418,15 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) exit_reason != EXIT_REASON_TASK_SWITCH)) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; - vcpu->run->internal.ndata = 2; + vcpu->run->internal.ndata = 3; vcpu->run->internal.data[0] = vectoring_info; vcpu->run->internal.data[1] = exit_reason; + vcpu->run->internal.data[2] = vcpu->arch.exit_qualification; + if (exit_reason == EXIT_REASON_EPT_MISCONFIG) { + vcpu->run->internal.ndata++; + vcpu->run->internal.data[3] = + vmcs_read64(GUEST_PHYSICAL_ADDRESS); + } return 0; } -- cgit v1.2.3-59-g8ed1b From abe594c2cf55b46d4feb61c01fe9063afff2e50c Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Sun, 9 Jul 2017 21:31:02 +0200 Subject: ALSA: pcm: Protect call to dma_mmap_coherent() by check for HAS_DMA If NO_DMA=y: sound/core/pcm_native.o: In function `snd_pcm_lib_default_mmap': pcm_native.c:(.text+0x144c): undefined reference to `bad_dma_ops' pcm_native.c:(.text+0x1474): undefined reference to `dma_common_mmap' Add a check for HAS_DMA to fix this. Signed-off-by: Geert Uytterhoeven Signed-off-by: Takashi Iwai --- sound/core/pcm_native.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 0d1834310531..b26c7e61d600 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -3502,7 +3502,7 @@ int snd_pcm_lib_default_mmap(struct snd_pcm_substream *substream, } #endif /* CONFIG_GENERIC_ALLOCATOR */ #ifndef CONFIG_X86 /* for avoiding warnings arch/x86/mm/pat.c */ - if (!substream->ops->page && + if (IS_ENABLED(CONFIG_HAS_DMA) && !substream->ops->page && substream->dma_buffer.dev.type == SNDRV_DMA_TYPE_DEV) return dma_mmap_coherent(substream->dma_buffer.dev.dev, area, -- cgit v1.2.3-59-g8ed1b From 85dc0f8554fa024b02eb50dcca71fa9881a45ea5 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 10 Jul 2017 16:05:58 +0200 Subject: ALSA: pcm: Simplify check for dma_mmap_coherent() availability We check the availability of dma_mmap_coherent() in hw_support_mmap() but with an ugly ifdef of lots of arch-checks. Now we have a nice CONFIG_ARCH_NO_COHERENT_DMA_MMAP kconfig, and this can be used together with CONFIG_HAS_DMA check for a cleaner and more comprehensive check. Signed-off-by: Takashi Iwai --- sound/core/pcm_native.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index b26c7e61d600..2a730f38e375 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -238,10 +238,8 @@ static bool hw_support_mmap(struct snd_pcm_substream *substream) { if (!(substream->runtime->hw.info & SNDRV_PCM_INFO_MMAP)) return false; - /* check architectures that return -EINVAL from dma_mmap_coherent() */ - /* FIXME: this should be some global flag */ -#if defined(CONFIG_C6X) || defined(CONFIG_FRV) || defined(CONFIG_MN10300) ||\ - defined(CONFIG_PARISC) || defined(CONFIG_XTENSA) + /* architecture supports dma_mmap_coherent()? */ +#if defined(CONFIG_ARCH_NO_COHERENT_DMA_MMAP) || !defined(CONFIG_HAS_DMA) if (!substream->ops->mmap && substream->dma_buffer.dev.type == SNDRV_DMA_TYPE_DEV) return false; -- cgit v1.2.3-59-g8ed1b From f01fc4177352614743ce3fe289687387fcf9e6c6 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Mon, 10 Jul 2017 13:34:08 +0100 Subject: ARM/PCI: Fix pcibios_init_resource() struct pci_host_bridge leak Since commit 97ad2bdcbe85 ("ARM/PCI: Convert PCI scan API to pci_scan_root_bus_bridge()") the space for struct pci_sys_data is allocated by pci_alloc_host_bridge() as part of the struct pci_host_bridge. Therefore, failure paths must deallocate the entire pci_host_bridge by using pci_free_host_bridge(). Fixes: 97ad2bdcbe85 ("ARM/PCI: Convert PCI scan API to pci_scan_root_bus_bridge()") Signed-off-by: Lorenzo Pieralisi [bhelgaas: changelog] Signed-off-by: Bjorn Helgaas Cc: Jason Cooper Cc: Russell King Cc: Andrew Lunn --- arch/arm/kernel/bios32.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c index 56dc1a3a33b4..c1809fb549dd 100644 --- a/arch/arm/kernel/bios32.c +++ b/arch/arm/kernel/bios32.c @@ -480,7 +480,7 @@ static void pcibios_init_hw(struct device *parent, struct hw_pci *hw, ret = pcibios_init_resource(nr, sys, hw->io_optional); if (ret) { - kfree(sys); + pci_free_host_bridge(bridge); break; } -- cgit v1.2.3-59-g8ed1b From 4aaf7694f841edc96fe0f72958aabe59204b3611 Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Tue, 4 Jul 2017 11:20:30 +0800 Subject: md/bitmap: don't read page from device with Bitmap_sync The device owns Bitmap_sync flag needs recovery to become in sync, and read page from this type device could get stale status. Also add comments for Bitmap_sync bit per the suggestion from Shaohua and Neil. Previous disscussion can be found here: https://marc.info/?t=149760428900004&r=1&w=2 Signed-off-by: Guoqing Jiang Signed-off-by: Shaohua Li --- drivers/md/bitmap.c | 3 ++- drivers/md/md.h | 4 +++- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index f4eace5ea184..40f3cd7eab0f 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -156,7 +156,8 @@ static int read_sb_page(struct mddev *mddev, loff_t offset, rdev_for_each(rdev, mddev) { if (! test_bit(In_sync, &rdev->flags) - || test_bit(Faulty, &rdev->flags)) + || test_bit(Faulty, &rdev->flags) + || test_bit(Bitmap_sync, &rdev->flags)) continue; target = offset + index * (PAGE_SIZE/512); diff --git a/drivers/md/md.h b/drivers/md/md.h index 991f0fe2dcc6..b50eb4ac1b82 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -134,7 +134,9 @@ enum flag_bits { Faulty, /* device is known to have a fault */ In_sync, /* device is in_sync with rest of array */ Bitmap_sync, /* ..actually, not quite In_sync. Need a - * bitmap-based recovery to get fully in sync + * bitmap-based recovery to get fully in sync. + * The bit is only meaningful before device + * has been passed to pers->hot_add_disk. */ WriteMostly, /* Avoid reading if at all possible */ AutoDetected, /* added by auto-detect */ -- cgit v1.2.3-59-g8ed1b From b5d27718f38843a74552e9a93d32e2391fd3999f Mon Sep 17 00:00:00 2001 From: Xiao Ni Date: Wed, 5 Jul 2017 17:34:04 +0800 Subject: Raid5 should update rdev->sectors after reshape The raid5 md device is created by the disks which we don't use the total size. For example, the size of the device is 5G and it just uses 3G of the devices to create one raid5 device. Then change the chunksize and wait reshape to finish. After reshape finishing stop the raid and assemble it again. It fails. mdadm -CR /dev/md0 -l5 -n3 /dev/loop[0-2] --size=3G --chunk=32 --assume-clean mdadm /dev/md0 --grow --chunk=64 wait reshape to finish mdadm -S /dev/md0 mdadm -As The error messages: [197519.814302] md: loop1 does not have a valid v1.2 superblock, not importing! [197519.821686] md: md_import_device returned -22 After reshape the data offset is changed. It selects backwards direction in this condition. In function super_1_load it compares the available space of the underlying device with sb->data_size. The new data offset gets bigger after reshape. So super_1_load returns -EINVAL. rdev->sectors is updated in md_finish_reshape. Then sb->data_size is set in super_1_sync based on rdev->sectors. So add md_finish_reshape in end_reshape. Signed-off-by: Xiao Ni Acked-by: Guoqing Jiang Cc: stable@vger.kernel.org Signed-off-by: Shaohua Li --- drivers/md/raid5.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 2ceb338b094b..aeeb8d6854e2 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -7951,12 +7951,10 @@ static void end_reshape(struct r5conf *conf) { if (!test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) { - struct md_rdev *rdev; spin_lock_irq(&conf->device_lock); conf->previous_raid_disks = conf->raid_disks; - rdev_for_each(rdev, conf->mddev) - rdev->data_offset = rdev->new_data_offset; + md_finish_reshape(conf->mddev); smp_wmb(); conf->reshape_progress = MaxSector; conf->mddev->reshape_position = MaxSector; -- cgit v1.2.3-59-g8ed1b From 6f6e0b217a93011f8e11b9a2d5521a08fcf36990 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 6 Jul 2017 16:58:33 -0500 Subject: drm/rockchip: fix NULL check on devm_kzalloc() return value The right variable to check here is port, not dp. This issue was detected using Coccinelle and the following semantic patch: @@ expression x; identifier fld; @@ * x = devm_kzalloc(...); ... when != x == NULL x->fld Signed-off-by: Gustavo A. R. Silva Acked-by: Mark Yao Signed-off-by: Sean Paul Link: http://patchwork.freedesktop.org/patch/msgid/20170706215833.GA25411@embeddedgus --- drivers/gpu/drm/rockchip/cdn-dp-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c index 14fa1f8351e8..9b0b0588bbed 100644 --- a/drivers/gpu/drm/rockchip/cdn-dp-core.c +++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c @@ -1195,7 +1195,7 @@ static int cdn_dp_probe(struct platform_device *pdev) continue; port = devm_kzalloc(dev, sizeof(*port), GFP_KERNEL); - if (!dp) + if (!port) return -ENOMEM; port->extcon = extcon; -- cgit v1.2.3-59-g8ed1b From 94df7fe0d3e6418113783ff646507287c233e1e3 Mon Sep 17 00:00:00 2001 From: Thomas Meyer Date: Fri, 7 Jul 2017 11:17:31 +0200 Subject: um: v2: Use generic NOTES macro Signed-off-by: Thomas Meyer Signed-off-by: Richard Weinberger --- arch/um/include/asm/common.lds.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/um/include/asm/common.lds.S b/arch/um/include/asm/common.lds.S index 133055311dce..9e6d5997cfc4 100644 --- a/arch/um/include/asm/common.lds.S +++ b/arch/um/include/asm/common.lds.S @@ -15,7 +15,7 @@ PROVIDE (_unprotected_end = .); . = ALIGN(4096); - .note : { *(.note.*) } + NOTES EXCEPTION_TABLE(0) BUG_TABLE -- cgit v1.2.3-59-g8ed1b From 61e8d462457f202bf0c6393133425ad387825e22 Mon Sep 17 00:00:00 2001 From: Richard Weinberger Date: Thu, 6 Jul 2017 09:35:27 +0200 Subject: um: Correctly check for PTRACE_GETRESET/SETREGSET When checking for PTRACE_GETRESET/SETREGSET, make sure that the correct header file is included. We need linux/ptrace.h which contains all ptrace UAPI related defines. Otherwise #if defined(PTRACE_GETRESET) is always false. Cc: Florian Fainelli Signed-off-by: Richard Weinberger --- arch/x86/um/user-offsets.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c index 8af0fb5d2780..ae4cd58c0c7a 100644 --- a/arch/x86/um/user-offsets.c +++ b/arch/x86/um/user-offsets.c @@ -5,7 +5,7 @@ #include #include #define __FRAME_OFFSETS -#include +#include #include #ifdef __i386__ -- cgit v1.2.3-59-g8ed1b From 41d0c2ecde19cfe93071ed7b979a53ba60b12840 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 6 Jul 2017 20:51:28 +1000 Subject: powerpc/powernv: Fix local TLB flush for boot and MCE on POWER9 There are two cases outside the normal address space management where a CPU's local TLB is to be flushed: 1. Host boot; in case something has left stale entries in the TLB (e.g., kexec). 2. Machine check; to clean corrupted TLB entries. CPU state restore from deep idle states also flushes the TLB. However this seems to be a side effect of reusing the boot code to set CPU state, rather than a requirement itself. The current flushing has a number of problems with ISA v3.0B: - The current radix mode of the MMU is not taken into account. tlbiel is undefined if the R field does not match the current radix mode. - ISA v3.0B hash must flush the partition and process table caches. - ISA v3.0B radix must flush partition and process scoped translations, partition and process table caches, and also the page walk cache. Add POWER9 cases to handle these, with radix vs hash determined by the host MMU mode. Signed-off-by: Nicholas Piggin Reviewed-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/cpu_setup_power.S | 13 ++++++-- arch/powerpc/kernel/dt_cpu_ftrs.c | 16 ++-------- arch/powerpc/kernel/mce_power.c | 56 ++++++++++++++++++++++++++++++++++- 3 files changed, 67 insertions(+), 18 deletions(-) diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index 10cb2896b2ae..610955fe8b81 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -218,13 +218,20 @@ __init_tlb_power8: ptesync 1: blr +/* + * Flush the TLB in hash mode. Hash must flush with RIC=2 once for process + * and one for partition scope to clear process and partition table entries. + */ __init_tlb_power9: - li r6,POWER9_TLB_SETS_HASH + li r6,POWER9_TLB_SETS_HASH - 1 mtctr r6 li r7,0xc00 /* IS field = 0b11 */ + li r8,0 ptesync -2: tlbiel r7 - addi r7,r7,0x1000 + PPC_TLBIEL(7, 8, 2, 1, 0) + PPC_TLBIEL(7, 8, 2, 0, 0) +2: addi r7,r7,0x1000 + PPC_TLBIEL(7, 8, 0, 0, 0) bdnz 2b ptesync 1: blr diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 4c7656dc4e04..1df770e8cbe0 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -94,9 +94,6 @@ static void (*init_pmu_registers)(void); static void cpufeatures_flush_tlb(void) { - unsigned long rb; - unsigned int i, num_sets; - /* * This is a temporary measure to keep equivalent TLB flush as the * cputable based setup code. @@ -105,24 +102,15 @@ static void cpufeatures_flush_tlb(void) case PVR_POWER8: case PVR_POWER8E: case PVR_POWER8NVL: - num_sets = POWER8_TLB_SETS; + __flush_tlb_power8(POWER8_TLB_SETS); break; case PVR_POWER9: - num_sets = POWER9_TLB_SETS_HASH; + __flush_tlb_power9(POWER9_TLB_SETS_HASH); break; default: - num_sets = 1; pr_err("unknown CPU version for boot TLB flush\n"); break; } - - asm volatile("ptesync" : : : "memory"); - rb = TLBIEL_INVAL_SET; - for (i = 0; i < num_sets; i++) { - asm volatile("tlbiel %0" : : "r" (rb)); - rb += 1 << TLBIEL_INVAL_SET_SHIFT; - } - asm volatile("ptesync" : : : "memory"); } static void __restore_cpu_cpufeatures(void) diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index d24e689e893f..b76ca198e09c 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -53,6 +53,60 @@ static void flush_tlb_206(unsigned int num_sets, unsigned int action) asm volatile("ptesync" : : : "memory"); } +static void flush_tlb_300(unsigned int num_sets, unsigned int action) +{ + unsigned long rb; + unsigned int i; + unsigned int r; + + switch (action) { + case TLB_INVAL_SCOPE_GLOBAL: + rb = TLBIEL_INVAL_SET; + break; + case TLB_INVAL_SCOPE_LPID: + rb = TLBIEL_INVAL_SET_LPID; + break; + default: + BUG(); + break; + } + + asm volatile("ptesync" : : : "memory"); + + if (early_radix_enabled()) + r = 1; + else + r = 0; + + /* + * First flush table/PWC caches with set 0, then flush the + * rest of the sets, partition scope. Radix must then do it + * all again with process scope. Hash just has to flush + * process table. + */ + asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4) : : + "r"(rb), "r"(0), "i"(2), "i"(0), "r"(r)); + for (i = 1; i < num_sets; i++) { + unsigned long set = i * (1< Date: Thu, 6 Jul 2017 18:46:43 +1000 Subject: powerpc/asm: Mark cr0 as clobbered in mftb() The workaround for the CELL timebase bug does not correctly mark cr0 as being clobbered. This means GCC doesn't know that the asm block changes cr0 and might leave the result of an unrelated comparison in cr0 across the block, which we then trash, leading to basically random behaviour. Fixes: 859deea949c3 ("[POWERPC] Cell timebase bug workaround") Cc: stable@vger.kernel.org # v2.6.19+ Signed-off-by: Oliver O'Halloran [mpe: Tweak change log and flag for stable] Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/reg.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 7e50e47375d6..a3b6575c7842 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -1303,7 +1303,7 @@ static inline void msr_check_and_clear(unsigned long bits) " .llong 0\n" \ ".previous" \ : "=r" (rval) \ - : "i" (CPU_FTR_CELL_TB_BUG), "i" (SPRN_TBRL)); \ + : "i" (CPU_FTR_CELL_TB_BUG), "i" (SPRN_TBRL) : "cr0"); \ rval;}) #else #define mftb() ({unsigned long rval; \ -- cgit v1.2.3-59-g8ed1b From c17d5d5f51f72f24e0e17a4450ae5010bf6962d9 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Mon, 10 Jul 2017 14:53:31 -0500 Subject: target: export lio pgr/alua support as device attr Older kernels could crash or hang if the user write/read some ALUA files with pscsi and tcmu backends. This patch exports if LIO supports executing PGR and ALUA scsi commands/checks for the se_device, so userspace can easily test. Signed-off-by: Mike Christie Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_configfs.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index 9b8abd55c21c..7e87d952bb7a 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -1085,6 +1085,24 @@ static ssize_t block_size_store(struct config_item *item, return count; } +static ssize_t alua_support_show(struct config_item *item, char *page) +{ + struct se_dev_attrib *da = to_attrib(item); + u8 flags = da->da_dev->transport->transport_flags; + + return snprintf(page, PAGE_SIZE, "%d\n", + flags & TRANSPORT_FLAG_PASSTHROUGH_ALUA ? 0 : 1); +} + +static ssize_t pgr_support_show(struct config_item *item, char *page) +{ + struct se_dev_attrib *da = to_attrib(item); + u8 flags = da->da_dev->transport->transport_flags; + + return snprintf(page, PAGE_SIZE, "%d\n", + flags & TRANSPORT_FLAG_PASSTHROUGH_PGR ? 0 : 1); +} + CONFIGFS_ATTR(, emulate_model_alias); CONFIGFS_ATTR(, emulate_dpo); CONFIGFS_ATTR(, emulate_fua_write); @@ -1116,6 +1134,8 @@ CONFIGFS_ATTR(, unmap_granularity); CONFIGFS_ATTR(, unmap_granularity_alignment); CONFIGFS_ATTR(, unmap_zeroes_data); CONFIGFS_ATTR(, max_write_same_len); +CONFIGFS_ATTR_RO(, alua_support); +CONFIGFS_ATTR_RO(, pgr_support); /* * dev_attrib attributes for devices using the target core SBC/SPC @@ -1154,6 +1174,8 @@ struct configfs_attribute *sbc_attrib_attrs[] = { &attr_unmap_granularity_alignment, &attr_unmap_zeroes_data, &attr_max_write_same_len, + &attr_alua_support, + &attr_pgr_support, NULL, }; EXPORT_SYMBOL(sbc_attrib_attrs); @@ -1168,6 +1190,8 @@ struct configfs_attribute *passthrough_attrib_attrs[] = { &attr_hw_block_size, &attr_hw_max_sectors, &attr_hw_queue_depth, + &attr_alua_support, + &attr_pgr_support, NULL, }; EXPORT_SYMBOL(passthrough_attrib_attrs); -- cgit v1.2.3-59-g8ed1b From 0de98709896d9c02ce3121ec3afb524253a5853f Mon Sep 17 00:00:00 2001 From: "Zhou, Wenjia" Date: Tue, 4 Jul 2017 15:47:00 +0800 Subject: drm/i915/gvt: Fix a memory leak in intel_gvt_init_gtt() It will causes memory leak, if the function setup_spt_oos() fail, in the function intel_gvt_init_gtt(), which allocated by get_zeroed_page() and mapped by dma_map_page(). Unmap and free the page, after STP oos initialize fail, it will fix this issue. Signed-off-by: Zhou, Wenjia Signed-off-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/gtt.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 66374dba3b1a..6166e34d892b 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -2259,6 +2259,8 @@ int intel_gvt_init_gtt(struct intel_gvt *gvt) ret = setup_spt_oos(gvt); if (ret) { gvt_err("fail to initialize SPT oos\n"); + dma_unmap_page(dev, daddr, 4096, PCI_DMA_BIDIRECTIONAL); + __free_page(gvt->gtt.scratch_ggtt_page); return ret; } } -- cgit v1.2.3-59-g8ed1b From 3364bf5fd00f0391ad090f547932a5c4b2068dbc Mon Sep 17 00:00:00 2001 From: Ping Gao Date: Tue, 4 Jul 2017 16:09:58 +0800 Subject: drm/i915/gvt: Audit the command buffer address The command buffer address in context like ring buffer base address and wa_ctx address need to be audit to make sure they are in the valid GGTT range. Signed-off-by: Ping Gao Signed-off-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/cmd_parser.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index 51241de5e7a7..713848c36349 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -2536,6 +2536,11 @@ static int scan_workload(struct intel_vgpu_workload *workload) gma_head == gma_tail) return 0; + if (!intel_gvt_ggtt_validate_range(s.vgpu, s.ring_start, s.ring_size)) { + ret = -EINVAL; + goto out; + } + ret = ip_gma_set(&s, gma_head); if (ret) goto out; @@ -2579,6 +2584,11 @@ static int scan_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx) s.rb_va = wa_ctx->indirect_ctx.shadow_va; s.workload = workload; + if (!intel_gvt_ggtt_validate_range(s.vgpu, s.ring_start, s.ring_size)) { + ret = -EINVAL; + goto out; + } + ret = ip_gma_set(&s, gma_head); if (ret) goto out; -- cgit v1.2.3-59-g8ed1b From 08673c3e27aa4407899e4fbb4738dac25370f706 Mon Sep 17 00:00:00 2001 From: Chuanxiao Dong Date: Fri, 7 Jul 2017 13:21:52 +0800 Subject: drm/i915/gvt: Revert "drm/i915/gvt: Fix possible recursive locking issue" This reverts commit 62d02fd1f807bf5a259a242c483c9fb98a242630. The rwsem recursive trace should not be fixed from kvmgt side by using a workqueue and it is an issue should be fixed in VFIO. So this one should be reverted. Signed-off-by: Chuanxiao Dong Cc: Zhenyu Wang Cc: stable@vger.kernel.org # v4.10+ Signed-off-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/gvt.h | 3 --- drivers/gpu/drm/i915/gvt/kvmgt.c | 55 ++++++++-------------------------------- 2 files changed, 10 insertions(+), 48 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index 28d817e96e58..3a74e79eac2f 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -182,9 +182,6 @@ struct intel_vgpu { struct kvm *kvm; struct work_struct release_work; atomic_t released; - struct work_struct unpin_work; - spinlock_t unpin_lock; /* To protect unpin_list */ - struct list_head unpin_list; } vdev; #endif }; diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 75a6e1d8af0d..fd0c85f9ef3c 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -78,7 +78,6 @@ struct gvt_dma { struct rb_node node; gfn_t gfn; unsigned long iova; - struct list_head list; }; static inline bool handle_valid(unsigned long handle) @@ -167,7 +166,6 @@ static void gvt_cache_add(struct intel_vgpu *vgpu, gfn_t gfn, new->gfn = gfn; new->iova = iova; - INIT_LIST_HEAD(&new->list); mutex_lock(&vgpu->vdev.cache_lock); while (*link) { @@ -199,52 +197,26 @@ static void __gvt_cache_remove_entry(struct intel_vgpu *vgpu, kfree(entry); } -static void intel_vgpu_unpin_work(struct work_struct *work) +static void gvt_cache_remove(struct intel_vgpu *vgpu, gfn_t gfn) { - struct intel_vgpu *vgpu = container_of(work, struct intel_vgpu, - vdev.unpin_work); struct device *dev = mdev_dev(vgpu->vdev.mdev); struct gvt_dma *this; - unsigned long gfn; - - for (;;) { - spin_lock(&vgpu->vdev.unpin_lock); - if (list_empty(&vgpu->vdev.unpin_list)) { - spin_unlock(&vgpu->vdev.unpin_lock); - break; - } - this = list_first_entry(&vgpu->vdev.unpin_list, - struct gvt_dma, list); - list_del(&this->list); - spin_unlock(&vgpu->vdev.unpin_lock); - - gfn = this->gfn; - vfio_unpin_pages(dev, &gfn, 1); - kfree(this); - } -} - -static bool gvt_cache_mark_remove(struct intel_vgpu *vgpu, gfn_t gfn) -{ - struct gvt_dma *this; + unsigned long g1; + int rc; mutex_lock(&vgpu->vdev.cache_lock); this = __gvt_cache_find(vgpu, gfn); if (!this) { mutex_unlock(&vgpu->vdev.cache_lock); - return false; + return; } + + g1 = gfn; gvt_dma_unmap_iova(vgpu, this->iova); - /* remove this from rb tree */ - rb_erase(&this->node, &vgpu->vdev.cache); + rc = vfio_unpin_pages(dev, &g1, 1); + WARN_ON(rc != 1); + __gvt_cache_remove_entry(vgpu, this); mutex_unlock(&vgpu->vdev.cache_lock); - - /* put this to the unpin_list */ - spin_lock(&vgpu->vdev.unpin_lock); - list_move_tail(&this->list, &vgpu->vdev.unpin_list); - spin_unlock(&vgpu->vdev.unpin_lock); - - return true; } static void gvt_cache_init(struct intel_vgpu *vgpu) @@ -485,9 +457,6 @@ static int intel_vgpu_create(struct kobject *kobj, struct mdev_device *mdev) } INIT_WORK(&vgpu->vdev.release_work, intel_vgpu_release_work); - INIT_WORK(&vgpu->vdev.unpin_work, intel_vgpu_unpin_work); - spin_lock_init(&vgpu->vdev.unpin_lock); - INIT_LIST_HEAD(&vgpu->vdev.unpin_list); vgpu->vdev.mdev = mdev; mdev_set_drvdata(mdev, vgpu); @@ -517,7 +486,6 @@ static int intel_vgpu_iommu_notifier(struct notifier_block *nb, struct intel_vgpu *vgpu = container_of(nb, struct intel_vgpu, vdev.iommu_notifier); - bool sched_unmap = false; if (action == VFIO_IOMMU_NOTIFY_DMA_UNMAP) { struct vfio_iommu_type1_dma_unmap *unmap = data; @@ -527,10 +495,7 @@ static int intel_vgpu_iommu_notifier(struct notifier_block *nb, end_gfn = gfn + unmap->size / PAGE_SIZE; while (gfn < end_gfn) - sched_unmap |= gvt_cache_mark_remove(vgpu, gfn++); - - if (sched_unmap) - schedule_work(&vgpu->vdev.unpin_work); + gvt_cache_remove(vgpu, gfn++); } return NOTIFY_OK; -- cgit v1.2.3-59-g8ed1b From 4cc74389a551dc95fce72d58c11e55a93b6ecd19 Mon Sep 17 00:00:00 2001 From: Weinan Li Date: Mon, 19 Jun 2017 08:49:17 +0800 Subject: drm/i915/gvt: remove scheduler_mutex in per-engine workload_thread For the vGPU workloads, now GVT-g use per vGPU scheduler, the per-ring work_thread only pick workload belongs to the current vGPU. And with time slice based scheduler, it waits all the engines become idle before do vGPU switch. So we can run free dispatch in per-ring work_thread, different ring running in different 'vGPU' won't happen. For the workloads between vGPU and Host, this scheduler_mutex can't block host to dispatch workload into other ring engines. Here remove this mutex since it impacts the performance when applications use more than 1 ring engines in 1 vgpu. ring0 running in vGPU1, ring1 running in Host. Will happen. ring0 running in vGPU1, ring1 running in vGPU2. Won't happen. Signed-off-by: Weinan Li Signed-off-by: Ping Gao Signed-off-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/scheduler.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 488fdea348a9..5aeba13a5de4 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -464,8 +464,6 @@ struct workload_thread_param { int ring_id; }; -static DEFINE_MUTEX(scheduler_mutex); - static int workload_thread(void *priv) { struct workload_thread_param *p = (struct workload_thread_param *)priv; @@ -497,8 +495,6 @@ static int workload_thread(void *priv) if (!workload) break; - mutex_lock(&scheduler_mutex); - gvt_dbg_sched("ring id %d next workload %p vgpu %d\n", workload->ring_id, workload, workload->vgpu->id); @@ -537,9 +533,6 @@ complete: FORCEWAKE_ALL); intel_runtime_pm_put(gvt->dev_priv); - - mutex_unlock(&scheduler_mutex); - } return 0; } -- cgit v1.2.3-59-g8ed1b From 0cf5ec41839d82ee7f8fbb47f137b7afc562b9f1 Mon Sep 17 00:00:00 2001 From: Chuanxiao Dong Date: Fri, 23 Jun 2017 13:01:11 +0800 Subject: drm/i915/gvt: Use fence error from GVT request for workload status The req->fence.error will be set if this request caused GPU hang so we can use this value to workload->status to indicate whether this GVT request caused any problem. If it caused GPU hang, we shouldn't trigger any context switch back to the guest. v2: - only take -EIO from fence->error. (Zhenyu) Fixes: 8f1117abb408 (drm/i915/gvt: handle workload lifecycle properly) Signed-off-by: Chuanxiao Dong Cc: Zhenyu Wang Signed-off-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/scheduler.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 5aeba13a5de4..4f7057d62d88 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -174,15 +174,6 @@ static int shadow_context_status_change(struct notifier_block *nb, atomic_set(&workload->shadow_ctx_active, 1); break; case INTEL_CONTEXT_SCHEDULE_OUT: - /* If the status is -EINPROGRESS means this workload - * doesn't meet any issue during dispatching so when - * get the SCHEDULE_OUT set the status to be zero for - * good. If the status is NOT -EINPROGRESS means there - * is something wrong happened during dispatching and - * the status should not be set to zero - */ - if (workload->status == -EINPROGRESS) - workload->status = 0; atomic_set(&workload->shadow_ctx_active, 0); break; default: @@ -427,6 +418,18 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id) wait_event(workload->shadow_ctx_status_wq, !atomic_read(&workload->shadow_ctx_active)); + /* If this request caused GPU hang, req->fence.error will + * be set to -EIO. Use -EIO to set workload status so + * that when this request caused GPU hang, didn't trigger + * context switch interrupt to guest. + */ + if (likely(workload->status == -EINPROGRESS)) { + if (workload->req->fence.error == -EIO) + workload->status = -EIO; + else + workload->status = 0; + } + i915_gem_request_put(fetch_and_zero(&workload->req)); if (!workload->status && !vgpu->resetting) { -- cgit v1.2.3-59-g8ed1b From 65553b12e8fd3730b07e486c15dd6574563ddc58 Mon Sep 17 00:00:00 2001 From: Kailang Yang Date: Tue, 11 Jul 2017 15:15:47 +0800 Subject: ALSA: hda/realtek - New codec device ID for ALC1220 Codec ID is 0x1168. It is another ALC1220 codec. Signed-off-by: Kailang Yang Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index e2116d2ea529..45d58fc1df39 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -379,6 +379,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec) break; case 0x10ec0899: case 0x10ec0900: + case 0x10ec1168: case 0x10ec1220: alc_update_coef_idx(codec, 0x7, 1<<1, 0); break; @@ -7815,6 +7816,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = { HDA_CODEC_ENTRY(0x10ec0892, "ALC892", patch_alc662), HDA_CODEC_ENTRY(0x10ec0899, "ALC898", patch_alc882), HDA_CODEC_ENTRY(0x10ec0900, "ALC1150", patch_alc882), + HDA_CODEC_ENTRY(0x10ec1168, "ALC1220", patch_alc882), HDA_CODEC_ENTRY(0x10ec1220, "ALC1220", patch_alc882), {} /* terminator */ }; -- cgit v1.2.3-59-g8ed1b From 50740024bc393b608f7e391ac35e70f33938dd24 Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Mon, 26 Jun 2017 10:33:49 +0200 Subject: drm/i915: Make DP-MST connector info work Commit 9a148a96fc3a ("drm/i915/debugfs: add dp mst info") adds support for DP-MST to intel_connector_info, but forgot to remove the early return for DP-MST. Remove it, and print out MST connectors directly. Fixes: 9a148a96fc3a ("drm/i915/debugfs: add dp mst info") Cc: # v4.11+ Cc: Dhinakaran Pandiyan Cc: Libin Yang Signed-off-by: Maarten Lankhorst Link: http://patchwork.freedesktop.org/patch/msgid/20170626083349.24389-1-maarten.lankhorst@linux.intel.com Reviewed-by: Dhinakaran Pandiyan (cherry picked from commit 77d1f615c78a73a04254fa2bff07ee9fa27145d9) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_debugfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 4577b0af6886..23cd865a3da6 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -3083,7 +3083,7 @@ static void intel_connector_info(struct seq_file *m, connector->display_info.cea_rev); } - if (!intel_encoder || intel_encoder->type == INTEL_OUTPUT_DP_MST) + if (!intel_encoder) return; switch (connector->connector_type) { -- cgit v1.2.3-59-g8ed1b From a66ca4146f3f736ff968c099926ccb1c1761b1a4 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 5 Jul 2017 16:24:56 +0100 Subject: spufs: Implement show_options Implement the show_options superblock op for spufs as part of a bid to get rid of s_options and generic_show_options() to make it easier to implement a context-based mount where the mount options can be passed individually over a file descriptor. Signed-off-by: David Howells cc: Jeremy Kerr cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Al Viro --- arch/powerpc/platforms/cell/spufs/inode.c | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index d8af9bc0489f..9558d725a99b 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -605,6 +605,24 @@ static const match_table_t spufs_tokens = { { Opt_err, NULL }, }; +static int spufs_show_options(struct seq_file *m, struct dentry *root) +{ + struct spufs_sb_info *sbi = spufs_get_sb_info(root->d_sb); + struct inode *inode = root->d_inode; + + if (!uid_eq(inode->i_uid, GLOBAL_ROOT_UID)) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, inode->i_uid)); + if (!gid_eq(inode->i_gid, GLOBAL_ROOT_GID)) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, inode->i_gid)); + if ((inode->i_mode & S_IALLUGO) != 0775) + seq_printf(m, ",mode=%o", inode->i_mode); + if (sbi->debug) + seq_puts(m, ",debug"); + return 0; +} + static int spufs_parse_options(struct super_block *sb, char *options, struct inode *root) { @@ -724,11 +742,9 @@ spufs_fill_super(struct super_block *sb, void *data, int silent) .destroy_inode = spufs_destroy_inode, .statfs = simple_statfs, .evict_inode = spufs_evict_inode, - .show_options = generic_show_options, + .show_options = spufs_show_options, }; - save_mount_options(sb, data); - info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) return -ENOMEM; -- cgit v1.2.3-59-g8ed1b From 3ab7947ac3b5cd625c186bb608678bffd881e472 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 5 Jul 2017 16:25:03 +0100 Subject: befs: Implement show_options Implement the show_options superblock op for befs as part of a bid to get rid of s_options and generic_show_options() to make it easier to implement a context-based mount where the mount options can be passed individually over a file descriptor. Signed-off-by: David Howells cc: Luis de Bethencourt cc: Salah Triki Signed-off-by: Al Viro --- fs/befs/linuxvfs.c | 24 +++++++++++++++++++++--- 1 file changed, 21 insertions(+), 3 deletions(-) diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index 63e7c4760bfb..4a4a5a366158 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -20,6 +20,7 @@ #include #include #include +#include #include "befs.h" #include "btree.h" @@ -53,6 +54,7 @@ static int befs_nls2utf(struct super_block *sb, const char *in, int in_len, static void befs_put_super(struct super_block *); static int befs_remount(struct super_block *, int *, char *); static int befs_statfs(struct dentry *, struct kstatfs *); +static int befs_show_options(struct seq_file *, struct dentry *); static int parse_options(char *, struct befs_mount_options *); static struct dentry *befs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type); @@ -66,7 +68,7 @@ static const struct super_operations befs_sops = { .put_super = befs_put_super, /* uninit super */ .statfs = befs_statfs, /* statfs */ .remount_fs = befs_remount, - .show_options = generic_show_options, + .show_options = befs_show_options, }; /* slab cache for befs_inode_info objects */ @@ -771,6 +773,24 @@ parse_options(char *options, struct befs_mount_options *opts) return 1; } +static int befs_show_options(struct seq_file *m, struct dentry *root) +{ + struct befs_sb_info *befs_sb = BEFS_SB(root->d_sb); + struct befs_mount_options *opts = &befs_sb->mount_opts; + + if (!uid_eq(opts->uid, GLOBAL_ROOT_UID)) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, opts->uid)); + if (!gid_eq(opts->gid, GLOBAL_ROOT_GID)) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, opts->gid)); + if (opts->iocharset) + seq_printf(m, ",charset=%s", opts->iocharset); + if (opts->debug) + seq_puts(m, ",debug"); + return 0; +} + /* This function has the responsibiltiy of getting the * filesystem ready for unmounting. * Basically, we free everything that we allocated in @@ -804,8 +824,6 @@ befs_fill_super(struct super_block *sb, void *data, int silent) const off_t x86_sb_off = 512; int blocksize; - save_mount_options(sb, data); - sb->s_fs_info = kzalloc(sizeof(*befs_sb), GFP_KERNEL); if (sb->s_fs_info == NULL) goto unacquire_none; -- cgit v1.2.3-59-g8ed1b From 26a7655e6a55768a082336dac8a4563344e890a2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 5 Jul 2017 16:25:16 +0100 Subject: affs: Implement show_options Implement the show_options superblock op for affs as part of a bid to get rid of s_options and generic_show_options() to make it easier to implement a context-based mount where the mount options can be passed individually over a file descriptor. Signed-off-by: David Howells Signed-off-by: Al Viro --- fs/affs/super.c | 42 +++++++++++++++++++++++++++++++++++++----- 1 file changed, 37 insertions(+), 5 deletions(-) diff --git a/fs/affs/super.c b/fs/affs/super.c index c2c27a8f128e..7bf47a41cb4f 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -20,9 +20,11 @@ #include #include #include +#include #include "affs.h" static int affs_statfs(struct dentry *dentry, struct kstatfs *buf); +static int affs_show_options(struct seq_file *m, struct dentry *root); static int affs_remount (struct super_block *sb, int *flags, char *data); static void @@ -159,7 +161,7 @@ static const struct super_operations affs_sops = { .sync_fs = affs_sync_fs, .statfs = affs_statfs, .remount_fs = affs_remount, - .show_options = generic_show_options, + .show_options = affs_show_options, }; enum { @@ -293,6 +295,40 @@ parse_options(char *options, kuid_t *uid, kgid_t *gid, int *mode, int *reserved, return 1; } +static int affs_show_options(struct seq_file *m, struct dentry *root) +{ + struct super_block *sb = root->d_sb; + struct affs_sb_info *sbi = AFFS_SB(sb); + + if (sb->s_blocksize) + seq_printf(m, ",bs=%lu", sb->s_blocksize); + if (affs_test_opt(sbi->s_flags, SF_SETMODE)) + seq_printf(m, ",mode=%o", sbi->s_mode); + if (affs_test_opt(sbi->s_flags, SF_MUFS)) + seq_puts(m, ",mufs"); + if (affs_test_opt(sbi->s_flags, SF_NO_TRUNCATE)) + seq_puts(m, ",nofilenametruncate"); + if (affs_test_opt(sbi->s_flags, SF_PREFIX)) + seq_printf(m, ",prefix=%s", sbi->s_prefix); + if (affs_test_opt(sbi->s_flags, SF_IMMUTABLE)) + seq_puts(m, ",protect"); + if (sbi->s_reserved != 2) + seq_printf(m, ",reserved=%u", sbi->s_reserved); + if (sbi->s_root_block != (sbi->s_reserved + sbi->s_partition_size - 1) / 2) + seq_printf(m, ",root=%u", sbi->s_root_block); + if (affs_test_opt(sbi->s_flags, SF_SETGID)) + seq_printf(m, ",setgid=%u", + from_kgid_munged(&init_user_ns, sbi->s_gid)); + if (affs_test_opt(sbi->s_flags, SF_SETUID)) + seq_printf(m, ",setuid=%u", + from_kuid_munged(&init_user_ns, sbi->s_uid)); + if (affs_test_opt(sbi->s_flags, SF_VERBOSE)) + seq_puts(m, ",verbose"); + if (sbi->s_volume[0]) + seq_printf(m, ",volume=%s", sbi->s_volume); + return 0; +} + /* This function definitely needs to be split up. Some fine day I'll * hopefully have the guts to do so. Until then: sorry for the mess. */ @@ -316,8 +352,6 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent) u8 sig[4]; int ret; - save_mount_options(sb, data); - pr_debug("read_super(%s)\n", data ? (const char *)data : "no options"); sb->s_magic = AFFS_SUPER_MAGIC; @@ -548,8 +582,6 @@ affs_remount(struct super_block *sb, int *flags, char *data) } flush_delayed_work(&sbi->sb_work); - if (new_opts) - replace_mount_options(sb, new_opts); sbi->s_flags = mount_flags; sbi->s_mode = mode; -- cgit v1.2.3-59-g8ed1b From 677018a6ce620c8ca85abae1a07a41d66247d420 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 5 Jul 2017 16:25:23 +0100 Subject: afs: Implement show_options Implement the show_options superblock op for afs as part of a bid to get rid of s_options and generic_show_options() to make it easier to implement a context-based mount where the mount options can be passed individually over a file descriptor. Also implement the show_devname op to display the correct device name and thus avoid the need to display the cell= and volume= options. Signed-off-by: David Howells cc: linux-afs@lists.infradead.org Signed-off-by: Al Viro --- fs/afs/super.c | 45 +++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 43 insertions(+), 2 deletions(-) diff --git a/fs/afs/super.c b/fs/afs/super.c index c79633e5cfd8..35d7e550b29c 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -37,6 +37,8 @@ static void afs_kill_super(struct super_block *sb); static struct inode *afs_alloc_inode(struct super_block *sb); static void afs_destroy_inode(struct inode *inode); static int afs_statfs(struct dentry *dentry, struct kstatfs *buf); +static int afs_show_devname(struct seq_file *m, struct dentry *root); +static int afs_show_options(struct seq_file *m, struct dentry *root); struct file_system_type afs_fs_type = { .owner = THIS_MODULE, @@ -53,7 +55,8 @@ static const struct super_operations afs_super_ops = { .drop_inode = afs_drop_inode, .destroy_inode = afs_destroy_inode, .evict_inode = afs_evict_inode, - .show_options = generic_show_options, + .show_devname = afs_show_devname, + .show_options = afs_show_options, }; static struct kmem_cache *afs_inode_cachep; @@ -135,6 +138,45 @@ void __exit afs_fs_exit(void) _leave(""); } +/* + * Display the mount device name in /proc/mounts. + */ +static int afs_show_devname(struct seq_file *m, struct dentry *root) +{ + struct afs_super_info *as = root->d_sb->s_fs_info; + struct afs_volume *volume = as->volume; + struct afs_cell *cell = volume->cell; + const char *suf = ""; + char pref = '%'; + + switch (volume->type) { + case AFSVL_RWVOL: + break; + case AFSVL_ROVOL: + pref = '#'; + if (volume->type_force) + suf = ".readonly"; + break; + case AFSVL_BACKVOL: + pref = '#'; + suf = ".backup"; + break; + } + + seq_printf(m, "%c%s:%s%s", pref, cell->name, volume->vlocation->vldb.name, suf); + return 0; +} + +/* + * Display the mount options in /proc/mounts. + */ +static int afs_show_options(struct seq_file *m, struct dentry *root) +{ + if (test_bit(AFS_VNODE_AUTOCELL, &AFS_FS_I(d_inode(root))->flags)) + seq_puts(m, "autocell"); + return 0; +} + /* * parse the mount options * - this function has been shamelessly adapted from the ext3 fs which @@ -426,7 +468,6 @@ static struct dentry *afs_mount(struct file_system_type *fs_type, deactivate_locked_super(sb); goto error; } - save_mount_options(sb, new_opts); sb->s_flags |= MS_ACTIVE; } else { _debug("reuse"); -- cgit v1.2.3-59-g8ed1b From 86a1da6d30ad727c2a9cc5d6a51bff6d830036b5 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 5 Jul 2017 16:25:30 +0100 Subject: isofs: Implement show_options Implement the show_options superblock op for omfs as part of a bid to get rid of s_options and generic_show_options() to make it easier to implement a context-based mount where the mount options can be passed individually over a file descriptor. Signed-off-by: David Howells cc: Jan Kara Signed-off-by: Al Viro --- fs/isofs/inode.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++++--- fs/isofs/isofs.h | 3 +++ 2 files changed, 51 insertions(+), 3 deletions(-) diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 020ba0936146..f80ee600d1bc 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -23,6 +23,7 @@ #include #include #include +#include #include "isofs.h" #include "zisofs.h" @@ -57,6 +58,7 @@ static void isofs_put_super(struct super_block *sb) static int isofs_read_inode(struct inode *, int relocated); static int isofs_statfs (struct dentry *, struct kstatfs *); +static int isofs_show_options(struct seq_file *, struct dentry *); static struct kmem_cache *isofs_inode_cachep; @@ -123,7 +125,7 @@ static const struct super_operations isofs_sops = { .put_super = isofs_put_super, .statfs = isofs_statfs, .remount_fs = isofs_remount, - .show_options = generic_show_options, + .show_options = isofs_show_options, }; @@ -472,6 +474,48 @@ static int parse_options(char *options, struct iso9660_options *popt) return 1; } +/* + * Display the mount options in /proc/mounts. + */ +static int isofs_show_options(struct seq_file *m, struct dentry *root) +{ + struct isofs_sb_info *sbi = ISOFS_SB(root->d_sb); + + if (!sbi->s_rock) seq_puts(m, ",norock"); + else if (!sbi->s_joliet_level) seq_puts(m, ",nojoliet"); + if (sbi->s_cruft) seq_puts(m, ",cruft"); + if (sbi->s_hide) seq_puts(m, ",hide"); + if (sbi->s_nocompress) seq_puts(m, ",nocompress"); + if (sbi->s_overriderockperm) seq_puts(m, ",overriderockperm"); + if (sbi->s_showassoc) seq_puts(m, ",showassoc"); + if (sbi->s_utf8) seq_puts(m, ",utf8"); + + if (sbi->s_check) seq_printf(m, ",check=%c", sbi->s_check); + if (sbi->s_mapping) seq_printf(m, ",map=%c", sbi->s_mapping); + if (sbi->s_session != -1) seq_printf(m, ",session=%u", sbi->s_session); + if (sbi->s_sbsector != -1) seq_printf(m, ",sbsector=%u", sbi->s_sbsector); + + if (root->d_sb->s_blocksize != 1024) + seq_printf(m, ",blocksize=%lu", root->d_sb->s_blocksize); + + if (sbi->s_uid_set) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, sbi->s_uid)); + if (sbi->s_gid_set) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, sbi->s_gid)); + + if (sbi->s_dmode != ISOFS_INVALID_MODE) + seq_printf(m, ",dmode=%o", sbi->s_dmode); + if (sbi->s_fmode != ISOFS_INVALID_MODE) + seq_printf(m, ",fmode=%o", sbi->s_fmode); + + if (sbi->s_nls_iocharset && + strcmp(sbi->s_nls_iocharset->charset, CONFIG_NLS_DEFAULT) != 0) + seq_printf(m, ",iocharset=%s", sbi->s_nls_iocharset->charset); + return 0; +} + /* * look if the driver can tell the multi session redirection value * @@ -583,8 +627,6 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent) int table, error = -EINVAL; unsigned int vol_desc_start; - save_mount_options(s, data); - sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) return -ENOMEM; @@ -605,6 +647,8 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent) opt.blocksize = sb_min_blocksize(s, opt.blocksize); sbi->s_high_sierra = 0; /* default is iso9660 */ + sbi->s_session = opt.session; + sbi->s_sbsector = opt.sbsector; vol_desc_start = (opt.sbsector != -1) ? opt.sbsector : isofs_get_last_session(s,opt.session); @@ -911,6 +955,7 @@ root_found: table += 2; if (opt.check == 'r') table++; + sbi->s_check = opt.check; if (table) s->s_d_op = &isofs_dentry_ops[table - 1]; diff --git a/fs/isofs/isofs.h b/fs/isofs/isofs.h index 0ac4c1f73fbd..133a456b0425 100644 --- a/fs/isofs/isofs.h +++ b/fs/isofs/isofs.h @@ -36,8 +36,11 @@ struct isofs_sb_info { unsigned long s_max_size; int s_rock_offset; /* offset of SUSP fields within SU area */ + s32 s_sbsector; unsigned char s_joliet_level; unsigned char s_mapping; + unsigned char s_check; + unsigned char s_session; unsigned int s_high_sierra:1; unsigned int s_rock:2; unsigned int s_utf8:1; -- cgit v1.2.3-59-g8ed1b From c4fac9100456995c10b65c13be84554258ed7fc8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 5 Jul 2017 16:25:37 +0100 Subject: 9p: Implement show_options Implement the show_options superblock op for 9p as part of a bid to get rid of s_options and generic_show_options() to make it easier to implement a context-based mount where the mount options can be passed individually over a file descriptor. Signed-off-by: David Howells cc: Eric Van Hensbergen cc: Ron Minnich cc: Latchesar Ionkov cc: v9fs-developer@lists.sourceforge.net Signed-off-by: Al Viro --- fs/9p/v9fs.c | 61 ++++++++++++++++++++++++++++++++++++++++++++++ fs/9p/v9fs.h | 3 +++ fs/9p/vfs_super.c | 6 ++--- include/net/9p/client.h | 13 ++++++++++ include/net/9p/transport.h | 1 + net/9p/client.c | 25 +++++++++++++++++++ net/9p/trans_fd.c | 31 ++++++++++++++++++++--- net/9p/trans_rdma.c | 31 ++++++++++++++++++++--- 8 files changed, 161 insertions(+), 10 deletions(-) diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index c202930086ed..8fb89ddc6cc7 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include @@ -82,6 +83,13 @@ static const match_table_t tokens = { {Opt_err, NULL} }; +static const char *const v9fs_cache_modes[nr__p9_cache_modes] = { + [CACHE_NONE] = "none", + [CACHE_MMAP] = "mmap", + [CACHE_LOOSE] = "loose", + [CACHE_FSCACHE] = "fscache", +}; + /* Interpret mount options for cache mode */ static int get_cache_mode(char *s) { @@ -104,6 +112,58 @@ static int get_cache_mode(char *s) return version; } +/* + * Display the mount options in /proc/mounts. + */ +int v9fs_show_options(struct seq_file *m, struct dentry *root) +{ + struct v9fs_session_info *v9ses = root->d_sb->s_fs_info; + + if (v9ses->debug) + seq_printf(m, ",debug=%x", v9ses->debug); + if (!uid_eq(v9ses->dfltuid, V9FS_DEFUID)) + seq_printf(m, ",dfltuid=%u", + from_kuid_munged(&init_user_ns, v9ses->dfltuid)); + if (!gid_eq(v9ses->dfltgid, V9FS_DEFGID)) + seq_printf(m, ",dfltgid=%u", + from_kgid_munged(&init_user_ns, v9ses->dfltgid)); + if (v9ses->afid != ~0) + seq_printf(m, ",afid=%u", v9ses->afid); + if (strcmp(v9ses->uname, V9FS_DEFUSER) != 0) + seq_printf(m, ",uname=%s", v9ses->uname); + if (strcmp(v9ses->aname, V9FS_DEFANAME) != 0) + seq_printf(m, ",aname=%s", v9ses->aname); + if (v9ses->nodev) + seq_puts(m, ",nodevmap"); + if (v9ses->cache) + seq_printf(m, ",%s", v9fs_cache_modes[v9ses->cache]); +#ifdef CONFIG_9P_FSCACHE + if (v9ses->cachetag && v9ses->cache == CACHE_FSCACHE) + seq_printf(m, ",cachetag=%s", v9ses->cachetag); +#endif + + switch (v9ses->flags & V9FS_ACCESS_MASK) { + case V9FS_ACCESS_USER: + seq_puts(m, ",access=user"); + break; + case V9FS_ACCESS_ANY: + seq_puts(m, ",access=any"); + break; + case V9FS_ACCESS_CLIENT: + seq_puts(m, ",access=client"); + break; + case V9FS_ACCESS_SINGLE: + seq_printf(m, ",access=%u", + from_kuid_munged(&init_user_ns, v9ses->uid)); + break; + } + + if (v9ses->flags & V9FS_POSIX_ACL) + seq_puts(m, ",posixacl"); + + return p9_show_client_options(m, v9ses->clnt); +} + /** * v9fs_parse_options - parse mount options into session structure * @v9ses: existing v9fs session information @@ -230,6 +290,7 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) break; case Opt_cachetag: #ifdef CONFIG_9P_FSCACHE + kfree(v9ses->cachetag); v9ses->cachetag = match_strdup(&args[0]); #endif break; diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 76eaf49abd3a..982e017acadb 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -67,6 +67,7 @@ enum p9_cache_modes { CACHE_MMAP, CACHE_LOOSE, CACHE_FSCACHE, + nr__p9_cache_modes }; /** @@ -137,6 +138,8 @@ static inline struct v9fs_inode *V9FS_I(const struct inode *inode) return container_of(inode, struct v9fs_inode, vfs_inode); } +extern int v9fs_show_options(struct seq_file *m, struct dentry *root); + struct p9_fid *v9fs_session_init(struct v9fs_session_info *, const char *, char *); extern void v9fs_session_close(struct v9fs_session_info *v9ses); diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index a0965fb587a5..8b75463cb211 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -33,7 +33,6 @@ #include #include #include -#include #include #include #include @@ -104,7 +103,6 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses, sb->s_flags |= MS_POSIXACL; #endif - save_mount_options(sb, data); return 0; } @@ -349,7 +347,7 @@ static const struct super_operations v9fs_super_ops = { .destroy_inode = v9fs_destroy_inode, .statfs = simple_statfs, .evict_inode = v9fs_evict_inode, - .show_options = generic_show_options, + .show_options = v9fs_show_options, .umount_begin = v9fs_umount_begin, .write_inode = v9fs_write_inode, }; @@ -360,7 +358,7 @@ static const struct super_operations v9fs_super_ops_dotl = { .statfs = v9fs_statfs, .drop_inode = v9fs_drop_inode, .evict_inode = v9fs_evict_inode, - .show_options = generic_show_options, + .show_options = v9fs_show_options, .umount_begin = v9fs_umount_begin, .write_inode = v9fs_write_inode_dotl, }; diff --git a/include/net/9p/client.h b/include/net/9p/client.h index b582339ccef5..7af9d769b97d 100644 --- a/include/net/9p/client.h +++ b/include/net/9p/client.h @@ -157,6 +157,18 @@ struct p9_client { enum p9_trans_status status; void *trans; + union { + struct { + int rfd; + int wfd; + } fd; + struct { + u16 port; + bool privport; + + } tcp; + } trans_opts; + struct p9_idpool *fidpool; struct list_head fidlist; @@ -213,6 +225,7 @@ struct p9_dirent { struct iov_iter; +int p9_show_client_options(struct seq_file *m, struct p9_client *clnt); int p9_client_statfs(struct p9_fid *fid, struct p9_rstatfs *sb); int p9_client_rename(struct p9_fid *fid, struct p9_fid *newdirfid, const char *name); diff --git a/include/net/9p/transport.h b/include/net/9p/transport.h index 5122b5e40f78..1625fb842ac4 100644 --- a/include/net/9p/transport.h +++ b/include/net/9p/transport.h @@ -62,6 +62,7 @@ struct p9_trans_module { int (*cancelled)(struct p9_client *, struct p9_req_t *req); int (*zc_request)(struct p9_client *, struct p9_req_t *, struct iov_iter *, struct iov_iter *, int , int, int); + int (*show_options)(struct seq_file *, struct p9_client *); }; void v9fs_register_trans(struct p9_trans_module *m); diff --git a/net/9p/client.c b/net/9p/client.c index 1218fb3b52da..4674235b0d9b 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include #include "protocol.h" @@ -77,6 +78,30 @@ inline int p9_is_proto_dotu(struct p9_client *clnt) } EXPORT_SYMBOL(p9_is_proto_dotu); +int p9_show_client_options(struct seq_file *m, struct p9_client *clnt) +{ + if (clnt->msize != 8192) + seq_printf(m, ",msize=%u", clnt->msize); + seq_printf(m, "trans=%s", clnt->trans_mod->name); + + switch (clnt->proto_version) { + case p9_proto_legacy: + seq_puts(m, ",noextend"); + break; + case p9_proto_2000u: + seq_puts(m, ",version=9p2000.u"); + break; + case p9_proto_2000L: + /* Default */ + break; + } + + if (clnt->trans_mod->show_options) + return clnt->trans_mod->show_options(m, clnt); + return 0; +} +EXPORT_SYMBOL(p9_show_client_options); + /* * Some error codes are taken directly from the server replies, * make sure they are valid. diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 7bc2208b6cc4..f2e0eaf58018 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #include #include @@ -51,6 +52,9 @@ #define MAX_SOCK_BUF (64*1024) #define MAXPOLLWADDR 2 +static struct p9_trans_module p9_tcp_trans; +static struct p9_trans_module p9_fd_trans; + /** * struct p9_fd_opts - per-transport options * @rfd: file descriptor for reading (trans=fd) @@ -63,7 +67,7 @@ struct p9_fd_opts { int rfd; int wfd; u16 port; - int privport; + bool privport; }; /* @@ -720,6 +724,20 @@ static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req) return 0; } +static int p9_fd_show_options(struct seq_file *m, struct p9_client *clnt) +{ + if (clnt->trans_mod == &p9_tcp_trans) { + if (clnt->trans_opts.tcp.port != P9_PORT) + seq_printf(m, "port=%u", clnt->trans_opts.tcp.port); + } else if (clnt->trans_mod == &p9_fd_trans) { + if (clnt->trans_opts.fd.rfd != ~0) + seq_printf(m, "rfd=%u", clnt->trans_opts.fd.rfd); + if (clnt->trans_opts.fd.wfd != ~0) + seq_printf(m, "wfd=%u", clnt->trans_opts.fd.wfd); + } + return 0; +} + /** * parse_opts - parse mount options into p9_fd_opts structure * @params: options string passed from mount @@ -738,7 +756,7 @@ static int parse_opts(char *params, struct p9_fd_opts *opts) opts->port = P9_PORT; opts->rfd = ~0; opts->wfd = ~0; - opts->privport = 0; + opts->privport = false; if (!params) return 0; @@ -776,7 +794,7 @@ static int parse_opts(char *params, struct p9_fd_opts *opts) opts->wfd = option; break; case Opt_privport: - opts->privport = 1; + opts->privport = true; break; default: continue; @@ -942,6 +960,8 @@ p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args) csocket = NULL; + client->trans_opts.tcp.port = opts.port; + client->trans_opts.tcp.privport = opts.privport; sin_server.sin_family = AF_INET; sin_server.sin_addr.s_addr = in_aton(addr); sin_server.sin_port = htons(opts.port); @@ -1020,6 +1040,8 @@ p9_fd_create(struct p9_client *client, const char *addr, char *args) struct p9_fd_opts opts; parse_opts(args, &opts); + client->trans_opts.fd.rfd = opts.rfd; + client->trans_opts.fd.wfd = opts.wfd; if (opts.rfd == ~0 || opts.wfd == ~0) { pr_err("Insufficient options for proto=fd\n"); @@ -1044,6 +1066,7 @@ static struct p9_trans_module p9_tcp_trans = { .request = p9_fd_request, .cancel = p9_fd_cancel, .cancelled = p9_fd_cancelled, + .show_options = p9_fd_show_options, .owner = THIS_MODULE, }; @@ -1056,6 +1079,7 @@ static struct p9_trans_module p9_unix_trans = { .request = p9_fd_request, .cancel = p9_fd_cancel, .cancelled = p9_fd_cancelled, + .show_options = p9_fd_show_options, .owner = THIS_MODULE, }; @@ -1068,6 +1092,7 @@ static struct p9_trans_module p9_fd_trans = { .request = p9_fd_request, .cancel = p9_fd_cancel, .cancelled = p9_fd_cancelled, + .show_options = p9_fd_show_options, .owner = THIS_MODULE, }; diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 553ed4ecb6a0..6d8e3031978f 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include #include @@ -70,6 +71,8 @@ * @dm_mr: DMA Memory Region pointer * @lkey: The local access only memory region key * @timeout: Number of uSecs to wait for connection management events + * @privport: Whether a privileged port may be used + * @port: The port to use * @sq_depth: The depth of the Send Queue * @sq_sem: Semaphore for the SQ * @rq_depth: The depth of the Receive Queue. @@ -95,6 +98,8 @@ struct p9_trans_rdma { struct ib_qp *qp; struct ib_cq *cq; long timeout; + bool privport; + u16 port; int sq_depth; struct semaphore sq_sem; int rq_depth; @@ -133,10 +138,10 @@ struct p9_rdma_context { */ struct p9_rdma_opts { short port; + bool privport; int sq_depth; int rq_depth; long timeout; - int privport; }; /* @@ -159,6 +164,23 @@ static match_table_t tokens = { {Opt_err, NULL}, }; +static int p9_rdma_show_options(struct seq_file *m, struct p9_client *clnt) +{ + struct p9_trans_rdma *rdma = clnt->trans; + + if (rdma->port != P9_PORT) + seq_printf(m, ",port=%u", rdma->port); + if (rdma->sq_depth != P9_RDMA_SQ_DEPTH) + seq_printf(m, ",sq=%u", rdma->sq_depth); + if (rdma->rq_depth != P9_RDMA_RQ_DEPTH) + seq_printf(m, ",rq=%u", rdma->rq_depth); + if (rdma->timeout != P9_RDMA_TIMEOUT) + seq_printf(m, ",timeout=%lu", rdma->timeout); + if (rdma->privport) + seq_puts(m, ",privport"); + return 0; +} + /** * parse_opts - parse mount options into rdma options structure * @params: options string passed from mount @@ -177,7 +199,7 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts) opts->sq_depth = P9_RDMA_SQ_DEPTH; opts->rq_depth = P9_RDMA_RQ_DEPTH; opts->timeout = P9_RDMA_TIMEOUT; - opts->privport = 0; + opts->privport = false; if (!params) return 0; @@ -218,7 +240,7 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts) opts->timeout = option; break; case Opt_privport: - opts->privport = 1; + opts->privport = true; break; default: continue; @@ -560,6 +582,8 @@ static struct p9_trans_rdma *alloc_rdma(struct p9_rdma_opts *opts) if (!rdma) return NULL; + rdma->port = opts->port; + rdma->privport = opts->privport; rdma->sq_depth = opts->sq_depth; rdma->rq_depth = opts->rq_depth; rdma->timeout = opts->timeout; @@ -733,6 +757,7 @@ static struct p9_trans_module p9_rdma_trans = { .request = rdma_request, .cancel = rdma_cancel, .cancelled = rdma_cancelled, + .show_options = p9_rdma_show_options, }; /** -- cgit v1.2.3-59-g8ed1b From 4dfdb71307675b19a54723a556371dad5e3b0083 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 5 Jul 2017 16:25:45 +0100 Subject: orangefs: Implement show_options Implement the show_options superblock op for orangefs as part of a bid to rid of s_options and generic_show_options() to make it easier to implement a context-based mount where the mount options can be passed individually over a file descriptor. Signed-off-by: David Howells cc: Mike Marshall cc: pvfs2-developers@beowulf-underground.org Signed-off-by: Al Viro --- fs/orangefs/super.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c index 5c7c273e17ec..5a1bed6c8c6a 100644 --- a/fs/orangefs/super.c +++ b/fs/orangefs/super.c @@ -35,6 +35,19 @@ static const match_table_t tokens = { uint64_t orangefs_features; +static int orangefs_show_options(struct seq_file *m, struct dentry *root) +{ + struct orangefs_sb_info_s *orangefs_sb = ORANGEFS_SB(root->d_sb); + + if (root->d_sb->s_flags & MS_POSIXACL) + seq_puts(m, ",acl"); + if (orangefs_sb->flags & ORANGEFS_OPT_INTR) + seq_puts(m, ",intr"); + if (orangefs_sb->flags & ORANGEFS_OPT_LOCAL_LOCK) + seq_puts(m, ",local_lock"); + return 0; +} + static int parse_mount_options(struct super_block *sb, char *options, int silent) { @@ -305,7 +318,7 @@ static const struct super_operations orangefs_s_ops = { .drop_inode = generic_delete_inode, .statfs = orangefs_statfs, .remount_fs = orangefs_remount_fs, - .show_options = generic_show_options, + .show_options = orangefs_show_options, }; static struct dentry *orangefs_fh_to_dentry(struct super_block *sb, -- cgit v1.2.3-59-g8ed1b From 1d278a879081ddc40286500e58868aaee47de257 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 5 Jul 2017 16:25:53 +0100 Subject: VFS: Kill off s_options and helpers Kill off s_options, save/replace_mount_options() and generic_show_options() as all filesystems now implement ->show_options() for themselves. This should make it easier to implement a context-based mount where the mount options can be passed individually over a file descriptor. Signed-off-by: David Howells Signed-off-by: Al Viro --- Documentation/filesystems/vfs.txt | 6 ---- fs/efivarfs/super.c | 1 - fs/namespace.c | 59 --------------------------------------- fs/super.c | 1 - include/linux/fs.h | 9 ------ 5 files changed, 76 deletions(-) diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index f42b90687d40..ee56a7d10da9 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -1187,12 +1187,6 @@ The underlying reason for the above rules is to make sure, that a mount can be accurately replicated (e.g. umounting and mounting again) based on the information found in /proc/mounts. -A simple method of saving options at mount/remount time and showing -them is provided with the save_mount_options() and -generic_show_options() helper functions. Please note, that using -these may have drawbacks. For more info see header comments for these -functions in fs/namespace.c. - Resources ========= diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index d7a7c53803c1..5b68e4294faa 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -29,7 +29,6 @@ static const struct super_operations efivarfs_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, .evict_inode = efivarfs_evict_inode, - .show_options = generic_show_options, }; static struct super_block *efivarfs_sb; diff --git a/fs/namespace.c b/fs/namespace.c index 544ab84642eb..0e1fdb306133 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1237,65 +1237,6 @@ struct vfsmount *mnt_clone_internal(const struct path *path) return &p->mnt; } -static inline void mangle(struct seq_file *m, const char *s) -{ - seq_escape(m, s, " \t\n\\"); -} - -/* - * Simple .show_options callback for filesystems which don't want to - * implement more complex mount option showing. - * - * See also save_mount_options(). - */ -int generic_show_options(struct seq_file *m, struct dentry *root) -{ - const char *options; - - rcu_read_lock(); - options = rcu_dereference(root->d_sb->s_options); - - if (options != NULL && options[0]) { - seq_putc(m, ','); - mangle(m, options); - } - rcu_read_unlock(); - - return 0; -} -EXPORT_SYMBOL(generic_show_options); - -/* - * If filesystem uses generic_show_options(), this function should be - * called from the fill_super() callback. - * - * The .remount_fs callback usually needs to be handled in a special - * way, to make sure, that previous options are not overwritten if the - * remount fails. - * - * Also note, that if the filesystem's .remount_fs function doesn't - * reset all options to their default value, but changes only newly - * given options, then the displayed options will not reflect reality - * any more. - */ -void save_mount_options(struct super_block *sb, char *options) -{ - BUG_ON(sb->s_options); - rcu_assign_pointer(sb->s_options, kstrdup(options, GFP_KERNEL)); -} -EXPORT_SYMBOL(save_mount_options); - -void replace_mount_options(struct super_block *sb, char *options) -{ - char *old = sb->s_options; - rcu_assign_pointer(sb->s_options, options); - if (old) { - synchronize_rcu(); - kfree(old); - } -} -EXPORT_SYMBOL(replace_mount_options); - #ifdef CONFIG_PROC_FS /* iterator; we want it to have access to namespace_sem, thus here... */ static void *m_start(struct seq_file *m, loff_t *pos) diff --git a/fs/super.c b/fs/super.c index dfb56a9665d8..6bc3352adcf3 100644 --- a/fs/super.c +++ b/fs/super.c @@ -168,7 +168,6 @@ static void destroy_super(struct super_block *s) WARN_ON(!list_empty(&s->s_mounts)); put_user_ns(s->s_user_ns); kfree(s->s_subtype); - kfree(s->s_options); call_rcu(&s->rcu, destroy_super_rcu); } diff --git a/include/linux/fs.h b/include/linux/fs.h index bc0c054894b9..e265b2ea72c6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1351,11 +1351,6 @@ struct super_block { */ char *s_subtype; - /* - * Saved mount options for lazy filesystems using - * generic_show_options() - */ - char __rcu *s_options; const struct dentry_operations *s_d_op; /* default d_op for dentries */ /* @@ -3033,10 +3028,6 @@ extern void setattr_copy(struct inode *inode, const struct iattr *attr); extern int file_update_time(struct file *file); -extern int generic_show_options(struct seq_file *m, struct dentry *root); -extern void save_mount_options(struct super_block *sb, char *options); -extern void replace_mount_options(struct super_block *sb, char *options); - static inline bool io_is_direct(struct file *filp) { return (filp->f_flags & O_DIRECT) || IS_DAX(filp->f_mapping->host); -- cgit v1.2.3-59-g8ed1b From 92ecd19a7e1dc1c928707835c28cb65f0740be2d Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Sat, 8 Jul 2017 16:00:09 +0100 Subject: MIPS: MIPS16e2: Report ASE presence in /proc/cpuinfo Only now that both feature determination and unaligned emulation is in place add reporting to /proc/cpuinfo, so that the presence of "mips16e2" there not only indicates our recognition of the hardware feature, but correct unaligned emulation as well. Signed-off-by: Maciej W. Rozycki Cc: James Hogan Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16757/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/proc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c index 4eff2aed7360..bbd83b810e51 100644 --- a/arch/mips/kernel/proc.c +++ b/arch/mips/kernel/proc.c @@ -109,6 +109,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) seq_printf(m, "ASEs implemented\t:"); if (cpu_has_mips16) seq_printf(m, "%s", " mips16"); + if (cpu_has_mips16e2) seq_printf(m, "%s", " mips16e2"); if (cpu_has_mdmx) seq_printf(m, "%s", " mdmx"); if (cpu_has_mips3d) seq_printf(m, "%s", " mips3d"); if (cpu_has_smartmips) seq_printf(m, "%s", " smartmips"); -- cgit v1.2.3-59-g8ed1b From 17753d16251837125014caa6b49406f52aef8916 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 21 Jun 2017 15:08:39 +0300 Subject: mmc: sdhci-acpi: Workaround conflict with PCI wifi on GPD Win handheld GPDwin uses PCI wifi which conflicts with SDIO's use of acpi_device_fix_up_power() on child device nodes. Specifically acpi_device_fix_up_power() causes the wifi module to get turned off. Identifying GPDwin is problematic, but since SDIO is only used for wifi, the presence of the PCI wifi card in the expected slot with an ACPI companion node, is used to indicate that acpi_device_fix_up_power() should be avoided. Signed-off-by: Adrian Hunter Acked-by: Hans de Goede Tested-by: Hans de Goede Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-acpi.c | 70 +++++++++++++++++++++++++++++++++++++++---- 1 file changed, 64 insertions(+), 6 deletions(-) diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c index cf66a3db71b8..ac678e9fb19a 100644 --- a/drivers/mmc/host/sdhci-acpi.c +++ b/drivers/mmc/host/sdhci-acpi.c @@ -45,6 +45,7 @@ #include #include #include +#include #endif #include "sdhci.h" @@ -134,6 +135,16 @@ static bool sdhci_acpi_byt(void) return x86_match_cpu(byt); } +static bool sdhci_acpi_cht(void) +{ + static const struct x86_cpu_id cht[] = { + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT }, + {} + }; + + return x86_match_cpu(cht); +} + #define BYT_IOSF_SCCEP 0x63 #define BYT_IOSF_OCP_NETCTRL0 0x1078 #define BYT_IOSF_OCP_TIMEOUT_BASE GENMASK(10, 8) @@ -178,6 +189,45 @@ static bool sdhci_acpi_byt_defer(struct device *dev) return false; } +static bool sdhci_acpi_cht_pci_wifi(unsigned int vendor, unsigned int device, + unsigned int slot, unsigned int parent_slot) +{ + struct pci_dev *dev, *parent, *from = NULL; + + while (1) { + dev = pci_get_device(vendor, device, from); + pci_dev_put(from); + if (!dev) + break; + parent = pci_upstream_bridge(dev); + if (ACPI_COMPANION(&dev->dev) && PCI_SLOT(dev->devfn) == slot && + parent && PCI_SLOT(parent->devfn) == parent_slot && + !pci_upstream_bridge(parent)) { + pci_dev_put(dev); + return true; + } + from = dev; + } + + return false; +} + +/* + * GPDwin uses PCI wifi which conflicts with SDIO's use of + * acpi_device_fix_up_power() on child device nodes. Identifying GPDwin is + * problematic, but since SDIO is only used for wifi, the presence of the PCI + * wifi card in the expected slot with an ACPI companion node, is used to + * indicate that acpi_device_fix_up_power() should be avoided. + */ +static inline bool sdhci_acpi_no_fixup_child_power(const char *hid, + const char *uid) +{ + return sdhci_acpi_cht() && + !strcmp(hid, "80860F14") && + !strcmp(uid, "2") && + sdhci_acpi_cht_pci_wifi(0x14e4, 0x43ec, 0, 28); +} + #else static inline void sdhci_acpi_byt_setting(struct device *dev) @@ -189,6 +239,12 @@ static inline bool sdhci_acpi_byt_defer(struct device *dev) return false; } +static inline bool sdhci_acpi_no_fixup_child_power(const char *hid, + const char *uid) +{ + return false; +} + #endif static int bxt_get_cd(struct mmc_host *mmc) @@ -389,18 +445,20 @@ static int sdhci_acpi_probe(struct platform_device *pdev) if (acpi_bus_get_device(handle, &device)) return -ENODEV; + hid = acpi_device_hid(device); + uid = device->pnp.unique_id; + /* Power on the SDHCI controller and its children */ acpi_device_fix_up_power(device); - list_for_each_entry(child, &device->children, node) - if (child->status.present && child->status.enabled) - acpi_device_fix_up_power(child); + if (!sdhci_acpi_no_fixup_child_power(hid, uid)) { + list_for_each_entry(child, &device->children, node) + if (child->status.present && child->status.enabled) + acpi_device_fix_up_power(child); + } if (sdhci_acpi_byt_defer(dev)) return -EPROBE_DEFER; - hid = acpi_device_hid(device); - uid = device->pnp.unique_id; - iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!iomem) return -ENOMEM; -- cgit v1.2.3-59-g8ed1b From 65ae8d2621a9fb20b53348311984ea79fee42a55 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Tue, 23 May 2017 13:40:23 +0100 Subject: MIPS16e2: Provide feature overrides for non-MIPS16 systems Hardcode the absence of the MIPS16e2 ASE for all the systems that do so for the MIPS16 ASE already, providing for code to be optimized away. Signed-off-by: Maciej W. Rozycki Reviewed-by: James Hogan Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16097/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/mach-ath25/cpu-feature-overrides.h | 1 + arch/mips/include/asm/mach-au1x00/cpu-feature-overrides.h | 1 + arch/mips/include/asm/mach-bcm63xx/cpu-feature-overrides.h | 1 + arch/mips/include/asm/mach-cobalt/cpu-feature-overrides.h | 1 + arch/mips/include/asm/mach-dec/cpu-feature-overrides.h | 1 + arch/mips/include/asm/mach-ip22/cpu-feature-overrides.h | 1 + arch/mips/include/asm/mach-ip27/cpu-feature-overrides.h | 1 + arch/mips/include/asm/mach-ip28/cpu-feature-overrides.h | 1 + arch/mips/include/asm/mach-ip32/cpu-feature-overrides.h | 1 + arch/mips/include/asm/mach-jz4740/cpu-feature-overrides.h | 1 + arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h | 1 + arch/mips/include/asm/mach-netlogic/cpu-feature-overrides.h | 1 + arch/mips/include/asm/mach-rc32434/cpu-feature-overrides.h | 1 + arch/mips/include/asm/mach-rm/cpu-feature-overrides.h | 1 + arch/mips/include/asm/mach-sibyte/cpu-feature-overrides.h | 1 + arch/mips/include/asm/mach-tx49xx/cpu-feature-overrides.h | 1 + 16 files changed, 16 insertions(+) diff --git a/arch/mips/include/asm/mach-ath25/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ath25/cpu-feature-overrides.h index ade0356df257..e6a8108cde4e 100644 --- a/arch/mips/include/asm/mach-ath25/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-ath25/cpu-feature-overrides.h @@ -40,6 +40,7 @@ #endif #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_mdmx 0 #define cpu_has_mips3d 0 #define cpu_has_smartmips 0 diff --git a/arch/mips/include/asm/mach-au1x00/cpu-feature-overrides.h b/arch/mips/include/asm/mach-au1x00/cpu-feature-overrides.h index c5b6eef0efa7..bace5b9ae4df 100644 --- a/arch/mips/include/asm/mach-au1x00/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-au1x00/cpu-feature-overrides.h @@ -31,6 +31,7 @@ #define cpu_has_ejtag 1 #define cpu_has_llsc 1 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_mdmx 0 #define cpu_has_mips3d 0 #define cpu_has_smartmips 0 diff --git a/arch/mips/include/asm/mach-bcm63xx/cpu-feature-overrides.h b/arch/mips/include/asm/mach-bcm63xx/cpu-feature-overrides.h index bc1167dbd4e3..b56cf10b91d3 100644 --- a/arch/mips/include/asm/mach-bcm63xx/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-bcm63xx/cpu-feature-overrides.h @@ -19,6 +19,7 @@ #define cpu_has_ejtag 1 #define cpu_has_llsc 1 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_mdmx 0 #define cpu_has_mips3d 0 #define cpu_has_smartmips 0 diff --git a/arch/mips/include/asm/mach-cobalt/cpu-feature-overrides.h b/arch/mips/include/asm/mach-cobalt/cpu-feature-overrides.h index 30c5cd9fd973..291fe90aafa5 100644 --- a/arch/mips/include/asm/mach-cobalt/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-cobalt/cpu-feature-overrides.h @@ -37,6 +37,7 @@ #endif #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_mdmx 0 #define cpu_has_mips3d 0 #define cpu_has_smartmips 0 diff --git a/arch/mips/include/asm/mach-dec/cpu-feature-overrides.h b/arch/mips/include/asm/mach-dec/cpu-feature-overrides.h index 21eae03d752a..2ec10237688c 100644 --- a/arch/mips/include/asm/mach-dec/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-dec/cpu-feature-overrides.h @@ -27,6 +27,7 @@ #define cpu_has_mcheck 0 #define cpu_has_ejtag 0 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_mdmx 0 #define cpu_has_mips3d 0 #define cpu_has_smartmips 0 diff --git a/arch/mips/include/asm/mach-ip22/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ip22/cpu-feature-overrides.h index 9b19b72dba56..b80d5eafc9db 100644 --- a/arch/mips/include/asm/mach-ip22/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-ip22/cpu-feature-overrides.h @@ -19,6 +19,7 @@ #define cpu_has_32fpr 1 #define cpu_has_counter 1 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_divec 0 #define cpu_has_cache_cdex_p 1 #define cpu_has_prefetch 0 diff --git a/arch/mips/include/asm/mach-ip27/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ip27/cpu-feature-overrides.h index 7449794eade6..136d6d464e32 100644 --- a/arch/mips/include/asm/mach-ip27/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-ip27/cpu-feature-overrides.h @@ -43,6 +43,7 @@ #define cpu_has_ejtag 0 #define cpu_has_llsc 1 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_mdmx 0 #define cpu_has_mips3d 0 #define cpu_has_smartmips 0 diff --git a/arch/mips/include/asm/mach-ip28/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ip28/cpu-feature-overrides.h index 4cec06d133db..ba8b4e30b3e2 100644 --- a/arch/mips/include/asm/mach-ip28/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-ip28/cpu-feature-overrides.h @@ -16,6 +16,7 @@ */ #define cpu_has_watch 1 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_divec 0 #define cpu_has_vce 0 #define cpu_has_cache_cdex_p 0 diff --git a/arch/mips/include/asm/mach-ip32/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ip32/cpu-feature-overrides.h index 241409b78ff1..63b4c889094b 100644 --- a/arch/mips/include/asm/mach-ip32/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-ip32/cpu-feature-overrides.h @@ -29,6 +29,7 @@ #define cpu_has_32fpr 1 #define cpu_has_counter 1 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_vce 0 #define cpu_has_cache_cdex_s 0 #define cpu_has_mcheck 0 diff --git a/arch/mips/include/asm/mach-jz4740/cpu-feature-overrides.h b/arch/mips/include/asm/mach-jz4740/cpu-feature-overrides.h index 0933f94a1e69..7c5e576f9d96 100644 --- a/arch/mips/include/asm/mach-jz4740/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-jz4740/cpu-feature-overrides.h @@ -23,6 +23,7 @@ #define cpu_has_ejtag 1 #define cpu_has_llsc 1 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_mdmx 0 #define cpu_has_mips3d 0 #define cpu_has_smartmips 0 diff --git a/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h b/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h index 89328a3d44d8..581915ce231c 100644 --- a/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h @@ -32,6 +32,7 @@ #define cpu_has_mcheck 0 #define cpu_has_mdmx 0 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_mips3d 0 #define cpu_has_mipsmt 0 #define cpu_has_smartmips 0 diff --git a/arch/mips/include/asm/mach-netlogic/cpu-feature-overrides.h b/arch/mips/include/asm/mach-netlogic/cpu-feature-overrides.h index 091deb1700e5..0c29ff820bb9 100644 --- a/arch/mips/include/asm/mach-netlogic/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-netlogic/cpu-feature-overrides.h @@ -13,6 +13,7 @@ #define cpu_has_4k_cache 1 #define cpu_has_watch 1 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_counter 1 #define cpu_has_divec 1 #define cpu_has_vce 0 diff --git a/arch/mips/include/asm/mach-rc32434/cpu-feature-overrides.h b/arch/mips/include/asm/mach-rc32434/cpu-feature-overrides.h index b15307597ee3..6a1087ee8c6e 100644 --- a/arch/mips/include/asm/mach-rc32434/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-rc32434/cpu-feature-overrides.h @@ -48,6 +48,7 @@ #define cpu_has_llsc 1 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_mdmx 0 #define cpu_has_mips3d 0 #define cpu_has_smartmips 0 diff --git a/arch/mips/include/asm/mach-rm/cpu-feature-overrides.h b/arch/mips/include/asm/mach-rm/cpu-feature-overrides.h index d38be668e338..e1e182300fea 100644 --- a/arch/mips/include/asm/mach-rm/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-rm/cpu-feature-overrides.h @@ -17,6 +17,7 @@ #define cpu_has_counter 1 #define cpu_has_watch 0 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_divec 0 #define cpu_has_cache_cdex_p 1 #define cpu_has_prefetch 0 diff --git a/arch/mips/include/asm/mach-sibyte/cpu-feature-overrides.h b/arch/mips/include/asm/mach-sibyte/cpu-feature-overrides.h index 92927b62b5a0..7022358057fd 100644 --- a/arch/mips/include/asm/mach-sibyte/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-sibyte/cpu-feature-overrides.h @@ -13,6 +13,7 @@ */ #define cpu_has_watch 1 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_divec 1 #define cpu_has_vce 0 #define cpu_has_cache_cdex_p 0 diff --git a/arch/mips/include/asm/mach-tx49xx/cpu-feature-overrides.h b/arch/mips/include/asm/mach-tx49xx/cpu-feature-overrides.h index 7f5144c6ce2d..b9d39dc45420 100644 --- a/arch/mips/include/asm/mach-tx49xx/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-tx49xx/cpu-feature-overrides.h @@ -6,6 +6,7 @@ #define cpu_has_inclusive_pcaches 0 #define cpu_has_mips16 0 +#define cpu_has_mips16e2 0 #define cpu_has_mdmx 0 #define cpu_has_mips3d 0 #define cpu_has_smartmips 0 -- cgit v1.2.3-59-g8ed1b From 54eca7eccc5e149825f831859123b692a565bca9 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Thu, 29 Jun 2017 10:12:33 +0100 Subject: MIPS: Drop duplicate HAVE_SYSCALL_TRACEPOINTS select MIPS selects HAVE_SYSCALL_TRACEPOINTS twice. The first was added back in v3.13 by commit 2d7bf993e073 ("MIPS: ftrace: Add support for syscall tracepoints."), but then a second redundant one was added in v4.2 by commit fb59e394c30c ("MIPS: ftrace: Enable support for syscall tracepoints."). Drop the duplicate select. Fixes: fb59e394c30c ("MIPS: ftrace: Enable support for syscall tracepoints.") Signed-off-by: James Hogan Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16654/ Signed-off-by: Ralf Baechle --- arch/mips/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 609986e8b21e..55e48a3e7f05 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -64,7 +64,6 @@ config MIPS select HAVE_PERF_EVENTS select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_SYSCALL_TRACEPOINTS - select HAVE_SYSCALL_TRACEPOINTS select HAVE_VIRT_CPU_ACCOUNTING_GEN select IRQ_FORCED_THREADING select MODULES_USE_ELF_RELA if MODULES && 64BIT -- cgit v1.2.3-59-g8ed1b From 4f32a39d49b25eaa66d2420f1f03d371ea4cd906 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Thu, 29 Jun 2017 10:12:34 +0100 Subject: MIPS: Negate error syscall return in trace The sys_exit trace event takes a single return value for the system call, which MIPS passes the value of the $v0 (result) register, however MIPS returns positive error codes in $v0 with $a3 specifying that $v0 contains an error code. As a result erroring system calls are traced returning positive error numbers that can't always be distinguished from success. Use regs_return_value() to negate the error code if $a3 is set. Fixes: 1d7bf993e073 ("MIPS: ftrace: Add support for syscall tracepoints.") Signed-off-by: James Hogan Cc: Steven Rostedt Cc: Ingo Molnar Cc: linux-mips@linux-mips.org Cc: # 3.13+ Patchwork: https://patchwork.linux-mips.org/patch/16651/ Acked-by: Steven Rostedt (VMware) Signed-off-by: Ralf Baechle --- arch/mips/kernel/ptrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index ba3b1f771256..8e2ea86dc23e 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -913,7 +913,7 @@ asmlinkage void syscall_trace_leave(struct pt_regs *regs) audit_syscall_exit(regs); if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) - trace_sys_exit(regs, regs->regs[2]); + trace_sys_exit(regs, regs_return_value(regs)); if (test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, 0); -- cgit v1.2.3-59-g8ed1b From becddba9f80f26a2b9ebe9bad2806304ed5e00e1 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Thu, 29 Jun 2017 10:12:35 +0100 Subject: MIPS: Correct forced syscall errors When the system call return value is forced to be an error (for example due to SECCOMP_RET_ERRNO), syscall_set_return_value() puts the error code in the return register $v0 and -1 in the error register $a3. However normally executed system calls put 1 in the error register rather than -1, so fix syscall_set_return_value() to be consistent with that. I don't anticipate that anything would have been broken by this, since the most natural way to check the error register on MIPS would be a conditional branch if error register is [not] equal to zero (bnez or beqz). Fixes: 1d7bf993e073 ("MIPS: ftrace: Add support for syscall tracepoints.") Signed-off-by: James Hogan Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16652/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/syscall.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h index d87882513ee3..7c713025b23f 100644 --- a/arch/mips/include/asm/syscall.h +++ b/arch/mips/include/asm/syscall.h @@ -85,7 +85,7 @@ static inline void syscall_set_return_value(struct task_struct *task, { if (error) { regs->regs[2] = -error; - regs->regs[7] = -1; + regs->regs[7] = 1; } else { regs->regs[2] = val; regs->regs[7] = 0; -- cgit v1.2.3-59-g8ed1b From 828db212bf4b63c68c51f6519435c48e8d79bd00 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Thu, 29 Jun 2017 10:12:36 +0100 Subject: MIPS: Traced negative syscalls should return -ENOSYS If a negative system call number is used when system call tracing is enabled, syscall_trace_enter() will return that negative system call number without having written the return value and error flag into the pt_regs. The caller then treats it as a cancelled system call and assumes that the return value and error flag are already written, leaving the negative system call number in the return register ($v0), and the 4th system call argument in the error register ($a3). Add a special case to detect this at the end of syscall_trace_enter(), to set the return value to error -ENOSYS when this happens. Fixes: d218af78492a ("MIPS: scall: Always run the seccomp syscall filters") Signed-off-by: James Hogan Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16653/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/ptrace.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index 8e2ea86dc23e..6dd13641a418 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -894,6 +894,13 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall) audit_syscall_entry(syscall, regs->regs[4], regs->regs[5], regs->regs[6], regs->regs[7]); + + /* + * Negative syscall numbers are mistaken for rejected syscalls, but + * won't have had the return value set appropriately, so we do so now. + */ + if (syscall < 0) + syscall_set_return_value(current, regs, -ENOSYS, 0); return syscall; } -- cgit v1.2.3-59-g8ed1b From 7461279bba4a62d192eda6dd10de68ac0543bfcd Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 17 Jun 2017 13:52:46 -0700 Subject: dt-bindings: Document img,boston-clock binding Add device tree binding documentation for the clocks provided by the MIPS Boston development board from Imagination Technologies, and a header file describing the available clocks for use by device trees & driver. Signed-off-by: Paul Burton Acked-by: Stephen Boyd Cc: Frank Rowand Cc: Michael Turquette Cc: Rob Herring Cc: devicetree@vger.kernel.org Cc: linux-clk@vger.kernel.org Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16482/ Signed-off-by: Ralf Baechle --- .../devicetree/bindings/clock/img,boston-clock.txt | 31 ++++++++++++++++++++++ MAINTAINERS | 7 +++++ include/dt-bindings/clock/boston-clock.h | 14 ++++++++++ 3 files changed, 52 insertions(+) create mode 100644 Documentation/devicetree/bindings/clock/img,boston-clock.txt create mode 100644 include/dt-bindings/clock/boston-clock.h diff --git a/Documentation/devicetree/bindings/clock/img,boston-clock.txt b/Documentation/devicetree/bindings/clock/img,boston-clock.txt new file mode 100644 index 000000000000..7bc5e9ffb624 --- /dev/null +++ b/Documentation/devicetree/bindings/clock/img,boston-clock.txt @@ -0,0 +1,31 @@ +Binding for Imagination Technologies MIPS Boston clock sources. + +This binding uses the common clock binding[1]. + +[1] Documentation/devicetree/bindings/clock/clock-bindings.txt + +The device node must be a child node of the syscon node corresponding to the +Boston system's platform registers. + +Required properties: +- compatible : Should be "img,boston-clock". +- #clock-cells : Should be set to 1. + Values available for clock consumers can be found in the header file: + + +Example: + + system-controller@17ffd000 { + compatible = "img,boston-platform-regs", "syscon"; + reg = <0x17ffd000 0x1000>; + + clk_boston: clock { + compatible = "img,boston-clock"; + #clock-cells = <1>; + }; + }; + + uart0: uart@17ffe000 { + /* ... */ + clocks = <&clk_boston BOSTON_CLK_SYS>; + }; diff --git a/MAINTAINERS b/MAINTAINERS index bcf2d258c0dd..0b977a6bf849 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8504,6 +8504,13 @@ F: arch/mips/include/asm/mach-loongson32/ F: drivers/*/*loongson1* F: drivers/*/*/*loongson1* +MIPS BOSTON DEVELOPMENT BOARD +M: Paul Burton +L: linux-mips@linux-mips.org +S: Maintained +F: Documentation/devicetree/bindings/clock/img,boston-clock.txt +F: include/dt-bindings/clock/boston-clock.h + MIROSOUND PCM20 FM RADIO RECEIVER DRIVER M: Hans Verkuil L: linux-media@vger.kernel.org diff --git a/include/dt-bindings/clock/boston-clock.h b/include/dt-bindings/clock/boston-clock.h new file mode 100644 index 000000000000..a6f009821137 --- /dev/null +++ b/include/dt-bindings/clock/boston-clock.h @@ -0,0 +1,14 @@ +/* + * Copyright (C) 2016 Imagination Technologies + * + * SPDX-License-Identifier: GPL-2.0 + */ + +#ifndef __DT_BINDINGS_CLOCK_BOSTON_CLOCK_H__ +#define __DT_BINDINGS_CLOCK_BOSTON_CLOCK_H__ + +#define BOSTON_CLK_INPUT 0 +#define BOSTON_CLK_SYS 1 +#define BOSTON_CLK_CPU 2 + +#endif /* __DT_BINDINGS_CLOCK_BOSTON_CLOCK_H__ */ -- cgit v1.2.3-59-g8ed1b From 6b0fd6c1a22da18a00f8ce12014d55ce0a316651 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 17 Jun 2017 13:52:47 -0700 Subject: clk: boston: Add a driver for MIPS Boston board clocks Add a driver for the clocks provided by the MIPS Boston board from Imagination Technologies. 2 clocks are provided - the system clock & the CPU clock - and each is a simple fixed rate clock whose frequency can be determined by reading a register provided by the board. Signed-off-by: Paul Burton Acked-by: Stephen Boyd Reviewed-by: James Hogan Cc: Michael Turquette Cc: linux-clk@vger.kernel.org Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16483/ Signed-off-by: Ralf Baechle --- MAINTAINERS | 1 + drivers/clk/Kconfig | 1 + drivers/clk/Makefile | 1 + drivers/clk/imgtec/Kconfig | 9 ++++ drivers/clk/imgtec/Makefile | 1 + drivers/clk/imgtec/clk-boston.c | 103 ++++++++++++++++++++++++++++++++++++++++ 6 files changed, 116 insertions(+) create mode 100644 drivers/clk/imgtec/Kconfig create mode 100644 drivers/clk/imgtec/Makefile create mode 100644 drivers/clk/imgtec/clk-boston.c diff --git a/MAINTAINERS b/MAINTAINERS index 0b977a6bf849..5513b85dd60e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8509,6 +8509,7 @@ M: Paul Burton L: linux-mips@linux-mips.org S: Maintained F: Documentation/devicetree/bindings/clock/img,boston-clock.txt +F: drivers/clk/imgtec/clk-boston.c F: include/dt-bindings/clock/boston-clock.h MIROSOUND PCM20 FM RADIO RECEIVER DRIVER diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig index 36cfea38135f..251a22139e73 100644 --- a/drivers/clk/Kconfig +++ b/drivers/clk/Kconfig @@ -219,6 +219,7 @@ config COMMON_CLK_VC5 source "drivers/clk/bcm/Kconfig" source "drivers/clk/hisilicon/Kconfig" +source "drivers/clk/imgtec/Kconfig" source "drivers/clk/mediatek/Kconfig" source "drivers/clk/meson/Kconfig" source "drivers/clk/mvebu/Kconfig" diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile index c19983afcb81..a4a7c5df8b93 100644 --- a/drivers/clk/Makefile +++ b/drivers/clk/Makefile @@ -59,6 +59,7 @@ obj-y += bcm/ obj-$(CONFIG_ARCH_BERLIN) += berlin/ obj-$(CONFIG_H8300) += h8300/ obj-$(CONFIG_ARCH_HISI) += hisilicon/ +obj-y += imgtec/ obj-$(CONFIG_ARCH_MXC) += imx/ obj-$(CONFIG_MACH_INGENIC) += ingenic/ obj-$(CONFIG_COMMON_CLK_KEYSTONE) += keystone/ diff --git a/drivers/clk/imgtec/Kconfig b/drivers/clk/imgtec/Kconfig new file mode 100644 index 000000000000..f6dcb748e9c4 --- /dev/null +++ b/drivers/clk/imgtec/Kconfig @@ -0,0 +1,9 @@ +config COMMON_CLK_BOSTON + bool "Clock driver for MIPS Boston boards" + depends on MIPS || COMPILE_TEST + select MFD_SYSCON + ---help--- + Enable this to support the system & CPU clocks on the MIPS Boston + development board from Imagination Technologies. These are simple + fixed rate clocks whose rate is determined by reading a platform + provided register. diff --git a/drivers/clk/imgtec/Makefile b/drivers/clk/imgtec/Makefile new file mode 100644 index 000000000000..ac779b8c22f2 --- /dev/null +++ b/drivers/clk/imgtec/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_COMMON_CLK_BOSTON) += clk-boston.o diff --git a/drivers/clk/imgtec/clk-boston.c b/drivers/clk/imgtec/clk-boston.c new file mode 100644 index 000000000000..f18f10351785 --- /dev/null +++ b/drivers/clk/imgtec/clk-boston.c @@ -0,0 +1,103 @@ +/* + * Copyright (C) 2016-2017 Imagination Technologies + * Author: Paul Burton + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#define pr_fmt(fmt) "clk-boston: " fmt + +#include +#include +#include +#include +#include +#include + +#include + +#define BOSTON_PLAT_MMCMDIV 0x30 +# define BOSTON_PLAT_MMCMDIV_CLK0DIV (0xff << 0) +# define BOSTON_PLAT_MMCMDIV_INPUT (0xff << 8) +# define BOSTON_PLAT_MMCMDIV_MUL (0xff << 16) +# define BOSTON_PLAT_MMCMDIV_CLK1DIV (0xff << 24) + +#define BOSTON_CLK_COUNT 3 + +static u32 ext_field(u32 val, u32 mask) +{ + return (val & mask) >> (ffs(mask) - 1); +} + +static void __init clk_boston_setup(struct device_node *np) +{ + unsigned long in_freq, cpu_freq, sys_freq; + uint mmcmdiv, mul, cpu_div, sys_div; + struct clk_hw_onecell_data *onecell; + struct regmap *regmap; + struct clk_hw *hw; + int err; + + regmap = syscon_node_to_regmap(np->parent); + if (IS_ERR(regmap)) { + pr_err("failed to find regmap\n"); + return; + } + + err = regmap_read(regmap, BOSTON_PLAT_MMCMDIV, &mmcmdiv); + if (err) { + pr_err("failed to read mmcm_div register: %d\n", err); + return; + } + + in_freq = ext_field(mmcmdiv, BOSTON_PLAT_MMCMDIV_INPUT) * 1000000; + mul = ext_field(mmcmdiv, BOSTON_PLAT_MMCMDIV_MUL); + + sys_div = ext_field(mmcmdiv, BOSTON_PLAT_MMCMDIV_CLK0DIV); + sys_freq = mult_frac(in_freq, mul, sys_div); + + cpu_div = ext_field(mmcmdiv, BOSTON_PLAT_MMCMDIV_CLK1DIV); + cpu_freq = mult_frac(in_freq, mul, cpu_div); + + onecell = kzalloc(sizeof(*onecell) + + (BOSTON_CLK_COUNT * sizeof(struct clk_hw *)), + GFP_KERNEL); + if (!onecell) + return; + + onecell->num = BOSTON_CLK_COUNT; + + hw = clk_hw_register_fixed_rate(NULL, "input", NULL, 0, in_freq); + if (IS_ERR(hw)) { + pr_err("failed to register input clock: %ld\n", PTR_ERR(hw)); + return; + } + onecell->hws[BOSTON_CLK_INPUT] = hw; + + hw = clk_hw_register_fixed_rate(NULL, "sys", "input", 0, sys_freq); + if (IS_ERR(hw)) { + pr_err("failed to register sys clock: %ld\n", PTR_ERR(hw)); + return; + } + onecell->hws[BOSTON_CLK_SYS] = hw; + + hw = clk_hw_register_fixed_rate(NULL, "cpu", "input", 0, cpu_freq); + if (IS_ERR(hw)) { + pr_err("failed to register cpu clock: %ld\n", PTR_ERR(hw)); + return; + } + onecell->hws[BOSTON_CLK_CPU] = hw; + + err = of_clk_add_hw_provider(np, of_clk_hw_onecell_get, onecell); + if (err) + pr_err("failed to add DT provider: %d\n", err); +} + +/* + * Use CLK_OF_DECLARE so that this driver is probed early enough to provide the + * CPU frequency for use with the GIC or cop0 counters/timers. + */ +CLK_OF_DECLARE(clk_boston, "img,boston-clock", clk_boston_setup); -- cgit v1.2.3-59-g8ed1b From 4d2804b7d76ef6e6cd85be74999548276d23067f Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 17 Jun 2017 13:52:48 -0700 Subject: MIPS: DTS: img: Don't attempt to build-in all .dtb files When building a FIT image we may want the kernel to build multiple .dtb files, but we don't want to build them all into the kernel binary as object files since they'll instead be included in the FIT image. Commit daa10170da27 ("MIPS: DTS: img: add device tree for Marduk board") however created arch/mips/boot/dts/img/Makefile with a line that builds any enabled .dtb files into the kernel. Remove this & build the pistachio object specifically, in preparation for adding .dtb targets which we don't want to build into the kernel. Signed-off-by: Paul Burton Cc: Rahul Bedarkar Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16484/ Signed-off-by: Ralf Baechle --- arch/mips/boot/dts/img/Makefile | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/mips/boot/dts/img/Makefile b/arch/mips/boot/dts/img/Makefile index 69a65f0f82d2..c178cf56f5b8 100644 --- a/arch/mips/boot/dts/img/Makefile +++ b/arch/mips/boot/dts/img/Makefile @@ -1,6 +1,5 @@ dtb-$(CONFIG_MACH_PISTACHIO) += pistachio_marduk.dtb - -obj-y += $(patsubst %.dtb, %.dtb.o, $(dtb-y)) +obj-$(CONFIG_MACH_PISTACHIO) += pistachio_marduk.dtb.o # Force kbuild to make empty built-in.o if necessary obj- += dummy.o -- cgit v1.2.3-59-g8ed1b From 6e62a888029b4adbbc55894eaa8b929221113948 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 17 Jun 2017 13:52:49 -0700 Subject: MIPS: generic: Support MIPS Boston development boards Add support for the MIPS Boston development board to generic kernels, which essentially amounts to: - Adding the device tree source for the MIPS Boston board. - Adding a Kconfig fragment which enables the appropriate drivers for the MIPS Boston board. With these changes in place generic kernels will support the board by default, and kernels with only the drivers needed for Boston enabled can be configured by setting BOARDS=boston during configuration. For example: $ make ARCH=mips 64r6el_defconfig BOARDS=boston Signed-off-by: Paul Burton Reviewed-by: James Hogan Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/16485/ Signed-off-by: Ralf Baechle --- MAINTAINERS | 2 + arch/mips/boot/dts/img/Makefile | 2 + arch/mips/boot/dts/img/boston.dts | 224 ++++++++++++++++++++++++++ arch/mips/configs/generic/board-boston.config | 48 ++++++ arch/mips/generic/Kconfig | 12 ++ arch/mips/generic/vmlinux.its.S | 25 +++ 6 files changed, 313 insertions(+) create mode 100644 arch/mips/boot/dts/img/boston.dts create mode 100644 arch/mips/configs/generic/board-boston.config diff --git a/MAINTAINERS b/MAINTAINERS index 5513b85dd60e..d034eb8031fa 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8509,6 +8509,8 @@ M: Paul Burton L: linux-mips@linux-mips.org S: Maintained F: Documentation/devicetree/bindings/clock/img,boston-clock.txt +F: arch/mips/boot/dts/img/boston.dts +F: arch/mips/configs/generic/board-boston.config F: drivers/clk/imgtec/clk-boston.c F: include/dt-bindings/clock/boston-clock.h diff --git a/arch/mips/boot/dts/img/Makefile b/arch/mips/boot/dts/img/Makefile index c178cf56f5b8..3d70958d0f5a 100644 --- a/arch/mips/boot/dts/img/Makefile +++ b/arch/mips/boot/dts/img/Makefile @@ -1,3 +1,5 @@ +dtb-$(CONFIG_FIT_IMAGE_FDT_BOSTON) += boston.dtb + dtb-$(CONFIG_MACH_PISTACHIO) += pistachio_marduk.dtb obj-$(CONFIG_MACH_PISTACHIO) += pistachio_marduk.dtb.o diff --git a/arch/mips/boot/dts/img/boston.dts b/arch/mips/boot/dts/img/boston.dts new file mode 100644 index 000000000000..53bfa29a7093 --- /dev/null +++ b/arch/mips/boot/dts/img/boston.dts @@ -0,0 +1,224 @@ +/dts-v1/; + +#include +#include +#include +#include + +/ { + #address-cells = <1>; + #size-cells = <1>; + compatible = "img,boston"; + + chosen { + stdout-path = "uart0:115200"; + }; + + aliases { + uart0 = &uart0; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + compatible = "img,mips"; + reg = <0>; + clocks = <&clk_boston BOSTON_CLK_CPU>; + }; + }; + + memory@0 { + device_type = "memory"; + reg = <0x00000000 0x10000000>; + }; + + pci0: pci@10000000 { + compatible = "xlnx,axi-pcie-host-1.00.a"; + device_type = "pci"; + reg = <0x10000000 0x2000000>; + + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + + interrupt-parent = <&gic>; + interrupts = ; + + ranges = <0x02000000 0 0x40000000 + 0x40000000 0 0x40000000>; + + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0 0 0 1 &pci0_intc 1>, + <0 0 0 2 &pci0_intc 2>, + <0 0 0 3 &pci0_intc 3>, + <0 0 0 4 &pci0_intc 4>; + + pci0_intc: interrupt-controller { + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <1>; + }; + }; + + pci1: pci@12000000 { + compatible = "xlnx,axi-pcie-host-1.00.a"; + device_type = "pci"; + reg = <0x12000000 0x2000000>; + + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + + interrupt-parent = <&gic>; + interrupts = ; + + ranges = <0x02000000 0 0x20000000 + 0x20000000 0 0x20000000>; + + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0 0 0 1 &pci1_intc 1>, + <0 0 0 2 &pci1_intc 2>, + <0 0 0 3 &pci1_intc 3>, + <0 0 0 4 &pci1_intc 4>; + + pci1_intc: interrupt-controller { + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <1>; + }; + }; + + pci2: pci@14000000 { + compatible = "xlnx,axi-pcie-host-1.00.a"; + device_type = "pci"; + reg = <0x14000000 0x2000000>; + + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + + interrupt-parent = <&gic>; + interrupts = ; + + ranges = <0x02000000 0 0x16000000 + 0x16000000 0 0x100000>; + + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0 0 0 1 &pci2_intc 1>, + <0 0 0 2 &pci2_intc 2>, + <0 0 0 3 &pci2_intc 3>, + <0 0 0 4 &pci2_intc 4>; + + pci2_intc: interrupt-controller { + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <1>; + }; + + pci2_root@0,0,0 { + compatible = "pci10ee,7021"; + reg = <0x00000000 0 0 0 0>; + + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + + eg20t_bridge@1,0,0 { + compatible = "pci8086,8800"; + reg = <0x00010000 0 0 0 0>; + + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + + eg20t_mac@2,0,1 { + compatible = "pci8086,8802"; + reg = <0x00020100 0 0 0 0>; + phy-reset-gpios = <&eg20t_gpio 6 + GPIO_ACTIVE_LOW>; + }; + + eg20t_gpio: eg20t_gpio@2,0,2 { + compatible = "pci8086,8803"; + reg = <0x00020200 0 0 0 0>; + + gpio-controller; + #gpio-cells = <2>; + }; + + eg20t_i2c@2,12,2 { + compatible = "pci8086,8817"; + reg = <0x00026200 0 0 0 0>; + + #address-cells = <1>; + #size-cells = <0>; + + rtc@0x68 { + compatible = "st,m41t81s"; + reg = <0x68>; + }; + }; + }; + }; + }; + + gic: interrupt-controller@16120000 { + compatible = "mti,gic"; + reg = <0x16120000 0x20000>; + + interrupt-controller; + #interrupt-cells = <3>; + + timer { + compatible = "mti,gic-timer"; + interrupts = ; + clocks = <&clk_boston BOSTON_CLK_CPU>; + }; + }; + + cdmm@16140000 { + compatible = "mti,mips-cdmm"; + reg = <0x16140000 0x8000>; + }; + + cpc@16200000 { + compatible = "mti,mips-cpc"; + reg = <0x16200000 0x8000>; + }; + + plat_regs: system-controller@17ffd000 { + compatible = "img,boston-platform-regs", "syscon"; + reg = <0x17ffd000 0x1000>; + + clk_boston: clock { + compatible = "img,boston-clock"; + #clock-cells = <1>; + }; + }; + + reboot: syscon-reboot { + compatible = "syscon-reboot"; + regmap = <&plat_regs>; + offset = <0x10>; + mask = <0x10>; + }; + + uart0: uart@17ffe000 { + compatible = "ns16550a"; + reg = <0x17ffe000 0x1000>; + reg-shift = <2>; + + interrupt-parent = <&gic>; + interrupts = ; + + clocks = <&clk_boston BOSTON_CLK_SYS>; + }; + + lcd: lcd@17fff000 { + compatible = "img,boston-lcd"; + reg = <0x17fff000 0x8>; + }; +}; diff --git a/arch/mips/configs/generic/board-boston.config b/arch/mips/configs/generic/board-boston.config new file mode 100644 index 000000000000..19560a45b683 --- /dev/null +++ b/arch/mips/configs/generic/board-boston.config @@ -0,0 +1,48 @@ +CONFIG_FIT_IMAGE_FDT_BOSTON=y + +CONFIG_ATA=y +CONFIG_SATA_AHCI=y +CONFIG_SCSI=y +CONFIG_BLK_DEV_SD=y + +CONFIG_AUXDISPLAY=y +CONFIG_IMG_ASCII_LCD=y + +CONFIG_COMMON_CLK_BOSTON=y + +CONFIG_DMADEVICES=y +CONFIG_PCH_DMA=y + +CONFIG_GPIOLIB=y +CONFIG_GPIO_SYSFS=y +CONFIG_GPIO_PCH=y + +CONFIG_I2C=y +CONFIG_I2C_EG20T=y + +CONFIG_MMC=y +CONFIG_MMC_SDHCI=y +CONFIG_MMC_SDHCI_PCI=y + +CONFIG_NETDEVICES=y +CONFIG_PCH_GBE=y + +CONFIG_PCI=y +CONFIG_PCI_MSI=y +CONFIG_PCIE_XILINX=y + +CONFIG_PCH_PHUB=y + +CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_M41T80=y + +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_OF_PLATFORM=y + +CONFIG_SPI=y +CONFIG_SPI_TOPCLIFF_PCH=y + +CONFIG_USB=y +CONFIG_USB_EHCI_HCD=y +CONFIG_USB_OHCI_HCD=y diff --git a/arch/mips/generic/Kconfig b/arch/mips/generic/Kconfig index 446b7c68133d..51ffbbaddee2 100644 --- a/arch/mips/generic/Kconfig +++ b/arch/mips/generic/Kconfig @@ -16,6 +16,8 @@ config YAMON_DT_SHIM and you wish to include code which helps translate various YAMON-provided environment variables into a device tree properties. +comment "Legacy (non-UHI/non-FIT) Boards" + config LEGACY_BOARD_SEAD3 bool "Support MIPS SEAD-3 boards" select LEGACY_BOARDS @@ -24,4 +26,14 @@ config LEGACY_BOARD_SEAD3 Enable this to include support for booting on MIPS SEAD-3 FPGA-based development boards, which boot using a legacy boot protocol. +comment "FIT/UHI Boards" + +config FIT_IMAGE_FDT_BOSTON + bool "Include FDT for MIPS Boston boards" + help + Enable this to include the FDT for the MIPS Boston development board + from Imagination Technologies in the FIT kernel image. You should + enable this if you wish to boot on a MIPS Boston board, as it is + expected by the bootloader. + endif diff --git a/arch/mips/generic/vmlinux.its.S b/arch/mips/generic/vmlinux.its.S index f67fbf1c8541..3390e2f80b80 100644 --- a/arch/mips/generic/vmlinux.its.S +++ b/arch/mips/generic/vmlinux.its.S @@ -29,3 +29,28 @@ }; }; }; + +#ifdef CONFIG_FIT_IMAGE_FDT_BOSTON +/ { + images { + fdt@boston { + description = "img,boston Device Tree"; + data = /incbin/("boot/dts/img/boston.dtb"); + type = "flat_dt"; + arch = "mips"; + compression = "none"; + hash@0 { + algo = "sha1"; + }; + }; + }; + + configurations { + conf@boston { + description = "Boston Linux kernel"; + kernel = "kernel@0"; + fdt = "fdt@boston"; + }; + }; +}; +#endif /* CONFIG_FIT_IMAGE_FDT_BOSTON */ -- cgit v1.2.3-59-g8ed1b From 5fdc66e046206306bf61ff2d626bfa52ca087f7b Mon Sep 17 00:00:00 2001 From: Matt Redfearn Date: Mon, 10 Jul 2017 09:43:31 +0100 Subject: MIPS: Fix minimum alignment requirement of IRQ stack Commit db8466c581cc ("MIPS: IRQ Stack: Unwind IRQ stack onto task stack") erroneously set the initial stack pointer of the IRQ stack to a value with a 4 byte alignment. The MIPS32 ABI requires that the minimum stack alignment is 8 byte, and the MIPS64 ABIs(n32/n64) require 16 byte minimum alignment. Fix IRQ_STACK_START such that it leaves space for the dummy stack frame (containing interrupted task kernel stack pointer) while also meeting minimum alignment requirements. Fixes: db8466c581cc ("MIPS: IRQ Stack: Unwind IRQ stack onto task stack") Reported-by: Darius Ivanauskas Signed-off-by: Matt Redfearn Cc: Chris Metcalf Cc: Petr Mladek Cc: Aaron Tomlin Cc: Jason A. Donenfeld Cc: linux-mips@linux-mips.org Cc: linux-kernel@vger.kernel.org Patchwork: https://patchwork.linux-mips.org/patch/16760/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/irq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h index ddd1c918103b..c5d351786416 100644 --- a/arch/mips/include/asm/irq.h +++ b/arch/mips/include/asm/irq.h @@ -18,7 +18,7 @@ #include #define IRQ_STACK_SIZE THREAD_SIZE -#define IRQ_STACK_START (IRQ_STACK_SIZE - sizeof(unsigned long)) +#define IRQ_STACK_START (IRQ_STACK_SIZE - 16) extern void *irq_stack[NR_CPUS]; -- cgit v1.2.3-59-g8ed1b From e5f5a5b06e51a36f6ddf31a4a485358263953a3d Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Sat, 8 Jul 2017 23:24:44 +0100 Subject: MIPS: Fix MIPS I ISA /proc/cpuinfo reporting Correct a commit 515a6393dbac ("MIPS: kernel: proc: Add MIPS R6 support to /proc/cpuinfo") regression that caused MIPS I systems to show no ISA levels supported in /proc/cpuinfo, e.g.: system type : Digital DECstation 2100/3100 machine : Unknown processor : 0 cpu model : R3000 V2.0 FPU V2.0 BogoMIPS : 10.69 wait instruction : no microsecond timers : no tlb_entries : 64 extra interrupt vector : no hardware watchpoint : no isa : ASEs implemented : shadow register sets : 1 kscratch registers : 0 package : 0 core : 0 VCED exceptions : not available VCEI exceptions : not available and similarly exclude `mips1' from the ISA list for any processors below MIPSr1. This is because the condition to show `mips1' on has been made `cpu_has_mips_r1' rather than newly-introduced `cpu_has_mips_1'. Use the correct condition then. Fixes: 515a6393dbac ("MIPS: kernel: proc: Add MIPS R6 support to /proc/cpuinfo") Signed-off-by: Maciej W. Rozycki Reviewed-by: James Hogan Cc: linux-mips@linux-mips.org Cc: stable@vger.kernel.org # 3.19+ Patchwork: https://patchwork.linux-mips.org/patch/16758/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/proc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c index bbd83b810e51..70604c753aa4 100644 --- a/arch/mips/kernel/proc.c +++ b/arch/mips/kernel/proc.c @@ -83,7 +83,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) } seq_printf(m, "isa\t\t\t:"); - if (cpu_has_mips_r1) + if (cpu_has_mips_1) seq_printf(m, " mips1"); if (cpu_has_mips_2) seq_printf(m, "%s", " mips2"); -- cgit v1.2.3-59-g8ed1b From 20dd4c624d25156d5ec3345bbb690b98175ef879 Mon Sep 17 00:00:00 2001 From: Madhavan Srinivasan Date: Tue, 11 Jul 2017 16:27:49 +0530 Subject: powerpc/perf: Fix SDAR_MODE value for continous sampling on Power9 In case of continous sampling (non-marked), the code currently sets MMCRA[SDAR_MODE] to 0b01 (Update on TLB miss) for Power9 DD1. On DD2 and later it copies the sdar_mode value from the event code, which for most events is 0b00 (No updates). However we must set a non-zero value for SDAR_MODE when doing continuous sampling, so honor the event code, unless it's zero, in which case we use use 0b01 (Update on TLB miss). Fixes: 78b4416aa249 ("powerpc/perf: Handle sdar_mode for marked event in power9") Cc: stable@vger.kernel.org # v4.11+ Signed-off-by: Madhavan Srinivasan Signed-off-by: Michael Ellerman --- arch/powerpc/perf/isa207-common.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c index 8125160be7bc..3f3aa9a7063a 100644 --- a/arch/powerpc/perf/isa207-common.c +++ b/arch/powerpc/perf/isa207-common.c @@ -90,13 +90,15 @@ static void mmcra_sdar_mode(u64 event, unsigned long *mmcra) * MMCRA[SDAR_MODE] will be set to 0b01 * For rest * MMCRA[SDAR_MODE] will be set from event code. + * If sdar_mode from event is zero, default to 0b01. Hardware + * requires that we set a non-zero value. */ if (cpu_has_feature(CPU_FTR_ARCH_300)) { if (is_event_marked(event) || (*mmcra & MMCRA_SAMPLE_ENABLE)) *mmcra &= MMCRA_SDAR_MODE_NO_UPDATES; - else if (!cpu_has_feature(CPU_FTR_POWER9_DD1)) + else if (!cpu_has_feature(CPU_FTR_POWER9_DD1) && p9_SDAR_MODE(event)) *mmcra |= p9_SDAR_MODE(event) << MMCRA_SDAR_MODE_SHIFT; - else if (cpu_has_feature(CPU_FTR_POWER9_DD1)) + else *mmcra |= MMCRA_SDAR_MODE_TLB; } else *mmcra |= MMCRA_SDAR_MODE_TLB; -- cgit v1.2.3-59-g8ed1b From 770c0d86013e22647b15af8df2707f81ee1d5cd0 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:49 +0900 Subject: nios2: remove unneeded arch/nios2/include/(generated/)asm/signal.h Currently, NIOS2 has three signal.h files under arch/nios2/include: [1] arch/nios2/include/asm/signal.h [2] arch/nios2/include/uapi/asm/signal.h [3] arch/nios2/include/generated/asm/signal.h [3] is build-time generated by scripts/Makefile.asm-generic. However, -I$(srctree)/arch/$(hdr-arch)/include search path is listed before -I$(objtree)/arch/$(hdr-arch)/include/generated in LINUXINCLUDE. Therefore [1] is always included instead of [3]. Remove [3] which is never included. If we look at [1], it just includes [2]. So, [1] can be removed as well. Signed-off-by: Masahiro Yamada Reviewed-by: Tobias Klauser --- arch/nios2/include/asm/Kbuild | 1 - arch/nios2/include/asm/signal.h | 22 ---------------------- 2 files changed, 23 deletions(-) delete mode 100644 arch/nios2/include/asm/signal.h diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild index e1a843def56f..c1c7f6736117 100644 --- a/arch/nios2/include/asm/Kbuild +++ b/arch/nios2/include/asm/Kbuild @@ -47,7 +47,6 @@ generic-y += segment.h generic-y += sembuf.h generic-y += serial.h generic-y += shmbuf.h -generic-y += signal.h generic-y += socket.h generic-y += sockios.h generic-y += spinlock.h diff --git a/arch/nios2/include/asm/signal.h b/arch/nios2/include/asm/signal.h deleted file mode 100644 index bbcf11eecb01..000000000000 --- a/arch/nios2/include/asm/signal.h +++ /dev/null @@ -1,22 +0,0 @@ -/* - * Copyright Altera Corporation (C) 2013. All rights reserved - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program. If not, see . - * - */ -#ifndef _NIOS2_SIGNAL_H -#define _NIOS2_SIGNAL_H - -#include - -#endif /* _NIOS2_SIGNAL_H */ -- cgit v1.2.3-59-g8ed1b From 3beb4256f922733330938eac70c9218ec3f0b5c5 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:50 +0900 Subject: nios2: move generic-y of exported headers to uapi/asm/Kbuild Since commit fcc8487d477a ("uapi: export all headers under uapi directories"), all (and only) headers under uapi directories are exported, but asm-generic wrappers are still exceptions. To complete de-coupling the uapi from kernel headers, move generic-y of exported headers to uapi/asm/Kbuild. With this change, "make headers_install" will just need to parse uapi/asm/Kbuild to build up exported headers. Also, move "generic-y += kprobes.h" up in order to keep the entries sorted. Signed-off-by: Masahiro Yamada Reviewed-by: Tobias Klauser --- arch/nios2/include/asm/Kbuild | 25 +------------------------ arch/nios2/include/uapi/asm/Kbuild | 23 +++++++++++++++++++++++ 2 files changed, 24 insertions(+), 24 deletions(-) diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild index c1c7f6736117..896c26ae0da9 100644 --- a/arch/nios2/include/asm/Kbuild +++ b/arch/nios2/include/asm/Kbuild @@ -1,8 +1,6 @@ generic-y += atomic.h -generic-y += auxvec.h generic-y += barrier.h generic-y += bitops.h -generic-y += bitsperlong.h generic-y += bug.h generic-y += bugs.h generic-y += clkdev.h @@ -12,54 +10,33 @@ generic-y += device.h generic-y += div64.h generic-y += dma.h generic-y += emergency-restart.h -generic-y += errno.h generic-y += exec.h generic-y += extable.h generic-y += fb.h -generic-y += fcntl.h generic-y += ftrace.h generic-y += futex.h generic-y += hardirq.h generic-y += hw_irq.h -generic-y += ioctl.h -generic-y += ioctls.h -generic-y += ipcbuf.h generic-y += irq_regs.h generic-y += irq_work.h generic-y += kdebug.h generic-y += kmap_types.h -generic-y += kvm_para.h +generic-y += kprobes.h generic-y += local.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h -generic-y += mman.h generic-y += module.h -generic-y += msgbuf.h -generic-y += param.h generic-y += pci.h generic-y += percpu.h -generic-y += poll.h -generic-y += posix_types.h generic-y += preempt.h -generic-y += resource.h generic-y += sections.h generic-y += segment.h -generic-y += sembuf.h generic-y += serial.h -generic-y += shmbuf.h -generic-y += socket.h -generic-y += sockios.h generic-y += spinlock.h -generic-y += stat.h -generic-y += statfs.h -generic-y += termbits.h -generic-y += termios.h generic-y += topology.h generic-y += trace_clock.h -generic-y += types.h generic-y += unaligned.h generic-y += user.h generic-y += vga.h generic-y += word-at-a-time.h generic-y += xor.h -generic-y += kprobes.h diff --git a/arch/nios2/include/uapi/asm/Kbuild b/arch/nios2/include/uapi/asm/Kbuild index 51eff5bc2eb4..ffca24da7647 100644 --- a/arch/nios2/include/uapi/asm/Kbuild +++ b/arch/nios2/include/uapi/asm/Kbuild @@ -1,6 +1,29 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += auxvec.h +generic-y += bitsperlong.h +generic-y += errno.h +generic-y += fcntl.h +generic-y += ioctl.h +generic-y += ioctls.h +generic-y += ipcbuf.h +generic-y += kvm_para.h +generic-y += mman.h +generic-y += msgbuf.h +generic-y += param.h +generic-y += poll.h +generic-y += posix_types.h +generic-y += resource.h +generic-y += sembuf.h generic-y += setup.h +generic-y += shmbuf.h generic-y += siginfo.h +generic-y += socket.h +generic-y += sockios.h +generic-y += stat.h +generic-y += statfs.h +generic-y += termbits.h +generic-y += termios.h +generic-y += types.h generic-y += ucontext.h -- cgit v1.2.3-59-g8ed1b From c23504c60ebbc27f9418e01a45e5d4111c4d5f8b Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:51 +0900 Subject: openrisc: move generic-y of exported headers to uapi/asm/Kbuild Since commit fcc8487d477a ("uapi: export all headers under uapi directories"), all (and only) headers under uapi directories are exported, but asm-generic wrappers are still exceptions. To complete de-coupling the uapi from kernel headers, move generic-y of exported headers to uapi/asm/Kbuild. With this change, "make headers_install" will just need to parse uapi/asm/Kbuild to build up exported headers. Also, move "generic-y += kprobes.h" up in order to keep the entries sorted. Signed-off-by: Masahiro Yamada Acked-by: Stafford Horne --- arch/openrisc/include/asm/Kbuild | 29 +---------------------------- arch/openrisc/include/uapi/asm/Kbuild | 27 +++++++++++++++++++++++++++ 2 files changed, 28 insertions(+), 28 deletions(-) diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild index 091585addb91..5bea416a7792 100644 --- a/arch/openrisc/include/asm/Kbuild +++ b/arch/openrisc/include/asm/Kbuild @@ -1,6 +1,4 @@ -generic-y += auxvec.h generic-y += barrier.h -generic-y += bitsperlong.h generic-y += bug.h generic-y += bugs.h generic-y += cacheflush.h @@ -11,57 +9,32 @@ generic-y += device.h generic-y += div64.h generic-y += dma.h generic-y += emergency-restart.h -generic-y += errno.h generic-y += exec.h generic-y += extable.h generic-y += fb.h -generic-y += fcntl.h generic-y += ftrace.h generic-y += hardirq.h generic-y += hw_irq.h -generic-y += ioctl.h -generic-y += ioctls.h -generic-y += ipcbuf.h generic-y += irq.h generic-y += irq_regs.h generic-y += irq_work.h generic-y += kdebug.h generic-y += kmap_types.h -generic-y += kvm_para.h +generic-y += kprobes.h generic-y += local.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h -generic-y += mman.h generic-y += module.h -generic-y += msgbuf.h generic-y += pci.h generic-y += percpu.h -generic-y += poll.h -generic-y += posix_types.h generic-y += preempt.h -generic-y += resource.h generic-y += sections.h generic-y += segment.h -generic-y += sembuf.h -generic-y += setup.h -generic-y += shmbuf.h -generic-y += shmparam.h -generic-y += signal.h -generic-y += socket.h -generic-y += sockios.h -generic-y += stat.h -generic-y += statfs.h generic-y += string.h -generic-y += swab.h generic-y += switch_to.h -generic-y += termbits.h -generic-y += termios.h generic-y += topology.h generic-y += trace_clock.h -generic-y += types.h -generic-y += ucontext.h generic-y += user.h generic-y += vga.h generic-y += word-at-a-time.h generic-y += xor.h -generic-y += kprobes.h diff --git a/arch/openrisc/include/uapi/asm/Kbuild b/arch/openrisc/include/uapi/asm/Kbuild index b55fc2ae1e8c..62286dbeb904 100644 --- a/arch/openrisc/include/uapi/asm/Kbuild +++ b/arch/openrisc/include/uapi/asm/Kbuild @@ -1,4 +1,31 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += auxvec.h +generic-y += bitsperlong.h +generic-y += errno.h +generic-y += fcntl.h +generic-y += ioctl.h +generic-y += ioctls.h +generic-y += ipcbuf.h +generic-y += kvm_para.h +generic-y += mman.h +generic-y += msgbuf.h +generic-y += poll.h +generic-y += posix_types.h +generic-y += resource.h +generic-y += sembuf.h +generic-y += setup.h +generic-y += shmbuf.h +generic-y += shmparam.h generic-y += siginfo.h +generic-y += signal.h +generic-y += socket.h +generic-y += sockios.h +generic-y += stat.h +generic-y += statfs.h +generic-y += swab.h +generic-y += termbits.h +generic-y += termios.h +generic-y += types.h +generic-y += ucontext.h -- cgit v1.2.3-59-g8ed1b From bd78acad8e866e1167f9de97c9b090ee6c2c96a7 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:52 +0900 Subject: parisc: move generic-y of exported headers to uapi/asm/Kbuild Since commit fcc8487d477a ("uapi: export all headers under uapi directories"), all (and only) headers under uapi directories are exported, but asm-generic wrappers are still exceptions. To complete de-coupling the uapi from kernel headers, move generic-y of exported headers to uapi/asm/Kbuild. With this change, "make headers_install" will just need to parse uapi/asm/Kbuild to build up exported headers. Also, move "generic-y += kprobes.h" up in order to keep the entries sorted. Signed-off-by: Masahiro Yamada --- arch/parisc/include/asm/Kbuild | 7 +------ arch/parisc/include/uapi/asm/Kbuild | 4 ++++ 2 files changed, 5 insertions(+), 6 deletions(-) diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild index a9909c2d04c5..a41139575ab4 100644 --- a/arch/parisc/include/asm/Kbuild +++ b/arch/parisc/include/asm/Kbuild @@ -1,5 +1,3 @@ - -generic-y += auxvec.h generic-y += barrier.h generic-y += clkdev.h generic-y += current.h @@ -11,14 +9,12 @@ generic-y += hw_irq.h generic-y += irq_regs.h generic-y += irq_work.h generic-y += kdebug.h -generic-y += kvm_para.h +generic-y += kprobes.h generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h -generic-y += param.h generic-y += percpu.h -generic-y += poll.h generic-y += preempt.h generic-y += seccomp.h generic-y += segment.h @@ -28,4 +24,3 @@ generic-y += user.h generic-y += vga.h generic-y += word-at-a-time.h generic-y += xor.h -generic-y += kprobes.h diff --git a/arch/parisc/include/uapi/asm/Kbuild b/arch/parisc/include/uapi/asm/Kbuild index 3971c60a7e7f..196d2a4efb31 100644 --- a/arch/parisc/include/uapi/asm/Kbuild +++ b/arch/parisc/include/uapi/asm/Kbuild @@ -1,4 +1,8 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += auxvec.h +generic-y += kvm_para.h +generic-y += param.h +generic-y += poll.h generic-y += resource.h -- cgit v1.2.3-59-g8ed1b From 895931232d9358e0016f580f26b336c29c9528cc Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:53 +0900 Subject: sh: move generic-y of exported headers to uapi/asm/Kbuild Since commit fcc8487d477a ("uapi: export all headers under uapi directories"), all (and only) headers under uapi directories are exported, but asm-generic wrappers are still exceptions. To complete de-coupling the uapi from kernel headers, move generic-y of exported headers to uapi/asm/Kbuild. With this change, "make headers_install" will just need to parse uapi/asm/Kbuild to build up exported headers. Signed-off-by: Masahiro Yamada --- arch/sh/include/asm/Kbuild | 19 ------------------- arch/sh/include/uapi/asm/Kbuild | 18 ++++++++++++++++++ 2 files changed, 18 insertions(+), 19 deletions(-) diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild index 590c91ae7541..1a6f9c39feef 100644 --- a/arch/sh/include/asm/Kbuild +++ b/arch/sh/include/asm/Kbuild @@ -1,39 +1,20 @@ - -generic-y += bitsperlong.h generic-y += clkdev.h generic-y += current.h generic-y += delay.h generic-y += div64.h generic-y += emergency-restart.h -generic-y += errno.h generic-y += exec.h -generic-y += fcntl.h -generic-y += ioctl.h -generic-y += ipcbuf.h generic-y += irq_regs.h generic-y += irq_work.h -generic-y += kvm_para.h generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h -generic-y += mman.h -generic-y += msgbuf.h -generic-y += param.h generic-y += parport.h generic-y += percpu.h -generic-y += poll.h generic-y += preempt.h -generic-y += resource.h generic-y += rwsem.h -generic-y += sembuf.h generic-y += serial.h -generic-y += shmbuf.h generic-y += sizes.h -generic-y += socket.h -generic-y += statfs.h -generic-y += termbits.h -generic-y += termios.h generic-y += trace_clock.h -generic-y += ucontext.h generic-y += xor.h diff --git a/arch/sh/include/uapi/asm/Kbuild b/arch/sh/include/uapi/asm/Kbuild index b55fc2ae1e8c..e28531333efa 100644 --- a/arch/sh/include/uapi/asm/Kbuild +++ b/arch/sh/include/uapi/asm/Kbuild @@ -1,4 +1,22 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += bitsperlong.h +generic-y += errno.h +generic-y += fcntl.h +generic-y += ioctl.h +generic-y += ipcbuf.h +generic-y += kvm_para.h +generic-y += mman.h +generic-y += msgbuf.h +generic-y += param.h +generic-y += poll.h +generic-y += resource.h +generic-y += sembuf.h +generic-y += shmbuf.h generic-y += siginfo.h +generic-y += socket.h +generic-y += statfs.h +generic-y += termbits.h +generic-y += termios.h +generic-y += ucontext.h -- cgit v1.2.3-59-g8ed1b From b6744e04143dfe99f00b98367bc7e9e3449d7c07 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:54 +0900 Subject: sparc: move generic-y of exported headers to uapi/asm/Kbuild Since commit fcc8487d477a ("uapi: export all headers under uapi directories"), all (and only) headers under uapi directories are exported, but asm-generic wrappers are still exceptions. To complete de-coupling the uapi from kernel headers, move generic-y of exported headers to uapi/asm/Kbuild. With this change, "make headers_install" will just need to parse uapi/asm/Kbuild to build up exported headers. Signed-off-by: Masahiro Yamada --- arch/sparc/include/asm/Kbuild | 1 - arch/sparc/include/uapi/asm/Kbuild | 2 ++ 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index e9e837bc3158..80ddc01f57ac 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -18,5 +18,4 @@ generic-y += preempt.h generic-y += rwsem.h generic-y += serial.h generic-y += trace_clock.h -generic-y += types.h generic-y += word-at-a-time.h diff --git a/arch/sparc/include/uapi/asm/Kbuild b/arch/sparc/include/uapi/asm/Kbuild index b15bf6bc0e94..2178c78c7c1a 100644 --- a/arch/sparc/include/uapi/asm/Kbuild +++ b/arch/sparc/include/uapi/asm/Kbuild @@ -1,2 +1,4 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm + +generic-y += types.h -- cgit v1.2.3-59-g8ed1b From c44e27181f8217bdab6f8ad25d34c68c26fbabb4 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:55 +0900 Subject: tile: move generic-y of exported headers to uapi/asm/Kbuild Since commit fcc8487d477a ("uapi: export all headers under uapi directories"), all (and only) headers under uapi directories are exported, but asm-generic wrappers are still exceptions. To complete de-coupling the uapi from kernel headers, move generic-y of exported headers to uapi/asm/Kbuild. With this change, "make headers_install" will just need to parse uapi/asm/Kbuild to build up exported headers. Signed-off-by: Masahiro Yamada --- arch/tile/include/asm/Kbuild | 19 ------------------- arch/tile/include/uapi/asm/Kbuild | 19 +++++++++++++++++++ 2 files changed, 19 insertions(+), 19 deletions(-) diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild index 16f0b08c8ce9..d28d2b8932c7 100644 --- a/arch/tile/include/asm/Kbuild +++ b/arch/tile/include/asm/Kbuild @@ -2,37 +2,18 @@ generic-y += bug.h generic-y += bugs.h generic-y += clkdev.h generic-y += emergency-restart.h -generic-y += errno.h generic-y += exec.h generic-y += extable.h generic-y += fb.h -generic-y += fcntl.h generic-y += hw_irq.h -generic-y += ioctl.h -generic-y += ioctls.h -generic-y += ipcbuf.h generic-y += irq_regs.h generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h -generic-y += msgbuf.h -generic-y += param.h generic-y += parport.h -generic-y += poll.h -generic-y += posix_types.h generic-y += preempt.h -generic-y += resource.h generic-y += seccomp.h -generic-y += sembuf.h generic-y += serial.h -generic-y += shmbuf.h -generic-y += shmparam.h -generic-y += socket.h -generic-y += sockios.h -generic-y += statfs.h -generic-y += termbits.h -generic-y += termios.h generic-y += trace_clock.h -generic-y += types.h generic-y += xor.h diff --git a/arch/tile/include/uapi/asm/Kbuild b/arch/tile/include/uapi/asm/Kbuild index 0c74c3c5ebfa..5711de0a1b5e 100644 --- a/arch/tile/include/uapi/asm/Kbuild +++ b/arch/tile/include/uapi/asm/Kbuild @@ -1,4 +1,23 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += errno.h +generic-y += fcntl.h +generic-y += ioctl.h +generic-y += ioctls.h +generic-y += ipcbuf.h +generic-y += msgbuf.h +generic-y += param.h +generic-y += poll.h +generic-y += posix_types.h +generic-y += resource.h +generic-y += sembuf.h +generic-y += shmbuf.h +generic-y += shmparam.h +generic-y += socket.h +generic-y += sockios.h +generic-y += statfs.h +generic-y += termbits.h +generic-y += termios.h +generic-y += types.h generic-y += ucontext.h -- cgit v1.2.3-59-g8ed1b From ee73056bee8ed47ba12de56ab83bcbe1a0618926 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:56 +0900 Subject: unicore32: move generic-y of exported headers to uapi/asm/Kbuild Since commit fcc8487d477a ("uapi: export all headers under uapi directories"), all (and only) headers under uapi directories are exported, but asm-generic wrappers are still exceptions. To complete de-coupling the uapi from kernel headers, move generic-y of exported headers to uapi/asm/Kbuild. With this change, "make headers_install" will just need to parse uapi/asm/Kbuild to build up exported headers. Also, move "generic-y += kprobes.h" up in order to keep the entries sorted. Signed-off-by: Masahiro Yamada --- arch/unicore32/include/asm/Kbuild | 30 +----------------------------- arch/unicore32/include/uapi/asm/Kbuild | 27 +++++++++++++++++++++++++++ 2 files changed, 28 insertions(+), 29 deletions(-) diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild index 7a53a55341de..fda7e2153086 100644 --- a/arch/unicore32/include/asm/Kbuild +++ b/arch/unicore32/include/asm/Kbuild @@ -1,66 +1,38 @@ - generic-y += atomic.h -generic-y += auxvec.h -generic-y += bitsperlong.h generic-y += bugs.h generic-y += clkdev.h generic-y += current.h generic-y += device.h generic-y += div64.h generic-y += emergency-restart.h -generic-y += errno.h generic-y += exec.h generic-y += extable.h generic-y += fb.h -generic-y += fcntl.h generic-y += ftrace.h generic-y += futex.h generic-y += hardirq.h generic-y += hw_irq.h -generic-y += ioctl.h -generic-y += ioctls.h -generic-y += ipcbuf.h generic-y += irq_regs.h generic-y += irq_work.h generic-y += kdebug.h generic-y += kmap_types.h +generic-y += kprobes.h generic-y += local.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h -generic-y += mman.h generic-y += module.h -generic-y += msgbuf.h -generic-y += param.h generic-y += parport.h generic-y += percpu.h -generic-y += poll.h -generic-y += posix_types.h generic-y += preempt.h -generic-y += resource.h generic-y += sections.h generic-y += segment.h -generic-y += sembuf.h generic-y += serial.h -generic-y += setup.h -generic-y += shmbuf.h -generic-y += shmparam.h -generic-y += signal.h generic-y += sizes.h -generic-y += socket.h -generic-y += sockios.h -generic-y += stat.h -generic-y += statfs.h -generic-y += swab.h generic-y += syscalls.h -generic-y += termbits.h -generic-y += termios.h generic-y += topology.h generic-y += trace_clock.h -generic-y += types.h -generic-y += ucontext.h generic-y += unaligned.h generic-y += user.h generic-y += vga.h generic-y += word-at-a-time.h generic-y += xor.h -generic-y += kprobes.h diff --git a/arch/unicore32/include/uapi/asm/Kbuild b/arch/unicore32/include/uapi/asm/Kbuild index 1c44d3b3eba0..759a71411169 100644 --- a/arch/unicore32/include/uapi/asm/Kbuild +++ b/arch/unicore32/include/uapi/asm/Kbuild @@ -1,5 +1,32 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm +generic-y += auxvec.h +generic-y += bitsperlong.h +generic-y += errno.h +generic-y += fcntl.h +generic-y += ioctl.h +generic-y += ioctls.h +generic-y += ipcbuf.h generic-y += kvm_para.h +generic-y += mman.h +generic-y += msgbuf.h +generic-y += param.h +generic-y += poll.h +generic-y += posix_types.h +generic-y += resource.h +generic-y += sembuf.h +generic-y += setup.h +generic-y += shmbuf.h +generic-y += shmparam.h generic-y += siginfo.h +generic-y += signal.h +generic-y += socket.h +generic-y += sockios.h +generic-y += stat.h +generic-y += statfs.h +generic-y += swab.h +generic-y += termbits.h +generic-y += termios.h +generic-y += types.h +generic-y += ucontext.h -- cgit v1.2.3-59-g8ed1b From 22c92aee6f95d9c82d33f04c90c6903a6a94df80 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:57 +0900 Subject: xtensa: move generic-y of exported headers to uapi/asm/Kbuild Since commit fcc8487d477a ("uapi: export all headers under uapi directories"), all (and only) headers under uapi directories are exported, but asm-generic wrappers are still exceptions. To complete de-coupling the uapi from kernel headers, move generic-y of exported headers to uapi/asm/Kbuild. With this change, "make headers_install" will just need to parse uapi/asm/Kbuild to build up exported headers. Also, move "generic-y += kprobes.h" up in order to keep the entries sorted. Signed-off-by: Masahiro Yamada --- arch/xtensa/include/asm/Kbuild | 10 +--------- arch/xtensa/include/uapi/asm/Kbuild | 9 +++++++++ 2 files changed, 10 insertions(+), 9 deletions(-) diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild index 30f6290109d4..c04efde775a5 100644 --- a/arch/xtensa/include/asm/Kbuild +++ b/arch/xtensa/include/asm/Kbuild @@ -1,20 +1,16 @@ -generic-y += bitsperlong.h generic-y += bug.h generic-y += clkdev.h generic-y += div64.h generic-y += dma-contiguous.h generic-y += emergency-restart.h -generic-y += errno.h generic-y += exec.h generic-y += extable.h -generic-y += fcntl.h generic-y += hardirq.h -generic-y += ioctl.h generic-y += irq_regs.h generic-y += irq_work.h generic-y += kdebug.h generic-y += kmap_types.h -generic-y += kvm_para.h +generic-y += kprobes.h generic-y += linkage.h generic-y += local.h generic-y += local64.h @@ -22,13 +18,9 @@ generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += percpu.h generic-y += preempt.h -generic-y += resource.h generic-y += rwsem.h generic-y += sections.h -generic-y += statfs.h -generic-y += termios.h generic-y += topology.h generic-y += trace_clock.h generic-y += word-at-a-time.h generic-y += xor.h -generic-y += kprobes.h diff --git a/arch/xtensa/include/uapi/asm/Kbuild b/arch/xtensa/include/uapi/asm/Kbuild index 4cb0d2f8868c..a5bcdfb890f1 100644 --- a/arch/xtensa/include/uapi/asm/Kbuild +++ b/arch/xtensa/include/uapi/asm/Kbuild @@ -1,3 +1,12 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm + +generic-y += bitsperlong.h +generic-y += errno.h +generic-y += fcntl.h +generic-y += ioctl.h +generic-y += kvm_para.h +generic-y += resource.h generic-y += siginfo.h +generic-y += statfs.h +generic-y += termios.h -- cgit v1.2.3-59-g8ed1b From d1b32bacffe189a0cdc2c36905a753535638cb1c Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:58 +0900 Subject: kbuild: do not include old-kbuild-file from Makefile.headersinst Now asm-generic wrappers to be exported are all listed in arch/*/include/uapi/asm/Kbuild. "make headers_install" no longer depends on any Kbuild files outside uapi directories. Signed-off-by: Masahiro Yamada --- scripts/Makefile.headersinst | 5 ----- 1 file changed, 5 deletions(-) diff --git a/scripts/Makefile.headersinst b/scripts/Makefile.headersinst index e9147f05ea77..e6343b34182a 100644 --- a/scripts/Makefile.headersinst +++ b/scripts/Makefile.headersinst @@ -40,11 +40,6 @@ ifeq ($(skip-inst),) kbuild-file := $(srctree)/$(obj)/Kbuild -include $(kbuild-file) -old-kbuild-file := $(srctree)/$(subst uapi/,,$(obj))/Kbuild -ifneq ($(wildcard $(old-kbuild-file)),) -include $(old-kbuild-file) -endif - installdir := $(INSTALL_HDR_PATH)/$(dst) gendir := $(objtree)/$(subst include/,include/generated/,$(obj)) header-files := $(notdir $(wildcard $(srcdir)/*.h)) -- cgit v1.2.3-59-g8ed1b From a9d9a400e0753491e3eacc9f4dbc60547ea1de45 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:32:59 +0900 Subject: kbuild: split exported generic header creation into uapi-asm-generic When we install headers, we are interested only in headers under uapi directories. Split out uapi-asm-generic target and make headers_install depend on it. It will avoid generating unneeded asm-generic wrappers. Signed-off-by: Masahiro Yamada --- Makefile | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/Makefile b/Makefile index 70c414b15859..f75a93fa9975 100644 --- a/Makefile +++ b/Makefile @@ -456,10 +456,11 @@ ifneq ($(KBUILD_SRC),) endif # Support for using generic headers in asm-generic -PHONY += asm-generic -asm-generic: +PHONY += asm-generic uapi-asm-generic +asm-generic: uapi-asm-generic $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.asm-generic \ src=asm obj=arch/$(SRCARCH)/include/generated/asm +uapi-asm-generic: $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.asm-generic \ src=uapi/asm obj=arch/$(SRCARCH)/include/generated/uapi/asm @@ -1143,7 +1144,7 @@ PHONY += archscripts archscripts: PHONY += __headers -__headers: $(version_h) scripts_basic asm-generic archheaders archscripts +__headers: $(version_h) scripts_basic uapi-asm-generic archheaders archscripts $(Q)$(MAKE) $(build)=scripts build_unifdef PHONY += headers_install_all -- cgit v1.2.3-59-g8ed1b From 09c3776c5472f2bc73b29b13d5947cec6103a99c Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 10 Jul 2017 03:33:00 +0900 Subject: kbuild: remove wrapper files handling from Makefile.headersinst scripts/Makefike.headersinst creates asm-generic wrappers by itself because scripts/Makefile.asm-generic created some of exported wrappers outside uapi directories. Now this distortion has been fixed. scripts/Makefile.headersinst can simply copy wrappers created by scripts/Makefile.asm-generic. Signed-off-by: Masahiro Yamada --- scripts/Makefile.headersinst | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/scripts/Makefile.headersinst b/scripts/Makefile.headersinst index e6343b34182a..343d586e566e 100644 --- a/scripts/Makefile.headersinst +++ b/scripts/Makefile.headersinst @@ -52,14 +52,8 @@ genhdr-files := $(filter-out $(header-files), $(genhdr-files)) install-file := $(installdir)/.install check-file := $(installdir)/.check -# generic-y list all files an architecture uses from asm-generic -# Use this to build a list of headers which require a wrapper -generic-files := $(notdir $(wildcard $(srctree)/include/uapi/asm-generic/*.h)) -wrapper-files := $(filter $(generic-files), $(generic-y)) -wrapper-files := $(filter-out $(header-files), $(wrapper-files)) - # all headers files for this dir -all-files := $(header-files) $(genhdr-files) $(wrapper-files) +all-files := $(header-files) $(genhdr-files) output-files := $(addprefix $(installdir)/, $(all-files)) ifneq ($(mandatory-y),) @@ -83,9 +77,6 @@ quiet_cmd_install = INSTALL $(printdir) ($(words $(all-files))\ cmd_install = \ $(CONFIG_SHELL) $< $(installdir) $(srcdir) $(header-files); \ $(CONFIG_SHELL) $< $(installdir) $(gendir) $(genhdr-files); \ - for F in $(wrapper-files); do \ - echo "\#include " > $(installdir)/$$F; \ - done; \ touch $@ quiet_cmd_remove = REMOVE $(unwanted) -- cgit v1.2.3-59-g8ed1b From d7f14c66c273b00aaa626f419d3155773a88d460 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Sun, 9 Jul 2017 20:02:36 +0200 Subject: kbuild: Enable Large File Support for hostprogs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This fixes the following build error for me when building on an 32 bit machine using an XFS file system: $ make scripts/basic/fixdep HOSTCC scripts/basic/fixdep fixdep: error fstat'ing depfile: scripts/basic/.fixdep.d: Value too large for defined data type Signed-off-by: Uwe Kleine-König Acked-by: Ben Hutchings Signed-off-by: Masahiro Yamada --- Makefile | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/Makefile b/Makefile index f75a93fa9975..1d6695ec3138 100644 --- a/Makefile +++ b/Makefile @@ -294,10 +294,17 @@ CONFIG_SHELL := $(shell if [ -x "$$BASH" ]; then echo $$BASH; \ else if [ -x /bin/bash ]; then echo /bin/bash; \ else echo sh; fi ; fi) +HOST_LFS_CFLAGS := $(shell getconf LFS_CFLAGS) +HOST_LFS_LDFLAGS := $(shell getconf LFS_LDFLAGS) +HOST_LFS_LIBS := $(shell getconf LFS_LIBS) + HOSTCC = gcc HOSTCXX = g++ -HOSTCFLAGS := -Wall -Wmissing-prototypes -Wstrict-prototypes -O2 -fomit-frame-pointer -std=gnu89 -HOSTCXXFLAGS = -O2 +HOSTCFLAGS := -Wall -Wmissing-prototypes -Wstrict-prototypes -O2 \ + -fomit-frame-pointer -std=gnu89 $(HOST_LFS_CFLAGS) +HOSTCXXFLAGS := -O2 $(HOST_LFS_CFLAGS) +HOSTLDFLAGS := $(HOST_LFS_LDFLAGS) +HOST_LOADLIBES := $(HOST_LFS_LIBS) ifeq ($(shell $(HOSTCC) -v 2>&1 | grep -c "clang version"), 1) HOSTCFLAGS += -Wno-unused-value -Wno-unused-parameter \ @@ -408,7 +415,7 @@ KERNELVERSION = $(VERSION)$(if $(PATCHLEVEL),.$(PATCHLEVEL)$(if $(SUBLEVEL),.$(S export VERSION PATCHLEVEL SUBLEVEL KERNELRELEASE KERNELVERSION export ARCH SRCARCH CONFIG_SHELL HOSTCC HOSTCFLAGS CROSS_COMPILE AS LD CC -export CPP AR NM STRIP OBJCOPY OBJDUMP +export CPP AR NM STRIP OBJCOPY OBJDUMP HOSTLDFLAGS HOST_LOADLIBES export MAKE AWK GENKSYMS INSTALLKERNEL PERL PYTHON UTS_MACHINE export HOSTCXX HOSTCXXFLAGS LDFLAGS_MODULE CHECK CHECKFLAGS -- cgit v1.2.3-59-g8ed1b From d40e0d4fb5613099a58c95a9403f51b03e40e861 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Wed, 5 Jul 2017 09:59:05 -0700 Subject: locking/qspinlock: Include linux/prefetch.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit kernel/locking/qspinlock.c makes use of prefetchw() but hasn't included linux/prefetch.h up until now, instead relying upon indirect inclusion of some header that defines prefetchw(). In the case of MIPS we generally obtain a definition of prefetchw() from asm/processor.h, included by way of linux/mutex.h, but only for configurations which select CONFIG_CPU_HAS_PREFETCH. For configurations which don't this leaves prefetchw() undefined leading to the following build failure: CC kernel/locking/qspinlock.o kernel/locking/qspinlock.c: In function ‘queued_spin_lock_slowpath’: kernel/locking/qspinlock.c:549:4: error: implicit declaration of function ‘prefetchw’ [-Werror=implicit-function-declaration] prefetchw(next); ^~~~~~~~~ Fix this by including linux/prefetch.h in order to ensure that we get a definition of prefetchw(). Signed-off-by: Paul Burton Cc: Ingo Molnar Cc: Peter Zijlstra Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Signed-off-by: Ralf Baechle --- kernel/locking/qspinlock.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index b2caec7315af..fd24153e8a48 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include -- cgit v1.2.3-59-g8ed1b From 7432b49b54cd931743f0b6e9f652bc329e4a242a Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 5 Jul 2017 17:09:41 +0200 Subject: mmc: block: Initialize ret in mmc_blk_issue_drv_op() for MMC_DRV_OP_IOCTL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With gcc 4.1.2: drivers/mmc/core/block.c: In function ‘mmc_blk_issue_drv_op’: drivers/mmc/core/block.c:1178: warning: ‘ret’ may be used uninitialized in this function Indeed, for MMC_DRV_OP_IOCTL, if mq_rq->ioc_count is zero, an uninitialized value will be stored in mq_rq->drv_op_result and passed to blk_end_request_all(). Can mq_rq->ioc_count be zero? - mmc_blk_ioctl_cmd() sets ioc_count to 1, so this is safe, - mmc_blk_ioctl_multi_cmd() obtains ioc_count from user space in response to the MMC_IOC_MULTI_CMD ioctl, and does allow zero. Initialize ret to zero to fix this for current and future callers. Fixes: 0493f6fe5bdee8ac ("mmc: block: Move boot partition locking into a driver op") Signed-off-by: Geert Uytterhoeven Signed-off-by: Ulf Hansson --- drivers/mmc/core/block.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 0cfac2d39107..4920ea1ece38 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -1182,7 +1182,7 @@ static void mmc_blk_issue_drv_op(struct mmc_queue *mq, struct request *req) switch (mq_rq->drv_op) { case MMC_DRV_OP_IOCTL: - for (i = 0; i < mq_rq->ioc_count; i++) { + for (i = 0, ret = 0; i < mq_rq->ioc_count; i++) { ret = __mmc_blk_ioctl_cmd(card, md, mq_rq->idata[i]); if (ret) break; -- cgit v1.2.3-59-g8ed1b From aab2ee03912be6e12bb5f4810be0b80a82168d3e Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 5 Jul 2017 17:09:42 +0200 Subject: mmc: block: Let MMC_IOC_MULTI_CMD return zero again for zero entries MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With gcc 4.1.2: drivers/mmc/core/block.c: In function ‘mmc_blk_ioctl_cmd_issue’: drivers/mmc/core/block.c:630: warning: ‘ioc_err’ may be used uninitialized in this function Indeed, if mq_rq->ioc_count is zero, an uninitialized value will be stored in mq_rq->drv_op_result and passed to blk_end_request_all(). Can mq_rq->ioc_count be zero? - mmc_blk_ioctl_cmd() sets ioc_count to 1, so this is safe, - mmc_blk_ioctl_multi_cmd() obtains ioc_count from user space in response to the MMC_IOC_MULTI_CMD ioctl, and does allow zero. To avoid returning an uninitialized value, and as it is pointless to do all this work when the MMC_IOC_MULTI_CMD ioctl is used with zero entries, check for this early in mmc_blk_ioctl_multi_cmd(), and return zero, like was returned before. Fixes: 3ecd8cf23f88d5df ("mmc: block: move multi-ioctl() to use block layer") Signed-off-by: Geert Uytterhoeven Signed-off-by: Ulf Hansson --- drivers/mmc/core/block.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 4920ea1ece38..e0363223996e 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -637,6 +637,9 @@ static int mmc_blk_ioctl_multi_cmd(struct block_device *bdev, sizeof(num_of_cmds))) return -EFAULT; + if (!num_of_cmds) + return 0; + if (num_of_cmds > MMC_IOC_MAX_CMDS) return -EINVAL; -- cgit v1.2.3-59-g8ed1b From e7d80c830489f67b1d0257e6919840100085dea9 Mon Sep 17 00:00:00 2001 From: Mike Marciniszyn Date: Thu, 22 Jun 2017 15:01:10 -0400 Subject: IB/iser: Handle lack of memory management extentions correctly max_fast_reg_page_list_len is only valid when the memory management extentions are signaled by the underlying driver. Fix by adjusting iser_calc_scsi_params() to use ISCSI_ISER_MAX_SG_TABLESIZE when the extentions are not indicated. Reported-by: Thomas Rosenstein Fixes: Commit df749cdc45d9 ("IB/iser: Support up to 8MB data transfer in a single command") Reviewed-by: Dennis Dalessandro Signed-off-by: Mike Marciniszyn Acked-by: Sagi Grimberg Tested-by: Thomas Rosenstein Signed-off-by: Doug Ledford --- drivers/infiniband/ulp/iser/iser_verbs.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c index c538a38c91ce..26a004e97ae0 100644 --- a/drivers/infiniband/ulp/iser/iser_verbs.c +++ b/drivers/infiniband/ulp/iser/iser_verbs.c @@ -708,8 +708,14 @@ iser_calc_scsi_params(struct iser_conn *iser_conn, unsigned short sg_tablesize, sup_sg_tablesize; sg_tablesize = DIV_ROUND_UP(max_sectors * 512, SIZE_4K); - sup_sg_tablesize = min_t(unsigned, ISCSI_ISER_MAX_SG_TABLESIZE, - device->ib_device->attrs.max_fast_reg_page_list_len); + if (device->ib_device->attrs.device_cap_flags & + IB_DEVICE_MEM_MGT_EXTENSIONS) + sup_sg_tablesize = + min_t( + uint, ISCSI_ISER_MAX_SG_TABLESIZE, + device->ib_device->attrs.max_fast_reg_page_list_len); + else + sup_sg_tablesize = ISCSI_ISER_MAX_SG_TABLESIZE; iser_conn->scsi_sg_tablesize = min(sg_tablesize, sup_sg_tablesize); } -- cgit v1.2.3-59-g8ed1b From b6ea01ba3fe9dcb5e08bbd9ed482845582a1e80b Mon Sep 17 00:00:00 2001 From: "Amrani, Ram" Date: Mon, 29 May 2017 11:18:54 +0300 Subject: RDMA/qedr: Add qedr to MAINTAINERS file Signed-off-by: Ram Amrani Signed-off-by: Ariel Elior Signed-off-by: Doug Ledford --- MAINTAINERS | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 053c3bdd1fe5..53437d46a39d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10531,6 +10531,14 @@ L: linux-scsi@vger.kernel.org S: Supported F: drivers/scsi/qedf/ +QLOGIC QL4xxx RDMA DRIVER +M: Ram Amrani +M: Ariel Elior +L: linux-rdma@vger.kernel.org +S: Supported +F: drivers/infiniband/hw/qedr/ +F: include/uapi/rdma/qedr-abi.h + QNX4 FILESYSTEM M: Anders Larsen W: http://www.alarsen.net/linux/qnx4fs/ -- cgit v1.2.3-59-g8ed1b From 2fd1d2c4ceb2248a727696962cf3370dc9f5a0a4 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 6 Jul 2017 08:41:06 -0500 Subject: proc: Fix proc_sys_prune_dcache to hold a sb reference Andrei Vagin writes: FYI: This bug has been reproduced on 4.11.7 > BUG: Dentry ffff895a3dd01240{i=4e7c09a,n=lo} still in use (1) [unmount of proc proc] > ------------[ cut here ]------------ > WARNING: CPU: 1 PID: 13588 at fs/dcache.c:1445 umount_check+0x6e/0x80 > CPU: 1 PID: 13588 Comm: kworker/1:1 Not tainted 4.11.7-200.fc25.x86_64 #1 > Hardware name: CompuLab sbc-flt1/fitlet, BIOS SBCFLT_0.08.04 06/27/2015 > Workqueue: events proc_cleanup_work > Call Trace: > dump_stack+0x63/0x86 > __warn+0xcb/0xf0 > warn_slowpath_null+0x1d/0x20 > umount_check+0x6e/0x80 > d_walk+0xc6/0x270 > ? dentry_free+0x80/0x80 > do_one_tree+0x26/0x40 > shrink_dcache_for_umount+0x2d/0x90 > generic_shutdown_super+0x1f/0xf0 > kill_anon_super+0x12/0x20 > proc_kill_sb+0x40/0x50 > deactivate_locked_super+0x43/0x70 > deactivate_super+0x5a/0x60 > cleanup_mnt+0x3f/0x90 > mntput_no_expire+0x13b/0x190 > kern_unmount+0x3e/0x50 > pid_ns_release_proc+0x15/0x20 > proc_cleanup_work+0x15/0x20 > process_one_work+0x197/0x450 > worker_thread+0x4e/0x4a0 > kthread+0x109/0x140 > ? process_one_work+0x450/0x450 > ? kthread_park+0x90/0x90 > ret_from_fork+0x2c/0x40 > ---[ end trace e1c109611e5d0b41 ]--- > VFS: Busy inodes after unmount of proc. Self-destruct in 5 seconds. Have a nice day... > BUG: unable to handle kernel NULL pointer dereference at (null) > IP: _raw_spin_lock+0xc/0x30 > PGD 0 Fix this by taking a reference to the super block in proc_sys_prune_dcache. The superblock reference is the core of the fix however the sysctl_inodes list is converted to a hlist so that hlist_del_init_rcu may be used. This allows proc_sys_prune_dache to remove inodes the sysctl_inodes list, while not causing problems for proc_sys_evict_inode when if it later choses to remove the inode from the sysctl_inodes list. Removing inodes from the sysctl_inodes list allows proc_sys_prune_dcache to have a progress guarantee, while still being able to drop all locks. The fact that head->unregistering is set in start_unregistering ensures that no more inodes will be added to the the sysctl_inodes list. Previously the code did a dance where it delayed calling iput until the next entry in the list was being considered to ensure the inode remained on the sysctl_inodes list until the next entry was walked to. The structure of the loop in this patch does not need that so is much easier to understand and maintain. Cc: stable@vger.kernel.org Reported-by: Andrei Vagin Tested-by: Andrei Vagin Fixes: ace0c791e6c3 ("proc/sysctl: Don't grab i_lock under sysctl_lock.") Fixes: d6cffbbe9a7e ("proc/sysctl: prune stale dentries during unregistering") Signed-off-by: "Eric W. Biederman" --- fs/proc/internal.h | 2 +- fs/proc/proc_sysctl.c | 43 ++++++++++++++++++++++++++++++------------- include/linux/sysctl.h | 2 +- 3 files changed, 32 insertions(+), 15 deletions(-) diff --git a/fs/proc/internal.h b/fs/proc/internal.h index c5ae09b6c726..18694598bebf 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -67,7 +67,7 @@ struct proc_inode { struct proc_dir_entry *pde; struct ctl_table_header *sysctl; struct ctl_table *sysctl_entry; - struct list_head sysctl_inodes; + struct hlist_node sysctl_inodes; const struct proc_ns_operations *ns_ops; struct inode vfs_inode; }; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 67985a7233c2..9bf06e2b1284 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -191,7 +191,7 @@ static void init_header(struct ctl_table_header *head, head->set = set; head->parent = NULL; head->node = node; - INIT_LIST_HEAD(&head->inodes); + INIT_HLIST_HEAD(&head->inodes); if (node) { struct ctl_table *entry; for (entry = table; entry->procname; entry++, node++) @@ -261,25 +261,42 @@ static void unuse_table(struct ctl_table_header *p) complete(p->unregistering); } -/* called under sysctl_lock */ static void proc_sys_prune_dcache(struct ctl_table_header *head) { - struct inode *inode, *prev = NULL; + struct inode *inode; struct proc_inode *ei; + struct hlist_node *node; + struct super_block *sb; rcu_read_lock(); - list_for_each_entry_rcu(ei, &head->inodes, sysctl_inodes) { - inode = igrab(&ei->vfs_inode); - if (inode) { - rcu_read_unlock(); - iput(prev); - prev = inode; - d_prune_aliases(inode); + for (;;) { + node = hlist_first_rcu(&head->inodes); + if (!node) + break; + ei = hlist_entry(node, struct proc_inode, sysctl_inodes); + spin_lock(&sysctl_lock); + hlist_del_init_rcu(&ei->sysctl_inodes); + spin_unlock(&sysctl_lock); + + inode = &ei->vfs_inode; + sb = inode->i_sb; + if (!atomic_inc_not_zero(&sb->s_active)) + continue; + inode = igrab(inode); + rcu_read_unlock(); + if (unlikely(!inode)) { + deactivate_super(sb); rcu_read_lock(); + continue; } + + d_prune_aliases(inode); + iput(inode); + deactivate_super(sb); + + rcu_read_lock(); } rcu_read_unlock(); - iput(prev); } /* called under sysctl_lock, will reacquire if has to wait */ @@ -461,7 +478,7 @@ static struct inode *proc_sys_make_inode(struct super_block *sb, } ei->sysctl = head; ei->sysctl_entry = table; - list_add_rcu(&ei->sysctl_inodes, &head->inodes); + hlist_add_head_rcu(&ei->sysctl_inodes, &head->inodes); head->count++; spin_unlock(&sysctl_lock); @@ -489,7 +506,7 @@ out: void proc_sys_evict_inode(struct inode *inode, struct ctl_table_header *head) { spin_lock(&sysctl_lock); - list_del_rcu(&PROC_I(inode)->sysctl_inodes); + hlist_del_init_rcu(&PROC_I(inode)->sysctl_inodes); if (!--head->count) kfree_rcu(head, rcu); spin_unlock(&sysctl_lock); diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 80d07816def0..1c04a26bfd2f 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -143,7 +143,7 @@ struct ctl_table_header struct ctl_table_set *set; struct ctl_dir *parent; struct ctl_node *node; - struct list_head inodes; /* head for proc_inode->sysctl_inodes */ + struct hlist_head inodes; /* head for proc_inode->sysctl_inodes */ }; struct ctl_dir { -- cgit v1.2.3-59-g8ed1b From c1bda752fdaead0c154c13a72a83faabc7dffc82 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 11 Jul 2017 13:41:34 +0200 Subject: platform/x86: peaq-wmi: Fix peaq_ignore_events_counter handling off by 1 If peaq_ignore_events_counter gets set to 1 we should skip polling 1 time, rather then ignoring it. Signed-off-by: Hans de Goede Signed-off-by: Darren Hart (VMware) --- drivers/platform/x86/peaq-wmi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/platform/x86/peaq-wmi.c b/drivers/platform/x86/peaq-wmi.c index ca75b4dc437e..77d1f90b0794 100644 --- a/drivers/platform/x86/peaq-wmi.c +++ b/drivers/platform/x86/peaq-wmi.c @@ -51,7 +51,7 @@ static void peaq_wmi_poll(struct input_polled_dev *dev) return; } - if (peaq_ignore_events_counter && --peaq_ignore_events_counter > 0) + if (peaq_ignore_events_counter && --peaq_ignore_events_counter >= 0) return; if (obj.integer.value) { -- cgit v1.2.3-59-g8ed1b From ee56ff71bbc405d841415809cb5ece079e7dd785 Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Tue, 11 Jul 2017 16:18:14 +0530 Subject: platform/x86: fujitsu-laptop: constify attribute_group structures. attribute_groups are not supposed to change at runtime. All functions working with attribute_groups provided by work with const attribute_group. So mark the non-const structs as const. File size before: text data bss dec hex filename 7474 1205 24 8703 21ff drivers/platform/x86/fujitsu-laptop.o File size After adding 'const': text data bss dec hex filename 7538 1141 24 8703 21ff drivers/platform/x86/fujitsu-laptop.o Signed-off-by: Arvind Yadav Reviewed-by: Jonathan Woithe Signed-off-by: Darren Hart (VMware) --- drivers/platform/x86/fujitsu-laptop.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/platform/x86/fujitsu-laptop.c b/drivers/platform/x86/fujitsu-laptop.c index 9a1034bec0fc..85de30f93a9c 100644 --- a/drivers/platform/x86/fujitsu-laptop.c +++ b/drivers/platform/x86/fujitsu-laptop.c @@ -317,7 +317,7 @@ static struct attribute *fujitsu_pf_attributes[] = { NULL }; -static struct attribute_group fujitsu_pf_attribute_group = { +static const struct attribute_group fujitsu_pf_attribute_group = { .attrs = fujitsu_pf_attributes }; -- cgit v1.2.3-59-g8ed1b From ab56246bee36b7226355d10f817ef8c27f56ef4b Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Tue, 11 Jul 2017 16:18:15 +0530 Subject: platform/x86: compal-laptop: constify attribute_group structures. attribute_groups are not supposed to change at runtime. All functions working with attribute_groups provided by work with const attribute_group. So mark the non-const structs as const. File size before: text data bss dec hex filename 6781 6144 34 12959 329f drivers/platform/x86/compal-laptop.o File size After adding 'const': text data bss dec hex filename 6845 6080 34 12959 329f drivers/platform/x86/compal-laptop.o Signed-off-by: Arvind Yadav Signed-off-by: Darren Hart (VMware) --- drivers/platform/x86/compal-laptop.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/platform/x86/compal-laptop.c b/drivers/platform/x86/compal-laptop.c index e1c2b6d4b24a..a8e4a539e704 100644 --- a/drivers/platform/x86/compal-laptop.c +++ b/drivers/platform/x86/compal-laptop.c @@ -718,7 +718,7 @@ static struct attribute *compal_platform_attrs[] = { &dev_attr_wake_up_mouse.attr, NULL }; -static struct attribute_group compal_platform_attr_group = { +static const struct attribute_group compal_platform_attr_group = { .attrs = compal_platform_attrs }; -- cgit v1.2.3-59-g8ed1b From 8546268e1177bd84157c7dc5bad82a2433fb5fea Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Tue, 11 Jul 2017 16:18:16 +0530 Subject: platform/x86: samsung-laptop: constify attribute_group structures. attribute_groups are not supposed to change at runtime. All functions working with attribute_groups provided by work with const attribute_group. So mark the non-const structs as const. File size before: text data bss dec hex filename 8710 5452 23 14185 3769 drivers/platform/x86/samsung-laptop.o File size After adding 'const': text data bss dec hex filename 8774 5388 23 14185 3769 drivers/platform/x86/samsung-laptop.o Signed-off-by: Arvind Yadav Signed-off-by: Darren Hart (VMware) --- drivers/platform/x86/samsung-laptop.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/platform/x86/samsung-laptop.c b/drivers/platform/x86/samsung-laptop.c index 5c4dfe48f03d..0c703feaeb88 100644 --- a/drivers/platform/x86/samsung-laptop.c +++ b/drivers/platform/x86/samsung-laptop.c @@ -1232,7 +1232,7 @@ static umode_t samsung_sysfs_is_visible(struct kobject *kobj, return ok ? attr->mode : 0; } -static struct attribute_group platform_attribute_group = { +static const struct attribute_group platform_attribute_group = { .is_visible = samsung_sysfs_is_visible, .attrs = platform_attributes }; -- cgit v1.2.3-59-g8ed1b From 4b7942d8d1ced3c82495953cb0bb90e7de6dbba6 Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Tue, 11 Jul 2017 16:18:17 +0530 Subject: platform/x86: alienware-wmi: constify attribute_group structures. attribute_groups are not supposed to change at runtime. All functions working with attribute_groups provided by work with const attribute_group. So mark the non-const structs as const. File size before: text data bss dec hex filename 6932 1016 48 7996 1f3c drivers/platform/x86/alienware-wmi.o File size After adding 'const': text data bss dec hex filename 7060 888 48 7996 1f64 drivers/platform/x86/alienware-wmi.o Signed-off-by: Arvind Yadav Signed-off-by: Darren Hart (VMware) --- drivers/platform/x86/alienware-wmi.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/platform/x86/alienware-wmi.c b/drivers/platform/x86/alienware-wmi.c index 9866fec78c1c..0831b428c217 100644 --- a/drivers/platform/x86/alienware-wmi.c +++ b/drivers/platform/x86/alienware-wmi.c @@ -604,7 +604,7 @@ static struct attribute *hdmi_attrs[] = { NULL, }; -static struct attribute_group hdmi_attribute_group = { +static const struct attribute_group hdmi_attribute_group = { .name = "hdmi", .attrs = hdmi_attrs, }; @@ -660,7 +660,7 @@ static struct attribute *amplifier_attrs[] = { NULL, }; -static struct attribute_group amplifier_attribute_group = { +static const struct attribute_group amplifier_attribute_group = { .name = "amplifier", .attrs = amplifier_attrs, }; @@ -741,7 +741,7 @@ static struct attribute *deepsleep_attrs[] = { NULL, }; -static struct attribute_group deepsleep_attribute_group = { +static const struct attribute_group deepsleep_attribute_group = { .name = "deepsleep", .attrs = deepsleep_attrs, }; -- cgit v1.2.3-59-g8ed1b From 24f584055c360d39cb55e91a7a1c53ddeb4a6147 Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Tue, 11 Jul 2017 16:18:18 +0530 Subject: platform/x86: panasonic-laptop: constify attribute_group structures. attribute_groups are not supposed to change at runtime. All functions working with attribute_groups provided by work with const attribute_group. So mark the non-const structs as const. File size before: text data bss dec hex filename 2505 600 4 3109 c25 drivers/platform/x86/panasonic-laptop.o File size After adding 'const': text data bss dec hex filename 2569 536 4 3109 c25 drivers/platform/x86/panasonic-laptop.o Signed-off-by: Arvind Yadav Signed-off-by: Darren Hart (VMware) --- drivers/platform/x86/panasonic-laptop.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/platform/x86/panasonic-laptop.c b/drivers/platform/x86/panasonic-laptop.c index 76b0a58e205b..5c39b3211709 100644 --- a/drivers/platform/x86/panasonic-laptop.c +++ b/drivers/platform/x86/panasonic-laptop.c @@ -437,7 +437,7 @@ static struct attribute *pcc_sysfs_entries[] = { NULL, }; -static struct attribute_group pcc_attr_group = { +static const struct attribute_group pcc_attr_group = { .name = NULL, /* put in device directory */ .attrs = pcc_sysfs_entries, }; -- cgit v1.2.3-59-g8ed1b From e90d9ba837b3b779644613a3b9e4845a0cd302f2 Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Tue, 11 Jul 2017 16:18:19 +0530 Subject: platform/x86: asus-wmi: constify attribute_group structures. attribute_groups are not supposed to change at runtime. All functions working with attribute_groups provided by work with const attribute_group. So mark the non-const structs as const. File size before: text data bss dec hex filename 13140 840 1 13981 369d drivers/platform/x86/asus-wmi.o File size After adding 'const': text data bss dec hex filename 13268 712 1 13981 368d drivers/platform/x86/asus-wmi.o Signed-off-by: Arvind Yadav Signed-off-by: Darren Hart (VMware) --- drivers/platform/x86/asus-wmi.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 6c7d86074b38..709e3a67391a 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -1433,7 +1433,7 @@ static umode_t asus_hwmon_sysfs_is_visible(struct kobject *kobj, return ok ? attr->mode : 0; } -static struct attribute_group hwmon_attribute_group = { +static const struct attribute_group hwmon_attribute_group = { .is_visible = asus_hwmon_sysfs_is_visible, .attrs = hwmon_attributes }; @@ -1821,7 +1821,7 @@ static umode_t asus_sysfs_is_visible(struct kobject *kobj, return ok ? attr->mode : 0; } -static struct attribute_group platform_attribute_group = { +static const struct attribute_group platform_attribute_group = { .is_visible = asus_sysfs_is_visible, .attrs = platform_attributes }; -- cgit v1.2.3-59-g8ed1b From 44bd76d0a3ff1901b66a739c4a9e68e6fdc0463c Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Tue, 11 Jul 2017 16:18:20 +0530 Subject: platform/x86: toshiba_acpi: constify attribute_group structures. attribute_groups are not supposed to change at runtime. All functions working with attribute_groups provided by work with const attribute_group. So mark the non-const structs as const. File size before: text data bss dec hex filename 26360 1072 24 27456 6b40 drivers/platform/x86/toshiba_acpi.o File size After adding 'const': text data bss dec hex filename 26424 1008 24 27456 6b40 drivers/platform/x86/toshiba_acpi.o Signed-off-by: Arvind Yadav Signed-off-by: Darren Hart (VMware) --- drivers/platform/x86/toshiba_acpi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c index 88f9f79a7cf6..bb1dcd7fbdeb 100644 --- a/drivers/platform/x86/toshiba_acpi.c +++ b/drivers/platform/x86/toshiba_acpi.c @@ -2419,7 +2419,7 @@ static umode_t toshiba_sysfs_is_visible(struct kobject *kobj, return exists ? attr->mode : 0; } -static struct attribute_group toshiba_attr_group = { +static const struct attribute_group toshiba_attr_group = { .is_visible = toshiba_sysfs_is_visible, .attrs = toshiba_attributes, }; -- cgit v1.2.3-59-g8ed1b From b3743c71b7c33a126d6d8942bb268775987400ec Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Tue, 11 Jul 2017 17:59:43 +0800 Subject: tcmu: Fix possbile memory leak / OOPs when recalculating cmd base size For all the entries allocated from the ring cmd area, the memory is something like the stack memory, which will always reserve the old data, so the entry->req.iov_bidi_cnt maybe none zero. On some environments, the crash could be reproduce very easy and some not. The following is the crash core trace as reported by Damien: [ 240.143969] CPU: 0 PID: 1285 Comm: iscsi_trx Not tainted 4.12.0-rc1+ #3 [ 240.150607] Hardware name: ASUS All Series/H87-PRO, BIOS 2104 10/28/2014 [ 240.157331] task: ffff8807de4f5800 task.stack: ffffc900047dc000 [ 240.163270] RIP: 0010:memcpy_erms+0x6/0x10 [ 240.167377] RSP: 0018:ffffc900047dfc68 EFLAGS: 00010202 [ 240.172621] RAX: ffffc9065db85540 RBX: ffff8807f7980000 RCX: 0000000000000010 [ 240.179771] RDX: 0000000000000010 RSI: ffff8807de574fe0 RDI: ffffc9065db85540 [ 240.186930] RBP: ffffc900047dfd30 R08: ffff8807de41b000 R09: 0000000000000000 [ 240.194088] R10: 0000000000000040 R11: ffff8807e9b726f0 R12: 00000006565726b0 [ 240.201246] R13: ffffc90007612ea0 R14: 000000065657d540 R15: 0000000000000000 [ 240.208397] FS: 0000000000000000(0000) GS:ffff88081fa00000(0000) knlGS:0000000000000000 [ 240.216510] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 240.222280] CR2: ffffc9065db85540 CR3: 0000000001c0f000 CR4: 00000000001406f0 [ 240.229430] Call Trace: [ 240.231887] ? tcmu_queue_cmd+0x83c/0xa80 [ 240.235916] ? target_check_reservation+0xcd/0x6f0 [ 240.240725] __target_execute_cmd+0x27/0xa0 [ 240.244918] target_execute_cmd+0x232/0x2c0 [ 240.249124] ? __local_bh_enable_ip+0x64/0xa0 [ 240.253499] iscsit_execute_cmd+0x20d/0x270 [ 240.257693] iscsit_sequence_cmd+0x110/0x190 [ 240.261985] iscsit_get_rx_pdu+0x360/0xc80 [ 240.267565] ? iscsi_target_rx_thread+0x54/0xd0 [ 240.273571] iscsi_target_rx_thread+0x9a/0xd0 [ 240.279413] kthread+0x113/0x150 [ 240.284120] ? iscsi_target_tx_thread+0x1e0/0x1e0 [ 240.290297] ? kthread_create_on_node+0x40/0x40 [ 240.296297] ret_from_fork+0x2e/0x40 [ 240.301332] Code: 90 90 90 90 90 eb 1e 0f 1f 00 48 89 f8 48 89 d1 48 c1 e9 03 83 e2 07 f3 48 a5 89 d1 f3 a4 c3 66 0f 1f 44 00 00 48 89 f8 48 89 d1 a4 c3 0f 1f 80 00 00 00 00 48 89 f8 48 83 fa 20 72 7e 40 38 [ 240.321751] RIP: memcpy_erms+0x6/0x10 RSP: ffffc900047dfc68 [ 240.328838] CR2: ffffc9065db85540 [ 240.333667] ---[ end trace b7e5354cfb54d08b ]--- To fix this, just memset all the entry memory before using it, and also to be more readable we adjust the bidi code. Fixed: fe25cc34795(tcmu: Recalculate the tcmu_cmd size to save cmd area memories) Reported-by: Bryant G. Ly Tested-by: Bryant G. Ly Reported-by: Damien Le Moal Tested-by: Damien Le Moal Reviewed-by: Mike Christie Signed-off-by: Xiubo Li Cc: # 4.12+ Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_user.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 2f1fa927682e..3b25ef3d5596 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -563,7 +563,7 @@ static int scatter_data_area(struct tcmu_dev *udev, to_offset = get_block_offset_user(udev, dbi, block_remaining); offset = DATA_BLOCK_SIZE - block_remaining; - to = (void *)(unsigned long)to + offset; + to += offset; if (*iov_cnt != 0 && to_offset == iov_tail(udev, *iov)) { @@ -636,7 +636,7 @@ static void gather_data_area(struct tcmu_dev *udev, struct tcmu_cmd *cmd, copy_bytes = min_t(size_t, sg_remaining, block_remaining); offset = DATA_BLOCK_SIZE - block_remaining; - from = (void *)(unsigned long)from + offset; + from += offset; tcmu_flush_dcache_range(from, copy_bytes); memcpy(to + sg->length - sg_remaining, from, copy_bytes); @@ -840,10 +840,9 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd) } entry = (void *) mb + CMDR_OFF + cmd_head; + memset(entry, 0, command_size); tcmu_hdr_set_op(&entry->hdr.len_op, TCMU_OP_CMD); entry->hdr.cmd_id = tcmu_cmd->cmd_id; - entry->hdr.kflags = 0; - entry->hdr.uflags = 0; /* Handle allocating space from the data area */ tcmu_cmd_reset_dbi_cur(tcmu_cmd); @@ -862,11 +861,10 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd) return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; } entry->req.iov_cnt = iov_cnt; - entry->req.iov_dif_cnt = 0; /* Handle BIDI commands */ + iov_cnt = 0; if (se_cmd->se_cmd_flags & SCF_BIDI) { - iov_cnt = 0; iov++; ret = scatter_data_area(udev, tcmu_cmd, se_cmd->t_bidi_data_sg, @@ -879,8 +877,8 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd) pr_err("tcmu: alloc and scatter bidi data failed\n"); return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; } - entry->req.iov_bidi_cnt = iov_cnt; } + entry->req.iov_bidi_cnt = iov_cnt; /* * Recalaulate the command's base size and size according -- cgit v1.2.3-59-g8ed1b From daf78c305148c5a52f75a7fd88461ffa7066aec6 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Tue, 11 Jul 2017 18:06:41 +0800 Subject: tcmu: clean up the code and with one small fix Remove useless blank line and code and at the same time add one error path to catch the errors. Reviewed-by: Mike Christie Signed-off-by: Xiubo Li Signed-off-by: Nicholas Bellinger --- drivers/target/target_core_user.c | 24 +++++++++++------------- 1 file changed, 11 insertions(+), 13 deletions(-) diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 3b25ef3d5596..80ee130f8253 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -342,7 +342,6 @@ static inline bool tcmu_get_empty_block(struct tcmu_dev *udev, page = radix_tree_lookup(&udev->data_blocks, dbi); if (!page) { - if (atomic_add_return(1, &global_db_count) > TCMU_GLOBAL_MAX_BLOCKS) { atomic_dec(&global_db_count); @@ -352,14 +351,11 @@ static inline bool tcmu_get_empty_block(struct tcmu_dev *udev, /* try to get new page from the mm */ page = alloc_page(GFP_KERNEL); if (!page) - return false; + goto err_alloc; ret = radix_tree_insert(&udev->data_blocks, dbi, page); - if (ret) { - __free_page(page); - return false; - } - + if (ret) + goto err_insert; } if (dbi > udev->dbi_max) @@ -369,6 +365,11 @@ static inline bool tcmu_get_empty_block(struct tcmu_dev *udev, tcmu_cmd_set_dbi(tcmu_cmd, dbi); return true; +err_insert: + __free_page(page); +err_alloc: + atomic_dec(&global_db_count); + return false; } static bool tcmu_get_empty_blocks(struct tcmu_dev *udev, @@ -527,7 +528,7 @@ static inline size_t get_block_offset_user(struct tcmu_dev *dev, DATA_BLOCK_SIZE - remaining; } -static inline size_t iov_tail(struct tcmu_dev *udev, struct iovec *iov) +static inline size_t iov_tail(struct iovec *iov) { return (size_t)iov->iov_base + iov->iov_len; } @@ -566,7 +567,7 @@ static int scatter_data_area(struct tcmu_dev *udev, to += offset; if (*iov_cnt != 0 && - to_offset == iov_tail(udev, *iov)) { + to_offset == iov_tail(*iov)) { (*iov)->iov_len += copy_bytes; } else { new_iov(iov, iov_cnt, udev); @@ -722,10 +723,7 @@ static bool is_ring_space_avail(struct tcmu_dev *udev, struct tcmu_cmd *cmd, } } - if (!tcmu_get_empty_blocks(udev, cmd)) - return false; - - return true; + return tcmu_get_empty_blocks(udev, cmd); } static inline size_t tcmu_cmd_get_base_cmd_size(size_t iov_cnt) -- cgit v1.2.3-59-g8ed1b From 55dd8cf2163e1866d9497c4f361d6ed42b3a192b Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Tue, 11 Jul 2017 10:50:00 -0700 Subject: Revert "qla2xxx: Fix incorrect tcm_qla2xxx_free_cmd use during TMR ABORT" This reverts commit 5f572526a18418258bfa137e3353656c25439500. As reported by Pascal here: http://www.spinics.net/lists/target-devel/msg15808.html there still appears to be another issue related to this change to drop the original bogus tcm_qla2xxx_free_cmd() usage from tcm_qla2xxx_handle_data_work() and tcm_qla2xxx_aborted_task(). So revert this for now, until Pascal can verify with further debug in place to understand what's going on. Reported-by: Pascal de Bruijn Cc: Pascal de Bruijn Cc: Himanshu Madhani Cc: Quinn Tran Cc: # 3.10+ Signed-off-by: Nicholas Bellinger --- drivers/scsi/qla2xxx/qla_target.c | 4 ---- drivers/scsi/qla2xxx/qla_target.h | 1 - drivers/scsi/qla2xxx/tcm_qla2xxx.c | 36 +++++++++++++++++++++++++++++++++--- 3 files changed, 33 insertions(+), 8 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 8f8ece900801..401e245477d4 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -4079,8 +4079,6 @@ static struct qla_tgt_cmd *qlt_get_tag(scsi_qla_host_t *vha, cmd = &((struct qla_tgt_cmd *)se_sess->sess_cmd_map)[tag]; memset(cmd, 0, sizeof(struct qla_tgt_cmd)); - init_completion(&cmd->write_pending_abort_comp); - memcpy(&cmd->atio, atio, sizeof(*atio)); cmd->state = QLA_TGT_STATE_NEW; cmd->tgt = vha->vha_tgt.qla_tgt; @@ -5085,8 +5083,6 @@ qlt_alloc_qfull_cmd(struct scsi_qla_host *vha, qlt_incr_num_pend_cmds(vha); INIT_LIST_HEAD(&cmd->cmd_list); - init_completion(&cmd->write_pending_abort_comp); - memcpy(&cmd->atio, atio, sizeof(*atio)); cmd->tgt = vha->vha_tgt.qla_tgt; diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h index 939e93c5d3ae..d64420251194 100644 --- a/drivers/scsi/qla2xxx/qla_target.h +++ b/drivers/scsi/qla2xxx/qla_target.h @@ -868,7 +868,6 @@ struct qla_tgt_cmd { unsigned char sense_buffer[TRANSPORT_SENSE_BUFFER]; spinlock_t cmd_lock; - struct completion write_pending_abort_comp; /* to save extra sess dereferences */ unsigned int conf_compl_supported:1; unsigned int sg_mapped:1; diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index 8c1bf9b14bb2..75aeb9fdfd06 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -415,7 +415,6 @@ static int tcm_qla2xxx_write_pending(struct se_cmd *se_cmd) static int tcm_qla2xxx_write_pending_status(struct se_cmd *se_cmd) { - struct qla_tgt_cmd *cmd = container_of(se_cmd, struct qla_tgt_cmd, se_cmd); unsigned long flags; /* * Check for WRITE_PENDING status to determine if we need to wait for @@ -425,7 +424,8 @@ static int tcm_qla2xxx_write_pending_status(struct se_cmd *se_cmd) if (se_cmd->t_state == TRANSPORT_WRITE_PENDING || se_cmd->t_state == TRANSPORT_COMPLETE_QF_WP) { spin_unlock_irqrestore(&se_cmd->t_state_lock, flags); - wait_for_completion(&cmd->write_pending_abort_comp); + wait_for_completion_timeout(&se_cmd->t_transport_stop_comp, + 50); return 0; } spin_unlock_irqrestore(&se_cmd->t_state_lock, flags); @@ -501,6 +501,7 @@ static int tcm_qla2xxx_handle_cmd(scsi_qla_host_t *vha, struct qla_tgt_cmd *cmd, static void tcm_qla2xxx_handle_data_work(struct work_struct *work) { struct qla_tgt_cmd *cmd = container_of(work, struct qla_tgt_cmd, work); + unsigned long flags; /* * Ensure that the complete FCP WRITE payload has been received. @@ -508,6 +509,17 @@ static void tcm_qla2xxx_handle_data_work(struct work_struct *work) */ cmd->cmd_in_wq = 0; + spin_lock_irqsave(&cmd->cmd_lock, flags); + cmd->data_work = 1; + if (cmd->aborted) { + cmd->data_work_free = 1; + spin_unlock_irqrestore(&cmd->cmd_lock, flags); + + tcm_qla2xxx_free_cmd(cmd); + return; + } + spin_unlock_irqrestore(&cmd->cmd_lock, flags); + cmd->vha->tgt_counters.qla_core_ret_ctio++; if (!cmd->write_data_transferred) { /* @@ -515,7 +527,7 @@ static void tcm_qla2xxx_handle_data_work(struct work_struct *work) * waiting upon completion in tcm_qla2xxx_write_pending_status() */ if (cmd->se_cmd.transport_state & CMD_T_ABORTED) { - complete(&cmd->write_pending_abort_comp); + complete(&cmd->se_cmd.t_transport_stop_comp); return; } @@ -741,13 +753,31 @@ static void tcm_qla2xxx_queue_tm_rsp(struct se_cmd *se_cmd) qlt_xmit_tm_rsp(mcmd); } +#define DATA_WORK_NOT_FREE(_cmd) (_cmd->data_work && !_cmd->data_work_free) static void tcm_qla2xxx_aborted_task(struct se_cmd *se_cmd) { struct qla_tgt_cmd *cmd = container_of(se_cmd, struct qla_tgt_cmd, se_cmd); + unsigned long flags; if (qlt_abort_cmd(cmd)) return; + + spin_lock_irqsave(&cmd->cmd_lock, flags); + if ((cmd->state == QLA_TGT_STATE_NEW)|| + ((cmd->state == QLA_TGT_STATE_DATA_IN) && + DATA_WORK_NOT_FREE(cmd))) { + cmd->data_work_free = 1; + spin_unlock_irqrestore(&cmd->cmd_lock, flags); + /* + * cmd has not reached fw, Use this trigger to free it. + */ + tcm_qla2xxx_free_cmd(cmd); + return; + } + spin_unlock_irqrestore(&cmd->cmd_lock, flags); + return; + } static void tcm_qla2xxx_clear_sess_lookup(struct tcm_qla2xxx_lport *, -- cgit v1.2.3-59-g8ed1b From 138d351eefb727ab9e41a3dc5f112ceb4f6e59f2 Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Fri, 7 Jul 2017 14:45:49 -0700 Subject: iscsi-target: Add login_keys_workaround attribute for non RFC initiators This patch re-introduces part of a long standing login workaround that was recently dropped by: commit 1c99de981f30b3e7868b8d20ce5479fa1c0fea46 Author: Nicholas Bellinger Date: Sun Apr 2 13:36:44 2017 -0700 iscsi-target: Drop work-around for legacy GlobalSAN initiator Namely, the workaround for FirstBurstLength ended up being required by Mellanox Flexboot PXE boot ROMs as reported by Robert. So this patch re-adds the work-around for FirstBurstLength within iscsi_check_proposer_for_optional_reply(), and makes the key optional to respond when the initiator does not propose, nor respond to it. Also as requested by Arun, this patch introduces a new TPG attribute named 'login_keys_workaround' that controls the use of both the FirstBurstLength workaround, as well as the two other existing workarounds for gPXE iSCSI boot client. By default, the workaround is enabled with login_keys_workaround=1, since Mellanox FlexBoot requires it, and Arun has verified the Qlogic MSFT initiator already proposes FirstBurstLength, so it's uneffected by this re-adding this part of the original work-around. Reported-by: Robert LeBlanc Cc: Robert LeBlanc Reviewed-by: Arun Easi Cc: # 3.1+ Signed-off-by: Nicholas Bellinger --- drivers/target/iscsi/iscsi_target_configfs.c | 2 ++ drivers/target/iscsi/iscsi_target_nego.c | 6 ++-- drivers/target/iscsi/iscsi_target_parameters.c | 41 ++++++++++++++++++-------- drivers/target/iscsi/iscsi_target_parameters.h | 2 +- drivers/target/iscsi/iscsi_target_tpg.c | 19 ++++++++++++ drivers/target/iscsi/iscsi_target_tpg.h | 1 + include/target/iscsi/iscsi_target_core.h | 9 ++++++ 7 files changed, 64 insertions(+), 16 deletions(-) diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index 535a8e06a401..0dd4c45f7575 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -781,6 +781,7 @@ DEF_TPG_ATTRIB(default_erl); DEF_TPG_ATTRIB(t10_pi); DEF_TPG_ATTRIB(fabric_prot_type); DEF_TPG_ATTRIB(tpg_enabled_sendtargets); +DEF_TPG_ATTRIB(login_keys_workaround); static struct configfs_attribute *lio_target_tpg_attrib_attrs[] = { &iscsi_tpg_attrib_attr_authentication, @@ -796,6 +797,7 @@ static struct configfs_attribute *lio_target_tpg_attrib_attrs[] = { &iscsi_tpg_attrib_attr_t10_pi, &iscsi_tpg_attrib_attr_fabric_prot_type, &iscsi_tpg_attrib_attr_tpg_enabled_sendtargets, + &iscsi_tpg_attrib_attr_login_keys_workaround, NULL, }; diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c index 96df63f1f795..7a6751fecd32 100644 --- a/drivers/target/iscsi/iscsi_target_nego.c +++ b/drivers/target/iscsi/iscsi_target_nego.c @@ -864,7 +864,8 @@ static int iscsi_target_handle_csg_zero( SENDER_TARGET, login->rsp_buf, &login->rsp_length, - conn->param_list); + conn->param_list, + conn->tpg->tpg_attrib.login_keys_workaround); if (ret < 0) return -1; @@ -934,7 +935,8 @@ static int iscsi_target_handle_csg_one(struct iscsi_conn *conn, struct iscsi_log SENDER_TARGET, login->rsp_buf, &login->rsp_length, - conn->param_list); + conn->param_list, + conn->tpg->tpg_attrib.login_keys_workaround); if (ret < 0) { iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_INITIATOR_ERR, ISCSI_LOGIN_STATUS_INIT_ERR); diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c index fce627628200..caab1045742d 100644 --- a/drivers/target/iscsi/iscsi_target_parameters.c +++ b/drivers/target/iscsi/iscsi_target_parameters.c @@ -765,7 +765,8 @@ static int iscsi_check_for_auth_key(char *key) return 0; } -static void iscsi_check_proposer_for_optional_reply(struct iscsi_param *param) +static void iscsi_check_proposer_for_optional_reply(struct iscsi_param *param, + bool keys_workaround) { if (IS_TYPE_BOOL_AND(param)) { if (!strcmp(param->value, NO)) @@ -773,19 +774,31 @@ static void iscsi_check_proposer_for_optional_reply(struct iscsi_param *param) } else if (IS_TYPE_BOOL_OR(param)) { if (!strcmp(param->value, YES)) SET_PSTATE_REPLY_OPTIONAL(param); - /* - * Required for gPXE iSCSI boot client - */ - if (!strcmp(param->name, IMMEDIATEDATA)) - SET_PSTATE_REPLY_OPTIONAL(param); + + if (keys_workaround) { + /* + * Required for gPXE iSCSI boot client + */ + if (!strcmp(param->name, IMMEDIATEDATA)) + SET_PSTATE_REPLY_OPTIONAL(param); + } } else if (IS_TYPE_NUMBER(param)) { if (!strcmp(param->name, MAXRECVDATASEGMENTLENGTH)) SET_PSTATE_REPLY_OPTIONAL(param); - /* - * Required for gPXE iSCSI boot client - */ - if (!strcmp(param->name, MAXCONNECTIONS)) - SET_PSTATE_REPLY_OPTIONAL(param); + + if (keys_workaround) { + /* + * Required for Mellanox Flexboot PXE boot ROM + */ + if (!strcmp(param->name, FIRSTBURSTLENGTH)) + SET_PSTATE_REPLY_OPTIONAL(param); + + /* + * Required for gPXE iSCSI boot client + */ + if (!strcmp(param->name, MAXCONNECTIONS)) + SET_PSTATE_REPLY_OPTIONAL(param); + } } else if (IS_PHASE_DECLARATIVE(param)) SET_PSTATE_REPLY_OPTIONAL(param); } @@ -1422,7 +1435,8 @@ int iscsi_encode_text_output( u8 sender, char *textbuf, u32 *length, - struct iscsi_param_list *param_list) + struct iscsi_param_list *param_list, + bool keys_workaround) { char *output_buf = NULL; struct iscsi_extra_response *er; @@ -1458,7 +1472,8 @@ int iscsi_encode_text_output( *length += 1; output_buf = textbuf + *length; SET_PSTATE_PROPOSER(param); - iscsi_check_proposer_for_optional_reply(param); + iscsi_check_proposer_for_optional_reply(param, + keys_workaround); pr_debug("Sending key: %s=%s\n", param->name, param->value); } diff --git a/drivers/target/iscsi/iscsi_target_parameters.h b/drivers/target/iscsi/iscsi_target_parameters.h index 9962ccf0ccd7..c47b73f57528 100644 --- a/drivers/target/iscsi/iscsi_target_parameters.h +++ b/drivers/target/iscsi/iscsi_target_parameters.h @@ -46,7 +46,7 @@ extern int iscsi_extract_key_value(char *, char **, char **); extern int iscsi_update_param_value(struct iscsi_param *, char *); extern int iscsi_decode_text_input(u8, u8, char *, u32, struct iscsi_conn *); extern int iscsi_encode_text_output(u8, u8, char *, u32 *, - struct iscsi_param_list *); + struct iscsi_param_list *, bool); extern int iscsi_check_negotiated_keys(struct iscsi_param_list *); extern void iscsi_set_connection_parameters(struct iscsi_conn_ops *, struct iscsi_param_list *); diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c index abaabbaebd88..594d07a1e995 100644 --- a/drivers/target/iscsi/iscsi_target_tpg.c +++ b/drivers/target/iscsi/iscsi_target_tpg.c @@ -227,6 +227,7 @@ static void iscsit_set_default_tpg_attribs(struct iscsi_portal_group *tpg) a->t10_pi = TA_DEFAULT_T10_PI; a->fabric_prot_type = TA_DEFAULT_FABRIC_PROT_TYPE; a->tpg_enabled_sendtargets = TA_DEFAULT_TPG_ENABLED_SENDTARGETS; + a->login_keys_workaround = TA_DEFAULT_LOGIN_KEYS_WORKAROUND; } int iscsit_tpg_add_portal_group(struct iscsi_tiqn *tiqn, struct iscsi_portal_group *tpg) @@ -895,3 +896,21 @@ int iscsit_ta_tpg_enabled_sendtargets( return 0; } + +int iscsit_ta_login_keys_workaround( + struct iscsi_portal_group *tpg, + u32 flag) +{ + struct iscsi_tpg_attrib *a = &tpg->tpg_attrib; + + if ((flag != 0) && (flag != 1)) { + pr_err("Illegal value %d\n", flag); + return -EINVAL; + } + + a->login_keys_workaround = flag; + pr_debug("iSCSI_TPG[%hu] - TPG enabled bit for login keys workaround: %s ", + tpg->tpgt, (a->login_keys_workaround) ? "ON" : "OFF"); + + return 0; +} diff --git a/drivers/target/iscsi/iscsi_target_tpg.h b/drivers/target/iscsi/iscsi_target_tpg.h index ceba29851167..59fd3cabe89d 100644 --- a/drivers/target/iscsi/iscsi_target_tpg.h +++ b/drivers/target/iscsi/iscsi_target_tpg.h @@ -48,5 +48,6 @@ extern int iscsit_ta_default_erl(struct iscsi_portal_group *, u32); extern int iscsit_ta_t10_pi(struct iscsi_portal_group *, u32); extern int iscsit_ta_fabric_prot_type(struct iscsi_portal_group *, u32); extern int iscsit_ta_tpg_enabled_sendtargets(struct iscsi_portal_group *, u32); +extern int iscsit_ta_login_keys_workaround(struct iscsi_portal_group *, u32); #endif /* ISCSI_TARGET_TPG_H */ diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index 7948fc68286b..0ca1fb08805b 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -66,6 +66,14 @@ struct sock; #define TA_DEFAULT_FABRIC_PROT_TYPE 0 /* TPG status needs to be enabled to return sendtargets discovery endpoint info */ #define TA_DEFAULT_TPG_ENABLED_SENDTARGETS 1 +/* + * Used to control the sending of keys with optional to respond state bit, + * as a workaround for non RFC compliant initiators,that do not propose, + * nor respond to specific keys required for login to complete. + * + * See iscsi_check_proposer_for_optional_reply() for more details. + */ +#define TA_DEFAULT_LOGIN_KEYS_WORKAROUND 1 #define ISCSI_IOV_DATA_BUFFER 5 @@ -768,6 +776,7 @@ struct iscsi_tpg_attrib { u8 t10_pi; u32 fabric_prot_type; u32 tpg_enabled_sendtargets; + u32 login_keys_workaround; struct iscsi_portal_group *tpg; }; -- cgit v1.2.3-59-g8ed1b From dea1d0f5f1284e3defee4b8484d9fc230686cd42 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 11 Jul 2017 22:06:24 +0200 Subject: smp/hotplug: Replace BUG_ON and react useful The move of the unpark functions to the control thread moved the BUG_ON() there as well. While it made some sense in the idle thread of the upcoming CPU, it's bogus to crash the control thread on the already online CPU, especially as the function has a return value and the callsite is prepared to handle an error return. Replace it with a WARN_ON_ONCE() and return a proper error code. Fixes: 9cd4f1a4e7a8 ("smp/hotplug: Move unparking of percpu threads to the control CPU") Rightfully-ranted-at-by: Linux Torvalds Signed-off-by: Thomas Gleixner --- kernel/cpu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/cpu.c b/kernel/cpu.c index ab860453841d..eee033134262 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -279,7 +279,8 @@ static int bringup_wait_for_ap(unsigned int cpu) /* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */ wait_for_completion(&st->done); - BUG_ON(!cpu_online(cpu)); + if (WARN_ON_ONCE((!cpu_online(cpu)))) + return -ECANCELED; /* Unpark the stopper thread and the hotplug thread of the target cpu */ stop_machine_unpark(cpu); -- cgit v1.2.3-59-g8ed1b From b11fb73743fc406204e0749ead18560aeda8b136 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 11 Jul 2017 15:43:24 -0400 Subject: tracing: Fixup trace file header alignment The addition of TGID to the tracing header added a check to see if TGID shoudl be displayed or not, and updated the header accordingly. Unfortunately, it broke the default header. Also add constant strings to use for spacing. This does remove the visibility of the header a bit, but cuts it down from the extended lines much greater than 80 characters. Before this change: # tracer: function # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # ||| / delay # TASK-PID CPU#|||| TIMESTAMP FUNCTION # | | | |||| | | swapper/0-1 [000] .... 0.277830: migration_init <-do_one_initcall swapper/0-1 [002] d... 13.861967: Unknown type 1201 swapper/0-1 [002] d..1 13.861970: Unknown type 1202 After this change: # tracer: function # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # ||| / delay # TASK-PID CPU# |||| TIMESTAMP FUNCTION # | | | |||| | | swapper/0-1 [000] .... 0.278245: migration_init <-do_one_initcall swapper/0-1 [003] d... 13.861189: Unknown type 1201 swapper/0-1 [003] d..1 13.861192: Unknown type 1202 Cc: Joel Fernandes Fixes: 441dae8f2f29 ("tracing: Add support for display of tgid in trace output") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 92af8fd1429b..dabd810a10cd 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3358,14 +3358,23 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file unsigned int flags) { bool tgid = flags & TRACE_ITER_RECORD_TGID; - - seq_printf(m, "# %s _-----=> irqs-off\n", tgid ? " " : ""); - seq_printf(m, "# %s / _----=> need-resched\n", tgid ? " " : ""); - seq_printf(m, "# %s| / _---=> hardirq/softirq\n", tgid ? " " : ""); - seq_printf(m, "# %s|| / _--=> preempt-depth\n", tgid ? " " : ""); - seq_printf(m, "# %s||| / delay\n", tgid ? " " : ""); - seq_printf(m, "# TASK-PID CPU#%s|||| TIMESTAMP FUNCTION\n", tgid ? " TGID " : ""); - seq_printf(m, "# | | | %s|||| | |\n", tgid ? " | " : ""); + const char tgid_space[] = " "; + const char space[] = " "; + + seq_printf(m, "# %s _-----=> irqs-off\n", + tgid ? tgid_space : space); + seq_printf(m, "# %s / _----=> need-resched\n", + tgid ? tgid_space : space); + seq_printf(m, "# %s| / _---=> hardirq/softirq\n", + tgid ? tgid_space : space); + seq_printf(m, "# %s|| / _--=> preempt-depth\n", + tgid ? tgid_space : space); + seq_printf(m, "# %s||| / delay\n", + tgid ? tgid_space : space); + seq_printf(m, "# TASK-PID CPU#%s|||| TIMESTAMP FUNCTION\n", + tgid ? " TGID " : space); + seq_printf(m, "# | | | %s|||| | |\n", + tgid ? " | " : space); } void -- cgit v1.2.3-59-g8ed1b From dc8d387210e3e2ab294031e8f6542329bc9141c4 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 11 Jul 2017 18:41:12 -0400 Subject: tracing: Update Documentation/trace/ftrace.txt The documentation of ftrace.txt has become rather outdated. Bring it closer to reality of todays kernel. Signed-off-by: Steven Rostedt (VMware) --- Documentation/trace/ftrace.txt | 508 ++++++++++++++++++++++++++++++++--------- 1 file changed, 396 insertions(+), 112 deletions(-) diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt index 94a987bd2bc5..a0bbf5fabe98 100644 --- a/Documentation/trace/ftrace.txt +++ b/Documentation/trace/ftrace.txt @@ -5,10 +5,11 @@ Copyright 2008 Red Hat Inc. Author: Steven Rostedt License: The GNU Free Documentation License, Version 1.2 (dual licensed under the GPL v2) -Reviewers: Elias Oltmanns, Randy Dunlap, Andrew Morton, - John Kacur, and David Teigland. +Original Reviewers: Elias Oltmanns, Randy Dunlap, Andrew Morton, + John Kacur, and David Teigland. Written for: 2.6.28-rc2 Updated for: 3.10 +Updated for: 4.13 - Copyright 2017 VMware Inc. Steven Rostedt Introduction ------------ @@ -26,9 +27,11 @@ a task is woken to the task is actually scheduled in. One of the most common uses of ftrace is the event tracing. Through out the kernel is hundreds of static event points that -can be enabled via the debugfs file system to see what is +can be enabled via the tracefs file system to see what is going on in certain parts of the kernel. +See events.txt for more information. + Implementation Details ---------------------- @@ -39,34 +42,47 @@ See ftrace-design.txt for details for arch porters and such. The File System --------------- -Ftrace uses the debugfs file system to hold the control files as +Ftrace uses the tracefs file system to hold the control files as well as the files to display output. -When debugfs is configured into the kernel (which selecting any ftrace -option will do) the directory /sys/kernel/debug will be created. To mount +When tracefs is configured into the kernel (which selecting any ftrace +option will do) the directory /sys/kernel/tracing will be created. To mount this directory, you can add to your /etc/fstab file: - debugfs /sys/kernel/debug debugfs defaults 0 0 + tracefs /sys/kernel/tracing tracefs defaults 0 0 Or you can mount it at run time with: - mount -t debugfs nodev /sys/kernel/debug + mount -t tracefs nodev /sys/kernel/tracing For quicker access to that directory you may want to make a soft link to it: - ln -s /sys/kernel/debug /debug + ln -s /sys/kernel/tracing /tracing + + *** NOTICE *** + +Before 4.1, all ftrace tracing control files were within the debugfs +file system, which is typically located at /sys/kernel/debug/tracing. +For backward compatibility, when mounting the debugfs file system, +the tracefs file system will be automatically mounted at: + + /sys/kernel/debug/tracing -Any selected ftrace option will also create a directory called tracing -within the debugfs. The rest of the document will assume that you are in -the ftrace directory (cd /sys/kernel/debug/tracing) and will only concentrate -on the files within that directory and not distract from the content with -the extended "/sys/kernel/debug/tracing" path name. +All files located in the tracefs file system will be located in that +debugfs file system directory as well. + + *** NOTICE *** + +Any selected ftrace option will also create the tracefs file system. +The rest of the document will assume that you are in the ftrace directory +(cd /sys/kernel/tracing) and will only concentrate on the files within that +directory and not distract from the content with the extended +"/sys/kernel/tracing" path name. That's it! (assuming that you have ftrace configured into your kernel) -After mounting debugfs, you can see a directory called -"tracing". This directory contains the control and output files +After mounting tracefs you will have access to the control and output files of ftrace. Here is a list of some of the key files: @@ -92,10 +108,20 @@ of ftrace. Here is a list of some of the key files: writing to the ring buffer, the tracing overhead may still be occurring. + The kernel function tracing_off() can be used within the + kernel to disable writing to the ring buffer, which will + set this file to "0". User space can re-enable tracing by + echoing "1" into the file. + + Note, the function and event trigger "traceoff" will also + set this file to zero and stop tracing. Which can also + be re-enabled by user space using this file. + trace: This file holds the output of the trace in a human - readable format (described below). + readable format (described below). Note, tracing is temporarily + disabled while this file is being read (opened). trace_pipe: @@ -109,7 +135,8 @@ of ftrace. Here is a list of some of the key files: will not be read again with a sequential read. The "trace" file is static, and if the tracer is not adding more data, it will display the same - information every time it is read. + information every time it is read. This file will not + disable tracing while being read. trace_options: @@ -128,12 +155,14 @@ of ftrace. Here is a list of some of the key files: tracing_max_latency: Some of the tracers record the max latency. - For example, the time interrupts are disabled. - This time is saved in this file. The max trace - will also be stored, and displayed by "trace". - A new max trace will only be recorded if the - latency is greater than the value in this - file. (in microseconds) + For example, the maximum time that interrupts are disabled. + The maximum time is saved in this file. The max trace will also be + stored, and displayed by "trace". A new max trace will only be + recorded if the latency is greater than the value in this file + (in microseconds). + + By echoing in a time into this file, no latency will be recorded + unless it is greater than the time in this file. tracing_thresh: @@ -152,32 +181,34 @@ of ftrace. Here is a list of some of the key files: that the kernel uses for allocation, usually 4 KB in size). If the last page allocated has room for more bytes than requested, the rest of the page will be used, - making the actual allocation bigger than requested. + making the actual allocation bigger than requested or shown. ( Note, the size may not be a multiple of the page size due to buffer management meta-data. ) + Buffer sizes for individual CPUs may vary + (see "per_cpu/cpu0/buffer_size_kb" below), and if they do + this file will show "X". + buffer_total_size_kb: This displays the total combined size of all the trace buffers. free_buffer: - If a process is performing the tracing, and the ring buffer - should be shrunk "freed" when the process is finished, even - if it were to be killed by a signal, this file can be used - for that purpose. On close of this file, the ring buffer will - be resized to its minimum size. Having a process that is tracing - also open this file, when the process exits its file descriptor - for this file will be closed, and in doing so, the ring buffer - will be "freed". + If a process is performing tracing, and the ring buffer should be + shrunk "freed" when the process is finished, even if it were to be + killed by a signal, this file can be used for that purpose. On close + of this file, the ring buffer will be resized to its minimum size. + Having a process that is tracing also open this file, when the process + exits its file descriptor for this file will be closed, and in doing so, + the ring buffer will be "freed". It may also stop tracing if disable_on_free option is set. tracing_cpumask: - This is a mask that lets the user only trace - on specified CPUs. The format is a hex string - representing the CPUs. + This is a mask that lets the user only trace on specified CPUs. + The format is a hex string representing the CPUs. set_ftrace_filter: @@ -190,6 +221,9 @@ of ftrace. Here is a list of some of the key files: to be traced. Echoing names of functions into this file will limit the trace to only those functions. + The functions listed in "available_filter_functions" are what + can be written into this file. + This interface also allows for commands to be used. See the "Filter commands" section for more details. @@ -202,7 +236,14 @@ of ftrace. Here is a list of some of the key files: set_ftrace_pid: - Have the function tracer only trace a single thread. + Have the function tracer only trace the threads whose PID are + listed in this file. + + If the "function-fork" option is set, then when a task whose + PID is listed in this file forks, the child's PID will + automatically be added to this file, and the child will be + traced by the function tracer as well. This option will also + cause PIDs of tasks that exit to be removed from the file. set_event_pid: @@ -217,17 +258,28 @@ of ftrace. Here is a list of some of the key files: set_graph_function: - Set a "trigger" function where tracing should start - with the function graph tracer (See the section - "dynamic ftrace" for more details). + Functions listed in this file will cause the function graph + tracer to only trace these functions and the functions that + they call. (See the section "dynamic ftrace" for more details). + + set_graph_notrace: + + Similar to set_graph_function, but will disable function graph + tracing when the function is hit until it exits the function. + This makes it possible to ignore tracing functions that are called + by a specific function. available_filter_functions: - This lists the functions that ftrace - has processed and can trace. These are the function - names that you can pass to "set_ftrace_filter" or - "set_ftrace_notrace". (See the section "dynamic ftrace" - below for more details.) + This lists the functions that ftrace has processed and can trace. + These are the function names that you can pass to + "set_ftrace_filter" or "set_ftrace_notrace". + (See the section "dynamic ftrace" below for more details.) + + dyn_ftrace_total_info: + + This file is for debugging purposes. The number of functions that + have been converted to nops and are available to be traced. enabled_functions: @@ -250,12 +302,21 @@ of ftrace. Here is a list of some of the key files: an 'I' will be displayed on the same line as the function that can be overridden. + If the architecture supports it, it will also show what callback + is being directly called by the function. If the count is greater + than 1 it most likely will be ftrace_ops_list_func(). + + If the callback of the function jumps to a trampoline that is + specific to a the callback and not the standard trampoline, + its address will be printed as well as the function that the + trampoline calls. + function_profile_enabled: When set it will enable all functions with either the function - tracer, or if enabled, the function graph tracer. It will + tracer, or if configured, the function graph tracer. It will keep a histogram of the number of functions that were called - and if run with the function graph tracer, it will also keep + and if the function graph tracer was configured, it will also keep track of the time spent in those functions. The histogram content can be displayed in the files: @@ -283,12 +344,11 @@ of ftrace. Here is a list of some of the key files: printk_formats: This is for tools that read the raw format files. If an event in - the ring buffer references a string (currently only trace_printk() - does this), only a pointer to the string is recorded into the buffer - and not the string itself. This prevents tools from knowing what - that string was. This file displays the string and address for - the string allowing tools to map the pointers to what the - strings were. + the ring buffer references a string, only a pointer to the string + is recorded into the buffer and not the string itself. This prevents + tools from knowing what that string was. This file displays the string + and address for the string allowing tools to map the pointers to what + the strings were. saved_cmdlines: @@ -298,6 +358,22 @@ of ftrace. Here is a list of some of the key files: comms for events. If a pid for a comm is not listed, then "<...>" is displayed in the output. + If the option "record-cmd" is set to "0", then comms of tasks + will not be saved during recording. By default, it is enabled. + + saved_cmdlines_size: + + By default, 128 comms are saved (see "saved_cmdlines" above). To + increase or decrease the amount of comms that are cached, echo + in a the number of comms to cache, into this file. + + saved_tgids: + + If the option "record-tgid" is set, on each scheduling context switch + the Task Group ID of a task is saved in a table mapping the PID of + the thread to its TGID. By default, the "record-tgid" option is + disabled. + snapshot: This displays the "snapshot" buffer and also lets the user @@ -336,6 +412,9 @@ of ftrace. Here is a list of some of the key files: # cat trace_clock [local] global counter x86-tsc + The clock with the square brackets around it is the one + in effect. + local: Default clock, but may not be in sync across CPUs global: This clock is in sync with all CPUs but may @@ -448,6 +527,23 @@ of ftrace. Here is a list of some of the key files: See events.txt for more information. + set_event: + + By echoing in the event into this file, will enable that event. + + See events.txt for more information. + + available_events: + + A list of events that can be enabled in tracing. + + See events.txt for more information. + + hwlat_detector: + + Directory for the Hardware Latency Detector. + See "Hardware Latency Detector" section below. + per_cpu: This is a directory that contains the trace per_cpu information. @@ -539,13 +635,25 @@ Here is the list of current tracers that may be configured. to draw a graph of function calls similar to C code source. + "blk" + + The block tracer. The tracer used by the blktrace user + application. + + "hwlat" + + The Hardware Latency tracer is used to detect if the hardware + produces any latency. See "Hardware Latency Detector" section + below. + "irqsoff" Traces the areas that disable interrupts and saves the trace with the longest max latency. See tracing_max_latency. When a new max is recorded, it replaces the old trace. It is best to view this - trace with the latency-format option enabled. + trace with the latency-format option enabled, which + happens automatically when the tracer is selected. "preemptoff" @@ -571,6 +679,26 @@ Here is the list of current tracers that may be configured. RT tasks (as the current "wakeup" does). This is useful for those interested in wake up timings of RT tasks. + "wakeup_dl" + + Traces and records the max latency that it takes for + a SCHED_DEADLINE task to be woken (as the "wakeup" and + "wakeup_rt" does). + + "mmiotrace" + + A special tracer that is used to trace binary module. + It will trace all the calls that a module makes to the + hardware. Everything it writes and reads from the I/O + as well. + + "branch" + + This tracer can be configured when tracing likely/unlikely + calls within the kernel. It will trace when a likely and + unlikely branch is hit and if it was correct in its prediction + of being correct. + "nop" This is the "trace nothing" tracer. To remove all @@ -582,7 +710,7 @@ Examples of using the tracer ---------------------------- Here are typical examples of using the tracers when controlling -them only with the debugfs interface (without using any +them only with the tracefs interface (without using any user-land utilities). Output format: @@ -674,7 +802,7 @@ why a latency happened. Here is a typical trace. This shows that the current tracer is "irqsoff" tracing the time for which interrupts were disabled. It gives the trace version (which never changes) and the version of the kernel upon which this was executed on -(3.10). Then it displays the max latency in microseconds (259 us). The number +(3.8). Then it displays the max latency in microseconds (259 us). The number of trace entries displayed and the total number (both are four: #4/4). VP, KP, SP, and HP are always zero and are reserved for later use. #P is the number of online CPUs (#P:4). @@ -709,6 +837,8 @@ explains which is which. '.' otherwise. hardirq/softirq: + 'Z' - NMI occurred inside a hardirq + 'z' - NMI is running 'H' - hard irq occurred inside a softirq. 'h' - hard irq is running 's' - soft irq is running @@ -757,24 +887,24 @@ nohex nobin noblock trace_printk -nobranch annotate nouserstacktrace nosym-userobj noprintk-msg-only context-info nolatency-format -sleep-time -graph-time record-cmd +norecord-tgid overwrite nodisable_on_free irq-info markers noevent-fork function-trace +nofunction-fork nodisplay-graph nostacktrace +nobranch To disable one of the options, echo in the option prepended with "no". @@ -830,8 +960,6 @@ Here are the available options: trace_printk - Can disable trace_printk() from writing into the buffer. - branch - Enable branch tracing with the tracer. - annotate - It is sometimes confusing when the CPU buffers are full and one CPU buffer had a lot of events recently, thus a shorter time frame, were another CPU may have only had @@ -850,7 +978,8 @@ Here are the available options: -0 [001] .Ns3 21169.031485: sub_preempt_count <-_raw_spin_unlock userstacktrace - This option changes the trace. It records a - stacktrace of the current userspace thread. + stacktrace of the current user space thread after + each trace event. sym-userobj - when user stacktrace are enabled, look up which object the address belongs to, and print a @@ -873,29 +1002,21 @@ x494] <- /root/a.out[+0x4a8] <- /lib/libc-2.7.so[+0x1e1a6] context-info - Show only the event data. Hides the comm, PID, timestamp, CPU, and other useful data. - latency-format - This option changes the trace. When - it is enabled, the trace displays - additional information about the - latencies, as described in "Latency - trace format". - - sleep-time - When running function graph tracer, to include - the time a task schedules out in its function. - When enabled, it will account time the task has been - scheduled out as part of the function call. - - graph-time - When running function profiler with function graph tracer, - to include the time to call nested functions. When this is - not set, the time reported for the function will only - include the time the function itself executed for, not the - time for functions that it called. + latency-format - This option changes the trace output. When it is enabled, + the trace displays additional information about the + latency, as described in "Latency trace format". record-cmd - When any event or tracer is enabled, a hook is enabled - in the sched_switch trace point to fill comm cache + in the sched_switch trace point to fill comm cache with mapped pids and comms. But this may cause some overhead, and if you only care about pids, and not the name of the task, disabling this option can lower the - impact of tracing. + impact of tracing. See "saved_cmdlines". + + record-tgid - When any event or tracer is enabled, a hook is enabled + in the sched_switch trace point to fill the cache of + mapped Thread Group IDs (TGID) mapping to pids. See + "saved_tgids". overwrite - This controls what happens when the trace buffer is full. If "1" (default), the oldest events are @@ -935,19 +1056,98 @@ x494] <- /root/a.out[+0x4a8] <- /lib/libc-2.7.so[+0x1e1a6] functions. This keeps the overhead of the tracer down when performing latency tests. + function-fork - When set, tasks with PIDs listed in set_ftrace_pid will + have the PIDs of their children added to set_ftrace_pid + when those tasks fork. Also, when tasks with PIDs in + set_ftrace_pid exit, their PIDs will be removed from the + file. + display-graph - When set, the latency tracers (irqsoff, wakeup, etc) will use function graph tracing instead of function tracing. - stacktrace - This is one of the options that changes the trace - itself. When a trace is recorded, so is the stack - of functions. This allows for back traces of - trace sites. + stacktrace - When set, a stack trace is recorded after any trace event + is recorded. + + branch - Enable branch tracing with the tracer. This enables branch + tracer along with the currently set tracer. Enabling this + with the "nop" tracer is the same as just enabling the + "branch" tracer. Note: Some tracers have their own options. They only appear in this file when the tracer is active. They always appear in the options directory. +Here are the per tracer options: + +Options for function tracer: + + func_stack_trace - When set, a stack trace is recorded after every + function that is recorded. NOTE! Limit the functions + that are recorded before enabling this, with + "set_ftrace_filter" otherwise the system performance + will be critically degraded. Remember to disable + this option before clearing the function filter. + +Options for function_graph tracer: + + Since the function_graph tracer has a slightly different output + it has its own options to control what is displayed. + + funcgraph-overrun - When set, the "overrun" of the graph stack is + displayed after each function traced. The + overrun, is when the stack depth of the calls + is greater than what is reserved for each task. + Each task has a fixed array of functions to + trace in the call graph. If the depth of the + calls exceeds that, the function is not traced. + The overrun is the number of functions missed + due to exceeding this array. + + funcgraph-cpu - When set, the CPU number of the CPU where the trace + occurred is displayed. + + funcgraph-overhead - When set, if the function takes longer than + A certain amount, then a delay marker is + displayed. See "delay" above, under the + header description. + + funcgraph-proc - Unlike other tracers, the process' command line + is not displayed by default, but instead only + when a task is traced in and out during a context + switch. Enabling this options has the command + of each process displayed at every line. + + funcgraph-duration - At the end of each function (the return) + the duration of the amount of time in the + function is displayed in microseconds. + + funcgraph-abstime - When set, the timestamp is displayed at each + line. + + funcgraph-irqs - When disabled, functions that happen inside an + interrupt will not be traced. + + funcgraph-tail - When set, the return event will include the function + that it represents. By default this is off, and + only a closing curly bracket "}" is displayed for + the return of a function. + + sleep-time - When running function graph tracer, to include + the time a task schedules out in its function. + When enabled, it will account time the task has been + scheduled out as part of the function call. + + graph-time - When running function profiler with function graph tracer, + to include the time to call nested functions. When this is + not set, the time reported for the function will only + include the time the function itself executed for, not the + time for functions that it called. + +Options for blk tracer: + + blk_classic - Shows a more minimalistic output. + irqsoff ------- @@ -1711,6 +1911,85 @@ events. -0 2d..3 6us : 0:120:R ==> [002] 5882: 94:R sleep +Hardware Latency Detector +------------------------- + +The hardware latency detector is executed by enabling the "hwlat" tracer. + +NOTE, this tracer will affect the performance of the system as it will +periodically make a CPU constantly busy with interrupts disabled. + + # echo hwlat > current_tracer + # sleep 100 + # cat trace +# tracer: hwlat +# +# _-----=> irqs-off +# / _----=> need-resched +# | / _---=> hardirq/softirq +# || / _--=> preempt-depth +# ||| / delay +# TASK-PID CPU# |||| TIMESTAMP FUNCTION +# | | | |||| | | + <...>-3638 [001] d... 19452.055471: #1 inner/outer(us): 12/14 ts:1499801089.066141940 + <...>-3638 [003] d... 19454.071354: #2 inner/outer(us): 11/9 ts:1499801091.082164365 + <...>-3638 [002] dn.. 19461.126852: #3 inner/outer(us): 12/9 ts:1499801098.138150062 + <...>-3638 [001] d... 19488.340960: #4 inner/outer(us): 8/12 ts:1499801125.354139633 + <...>-3638 [003] d... 19494.388553: #5 inner/outer(us): 8/12 ts:1499801131.402150961 + <...>-3638 [003] d... 19501.283419: #6 inner/outer(us): 0/12 ts:1499801138.297435289 nmi-total:4 nmi-count:1 + + +The above output is somewhat the same in the header. All events will have +interrupts disabled 'd'. Under the FUNCTION title there is: + + #1 - This is the count of events recorded that were greater than the + tracing_threshold (See below). + + inner/outer(us): 12/14 + + This shows two numbers as "inner latency" and "outer latency". The test + runs in a loop checking a timestamp twice. The latency detected within + the two timestamps is the "inner latency" and the latency detected + after the previous timestamp and the next timestamp in the loop is + the "outer latency". + + ts:1499801089.066141940 + + The absolute timestamp that the event happened. + + nmi-total:4 nmi-count:1 + + On architectures that support it, if an NMI comes in during the + test, the time spent in NMI is reported in "nmi-total" (in + microseconds). + + All architectures that have NMIs will show the "nmi-count" if an + NMI comes in during the test. + +hwlat files: + + tracing_threshold - This gets automatically set to "10" to represent 10 + microseconds. This is the threshold of latency that + needs to be detected before the trace will be recorded. + + Note, when hwlat tracer is finished (another tracer is + written into "current_tracer"), the original value for + tracing_threshold is placed back into this file. + + hwlat_detector/width - The length of time the test runs with interrupts + disabled. + + hwlat_detector/window - The length of time of the window which the test + runs. That is, the test will run for "width" + microseconds per "window" microseconds + + tracing_cpumask - When the test is started. A kernel thread is created that + runs the test. This thread will alternate between CPUs + listed in the tracing_cpumask between each period + (one "window"). To limit the test to specific CPUs + set the mask in this file to only the CPUs that the test + should run on. + function -------- @@ -1821,15 +2100,15 @@ something like this simple program: #define STR(x) _STR(x) #define MAX_PATH 256 -const char *find_debugfs(void) +const char *find_tracefs(void) { - static char debugfs[MAX_PATH+1]; - static int debugfs_found; + static char tracefs[MAX_PATH+1]; + static int tracefs_found; char type[100]; FILE *fp; - if (debugfs_found) - return debugfs; + if (tracefs_found) + return tracefs; if ((fp = fopen("/proc/mounts","r")) == NULL) { perror("/proc/mounts"); @@ -1839,27 +2118,27 @@ const char *find_debugfs(void) while (fscanf(fp, "%*s %" STR(MAX_PATH) "s %99s %*s %*d %*d\n", - debugfs, type) == 2) { - if (strcmp(type, "debugfs") == 0) + tracefs, type) == 2) { + if (strcmp(type, "tracefs") == 0) break; } fclose(fp); - if (strcmp(type, "debugfs") != 0) { - fprintf(stderr, "debugfs not mounted"); + if (strcmp(type, "tracefs") != 0) { + fprintf(stderr, "tracefs not mounted"); return NULL; } - strcat(debugfs, "/tracing/"); - debugfs_found = 1; + strcat(tracefs, "/tracing/"); + tracefs_found = 1; - return debugfs; + return tracefs; } const char *tracing_file(const char *file_name) { static char trace_file[MAX_PATH+1]; - snprintf(trace_file, MAX_PATH, "%s/%s", find_debugfs(), file_name); + snprintf(trace_file, MAX_PATH, "%s/%s", find_tracefs(), file_name); return trace_file; } @@ -1898,12 +2177,12 @@ Or this simple script! ------ #!/bin/bash -debugfs=`sed -ne 's/^debugfs \(.*\) debugfs.*/\1/p' /proc/mounts` -echo nop > $debugfs/tracing/current_tracer -echo 0 > $debugfs/tracing/tracing_on -echo $$ > $debugfs/tracing/set_ftrace_pid -echo function > $debugfs/tracing/current_tracer -echo 1 > $debugfs/tracing/tracing_on +tracefs=`sed -ne 's/^tracefs \(.*\) tracefs.*/\1/p' /proc/mounts` +echo nop > $tracefs/tracing/current_tracer +echo 0 > $tracefs/tracing/tracing_on +echo $$ > $tracefs/tracing/set_ftrace_pid +echo function > $tracefs/tracing/current_tracer +echo 1 > $tracefs/tracing/tracing_on exec "$@" ------ @@ -2145,13 +2424,18 @@ include the -pg switch in the compiling of the kernel.) At compile time every C file object is run through the recordmcount program (located in the scripts directory). This program will parse the ELF headers in the C object to find all -the locations in the .text section that call mcount. (Note, only -white listed .text sections are processed, since processing other -sections like .init.text may cause races due to those sections -being freed unexpectedly). - -A new section called "__mcount_loc" is created that holds -references to all the mcount call sites in the .text section. +the locations in the .text section that call mcount. Starting +with gcc verson 4.6, the -mfentry has been added for x86, which +calls "__fentry__" instead of "mcount". Which is called before +the creation of the stack frame. + +Note, not all sections are traced. They may be prevented by either +a notrace, or blocked another way and all inline functions are not +traced. Check the "available_filter_functions" file to see what functions +can be traced. + +A section called "__mcount_loc" is created that holds +references to all the mcount/fentry call sites in the .text section. The recordmcount program re-links this section back into the original object. The final linking stage of the kernel will add all these references into a single table. @@ -2679,7 +2963,7 @@ in time without stopping tracing. Ftrace swaps the current buffer with a spare buffer, and tracing continues in the new current (=previous spare) buffer. -The following debugfs files in "tracing" are related to this +The following tracefs files in "tracing" are related to this feature: snapshot: @@ -2752,7 +3036,7 @@ cat: snapshot: Device or resource busy Instances --------- -In the debugfs tracing directory is a directory called "instances". +In the tracefs tracing directory is a directory called "instances". This directory can have new directories created inside of it using mkdir, and removing directories with rmdir. The directory created with mkdir in this directory will already contain files and other -- cgit v1.2.3-59-g8ed1b From bbd1d27d863d5c0acee65ecd0c2e34035e1df5ea Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 11 Jul 2017 19:21:04 -0400 Subject: tracing: Do note expose stack_trace_filter without DYNAMIC_FTRACE The "stack_trace_filter" file only makes sense if DYNAMIC_FTRACE is configured in. If it is not, then the user can not filter any functions. Not only that, the open function causes warnings when DYNAMIC_FTRACE is not set. Link: http://lkml.kernel.org/r/20170710110521.600806-1-arnd@arndb.de Reported-by: Arnd Bergmann Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_stack.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index b4a751e8f9d6..a4df67cbc711 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -406,6 +406,8 @@ static const struct file_operations stack_trace_fops = { .release = seq_release, }; +#ifdef CONFIG_DYNAMIC_FTRACE + static int stack_trace_filter_open(struct inode *inode, struct file *file) { @@ -423,6 +425,8 @@ static const struct file_operations stack_trace_filter_fops = { .release = ftrace_regex_release, }; +#endif /* CONFIG_DYNAMIC_FTRACE */ + int stack_trace_sysctl(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, @@ -477,8 +481,10 @@ static __init int stack_trace_init(void) trace_create_file("stack_trace", 0444, d_tracer, NULL, &stack_trace_fops); +#ifdef CONFIG_DYNAMIC_FTRACE trace_create_file("stack_trace_filter", 0444, d_tracer, &trace_ops, &stack_trace_filter_fops); +#endif if (stack_trace_filter_buf[0]) ftrace_set_early_filter(&trace_ops, stack_trace_filter_buf, 1); -- cgit v1.2.3-59-g8ed1b From 69449bbd65687e8e5fb968a5a0c46089f6af6001 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 10 Jul 2017 10:44:03 +0200 Subject: ftrace: Hide cached module code for !CONFIG_MODULES When modules are disabled, we get a harmless build warning: kernel/trace/ftrace.c:4051:13: error: 'process_cached_mods' defined but not used [-Werror=unused-function] This adds the same #ifdef around the new code that exists around its caller. Link: http://lkml.kernel.org/r/20170710084413.1820568-1-arnd@arndb.de Fixes: d7fbf8df7ca0 ("ftrace: Implement cached modules tracing on module load") Signed-off-by: Arnd Bergmann Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 2953d558bbee..4706f0ed193e 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3978,6 +3978,7 @@ static int ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, int reset, int enable); +#ifdef CONFIG_MODULES static void process_mod_list(struct list_head *head, struct ftrace_ops *ops, char *mod, bool enable) { @@ -4068,6 +4069,7 @@ static void process_cached_mods(const char *mod_name) kfree(mod); } +#endif /* * We register the module command as a template to show others how -- cgit v1.2.3-59-g8ed1b From 3f0bd8dad0db73f5d71b355aec5ab33b374260ba Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Mon, 19 Jun 2017 09:51:28 +1000 Subject: powerpc/perf: Add POWER9 alternate PM_RUN_CYC and PM_RUN_INST_CMPL events Similar to POWER8, POWER9 can count run cycles and run instructions completed on more than one PMU. Signed-off-by: Anton Blanchard Acked-by: Madhavan Srinivasan Signed-off-by: Michael Ellerman --- arch/powerpc/perf/power9-events-list.h | 4 ++++ arch/powerpc/perf/power9-pmu.c | 2 ++ 2 files changed, 6 insertions(+) diff --git a/arch/powerpc/perf/power9-events-list.h b/arch/powerpc/perf/power9-events-list.h index 80204e064362..50689180a6c1 100644 --- a/arch/powerpc/perf/power9-events-list.h +++ b/arch/powerpc/perf/power9-events-list.h @@ -51,8 +51,12 @@ EVENT(PM_DTLB_MISS, 0x300fc) EVENT(PM_ITLB_MISS, 0x400fc) /* Run_Instructions */ EVENT(PM_RUN_INST_CMPL, 0x500fa) +/* Alternate event code for PM_RUN_INST_CMPL */ +EVENT(PM_RUN_INST_CMPL_ALT, 0x400fa) /* Run_cycles */ EVENT(PM_RUN_CYC, 0x600f4) +/* Alternate event code for Run_cycles */ +EVENT(PM_RUN_CYC_ALT, 0x200f4) /* Instruction Dispatched */ EVENT(PM_INST_DISP, 0x200f2) EVENT(PM_INST_DISP_ALT, 0x300f2) diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c index f17435e4a489..2280cf87ff9c 100644 --- a/arch/powerpc/perf/power9-pmu.c +++ b/arch/powerpc/perf/power9-pmu.c @@ -107,6 +107,8 @@ extern struct attribute_group isa207_pmu_format_group; /* Table of alternatives, sorted by column 0 */ static const unsigned int power9_event_alternatives[][MAX_ALT] = { { PM_INST_DISP, PM_INST_DISP_ALT }, + { PM_RUN_CYC_ALT, PM_RUN_CYC }, + { PM_RUN_INST_CMPL_ALT, PM_RUN_INST_CMPL }, }; static int power9_get_alternatives(u64 event, unsigned int flags, u64 alt[]) -- cgit v1.2.3-59-g8ed1b From 87c4b83e0fe234a1f0eed131ab6fa232036860d5 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Thu, 15 Jun 2017 09:46:38 +1000 Subject: powerpc: Fix emulation of mcrf in emulate_step() The mcrf emulation code was using the CR field number directly as the shift value, without taking into account that CR fields are numbered from 0-7 starting at the high bits. That meant it was looking at the CR fields in the reverse order. Fixes: cf87c3f6b647 ("powerpc: Emulate icbi, mcrf and conditional-trap instructions") Cc: stable@vger.kernel.org # v3.18+ Signed-off-by: Anton Blanchard Acked-by: Naveen N. Rao Signed-off-by: Michael Ellerman --- arch/powerpc/lib/sstep.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index 33117f8a0882..fb84f51b1f0b 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -683,8 +683,10 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, case 19: switch ((instr >> 1) & 0x3ff) { case 0: /* mcrf */ - rd = (instr >> 21) & 0x1c; - ra = (instr >> 16) & 0x1c; + rd = 7 - ((instr >> 23) & 0x7); + ra = 7 - ((instr >> 18) & 0x7); + rd *= 4; + ra *= 4; val = (regs->ccr >> ra) & 0xf; regs->ccr = (regs->ccr & ~(0xfUL << rd)) | (val << rd); goto instr_done; -- cgit v1.2.3-59-g8ed1b From 64e756c55aa46fc18fd53e8f3598b73b528d8637 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Thu, 15 Jun 2017 09:46:39 +1000 Subject: powerpc: Fix emulation of mfocrf in emulate_step() From POWER4 onwards, mfocrf() only places the specified CR field into the destination GPR, and the rest of it is set to 0. The PowerPC AS from version 3.0 now requires this behaviour. The emulation code currently puts the entire CR into the destination GPR. Fix it. Fixes: 6888199f7fe5 ("[POWERPC] Emulate more instructions in software") Cc: stable@vger.kernel.org # v2.6.22+ Signed-off-by: Anton Blanchard Acked-by: Naveen N. Rao Signed-off-by: Michael Ellerman --- arch/powerpc/lib/sstep.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index fb84f51b1f0b..ee33327686ae 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -966,6 +966,19 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, #endif case 19: /* mfcr */ + if ((instr >> 20) & 1) { + imm = 0xf0000000UL; + for (sh = 0; sh < 8; ++sh) { + if (instr & (0x80000 >> sh)) { + regs->gpr[rd] = regs->ccr & imm; + break; + } + imm >>= 4; + } + + goto instr_done; + } + regs->gpr[rd] = regs->ccr; regs->gpr[rd] &= 0xffffffffUL; goto instr_done; -- cgit v1.2.3-59-g8ed1b From 19d39a3810e7032f311ef83effdac40339b9d022 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 11 Jul 2017 23:41:52 +0200 Subject: genirq: Keep chip buslock across irq_request/release_resources() Moving the irq_request/release_resources() callbacks out of the spinlocked, irq disabled and bus locked region, unearthed an interesting abuse of the irq_bus_lock/irq_bus_sync_unlock() callbacks. The OMAP GPIO driver does merily power management inside of them. The irq_request_resources() callback of this GPIO irqchip calls a function which reads a GPIO register. That read aborts now because the clock of the GPIO block is not magically enabled via the irq_bus_lock() callback. Move the callbacks under the bus lock again to prevent this. In the free_irq() path this requires to drop the bus_lock before calling synchronize_irq() and reaquiring it before calling the irq_release_resources() callback. The bus lock can't be held because: 1) The data which has been changed between bus_lock/un_lock is cached in the irq chip driver private data and needs to go out to the irq chip via the slow bus (usually SPI or I2C) before calling synchronize_irq(). That's the reason why this bus_lock/unlock magic exists in the first place, as you cannot do SPI/I2C transactions while holding desc->lock with interrupts disabled. 2) synchronize_irq() will actually deadlock, if there is a handler on flight. These chips use threaded handlers for obvious reasons, as they allow to do SPI/I2C communication. When the threaded handler returns then bus_lock needs to be taken in irq_finalize_oneshot() as we need to talk to the actual irq chip once more. After that the threaded handler is marked done, which makes synchronize_irq() return. So if we hold bus_lock accross the synchronize_irq() call, the handler cannot mark itself done because it blocks on the bus lock. That in turn makes synchronize_irq() wait forever on the threaded handler to complete.... Add the missing unlock of desc->request_mutex in the error path of __free_irq() and add a bunch of comments to explain the locking and protection rules. Fixes: 46e48e257360 ("genirq: Move irq resource handling out of spinlocked region") Reported-and-tested-by: Sebastian Reichel Reported-and-tested-by: Tony Lindgren Reported-by: Pavel Machek Signed-off-by: Thomas Gleixner Not-longer-ranted-at-by: Linus Torvalds Cc: Linus Walleij Cc: Grygorii Strashko Cc: Marc Zyngier --- kernel/irq/manage.c | 63 ++++++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 53 insertions(+), 10 deletions(-) diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 5624b2dd6b58..1d1a5b945ab4 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1090,6 +1090,16 @@ setup_irq_thread(struct irqaction *new, unsigned int irq, bool secondary) /* * Internal function to register an irqaction - typically used to * allocate special interrupts that are part of the architecture. + * + * Locking rules: + * + * desc->request_mutex Provides serialization against a concurrent free_irq() + * chip_bus_lock Provides serialization for slow bus operations + * desc->lock Provides serialization against hard interrupts + * + * chip_bus_lock and desc->lock are sufficient for all other management and + * interrupt related functions. desc->request_mutex solely serializes + * request/free_irq(). */ static int __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) @@ -1167,20 +1177,35 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) if (desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE) new->flags &= ~IRQF_ONESHOT; + /* + * Protects against a concurrent __free_irq() call which might wait + * for synchronize_irq() to complete without holding the optional + * chip bus lock and desc->lock. + */ mutex_lock(&desc->request_mutex); + + /* + * Acquire bus lock as the irq_request_resources() callback below + * might rely on the serialization or the magic power management + * functions which are abusing the irq_bus_lock() callback, + */ + chip_bus_lock(desc); + + /* First installed action requests resources. */ if (!desc->action) { ret = irq_request_resources(desc); if (ret) { pr_err("Failed to request resources for %s (irq %d) on irqchip %s\n", new->name, irq, desc->irq_data.chip->name); - goto out_mutex; + goto out_bus_unlock; } } - chip_bus_lock(desc); - /* * The following block of code has to be executed atomically + * protected against a concurrent interrupt and any of the other + * management calls which are not serialized via + * desc->request_mutex or the optional bus lock. */ raw_spin_lock_irqsave(&desc->lock, flags); old_ptr = &desc->action; @@ -1286,10 +1311,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) ret = __irq_set_trigger(desc, new->flags & IRQF_TRIGGER_MASK); - if (ret) { - irq_release_resources(desc); + if (ret) goto out_unlock; - } } desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \ @@ -1385,12 +1408,10 @@ mismatch: out_unlock: raw_spin_unlock_irqrestore(&desc->lock, flags); - chip_bus_sync_unlock(desc); - if (!desc->action) irq_release_resources(desc); - -out_mutex: +out_bus_unlock: + chip_bus_sync_unlock(desc); mutex_unlock(&desc->request_mutex); out_thread: @@ -1472,6 +1493,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) WARN(1, "Trying to free already-free IRQ %d\n", irq); raw_spin_unlock_irqrestore(&desc->lock, flags); chip_bus_sync_unlock(desc); + mutex_unlock(&desc->request_mutex); return NULL; } @@ -1498,6 +1520,20 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) #endif raw_spin_unlock_irqrestore(&desc->lock, flags); + /* + * Drop bus_lock here so the changes which were done in the chip + * callbacks above are synced out to the irq chips which hang + * behind a slow bus (I2C, SPI) before calling synchronize_irq(). + * + * Aside of that the bus_lock can also be taken from the threaded + * handler in irq_finalize_oneshot() which results in a deadlock + * because synchronize_irq() would wait forever for the thread to + * complete, which is blocked on the bus lock. + * + * The still held desc->request_mutex() protects against a + * concurrent request_irq() of this irq so the release of resources + * and timing data is properly serialized. + */ chip_bus_sync_unlock(desc); unregister_handler_proc(irq, action); @@ -1530,8 +1566,15 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) } } + /* Last action releases resources */ if (!desc->action) { + /* + * Reaquire bus lock as irq_release_resources() might + * require it to deallocate resources over the slow bus. + */ + chip_bus_lock(desc); irq_release_resources(desc); + chip_bus_sync_unlock(desc); irq_remove_timings(desc); } -- cgit v1.2.3-59-g8ed1b From 7459e1d25ffefa2b1be799477fcc1f6c62f6cec7 Mon Sep 17 00:00:00 2001 From: Horia Geantă Date: Fri, 7 Jul 2017 16:57:06 +0300 Subject: crypto: caam - fix signals handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Driver does not properly handle the case when signals interrupt wait_for_completion_interruptible(): -it does not check for return value -completion structure is allocated on stack; in case a signal interrupts the sleep, it will go out of scope, causing the worker thread (caam_jr_dequeue) to fail when it accesses it wait_for_completion_interruptible() is replaced with uninterruptable wait_for_completion(). We choose to block all signals while waiting for I/O (device executing the split key generation job descriptor) since the alternative - in order to have a deterministic device state - would be to flush the job ring (aborting *all* in-progress jobs). Cc: Fixes: 045e36780f115 ("crypto: caam - ahash hmac support") Fixes: 4c1ec1f930154 ("crypto: caam - refactor key_gen, sg") Signed-off-by: Horia Geantă Signed-off-by: Herbert Xu --- drivers/crypto/caam/caamhash.c | 2 +- drivers/crypto/caam/key_gen.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c index 7c44c90ad593..910ec61cae09 100644 --- a/drivers/crypto/caam/caamhash.c +++ b/drivers/crypto/caam/caamhash.c @@ -396,7 +396,7 @@ static int hash_digest_key(struct caam_hash_ctx *ctx, const u8 *key_in, ret = caam_jr_enqueue(jrdev, desc, split_key_done, &result); if (!ret) { /* in progress */ - wait_for_completion_interruptible(&result.completion); + wait_for_completion(&result.completion); ret = result.err; #ifdef DEBUG print_hex_dump(KERN_ERR, diff --git a/drivers/crypto/caam/key_gen.c b/drivers/crypto/caam/key_gen.c index 1bb2816a9b4d..c425d4adaf2a 100644 --- a/drivers/crypto/caam/key_gen.c +++ b/drivers/crypto/caam/key_gen.c @@ -149,7 +149,7 @@ int gen_split_key(struct device *jrdev, u8 *key_out, ret = caam_jr_enqueue(jrdev, desc, split_key_done, &result); if (!ret) { /* in progress */ - wait_for_completion_interruptible(&result.completion); + wait_for_completion(&result.completion); ret = result.err; #ifdef DEBUG print_hex_dump(KERN_ERR, "ctx.key@"__stringify(__LINE__)": ", -- cgit v1.2.3-59-g8ed1b From 2acce6aa9f6569d4e135b2c4cfb56acce95efaeb Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 10 Jul 2017 22:00:48 +0800 Subject: Networking crypto: af_alg - Avoid sock_graft call warning The newly added sock_graft warning triggers in af_alg_accept. It's harmless as we're essentially doing sock->sk = sock->sk. The sock_graft call is actually redundant because all the work it does is subsumed by sock_init_data. However, it was added to placate SELinux as it uses it to initialise its internal state. This patch avoisd the warning by making the SELinux call directly. Reported-by: Linus Torvalds Signed-off-by: Herbert Xu Acked-by: David S. Miller --- crypto/af_alg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 3556d8eb54a7..92a3d540d920 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -287,7 +287,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock, bool kern) goto unlock; sock_init_data(newsock, sk2); - sock_graft(sk2, newsock); + security_sock_graft(sk2, newsock); security_sk_clone(sk, sk2); err = type->accept(ask->private, sk2); -- cgit v1.2.3-59-g8ed1b From 1606043f214f912a52195293614935811a6e3e53 Mon Sep 17 00:00:00 2001 From: Gilad Ben-Yossef Date: Wed, 28 Jun 2017 10:22:03 +0300 Subject: crypto: atmel - only treat EBUSY as transient if backlog The Atmel SHA driver was treating -EBUSY as indication of queueing to backlog without checking that backlog is enabled for the request. Fix it by checking request flags. Cc: Signed-off-by: Gilad Ben-Yossef Signed-off-by: Herbert Xu --- drivers/crypto/atmel-sha.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c index a9482023d7d3..dad4e5bad827 100644 --- a/drivers/crypto/atmel-sha.c +++ b/drivers/crypto/atmel-sha.c @@ -1204,7 +1204,9 @@ static int atmel_sha_finup(struct ahash_request *req) ctx->flags |= SHA_FLAGS_FINUP; err1 = atmel_sha_update(req); - if (err1 == -EINPROGRESS || err1 == -EBUSY) + if (err1 == -EINPROGRESS || + (err1 == -EBUSY && (ahash_request_flags(req) & + CRYPTO_TFM_REQ_MAY_BACKLOG))) return err1; /* -- cgit v1.2.3-59-g8ed1b From 854b06f768794cd664886ec3ba3a5b1c58d42167 Mon Sep 17 00:00:00 2001 From: David Gstir Date: Wed, 28 Jun 2017 15:27:10 +0200 Subject: crypto: caam - properly set IV after {en,de}crypt MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Certain cipher modes like CTS expect the IV (req->info) of ablkcipher_request (or equivalently req->iv of skcipher_request) to contain the last ciphertext block when the {en,de}crypt operation is done. This is currently not the case for the CAAM driver which in turn breaks e.g. cts(cbc(aes)) when the CAAM driver is enabled. This patch fixes the CAAM driver to properly set the IV after the {en,de}crypt operation of ablkcipher finishes. This issue was revealed by the changes in the SW CTS mode in commit 0605c41cc53ca ("crypto: cts - Convert to skcipher") Cc: # 4.8+ Signed-off-by: David Gstir Reviewed-by: Horia Geantă Signed-off-by: Herbert Xu --- drivers/crypto/caam/caamalg.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c index fde399c88779..0488b7f81dcf 100644 --- a/drivers/crypto/caam/caamalg.c +++ b/drivers/crypto/caam/caamalg.c @@ -882,10 +882,10 @@ static void ablkcipher_encrypt_done(struct device *jrdev, u32 *desc, u32 err, { struct ablkcipher_request *req = context; struct ablkcipher_edesc *edesc; -#ifdef DEBUG struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req); int ivsize = crypto_ablkcipher_ivsize(ablkcipher); +#ifdef DEBUG dev_err(jrdev, "%s %d: err 0x%x\n", __func__, __LINE__, err); #endif @@ -904,6 +904,14 @@ static void ablkcipher_encrypt_done(struct device *jrdev, u32 *desc, u32 err, #endif ablkcipher_unmap(jrdev, edesc, req); + + /* + * The crypto API expects us to set the IV (req->info) to the last + * ciphertext block. This is used e.g. by the CTS mode. + */ + scatterwalk_map_and_copy(req->info, req->dst, req->nbytes - ivsize, + ivsize, 0); + kfree(edesc); ablkcipher_request_complete(req, err); @@ -914,10 +922,10 @@ static void ablkcipher_decrypt_done(struct device *jrdev, u32 *desc, u32 err, { struct ablkcipher_request *req = context; struct ablkcipher_edesc *edesc; -#ifdef DEBUG struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req); int ivsize = crypto_ablkcipher_ivsize(ablkcipher); +#ifdef DEBUG dev_err(jrdev, "%s %d: err 0x%x\n", __func__, __LINE__, err); #endif @@ -935,6 +943,14 @@ static void ablkcipher_decrypt_done(struct device *jrdev, u32 *desc, u32 err, #endif ablkcipher_unmap(jrdev, edesc, req); + + /* + * The crypto API expects us to set the IV (req->info) to the last + * ciphertext block. + */ + scatterwalk_map_and_copy(req->info, req->src, req->nbytes - ivsize, + ivsize, 0); + kfree(edesc); ablkcipher_request_complete(req, err); -- cgit v1.2.3-59-g8ed1b From d3f1d2f7863137c5d71e64041b48968db29b149e Mon Sep 17 00:00:00 2001 From: Harsh Jain Date: Fri, 23 Jun 2017 19:45:11 +0530 Subject: crypto: chcr - Avoid algo allocation in softirq. Thsi patch fixes calling "crypto_alloc_cipher" call in bottom halves. Pre allocate aes cipher required to update Tweak value for XTS. Signed-off-by: Harsh Jain Signed-off-by: Herbert Xu --- drivers/crypto/chelsio/chcr_algo.c | 23 +++++++++++++++-------- drivers/crypto/chelsio/chcr_crypto.h | 1 + 2 files changed, 16 insertions(+), 8 deletions(-) diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c index aa4e5b88483d..508cbc79e508 100644 --- a/drivers/crypto/chelsio/chcr_algo.c +++ b/drivers/crypto/chelsio/chcr_algo.c @@ -899,26 +899,20 @@ static int chcr_update_tweak(struct ablkcipher_request *req, u8 *iv) u8 *key; unsigned int keylen; - cipher = crypto_alloc_cipher("aes-generic", 0, 0); + cipher = ablkctx->aes_generic; memcpy(iv, req->info, AES_BLOCK_SIZE); - if (IS_ERR(cipher)) { - ret = -ENOMEM; - goto out; - } keylen = ablkctx->enckey_len / 2; key = ablkctx->key + keylen; ret = crypto_cipher_setkey(cipher, key, keylen); if (ret) - goto out1; + goto out; crypto_cipher_encrypt_one(cipher, iv, iv); for (i = 0; i < (reqctx->processed / AES_BLOCK_SIZE); i++) gf128mul_x_ble((le128 *)iv, (le128 *)iv); crypto_cipher_decrypt_one(cipher, iv, iv); -out1: - crypto_free_cipher(cipher); out: return ret; } @@ -1262,6 +1256,17 @@ static int chcr_cra_init(struct crypto_tfm *tfm) pr_err("failed to allocate fallback for %s\n", alg->cra_name); return PTR_ERR(ablkctx->sw_cipher); } + + if (get_cryptoalg_subtype(tfm) == CRYPTO_ALG_SUB_TYPE_XTS) { + /* To update tweak*/ + ablkctx->aes_generic = crypto_alloc_cipher("aes-generic", 0, 0); + if (IS_ERR(ablkctx->aes_generic)) { + pr_err("failed to allocate aes cipher for tweak\n"); + return PTR_ERR(ablkctx->aes_generic); + } + } else + ablkctx->aes_generic = NULL; + tfm->crt_ablkcipher.reqsize = sizeof(struct chcr_blkcipher_req_ctx); return chcr_device_init(crypto_tfm_ctx(tfm)); } @@ -1292,6 +1297,8 @@ static void chcr_cra_exit(struct crypto_tfm *tfm) struct ablk_ctx *ablkctx = ABLK_CTX(ctx); crypto_free_skcipher(ablkctx->sw_cipher); + if (ablkctx->aes_generic) + crypto_free_cipher(ablkctx->aes_generic); } static int get_alg_config(struct algo_param *params, diff --git a/drivers/crypto/chelsio/chcr_crypto.h b/drivers/crypto/chelsio/chcr_crypto.h index a4f95b014b46..30af1ee17b87 100644 --- a/drivers/crypto/chelsio/chcr_crypto.h +++ b/drivers/crypto/chelsio/chcr_crypto.h @@ -155,6 +155,7 @@ struct ablk_ctx { struct crypto_skcipher *sw_cipher; + struct crypto_cipher *aes_generic; __be32 key_ctx_hdr; unsigned int enckey_len; unsigned char ciph_mode; -- cgit v1.2.3-59-g8ed1b From b8fc3397c9e88dc7889b56395d04c1f3d65d186f Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 20 Jun 2017 11:35:50 +0100 Subject: crypto: cavium - make several functions static The functions cvm_encrypt, cvm_decrypt, cvm_xts_setkey and cvm_enc_dec_init does not need to be in global scope, so make them static. Signed-off-by: Colin Ian King Acked-by: David S. Miller Signed-off-by: Herbert Xu --- drivers/crypto/cavium/cpt/cptvf_algs.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/crypto/cavium/cpt/cptvf_algs.c b/drivers/crypto/cavium/cpt/cptvf_algs.c index 1b220f3ed017..df21d996db7e 100644 --- a/drivers/crypto/cavium/cpt/cptvf_algs.c +++ b/drivers/crypto/cavium/cpt/cptvf_algs.c @@ -222,17 +222,17 @@ static inline int cvm_enc_dec(struct ablkcipher_request *req, u32 enc) return -EINPROGRESS; } -int cvm_encrypt(struct ablkcipher_request *req) +static int cvm_encrypt(struct ablkcipher_request *req) { return cvm_enc_dec(req, true); } -int cvm_decrypt(struct ablkcipher_request *req) +static int cvm_decrypt(struct ablkcipher_request *req) { return cvm_enc_dec(req, false); } -int cvm_xts_setkey(struct crypto_ablkcipher *cipher, const u8 *key, +static int cvm_xts_setkey(struct crypto_ablkcipher *cipher, const u8 *key, u32 keylen) { struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher); @@ -336,7 +336,7 @@ static int cvm_ecb_des3_setkey(struct crypto_ablkcipher *cipher, const u8 *key, return cvm_setkey(cipher, key, keylen, DES3_ECB); } -int cvm_enc_dec_init(struct crypto_tfm *tfm) +static int cvm_enc_dec_init(struct crypto_tfm *tfm) { struct cvm_enc_ctx *ctx = crypto_tfm_ctx(tfm); -- cgit v1.2.3-59-g8ed1b From 1dc482b6578e2869e51c35276017178503d5ac81 Mon Sep 17 00:00:00 2001 From: Mark Salter Date: Tue, 11 Jul 2017 12:45:43 -0400 Subject: ACPI / irq: Fix return code of acpi_gsi_to_irq() The function acpi_gsi_to_irq() must return 0 on success as the caller ghes_probe expects an 0 for success. This change also matches x86 implementation. This patch was submitted around 4.5 timeframe but wasn't pushed because it didn't fix a real problem. Now that RAS/GHES patches are in kernel, this fixes an error seen on a Mustang (arm64) platform: GHES: Failed to map GSI to IRQ for generic hardware error source: 2 GHES: probe of GHES.2 failed with error 81 Signed-off-by: Tuan Phan Signed-off-by: Loc Ho Signed-off-by: Mark Salter Acked-by: Lorenzo Pieralisi Signed-off-by: Rafael J. Wysocki --- drivers/acpi/irq.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/acpi/irq.c b/drivers/acpi/irq.c index 830299a74b84..7c352cba0528 100644 --- a/drivers/acpi/irq.c +++ b/drivers/acpi/irq.c @@ -24,7 +24,7 @@ static struct fwnode_handle *acpi_gsi_domain_id; * * irq location updated with irq value [>0 on success, 0 on failure] * - * Returns: linux IRQ number on success (>0) + * Returns: 0 on success * -EINVAL on failure */ int acpi_gsi_to_irq(u32 gsi, unsigned int *irq) @@ -37,7 +37,7 @@ int acpi_gsi_to_irq(u32 gsi, unsigned int *irq) * *irq == 0 means no mapping, that should * be reported as a failure */ - return (*irq > 0) ? *irq : -EINVAL; + return (*irq > 0) ? 0 : -EINVAL; } EXPORT_SYMBOL_GPL(acpi_gsi_to_irq); -- cgit v1.2.3-59-g8ed1b From 662591461c4b9a1e3b9b159dbf37648a585ebaae Mon Sep 17 00:00:00 2001 From: Lv Zheng Date: Wed, 12 Jul 2017 11:09:09 +0800 Subject: ACPI / EC: Drop EC noirq hooks to fix a regression According to bug reports, although the busy polling mode can make noirq stages execute faster, it causes abnormal fan blowing up after system resume (see the first link below for a video demonstration) on Lenovo ThinkPad X1 Carbon - the 5th Generation. The problem can be fixed by upgrading the EC firmware on that machine. However, many reporters confirm that the problem can be fixed by stopping busy polling during suspend/resume and for some of them upgrading the EC firmware is not an option. For this reason, drop the noirq stage hooks from the EC driver to fix the regression. Fixes: c3a696b6e8f8 (ACPI / EC: Use busy polling mode when GPE is not enabled) Link: https://youtu.be/9NQ9x-Jm99Q Link: https://bugzilla.kernel.org/show_bug.cgi?id=196129 Reported-by: Andreas Lindhe Tested-by: Gjorgji Jankovski Tested-by: Damjan Georgievski Tested-by: Fernando Chaves Tested-by: Tomislav Ivek Tested-by: Denis P. Signed-off-by: Lv Zheng Cc: All applicable Signed-off-by: Rafael J. Wysocki --- drivers/acpi/ec.c | 19 ------------------- 1 file changed, 19 deletions(-) diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 77c18a5547ed..b65016f1f624 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1870,24 +1870,6 @@ error: } #ifdef CONFIG_PM_SLEEP -static int acpi_ec_suspend_noirq(struct device *dev) -{ - struct acpi_ec *ec = - acpi_driver_data(to_acpi_device(dev)); - - acpi_ec_enter_noirq(ec); - return 0; -} - -static int acpi_ec_resume_noirq(struct device *dev) -{ - struct acpi_ec *ec = - acpi_driver_data(to_acpi_device(dev)); - - acpi_ec_leave_noirq(ec); - return 0; -} - static int acpi_ec_suspend(struct device *dev) { struct acpi_ec *ec = @@ -1909,7 +1891,6 @@ static int acpi_ec_resume(struct device *dev) #endif static const struct dev_pm_ops acpi_ec_pm = { - SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(acpi_ec_suspend_noirq, acpi_ec_resume_noirq) SET_SYSTEM_SLEEP_PM_OPS(acpi_ec_suspend, acpi_ec_resume) }; -- cgit v1.2.3-59-g8ed1b From 9c40f956ce9b331493347d1b3cb7e384f7dc0581 Mon Sep 17 00:00:00 2001 From: Lv Zheng Date: Wed, 12 Jul 2017 11:09:17 +0800 Subject: Revert "ACPI / EC: Enable event freeze mode..." to fix a regression On Lenovo ThinkPad X1 Carbon - the 5th Generation, enabling an earlier EC event freezing timing causes acpitz-virtual-0 to report a stuck 48C temparature. And with EC firmware revisioned as 1.14, without reverting back to old EC event freezing timing, the fan still blows up after a system resume. This reverts the culprit change so that the regression can be fixed without upgrading the EC firmware. Fixes: d30283057ecd (ACPI / EC: Enable event freeze mode to improve event handling) Link: https://bugzilla.kernel.org/show_bug.cgi?id=191181#c168 Tested-by: Damjan Georgievski Signed-off-by: Lv Zheng Cc: 4.9+ # 4.9+ Signed-off-by: Rafael J. Wysocki --- drivers/acpi/ec.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index b65016f1f624..20d9e9f0e231 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -147,7 +147,7 @@ static unsigned int ec_storm_threshold __read_mostly = 8; module_param(ec_storm_threshold, uint, 0644); MODULE_PARM_DESC(ec_storm_threshold, "Maxim false GPE numbers not considered as GPE storm"); -static bool ec_freeze_events __read_mostly = true; +static bool ec_freeze_events __read_mostly = false; module_param(ec_freeze_events, bool, 0644); MODULE_PARM_DESC(ec_freeze_events, "Disabling event handling during suspend/resume"); -- cgit v1.2.3-59-g8ed1b From 3b6a70be5ac81673af1ca8b4dae84743cb9fcc87 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sun, 9 Jul 2017 21:05:12 +0200 Subject: ACPI / x86: Allow matching always_present_id array entries by DMI On some x86 systems the DSDT hides APCI devices to work around Windows driver bugs. On one such system the device is even hidden until a certain time after _SB.PCI0.GFX0.LCD.LCD1._ON gets called has passed *and* _STA has been called at least 3 times since. TL;DR: it is a mess. Until now the always_present_id matching was used to force status for a whole class of devices, e.g. always enable PWM1 on CHerry Trail devices. This commit extends the always_present_id matching code to optionally also check for a DMI match so that we can also add system specific quirks to the always_present_id array. Signed-off-by: Hans de Goede Reviewed-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- drivers/acpi/x86/utils.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c index bd86b809c848..b0e16516adfd 100644 --- a/drivers/acpi/x86/utils.c +++ b/drivers/acpi/x86/utils.c @@ -12,6 +12,7 @@ */ #include +#include #include #include #include "../internal.h" @@ -20,6 +21,10 @@ * Some ACPI devices are hidden (status == 0x0) in recent BIOS-es because * some recent Windows drivers bind to one device but poke at multiple * devices at the same time, so the others get hidden. + * + * Some BIOS-es (temporarily) hide specific APCI devices to work around Windows + * driver bugs. We use DMI matching to match known cases of this. + * * We work around this by always reporting ACPI_STA_DEFAULT for these * devices. Note this MUST only be done for devices where this is safe. * @@ -31,14 +36,16 @@ struct always_present_id { struct acpi_device_id hid[2]; struct x86_cpu_id cpu_ids[2]; + struct dmi_system_id dmi_ids[2]; /* Optional */ const char *uid; }; #define ICPU(model) { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, } -#define ENTRY(hid, uid, cpu_models) { \ +#define ENTRY(hid, uid, cpu_models, dmi...) { \ { { hid, }, {} }, \ { cpu_models, {} }, \ + { { .matches = dmi }, {} }, \ uid, \ } @@ -47,13 +54,13 @@ static const struct always_present_id always_present_ids[] = { * Bay / Cherry Trail PWM directly poked by GPU driver in win10, * but Linux uses a separate PWM driver, harmless if not used. */ - ENTRY("80860F09", "1", ICPU(INTEL_FAM6_ATOM_SILVERMONT1)), - ENTRY("80862288", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT)), + ENTRY("80860F09", "1", ICPU(INTEL_FAM6_ATOM_SILVERMONT1), {}), + ENTRY("80862288", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT), {}), /* * The INT0002 device is necessary to clear wakeup interrupt sources * on Cherry Trail devices, without it we get nobody cared IRQ msgs. */ - ENTRY("INT0002", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT)), + ENTRY("INT0002", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT), {}), }; bool acpi_device_always_present(struct acpi_device *adev) @@ -76,6 +83,10 @@ bool acpi_device_always_present(struct acpi_device *adev) if (!x86_match_cpu(always_present_ids[i].cpu_ids)) continue; + if (always_present_ids[i].dmi_ids[0].matches[0].slot && + !dmi_check_system(always_present_ids[i].dmi_ids)) + continue; + if (old_status != ACPI_STA_DEFAULT) /* Log only once */ dev_info(&adev->dev, "Device [%s] is in always present list\n", -- cgit v1.2.3-59-g8ed1b From b5cc1699191829cda2dd9447210e1e801e2082c9 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sun, 9 Jul 2017 21:05:13 +0200 Subject: ACPI / x86: Add Dell Venue 11 Pro 7130 touchscreen to always_present_ids The _STA method of the Venue 11 Pro 7130 touchscreen has this ugliness: Method (_STA, 0, NotSerialized) // _STA: Status { If ((SDS1 & One) == One) { If (RST1 == Zero) { Return (0x0F) } ElseIf (RST2 == Zero) { RST2 = One TMRV = Timer } Else { Local0 = ((Timer - TMRV) / 0x2710) If (Local0 > TMRI) { RST2 = Zero RST1 = Zero } } } Else { Return (Zero) } } Whereby RST1 gets set by _SB.PCI0.GFX0.LCD.LCD1._ON, this means that after RST1 has been set first _STA must be called to set TIMER and then after enough time has elapsed _STA must be called twice more, once to clear RST1 and once to finally return 0xf before the touchscreen will show up. Which is just crazy. This commit adds an always_present_ids entry for the SYNA7500 touchscreen ACPI node, together with a DMI match for the Venue 11 Pro 7130, fixing the touchscreen not working on this device. Signed-off-by: Hans de Goede Reviewed-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- drivers/acpi/x86/utils.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c index b0e16516adfd..eb6caf6f708b 100644 --- a/drivers/acpi/x86/utils.c +++ b/drivers/acpi/x86/utils.c @@ -61,6 +61,15 @@ static const struct always_present_id always_present_ids[] = { * on Cherry Trail devices, without it we get nobody cared IRQ msgs. */ ENTRY("INT0002", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT), {}), + /* + * On the Dell Venue 11 Pro 7130 the DSDT hides the touchscreen ACPI + * device until a certain time after _SB.PCI0.GFX0.LCD.LCD1._ON gets + * called has passed *and* _STA has been called at least 3 times since. + */ + ENTRY("SYNA7500", "1", ICPU(INTEL_FAM6_HASWELL_ULT), { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Venue 11 Pro 7130"), + }), }; bool acpi_device_always_present(struct acpi_device *adev) -- cgit v1.2.3-59-g8ed1b From 906dc284d00c8aa8e2ad3f71182cf9fa3107e35a Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sun, 9 Jul 2017 21:05:14 +0200 Subject: ACPI / x86: Add KIOX000A accelerometer on GPD win to always_present_ids array The GPD win BIOS dated 20170320 has disabled the accelerometer, the drivers sometimes cause crashes under Windows and this is how the manufacturer has solved this :| I see no other way to keep the accelerometer working under Windows then adding it to the always_present_ids array. Signed-off-by: Hans de Goede Reviewed-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- drivers/acpi/x86/utils.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c index eb6caf6f708b..b4fbb9929482 100644 --- a/drivers/acpi/x86/utils.c +++ b/drivers/acpi/x86/utils.c @@ -70,6 +70,19 @@ static const struct always_present_id always_present_ids[] = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "Venue 11 Pro 7130"), }), + /* + * The GPD win BIOS dated 20170320 has disabled the accelerometer, the + * drivers sometimes cause crashes under Windows and this is how the + * manufacturer has solved this :| Note that the the DMI data is less + * generic then it seems, a board_vendor of "AMI Corporation" is quite + * rare and a board_name of "Default String" also is rare. + */ + ENTRY("KIOX000A", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT), { + DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"), + DMI_MATCH(DMI_BOARD_NAME, "Default string"), + DMI_MATCH(DMI_PRODUCT_NAME, "Default string"), + DMI_MATCH(DMI_BIOS_DATE, "03/20/2017") + }), }; bool acpi_device_always_present(struct acpi_device *adev) -- cgit v1.2.3-59-g8ed1b From e8158b486d5f3f55cf372c5a32b42f263bf7f123 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Tue, 11 Jul 2017 18:20:20 +0300 Subject: device property: Introduce fwnode_call_bool_op() for ops that return bool fwnode_call_int_op() isn't suitable for calling ops that return bool since it effectively causes the result returned to the user to be true when an op hasn't been defined or the fwnode is NULL. Address this by introducing fwnode_call_bool_op() for calling ops that return bool. Fixes: 3708184afc77 "device property: Move FW type specific functionality to FW specific files" Fixes: 2294b3af05e9 "device property: Introduce fwnode_device_is_available()" Reported-by: Dan Carpenter Signed-off-by: Sakari Ailus Signed-off-by: Rafael J. Wysocki --- drivers/base/property.c | 6 +++--- include/linux/fwnode.h | 4 ++++ 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/base/property.c b/drivers/base/property.c index 692007e5a94b..edf02c1b5845 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -253,10 +253,10 @@ bool fwnode_property_present(struct fwnode_handle *fwnode, const char *propname) { bool ret; - ret = fwnode_call_int_op(fwnode, property_present, propname); + ret = fwnode_call_bool_op(fwnode, property_present, propname); if (ret == false && !IS_ERR_OR_NULL(fwnode) && !IS_ERR_OR_NULL(fwnode->secondary)) - ret = fwnode_call_int_op(fwnode->secondary, property_present, + ret = fwnode_call_bool_op(fwnode->secondary, property_present, propname); return ret; } @@ -1027,7 +1027,7 @@ EXPORT_SYMBOL_GPL(fwnode_handle_put); */ bool fwnode_device_is_available(struct fwnode_handle *fwnode) { - return fwnode_call_int_op(fwnode, device_is_available); + return fwnode_call_bool_op(fwnode, device_is_available); } EXPORT_SYMBOL_GPL(fwnode_device_is_available); diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 9ab375419189..50893a1646cf 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -99,6 +99,10 @@ struct fwnode_operations { (fwnode ? (fwnode_has_op(fwnode, op) ? \ (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : -ENXIO) : \ -EINVAL) +#define fwnode_call_bool_op(fwnode, op, ...) \ + (fwnode ? (fwnode_has_op(fwnode, op) ? \ + (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : false) : \ + false) #define fwnode_call_ptr_op(fwnode, op, ...) \ (fwnode_has_op(fwnode, op) ? \ (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : NULL) -- cgit v1.2.3-59-g8ed1b From 01e6a61aceb82e13bec29502a8eb70d9574f97ad Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 11 Jul 2017 22:10:54 +1000 Subject: powerpc/64: Fix atomic64_inc_not_zero() to return an int Although it's not documented anywhere, there is an expectation that atomic64_inc_not_zero() returns a result which fits in an int. This is the behaviour implemented on all arches except powerpc. This has caused at least one bug in practice, in the percpu-refcount code, where the long result from our atomic64_inc_not_zero() was truncated to an int leading to lost references and stuck systems. That was worked around in that code in commit 966d2b04e070 ("percpu-refcount: fix reference leak during percpu-atomic transition"). To the best of my grepping abilities there are no other callers in-tree which truncate the value, but we should fix it anyway. Because the breakage is subtle and potentially very harmful I'm also tagging it for stable. Code generation is largely unaffected because in most cases the callers are just using the result for a test anyway. In particular the case of fget() that was mentioned in commit a6cf7ed5119f ("powerpc/atomic: Implement atomic*_inc_not_zero") generates exactly the same code. Fixes: a6cf7ed5119f ("powerpc/atomic: Implement atomic*_inc_not_zero") Cc: stable@vger.kernel.org # v3.4 Noticed-by: Linus Torvalds Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/atomic.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index 2b90335194a7..a2cc8010cd72 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -560,7 +560,7 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) * Atomically increments @v by 1, so long as @v is non-zero. * Returns non-zero if @v was non-zero, and zero otherwise. */ -static __inline__ long atomic64_inc_not_zero(atomic64_t *v) +static __inline__ int atomic64_inc_not_zero(atomic64_t *v) { long t1, t2; @@ -579,7 +579,7 @@ static __inline__ long atomic64_inc_not_zero(atomic64_t *v) : "r" (&v->counter) : "cc", "xer", "memory"); - return t1; + return t1 != 0; } #endif /* __powerpc64__ */ -- cgit v1.2.3-59-g8ed1b From d4436c0dba8d4d780588179a2e192a867d266a10 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Mon, 10 Jul 2017 16:23:52 -0700 Subject: cpufreq: intel_pstate: Fix ratio setting for min_perf_pct When the minimum performance limit percentage is set to the power-up default, it is possible that minimum performance ratio is off by one. In the set_policy() callback the minimum ratio is calculated by applying global.min_perf_pct to turbo_ratio and rounding up, but the power-up default global.min_perf_pct is already rounded up to the next percent in min_perf_pct_min(). That results in two round up operations, so for the default min_perf_pct one of them is not required. It is better to remove rounding up in min_perf_pct_min() as this matches the displayed min_perf_pct prior to commit c5a2ee7dde89 (cpufreq: intel_pstate: Active mode P-state limits rework) in 4.12. For example on a platform with max turbo ratio of 37 and minimum ratio of 10, the min_perf_pct resulted in 28 with the above commit. Before this commit it was 27 and it will be the same after this change. Fixes: 1a4fe38add8b (cpufreq: intel_pstate: Remove max/min fractions to limit performance) Reported-by: Artem Bityutskiy Signed-off-by: Srinivas Pandruvada Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 756483251832..2386d7036e90 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -572,7 +572,7 @@ static int min_perf_pct_min(void) int turbo_pstate = cpu->pstate.turbo_pstate; return turbo_pstate ? - DIV_ROUND_UP(cpu->pstate.min_pstate * 100, turbo_pstate) : 0; + (cpu->pstate.min_pstate * 100 / turbo_pstate) : 0; } static s16 intel_pstate_get_epb(struct cpudata *cpu_data) -- cgit v1.2.3-59-g8ed1b From 2ca30331c156ca9e97643ad05dd8930b8fe78b01 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 10 Jul 2017 10:21:40 +0300 Subject: PM / QoS: return -EINVAL for bogus strings In the current code, if the user accidentally writes a bogus command to this sysfs file, then we set the latency tolerance to an uninitialized variable. Fixes: 2d984ad132a8 (PM / QoS: Introcuce latency tolerance device PM QoS type) Signed-off-by: Dan Carpenter Acked-by: Pavel Machek Cc: 3.15+ # 3.15+ Signed-off-by: Rafael J. Wysocki --- drivers/base/power/sysfs.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c index 185a52581cfa..156ab57bca77 100644 --- a/drivers/base/power/sysfs.c +++ b/drivers/base/power/sysfs.c @@ -272,6 +272,8 @@ static ssize_t pm_qos_latency_tolerance_store(struct device *dev, value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT; else if (!strcmp(buf, "any") || !strcmp(buf, "any\n")) value = PM_QOS_LATENCY_ANY; + else + return -EINVAL; } ret = dev_pm_qos_update_user_latency_tolerance(dev, value); return ret < 0 ? ret : n; -- cgit v1.2.3-59-g8ed1b From ab2f7cf141aa6734c4ca7525132d8cc236efee77 Mon Sep 17 00:00:00 2001 From: Vikram Mulukutla Date: Thu, 6 Jul 2017 10:53:20 -0700 Subject: cpufreq: schedutil: Fix sugov_start() versus sugov_update_shared() race With a shared policy in place, when one of the CPUs in the policy is hotplugged out and then brought back online, sugov_stop() and sugov_start() are called in order. sugov_stop() removes utilization hooks for each CPU in the policy and does nothing else in the for_each_cpu() loop. sugov_start() on the other hand iterates through the CPUs in the policy and re-initializes the per-cpu structure _and_ adds the utilization hook. This implies that the scheduler is allowed to invoke a CPU's utilization update hook when the rest of the per-cpu structures have yet to be re-inited. Apart from some strange values in tracepoints this doesn't cause a problem, but if we do end up accessing a pointer from the per-cpu sugov_cpu structure somewhere in the sugov_update_shared() path, we will likely see crashes since the memset for another CPU in the policy is free to race with sugov_update_shared from the CPU that is ready to go. So let's fix this now to first init all per-cpu structures, and then add the per-cpu utilization update hooks all at once. Signed-off-by: Vikram Mulukutla Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- kernel/sched/cpufreq_schedutil.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 076a2e31951c..29a397067ffa 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -610,6 +610,11 @@ static int sugov_start(struct cpufreq_policy *policy) sg_cpu->sg_policy = sg_policy; sg_cpu->flags = SCHED_CPUFREQ_RT; sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq; + } + + for_each_cpu(cpu, policy->cpus) { + struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu); + cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util, policy_is_shared(policy) ? sugov_update_shared : -- cgit v1.2.3-59-g8ed1b From 44925dfff05fd1a897992d278b15a6b6b55e79a7 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 12 Jul 2017 10:33:40 +0300 Subject: ftrace: Remove an unneeded NULL check "func" can't be NULL and it doesn't make sense to check because we've already derefenced it. Link: http://lkml.kernel.org/r/20170712073340.4enzeojeoupuds5a@mwanda Signed-off-by: Dan Carpenter Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 4706f0ed193e..5fb5b40b3ae8 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3950,7 +3950,7 @@ static int cache_mod(struct trace_array *tr, continue; /* no func matches all */ - if (!func || strcmp(func, "*") == 0 || + if (strcmp(func, "*") == 0 || (ftrace_mod->func && strcmp(ftrace_mod->func, func) == 0)) { ret = 0; -- cgit v1.2.3-59-g8ed1b From 2e028c4fe12907f226b8221815f16c2486ad3aa7 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 12 Jul 2017 10:35:57 +0300 Subject: ftrace: Fix uninitialized variable in match_records() My static checker complains that if "func" is NULL then "clear_filter" is uninitialized. This seems like it could be true, although it's possible something subtle is happening that I haven't seen. kernel/trace/ftrace.c:3844 match_records() error: uninitialized symbol 'clear_filter'. Link: http://lkml.kernel.org/r/20170712073556.h6tkpjcdzjaozozs@mwanda Cc: stable@vger.kernel.org Fixes: f0a3b154bd7 ("ftrace: Clarify code for mod command") Signed-off-by: Dan Carpenter Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 5fb5b40b3ae8..53f6b6401cf0 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3816,7 +3816,7 @@ match_records(struct ftrace_hash *hash, char *func, int len, char *mod) int exclude_mod = 0; int found = 0; int ret; - int clear_filter; + int clear_filter = 0; if (func) { func_g.type = filter_parse_regex(func, len, &func_g.search, -- cgit v1.2.3-59-g8ed1b From 2ad67141f1e47dc063b202993835361a06239aaa Mon Sep 17 00:00:00 2001 From: Tushar Dave Date: Tue, 11 Jul 2017 14:34:47 -0700 Subject: SPARC64: Fix sun4v DMA panic 64bit DMA only supported on sun4v equipped with ATU IOMMU HW. 'Commit b02c2b0bfd7ae ("sparc: remove arch specific dma_supported implementations")' introduced a code that incorrectly allow dma_supported() to succeed for 64bit dma mask even if system doesn't have ATU IOMMU. This results into panic. Fix it. Reported-by: Meelis Roos Signed-off-by: Tushar Dave Reviewed-by: Christoph Hellwig Signed-off-by: David S. Miller --- arch/sparc/kernel/pci_sun4v.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c index 24f21c726dfa..f10e2f712394 100644 --- a/arch/sparc/kernel/pci_sun4v.c +++ b/arch/sparc/kernel/pci_sun4v.c @@ -673,12 +673,14 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist, static int dma_4v_supported(struct device *dev, u64 device_mask) { struct iommu *iommu = dev->archdata.iommu; - u64 dma_addr_mask; + u64 dma_addr_mask = iommu->dma_addr_mask; - if (device_mask > DMA_BIT_MASK(32) && iommu->atu) - dma_addr_mask = iommu->atu->dma_addr_mask; - else - dma_addr_mask = iommu->dma_addr_mask; + if (device_mask > DMA_BIT_MASK(32)) { + if (iommu->atu) + dma_addr_mask = iommu->atu->dma_addr_mask; + else + return 0; + } if ((device_mask & dma_addr_mask) == dma_addr_mask) return 1; -- cgit v1.2.3-59-g8ed1b From 6409e84ec58fc4c0085d8921f8e01815dc871971 Mon Sep 17 00:00:00 2001 From: Artur Paszkiewicz Date: Tue, 11 Jul 2017 16:16:24 +0200 Subject: raid5-ppl: use BIOSET_NEED_BVECS when creating bioset This bioset is used for allocating bios with nr_iovecs > 0 so this flag must be set. Fixes: 011067b05668 ("blk: replace bioset_create_nobvec() with a flags arg to bioset_create()") Signed-off-by: Artur Paszkiewicz Signed-off-by: Shaohua Li --- drivers/md/raid5-ppl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index 77cce3573aa8..44ad5baf3206 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -1150,7 +1150,7 @@ int ppl_init_log(struct r5conf *conf) goto err; } - ppl_conf->bs = bioset_create(conf->raid_disks, 0, 0); + ppl_conf->bs = bioset_create(conf->raid_disks, 0, BIOSET_NEED_BVECS); if (!ppl_conf->bs) { ret = -ENOMEM; goto err; -- cgit v1.2.3-59-g8ed1b From fa43bc2a5a041c8935c1f6f5f8ab2d57efdd9644 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 12 Jul 2017 18:28:10 +0200 Subject: atyfb: hide unused variable The vdisplay variable is now only accessed inside of an #ifdef, producing a harmless warning: drivers/video/fbdev/aty/atyfb_base.c: In function 'aty_var_to_crtc': drivers/video/fbdev/aty/atyfb_base.c:805:19: error: unused variable 'vdisplay' [-Werror=unused-variable] This moves the declaration into the ifdef as well. Fixes: dd7d958ae912 ("video: fbdev: aty: remove useless variable assignments in aty_var_to_crtc()") Signed-off-by: Arnd Bergmann Cc: "Gustavo A. R. Silva" Signed-off-by: Bartlomiej Zolnierkiewicz --- drivers/video/fbdev/aty/atyfb_base.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c index 3142d7f7020f..b55fdac9c9f5 100644 --- a/drivers/video/fbdev/aty/atyfb_base.c +++ b/drivers/video/fbdev/aty/atyfb_base.c @@ -802,7 +802,7 @@ static int aty_var_to_crtc(const struct fb_info *info, { struct atyfb_par *par = (struct atyfb_par *) info->par; u32 xres, yres, vxres, vyres, xoffset, yoffset, bpp; - u32 sync, vmode, vdisplay; + u32 sync, vmode; u32 h_total, h_disp, h_sync_strt, h_sync_end, h_sync_dly, h_sync_wid, h_sync_pol; u32 v_total, v_disp, v_sync_strt, v_sync_end, v_sync_wid, v_sync_pol, c_sync; u32 pix_width, dp_pix_width, dp_chain_mask; @@ -1030,7 +1030,7 @@ static int aty_var_to_crtc(const struct fb_info *info, crtc->gen_cntl |= CRTC_INTERLACE_EN; #ifdef CONFIG_FB_ATY_GENERIC_LCD if (par->lcd_table != 0) { - vdisplay = yres; + u32 vdisplay = yres; if (vmode & FB_VMODE_DOUBLE) vdisplay <<= 1; crtc->gen_cntl &= ~(CRTC2_EN | CRTC2_PIX_WIDTH); -- cgit v1.2.3-59-g8ed1b From 4c99ceda0d067c06f228a27b6870f548d3218cc6 Mon Sep 17 00:00:00 2001 From: Benjamin Gaignard Date: Wed, 12 Jul 2017 18:28:11 +0200 Subject: fbdev: make get_fb_unmapped_area depends of !MMU MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Even if CONFIG_FB_PROVIDE_GET_FB_UNMAPPED_AREA flag is selected do not compile and use get_fb_unmapped_area() if CONFIG_MMU is also set. This will avoid mmap errors when compiling multi architectures at same time. Signed-off-by: Benjamin Gaignard Reviewed-by: Daniel Vetter Cc: Noralf Trønnes Cc: Emil Velikov Cc: Yannick Fertre Cc: Eric Engestrom Signed-off-by: Bartlomiej Zolnierkiewicz --- drivers/video/fbdev/core/fbmem.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index 069fe7960df1..f20c5d23483c 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1492,7 +1492,7 @@ __releases(&info->lock) return 0; } -#ifdef CONFIG_FB_PROVIDE_GET_FB_UNMAPPED_AREA +#if defined(CONFIG_FB_PROVIDE_GET_FB_UNMAPPED_AREA) && !defined(CONFIG_MMU) unsigned long get_fb_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) @@ -1519,7 +1519,8 @@ static const struct file_operations fb_fops = { .open = fb_open, .release = fb_release, #if defined(HAVE_ARCH_FB_UNMAPPED_AREA) || \ - defined(CONFIG_FB_PROVIDE_GET_FB_UNMAPPED_AREA) + (defined(CONFIG_FB_PROVIDE_GET_FB_UNMAPPED_AREA) && \ + !defined(CONFIG_MMU)) .get_unmapped_area = get_fb_unmapped_area, #endif #ifdef CONFIG_FB_DEFERRED_IO -- cgit v1.2.3-59-g8ed1b From 7cdc2d62f9cce8a02eb2a5fbfca6813f04189487 Mon Sep 17 00:00:00 2001 From: Jim Mattson Date: Thu, 6 Jul 2017 16:33:05 -0700 Subject: kvm: nVMX: Don't set vmcs12 to "launched" when VMLAUNCH fails The VMCS launch state is not set to "launched" unless the VMLAUNCH actually succeeds. VMLAUNCH failure includes VM-exits with bit 31 set. Note that this change does not address the general problem that a failure to launch/resume vmcs02 (i.e. vmx->fail) is not handled correctly. Signed-off-by: Jim Mattson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 7592a18ecc1c..ef978d5983ae 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -10435,8 +10435,6 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) return 1; } - vmcs12->launch_state = 1; - /* * Note no nested_vmx_succeed or nested_vmx_fail here. At this point * we are no longer running L1, and VMLAUNCH/VMRESUME has not yet @@ -10810,6 +10808,8 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); if (!(vmcs12->vm_exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) { + vmcs12->launch_state = 1; + /* vm_entry_intr_info_field is cleared on exit. Emulate this * instead of reading the real value. */ vmcs12->vm_entry_intr_info_field &= ~INTR_INFO_VALID_MASK; -- cgit v1.2.3-59-g8ed1b From 56a205100d3933f785ca970c58aecedd94ff90b2 Mon Sep 17 00:00:00 2001 From: Jim Mattson Date: Thu, 6 Jul 2017 16:33:06 -0700 Subject: kvm: nVMX: Validate the I/O bitmaps on nested VM-entry According to the SDM, if the "use I/O bitmaps" VM-execution control is 1, bits 11:0 of each I/O-bitmap address must be 0. Neither address should set any bits beyond the processor's physical-address width. Signed-off-by: Jim Mattson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index ef978d5983ae..22034ac4b5f2 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -9595,6 +9595,19 @@ static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu) ns_to_ktime(preemption_timeout), HRTIMER_MODE_REL); } +static int nested_vmx_check_io_bitmap_controls(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) + return 0; + + if (!page_address_valid(vcpu, vmcs12->io_bitmap_a) || + !page_address_valid(vcpu, vmcs12->io_bitmap_b)) + return -EINVAL; + + return 0; +} + static int nested_vmx_check_msr_bitmap_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { @@ -10299,6 +10312,9 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT) return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + if (nested_vmx_check_io_bitmap_controls(vcpu, vmcs12)) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + if (nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12)) return VMXERR_ENTRY_INVALID_CONTROL_FIELD; -- cgit v1.2.3-59-g8ed1b From 5fa99cbe7b666dce6dd8ac55b253778893b9c5df Mon Sep 17 00:00:00 2001 From: Jim Mattson Date: Thu, 6 Jul 2017 16:33:07 -0700 Subject: kvm: nVMX: Fix nested_vmx_check_msr_bitmap_controls Allow the L1 guest to specify the last page of addressable guest physical memory for an L2 MSR permission bitmap. Also remove the vmcs12_read_any() check that should never fail. Fixes: 3af18d9c5fe95 ("KVM: nVMX: Prepare for using hardware MSR bitmap") Signed-off-by: Jim Mattson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx.c | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 22034ac4b5f2..e02c7004b64b 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -4634,6 +4634,11 @@ static bool guest_state_valid(struct kvm_vcpu *vcpu) return true; } +static bool page_address_valid(struct kvm_vcpu *vcpu, gpa_t gpa) +{ + return PAGE_ALIGNED(gpa) && !(gpa >> cpuid_maxphyaddr(vcpu)); +} + static int init_rmode_tss(struct kvm *kvm) { gfn_t fn; @@ -9611,20 +9616,10 @@ static int nested_vmx_check_io_bitmap_controls(struct kvm_vcpu *vcpu, static int nested_vmx_check_msr_bitmap_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - int maxphyaddr; - u64 addr; - if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS)) return 0; - if (vmcs12_read_any(vcpu, MSR_BITMAP, &addr)) { - WARN_ON(1); - return -EINVAL; - } - maxphyaddr = cpuid_maxphyaddr(vcpu); - - if (!PAGE_ALIGNED(vmcs12->msr_bitmap) || - ((addr + PAGE_SIZE) >> maxphyaddr)) + if (!page_address_valid(vcpu, vmcs12->msr_bitmap)) return -EINVAL; return 0; -- cgit v1.2.3-59-g8ed1b From 85fd514e24238a633c971332aa96a2e5c4ddd502 Mon Sep 17 00:00:00 2001 From: Jim Mattson Date: Fri, 7 Jul 2017 12:51:41 -0700 Subject: kvm: nVMX: Shadow "high" parts of shadowed 64-bit VMCS fields Inconsistencies result from shadowing only accesses to the full 64-bits of a 64-bit VMCS field, but not shadowing accesses to the high 32-bits of the field. The "high" part of a 64-bit field should be shadowed whenever the full 64-bit field is shadowed. Signed-off-by: Jim Mattson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx.c | 60 +++++++++++++++++++++++++++++++----------------------- 1 file changed, 34 insertions(+), 26 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index e02c7004b64b..32db3f5dce7f 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3764,6 +3764,25 @@ static void free_kvm_area(void) } } +enum vmcs_field_type { + VMCS_FIELD_TYPE_U16 = 0, + VMCS_FIELD_TYPE_U64 = 1, + VMCS_FIELD_TYPE_U32 = 2, + VMCS_FIELD_TYPE_NATURAL_WIDTH = 3 +}; + +static inline int vmcs_field_type(unsigned long field) +{ + if (0x1 & field) /* the *_HIGH fields are all 32 bit */ + return VMCS_FIELD_TYPE_U32; + return (field >> 13) & 0x3 ; +} + +static inline int vmcs_field_readonly(unsigned long field) +{ + return (((field >> 10) & 0x3) == 1); +} + static void init_vmcs_shadow_fields(void) { int i, j; @@ -3789,14 +3808,22 @@ static void init_vmcs_shadow_fields(void) /* shadowed fields guest access without vmexit */ for (i = 0; i < max_shadow_read_write_fields; i++) { - clear_bit(shadow_read_write_fields[i], - vmx_vmwrite_bitmap); - clear_bit(shadow_read_write_fields[i], - vmx_vmread_bitmap); + unsigned long field = shadow_read_write_fields[i]; + + clear_bit(field, vmx_vmwrite_bitmap); + clear_bit(field, vmx_vmread_bitmap); + if (vmcs_field_type(field) == VMCS_FIELD_TYPE_U64) { + clear_bit(field + 1, vmx_vmwrite_bitmap); + clear_bit(field + 1, vmx_vmread_bitmap); + } + } + for (i = 0; i < max_shadow_read_only_fields; i++) { + unsigned long field = shadow_read_only_fields[i]; + + clear_bit(field, vmx_vmread_bitmap); + if (vmcs_field_type(field) == VMCS_FIELD_TYPE_U64) + clear_bit(field + 1, vmx_vmread_bitmap); } - for (i = 0; i < max_shadow_read_only_fields; i++) - clear_bit(shadow_read_only_fields[i], - vmx_vmread_bitmap); } static __init int alloc_kvm_area(void) @@ -7219,25 +7246,6 @@ static int handle_vmresume(struct kvm_vcpu *vcpu) return nested_vmx_run(vcpu, false); } -enum vmcs_field_type { - VMCS_FIELD_TYPE_U16 = 0, - VMCS_FIELD_TYPE_U64 = 1, - VMCS_FIELD_TYPE_U32 = 2, - VMCS_FIELD_TYPE_NATURAL_WIDTH = 3 -}; - -static inline int vmcs_field_type(unsigned long field) -{ - if (0x1 & field) /* the *_HIGH fields are all 32 bit */ - return VMCS_FIELD_TYPE_U32; - return (field >> 13) & 0x3 ; -} - -static inline int vmcs_field_readonly(unsigned long field) -{ - return (((field >> 10) & 0x3) == 1); -} - /* * Read a vmcs12 field. Since these can have varying lengths and we return * one type, we chose the biggest type (u64) and zero-extend the return value -- cgit v1.2.3-59-g8ed1b From b9091b1c654953cc9615f282704a6df8e31549cf Mon Sep 17 00:00:00 2001 From: "Subhransu S. Prusty" Date: Wed, 12 Jul 2017 20:12:04 +0530 Subject: ALSA: hda - Add hdmi id for a Geminilake variant Few GLK platform variants report a different vendor id. Add it. Also add the missing check for GLK in is_haswell_plus(). Signed-off-by: Subhransu S. Prusty Acked-by: Vinod Koul Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_hdmi.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 76c85f08bea6..d549f35f39d3 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -53,9 +53,11 @@ MODULE_PARM_DESC(static_hdmi_pcm, "Don't restrict PCM parameters per ELD info"); #define is_skylake(codec) ((codec)->core.vendor_id == 0x80862809) #define is_broxton(codec) ((codec)->core.vendor_id == 0x8086280a) #define is_kabylake(codec) ((codec)->core.vendor_id == 0x8086280b) +#define is_geminilake(codec) (((codec)->core.vendor_id == 0x8086280d) || \ + ((codec)->core.vendor_id == 0x80862800)) #define is_haswell_plus(codec) (is_haswell(codec) || is_broadwell(codec) \ || is_skylake(codec) || is_broxton(codec) \ - || is_kabylake(codec)) + || is_kabylake(codec)) || is_geminilake(codec) #define is_valleyview(codec) ((codec)->core.vendor_id == 0x80862882) #define is_cherryview(codec) ((codec)->core.vendor_id == 0x80862883) @@ -3790,6 +3792,7 @@ HDA_CODEC_ENTRY(0x80862809, "Skylake HDMI", patch_i915_hsw_hdmi), HDA_CODEC_ENTRY(0x8086280a, "Broxton HDMI", patch_i915_hsw_hdmi), HDA_CODEC_ENTRY(0x8086280b, "Kabylake HDMI", patch_i915_hsw_hdmi), HDA_CODEC_ENTRY(0x8086280d, "Geminilake HDMI", patch_i915_glk_hdmi), +HDA_CODEC_ENTRY(0x80862800, "Geminilake HDMI", patch_i915_glk_hdmi), HDA_CODEC_ENTRY(0x80862880, "CedarTrail HDMI", patch_generic_hdmi), HDA_CODEC_ENTRY(0x80862882, "Valleyview2 HDMI", patch_i915_byt_hdmi), HDA_CODEC_ENTRY(0x80862883, "Braswell HDMI", patch_i915_byt_hdmi), -- cgit v1.2.3-59-g8ed1b From 34d5ac2af644a10958e144b7bb937d289dfd158d Mon Sep 17 00:00:00 2001 From: Shawn Lin Date: Tue, 11 Jul 2017 18:15:08 +0800 Subject: PCI: rockchip: Check for pci_scan_root_bus_bridge() failure correctly pci_scan_root_bus_bridge() returns zero for success, or a negative errno. A typo in ae13cb9b1926 ("PCI: rockchip: Convert PCI scan API to pci_scan_root_bus_bridge()") treated zero as a failure. Fix the typo. Fixes: ae13cb9b1926 ("PCI: rockchip: Convert PCI scan API to pci_scan_root_bus_bridge()") Signed-off-by: Shawn Lin [bhelgaas: changelog] Signed-off-by: Bjorn Helgaas Acked-by: Lorenzo Pieralisi --- drivers/pci/host/pcie-rockchip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/host/pcie-rockchip.c b/drivers/pci/host/pcie-rockchip.c index 5acf8694fb23..7bb9870f6d8c 100644 --- a/drivers/pci/host/pcie-rockchip.c +++ b/drivers/pci/host/pcie-rockchip.c @@ -1483,7 +1483,7 @@ static int rockchip_pcie_probe(struct platform_device *pdev) bridge->swizzle_irq = pci_common_swizzle; err = pci_scan_root_bus_bridge(bridge); - if (!err) + if (err < 0) goto err_free_res; bus = bridge->bus; -- cgit v1.2.3-59-g8ed1b From 340d394a789518018f834ff70f7534fc463d3226 Mon Sep 17 00:00:00 2001 From: Chen Hong Date: Sun, 2 Jul 2017 15:11:10 -0700 Subject: Input: i8042 - fix crash at boot time The driver checks port->exists twice in i8042_interrupt(), first when trying to assign temporary "serio" variable, and second time when deciding whether it should call serio_interrupt(). The value of port->exists may change between the 2 checks, and we may end up calling serio_interrupt() with a NULL pointer: BUG: unable to handle kernel NULL pointer dereference at 0000000000000050 IP: [] _spin_lock_irqsave+0x1f/0x40 PGD 0 Oops: 0002 [#1] SMP last sysfs file: CPU 0 Modules linked in: Pid: 1, comm: swapper Not tainted 2.6.32-358.el6.x86_64 #1 QEMU Standard PC (i440FX + PIIX, 1996) RIP: 0010:[] [] _spin_lock_irqsave+0x1f/0x40 RSP: 0018:ffff880028203cc0 EFLAGS: 00010082 RAX: 0000000000010000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000282 RSI: 0000000000000098 RDI: 0000000000000050 RBP: ffff880028203cc0 R08: ffff88013e79c000 R09: ffff880028203ee0 R10: 0000000000000298 R11: 0000000000000282 R12: 0000000000000050 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000098 FS: 0000000000000000(0000) GS:ffff880028200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b CR2: 0000000000000050 CR3: 0000000001a85000 CR4: 00000000001407f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process swapper (pid: 1, threadinfo ffff88013e79c000, task ffff88013e79b500) Stack: ffff880028203d00 ffffffff813de186 ffffffffffffff02 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000098 ffff880028203d70 ffffffff813e0162 ffff880028203d20 ffffffff8103b8ac Call Trace: [] serio_interrupt+0x36/0xa0 [] i8042_interrupt+0x132/0x3a0 [] ? kvm_clock_read+0x1c/0x20 [] ? kvm_clock_get_cycles+0x9/0x10 [] handle_IRQ_event+0x60/0x170 [] ? kvm_guest_apic_eoi_write+0x44/0x50 [] handle_edge_irq+0xde/0x180 [] handle_irq+0x49/0xa0 [] do_IRQ+0x6c/0xf0 [] ret_from_intr+0x0/0x11 [] ? __do_softirq+0x73/0x1e0 [] ? hrtimer_interrupt+0x14b/0x260 [] ? call_softirq+0x1c/0x30 [] ? do_softirq+0x65/0xa0 [] ? irq_exit+0x85/0x90 [] ? smp_apic_timer_interrupt+0x70/0x9b [] ? apic_timer_interrupt+0x13/0x20 To avoid the issue let's change the second check to test whether serio is NULL or not. Also, let's take i8042_lock in i8042_start() and i8042_stop() instead of trying to be overly smart and using memory barriers. Signed-off-by: Chen Hong [dtor: take lock in i8042_start()/i8042_stop()] Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov --- drivers/input/serio/i8042.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index c52da651269b..824f4c1c1f31 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -436,8 +436,10 @@ static int i8042_start(struct serio *serio) { struct i8042_port *port = serio->port_data; + spin_lock_irq(&i8042_lock); port->exists = true; - mb(); + spin_unlock_irq(&i8042_lock); + return 0; } @@ -450,16 +452,20 @@ static void i8042_stop(struct serio *serio) { struct i8042_port *port = serio->port_data; + spin_lock_irq(&i8042_lock); port->exists = false; + port->serio = NULL; + spin_unlock_irq(&i8042_lock); /* + * We need to make sure that interrupt handler finishes using + * our serio port before we return from this function. * We synchronize with both AUX and KBD IRQs because there is * a (very unlikely) chance that AUX IRQ is raised for KBD port * and vice versa. */ synchronize_irq(I8042_AUX_IRQ); synchronize_irq(I8042_KBD_IRQ); - port->serio = NULL; } /* @@ -576,7 +582,7 @@ static irqreturn_t i8042_interrupt(int irq, void *dev_id) spin_unlock_irqrestore(&i8042_lock, flags); - if (likely(port->exists && !filtered)) + if (likely(serio && !filtered)) serio_interrupt(serio, data, dfl); out: -- cgit v1.2.3-59-g8ed1b From 8c6ae4980e70395cbdfdf605c29673c5a6a89d9a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 30 Jun 2017 12:03:54 -0400 Subject: sunrpc: Allocate up to RPCSVC_MAXPAGES per svc_rqst svcrdma needs 259 pages allocated to receive 1MB NFSv4.0 WRITE requests: - 1 page for the transport header and head iovec - 256 pages for the data payload - 1 page for the trailing GETATTR request (since NFSD XDR decoding does not look for a tail iovec, the GETATTR is stuck at the end of the rqstp->rq_arg.pages list) - 1 page for building the reply xdr_buf But RPCSVC_MAXPAGES is already 259 (on x86_64). The problem is that svc_alloc_arg never allocates that many pages. To address this: 1. The final element of rq_pages always points to NULL. To accommodate up to 259 pages in rq_pages, add an extra element to rq_pages for the array termination sentinel. 2. Adjust the calculation of "pages" to match how RPCSVC_MAXPAGES is calculated, so it can go up to 259. Bruce noted that the calculation assumes sv_max_mesg is a multiple of PAGE_SIZE, which might not always be true. I didn't change this assumption. 3. Change the loop boundaries to allow 259 pages to be allocated. Additional clean-up: WARN_ON_ONCE adds an extra conditional branch, which is basically never taken. And there's no need to dump the stack here because svc_alloc_arg has only one caller. Keeping that NULL "array termination sentinel"; there doesn't appear to be any code that depends on it, only code in nfsd_splice_actor() which needs the 259th element to be initialized to *something*. So it's possible we could just keep the array at 259 elements and drop that final NULL, but we're being conservative for now. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 2 +- net/sunrpc/svc_xprt.c | 10 ++++++---- 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index eec04982a7ea..a3f8af9bd543 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -246,7 +246,7 @@ struct svc_rqst { size_t rq_xprt_hlen; /* xprt header len */ struct xdr_buf rq_arg; struct xdr_buf rq_res; - struct page * rq_pages[RPCSVC_MAXPAGES]; + struct page *rq_pages[RPCSVC_MAXPAGES + 1]; struct page * *rq_respages; /* points into rq_pages */ struct page * *rq_next_page; /* next reply page to use */ struct page * *rq_page_end; /* one past the last page */ diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 7bfe1fb42add..d16a8b423c20 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -659,11 +659,13 @@ static int svc_alloc_arg(struct svc_rqst *rqstp) int i; /* now allocate needed pages. If we get a failure, sleep briefly */ - pages = (serv->sv_max_mesg + PAGE_SIZE) / PAGE_SIZE; - WARN_ON_ONCE(pages >= RPCSVC_MAXPAGES); - if (pages >= RPCSVC_MAXPAGES) + pages = (serv->sv_max_mesg + 2 * PAGE_SIZE) >> PAGE_SHIFT; + if (pages > RPCSVC_MAXPAGES) { + pr_warn_once("svc: warning: pages=%u > RPCSVC_MAXPAGES=%lu\n", + pages, RPCSVC_MAXPAGES); /* use as many pages as possible */ - pages = RPCSVC_MAXPAGES - 1; + pages = RPCSVC_MAXPAGES; + } for (i = 0; i < pages ; i++) while (rqstp->rq_pages[i] == NULL) { struct page *p = alloc_page(GFP_KERNEL); -- cgit v1.2.3-59-g8ed1b From 026d958b38c628a1b4ced534808945365e2747a5 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 23 Jun 2017 17:18:24 -0400 Subject: svcrdma: Add recvfrom helpers to svc_rdma_rw.c svc_rdma_rw.c already contains helpers for the sendto path. Introduce helpers for the recvfrom path. The plan is to replace the local NFSD bespoke code that constructs and posts RDMA Read Work Requests with calls to the rdma_rw API. This shares code with other RDMA-enabled ULPs that manages the gory details of buffer registration and posting Work Requests. This new code also puts all RDMA_NOMSG-specific logic in one place. Lastly, the use of rqstp->rq_arg.pages is deprecated in favor of using rqstp->rq_pages directly, for clarity. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 3 + net/sunrpc/xprtrdma/svc_rdma_rw.c | 425 +++++++++++++++++++++++++++++++++++++- 2 files changed, 427 insertions(+), 1 deletion(-) diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 3ca991657889..cf5d5412298b 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -196,6 +196,9 @@ extern int rdma_read_chunk_frmr(struct svcxprt_rdma *, struct svc_rqst *, /* svc_rdma_rw.c */ extern void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma); +extern int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, + struct svc_rqst *rqstp, + struct svc_rdma_op_ctxt *head, __be32 *p); extern int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, __be32 *wr_ch, struct xdr_buf *xdr); extern int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma, diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index 3b35364d9a6b..77d38a4b8d99 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -12,6 +12,9 @@ #define RPCDBG_FACILITY RPCDBG_SVCXPRT +static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc); +static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc); + /* Each R/W context contains state for one chain of RDMA Read or * Write Work Requests. * @@ -177,6 +180,7 @@ svc_rdma_write_info_alloc(struct svcxprt_rdma *rdma, __be32 *chunk) info->wi_nsegs = be32_to_cpup(++chunk); info->wi_segs = ++chunk; svc_rdma_cc_init(rdma, &info->wi_cc, DMA_TO_DEVICE); + info->wi_cc.cc_cqe.done = svc_rdma_write_done; return info; } @@ -216,6 +220,76 @@ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc) svc_rdma_write_info_free(info); } +/* State for pulling a Read chunk. + */ +struct svc_rdma_read_info { + struct svc_rdma_op_ctxt *ri_readctxt; + unsigned int ri_position; + unsigned int ri_pageno; + unsigned int ri_pageoff; + unsigned int ri_chunklen; + + struct svc_rdma_chunk_ctxt ri_cc; +}; + +static struct svc_rdma_read_info * +svc_rdma_read_info_alloc(struct svcxprt_rdma *rdma) +{ + struct svc_rdma_read_info *info; + + info = kmalloc(sizeof(*info), GFP_KERNEL); + if (!info) + return info; + + svc_rdma_cc_init(rdma, &info->ri_cc, DMA_FROM_DEVICE); + info->ri_cc.cc_cqe.done = svc_rdma_wc_read_done; + return info; +} + +static void svc_rdma_read_info_free(struct svc_rdma_read_info *info) +{ + svc_rdma_cc_release(&info->ri_cc); + kfree(info); +} + +/** + * svc_rdma_wc_read_done - Handle completion of an RDMA Read ctx + * @cq: controlling Completion Queue + * @wc: Work Completion + * + */ +static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc) +{ + struct ib_cqe *cqe = wc->wr_cqe; + struct svc_rdma_chunk_ctxt *cc = + container_of(cqe, struct svc_rdma_chunk_ctxt, cc_cqe); + struct svcxprt_rdma *rdma = cc->cc_rdma; + struct svc_rdma_read_info *info = + container_of(cc, struct svc_rdma_read_info, ri_cc); + + atomic_add(cc->cc_sqecount, &rdma->sc_sq_avail); + wake_up(&rdma->sc_send_wait); + + if (unlikely(wc->status != IB_WC_SUCCESS)) { + set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags); + if (wc->status != IB_WC_WR_FLUSH_ERR) + pr_err("svcrdma: read ctx: %s (%u/0x%x)\n", + ib_wc_status_msg(wc->status), + wc->status, wc->vendor_err); + svc_rdma_put_context(info->ri_readctxt, 1); + } else { + spin_lock(&rdma->sc_rq_dto_lock); + list_add_tail(&info->ri_readctxt->list, + &rdma->sc_read_complete_q); + spin_unlock(&rdma->sc_rq_dto_lock); + + set_bit(XPT_DATA, &rdma->sc_xprt.xpt_flags); + svc_xprt_enqueue(&rdma->sc_xprt); + } + + svc_rdma_read_info_free(info); +} + /* This function sleeps when the transport's Send Queue is congested. * * Assumptions: @@ -335,7 +409,6 @@ svc_rdma_build_writes(struct svc_rdma_write_info *info, __be32 *seg; int ret; - cc->cc_cqe.done = svc_rdma_write_done; seg = info->wi_segs + info->wi_seg_no * rpcrdma_segment_maxsz; do { unsigned int write_len; @@ -515,3 +588,353 @@ out_err: svc_rdma_write_info_free(info); return ret; } + +static int svc_rdma_build_read_segment(struct svc_rdma_read_info *info, + struct svc_rqst *rqstp, + u32 rkey, u32 len, u64 offset) +{ + struct svc_rdma_op_ctxt *head = info->ri_readctxt; + struct svc_rdma_chunk_ctxt *cc = &info->ri_cc; + struct svc_rdma_rw_ctxt *ctxt; + unsigned int sge_no, seg_len; + struct scatterlist *sg; + int ret; + + sge_no = PAGE_ALIGN(info->ri_pageoff + len) >> PAGE_SHIFT; + ctxt = svc_rdma_get_rw_ctxt(cc->cc_rdma, sge_no); + if (!ctxt) + goto out_noctx; + ctxt->rw_nents = sge_no; + + dprintk("svcrdma: reading segment %u@0x%016llx:0x%08x (%u sges)\n", + len, offset, rkey, sge_no); + + sg = ctxt->rw_sg_table.sgl; + for (sge_no = 0; sge_no < ctxt->rw_nents; sge_no++) { + seg_len = min_t(unsigned int, len, + PAGE_SIZE - info->ri_pageoff); + + head->arg.pages[info->ri_pageno] = + rqstp->rq_pages[info->ri_pageno]; + if (!info->ri_pageoff) + head->count++; + + sg_set_page(sg, rqstp->rq_pages[info->ri_pageno], + seg_len, info->ri_pageoff); + sg = sg_next(sg); + + info->ri_pageoff += seg_len; + if (info->ri_pageoff == PAGE_SIZE) { + info->ri_pageno++; + info->ri_pageoff = 0; + } + len -= seg_len; + + /* Safety check */ + if (len && + &rqstp->rq_pages[info->ri_pageno + 1] > rqstp->rq_page_end) + goto out_overrun; + } + + ret = rdma_rw_ctx_init(&ctxt->rw_ctx, cc->cc_rdma->sc_qp, + cc->cc_rdma->sc_port_num, + ctxt->rw_sg_table.sgl, ctxt->rw_nents, + 0, offset, rkey, DMA_FROM_DEVICE); + if (ret < 0) + goto out_initerr; + + list_add(&ctxt->rw_list, &cc->cc_rwctxts); + cc->cc_sqecount += ret; + return 0; + +out_noctx: + dprintk("svcrdma: no R/W ctxs available\n"); + return -ENOMEM; + +out_overrun: + dprintk("svcrdma: request overruns rq_pages\n"); + return -EINVAL; + +out_initerr: + svc_rdma_put_rw_ctxt(cc->cc_rdma, ctxt); + pr_err("svcrdma: failed to map pagelist (%d)\n", ret); + return -EIO; +} + +static int svc_rdma_build_read_chunk(struct svc_rqst *rqstp, + struct svc_rdma_read_info *info, + __be32 *p) +{ + int ret; + + info->ri_chunklen = 0; + while (*p++ != xdr_zero) { + u32 rs_handle, rs_length; + u64 rs_offset; + + if (be32_to_cpup(p++) != info->ri_position) + break; + rs_handle = be32_to_cpup(p++); + rs_length = be32_to_cpup(p++); + p = xdr_decode_hyper(p, &rs_offset); + + ret = svc_rdma_build_read_segment(info, rqstp, + rs_handle, rs_length, + rs_offset); + if (ret < 0) + break; + + info->ri_chunklen += rs_length; + } + + return ret; +} + +/* If there is inline content following the Read chunk, append it to + * the page list immediately following the data payload. This has to + * be done after the reader function has determined how many pages + * were consumed for RDMA Read. + * + * On entry, ri_pageno and ri_pageoff point directly to the end of the + * page list. On exit, both have been updated to the new "next byte". + * + * Assumptions: + * - Inline content fits entirely in rq_pages[0] + * - Trailing content is only a handful of bytes + */ +static int svc_rdma_copy_tail(struct svc_rqst *rqstp, + struct svc_rdma_read_info *info) +{ + struct svc_rdma_op_ctxt *head = info->ri_readctxt; + unsigned int tail_length, remaining; + u8 *srcp, *destp; + + /* Assert that all inline content fits in page 0. This is an + * implementation limit, not a protocol limit. + */ + if (head->arg.head[0].iov_len > PAGE_SIZE) { + pr_warn_once("svcrdma: too much trailing inline content\n"); + return -EINVAL; + } + + srcp = head->arg.head[0].iov_base; + srcp += info->ri_position; + tail_length = head->arg.head[0].iov_len - info->ri_position; + remaining = tail_length; + + /* If there is room on the last page in the page list, try to + * fit the trailing content there. + */ + if (info->ri_pageoff > 0) { + unsigned int len; + + len = min_t(unsigned int, remaining, + PAGE_SIZE - info->ri_pageoff); + destp = page_address(rqstp->rq_pages[info->ri_pageno]); + destp += info->ri_pageoff; + + memcpy(destp, srcp, len); + srcp += len; + destp += len; + info->ri_pageoff += len; + remaining -= len; + + if (info->ri_pageoff == PAGE_SIZE) { + info->ri_pageno++; + info->ri_pageoff = 0; + } + } + + /* Otherwise, a fresh page is needed. */ + if (remaining) { + head->arg.pages[info->ri_pageno] = + rqstp->rq_pages[info->ri_pageno]; + head->count++; + + destp = page_address(rqstp->rq_pages[info->ri_pageno]); + memcpy(destp, srcp, remaining); + info->ri_pageoff += remaining; + } + + head->arg.page_len += tail_length; + head->arg.len += tail_length; + head->arg.buflen += tail_length; + return 0; +} + +/* Construct RDMA Reads to pull over a normal Read chunk. The chunk + * data lands in the page list of head->arg.pages. + * + * Currently NFSD does not look at the head->arg.tail[0] iovec. + * Therefore, XDR round-up of the Read chunk and trailing + * inline content must both be added at the end of the pagelist. + */ +static int svc_rdma_build_normal_read_chunk(struct svc_rqst *rqstp, + struct svc_rdma_read_info *info, + __be32 *p) +{ + struct svc_rdma_op_ctxt *head = info->ri_readctxt; + int ret; + + dprintk("svcrdma: Reading Read chunk at position %u\n", + info->ri_position); + + info->ri_pageno = head->hdr_count; + info->ri_pageoff = 0; + + ret = svc_rdma_build_read_chunk(rqstp, info, p); + if (ret < 0) + goto out; + + /* Read chunk may need XDR round-up (see RFC 5666, s. 3.7). + */ + if (info->ri_chunklen & 3) { + u32 padlen = 4 - (info->ri_chunklen & 3); + + info->ri_chunklen += padlen; + + /* NB: data payload always starts on XDR alignment, + * thus the pad can never contain a page boundary. + */ + info->ri_pageoff += padlen; + if (info->ri_pageoff == PAGE_SIZE) { + info->ri_pageno++; + info->ri_pageoff = 0; + } + } + + head->arg.page_len = info->ri_chunklen; + head->arg.len += info->ri_chunklen; + head->arg.buflen += info->ri_chunklen; + + if (info->ri_position < head->arg.head[0].iov_len) { + ret = svc_rdma_copy_tail(rqstp, info); + if (ret < 0) + goto out; + } + head->arg.head[0].iov_len = info->ri_position; + +out: + return ret; +} + +/* Construct RDMA Reads to pull over a Position Zero Read chunk. + * The start of the data lands in the first page just after + * the Transport header, and the rest lands in the page list of + * head->arg.pages. + * + * Assumptions: + * - A PZRC has an XDR-aligned length (no implicit round-up). + * - There can be no trailing inline content (IOW, we assume + * a PZRC is never sent in an RDMA_MSG message, though it's + * allowed by spec). + */ +static int svc_rdma_build_pz_read_chunk(struct svc_rqst *rqstp, + struct svc_rdma_read_info *info, + __be32 *p) +{ + struct svc_rdma_op_ctxt *head = info->ri_readctxt; + int ret; + + dprintk("svcrdma: Reading Position Zero Read chunk\n"); + + info->ri_pageno = head->hdr_count - 1; + info->ri_pageoff = offset_in_page(head->byte_len); + + ret = svc_rdma_build_read_chunk(rqstp, info, p); + if (ret < 0) + goto out; + + head->arg.len += info->ri_chunklen; + head->arg.buflen += info->ri_chunklen; + + if (head->arg.len <= head->sge[0].length) { + /* Transport header and RPC message fit entirely + * in page where head iovec resides. + */ + head->arg.head[0].iov_len = info->ri_chunklen; + } else { + /* Transport header and part of RPC message reside + * in the head iovec's page. + */ + head->arg.head[0].iov_len = + head->sge[0].length - head->byte_len; + head->arg.page_len = + info->ri_chunklen - head->arg.head[0].iov_len; + } + +out: + return ret; +} + +/** + * svc_rdma_recv_read_chunk - Pull a Read chunk from the client + * @rdma: controlling RDMA transport + * @rqstp: set of pages to use as Read sink buffers + * @head: pages under I/O collect here + * @p: pointer to start of Read chunk + * + * Returns: + * %0 if all needed RDMA Reads were posted successfully, + * %-EINVAL if client provided too many segments, + * %-ENOMEM if rdma_rw context pool was exhausted, + * %-ENOTCONN if posting failed (connection is lost), + * %-EIO if rdma_rw initialization failed (DMA mapping, etc). + * + * Assumptions: + * - All Read segments in @p have the same Position value. + */ +int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, struct svc_rqst *rqstp, + struct svc_rdma_op_ctxt *head, __be32 *p) +{ + struct svc_rdma_read_info *info; + struct page **page; + int ret; + + /* The request (with page list) is constructed in + * head->arg. Pages involved with RDMA Read I/O are + * transferred there. + */ + head->hdr_count = head->count; + head->arg.head[0] = rqstp->rq_arg.head[0]; + head->arg.tail[0] = rqstp->rq_arg.tail[0]; + head->arg.pages = head->pages; + head->arg.page_base = 0; + head->arg.page_len = 0; + head->arg.len = rqstp->rq_arg.len; + head->arg.buflen = rqstp->rq_arg.buflen; + + info = svc_rdma_read_info_alloc(rdma); + if (!info) + return -ENOMEM; + info->ri_readctxt = head; + + info->ri_position = be32_to_cpup(p + 1); + if (info->ri_position) + ret = svc_rdma_build_normal_read_chunk(rqstp, info, p); + else + ret = svc_rdma_build_pz_read_chunk(rqstp, info, p); + + /* Mark the start of the pages that can be used for the reply */ + if (info->ri_pageoff > 0) + info->ri_pageno++; + rqstp->rq_respages = &rqstp->rq_pages[info->ri_pageno]; + rqstp->rq_next_page = rqstp->rq_respages + 1; + + if (ret < 0) + goto out; + + ret = svc_rdma_post_chunk_ctxt(&info->ri_cc); + +out: + /* Read sink pages have been moved from rqstp->rq_pages to + * head->arg.pages. Force svc_recv to refill those slots + * in rq_pages. + */ + for (page = rqstp->rq_pages; page < rqstp->rq_respages; page++) + *page = NULL; + + if (ret < 0) + svc_rdma_read_info_free(info); + return ret; +} -- cgit v1.2.3-59-g8ed1b From cafc739892f34b9090413179ca259409fc43bfae Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 23 Jun 2017 17:18:33 -0400 Subject: svcrdma: Use generic RDMA R/W API in RPC Call path The current svcrdma recvfrom code path has a lot of detail about registration mode and the type of port (iWARP, IB, etc). Instead, use the RDMA core's generic R/W API. This shares code with other RDMA-enabled ULPs that manages the gory details of buffer registration and the posting of RDMA Read Work Requests. Since the Read list marshaling code is being replaced, I took the opportunity to replace C structure-based XDR encoding code with more portable code that uses pointer arithmetic. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 14 - net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 547 ++++++------------------------- net/sunrpc/xprtrdma/svc_rdma_transport.c | 13 - 3 files changed, 106 insertions(+), 468 deletions(-) diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index cf5d5412298b..b1ba19ba1071 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -82,10 +82,7 @@ struct svc_rdma_op_ctxt { int hdr_count; struct xdr_buf arg; struct ib_cqe cqe; - struct ib_cqe reg_cqe; - struct ib_cqe inv_cqe; u32 byte_len; - u32 position; struct svcxprt_rdma *xprt; unsigned long flags; enum dma_data_direction direction; @@ -116,7 +113,6 @@ struct svcxprt_rdma { struct list_head sc_accept_q; /* Conn. waiting accept */ int sc_ord; /* RDMA read limit */ int sc_max_sge; - int sc_max_sge_rd; /* max sge for read target */ bool sc_snd_w_inv; /* OK to use Send With Invalidate */ atomic_t sc_sq_avail; /* SQEs ready to be consumed */ @@ -141,10 +137,6 @@ struct svcxprt_rdma { struct ib_qp *sc_qp; struct ib_cq *sc_rq_cq; struct ib_cq *sc_sq_cq; - int (*sc_reader)(struct svcxprt_rdma *, - struct svc_rqst *, - struct svc_rdma_op_ctxt *, - int *, u32 *, u32, u32, u64, bool); u32 sc_dev_caps; /* distilled device caps */ unsigned int sc_frmr_pg_list_len; struct list_head sc_frmr_q; @@ -187,12 +179,6 @@ extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, /* svc_rdma_recvfrom.c */ extern int svc_rdma_recvfrom(struct svc_rqst *); -extern int rdma_read_chunk_lcl(struct svcxprt_rdma *, struct svc_rqst *, - struct svc_rdma_op_ctxt *, int *, u32 *, - u32, u32, u64, bool); -extern int rdma_read_chunk_frmr(struct svcxprt_rdma *, struct svc_rqst *, - struct svc_rdma_op_ctxt *, int *, u32 *, - u32, u32, u64, bool); /* svc_rdma_rw.c */ extern void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma); diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 1452bd02d857..5fbcb73dd68d 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -41,13 +41,66 @@ * Author: Tom Tucker */ -#include -#include -#include -#include +/* Operation + * + * The main entry point is svc_rdma_recvfrom. This is called from + * svc_recv when the transport indicates there is incoming data to + * be read. "Data Ready" is signaled when an RDMA Receive completes, + * or when a set of RDMA Reads complete. + * + * An svc_rqst is passed in. This structure contains an array of + * free pages (rq_pages) that will contain the incoming RPC message. + * + * Short messages are moved directly into svc_rqst::rq_arg, and + * the RPC Call is ready to be processed by the Upper Layer. + * svc_rdma_recvfrom returns the length of the RPC Call message, + * completing the reception of the RPC Call. + * + * However, when an incoming message has Read chunks, + * svc_rdma_recvfrom must post RDMA Reads to pull the RPC Call's + * data payload from the client. svc_rdma_recvfrom sets up the + * RDMA Reads using pages in svc_rqst::rq_pages, which are + * transferred to an svc_rdma_op_ctxt for the duration of the + * I/O. svc_rdma_recvfrom then returns zero, since the RPC message + * is still not yet ready. + * + * When the Read chunk payloads have become available on the + * server, "Data Ready" is raised again, and svc_recv calls + * svc_rdma_recvfrom again. This second call may use a different + * svc_rqst than the first one, thus any information that needs + * to be preserved across these two calls is kept in an + * svc_rdma_op_ctxt. + * + * The second call to svc_rdma_recvfrom performs final assembly + * of the RPC Call message, using the RDMA Read sink pages kept in + * the svc_rdma_op_ctxt. The xdr_buf is copied from the + * svc_rdma_op_ctxt to the second svc_rqst. The second call returns + * the length of the completed RPC Call message. + * + * Page Management + * + * Pages under I/O must be transferred from the first svc_rqst to an + * svc_rdma_op_ctxt before the first svc_rdma_recvfrom call returns. + * + * The first svc_rqst supplies pages for RDMA Reads. These are moved + * from rqstp::rq_pages into ctxt::pages. The consumed elements of + * the rq_pages array are set to NULL and refilled with the first + * svc_rdma_recvfrom call returns. + * + * During the second svc_rdma_recvfrom call, RDMA Read sink pages + * are transferred from the svc_rdma_op_ctxt to the second svc_rqst + * (see rdma_read_complete() below). + */ + #include #include #include + +#include + +#include +#include +#include #include #define RPCDBG_FACILITY RPCDBG_SVCXPRT @@ -61,7 +114,6 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp, struct svc_rdma_op_ctxt *ctxt, u32 byte_count) { - struct rpcrdma_msg *rmsgp; struct page *page; u32 bc; int sge_no; @@ -85,13 +137,6 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp, rqstp->rq_arg.page_len = bc; rqstp->rq_arg.page_base = 0; - /* RDMA_NOMSG: RDMA READ data should land just after RDMA RECV data */ - rmsgp = (struct rpcrdma_msg *)rqstp->rq_arg.head[0].iov_base; - if (rmsgp->rm_type == rdma_nomsg) - rqstp->rq_arg.pages = &rqstp->rq_pages[0]; - else - rqstp->rq_arg.pages = &rqstp->rq_pages[1]; - sge_no = 1; while (bc && sge_no < ctxt->count) { page = ctxt->pages[sge_no]; @@ -320,395 +365,6 @@ out_inval: return -EINVAL; } -/* Issue an RDMA_READ using the local lkey to map the data sink */ -int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt, - struct svc_rqst *rqstp, - struct svc_rdma_op_ctxt *head, - int *page_no, - u32 *page_offset, - u32 rs_handle, - u32 rs_length, - u64 rs_offset, - bool last) -{ - struct ib_rdma_wr read_wr; - int pages_needed = PAGE_ALIGN(*page_offset + rs_length) >> PAGE_SHIFT; - struct svc_rdma_op_ctxt *ctxt = svc_rdma_get_context(xprt); - int ret, read, pno; - u32 pg_off = *page_offset; - u32 pg_no = *page_no; - - ctxt->direction = DMA_FROM_DEVICE; - ctxt->read_hdr = head; - pages_needed = min_t(int, pages_needed, xprt->sc_max_sge_rd); - read = min_t(int, (pages_needed << PAGE_SHIFT) - *page_offset, - rs_length); - - for (pno = 0; pno < pages_needed; pno++) { - int len = min_t(int, rs_length, PAGE_SIZE - pg_off); - - head->arg.pages[pg_no] = rqstp->rq_arg.pages[pg_no]; - head->arg.page_len += len; - - head->arg.len += len; - if (!pg_off) - head->count++; - rqstp->rq_respages = &rqstp->rq_arg.pages[pg_no+1]; - rqstp->rq_next_page = rqstp->rq_respages + 1; - ctxt->sge[pno].addr = - ib_dma_map_page(xprt->sc_cm_id->device, - head->arg.pages[pg_no], pg_off, - PAGE_SIZE - pg_off, - DMA_FROM_DEVICE); - ret = ib_dma_mapping_error(xprt->sc_cm_id->device, - ctxt->sge[pno].addr); - if (ret) - goto err; - svc_rdma_count_mappings(xprt, ctxt); - - ctxt->sge[pno].lkey = xprt->sc_pd->local_dma_lkey; - ctxt->sge[pno].length = len; - ctxt->count++; - - /* adjust offset and wrap to next page if needed */ - pg_off += len; - if (pg_off == PAGE_SIZE) { - pg_off = 0; - pg_no++; - } - rs_length -= len; - } - - if (last && rs_length == 0) - set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags); - else - clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags); - - memset(&read_wr, 0, sizeof(read_wr)); - ctxt->cqe.done = svc_rdma_wc_read; - read_wr.wr.wr_cqe = &ctxt->cqe; - read_wr.wr.opcode = IB_WR_RDMA_READ; - read_wr.wr.send_flags = IB_SEND_SIGNALED; - read_wr.rkey = rs_handle; - read_wr.remote_addr = rs_offset; - read_wr.wr.sg_list = ctxt->sge; - read_wr.wr.num_sge = pages_needed; - - ret = svc_rdma_send(xprt, &read_wr.wr); - if (ret) { - pr_err("svcrdma: Error %d posting RDMA_READ\n", ret); - set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); - goto err; - } - - /* return current location in page array */ - *page_no = pg_no; - *page_offset = pg_off; - ret = read; - atomic_inc(&rdma_stat_read); - return ret; - err: - svc_rdma_unmap_dma(ctxt); - svc_rdma_put_context(ctxt, 0); - return ret; -} - -/* Issue an RDMA_READ using an FRMR to map the data sink */ -int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt, - struct svc_rqst *rqstp, - struct svc_rdma_op_ctxt *head, - int *page_no, - u32 *page_offset, - u32 rs_handle, - u32 rs_length, - u64 rs_offset, - bool last) -{ - struct ib_rdma_wr read_wr; - struct ib_send_wr inv_wr; - struct ib_reg_wr reg_wr; - u8 key; - int nents = PAGE_ALIGN(*page_offset + rs_length) >> PAGE_SHIFT; - struct svc_rdma_op_ctxt *ctxt = svc_rdma_get_context(xprt); - struct svc_rdma_fastreg_mr *frmr = svc_rdma_get_frmr(xprt); - int ret, read, pno, dma_nents, n; - u32 pg_off = *page_offset; - u32 pg_no = *page_no; - - if (IS_ERR(frmr)) - return -ENOMEM; - - ctxt->direction = DMA_FROM_DEVICE; - ctxt->frmr = frmr; - nents = min_t(unsigned int, nents, xprt->sc_frmr_pg_list_len); - read = min_t(int, (nents << PAGE_SHIFT) - *page_offset, rs_length); - - frmr->direction = DMA_FROM_DEVICE; - frmr->access_flags = (IB_ACCESS_LOCAL_WRITE|IB_ACCESS_REMOTE_WRITE); - frmr->sg_nents = nents; - - for (pno = 0; pno < nents; pno++) { - int len = min_t(int, rs_length, PAGE_SIZE - pg_off); - - head->arg.pages[pg_no] = rqstp->rq_arg.pages[pg_no]; - head->arg.page_len += len; - head->arg.len += len; - if (!pg_off) - head->count++; - - sg_set_page(&frmr->sg[pno], rqstp->rq_arg.pages[pg_no], - len, pg_off); - - rqstp->rq_respages = &rqstp->rq_arg.pages[pg_no+1]; - rqstp->rq_next_page = rqstp->rq_respages + 1; - - /* adjust offset and wrap to next page if needed */ - pg_off += len; - if (pg_off == PAGE_SIZE) { - pg_off = 0; - pg_no++; - } - rs_length -= len; - } - - if (last && rs_length == 0) - set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags); - else - clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags); - - dma_nents = ib_dma_map_sg(xprt->sc_cm_id->device, - frmr->sg, frmr->sg_nents, - frmr->direction); - if (!dma_nents) { - pr_err("svcrdma: failed to dma map sg %p\n", - frmr->sg); - return -ENOMEM; - } - - n = ib_map_mr_sg(frmr->mr, frmr->sg, frmr->sg_nents, NULL, PAGE_SIZE); - if (unlikely(n != frmr->sg_nents)) { - pr_err("svcrdma: failed to map mr %p (%d/%d elements)\n", - frmr->mr, n, frmr->sg_nents); - return n < 0 ? n : -EINVAL; - } - - /* Bump the key */ - key = (u8)(frmr->mr->lkey & 0x000000FF); - ib_update_fast_reg_key(frmr->mr, ++key); - - ctxt->sge[0].addr = frmr->mr->iova; - ctxt->sge[0].lkey = frmr->mr->lkey; - ctxt->sge[0].length = frmr->mr->length; - ctxt->count = 1; - ctxt->read_hdr = head; - - /* Prepare REG WR */ - ctxt->reg_cqe.done = svc_rdma_wc_reg; - reg_wr.wr.wr_cqe = &ctxt->reg_cqe; - reg_wr.wr.opcode = IB_WR_REG_MR; - reg_wr.wr.send_flags = IB_SEND_SIGNALED; - reg_wr.wr.num_sge = 0; - reg_wr.mr = frmr->mr; - reg_wr.key = frmr->mr->lkey; - reg_wr.access = frmr->access_flags; - reg_wr.wr.next = &read_wr.wr; - - /* Prepare RDMA_READ */ - memset(&read_wr, 0, sizeof(read_wr)); - ctxt->cqe.done = svc_rdma_wc_read; - read_wr.wr.wr_cqe = &ctxt->cqe; - read_wr.wr.send_flags = IB_SEND_SIGNALED; - read_wr.rkey = rs_handle; - read_wr.remote_addr = rs_offset; - read_wr.wr.sg_list = ctxt->sge; - read_wr.wr.num_sge = 1; - if (xprt->sc_dev_caps & SVCRDMA_DEVCAP_READ_W_INV) { - read_wr.wr.opcode = IB_WR_RDMA_READ_WITH_INV; - read_wr.wr.ex.invalidate_rkey = ctxt->frmr->mr->lkey; - } else { - read_wr.wr.opcode = IB_WR_RDMA_READ; - read_wr.wr.next = &inv_wr; - /* Prepare invalidate */ - memset(&inv_wr, 0, sizeof(inv_wr)); - ctxt->inv_cqe.done = svc_rdma_wc_inv; - inv_wr.wr_cqe = &ctxt->inv_cqe; - inv_wr.opcode = IB_WR_LOCAL_INV; - inv_wr.send_flags = IB_SEND_SIGNALED | IB_SEND_FENCE; - inv_wr.ex.invalidate_rkey = frmr->mr->lkey; - } - - /* Post the chain */ - ret = svc_rdma_send(xprt, ®_wr.wr); - if (ret) { - pr_err("svcrdma: Error %d posting RDMA_READ\n", ret); - set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); - goto err; - } - - /* return current location in page array */ - *page_no = pg_no; - *page_offset = pg_off; - ret = read; - atomic_inc(&rdma_stat_read); - return ret; - err: - svc_rdma_put_context(ctxt, 0); - svc_rdma_put_frmr(xprt, frmr); - return ret; -} - -/* If there was additional inline content, append it to the end of arg.pages. - * Tail copy has to be done after the reader function has determined how many - * pages are needed for RDMA READ. - */ -static int -rdma_copy_tail(struct svc_rqst *rqstp, struct svc_rdma_op_ctxt *head, - u32 position, u32 byte_count, u32 page_offset, int page_no) -{ - char *srcp, *destp; - - srcp = head->arg.head[0].iov_base + position; - byte_count = head->arg.head[0].iov_len - position; - if (byte_count > PAGE_SIZE) { - dprintk("svcrdma: large tail unsupported\n"); - return 0; - } - - /* Fit as much of the tail on the current page as possible */ - if (page_offset != PAGE_SIZE) { - destp = page_address(rqstp->rq_arg.pages[page_no]); - destp += page_offset; - while (byte_count--) { - *destp++ = *srcp++; - page_offset++; - if (page_offset == PAGE_SIZE && byte_count) - goto more; - } - goto done; - } - -more: - /* Fit the rest on the next page */ - page_no++; - destp = page_address(rqstp->rq_arg.pages[page_no]); - while (byte_count--) - *destp++ = *srcp++; - - rqstp->rq_respages = &rqstp->rq_arg.pages[page_no+1]; - rqstp->rq_next_page = rqstp->rq_respages + 1; - -done: - byte_count = head->arg.head[0].iov_len - position; - head->arg.page_len += byte_count; - head->arg.len += byte_count; - head->arg.buflen += byte_count; - return 1; -} - -/* Returns the address of the first read chunk or if no read chunk - * is present - */ -static struct rpcrdma_read_chunk * -svc_rdma_get_read_chunk(struct rpcrdma_msg *rmsgp) -{ - struct rpcrdma_read_chunk *ch = - (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0]; - - if (ch->rc_discrim == xdr_zero) - return NULL; - return ch; -} - -static int rdma_read_chunks(struct svcxprt_rdma *xprt, - struct rpcrdma_msg *rmsgp, - struct svc_rqst *rqstp, - struct svc_rdma_op_ctxt *head) -{ - int page_no, ret; - struct rpcrdma_read_chunk *ch; - u32 handle, page_offset, byte_count; - u32 position; - u64 rs_offset; - bool last; - - /* If no read list is present, return 0 */ - ch = svc_rdma_get_read_chunk(rmsgp); - if (!ch) - return 0; - - /* The request is completed when the RDMA_READs complete. The - * head context keeps all the pages that comprise the - * request. - */ - head->arg.head[0] = rqstp->rq_arg.head[0]; - head->arg.tail[0] = rqstp->rq_arg.tail[0]; - head->hdr_count = head->count; - head->arg.page_base = 0; - head->arg.page_len = 0; - head->arg.len = rqstp->rq_arg.len; - head->arg.buflen = rqstp->rq_arg.buflen; - - /* RDMA_NOMSG: RDMA READ data should land just after RDMA RECV data */ - position = be32_to_cpu(ch->rc_position); - if (position == 0) { - head->arg.pages = &head->pages[0]; - page_offset = head->byte_len; - } else { - head->arg.pages = &head->pages[head->count]; - page_offset = 0; - } - - ret = 0; - page_no = 0; - for (; ch->rc_discrim != xdr_zero; ch++) { - if (be32_to_cpu(ch->rc_position) != position) - goto err; - - handle = be32_to_cpu(ch->rc_target.rs_handle), - byte_count = be32_to_cpu(ch->rc_target.rs_length); - xdr_decode_hyper((__be32 *)&ch->rc_target.rs_offset, - &rs_offset); - - while (byte_count > 0) { - last = (ch + 1)->rc_discrim == xdr_zero; - ret = xprt->sc_reader(xprt, rqstp, head, - &page_no, &page_offset, - handle, byte_count, - rs_offset, last); - if (ret < 0) - goto err; - byte_count -= ret; - rs_offset += ret; - head->arg.buflen += ret; - } - } - - /* Read list may need XDR round-up (see RFC 5666, s. 3.7) */ - if (page_offset & 3) { - u32 pad = 4 - (page_offset & 3); - - head->arg.tail[0].iov_len += pad; - head->arg.len += pad; - head->arg.buflen += pad; - page_offset += pad; - } - - ret = 1; - if (position && position < head->arg.head[0].iov_len) - ret = rdma_copy_tail(rqstp, head, position, - byte_count, page_offset, page_no); - head->arg.head[0].iov_len = position; - head->position = position; - - err: - /* Detach arg pages. svc_recv will replenish them */ - for (page_no = 0; - &rqstp->rq_pages[page_no] < rqstp->rq_respages; page_no++) - rqstp->rq_pages[page_no] = NULL; - - return ret; -} - static void rdma_read_complete(struct svc_rqst *rqstp, struct svc_rdma_op_ctxt *head) { @@ -720,24 +376,9 @@ static void rdma_read_complete(struct svc_rqst *rqstp, rqstp->rq_pages[page_no] = head->pages[page_no]; } - /* Adjustments made for RDMA_NOMSG type requests */ - if (head->position == 0) { - if (head->arg.len <= head->sge[0].length) { - head->arg.head[0].iov_len = head->arg.len - - head->byte_len; - head->arg.page_len = 0; - } else { - head->arg.head[0].iov_len = head->sge[0].length - - head->byte_len; - head->arg.page_len = head->arg.len - - head->sge[0].length; - } - } - /* Point rq_arg.pages past header */ rqstp->rq_arg.pages = &rqstp->rq_pages[head->hdr_count]; rqstp->rq_arg.page_len = head->arg.page_len; - rqstp->rq_arg.page_base = head->arg.page_base; /* rq_respages starts after the last arg page */ rqstp->rq_respages = &rqstp->rq_pages[page_no]; @@ -834,10 +475,35 @@ static bool svc_rdma_is_backchannel_reply(struct svc_xprt *xprt, return true; } -/* - * Set up the rqstp thread context to point to the RQ buffer. If - * necessary, pull additional data from the client with an RDMA_READ - * request. +/** + * svc_rdma_recvfrom - Receive an RPC call + * @rqstp: request structure into which to receive an RPC Call + * + * Returns: + * The positive number of bytes in the RPC Call message, + * %0 if there were no Calls ready to return, + * %-EINVAL if the Read chunk data is too large, + * %-ENOMEM if rdma_rw context pool was exhausted, + * %-ENOTCONN if posting failed (connection is lost), + * %-EIO if rdma_rw initialization failed (DMA mapping, etc). + * + * Called in a loop when XPT_DATA is set. XPT_DATA is cleared only + * when there are no remaining ctxt's to process. + * + * The next ctxt is removed from the "receive" lists. + * + * - If the ctxt completes a Read, then finish assembling the Call + * message and return the number of bytes in the message. + * + * - If the ctxt completes a Receive, then construct the Call + * message from the contents of the Receive buffer. + * + * - If there are no Read chunks in this message, then finish + * assembling the Call message and return the number of bytes + * in the message. + * + * - If there are Read chunks in this message, post Read WRs to + * pull that payload and return 0. */ int svc_rdma_recvfrom(struct svc_rqst *rqstp) { @@ -845,11 +511,9 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) struct svcxprt_rdma *rdma_xprt = container_of(xprt, struct svcxprt_rdma, sc_xprt); struct svc_rdma_op_ctxt *ctxt; - struct rpcrdma_msg *rmsgp; + __be32 *p; int ret; - dprintk("svcrdma: rqstp=%p\n", rqstp); - spin_lock(&rdma_xprt->sc_rq_dto_lock); if (!list_empty(&rdma_xprt->sc_read_complete_q)) { ctxt = list_first_entry(&rdma_xprt->sc_read_complete_q, @@ -870,7 +534,7 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) } spin_unlock(&rdma_xprt->sc_rq_dto_lock); - dprintk("svcrdma: processing ctxt=%p on xprt=%p, rqstp=%p\n", + dprintk("svcrdma: recvfrom: ctxt=%p on xprt=%p, rqstp=%p\n", ctxt, rdma_xprt, rqstp); atomic_inc(&rdma_stat_recv); @@ -878,7 +542,7 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) rdma_build_arg_xdr(rqstp, ctxt, ctxt->byte_len); /* Decode the RDMA header. */ - rmsgp = (struct rpcrdma_msg *)rqstp->rq_arg.head[0].iov_base; + p = (__be32 *)rqstp->rq_arg.head[0].iov_base; ret = svc_rdma_xdr_decode_req(&rqstp->rq_arg); if (ret < 0) goto out_err; @@ -886,9 +550,8 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) goto out_drop; rqstp->rq_xprt_hlen = ret; - if (svc_rdma_is_backchannel_reply(xprt, &rmsgp->rm_xid)) { - ret = svc_rdma_handle_bc_reply(xprt->xpt_bc_xprt, - &rmsgp->rm_xid, + if (svc_rdma_is_backchannel_reply(xprt, p)) { + ret = svc_rdma_handle_bc_reply(xprt->xpt_bc_xprt, p, &rqstp->rq_arg); svc_rdma_put_context(ctxt, 0); if (ret) @@ -896,16 +559,9 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) return ret; } - /* Read read-list data. */ - ret = rdma_read_chunks(rdma_xprt, rmsgp, rqstp, ctxt); - if (ret > 0) { - /* read-list posted, defer until data received from client. */ - goto defer; - } else if (ret < 0) { - /* Post of read-list failed, free context. */ - svc_rdma_put_context(ctxt, 1); - return 0; - } + p += rpcrdma_fixed_maxsz; + if (*p != xdr_zero) + goto out_readchunk; complete: ret = rqstp->rq_arg.head[0].iov_len @@ -921,13 +577,22 @@ complete: svc_xprt_copy_addrs(rqstp, xprt); return ret; +out_readchunk: + ret = svc_rdma_recv_read_chunk(rdma_xprt, rqstp, ctxt, p); + if (ret < 0) + goto out_postfail; + return 0; + out_err: - svc_rdma_send_error(rdma_xprt, &rmsgp->rm_xid, ret); + svc_rdma_send_error(rdma_xprt, p, ret); svc_rdma_put_context(ctxt, 0); return 0; -defer: - return 0; +out_postfail: + if (ret == -EINVAL) + svc_rdma_send_error(rdma_xprt, p, ret); + svc_rdma_put_context(ctxt, 1); + return ret; out_drop: svc_rdma_put_context(ctxt, 1); diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index a9d9cb1ba4c6..72d2dcdca2e1 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -908,8 +908,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) * capabilities of this particular device */ newxprt->sc_max_sge = min((size_t)dev->attrs.max_sge, (size_t)RPCSVC_MAXPAGES); - newxprt->sc_max_sge_rd = min_t(size_t, dev->attrs.max_sge_rd, - RPCSVC_MAXPAGES); newxprt->sc_max_req_size = svcrdma_max_req_size; newxprt->sc_max_requests = min_t(u32, dev->attrs.max_qp_wr, svcrdma_max_requests); @@ -998,12 +996,10 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) * NB: iWARP requires remote write access for the data sink * of an RDMA_READ. IB does not. */ - newxprt->sc_reader = rdma_read_chunk_lcl; if (dev->attrs.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) { newxprt->sc_frmr_pg_list_len = dev->attrs.max_fast_reg_page_list_len; newxprt->sc_dev_caps |= SVCRDMA_DEVCAP_FAST_REG; - newxprt->sc_reader = rdma_read_chunk_frmr; } else newxprt->sc_snd_w_inv = false; @@ -1056,7 +1052,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) sap = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.dst_addr; dprintk(" remote address : %pIS:%u\n", sap, rpc_get_port(sap)); dprintk(" max_sge : %d\n", newxprt->sc_max_sge); - dprintk(" max_sge_rd : %d\n", newxprt->sc_max_sge_rd); dprintk(" sq_depth : %d\n", newxprt->sc_sq_depth); dprintk(" max_requests : %d\n", newxprt->sc_max_requests); dprintk(" ord : %d\n", newxprt->sc_ord); @@ -1117,12 +1112,6 @@ static void __svc_rdma_free(struct work_struct *work) pr_err("svcrdma: sc_xprt still in use? (%d)\n", kref_read(&xprt->xpt_ref)); - /* - * Destroy queued, but not processed read completions. Note - * that this cleanup has to be done before destroying the - * cm_id because the device ptr is needed to unmap the dma in - * svc_rdma_put_context. - */ while (!list_empty(&rdma->sc_read_complete_q)) { struct svc_rdma_op_ctxt *ctxt; ctxt = list_first_entry(&rdma->sc_read_complete_q, @@ -1130,8 +1119,6 @@ static void __svc_rdma_free(struct work_struct *work) list_del(&ctxt->list); svc_rdma_put_context(ctxt, 1); } - - /* Destroy queued, but not processed recv completions */ while (!list_empty(&rdma->sc_rq_dto_q)) { struct svc_rdma_op_ctxt *ctxt; ctxt = list_first_entry(&rdma->sc_rq_dto_q, -- cgit v1.2.3-59-g8ed1b From 71641d99ce037ea226f94d5e08f2a8f71eba08f4 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 23 Jun 2017 17:18:41 -0400 Subject: svcrdma: Properly compute .len and .buflen for received RPC Calls When an RPC-over-RDMA request is received, the Receive buffer contains a Transport Header possibly followed by an RPC message. Even though rq_arg.head[0] (as passed to NFSD) does not contain the Transport Header header, currently rq_arg.len includes the size of the Transport Header. That violates the intent of the xdr_buf API contract. .buflen should include everything, but .len should be exactly the length of the RPC message in the buffer. The rq_arg fields are summed together at the end of svc_rdma_recvfrom to obtain the correct return value. rq_arg.len really ought to contain the correct number of bytes already, but it currently doesn't due to the above misbehavior. Let's instead ensure that .buflen includes the length of the transport header, and that .len is always equal to head.iov_len + .page_len + tail.iov_len . Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 14 ++++---------- net/sunrpc/xprtrdma/svc_rdma_rw.c | 2 +- 2 files changed, 5 insertions(+), 11 deletions(-) diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 5fbcb73dd68d..ad4bd62eebf1 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -143,7 +143,6 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp, put_page(rqstp->rq_pages[sge_no]); rqstp->rq_pages[sge_no] = page; bc -= min_t(u32, bc, ctxt->sge[sge_no].length); - rqstp->rq_arg.buflen += ctxt->sge[sge_no].length; sge_no++; } rqstp->rq_respages = &rqstp->rq_pages[sge_no]; @@ -338,6 +337,7 @@ static int svc_rdma_xdr_decode_req(struct xdr_buf *rq_arg) rq_arg->head[0].iov_base = p; hdr_len = (unsigned long)p - (unsigned long)rdma_argp; rq_arg->head[0].iov_len -= hdr_len; + rq_arg->len -= hdr_len; dprintk("svcrdma: received %s request for XID 0x%08x, hdr_len=%u\n", proc, be32_to_cpup(rdma_argp), hdr_len); return hdr_len; @@ -564,18 +564,12 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) goto out_readchunk; complete: - ret = rqstp->rq_arg.head[0].iov_len - + rqstp->rq_arg.page_len - + rqstp->rq_arg.tail[0].iov_len; svc_rdma_put_context(ctxt, 0); - dprintk("svcrdma: ret=%d, rq_arg.len=%u, " - "rq_arg.head[0].iov_base=%p, rq_arg.head[0].iov_len=%zd\n", - ret, rqstp->rq_arg.len, - rqstp->rq_arg.head[0].iov_base, - rqstp->rq_arg.head[0].iov_len); + dprintk("svcrdma: recvfrom: xprt=%p, rqstp=%p, rq_arg.len=%u\n", + rdma_xprt, rqstp, rqstp->rq_arg.len); rqstp->rq_prot = IPPROTO_MAX; svc_xprt_copy_addrs(rqstp, xprt); - return ret; + return rqstp->rq_arg.len; out_readchunk: ret = svc_rdma_recv_read_chunk(rdma_xprt, rqstp, ctxt, p); diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index 77d38a4b8d99..9d7a151b4885 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -848,7 +848,7 @@ static int svc_rdma_build_pz_read_chunk(struct svc_rqst *rqstp, head->arg.len += info->ri_chunklen; head->arg.buflen += info->ri_chunklen; - if (head->arg.len <= head->sge[0].length) { + if (head->arg.buflen <= head->sge[0].length) { /* Transport header and RPC message fit entirely * in page where head iovec resides. */ -- cgit v1.2.3-59-g8ed1b From c84dc900d737a8d8f08768622226980ee863403b Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 23 Jun 2017 17:18:49 -0400 Subject: svcrdma: Remove unused Read completion handlers Clean up: The generic RDMA R/W API conversion of svc_rdma_recvfrom replaced the Register, Read, and Invalidate completion handlers. Remove the old ones, which are no longer used. These handlers shared some helper code with svc_rdma_wc_send. Fold the wc_common helper back into the one remaining completion handler. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 4 +- net/sunrpc/xprtrdma/svc_rdma_transport.c | 93 ++++---------------------------- 2 files changed, 10 insertions(+), 87 deletions(-) diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index b1ba19ba1071..06d58a3f74bc 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -77,17 +77,15 @@ extern atomic_t rdma_stat_sq_prod; */ struct svc_rdma_op_ctxt { struct list_head list; - struct svc_rdma_op_ctxt *read_hdr; struct svc_rdma_fastreg_mr *frmr; - int hdr_count; struct xdr_buf arg; struct ib_cqe cqe; u32 byte_len; struct svcxprt_rdma *xprt; - unsigned long flags; enum dma_data_direction direction; int count; unsigned int mapped_sges; + int hdr_count; struct ib_send_wr send_wr; struct ib_sge sge[1 + RPCRDMA_MAX_INLINE_THRESH / PAGE_SIZE]; struct page *pages[RPCSVC_MAXPAGES]; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 72d2dcdca2e1..c915cba0f8e6 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -346,36 +346,6 @@ out: svc_xprt_put(&xprt->sc_xprt); } -static void svc_rdma_send_wc_common(struct svcxprt_rdma *xprt, - struct ib_wc *wc, - const char *opname) -{ - if (wc->status != IB_WC_SUCCESS) - goto err; - -out: - atomic_inc(&xprt->sc_sq_avail); - wake_up(&xprt->sc_send_wait); - return; - -err: - set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); - if (wc->status != IB_WC_WR_FLUSH_ERR) - pr_err("svcrdma: %s: %s (%u/0x%x)\n", - opname, ib_wc_status_msg(wc->status), - wc->status, wc->vendor_err); - goto out; -} - -static void svc_rdma_send_wc_common_put(struct ib_cq *cq, struct ib_wc *wc, - const char *opname) -{ - struct svcxprt_rdma *xprt = cq->cq_context; - - svc_rdma_send_wc_common(xprt, wc, opname); - svc_xprt_put(&xprt->sc_xprt); -} - /** * svc_rdma_wc_send - Invoked by RDMA provider for each polled Send WC * @cq: completion queue @@ -383,74 +353,29 @@ static void svc_rdma_send_wc_common_put(struct ib_cq *cq, struct ib_wc *wc, * */ void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc) -{ - struct ib_cqe *cqe = wc->wr_cqe; - struct svc_rdma_op_ctxt *ctxt; - - svc_rdma_send_wc_common_put(cq, wc, "send"); - - ctxt = container_of(cqe, struct svc_rdma_op_ctxt, cqe); - svc_rdma_unmap_dma(ctxt); - svc_rdma_put_context(ctxt, 1); -} - -/** - * svc_rdma_wc_reg - Invoked by RDMA provider for each polled FASTREG WC - * @cq: completion queue - * @wc: completed WR - * - */ -void svc_rdma_wc_reg(struct ib_cq *cq, struct ib_wc *wc) -{ - svc_rdma_send_wc_common_put(cq, wc, "fastreg"); -} - -/** - * svc_rdma_wc_read - Invoked by RDMA provider for each polled Read WC - * @cq: completion queue - * @wc: completed WR - * - */ -void svc_rdma_wc_read(struct ib_cq *cq, struct ib_wc *wc) { struct svcxprt_rdma *xprt = cq->cq_context; struct ib_cqe *cqe = wc->wr_cqe; struct svc_rdma_op_ctxt *ctxt; - svc_rdma_send_wc_common(xprt, wc, "read"); + atomic_inc(&xprt->sc_sq_avail); + wake_up(&xprt->sc_send_wait); ctxt = container_of(cqe, struct svc_rdma_op_ctxt, cqe); svc_rdma_unmap_dma(ctxt); - svc_rdma_put_frmr(xprt, ctxt->frmr); - - if (test_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags)) { - struct svc_rdma_op_ctxt *read_hdr; - - read_hdr = ctxt->read_hdr; - spin_lock(&xprt->sc_rq_dto_lock); - list_add_tail(&read_hdr->list, - &xprt->sc_read_complete_q); - spin_unlock(&xprt->sc_rq_dto_lock); + svc_rdma_put_context(ctxt, 1); - set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags); - svc_xprt_enqueue(&xprt->sc_xprt); + if (unlikely(wc->status != IB_WC_SUCCESS)) { + set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); + if (wc->status != IB_WC_WR_FLUSH_ERR) + pr_err("svcrdma: Send: %s (%u/0x%x)\n", + ib_wc_status_msg(wc->status), + wc->status, wc->vendor_err); } - svc_rdma_put_context(ctxt, 0); svc_xprt_put(&xprt->sc_xprt); } -/** - * svc_rdma_wc_inv - Invoked by RDMA provider for each polled LOCAL_INV WC - * @cq: completion queue - * @wc: completed WR - * - */ -void svc_rdma_wc_inv(struct ib_cq *cq, struct ib_wc *wc) -{ - svc_rdma_send_wc_common_put(cq, wc, "localInv"); -} - static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv, int listener) { -- cgit v1.2.3-59-g8ed1b From 463e63d7014442002399903af027b63ae38f6e77 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 23 Jun 2017 17:18:57 -0400 Subject: svcrdma: Remove frmr cache Clean up: Now that the svc_rdma_recvfrom path uses the rdma_rw API, the details of Read sink buffer registration are dealt with by the kernel's RDMA core. This cache is no longer used, and can be removed. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 18 ------- net/sunrpc/xprtrdma/svc_rdma_transport.c | 86 -------------------------------- 2 files changed, 104 deletions(-) diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 06d58a3f74bc..fd7775f70bb5 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -77,7 +77,6 @@ extern atomic_t rdma_stat_sq_prod; */ struct svc_rdma_op_ctxt { struct list_head list; - struct svc_rdma_fastreg_mr *frmr; struct xdr_buf arg; struct ib_cqe cqe; u32 byte_len; @@ -91,17 +90,6 @@ struct svc_rdma_op_ctxt { struct page *pages[RPCSVC_MAXPAGES]; }; -struct svc_rdma_fastreg_mr { - struct ib_mr *mr; - struct scatterlist *sg; - int sg_nents; - unsigned long access_flags; - enum dma_data_direction direction; - struct list_head frmr_list; -}; - -#define RDMACTXT_F_LAST_CTXT 2 - #define SVCRDMA_DEVCAP_FAST_REG 1 /* fast mr registration */ #define SVCRDMA_DEVCAP_READ_W_INV 2 /* read w/ invalidate */ @@ -136,9 +124,6 @@ struct svcxprt_rdma { struct ib_cq *sc_rq_cq; struct ib_cq *sc_sq_cq; u32 sc_dev_caps; /* distilled device caps */ - unsigned int sc_frmr_pg_list_len; - struct list_head sc_frmr_q; - spinlock_t sc_frmr_q_lock; spinlock_t sc_lock; /* transport lock */ @@ -210,9 +195,6 @@ extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *); extern struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *); extern void svc_rdma_put_context(struct svc_rdma_op_ctxt *, int); extern void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt); -extern struct svc_rdma_fastreg_mr *svc_rdma_get_frmr(struct svcxprt_rdma *); -extern void svc_rdma_put_frmr(struct svcxprt_rdma *, - struct svc_rdma_fastreg_mr *); extern void svc_sq_reap(struct svcxprt_rdma *); extern void svc_rq_reap(struct svcxprt_rdma *); extern void svc_rdma_prep_reply_hdr(struct svc_rqst *); diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index c915cba0f8e6..8864105d86ec 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -202,7 +202,6 @@ struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt) out: ctxt->count = 0; ctxt->mapped_sges = 0; - ctxt->frmr = NULL; return ctxt; out_empty: @@ -387,14 +386,12 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv, INIT_LIST_HEAD(&cma_xprt->sc_accept_q); INIT_LIST_HEAD(&cma_xprt->sc_rq_dto_q); INIT_LIST_HEAD(&cma_xprt->sc_read_complete_q); - INIT_LIST_HEAD(&cma_xprt->sc_frmr_q); INIT_LIST_HEAD(&cma_xprt->sc_ctxts); INIT_LIST_HEAD(&cma_xprt->sc_rw_ctxts); init_waitqueue_head(&cma_xprt->sc_send_wait); spin_lock_init(&cma_xprt->sc_lock); spin_lock_init(&cma_xprt->sc_rq_dto_lock); - spin_lock_init(&cma_xprt->sc_frmr_q_lock); spin_lock_init(&cma_xprt->sc_ctxt_lock); spin_lock_init(&cma_xprt->sc_rw_ctxt_lock); @@ -705,86 +702,6 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, return ERR_PTR(ret); } -static struct svc_rdma_fastreg_mr *rdma_alloc_frmr(struct svcxprt_rdma *xprt) -{ - struct ib_mr *mr; - struct scatterlist *sg; - struct svc_rdma_fastreg_mr *frmr; - u32 num_sg; - - frmr = kmalloc(sizeof(*frmr), GFP_KERNEL); - if (!frmr) - goto err; - - num_sg = min_t(u32, RPCSVC_MAXPAGES, xprt->sc_frmr_pg_list_len); - mr = ib_alloc_mr(xprt->sc_pd, IB_MR_TYPE_MEM_REG, num_sg); - if (IS_ERR(mr)) - goto err_free_frmr; - - sg = kcalloc(RPCSVC_MAXPAGES, sizeof(*sg), GFP_KERNEL); - if (!sg) - goto err_free_mr; - - sg_init_table(sg, RPCSVC_MAXPAGES); - - frmr->mr = mr; - frmr->sg = sg; - INIT_LIST_HEAD(&frmr->frmr_list); - return frmr; - - err_free_mr: - ib_dereg_mr(mr); - err_free_frmr: - kfree(frmr); - err: - return ERR_PTR(-ENOMEM); -} - -static void rdma_dealloc_frmr_q(struct svcxprt_rdma *xprt) -{ - struct svc_rdma_fastreg_mr *frmr; - - while (!list_empty(&xprt->sc_frmr_q)) { - frmr = list_entry(xprt->sc_frmr_q.next, - struct svc_rdma_fastreg_mr, frmr_list); - list_del_init(&frmr->frmr_list); - kfree(frmr->sg); - ib_dereg_mr(frmr->mr); - kfree(frmr); - } -} - -struct svc_rdma_fastreg_mr *svc_rdma_get_frmr(struct svcxprt_rdma *rdma) -{ - struct svc_rdma_fastreg_mr *frmr = NULL; - - spin_lock(&rdma->sc_frmr_q_lock); - if (!list_empty(&rdma->sc_frmr_q)) { - frmr = list_entry(rdma->sc_frmr_q.next, - struct svc_rdma_fastreg_mr, frmr_list); - list_del_init(&frmr->frmr_list); - frmr->sg_nents = 0; - } - spin_unlock(&rdma->sc_frmr_q_lock); - if (frmr) - return frmr; - - return rdma_alloc_frmr(rdma); -} - -void svc_rdma_put_frmr(struct svcxprt_rdma *rdma, - struct svc_rdma_fastreg_mr *frmr) -{ - if (frmr) { - ib_dma_unmap_sg(rdma->sc_cm_id->device, - frmr->sg, frmr->sg_nents, frmr->direction); - spin_lock(&rdma->sc_frmr_q_lock); - WARN_ON_ONCE(!list_empty(&frmr->frmr_list)); - list_add(&frmr->frmr_list, &rdma->sc_frmr_q); - spin_unlock(&rdma->sc_frmr_q_lock); - } -} - /* * This is the xpo_recvfrom function for listening endpoints. Its * purpose is to accept incoming connections. The CMA callback handler @@ -922,8 +839,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) * of an RDMA_READ. IB does not. */ if (dev->attrs.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) { - newxprt->sc_frmr_pg_list_len = - dev->attrs.max_fast_reg_page_list_len; newxprt->sc_dev_caps |= SVCRDMA_DEVCAP_FAST_REG; } else newxprt->sc_snd_w_inv = false; @@ -1063,7 +978,6 @@ static void __svc_rdma_free(struct work_struct *work) xprt->xpt_bc_xprt = NULL; } - rdma_dealloc_frmr_q(rdma); svc_rdma_destroy_rw_ctxts(rdma); svc_rdma_destroy_ctxts(rdma); -- cgit v1.2.3-59-g8ed1b From 0d956e694ad2d4b8fb3940dc19e738e1fc158353 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 23 Jun 2017 17:19:05 -0400 Subject: svcrdma: Clean-up svc_rdma_unmap_dma There's no longer a need to compare each SGE's lkey with the PD's local_dma_lkey. Now that FRWR is gone, all DMA mappings are for pages that were registered with this key. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- net/sunrpc/xprtrdma/svc_rdma_transport.c | 19 +++++-------------- 1 file changed, 5 insertions(+), 14 deletions(-) diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 8864105d86ec..75bd11f2b69e 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -225,22 +225,13 @@ void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt) { struct svcxprt_rdma *xprt = ctxt->xprt; struct ib_device *device = xprt->sc_cm_id->device; - u32 lkey = xprt->sc_pd->local_dma_lkey; unsigned int i; - for (i = 0; i < ctxt->mapped_sges; i++) { - /* - * Unmap the DMA addr in the SGE if the lkey matches - * the local_dma_lkey, otherwise, ignore it since it is - * an FRMR lkey and will be unmapped later when the - * last WR that uses it completes. - */ - if (ctxt->sge[i].lkey == lkey) - ib_dma_unmap_page(device, - ctxt->sge[i].addr, - ctxt->sge[i].length, - ctxt->direction); - } + for (i = 0; i < ctxt->mapped_sges; i++) + ib_dma_unmap_page(device, + ctxt->sge[i].addr, + ctxt->sge[i].length, + ctxt->direction); ctxt->mapped_sges = 0; } -- cgit v1.2.3-59-g8ed1b From 9450ca8e2febb0000a5efd4f5870915d59ae62bc Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 23 Jun 2017 17:19:13 -0400 Subject: svcrdma: Clean up after converting svc_rdma_recvfrom to rdma_rw API Clean up: Registration mode details are now handled by the rdma_rw API, and thus can be removed from svcrdma. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 4 ---- net/sunrpc/xprtrdma/svc_rdma_transport.c | 39 ++++---------------------------- 2 files changed, 4 insertions(+), 39 deletions(-) diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index fd7775f70bb5..995c6fe9ee90 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -90,9 +90,6 @@ struct svc_rdma_op_ctxt { struct page *pages[RPCSVC_MAXPAGES]; }; -#define SVCRDMA_DEVCAP_FAST_REG 1 /* fast mr registration */ -#define SVCRDMA_DEVCAP_READ_W_INV 2 /* read w/ invalidate */ - struct svcxprt_rdma { struct svc_xprt sc_xprt; /* SVC transport structure */ struct rdma_cm_id *sc_cm_id; /* RDMA connection id */ @@ -123,7 +120,6 @@ struct svcxprt_rdma { struct ib_qp *sc_qp; struct ib_cq *sc_rq_cq; struct ib_cq *sc_sq_cq; - u32 sc_dev_caps; /* distilled device caps */ spinlock_t sc_lock; /* transport lock */ diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 75bd11f2b69e..e660d4965b18 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -783,7 +783,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) memset(&qp_attr, 0, sizeof qp_attr); qp_attr.event_handler = qp_event_handler; qp_attr.qp_context = &newxprt->sc_xprt; - qp_attr.port_num = newxprt->sc_cm_id->port_num; + qp_attr.port_num = newxprt->sc_port_num; qp_attr.cap.max_rdma_ctxs = newxprt->sc_max_requests; qp_attr.cap.max_send_wr = newxprt->sc_sq_depth; qp_attr.cap.max_recv_wr = newxprt->sc_rq_depth; @@ -807,43 +807,12 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) } newxprt->sc_qp = newxprt->sc_cm_id->qp; - /* - * Use the most secure set of MR resources based on the - * transport type and available memory management features in - * the device. Here's the table implemented below: - * - * Fast Global DMA Remote WR - * Reg LKEY MR Access - * Sup'd Sup'd Needed Needed - * - * IWARP N N Y Y - * N Y Y Y - * Y N Y N - * Y Y N - - * - * IB N N Y N - * N Y N - - * Y N Y N - * Y Y N - - * - * NB: iWARP requires remote write access for the data sink - * of an RDMA_READ. IB does not. - */ - if (dev->attrs.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) { - newxprt->sc_dev_caps |= SVCRDMA_DEVCAP_FAST_REG; - } else + if (!(dev->attrs.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS)) newxprt->sc_snd_w_inv = false; - - /* - * Determine if a DMA MR is required and if so, what privs are required - */ - if (!rdma_protocol_iwarp(dev, newxprt->sc_cm_id->port_num) && - !rdma_ib_or_roce(dev, newxprt->sc_cm_id->port_num)) + if (!rdma_protocol_iwarp(dev, newxprt->sc_port_num) && + !rdma_ib_or_roce(dev, newxprt->sc_port_num)) goto errout; - if (rdma_protocol_iwarp(dev, newxprt->sc_cm_id->port_num)) - newxprt->sc_dev_caps |= SVCRDMA_DEVCAP_READ_W_INV; - /* Post receive buffers */ for (i = 0; i < newxprt->sc_max_requests; i++) { ret = svc_rdma_post_recv(newxprt, GFP_KERNEL); -- cgit v1.2.3-59-g8ed1b From 91b022ec8b1214d0fdfc503be305a19e6f7c5164 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 23 Jun 2017 17:19:21 -0400 Subject: svcrdma: use offset_in_page() macro Clean up: Use offset_in_page() macro instead of open-coding. Reported-by: Geliang Tang Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- net/sunrpc/xprtrdma/svc_rdma_rw.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index 9d7a151b4885..9859736b331b 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -372,8 +372,9 @@ static void svc_rdma_pagelist_to_sg(struct svc_rdma_write_info *info, struct scatterlist *sg; struct page **page; - page_off = (info->wi_next_off + xdr->page_base) & ~PAGE_MASK; - page_no = (info->wi_next_off + xdr->page_base) >> PAGE_SHIFT; + page_off = info->wi_next_off + xdr->page_base; + page_no = page_off >> PAGE_SHIFT; + page_off = offset_in_page(page_off); page = xdr->pages + page_no; info->wi_next_off += remaining; sg = ctxt->rw_sg_table.sgl; -- cgit v1.2.3-59-g8ed1b From 35a30fc389b5961b42bb73ef751f3bc85190a118 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 23 Jun 2017 17:19:29 -0400 Subject: svcrdma: Remove svc_rdma_chunk_ctxt::cc_dir field Clean up: No need to save the I/O direction. The functions that release svc_rdma_chunk_ctxt already know what direction to use. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- net/sunrpc/xprtrdma/svc_rdma_rw.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index 9859736b331b..933f79bed270 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -116,22 +116,20 @@ struct svc_rdma_chunk_ctxt { struct svcxprt_rdma *cc_rdma; struct list_head cc_rwctxts; int cc_sqecount; - enum dma_data_direction cc_dir; }; static void svc_rdma_cc_init(struct svcxprt_rdma *rdma, - struct svc_rdma_chunk_ctxt *cc, - enum dma_data_direction dir) + struct svc_rdma_chunk_ctxt *cc) { cc->cc_rdma = rdma; svc_xprt_get(&rdma->sc_xprt); INIT_LIST_HEAD(&cc->cc_rwctxts); cc->cc_sqecount = 0; - cc->cc_dir = dir; } -static void svc_rdma_cc_release(struct svc_rdma_chunk_ctxt *cc) +static void svc_rdma_cc_release(struct svc_rdma_chunk_ctxt *cc, + enum dma_data_direction dir) { struct svcxprt_rdma *rdma = cc->cc_rdma; struct svc_rdma_rw_ctxt *ctxt; @@ -141,7 +139,7 @@ static void svc_rdma_cc_release(struct svc_rdma_chunk_ctxt *cc) rdma_rw_ctx_destroy(&ctxt->rw_ctx, rdma->sc_qp, rdma->sc_port_num, ctxt->rw_sg_table.sgl, - ctxt->rw_nents, cc->cc_dir); + ctxt->rw_nents, dir); svc_rdma_put_rw_ctxt(rdma, ctxt); } svc_xprt_put(&rdma->sc_xprt); @@ -179,14 +177,14 @@ svc_rdma_write_info_alloc(struct svcxprt_rdma *rdma, __be32 *chunk) info->wi_seg_no = 0; info->wi_nsegs = be32_to_cpup(++chunk); info->wi_segs = ++chunk; - svc_rdma_cc_init(rdma, &info->wi_cc, DMA_TO_DEVICE); + svc_rdma_cc_init(rdma, &info->wi_cc); info->wi_cc.cc_cqe.done = svc_rdma_write_done; return info; } static void svc_rdma_write_info_free(struct svc_rdma_write_info *info) { - svc_rdma_cc_release(&info->wi_cc); + svc_rdma_cc_release(&info->wi_cc, DMA_TO_DEVICE); kfree(info); } @@ -241,14 +239,14 @@ svc_rdma_read_info_alloc(struct svcxprt_rdma *rdma) if (!info) return info; - svc_rdma_cc_init(rdma, &info->ri_cc, DMA_FROM_DEVICE); + svc_rdma_cc_init(rdma, &info->ri_cc); info->ri_cc.cc_cqe.done = svc_rdma_wc_read_done; return info; } static void svc_rdma_read_info_free(struct svc_rdma_read_info *info) { - svc_rdma_cc_release(&info->ri_cc); + svc_rdma_cc_release(&info->ri_cc, DMA_FROM_DEVICE); kfree(info); } -- cgit v1.2.3-59-g8ed1b From 630458e730b82efe1f6eb90e6bcabad02fe76e20 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Thu, 11 May 2017 14:45:06 -0400 Subject: nfsd4: factor ctime into change attribute Factoring ctime into the nfsv4 change attribute gives us better properties than just i_version alone. Eventually we'll likely also expose this (as opposed to raw i_version) to userspace, at which point we'll want to move it to a common helper, called from either userspace or individual filesystems. For now, nfsd is the only user. Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs3xdr.c | 2 +- fs/nfsd/nfs4xdr.c | 2 +- fs/nfsd/nfsfh.h | 24 +++++++++++++++++++++++- 3 files changed, 25 insertions(+), 3 deletions(-) diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index b8838d3023ff..bf444b664011 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -260,7 +260,7 @@ void fill_post_wcc(struct svc_fh *fhp) printk("nfsd: inode locked twice during operation.\n"); err = fh_getattr(fhp, &fhp->fh_post_attr); - fhp->fh_post_change = d_inode(fhp->fh_dentry)->i_version; + fhp->fh_post_change = nfsd4_change_attribute(d_inode(fhp->fh_dentry)); if (err) { fhp->fh_post_saved = false; /* Grab the ctime anyway - set_change_info might use it */ diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 54e212e3541e..20fbcab97753 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1973,7 +1973,7 @@ static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode, *p++ = cpu_to_be32(convert_to_wallclock(exp->cd->flush_time)); *p++ = 0; } else if (IS_I_VERSION(inode)) { - p = xdr_encode_hyper(p, inode->i_version); + p = xdr_encode_hyper(p, nfsd4_change_attribute(inode)); } else { *p++ = cpu_to_be32(stat->ctime.tv_sec); *p++ = cpu_to_be32(stat->ctime.tv_nsec); diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index f84fe6bf9aee..e47cf6c2ac28 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -240,6 +240,28 @@ fh_clear_wcc(struct svc_fh *fhp) fhp->fh_pre_saved = false; } +/* + * We could use i_version alone as the change attribute. However, + * i_version can go backwards after a reboot. On its own that doesn't + * necessarily cause a problem, but if i_version goes backwards and then + * is incremented again it could reuse a value that was previously used + * before boot, and a client who queried the two values might + * incorrectly assume nothing changed. + * + * By using both ctime and the i_version counter we guarantee that as + * long as time doesn't go backwards we never reuse an old value. + */ +static inline u64 nfsd4_change_attribute(struct inode *inode) +{ + u64 chattr; + + chattr = inode->i_ctime.tv_sec; + chattr <<= 30; + chattr += inode->i_ctime.tv_nsec; + chattr += inode->i_version; + return chattr; +} + /* * Fill in the pre_op attr for the wcc data */ @@ -253,7 +275,7 @@ fill_pre_wcc(struct svc_fh *fhp) fhp->fh_pre_mtime = inode->i_mtime; fhp->fh_pre_ctime = inode->i_ctime; fhp->fh_pre_size = inode->i_size; - fhp->fh_pre_change = inode->i_version; + fhp->fh_pre_change = nfsd4_change_attribute(inode); fhp->fh_pre_saved = true; } } -- cgit v1.2.3-59-g8ed1b From 0bc48bea36d178aea9d7f83f66a1b397cec9db5c Mon Sep 17 00:00:00 2001 From: Radim Krčmář Date: Tue, 16 May 2017 22:50:00 +0200 Subject: KVM: x86: update master clock before computing kvmclock_offset MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit kvm master clock usually has a different frequency than the kernel boot clock. This is not a problem until the master clock is updated; update uses the current kernel boot clock to compute new kvm clock, which erases any kvm clock cycles that might have built up due to frequency difference over a long period. KVM_SET_CLOCK is one of places where we can safely update master clock as the guest-visible clock is going to be shifted anyway. The problem with current code is that it updates the kvm master clock after updating the offset. If the master clock was enabled before calling KVM_SET_CLOCK, then it might have built up a significant delta from kernel boot clock. In the worst case, the time set by userspace would be shifted by so much that it couldn't have been set at any point during KVM_SET_CLOCK. To fix this, move kvm_gen_update_masterclock() before computing kvmclock_offset, which means that the master clock and kernel boot clock will be sufficiently close together. Another solution would be to replace get_kvmclock_ns() with "ktime_get_boot_ns() + ka->kvmclock_offset", which is marginally more accurate, but would break symmetry with KVM_GET_CLOCK. Signed-off-by: Radim Krčmář --- arch/x86/kvm/x86.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6c7266f7766d..ca128a9c9cc4 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4188,9 +4188,15 @@ long kvm_arch_vm_ioctl(struct file *filp, goto out; r = 0; + /* + * TODO: userspace has to take care of races with VCPU_RUN, so + * kvm_gen_update_masterclock() can be cut down to locked + * pvclock_update_vm_gtod_copy(). + */ + kvm_gen_update_masterclock(kvm); now_ns = get_kvmclock_ns(kvm); kvm->arch.kvmclock_offset += user_ns.clock - now_ns; - kvm_gen_update_masterclock(kvm); + kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE); break; } case KVM_GET_CLOCK: { -- cgit v1.2.3-59-g8ed1b From 48ae0fb49b2e8380e60c5072f18005c8a98c6520 Mon Sep 17 00:00:00 2001 From: Jim Mattson Date: Mon, 22 May 2017 09:48:33 -0700 Subject: kvm: vmx: Properly handle machine check during VM-entry MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit vmx_complete_atomic_exit should call kvm_machine_check for any VM-entry failure due to a machine-check event. Such an exit should be recognized solely by its basic exit reason (i.e. the low 16 bits of the VMCS exit reason field). None of the other VMCS exit information fields contain valid information when the VM-exit is due to "VM-entry failure due to machine-check event". Signed-off-by: Jim Mattson Reviewed-by: Xiao Guangrong [Changed VM_EXIT_INTR_INFO condition to better describe its reason.] Signed-off-by: Radim Krčmář --- arch/x86/kvm/vmx.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 32db3f5dce7f..25f2fdccf625 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -8630,17 +8630,20 @@ static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu) static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx) { - u32 exit_intr_info; + u32 exit_intr_info = 0; + u16 basic_exit_reason = (u16)vmx->exit_reason; - if (!(vmx->exit_reason == EXIT_REASON_MCE_DURING_VMENTRY - || vmx->exit_reason == EXIT_REASON_EXCEPTION_NMI)) + if (!(basic_exit_reason == EXIT_REASON_MCE_DURING_VMENTRY + || basic_exit_reason == EXIT_REASON_EXCEPTION_NMI)) return; - vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - exit_intr_info = vmx->exit_intr_info; + if (!(vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) + exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); + vmx->exit_intr_info = exit_intr_info; /* Handle machine checks before interrupts are enabled */ - if (is_machine_check(exit_intr_info)) + if (basic_exit_reason == EXIT_REASON_MCE_DURING_VMENTRY || + is_machine_check(exit_intr_info)) kvm_machine_check(); /* We need to handle NMIs before interrupts are enabled */ -- cgit v1.2.3-59-g8ed1b From 949c033694864082db9b3f5304723a6d7407f8e2 Mon Sep 17 00:00:00 2001 From: Gleb Fotengauer-Malinovskiy Date: Tue, 11 Jul 2017 00:22:33 +0300 Subject: KVM: s390: Fix KVM_S390_GET_CMMA_BITS ioctl definition MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In case of KVM_S390_GET_CMMA_BITS, the kernel does not only read struct kvm_s390_cmma_log passed from userspace (which constitutes _IOC_WRITE), it also writes back a return value (which constitutes _IOC_READ) making this an _IOWR ioctl instead of _IOW. Fixes: 4036e387 ("KVM: s390: ioctls to get and set guest storage attributes") Signed-off-by: Gleb Fotengauer-Malinovskiy Acked-by: Christian Borntraeger Signed-off-by: Radim Krčmář --- include/uapi/linux/kvm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index c0b6dfec5f87..ebd604c222d8 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1351,7 +1351,7 @@ struct kvm_s390_ucas_mapping { /* Available with KVM_CAP_X86_SMM */ #define KVM_SMI _IO(KVMIO, 0xb7) /* Available with KVM_CAP_S390_CMMA_MIGRATION */ -#define KVM_S390_GET_CMMA_BITS _IOW(KVMIO, 0xb8, struct kvm_s390_cmma_log) +#define KVM_S390_GET_CMMA_BITS _IOWR(KVMIO, 0xb8, struct kvm_s390_cmma_log) #define KVM_S390_SET_CMMA_BITS _IOW(KVMIO, 0xb9, struct kvm_s390_cmma_log) #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) -- cgit v1.2.3-59-g8ed1b From fb5307298e49ec1668c3a9ec888c1b9da4347395 Mon Sep 17 00:00:00 2001 From: Radim Krčmář Date: Mon, 10 Jul 2017 20:53:28 +0200 Subject: KVM: x86: take slots_lock in kvm_free_pit MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit kvm_vm_release() did not have slots_lock when calling kvm_io_bus_unregister_dev() and this went unnoticed until 4a12f9517728 ("KVM: mark kvm->busses as rcu protected") added dynamic checks. Luckily, there should be no race at that point: ============================= WARNING: suspicious RCU usage 4.12.0.kvm+ #0 Not tainted ----------------------------- ./include/linux/kvm_host.h:479 suspicious rcu_dereference_check() usage! lockdep_rcu_suspicious+0xc5/0x100 kvm_io_bus_unregister_dev+0x173/0x190 [kvm] kvm_free_pit+0x28/0x80 [kvm] kvm_arch_sync_events+0x2d/0x30 [kvm] kvm_put_kvm+0xa7/0x2a0 [kvm] kvm_vm_release+0x21/0x30 [kvm] Reviewed-by: David Hildenbrand Signed-off-by: Radim Krčmář --- arch/x86/kvm/i8254.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index a78b445ce411..af192895b1fc 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -724,8 +724,10 @@ void kvm_free_pit(struct kvm *kvm) struct kvm_pit *pit = kvm->arch.vpit; if (pit) { + mutex_lock(&kvm->slots_lock); kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &pit->dev); kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &pit->speaker_dev); + mutex_unlock(&kvm->slots_lock); kvm_pit_set_reinject(pit, false); hrtimer_cancel(&pit->pit_state.timer); kthread_destroy_worker(pit->worker); -- cgit v1.2.3-59-g8ed1b From b742c1e6e79ddf4192d76336da2407c65ca7242f Mon Sep 17 00:00:00 2001 From: Ladi Prosek Date: Thu, 22 Jun 2017 09:05:26 +0200 Subject: KVM: SVM: handle singlestep exception when skipping emulated instructions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit kvm_skip_emulated_instruction handles the singlestep debug exception which is something we almost always want. This commit (specifically the change in rdmsr_interception) makes the debug.flat KVM unit test pass on AMD. Two call sites still call skip_emulated_instruction directly: * In svm_queue_exception where it's used only for moving the rip forward * In task_switch_interception which is analogous to handle_task_switch in VMX Signed-off-by: Ladi Prosek Signed-off-by: Radim Krčmář --- arch/x86/kvm/svm.c | 59 ++++++++++++++++++++++++++++++------------------------ 1 file changed, 33 insertions(+), 26 deletions(-) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 905ea6052517..3da42d7c629e 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -2267,7 +2267,7 @@ static int io_interception(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu = &svm->vcpu; u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */ - int size, in, string; + int size, in, string, ret; unsigned port; ++svm->vcpu.stat.io_exits; @@ -2279,10 +2279,16 @@ static int io_interception(struct vcpu_svm *svm) port = io_info >> 16; size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; svm->next_rip = svm->vmcb->control.exit_info_2; - skip_emulated_instruction(&svm->vcpu); + ret = kvm_skip_emulated_instruction(&svm->vcpu); - return in ? kvm_fast_pio_in(vcpu, size, port) - : kvm_fast_pio_out(vcpu, size, port); + /* + * TODO: we might be squashing a KVM_GUESTDBG_SINGLESTEP-triggered + * KVM_EXIT_DEBUG here. + */ + if (in) + return kvm_fast_pio_in(vcpu, size, port) && ret; + else + return kvm_fast_pio_out(vcpu, size, port) && ret; } static int nmi_interception(struct vcpu_svm *svm) @@ -3055,6 +3061,7 @@ static int vmload_interception(struct vcpu_svm *svm) { struct vmcb *nested_vmcb; struct page *page; + int ret; if (nested_svm_check_permissions(svm)) return 1; @@ -3064,18 +3071,19 @@ static int vmload_interception(struct vcpu_svm *svm) return 1; svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; - skip_emulated_instruction(&svm->vcpu); + ret = kvm_skip_emulated_instruction(&svm->vcpu); nested_svm_vmloadsave(nested_vmcb, svm->vmcb); nested_svm_unmap(page); - return 1; + return ret; } static int vmsave_interception(struct vcpu_svm *svm) { struct vmcb *nested_vmcb; struct page *page; + int ret; if (nested_svm_check_permissions(svm)) return 1; @@ -3085,12 +3093,12 @@ static int vmsave_interception(struct vcpu_svm *svm) return 1; svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; - skip_emulated_instruction(&svm->vcpu); + ret = kvm_skip_emulated_instruction(&svm->vcpu); nested_svm_vmloadsave(svm->vmcb, nested_vmcb); nested_svm_unmap(page); - return 1; + return ret; } static int vmrun_interception(struct vcpu_svm *svm) @@ -3123,25 +3131,29 @@ failed: static int stgi_interception(struct vcpu_svm *svm) { + int ret; + if (nested_svm_check_permissions(svm)) return 1; svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; - skip_emulated_instruction(&svm->vcpu); + ret = kvm_skip_emulated_instruction(&svm->vcpu); kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); enable_gif(svm); - return 1; + return ret; } static int clgi_interception(struct vcpu_svm *svm) { + int ret; + if (nested_svm_check_permissions(svm)) return 1; svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; - skip_emulated_instruction(&svm->vcpu); + ret = kvm_skip_emulated_instruction(&svm->vcpu); disable_gif(svm); @@ -3152,7 +3164,7 @@ static int clgi_interception(struct vcpu_svm *svm) mark_dirty(svm->vmcb, VMCB_INTR); } - return 1; + return ret; } static int invlpga_interception(struct vcpu_svm *svm) @@ -3166,8 +3178,7 @@ static int invlpga_interception(struct vcpu_svm *svm) kvm_mmu_invlpg(vcpu, kvm_register_read(&svm->vcpu, VCPU_REGS_RAX)); svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; - skip_emulated_instruction(&svm->vcpu); - return 1; + return kvm_skip_emulated_instruction(&svm->vcpu); } static int skinit_interception(struct vcpu_svm *svm) @@ -3190,7 +3201,7 @@ static int xsetbv_interception(struct vcpu_svm *svm) if (kvm_set_xcr(&svm->vcpu, index, new_bv) == 0) { svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; - skip_emulated_instruction(&svm->vcpu); + return kvm_skip_emulated_instruction(&svm->vcpu); } return 1; @@ -3286,8 +3297,7 @@ static int invlpg_interception(struct vcpu_svm *svm) return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; kvm_mmu_invlpg(&svm->vcpu, svm->vmcb->control.exit_info_1); - skip_emulated_instruction(&svm->vcpu); - return 1; + return kvm_skip_emulated_instruction(&svm->vcpu); } static int emulate_on_interception(struct vcpu_svm *svm) @@ -3437,9 +3447,7 @@ static int dr_interception(struct vcpu_svm *svm) kvm_register_write(&svm->vcpu, reg, val); } - skip_emulated_instruction(&svm->vcpu); - - return 1; + return kvm_skip_emulated_instruction(&svm->vcpu); } static int cr8_write_interception(struct vcpu_svm *svm) @@ -3562,6 +3570,7 @@ static int rdmsr_interception(struct vcpu_svm *svm) if (svm_get_msr(&svm->vcpu, &msr_info)) { trace_kvm_msr_read_ex(ecx); kvm_inject_gp(&svm->vcpu, 0); + return 1; } else { trace_kvm_msr_read(ecx, msr_info.data); @@ -3570,9 +3579,8 @@ static int rdmsr_interception(struct vcpu_svm *svm) kvm_register_write(&svm->vcpu, VCPU_REGS_RDX, msr_info.data >> 32); svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; - skip_emulated_instruction(&svm->vcpu); + return kvm_skip_emulated_instruction(&svm->vcpu); } - return 1; } static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data) @@ -3698,11 +3706,11 @@ static int wrmsr_interception(struct vcpu_svm *svm) if (kvm_set_msr(&svm->vcpu, &msr)) { trace_kvm_msr_write_ex(ecx, data); kvm_inject_gp(&svm->vcpu, 0); + return 1; } else { trace_kvm_msr_write(ecx, data); - skip_emulated_instruction(&svm->vcpu); + return kvm_skip_emulated_instruction(&svm->vcpu); } - return 1; } static int msr_interception(struct vcpu_svm *svm) @@ -3731,8 +3739,7 @@ static int pause_interception(struct vcpu_svm *svm) static int nop_interception(struct vcpu_svm *svm) { - skip_emulated_instruction(&(svm->vcpu)); - return 1; + return kvm_skip_emulated_instruction(&(svm->vcpu)); } static int monitor_interception(struct vcpu_svm *svm) -- cgit v1.2.3-59-g8ed1b From 8a77e90966e92759f94087f9845d413290be0d70 Mon Sep 17 00:00:00 2001 From: Janakarajan Natarajan Date: Thu, 6 Jul 2017 15:50:44 -0500 Subject: KVM: SVM: Prepare for new bit definition in lbr_ctl MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The lbr_ctl variable in the vmcb control area is used to enable or disable Last Branch Record (LBR) virtualization. However, this is to be done using only bit 0 of the variable. To correct this and to prepare for a new feature, change the current usage to work only on a particular bit. Signed-off-by: Janakarajan Natarajan Reviewed-by: Paolo Bonzini Signed-off-by: Radim Krčmář --- arch/x86/include/asm/svm.h | 2 ++ arch/x86/kvm/svm.c | 4 ++-- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 14824fc78f7e..d1163f64d732 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -119,6 +119,8 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define AVIC_ENABLE_SHIFT 31 #define AVIC_ENABLE_MASK (1 << AVIC_ENABLE_SHIFT) +#define LBR_CTL_ENABLE_MASK BIT_ULL(0) + #define SVM_INTERRUPT_SHADOW_MASK 1 #define SVM_IOIO_STR_SHIFT 2 diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 3da42d7c629e..6e72127c0d0e 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -947,7 +947,7 @@ static void svm_enable_lbrv(struct vcpu_svm *svm) { u32 *msrpm = svm->msrpm; - svm->vmcb->control.lbr_ctl = 1; + svm->vmcb->control.lbr_ctl |= LBR_CTL_ENABLE_MASK; set_msr_interception(msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1); set_msr_interception(msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1); set_msr_interception(msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); @@ -958,7 +958,7 @@ static void svm_disable_lbrv(struct vcpu_svm *svm) { u32 *msrpm = svm->msrpm; - svm->vmcb->control.lbr_ctl = 0; + svm->vmcb->control.lbr_ctl &= ~LBR_CTL_ENABLE_MASK; set_msr_interception(msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0); set_msr_interception(msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0); set_msr_interception(msrpm, MSR_IA32_LASTINTFROMIP, 0, 0); -- cgit v1.2.3-59-g8ed1b From 0dc92119b50be539a5480d72a00ae8098bdba2fc Mon Sep 17 00:00:00 2001 From: Janakarajan Natarajan Date: Thu, 6 Jul 2017 15:50:45 -0500 Subject: KVM: SVM: Rename lbr_ctl field in the vmcb control area MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rename the lbr_ctl variable to better reflect the purpose of the field - provide support for virtualization extensions. Signed-off-by: Janakarajan Natarajan Reviewed-by: Paolo Bonzini Signed-off-by: Radim Krčmář --- arch/x86/include/asm/svm.h | 2 +- arch/x86/kvm/svm.c | 10 +++++----- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index d1163f64d732..74d139352491 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -83,7 +83,7 @@ struct __attribute__ ((__packed__)) vmcb_control_area { u32 event_inj; u32 event_inj_err; u64 nested_cr3; - u64 lbr_ctl; + u64 virt_ext; u32 clean; u32 reserved_5; u64 next_rip; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 6e72127c0d0e..9a09f89145f2 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -947,7 +947,7 @@ static void svm_enable_lbrv(struct vcpu_svm *svm) { u32 *msrpm = svm->msrpm; - svm->vmcb->control.lbr_ctl |= LBR_CTL_ENABLE_MASK; + svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK; set_msr_interception(msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1); set_msr_interception(msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1); set_msr_interception(msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); @@ -958,7 +958,7 @@ static void svm_disable_lbrv(struct vcpu_svm *svm) { u32 *msrpm = svm->msrpm; - svm->vmcb->control.lbr_ctl &= ~LBR_CTL_ENABLE_MASK; + svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK; set_msr_interception(msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0); set_msr_interception(msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0); set_msr_interception(msrpm, MSR_IA32_LASTINTFROMIP, 0, 0); @@ -2708,7 +2708,7 @@ static inline void copy_vmcb_control_area(struct vmcb *dst_vmcb, struct vmcb *fr dst->event_inj = from->event_inj; dst->event_inj_err = from->event_inj_err; dst->nested_cr3 = from->nested_cr3; - dst->lbr_ctl = from->lbr_ctl; + dst->virt_ext = from->virt_ext; } static int nested_svm_vmexit(struct vcpu_svm *svm) @@ -3014,7 +3014,7 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) /* We don't want to see VMMCALLs from a nested guest */ clr_intercept(svm, INTERCEPT_VMMCALL); - svm->vmcb->control.lbr_ctl = nested_vmcb->control.lbr_ctl; + svm->vmcb->control.virt_ext = nested_vmcb->control.virt_ext; svm->vmcb->control.int_vector = nested_vmcb->control.int_vector; svm->vmcb->control.int_state = nested_vmcb->control.int_state; svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset; @@ -4124,7 +4124,7 @@ static void dump_vmcb(struct kvm_vcpu *vcpu) pr_err("%-20s%016llx\n", "avic_vapic_bar:", control->avic_vapic_bar); pr_err("%-20s%08x\n", "event_inj:", control->event_inj); pr_err("%-20s%08x\n", "event_inj_err:", control->event_inj_err); - pr_err("%-20s%lld\n", "lbr_ctl:", control->lbr_ctl); + pr_err("%-20s%lld\n", "virt_ext:", control->virt_ext); pr_err("%-20s%016llx\n", "next_rip:", control->next_rip); pr_err("%-20s%016llx\n", "avic_backing_page:", control->avic_backing_page); pr_err("%-20s%016llx\n", "avic_logical_id:", control->avic_logical_id); -- cgit v1.2.3-59-g8ed1b From 76ff359249f1e80ff0d6ced3b52b1088c4e61b9b Mon Sep 17 00:00:00 2001 From: Janakarajan Natarajan Date: Thu, 6 Jul 2017 15:50:46 -0500 Subject: KVM: SVM: Add Virtual VMLOAD VMSAVE feature definition MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Define a new cpufeature definition for Virtual VMLOAD VMSAVE. Signed-off-by: Janakarajan Natarajan Reviewed-by: Paolo Bonzini Signed-off-by: Radim Krčmář --- arch/x86/include/asm/cpufeatures.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 2701e5f8145b..ca3c48c0872f 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -286,6 +286,7 @@ #define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */ #define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ #define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ +#define X86_FEATURE_VIRTUAL_VMLOAD_VMSAVE (15*32+15) /* Virtual VMLOAD VMSAVE */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */ #define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ -- cgit v1.2.3-59-g8ed1b From 89c8a4984fc98e625517bfe5083342d77ee35811 Mon Sep 17 00:00:00 2001 From: Janakarajan Natarajan Date: Thu, 6 Jul 2017 15:50:47 -0500 Subject: KVM: SVM: Enable Virtual VMLOAD VMSAVE feature MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Enable the Virtual VMLOAD VMSAVE feature. This is done by setting bit 1 at position B8h in the vmcb. The processor must have nested paging enabled, be in 64-bit mode and have support for the Virtual VMLOAD VMSAVE feature for the bit to be set in the vmcb. Signed-off-by: Janakarajan Natarajan Reviewed-by: Paolo Bonzini Signed-off-by: Radim Krčmář --- arch/x86/include/asm/svm.h | 1 + arch/x86/kvm/svm.c | 24 ++++++++++++++++++++++++ 2 files changed, 25 insertions(+) diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 74d139352491..58fffe79e417 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -120,6 +120,7 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define AVIC_ENABLE_MASK (1 << AVIC_ENABLE_SHIFT) #define LBR_CTL_ENABLE_MASK BIT_ULL(0) +#define VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK BIT_ULL(1) #define SVM_INTERRUPT_SHADOW_MASK 1 diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 9a09f89145f2..4c98d362e3e4 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -277,6 +277,10 @@ static int avic; module_param(avic, int, S_IRUGO); #endif +/* enable/disable Virtual VMLOAD VMSAVE */ +static int vls = true; +module_param(vls, int, 0444); + /* AVIC VM ID bit masks and lock */ static DECLARE_BITMAP(avic_vm_id_bitmap, AVIC_VM_ID_NR); static DEFINE_SPINLOCK(avic_vm_id_lock); @@ -1093,6 +1097,16 @@ static __init int svm_hardware_setup(void) } } + if (vls) { + if (!npt_enabled || + !boot_cpu_has(X86_FEATURE_VIRTUAL_VMLOAD_VMSAVE) || + !IS_ENABLED(CONFIG_X86_64)) { + vls = false; + } else { + pr_info("Virtual VMLOAD VMSAVE supported\n"); + } + } + return 0; err: @@ -1280,6 +1294,16 @@ static void init_vmcb(struct vcpu_svm *svm) if (avic) avic_init_vmcb(svm); + /* + * If hardware supports Virtual VMLOAD VMSAVE then enable it + * in VMCB and clear intercepts to avoid #VMEXIT. + */ + if (vls) { + clr_intercept(svm, INTERCEPT_VMLOAD); + clr_intercept(svm, INTERCEPT_VMSAVE); + svm->vmcb->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; + } + mark_all_dirty(svm->vmcb); enable_gif(svm); -- cgit v1.2.3-59-g8ed1b From 286de8f6ac9202f1c9012784639156c6ec386eb8 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Wed, 12 Jul 2017 17:56:44 +0200 Subject: KVM: trigger uevents when creating or destroying a VM MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds a few lines to the KVM common code to fire a KOBJ_CHANGE uevent whenever a KVM VM is created or destroyed. The event carries five environment variables: CREATED indicates how many times a new VM has been created. It is useful for example to trigger specific actions when the first VM is started COUNT indicates how many VMs are currently active. This can be used for logging or monitoring purposes PID has the pid of the KVM process that has been started or stopped. This can be used to perform process-specific tuning. STATS_PATH contains the path in debugfs to the directory with all the runtime statistics for this VM. This is useful for performance monitoring and profiling. EVENT described the type of event, its value can be either "create" or "destroy" Specific udev rules can be then set up in userspace to deal with the creation or destruction of VMs as needed. Signed-off-by: Claudio Imbrenda Signed-off-by: Radim Krčmář --- virt/kvm/kvm_main.c | 69 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 69 insertions(+) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 7766c2b52797..82987d457b8b 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -130,6 +130,12 @@ EXPORT_SYMBOL_GPL(kvm_rebooting); static bool largepages_enabled = true; +#define KVM_EVENT_CREATE_VM 0 +#define KVM_EVENT_DESTROY_VM 1 +static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm); +static unsigned long long kvm_createvm_count; +static unsigned long long kvm_active_vms; + bool kvm_is_reserved_pfn(kvm_pfn_t pfn) { if (pfn_valid(pfn)) @@ -740,6 +746,7 @@ static void kvm_destroy_vm(struct kvm *kvm) int i; struct mm_struct *mm = kvm->mm; + kvm_uevent_notify_change(KVM_EVENT_DESTROY_VM, kvm); kvm_destroy_vm_debugfs(kvm); kvm_arch_sync_events(kvm); spin_lock(&kvm_lock); @@ -3220,6 +3227,7 @@ static int kvm_dev_ioctl_create_vm(unsigned long type) fput(file); return -ENOMEM; } + kvm_uevent_notify_change(KVM_EVENT_CREATE_VM, kvm); fd_install(r, file); return r; @@ -3872,6 +3880,67 @@ static const struct file_operations *stat_fops[] = { [KVM_STAT_VM] = &vm_stat_fops, }; +static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) +{ + struct kobj_uevent_env *env; + char *tmp, *pathbuf = NULL; + unsigned long long created, active; + + if (!kvm_dev.this_device || !kvm) + return; + + spin_lock(&kvm_lock); + if (type == KVM_EVENT_CREATE_VM) { + kvm_createvm_count++; + kvm_active_vms++; + } else if (type == KVM_EVENT_DESTROY_VM) { + kvm_active_vms--; + } + created = kvm_createvm_count; + active = kvm_active_vms; + spin_unlock(&kvm_lock); + + env = kzalloc(sizeof(*env), GFP_KERNEL); + if (!env) + return; + + add_uevent_var(env, "CREATED=%llu", created); + add_uevent_var(env, "COUNT=%llu", active); + + if (type == KVM_EVENT_CREATE_VM) + add_uevent_var(env, "EVENT=create"); + else if (type == KVM_EVENT_DESTROY_VM) + add_uevent_var(env, "EVENT=destroy"); + + if (kvm->debugfs_dentry) { + char p[ITOA_MAX_LEN]; + + snprintf(p, sizeof(p), "%s", kvm->debugfs_dentry->d_name.name); + tmp = strchrnul(p + 1, '-'); + *tmp = '\0'; + add_uevent_var(env, "PID=%s", p); + pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); + if (pathbuf) { + /* sizeof counts the final '\0' */ + int len = sizeof("STATS_PATH=") - 1; + const char *pvar = "STATS_PATH="; + + tmp = dentry_path_raw(kvm->debugfs_dentry, + pathbuf + len, + PATH_MAX - len); + if (!IS_ERR(tmp)) { + memcpy(tmp - len, pvar, len); + env->envp[env->envp_idx++] = tmp - len; + } + } + } + /* no need for checks, since we are adding at most only 5 keys */ + env->envp[env->envp_idx++] = NULL; + kobject_uevent_env(&kvm_dev.this_device->kobj, KOBJ_CHANGE, env->envp); + kfree(env); + kfree(pathbuf); +} + static int kvm_init_debug(void) { int r = -EEXIST; -- cgit v1.2.3-59-g8ed1b From c57ec8fb7c025322f25a077afc94e0ef18cc3d89 Mon Sep 17 00:00:00 2001 From: Nilesh Javali Date: Tue, 27 Jun 2017 02:26:56 -0700 Subject: scsi: qedi: Add support for Boot from SAN over iSCSI offload This patch adds support for Boot from SAN over iSCSI offload. The iSCSI boot information in the NVRAM is populated under /sys/firmware/iscsi_bootX/ using qed NVM-image reading API and further exported to open-iscsi to perform iSCSI login enabling boot over offload iSCSI interface in a Boot from SAN environment. Signed-off-by: Arun Easi Signed-off-by: Andrew Vasquez Signed-off-by: Manish Rangankar Signed-off-by: Nilesh Javali Signed-off-by: Martin K. Petersen --- drivers/scsi/qedi/qedi.h | 17 ++ drivers/scsi/qedi/qedi_main.c | 419 +++++++++++++++++++++++++++++++++ drivers/scsi/qedi/qedi_nvm_iscsi_cfg.h | 210 +++++++++++++++++ 3 files changed, 646 insertions(+) create mode 100644 drivers/scsi/qedi/qedi_nvm_iscsi_cfg.h diff --git a/drivers/scsi/qedi/qedi.h b/drivers/scsi/qedi/qedi.h index 32632c9b2276..91d2f51c351b 100644 --- a/drivers/scsi/qedi/qedi.h +++ b/drivers/scsi/qedi/qedi.h @@ -23,11 +23,17 @@ #include #include #include "qedi_version.h" +#include "qedi_nvm_iscsi_cfg.h" #define QEDI_MODULE_NAME "qedi" struct qedi_endpoint; +#ifndef GET_FIELD2 +#define GET_FIELD2(value, name) \ + (((value) & (name ## _MASK)) >> (name ## _OFFSET)) +#endif + /* * PCI function probe defines */ @@ -66,6 +72,11 @@ struct qedi_endpoint; #define QEDI_HW_DMA_BOUNDARY 0xfff #define QEDI_PATH_HANDLE 0xFE0000000UL +enum qedi_nvm_tgts { + QEDI_NVM_TGT_PRI, + QEDI_NVM_TGT_SEC, +}; + struct qedi_uio_ctrl { /* meta data */ u32 uio_hsi_version; @@ -283,6 +294,8 @@ struct qedi_ctx { void *bdq_pbl_list; dma_addr_t bdq_pbl_list_dma; u8 bdq_pbl_list_num_entries; + struct nvm_iscsi_cfg *iscsi_cfg; + dma_addr_t nvm_buf_dma; void __iomem *bdq_primary_prod; void __iomem *bdq_secondary_prod; u16 bdq_prod_idx; @@ -337,6 +350,10 @@ struct qedi_ctx { bool use_fast_sge; atomic_t num_offloads; +#define SYSFS_FLAG_FW_SEL_BOOT 2 +#define IPV6_LEN 41 +#define IPV4_LEN 17 + struct iscsi_boot_kset *boot_kset; }; struct qedi_work { diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index 5f5a4ef2e529..2c3783684815 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -1143,6 +1144,30 @@ exit_setup_int: return rc; } +static void qedi_free_nvm_iscsi_cfg(struct qedi_ctx *qedi) +{ + if (qedi->iscsi_cfg) + dma_free_coherent(&qedi->pdev->dev, + sizeof(struct nvm_iscsi_cfg), + qedi->iscsi_cfg, qedi->nvm_buf_dma); +} + +static int qedi_alloc_nvm_iscsi_cfg(struct qedi_ctx *qedi) +{ + qedi->iscsi_cfg = dma_zalloc_coherent(&qedi->pdev->dev, + sizeof(struct nvm_iscsi_cfg), + &qedi->nvm_buf_dma, GFP_KERNEL); + if (!qedi->iscsi_cfg) { + QEDI_ERR(&qedi->dbg_ctx, "Could not allocate NVM BUF.\n"); + return -ENOMEM; + } + QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, + "NVM BUF addr=0x%p dma=0x%llx.\n", qedi->iscsi_cfg, + qedi->nvm_buf_dma); + + return 0; +} + static void qedi_free_bdq(struct qedi_ctx *qedi) { int i; @@ -1183,6 +1208,7 @@ static void qedi_free_global_queues(struct qedi_ctx *qedi) kfree(gl[i]); } qedi_free_bdq(qedi); + qedi_free_nvm_iscsi_cfg(qedi); } static int qedi_alloc_bdq(struct qedi_ctx *qedi) @@ -1309,6 +1335,11 @@ static int qedi_alloc_global_queues(struct qedi_ctx *qedi) if (rc) goto mem_alloc_failure; + /* Allocate DMA coherent buffers for NVM_ISCSI_CFG */ + rc = qedi_alloc_nvm_iscsi_cfg(qedi); + if (rc) + goto mem_alloc_failure; + /* Allocate a CQ and an associated PBL for each MSI-X * vector. */ @@ -1671,6 +1702,387 @@ void qedi_reset_host_mtu(struct qedi_ctx *qedi, u16 mtu) qedi_ops->ll2->start(qedi->cdev, ¶ms); } +/** + * qedi_get_nvram_block: - Scan through the iSCSI NVRAM block (while accounting + * for gaps) for the matching absolute-pf-id of the QEDI device. + */ +static struct nvm_iscsi_block * +qedi_get_nvram_block(struct qedi_ctx *qedi) +{ + int i; + u8 pf; + u32 flags; + struct nvm_iscsi_block *block; + + pf = qedi->dev_info.common.abs_pf_id; + block = &qedi->iscsi_cfg->block[0]; + for (i = 0; i < NUM_OF_ISCSI_PF_SUPPORTED; i++, block++) { + flags = ((block->id) & NVM_ISCSI_CFG_BLK_CTRL_FLAG_MASK) >> + NVM_ISCSI_CFG_BLK_CTRL_FLAG_OFFSET; + if (flags & (NVM_ISCSI_CFG_BLK_CTRL_FLAG_IS_NOT_EMPTY | + NVM_ISCSI_CFG_BLK_CTRL_FLAG_PF_MAPPED) && + (pf == (block->id & NVM_ISCSI_CFG_BLK_MAPPED_PF_ID_MASK) + >> NVM_ISCSI_CFG_BLK_MAPPED_PF_ID_OFFSET)) + return block; + } + return NULL; +} + +static ssize_t qedi_show_boot_eth_info(void *data, int type, char *buf) +{ + struct qedi_ctx *qedi = data; + struct nvm_iscsi_initiator *initiator; + char *str = buf; + int rc = 1; + u32 ipv6_en, dhcp_en, ip_len; + struct nvm_iscsi_block *block; + char *fmt, *ip, *sub, *gw; + + block = qedi_get_nvram_block(qedi); + if (!block) + return 0; + + initiator = &block->initiator; + ipv6_en = block->generic.ctrl_flags & + NVM_ISCSI_CFG_GEN_IPV6_ENABLED; + dhcp_en = block->generic.ctrl_flags & + NVM_ISCSI_CFG_GEN_DHCP_TCPIP_CONFIG_ENABLED; + /* Static IP assignments. */ + fmt = ipv6_en ? "%pI6\n" : "%pI4\n"; + ip = ipv6_en ? initiator->ipv6.addr.byte : initiator->ipv4.addr.byte; + ip_len = ipv6_en ? IPV6_LEN : IPV4_LEN; + sub = ipv6_en ? initiator->ipv6.subnet_mask.byte : + initiator->ipv4.subnet_mask.byte; + gw = ipv6_en ? initiator->ipv6.gateway.byte : + initiator->ipv4.gateway.byte; + /* DHCP IP adjustments. */ + fmt = dhcp_en ? "%s\n" : fmt; + if (dhcp_en) { + ip = ipv6_en ? "0::0" : "0.0.0.0"; + sub = ip; + gw = ip; + ip_len = ipv6_en ? 5 : 8; + } + + switch (type) { + case ISCSI_BOOT_ETH_IP_ADDR: + rc = snprintf(str, ip_len, fmt, ip); + break; + case ISCSI_BOOT_ETH_SUBNET_MASK: + rc = snprintf(str, ip_len, fmt, sub); + break; + case ISCSI_BOOT_ETH_GATEWAY: + rc = snprintf(str, ip_len, fmt, gw); + break; + case ISCSI_BOOT_ETH_FLAGS: + rc = snprintf(str, 3, "%hhd\n", + SYSFS_FLAG_FW_SEL_BOOT); + break; + case ISCSI_BOOT_ETH_INDEX: + rc = snprintf(str, 3, "0\n"); + break; + case ISCSI_BOOT_ETH_MAC: + rc = sysfs_format_mac(str, qedi->mac, ETH_ALEN); + break; + case ISCSI_BOOT_ETH_VLAN: + rc = snprintf(str, 12, "%d\n", + GET_FIELD2(initiator->generic_cont0, + NVM_ISCSI_CFG_INITIATOR_VLAN)); + break; + case ISCSI_BOOT_ETH_ORIGIN: + if (dhcp_en) + rc = snprintf(str, 3, "3\n"); + break; + default: + rc = 0; + break; + } + + return rc; +} + +static umode_t qedi_eth_get_attr_visibility(void *data, int type) +{ + int rc = 1; + + switch (type) { + case ISCSI_BOOT_ETH_FLAGS: + case ISCSI_BOOT_ETH_MAC: + case ISCSI_BOOT_ETH_INDEX: + case ISCSI_BOOT_ETH_IP_ADDR: + case ISCSI_BOOT_ETH_SUBNET_MASK: + case ISCSI_BOOT_ETH_GATEWAY: + case ISCSI_BOOT_ETH_ORIGIN: + case ISCSI_BOOT_ETH_VLAN: + rc = 0444; + break; + default: + rc = 0; + break; + } + return rc; +} + +static ssize_t qedi_show_boot_ini_info(void *data, int type, char *buf) +{ + struct qedi_ctx *qedi = data; + struct nvm_iscsi_initiator *initiator; + char *str = buf; + int rc; + struct nvm_iscsi_block *block; + + block = qedi_get_nvram_block(qedi); + if (!block) + return 0; + + initiator = &block->initiator; + + switch (type) { + case ISCSI_BOOT_INI_INITIATOR_NAME: + rc = snprintf(str, NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN, "%s\n", + initiator->initiator_name.byte); + break; + default: + rc = 0; + break; + } + return rc; +} + +static umode_t qedi_ini_get_attr_visibility(void *data, int type) +{ + int rc; + + switch (type) { + case ISCSI_BOOT_INI_INITIATOR_NAME: + rc = 0444; + break; + default: + rc = 0; + break; + } + return rc; +} + +static ssize_t +qedi_show_boot_tgt_info(struct qedi_ctx *qedi, int type, + char *buf, enum qedi_nvm_tgts idx) +{ + char *str = buf; + int rc = 1; + u32 ctrl_flags, ipv6_en, chap_en, mchap_en, ip_len; + struct nvm_iscsi_block *block; + char *chap_name, *chap_secret; + char *mchap_name, *mchap_secret; + + block = qedi_get_nvram_block(qedi); + if (!block) + goto exit_show_tgt_info; + + QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_EVT, + "Port:%d, tgt_idx:%d\n", + GET_FIELD2(block->id, NVM_ISCSI_CFG_BLK_MAPPED_PF_ID), idx); + + ctrl_flags = block->target[idx].ctrl_flags & + NVM_ISCSI_CFG_TARGET_ENABLED; + + if (!ctrl_flags) { + QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_EVT, + "Target disabled\n"); + goto exit_show_tgt_info; + } + + ipv6_en = block->generic.ctrl_flags & + NVM_ISCSI_CFG_GEN_IPV6_ENABLED; + ip_len = ipv6_en ? IPV6_LEN : IPV4_LEN; + chap_en = block->generic.ctrl_flags & + NVM_ISCSI_CFG_GEN_CHAP_ENABLED; + chap_name = chap_en ? block->initiator.chap_name.byte : NULL; + chap_secret = chap_en ? block->initiator.chap_password.byte : NULL; + + mchap_en = block->generic.ctrl_flags & + NVM_ISCSI_CFG_GEN_CHAP_MUTUAL_ENABLED; + mchap_name = mchap_en ? block->target[idx].chap_name.byte : NULL; + mchap_secret = mchap_en ? block->target[idx].chap_password.byte : NULL; + + switch (type) { + case ISCSI_BOOT_TGT_NAME: + rc = snprintf(str, NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN, "%s\n", + block->target[idx].target_name.byte); + break; + case ISCSI_BOOT_TGT_IP_ADDR: + if (ipv6_en) + rc = snprintf(str, ip_len, "%pI6\n", + block->target[idx].ipv6_addr.byte); + else + rc = snprintf(str, ip_len, "%pI4\n", + block->target[idx].ipv4_addr.byte); + break; + case ISCSI_BOOT_TGT_PORT: + rc = snprintf(str, 12, "%d\n", + GET_FIELD2(block->target[idx].generic_cont0, + NVM_ISCSI_CFG_TARGET_TCP_PORT)); + break; + case ISCSI_BOOT_TGT_LUN: + rc = snprintf(str, 22, "%.*d\n", + block->target[idx].lun.value[1], + block->target[idx].lun.value[0]); + break; + case ISCSI_BOOT_TGT_CHAP_NAME: + rc = snprintf(str, NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN, "%s\n", + chap_name); + break; + case ISCSI_BOOT_TGT_CHAP_SECRET: + rc = snprintf(str, NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN, "%s\n", + chap_secret); + break; + case ISCSI_BOOT_TGT_REV_CHAP_NAME: + rc = snprintf(str, NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN, "%s\n", + mchap_name); + break; + case ISCSI_BOOT_TGT_REV_CHAP_SECRET: + rc = snprintf(str, NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN, "%s\n", + mchap_secret); + break; + case ISCSI_BOOT_TGT_FLAGS: + rc = snprintf(str, 3, "%hhd\n", SYSFS_FLAG_FW_SEL_BOOT); + break; + case ISCSI_BOOT_TGT_NIC_ASSOC: + rc = snprintf(str, 3, "0\n"); + break; + default: + rc = 0; + break; + } + +exit_show_tgt_info: + return rc; +} + +static ssize_t qedi_show_boot_tgt_pri_info(void *data, int type, char *buf) +{ + struct qedi_ctx *qedi = data; + + return qedi_show_boot_tgt_info(qedi, type, buf, QEDI_NVM_TGT_PRI); +} + +static ssize_t qedi_show_boot_tgt_sec_info(void *data, int type, char *buf) +{ + struct qedi_ctx *qedi = data; + + return qedi_show_boot_tgt_info(qedi, type, buf, QEDI_NVM_TGT_SEC); +} + +static umode_t qedi_tgt_get_attr_visibility(void *data, int type) +{ + int rc; + + switch (type) { + case ISCSI_BOOT_TGT_NAME: + case ISCSI_BOOT_TGT_IP_ADDR: + case ISCSI_BOOT_TGT_PORT: + case ISCSI_BOOT_TGT_LUN: + case ISCSI_BOOT_TGT_CHAP_NAME: + case ISCSI_BOOT_TGT_CHAP_SECRET: + case ISCSI_BOOT_TGT_REV_CHAP_NAME: + case ISCSI_BOOT_TGT_REV_CHAP_SECRET: + case ISCSI_BOOT_TGT_NIC_ASSOC: + case ISCSI_BOOT_TGT_FLAGS: + rc = 0444; + break; + default: + rc = 0; + break; + } + return rc; +} + +static void qedi_boot_release(void *data) +{ + struct qedi_ctx *qedi = data; + + scsi_host_put(qedi->shost); +} + +static int qedi_get_boot_info(struct qedi_ctx *qedi) +{ + int ret = 1; + u16 len; + + len = sizeof(struct nvm_iscsi_cfg); + + QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, + "Get NVM iSCSI CFG image\n"); + ret = qedi_ops->common->nvm_get_image(qedi->cdev, + QED_NVM_IMAGE_ISCSI_CFG, + (char *)qedi->iscsi_cfg, len); + if (ret) + QEDI_ERR(&qedi->dbg_ctx, + "Could not get NVM image. ret = %d\n", ret); + + return ret; +} + +static int qedi_setup_boot_info(struct qedi_ctx *qedi) +{ + struct iscsi_boot_kobj *boot_kobj; + + if (qedi_get_boot_info(qedi)) + return -EPERM; + + qedi->boot_kset = iscsi_boot_create_host_kset(qedi->shost->host_no); + if (!qedi->boot_kset) + goto kset_free; + + if (!scsi_host_get(qedi->shost)) + goto kset_free; + + boot_kobj = iscsi_boot_create_target(qedi->boot_kset, 0, qedi, + qedi_show_boot_tgt_pri_info, + qedi_tgt_get_attr_visibility, + qedi_boot_release); + if (!boot_kobj) + goto put_host; + + if (!scsi_host_get(qedi->shost)) + goto kset_free; + + boot_kobj = iscsi_boot_create_target(qedi->boot_kset, 1, qedi, + qedi_show_boot_tgt_sec_info, + qedi_tgt_get_attr_visibility, + qedi_boot_release); + if (!boot_kobj) + goto put_host; + + if (!scsi_host_get(qedi->shost)) + goto kset_free; + + boot_kobj = iscsi_boot_create_initiator(qedi->boot_kset, 0, qedi, + qedi_show_boot_ini_info, + qedi_ini_get_attr_visibility, + qedi_boot_release); + if (!boot_kobj) + goto put_host; + + if (!scsi_host_get(qedi->shost)) + goto kset_free; + + boot_kobj = iscsi_boot_create_ethernet(qedi->boot_kset, 0, qedi, + qedi_show_boot_eth_info, + qedi_eth_get_attr_visibility, + qedi_boot_release); + if (!boot_kobj) + goto put_host; + + return 0; + +put_host: + scsi_host_put(qedi->shost); +kset_free: + iscsi_boot_destroy_kset(qedi->boot_kset); + return -ENOMEM; +} + static void __qedi_remove(struct pci_dev *pdev, int mode) { struct qedi_ctx *qedi = pci_get_drvdata(pdev); @@ -1724,6 +2136,9 @@ static void __qedi_remove(struct pci_dev *pdev, int mode) qedi->ll2_recv_thread = NULL; } qedi_ll2_free_skbs(qedi); + + if (qedi->boot_kset) + iscsi_boot_destroy_kset(qedi->boot_kset); } } @@ -1967,6 +2382,10 @@ static int __qedi_probe(struct pci_dev *pdev, int mode) /* F/w needs 1st task context memory entry for performance */ set_bit(QEDI_RESERVE_TASK_ID, qedi->task_idx_map); atomic_set(&qedi->num_offloads, 0); + + if (qedi_setup_boot_info(qedi)) + QEDI_ERR(&qedi->dbg_ctx, + "No iSCSI boot target configured\n"); } return 0; diff --git a/drivers/scsi/qedi/qedi_nvm_iscsi_cfg.h b/drivers/scsi/qedi/qedi_nvm_iscsi_cfg.h new file mode 100644 index 000000000000..df39b69b366d --- /dev/null +++ b/drivers/scsi/qedi/qedi_nvm_iscsi_cfg.h @@ -0,0 +1,210 @@ +/* + * QLogic iSCSI Offload Driver + * Copyright (c) 2016 Cavium Inc. + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef NVM_ISCSI_CFG_H +#define NVM_ISCSI_CFG_H + +#define NUM_OF_ISCSI_TARGET_PER_PF 4 /* Defined as per the + * ISCSI IBFT constraint + */ +#define NUM_OF_ISCSI_PF_SUPPORTED 4 /* One PF per Port - + * assuming 4 port card + */ + +#define NVM_ISCSI_CFG_DHCP_NAME_MAX_LEN 256 + +union nvm_iscsi_dhcp_vendor_id { + u32 value[NVM_ISCSI_CFG_DHCP_NAME_MAX_LEN / 4]; + u8 byte[NVM_ISCSI_CFG_DHCP_NAME_MAX_LEN]; +}; + +#define NVM_ISCSI_IPV4_ADDR_BYTE_LEN 4 +union nvm_iscsi_ipv4_addr { + u32 addr; + u8 byte[NVM_ISCSI_IPV4_ADDR_BYTE_LEN]; +}; + +#define NVM_ISCSI_IPV6_ADDR_BYTE_LEN 16 +union nvm_iscsi_ipv6_addr { + u32 addr[4]; + u8 byte[NVM_ISCSI_IPV6_ADDR_BYTE_LEN]; +}; + +struct nvm_iscsi_initiator_ipv4 { + union nvm_iscsi_ipv4_addr addr; /* 0x0 */ + union nvm_iscsi_ipv4_addr subnet_mask; /* 0x4 */ + union nvm_iscsi_ipv4_addr gateway; /* 0x8 */ + union nvm_iscsi_ipv4_addr primary_dns; /* 0xC */ + union nvm_iscsi_ipv4_addr secondary_dns; /* 0x10 */ + union nvm_iscsi_ipv4_addr dhcp_addr; /* 0x14 */ + + union nvm_iscsi_ipv4_addr isns_server; /* 0x18 */ + union nvm_iscsi_ipv4_addr slp_server; /* 0x1C */ + union nvm_iscsi_ipv4_addr primay_radius_server; /* 0x20 */ + union nvm_iscsi_ipv4_addr secondary_radius_server; /* 0x24 */ + + union nvm_iscsi_ipv4_addr rsvd[4]; /* 0x28 */ +}; + +struct nvm_iscsi_initiator_ipv6 { + union nvm_iscsi_ipv6_addr addr; /* 0x0 */ + union nvm_iscsi_ipv6_addr subnet_mask; /* 0x10 */ + union nvm_iscsi_ipv6_addr gateway; /* 0x20 */ + union nvm_iscsi_ipv6_addr primary_dns; /* 0x30 */ + union nvm_iscsi_ipv6_addr secondary_dns; /* 0x40 */ + union nvm_iscsi_ipv6_addr dhcp_addr; /* 0x50 */ + + union nvm_iscsi_ipv6_addr isns_server; /* 0x60 */ + union nvm_iscsi_ipv6_addr slp_server; /* 0x70 */ + union nvm_iscsi_ipv6_addr primay_radius_server; /* 0x80 */ + union nvm_iscsi_ipv6_addr secondary_radius_server; /* 0x90 */ + + union nvm_iscsi_ipv6_addr rsvd[3]; /* 0xA0 */ + + u32 config; /* 0xD0 */ +#define NVM_ISCSI_CFG_INITIATOR_IPV6_SUBNET_MASK_PREFIX_MASK 0x000000FF +#define NVM_ISCSI_CFG_INITIATOR_IPV6_SUBNET_MASK_PREFIX_OFFSET 0 + + u32 rsvd_1[3]; +}; + +#define NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN 256 +union nvm_iscsi_name { + u32 value[NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN / 4]; + u8 byte[NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN]; +}; + +#define NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN 256 +union nvm_iscsi_chap_name { + u32 value[NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN / 4]; + u8 byte[NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN]; +}; + +#define NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN 16 /* md5 need per RFC1996 + * is 16 octets + */ +union nvm_iscsi_chap_password { + u32 value[NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN / 4]; + u8 byte[NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN]; +}; + +union nvm_iscsi_lun { + u8 byte[8]; + u32 value[2]; +}; + +struct nvm_iscsi_generic { + u32 ctrl_flags; /* 0x0 */ +#define NVM_ISCSI_CFG_GEN_CHAP_ENABLED BIT(0) +#define NVM_ISCSI_CFG_GEN_DHCP_TCPIP_CONFIG_ENABLED BIT(1) +#define NVM_ISCSI_CFG_GEN_DHCP_ISCSI_CONFIG_ENABLED BIT(2) +#define NVM_ISCSI_CFG_GEN_IPV6_ENABLED BIT(3) +#define NVM_ISCSI_CFG_GEN_IPV4_FALLBACK_ENABLED BIT(4) +#define NVM_ISCSI_CFG_GEN_ISNS_WORLD_LOGIN BIT(5) +#define NVM_ISCSI_CFG_GEN_ISNS_SELECTIVE_LOGIN BIT(6) +#define NVM_ISCSI_CFG_GEN_ADDR_REDIRECT_ENABLED BIT(7) +#define NVM_ISCSI_CFG_GEN_CHAP_MUTUAL_ENABLED BIT(8) + + u32 timeout; /* 0x4 */ +#define NVM_ISCSI_CFG_GEN_DHCP_REQUEST_TIMEOUT_MASK 0x0000FFFF +#define NVM_ISCSI_CFG_GEN_DHCP_REQUEST_TIMEOUT_OFFSET 0 +#define NVM_ISCSI_CFG_GEN_PORT_LOGIN_TIMEOUT_MASK 0xFFFF0000 +#define NVM_ISCSI_CFG_GEN_PORT_LOGIN_TIMEOUT_OFFSET 16 + + union nvm_iscsi_dhcp_vendor_id dhcp_vendor_id; /* 0x8 */ + u32 rsvd[62]; /* 0x108 */ +}; + +struct nvm_iscsi_initiator { + struct nvm_iscsi_initiator_ipv4 ipv4; /* 0x0 */ + struct nvm_iscsi_initiator_ipv6 ipv6; /* 0x38 */ + + union nvm_iscsi_name initiator_name; /* 0x118 */ + union nvm_iscsi_chap_name chap_name; /* 0x218 */ + union nvm_iscsi_chap_password chap_password; /* 0x318 */ + + u32 generic_cont0; /* 0x398 */ +#define NVM_ISCSI_CFG_INITIATOR_VLAN_MASK 0x0000FFFF +#define NVM_ISCSI_CFG_INITIATOR_VLAN_OFFSET 0 +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_MASK 0x00030000 +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_OFFSET 16 +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_4 1 +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_6 2 +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_4_AND_6 3 + + u32 ctrl_flags; +#define NVM_ISCSI_CFG_INITIATOR_IP_VERSION_PRIORITY_V6 BIT(0) +#define NVM_ISCSI_CFG_INITIATOR_VLAN_ENABLED BIT(1) + + u32 rsvd[116]; /* 0x32C */ +}; + +struct nvm_iscsi_target { + u32 ctrl_flags; /* 0x0 */ +#define NVM_ISCSI_CFG_TARGET_ENABLED BIT(0) +#define NVM_ISCSI_CFG_BOOT_TIME_LOGIN_STATUS BIT(1) + + u32 generic_cont0; /* 0x4 */ +#define NVM_ISCSI_CFG_TARGET_TCP_PORT_MASK 0x0000FFFF +#define NVM_ISCSI_CFG_TARGET_TCP_PORT_OFFSET 0 + + u32 ip_ver; +#define NVM_ISCSI_CFG_IPv4 4 +#define NVM_ISCSI_CFG_IPv6 6 + + u32 rsvd_1[7]; /* 0x24 */ + union nvm_iscsi_ipv4_addr ipv4_addr; /* 0x28 */ + union nvm_iscsi_ipv6_addr ipv6_addr; /* 0x2C */ + union nvm_iscsi_lun lun; /* 0x3C */ + + union nvm_iscsi_name target_name; /* 0x44 */ + union nvm_iscsi_chap_name chap_name; /* 0x144 */ + union nvm_iscsi_chap_password chap_password; /* 0x244 */ + + u32 rsvd_2[107]; /* 0x2C4 */ +}; + +struct nvm_iscsi_block { + u32 id; /* 0x0 */ +#define NVM_ISCSI_CFG_BLK_MAPPED_PF_ID_MASK 0x0000000F +#define NVM_ISCSI_CFG_BLK_MAPPED_PF_ID_OFFSET 0 +#define NVM_ISCSI_CFG_BLK_CTRL_FLAG_MASK 0x00000FF0 +#define NVM_ISCSI_CFG_BLK_CTRL_FLAG_OFFSET 4 +#define NVM_ISCSI_CFG_BLK_CTRL_FLAG_IS_NOT_EMPTY BIT(0) +#define NVM_ISCSI_CFG_BLK_CTRL_FLAG_PF_MAPPED BIT(1) + + u32 rsvd_1[5]; /* 0x4 */ + + struct nvm_iscsi_generic generic; /* 0x18 */ + struct nvm_iscsi_initiator initiator; /* 0x218 */ + struct nvm_iscsi_target target[NUM_OF_ISCSI_TARGET_PER_PF]; + /* 0x718 */ + + u32 rsvd_2[58]; /* 0x1718 */ + /* total size - 0x1800 - 6K block */ +}; + +struct nvm_iscsi_cfg { + u32 id; /* 0x0 */ +#define NVM_ISCSI_CFG_BLK_VERSION_MINOR_MASK 0x000000FF +#define NVM_ISCSI_CFG_BLK_VERSION_MAJOR_MASK 0x0000FF00 +#define NVM_ISCSI_CFG_BLK_SIGNATURE_MASK 0xFFFF0000 +#define NVM_ISCSI_CFG_BLK_SIGNATURE 0x49430000 /* IC - Iscsi + * Config + */ + +#define NVM_ISCSI_CFG_BLK_VERSION_MAJOR 0 +#define NVM_ISCSI_CFG_BLK_VERSION_MINOR 10 +#define NVM_ISCSI_CFG_BLK_VERSION ((NVM_ISCSI_CFG_BLK_VERSION_MAJOR << 8) | \ + NVM_ISCSI_CFG_BLK_VERSION_MINOR) + + struct nvm_iscsi_block block[NUM_OF_ISCSI_PF_SUPPORTED]; /* 0x4 */ +}; + +#endif -- cgit v1.2.3-59-g8ed1b From c3a73ed8a82b666ac01466d3badd7824eae89c44 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 12 Jul 2017 13:15:11 +0200 Subject: platform/x86: silead_dmi: Add entry for Ployer Momo7w tablet touchscreen This Ployer Momo7w revision has the same hardware as the Trekstor ST70416-6, so we re-use the surftab_wintron70_st70416_6_data. Signed-off-by: Hans de Goede Signed-off-by: Darren Hart (VMware) --- drivers/platform/x86/silead_dmi.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/platform/x86/silead_dmi.c b/drivers/platform/x86/silead_dmi.c index f9e840aa5592..1157a7b646d6 100644 --- a/drivers/platform/x86/silead_dmi.c +++ b/drivers/platform/x86/silead_dmi.c @@ -173,6 +173,16 @@ static const struct dmi_system_id silead_ts_dmi_table[] = { DMI_MATCH(DMI_BIOS_VERSION, "TREK.G.WI71C.JGBMRBA04"), }, }, + { + /* Ployer Momo7w (same hardware as the Trekstor ST70416-6) */ + .driver_data = (void *)&surftab_wintron70_st70416_6_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Shenzhen PLOYER"), + DMI_MATCH(DMI_PRODUCT_NAME, "MOMO7W"), + /* Exact match, different versions need different fw */ + DMI_MATCH(DMI_BIOS_VERSION, "MOMO.G.WI71C.MABMRBA02"), + }, + }, { /* GP-electronic T701 */ .driver_data = (void *)&gp_electronic_t701_data, -- cgit v1.2.3-59-g8ed1b From eeac8cda2c957e156093933b860eec09e488fe15 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 30 Jun 2017 11:01:06 +0300 Subject: scsi: cxlflash: return -EFAULT if copy_from_user() fails The copy_from/to_user() functions return the number of bytes remaining to be copied but we had intended to return -EFAULT here. Fixes: bc88ac47d5cb ("scsi: cxlflash: Support AFU debug") Signed-off-by: Dan Carpenter Acked-by: Matthew R. Ochs Signed-off-by: Martin K. Petersen --- drivers/scsi/cxlflash/main.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c index 077f62e208aa..6a4367cc9caa 100644 --- a/drivers/scsi/cxlflash/main.c +++ b/drivers/scsi/cxlflash/main.c @@ -3401,9 +3401,10 @@ static int cxlflash_afu_debug(struct cxlflash_cfg *cfg, if (is_write) { req_flags |= SISL_REQ_FLAGS_HOST_WRITE; - rc = copy_from_user(kbuf, ubuf, ulen); - if (unlikely(rc)) + if (copy_from_user(kbuf, ubuf, ulen)) { + rc = -EFAULT; goto out; + } } } @@ -3431,8 +3432,10 @@ static int cxlflash_afu_debug(struct cxlflash_cfg *cfg, goto out; } - if (ulen && !is_write) - rc = copy_to_user(ubuf, kbuf, ulen); + if (ulen && !is_write) { + if (copy_to_user(ubuf, kbuf, ulen)) + rc = -EFAULT; + } out: kfree(buf); dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc); -- cgit v1.2.3-59-g8ed1b From 0ce3fcaff92908c370334ce3b9111aeea71159d6 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 12 Jul 2017 03:05:39 +0200 Subject: PCI / PM: Restore PME Enable after config space restoration Commit dc15e71eefc7 (PCI / PM: Restore PME Enable if skipping wakeup setup) introduced a mechanism by which the PME Enable bit can be restored by pci_enable_wake() if dev->wakeup_prepared is set in case it has been overwritten by PCI config space restoration. However, that commit overlooked the fact that on some systems (Dell XPS13 9360 in particular) the AML handling wakeup events checks PME Status and PME Enable and it won't trigger a Notify() for devices where those bits are not set while it is running. That happens during resume from suspend-to-idle when pci_restore_state() invoked by pci_pm_default_resume_early() clears PME Enable before the wakeup events are processed by AML, effectively causing those wakeup events to be ignored. Fix this issue by restoring the PME Enable configuration right after pci_restore_state() has been called instead of doing that in pci_enable_wake(). Fixes: dc15e71eefc7 (PCI / PM: Restore PME Enable if skipping wakeup setup) Signed-off-by: Rafael J. Wysocki Acked-by: Bjorn Helgaas --- drivers/pci/pci-driver.c | 2 ++ drivers/pci/pci.c | 16 ++++++++-------- drivers/pci/pci.h | 1 + 3 files changed, 11 insertions(+), 8 deletions(-) diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index ffe7d54d9328..1a93b48b0dd9 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -506,6 +506,7 @@ static int pci_restore_standard_config(struct pci_dev *pci_dev) } pci_restore_state(pci_dev); + pci_pme_restore(pci_dev); return 0; } @@ -517,6 +518,7 @@ static void pci_pm_default_resume_early(struct pci_dev *pci_dev) { pci_power_up(pci_dev); pci_restore_state(pci_dev); + pci_pme_restore(pci_dev); pci_fixup_device(pci_fixup_resume_early, pci_dev); } diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 0b5302a9fdae..d1443a161b35 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1798,7 +1798,11 @@ static void __pci_pme_active(struct pci_dev *dev, bool enable) pci_write_config_word(dev, dev->pm_cap + PCI_PM_CTRL, pmcsr); } -static void pci_pme_restore(struct pci_dev *dev) +/** + * pci_pme_restore - Restore PME configuration after config space restore. + * @dev: PCI device to update. + */ +void pci_pme_restore(struct pci_dev *dev) { u16 pmcsr; @@ -1808,6 +1812,7 @@ static void pci_pme_restore(struct pci_dev *dev) pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr); if (dev->wakeup_prepared) { pmcsr |= PCI_PM_CTRL_PME_ENABLE; + pmcsr &= ~PCI_PM_CTRL_PME_STATUS; } else { pmcsr &= ~PCI_PM_CTRL_PME_ENABLE; pmcsr |= PCI_PM_CTRL_PME_STATUS; @@ -1904,14 +1909,9 @@ int pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable) { int ret = 0; - /* - * Don't do the same thing twice in a row for one device, but restore - * PME Enable in case it has been updated by config space restoration. - */ - if (!!enable == !!dev->wakeup_prepared) { - pci_pme_restore(dev); + /* Don't do the same thing twice in a row for one device. */ + if (!!enable == !!dev->wakeup_prepared) return 0; - } /* * According to "PCI System Architecture" 4th ed. by Tom Shanley & Don diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 240b2c0fed4b..0a6e737f5325 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -71,6 +71,7 @@ void pci_power_up(struct pci_dev *dev); void pci_disable_enabled_device(struct pci_dev *dev); int pci_finish_runtime_suspend(struct pci_dev *dev); int __pci_pme_wakeup(struct pci_dev *dev, void *ign); +void pci_pme_restore(struct pci_dev *dev); bool pci_dev_keep_suspended(struct pci_dev *dev); void pci_dev_complete_resume(struct pci_dev *pci_dev); void pci_config_pm_runtime_get(struct pci_dev *dev); -- cgit v1.2.3-59-g8ed1b From f5f44c6ffe0b39ee37e1d2963ee0d48cbc1ec038 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 3 Jul 2017 11:17:27 +0100 Subject: scsi: isci: fix typo in function names There are a couple of typos in function names and spelling of request where the letters u and e are swapped: scu_ssp_reqeust_construct_task_context scu_sata_reqeust_construct_task_context Fix the spelling of request. Signed-off-by: Colin Ian King Signed-off-by: Martin K. Petersen --- drivers/scsi/isci/request.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/scsi/isci/request.c b/drivers/scsi/isci/request.c index 47f66e949745..ed197bc8e801 100644 --- a/drivers/scsi/isci/request.c +++ b/drivers/scsi/isci/request.c @@ -213,7 +213,7 @@ static void sci_task_request_build_ssp_task_iu(struct isci_request *ireq) * @task_context: * */ -static void scu_ssp_reqeust_construct_task_context( +static void scu_ssp_request_construct_task_context( struct isci_request *ireq, struct scu_task_context *task_context) { @@ -425,7 +425,7 @@ static void scu_ssp_io_request_construct_task_context(struct isci_request *ireq, u8 prot_type = scsi_get_prot_type(scmd); u8 prot_op = scsi_get_prot_op(scmd); - scu_ssp_reqeust_construct_task_context(ireq, task_context); + scu_ssp_request_construct_task_context(ireq, task_context); task_context->ssp_command_iu_length = sizeof(struct ssp_cmd_iu) / sizeof(u32); @@ -472,7 +472,7 @@ static void scu_ssp_task_request_construct_task_context(struct isci_request *ire { struct scu_task_context *task_context = ireq->tc; - scu_ssp_reqeust_construct_task_context(ireq, task_context); + scu_ssp_request_construct_task_context(ireq, task_context); task_context->control_frame = 1; task_context->priority = SCU_TASK_PRIORITY_HIGH; @@ -495,7 +495,7 @@ static void scu_ssp_task_request_construct_task_context(struct isci_request *ire * the command buffer is complete. none Revisit task context construction to * determine what is common for SSP/SMP/STP task context structures. */ -static void scu_sata_reqeust_construct_task_context( +static void scu_sata_request_construct_task_context( struct isci_request *ireq, struct scu_task_context *task_context) { @@ -562,7 +562,7 @@ static void scu_stp_raw_request_construct_task_context(struct isci_request *ireq { struct scu_task_context *task_context = ireq->tc; - scu_sata_reqeust_construct_task_context(ireq, task_context); + scu_sata_request_construct_task_context(ireq, task_context); task_context->control_frame = 0; task_context->priority = SCU_TASK_PRIORITY_NORMAL; @@ -613,7 +613,7 @@ static void sci_stp_optimized_request_construct(struct isci_request *ireq, struct scu_task_context *task_context = ireq->tc; /* Build the STP task context structure */ - scu_sata_reqeust_construct_task_context(ireq, task_context); + scu_sata_request_construct_task_context(ireq, task_context); /* Copy over the SGL elements */ sci_request_build_sgl(ireq); @@ -1401,7 +1401,7 @@ static enum sci_status sci_stp_request_pio_data_out_transmit_data(struct isci_re * @data_buffer: The buffer of data to be copied. * @length: The length of the data transfer. * - * Copy the data from the buffer for the length specified to the IO reqeust SGL + * Copy the data from the buffer for the length specified to the IO request SGL * specified data region. enum sci_status */ static enum sci_status -- cgit v1.2.3-59-g8ed1b From 4feca6a52b9812f53bc5c20829fd4e37e710db34 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 3 Jul 2017 11:24:02 +0100 Subject: scsi: qedi: fix another spelling mistake: "alloction" -> "allocation" Trivial fix to spelling mistake in QEDF_ERR message. I should have also included this in a previous fix, but I only just spotted this one. Signed-off-by: Colin Ian King Acked-by: Manish Rangankar Signed-off-by: Martin K. Petersen --- drivers/scsi/qedi/qedi_fw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c index 19254bd739d9..93d54acd4a22 100644 --- a/drivers/scsi/qedi/qedi_fw.c +++ b/drivers/scsi/qedi/qedi_fw.c @@ -1411,7 +1411,7 @@ static void qedi_tmf_work(struct work_struct *work) list_work = kzalloc(sizeof(*list_work), GFP_ATOMIC); if (!list_work) { - QEDI_ERR(&qedi->dbg_ctx, "Memory alloction failed\n"); + QEDI_ERR(&qedi->dbg_ctx, "Memory allocation failed\n"); goto abort_ret; } -- cgit v1.2.3-59-g8ed1b From 40bf6a35483ee25271ce2a90d8976cf1409a033a Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Wed, 12 Jul 2017 10:23:13 +0200 Subject: rtc: Remove wrong deprecation comment rtc_time_to_tm and rtc_tm_to_time are not deprecated and make perfect sense for RTCs that are simple 32bit counters. Signed-off-by: Alexandre Belloni --- include/linux/rtc.h | 6 ------ 1 file changed, 6 deletions(-) diff --git a/include/linux/rtc.h b/include/linux/rtc.h index d53ecdc060cf..0a0f0d14a5fb 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -33,17 +33,11 @@ static inline time64_t rtc_tm_sub(struct rtc_time *lhs, struct rtc_time *rhs) return rtc_tm_to_time64(lhs) - rtc_tm_to_time64(rhs); } -/** - * Deprecated. Use rtc_time64_to_tm(). - */ static inline void rtc_time_to_tm(unsigned long time, struct rtc_time *tm) { rtc_time64_to_tm(time, tm); } -/** - * Deprecated. Use rtc_tm_to_time64(). - */ static inline int rtc_tm_to_time(struct rtc_time *tm, unsigned long *time) { *time = rtc_tm_to_time64(tm); -- cgit v1.2.3-59-g8ed1b From acef2690d16f38a0687552b391674201ad7c5783 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 3 Jul 2017 20:21:39 +0100 Subject: scsi: qedf: fix spelling mistake: "offlading" -> "offloading" Trivial fix to spelling mistake in QEDF_INFO message and remove duplicated "since" (thanks to Tyrel Datwyler for spotting the latter issue). Signed-off-by: Colin Ian King Acked-by: Chad Dupuis Reviewed-by: Tyrel Datwyler Signed-off-by: Martin K. Petersen --- drivers/scsi/qedf/qedf_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index b58bba4604e8..7786c97e033f 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -1227,7 +1227,7 @@ static void qedf_rport_event_handler(struct fc_lport *lport, if (rdata->spp_type != FC_TYPE_FCP) { QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC, - "Not offlading since since spp type isn't FCP\n"); + "Not offloading since spp type isn't FCP\n"); break; } if (!(rdata->ids.roles & FC_RPORT_ROLE_FCP_TARGET)) { -- cgit v1.2.3-59-g8ed1b From a680f1d463aeaeb00d22af257a56e111967c2f18 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 5 Jul 2017 10:30:56 +0200 Subject: scsi: virtio_scsi: always read VPD pages for multiqueue too Multi-queue virtio-scsi uses a different scsi_host_template struct. Add the .device_alloc field there, too. Fixes: 25d1d50e23275e141e3a3fe06c25a99f4c4bf4e0 Cc: stable@vger.kernel.org Cc: David Gibson Signed-off-by: Paolo Bonzini Reviewed-by: Fam Zheng Reviewed-by: Stefan Hajnoczi Signed-off-by: Martin K. Petersen --- drivers/scsi/virtio_scsi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 8b93197daefe..9be211d68b15 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -837,6 +837,7 @@ static struct scsi_host_template virtscsi_host_template_multi = { .eh_abort_handler = virtscsi_abort, .eh_device_reset_handler = virtscsi_device_reset, .eh_timed_out = virtscsi_eh_timed_out, + .slave_alloc = virtscsi_device_alloc, .can_queue = 1024, .dma_boundary = UINT_MAX, -- cgit v1.2.3-59-g8ed1b From 68c59fcea1f2c6a54c62aa896cc623c1b5bc9b47 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Fri, 7 Jul 2017 10:56:38 +0200 Subject: scsi: sg: fix SG_DXFER_FROM_DEV transfers SG_DXFER_FROM_DEV transfers do not necessarily have a dxferp as we set it to NULL for the old sg_io read/write interface, but must have a length bigger than 0. This fixes a regression introduced by commit 28676d869bbb ("scsi: sg: check for valid direction before starting the request") Signed-off-by: Johannes Thumshirn Fixes: 28676d869bbb ("scsi: sg: check for valid direction before starting the request") Reported-by: Chris Clayton Tested-by: Chris Clayton Cc: Douglas Gilbert Reviewed-by: Hannes Reinecke Tested-by: Chris Clayton Acked-by: Douglas Gilbert Signed-off-by: Martin K. Petersen --- drivers/scsi/sg.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 21225d62b0c1..1e82d4128a84 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -758,8 +758,11 @@ static bool sg_is_valid_dxfer(sg_io_hdr_t *hp) if (hp->dxferp || hp->dxfer_len > 0) return false; return true; - case SG_DXFER_TO_DEV: case SG_DXFER_FROM_DEV: + if (hp->dxfer_len < 0) + return false; + return true; + case SG_DXFER_TO_DEV: case SG_DXFER_TO_FROM_DEV: if (!hp->dxferp || hp->dxfer_len == 0) return false; -- cgit v1.2.3-59-g8ed1b From fb2028a0b24e0823bbc0a28e6f0f1bd9fbbf733c Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 10 Jul 2017 11:47:40 +0300 Subject: scsi: qla2xxx: Off by one in qlt_ctio_to_cmd() There are "req->num_outstanding_cmds" elements in the req->outstanding_cmds[] array so the > here should be >=. Signed-off-by: Dan Carpenter Reviewed-by: Nicholas Bellinger Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_target.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 2a0173e5d10e..986a4270b2ff 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -3747,7 +3747,7 @@ static struct qla_tgt_cmd *qlt_ctio_to_cmd(struct scsi_qla_host *vha, h &= QLA_CMD_HANDLE_MASK; if (h != QLA_TGT_NULL_HANDLE) { - if (unlikely(h > req->num_outstanding_cmds)) { + if (unlikely(h >= req->num_outstanding_cmds)) { ql_dbg(ql_dbg_tgt, vha, 0xe052, "qla_target(%d): Wrong handle %x received\n", vha->vp_idx, handle); -- cgit v1.2.3-59-g8ed1b From 89b203e9d07d4079367120a6fe271ad9e9b751c0 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 11 Jul 2017 13:11:44 +0100 Subject: scsi: hisi_sas: make several const arrays static Don't populate various tables on the stack but make them static const. Makes the object code smaller by over 280 bytes: Before: text data bss dec hex filename 39887 5080 64 45031 afe7 hisi_sas_v2_hw.o After: text data bss dec hex filename 39318 5368 64 44750 aece hisi_sas_v2_hw.o Signed-off-by: Colin Ian King Acked-by: John Garry Signed-off-by: Martin K. Petersen --- drivers/scsi/hisi_sas/hisi_sas_v2_hw.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c index 551d103c27f1..2bfea7082e3a 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c @@ -1693,7 +1693,7 @@ static int prep_ssp_v2_hw(struct hisi_hba *hisi_hba, static int parse_trans_tx_err_code_v2_hw(u32 err_msk) { - const u8 trans_tx_err_code_prio[] = { + static const u8 trans_tx_err_code_prio[] = { TRANS_TX_OPEN_FAIL_WITH_IT_NEXUS_LOSS, TRANS_TX_ERR_PHY_NOT_ENABLE, TRANS_TX_OPEN_CNX_ERR_WRONG_DESTINATION, @@ -1738,7 +1738,7 @@ static int parse_trans_tx_err_code_v2_hw(u32 err_msk) static int parse_trans_rx_err_code_v2_hw(u32 err_msk) { - const u8 trans_rx_err_code_prio[] = { + static const u8 trans_rx_err_code_prio[] = { TRANS_RX_ERR_WITH_RXFRAME_CRC_ERR, TRANS_RX_ERR_WITH_RXFIS_8B10B_DISP_ERR, TRANS_RX_ERR_WITH_RXFRAME_HAVE_ERRPRM, @@ -1784,7 +1784,7 @@ static int parse_trans_rx_err_code_v2_hw(u32 err_msk) static int parse_dma_tx_err_code_v2_hw(u32 err_msk) { - const u8 dma_tx_err_code_prio[] = { + static const u8 dma_tx_err_code_prio[] = { DMA_TX_UNEXP_XFER_ERR, DMA_TX_UNEXP_RETRANS_ERR, DMA_TX_XFER_LEN_OVERFLOW, @@ -1810,7 +1810,7 @@ static int parse_dma_tx_err_code_v2_hw(u32 err_msk) static int parse_sipc_rx_err_code_v2_hw(u32 err_msk) { - const u8 sipc_rx_err_code_prio[] = { + static const u8 sipc_rx_err_code_prio[] = { SIPC_RX_FIS_STATUS_ERR_BIT_VLD, SIPC_RX_PIO_WRSETUP_STATUS_DRQ_ERR, SIPC_RX_FIS_STATUS_BSY_BIT_ERR, @@ -1836,7 +1836,7 @@ static int parse_sipc_rx_err_code_v2_hw(u32 err_msk) static int parse_dma_rx_err_code_v2_hw(u32 err_msk) { - const u8 dma_rx_err_code_prio[] = { + static const u8 dma_rx_err_code_prio[] = { DMA_RX_UNKNOWN_FRM_ERR, DMA_RX_DATA_LEN_OVERFLOW, DMA_RX_DATA_LEN_UNDERFLOW, -- cgit v1.2.3-59-g8ed1b From 6f37e2102778d3437a416684680cc5ce295f2042 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 12 Jul 2017 10:30:22 +0300 Subject: scsi: libfc: pass an error pointer to fc_disc_error() This patch is basically to silence a static checker warning. drivers/scsi/libfc/fc_disc.c:326 fc_disc_error() warn: passing a valid pointer to 'PTR_ERR' It doesn't affect runtime because it treats -ENOMEM and a valid pointer the same. But the documentation says we should be passing an error pointer. Signed-off-by: Dan Carpenter Acked-by: Johannes Thumshirn Signed-off-by: Martin K. Petersen --- drivers/scsi/libfc/fc_disc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/libfc/fc_disc.c b/drivers/scsi/libfc/fc_disc.c index fd501f8dbb11..8660f923ace0 100644 --- a/drivers/scsi/libfc/fc_disc.c +++ b/drivers/scsi/libfc/fc_disc.c @@ -573,7 +573,7 @@ static void fc_disc_gpn_ft_resp(struct fc_seq *sp, struct fc_frame *fp, event = DISC_EV_FAILED; } if (error) - fc_disc_error(disc, fp); + fc_disc_error(disc, ERR_PTR(error)); else if (event != DISC_EV_NONE) fc_disc_done(disc, event); fc_frame_free(fp); -- cgit v1.2.3-59-g8ed1b From 7d2b39ab9b0d67c3e6c66e3b68644522d4e15392 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Wed, 12 Jul 2017 16:39:31 -0600 Subject: docs: Include uaccess docs from the right file Documentation/core-api/kernel-api.rst was including kerneldoc comments from arch/x86/include/asm/uaccess_32.h, but the relevant comments moved to .../uaccess.h some time ago. Correct the include to pick up the comments and eliminate a warning. Signed-off-by: Jonathan Corbet --- Documentation/core-api/kernel-api.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst index 9ec8488319dc..17b00914c6ab 100644 --- a/Documentation/core-api/kernel-api.rst +++ b/Documentation/core-api/kernel-api.rst @@ -114,7 +114,7 @@ The Slab Cache User Space Memory Access ------------------------ -.. kernel-doc:: arch/x86/include/asm/uaccess_32.h +.. kernel-doc:: arch/x86/include/asm/uaccess.h :internal: .. kernel-doc:: arch/x86/lib/usercopy_32.c -- cgit v1.2.3-59-g8ed1b From 6d16e9143e9ef7e4c3f497f1111dfd48eaf2bab6 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Wed, 12 Jul 2017 16:44:38 -0600 Subject: docs: Turn off section numbering for the input docs The input docs enable section numbering at multiple levels, leading to a lot of bright-red "nested numbered toctree" warnings in newer Sphinx versions. Just take that directive out for now to help alleviate the global red-pixel shortage. Signed-off-by: Jonathan Corbet --- Documentation/input/index.rst | 1 - 1 file changed, 1 deletion(-) diff --git a/Documentation/input/index.rst b/Documentation/input/index.rst index 7a3e71c2bd00..9888f5cbf6d5 100644 --- a/Documentation/input/index.rst +++ b/Documentation/input/index.rst @@ -6,7 +6,6 @@ Contents: .. toctree:: :maxdepth: 2 - :numbered: input_uapi input_kapi -- cgit v1.2.3-59-g8ed1b From 3afadfd902a7477db0b121a3fcbd964d3606c29f Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 7 Jul 2017 03:21:17 +0900 Subject: memory-barriers.txt: Fix broken link to atomic_ops.txt Few obsolete links to atomic_ops.txt exist in memory-barriers.txt though the file has moved to core-api/atomic_ops.rst. This commit fixes the obsolete links. Signed-off-by: SeongJae Park Signed-off-by: Jonathan Corbet --- Documentation/memory-barriers.txt | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index f1c9eaa45a57..3ed0d8bf2412 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -1876,8 +1876,8 @@ There are some more advanced barrier functions: This makes sure that the death mark on the object is perceived to be set *before* the reference counter is decremented. - See Documentation/atomic_ops.txt for more information. See the "Atomic - operations" subsection for information on where to use these. + See Documentation/core-api/atomic_ops.rst for more information. See the + "Atomic operations" subsection for information on where to use these. (*) lockless_dereference(); @@ -2584,7 +2584,7 @@ situations because on some CPUs the atomic instructions used imply full memory barriers, and so barrier instructions are superfluous in conjunction with them, and in such cases the special barrier primitives will be no-ops. -See Documentation/atomic_ops.txt for more information. +See Documentation/core-api/atomic_ops.rst for more information. ACCESSING DEVICES -- cgit v1.2.3-59-g8ed1b From 51e988f4092428e3d2c9f141fba9f86583bc82f3 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 7 Jul 2017 03:21:18 +0900 Subject: kokr/memory-barriers.txt: Fix obsolete link to atomic_ops.txt Obsolete links to atomic_ops.txt exist in ko_KR/memory-barriers.txt though the file has moved to core-api/atomic_ops.rst. This commit fixes the obsolete links. Signed-off-by: SeongJae Park Signed-off-by: Jonathan Corbet --- Documentation/translations/ko_KR/memory-barriers.txt | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/Documentation/translations/ko_KR/memory-barriers.txt b/Documentation/translations/ko_KR/memory-barriers.txt index c6f4ead76ce7..38310dcd6620 100644 --- a/Documentation/translations/ko_KR/memory-barriers.txt +++ b/Documentation/translations/ko_KR/memory-barriers.txt @@ -523,11 +523,11 @@ CPU 에게 기대할 수 있는 최소한의 보장사항 몇가지가 있습니 즉, ACQUIRE 는 최소한의 "취득" 동작처럼, 그리고 RELEASE 는 최소한의 "공개" 처럼 동작한다는 의미입니다. -atomic_ops.txt 에서 설명되는 어토믹 오퍼레이션들 중에는 완전히 순서잡힌 것들과 -(배리어를 사용하지 않는) 완화된 순서의 것들 외에 ACQUIRE 와 RELEASE 부류의 -것들도 존재합니다. 로드와 스토어를 모두 수행하는 조합된 어토믹 오퍼레이션에서, -ACQUIRE 는 해당 오퍼레이션의 로드 부분에만 적용되고 RELEASE 는 해당 -오퍼레이션의 스토어 부분에만 적용됩니다. +core-api/atomic_ops.rst 에서 설명되는 어토믹 오퍼레이션들 중에는 완전히 +순서잡힌 것들과 (배리어를 사용하지 않는) 완화된 순서의 것들 외에 ACQUIRE 와 +RELEASE 부류의 것들도 존재합니다. 로드와 스토어를 모두 수행하는 조합된 어토믹 +오퍼레이션에서, ACQUIRE 는 해당 오퍼레이션의 로드 부분에만 적용되고 RELEASE 는 +해당 오퍼레이션의 스토어 부분에만 적용됩니다. 메모리 배리어들은 두 CPU 간, 또는 CPU 와 디바이스 간에 상호작용의 가능성이 있을 때에만 필요합니다. 만약 어떤 코드에 그런 상호작용이 없을 것이 보장된다면, 해당 @@ -1848,7 +1848,7 @@ Mandatory 배리어들은 SMP 시스템에서도 UP 시스템에서도 SMP 효 이 코드는 객체의 업데이트된 death 마크가 레퍼런스 카운터 감소 동작 *전에* 보일 것을 보장합니다. - 더 많은 정보를 위해선 Documentation/atomic_ops.txt 문서를 참고하세요. + 더 많은 정보를 위해선 Documentation/core-api/atomic_ops.rst 문서를 참고하세요. 어디서 이것들을 사용해야 할지 궁금하다면 "어토믹 오퍼레이션" 서브섹션을 참고하세요. @@ -2550,7 +2550,7 @@ CPU 에서는 사용되는 어토믹 인스트럭션 자체에 메모리 배리 있는데, 그런 경우에 이 특수 메모리 배리어 도구들은 no-op 이 되어 실질적으로 아무일도 하지 않습니다. -더 많은 내용을 위해선 Documentation/atomic_ops.txt 를 참고하세요. +더 많은 내용을 위해선 Documentation/core-api/atomic_ops.rst 를 참고하세요. 디바이스 액세스 -- cgit v1.2.3-59-g8ed1b From 0a2c13d9cd76c84f2520f573ff83f777eb7464aa Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Wed, 12 Jul 2017 14:33:01 -0700 Subject: include/linux/dcache.h: use unsigned chars in struct name_snapshot "kernel.h: handle pointers to arrays better in container_of()" triggers: In file included from include/uapi/linux/stddef.h:1:0, from include/linux/stddef.h:4, from include/uapi/linux/posix_types.h:4, from include/uapi/linux/types.h:13, from include/linux/types.h:5, from include/linux/syscalls.h:71, from fs/dcache.c:17: fs/dcache.c: In function 'release_dentry_name_snapshot': include/linux/compiler.h:542:38: error: call to '__compiletime_assert_305' declared with attribute error: pointer type mismatch in container_of() _compiletime_assert(condition, msg, __compiletime_assert_, __LINE__) ^ include/linux/compiler.h:525:4: note: in definition of macro '__compiletime_assert' prefix ## suffix(); \ ^ include/linux/compiler.h:542:2: note: in expansion of macro '_compiletime_assert' _compiletime_assert(condition, msg, __compiletime_assert_, __LINE__) ^ include/linux/build_bug.h:46:37: note: in expansion of macro 'compiletime_assert' #define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg) ^ include/linux/kernel.h:860:2: note: in expansion of macro 'BUILD_BUG_ON_MSG' BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ ^ fs/dcache.c:305:7: note: in expansion of macro 'container_of' p = container_of(name->name, struct external_name, name[0]); Switch name_snapshot to use unsigned chars, matching struct qstr and struct external_name. Link: http://lkml.kernel.org/r/20170710152134.0f78c1e6@canb.auug.org.au Signed-off-by: Stephen Rothwell Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dcache.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 025727bf6797..c706eaac692e 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -592,8 +592,8 @@ static inline struct inode *d_real_inode(const struct dentry *dentry) } struct name_snapshot { - const char *name; - char inline_name[DNAME_INLINE_LEN]; + const unsigned char *name; + unsigned char inline_name[DNAME_INLINE_LEN]; }; void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *); void release_dentry_name_snapshot(struct name_snapshot *); -- cgit v1.2.3-59-g8ed1b From c7acec713d14c6ce8a20154f9dfda258d6bcad3b Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Wed, 12 Jul 2017 14:33:04 -0700 Subject: kernel.h: handle pointers to arrays better in container_of() If the first parameter of container_of() is a pointer to a non-const-qualified array type (and the third parameter names a non-const-qualified array member), the local variable __mptr will be defined with a const-qualified array type. In ISO C, these types are incompatible. They work as expected in GNU C, but some versions will issue warnings. For example, GCC 4.9 produces the warning "initialization from incompatible pointer type". Here is an example of where the problem occurs: ------------------------------------------------------- #include #include MODULE_LICENSE("GPL"); struct st { int a; char b[16]; }; static int __init example_init(void) { struct st t = { .a = 101, .b = "hello" }; char (*p)[16] = &t.b; struct st *x = container_of(p, struct st, b); printk(KERN_DEBUG "%p %p\n", (void *)&t, (void *)x); return 0; } static void __exit example_exit(void) { } module_init(example_init); module_exit(example_exit); ------------------------------------------------------- Building the module with gcc-4.9 results in these warnings (where '{m}' is the module source and '{k}' is the kernel source): ------------------------------------------------------- In file included from {m}/example.c:1:0: {m}/example.c: In function `example_init': {k}/include/linux/kernel.h:854:48: warning: initialization from incompatible pointer type const typeof( ((type *)0)->member ) *__mptr = (ptr); \ ^ {m}/example.c:14:17: note: in expansion of macro `container_of' struct st *x = container_of(p, struct st, b); ^ {k}/include/linux/kernel.h:854:48: warning: (near initialization for `x') const typeof( ((type *)0)->member ) *__mptr = (ptr); \ ^ {m}/example.c:14:17: note: in expansion of macro `container_of' struct st *x = container_of(p, struct st, b); ^ ------------------------------------------------------- Replace the type checking performed by the macro to avoid these warnings. Make sure `*(ptr)` either has type compatible with the member, or has type compatible with `void`, ignoring qualifiers. Raise compiler errors if this is not true. This is stronger than the previous behaviour, which only resulted in compiler warnings for a type mismatch. [arnd@arndb.de: fix new warnings for container_of()] Link: http://lkml.kernel.org/r/20170620200940.90557-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170525120316.24473-7-abbotti@mev.co.uk Signed-off-by: Ian Abbott Signed-off-by: Arnd Bergmann Acked-by: Michal Nazarewicz Acked-by: Kees Cook Cc: Hidehiro Kawai Cc: Borislav Petkov Cc: Rasmus Villemoes Cc: Johannes Berg Cc: Peter Zijlstra Cc: Alexander Potapenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 1c91f26e2996..bd6d96cf80b1 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -854,9 +855,12 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * @member: the name of the member within the struct. * */ -#define container_of(ptr, type, member) ({ \ - const typeof( ((type *)0)->member ) *__mptr = (ptr); \ - (type *)( (char *)__mptr - offsetof(type,member) );}) +#define container_of(ptr, type, member) ({ \ + void *__mptr = (void *)(ptr); \ + BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ + !__same_type(*(ptr), void), \ + "pointer type mismatch in container_of()"); \ + ((type *)(__mptr - offsetof(type, member))); }) /* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */ #ifdef CONFIG_FTRACE_MCOUNT_RECORD -- cgit v1.2.3-59-g8ed1b From 91a90140f9987101d730b7dad8c6406321285da8 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 12 Jul 2017 14:33:08 -0700 Subject: mm/memory.c: mark create_huge_pmd() inline to prevent build failure With gcc 4.1.2: mm/memory.o: In function `create_huge_pmd': memory.c:(.text+0x93e): undefined reference to `do_huge_pmd_anonymous_page' Interestingly, create_huge_pmd() is emitted in the assembler output, but never called. Converting transparent_hugepage_enabled() from a macro to a static inline function reduced the ability of the compiler to remove unused code. Fix this by marking create_huge_pmd() inline. Fixes: 16981d763501c0e0 ("mm: improve readability of transparent_hugepage_enabled()") Link: http://lkml.kernel.org/r/1499842660-10665-1-git-send-email-geert@linux-m68k.org Signed-off-by: Geert Uytterhoeven Acked-by: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memory.c b/mm/memory.c index cbb57194687e..0e517be91a89 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3591,7 +3591,7 @@ out: return 0; } -static int create_huge_pmd(struct vm_fault *vmf) +static inline int create_huge_pmd(struct vm_fault *vmf) { if (vma_is_anonymous(vmf->vma)) return do_huge_pmd_anonymous_page(vmf); -- cgit v1.2.3-59-g8ed1b From 112166f88cf83dd11486cf1818672d42b540865b Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 12 Jul 2017 14:33:11 -0700 Subject: kernel/fork.c: virtually mapped stacks: do not disable interrupts The reason to disable interrupts seems to be to avoid switching to a different processor while handling per cpu data using individual loads and stores. If we use per cpu RMV primitives we will not have to disable interrupts. Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1705171055130.5898@east.gentwo.org Signed-off-by: Christoph Lameter Cc: Andy Lutomirski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) diff --git a/kernel/fork.c b/kernel/fork.c index 0f69a3e5281e..d2b9d7c31eaf 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -205,19 +205,17 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) void *stack; int i; - local_irq_disable(); for (i = 0; i < NR_CACHED_STACKS; i++) { - struct vm_struct *s = this_cpu_read(cached_stacks[i]); + struct vm_struct *s; + + s = this_cpu_xchg(cached_stacks[i], NULL); if (!s) continue; - this_cpu_write(cached_stacks[i], NULL); tsk->stack_vm_area = s; - local_irq_enable(); return s->addr; } - local_irq_enable(); stack = __vmalloc_node_range(THREAD_SIZE, THREAD_SIZE, VMALLOC_START, VMALLOC_END, @@ -245,19 +243,15 @@ static inline void free_thread_stack(struct task_struct *tsk) { #ifdef CONFIG_VMAP_STACK if (task_stack_vm_area(tsk)) { - unsigned long flags; int i; - local_irq_save(flags); for (i = 0; i < NR_CACHED_STACKS; i++) { - if (this_cpu_read(cached_stacks[i])) + if (this_cpu_cmpxchg(cached_stacks[i], + NULL, tsk->stack_vm_area) != NULL) continue; - this_cpu_write(cached_stacks[i], tsk->stack_vm_area); - local_irq_restore(flags); return; } - local_irq_restore(flags); vfree_atomic(tsk->stack); return; -- cgit v1.2.3-59-g8ed1b From 203e9e41219b4e7357104e525e91ac609fba2c6c Mon Sep 17 00:00:00 2001 From: Xunlei Pang Date: Wed, 12 Jul 2017 14:33:14 -0700 Subject: kexec: move vmcoreinfo out of the kernel's .bss section As Eric said, "what we need to do is move the variable vmcoreinfo_note out of the kernel's .bss section. And modify the code to regenerate and keep this information in something like the control page. Definitely something like this needs a page all to itself, and ideally far away from any other kernel data structures. I clearly was not watching closely the data someone decided to keep this silly thing in the kernel's .bss section." This patch allocates extra pages for these vmcoreinfo_XXX variables, one advantage is that it enhances some safety of vmcoreinfo, because vmcoreinfo now is kept far away from other kernel data structures. Link: http://lkml.kernel.org/r/1493281021-20737-1-git-send-email-xlpang@redhat.com Signed-off-by: Xunlei Pang Tested-by: Michael Holzheu Reviewed-by: Juergen Gross Suggested-by: Eric Biederman Cc: Benjamin Herrenschmidt Cc: Dave Young Cc: Hari Bathini Cc: Mahesh Salgaonkar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/kernel/machine_kexec.c | 5 ----- arch/s390/kernel/machine_kexec.c | 1 + arch/s390/kernel/setup.c | 6 ------ arch/x86/kernel/crash.c | 2 +- arch/x86/xen/mmu_pv.c | 4 ++-- include/linux/crash_core.h | 4 ++-- kernel/crash_core.c | 26 ++++++++++++++++++++++---- kernel/ksysfs.c | 2 +- 8 files changed, 29 insertions(+), 21 deletions(-) diff --git a/arch/ia64/kernel/machine_kexec.c b/arch/ia64/kernel/machine_kexec.c index 599507bcec91..c14815dca747 100644 --- a/arch/ia64/kernel/machine_kexec.c +++ b/arch/ia64/kernel/machine_kexec.c @@ -163,8 +163,3 @@ void arch_crash_save_vmcoreinfo(void) #endif } -phys_addr_t paddr_vmcoreinfo_note(void) -{ - return ia64_tpa((unsigned long)(char *)&vmcoreinfo_note); -} - diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index 49a6bd45957b..3d0b14afa232 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -246,6 +246,7 @@ void arch_crash_save_vmcoreinfo(void) VMCOREINFO_SYMBOL(lowcore_ptr); VMCOREINFO_SYMBOL(high_memory); VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS); + mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note()); } void machine_shutdown(void) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 3ae756c0db3d..3d1d808ea8a9 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -496,11 +496,6 @@ static void __init setup_memory_end(void) pr_notice("The maximum memory size is %luMB\n", memory_end >> 20); } -static void __init setup_vmcoreinfo(void) -{ - mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note()); -} - #ifdef CONFIG_CRASH_DUMP /* @@ -939,7 +934,6 @@ void __init setup_arch(char **cmdline_p) #endif setup_resources(); - setup_vmcoreinfo(); setup_lowcore(); smp_fill_possible_mask(); cpu_detect_mhz_feature(); diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 22217ece26c8..44404e2307bb 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -457,7 +457,7 @@ static int prepare_elf64_headers(struct crash_elf_data *ced, bufp += sizeof(Elf64_Phdr); phdr->p_type = PT_NOTE; phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note(); - phdr->p_filesz = phdr->p_memsz = sizeof(vmcoreinfo_note); + phdr->p_filesz = phdr->p_memsz = VMCOREINFO_NOTE_SIZE; (ehdr->e_phnum)++; #ifdef CONFIG_X86_64 diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 1d7a7213a310..cab28cf2cffb 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -2693,8 +2693,8 @@ EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region); phys_addr_t paddr_vmcoreinfo_note(void) { if (xen_pv_domain()) - return virt_to_machine(&vmcoreinfo_note).maddr; + return virt_to_machine(vmcoreinfo_note).maddr; else - return __pa_symbol(&vmcoreinfo_note); + return __pa(vmcoreinfo_note); } #endif /* CONFIG_KEXEC_CORE */ diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index 4090a42578a8..87506a02e914 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -19,7 +19,7 @@ CRASH_CORE_NOTE_NAME_BYTES + \ CRASH_CORE_NOTE_DESC_BYTES) -#define VMCOREINFO_BYTES (4096) +#define VMCOREINFO_BYTES PAGE_SIZE #define VMCOREINFO_NOTE_NAME "VMCOREINFO" #define VMCOREINFO_NOTE_NAME_BYTES ALIGN(sizeof(VMCOREINFO_NOTE_NAME), 4) #define VMCOREINFO_NOTE_SIZE ((CRASH_CORE_NOTE_HEAD_BYTES * 2) + \ @@ -56,7 +56,7 @@ phys_addr_t paddr_vmcoreinfo_note(void); #define VMCOREINFO_CONFIG(name) \ vmcoreinfo_append_str("CONFIG_%s=y\n", #name) -extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4]; +extern u32 *vmcoreinfo_note; extern size_t vmcoreinfo_size; extern size_t vmcoreinfo_max_size; diff --git a/kernel/crash_core.c b/kernel/crash_core.c index fcbd568f1e95..2837d6164db8 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -14,10 +14,10 @@ #include /* vmcoreinfo stuff */ -static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES]; -u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4]; +static unsigned char *vmcoreinfo_data; size_t vmcoreinfo_size; -size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data); +size_t vmcoreinfo_max_size = VMCOREINFO_BYTES; +u32 *vmcoreinfo_note; /* * parsing the "crashkernel" commandline @@ -326,6 +326,9 @@ static void update_vmcoreinfo_note(void) void crash_save_vmcoreinfo(void) { + if (!vmcoreinfo_note) + return; + vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds()); update_vmcoreinfo_note(); } @@ -356,11 +359,26 @@ void __weak arch_crash_save_vmcoreinfo(void) phys_addr_t __weak paddr_vmcoreinfo_note(void) { - return __pa_symbol((unsigned long)(char *)&vmcoreinfo_note); + return __pa(vmcoreinfo_note); } static int __init crash_save_vmcoreinfo_init(void) { + vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL); + if (!vmcoreinfo_data) { + pr_warn("Memory allocation for vmcoreinfo_data failed\n"); + return -ENOMEM; + } + + vmcoreinfo_note = alloc_pages_exact(VMCOREINFO_NOTE_SIZE, + GFP_KERNEL | __GFP_ZERO); + if (!vmcoreinfo_note) { + free_page((unsigned long)vmcoreinfo_data); + vmcoreinfo_data = NULL; + pr_warn("Memory allocation for vmcoreinfo_note failed\n"); + return -ENOMEM; + } + VMCOREINFO_OSRELEASE(init_uts_ns.name.release); VMCOREINFO_PAGESIZE(PAGE_SIZE); diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index df1a9aa602a0..46ba853656f6 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -134,7 +134,7 @@ static ssize_t vmcoreinfo_show(struct kobject *kobj, { phys_addr_t vmcore_base = paddr_vmcoreinfo_note(); return sprintf(buf, "%pa %x\n", &vmcore_base, - (unsigned int)sizeof(vmcoreinfo_note)); + (unsigned int)VMCOREINFO_NOTE_SIZE); } KERNEL_ATTR_RO(vmcoreinfo); -- cgit v1.2.3-59-g8ed1b From 5203f4995d9a87952a83c2ce7866adbbe8f97bb5 Mon Sep 17 00:00:00 2001 From: Xunlei Pang Date: Wed, 12 Jul 2017 14:33:17 -0700 Subject: powerpc/fadump: use the correct VMCOREINFO_NOTE_SIZE for phdr vmcoreinfo_max_size stands for the vmcoreinfo_data, the correct one we should use is vmcoreinfo_note whose total size is VMCOREINFO_NOTE_SIZE. Like explained in commit 77019967f06b ("kdump: fix exported size of vmcoreinfo note"), it should not affect the actual function, but we better fix it, also this change should be safe and backward compatible. After this, we can get rid of variable vmcoreinfo_max_size, let's use the corresponding macros directly, fewer variables means more safety for vmcoreinfo operation. [xlpang@redhat.com: fix build warning] Link: http://lkml.kernel.org/r/1494830606-27736-1-git-send-email-xlpang@redhat.com Link: http://lkml.kernel.org/r/1493281021-20737-2-git-send-email-xlpang@redhat.com Signed-off-by: Xunlei Pang Reviewed-by: Mahesh Salgaonkar Reviewed-by: Dave Young Cc: Hari Bathini Cc: Benjamin Herrenschmidt Cc: Eric Biederman Cc: Juergen Gross Cc: Michael Holzheu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/kernel/fadump.c | 3 +-- include/linux/crash_core.h | 1 - kernel/crash_core.c | 3 +-- 3 files changed, 2 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 3079518f2245..dc0c49cfd90a 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -999,8 +999,7 @@ static int fadump_create_elfcore_headers(char *bufp) phdr->p_paddr = fadump_relocate(paddr_vmcoreinfo_note()); phdr->p_offset = phdr->p_paddr; - phdr->p_memsz = vmcoreinfo_max_size; - phdr->p_filesz = vmcoreinfo_max_size; + phdr->p_memsz = phdr->p_filesz = VMCOREINFO_NOTE_SIZE; /* Increment number of program headers. */ (elf->e_phnum)++; diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index 87506a02e914..e5df1b3cf072 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -58,7 +58,6 @@ phys_addr_t paddr_vmcoreinfo_note(void); extern u32 *vmcoreinfo_note; extern size_t vmcoreinfo_size; -extern size_t vmcoreinfo_max_size; Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, void *data, size_t data_len); diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 2837d6164db8..315adbf9cb68 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -16,7 +16,6 @@ /* vmcoreinfo stuff */ static unsigned char *vmcoreinfo_data; size_t vmcoreinfo_size; -size_t vmcoreinfo_max_size = VMCOREINFO_BYTES; u32 *vmcoreinfo_note; /* @@ -343,7 +342,7 @@ void vmcoreinfo_append_str(const char *fmt, ...) r = vscnprintf(buf, sizeof(buf), fmt, args); va_end(args); - r = min(r, vmcoreinfo_max_size - vmcoreinfo_size); + r = min(r, (size_t)VMCOREINFO_BYTES - vmcoreinfo_size); memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r); -- cgit v1.2.3-59-g8ed1b From 1229384f5b856d83698c38f9dedfd836e26711cb Mon Sep 17 00:00:00 2001 From: Xunlei Pang Date: Wed, 12 Jul 2017 14:33:21 -0700 Subject: kdump: protect vmcoreinfo data under the crash memory Currently vmcoreinfo data is updated at boot time subsys_initcall(), it has the risk of being modified by some wrong code during system is running. As a result, vmcore dumped may contain the wrong vmcoreinfo. Later on, when using "crash", "makedumpfile", etc utility to parse this vmcore, we probably will get "Segmentation fault" or other unexpected errors. E.g. 1) wrong code overwrites vmcoreinfo_data; 2) further crashes the system; 3) trigger kdump, then we obviously will fail to recognize the crash context correctly due to the corrupted vmcoreinfo. Now except for vmcoreinfo, all the crash data is well protected(including the cpu note which is fully updated in the crash path, thus its correctness is guaranteed). Given that vmcoreinfo data is a large chunk prepared for kdump, we better protect it as well. To solve this, we relocate and copy vmcoreinfo_data to the crash memory when kdump is loading via kexec syscalls. Because the whole crash memory will be protected by existing arch_kexec_protect_crashkres() mechanism, we naturally protect vmcoreinfo_data from write(even read) access under kernel direct mapping after kdump is loaded. Since kdump is usually loaded at the very early stage after boot, we can trust the correctness of the vmcoreinfo data copied. On the other hand, we still need to operate the vmcoreinfo safe copy when crash happens to generate vmcoreinfo_note again, we rely on vmap() to map out a new kernel virtual address and update to use this new one instead in the following crash_save_vmcoreinfo(). BTW, we do not touch vmcoreinfo_note, because it will be fully updated using the protected vmcoreinfo_data after crash which is surely correct just like the cpu crash note. Link: http://lkml.kernel.org/r/1493281021-20737-3-git-send-email-xlpang@redhat.com Signed-off-by: Xunlei Pang Tested-by: Michael Holzheu Cc: Benjamin Herrenschmidt Cc: Dave Young Cc: Eric Biederman Cc: Hari Bathini Cc: Juergen Gross Cc: Mahesh Salgaonkar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/crash_core.h | 2 +- include/linux/kexec.h | 2 ++ kernel/crash_core.c | 17 ++++++++++++++++- kernel/kexec.c | 8 ++++++++ kernel/kexec_core.c | 39 +++++++++++++++++++++++++++++++++++++++ kernel/kexec_file.c | 8 ++++++++ 6 files changed, 74 insertions(+), 2 deletions(-) diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index e5df1b3cf072..2df2118fbe13 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -28,6 +28,7 @@ typedef u32 note_buf_t[CRASH_CORE_NOTE_BYTES/4]; +void crash_update_vmcoreinfo_safecopy(void *ptr); void crash_save_vmcoreinfo(void); void arch_crash_save_vmcoreinfo(void); __printf(1, 2) @@ -57,7 +58,6 @@ phys_addr_t paddr_vmcoreinfo_note(void); vmcoreinfo_append_str("CONFIG_%s=y\n", #name) extern u32 *vmcoreinfo_note; -extern size_t vmcoreinfo_size; Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, void *data, size_t data_len); diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 65888418fb69..dd056fab9e35 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -172,6 +172,7 @@ struct kimage { unsigned long start; struct page *control_code_page; struct page *swap_page; + void *vmcoreinfo_data_copy; /* locates in the crash memory */ unsigned long nr_segments; struct kexec_segment segment[KEXEC_SEGMENT_MAX]; @@ -241,6 +242,7 @@ extern void crash_kexec(struct pt_regs *); int kexec_should_crash(struct task_struct *); int kexec_crash_loaded(void); void crash_save_cpu(struct pt_regs *regs, int cpu); +extern int kimage_crash_copy_vmcoreinfo(struct kimage *image); extern struct kimage *kexec_image; extern struct kimage *kexec_crash_image; diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 315adbf9cb68..6db80fc0810b 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -15,9 +15,12 @@ /* vmcoreinfo stuff */ static unsigned char *vmcoreinfo_data; -size_t vmcoreinfo_size; +static size_t vmcoreinfo_size; u32 *vmcoreinfo_note; +/* trusted vmcoreinfo, e.g. we can make a copy in the crash memory */ +static unsigned char *vmcoreinfo_data_safecopy; + /* * parsing the "crashkernel" commandline * @@ -323,11 +326,23 @@ static void update_vmcoreinfo_note(void) final_note(buf); } +void crash_update_vmcoreinfo_safecopy(void *ptr) +{ + if (ptr) + memcpy(ptr, vmcoreinfo_data, vmcoreinfo_size); + + vmcoreinfo_data_safecopy = ptr; +} + void crash_save_vmcoreinfo(void) { if (!vmcoreinfo_note) return; + /* Use the safe copy to generate vmcoreinfo note if have */ + if (vmcoreinfo_data_safecopy) + vmcoreinfo_data = vmcoreinfo_data_safecopy; + vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds()); update_vmcoreinfo_note(); } diff --git a/kernel/kexec.c b/kernel/kexec.c index 980936a90ee6..e62ec4dc6620 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -144,6 +144,14 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments, if (ret) goto out; + /* + * Some architecture(like S390) may touch the crash memory before + * machine_kexec_prepare(), we must copy vmcoreinfo data after it. + */ + ret = kimage_crash_copy_vmcoreinfo(image); + if (ret) + goto out; + for (i = 0; i < nr_segments; i++) { ret = kimage_load_segment(image, &image->segment[i]); if (ret) diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 154ffb489b93..1ae7c41c33c1 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -482,6 +482,40 @@ struct page *kimage_alloc_control_pages(struct kimage *image, return pages; } +int kimage_crash_copy_vmcoreinfo(struct kimage *image) +{ + struct page *vmcoreinfo_page; + void *safecopy; + + if (image->type != KEXEC_TYPE_CRASH) + return 0; + + /* + * For kdump, allocate one vmcoreinfo safe copy from the + * crash memory. as we have arch_kexec_protect_crashkres() + * after kexec syscall, we naturally protect it from write + * (even read) access under kernel direct mapping. But on + * the other hand, we still need to operate it when crash + * happens to generate vmcoreinfo note, hereby we rely on + * vmap for this purpose. + */ + vmcoreinfo_page = kimage_alloc_control_pages(image, 0); + if (!vmcoreinfo_page) { + pr_warn("Could not allocate vmcoreinfo buffer\n"); + return -ENOMEM; + } + safecopy = vmap(&vmcoreinfo_page, 1, VM_MAP, PAGE_KERNEL); + if (!safecopy) { + pr_warn("Could not vmap vmcoreinfo buffer\n"); + return -ENOMEM; + } + + image->vmcoreinfo_data_copy = safecopy; + crash_update_vmcoreinfo_safecopy(safecopy); + + return 0; +} + static int kimage_add_entry(struct kimage *image, kimage_entry_t entry) { if (*image->entry != 0) @@ -569,6 +603,11 @@ void kimage_free(struct kimage *image) if (!image) return; + if (image->vmcoreinfo_data_copy) { + crash_update_vmcoreinfo_safecopy(NULL); + vunmap(image->vmcoreinfo_data_copy); + } + kimage_free_extra_pages(image); for_each_kimage_entry(image, ptr, entry) { if (entry & IND_INDIRECTION) { diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 766e7e4d3ad9..c8f7f77e9fa9 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -298,6 +298,14 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, if (ret) goto out; + /* + * Some architecture(like S390) may touch the crash memory before + * machine_kexec_prepare(), we must copy vmcoreinfo data after it. + */ + ret = kimage_crash_copy_vmcoreinfo(image); + if (ret) + goto out; + ret = kexec_calculate_store_digests(image); if (ret) goto out; -- cgit v1.2.3-59-g8ed1b From a711bdc095d2c9b6ad15e737d1cdc46409b09538 Mon Sep 17 00:00:00 2001 From: Bharat Bhushan Date: Wed, 12 Jul 2017 14:33:24 -0700 Subject: kexec/kdump: minor Documentation updates for arm64 and Image Minor updates in Documentation for arm64 as relocatable kernel. Also this patch updates documentation for using uncompressed image "Image" which is used for ARM64. Link: http://lkml.kernel.org/r/1495104793-6563-1-git-send-email-Bharat.Bhushan@nxp.com Signed-off-by: Bharat Bhushan Cc: Dave Young Cc: Baoquan He Cc: Vivek Goyal Cc: Jonathan Corbet Cc: AKASHI Takahiro Cc: Pratyush Anand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kdump/kdump.txt | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt index 615434d81108..51814450a7f8 100644 --- a/Documentation/kdump/kdump.txt +++ b/Documentation/kdump/kdump.txt @@ -112,8 +112,8 @@ There are two possible methods of using Kdump. 2) Or use the system kernel binary itself as dump-capture kernel and there is no need to build a separate dump-capture kernel. This is possible only with the architectures which support a relocatable kernel. As - of today, i386, x86_64, ppc64, ia64 and arm architectures support relocatable - kernel. + of today, i386, x86_64, ppc64, ia64, arm and arm64 architectures support + relocatable kernel. Building a relocatable kernel is advantageous from the point of view that one does not have to build a second kernel for capturing the dump. But @@ -339,7 +339,7 @@ For arm: For arm64: - Use vmlinux or Image -If you are using a uncompressed vmlinux image then use following command +If you are using an uncompressed vmlinux image then use following command to load dump-capture kernel. kexec -p \ @@ -361,6 +361,12 @@ to load dump-capture kernel. --dtb= \ --append="root= " +If you are using an uncompressed Image, then use following command +to load dump-capture kernel. + + kexec -p \ + --initrd= \ + --append="root= " Please note, that --args-linux does not need to be specified for ia64. It is planned to make this a no-op on that architecture, but for now -- cgit v1.2.3-59-g8ed1b From 89c5b53b16bf577079d4f0311406dbea3c71202c Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Wed, 12 Jul 2017 14:33:27 -0700 Subject: sysctl: fix lax sysctl_check_table() sanity check Patch series "sysctl: few fixes", v5. I've been working on making kmod more deterministic, and as I did that I couldn't help but notice a few issues with sysctl. My end goal was just to fix unsigned int support, which back then was completely broken. Liping Zhang has sent up small atomic fixes, however it still missed yet one more fix and Alexey Dobriyan had also suggested to just drop array support given its complexity. I have inspected array support using Coccinelle and indeed its not that popular, so if in fact we can avoid it for new interfaces, I agree its best. I did develop a sysctl stress driver but will hold that off for another series. This patch (of 5): Commit 7c60c48f58a7 ("sysctl: Improve the sysctl sanity checks") improved sanity checks considerbly, however the enhancements on sysctl_check_table() meant adding a functional change so that only the last table entry's sanity error is propagated. It also changed the way errors were propagated so that each new check reset the err value, this means only last sanity check computed is used for an error. This has been in the kernel since v3.4 days. Fix this by carrying on errors from previous checks and iterations as we traverse the table and ensuring we keep any error from previous checks. We keep iterating on the table even if an error is found so we can complain for all errors found in one shot. This works as -EINVAL is always returned on error anyway, and the check for error is any non-zero value. Fixes: 7c60c48f58a7 ("sysctl: Improve the sysctl sanity checks") Link: http://lkml.kernel.org/r/20170519033554.18592-2-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez Cc: Al Viro Cc: "Eric W. Biederman" Cc: Alexey Dobriyan Cc: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/proc_sysctl.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 67985a7233c2..32c9c5630507 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1066,7 +1066,7 @@ static int sysctl_check_table(const char *path, struct ctl_table *table) int err = 0; for (; table->procname; table++) { if (table->child) - err = sysctl_err(path, table, "Not a file"); + err |= sysctl_err(path, table, "Not a file"); if ((table->proc_handler == proc_dostring) || (table->proc_handler == proc_dointvec) || @@ -1078,15 +1078,15 @@ static int sysctl_check_table(const char *path, struct ctl_table *table) (table->proc_handler == proc_doulongvec_minmax) || (table->proc_handler == proc_doulongvec_ms_jiffies_minmax)) { if (!table->data) - err = sysctl_err(path, table, "No data"); + err |= sysctl_err(path, table, "No data"); if (!table->maxlen) - err = sysctl_err(path, table, "No maxlen"); + err |= sysctl_err(path, table, "No maxlen"); } if (!table->proc_handler) - err = sysctl_err(path, table, "No proc_handler"); + err |= sysctl_err(path, table, "No proc_handler"); if ((table->mode & (S_IRUGO|S_IWUGO)) != table->mode) - err = sysctl_err(path, table, "bogus .mode 0%o", + err |= sysctl_err(path, table, "bogus .mode 0%o", table->mode); } return err; -- cgit v1.2.3-59-g8ed1b From a19ac3374995382a994653ff372b98ea7cbad548 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Wed, 12 Jul 2017 14:33:30 -0700 Subject: sysctl: kdoc'ify sysctl_writes_strict Document the different sysctl_writes_strict modes in code. Link: http://lkml.kernel.org/r/20170519033554.18592-3-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez Cc: Al Viro Cc: "Eric W. Biederman" Cc: Alexey Dobriyan Cc: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 29 +++++++++++++++++++++++++---- 1 file changed, 25 insertions(+), 4 deletions(-) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 4dfba1a76cc3..02725178694a 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -174,11 +174,32 @@ extern int no_unaligned_warning; #ifdef CONFIG_PROC_SYSCTL -#define SYSCTL_WRITES_LEGACY -1 -#define SYSCTL_WRITES_WARN 0 -#define SYSCTL_WRITES_STRICT 1 +/** + * enum sysctl_writes_mode - supported sysctl write modes + * + * @SYSCTL_WRITES_LEGACY: each write syscall must fully contain the sysctl value + * to be written, and multiple writes on the same sysctl file descriptor + * will rewrite the sysctl value, regardless of file position. No warning + * is issued when the initial position is not 0. + * @SYSCTL_WRITES_WARN: same as above but warn when the initial file position is + * not 0. + * @SYSCTL_WRITES_STRICT: writes to numeric sysctl entries must always be at + * file position 0 and the value must be fully contained in the buffer + * sent to the write syscall. If dealing with strings respect the file + * position, but restrict this to the max length of the buffer, anything + * passed the max lenght will be ignored. Multiple writes will append + * to the buffer. + * + * These write modes control how current file position affects the behavior of + * updating sysctl values through the proc interface on each write. + */ +enum sysctl_writes_mode { + SYSCTL_WRITES_LEGACY = -1, + SYSCTL_WRITES_WARN = 0, + SYSCTL_WRITES_STRICT = 1, +}; -static int sysctl_writes_strict = SYSCTL_WRITES_STRICT; +static enum sysctl_writes_mode sysctl_writes_strict = SYSCTL_WRITES_STRICT; static int proc_do_cad_pid(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); -- cgit v1.2.3-59-g8ed1b From d383d48470819e86fe30eb72f0e9494e1ee0e2af Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Wed, 12 Jul 2017 14:33:33 -0700 Subject: sysctl: fold sysctl_writes_strict checks into helper The mode sysctl_writes_strict positional checks keep being copy and pasted as we add new proc handlers. Just add a helper to avoid code duplication. Link: http://lkml.kernel.org/r/20170519033554.18592-4-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez Suggested-by: Kees Cook Cc: Al Viro Cc: "Eric W. Biederman" Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 56 ++++++++++++++++++++++++++++++++------------------------ 1 file changed, 32 insertions(+), 24 deletions(-) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 02725178694a..6f3bb1f099fa 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1970,6 +1970,32 @@ static void warn_sysctl_write(struct ctl_table *table) current->comm, table->procname); } +/** + * proc_first_pos_non_zero_ignore - check if firs position is allowed + * @ppos: file position + * @table: the sysctl table + * + * Returns true if the first position is non-zero and the sysctl_writes_strict + * mode indicates this is not allowed for numeric input types. String proc + * hadlers can ignore the return value. + */ +static bool proc_first_pos_non_zero_ignore(loff_t *ppos, + struct ctl_table *table) +{ + if (!*ppos) + return false; + + switch (sysctl_writes_strict) { + case SYSCTL_WRITES_STRICT: + return true; + case SYSCTL_WRITES_WARN: + warn_sysctl_write(table); + return false; + default: + return false; + } +} + /** * proc_dostring - read a string sysctl * @table: the sysctl table @@ -1990,8 +2016,8 @@ static void warn_sysctl_write(struct ctl_table *table) int proc_dostring(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - if (write && *ppos && sysctl_writes_strict == SYSCTL_WRITES_WARN) - warn_sysctl_write(table); + if (write) + proc_first_pos_non_zero_ignore(ppos, table); return _proc_do_string((char *)(table->data), table->maxlen, write, (char __user *)buffer, lenp, ppos); @@ -2193,17 +2219,8 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, conv = do_proc_dointvec_conv; if (write) { - if (*ppos) { - switch (sysctl_writes_strict) { - case SYSCTL_WRITES_STRICT: - goto out; - case SYSCTL_WRITES_WARN: - warn_sysctl_write(table); - break; - default: - break; - } - } + if (proc_first_pos_non_zero_ignore(ppos, table)) + goto out; if (left > PAGE_SIZE - 1) left = PAGE_SIZE - 1; @@ -2468,17 +2485,8 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int left = *lenp; if (write) { - if (*ppos) { - switch (sysctl_writes_strict) { - case SYSCTL_WRITES_STRICT: - goto out; - case SYSCTL_WRITES_WARN: - warn_sysctl_write(table); - break; - default: - break; - } - } + if (proc_first_pos_non_zero_ignore(ppos, table)) + goto out; if (left > PAGE_SIZE - 1) left = PAGE_SIZE - 1; -- cgit v1.2.3-59-g8ed1b From 4f2fec00afa60aa8e5d1b7f2a8e0526900f55623 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Wed, 12 Jul 2017 14:33:36 -0700 Subject: sysctl: simplify unsigned int support Commit e7d316a02f68 ("sysctl: handle error writing UINT_MAX to u32 fields") added proc_douintvec() to start help adding support for unsigned int, this however was only half the work needed. Two fixes have come in since then for the following issues: o Printing the values shows a negative value, this happens since do_proc_dointvec() and this uses proc_put_long() This was fixed by commit 5380e5644afbba9 ("sysctl: don't print negative flag for proc_douintvec"). o We can easily wrap around the int values: UINT_MAX is 4294967295, if we echo in 4294967295 + 1 we end up with 0, using 4294967295 + 2 we end up with 1. o We echo negative values in and they are accepted This was fixed by commit 425fffd886ba ("sysctl: report EINVAL if value is larger than UINT_MAX for proc_douintvec"). It still also failed to be added to sysctl_check_table()... instead of adding it with the current implementation just provide a proper and simplified unsigned int support without any array unsigned int support with no negative support at all. Historically sysctl proc helpers have supported arrays, due to the complexity this adds though we've taken a step back to evaluate array users to determine if its worth upkeeping for unsigned int. An evaluation using Coccinelle has been done to perform a grammatical search to ask ourselves: o How many sysctl proc_dointvec() (int) users exist which likely should be moved over to proc_douintvec() (unsigned int) ? Answer: about 8 - Of these how many are array users ? Answer: Probably only 1 o How many sysctl array users exist ? Answer: about 12 This last question gives us an idea just how popular arrays: they are not. Array support should probably just be kept for strings. The identified uint ports are: drivers/infiniband/core/ucma.c - max_backlog drivers/infiniband/core/iwcm.c - default_backlog net/core/sysctl_net_core.c - rps_sock_flow_sysctl() net/netfilter/nf_conntrack_timestamp.c - nf_conntrack_timestamp -- bool net/netfilter/nf_conntrack_acct.c nf_conntrack_acct -- bool net/netfilter/nf_conntrack_ecache.c - nf_conntrack_events -- bool net/netfilter/nf_conntrack_helper.c - nf_conntrack_helper -- bool net/phonet/sysctl.c proc_local_port_range() The only possible array users is proc_local_port_range() but it does not seem worth it to add array support just for this given the range support works just as well. Unsigned int support should be desirable more for when you *need* more than INT_MAX or using int min/max support then does not suffice for your ranges. If you forget and by mistake happen to register an unsigned int proc entry with an array, the driver will fail and you will get something as follows: sysctl table check failed: debug/test_sysctl//uint_0002 array now allowed CPU: 2 PID: 1342 Comm: modprobe Tainted: G W E Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Call Trace: dump_stack+0x63/0x81 __register_sysctl_table+0x350/0x650 ? kmem_cache_alloc_trace+0x107/0x240 __register_sysctl_paths+0x1b3/0x1e0 ? 0xffffffffc005f000 register_sysctl_table+0x1f/0x30 test_sysctl_init+0x10/0x1000 [test_sysctl] do_one_initcall+0x52/0x1a0 ? kmem_cache_alloc_trace+0x107/0x240 do_init_module+0x5f/0x200 load_module+0x1867/0x1bd0 ? __symbol_put+0x60/0x60 SYSC_finit_module+0xdf/0x110 SyS_finit_module+0xe/0x10 entry_SYSCALL_64_fastpath+0x1e/0xad RIP: 0033:0x7f042b22d119 Fixes: e7d316a02f68 ("sysctl: handle error writing UINT_MAX to u32 fields") Link: http://lkml.kernel.org/r/20170519033554.18592-5-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez Suggested-by: Alexey Dobriyan Cc: Subash Abhinov Kasiviswanathan Cc: Liping Zhang Cc: Alexey Dobriyan Cc: Heinrich Schuchardt Cc: Kees Cook Cc: "David S. Miller" Cc: Ingo Molnar Cc: Al Viro Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/proc_sysctl.c | 14 +++++ kernel/sysctl.c | 153 +++++++++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 160 insertions(+), 7 deletions(-) diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 32c9c5630507..ee6feba8b6c0 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1061,6 +1061,18 @@ static int sysctl_err(const char *path, struct ctl_table *table, char *fmt, ...) return -EINVAL; } +static int sysctl_check_table_array(const char *path, struct ctl_table *table) +{ + int err = 0; + + if (table->proc_handler == proc_douintvec) { + if (table->maxlen != sizeof(unsigned int)) + err |= sysctl_err(path, table, "array now allowed"); + } + + return err; +} + static int sysctl_check_table(const char *path, struct ctl_table *table) { int err = 0; @@ -1081,6 +1093,8 @@ static int sysctl_check_table(const char *path, struct ctl_table *table) err |= sysctl_err(path, table, "No data"); if (!table->maxlen) err |= sysctl_err(path, table, "No maxlen"); + else + err |= sysctl_check_table_array(path, table); } if (!table->proc_handler) err |= sysctl_err(path, table, "No proc_handler"); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 6f3bb1f099fa..d12078fc215f 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2175,19 +2175,18 @@ static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp, return 0; } -static int do_proc_douintvec_conv(bool *negp, unsigned long *lvalp, - int *valp, - int write, void *data) +static int do_proc_douintvec_conv(unsigned long *lvalp, + unsigned int *valp, + int write, void *data) { if (write) { - if (*negp) + if (*lvalp > UINT_MAX) return -EINVAL; if (*lvalp > UINT_MAX) return -EINVAL; *valp = *lvalp; } else { unsigned int val = *valp; - *negp = false; *lvalp = (unsigned long)val; } return 0; @@ -2287,6 +2286,146 @@ static int do_proc_dointvec(struct ctl_table *table, int write, buffer, lenp, ppos, conv, data); } +static int do_proc_douintvec_w(unsigned int *tbl_data, + struct ctl_table *table, + void __user *buffer, + size_t *lenp, loff_t *ppos, + int (*conv)(unsigned long *lvalp, + unsigned int *valp, + int write, void *data), + void *data) +{ + unsigned long lval; + int err = 0; + size_t left; + bool neg; + char *kbuf = NULL, *p; + + left = *lenp; + + if (proc_first_pos_non_zero_ignore(ppos, table)) + goto bail_early; + + if (left > PAGE_SIZE - 1) + left = PAGE_SIZE - 1; + + p = kbuf = memdup_user_nul(buffer, left); + if (IS_ERR(kbuf)) + return -EINVAL; + + left -= proc_skip_spaces(&p); + if (!left) { + err = -EINVAL; + goto out_free; + } + + err = proc_get_long(&p, &left, &lval, &neg, + proc_wspace_sep, + sizeof(proc_wspace_sep), NULL); + if (err || neg) { + err = -EINVAL; + goto out_free; + } + + if (conv(&lval, tbl_data, 1, data)) { + err = -EINVAL; + goto out_free; + } + + if (!err && left) + left -= proc_skip_spaces(&p); + +out_free: + kfree(kbuf); + if (err) + return -EINVAL; + + return 0; + + /* This is in keeping with old __do_proc_dointvec() */ +bail_early: + *ppos += *lenp; + return err; +} + +static int do_proc_douintvec_r(unsigned int *tbl_data, void __user *buffer, + size_t *lenp, loff_t *ppos, + int (*conv)(unsigned long *lvalp, + unsigned int *valp, + int write, void *data), + void *data) +{ + unsigned long lval; + int err = 0; + size_t left; + + left = *lenp; + + if (conv(&lval, tbl_data, 0, data)) { + err = -EINVAL; + goto out; + } + + err = proc_put_long(&buffer, &left, lval, false); + if (err || !left) + goto out; + + err = proc_put_char(&buffer, &left, '\n'); + +out: + *lenp -= left; + *ppos += *lenp; + + return err; +} + +static int __do_proc_douintvec(void *tbl_data, struct ctl_table *table, + int write, void __user *buffer, + size_t *lenp, loff_t *ppos, + int (*conv)(unsigned long *lvalp, + unsigned int *valp, + int write, void *data), + void *data) +{ + unsigned int *i, vleft; + + if (!tbl_data || !table->maxlen || !*lenp || (*ppos && !write)) { + *lenp = 0; + return 0; + } + + i = (unsigned int *) tbl_data; + vleft = table->maxlen / sizeof(*i); + + /* + * Arrays are not supported, keep this simple. *Do not* add + * support for them. + */ + if (vleft != 1) { + *lenp = 0; + return -EINVAL; + } + + if (!conv) + conv = do_proc_douintvec_conv; + + if (write) + return do_proc_douintvec_w(i, table, buffer, lenp, ppos, + conv, data); + return do_proc_douintvec_r(i, buffer, lenp, ppos, conv, data); +} + +static int do_proc_douintvec(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos, + int (*conv)(unsigned long *lvalp, + unsigned int *valp, + int write, void *data), + void *data) +{ + return __do_proc_douintvec(table->data, table, write, + buffer, lenp, ppos, conv, data); +} + /** * proc_dointvec - read a vector of integers * @table: the sysctl table @@ -2322,8 +2461,8 @@ int proc_dointvec(struct ctl_table *table, int write, int proc_douintvec(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_dointvec(table, write, buffer, lenp, ppos, - do_proc_douintvec_conv, NULL); + return do_proc_douintvec(table, write, buffer, lenp, ppos, + do_proc_douintvec_conv, NULL); } /* -- cgit v1.2.3-59-g8ed1b From 61d9b56a89208d8cccd0b4cfec7e6959717e16e3 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Wed, 12 Jul 2017 14:33:40 -0700 Subject: sysctl: add unsigned int range support To keep parity with regular int interfaces provide the an unsigned int proc_douintvec_minmax() which allows you to specify a range of allowed valid numbers. Adding proc_douintvec_minmax_sysadmin() is easy but we can wait for an actual user for that. Link: http://lkml.kernel.org/r/20170519033554.18592-6-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez Acked-by: Kees Cook Cc: Subash Abhinov Kasiviswanathan Cc: Heinrich Schuchardt Cc: Kees Cook Cc: "David S. Miller" Cc: Ingo Molnar Cc: Al Viro Cc: "Eric W. Biederman" Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/proc_sysctl.c | 4 ++- include/linux/sysctl.h | 3 +++ kernel/sysctl.c | 66 ++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 72 insertions(+), 1 deletion(-) diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index ee6feba8b6c0..8f9d564d0969 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1065,7 +1065,8 @@ static int sysctl_check_table_array(const char *path, struct ctl_table *table) { int err = 0; - if (table->proc_handler == proc_douintvec) { + if ((table->proc_handler == proc_douintvec) || + (table->proc_handler == proc_douintvec_minmax)) { if (table->maxlen != sizeof(unsigned int)) err |= sysctl_err(path, table, "array now allowed"); } @@ -1083,6 +1084,7 @@ static int sysctl_check_table(const char *path, struct ctl_table *table) if ((table->proc_handler == proc_dostring) || (table->proc_handler == proc_dointvec) || (table->proc_handler == proc_douintvec) || + (table->proc_handler == proc_douintvec_minmax) || (table->proc_handler == proc_dointvec_minmax) || (table->proc_handler == proc_dointvec_jiffies) || (table->proc_handler == proc_dointvec_userhz_jiffies) || diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 80d07816def0..225001d437ae 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -47,6 +47,9 @@ extern int proc_douintvec(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec_minmax(struct ctl_table *, int, void __user *, size_t *, loff_t *); +extern int proc_douintvec_minmax(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); extern int proc_dointvec_jiffies(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index d12078fc215f..df9f2a367882 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2567,6 +2567,65 @@ int proc_dointvec_minmax(struct ctl_table *table, int write, do_proc_dointvec_minmax_conv, ¶m); } +struct do_proc_douintvec_minmax_conv_param { + unsigned int *min; + unsigned int *max; +}; + +static int do_proc_douintvec_minmax_conv(unsigned long *lvalp, + unsigned int *valp, + int write, void *data) +{ + struct do_proc_douintvec_minmax_conv_param *param = data; + + if (write) { + unsigned int val = *lvalp; + + if ((param->min && *param->min > val) || + (param->max && *param->max < val)) + return -ERANGE; + + if (*lvalp > UINT_MAX) + return -EINVAL; + *valp = val; + } else { + unsigned int val = *valp; + *lvalp = (unsigned long) val; + } + + return 0; +} + +/** + * proc_douintvec_minmax - read a vector of unsigned ints with min/max values + * @table: the sysctl table + * @write: %TRUE if this is a write to the sysctl file + * @buffer: the user buffer + * @lenp: the size of the user buffer + * @ppos: file position + * + * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer + * values from/to the user buffer, treated as an ASCII string. Negative + * strings are not allowed. + * + * This routine will ensure the values are within the range specified by + * table->extra1 (min) and table->extra2 (max). There is a final sanity + * check for UINT_MAX to avoid having to support wrap around uses from + * userspace. + * + * Returns 0 on success. + */ +int proc_douintvec_minmax(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct do_proc_douintvec_minmax_conv_param param = { + .min = (unsigned int *) table->extra1, + .max = (unsigned int *) table->extra2, + }; + return do_proc_douintvec(table, write, buffer, lenp, ppos, + do_proc_douintvec_minmax_conv, ¶m); +} + static void validate_coredump_safety(void) { #ifdef CONFIG_COREDUMP @@ -3066,6 +3125,12 @@ int proc_dointvec_minmax(struct ctl_table *table, int write, return -ENOSYS; } +int proc_douintvec_minmax(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return -ENOSYS; +} + int proc_dointvec_jiffies(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -3108,6 +3173,7 @@ EXPORT_SYMBOL(proc_dointvec); EXPORT_SYMBOL(proc_douintvec); EXPORT_SYMBOL(proc_dointvec_jiffies); EXPORT_SYMBOL(proc_dointvec_minmax); +EXPORT_SYMBOL_GPL(proc_douintvec_minmax); EXPORT_SYMBOL(proc_dointvec_userhz_jiffies); EXPORT_SYMBOL(proc_dointvec_ms_jiffies); EXPORT_SYMBOL(proc_dostring); -- cgit v1.2.3-59-g8ed1b From 9308f2f9e7f055cf3934645ec622bb5259dc1c14 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Wed, 12 Jul 2017 14:33:43 -0700 Subject: test_sysctl: add dedicated proc sysctl test driver The existing tools/testing/selftests/sysctl/ tests include two test cases, but these use existing production kernel sysctl interfaces. We want to expand test coverage but we can't just be looking for random safe production values to poke at, that's just insane! Instead just dedicate a test driver for debugging purposes and port the existing scripts to use it. This will make it easier for further tests to be added. Subsequent patches will extend our test coverage for sysctl. The stress test driver uses a new license (GPL on Linux, copyleft-next outside of Linux). Linus was fine with this [0] and later due to Ted's and Alans's request ironed out an "or" language clause to use [1] which is already present upstream. [0] https://lkml.kernel.org/r/CA+55aFyhxcvD+q7tp+-yrSFDKfR0mOHgyEAe=f_94aKLsOu0Og@mail.gmail.com [1] https://lkml.kernel.org/r/1495234558.7848.122.camel@linux.intel.com Link: http://lkml.kernel.org/r/20170630224431.17374-2-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez Acked-by: Kees Cook Cc: "Eric W. Biederman" Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/Kconfig.debug | 11 +++ lib/Makefile | 1 + lib/test_sysctl.c | 113 ++++++++++++++++++++++++ tools/testing/selftests/sysctl/config | 1 + tools/testing/selftests/sysctl/run_numerictests | 4 +- tools/testing/selftests/sysctl/run_stringtests | 4 +- 6 files changed, 130 insertions(+), 4 deletions(-) create mode 100644 lib/test_sysctl.c create mode 100644 tools/testing/selftests/sysctl/config diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index e20fc079bebd..f28f4252e54a 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1785,6 +1785,17 @@ config TEST_FIRMWARE If unsure, say N. +config TEST_SYSCTL + tristate "sysctl test driver" + default n + depends on PROC_SYSCTL + help + This builds the "test_sysctl" module. This driver enables to test the + proc sysctl interfaces available to drivers safely without affecting + production knobs which might alter system functionality. + + If unsure, say N. + config TEST_UDELAY tristate "udelay test driver" default n diff --git a/lib/Makefile b/lib/Makefile index 5a008329324e..85e91e51a9fe 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -46,6 +46,7 @@ obj-$(CONFIG_TEST_HEXDUMP) += test_hexdump.o obj-y += kstrtox.o obj-$(CONFIG_TEST_BPF) += test_bpf.o obj-$(CONFIG_TEST_FIRMWARE) += test_firmware.o +obj-$(CONFIG_TEST_SYSCTL) += test_sysctl.o obj-$(CONFIG_TEST_HASH) += test_hash.o test_siphash.o obj-$(CONFIG_TEST_KASAN) += test_kasan.o obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o diff --git a/lib/test_sysctl.c b/lib/test_sysctl.c new file mode 100644 index 000000000000..b2163bfb6eb2 --- /dev/null +++ b/lib/test_sysctl.c @@ -0,0 +1,113 @@ +/* + * proc sysctl test driver + * + * Copyright (C) 2017 Luis R. Rodriguez + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or at your option any + * later version; or, when distributed separately from the Linux kernel or + * when incorporated into other software packages, subject to the following + * license: + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of copyleft-next (version 0.3.1 or later) as published + * at http://copyleft-next.org/. + */ + +/* + * This module provides an interface to the the proc sysctl interfaces. This + * driver requires CONFIG_PROC_SYSCTL. It will not normally be loaded by the + * system unless explicitly requested by name. You can also build this driver + * into your kernel. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static int i_zero; +static int i_one_hundred = 100; + +struct test_sysctl_data { + int int_0001; + char string_0001[65]; +}; + +static struct test_sysctl_data test_data = { + .int_0001 = 60, + .string_0001 = "(none)", +}; + +/* These are all under /proc/sys/debug/test_sysctl/ */ +static struct ctl_table test_table[] = { + { + .procname = "int_0001", + .data = &test_data.int_0001, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &i_zero, + .extra2 = &i_one_hundred, + }, + { + .procname = "string_0001", + .data = &test_data.string_0001, + .maxlen = sizeof(test_data.string_0001), + .mode = 0644, + .proc_handler = proc_dostring, + }, + { } +}; + +static struct ctl_table test_sysctl_table[] = { + { + .procname = "test_sysctl", + .maxlen = 0, + .mode = 0555, + .child = test_table, + }, + { } +}; + +static struct ctl_table test_sysctl_root_table[] = { + { + .procname = "debug", + .maxlen = 0, + .mode = 0555, + .child = test_sysctl_table, + }, + { } +}; + +static struct ctl_table_header *test_sysctl_header; + +static int __init test_sysctl_init(void) +{ + test_sysctl_header = register_sysctl_table(test_sysctl_root_table); + if (!test_sysctl_header) + return -ENOMEM; + return 0; +} +late_initcall(test_sysctl_init); + +static void __exit test_sysctl_exit(void) +{ + if (test_sysctl_header) + unregister_sysctl_table(test_sysctl_header); +} + +module_exit(test_sysctl_exit); + +MODULE_AUTHOR("Luis R. Rodriguez "); +MODULE_LICENSE("GPL"); diff --git a/tools/testing/selftests/sysctl/config b/tools/testing/selftests/sysctl/config new file mode 100644 index 000000000000..6ca14800d755 --- /dev/null +++ b/tools/testing/selftests/sysctl/config @@ -0,0 +1 @@ +CONFIG_TEST_SYSCTL=y diff --git a/tools/testing/selftests/sysctl/run_numerictests b/tools/testing/selftests/sysctl/run_numerictests index e6e76c93d948..c375ce0f4c15 100755 --- a/tools/testing/selftests/sysctl/run_numerictests +++ b/tools/testing/selftests/sysctl/run_numerictests @@ -1,7 +1,7 @@ #!/bin/sh -SYSCTL="/proc/sys" -TARGET="${SYSCTL}/vm/swappiness" +SYSCTL="/proc/sys/debug/test_sysctl/" +TARGET="${SYSCTL}/int_0001" ORIG=$(cat "${TARGET}") TEST_STR=$(( $ORIG + 1 )) diff --git a/tools/testing/selftests/sysctl/run_stringtests b/tools/testing/selftests/sysctl/run_stringtests index 857ec667fb02..a6f2618afeaa 100755 --- a/tools/testing/selftests/sysctl/run_stringtests +++ b/tools/testing/selftests/sysctl/run_stringtests @@ -1,7 +1,7 @@ #!/bin/sh -SYSCTL="/proc/sys" -TARGET="${SYSCTL}/kernel/domainname" +SYSCTL="/proc/sys/debug/test_sysctl/" +TARGET="${SYSCTL}/string_0001" ORIG=$(cat "${TARGET}") TEST_STR="Testing sysctl" -- cgit v1.2.3-59-g8ed1b From 64b671204afd71591e774e7237b7c862ac5bbd97 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Wed, 12 Jul 2017 14:33:46 -0700 Subject: test_sysctl: add generic script to expand on tests This adds a generic script to let us more easily add more tests cases. Since we really have only two types of tests cases just fold them into the one file. Each test unit is now identified into its separate function: # ./sysctl.sh -l Test ID list: TEST_ID x NUM_TEST TEST_ID: Test ID NUM_TESTS: Number of recommended times to run the test 0001 x 1 - tests proc_dointvec_minmax() 0002 x 1 - tests proc_dostring() For now we start off with what we had before, and run only each test once. We can now watch a test case until it fails: ./sysctl.sh -w 0002 We can also run a test case x number of times, say we want to run a test case 100 times: ./sysctl.sh -c 0001 100 To run a test case only once, for example: ./sysctl.sh -s 0002 The default settings are specified at the top of sysctl.sh. Link: http://lkml.kernel.org/r/20170630224431.17374-3-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez Cc: Kees Cook Cc: "Eric W. Biederman" Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/selftests/sysctl/Makefile | 3 +- tools/testing/selftests/sysctl/common_tests | 131 ------- tools/testing/selftests/sysctl/run_numerictests | 10 - tools/testing/selftests/sysctl/run_stringtests | 77 ---- tools/testing/selftests/sysctl/sysctl.sh | 494 ++++++++++++++++++++++++ 5 files changed, 495 insertions(+), 220 deletions(-) delete mode 100644 tools/testing/selftests/sysctl/common_tests delete mode 100755 tools/testing/selftests/sysctl/run_numerictests delete mode 100755 tools/testing/selftests/sysctl/run_stringtests create mode 100644 tools/testing/selftests/sysctl/sysctl.sh diff --git a/tools/testing/selftests/sysctl/Makefile b/tools/testing/selftests/sysctl/Makefile index b3c33e071f10..95c320b354e8 100644 --- a/tools/testing/selftests/sysctl/Makefile +++ b/tools/testing/selftests/sysctl/Makefile @@ -4,8 +4,7 @@ # No binaries, but make sure arg-less "make" doesn't trigger "run_tests". all: -TEST_PROGS := run_numerictests run_stringtests -TEST_FILES := common_tests +TEST_PROGS := sysctl.sh include ../lib.mk diff --git a/tools/testing/selftests/sysctl/common_tests b/tools/testing/selftests/sysctl/common_tests deleted file mode 100644 index b6862322962f..000000000000 --- a/tools/testing/selftests/sysctl/common_tests +++ /dev/null @@ -1,131 +0,0 @@ -#!/bin/sh - -TEST_FILE=$(mktemp) - -echo "== Testing sysctl behavior against ${TARGET} ==" - -set_orig() -{ - echo "${ORIG}" > "${TARGET}" -} - -set_test() -{ - echo "${TEST_STR}" > "${TARGET}" -} - -verify() -{ - local seen - seen=$(cat "$1") - if [ "${seen}" != "${TEST_STR}" ]; then - return 1 - fi - return 0 -} - -exit_test() -{ - if [ ! -z ${old_strict} ]; then - echo ${old_strict} > ${WRITES_STRICT} - fi - exit $rc -} - -trap 'set_orig; rm -f "${TEST_FILE}"' EXIT - -rc=0 - -echo -n "Writing test file ... " -echo "${TEST_STR}" > "${TEST_FILE}" -if ! verify "${TEST_FILE}"; then - echo "FAIL" >&2 - exit 1 -else - echo "ok" -fi - -echo -n "Checking sysctl is not set to test value ... " -if verify "${TARGET}"; then - echo "FAIL" >&2 - exit 1 -else - echo "ok" -fi - -echo -n "Writing sysctl from shell ... " -set_test -if ! verify "${TARGET}"; then - echo "FAIL" >&2 - exit 1 -else - echo "ok" -fi - -echo -n "Resetting sysctl to original value ... " -set_orig -if verify "${TARGET}"; then - echo "FAIL" >&2 - exit 1 -else - echo "ok" -fi - -echo -n "Checking write strict setting ... " -WRITES_STRICT="${SYSCTL}/kernel/sysctl_writes_strict" -if [ ! -e ${WRITES_STRICT} ]; then - echo "FAIL, but skip in case of old kernel" >&2 -else - old_strict=$(cat ${WRITES_STRICT}) - if [ "$old_strict" = "1" ]; then - echo "ok" - else - echo "FAIL, strict value is 0 but force to 1 to continue" >&2 - echo "1" > ${WRITES_STRICT} - fi -fi - -# Now that we've validated the sanity of "set_test" and "set_orig", -# we can use those functions to set starting states before running -# specific behavioral tests. - -echo -n "Writing entire sysctl in single write ... " -set_orig -dd if="${TEST_FILE}" of="${TARGET}" bs=4096 2>/dev/null -if ! verify "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Writing middle of sysctl after synchronized seek ... " -set_test -dd if="${TEST_FILE}" of="${TARGET}" bs=1 seek=1 skip=1 2>/dev/null -if ! verify "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Writing beyond end of sysctl ... " -set_orig -dd if="${TEST_FILE}" of="${TARGET}" bs=20 seek=2 2>/dev/null -if verify "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Writing sysctl with multiple long writes ... " -set_orig -(perl -e 'print "A" x 50;'; echo "${TEST_STR}") | \ - dd of="${TARGET}" bs=50 2>/dev/null -if verify "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi diff --git a/tools/testing/selftests/sysctl/run_numerictests b/tools/testing/selftests/sysctl/run_numerictests deleted file mode 100755 index c375ce0f4c15..000000000000 --- a/tools/testing/selftests/sysctl/run_numerictests +++ /dev/null @@ -1,10 +0,0 @@ -#!/bin/sh - -SYSCTL="/proc/sys/debug/test_sysctl/" -TARGET="${SYSCTL}/int_0001" -ORIG=$(cat "${TARGET}") -TEST_STR=$(( $ORIG + 1 )) - -. ./common_tests - -exit_test diff --git a/tools/testing/selftests/sysctl/run_stringtests b/tools/testing/selftests/sysctl/run_stringtests deleted file mode 100755 index a6f2618afeaa..000000000000 --- a/tools/testing/selftests/sysctl/run_stringtests +++ /dev/null @@ -1,77 +0,0 @@ -#!/bin/sh - -SYSCTL="/proc/sys/debug/test_sysctl/" -TARGET="${SYSCTL}/string_0001" -ORIG=$(cat "${TARGET}") -TEST_STR="Testing sysctl" - -. ./common_tests - -# Only string sysctls support seeking/appending. -MAXLEN=65 - -echo -n "Writing entire sysctl in short writes ... " -set_orig -dd if="${TEST_FILE}" of="${TARGET}" bs=1 2>/dev/null -if ! verify "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Writing middle of sysctl after unsynchronized seek ... " -set_test -dd if="${TEST_FILE}" of="${TARGET}" bs=1 seek=1 2>/dev/null -if verify "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Checking sysctl maxlen is at least $MAXLEN ... " -set_orig -perl -e 'print "A" x ('"${MAXLEN}"'-2), "B";' | \ - dd of="${TARGET}" bs="${MAXLEN}" 2>/dev/null -if ! grep -q B "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Checking sysctl keeps original string on overflow append ... " -set_orig -perl -e 'print "A" x ('"${MAXLEN}"'-1), "B";' | \ - dd of="${TARGET}" bs=$(( MAXLEN - 1 )) 2>/dev/null -if grep -q B "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Checking sysctl stays NULL terminated on write ... " -set_orig -perl -e 'print "A" x ('"${MAXLEN}"'-1), "B";' | \ - dd of="${TARGET}" bs="${MAXLEN}" 2>/dev/null -if grep -q B "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -echo -n "Checking sysctl stays NULL terminated on overwrite ... " -set_orig -perl -e 'print "A" x ('"${MAXLEN}"'-1), "BB";' | \ - dd of="${TARGET}" bs=$(( $MAXLEN + 1 )) 2>/dev/null -if grep -q B "${TARGET}"; then - echo "FAIL" >&2 - rc=1 -else - echo "ok" -fi - -exit_test diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh new file mode 100644 index 000000000000..cbe1345d7c1d --- /dev/null +++ b/tools/testing/selftests/sysctl/sysctl.sh @@ -0,0 +1,494 @@ +#!/bin/bash +# Copyright (C) 2017 Luis R. Rodriguez +# +# This program is free software; you can redistribute it and/or modify it +# under the terms of the GNU General Public License as published by the Free +# Software Foundation; either version 2 of the License, or at your option any +# later version; or, when distributed separately from the Linux kernel or +# when incorporated into other software packages, subject to the following +# license: +# +# This program is free software; you can redistribute it and/or modify it +# under the terms of copyleft-next (version 0.3.1 or later) as published +# at http://copyleft-next.org/. + +# This performs a series tests against the proc sysctl interface. + +TEST_NAME="sysctl" +TEST_DRIVER="test_${TEST_NAME}" +TEST_DIR=$(dirname $0) +TEST_FILE=$(mktemp) + +# This represents +# +# TEST_ID:TEST_COUNT:ENABLED +# +# TEST_ID: is the test id number +# TEST_COUNT: number of times we should run the test +# ENABLED: 1 if enabled, 0 otherwise +# +# Once these are enabled please leave them as-is. Write your own test, +# we have tons of space. +ALL_TESTS="0001:1:1" +ALL_TESTS="$ALL_TESTS 0002:1:1" + +test_modprobe() +{ + if [ ! -d $DIR ]; then + echo "$0: $DIR not present" >&2 + echo "You must have the following enabled in your kernel:" >&2 + cat $TEST_DIR/config >&2 + exit 1 + fi +} + +function allow_user_defaults() +{ + if [ -z $DIR ]; then + DIR="/sys/module/test_sysctl/" + fi + if [ -z $DEFAULT_NUM_TESTS ]; then + DEFAULT_NUM_TESTS=50 + fi + if [ -z $SYSCTL ]; then + SYSCTL="/proc/sys/debug/test_sysctl" + fi + if [ -z $PROD_SYSCTL ]; then + PROD_SYSCTL="/proc/sys" + fi + if [ -z $WRITES_STRICT ]; then + WRITES_STRICT="${PROD_SYSCTL}/kernel/sysctl_writes_strict" + fi +} + +function check_production_sysctl_writes_strict() +{ + echo -n "Checking production write strict setting ... " + if [ ! -e ${WRITES_STRICT} ]; then + echo "FAIL, but skip in case of old kernel" >&2 + else + old_strict=$(cat ${WRITES_STRICT}) + if [ "$old_strict" = "1" ]; then + echo "ok" + else + echo "FAIL, strict value is 0 but force to 1 to continue" >&2 + echo "1" > ${WRITES_STRICT} + fi + fi +} + +test_reqs() +{ + uid=$(id -u) + if [ $uid -ne 0 ]; then + echo $msg must be run as root >&2 + exit 0 + fi + + if ! which perl 2> /dev/null > /dev/null; then + echo "$0: You need perl installed" + exit 1 + fi +} + +function load_req_mod() +{ + trap "test_modprobe" EXIT + + if [ ! -d $DIR ]; then + modprobe $TEST_DRIVER + if [ $? -ne 0 ]; then + exit + fi + fi +} + +set_orig() +{ + if [ ! -z $TARGET ]; then + echo "${ORIG}" > "${TARGET}" + fi +} + +set_test() +{ + echo "${TEST_STR}" > "${TARGET}" +} + +verify() +{ + local seen + seen=$(cat "$1") + if [ "${seen}" != "${TEST_STR}" ]; then + return 1 + fi + return 0 +} + +test_rc() +{ + if [[ $rc != 0 ]]; then + echo "Failed test, return value: $rc" >&2 + exit $rc + fi +} + +test_finish() +{ + set_orig + rm -f "${TEST_FILE}" + + if [ ! -z ${old_strict} ]; then + echo ${old_strict} > ${WRITES_STRICT} + fi + exit $rc +} + +run_numerictests() +{ + echo "== Testing sysctl behavior against ${TARGET} ==" + + rc=0 + + echo -n "Writing test file ... " + echo "${TEST_STR}" > "${TEST_FILE}" + if ! verify "${TEST_FILE}"; then + echo "FAIL" >&2 + exit 1 + else + echo "ok" + fi + + echo -n "Checking sysctl is not set to test value ... " + if verify "${TARGET}"; then + echo "FAIL" >&2 + exit 1 + else + echo "ok" + fi + + echo -n "Writing sysctl from shell ... " + set_test + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + exit 1 + else + echo "ok" + fi + + echo -n "Resetting sysctl to original value ... " + set_orig + if verify "${TARGET}"; then + echo "FAIL" >&2 + exit 1 + else + echo "ok" + fi + + # Now that we've validated the sanity of "set_test" and "set_orig", + # we can use those functions to set starting states before running + # specific behavioral tests. + + echo -n "Writing entire sysctl in single write ... " + set_orig + dd if="${TEST_FILE}" of="${TARGET}" bs=4096 2>/dev/null + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Writing middle of sysctl after synchronized seek ... " + set_test + dd if="${TEST_FILE}" of="${TARGET}" bs=1 seek=1 skip=1 2>/dev/null + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Writing beyond end of sysctl ... " + set_orig + dd if="${TEST_FILE}" of="${TARGET}" bs=20 seek=2 2>/dev/null + if verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Writing sysctl with multiple long writes ... " + set_orig + (perl -e 'print "A" x 50;'; echo "${TEST_STR}") | \ + dd of="${TARGET}" bs=50 2>/dev/null + if verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + test_rc +} + +run_stringtests() +{ + echo -n "Writing entire sysctl in short writes ... " + set_orig + dd if="${TEST_FILE}" of="${TARGET}" bs=1 2>/dev/null + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Writing middle of sysctl after unsynchronized seek ... " + set_test + dd if="${TEST_FILE}" of="${TARGET}" bs=1 seek=1 2>/dev/null + if verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Checking sysctl maxlen is at least $MAXLEN ... " + set_orig + perl -e 'print "A" x ('"${MAXLEN}"'-2), "B";' | \ + dd of="${TARGET}" bs="${MAXLEN}" 2>/dev/null + if ! grep -q B "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Checking sysctl keeps original string on overflow append ... " + set_orig + perl -e 'print "A" x ('"${MAXLEN}"'-1), "B";' | \ + dd of="${TARGET}" bs=$(( MAXLEN - 1 )) 2>/dev/null + if grep -q B "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Checking sysctl stays NULL terminated on write ... " + set_orig + perl -e 'print "A" x ('"${MAXLEN}"'-1), "B";' | \ + dd of="${TARGET}" bs="${MAXLEN}" 2>/dev/null + if grep -q B "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + echo -n "Checking sysctl stays NULL terminated on overwrite ... " + set_orig + perl -e 'print "A" x ('"${MAXLEN}"'-1), "BB";' | \ + dd of="${TARGET}" bs=$(( $MAXLEN + 1 )) 2>/dev/null + if grep -q B "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + + test_rc +} + +sysctl_test_0001() +{ + TARGET="${SYSCTL}/int_0001" + ORIG=$(cat "${TARGET}") + TEST_STR=$(( $ORIG + 1 )) + + run_numerictests +} + +sysctl_test_0002() +{ + TARGET="${SYSCTL}/string_0001" + ORIG=$(cat "${TARGET}") + TEST_STR="Testing sysctl" + # Only string sysctls support seeking/appending. + MAXLEN=65 + + run_numerictests + run_stringtests +} + +list_tests() +{ + echo "Test ID list:" + echo + echo "TEST_ID x NUM_TEST" + echo "TEST_ID: Test ID" + echo "NUM_TESTS: Number of recommended times to run the test" + echo + echo "0001 x $(get_test_count 0001) - tests proc_dointvec_minmax()" + echo "0002 x $(get_test_count 0002) - tests proc_dostring()" +} + +test_reqs + +usage() +{ + NUM_TESTS=$(grep -o ' ' <<<"$ALL_TESTS" | grep -c .) + let NUM_TESTS=$NUM_TESTS+1 + MAX_TEST=$(printf "%04d\n" $NUM_TESTS) + echo "Usage: $0 [ -t <4-number-digit> ] | [ -w <4-number-digit> ] |" + echo " [ -s <4-number-digit> ] | [ -c <4-number-digit> " + echo " [ all ] [ -h | --help ] [ -l ]" + echo "" + echo "Valid tests: 0001-$MAX_TEST" + echo "" + echo " all Runs all tests (default)" + echo " -t Run test ID the number amount of times is recommended" + echo " -w Watch test ID run until it runs into an error" + echo " -c Run test ID once" + echo " -s Run test ID x test-count number of times" + echo " -l List all test ID list" + echo " -h|--help Help" + echo + echo "If an error every occurs execution will immediately terminate." + echo "If you are adding a new test try using -w first to" + echo "make sure the test passes a series of tests." + echo + echo Example uses: + echo + echo "$TEST_NAME.sh -- executes all tests" + echo "$TEST_NAME.sh -t 0002 -- Executes test ID 0002 number of times is recomended" + echo "$TEST_NAME.sh -w 0002 -- Watch test ID 0002 run until an error occurs" + echo "$TEST_NAME.sh -s 0002 -- Run test ID 0002 once" + echo "$TEST_NAME.sh -c 0002 3 -- Run test ID 0002 three times" + echo + list_tests + exit 1 +} + +function test_num() +{ + re='^[0-9]+$' + if ! [[ $1 =~ $re ]]; then + usage + fi +} + +function get_test_count() +{ + test_num $1 + TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}') + LAST_TWO=${TEST_DATA#*:*} + echo ${LAST_TWO%:*} +} + +function get_test_enabled() +{ + test_num $1 + TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}') + echo ${TEST_DATA#*:*:} +} + +function run_all_tests() +{ + for i in $ALL_TESTS ; do + TEST_ID=${i%:*:*} + ENABLED=$(get_test_enabled $TEST_ID) + TEST_COUNT=$(get_test_count $TEST_ID) + if [[ $ENABLED -eq "1" ]]; then + test_case $TEST_ID $TEST_COUNT + fi + done +} + +function watch_log() +{ + if [ $# -ne 3 ]; then + clear + fi + date + echo "Running test: $2 - run #$1" +} + +function watch_case() +{ + i=0 + while [ 1 ]; do + + if [ $# -eq 1 ]; then + test_num $1 + watch_log $i ${TEST_NAME}_test_$1 + ${TEST_NAME}_test_$1 + else + watch_log $i all + run_all_tests + fi + let i=$i+1 + done +} + +function test_case() +{ + NUM_TESTS=$DEFAULT_NUM_TESTS + if [ $# -eq 2 ]; then + NUM_TESTS=$2 + fi + + i=0 + while [ $i -lt $NUM_TESTS ]; do + test_num $1 + watch_log $i ${TEST_NAME}_test_$1 noclear + RUN_TEST=${TEST_NAME}_test_$1 + $RUN_TEST + let i=$i+1 + done +} + +function parse_args() +{ + if [ $# -eq 0 ]; then + run_all_tests + else + if [[ "$1" = "all" ]]; then + run_all_tests + elif [[ "$1" = "-w" ]]; then + shift + watch_case $@ + elif [[ "$1" = "-t" ]]; then + shift + test_num $1 + test_case $1 $(get_test_count $1) + elif [[ "$1" = "-c" ]]; then + shift + test_num $1 + test_num $2 + test_case $1 $2 + elif [[ "$1" = "-s" ]]; then + shift + test_case $1 1 + elif [[ "$1" = "-l" ]]; then + list_tests + elif [[ "$1" = "-h" || "$1" = "--help" ]]; then + usage + else + usage + fi + fi +} + +test_reqs +allow_user_defaults +check_production_sysctl_writes_strict +load_req_mod + +trap "test_finish" EXIT + +parse_args $@ + +exit 0 -- cgit v1.2.3-59-g8ed1b From 1c0357c846452add7c2c863ec372010e3d2ca943 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Wed, 12 Jul 2017 14:33:49 -0700 Subject: test_sysctl: test against PAGE_SIZE for int Add the following tests to ensure we do not regress: o Test using a buffer full of space (PAGE_SIZE-1) followed by a single digit works o Test using a buffer full of spaces (PAGE_SIZE or over) will fail As tests increase instead of unloading the module and reloading it we can just do a shell reset_vals() with a reset to values we know are set at init on the driver. Link: http://lkml.kernel.org/r/20170630224431.17374-4-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez Cc: Kees Cook Cc: "Eric W. Biederman" Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/selftests/sysctl/sysctl.sh | 66 ++++++++++++++++++++++++++++++++ 1 file changed, 66 insertions(+) diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh index cbe1345d7c1d..6ec807576f7c 100644 --- a/tools/testing/selftests/sysctl/sysctl.sh +++ b/tools/testing/selftests/sysctl/sysctl.sh @@ -75,6 +75,13 @@ function check_production_sysctl_writes_strict() echo "1" > ${WRITES_STRICT} fi fi + + if [ -z $PAGE_SIZE ]; then + PAGE_SIZE=$(getconf PAGESIZE) + fi + if [ -z $MAX_DIGITS ]; then + MAX_DIGITS=$(($PAGE_SIZE/8)) + fi } test_reqs() @@ -89,6 +96,10 @@ test_reqs() echo "$0: You need perl installed" exit 1 fi + if ! which getconf 2> /dev/null > /dev/null; then + echo "$0: You need getconf installed" + exit 1 + fi } function load_req_mod() @@ -103,6 +114,23 @@ function load_req_mod() fi } +reset_vals() +{ + VAL="" + TRIGGER=$(basename ${TARGET}) + case "$TRIGGER" in + int_0001) + VAL="60" + ;; + string_0001) + VAL="(none)" + ;; + *) + ;; + esac + echo -n $VAL > $TARGET +} + set_orig() { if [ ! -z $TARGET ]; then @@ -229,7 +257,42 @@ run_numerictests() else echo "ok" fi + test_rc +} + +# Your test must accept digits 3 and 4 to use this +run_limit_digit() +{ + echo -n "Checking ignoring spaces up to PAGE_SIZE works on write ..." + reset_vals + LIMIT=$((MAX_DIGITS -1)) + TEST_STR="3" + (perl -e 'print " " x '$LIMIT';'; echo "${TEST_STR}") | \ + dd of="${TARGET}" 2>/dev/null + + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Checking passing PAGE_SIZE of spaces fails on write ..." + reset_vals + + LIMIT=$((MAX_DIGITS)) + TEST_STR="4" + (perl -e 'print " " x '$LIMIT';'; echo "${TEST_STR}") | \ + dd of="${TARGET}" 2>/dev/null + + if verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi test_rc } @@ -305,15 +368,18 @@ run_stringtests() sysctl_test_0001() { TARGET="${SYSCTL}/int_0001" + reset_vals ORIG=$(cat "${TARGET}") TEST_STR=$(( $ORIG + 1 )) run_numerictests + run_limit_digit } sysctl_test_0002() { TARGET="${SYSCTL}/string_0001" + reset_vals ORIG=$(cat "${TARGET}") TEST_STR="Testing sysctl" # Only string sysctls support seeking/appending. -- cgit v1.2.3-59-g8ed1b From eb965eda1cabf26e62afc07a06cdf2fd5aaa2906 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Wed, 12 Jul 2017 14:33:52 -0700 Subject: test_sysctl: add simple proc_dointvec() case Test against a simple proc_dointvec() case. While at it, add a test against INT_MAX. Make sure INT_MAX works, and INT_MAX+1 will fail. Also test negative values work. Link: http://lkml.kernel.org/r/20170630224431.17374-5-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez Cc: Kees Cook Cc: "Eric W. Biederman" Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/test_sysctl.c | 11 ++++++ tools/testing/selftests/sysctl/sysctl.sh | 62 ++++++++++++++++++++++++++++++++ 2 files changed, 73 insertions(+) diff --git a/lib/test_sysctl.c b/lib/test_sysctl.c index b2163bfb6eb2..1472e1ae4931 100644 --- a/lib/test_sysctl.c +++ b/lib/test_sysctl.c @@ -41,11 +41,15 @@ static int i_one_hundred = 100; struct test_sysctl_data { int int_0001; + int int_0002; + char string_0001[65]; }; static struct test_sysctl_data test_data = { .int_0001 = 60, + .int_0002 = 1, + .string_0001 = "(none)", }; @@ -60,6 +64,13 @@ static struct ctl_table test_table[] = { .extra1 = &i_zero, .extra2 = &i_one_hundred, }, + { + .procname = "int_0002", + .data = &test_data.int_0002, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { .procname = "string_0001", .data = &test_data.string_0001, diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh index 6ec807576f7c..7ba3fa2bbd54 100644 --- a/tools/testing/selftests/sysctl/sysctl.sh +++ b/tools/testing/selftests/sysctl/sysctl.sh @@ -31,6 +31,7 @@ TEST_FILE=$(mktemp) # we have tons of space. ALL_TESTS="0001:1:1" ALL_TESTS="$ALL_TESTS 0002:1:1" +ALL_TESTS="$ALL_TESTS 0003:1:1" test_modprobe() { @@ -82,6 +83,9 @@ function check_production_sysctl_writes_strict() if [ -z $MAX_DIGITS ]; then MAX_DIGITS=$(($PAGE_SIZE/8)) fi + if [ -z $INT_MAX ]; then + INT_MAX=$(getconf INT_MAX) + fi } test_reqs() @@ -122,6 +126,9 @@ reset_vals() int_0001) VAL="60" ;; + int_0002) + VAL="1" + ;; string_0001) VAL="(none)" ;; @@ -296,6 +303,48 @@ run_limit_digit() test_rc } +# You are using an int +run_limit_digit_int() +{ + echo -n "Testing INT_MAX works ..." + reset_vals + TEST_STR="$INT_MAX" + echo -n $TEST_STR > $TARGET + + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Testing INT_MAX + 1 will fail as expected..." + reset_vals + let TEST_STR=$INT_MAX+1 + echo -n $TEST_STR > $TARGET 2> /dev/null + + if verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Testing negative values will work as expected..." + reset_vals + TEST_STR="-3" + echo -n $TEST_STR > $TARGET 2> /dev/null + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc +} + run_stringtests() { echo -n "Writing entire sysctl in short writes ... " @@ -389,6 +438,18 @@ sysctl_test_0002() run_stringtests } +sysctl_test_0003() +{ + TARGET="${SYSCTL}/int_0002" + reset_vals + ORIG=$(cat "${TARGET}") + TEST_STR=$(( $ORIG + 1 )) + + run_numerictests + run_limit_digit + run_limit_digit_int +} + list_tests() { echo "Test ID list:" @@ -399,6 +460,7 @@ list_tests() echo echo "0001 x $(get_test_count 0001) - tests proc_dointvec_minmax()" echo "0002 x $(get_test_count 0002) - tests proc_dostring()" + echo "0003 x $(get_test_count 0003) - tests proc_dointvec()" } test_reqs -- cgit v1.2.3-59-g8ed1b From 2920fad3a5d394b66011c7f35c7b05278354055e Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Wed, 12 Jul 2017 14:33:55 -0700 Subject: test_sysctl: add simple proc_douintvec() case Test against a simple proc_douintvec() case. While at it, add a test against UINT_MAX. Make sure UINT_MAX works, and UINT_MAX+1 will fail and that negative values are not accepted. Link: http://lkml.kernel.org/r/20170630224431.17374-6-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez Cc: Kees Cook Cc: "Eric W. Biederman" Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/test_sysctl.c | 11 ++++++ tools/testing/selftests/sysctl/sysctl.sh | 63 ++++++++++++++++++++++++++++++++ 2 files changed, 74 insertions(+) diff --git a/lib/test_sysctl.c b/lib/test_sysctl.c index 1472e1ae4931..53db3513ab08 100644 --- a/lib/test_sysctl.c +++ b/lib/test_sysctl.c @@ -43,6 +43,8 @@ struct test_sysctl_data { int int_0001; int int_0002; + unsigned int uint_0001; + char string_0001[65]; }; @@ -50,6 +52,8 @@ static struct test_sysctl_data test_data = { .int_0001 = 60, .int_0002 = 1, + .uint_0001 = 314, + .string_0001 = "(none)", }; @@ -71,6 +75,13 @@ static struct ctl_table test_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "uint_0001", + .data = &test_data.uint_0001, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_douintvec, + }, { .procname = "string_0001", .data = &test_data.string_0001, diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh index 7ba3fa2bbd54..abeef675a884 100644 --- a/tools/testing/selftests/sysctl/sysctl.sh +++ b/tools/testing/selftests/sysctl/sysctl.sh @@ -32,6 +32,7 @@ TEST_FILE=$(mktemp) ALL_TESTS="0001:1:1" ALL_TESTS="$ALL_TESTS 0002:1:1" ALL_TESTS="$ALL_TESTS 0003:1:1" +ALL_TESTS="$ALL_TESTS 0004:1:1" test_modprobe() { @@ -86,6 +87,9 @@ function check_production_sysctl_writes_strict() if [ -z $INT_MAX ]; then INT_MAX=$(getconf INT_MAX) fi + if [ -z $UINT_MAX ]; then + UINT_MAX=$(getconf UINT_MAX) + fi } test_reqs() @@ -129,6 +133,9 @@ reset_vals() int_0002) VAL="1" ;; + uint_0001) + VAL="314" + ;; string_0001) VAL="(none)" ;; @@ -345,6 +352,49 @@ run_limit_digit_int() test_rc } +# You are using an unsigned int +run_limit_digit_uint() +{ + echo -n "Testing UINT_MAX works ..." + reset_vals + TEST_STR="$UINT_MAX" + echo -n $TEST_STR > $TARGET + + if ! verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Testing UINT_MAX + 1 will fail as expected..." + reset_vals + TEST_STR=$(($UINT_MAX+1)) + echo -n $TEST_STR > $TARGET 2> /dev/null + + if verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Testing negative values will not work as expected ..." + reset_vals + TEST_STR="-3" + echo -n $TEST_STR > $TARGET 2> /dev/null + + if verify "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc +} + run_stringtests() { echo -n "Writing entire sysctl in short writes ... " @@ -450,6 +500,18 @@ sysctl_test_0003() run_limit_digit_int } +sysctl_test_0004() +{ + TARGET="${SYSCTL}/uint_0001" + reset_vals + ORIG=$(cat "${TARGET}") + TEST_STR=$(( $ORIG + 1 )) + + run_numerictests + run_limit_digit + run_limit_digit_uint +} + list_tests() { echo "Test ID list:" @@ -461,6 +523,7 @@ list_tests() echo "0001 x $(get_test_count 0001) - tests proc_dointvec_minmax()" echo "0002 x $(get_test_count 0002) - tests proc_dostring()" echo "0003 x $(get_test_count 0003) - tests proc_dointvec()" + echo "0004 x $(get_test_count 0004) - tests proc_douintvec()" } test_reqs -- cgit v1.2.3-59-g8ed1b From 7c43a657a4beadeb6d2fe1a00732261e313a807f Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Wed, 12 Jul 2017 14:33:58 -0700 Subject: test_sysctl: test against int proc_dointvec() array support Add a few initial respective tests for an array: o Echoing values separated by spaces works o Echoing only first elements will set first elements o Confirm PAGE_SIZE limit still applies even if an array is used Link: http://lkml.kernel.org/r/20170630224431.17374-7-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez Cc: Kees Cook Cc: "Eric W. Biederman" Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/test_sysctl.c | 13 +++++ tools/testing/selftests/sysctl/sysctl.sh | 89 ++++++++++++++++++++++++++++++++ 2 files changed, 102 insertions(+) diff --git a/lib/test_sysctl.c b/lib/test_sysctl.c index 53db3513ab08..3dd801c1c85b 100644 --- a/lib/test_sysctl.c +++ b/lib/test_sysctl.c @@ -42,6 +42,7 @@ static int i_one_hundred = 100; struct test_sysctl_data { int int_0001; int int_0002; + int int_0003[4]; unsigned int uint_0001; @@ -52,6 +53,11 @@ static struct test_sysctl_data test_data = { .int_0001 = 60, .int_0002 = 1, + .int_0003[0] = 0, + .int_0003[1] = 1, + .int_0003[2] = 2, + .int_0003[3] = 3, + .uint_0001 = 314, .string_0001 = "(none)", @@ -75,6 +81,13 @@ static struct ctl_table test_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "int_0003", + .data = &test_data.int_0003, + .maxlen = sizeof(test_data.int_0003), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { .procname = "uint_0001", .data = &test_data.uint_0001, diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh index abeef675a884..ec232c3cfcaa 100644 --- a/tools/testing/selftests/sysctl/sysctl.sh +++ b/tools/testing/selftests/sysctl/sysctl.sh @@ -33,6 +33,7 @@ ALL_TESTS="0001:1:1" ALL_TESTS="$ALL_TESTS 0002:1:1" ALL_TESTS="$ALL_TESTS 0003:1:1" ALL_TESTS="$ALL_TESTS 0004:1:1" +ALL_TESTS="$ALL_TESTS 0005:3:1" test_modprobe() { @@ -108,6 +109,10 @@ test_reqs() echo "$0: You need getconf installed" exit 1 fi + if ! which diff 2> /dev/null > /dev/null; then + echo "$0: You need diff installed" + exit 1 + fi } function load_req_mod() @@ -167,6 +172,12 @@ verify() return 0 } +verify_diff_w() +{ + echo "$TEST_STR" | diff -q -w -u - $1 + return $? +} + test_rc() { if [[ $rc != 0 ]]; then @@ -352,6 +363,74 @@ run_limit_digit_int() test_rc } +# You used an int array +run_limit_digit_int_array() +{ + echo -n "Testing array works as expected ... " + TEST_STR="4 3 2 1" + echo -n $TEST_STR > $TARGET + + if ! verify_diff_w "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Testing skipping trailing array elements works ... " + # Do not reset_vals, carry on the values from the last test. + # If we only echo in two digits the last two are left intact + TEST_STR="100 101" + echo -n $TEST_STR > $TARGET + # After we echo in, to help diff we need to set on TEST_STR what + # we expect the result to be. + TEST_STR="100 101 2 1" + + if ! verify_diff_w "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Testing PAGE_SIZE limit on array works ... " + # Do not reset_vals, carry on the values from the last test. + # Even if you use an int array, you are still restricted to + # MAX_DIGITS, this is a known limitation. Test limit works. + LIMIT=$((MAX_DIGITS -1)) + TEST_STR="9" + (perl -e 'print " " x '$LIMIT';'; echo "${TEST_STR}") | \ + dd of="${TARGET}" 2>/dev/null + + TEST_STR="9 101 2 1" + if ! verify_diff_w "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc + + echo -n "Testing exceeding PAGE_SIZE limit fails as expected ... " + # Do not reset_vals, carry on the values from the last test. + # Now go over limit. + LIMIT=$((MAX_DIGITS)) + TEST_STR="7" + (perl -e 'print " " x '$LIMIT';'; echo "${TEST_STR}") | \ + dd of="${TARGET}" 2>/dev/null + + TEST_STR="7 101 2 1" + if verify_diff_w "${TARGET}"; then + echo "FAIL" >&2 + rc=1 + else + echo "ok" + fi + test_rc +} + # You are using an unsigned int run_limit_digit_uint() { @@ -512,6 +591,15 @@ sysctl_test_0004() run_limit_digit_uint } +sysctl_test_0005() +{ + TARGET="${SYSCTL}/int_0003" + reset_vals + ORIG=$(cat "${TARGET}") + + run_limit_digit_int_array +} + list_tests() { echo "Test ID list:" @@ -524,6 +612,7 @@ list_tests() echo "0002 x $(get_test_count 0002) - tests proc_dostring()" echo "0003 x $(get_test_count 0003) - tests proc_dointvec()" echo "0004 x $(get_test_count 0004) - tests proc_douintvec()" + echo "0005 x $(get_test_count 0005) - tests proc_douintvec() array" } test_reqs -- cgit v1.2.3-59-g8ed1b From 9380fa60b10ebd6ee7c3fcdb2cf162f4d7cf9fc5 Mon Sep 17 00:00:00 2001 From: Mateusz Jurczyk Date: Wed, 12 Jul 2017 14:34:01 -0700 Subject: kernel/sysctl_binary.c: check name array length in deprecated_sysctl_warning() Prevent use of uninitialized memory (originating from the stack frame of do_sysctl()) by verifying that the name array is filled with sufficient input data before comparing its specific entries with integer constants. Through timing measurement or analyzing the kernel debug logs, a user-mode program could potentially infer the results of comparisons against the uninitialized memory, and acquire some (very limited) information about the state of the kernel stack. The change also eliminates possible future warnings by tools such as KMSAN and other code checkers / instrumentations. Link: http://lkml.kernel.org/r/20170524122139.21333-1-mjurczyk@google.com Signed-off-by: Mateusz Jurczyk Acked-by: Kees Cook Cc: "David S. Miller" Cc: Matthew Whitehead Cc: "Eric W. Biederman" Cc: Tetsuo Handa Cc: Alexander Potapenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl_binary.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index 939a158eab11..02e1859f2ca8 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -1346,7 +1346,7 @@ static void deprecated_sysctl_warning(const int *name, int nlen) * CTL_KERN/KERN_VERSION is used by older glibc and cannot * ever go away. */ - if (name[0] == CTL_KERN && name[1] == KERN_VERSION) + if (nlen >= 2 && name[0] == CTL_KERN && name[1] == KERN_VERSION) return; if (printk_ratelimit()) { -- cgit v1.2.3-59-g8ed1b From ee7998c50c2697737c6530431709f77c852bf0d6 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Jul 2017 14:34:04 -0700 Subject: random: do not ignore early device randomness The add_device_randomness() function would ignore incoming bytes if the crng wasn't ready. This additionally makes sure to make an early enough call to add_latent_entropy() to influence the initial stack canary, which is especially important on non-x86 systems where it stays the same through the life of the boot. Link: http://lkml.kernel.org/r/20170626233038.GA48751@beast Signed-off-by: Kees Cook Cc: "Theodore Ts'o" Cc: Arnd Bergmann Cc: Greg Kroah-Hartman Cc: Ingo Molnar Cc: Jessica Yu Cc: Steven Rostedt (VMware) Cc: Viresh Kumar Cc: Tejun Heo Cc: Prarit Bhargava Cc: Lokesh Vutla Cc: Nicholas Piggin Cc: AKASHI Takahiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/char/random.c | 5 +++++ init/main.c | 1 + 2 files changed, 6 insertions(+) diff --git a/drivers/char/random.c b/drivers/char/random.c index 01a260f67437..23cab7a8c1c1 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -987,6 +987,11 @@ void add_device_randomness(const void *buf, unsigned int size) unsigned long time = random_get_entropy() ^ jiffies; unsigned long flags; + if (!crng_ready()) { + crng_fast_load(buf, size); + return; + } + trace_add_device_randomness(size, _RET_IP_); spin_lock_irqsave(&input_pool.lock, flags); _mix_pool_bytes(&input_pool, buf, size); diff --git a/init/main.c b/init/main.c index df58a416dd1d..052481fbe363 100644 --- a/init/main.c +++ b/init/main.c @@ -518,6 +518,7 @@ asmlinkage __visible void __init start_kernel(void) /* * Set up the initial canary ASAP: */ + add_latent_entropy(); boot_init_stack_canary(); cgroup_init_early(); -- cgit v1.2.3-59-g8ed1b From 5f9f48f5b385457426b4b8f3f4a604019a8e7350 Mon Sep 17 00:00:00 2001 From: Rakesh Pandit Date: Wed, 12 Jul 2017 14:34:07 -0700 Subject: bfs: fix sanity checks for empty files Mount fails if file system image has empty files because of sanity check while reading superblock. For empty files disk offset to end of file (i_eoffset) is cpu_to_le32(-1). Sanity check comparison, which compares disk offset with file system size isn't valid for this value and hence is ignored with this patch. Steps to reproduce: $ dd if=/dev/zero of=bfs-image count=204800 $ mkfs.bfs bfs-image $ mkdir bfs-mount-point $ sudo mount -t bfs -o loop bfs-image bfs-mount-point/ $ cd bfs-mount-point/ $ sudo touch a $ cd .. $ sudo umount bfs-mount-point/ $ sudo mount -t bfs -o loop bfs-image bfs-mount-point/ mount: /dev/loop0: can't read superblock $ dmesg [25526.689580] BFS-fs: bfs_fill_super(): Inode 0x00000003 corrupted Tigran said: "If you had created the filesystem with the proper mkfs under SCO UnixWare 7 you (probably) wouldn't encounter this issue. But since commercial Unix-es are now part of history and the only proper way is the Linux mkfs.bfs utility, your patch is fine" Link: http://lkml.kernel.org/r/20170505201625.GA3097@hercules.tuxera.com Signed-off-by: Rakesh Pandit Acked-by: Tigran Aivazian Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/bfs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index 25e312cb6071..9a69392f1fb3 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -419,7 +419,7 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent) if (i_sblock > info->si_blocks || i_eblock > info->si_blocks || i_sblock > i_eblock || - i_eoff > s_size || + (i_eoff != le32_to_cpu(-1) && i_eoff > s_size) || i_sblock * BFS_BSIZE > i_eoff) { printf("Inode 0x%08x corrupted\n", i); -- cgit v1.2.3-59-g8ed1b From 59224ac1cf9cacf76a82266854921ca6c9887f20 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Wed, 12 Jul 2017 14:34:10 -0700 Subject: fs/Kconfig: kill CONFIG_PERCPU_RWSEM some more As of commit bf3eac84c42d ("percpu-rwsem: kill CONFIG_PERCPU_RWSEM") we unconditionally build pcpu-rwsems. Remove a leftover in for FILE_LOCKING. Link: http://lkml.kernel.org/r/20170518180115.2794-1-dave@stgolabs.net Signed-off-by: Davidlohr Bueso Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/Kconfig b/fs/Kconfig index b0e42b6a96b9..7aee6d699fd6 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -80,7 +80,6 @@ config EXPORTFS_BLOCK_OPS config FILE_LOCKING bool "Enable POSIX file locking API" if EXPERT default y - select PERCPU_RWSEM help This option enables standard file locking support, required for filesystems like NFS and for the flock() system -- cgit v1.2.3-59-g8ed1b From 821f74402a4c67de63cb6bab5bae7c7a3b298ac2 Mon Sep 17 00:00:00 2001 From: Peter Griffin Date: Wed, 12 Jul 2017 14:34:13 -0700 Subject: scripts/gdb: add lx-fdtdump command lx-fdtdump dumps the flattened device tree passed to the kernel from the bootloader to the filename specified as the command argument. If no argument is provided it defaults to fdtdump.dtb. This then allows further post processing on the machine running GDB. The fdt header is also also printed in the GDB console. For example: (gdb) lx-fdtdump fdt_magic: 0xD00DFEED fdt_totalsize: 0xC108 off_dt_struct: 0x38 off_dt_strings: 0x3804 off_mem_rsvmap: 0x28 version: 17 last_comp_version: 16 Dumped fdt to fdtdump.dtb >fdtdump fdtdump.dtb | less This command is useful as the bootloader can often re-write parts of the device tree, and this can sometimes cause the kernel to not boot. Link: http://lkml.kernel.org/r/1481280065-5336-2-git-send-email-kbingham@kernel.org Signed-off-by: Peter Griffin Signed-off-by: Kieran Bingham Cc: Jason Wessel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/gdb/linux/constants.py.in | 7 ++++ scripts/gdb/linux/proc.py | 73 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 80 insertions(+) diff --git a/scripts/gdb/linux/constants.py.in b/scripts/gdb/linux/constants.py.in index 7986f4e0da12..7aad82406422 100644 --- a/scripts/gdb/linux/constants.py.in +++ b/scripts/gdb/linux/constants.py.in @@ -14,6 +14,7 @@ #include #include +#include /* We need to stringify expanded macros so that they can be parsed */ @@ -50,3 +51,9 @@ LX_VALUE(MNT_NOEXEC) LX_VALUE(MNT_NOATIME) LX_VALUE(MNT_NODIRATIME) LX_VALUE(MNT_RELATIME) + +/* linux/of_fdt.h> */ +LX_VALUE(OF_DT_HEADER) + +/* Kernel Configs */ +LX_CONFIG(CONFIG_OF) diff --git a/scripts/gdb/linux/proc.py b/scripts/gdb/linux/proc.py index 38b1f09d1cd9..086d27223c0c 100644 --- a/scripts/gdb/linux/proc.py +++ b/scripts/gdb/linux/proc.py @@ -16,6 +16,7 @@ from linux import constants from linux import utils from linux import tasks from linux import lists +from struct import * class LxCmdLine(gdb.Command): @@ -195,3 +196,75 @@ values of that process namespace""" info_opts(MNT_INFO, m_flags))) LxMounts() + + +class LxFdtDump(gdb.Command): + """Output Flattened Device Tree header and dump FDT blob to the filename + specified as the command argument. Equivalent to + 'cat /proc/fdt > fdtdump.dtb' on a running target""" + + def __init__(self): + super(LxFdtDump, self).__init__("lx-fdtdump", gdb.COMMAND_DATA, + gdb.COMPLETE_FILENAME) + + def fdthdr_to_cpu(self, fdt_header): + + fdt_header_be = ">IIIIIII" + fdt_header_le = " Date: Wed, 12 Jul 2017 14:34:16 -0700 Subject: scripts/gdb: lx-dmesg: cast log_buf to void* for addr fetch In some cases it is possible for the str() conversion here to throw encoding errors because log_buf might not point to valid ascii. For example: (gdb) python print str(gdb.parse_and_eval("log_buf")) Traceback (most recent call last): File "", line 1, in UnicodeEncodeError: 'ascii' codec can't encode character u'\u0303' in position 24: ordinal not in range(128) Avoid this by explicitly casting to (void *) inside the gdb expression. Link: http://lkml.kernel.org/r/ba6f85dbb02ca980ebd0e2399b0649423399b565.1498481469.git.leonard.crestez@nxp.com Signed-off-by: Leonard Crestez Reviewed-by: Jan Kiszka Cc: Jason Wessel Cc: Kieran Bingham Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/gdb/linux/dmesg.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/gdb/linux/dmesg.py b/scripts/gdb/linux/dmesg.py index 5afd1098e33a..f5a030333dfd 100644 --- a/scripts/gdb/linux/dmesg.py +++ b/scripts/gdb/linux/dmesg.py @@ -24,7 +24,7 @@ class LxDmesg(gdb.Command): def invoke(self, arg, from_tty): log_buf_addr = int(str(gdb.parse_and_eval( - "'printk.c'::log_buf")).split()[0], 16) + "(void *)'printk.c'::log_buf")).split()[0], 16) log_first_idx = int(gdb.parse_and_eval("'printk.c'::log_first_idx")) log_next_idx = int(gdb.parse_and_eval("'printk.c'::log_next_idx")) log_buf_len = int(gdb.parse_and_eval("'printk.c'::log_buf_len")) -- cgit v1.2.3-59-g8ed1b From 46d10a094353c05144f3b0530516bdac3ce7c435 Mon Sep 17 00:00:00 2001 From: Leonard Crestez Date: Wed, 12 Jul 2017 14:34:19 -0700 Subject: scripts/gdb: lx-dmesg: use explicit encoding=utf8 errors=replace Use errors=replace because it is never desirable for lx-dmesg to fail on string decoding errors, not even if the log buffer is corrupt and we show incorrect info. The kernel will sometimes print utf8, for example the copyright symbol from jffs2. In order to make this work specify 'utf8' everywhere because python2 otherwise defaults to 'ascii'. In theory the second errors='replace' is not be required because everything that can be decoded as utf8 should also be encodable back to utf8. But it's better to be extra safe here. It's worth noting that this is definitely not true for encoding='ascii', unknown characters are replaced with U+FFFD REPLACEMENT CHARACTER and they fail to encode back to ascii. Link: http://lkml.kernel.org/r/acee067f3345954ed41efb77b80eebdc038619c6.1498481469.git.leonard.crestez@nxp.com Signed-off-by: Leonard Crestez Acked-by: Jan Kiszka Cc: Jason Wessel Cc: Kieran Bingham Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/gdb/linux/dmesg.py | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/scripts/gdb/linux/dmesg.py b/scripts/gdb/linux/dmesg.py index f5a030333dfd..6d2e09a2ad2f 100644 --- a/scripts/gdb/linux/dmesg.py +++ b/scripts/gdb/linux/dmesg.py @@ -12,6 +12,7 @@ # import gdb +import sys from linux import utils @@ -52,13 +53,19 @@ class LxDmesg(gdb.Command): continue text_len = utils.read_u16(log_buf[pos + 10:pos + 12]) - text = log_buf[pos + 16:pos + 16 + text_len].decode() + text = log_buf[pos + 16:pos + 16 + text_len].decode( + encoding='utf8', errors='replace') time_stamp = utils.read_u64(log_buf[pos:pos + 8]) for line in text.splitlines(): - gdb.write("[{time:12.6f}] {line}\n".format( + msg = u"[{time:12.6f}] {line}\n".format( time=time_stamp / 1000000000.0, - line=line)) + line=line) + # With python2 gdb.write will attempt to convert unicode to + # ascii and might fail so pass an utf8-encoded str instead. + if sys.hexversion < 0x03000000: + msg = msg.encode(encoding='utf8', errors='replace') + gdb.write(msg) pos += length -- cgit v1.2.3-59-g8ed1b From 9263969a46fc899092ba4f8c4206fa2340c9a64e Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Wed, 12 Jul 2017 14:34:22 -0700 Subject: kfifo: clean up example to not use page_link This is a layering violation so we replace the uses with calls to sg_page(). This is a prep patch for replacing page_link and this is one of the very few uses outside of scatterlist.h. Link: http://lkml.kernel.org/r/1495663199-22234-1-git-send-email-logang@deltatee.com Signed-off-by: Logan Gunthorpe Signed-off-by: Stephen Bates Acked-by: Stefani Seibold Cc: Stefani Seibold Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- samples/kfifo/dma-example.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/samples/kfifo/dma-example.c b/samples/kfifo/dma-example.c index aa243db93f01..be0d4a5fdf53 100644 --- a/samples/kfifo/dma-example.c +++ b/samples/kfifo/dma-example.c @@ -75,8 +75,8 @@ static int __init example_init(void) for (i = 0; i < nents; i++) { printk(KERN_INFO "sg[%d] -> " - "page_link 0x%.8lx offset 0x%.8x length 0x%.8x\n", - i, sg[i].page_link, sg[i].offset, sg[i].length); + "page %p offset 0x%.8x length 0x%.8x\n", + i, sg_page(&sg[i]), sg[i].offset, sg[i].length); if (sg_is_last(&sg[i])) break; @@ -104,8 +104,8 @@ static int __init example_init(void) for (i = 0; i < nents; i++) { printk(KERN_INFO "sg[%d] -> " - "page_link 0x%.8lx offset 0x%.8x length 0x%.8x\n", - i, sg[i].page_link, sg[i].offset, sg[i].length); + "page %p offset 0x%.8x length 0x%.8x\n", + i, sg_page(&sg[i]), sg[i].offset, sg[i].length); if (sg_is_last(&sg[i])) break; -- cgit v1.2.3-59-g8ed1b From 77493f04b74cdff3a61fb3fb14b1f5a71d88fd5f Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Wed, 12 Jul 2017 14:34:25 -0700 Subject: procfs: fdinfo: extend information about epoll target files Since it is possbile to have same number in tfd field (say file added, closed, then nother file dup'ed to same number and added back) it is imposible to distinguish such target files solely by their numbers. Strictly speaking regular applications don't need to recognize these targets at all but for checkpoint/restore sake we need to collect targets to be able to push them back on restore stage in a proper order. Thus lets add file position, inode and device number where this target lays. This three fields can be used as a primary key for sorting, and together with kcmp help CRIU can find out an exact file target (from the whole set of processes being checkpointed). Link: http://lkml.kernel.org/r/20170424154423.436491881@gmail.com Signed-off-by: Cyrill Gorcunov Acked-by: Andrei Vagin Cc: Al Viro Cc: Pavel Emelyanov Cc: Michael Kerrisk Cc: Jason Baron Cc: Andy Lutomirski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/proc.txt | 6 +++++- fs/eventpoll.c | 8 ++++++-- 2 files changed, 11 insertions(+), 3 deletions(-) diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 4cddbce85ac9..adba21b5ada7 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -1786,12 +1786,16 @@ pair provide additional information particular to the objects they represent. pos: 0 flags: 02 mnt_id: 9 - tfd: 5 events: 1d data: ffffffffffffffff + tfd: 5 events: 1d data: ffffffffffffffff pos:0 ino:61af sdev:7 where 'tfd' is a target file descriptor number in decimal form, 'events' is events mask being watched and the 'data' is data associated with a target [see epoll(7) for more details]. + The 'pos' is current offset of the target file in decimal form + [see lseek(2)], 'ino' and 'sdev' are inode and device numbers + where target file resides, all in hex format. + Fsnotify files ~~~~~~~~~~~~~~ For inotify files the format is the following diff --git a/fs/eventpoll.c b/fs/eventpoll.c index a6d194831ed8..322904c3ebdf 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -960,10 +960,14 @@ static void ep_show_fdinfo(struct seq_file *m, struct file *f) mutex_lock(&ep->mtx); for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) { struct epitem *epi = rb_entry(rbp, struct epitem, rbn); + struct inode *inode = file_inode(epi->ffd.file); - seq_printf(m, "tfd: %8d events: %8x data: %16llx\n", + seq_printf(m, "tfd: %8d events: %8x data: %16llx " + " pos:%lli ino:%lx sdev:%x\n", epi->ffd.fd, epi->event.events, - (long long)epi->event.data); + (long long)epi->event.data, + (long long)epi->ffd.file->f_pos, + inode->i_ino, inode->i_sb->s_dev); if (seq_has_overflowed(m)) break; } -- cgit v1.2.3-59-g8ed1b From 0791e3644e5ef21646fe565b9061788d05ec71d4 Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Wed, 12 Jul 2017 14:34:28 -0700 Subject: kcmp: add KCMP_EPOLL_TFD mode to compare epoll target files With current epoll architecture target files are addressed with file_struct and file descriptor number, where the last is not unique. Moreover files can be transferred from another process via unix socket, added into queue and closed then so we won't find this descriptor in the task fdinfo list. Thus to checkpoint and restore such processes CRIU needs to find out where exactly the target file is present to add it into epoll queue. For this sake one can use kcmp call where some particular target file from the queue is compared with arbitrary file passed as an argument. Because epoll target files can have same file descriptor number but different file_struct a caller should explicitly specify the offset within. To test if some particular file is matching entry inside epoll one have to - fill kcmp_epoll_slot structure with epoll file descriptor, target file number and target file offset (in case if only one target is present then it should be 0) - call kcmp as kcmp(pid1, pid2, KCMP_EPOLL_TFD, fd, &kcmp_epoll_slot) - the kernel fetch file pointer matching file descriptor @fd of pid1 - lookups for file struct in epoll queue of pid2 and returns traditional 0,1,2 result for sorting purpose Link: http://lkml.kernel.org/r/20170424154423.511592110@gmail.com Signed-off-by: Cyrill Gorcunov Acked-by: Andrey Vagin Cc: Al Viro Cc: Pavel Emelyanov Cc: Michael Kerrisk Cc: Jason Baron Cc: Andy Lutomirski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/eventpoll.c | 42 ++++++++++++++++++++++++++++++++++ include/linux/eventpoll.h | 3 +++ include/uapi/linux/kcmp.h | 10 +++++++++ kernel/kcmp.c | 57 +++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 112 insertions(+) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 322904c3ebdf..e7e9901c3790 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1077,6 +1077,48 @@ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd) return epir; } +static struct epitem *ep_find_tfd(struct eventpoll *ep, int tfd, unsigned long toff) +{ + struct rb_node *rbp; + struct epitem *epi; + + for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) { + epi = rb_entry(rbp, struct epitem, rbn); + if (epi->ffd.fd == tfd) { + if (toff == 0) + return epi; + else + toff--; + } + cond_resched(); + } + + return NULL; +} + +struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, + unsigned long toff) +{ + struct file *file_raw; + struct eventpoll *ep; + struct epitem *epi; + + if (!is_file_epoll(file)) + return ERR_PTR(-EINVAL); + + ep = file->private_data; + + mutex_lock(&ep->mtx); + epi = ep_find_tfd(ep, tfd, toff); + if (epi) + file_raw = epi->ffd.file; + else + file_raw = ERR_PTR(-ENOENT); + mutex_unlock(&ep->mtx); + + return file_raw; +} + /* * This is the callback that is passed to the wait queue wakeup * mechanism. It is called by the stored file descriptors when they diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index 6daf6d4971f6..d8625d214ea7 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -14,6 +14,7 @@ #define _LINUX_EVENTPOLL_H #include +#include /* Forward declarations to avoid compiler errors */ @@ -22,6 +23,8 @@ struct file; #ifdef CONFIG_EPOLL +struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff); + /* Used to initialize the epoll bits inside the "struct file" */ static inline void eventpoll_init_file(struct file *file) { diff --git a/include/uapi/linux/kcmp.h b/include/uapi/linux/kcmp.h index 84df14b37360..481e103da78e 100644 --- a/include/uapi/linux/kcmp.h +++ b/include/uapi/linux/kcmp.h @@ -1,6 +1,8 @@ #ifndef _UAPI_LINUX_KCMP_H #define _UAPI_LINUX_KCMP_H +#include + /* Comparison type */ enum kcmp_type { KCMP_FILE, @@ -10,8 +12,16 @@ enum kcmp_type { KCMP_SIGHAND, KCMP_IO, KCMP_SYSVSEM, + KCMP_EPOLL_TFD, KCMP_TYPES, }; +/* Slot for KCMP_EPOLL_TFD */ +struct kcmp_epoll_slot { + __u32 efd; /* epoll file descriptor */ + __u32 tfd; /* target file number */ + __u32 toff; /* target offset within same numbered sequence */ +}; + #endif /* _UAPI_LINUX_KCMP_H */ diff --git a/kernel/kcmp.c b/kernel/kcmp.c index 3a47fa998fe0..ea34ed8bb952 100644 --- a/kernel/kcmp.c +++ b/kernel/kcmp.c @@ -11,6 +11,10 @@ #include #include #include +#include +#include +#include +#include #include @@ -94,6 +98,56 @@ static int kcmp_lock(struct mutex *m1, struct mutex *m2) return err; } +#ifdef CONFIG_EPOLL +static int kcmp_epoll_target(struct task_struct *task1, + struct task_struct *task2, + unsigned long idx1, + struct kcmp_epoll_slot __user *uslot) +{ + struct file *filp, *filp_epoll, *filp_tgt; + struct kcmp_epoll_slot slot; + struct files_struct *files; + + if (copy_from_user(&slot, uslot, sizeof(slot))) + return -EFAULT; + + filp = get_file_raw_ptr(task1, idx1); + if (!filp) + return -EBADF; + + files = get_files_struct(task2); + if (!files) + return -EBADF; + + spin_lock(&files->file_lock); + filp_epoll = fcheck_files(files, slot.efd); + if (filp_epoll) + get_file(filp_epoll); + else + filp_tgt = ERR_PTR(-EBADF); + spin_unlock(&files->file_lock); + put_files_struct(files); + + if (filp_epoll) { + filp_tgt = get_epoll_tfile_raw_ptr(filp_epoll, slot.tfd, slot.toff); + fput(filp_epoll); + } else + + if (IS_ERR(filp_tgt)) + return PTR_ERR(filp_tgt); + + return kcmp_ptr(filp, filp_tgt, KCMP_FILE); +} +#else +static int kcmp_epoll_target(struct task_struct *task1, + struct task_struct *task2, + unsigned long idx1, + struct kcmp_epoll_slot __user *uslot) +{ + return -EOPNOTSUPP; +} +#endif + SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type, unsigned long, idx1, unsigned long, idx2) { @@ -165,6 +219,9 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type, ret = -EOPNOTSUPP; #endif break; + case KCMP_EPOLL_TFD: + ret = kcmp_epoll_target(task1, task2, idx1, (void *)idx2); + break; default: ret = -EINVAL; break; -- cgit v1.2.3-59-g8ed1b From 92ef6da3d06ff551a86de41ae37df9cc4b58d7a0 Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Wed, 12 Jul 2017 14:34:31 -0700 Subject: kcmp: fs/epoll: wrap kcmp code with CONFIG_CHECKPOINT_RESTORE kcmp syscall is build iif CONFIG_CHECKPOINT_RESTORE is selected, so wrap appropriate helpers in epoll code with the config to build it conditionally. Link: http://lkml.kernel.org/r/20170513083456.GG1881@uranus.lan Signed-off-by: Cyrill Gorcunov Reported-by: Andrew Morton Cc: Andrey Vagin Cc: Al Viro Cc: Pavel Emelyanov Cc: Michael Kerrisk Cc: Jason Baron Cc: Andy Lutomirski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/eventpoll.c | 2 ++ include/linux/eventpoll.h | 2 ++ 2 files changed, 4 insertions(+) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index e7e9901c3790..e767e4389cb1 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1077,6 +1077,7 @@ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd) return epir; } +#ifdef CONFIG_CHECKPOINT_RESTORE static struct epitem *ep_find_tfd(struct eventpoll *ep, int tfd, unsigned long toff) { struct rb_node *rbp; @@ -1118,6 +1119,7 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, return file_raw; } +#endif /* CONFIG_CHECKPOINT_RESTORE */ /* * This is the callback that is passed to the wait queue wakeup diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index d8625d214ea7..2f14ac73d01d 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -23,7 +23,9 @@ struct file; #ifdef CONFIG_EPOLL +#ifdef CONFIG_CHECKPOINT_RESTORE struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff); +#endif /* Used to initialize the epoll bits inside the "struct file" */ static inline void eventpoll_init_file(struct file *file) -- cgit v1.2.3-59-g8ed1b From e41d58185f1444368873d4d7422f7664a68be61d Mon Sep 17 00:00:00 2001 From: Dmitry Vyukov Date: Wed, 12 Jul 2017 14:34:35 -0700 Subject: fault-inject: support systematic fault injection Add /proc/self/task//fail-nth file that allows failing 0-th, 1-st, 2-nd and so on calls systematically. Excerpt from the added documentation: "Write to this file of integer N makes N-th call in the current task fail (N is 0-based). Read from this file returns a single char 'Y' or 'N' that says if the fault setup with a previous write to this file was injected or not, and disables the fault if it wasn't yet injected. Note that this file enables all types of faults (slab, futex, etc). This setting takes precedence over all other generic settings like probability, interval, times, etc. But per-capability settings (e.g. fail_futex/ignore-private) take precedence over it. This feature is intended for systematic testing of faults in a single system call. See an example below" Why add a new setting: 1. Existing settings are global rather than per-task. So parallel testing is not possible. 2. attr->interval is close but it depends on attr->count which is non reset to 0, so interval does not work as expected. 3. Trying to model this with existing settings requires manipulations of all of probability, interval, times, space, task-filter and unexposed count and per-task make-it-fail files. 4. Existing settings are per-failure-type, and the set of failure types is potentially expanding. 5. make-it-fail can't be changed by unprivileged user and aggressive stress testing better be done from an unprivileged user. Similarly, this would require opening the debugfs files to the unprivileged user, as he would need to reopen at least times file (not possible to pre-open before dropping privs). The proposed interface solves all of the above (see the example). We want to integrate this into syzkaller fuzzer. A prototype has found 10 bugs in kernel in first day of usage: https://groups.google.com/forum/#!searchin/syzkaller/%22FAULT_INJECTION%22%7Csort:relevance I've made the current interface work with all types of our sandboxes. For setuid the secret sauce was prctl(PR_SET_DUMPABLE, 1, 0, 0, 0) to make /proc entries non-root owned. So I am fine with the current version of the code. [akpm@linux-foundation.org: fix build] Link: http://lkml.kernel.org/r/20170328130128.101773-1-dvyukov@google.com Signed-off-by: Dmitry Vyukov Cc: Akinobu Mita Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/fault-injection/fault-injection.txt | 78 +++++++++++++++++++++++ fs/proc/base.c | 52 +++++++++++++++ include/linux/sched.h | 1 + kernel/fork.c | 4 ++ lib/fault-inject.c | 7 ++ 5 files changed, 142 insertions(+) diff --git a/Documentation/fault-injection/fault-injection.txt b/Documentation/fault-injection/fault-injection.txt index 415484f3d59a..192d8cbcc5f9 100644 --- a/Documentation/fault-injection/fault-injection.txt +++ b/Documentation/fault-injection/fault-injection.txt @@ -134,6 +134,22 @@ use the boot option: fail_futex= mmc_core.fail_request=,,, +o proc entries + +- /proc/self/task//fail-nth: + + Write to this file of integer N makes N-th call in the current task fail + (N is 0-based). Read from this file returns a single char 'Y' or 'N' + that says if the fault setup with a previous write to this file was + injected or not, and disables the fault if it wasn't yet injected. + Note that this file enables all types of faults (slab, futex, etc). + This setting takes precedence over all other generic debugfs settings + like probability, interval, times, etc. But per-capability settings + (e.g. fail_futex/ignore-private) take precedence over it. + + This feature is intended for systematic testing of faults in a single + system call. See an example below. + How to add new fault injection capability ----------------------------------------- @@ -278,3 +294,65 @@ allocation failure. # env FAILCMD_TYPE=fail_page_alloc \ ./tools/testing/fault-injection/failcmd.sh --times=100 \ -- make -C tools/testing/selftests/ run_tests + +Systematic faults using fail-nth +--------------------------------- + +The following code systematically faults 0-th, 1-st, 2-nd and so on +capabilities in the socketpair() system call. + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +int main() +{ + int i, err, res, fail_nth, fds[2]; + char buf[128]; + + system("echo N > /sys/kernel/debug/failslab/ignore-gfp-wait"); + sprintf(buf, "/proc/self/task/%ld/fail-nth", syscall(SYS_gettid)); + fail_nth = open(buf, O_RDWR); + for (i = 0;; i++) { + sprintf(buf, "%d", i); + write(fail_nth, buf, strlen(buf)); + res = socketpair(AF_LOCAL, SOCK_STREAM, 0, fds); + err = errno; + read(fail_nth, buf, 1); + if (res == 0) { + close(fds[0]); + close(fds[1]); + } + printf("%d-th fault %c: res=%d/%d\n", i, buf[0], res, err); + if (buf[0] != 'Y') + break; + } + return 0; +} + +An example output: + +0-th fault Y: res=-1/23 +1-th fault Y: res=-1/23 +2-th fault Y: res=-1/23 +3-th fault Y: res=-1/12 +4-th fault Y: res=-1/12 +5-th fault Y: res=-1/23 +6-th fault Y: res=-1/23 +7-th fault Y: res=-1/23 +8-th fault Y: res=-1/12 +9-th fault Y: res=-1/12 +10-th fault Y: res=-1/12 +11-th fault Y: res=-1/12 +12-th fault Y: res=-1/12 +13-th fault Y: res=-1/12 +14-th fault Y: res=-1/12 +15-th fault Y: res=-1/12 +16-th fault N: res=0/12 diff --git a/fs/proc/base.c b/fs/proc/base.c index f1e1927ccd48..88b773f318cd 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1355,6 +1355,53 @@ static const struct file_operations proc_fault_inject_operations = { .write = proc_fault_inject_write, .llseek = generic_file_llseek, }; + +static ssize_t proc_fail_nth_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task; + int err, n; + + task = get_proc_task(file_inode(file)); + if (!task) + return -ESRCH; + put_task_struct(task); + if (task != current) + return -EPERM; + err = kstrtoint_from_user(buf, count, 10, &n); + if (err) + return err; + if (n < 0 || n == INT_MAX) + return -EINVAL; + current->fail_nth = n + 1; + return count; +} + +static ssize_t proc_fail_nth_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task; + int err; + + task = get_proc_task(file_inode(file)); + if (!task) + return -ESRCH; + put_task_struct(task); + if (task != current) + return -EPERM; + if (count < 1) + return -EINVAL; + err = put_user((char)(current->fail_nth ? 'N' : 'Y'), buf); + if (err) + return err; + current->fail_nth = 0; + return 1; +} + +static const struct file_operations proc_fail_nth_operations = { + .read = proc_fail_nth_read, + .write = proc_fail_nth_write, +}; #endif @@ -3311,6 +3358,11 @@ static const struct pid_entry tid_base_stuff[] = { #endif #ifdef CONFIG_FAULT_INJECTION REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), + /* + * Operations on the file check that the task is current, + * so we create it with 0666 to support testing under unprivileged user. + */ + REG("fail-nth", 0666, proc_fail_nth_operations), #endif #ifdef CONFIG_TASK_IO_ACCOUNTING ONE("io", S_IRUSR, proc_tid_io_accounting), diff --git a/include/linux/sched.h b/include/linux/sched.h index 20814b7d7d70..3822d749fc9e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -974,6 +974,7 @@ struct task_struct { #ifdef CONFIG_FAULT_INJECTION int make_it_fail; + int fail_nth; #endif /* * When (nr_dirtied >= nr_dirtied_pause), it's time to call diff --git a/kernel/fork.c b/kernel/fork.c index d2b9d7c31eaf..ade237a96308 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -573,6 +573,10 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) kcov_task_init(tsk); +#ifdef CONFIG_FAULT_INJECTION + tsk->fail_nth = 0; +#endif + return tsk; free_stack: diff --git a/lib/fault-inject.c b/lib/fault-inject.c index 4ff157159a0d..09ac73c177fd 100644 --- a/lib/fault-inject.c +++ b/lib/fault-inject.c @@ -107,6 +107,12 @@ static inline bool fail_stacktrace(struct fault_attr *attr) bool should_fail(struct fault_attr *attr, ssize_t size) { + if (in_task() && current->fail_nth) { + if (--current->fail_nth == 0) + goto fail; + return false; + } + /* No need to check any other properties if the probability is 0 */ if (attr->probability == 0) return false; @@ -134,6 +140,7 @@ bool should_fail(struct fault_attr *attr, ssize_t size) if (!fail_stacktrace(attr)) return false; +fail: fail_dump(attr); if (atomic_read(&attr->times) != -1) -- cgit v1.2.3-59-g8ed1b From 1a23395672658969a4035dcc518ea6cab835c579 Mon Sep 17 00:00:00 2001 From: Manfred Spraul Date: Wed, 12 Jul 2017 14:34:38 -0700 Subject: ipc/sem.c: remove sem_base, embed struct sem sma->sem_base is initialized with sma->sem_base = (struct sem *) &sma[1]; The current code has four problems: - There is an unnecessary pointer dereference - sem_base is not needed. - Alignment for struct sem only works by chance. - The current code causes false positive for static code analysis. - This is a cast between different non-void types, which the future randstruct GCC plugin warns on. And, as bonus, the code size gets smaller: Before: 0 .text 00003770 After: 0 .text 0000374e [manfred@colorfullife.com: s/[0]/[]/, per hch] Link: http://lkml.kernel.org/r/20170525185107.12869-2-manfred@colorfullife.com Link: http://lkml.kernel.org/r/20170515171912.6298-2-manfred@colorfullife.com Signed-off-by: Manfred Spraul Acked-by: Kees Cook Cc: Kees Cook Cc: <1vier1@web.de> Cc: Davidlohr Bueso Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Fabian Frederick Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sem.h | 22 +++++++++++++- ipc/sem.c | 88 +++++++++++++++++++++-------------------------------- 2 files changed, 55 insertions(+), 55 deletions(-) diff --git a/include/linux/sem.h b/include/linux/sem.h index 9edec926e9d9..9db14093b73c 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -8,11 +8,29 @@ struct task_struct; +/* One semaphore structure for each semaphore in the system. */ +struct sem { + int semval; /* current value */ + /* + * PID of the process that last modified the semaphore. For + * Linux, specifically these are: + * - semop + * - semctl, via SETVAL and SETALL. + * - at task exit when performing undo adjustments (see exit_sem). + */ + int sempid; + spinlock_t lock; /* spinlock for fine-grained semtimedop */ + struct list_head pending_alter; /* pending single-sop operations */ + /* that alter the semaphore */ + struct list_head pending_const; /* pending single-sop operations */ + /* that do not alter the semaphore*/ + time_t sem_otime; /* candidate for sem_otime */ +} ____cacheline_aligned_in_smp; + /* One sem_array data structure for each set of semaphores in the system. */ struct sem_array { struct kern_ipc_perm sem_perm; /* permissions .. see ipc.h */ time_t sem_ctime; /* last change time */ - struct sem *sem_base; /* ptr to first semaphore in array */ struct list_head pending_alter; /* pending operations */ /* that alter the array */ struct list_head pending_const; /* pending complex operations */ @@ -21,6 +39,8 @@ struct sem_array { int sem_nsems; /* no. of semaphores in array */ int complex_count; /* pending complex operations */ unsigned int use_global_lock;/* >0: global lock required */ + + struct sem sems[]; }; #ifdef CONFIG_SYSVIPC diff --git a/ipc/sem.c b/ipc/sem.c index 947dc2348271..fff8337ebab3 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -87,24 +87,6 @@ #include #include "util.h" -/* One semaphore structure for each semaphore in the system. */ -struct sem { - int semval; /* current value */ - /* - * PID of the process that last modified the semaphore. For - * Linux, specifically these are: - * - semop - * - semctl, via SETVAL and SETALL. - * - at task exit when performing undo adjustments (see exit_sem). - */ - int sempid; - spinlock_t lock; /* spinlock for fine-grained semtimedop */ - struct list_head pending_alter; /* pending single-sop operations */ - /* that alter the semaphore */ - struct list_head pending_const; /* pending single-sop operations */ - /* that do not alter the semaphore*/ - time_t sem_otime; /* candidate for sem_otime */ -} ____cacheline_aligned_in_smp; /* One queue for each sleeping process in the system. */ struct sem_queue { @@ -175,7 +157,7 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it); * sem_array.sem_undo * * b) global or semaphore sem_lock() for read/write: - * sem_array.sem_base[i].pending_{const,alter}: + * sem_array.sems[i].pending_{const,alter}: * * c) special: * sem_undo_list.list_proc: @@ -250,7 +232,7 @@ static void unmerge_queues(struct sem_array *sma) */ list_for_each_entry_safe(q, tq, &sma->pending_alter, list) { struct sem *curr; - curr = &sma->sem_base[q->sops[0].sem_num]; + curr = &sma->sems[q->sops[0].sem_num]; list_add_tail(&q->list, &curr->pending_alter); } @@ -270,7 +252,7 @@ static void merge_queues(struct sem_array *sma) { int i; for (i = 0; i < sma->sem_nsems; i++) { - struct sem *sem = sma->sem_base + i; + struct sem *sem = &sma->sems[i]; list_splice_init(&sem->pending_alter, &sma->pending_alter); } @@ -306,7 +288,7 @@ static void complexmode_enter(struct sem_array *sma) sma->use_global_lock = USE_GLOBAL_LOCK_HYSTERESIS; for (i = 0; i < sma->sem_nsems; i++) { - sem = sma->sem_base + i; + sem = &sma->sems[i]; spin_lock(&sem->lock); spin_unlock(&sem->lock); } @@ -366,7 +348,7 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops, * * Both facts are tracked by use_global_mode. */ - sem = sma->sem_base + sops->sem_num; + sem = &sma->sems[sops->sem_num]; /* * Initial check for use_global_lock. Just an optimization, @@ -421,7 +403,7 @@ static inline void sem_unlock(struct sem_array *sma, int locknum) complexmode_tryleave(sma); ipc_unlock_object(&sma->sem_perm); } else { - struct sem *sem = sma->sem_base + locknum; + struct sem *sem = &sma->sems[locknum]; spin_unlock(&sem->lock); } } @@ -487,7 +469,7 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params) if (ns->used_sems + nsems > ns->sc_semmns) return -ENOSPC; - size = sizeof(*sma) + nsems * sizeof(struct sem); + size = sizeof(*sma) + nsems * sizeof(sma->sems[0]); sma = ipc_rcu_alloc(size); if (!sma) return -ENOMEM; @@ -504,12 +486,10 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params) return retval; } - sma->sem_base = (struct sem *) &sma[1]; - for (i = 0; i < nsems; i++) { - INIT_LIST_HEAD(&sma->sem_base[i].pending_alter); - INIT_LIST_HEAD(&sma->sem_base[i].pending_const); - spin_lock_init(&sma->sem_base[i].lock); + INIT_LIST_HEAD(&sma->sems[i].pending_alter); + INIT_LIST_HEAD(&sma->sems[i].pending_const); + spin_lock_init(&sma->sems[i].lock); } sma->complex_count = 0; @@ -612,7 +592,7 @@ static int perform_atomic_semop_slow(struct sem_array *sma, struct sem_queue *q) un = q->undo; for (sop = sops; sop < sops + nsops; sop++) { - curr = sma->sem_base + sop->sem_num; + curr = &sma->sems[sop->sem_num]; sem_op = sop->sem_op; result = curr->semval; @@ -639,7 +619,7 @@ static int perform_atomic_semop_slow(struct sem_array *sma, struct sem_queue *q) sop--; pid = q->pid; while (sop >= sops) { - sma->sem_base[sop->sem_num].sempid = pid; + sma->sems[sop->sem_num].sempid = pid; sop--; } @@ -661,7 +641,7 @@ undo: sop--; while (sop >= sops) { sem_op = sop->sem_op; - sma->sem_base[sop->sem_num].semval -= sem_op; + sma->sems[sop->sem_num].semval -= sem_op; if (sop->sem_flg & SEM_UNDO) un->semadj[sop->sem_num] += sem_op; sop--; @@ -692,7 +672,7 @@ static int perform_atomic_semop(struct sem_array *sma, struct sem_queue *q) * until the operations can go through. */ for (sop = sops; sop < sops + nsops; sop++) { - curr = sma->sem_base + sop->sem_num; + curr = &sma->sems[sop->sem_num]; sem_op = sop->sem_op; result = curr->semval; @@ -716,7 +696,7 @@ static int perform_atomic_semop(struct sem_array *sma, struct sem_queue *q) } for (sop = sops; sop < sops + nsops; sop++) { - curr = sma->sem_base + sop->sem_num; + curr = &sma->sems[sop->sem_num]; sem_op = sop->sem_op; result = curr->semval; @@ -815,7 +795,7 @@ static int wake_const_ops(struct sem_array *sma, int semnum, if (semnum == -1) pending_list = &sma->pending_const; else - pending_list = &sma->sem_base[semnum].pending_const; + pending_list = &sma->sems[semnum].pending_const; list_for_each_entry_safe(q, tmp, pending_list, list) { int error = perform_atomic_semop(sma, q); @@ -856,7 +836,7 @@ static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops, for (i = 0; i < nsops; i++) { int num = sops[i].sem_num; - if (sma->sem_base[num].semval == 0) { + if (sma->sems[num].semval == 0) { got_zero = 1; semop_completed |= wake_const_ops(sma, num, wake_q); } @@ -867,7 +847,7 @@ static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops, * Assume all were changed. */ for (i = 0; i < sma->sem_nsems; i++) { - if (sma->sem_base[i].semval == 0) { + if (sma->sems[i].semval == 0) { got_zero = 1; semop_completed |= wake_const_ops(sma, i, wake_q); } @@ -909,7 +889,7 @@ static int update_queue(struct sem_array *sma, int semnum, struct wake_q_head *w if (semnum == -1) pending_list = &sma->pending_alter; else - pending_list = &sma->sem_base[semnum].pending_alter; + pending_list = &sma->sems[semnum].pending_alter; again: list_for_each_entry_safe(q, tmp, pending_list, list) { @@ -922,7 +902,7 @@ again: * be in the per semaphore pending queue, and decrements * cannot be successful if the value is already 0. */ - if (semnum != -1 && sma->sem_base[semnum].semval == 0) + if (semnum != -1 && sma->sems[semnum].semval == 0) break; error = perform_atomic_semop(sma, q); @@ -959,9 +939,9 @@ again: static void set_semotime(struct sem_array *sma, struct sembuf *sops) { if (sops == NULL) { - sma->sem_base[0].sem_otime = get_seconds(); + sma->sems[0].sem_otime = get_seconds(); } else { - sma->sem_base[sops[0].sem_num].sem_otime = + sma->sems[sops[0].sem_num].sem_otime = get_seconds(); } } @@ -1067,9 +1047,9 @@ static int count_semcnt(struct sem_array *sma, ushort semnum, semcnt = 0; /* First: check the simple operations. They are easy to evaluate */ if (count_zero) - l = &sma->sem_base[semnum].pending_const; + l = &sma->sems[semnum].pending_const; else - l = &sma->sem_base[semnum].pending_alter; + l = &sma->sems[semnum].pending_alter; list_for_each_entry(q, l, list) { /* all task on a per-semaphore list sleep on exactly @@ -1124,7 +1104,7 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) wake_up_sem_queue_prepare(q, -EIDRM, &wake_q); } for (i = 0; i < sma->sem_nsems; i++) { - struct sem *sem = sma->sem_base + i; + struct sem *sem = &sma->sems[i]; list_for_each_entry_safe(q, tq, &sem->pending_const, list) { unlink_queue(sma, q); wake_up_sem_queue_prepare(q, -EIDRM, &wake_q); @@ -1174,9 +1154,9 @@ static time_t get_semotime(struct sem_array *sma) int i; time_t res; - res = sma->sem_base[0].sem_otime; + res = sma->sems[0].sem_otime; for (i = 1; i < sma->sem_nsems; i++) { - time_t to = sma->sem_base[i].sem_otime; + time_t to = sma->sems[i].sem_otime; if (to > res) res = to; @@ -1325,7 +1305,7 @@ static int semctl_setval(struct ipc_namespace *ns, int semid, int semnum, return -EIDRM; } - curr = &sma->sem_base[semnum]; + curr = &sma->sems[semnum]; ipc_assert_locked_object(&sma->sem_perm); list_for_each_entry(un, &sma->list_id, list_id) @@ -1402,7 +1382,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, } } for (i = 0; i < sma->sem_nsems; i++) - sem_io[i] = sma->sem_base[i].semval; + sem_io[i] = sma->sems[i].semval; sem_unlock(sma, -1); rcu_read_unlock(); err = 0; @@ -1450,8 +1430,8 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, } for (i = 0; i < nsems; i++) { - sma->sem_base[i].semval = sem_io[i]; - sma->sem_base[i].sempid = task_tgid_vnr(current); + sma->sems[i].semval = sem_io[i]; + sma->sems[i].sempid = task_tgid_vnr(current); } ipc_assert_locked_object(&sma->sem_perm); @@ -1476,7 +1456,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, err = -EIDRM; goto out_unlock; } - curr = &sma->sem_base[semnum]; + curr = &sma->sems[semnum]; switch (cmd) { case GETVAL: @@ -1932,7 +1912,7 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops, */ if (nsops == 1) { struct sem *curr; - curr = &sma->sem_base[sops->sem_num]; + curr = &sma->sems[sops->sem_num]; if (alter) { if (sma->complex_count) { @@ -2146,7 +2126,7 @@ void exit_sem(struct task_struct *tsk) /* perform adjustments registered in un */ for (i = 0; i < sma->sem_nsems; i++) { - struct sem *semaphore = &sma->sem_base[i]; + struct sem *semaphore = &sma->sems[i]; if (un->semadj[i]) { semaphore->semval += un->semadj[i]; /* -- cgit v1.2.3-59-g8ed1b From dba4cdd39e698d8dcdad0656825423052ac90ccd Mon Sep 17 00:00:00 2001 From: Manfred Spraul Date: Wed, 12 Jul 2017 14:34:41 -0700 Subject: ipc: merge ipc_rcu and kern_ipc_perm ipc has two management structures that exist for every id: - struct kern_ipc_perm, it contains e.g. the permissions. - struct ipc_rcu, it contains the rcu head for rcu handling and the refcount. The patch merges both structures. As a bonus, we may save one cacheline, because both structures are cacheline aligned. In addition, it reduces the number of casts, instead most codepaths can use container_of. To simplify code, the ipc_rcu_alloc initializes the allocation to 0. [manfred@colorfullife.com: really include the memset() into ipc_alloc_rcu()] Link: http://lkml.kernel.org/r/564f8612-0601-b267-514f-a9f650ec9b32@colorfullife.com Link: http://lkml.kernel.org/r/20170525185107.12869-3-manfred@colorfullife.com Signed-off-by: Manfred Spraul Cc: Davidlohr Bueso Cc: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipc.h | 3 +++ ipc/msg.c | 19 +++++++++++-------- ipc/sem.c | 34 +++++++++++++++++----------------- ipc/shm.c | 18 +++++++++++------- ipc/util.c | 35 +++++++++++++++++------------------ ipc/util.h | 18 +++++++----------- 6 files changed, 66 insertions(+), 61 deletions(-) diff --git a/include/linux/ipc.h b/include/linux/ipc.h index 71fd92d81b26..5591f055e13f 100644 --- a/include/linux/ipc.h +++ b/include/linux/ipc.h @@ -20,6 +20,9 @@ struct kern_ipc_perm { umode_t mode; unsigned long seq; void *security; + + struct rcu_head rcu; + atomic_t refcount; } ____cacheline_aligned_in_smp; #endif /* _LINUX_IPC_H */ diff --git a/ipc/msg.c b/ipc/msg.c index 104926dc72be..0ed7dae7d4e8 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -97,8 +97,8 @@ static inline void msg_rmid(struct ipc_namespace *ns, struct msg_queue *s) static void msg_rcu_free(struct rcu_head *head) { - struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu); - struct msg_queue *msq = ipc_rcu_to_struct(p); + struct kern_ipc_perm *p = container_of(head, struct kern_ipc_perm, rcu); + struct msg_queue *msq = container_of(p, struct msg_queue, q_perm); security_msg_queue_free(msq); ipc_rcu_free(head); @@ -118,7 +118,10 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params) key_t key = params->key; int msgflg = params->flg; - msq = ipc_rcu_alloc(sizeof(*msq)); + BUILD_BUG_ON(offsetof(struct msg_queue, q_perm) != 0); + + msq = container_of(ipc_rcu_alloc(sizeof(*msq)), struct msg_queue, + q_perm); if (!msq) return -ENOMEM; @@ -128,7 +131,7 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params) msq->q_perm.security = NULL; retval = security_msg_queue_alloc(msq); if (retval) { - ipc_rcu_putref(msq, ipc_rcu_free); + ipc_rcu_putref(&msq->q_perm, ipc_rcu_free); return retval; } @@ -144,7 +147,7 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params) /* ipc_addid() locks msq upon success. */ id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni); if (id < 0) { - ipc_rcu_putref(msq, msg_rcu_free); + ipc_rcu_putref(&msq->q_perm, msg_rcu_free); return id; } @@ -249,7 +252,7 @@ static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) free_msg(msg); } atomic_sub(msq->q_cbytes, &ns->msg_bytes); - ipc_rcu_putref(msq, msg_rcu_free); + ipc_rcu_putref(&msq->q_perm, msg_rcu_free); } /* @@ -688,7 +691,7 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext, /* enqueue the sender and prepare to block */ ss_add(msq, &s, msgsz); - if (!ipc_rcu_getref(msq)) { + if (!ipc_rcu_getref(&msq->q_perm)) { err = -EIDRM; goto out_unlock0; } @@ -700,7 +703,7 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext, rcu_read_lock(); ipc_lock_object(&msq->q_perm); - ipc_rcu_putref(msq, msg_rcu_free); + ipc_rcu_putref(&msq->q_perm, msg_rcu_free); /* raced with RMID? */ if (!ipc_valid_object(&msq->q_perm)) { err = -EIDRM; diff --git a/ipc/sem.c b/ipc/sem.c index fff8337ebab3..bdff6d93d2c7 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -260,8 +260,8 @@ static void merge_queues(struct sem_array *sma) static void sem_rcu_free(struct rcu_head *head) { - struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu); - struct sem_array *sma = ipc_rcu_to_struct(p); + struct kern_ipc_perm *p = container_of(head, struct kern_ipc_perm, rcu); + struct sem_array *sma = container_of(p, struct sem_array, sem_perm); security_sem_free(sma); ipc_rcu_free(head); @@ -438,7 +438,7 @@ static inline struct sem_array *sem_obtain_object_check(struct ipc_namespace *ns static inline void sem_lock_and_putref(struct sem_array *sma) { sem_lock(sma, NULL, -1); - ipc_rcu_putref(sma, sem_rcu_free); + ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); } static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s) @@ -469,20 +469,20 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params) if (ns->used_sems + nsems > ns->sc_semmns) return -ENOSPC; + BUILD_BUG_ON(offsetof(struct sem_array, sem_perm) != 0); + size = sizeof(*sma) + nsems * sizeof(sma->sems[0]); - sma = ipc_rcu_alloc(size); + sma = container_of(ipc_rcu_alloc(size), struct sem_array, sem_perm); if (!sma) return -ENOMEM; - memset(sma, 0, size); - sma->sem_perm.mode = (semflg & S_IRWXUGO); sma->sem_perm.key = key; sma->sem_perm.security = NULL; retval = security_sem_alloc(sma); if (retval) { - ipc_rcu_putref(sma, ipc_rcu_free); + ipc_rcu_putref(&sma->sem_perm, ipc_rcu_free); return retval; } @@ -502,7 +502,7 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params) id = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni); if (id < 0) { - ipc_rcu_putref(sma, sem_rcu_free); + ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); return id; } ns->used_sems += nsems; @@ -1122,7 +1122,7 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) wake_up_q(&wake_q); ns->used_sems -= sma->sem_nsems; - ipc_rcu_putref(sma, sem_rcu_free); + ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); } static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in, int version) @@ -1362,7 +1362,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, goto out_unlock; } if (nsems > SEMMSL_FAST) { - if (!ipc_rcu_getref(sma)) { + if (!ipc_rcu_getref(&sma->sem_perm)) { err = -EIDRM; goto out_unlock; } @@ -1370,7 +1370,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, rcu_read_unlock(); sem_io = ipc_alloc(sizeof(ushort)*nsems); if (sem_io == NULL) { - ipc_rcu_putref(sma, sem_rcu_free); + ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); return -ENOMEM; } @@ -1395,7 +1395,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, int i; struct sem_undo *un; - if (!ipc_rcu_getref(sma)) { + if (!ipc_rcu_getref(&sma->sem_perm)) { err = -EIDRM; goto out_rcu_wakeup; } @@ -1404,20 +1404,20 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, if (nsems > SEMMSL_FAST) { sem_io = ipc_alloc(sizeof(ushort)*nsems); if (sem_io == NULL) { - ipc_rcu_putref(sma, sem_rcu_free); + ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); return -ENOMEM; } } if (copy_from_user(sem_io, p, nsems*sizeof(ushort))) { - ipc_rcu_putref(sma, sem_rcu_free); + ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); err = -EFAULT; goto out_free; } for (i = 0; i < nsems; i++) { if (sem_io[i] > SEMVMX) { - ipc_rcu_putref(sma, sem_rcu_free); + ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); err = -ERANGE; goto out_free; } @@ -1699,7 +1699,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid) } nsems = sma->sem_nsems; - if (!ipc_rcu_getref(sma)) { + if (!ipc_rcu_getref(&sma->sem_perm)) { rcu_read_unlock(); un = ERR_PTR(-EIDRM); goto out; @@ -1709,7 +1709,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid) /* step 2: allocate new undo structure */ new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL); if (!new) { - ipc_rcu_putref(sma, sem_rcu_free); + ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); return ERR_PTR(-ENOMEM); } diff --git a/ipc/shm.c b/ipc/shm.c index f45c7959b264..5ef6d31a52c5 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -174,9 +174,10 @@ static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp) static void shm_rcu_free(struct rcu_head *head) { - struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu); - struct shmid_kernel *shp = ipc_rcu_to_struct(p); - + struct kern_ipc_perm *ptr = container_of(head, struct kern_ipc_perm, + rcu); + struct shmid_kernel *shp = container_of(ptr, struct shmid_kernel, + shm_perm); security_shm_free(shp); ipc_rcu_free(head); } @@ -241,7 +242,7 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) user_shm_unlock(i_size_read(file_inode(shm_file)), shp->mlock_user); fput(shm_file); - ipc_rcu_putref(shp, shm_rcu_free); + ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); } /* @@ -542,7 +543,10 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) ns->shm_tot + numpages > ns->shm_ctlall) return -ENOSPC; - shp = ipc_rcu_alloc(sizeof(*shp)); + BUILD_BUG_ON(offsetof(struct shmid_kernel, shm_perm) != 0); + + shp = container_of(ipc_rcu_alloc(sizeof(*shp)), struct shmid_kernel, + shm_perm); if (!shp) return -ENOMEM; @@ -553,7 +557,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) shp->shm_perm.security = NULL; error = security_shm_alloc(shp); if (error) { - ipc_rcu_putref(shp, ipc_rcu_free); + ipc_rcu_putref(&shp->shm_perm, ipc_rcu_free); return error; } @@ -624,7 +628,7 @@ no_id: user_shm_unlock(size, shp->mlock_user); fput(file); no_file: - ipc_rcu_putref(shp, shm_rcu_free); + ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); return error; } diff --git a/ipc/util.c b/ipc/util.c index caec7b1bfaa3..5d1ff1035efe 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -418,46 +418,45 @@ void ipc_free(void *ptr) } /** - * ipc_rcu_alloc - allocate ipc and rcu space + * ipc_rcu_alloc - allocate ipc space * @size: size desired * - * Allocate memory for the rcu header structure + the object. - * Returns the pointer to the object or NULL upon failure. + * Allocate memory for an ipc object. + * The first member must be struct kern_ipc_perm. */ -void *ipc_rcu_alloc(int size) +struct kern_ipc_perm *ipc_rcu_alloc(int size) { /* * We prepend the allocation with the rcu struct */ - struct ipc_rcu *out = ipc_alloc(sizeof(struct ipc_rcu) + size); + struct kern_ipc_perm *out = ipc_alloc(size); if (unlikely(!out)) return NULL; + + memset(out, 0, size); atomic_set(&out->refcount, 1); - return out + 1; + return out; } -int ipc_rcu_getref(void *ptr) +int ipc_rcu_getref(struct kern_ipc_perm *ptr) { - struct ipc_rcu *p = ((struct ipc_rcu *)ptr) - 1; - - return atomic_inc_not_zero(&p->refcount); + return atomic_inc_not_zero(&ptr->refcount); } -void ipc_rcu_putref(void *ptr, void (*func)(struct rcu_head *head)) +void ipc_rcu_putref(struct kern_ipc_perm *ptr, + void (*func)(struct rcu_head *head)) { - struct ipc_rcu *p = ((struct ipc_rcu *)ptr) - 1; - - if (!atomic_dec_and_test(&p->refcount)) + if (!atomic_dec_and_test(&ptr->refcount)) return; - call_rcu(&p->rcu, func); + call_rcu(&ptr->rcu, func); } -void ipc_rcu_free(struct rcu_head *head) +void ipc_rcu_free(struct rcu_head *h) { - struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu); + struct kern_ipc_perm *ptr = container_of(h, struct kern_ipc_perm, rcu); - kvfree(p); + kvfree(ptr); } /** diff --git a/ipc/util.h b/ipc/util.h index 60ddccca464d..09d0f918c3e2 100644 --- a/ipc/util.h +++ b/ipc/util.h @@ -47,13 +47,6 @@ static inline void msg_exit_ns(struct ipc_namespace *ns) { } static inline void shm_exit_ns(struct ipc_namespace *ns) { } #endif -struct ipc_rcu { - struct rcu_head rcu; - atomic_t refcount; -} ____cacheline_aligned_in_smp; - -#define ipc_rcu_to_struct(p) ((void *)(p+1)) - /* * Structure that holds the parameters needed by the ipc operations * (see after) @@ -125,11 +118,14 @@ void ipc_free(void *ptr); * Objects are reference counted, they start with reference count 1. * getref increases the refcount, the putref call that reduces the recount * to 0 schedules the rcu destruction. Caller must guarantee locking. + * + * struct kern_ipc_perm must be the first member in the allocated structure. */ -void *ipc_rcu_alloc(int size); -int ipc_rcu_getref(void *ptr); -void ipc_rcu_putref(void *ptr, void (*func)(struct rcu_head *head)); -void ipc_rcu_free(struct rcu_head *head); +struct kern_ipc_perm *ipc_rcu_alloc(int size); +int ipc_rcu_getref(struct kern_ipc_perm *ptr); +void ipc_rcu_putref(struct kern_ipc_perm *ptr, + void (*func)(struct rcu_head *head)); +void ipc_rcu_free(struct rcu_head *h); struct kern_ipc_perm *ipc_lock(struct ipc_ids *, int); struct kern_ipc_perm *ipc_obtain_object_idr(struct ipc_ids *ids, int id); -- cgit v1.2.3-59-g8ed1b From 2cd648c110b5570c3280bd645797658cabbe5f5c Mon Sep 17 00:00:00 2001 From: Manfred Spraul Date: Wed, 12 Jul 2017 14:34:44 -0700 Subject: include/linux/sem.h: correctly document sem_ctime sem_ctime is initialized to the semget() time and then updated at every semctl() that changes the array. Thus it does not represent the time of the last change. Especially, semop() calls are only stored in sem_otime, not in sem_ctime. This is already described in ipc/sem.c, I just overlooked that there is a comment in include/linux/sem.h and man semctl(2) as well. So: Correct wrong comments. Link: http://lkml.kernel.org/r/20170515171912.6298-4-manfred@colorfullife.com Signed-off-by: Manfred Spraul Cc: Kees Cook Cc: <1vier1@web.de> Cc: Davidlohr Bueso Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Fabian Frederick Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sem.h | 2 +- include/uapi/linux/sem.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/sem.h b/include/linux/sem.h index 9db14093b73c..be5cf2ea14ad 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -30,7 +30,7 @@ struct sem { /* One sem_array data structure for each set of semaphores in the system. */ struct sem_array { struct kern_ipc_perm sem_perm; /* permissions .. see ipc.h */ - time_t sem_ctime; /* last change time */ + time_t sem_ctime; /* create/last semctl() time */ struct list_head pending_alter; /* pending operations */ /* that alter the array */ struct list_head pending_const; /* pending complex operations */ diff --git a/include/uapi/linux/sem.h b/include/uapi/linux/sem.h index dd73b908b2f3..67eb90361692 100644 --- a/include/uapi/linux/sem.h +++ b/include/uapi/linux/sem.h @@ -23,7 +23,7 @@ struct semid_ds { struct ipc_perm sem_perm; /* permissions .. see ipc.h */ __kernel_time_t sem_otime; /* last semop time */ - __kernel_time_t sem_ctime; /* last change time */ + __kernel_time_t sem_ctime; /* create/last semctl() time */ struct sem *sem_base; /* ptr to first semaphore in array */ struct sem_queue *sem_pending; /* pending operations to be processed */ struct sem_queue **sem_pending_last; /* last pending operation */ -- cgit v1.2.3-59-g8ed1b From f8dbe8d290637ac3f68600e30d092393fe9b40a5 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Jul 2017 14:34:47 -0700 Subject: ipc: drop non-RCU allocation The only users of ipc_alloc() were ipc_rcu_alloc() and the on-heap sem_io fall-back memory. Better to just open-code these to make things easier to read. [manfred@colorfullife.com: Rediff due to inclusion of memset() into ipc_rcu_alloc()] Link: http://lkml.kernel.org/r/20170525185107.12869-5-manfred@colorfullife.com Signed-off-by: Kees Cook Signed-off-by: Manfred Spraul Cc: Davidlohr Bueso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/sem.c | 8 +++++--- ipc/util.c | 25 +------------------------ ipc/util.h | 6 ------ 3 files changed, 6 insertions(+), 33 deletions(-) diff --git a/ipc/sem.c b/ipc/sem.c index bdff6d93d2c7..484ccf83cf85 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -1368,7 +1368,8 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, } sem_unlock(sma, -1); rcu_read_unlock(); - sem_io = ipc_alloc(sizeof(ushort)*nsems); + sem_io = kvmalloc_array(nsems, sizeof(ushort), + GFP_KERNEL); if (sem_io == NULL) { ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); return -ENOMEM; @@ -1402,7 +1403,8 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, rcu_read_unlock(); if (nsems > SEMMSL_FAST) { - sem_io = ipc_alloc(sizeof(ushort)*nsems); + sem_io = kvmalloc_array(nsems, sizeof(ushort), + GFP_KERNEL); if (sem_io == NULL) { ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); return -ENOMEM; @@ -1480,7 +1482,7 @@ out_rcu_wakeup: wake_up_q(&wake_q); out_free: if (sem_io != fast_sem_io) - ipc_free(sem_io); + kvfree(sem_io); return err; } diff --git a/ipc/util.c b/ipc/util.c index 5d1ff1035efe..dd73feb1569a 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -394,29 +394,6 @@ void ipc_rmid(struct ipc_ids *ids, struct kern_ipc_perm *ipcp) ipcp->deleted = true; } -/** - * ipc_alloc - allocate ipc space - * @size: size desired - * - * Allocate memory from the appropriate pools and return a pointer to it. - * NULL is returned if the allocation fails - */ -void *ipc_alloc(int size) -{ - return kvmalloc(size, GFP_KERNEL); -} - -/** - * ipc_free - free ipc space - * @ptr: pointer returned by ipc_alloc - * - * Free a block created with ipc_alloc(). - */ -void ipc_free(void *ptr) -{ - kvfree(ptr); -} - /** * ipc_rcu_alloc - allocate ipc space * @size: size desired @@ -429,7 +406,7 @@ struct kern_ipc_perm *ipc_rcu_alloc(int size) /* * We prepend the allocation with the rcu struct */ - struct kern_ipc_perm *out = ipc_alloc(size); + struct kern_ipc_perm *out = kvmalloc(size, GFP_KERNEL); if (unlikely(!out)) return NULL; diff --git a/ipc/util.h b/ipc/util.h index 09d0f918c3e2..2578fd9be835 100644 --- a/ipc/util.h +++ b/ipc/util.h @@ -107,12 +107,6 @@ void ipc_rmid(struct ipc_ids *, struct kern_ipc_perm *); /* must be called with ipcp locked */ int ipcperms(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp, short flg); -/* for rare, potentially huge allocations. - * both function can sleep - */ -void *ipc_alloc(int size); -void ipc_free(void *ptr); - /* * For allocation that need to be freed by RCU. * Objects are reference counted, they start with reference count 1. -- cgit v1.2.3-59-g8ed1b From 1b4654ef72f61c84704b3c79b50fdeed8747fc56 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Jul 2017 14:34:50 -0700 Subject: ipc/sem: do not use ipc_rcu_free() Avoid using ipc_rcu_free, since it just re-finds the original structure pointer. For the pre-list-init failure path, there is no RCU needed, since it was just allocated. It can be directly freed. Link: http://lkml.kernel.org/r/20170525185107.12869-6-manfred@colorfullife.com Signed-off-by: Kees Cook Signed-off-by: Manfred Spraul Cc: Davidlohr Bueso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/sem.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/ipc/sem.c b/ipc/sem.c index 484ccf83cf85..a04c4d6d120c 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -258,13 +258,18 @@ static void merge_queues(struct sem_array *sma) } } +static void __sem_free(struct sem_array *sma) +{ + kvfree(sma); +} + static void sem_rcu_free(struct rcu_head *head) { struct kern_ipc_perm *p = container_of(head, struct kern_ipc_perm, rcu); struct sem_array *sma = container_of(p, struct sem_array, sem_perm); security_sem_free(sma); - ipc_rcu_free(head); + __sem_free(sma); } /* @@ -482,7 +487,7 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params) sma->sem_perm.security = NULL; retval = security_sem_alloc(sma); if (retval) { - ipc_rcu_putref(&sma->sem_perm, ipc_rcu_free); + __sem_free(sma); return retval; } -- cgit v1.2.3-59-g8ed1b From 66470b18179f8839a62b4c20ffd3903a4025fe90 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Jul 2017 14:34:53 -0700 Subject: ipc/shm: do not use ipc_rcu_free() Avoid using ipc_rcu_free, since it just re-finds the original structure pointer. For the pre-list-init failure path, there is no RCU needed, since it was just allocated. It can be directly freed. Link: http://lkml.kernel.org/r/20170525185107.12869-7-manfred@colorfullife.com Signed-off-by: Kees Cook Signed-off-by: Manfred Spraul Cc: Davidlohr Bueso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/shm.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/ipc/shm.c b/ipc/shm.c index 5ef6d31a52c5..566c1e193ee1 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -172,6 +172,11 @@ static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp) ipc_lock_object(&ipcp->shm_perm); } +static void __shm_free(struct shmid_kernel *shp) +{ + kvfree(shp); +} + static void shm_rcu_free(struct rcu_head *head) { struct kern_ipc_perm *ptr = container_of(head, struct kern_ipc_perm, @@ -179,7 +184,7 @@ static void shm_rcu_free(struct rcu_head *head) struct shmid_kernel *shp = container_of(ptr, struct shmid_kernel, shm_perm); security_shm_free(shp); - ipc_rcu_free(head); + __shm_free(shp); } static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s) @@ -557,7 +562,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) shp->shm_perm.security = NULL; error = security_shm_alloc(shp); if (error) { - ipc_rcu_putref(&shp->shm_perm, ipc_rcu_free); + __shm_free(shp); return error; } -- cgit v1.2.3-59-g8ed1b From 9ef5932f8a1134b9d93676ee26701b2be90c7a95 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Jul 2017 14:34:56 -0700 Subject: ipc/msg: do not use ipc_rcu_free() Avoid using ipc_rcu_free, since it just re-finds the original structure pointer. For the pre-list-init failure path, there is no RCU needed, since it was just allocated. It can be directly freed. Link: http://lkml.kernel.org/r/20170525185107.12869-8-manfred@colorfullife.com Signed-off-by: Kees Cook Signed-off-by: Manfred Spraul Cc: Davidlohr Bueso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/msg.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/ipc/msg.c b/ipc/msg.c index 0ed7dae7d4e8..25d43e27ef12 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -95,13 +95,18 @@ static inline void msg_rmid(struct ipc_namespace *ns, struct msg_queue *s) ipc_rmid(&msg_ids(ns), &s->q_perm); } +static void __msg_free(struct msg_queue *msq) +{ + kvfree(msq); +} + static void msg_rcu_free(struct rcu_head *head) { struct kern_ipc_perm *p = container_of(head, struct kern_ipc_perm, rcu); struct msg_queue *msq = container_of(p, struct msg_queue, q_perm); security_msg_queue_free(msq); - ipc_rcu_free(head); + __msg_free(msq); } /** @@ -131,7 +136,7 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params) msq->q_perm.security = NULL; retval = security_msg_queue_alloc(msq); if (retval) { - ipc_rcu_putref(&msq->q_perm, ipc_rcu_free); + __msg_free(msq); return retval; } -- cgit v1.2.3-59-g8ed1b From 5ccc8fb54f1c083f1dc7e073150ec18d43457872 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Jul 2017 14:34:59 -0700 Subject: ipc/util: drop ipc_rcu_free() There are no more callers of ipc_rcu_free(), so remove it. Link: http://lkml.kernel.org/r/20170525185107.12869-9-manfred@colorfullife.com Signed-off-by: Kees Cook Signed-off-by: Manfred Spraul Cc: Davidlohr Bueso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/util.c | 7 ------- ipc/util.h | 1 - 2 files changed, 8 deletions(-) diff --git a/ipc/util.c b/ipc/util.c index dd73feb1569a..556884bab698 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -429,13 +429,6 @@ void ipc_rcu_putref(struct kern_ipc_perm *ptr, call_rcu(&ptr->rcu, func); } -void ipc_rcu_free(struct rcu_head *h) -{ - struct kern_ipc_perm *ptr = container_of(h, struct kern_ipc_perm, rcu); - - kvfree(ptr); -} - /** * ipcperms - check ipc permissions * @ns: ipc namespace diff --git a/ipc/util.h b/ipc/util.h index 2578fd9be835..44efbc0b635b 100644 --- a/ipc/util.h +++ b/ipc/util.h @@ -119,7 +119,6 @@ struct kern_ipc_perm *ipc_rcu_alloc(int size); int ipc_rcu_getref(struct kern_ipc_perm *ptr); void ipc_rcu_putref(struct kern_ipc_perm *ptr, void (*func)(struct rcu_head *head)); -void ipc_rcu_free(struct rcu_head *h); struct kern_ipc_perm *ipc_lock(struct ipc_ids *, int); struct kern_ipc_perm *ipc_obtain_object_idr(struct ipc_ids *ids, int id); -- cgit v1.2.3-59-g8ed1b From 101ede01dfd5072651965e974bc6e30c8d0748e2 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Jul 2017 14:35:02 -0700 Subject: ipc/sem: avoid ipc_rcu_alloc() Instead of using ipc_rcu_alloc() which only performs the refcount bump, open code it to perform better sem-specific checks. This also allows for sem_array structure layout to be randomized in the future. [manfred@colorfullife.com: Rediff, because the memset was temporarily inside ipc_rcu_alloc()] Link: http://lkml.kernel.org/r/20170525185107.12869-10-manfred@colorfullife.com Signed-off-by: Kees Cook Signed-off-by: Manfred Spraul Cc: Davidlohr Bueso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/sem.c | 25 ++++++++++++++++++++----- 1 file changed, 20 insertions(+), 5 deletions(-) diff --git a/ipc/sem.c b/ipc/sem.c index a04c4d6d120c..445a5b5eb88f 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -451,6 +451,25 @@ static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s) ipc_rmid(&sem_ids(ns), &s->sem_perm); } +static struct sem_array *sem_alloc(size_t nsems) +{ + struct sem_array *sma; + size_t size; + + if (nsems > (INT_MAX - sizeof(*sma)) / sizeof(sma->sems[0])) + return NULL; + + size = sizeof(*sma) + nsems * sizeof(sma->sems[0]); + sma = kvmalloc(size, GFP_KERNEL); + if (unlikely(!sma)) + return NULL; + + memset(sma, 0, size); + atomic_set(&sma->sem_perm.refcount, 1); + + return sma; +} + /** * newary - Create a new semaphore set * @ns: namespace @@ -463,7 +482,6 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params) int id; int retval; struct sem_array *sma; - int size; key_t key = params->key; int nsems = params->u.nsems; int semflg = params->flg; @@ -474,10 +492,7 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params) if (ns->used_sems + nsems > ns->sc_semmns) return -ENOSPC; - BUILD_BUG_ON(offsetof(struct sem_array, sem_perm) != 0); - - size = sizeof(*sma) + nsems * sizeof(sma->sems[0]); - sma = container_of(ipc_rcu_alloc(size), struct sem_array, sem_perm); + sma = sem_alloc(nsems); if (!sma) return -ENOMEM; -- cgit v1.2.3-59-g8ed1b From 3e0c24042e5aa55eee817caeca67246df69931e1 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Jul 2017 14:35:05 -0700 Subject: ipc/shm: avoid ipc_rcu_alloc() Instead of using ipc_rcu_alloc() which only performs the refcount bump, open code it. This also allows for shmid_kernel structure layout to be randomized in the future. Link: http://lkml.kernel.org/r/20170525185107.12869-11-manfred@colorfullife.com Signed-off-by: Kees Cook Signed-off-by: Manfred Spraul Cc: Davidlohr Bueso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/shm.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/ipc/shm.c b/ipc/shm.c index 566c1e193ee1..2ac489ef56e4 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -518,6 +518,19 @@ static const struct vm_operations_struct shm_vm_ops = { #endif }; +static struct shmid_kernel *shm_alloc(void) +{ + struct shmid_kernel *shp; + + shp = kvmalloc(sizeof(*shp), GFP_KERNEL); + if (unlikely(!shp)) + return NULL; + + atomic_set(&shp->shm_perm.refcount, 1); + + return shp; +} + /** * newseg - Create a new shared memory segment * @ns: namespace @@ -548,10 +561,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) ns->shm_tot + numpages > ns->shm_ctlall) return -ENOSPC; - BUILD_BUG_ON(offsetof(struct shmid_kernel, shm_perm) != 0); - - shp = container_of(ipc_rcu_alloc(sizeof(*shp)), struct shmid_kernel, - shm_perm); + shp = shm_alloc(); if (!shp) return -ENOMEM; -- cgit v1.2.3-59-g8ed1b From 52f908904e7e05b6300162faa48152df073be645 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Jul 2017 14:35:07 -0700 Subject: ipc/msg: avoid ipc_rcu_alloc() Instead of using ipc_rcu_alloc() which only performs the refcount bump, open code it. This also allows for msg_queue structure layout to be randomized in the future. Link: http://lkml.kernel.org/r/20170525185107.12869-12-manfred@colorfullife.com Signed-off-by: Kees Cook Signed-off-by: Manfred Spraul Cc: Davidlohr Bueso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/msg.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/ipc/msg.c b/ipc/msg.c index 25d43e27ef12..10094a731b8e 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -109,6 +109,19 @@ static void msg_rcu_free(struct rcu_head *head) __msg_free(msq); } +static struct msg_queue *msg_alloc(void) +{ + struct msg_queue *msq; + + msq = kvmalloc(sizeof(*msq), GFP_KERNEL); + if (unlikely(!msq)) + return NULL; + + atomic_set(&msq->q_perm.refcount, 1); + + return msq; +} + /** * newque - Create a new msg queue * @ns: namespace @@ -123,10 +136,7 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params) key_t key = params->key; int msgflg = params->flg; - BUILD_BUG_ON(offsetof(struct msg_queue, q_perm) != 0); - - msq = container_of(ipc_rcu_alloc(sizeof(*msq)), struct msg_queue, - q_perm); + msq = msg_alloc(); if (!msq) return -ENOMEM; -- cgit v1.2.3-59-g8ed1b From c3f6fb6fe4e638a58eae558cb209c463cd46c2fc Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Jul 2017 14:35:10 -0700 Subject: ipc/util: drop ipc_rcu_alloc() No callers remain for ipc_rcu_alloc(). Drop the function. [manfred@colorfullife.com: Rediff because the memset was temporarily inside ipc_rcu_free()] Link: http://lkml.kernel.org/r/20170525185107.12869-13-manfred@colorfullife.com Signed-off-by: Kees Cook Signed-off-by: Manfred Spraul Cc: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/util.c | 21 --------------------- ipc/util.h | 3 --- 2 files changed, 24 deletions(-) diff --git a/ipc/util.c b/ipc/util.c index 556884bab698..2428dd44ca97 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -394,27 +394,6 @@ void ipc_rmid(struct ipc_ids *ids, struct kern_ipc_perm *ipcp) ipcp->deleted = true; } -/** - * ipc_rcu_alloc - allocate ipc space - * @size: size desired - * - * Allocate memory for an ipc object. - * The first member must be struct kern_ipc_perm. - */ -struct kern_ipc_perm *ipc_rcu_alloc(int size) -{ - /* - * We prepend the allocation with the rcu struct - */ - struct kern_ipc_perm *out = kvmalloc(size, GFP_KERNEL); - if (unlikely(!out)) - return NULL; - - memset(out, 0, size); - atomic_set(&out->refcount, 1); - return out; -} - int ipc_rcu_getref(struct kern_ipc_perm *ptr) { return atomic_inc_not_zero(&ptr->refcount); diff --git a/ipc/util.h b/ipc/util.h index 44efbc0b635b..77336c2bdb9c 100644 --- a/ipc/util.h +++ b/ipc/util.h @@ -112,10 +112,7 @@ int ipcperms(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp, short flg); * Objects are reference counted, they start with reference count 1. * getref increases the refcount, the putref call that reduces the recount * to 0 schedules the rcu destruction. Caller must guarantee locking. - * - * struct kern_ipc_perm must be the first member in the allocated structure. */ -struct kern_ipc_perm *ipc_rcu_alloc(int size); int ipc_rcu_getref(struct kern_ipc_perm *ptr); void ipc_rcu_putref(struct kern_ipc_perm *ptr, void (*func)(struct rcu_head *head)); -- cgit v1.2.3-59-g8ed1b From 2ec55f8024db859d70f14c26e91ca044328dd50d Mon Sep 17 00:00:00 2001 From: Manfred Spraul Date: Wed, 12 Jul 2017 14:35:13 -0700 Subject: ipc/sem.c: avoid ipc_rcu_putref for failed ipc_addid() Loosely based on a patch from Kees Cook : - id and retval can be merged - if ipc_addid() fails, then use call_rcu() directly. The difference is that call_rcu is used for failed ipc_addid() calls, to continue to guaranteed an rcu delay for security_sem_free(). Link: http://lkml.kernel.org/r/20170525185107.12869-14-manfred@colorfullife.com Signed-off-by: Manfred Spraul Cc: Kees Cook Cc: Davidlohr Bueso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/sem.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/ipc/sem.c b/ipc/sem.c index 445a5b5eb88f..2b2ed56e0fde 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -479,7 +479,6 @@ static struct sem_array *sem_alloc(size_t nsems) */ static int newary(struct ipc_namespace *ns, struct ipc_params *params) { - int id; int retval; struct sem_array *sma; key_t key = params->key; @@ -520,10 +519,10 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params) sma->sem_nsems = nsems; sma->sem_ctime = get_seconds(); - id = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni); - if (id < 0) { - ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); - return id; + retval = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni); + if (retval < 0) { + call_rcu(&sma->sem_perm.rcu, sem_rcu_free); + return retval; } ns->used_sems += nsems; -- cgit v1.2.3-59-g8ed1b From a2642f8770993a1598500bb6a8082b7c32faff8b Mon Sep 17 00:00:00 2001 From: Manfred Spraul Date: Wed, 12 Jul 2017 14:35:16 -0700 Subject: ipc/shm.c: avoid ipc_rcu_putref for failed ipc_addid() Loosely based on a patch from Kees Cook : - id and error can be merged - if operations before ipc_addid() fail, then use call_rcu() directly. The difference is that call_rcu is used for failures after security_shm_alloc(), to continue to guaranteed an rcu delay for security_sem_free(). Link: http://lkml.kernel.org/r/20170525185107.12869-15-manfred@colorfullife.com Signed-off-by: Manfred Spraul Cc: Kees Cook Cc: Davidlohr Bueso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/shm.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/ipc/shm.c b/ipc/shm.c index 2ac489ef56e4..c5976d318ed1 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -548,7 +548,6 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) size_t numpages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; struct file *file; char name[13]; - int id; vm_flags_t acctflag = 0; if (size < SHMMIN || size > ns->shm_ctlmax) @@ -617,11 +616,9 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) shp->shm_file = file; shp->shm_creator = current; - id = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni); - if (id < 0) { - error = id; + error = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni); + if (error < 0) goto no_id; - } list_add(&shp->shm_clist, ¤t->sysvshm.shm_clist); @@ -643,7 +640,7 @@ no_id: user_shm_unlock(size, shp->mlock_user); fput(file); no_file: - ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); + call_rcu(&shp->shm_perm.rcu, shm_rcu_free); return error; } -- cgit v1.2.3-59-g8ed1b From 51c23b7b7db52493d4fc869cec8c3e8fe27bfcd3 Mon Sep 17 00:00:00 2001 From: Manfred Spraul Date: Wed, 12 Jul 2017 14:35:19 -0700 Subject: ipc/msg.c: avoid ipc_rcu_putref for failed ipc_addid() Loosely based on a patch from Kees Cook : - id and retval can be merged - if ipc_addid() fails, then use call_rcu() directly. The difference is that call_rcu is used for failed ipc_addid() calls, to continue to guaranteed an rcu delay for security_msg_queue_free(). Link: http://lkml.kernel.org/r/20170525185107.12869-16-manfred@colorfullife.com Signed-off-by: Manfred Spraul Cc: Kees Cook Cc: Davidlohr Bueso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/msg.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/ipc/msg.c b/ipc/msg.c index 10094a731b8e..cd90bfde89a4 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -132,7 +132,7 @@ static struct msg_queue *msg_alloc(void) static int newque(struct ipc_namespace *ns, struct ipc_params *params) { struct msg_queue *msq; - int id, retval; + int retval; key_t key = params->key; int msgflg = params->flg; @@ -160,10 +160,10 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params) INIT_LIST_HEAD(&msq->q_senders); /* ipc_addid() locks msq upon success. */ - id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni); - if (id < 0) { - ipc_rcu_putref(&msq->q_perm, msg_rcu_free); - return id; + retval = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni); + if (retval < 0) { + call_rcu(&msq->q_perm.rcu, msg_rcu_free); + return retval; } ipc_unlock_object(&msq->q_perm); -- cgit v1.2.3-59-g8ed1b From 3d3653f9732c73feb8c4addfc1cbdaa292a399fa Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Jul 2017 14:35:22 -0700 Subject: ipc: move atomic_set() to where it is needed Only after ipc_addid() has succeeded will refcounting be used, so move initialization into ipc_addid() and remove from open-coded *_alloc() routines. Link: http://lkml.kernel.org/r/20170525185107.12869-17-manfred@colorfullife.com Signed-off-by: Kees Cook Signed-off-by: Manfred Spraul Cc: Davidlohr Bueso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/msg.c | 2 -- ipc/sem.c | 1 - ipc/shm.c | 2 -- ipc/util.c | 1 + 4 files changed, 1 insertion(+), 5 deletions(-) diff --git a/ipc/msg.c b/ipc/msg.c index cd90bfde89a4..770342e1d327 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -117,8 +117,6 @@ static struct msg_queue *msg_alloc(void) if (unlikely(!msq)) return NULL; - atomic_set(&msq->q_perm.refcount, 1); - return msq; } diff --git a/ipc/sem.c b/ipc/sem.c index 2b2ed56e0fde..5f137738819d 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -465,7 +465,6 @@ static struct sem_array *sem_alloc(size_t nsems) return NULL; memset(sma, 0, size); - atomic_set(&sma->sem_perm.refcount, 1); return sma; } diff --git a/ipc/shm.c b/ipc/shm.c index c5976d318ed1..d1988ef821a1 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -526,8 +526,6 @@ static struct shmid_kernel *shm_alloc(void) if (unlikely(!shp)) return NULL; - atomic_set(&shp->shm_perm.refcount, 1); - return shp; } diff --git a/ipc/util.c b/ipc/util.c index 2428dd44ca97..1a2cb02467ab 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -232,6 +232,7 @@ int ipc_addid(struct ipc_ids *ids, struct kern_ipc_perm *new, int size) idr_preload(GFP_KERNEL); + atomic_set(&new->refcount, 1); spin_lock_init(&new->lock); new->deleted = false; rcu_read_lock(); -- cgit v1.2.3-59-g8ed1b From 42e618f77dabc82c697915c193d729e9d16e2a75 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Jul 2017 14:35:25 -0700 Subject: ipc/shm: remove special shm_alloc/free There is nothing special about the shm_alloc/free routines any more, so remove them to make code more readable. [manfred@colorfullife.com: Rediff, to continue to keep rcu for free calls after a successful security_shm_alloc()] Link: http://lkml.kernel.org/r/20170525185107.12869-18-manfred@colorfullife.com Signed-off-by: Kees Cook Signed-off-by: Manfred Spraul Cc: Davidlohr Bueso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/shm.c | 24 ++++-------------------- 1 file changed, 4 insertions(+), 20 deletions(-) diff --git a/ipc/shm.c b/ipc/shm.c index d1988ef821a1..28a444861a8f 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -172,11 +172,6 @@ static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp) ipc_lock_object(&ipcp->shm_perm); } -static void __shm_free(struct shmid_kernel *shp) -{ - kvfree(shp); -} - static void shm_rcu_free(struct rcu_head *head) { struct kern_ipc_perm *ptr = container_of(head, struct kern_ipc_perm, @@ -184,7 +179,7 @@ static void shm_rcu_free(struct rcu_head *head) struct shmid_kernel *shp = container_of(ptr, struct shmid_kernel, shm_perm); security_shm_free(shp); - __shm_free(shp); + kvfree(shp); } static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s) @@ -518,17 +513,6 @@ static const struct vm_operations_struct shm_vm_ops = { #endif }; -static struct shmid_kernel *shm_alloc(void) -{ - struct shmid_kernel *shp; - - shp = kvmalloc(sizeof(*shp), GFP_KERNEL); - if (unlikely(!shp)) - return NULL; - - return shp; -} - /** * newseg - Create a new shared memory segment * @ns: namespace @@ -558,8 +542,8 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) ns->shm_tot + numpages > ns->shm_ctlall) return -ENOSPC; - shp = shm_alloc(); - if (!shp) + shp = kvmalloc(sizeof(*shp), GFP_KERNEL); + if (unlikely(!shp)) return -ENOMEM; shp->shm_perm.key = key; @@ -569,7 +553,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) shp->shm_perm.security = NULL; error = security_shm_alloc(shp); if (error) { - __shm_free(shp); + kvfree(shp); return error; } -- cgit v1.2.3-59-g8ed1b From fb259c310f79d295c2da2934ff2282e1b7c30529 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Jul 2017 14:35:28 -0700 Subject: ipc/msg: remove special msg_alloc/free There is nothing special about the msg_alloc/free routines any more, so remove them to make code more readable. [manfred@colorfullife.com: Rediff to keep rcu protection for security_msg_queue_alloc()] Link: http://lkml.kernel.org/r/20170525185107.12869-19-manfred@colorfullife.com Signed-off-by: Kees Cook Signed-off-by: Manfred Spraul Cc: Davidlohr Bueso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/msg.c | 24 ++++-------------------- 1 file changed, 4 insertions(+), 20 deletions(-) diff --git a/ipc/msg.c b/ipc/msg.c index 770342e1d327..5b25e0755656 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -95,29 +95,13 @@ static inline void msg_rmid(struct ipc_namespace *ns, struct msg_queue *s) ipc_rmid(&msg_ids(ns), &s->q_perm); } -static void __msg_free(struct msg_queue *msq) -{ - kvfree(msq); -} - static void msg_rcu_free(struct rcu_head *head) { struct kern_ipc_perm *p = container_of(head, struct kern_ipc_perm, rcu); struct msg_queue *msq = container_of(p, struct msg_queue, q_perm); security_msg_queue_free(msq); - __msg_free(msq); -} - -static struct msg_queue *msg_alloc(void) -{ - struct msg_queue *msq; - - msq = kvmalloc(sizeof(*msq), GFP_KERNEL); - if (unlikely(!msq)) - return NULL; - - return msq; + kvfree(msq); } /** @@ -134,8 +118,8 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params) key_t key = params->key; int msgflg = params->flg; - msq = msg_alloc(); - if (!msq) + msq = kvmalloc(sizeof(*msq), GFP_KERNEL); + if (unlikely(!msq)) return -ENOMEM; msq->q_perm.mode = msgflg & S_IRWXUGO; @@ -144,7 +128,7 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params) msq->q_perm.security = NULL; retval = security_msg_queue_alloc(msq); if (retval) { - __msg_free(msq); + kvfree(msq); return retval; } -- cgit v1.2.3-59-g8ed1b From e2029dfeef7b09f08ac8572e8be3d4c624d1f79a Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Jul 2017 14:35:31 -0700 Subject: ipc/sem: drop __sem_free() The remaining users of __sem_free() can simply call kvfree() instead for better readability. [manfred@colorfullife.com: Rediff to keep rcu protection for security_sem_alloc()] Link: http://lkml.kernel.org/r/20170525185107.12869-20-manfred@colorfullife.com Signed-off-by: Kees Cook Signed-off-by: Manfred Spraul Cc: Davidlohr Bueso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/sem.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/ipc/sem.c b/ipc/sem.c index 5f137738819d..9e70cd7a17da 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -258,18 +258,13 @@ static void merge_queues(struct sem_array *sma) } } -static void __sem_free(struct sem_array *sma) -{ - kvfree(sma); -} - static void sem_rcu_free(struct rcu_head *head) { struct kern_ipc_perm *p = container_of(head, struct kern_ipc_perm, rcu); struct sem_array *sma = container_of(p, struct sem_array, sem_perm); security_sem_free(sma); - __sem_free(sma); + kvfree(sma); } /* @@ -500,7 +495,7 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params) sma->sem_perm.security = NULL; retval = security_sem_alloc(sma); if (retval) { - __sem_free(sma); + kvfree(sma); return retval; } -- cgit v1.2.3-59-g8ed1b From 62b49c9908bcee88347efe8b4ed1b4f53c60ee66 Mon Sep 17 00:00:00 2001 From: Manfred Spraul Date: Wed, 12 Jul 2017 14:35:34 -0700 Subject: ipc/util.h: update documentation for ipc_getref() and ipc_putref() Now that ipc_rcu_alloc() and ipc_rcu_free() are removed, document when it is valid to use ipc_getref() and ipc_putref(). Link: http://lkml.kernel.org/r/20170525185107.12869-21-manfred@colorfullife.com Signed-off-by: Manfred Spraul Cc: Davidlohr Bueso Cc: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/util.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/ipc/util.h b/ipc/util.h index 77336c2bdb9c..c692010e6f0a 100644 --- a/ipc/util.h +++ b/ipc/util.h @@ -112,6 +112,9 @@ int ipcperms(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp, short flg); * Objects are reference counted, they start with reference count 1. * getref increases the refcount, the putref call that reduces the recount * to 0 schedules the rcu destruction. Caller must guarantee locking. + * + * refcount is initialized by ipc_addid(), before that point call_rcu() + * must be used. */ int ipc_rcu_getref(struct kern_ipc_perm *ptr); void ipc_rcu_putref(struct kern_ipc_perm *ptr, -- cgit v1.2.3-59-g8ed1b From eacd86ca3b036e55e172b7279f101cef4a6ff3a4 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 12 Jul 2017 14:35:37 -0700 Subject: net/netfilter/x_tables.c: use kvmalloc() in xt_alloc_table_info() xt_alloc_table_info() basically opencodes kvmalloc() so use the library function instead. Link: http://lkml.kernel.org/r/20170531155145.17111-4-mhocko@kernel.org Signed-off-by: Michal Hocko Cc: Pablo Neira Ayuso Cc: Jozsef Kadlecsik Cc: Florian Westphal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- net/netfilter/x_tables.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 1770c1d9b37f..e1648238a9c9 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1003,14 +1003,10 @@ struct xt_table_info *xt_alloc_table_info(unsigned int size) if ((SMP_ALIGN(size) >> PAGE_SHIFT) + 2 > totalram_pages) return NULL; - if (sz <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) - info = kmalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); - if (!info) { - info = __vmalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY, - PAGE_KERNEL); - if (!info) - return NULL; - } + info = kvmalloc(sz, GFP_KERNEL); + if (!info) + return NULL; + memset(info, 0, sizeof(*info)); info->size = size; return info; -- cgit v1.2.3-59-g8ed1b From 24bb44612c5f93a1dff1f7e71b7b7b109a988791 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 12 Jul 2017 14:35:40 -0700 Subject: kernel/watchdog: remove unused declaration Patch series "Improve watchdog config for arch watchdogs", v4. A series to make the hardlockup watchdog more easily replaceable by arch code. The last patch provides some justification for why we want to do this (existing sparc watchdog is another that could benefit). This patch (of 5): Remove unused declaration. Link: http://lkml.kernel.org/r/20170616065715.18390-2-npiggin@gmail.com Signed-off-by: Nicholas Piggin Reviewed-by: Don Zickus Reviewed-by: Babu Moger Tested-by: Babu Moger [sparc] Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nmi.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/include/linux/nmi.h b/include/linux/nmi.h index aa3cd0878270..5e2e57536d98 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -12,9 +12,6 @@ extern void touch_softlockup_watchdog_sched(void); extern void touch_softlockup_watchdog(void); extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); -extern int proc_dowatchdog_thresh(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos); extern unsigned int softlockup_panic; extern unsigned int hardlockup_panic; void lockup_detector_init(void); -- cgit v1.2.3-59-g8ed1b From f2e0cff85ed111a3cf24d894c3fa11697dfae628 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 12 Jul 2017 14:35:43 -0700 Subject: kernel/watchdog: introduce arch_touch_nmi_watchdog() For architectures that define HAVE_NMI_WATCHDOG, instead of having them provide the complete touch_nmi_watchdog() function, just have them provide arch_touch_nmi_watchdog(). This gives the generic code more flexibility in implementing this function, and arch implementations don't miss out on touching the softlockup watchdog or other generic details. Link: http://lkml.kernel.org/r/20170616065715.18390-3-npiggin@gmail.com Signed-off-by: Nicholas Piggin Reviewed-by: Don Zickus Reviewed-by: Babu Moger Tested-by: Babu Moger [sparc] Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/blackfin/include/asm/nmi.h | 2 ++ arch/blackfin/kernel/nmi.c | 2 +- arch/mn10300/include/asm/nmi.h | 2 ++ arch/mn10300/kernel/mn10300-watchdog-low.S | 8 ++++---- arch/mn10300/kernel/mn10300-watchdog.c | 2 +- arch/sparc/include/asm/nmi.h | 1 + arch/sparc/kernel/nmi.c | 6 ++---- include/linux/nmi.h | 27 ++++++++++++++++----------- kernel/watchdog_hld.c | 5 ++--- 9 files changed, 31 insertions(+), 24 deletions(-) diff --git a/arch/blackfin/include/asm/nmi.h b/arch/blackfin/include/asm/nmi.h index b9caac4fcfd8..107d23705f46 100644 --- a/arch/blackfin/include/asm/nmi.h +++ b/arch/blackfin/include/asm/nmi.h @@ -9,4 +9,6 @@ #include +extern void arch_touch_nmi_watchdog(void); + #endif diff --git a/arch/blackfin/kernel/nmi.c b/arch/blackfin/kernel/nmi.c index 633c37083e87..1e714329fe8a 100644 --- a/arch/blackfin/kernel/nmi.c +++ b/arch/blackfin/kernel/nmi.c @@ -190,7 +190,7 @@ static int __init init_nmi_wdt(void) } device_initcall(init_nmi_wdt); -void touch_nmi_watchdog(void) +void arch_touch_nmi_watchdog(void) { atomic_set(&nmi_touched[smp_processor_id()], 1); } diff --git a/arch/mn10300/include/asm/nmi.h b/arch/mn10300/include/asm/nmi.h index f3671cbbc117..b05627597b1b 100644 --- a/arch/mn10300/include/asm/nmi.h +++ b/arch/mn10300/include/asm/nmi.h @@ -11,4 +11,6 @@ #ifndef _ASM_NMI_H #define _ASM_NMI_H +extern void arch_touch_nmi_watchdog(void); + #endif /* _ASM_NMI_H */ diff --git a/arch/mn10300/kernel/mn10300-watchdog-low.S b/arch/mn10300/kernel/mn10300-watchdog-low.S index f2f5c9cfaabd..34f8773de7d0 100644 --- a/arch/mn10300/kernel/mn10300-watchdog-low.S +++ b/arch/mn10300/kernel/mn10300-watchdog-low.S @@ -50,9 +50,9 @@ watchdog_handler: # we can't inline it) # ############################################################################### - .globl touch_nmi_watchdog - .type touch_nmi_watchdog,@function -touch_nmi_watchdog: + .globl arch_touch_nmi_watchdog + .type arch_touch_nmi_watchdog,@function +arch_touch_nmi_watchdog: clr d0 clr d1 mov watchdog_alert_counter, a0 @@ -63,4 +63,4 @@ touch_nmi_watchdog: lne ret [],0 - .size touch_nmi_watchdog,.-touch_nmi_watchdog + .size arch_touch_nmi_watchdog,.-arch_touch_nmi_watchdog diff --git a/arch/mn10300/kernel/mn10300-watchdog.c b/arch/mn10300/kernel/mn10300-watchdog.c index a2d8e6938d67..0d5641beadf5 100644 --- a/arch/mn10300/kernel/mn10300-watchdog.c +++ b/arch/mn10300/kernel/mn10300-watchdog.c @@ -31,7 +31,7 @@ static unsigned int watchdog; static unsigned int watchdog_hz = 1; unsigned int watchdog_alert_counter[NR_CPUS]; -EXPORT_SYMBOL(touch_nmi_watchdog); +EXPORT_SYMBOL(arch_touch_nmi_watchdog); /* * the best way to detect whether a CPU has a 'hard lockup' problem diff --git a/arch/sparc/include/asm/nmi.h b/arch/sparc/include/asm/nmi.h index 26ad2b2607c6..284eac3ffaf2 100644 --- a/arch/sparc/include/asm/nmi.h +++ b/arch/sparc/include/asm/nmi.h @@ -7,6 +7,7 @@ void nmi_adjust_hz(unsigned int new_hz); extern atomic_t nmi_active; +void arch_touch_nmi_watchdog(void); void start_nmi_watchdog(void *unused); void stop_nmi_watchdog(void *unused); diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c index 95e73c63c99d..048ad783ea3f 100644 --- a/arch/sparc/kernel/nmi.c +++ b/arch/sparc/kernel/nmi.c @@ -51,7 +51,7 @@ static DEFINE_PER_CPU(unsigned int, last_irq_sum); static DEFINE_PER_CPU(long, alert_counter); static DEFINE_PER_CPU(int, nmi_touch); -void touch_nmi_watchdog(void) +void arch_touch_nmi_watchdog(void) { if (atomic_read(&nmi_active)) { int cpu; @@ -61,10 +61,8 @@ void touch_nmi_watchdog(void) per_cpu(nmi_touch, cpu) = 1; } } - - touch_softlockup_watchdog(); } -EXPORT_SYMBOL(touch_nmi_watchdog); +EXPORT_SYMBOL(arch_touch_nmi_watchdog); static void die_nmi(const char *str, struct pt_regs *regs, int do_panic) { diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 5e2e57536d98..bd387ef8bccd 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -6,6 +6,9 @@ #include #include +#if defined(CONFIG_HAVE_NMI_WATCHDOG) +#include +#endif #ifdef CONFIG_LOCKUP_DETECTOR extern void touch_softlockup_watchdog_sched(void); @@ -58,6 +61,18 @@ static inline void reset_hung_task_detector(void) #define NMI_WATCHDOG_ENABLED (1 << NMI_WATCHDOG_ENABLED_BIT) #define SOFT_WATCHDOG_ENABLED (1 << SOFT_WATCHDOG_ENABLED_BIT) +#if defined(CONFIG_HARDLOCKUP_DETECTOR) +extern void hardlockup_detector_disable(void); +#else +static inline void hardlockup_detector_disable(void) {} +#endif + +#if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG) +extern void arch_touch_nmi_watchdog(void); +#else +static inline void arch_touch_nmi_watchdog(void) {} +#endif + /** * touch_nmi_watchdog - restart NMI watchdog timeout. * @@ -65,21 +80,11 @@ static inline void reset_hung_task_detector(void) * may be used to reset the timeout - for code which intentionally * disables interrupts for a long time. This call is stateless. */ -#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) -#include -extern void touch_nmi_watchdog(void); -#else static inline void touch_nmi_watchdog(void) { + arch_touch_nmi_watchdog(); touch_softlockup_watchdog(); } -#endif - -#if defined(CONFIG_HARDLOCKUP_DETECTOR) -extern void hardlockup_detector_disable(void); -#else -static inline void hardlockup_detector_disable(void) {} -#endif /* * Create trigger_all_cpu_backtrace() out of the arch-provided diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 54a427d1f344..90d688df6ce1 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -56,7 +56,7 @@ static int __init hardlockup_panic_setup(char *str) } __setup("nmi_watchdog=", hardlockup_panic_setup); -void touch_nmi_watchdog(void) +void arch_touch_nmi_watchdog(void) { /* * Using __raw here because some code paths have @@ -66,9 +66,8 @@ void touch_nmi_watchdog(void) * going off. */ raw_cpu_write(watchdog_nmi_touch, true); - touch_softlockup_watchdog(); } -EXPORT_SYMBOL(touch_nmi_watchdog); +EXPORT_SYMBOL(arch_touch_nmi_watchdog); static struct perf_event_attr wd_hw_attr = { .type = PERF_TYPE_HARDWARE, -- cgit v1.2.3-59-g8ed1b From 05a4a95279311c3a4633b4277a5d21cfd616c6c7 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 12 Jul 2017 14:35:46 -0700 Subject: kernel/watchdog: split up config options Split SOFTLOCKUP_DETECTOR from LOCKUP_DETECTOR, and split HARDLOCKUP_DETECTOR_PERF from HARDLOCKUP_DETECTOR. LOCKUP_DETECTOR implies the general boot, sysctl, and programming interfaces for the lockup detectors. An architecture that wants to use a hard lockup detector must define HAVE_HARDLOCKUP_DETECTOR_PERF or HAVE_HARDLOCKUP_DETECTOR_ARCH. Alternatively an arch can define HAVE_NMI_WATCHDOG, which provides the minimum arch_touch_nmi_watchdog, and it otherwise does its own thing and does not implement the LOCKUP_DETECTOR interfaces. sparc is unusual in that it has started to implement some of the interfaces, but not fully yet. It should probably be converted to a full HAVE_HARDLOCKUP_DETECTOR_ARCH. [npiggin@gmail.com: fix] Link: http://lkml.kernel.org/r/20170617223522.66c0ad88@roar.ozlabs.ibm.com Link: http://lkml.kernel.org/r/20170616065715.18390-4-npiggin@gmail.com Signed-off-by: Nicholas Piggin Reviewed-by: Don Zickus Reviewed-by: Babu Moger Tested-by: Babu Moger [sparc] Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/Kconfig | 25 ++++- arch/powerpc/Kconfig | 1 + arch/powerpc/kernel/setup_64.c | 2 +- arch/x86/Kconfig | 1 + arch/x86/kernel/apic/hw_nmi.c | 2 +- include/linux/nmi.h | 29 +++-- kernel/Makefile | 2 +- kernel/sysctl.c | 31 +++--- kernel/watchdog.c | 243 +++++++++++++++++++++++++++-------------- kernel/watchdog_hld.c | 32 ------ lib/Kconfig.debug | 45 +++++--- 11 files changed, 251 insertions(+), 162 deletions(-) diff --git a/arch/Kconfig b/arch/Kconfig index cae0958a2298..fb9bd7d36b05 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -198,9 +198,6 @@ config HAVE_KPROBES_ON_FTRACE config HAVE_NMI bool -config HAVE_NMI_WATCHDOG - depends on HAVE_NMI - bool # # An arch should select this if it provides all these things: # @@ -288,6 +285,28 @@ config HAVE_PERF_EVENTS_NMI subsystem. Also has support for calculating CPU cycle events to determine how many clock cycles in a given period. +config HAVE_HARDLOCKUP_DETECTOR_PERF + bool + depends on HAVE_PERF_EVENTS_NMI + help + The arch chooses to use the generic perf-NMI-based hardlockup + detector. Must define HAVE_PERF_EVENTS_NMI. + +config HAVE_NMI_WATCHDOG + depends on HAVE_NMI + bool + help + The arch provides a low level NMI watchdog. It provides + asm/nmi.h, and defines its own arch_touch_nmi_watchdog(). + +config HAVE_HARDLOCKUP_DETECTOR_ARCH + bool + select HAVE_NMI_WATCHDOG + help + The arch chooses to provide its own hardlockup detector, which is + a superset of the HAVE_NMI_WATCHDOG. It also conforms to config + interfaces and parameters provided by hardlockup detector subsystem. + config HAVE_PERF_REGS bool help diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 7177a3f4f418..63ed758e1d20 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -197,6 +197,7 @@ config PPC select HAVE_OPTPROBES if PPC64 select HAVE_PERF_EVENTS select HAVE_PERF_EVENTS_NMI if PPC64 + select HAVE_HARDLOCKUP_DETECTOR_PERF if HAVE_PERF_EVENTS_NMI select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select HAVE_RCU_TABLE_FREE if SMP diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 4640f6d64f8b..074a075a9cdb 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -752,7 +752,7 @@ struct ppc_pci_io ppc_pci_io; EXPORT_SYMBOL(ppc_pci_io); #endif -#ifdef CONFIG_HARDLOCKUP_DETECTOR +#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF u64 hw_nmi_get_sample_period(int watchdog_thresh) { return ppc_proc_freq * watchdog_thresh; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 94a18681353d..3d2b8ce54e00 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -162,6 +162,7 @@ config X86 select HAVE_PCSPKR_PLATFORM select HAVE_PERF_EVENTS select HAVE_PERF_EVENTS_NMI + select HAVE_HARDLOCKUP_DETECTOR_PERF if HAVE_PERF_EVENTS_NMI select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select HAVE_REGS_AND_STACK_ACCESS_API diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index c73c9fb281e1..d6f387780849 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -19,7 +19,7 @@ #include #include -#ifdef CONFIG_HARDLOCKUP_DETECTOR +#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF u64 hw_nmi_get_sample_period(int watchdog_thresh) { return (u64)(cpu_khz) * 1000 * watchdog_thresh; diff --git a/include/linux/nmi.h b/include/linux/nmi.h index bd387ef8bccd..8aa01fd859fb 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -11,13 +11,21 @@ #endif #ifdef CONFIG_LOCKUP_DETECTOR +void lockup_detector_init(void); +#else +static inline void lockup_detector_init(void) +{ +} +#endif + +#ifdef CONFIG_SOFTLOCKUP_DETECTOR extern void touch_softlockup_watchdog_sched(void); extern void touch_softlockup_watchdog(void); extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); extern unsigned int softlockup_panic; -extern unsigned int hardlockup_panic; -void lockup_detector_init(void); +extern int soft_watchdog_enabled; +extern atomic_t watchdog_park_in_progress; #else static inline void touch_softlockup_watchdog_sched(void) { @@ -31,9 +39,6 @@ static inline void touch_softlockup_watchdog_sync(void) static inline void touch_all_softlockup_watchdogs(void) { } -static inline void lockup_detector_init(void) -{ -} #endif #ifdef CONFIG_DETECT_HUNG_TASK @@ -63,15 +68,18 @@ static inline void reset_hung_task_detector(void) #if defined(CONFIG_HARDLOCKUP_DETECTOR) extern void hardlockup_detector_disable(void); +extern unsigned int hardlockup_panic; #else static inline void hardlockup_detector_disable(void) {} #endif -#if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG) +#if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF) extern void arch_touch_nmi_watchdog(void); #else +#if !defined(CONFIG_HAVE_NMI_WATCHDOG) static inline void arch_touch_nmi_watchdog(void) {} #endif +#endif /** * touch_nmi_watchdog - restart NMI watchdog timeout. @@ -141,15 +149,18 @@ static inline bool trigger_single_cpu_backtrace(int cpu) } #endif -#ifdef CONFIG_LOCKUP_DETECTOR +#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF u64 hw_nmi_get_sample_period(int watchdog_thresh); +#endif + +#ifdef CONFIG_LOCKUP_DETECTOR extern int nmi_watchdog_enabled; -extern int soft_watchdog_enabled; extern int watchdog_user_enabled; extern int watchdog_thresh; extern unsigned long watchdog_enabled; +extern struct cpumask watchdog_cpumask; extern unsigned long *watchdog_cpumask_bits; -extern atomic_t watchdog_park_in_progress; +extern int __read_mostly watchdog_suspended; #ifdef CONFIG_SMP extern int sysctl_softlockup_all_cpu_backtrace; extern int sysctl_hardlockup_all_cpu_backtrace; diff --git a/kernel/Makefile b/kernel/Makefile index 72aa080f91f0..4cb8e8b23c6e 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -82,7 +82,7 @@ obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_KGDB) += debug/ obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o -obj-$(CONFIG_HARDLOCKUP_DETECTOR) += watchdog_hld.o +obj-$(CONFIG_HARDLOCKUP_DETECTOR_PERF) += watchdog_hld.o obj-$(CONFIG_SECCOMP) += seccomp.o obj-$(CONFIG_RELAY) += relay.o obj-$(CONFIG_SYSCTL) += utsname_sysctl.o diff --git a/kernel/sysctl.c b/kernel/sysctl.c index df9f2a367882..6648fbbb8157 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -900,6 +900,14 @@ static struct ctl_table kern_table[] = { .extra2 = &zero, #endif }, + { + .procname = "watchdog_cpumask", + .data = &watchdog_cpumask_bits, + .maxlen = NR_CPUS, + .mode = 0644, + .proc_handler = proc_watchdog_cpumask, + }, +#ifdef CONFIG_SOFTLOCKUP_DETECTOR { .procname = "soft_watchdog", .data = &soft_watchdog_enabled, @@ -909,13 +917,6 @@ static struct ctl_table kern_table[] = { .extra1 = &zero, .extra2 = &one, }, - { - .procname = "watchdog_cpumask", - .data = &watchdog_cpumask_bits, - .maxlen = NR_CPUS, - .mode = 0644, - .proc_handler = proc_watchdog_cpumask, - }, { .procname = "softlockup_panic", .data = &softlockup_panic, @@ -925,27 +926,29 @@ static struct ctl_table kern_table[] = { .extra1 = &zero, .extra2 = &one, }, -#ifdef CONFIG_HARDLOCKUP_DETECTOR +#ifdef CONFIG_SMP { - .procname = "hardlockup_panic", - .data = &hardlockup_panic, + .procname = "softlockup_all_cpu_backtrace", + .data = &sysctl_softlockup_all_cpu_backtrace, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &one, }, +#endif /* CONFIG_SMP */ #endif -#ifdef CONFIG_SMP +#ifdef CONFIG_HARDLOCKUP_DETECTOR { - .procname = "softlockup_all_cpu_backtrace", - .data = &sysctl_softlockup_all_cpu_backtrace, + .procname = "hardlockup_panic", + .data = &hardlockup_panic, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &one, }, +#ifdef CONFIG_SMP { .procname = "hardlockup_all_cpu_backtrace", .data = &sysctl_hardlockup_all_cpu_backtrace, @@ -957,6 +960,8 @@ static struct ctl_table kern_table[] = { }, #endif /* CONFIG_SMP */ #endif +#endif + #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) { .procname = "unknown_nmi_panic", diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 03e0b69bb5bf..1fba9c3d66dc 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -29,15 +29,58 @@ #include #include +/* Watchdog configuration */ static DEFINE_MUTEX(watchdog_proc_mutex); -#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) -unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED|NMI_WATCHDOG_ENABLED; +int __read_mostly nmi_watchdog_enabled; + +#if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG) +unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED | + NMI_WATCHDOG_ENABLED; #else unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED; #endif -int __read_mostly nmi_watchdog_enabled; + +#ifdef CONFIG_HARDLOCKUP_DETECTOR +/* boot commands */ +/* + * Should we panic when a soft-lockup or hard-lockup occurs: + */ +unsigned int __read_mostly hardlockup_panic = + CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE; +/* + * We may not want to enable hard lockup detection by default in all cases, + * for example when running the kernel as a guest on a hypervisor. In these + * cases this function can be called to disable hard lockup detection. This + * function should only be executed once by the boot processor before the + * kernel command line parameters are parsed, because otherwise it is not + * possible to override this in hardlockup_panic_setup(). + */ +void hardlockup_detector_disable(void) +{ + watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; +} + +static int __init hardlockup_panic_setup(char *str) +{ + if (!strncmp(str, "panic", 5)) + hardlockup_panic = 1; + else if (!strncmp(str, "nopanic", 7)) + hardlockup_panic = 0; + else if (!strncmp(str, "0", 1)) + watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; + else if (!strncmp(str, "1", 1)) + watchdog_enabled |= NMI_WATCHDOG_ENABLED; + return 1; +} +__setup("nmi_watchdog=", hardlockup_panic_setup); + +#endif + +#ifdef CONFIG_SOFTLOCKUP_DETECTOR int __read_mostly soft_watchdog_enabled; +#endif + int __read_mostly watchdog_user_enabled; int __read_mostly watchdog_thresh = 10; @@ -45,15 +88,9 @@ int __read_mostly watchdog_thresh = 10; int __read_mostly sysctl_softlockup_all_cpu_backtrace; int __read_mostly sysctl_hardlockup_all_cpu_backtrace; #endif -static struct cpumask watchdog_cpumask __read_mostly; +struct cpumask watchdog_cpumask __read_mostly; unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); -/* Helper for online, unparked cpus. */ -#define for_each_watchdog_cpu(cpu) \ - for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask) - -atomic_t watchdog_park_in_progress = ATOMIC_INIT(0); - /* * The 'watchdog_running' variable is set to 1 when the watchdog threads * are registered/started and is set to 0 when the watchdog threads are @@ -72,7 +109,27 @@ static int __read_mostly watchdog_running; * of 'watchdog_running' cannot change while the watchdog is deactivated * temporarily (see related code in 'proc' handlers). */ -static int __read_mostly watchdog_suspended; +int __read_mostly watchdog_suspended; + +/* + * These functions can be overridden if an architecture implements its + * own hardlockup detector. + */ +int __weak watchdog_nmi_enable(unsigned int cpu) +{ + return 0; +} +void __weak watchdog_nmi_disable(unsigned int cpu) +{ +} + +#ifdef CONFIG_SOFTLOCKUP_DETECTOR + +/* Helper for online, unparked cpus. */ +#define for_each_watchdog_cpu(cpu) \ + for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask) + +atomic_t watchdog_park_in_progress = ATOMIC_INIT(0); static u64 __read_mostly sample_period; @@ -120,6 +177,7 @@ static int __init softlockup_all_cpu_backtrace_setup(char *str) return 1; } __setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup); +#ifdef CONFIG_HARDLOCKUP_DETECTOR static int __init hardlockup_all_cpu_backtrace_setup(char *str) { sysctl_hardlockup_all_cpu_backtrace = @@ -128,6 +186,7 @@ static int __init hardlockup_all_cpu_backtrace_setup(char *str) } __setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup); #endif +#endif /* * Hard-lockup warnings should be triggered after just a few seconds. Soft- @@ -213,18 +272,6 @@ void touch_softlockup_watchdog_sync(void) __this_cpu_write(watchdog_touch_ts, 0); } -/* watchdog detector functions */ -bool is_hardlockup(void) -{ - unsigned long hrint = __this_cpu_read(hrtimer_interrupts); - - if (__this_cpu_read(hrtimer_interrupts_saved) == hrint) - return true; - - __this_cpu_write(hrtimer_interrupts_saved, hrint); - return false; -} - static int is_softlockup(unsigned long touch_ts) { unsigned long now = get_timestamp(); @@ -237,21 +284,21 @@ static int is_softlockup(unsigned long touch_ts) return 0; } -static void watchdog_interrupt_count(void) +/* watchdog detector functions */ +bool is_hardlockup(void) { - __this_cpu_inc(hrtimer_interrupts); -} + unsigned long hrint = __this_cpu_read(hrtimer_interrupts); -/* - * These two functions are mostly architecture specific - * defining them as weak here. - */ -int __weak watchdog_nmi_enable(unsigned int cpu) -{ - return 0; + if (__this_cpu_read(hrtimer_interrupts_saved) == hrint) + return true; + + __this_cpu_write(hrtimer_interrupts_saved, hrint); + return false; } -void __weak watchdog_nmi_disable(unsigned int cpu) + +static void watchdog_interrupt_count(void) { + __this_cpu_inc(hrtimer_interrupts); } static int watchdog_enable_all_cpus(void); @@ -502,57 +549,6 @@ static void watchdog_unpark_threads(void) kthread_unpark(per_cpu(softlockup_watchdog, cpu)); } -/* - * Suspend the hard and soft lockup detector by parking the watchdog threads. - */ -int lockup_detector_suspend(void) -{ - int ret = 0; - - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); - /* - * Multiple suspend requests can be active in parallel (counted by - * the 'watchdog_suspended' variable). If the watchdog threads are - * running, the first caller takes care that they will be parked. - * The state of 'watchdog_running' cannot change while a suspend - * request is active (see related code in 'proc' handlers). - */ - if (watchdog_running && !watchdog_suspended) - ret = watchdog_park_threads(); - - if (ret == 0) - watchdog_suspended++; - else { - watchdog_disable_all_cpus(); - pr_err("Failed to suspend lockup detectors, disabled\n"); - watchdog_enabled = 0; - } - - mutex_unlock(&watchdog_proc_mutex); - - return ret; -} - -/* - * Resume the hard and soft lockup detector by unparking the watchdog threads. - */ -void lockup_detector_resume(void) -{ - mutex_lock(&watchdog_proc_mutex); - - watchdog_suspended--; - /* - * The watchdog threads are unparked if they were previously running - * and if there is no more active suspend request. - */ - if (watchdog_running && !watchdog_suspended) - watchdog_unpark_threads(); - - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); -} - static int update_watchdog_all_cpus(void) { int ret; @@ -604,6 +600,81 @@ static void watchdog_disable_all_cpus(void) } } +#else /* SOFTLOCKUP */ +static int watchdog_park_threads(void) +{ + return 0; +} + +static void watchdog_unpark_threads(void) +{ +} + +static int watchdog_enable_all_cpus(void) +{ + return 0; +} + +static void watchdog_disable_all_cpus(void) +{ +} + +static void set_sample_period(void) +{ +} +#endif /* SOFTLOCKUP */ + +/* + * Suspend the hard and soft lockup detector by parking the watchdog threads. + */ +int lockup_detector_suspend(void) +{ + int ret = 0; + + get_online_cpus(); + mutex_lock(&watchdog_proc_mutex); + /* + * Multiple suspend requests can be active in parallel (counted by + * the 'watchdog_suspended' variable). If the watchdog threads are + * running, the first caller takes care that they will be parked. + * The state of 'watchdog_running' cannot change while a suspend + * request is active (see related code in 'proc' handlers). + */ + if (watchdog_running && !watchdog_suspended) + ret = watchdog_park_threads(); + + if (ret == 0) + watchdog_suspended++; + else { + watchdog_disable_all_cpus(); + pr_err("Failed to suspend lockup detectors, disabled\n"); + watchdog_enabled = 0; + } + + mutex_unlock(&watchdog_proc_mutex); + + return ret; +} + +/* + * Resume the hard and soft lockup detector by unparking the watchdog threads. + */ +void lockup_detector_resume(void) +{ + mutex_lock(&watchdog_proc_mutex); + + watchdog_suspended--; + /* + * The watchdog threads are unparked if they were previously running + * and if there is no more active suspend request. + */ + if (watchdog_running && !watchdog_suspended) + watchdog_unpark_threads(); + + mutex_unlock(&watchdog_proc_mutex); + put_online_cpus(); +} + #ifdef CONFIG_SYSCTL /* @@ -810,9 +881,11 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, * a temporary cpumask, so we are likely not in a * position to do much else to make things better. */ +#ifdef CONFIG_SOFTLOCKUP_DETECTOR if (smpboot_update_cpumask_percpu_thread( &watchdog_threads, &watchdog_cpumask) != 0) pr_err("cpumask update failed\n"); +#endif } } out: diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 90d688df6ce1..295a0d84934c 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -22,39 +22,7 @@ static DEFINE_PER_CPU(bool, hard_watchdog_warn); static DEFINE_PER_CPU(bool, watchdog_nmi_touch); static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); -/* boot commands */ -/* - * Should we panic when a soft-lockup or hard-lockup occurs: - */ -unsigned int __read_mostly hardlockup_panic = - CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE; static unsigned long hardlockup_allcpu_dumped; -/* - * We may not want to enable hard lockup detection by default in all cases, - * for example when running the kernel as a guest on a hypervisor. In these - * cases this function can be called to disable hard lockup detection. This - * function should only be executed once by the boot processor before the - * kernel command line parameters are parsed, because otherwise it is not - * possible to override this in hardlockup_panic_setup(). - */ -void hardlockup_detector_disable(void) -{ - watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; -} - -static int __init hardlockup_panic_setup(char *str) -{ - if (!strncmp(str, "panic", 5)) - hardlockup_panic = 1; - else if (!strncmp(str, "nopanic", 7)) - hardlockup_panic = 0; - else if (!strncmp(str, "0", 1)) - watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; - else if (!strncmp(str, "1", 1)) - watchdog_enabled |= NMI_WATCHDOG_ENABLED; - return 1; -} -__setup("nmi_watchdog=", hardlockup_panic_setup); void arch_touch_nmi_watchdog(void) { diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index f28f4252e54a..b0d01c6d4e03 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -778,34 +778,45 @@ config DEBUG_SHIRQ menu "Debug Lockups and Hangs" config LOCKUP_DETECTOR - bool "Detect Hard and Soft Lockups" + bool + +config SOFTLOCKUP_DETECTOR + bool "Detect Soft Lockups" depends on DEBUG_KERNEL && !S390 + select LOCKUP_DETECTOR help Say Y here to enable the kernel to act as a watchdog to detect - hard and soft lockups. + soft lockups. Softlockups are bugs that cause the kernel to loop in kernel mode for more than 20 seconds, without giving other tasks a chance to run. The current stack trace is displayed upon detection and the system will stay locked up. +config HARDLOCKUP_DETECTOR_PERF + bool + select SOFTLOCKUP_DETECTOR + +# +# arch/ can define HAVE_HARDLOCKUP_DETECTOR_ARCH to provide their own hard +# lockup detector rather than the perf based detector. +# +config HARDLOCKUP_DETECTOR + bool "Detect Hard Lockups" + depends on DEBUG_KERNEL && !S390 + depends on HAVE_HARDLOCKUP_DETECTOR_PERF || HAVE_HARDLOCKUP_DETECTOR_ARCH + select LOCKUP_DETECTOR + select HARDLOCKUP_DETECTOR_PERF if HAVE_HARDLOCKUP_DETECTOR_PERF + select HARDLOCKUP_DETECTOR_ARCH if HAVE_HARDLOCKUP_DETECTOR_ARCH + help + Say Y here to enable the kernel to act as a watchdog to detect + hard lockups. + Hardlockups are bugs that cause the CPU to loop in kernel mode for more than 10 seconds, without letting other interrupts have a chance to run. The current stack trace is displayed upon detection and the system will stay locked up. - The overhead should be minimal. A periodic hrtimer runs to - generate interrupts and kick the watchdog task every 4 seconds. - An NMI is generated every 10 seconds or so to check for hardlockups. - - The frequency of hrtimer and NMI events and the soft and hard lockup - thresholds can be controlled through the sysctl watchdog_thresh. - -config HARDLOCKUP_DETECTOR - def_bool y - depends on LOCKUP_DETECTOR && !HAVE_NMI_WATCHDOG - depends on PERF_EVENTS && HAVE_PERF_EVENTS_NMI - config BOOTPARAM_HARDLOCKUP_PANIC bool "Panic (Reboot) On Hard Lockups" depends on HARDLOCKUP_DETECTOR @@ -826,7 +837,7 @@ config BOOTPARAM_HARDLOCKUP_PANIC_VALUE config BOOTPARAM_SOFTLOCKUP_PANIC bool "Panic (Reboot) On Soft Lockups" - depends on LOCKUP_DETECTOR + depends on SOFTLOCKUP_DETECTOR help Say Y here to enable the kernel to panic on "soft lockups", which are bugs that cause the kernel to loop in kernel @@ -843,7 +854,7 @@ config BOOTPARAM_SOFTLOCKUP_PANIC config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE int - depends on LOCKUP_DETECTOR + depends on SOFTLOCKUP_DETECTOR range 0 1 default 0 if !BOOTPARAM_SOFTLOCKUP_PANIC default 1 if BOOTPARAM_SOFTLOCKUP_PANIC @@ -851,7 +862,7 @@ config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE config DETECT_HUNG_TASK bool "Detect Hung Tasks" depends on DEBUG_KERNEL - default LOCKUP_DETECTOR + default SOFTLOCKUP_DETECTOR help Say Y here to enable the kernel to detect "hung tasks", which are bugs that cause the task to be stuck in -- cgit v1.2.3-59-g8ed1b From a10a842ff81a7e3810817b3b04e4c432b6191e21 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 12 Jul 2017 14:35:49 -0700 Subject: kernel/watchdog: provide watchdog_nmi_reconfigure() for arch watchdogs After reconfiguring watchdog sysctls etc., architecture specific watchdogs may not get all their parameters updated. watchdog_nmi_reconfigure() can be implemented to pull the new values in and set the arch NMI watchdog. [npiggin@gmail.com: add code comments] Link: http://lkml.kernel.org/r/20170617125933.774d3858@roar.ozlabs.ibm.com [arnd@arndb.de: hide unused function] Link: http://lkml.kernel.org/r/20170620204854.966601-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170616065715.18390-5-npiggin@gmail.com Signed-off-by: Nicholas Piggin Signed-off-by: Arnd Bergmann Reviewed-by: Don Zickus Tested-by: Babu Moger [sparc] Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/watchdog.c | 48 ++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 44 insertions(+), 4 deletions(-) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 1fba9c3d66dc..cabe3e9fb620 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -114,6 +114,10 @@ int __read_mostly watchdog_suspended; /* * These functions can be overridden if an architecture implements its * own hardlockup detector. + * + * watchdog_nmi_enable/disable can be implemented to start and stop when + * softlockup watchdog threads start and stop. The arch must select the + * SOFTLOCKUP_DETECTOR Kconfig. */ int __weak watchdog_nmi_enable(unsigned int cpu) { @@ -123,6 +127,22 @@ void __weak watchdog_nmi_disable(unsigned int cpu) { } +/* + * watchdog_nmi_reconfigure can be implemented to be notified after any + * watchdog configuration change. The arch hardlockup watchdog should + * respond to the following variables: + * - nmi_watchdog_enabled + * - watchdog_thresh + * - watchdog_cpumask + * - sysctl_hardlockup_all_cpu_backtrace + * - hardlockup_panic + * - watchdog_suspended + */ +void __weak watchdog_nmi_reconfigure(void) +{ +} + + #ifdef CONFIG_SOFTLOCKUP_DETECTOR /* Helper for online, unparked cpus. */ @@ -600,6 +620,14 @@ static void watchdog_disable_all_cpus(void) } } +#ifdef CONFIG_SYSCTL +static int watchdog_update_cpus(void) +{ + return smpboot_update_cpumask_percpu_thread( + &watchdog_threads, &watchdog_cpumask); +} +#endif + #else /* SOFTLOCKUP */ static int watchdog_park_threads(void) { @@ -619,6 +647,13 @@ static void watchdog_disable_all_cpus(void) { } +#ifdef CONFIG_SYSCTL +static int watchdog_update_cpus(void) +{ + return 0; +} +#endif + static void set_sample_period(void) { } @@ -651,6 +686,8 @@ int lockup_detector_suspend(void) watchdog_enabled = 0; } + watchdog_nmi_reconfigure(); + mutex_unlock(&watchdog_proc_mutex); return ret; @@ -671,6 +708,8 @@ void lockup_detector_resume(void) if (watchdog_running && !watchdog_suspended) watchdog_unpark_threads(); + watchdog_nmi_reconfigure(); + mutex_unlock(&watchdog_proc_mutex); put_online_cpus(); } @@ -696,6 +735,8 @@ static int proc_watchdog_update(void) else watchdog_disable_all_cpus(); + watchdog_nmi_reconfigure(); + return err; } @@ -881,12 +922,11 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, * a temporary cpumask, so we are likely not in a * position to do much else to make things better. */ -#ifdef CONFIG_SOFTLOCKUP_DETECTOR - if (smpboot_update_cpumask_percpu_thread( - &watchdog_threads, &watchdog_cpumask) != 0) + if (watchdog_update_cpus() != 0) pr_err("cpumask update failed\n"); -#endif } + + watchdog_nmi_reconfigure(); } out: mutex_unlock(&watchdog_proc_mutex); -- cgit v1.2.3-59-g8ed1b From 2104180a53698df5aec35aed5f840a26ade0551d Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 12 Jul 2017 14:35:52 -0700 Subject: powerpc/64s: implement arch-specific hardlockup watchdog Implement an arch-speicfic watchdog rather than use the perf-based hardlockup detector. The new watchdog takes the soft-NMI directly, rather than going through perf. Perf interrupts are to be made maskable in future, so that would prevent the perf detector from working in those regions. Additionally, implement a SMP based detector where all CPUs watch one another by pinging a shared cpumask. This is because powerpc Book3S does not have a true periodic local NMI, but some platforms do implement a true NMI IPI. If a CPU is stuck with interrupts hard disabled, the soft-NMI watchdog does not work, but the SMP watchdog will. Even on platforms without a true NMI IPI to get a good trace from the stuck CPU, other CPUs will notice the lockup sufficiently to report it and panic. [npiggin@gmail.com: honor watchdog disable at boot/hotplug] Link: http://lkml.kernel.org/r/20170621001346.5bb337c9@roar.ozlabs.ibm.com [npiggin@gmail.com: fix false positive warning at CPU unplug] Link: http://lkml.kernel.org/r/20170630080740.20766-1-npiggin@gmail.com [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/20170616065715.18390-6-npiggin@gmail.com Signed-off-by: Nicholas Piggin Reviewed-by: Don Zickus Tested-by: Babu Moger [sparc] Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/Kconfig | 7 +- arch/powerpc/include/asm/nmi.h | 11 + arch/powerpc/include/asm/smp.h | 2 + arch/powerpc/kernel/Makefile | 1 + arch/powerpc/kernel/exceptions-64s.S | 30 ++- arch/powerpc/kernel/kvm.c | 7 + arch/powerpc/kernel/setup_64.c | 19 -- arch/powerpc/kernel/smp.c | 20 +- arch/powerpc/kernel/watchdog.c | 386 +++++++++++++++++++++++++++++++++++ 9 files changed, 458 insertions(+), 25 deletions(-) create mode 100644 arch/powerpc/kernel/watchdog.c diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 63ed758e1d20..fce2f4f20891 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -82,7 +82,7 @@ config NR_IRQS config NMI_IPI bool - depends on SMP && (DEBUGGER || KEXEC_CORE) + depends on SMP && (DEBUGGER || KEXEC_CORE || HARDLOCKUP_DETECTOR) default y config STACKTRACE_SUPPORT @@ -192,12 +192,13 @@ config PPC select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_MOD_ARCH_SPECIFIC - select HAVE_NMI if PERF_EVENTS + select HAVE_NMI if PERF_EVENTS || (PPC64 && PPC_BOOK3S) + select HAVE_HARDLOCKUP_DETECTOR_ARCH if (PPC64 && PPC_BOOK3S) select HAVE_OPROFILE select HAVE_OPTPROBES if PPC64 select HAVE_PERF_EVENTS select HAVE_PERF_EVENTS_NMI if PPC64 - select HAVE_HARDLOCKUP_DETECTOR_PERF if HAVE_PERF_EVENTS_NMI + select HAVE_HARDLOCKUP_DETECTOR_PERF if HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select HAVE_RCU_TABLE_FREE if SMP diff --git a/arch/powerpc/include/asm/nmi.h b/arch/powerpc/include/asm/nmi.h index ff1ccb375e60..6f8e79cd35d8 100644 --- a/arch/powerpc/include/asm/nmi.h +++ b/arch/powerpc/include/asm/nmi.h @@ -1,4 +1,15 @@ #ifndef _ASM_NMI_H #define _ASM_NMI_H +#ifdef CONFIG_HARDLOCKUP_DETECTOR +extern void arch_touch_nmi_watchdog(void); + +extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, + bool exclude_self); +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace + +#else +static inline void arch_touch_nmi_watchdog(void) {} +#endif + #endif /* _ASM_NMI_H */ diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index ebddb2111d87..8ea98504f900 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -55,6 +55,8 @@ struct smp_ops_t { int (*cpu_bootable)(unsigned int nr); }; +extern void smp_flush_nmi_ipi(u64 delay_us); +extern int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us); extern void smp_send_debugger_break(void); extern void start_secondary_resume(void); extern void smp_generic_give_timebase(void); diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 0845eebc5af3..4aa7c147e447 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -38,6 +38,7 @@ obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \ signal_64.o ptrace32.o \ paca.o nvram_64.o firmware.o obj-$(CONFIG_VDSO32) += vdso32/ +obj-$(CONFIG_HARDLOCKUP_DETECTOR) += watchdog.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 4c18a5fbb4bb..e6d8354d79ef 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1314,6 +1314,31 @@ EXC_REAL_NONE(0x1800, 0x100) EXC_VIRT_NONE(0x5800, 0x100) #endif +#if defined(CONFIG_HARDLOCKUP_DETECTOR) && defined(CONFIG_HAVE_HARDLOCKUP_DETECTOR_ARCH) + +#define MASKED_DEC_HANDLER_LABEL 3f + +#define MASKED_DEC_HANDLER(_H) \ +3: /* soft-nmi */ \ + std r12,PACA_EXGEN+EX_R12(r13); \ + GET_SCRATCH0(r10); \ + std r10,PACA_EXGEN+EX_R13(r13); \ + EXCEPTION_PROLOG_PSERIES_1(soft_nmi_common, _H) + +EXC_COMMON_BEGIN(soft_nmi_common) + mr r10,r1 + ld r1,PACAEMERGSP(r13) + ld r1,PACA_NMI_EMERG_SP(r13) + subi r1,r1,INT_FRAME_SIZE + EXCEPTION_COMMON_NORET_STACK(PACA_EXGEN, 0x900, + system_reset, soft_nmi_interrupt, + ADD_NVGPRS;ADD_RECONCILE) + b ret_from_except + +#else +#define MASKED_DEC_HANDLER_LABEL 2f /* normal return */ +#define MASKED_DEC_HANDLER(_H) +#endif /* * An interrupt came in while soft-disabled. We set paca->irq_happened, then: @@ -1336,7 +1361,7 @@ masked_##_H##interrupt: \ lis r10,0x7fff; \ ori r10,r10,0xffff; \ mtspr SPRN_DEC,r10; \ - b 2f; \ + b MASKED_DEC_HANDLER_LABEL; \ 1: cmpwi r10,PACA_IRQ_DBELL; \ beq 2f; \ cmpwi r10,PACA_IRQ_HMI; \ @@ -1351,7 +1376,8 @@ masked_##_H##interrupt: \ ld r11,PACA_EXGEN+EX_R11(r13); \ GET_SCRATCH0(r13); \ ##_H##rfid; \ - b . + b .; \ + MASKED_DEC_HANDLER(_H) /* * Real mode exceptions actually use this too, but alternate diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index 9ad37f827a97..1086ea37c832 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -25,6 +25,7 @@ #include #include #include +#include /* hardlockup_detector_disable() */ #include #include @@ -718,6 +719,12 @@ static __init void kvm_free_tmp(void) static int __init kvm_guest_init(void) { + /* + * The hardlockup detector is likely to get false positives in + * KVM guests, so disable it by default. + */ + hardlockup_detector_disable(); + if (!kvm_para_available()) goto free_tmp; diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 074a075a9cdb..af23d4b576ec 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -751,22 +751,3 @@ unsigned long memory_block_size_bytes(void) struct ppc_pci_io ppc_pci_io; EXPORT_SYMBOL(ppc_pci_io); #endif - -#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF -u64 hw_nmi_get_sample_period(int watchdog_thresh) -{ - return ppc_proc_freq * watchdog_thresh; -} - -/* - * The hardlockup detector breaks PMU event based branches and is likely - * to get false positives in KVM guests, so disable it by default. - */ -static int __init disable_hardlockup_detector(void) -{ - hardlockup_detector_disable(); - - return 0; -} -early_initcall(disable_hardlockup_detector); -#endif diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index c6b8bace1766..997c88d54acf 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -435,13 +435,31 @@ static void do_smp_send_nmi_ipi(int cpu) } } +void smp_flush_nmi_ipi(u64 delay_us) +{ + unsigned long flags; + + nmi_ipi_lock_start(&flags); + while (nmi_ipi_busy_count) { + nmi_ipi_unlock_end(&flags); + udelay(1); + if (delay_us) { + delay_us--; + if (!delay_us) + return; + } + nmi_ipi_lock_start(&flags); + } + nmi_ipi_unlock_end(&flags); +} + /* * - cpu is the target CPU (must not be this CPU), or NMI_IPI_ALL_OTHERS. * - fn is the target callback function. * - delay_us > 0 is the delay before giving up waiting for targets to * enter the handler, == 0 specifies indefinite delay. */ -static int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us) +int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us) { unsigned long flags; int me = raw_smp_processor_id(); diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c new file mode 100644 index 000000000000..b67f8b03a32d --- /dev/null +++ b/arch/powerpc/kernel/watchdog.c @@ -0,0 +1,386 @@ +/* + * Watchdog support on powerpc systems. + * + * Copyright 2017, IBM Corporation. + * + * This uses code from arch/sparc/kernel/nmi.c and kernel/watchdog.c + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +/* + * The watchdog has a simple timer that runs on each CPU, once per timer + * period. This is the heartbeat. + * + * Then there are checks to see if the heartbeat has not triggered on a CPU + * for the panic timeout period. Currently the watchdog only supports an + * SMP check, so the heartbeat only turns on when we have 2 or more CPUs. + * + * This is not an NMI watchdog, but Linux uses that name for a generic + * watchdog in some cases, so NMI gets used in some places. + */ + +static cpumask_t wd_cpus_enabled __read_mostly; + +static u64 wd_panic_timeout_tb __read_mostly; /* timebase ticks until panic */ +static u64 wd_smp_panic_timeout_tb __read_mostly; /* panic other CPUs */ + +static u64 wd_timer_period_ms __read_mostly; /* interval between heartbeat */ + +static DEFINE_PER_CPU(struct timer_list, wd_timer); +static DEFINE_PER_CPU(u64, wd_timer_tb); + +/* + * These are for the SMP checker. CPUs clear their pending bit in their + * heartbeat. If the bitmask becomes empty, the time is noted and the + * bitmask is refilled. + * + * All CPUs clear their bit in the pending mask every timer period. + * Once all have cleared, the time is noted and the bits are reset. + * If the time since all clear was greater than the panic timeout, + * we can panic with the list of stuck CPUs. + * + * This will work best with NMI IPIs for crash code so the stuck CPUs + * can be pulled out to get their backtraces. + */ +static unsigned long __wd_smp_lock; +static cpumask_t wd_smp_cpus_pending; +static cpumask_t wd_smp_cpus_stuck; +static u64 wd_smp_last_reset_tb; + +static inline void wd_smp_lock(unsigned long *flags) +{ + /* + * Avoid locking layers if possible. + * This may be called from low level interrupt handlers at some + * point in future. + */ + local_irq_save(*flags); + while (unlikely(test_and_set_bit_lock(0, &__wd_smp_lock))) + cpu_relax(); +} + +static inline void wd_smp_unlock(unsigned long *flags) +{ + clear_bit_unlock(0, &__wd_smp_lock); + local_irq_restore(*flags); +} + +static void wd_lockup_ipi(struct pt_regs *regs) +{ + pr_emerg("Watchdog CPU:%d Hard LOCKUP\n", raw_smp_processor_id()); + print_modules(); + print_irqtrace_events(current); + if (regs) + show_regs(regs); + else + dump_stack(); + + if (hardlockup_panic) + nmi_panic(regs, "Hard LOCKUP"); +} + +static void set_cpu_stuck(int cpu, u64 tb) +{ + cpumask_set_cpu(cpu, &wd_smp_cpus_stuck); + cpumask_clear_cpu(cpu, &wd_smp_cpus_pending); + if (cpumask_empty(&wd_smp_cpus_pending)) { + wd_smp_last_reset_tb = tb; + cpumask_andnot(&wd_smp_cpus_pending, + &wd_cpus_enabled, + &wd_smp_cpus_stuck); + } +} + +static void watchdog_smp_panic(int cpu, u64 tb) +{ + unsigned long flags; + int c; + + wd_smp_lock(&flags); + /* Double check some things under lock */ + if ((s64)(tb - wd_smp_last_reset_tb) < (s64)wd_smp_panic_timeout_tb) + goto out; + if (cpumask_test_cpu(cpu, &wd_smp_cpus_pending)) + goto out; + if (cpumask_weight(&wd_smp_cpus_pending) == 0) + goto out; + + pr_emerg("Watchdog CPU:%d detected Hard LOCKUP other CPUS:%*pbl\n", + cpu, cpumask_pr_args(&wd_smp_cpus_pending)); + + /* + * Try to trigger the stuck CPUs. + */ + for_each_cpu(c, &wd_smp_cpus_pending) { + if (c == cpu) + continue; + smp_send_nmi_ipi(c, wd_lockup_ipi, 1000000); + } + smp_flush_nmi_ipi(1000000); + + /* Take the stuck CPU out of the watch group */ + for_each_cpu(c, &wd_smp_cpus_pending) + set_cpu_stuck(c, tb); + +out: + wd_smp_unlock(&flags); + + printk_safe_flush(); + /* + * printk_safe_flush() seems to require another print + * before anything actually goes out to console. + */ + if (sysctl_hardlockup_all_cpu_backtrace) + trigger_allbutself_cpu_backtrace(); + + if (hardlockup_panic) + nmi_panic(NULL, "Hard LOCKUP"); +} + +static void wd_smp_clear_cpu_pending(int cpu, u64 tb) +{ + if (!cpumask_test_cpu(cpu, &wd_smp_cpus_pending)) { + if (unlikely(cpumask_test_cpu(cpu, &wd_smp_cpus_stuck))) { + unsigned long flags; + + pr_emerg("Watchdog CPU:%d became unstuck\n", cpu); + wd_smp_lock(&flags); + cpumask_clear_cpu(cpu, &wd_smp_cpus_stuck); + wd_smp_unlock(&flags); + } + return; + } + cpumask_clear_cpu(cpu, &wd_smp_cpus_pending); + if (cpumask_empty(&wd_smp_cpus_pending)) { + unsigned long flags; + + wd_smp_lock(&flags); + if (cpumask_empty(&wd_smp_cpus_pending)) { + wd_smp_last_reset_tb = tb; + cpumask_andnot(&wd_smp_cpus_pending, + &wd_cpus_enabled, + &wd_smp_cpus_stuck); + } + wd_smp_unlock(&flags); + } +} + +static void watchdog_timer_interrupt(int cpu) +{ + u64 tb = get_tb(); + + per_cpu(wd_timer_tb, cpu) = tb; + + wd_smp_clear_cpu_pending(cpu, tb); + + if ((s64)(tb - wd_smp_last_reset_tb) >= (s64)wd_smp_panic_timeout_tb) + watchdog_smp_panic(cpu, tb); +} + +void soft_nmi_interrupt(struct pt_regs *regs) +{ + unsigned long flags; + int cpu = raw_smp_processor_id(); + u64 tb; + + if (!cpumask_test_cpu(cpu, &wd_cpus_enabled)) + return; + + nmi_enter(); + tb = get_tb(); + if (tb - per_cpu(wd_timer_tb, cpu) >= wd_panic_timeout_tb) { + per_cpu(wd_timer_tb, cpu) = tb; + + wd_smp_lock(&flags); + if (cpumask_test_cpu(cpu, &wd_smp_cpus_stuck)) { + wd_smp_unlock(&flags); + goto out; + } + set_cpu_stuck(cpu, tb); + + pr_emerg("Watchdog CPU:%d Hard LOCKUP\n", cpu); + print_modules(); + print_irqtrace_events(current); + if (regs) + show_regs(regs); + else + dump_stack(); + + wd_smp_unlock(&flags); + + if (sysctl_hardlockup_all_cpu_backtrace) + trigger_allbutself_cpu_backtrace(); + + if (hardlockup_panic) + nmi_panic(regs, "Hard LOCKUP"); + } + if (wd_panic_timeout_tb < 0x7fffffff) + mtspr(SPRN_DEC, wd_panic_timeout_tb); + +out: + nmi_exit(); +} + +static void wd_timer_reset(unsigned int cpu, struct timer_list *t) +{ + t->expires = jiffies + msecs_to_jiffies(wd_timer_period_ms); + if (wd_timer_period_ms > 1000) + t->expires = __round_jiffies_up(t->expires, cpu); + add_timer_on(t, cpu); +} + +static void wd_timer_fn(unsigned long data) +{ + struct timer_list *t = this_cpu_ptr(&wd_timer); + int cpu = smp_processor_id(); + + watchdog_timer_interrupt(cpu); + + wd_timer_reset(cpu, t); +} + +void arch_touch_nmi_watchdog(void) +{ + int cpu = smp_processor_id(); + + watchdog_timer_interrupt(cpu); +} +EXPORT_SYMBOL(arch_touch_nmi_watchdog); + +static void start_watchdog_timer_on(unsigned int cpu) +{ + struct timer_list *t = per_cpu_ptr(&wd_timer, cpu); + + per_cpu(wd_timer_tb, cpu) = get_tb(); + + setup_pinned_timer(t, wd_timer_fn, 0); + wd_timer_reset(cpu, t); +} + +static void stop_watchdog_timer_on(unsigned int cpu) +{ + struct timer_list *t = per_cpu_ptr(&wd_timer, cpu); + + del_timer_sync(t); +} + +static int start_wd_on_cpu(unsigned int cpu) +{ + if (cpumask_test_cpu(cpu, &wd_cpus_enabled)) { + WARN_ON(1); + return 0; + } + + if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) + return 0; + + if (watchdog_suspended) + return 0; + + if (!cpumask_test_cpu(cpu, &watchdog_cpumask)) + return 0; + + cpumask_set_cpu(cpu, &wd_cpus_enabled); + if (cpumask_weight(&wd_cpus_enabled) == 1) { + cpumask_set_cpu(cpu, &wd_smp_cpus_pending); + wd_smp_last_reset_tb = get_tb(); + } + smp_wmb(); + start_watchdog_timer_on(cpu); + + return 0; +} + +static int stop_wd_on_cpu(unsigned int cpu) +{ + if (!cpumask_test_cpu(cpu, &wd_cpus_enabled)) + return 0; /* Can happen in CPU unplug case */ + + stop_watchdog_timer_on(cpu); + + cpumask_clear_cpu(cpu, &wd_cpus_enabled); + wd_smp_clear_cpu_pending(cpu, get_tb()); + + return 0; +} + +static void watchdog_calc_timeouts(void) +{ + wd_panic_timeout_tb = watchdog_thresh * ppc_tb_freq; + + /* Have the SMP detector trigger a bit later */ + wd_smp_panic_timeout_tb = wd_panic_timeout_tb * 3 / 2; + + /* 2/5 is the factor that the perf based detector uses */ + wd_timer_period_ms = watchdog_thresh * 1000 * 2 / 5; +} + +void watchdog_nmi_reconfigure(void) +{ + int cpu; + + watchdog_calc_timeouts(); + + for_each_cpu(cpu, &wd_cpus_enabled) + stop_wd_on_cpu(cpu); + + for_each_cpu_and(cpu, cpu_online_mask, &watchdog_cpumask) + start_wd_on_cpu(cpu); +} + +/* + * This runs after lockup_detector_init() which sets up watchdog_cpumask. + */ +static int __init powerpc_watchdog_init(void) +{ + int err; + + watchdog_calc_timeouts(); + + err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "powerpc/watchdog:online", + start_wd_on_cpu, stop_wd_on_cpu); + if (err < 0) + pr_warn("Watchdog could not be initialized"); + + return 0; +} +arch_initcall(powerpc_watchdog_init); + +static void handle_backtrace_ipi(struct pt_regs *regs) +{ + nmi_cpu_backtrace(regs); +} + +static void raise_backtrace_ipi(cpumask_t *mask) +{ + unsigned int cpu; + + for_each_cpu(cpu, mask) { + if (cpu == smp_processor_id()) + handle_backtrace_ipi(NULL); + else + smp_send_nmi_ipi(cpu, handle_backtrace_ipi, 1000000); + } +} + +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) +{ + nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace_ipi); +} -- cgit v1.2.3-59-g8ed1b From 3e2c044a54e6b6373606f8ffad42a4a0759fcf3d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Jul 2017 14:35:55 -0700 Subject: efi: avoid fortify checks in EFI stub This avoids CONFIG_FORTIFY_SOURCE from being enabled during the EFI stub build, as adding a panic() implementation may not work well. This can be adjusted in the future. Link: http://lkml.kernel.org/r/1497903987-21002-2-git-send-email-keescook@chromium.org Signed-off-by: Kees Cook Suggested-by: Daniel Micay Reviewed-by: Ard Biesheuvel Acked-by: Mark Rutland Cc: Matt Fleming Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/firmware/efi/libstub/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index f7425960f6a5..37e24f525162 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -17,6 +17,7 @@ cflags-$(CONFIG_ARM) := $(subst -pg,,$(KBUILD_CFLAGS)) \ cflags-$(CONFIG_EFI_ARMSTUB) += -I$(srctree)/scripts/dtc/libfdt KBUILD_CFLAGS := $(cflags-y) -DDISABLE_BRANCH_PROFILING \ + -D__NO_FORTIFY \ $(call cc-option,-ffreestanding) \ $(call cc-option,-fno-stack-protector) -- cgit v1.2.3-59-g8ed1b From e2ae8ab4b571e2e4094a28acb60649bc2732c67f Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Jul 2017 14:35:58 -0700 Subject: kexec_file: adjust declaration of kexec_purgatory Defining kexec_purgatory as a zero-length char array upsets compile time size checking. Since this is built on a per-arch basis, define it as an unsized char array (like is done for other similar things, e.g. linker sections). This silences the warning generated by the future CONFIG_FORTIFY_SOURCE, which did not like the memcmp() of a "0 byte" array. This drops the __weak and uses an extern instead, since both users define kexec_purgatory. Link: http://lkml.kernel.org/r/1497903987-21002-4-git-send-email-keescook@chromium.org Signed-off-by: Kees Cook Acked-by: "Eric W. Biederman" Cc: Daniel Micay Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/kexec_file.c | 7 ------- kernel/kexec_internal.h | 2 ++ 2 files changed, 2 insertions(+), 7 deletions(-) diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index c8f7f77e9fa9..9f48f4412297 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -26,13 +26,6 @@ #include #include "kexec_internal.h" -/* - * Declare these symbols weak so that if architecture provides a purgatory, - * these will be overridden. - */ -char __weak kexec_purgatory[0]; -size_t __weak kexec_purgatory_size = 0; - static int kexec_calculate_store_digests(struct kimage *image); /* Architectures can provide this probe function */ diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h index 799a8a452187..50dfcb039a41 100644 --- a/kernel/kexec_internal.h +++ b/kernel/kexec_internal.h @@ -17,6 +17,8 @@ extern struct mutex kexec_mutex; #ifdef CONFIG_KEXEC_FILE #include void kimage_file_post_load_cleanup(struct kimage *image); +extern char kexec_purgatory[]; +extern size_t kexec_purgatory_size; #else /* CONFIG_KEXEC_FILE */ static inline void kimage_file_post_load_cleanup(struct kimage *image) { } #endif /* CONFIG_KEXEC_FILE */ -- cgit v1.2.3-59-g8ed1b From 4c93496f18ce5044d78e4f7f9e018682a4f44b3d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Jul 2017 14:36:01 -0700 Subject: IB/rxe: do not copy extra stack memory to skb This fixes a over-read condition detected by FORTIFY_SOURCE for this line: memcpy(SKB_TO_PKT(skb), &ack_pkt, sizeof(skb->cb)); The error was: In file included from ./include/linux/bitmap.h:8:0, from ./include/linux/cpumask.h:11, from ./include/linux/mm_types_task.h:13, from ./include/linux/mm_types.h:4, from ./include/linux/kmemcheck.h:4, from ./include/linux/skbuff.h:18, from drivers/infiniband/sw/rxe/rxe_resp.c:34: In function 'memcpy', inlined from 'send_atomic_ack.constprop' at drivers/infiniband/sw/rxe/rxe_resp.c:998:2, inlined from 'acknowledge' at drivers/infiniband/sw/rxe/rxe_resp.c:1026:3, inlined from 'rxe_responder' at drivers/infiniband/sw/rxe/rxe_resp.c:1286:10: ./include/linux/string.h:309:4: error: call to '__read_overflow2' declared with attribute error: detected read beyond size of object passed as 2nd parameter __read_overflow2(); Daniel Micay noted that struct rxe_pkt_info is 32 bytes on 32-bit architectures, but skb->cb is still 64. The memcpy() over-reads 32 bytes. This fixes it by zeroing the unused bytes in skb->cb. Link: http://lkml.kernel.org/r/1497903987-21002-5-git-send-email-keescook@chromium.org Signed-off-by: Kees Cook Cc: Moni Shoua Cc: Doug Ledford Cc: Sean Hefty Cc: Daniel Micay Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/infiniband/sw/rxe/rxe_resp.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 23039768f541..be944d5aa9af 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -995,7 +995,9 @@ static int send_atomic_ack(struct rxe_qp *qp, struct rxe_pkt_info *pkt, free_rd_atomic_resource(qp, res); rxe_advance_resp_resource(qp); - memcpy(SKB_TO_PKT(skb), &ack_pkt, sizeof(skb->cb)); + memcpy(SKB_TO_PKT(skb), &ack_pkt, sizeof(ack_pkt)); + memset((unsigned char *)SKB_TO_PKT(skb) + sizeof(ack_pkt), 0, + sizeof(skb->cb) - sizeof(ack_pkt)); res->type = RXE_ATOMIC_MASK; res->atomic.skb = skb; -- cgit v1.2.3-59-g8ed1b From 054f367a32381b5640c5d150fe0b7ba285564998 Mon Sep 17 00:00:00 2001 From: Daniel Axtens Date: Wed, 12 Jul 2017 14:36:04 -0700 Subject: powerpc: don't fortify prom_init prom_init is a bit special; in theory it should be able to be linked separately to the kernel. To keep this from getting too complex, the symbols that prom_init.c uses are checked. Fortification adds symbols, and it gets quite messy as it includes things like panic(). So just don't fortify prom_init.c for now. Link: http://lkml.kernel.org/r/1497903987-21002-6-git-send-email-keescook@chromium.org Signed-off-by: Daniel Axtens Signed-off-by: Kees Cook Acked-by: Michael Ellerman Cc: Daniel Micay Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/kernel/prom_init.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index dd8a04f3053a..613f79f03877 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -15,6 +15,9 @@ #undef DEBUG_PROM +/* we cannot use FORTIFY as it brings in new symbols */ +#define __NO_FORTIFY + #include #include #include -- cgit v1.2.3-59-g8ed1b From c69a48cdb301a18697bc8c9935baf4f32861cf9e Mon Sep 17 00:00:00 2001 From: Daniel Axtens Date: Wed, 12 Jul 2017 14:36:07 -0700 Subject: powerpc: make feature-fixup tests fortify-safe Testing the fortified string functions[1] would cause a kernel panic on boot in test_feature_fixups() due to a buffer overflow in memcmp. This boils down to things like this: extern unsigned int ftr_fixup_test1; extern unsigned int ftr_fixup_test1_orig; check(memcmp(&ftr_fixup_test1, &ftr_fixup_test1_orig, size) == 0); We know that these are asm labels so it is safe to read up to 'size' bytes at those addresses. However, because we have passed the address of a single unsigned int to memcmp, the compiler believes the underlying object is in fact a single unsigned int. So if size > sizeof(unsigned int), there will be a panic at runtime. We can fix this by changing the types: instead of calling the asm labels unsigned ints, call them unsigned int[]s. Therefore the size isn't incorrectly determined at compile time and we get a regular unsafe memcmp and no panic. [1] http://openwall.com/lists/kernel-hardening/2017/05/09/2 Link: http://lkml.kernel.org/r/1497903987-21002-7-git-send-email-keescook@chromium.org Signed-off-by: Daniel Axtens Signed-off-by: Kees Cook Suggested-by: Michael Ellerman Tested-by: Andrew Donnellan Reviewed-by: Andrew Donnellan Cc: Kees Cook Cc: Daniel Micay Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/lib/feature-fixups.c | 180 +++++++++++++++++++------------------- 1 file changed, 90 insertions(+), 90 deletions(-) diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index f3917705c686..41cf5ae273cf 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -233,192 +233,192 @@ static long calc_offset(struct fixup_entry *entry, unsigned int *p) static void test_basic_patching(void) { - extern unsigned int ftr_fixup_test1; - extern unsigned int end_ftr_fixup_test1; - extern unsigned int ftr_fixup_test1_orig; - extern unsigned int ftr_fixup_test1_expected; - int size = &end_ftr_fixup_test1 - &ftr_fixup_test1; + extern unsigned int ftr_fixup_test1[]; + extern unsigned int end_ftr_fixup_test1[]; + extern unsigned int ftr_fixup_test1_orig[]; + extern unsigned int ftr_fixup_test1_expected[]; + int size = end_ftr_fixup_test1 - ftr_fixup_test1; fixup.value = fixup.mask = 8; - fixup.start_off = calc_offset(&fixup, &ftr_fixup_test1 + 1); - fixup.end_off = calc_offset(&fixup, &ftr_fixup_test1 + 2); + fixup.start_off = calc_offset(&fixup, ftr_fixup_test1 + 1); + fixup.end_off = calc_offset(&fixup, ftr_fixup_test1 + 2); fixup.alt_start_off = fixup.alt_end_off = 0; /* Sanity check */ - check(memcmp(&ftr_fixup_test1, &ftr_fixup_test1_orig, size) == 0); + check(memcmp(ftr_fixup_test1, ftr_fixup_test1_orig, size) == 0); /* Check we don't patch if the value matches */ patch_feature_section(8, &fixup); - check(memcmp(&ftr_fixup_test1, &ftr_fixup_test1_orig, size) == 0); + check(memcmp(ftr_fixup_test1, ftr_fixup_test1_orig, size) == 0); /* Check we do patch if the value doesn't match */ patch_feature_section(0, &fixup); - check(memcmp(&ftr_fixup_test1, &ftr_fixup_test1_expected, size) == 0); + check(memcmp(ftr_fixup_test1, ftr_fixup_test1_expected, size) == 0); /* Check we do patch if the mask doesn't match */ - memcpy(&ftr_fixup_test1, &ftr_fixup_test1_orig, size); - check(memcmp(&ftr_fixup_test1, &ftr_fixup_test1_orig, size) == 0); + memcpy(ftr_fixup_test1, ftr_fixup_test1_orig, size); + check(memcmp(ftr_fixup_test1, ftr_fixup_test1_orig, size) == 0); patch_feature_section(~8, &fixup); - check(memcmp(&ftr_fixup_test1, &ftr_fixup_test1_expected, size) == 0); + check(memcmp(ftr_fixup_test1, ftr_fixup_test1_expected, size) == 0); } static void test_alternative_patching(void) { - extern unsigned int ftr_fixup_test2; - extern unsigned int end_ftr_fixup_test2; - extern unsigned int ftr_fixup_test2_orig; - extern unsigned int ftr_fixup_test2_alt; - extern unsigned int ftr_fixup_test2_expected; - int size = &end_ftr_fixup_test2 - &ftr_fixup_test2; + extern unsigned int ftr_fixup_test2[]; + extern unsigned int end_ftr_fixup_test2[]; + extern unsigned int ftr_fixup_test2_orig[]; + extern unsigned int ftr_fixup_test2_alt[]; + extern unsigned int ftr_fixup_test2_expected[]; + int size = end_ftr_fixup_test2 - ftr_fixup_test2; fixup.value = fixup.mask = 0xF; - fixup.start_off = calc_offset(&fixup, &ftr_fixup_test2 + 1); - fixup.end_off = calc_offset(&fixup, &ftr_fixup_test2 + 2); - fixup.alt_start_off = calc_offset(&fixup, &ftr_fixup_test2_alt); - fixup.alt_end_off = calc_offset(&fixup, &ftr_fixup_test2_alt + 1); + fixup.start_off = calc_offset(&fixup, ftr_fixup_test2 + 1); + fixup.end_off = calc_offset(&fixup, ftr_fixup_test2 + 2); + fixup.alt_start_off = calc_offset(&fixup, ftr_fixup_test2_alt); + fixup.alt_end_off = calc_offset(&fixup, ftr_fixup_test2_alt + 1); /* Sanity check */ - check(memcmp(&ftr_fixup_test2, &ftr_fixup_test2_orig, size) == 0); + check(memcmp(ftr_fixup_test2, ftr_fixup_test2_orig, size) == 0); /* Check we don't patch if the value matches */ patch_feature_section(0xF, &fixup); - check(memcmp(&ftr_fixup_test2, &ftr_fixup_test2_orig, size) == 0); + check(memcmp(ftr_fixup_test2, ftr_fixup_test2_orig, size) == 0); /* Check we do patch if the value doesn't match */ patch_feature_section(0, &fixup); - check(memcmp(&ftr_fixup_test2, &ftr_fixup_test2_expected, size) == 0); + check(memcmp(ftr_fixup_test2, ftr_fixup_test2_expected, size) == 0); /* Check we do patch if the mask doesn't match */ - memcpy(&ftr_fixup_test2, &ftr_fixup_test2_orig, size); - check(memcmp(&ftr_fixup_test2, &ftr_fixup_test2_orig, size) == 0); + memcpy(ftr_fixup_test2, ftr_fixup_test2_orig, size); + check(memcmp(ftr_fixup_test2, ftr_fixup_test2_orig, size) == 0); patch_feature_section(~0xF, &fixup); - check(memcmp(&ftr_fixup_test2, &ftr_fixup_test2_expected, size) == 0); + check(memcmp(ftr_fixup_test2, ftr_fixup_test2_expected, size) == 0); } static void test_alternative_case_too_big(void) { - extern unsigned int ftr_fixup_test3; - extern unsigned int end_ftr_fixup_test3; - extern unsigned int ftr_fixup_test3_orig; - extern unsigned int ftr_fixup_test3_alt; - int size = &end_ftr_fixup_test3 - &ftr_fixup_test3; + extern unsigned int ftr_fixup_test3[]; + extern unsigned int end_ftr_fixup_test3[]; + extern unsigned int ftr_fixup_test3_orig[]; + extern unsigned int ftr_fixup_test3_alt[]; + int size = end_ftr_fixup_test3 - ftr_fixup_test3; fixup.value = fixup.mask = 0xC; - fixup.start_off = calc_offset(&fixup, &ftr_fixup_test3 + 1); - fixup.end_off = calc_offset(&fixup, &ftr_fixup_test3 + 2); - fixup.alt_start_off = calc_offset(&fixup, &ftr_fixup_test3_alt); - fixup.alt_end_off = calc_offset(&fixup, &ftr_fixup_test3_alt + 2); + fixup.start_off = calc_offset(&fixup, ftr_fixup_test3 + 1); + fixup.end_off = calc_offset(&fixup, ftr_fixup_test3 + 2); + fixup.alt_start_off = calc_offset(&fixup, ftr_fixup_test3_alt); + fixup.alt_end_off = calc_offset(&fixup, ftr_fixup_test3_alt + 2); /* Sanity check */ - check(memcmp(&ftr_fixup_test3, &ftr_fixup_test3_orig, size) == 0); + check(memcmp(ftr_fixup_test3, ftr_fixup_test3_orig, size) == 0); /* Expect nothing to be patched, and the error returned to us */ check(patch_feature_section(0xF, &fixup) == 1); - check(memcmp(&ftr_fixup_test3, &ftr_fixup_test3_orig, size) == 0); + check(memcmp(ftr_fixup_test3, ftr_fixup_test3_orig, size) == 0); check(patch_feature_section(0, &fixup) == 1); - check(memcmp(&ftr_fixup_test3, &ftr_fixup_test3_orig, size) == 0); + check(memcmp(ftr_fixup_test3, ftr_fixup_test3_orig, size) == 0); check(patch_feature_section(~0xF, &fixup) == 1); - check(memcmp(&ftr_fixup_test3, &ftr_fixup_test3_orig, size) == 0); + check(memcmp(ftr_fixup_test3, ftr_fixup_test3_orig, size) == 0); } static void test_alternative_case_too_small(void) { - extern unsigned int ftr_fixup_test4; - extern unsigned int end_ftr_fixup_test4; - extern unsigned int ftr_fixup_test4_orig; - extern unsigned int ftr_fixup_test4_alt; - extern unsigned int ftr_fixup_test4_expected; - int size = &end_ftr_fixup_test4 - &ftr_fixup_test4; + extern unsigned int ftr_fixup_test4[]; + extern unsigned int end_ftr_fixup_test4[]; + extern unsigned int ftr_fixup_test4_orig[]; + extern unsigned int ftr_fixup_test4_alt[]; + extern unsigned int ftr_fixup_test4_expected[]; + int size = end_ftr_fixup_test4 - ftr_fixup_test4; unsigned long flag; /* Check a high-bit flag */ flag = 1UL << ((sizeof(unsigned long) - 1) * 8); fixup.value = fixup.mask = flag; - fixup.start_off = calc_offset(&fixup, &ftr_fixup_test4 + 1); - fixup.end_off = calc_offset(&fixup, &ftr_fixup_test4 + 5); - fixup.alt_start_off = calc_offset(&fixup, &ftr_fixup_test4_alt); - fixup.alt_end_off = calc_offset(&fixup, &ftr_fixup_test4_alt + 2); + fixup.start_off = calc_offset(&fixup, ftr_fixup_test4 + 1); + fixup.end_off = calc_offset(&fixup, ftr_fixup_test4 + 5); + fixup.alt_start_off = calc_offset(&fixup, ftr_fixup_test4_alt); + fixup.alt_end_off = calc_offset(&fixup, ftr_fixup_test4_alt + 2); /* Sanity check */ - check(memcmp(&ftr_fixup_test4, &ftr_fixup_test4_orig, size) == 0); + check(memcmp(ftr_fixup_test4, ftr_fixup_test4_orig, size) == 0); /* Check we don't patch if the value matches */ patch_feature_section(flag, &fixup); - check(memcmp(&ftr_fixup_test4, &ftr_fixup_test4_orig, size) == 0); + check(memcmp(ftr_fixup_test4, ftr_fixup_test4_orig, size) == 0); /* Check we do patch if the value doesn't match */ patch_feature_section(0, &fixup); - check(memcmp(&ftr_fixup_test4, &ftr_fixup_test4_expected, size) == 0); + check(memcmp(ftr_fixup_test4, ftr_fixup_test4_expected, size) == 0); /* Check we do patch if the mask doesn't match */ - memcpy(&ftr_fixup_test4, &ftr_fixup_test4_orig, size); - check(memcmp(&ftr_fixup_test4, &ftr_fixup_test4_orig, size) == 0); + memcpy(ftr_fixup_test4, ftr_fixup_test4_orig, size); + check(memcmp(ftr_fixup_test4, ftr_fixup_test4_orig, size) == 0); patch_feature_section(~flag, &fixup); - check(memcmp(&ftr_fixup_test4, &ftr_fixup_test4_expected, size) == 0); + check(memcmp(ftr_fixup_test4, ftr_fixup_test4_expected, size) == 0); } static void test_alternative_case_with_branch(void) { - extern unsigned int ftr_fixup_test5; - extern unsigned int end_ftr_fixup_test5; - extern unsigned int ftr_fixup_test5_expected; - int size = &end_ftr_fixup_test5 - &ftr_fixup_test5; + extern unsigned int ftr_fixup_test5[]; + extern unsigned int end_ftr_fixup_test5[]; + extern unsigned int ftr_fixup_test5_expected[]; + int size = end_ftr_fixup_test5 - ftr_fixup_test5; - check(memcmp(&ftr_fixup_test5, &ftr_fixup_test5_expected, size) == 0); + check(memcmp(ftr_fixup_test5, ftr_fixup_test5_expected, size) == 0); } static void test_alternative_case_with_external_branch(void) { - extern unsigned int ftr_fixup_test6; - extern unsigned int end_ftr_fixup_test6; - extern unsigned int ftr_fixup_test6_expected; - int size = &end_ftr_fixup_test6 - &ftr_fixup_test6; + extern unsigned int ftr_fixup_test6[]; + extern unsigned int end_ftr_fixup_test6[]; + extern unsigned int ftr_fixup_test6_expected[]; + int size = end_ftr_fixup_test6 - ftr_fixup_test6; - check(memcmp(&ftr_fixup_test6, &ftr_fixup_test6_expected, size) == 0); + check(memcmp(ftr_fixup_test6, ftr_fixup_test6_expected, size) == 0); } static void test_cpu_macros(void) { - extern u8 ftr_fixup_test_FTR_macros; - extern u8 ftr_fixup_test_FTR_macros_expected; - unsigned long size = &ftr_fixup_test_FTR_macros_expected - - &ftr_fixup_test_FTR_macros; + extern u8 ftr_fixup_test_FTR_macros[]; + extern u8 ftr_fixup_test_FTR_macros_expected[]; + unsigned long size = ftr_fixup_test_FTR_macros_expected - + ftr_fixup_test_FTR_macros; /* The fixups have already been done for us during boot */ - check(memcmp(&ftr_fixup_test_FTR_macros, - &ftr_fixup_test_FTR_macros_expected, size) == 0); + check(memcmp(ftr_fixup_test_FTR_macros, + ftr_fixup_test_FTR_macros_expected, size) == 0); } static void test_fw_macros(void) { #ifdef CONFIG_PPC64 - extern u8 ftr_fixup_test_FW_FTR_macros; - extern u8 ftr_fixup_test_FW_FTR_macros_expected; - unsigned long size = &ftr_fixup_test_FW_FTR_macros_expected - - &ftr_fixup_test_FW_FTR_macros; + extern u8 ftr_fixup_test_FW_FTR_macros[]; + extern u8 ftr_fixup_test_FW_FTR_macros_expected[]; + unsigned long size = ftr_fixup_test_FW_FTR_macros_expected - + ftr_fixup_test_FW_FTR_macros; /* The fixups have already been done for us during boot */ - check(memcmp(&ftr_fixup_test_FW_FTR_macros, - &ftr_fixup_test_FW_FTR_macros_expected, size) == 0); + check(memcmp(ftr_fixup_test_FW_FTR_macros, + ftr_fixup_test_FW_FTR_macros_expected, size) == 0); #endif } static void test_lwsync_macros(void) { - extern u8 lwsync_fixup_test; - extern u8 end_lwsync_fixup_test; - extern u8 lwsync_fixup_test_expected_LWSYNC; - extern u8 lwsync_fixup_test_expected_SYNC; - unsigned long size = &end_lwsync_fixup_test - - &lwsync_fixup_test; + extern u8 lwsync_fixup_test[]; + extern u8 end_lwsync_fixup_test[]; + extern u8 lwsync_fixup_test_expected_LWSYNC[]; + extern u8 lwsync_fixup_test_expected_SYNC[]; + unsigned long size = end_lwsync_fixup_test - + lwsync_fixup_test; /* The fixups have already been done for us during boot */ if (cur_cpu_spec->cpu_features & CPU_FTR_LWSYNC) { - check(memcmp(&lwsync_fixup_test, - &lwsync_fixup_test_expected_LWSYNC, size) == 0); + check(memcmp(lwsync_fixup_test, + lwsync_fixup_test_expected_LWSYNC, size) == 0); } else { - check(memcmp(&lwsync_fixup_test, - &lwsync_fixup_test_expected_SYNC, size) == 0); + check(memcmp(lwsync_fixup_test, + lwsync_fixup_test_expected_SYNC, size) == 0); } } -- cgit v1.2.3-59-g8ed1b From 6974f0c4555e285ab217cee58b6e874f776ff409 Mon Sep 17 00:00:00 2001 From: Daniel Micay Date: Wed, 12 Jul 2017 14:36:10 -0700 Subject: include/linux/string.h: add the option of fortified string.h functions This adds support for compiling with a rough equivalent to the glibc _FORTIFY_SOURCE=1 feature, providing compile-time and runtime buffer overflow checks for string.h functions when the compiler determines the size of the source or destination buffer at compile-time. Unlike glibc, it covers buffer reads in addition to writes. GNU C __builtin_*_chk intrinsics are avoided because they would force a much more complex implementation. They aren't designed to detect read overflows and offer no real benefit when using an implementation based on inline checks. Inline checks don't add up to much code size and allow full use of the regular string intrinsics while avoiding the need for a bunch of _chk functions and per-arch assembly to avoid wrapper overhead. This detects various overflows at compile-time in various drivers and some non-x86 core kernel code. There will likely be issues caught in regular use at runtime too. Future improvements left out of initial implementation for simplicity, as it's all quite optional and can be done incrementally: * Some of the fortified string functions (strncpy, strcat), don't yet place a limit on reads from the source based on __builtin_object_size of the source buffer. * Extending coverage to more string functions like strlcat. * It should be possible to optionally use __builtin_object_size(x, 1) for some functions (C strings) to detect intra-object overflows (like glibc's _FORTIFY_SOURCE=2), but for now this takes the conservative approach to avoid likely compatibility issues. * The compile-time checks should be made available via a separate config option which can be enabled by default (or always enabled) once enough time has passed to get the issues it catches fixed. Kees said: "This is great to have. While it was out-of-tree code, it would have blocked at least CVE-2016-3858 from being exploitable (improper size argument to strlcpy()). I've sent a number of fixes for out-of-bounds-reads that this detected upstream already" [arnd@arndb.de: x86: fix fortified memcpy] Link: http://lkml.kernel.org/r/20170627150047.660360-1-arnd@arndb.de [keescook@chromium.org: avoid panic() in favor of BUG()] Link: http://lkml.kernel.org/r/20170626235122.GA25261@beast [keescook@chromium.org: move from -mm, add ARCH_HAS_FORTIFY_SOURCE, tweak Kconfig help] Link: http://lkml.kernel.org/r/20170526095404.20439-1-danielmicay@gmail.com Link: http://lkml.kernel.org/r/1497903987-21002-8-git-send-email-keescook@chromium.org Signed-off-by: Daniel Micay Signed-off-by: Kees Cook Signed-off-by: Arnd Bergmann Acked-by: Kees Cook Cc: Mark Rutland Cc: Daniel Axtens Cc: Rasmus Villemoes Cc: Andy Shevchenko Cc: Chris Metcalf Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/Kconfig | 6 ++ arch/arm64/Kconfig | 1 + arch/arm64/include/asm/string.h | 5 + arch/powerpc/Kconfig | 1 + arch/x86/Kconfig | 1 + arch/x86/boot/compressed/misc.c | 5 + arch/x86/include/asm/string_32.h | 9 ++ arch/x86/include/asm/string_64.h | 7 ++ arch/x86/lib/memcpy_32.c | 2 +- include/linux/string.h | 200 +++++++++++++++++++++++++++++++++++++++ lib/string.c | 7 ++ security/Kconfig | 7 ++ 12 files changed, 250 insertions(+), 1 deletion(-) diff --git a/arch/Kconfig b/arch/Kconfig index fb9bd7d36b05..21d0089117fe 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -223,6 +223,12 @@ config GENERIC_SMP_IDLE_THREAD config GENERIC_IDLE_POLL_SETUP bool +config ARCH_HAS_FORTIFY_SOURCE + bool + help + An architecture should select this when it can successfully + build and run with CONFIG_FORTIFY_SOURCE. + # Select if arch has all set_memory_ro/rw/x/nx() functions in asm/cacheflush.h config ARCH_HAS_SET_MEMORY bool diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 8addb851ab5e..dfd908630631 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -12,6 +12,7 @@ config ARM64 select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_ELF_RANDOMIZE + select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA select ARCH_HAS_KCOV diff --git a/arch/arm64/include/asm/string.h b/arch/arm64/include/asm/string.h index 2eb714c4639f..d0aa42907569 100644 --- a/arch/arm64/include/asm/string.h +++ b/arch/arm64/include/asm/string.h @@ -63,6 +63,11 @@ extern int memcmp(const void *, const void *, size_t); #define memcpy(dst, src, len) __memcpy(dst, src, len) #define memmove(dst, src, len) __memmove(dst, src, len) #define memset(s, c, n) __memset(s, c, n) + +#ifndef __NO_FORTIFY +#define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */ +#endif + #endif #endif diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index fce2f4f20891..36f858c37ca7 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -125,6 +125,7 @@ config PPC select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_DMA_SET_COHERENT_MASK select ARCH_HAS_ELF_RANDOMIZE + select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE select ARCH_HAS_SG_CHAIN diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 3d2b8ce54e00..781521b7cf9e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -50,6 +50,7 @@ config X86 select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FAST_MULTIPLIER + select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV if X86_64 select ARCH_HAS_MMIO_FLUSH diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 00241c815524..a0838ab929f2 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -411,3 +411,8 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, debug_putstr("done.\nBooting the kernel.\n"); return output; } + +void fortify_panic(const char *name) +{ + error("detected buffer overflow"); +} diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h index 3d3e8353ee5c..e9ee84873de5 100644 --- a/arch/x86/include/asm/string_32.h +++ b/arch/x86/include/asm/string_32.h @@ -142,7 +142,9 @@ static __always_inline void *__constant_memcpy(void *to, const void *from, } #define __HAVE_ARCH_MEMCPY +extern void *memcpy(void *, const void *, size_t); +#ifndef CONFIG_FORTIFY_SOURCE #ifdef CONFIG_X86_USE_3DNOW #include @@ -195,11 +197,15 @@ static inline void *__memcpy3d(void *to, const void *from, size_t len) #endif #endif +#endif /* !CONFIG_FORTIFY_SOURCE */ #define __HAVE_ARCH_MEMMOVE void *memmove(void *dest, const void *src, size_t n); +extern int memcmp(const void *, const void *, size_t); +#ifndef CONFIG_FORTIFY_SOURCE #define memcmp __builtin_memcmp +#endif #define __HAVE_ARCH_MEMCHR extern void *memchr(const void *cs, int c, size_t count); @@ -321,6 +327,8 @@ void *__constant_c_and_count_memset(void *s, unsigned long pattern, : __memset_generic((s), (c), (count))) #define __HAVE_ARCH_MEMSET +extern void *memset(void *, int, size_t); +#ifndef CONFIG_FORTIFY_SOURCE #if (__GNUC__ >= 4) #define memset(s, c, count) __builtin_memset(s, c, count) #else @@ -330,6 +338,7 @@ void *__constant_c_and_count_memset(void *s, unsigned long pattern, (count)) \ : __memset((s), (c), (count))) #endif +#endif /* !CONFIG_FORTIFY_SOURCE */ /* * find the first occurrence of byte 'c', or 1 past the area if none diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index 1f22bc277c45..2a8c822de1fc 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -31,6 +31,7 @@ static __always_inline void *__inline_memcpy(void *to, const void *from, size_t extern void *memcpy(void *to, const void *from, size_t len); extern void *__memcpy(void *to, const void *from, size_t len); +#ifndef CONFIG_FORTIFY_SOURCE #ifndef CONFIG_KMEMCHECK #if (__GNUC__ == 4 && __GNUC_MINOR__ < 3) || __GNUC__ < 4 #define memcpy(dst, src, len) \ @@ -51,6 +52,7 @@ extern void *__memcpy(void *to, const void *from, size_t len); */ #define memcpy(dst, src, len) __inline_memcpy((dst), (src), (len)) #endif +#endif /* !CONFIG_FORTIFY_SOURCE */ #define __HAVE_ARCH_MEMSET void *memset(void *s, int c, size_t n); @@ -77,6 +79,11 @@ int strcmp(const char *cs, const char *ct); #define memcpy(dst, src, len) __memcpy(dst, src, len) #define memmove(dst, src, len) __memmove(dst, src, len) #define memset(s, c, n) __memset(s, c, n) + +#ifndef __NO_FORTIFY +#define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */ +#endif + #endif #define __HAVE_ARCH_MEMCPY_MCSAFE 1 diff --git a/arch/x86/lib/memcpy_32.c b/arch/x86/lib/memcpy_32.c index cad12634d6bd..2eab7d0bfedd 100644 --- a/arch/x86/lib/memcpy_32.c +++ b/arch/x86/lib/memcpy_32.c @@ -6,7 +6,7 @@ __visible void *memcpy(void *to, const void *from, size_t n) { -#ifdef CONFIG_X86_USE_3DNOW +#if defined(CONFIG_X86_USE_3DNOW) && !defined(CONFIG_FORTIFY_SOURCE) return __memcpy3d(to, from, n); #else return __memcpy(to, from, n); diff --git a/include/linux/string.h b/include/linux/string.h index 7439d83eaa33..96f5a5fd0377 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -193,4 +193,204 @@ static inline const char *kbasename(const char *path) return tail ? tail + 1 : path; } +#define __FORTIFY_INLINE extern __always_inline __attribute__((gnu_inline)) +#define __RENAME(x) __asm__(#x) + +void fortify_panic(const char *name) __noreturn __cold; +void __read_overflow(void) __compiletime_error("detected read beyond size of object passed as 1st parameter"); +void __read_overflow2(void) __compiletime_error("detected read beyond size of object passed as 2nd parameter"); +void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter"); + +#if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) +__FORTIFY_INLINE char *strcpy(char *p, const char *q) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __builtin_strcpy(p, q); + if (strscpy(p, q, p_size < q_size ? p_size : q_size) < 0) + fortify_panic(__func__); + return p; +} + +__FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __write_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __builtin_strncpy(p, q, size); +} + +__FORTIFY_INLINE char *strcat(char *p, const char *q) +{ + size_t p_size = __builtin_object_size(p, 0); + if (p_size == (size_t)-1) + return __builtin_strcat(p, q); + if (strlcat(p, q, p_size) >= p_size) + fortify_panic(__func__); + return p; +} + +__FORTIFY_INLINE __kernel_size_t strlen(const char *p) +{ + __kernel_size_t ret; + size_t p_size = __builtin_object_size(p, 0); + if (p_size == (size_t)-1) + return __builtin_strlen(p); + ret = strnlen(p, p_size); + if (p_size <= ret) + fortify_panic(__func__); + return ret; +} + +extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); +__FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) +{ + size_t p_size = __builtin_object_size(p, 0); + __kernel_size_t ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size); + if (p_size <= ret && maxlen != ret) + fortify_panic(__func__); + return ret; +} + +/* defined after fortified strlen to reuse it */ +extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy); +__FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) +{ + size_t ret; + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __real_strlcpy(p, q, size); + ret = strlen(q); + if (size) { + size_t len = (ret >= size) ? size - 1 : ret; + if (__builtin_constant_p(len) && len >= p_size) + __write_overflow(); + if (len >= p_size) + fortify_panic(__func__); + __builtin_memcpy(p, q, len); + p[len] = '\0'; + } + return ret; +} + +/* defined after fortified strlen and strnlen to reuse them */ +__FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) +{ + size_t p_len, copy_len; + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __builtin_strncat(p, q, count); + p_len = strlen(p); + copy_len = strnlen(q, count); + if (p_size < p_len + copy_len + 1) + fortify_panic(__func__); + __builtin_memcpy(p + p_len, q, copy_len); + p[p_len + copy_len] = '\0'; + return p; +} + +__FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __write_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __builtin_memset(p, c, size); +} + +__FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (__builtin_constant_p(size)) { + if (p_size < size) + __write_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __builtin_memcpy(p, q, size); +} + +__FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (__builtin_constant_p(size)) { + if (p_size < size) + __write_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __builtin_memmove(p, q, size); +} + +extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); +__FORTIFY_INLINE void *memscan(void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_memscan(p, c, size); +} + +__FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (__builtin_constant_p(size)) { + if (p_size < size) + __read_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __builtin_memcmp(p, q, size); +} + +__FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __builtin_memchr(p, c, size); +} + +void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); +__FORTIFY_INLINE void *memchr_inv(const void *p, int c, size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_memchr_inv(p, c, size); +} + +extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup); +__FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_kmemdup(p, size, gfp); +} +#endif + #endif /* _LINUX_STRING_H_ */ diff --git a/lib/string.c b/lib/string.c index 1c1fc9187b05..ebbb99c775bd 100644 --- a/lib/string.c +++ b/lib/string.c @@ -978,3 +978,10 @@ char *strreplace(char *s, char old, char new) return s; } EXPORT_SYMBOL(strreplace); + +void fortify_panic(const char *name) +{ + pr_emerg("detected buffer overflow in %s\n", name); + BUG(); +} +EXPORT_SYMBOL(fortify_panic); diff --git a/security/Kconfig b/security/Kconfig index d540bfe73190..e8e449444e65 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -163,6 +163,13 @@ config HARDENED_USERCOPY_PAGESPAN been removed. This config is intended to be used only while trying to find such users. +config FORTIFY_SOURCE + bool "Harden common str/mem functions against buffer overflows" + depends on ARCH_HAS_FORTIFY_SOURCE + help + Detect overflows of buffers in common string and memory functions + where the compiler can determine and validate the buffer sizes. + config STATIC_USERMODEHELPER bool "Force all usermode helper calls through a single binary" help -- cgit v1.2.3-59-g8ed1b From 579e14524c6593cb651a806a6563e14b263c00e2 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 12 Jul 2017 14:36:13 -0700 Subject: sh: mark end of BUG() implementation as unreachable When building the sh architecture, the compiler doesn't realize that BUG() doesn't return, so it will complain about functions using BUG() that are marked with the noreturn attribute: lib/string.c: In function 'fortify_panic': >> lib/string.c:986:1: warning: 'noreturn' function does return } ^ Link: http://lkml.kernel.org/r/20170627192050.GA66784@beast Signed-off-by: Kees Cook Cc: Yoshinori Sato Cc: Rich Felker Cc: Daniel Micay Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/sh/include/asm/bug.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/sh/include/asm/bug.h b/arch/sh/include/asm/bug.h index 1b77f068be2b..c9828f785ca0 100644 --- a/arch/sh/include/asm/bug.h +++ b/arch/sh/include/asm/bug.h @@ -48,6 +48,7 @@ do { \ "i" (__FILE__), \ "i" (__LINE__), "i" (0), \ "i" (sizeof(struct bug_entry))); \ + unreachable(); \ } while (0) #define __WARN_FLAGS(flags) \ -- cgit v1.2.3-59-g8ed1b From 022c204040f3fd22d6445bc35517786195b7ae80 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Wed, 12 Jul 2017 14:36:17 -0700 Subject: random,stackprotect: introduce get_random_canary function Patch series "stackprotector: ascii armor the stack canary", v2. Zero out the first byte of the stack canary value on 64 bit systems, in order to mitigate unterminated C string overflows. The null byte both prevents C string functions from reading the canary, and from writing it if the canary value were guessed or obtained through some other means. Reducing the entropy by 8 bits is acceptable on 64-bit systems, which will still have 56 bits of entropy left, but not on 32 bit systems, so the "ascii armor" canary is only implemented on 64-bit systems. Inspired by the "ascii armor" code in execshield and Daniel Micay's linux-hardened tree. Also see https://github.com/thestinger/linux-hardened/ This patch (of 5): Introduce get_random_canary(), which provides a random unsigned long canary value with the first byte zeroed out on 64 bit architectures, in order to mitigate non-terminated C string overflows. The null byte both prevents C string functions from reading the canary, and from writing it if the canary value were guessed or obtained through some other means. Reducing the entropy by 8 bits is acceptable on 64-bit systems, which will still have 56 bits of entropy left, but not on 32 bit systems, so the "ascii armor" canary is only implemented on 64-bit systems. Inspired by the "ascii armor" code in the old execshield patches, and Daniel Micay's linux-hardened tree. Link: http://lkml.kernel.org/r/20170524155751.424-2-riel@redhat.com Signed-off-by: Rik van Riel Acked-by: Kees Cook Cc: Daniel Micay Cc: "Theodore Ts'o" Cc: H. Peter Anvin Cc: Andy Lutomirski Cc: Ingo Molnar Cc: Catalin Marinas Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/random.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/include/linux/random.h b/include/linux/random.h index ed5c3838780d..1fa0dc880bd7 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -57,6 +57,27 @@ static inline unsigned long get_random_long(void) #endif } +/* + * On 64-bit architectures, protect against non-terminated C string overflows + * by zeroing out the first byte of the canary; this leaves 56 bits of entropy. + */ +#ifdef CONFIG_64BIT +# ifdef __LITTLE_ENDIAN +# define CANARY_MASK 0xffffffffffffff00UL +# else /* big endian, 64 bits: */ +# define CANARY_MASK 0x00ffffffffffffffUL +# endif +#else /* 32 bits: */ +# define CANARY_MASK 0xffffffffUL +#endif + +static inline unsigned long get_random_canary(void) +{ + unsigned long val = get_random_long(); + + return val & CANARY_MASK; +} + unsigned long randomize_page(unsigned long start, unsigned long range); u32 prandom_u32(void); -- cgit v1.2.3-59-g8ed1b From 7cd815bce828220deffd1654265f0ef891567774 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Wed, 12 Jul 2017 14:36:20 -0700 Subject: fork,random: use get_random_canary() to set tsk->stack_canary Use the ascii-armor canary to prevent unterminated C string overflows from being able to successfully overwrite the canary, even if they somehow obtain the canary value. Inspired by execshield ascii-armor and Daniel Micay's linux-hardened tree. Link: http://lkml.kernel.org/r/20170524155751.424-3-riel@redhat.com Signed-off-by: Rik van Riel Acked-by: Kees Cook Cc: Daniel Micay Cc: "Theodore Ts'o" Cc: H. Peter Anvin Cc: Andy Lutomirski Cc: Ingo Molnar Cc: Catalin Marinas Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/fork.c b/kernel/fork.c index ade237a96308..17921b0390b4 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -554,7 +554,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) set_task_stack_end_magic(tsk); #ifdef CONFIG_CC_STACKPROTECTOR - tsk->stack_canary = get_random_long(); + tsk->stack_canary = get_random_canary(); #endif /* -- cgit v1.2.3-59-g8ed1b From bf9eb5443844e288b73f7963dfc67a0d2fbc3849 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Wed, 12 Jul 2017 14:36:23 -0700 Subject: x86: ascii armor the x86_64 boot init stack canary Use the ascii-armor canary to prevent unterminated C string overflows from being able to successfully overwrite the canary, even if they somehow obtain the canary value. Inspired by execshield ascii-armor and Daniel Micay's linux-hardened tree. Link: http://lkml.kernel.org/r/20170524155751.424-4-riel@redhat.com Signed-off-by: Rik van Riel Acked-by: Kees Cook Cc: Daniel Micay Cc: "Theodore Ts'o" Cc: H. Peter Anvin Cc: Andy Lutomirski Cc: Ingo Molnar Cc: Catalin Marinas Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/stackprotector.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index dcbd9bcce714..8abedf1d650e 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -74,6 +74,7 @@ static __always_inline void boot_init_stack_canary(void) get_random_bytes(&canary, sizeof(canary)); tsc = rdtsc(); canary += tsc + (tsc << 32UL); + canary &= CANARY_MASK; current->stack_canary = canary; #ifdef CONFIG_X86_64 -- cgit v1.2.3-59-g8ed1b From d21f54988bb2927341757d42152440c3abcae4eb Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Wed, 12 Jul 2017 14:36:26 -0700 Subject: arm64: ascii armor the arm64 boot init stack canary Use the ascii-armor canary to prevent unterminated C string overflows from being able to successfully overwrite the canary, even if they somehow obtain the canary value. Inspired by execshield ascii-armor and Daniel Micay's linux-hardened tree. Link: http://lkml.kernel.org/r/20170524155751.424-5-riel@redhat.com Signed-off-by: Rik van Riel Acked-by: Kees Cook Cc: Daniel Micay Cc: "Theodore Ts'o" Cc: H. Peter Anvin Cc: Andy Lutomirski Cc: Ingo Molnar Cc: Catalin Marinas Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/include/asm/stackprotector.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/include/asm/stackprotector.h b/arch/arm64/include/asm/stackprotector.h index fe5e287dc56b..b86a0865ddf1 100644 --- a/arch/arm64/include/asm/stackprotector.h +++ b/arch/arm64/include/asm/stackprotector.h @@ -30,6 +30,7 @@ static __always_inline void boot_init_stack_canary(void) /* Try to get a semi random initial value. */ get_random_bytes(&canary, sizeof(canary)); canary ^= LINUX_VERSION_CODE; + canary &= CANARY_MASK; current->stack_canary = canary; __stack_chk_guard = current->stack_canary; -- cgit v1.2.3-59-g8ed1b From 2c8340eda45cee1784f7b29e6d7dcc740ea3d02a Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Wed, 12 Jul 2017 14:36:29 -0700 Subject: sh64: ascii armor the sh64 boot init stack canary Use the ascii-armor canary to prevent unterminated C string overflows from being able to successfully overwrite the canary, even if they somehow obtain the canary value. Inspired by execshield ascii-armor and Daniel Micay's linux-hardened tree. Link: http://lkml.kernel.org/r/20170524123446.78510066@annuminas.surriel.com Signed-off-by: Rik van Riel Acked-by: Kees Cook Cc: Daniel Micay Cc: "Theodore Ts'o" Cc: H. Peter Anvin Cc: Andy Lutomirski Cc: Ingo Molnar Cc: Catalin Marinas Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/sh/include/asm/stackprotector.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/sh/include/asm/stackprotector.h b/arch/sh/include/asm/stackprotector.h index d9df3a76847c..141515a43b78 100644 --- a/arch/sh/include/asm/stackprotector.h +++ b/arch/sh/include/asm/stackprotector.h @@ -19,6 +19,7 @@ static __always_inline void boot_init_stack_canary(void) /* Try to get a semi random initial value. */ get_random_bytes(&canary, sizeof(canary)); canary ^= LINUX_VERSION_CODE; + canary &= CANARY_MASK; current->stack_canary = canary; __stack_chk_guard = current->stack_canary; -- cgit v1.2.3-59-g8ed1b From c204d21f2232d875e36b8774c36ffd027dc1d606 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Wed, 12 Jul 2017 14:36:33 -0700 Subject: x86/mmap: properly account for stack randomization in mmap_base When RLIMIT_STACK is, for example, 256MB, the current code results in a gap between the top of the task and mmap_base of 256MB, failing to take into account the amount by which the stack address was randomized. In other words, the stack gets less than RLIMIT_STACK space. Ensure that the gap between the stack and mmap_base always takes stack randomization and the stack guard gap into account. Obtained from Daniel Micay's linux-hardened tree. Link: http://lkml.kernel.org/r/20170622200033.25714-2-riel@redhat.com Signed-off-by: Daniel Micay Signed-off-by: Rik van Riel Reported-by: Florian Weimer Acked-by: Ingo Molnar Cc: Will Deacon Cc: Daniel Micay Cc: Benjamin Herrenschmidt Cc: Hugh Dickins Cc: Catalin Marinas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/mm/mmap.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 797295e792b2..229d04a83f85 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -92,13 +92,18 @@ unsigned long arch_mmap_rnd(void) static unsigned long mmap_base(unsigned long rnd, unsigned long task_size) { unsigned long gap = rlimit(RLIMIT_STACK); + unsigned long pad = stack_maxrandom_size(task_size) + stack_guard_gap; unsigned long gap_min, gap_max; + /* Values close to RLIM_INFINITY can overflow. */ + if (gap + pad > gap) + gap += pad; + /* * Top of mmap area (just below the process stack). * Leave an at least ~128 MB hole with possible stack randomization. */ - gap_min = SIZE_128M + stack_maxrandom_size(task_size); + gap_min = SIZE_128M; gap_max = (task_size / 6) * 5; if (gap < gap_min) -- cgit v1.2.3-59-g8ed1b From cf92251dc52d2dfae6c6adaeae8b12ea50686946 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Wed, 12 Jul 2017 14:36:36 -0700 Subject: arm64/mmap: properly account for stack randomization in mmap_base When RLIMIT_STACK is, for example, 256MB, the current code results in a gap between the top of the task and mmap_base of 256MB, failing to take into account the amount by which the stack address was randomized. In other words, the stack gets less than RLIMIT_STACK space. Ensure that the gap between the stack and mmap_base always takes stack randomization and the stack guard gap into account. Obtained from Daniel Micay's linux-hardened tree. Link: http://lkml.kernel.org/r/20170622200033.25714-3-riel@redhat.com Signed-off-by: Daniel Micay Signed-off-by: Rik van Riel Reported-by: Florian Weimer Cc: Ingo Molnar Cc: Will Deacon Cc: Daniel Micay Cc: Benjamin Herrenschmidt Cc: Hugh Dickins Cc: Catalin Marinas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/mm/mmap.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index adc208c2ae9c..decccffb03ca 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -35,7 +35,7 @@ * Leave enough space between the mmap area and the stack to honour ulimit in * the face of randomisation. */ -#define MIN_GAP (SZ_128M + ((STACK_RND_MASK << PAGE_SHIFT) + 1)) +#define MIN_GAP (SZ_128M) #define MAX_GAP (STACK_TOP/6*5) static int mmap_is_legacy(void) @@ -65,6 +65,11 @@ unsigned long arch_mmap_rnd(void) static unsigned long mmap_base(unsigned long rnd) { unsigned long gap = rlimit(RLIMIT_STACK); + unsigned long pad = (STACK_RND_MASK << PAGE_SHIFT) + stack_guard_gap; + + /* Values close to RLIM_INFINITY can overflow. */ + if (gap + pad > gap) + gap += pad; if (gap < MIN_GAP) gap = MIN_GAP; -- cgit v1.2.3-59-g8ed1b From 0a782dc31f4d867921eb7caf1f4bb1222e45bb0e Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Wed, 12 Jul 2017 14:36:39 -0700 Subject: powerpc,mmap: properly account for stack randomization in mmap_base When RLIMIT_STACK is, for example, 256MB, the current code results in a gap between the top of the task and mmap_base of 256MB, failing to take into account the amount by which the stack address was randomized. In other words, the stack gets less than RLIMIT_STACK space. Ensure that the gap between the stack and mmap_base always takes stack randomization and the stack guard gap into account. Inspired by Daniel Micay's linux-hardened tree. Link: http://lkml.kernel.org/r/20170622200033.25714-4-riel@redhat.com Signed-off-by: Rik van Riel Reported-by: Florian Weimer Cc: Ingo Molnar Cc: Will Deacon Cc: Daniel Micay Cc: Benjamin Herrenschmidt Cc: Hugh Dickins Cc: Catalin Marinas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/mm/mmap.c | 28 +++++++++++++++++++--------- 1 file changed, 19 insertions(+), 9 deletions(-) diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c index 0ee6be4f1ba4..5d78b193fec4 100644 --- a/arch/powerpc/mm/mmap.c +++ b/arch/powerpc/mm/mmap.c @@ -34,16 +34,9 @@ /* * Top of mmap area (just below the process stack). * - * Leave at least a ~128 MB hole on 32bit applications. - * - * On 64bit applications we randomise the stack by 1GB so we need to - * space our mmap start address by a further 1GB, otherwise there is a - * chance the mmap area will end up closer to the stack than our ulimit - * requires. + * Leave at least a ~128 MB hole. */ -#define MIN_GAP32 (128*1024*1024) -#define MIN_GAP64 ((128 + 1024)*1024*1024UL) -#define MIN_GAP ((is_32bit_task()) ? MIN_GAP32 : MIN_GAP64) +#define MIN_GAP (128*1024*1024) #define MAX_GAP (TASK_SIZE/6*5) static inline int mmap_is_legacy(void) @@ -71,9 +64,26 @@ unsigned long arch_mmap_rnd(void) return rnd << PAGE_SHIFT; } +static inline unsigned long stack_maxrandom_size(void) +{ + if (!(current->flags & PF_RANDOMIZE)) + return 0; + + /* 8MB for 32bit, 1GB for 64bit */ + if (is_32bit_task()) + return (1<<23); + else + return (1<<30); +} + static inline unsigned long mmap_base(unsigned long rnd) { unsigned long gap = rlimit(RLIMIT_STACK); + unsigned long pad = stack_maxrandom_size() + stack_guard_gap; + + /* Values close to RLIM_INFINITY can overflow. */ + if (gap + pad > gap) + gap += pad; if (gap < MIN_GAP) gap = MIN_GAP; -- cgit v1.2.3-59-g8ed1b From 473738eb78c3e379d682fb8a3cf7e1d17beded9f Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 12 Jul 2017 14:36:42 -0700 Subject: MIPS: do not use __GFP_REPEAT for order-0 request Patch series "mm: give __GFP_REPEAT a better semantic". The main motivation for the change is that the current implementation of __GFP_REPEAT is not very much useful. The documentation says: * __GFP_REPEAT: Try hard to allocate the memory, but the allocation attempt * _might_ fail. This depends upon the particular VM implementation. It just fails to mention that this is true only for large (costly) high order which has been the case since the flag was introduced. A similar semantic would be really helpful for smal orders as well, though, because we have places where a failure with a specific fallback error handling is preferred to a potential endless loop inside the page allocator. The earlier cleanup dropped __GFP_REPEAT usage for low (!costly) order users so only those which might use larger orders have stayed. One new user added in the meantime is addressed in patch 1. Let's rename the flag to something more verbose and use it for existing users. Semantic for those will not change. Then implement low (!costly) orders failure path which is hit after the page allocator is about to invoke the oom killer. With that we have a good counterpart for __GFP_NORETRY and finally can tell try as hard as possible without the OOM killer. Xfs code already has an existing annotation for allocations which are allowed to fail and we can trivially map them to the new gfp flag because it will provide the semantic KM_MAYFAIL wants. Christoph didn't consider the new flag really necessary but didn't respond to the OOM killer aspect of the change so I have kept the patch. If this is still seen as not really needed I can drop the patch. kvmalloc will allow also !costly high order allocations to retry hard before falling back to the vmalloc. drm/i915 asked for the new semantic explicitly. Memory migration code, especially for the memory hotplug, should back off rather than invoking the OOM killer as well. This patch (of 6): Commit 3377e227af44 ("MIPS: Add 48-bit VA space (and 4-level page tables) for 4K pages.") has added a new __GFP_REPEAT user but using this flag doesn't really make any sense for order-0 request which is the case here because PUD_ORDER is 0. __GFP_REPEAT has historically effect only on allocation requests with order > PAGE_ALLOC_COSTLY_ORDER. This doesn't introduce any functional change. This is a preparatory patch for later work which renames the flag and redefines its semantic. Link: http://lkml.kernel.org/r/20170623085345.11304-2-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Alex Belits Cc: David Daney Cc: Ralf Baechle Cc: Johannes Weiner Cc: Mel Gorman Cc: NeilBrown Cc: Christoph Hellwig Cc: Chris Wilson Cc: Darrick J. Wong Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/mips/include/asm/pgalloc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h index a1bdb1ea5234..39b9f311c4ef 100644 --- a/arch/mips/include/asm/pgalloc.h +++ b/arch/mips/include/asm/pgalloc.h @@ -116,7 +116,7 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) { pud_t *pud; - pud = (pud_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT, PUD_ORDER); + pud = (pud_t *) __get_free_pages(GFP_KERNEL, PUD_ORDER); if (pud) pud_init((unsigned long)pud, (unsigned long)invalid_pmd_table); return pud; -- cgit v1.2.3-59-g8ed1b From dcda9b04713c3f6ff0875652924844fae28286ea Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 12 Jul 2017 14:36:45 -0700 Subject: mm, tree wide: replace __GFP_REPEAT by __GFP_RETRY_MAYFAIL with more useful semantic __GFP_REPEAT was designed to allow retry-but-eventually-fail semantic to the page allocator. This has been true but only for allocations requests larger than PAGE_ALLOC_COSTLY_ORDER. It has been always ignored for smaller sizes. This is a bit unfortunate because there is no way to express the same semantic for those requests and they are considered too important to fail so they might end up looping in the page allocator for ever, similarly to GFP_NOFAIL requests. Now that the whole tree has been cleaned up and accidental or misled usage of __GFP_REPEAT flag has been removed for !costly requests we can give the original flag a better name and more importantly a more useful semantic. Let's rename it to __GFP_RETRY_MAYFAIL which tells the user that the allocator would try really hard but there is no promise of a success. This will work independent of the order and overrides the default allocator behavior. Page allocator users have several levels of guarantee vs. cost options (take GFP_KERNEL as an example) - GFP_KERNEL & ~__GFP_RECLAIM - optimistic allocation without _any_ attempt to free memory at all. The most light weight mode which even doesn't kick the background reclaim. Should be used carefully because it might deplete the memory and the next user might hit the more aggressive reclaim - GFP_KERNEL & ~__GFP_DIRECT_RECLAIM (or GFP_NOWAIT)- optimistic allocation without any attempt to free memory from the current context but can wake kswapd to reclaim memory if the zone is below the low watermark. Can be used from either atomic contexts or when the request is a performance optimization and there is another fallback for a slow path. - (GFP_KERNEL|__GFP_HIGH) & ~__GFP_DIRECT_RECLAIM (aka GFP_ATOMIC) - non sleeping allocation with an expensive fallback so it can access some portion of memory reserves. Usually used from interrupt/bh context with an expensive slow path fallback. - GFP_KERNEL - both background and direct reclaim are allowed and the _default_ page allocator behavior is used. That means that !costly allocation requests are basically nofail but there is no guarantee of that behavior so failures have to be checked properly by callers (e.g. OOM killer victim is allowed to fail currently). - GFP_KERNEL | __GFP_NORETRY - overrides the default allocator behavior and all allocation requests fail early rather than cause disruptive reclaim (one round of reclaim in this implementation). The OOM killer is not invoked. - GFP_KERNEL | __GFP_RETRY_MAYFAIL - overrides the default allocator behavior and all allocation requests try really hard. The request will fail if the reclaim cannot make any progress. The OOM killer won't be triggered. - GFP_KERNEL | __GFP_NOFAIL - overrides the default allocator behavior and all allocation requests will loop endlessly until they succeed. This might be really dangerous especially for larger orders. Existing users of __GFP_REPEAT are changed to __GFP_RETRY_MAYFAIL because they already had their semantic. No new users are added. __alloc_pages_slowpath is changed to bail out for __GFP_RETRY_MAYFAIL if there is no progress and we have already passed the OOM point. This means that all the reclaim opportunities have been exhausted except the most disruptive one (the OOM killer) and a user defined fallback behavior is more sensible than keep retrying in the page allocator. [akpm@linux-foundation.org: fix arch/sparc/kernel/mdesc.c] [mhocko@suse.com: semantic fix] Link: http://lkml.kernel.org/r/20170626123847.GM11534@dhcp22.suse.cz [mhocko@kernel.org: address other thing spotted by Vlastimil] Link: http://lkml.kernel.org/r/20170626124233.GN11534@dhcp22.suse.cz Link: http://lkml.kernel.org/r/20170623085345.11304-3-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Alex Belits Cc: Chris Wilson Cc: Christoph Hellwig Cc: Darrick J. Wong Cc: David Daney Cc: Johannes Weiner Cc: Mel Gorman Cc: NeilBrown Cc: Ralf Baechle Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/DMA-ISA-LPC.txt | 2 +- arch/powerpc/include/asm/book3s/64/pgalloc.h | 2 +- arch/powerpc/kvm/book3s_64_mmu_hv.c | 2 +- arch/sparc/kernel/mdesc.c | 2 +- drivers/mmc/host/wbsd.c | 2 +- drivers/s390/char/vmcp.c | 2 +- drivers/target/target_core_transport.c | 2 +- drivers/vhost/net.c | 2 +- drivers/vhost/scsi.c | 2 +- drivers/vhost/vsock.c | 2 +- include/linux/gfp.h | 56 +++++++++++++++++++++------- include/linux/slab.h | 3 +- include/trace/events/mmflags.h | 2 +- mm/hugetlb.c | 4 +- mm/internal.h | 2 +- mm/page_alloc.c | 14 +++++-- mm/sparse-vmemmap.c | 4 +- mm/util.c | 6 +-- mm/vmalloc.c | 2 +- mm/vmscan.c | 8 ++-- net/core/dev.c | 6 +-- net/core/skbuff.c | 2 +- net/sched/sch_fq.c | 2 +- tools/perf/builtin-kmem.c | 2 +- 24 files changed, 86 insertions(+), 47 deletions(-) diff --git a/Documentation/DMA-ISA-LPC.txt b/Documentation/DMA-ISA-LPC.txt index c41331398752..7a065ac4a9d1 100644 --- a/Documentation/DMA-ISA-LPC.txt +++ b/Documentation/DMA-ISA-LPC.txt @@ -42,7 +42,7 @@ requirements you pass the flag GFP_DMA to kmalloc. Unfortunately the memory available for ISA DMA is scarce so unless you allocate the memory during boot-up it's a good idea to also pass -__GFP_REPEAT and __GFP_NOWARN to make the allocator try a bit harder. +__GFP_RETRY_MAYFAIL and __GFP_NOWARN to make the allocator try a bit harder. (This scarcity also means that you should allocate the buffer as early as possible and not release it until the driver is unloaded.) diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h index 20b1485ff1e8..e2329db9d6f4 100644 --- a/arch/powerpc/include/asm/book3s/64/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -56,7 +56,7 @@ static inline pgd_t *radix__pgd_alloc(struct mm_struct *mm) return (pgd_t *)__get_free_page(pgtable_gfp_flags(mm, PGALLOC_GFP)); #else struct page *page; - page = alloc_pages(pgtable_gfp_flags(mm, PGALLOC_GFP | __GFP_REPEAT), + page = alloc_pages(pgtable_gfp_flags(mm, PGALLOC_GFP | __GFP_RETRY_MAYFAIL), 4); if (!page) return NULL; diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 710e491206ed..8cb0190e2a73 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -93,7 +93,7 @@ int kvmppc_allocate_hpt(struct kvm_hpt_info *info, u32 order) } if (!hpt) - hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT + hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_RETRY_MAYFAIL |__GFP_NOWARN, order - PAGE_SHIFT); if (!hpt) diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c index e4b4e790bf89..fa466ce45bc9 100644 --- a/arch/sparc/kernel/mdesc.c +++ b/arch/sparc/kernel/mdesc.c @@ -205,7 +205,7 @@ static struct mdesc_handle *mdesc_kmalloc(unsigned int mdesc_size) handle_size = (sizeof(struct mdesc_handle) - sizeof(struct mdesc_hdr) + mdesc_size); - base = kmalloc(handle_size + 15, GFP_KERNEL | __GFP_REPEAT); + base = kmalloc(handle_size + 15, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!base) return NULL; diff --git a/drivers/mmc/host/wbsd.c b/drivers/mmc/host/wbsd.c index e15a9733fcfd..9668616faf16 100644 --- a/drivers/mmc/host/wbsd.c +++ b/drivers/mmc/host/wbsd.c @@ -1386,7 +1386,7 @@ static void wbsd_request_dma(struct wbsd_host *host, int dma) * order for ISA to be able to DMA to it. */ host->dma_buffer = kmalloc(WBSD_DMA_SIZE, - GFP_NOIO | GFP_DMA | __GFP_REPEAT | __GFP_NOWARN); + GFP_NOIO | GFP_DMA | __GFP_RETRY_MAYFAIL | __GFP_NOWARN); if (!host->dma_buffer) goto free; diff --git a/drivers/s390/char/vmcp.c b/drivers/s390/char/vmcp.c index 65f5a794f26d..98749fa817da 100644 --- a/drivers/s390/char/vmcp.c +++ b/drivers/s390/char/vmcp.c @@ -98,7 +98,7 @@ vmcp_write(struct file *file, const char __user *buff, size_t count, } if (!session->response) session->response = (char *)__get_free_pages(GFP_KERNEL - | __GFP_REPEAT | GFP_DMA, + | __GFP_RETRY_MAYFAIL | GFP_DMA, get_order(session->bufsize)); if (!session->response) { mutex_unlock(&session->mutex); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index f1b3a46bdcaf..1bdc10651bcd 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -252,7 +252,7 @@ int transport_alloc_session_tags(struct se_session *se_sess, int rc; se_sess->sess_cmd_map = kzalloc(tag_num * tag_size, - GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); + GFP_KERNEL | __GFP_NOWARN | __GFP_RETRY_MAYFAIL); if (!se_sess->sess_cmd_map) { se_sess->sess_cmd_map = vzalloc(tag_num * tag_size); if (!se_sess->sess_cmd_map) { diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index e3d7ea1288c6..06d044862e58 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -897,7 +897,7 @@ static int vhost_net_open(struct inode *inode, struct file *f) struct sk_buff **queue; int i; - n = kvmalloc(sizeof *n, GFP_KERNEL | __GFP_REPEAT); + n = kvmalloc(sizeof *n, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!n) return -ENOMEM; vqs = kmalloc(VHOST_NET_VQ_MAX * sizeof(*vqs), GFP_KERNEL); diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index fd6c8b66f06f..ff02a942c4d5 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -1404,7 +1404,7 @@ static int vhost_scsi_open(struct inode *inode, struct file *f) struct vhost_virtqueue **vqs; int r = -ENOMEM, i; - vs = kzalloc(sizeof(*vs), GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); + vs = kzalloc(sizeof(*vs), GFP_KERNEL | __GFP_NOWARN | __GFP_RETRY_MAYFAIL); if (!vs) { vs = vzalloc(sizeof(*vs)); if (!vs) diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 3f63e03de8e8..c9de9c41aa97 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -508,7 +508,7 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file) /* This struct is large and allocation could fail, fall back to vmalloc * if there is no other way. */ - vsock = kvmalloc(sizeof(*vsock), GFP_KERNEL | __GFP_REPEAT); + vsock = kvmalloc(sizeof(*vsock), GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!vsock) return -ENOMEM; diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 4c6656f1fee7..bcfb9f7c46f5 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -25,7 +25,7 @@ struct vm_area_struct; #define ___GFP_FS 0x80u #define ___GFP_COLD 0x100u #define ___GFP_NOWARN 0x200u -#define ___GFP_REPEAT 0x400u +#define ___GFP_RETRY_MAYFAIL 0x400u #define ___GFP_NOFAIL 0x800u #define ___GFP_NORETRY 0x1000u #define ___GFP_MEMALLOC 0x2000u @@ -136,26 +136,56 @@ struct vm_area_struct; * * __GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim. * - * __GFP_REPEAT: Try hard to allocate the memory, but the allocation attempt - * _might_ fail. This depends upon the particular VM implementation. + * The default allocator behavior depends on the request size. We have a concept + * of so called costly allocations (with order > PAGE_ALLOC_COSTLY_ORDER). + * !costly allocations are too essential to fail so they are implicitly + * non-failing by default (with some exceptions like OOM victims might fail so + * the caller still has to check for failures) while costly requests try to be + * not disruptive and back off even without invoking the OOM killer. + * The following three modifiers might be used to override some of these + * implicit rules + * + * __GFP_NORETRY: The VM implementation will try only very lightweight + * memory direct reclaim to get some memory under memory pressure (thus + * it can sleep). It will avoid disruptive actions like OOM killer. The + * caller must handle the failure which is quite likely to happen under + * heavy memory pressure. The flag is suitable when failure can easily be + * handled at small cost, such as reduced throughput + * + * __GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim + * procedures that have previously failed if there is some indication + * that progress has been made else where. It can wait for other + * tasks to attempt high level approaches to freeing memory such as + * compaction (which removes fragmentation) and page-out. + * There is still a definite limit to the number of retries, but it is + * a larger limit than with __GFP_NORETRY. + * Allocations with this flag may fail, but only when there is + * genuinely little unused memory. While these allocations do not + * directly trigger the OOM killer, their failure indicates that + * the system is likely to need to use the OOM killer soon. The + * caller must handle failure, but can reasonably do so by failing + * a higher-level request, or completing it only in a much less + * efficient manner. + * If the allocation does fail, and the caller is in a position to + * free some non-essential memory, doing so could benefit the system + * as a whole. * * __GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller - * cannot handle allocation failures. New users should be evaluated carefully - * (and the flag should be used only when there is no reasonable failure - * policy) but it is definitely preferable to use the flag rather than - * opencode endless loop around allocator. - * - * __GFP_NORETRY: The VM implementation must not retry indefinitely and will - * return NULL when direct reclaim and memory compaction have failed to allow - * the allocation to succeed. The OOM killer is not called with the current - * implementation. + * cannot handle allocation failures. The allocation could block + * indefinitely but will never return with failure. Testing for + * failure is pointless. + * New users should be evaluated carefully (and the flag should be + * used only when there is no reasonable failure policy) but it is + * definitely preferable to use the flag rather than opencode endless + * loop around allocator. + * Using this flag for costly allocations is _highly_ discouraged. */ #define __GFP_IO ((__force gfp_t)___GFP_IO) #define __GFP_FS ((__force gfp_t)___GFP_FS) #define __GFP_DIRECT_RECLAIM ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */ #define __GFP_KSWAPD_RECLAIM ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */ #define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM)) -#define __GFP_REPEAT ((__force gfp_t)___GFP_REPEAT) +#define __GFP_RETRY_MAYFAIL ((__force gfp_t)___GFP_RETRY_MAYFAIL) #define __GFP_NOFAIL ((__force gfp_t)___GFP_NOFAIL) #define __GFP_NORETRY ((__force gfp_t)___GFP_NORETRY) diff --git a/include/linux/slab.h b/include/linux/slab.h index 04a7f7993e67..41473df6dfb0 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -471,7 +471,8 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) * * %__GFP_NOWARN - If allocation fails, don't issue any warnings. * - * %__GFP_REPEAT - If allocation fails initially, try once more before failing. + * %__GFP_RETRY_MAYFAIL - Try really hard to succeed the allocation but fail + * eventually. * * There are other flags available as well, but these are not intended * for general use, and so are not documented here. For a full list of diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 10e3663a75a6..8e50d01c645f 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -34,7 +34,7 @@ {(unsigned long)__GFP_FS, "__GFP_FS"}, \ {(unsigned long)__GFP_COLD, "__GFP_COLD"}, \ {(unsigned long)__GFP_NOWARN, "__GFP_NOWARN"}, \ - {(unsigned long)__GFP_REPEAT, "__GFP_REPEAT"}, \ + {(unsigned long)__GFP_RETRY_MAYFAIL, "__GFP_RETRY_MAYFAIL"}, \ {(unsigned long)__GFP_NOFAIL, "__GFP_NOFAIL"}, \ {(unsigned long)__GFP_NORETRY, "__GFP_NORETRY"}, \ {(unsigned long)__GFP_COMP, "__GFP_COMP"}, \ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 1e516520433d..bc48ee783dd9 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1384,7 +1384,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) page = __alloc_pages_node(nid, htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE| - __GFP_REPEAT|__GFP_NOWARN, + __GFP_RETRY_MAYFAIL|__GFP_NOWARN, huge_page_order(h)); if (page) { prep_new_huge_page(h, page, nid); @@ -1525,7 +1525,7 @@ static struct page *__hugetlb_alloc_buddy_huge_page(struct hstate *h, { int order = huge_page_order(h); - gfp_mask |= __GFP_COMP|__GFP_REPEAT|__GFP_NOWARN; + gfp_mask |= __GFP_COMP|__GFP_RETRY_MAYFAIL|__GFP_NOWARN; if (nid == NUMA_NO_NODE) nid = numa_mem_id(); return __alloc_pages_nodemask(gfp_mask, order, nid, nmask); diff --git a/mm/internal.h b/mm/internal.h index 0e4f558412fb..24d88f084705 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -23,7 +23,7 @@ * hints such as HIGHMEM usage. */ #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\ - __GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\ + __GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\ __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\ __GFP_ATOMIC) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 64b7d82a9b1a..6d30e914afb6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3284,6 +3284,14 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, /* The OOM killer will not help higher order allocs */ if (order > PAGE_ALLOC_COSTLY_ORDER) goto out; + /* + * We have already exhausted all our reclaim opportunities without any + * success so it is time to admit defeat. We will skip the OOM killer + * because it is very likely that the caller has a more reasonable + * fallback than shooting a random task. + */ + if (gfp_mask & __GFP_RETRY_MAYFAIL) + goto out; /* The OOM killer does not needlessly kill tasks for lowmem */ if (ac->high_zoneidx < ZONE_NORMAL) goto out; @@ -3413,7 +3421,7 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, } /* - * !costly requests are much more important than __GFP_REPEAT + * !costly requests are much more important than __GFP_RETRY_MAYFAIL * costly ones because they are de facto nofail and invoke OOM * killer to move on while costly can fail and users are ready * to cope with that. 1/4 retries is rather arbitrary but we @@ -3920,9 +3928,9 @@ retry: /* * Do not retry costly high order allocations unless they are - * __GFP_REPEAT + * __GFP_RETRY_MAYFAIL */ - if (costly_order && !(gfp_mask & __GFP_REPEAT)) + if (costly_order && !(gfp_mask & __GFP_RETRY_MAYFAIL)) goto nopage; if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags, diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index a56c3989f773..c50b1a14d55e 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -56,11 +56,11 @@ void * __meminit vmemmap_alloc_block(unsigned long size, int node) if (node_state(node, N_HIGH_MEMORY)) page = alloc_pages_node( - node, GFP_KERNEL | __GFP_ZERO | __GFP_REPEAT, + node, GFP_KERNEL | __GFP_ZERO | __GFP_RETRY_MAYFAIL, get_order(size)); else page = alloc_pages( - GFP_KERNEL | __GFP_ZERO | __GFP_REPEAT, + GFP_KERNEL | __GFP_ZERO | __GFP_RETRY_MAYFAIL, get_order(size)); if (page) return page_address(page); diff --git a/mm/util.c b/mm/util.c index 26be6407abd7..6520f2d4a226 100644 --- a/mm/util.c +++ b/mm/util.c @@ -339,7 +339,7 @@ EXPORT_SYMBOL(vm_mmap); * Uses kmalloc to get the memory but if the allocation fails then falls back * to the vmalloc allocator. Use kvfree for freeing the memory. * - * Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported. __GFP_REPEAT + * Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported. __GFP_RETRY_MAYFAIL * is supported only for large (>32kB) allocations, and it should be used only if * kmalloc is preferable to the vmalloc fallback, due to visible performance drawbacks. * @@ -367,11 +367,11 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) kmalloc_flags |= __GFP_NOWARN; /* - * We have to override __GFP_REPEAT by __GFP_NORETRY for !costly + * We have to override __GFP_RETRY_MAYFAIL by __GFP_NORETRY for !costly * requests because there is no other way to tell the allocator * that we want to fail rather than retry endlessly. */ - if (!(kmalloc_flags & __GFP_REPEAT) || + if (!(kmalloc_flags & __GFP_RETRY_MAYFAIL) || (size <= PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) kmalloc_flags |= __GFP_NORETRY; } diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 6016ab079e2b..8698c1c86c4d 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1795,7 +1795,7 @@ fail: * allocator with @gfp_mask flags. Map them into contiguous * kernel virtual space, using a pagetable protection of @prot. * - * Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_REPEAT + * Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_RETRY_MAYFAIL * and __GFP_NOFAIL are not supported * * Any use of gfp flags outside of GFP_KERNEL should be consulted diff --git a/mm/vmscan.c b/mm/vmscan.c index e9210f825219..a1af041930a6 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2506,18 +2506,18 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat, return false; /* Consider stopping depending on scan and reclaim activity */ - if (sc->gfp_mask & __GFP_REPEAT) { + if (sc->gfp_mask & __GFP_RETRY_MAYFAIL) { /* - * For __GFP_REPEAT allocations, stop reclaiming if the + * For __GFP_RETRY_MAYFAIL allocations, stop reclaiming if the * full LRU list has been scanned and we are still failing * to reclaim pages. This full LRU scan is potentially - * expensive but a __GFP_REPEAT caller really wants to succeed + * expensive but a __GFP_RETRY_MAYFAIL caller really wants to succeed */ if (!nr_reclaimed && !nr_scanned) return false; } else { /* - * For non-__GFP_REPEAT allocations which can presumably + * For non-__GFP_RETRY_MAYFAIL allocations which can presumably * fail without consequence, stop if we failed to reclaim * any pages from the last SWAP_CLUSTER_MAX number of * pages that were scanned. This will return to the diff --git a/net/core/dev.c b/net/core/dev.c index 02440518dd69..8515f8fe0460 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7384,7 +7384,7 @@ static int netif_alloc_rx_queues(struct net_device *dev) BUG_ON(count < 1); - rx = kvzalloc(sz, GFP_KERNEL | __GFP_REPEAT); + rx = kvzalloc(sz, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!rx) return -ENOMEM; @@ -7424,7 +7424,7 @@ static int netif_alloc_netdev_queues(struct net_device *dev) if (count < 1 || count > 0xffff) return -EINVAL; - tx = kvzalloc(sz, GFP_KERNEL | __GFP_REPEAT); + tx = kvzalloc(sz, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!tx) return -ENOMEM; @@ -7965,7 +7965,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, /* ensure 32-byte alignment of whole construct */ alloc_size += NETDEV_ALIGN - 1; - p = kvzalloc(alloc_size, GFP_KERNEL | __GFP_REPEAT); + p = kvzalloc(alloc_size, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!p) return NULL; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 8b11341ed69a..f990eb8b30a9 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4747,7 +4747,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, gfp_head = gfp_mask; if (gfp_head & __GFP_DIRECT_RECLAIM) - gfp_head |= __GFP_REPEAT; + gfp_head |= __GFP_RETRY_MAYFAIL; *errcode = -ENOBUFS; skb = alloc_skb(header_len, gfp_head); diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 147fde73a0f5..263d16e3219e 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -648,7 +648,7 @@ static int fq_resize(struct Qdisc *sch, u32 log) return 0; /* If XPS was setup, we can allocate memory on right NUMA node */ - array = kvmalloc_node(sizeof(struct rb_root) << log, GFP_KERNEL | __GFP_REPEAT, + array = kvmalloc_node(sizeof(struct rb_root) << log, GFP_KERNEL | __GFP_RETRY_MAYFAIL, netdev_queue_numa_node_read(sch->dev_queue)); if (!array) return -ENOMEM; diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 0a8a1c45af87..a1497c516d85 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -643,7 +643,7 @@ static const struct { { "__GFP_FS", "F" }, { "__GFP_COLD", "CO" }, { "__GFP_NOWARN", "NWR" }, - { "__GFP_REPEAT", "R" }, + { "__GFP_RETRY_MAYFAIL", "R" }, { "__GFP_NOFAIL", "NF" }, { "__GFP_NORETRY", "NR" }, { "__GFP_COMP", "C" }, -- cgit v1.2.3-59-g8ed1b From 91c63ecda75d3004da8ffd5d2590383e0ba47722 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 12 Jul 2017 14:36:49 -0700 Subject: xfs: map KM_MAYFAIL to __GFP_RETRY_MAYFAIL KM_MAYFAIL didn't have any suitable GFP_FOO counterpart until recently so it relied on the default page allocator behavior for the given set of flags. This means that small allocations actually never failed. Now that we have __GFP_RETRY_MAYFAIL flag which works independently on the allocation request size we can map KM_MAYFAIL to it. The allocator will try as hard as it can to fulfill the request but fails eventually if the progress cannot be made. It does so without triggering the OOM killer which can be seen as an improvement because KM_MAYFAIL users should be able to deal with allocation failures. Link: http://lkml.kernel.org/r/20170623085345.11304-4-mhocko@kernel.org Signed-off-by: Michal Hocko Cc: Darrick J. Wong Cc: Christoph Hellwig Cc: Alex Belits Cc: Chris Wilson Cc: David Daney Cc: Johannes Weiner Cc: Mel Gorman Cc: NeilBrown Cc: Ralf Baechle Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/xfs/kmem.h | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h index d6ea520162b2..4d85992d75b2 100644 --- a/fs/xfs/kmem.h +++ b/fs/xfs/kmem.h @@ -54,6 +54,16 @@ kmem_flags_convert(xfs_km_flags_t flags) lflags &= ~__GFP_FS; } + /* + * Default page/slab allocator behavior is to retry for ever + * for small allocations. We can override this behavior by using + * __GFP_RETRY_MAYFAIL which will tell the allocator to retry as long + * as it is feasible but rather fail than retry forever for all + * request sizes. + */ + if (flags & KM_MAYFAIL) + lflags |= __GFP_RETRY_MAYFAIL; + if (flags & KM_ZERO) lflags |= __GFP_ZERO; -- cgit v1.2.3-59-g8ed1b From cc965a29db172c28e25b9742db86a85766a08bf5 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 12 Jul 2017 14:36:52 -0700 Subject: mm: kvmalloc support __GFP_RETRY_MAYFAIL for all sizes Now that __GFP_RETRY_MAYFAIL has a reasonable semantic regardless of the request size we can drop the hackish implementation for !costly orders. __GFP_RETRY_MAYFAIL retries as long as the reclaim makes a forward progress and backs of when we are out of memory for the requested size. Therefore we do not need to enforce__GFP_NORETRY for !costly orders just to silent the oom killer anymore. Link: http://lkml.kernel.org/r/20170623085345.11304-5-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Alex Belits Cc: Chris Wilson Cc: Christoph Hellwig Cc: Darrick J. Wong Cc: David Daney Cc: Johannes Weiner Cc: Mel Gorman Cc: NeilBrown Cc: Ralf Baechle Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/util.c | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) diff --git a/mm/util.c b/mm/util.c index 6520f2d4a226..ee250e2cde34 100644 --- a/mm/util.c +++ b/mm/util.c @@ -339,9 +339,9 @@ EXPORT_SYMBOL(vm_mmap); * Uses kmalloc to get the memory but if the allocation fails then falls back * to the vmalloc allocator. Use kvfree for freeing the memory. * - * Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported. __GFP_RETRY_MAYFAIL - * is supported only for large (>32kB) allocations, and it should be used only if - * kmalloc is preferable to the vmalloc fallback, due to visible performance drawbacks. + * Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported. + * __GFP_RETRY_MAYFAIL is supported, and it should be used only if kmalloc is + * preferable to the vmalloc fallback, due to visible performance drawbacks. * * Any use of gfp flags outside of GFP_KERNEL should be consulted with mm people. */ @@ -366,13 +366,7 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) if (size > PAGE_SIZE) { kmalloc_flags |= __GFP_NOWARN; - /* - * We have to override __GFP_RETRY_MAYFAIL by __GFP_NORETRY for !costly - * requests because there is no other way to tell the allocator - * that we want to fail rather than retry endlessly. - */ - if (!(kmalloc_flags & __GFP_RETRY_MAYFAIL) || - (size <= PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) + if (!(kmalloc_flags & __GFP_RETRY_MAYFAIL)) kmalloc_flags |= __GFP_NORETRY; } -- cgit v1.2.3-59-g8ed1b From dbb329561ae9ccfb942b6ba330030a4654e8908e Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 12 Jul 2017 14:36:55 -0700 Subject: drm/i915: use __GFP_RETRY_MAYFAIL Commit 24f8e00a8a2e ("drm/i915: Prefer to report ENOMEM rather than incur the oom for gfx allocations") has tried to remove disruptive OOM killer because the userspace should be able to cope with allocation failures. At the time only __GFP_NORETRY could achieve that and it turned out that this would fail the allocations just too easily. So "drm/i915: Remove __GFP_NORETRY from our buffer allocator" removed it and hoped for a better solution. __GFP_RETRY_MAYFAIL is that solution. It will keep retrying the allocation until there is no more progress and we would go OOM. Instead we fail the allocation and let the caller to deal with it. Link: http://lkml.kernel.org/r/20170623085345.11304-6-mhocko@kernel.org Signed-off-by: Michal Hocko Cc: Chris Wilson Cc: Alex Belits Cc: Christoph Hellwig Cc: Darrick J. Wong Cc: David Daney Cc: Johannes Weiner Cc: Mel Gorman Cc: NeilBrown Cc: Ralf Baechle Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/gpu/drm/i915/i915_gem.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 7dcac3bfb771..969bac8404f1 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2434,8 +2434,9 @@ rebuild_st: * again with !__GFP_NORETRY. However, we still * want to fail this allocation rather than * trigger the out-of-memory killer and for - * this we want the future __GFP_MAYFAIL. + * this we want __GFP_RETRY_MAYFAIL. */ + gfp |= __GFP_RETRY_MAYFAIL; } } while (1); -- cgit v1.2.3-59-g8ed1b From 0f55685627d6dd2beda55a82abc02297f0f8e5c2 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 12 Jul 2017 14:36:58 -0700 Subject: mm, migration: do not trigger OOM killer when migrating memory Page migration (for memory hotplug, soft_offline_page or mbind) needs to allocate a new memory. This can trigger an oom killer if the target memory is depleated. Although quite unlikely, still possible, especially for the memory hotplug (offlining of memoery). Up to now we didn't really have reasonable means to back off. __GFP_NORETRY can fail just too easily and __GFP_THISNODE sticks to a single node and that is not suitable for all callers. But now that we have __GFP_RETRY_MAYFAIL we should use it. It is preferable to fail the migration than disrupt the system by killing some processes. Link: http://lkml.kernel.org/r/20170623085345.11304-7-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Alex Belits Cc: Chris Wilson Cc: Christoph Hellwig Cc: Darrick J. Wong Cc: David Daney Cc: Johannes Weiner Cc: Mel Gorman Cc: NeilBrown Cc: Ralf Baechle Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 2 +- mm/mempolicy.c | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 4634da521238..3e0d405dc842 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -34,7 +34,7 @@ extern char *migrate_reason_names[MR_TYPES]; static inline struct page *new_page_nodemask(struct page *page, int preferred_nid, nodemask_t *nodemask) { - gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE; + gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL; if (PageHuge(page)) return alloc_huge_page_nodemask(page_hstate(compound_head(page)), diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 7d8e56214ac0..d911fa5cb2a7 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1078,7 +1078,8 @@ static struct page *new_page(struct page *page, unsigned long start, int **x) /* * if !vma, alloc_page_vma() will use task or system default policy */ - return alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); + return alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL, + vma, address); } #else -- cgit v1.2.3-59-g8ed1b From 596ed45b5b5b7e4624c813ddeffe0e100f8b13ba Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jul 2017 14:37:02 -0700 Subject: checkpatch: improve the STORAGE_CLASS test Make sure static, extern, and asmlinkage appear before a specific type. e.g.: int asmlinkage foo(void) is better written asmlinkage int foo(void) Link: http://lkml.kernel.org/r/31704c96df2d5fd9df0b41165940a7a4feb16a63.1499284835.git.joe@perches.com Signed-off-by: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/checkpatch.pl | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 8f940c09918f..2287a0bca863 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -5576,10 +5576,18 @@ sub process { "architecture specific defines should be avoided\n" . $herecurr); } +# check that the storage class is not after a type + if ($line =~ /\b($Type)\s+($Storage)\b/) { + WARN("STORAGE_CLASS", + "storage class '$2' should be located before type '$1'\n" . $herecurr); + } # Check that the storage class is at the beginning of a declaration - if ($line =~ /\b$Storage\b/ && $line !~ /^.\s*$Storage\b/) { + if ($line =~ /\b$Storage\b/ && + $line !~ /^.\s*$Storage/ && + $line =~ /^.\s*(.+?)\$Storage\s/ && + $1 !~ /[\,\)]\s*$/) { WARN("STORAGE_CLASS", - "storage class should be at the beginning of the declaration\n" . $herecurr) + "storage class should be at the beginning of the declaration\n" . $herecurr); } # check the location of the inline attribute, that it is between -- cgit v1.2.3-59-g8ed1b From ead9fba6b8e9a81107807f5a221576cb01206a6e Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jul 2017 14:37:05 -0700 Subject: ARM: KVM: move asmlinkage before type asmlinkage is either 'extern "C"' or blank. Move the uses of asmlinkage before the return types to be similar to the rest of the kernel. Link: http://lkml.kernel.org/r/005b8e120650c6a13b541e420f4e3605603fe9e6.1499284835.git.joe@perches.com Signed-off-by: Joe Perches Cc: Christoffer Dall Cc: Marc Zyngier Cc: Paolo Bonzini Cc: Radim Krcmar Cc: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/include/asm/kvm_hyp.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm/include/asm/kvm_hyp.h b/arch/arm/include/asm/kvm_hyp.h index 58508900c4bb..14b5903f0224 100644 --- a/arch/arm/include/asm/kvm_hyp.h +++ b/arch/arm/include/asm/kvm_hyp.h @@ -110,8 +110,8 @@ void __sysreg_restore_state(struct kvm_cpu_context *ctxt); void __vgic_v3_save_state(struct kvm_vcpu *vcpu); void __vgic_v3_restore_state(struct kvm_vcpu *vcpu); -void asmlinkage __vfp_save_state(struct vfp_hard_struct *vfp); -void asmlinkage __vfp_restore_state(struct vfp_hard_struct *vfp); +asmlinkage void __vfp_save_state(struct vfp_hard_struct *vfp); +asmlinkage void __vfp_restore_state(struct vfp_hard_struct *vfp); static inline bool __vfp_enabled(void) { return !(read_sysreg(HCPTR) & (HCPTR_TCP(11) | HCPTR_TCP(10))); @@ -120,8 +120,8 @@ static inline bool __vfp_enabled(void) void __hyp_text __banked_save_state(struct kvm_cpu_context *ctxt); void __hyp_text __banked_restore_state(struct kvm_cpu_context *ctxt); -int asmlinkage __guest_enter(struct kvm_vcpu *vcpu, +asmlinkage int __guest_enter(struct kvm_vcpu *vcpu, struct kvm_cpu_context *host); -int asmlinkage __hyp_do_panic(const char *, int, u32); +asmlinkage int __hyp_do_panic(const char *, int, u32); #endif /* __ARM_KVM_HYP_H__ */ -- cgit v1.2.3-59-g8ed1b From 1e90d0ed327a289c6fee4f36b25f67d3d7864a43 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jul 2017 14:37:08 -0700 Subject: ARM: HP Jornada 7XX: move inline before return type Convert 'u8 inline' to 'inline u8' to be the same style used by the rest of the kernel. Miscellanea: jornada_ssp_reverse is an odd function. It is declared inline but is also EXPORT_SYMBOL. It is also apparently only used by jornada720_ssp.c Likely the EXPORT_SYMBOL could be removed and the function converted to static. The addition of static and removal of EXPORT_SYMBOL was not done. Link: http://lkml.kernel.org/r/5bd3b2bf39c6c9caf773949f18158f8f5ec08582.1499284835.git.joe@perches.com Signed-off-by: Joe Perches Cc: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/mach-sa1100/jornada720_ssp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/mach-sa1100/jornada720_ssp.c b/arch/arm/mach-sa1100/jornada720_ssp.c index b143c4659346..7fc11a3c17b4 100644 --- a/arch/arm/mach-sa1100/jornada720_ssp.c +++ b/arch/arm/mach-sa1100/jornada720_ssp.c @@ -33,7 +33,7 @@ static unsigned long jornada_ssp_flags; * we need to reverse all data we receive from the mcu due to its physical location * returns : 01110111 -> 11101110 */ -u8 inline jornada_ssp_reverse(u8 byte) +inline u8 jornada_ssp_reverse(u8 byte) { return ((0x80 & byte) >> 7) | -- cgit v1.2.3-59-g8ed1b From 8d95a3dca060b09ddafa4cd1c82f27ab19490fad Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jul 2017 14:37:10 -0700 Subject: CRIS: gpio: move inline before return type Move inline to be like the rest of the kernel. Link: http://lkml.kernel.org/r/6bf1bec049897c4158f698b866810f47c728f233.1499284835.git.joe@perches.com Signed-off-by: Joe Perches Cc: Mikael Starvik Cc: Jesper Nilsson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/cris/arch-v10/drivers/gpio.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/cris/arch-v10/drivers/gpio.c b/arch/cris/arch-v10/drivers/gpio.c index 64285e0d3481..dfd3b3ba5e4e 100644 --- a/arch/cris/arch-v10/drivers/gpio.c +++ b/arch/cris/arch-v10/drivers/gpio.c @@ -399,7 +399,7 @@ out: /* Main device API. ioctl's to read/set/clear bits, as well as to * set alarms to wait for using a subsequent select(). */ -unsigned long inline setget_input(struct gpio_private *priv, unsigned long arg) +inline unsigned long setget_input(struct gpio_private *priv, unsigned long arg) { /* Set direction 0=unchanged 1=input, * return mask with 1=input */ @@ -450,7 +450,7 @@ unsigned long inline setget_input(struct gpio_private *priv, unsigned long arg) return dir_g_in_bits; } /* setget_input */ -unsigned long inline setget_output(struct gpio_private *priv, unsigned long arg) +inline unsigned long setget_output(struct gpio_private *priv, unsigned long arg) { if (USE_PORTS(priv)) { *priv->dir = *priv->dir_shadow |= -- cgit v1.2.3-59-g8ed1b From 1d731bb77247b9456680f379c31c30f9774473ce Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jul 2017 14:37:13 -0700 Subject: FRV: tlbflush: move asmlinkage before return type Make the use of asmlinkage like the rest of the kernel. Link: http://lkml.kernel.org/r/efb2dfed4d9315bf68ec0334c81b65af176a0174.1499284835.git.joe@perches.com Signed-off-by: Joe Perches Cc: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/frv/include/asm/tlbflush.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/frv/include/asm/tlbflush.h b/arch/frv/include/asm/tlbflush.h index 7ac5eafc5d98..75879420f578 100644 --- a/arch/frv/include/asm/tlbflush.h +++ b/arch/frv/include/asm/tlbflush.h @@ -18,10 +18,10 @@ #ifdef CONFIG_MMU #ifndef __ASSEMBLY__ -extern void asmlinkage __flush_tlb_all(void); -extern void asmlinkage __flush_tlb_mm(unsigned long contextid); -extern void asmlinkage __flush_tlb_page(unsigned long contextid, unsigned long start); -extern void asmlinkage __flush_tlb_range(unsigned long contextid, +extern asmlinkage void __flush_tlb_all(void); +extern asmlinkage void __flush_tlb_mm(unsigned long contextid); +extern asmlinkage void __flush_tlb_page(unsigned long contextid, unsigned long start); +extern asmlinkage void __flush_tlb_range(unsigned long contextid, unsigned long start, unsigned long end); #endif /* !__ASSEMBLY__ */ -- cgit v1.2.3-59-g8ed1b From d778931d7b32ada39de0a45267b0c4af0600e277 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jul 2017 14:37:16 -0700 Subject: ia64: move inline before return type Make the use of inline like the rest of the kernel. Link: http://lkml.kernel.org/r/d47074493af80ce12590340294bc49618165c30d.1499284835.git.joe@perches.com Signed-off-by: Joe Perches Cc: Tony Luck Cc: Fenghua Yu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/kernel/mca.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index 79c7c46d7dc1..555b11180156 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -334,7 +334,7 @@ static void ia64_mlogbuf_dump_from_init(void) ia64_mlogbuf_dump(); } -static void inline +static inline void ia64_mca_spin(const char *func) { if (monarch_cpu == smp_processor_id()) -- cgit v1.2.3-59-g8ed1b From c02f2a911f2bb833f982d869e3a4ae67e1468969 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jul 2017 14:37:19 -0700 Subject: ia64: sn: pci: move inline before type Make the use of inline like the rest of the kernel. Link: http://lkml.kernel.org/r/f42b2202bd0d4e7ccf79ce5348bb255a035e67bb.1499284835.git.joe@perches.com Signed-off-by: Joe Perches Cc: Tony Luck Cc: Fenghua Yu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/sn/pci/pcibr/pcibr_ate.c | 2 +- arch/ia64/sn/pci/tioce_provider.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/ia64/sn/pci/pcibr/pcibr_ate.c b/arch/ia64/sn/pci/pcibr/pcibr_ate.c index 5bc34eac9e01..b67bb4cb73ff 100644 --- a/arch/ia64/sn/pci/pcibr/pcibr_ate.c +++ b/arch/ia64/sn/pci/pcibr/pcibr_ate.c @@ -140,7 +140,7 @@ static inline u64 __iomem *pcibr_ate_addr(struct pcibus_info *pcibus_info, /* * Update the ate. */ -void inline +inline void ate_write(struct pcibus_info *pcibus_info, int ate_index, int count, volatile u64 ate) { diff --git a/arch/ia64/sn/pci/tioce_provider.c b/arch/ia64/sn/pci/tioce_provider.c index 46d3df4b03a1..3bd9abc35485 100644 --- a/arch/ia64/sn/pci/tioce_provider.c +++ b/arch/ia64/sn/pci/tioce_provider.c @@ -52,7 +52,7 @@ * All registers defined in struct tioce will meet that criteria. */ -static void inline +static inline void tioce_mmr_war_pre(struct tioce_kernel *kern, void __iomem *mmr_addr) { u64 mmr_base; @@ -78,7 +78,7 @@ tioce_mmr_war_pre(struct tioce_kernel *kern, void __iomem *mmr_addr) } } -static void inline +static inline void tioce_mmr_war_post(struct tioce_kernel *kern, void __iomem *mmr_addr) { u64 mmr_base; -- cgit v1.2.3-59-g8ed1b From 9d8a9ae2818fa44099195146a7fa85963409a2e9 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jul 2017 14:37:22 -0700 Subject: m68k: coldfire: move inline before return type Make the code like the rest of the kernel. Link: http://lkml.kernel.org/r/14db9c166d5b68efa77e337cfe49bb9b29bca3f7.1499284835.git.joe@perches.com Signed-off-by: Joe Perches Acked-by: Greg Ungerer Cc: Geert Uytterhoeven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/m68k/coldfire/intc-simr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/m68k/coldfire/intc-simr.c b/arch/m68k/coldfire/intc-simr.c index 7cf2c156f72d..15c4b7a6e38f 100644 --- a/arch/m68k/coldfire/intc-simr.c +++ b/arch/m68k/coldfire/intc-simr.c @@ -35,7 +35,7 @@ #define EINT7 67 /* EDGE Port interrupt 7 */ static unsigned int irqebitmap[] = { 0, 1, 4, 7 }; -static unsigned int inline irq2ebit(unsigned int irq) +static inline unsigned int irq2ebit(unsigned int irq) { return irqebitmap[irq - EINT0]; } @@ -51,7 +51,7 @@ static unsigned int inline irq2ebit(unsigned int irq) #define EINT1 65 /* EDGE Port interrupt 1 */ #define EINT7 71 /* EDGE Port interrupt 7 */ -static unsigned int inline irq2ebit(unsigned int irq) +static inline unsigned int irq2ebit(unsigned int irq) { return irq - EINT0; } -- cgit v1.2.3-59-g8ed1b From b745fcb949f90762e7e126737683e2a26a4e8035 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jul 2017 14:37:25 -0700 Subject: MIPS: SMP: move asmlinkage before return type Make the code like the rest of the kernel. Link: http://lkml.kernel.org/r/756d3fb543e981b9284e756fa27616725a354b28.1499284835.git.joe@perches.com Signed-off-by: Joe Perches Cc: Ralf Baechle Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/mips/include/asm/smp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h index 98a117a05fbc..bab3d41e5987 100644 --- a/arch/mips/include/asm/smp.h +++ b/arch/mips/include/asm/smp.h @@ -47,7 +47,7 @@ extern int __cpu_logical_map[NR_CPUS]; /* Mask of CPUs which are currently definitely operating coherently */ extern cpumask_t cpu_coherent_mask; -extern void asmlinkage smp_bootstrap(void); +extern asmlinkage void smp_bootstrap(void); extern void calculate_cpu_foreign_map(void); -- cgit v1.2.3-59-g8ed1b From 0cef25c1d89fb617683fc76645bb27ab297f2a1e Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jul 2017 14:37:28 -0700 Subject: sh: move inline before return type Make the code like the rest of the kernel. Link: http://lkml.kernel.org/r/f81bb2a67a97b1fd8b6ea99bd350d8a0f6864fb1.1499284835.git.joe@perches.com Signed-off-by: Joe Perches Cc: Yoshinori Sato Cc: Rich Felker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/sh/mm/cache-sh5.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/sh/mm/cache-sh5.c b/arch/sh/mm/cache-sh5.c index d94dadedf74f..445b5e69b73c 100644 --- a/arch/sh/mm/cache-sh5.c +++ b/arch/sh/mm/cache-sh5.c @@ -234,7 +234,7 @@ static void sh64_icache_inv_current_user_range(unsigned long start, unsigned lon #define DUMMY_ALLOCO_AREA_SIZE ((L1_CACHE_BYTES << 10) + (1024 * 4)) static unsigned char dummy_alloco_area[DUMMY_ALLOCO_AREA_SIZE] __cacheline_aligned = { 0, }; -static void inline sh64_dcache_purge_sets(int sets_to_purge_base, int n_sets) +static inline void sh64_dcache_purge_sets(int sets_to_purge_base, int n_sets) { /* Purge all ways in a particular block of sets, specified by the base set number and number of sets. Can handle wrap-around, if that's -- cgit v1.2.3-59-g8ed1b From 0825f49f225bd24c3ae46ff2bb716067e3684fc3 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jul 2017 14:37:31 -0700 Subject: x86/efi: move asmlinkage before return type Make the code like the rest of the kernel. Link: http://lkml.kernel.org/r/1cd3d401626e51ea0e2333a860e76e80bc560a4c.1499284835.git.joe@perches.com Signed-off-by: Joe Perches Cc: Matt Fleming Cc: Ard Biesheuvel Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/efi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index d2ff779f347e..796ff6c1aa53 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -33,7 +33,7 @@ #ifdef CONFIG_X86_32 -extern unsigned long asmlinkage efi_call_phys(void *, ...); +extern asmlinkage unsigned long efi_call_phys(void *, ...); #define arch_efi_call_virt_setup() kernel_fpu_begin() #define arch_efi_call_virt_teardown() kernel_fpu_end() @@ -52,7 +52,7 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...); #define EFI_LOADER_SIGNATURE "EL64" -extern u64 asmlinkage efi_call(void *fp, ...); +extern asmlinkage u64 efi_call(void *fp, ...); #define efi_call_phys(f, args...) efi_call((f), args) -- cgit v1.2.3-59-g8ed1b From e0710e510c59602e4fa80d784c946e02e8968523 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jul 2017 14:37:34 -0700 Subject: drivers: s390: move static and inline before return type Make the code like the rest of the kernel. Link: http://lkml.kernel.org/r/3f980cd89084ae09716353aba3171e4b3815e690.1499284835.git.joe@perches.com Signed-off-by: Joe Perches Cc: Julian Wiedmann Cc: Ursula Braun Cc: Martin Schwidefsky Cc: Heiko Carstens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/s390/net/ctcm_main.c | 2 +- drivers/s390/net/qeth_l3_main.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/s390/net/ctcm_main.c b/drivers/s390/net/ctcm_main.c index 1563b1458e44..2ade6131a89f 100644 --- a/drivers/s390/net/ctcm_main.c +++ b/drivers/s390/net/ctcm_main.c @@ -1115,7 +1115,7 @@ static const struct net_device_ops ctcm_mpc_netdev_ops = { .ndo_start_xmit = ctcmpc_tx, }; -void static ctcm_dev_setup(struct net_device *dev) +static void ctcm_dev_setup(struct net_device *dev) { dev->type = ARPHRD_SLIP; dev->tx_queue_len = 100; diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 3062cde33a3d..8975cd321390 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -2408,7 +2408,7 @@ static int qeth_l3_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) return rc; } -int inline qeth_l3_get_cast_type(struct qeth_card *card, struct sk_buff *skb) +inline int qeth_l3_get_cast_type(struct qeth_card *card, struct sk_buff *skb) { int cast_type = RTN_UNSPEC; struct neighbour *n = NULL; -- cgit v1.2.3-59-g8ed1b From a9e5bfdb9d786efbc6995edfe6902788527457ad Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jul 2017 14:37:37 -0700 Subject: drivers: tty: serial: move inline before return type Make the code like the rest of the kernel. Link: http://lkml.kernel.org/r/55d3e89d50bb03d603bfb28019fab07f48bdc714.1499284835.git.joe@perches.com Signed-off-by: Joe Perches Cc: Pat Gefre Cc: Greg Kroah-Hartman Cc: Jiri Slaby Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/tty/serial/ioc3_serial.c | 4 ++-- drivers/tty/serial/ioc4_serial.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/tty/serial/ioc3_serial.c b/drivers/tty/serial/ioc3_serial.c index 2a61dd6b4009..906ee770ff4a 100644 --- a/drivers/tty/serial/ioc3_serial.c +++ b/drivers/tty/serial/ioc3_serial.c @@ -377,7 +377,7 @@ static struct ioc3_port *get_ioc3_port(struct uart_port *the_port) * called per port from attach... * @port: port to initialize */ -static int inline port_init(struct ioc3_port *port) +static inline int port_init(struct ioc3_port *port) { uint32_t sio_cr; struct port_hooks *hooks = port->ip_hooks; @@ -1430,7 +1430,7 @@ static int receive_chars(struct uart_port *the_port) * @pending: interrupts to handle */ -static int inline +static inline int ioc3uart_intr_one(struct ioc3_submodule *is, struct ioc3_driver_data *idd, unsigned int pending) diff --git a/drivers/tty/serial/ioc4_serial.c b/drivers/tty/serial/ioc4_serial.c index f96bcf9bee25..43d7d32eb150 100644 --- a/drivers/tty/serial/ioc4_serial.c +++ b/drivers/tty/serial/ioc4_serial.c @@ -824,7 +824,7 @@ pending_intrs(struct ioc4_soft *soft, int type) * called per port from attach... * @port: port to initialize */ -static int inline port_init(struct ioc4_port *port) +static inline int port_init(struct ioc4_port *port) { uint32_t sio_cr; struct hooks *hooks = port->ip_hooks; @@ -1048,7 +1048,7 @@ static irqreturn_t ioc4_intr(int irq, void *arg) * IOC4 with serial ports in the system. * @idd: Master module data for this IOC4 */ -static int inline ioc4_attach_local(struct ioc4_driver_data *idd) +static inline int ioc4_attach_local(struct ioc4_driver_data *idd) { struct ioc4_port *port; struct ioc4_port *ports[IOC4_NUM_SERIAL_PORTS]; -- cgit v1.2.3-59-g8ed1b From 4abf87f41a6cedf7a780af63991d6bebec303be0 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jul 2017 14:37:40 -0700 Subject: USB: serial: safe_serial: move __inline__ before return type Make the code like the rest of the kernel. Also use inline instead of __inline__. Link: http://lkml.kernel.org/r/a5072b74b6c293e6ec93c4900482e9d3267f15b2.1499284835.git.joe@perches.com Signed-off-by: Joe Perches Cc: Johan Hovold Cc: Greg Kroah-Hartman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/usb/serial/safe_serial.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/serial/safe_serial.c b/drivers/usb/serial/safe_serial.c index 8a069aa154ed..27d7a7016298 100644 --- a/drivers/usb/serial/safe_serial.c +++ b/drivers/usb/serial/safe_serial.c @@ -180,7 +180,7 @@ static const __u16 crc10_table[256] = { * Perform a memcpy and calculate fcs using ppp 10bit CRC algorithm. Return * new 10 bit FCS. */ -static __u16 __inline__ fcs_compute10(unsigned char *sp, int len, __u16 fcs) +static inline __u16 fcs_compute10(unsigned char *sp, int len, __u16 fcs) { for (; len-- > 0; fcs = CRC10_FCS(fcs, *sp++)); return fcs; -- cgit v1.2.3-59-g8ed1b From dce3944717523bfe65e2b3cbd1d3af0ccc27ace9 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jul 2017 14:37:43 -0700 Subject: video: fbdev: intelfb: move inline before return type Make the code like the rest of the kernel. But there is an oddity here because the inline should probably be removed. It's an extern function in intelfb.h and it is used in intelfbdrv.c and intelfbhw.c. The inline is kept here as I suppose it's possible for some compiler to make the uses inline in intelfbdrv and and also create an external function for intelfbhw. Link: http://lkml.kernel.org/r/8ba151a1fdc84e42cbf4aafc798513c0158edee1.1499284835.git.joe@perches.com Signed-off-by: Joe Perches Cc: Maik Broemme Cc: Bartlomiej Zolnierkiewicz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/video/fbdev/intelfb/intelfbdrv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/video/fbdev/intelfb/intelfbdrv.c b/drivers/video/fbdev/intelfb/intelfbdrv.c index 6b444400a86c..ffc391208b27 100644 --- a/drivers/video/fbdev/intelfb/intelfbdrv.c +++ b/drivers/video/fbdev/intelfb/intelfbdrv.c @@ -907,7 +907,7 @@ static void intelfb_pci_unregister(struct pci_dev *pdev) * helper functions * ***************************************************************/ -int __inline__ intelfb_var_to_depth(const struct fb_var_screeninfo *var) +__inline__ int intelfb_var_to_depth(const struct fb_var_screeninfo *var) { DBG_MSG("intelfb_var_to_depth: bpp: %d, green.length is %d\n", var->bits_per_pixel, var->green.length); -- cgit v1.2.3-59-g8ed1b From ba168a46b0b9e06f38f63ef9adf182950c82d6e0 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jul 2017 14:37:46 -0700 Subject: video: fbdev: omap: move inline before return type Make the code like the rest of the kernel. Link: http://lkml.kernel.org/r/bc5927726abc70d7c066df7ab4cb7cfce4a7b577.1499284835.git.joe@perches.com Signed-off-by: Joe Perches Cc: Tomi Valkeinen Cc: Bartlomiej Zolnierkiewicz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/video/fbdev/omap/lcdc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/video/fbdev/omap/lcdc.c b/drivers/video/fbdev/omap/lcdc.c index e3d9b9ea5498..938cba0d24ae 100644 --- a/drivers/video/fbdev/omap/lcdc.c +++ b/drivers/video/fbdev/omap/lcdc.c @@ -79,12 +79,12 @@ static struct omap_lcd_controller { unsigned long vram_size; } lcdc; -static void inline enable_irqs(int mask) +static inline void enable_irqs(int mask) { lcdc.irq_mask |= mask; } -static void inline disable_irqs(int mask) +static inline void disable_irqs(int mask) { lcdc.irq_mask &= ~mask; } @@ -466,7 +466,7 @@ static void calc_ck_div(int is_tft, int pck, int *pck_div) } } -static void inline setup_regs(void) +static inline void setup_regs(void) { u32 l; struct lcd_panel *panel = lcdc.fbdev->panel; -- cgit v1.2.3-59-g8ed1b From c945dccc80856107f109c36a7d0e29a371b5d1b5 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jul 2017 14:37:48 -0700 Subject: ARM: samsung: usb-ohci: move inline before return type Make the code like the rest of the kernel. Link: http://lkml.kernel.org/r/667a515b8d0f10f2465d519f8595edd91552fc5e.1499284835.git.joe@perches.com Signed-off-by: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/platform_data/usb-ohci-s3c2410.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/platform_data/usb-ohci-s3c2410.h b/include/linux/platform_data/usb-ohci-s3c2410.h index 7fa1fbefc3f2..cc7554ae6e8b 100644 --- a/include/linux/platform_data/usb-ohci-s3c2410.h +++ b/include/linux/platform_data/usb-ohci-s3c2410.h @@ -31,7 +31,7 @@ struct s3c2410_hcd_info { void (*report_oc)(struct s3c2410_hcd_info *, int ports); }; -static void inline s3c2410_usb_report_oc(struct s3c2410_hcd_info *info, int ports) +static inline void s3c2410_usb_report_oc(struct s3c2410_hcd_info *info, int ports) { if (info->report_oc != NULL) { (info->report_oc)(info, ports); -- cgit v1.2.3-59-g8ed1b From 3e8f399da490e6ac20a3cfd6aa404c9aa961a9a2 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Wed, 12 Jul 2017 14:37:51 -0700 Subject: writeback: rework wb_[dec|inc]_stat family of functions Currently the writeback statistics code uses a percpu counters to hold various statistics. Furthermore we have 2 families of functions - those which disable local irq and those which doesn't and whose names begin with double underscore. However, they both end up calling __add_wb_stats which in turn calls percpu_counter_add_batch which is already irq-safe. Exploiting this fact allows to eliminated the __wb_* functions since they don't add any further protection than we already have. Furthermore, refactor the wb_* function to call __add_wb_stat directly without the irq-disabling dance. This will likely result in better runtime of code which deals with modifying the stat counters. While at it also document why percpu_counter_add_batch is in fact preempt and irq-safe since at least 3 people got confused. Link: http://lkml.kernel.org/r/1498029937-27293-1-git-send-email-nborisov@suse.com Signed-off-by: Nikolay Borisov Acked-by: Tejun Heo Reviewed-by: Jan Kara Cc: Josef Bacik Cc: Mel Gorman Cc: Jeff Layton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fs-writeback.c | 8 ++++---- include/linux/backing-dev.h | 24 ++---------------------- lib/percpu_counter.c | 7 +++++++ mm/page-writeback.c | 10 +++++----- 4 files changed, 18 insertions(+), 31 deletions(-) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 8b426f83909f..245c430a2e41 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -380,8 +380,8 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) struct page *page = radix_tree_deref_slot_protected(slot, &mapping->tree_lock); if (likely(page) && PageDirty(page)) { - __dec_wb_stat(old_wb, WB_RECLAIMABLE); - __inc_wb_stat(new_wb, WB_RECLAIMABLE); + dec_wb_stat(old_wb, WB_RECLAIMABLE); + inc_wb_stat(new_wb, WB_RECLAIMABLE); } } @@ -391,8 +391,8 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) &mapping->tree_lock); if (likely(page)) { WARN_ON_ONCE(!PageWriteback(page)); - __dec_wb_stat(old_wb, WB_WRITEBACK); - __inc_wb_stat(new_wb, WB_WRITEBACK); + dec_wb_stat(old_wb, WB_WRITEBACK); + inc_wb_stat(new_wb, WB_WRITEBACK); } } diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 334165c911f0..854e1bdd0b2a 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -69,34 +69,14 @@ static inline void __add_wb_stat(struct bdi_writeback *wb, percpu_counter_add_batch(&wb->stat[item], amount, WB_STAT_BATCH); } -static inline void __inc_wb_stat(struct bdi_writeback *wb, - enum wb_stat_item item) -{ - __add_wb_stat(wb, item, 1); -} - static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { - unsigned long flags; - - local_irq_save(flags); - __inc_wb_stat(wb, item); - local_irq_restore(flags); -} - -static inline void __dec_wb_stat(struct bdi_writeback *wb, - enum wb_stat_item item) -{ - __add_wb_stat(wb, item, -1); + __add_wb_stat(wb, item, 1); } static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { - unsigned long flags; - - local_irq_save(flags); - __dec_wb_stat(wb, item); - local_irq_restore(flags); + __add_wb_stat(wb, item, -1); } static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c index 8ee7e5ec21be..3bf4a9984f4c 100644 --- a/lib/percpu_counter.c +++ b/lib/percpu_counter.c @@ -72,6 +72,13 @@ void percpu_counter_set(struct percpu_counter *fbc, s64 amount) } EXPORT_SYMBOL(percpu_counter_set); +/** + * This function is both preempt and irq safe. The former is due to explicit + * preemption disable. The latter is guaranteed by the fact that the slow path + * is explicitly protected by an irq-safe spinlock whereas the fast patch uses + * this_cpu_add which is irq-safe by definition. Hence there is no need muck + * with irq state before calling this one + */ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { s64 count; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 0b60cc7ddac2..96e93b214d31 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -601,7 +601,7 @@ static inline void __wb_writeout_inc(struct bdi_writeback *wb) { struct wb_domain *cgdom; - __inc_wb_stat(wb, WB_WRITTEN); + inc_wb_stat(wb, WB_WRITTEN); wb_domain_writeout_inc(&global_wb_domain, &wb->completions, wb->bdi->max_prop_frac); @@ -2435,8 +2435,8 @@ void account_page_dirtied(struct page *page, struct address_space *mapping) __inc_lruvec_page_state(page, NR_FILE_DIRTY); __inc_zone_page_state(page, NR_ZONE_WRITE_PENDING); __inc_node_page_state(page, NR_DIRTIED); - __inc_wb_stat(wb, WB_RECLAIMABLE); - __inc_wb_stat(wb, WB_DIRTIED); + inc_wb_stat(wb, WB_RECLAIMABLE); + inc_wb_stat(wb, WB_DIRTIED); task_io_account_write(PAGE_SIZE); current->nr_dirtied++; this_cpu_inc(bdp_ratelimits); @@ -2741,7 +2741,7 @@ int test_clear_page_writeback(struct page *page) if (bdi_cap_account_writeback(bdi)) { struct bdi_writeback *wb = inode_to_wb(inode); - __dec_wb_stat(wb, WB_WRITEBACK); + dec_wb_stat(wb, WB_WRITEBACK); __wb_writeout_inc(wb); } } @@ -2786,7 +2786,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write) page_index(page), PAGECACHE_TAG_WRITEBACK); if (bdi_cap_account_writeback(bdi)) - __inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK); + inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK); /* * We can come through here when swapping anonymous -- cgit v1.2.3-59-g8ed1b From c7b5a4e6e8fbef8fdf2c529f953000d24c561339 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 6 Jul 2017 02:32:02 +0200 Subject: PCI / PM: Fix native PME handling during system suspend/resume Commit 76cde7e49590 (PCI / PM: Make PCIe PME interrupts wake up from suspend-to-idle) went too far with preventing pcie_pme_work_fn() from clearing the root port's PME Status and re-enabling the PME interrupt which should be done for PMEs to work correctly after system resume. The failing scenario is as follows: 1. pcie_pme_suspend() finds that the PME IRQ should be designated for system wakeup, so it calls enable_irq_wake() and then sets data->suspend_level to PME_SUSPEND_WAKEUP. 2. PME interrupt happens at this point. 3. pcie_pme_irq() runs, disables the PME interrupt and queues up the execution of pcie_pme_work_fn(). 4. pcie_pme_work_fn() runs before pcie_pme_resume() and breaks out of the loop right away, because data->suspend_level is not PME_SUSPEND_NONE, and it doesn't re-enable the PME interrupt for the same reason. 5. pcie_pme_resume() runs and simply calls disable_irq_wake() without re-enabling the PME interrupt (because data->suspend_level is not PME_SUSPEND_NONE), so the PME interrupt remains disabled and the PME Status remains set. To fix this notice that there is no reason why pcie_pme_work_fn() should behave in a special way during system resume if the PME interrupt is not disabled by pcie_pme_suspend() and partially revert commit 76cde7e49590 and restore the previous (and correct) behavior of pcie_pme_work_fn(). Fixes: 76cde7e49590 (PCI / PM: Make PCIe PME interrupts wake up from suspend-to-idle) Reported-and-tested-by: Naresh Solanki Signed-off-by: Rafael J. Wysocki Acked-by: Bjorn Helgaas --- drivers/pci/pcie/pme.c | 35 +++++++++++++---------------------- 1 file changed, 13 insertions(+), 22 deletions(-) diff --git a/drivers/pci/pcie/pme.c b/drivers/pci/pcie/pme.c index 80e58d25006d..fafdb165dd2e 100644 --- a/drivers/pci/pcie/pme.c +++ b/drivers/pci/pcie/pme.c @@ -40,17 +40,11 @@ static int __init pcie_pme_setup(char *str) } __setup("pcie_pme=", pcie_pme_setup); -enum pme_suspend_level { - PME_SUSPEND_NONE = 0, - PME_SUSPEND_WAKEUP, - PME_SUSPEND_NOIRQ, -}; - struct pcie_pme_service_data { spinlock_t lock; struct pcie_device *srv; struct work_struct work; - enum pme_suspend_level suspend_level; + bool noirq; /* If set, keep the PME interrupt disabled. */ }; /** @@ -228,7 +222,7 @@ static void pcie_pme_work_fn(struct work_struct *work) spin_lock_irq(&data->lock); for (;;) { - if (data->suspend_level != PME_SUSPEND_NONE) + if (data->noirq) break; pcie_capability_read_dword(port, PCI_EXP_RTSTA, &rtsta); @@ -255,7 +249,7 @@ static void pcie_pme_work_fn(struct work_struct *work) spin_lock_irq(&data->lock); } - if (data->suspend_level == PME_SUSPEND_NONE) + if (!data->noirq) pcie_pme_interrupt_enable(port, true); spin_unlock_irq(&data->lock); @@ -378,7 +372,7 @@ static int pcie_pme_suspend(struct pcie_device *srv) { struct pcie_pme_service_data *data = get_service_data(srv); struct pci_dev *port = srv->port; - bool wakeup, wake_irq_enabled = false; + bool wakeup; int ret; if (device_may_wakeup(&port->dev)) { @@ -388,19 +382,16 @@ static int pcie_pme_suspend(struct pcie_device *srv) wakeup = pcie_pme_check_wakeup(port->subordinate); up_read(&pci_bus_sem); } - spin_lock_irq(&data->lock); if (wakeup) { ret = enable_irq_wake(srv->irq); - if (ret == 0) { - data->suspend_level = PME_SUSPEND_WAKEUP; - wake_irq_enabled = true; - } - } - if (!wake_irq_enabled) { - pcie_pme_interrupt_enable(port, false); - pcie_clear_root_pme_status(port); - data->suspend_level = PME_SUSPEND_NOIRQ; + if (!ret) + return 0; } + + spin_lock_irq(&data->lock); + pcie_pme_interrupt_enable(port, false); + pcie_clear_root_pme_status(port); + data->noirq = true; spin_unlock_irq(&data->lock); synchronize_irq(srv->irq); @@ -417,15 +408,15 @@ static int pcie_pme_resume(struct pcie_device *srv) struct pcie_pme_service_data *data = get_service_data(srv); spin_lock_irq(&data->lock); - if (data->suspend_level == PME_SUSPEND_NOIRQ) { + if (data->noirq) { struct pci_dev *port = srv->port; pcie_clear_root_pme_status(port); pcie_pme_interrupt_enable(port, true); + data->noirq = false; } else { disable_irq_wake(srv->irq); } - data->suspend_level = PME_SUSPEND_NONE; spin_unlock_irq(&data->lock); return 0; -- cgit v1.2.3-59-g8ed1b From 3c48d86cc959309ee168fb87737a8cb3f97c5224 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Wed, 12 Jul 2017 15:04:16 -0700 Subject: clk: Provide bulk prepare_enable disable_unprepare variants This extends the existing set of bulk helpers with prepare_enable and disable_unprepare variants. Cc: Russell King , Cc: Dong Aisheng Signed-off-by: Bjorn Andersson Signed-off-by: Stephen Boyd --- include/linux/clk.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/include/linux/clk.h b/include/linux/clk.h index c673f0b91751..690e6a6921e1 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -657,6 +657,28 @@ static inline void clk_disable_unprepare(struct clk *clk) clk_unprepare(clk); } +static inline int clk_bulk_prepare_enable(int num_clks, + struct clk_bulk_data *clks) +{ + int ret; + + ret = clk_bulk_prepare(num_clks, clks); + if (ret) + return ret; + ret = clk_bulk_enable(num_clks, clks); + if (ret) + clk_bulk_unprepare(num_clks, clks); + + return ret; +} + +static inline void clk_bulk_disable_unprepare(int num_clks, + struct clk_bulk_data *clks) +{ + clk_bulk_disable(num_clks, clks); + clk_bulk_unprepare(num_clks, clks); +} + #if defined(CONFIG_OF) && defined(CONFIG_COMMON_CLK) struct clk *of_clk_get(struct device_node *np, int index); struct clk *of_clk_get_by_name(struct device_node *np, const char *name); -- cgit v1.2.3-59-g8ed1b From bbdc74dc19e09ac4e71bfb219596b3d5bc786720 Mon Sep 17 00:00:00 2001 From: Grzegorz Sluja Date: Thu, 13 Jul 2017 11:17:58 +0200 Subject: mmc: block: Prevent new req entering queue after its cleanup The commit 304419d8a7e9 ("mmc: core: Allocate per-request data using the block layer core"), refactored the mechanism of queue handling, but also made mmc_init_request() to be called after mmc_cleanup_queue(). This triggers a null pointer dereference: [ 683.123791] BUG: unable to handle kernel NULL pointer dereference at (null) [ 683.123801] IP: mmc_init_request+0x2c/0xf0 [mmc_block] ... [ 683.123905] Call Trace: [ 683.123913] alloc_request_size+0x4f/0x70 [ 683.123919] mempool_alloc+0x5f/0x150 [ 683.123925] ? __enqueue_entity+0x6c/0x70 [ 683.123928] get_request+0x3ad/0x720 [ 683.123933] ? prepare_to_wait_event+0x110/0x110 [ 683.123937] blk_queue_bio+0xc1/0x3a0 [ 683.123940] generic_make_request+0xf8/0x2a0 [ 683.123942] submit_bio+0x75/0x150 [ 683.123947] submit_bio_wait+0x51/0x70 [ 683.123951] blkdev_issue_flush+0x5c/0x90 [ 683.123956] ext4_sync_fs+0x171/0x1b0 [ 683.123961] sync_filesystem+0x73/0x90 [ 683.123965] fsync_bdev+0x24/0x50 [ 683.123971] invalidate_partition+0x24/0x50 [ 683.123973] del_gendisk+0xb2/0x2a0 [ 683.123977] mmc_blk_remove_req.part.38+0x71/0xa0 [mmc_block] [ 683.123980] mmc_blk_remove+0xba/0x190 [mmc_block] [ 683.123990] mmc_bus_remove+0x1a/0x20 [mmc_core] [ 683.123995] device_release_driver_internal+0x141/0x200 [ 683.123999] device_release_driver+0x12/0x20 [ 683.124001] bus_remove_device+0xfd/0x170 [ 683.124004] device_del+0x1e8/0x330 [ 683.124012] mmc_remove_card+0x60/0xc0 [mmc_core] [ 683.124019] mmc_remove+0x19/0x30 [mmc_core] [ 683.124025] mmc_stop_host+0xfb/0x1a0 [mmc_core] [ 683.124032] mmc_remove_host+0x1a/0x40 [mmc_core] [ 683.124037] sdhci_remove_host+0x2e/0x1c0 [mmc_sdhci] [ 683.124042] sdhci_pci_remove_slot+0x3f/0x80 [sdhci_pci] [ 683.124045] sdhci_pci_remove+0x39/0x70 [sdhci_pci] [ 683.124049] pci_device_remove+0x39/0xc0 [ 683.124052] device_release_driver_internal+0x141/0x200 [ 683.124056] driver_detach+0x3f/0x80 [ 683.124059] bus_remove_driver+0x55/0xd0 [ 683.124062] driver_unregister+0x2c/0x50 [ 683.124065] pci_unregister_driver+0x29/0x90 [ 683.124069] sdhci_driver_exit+0x10/0x4f3 [sdhci_pci] [ 683.124073] SyS_delete_module+0x171/0x250 [ 683.124078] entry_SYSCALL_64_fastpath+0x1e/0xa9 Fix this by setting the queue DYING flag before cleanup the queue, as it prevents new reqs from entering the queue. Signed-off-by: Grzegorz Sluja Signed-off-by: Linus Walleij Fixes: 304419d8a7e9 ("mmc: core: Allocate per-request data using the...") [Ulf: Updated the changelog] Signed-off-by: Ulf Hansson --- drivers/mmc/core/block.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index e0363223996e..8ac59dc80f23 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -2170,6 +2170,7 @@ static void mmc_blk_remove_req(struct mmc_blk_data *md) * from being accepted. */ card = md->queue.card; + blk_set_queue_dying(md->queue.queue); mmc_cleanup_queue(&md->queue); if (md->disk->flags & GENHD_FL_UP) { device_remove_file(disk_to_dev(md->disk), &md->force_ro); -- cgit v1.2.3-59-g8ed1b From 9c284c41c0886f09e75c323a16278b6d353b0b4a Mon Sep 17 00:00:00 2001 From: Chris Brandt Date: Wed, 12 Jul 2017 08:40:01 -0700 Subject: mmc: tmio-mmc: fix bad pointer math The existing code gives an incorrect pointer value. The buffer pointer 'buf' was of type unsigned short *, and 'count' was a number in bytes. A cast of buf should have been used. However, instead of casting, just change the code to use u32 pointers. Reported-by: Dan Carpenter Fixes: 8185e51f358a: ("mmc: tmio-mmc: add support for 32bit data port") Signed-off-by: Chris Brandt Reviewed-by: Geert Uytterhoeven Acked-by: Wolfram Sang Cc: Signed-off-by: Ulf Hansson --- drivers/mmc/host/tmio_mmc_core.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c index 82b80d42f7ae..88a94355ac90 100644 --- a/drivers/mmc/host/tmio_mmc_core.c +++ b/drivers/mmc/host/tmio_mmc_core.c @@ -409,30 +409,29 @@ static void tmio_mmc_transfer_data(struct tmio_mmc_host *host, * Transfer the data */ if (host->pdata->flags & TMIO_MMC_32BIT_DATA_PORT) { - u8 data[4] = { }; + u32 data = 0; + u32 *buf32 = (u32 *)buf; if (is_read) - sd_ctrl_read32_rep(host, CTL_SD_DATA_PORT, (u32 *)buf, + sd_ctrl_read32_rep(host, CTL_SD_DATA_PORT, buf32, count >> 2); else - sd_ctrl_write32_rep(host, CTL_SD_DATA_PORT, (u32 *)buf, + sd_ctrl_write32_rep(host, CTL_SD_DATA_PORT, buf32, count >> 2); /* if count was multiple of 4 */ if (!(count & 0x3)) return; - buf8 = (u8 *)(buf + (count >> 2)); + buf32 += count >> 2; count %= 4; if (is_read) { - sd_ctrl_read32_rep(host, CTL_SD_DATA_PORT, - (u32 *)data, 1); - memcpy(buf8, data, count); + sd_ctrl_read32_rep(host, CTL_SD_DATA_PORT, &data, 1); + memcpy(buf32, &data, count); } else { - memcpy(data, buf8, count); - sd_ctrl_write32_rep(host, CTL_SD_DATA_PORT, - (u32 *)data, 1); + memcpy(&data, buf32, count); + sd_ctrl_write32_rep(host, CTL_SD_DATA_PORT, &data, 1); } return; -- cgit v1.2.3-59-g8ed1b From 4d9bcaddacf23861c5ee088b0c03e7034c3d59d6 Mon Sep 17 00:00:00 2001 From: "Ernesto A. Fernández" Date: Fri, 23 Jun 2017 21:37:21 -0300 Subject: ext2: Fix memory leak when truncate races ext2_get_blocks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Buffer heads referencing indirect blocks may not be released if the file is truncated at the right time. This happens because ext2_get_branch() returns NULL when it finds the whole chain of indirect blocks already set, and when truncate alters the chain this value of NULL is treated as the address of the last head to be released. Handle this in the same way as it's done after the got_it label. Signed-off-by: Ernesto A. Fernández Signed-off-by: Jan Kara --- fs/ext2/inode.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 2dcbd5698884..30163d007b2f 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -659,6 +659,7 @@ static int ext2_get_blocks(struct inode *inode, */ err = -EAGAIN; count = 0; + partial = chain + depth - 1; break; } blk = le32_to_cpu(*(chain[depth-1].p + count)); -- cgit v1.2.3-59-g8ed1b From 4cf56a89c696e66d10612b43b7e95852611e76c2 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Tue, 11 Jul 2017 10:02:18 -0700 Subject: HID: multitouch: do not blindly set EV_KEY or EV_ABS bits Now that input core insists on having dev->absinfo when device claims to generate EV_ABS in its dev->evbit, we should not be blindly setting that bit. The code in question might have been needed before input_set_abs_params() started setting EV_ABS in device's evbit, but not anymore, and is now breaking devices such as SMART SPNL-6075 Touchscreen. Fixes: 6ecfe51b4082 ("Input: refuse to register absolute devices ...") Reported-by: Matthias Fend Tested-by: Matthias Fend Cc: stable@vger.kernel.org Reviewed-by: Benjamin Tissoires Signed-off-by: Dmitry Torokhov Signed-off-by: Jiri Kosina --- drivers/hid/hid-multitouch.c | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index f3e35e7a189d..aff20f4b6d97 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -620,16 +620,6 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi, return 0; } -static int mt_touch_input_mapped(struct hid_device *hdev, struct hid_input *hi, - struct hid_field *field, struct hid_usage *usage, - unsigned long **bit, int *max) -{ - if (usage->type == EV_KEY || usage->type == EV_ABS) - set_bit(usage->type, hi->input->evbit); - - return -1; -} - static int mt_compute_slot(struct mt_device *td, struct input_dev *input) { __s32 quirks = td->mtclass.quirks; @@ -969,8 +959,10 @@ static int mt_input_mapped(struct hid_device *hdev, struct hid_input *hi, return 0; if (field->application == HID_DG_TOUCHSCREEN || - field->application == HID_DG_TOUCHPAD) - return mt_touch_input_mapped(hdev, hi, field, usage, bit, max); + field->application == HID_DG_TOUCHPAD) { + /* We own these mappings, tell hid-input to ignore them */ + return -1; + } /* let hid-core decide for the others */ return 0; -- cgit v1.2.3-59-g8ed1b From a826faf108e2d855929342268e68c43ba667379a Mon Sep 17 00:00:00 2001 From: Ladi Prosek Date: Mon, 26 Jun 2017 09:56:43 +0200 Subject: KVM: x86: make backwards_tsc_observed a per-VM variable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The backwards_tsc_observed global introduced in commit 16a9602 is never reset to false. If a VM happens to be running while the host is suspended (a common source of the TSC jumping backwards), master clock will never be enabled again for any VM. In contrast, if no VM is running while the host is suspended, master clock is unaffected. This is inconsistent and unnecessarily strict. Let's track the backwards_tsc_observed variable separately and let each VM start with a clean slate. Real world impact: My Windows VMs get slower after my laptop undergoes a suspend/resume cycle. The only way to get the perf back is unloading and reloading the kvm module. Signed-off-by: Ladi Prosek Signed-off-by: Radim Krčmář --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/x86.c | 6 ++---- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 1588e9e3dc01..ef37d0dc61bd 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -803,6 +803,7 @@ struct kvm_arch { int audit_point; #endif + bool backwards_tsc_observed; bool boot_vcpu_runs_old_kvmclock; u32 bsp_vcpu_id; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ca128a9c9cc4..08aa5e442aa7 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -134,8 +134,6 @@ module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR); static bool __read_mostly vector_hashing = true; module_param(vector_hashing, bool, S_IRUGO); -static bool __read_mostly backwards_tsc_observed = false; - #define KVM_NR_SHARED_MSRS 16 struct kvm_shared_msrs_global { @@ -1719,7 +1717,7 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm) &ka->master_cycle_now); ka->use_master_clock = host_tsc_clocksource && vcpus_matched - && !backwards_tsc_observed + && !ka->backwards_tsc_observed && !ka->boot_vcpu_runs_old_kvmclock; if (ka->use_master_clock) @@ -7835,8 +7833,8 @@ int kvm_arch_hardware_enable(void) */ if (backwards_tsc) { u64 delta_cyc = max_tsc - local_tsc; - backwards_tsc_observed = true; list_for_each_entry(kvm, &vm_list, vm_list) { + kvm->arch.backwards_tsc_observed = true; kvm_for_each_vcpu(i, vcpu, kvm) { vcpu->arch.tsc_offset_adjustment += delta_cyc; vcpu->arch.last_host_tsc = local_tsc; -- cgit v1.2.3-59-g8ed1b From efc479e6900c22bad9a2b649d13405ed9cde2d53 Mon Sep 17 00:00:00 2001 From: Roman Kagan Date: Thu, 22 Jun 2017 16:51:01 +0300 Subject: kvm: x86: hyperv: add KVM_CAP_HYPERV_SYNIC2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a flaw in the Hyper-V SynIC implementation in KVM: when message page or event flags page is enabled by setting the corresponding msr, KVM zeroes it out. This is problematic because on migration the corresponding MSRs are loaded on the destination, so the content of those pages is lost. This went unnoticed so far because the only user of those pages was in-KVM hyperv synic timers, which could continue working despite that zeroing. Newer QEMU uses those pages for Hyper-V VMBus implementation, and zeroing them breaks the migration. Besides, in newer QEMU the content of those pages is fully managed by QEMU, so zeroing them is undesirable even when writing the MSRs from the guest side. To support this new scheme, introduce a new capability, KVM_CAP_HYPERV_SYNIC2, which, when enabled, makes sure that the synic pages aren't zeroed out in KVM. Signed-off-by: Roman Kagan Signed-off-by: Radim Krčmář --- Documentation/virtual/kvm/api.txt | 9 +++++++++ arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/hyperv.c | 13 +++++++++---- arch/x86/kvm/hyperv.h | 2 +- arch/x86/kvm/x86.c | 7 ++++++- include/uapi/linux/kvm.h | 1 + 6 files changed, 27 insertions(+), 6 deletions(-) diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 3a9831b72945..78ac577c9378 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -4329,3 +4329,12 @@ Querying this capability returns a bitmap indicating the possible virtual SMT modes that can be set using KVM_CAP_PPC_SMT. If bit N (counting from the right) is set, then a virtual SMT mode of 2^N is available. + +8.11 KVM_CAP_HYPERV_SYNIC2 + +Architectures: x86 + +This capability enables a newer version of Hyper-V Synthetic interrupt +controller (SynIC). The only difference with KVM_CAP_HYPERV_SYNIC is that KVM +doesn't clear SynIC message and event flags pages when they are enabled by +writing to the respective MSRs. diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index ef37d0dc61bd..9d8de5dd7546 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -462,6 +462,7 @@ struct kvm_vcpu_hv_synic { DECLARE_BITMAP(auto_eoi_bitmap, 256); DECLARE_BITMAP(vec_bitmap, 256); bool active; + bool dont_zero_synic_pages; }; /* Hyper-V per vcpu emulation context */ diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index ebae57ac5902..a8084406707e 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -221,7 +221,8 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic, synic->version = data; break; case HV_X64_MSR_SIEFP: - if (data & HV_SYNIC_SIEFP_ENABLE) + if ((data & HV_SYNIC_SIEFP_ENABLE) && !host && + !synic->dont_zero_synic_pages) if (kvm_clear_guest(vcpu->kvm, data & PAGE_MASK, PAGE_SIZE)) { ret = 1; @@ -232,7 +233,8 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic, synic_exit(synic, msr); break; case HV_X64_MSR_SIMP: - if (data & HV_SYNIC_SIMP_ENABLE) + if ((data & HV_SYNIC_SIMP_ENABLE) && !host && + !synic->dont_zero_synic_pages) if (kvm_clear_guest(vcpu->kvm, data & PAGE_MASK, PAGE_SIZE)) { ret = 1; @@ -687,14 +689,17 @@ void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) stimer_init(&hv_vcpu->stimer[i], i); } -int kvm_hv_activate_synic(struct kvm_vcpu *vcpu) +int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages) { + struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu); + /* * Hyper-V SynIC auto EOI SINT's are * not compatible with APICV, so deactivate APICV */ kvm_vcpu_deactivate_apicv(vcpu); - vcpu_to_synic(vcpu)->active = true; + synic->active = true; + synic->dont_zero_synic_pages = dont_zero_synic_pages; return 0; } diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index cd1119538add..12f65fe1011d 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -56,7 +56,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu); void kvm_hv_irq_routing_update(struct kvm *kvm); int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint); void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector); -int kvm_hv_activate_synic(struct kvm_vcpu *vcpu); +int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages); void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu); void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 08aa5e442aa7..4f41c5222ecd 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2659,6 +2659,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV_VAPIC: case KVM_CAP_HYPERV_SPIN: case KVM_CAP_HYPERV_SYNIC: + case KVM_CAP_HYPERV_SYNIC2: case KVM_CAP_PCI_SEGMENT: case KVM_CAP_DEBUGREGS: case KVM_CAP_X86_ROBUST_SINGLESTEP: @@ -3382,10 +3383,14 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return -EINVAL; switch (cap->cap) { + case KVM_CAP_HYPERV_SYNIC2: + if (cap->args[0]) + return -EINVAL; case KVM_CAP_HYPERV_SYNIC: if (!irqchip_in_kernel(vcpu->kvm)) return -EINVAL; - return kvm_hv_activate_synic(vcpu); + return kvm_hv_activate_synic(vcpu, cap->cap == + KVM_CAP_HYPERV_SYNIC2); default: return -EINVAL; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index ebd604c222d8..38b2cfbc8112 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -927,6 +927,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_CMMA_MIGRATION 145 #define KVM_CAP_PPC_FWNMI 146 #define KVM_CAP_PPC_SMT_POSSIBLE 147 +#define KVM_CAP_HYPERV_SYNIC2 148 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3-59-g8ed1b From e4a6a3424b75f23f6bb1cc479974fc305a4b9f78 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Thu, 13 Jul 2017 14:27:58 +0800 Subject: bpf: fix return in bpf_skb_adjust_net The bpf_skb_adjust_net() ignores the return value of bpf_skb_net_shrink/grow, and always return 0, fix it by return 'ret'. Signed-off-by: Kefeng Wang Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- net/core/filter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/filter.c b/net/core/filter.c index c7f737058d89..f44fc22fd45a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2248,7 +2248,7 @@ static int bpf_skb_adjust_net(struct sk_buff *skb, s32 len_diff) bpf_skb_net_grow(skb, len_diff_abs); bpf_compute_data_end(skb); - return 0; + return ret; } BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, -- cgit v1.2.3-59-g8ed1b From 0db01097cabd97897d123b4c5d805d1a7b061d82 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Thu, 13 Jul 2017 10:57:40 +0200 Subject: xgene: Don't fail probe, if there is no clk resource for SGMII interfaces This change fixes following problem [ 1.827940] xgene-enet: probe of 1f210030.ethernet failed with error -2 which leads to a missing ethernet interface (reproducable at least on Gigabyte MP30-AR0 and APM Mustang systems). The check for a valid clk resource fails, because DT doesn't provide a clock for sgenet1. But the driver doesn't use this clk, if the ethernet port is connected via SGMII. Therefore this patch avoids probing for clk on SGMII interfaces. Fixes: 9aea7779b764 ("drivers: net: xgene: Fix crash on DT systems") Signed-off-by: Thomas Bogendoerfer Signed-off-by: David S. Miller --- drivers/net/ethernet/apm/xgene/xgene_enet_main.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index d3906f6b01bd..86058a9f3417 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -1785,16 +1785,18 @@ static int xgene_enet_get_resources(struct xgene_enet_pdata *pdata) xgene_enet_gpiod_get(pdata); - pdata->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(pdata->clk)) { - /* Abort if the clock is defined but couldn't be retrived. - * Always abort if the clock is missing on DT system as - * the driver can't cope with this case. - */ - if (PTR_ERR(pdata->clk) != -ENOENT || dev->of_node) - return PTR_ERR(pdata->clk); - /* Firmware may have set up the clock already. */ - dev_info(dev, "clocks have been setup already\n"); + if (pdata->phy_mode != PHY_INTERFACE_MODE_SGMII) { + pdata->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(pdata->clk)) { + /* Abort if the clock is defined but couldn't be + * retrived. Always abort if the clock is missing on + * DT system as the driver can't cope with this case. + */ + if (PTR_ERR(pdata->clk) != -ENOENT || dev->of_node) + return PTR_ERR(pdata->clk); + /* Firmware may have set up the clock already. */ + dev_info(dev, "clocks have been setup already\n"); + } } if (pdata->phy_mode != PHY_INTERFACE_MODE_XGMII) -- cgit v1.2.3-59-g8ed1b From 22c608919bd4f0fae8e70e1284c83e0f1d507f34 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 11 Jul 2017 11:52:23 +0100 Subject: net: broadcom: bnx2x: make a couple of const arrays static Don't populate various tables on the stack but make them static const. Makes the object code smaller by nearly 200 bytes: Before: text data bss dec hex filename 113468 11200 0 124668 1e6fc bnx2x_ethtool.o After: text data bss dec hex filename 113129 11344 0 124473 1e639 bnx2x_ethtool.o Signed-off-by: Colin Ian King Acked-by: Yuval Mintz Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index 43423744fdfa..21bc4bed6b26 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -2886,7 +2886,7 @@ static int bnx2x_test_nvram_tbl(struct bnx2x *bp, static int bnx2x_test_nvram(struct bnx2x *bp) { - const struct crc_pair nvram_tbl[] = { + static const struct crc_pair nvram_tbl[] = { { 0, 0x14 }, /* bootstrap */ { 0x14, 0xec }, /* dir */ { 0x100, 0x350 }, /* manuf_info */ @@ -2895,7 +2895,7 @@ static int bnx2x_test_nvram(struct bnx2x *bp) { 0x708, 0x70 }, /* manuf_key_info */ { 0, 0 } }; - const struct crc_pair nvram_tbl2[] = { + static const struct crc_pair nvram_tbl2[] = { { 0x7e8, 0x350 }, /* manuf_info2 */ { 0xb38, 0xf0 }, /* feature_info */ { 0, 0 } -- cgit v1.2.3-59-g8ed1b From f56ff774871d95f60c3f858419cf7424e6c361cf Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 11 Jul 2017 12:18:48 +0100 Subject: net: stmmac: make const array route_possibilities static Don't populate array route_possibilities on the stack but make it static const. Makes the object code a little smaller by 85 bytes: Before: text data bss dec hex filename 9901 2448 0 12349 303d dwmac4_core.o After: text data bss dec hex filename 9760 2504 0 12264 2fe8 dwmac4_core.o Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index f233bf8b4ebb..c4407e8e39a3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -117,7 +117,7 @@ static void dwmac4_tx_queue_routing(struct mac_device_info *hw, void __iomem *ioaddr = hw->pcsr; u32 value; - const struct stmmac_rx_routing route_possibilities[] = { + static const struct stmmac_rx_routing route_possibilities[] = { { GMAC_RXQCTRL_AVCPQ_MASK, GMAC_RXQCTRL_AVCPQ_SHIFT }, { GMAC_RXQCTRL_PTPQ_MASK, GMAC_RXQCTRL_PTPQ_SHIFT }, { GMAC_RXQCTRL_DCBCPQ_MASK, GMAC_RXQCTRL_DCBCPQ_SHIFT }, -- cgit v1.2.3-59-g8ed1b From bf98bd0be1ba509c5e6d77524ffac192f1edb2dd Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 11 Jul 2017 12:47:33 +0100 Subject: rt2x00: make const array glrt_table static Don't populate array glrt_table on the stack but make it static. Makes the object code a smaller by over 670 bytes: Before: text data bss dec hex filename 131772 4733 0 136505 21539 rt2800lib.o After: text data bss dec hex filename 131043 4789 0 135832 21298 rt2800lib.o Signed-off-by: Colin Ian King Acked-by: Stanislaw Gruszka Signed-off-by: David S. Miller --- drivers/net/wireless/ralink/rt2x00/rt2800lib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c index 6e2e760d98b1..0b75def39c6c 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c @@ -5704,7 +5704,7 @@ static void rt2800_init_freq_calibration(struct rt2x00_dev *rt2x00dev) static void rt2800_init_bbp_5592_glrt(struct rt2x00_dev *rt2x00dev) { - const u8 glrt_table[] = { + static const u8 glrt_table[] = { 0xE0, 0x1F, 0X38, 0x32, 0x08, 0x28, 0x19, 0x0A, 0xFF, 0x00, /* 128 ~ 137 */ 0x16, 0x10, 0x10, 0x0B, 0x36, 0x2C, 0x26, 0x24, 0x42, 0x36, /* 138 ~ 147 */ 0x30, 0x2D, 0x4C, 0x46, 0x3D, 0x40, 0x3E, 0x42, 0x3D, 0x40, /* 148 ~ 157 */ -- cgit v1.2.3-59-g8ed1b From 5e349fc03cdd44c670aaf3affaa6f0426c5e553f Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 13 Jul 2017 12:22:24 +0100 Subject: dccp: make const array error_code static Don't populate array error_code on the stack but make it static. Makes the object code smaller by almost 250 bytes: Before: text data bss dec hex filename 10366 983 0 11349 2c55 net/dccp/input.o After: text data bss dec hex filename 10161 1039 0 11200 2bc0 net/dccp/input.o Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- net/dccp/input.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/dccp/input.c b/net/dccp/input.c index 4a05d7876850..fa6be9750bb4 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -126,7 +126,7 @@ static int dccp_rcv_closereq(struct sock *sk, struct sk_buff *skb) static u16 dccp_reset_code_convert(const u8 code) { - const u16 error_code[] = { + static const u16 error_code[] = { [DCCP_RESET_CODE_CLOSED] = 0, /* normal termination */ [DCCP_RESET_CODE_UNSPECIFIED] = 0, /* nothing known */ [DCCP_RESET_CODE_ABORTED] = ECONNRESET, -- cgit v1.2.3-59-g8ed1b From 803d5b6ebfb06a0d2ee3699fea4f1c7593958566 Mon Sep 17 00:00:00 2001 From: Ganesh Goudar Date: Thu, 13 Jul 2017 18:45:07 +0530 Subject: cxgb4: add new T5 pci device id's Add 0x50a3 and 0x50a4 T5 device id's Signed-off-by: Ganesh Goudar Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h index 99987d8e437e..aa28299aef5f 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h @@ -174,6 +174,8 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN CH_PCI_ID_TABLE_FENTRY(0x50a0), /* Custom T540-CR */ CH_PCI_ID_TABLE_FENTRY(0x50a1), /* Custom T540-CR */ CH_PCI_ID_TABLE_FENTRY(0x50a2), /* Custom T540-KR4 */ + CH_PCI_ID_TABLE_FENTRY(0x50a3), /* Custom T580-KR4 */ + CH_PCI_ID_TABLE_FENTRY(0x50a4), /* Custom 2x T540-CR */ /* T6 adapters: */ -- cgit v1.2.3-59-g8ed1b From 2683701201ddb9a2a4d0fda5d950ab50ca8e77e4 Mon Sep 17 00:00:00 2001 From: Rolf Eike Beer Date: Thu, 13 Jul 2017 16:46:43 +0200 Subject: netlink: correctly document nla_put_u64_64bit() Signed-off-by: Rolf Eike Beer Signed-off-by: David S. Miller --- include/net/netlink.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/net/netlink.h b/include/net/netlink.h index 01709172b3d3..ef8e6c3a80a6 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -98,8 +98,8 @@ * nla_put_u8(skb, type, value) add u8 attribute to skb * nla_put_u16(skb, type, value) add u16 attribute to skb * nla_put_u32(skb, type, value) add u32 attribute to skb - * nla_put_u64_64bits(skb, type, - * value, padattr) add u64 attribute to skb + * nla_put_u64_64bit(skb, type, + * value, padattr) add u64 attribute to skb * nla_put_s8(skb, type, value) add s8 attribute to skb * nla_put_s16(skb, type, value) add s16 attribute to skb * nla_put_s32(skb, type, value) add s32 attribute to skb -- cgit v1.2.3-59-g8ed1b From fdb254db21bb4aed44a0bc7fe993e58d3848c926 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 11 Jul 2017 16:22:59 +0100 Subject: isofs: Fix isofs_show_options() The isofs patch needs a small fix to handle a signed/unsigned comparison that the compiler didn't flag - thanks to Dan for catching it. It should be noted, however, the session number handing appears to be incorrect between where it is parsed and where it is used. Signed-off-by: David Howells Signed-off-by: Al Viro --- fs/isofs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index f80ee600d1bc..8cf898a59730 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -492,7 +492,7 @@ static int isofs_show_options(struct seq_file *m, struct dentry *root) if (sbi->s_check) seq_printf(m, ",check=%c", sbi->s_check); if (sbi->s_mapping) seq_printf(m, ",map=%c", sbi->s_mapping); - if (sbi->s_session != -1) seq_printf(m, ",session=%u", sbi->s_session); + if (sbi->s_session != 255) seq_printf(m, ",session=%u", sbi->s_session - 1); if (sbi->s_sbsector != -1) seq_printf(m, ",sbsector=%u", sbi->s_sbsector); if (root->d_sb->s_blocksize != 1024) -- cgit v1.2.3-59-g8ed1b From 7d84120b5ba61912a5333f5fe2c4e8f35ef9514f Mon Sep 17 00:00:00 2001 From: Rafał Miłecki Date: Sun, 25 Jun 2017 13:11:54 +0200 Subject: Documentation: ABI: mtd: describe "offset" more precisely MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit So far Linux supported only two levels of MTD devices so we didn't need a very precise description for this sysfs file. With commit 97519dc52b44a ("mtd: partitions: add support for subpartitions") there is support for a tree structure so we should have more precise description. Using "parent" and "flash device" makes it more accurate. Signed-off-by: Rafał Miłecki Signed-off-by: Brian Norris --- Documentation/ABI/testing/sysfs-class-mtd | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-class-mtd b/Documentation/ABI/testing/sysfs-class-mtd index 3b5c3bca9186..f34e592301d1 100644 --- a/Documentation/ABI/testing/sysfs-class-mtd +++ b/Documentation/ABI/testing/sysfs-class-mtd @@ -229,6 +229,6 @@ KernelVersion: 4.1 Contact: linux-mtd@lists.infradead.org Description: For a partition, the offset of that partition from the start - of the master device in bytes. This attribute is absent on - main devices, so it can be used to distinguish between - partitions and devices that aren't partitions. + of the parent (another partition or a flash device) in bytes. + This attribute is absent on flash devices, so it can be used + to distinguish them from partitions. -- cgit v1.2.3-59-g8ed1b From b20dae70bfa5014fdf201d0a8589271b888e4927 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 13 Jul 2017 18:51:15 +0100 Subject: svcrdma: fix an incorrect check on -E2BIG and -EINVAL The current check will always be true and will always jump to err1, this looks dubious to me. I believe && should be used instead of ||. Detected by CoverityScan, CID#1450120 ("Logically Dead Code") Fixes: 107c1d0a991a ("svcrdma: Avoid Send Queue overflow") Signed-off-by: Colin Ian King Reviewed-by: Chuck Lever Signed-off-by: J. Bruce Fields --- net/sunrpc/xprtrdma/svc_rdma_sendto.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 19fd01e4b690..7c3a211e0e9a 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -684,7 +684,7 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) return 0; err2: - if (ret != -E2BIG || ret != -EINVAL) + if (ret != -E2BIG && ret != -EINVAL) goto err1; ret = svc_rdma_post_recv(rdma, GFP_KERNEL); -- cgit v1.2.3-59-g8ed1b From 266530b34cb679188d5b2bd6e580b8105f4cb593 Mon Sep 17 00:00:00 2001 From: Jeffy Chen Date: Wed, 12 Jul 2017 14:18:32 +0800 Subject: drm: Add missing field copy in compat_drm_version DRM_IOCTL_VERSION is supposed to update the name_len/date_len/desc_len fields to user. Fixes: 012c6741c6aa ("switch compat_drm_version() to drm_ioctl_kernel()") Signed-off-by: Jeffy Chen Reviewed-by: Daniel Vetter Signed-off-by: Linus Torvalds --- drivers/gpu/drm/drm_ioc32.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/drm_ioc32.c b/drivers/gpu/drm/drm_ioc32.c index 0b2d8c4a2fa5..d1f202852028 100644 --- a/drivers/gpu/drm/drm_ioc32.c +++ b/drivers/gpu/drm/drm_ioc32.c @@ -112,6 +112,9 @@ static int compat_drm_version(struct file *file, unsigned int cmd, v32.version_major = v.version_major; v32.version_minor = v.version_minor; v32.version_patchlevel = v.version_patchlevel; + v32.name_len = v.name_len; + v32.date_len = v.date_len; + v32.desc_len = v.desc_len; if (copy_to_user((void __user *)arg, &v32, sizeof(v32))) return -EFAULT; return 0; -- cgit v1.2.3-59-g8ed1b From 6592e58c6b68e61f003a01ba29a3716e7e2e9484 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 12 Jul 2017 23:36:02 +0100 Subject: Btrfs: fix write corruption due to bio cloning on raid5/6 The recent changes to make bio cloning faster (added in the 4.13 merge window) by using the bio_clone_fast() API introduced a regression on raid5/6 modes, because cloned bios have an invalid bi_vcnt field (therefore it can not be used) and the raid5/6 code uses the bio_for_each_segment_all() API to iterate the segments of a bio, and this API uses a bio's bi_vcnt field. The issue is very simple to trigger by doing for example a direct IO write against a raid5 or raid6 filesystem and then attempting to read what we wrote before: $ mkfs.btrfs -m raid5 -d raid5 -f /dev/sdc /dev/sdd /dev/sde /dev/sdf $ mount /dev/sdc /mnt $ xfs_io -f -d -c "pwrite -S 0xab 0 1M" /mnt/foobar $ od -t x1 /mnt/foobar od: /mnt/foobar: read error: Input/output error For that example, the following is also reported in dmesg/syslog: [18274.985557] btrfs_print_data_csum_error: 18 callbacks suppressed [18274.995277] BTRFS warning (device sdf): csum failed root 5 ino 257 off 0 csum 0x98f94189 expected csum 0x94374193 mirror 1 [18274.997205] BTRFS warning (device sdf): csum failed root 5 ino 257 off 4096 csum 0x98f94189 expected csum 0x94374193 mirror 1 [18275.025221] BTRFS warning (device sdf): csum failed root 5 ino 257 off 8192 csum 0x98f94189 expected csum 0x94374193 mirror 1 [18275.047422] BTRFS warning (device sdf): csum failed root 5 ino 257 off 12288 csum 0x98f94189 expected csum 0x94374193 mirror 1 [18275.054818] BTRFS warning (device sdf): csum failed root 5 ino 257 off 4096 csum 0x98f94189 expected csum 0x94374193 mirror 1 [18275.054834] BTRFS warning (device sdf): csum failed root 5 ino 257 off 8192 csum 0x98f94189 expected csum 0x94374193 mirror 1 [18275.054943] BTRFS warning (device sdf): csum failed root 5 ino 257 off 8192 csum 0x98f94189 expected csum 0x94374193 mirror 2 [18275.055207] BTRFS warning (device sdf): csum failed root 5 ino 257 off 8192 csum 0x98f94189 expected csum 0x94374193 mirror 3 [18275.055571] BTRFS warning (device sdf): csum failed root 5 ino 257 off 0 csum 0x98f94189 expected csum 0x94374193 mirror 1 [18275.062171] BTRFS warning (device sdf): csum failed root 5 ino 257 off 12288 csum 0x98f94189 expected csum 0x94374193 mirror 1 A scrub will also fail correcting bad copies, mentioning the following in dmesg/syslog: [18276.128696] scrub_handle_errored_block: 498 callbacks suppressed [18276.129617] BTRFS warning (device sdf): checksum error at logical 2186346496 on dev /dev/sde, sector 2116608, root 5, inode 257, offset 65536, length 4096, links $ [18276.149235] btrfs_dev_stat_print_on_error: 498 callbacks suppressed [18276.157897] BTRFS error (device sdf): bdev /dev/sde errs: wr 0, rd 0, flush 0, corrupt 1, gen 0 [18276.206059] BTRFS warning (device sdf): checksum error at logical 2186477568 on dev /dev/sdd, sector 2116736, root 5, inode 257, offset 196608, length 4096, links$ [18276.206059] BTRFS error (device sdf): bdev /dev/sdd errs: wr 0, rd 0, flush 0, corrupt 1, gen 0 [18276.306552] BTRFS warning (device sdf): checksum error at logical 2186543104 on dev /dev/sdd, sector 2116864, root 5, inode 257, offset 262144, length 4096, links$ [18276.319152] BTRFS error (device sdf): bdev /dev/sdd errs: wr 0, rd 0, flush 0, corrupt 2, gen 0 [18276.394316] BTRFS warning (device sdf): checksum error at logical 2186739712 on dev /dev/sdf, sector 2116992, root 5, inode 257, offset 458752, length 4096, links$ [18276.396348] BTRFS error (device sdf): bdev /dev/sdf errs: wr 0, rd 0, flush 0, corrupt 1, gen 0 [18276.434127] BTRFS warning (device sdf): checksum error at logical 2186870784 on dev /dev/sde, sector 2117120, root 5, inode 257, offset 589824, length 4096, links$ [18276.434127] BTRFS error (device sdf): bdev /dev/sde errs: wr 0, rd 0, flush 0, corrupt 2, gen 0 [18276.500504] BTRFS error (device sdf): unable to fixup (regular) error at logical 2186477568 on dev /dev/sdd [18276.538400] BTRFS warning (device sdf): checksum error at logical 2186481664 on dev /dev/sdd, sector 2116744, root 5, inode 257, offset 200704, length 4096, links$ [18276.540452] BTRFS error (device sdf): bdev /dev/sdd errs: wr 0, rd 0, flush 0, corrupt 3, gen 0 [18276.542012] BTRFS error (device sdf): unable to fixup (regular) error at logical 2186481664 on dev /dev/sdd [18276.585030] BTRFS error (device sdf): unable to fixup (regular) error at logical 2186346496 on dev /dev/sde [18276.598306] BTRFS warning (device sdf): checksum error at logical 2186412032 on dev /dev/sde, sector 2116736, root 5, inode 257, offset 131072, length 4096, links$ [18276.598310] BTRFS error (device sdf): bdev /dev/sde errs: wr 0, rd 0, flush 0, corrupt 3, gen 0 [18276.598582] BTRFS error (device sdf): unable to fixup (regular) error at logical 2186350592 on dev /dev/sde [18276.603455] BTRFS error (device sdf): bdev /dev/sde errs: wr 0, rd 0, flush 0, corrupt 4, gen 0 [18276.638362] BTRFS warning (device sdf): checksum error at logical 2186354688 on dev /dev/sde, sector 2116624, root 5, inode 257, offset 73728, length 4096, links $ [18276.640445] BTRFS error (device sdf): bdev /dev/sde errs: wr 0, rd 0, flush 0, corrupt 5, gen 0 [18276.645942] BTRFS error (device sdf): unable to fixup (regular) error at logical 2186354688 on dev /dev/sde [18276.657204] BTRFS error (device sdf): unable to fixup (regular) error at logical 2186412032 on dev /dev/sde [18276.660563] BTRFS warning (device sdf): checksum error at logical 2186416128 on dev /dev/sde, sector 2116744, root 5, inode 257, offset 135168, length 4096, links$ [18276.664609] BTRFS error (device sdf): bdev /dev/sde errs: wr 0, rd 0, flush 0, corrupt 6, gen 0 [18276.664609] BTRFS error (device sdf): unable to fixup (regular) error at logical 2186358784 on dev /dev/sde So fix this by using the bio_for_each_segment() API and setting before the bio's bi_iter field to the value of the corresponding btrfs bio container's saved iterator if we are processing a cloned bio in the raid5/6 code (the same code processes both cloned and non-cloned bios). This incorrect iteration of cloned bios was also causing some occasional BUG_ONs when running fstest btrfs/064, which have a trace like the following: [ 6674.416156] ------------[ cut here ]------------ [ 6674.416157] kernel BUG at fs/btrfs/raid56.c:1897! [ 6674.416159] invalid opcode: 0000 [#1] PREEMPT SMP [ 6674.416160] Modules linked in: dm_flakey dm_mod dax ppdev tpm_tis parport_pc tpm_tis_core evdev tpm psmouse sg i2c_piix4 pcspkr parport i2c_core serio_raw button s [ 6674.416184] CPU: 3 PID: 19236 Comm: kworker/u32:10 Not tainted 4.12.0-rc6-btrfs-next-44+ #1 [ 6674.416185] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.1-0-gb3ef39f-prebuilt.qemu-project.org 04/01/2014 [ 6674.416210] Workqueue: btrfs-endio btrfs_endio_helper [btrfs] [ 6674.416211] task: ffff880147f6c740 task.stack: ffffc90001fb8000 [ 6674.416229] RIP: 0010:__raid_recover_end_io+0x1ac/0x370 [btrfs] [ 6674.416230] RSP: 0018:ffffc90001fbbb90 EFLAGS: 00010217 [ 6674.416231] RAX: ffff8801ff4b4f00 RBX: 0000000000000002 RCX: 0000000000000001 [ 6674.416232] RDX: ffff880099b045d8 RSI: ffffffff81a5f6e0 RDI: 0000000000000004 [ 6674.416232] RBP: ffffc90001fbbbc8 R08: 0000000000000001 R09: 0000000000000001 [ 6674.416233] R10: ffffc90001fbbac8 R11: 0000000000001000 R12: 0000000000000002 [ 6674.416234] R13: ffff880099b045c0 R14: 0000000000000004 R15: ffff88012bff2000 [ 6674.416235] FS: 0000000000000000(0000) GS:ffff88023f2c0000(0000) knlGS:0000000000000000 [ 6674.416235] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 6674.416236] CR2: 00007f28cf282000 CR3: 00000001000c6000 CR4: 00000000000006e0 [ 6674.416239] Call Trace: [ 6674.416259] __raid56_parity_recover+0xfc/0x16e [btrfs] [ 6674.416276] raid56_parity_recover+0x157/0x16b [btrfs] [ 6674.416293] btrfs_map_bio+0xe0/0x259 [btrfs] [ 6674.416310] btrfs_submit_bio_hook+0xbf/0x147 [btrfs] [ 6674.416327] end_bio_extent_readpage+0x27b/0x4a0 [btrfs] [ 6674.416331] bio_endio+0x17d/0x1b3 [ 6674.416346] end_workqueue_fn+0x3c/0x3f [btrfs] [ 6674.416362] btrfs_scrubparity_helper+0x1aa/0x3b8 [btrfs] [ 6674.416379] btrfs_endio_helper+0xe/0x10 [btrfs] [ 6674.416381] process_one_work+0x276/0x4b6 [ 6674.416384] worker_thread+0x1ac/0x266 [ 6674.416386] ? rescuer_thread+0x278/0x278 [ 6674.416387] kthread+0x106/0x10e [ 6674.416389] ? __list_del_entry+0x22/0x22 [ 6674.416391] ret_from_fork+0x27/0x40 [ 6674.416395] Code: 44 89 e2 be 00 10 00 00 ff 15 b0 ab ef ff eb 72 4d 89 e8 89 d9 44 89 e2 be 00 10 00 00 ff 15 a3 ab ef ff eb 5d 41 83 fc ff 74 02 <0f> 0b 49 63 97 [ 6674.416432] RIP: __raid_recover_end_io+0x1ac/0x370 [btrfs] RSP: ffffc90001fbbb90 [ 6674.416434] ---[ end trace 74d56ebe7489dd6a ]--- Signed-off-by: Filipe Manana Reviewed-by: Liu Bo --- fs/btrfs/raid56.c | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index b9abb0b01021..b89d07003697 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -1136,20 +1136,27 @@ static void validate_rbio_for_rmw(struct btrfs_raid_bio *rbio) static void index_rbio_pages(struct btrfs_raid_bio *rbio) { struct bio *bio; - struct bio_vec *bvec; u64 start; unsigned long stripe_offset; unsigned long page_index; - int i; spin_lock_irq(&rbio->bio_list_lock); bio_list_for_each(bio, &rbio->bio_list) { + struct bio_vec bvec; + struct bvec_iter iter; + int i = 0; + start = (u64)bio->bi_iter.bi_sector << 9; stripe_offset = start - rbio->bbio->raid_map[0]; page_index = stripe_offset >> PAGE_SHIFT; - bio_for_each_segment_all(bvec, bio, i) - rbio->bio_pages[page_index + i] = bvec->bv_page; + if (bio_flagged(bio, BIO_CLONED)) + bio->bi_iter = btrfs_io_bio(bio)->iter; + + bio_for_each_segment(bvec, bio, iter) { + rbio->bio_pages[page_index + i] = bvec.bv_page; + i++; + } } spin_unlock_irq(&rbio->bio_list_lock); } @@ -1423,11 +1430,14 @@ static int fail_bio_stripe(struct btrfs_raid_bio *rbio, */ static void set_bio_pages_uptodate(struct bio *bio) { - struct bio_vec *bvec; - int i; + struct bio_vec bvec; + struct bvec_iter iter; + + if (bio_flagged(bio, BIO_CLONED)) + bio->bi_iter = btrfs_io_bio(bio)->iter; - bio_for_each_segment_all(bvec, bio, i) - SetPageUptodate(bvec->bv_page); + bio_for_each_segment(bvec, bio, iter) + SetPageUptodate(bvec.bv_page); } /* -- cgit v1.2.3-59-g8ed1b From 0aebdc52ca824c38837a652548028e45da72628f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 09:31:19 +0200 Subject: sunrpc: properly type argument to kxdreproc_t Pass struct rpc_request as the first argument instead of an untyped blob, and mark the data object as const. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton --- include/linux/sunrpc/xdr.h | 5 ++++- net/sunrpc/clnt.c | 3 ++- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 054c8cde18f3..290f189de200 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -17,6 +17,8 @@ #include #include +struct rpc_rqst; + /* * Buffer adjustment */ @@ -222,7 +224,8 @@ struct xdr_stream { /* * These are the xdr_stream style generic XDR encode and decode functions. */ -typedef void (*kxdreproc_t)(void *rqstp, struct xdr_stream *xdr, void *obj); +typedef void (*kxdreproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + const void *obj); typedef int (*kxdrdproc_t)(void *rqstp, struct xdr_stream *xdr, void *obj); extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index b5cb921775a0..9fee20dc0c80 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2476,7 +2476,8 @@ out_overflow: goto out_garbage; } -static void rpcproc_encode_null(void *rqstp, struct xdr_stream *xdr, void *obj) +static void rpcproc_encode_null(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + const void *obj) { } -- cgit v1.2.3-59-g8ed1b From 8be9d07f0ca68a188ab448e5fad8ea5d7420f535 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 09:59:45 +0200 Subject: sunrpc: fix encoder callback prototypes Declare the p_encode callbacks with the proper prototype instead of casting to kxdreproc_t and losing all type safety. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton Acked-by: Trond Myklebust --- net/sunrpc/rpcb_clnt.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 5b30603596d0..d0269a39afdf 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -843,8 +843,9 @@ static void rpcb_getport_done(struct rpc_task *child, void *data) */ static void rpcb_enc_mapping(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct rpcbind_args *rpcb) + const void *data) { + const struct rpcbind_args *rpcb = data; __be32 *p; dprintk("RPC: %5u encoding PMAP_%s call (%u, %u, %d, %u)\n", @@ -917,8 +918,9 @@ static void encode_rpcb_string(struct xdr_stream *xdr, const char *string, } static void rpcb_enc_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct rpcbind_args *rpcb) + const void *data) { + const struct rpcbind_args *rpcb = data; __be32 *p; dprintk("RPC: %5u encoding RPCB_%s call (%u, %u, '%s', '%s')\n", @@ -992,7 +994,7 @@ out_fail: static struct rpc_procinfo rpcb_procedures2[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, - .p_encode = (kxdreproc_t)rpcb_enc_mapping, + .p_encode = rpcb_enc_mapping, .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_setres_sz, @@ -1002,7 +1004,7 @@ static struct rpc_procinfo rpcb_procedures2[] = { }, [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, - .p_encode = (kxdreproc_t)rpcb_enc_mapping, + .p_encode = rpcb_enc_mapping, .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_setres_sz, @@ -1012,7 +1014,7 @@ static struct rpc_procinfo rpcb_procedures2[] = { }, [RPCBPROC_GETPORT] = { .p_proc = RPCBPROC_GETPORT, - .p_encode = (kxdreproc_t)rpcb_enc_mapping, + .p_encode = rpcb_enc_mapping, .p_decode = (kxdrdproc_t)rpcb_dec_getport, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_getportres_sz, @@ -1025,7 +1027,7 @@ static struct rpc_procinfo rpcb_procedures2[] = { static struct rpc_procinfo rpcb_procedures3[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, - .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_encode = rpcb_enc_getaddr, .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, @@ -1035,7 +1037,7 @@ static struct rpc_procinfo rpcb_procedures3[] = { }, [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, - .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_encode = rpcb_enc_getaddr, .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, @@ -1045,7 +1047,7 @@ static struct rpc_procinfo rpcb_procedures3[] = { }, [RPCBPROC_GETADDR] = { .p_proc = RPCBPROC_GETADDR, - .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_encode = rpcb_enc_getaddr, .p_decode = (kxdrdproc_t)rpcb_dec_getaddr, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_getaddrres_sz, @@ -1058,7 +1060,7 @@ static struct rpc_procinfo rpcb_procedures3[] = { static struct rpc_procinfo rpcb_procedures4[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, - .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_encode = rpcb_enc_getaddr, .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, @@ -1068,7 +1070,7 @@ static struct rpc_procinfo rpcb_procedures4[] = { }, [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, - .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_encode = rpcb_enc_getaddr, .p_decode = (kxdrdproc_t)rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, @@ -1078,7 +1080,7 @@ static struct rpc_procinfo rpcb_procedures4[] = { }, [RPCBPROC_GETADDR] = { .p_proc = RPCBPROC_GETADDR, - .p_encode = (kxdreproc_t)rpcb_enc_getaddr, + .p_encode = rpcb_enc_getaddr, .p_decode = (kxdrdproc_t)rpcb_dec_getaddr, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_getaddrres_sz, -- cgit v1.2.3-59-g8ed1b From d16073389bb48a2caf7c62cd7089a2009c8717b8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 09:34:04 +0200 Subject: lockd: fix encoder callback prototypes Declare the p_encode callbacks with the proper prototype instead of casting to kxdreproc_t and losing all type safety. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton Acked-by: Trond Myklebust --- fs/lockd/clnt4xdr.c | 22 +++++++++++++++------- fs/lockd/clntxdr.c | 22 +++++++++++++++------- fs/lockd/mon.c | 8 ++++---- 3 files changed, 34 insertions(+), 18 deletions(-) diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c index d3e40db28930..3cbad662120a 100644 --- a/fs/lockd/clnt4xdr.c +++ b/fs/lockd/clnt4xdr.c @@ -381,8 +381,9 @@ static void encode_nlm4_lock(struct xdr_stream *xdr, */ static void nlm4_xdr_enc_testargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -402,8 +403,9 @@ static void nlm4_xdr_enc_testargs(struct rpc_rqst *req, */ static void nlm4_xdr_enc_lockargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -424,8 +426,9 @@ static void nlm4_xdr_enc_lockargs(struct rpc_rqst *req, */ static void nlm4_xdr_enc_cancargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -442,8 +445,9 @@ static void nlm4_xdr_enc_cancargs(struct rpc_rqst *req, */ static void nlm4_xdr_enc_unlockargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -458,8 +462,10 @@ static void nlm4_xdr_enc_unlockargs(struct rpc_rqst *req, */ static void nlm4_xdr_enc_res(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_res *result) + const void *data) { + const struct nlm_res *result = data; + encode_cookie(xdr, &result->cookie); encode_nlm4_stat(xdr, result->status); } @@ -479,8 +485,10 @@ static void nlm4_xdr_enc_res(struct rpc_rqst *req, */ static void nlm4_xdr_enc_testres(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_res *result) + const void *data) { + const struct nlm_res *result = data; + encode_cookie(xdr, &result->cookie); encode_nlm4_stat(xdr, result->status); if (result->status == nlm_lck_denied) @@ -566,7 +574,7 @@ out: #define PROC(proc, argtype, restype) \ [NLMPROC_##proc] = { \ .p_proc = NLMPROC_##proc, \ - .p_encode = (kxdreproc_t)nlm4_xdr_enc_##argtype, \ + .p_encode = nlm4_xdr_enc_##argtype, \ .p_decode = (kxdrdproc_t)nlm4_xdr_dec_##restype, \ .p_arglen = NLM4_##argtype##_sz, \ .p_replen = NLM4_##restype##_sz, \ diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c index 3e9f7874b975..825c0fde8c80 100644 --- a/fs/lockd/clntxdr.c +++ b/fs/lockd/clntxdr.c @@ -374,8 +374,9 @@ static void encode_nlm_lock(struct xdr_stream *xdr, */ static void nlm_xdr_enc_testargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -395,8 +396,9 @@ static void nlm_xdr_enc_testargs(struct rpc_rqst *req, */ static void nlm_xdr_enc_lockargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -417,8 +419,9 @@ static void nlm_xdr_enc_lockargs(struct rpc_rqst *req, */ static void nlm_xdr_enc_cancargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -435,8 +438,9 @@ static void nlm_xdr_enc_cancargs(struct rpc_rqst *req, */ static void nlm_xdr_enc_unlockargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -451,8 +455,10 @@ static void nlm_xdr_enc_unlockargs(struct rpc_rqst *req, */ static void nlm_xdr_enc_res(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_res *result) + const void *data) { + const struct nlm_res *result = data; + encode_cookie(xdr, &result->cookie); encode_nlm_stat(xdr, result->status); } @@ -479,8 +485,10 @@ static void encode_nlm_testrply(struct xdr_stream *xdr, static void nlm_xdr_enc_testres(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_res *result) + const void *data) { + const struct nlm_res *result = data; + encode_cookie(xdr, &result->cookie); encode_nlm_stat(xdr, result->status); encode_nlm_testrply(xdr, result); @@ -564,7 +572,7 @@ out: #define PROC(proc, argtype, restype) \ [NLMPROC_##proc] = { \ .p_proc = NLMPROC_##proc, \ - .p_encode = (kxdreproc_t)nlm_xdr_enc_##argtype, \ + .p_encode = nlm_xdr_enc_##argtype, \ .p_decode = (kxdrdproc_t)nlm_xdr_dec_##restype, \ .p_arglen = NLM_##argtype##_sz, \ .p_replen = NLM_##restype##_sz, \ diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 19166d4a8d31..8043fd4b8a5c 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -476,14 +476,14 @@ static void encode_priv(struct xdr_stream *xdr, const struct nsm_args *argp) } static void nsm_xdr_enc_mon(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nsm_args *argp) + const void *argp) { encode_mon_id(xdr, argp); encode_priv(xdr, argp); } static void nsm_xdr_enc_unmon(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nsm_args *argp) + const void *argp) { encode_mon_id(xdr, argp); } @@ -532,7 +532,7 @@ static int nsm_xdr_dec_stat(struct rpc_rqst *rqstp, static struct rpc_procinfo nsm_procedures[] = { [NSMPROC_MON] = { .p_proc = NSMPROC_MON, - .p_encode = (kxdreproc_t)nsm_xdr_enc_mon, + .p_encode = nsm_xdr_enc_mon, .p_decode = (kxdrdproc_t)nsm_xdr_dec_stat_res, .p_arglen = SM_mon_sz, .p_replen = SM_monres_sz, @@ -541,7 +541,7 @@ static struct rpc_procinfo nsm_procedures[] = { }, [NSMPROC_UNMON] = { .p_proc = NSMPROC_UNMON, - .p_encode = (kxdreproc_t)nsm_xdr_enc_unmon, + .p_encode = nsm_xdr_enc_unmon, .p_decode = (kxdrdproc_t)nsm_xdr_dec_stat, .p_arglen = SM_mon_id_sz, .p_replen = SM_unmonres_sz, -- cgit v1.2.3-59-g8ed1b From fcc85819ee4826f52b0d6c959c759329e6d87bfc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 10:01:49 +0200 Subject: nfs: fix encoder callback prototypes Declare the p_encode callbacks with the proper prototype instead of casting to kxdreproc_t and losing all type safety. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton Acked-by: Trond Myklebust --- fs/nfs/mount_clnt.c | 10 +-- fs/nfs/nfs2xdr.c | 49 ++++++++++---- fs/nfs/nfs3xdr.c | 83 ++++++++++++++++------- fs/nfs/nfs42xdr.c | 34 ++++++---- fs/nfs/nfs4xdr.c | 188 +++++++++++++++++++++++++++++++++------------------- 5 files changed, 242 insertions(+), 122 deletions(-) diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index 09b190015df4..f435d640d552 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -304,7 +304,7 @@ static void encode_mntdirpath(struct xdr_stream *xdr, const char *pathname) } static void mnt_xdr_enc_dirpath(struct rpc_rqst *req, struct xdr_stream *xdr, - const char *dirpath) + const void *dirpath) { encode_mntdirpath(xdr, dirpath); } @@ -467,7 +467,7 @@ static int mnt_xdr_dec_mountres3(struct rpc_rqst *req, static struct rpc_procinfo mnt_procedures[] = { [MOUNTPROC_MNT] = { .p_proc = MOUNTPROC_MNT, - .p_encode = (kxdreproc_t)mnt_xdr_enc_dirpath, + .p_encode = mnt_xdr_enc_dirpath, .p_decode = (kxdrdproc_t)mnt_xdr_dec_mountres, .p_arglen = MNT_enc_dirpath_sz, .p_replen = MNT_dec_mountres_sz, @@ -476,7 +476,7 @@ static struct rpc_procinfo mnt_procedures[] = { }, [MOUNTPROC_UMNT] = { .p_proc = MOUNTPROC_UMNT, - .p_encode = (kxdreproc_t)mnt_xdr_enc_dirpath, + .p_encode = mnt_xdr_enc_dirpath, .p_arglen = MNT_enc_dirpath_sz, .p_statidx = MOUNTPROC_UMNT, .p_name = "UMOUNT", @@ -486,7 +486,7 @@ static struct rpc_procinfo mnt_procedures[] = { static struct rpc_procinfo mnt3_procedures[] = { [MOUNTPROC3_MNT] = { .p_proc = MOUNTPROC3_MNT, - .p_encode = (kxdreproc_t)mnt_xdr_enc_dirpath, + .p_encode = mnt_xdr_enc_dirpath, .p_decode = (kxdrdproc_t)mnt_xdr_dec_mountres3, .p_arglen = MNT_enc_dirpath_sz, .p_replen = MNT_dec_mountres3_sz, @@ -495,7 +495,7 @@ static struct rpc_procinfo mnt3_procedures[] = { }, [MOUNTPROC3_UMNT] = { .p_proc = MOUNTPROC3_UMNT, - .p_encode = (kxdreproc_t)mnt_xdr_enc_dirpath, + .p_encode = mnt_xdr_enc_dirpath, .p_arglen = MNT_enc_dirpath_sz, .p_statidx = MOUNTPROC3_UMNT, .p_name = "UMOUNT", diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index b4e03ed8599d..8ecd58597228 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -568,8 +568,10 @@ out_default: static void nfs2_xdr_enc_fhandle(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_fh *fh) + const void *data) { + const struct nfs_fh *fh = data; + encode_fhandle(xdr, fh); } @@ -583,23 +585,29 @@ static void nfs2_xdr_enc_fhandle(struct rpc_rqst *req, */ static void nfs2_xdr_enc_sattrargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_sattrargs *args) + const void *data) { + const struct nfs_sattrargs *args = data; + encode_fhandle(xdr, args->fh); encode_sattr(xdr, args->sattr); } static void nfs2_xdr_enc_diropargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_diropargs *args) + const void *data) { + const struct nfs_diropargs *args = data; + encode_diropargs(xdr, args->fh, args->name, args->len); } static void nfs2_xdr_enc_readlinkargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_readlinkargs *args) + const void *data) { + const struct nfs_readlinkargs *args = data; + encode_fhandle(xdr, args->fh); prepare_reply_buffer(req, args->pages, args->pgbase, args->pglen, NFS_readlinkres_sz); @@ -632,8 +640,10 @@ static void encode_readargs(struct xdr_stream *xdr, static void nfs2_xdr_enc_readargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_pgio_args *args) + const void *data) { + const struct nfs_pgio_args *args = data; + encode_readargs(xdr, args); prepare_reply_buffer(req, args->pages, args->pgbase, args->count, NFS_readres_sz); @@ -672,8 +682,10 @@ static void encode_writeargs(struct xdr_stream *xdr, static void nfs2_xdr_enc_writeargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_pgio_args *args) + const void *data) { + const struct nfs_pgio_args *args = data; + encode_writeargs(xdr, args); xdr->buf->flags |= XDRBUF_WRITE; } @@ -688,16 +700,20 @@ static void nfs2_xdr_enc_writeargs(struct rpc_rqst *req, */ static void nfs2_xdr_enc_createargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_createargs *args) + const void *data) { + const struct nfs_createargs *args = data; + encode_diropargs(xdr, args->fh, args->name, args->len); encode_sattr(xdr, args->sattr); } static void nfs2_xdr_enc_removeargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_removeargs *args) + const void *data) { + const struct nfs_removeargs *args = data; + encode_diropargs(xdr, args->fh, args->name.name, args->name.len); } @@ -711,8 +727,9 @@ static void nfs2_xdr_enc_removeargs(struct rpc_rqst *req, */ static void nfs2_xdr_enc_renameargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_renameargs *args) + const void *data) { + const struct nfs_renameargs *args = data; const struct qstr *old = args->old_name; const struct qstr *new = args->new_name; @@ -730,8 +747,10 @@ static void nfs2_xdr_enc_renameargs(struct rpc_rqst *req, */ static void nfs2_xdr_enc_linkargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_linkargs *args) + const void *data) { + const struct nfs_linkargs *args = data; + encode_fhandle(xdr, args->fromfh); encode_diropargs(xdr, args->tofh, args->toname, args->tolen); } @@ -747,8 +766,10 @@ static void nfs2_xdr_enc_linkargs(struct rpc_rqst *req, */ static void nfs2_xdr_enc_symlinkargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_symlinkargs *args) + const void *data) { + const struct nfs_symlinkargs *args = data; + encode_diropargs(xdr, args->fromfh, args->fromname, args->fromlen); encode_path(xdr, args->pages, args->pathlen); encode_sattr(xdr, args->sattr); @@ -777,8 +798,10 @@ static void encode_readdirargs(struct xdr_stream *xdr, static void nfs2_xdr_enc_readdirargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_readdirargs *args) + const void *data) { + const struct nfs_readdirargs *args = data; + encode_readdirargs(xdr, args); prepare_reply_buffer(req, args->pages, 0, args->count, NFS_readdirres_sz); @@ -1118,7 +1141,7 @@ static int nfs_stat_to_errno(enum nfs_stat status) #define PROC(proc, argtype, restype, timer) \ [NFSPROC_##proc] = { \ .p_proc = NFSPROC_##proc, \ - .p_encode = (kxdreproc_t)nfs2_xdr_enc_##argtype, \ + .p_encode = nfs2_xdr_enc_##argtype, \ .p_decode = (kxdrdproc_t)nfs2_xdr_dec_##restype, \ .p_arglen = NFS_##argtype##_sz, \ .p_replen = NFS_##restype##_sz, \ diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 267126d32ec0..773150678633 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -846,8 +846,10 @@ static void encode_diropargs3(struct xdr_stream *xdr, const struct nfs_fh *fh, */ static void nfs3_xdr_enc_getattr3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_fh *fh) + const void *data) { + const struct nfs_fh *fh = data; + encode_nfs_fh3(xdr, fh); } @@ -884,8 +886,9 @@ static void encode_sattrguard3(struct xdr_stream *xdr, static void nfs3_xdr_enc_setattr3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_sattrargs *args) + const void *data) { + const struct nfs3_sattrargs *args = data; encode_nfs_fh3(xdr, args->fh); encode_sattr3(xdr, args->sattr); encode_sattrguard3(xdr, args); @@ -900,8 +903,10 @@ static void nfs3_xdr_enc_setattr3args(struct rpc_rqst *req, */ static void nfs3_xdr_enc_lookup3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_diropargs *args) + const void *data) { + const struct nfs3_diropargs *args = data; + encode_diropargs3(xdr, args->fh, args->name, args->len); } @@ -922,8 +927,10 @@ static void encode_access3args(struct xdr_stream *xdr, static void nfs3_xdr_enc_access3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_accessargs *args) + const void *data) { + const struct nfs3_accessargs *args = data; + encode_access3args(xdr, args); } @@ -936,8 +943,10 @@ static void nfs3_xdr_enc_access3args(struct rpc_rqst *req, */ static void nfs3_xdr_enc_readlink3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_readlinkargs *args) + const void *data) { + const struct nfs3_readlinkargs *args = data; + encode_nfs_fh3(xdr, args->fh); prepare_reply_buffer(req, args->pages, args->pgbase, args->pglen, NFS3_readlinkres_sz); @@ -966,8 +975,10 @@ static void encode_read3args(struct xdr_stream *xdr, static void nfs3_xdr_enc_read3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_pgio_args *args) + const void *data) { + const struct nfs_pgio_args *args = data; + encode_read3args(xdr, args); prepare_reply_buffer(req, args->pages, args->pgbase, args->count, NFS3_readres_sz); @@ -1008,8 +1019,10 @@ static void encode_write3args(struct xdr_stream *xdr, static void nfs3_xdr_enc_write3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_pgio_args *args) + const void *data) { + const struct nfs_pgio_args *args = data; + encode_write3args(xdr, args); xdr->buf->flags |= XDRBUF_WRITE; } @@ -1055,8 +1068,10 @@ static void encode_createhow3(struct xdr_stream *xdr, static void nfs3_xdr_enc_create3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_createargs *args) + const void *data) { + const struct nfs3_createargs *args = data; + encode_diropargs3(xdr, args->fh, args->name, args->len); encode_createhow3(xdr, args); } @@ -1071,8 +1086,10 @@ static void nfs3_xdr_enc_create3args(struct rpc_rqst *req, */ static void nfs3_xdr_enc_mkdir3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_mkdirargs *args) + const void *data) { + const struct nfs3_mkdirargs *args = data; + encode_diropargs3(xdr, args->fh, args->name, args->len); encode_sattr3(xdr, args->sattr); } @@ -1091,16 +1108,20 @@ static void nfs3_xdr_enc_mkdir3args(struct rpc_rqst *req, * }; */ static void encode_symlinkdata3(struct xdr_stream *xdr, - const struct nfs3_symlinkargs *args) + const void *data) { + const struct nfs3_symlinkargs *args = data; + encode_sattr3(xdr, args->sattr); encode_nfspath3(xdr, args->pages, args->pathlen); } static void nfs3_xdr_enc_symlink3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_symlinkargs *args) + const void *data) { + const struct nfs3_symlinkargs *args = data; + encode_diropargs3(xdr, args->fromfh, args->fromname, args->fromlen); encode_symlinkdata3(xdr, args); xdr->buf->flags |= XDRBUF_WRITE; @@ -1160,8 +1181,10 @@ static void encode_mknoddata3(struct xdr_stream *xdr, static void nfs3_xdr_enc_mknod3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_mknodargs *args) + const void *data) { + const struct nfs3_mknodargs *args = data; + encode_diropargs3(xdr, args->fh, args->name, args->len); encode_mknoddata3(xdr, args); } @@ -1175,8 +1198,10 @@ static void nfs3_xdr_enc_mknod3args(struct rpc_rqst *req, */ static void nfs3_xdr_enc_remove3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_removeargs *args) + const void *data) { + const struct nfs_removeargs *args = data; + encode_diropargs3(xdr, args->fh, args->name.name, args->name.len); } @@ -1190,8 +1215,9 @@ static void nfs3_xdr_enc_remove3args(struct rpc_rqst *req, */ static void nfs3_xdr_enc_rename3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_renameargs *args) + const void *data) { + const struct nfs_renameargs *args = data; const struct qstr *old = args->old_name; const struct qstr *new = args->new_name; @@ -1209,8 +1235,10 @@ static void nfs3_xdr_enc_rename3args(struct rpc_rqst *req, */ static void nfs3_xdr_enc_link3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_linkargs *args) + const void *data) { + const struct nfs3_linkargs *args = data; + encode_nfs_fh3(xdr, args->fromfh); encode_diropargs3(xdr, args->tofh, args->toname, args->tolen); } @@ -1240,8 +1268,10 @@ static void encode_readdir3args(struct xdr_stream *xdr, static void nfs3_xdr_enc_readdir3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_readdirargs *args) + const void *data) { + const struct nfs3_readdirargs *args = data; + encode_readdir3args(xdr, args); prepare_reply_buffer(req, args->pages, 0, args->count, NFS3_readdirres_sz); @@ -1280,8 +1310,10 @@ static void encode_readdirplus3args(struct xdr_stream *xdr, static void nfs3_xdr_enc_readdirplus3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_readdirargs *args) + const void *data) { + const struct nfs3_readdirargs *args = data; + encode_readdirplus3args(xdr, args); prepare_reply_buffer(req, args->pages, 0, args->count, NFS3_readdirres_sz); @@ -1310,8 +1342,10 @@ static void encode_commit3args(struct xdr_stream *xdr, static void nfs3_xdr_enc_commit3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_commitargs *args) + const void *data) { + const struct nfs_commitargs *args = data; + encode_commit3args(xdr, args); } @@ -1319,8 +1353,10 @@ static void nfs3_xdr_enc_commit3args(struct rpc_rqst *req, static void nfs3_xdr_enc_getacl3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_getaclargs *args) + const void *data) { + const struct nfs3_getaclargs *args = data; + encode_nfs_fh3(xdr, args->fh); encode_uint32(xdr, args->mask); if (args->mask & (NFS_ACL | NFS_DFACL)) @@ -1331,8 +1367,9 @@ static void nfs3_xdr_enc_getacl3args(struct rpc_rqst *req, static void nfs3_xdr_enc_setacl3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_setaclargs *args) + const void *data) { + const struct nfs3_setaclargs *args = data; unsigned int base; int error; @@ -2495,7 +2532,7 @@ static int nfs3_stat_to_errno(enum nfs_stat status) #define PROC(proc, argtype, restype, timer) \ [NFS3PROC_##proc] = { \ .p_proc = NFS3PROC_##proc, \ - .p_encode = (kxdreproc_t)nfs3_xdr_enc_##argtype##3args, \ + .p_encode = nfs3_xdr_enc_##argtype##3args, \ .p_decode = (kxdrdproc_t)nfs3_xdr_dec_##restype##3res, \ .p_arglen = NFS3_##argtype##args_sz, \ .p_replen = NFS3_##restype##res_sz, \ @@ -2538,7 +2575,7 @@ const struct rpc_version nfs_version3 = { static struct rpc_procinfo nfs3_acl_procedures[] = { [ACLPROC3_GETACL] = { .p_proc = ACLPROC3_GETACL, - .p_encode = (kxdreproc_t)nfs3_xdr_enc_getacl3args, + .p_encode = nfs3_xdr_enc_getacl3args, .p_decode = (kxdrdproc_t)nfs3_xdr_dec_getacl3res, .p_arglen = ACL3_getaclargs_sz, .p_replen = ACL3_getaclres_sz, @@ -2547,7 +2584,7 @@ static struct rpc_procinfo nfs3_acl_procedures[] = { }, [ACLPROC3_SETACL] = { .p_proc = ACLPROC3_SETACL, - .p_encode = (kxdreproc_t)nfs3_xdr_enc_setacl3args, + .p_encode = nfs3_xdr_enc_setacl3args, .p_decode = (kxdrdproc_t)nfs3_xdr_dec_setacl3res, .p_arglen = ACL3_setaclargs_sz, .p_replen = ACL3_setaclres_sz, diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index 528362f69cc1..0a1bd60a1f8e 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -112,7 +112,7 @@ decode_getattr_maxsz) static void encode_fallocate(struct xdr_stream *xdr, - struct nfs42_falloc_args *args) + const struct nfs42_falloc_args *args) { encode_nfs4_stateid(xdr, &args->falloc_stateid); encode_uint64(xdr, args->falloc_offset); @@ -120,7 +120,7 @@ static void encode_fallocate(struct xdr_stream *xdr, } static void encode_allocate(struct xdr_stream *xdr, - struct nfs42_falloc_args *args, + const struct nfs42_falloc_args *args, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_ALLOCATE, decode_allocate_maxsz, hdr); @@ -128,7 +128,7 @@ static void encode_allocate(struct xdr_stream *xdr, } static void encode_copy(struct xdr_stream *xdr, - struct nfs42_copy_args *args, + const struct nfs42_copy_args *args, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_COPY, decode_copy_maxsz, hdr); @@ -145,7 +145,7 @@ static void encode_copy(struct xdr_stream *xdr, } static void encode_deallocate(struct xdr_stream *xdr, - struct nfs42_falloc_args *args, + const struct nfs42_falloc_args *args, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_DEALLOCATE, decode_deallocate_maxsz, hdr); @@ -153,7 +153,7 @@ static void encode_deallocate(struct xdr_stream *xdr, } static void encode_seek(struct xdr_stream *xdr, - struct nfs42_seek_args *args, + const struct nfs42_seek_args *args, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_SEEK, decode_seek_maxsz, hdr); @@ -163,7 +163,7 @@ static void encode_seek(struct xdr_stream *xdr, } static void encode_layoutstats(struct xdr_stream *xdr, - struct nfs42_layoutstat_args *args, + const struct nfs42_layoutstat_args *args, struct nfs42_layoutstat_devinfo *devinfo, struct compound_hdr *hdr) { @@ -191,7 +191,7 @@ static void encode_layoutstats(struct xdr_stream *xdr, } static void encode_clone(struct xdr_stream *xdr, - struct nfs42_clone_args *args, + const struct nfs42_clone_args *args, struct compound_hdr *hdr) { __be32 *p; @@ -210,8 +210,9 @@ static void encode_clone(struct xdr_stream *xdr, */ static void nfs4_xdr_enc_allocate(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs42_falloc_args *args) + const void *data) { + const struct nfs42_falloc_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -225,7 +226,7 @@ static void nfs4_xdr_enc_allocate(struct rpc_rqst *req, } static void encode_copy_commit(struct xdr_stream *xdr, - struct nfs42_copy_args *args, + const struct nfs42_copy_args *args, struct compound_hdr *hdr) { __be32 *p; @@ -241,8 +242,9 @@ static void encode_copy_commit(struct xdr_stream *xdr, */ static void nfs4_xdr_enc_copy(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs42_copy_args *args) + const void *data) { + const struct nfs42_copy_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -262,8 +264,9 @@ static void nfs4_xdr_enc_copy(struct rpc_rqst *req, */ static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs42_falloc_args *args) + const void *data) { + const struct nfs42_falloc_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -281,8 +284,9 @@ static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req, */ static void nfs4_xdr_enc_seek(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs42_seek_args *args) + const void *data) { + const struct nfs42_seek_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -299,8 +303,9 @@ static void nfs4_xdr_enc_seek(struct rpc_rqst *req, */ static void nfs4_xdr_enc_layoutstats(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs42_layoutstat_args *args) + const void *data) { + const struct nfs42_layoutstat_args *args = data; int i; struct compound_hdr hdr = { @@ -321,8 +326,9 @@ static void nfs4_xdr_enc_layoutstats(struct rpc_rqst *req, */ static void nfs4_xdr_enc_clone(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs42_clone_args *args) + const void *data) { + const struct nfs42_clone_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 3aebfdc82b30..c5036ef770f9 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1651,7 +1651,8 @@ encode_restorefh(struct xdr_stream *xdr, struct compound_hdr *hdr) } static void -encode_setacl(struct xdr_stream *xdr, struct nfs_setaclargs *arg, struct compound_hdr *hdr) +encode_setacl(struct xdr_stream *xdr, const struct nfs_setaclargs *arg, + struct compound_hdr *hdr) { __be32 *p; @@ -1735,7 +1736,7 @@ static void encode_secinfo(struct xdr_stream *xdr, const struct qstr *name, stru #if defined(CONFIG_NFS_V4_1) /* NFSv4.1 operations */ static void encode_bind_conn_to_session(struct xdr_stream *xdr, - struct nfs41_bind_conn_to_session_args *args, + const struct nfs41_bind_conn_to_session_args *args, struct compound_hdr *hdr) { __be32 *p; @@ -1748,7 +1749,7 @@ static void encode_bind_conn_to_session(struct xdr_stream *xdr, *p = (args->use_conn_in_rdma_mode) ? cpu_to_be32(1) : cpu_to_be32(0); } -static void encode_op_map(struct xdr_stream *xdr, struct nfs4_op_map *op_map) +static void encode_op_map(struct xdr_stream *xdr, const struct nfs4_op_map *op_map) { unsigned int i; encode_uint32(xdr, NFS4_OP_MAP_NUM_WORDS); @@ -1757,7 +1758,7 @@ static void encode_op_map(struct xdr_stream *xdr, struct nfs4_op_map *op_map) } static void encode_exchange_id(struct xdr_stream *xdr, - struct nfs41_exchange_id_args *args, + const struct nfs41_exchange_id_args *args, struct compound_hdr *hdr) { __be32 *p; @@ -1809,7 +1810,7 @@ static void encode_exchange_id(struct xdr_stream *xdr, } static void encode_create_session(struct xdr_stream *xdr, - struct nfs41_create_session_args *args, + const struct nfs41_create_session_args *args, struct compound_hdr *hdr) { __be32 *p; @@ -1862,7 +1863,7 @@ static void encode_create_session(struct xdr_stream *xdr, } static void encode_destroy_session(struct xdr_stream *xdr, - struct nfs4_session *session, + const struct nfs4_session *session, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_DESTROY_SESSION, decode_destroy_session_maxsz, hdr); @@ -1878,7 +1879,7 @@ static void encode_destroy_clientid(struct xdr_stream *xdr, } static void encode_reclaim_complete(struct xdr_stream *xdr, - struct nfs41_reclaim_complete_args *args, + const struct nfs41_reclaim_complete_args *args, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_RECLAIM_COMPLETE, decode_reclaim_complete_maxsz, hdr); @@ -1974,7 +1975,7 @@ encode_layoutget(struct xdr_stream *xdr, static int encode_layoutcommit(struct xdr_stream *xdr, struct inode *inode, - struct nfs4_layoutcommit_args *args, + const struct nfs4_layoutcommit_args *args, struct compound_hdr *hdr) { __be32 *p; @@ -2044,7 +2045,7 @@ encode_secinfo_no_name(struct xdr_stream *xdr, } static void encode_test_stateid(struct xdr_stream *xdr, - struct nfs41_test_stateid_args *args, + const struct nfs41_test_stateid_args *args, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_TEST_STATEID, decode_test_stateid_maxsz, hdr); @@ -2053,7 +2054,7 @@ static void encode_test_stateid(struct xdr_stream *xdr, } static void encode_free_stateid(struct xdr_stream *xdr, - struct nfs41_free_stateid_args *args, + const struct nfs41_free_stateid_args *args, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_FREE_STATEID, decode_free_stateid_maxsz, hdr); @@ -2086,8 +2087,9 @@ static u32 nfs4_xdr_minorversion(const struct nfs4_sequence_args *args) * Encode an ACCESS request */ static void nfs4_xdr_enc_access(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_accessargs *args) + const void *data) { + const struct nfs4_accessargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2104,8 +2106,9 @@ static void nfs4_xdr_enc_access(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode LOOKUP request */ static void nfs4_xdr_enc_lookup(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_lookup_arg *args) + const void *data) { + const struct nfs4_lookup_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2124,8 +2127,9 @@ static void nfs4_xdr_enc_lookup(struct rpc_rqst *req, struct xdr_stream *xdr, */ static void nfs4_xdr_enc_lookup_root(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_lookup_root_arg *args) + const void *data) { + const struct nfs4_lookup_root_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2142,8 +2146,9 @@ static void nfs4_xdr_enc_lookup_root(struct rpc_rqst *req, * Encode REMOVE request */ static void nfs4_xdr_enc_remove(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_removeargs *args) + const void *data) { + const struct nfs_removeargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2159,8 +2164,9 @@ static void nfs4_xdr_enc_remove(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode RENAME request */ static void nfs4_xdr_enc_rename(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_renameargs *args) + const void *data) { + const struct nfs_renameargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2178,8 +2184,9 @@ static void nfs4_xdr_enc_rename(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode LINK request */ static void nfs4_xdr_enc_link(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_link_arg *args) + const void *data) { + const struct nfs4_link_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2199,8 +2206,9 @@ static void nfs4_xdr_enc_link(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode CREATE request */ static void nfs4_xdr_enc_create(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_create_arg *args) + const void *data) { + const struct nfs4_create_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2218,8 +2226,10 @@ static void nfs4_xdr_enc_create(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode SYMLINK request */ static void nfs4_xdr_enc_symlink(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_create_arg *args) + const void *data) { + const struct nfs4_create_arg *args = data; + nfs4_xdr_enc_create(req, xdr, args); } @@ -2227,8 +2237,9 @@ static void nfs4_xdr_enc_symlink(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode GETATTR request */ static void nfs4_xdr_enc_getattr(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_getattr_arg *args) + const void *data) { + const struct nfs4_getattr_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2244,8 +2255,9 @@ static void nfs4_xdr_enc_getattr(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode a CLOSE request */ static void nfs4_xdr_enc_close(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_closeargs *args) + const void *data) { + const struct nfs_closeargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2265,8 +2277,9 @@ static void nfs4_xdr_enc_close(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode an OPEN request */ static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_openargs *args) + const void *data) { + const struct nfs_openargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2287,8 +2300,9 @@ static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr, */ static void nfs4_xdr_enc_open_confirm(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_open_confirmargs *args) + const void *data) { + const struct nfs_open_confirmargs *args = data; struct compound_hdr hdr = { .nops = 0, }; @@ -2304,8 +2318,9 @@ static void nfs4_xdr_enc_open_confirm(struct rpc_rqst *req, */ static void nfs4_xdr_enc_open_noattr(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_openargs *args) + const void *data) { + const struct nfs_openargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2325,8 +2340,9 @@ static void nfs4_xdr_enc_open_noattr(struct rpc_rqst *req, */ static void nfs4_xdr_enc_open_downgrade(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_closeargs *args) + const void *data) { + const struct nfs_closeargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2344,8 +2360,9 @@ static void nfs4_xdr_enc_open_downgrade(struct rpc_rqst *req, * Encode a LOCK request */ static void nfs4_xdr_enc_lock(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_lock_args *args) + const void *data) { + const struct nfs_lock_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2361,8 +2378,9 @@ static void nfs4_xdr_enc_lock(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode a LOCKT request */ static void nfs4_xdr_enc_lockt(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_lockt_args *args) + const void *data) { + const struct nfs_lockt_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2378,8 +2396,9 @@ static void nfs4_xdr_enc_lockt(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode a LOCKU request */ static void nfs4_xdr_enc_locku(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_locku_args *args) + const void *data) { + const struct nfs_locku_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2393,8 +2412,9 @@ static void nfs4_xdr_enc_locku(struct rpc_rqst *req, struct xdr_stream *xdr, static void nfs4_xdr_enc_release_lockowner(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_release_lockowner_args *args) + const void *data) { + const struct nfs_release_lockowner_args *args = data; struct compound_hdr hdr = { .minorversion = 0, }; @@ -2408,8 +2428,9 @@ static void nfs4_xdr_enc_release_lockowner(struct rpc_rqst *req, * Encode a READLINK request */ static void nfs4_xdr_enc_readlink(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_readlink *args) + const void *data) { + const struct nfs4_readlink *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2428,8 +2449,9 @@ static void nfs4_xdr_enc_readlink(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode a READDIR request */ static void nfs4_xdr_enc_readdir(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_readdir_arg *args) + const void *data) { + const struct nfs4_readdir_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2451,8 +2473,9 @@ static void nfs4_xdr_enc_readdir(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode a READ request */ static void nfs4_xdr_enc_read(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_pgio_args *args) + const void *data) { + const struct nfs_pgio_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2472,8 +2495,9 @@ static void nfs4_xdr_enc_read(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode an SETATTR request */ static void nfs4_xdr_enc_setattr(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_setattrargs *args) + const void *data) { + const struct nfs_setattrargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2490,8 +2514,9 @@ static void nfs4_xdr_enc_setattr(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode a GETACL request */ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_getaclargs *args) + const void *data) { + const struct nfs_getaclargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2513,8 +2538,9 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode a WRITE request */ static void nfs4_xdr_enc_write(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_pgio_args *args) + const void *data) { + const struct nfs_pgio_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2533,8 +2559,9 @@ static void nfs4_xdr_enc_write(struct rpc_rqst *req, struct xdr_stream *xdr, * a COMMIT request */ static void nfs4_xdr_enc_commit(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_commitargs *args) + const void *data) { + const struct nfs_commitargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2550,8 +2577,9 @@ static void nfs4_xdr_enc_commit(struct rpc_rqst *req, struct xdr_stream *xdr, * FSINFO request */ static void nfs4_xdr_enc_fsinfo(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_fsinfo_arg *args) + const void *data) { + const struct nfs4_fsinfo_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2567,8 +2595,9 @@ static void nfs4_xdr_enc_fsinfo(struct rpc_rqst *req, struct xdr_stream *xdr, * a PATHCONF request */ static void nfs4_xdr_enc_pathconf(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_pathconf_arg *args) + const void *data) { + const struct nfs4_pathconf_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2585,8 +2614,9 @@ static void nfs4_xdr_enc_pathconf(struct rpc_rqst *req, struct xdr_stream *xdr, * a STATFS request */ static void nfs4_xdr_enc_statfs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_statfs_arg *args) + const void *data) { + const struct nfs4_statfs_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2604,8 +2634,9 @@ static void nfs4_xdr_enc_statfs(struct rpc_rqst *req, struct xdr_stream *xdr, */ static void nfs4_xdr_enc_server_caps(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_server_caps_arg *args) + const void *data) { + const struct nfs4_server_caps_arg *args = data; const u32 *bitmask = args->bitmask; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), @@ -2622,8 +2653,10 @@ static void nfs4_xdr_enc_server_caps(struct rpc_rqst *req, * a RENEW request */ static void nfs4_xdr_enc_renew(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_client *clp) + const void *data) + { + const struct nfs_client *clp = data; struct compound_hdr hdr = { .nops = 0, }; @@ -2638,8 +2671,9 @@ static void nfs4_xdr_enc_renew(struct rpc_rqst *req, struct xdr_stream *xdr, */ static void nfs4_xdr_enc_setclientid(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_setclientid *sc) + const void *data) { + const struct nfs4_setclientid *sc = data; struct compound_hdr hdr = { .nops = 0, }; @@ -2654,8 +2688,9 @@ static void nfs4_xdr_enc_setclientid(struct rpc_rqst *req, */ static void nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_setclientid_res *arg) + const void *data) { + const struct nfs4_setclientid_res *arg = data; struct compound_hdr hdr = { .nops = 0, }; @@ -2670,8 +2705,9 @@ static void nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req, */ static void nfs4_xdr_enc_delegreturn(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_delegreturnargs *args) + const void *data) { + const struct nfs4_delegreturnargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2692,8 +2728,9 @@ static void nfs4_xdr_enc_delegreturn(struct rpc_rqst *req, */ static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_fs_locations_arg *args) + const void *data) { + const struct nfs4_fs_locations_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2715,8 +2752,8 @@ static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req, } /* Set up reply kvec to capture returned fs_locations array. */ - xdr_inline_pages(&req->rq_rcv_buf, replen << 2, &args->page, - 0, PAGE_SIZE); + xdr_inline_pages(&req->rq_rcv_buf, replen << 2, + (struct page **)&args->page, 0, PAGE_SIZE); encode_nops(&hdr); } @@ -2725,8 +2762,9 @@ static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req, */ static void nfs4_xdr_enc_secinfo(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_secinfo_arg *args) + const void *data) { + const struct nfs4_secinfo_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2743,8 +2781,9 @@ static void nfs4_xdr_enc_secinfo(struct rpc_rqst *req, */ static void nfs4_xdr_enc_fsid_present(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_fsid_present_arg *args) + const void *data) { + const struct nfs4_fsid_present_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2764,8 +2803,9 @@ static void nfs4_xdr_enc_fsid_present(struct rpc_rqst *req, */ static void nfs4_xdr_enc_bind_conn_to_session(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs41_bind_conn_to_session_args *args) + const void *data) { + const struct nfs41_bind_conn_to_session_args *args = data; struct compound_hdr hdr = { .minorversion = args->client->cl_mvops->minor_version, }; @@ -2780,8 +2820,9 @@ static void nfs4_xdr_enc_bind_conn_to_session(struct rpc_rqst *req, */ static void nfs4_xdr_enc_exchange_id(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs41_exchange_id_args *args) + const void *data) { + const struct nfs41_exchange_id_args *args = data; struct compound_hdr hdr = { .minorversion = args->client->cl_mvops->minor_version, }; @@ -2796,8 +2837,9 @@ static void nfs4_xdr_enc_exchange_id(struct rpc_rqst *req, */ static void nfs4_xdr_enc_create_session(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs41_create_session_args *args) + const void *data) { + const struct nfs41_create_session_args *args = data; struct compound_hdr hdr = { .minorversion = args->client->cl_mvops->minor_version, }; @@ -2812,8 +2854,9 @@ static void nfs4_xdr_enc_create_session(struct rpc_rqst *req, */ static void nfs4_xdr_enc_destroy_session(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_session *session) + const void *data) { + const struct nfs4_session *session = data; struct compound_hdr hdr = { .minorversion = session->clp->cl_mvops->minor_version, }; @@ -2828,8 +2871,9 @@ static void nfs4_xdr_enc_destroy_session(struct rpc_rqst *req, */ static void nfs4_xdr_enc_destroy_clientid(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_client *clp) + const void *data) { + const struct nfs_client *clp = data; struct compound_hdr hdr = { .minorversion = clp->cl_mvops->minor_version, }; @@ -2843,8 +2887,9 @@ static void nfs4_xdr_enc_destroy_clientid(struct rpc_rqst *req, * a SEQUENCE request */ static void nfs4_xdr_enc_sequence(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_sequence_args *args) + const void *data) { + const struct nfs4_sequence_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(args), }; @@ -2859,8 +2904,9 @@ static void nfs4_xdr_enc_sequence(struct rpc_rqst *req, struct xdr_stream *xdr, */ static void nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_get_lease_time_args *args) + const void *data) { + const struct nfs4_get_lease_time_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->la_seq_args), }; @@ -2878,8 +2924,9 @@ static void nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req, */ static void nfs4_xdr_enc_reclaim_complete(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs41_reclaim_complete_args *args) + const void *data) { + const struct nfs41_reclaim_complete_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args) }; @@ -2895,8 +2942,9 @@ static void nfs4_xdr_enc_reclaim_complete(struct rpc_rqst *req, */ static void nfs4_xdr_enc_getdeviceinfo(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_getdeviceinfo_args *args) + const void *data) { + const struct nfs4_getdeviceinfo_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2919,8 +2967,9 @@ static void nfs4_xdr_enc_getdeviceinfo(struct rpc_rqst *req, */ static void nfs4_xdr_enc_layoutget(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_layoutget_args *args) + const void *data) { + const struct nfs4_layoutget_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2941,8 +2990,9 @@ static void nfs4_xdr_enc_layoutget(struct rpc_rqst *req, */ static void nfs4_xdr_enc_layoutcommit(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_layoutcommit_args *args) + const void *priv) { + const struct nfs4_layoutcommit_args *args = priv; struct nfs4_layoutcommit_data *data = container_of(args, struct nfs4_layoutcommit_data, args); struct compound_hdr hdr = { @@ -2962,8 +3012,9 @@ static void nfs4_xdr_enc_layoutcommit(struct rpc_rqst *req, */ static void nfs4_xdr_enc_layoutreturn(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_layoutreturn_args *args) + const void *data) { + const struct nfs4_layoutreturn_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2978,10 +3029,11 @@ static void nfs4_xdr_enc_layoutreturn(struct rpc_rqst *req, /* * Encode SECINFO_NO_NAME request */ -static int nfs4_xdr_enc_secinfo_no_name(struct rpc_rqst *req, +static void nfs4_xdr_enc_secinfo_no_name(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs41_secinfo_no_name_args *args) + const void *data) { + const struct nfs41_secinfo_no_name_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2991,7 +3043,6 @@ static int nfs4_xdr_enc_secinfo_no_name(struct rpc_rqst *req, encode_putrootfh(xdr, &hdr); encode_secinfo_no_name(xdr, args, &hdr); encode_nops(&hdr); - return 0; } /* @@ -2999,8 +3050,9 @@ static int nfs4_xdr_enc_secinfo_no_name(struct rpc_rqst *req, */ static void nfs4_xdr_enc_test_stateid(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs41_test_stateid_args *args) + const void *data) { + const struct nfs41_test_stateid_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -3016,8 +3068,9 @@ static void nfs4_xdr_enc_test_stateid(struct rpc_rqst *req, */ static void nfs4_xdr_enc_free_stateid(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs41_free_stateid_args *args) + const void *data) { + const struct nfs41_free_stateid_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -6364,8 +6417,9 @@ out: * Encode an SETACL request */ static void nfs4_xdr_enc_setacl(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_setaclargs *args) + const void *data) { + const struct nfs_setaclargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -7484,7 +7538,7 @@ nfs4_stat_to_errno(int stat) #define PROC(proc, argtype, restype) \ [NFSPROC4_CLNT_##proc] = { \ .p_proc = NFSPROC4_COMPOUND, \ - .p_encode = (kxdreproc_t)nfs4_xdr_##argtype, \ + .p_encode = nfs4_xdr_##argtype, \ .p_decode = (kxdrdproc_t)nfs4_xdr_##restype, \ .p_arglen = NFS4_##argtype##_sz, \ .p_replen = NFS4_##restype##_sz, \ -- cgit v1.2.3-59-g8ed1b From 843efb7d7d98364645a7f23eaa13a0649075815f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 14:47:53 +0200 Subject: nfsd: fix encoder callback prototypes Declare the p_encode callbacks with the proper prototype instead of casting to kxdreproc_t and losing all type safety. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton --- fs/nfsd/nfs4callback.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 0274db6e65d0..bede418237ee 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -468,7 +468,7 @@ static int decode_cb_sequence4res(struct xdr_stream *xdr, * NB: Without this zero space reservation, callbacks over krb5p fail */ static void nfs4_xdr_enc_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr, - void *__unused) + const void *__unused) { xdr_reserve_space(xdr, 0); } @@ -477,8 +477,9 @@ static void nfs4_xdr_enc_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr, * 20.2. Operation 4: CB_RECALL - Recall a Delegation */ static void nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfsd4_callback *cb) + const void *data) { + const struct nfsd4_callback *cb = data; const struct nfs4_delegation *dp = cb_to_delegation(cb); struct nfs4_cb_compound_hdr hdr = { .ident = cb->cb_clp->cl_cb_ident, @@ -585,8 +586,9 @@ static void encode_cb_layout4args(struct xdr_stream *xdr, static void nfs4_xdr_enc_cb_layout(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfsd4_callback *cb) + const void *data) { + const struct nfsd4_callback *cb = data; const struct nfs4_layout_stateid *ls = container_of(cb, struct nfs4_layout_stateid, ls_recall); struct nfs4_cb_compound_hdr hdr = { @@ -631,8 +633,9 @@ static void encode_stateowner(struct xdr_stream *xdr, struct nfs4_stateowner *so static void nfs4_xdr_enc_cb_notify_lock(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfsd4_callback *cb) + const void *data) { + const struct nfsd4_callback *cb = data; const struct nfsd4_blocked_lock *nbl = container_of(cb, struct nfsd4_blocked_lock, nbl_cb); struct nfs4_lockowner *lo = (struct nfs4_lockowner *)nbl->nbl_lock.fl_owner; @@ -682,7 +685,7 @@ static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp, #define PROC(proc, call, argtype, restype) \ [NFSPROC4_CLNT_##proc] = { \ .p_proc = NFSPROC4_CB_##call, \ - .p_encode = (kxdreproc_t)nfs4_xdr_enc_##argtype, \ + .p_encode = nfs4_xdr_enc_##argtype, \ .p_decode = (kxdrdproc_t)nfs4_xdr_dec_##restype, \ .p_arglen = NFS4_enc_##argtype##_sz, \ .p_replen = NFS4_dec_##restype##_sz, \ -- cgit v1.2.3-59-g8ed1b From df179381223f299b6c16ae134b5853aeee94b09e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 14:54:06 +0200 Subject: sunrpc/auth_gss: nfsd: fix encoder callback prototypes Declare the p_encode callbacks with the proper prototype instead of casting to kxdreproc_t and losing all type safety. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton Acked-by: Trond Myklebust --- net/sunrpc/auth_gss/gss_rpc_upcall.c | 2 +- net/sunrpc/auth_gss/gss_rpc_xdr.c | 11 ++++++----- net/sunrpc/auth_gss/gss_rpc_xdr.h | 2 +- 3 files changed, 8 insertions(+), 7 deletions(-) diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index f0c6a8c78a56..45ab924da726 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -55,7 +55,7 @@ enum { #define PROC(proc, name) \ [GSSX_##proc] = { \ .p_proc = GSSX_##proc, \ - .p_encode = (kxdreproc_t)gssx_enc_##name, \ + .p_encode = gssx_enc_##name, \ .p_decode = (kxdrdproc_t)gssx_dec_##name, \ .p_arglen = GSSX_ARG_##name##_sz, \ .p_replen = GSSX_RES_##name##_sz, \ diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c index 25d9a9cf7b66..5e54f4743092 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.c +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c @@ -44,7 +44,7 @@ static int gssx_dec_bool(struct xdr_stream *xdr, u32 *v) } static int gssx_enc_buffer(struct xdr_stream *xdr, - gssx_buffer *buf) + const gssx_buffer *buf) { __be32 *p; @@ -56,7 +56,7 @@ static int gssx_enc_buffer(struct xdr_stream *xdr, } static int gssx_enc_in_token(struct xdr_stream *xdr, - struct gssp_in_token *in) + const struct gssp_in_token *in) { __be32 *p; @@ -130,7 +130,7 @@ static int gssx_dec_option(struct xdr_stream *xdr, } static int dummy_enc_opt_array(struct xdr_stream *xdr, - struct gssx_option_array *oa) + const struct gssx_option_array *oa) { __be32 *p; @@ -348,7 +348,7 @@ static int gssx_dec_status(struct xdr_stream *xdr, } static int gssx_enc_call_ctx(struct xdr_stream *xdr, - struct gssx_call_ctx *ctx) + const struct gssx_call_ctx *ctx) { struct gssx_option opt; __be32 *p; @@ -733,8 +733,9 @@ static int gssx_enc_cb(struct xdr_stream *xdr, struct gssx_cb *cb) void gssx_enc_accept_sec_context(struct rpc_rqst *req, struct xdr_stream *xdr, - struct gssx_arg_accept_sec_context *arg) + const void *data) { + const struct gssx_arg_accept_sec_context *arg = data; int err; err = gssx_enc_call_ctx(xdr, &arg->call_ctx); diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.h b/net/sunrpc/auth_gss/gss_rpc_xdr.h index 9d88c6239f01..87cd719ca0ad 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.h +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.h @@ -179,7 +179,7 @@ struct gssx_res_accept_sec_context { #define gssx_dec_init_sec_context NULL void gssx_enc_accept_sec_context(struct rpc_rqst *req, struct xdr_stream *xdr, - struct gssx_arg_accept_sec_context *args); + const void *data); int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp, struct xdr_stream *xdr, struct gssx_res_accept_sec_context *res); -- cgit v1.2.3-59-g8ed1b From 993328e2b31fedc35276a4828039ad7af6d519cb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 14:58:11 +0200 Subject: sunrpc: properly type argument to kxdrdproc_t Pass struct rpc_request as the first argument instead of an untyped blob. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton Acked-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 3 ++- net/sunrpc/clnt.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 290f189de200..ed0fbf0d8d0f 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -226,7 +226,8 @@ struct xdr_stream { */ typedef void (*kxdreproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr, const void *obj); -typedef int (*kxdrdproc_t)(void *rqstp, struct xdr_stream *xdr, void *obj); +typedef int (*kxdrdproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + void *obj); extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p); extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 9fee20dc0c80..964d5c4a1b60 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2481,7 +2481,8 @@ static void rpcproc_encode_null(struct rpc_rqst *rqstp, struct xdr_stream *xdr, { } -static int rpcproc_decode_null(void *rqstp, struct xdr_stream *xdr, void *obj) +static int rpcproc_decode_null(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + void *obj) { return 0; } -- cgit v1.2.3-59-g8ed1b From 555966beff70ed612728521f0c12298a5127b7e5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 15:00:29 +0200 Subject: sunrpc: fix decoder callback prototypes Declare the p_decode callbacks with the proper prototype instead of casting to kxdrdproc_t and losing all type safety. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton --- net/sunrpc/rpcb_clnt.c | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-) diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index d0269a39afdf..f67b9e2897b4 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -861,8 +861,9 @@ static void rpcb_enc_mapping(struct rpc_rqst *req, struct xdr_stream *xdr, } static int rpcb_dec_getport(struct rpc_rqst *req, struct xdr_stream *xdr, - struct rpcbind_args *rpcb) + void *data) { + struct rpcbind_args *rpcb = data; unsigned long port; __be32 *p; @@ -883,8 +884,9 @@ static int rpcb_dec_getport(struct rpc_rqst *req, struct xdr_stream *xdr, } static int rpcb_dec_set(struct rpc_rqst *req, struct xdr_stream *xdr, - unsigned int *boolp) + void *data) { + unsigned int *boolp = data; __be32 *p; p = xdr_inline_decode(xdr, 4); @@ -939,8 +941,9 @@ static void rpcb_enc_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr, } static int rpcb_dec_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr, - struct rpcbind_args *rpcb) + void *data) { + struct rpcbind_args *rpcb = data; struct sockaddr_storage address; struct sockaddr *sap = (struct sockaddr *)&address; __be32 *p; @@ -995,7 +998,7 @@ static struct rpc_procinfo rpcb_procedures2[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, .p_encode = rpcb_enc_mapping, - .p_decode = (kxdrdproc_t)rpcb_dec_set, + .p_decode = rpcb_dec_set, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_SET, @@ -1005,7 +1008,7 @@ static struct rpc_procinfo rpcb_procedures2[] = { [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, .p_encode = rpcb_enc_mapping, - .p_decode = (kxdrdproc_t)rpcb_dec_set, + .p_decode = rpcb_dec_set, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_UNSET, @@ -1015,7 +1018,7 @@ static struct rpc_procinfo rpcb_procedures2[] = { [RPCBPROC_GETPORT] = { .p_proc = RPCBPROC_GETPORT, .p_encode = rpcb_enc_mapping, - .p_decode = (kxdrdproc_t)rpcb_dec_getport, + .p_decode = rpcb_dec_getport, .p_arglen = RPCB_mappingargs_sz, .p_replen = RPCB_getportres_sz, .p_statidx = RPCBPROC_GETPORT, @@ -1028,7 +1031,7 @@ static struct rpc_procinfo rpcb_procedures3[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, .p_encode = rpcb_enc_getaddr, - .p_decode = (kxdrdproc_t)rpcb_dec_set, + .p_decode = rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_SET, @@ -1038,7 +1041,7 @@ static struct rpc_procinfo rpcb_procedures3[] = { [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, .p_encode = rpcb_enc_getaddr, - .p_decode = (kxdrdproc_t)rpcb_dec_set, + .p_decode = rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_UNSET, @@ -1048,7 +1051,7 @@ static struct rpc_procinfo rpcb_procedures3[] = { [RPCBPROC_GETADDR] = { .p_proc = RPCBPROC_GETADDR, .p_encode = rpcb_enc_getaddr, - .p_decode = (kxdrdproc_t)rpcb_dec_getaddr, + .p_decode = rpcb_dec_getaddr, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_getaddrres_sz, .p_statidx = RPCBPROC_GETADDR, @@ -1061,7 +1064,7 @@ static struct rpc_procinfo rpcb_procedures4[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, .p_encode = rpcb_enc_getaddr, - .p_decode = (kxdrdproc_t)rpcb_dec_set, + .p_decode = rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_SET, @@ -1071,7 +1074,7 @@ static struct rpc_procinfo rpcb_procedures4[] = { [RPCBPROC_UNSET] = { .p_proc = RPCBPROC_UNSET, .p_encode = rpcb_enc_getaddr, - .p_decode = (kxdrdproc_t)rpcb_dec_set, + .p_decode = rpcb_dec_set, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_setres_sz, .p_statidx = RPCBPROC_UNSET, @@ -1081,7 +1084,7 @@ static struct rpc_procinfo rpcb_procedures4[] = { [RPCBPROC_GETADDR] = { .p_proc = RPCBPROC_GETADDR, .p_encode = rpcb_enc_getaddr, - .p_decode = (kxdrdproc_t)rpcb_dec_getaddr, + .p_decode = rpcb_dec_getaddr, .p_arglen = RPCB_getaddrargs_sz, .p_replen = RPCB_getaddrres_sz, .p_statidx = RPCBPROC_GETADDR, -- cgit v1.2.3-59-g8ed1b From c56c620b3e48feb5a6444707a05f9baeae1af9ef Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 15:03:02 +0200 Subject: sunrpc/auth_gss: fix decoder callback prototypes Declare the p_decode callbacks with the proper prototype instead of casting to kxdrdproc_t and losing all type safety. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton Acked-by: Trond Myklebust --- net/sunrpc/auth_gss/gss_rpc_upcall.c | 2 +- net/sunrpc/auth_gss/gss_rpc_xdr.c | 3 ++- net/sunrpc/auth_gss/gss_rpc_xdr.h | 2 +- 3 files changed, 4 insertions(+), 3 deletions(-) diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index 45ab924da726..a80b8e607478 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -56,7 +56,7 @@ enum { [GSSX_##proc] = { \ .p_proc = GSSX_##proc, \ .p_encode = gssx_enc_##name, \ - .p_decode = (kxdrdproc_t)gssx_dec_##name, \ + .p_decode = gssx_dec_##name, \ .p_arglen = GSSX_ARG_##name##_sz, \ .p_replen = GSSX_RES_##name##_sz, \ .p_statidx = GSSX_##proc, \ diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c index 5e54f4743092..c4778cae58ef 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.c +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c @@ -790,8 +790,9 @@ done: int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct gssx_res_accept_sec_context *res) + void *data) { + struct gssx_res_accept_sec_context *res = data; u32 value_follows; int err; struct page *scratch; diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.h b/net/sunrpc/auth_gss/gss_rpc_xdr.h index 87cd719ca0ad..146c31032917 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.h +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.h @@ -182,7 +182,7 @@ void gssx_enc_accept_sec_context(struct rpc_rqst *req, const void *data); int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct gssx_res_accept_sec_context *res); + void *data); #define gssx_enc_release_handle NULL #define gssx_dec_release_handle NULL #define gssx_enc_get_mic NULL -- cgit v1.2.3-59-g8ed1b From 5362a4ec830e0b5f4db59ad05fc32b10268abe91 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 15:04:45 +0200 Subject: nfsd: fix decoder callback prototypes Declare the p_decode callbacks with the proper prototype instead of casting to kxdrdproc_t and losing all type safety. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton --- fs/nfsd/nfs4callback.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index bede418237ee..a2bedbd05b2b 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -513,8 +513,9 @@ static int nfs4_xdr_dec_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr, */ static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfsd4_callback *cb) + void *data) { + struct nfsd4_callback *cb = data; struct nfs4_cb_compound_hdr hdr; int status; @@ -604,8 +605,9 @@ static void nfs4_xdr_enc_cb_layout(struct rpc_rqst *req, static int nfs4_xdr_dec_cb_layout(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfsd4_callback *cb) + void *data) { + struct nfsd4_callback *cb = data; struct nfs4_cb_compound_hdr hdr; int status; @@ -662,8 +664,9 @@ static void nfs4_xdr_enc_cb_notify_lock(struct rpc_rqst *req, static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfsd4_callback *cb) + void *data) { + struct nfsd4_callback *cb = data; struct nfs4_cb_compound_hdr hdr; int status; @@ -686,7 +689,7 @@ static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp, [NFSPROC4_CLNT_##proc] = { \ .p_proc = NFSPROC4_CB_##call, \ .p_encode = nfs4_xdr_enc_##argtype, \ - .p_decode = (kxdrdproc_t)nfs4_xdr_dec_##restype, \ + .p_decode = nfs4_xdr_dec_##restype, \ .p_arglen = NFS4_enc_##argtype##_sz, \ .p_replen = NFS4_dec_##restype##_sz, \ .p_statidx = NFSPROC4_CB_##call, \ -- cgit v1.2.3-59-g8ed1b From 04000564c1fc72770e4946cc3adb3ea9cd544bb2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 15:06:20 +0200 Subject: lockd: fix decoder callback prototypes Declare the p_decode callbacks with the proper prototype instead of casting to kxdrdproc_t and losing all type safety. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton Acked-by: Trond Myklebust --- fs/lockd/clnt4xdr.c | 8 +++++--- fs/lockd/clntxdr.c | 8 +++++--- fs/lockd/mon.c | 10 ++++++---- 3 files changed, 16 insertions(+), 10 deletions(-) diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c index 3cbad662120a..f0ab7a99dd23 100644 --- a/fs/lockd/clnt4xdr.c +++ b/fs/lockd/clnt4xdr.c @@ -533,8 +533,9 @@ out: static int nlm4_xdr_dec_testres(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nlm_res *result) + void *data) { + struct nlm_res *result = data; int error; error = decode_cookie(xdr, &result->cookie); @@ -553,8 +554,9 @@ out: */ static int nlm4_xdr_dec_res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nlm_res *result) + void *data) { + struct nlm_res *result = data; int error; error = decode_cookie(xdr, &result->cookie); @@ -575,7 +577,7 @@ out: [NLMPROC_##proc] = { \ .p_proc = NLMPROC_##proc, \ .p_encode = nlm4_xdr_enc_##argtype, \ - .p_decode = (kxdrdproc_t)nlm4_xdr_dec_##restype, \ + .p_decode = nlm4_xdr_dec_##restype, \ .p_arglen = NLM4_##argtype##_sz, \ .p_replen = NLM4_##restype##_sz, \ .p_statidx = NLMPROC_##proc, \ diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c index 825c0fde8c80..17e7f08b3a22 100644 --- a/fs/lockd/clntxdr.c +++ b/fs/lockd/clntxdr.c @@ -531,8 +531,9 @@ out: static int nlm_xdr_dec_testres(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nlm_res *result) + void *data) { + struct nlm_res *result = data; int error; error = decode_cookie(xdr, &result->cookie); @@ -551,8 +552,9 @@ out: */ static int nlm_xdr_dec_res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nlm_res *result) + void *data) { + struct nlm_res *result = data; int error; error = decode_cookie(xdr, &result->cookie); @@ -573,7 +575,7 @@ out: [NLMPROC_##proc] = { \ .p_proc = NLMPROC_##proc, \ .p_encode = nlm_xdr_enc_##argtype, \ - .p_decode = (kxdrdproc_t)nlm_xdr_dec_##restype, \ + .p_decode = nlm_xdr_dec_##restype, \ .p_arglen = NLM_##argtype##_sz, \ .p_replen = NLM_##restype##_sz, \ .p_statidx = NLMPROC_##proc, \ diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 8043fd4b8a5c..80630f0347e1 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -490,8 +490,9 @@ static void nsm_xdr_enc_unmon(struct rpc_rqst *req, struct xdr_stream *xdr, static int nsm_xdr_dec_stat_res(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nsm_res *resp) + void *data) { + struct nsm_res *resp = data; __be32 *p; p = xdr_inline_decode(xdr, 4 + 4); @@ -507,8 +508,9 @@ static int nsm_xdr_dec_stat_res(struct rpc_rqst *rqstp, static int nsm_xdr_dec_stat(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nsm_res *resp) + void *data) { + struct nsm_res *resp = data; __be32 *p; p = xdr_inline_decode(xdr, 4); @@ -533,7 +535,7 @@ static struct rpc_procinfo nsm_procedures[] = { [NSMPROC_MON] = { .p_proc = NSMPROC_MON, .p_encode = nsm_xdr_enc_mon, - .p_decode = (kxdrdproc_t)nsm_xdr_dec_stat_res, + .p_decode = nsm_xdr_dec_stat_res, .p_arglen = SM_mon_sz, .p_replen = SM_monres_sz, .p_statidx = NSMPROC_MON, @@ -542,7 +544,7 @@ static struct rpc_procinfo nsm_procedures[] = { [NSMPROC_UNMON] = { .p_proc = NSMPROC_UNMON, .p_encode = nsm_xdr_enc_unmon, - .p_decode = (kxdrdproc_t)nsm_xdr_dec_stat, + .p_decode = nsm_xdr_dec_stat, .p_arglen = SM_mon_id_sz, .p_replen = SM_unmonres_sz, .p_statidx = NSMPROC_UNMON, -- cgit v1.2.3-59-g8ed1b From fc016483eb0b2a19ef1e84ef8f8753c8ec9ac7f8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 15:09:02 +0200 Subject: nfs: fix decoder callback prototypes Declare the p_decode callbacks with the proper prototype instead of casting to kxdrdproc_t and losing all type safety. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton Acked-by: Trond Myklebust --- fs/nfs/mount_clnt.c | 10 ++-- fs/nfs/nfs2xdr.c | 15 +++--- fs/nfs/nfs3xdr.c | 55 +++++++++++++-------- fs/nfs/nfs42xdr.c | 18 ++++--- fs/nfs/nfs4xdr.c | 137 ++++++++++++++++++++++++++++++++++------------------ 5 files changed, 151 insertions(+), 84 deletions(-) diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index f435d640d552..806657d65074 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -357,8 +357,9 @@ static int decode_fhandle(struct xdr_stream *xdr, struct mountres *res) static int mnt_xdr_dec_mountres(struct rpc_rqst *req, struct xdr_stream *xdr, - struct mountres *res) + void *data) { + struct mountres *res = data; int status; status = decode_status(xdr, res); @@ -449,8 +450,9 @@ static int decode_auth_flavors(struct xdr_stream *xdr, struct mountres *res) static int mnt_xdr_dec_mountres3(struct rpc_rqst *req, struct xdr_stream *xdr, - struct mountres *res) + void *data) { + struct mountres *res = data; int status; status = decode_fhs_status(xdr, res); @@ -468,7 +470,7 @@ static struct rpc_procinfo mnt_procedures[] = { [MOUNTPROC_MNT] = { .p_proc = MOUNTPROC_MNT, .p_encode = mnt_xdr_enc_dirpath, - .p_decode = (kxdrdproc_t)mnt_xdr_dec_mountres, + .p_decode = mnt_xdr_dec_mountres, .p_arglen = MNT_enc_dirpath_sz, .p_replen = MNT_dec_mountres_sz, .p_statidx = MOUNTPROC_MNT, @@ -487,7 +489,7 @@ static struct rpc_procinfo mnt3_procedures[] = { [MOUNTPROC3_MNT] = { .p_proc = MOUNTPROC3_MNT, .p_encode = mnt_xdr_enc_dirpath, - .p_decode = (kxdrdproc_t)mnt_xdr_dec_mountres3, + .p_decode = mnt_xdr_dec_mountres3, .p_arglen = MNT_enc_dirpath_sz, .p_replen = MNT_dec_mountres3_sz, .p_statidx = MOUNTPROC3_MNT, diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index 8ecd58597228..a299648ea321 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -832,13 +832,13 @@ out_default: } static int nfs2_xdr_dec_attrstat(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_fattr *result) + void *result) { return decode_attrstat(xdr, result, NULL); } static int nfs2_xdr_dec_diropres(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_diropok *result) + void *result) { return decode_diropres(xdr, result); } @@ -883,8 +883,9 @@ out_default: * }; */ static int nfs2_xdr_dec_readres(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_pgio_res *result) + void *data) { + struct nfs_pgio_res *result = data; enum nfs_stat status; int error; @@ -905,8 +906,10 @@ out_default: } static int nfs2_xdr_dec_writeres(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_pgio_res *result) + void *data) { + struct nfs_pgio_res *result = data; + /* All NFSv2 writes are "file sync" writes */ result->verf->committed = NFS_FILE_SYNC; return decode_attrstat(xdr, result->fattr, &result->op_status); @@ -1057,7 +1060,7 @@ out_overflow: } static int nfs2_xdr_dec_statfsres(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs2_fsstat *result) + void *result) { enum nfs_stat status; int error; @@ -1142,7 +1145,7 @@ static int nfs_stat_to_errno(enum nfs_stat status) [NFSPROC_##proc] = { \ .p_proc = NFSPROC_##proc, \ .p_encode = nfs2_xdr_enc_##argtype, \ - .p_decode = (kxdrdproc_t)nfs2_xdr_dec_##restype, \ + .p_decode = nfs2_xdr_dec_##restype, \ .p_arglen = NFS_##argtype##_sz, \ .p_replen = NFS_##restype##_sz, \ .p_timer = timer, \ diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 773150678633..cc272eb8be3e 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -1419,7 +1419,7 @@ static void nfs3_xdr_enc_setacl3args(struct rpc_rqst *req, */ static int nfs3_xdr_dec_getattr3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_fattr *result) + void *result) { enum nfs_stat status; int error; @@ -1456,7 +1456,7 @@ out_default: */ static int nfs3_xdr_dec_setattr3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_fattr *result) + void *result) { enum nfs_stat status; int error; @@ -1497,8 +1497,9 @@ out_status: */ static int nfs3_xdr_dec_lookup3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs3_diropres *result) + void *data) { + struct nfs3_diropres *result = data; enum nfs_stat status; int error; @@ -1544,8 +1545,9 @@ out_default: */ static int nfs3_xdr_dec_access3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs3_accessres *result) + void *data) { + struct nfs3_accessres *result = data; enum nfs_stat status; int error; @@ -1585,7 +1587,7 @@ out_default: */ static int nfs3_xdr_dec_readlink3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_fattr *result) + void *result) { enum nfs_stat status; int error; @@ -1663,8 +1665,9 @@ out_overflow: } static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_pgio_res *result) + void *data) { + struct nfs_pgio_res *result = data; enum nfs_stat status; int error; @@ -1736,8 +1739,9 @@ out_eio: } static int nfs3_xdr_dec_write3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_pgio_res *result) + void *data) { + struct nfs_pgio_res *result = data; enum nfs_stat status; int error; @@ -1801,8 +1805,9 @@ out: static int nfs3_xdr_dec_create3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs3_diropres *result) + void *data) { + struct nfs3_diropres *result = data; enum nfs_stat status; int error; @@ -1841,8 +1846,9 @@ out_default: */ static int nfs3_xdr_dec_remove3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_removeres *result) + void *data) { + struct nfs_removeres *result = data; enum nfs_stat status; int error; @@ -1882,8 +1888,9 @@ out_status: */ static int nfs3_xdr_dec_rename3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_renameres *result) + void *data) { + struct nfs_renameres *result = data; enum nfs_stat status; int error; @@ -1925,8 +1932,9 @@ out_status: * }; */ static int nfs3_xdr_dec_link3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs3_linkres *result) + void *data) { + struct nfs3_linkres *result = data; enum nfs_stat status; int error; @@ -2109,8 +2117,9 @@ out: static int nfs3_xdr_dec_readdir3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs3_readdirres *result) + void *data) { + struct nfs3_readdirres *result = data; enum nfs_stat status; int error; @@ -2177,8 +2186,9 @@ out_overflow: static int nfs3_xdr_dec_fsstat3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_fsstat *result) + void *data) { + struct nfs_fsstat *result = data; enum nfs_stat status; int error; @@ -2253,8 +2263,9 @@ out_overflow: static int nfs3_xdr_dec_fsinfo3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_fsinfo *result) + void *data) { + struct nfs_fsinfo *result = data; enum nfs_stat status; int error; @@ -2316,8 +2327,9 @@ out_overflow: static int nfs3_xdr_dec_pathconf3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_pathconf *result) + void *data) { + struct nfs_pathconf *result = data; enum nfs_stat status; int error; @@ -2357,8 +2369,9 @@ out_status: */ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_commitres *result) + void *data) { + struct nfs_commitres *result = data; enum nfs_stat status; int error; @@ -2426,7 +2439,7 @@ out: static int nfs3_xdr_dec_getacl3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs3_getaclres *result) + void *result) { enum nfs_stat status; int error; @@ -2445,7 +2458,7 @@ out_default: static int nfs3_xdr_dec_setacl3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_fattr *result) + void *result) { enum nfs_stat status; int error; @@ -2533,7 +2546,7 @@ static int nfs3_stat_to_errno(enum nfs_stat status) [NFS3PROC_##proc] = { \ .p_proc = NFS3PROC_##proc, \ .p_encode = nfs3_xdr_enc_##argtype##3args, \ - .p_decode = (kxdrdproc_t)nfs3_xdr_dec_##restype##3res, \ + .p_decode = nfs3_xdr_dec_##restype##3res, \ .p_arglen = NFS3_##argtype##args_sz, \ .p_replen = NFS3_##restype##res_sz, \ .p_timer = timer, \ @@ -2576,7 +2589,7 @@ static struct rpc_procinfo nfs3_acl_procedures[] = { [ACLPROC3_GETACL] = { .p_proc = ACLPROC3_GETACL, .p_encode = nfs3_xdr_enc_getacl3args, - .p_decode = (kxdrdproc_t)nfs3_xdr_dec_getacl3res, + .p_decode = nfs3_xdr_dec_getacl3res, .p_arglen = ACL3_getaclargs_sz, .p_replen = ACL3_getaclres_sz, .p_timer = 1, @@ -2585,7 +2598,7 @@ static struct rpc_procinfo nfs3_acl_procedures[] = { [ACLPROC3_SETACL] = { .p_proc = ACLPROC3_SETACL, .p_encode = nfs3_xdr_enc_setacl3args, - .p_decode = (kxdrdproc_t)nfs3_xdr_dec_setacl3res, + .p_decode = nfs3_xdr_dec_setacl3res, .p_arglen = ACL3_setaclargs_sz, .p_replen = ACL3_setaclres_sz, .p_timer = 0, diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index 0a1bd60a1f8e..5ee1b0f0d904 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -454,8 +454,9 @@ static int decode_clone(struct xdr_stream *xdr) */ static int nfs4_xdr_dec_allocate(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs42_falloc_res *res) + void *data) { + struct nfs42_falloc_res *res = data; struct compound_hdr hdr; int status; @@ -481,8 +482,9 @@ out: */ static int nfs4_xdr_dec_copy(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs42_copy_res *res) + void *data) { + struct nfs42_copy_res *res = data; struct compound_hdr hdr; int status; @@ -514,8 +516,9 @@ out: */ static int nfs4_xdr_dec_deallocate(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs42_falloc_res *res) + void *data) { + struct nfs42_falloc_res *res = data; struct compound_hdr hdr; int status; @@ -541,8 +544,9 @@ out: */ static int nfs4_xdr_dec_seek(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs42_seek_res *res) + void *data) { + struct nfs42_seek_res *res = data; struct compound_hdr hdr; int status; @@ -565,8 +569,9 @@ out: */ static int nfs4_xdr_dec_layoutstats(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs42_layoutstat_res *res) + void *data) { + struct nfs42_layoutstat_res *res = data; struct compound_hdr hdr; int status, i; @@ -595,8 +600,9 @@ out: */ static int nfs4_xdr_dec_clone(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs42_clone_res *res) + void *data) { + struct nfs42_clone_res *res = data; struct compound_hdr hdr; int status; diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index c5036ef770f9..797f3ce75286 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -6154,8 +6154,9 @@ int decode_layoutreturn(struct xdr_stream *xdr, */ static int nfs4_xdr_dec_open_downgrade(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_closeres *res) + void *data) { + struct nfs_closeres *res = data; struct compound_hdr hdr; int status; @@ -6183,8 +6184,9 @@ out: * Decode ACCESS response */ static int nfs4_xdr_dec_access(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_accessres *res) + void *data) { + struct nfs4_accessres *res = data; struct compound_hdr hdr; int status; @@ -6209,8 +6211,9 @@ out: * Decode LOOKUP response */ static int nfs4_xdr_dec_lookup(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_lookup_res *res) + void *data) { + struct nfs4_lookup_res *res = data; struct compound_hdr hdr; int status; @@ -6239,8 +6242,9 @@ out: */ static int nfs4_xdr_dec_lookup_root(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_lookup_res *res) + void *data) { + struct nfs4_lookup_res *res = data; struct compound_hdr hdr; int status; @@ -6265,8 +6269,9 @@ out: * Decode REMOVE response */ static int nfs4_xdr_dec_remove(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_removeres *res) + void *data) { + struct nfs_removeres *res = data; struct compound_hdr hdr; int status; @@ -6288,8 +6293,9 @@ out: * Decode RENAME response */ static int nfs4_xdr_dec_rename(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_renameres *res) + void *data) { + struct nfs_renameres *res = data; struct compound_hdr hdr; int status; @@ -6317,8 +6323,9 @@ out: * Decode LINK response */ static int nfs4_xdr_dec_link(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_link_res *res) + void *data) { + struct nfs4_link_res *res = data; struct compound_hdr hdr; int status; @@ -6356,8 +6363,9 @@ out: * Decode CREATE response */ static int nfs4_xdr_dec_create(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_create_res *res) + void *data) { + struct nfs4_create_res *res = data; struct compound_hdr hdr; int status; @@ -6385,7 +6393,7 @@ out: * Decode SYMLINK response */ static int nfs4_xdr_dec_symlink(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_create_res *res) + void *res) { return nfs4_xdr_dec_create(rqstp, xdr, res); } @@ -6394,8 +6402,9 @@ static int nfs4_xdr_dec_symlink(struct rpc_rqst *rqstp, struct xdr_stream *xdr, * Decode GETATTR response */ static int nfs4_xdr_dec_getattr(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_getattr_res *res) + void *data) { + struct nfs4_getattr_res *res = data; struct compound_hdr hdr; int status; @@ -6436,8 +6445,9 @@ static void nfs4_xdr_enc_setacl(struct rpc_rqst *req, struct xdr_stream *xdr, */ static int nfs4_xdr_dec_setacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_setaclres *res) + void *data) { + struct nfs_setaclres *res = data; struct compound_hdr hdr; int status; @@ -6460,8 +6470,9 @@ out: */ static int nfs4_xdr_dec_getacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_getaclres *res) + void *data) { + struct nfs_getaclres *res = data; struct compound_hdr hdr; int status; @@ -6488,8 +6499,9 @@ out: * Decode CLOSE response */ static int nfs4_xdr_dec_close(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_closeres *res) + void *data) { + struct nfs_closeres *res = data; struct compound_hdr hdr; int status; @@ -6522,8 +6534,9 @@ out: * Decode OPEN response */ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_openres *res) + void *data) { + struct nfs_openres *res = data; struct compound_hdr hdr; int status; @@ -6554,8 +6567,9 @@ out: */ static int nfs4_xdr_dec_open_confirm(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_open_confirmres *res) + void *data) { + struct nfs_open_confirmres *res = data; struct compound_hdr hdr; int status; @@ -6575,8 +6589,9 @@ out: */ static int nfs4_xdr_dec_open_noattr(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_openres *res) + void *data) { + struct nfs_openres *res = data; struct compound_hdr hdr; int status; @@ -6604,8 +6619,9 @@ out: */ static int nfs4_xdr_dec_setattr(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_setattrres *res) + void *data) { + struct nfs_setattrres *res = data; struct compound_hdr hdr; int status; @@ -6630,8 +6646,9 @@ out: * Decode LOCK response */ static int nfs4_xdr_dec_lock(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_lock_res *res) + void *data) { + struct nfs_lock_res *res = data; struct compound_hdr hdr; int status; @@ -6653,8 +6670,9 @@ out: * Decode LOCKT response */ static int nfs4_xdr_dec_lockt(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_lockt_res *res) + void *data) { + struct nfs_lockt_res *res = data; struct compound_hdr hdr; int status; @@ -6676,8 +6694,9 @@ out: * Decode LOCKU response */ static int nfs4_xdr_dec_locku(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_locku_res *res) + void *data) { + struct nfs_locku_res *res = data; struct compound_hdr hdr; int status; @@ -6712,8 +6731,9 @@ static int nfs4_xdr_dec_release_lockowner(struct rpc_rqst *rqstp, */ static int nfs4_xdr_dec_readlink(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_readlink_res *res) + void *data) { + struct nfs4_readlink_res *res = data; struct compound_hdr hdr; int status; @@ -6735,8 +6755,9 @@ out: * Decode READDIR response */ static int nfs4_xdr_dec_readdir(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_readdir_res *res) + void *data) { + struct nfs4_readdir_res *res = data; struct compound_hdr hdr; int status; @@ -6758,8 +6779,9 @@ out: * Decode Read response */ static int nfs4_xdr_dec_read(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_pgio_res *res) + void *data) { + struct nfs_pgio_res *res = data; struct compound_hdr hdr; int status; @@ -6784,8 +6806,9 @@ out: * Decode WRITE response */ static int nfs4_xdr_dec_write(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_pgio_res *res) + void *data) { + struct nfs_pgio_res *res = data; struct compound_hdr hdr; int status; @@ -6814,8 +6837,9 @@ out: * Decode COMMIT response */ static int nfs4_xdr_dec_commit(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_commitres *res) + void *data) { + struct nfs_commitres *res = data; struct compound_hdr hdr; int status; @@ -6838,8 +6862,9 @@ out: * Decode FSINFO response */ static int nfs4_xdr_dec_fsinfo(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_fsinfo_res *res) + void *data) { + struct nfs4_fsinfo_res *res = data; struct compound_hdr hdr; int status; @@ -6857,8 +6882,9 @@ static int nfs4_xdr_dec_fsinfo(struct rpc_rqst *req, struct xdr_stream *xdr, * Decode PATHCONF response */ static int nfs4_xdr_dec_pathconf(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_pathconf_res *res) + void *data) { + struct nfs4_pathconf_res *res = data; struct compound_hdr hdr; int status; @@ -6876,8 +6902,9 @@ static int nfs4_xdr_dec_pathconf(struct rpc_rqst *req, struct xdr_stream *xdr, * Decode STATFS response */ static int nfs4_xdr_dec_statfs(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_statfs_res *res) + void *data) { + struct nfs4_statfs_res *res = data; struct compound_hdr hdr; int status; @@ -6896,8 +6923,9 @@ static int nfs4_xdr_dec_statfs(struct rpc_rqst *req, struct xdr_stream *xdr, */ static int nfs4_xdr_dec_server_caps(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_server_caps_res *res) + void *data) { + struct nfs4_server_caps_res *res = data; struct compound_hdr hdr; int status; @@ -6935,8 +6963,9 @@ static int nfs4_xdr_dec_renew(struct rpc_rqst *rqstp, struct xdr_stream *xdr, */ static int nfs4_xdr_dec_setclientid(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_setclientid_res *res) + void *data) { + struct nfs4_setclientid_res *res = data; struct compound_hdr hdr; int status; @@ -6950,7 +6979,8 @@ static int nfs4_xdr_dec_setclientid(struct rpc_rqst *req, * Decode SETCLIENTID_CONFIRM response */ static int nfs4_xdr_dec_setclientid_confirm(struct rpc_rqst *req, - struct xdr_stream *xdr) + struct xdr_stream *xdr, + void *data) { struct compound_hdr hdr; int status; @@ -6966,8 +6996,9 @@ static int nfs4_xdr_dec_setclientid_confirm(struct rpc_rqst *req, */ static int nfs4_xdr_dec_delegreturn(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_delegreturnres *res) + void *data) { + struct nfs4_delegreturnres *res = data; struct compound_hdr hdr; int status; @@ -7001,8 +7032,9 @@ out: */ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_fs_locations_res *res) + void *data) { + struct nfs4_fs_locations_res *res = data; struct compound_hdr hdr; int status; @@ -7044,8 +7076,9 @@ out: */ static int nfs4_xdr_dec_secinfo(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_secinfo_res *res) + void *data) { + struct nfs4_secinfo_res *res = data; struct compound_hdr hdr; int status; @@ -7068,8 +7101,9 @@ out: */ static int nfs4_xdr_dec_fsid_present(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_fsid_present_res *res) + void *data) { + struct nfs4_fsid_present_res *res = data; struct compound_hdr hdr; int status; @@ -7129,7 +7163,7 @@ static int nfs4_xdr_dec_exchange_id(struct rpc_rqst *rqstp, */ static int nfs4_xdr_dec_create_session(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs41_create_session_res *res) + void *res) { struct compound_hdr hdr; int status; @@ -7177,7 +7211,7 @@ static int nfs4_xdr_dec_destroy_clientid(struct rpc_rqst *rqstp, */ static int nfs4_xdr_dec_sequence(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_sequence_res *res) + void *res) { struct compound_hdr hdr; int status; @@ -7193,8 +7227,9 @@ static int nfs4_xdr_dec_sequence(struct rpc_rqst *rqstp, */ static int nfs4_xdr_dec_get_lease_time(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_get_lease_time_res *res) + void *data) { + struct nfs4_get_lease_time_res *res = data; struct compound_hdr hdr; int status; @@ -7213,8 +7248,9 @@ static int nfs4_xdr_dec_get_lease_time(struct rpc_rqst *rqstp, */ static int nfs4_xdr_dec_reclaim_complete(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs41_reclaim_complete_res *res) + void *data) { + struct nfs41_reclaim_complete_res *res = data; struct compound_hdr hdr; int status; @@ -7231,8 +7267,9 @@ static int nfs4_xdr_dec_reclaim_complete(struct rpc_rqst *rqstp, */ static int nfs4_xdr_dec_getdeviceinfo(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_getdeviceinfo_res *res) + void *data) { + struct nfs4_getdeviceinfo_res *res = data; struct compound_hdr hdr; int status; @@ -7252,8 +7289,9 @@ out: */ static int nfs4_xdr_dec_layoutget(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_layoutget_res *res) + void *data) { + struct nfs4_layoutget_res *res = data; struct compound_hdr hdr; int status; @@ -7276,8 +7314,9 @@ out: */ static int nfs4_xdr_dec_layoutreturn(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_layoutreturn_res *res) + void *data) { + struct nfs4_layoutreturn_res *res = data; struct compound_hdr hdr; int status; @@ -7300,8 +7339,9 @@ out: */ static int nfs4_xdr_dec_layoutcommit(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_layoutcommit_res *res) + void *data) { + struct nfs4_layoutcommit_res *res = data; struct compound_hdr hdr; int status; @@ -7327,8 +7367,9 @@ out: */ static int nfs4_xdr_dec_secinfo_no_name(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_secinfo_res *res) + void *data) { + struct nfs4_secinfo_res *res = data; struct compound_hdr hdr; int status; @@ -7351,8 +7392,9 @@ out: */ static int nfs4_xdr_dec_test_stateid(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs41_test_stateid_res *res) + void *data) { + struct nfs41_test_stateid_res *res = data; struct compound_hdr hdr; int status; @@ -7372,8 +7414,9 @@ out: */ static int nfs4_xdr_dec_free_stateid(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs41_free_stateid_res *res) + void *data) { + struct nfs41_free_stateid_res *res = data; struct compound_hdr hdr; int status; @@ -7539,7 +7582,7 @@ nfs4_stat_to_errno(int stat) [NFSPROC4_CLNT_##proc] = { \ .p_proc = NFSPROC4_COMPOUND, \ .p_encode = nfs4_xdr_##argtype, \ - .p_decode = (kxdrdproc_t)nfs4_xdr_##restype, \ + .p_decode = nfs4_xdr_##restype, \ .p_arglen = NFS4_##argtype##_sz, \ .p_replen = NFS4_##restype##_sz, \ .p_statidx = NFSPROC4_CLNT_##proc, \ -- cgit v1.2.3-59-g8ed1b From 947c6e431d1feb0bb62397cbb03d6e7292a35425 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 11 May 2017 09:22:18 +0200 Subject: nfs: don't cast callback decode/proc/encode routines Instead declare all functions with the proper methods signature. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton Acked-by: Trond Myklebust --- fs/nfs/callback.h | 27 ++++++---------- fs/nfs/callback_proc.c | 33 ++++++++++++------- fs/nfs/callback_xdr.c | 86 +++++++++++++++++++++++++++----------------------- 3 files changed, 77 insertions(+), 69 deletions(-) diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h index c701c308fac5..3dc54d7cb19c 100644 --- a/fs/nfs/callback.h +++ b/fs/nfs/callback.h @@ -114,8 +114,7 @@ struct cb_sequenceres { uint32_t csr_target_highestslotid; }; -extern __be32 nfs4_callback_sequence(struct cb_sequenceargs *args, - struct cb_sequenceres *res, +extern __be32 nfs4_callback_sequence(void *argp, void *resp, struct cb_process_state *cps); #define RCA4_TYPE_MASK_RDATA_DLG 0 @@ -134,15 +133,13 @@ struct cb_recallanyargs { uint32_t craa_type_mask; }; -extern __be32 nfs4_callback_recallany(struct cb_recallanyargs *args, - void *dummy, +extern __be32 nfs4_callback_recallany(void *argp, void *resp, struct cb_process_state *cps); struct cb_recallslotargs { uint32_t crsa_target_highest_slotid; }; -extern __be32 nfs4_callback_recallslot(struct cb_recallslotargs *args, - void *dummy, +extern __be32 nfs4_callback_recallslot(void *argp, void *resp, struct cb_process_state *cps); struct cb_layoutrecallargs { @@ -159,9 +156,8 @@ struct cb_layoutrecallargs { }; }; -extern __be32 nfs4_callback_layoutrecall( - struct cb_layoutrecallargs *args, - void *dummy, struct cb_process_state *cps); +extern __be32 nfs4_callback_layoutrecall(void *argp, void *resp, + struct cb_process_state *cps); struct cb_devicenotifyitem { uint32_t cbd_notify_type; @@ -175,9 +171,8 @@ struct cb_devicenotifyargs { struct cb_devicenotifyitem *devs; }; -extern __be32 nfs4_callback_devicenotify( - struct cb_devicenotifyargs *args, - void *dummy, struct cb_process_state *cps); +extern __be32 nfs4_callback_devicenotify(void *argp, void *resp, + struct cb_process_state *cps); struct cb_notify_lock_args { struct nfs_fh cbnl_fh; @@ -185,15 +180,13 @@ struct cb_notify_lock_args { bool cbnl_valid; }; -extern __be32 nfs4_callback_notify_lock(struct cb_notify_lock_args *args, - void *dummy, +extern __be32 nfs4_callback_notify_lock(void *argp, void *resp, struct cb_process_state *cps); #endif /* CONFIG_NFS_V4_1 */ extern int check_gss_callback_principal(struct nfs_client *, struct svc_rqst *); -extern __be32 nfs4_callback_getattr(struct cb_getattrargs *args, - struct cb_getattrres *res, +extern __be32 nfs4_callback_getattr(void *argp, void *resp, struct cb_process_state *cps); -extern __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy, +extern __be32 nfs4_callback_recall(void *argp, void *resp, struct cb_process_state *cps); #if IS_ENABLED(CONFIG_NFS_V4) extern int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt); diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index 52479f180ea1..5427cdf04c5a 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -19,10 +19,11 @@ #define NFSDBG_FACILITY NFSDBG_CALLBACK -__be32 nfs4_callback_getattr(struct cb_getattrargs *args, - struct cb_getattrres *res, +__be32 nfs4_callback_getattr(void *argp, void *resp, struct cb_process_state *cps) { + struct cb_getattrargs *args = argp; + struct cb_getattrres *res = resp; struct nfs_delegation *delegation; struct nfs_inode *nfsi; struct inode *inode; @@ -68,9 +69,10 @@ out: return res->status; } -__be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy, +__be32 nfs4_callback_recall(void *argp, void *resp, struct cb_process_state *cps) { + struct cb_recallargs *args = argp; struct inode *inode; __be32 res; @@ -324,9 +326,10 @@ static u32 do_callback_layoutrecall(struct nfs_client *clp, return initiate_bulk_draining(clp, args); } -__be32 nfs4_callback_layoutrecall(struct cb_layoutrecallargs *args, - void *dummy, struct cb_process_state *cps) +__be32 nfs4_callback_layoutrecall(void *argp, void *resp, + struct cb_process_state *cps) { + struct cb_layoutrecallargs *args = argp; u32 res = NFS4ERR_OP_NOT_IN_SESSION; if (cps->clp) @@ -345,9 +348,10 @@ static void pnfs_recall_all_layouts(struct nfs_client *clp) do_callback_layoutrecall(clp, &args); } -__be32 nfs4_callback_devicenotify(struct cb_devicenotifyargs *args, - void *dummy, struct cb_process_state *cps) +__be32 nfs4_callback_devicenotify(void *argp, void *resp, + struct cb_process_state *cps) { + struct cb_devicenotifyargs *args = argp; int i; __be32 res = 0; struct nfs_client *clp = cps->clp; @@ -469,10 +473,11 @@ out: return status; } -__be32 nfs4_callback_sequence(struct cb_sequenceargs *args, - struct cb_sequenceres *res, +__be32 nfs4_callback_sequence(void *argp, void *resp, struct cb_process_state *cps) { + struct cb_sequenceargs *args = argp; + struct cb_sequenceres *res = resp; struct nfs4_slot_table *tbl; struct nfs4_slot *slot; struct nfs_client *clp; @@ -571,9 +576,10 @@ validate_bitmap_values(unsigned long mask) return (mask & ~RCA4_TYPE_MASK_ALL) == 0; } -__be32 nfs4_callback_recallany(struct cb_recallanyargs *args, void *dummy, +__be32 nfs4_callback_recallany(void *argp, void *resp, struct cb_process_state *cps) { + struct cb_recallanyargs *args = argp; __be32 status; fmode_t flags = 0; @@ -606,9 +612,10 @@ out: } /* Reduce the fore channel's max_slots to the target value */ -__be32 nfs4_callback_recallslot(struct cb_recallslotargs *args, void *dummy, +__be32 nfs4_callback_recallslot(void *argp, void *resp, struct cb_process_state *cps) { + struct cb_recallslotargs *args = argp; struct nfs4_slot_table *fc_tbl; __be32 status; @@ -631,9 +638,11 @@ out: return status; } -__be32 nfs4_callback_notify_lock(struct cb_notify_lock_args *args, void *dummy, +__be32 nfs4_callback_notify_lock(void *argp, void *resp, struct cb_process_state *cps) { + struct cb_notify_lock_args *args = argp; + if (!cps->clp) /* set in cb_sequence */ return htonl(NFS4ERR_OP_NOT_IN_SESSION); diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index c14758e08d73..287c02202b25 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -43,16 +43,11 @@ /* Internal error code */ #define NFS4ERR_RESOURCE_HDR 11050 -typedef __be32 (*callback_process_op_t)(void *, void *, - struct cb_process_state *); -typedef __be32 (*callback_decode_arg_t)(struct svc_rqst *, struct xdr_stream *, void *); -typedef __be32 (*callback_encode_res_t)(struct svc_rqst *, struct xdr_stream *, void *); - - struct callback_op { - callback_process_op_t process_op; - callback_decode_arg_t decode_args; - callback_encode_res_t encode_res; + __be32 (*process_op)(void *, void *, struct cb_process_state *); + __be32 (*decode_args)(struct svc_rqst *, struct xdr_stream *, void *); + __be32 (*encode_res)(struct svc_rqst *, struct xdr_stream *, + const void *); long res_maxsize; }; @@ -184,8 +179,10 @@ static __be32 decode_op_hdr(struct xdr_stream *xdr, unsigned int *op) return 0; } -static __be32 decode_getattr_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, struct cb_getattrargs *args) +static __be32 decode_getattr_args(struct svc_rqst *rqstp, + struct xdr_stream *xdr, void *argp) { + struct cb_getattrargs *args = argp; __be32 status; status = decode_fh(xdr, &args->fh); @@ -194,8 +191,10 @@ static __be32 decode_getattr_args(struct svc_rqst *rqstp, struct xdr_stream *xdr return decode_bitmap(xdr, args->bitmap); } -static __be32 decode_recall_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, struct cb_recallargs *args) +static __be32 decode_recall_args(struct svc_rqst *rqstp, + struct xdr_stream *xdr, void *argp) { + struct cb_recallargs *args = argp; __be32 *p; __be32 status; @@ -217,9 +216,9 @@ static __be32 decode_layout_stateid(struct xdr_stream *xdr, nfs4_stateid *statei } static __be32 decode_layoutrecall_args(struct svc_rqst *rqstp, - struct xdr_stream *xdr, - struct cb_layoutrecallargs *args) + struct xdr_stream *xdr, void *argp) { + struct cb_layoutrecallargs *args = argp; __be32 *p; __be32 status = 0; uint32_t iomode; @@ -262,8 +261,9 @@ static __be32 decode_layoutrecall_args(struct svc_rqst *rqstp, static __be32 decode_devicenotify_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, - struct cb_devicenotifyargs *args) + void *argp) { + struct cb_devicenotifyargs *args = argp; __be32 *p; __be32 status = 0; u32 tmp; @@ -403,8 +403,9 @@ out: static __be32 decode_cb_sequence_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, - struct cb_sequenceargs *args) + void *argp) { + struct cb_sequenceargs *args = argp; __be32 *p; int i; __be32 status; @@ -450,8 +451,9 @@ out_free: static __be32 decode_recallany_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, - struct cb_recallanyargs *args) + void *argp) { + struct cb_recallanyargs *args = argp; uint32_t bitmap[2]; __be32 *p, status; @@ -469,8 +471,9 @@ static __be32 decode_recallany_args(struct svc_rqst *rqstp, static __be32 decode_recallslot_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, - struct cb_recallslotargs *args) + void *argp) { + struct cb_recallslotargs *args = argp; __be32 *p; p = read_buf(xdr, 4); @@ -510,8 +513,10 @@ static __be32 decode_lockowner(struct xdr_stream *xdr, struct cb_notify_lock_arg return 0; } -static __be32 decode_notify_lock_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, struct cb_notify_lock_args *args) +static __be32 decode_notify_lock_args(struct svc_rqst *rqstp, + struct xdr_stream *xdr, void *argp) { + struct cb_notify_lock_args *args = argp; __be32 status; status = decode_fh(xdr, &args->cbnl_fh); @@ -641,8 +646,10 @@ static __be32 encode_op_hdr(struct xdr_stream *xdr, uint32_t op, __be32 res) return 0; } -static __be32 encode_getattr_res(struct svc_rqst *rqstp, struct xdr_stream *xdr, const struct cb_getattrres *res) +static __be32 encode_getattr_res(struct svc_rqst *rqstp, struct xdr_stream *xdr, + const void *resp) { + const struct cb_getattrres *res = resp; __be32 *savep = NULL; __be32 status = res->status; @@ -683,8 +690,9 @@ static __be32 encode_sessionid(struct xdr_stream *xdr, static __be32 encode_cb_sequence_res(struct svc_rqst *rqstp, struct xdr_stream *xdr, - const struct cb_sequenceres *res) + const void *resp) { + const struct cb_sequenceres *res = resp; __be32 *p; __be32 status = res->csr_status; @@ -938,48 +946,46 @@ static struct callback_op callback_ops[] = { .res_maxsize = CB_OP_HDR_RES_MAXSZ, }, [OP_CB_GETATTR] = { - .process_op = (callback_process_op_t)nfs4_callback_getattr, - .decode_args = (callback_decode_arg_t)decode_getattr_args, - .encode_res = (callback_encode_res_t)encode_getattr_res, + .process_op = nfs4_callback_getattr, + .decode_args = decode_getattr_args, + .encode_res = encode_getattr_res, .res_maxsize = CB_OP_GETATTR_RES_MAXSZ, }, [OP_CB_RECALL] = { - .process_op = (callback_process_op_t)nfs4_callback_recall, - .decode_args = (callback_decode_arg_t)decode_recall_args, + .process_op = nfs4_callback_recall, + .decode_args = decode_recall_args, .res_maxsize = CB_OP_RECALL_RES_MAXSZ, }, #if defined(CONFIG_NFS_V4_1) [OP_CB_LAYOUTRECALL] = { - .process_op = (callback_process_op_t)nfs4_callback_layoutrecall, - .decode_args = - (callback_decode_arg_t)decode_layoutrecall_args, + .process_op = nfs4_callback_layoutrecall, + .decode_args = decode_layoutrecall_args, .res_maxsize = CB_OP_LAYOUTRECALL_RES_MAXSZ, }, [OP_CB_NOTIFY_DEVICEID] = { - .process_op = (callback_process_op_t)nfs4_callback_devicenotify, - .decode_args = - (callback_decode_arg_t)decode_devicenotify_args, + .process_op = nfs4_callback_devicenotify, + .decode_args = decode_devicenotify_args, .res_maxsize = CB_OP_DEVICENOTIFY_RES_MAXSZ, }, [OP_CB_SEQUENCE] = { - .process_op = (callback_process_op_t)nfs4_callback_sequence, - .decode_args = (callback_decode_arg_t)decode_cb_sequence_args, - .encode_res = (callback_encode_res_t)encode_cb_sequence_res, + .process_op = nfs4_callback_sequence, + .decode_args = decode_cb_sequence_args, + .encode_res = encode_cb_sequence_res, .res_maxsize = CB_OP_SEQUENCE_RES_MAXSZ, }, [OP_CB_RECALL_ANY] = { - .process_op = (callback_process_op_t)nfs4_callback_recallany, - .decode_args = (callback_decode_arg_t)decode_recallany_args, + .process_op = nfs4_callback_recallany, + .decode_args = decode_recallany_args, .res_maxsize = CB_OP_RECALLANY_RES_MAXSZ, }, [OP_CB_RECALL_SLOT] = { - .process_op = (callback_process_op_t)nfs4_callback_recallslot, - .decode_args = (callback_decode_arg_t)decode_recallslot_args, + .process_op = nfs4_callback_recallslot, + .decode_args = decode_recallslot_args, .res_maxsize = CB_OP_RECALLSLOT_RES_MAXSZ, }, [OP_CB_NOTIFY_LOCK] = { - .process_op = (callback_process_op_t)nfs4_callback_notify_lock, - .decode_args = (callback_decode_arg_t)decode_notify_lock_args, + .process_op = nfs4_callback_notify_lock, + .decode_args = decode_notify_lock_args, .res_maxsize = CB_OP_NOTIFY_LOCK_RES_MAXSZ, }, #endif /* CONFIG_NFS_V4_1 */ -- cgit v1.2.3-59-g8ed1b From e91ff8e3c4cf0e4227fddabec87683401fc657ac Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 23:32:18 +0200 Subject: lockd: fix some weird indentation Remove double indentation of a few struct rpc_version and struct rpc_program instance. Signed-off-by: Christoph Hellwig Acked-by: Trond Myklebust --- fs/lockd/clntxdr.c | 22 +++++++++++----------- fs/lockd/mon.c | 16 ++++++++-------- 2 files changed, 19 insertions(+), 19 deletions(-) diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c index 17e7f08b3a22..bd8a976785ae 100644 --- a/fs/lockd/clntxdr.c +++ b/fs/lockd/clntxdr.c @@ -601,15 +601,15 @@ static struct rpc_procinfo nlm_procedures[] = { }; static const struct rpc_version nlm_version1 = { - .number = 1, - .nrprocs = ARRAY_SIZE(nlm_procedures), - .procs = nlm_procedures, + .number = 1, + .nrprocs = ARRAY_SIZE(nlm_procedures), + .procs = nlm_procedures, }; static const struct rpc_version nlm_version3 = { - .number = 3, - .nrprocs = ARRAY_SIZE(nlm_procedures), - .procs = nlm_procedures, + .number = 3, + .nrprocs = ARRAY_SIZE(nlm_procedures), + .procs = nlm_procedures, }; static const struct rpc_version *nlm_versions[] = { @@ -623,9 +623,9 @@ static const struct rpc_version *nlm_versions[] = { static struct rpc_stat nlm_rpc_stats; const struct rpc_program nlm_program = { - .name = "lockd", - .number = NLM_PROGRAM, - .nrvers = ARRAY_SIZE(nlm_versions), - .version = nlm_versions, - .stats = &nlm_rpc_stats, + .name = "lockd", + .number = NLM_PROGRAM, + .nrvers = ARRAY_SIZE(nlm_versions), + .version = nlm_versions, + .stats = &nlm_rpc_stats, }; diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 80630f0347e1..62424e929a7f 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -553,9 +553,9 @@ static struct rpc_procinfo nsm_procedures[] = { }; static const struct rpc_version nsm_version1 = { - .number = 1, - .nrprocs = ARRAY_SIZE(nsm_procedures), - .procs = nsm_procedures + .number = 1, + .nrprocs = ARRAY_SIZE(nsm_procedures), + .procs = nsm_procedures }; static const struct rpc_version *nsm_version[] = { @@ -565,9 +565,9 @@ static const struct rpc_version *nsm_version[] = { static struct rpc_stat nsm_stats; static const struct rpc_program nsm_program = { - .name = "statd", - .number = NSM_PROGRAM, - .nrvers = ARRAY_SIZE(nsm_version), - .version = nsm_version, - .stats = &nsm_stats + .name = "statd", + .number = NSM_PROGRAM, + .nrvers = ARRAY_SIZE(nsm_version), + .version = nsm_version, + .stats = &nsm_stats }; -- cgit v1.2.3-59-g8ed1b From c551858a884b6d81def3d1528a9002ba97f5d4ad Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 23:27:10 +0200 Subject: sunrpc: move p_count out of struct rpc_procinfo p_count is the only writeable memeber of struct rpc_procinfo, which is a good candidate to be const-ified as it contains function pointers. This patch moves it into out out struct rpc_procinfo, and into a separate writable array that is pointed to by struct rpc_version and indexed by p_statidx. Signed-off-by: Christoph Hellwig --- fs/lockd/clnt4xdr.c | 2 ++ fs/lockd/clntxdr.c | 4 ++++ fs/lockd/mon.c | 4 +++- fs/nfs/mount_clnt.c | 5 ++++- fs/nfs/nfs2xdr.c | 4 +++- fs/nfs/nfs3xdr.c | 6 +++++- fs/nfs/nfs4xdr.c | 4 +++- fs/nfsd/nfs4callback.c | 4 +++- include/linux/sunrpc/clnt.h | 2 +- net/sunrpc/auth_gss/gss_rpc_upcall.c | 3 ++- net/sunrpc/clnt.c | 6 ++++-- net/sunrpc/rpcb_clnt.c | 12 +++++++++--- net/sunrpc/stats.c | 3 +-- 13 files changed, 44 insertions(+), 15 deletions(-) diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c index f0ab7a99dd23..7c255d1d7c64 100644 --- a/fs/lockd/clnt4xdr.c +++ b/fs/lockd/clnt4xdr.c @@ -602,8 +602,10 @@ static struct rpc_procinfo nlm4_procedures[] = { PROC(GRANTED_RES, res, norep), }; +static unsigned int nlm_version4_counts[ARRAY_SIZE(nlm4_procedures)]; const struct rpc_version nlm_version4 = { .number = 4, .nrprocs = ARRAY_SIZE(nlm4_procedures), .procs = nlm4_procedures, + .counts = nlm_version4_counts, }; diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c index bd8a976785ae..39500c5743a5 100644 --- a/fs/lockd/clntxdr.c +++ b/fs/lockd/clntxdr.c @@ -600,16 +600,20 @@ static struct rpc_procinfo nlm_procedures[] = { PROC(GRANTED_RES, res, norep), }; +static unsigned int nlm_version1_counts[ARRAY_SIZE(nlm_procedures)]; static const struct rpc_version nlm_version1 = { .number = 1, .nrprocs = ARRAY_SIZE(nlm_procedures), .procs = nlm_procedures, + .counts = nlm_version1_counts, }; +static unsigned int nlm_version3_counts[ARRAY_SIZE(nlm_procedures)]; static const struct rpc_version nlm_version3 = { .number = 3, .nrprocs = ARRAY_SIZE(nlm_procedures), .procs = nlm_procedures, + .counts = nlm_version3_counts, }; static const struct rpc_version *nlm_versions[] = { diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 62424e929a7f..fe4ec82764fe 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -552,10 +552,12 @@ static struct rpc_procinfo nsm_procedures[] = { }, }; +static unsigned int nsm_version1_counts[ARRAY_SIZE(nsm_procedures)]; static const struct rpc_version nsm_version1 = { .number = 1, .nrprocs = ARRAY_SIZE(nsm_procedures), - .procs = nsm_procedures + .procs = nsm_procedures, + .counts = nsm_version1_counts, }; static const struct rpc_version *nsm_version[] = { diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index 806657d65074..d25914aa8bf9 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -504,17 +504,20 @@ static struct rpc_procinfo mnt3_procedures[] = { }, }; - +static unsigned int mnt_counts[ARRAY_SIZE(mnt_procedures)]; static const struct rpc_version mnt_version1 = { .number = 1, .nrprocs = ARRAY_SIZE(mnt_procedures), .procs = mnt_procedures, + .counts = mnt_counts, }; +static unsigned int mnt3_counts[ARRAY_SIZE(mnt_procedures)]; static const struct rpc_version mnt_version3 = { .number = 3, .nrprocs = ARRAY_SIZE(mnt3_procedures), .procs = mnt3_procedures, + .counts = mnt3_counts, }; static const struct rpc_version *mnt_version[] = { diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index a299648ea321..16b4526299c1 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -1170,8 +1170,10 @@ struct rpc_procinfo nfs_procedures[] = { PROC(STATFS, fhandle, statfsres, 0), }; +static unsigned int nfs_version2_counts[ARRAY_SIZE(nfs_procedures)]; const struct rpc_version nfs_version2 = { .number = 2, .nrprocs = ARRAY_SIZE(nfs_procedures), - .procs = nfs_procedures + .procs = nfs_procedures, + .counts = nfs_version2_counts, }; diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index cc272eb8be3e..a017ec5c7a9d 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -2578,10 +2578,12 @@ struct rpc_procinfo nfs3_procedures[] = { PROC(COMMIT, commit, commit, 5), }; +static unsigned int nfs_version3_counts[ARRAY_SIZE(nfs3_procedures)]; const struct rpc_version nfs_version3 = { .number = 3, .nrprocs = ARRAY_SIZE(nfs3_procedures), - .procs = nfs3_procedures + .procs = nfs3_procedures, + .counts = nfs_version3_counts, }; #ifdef CONFIG_NFS_V3_ACL @@ -2606,10 +2608,12 @@ static struct rpc_procinfo nfs3_acl_procedures[] = { }, }; +static unsigned int nfs3_acl_counts[ARRAY_SIZE(nfs3_acl_procedures)]; const struct rpc_version nfsacl_version3 = { .number = 3, .nrprocs = sizeof(nfs3_acl_procedures)/ sizeof(nfs3_acl_procedures[0]), .procs = nfs3_acl_procedures, + .counts = nfs3_acl_counts, }; #endif /* CONFIG_NFS_V3_ACL */ diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 797f3ce75286..40cf5529e65f 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -7661,10 +7661,12 @@ struct rpc_procinfo nfs4_procedures[] = { #endif /* CONFIG_NFS_V4_2 */ }; +static unsigned int nfs_version4_counts[ARRAY_SIZE(nfs4_procedures)]; const struct rpc_version nfs_version4 = { .number = 4, .nrprocs = ARRAY_SIZE(nfs4_procedures), - .procs = nfs4_procedures + .procs = nfs4_procedures, + .counts = nfs_version4_counts, }; /* diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index a2bedbd05b2b..afa961fe073c 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -705,6 +705,7 @@ static struct rpc_procinfo nfs4_cb_procedures[] = { PROC(CB_NOTIFY_LOCK, COMPOUND, cb_notify_lock, cb_notify_lock), }; +static unsigned int nfs4_cb_counts[ARRAY_SIZE(nfs4_cb_procedures)]; static struct rpc_version nfs_cb_version4 = { /* * Note on the callback rpc program version number: despite language in rfc @@ -715,7 +716,8 @@ static struct rpc_version nfs_cb_version4 = { */ .number = 1, .nrprocs = ARRAY_SIZE(nfs4_cb_procedures), - .procs = nfs4_cb_procedures + .procs = nfs4_cb_procedures, + .counts = nfs4_cb_counts, }; static const struct rpc_version *nfs_cb_version[] = { diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 6095ecba0dde..c75ba37151fe 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -88,6 +88,7 @@ struct rpc_version { u32 number; /* version number */ unsigned int nrprocs; /* number of procs */ struct rpc_procinfo * procs; /* procedure array */ + unsigned int *counts; /* call counts */ }; /* @@ -99,7 +100,6 @@ struct rpc_procinfo { kxdrdproc_t p_decode; /* XDR decode function */ unsigned int p_arglen; /* argument hdr length (u32) */ unsigned int p_replen; /* reply hdr length (u32) */ - unsigned int p_count; /* call count */ unsigned int p_timer; /* Which RTT timer to use */ u32 p_statidx; /* Which procedure to account */ const char * p_name; /* name of procedure */ diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index a80b8e607478..f8729b647605 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -364,11 +364,12 @@ void gssp_free_upcall_data(struct gssp_upcall_data *data) /* * Initialization stuff */ - +static unsigned int gssp_version1_counts[ARRAY_SIZE(gssp_procedures)]; static const struct rpc_version gssp_version1 = { .number = GSSPROXY_VERS_1, .nrprocs = ARRAY_SIZE(gssp_procedures), .procs = gssp_procedures, + .counts = gssp_version1_counts, }; static const struct rpc_version *gssp_version[] = { diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 964d5c4a1b60..f2d1f971247b 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1517,14 +1517,16 @@ static void call_start(struct rpc_task *task) { struct rpc_clnt *clnt = task->tk_client; + int idx = task->tk_msg.rpc_proc->p_statidx; dprintk("RPC: %5u call_start %s%d proc %s (%s)\n", task->tk_pid, clnt->cl_program->name, clnt->cl_vers, rpc_proc_name(task), (RPC_IS_ASYNC(task) ? "async" : "sync")); - /* Increment call count */ - task->tk_msg.rpc_proc->p_count++; + /* Increment call count (version might not be valid for ping) */ + if (clnt->cl_program->version[clnt->cl_vers]) + clnt->cl_program->version[clnt->cl_vers]->counts[idx]++; clnt->cl_stats->rpccnt++; task->tk_action = call_reserve; } diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index f67b9e2897b4..9d47b9d3bbee 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -1117,22 +1117,28 @@ static const struct rpcb_info rpcb_next_version6[] = { }, }; +static unsigned int rpcb_version2_counts[ARRAY_SIZE(rpcb_procedures2)]; static const struct rpc_version rpcb_version2 = { .number = RPCBVERS_2, .nrprocs = ARRAY_SIZE(rpcb_procedures2), - .procs = rpcb_procedures2 + .procs = rpcb_procedures2, + .counts = rpcb_version2_counts, }; +static unsigned int rpcb_version3_counts[ARRAY_SIZE(rpcb_procedures3)]; static const struct rpc_version rpcb_version3 = { .number = RPCBVERS_3, .nrprocs = ARRAY_SIZE(rpcb_procedures3), - .procs = rpcb_procedures3 + .procs = rpcb_procedures3, + .counts = rpcb_version3_counts, }; +static unsigned int rpcb_version4_counts[ARRAY_SIZE(rpcb_procedures4)]; static const struct rpc_version rpcb_version4 = { .number = RPCBVERS_4, .nrprocs = ARRAY_SIZE(rpcb_procedures4), - .procs = rpcb_procedures4 + .procs = rpcb_procedures4, + .counts = rpcb_version4_counts, }; static const struct rpc_version *rpcb_version[] = { diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c index caeb01ad2b5a..91c84d18bf9a 100644 --- a/net/sunrpc/stats.c +++ b/net/sunrpc/stats.c @@ -55,8 +55,7 @@ static int rpc_proc_show(struct seq_file *seq, void *v) { seq_printf(seq, "proc%u %u", vers->number, vers->nrprocs); for (j = 0; j < vers->nrprocs; j++) - seq_printf(seq, " %u", - vers->procs[j].p_count); + seq_printf(seq, " %u", vers->counts[j]); seq_putc(seq, '\n'); } return 0; -- cgit v1.2.3-59-g8ed1b From 9ae7d8ff2948c4514b9a6bfef7f1a548ea6ab190 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 12 May 2017 15:51:24 +0200 Subject: nfs: use ARRAY_SIZE() in the nfsacl_version3 declaration Signed-off-by: Christoph Hellwig --- fs/nfs/nfs3xdr.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index a017ec5c7a9d..85ff1187e637 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -2611,8 +2611,7 @@ static struct rpc_procinfo nfs3_acl_procedures[] = { static unsigned int nfs3_acl_counts[ARRAY_SIZE(nfs3_acl_procedures)]; const struct rpc_version nfsacl_version3 = { .number = 3, - .nrprocs = sizeof(nfs3_acl_procedures)/ - sizeof(nfs3_acl_procedures[0]), + .nrprocs = ARRAY_SIZE(nfs3_acl_procedures), .procs = nfs3_acl_procedures, .counts = nfs3_acl_counts, }; -- cgit v1.2.3-59-g8ed1b From 511e936bf2b3e8be2a3160ace3d86be07962a7a8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 12 May 2017 15:36:49 +0200 Subject: sunrpc: mark all struct rpc_procinfo instances as const struct rpc_procinfo contains function pointers, and marking it as constant avoids it being able to be used as an attach vector for code injections. Signed-off-by: Christoph Hellwig Acked-by: Trond Myklebust --- fs/lockd/clnt4xdr.c | 2 +- fs/lockd/clntxdr.c | 2 +- fs/lockd/mon.c | 2 +- fs/nfs/internal.h | 6 +++--- fs/nfs/mount_clnt.c | 4 ++-- fs/nfs/nfs2xdr.c | 2 +- fs/nfs/nfs3xdr.c | 4 ++-- fs/nfs/nfs4_fs.h | 2 +- fs/nfs/nfs4xdr.c | 2 +- fs/nfsd/nfs4callback.c | 2 +- include/linux/sunrpc/clnt.h | 4 ++-- include/linux/sunrpc/sched.h | 2 +- net/sunrpc/auth_gss/gss_rpc_upcall.c | 2 +- net/sunrpc/clnt.c | 4 ++-- net/sunrpc/rpcb_clnt.c | 19 ++++++++++--------- net/sunrpc/stats.c | 2 +- 16 files changed, 31 insertions(+), 30 deletions(-) diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c index 7c255d1d7c64..c349fc0f9b80 100644 --- a/fs/lockd/clnt4xdr.c +++ b/fs/lockd/clnt4xdr.c @@ -584,7 +584,7 @@ out: .p_name = #proc, \ } -static struct rpc_procinfo nlm4_procedures[] = { +static const struct rpc_procinfo nlm4_procedures[] = { PROC(TEST, testargs, testres), PROC(LOCK, lockargs, res), PROC(CANCEL, cancargs, res), diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c index 39500c5743a5..3b4724a6c4ee 100644 --- a/fs/lockd/clntxdr.c +++ b/fs/lockd/clntxdr.c @@ -582,7 +582,7 @@ out: .p_name = #proc, \ } -static struct rpc_procinfo nlm_procedures[] = { +static const struct rpc_procinfo nlm_procedures[] = { PROC(TEST, testargs, testres), PROC(LOCK, lockargs, res), PROC(CANCEL, cancargs, res), diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index fe4ec82764fe..9d8166c39c54 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -531,7 +531,7 @@ static int nsm_xdr_dec_stat(struct rpc_rqst *rqstp, #define SM_monres_sz 2 #define SM_unmonres_sz 1 -static struct rpc_procinfo nsm_procedures[] = { +static const struct rpc_procinfo nsm_procedures[] = { [NSMPROC_MON] = { .p_proc = NSMPROC_MON, .p_encode = nsm_xdr_enc_mon, diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 3e24392f2caa..dc2a29a7d48b 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -270,12 +270,12 @@ static inline bool nfs_match_open_context(const struct nfs_open_context *ctx1, } /* nfs2xdr.c */ -extern struct rpc_procinfo nfs_procedures[]; +extern const struct rpc_procinfo nfs_procedures[]; extern int nfs2_decode_dirent(struct xdr_stream *, struct nfs_entry *, int); /* nfs3xdr.c */ -extern struct rpc_procinfo nfs3_procedures[]; +extern const struct rpc_procinfo nfs3_procedures[]; extern int nfs3_decode_dirent(struct xdr_stream *, struct nfs_entry *, int); @@ -292,7 +292,7 @@ extern const u32 nfs41_maxgetdevinfo_overhead; /* nfs4proc.c */ #if IS_ENABLED(CONFIG_NFS_V4) -extern struct rpc_procinfo nfs4_procedures[]; +extern const struct rpc_procinfo nfs4_procedures[]; #endif #ifdef CONFIG_NFS_V4_SECURITY_LABEL diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index d25914aa8bf9..3efe946672be 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -466,7 +466,7 @@ static int mnt_xdr_dec_mountres3(struct rpc_rqst *req, return decode_auth_flavors(xdr, res); } -static struct rpc_procinfo mnt_procedures[] = { +static const struct rpc_procinfo mnt_procedures[] = { [MOUNTPROC_MNT] = { .p_proc = MOUNTPROC_MNT, .p_encode = mnt_xdr_enc_dirpath, @@ -485,7 +485,7 @@ static struct rpc_procinfo mnt_procedures[] = { }, }; -static struct rpc_procinfo mnt3_procedures[] = { +static const struct rpc_procinfo mnt3_procedures[] = { [MOUNTPROC3_MNT] = { .p_proc = MOUNTPROC3_MNT, .p_encode = mnt_xdr_enc_dirpath, diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index 16b4526299c1..c8a7e98c1371 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -1152,7 +1152,7 @@ static int nfs_stat_to_errno(enum nfs_stat status) .p_statidx = NFSPROC_##proc, \ .p_name = #proc, \ } -struct rpc_procinfo nfs_procedures[] = { +const struct rpc_procinfo nfs_procedures[] = { PROC(GETATTR, fhandle, attrstat, 1), PROC(SETATTR, sattrargs, attrstat, 0), PROC(LOOKUP, diropargs, diropres, 2), diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 85ff1187e637..670eddb3ae36 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -2554,7 +2554,7 @@ static int nfs3_stat_to_errno(enum nfs_stat status) .p_name = #proc, \ } -struct rpc_procinfo nfs3_procedures[] = { +const struct rpc_procinfo nfs3_procedures[] = { PROC(GETATTR, getattr, getattr, 1), PROC(SETATTR, setattr, setattr, 0), PROC(LOOKUP, lookup, lookup, 2), @@ -2587,7 +2587,7 @@ const struct rpc_version nfs_version3 = { }; #ifdef CONFIG_NFS_V3_ACL -static struct rpc_procinfo nfs3_acl_procedures[] = { +static const struct rpc_procinfo nfs3_acl_procedures[] = { [ACLPROC3_GETACL] = { .p_proc = ACLPROC3_GETACL, .p_encode = nfs3_xdr_enc_getacl3args, diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index af285cc27ccf..9b0cf3872722 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -493,7 +493,7 @@ static inline void nfs4_unregister_sysctl(void) #endif /* nfs4xdr.c */ -extern struct rpc_procinfo nfs4_procedures[]; +extern const struct rpc_procinfo nfs4_procedures[]; struct nfs4_mount_data; diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 40cf5529e65f..0f1f290c97cd 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -7594,7 +7594,7 @@ nfs4_stat_to_errno(int stat) .p_name = #proc, \ } -struct rpc_procinfo nfs4_procedures[] = { +const struct rpc_procinfo nfs4_procedures[] = { PROC(READ, enc_read, dec_read), PROC(WRITE, enc_write, dec_write), PROC(COMMIT, enc_commit, dec_commit), diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index afa961fe073c..ac10f78c0fb3 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -696,7 +696,7 @@ static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp, .p_name = #proc, \ } -static struct rpc_procinfo nfs4_cb_procedures[] = { +static const struct rpc_procinfo nfs4_cb_procedures[] = { PROC(CB_NULL, NULL, cb_null, cb_null), PROC(CB_RECALL, COMPOUND, cb_recall, cb_recall), #ifdef CONFIG_NFSD_PNFS diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index c75ba37151fe..55ef67bea06b 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -39,7 +39,7 @@ struct rpc_clnt { struct list_head cl_tasks; /* List of tasks */ spinlock_t cl_lock; /* spinlock */ struct rpc_xprt __rcu * cl_xprt; /* transport */ - struct rpc_procinfo * cl_procinfo; /* procedure info */ + const struct rpc_procinfo *cl_procinfo; /* procedure info */ u32 cl_prog, /* RPC program number */ cl_vers, /* RPC version number */ cl_maxproc; /* max procedure number */ @@ -87,7 +87,7 @@ struct rpc_program { struct rpc_version { u32 number; /* version number */ unsigned int nrprocs; /* number of procs */ - struct rpc_procinfo * procs; /* procedure array */ + const struct rpc_procinfo *procs; /* procedure array */ unsigned int *counts; /* call counts */ }; diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 7ba040c797ec..ed60253abd0a 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -22,7 +22,7 @@ */ struct rpc_procinfo; struct rpc_message { - struct rpc_procinfo * rpc_proc; /* Procedure information */ + const struct rpc_procinfo *rpc_proc; /* Procedure information */ void * rpc_argp; /* Arguments */ void * rpc_resp; /* Result */ struct rpc_cred * rpc_cred; /* Credentials */ diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index f8729b647605..46b295e4f2b8 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -63,7 +63,7 @@ enum { .p_name = #proc, \ } -static struct rpc_procinfo gssp_procedures[] = { +static const struct rpc_procinfo gssp_procedures[] = { PROC(INDICATE_MECHS, indicate_mechs), PROC(GET_CALL_CONTEXT, get_call_context), PROC(IMPORT_AND_CANON_NAME, import_and_canon_name), diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index f2d1f971247b..2e49d1f892b7 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1674,7 +1674,7 @@ call_allocate(struct rpc_task *task) unsigned int slack = task->tk_rqstp->rq_cred->cr_auth->au_cslack; struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; - struct rpc_procinfo *proc = task->tk_msg.rpc_proc; + const struct rpc_procinfo *proc = task->tk_msg.rpc_proc; int status; dprint_status(task); @@ -2489,7 +2489,7 @@ static int rpcproc_decode_null(struct rpc_rqst *rqstp, struct xdr_stream *xdr, return 0; } -static struct rpc_procinfo rpcproc_null = { +static const struct rpc_procinfo rpcproc_null = { .p_encode = rpcproc_encode_null, .p_decode = rpcproc_decode_null, }; diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 9d47b9d3bbee..ea0676f199c8 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -128,13 +128,13 @@ struct rpcbind_args { int r_status; }; -static struct rpc_procinfo rpcb_procedures2[]; -static struct rpc_procinfo rpcb_procedures3[]; -static struct rpc_procinfo rpcb_procedures4[]; +static const struct rpc_procinfo rpcb_procedures2[]; +static const struct rpc_procinfo rpcb_procedures3[]; +static const struct rpc_procinfo rpcb_procedures4[]; struct rpcb_info { u32 rpc_vers; - struct rpc_procinfo * rpc_proc; + const struct rpc_procinfo *rpc_proc; }; static const struct rpcb_info rpcb_next_version[]; @@ -620,7 +620,8 @@ int rpcb_v4_register(struct net *net, const u32 program, const u32 version, return -EAFNOSUPPORT; } -static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, struct rpcbind_args *map, struct rpc_procinfo *proc) +static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, + struct rpcbind_args *map, const struct rpc_procinfo *proc) { struct rpc_message msg = { .rpc_proc = proc, @@ -671,7 +672,7 @@ static struct rpc_clnt *rpcb_find_transport_owner(struct rpc_clnt *clnt) void rpcb_getport_async(struct rpc_task *task) { struct rpc_clnt *clnt; - struct rpc_procinfo *proc; + const struct rpc_procinfo *proc; u32 bind_version; struct rpc_xprt *xprt; struct rpc_clnt *rpcb_clnt; @@ -994,7 +995,7 @@ out_fail: * since the Linux kernel RPC code requires only these. */ -static struct rpc_procinfo rpcb_procedures2[] = { +static const struct rpc_procinfo rpcb_procedures2[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, .p_encode = rpcb_enc_mapping, @@ -1027,7 +1028,7 @@ static struct rpc_procinfo rpcb_procedures2[] = { }, }; -static struct rpc_procinfo rpcb_procedures3[] = { +static const struct rpc_procinfo rpcb_procedures3[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, .p_encode = rpcb_enc_getaddr, @@ -1060,7 +1061,7 @@ static struct rpc_procinfo rpcb_procedures3[] = { }, }; -static struct rpc_procinfo rpcb_procedures4[] = { +static const struct rpc_procinfo rpcb_procedures4[] = { [RPCBPROC_SET] = { .p_proc = RPCBPROC_SET, .p_encode = rpcb_enc_getaddr, diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c index 91c84d18bf9a..8b6c35ae1d57 100644 --- a/net/sunrpc/stats.c +++ b/net/sunrpc/stats.c @@ -191,7 +191,7 @@ void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats) EXPORT_SYMBOL_GPL(rpc_count_iostats); static void _print_name(struct seq_file *seq, unsigned int op, - struct rpc_procinfo *procs) + const struct rpc_procinfo *procs) { if (procs[op].p_name) seq_printf(seq, "\t%12s: ", procs[op].p_name); -- cgit v1.2.3-59-g8ed1b From 39d43f75c6a1c214e035c143628cd8a985484bad Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 12 May 2017 15:58:06 +0200 Subject: nfsd4: const-ify nfs_cb_version4 Signed-off-by: Christoph Hellwig --- fs/nfsd/nfs4callback.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index ac10f78c0fb3..b45083c0f9ae 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -706,7 +706,7 @@ static const struct rpc_procinfo nfs4_cb_procedures[] = { }; static unsigned int nfs4_cb_counts[ARRAY_SIZE(nfs4_cb_procedures)]; -static struct rpc_version nfs_cb_version4 = { +static const struct rpc_version nfs_cb_version4 = { /* * Note on the callback rpc program version number: despite language in rfc * 5661 section 18.36.3 requiring servers to use 4 in this field, the -- cgit v1.2.3-59-g8ed1b From ec7e8caec9cf4f3cef5245220d0129380355d938 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 17:59:13 +0200 Subject: nfsd: use named initializers in PROC() Signed-off-by: Christoph Hellwig --- fs/nfsd/nfs2acl.c | 22 +++++++++++----------- fs/nfsd/nfs3acl.c | 22 +++++++++++----------- fs/nfsd/nfs4proc.c | 10 +++++----- 3 files changed, 27 insertions(+), 27 deletions(-) diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 838f90f3f890..12933d07204c 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -345,17 +345,17 @@ static int nfsaclsvc_release_access(struct svc_rqst *rqstp, __be32 *p, #define nfsd3_voidres nfsd3_voidargs struct nfsd3_voidargs { int dummy; }; -#define PROC(name, argt, rest, relt, cache, respsize) \ - { (svc_procfunc) nfsacld_proc_##name, \ - (kxdrproc_t) nfsaclsvc_decode_##argt##args, \ - (kxdrproc_t) nfsaclsvc_encode_##rest##res, \ - (kxdrproc_t) nfsaclsvc_release_##relt, \ - sizeof(struct nfsd3_##argt##args), \ - sizeof(struct nfsd3_##rest##res), \ - 0, \ - cache, \ - respsize, \ - } +#define PROC(name, argt, rest, relt, cache, respsize) \ +{ \ + .pc_func = (svc_procfunc) nfsacld_proc_##name, \ + .pc_decode = (kxdrproc_t) nfsaclsvc_decode_##argt##args, \ + .pc_encode = (kxdrproc_t) nfsaclsvc_encode_##rest##res, \ + .pc_release = (kxdrproc_t) nfsaclsvc_release_##relt, \ + .pc_argsize = sizeof(struct nfsd3_##argt##args), \ + .pc_ressize = sizeof(struct nfsd3_##rest##res), \ + .pc_cachetype = cache, \ + .pc_xdrressize = respsize, \ +} #define ST 1 /* status*/ #define AT 21 /* attributes */ diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index dcb5f79076c0..db988a229b3a 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -237,17 +237,17 @@ static int nfs3svc_release_getacl(struct svc_rqst *rqstp, __be32 *p, #define nfsd3_voidres nfsd3_voidargs struct nfsd3_voidargs { int dummy; }; -#define PROC(name, argt, rest, relt, cache, respsize) \ - { (svc_procfunc) nfsd3_proc_##name, \ - (kxdrproc_t) nfs3svc_decode_##argt##args, \ - (kxdrproc_t) nfs3svc_encode_##rest##res, \ - (kxdrproc_t) nfs3svc_release_##relt, \ - sizeof(struct nfsd3_##argt##args), \ - sizeof(struct nfsd3_##rest##res), \ - 0, \ - cache, \ - respsize, \ - } +#define PROC(name, argt, rest, relt, cache, respsize) \ +{ \ + .pc_func = (svc_procfunc) nfsd3_proc_##name, \ + .pc_decode = (kxdrproc_t) nfs3svc_decode_##argt##args, \ + .pc_encode = (kxdrproc_t) nfs3svc_encode_##rest##res, \ + .pc_release = (kxdrproc_t) nfs3svc_release_##relt, \ + .pc_argsize = sizeof(struct nfsd3_##argt##args), \ + .pc_ressize = sizeof(struct nfsd3_##rest##res), \ + .pc_cachetype = cache, \ + .pc_xdrressize = respsize, \ +} #define ST 1 /* status*/ #define AT 21 /* attributes */ diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index dadb3bf305b2..0833686ccdd3 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1673,10 +1673,10 @@ static void svcxdr_init_encode(struct svc_rqst *rqstp, * COMPOUND call. */ static __be32 -nfsd4_proc_compound(struct svc_rqst *rqstp, - struct nfsd4_compoundargs *args, - struct nfsd4_compoundres *resp) +nfsd4_proc_compound(struct svc_rqst *rqstp, void *arg, void *res) { + struct nfsd4_compoundargs *args = arg; + struct nfsd4_compoundres *resp = res; struct nfsd4_op *op; struct nfsd4_operation *opdesc; struct nfsd4_compound_state *cstate = &resp->cstate; @@ -2517,7 +2517,7 @@ struct nfsd4_voidargs { int dummy; }; static struct svc_procedure nfsd_procedures4[2] = { [NFSPROC4_NULL] = { - .pc_func = (svc_procfunc) nfsd4_proc_null, + .pc_func = nfsd4_proc_null, .pc_encode = (kxdrproc_t) nfs4svc_encode_voidres, .pc_argsize = sizeof(struct nfsd4_voidargs), .pc_ressize = sizeof(struct nfsd4_voidres), @@ -2525,7 +2525,7 @@ static struct svc_procedure nfsd_procedures4[2] = { .pc_xdrressize = 1, }, [NFSPROC4_COMPOUND] = { - .pc_func = (svc_procfunc) nfsd4_proc_compound, + .pc_func = nfsd4_proc_compound, .pc_decode = (kxdrproc_t) nfs4svc_decode_compoundargs, .pc_encode = (kxdrproc_t) nfs4svc_encode_compoundres, .pc_argsize = sizeof(struct nfsd4_compoundargs), -- cgit v1.2.3-59-g8ed1b From 36ba89c2a40fe138898b394106205a3853ef2a4d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 18:03:06 +0200 Subject: nfsd: remove the unused PROC() macro in nfs3proc.c Signed-off-by: Christoph Hellwig --- fs/nfsd/nfs3proc.c | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 045c9081eabe..24e035190770 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -647,18 +647,6 @@ nfsd3_proc_commit(struct svc_rqst * rqstp, struct nfsd3_commitargs *argp, #define nfsd3_voidres nfsd3_voidargs struct nfsd3_voidargs { int dummy; }; -#define PROC(name, argt, rest, relt, cache, respsize) \ - { (svc_procfunc) nfsd3_proc_##name, \ - (kxdrproc_t) nfs3svc_decode_##argt##args, \ - (kxdrproc_t) nfs3svc_encode_##rest##res, \ - (kxdrproc_t) nfs3svc_release_##relt, \ - sizeof(struct nfsd3_##argt##args), \ - sizeof(struct nfsd3_##rest##res), \ - 0, \ - cache, \ - respsize, \ - } - #define ST 1 /* status*/ #define FH 17 /* filehandle with length */ #define AT 21 /* attributes */ -- cgit v1.2.3-59-g8ed1b From 1c8a5409f3c4748ff42c1721d9578dd03091f378 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 17:35:49 +0200 Subject: sunrpc: properly type pc_func callbacks Drop the argp and resp arguments as they can trivially be derived from the rqstp argument. With that all functions now have the same prototype, and we can remove the unsafe casting to svc_procfunc as well as the svc_procfunc typedef itself. Signed-off-by: Christoph Hellwig --- fs/lockd/svc4proc.c | 118 ++++++++++++++++++++++------------- fs/lockd/svcproc.c | 118 ++++++++++++++++++++++------------- fs/nfs/callback_xdr.c | 7 ++- fs/nfsd/nfs2acl.c | 25 ++++---- fs/nfsd/nfs3acl.c | 15 ++--- fs/nfsd/nfs3proc.c | 151 ++++++++++++++++++++++++++------------------- fs/nfsd/nfs4proc.c | 9 +-- fs/nfsd/nfsproc.c | 104 +++++++++++++++++-------------- fs/nfsd/nfssvc.c | 2 +- include/linux/sunrpc/svc.h | 4 +- net/sunrpc/svc.c | 2 +- 11 files changed, 328 insertions(+), 227 deletions(-) diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 09c576f26c7b..3e4cba029d3d 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -62,7 +62,7 @@ no_locks: * NULL: Test for presence of service */ static __be32 -nlm4svc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) +nlm4svc_proc_null(struct svc_rqst *rqstp) { dprintk("lockd: NULL called\n"); return rpc_success; @@ -72,9 +72,9 @@ nlm4svc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) * TEST: Check for conflicting lock */ static __be32 -nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +__nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; __be32 rc = rpc_success; @@ -99,9 +99,15 @@ nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, } static __be32 -nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlm4svc_proc_test(struct svc_rqst *rqstp) { + return __nlm4svc_proc_test(rqstp, rqstp->rq_resp); +} + +static __be32 +__nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_res *resp) +{ + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; __be32 rc = rpc_success; @@ -141,9 +147,15 @@ nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, } static __be32 -nlm4svc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlm4svc_proc_lock(struct svc_rqst *rqstp) +{ + return __nlm4svc_proc_lock(rqstp, rqstp->rq_resp); +} + +static __be32 +__nlm4svc_proc_cancel(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; @@ -170,13 +182,19 @@ nlm4svc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp, return rpc_success; } +static __be32 +nlm4svc_proc_cancel(struct svc_rqst *rqstp) +{ + return __nlm4svc_proc_cancel(rqstp, rqstp->rq_resp); +} + /* * UNLOCK: release a lock */ static __be32 -nlm4svc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +__nlm4svc_proc_unlock(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; @@ -203,14 +221,21 @@ nlm4svc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp, return rpc_success; } +static __be32 +nlm4svc_proc_unlock(struct svc_rqst *rqstp) +{ + return __nlm4svc_proc_unlock(rqstp, rqstp->rq_resp); +} + /* * GRANTED: A server calls us to tell that a process' lock request * was granted */ static __be32 -nlm4svc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +__nlm4svc_proc_granted(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; + resp->cookie = argp->cookie; dprintk("lockd: GRANTED called\n"); @@ -219,6 +244,12 @@ nlm4svc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp, return rpc_success; } +static __be32 +nlm4svc_proc_granted(struct svc_rqst *rqstp) +{ + return __nlm4svc_proc_granted(rqstp, rqstp->rq_resp); +} + /* * This is the generic lockd callback for async RPC calls */ @@ -243,9 +274,10 @@ static const struct rpc_call_ops nlm4svc_callback_ops = { * because we send the callback before the reply proper. I hope this * doesn't break any clients. */ -static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args *argp, - __be32 (*func)(struct svc_rqst *, struct nlm_args *, struct nlm_res *)) +static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc, + __be32 (*func)(struct svc_rqst *, struct nlm_res *)) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_rqst *call; __be32 stat; @@ -261,7 +293,7 @@ static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args if (call == NULL) return rpc_system_err; - stat = func(rqstp, argp, &call->a_res); + stat = func(rqstp, &call->a_res); if (stat != 0) { nlmsvc_release_call(call); return stat; @@ -273,48 +305,44 @@ static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args return rpc_success; } -static __be32 nlm4svc_proc_test_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlm4svc_proc_test_msg(struct svc_rqst *rqstp) { dprintk("lockd: TEST_MSG called\n"); - return nlm4svc_callback(rqstp, NLMPROC_TEST_RES, argp, nlm4svc_proc_test); + return nlm4svc_callback(rqstp, NLMPROC_TEST_RES, __nlm4svc_proc_test); } -static __be32 nlm4svc_proc_lock_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlm4svc_proc_lock_msg(struct svc_rqst *rqstp) { dprintk("lockd: LOCK_MSG called\n"); - return nlm4svc_callback(rqstp, NLMPROC_LOCK_RES, argp, nlm4svc_proc_lock); + return nlm4svc_callback(rqstp, NLMPROC_LOCK_RES, __nlm4svc_proc_lock); } -static __be32 nlm4svc_proc_cancel_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlm4svc_proc_cancel_msg(struct svc_rqst *rqstp) { dprintk("lockd: CANCEL_MSG called\n"); - return nlm4svc_callback(rqstp, NLMPROC_CANCEL_RES, argp, nlm4svc_proc_cancel); + return nlm4svc_callback(rqstp, NLMPROC_CANCEL_RES, __nlm4svc_proc_cancel); } -static __be32 nlm4svc_proc_unlock_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlm4svc_proc_unlock_msg(struct svc_rqst *rqstp) { dprintk("lockd: UNLOCK_MSG called\n"); - return nlm4svc_callback(rqstp, NLMPROC_UNLOCK_RES, argp, nlm4svc_proc_unlock); + return nlm4svc_callback(rqstp, NLMPROC_UNLOCK_RES, __nlm4svc_proc_unlock); } -static __be32 nlm4svc_proc_granted_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlm4svc_proc_granted_msg(struct svc_rqst *rqstp) { dprintk("lockd: GRANTED_MSG called\n"); - return nlm4svc_callback(rqstp, NLMPROC_GRANTED_RES, argp, nlm4svc_proc_granted); + return nlm4svc_callback(rqstp, NLMPROC_GRANTED_RES, __nlm4svc_proc_granted); } /* * SHARE: create a DOS share or alter existing share. */ static __be32 -nlm4svc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlm4svc_proc_share(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; + struct nlm_res *resp = rqstp->rq_resp; struct nlm_host *host; struct nlm_file *file; @@ -345,9 +373,10 @@ nlm4svc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp, * UNSHARE: Release a DOS share. */ static __be32 -nlm4svc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlm4svc_proc_unshare(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; + struct nlm_res *resp = rqstp->rq_resp; struct nlm_host *host; struct nlm_file *file; @@ -378,22 +407,23 @@ nlm4svc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp, * NM_LOCK: Create an unmonitored lock */ static __be32 -nlm4svc_proc_nm_lock(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlm4svc_proc_nm_lock(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; + dprintk("lockd: NM_LOCK called\n"); argp->monitor = 0; /* just clean the monitor flag */ - return nlm4svc_proc_lock(rqstp, argp, resp); + return nlm4svc_proc_lock(rqstp); } /* * FREE_ALL: Release all locks and shares held by client */ static __be32 -nlm4svc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +nlm4svc_proc_free_all(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; /* Obtain client */ @@ -409,9 +439,10 @@ nlm4svc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp, * SM_NOTIFY: private callback from statd (not part of official NLM proto) */ static __be32 -nlm4svc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp, - void *resp) +nlm4svc_proc_sm_notify(struct svc_rqst *rqstp) { + struct nlm_reboot *argp = rqstp->rq_argp; + dprintk("lockd: SM_NOTIFY called\n"); if (!nlm_privileged_requester(rqstp)) { @@ -429,9 +460,10 @@ nlm4svc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp, * client sent a GRANTED_RES, let's remove the associated block */ static __be32 -nlm4svc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res *argp, - void *resp) +nlm4svc_proc_granted_res(struct svc_rqst *rqstp) { + struct nlm_res *argp = rqstp->rq_argp; + if (!nlmsvc_ops) return rpc_success; @@ -463,7 +495,7 @@ nlm4svc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res *argp, struct nlm_void { int dummy; }; #define PROC(name, xargt, xrest, argt, rest, respsize) \ - { .pc_func = (svc_procfunc) nlm4svc_proc_##name, \ + { .pc_func = nlm4svc_proc_##name, \ .pc_decode = (kxdrproc_t) nlm4svc_decode_##xargt, \ .pc_encode = (kxdrproc_t) nlm4svc_encode_##xrest, \ .pc_release = NULL, \ diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index fb26b9f522e7..3add50661fab 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -92,7 +92,7 @@ no_locks: * NULL: Test for presence of service */ static __be32 -nlmsvc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) +nlmsvc_proc_null(struct svc_rqst *rqstp) { dprintk("lockd: NULL called\n"); return rpc_success; @@ -102,9 +102,9 @@ nlmsvc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) * TEST: Check for conflicting lock */ static __be32 -nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +__nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; __be32 rc = rpc_success; @@ -130,9 +130,15 @@ nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, } static __be32 -nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlmsvc_proc_test(struct svc_rqst *rqstp) { + return __nlmsvc_proc_test(rqstp, rqstp->rq_resp); +} + +static __be32 +__nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_res *resp) +{ + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; __be32 rc = rpc_success; @@ -172,9 +178,15 @@ nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, } static __be32 -nlmsvc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlmsvc_proc_lock(struct svc_rqst *rqstp) +{ + return __nlmsvc_proc_lock(rqstp, rqstp->rq_resp); +} + +static __be32 +__nlmsvc_proc_cancel(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; struct net *net = SVC_NET(rqstp); @@ -202,13 +214,19 @@ nlmsvc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp, return rpc_success; } +static __be32 +nlmsvc_proc_cancel(struct svc_rqst *rqstp) +{ + return __nlmsvc_proc_cancel(rqstp, rqstp->rq_resp); +} + /* * UNLOCK: release a lock */ static __be32 -nlmsvc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +__nlmsvc_proc_unlock(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; struct net *net = SVC_NET(rqstp); @@ -236,14 +254,21 @@ nlmsvc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp, return rpc_success; } +static __be32 +nlmsvc_proc_unlock(struct svc_rqst *rqstp) +{ + return __nlmsvc_proc_unlock(rqstp, rqstp->rq_resp); +} + /* * GRANTED: A server calls us to tell that a process' lock request * was granted */ static __be32 -nlmsvc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +__nlmsvc_proc_granted(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; + resp->cookie = argp->cookie; dprintk("lockd: GRANTED called\n"); @@ -252,6 +277,12 @@ nlmsvc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp, return rpc_success; } +static __be32 +nlmsvc_proc_granted(struct svc_rqst *rqstp) +{ + return __nlmsvc_proc_granted(rqstp, rqstp->rq_resp); +} + /* * This is the generic lockd callback for async RPC calls */ @@ -284,9 +315,10 @@ static const struct rpc_call_ops nlmsvc_callback_ops = { * because we send the callback before the reply proper. I hope this * doesn't break any clients. */ -static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args *argp, - __be32 (*func)(struct svc_rqst *, struct nlm_args *, struct nlm_res *)) +static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc, + __be32 (*func)(struct svc_rqst *, struct nlm_res *)) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_rqst *call; __be32 stat; @@ -302,7 +334,7 @@ static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args if (call == NULL) return rpc_system_err; - stat = func(rqstp, argp, &call->a_res); + stat = func(rqstp, &call->a_res); if (stat != 0) { nlmsvc_release_call(call); return stat; @@ -314,50 +346,46 @@ static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args return rpc_success; } -static __be32 nlmsvc_proc_test_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlmsvc_proc_test_msg(struct svc_rqst *rqstp) { dprintk("lockd: TEST_MSG called\n"); - return nlmsvc_callback(rqstp, NLMPROC_TEST_RES, argp, nlmsvc_proc_test); + return nlmsvc_callback(rqstp, NLMPROC_TEST_RES, __nlmsvc_proc_test); } -static __be32 nlmsvc_proc_lock_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlmsvc_proc_lock_msg(struct svc_rqst *rqstp) { dprintk("lockd: LOCK_MSG called\n"); - return nlmsvc_callback(rqstp, NLMPROC_LOCK_RES, argp, nlmsvc_proc_lock); + return nlmsvc_callback(rqstp, NLMPROC_LOCK_RES, __nlmsvc_proc_lock); } -static __be32 nlmsvc_proc_cancel_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlmsvc_proc_cancel_msg(struct svc_rqst *rqstp) { dprintk("lockd: CANCEL_MSG called\n"); - return nlmsvc_callback(rqstp, NLMPROC_CANCEL_RES, argp, nlmsvc_proc_cancel); + return nlmsvc_callback(rqstp, NLMPROC_CANCEL_RES, __nlmsvc_proc_cancel); } static __be32 -nlmsvc_proc_unlock_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +nlmsvc_proc_unlock_msg(struct svc_rqst *rqstp) { dprintk("lockd: UNLOCK_MSG called\n"); - return nlmsvc_callback(rqstp, NLMPROC_UNLOCK_RES, argp, nlmsvc_proc_unlock); + return nlmsvc_callback(rqstp, NLMPROC_UNLOCK_RES, __nlmsvc_proc_unlock); } static __be32 -nlmsvc_proc_granted_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +nlmsvc_proc_granted_msg(struct svc_rqst *rqstp) { dprintk("lockd: GRANTED_MSG called\n"); - return nlmsvc_callback(rqstp, NLMPROC_GRANTED_RES, argp, nlmsvc_proc_granted); + return nlmsvc_callback(rqstp, NLMPROC_GRANTED_RES, __nlmsvc_proc_granted); } /* * SHARE: create a DOS share or alter existing share. */ static __be32 -nlmsvc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlmsvc_proc_share(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; + struct nlm_res *resp = rqstp->rq_resp; struct nlm_host *host; struct nlm_file *file; @@ -388,9 +416,10 @@ nlmsvc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp, * UNSHARE: Release a DOS share. */ static __be32 -nlmsvc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlmsvc_proc_unshare(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; + struct nlm_res *resp = rqstp->rq_resp; struct nlm_host *host; struct nlm_file *file; @@ -421,22 +450,23 @@ nlmsvc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp, * NM_LOCK: Create an unmonitored lock */ static __be32 -nlmsvc_proc_nm_lock(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlmsvc_proc_nm_lock(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; + dprintk("lockd: NM_LOCK called\n"); argp->monitor = 0; /* just clean the monitor flag */ - return nlmsvc_proc_lock(rqstp, argp, resp); + return nlmsvc_proc_lock(rqstp); } /* * FREE_ALL: Release all locks and shares held by client */ static __be32 -nlmsvc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +nlmsvc_proc_free_all(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; /* Obtain client */ @@ -452,9 +482,10 @@ nlmsvc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp, * SM_NOTIFY: private callback from statd (not part of official NLM proto) */ static __be32 -nlmsvc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp, - void *resp) +nlmsvc_proc_sm_notify(struct svc_rqst *rqstp) { + struct nlm_reboot *argp = rqstp->rq_argp; + dprintk("lockd: SM_NOTIFY called\n"); if (!nlm_privileged_requester(rqstp)) { @@ -472,9 +503,10 @@ nlmsvc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp, * client sent a GRANTED_RES, let's remove the associated block */ static __be32 -nlmsvc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res *argp, - void *resp) +nlmsvc_proc_granted_res(struct svc_rqst *rqstp) { + struct nlm_res *argp = rqstp->rq_argp; + if (!nlmsvc_ops) return rpc_success; @@ -505,7 +537,7 @@ nlmsvc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res *argp, struct nlm_void { int dummy; }; #define PROC(name, xargt, xrest, argt, rest, respsize) \ - { .pc_func = (svc_procfunc) nlmsvc_proc_##name, \ + { .pc_func = nlmsvc_proc_##name, \ .pc_decode = (kxdrproc_t) nlmsvc_decode_##xargt, \ .pc_encode = (kxdrproc_t) nlmsvc_encode_##xrest, \ .pc_release = NULL, \ diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 287c02202b25..5a14bdaa5986 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -53,7 +53,7 @@ struct callback_op { static struct callback_op callback_ops[]; -static __be32 nfs4_callback_null(struct svc_rqst *rqstp, void *argp, void *resp) +static __be32 nfs4_callback_null(struct svc_rqst *rqstp) { return htonl(NFS4_OK); } @@ -880,7 +880,7 @@ encode_hdr: /* * Decode, process and encode a COMPOUND */ -static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *resp) +static __be32 nfs4_callback_compound(struct svc_rqst *rqstp) { struct cb_compound_hdr_arg hdr_arg = { 0 }; struct cb_compound_hdr_res hdr_res = { NULL }; @@ -916,7 +916,8 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r while (status == 0 && nops != hdr_arg.nops) { status = process_op(nops, rqstp, &xdr_in, - argp, &xdr_out, resp, &cps); + rqstp->rq_argp, &xdr_out, rqstp->rq_resp, + &cps); nops++; } diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 12933d07204c..4b7f84fa1fa5 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -19,7 +19,7 @@ * NULL call. */ static __be32 -nfsacld_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) +nfsacld_proc_null(struct svc_rqst *rqstp) { return nfs_ok; } @@ -27,9 +27,10 @@ nfsacld_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) /* * Get the Access and/or Default ACL of a file. */ -static __be32 nfsacld_proc_getacl(struct svc_rqst * rqstp, - struct nfsd3_getaclargs *argp, struct nfsd3_getaclres *resp) +static __be32 nfsacld_proc_getacl(struct svc_rqst *rqstp) { + struct nfsd3_getaclargs *argp = rqstp->rq_argp; + struct nfsd3_getaclres *resp = rqstp->rq_resp; struct posix_acl *acl; struct inode *inode; svc_fh *fh; @@ -87,10 +88,10 @@ fail: /* * Set the Access and/or Default ACL of a file. */ -static __be32 nfsacld_proc_setacl(struct svc_rqst * rqstp, - struct nfsd3_setaclargs *argp, - struct nfsd_attrstat *resp) +static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp) { + struct nfsd3_setaclargs *argp = rqstp->rq_argp; + struct nfsd_attrstat *resp = rqstp->rq_resp; struct inode *inode; svc_fh *fh; __be32 nfserr = 0; @@ -141,9 +142,10 @@ out_errno: /* * Check file attributes */ -static __be32 nfsacld_proc_getattr(struct svc_rqst * rqstp, - struct nfsd_fhandle *argp, struct nfsd_attrstat *resp) +static __be32 nfsacld_proc_getattr(struct svc_rqst *rqstp) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + struct nfsd_attrstat *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: GETATTR %s\n", SVCFH_fmt(&argp->fh)); @@ -158,9 +160,10 @@ static __be32 nfsacld_proc_getattr(struct svc_rqst * rqstp, /* * Check file access */ -static __be32 nfsacld_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessargs *argp, - struct nfsd3_accessres *resp) +static __be32 nfsacld_proc_access(struct svc_rqst *rqstp) { + struct nfsd3_accessargs *argp = rqstp->rq_argp; + struct nfsd3_accessres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: ACCESS(2acl) %s 0x%x\n", @@ -347,7 +350,7 @@ struct nfsd3_voidargs { int dummy; }; #define PROC(name, argt, rest, relt, cache, respsize) \ { \ - .pc_func = (svc_procfunc) nfsacld_proc_##name, \ + .pc_func = nfsacld_proc_##name, \ .pc_decode = (kxdrproc_t) nfsaclsvc_decode_##argt##args, \ .pc_encode = (kxdrproc_t) nfsaclsvc_encode_##rest##res, \ .pc_release = (kxdrproc_t) nfsaclsvc_release_##relt, \ diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index db988a229b3a..5e42004035e0 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -18,7 +18,7 @@ * NULL call. */ static __be32 -nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) +nfsd3_proc_null(struct svc_rqst *rqstp) { return nfs_ok; } @@ -26,9 +26,10 @@ nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) /* * Get the Access and/or Default ACL of a file. */ -static __be32 nfsd3_proc_getacl(struct svc_rqst * rqstp, - struct nfsd3_getaclargs *argp, struct nfsd3_getaclres *resp) +static __be32 nfsd3_proc_getacl(struct svc_rqst *rqstp) { + struct nfsd3_getaclargs *argp = rqstp->rq_argp; + struct nfsd3_getaclres *resp = rqstp->rq_resp; struct posix_acl *acl; struct inode *inode; svc_fh *fh; @@ -80,10 +81,10 @@ fail: /* * Set the Access and/or Default ACL of a file. */ -static __be32 nfsd3_proc_setacl(struct svc_rqst * rqstp, - struct nfsd3_setaclargs *argp, - struct nfsd3_attrstat *resp) +static __be32 nfsd3_proc_setacl(struct svc_rqst *rqstp) { + struct nfsd3_setaclargs *argp = rqstp->rq_argp; + struct nfsd3_attrstat *resp = rqstp->rq_resp; struct inode *inode; svc_fh *fh; __be32 nfserr = 0; @@ -239,7 +240,7 @@ struct nfsd3_voidargs { int dummy; }; #define PROC(name, argt, rest, relt, cache, respsize) \ { \ - .pc_func = (svc_procfunc) nfsd3_proc_##name, \ + .pc_func = nfsd3_proc_##name, \ .pc_decode = (kxdrproc_t) nfs3svc_decode_##argt##args, \ .pc_encode = (kxdrproc_t) nfs3svc_encode_##rest##res, \ .pc_release = (kxdrproc_t) nfs3svc_release_##relt, \ diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 24e035190770..4a2bae07cfbf 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -31,7 +31,7 @@ static int nfs3_ftypes[] = { * NULL call. */ static __be32 -nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) +nfsd3_proc_null(struct svc_rqst *rqstp) { return nfs_ok; } @@ -40,9 +40,10 @@ nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) * Get a file's attributes */ static __be32 -nfsd3_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle *argp, - struct nfsd3_attrstat *resp) +nfsd3_proc_getattr(struct svc_rqst *rqstp) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + struct nfsd3_attrstat *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: GETATTR(3) %s\n", @@ -63,9 +64,10 @@ nfsd3_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle *argp, * Set a file's attributes */ static __be32 -nfsd3_proc_setattr(struct svc_rqst *rqstp, struct nfsd3_sattrargs *argp, - struct nfsd3_attrstat *resp) +nfsd3_proc_setattr(struct svc_rqst *rqstp) { + struct nfsd3_sattrargs *argp = rqstp->rq_argp; + struct nfsd3_attrstat *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: SETATTR(3) %s\n", @@ -81,9 +83,10 @@ nfsd3_proc_setattr(struct svc_rqst *rqstp, struct nfsd3_sattrargs *argp, * Look up a path name component */ static __be32 -nfsd3_proc_lookup(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp, - struct nfsd3_diropres *resp) +nfsd3_proc_lookup(struct svc_rqst *rqstp) { + struct nfsd3_diropargs *argp = rqstp->rq_argp; + struct nfsd3_diropres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: LOOKUP(3) %s %.*s\n", @@ -105,9 +108,10 @@ nfsd3_proc_lookup(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp, * Check file access */ static __be32 -nfsd3_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessargs *argp, - struct nfsd3_accessres *resp) +nfsd3_proc_access(struct svc_rqst *rqstp) { + struct nfsd3_accessargs *argp = rqstp->rq_argp; + struct nfsd3_accessres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: ACCESS(3) %s 0x%x\n", @@ -124,9 +128,10 @@ nfsd3_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessargs *argp, * Read a symlink. */ static __be32 -nfsd3_proc_readlink(struct svc_rqst *rqstp, struct nfsd3_readlinkargs *argp, - struct nfsd3_readlinkres *resp) +nfsd3_proc_readlink(struct svc_rqst *rqstp) { + struct nfsd3_readlinkargs *argp = rqstp->rq_argp; + struct nfsd3_readlinkres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: READLINK(3) %s\n", SVCFH_fmt(&argp->fh)); @@ -142,9 +147,10 @@ nfsd3_proc_readlink(struct svc_rqst *rqstp, struct nfsd3_readlinkargs *argp, * Read a portion of a file. */ static __be32 -nfsd3_proc_read(struct svc_rqst *rqstp, struct nfsd3_readargs *argp, - struct nfsd3_readres *resp) +nfsd3_proc_read(struct svc_rqst *rqstp) { + struct nfsd3_readargs *argp = rqstp->rq_argp; + struct nfsd3_readres *resp = rqstp->rq_resp; __be32 nfserr; u32 max_blocksize = svc_max_payload(rqstp); unsigned long cnt = min(argp->count, max_blocksize); @@ -179,9 +185,10 @@ nfsd3_proc_read(struct svc_rqst *rqstp, struct nfsd3_readargs *argp, * Write data to a file */ static __be32 -nfsd3_proc_write(struct svc_rqst *rqstp, struct nfsd3_writeargs *argp, - struct nfsd3_writeres *resp) +nfsd3_proc_write(struct svc_rqst *rqstp) { + struct nfsd3_writeargs *argp = rqstp->rq_argp; + struct nfsd3_writeres *resp = rqstp->rq_resp; __be32 nfserr; unsigned long cnt = argp->len; @@ -206,9 +213,10 @@ nfsd3_proc_write(struct svc_rqst *rqstp, struct nfsd3_writeargs *argp, * first reports about SunOS compatibility problems start to pour in... */ static __be32 -nfsd3_proc_create(struct svc_rqst *rqstp, struct nfsd3_createargs *argp, - struct nfsd3_diropres *resp) +nfsd3_proc_create(struct svc_rqst *rqstp) { + struct nfsd3_createargs *argp = rqstp->rq_argp; + struct nfsd3_diropres *resp = rqstp->rq_resp; svc_fh *dirfhp, *newfhp = NULL; struct iattr *attr; __be32 nfserr; @@ -243,9 +251,10 @@ nfsd3_proc_create(struct svc_rqst *rqstp, struct nfsd3_createargs *argp, * Make directory. This operation is not idempotent. */ static __be32 -nfsd3_proc_mkdir(struct svc_rqst *rqstp, struct nfsd3_createargs *argp, - struct nfsd3_diropres *resp) +nfsd3_proc_mkdir(struct svc_rqst *rqstp) { + struct nfsd3_createargs *argp = rqstp->rq_argp; + struct nfsd3_diropres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: MKDIR(3) %s %.*s\n", @@ -263,9 +272,10 @@ nfsd3_proc_mkdir(struct svc_rqst *rqstp, struct nfsd3_createargs *argp, } static __be32 -nfsd3_proc_symlink(struct svc_rqst *rqstp, struct nfsd3_symlinkargs *argp, - struct nfsd3_diropres *resp) +nfsd3_proc_symlink(struct svc_rqst *rqstp) { + struct nfsd3_symlinkargs *argp = rqstp->rq_argp; + struct nfsd3_diropres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: SYMLINK(3) %s %.*s -> %.*s\n", @@ -284,9 +294,10 @@ nfsd3_proc_symlink(struct svc_rqst *rqstp, struct nfsd3_symlinkargs *argp, * Make socket/fifo/device. */ static __be32 -nfsd3_proc_mknod(struct svc_rqst *rqstp, struct nfsd3_mknodargs *argp, - struct nfsd3_diropres *resp) +nfsd3_proc_mknod(struct svc_rqst *rqstp) { + struct nfsd3_mknodargs *argp = rqstp->rq_argp; + struct nfsd3_diropres *resp = rqstp->rq_resp; __be32 nfserr; int type; dev_t rdev = 0; @@ -321,9 +332,10 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp, struct nfsd3_mknodargs *argp, * Remove file/fifo/socket etc. */ static __be32 -nfsd3_proc_remove(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp, - struct nfsd3_attrstat *resp) +nfsd3_proc_remove(struct svc_rqst *rqstp) { + struct nfsd3_diropargs *argp = rqstp->rq_argp; + struct nfsd3_attrstat *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: REMOVE(3) %s %.*s\n", @@ -342,9 +354,10 @@ nfsd3_proc_remove(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp, * Remove a directory */ static __be32 -nfsd3_proc_rmdir(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp, - struct nfsd3_attrstat *resp) +nfsd3_proc_rmdir(struct svc_rqst *rqstp) { + struct nfsd3_diropargs *argp = rqstp->rq_argp; + struct nfsd3_attrstat *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: RMDIR(3) %s %.*s\n", @@ -359,9 +372,10 @@ nfsd3_proc_rmdir(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp, } static __be32 -nfsd3_proc_rename(struct svc_rqst *rqstp, struct nfsd3_renameargs *argp, - struct nfsd3_renameres *resp) +nfsd3_proc_rename(struct svc_rqst *rqstp) { + struct nfsd3_renameargs *argp = rqstp->rq_argp; + struct nfsd3_renameres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: RENAME(3) %s %.*s ->\n", @@ -381,9 +395,10 @@ nfsd3_proc_rename(struct svc_rqst *rqstp, struct nfsd3_renameargs *argp, } static __be32 -nfsd3_proc_link(struct svc_rqst *rqstp, struct nfsd3_linkargs *argp, - struct nfsd3_linkres *resp) +nfsd3_proc_link(struct svc_rqst *rqstp) { + struct nfsd3_linkargs *argp = rqstp->rq_argp; + struct nfsd3_linkres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: LINK(3) %s ->\n", @@ -404,9 +419,10 @@ nfsd3_proc_link(struct svc_rqst *rqstp, struct nfsd3_linkargs *argp, * Read a portion of a directory. */ static __be32 -nfsd3_proc_readdir(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp, - struct nfsd3_readdirres *resp) +nfsd3_proc_readdir(struct svc_rqst *rqstp) { + struct nfsd3_readdirargs *argp = rqstp->rq_argp; + struct nfsd3_readdirres *resp = rqstp->rq_resp; __be32 nfserr; int count; @@ -440,9 +456,10 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp, * For now, we choose to ignore the dircount parameter. */ static __be32 -nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp, - struct nfsd3_readdirres *resp) +nfsd3_proc_readdirplus(struct svc_rqst *rqstp) { + struct nfsd3_readdirargs *argp = rqstp->rq_argp; + struct nfsd3_readdirres *resp = rqstp->rq_resp; __be32 nfserr; int count = 0; loff_t offset; @@ -507,9 +524,10 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp, * Get file system stats */ static __be32 -nfsd3_proc_fsstat(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, - struct nfsd3_fsstatres *resp) +nfsd3_proc_fsstat(struct svc_rqst *rqstp) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + struct nfsd3_fsstatres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: FSSTAT(3) %s\n", @@ -524,9 +542,10 @@ nfsd3_proc_fsstat(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, * Get file system info */ static __be32 -nfsd3_proc_fsinfo(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, - struct nfsd3_fsinfores *resp) +nfsd3_proc_fsinfo(struct svc_rqst *rqstp) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + struct nfsd3_fsinfores *resp = rqstp->rq_resp; __be32 nfserr; u32 max_blocksize = svc_max_payload(rqstp); @@ -567,9 +586,10 @@ nfsd3_proc_fsinfo(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, * Get pathconf info for the specified file */ static __be32 -nfsd3_proc_pathconf(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, - struct nfsd3_pathconfres *resp) +nfsd3_proc_pathconf(struct svc_rqst *rqstp) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + struct nfsd3_pathconfres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: PATHCONF(3) %s\n", @@ -610,9 +630,10 @@ nfsd3_proc_pathconf(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, * Commit a file (range) to stable storage. */ static __be32 -nfsd3_proc_commit(struct svc_rqst * rqstp, struct nfsd3_commitargs *argp, - struct nfsd3_commitres *resp) +nfsd3_proc_commit(struct svc_rqst *rqstp) { + struct nfsd3_commitargs *argp = rqstp->rq_argp; + struct nfsd3_commitres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: COMMIT(3) %s %u@%Lu\n", @@ -655,7 +676,7 @@ struct nfsd3_voidargs { int dummy; }; static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_NULL] = { - .pc_func = (svc_procfunc) nfsd3_proc_null, + .pc_func = nfsd3_proc_null, .pc_encode = (kxdrproc_t) nfs3svc_encode_voidres, .pc_argsize = sizeof(struct nfsd3_voidargs), .pc_ressize = sizeof(struct nfsd3_voidres), @@ -663,7 +684,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST, }, [NFS3PROC_GETATTR] = { - .pc_func = (svc_procfunc) nfsd3_proc_getattr, + .pc_func = nfsd3_proc_getattr, .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_attrstatres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, @@ -673,7 +694,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+AT, }, [NFS3PROC_SETATTR] = { - .pc_func = (svc_procfunc) nfsd3_proc_setattr, + .pc_func = nfsd3_proc_setattr, .pc_decode = (kxdrproc_t) nfs3svc_decode_sattrargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, @@ -683,7 +704,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+WC, }, [NFS3PROC_LOOKUP] = { - .pc_func = (svc_procfunc) nfsd3_proc_lookup, + .pc_func = nfsd3_proc_lookup, .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_diropres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, @@ -693,7 +714,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+FH+pAT+pAT, }, [NFS3PROC_ACCESS] = { - .pc_func = (svc_procfunc) nfsd3_proc_access, + .pc_func = nfsd3_proc_access, .pc_decode = (kxdrproc_t) nfs3svc_decode_accessargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_accessres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, @@ -703,7 +724,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+pAT+1, }, [NFS3PROC_READLINK] = { - .pc_func = (svc_procfunc) nfsd3_proc_readlink, + .pc_func = nfsd3_proc_readlink, .pc_decode = (kxdrproc_t) nfs3svc_decode_readlinkargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readlinkres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, @@ -713,7 +734,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+pAT+1+NFS3_MAXPATHLEN/4, }, [NFS3PROC_READ] = { - .pc_func = (svc_procfunc) nfsd3_proc_read, + .pc_func = nfsd3_proc_read, .pc_decode = (kxdrproc_t) nfs3svc_decode_readargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, @@ -723,7 +744,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+pAT+4+NFSSVC_MAXBLKSIZE/4, }, [NFS3PROC_WRITE] = { - .pc_func = (svc_procfunc) nfsd3_proc_write, + .pc_func = nfsd3_proc_write, .pc_decode = (kxdrproc_t) nfs3svc_decode_writeargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_writeres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, @@ -733,7 +754,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+WC+4, }, [NFS3PROC_CREATE] = { - .pc_func = (svc_procfunc) nfsd3_proc_create, + .pc_func = nfsd3_proc_create, .pc_decode = (kxdrproc_t) nfs3svc_decode_createargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, @@ -743,7 +764,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+(1+FH+pAT)+WC, }, [NFS3PROC_MKDIR] = { - .pc_func = (svc_procfunc) nfsd3_proc_mkdir, + .pc_func = nfsd3_proc_mkdir, .pc_decode = (kxdrproc_t) nfs3svc_decode_mkdirargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, @@ -753,7 +774,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+(1+FH+pAT)+WC, }, [NFS3PROC_SYMLINK] = { - .pc_func = (svc_procfunc) nfsd3_proc_symlink, + .pc_func = nfsd3_proc_symlink, .pc_decode = (kxdrproc_t) nfs3svc_decode_symlinkargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, @@ -763,7 +784,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+(1+FH+pAT)+WC, }, [NFS3PROC_MKNOD] = { - .pc_func = (svc_procfunc) nfsd3_proc_mknod, + .pc_func = nfsd3_proc_mknod, .pc_decode = (kxdrproc_t) nfs3svc_decode_mknodargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, @@ -773,7 +794,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+(1+FH+pAT)+WC, }, [NFS3PROC_REMOVE] = { - .pc_func = (svc_procfunc) nfsd3_proc_remove, + .pc_func = nfsd3_proc_remove, .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, @@ -783,7 +804,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+WC, }, [NFS3PROC_RMDIR] = { - .pc_func = (svc_procfunc) nfsd3_proc_rmdir, + .pc_func = nfsd3_proc_rmdir, .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, @@ -793,7 +814,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+WC, }, [NFS3PROC_RENAME] = { - .pc_func = (svc_procfunc) nfsd3_proc_rename, + .pc_func = nfsd3_proc_rename, .pc_decode = (kxdrproc_t) nfs3svc_decode_renameargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_renameres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, @@ -803,7 +824,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+WC+WC, }, [NFS3PROC_LINK] = { - .pc_func = (svc_procfunc) nfsd3_proc_link, + .pc_func = nfsd3_proc_link, .pc_decode = (kxdrproc_t) nfs3svc_decode_linkargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_linkres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, @@ -813,7 +834,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+pAT+WC, }, [NFS3PROC_READDIR] = { - .pc_func = (svc_procfunc) nfsd3_proc_readdir, + .pc_func = nfsd3_proc_readdir, .pc_decode = (kxdrproc_t) nfs3svc_decode_readdirargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, @@ -822,7 +843,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_cachetype = RC_NOCACHE, }, [NFS3PROC_READDIRPLUS] = { - .pc_func = (svc_procfunc) nfsd3_proc_readdirplus, + .pc_func = nfsd3_proc_readdirplus, .pc_decode = (kxdrproc_t) nfs3svc_decode_readdirplusargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, @@ -831,7 +852,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_cachetype = RC_NOCACHE, }, [NFS3PROC_FSSTAT] = { - .pc_func = (svc_procfunc) nfsd3_proc_fsstat, + .pc_func = nfsd3_proc_fsstat, .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_fsstatres, .pc_argsize = sizeof(struct nfsd3_fhandleargs), @@ -840,7 +861,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+pAT+2*6+1, }, [NFS3PROC_FSINFO] = { - .pc_func = (svc_procfunc) nfsd3_proc_fsinfo, + .pc_func = nfsd3_proc_fsinfo, .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_fsinfores, .pc_argsize = sizeof(struct nfsd3_fhandleargs), @@ -849,7 +870,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+pAT+12, }, [NFS3PROC_PATHCONF] = { - .pc_func = (svc_procfunc) nfsd3_proc_pathconf, + .pc_func = nfsd3_proc_pathconf, .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_pathconfres, .pc_argsize = sizeof(struct nfsd3_fhandleargs), @@ -858,7 +879,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_xdrressize = ST+pAT+6, }, [NFS3PROC_COMMIT] = { - .pc_func = (svc_procfunc) nfsd3_proc_commit, + .pc_func = nfsd3_proc_commit, .pc_decode = (kxdrproc_t) nfs3svc_decode_commitargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_commitres, .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 0833686ccdd3..43b2e5ab4430 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1510,7 +1510,7 @@ out: * NULL call. */ static __be32 -nfsd4_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) +nfsd4_proc_null(struct svc_rqst *rqstp) { return nfs_ok; } @@ -1524,6 +1524,7 @@ static inline void nfsd4_increment_op_stats(u32 opnum) typedef __be32(*nfsd4op_func)(struct svc_rqst *, struct nfsd4_compound_state *, void *); typedef u32(*nfsd4op_rsize)(struct svc_rqst *, struct nfsd4_op *op); + typedef void(*stateid_setter)(struct nfsd4_compound_state *, void *); typedef void(*stateid_getter)(struct nfsd4_compound_state *, void *); @@ -1673,10 +1674,10 @@ static void svcxdr_init_encode(struct svc_rqst *rqstp, * COMPOUND call. */ static __be32 -nfsd4_proc_compound(struct svc_rqst *rqstp, void *arg, void *res) +nfsd4_proc_compound(struct svc_rqst *rqstp) { - struct nfsd4_compoundargs *args = arg; - struct nfsd4_compoundres *resp = res; + struct nfsd4_compoundargs *args = rqstp->rq_argp; + struct nfsd4_compoundres *resp = rqstp->rq_resp; struct nfsd4_op *op; struct nfsd4_operation *opdesc; struct nfsd4_compound_state *cstate = &resp->cstate; diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 03a7e9da4da0..448505b939db 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -17,7 +17,7 @@ typedef struct svc_buf svc_buf; static __be32 -nfsd_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) +nfsd_proc_null(struct svc_rqst *rqstp) { return nfs_ok; } @@ -39,9 +39,10 @@ nfsd_return_dirop(__be32 err, struct nfsd_diropres *resp) * N.B. After this call resp->fh needs an fh_put */ static __be32 -nfsd_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle *argp, - struct nfsd_attrstat *resp) +nfsd_proc_getattr(struct svc_rqst *rqstp) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + struct nfsd_attrstat *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: GETATTR %s\n", SVCFH_fmt(&argp->fh)); @@ -56,9 +57,10 @@ nfsd_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle *argp, * N.B. After this call resp->fh needs an fh_put */ static __be32 -nfsd_proc_setattr(struct svc_rqst *rqstp, struct nfsd_sattrargs *argp, - struct nfsd_attrstat *resp) +nfsd_proc_setattr(struct svc_rqst *rqstp) { + struct nfsd_sattrargs *argp = rqstp->rq_argp; + struct nfsd_attrstat *resp = rqstp->rq_resp; struct iattr *iap = &argp->attrs; struct svc_fh *fhp; __be32 nfserr; @@ -122,9 +124,10 @@ done: * N.B. After this call resp->fh needs an fh_put */ static __be32 -nfsd_proc_lookup(struct svc_rqst *rqstp, struct nfsd_diropargs *argp, - struct nfsd_diropres *resp) +nfsd_proc_lookup(struct svc_rqst *rqstp) { + struct nfsd_diropargs *argp = rqstp->rq_argp; + struct nfsd_diropres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: LOOKUP %s %.*s\n", @@ -142,9 +145,10 @@ nfsd_proc_lookup(struct svc_rqst *rqstp, struct nfsd_diropargs *argp, * Read a symlink. */ static __be32 -nfsd_proc_readlink(struct svc_rqst *rqstp, struct nfsd_readlinkargs *argp, - struct nfsd_readlinkres *resp) +nfsd_proc_readlink(struct svc_rqst *rqstp) { + struct nfsd_readlinkargs *argp = rqstp->rq_argp; + struct nfsd_readlinkres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: READLINK %s\n", SVCFH_fmt(&argp->fh)); @@ -162,9 +166,10 @@ nfsd_proc_readlink(struct svc_rqst *rqstp, struct nfsd_readlinkargs *argp, * N.B. After this call resp->fh needs an fh_put */ static __be32 -nfsd_proc_read(struct svc_rqst *rqstp, struct nfsd_readargs *argp, - struct nfsd_readres *resp) +nfsd_proc_read(struct svc_rqst *rqstp) { + struct nfsd_readargs *argp = rqstp->rq_argp; + struct nfsd_readres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: READ %s %d bytes at %d\n", @@ -200,9 +205,10 @@ nfsd_proc_read(struct svc_rqst *rqstp, struct nfsd_readargs *argp, * N.B. After this call resp->fh needs an fh_put */ static __be32 -nfsd_proc_write(struct svc_rqst *rqstp, struct nfsd_writeargs *argp, - struct nfsd_attrstat *resp) +nfsd_proc_write(struct svc_rqst *rqstp) { + struct nfsd_writeargs *argp = rqstp->rq_argp; + struct nfsd_attrstat *resp = rqstp->rq_resp; __be32 nfserr; unsigned long cnt = argp->len; @@ -222,9 +228,10 @@ nfsd_proc_write(struct svc_rqst *rqstp, struct nfsd_writeargs *argp, * N.B. After this call _both_ argp->fh and resp->fh need an fh_put */ static __be32 -nfsd_proc_create(struct svc_rqst *rqstp, struct nfsd_createargs *argp, - struct nfsd_diropres *resp) +nfsd_proc_create(struct svc_rqst *rqstp) { + struct nfsd_createargs *argp = rqstp->rq_argp; + struct nfsd_diropres *resp = rqstp->rq_resp; svc_fh *dirfhp = &argp->fh; svc_fh *newfhp = &resp->fh; struct iattr *attr = &argp->attrs; @@ -377,9 +384,9 @@ done: } static __be32 -nfsd_proc_remove(struct svc_rqst *rqstp, struct nfsd_diropargs *argp, - void *resp) +nfsd_proc_remove(struct svc_rqst *rqstp) { + struct nfsd_diropargs *argp = rqstp->rq_argp; __be32 nfserr; dprintk("nfsd: REMOVE %s %.*s\n", SVCFH_fmt(&argp->fh), @@ -392,9 +399,9 @@ nfsd_proc_remove(struct svc_rqst *rqstp, struct nfsd_diropargs *argp, } static __be32 -nfsd_proc_rename(struct svc_rqst *rqstp, struct nfsd_renameargs *argp, - void *resp) +nfsd_proc_rename(struct svc_rqst *rqstp) { + struct nfsd_renameargs *argp = rqstp->rq_argp; __be32 nfserr; dprintk("nfsd: RENAME %s %.*s -> \n", @@ -410,9 +417,9 @@ nfsd_proc_rename(struct svc_rqst *rqstp, struct nfsd_renameargs *argp, } static __be32 -nfsd_proc_link(struct svc_rqst *rqstp, struct nfsd_linkargs *argp, - void *resp) +nfsd_proc_link(struct svc_rqst *rqstp) { + struct nfsd_linkargs *argp = rqstp->rq_argp; __be32 nfserr; dprintk("nfsd: LINK %s ->\n", @@ -430,9 +437,9 @@ nfsd_proc_link(struct svc_rqst *rqstp, struct nfsd_linkargs *argp, } static __be32 -nfsd_proc_symlink(struct svc_rqst *rqstp, struct nfsd_symlinkargs *argp, - void *resp) +nfsd_proc_symlink(struct svc_rqst *rqstp) { + struct nfsd_symlinkargs *argp = rqstp->rq_argp; struct svc_fh newfh; __be32 nfserr; @@ -460,9 +467,10 @@ nfsd_proc_symlink(struct svc_rqst *rqstp, struct nfsd_symlinkargs *argp, * N.B. After this call resp->fh needs an fh_put */ static __be32 -nfsd_proc_mkdir(struct svc_rqst *rqstp, struct nfsd_createargs *argp, - struct nfsd_diropres *resp) +nfsd_proc_mkdir(struct svc_rqst *rqstp) { + struct nfsd_createargs *argp = rqstp->rq_argp; + struct nfsd_diropres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: MKDIR %s %.*s\n", SVCFH_fmt(&argp->fh), argp->len, argp->name); @@ -484,9 +492,9 @@ nfsd_proc_mkdir(struct svc_rqst *rqstp, struct nfsd_createargs *argp, * Remove a directory */ static __be32 -nfsd_proc_rmdir(struct svc_rqst *rqstp, struct nfsd_diropargs *argp, - void *resp) +nfsd_proc_rmdir(struct svc_rqst *rqstp) { + struct nfsd_diropargs *argp = rqstp->rq_argp; __be32 nfserr; dprintk("nfsd: RMDIR %s %.*s\n", SVCFH_fmt(&argp->fh), argp->len, argp->name); @@ -500,9 +508,10 @@ nfsd_proc_rmdir(struct svc_rqst *rqstp, struct nfsd_diropargs *argp, * Read a portion of a directory. */ static __be32 -nfsd_proc_readdir(struct svc_rqst *rqstp, struct nfsd_readdirargs *argp, - struct nfsd_readdirres *resp) +nfsd_proc_readdir(struct svc_rqst *rqstp) { + struct nfsd_readdirargs *argp = rqstp->rq_argp; + struct nfsd_readdirres *resp = rqstp->rq_resp; int count; __be32 nfserr; loff_t offset; @@ -540,9 +549,10 @@ nfsd_proc_readdir(struct svc_rqst *rqstp, struct nfsd_readdirargs *argp, * Get file system info */ static __be32 -nfsd_proc_statfs(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, - struct nfsd_statfsres *resp) +nfsd_proc_statfs(struct svc_rqst *rqstp) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + struct nfsd_statfsres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: STATFS %s\n", SVCFH_fmt(&argp->fh)); @@ -565,7 +575,7 @@ struct nfsd_void { int dummy; }; static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_NULL] = { - .pc_func = (svc_procfunc) nfsd_proc_null, + .pc_func = nfsd_proc_null, .pc_decode = (kxdrproc_t) nfssvc_decode_void, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_void), @@ -574,7 +584,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST, }, [NFSPROC_GETATTR] = { - .pc_func = (svc_procfunc) nfsd_proc_getattr, + .pc_func = nfsd_proc_getattr, .pc_decode = (kxdrproc_t) nfssvc_decode_fhandle, .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, .pc_release = (kxdrproc_t) nfssvc_release_fhandle, @@ -584,7 +594,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST+AT, }, [NFSPROC_SETATTR] = { - .pc_func = (svc_procfunc) nfsd_proc_setattr, + .pc_func = nfsd_proc_setattr, .pc_decode = (kxdrproc_t) nfssvc_decode_sattrargs, .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, .pc_release = (kxdrproc_t) nfssvc_release_fhandle, @@ -602,7 +612,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST, }, [NFSPROC_LOOKUP] = { - .pc_func = (svc_procfunc) nfsd_proc_lookup, + .pc_func = nfsd_proc_lookup, .pc_decode = (kxdrproc_t) nfssvc_decode_diropargs, .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, .pc_release = (kxdrproc_t) nfssvc_release_fhandle, @@ -612,7 +622,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST+FH+AT, }, [NFSPROC_READLINK] = { - .pc_func = (svc_procfunc) nfsd_proc_readlink, + .pc_func = nfsd_proc_readlink, .pc_decode = (kxdrproc_t) nfssvc_decode_readlinkargs, .pc_encode = (kxdrproc_t) nfssvc_encode_readlinkres, .pc_argsize = sizeof(struct nfsd_readlinkargs), @@ -621,7 +631,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST+1+NFS_MAXPATHLEN/4, }, [NFSPROC_READ] = { - .pc_func = (svc_procfunc) nfsd_proc_read, + .pc_func = nfsd_proc_read, .pc_decode = (kxdrproc_t) nfssvc_decode_readargs, .pc_encode = (kxdrproc_t) nfssvc_encode_readres, .pc_release = (kxdrproc_t) nfssvc_release_fhandle, @@ -639,7 +649,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST, }, [NFSPROC_WRITE] = { - .pc_func = (svc_procfunc) nfsd_proc_write, + .pc_func = nfsd_proc_write, .pc_decode = (kxdrproc_t) nfssvc_decode_writeargs, .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, .pc_release = (kxdrproc_t) nfssvc_release_fhandle, @@ -649,7 +659,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST+AT, }, [NFSPROC_CREATE] = { - .pc_func = (svc_procfunc) nfsd_proc_create, + .pc_func = nfsd_proc_create, .pc_decode = (kxdrproc_t) nfssvc_decode_createargs, .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, .pc_release = (kxdrproc_t) nfssvc_release_fhandle, @@ -659,7 +669,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST+FH+AT, }, [NFSPROC_REMOVE] = { - .pc_func = (svc_procfunc) nfsd_proc_remove, + .pc_func = nfsd_proc_remove, .pc_decode = (kxdrproc_t) nfssvc_decode_diropargs, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_diropargs), @@ -668,7 +678,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST, }, [NFSPROC_RENAME] = { - .pc_func = (svc_procfunc) nfsd_proc_rename, + .pc_func = nfsd_proc_rename, .pc_decode = (kxdrproc_t) nfssvc_decode_renameargs, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_renameargs), @@ -677,7 +687,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST, }, [NFSPROC_LINK] = { - .pc_func = (svc_procfunc) nfsd_proc_link, + .pc_func = nfsd_proc_link, .pc_decode = (kxdrproc_t) nfssvc_decode_linkargs, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_linkargs), @@ -686,7 +696,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST, }, [NFSPROC_SYMLINK] = { - .pc_func = (svc_procfunc) nfsd_proc_symlink, + .pc_func = nfsd_proc_symlink, .pc_decode = (kxdrproc_t) nfssvc_decode_symlinkargs, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_symlinkargs), @@ -695,7 +705,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST, }, [NFSPROC_MKDIR] = { - .pc_func = (svc_procfunc) nfsd_proc_mkdir, + .pc_func = nfsd_proc_mkdir, .pc_decode = (kxdrproc_t) nfssvc_decode_createargs, .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, .pc_release = (kxdrproc_t) nfssvc_release_fhandle, @@ -705,7 +715,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST+FH+AT, }, [NFSPROC_RMDIR] = { - .pc_func = (svc_procfunc) nfsd_proc_rmdir, + .pc_func = nfsd_proc_rmdir, .pc_decode = (kxdrproc_t) nfssvc_decode_diropargs, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_diropargs), @@ -714,7 +724,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST, }, [NFSPROC_READDIR] = { - .pc_func = (svc_procfunc) nfsd_proc_readdir, + .pc_func = nfsd_proc_readdir, .pc_decode = (kxdrproc_t) nfssvc_decode_readdirargs, .pc_encode = (kxdrproc_t) nfssvc_encode_readdirres, .pc_argsize = sizeof(struct nfsd_readdirargs), @@ -722,7 +732,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_cachetype = RC_NOCACHE, }, [NFSPROC_STATFS] = { - .pc_func = (svc_procfunc) nfsd_proc_statfs, + .pc_func = nfsd_proc_statfs, .pc_decode = (kxdrproc_t) nfssvc_decode_fhandle, .pc_encode = (kxdrproc_t) nfssvc_encode_statfsres, .pc_argsize = sizeof(struct nfsd_fhandle), diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 59979f0bbd4b..d64895fd8d25 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -827,7 +827,7 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) rqstp->rq_res.head[0].iov_len += sizeof(__be32); /* Now call the procedure handler, and encode NFS status. */ - nfserr = proc->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp); + nfserr = proc->pc_func(rqstp); nfserr = map_new_errors(rqstp->rq_vers, nfserr); if (nfserr == nfserr_dropit || test_bit(RQ_DROPME, &rqstp->rq_flags)) { dprintk("nfsd: Dropping request; may be revisited later\n"); diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 11cef5a7bc87..3b58c55614c7 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -419,9 +419,9 @@ struct svc_version { /* * RPC procedure info */ -typedef __be32 (*svc_procfunc)(struct svc_rqst *, void *argp, void *resp); struct svc_procedure { - svc_procfunc pc_func; /* process the request */ + /* process the request: */ + __be32 (*pc_func)(struct svc_rqst *); kxdrproc_t pc_decode; /* XDR decode args */ kxdrproc_t pc_encode; /* XDR encode result */ kxdrproc_t pc_release; /* XDR free result */ diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index bc0f5a0ecbdc..95335455ad38 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1281,7 +1281,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) if (xdr && !xdr(rqstp, argv->iov_base, rqstp->rq_argp)) goto err_garbage; - *statp = procp->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp); + *statp = procp->pc_func(rqstp); /* Encode reply */ if (*statp == rpc_drop_reply || -- cgit v1.2.3-59-g8ed1b From 1150ded804c2be6d02efef3e39e39e570c9cea21 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 18:48:24 +0200 Subject: sunrpc: properly type pc_release callbacks Drop the p and resp arguments as they are always NULL or can trivially be derived from the rqstp argument. With that all functions now have the same prototype, and we can remove the unsafe casting to kxdrproc_t. Signed-off-by: Christoph Hellwig --- fs/nfsd/nfs2acl.c | 22 +++++++++++----------- fs/nfsd/nfs3acl.c | 8 ++++---- fs/nfsd/nfs3proc.c | 36 ++++++++++++++++++------------------ fs/nfsd/nfs3xdr.c | 16 ++++++++-------- fs/nfsd/nfs4xdr.c | 4 +--- fs/nfsd/nfsproc.c | 14 +++++++------- fs/nfsd/nfsxdr.c | 8 ++++---- fs/nfsd/xdr.h | 2 +- fs/nfsd/xdr3.h | 6 ++---- fs/nfsd/xdr4.h | 2 +- include/linux/sunrpc/svc.h | 3 ++- net/sunrpc/svc.c | 8 ++++---- 12 files changed, 63 insertions(+), 66 deletions(-) diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 4b7f84fa1fa5..302441027f50 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -318,27 +318,27 @@ static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p, /* * XDR release functions */ -static int nfsaclsvc_release_getacl(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_getaclres *resp) +static void nfsaclsvc_release_getacl(struct svc_rqst *rqstp) { + struct nfsd3_getaclres *resp = rqstp->rq_resp; + fh_put(&resp->fh); posix_acl_release(resp->acl_access); posix_acl_release(resp->acl_default); - return 1; } -static int nfsaclsvc_release_attrstat(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_attrstat *resp) +static void nfsaclsvc_release_attrstat(struct svc_rqst *rqstp) { + struct nfsd_attrstat *resp = rqstp->rq_resp; + fh_put(&resp->fh); - return 1; } -static int nfsaclsvc_release_access(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_accessres *resp) +static void nfsaclsvc_release_access(struct svc_rqst *rqstp) { - fh_put(&resp->fh); - return 1; + struct nfsd3_accessres *resp = rqstp->rq_resp; + + fh_put(&resp->fh); } #define nfsaclsvc_decode_voidargs NULL @@ -353,7 +353,7 @@ struct nfsd3_voidargs { int dummy; }; .pc_func = nfsacld_proc_##name, \ .pc_decode = (kxdrproc_t) nfsaclsvc_decode_##argt##args, \ .pc_encode = (kxdrproc_t) nfsaclsvc_encode_##rest##res, \ - .pc_release = (kxdrproc_t) nfsaclsvc_release_##relt, \ + .pc_release = nfsaclsvc_release_##relt, \ .pc_argsize = sizeof(struct nfsd3_##argt##args), \ .pc_ressize = sizeof(struct nfsd3_##rest##res), \ .pc_cachetype = cache, \ diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 5e42004035e0..56cdff4e954c 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -223,13 +223,13 @@ static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p, /* * XDR release functions */ -static int nfs3svc_release_getacl(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_getaclres *resp) +static void nfs3svc_release_getacl(struct svc_rqst *rqstp) { + struct nfsd3_getaclres *resp = rqstp->rq_resp; + fh_put(&resp->fh); posix_acl_release(resp->acl_access); posix_acl_release(resp->acl_default); - return 1; } #define nfs3svc_decode_voidargs NULL @@ -243,7 +243,7 @@ struct nfsd3_voidargs { int dummy; }; .pc_func = nfsd3_proc_##name, \ .pc_decode = (kxdrproc_t) nfs3svc_decode_##argt##args, \ .pc_encode = (kxdrproc_t) nfs3svc_encode_##rest##res, \ - .pc_release = (kxdrproc_t) nfs3svc_release_##relt, \ + .pc_release = nfs3svc_release_##relt, \ .pc_argsize = sizeof(struct nfsd3_##argt##args), \ .pc_ressize = sizeof(struct nfsd3_##rest##res), \ .pc_cachetype = cache, \ diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 4a2bae07cfbf..f0cccc0768ce 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -687,7 +687,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_getattr, .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_attrstatres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_attrstatres), .pc_cachetype = RC_NOCACHE, @@ -697,7 +697,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_setattr, .pc_decode = (kxdrproc_t) nfs3svc_decode_sattrargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_sattrargs), .pc_ressize = sizeof(struct nfsd3_wccstatres), .pc_cachetype = RC_REPLBUFF, @@ -707,7 +707,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_lookup, .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_diropres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, + .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_diropargs), .pc_ressize = sizeof(struct nfsd3_diropres), .pc_cachetype = RC_NOCACHE, @@ -717,7 +717,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_access, .pc_decode = (kxdrproc_t) nfs3svc_decode_accessargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_accessres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_accessargs), .pc_ressize = sizeof(struct nfsd3_accessres), .pc_cachetype = RC_NOCACHE, @@ -727,7 +727,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_readlink, .pc_decode = (kxdrproc_t) nfs3svc_decode_readlinkargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readlinkres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readlinkargs), .pc_ressize = sizeof(struct nfsd3_readlinkres), .pc_cachetype = RC_NOCACHE, @@ -737,7 +737,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_read, .pc_decode = (kxdrproc_t) nfs3svc_decode_readargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readargs), .pc_ressize = sizeof(struct nfsd3_readres), .pc_cachetype = RC_NOCACHE, @@ -747,7 +747,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_write, .pc_decode = (kxdrproc_t) nfs3svc_decode_writeargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_writeres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_writeargs), .pc_ressize = sizeof(struct nfsd3_writeres), .pc_cachetype = RC_REPLBUFF, @@ -757,7 +757,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_create, .pc_decode = (kxdrproc_t) nfs3svc_decode_createargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, + .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_createargs), .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, @@ -767,7 +767,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_mkdir, .pc_decode = (kxdrproc_t) nfs3svc_decode_mkdirargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, + .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_mkdirargs), .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, @@ -777,7 +777,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_symlink, .pc_decode = (kxdrproc_t) nfs3svc_decode_symlinkargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, + .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_symlinkargs), .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, @@ -787,7 +787,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_mknod, .pc_decode = (kxdrproc_t) nfs3svc_decode_mknodargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, + .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_mknodargs), .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, @@ -797,7 +797,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_remove, .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_diropargs), .pc_ressize = sizeof(struct nfsd3_wccstatres), .pc_cachetype = RC_REPLBUFF, @@ -807,7 +807,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_rmdir, .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_diropargs), .pc_ressize = sizeof(struct nfsd3_wccstatres), .pc_cachetype = RC_REPLBUFF, @@ -817,7 +817,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_rename, .pc_decode = (kxdrproc_t) nfs3svc_decode_renameargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_renameres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, + .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_renameargs), .pc_ressize = sizeof(struct nfsd3_renameres), .pc_cachetype = RC_REPLBUFF, @@ -827,7 +827,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_link, .pc_decode = (kxdrproc_t) nfs3svc_decode_linkargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_linkres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, + .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_linkargs), .pc_ressize = sizeof(struct nfsd3_linkres), .pc_cachetype = RC_REPLBUFF, @@ -837,7 +837,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_readdir, .pc_decode = (kxdrproc_t) nfs3svc_decode_readdirargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readdirargs), .pc_ressize = sizeof(struct nfsd3_readdirres), .pc_cachetype = RC_NOCACHE, @@ -846,7 +846,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_readdirplus, .pc_decode = (kxdrproc_t) nfs3svc_decode_readdirplusargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readdirplusargs), .pc_ressize = sizeof(struct nfsd3_readdirres), .pc_cachetype = RC_NOCACHE, @@ -882,7 +882,7 @@ static struct svc_procedure nfsd_procedures3[22] = { .pc_func = nfsd3_proc_commit, .pc_decode = (kxdrproc_t) nfs3svc_decode_commitargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_commitres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_commitargs), .pc_ressize = sizeof(struct nfsd3_commitres), .pc_cachetype = RC_NOCACHE, diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 452334694a5d..c3d3ef28347c 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -1103,19 +1103,19 @@ nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p, /* * XDR release functions */ -int -nfs3svc_release_fhandle(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_attrstat *resp) +void +nfs3svc_release_fhandle(struct svc_rqst *rqstp) { + struct nfsd3_attrstat *resp = rqstp->rq_resp; + fh_put(&resp->fh); - return 1; } -int -nfs3svc_release_fhandle2(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_fhandle_pair *resp) +void +nfs3svc_release_fhandle2(struct svc_rqst *rqstp) { + struct nfsd3_fhandle_pair *resp = rqstp->rq_resp; + fh_put(&resp->fh1); fh_put(&resp->fh2); - return 1; } diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 26780d53a6f9..5aa847bdfc63 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -4543,9 +4543,8 @@ nfs4svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy) return xdr_ressize_check(rqstp, p); } -int nfsd4_release_compoundargs(void *rq, __be32 *p, void *resp) +void nfsd4_release_compoundargs(struct svc_rqst *rqstp) { - struct svc_rqst *rqstp = rq; struct nfsd4_compoundargs *args = rqstp->rq_argp; if (args->ops != args->iops) { @@ -4559,7 +4558,6 @@ int nfsd4_release_compoundargs(void *rq, __be32 *p, void *resp) args->to_free = tb->next; kfree(tb); } - return 1; } int diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 448505b939db..dc32e0f8480d 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -587,7 +587,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_func = nfsd_proc_getattr, .pc_decode = (kxdrproc_t) nfssvc_decode_fhandle, .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, - .pc_release = (kxdrproc_t) nfssvc_release_fhandle, + .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_NOCACHE, @@ -597,7 +597,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_func = nfsd_proc_setattr, .pc_decode = (kxdrproc_t) nfssvc_decode_sattrargs, .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, - .pc_release = (kxdrproc_t) nfssvc_release_fhandle, + .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_sattrargs), .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_REPLBUFF, @@ -615,7 +615,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_func = nfsd_proc_lookup, .pc_decode = (kxdrproc_t) nfssvc_decode_diropargs, .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, - .pc_release = (kxdrproc_t) nfssvc_release_fhandle, + .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_diropargs), .pc_ressize = sizeof(struct nfsd_diropres), .pc_cachetype = RC_NOCACHE, @@ -634,7 +634,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_func = nfsd_proc_read, .pc_decode = (kxdrproc_t) nfssvc_decode_readargs, .pc_encode = (kxdrproc_t) nfssvc_encode_readres, - .pc_release = (kxdrproc_t) nfssvc_release_fhandle, + .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_readargs), .pc_ressize = sizeof(struct nfsd_readres), .pc_cachetype = RC_NOCACHE, @@ -652,7 +652,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_func = nfsd_proc_write, .pc_decode = (kxdrproc_t) nfssvc_decode_writeargs, .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, - .pc_release = (kxdrproc_t) nfssvc_release_fhandle, + .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_writeargs), .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_REPLBUFF, @@ -662,7 +662,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_func = nfsd_proc_create, .pc_decode = (kxdrproc_t) nfssvc_decode_createargs, .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, - .pc_release = (kxdrproc_t) nfssvc_release_fhandle, + .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_createargs), .pc_ressize = sizeof(struct nfsd_diropres), .pc_cachetype = RC_REPLBUFF, @@ -708,7 +708,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_func = nfsd_proc_mkdir, .pc_decode = (kxdrproc_t) nfssvc_decode_createargs, .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, - .pc_release = (kxdrproc_t) nfssvc_release_fhandle, + .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_createargs), .pc_ressize = sizeof(struct nfsd_diropres), .pc_cachetype = RC_REPLBUFF, diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index de07ff625777..2facfc6ac8f3 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -543,10 +543,10 @@ nfssvc_encode_entry(void *ccdv, const char *name, /* * XDR release functions */ -int -nfssvc_release_fhandle(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_fhandle *resp) +void +nfssvc_release_fhandle(struct svc_rqst *rqstp) { + struct nfsd_fhandle *resp = rqstp->rq_resp; + fh_put(&resp->fh); - return 1; } diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h index 4f0481d63804..2c21fa843fbf 100644 --- a/fs/nfsd/xdr.h +++ b/fs/nfsd/xdr.h @@ -164,7 +164,7 @@ int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *, struct nfsd_readdirres int nfssvc_encode_entry(void *, const char *name, int namlen, loff_t offset, u64 ino, unsigned int); -int nfssvc_release_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *); +void nfssvc_release_fhandle(struct svc_rqst *); /* Helper functions for NFSv2 ACL code */ __be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat); diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h index 335e04aaf7db..23fe456a223b 100644 --- a/fs/nfsd/xdr3.h +++ b/fs/nfsd/xdr3.h @@ -330,10 +330,8 @@ int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *, int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *, struct nfsd3_commitres *); -int nfs3svc_release_fhandle(struct svc_rqst *, __be32 *, - struct nfsd3_attrstat *); -int nfs3svc_release_fhandle2(struct svc_rqst *, __be32 *, - struct nfsd3_fhandle_pair *); +void nfs3svc_release_fhandle(struct svc_rqst *); +void nfs3svc_release_fhandle2(struct svc_rqst *); int nfs3svc_encode_entry(void *, const char *name, int namlen, loff_t offset, u64 ino, unsigned int); diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 8fda4abdf3b1..a158579d55a2 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -743,7 +743,7 @@ extern __be32 nfsd4_release_lockowner(struct svc_rqst *rqstp, struct nfsd4_compound_state *, struct nfsd4_release_lockowner *rlockowner); -extern int nfsd4_release_compoundargs(void *rq, __be32 *p, void *resp); +extern void nfsd4_release_compoundargs(struct svc_rqst *rqstp); extern __be32 nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *, struct nfsd4_delegreturn *dr); extern __be32 nfsd4_renew(struct svc_rqst *rqstp, diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 3b58c55614c7..c73194e9c2bd 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -424,7 +424,8 @@ struct svc_procedure { __be32 (*pc_func)(struct svc_rqst *); kxdrproc_t pc_decode; /* XDR decode args */ kxdrproc_t pc_encode; /* XDR encode result */ - kxdrproc_t pc_release; /* XDR free result */ + /* XDR free result: */ + void (*pc_release)(struct svc_rqst *); unsigned int pc_argsize; /* argument struct size */ unsigned int pc_ressize; /* result struct size */ unsigned int pc_count; /* call count */ diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 95335455ad38..4611cb7adc04 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1287,12 +1287,12 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) if (*statp == rpc_drop_reply || test_bit(RQ_DROPME, &rqstp->rq_flags)) { if (procp->pc_release) - procp->pc_release(rqstp, NULL, rqstp->rq_resp); + procp->pc_release(rqstp); goto dropit; } if (*statp == rpc_autherr_badcred) { if (procp->pc_release) - procp->pc_release(rqstp, NULL, rqstp->rq_resp); + procp->pc_release(rqstp); goto err_bad_auth; } if (*statp == rpc_success && @@ -1307,7 +1307,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) if (!versp->vs_dispatch(rqstp, statp)) { /* Release reply info */ if (procp->pc_release) - procp->pc_release(rqstp, NULL, rqstp->rq_resp); + procp->pc_release(rqstp); goto dropit; } } @@ -1318,7 +1318,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) /* Release reply info */ if (procp->pc_release) - procp->pc_release(rqstp, NULL, rqstp->rq_resp); + procp->pc_release(rqstp); if (procp->pc_encode == NULL) goto dropit; -- cgit v1.2.3-59-g8ed1b From cc6acc20a606f9ca65a6338af8204b7ae9e67b1a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 19:01:48 +0200 Subject: sunrpc: properly type pc_decode callbacks Drop the argp argument as it can trivially be derived from the rqstp argument. With that all functions now have the same prototype, and we can remove the unsafe casting to kxdrproc_t. Signed-off-by: Christoph Hellwig --- fs/lockd/svc4proc.c | 2 +- fs/lockd/svcproc.c | 2 +- fs/lockd/xdr.c | 29 ++++++++++++------ fs/lockd/xdr4.c | 29 ++++++++++++------ fs/nfs/callback_xdr.c | 4 +-- fs/nfsd/nfs2acl.c | 21 +++++++------ fs/nfsd/nfs3acl.c | 11 +++---- fs/nfsd/nfs3proc.c | 42 +++++++++++++------------- fs/nfsd/nfs3xdr.c | 74 +++++++++++++++++++++++++++------------------- fs/nfsd/nfs4proc.c | 2 +- fs/nfsd/nfs4xdr.c | 4 ++- fs/nfsd/nfsproc.c | 36 +++++++++++----------- fs/nfsd/nfssvc.c | 5 ++-- fs/nfsd/nfsxdr.c | 53 ++++++++++++++++++++------------- fs/nfsd/xdr.h | 34 ++++++++------------- fs/nfsd/xdr3.h | 47 ++++++++++------------------- fs/nfsd/xdr4.h | 3 +- include/linux/lockd/xdr.h | 18 +++++------ include/linux/lockd/xdr4.h | 18 +++++------ include/linux/sunrpc/svc.h | 3 +- net/sunrpc/svc.c | 9 ++++-- 21 files changed, 237 insertions(+), 209 deletions(-) diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 3e4cba029d3d..804744f7528c 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -496,7 +496,7 @@ struct nlm_void { int dummy; }; #define PROC(name, xargt, xrest, argt, rest, respsize) \ { .pc_func = nlm4svc_proc_##name, \ - .pc_decode = (kxdrproc_t) nlm4svc_decode_##xargt, \ + .pc_decode = nlm4svc_decode_##xargt, \ .pc_encode = (kxdrproc_t) nlm4svc_encode_##xrest, \ .pc_release = NULL, \ .pc_argsize = sizeof(struct nlm_##argt), \ diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index 3add50661fab..204a698f7d41 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -538,7 +538,7 @@ struct nlm_void { int dummy; }; #define PROC(name, xargt, xrest, argt, rest, respsize) \ { .pc_func = nlmsvc_proc_##name, \ - .pc_decode = (kxdrproc_t) nlmsvc_decode_##xargt, \ + .pc_decode = nlmsvc_decode_##xargt, \ .pc_encode = (kxdrproc_t) nlmsvc_encode_##xrest, \ .pc_release = NULL, \ .pc_argsize = sizeof(struct nlm_##argt), \ diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c index 5b651daad518..b57af63fba56 100644 --- a/fs/lockd/xdr.c +++ b/fs/lockd/xdr.c @@ -182,8 +182,9 @@ nlm_encode_testres(__be32 *p, struct nlm_res *resp) * First, the server side XDR functions */ int -nlmsvc_decode_testargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlmsvc_decode_testargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!(p = nlm_decode_cookie(p, &argp->cookie))) @@ -207,8 +208,9 @@ nlmsvc_encode_testres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) } int -nlmsvc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlmsvc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!(p = nlm_decode_cookie(p, &argp->cookie))) @@ -227,8 +229,9 @@ nlmsvc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) } int -nlmsvc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlmsvc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!(p = nlm_decode_cookie(p, &argp->cookie))) @@ -243,8 +246,10 @@ nlmsvc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) } int -nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; + if (!(p = nlm_decode_cookie(p, &argp->cookie)) || !(p = nlm_decode_lock(p, &argp->lock))) return 0; @@ -253,8 +258,9 @@ nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) } int -nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; memset(lock, 0, sizeof(*lock)); @@ -293,8 +299,9 @@ nlmsvc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) } int -nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp) +nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; if (!(p = xdr_decode_string_inplace(p, &lock->caller, @@ -305,8 +312,10 @@ nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp) } int -nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp) +nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_reboot *argp = rqstp->rq_argp; + if (!(p = xdr_decode_string_inplace(p, &argp->mon, &argp->len, SM_MAXSTRLEN))) return 0; argp->state = ntohl(*p++); @@ -316,8 +325,10 @@ nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp) } int -nlmsvc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlmsvc_decode_res(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_argp; + if (!(p = nlm_decode_cookie(p, &resp->cookie))) return 0; resp->status = *p++; @@ -325,7 +336,7 @@ nlmsvc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) } int -nlmsvc_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nlmsvc_decode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_argsize_check(rqstp, p); } diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c index dfa4789cd460..46e18598a15c 100644 --- a/fs/lockd/xdr4.c +++ b/fs/lockd/xdr4.c @@ -179,8 +179,9 @@ nlm4_encode_testres(__be32 *p, struct nlm_res *resp) * First, the server side XDR functions */ int -nlm4svc_decode_testargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlm4svc_decode_testargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!(p = nlm4_decode_cookie(p, &argp->cookie))) @@ -204,8 +205,9 @@ nlm4svc_encode_testres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) } int -nlm4svc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlm4svc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!(p = nlm4_decode_cookie(p, &argp->cookie))) @@ -224,8 +226,9 @@ nlm4svc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) } int -nlm4svc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlm4svc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!(p = nlm4_decode_cookie(p, &argp->cookie))) @@ -240,8 +243,10 @@ nlm4svc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) } int -nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; + if (!(p = nlm4_decode_cookie(p, &argp->cookie)) || !(p = nlm4_decode_lock(p, &argp->lock))) return 0; @@ -250,8 +255,9 @@ nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) } int -nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; memset(lock, 0, sizeof(*lock)); @@ -290,8 +296,9 @@ nlm4svc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) } int -nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp) +nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; if (!(p = xdr_decode_string_inplace(p, &lock->caller, @@ -302,8 +309,10 @@ nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp) } int -nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp) +nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_reboot *argp = rqstp->rq_argp; + if (!(p = xdr_decode_string_inplace(p, &argp->mon, &argp->len, SM_MAXSTRLEN))) return 0; argp->state = ntohl(*p++); @@ -313,8 +322,10 @@ nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp } int -nlm4svc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlm4svc_decode_res(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_argp; + if (!(p = nlm4_decode_cookie(p, &resp->cookie))) return 0; resp->status = *p++; @@ -322,7 +333,7 @@ nlm4svc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) } int -nlm4svc_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nlm4svc_decode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_argsize_check(rqstp, p); } diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 5a14bdaa5986..23ecbf7a40c1 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -58,7 +58,7 @@ static __be32 nfs4_callback_null(struct svc_rqst *rqstp) return htonl(NFS4_OK); } -static int nfs4_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +static int nfs4_decode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_argsize_check(rqstp, p); } @@ -998,7 +998,7 @@ static struct callback_op callback_ops[] = { static struct svc_procedure nfs4_callback_procedures1[] = { [CB_NULL] = { .pc_func = nfs4_callback_null, - .pc_decode = (kxdrproc_t)nfs4_decode_void, + .pc_decode = nfs4_decode_void, .pc_encode = (kxdrproc_t)nfs4_encode_void, .pc_xdrressize = 1, }, diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 302441027f50..bcfdaa83ee6c 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -182,9 +182,10 @@ static __be32 nfsacld_proc_access(struct svc_rqst *rqstp) /* * XDR decode functions */ -static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_getaclargs *argp) +static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_getaclargs *argp = rqstp->rq_argp; + p = nfs2svc_decode_fh(p, &argp->fh); if (!p) return 0; @@ -194,9 +195,9 @@ static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p, } -static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_setaclargs *argp) +static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_setaclargs *argp = rqstp->rq_argp; struct kvec *head = rqstp->rq_arg.head; unsigned int base; int n; @@ -220,18 +221,20 @@ static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p, return (n > 0); } -static int nfsaclsvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_fhandle *argp) +static int nfsaclsvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + p = nfs2svc_decode_fh(p, &argp->fh); if (!p) return 0; return xdr_argsize_check(rqstp, p); } -static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_accessargs *argp) +static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_accessargs *argp = rqstp->rq_argp; + p = nfs2svc_decode_fh(p, &argp->fh); if (!p) return 0; @@ -351,7 +354,7 @@ struct nfsd3_voidargs { int dummy; }; #define PROC(name, argt, rest, relt, cache, respsize) \ { \ .pc_func = nfsacld_proc_##name, \ - .pc_decode = (kxdrproc_t) nfsaclsvc_decode_##argt##args, \ + .pc_decode = nfsaclsvc_decode_##argt##args, \ .pc_encode = (kxdrproc_t) nfsaclsvc_encode_##rest##res, \ .pc_release = nfsaclsvc_release_##relt, \ .pc_argsize = sizeof(struct nfsd3_##argt##args), \ diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 56cdff4e954c..4e68d6b5f409 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -124,9 +124,10 @@ out: /* * XDR decode functions */ -static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_getaclargs *args) +static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_getaclargs *args = rqstp->rq_argp; + p = nfs3svc_decode_fh(p, &args->fh); if (!p) return 0; @@ -136,9 +137,9 @@ static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p, } -static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_setaclargs *args) +static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_setaclargs *args = rqstp->rq_argp; struct kvec *head = rqstp->rq_arg.head; unsigned int base; int n; @@ -241,7 +242,7 @@ struct nfsd3_voidargs { int dummy; }; #define PROC(name, argt, rest, relt, cache, respsize) \ { \ .pc_func = nfsd3_proc_##name, \ - .pc_decode = (kxdrproc_t) nfs3svc_decode_##argt##args, \ + .pc_decode = nfs3svc_decode_##argt##args, \ .pc_encode = (kxdrproc_t) nfs3svc_encode_##rest##res, \ .pc_release = nfs3svc_release_##relt, \ .pc_argsize = sizeof(struct nfsd3_##argt##args), \ diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index f0cccc0768ce..ed83e8a9e7b4 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -685,7 +685,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_GETATTR] = { .pc_func = nfsd3_proc_getattr, - .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs, + .pc_decode = nfs3svc_decode_fhandleargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_attrstatres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_fhandleargs), @@ -695,7 +695,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_SETATTR] = { .pc_func = nfsd3_proc_setattr, - .pc_decode = (kxdrproc_t) nfs3svc_decode_sattrargs, + .pc_decode = nfs3svc_decode_sattrargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_sattrargs), @@ -705,7 +705,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_LOOKUP] = { .pc_func = nfsd3_proc_lookup, - .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs, + .pc_decode = nfs3svc_decode_diropargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_diropres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_diropargs), @@ -715,7 +715,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_ACCESS] = { .pc_func = nfsd3_proc_access, - .pc_decode = (kxdrproc_t) nfs3svc_decode_accessargs, + .pc_decode = nfs3svc_decode_accessargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_accessres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_accessargs), @@ -725,7 +725,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_READLINK] = { .pc_func = nfsd3_proc_readlink, - .pc_decode = (kxdrproc_t) nfs3svc_decode_readlinkargs, + .pc_decode = nfs3svc_decode_readlinkargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readlinkres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readlinkargs), @@ -735,7 +735,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_READ] = { .pc_func = nfsd3_proc_read, - .pc_decode = (kxdrproc_t) nfs3svc_decode_readargs, + .pc_decode = nfs3svc_decode_readargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readargs), @@ -745,7 +745,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_WRITE] = { .pc_func = nfsd3_proc_write, - .pc_decode = (kxdrproc_t) nfs3svc_decode_writeargs, + .pc_decode = nfs3svc_decode_writeargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_writeres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_writeargs), @@ -755,7 +755,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_CREATE] = { .pc_func = nfsd3_proc_create, - .pc_decode = (kxdrproc_t) nfs3svc_decode_createargs, + .pc_decode = nfs3svc_decode_createargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_createargs), @@ -765,7 +765,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_MKDIR] = { .pc_func = nfsd3_proc_mkdir, - .pc_decode = (kxdrproc_t) nfs3svc_decode_mkdirargs, + .pc_decode = nfs3svc_decode_mkdirargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_mkdirargs), @@ -775,7 +775,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_SYMLINK] = { .pc_func = nfsd3_proc_symlink, - .pc_decode = (kxdrproc_t) nfs3svc_decode_symlinkargs, + .pc_decode = nfs3svc_decode_symlinkargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_symlinkargs), @@ -785,7 +785,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_MKNOD] = { .pc_func = nfsd3_proc_mknod, - .pc_decode = (kxdrproc_t) nfs3svc_decode_mknodargs, + .pc_decode = nfs3svc_decode_mknodargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_mknodargs), @@ -795,7 +795,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_REMOVE] = { .pc_func = nfsd3_proc_remove, - .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs, + .pc_decode = nfs3svc_decode_diropargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_diropargs), @@ -805,7 +805,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_RMDIR] = { .pc_func = nfsd3_proc_rmdir, - .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs, + .pc_decode = nfs3svc_decode_diropargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_diropargs), @@ -815,7 +815,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_RENAME] = { .pc_func = nfsd3_proc_rename, - .pc_decode = (kxdrproc_t) nfs3svc_decode_renameargs, + .pc_decode = nfs3svc_decode_renameargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_renameres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_renameargs), @@ -825,7 +825,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_LINK] = { .pc_func = nfsd3_proc_link, - .pc_decode = (kxdrproc_t) nfs3svc_decode_linkargs, + .pc_decode = nfs3svc_decode_linkargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_linkres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_linkargs), @@ -835,7 +835,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_READDIR] = { .pc_func = nfsd3_proc_readdir, - .pc_decode = (kxdrproc_t) nfs3svc_decode_readdirargs, + .pc_decode = nfs3svc_decode_readdirargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readdirargs), @@ -844,7 +844,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_READDIRPLUS] = { .pc_func = nfsd3_proc_readdirplus, - .pc_decode = (kxdrproc_t) nfs3svc_decode_readdirplusargs, + .pc_decode = nfs3svc_decode_readdirplusargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readdirplusargs), @@ -853,7 +853,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_FSSTAT] = { .pc_func = nfsd3_proc_fsstat, - .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs, + .pc_decode = nfs3svc_decode_fhandleargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_fsstatres, .pc_argsize = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_fsstatres), @@ -862,7 +862,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_FSINFO] = { .pc_func = nfsd3_proc_fsinfo, - .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs, + .pc_decode = nfs3svc_decode_fhandleargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_fsinfores, .pc_argsize = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_fsinfores), @@ -871,7 +871,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_PATHCONF] = { .pc_func = nfsd3_proc_pathconf, - .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs, + .pc_decode = nfs3svc_decode_fhandleargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_pathconfres, .pc_argsize = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_pathconfres), @@ -880,7 +880,7 @@ static struct svc_procedure nfsd_procedures3[22] = { }, [NFS3PROC_COMMIT] = { .pc_func = nfsd3_proc_commit, - .pc_decode = (kxdrproc_t) nfs3svc_decode_commitargs, + .pc_decode = nfs3svc_decode_commitargs, .pc_encode = (kxdrproc_t) nfs3svc_encode_commitres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_commitargs), diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index c3d3ef28347c..c56089ac2819 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -273,8 +273,10 @@ void fill_post_wcc(struct svc_fh *fhp) * XDR decode functions */ int -nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *args) +nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_fhandle *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; @@ -282,9 +284,10 @@ nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *a } int -nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_sattrargs *args) +nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_sattrargs *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; @@ -300,9 +303,10 @@ nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_diropargs *args) +nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_diropargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->fh)) || !(p = decode_filename(p, &args->name, &args->len))) return 0; @@ -311,9 +315,10 @@ nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_accessargs *args) +nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_accessargs *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; @@ -323,9 +328,9 @@ nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_readargs *args) +nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_readargs *args = rqstp->rq_argp; unsigned int len; int v; u32 max_blocksize = svc_max_payload(rqstp); @@ -353,9 +358,9 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_writeargs *args) +nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_writeargs *args = rqstp->rq_argp; unsigned int len, v, hdr, dlen; u32 max_blocksize = svc_max_payload(rqstp); struct kvec *head = rqstp->rq_arg.head; @@ -413,9 +418,10 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_createargs *args) +nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_createargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->fh)) || !(p = decode_filename(p, &args->name, &args->len))) return 0; @@ -435,10 +441,12 @@ nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p, return xdr_argsize_check(rqstp, p); } + int -nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_createargs *args) +nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_createargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->fh)) || !(p = decode_filename(p, &args->name, &args->len))) return 0; @@ -448,9 +456,9 @@ nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_symlinkargs *args) +nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_symlinkargs *args = rqstp->rq_argp; unsigned int len, avail; char *old, *new; struct kvec *vec; @@ -500,9 +508,10 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_mknodargs *args) +nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_mknodargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->fh)) || !(p = decode_filename(p, &args->name, &args->len))) return 0; @@ -522,9 +531,10 @@ nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_renameargs *args) +nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_renameargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->ffh)) || !(p = decode_filename(p, &args->fname, &args->flen)) || !(p = decode_fh(p, &args->tfh)) @@ -535,9 +545,10 @@ nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_readlinkargs *args) +nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_readlinkargs *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; @@ -547,9 +558,10 @@ nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_linkargs *args) +nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_linkargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->ffh)) || !(p = decode_fh(p, &args->tfh)) || !(p = decode_filename(p, &args->tname, &args->tlen))) @@ -559,9 +571,9 @@ nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_readdirargs *args) +nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_readdirargs *args = rqstp->rq_argp; p = decode_fh(p, &args->fh); if (!p) return 0; @@ -576,9 +588,9 @@ nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_readdirargs *args) +nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_readdirargs *args = rqstp->rq_argp; int len; u32 max_blocksize = svc_max_payload(rqstp); @@ -602,9 +614,9 @@ nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_commitargs *args) +nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_commitargs *args = rqstp->rq_argp; p = decode_fh(p, &args->fh); if (!p) return 0; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 43b2e5ab4430..19c7d4b989c4 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -2527,7 +2527,7 @@ static struct svc_procedure nfsd_procedures4[2] = { }, [NFSPROC4_COMPOUND] = { .pc_func = nfsd4_proc_compound, - .pc_decode = (kxdrproc_t) nfs4svc_decode_compoundargs, + .pc_decode = nfs4svc_decode_compoundargs, .pc_encode = (kxdrproc_t) nfs4svc_encode_compoundres, .pc_argsize = sizeof(struct nfsd4_compoundargs), .pc_ressize = sizeof(struct nfsd4_compoundres), diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 5aa847bdfc63..3a7e117bd11e 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -4561,8 +4561,10 @@ void nfsd4_release_compoundargs(struct svc_rqst *rqstp) } int -nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compoundargs *args) +nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd4_compoundargs *args = rqstp->rq_argp; + if (rqstp->rq_arg.head[0].iov_len % 4) { /* client is nuts */ dprintk("%s: compound not properly padded! (peeraddr=%pISc xid=0x%x)", diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index dc32e0f8480d..d351d0ef6d34 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -576,7 +576,7 @@ struct nfsd_void { int dummy; }; static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_NULL] = { .pc_func = nfsd_proc_null, - .pc_decode = (kxdrproc_t) nfssvc_decode_void, + .pc_decode = nfssvc_decode_void, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_void), .pc_ressize = sizeof(struct nfsd_void), @@ -585,7 +585,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_GETATTR] = { .pc_func = nfsd_proc_getattr, - .pc_decode = (kxdrproc_t) nfssvc_decode_fhandle, + .pc_decode = nfssvc_decode_fhandle, .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_fhandle), @@ -595,7 +595,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_SETATTR] = { .pc_func = nfsd_proc_setattr, - .pc_decode = (kxdrproc_t) nfssvc_decode_sattrargs, + .pc_decode = nfssvc_decode_sattrargs, .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_sattrargs), @@ -604,7 +604,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST+AT, }, [NFSPROC_ROOT] = { - .pc_decode = (kxdrproc_t) nfssvc_decode_void, + .pc_decode = nfssvc_decode_void, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_void), .pc_ressize = sizeof(struct nfsd_void), @@ -613,7 +613,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_LOOKUP] = { .pc_func = nfsd_proc_lookup, - .pc_decode = (kxdrproc_t) nfssvc_decode_diropargs, + .pc_decode = nfssvc_decode_diropargs, .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_diropargs), @@ -623,7 +623,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_READLINK] = { .pc_func = nfsd_proc_readlink, - .pc_decode = (kxdrproc_t) nfssvc_decode_readlinkargs, + .pc_decode = nfssvc_decode_readlinkargs, .pc_encode = (kxdrproc_t) nfssvc_encode_readlinkres, .pc_argsize = sizeof(struct nfsd_readlinkargs), .pc_ressize = sizeof(struct nfsd_readlinkres), @@ -632,7 +632,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_READ] = { .pc_func = nfsd_proc_read, - .pc_decode = (kxdrproc_t) nfssvc_decode_readargs, + .pc_decode = nfssvc_decode_readargs, .pc_encode = (kxdrproc_t) nfssvc_encode_readres, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_readargs), @@ -641,7 +641,7 @@ static struct svc_procedure nfsd_procedures2[18] = { .pc_xdrressize = ST+AT+1+NFSSVC_MAXBLKSIZE_V2/4, }, [NFSPROC_WRITECACHE] = { - .pc_decode = (kxdrproc_t) nfssvc_decode_void, + .pc_decode = nfssvc_decode_void, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_void), .pc_ressize = sizeof(struct nfsd_void), @@ -650,7 +650,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_WRITE] = { .pc_func = nfsd_proc_write, - .pc_decode = (kxdrproc_t) nfssvc_decode_writeargs, + .pc_decode = nfssvc_decode_writeargs, .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_writeargs), @@ -660,7 +660,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_CREATE] = { .pc_func = nfsd_proc_create, - .pc_decode = (kxdrproc_t) nfssvc_decode_createargs, + .pc_decode = nfssvc_decode_createargs, .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_createargs), @@ -670,7 +670,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_REMOVE] = { .pc_func = nfsd_proc_remove, - .pc_decode = (kxdrproc_t) nfssvc_decode_diropargs, + .pc_decode = nfssvc_decode_diropargs, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_diropargs), .pc_ressize = sizeof(struct nfsd_void), @@ -679,7 +679,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_RENAME] = { .pc_func = nfsd_proc_rename, - .pc_decode = (kxdrproc_t) nfssvc_decode_renameargs, + .pc_decode = nfssvc_decode_renameargs, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_renameargs), .pc_ressize = sizeof(struct nfsd_void), @@ -688,7 +688,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_LINK] = { .pc_func = nfsd_proc_link, - .pc_decode = (kxdrproc_t) nfssvc_decode_linkargs, + .pc_decode = nfssvc_decode_linkargs, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_linkargs), .pc_ressize = sizeof(struct nfsd_void), @@ -697,7 +697,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_SYMLINK] = { .pc_func = nfsd_proc_symlink, - .pc_decode = (kxdrproc_t) nfssvc_decode_symlinkargs, + .pc_decode = nfssvc_decode_symlinkargs, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_symlinkargs), .pc_ressize = sizeof(struct nfsd_void), @@ -706,7 +706,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_MKDIR] = { .pc_func = nfsd_proc_mkdir, - .pc_decode = (kxdrproc_t) nfssvc_decode_createargs, + .pc_decode = nfssvc_decode_createargs, .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_createargs), @@ -716,7 +716,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_RMDIR] = { .pc_func = nfsd_proc_rmdir, - .pc_decode = (kxdrproc_t) nfssvc_decode_diropargs, + .pc_decode = nfssvc_decode_diropargs, .pc_encode = (kxdrproc_t) nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_diropargs), .pc_ressize = sizeof(struct nfsd_void), @@ -725,7 +725,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_READDIR] = { .pc_func = nfsd_proc_readdir, - .pc_decode = (kxdrproc_t) nfssvc_decode_readdirargs, + .pc_decode = nfssvc_decode_readdirargs, .pc_encode = (kxdrproc_t) nfssvc_encode_readdirres, .pc_argsize = sizeof(struct nfsd_readdirargs), .pc_ressize = sizeof(struct nfsd_readdirres), @@ -733,7 +733,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_STATFS] = { .pc_func = nfsd_proc_statfs, - .pc_decode = (kxdrproc_t) nfssvc_decode_fhandle, + .pc_decode = nfssvc_decode_fhandle, .pc_encode = (kxdrproc_t) nfssvc_encode_statfsres, .pc_argsize = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd_statfsres), diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index d64895fd8d25..3e00499d7ad7 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -801,9 +801,8 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) */ rqstp->rq_cachetype = proc->pc_cachetype; /* Decode arguments */ - xdr = proc->pc_decode; - if (xdr && !xdr(rqstp, (__be32*)rqstp->rq_arg.head[0].iov_base, - rqstp->rq_argp)) { + if (proc->pc_decode && + !proc->pc_decode(rqstp, (__be32*)rqstp->rq_arg.head[0].iov_base)) { dprintk("nfsd: failed to decode arguments!\n"); *statp = rpc_garbage_args; return 1; diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index 2facfc6ac8f3..19cf04ebf388 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -206,14 +206,16 @@ __be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *f * XDR decode functions */ int -nfssvc_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nfssvc_decode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_argsize_check(rqstp, p); } int -nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *args) +nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_fhandle *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; @@ -221,9 +223,10 @@ nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *ar } int -nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_sattrargs *args) +nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_sattrargs *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; @@ -233,9 +236,10 @@ nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_diropargs *args) +nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_diropargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->fh)) || !(p = decode_filename(p, &args->name, &args->len))) return 0; @@ -244,9 +248,9 @@ nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_readargs *args) +nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_readargs *args = rqstp->rq_argp; unsigned int len; int v; p = decode_fh(p, &args->fh); @@ -276,9 +280,9 @@ nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_writeargs *args) +nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_writeargs *args = rqstp->rq_argp; unsigned int len, hdr, dlen; struct kvec *head = rqstp->rq_arg.head; int v; @@ -332,9 +336,10 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_createargs *args) +nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_createargs *args = rqstp->rq_argp; + if ( !(p = decode_fh(p, &args->fh)) || !(p = decode_filename(p, &args->name, &args->len))) return 0; @@ -344,9 +349,10 @@ nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_renameargs *args) +nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_renameargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->ffh)) || !(p = decode_filename(p, &args->fname, &args->flen)) || !(p = decode_fh(p, &args->tfh)) @@ -357,8 +363,10 @@ nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readlinkargs *args) +nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_readlinkargs *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; @@ -368,9 +376,10 @@ nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readli } int -nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_linkargs *args) +nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_linkargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->ffh)) || !(p = decode_fh(p, &args->tfh)) || !(p = decode_filename(p, &args->tname, &args->tlen))) @@ -380,9 +389,10 @@ nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_symlinkargs *args) +nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_symlinkargs *args = rqstp->rq_argp; + if ( !(p = decode_fh(p, &args->ffh)) || !(p = decode_filename(p, &args->fname, &args->flen)) || !(p = decode_pathname(p, &args->tname, &args->tlen))) @@ -393,9 +403,10 @@ nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_readdirargs *args) +nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_readdirargs *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h index 2c21fa843fbf..8eeb752cf6f8 100644 --- a/fs/nfsd/xdr.h +++ b/fs/nfsd/xdr.h @@ -131,28 +131,18 @@ union nfsd_xdrstore { #define NFS2_SVC_XDRSIZE sizeof(union nfsd_xdrstore) -int nfssvc_decode_void(struct svc_rqst *, __be32 *, void *); -int nfssvc_decode_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *); -int nfssvc_decode_sattrargs(struct svc_rqst *, __be32 *, - struct nfsd_sattrargs *); -int nfssvc_decode_diropargs(struct svc_rqst *, __be32 *, - struct nfsd_diropargs *); -int nfssvc_decode_readargs(struct svc_rqst *, __be32 *, - struct nfsd_readargs *); -int nfssvc_decode_writeargs(struct svc_rqst *, __be32 *, - struct nfsd_writeargs *); -int nfssvc_decode_createargs(struct svc_rqst *, __be32 *, - struct nfsd_createargs *); -int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *, - struct nfsd_renameargs *); -int nfssvc_decode_readlinkargs(struct svc_rqst *, __be32 *, - struct nfsd_readlinkargs *); -int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *, - struct nfsd_linkargs *); -int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *, - struct nfsd_symlinkargs *); -int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *, - struct nfsd_readdirargs *); +int nfssvc_decode_void(struct svc_rqst *, __be32 *); +int nfssvc_decode_fhandle(struct svc_rqst *, __be32 *); +int nfssvc_decode_sattrargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_diropargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_readargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_writeargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_createargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_readlinkargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *); int nfssvc_encode_void(struct svc_rqst *, __be32 *, void *); int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *, struct nfsd_attrstat *); int nfssvc_encode_diropres(struct svc_rqst *, __be32 *, struct nfsd_diropres *); diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h index 23fe456a223b..f79be4c42e4a 100644 --- a/fs/nfsd/xdr3.h +++ b/fs/nfsd/xdr3.h @@ -269,37 +269,22 @@ union nfsd3_xdrstore { #define NFS3_SVC_XDRSIZE sizeof(union nfsd3_xdrstore) -int nfs3svc_decode_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *); -int nfs3svc_decode_sattrargs(struct svc_rqst *, __be32 *, - struct nfsd3_sattrargs *); -int nfs3svc_decode_diropargs(struct svc_rqst *, __be32 *, - struct nfsd3_diropargs *); -int nfs3svc_decode_accessargs(struct svc_rqst *, __be32 *, - struct nfsd3_accessargs *); -int nfs3svc_decode_readargs(struct svc_rqst *, __be32 *, - struct nfsd3_readargs *); -int nfs3svc_decode_writeargs(struct svc_rqst *, __be32 *, - struct nfsd3_writeargs *); -int nfs3svc_decode_createargs(struct svc_rqst *, __be32 *, - struct nfsd3_createargs *); -int nfs3svc_decode_mkdirargs(struct svc_rqst *, __be32 *, - struct nfsd3_createargs *); -int nfs3svc_decode_mknodargs(struct svc_rqst *, __be32 *, - struct nfsd3_mknodargs *); -int nfs3svc_decode_renameargs(struct svc_rqst *, __be32 *, - struct nfsd3_renameargs *); -int nfs3svc_decode_readlinkargs(struct svc_rqst *, __be32 *, - struct nfsd3_readlinkargs *); -int nfs3svc_decode_linkargs(struct svc_rqst *, __be32 *, - struct nfsd3_linkargs *); -int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *, - struct nfsd3_symlinkargs *); -int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *, - struct nfsd3_readdirargs *); -int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *, - struct nfsd3_readdirargs *); -int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *, - struct nfsd3_commitargs *); +int nfs3svc_decode_fhandle(struct svc_rqst *, __be32 *); +int nfs3svc_decode_sattrargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_diropargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_accessargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_readargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_writeargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_createargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_mkdirargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_mknodargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_renameargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_readlinkargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_linkargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *); int nfs3svc_encode_voidres(struct svc_rqst *, __be32 *, void *); int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *, struct nfsd3_attrstat *); diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index a158579d55a2..2a53c1233884 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -683,8 +683,7 @@ set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp) bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp); int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *, void *); -int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *, - struct nfsd4_compoundargs *); +int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *); int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *, struct nfsd4_compoundres *); __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32); diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index d39ed1cc5fbf..0416600844ce 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -95,19 +95,19 @@ struct nlm_reboot { */ #define NLMSVC_XDRSIZE sizeof(struct nlm_args) -int nlmsvc_decode_testargs(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlmsvc_decode_testargs(struct svc_rqst *, __be32 *); int nlmsvc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlmsvc_decode_lockargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_decode_cancargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_decode_unlockargs(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlmsvc_decode_lockargs(struct svc_rqst *, __be32 *); +int nlmsvc_decode_cancargs(struct svc_rqst *, __be32 *); +int nlmsvc_decode_unlockargs(struct svc_rqst *, __be32 *); int nlmsvc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlmsvc_decode_res(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlmsvc_decode_res(struct svc_rqst *, __be32 *); int nlmsvc_encode_void(struct svc_rqst *, __be32 *, void *); -int nlmsvc_decode_void(struct svc_rqst *, __be32 *, void *); -int nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlmsvc_decode_void(struct svc_rqst *, __be32 *); +int nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *); int nlmsvc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlmsvc_decode_notify(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_decode_reboot(struct svc_rqst *, __be32 *, struct nlm_reboot *); +int nlmsvc_decode_notify(struct svc_rqst *, __be32 *); +int nlmsvc_decode_reboot(struct svc_rqst *, __be32 *); /* int nlmclt_encode_testargs(struct rpc_rqst *, u32 *, struct nlm_args *); int nlmclt_encode_lockargs(struct rpc_rqst *, u32 *, struct nlm_args *); diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index e58c88b52ce1..951bbe31fdb8 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -23,19 +23,19 @@ -int nlm4svc_decode_testargs(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlm4svc_decode_testargs(struct svc_rqst *, __be32 *); int nlm4svc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlm4svc_decode_lockargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_decode_cancargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_decode_unlockargs(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlm4svc_decode_lockargs(struct svc_rqst *, __be32 *); +int nlm4svc_decode_cancargs(struct svc_rqst *, __be32 *); +int nlm4svc_decode_unlockargs(struct svc_rqst *, __be32 *); int nlm4svc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlm4svc_decode_res(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlm4svc_decode_res(struct svc_rqst *, __be32 *); int nlm4svc_encode_void(struct svc_rqst *, __be32 *, void *); -int nlm4svc_decode_void(struct svc_rqst *, __be32 *, void *); -int nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *, struct nlm_args *); +int nlm4svc_decode_void(struct svc_rqst *, __be32 *); +int nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *); int nlm4svc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlm4svc_decode_notify(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_decode_reboot(struct svc_rqst *, __be32 *, struct nlm_reboot *); +int nlm4svc_decode_notify(struct svc_rqst *, __be32 *); +int nlm4svc_decode_reboot(struct svc_rqst *, __be32 *); /* int nlmclt_encode_testargs(struct rpc_rqst *, u32 *, struct nlm_args *); int nlmclt_encode_lockargs(struct rpc_rqst *, u32 *, struct nlm_args *); diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index c73194e9c2bd..d8703a5ab81e 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -422,7 +422,8 @@ struct svc_version { struct svc_procedure { /* process the request: */ __be32 (*pc_func)(struct svc_rqst *); - kxdrproc_t pc_decode; /* XDR decode args */ + /* XDR decode args: */ + int (*pc_decode)(struct svc_rqst *, __be32 *data); kxdrproc_t pc_encode; /* XDR encode result */ /* XDR free result: */ void (*pc_release)(struct svc_rqst *); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 4611cb7adc04..18024c1b9b7b 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1276,9 +1276,12 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) /* Call the function that processes the request. */ if (!versp->vs_dispatch) { - /* Decode arguments */ - xdr = procp->pc_decode; - if (xdr && !xdr(rqstp, argv->iov_base, rqstp->rq_argp)) + /* + * Decode arguments + * XXX: why do we ignore the return value? + */ + if (procp->pc_decode && + !procp->pc_decode(rqstp, argv->iov_base)) goto err_garbage; *statp = procp->pc_func(rqstp); -- cgit v1.2.3-59-g8ed1b From d16d1867215663907f3212590d1a9d32398a0f47 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 19:42:02 +0200 Subject: sunrpc: properly type pc_encode callbacks Drop the resp argument as it can trivially be derived from the rqstp argument. With that all functions now have the same prototype, and we can remove the unsafe casting to kxdrproc_t. Signed-off-by: Christoph Hellwig Acked-by: Trond Myklebust --- fs/lockd/svc4proc.c | 2 +- fs/lockd/svcproc.c | 2 +- fs/lockd/xdr.c | 14 ++++++--- fs/lockd/xdr4.c | 14 ++++++--- fs/nfs/callback_xdr.c | 6 ++-- fs/nfsd/nfs2acl.c | 18 ++++++----- fs/nfsd/nfs3acl.c | 11 +++---- fs/nfsd/nfs3proc.c | 44 +++++++++++++-------------- fs/nfsd/nfs3xdr.c | 74 +++++++++++++++++++++++++++------------------- fs/nfsd/nfs4proc.c | 4 +-- fs/nfsd/nfs4xdr.c | 5 ++-- fs/nfsd/nfsproc.c | 36 +++++++++++----------- fs/nfsd/nfssvc.c | 5 +--- fs/nfsd/nfsxdr.c | 31 +++++++++++-------- fs/nfsd/xdr.h | 14 ++++----- fs/nfsd/xdr3.h | 45 ++++++++++------------------ fs/nfsd/xdr4.h | 5 ++-- include/linux/lockd/xdr.h | 8 ++--- include/linux/lockd/xdr4.h | 8 ++--- include/linux/sunrpc/svc.h | 3 +- net/sunrpc/svc.c | 6 ++-- 21 files changed, 185 insertions(+), 170 deletions(-) diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 804744f7528c..fed016155791 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -497,7 +497,7 @@ struct nlm_void { int dummy; }; #define PROC(name, xargt, xrest, argt, rest, respsize) \ { .pc_func = nlm4svc_proc_##name, \ .pc_decode = nlm4svc_decode_##xargt, \ - .pc_encode = (kxdrproc_t) nlm4svc_encode_##xrest, \ + .pc_encode = nlm4svc_encode_##xrest, \ .pc_release = NULL, \ .pc_argsize = sizeof(struct nlm_##argt), \ .pc_ressize = sizeof(struct nlm_##rest), \ diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index 204a698f7d41..14648b051eba 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -539,7 +539,7 @@ struct nlm_void { int dummy; }; #define PROC(name, xargt, xrest, argt, rest, respsize) \ { .pc_func = nlmsvc_proc_##name, \ .pc_decode = nlmsvc_decode_##xargt, \ - .pc_encode = (kxdrproc_t) nlmsvc_encode_##xrest, \ + .pc_encode = nlmsvc_encode_##xrest, \ .pc_release = NULL, \ .pc_argsize = sizeof(struct nlm_##argt), \ .pc_ressize = sizeof(struct nlm_##rest), \ diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c index b57af63fba56..442bbd0b0b29 100644 --- a/fs/lockd/xdr.c +++ b/fs/lockd/xdr.c @@ -200,8 +200,10 @@ nlmsvc_decode_testargs(struct svc_rqst *rqstp, __be32 *p) } int -nlmsvc_encode_testres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlmsvc_encode_testres(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_resp; + if (!(p = nlm_encode_testres(p, resp))) return 0; return xdr_ressize_check(rqstp, p); @@ -280,8 +282,10 @@ nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) } int -nlmsvc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlmsvc_encode_shareres(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_resp; + if (!(p = nlm_encode_cookie(p, &resp->cookie))) return 0; *p++ = resp->status; @@ -290,8 +294,10 @@ nlmsvc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) } int -nlmsvc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlmsvc_encode_res(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_resp; + if (!(p = nlm_encode_cookie(p, &resp->cookie))) return 0; *p++ = resp->status; @@ -342,7 +348,7 @@ nlmsvc_decode_void(struct svc_rqst *rqstp, __be32 *p) } int -nlmsvc_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nlmsvc_encode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_ressize_check(rqstp, p); } diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c index 46e18598a15c..2a0cd5679c49 100644 --- a/fs/lockd/xdr4.c +++ b/fs/lockd/xdr4.c @@ -197,8 +197,10 @@ nlm4svc_decode_testargs(struct svc_rqst *rqstp, __be32 *p) } int -nlm4svc_encode_testres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlm4svc_encode_testres(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_resp; + if (!(p = nlm4_encode_testres(p, resp))) return 0; return xdr_ressize_check(rqstp, p); @@ -277,8 +279,10 @@ nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) } int -nlm4svc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlm4svc_encode_shareres(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_resp; + if (!(p = nlm4_encode_cookie(p, &resp->cookie))) return 0; *p++ = resp->status; @@ -287,8 +291,10 @@ nlm4svc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) } int -nlm4svc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlm4svc_encode_res(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_resp; + if (!(p = nlm4_encode_cookie(p, &resp->cookie))) return 0; *p++ = resp->status; @@ -339,7 +345,7 @@ nlm4svc_decode_void(struct svc_rqst *rqstp, __be32 *p) } int -nlm4svc_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nlm4svc_encode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_ressize_check(rqstp, p); } diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 23ecbf7a40c1..acf75dc63e14 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -63,7 +63,7 @@ static int nfs4_decode_void(struct svc_rqst *rqstp, __be32 *p) return xdr_argsize_check(rqstp, p); } -static int nfs4_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +static int nfs4_encode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_ressize_check(rqstp, p); } @@ -999,12 +999,12 @@ static struct svc_procedure nfs4_callback_procedures1[] = { [CB_NULL] = { .pc_func = nfs4_callback_null, .pc_decode = nfs4_decode_void, - .pc_encode = (kxdrproc_t)nfs4_encode_void, + .pc_encode = nfs4_encode_void, .pc_xdrressize = 1, }, [CB_COMPOUND] = { .pc_func = nfs4_callback_compound, - .pc_encode = (kxdrproc_t)nfs4_encode_void, + .pc_encode = nfs4_encode_void, .pc_argsize = 256, .pc_ressize = 256, .pc_xdrressize = NFS4_CALLBACK_BUFSIZE, diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index bcfdaa83ee6c..fc6b179c8fff 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -251,15 +251,15 @@ static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p) * There must be an encoding function for void results so svc_process * will work properly. */ -static int nfsaclsvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy) +static int nfsaclsvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p) { return xdr_ressize_check(rqstp, p); } /* GETACL */ -static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_getaclres *resp) +static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_getaclres *resp = rqstp->rq_resp; struct dentry *dentry = resp->fh.fh_dentry; struct inode *inode; struct kvec *head = rqstp->rq_res.head; @@ -302,17 +302,19 @@ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p, return (n > 0); } -static int nfsaclsvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_attrstat *resp) +static int nfsaclsvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_attrstat *resp = rqstp->rq_resp; + p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat); return xdr_ressize_check(rqstp, p); } /* ACCESS */ -static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_accessres *resp) +static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_accessres *resp = rqstp->rq_resp; + p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat); *p++ = htonl(resp->access); return xdr_ressize_check(rqstp, p); @@ -355,7 +357,7 @@ struct nfsd3_voidargs { int dummy; }; { \ .pc_func = nfsacld_proc_##name, \ .pc_decode = nfsaclsvc_decode_##argt##args, \ - .pc_encode = (kxdrproc_t) nfsaclsvc_encode_##rest##res, \ + .pc_encode = nfsaclsvc_encode_##rest##res, \ .pc_release = nfsaclsvc_release_##relt, \ .pc_argsize = sizeof(struct nfsd3_##argt##args), \ .pc_ressize = sizeof(struct nfsd3_##rest##res), \ diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 4e68d6b5f409..9437b758cbfd 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -168,9 +168,9 @@ static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p) */ /* GETACL */ -static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_getaclres *resp) +static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_getaclres *resp = rqstp->rq_resp; struct dentry *dentry = resp->fh.fh_dentry; p = nfs3svc_encode_post_op_attr(rqstp, p, &resp->fh); @@ -213,9 +213,10 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p, } /* SETACL */ -static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_attrstat *resp) +static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_attrstat *resp = rqstp->rq_resp; + p = nfs3svc_encode_post_op_attr(rqstp, p, &resp->fh); return xdr_ressize_check(rqstp, p); @@ -243,7 +244,7 @@ struct nfsd3_voidargs { int dummy; }; { \ .pc_func = nfsd3_proc_##name, \ .pc_decode = nfs3svc_decode_##argt##args, \ - .pc_encode = (kxdrproc_t) nfs3svc_encode_##rest##res, \ + .pc_encode = nfs3svc_encode_##rest##res, \ .pc_release = nfs3svc_release_##relt, \ .pc_argsize = sizeof(struct nfsd3_##argt##args), \ .pc_ressize = sizeof(struct nfsd3_##rest##res), \ diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index ed83e8a9e7b4..17c90c41a3a6 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -677,7 +677,7 @@ struct nfsd3_voidargs { int dummy; }; static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_NULL] = { .pc_func = nfsd3_proc_null, - .pc_encode = (kxdrproc_t) nfs3svc_encode_voidres, + .pc_encode = nfs3svc_encode_voidres, .pc_argsize = sizeof(struct nfsd3_voidargs), .pc_ressize = sizeof(struct nfsd3_voidres), .pc_cachetype = RC_NOCACHE, @@ -686,7 +686,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_GETATTR] = { .pc_func = nfsd3_proc_getattr, .pc_decode = nfs3svc_decode_fhandleargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_attrstatres, + .pc_encode = nfs3svc_encode_attrstatres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_attrstatres), @@ -696,7 +696,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_SETATTR] = { .pc_func = nfsd3_proc_setattr, .pc_decode = nfs3svc_decode_sattrargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, + .pc_encode = nfs3svc_encode_wccstatres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_sattrargs), .pc_ressize = sizeof(struct nfsd3_wccstatres), @@ -706,7 +706,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_LOOKUP] = { .pc_func = nfsd3_proc_lookup, .pc_decode = nfs3svc_decode_diropargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_diropres, + .pc_encode = nfs3svc_encode_diropres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_diropargs), .pc_ressize = sizeof(struct nfsd3_diropres), @@ -716,7 +716,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_ACCESS] = { .pc_func = nfsd3_proc_access, .pc_decode = nfs3svc_decode_accessargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_accessres, + .pc_encode = nfs3svc_encode_accessres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_accessargs), .pc_ressize = sizeof(struct nfsd3_accessres), @@ -726,7 +726,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_READLINK] = { .pc_func = nfsd3_proc_readlink, .pc_decode = nfs3svc_decode_readlinkargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_readlinkres, + .pc_encode = nfs3svc_encode_readlinkres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readlinkargs), .pc_ressize = sizeof(struct nfsd3_readlinkres), @@ -736,7 +736,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_READ] = { .pc_func = nfsd3_proc_read, .pc_decode = nfs3svc_decode_readargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_readres, + .pc_encode = nfs3svc_encode_readres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readargs), .pc_ressize = sizeof(struct nfsd3_readres), @@ -746,7 +746,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_WRITE] = { .pc_func = nfsd3_proc_write, .pc_decode = nfs3svc_decode_writeargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_writeres, + .pc_encode = nfs3svc_encode_writeres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_writeargs), .pc_ressize = sizeof(struct nfsd3_writeres), @@ -756,7 +756,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_CREATE] = { .pc_func = nfsd3_proc_create, .pc_decode = nfs3svc_decode_createargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, + .pc_encode = nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_createargs), .pc_ressize = sizeof(struct nfsd3_createres), @@ -766,7 +766,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_MKDIR] = { .pc_func = nfsd3_proc_mkdir, .pc_decode = nfs3svc_decode_mkdirargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, + .pc_encode = nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_mkdirargs), .pc_ressize = sizeof(struct nfsd3_createres), @@ -776,7 +776,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_SYMLINK] = { .pc_func = nfsd3_proc_symlink, .pc_decode = nfs3svc_decode_symlinkargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, + .pc_encode = nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_symlinkargs), .pc_ressize = sizeof(struct nfsd3_createres), @@ -786,7 +786,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_MKNOD] = { .pc_func = nfsd3_proc_mknod, .pc_decode = nfs3svc_decode_mknodargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, + .pc_encode = nfs3svc_encode_createres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_mknodargs), .pc_ressize = sizeof(struct nfsd3_createres), @@ -796,7 +796,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_REMOVE] = { .pc_func = nfsd3_proc_remove, .pc_decode = nfs3svc_decode_diropargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, + .pc_encode = nfs3svc_encode_wccstatres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_diropargs), .pc_ressize = sizeof(struct nfsd3_wccstatres), @@ -806,7 +806,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_RMDIR] = { .pc_func = nfsd3_proc_rmdir, .pc_decode = nfs3svc_decode_diropargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, + .pc_encode = nfs3svc_encode_wccstatres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_diropargs), .pc_ressize = sizeof(struct nfsd3_wccstatres), @@ -816,7 +816,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_RENAME] = { .pc_func = nfsd3_proc_rename, .pc_decode = nfs3svc_decode_renameargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_renameres, + .pc_encode = nfs3svc_encode_renameres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_renameargs), .pc_ressize = sizeof(struct nfsd3_renameres), @@ -826,7 +826,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_LINK] = { .pc_func = nfsd3_proc_link, .pc_decode = nfs3svc_decode_linkargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_linkres, + .pc_encode = nfs3svc_encode_linkres, .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_linkargs), .pc_ressize = sizeof(struct nfsd3_linkres), @@ -836,7 +836,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_READDIR] = { .pc_func = nfsd3_proc_readdir, .pc_decode = nfs3svc_decode_readdirargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres, + .pc_encode = nfs3svc_encode_readdirres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readdirargs), .pc_ressize = sizeof(struct nfsd3_readdirres), @@ -845,7 +845,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_READDIRPLUS] = { .pc_func = nfsd3_proc_readdirplus, .pc_decode = nfs3svc_decode_readdirplusargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres, + .pc_encode = nfs3svc_encode_readdirres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readdirplusargs), .pc_ressize = sizeof(struct nfsd3_readdirres), @@ -854,7 +854,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_FSSTAT] = { .pc_func = nfsd3_proc_fsstat, .pc_decode = nfs3svc_decode_fhandleargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_fsstatres, + .pc_encode = nfs3svc_encode_fsstatres, .pc_argsize = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_fsstatres), .pc_cachetype = RC_NOCACHE, @@ -863,7 +863,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_FSINFO] = { .pc_func = nfsd3_proc_fsinfo, .pc_decode = nfs3svc_decode_fhandleargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_fsinfores, + .pc_encode = nfs3svc_encode_fsinfores, .pc_argsize = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_fsinfores), .pc_cachetype = RC_NOCACHE, @@ -872,7 +872,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_PATHCONF] = { .pc_func = nfsd3_proc_pathconf, .pc_decode = nfs3svc_decode_fhandleargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_pathconfres, + .pc_encode = nfs3svc_encode_pathconfres, .pc_argsize = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_pathconfres), .pc_cachetype = RC_NOCACHE, @@ -881,7 +881,7 @@ static struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_COMMIT] = { .pc_func = nfsd3_proc_commit, .pc_decode = nfs3svc_decode_commitargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_commitres, + .pc_encode = nfs3svc_encode_commitres, .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_commitargs), .pc_ressize = sizeof(struct nfsd3_commitres), diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index c56089ac2819..b8838d3023ff 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -634,16 +634,17 @@ nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p) * will work properly. */ int -nfs3svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nfs3svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p) { return xdr_ressize_check(rqstp, p); } /* GETATTR */ int -nfs3svc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_attrstat *resp) +nfs3svc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_attrstat *resp = rqstp->rq_resp; + if (resp->status == 0) { lease_get_mtime(d_inode(resp->fh.fh_dentry), &resp->stat.mtime); @@ -654,18 +655,20 @@ nfs3svc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p, /* SETATTR, REMOVE, RMDIR */ int -nfs3svc_encode_wccstat(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_attrstat *resp) +nfs3svc_encode_wccstat(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_attrstat *resp = rqstp->rq_resp; + p = encode_wcc_data(rqstp, p, &resp->fh); return xdr_ressize_check(rqstp, p); } /* LOOKUP */ int -nfs3svc_encode_diropres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_diropres *resp) +nfs3svc_encode_diropres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_diropres *resp = rqstp->rq_resp; + if (resp->status == 0) { p = encode_fh(p, &resp->fh); p = encode_post_op_attr(rqstp, p, &resp->fh); @@ -676,9 +679,10 @@ nfs3svc_encode_diropres(struct svc_rqst *rqstp, __be32 *p, /* ACCESS */ int -nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_accessres *resp) +nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_accessres *resp = rqstp->rq_resp; + p = encode_post_op_attr(rqstp, p, &resp->fh); if (resp->status == 0) *p++ = htonl(resp->access); @@ -687,9 +691,10 @@ nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p, /* READLINK */ int -nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_readlinkres *resp) +nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_readlinkres *resp = rqstp->rq_resp; + p = encode_post_op_attr(rqstp, p, &resp->fh); if (resp->status == 0) { *p++ = htonl(resp->len); @@ -708,9 +713,10 @@ nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p, /* READ */ int -nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_readres *resp) +nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_readres *resp = rqstp->rq_resp; + p = encode_post_op_attr(rqstp, p, &resp->fh); if (resp->status == 0) { *p++ = htonl(resp->count); @@ -732,9 +738,9 @@ nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p, /* WRITE */ int -nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_writeres *resp) +nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_writeres *resp = rqstp->rq_resp; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); p = encode_wcc_data(rqstp, p, &resp->fh); @@ -749,9 +755,10 @@ nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p, /* CREATE, MKDIR, SYMLINK, MKNOD */ int -nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_diropres *resp) +nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_diropres *resp = rqstp->rq_resp; + if (resp->status == 0) { *p++ = xdr_one; p = encode_fh(p, &resp->fh); @@ -763,9 +770,10 @@ nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p, /* RENAME */ int -nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_renameres *resp) +nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_renameres *resp = rqstp->rq_resp; + p = encode_wcc_data(rqstp, p, &resp->ffh); p = encode_wcc_data(rqstp, p, &resp->tfh); return xdr_ressize_check(rqstp, p); @@ -773,9 +781,10 @@ nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p, /* LINK */ int -nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_linkres *resp) +nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_linkres *resp = rqstp->rq_resp; + p = encode_post_op_attr(rqstp, p, &resp->fh); p = encode_wcc_data(rqstp, p, &resp->tfh); return xdr_ressize_check(rqstp, p); @@ -783,9 +792,10 @@ nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p, /* READDIR */ int -nfs3svc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_readdirres *resp) +nfs3svc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_readdirres *resp = rqstp->rq_resp; + p = encode_post_op_attr(rqstp, p, &resp->fh); if (resp->status == 0) { @@ -1033,9 +1043,9 @@ nfs3svc_encode_entry_plus(void *cd, const char *name, /* FSSTAT */ int -nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_fsstatres *resp) +nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_fsstatres *resp = rqstp->rq_resp; struct kstatfs *s = &resp->stats; u64 bs = s->f_bsize; @@ -1055,9 +1065,10 @@ nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p, /* FSINFO */ int -nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_fsinfores *resp) +nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_fsinfores *resp = rqstp->rq_resp; + *p++ = xdr_zero; /* no post_op_attr */ if (resp->status == 0) { @@ -1079,9 +1090,10 @@ nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p, /* PATHCONF */ int -nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_pathconfres *resp) +nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_pathconfres *resp = rqstp->rq_resp; + *p++ = xdr_zero; /* no post_op_attr */ if (resp->status == 0) { @@ -1098,9 +1110,9 @@ nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p, /* COMMIT */ int -nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_commitres *resp) +nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_commitres *resp = rqstp->rq_resp; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); p = encode_wcc_data(rqstp, p, &resp->fh); diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 19c7d4b989c4..726d28376f7b 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -2519,7 +2519,7 @@ struct nfsd4_voidargs { int dummy; }; static struct svc_procedure nfsd_procedures4[2] = { [NFSPROC4_NULL] = { .pc_func = nfsd4_proc_null, - .pc_encode = (kxdrproc_t) nfs4svc_encode_voidres, + .pc_encode = nfs4svc_encode_voidres, .pc_argsize = sizeof(struct nfsd4_voidargs), .pc_ressize = sizeof(struct nfsd4_voidres), .pc_cachetype = RC_NOCACHE, @@ -2528,7 +2528,7 @@ static struct svc_procedure nfsd_procedures4[2] = { [NFSPROC4_COMPOUND] = { .pc_func = nfsd4_proc_compound, .pc_decode = nfs4svc_decode_compoundargs, - .pc_encode = (kxdrproc_t) nfs4svc_encode_compoundres, + .pc_encode = nfs4svc_encode_compoundres, .pc_argsize = sizeof(struct nfsd4_compoundargs), .pc_ressize = sizeof(struct nfsd4_compoundres), .pc_release = nfsd4_release_compoundargs, diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 3a7e117bd11e..54e212e3541e 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -4538,7 +4538,7 @@ nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op) } int -nfs4svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nfs4svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p) { return xdr_ressize_check(rqstp, p); } @@ -4584,11 +4584,12 @@ nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p) } int -nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compoundres *resp) +nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p) { /* * All that remains is to write the tag and operation count... */ + struct nfsd4_compoundres *resp = rqstp->rq_resp; struct xdr_buf *buf = resp->xdr.buf; WARN_ON_ONCE(buf->len != buf->head[0].iov_len + buf->page_len + diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index d351d0ef6d34..0ef88d0e67d9 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -577,7 +577,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_NULL] = { .pc_func = nfsd_proc_null, .pc_decode = nfssvc_decode_void, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_void), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_NOCACHE, @@ -586,7 +586,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_GETATTR] = { .pc_func = nfsd_proc_getattr, .pc_decode = nfssvc_decode_fhandle, - .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, + .pc_encode = nfssvc_encode_attrstat, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd_attrstat), @@ -596,7 +596,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_SETATTR] = { .pc_func = nfsd_proc_setattr, .pc_decode = nfssvc_decode_sattrargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, + .pc_encode = nfssvc_encode_attrstat, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_sattrargs), .pc_ressize = sizeof(struct nfsd_attrstat), @@ -605,7 +605,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_ROOT] = { .pc_decode = nfssvc_decode_void, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_void), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_NOCACHE, @@ -614,7 +614,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_LOOKUP] = { .pc_func = nfsd_proc_lookup, .pc_decode = nfssvc_decode_diropargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, + .pc_encode = nfssvc_encode_diropres, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_diropargs), .pc_ressize = sizeof(struct nfsd_diropres), @@ -624,7 +624,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_READLINK] = { .pc_func = nfsd_proc_readlink, .pc_decode = nfssvc_decode_readlinkargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_readlinkres, + .pc_encode = nfssvc_encode_readlinkres, .pc_argsize = sizeof(struct nfsd_readlinkargs), .pc_ressize = sizeof(struct nfsd_readlinkres), .pc_cachetype = RC_NOCACHE, @@ -633,7 +633,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_READ] = { .pc_func = nfsd_proc_read, .pc_decode = nfssvc_decode_readargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_readres, + .pc_encode = nfssvc_encode_readres, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_readargs), .pc_ressize = sizeof(struct nfsd_readres), @@ -642,7 +642,7 @@ static struct svc_procedure nfsd_procedures2[18] = { }, [NFSPROC_WRITECACHE] = { .pc_decode = nfssvc_decode_void, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_void), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_NOCACHE, @@ -651,7 +651,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_WRITE] = { .pc_func = nfsd_proc_write, .pc_decode = nfssvc_decode_writeargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, + .pc_encode = nfssvc_encode_attrstat, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_writeargs), .pc_ressize = sizeof(struct nfsd_attrstat), @@ -661,7 +661,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_CREATE] = { .pc_func = nfsd_proc_create, .pc_decode = nfssvc_decode_createargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, + .pc_encode = nfssvc_encode_diropres, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_createargs), .pc_ressize = sizeof(struct nfsd_diropres), @@ -671,7 +671,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_REMOVE] = { .pc_func = nfsd_proc_remove, .pc_decode = nfssvc_decode_diropargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_diropargs), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_REPLSTAT, @@ -680,7 +680,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_RENAME] = { .pc_func = nfsd_proc_rename, .pc_decode = nfssvc_decode_renameargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_renameargs), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_REPLSTAT, @@ -689,7 +689,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_LINK] = { .pc_func = nfsd_proc_link, .pc_decode = nfssvc_decode_linkargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_linkargs), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_REPLSTAT, @@ -698,7 +698,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_SYMLINK] = { .pc_func = nfsd_proc_symlink, .pc_decode = nfssvc_decode_symlinkargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_symlinkargs), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_REPLSTAT, @@ -707,7 +707,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_MKDIR] = { .pc_func = nfsd_proc_mkdir, .pc_decode = nfssvc_decode_createargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, + .pc_encode = nfssvc_encode_diropres, .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_createargs), .pc_ressize = sizeof(struct nfsd_diropres), @@ -717,7 +717,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_RMDIR] = { .pc_func = nfsd_proc_rmdir, .pc_decode = nfssvc_decode_diropargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_diropargs), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_REPLSTAT, @@ -726,7 +726,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_READDIR] = { .pc_func = nfsd_proc_readdir, .pc_decode = nfssvc_decode_readdirargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_readdirres, + .pc_encode = nfssvc_encode_readdirres, .pc_argsize = sizeof(struct nfsd_readdirargs), .pc_ressize = sizeof(struct nfsd_readdirres), .pc_cachetype = RC_NOCACHE, @@ -734,7 +734,7 @@ static struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_STATFS] = { .pc_func = nfsd_proc_statfs, .pc_decode = nfssvc_decode_fhandle, - .pc_encode = (kxdrproc_t) nfssvc_encode_statfsres, + .pc_encode = nfssvc_encode_statfsres, .pc_argsize = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd_statfsres), .pc_cachetype = RC_NOCACHE, diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 3e00499d7ad7..555233664124 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -782,7 +782,6 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) { struct svc_procedure *proc; - kxdrproc_t xdr; __be32 nfserr; __be32 *nfserrp; @@ -841,9 +840,7 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) * For NFSv2, additional info is never returned in case of an error. */ if (!(nfserr && rqstp->rq_vers == 2)) { - xdr = proc->pc_encode; - if (xdr && !xdr(rqstp, nfserrp, - rqstp->rq_resp)) { + if (proc->pc_encode && !proc->pc_encode(rqstp, nfserrp)) { /* Failed to encode result. Release cache entry */ dprintk("nfsd: failed to encode result!\n"); nfsd_cache_update(rqstp, RC_NOCACHE, NULL); diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index 19cf04ebf388..e4da2717982d 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -422,32 +422,35 @@ nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) * XDR encode functions */ int -nfssvc_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nfssvc_encode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_ressize_check(rqstp, p); } int -nfssvc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_attrstat *resp) +nfssvc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_attrstat *resp = rqstp->rq_resp; + p = encode_fattr(rqstp, p, &resp->fh, &resp->stat); return xdr_ressize_check(rqstp, p); } int -nfssvc_encode_diropres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_diropres *resp) +nfssvc_encode_diropres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_diropres *resp = rqstp->rq_resp; + p = encode_fh(p, &resp->fh); p = encode_fattr(rqstp, p, &resp->fh, &resp->stat); return xdr_ressize_check(rqstp, p); } int -nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_readlinkres *resp) +nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_readlinkres *resp = rqstp->rq_resp; + *p++ = htonl(resp->len); xdr_ressize_check(rqstp, p); rqstp->rq_res.page_len = resp->len; @@ -461,9 +464,10 @@ nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_readres *resp) +nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_readres *resp = rqstp->rq_resp; + p = encode_fattr(rqstp, p, &resp->fh, &resp->stat); *p++ = htonl(resp->count); xdr_ressize_check(rqstp, p); @@ -480,9 +484,10 @@ nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_readdirres *resp) +nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_readdirres *resp = rqstp->rq_resp; + xdr_ressize_check(rqstp, p); p = resp->buffer; *p++ = 0; /* no more entries */ @@ -493,9 +498,9 @@ nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_statfsres *resp) +nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_statfsres *resp = rqstp->rq_resp; struct kstatfs *stat = &resp->stats; *p++ = htonl(NFSSVC_MAXBLKSIZE_V2); /* max transfer size */ diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h index 8eeb752cf6f8..457ce45e5084 100644 --- a/fs/nfsd/xdr.h +++ b/fs/nfsd/xdr.h @@ -143,13 +143,13 @@ int nfssvc_decode_readlinkargs(struct svc_rqst *, __be32 *); int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *); int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *); int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *); -int nfssvc_encode_void(struct svc_rqst *, __be32 *, void *); -int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *, struct nfsd_attrstat *); -int nfssvc_encode_diropres(struct svc_rqst *, __be32 *, struct nfsd_diropres *); -int nfssvc_encode_readlinkres(struct svc_rqst *, __be32 *, struct nfsd_readlinkres *); -int nfssvc_encode_readres(struct svc_rqst *, __be32 *, struct nfsd_readres *); -int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *, struct nfsd_statfsres *); -int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *, struct nfsd_readdirres *); +int nfssvc_encode_void(struct svc_rqst *, __be32 *); +int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *); +int nfssvc_encode_diropres(struct svc_rqst *, __be32 *); +int nfssvc_encode_readlinkres(struct svc_rqst *, __be32 *); +int nfssvc_encode_readres(struct svc_rqst *, __be32 *); +int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *); +int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *); int nfssvc_encode_entry(void *, const char *name, int namlen, loff_t offset, u64 ino, unsigned int); diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h index f79be4c42e4a..80d7da620e91 100644 --- a/fs/nfsd/xdr3.h +++ b/fs/nfsd/xdr3.h @@ -285,35 +285,22 @@ int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *); int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *); int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *); int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *); -int nfs3svc_encode_voidres(struct svc_rqst *, __be32 *, void *); -int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *, - struct nfsd3_attrstat *); -int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *, - struct nfsd3_attrstat *); -int nfs3svc_encode_diropres(struct svc_rqst *, __be32 *, - struct nfsd3_diropres *); -int nfs3svc_encode_accessres(struct svc_rqst *, __be32 *, - struct nfsd3_accessres *); -int nfs3svc_encode_readlinkres(struct svc_rqst *, __be32 *, - struct nfsd3_readlinkres *); -int nfs3svc_encode_readres(struct svc_rqst *, __be32 *, struct nfsd3_readres *); -int nfs3svc_encode_writeres(struct svc_rqst *, __be32 *, struct nfsd3_writeres *); -int nfs3svc_encode_createres(struct svc_rqst *, __be32 *, - struct nfsd3_diropres *); -int nfs3svc_encode_renameres(struct svc_rqst *, __be32 *, - struct nfsd3_renameres *); -int nfs3svc_encode_linkres(struct svc_rqst *, __be32 *, - struct nfsd3_linkres *); -int nfs3svc_encode_readdirres(struct svc_rqst *, __be32 *, - struct nfsd3_readdirres *); -int nfs3svc_encode_fsstatres(struct svc_rqst *, __be32 *, - struct nfsd3_fsstatres *); -int nfs3svc_encode_fsinfores(struct svc_rqst *, __be32 *, - struct nfsd3_fsinfores *); -int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *, - struct nfsd3_pathconfres *); -int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *, - struct nfsd3_commitres *); +int nfs3svc_encode_voidres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *); +int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *); +int nfs3svc_encode_diropres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_accessres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_readlinkres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_readres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_writeres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_createres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_renameres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_linkres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_readdirres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_fsstatres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_fsinfores(struct svc_rqst *, __be32 *); +int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *); void nfs3svc_release_fhandle(struct svc_rqst *); void nfs3svc_release_fhandle2(struct svc_rqst *); diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 2a53c1233884..eb7f9239304f 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -682,10 +682,9 @@ set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp) bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp); -int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *, void *); +int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *); int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *); -int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *, - struct nfsd4_compoundres *); +int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *); __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32); void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *); void nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op); diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index 0416600844ce..7acbecc21a40 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -96,16 +96,16 @@ struct nlm_reboot { #define NLMSVC_XDRSIZE sizeof(struct nlm_args) int nlmsvc_decode_testargs(struct svc_rqst *, __be32 *); -int nlmsvc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlmsvc_encode_testres(struct svc_rqst *, __be32 *); int nlmsvc_decode_lockargs(struct svc_rqst *, __be32 *); int nlmsvc_decode_cancargs(struct svc_rqst *, __be32 *); int nlmsvc_decode_unlockargs(struct svc_rqst *, __be32 *); -int nlmsvc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlmsvc_encode_res(struct svc_rqst *, __be32 *); int nlmsvc_decode_res(struct svc_rqst *, __be32 *); -int nlmsvc_encode_void(struct svc_rqst *, __be32 *, void *); +int nlmsvc_encode_void(struct svc_rqst *, __be32 *); int nlmsvc_decode_void(struct svc_rqst *, __be32 *); int nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *); -int nlmsvc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlmsvc_encode_shareres(struct svc_rqst *, __be32 *); int nlmsvc_decode_notify(struct svc_rqst *, __be32 *); int nlmsvc_decode_reboot(struct svc_rqst *, __be32 *); /* diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index 951bbe31fdb8..bf1645609225 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -24,16 +24,16 @@ int nlm4svc_decode_testargs(struct svc_rqst *, __be32 *); -int nlm4svc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlm4svc_encode_testres(struct svc_rqst *, __be32 *); int nlm4svc_decode_lockargs(struct svc_rqst *, __be32 *); int nlm4svc_decode_cancargs(struct svc_rqst *, __be32 *); int nlm4svc_decode_unlockargs(struct svc_rqst *, __be32 *); -int nlm4svc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlm4svc_encode_res(struct svc_rqst *, __be32 *); int nlm4svc_decode_res(struct svc_rqst *, __be32 *); -int nlm4svc_encode_void(struct svc_rqst *, __be32 *, void *); +int nlm4svc_encode_void(struct svc_rqst *, __be32 *); int nlm4svc_decode_void(struct svc_rqst *, __be32 *); int nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *); -int nlm4svc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *); +int nlm4svc_encode_shareres(struct svc_rqst *, __be32 *); int nlm4svc_decode_notify(struct svc_rqst *, __be32 *); int nlm4svc_decode_reboot(struct svc_rqst *, __be32 *); /* diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index d8703a5ab81e..bd9e313c444a 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -424,7 +424,8 @@ struct svc_procedure { __be32 (*pc_func)(struct svc_rqst *); /* XDR decode args: */ int (*pc_decode)(struct svc_rqst *, __be32 *data); - kxdrproc_t pc_encode; /* XDR encode result */ + /* XDR encode result: */ + int (*pc_encode)(struct svc_rqst *, __be32 *data); /* XDR free result: */ void (*pc_release)(struct svc_rqst *); unsigned int pc_argsize; /* argument struct size */ diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 18024c1b9b7b..aa643a29fdc6 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1154,7 +1154,6 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) struct svc_version *versp = NULL; /* compiler food */ struct svc_procedure *procp = NULL; struct svc_serv *serv = rqstp->rq_server; - kxdrproc_t xdr; __be32 *statp; u32 prog, vers, proc; __be32 auth_stat, rpc_stat; @@ -1298,9 +1297,8 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) procp->pc_release(rqstp); goto err_bad_auth; } - if (*statp == rpc_success && - (xdr = procp->pc_encode) && - !xdr(rqstp, resv->iov_base+resv->iov_len, rqstp->rq_resp)) { + if (*statp == rpc_success && procp->pc_encode && + !procp->pc_encode(rqstp, resv->iov_base + resv->iov_len)) { dprintk("svc: failed to encode reply\n"); /* serv->sv_stats->rpcsystemerr++; */ *statp = rpc_system_err; -- cgit v1.2.3-59-g8ed1b From 408b3d46ae06e1d219f31cbe629789a5e5c862aa Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 19:56:10 +0200 Subject: sunrpc: remove kxdrproc_t Remove the now unused typedef. Signed-off-by: Christoph Hellwig --- include/linux/sunrpc/xdr.h | 7 ------- 1 file changed, 7 deletions(-) diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index ed0fbf0d8d0f..261b48a2701d 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -34,13 +34,6 @@ struct xdr_netobj { u8 * data; }; -/* - * This is the legacy generic XDR function. rqstp is either a rpc_rqst - * (client side) or svc_rqst pointer (server side). - * Encode functions always assume there's enough room in the buffer. - */ -typedef int (*kxdrproc_t)(void *rqstp, __be32 *data, void *obj); - /* * Basic structure for transmission/reception of a client XDR message. * Features a header (for a linear buffer containing RPC headers -- cgit v1.2.3-59-g8ed1b From 6c9600a71d9c00a49e6a915b228f3f0b542a6067 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 20:03:15 +0200 Subject: nfsd4: properly type op_set_currentstateid callbacks Given the args union in struct nfsd4_op a name, and pass it to the op_set_currentstateid callbacks instead of using unsafe function pointer casts. Signed-off-by: Christoph Hellwig --- fs/nfsd/current_stateid.h | 12 ++++++++---- fs/nfsd/nfs4proc.c | 12 ++++++------ fs/nfsd/nfs4state.c | 20 ++++++++++++-------- fs/nfsd/xdr4.h | 2 +- 4 files changed, 27 insertions(+), 19 deletions(-) diff --git a/fs/nfsd/current_stateid.h b/fs/nfsd/current_stateid.h index 4123551208d8..3c80a7b5302d 100644 --- a/fs/nfsd/current_stateid.h +++ b/fs/nfsd/current_stateid.h @@ -8,10 +8,14 @@ extern void clear_current_stateid(struct nfsd4_compound_state *cstate); /* * functions to set current state id */ -extern void nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *); -extern void nfsd4_set_openstateid(struct nfsd4_compound_state *, struct nfsd4_open *); -extern void nfsd4_set_lockstateid(struct nfsd4_compound_state *, struct nfsd4_lock *); -extern void nfsd4_set_closestateid(struct nfsd4_compound_state *, struct nfsd4_close *); +extern void nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_set_openstateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_set_lockstateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_set_closestateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); /* * functions to consume current state id diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 726d28376f7b..91cee9e2b4f3 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1525,7 +1525,6 @@ typedef __be32(*nfsd4op_func)(struct svc_rqst *, struct nfsd4_compound_state *, void *); typedef u32(*nfsd4op_rsize)(struct svc_rqst *, struct nfsd4_op *op); -typedef void(*stateid_setter)(struct nfsd4_compound_state *, void *); typedef void(*stateid_getter)(struct nfsd4_compound_state *, void *); enum nfsd4_op_flags { @@ -1565,7 +1564,8 @@ struct nfsd4_operation { /* Try to get response size before operation */ nfsd4op_rsize op_rsize_bop; stateid_getter op_get_currentstateid; - stateid_setter op_set_currentstateid; + void (*op_set_currentstateid)(struct nfsd4_compound_state *, + union nfsd4_op_u *); }; static struct nfsd4_operation nfsd4_ops[]; @@ -2104,7 +2104,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_name = "OP_CLOSE", .op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize, .op_get_currentstateid = (stateid_getter)nfsd4_get_closestateid, - .op_set_currentstateid = (stateid_setter)nfsd4_set_closestateid, + .op_set_currentstateid = nfsd4_set_closestateid, }, [OP_COMMIT] = { .op_func = (nfsd4op_func)nfsd4_commit, @@ -2148,7 +2148,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LOCK", .op_rsize_bop = (nfsd4op_rsize)nfsd4_lock_rsize, - .op_set_currentstateid = (stateid_setter)nfsd4_set_lockstateid, + .op_set_currentstateid = nfsd4_set_lockstateid, }, [OP_LOCKT] = { .op_func = (nfsd4op_func)nfsd4_lockt, @@ -2184,7 +2184,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = OP_HANDLES_WRONGSEC | OP_MODIFIES_SOMETHING, .op_name = "OP_OPEN", .op_rsize_bop = (nfsd4op_rsize)nfsd4_open_rsize, - .op_set_currentstateid = (stateid_setter)nfsd4_set_openstateid, + .op_set_currentstateid = nfsd4_set_openstateid, }, [OP_OPEN_CONFIRM] = { .op_func = (nfsd4op_func)nfsd4_open_confirm, @@ -2198,7 +2198,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_name = "OP_OPEN_DOWNGRADE", .op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize, .op_get_currentstateid = (stateid_getter)nfsd4_get_opendowngradestateid, - .op_set_currentstateid = (stateid_setter)nfsd4_set_opendowngradestateid, + .op_set_currentstateid = nfsd4_set_opendowngradestateid, }, [OP_PUTFH] = { .op_func = (nfsd4op_func)nfsd4_putfh, diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 22002fb75a18..f9552357923e 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -7103,27 +7103,31 @@ clear_current_stateid(struct nfsd4_compound_state *cstate) * functions to set current state id */ void -nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *odp) +nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - put_stateid(cstate, &odp->od_stateid); + put_stateid(cstate, &u->open_downgrade.od_stateid); } void -nfsd4_set_openstateid(struct nfsd4_compound_state *cstate, struct nfsd4_open *open) +nfsd4_set_openstateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - put_stateid(cstate, &open->op_stateid); + put_stateid(cstate, &u->open.op_stateid); } void -nfsd4_set_closestateid(struct nfsd4_compound_state *cstate, struct nfsd4_close *close) +nfsd4_set_closestateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - put_stateid(cstate, &close->cl_stateid); + put_stateid(cstate, &u->close.cl_stateid); } void -nfsd4_set_lockstateid(struct nfsd4_compound_state *cstate, struct nfsd4_lock *lock) +nfsd4_set_lockstateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - put_stateid(cstate, &lock->lk_resp_stateid); + put_stateid(cstate, &u->lock.lk_resp_stateid); } /* diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index eb7f9239304f..b625f4aa1061 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -539,7 +539,7 @@ struct nfsd4_seek { struct nfsd4_op { int opnum; __be32 status; - union { + union nfsd4_op_u { struct nfsd4_access access; struct nfsd4_close close; struct nfsd4_commit commit; -- cgit v1.2.3-59-g8ed1b From c2a1102aa2add2f6757586541fc9c22d9b71bdf3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 20:37:33 +0200 Subject: nfsd4: properly type op_get_currentstateid callbacks Pass union nfsd4_op_u to the op_set_currentstateid callbacks instead of using unsafe function pointer casts. Signed-off-by: Christoph Hellwig --- fs/nfsd/current_stateid.h | 24 ++++++++++++++++-------- fs/nfsd/nfs4proc.c | 21 ++++++++++----------- fs/nfsd/nfs4state.c | 40 ++++++++++++++++++++++++---------------- 3 files changed, 50 insertions(+), 35 deletions(-) diff --git a/fs/nfsd/current_stateid.h b/fs/nfsd/current_stateid.h index 3c80a7b5302d..34075cee573a 100644 --- a/fs/nfsd/current_stateid.h +++ b/fs/nfsd/current_stateid.h @@ -20,13 +20,21 @@ extern void nfsd4_set_closestateid(struct nfsd4_compound_state *, /* * functions to consume current state id */ -extern void nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *); -extern void nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *, struct nfsd4_delegreturn *); -extern void nfsd4_get_freestateid(struct nfsd4_compound_state *, struct nfsd4_free_stateid *); -extern void nfsd4_get_setattrstateid(struct nfsd4_compound_state *, struct nfsd4_setattr *); -extern void nfsd4_get_closestateid(struct nfsd4_compound_state *, struct nfsd4_close *); -extern void nfsd4_get_lockustateid(struct nfsd4_compound_state *, struct nfsd4_locku *); -extern void nfsd4_get_readstateid(struct nfsd4_compound_state *, struct nfsd4_read *); -extern void nfsd4_get_writestateid(struct nfsd4_compound_state *, struct nfsd4_write *); +extern void nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_get_freestateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_get_setattrstateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_get_closestateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_get_lockustateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_get_readstateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_get_writestateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); #endif /* _NFSD4_CURRENT_STATE_H */ diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 91cee9e2b4f3..c06ed1cdfca9 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1525,8 +1525,6 @@ typedef __be32(*nfsd4op_func)(struct svc_rqst *, struct nfsd4_compound_state *, void *); typedef u32(*nfsd4op_rsize)(struct svc_rqst *, struct nfsd4_op *op); -typedef void(*stateid_getter)(struct nfsd4_compound_state *, void *); - enum nfsd4_op_flags { ALLOWED_WITHOUT_FH = 1 << 0, /* No current filehandle required */ ALLOWED_ON_ABSENT_FS = 1 << 1, /* ops processed on absent fs */ @@ -1563,7 +1561,8 @@ struct nfsd4_operation { char *op_name; /* Try to get response size before operation */ nfsd4op_rsize op_rsize_bop; - stateid_getter op_get_currentstateid; + void (*op_get_currentstateid)(struct nfsd4_compound_state *, + union nfsd4_op_u *); void (*op_set_currentstateid)(struct nfsd4_compound_state *, union nfsd4_op_u *); }; @@ -2103,7 +2102,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_CLOSE", .op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize, - .op_get_currentstateid = (stateid_getter)nfsd4_get_closestateid, + .op_get_currentstateid = nfsd4_get_closestateid, .op_set_currentstateid = nfsd4_set_closestateid, }, [OP_COMMIT] = { @@ -2123,7 +2122,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_DELEGRETURN", .op_rsize_bop = nfsd4_only_status_rsize, - .op_get_currentstateid = (stateid_getter)nfsd4_get_delegreturnstateid, + .op_get_currentstateid = nfsd4_get_delegreturnstateid, }, [OP_GETATTR] = { .op_func = (nfsd4op_func)nfsd4_getattr, @@ -2160,7 +2159,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LOCKU", .op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize, - .op_get_currentstateid = (stateid_getter)nfsd4_get_lockustateid, + .op_get_currentstateid = nfsd4_get_lockustateid, }, [OP_LOOKUP] = { .op_func = (nfsd4op_func)nfsd4_lookup, @@ -2197,7 +2196,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_OPEN_DOWNGRADE", .op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize, - .op_get_currentstateid = (stateid_getter)nfsd4_get_opendowngradestateid, + .op_get_currentstateid = nfsd4_get_opendowngradestateid, .op_set_currentstateid = nfsd4_set_opendowngradestateid, }, [OP_PUTFH] = { @@ -2225,7 +2224,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_func = (nfsd4op_func)nfsd4_read, .op_name = "OP_READ", .op_rsize_bop = (nfsd4op_rsize)nfsd4_read_rsize, - .op_get_currentstateid = (stateid_getter)nfsd4_get_readstateid, + .op_get_currentstateid = nfsd4_get_readstateid, }, [OP_READDIR] = { .op_func = (nfsd4op_func)nfsd4_readdir, @@ -2281,7 +2280,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_name = "OP_SETATTR", .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_rsize_bop = (nfsd4op_rsize)nfsd4_setattr_rsize, - .op_get_currentstateid = (stateid_getter)nfsd4_get_setattrstateid, + .op_get_currentstateid = nfsd4_get_setattrstateid, }, [OP_SETCLIENTID] = { .op_func = (nfsd4op_func)nfsd4_setclientid, @@ -2307,7 +2306,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_WRITE", .op_rsize_bop = (nfsd4op_rsize)nfsd4_write_rsize, - .op_get_currentstateid = (stateid_getter)nfsd4_get_writestateid, + .op_get_currentstateid = nfsd4_get_writestateid, }, [OP_RELEASE_LOCKOWNER] = { .op_func = (nfsd4op_func)nfsd4_release_lockowner, @@ -2387,7 +2386,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_func = (nfsd4op_func)nfsd4_free_stateid, .op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING, .op_name = "OP_FREE_STATEID", - .op_get_currentstateid = (stateid_getter)nfsd4_get_freestateid, + .op_get_currentstateid = nfsd4_get_freestateid, .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, }, #ifdef CONFIG_NFSD_PNFS diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index f9552357923e..01ab21f8d34d 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -7135,49 +7135,57 @@ nfsd4_set_lockstateid(struct nfsd4_compound_state *cstate, */ void -nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *odp) +nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &odp->od_stateid); + get_stateid(cstate, &u->open_downgrade.od_stateid); } void -nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *cstate, struct nfsd4_delegreturn *drp) +nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &drp->dr_stateid); + get_stateid(cstate, &u->delegreturn.dr_stateid); } void -nfsd4_get_freestateid(struct nfsd4_compound_state *cstate, struct nfsd4_free_stateid *fsp) +nfsd4_get_freestateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &fsp->fr_stateid); + get_stateid(cstate, &u->free_stateid.fr_stateid); } void -nfsd4_get_setattrstateid(struct nfsd4_compound_state *cstate, struct nfsd4_setattr *setattr) +nfsd4_get_setattrstateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &setattr->sa_stateid); + get_stateid(cstate, &u->setattr.sa_stateid); } void -nfsd4_get_closestateid(struct nfsd4_compound_state *cstate, struct nfsd4_close *close) +nfsd4_get_closestateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &close->cl_stateid); + get_stateid(cstate, &u->close.cl_stateid); } void -nfsd4_get_lockustateid(struct nfsd4_compound_state *cstate, struct nfsd4_locku *locku) +nfsd4_get_lockustateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &locku->lu_stateid); + get_stateid(cstate, &u->locku.lu_stateid); } void -nfsd4_get_readstateid(struct nfsd4_compound_state *cstate, struct nfsd4_read *read) +nfsd4_get_readstateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &read->rd_stateid); + get_stateid(cstate, &u->read.rd_stateid); } void -nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, struct nfsd4_write *write) +nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &write->wr_stateid); + get_stateid(cstate, &u->write.wr_stateid); } -- cgit v1.2.3-59-g8ed1b From 62bbf8bbb2fa3aba16e29585b3396264c1a2b2f4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 20:42:10 +0200 Subject: nfsd4: remove nfsd4op_rsize Except for a lot of unnecessary casts this typedef only has one user, so remove the casts and expand it in struct nfsd4_operation. Signed-off-by: Christoph Hellwig --- fs/nfsd/nfs4proc.c | 109 ++++++++++++++++++++++++++--------------------------- 1 file changed, 54 insertions(+), 55 deletions(-) diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index c06ed1cdfca9..c1e31edf922d 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1523,7 +1523,6 @@ static inline void nfsd4_increment_op_stats(u32 opnum) typedef __be32(*nfsd4op_func)(struct svc_rqst *, struct nfsd4_compound_state *, void *); -typedef u32(*nfsd4op_rsize)(struct svc_rqst *, struct nfsd4_op *op); enum nfsd4_op_flags { ALLOWED_WITHOUT_FH = 1 << 0, /* No current filehandle required */ @@ -1560,7 +1559,7 @@ struct nfsd4_operation { u32 op_flags; char *op_name; /* Try to get response size before operation */ - nfsd4op_rsize op_rsize_bop; + u32 (*op_rsize_bop)(struct svc_rqst *, struct nfsd4_op *); void (*op_get_currentstateid)(struct nfsd4_compound_state *, union nfsd4_op_u *); void (*op_set_currentstateid)(struct nfsd4_compound_state *, @@ -2095,13 +2094,13 @@ static struct nfsd4_operation nfsd4_ops[] = { [OP_ACCESS] = { .op_func = (nfsd4op_func)nfsd4_access, .op_name = "OP_ACCESS", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_access_rsize, + .op_rsize_bop = nfsd4_access_rsize, }, [OP_CLOSE] = { .op_func = (nfsd4op_func)nfsd4_close, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_CLOSE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize, + .op_rsize_bop = nfsd4_status_stateid_rsize, .op_get_currentstateid = nfsd4_get_closestateid, .op_set_currentstateid = nfsd4_set_closestateid, }, @@ -2109,13 +2108,13 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_func = (nfsd4op_func)nfsd4_commit, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_COMMIT", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_commit_rsize, + .op_rsize_bop = nfsd4_commit_rsize, }, [OP_CREATE] = { .op_func = (nfsd4op_func)nfsd4_create, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME | OP_CLEAR_STATEID, .op_name = "OP_CREATE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_create_rsize, + .op_rsize_bop = nfsd4_create_rsize, }, [OP_DELEGRETURN] = { .op_func = (nfsd4op_func)nfsd4_delegreturn, @@ -2133,69 +2132,69 @@ static struct nfsd4_operation nfsd4_ops[] = { [OP_GETFH] = { .op_func = (nfsd4op_func)nfsd4_getfh, .op_name = "OP_GETFH", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_getfh_rsize, + .op_rsize_bop = nfsd4_getfh_rsize, }, [OP_LINK] = { .op_func = (nfsd4op_func)nfsd4_link, .op_flags = ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_LINK", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_link_rsize, + .op_rsize_bop = nfsd4_link_rsize, }, [OP_LOCK] = { .op_func = (nfsd4op_func)nfsd4_lock, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LOCK", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_lock_rsize, + .op_rsize_bop = nfsd4_lock_rsize, .op_set_currentstateid = nfsd4_set_lockstateid, }, [OP_LOCKT] = { .op_func = (nfsd4op_func)nfsd4_lockt, .op_name = "OP_LOCKT", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_lock_rsize, + .op_rsize_bop = nfsd4_lock_rsize, }, [OP_LOCKU] = { .op_func = (nfsd4op_func)nfsd4_locku, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LOCKU", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize, + .op_rsize_bop = nfsd4_status_stateid_rsize, .op_get_currentstateid = nfsd4_get_lockustateid, }, [OP_LOOKUP] = { .op_func = (nfsd4op_func)nfsd4_lookup, .op_flags = OP_HANDLES_WRONGSEC | OP_CLEAR_STATEID, .op_name = "OP_LOOKUP", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_LOOKUPP] = { .op_func = (nfsd4op_func)nfsd4_lookupp, .op_flags = OP_HANDLES_WRONGSEC | OP_CLEAR_STATEID, .op_name = "OP_LOOKUPP", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_NVERIFY] = { .op_func = (nfsd4op_func)nfsd4_nverify, .op_name = "OP_NVERIFY", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_OPEN] = { .op_func = (nfsd4op_func)nfsd4_open, .op_flags = OP_HANDLES_WRONGSEC | OP_MODIFIES_SOMETHING, .op_name = "OP_OPEN", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_open_rsize, + .op_rsize_bop = nfsd4_open_rsize, .op_set_currentstateid = nfsd4_set_openstateid, }, [OP_OPEN_CONFIRM] = { .op_func = (nfsd4op_func)nfsd4_open_confirm, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_OPEN_CONFIRM", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize, + .op_rsize_bop = nfsd4_status_stateid_rsize, }, [OP_OPEN_DOWNGRADE] = { .op_func = (nfsd4op_func)nfsd4_open_downgrade, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_OPEN_DOWNGRADE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize, + .op_rsize_bop = nfsd4_status_stateid_rsize, .op_get_currentstateid = nfsd4_get_opendowngradestateid, .op_set_currentstateid = nfsd4_set_opendowngradestateid, }, @@ -2204,56 +2203,56 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID, .op_name = "OP_PUTFH", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_PUTPUBFH] = { .op_func = (nfsd4op_func)nfsd4_putrootfh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID, .op_name = "OP_PUTPUBFH", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_PUTROOTFH] = { .op_func = (nfsd4op_func)nfsd4_putrootfh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID, .op_name = "OP_PUTROOTFH", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_READ] = { .op_func = (nfsd4op_func)nfsd4_read, .op_name = "OP_READ", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_read_rsize, + .op_rsize_bop = nfsd4_read_rsize, .op_get_currentstateid = nfsd4_get_readstateid, }, [OP_READDIR] = { .op_func = (nfsd4op_func)nfsd4_readdir, .op_name = "OP_READDIR", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_readdir_rsize, + .op_rsize_bop = nfsd4_readdir_rsize, }, [OP_READLINK] = { .op_func = (nfsd4op_func)nfsd4_readlink, .op_name = "OP_READLINK", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_readlink_rsize, + .op_rsize_bop = nfsd4_readlink_rsize, }, [OP_REMOVE] = { .op_func = (nfsd4op_func)nfsd4_remove, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_REMOVE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_remove_rsize, + .op_rsize_bop = nfsd4_remove_rsize, }, [OP_RENAME] = { .op_func = (nfsd4op_func)nfsd4_rename, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_RENAME", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_rename_rsize, + .op_rsize_bop = nfsd4_rename_rsize, }, [OP_RENEW] = { .op_func = (nfsd4op_func)nfsd4_renew, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING, .op_name = "OP_RENEW", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_RESTOREFH] = { @@ -2261,25 +2260,25 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING, .op_name = "OP_RESTOREFH", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_SAVEFH] = { .op_func = (nfsd4op_func)nfsd4_savefh, .op_flags = OP_HANDLES_WRONGSEC | OP_MODIFIES_SOMETHING, .op_name = "OP_SAVEFH", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_SECINFO] = { .op_func = (nfsd4op_func)nfsd4_secinfo, .op_flags = OP_HANDLES_WRONGSEC, .op_name = "OP_SECINFO", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_secinfo_rsize, + .op_rsize_bop = nfsd4_secinfo_rsize, }, [OP_SETATTR] = { .op_func = (nfsd4op_func)nfsd4_setattr, .op_name = "OP_SETATTR", .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, - .op_rsize_bop = (nfsd4op_rsize)nfsd4_setattr_rsize, + .op_rsize_bop = nfsd4_setattr_rsize, .op_get_currentstateid = nfsd4_get_setattrstateid, }, [OP_SETCLIENTID] = { @@ -2287,25 +2286,25 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_SETCLIENTID", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_setclientid_rsize, + .op_rsize_bop = nfsd4_setclientid_rsize, }, [OP_SETCLIENTID_CONFIRM] = { .op_func = (nfsd4op_func)nfsd4_setclientid_confirm, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_SETCLIENTID_CONFIRM", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_VERIFY] = { .op_func = (nfsd4op_func)nfsd4_verify, .op_name = "OP_VERIFY", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_WRITE] = { .op_func = (nfsd4op_func)nfsd4_write, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_WRITE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_write_rsize, + .op_rsize_bop = nfsd4_write_rsize, .op_get_currentstateid = nfsd4_get_writestateid, }, [OP_RELEASE_LOCKOWNER] = { @@ -2313,7 +2312,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING, .op_name = "OP_RELEASE_LOCKOWNER", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, /* NFSv4.1 operations */ @@ -2322,97 +2321,97 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_EXCHANGE_ID", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_exchange_id_rsize, + .op_rsize_bop = nfsd4_exchange_id_rsize, }, [OP_BACKCHANNEL_CTL] = { .op_func = (nfsd4op_func)nfsd4_backchannel_ctl, .op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING, .op_name = "OP_BACKCHANNEL_CTL", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_BIND_CONN_TO_SESSION] = { .op_func = (nfsd4op_func)nfsd4_bind_conn_to_session, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_BIND_CONN_TO_SESSION", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_bind_conn_to_session_rsize, + .op_rsize_bop = nfsd4_bind_conn_to_session_rsize, }, [OP_CREATE_SESSION] = { .op_func = (nfsd4op_func)nfsd4_create_session, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_CREATE_SESSION", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_create_session_rsize, + .op_rsize_bop = nfsd4_create_session_rsize, }, [OP_DESTROY_SESSION] = { .op_func = (nfsd4op_func)nfsd4_destroy_session, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_DESTROY_SESSION", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_SEQUENCE] = { .op_func = (nfsd4op_func)nfsd4_sequence, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP, .op_name = "OP_SEQUENCE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_sequence_rsize, + .op_rsize_bop = nfsd4_sequence_rsize, }, [OP_DESTROY_CLIENTID] = { .op_func = (nfsd4op_func)nfsd4_destroy_clientid, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_DESTROY_CLIENTID", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_RECLAIM_COMPLETE] = { .op_func = (nfsd4op_func)nfsd4_reclaim_complete, .op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING, .op_name = "OP_RECLAIM_COMPLETE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_SECINFO_NO_NAME] = { .op_func = (nfsd4op_func)nfsd4_secinfo_no_name, .op_flags = OP_HANDLES_WRONGSEC, .op_name = "OP_SECINFO_NO_NAME", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_secinfo_rsize, + .op_rsize_bop = nfsd4_secinfo_rsize, }, [OP_TEST_STATEID] = { .op_func = (nfsd4op_func)nfsd4_test_stateid, .op_flags = ALLOWED_WITHOUT_FH, .op_name = "OP_TEST_STATEID", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_test_stateid_rsize, + .op_rsize_bop = nfsd4_test_stateid_rsize, }, [OP_FREE_STATEID] = { .op_func = (nfsd4op_func)nfsd4_free_stateid, .op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING, .op_name = "OP_FREE_STATEID", .op_get_currentstateid = nfsd4_get_freestateid, - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, #ifdef CONFIG_NFSD_PNFS [OP_GETDEVICEINFO] = { .op_func = (nfsd4op_func)nfsd4_getdeviceinfo, .op_flags = ALLOWED_WITHOUT_FH, .op_name = "OP_GETDEVICEINFO", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_getdeviceinfo_rsize, + .op_rsize_bop = nfsd4_getdeviceinfo_rsize, }, [OP_LAYOUTGET] = { .op_func = (nfsd4op_func)nfsd4_layoutget, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LAYOUTGET", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutget_rsize, + .op_rsize_bop = nfsd4_layoutget_rsize, }, [OP_LAYOUTCOMMIT] = { .op_func = (nfsd4op_func)nfsd4_layoutcommit, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LAYOUTCOMMIT", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutcommit_rsize, + .op_rsize_bop = nfsd4_layoutcommit_rsize, }, [OP_LAYOUTRETURN] = { .op_func = (nfsd4op_func)nfsd4_layoutreturn, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LAYOUTRETURN", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutreturn_rsize, + .op_rsize_bop = nfsd4_layoutreturn_rsize, }, #endif /* CONFIG_NFSD_PNFS */ @@ -2421,30 +2420,30 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_func = (nfsd4op_func)nfsd4_allocate, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_ALLOCATE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_DEALLOCATE] = { .op_func = (nfsd4op_func)nfsd4_deallocate, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_DEALLOCATE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_CLONE] = { .op_func = (nfsd4op_func)nfsd4_clone, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_CLONE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_COPY] = { .op_func = (nfsd4op_func)nfsd4_copy, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_COPY", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_copy_rsize, + .op_rsize_bop = nfsd4_copy_rsize, }, [OP_SEEK] = { .op_func = (nfsd4op_func)nfsd4_seek, .op_name = "OP_SEEK", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_seek_rsize, + .op_rsize_bop = nfsd4_seek_rsize, }, }; -- cgit v1.2.3-59-g8ed1b From 72edc37a2c7a30a4bc64889a4eaa8bfd3d308a3a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 20:58:35 +0200 Subject: nfsd4: properly type op_func callbacks Pass union nfsd4_op_u to the op_func callbacks instead of using unsafe function pointer casts. It also adds two missing structures to struct nfsd4_op.u to facilitate this. Signed-off-by: Christoph Hellwig --- fs/nfsd/nfs4proc.c | 234 ++++++++++++++++++++++++++++------------------------ fs/nfsd/nfs4state.c | 82 +++++++++++------- fs/nfsd/xdr4.h | 66 +++++++-------- 3 files changed, 209 insertions(+), 173 deletions(-) diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index c1e31edf922d..403c1d14d99a 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -344,8 +344,9 @@ copy_clientid(clientid_t *clid, struct nfsd4_session *session) static __be32 nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_open *open) + union nfsd4_op_u *u) { + struct nfsd4_open *open = &u->open; __be32 status; struct svc_fh *resfh = NULL; struct net *net = SVC_NET(rqstp); @@ -467,14 +468,14 @@ out: */ static __be32 nfsd4_open_omfg(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_op *op) { - struct nfsd4_open *open = (struct nfsd4_open *)&op->u; + struct nfsd4_open *open = &op->u.open; if (!seqid_mutating_err(ntohl(op->status))) return op->status; if (nfsd4_has_session(cstate)) return op->status; open->op_xdr_error = op->status; - return nfsd4_open(rqstp, cstate, open); + return nfsd4_open(rqstp, cstate, &op->u); } /* @@ -482,19 +483,21 @@ static __be32 nfsd4_open_omfg(struct svc_rqst *rqstp, struct nfsd4_compound_stat */ static __be32 nfsd4_getfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct svc_fh **getfh) + union nfsd4_op_u *u) { if (!cstate->current_fh.fh_dentry) return nfserr_nofilehandle; - *getfh = &cstate->current_fh; + u->getfh = &cstate->current_fh; return nfs_ok; } static __be32 nfsd4_putfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_putfh *putfh) + union nfsd4_op_u *u) { + struct nfsd4_putfh *putfh = &u->putfh; + fh_put(&cstate->current_fh); cstate->current_fh.fh_handle.fh_size = putfh->pf_fhlen; memcpy(&cstate->current_fh.fh_handle.fh_base, putfh->pf_fhval, @@ -504,7 +507,7 @@ nfsd4_putfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_putrootfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - void *arg) + union nfsd4_op_u *u) { __be32 status; @@ -515,7 +518,7 @@ nfsd4_putrootfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_restorefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - void *arg) + union nfsd4_op_u *u) { if (!cstate->save_fh.fh_dentry) return nfserr_restorefh; @@ -530,7 +533,7 @@ nfsd4_restorefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_savefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - void *arg) + union nfsd4_op_u *u) { if (!cstate->current_fh.fh_dentry) return nfserr_nofilehandle; @@ -548,8 +551,10 @@ nfsd4_savefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, */ static __be32 nfsd4_access(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_access *access) + union nfsd4_op_u *u) { + struct nfsd4_access *access = &u->access; + if (access->ac_req_access & ~NFS3_ACCESS_FULL) return nfserr_inval; @@ -574,8 +579,10 @@ static void gen_boot_verifier(nfs4_verifier *verifier, struct net *net) static __be32 nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_commit *commit) + union nfsd4_op_u *u) { + struct nfsd4_commit *commit = &u->commit; + gen_boot_verifier(&commit->co_verf, SVC_NET(rqstp)); return nfsd_commit(rqstp, &cstate->current_fh, commit->co_offset, commit->co_count); @@ -583,8 +590,9 @@ nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_create *create) + union nfsd4_op_u *u) { + struct nfsd4_create *create = &u->create; struct svc_fh resfh; __be32 status; dev_t rdev; @@ -670,8 +678,9 @@ out: static __be32 nfsd4_getattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_getattr *getattr) + union nfsd4_op_u *u) { + struct nfsd4_getattr *getattr = &u->getattr; __be32 status; status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP); @@ -691,8 +700,9 @@ nfsd4_getattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_link(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_link *link) + union nfsd4_op_u *u) { + struct nfsd4_link *link = &u->link; __be32 status = nfserr_nofilehandle; if (!cstate->save_fh.fh_dentry) @@ -723,24 +733,25 @@ static __be32 nfsd4_do_lookupp(struct svc_rqst *rqstp, struct svc_fh *fh) static __be32 nfsd4_lookupp(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - void *arg) + union nfsd4_op_u *u) { return nfsd4_do_lookupp(rqstp, &cstate->current_fh); } static __be32 nfsd4_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_lookup *lookup) + union nfsd4_op_u *u) { return nfsd_lookup(rqstp, &cstate->current_fh, - lookup->lo_name, lookup->lo_len, + u->lookup.lo_name, u->lookup.lo_len, &cstate->current_fh); } static __be32 nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_read *read) + union nfsd4_op_u *u) { + struct nfsd4_read *read = &u->read; __be32 status; read->rd_filp = NULL; @@ -775,8 +786,9 @@ out: static __be32 nfsd4_readdir(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_readdir *readdir) + union nfsd4_op_u *u) { + struct nfsd4_readdir *readdir = &u->readdir; u64 cookie = readdir->rd_cookie; static const nfs4_verifier zeroverf; @@ -800,17 +812,18 @@ nfsd4_readdir(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_readlink(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_readlink *readlink) + union nfsd4_op_u *u) { - readlink->rl_rqstp = rqstp; - readlink->rl_fhp = &cstate->current_fh; + u->readlink.rl_rqstp = rqstp; + u->readlink.rl_fhp = &cstate->current_fh; return nfs_ok; } static __be32 nfsd4_remove(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_remove *remove) + union nfsd4_op_u *u) { + struct nfsd4_remove *remove = &u->remove; __be32 status; if (opens_in_grace(SVC_NET(rqstp))) @@ -826,8 +839,9 @@ nfsd4_remove(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_rename(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_rename *rename) + union nfsd4_op_u *u) { + struct nfsd4_rename *rename = &u->rename; __be32 status = nfserr_nofilehandle; if (!cstate->save_fh.fh_dentry) @@ -847,8 +861,9 @@ nfsd4_rename(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_secinfo *secinfo) + union nfsd4_op_u *u) { + struct nfsd4_secinfo *secinfo = &u->secinfo; struct svc_export *exp; struct dentry *dentry; __be32 err; @@ -876,11 +891,11 @@ nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_secinfo_no_name(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_secinfo_no_name *sin) + union nfsd4_op_u *u) { __be32 err; - switch (sin->sin_style) { + switch (u->secinfo_no_name.sin_style) { case NFS4_SECINFO_STYLE4_CURRENT_FH: break; case NFS4_SECINFO_STYLE4_PARENT: @@ -892,15 +907,16 @@ nfsd4_secinfo_no_name(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstat return nfserr_inval; } - sin->sin_exp = exp_get(cstate->current_fh.fh_export); + u->secinfo_no_name.sin_exp = exp_get(cstate->current_fh.fh_export); fh_put(&cstate->current_fh); return nfs_ok; } static __be32 nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_setattr *setattr) + union nfsd4_op_u *u) { + struct nfsd4_setattr *setattr = &u->setattr; __be32 status = nfs_ok; int err; @@ -960,8 +976,9 @@ static int fill_in_write_vector(struct kvec *vec, struct nfsd4_write *write) static __be32 nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_write *write) + union nfsd4_op_u *u) { + struct nfsd4_write *write = &u->write; stateid_t *stateid = &write->wr_stateid; struct file *filp = NULL; __be32 status = nfs_ok; @@ -1034,8 +1051,9 @@ out_put_src: static __be32 nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_clone *clone) + union nfsd4_op_u *u) { + struct nfsd4_clone *clone = &u->clone; struct file *src, *dst; __be32 status; @@ -1055,8 +1073,9 @@ out: static __be32 nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_copy *copy) + union nfsd4_op_u *u) { + struct nfsd4_copy *copy = &u->copy; struct file *src, *dst; __be32 status; ssize_t bytes; @@ -1111,23 +1130,24 @@ nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_allocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_fallocate *fallocate) + union nfsd4_op_u *u) { - return nfsd4_fallocate(rqstp, cstate, fallocate, 0); + return nfsd4_fallocate(rqstp, cstate, &u->allocate, 0); } static __be32 nfsd4_deallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_fallocate *fallocate) + union nfsd4_op_u *u) { - return nfsd4_fallocate(rqstp, cstate, fallocate, + return nfsd4_fallocate(rqstp, cstate, &u->deallocate, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE); } static __be32 nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_seek *seek) + union nfsd4_op_u *u) { + struct nfsd4_seek *seek = &u->seek; int whence; __be32 status; struct file *file; @@ -1232,21 +1252,21 @@ out_kfree: static __be32 nfsd4_nverify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_verify *verify) + union nfsd4_op_u *u) { __be32 status; - status = _nfsd4_verify(rqstp, cstate, verify); + status = _nfsd4_verify(rqstp, cstate, &u->verify); return status == nfserr_not_same ? nfs_ok : status; } static __be32 nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_verify *verify) + union nfsd4_op_u *u) { __be32 status; - status = _nfsd4_verify(rqstp, cstate, verify); + status = _nfsd4_verify(rqstp, cstate, &u->nverify); return status == nfserr_same ? nfs_ok : status; } @@ -1271,9 +1291,9 @@ nfsd4_layout_verify(struct svc_export *exp, unsigned int layout_type) static __be32 nfsd4_getdeviceinfo(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_getdeviceinfo *gdp) + struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct nfsd4_getdeviceinfo *gdp = &u->getdeviceinfo; const struct nfsd4_layout_ops *ops; struct nfsd4_deviceid_map *map; struct svc_export *exp; @@ -1317,9 +1337,9 @@ out: static __be32 nfsd4_layoutget(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_layoutget *lgp) + struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct nfsd4_layoutget *lgp = &u->layoutget; struct svc_fh *current_fh = &cstate->current_fh; const struct nfsd4_layout_ops *ops; struct nfs4_layout_stateid *ls; @@ -1397,9 +1417,9 @@ out: static __be32 nfsd4_layoutcommit(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_layoutcommit *lcp) + struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct nfsd4_layoutcommit *lcp = &u->layoutcommit; const struct nfsd4_layout_seg *seg = &lcp->lc_seg; struct svc_fh *current_fh = &cstate->current_fh; const struct nfsd4_layout_ops *ops; @@ -1461,9 +1481,9 @@ out: static __be32 nfsd4_layoutreturn(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_layoutreturn *lrp) + struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct nfsd4_layoutreturn *lrp = &u->layoutreturn; struct svc_fh *current_fh = &cstate->current_fh; __be32 nfserr; @@ -1521,9 +1541,6 @@ static inline void nfsd4_increment_op_stats(u32 opnum) nfsdstats.nfs4_opcount[opnum]++; } -typedef __be32(*nfsd4op_func)(struct svc_rqst *, struct nfsd4_compound_state *, - void *); - enum nfsd4_op_flags { ALLOWED_WITHOUT_FH = 1 << 0, /* No current filehandle required */ ALLOWED_ON_ABSENT_FS = 1 << 1, /* ops processed on absent fs */ @@ -1555,7 +1572,8 @@ enum nfsd4_op_flags { }; struct nfsd4_operation { - nfsd4op_func op_func; + __be32 (*op_func)(struct svc_rqst *, struct nfsd4_compound_state *, + union nfsd4_op_u *); u32 op_flags; char *op_name; /* Try to get response size before operation */ @@ -2092,12 +2110,12 @@ static inline u32 nfsd4_seek_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) static struct nfsd4_operation nfsd4_ops[] = { [OP_ACCESS] = { - .op_func = (nfsd4op_func)nfsd4_access, + .op_func = nfsd4_access, .op_name = "OP_ACCESS", .op_rsize_bop = nfsd4_access_rsize, }, [OP_CLOSE] = { - .op_func = (nfsd4op_func)nfsd4_close, + .op_func = nfsd4_close, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_CLOSE", .op_rsize_bop = nfsd4_status_stateid_rsize, @@ -2105,93 +2123,93 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_set_currentstateid = nfsd4_set_closestateid, }, [OP_COMMIT] = { - .op_func = (nfsd4op_func)nfsd4_commit, + .op_func = nfsd4_commit, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_COMMIT", .op_rsize_bop = nfsd4_commit_rsize, }, [OP_CREATE] = { - .op_func = (nfsd4op_func)nfsd4_create, + .op_func = nfsd4_create, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME | OP_CLEAR_STATEID, .op_name = "OP_CREATE", .op_rsize_bop = nfsd4_create_rsize, }, [OP_DELEGRETURN] = { - .op_func = (nfsd4op_func)nfsd4_delegreturn, + .op_func = nfsd4_delegreturn, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_DELEGRETURN", .op_rsize_bop = nfsd4_only_status_rsize, .op_get_currentstateid = nfsd4_get_delegreturnstateid, }, [OP_GETATTR] = { - .op_func = (nfsd4op_func)nfsd4_getattr, + .op_func = nfsd4_getattr, .op_flags = ALLOWED_ON_ABSENT_FS, .op_rsize_bop = nfsd4_getattr_rsize, .op_name = "OP_GETATTR", }, [OP_GETFH] = { - .op_func = (nfsd4op_func)nfsd4_getfh, + .op_func = nfsd4_getfh, .op_name = "OP_GETFH", .op_rsize_bop = nfsd4_getfh_rsize, }, [OP_LINK] = { - .op_func = (nfsd4op_func)nfsd4_link, + .op_func = nfsd4_link, .op_flags = ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_LINK", .op_rsize_bop = nfsd4_link_rsize, }, [OP_LOCK] = { - .op_func = (nfsd4op_func)nfsd4_lock, + .op_func = nfsd4_lock, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LOCK", .op_rsize_bop = nfsd4_lock_rsize, .op_set_currentstateid = nfsd4_set_lockstateid, }, [OP_LOCKT] = { - .op_func = (nfsd4op_func)nfsd4_lockt, + .op_func = nfsd4_lockt, .op_name = "OP_LOCKT", .op_rsize_bop = nfsd4_lock_rsize, }, [OP_LOCKU] = { - .op_func = (nfsd4op_func)nfsd4_locku, + .op_func = nfsd4_locku, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LOCKU", .op_rsize_bop = nfsd4_status_stateid_rsize, .op_get_currentstateid = nfsd4_get_lockustateid, }, [OP_LOOKUP] = { - .op_func = (nfsd4op_func)nfsd4_lookup, + .op_func = nfsd4_lookup, .op_flags = OP_HANDLES_WRONGSEC | OP_CLEAR_STATEID, .op_name = "OP_LOOKUP", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_LOOKUPP] = { - .op_func = (nfsd4op_func)nfsd4_lookupp, + .op_func = nfsd4_lookupp, .op_flags = OP_HANDLES_WRONGSEC | OP_CLEAR_STATEID, .op_name = "OP_LOOKUPP", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_NVERIFY] = { - .op_func = (nfsd4op_func)nfsd4_nverify, + .op_func = nfsd4_nverify, .op_name = "OP_NVERIFY", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_OPEN] = { - .op_func = (nfsd4op_func)nfsd4_open, + .op_func = nfsd4_open, .op_flags = OP_HANDLES_WRONGSEC | OP_MODIFIES_SOMETHING, .op_name = "OP_OPEN", .op_rsize_bop = nfsd4_open_rsize, .op_set_currentstateid = nfsd4_set_openstateid, }, [OP_OPEN_CONFIRM] = { - .op_func = (nfsd4op_func)nfsd4_open_confirm, + .op_func = nfsd4_open_confirm, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_OPEN_CONFIRM", .op_rsize_bop = nfsd4_status_stateid_rsize, }, [OP_OPEN_DOWNGRADE] = { - .op_func = (nfsd4op_func)nfsd4_open_downgrade, + .op_func = nfsd4_open_downgrade, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_OPEN_DOWNGRADE", .op_rsize_bop = nfsd4_status_stateid_rsize, @@ -2199,56 +2217,56 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_set_currentstateid = nfsd4_set_opendowngradestateid, }, [OP_PUTFH] = { - .op_func = (nfsd4op_func)nfsd4_putfh, + .op_func = nfsd4_putfh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID, .op_name = "OP_PUTFH", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_PUTPUBFH] = { - .op_func = (nfsd4op_func)nfsd4_putrootfh, + .op_func = nfsd4_putrootfh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID, .op_name = "OP_PUTPUBFH", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_PUTROOTFH] = { - .op_func = (nfsd4op_func)nfsd4_putrootfh, + .op_func = nfsd4_putrootfh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID, .op_name = "OP_PUTROOTFH", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_READ] = { - .op_func = (nfsd4op_func)nfsd4_read, + .op_func = nfsd4_read, .op_name = "OP_READ", .op_rsize_bop = nfsd4_read_rsize, .op_get_currentstateid = nfsd4_get_readstateid, }, [OP_READDIR] = { - .op_func = (nfsd4op_func)nfsd4_readdir, + .op_func = nfsd4_readdir, .op_name = "OP_READDIR", .op_rsize_bop = nfsd4_readdir_rsize, }, [OP_READLINK] = { - .op_func = (nfsd4op_func)nfsd4_readlink, + .op_func = nfsd4_readlink, .op_name = "OP_READLINK", .op_rsize_bop = nfsd4_readlink_rsize, }, [OP_REMOVE] = { - .op_func = (nfsd4op_func)nfsd4_remove, + .op_func = nfsd4_remove, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_REMOVE", .op_rsize_bop = nfsd4_remove_rsize, }, [OP_RENAME] = { - .op_func = (nfsd4op_func)nfsd4_rename, + .op_func = nfsd4_rename, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_RENAME", .op_rsize_bop = nfsd4_rename_rsize, }, [OP_RENEW] = { - .op_func = (nfsd4op_func)nfsd4_renew, + .op_func = nfsd4_renew, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING, .op_name = "OP_RENEW", @@ -2256,59 +2274,59 @@ static struct nfsd4_operation nfsd4_ops[] = { }, [OP_RESTOREFH] = { - .op_func = (nfsd4op_func)nfsd4_restorefh, + .op_func = nfsd4_restorefh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING, .op_name = "OP_RESTOREFH", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_SAVEFH] = { - .op_func = (nfsd4op_func)nfsd4_savefh, + .op_func = nfsd4_savefh, .op_flags = OP_HANDLES_WRONGSEC | OP_MODIFIES_SOMETHING, .op_name = "OP_SAVEFH", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_SECINFO] = { - .op_func = (nfsd4op_func)nfsd4_secinfo, + .op_func = nfsd4_secinfo, .op_flags = OP_HANDLES_WRONGSEC, .op_name = "OP_SECINFO", .op_rsize_bop = nfsd4_secinfo_rsize, }, [OP_SETATTR] = { - .op_func = (nfsd4op_func)nfsd4_setattr, + .op_func = nfsd4_setattr, .op_name = "OP_SETATTR", .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_rsize_bop = nfsd4_setattr_rsize, .op_get_currentstateid = nfsd4_get_setattrstateid, }, [OP_SETCLIENTID] = { - .op_func = (nfsd4op_func)nfsd4_setclientid, + .op_func = nfsd4_setclientid, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_SETCLIENTID", .op_rsize_bop = nfsd4_setclientid_rsize, }, [OP_SETCLIENTID_CONFIRM] = { - .op_func = (nfsd4op_func)nfsd4_setclientid_confirm, + .op_func = nfsd4_setclientid_confirm, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_SETCLIENTID_CONFIRM", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_VERIFY] = { - .op_func = (nfsd4op_func)nfsd4_verify, + .op_func = nfsd4_verify, .op_name = "OP_VERIFY", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_WRITE] = { - .op_func = (nfsd4op_func)nfsd4_write, + .op_func = nfsd4_write, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_WRITE", .op_rsize_bop = nfsd4_write_rsize, .op_get_currentstateid = nfsd4_get_writestateid, }, [OP_RELEASE_LOCKOWNER] = { - .op_func = (nfsd4op_func)nfsd4_release_lockowner, + .op_func = nfsd4_release_lockowner, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING, .op_name = "OP_RELEASE_LOCKOWNER", @@ -2317,72 +2335,72 @@ static struct nfsd4_operation nfsd4_ops[] = { /* NFSv4.1 operations */ [OP_EXCHANGE_ID] = { - .op_func = (nfsd4op_func)nfsd4_exchange_id, + .op_func = nfsd4_exchange_id, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_EXCHANGE_ID", .op_rsize_bop = nfsd4_exchange_id_rsize, }, [OP_BACKCHANNEL_CTL] = { - .op_func = (nfsd4op_func)nfsd4_backchannel_ctl, + .op_func = nfsd4_backchannel_ctl, .op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING, .op_name = "OP_BACKCHANNEL_CTL", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_BIND_CONN_TO_SESSION] = { - .op_func = (nfsd4op_func)nfsd4_bind_conn_to_session, + .op_func = nfsd4_bind_conn_to_session, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_BIND_CONN_TO_SESSION", .op_rsize_bop = nfsd4_bind_conn_to_session_rsize, }, [OP_CREATE_SESSION] = { - .op_func = (nfsd4op_func)nfsd4_create_session, + .op_func = nfsd4_create_session, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_CREATE_SESSION", .op_rsize_bop = nfsd4_create_session_rsize, }, [OP_DESTROY_SESSION] = { - .op_func = (nfsd4op_func)nfsd4_destroy_session, + .op_func = nfsd4_destroy_session, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_DESTROY_SESSION", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_SEQUENCE] = { - .op_func = (nfsd4op_func)nfsd4_sequence, + .op_func = nfsd4_sequence, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP, .op_name = "OP_SEQUENCE", .op_rsize_bop = nfsd4_sequence_rsize, }, [OP_DESTROY_CLIENTID] = { - .op_func = (nfsd4op_func)nfsd4_destroy_clientid, + .op_func = nfsd4_destroy_clientid, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_DESTROY_CLIENTID", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_RECLAIM_COMPLETE] = { - .op_func = (nfsd4op_func)nfsd4_reclaim_complete, + .op_func = nfsd4_reclaim_complete, .op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING, .op_name = "OP_RECLAIM_COMPLETE", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_SECINFO_NO_NAME] = { - .op_func = (nfsd4op_func)nfsd4_secinfo_no_name, + .op_func = nfsd4_secinfo_no_name, .op_flags = OP_HANDLES_WRONGSEC, .op_name = "OP_SECINFO_NO_NAME", .op_rsize_bop = nfsd4_secinfo_rsize, }, [OP_TEST_STATEID] = { - .op_func = (nfsd4op_func)nfsd4_test_stateid, + .op_func = nfsd4_test_stateid, .op_flags = ALLOWED_WITHOUT_FH, .op_name = "OP_TEST_STATEID", .op_rsize_bop = nfsd4_test_stateid_rsize, }, [OP_FREE_STATEID] = { - .op_func = (nfsd4op_func)nfsd4_free_stateid, + .op_func = nfsd4_free_stateid, .op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING, .op_name = "OP_FREE_STATEID", .op_get_currentstateid = nfsd4_get_freestateid, @@ -2390,25 +2408,25 @@ static struct nfsd4_operation nfsd4_ops[] = { }, #ifdef CONFIG_NFSD_PNFS [OP_GETDEVICEINFO] = { - .op_func = (nfsd4op_func)nfsd4_getdeviceinfo, + .op_func = nfsd4_getdeviceinfo, .op_flags = ALLOWED_WITHOUT_FH, .op_name = "OP_GETDEVICEINFO", .op_rsize_bop = nfsd4_getdeviceinfo_rsize, }, [OP_LAYOUTGET] = { - .op_func = (nfsd4op_func)nfsd4_layoutget, + .op_func = nfsd4_layoutget, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LAYOUTGET", .op_rsize_bop = nfsd4_layoutget_rsize, }, [OP_LAYOUTCOMMIT] = { - .op_func = (nfsd4op_func)nfsd4_layoutcommit, + .op_func = nfsd4_layoutcommit, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LAYOUTCOMMIT", .op_rsize_bop = nfsd4_layoutcommit_rsize, }, [OP_LAYOUTRETURN] = { - .op_func = (nfsd4op_func)nfsd4_layoutreturn, + .op_func = nfsd4_layoutreturn, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LAYOUTRETURN", .op_rsize_bop = nfsd4_layoutreturn_rsize, @@ -2417,31 +2435,31 @@ static struct nfsd4_operation nfsd4_ops[] = { /* NFSv4.2 operations */ [OP_ALLOCATE] = { - .op_func = (nfsd4op_func)nfsd4_allocate, + .op_func = nfsd4_allocate, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_ALLOCATE", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_DEALLOCATE] = { - .op_func = (nfsd4op_func)nfsd4_deallocate, + .op_func = nfsd4_deallocate, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_DEALLOCATE", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_CLONE] = { - .op_func = (nfsd4op_func)nfsd4_clone, + .op_func = nfsd4_clone, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_CLONE", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_COPY] = { - .op_func = (nfsd4op_func)nfsd4_copy, + .op_func = nfsd4_copy, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_COPY", .op_rsize_bop = nfsd4_copy_rsize, }, [OP_SEEK] = { - .op_func = (nfsd4op_func)nfsd4_seek, + .op_func = nfsd4_seek, .op_name = "OP_SEEK", .op_rsize_bop = nfsd4_seek_rsize, }, diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 01ab21f8d34d..0c04f81aa63b 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -2402,10 +2402,10 @@ static bool client_has_state(struct nfs4_client *clp) } __be32 -nfsd4_exchange_id(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_exchange_id *exid) +nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { + struct nfsd4_exchange_id *exid = &u->exchange_id; struct nfs4_client *conf, *new; struct nfs4_client *unconf = NULL; __be32 status; @@ -2698,9 +2698,9 @@ static __be32 nfsd4_check_cb_sec(struct nfsd4_cb_sec *cbs) __be32 nfsd4_create_session(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_create_session *cr_ses) + struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct nfsd4_create_session *cr_ses = &u->create_session; struct sockaddr *sa = svc_addr(rqstp); struct nfs4_client *conf, *unconf; struct nfs4_client *old = NULL; @@ -2824,8 +2824,11 @@ static __be32 nfsd4_map_bcts_dir(u32 *dir) return nfserr_inval; } -__be32 nfsd4_backchannel_ctl(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_backchannel_ctl *bc) +__be32 nfsd4_backchannel_ctl(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { + struct nfsd4_backchannel_ctl *bc = &u->backchannel_ctl; struct nfsd4_session *session = cstate->session; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); __be32 status; @@ -2845,8 +2848,9 @@ __be32 nfsd4_backchannel_ctl(struct svc_rqst *rqstp, struct nfsd4_compound_state __be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_bind_conn_to_session *bcts) + union nfsd4_op_u *u) { + struct nfsd4_bind_conn_to_session *bcts = &u->bind_conn_to_session; __be32 status; struct nfsd4_conn *conn; struct nfsd4_session *session; @@ -2886,10 +2890,10 @@ static bool nfsd4_compound_in_session(struct nfsd4_session *session, struct nfs4 } __be32 -nfsd4_destroy_session(struct svc_rqst *r, - struct nfsd4_compound_state *cstate, - struct nfsd4_destroy_session *sessionid) +nfsd4_destroy_session(struct svc_rqst *r, struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { + struct nfsd4_destroy_session *sessionid = &u->destroy_session; struct nfsd4_session *ses; __be32 status; int ref_held_by_me = 0; @@ -2983,10 +2987,10 @@ static bool nfsd4_request_too_big(struct svc_rqst *rqstp, } __be32 -nfsd4_sequence(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_sequence *seq) +nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { + struct nfsd4_sequence *seq = &u->sequence; struct nfsd4_compoundres *resp = rqstp->rq_resp; struct xdr_stream *xdr = &resp->xdr; struct nfsd4_session *session; @@ -3120,8 +3124,11 @@ nfsd4_sequence_done(struct nfsd4_compoundres *resp) } __be32 -nfsd4_destroy_clientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_destroy_clientid *dc) +nfsd4_destroy_clientid(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { + struct nfsd4_destroy_clientid *dc = &u->destroy_clientid; struct nfs4_client *conf, *unconf; struct nfs4_client *clp = NULL; __be32 status = 0; @@ -3161,8 +3168,10 @@ out: } __be32 -nfsd4_reclaim_complete(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_reclaim_complete *rc) +nfsd4_reclaim_complete(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct nfsd4_reclaim_complete *rc = &u->reclaim_complete; __be32 status = 0; if (rc->rca_one_fs) { @@ -3199,8 +3208,9 @@ out: __be32 nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_setclientid *setclid) + union nfsd4_op_u *u) { + struct nfsd4_setclientid *setclid = &u->setclientid; struct xdr_netobj clname = setclid->se_name; nfs4_verifier clverifier = setclid->se_verf; struct nfs4_client *conf, *new; @@ -3257,9 +3267,11 @@ out: __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_setclientid_confirm *setclientid_confirm) + struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { + struct nfsd4_setclientid_confirm *setclientid_confirm = + &u->setclientid_confirm; struct nfs4_client *conf, *unconf; struct nfs4_client *old = NULL; nfs4_verifier confirm = setclientid_confirm->sc_confirm; @@ -4506,8 +4518,9 @@ void nfsd4_cleanup_open_state(struct nfsd4_compound_state *cstate, __be32 nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - clientid_t *clid) + union nfsd4_op_u *u) { + clientid_t *clid = &u->renew; struct nfs4_client *clp; __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); @@ -4993,8 +5006,9 @@ out: */ __be32 nfsd4_test_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_test_stateid *test_stateid) + union nfsd4_op_u *u) { + struct nfsd4_test_stateid *test_stateid = &u->test_stateid; struct nfsd4_test_stateid_id *stateid; struct nfs4_client *cl = cstate->session->se_client; @@ -5033,8 +5047,9 @@ out: __be32 nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_free_stateid *free_stateid) + union nfsd4_op_u *u) { + struct nfsd4_free_stateid *free_stateid = &u->free_stateid; stateid_t *stateid = &free_stateid->fr_stateid; struct nfs4_stid *s; struct nfs4_delegation *dp; @@ -5162,8 +5177,9 @@ static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cs __be32 nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_open_confirm *oc) + union nfsd4_op_u *u) { + struct nfsd4_open_confirm *oc = &u->open_confirm; __be32 status; struct nfs4_openowner *oo; struct nfs4_ol_stateid *stp; @@ -5230,9 +5246,9 @@ static inline void nfs4_stateid_downgrade(struct nfs4_ol_stateid *stp, u32 to_ac __be32 nfsd4_open_downgrade(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_open_downgrade *od) + struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct nfsd4_open_downgrade *od = &u->open_downgrade; __be32 status; struct nfs4_ol_stateid *stp; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); @@ -5300,8 +5316,9 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s) */ __be32 nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_close *close) + union nfsd4_op_u *u) { + struct nfsd4_close *close = &u->close; __be32 status; struct nfs4_ol_stateid *stp; struct net *net = SVC_NET(rqstp); @@ -5330,8 +5347,9 @@ out: __be32 nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_delegreturn *dr) + union nfsd4_op_u *u) { + struct nfsd4_delegreturn *dr = &u->delegreturn; struct nfs4_delegation *dp; stateid_t *stateid = &dr->dr_stateid; struct nfs4_stid *s; @@ -5706,8 +5724,9 @@ out: */ __be32 nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_lock *lock) + union nfsd4_op_u *u) { + struct nfsd4_lock *lock = &u->lock; struct nfs4_openowner *open_sop = NULL; struct nfs4_lockowner *lock_sop = NULL; struct nfs4_ol_stateid *lock_stp = NULL; @@ -5939,8 +5958,9 @@ static __be32 nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct */ __be32 nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_lockt *lockt) + union nfsd4_op_u *u) { + struct nfsd4_lockt *lockt = &u->lockt; struct file_lock *file_lock = NULL; struct nfs4_lockowner *lo = NULL; __be32 status; @@ -6012,8 +6032,9 @@ out: __be32 nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_locku *locku) + union nfsd4_op_u *u) { + struct nfsd4_locku *locku = &u->locku; struct nfs4_ol_stateid *stp; struct file *filp = NULL; struct file_lock *file_lock = NULL; @@ -6119,8 +6140,9 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) __be32 nfsd4_release_lockowner(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_release_lockowner *rlockowner) + union nfsd4_op_u *u) { + struct nfsd4_release_lockowner *rlockowner = &u->release_lockowner; clientid_t *clid = &rlockowner->rl_clientid; struct nfs4_stateowner *sop; struct nfs4_lockowner *lo = NULL; diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index b625f4aa1061..72c6ad136107 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -577,6 +577,7 @@ struct nfsd4_op { struct nfsd4_bind_conn_to_session bind_conn_to_session; struct nfsd4_create_session create_session; struct nfsd4_destroy_session destroy_session; + struct nfsd4_destroy_clientid destroy_clientid; struct nfsd4_sequence sequence; struct nfsd4_reclaim_complete reclaim_complete; struct nfsd4_test_stateid test_stateid; @@ -585,6 +586,7 @@ struct nfsd4_op { struct nfsd4_layoutget layoutget; struct nfsd4_layoutcommit layoutcommit; struct nfsd4_layoutreturn layoutreturn; + struct nfsd4_secinfo_no_name secinfo_no_name; /* NFSv4.2 */ struct nfsd4_fallocate allocate; @@ -693,27 +695,26 @@ __be32 nfsd4_encode_fattr_to_buf(__be32 **p, int words, struct dentry *dentry, u32 *bmval, struct svc_rqst *, int ignore_crossmnt); extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_setclientid *setclid); + struct nfsd4_compound_state *, union nfsd4_op_u *u); extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_setclientid_confirm *setclientid_confirm); + struct nfsd4_compound_state *, union nfsd4_op_u *u); extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, struct nfsd4_exchange_id *); -extern __be32 nfsd4_backchannel_ctl(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_backchannel_ctl *); -extern __be32 nfsd4_bind_conn_to_session(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_bind_conn_to_session *); + struct nfsd4_compound_state *, union nfsd4_op_u *u); +extern __be32 nfsd4_backchannel_ctl(struct svc_rqst *, + struct nfsd4_compound_state *, union nfsd4_op_u *u); +extern __be32 nfsd4_bind_conn_to_session(struct svc_rqst *, + struct nfsd4_compound_state *, union nfsd4_op_u *u); extern __be32 nfsd4_create_session(struct svc_rqst *, - struct nfsd4_compound_state *, - struct nfsd4_create_session *); + struct nfsd4_compound_state *, union nfsd4_op_u *u); extern __be32 nfsd4_sequence(struct svc_rqst *, - struct nfsd4_compound_state *, - struct nfsd4_sequence *); + struct nfsd4_compound_state *, union nfsd4_op_u *u); extern void nfsd4_sequence_done(struct nfsd4_compoundres *resp); extern __be32 nfsd4_destroy_session(struct svc_rqst *, - struct nfsd4_compound_state *, - struct nfsd4_destroy_session *); -extern __be32 nfsd4_destroy_clientid(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_destroy_clientid *); -__be32 nfsd4_reclaim_complete(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_reclaim_complete *); + struct nfsd4_compound_state *, union nfsd4_op_u *u); +extern __be32 nfsd4_destroy_clientid(struct svc_rqst *, struct nfsd4_compound_state *, + union nfsd4_op_u *u); +__be32 nfsd4_reclaim_complete(struct svc_rqst *, struct nfsd4_compound_state *, + union nfsd4_op_u *u); extern __be32 nfsd4_process_open1(struct nfsd4_compound_state *, struct nfsd4_open *open, struct nfsd_net *nn); extern __be32 nfsd4_process_open2(struct svc_rqst *rqstp, @@ -722,34 +723,29 @@ extern void nfsd4_cstate_clear_replay(struct nfsd4_compound_state *cstate); extern void nfsd4_cleanup_open_state(struct nfsd4_compound_state *cstate, struct nfsd4_open *open); extern __be32 nfsd4_open_confirm(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, struct nfsd4_open_confirm *oc); -extern __be32 nfsd4_close(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_close *close); + struct nfsd4_compound_state *, union nfsd4_op_u *u); +extern __be32 nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *, + union nfsd4_op_u *u); extern __be32 nfsd4_open_downgrade(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_open_downgrade *od); + struct nfsd4_compound_state *, union nfsd4_op_u *u); extern __be32 nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *, - struct nfsd4_lock *lock); -extern __be32 nfsd4_lockt(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_lockt *lockt); -extern __be32 nfsd4_locku(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_locku *locku); + union nfsd4_op_u *u); +extern __be32 nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *, + union nfsd4_op_u *u); +extern __be32 nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *, + union nfsd4_op_u *u); extern __be32 nfsd4_release_lockowner(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_release_lockowner *rlockowner); + struct nfsd4_compound_state *, union nfsd4_op_u *u); extern void nfsd4_release_compoundargs(struct svc_rqst *rqstp); extern __be32 nfsd4_delegreturn(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, struct nfsd4_delegreturn *dr); -extern __be32 nfsd4_renew(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, clientid_t *clid); + struct nfsd4_compound_state *, union nfsd4_op_u *u); +extern __be32 nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *, + union nfsd4_op_u *u); extern __be32 nfsd4_test_stateid(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, struct nfsd4_test_stateid *test_stateid); + struct nfsd4_compound_state *, union nfsd4_op_u *); extern __be32 nfsd4_free_stateid(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, struct nfsd4_free_stateid *free_stateid); + struct nfsd4_compound_state *, union nfsd4_op_u *); extern void nfsd4_bump_seqid(struct nfsd4_compound_state *, __be32 nfserr); #endif -- cgit v1.2.3-59-g8ed1b From 0becc1181cdba562730be4d4b8a5fcb4368ef527 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 23:40:27 +0200 Subject: sunrpc: move pc_count out of struct svc_procinfo pc_count is the only writeable memeber of struct svc_procinfo, which is a good candidate to be const-ified as it contains function pointers. This patch moves it into out out struct svc_procinfo, and into a separate writable array that is pointed to by struct svc_version. Signed-off-by: Christoph Hellwig --- fs/lockd/svc.c | 6 ++++++ fs/nfs/callback_xdr.c | 4 ++++ fs/nfsd/nfs2acl.c | 2 ++ fs/nfsd/nfs3acl.c | 2 ++ fs/nfsd/nfs3proc.c | 2 ++ fs/nfsd/nfs4proc.c | 2 ++ fs/nfsd/nfsproc.c | 2 ++ include/linux/sunrpc/svc.h | 2 +- net/sunrpc/stats.c | 11 ++++++----- net/sunrpc/svc.c | 2 +- 10 files changed, 28 insertions(+), 7 deletions(-) diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 5d481e8a1b5d..cc6abe6280bc 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -739,23 +739,29 @@ module_exit(exit_nlm); /* * Define NLM program and procedures */ +static unsigned int nlmsvc_version1_count[17]; static struct svc_version nlmsvc_version1 = { .vs_vers = 1, .vs_nproc = 17, .vs_proc = nlmsvc_procedures, + .vs_count = nlmsvc_version1_count, .vs_xdrsize = NLMSVC_XDRSIZE, }; +static unsigned int nlmsvc_version3_count[24]; static struct svc_version nlmsvc_version3 = { .vs_vers = 3, .vs_nproc = 24, .vs_proc = nlmsvc_procedures, + .vs_count = nlmsvc_version3_count, .vs_xdrsize = NLMSVC_XDRSIZE, }; #ifdef CONFIG_LOCKD_V4 +static unsigned int nlmsvc_version4_count[24]; static struct svc_version nlmsvc_version4 = { .vs_vers = 4, .vs_nproc = 24, .vs_proc = nlmsvc_procedures4, + .vs_count = nlmsvc_version4_count, .vs_xdrsize = NLMSVC_XDRSIZE, }; #endif diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index acf75dc63e14..ecd46b8c0985 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -1011,20 +1011,24 @@ static struct svc_procedure nfs4_callback_procedures1[] = { } }; +static unsigned int nfs4_callback_count1[ARRAY_SIZE(nfs4_callback_procedures1)]; struct svc_version nfs4_callback_version1 = { .vs_vers = 1, .vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1), .vs_proc = nfs4_callback_procedures1, + .vs_count = nfs4_callback_count1, .vs_xdrsize = NFS4_CALLBACK_XDRSIZE, .vs_dispatch = NULL, .vs_hidden = true, .vs_need_cong_ctrl = true, }; +static unsigned int nfs4_callback_count4[ARRAY_SIZE(nfs4_callback_procedures1)]; struct svc_version nfs4_callback_version4 = { .vs_vers = 4, .vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1), .vs_proc = nfs4_callback_procedures1, + .vs_count = nfs4_callback_count4, .vs_xdrsize = NFS4_CALLBACK_XDRSIZE, .vs_dispatch = NULL, .vs_hidden = true, diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index fc6b179c8fff..026edfe73fd5 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -378,10 +378,12 @@ static struct svc_procedure nfsd_acl_procedures2[] = { PROC(access, access, access, access, RC_NOCACHE, ST+AT+1), }; +static unsigned int nfsd_acl_count2[ARRAY_SIZE(nfsd_acl_procedures2)]; struct svc_version nfsd_acl_version2 = { .vs_vers = 2, .vs_nproc = 5, .vs_proc = nfsd_acl_procedures2, + .vs_count = nfsd_acl_count2, .vs_dispatch = nfsd_dispatch, .vs_xdrsize = NFS3_SVC_XDRSIZE, }; diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 9437b758cbfd..73c0970ccefb 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -263,10 +263,12 @@ static struct svc_procedure nfsd_acl_procedures3[] = { PROC(setacl, setacl, setacl, fhandle, RC_NOCACHE, ST+pAT), }; +static unsigned int nfsd_acl_count3[ARRAY_SIZE(nfsd_acl_procedures3)]; struct svc_version nfsd_acl_version3 = { .vs_vers = 3, .vs_nproc = 3, .vs_proc = nfsd_acl_procedures3, + .vs_count = nfsd_acl_count3, .vs_dispatch = nfsd_dispatch, .vs_xdrsize = NFS3_SVC_XDRSIZE, }; diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 17c90c41a3a6..b5823802e278 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -890,10 +890,12 @@ static struct svc_procedure nfsd_procedures3[22] = { }, }; +static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures3)]; struct svc_version nfsd_version3 = { .vs_vers = 3, .vs_nproc = 22, .vs_proc = nfsd_procedures3, + .vs_count = nfsd_count3, .vs_dispatch = nfsd_dispatch, .vs_xdrsize = NFS3_SVC_XDRSIZE, }; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 403c1d14d99a..4de6a9950722 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -2553,10 +2553,12 @@ static struct svc_procedure nfsd_procedures4[2] = { }, }; +static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures4)]; struct svc_version nfsd_version4 = { .vs_vers = 4, .vs_nproc = 2, .vs_proc = nfsd_procedures4, + .vs_count = nfsd_count3, .vs_dispatch = nfsd_dispatch, .vs_xdrsize = NFS4_SVC_XDRSIZE, .vs_rpcb_optnl = true, diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 0ef88d0e67d9..44b157553733 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -743,10 +743,12 @@ static struct svc_procedure nfsd_procedures2[18] = { }; +static unsigned int nfsd_count2[ARRAY_SIZE(nfsd_procedures2)]; struct svc_version nfsd_version2 = { .vs_vers = 2, .vs_nproc = 18, .vs_proc = nfsd_procedures2, + .vs_count = nfsd_count2, .vs_dispatch = nfsd_dispatch, .vs_xdrsize = NFS2_SVC_XDRSIZE, }; diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index bd9e313c444a..bcd114f038ef 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -398,6 +398,7 @@ struct svc_version { u32 vs_vers; /* version number */ u32 vs_nproc; /* number of procedures */ struct svc_procedure * vs_proc; /* per-procedure info */ + unsigned int *vs_count; /* call counts */ u32 vs_xdrsize; /* xdrsize needed for this version */ /* Don't register with rpcbind */ @@ -430,7 +431,6 @@ struct svc_procedure { void (*pc_release)(struct svc_rqst *); unsigned int pc_argsize; /* argument struct size */ unsigned int pc_ressize; /* result struct size */ - unsigned int pc_count; /* call count */ unsigned int pc_cachetype; /* cache info (NFS) */ unsigned int pc_xdrressize; /* maximum size of XDR reply */ }; diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c index 8b6c35ae1d57..1e671333c3d5 100644 --- a/net/sunrpc/stats.c +++ b/net/sunrpc/stats.c @@ -77,9 +77,9 @@ static const struct file_operations rpc_proc_fops = { /* * Get RPC server stats */ -void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp) { +void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp) +{ const struct svc_program *prog = statp->program; - const struct svc_procedure *proc; const struct svc_version *vers; unsigned int i, j; @@ -98,11 +98,12 @@ void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp) { statp->rpcbadclnt); for (i = 0; i < prog->pg_nvers; i++) { - if (!(vers = prog->pg_vers[i]) || !(proc = vers->vs_proc)) + vers = prog->pg_vers[i]; + if (!vers) continue; seq_printf(seq, "proc%d %u", i, vers->vs_nproc); - for (j = 0; j < vers->vs_nproc; j++, proc++) - seq_printf(seq, " %u", proc->pc_count); + for (j = 0; j < vers->vs_nproc; j++) + seq_printf(seq, " %u", vers->vs_count[j]); seq_putc(seq, '\n'); } } diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index aa643a29fdc6..6452592194ac 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1261,7 +1261,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) svc_putnl(resv, RPC_SUCCESS); /* Bump per-procedure stats counter */ - procp->pc_count++; + versp->vs_count[proc]++; /* Initialize storage for argp and resp */ memset(rqstp->rq_argp, 0, procp->pc_argsize); -- cgit v1.2.3-59-g8ed1b From b9c744c19c441f306239ac3e60a2a95b40d698f8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 12 May 2017 16:11:49 +0200 Subject: sunrpc: mark all struct svc_procinfo instances as const struct svc_procinfo contains function pointers, and marking it as constant avoids it being able to be used as an attach vector for code injections. Signed-off-by: Christoph Hellwig --- fs/lockd/svc4proc.c | 2 +- fs/lockd/svcproc.c | 2 +- fs/nfs/callback_xdr.c | 2 +- fs/nfsd/nfs2acl.c | 2 +- fs/nfsd/nfs3acl.c | 2 +- fs/nfsd/nfs3proc.c | 2 +- fs/nfsd/nfs4proc.c | 2 +- fs/nfsd/nfsproc.c | 2 +- fs/nfsd/nfssvc.c | 4 ++-- include/linux/lockd/lockd.h | 4 ++-- include/linux/sunrpc/svc.h | 4 ++-- net/sunrpc/svc.c | 2 +- 12 files changed, 15 insertions(+), 15 deletions(-) diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index fed016155791..82925f17ec45 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -507,7 +507,7 @@ struct nlm_void { int dummy; }; #define No (1+1024/4) /* netobj */ #define St 1 /* status */ #define Rg 4 /* range (offset + length) */ -struct svc_procedure nlmsvc_procedures4[] = { +const struct svc_procedure nlmsvc_procedures4[] = { PROC(null, void, void, void, void, 1), PROC(test, testargs, testres, args, res, Ck+St+2+No+Rg), PROC(lock, lockargs, res, args, res, Ck+St), diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index 14648b051eba..07915162581d 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -551,7 +551,7 @@ struct nlm_void { int dummy; }; #define No (1+1024/4) /* Net Obj */ #define Rg 2 /* range - offset + size */ -struct svc_procedure nlmsvc_procedures[] = { +const struct svc_procedure nlmsvc_procedures[] = { PROC(null, void, void, void, void, 1), PROC(test, testargs, testres, args, res, Ck+St+2+No+Rg), PROC(lock, lockargs, res, args, res, Ck+St), diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index ecd46b8c0985..ae249f27297f 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -995,7 +995,7 @@ static struct callback_op callback_ops[] = { /* * Define NFS4 callback procedures */ -static struct svc_procedure nfs4_callback_procedures1[] = { +static const struct svc_procedure nfs4_callback_procedures1[] = { [CB_NULL] = { .pc_func = nfs4_callback_null, .pc_decode = nfs4_decode_void, diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 026edfe73fd5..c3f6b8a6b659 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -370,7 +370,7 @@ struct nfsd3_voidargs { int dummy; }; #define pAT (1+AT) /* post attributes - conditional */ #define ACL (1+NFS_ACL_MAX_ENTRIES*3) /* Access Control List */ -static struct svc_procedure nfsd_acl_procedures2[] = { +static const struct svc_procedure nfsd_acl_procedures2[] = { PROC(null, void, void, void, RC_NOCACHE, ST), PROC(getacl, getacl, getacl, getacl, RC_NOCACHE, ST+1+2*(1+ACL)), PROC(setacl, setacl, attrstat, attrstat, RC_NOCACHE, ST+AT), diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 73c0970ccefb..1a482ac9d4e9 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -257,7 +257,7 @@ struct nfsd3_voidargs { int dummy; }; #define pAT (1+AT) /* post attributes - conditional */ #define ACL (1+NFS_ACL_MAX_ENTRIES*3) /* Access Control List */ -static struct svc_procedure nfsd_acl_procedures3[] = { +static const struct svc_procedure nfsd_acl_procedures3[] = { PROC(null, void, void, void, RC_NOCACHE, ST), PROC(getacl, getacl, getacl, getacl, RC_NOCACHE, ST+1+2*(1+ACL)), PROC(setacl, setacl, setacl, fhandle, RC_NOCACHE, ST+pAT), diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index b5823802e278..96e0e6a2af51 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -674,7 +674,7 @@ struct nfsd3_voidargs { int dummy; }; #define pAT (1+AT) /* post attributes - conditional */ #define WC (7+pAT) /* WCC attributes */ -static struct svc_procedure nfsd_procedures3[22] = { +static const struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_NULL] = { .pc_func = nfsd3_proc_null, .pc_encode = nfs3svc_encode_voidres, diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 4de6a9950722..68aa175b1cb3 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -2532,7 +2532,7 @@ static const char *nfsd4_op_name(unsigned opnum) #define nfsd4_voidres nfsd4_voidargs struct nfsd4_voidargs { int dummy; }; -static struct svc_procedure nfsd_procedures4[2] = { +static const struct svc_procedure nfsd_procedures4[2] = { [NFSPROC4_NULL] = { .pc_func = nfsd4_proc_null, .pc_encode = nfs4svc_encode_voidres, diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 44b157553733..a68b686fda12 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -573,7 +573,7 @@ struct nfsd_void { int dummy; }; #define FH 8 /* filehandle */ #define AT 18 /* attributes */ -static struct svc_procedure nfsd_procedures2[18] = { +static const struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_NULL] = { .pc_func = nfsd_proc_null, .pc_decode = nfssvc_decode_void, diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 555233664124..379b310c445d 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -756,7 +756,7 @@ static __be32 map_new_errors(u32 vers, __be32 nfserr) * problem, we enforce these assumptions here: */ static bool nfs_request_too_big(struct svc_rqst *rqstp, - struct svc_procedure *proc) + const struct svc_procedure *proc) { /* * The ACL code has more careful bounds-checking and is not @@ -781,7 +781,7 @@ static bool nfs_request_too_big(struct svc_rqst *rqstp, int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) { - struct svc_procedure *proc; + const struct svc_procedure *proc; __be32 nfserr; __be32 *nfserrp; diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 41f7b6a04d69..3eca67728366 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -192,9 +192,9 @@ struct nlm_block { * Global variables */ extern const struct rpc_program nlm_program; -extern struct svc_procedure nlmsvc_procedures[]; +extern const struct svc_procedure nlmsvc_procedures[]; #ifdef CONFIG_LOCKD_V4 -extern struct svc_procedure nlmsvc_procedures4[]; +extern const struct svc_procedure nlmsvc_procedures4[]; #endif extern int nlmsvc_grace_period; extern unsigned long nlmsvc_timeout; diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index bcd114f038ef..992ea3419795 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -237,7 +237,7 @@ struct svc_rqst { struct svc_serv * rq_server; /* RPC service definition */ struct svc_pool * rq_pool; /* thread pool */ - struct svc_procedure * rq_procinfo; /* procedure info */ + const struct svc_procedure *rq_procinfo;/* procedure info */ struct auth_ops * rq_authop; /* authentication flavour */ struct svc_cred rq_cred; /* auth info */ void * rq_xprt_ctxt; /* transport specific context ptr */ @@ -397,7 +397,7 @@ struct svc_program { struct svc_version { u32 vs_vers; /* version number */ u32 vs_nproc; /* number of procedures */ - struct svc_procedure * vs_proc; /* per-procedure info */ + const struct svc_procedure *vs_proc; /* per-procedure info */ unsigned int *vs_count; /* call counts */ u32 vs_xdrsize; /* xdrsize needed for this version */ diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 6452592194ac..049963d676a7 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1152,7 +1152,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) { struct svc_program *progp; struct svc_version *versp = NULL; /* compiler food */ - struct svc_procedure *procp = NULL; + const struct svc_procedure *procp = NULL; struct svc_serv *serv = rqstp->rq_server; __be32 *statp; u32 prog, vers, proc; -- cgit v1.2.3-59-g8ed1b From aa8217d5dcb1db594d816794ef6ab434ebf3e127 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 12 May 2017 16:21:37 +0200 Subject: sunrpc: mark all struct svc_version instances as const Signed-off-by: Christoph Hellwig Acked-by: Trond Myklebust --- fs/lockd/svc.c | 38 +++++++++++++++++++------------------- fs/nfs/callback.c | 2 +- fs/nfs/callback_xdr.c | 4 ++-- fs/nfs/internal.h | 4 ++-- fs/nfs/nfs4_fs.h | 4 ++-- fs/nfsd/nfs2acl.c | 14 +++++++------- fs/nfsd/nfs3acl.c | 14 +++++++------- fs/nfsd/nfs3proc.c | 14 +++++++------- fs/nfsd/nfs4proc.c | 2 +- fs/nfsd/nfsd.h | 6 +++--- fs/nfsd/nfsproc.c | 14 +++++++------- fs/nfsd/nfssvc.c | 8 ++++---- include/linux/sunrpc/svc.h | 2 +- net/sunrpc/svc.c | 4 ++-- 14 files changed, 65 insertions(+), 65 deletions(-) diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index cc6abe6280bc..726b6cecf430 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -740,32 +740,32 @@ module_exit(exit_nlm); * Define NLM program and procedures */ static unsigned int nlmsvc_version1_count[17]; -static struct svc_version nlmsvc_version1 = { - .vs_vers = 1, - .vs_nproc = 17, - .vs_proc = nlmsvc_procedures, - .vs_count = nlmsvc_version1_count, - .vs_xdrsize = NLMSVC_XDRSIZE, +static const struct svc_version nlmsvc_version1 = { + .vs_vers = 1, + .vs_nproc = 17, + .vs_proc = nlmsvc_procedures, + .vs_count = nlmsvc_version1_count, + .vs_xdrsize = NLMSVC_XDRSIZE, }; static unsigned int nlmsvc_version3_count[24]; -static struct svc_version nlmsvc_version3 = { - .vs_vers = 3, - .vs_nproc = 24, - .vs_proc = nlmsvc_procedures, - .vs_count = nlmsvc_version3_count, - .vs_xdrsize = NLMSVC_XDRSIZE, +static const struct svc_version nlmsvc_version3 = { + .vs_vers = 3, + .vs_nproc = 24, + .vs_proc = nlmsvc_procedures, + .vs_count = nlmsvc_version3_count, + .vs_xdrsize = NLMSVC_XDRSIZE, }; #ifdef CONFIG_LOCKD_V4 static unsigned int nlmsvc_version4_count[24]; -static struct svc_version nlmsvc_version4 = { - .vs_vers = 4, - .vs_nproc = 24, - .vs_proc = nlmsvc_procedures4, - .vs_count = nlmsvc_version4_count, - .vs_xdrsize = NLMSVC_XDRSIZE, +static const struct svc_version nlmsvc_version4 = { + .vs_vers = 4, + .vs_nproc = 24, + .vs_proc = nlmsvc_procedures4, + .vs_count = nlmsvc_version4_count, + .vs_xdrsize = NLMSVC_XDRSIZE, }; #endif -static struct svc_version * nlmsvc_version[] = { +static const struct svc_version *nlmsvc_version[] = { [1] = &nlmsvc_version1, [3] = &nlmsvc_version3, #ifdef CONFIG_LOCKD_V4 diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 73a1f928226c..34323877ec13 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -439,7 +439,7 @@ static int nfs_callback_authenticate(struct svc_rqst *rqstp) /* * Define NFS4 callback program */ -static struct svc_version *nfs4_callback_version[] = { +static const struct svc_version *nfs4_callback_version[] = { [1] = &nfs4_callback_version1, [4] = &nfs4_callback_version4, }; diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index ae249f27297f..01a430e51daa 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -1012,7 +1012,7 @@ static const struct svc_procedure nfs4_callback_procedures1[] = { }; static unsigned int nfs4_callback_count1[ARRAY_SIZE(nfs4_callback_procedures1)]; -struct svc_version nfs4_callback_version1 = { +const struct svc_version nfs4_callback_version1 = { .vs_vers = 1, .vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1), .vs_proc = nfs4_callback_procedures1, @@ -1024,7 +1024,7 @@ struct svc_version nfs4_callback_version1 = { }; static unsigned int nfs4_callback_count4[ARRAY_SIZE(nfs4_callback_procedures1)]; -struct svc_version nfs4_callback_version4 = { +const struct svc_version nfs4_callback_version4 = { .vs_vers = 4, .vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1), .vs_proc = nfs4_callback_procedures1, diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index dc2a29a7d48b..1c0ce9c15e94 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -225,8 +225,8 @@ static inline void nfs_fs_proc_exit(void) #endif /* callback_xdr.c */ -extern struct svc_version nfs4_callback_version1; -extern struct svc_version nfs4_callback_version4; +extern const struct svc_version nfs4_callback_version1; +extern const struct svc_version nfs4_callback_version4; struct nfs_pageio_descriptor; /* pagelist.c */ diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 9b0cf3872722..40bd05f05e74 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -498,8 +498,8 @@ extern const struct rpc_procinfo nfs4_procedures[]; struct nfs4_mount_data; /* callback_xdr.c */ -extern struct svc_version nfs4_callback_version1; -extern struct svc_version nfs4_callback_version4; +extern const struct svc_version nfs4_callback_version1; +extern const struct svc_version nfs4_callback_version4; static inline void nfs4_stateid_copy(nfs4_stateid *dst, const nfs4_stateid *src) { diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index c3f6b8a6b659..6276ec8608b0 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -379,11 +379,11 @@ static const struct svc_procedure nfsd_acl_procedures2[] = { }; static unsigned int nfsd_acl_count2[ARRAY_SIZE(nfsd_acl_procedures2)]; -struct svc_version nfsd_acl_version2 = { - .vs_vers = 2, - .vs_nproc = 5, - .vs_proc = nfsd_acl_procedures2, - .vs_count = nfsd_acl_count2, - .vs_dispatch = nfsd_dispatch, - .vs_xdrsize = NFS3_SVC_XDRSIZE, +const struct svc_version nfsd_acl_version2 = { + .vs_vers = 2, + .vs_nproc = 5, + .vs_proc = nfsd_acl_procedures2, + .vs_count = nfsd_acl_count2, + .vs_dispatch = nfsd_dispatch, + .vs_xdrsize = NFS3_SVC_XDRSIZE, }; diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 1a482ac9d4e9..01976529f042 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -264,12 +264,12 @@ static const struct svc_procedure nfsd_acl_procedures3[] = { }; static unsigned int nfsd_acl_count3[ARRAY_SIZE(nfsd_acl_procedures3)]; -struct svc_version nfsd_acl_version3 = { - .vs_vers = 3, - .vs_nproc = 3, - .vs_proc = nfsd_acl_procedures3, - .vs_count = nfsd_acl_count3, - .vs_dispatch = nfsd_dispatch, - .vs_xdrsize = NFS3_SVC_XDRSIZE, +const struct svc_version nfsd_acl_version3 = { + .vs_vers = 3, + .vs_nproc = 3, + .vs_proc = nfsd_acl_procedures3, + .vs_count = nfsd_acl_count3, + .vs_dispatch = nfsd_dispatch, + .vs_xdrsize = NFS3_SVC_XDRSIZE, }; diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 96e0e6a2af51..2cb56a0d6625 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -891,11 +891,11 @@ static const struct svc_procedure nfsd_procedures3[22] = { }; static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures3)]; -struct svc_version nfsd_version3 = { - .vs_vers = 3, - .vs_nproc = 22, - .vs_proc = nfsd_procedures3, - .vs_count = nfsd_count3, - .vs_dispatch = nfsd_dispatch, - .vs_xdrsize = NFS3_SVC_XDRSIZE, +const struct svc_version nfsd_version3 = { + .vs_vers = 3, + .vs_nproc = 22, + .vs_proc = nfsd_procedures3, + .vs_dispatch = nfsd_dispatch, + .vs_count = nfsd_count3, + .vs_xdrsize = NFS3_SVC_XDRSIZE, }; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 68aa175b1cb3..3cbd065c639f 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -2554,7 +2554,7 @@ static const struct svc_procedure nfsd_procedures4[2] = { }; static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures4)]; -struct svc_version nfsd_version4 = { +const struct svc_version nfsd_version4 = { .vs_vers = 4, .vs_nproc = 2, .vs_proc = nfsd_procedures4, diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index d96606801d47..b9c538ab7a59 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -60,7 +60,7 @@ struct readdir_cd { extern struct svc_program nfsd_program; -extern struct svc_version nfsd_version2, nfsd_version3, +extern const struct svc_version nfsd_version2, nfsd_version3, nfsd_version4; extern struct mutex nfsd_mutex; extern spinlock_t nfsd_drc_lock; @@ -86,12 +86,12 @@ void nfsd_destroy(struct net *net); #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) #ifdef CONFIG_NFSD_V2_ACL -extern struct svc_version nfsd_acl_version2; +extern const struct svc_version nfsd_acl_version2; #else #define nfsd_acl_version2 NULL #endif #ifdef CONFIG_NFSD_V3_ACL -extern struct svc_version nfsd_acl_version3; +extern const struct svc_version nfsd_acl_version3; #else #define nfsd_acl_version3 NULL #endif diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index a68b686fda12..5076ae2b8258 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -744,13 +744,13 @@ static const struct svc_procedure nfsd_procedures2[18] = { static unsigned int nfsd_count2[ARRAY_SIZE(nfsd_procedures2)]; -struct svc_version nfsd_version2 = { - .vs_vers = 2, - .vs_nproc = 18, - .vs_proc = nfsd_procedures2, - .vs_count = nfsd_count2, - .vs_dispatch = nfsd_dispatch, - .vs_xdrsize = NFS2_SVC_XDRSIZE, +const struct svc_version nfsd_version2 = { + .vs_vers = 2, + .vs_nproc = 18, + .vs_proc = nfsd_procedures2, + .vs_count = nfsd_count2, + .vs_dispatch = nfsd_dispatch, + .vs_xdrsize = NFS2_SVC_XDRSIZE, }; /* diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 379b310c445d..063ae7de2c12 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -68,14 +68,14 @@ unsigned long nfsd_drc_mem_used; #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) static struct svc_stat nfsd_acl_svcstats; -static struct svc_version * nfsd_acl_version[] = { +static const struct svc_version *nfsd_acl_version[] = { [2] = &nfsd_acl_version2, [3] = &nfsd_acl_version3, }; #define NFSD_ACL_MINVERS 2 #define NFSD_ACL_NRVERS ARRAY_SIZE(nfsd_acl_version) -static struct svc_version *nfsd_acl_versions[NFSD_ACL_NRVERS]; +static const struct svc_version *nfsd_acl_versions[NFSD_ACL_NRVERS]; static struct svc_program nfsd_acl_program = { .pg_prog = NFS_ACL_PROGRAM, @@ -92,7 +92,7 @@ static struct svc_stat nfsd_acl_svcstats = { }; #endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */ -static struct svc_version * nfsd_version[] = { +static const struct svc_version *nfsd_version[] = { [2] = &nfsd_version2, #if defined(CONFIG_NFSD_V3) [3] = &nfsd_version3, @@ -104,7 +104,7 @@ static struct svc_version * nfsd_version[] = { #define NFSD_MINVERS 2 #define NFSD_NRVERS ARRAY_SIZE(nfsd_version) -static struct svc_version *nfsd_versions[NFSD_NRVERS]; +static const struct svc_version *nfsd_versions[NFSD_NRVERS]; struct svc_program nfsd_program = { #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 992ea3419795..eec04982a7ea 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -384,7 +384,7 @@ struct svc_program { unsigned int pg_lovers; /* lowest version */ unsigned int pg_hivers; /* highest version */ unsigned int pg_nvers; /* number of versions */ - struct svc_version ** pg_vers; /* version array */ + const struct svc_version **pg_vers; /* version array */ char * pg_name; /* service name */ char * pg_class; /* class name: services sharing authentication */ struct svc_stat * pg_stats; /* rpc statistics */ diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 049963d676a7..45b4f2d2e3bd 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1008,7 +1008,7 @@ int svc_register(const struct svc_serv *serv, struct net *net, const unsigned short port) { struct svc_program *progp; - struct svc_version *vers; + const struct svc_version *vers; unsigned int i; int error = 0; @@ -1151,7 +1151,7 @@ static int svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) { struct svc_program *progp; - struct svc_version *versp = NULL; /* compiler food */ + const struct svc_version *versp = NULL; /* compiler food */ const struct svc_procedure *procp = NULL; struct svc_serv *serv = rqstp->rq_server; __be32 *statp; -- cgit v1.2.3-59-g8ed1b From 800222f80fedca63baf05d28028a0d18e9b8d7a5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2017 23:46:47 +0200 Subject: nfsd4: const-ify nfsd4_ops nfsd4_ops contains function pointers, and marking it as constant avoids it being able to be used as an attach vector for code injections. Signed-off-by: Christoph Hellwig --- fs/nfsd/nfs4proc.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 3cbd065c639f..d27e75ad25e3 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1584,7 +1584,7 @@ struct nfsd4_operation { union nfsd4_op_u *); }; -static struct nfsd4_operation nfsd4_ops[]; +static const struct nfsd4_operation nfsd4_ops[]; static const char *nfsd4_op_name(unsigned opnum); @@ -1621,7 +1621,7 @@ static __be32 nfs41_check_op_ordering(struct nfsd4_compoundargs *args) return nfs_ok; } -static inline struct nfsd4_operation *OPDESC(struct nfsd4_op *op) +static inline const struct nfsd4_operation *OPDESC(struct nfsd4_op *op) { return &nfsd4_ops[op->opnum]; } @@ -1639,10 +1639,9 @@ static bool need_wrongsec_check(struct svc_rqst *rqstp) struct nfsd4_compoundargs *argp = rqstp->rq_argp; struct nfsd4_op *this = &argp->ops[resp->opcnt - 1]; struct nfsd4_op *next = &argp->ops[resp->opcnt]; - struct nfsd4_operation *thisd; - struct nfsd4_operation *nextd; + const struct nfsd4_operation *thisd = OPDESC(this); + const struct nfsd4_operation *nextd; - thisd = OPDESC(this); /* * Most ops check wronsec on our own; only the putfh-like ops * have special rules. @@ -1695,7 +1694,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) struct nfsd4_compoundargs *args = rqstp->rq_argp; struct nfsd4_compoundres *resp = rqstp->rq_resp; struct nfsd4_op *op; - struct nfsd4_operation *opdesc; + const struct nfsd4_operation *opdesc; struct nfsd4_compound_state *cstate = &resp->cstate; struct svc_fh *current_fh = &cstate->current_fh; struct svc_fh *save_fh = &cstate->save_fh; @@ -2108,7 +2107,7 @@ static inline u32 nfsd4_seek_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) return (op_encode_hdr_size + 3) * sizeof(__be32); } -static struct nfsd4_operation nfsd4_ops[] = { +static const struct nfsd4_operation nfsd4_ops[] = { [OP_ACCESS] = { .op_func = nfsd4_access, .op_name = "OP_ACCESS", -- cgit v1.2.3-59-g8ed1b From 18fe6a23e3114a6737471570753b708ff293b9de Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 16 Jun 2017 12:06:59 -0400 Subject: NFS: Set FATTR4_WORD0_TYPE for . and .. entries The current code worked okay for getdents(), but getdents64() expects the d_type field to get filled out properly in the stat structure. Setting this field fixes xfstests generic/401. Signed-off-by: Anna Schumaker --- fs/nfs/nfs4proc.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index c08c46a3b8cd..735b3068a2d1 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -275,6 +275,7 @@ const u32 nfs4_fs_locations_bitmap[3] = { static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dentry, struct nfs4_readdir_arg *readdir) { + unsigned int attrs = FATTR4_WORD0_FILEID | FATTR4_WORD0_TYPE; __be32 *start, *p; if (cookie > 2) { @@ -305,8 +306,9 @@ static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dent memcpy(p, ".\0\0\0", 4); /* entry */ p++; *p++ = xdr_one; /* bitmap length */ - *p++ = htonl(FATTR4_WORD0_FILEID); /* bitmap */ - *p++ = htonl(8); /* attribute buffer length */ + *p++ = htonl(attrs); /* bitmap */ + *p++ = htonl(12); /* attribute buffer length */ + *p++ = htonl(NF4DIR); p = xdr_encode_hyper(p, NFS_FILEID(d_inode(dentry))); } @@ -317,8 +319,9 @@ static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dent memcpy(p, "..\0\0", 4); /* entry */ p++; *p++ = xdr_one; /* bitmap length */ - *p++ = htonl(FATTR4_WORD0_FILEID); /* bitmap */ - *p++ = htonl(8); /* attribute buffer length */ + *p++ = htonl(attrs); /* bitmap */ + *p++ = htonl(12); /* attribute buffer length */ + *p++ = htonl(NF4DIR); p = xdr_encode_hyper(p, NFS_FILEID(d_inode(dentry->d_parent))); readdir->pgbase = (char *)p - (char *)start; -- cgit v1.2.3-59-g8ed1b From a7a3b1e971cd806b81ecea3a234d8dae9de0add0 Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Tue, 20 Jun 2017 08:33:44 -0400 Subject: NFS: convert flags to bool NFS uses some int, and unsigned int :1, and bool as flags in structs and args. Assert the preference for uniformly replacing these with the bool type. Signed-off-by: Benjamin Coddington Signed-off-by: Anna Schumaker --- fs/nfs/dir.c | 16 ++++++++-------- fs/nfs/internal.h | 6 +++--- fs/nfs/nfs2xdr.c | 2 +- fs/nfs/nfs3proc.c | 2 +- fs/nfs/nfs3xdr.c | 2 +- fs/nfs/nfs4proc.c | 42 +++++++++++++++++++++--------------------- fs/nfs/nfs4xdr.c | 2 +- fs/nfs/proc.c | 2 +- include/linux/nfs_xdr.h | 10 +++++----- 9 files changed, 42 insertions(+), 42 deletions(-) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 32ccd7754f8a..9688e9bb13dc 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -151,7 +151,7 @@ struct nfs_cache_array { struct nfs_cache_array_entry array[0]; }; -typedef int (*decode_dirent_t)(struct xdr_stream *, struct nfs_entry *, int); +typedef int (*decode_dirent_t)(struct xdr_stream *, struct nfs_entry *, bool); typedef struct { struct file *file; struct page *page; @@ -165,8 +165,8 @@ typedef struct { unsigned long timestamp; unsigned long gencount; unsigned int cache_entry_index; - unsigned int plus:1; - unsigned int eof:1; + bool plus; + bool eof; } nfs_readdir_descriptor_t; /* @@ -355,7 +355,7 @@ int nfs_readdir_xdr_filler(struct page **pages, nfs_readdir_descriptor_t *desc, if (error == -ENOTSUPP && desc->plus) { NFS_SERVER(inode)->caps &= ~NFS_CAP_READDIRPLUS; clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags); - desc->plus = 0; + desc->plus = false; goto again; } goto error; @@ -557,7 +557,7 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en count++; - if (desc->plus != 0) + if (desc->plus) nfs_prime_dcache(file_dentry(desc->file), entry); status = nfs_readdir_add_to_array(entry, page); @@ -860,7 +860,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) desc->ctx = ctx; desc->dir_cookie = &dir_ctx->dir_cookie; desc->decode = NFS_PROTO(inode)->decode_dirent; - desc->plus = nfs_use_readdirplus(inode, ctx) ? 1 : 0; + desc->plus = nfs_use_readdirplus(inode, ctx); if (ctx->pos == 0 || nfs_attribute_cache_expired(inode)) res = nfs_revalidate_mapping(inode, file->f_mapping); @@ -885,8 +885,8 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags); nfs_zap_caches(inode); desc->page_index = 0; - desc->plus = 0; - desc->eof = 0; + desc->plus = false; + desc->eof = false; continue; } if (res < 0) diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 1c0ce9c15e94..c5054edb0157 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -272,17 +272,17 @@ static inline bool nfs_match_open_context(const struct nfs_open_context *ctx1, /* nfs2xdr.c */ extern const struct rpc_procinfo nfs_procedures[]; extern int nfs2_decode_dirent(struct xdr_stream *, - struct nfs_entry *, int); + struct nfs_entry *, bool); /* nfs3xdr.c */ extern const struct rpc_procinfo nfs3_procedures[]; extern int nfs3_decode_dirent(struct xdr_stream *, - struct nfs_entry *, int); + struct nfs_entry *, bool); /* nfs4xdr.c */ #if IS_ENABLED(CONFIG_NFS_V4) extern int nfs4_decode_dirent(struct xdr_stream *, - struct nfs_entry *, int); + struct nfs_entry *, bool); #endif #ifdef CONFIG_NFS_V4_1 extern const u32 nfs41_maxread_overhead; diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index c8a7e98c1371..fe68dabfbde6 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -939,7 +939,7 @@ static int nfs2_xdr_dec_writeres(struct rpc_rqst *req, struct xdr_stream *xdr, * }; */ int nfs2_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, - int plus) + bool plus) { __be32 *p; int error; diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 0c07b567118d..df4a7d3ab915 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -621,7 +621,7 @@ out: */ static int nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, - u64 cookie, struct page **pages, unsigned int count, int plus) + u64 cookie, struct page **pages, unsigned int count, bool plus) { struct inode *dir = d_inode(dentry); __be32 *verf = NFS_I(dir)->cookieverf; diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 670eddb3ae36..e82c9e553224 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -1991,7 +1991,7 @@ out_status: * }; */ int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, - int plus) + bool plus) { struct nfs_entry old = *entry; __be32 *p; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 735b3068a2d1..e678fa8f6979 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1037,11 +1037,11 @@ struct nfs4_opendata { struct nfs4_state *state; struct iattr attrs; unsigned long timestamp; - unsigned int rpc_done : 1; - unsigned int file_created : 1; - unsigned int is_recover : 1; + bool rpc_done; + bool file_created; + bool is_recover; + bool cancelled; int rpc_status; - int cancelled; }; static bool nfs4_clear_cap_atomic_open_v1(struct nfs_server *server, @@ -1965,7 +1965,7 @@ static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata) nfs4_stateid_copy(&data->o_res.stateid, &data->c_res.stateid); nfs_confirm_seqid(&data->owner->so_seqid, 0); renew_lease(data->o_res.server, data->timestamp); - data->rpc_done = 1; + data->rpc_done = true; } } @@ -1975,7 +1975,7 @@ static void nfs4_open_confirm_release(void *calldata) struct nfs4_state *state = NULL; /* If this request hasn't been cancelled, do nothing */ - if (data->cancelled == 0) + if (!data->cancelled) goto out_free; /* In case of error, no cleanup! */ if (!data->rpc_done) @@ -2018,7 +2018,7 @@ static int _nfs4_proc_open_confirm(struct nfs4_opendata *data) nfs4_init_sequence(&data->c_arg.seq_args, &data->c_res.seq_res, 1); kref_get(&data->kref); - data->rpc_done = 0; + data->rpc_done = false; data->rpc_status = 0; data->timestamp = jiffies; if (data->is_recover) @@ -2028,7 +2028,7 @@ static int _nfs4_proc_open_confirm(struct nfs4_opendata *data) return PTR_ERR(task); status = rpc_wait_for_completion_task(task); if (status != 0) { - data->cancelled = 1; + data->cancelled = true; smp_wmb(); } else status = data->rpc_status; @@ -2127,7 +2127,7 @@ static void nfs4_open_done(struct rpc_task *task, void *calldata) if (!(data->o_res.rflags & NFS4_OPEN_RESULT_CONFIRM)) nfs_confirm_seqid(&data->owner->so_seqid, 0); } - data->rpc_done = 1; + data->rpc_done = true; } static void nfs4_open_release(void *calldata) @@ -2136,7 +2136,7 @@ static void nfs4_open_release(void *calldata) struct nfs4_state *state = NULL; /* If this request hasn't been cancelled, do nothing */ - if (data->cancelled == 0) + if (!data->cancelled) goto out_free; /* In case of error, no cleanup! */ if (data->rpc_status != 0 || !data->rpc_done) @@ -2182,20 +2182,20 @@ static int nfs4_run_open_task(struct nfs4_opendata *data, int isrecover) nfs4_init_sequence(&o_arg->seq_args, &o_res->seq_res, 1); kref_get(&data->kref); - data->rpc_done = 0; + data->rpc_done = false; data->rpc_status = 0; - data->cancelled = 0; - data->is_recover = 0; + data->cancelled = false; + data->is_recover = false; if (isrecover) { nfs4_set_sequence_privileged(&o_arg->seq_args); - data->is_recover = 1; + data->is_recover = true; } task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); status = rpc_wait_for_completion_task(task); if (status != 0) { - data->cancelled = 1; + data->cancelled = true; smp_wmb(); } else status = data->rpc_status; @@ -2290,9 +2290,9 @@ static int _nfs4_proc_open(struct nfs4_opendata *data) if (o_arg->open_flags & O_CREAT) { if (o_arg->open_flags & O_EXCL) - data->file_created = 1; + data->file_created = true; else if (o_res->cinfo.before != o_res->cinfo.after) - data->file_created = 1; + data->file_created = true; if (data->file_created || dir->i_version != o_res->cinfo.after) update_changeattr(dir, &o_res->cinfo, o_res->f_attr->time_start); @@ -4275,7 +4275,7 @@ static int nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry, } static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, - u64 cookie, struct page **pages, unsigned int count, int plus) + u64 cookie, struct page **pages, unsigned int count, bool plus) { struct inode *dir = d_inode(dentry); struct nfs4_readdir_arg args = { @@ -4313,7 +4313,7 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, } static int nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, - u64 cookie, struct page **pages, unsigned int count, int plus) + u64 cookie, struct page **pages, unsigned int count, bool plus) { struct nfs4_exception exception = { }; int err; @@ -6137,7 +6137,7 @@ static void nfs4_lock_release(void *calldata) dprintk("%s: begin!\n", __func__); nfs_free_seqid(data->arg.open_seqid); - if (data->cancelled != 0) { + if (data->cancelled) { struct rpc_task *task; task = nfs4_do_unlck(&data->fl, data->ctx, data->lsp, data->arg.lock_seqid); @@ -6220,7 +6220,7 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f nfs4_handle_setlk_error(data->server, data->lsp, data->arg.new_lock_owner, ret); } else - data->cancelled = 1; + data->cancelled = true; rpc_put_task(task); dprintk("%s: done, ret = %d!\n", __func__, ret); trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret); diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 0f1f290c97cd..495d493d3a35 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -7447,7 +7447,7 @@ out: * on a directory already in our cache. */ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, - int plus) + bool plus) { unsigned int savep; uint32_t bitmap[3] = {0}; diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index 9872cf676a50..7962e49097c3 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -485,7 +485,7 @@ nfs_proc_rmdir(struct inode *dir, const struct qstr *name) */ static int nfs_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, - u64 cookie, struct page **pages, unsigned int count, int plus) + u64 cookie, struct page **pages, unsigned int count, bool plus) { struct inode *dir = d_inode(dentry); struct nfs_readdirargs arg = { diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index b28c83475ee8..9b42bffbe07b 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -878,7 +878,7 @@ struct nfs3_readdirargs { struct nfs_fh * fh; __u64 cookie; __be32 verf[2]; - int plus; + bool plus; unsigned int count; struct page ** pages; }; @@ -909,7 +909,7 @@ struct nfs3_linkres { struct nfs3_readdirres { struct nfs_fattr * dir_attr; __be32 * verf; - int plus; + bool plus; }; struct nfs3_getaclres { @@ -1053,7 +1053,7 @@ struct nfs4_readdir_arg { struct page ** pages; /* zero-copy data */ unsigned int pgbase; /* zero-copy data */ const u32 * bitmask; - int plus; + bool plus; }; struct nfs4_readdir_res { @@ -1585,7 +1585,7 @@ struct nfs_rpc_ops { int (*mkdir) (struct inode *, struct dentry *, struct iattr *); int (*rmdir) (struct inode *, const struct qstr *); int (*readdir) (struct dentry *, struct rpc_cred *, - u64, struct page **, unsigned int, int); + u64, struct page **, unsigned int, bool); int (*mknod) (struct inode *, struct dentry *, struct iattr *, dev_t); int (*statfs) (struct nfs_server *, struct nfs_fh *, @@ -1595,7 +1595,7 @@ struct nfs_rpc_ops { int (*pathconf) (struct nfs_server *, struct nfs_fh *, struct nfs_pathconf *); int (*set_capabilities)(struct nfs_server *, struct nfs_fh *); - int (*decode_dirent)(struct xdr_stream *, struct nfs_entry *, int); + int (*decode_dirent)(struct xdr_stream *, struct nfs_entry *, bool); int (*pgio_rpc_prepare)(struct rpc_task *, struct nfs_pgio_header *); void (*read_setup)(struct nfs_pgio_header *, struct rpc_message *); -- cgit v1.2.3-59-g8ed1b From 818a8dbe83fddff534b814a7d4e0c75b511dff2e Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Fri, 16 Jun 2017 11:13:00 -0400 Subject: NFS: nfs_rename() - revalidate directories on -ERESTARTSYS An interrupted rename will leave the old dentry behind if the rename succeeds. Fix this by forcing a lookup the next time through ->d_revalidate. A previous attempt at solving this problem took the approach to complete the work of the rename asynchronously, however that approach was wrong since it would allow the d_move() to occur after the directory's i_mutex had been dropped by the original process. Signed-off-by: Benjamin Coddington Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- fs/nfs/dir.c | 6 +++++- fs/nfs/unlink.c | 13 +++++++++++++ include/linux/nfs_xdr.h | 1 + 3 files changed, 19 insertions(+), 1 deletion(-) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 9688e9bb13dc..ab69ebb48350 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2056,7 +2056,11 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, } error = rpc_wait_for_completion_task(task); - if (error == 0) + if (error != 0) { + ((struct nfs_renamedata *)task->tk_calldata)->cancelled = 1; + /* Paired with the atomic_dec_and_test() barrier in rpc_do_put_task() */ + smp_wmb(); + } else error = task->tk_status; rpc_put_task(task); out: diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index 191aa577dd1f..e3949d93085c 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -288,6 +288,19 @@ static void nfs_async_rename_release(void *calldata) if (d_really_is_positive(data->old_dentry)) nfs_mark_for_revalidate(d_inode(data->old_dentry)); + /* The result of the rename is unknown. Play it safe by + * forcing a new lookup */ + if (data->cancelled) { + spin_lock(&data->old_dir->i_lock); + nfs_force_lookup_revalidate(data->old_dir); + spin_unlock(&data->old_dir->i_lock); + if (data->new_dir != data->old_dir) { + spin_lock(&data->new_dir->i_lock); + nfs_force_lookup_revalidate(data->new_dir); + spin_unlock(&data->new_dir->i_lock); + } + } + dput(data->old_dentry); dput(data->new_dentry); iput(data->old_dir); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 9b42bffbe07b..9463eeff9e3c 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1533,6 +1533,7 @@ struct nfs_renamedata { struct nfs_fattr new_fattr; void (*complete)(struct rpc_task *, struct nfs_renamedata *); long timeout; + bool cancelled; }; struct nfs_access_entry; -- cgit v1.2.3-59-g8ed1b From 92ea011f7cbade821ebd56a1f70d20331c0320c8 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 20 Jun 2017 19:35:39 -0400 Subject: SUNRPC: Make slot allocation more reliable In xprt_alloc_slot(), the spin lock is only needed to provide atomicity between the atomic_add_unless() failure and the call to xprt_add_backlog(). We do not actually need to hold it across the memory allocation itself. By dropping the lock, we can use a more resilient GFP_NOFS allocation, just as we now do in the rest of the RPC client code. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- net/sunrpc/xprt.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 3e63c5e97ebe..4654a9934269 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1047,13 +1047,15 @@ out: return ret; } -static struct rpc_rqst *xprt_dynamic_alloc_slot(struct rpc_xprt *xprt, gfp_t gfp_flags) +static struct rpc_rqst *xprt_dynamic_alloc_slot(struct rpc_xprt *xprt) { struct rpc_rqst *req = ERR_PTR(-EAGAIN); if (!atomic_add_unless(&xprt->num_reqs, 1, xprt->max_reqs)) goto out; - req = kzalloc(sizeof(struct rpc_rqst), gfp_flags); + spin_unlock(&xprt->reserve_lock); + req = kzalloc(sizeof(struct rpc_rqst), GFP_NOFS); + spin_lock(&xprt->reserve_lock); if (req != NULL) goto out; atomic_dec(&xprt->num_reqs); @@ -1081,7 +1083,7 @@ void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task) list_del(&req->rq_list); goto out_init_req; } - req = xprt_dynamic_alloc_slot(xprt, GFP_NOWAIT|__GFP_NOWARN); + req = xprt_dynamic_alloc_slot(xprt); if (!IS_ERR(req)) goto out_init_req; switch (PTR_ERR(req)) { -- cgit v1.2.3-59-g8ed1b From b5973a8c1ccf375c9ab9e2428e1185e3f799af06 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 20 Jun 2017 19:35:36 -0400 Subject: NFS: Remove unused fields in the page I/O structures Remove the 'layout_private' fields that were only used by the pNFS OSD layout driver. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/pagelist.c | 2 -- include/linux/nfs_page.h | 1 - include/linux/nfs_xdr.h | 1 - 3 files changed, 4 deletions(-) diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index ad92b401326c..de107d866297 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -51,7 +51,6 @@ void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, hdr->io_start = req_offset(hdr->req); hdr->good_bytes = mirror->pg_count; hdr->dreq = desc->pg_dreq; - hdr->layout_private = desc->pg_layout_private; hdr->release = release; hdr->completion_ops = desc->pg_completion_ops; if (hdr->completion_ops->init_hdr) @@ -711,7 +710,6 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, desc->pg_error = 0; desc->pg_lseg = NULL; desc->pg_dreq = NULL; - desc->pg_layout_private = NULL; desc->pg_bsize = bsize; desc->pg_mirror_count = 1; diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 247cc3d3498f..6138cf91346b 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -94,7 +94,6 @@ struct nfs_pageio_descriptor { const struct nfs_pgio_completion_ops *pg_completion_ops; struct pnfs_layout_segment *pg_lseg; struct nfs_direct_req *pg_dreq; - void *pg_layout_private; unsigned int pg_bsize; /* default bsize for mirrors */ u32 pg_mirror_count; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 9463eeff9e3c..7f1e04941763 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1436,7 +1436,6 @@ struct nfs_pgio_header { const struct nfs_pgio_completion_ops *completion_ops; const struct nfs_rw_ops *rw_ops; struct nfs_direct_req *dreq; - void *layout_private; spinlock_t lock; /* fields protected by lock */ int pnfs_error; -- cgit v1.2.3-59-g8ed1b From 919e3bd9a87593520a2c5dfda27bd3e6599852ed Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 20 Jun 2017 19:35:37 -0400 Subject: NFS: Ensure we commit after writeback is complete If the page cache is being flushed, then we want to ensure that we do start a commit once the pages are done being flushed. If we just wait until all I/O is done to that file, we can end up livelocking until the balance_dirty_pages() mechanism puts its foot down and forces I/O to stop. So instead we do more or less the same thing that O_DIRECT does, and set up a counter to tell us when the flush is done, Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/pagelist.c | 3 +++ fs/nfs/write.c | 57 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/nfs_page.h | 1 + include/linux/nfs_xdr.h | 2 ++ 4 files changed, 63 insertions(+) diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index de107d866297..83d2918f1b13 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -50,6 +50,7 @@ void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, hdr->cred = hdr->req->wb_context->cred; hdr->io_start = req_offset(hdr->req); hdr->good_bytes = mirror->pg_count; + hdr->io_completion = desc->pg_io_completion; hdr->dreq = desc->pg_dreq; hdr->release = release; hdr->completion_ops = desc->pg_completion_ops; @@ -709,6 +710,7 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, desc->pg_ioflags = io_flags; desc->pg_error = 0; desc->pg_lseg = NULL; + desc->pg_io_completion = NULL; desc->pg_dreq = NULL; desc->pg_bsize = bsize; @@ -1231,6 +1233,7 @@ int nfs_pageio_resend(struct nfs_pageio_descriptor *desc, { LIST_HEAD(failed); + desc->pg_io_completion = hdr->io_completion; desc->pg_dreq = hdr->dreq; while (!list_empty(&hdr->pages)) { struct nfs_page *req = nfs_list_entry(hdr->pages.next); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index db7ba542559e..051197cb9195 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -40,6 +40,12 @@ #define MIN_POOL_WRITE (32) #define MIN_POOL_COMMIT (4) +struct nfs_io_completion { + void (*complete)(void *data); + void *data; + struct kref refcount; +}; + /* * Local function declarations */ @@ -108,6 +114,39 @@ static void nfs_writehdr_free(struct nfs_pgio_header *hdr) mempool_free(hdr, nfs_wdata_mempool); } +static struct nfs_io_completion *nfs_io_completion_alloc(gfp_t gfp_flags) +{ + return kmalloc(sizeof(struct nfs_io_completion), gfp_flags); +} + +static void nfs_io_completion_init(struct nfs_io_completion *ioc, + void (*complete)(void *), void *data) +{ + ioc->complete = complete; + ioc->data = data; + kref_init(&ioc->refcount); +} + +static void nfs_io_completion_release(struct kref *kref) +{ + struct nfs_io_completion *ioc = container_of(kref, + struct nfs_io_completion, refcount); + ioc->complete(ioc->data); + kfree(ioc); +} + +static void nfs_io_completion_get(struct nfs_io_completion *ioc) +{ + if (ioc != NULL) + kref_get(&ioc->refcount); +} + +static void nfs_io_completion_put(struct nfs_io_completion *ioc) +{ + if (ioc != NULL) + kref_put(&ioc->refcount, nfs_io_completion_release); +} + static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error) { ctx->error = error; @@ -681,18 +720,29 @@ static int nfs_writepages_callback(struct page *page, struct writeback_control * return ret; } +static void nfs_io_completion_commit(void *inode) +{ + nfs_commit_inode(inode, 0); +} + int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct inode *inode = mapping->host; struct nfs_pageio_descriptor pgio; + struct nfs_io_completion *ioc = nfs_io_completion_alloc(GFP_NOFS); int err; nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES); + if (ioc) + nfs_io_completion_init(ioc, nfs_io_completion_commit, inode); + nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), false, &nfs_async_write_completion_ops); + pgio.pg_io_completion = ioc; err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio); nfs_pageio_complete(&pgio); + nfs_io_completion_put(ioc); if (err < 0) goto out_err; @@ -940,6 +990,11 @@ int nfs_write_need_commit(struct nfs_pgio_header *hdr) return hdr->verf.committed != NFS_FILE_SYNC; } +static void nfs_async_write_init(struct nfs_pgio_header *hdr) +{ + nfs_io_completion_get(hdr->io_completion); +} + static void nfs_write_completion(struct nfs_pgio_header *hdr) { struct nfs_commit_info cinfo; @@ -973,6 +1028,7 @@ next: nfs_release_request(req); } out: + nfs_io_completion_put(hdr->io_completion); hdr->release(hdr); } @@ -1378,6 +1434,7 @@ static void nfs_async_write_reschedule_io(struct nfs_pgio_header *hdr) } static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops = { + .init_hdr = nfs_async_write_init, .error_cleanup = nfs_async_write_error, .completion = nfs_write_completion, .reschedule_io = nfs_async_write_reschedule_io, diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 6138cf91346b..abbee2d15dce 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -93,6 +93,7 @@ struct nfs_pageio_descriptor { const struct rpc_call_ops *pg_rpc_callops; const struct nfs_pgio_completion_ops *pg_completion_ops; struct pnfs_layout_segment *pg_lseg; + struct nfs_io_completion *pg_io_completion; struct nfs_direct_req *pg_dreq; unsigned int pg_bsize; /* default bsize for mirrors */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 7f1e04941763..89093341f076 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1422,6 +1422,7 @@ enum { NFS_IOHDR_STAT, }; +struct nfs_io_completion; struct nfs_pgio_header { struct inode *inode; struct rpc_cred *cred; @@ -1435,6 +1436,7 @@ struct nfs_pgio_header { void (*release) (struct nfs_pgio_header *hdr); const struct nfs_pgio_completion_ops *completion_ops; const struct nfs_rw_ops *rw_ops; + struct nfs_io_completion *io_completion; struct nfs_direct_req *dreq; spinlock_t lock; /* fields protected by lock */ -- cgit v1.2.3-59-g8ed1b From 1a4edf0f46b0cb87dd5020481d355cd5cc456c47 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 20 Jun 2017 19:35:38 -0400 Subject: NFS: Fix commit policy for non-blocking calls to nfs_write_inode() Now that the writes will schedule a commit on their own, we don't need nfs_write_inode() to schedule one if there are outstanding writes, and we're being called in non-blocking mode. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/write.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 051197cb9195..b1af5dee5e0a 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1941,7 +1941,7 @@ int nfs_write_inode(struct inode *inode, struct writeback_control *wbc) /* Don't commit yet if this is a non-blocking flush and there * are a lot of outstanding writes for this mapping. */ - if (nfsi->commit_info.ncommit <= (nfsi->nrequests >> 1)) + if (mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK)) goto out_mark_dirty; /* don't wait for the COMMIT response */ -- cgit v1.2.3-59-g8ed1b From 2eb3aea7d9c43325a12df312adfc7fb25bbd636b Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Fri, 9 Jun 2017 11:03:23 -0400 Subject: NFS: Fix initialization of nfs_page_array->npages Commit 8ef9b0b9e1c0 open-coded nfs_pgarray_set(), and left out the initialization of the nfs_page_array's npages. This mistake didn't show up until testing with block layouts, and there shows that all pNFS reads return -EIO. Fixes: 8ef9b0b9e1c0 ("NFS: move nfs_pgarray_set() to open code") Signed-off-by: Benjamin Coddington Cc: stable@vger.kernel.org # 4.12 Signed-off-by: Anna Schumaker --- fs/nfs/pagelist.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 83d2918f1b13..8a23e2b40b04 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -779,6 +779,7 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc, gfp_t gfp_flags = GFP_KERNEL; pagecount = nfs_page_array_len(mirror->pg_base, mirror->pg_count); + pg_array->npages = pagecount; if (pagecount <= ARRAY_SIZE(pg_array->page_array)) pg_array->pagevec = pg_array->page_array; -- cgit v1.2.3-59-g8ed1b From ce85bd29210f2cd84dc1f762c3992d8e6db822c2 Mon Sep 17 00:00:00 2001 From: Tuo Chen Peng Date: Tue, 6 Jun 2017 23:42:44 -0700 Subject: nfs: Fix fscache stat printing in nfs_show_stats() nfs_show_stats() was incorrectly reading statistics for bytes when printing that for fsc. It caused files like /proc/self/mountstats to report incorrect fsc statistics for NFS mounts. Signed-off-by: Tuo Chen Peng Signed-off-by: Anna Schumaker --- fs/nfs/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/super.c b/fs/nfs/super.c index eceb4eabb064..b4176393f049 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -879,7 +879,7 @@ int nfs_show_stats(struct seq_file *m, struct dentry *root) if (nfss->options & NFS_OPTION_FSCACHE) { seq_printf(m, "\n\tfsc:\t"); for (i = 0; i < __NFSIOS_FSCACHEMAX; i++) - seq_printf(m, "%Lu ", totals.bytes[i]); + seq_printf(m, "%Lu ", totals.fscache[i]); } #endif seq_printf(m, "\n"); -- cgit v1.2.3-59-g8ed1b From 4cd1ec95bdec8aedb280ca0f244ededb76f747ab Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 23 Jun 2017 18:16:25 +0300 Subject: NFS: silence a uninitialized variable warning Static checkers have gotten clever enough to complain that "id_long" is uninitialized on the failure path. It's harmless, but simple to fix. Signed-off-by: Dan Carpenter Signed-off-by: Anna Schumaker --- fs/nfs/nfs4idmap.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c index 835c163f61af..dd5d27da8c0c 100644 --- a/fs/nfs/nfs4idmap.c +++ b/fs/nfs/nfs4idmap.c @@ -364,7 +364,8 @@ static int nfs_idmap_lookup_id(const char *name, size_t namelen, const char *typ ret = -EINVAL; } else { ret = kstrtol(id_str, 10, &id_long); - *id = (__u32)id_long; + if (!ret) + *id = (__u32)id_long; } return ret; } -- cgit v1.2.3-59-g8ed1b From a0bc01e0f1fa39702b5244b3bac699bea0d4f413 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Fri, 23 Jun 2017 10:26:58 -0400 Subject: PNFS fix EACCESS on commit to DS handling Commit fabbbee0eb0f "PNFS fix fallback to MDS if got error on commit to DS" moved the pnfs_set_lo_fail() to unhandled errors which was not correct and lead to a kernel oops on umount. Instead, fix the original EACCESS on commit to DS error by getting the new layout and re-doing the IO. Fixes: fabbbee0eb0f ("PNFS fix fallback to MDS if got error on commit to DS") Signed-off-by: Olga Kornievskaia Cc: stable@vger.kernel.org # v4.12 Signed-off-by: Anna Schumaker --- fs/nfs/filelayout/filelayout.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 1cf85d65b748..3e486cd01caf 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -172,6 +172,7 @@ static int filelayout_async_handle_error(struct rpc_task *task, case -NFS4ERR_RETRY_UNCACHED_REP: break; /* Invalidate Layout errors */ + case -NFS4ERR_ACCESS: case -NFS4ERR_PNFS_NO_LAYOUT: case -ESTALE: /* mapped NFS4ERR_STALE */ case -EBADHANDLE: /* mapped NFS4ERR_BADHANDLE */ @@ -202,10 +203,10 @@ static int filelayout_async_handle_error(struct rpc_task *task, task->tk_status); nfs4_mark_deviceid_unavailable(devid); pnfs_error_mark_layout_for_return(inode, lseg); + pnfs_set_lo_fail(lseg); rpc_wake_up(&tbl->slot_tbl_waitq); /* fall through */ default: - pnfs_set_lo_fail(lseg); reset: dprintk("%s Retry through MDS. Error %d\n", __func__, task->tk_status); -- cgit v1.2.3-59-g8ed1b From 22368ff11d72eb06051f9b51abbc6842496c2d3a Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Fri, 23 Jun 2017 10:26:59 -0400 Subject: PNFS for stateid errors retry against MDS first Upon receiving a stateid error such as BAD_STATEID, the client should retry the operation against the MDS before deciding to do stateid recovery. Previously, the code would initiate state recovery and it could lead to a race in a state manager that could chose an incorrect recovery method which would lead to the EIO failure for the application. Signed-off-by: Olga Kornievskaia Signed-off-by: Anna Schumaker --- fs/nfs/filelayout/filelayout.c | 28 ---------------------------- fs/nfs/flexfilelayout/flexfilelayout.c | 33 --------------------------------- 2 files changed, 61 deletions(-) diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 3e486cd01caf..080fc6b278bd 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -126,32 +126,13 @@ static int filelayout_async_handle_error(struct rpc_task *task, { struct pnfs_layout_hdr *lo = lseg->pls_layout; struct inode *inode = lo->plh_inode; - struct nfs_server *mds_server = NFS_SERVER(inode); struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg); - struct nfs_client *mds_client = mds_server->nfs_client; struct nfs4_slot_table *tbl = &clp->cl_session->fc_slot_table; if (task->tk_status >= 0) return 0; switch (task->tk_status) { - /* MDS state errors */ - case -NFS4ERR_DELEG_REVOKED: - case -NFS4ERR_ADMIN_REVOKED: - case -NFS4ERR_BAD_STATEID: - case -NFS4ERR_OPENMODE: - if (state == NULL) - break; - if (nfs4_schedule_stateid_recovery(mds_server, state) < 0) - goto out_bad_stateid; - goto wait_on_recovery; - case -NFS4ERR_EXPIRED: - if (state != NULL) { - if (nfs4_schedule_stateid_recovery(mds_server, state) < 0) - goto out_bad_stateid; - } - nfs4_schedule_lease_recovery(mds_client); - goto wait_on_recovery; /* DS session errors */ case -NFS4ERR_BADSESSION: case -NFS4ERR_BADSLOT: @@ -212,17 +193,8 @@ reset: task->tk_status); return -NFS4ERR_RESET_TO_MDS; } -out: task->tk_status = 0; return -EAGAIN; -out_bad_stateid: - task->tk_status = -EIO; - return 0; -wait_on_recovery: - rpc_sleep_on(&mds_client->cl_rpcwaitq, task, NULL); - if (test_bit(NFS4CLNT_MANAGER_RUNNING, &mds_client->cl_state) == 0) - rpc_wake_up_queued_task(&mds_client->cl_rpcwaitq, task); - goto out; } /* NFS_PROTO call done callback routines */ diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 23542dc44a25..1f2ac3dd0fe5 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1050,34 +1050,10 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task, { struct pnfs_layout_hdr *lo = lseg->pls_layout; struct inode *inode = lo->plh_inode; - struct nfs_server *mds_server = NFS_SERVER(inode); - struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx); - struct nfs_client *mds_client = mds_server->nfs_client; struct nfs4_slot_table *tbl = &clp->cl_session->fc_slot_table; switch (task->tk_status) { - /* MDS state errors */ - case -NFS4ERR_DELEG_REVOKED: - case -NFS4ERR_ADMIN_REVOKED: - case -NFS4ERR_BAD_STATEID: - if (state == NULL) - break; - nfs_remove_bad_delegation(state->inode, NULL); - case -NFS4ERR_OPENMODE: - if (state == NULL) - break; - if (nfs4_schedule_stateid_recovery(mds_server, state) < 0) - goto out_bad_stateid; - goto wait_on_recovery; - case -NFS4ERR_EXPIRED: - if (state != NULL) { - if (nfs4_schedule_stateid_recovery(mds_server, state) < 0) - goto out_bad_stateid; - } - nfs4_schedule_lease_recovery(mds_client); - goto wait_on_recovery; - /* DS session errors */ case -NFS4ERR_BADSESSION: case -NFS4ERR_BADSLOT: case -NFS4ERR_BAD_HIGH_SLOT: @@ -1137,17 +1113,8 @@ reset: task->tk_status); return -NFS4ERR_RESET_TO_MDS; } -out: task->tk_status = 0; return -EAGAIN; -out_bad_stateid: - task->tk_status = -EIO; - return 0; -wait_on_recovery: - rpc_sleep_on(&mds_client->cl_rpcwaitq, task, NULL); - if (test_bit(NFS4CLNT_MANAGER_RUNNING, &mds_client->cl_state) == 0) - rpc_wake_up_queued_task(&mds_client->cl_rpcwaitq, task); - goto out; } /* Retry all errors through either pNFS or MDS except for -EJUKEBOX */ -- cgit v1.2.3-59-g8ed1b From cc89684c9a265828ce061037f1f79f4a68ccd3f7 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 5 Jul 2017 12:22:20 +1000 Subject: NFS: only invalidate dentrys that are clearly invalid. Since commit bafc9b754f75 ("vfs: More precise tests in d_invalidate") in v3.18, a return of '0' from ->d_revalidate() will cause the dentry to be invalidated even if it has filesystems mounted on or it or on a descendant. The mounted filesystem is unmounted. This means we need to be careful not to return 0 unless the directory referred to truly is invalid. So -ESTALE or -ENOENT should invalidate the directory. Other errors such a -EPERM or -ERESTARTSYS should be returned from ->d_revalidate() so they are propagated to the caller. A particular problem can be demonstrated by: 1/ mount an NFS filesystem using NFSv3 on /mnt 2/ mount any other filesystem on /mnt/foo 3/ ls /mnt/foo 4/ turn off network, or otherwise make the server unable to respond 5/ ls /mnt/foo & 6/ cat /proc/$!/stack # note that nfs_lookup_revalidate is in the call stack 7/ kill -9 $! # this results in -ERESTARTSYS being returned 8/ observe that /mnt/foo has been unmounted. This patch changes nfs_lookup_revalidate() to only treat -ESTALE from nfs_lookup_verify_inode() and -ESTALE or -ENOENT from ->lookup() as indicating an invalid inode. Other errors are returned. Also nfs_check_inode_attributes() is changed to return -ESTALE rather than -EIO. This is consistent with the error returned in similar circumstances from nfs_update_inode(). As this bug allows any user to unmount a filesystem mounted on an NFS filesystem, this fix is suitable for stable kernels. Fixes: bafc9b754f75 ("vfs: More precise tests in d_invalidate") Cc: stable@vger.kernel.org (v3.18+) Signed-off-by: NeilBrown Signed-off-by: Anna Schumaker --- fs/nfs/dir.c | 12 ++++++++---- fs/nfs/inode.c | 4 ++-- 2 files changed, 10 insertions(+), 6 deletions(-) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index ab69ebb48350..98b18aaf45c9 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1115,11 +1115,13 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) /* Force a full look up iff the parent directory has changed */ if (!nfs_is_exclusive_create(dir, flags) && nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU)) { - - if (nfs_lookup_verify_inode(inode, flags)) { + error = nfs_lookup_verify_inode(inode, flags); + if (error) { if (flags & LOOKUP_RCU) return -ECHILD; - goto out_zap_parent; + if (error == -ESTALE) + goto out_zap_parent; + goto out_error; } nfs_advise_use_readdirplus(dir); goto out_valid; @@ -1144,8 +1146,10 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) trace_nfs_lookup_revalidate_enter(dir, dentry, flags); error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label); trace_nfs_lookup_revalidate_exit(dir, dentry, flags, error); - if (error) + if (error == -ESTALE || error == -ENOENT) goto out_bad; + if (error) + goto out_error; if (nfs_compare_fh(NFS_FH(inode), fhandle)) goto out_bad; if ((error = nfs_refresh_inode(inode, fattr)) != 0) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 1de93ba78dc9..8c465d3c7e05 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1315,9 +1315,9 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat return 0; /* Has the inode gone and changed behind our back? */ if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid) - return -EIO; + return -ESTALE; if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT)) - return -EIO; + return -ESTALE; if (!nfs_file_has_buffered_writers(nfsi)) { /* Verify a few of the more important attributes */ -- cgit v1.2.3-59-g8ed1b From eaa2b82c3b3c938ab4635f8967d33f3e581da836 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 3 Jul 2017 15:27:26 +1000 Subject: NFS: guard against confused server in nfs_atomic_open() A confused server could return a filehandle for an NFSv4 OPEN request, which it previously returned for a directory. So the inode returned by ->open_context() in nfs_atomic_open() could conceivably be a directory inode. This has particular implications for the call to nfs_file_set_open_context() in nfs_finish_open(). If that is called on a directory inode, then the nfs_open_context that gets stored in the filp->private_data will be linked to nfs_inode->open_files. When the directory is closed, nfs_closedir() will (ultimately) free the ->private_data, but not unlink it from nfs_inode->open_files (because it doesn't expect an nfs_open_context there). Subsequently the memory could get used for something else and eventually if the ->open_files list is walked, the walker will fall off the end and crash. So: change nfs_finish_open() to only call nfs_file_set_open_context() for regular-file inodes. This failure mode has been seen in a production setting (unknown NFS server implementation). The kernel was v3.0 and the specific sequence seen would not affect more recent kernels, but I think a risk is still present, and caution is wise. Signed-off-by: NeilBrown Signed-off-by: Anna Schumaker --- fs/nfs/dir.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 98b18aaf45c9..90bc4025ca3c 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1431,8 +1431,10 @@ static int nfs_finish_open(struct nfs_open_context *ctx, err = finish_open(file, dentry, do_open, opened); if (err) goto out; - nfs_file_set_open_context(file, ctx); - + if (S_ISREG(file->f_path.dentry->d_inode->i_mode)) + nfs_file_set_open_context(file, ctx); + else + err = -ESTALE; out: return err; } -- cgit v1.2.3-59-g8ed1b From 26fde4dfcbdcbbac394bb35de0c0f842de6972b5 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 3 Jul 2017 15:27:26 +1000 Subject: NFS: check for nfs_refresh_inode() errors in nfs_fhget() If an NFS server returns a filehandle that we have previously seen, and reports a different type, then nfs_refresh_inode() will log a warning and return an error. nfs_fhget() does not check for this error and may return an inode with a different type than the one that the server reported. This is likely to cause confusion, and is one way that ->open_context() could return a directory inode as discussed in the previous patch. So if nfs_refresh_inode() returns and error, return that error from nfs_fhget() to avoid the confusion propagating. Signed-off-by: NeilBrown Signed-off-by: Anna Schumaker --- fs/nfs/inode.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 8c465d3c7e05..7e7a894601b9 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -525,8 +525,14 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st nfs_fscache_init_inode(inode); unlock_new_inode(inode); - } else - nfs_refresh_inode(inode, fattr); + } else { + int err = nfs_refresh_inode(inode, fattr); + if (err < 0) { + iput(inode); + inode = ERR_PTR(err); + goto out_no_inode; + } + } dprintk("NFS: nfs_fhget(%s/%Lu fh_crc=0x%08x ct=%d)\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode), -- cgit v1.2.3-59-g8ed1b From 04d25b7d5d1b43fbaffe4ad4bb21288f0f305338 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 8 Jun 2017 11:51:48 -0400 Subject: xprtrdma: On invalidation failure, remove MWs from rl_registered Callers assume the ro_unmap_sync and ro_unmap_safe methods empty the list of registered MRs. Ensure that all paths through fmr_op_unmap_sync() remove MWs from that list. Fixes: 9d6b04097882 ("xprtrdma: Place registered MWs on a ... ") Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/fmr_ops.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index 59e64025ed96..21f3cd5e2d6b 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -295,6 +295,7 @@ out_reset: pr_err("rpcrdma: ib_unmap_fmr failed (%i)\n", rc); list_for_each_entry_safe(mw, tmp, &req->rl_registered, mw_list) { + list_del_init(&mw->mw_list); list_del_init(&mw->fmr.fm_mr->list); fmr_op_recover_mr(mw); } -- cgit v1.2.3-59-g8ed1b From 4b196dc6fee9ba838ebabf824e294a429c79b27d Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 8 Jun 2017 11:51:56 -0400 Subject: xprtrdma: Pre-mark remotely invalidated MRs There are rare cases where an rpcrdma_req and its matched rpcrdma_rep can be re-used, via rpcrdma_buffer_put, while the RPC reply handler is still using that req. This is typically due to a signal firing at just the wrong instant. As part of closing this race window, avoid using the wrong rpcrdma_rep to detect remotely invalidated MRs. Mark MRs as invalidated while we are sure the rep is still OK to use. BugLink: https://bugzilla.linux-nfs.org/show_bug.cgi?id=305 Fixes: 68791649a725 ('xprtrdma: Invalidate in the RPC reply ... ') Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/frwr_ops.c | 4 +--- net/sunrpc/xprtrdma/rpc_rdma.c | 22 ++++++++++++++++++++-- net/sunrpc/xprtrdma/verbs.c | 1 + net/sunrpc/xprtrdma/xprt_rdma.h | 6 ++++++ 4 files changed, 28 insertions(+), 5 deletions(-) diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index f81dd93176c0..31290cbedfe0 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -464,7 +464,6 @@ static void frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) { struct ib_send_wr *first, **prev, *last, *bad_wr; - struct rpcrdma_rep *rep = req->rl_reply; struct rpcrdma_ia *ia = &r_xprt->rx_ia; struct rpcrdma_frmr *f; struct rpcrdma_mw *mw; @@ -483,8 +482,7 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) list_for_each_entry(mw, &req->rl_registered, mw_list) { mw->frmr.fr_state = FRMR_IS_INVALID; - if ((rep->rr_wc_flags & IB_WC_WITH_INVALIDATE) && - (mw->mw_handle == rep->rr_inv_rkey)) + if (mw->mw_flags & RPCRDMA_MW_F_RI) continue; f = &mw->frmr; diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 694e9b13ecf0..2356a6305f25 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -928,6 +928,24 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) return fixup_copy_count; } +/* Caller must guarantee @rep remains stable during this call. + */ +static void +rpcrdma_mark_remote_invalidation(struct list_head *mws, + struct rpcrdma_rep *rep) +{ + struct rpcrdma_mw *mw; + + if (!(rep->rr_wc_flags & IB_WC_WITH_INVALIDATE)) + return; + + list_for_each_entry(mw, mws, mw_list) + if (mw->mw_handle == rep->rr_inv_rkey) { + mw->mw_flags = RPCRDMA_MW_F_RI; + break; /* only one invalidated MR per RPC */ + } +} + #if defined(CONFIG_SUNRPC_BACKCHANNEL) /* By convention, backchannel calls arrive via rdma_msg type * messages, and never populate the chunk lists. This makes @@ -1006,13 +1024,13 @@ rpcrdma_reply_handler(struct work_struct *work) /* Sanity checking has passed. We are now committed * to complete this transaction. */ + rpcrdma_mark_remote_invalidation(&req->rl_registered, rep); list_del_init(&rqst->rq_list); + req->rl_reply = rep; spin_unlock_bh(&xprt->transport_lock); dprintk("RPC: %s: reply %p completes request %p (xid 0x%08x)\n", __func__, rep, req, be32_to_cpu(headerp->rm_xid)); - /* from here on, the reply is no longer an orphan */ - req->rl_reply = rep; xprt->reestablish_timeout = 0; if (headerp->rm_vers != rpcrdma_version) diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 3dbce9ac4327..a8be66d806dc 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1187,6 +1187,7 @@ rpcrdma_get_mw(struct rpcrdma_xprt *r_xprt) if (!mw) goto out_nomws; + mw->mw_flags = 0; return mw; out_nomws: diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 1d66acf1a723..2e027335fcbc 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -271,6 +271,7 @@ struct rpcrdma_mw { struct scatterlist *mw_sg; int mw_nents; enum dma_data_direction mw_dir; + unsigned long mw_flags; union { struct rpcrdma_fmr fmr; struct rpcrdma_frmr frmr; @@ -282,6 +283,11 @@ struct rpcrdma_mw { struct list_head mw_all; }; +/* mw_flags */ +enum { + RPCRDMA_MW_F_RI = 1, +}; + /* * struct rpcrdma_req -- structure central to the request/reply sequence. * -- cgit v1.2.3-59-g8ed1b From 451d26e151f0792601d10378a608c52304b6a357 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 8 Jun 2017 11:52:04 -0400 Subject: xprtrdma: Pass only the list of registered MRs to ro_unmap_sync There are rare cases where an rpcrdma_req can be re-used (via rpcrdma_buffer_put) while the RPC reply handler is still running. This is due to a signal firing at just the wrong instant. Since commit 9d6b04097882 ("xprtrdma: Place registered MWs on a per-req list"), rpcrdma_mws are self-contained; ie., they fully describe an MR and scatterlist, and no part of that information is stored in struct rpcrdma_req. As part of closing the above race window, pass only the req's list of registered MRs to ro_unmap_sync, rather than the rpcrdma_req itself. Some extra transport header sanity checking is removed. Since the client depends on its own recollection of what memory had been registered, there doesn't seem to be a way to abuse this change. And, the check was not terribly effective. If the client had sent Read chunks, the "list_empty" test is negative in both of the removed cases, which are actually looking for Write or Reply chunks. BugLink: https://bugzilla.linux-nfs.org/show_bug.cgi?id=305 Fixes: 68791649a725 ('xprtrdma: Invalidate in the RPC reply ... ') Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/fmr_ops.c | 16 +++++++++------- net/sunrpc/xprtrdma/frwr_ops.c | 19 +++++++++---------- net/sunrpc/xprtrdma/rpc_rdma.c | 16 +++++++--------- net/sunrpc/xprtrdma/xprt_rdma.h | 2 +- 4 files changed, 26 insertions(+), 27 deletions(-) diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index 21f3cd5e2d6b..5556ed99b4b7 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -255,24 +255,26 @@ out_maperr: * Sleeps until it is safe for the host CPU to access the * previously mapped memory regions. * - * Caller ensures that req->rl_registered is not empty. + * Caller ensures that @mws is not empty before the call. This + * function empties the list. */ static void -fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) +fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct list_head *mws) { struct rpcrdma_mw *mw, *tmp; LIST_HEAD(unmap_list); int rc; - dprintk("RPC: %s: req %p\n", __func__, req); - /* ORDER: Invalidate all of the req's MRs first * * ib_unmap_fmr() is slow, so use a single call instead * of one call per mapped FMR. */ - list_for_each_entry(mw, &req->rl_registered, mw_list) + list_for_each_entry(mw, mws, mw_list) { + dprintk("RPC: %s: unmapping fmr %p\n", + __func__, &mw->fmr); list_add_tail(&mw->fmr.fm_mr->list, &unmap_list); + } r_xprt->rx_stats.local_inv_needed++; rc = ib_unmap_fmr(&unmap_list); if (rc) @@ -281,7 +283,7 @@ fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) /* ORDER: Now DMA unmap all of the req's MRs, and return * them to the free MW list. */ - list_for_each_entry_safe(mw, tmp, &req->rl_registered, mw_list) { + list_for_each_entry_safe(mw, tmp, mws, mw_list) { list_del_init(&mw->mw_list); list_del_init(&mw->fmr.fm_mr->list); ib_dma_unmap_sg(r_xprt->rx_ia.ri_device, @@ -294,7 +296,7 @@ fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) out_reset: pr_err("rpcrdma: ib_unmap_fmr failed (%i)\n", rc); - list_for_each_entry_safe(mw, tmp, &req->rl_registered, mw_list) { + list_for_each_entry_safe(mw, tmp, mws, mw_list) { list_del_init(&mw->mw_list); list_del_init(&mw->fmr.fm_mr->list); fmr_op_recover_mr(mw); diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 31290cbedfe0..97f9f85fa5c1 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -458,10 +458,11 @@ out_senderr: * Sleeps until it is safe for the host CPU to access the * previously mapped memory regions. * - * Caller ensures that req->rl_registered is not empty. + * Caller ensures that @mws is not empty before the call. This + * function empties the list. */ static void -frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) +frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct list_head *mws) { struct ib_send_wr *first, **prev, *last, *bad_wr; struct rpcrdma_ia *ia = &r_xprt->rx_ia; @@ -469,9 +470,7 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) struct rpcrdma_mw *mw; int count, rc; - dprintk("RPC: %s: req %p\n", __func__, req); - - /* ORDER: Invalidate all of the req's MRs first + /* ORDER: Invalidate all of the MRs first * * Chain the LOCAL_INV Work Requests and post them with * a single ib_post_send() call. @@ -479,7 +478,7 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) f = NULL; count = 0; prev = &first; - list_for_each_entry(mw, &req->rl_registered, mw_list) { + list_for_each_entry(mw, mws, mw_list) { mw->frmr.fr_state = FRMR_IS_INVALID; if (mw->mw_flags & RPCRDMA_MW_F_RI) @@ -528,12 +527,12 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) wait_for_completion(&f->fr_linv_done); - /* ORDER: Now DMA unmap all of the req's MRs, and return + /* ORDER: Now DMA unmap all of the MRs, and return * them to the free MW list. */ unmap: - while (!list_empty(&req->rl_registered)) { - mw = rpcrdma_pop_mw(&req->rl_registered); + while (!list_empty(mws)) { + mw = rpcrdma_pop_mw(mws); dprintk("RPC: %s: DMA unmapping frmr %p\n", __func__, &mw->frmr); ib_dma_unmap_sg(ia->ri_device, @@ -549,7 +548,7 @@ reset_mrs: /* Find and reset the MRs in the LOCAL_INV WRs that did not * get posted. This is synchronous, and slow. */ - list_for_each_entry(mw, &req->rl_registered, mw_list) { + list_for_each_entry(mw, mws, mw_list) { f = &mw->frmr; if (mw->mw_handle == bad_wr->ex.invalidate_rkey) { __frwr_reset_mr(ia, mw); diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 2356a6305f25..c88132d02fb8 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -995,6 +995,7 @@ rpcrdma_reply_handler(struct work_struct *work) __be32 *iptr; int rdmalen, status, rmerr; unsigned long cwnd; + struct list_head mws; dprintk("RPC: %s: incoming rep %p\n", __func__, rep); @@ -1024,7 +1025,8 @@ rpcrdma_reply_handler(struct work_struct *work) /* Sanity checking has passed. We are now committed * to complete this transaction. */ - rpcrdma_mark_remote_invalidation(&req->rl_registered, rep); + list_replace_init(&req->rl_registered, &mws); + rpcrdma_mark_remote_invalidation(&mws, rep); list_del_init(&rqst->rq_list); req->rl_reply = rep; spin_unlock_bh(&xprt->transport_lock); @@ -1042,12 +1044,9 @@ rpcrdma_reply_handler(struct work_struct *work) case rdma_msg: /* never expect read chunks */ /* never expect reply chunks (two ways to check) */ - /* never expect write chunks without having offered RDMA */ if (headerp->rm_body.rm_chunks[0] != xdr_zero || (headerp->rm_body.rm_chunks[1] == xdr_zero && - headerp->rm_body.rm_chunks[2] != xdr_zero) || - (headerp->rm_body.rm_chunks[1] != xdr_zero && - list_empty(&req->rl_registered))) + headerp->rm_body.rm_chunks[2] != xdr_zero)) goto badheader; if (headerp->rm_body.rm_chunks[1] != xdr_zero) { /* count any expected write chunks in read reply */ @@ -1084,8 +1083,7 @@ rpcrdma_reply_handler(struct work_struct *work) /* never expect read or write chunks, always reply chunks */ if (headerp->rm_body.rm_chunks[0] != xdr_zero || headerp->rm_body.rm_chunks[1] != xdr_zero || - headerp->rm_body.rm_chunks[2] != xdr_one || - list_empty(&req->rl_registered)) + headerp->rm_body.rm_chunks[2] != xdr_one) goto badheader; iptr = (__be32 *)((unsigned char *)headerp + RPCRDMA_HDRLEN_MIN); @@ -1118,8 +1116,8 @@ out: * control: waking the next RPC waits until this RPC has * relinquished all its Send Queue entries. */ - if (!list_empty(&req->rl_registered)) - r_xprt->rx_ia.ri_ops->ro_unmap_sync(r_xprt, req); + if (!list_empty(&mws)) + r_xprt->rx_ia.ri_ops->ro_unmap_sync(r_xprt, &mws); spin_lock_bh(&xprt->transport_lock); cwnd = xprt->cwnd; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 2e027335fcbc..1c23117bf1b0 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -467,7 +467,7 @@ struct rpcrdma_memreg_ops { struct rpcrdma_mr_seg *, int, bool, struct rpcrdma_mw **); void (*ro_unmap_sync)(struct rpcrdma_xprt *, - struct rpcrdma_req *); + struct list_head *); void (*ro_unmap_safe)(struct rpcrdma_xprt *, struct rpcrdma_req *, bool); void (*ro_recover_mr)(struct rpcrdma_mw *); -- cgit v1.2.3-59-g8ed1b From a80d66c9e0d1ac31fa3427340efa0bf79b338023 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 8 Jun 2017 11:52:12 -0400 Subject: xprtrdma: Rename rpcrdma_req::rl_free Clean up: I'm about to use the rl_free field for purposes other than a free list. So use a more generic name. This is a refactoring change only. BugLink: https://bugzilla.linux-nfs.org/show_bug.cgi?id=305 Fixes: 68791649a725 ('xprtrdma: Invalidate in the RPC reply ... ') Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/verbs.c | 9 ++++----- net/sunrpc/xprtrdma/xprt_rdma.h | 2 +- 2 files changed, 5 insertions(+), 6 deletions(-) diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index a8be66d806dc..df72224604d2 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -971,7 +971,6 @@ rpcrdma_create_req(struct rpcrdma_xprt *r_xprt) if (req == NULL) return ERR_PTR(-ENOMEM); - INIT_LIST_HEAD(&req->rl_free); spin_lock(&buffer->rb_reqslock); list_add(&req->rl_all, &buffer->rb_allreqs); spin_unlock(&buffer->rb_reqslock); @@ -1055,7 +1054,7 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) goto out; } req->rl_backchannel = false; - list_add(&req->rl_free, &buf->rb_send_bufs); + list_add(&req->rl_list, &buf->rb_send_bufs); } INIT_LIST_HEAD(&buf->rb_recv_bufs); @@ -1084,8 +1083,8 @@ rpcrdma_buffer_get_req_locked(struct rpcrdma_buffer *buf) struct rpcrdma_req *req; req = list_first_entry(&buf->rb_send_bufs, - struct rpcrdma_req, rl_free); - list_del(&req->rl_free); + struct rpcrdma_req, rl_list); + list_del(&req->rl_list); return req; } @@ -1268,7 +1267,7 @@ rpcrdma_buffer_put(struct rpcrdma_req *req) spin_lock(&buffers->rb_lock); buffers->rb_send_count--; - list_add_tail(&req->rl_free, &buffers->rb_send_bufs); + list_add_tail(&req->rl_list, &buffers->rb_send_bufs); if (rep) { buffers->rb_recv_count--; list_add_tail(&rep->rr_list, &buffers->rb_recv_bufs); diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 1c23117bf1b0..ad918c840fc7 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -340,7 +340,7 @@ enum { struct rpcrdma_buffer; struct rpcrdma_req { - struct list_head rl_free; + struct list_head rl_list; unsigned int rl_mapped_sges; unsigned int rl_connect_cookie; struct rpcrdma_buffer *rl_buffer; -- cgit v1.2.3-59-g8ed1b From 431af645cf662652bc43c7a26f87cb40aedb01d9 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 8 Jun 2017 11:52:20 -0400 Subject: xprtrdma: Fix client lock-up after application signal fires After a signal, the RPC client aborts synchronous RPCs running on behalf of the signaled application. The server is still executing those RPCs, and will write the results back into the client's memory when it's done. By the time the server writes the results, that memory is likely being used for other purposes. Therefore xprtrdma has to immediately invalidate all memory regions used by those aborted RPCs to prevent the server's writes from clobbering that re-used memory. With FMR memory registration, invalidation takes a relatively long time. In fact, the invalidation is often still running when the server tries to write the results into the memory regions that are being invalidated. This sets up a race between two processes: 1. After the signal, xprt_rdma_free calls ro_unmap_safe. 2. While ro_unmap_safe is still running, the server replies and rpcrdma_reply_handler runs, calling ro_unmap_sync. Both processes invoke ib_unmap_fmr on the same FMR. The mlx4 driver allows two ib_unmap_fmr calls on the same FMR at the same time, but HCAs generally don't tolerate this. Sometimes this can result in a system crash. If the HCA happens to survive, rpcrdma_reply_handler continues. It removes the rpc_rqst from rq_list and releases the transport_lock. This enables xprt_rdma_free to run in another process, and the rpc_rqst is released while rpcrdma_reply_handler is still waiting for the ib_unmap_fmr call to finish. But further down in rpcrdma_reply_handler, the transport_lock is taken again, and "rqst" is dereferenced. If "rqst" has already been released, this triggers a general protection fault. Since bottom- halves are disabled, the system locks up. Address both issues by reversing the order of the xprt_lookup_rqst call and the ro_unmap_sync call. Introduce a separate lookup mechanism for rpcrdma_req's to enable calling ro_unmap_sync before xprt_lookup_rqst. Now the handler takes the transport_lock once and holds it for the XID lookup and RPC completion. BugLink: https://bugzilla.linux-nfs.org/show_bug.cgi?id=305 Fixes: 68791649a725 ('xprtrdma: Invalidate in the RPC reply ... ') Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/rpc_rdma.c | 79 ++++++++++++++++++++++++++--------------- net/sunrpc/xprtrdma/transport.c | 3 +- net/sunrpc/xprtrdma/verbs.c | 3 +- net/sunrpc/xprtrdma/xprt_rdma.h | 30 ++++++++++++++++ 4 files changed, 84 insertions(+), 31 deletions(-) diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index c88132d02fb8..b6584ae8e251 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -734,6 +734,9 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) rpclen = 0; } + req->rl_xid = rqst->rq_xid; + rpcrdma_insert_req(&r_xprt->rx_buf, req); + /* This implementation supports the following combinations * of chunk lists in one RPC-over-RDMA Call message: * @@ -987,11 +990,12 @@ rpcrdma_reply_handler(struct work_struct *work) { struct rpcrdma_rep *rep = container_of(work, struct rpcrdma_rep, rr_work); + struct rpcrdma_xprt *r_xprt = rep->rr_rxprt; + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + struct rpc_xprt *xprt = &r_xprt->rx_xprt; struct rpcrdma_msg *headerp; struct rpcrdma_req *req; struct rpc_rqst *rqst; - struct rpcrdma_xprt *r_xprt = rep->rr_rxprt; - struct rpc_xprt *xprt = &r_xprt->rx_xprt; __be32 *iptr; int rdmalen, status, rmerr; unsigned long cwnd; @@ -1013,28 +1017,45 @@ rpcrdma_reply_handler(struct work_struct *work) /* Match incoming rpcrdma_rep to an rpcrdma_req to * get context for handling any incoming chunks. */ - spin_lock_bh(&xprt->transport_lock); - rqst = xprt_lookup_rqst(xprt, headerp->rm_xid); - if (!rqst) + spin_lock(&buf->rb_lock); + req = rpcrdma_lookup_req_locked(&r_xprt->rx_buf, + headerp->rm_xid); + if (!req) goto out_nomatch; - - req = rpcr_to_rdmar(rqst); if (req->rl_reply) goto out_duplicate; - /* Sanity checking has passed. We are now committed - * to complete this transaction. - */ list_replace_init(&req->rl_registered, &mws); rpcrdma_mark_remote_invalidation(&mws, rep); - list_del_init(&rqst->rq_list); + + /* Avoid races with signals and duplicate replies + * by marking this req as matched. + */ req->rl_reply = rep; - spin_unlock_bh(&xprt->transport_lock); + spin_unlock(&buf->rb_lock); + dprintk("RPC: %s: reply %p completes request %p (xid 0x%08x)\n", __func__, rep, req, be32_to_cpu(headerp->rm_xid)); - xprt->reestablish_timeout = 0; + /* Invalidate and unmap the data payloads before waking the + * waiting application. This guarantees the memory regions + * are properly fenced from the server before the application + * accesses the data. It also ensures proper send flow control: + * waking the next RPC waits until this RPC has relinquished + * all its Send Queue entries. + */ + if (!list_empty(&mws)) + r_xprt->rx_ia.ri_ops->ro_unmap_sync(r_xprt, &mws); + /* Perform XID lookup, reconstruction of the RPC reply, and + * RPC completion while holding the transport lock to ensure + * the rep, rqst, and rq_task pointers remain stable. + */ + spin_lock_bh(&xprt->transport_lock); + rqst = xprt_lookup_rqst(xprt, headerp->rm_xid); + if (!rqst) + goto out_norqst; + xprt->reestablish_timeout = 0; if (headerp->rm_vers != rpcrdma_version) goto out_badversion; @@ -1109,17 +1130,6 @@ badheader: } out: - /* Invalidate and flush the data payloads before waking the - * waiting application. This guarantees the memory region is - * properly fenced from the server before the application - * accesses the data. It also ensures proper send flow - * control: waking the next RPC waits until this RPC has - * relinquished all its Send Queue entries. - */ - if (!list_empty(&mws)) - r_xprt->rx_ia.ri_ops->ro_unmap_sync(r_xprt, &mws); - - spin_lock_bh(&xprt->transport_lock); cwnd = xprt->cwnd; xprt->cwnd = atomic_read(&r_xprt->rx_buf.rb_credits) << RPC_CWNDSHIFT; if (xprt->cwnd > cwnd) @@ -1128,7 +1138,7 @@ out: xprt_complete_rqst(rqst->rq_task, status); spin_unlock_bh(&xprt->transport_lock); dprintk("RPC: %s: xprt_complete_rqst(0x%p, 0x%p, %d)\n", - __func__, xprt, rqst, status); + __func__, xprt, rqst, status); return; out_badstatus: @@ -1177,26 +1187,37 @@ out_rdmaerr: r_xprt->rx_stats.bad_reply_count++; goto out; -/* If no pending RPC transaction was matched, post a replacement - * receive buffer before returning. +/* The req was still available, but by the time the transport_lock + * was acquired, the rqst and task had been released. Thus the RPC + * has already been terminated. */ +out_norqst: + spin_unlock_bh(&xprt->transport_lock); + rpcrdma_buffer_put(req); + dprintk("RPC: %s: race, no rqst left for req %p\n", + __func__, req); + return; + out_shortreply: dprintk("RPC: %s: short/invalid reply\n", __func__); goto repost; out_nomatch: - spin_unlock_bh(&xprt->transport_lock); + spin_unlock(&buf->rb_lock); dprintk("RPC: %s: no match for incoming xid 0x%08x len %d\n", __func__, be32_to_cpu(headerp->rm_xid), rep->rr_len); goto repost; out_duplicate: - spin_unlock_bh(&xprt->transport_lock); + spin_unlock(&buf->rb_lock); dprintk("RPC: %s: " "duplicate reply %p to RPC request %p: xid 0x%08x\n", __func__, rep, req, be32_to_cpu(headerp->rm_xid)); +/* If no pending RPC transaction was matched, post a replacement + * receive buffer before returning. + */ repost: r_xprt->rx_stats.bad_reply_count++; if (rpcrdma_ep_post_recv(&r_xprt->rx_ia, rep)) diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 62ecbccd9748..d1c458e5ec4d 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -684,7 +684,8 @@ xprt_rdma_free(struct rpc_task *task) dprintk("RPC: %s: called on 0x%p\n", __func__, req->rl_reply); - if (unlikely(!list_empty(&req->rl_registered))) + rpcrdma_remove_req(&r_xprt->rx_buf, req); + if (!list_empty(&req->rl_registered)) ia->ri_ops->ro_unmap_safe(r_xprt, req, !RPC_IS_ASYNC(task)); rpcrdma_unmap_sges(ia, req); rpcrdma_buffer_put(req); diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index df72224604d2..a215a8759dc2 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1032,6 +1032,7 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) spin_lock_init(&buf->rb_recovery_lock); INIT_LIST_HEAD(&buf->rb_mws); INIT_LIST_HEAD(&buf->rb_all); + INIT_LIST_HEAD(&buf->rb_pending); INIT_LIST_HEAD(&buf->rb_stale_mrs); INIT_DELAYED_WORK(&buf->rb_refresh_worker, rpcrdma_mr_refresh_worker); @@ -1084,7 +1085,7 @@ rpcrdma_buffer_get_req_locked(struct rpcrdma_buffer *buf) req = list_first_entry(&buf->rb_send_bufs, struct rpcrdma_req, rl_list); - list_del(&req->rl_list); + list_del_init(&req->rl_list); return req; } diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index ad918c840fc7..b282d3f8cdd8 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -341,6 +341,7 @@ enum { struct rpcrdma_buffer; struct rpcrdma_req { struct list_head rl_list; + __be32 rl_xid; unsigned int rl_mapped_sges; unsigned int rl_connect_cookie; struct rpcrdma_buffer *rl_buffer; @@ -402,6 +403,7 @@ struct rpcrdma_buffer { int rb_send_count, rb_recv_count; struct list_head rb_send_bufs; struct list_head rb_recv_bufs; + struct list_head rb_pending; u32 rb_max_requests; atomic_t rb_credits; /* most recent credit grant */ @@ -550,6 +552,34 @@ void rpcrdma_destroy_req(struct rpcrdma_req *); int rpcrdma_buffer_create(struct rpcrdma_xprt *); void rpcrdma_buffer_destroy(struct rpcrdma_buffer *); +static inline void +rpcrdma_insert_req(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req) +{ + spin_lock(&buffers->rb_lock); + if (list_empty(&req->rl_list)) + list_add_tail(&req->rl_list, &buffers->rb_pending); + spin_unlock(&buffers->rb_lock); +} + +static inline struct rpcrdma_req * +rpcrdma_lookup_req_locked(struct rpcrdma_buffer *buffers, __be32 xid) +{ + struct rpcrdma_req *pos; + + list_for_each_entry(pos, &buffers->rb_pending, rl_list) + if (pos->rl_xid == xid) + return pos; + return NULL; +} + +static inline void +rpcrdma_remove_req(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req) +{ + spin_lock(&buffers->rb_lock); + list_del(&req->rl_list); + spin_unlock(&buffers->rb_lock); +} + struct rpcrdma_mw *rpcrdma_get_mw(struct rpcrdma_xprt *); void rpcrdma_put_mw(struct rpcrdma_xprt *, struct rpcrdma_mw *); struct rpcrdma_req *rpcrdma_buffer_get(struct rpcrdma_buffer *); -- cgit v1.2.3-59-g8ed1b From 8d75483a232aea9c3224b8146edf45b3bbb552fd Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 8 Jun 2017 11:52:28 -0400 Subject: xprtrdma: Fix FRWR invalidation error recovery When ib_post_send() fails, all LOCAL_INV WRs past @bad_wr have to be examined, and the MRs reset by hand. I'm not sure how the existing code can work by comparing R_keys. Restructure the logic so that instead it walks the chain of WRs, starting from the first bad one. Make sure to wait for completion if at least one WR was actually posted. Otherwise, if the ib_post_send fails, we can end up DMA-unmapping the MR while LOCAL_INV operations are in flight. Commit 7a89f9c626e3 ("xprtrdma: Honor ->send_request API contract") added the rdma_disconnect() call site. The disconnect actually causes more problems than it solves, and SQ overruns happen only as a result of software bugs. So remove it. Fixes: d7a21c1bed54 ("xprtrdma: Reset MRs in frwr_op_unmap_sync()") Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/frwr_ops.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 97f9f85fa5c1..24631e0edadb 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -521,12 +521,13 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct list_head *mws) * unless ri_id->qp is a valid pointer. */ r_xprt->rx_stats.local_inv_needed++; + bad_wr = NULL; rc = ib_post_send(ia->ri_id->qp, first, &bad_wr); + if (bad_wr != first) + wait_for_completion(&f->fr_linv_done); if (rc) goto reset_mrs; - wait_for_completion(&f->fr_linv_done); - /* ORDER: Now DMA unmap all of the MRs, and return * them to the free MW list. */ @@ -543,17 +544,19 @@ unmap: reset_mrs: pr_err("rpcrdma: FRMR invalidate ib_post_send returned %i\n", rc); - rdma_disconnect(ia->ri_id); /* Find and reset the MRs in the LOCAL_INV WRs that did not - * get posted. This is synchronous, and slow. + * get posted. */ - list_for_each_entry(mw, mws, mw_list) { - f = &mw->frmr; - if (mw->mw_handle == bad_wr->ex.invalidate_rkey) { - __frwr_reset_mr(ia, mw); - bad_wr = bad_wr->next; - } + rpcrdma_init_cqcount(&r_xprt->rx_ep, -count); + while (bad_wr) { + f = container_of(bad_wr, struct rpcrdma_frmr, + fr_invwr); + mw = container_of(f, struct rpcrdma_mw, frmr); + + __frwr_reset_mr(ia, mw); + + bad_wr = bad_wr->next; } goto unmap; } -- cgit v1.2.3-59-g8ed1b From 1f541895dae956df0be14a3190f507b601ac3fcc Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 8 Jun 2017 11:52:36 -0400 Subject: xprtrdma: Don't defer MR recovery if ro_map fails Deferred MR recovery does a DMA-unmapping of the MW. However, ro_map invokes rpcrdma_defer_mr_recovery in some error cases where the MW has not even been DMA-mapped yet. Avoid a DMA-unmapping error replacing rpcrdma_defer_mr_recovery. Also note that if ib_dma_map_sg is asked to map 0 nents, it will return 0. So the extra "if (i == 0)" check is no longer needed. Fixes: 42fe28f60763 ("xprtrdma: Do not leak an MW during a DMA ...") Fixes: 505bbe64dd04 ("xprtrdma: Refactor MR recovery work queues") Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/fmr_ops.c | 18 +++++++++--------- net/sunrpc/xprtrdma/frwr_ops.c | 19 ++++++++----------- 2 files changed, 17 insertions(+), 20 deletions(-) diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index 5556ed99b4b7..2f4eacdde3f2 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -213,13 +213,11 @@ fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len)) break; } - mw->mw_nents = i; mw->mw_dir = rpcrdma_data_dir(writing); - if (i == 0) - goto out_dmamap_err; - if (!ib_dma_map_sg(r_xprt->rx_ia.ri_device, - mw->mw_sg, mw->mw_nents, mw->mw_dir)) + mw->mw_nents = ib_dma_map_sg(r_xprt->rx_ia.ri_device, + mw->mw_sg, i, mw->mw_dir); + if (!mw->mw_nents) goto out_dmamap_err; for (i = 0, dma_pages = mw->fmr.fm_physaddrs; i < mw->mw_nents; i++) @@ -237,16 +235,18 @@ fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, return mw->mw_nents; out_dmamap_err: - pr_err("rpcrdma: failed to dma map sg %p sg_nents %u\n", - mw->mw_sg, mw->mw_nents); - rpcrdma_defer_mr_recovery(mw); + pr_err("rpcrdma: failed to DMA map sg %p sg_nents %d\n", + mw->mw_sg, i); + rpcrdma_put_mw(r_xprt, mw); return -EIO; out_maperr: pr_err("rpcrdma: ib_map_phys_fmr %u@0x%llx+%i (%d) status %i\n", len, (unsigned long long)dma_pages[0], pageoff, mw->mw_nents, rc); - rpcrdma_defer_mr_recovery(mw); + ib_dma_unmap_sg(r_xprt->rx_ia.ri_device, + mw->mw_sg, mw->mw_nents, mw->mw_dir); + rpcrdma_put_mw(r_xprt, mw); return -EIO; } diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 24631e0edadb..8f63d38e45a2 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -355,7 +355,7 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, struct ib_mr *mr; struct ib_reg_wr *reg_wr; struct ib_send_wr *bad_wr; - int rc, i, n, dma_nents; + int rc, i, n; u8 key; mw = NULL; @@ -391,14 +391,10 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len)) break; } - mw->mw_nents = i; mw->mw_dir = rpcrdma_data_dir(writing); - if (i == 0) - goto out_dmamap_err; - dma_nents = ib_dma_map_sg(ia->ri_device, - mw->mw_sg, mw->mw_nents, mw->mw_dir); - if (!dma_nents) + mw->mw_nents = ib_dma_map_sg(ia->ri_device, mw->mw_sg, i, mw->mw_dir); + if (!mw->mw_nents) goto out_dmamap_err; n = ib_map_mr_sg(mr, mw->mw_sg, mw->mw_nents, NULL, PAGE_SIZE); @@ -436,13 +432,14 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, return mw->mw_nents; out_dmamap_err: - pr_err("rpcrdma: failed to dma map sg %p sg_nents %u\n", - mw->mw_sg, mw->mw_nents); - rpcrdma_defer_mr_recovery(mw); + pr_err("rpcrdma: failed to DMA map sg %p sg_nents %d\n", + mw->mw_sg, i); + frmr->fr_state = FRMR_IS_INVALID; + rpcrdma_put_mw(r_xprt, mw); return -EIO; out_mapmr_err: - pr_err("rpcrdma: failed to map mr %p (%u/%u)\n", + pr_err("rpcrdma: failed to map mr %p (%d/%d)\n", frmr->fr_mr, n, mw->mw_nents); rpcrdma_defer_mr_recovery(mw); return -EIO; -- cgit v1.2.3-59-g8ed1b From 8dcbec6d20eb881ba368d0aebc3a8a678aebb1da Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 8 Jun 2017 11:52:44 -0400 Subject: NFSv4.1: Handle EXCHGID4_FLAG_CONFIRMED_R during NFSv4.1 migration Transparent State Migration copies a client's lease state from the server where a filesystem used to reside to the server where it now resides. When an NFSv4.1 client first contacts that destination server, it uses EXCHANGE_ID to detect trunking relationships. The lease that was copied there is returned to that client, but the destination server sets EXCHGID4_FLAG_CONFIRMED_R when replying to the client. This is because the lease was confirmed on the source server (before it was copied). Normally, when CONFIRMED_R is set, a client purges the lease and creates a new one. However, that throws away the entire benefit of Transparent State Migration. Therefore, the client must not purge that lease when it is possible that Transparent State Migration has occurred. Reported-by: Xuan Qi Signed-off-by: Chuck Lever Tested-by: Xuan Qi Signed-off-by: Anna Schumaker --- fs/nfs/nfs4client.c | 5 +++++ fs/nfs/nfs4state.c | 16 +++++++++++----- include/linux/nfs_fs_sb.h | 2 ++ 3 files changed, 18 insertions(+), 5 deletions(-) diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 66776f022111..50566acb5469 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -414,6 +414,7 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp, if (clp != old) clp->cl_preserve_clid = true; nfs_put_client(clp); + clear_bit(NFS_CS_TSM_POSSIBLE, &clp->cl_flags); return old; error: @@ -852,6 +853,8 @@ static int nfs4_set_client(struct nfs_server *server, set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); if (server->options & NFS_OPTION_MIGRATION) set_bit(NFS_CS_MIGRATION, &cl_init.init_flags); + if (test_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status)) + set_bit(NFS_CS_TSM_POSSIBLE, &cl_init.init_flags); /* Allocate or find a client reference we can use */ clp = nfs_get_client(&cl_init); @@ -1212,9 +1215,11 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname, return -EAFNOSUPPORT; nfs_server_remove_lists(server); + set_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status); error = nfs4_set_client(server, hostname, sap, salen, buf, clp->cl_proto, clnt->cl_timeout, clp->cl_minorversion, net); + clear_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status); nfs_put_client(clp); if (error != 0) { nfs_server_insert_lists(server); diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index b34de036501b..83f8e60bb1e3 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -352,11 +352,17 @@ int nfs41_discover_server_trunking(struct nfs_client *clp, if (clp != *result) return 0; - /* Purge state if the client id was established in a prior instance */ - if (clp->cl_exchange_flags & EXCHGID4_FLAG_CONFIRMED_R) - set_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state); - else - set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); + /* + * Purge state if the client id was established in a prior + * instance and the client id could not have arrived on the + * server via Transparent State Migration. + */ + if (clp->cl_exchange_flags & EXCHGID4_FLAG_CONFIRMED_R) { + if (!test_bit(NFS_CS_TSM_POSSIBLE, &clp->cl_flags)) + set_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state); + else + set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); + } nfs4_schedule_state_manager(clp); status = nfs_wait_client_init_complete(clp); if (status < 0) diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index e418a1096662..74c44665e6d3 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -42,6 +42,7 @@ struct nfs_client { #define NFS_CS_MIGRATION 2 /* - transparent state migr */ #define NFS_CS_INFINITE_SLOTS 3 /* - don't limit TCP slots */ #define NFS_CS_NO_RETRANS_TIMEOUT 4 /* - Disable retransmit timeouts */ +#define NFS_CS_TSM_POSSIBLE 5 /* - Maybe state migration */ struct sockaddr_storage cl_addr; /* server identifier */ size_t cl_addrlen; char * cl_hostname; /* hostname of server */ @@ -210,6 +211,7 @@ struct nfs_server { unsigned long mig_status; #define NFS_MIG_IN_TRANSITION (1) #define NFS_MIG_FAILED (2) +#define NFS_MIG_TSM_POSSIBLE (3) void (*destroy)(struct nfs_server *); -- cgit v1.2.3-59-g8ed1b From 838edb94977b96f191800d7ce39b2505419aac4a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 8 Jun 2017 11:52:52 -0400 Subject: NFSv4.1: Use seqid returned by EXCHANGE_ID after state migration Transparent State Migration copies a client's lease state from the server where a filesystem used to reside to the server where it now resides. When an NFSv4.1 client first contacts that destination server, it uses EXCHANGE_ID to detect trunking relationships. The lease that was copied there is returned to that client, but the destination server sets EXCHGID4_FLAG_CONFIRMED_R when replying to the client. This is because the lease was confirmed on the source server (before it was copied). When CONFIRMED_R is set, the client throws away the sequence ID returned by the server. During a Transparent State Migration, however there's no other way for the client to know what sequence ID to use with a lease that's been migrated. Therefore, the client must save and use the contrived slot sequence value returned by the destination server even when CONFIRMED_R is set. Note that some servers always return a seqid of 1 after a migration. Reported-by: Xuan Qi Signed-off-by: Chuck Lever Tested-by: Xuan Qi Signed-off-by: Anna Schumaker --- fs/nfs/nfs4proc.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index e678fa8f6979..01dcd4c8dc4f 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7378,12 +7378,11 @@ static void nfs4_exchange_id_done(struct rpc_task *task, void *data) if (status == 0) { clp->cl_clientid = cdata->res.clientid; clp->cl_exchange_flags = cdata->res.flags; + clp->cl_seqid = cdata->res.seqid; /* Client ID is not confirmed */ - if (!(cdata->res.flags & EXCHGID4_FLAG_CONFIRMED_R)) { + if (!(cdata->res.flags & EXCHGID4_FLAG_CONFIRMED_R)) clear_bit(NFS4_SESSION_ESTABLISHED, - &clp->cl_session->session_state); - clp->cl_seqid = cdata->res.seqid; - } + &clp->cl_session->session_state); kfree(clp->cl_serverowner); clp->cl_serverowner = cdata->res.server_owner; -- cgit v1.2.3-59-g8ed1b From 173b8f49b3af3d5102168793436dc17b94476b74 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 8 Jun 2017 11:53:00 -0400 Subject: xprtrdma: Demote "connect" log messages Some have complained about the log messages generated when xprtrdma opens or closes a connection to a server. When an NFS mount is mostly idle these can appear every few minutes as the client idles out the connection and reconnects. Connection and disconnection is a normal part of operation, and not exceptional, so change these to dprintk's for now. At some point all of these will be converted to tracepoints, but that's for another day. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/verbs.c | 44 ++++++++------------------------------------ 1 file changed, 8 insertions(+), 36 deletions(-) diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index a215a8759dc2..e4171f2abe37 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -243,8 +243,6 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event) #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) struct sockaddr *sap = (struct sockaddr *)&ep->rep_remote_addr; #endif - struct ib_qp_attr *attr = &ia->ri_qp_attr; - struct ib_qp_init_attr *iattr = &ia->ri_qp_init_attr; int connstate = 0; switch (event->event) { @@ -267,7 +265,8 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event) break; case RDMA_CM_EVENT_DEVICE_REMOVAL: #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) - pr_info("rpcrdma: removing device for %pIS:%u\n", + pr_info("rpcrdma: removing device %s for %pIS:%u\n", + ia->ri_device->name, sap, rpc_get_port(sap)); #endif set_bit(RPCRDMA_IAF_REMOVING, &ia->ri_flags); @@ -282,13 +281,6 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event) return 1; case RDMA_CM_EVENT_ESTABLISHED: connstate = 1; - ib_query_qp(ia->ri_id->qp, attr, - IB_QP_MAX_QP_RD_ATOMIC | IB_QP_MAX_DEST_RD_ATOMIC, - iattr); - dprintk("RPC: %s: %d responder resources" - " (%d initiator)\n", - __func__, attr->max_dest_rd_atomic, - attr->max_rd_atomic); rpcrdma_update_connect_private(xprt, &event->param.conn); goto connected; case RDMA_CM_EVENT_CONNECT_ERROR: @@ -298,11 +290,9 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event) connstate = -ENETDOWN; goto connected; case RDMA_CM_EVENT_REJECTED: -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) - pr_info("rpcrdma: connection to %pIS:%u on %s rejected: %s\n", - sap, rpc_get_port(sap), ia->ri_device->name, + dprintk("rpcrdma: connection to %pIS:%u rejected: %s\n", + sap, rpc_get_port(sap), rdma_reject_msg(id, event->status)); -#endif connstate = -ECONNREFUSED; if (event->status == IB_CM_REJ_STALE_CONN) connstate = -EAGAIN; @@ -310,37 +300,19 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event) case RDMA_CM_EVENT_DISCONNECTED: connstate = -ECONNABORTED; connected: - dprintk("RPC: %s: %sconnected\n", - __func__, connstate > 0 ? "" : "dis"); atomic_set(&xprt->rx_buf.rb_credits, 1); ep->rep_connected = connstate; rpcrdma_conn_func(ep); wake_up_all(&ep->rep_connect_wait); /*FALLTHROUGH*/ default: - dprintk("RPC: %s: %pIS:%u (ep 0x%p): %s\n", - __func__, sap, rpc_get_port(sap), ep, - rdma_event_msg(event->event)); + dprintk("RPC: %s: %pIS:%u on %s/%s (ep 0x%p): %s\n", + __func__, sap, rpc_get_port(sap), + ia->ri_device->name, ia->ri_ops->ro_displayname, + ep, rdma_event_msg(event->event)); break; } -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) - if (connstate == 1) { - int ird = attr->max_dest_rd_atomic; - int tird = ep->rep_remote_cma.responder_resources; - - pr_info("rpcrdma: connection to %pIS:%u on %s, memreg '%s', %d credits, %d responders%s\n", - sap, rpc_get_port(sap), - ia->ri_device->name, - ia->ri_ops->ro_displayname, - xprt->rx_buf.rb_max_requests, - ird, ird < 4 && ird < tird / 2 ? " (low!)" : ""); - } else if (connstate < 0) { - pr_info("rpcrdma: connection to %pIS:%u closed (%d)\n", - sap, rpc_get_port(sap), connstate); - } -#endif - return 0; } -- cgit v1.2.3-59-g8ed1b From e2f6ef09156284e35f780be47559809753d4b499 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 8 Jun 2017 11:53:08 -0400 Subject: xprtrdma: FMR does not need list_del_init() Clean up. Commit 38f1932e60ba ("xprtrdma: Remove FMRs from the unmap list after unmapping") utilized list_del_init() to try to prevent some list corruption. The corruption was actually caused by the reply handler racing with a signal. Now that MR invalidation is properly serialized, list_del_init() can safely be replaced. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/fmr_ops.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index 2f4eacdde3f2..d3f84bb1d443 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -91,7 +91,7 @@ __fmr_unmap(struct rpcrdma_mw *mw) list_add(&mw->fmr.fm_mr->list, &l); rc = ib_unmap_fmr(&l); - list_del_init(&mw->fmr.fm_mr->list); + list_del(&mw->fmr.fm_mr->list); return rc; } @@ -261,7 +261,7 @@ out_maperr: static void fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct list_head *mws) { - struct rpcrdma_mw *mw, *tmp; + struct rpcrdma_mw *mw; LIST_HEAD(unmap_list); int rc; @@ -283,9 +283,11 @@ fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct list_head *mws) /* ORDER: Now DMA unmap all of the req's MRs, and return * them to the free MW list. */ - list_for_each_entry_safe(mw, tmp, mws, mw_list) { - list_del_init(&mw->mw_list); - list_del_init(&mw->fmr.fm_mr->list); + while (!list_empty(mws)) { + mw = rpcrdma_pop_mw(mws); + dprintk("RPC: %s: DMA unmapping fmr %p\n", + __func__, &mw->fmr); + list_del(&mw->fmr.fm_mr->list); ib_dma_unmap_sg(r_xprt->rx_ia.ri_device, mw->mw_sg, mw->mw_nents, mw->mw_dir); rpcrdma_put_mw(r_xprt, mw); @@ -296,9 +298,9 @@ fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct list_head *mws) out_reset: pr_err("rpcrdma: ib_unmap_fmr failed (%i)\n", rc); - list_for_each_entry_safe(mw, tmp, mws, mw_list) { - list_del_init(&mw->mw_list); - list_del_init(&mw->fmr.fm_mr->list); + while (!list_empty(mws)) { + mw = rpcrdma_pop_mw(mws); + list_del(&mw->fmr.fm_mr->list); fmr_op_recover_mr(mw); } } -- cgit v1.2.3-59-g8ed1b From d933cc32019063fc4beb8b20528ca724bd1b7a52 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 8 Jun 2017 11:53:16 -0400 Subject: xprtrdma: Replace PAGE_MASK with offset_in_page() Clean up. Reported by: Geliang Tang Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/rpc_rdma.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index b6584ae8e251..ca4d6e4528f3 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -141,7 +141,7 @@ static bool rpcrdma_args_inline(struct rpcrdma_xprt *r_xprt, if (xdr->page_len) { remaining = xdr->page_len; - offset = xdr->page_base & ~PAGE_MASK; + offset = offset_in_page(xdr->page_base); count = 0; while (remaining) { remaining -= min_t(unsigned int, @@ -222,7 +222,7 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf, len = xdrbuf->page_len; ppages = xdrbuf->pages + (xdrbuf->page_base >> PAGE_SHIFT); - page_base = xdrbuf->page_base & ~PAGE_MASK; + page_base = offset_in_page(xdrbuf->page_base); p = 0; while (len && n < RPCRDMA_MAX_SEGS) { if (!ppages[p]) { @@ -540,7 +540,7 @@ rpcrdma_prepare_msg_sges(struct rpcrdma_ia *ia, struct rpcrdma_req *req, goto out; page = virt_to_page(xdr->tail[0].iov_base); - page_base = (unsigned long)xdr->tail[0].iov_base & ~PAGE_MASK; + page_base = offset_in_page(xdr->tail[0].iov_base); /* If the content in the page list is an odd length, * xdr_write_pages() has added a pad at the beginning @@ -557,7 +557,7 @@ rpcrdma_prepare_msg_sges(struct rpcrdma_ia *ia, struct rpcrdma_req *req, */ if (xdr->page_len) { ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT); - page_base = xdr->page_base & ~PAGE_MASK; + page_base = offset_in_page(xdr->page_base); remaining = xdr->page_len; while (remaining) { sge_no++; @@ -587,7 +587,7 @@ rpcrdma_prepare_msg_sges(struct rpcrdma_ia *ia, struct rpcrdma_req *req, */ if (xdr->tail[0].iov_len) { page = virt_to_page(xdr->tail[0].iov_base); - page_base = (unsigned long)xdr->tail[0].iov_base & ~PAGE_MASK; + page_base = offset_in_page(xdr->tail[0].iov_base); len = xdr->tail[0].iov_len; map_tail: @@ -878,9 +878,9 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) srcp += curlen; copy_len -= curlen; - page_base = rqst->rq_rcv_buf.page_base; - ppages = rqst->rq_rcv_buf.pages + (page_base >> PAGE_SHIFT); - page_base &= ~PAGE_MASK; + ppages = rqst->rq_rcv_buf.pages + + (rqst->rq_rcv_buf.page_base >> PAGE_SHIFT); + page_base = offset_in_page(rqst->rq_rcv_buf.page_base); fixup_copy_count = 0; if (copy_len && rqst->rq_rcv_buf.page_len) { int pagelist_len; -- cgit v1.2.3-59-g8ed1b From 6afafa7799cf6fa3c0efb6887704506d21965ad6 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 8 Jun 2017 11:53:24 -0400 Subject: xprtrdma: Fix documenting comments in frwr_ops.c Clean up. FASTREG and LOCAL_INV WRs are typically not signaled. localinv_wake is used for the last LOCAL_INV WR in a chain, which is always signaled. The documenting comments should reflect that. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/frwr_ops.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 8f63d38e45a2..6aea36a38bfd 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -277,7 +277,7 @@ __frwr_sendcompletion_flush(struct ib_wc *wc, const char *wr) } /** - * frwr_wc_fastreg - Invoked by RDMA provider for each polled FastReg WC + * frwr_wc_fastreg - Invoked by RDMA provider for a flushed FastReg WC * @cq: completion queue (ignored) * @wc: completed WR * @@ -298,7 +298,7 @@ frwr_wc_fastreg(struct ib_cq *cq, struct ib_wc *wc) } /** - * frwr_wc_localinv - Invoked by RDMA provider for each polled LocalInv WC + * frwr_wc_localinv - Invoked by RDMA provider for a flushed LocalInv WC * @cq: completion queue (ignored) * @wc: completed WR * @@ -319,7 +319,7 @@ frwr_wc_localinv(struct ib_cq *cq, struct ib_wc *wc) } /** - * frwr_wc_localinv - Invoked by RDMA provider for each polled LocalInv WC + * frwr_wc_localinv_wake - Invoked by RDMA provider for a signaled LocalInv WC * @cq: completion queue (ignored) * @wc: completed WR * -- cgit v1.2.3-59-g8ed1b From 1ee48bdd22440c0b45f215fc41e16032383c1c81 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Thu, 6 Jul 2017 09:43:02 -0400 Subject: NFSv4.2 fix size storage for nfs42_proc_copy Return size of COPY is u64 but it was assigned to an "int" status. Signed-off-by: Olga Kornievskaia Signed-off-by: Anna Schumaker --- fs/nfs/nfs42proc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 319a47db218d..6c2db51e67a7 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -146,7 +146,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, loff_t pos_src = args->src_pos; loff_t pos_dst = args->dst_pos; size_t count = args->count; - int status; + ssize_t status; status = nfs4_set_rw_stateid(&args->src_stateid, src_lock->open_context, src_lock, FMODE_READ); -- cgit v1.2.3-59-g8ed1b From 15a8b93fd5690de017ce665382ea45e5d61811a4 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Sat, 10 Jun 2017 04:59:07 +0200 Subject: sunrpc: use constant time memory comparison for mac Otherwise, we enable a MAC forgery via timing attack. Signed-off-by: Jason A. Donenfeld Cc: "J. Bruce Fields" Cc: Jeff Layton Cc: Trond Myklebust Cc: Anna Schumaker Cc: linux-nfs@vger.kernel.org Cc: stable@vger.kernel.org Signed-off-by: Anna Schumaker --- net/sunrpc/auth_gss/gss_krb5_crypto.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index fb39284ec174..12649c9fedab 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -34,6 +34,7 @@ * WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR A PARTICULAR PURPOSE. */ +#include #include #include #include @@ -927,7 +928,7 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, if (ret) goto out_err; - if (memcmp(pkt_hmac, our_hmac, kctx->gk5e->cksumlength) != 0) { + if (crypto_memneq(pkt_hmac, our_hmac, kctx->gk5e->cksumlength) != 0) { ret = GSS_S_BAD_SIG; goto out_err; } -- cgit v1.2.3-59-g8ed1b From 774d9513a3f29048cce3ed5df3b0a0da9897678c Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Thu, 29 Jun 2017 06:34:50 -0700 Subject: nfs: replace d_add with d_splice_alias in atomic_open It's a trival change but follows knfsd export document that asks for d_splice_alias during lookup. Signed-off-by: Peng Tao Signed-off-by: Anna Schumaker --- fs/nfs/dir.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 90bc4025ca3c..1255891e5695 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1518,7 +1518,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, d_drop(dentry); switch (err) { case -ENOENT: - d_add(dentry, NULL); + d_splice_alias(NULL, dentry); nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); break; case -EISDIR: -- cgit v1.2.3-59-g8ed1b From f174ff7a0ab6a097455a94abfc99517940041c07 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Thu, 29 Jun 2017 06:34:51 -0700 Subject: nfs: add a nfs_ilookup helper This helper will allow to find an existing NFS inode by the file handle and fattr. Signed-off-by: Peng Tao [hch: split from a larger patch] Signed-off-by: Christoph Hellwig Signed-off-by: Anna Schumaker --- fs/nfs/inode.c | 22 ++++++++++++++++++++++ include/linux/nfs_fs.h | 1 + 2 files changed, 23 insertions(+) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 7e7a894601b9..109279d6d91b 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -386,6 +386,28 @@ void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, #endif EXPORT_SYMBOL_GPL(nfs_setsecurity); +/* Search for inode identified by fh, fileid and i_mode in inode cache. */ +struct inode * +nfs_ilookup(struct super_block *sb, struct nfs_fattr *fattr, struct nfs_fh *fh) +{ + struct nfs_find_desc desc = { + .fh = fh, + .fattr = fattr, + }; + struct inode *inode; + unsigned long hash; + + if (!(fattr->valid & NFS_ATTR_FATTR_FILEID) || + !(fattr->valid & NFS_ATTR_FATTR_TYPE)) + return NULL; + + hash = nfs_fattr_to_ino_t(fattr); + inode = ilookup5(sb, hash, nfs_find_actor, &desc); + + dprintk("%s: returning %p\n", __func__, inode); + return inode; +} + /* * This is our front-end to iget that looks up inodes by file handle * instead of inode number. diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index bb0eb2c9acca..e52cc55ac300 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -332,6 +332,7 @@ extern void nfs_zap_caches(struct inode *); extern void nfs_invalidate_atime(struct inode *); extern struct inode *nfs_fhget(struct super_block *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *); +struct inode *nfs_ilookup(struct super_block *sb, struct nfs_fattr *, struct nfs_fh *); extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *); extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr); -- cgit v1.2.3-59-g8ed1b From 5b5faaf6df73412af0278997db36dbcb51011d9d Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 29 Jun 2017 06:34:52 -0700 Subject: nfs4: add NFSv4 LOOKUPP handlers This will be needed in order to implement the get_parent export op for nfsd. Signed-off-by: Jeff Layton Signed-off-by: Anna Schumaker --- fs/nfs/nfs4proc.c | 49 ++++++++++++++++++++++++++++++++ fs/nfs/nfs4trace.h | 29 +++++++++++++++++++ fs/nfs/nfs4xdr.c | 75 +++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/nfs4.h | 1 + include/linux/nfs_xdr.h | 17 ++++++++++- 5 files changed, 170 insertions(+), 1 deletion(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 01dcd4c8dc4f..e1a26c653e78 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3805,6 +3805,54 @@ nfs4_proc_lookup_mountpoint(struct inode *dir, const struct qstr *name, return (client == NFS_CLIENT(dir)) ? rpc_clone_client(client) : client; } +static int _nfs4_proc_lookupp(struct inode *inode, + struct nfs_fh *fhandle, struct nfs_fattr *fattr, + struct nfs4_label *label) +{ + struct rpc_clnt *clnt = NFS_CLIENT(inode); + struct nfs_server *server = NFS_SERVER(inode); + int status; + struct nfs4_lookupp_arg args = { + .bitmask = server->attr_bitmask, + .fh = NFS_FH(inode), + }; + struct nfs4_lookupp_res res = { + .server = server, + .fattr = fattr, + .label = label, + .fh = fhandle, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LOOKUPP], + .rpc_argp = &args, + .rpc_resp = &res, + }; + + args.bitmask = nfs4_bitmask(server, label); + + nfs_fattr_init(fattr); + + dprintk("NFS call lookupp ino=0x%lx\n", inode->i_ino); + status = nfs4_call_sync(clnt, server, &msg, &args.seq_args, + &res.seq_res, 0); + dprintk("NFS reply lookupp: %d\n", status); + return status; +} + +static int nfs4_proc_lookupp(struct inode *inode, struct nfs_fh *fhandle, + struct nfs_fattr *fattr, struct nfs4_label *label) +{ + struct nfs4_exception exception = { }; + int err; + do { + err = _nfs4_proc_lookupp(inode, fhandle, fattr, label); + trace_nfs4_lookupp(inode, err); + err = nfs4_handle_exception(NFS_SERVER(inode), err, + &exception); + } while (exception.retry); + return err; +} + static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry) { struct nfs_server *server = NFS_SERVER(inode); @@ -9314,6 +9362,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .getattr = nfs4_proc_getattr, .setattr = nfs4_proc_setattr, .lookup = nfs4_proc_lookup, + .lookupp = nfs4_proc_lookupp, .access = nfs4_proc_access, .readlink = nfs4_proc_readlink, .create = nfs4_proc_create, diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index 845d0eadefc9..be1da19c65d6 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -891,6 +891,35 @@ DEFINE_NFS4_LOOKUP_EVENT(nfs4_remove); DEFINE_NFS4_LOOKUP_EVENT(nfs4_get_fs_locations); DEFINE_NFS4_LOOKUP_EVENT(nfs4_secinfo); +TRACE_EVENT(nfs4_lookupp, + TP_PROTO( + const struct inode *inode, + int error + ), + + TP_ARGS(inode, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u64, ino) + __field(int, error) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = NFS_FILEID(inode); + __entry->error = error; + ), + + TP_printk( + "error=%d (%s) inode=%02x:%02x:%llu", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->ino + ) +); + TRACE_EVENT(nfs4_rename, TP_PROTO( const struct inode *olddir, diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 495d493d3a35..fa3eb361d4f8 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -159,6 +159,8 @@ static int nfs4_stat_to_errno(int); (op_decode_hdr_maxsz) #define encode_lookup_maxsz (op_encode_hdr_maxsz + nfs4_name_maxsz) #define decode_lookup_maxsz (op_decode_hdr_maxsz) +#define encode_lookupp_maxsz (op_encode_hdr_maxsz) +#define decode_lookupp_maxsz (op_decode_hdr_maxsz) #define encode_share_access_maxsz \ (2) #define encode_createmode_maxsz (1 + encode_attrs_maxsz + encode_verifier_maxsz) @@ -618,6 +620,18 @@ static int nfs4_stat_to_errno(int); decode_lookup_maxsz + \ decode_getattr_maxsz + \ decode_getfh_maxsz) +#define NFS4_enc_lookupp_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_lookupp_maxsz + \ + encode_getattr_maxsz + \ + encode_getfh_maxsz) +#define NFS4_dec_lookupp_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_lookupp_maxsz + \ + decode_getattr_maxsz + \ + decode_getfh_maxsz) #define NFS4_enc_lookup_root_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putrootfh_maxsz + \ @@ -1368,6 +1382,11 @@ static void encode_lookup(struct xdr_stream *xdr, const struct qstr *name, struc encode_string(xdr, name->len, name->name); } +static void encode_lookupp(struct xdr_stream *xdr, struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_LOOKUPP, decode_lookupp_maxsz, hdr); +} + static void encode_share_access(struct xdr_stream *xdr, u32 share_access) { __be32 *p; @@ -2122,6 +2141,26 @@ static void nfs4_xdr_enc_lookup(struct rpc_rqst *req, struct xdr_stream *xdr, encode_nops(&hdr); } +/* + * Encode LOOKUPP request + */ +static void nfs4_xdr_enc_lookupp(struct rpc_rqst *req, struct xdr_stream *xdr, + const void *data) +{ + const struct nfs4_lookupp_arg *args = data; + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_lookupp(xdr, &hdr); + encode_getfh(xdr, &hdr); + encode_getfattr(xdr, args->bitmask, &hdr); + encode_nops(&hdr); +} + /* * Encode LOOKUP_ROOT request */ @@ -5058,6 +5097,11 @@ static int decode_lookup(struct xdr_stream *xdr) return decode_op_hdr(xdr, OP_LOOKUP); } +static int decode_lookupp(struct xdr_stream *xdr) +{ + return decode_op_hdr(xdr, OP_LOOKUPP); +} + /* This is too sick! */ static int decode_space_limit(struct xdr_stream *xdr, unsigned long *pagemod_limit) @@ -6237,6 +6281,36 @@ out: return status; } +/* + * Decode LOOKUPP response + */ +static int nfs4_xdr_dec_lookupp(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + void *data) +{ + struct nfs4_lookupp_res *res = data; + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_lookupp(xdr); + if (status) + goto out; + status = decode_getfh(xdr, res->fh); + if (status) + goto out; + status = decode_getfattr_label(xdr, res->fattr, res->label, res->server); +out: + return status; +} + /* * Decode LOOKUP_ROOT response */ @@ -7614,6 +7688,7 @@ const struct rpc_procinfo nfs4_procedures[] = { PROC(ACCESS, enc_access, dec_access), PROC(GETATTR, enc_getattr, dec_getattr), PROC(LOOKUP, enc_lookup, dec_lookup), + PROC(LOOKUPP, enc_lookupp, dec_lookupp), PROC(LOOKUP_ROOT, enc_lookup_root, dec_lookup_root), PROC(REMOVE, enc_remove, dec_remove), PROC(RENAME, enc_rename, dec_rename), diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 1b1ca04820a3..47239c336688 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -479,6 +479,7 @@ enum { NFSPROC4_CLNT_ACCESS, NFSPROC4_CLNT_GETATTR, NFSPROC4_CLNT_LOOKUP, + NFSPROC4_CLNT_LOOKUPP, NFSPROC4_CLNT_LOOKUP_ROOT, NFSPROC4_CLNT_REMOVE, NFSPROC4_CLNT_RENAME, diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 89093341f076..ca3bcc4ed4e5 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1012,7 +1012,6 @@ struct nfs4_link_res { struct nfs_fattr * dir_attr; }; - struct nfs4_lookup_arg { struct nfs4_sequence_args seq_args; const struct nfs_fh * dir_fh; @@ -1028,6 +1027,20 @@ struct nfs4_lookup_res { struct nfs4_label *label; }; +struct nfs4_lookupp_arg { + struct nfs4_sequence_args seq_args; + const struct nfs_fh *fh; + const u32 *bitmask; +}; + +struct nfs4_lookupp_res { + struct nfs4_sequence_res seq_res; + const struct nfs_server *server; + struct nfs_fattr *fattr; + struct nfs_fh *fh; + struct nfs4_label *label; +}; + struct nfs4_lookup_root_arg { struct nfs4_sequence_args seq_args; const u32 * bitmask; @@ -1569,6 +1582,8 @@ struct nfs_rpc_ops { int (*lookup) (struct inode *, const struct qstr *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *); + int (*lookupp) (struct inode *, struct nfs_fh *, + struct nfs_fattr *, struct nfs4_label *); int (*access) (struct inode *, struct nfs_access_entry *); int (*readlink)(struct inode *, struct page *, unsigned int, unsigned int); -- cgit v1.2.3-59-g8ed1b From 5d89fb33223e0be32e4100623b915048b02beeec Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 13 Jul 2017 13:36:40 -0700 Subject: net: set fib rule refcount after malloc The configure callback of fib_rules_ops can change the refcnt of a fib rule. For instance, mlxsw takes a refcnt when adding the processing of the rule to a work queue. Thus the rule refcnt can not be reset to to 1 afterwards. Move the refcnt setting to after the allocation. Fixes: 5361e209dd30 ("net: avoid one splat in fib_nl_delrule()") Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/core/fib_rules.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index a0093e1b0235..fdcb1bcd2afa 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -400,6 +400,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, err = -ENOMEM; goto errout; } + refcount_set(&rule->refcnt, 1); rule->fr_net = net; rule->pref = tb[FRA_PRIORITY] ? nla_get_u32(tb[FRA_PRIORITY]) @@ -517,8 +518,6 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, last = r; } - refcount_set(&rule->refcnt, 1); - if (last) list_add_rcu(&rule->list, &last->list); else -- cgit v1.2.3-59-g8ed1b From 20fa19027286983ab2734b5910c4a687436e0c31 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Thu, 29 Jun 2017 06:34:53 -0700 Subject: nfs: add export operations This support for opening files on NFS by file handle, both through the open_by_handle syscall, and for re-exporting NFS (for example using a different version). The support is very basic for now, as each open by handle will have to do an NFSv4 open operation on the wire. In the future this will hopefully be mitigated by an open file cache, as well as various optimizations in NFS for this specific case. Signed-off-by: Peng Tao [hch: incorporated various changes, resplit the patches, new changelog] Signed-off-by: Christoph Hellwig Signed-off-by: Anna Schumaker --- fs/nfs/Makefile | 2 +- fs/nfs/export.c | 177 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ fs/nfs/internal.h | 2 + fs/nfs/super.c | 2 + 4 files changed, 182 insertions(+), 1 deletion(-) create mode 100644 fs/nfs/export.c diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index 98f4e5728a67..1fb118902d57 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -7,7 +7,7 @@ obj-$(CONFIG_NFS_FS) += nfs.o CFLAGS_nfstrace.o += -I$(src) nfs-y := client.o dir.o file.o getroot.o inode.o super.o \ io.o direct.o pagelist.o read.o symlink.o unlink.o \ - write.o namespace.o mount_clnt.o nfstrace.o + write.o namespace.o mount_clnt.o nfstrace.o export.o nfs-$(CONFIG_ROOT_NFS) += nfsroot.o nfs-$(CONFIG_SYSCTL) += sysctl.o nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o diff --git a/fs/nfs/export.c b/fs/nfs/export.c new file mode 100644 index 000000000000..249cb96cc5b5 --- /dev/null +++ b/fs/nfs/export.c @@ -0,0 +1,177 @@ +/* + * Copyright (c) 2015, Primary Data, Inc. All rights reserved. + * + * Tao Peng + */ +#include +#include +#include +#include + +#include "internal.h" +#include "nfstrace.h" + +#define NFSDBG_FACILITY NFSDBG_VFS + +enum { + FILEID_HIGH_OFF = 0, /* inode fileid high */ + FILEID_LOW_OFF, /* inode fileid low */ + FILE_I_TYPE_OFF, /* inode type */ + EMBED_FH_OFF /* embeded server fh */ +}; + + +static struct nfs_fh *nfs_exp_embedfh(__u32 *p) +{ + return (struct nfs_fh *)(p + EMBED_FH_OFF); +} + +/* + * Let's break subtree checking for now... otherwise we'll have to embed parent fh + * but there might not be enough space. + */ +static int +nfs_encode_fh(struct inode *inode, __u32 *p, int *max_len, struct inode *parent) +{ + struct nfs_fh *server_fh = NFS_FH(inode); + struct nfs_fh *clnt_fh = nfs_exp_embedfh(p); + size_t fh_size = offsetof(struct nfs_fh, data) + server_fh->size; + int len = EMBED_FH_OFF + XDR_QUADLEN(fh_size); + + dprintk("%s: max fh len %d inode %p parent %p", + __func__, *max_len, inode, parent); + + if (*max_len < len || IS_AUTOMOUNT(inode)) { + dprintk("%s: fh len %d too small, required %d\n", + __func__, *max_len, len); + *max_len = len; + return FILEID_INVALID; + } + if (IS_AUTOMOUNT(inode)) { + *max_len = FILEID_INVALID; + goto out; + } + + p[FILEID_HIGH_OFF] = NFS_FILEID(inode) >> 32; + p[FILEID_LOW_OFF] = NFS_FILEID(inode); + p[FILE_I_TYPE_OFF] = inode->i_mode & S_IFMT; + p[len - 1] = 0; /* Padding */ + nfs_copy_fh(clnt_fh, server_fh); + *max_len = len; +out: + dprintk("%s: result fh fileid %llu mode %u size %d\n", + __func__, NFS_FILEID(inode), inode->i_mode, *max_len); + return *max_len; +} + +static struct dentry * +nfs_fh_to_dentry(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type) +{ + struct nfs4_label *label = NULL; + struct nfs_fattr *fattr = NULL; + struct nfs_fh *server_fh = nfs_exp_embedfh(fid->raw); + size_t fh_size = offsetof(struct nfs_fh, data) + server_fh->size; + const struct nfs_rpc_ops *rpc_ops; + struct dentry *dentry; + struct inode *inode; + int len = EMBED_FH_OFF + XDR_QUADLEN(fh_size); + u32 *p = fid->raw; + int ret; + + /* NULL translates to ESTALE */ + if (fh_len < len || fh_type != len) + return NULL; + + fattr = nfs_alloc_fattr(); + if (fattr == NULL) { + dentry = ERR_PTR(-ENOMEM); + goto out; + } + + fattr->fileid = ((u64)p[FILEID_HIGH_OFF] << 32) + p[FILEID_LOW_OFF]; + fattr->mode = p[FILE_I_TYPE_OFF]; + fattr->valid |= NFS_ATTR_FATTR_FILEID | NFS_ATTR_FATTR_TYPE; + + dprintk("%s: fileid %llu mode %d\n", __func__, fattr->fileid, fattr->mode); + + inode = nfs_ilookup(sb, fattr, server_fh); + if (inode) + goto out_found; + + label = nfs4_label_alloc(NFS_SB(sb), GFP_KERNEL); + if (IS_ERR(label)) { + dentry = ERR_CAST(label); + goto out_free_fattr; + } + + rpc_ops = NFS_SB(sb)->nfs_client->rpc_ops; + ret = rpc_ops->getattr(NFS_SB(sb), server_fh, fattr, label); + if (ret) { + dprintk("%s: getattr failed %d\n", __func__, ret); + dentry = ERR_PTR(ret); + goto out_free_label; + } + + inode = nfs_fhget(sb, server_fh, fattr, label); + +out_found: + dentry = d_obtain_alias(inode); + +out_free_label: + nfs4_label_free(label); +out_free_fattr: + nfs_free_fattr(fattr); +out: + return dentry; +} + +static struct dentry * +nfs_get_parent(struct dentry *dentry) +{ + int ret; + struct inode *inode = d_inode(dentry), *pinode; + struct super_block *sb = inode->i_sb; + struct nfs_server *server = NFS_SB(sb); + struct nfs_fattr *fattr = NULL; + struct nfs4_label *label = NULL; + struct dentry *parent; + struct nfs_rpc_ops const *ops = server->nfs_client->rpc_ops; + struct nfs_fh fh; + + if (!ops->lookupp) + return ERR_PTR(-EACCES); + + fattr = nfs_alloc_fattr(); + if (fattr == NULL) { + parent = ERR_PTR(-ENOMEM); + goto out; + } + + label = nfs4_label_alloc(server, GFP_KERNEL); + if (IS_ERR(label)) { + parent = ERR_CAST(label); + goto out_free_fattr; + } + + ret = ops->lookupp(inode, &fh, fattr, label); + if (ret) { + parent = ERR_PTR(ret); + goto out_free_label; + } + + pinode = nfs_fhget(sb, &fh, fattr, label); + parent = d_obtain_alias(pinode); +out_free_label: + nfs4_label_free(label); +out_free_fattr: + nfs_free_fattr(fattr); +out: + return parent; +} + +const struct export_operations nfs_export_ops = { + .encode_fh = nfs_encode_fh, + .fh_to_dentry = nfs_fh_to_dentry, + .get_parent = nfs_get_parent, +}; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index c5054edb0157..2ebd57498986 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -10,6 +10,8 @@ #define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS) +extern const struct export_operations nfs_export_ops; + struct nfs_string; /* Maximum number of readahead requests diff --git a/fs/nfs/super.c b/fs/nfs/super.c index b4176393f049..b5271644b472 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2339,6 +2339,7 @@ void nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info) */ sb->s_flags |= MS_POSIXACL; sb->s_time_gran = 1; + sb->s_export_op = &nfs_export_ops; } nfs_initialise_sb(sb); @@ -2360,6 +2361,7 @@ static void nfs_clone_super(struct super_block *sb, sb->s_xattr = old_sb->s_xattr; sb->s_op = old_sb->s_op; sb->s_time_gran = 1; + sb->s_export_op = old_sb->s_export_op; if (server->nfs_client->rpc_ops->version != 2) { /* The VFS shouldn't apply the umask to mode bits. We will do -- cgit v1.2.3-59-g8ed1b From b4f937cffa66b3d56eb8f586e620d0b223a281a3 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 11 Jul 2017 17:53:48 -0400 Subject: NFS: Don't run wake_up_bit() when nobody is waiting... "perf lock" shows fairly heavy contention for the bit waitqueue locks when doing an I/O heavy workload. Use a bit to tell whether or not there has been contention for a lock so that we can optimise away the bit waitqueue options in those cases. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/pagelist.c | 17 ++++++++++++++++- include/linux/nfs_page.h | 2 ++ 2 files changed, 18 insertions(+), 1 deletion(-) diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 8a23e2b40b04..de9066a92c0d 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -155,9 +155,12 @@ nfs_page_group_lock(struct nfs_page *req, bool nonblock) if (!test_and_set_bit(PG_HEADLOCK, &head->wb_flags)) return 0; - if (!nonblock) + if (!nonblock) { + set_bit(PG_CONTENDED1, &head->wb_flags); + smp_mb__after_atomic(); return wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK, TASK_UNINTERRUPTIBLE); + } return -EAGAIN; } @@ -175,6 +178,10 @@ nfs_page_group_lock_wait(struct nfs_page *req) WARN_ON_ONCE(head != head->wb_head); + if (!test_bit(PG_HEADLOCK, &head->wb_flags)) + return; + set_bit(PG_CONTENDED1, &head->wb_flags); + smp_mb__after_atomic(); wait_on_bit(&head->wb_flags, PG_HEADLOCK, TASK_UNINTERRUPTIBLE); } @@ -193,6 +200,8 @@ nfs_page_group_unlock(struct nfs_page *req) smp_mb__before_atomic(); clear_bit(PG_HEADLOCK, &head->wb_flags); smp_mb__after_atomic(); + if (!test_bit(PG_CONTENDED1, &head->wb_flags)) + return; wake_up_bit(&head->wb_flags, PG_HEADLOCK); } @@ -383,6 +392,8 @@ void nfs_unlock_request(struct nfs_page *req) smp_mb__before_atomic(); clear_bit(PG_BUSY, &req->wb_flags); smp_mb__after_atomic(); + if (!test_bit(PG_CONTENDED2, &req->wb_flags)) + return; wake_up_bit(&req->wb_flags, PG_BUSY); } @@ -465,6 +476,10 @@ void nfs_release_request(struct nfs_page *req) int nfs_wait_on_request(struct nfs_page *req) { + if (!test_bit(PG_BUSY, &req->wb_flags)) + return 0; + set_bit(PG_CONTENDED2, &req->wb_flags); + smp_mb__after_atomic(); return wait_on_bit_io(&req->wb_flags, PG_BUSY, TASK_UNINTERRUPTIBLE); } diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index abbee2d15dce..d67b67ae6c8b 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -33,6 +33,8 @@ enum { PG_UPTODATE, /* page group sync bit in read path */ PG_WB_END, /* page group sync bit in write path */ PG_REMOVE, /* page group sync bit in write path */ + PG_CONTENDED1, /* Is someone waiting for a lock? */ + PG_CONTENDED2, /* Is someone waiting for a lock? */ }; struct nfs_inode; -- cgit v1.2.3-59-g8ed1b From cf69f8248cc89c0a0e82f8332f9e7f13ab014c98 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 13 Jul 2017 12:14:33 -0700 Subject: xfs: fixup xfs_attr_get_ilocked The comment mentioned the wrong lock. Also add an ASSERT to assert this locking precondition. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/libxfs/xfs_attr.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index ef8a1c75a467..de7b9bd30bec 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -114,12 +114,14 @@ xfs_inode_hasattr( * Overall external interface routines. *========================================================================*/ -/* Retrieve an extended attribute and its value. Must have iolock. */ +/* Retrieve an extended attribute and its value. Must have ilock. */ int xfs_attr_get_ilocked( struct xfs_inode *ip, struct xfs_da_args *args) { + ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); + if (!xfs_inode_hasattr(ip)) return -ENOATTR; else if (ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) -- cgit v1.2.3-59-g8ed1b From 5af7777e11f5a91dd90247035978bef6c95065e4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 13 Jul 2017 12:14:33 -0700 Subject: xfs: assert locking precondіtion in xfs_attr_list_int_ilocked MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_attr_list.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c index 545eca508d42..7740c8a5e736 100644 --- a/fs/xfs/xfs_attr_list.c +++ b/fs/xfs/xfs_attr_list.c @@ -463,6 +463,8 @@ xfs_attr_list_int_ilocked( { struct xfs_inode *dp = context->dp; + ASSERT(xfs_isilocked(dp, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); + /* * Decide on what work routines to call based on the inode size. */ -- cgit v1.2.3-59-g8ed1b From 29db2500f6a92d63834a40c5e9eebab34c78c53a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 13 Jul 2017 12:14:34 -0700 Subject: xfs: assert locking precondition in xfs_readlink_bmap_ilocked Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_symlink.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index 12cd9cf7de41..23a50d7aa46a 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -61,6 +61,8 @@ xfs_readlink_bmap_ilocked( int fsblocks = 0; int offset; + ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); + fsblocks = xfs_symlink_blocks(mp, pathlen); error = xfs_bmapi_read(ip, 0, fsblocks, mval, &nmaps, 0); if (error) -- cgit v1.2.3-59-g8ed1b From 0891f9971a3b00d243d5743cc78a628ad060adea Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 13 Jul 2017 12:14:34 -0700 Subject: Revert "xfs: grab dquots without taking the ilock" This reverts commit 50e0bdbe9f48f98bb02eac7030d682f4716884ae. The new XFS_QMOPT_NOLOCK isn't used at all, and conditional locking based on a flag is always the wrong thing to do - we should be having helpers that can be called without the lock instead. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/libxfs/xfs_quota_defs.h | 2 -- fs/xfs/xfs_dquot.c | 14 ++++---------- 2 files changed, 4 insertions(+), 12 deletions(-) diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h index 2834574cb6e7..d69c772271cb 100644 --- a/fs/xfs/libxfs/xfs_quota_defs.h +++ b/fs/xfs/libxfs/xfs_quota_defs.h @@ -136,8 +136,6 @@ typedef uint16_t xfs_qwarncnt_t; */ #define XFS_QMOPT_INHERIT 0x1000000 -#define XFS_QMOPT_NOLOCK 0x2000000 /* don't ilock during dqget */ - /* * flags to xfs_trans_mod_dquot. */ diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index f89f7b5241e6..fd2ef8c2c9a7 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -472,23 +472,18 @@ xfs_qm_dqtobp( struct xfs_mount *mp = dqp->q_mount; xfs_dqid_t id = be32_to_cpu(dqp->q_core.d_id); struct xfs_trans *tp = (tpp ? *tpp : NULL); - uint lock_mode = 0; + uint lock_mode; quotip = xfs_quota_inode(dqp->q_mount, dqp->dq_flags); dqp->q_fileoffset = (xfs_fileoff_t)id / mp->m_quotainfo->qi_dqperchunk; - ASSERT(!(flags & XFS_QMOPT_NOLOCK) || - xfs_isilocked(quotip, XFS_ILOCK_SHARED) || - xfs_isilocked(quotip, XFS_ILOCK_EXCL)); - if (!(flags & XFS_QMOPT_NOLOCK)) - lock_mode = xfs_ilock_data_map_shared(quotip); + lock_mode = xfs_ilock_data_map_shared(quotip); if (!xfs_this_quota_on(dqp->q_mount, dqp->dq_flags)) { /* * Return if this type of quotas is turned off while we * didn't have the quota inode lock. */ - if (lock_mode) - xfs_iunlock(quotip, lock_mode); + xfs_iunlock(quotip, lock_mode); return -ESRCH; } @@ -498,8 +493,7 @@ xfs_qm_dqtobp( error = xfs_bmapi_read(quotip, dqp->q_fileoffset, XFS_DQUOT_CLUSTER_SIZE_FSB, &map, &nmaps, 0); - if (lock_mode) - xfs_iunlock(quotip, lock_mode); + xfs_iunlock(quotip, lock_mode); if (error) return error; -- cgit v1.2.3-59-g8ed1b From d6ab17f261919d212ec0a9e33d01f46df0ec1fde Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 12 Jul 2017 10:26:47 -0700 Subject: vfs: in iomap seek_{hole,data}, return -ENXIO for negative offsets In the iomap implementations of SEEK_HOLE and SEEK_DATA, make sure we return -ENXIO for negative offsets. Inspired-by: Mateusz S Signed-off-by: Darrick J. Wong --- fs/iomap.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/iomap.c b/fs/iomap.c index 432eed8f091f..16f5c07451bf 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -610,8 +610,8 @@ iomap_seek_hole(struct inode *inode, loff_t offset, const struct iomap_ops *ops) loff_t length = size - offset; loff_t ret; - /* Nothing to be found beyond the end of the file. */ - if (offset >= size) + /* Nothing to be found before or beyond the end of the file. */ + if (offset < 0 || offset >= size) return -ENXIO; while (length > 0) { @@ -656,8 +656,8 @@ iomap_seek_data(struct inode *inode, loff_t offset, const struct iomap_ops *ops) loff_t length = size - offset; loff_t ret; - /* Nothing to be found beyond the end of the file. */ - if (offset >= size) + /* Nothing to be found before or beyond the end of the file. */ + if (offset < 0 || offset >= size) return -ENXIO; while (length > 0) { -- cgit v1.2.3-59-g8ed1b From 6e34e1f23d780978da65968327cbba6d7013a73f Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Thu, 13 Jul 2017 15:03:51 -0700 Subject: cpufreq: intel_pstate: Correct the busy calculation for KNL The busy percent calculated for the Knights Landing (KNL) platform is 1024 times smaller than the correct busy value. This causes performance to get stuck at the lowest ratio. The scaling algorithm used for KNL is performance-based, but it still looks at the CPU load to set the scaled busy factor to 0 when the load is less than 1 percent. In this case, since the computed load is 1024x smaller than it should be, the scaled busy factor will always be 0, irrespective of CPU business. This needs a fix similar to the turbostat one in commit b2b34dfe4d9a (tools/power turbostat: KNL workaround for %Busy and Avg_MHz). For this reason, add one more callback to processor-specific callbacks to specify an MPERF multiplier represented by a number of bit positions to shift the value of that register to the left to copmensate for its rate difference with respect to the TSC. This shift value is used during CPU busy calculations. Fixes: ffb810563c (intel_pstate: Avoid getting stuck in high P-states when idle) Reported-and-tested-by: Artem Bityutskiy Signed-off-by: Srinivas Pandruvada Cc: 4.6+ # 4.6+ [ rjw: Changelog ] Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 2386d7036e90..0ddc0d045831 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -225,6 +225,9 @@ struct global_params { * @vid: Stores VID limits for this CPU * @pid: Stores PID parameters for this CPU * @last_sample_time: Last Sample time + * @aperf_mperf_shift: Number of clock cycles after aperf, merf is incremented + * This shift is a multiplier to mperf delta to + * calculate CPU busy. * @prev_aperf: Last APERF value read from APERF MSR * @prev_mperf: Last MPERF value read from MPERF MSR * @prev_tsc: Last timestamp counter (TSC) value @@ -259,6 +262,7 @@ struct cpudata { u64 last_update; u64 last_sample_time; + u64 aperf_mperf_shift; u64 prev_aperf; u64 prev_mperf; u64 prev_tsc; @@ -321,6 +325,7 @@ struct pstate_funcs { int (*get_min)(void); int (*get_turbo)(void); int (*get_scaling)(void); + int (*get_aperf_mperf_shift)(void); u64 (*get_val)(struct cpudata*, int pstate); void (*get_vid)(struct cpudata *); void (*update_util)(struct update_util_data *data, u64 time, @@ -1490,6 +1495,11 @@ static u64 core_get_val(struct cpudata *cpudata, int pstate) return val; } +static int knl_get_aperf_mperf_shift(void) +{ + return 10; +} + static int knl_get_turbo_pstate(void) { u64 value; @@ -1547,6 +1557,9 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) cpu->pstate.max_freq = cpu->pstate.max_pstate * cpu->pstate.scaling; cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling; + if (pstate_funcs.get_aperf_mperf_shift) + cpu->aperf_mperf_shift = pstate_funcs.get_aperf_mperf_shift(); + if (pstate_funcs.get_vid) pstate_funcs.get_vid(cpu); @@ -1620,7 +1633,8 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu) int32_t busy_frac, boost; int target, avg_pstate; - busy_frac = div_fp(sample->mperf, sample->tsc); + busy_frac = div_fp(sample->mperf << cpu->aperf_mperf_shift, + sample->tsc); boost = cpu->iowait_boost; cpu->iowait_boost >>= 1; @@ -1679,7 +1693,8 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu) sample_ratio = div_fp(pid_params.sample_rate_ns, duration_ns); perf_scaled = mul_fp(perf_scaled, sample_ratio); } else { - sample_ratio = div_fp(100 * cpu->sample.mperf, cpu->sample.tsc); + sample_ratio = div_fp(100 * (cpu->sample.mperf << cpu->aperf_mperf_shift), + cpu->sample.tsc); if (sample_ratio < int_tofp(1)) perf_scaled = 0; } @@ -1811,6 +1826,7 @@ static const struct pstate_funcs knl_funcs = { .get_max_physical = core_get_max_pstate_physical, .get_min = core_get_min_pstate, .get_turbo = knl_get_turbo_pstate, + .get_aperf_mperf_shift = knl_get_aperf_mperf_shift, .get_scaling = core_get_scaling, .get_val = core_get_val, .update_util = intel_pstate_update_util_pid, @@ -2407,6 +2423,7 @@ static void __init copy_cpu_funcs(struct pstate_funcs *funcs) pstate_funcs.get_val = funcs->get_val; pstate_funcs.get_vid = funcs->get_vid; pstate_funcs.update_util = funcs->update_util; + pstate_funcs.get_aperf_mperf_shift = funcs->get_aperf_mperf_shift; intel_pstate_use_acpi_profile(); } -- cgit v1.2.3-59-g8ed1b From 5ccbdbf9870fe9efe78d77df23d5e7d8641c36f8 Mon Sep 17 00:00:00 2001 From: Jarkko Sakkinen Date: Thu, 13 Jul 2017 13:16:49 +0100 Subject: modsign: add markers to endif-statements in certs/Makefile It's a bit hard for eye to track certs/Makefile if you are not accustomed to it. This commit adds comments to key endif statements in order to help to keep the context while reading this file. Signed-off-by: Jarkko Sakkinen Signed-off-by: David Howells Signed-off-by: James Morris --- certs/Makefile | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/certs/Makefile b/certs/Makefile index 4119bb376ea1..847361ce14d1 100644 --- a/certs/Makefile +++ b/certs/Makefile @@ -26,7 +26,7 @@ quiet_cmd_extract_certs = EXTRACT_CERTS $(patsubst "%",%,$(2)) targets += x509_certificate_list $(obj)/x509_certificate_list: scripts/extract-cert $(SYSTEM_TRUSTED_KEYS_SRCPREFIX)$(SYSTEM_TRUSTED_KEYS_FILENAME) FORCE $(call if_changed,extract_certs,$(SYSTEM_TRUSTED_KEYS_SRCPREFIX)$(CONFIG_SYSTEM_TRUSTED_KEYS)) -endif +endif # CONFIG_SYSTEM_TRUSTED_KEYRING clean-files := x509_certificate_list .x509.list @@ -87,7 +87,7 @@ $(obj)/x509.genkey: @echo >>$@ "keyUsage=digitalSignature" @echo >>$@ "subjectKeyIdentifier=hash" @echo >>$@ "authorityKeyIdentifier=keyid" -endif +endif # CONFIG_MODULE_SIG_KEY $(eval $(call config_filename,MODULE_SIG_KEY)) @@ -102,4 +102,4 @@ $(obj)/system_certificates.o: $(obj)/signing_key.x509 targets += signing_key.x509 $(obj)/signing_key.x509: scripts/extract-cert $(X509_DEP) FORCE $(call if_changed,extract_certs,$(MODULE_SIG_KEY_SRCPREFIX)$(CONFIG_MODULE_SIG_KEY)) -endif +endif # CONFIG_MODULE_SIG -- cgit v1.2.3-59-g8ed1b From 4f9dabfaf8df971f8a3b6aa324f8f817be38d538 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 13 Jul 2017 13:16:56 +0100 Subject: KEYS: DH: validate __spare field Syscalls must validate that their reserved arguments are zero and return EINVAL otherwise. Otherwise, it will be impossible to actually use them for anything in the future because existing programs may be passing garbage in. This is standard practice when adding new APIs. Cc: stable@vger.kernel.org Signed-off-by: Eric Biggers Signed-off-by: David Howells Signed-off-by: James Morris --- security/keys/compat_dh.c | 2 ++ security/keys/dh.c | 5 +++++ 2 files changed, 7 insertions(+) diff --git a/security/keys/compat_dh.c b/security/keys/compat_dh.c index a6a659b6bcb6..aa6b34cafe5f 100644 --- a/security/keys/compat_dh.c +++ b/security/keys/compat_dh.c @@ -33,6 +33,8 @@ long compat_keyctl_dh_compute(struct keyctl_dh_params __user *params, kdfcopy.hashname = compat_ptr(compat_kdfcopy.hashname); kdfcopy.otherinfo = compat_ptr(compat_kdfcopy.otherinfo); kdfcopy.otherinfolen = compat_kdfcopy.otherinfolen; + memcpy(kdfcopy.__spare, compat_kdfcopy.__spare, + sizeof(kdfcopy.__spare)); return __keyctl_dh_compute(params, buffer, buflen, &kdfcopy); } diff --git a/security/keys/dh.c b/security/keys/dh.c index 4755d4b4f945..d1ea9f325f94 100644 --- a/security/keys/dh.c +++ b/security/keys/dh.c @@ -266,6 +266,11 @@ long __keyctl_dh_compute(struct keyctl_dh_params __user *params, if (kdfcopy) { char *hashname; + if (memchr_inv(kdfcopy->__spare, 0, sizeof(kdfcopy->__spare))) { + ret = -EINVAL; + goto out1; + } + if (buflen > KEYCTL_KDF_MAX_OUTPUT_LEN || kdfcopy->otherinfolen > KEYCTL_KDF_MAX_OI_LEN) { ret = -EMSGSIZE; -- cgit v1.2.3-59-g8ed1b From 7228b66aaf723a623e578aa4db7d083bb39546c9 Mon Sep 17 00:00:00 2001 From: Mat Martineau Date: Thu, 13 Jul 2017 13:17:03 +0100 Subject: KEYS: Add documentation for asymmetric keyring restrictions Provide more specific examples of keyring restrictions as applied to X.509 signature chain verification. Signed-off-by: Mat Martineau Signed-off-by: David Howells Signed-off-by: James Morris --- Documentation/crypto/asymmetric-keys.txt | 65 ++++++++++++++++++++++++++++---- Documentation/security/keys/core.rst | 6 +++ 2 files changed, 63 insertions(+), 8 deletions(-) diff --git a/Documentation/crypto/asymmetric-keys.txt b/Documentation/crypto/asymmetric-keys.txt index b82b6ad48488..5969bf42562a 100644 --- a/Documentation/crypto/asymmetric-keys.txt +++ b/Documentation/crypto/asymmetric-keys.txt @@ -10,6 +10,7 @@ Contents: - Signature verification. - Asymmetric key subtypes. - Instantiation data parsers. + - Keyring link restrictions. ======== @@ -318,7 +319,8 @@ KEYRING LINK RESTRICTIONS ========================= Keyrings created from userspace using add_key can be configured to check the -signature of the key being linked. +signature of the key being linked. Keys without a valid signature are not +allowed to link. Several restriction methods are available: @@ -327,9 +329,10 @@ Several restriction methods are available: - Option string used with KEYCTL_RESTRICT_KEYRING: - "builtin_trusted" - The kernel builtin trusted keyring will be searched for the signing - key. The ca_keys kernel parameter also affects which keys are used for - signature verification. + The kernel builtin trusted keyring will be searched for the signing key. + If the builtin trusted keyring is not configured, all links will be + rejected. The ca_keys kernel parameter also affects which keys are used + for signature verification. (2) Restrict using the kernel builtin and secondary trusted keyrings @@ -337,8 +340,10 @@ Several restriction methods are available: - "builtin_and_secondary_trusted" The kernel builtin and secondary trusted keyrings will be searched for the - signing key. The ca_keys kernel parameter also affects which keys are used - for signature verification. + signing key. If the secondary trusted keyring is not configured, this + restriction will behave like the "builtin_trusted" option. The ca_keys + kernel parameter also affects which keys are used for signature + verification. (3) Restrict using a separate key or keyring @@ -346,7 +351,7 @@ Several restriction methods are available: - "key_or_keyring:[:chain]" Whenever a key link is requested, the link will only succeed if the key - being linked is signed by one of the designated keys. This key may be + being linked is signed by one of the designated keys. This key may be specified directly by providing a serial number for one asymmetric key, or a group of keys may be searched for the signing key by providing the serial number for a keyring. @@ -354,7 +359,51 @@ Several restriction methods are available: When the "chain" option is provided at the end of the string, the keys within the destination keyring will also be searched for signing keys. This allows for verification of certificate chains by adding each - cert in order (starting closest to the root) to one keyring. + certificate in order (starting closest to the root) to a keyring. For + instance, one keyring can be populated with links to a set of root + certificates, with a separate, restricted keyring set up for each + certificate chain to be validated: + + # Create and populate a keyring for root certificates + root_id=`keyctl add keyring root-certs "" @s` + keyctl padd asymmetric "" $root_id < root1.cert + keyctl padd asymmetric "" $root_id < root2.cert + + # Create and restrict a keyring for the certificate chain + chain_id=`keyctl add keyring chain "" @s` + keyctl restrict_keyring $chain_id asymmetric key_or_keyring:$root_id:chain + + # Attempt to add each certificate in the chain, starting with the + # certificate closest to the root. + keyctl padd asymmetric "" $chain_id < intermediateA.cert + keyctl padd asymmetric "" $chain_id < intermediateB.cert + keyctl padd asymmetric "" $chain_id < end-entity.cert + + If the final end-entity certificate is successfully added to the "chain" + keyring, we can be certain that it has a valid signing chain going back to + one of the root certificates. + + A single keyring can be used to verify a chain of signatures by + restricting the keyring after linking the root certificate: + + # Create a keyring for the certificate chain and add the root + chain2_id=`keyctl add keyring chain2 "" @s` + keyctl padd asymmetric "" $chain2_id < root1.cert + + # Restrict the keyring that already has root1.cert linked. The cert + # will remain linked by the keyring. + keyctl restrict_keyring $chain2_id asymmetric key_or_keyring:0:chain + + # Attempt to add each certificate in the chain, starting with the + # certificate closest to the root. + keyctl padd asymmetric "" $chain2_id < intermediateA.cert + keyctl padd asymmetric "" $chain2_id < intermediateB.cert + keyctl padd asymmetric "" $chain2_id < end-entity.cert + + If the final end-entity certificate is successfully added to the "chain2" + keyring, we can be certain that there is a valid signing chain going back + to the root certificate that was added before the keyring was restricted. + In all of these cases, if the signing key is found the signature of the key to be linked will be verified using the signing key. The requested key is added diff --git a/Documentation/security/keys/core.rst b/Documentation/security/keys/core.rst index 0d831a7afe4f..1648fa80b3bf 100644 --- a/Documentation/security/keys/core.rst +++ b/Documentation/security/keys/core.rst @@ -894,6 +894,12 @@ The keyctl syscall functions are: To apply a keyring restriction the process must have Set Attribute permission and the keyring must not be previously restricted. + One application of restricted keyrings is to verify X.509 certificate + chains or individual certificate signatures using the asymmetric key type. + See Documentation/crypto/asymmetric-keys.txt for specific restrictions + applicable to the asymmetric key type. + + Kernel Services =============== -- cgit v1.2.3-59-g8ed1b From cfcd20e5caad6ba552978c16ed8bed7edb0143cf Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Thu, 13 Jul 2017 18:30:39 -0700 Subject: KVM: x86: Simplify kvm_x86_ops->queue_exception parameter list MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch removes all arguments except the first in kvm_x86_ops->queue_exception since they can extract the arguments from vcpu->arch.exception themselves. Cc: Paolo Bonzini Cc: Radim Krčmář Signed-off-by: Wanpeng Li Signed-off-by: Radim Krčmář --- arch/x86/include/asm/kvm_host.h | 4 +--- arch/x86/kvm/svm.c | 8 +++++--- arch/x86/kvm/vmx.c | 8 +++++--- arch/x86/kvm/x86.c | 5 +---- 4 files changed, 12 insertions(+), 13 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 9d8de5dd7546..8d11ddcb0dbf 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -954,9 +954,7 @@ struct kvm_x86_ops { unsigned char *hypercall_addr); void (*set_irq)(struct kvm_vcpu *vcpu); void (*set_nmi)(struct kvm_vcpu *vcpu); - void (*queue_exception)(struct kvm_vcpu *vcpu, unsigned nr, - bool has_error_code, u32 error_code, - bool reinject); + void (*queue_exception)(struct kvm_vcpu *vcpu); void (*cancel_injection)(struct kvm_vcpu *vcpu); int (*interrupt_allowed)(struct kvm_vcpu *vcpu); int (*nmi_allowed)(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 4c98d362e3e4..cde756a02b1a 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -637,11 +637,13 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) svm_set_interrupt_shadow(vcpu, 0); } -static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, - bool has_error_code, u32 error_code, - bool reinject) +static void svm_queue_exception(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + unsigned nr = vcpu->arch.exception.nr; + bool has_error_code = vcpu->arch.exception.has_error_code; + bool reinject = vcpu->arch.exception.reinject; + u32 error_code = vcpu->arch.exception.error_code; /* * If we are within a nested VM we'd better #VMEXIT and let the guest diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 25f2fdccf625..69cc228436ea 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2435,11 +2435,13 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr) return 1; } -static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, - bool has_error_code, u32 error_code, - bool reinject) +static void vmx_queue_exception(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned nr = vcpu->arch.exception.nr; + bool has_error_code = vcpu->arch.exception.has_error_code; + bool reinject = vcpu->arch.exception.reinject; + u32 error_code = vcpu->arch.exception.error_code; u32 intr_info = nr | INTR_INFO_VALID_MASK; if (!reinject && is_guest_mode(vcpu) && diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4f41c5222ecd..e149c92476f1 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6356,10 +6356,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) kvm_update_dr7(vcpu); } - kvm_x86_ops->queue_exception(vcpu, vcpu->arch.exception.nr, - vcpu->arch.exception.has_error_code, - vcpu->arch.exception.error_code, - vcpu->arch.exception.reinject); + kvm_x86_ops->queue_exception(vcpu); return 0; } -- cgit v1.2.3-59-g8ed1b From 1261bfa326f5e903166498628a1894edce0caabc Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Thu, 13 Jul 2017 18:30:40 -0700 Subject: KVM: async_pf: Add L1 guest async_pf #PF vmexit handler MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds the L1 guest async page fault #PF vmexit handler, such by L1 similar to ordinary async page fault. Cc: Paolo Bonzini Cc: Radim Krčmář Signed-off-by: Wanpeng Li [Passed insn parameters to kvm_mmu_page_fault().] Signed-off-by: Radim Krčmář --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/mmu.c | 33 +++++++++++++++++++++++++++++++++ arch/x86/kvm/mmu.h | 3 +++ arch/x86/kvm/svm.c | 36 ++++++------------------------------ arch/x86/kvm/vmx.c | 15 ++++++++------- 5 files changed, 51 insertions(+), 37 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 8d11ddcb0dbf..4f20ee6c79a1 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -650,6 +650,7 @@ struct kvm_vcpu_arch { u64 msr_val; u32 id; bool send_user_only; + u32 host_apf_reason; } apf; /* OSVW MSRs (AMD only) */ diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index aafd399cf8c6..3825a35cd752 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -46,6 +46,7 @@ #include #include #include +#include "trace.h" /* * When setting this variable to true it enables Two-Dimensional-Paging @@ -3780,6 +3781,38 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, return false; } +int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, + u64 fault_address, char *insn, int insn_len, + bool need_unprotect) +{ + int r = 1; + + switch (vcpu->arch.apf.host_apf_reason) { + default: + trace_kvm_page_fault(fault_address, error_code); + + if (need_unprotect && kvm_event_needs_reinjection(vcpu)) + kvm_mmu_unprotect_page_virt(vcpu, fault_address); + r = kvm_mmu_page_fault(vcpu, fault_address, error_code, insn, + insn_len); + break; + case KVM_PV_REASON_PAGE_NOT_PRESENT: + vcpu->arch.apf.host_apf_reason = 0; + local_irq_disable(); + kvm_async_pf_task_wait(fault_address); + local_irq_enable(); + break; + case KVM_PV_REASON_PAGE_READY: + vcpu->arch.apf.host_apf_reason = 0; + local_irq_disable(); + kvm_async_pf_task_wake(fault_address); + local_irq_enable(); + break; + } + return r; +} +EXPORT_SYMBOL_GPL(kvm_handle_page_fault); + static bool check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level) { diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index a276834950c1..d7d248a000dd 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -77,6 +77,9 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu); void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, bool accessed_dirty); bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); +int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, + u64 fault_address, char *insn, int insn_len, + bool need_unprotect); static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm) { diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index cde756a02b1a..fb23497cf915 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -194,7 +194,6 @@ struct vcpu_svm { unsigned int3_injected; unsigned long int3_rip; - u32 apf_reason; /* cached guest cpuid flags for faster access */ bool nrips_enabled : 1; @@ -2122,34 +2121,11 @@ static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value) static int pf_interception(struct vcpu_svm *svm) { u64 fault_address = svm->vmcb->control.exit_info_2; - u64 error_code; - int r = 1; + u64 error_code = svm->vmcb->control.exit_info_1; - switch (svm->apf_reason) { - default: - error_code = svm->vmcb->control.exit_info_1; - - trace_kvm_page_fault(fault_address, error_code); - if (!npt_enabled && kvm_event_needs_reinjection(&svm->vcpu)) - kvm_mmu_unprotect_page_virt(&svm->vcpu, fault_address); - r = kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code, + return kvm_handle_page_fault(&svm->vcpu, error_code, fault_address, svm->vmcb->control.insn_bytes, - svm->vmcb->control.insn_len); - break; - case KVM_PV_REASON_PAGE_NOT_PRESENT: - svm->apf_reason = 0; - local_irq_disable(); - kvm_async_pf_task_wait(fault_address); - local_irq_enable(); - break; - case KVM_PV_REASON_PAGE_READY: - svm->apf_reason = 0; - local_irq_disable(); - kvm_async_pf_task_wake(fault_address); - local_irq_enable(); - break; - } - return r; + svm->vmcb->control.insn_len, !npt_enabled); } static int db_interception(struct vcpu_svm *svm) @@ -2630,7 +2606,7 @@ static int nested_svm_exit_special(struct vcpu_svm *svm) break; case SVM_EXIT_EXCP_BASE + PF_VECTOR: /* When we're shadowing, trap PFs, but not async PF */ - if (!npt_enabled && svm->apf_reason == 0) + if (!npt_enabled && svm->vcpu.arch.apf.host_apf_reason == 0) return NESTED_EXIT_HOST; break; default: @@ -2677,7 +2653,7 @@ static int nested_svm_intercept(struct vcpu_svm *svm) } /* async page fault always cause vmexit */ else if ((exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) && - svm->apf_reason != 0) + svm->vcpu.arch.apf.host_apf_reason != 0) vmexit = NESTED_EXIT_DONE; break; } @@ -4998,7 +4974,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) /* if exit due to PF check for async PF */ if (svm->vmcb->control.exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) - svm->apf_reason = kvm_read_and_reset_pf_reason(); + svm->vcpu.arch.apf.host_apf_reason = kvm_read_and_reset_pf_reason(); if (npt_enabled) { vcpu->arch.regs_avail &= ~(1 << VCPU_EXREG_PDPTR); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 69cc228436ea..c9c46e63f744 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -5698,14 +5698,11 @@ static int handle_exception(struct kvm_vcpu *vcpu) } if (is_page_fault(intr_info)) { - /* EPT won't cause page fault directly */ - BUG_ON(enable_ept); cr2 = vmcs_readl(EXIT_QUALIFICATION); - trace_kvm_page_fault(cr2, error_code); - - if (kvm_event_needs_reinjection(vcpu)) - kvm_mmu_unprotect_page_virt(vcpu, cr2); - return kvm_mmu_page_fault(vcpu, cr2, error_code, NULL, 0); + /* EPT won't cause page fault directly */ + WARN_ON_ONCE(!vcpu->arch.apf.host_apf_reason && enable_ept); + return kvm_handle_page_fault(vcpu, error_code, cr2, NULL, 0, + true); } ex_no = intr_info & INTR_INFO_VECTOR_MASK; @@ -8643,6 +8640,10 @@ static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx) exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); vmx->exit_intr_info = exit_intr_info; + /* if exit due to PF check for async PF */ + if (is_page_fault(exit_intr_info)) + vmx->vcpu.arch.apf.host_apf_reason = kvm_read_and_reset_pf_reason(); + /* Handle machine checks before interrupts are enabled */ if (basic_exit_reason == EXIT_REASON_MCE_DURING_VMENTRY || is_machine_check(exit_intr_info)) -- cgit v1.2.3-59-g8ed1b From adfe20fb48785dd73af3bf91407196eb5403c8cf Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Thu, 13 Jul 2017 18:30:41 -0700 Subject: KVM: async_pf: Force a nested vmexit if the injected #PF is async_pf MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add an nested_apf field to vcpu->arch.exception to identify an async page fault, and constructs the expected vm-exit information fields. Force a nested VM exit from nested_vmx_check_exception() if the injected #PF is async page fault. Cc: Paolo Bonzini Cc: Radim Krčmář Signed-off-by: Wanpeng Li Signed-off-by: Radim Krčmář --- arch/x86/include/asm/kvm_emulate.h | 1 + arch/x86/include/asm/kvm_host.h | 2 ++ arch/x86/kvm/svm.c | 16 ++++++++++------ arch/x86/kvm/vmx.c | 17 ++++++++++++++--- arch/x86/kvm/x86.c | 9 ++++++++- 5 files changed, 35 insertions(+), 10 deletions(-) diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 722d0e568863..fde36f189836 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -23,6 +23,7 @@ struct x86_exception { u16 error_code; bool nested_page_fault; u64 address; /* cr2 or nested page fault gpa */ + u8 async_page_fault; }; /* diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 4f20ee6c79a1..5e9ac508f718 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -550,6 +550,7 @@ struct kvm_vcpu_arch { bool reinject; u8 nr; u32 error_code; + u8 nested_apf; } exception; struct kvm_queued_interrupt { @@ -651,6 +652,7 @@ struct kvm_vcpu_arch { u32 id; bool send_user_only; u32 host_apf_reason; + unsigned long nested_apf_token; } apf; /* OSVW MSRs (AMD only) */ diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index fb23497cf915..4d8141e533c3 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -2423,15 +2423,19 @@ static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, if (!is_guest_mode(&svm->vcpu)) return 0; + vmexit = nested_svm_intercept(svm); + if (vmexit != NESTED_EXIT_DONE) + return 0; + svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr; svm->vmcb->control.exit_code_hi = 0; svm->vmcb->control.exit_info_1 = error_code; - svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2; - - vmexit = nested_svm_intercept(svm); - if (vmexit == NESTED_EXIT_DONE) - svm->nested.exit_required = true; + if (svm->vcpu.arch.exception.nested_apf) + svm->vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token; + else + svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2; + svm->nested.exit_required = true; return vmexit; } @@ -2653,7 +2657,7 @@ static int nested_svm_intercept(struct vcpu_svm *svm) } /* async page fault always cause vmexit */ else if ((exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) && - svm->vcpu.arch.apf.host_apf_reason != 0) + svm->vcpu.arch.exception.nested_apf != 0) vmexit = NESTED_EXIT_DONE; break; } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index c9c46e63f744..5a3bb1a697a2 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2422,13 +2422,24 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) * KVM wants to inject page-faults which it got to the guest. This function * checks whether in a nested guest, we need to inject them to L1 or L2. */ -static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr) +static int nested_vmx_check_exception(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + unsigned int nr = vcpu->arch.exception.nr; - if (!(vmcs12->exception_bitmap & (1u << nr))) + if (!((vmcs12->exception_bitmap & (1u << nr)) || + (nr == PF_VECTOR && vcpu->arch.exception.nested_apf))) return 0; + if (vcpu->arch.exception.nested_apf) { + vmcs_write32(VM_EXIT_INTR_ERROR_CODE, vcpu->arch.exception.error_code); + nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, + PF_VECTOR | INTR_TYPE_HARD_EXCEPTION | + INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK, + vcpu->arch.apf.nested_apf_token); + return 1; + } + nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, vmcs_read32(VM_EXIT_INTR_INFO), vmcs_readl(EXIT_QUALIFICATION)); @@ -2445,7 +2456,7 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu) u32 intr_info = nr | INTR_INFO_VALID_MASK; if (!reinject && is_guest_mode(vcpu) && - nested_vmx_check_exception(vcpu, nr)) + nested_vmx_check_exception(vcpu)) return; if (has_error_code) { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e149c92476f1..f3f10154c133 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -450,7 +450,12 @@ EXPORT_SYMBOL_GPL(kvm_complete_insn_gp); void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { ++vcpu->stat.pf_guest; - vcpu->arch.cr2 = fault->address; + vcpu->arch.exception.nested_apf = + is_guest_mode(vcpu) && fault->async_page_fault; + if (vcpu->arch.exception.nested_apf) + vcpu->arch.apf.nested_apf_token = fault->address; + else + vcpu->arch.cr2 = fault->address; kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code); } EXPORT_SYMBOL_GPL(kvm_inject_page_fault); @@ -8582,6 +8587,7 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, fault.error_code = 0; fault.nested_page_fault = false; fault.address = work->arch.token; + fault.async_page_fault = true; kvm_inject_page_fault(vcpu, &fault); } } @@ -8604,6 +8610,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, fault.error_code = 0; fault.nested_page_fault = false; fault.address = work->arch.token; + fault.async_page_fault = true; kvm_inject_page_fault(vcpu, &fault); } vcpu->arch.apf.halted = false; -- cgit v1.2.3-59-g8ed1b From 52a5c155cf79f1f059bffebf4d06d0249573e659 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Thu, 13 Jul 2017 18:30:42 -0700 Subject: KVM: async_pf: Let guest support delivery of async_pf from guest mode MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Adds another flag bit (bit 2) to MSR_KVM_ASYNC_PF_EN. If bit 2 is 1, async page faults are delivered to L1 as #PF vmexits; if bit 2 is 0, kvm_can_do_async_pf returns 0 if in guest mode. This is similar to what svm.c wanted to do all along, but it is only enabled for Linux as L1 hypervisor. Foreign hypervisors must never receive async page faults as vmexits, because they'd probably be very confused about that. Cc: Paolo Bonzini Cc: Radim Krčmář Signed-off-by: Wanpeng Li Signed-off-by: Radim Krčmář --- Documentation/virtual/kvm/msr.txt | 5 +++-- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/include/uapi/asm/kvm_para.h | 1 + arch/x86/kernel/kvm.c | 7 ++++++- arch/x86/kvm/mmu.c | 2 +- arch/x86/kvm/vmx.c | 2 +- arch/x86/kvm/x86.c | 5 +++-- 7 files changed, 16 insertions(+), 7 deletions(-) diff --git a/Documentation/virtual/kvm/msr.txt b/Documentation/virtual/kvm/msr.txt index 0a9ea515512a..1ebecc115dc6 100644 --- a/Documentation/virtual/kvm/msr.txt +++ b/Documentation/virtual/kvm/msr.txt @@ -166,10 +166,11 @@ MSR_KVM_SYSTEM_TIME: 0x12 MSR_KVM_ASYNC_PF_EN: 0x4b564d02 data: Bits 63-6 hold 64-byte aligned physical address of a 64 byte memory area which must be in guest RAM and must be - zeroed. Bits 5-2 are reserved and should be zero. Bit 0 is 1 + zeroed. Bits 5-3 are reserved and should be zero. Bit 0 is 1 when asynchronous page faults are enabled on the vcpu 0 when disabled. Bit 1 is 1 if asynchronous page faults can be injected - when vcpu is in cpl == 0. + when vcpu is in cpl == 0. Bit 2 is 1 if asynchronous page faults + are delivered to L1 as #PF vmexits. First 4 byte of 64 byte memory location will be written to by the hypervisor at the time of asynchronous page fault (APF) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 5e9ac508f718..da3261e384d3 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -653,6 +653,7 @@ struct kvm_vcpu_arch { bool send_user_only; u32 host_apf_reason; unsigned long nested_apf_token; + bool delivery_as_pf_vmexit; } apf; /* OSVW MSRs (AMD only) */ diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index cff0bb6556f8..a965e5b0d328 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -67,6 +67,7 @@ struct kvm_clock_pairing { #define KVM_ASYNC_PF_ENABLED (1 << 0) #define KVM_ASYNC_PF_SEND_ALWAYS (1 << 1) +#define KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT (1 << 2) /* Operations for KVM_HC_MMU_OP */ #define KVM_MMU_OP_WRITE_PTE 1 diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 43e10d6fdbed..71c17a5be983 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -330,7 +330,12 @@ static void kvm_guest_cpu_init(void) #ifdef CONFIG_PREEMPT pa |= KVM_ASYNC_PF_SEND_ALWAYS; #endif - wrmsrl(MSR_KVM_ASYNC_PF_EN, pa | KVM_ASYNC_PF_ENABLED); + pa |= KVM_ASYNC_PF_ENABLED; + + /* Async page fault support for L1 hypervisor is optional */ + if (wrmsr_safe(MSR_KVM_ASYNC_PF_EN, + (pa | KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT) & 0xffffffff, pa >> 32) < 0) + wrmsrl(MSR_KVM_ASYNC_PF_EN, pa); __this_cpu_write(apf_reason.enabled, 1); printk(KERN_INFO"KVM setup async PF for cpu %d\n", smp_processor_id()); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 3825a35cd752..9b1dd114956a 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3749,7 +3749,7 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) kvm_event_needs_reinjection(vcpu))) return false; - if (is_guest_mode(vcpu)) + if (!vcpu->arch.apf.delivery_as_pf_vmexit && is_guest_mode(vcpu)) return false; return kvm_x86_ops->interrupt_allowed(vcpu); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 5a3bb1a697a2..84e62acf2dd8 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -8037,7 +8037,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) if (is_nmi(intr_info)) return false; else if (is_page_fault(intr_info)) - return enable_ept; + return !vmx->vcpu.arch.apf.host_apf_reason && enable_ept; else if (is_no_device(intr_info) && !(vmcs12->guest_cr0 & X86_CR0_TS)) return false; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f3f10154c133..6753f0982791 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2063,8 +2063,8 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) { gpa_t gpa = data & ~0x3f; - /* Bits 2:5 are reserved, Should be zero */ - if (data & 0x3c) + /* Bits 3:5 are reserved, Should be zero */ + if (data & 0x38) return 1; vcpu->arch.apf.msr_val = data; @@ -2080,6 +2080,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) return 1; vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS); + vcpu->arch.apf.delivery_as_pf_vmexit = data & KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT; kvm_async_pf_wakeup_all(vcpu); return 0; } -- cgit v1.2.3-59-g8ed1b From d3457c877b14aaee8c52923eedf05a3b78af0476 Mon Sep 17 00:00:00 2001 From: Roman Kagan Date: Fri, 14 Jul 2017 17:13:20 +0300 Subject: kvm: x86: hyperv: make VP_INDEX managed by userspace MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Hyper-V identifies vCPUs by Virtual Processor Index, which can be queried via HV_X64_MSR_VP_INDEX msr. It is defined by the spec as a sequential number which can't exceed the maximum number of vCPUs per VM. APIC ids can be sparse and thus aren't a valid replacement for VP indices. Current KVM uses its internal vcpu index as VP_INDEX. However, to make it predictable and persistent across VM migrations, the userspace has to control the value of VP_INDEX. This patch achieves that, by storing vp_index explicitly on vcpu, and allowing HV_X64_MSR_VP_INDEX to be set from the host side. For compatibility it's initialized to KVM vcpu index. Also a few variables are renamed to make clear distinction betweed this Hyper-V vp_index and KVM vcpu_id (== APIC id). Besides, a new capability, KVM_CAP_HYPERV_VP_INDEX, is added to allow the userspace to skip attempting msr writes where unsupported, to avoid spamming error logs. Signed-off-by: Roman Kagan Signed-off-by: Radim Krčmář --- Documentation/virtual/kvm/api.txt | 9 +++++++ arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/hyperv.c | 54 +++++++++++++++++++++++++-------------- arch/x86/kvm/hyperv.h | 1 + arch/x86/kvm/x86.c | 3 +++ include/uapi/linux/kvm.h | 1 + 6 files changed, 50 insertions(+), 19 deletions(-) diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 78ac577c9378..e63a35fafef0 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -4338,3 +4338,12 @@ This capability enables a newer version of Hyper-V Synthetic interrupt controller (SynIC). The only difference with KVM_CAP_HYPERV_SYNIC is that KVM doesn't clear SynIC message and event flags pages when they are enabled by writing to the respective MSRs. + +8.12 KVM_CAP_HYPERV_VP_INDEX + +Architectures: x86 + +This capability indicates that userspace can load HV_X64_MSR_VP_INDEX msr. Its +value is used to denote the target vcpu for a SynIC interrupt. For +compatibilty, KVM initializes this msr to KVM's internal vcpu index. When this +capability is absent, userspace can still query this msr's value. diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index da3261e384d3..87ac4fba6d8e 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -467,6 +467,7 @@ struct kvm_vcpu_hv_synic { /* Hyper-V per vcpu emulation context */ struct kvm_vcpu_hv { + u32 vp_index; u64 hv_vapic; s64 runtime_offset; struct kvm_vcpu_hv_synic synic; diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index a8084406707e..2695a34fa1c5 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -106,14 +106,27 @@ static int synic_set_sint(struct kvm_vcpu_hv_synic *synic, int sint, return 0; } -static struct kvm_vcpu_hv_synic *synic_get(struct kvm *kvm, u32 vcpu_id) +static struct kvm_vcpu *get_vcpu_by_vpidx(struct kvm *kvm, u32 vpidx) +{ + struct kvm_vcpu *vcpu = NULL; + int i; + + if (vpidx < KVM_MAX_VCPUS) + vcpu = kvm_get_vcpu(kvm, vpidx); + if (vcpu && vcpu_to_hv_vcpu(vcpu)->vp_index == vpidx) + return vcpu; + kvm_for_each_vcpu(i, vcpu, kvm) + if (vcpu_to_hv_vcpu(vcpu)->vp_index == vpidx) + return vcpu; + return NULL; +} + +static struct kvm_vcpu_hv_synic *synic_get(struct kvm *kvm, u32 vpidx) { struct kvm_vcpu *vcpu; struct kvm_vcpu_hv_synic *synic; - if (vcpu_id >= atomic_read(&kvm->online_vcpus)) - return NULL; - vcpu = kvm_get_vcpu(kvm, vcpu_id); + vcpu = get_vcpu_by_vpidx(kvm, vpidx); if (!vcpu) return NULL; synic = vcpu_to_synic(vcpu); @@ -320,11 +333,11 @@ static int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint) return ret; } -int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint) +int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vpidx, u32 sint) { struct kvm_vcpu_hv_synic *synic; - synic = synic_get(kvm, vcpu_id); + synic = synic_get(kvm, vpidx); if (!synic) return -EINVAL; @@ -343,11 +356,11 @@ void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector) kvm_hv_notify_acked_sint(vcpu, i); } -static int kvm_hv_set_sint_gsi(struct kvm *kvm, u32 vcpu_id, u32 sint, int gsi) +static int kvm_hv_set_sint_gsi(struct kvm *kvm, u32 vpidx, u32 sint, int gsi) { struct kvm_vcpu_hv_synic *synic; - synic = synic_get(kvm, vcpu_id); + synic = synic_get(kvm, vpidx); if (!synic) return -EINVAL; @@ -689,6 +702,13 @@ void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) stimer_init(&hv_vcpu->stimer[i], i); } +void kvm_hv_vcpu_postcreate(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu); + + hv_vcpu->vp_index = kvm_vcpu_get_idx(vcpu); +} + int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages) { struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu); @@ -983,6 +1003,11 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv; switch (msr) { + case HV_X64_MSR_VP_INDEX: + if (!host) + return 1; + hv->vp_index = (u32)data; + break; case HV_X64_MSR_APIC_ASSIST_PAGE: { u64 gfn; unsigned long addr; @@ -1094,18 +1119,9 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv; switch (msr) { - case HV_X64_MSR_VP_INDEX: { - int r; - struct kvm_vcpu *v; - - kvm_for_each_vcpu(r, v, vcpu->kvm) { - if (v == vcpu) { - data = r; - break; - } - } + case HV_X64_MSR_VP_INDEX: + data = hv->vp_index; break; - } case HV_X64_MSR_EOI: return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata); case HV_X64_MSR_ICR: diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 12f65fe1011d..e637631a9574 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -59,6 +59,7 @@ void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector); int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages); void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu); +void kvm_hv_vcpu_postcreate(struct kvm_vcpu *vcpu); void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu); static inline struct kvm_vcpu_hv_stimer *vcpu_to_stimer(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6753f0982791..5b8f07889f6a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2666,6 +2666,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV_SPIN: case KVM_CAP_HYPERV_SYNIC: case KVM_CAP_HYPERV_SYNIC2: + case KVM_CAP_HYPERV_VP_INDEX: case KVM_CAP_PCI_SEGMENT: case KVM_CAP_DEBUGREGS: case KVM_CAP_X86_ROBUST_SINGLESTEP: @@ -7688,6 +7689,8 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) struct msr_data msr; struct kvm *kvm = vcpu->kvm; + kvm_hv_vcpu_postcreate(vcpu); + if (vcpu_load(vcpu)) return; msr.data = 0x0; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 38b2cfbc8112..6cd63c18708a 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -928,6 +928,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_PPC_FWNMI 146 #define KVM_CAP_PPC_SMT_POSSIBLE 147 #define KVM_CAP_HYPERV_SYNIC2 148 +#define KVM_CAP_HYPERV_VP_INDEX 149 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3-59-g8ed1b From 457839ed3e78618cf0354cf79a1f47fe6eb26aef Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Mon, 10 Jul 2017 14:35:23 +0200 Subject: mdio: mux: fix parsing mux registers outside of the PHY address range mdio_mux_init parses the child nodes of the MDIO mux. When using "mdio-mux-mmioreg" the child nodes are describing the register value that is written to switch between the MDIO busses. The change which makes the error messages more verbose changed the parsing of the "reg" property from a simple of_property_read_u32 call to of_mdio_parse_addr. On a Khadas VIM (based on the Meson GXL SoC, which uses mdio-mux-mmioreg) this prevents registering the MDIO mux (because the "reg" values on the MDIO mux child nodes are 0x2009087f and 0xe40908ff) and leads to the following errors: mdio-mux-mmioreg c883455c.eth-phy-mux: /soc/periphs@c8834000/eth-phy-mux/mdio@e40908ff PHY address -469169921 is too large mdio-mux-mmioreg c883455c.eth-phy-mux: Error: Failed to find reg for child /soc/periphs@c8834000/eth-phy-mux/mdio@e40908ff mdio-mux-mmioreg c883455c.eth-phy-mux: /soc/periphs@c8834000/eth-phy-mux/mdio@2009087f PHY address 537462911 is too large mdio-mux-mmioreg c883455c.eth-phy-mux: Error: Failed to find reg for child /soc/periphs@c8834000/eth-phy-mux/mdio@2009087f mdio-mux-mmioreg c883455c.eth-phy-mux: Error: No acceptable child buses found mdio-mux-mmioreg c883455c.eth-phy-mux: failed to register mdio-mux bus /soc/periphs@c8834000/eth-phy-mux (as a result of that ethernet is not working, because the PHY which is connected through the mux' child MDIO bus, which is not being registered). Fix this by reverting the change from of_mdio_parse_addr to of_mdio_parse_addr. Fixes: 342fa1964439 ("mdio: mux: make child bus walking more permissive and errors more verbose") Signed-off-by: Martin Blumenstingl Acked-by: Neil Armstrong Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/mdio-mux.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/phy/mdio-mux.c b/drivers/net/phy/mdio-mux.c index 00755b6a42cf..c608e1dfaf09 100644 --- a/drivers/net/phy/mdio-mux.c +++ b/drivers/net/phy/mdio-mux.c @@ -135,8 +135,8 @@ int mdio_mux_init(struct device *dev, for_each_available_child_of_node(dev->of_node, child_bus_node) { int v; - v = of_mdio_parse_addr(dev, child_bus_node); - if (v < 0) { + r = of_property_read_u32(child_bus_node, "reg", &v); + if (r) { dev_err(dev, "Error: Failed to find reg for child %s\n", of_node_full_name(child_bus_node)); -- cgit v1.2.3-59-g8ed1b From 2b02c20ce0c28974b44e69a2e2f5ddc6a470ad6f Mon Sep 17 00:00:00 2001 From: Enrico Mioso Date: Tue, 11 Jul 2017 17:21:52 +0200 Subject: cdc_ncm: Set NTB format again after altsetting switch for Huawei devices MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some firmwares in Huawei E3372H devices have been observed to switch back to NTB 32-bit format after altsetting switch. This patch implements a driver flag to check for the device settings and set NTB format to 16-bit again if needed. The flag has been activated for devices controlled by the huawei_cdc_ncm.c driver. V1->V2: - fixed broken error checks - some corrections to the commit message V2->V3: - variable name changes, to clarify what's happening - check (and possibly set) the NTB format later in the common bind code path Signed-off-by: Enrico Mioso Reported-and-tested-by: Christian Panton Reviewed-by: Bjørn Mork CC: Bjørn Mork CC: Christian Panton CC: linux-usb@vger.kernel.org CC: netdev@vger.kernel.org CC: Oliver Neukum Signed-off-by: David S. Miller --- drivers/net/usb/cdc_ncm.c | 28 ++++++++++++++++++++++++++++ drivers/net/usb/huawei_cdc_ncm.c | 6 ++++++ include/linux/usb/cdc_ncm.h | 1 + 3 files changed, 35 insertions(+) diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index d103a1d4fb36..8f572b9f3625 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -768,8 +768,10 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ u8 *buf; int len; int temp; + int err; u8 iface_no; struct usb_cdc_parsed_header hdr; + u16 curr_ntb_format; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) @@ -874,6 +876,32 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ goto error2; } + /* + * Some Huawei devices have been observed to come out of reset in NDP32 mode. + * Let's check if this is the case, and set the device to NDP16 mode again if + * needed. + */ + if (ctx->drvflags & CDC_NCM_FLAG_RESET_NTB16) { + err = usbnet_read_cmd(dev, USB_CDC_GET_NTB_FORMAT, + USB_TYPE_CLASS | USB_DIR_IN | USB_RECIP_INTERFACE, + 0, iface_no, &curr_ntb_format, 2); + if (err < 0) { + goto error2; + } + + if (curr_ntb_format == USB_CDC_NCM_NTB32_FORMAT) { + dev_info(&intf->dev, "resetting NTB format to 16-bit"); + err = usbnet_write_cmd(dev, USB_CDC_SET_NTB_FORMAT, + USB_TYPE_CLASS | USB_DIR_OUT + | USB_RECIP_INTERFACE, + USB_CDC_NCM_NTB16_FORMAT, + iface_no, NULL, 0); + + if (err < 0) + goto error2; + } + } + cdc_ncm_find_endpoints(dev, ctx->data); cdc_ncm_find_endpoints(dev, ctx->control); if (!dev->in || !dev->out || !dev->status) { diff --git a/drivers/net/usb/huawei_cdc_ncm.c b/drivers/net/usb/huawei_cdc_ncm.c index 2680a65cd5e4..63f28908afda 100644 --- a/drivers/net/usb/huawei_cdc_ncm.c +++ b/drivers/net/usb/huawei_cdc_ncm.c @@ -80,6 +80,12 @@ static int huawei_cdc_ncm_bind(struct usbnet *usbnet_dev, * be at the end of the frame. */ drvflags |= CDC_NCM_FLAG_NDP_TO_END; + + /* Additionally, it has been reported that some Huawei E3372H devices, with + * firmware version 21.318.01.00.541, come out of reset in NTB32 format mode, hence + * needing to be set to the NTB16 one again. + */ + drvflags |= CDC_NCM_FLAG_RESET_NTB16; ret = cdc_ncm_bind_common(usbnet_dev, intf, 1, drvflags); if (ret) goto err; diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 021f7a88f52c..1a59699cf82a 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -83,6 +83,7 @@ /* Driver flags */ #define CDC_NCM_FLAG_NDP_TO_END 0x02 /* NDP is placed at end of frame */ #define CDC_MBIM_FLAG_AVOID_ALTSETTING_TOGGLE 0x04 /* Avoid altsetting toggle during init */ +#define CDC_NCM_FLAG_RESET_NTB16 0x08 /* set NDP16 one more time after altsetting switch */ #define cdc_ncm_comm_intf_is_mbim(x) ((x)->desc.bInterfaceSubClass == USB_CDC_SUBCLASS_MBIM && \ (x)->desc.bInterfaceProtocol == USB_CDC_PROTO_NONE) -- cgit v1.2.3-59-g8ed1b From 230cd1279d0019d52f9529c7d91c96d095cae755 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Wed, 12 Jul 2017 15:56:41 -0700 Subject: netpoll: shut up a kernel warning on refcount When we convert atomic_t to refcount_t, a new kernel warning on "increment on 0" is introduced in the netpoll code, zap_completion_queue(). In fact for this special case, we know the refcount is 0 and we just have to set it to 1 to satisfy the following dev_kfree_skb_any(), so we can just use refcount_set(..., 1) instead. Fixes: 633547973ffc ("net: convert sk_buff.users from atomic_t to refcount_t") Reported-by: Dave Jones Cc: Reshetova, Elena Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/core/netpoll.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/netpoll.c b/net/core/netpoll.c index d3408a693166..8357f164c660 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -277,7 +277,7 @@ static void zap_completion_queue(void) struct sk_buff *skb = clist; clist = clist->next; if (!skb_irq_freeable(skb)) { - refcount_inc(&skb->users); + refcount_set(&skb->users, 1); dev_kfree_skb_any(skb); /* put this one back */ } else { __kfree_skb(skb); -- cgit v1.2.3-59-g8ed1b From 1e4babee70a2e2d8f9e0da06f013563b0e26f654 Mon Sep 17 00:00:00 2001 From: LiuJian Date: Thu, 13 Jul 2017 18:57:54 +0800 Subject: net: hns: add acpi function of xge led control The current code only support DT method to control xge led. This patch is the implementation of acpi method to control xge led. Signed-off-by: LiuJian Reviewed-by: John Garry Reviewed-by: Yunsheng Lin Reviewed-by: Daode Huang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c | 3 +- drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c | 58 +++++++++++++++++++++- 2 files changed, 58 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index ff864a187d5a..a37166ee577b 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -776,8 +776,9 @@ void hns_ae_update_led_status(struct hnae_handle *handle) assert(handle); mac_cb = hns_get_mac_cb(handle); - if (!mac_cb->cpld_ctrl) + if (mac_cb->media_type != HNAE_MEDIA_TYPE_FIBER) return; + hns_set_led_opt(mac_cb); } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c index 7a8addda726e..408b63faf9a8 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c @@ -53,6 +53,34 @@ static u32 dsaf_read_sub(struct dsaf_device *dsaf_dev, u32 reg) return ret; } +static void hns_dsaf_acpi_ledctrl_by_port(struct hns_mac_cb *mac_cb, u8 op_type, + u32 link, u32 port, u32 act) +{ + union acpi_object *obj; + union acpi_object obj_args[3], argv4; + + obj_args[0].integer.type = ACPI_TYPE_INTEGER; + obj_args[0].integer.value = link; + obj_args[1].integer.type = ACPI_TYPE_INTEGER; + obj_args[1].integer.value = port; + obj_args[2].integer.type = ACPI_TYPE_INTEGER; + obj_args[2].integer.value = act; + + argv4.type = ACPI_TYPE_PACKAGE; + argv4.package.count = 3; + argv4.package.elements = obj_args; + + obj = acpi_evaluate_dsm(ACPI_HANDLE(mac_cb->dev), + &hns_dsaf_acpi_dsm_guid, 0, op_type, &argv4); + if (!obj) { + dev_warn(mac_cb->dev, "ledctrl fail, link:%d port:%d act:%d!\n", + link, port, act); + return; + } + + ACPI_FREE(obj); +} + static void hns_cpld_set_led(struct hns_mac_cb *mac_cb, int link_status, u16 speed, int data) { @@ -93,6 +121,18 @@ static void hns_cpld_set_led(struct hns_mac_cb *mac_cb, int link_status, } } +static void hns_cpld_set_led_acpi(struct hns_mac_cb *mac_cb, int link_status, + u16 speed, int data) +{ + if (!mac_cb) { + pr_err("cpld_led_set mac_cb is null!\n"); + return; + } + + hns_dsaf_acpi_ledctrl_by_port(mac_cb, HNS_OP_LED_SET_FUNC, + link_status, mac_cb->mac_id, data); +} + static void cpld_led_reset(struct hns_mac_cb *mac_cb) { if (!mac_cb || !mac_cb->cpld_ctrl) @@ -103,6 +143,20 @@ static void cpld_led_reset(struct hns_mac_cb *mac_cb) mac_cb->cpld_led_value = CPLD_LED_DEFAULT_VALUE; } +static void cpld_led_reset_acpi(struct hns_mac_cb *mac_cb) +{ + if (!mac_cb) { + pr_err("cpld_led_reset mac_cb is null!\n"); + return; + } + + if (mac_cb->media_type != HNAE_MEDIA_TYPE_FIBER) + return; + + hns_dsaf_acpi_ledctrl_by_port(mac_cb, HNS_OP_LED_SET_FUNC, + 0, mac_cb->mac_id, 0); +} + static int cpld_set_led_id(struct hns_mac_cb *mac_cb, enum hnae_led_state status) { @@ -604,8 +658,8 @@ struct dsaf_misc_op *hns_misc_op_get(struct dsaf_device *dsaf_dev) misc_op->cfg_serdes_loopback = hns_mac_config_sds_loopback; } else if (is_acpi_node(dsaf_dev->dev->fwnode)) { - misc_op->cpld_set_led = hns_cpld_set_led; - misc_op->cpld_reset_led = cpld_led_reset; + misc_op->cpld_set_led = hns_cpld_set_led_acpi; + misc_op->cpld_reset_led = cpld_led_reset_acpi; misc_op->cpld_set_led_id = cpld_set_led_id; misc_op->dsaf_reset = hns_dsaf_rst_acpi; -- cgit v1.2.3-59-g8ed1b From 40fbbce007cb458da4c15cbf53beacf6b755cedc Mon Sep 17 00:00:00 2001 From: Ganesh Goudar Date: Thu, 13 Jul 2017 18:36:50 +0530 Subject: cxgb4: ptp_clock_register() returns error pointers Check ptp_clock_register() return not only for NULL but also for error pointers, and also nullify adapter->ptp_clock if ptp_clock_register() fails. Fixes: 9c33e4208bce ("cxgb4: Add PTP Hardware Clock (PHC) support") Reported-by: Dan Carpenter Cc: Richard Cochran Signed-off-by: Ganesh Goudar Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c index 50517cfd9671..9f9d6cae39d5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c @@ -441,7 +441,8 @@ void cxgb4_ptp_init(struct adapter *adapter) adapter->ptp_clock = ptp_clock_register(&adapter->ptp_clock_info, &adapter->pdev->dev); - if (!adapter->ptp_clock) { + if (IS_ERR_OR_NULL(adapter->ptp_clock)) { + adapter->ptp_clock = NULL; dev_err(adapter->pdev_dev, "PTP %s Clock registration has failed\n", __func__); return; -- cgit v1.2.3-59-g8ed1b From 31a4562d7408493c6377933ff2f7d7302dbdea80 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Thu, 13 Jul 2017 16:09:10 +0300 Subject: net: bridge: fix dest lookup when vlan proto doesn't match With 802.1ad support the vlan_ingress code started checking for vlan protocol mismatch which causes the current tag to be inserted and the bridge vlan protocol & pvid to be set. The vlan tag insertion changes the skb mac_header and thus the lookup mac dest pointer which was loaded prior to calling br_allowed_ingress in br_handle_frame_finish is VLAN_HLEN bytes off now, pointing to the last two bytes of the destination mac and the first four of the source mac causing lookups to always fail and broadcasting all such packets to all ports. Same thing happens for locally originated packets when passing via br_dev_xmit. So load the dest pointer after the vlan checks and possible skb change. Fixes: 8580e2117c06 ("bridge: Prepare for 802.1ad vlan filtering support") Reported-by: Anitha Narasimha Murthy Signed-off-by: Nikolay Aleksandrov Acked-by: Toshiaki Makita Signed-off-by: David S. Miller --- net/bridge/br_device.c | 3 ++- net/bridge/br_input.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index f0f3447e8aa4..861ae2a165f4 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -34,11 +34,11 @@ static struct lock_class_key bridge_netdev_addr_lock_key; netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); - const unsigned char *dest = skb->data; struct net_bridge_fdb_entry *dst; struct net_bridge_mdb_entry *mdst; struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats); const struct nf_br_ops *nf_ops; + const unsigned char *dest; u16 vid = 0; rcu_read_lock(); @@ -61,6 +61,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid)) goto out; + dest = eth_hdr(skb)->h_dest; if (is_broadcast_ether_addr(dest)) { br_flood(br, skb, BR_PKT_BROADCAST, false, true); } else if (is_multicast_ether_addr(dest)) { diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 013f2290bfa5..7637f58c1226 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -131,11 +131,11 @@ static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br, int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_bridge_port *p = br_port_get_rcu(skb->dev); - const unsigned char *dest = eth_hdr(skb)->h_dest; enum br_pkt_type pkt_type = BR_PKT_UNICAST; struct net_bridge_fdb_entry *dst = NULL; struct net_bridge_mdb_entry *mdst; bool local_rcv, mcast_hit = false; + const unsigned char *dest; struct net_bridge *br; u16 vid = 0; @@ -153,6 +153,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, false); local_rcv = !!(br->dev->flags & IFF_PROMISC); + dest = eth_hdr(skb)->h_dest; if (is_multicast_ether_addr(dest)) { /* by definition the broadcast is also a multicast address */ if (is_broadcast_ether_addr(dest)) { -- cgit v1.2.3-59-g8ed1b From ccd4eb49f3392ebf989d58bd013a7bf44cdca4d6 Mon Sep 17 00:00:00 2001 From: Iván Briano Date: Thu, 13 Jul 2017 09:46:58 -0700 Subject: net/packet: Fix Tx queue selection for AF_PACKET MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When PACKET_QDISC_BYPASS is not used, Tx queue selection will be done before the packet is enqueued, taking into account any mappings set by a queuing discipline such as mqprio without hardware offloading. This selection may be affected by a previously saved queue_mapping, either on the Rx path, or done before the packet reaches the device, as it's currently the case for AF_PACKET. In order for queue selection to work as expected when using traffic control, there can't be another selection done before that point is reached, so move the call to packet_pick_tx_queue to packet_direct_xmit, leaving the default xmit path as it was before PACKET_QDISC_BYPASS was introduced. A forward declaration of packet_pick_tx_queue() is introduced to avoid the need to reorder the functions within the file. Fixes: d346a3fae3ff ("packet: introduce PACKET_QDISC_BYPASS socket option") Signed-off-by: Iván Briano Signed-off-by: David S. Miller --- net/packet/af_packet.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index e3beb28203eb..008bb34ee324 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -214,6 +214,7 @@ static void prb_clear_rxhash(struct tpacket_kbdq_core *, static void prb_fill_vlan_info(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void packet_flush_mclist(struct sock *sk); +static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb); struct packet_skb_cb { union { @@ -260,6 +261,7 @@ static int packet_direct_xmit(struct sk_buff *skb) if (skb != orig_skb) goto drop; + packet_pick_tx_queue(dev, skb); txq = skb_get_tx_queue(dev, skb); local_bh_disable(); @@ -2747,8 +2749,6 @@ tpacket_error: goto tpacket_error; } - packet_pick_tx_queue(dev, skb); - skb->destructor = tpacket_destruct_skb; __packet_set_status(po, ph, TP_STATUS_SENDING); packet_inc_pending(&po->tx_ring); @@ -2931,8 +2931,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->priority = sk->sk_priority; skb->mark = sockc.mark; - packet_pick_tx_queue(dev, skb); - if (po->has_vnet_hdr) { err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le()); if (err) -- cgit v1.2.3-59-g8ed1b From c4c4290c17bd099b7654d683f8ab6233b4f4a364 Mon Sep 17 00:00:00 2001 From: Roman Mashak Date: Thu, 13 Jul 2017 13:12:18 -0400 Subject: net sched actions: rename act_get_notify() to tcf_get_notify() Make name consistent with other TC event notification routines, such as tcf_add_notify() and tcf_del_notify() Signed-off-by: Roman Mashak Signed-off-by: David S. Miller --- net/sched/act_api.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/sched/act_api.c b/net/sched/act_api.c index aed6cf2e9fd8..f2e9ed34a963 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -835,7 +835,7 @@ out_nlmsg_trim: } static int -act_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, +tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, struct list_head *actions, int event) { struct sk_buff *skb; @@ -1018,7 +1018,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, } if (event == RTM_GETACTION) - ret = act_get_notify(net, portid, n, &actions, event); + ret = tcf_get_notify(net, portid, n, &actions, event); else { /* delete */ ret = tcf_del_notify(net, n, &actions, portid); if (ret) -- cgit v1.2.3-59-g8ed1b From a8f5cb9e79913a6918f87495d4969706f8817b8e Mon Sep 17 00:00:00 2001 From: Petr Kulhavy Date: Thu, 13 Jul 2017 19:40:57 +0200 Subject: smsc95xx: use ethtool_op_get_ts_info() This change enables the use of SW timestamping on Raspberry PI. smsc95xx uses the usbnet transmit function usbnet_start_xmit(), which implements software timestamping. However the SOF_TIMESTAMPING_TX_SOFTWARE capability was missing and only SOF_TIMESTAMPING_RX_SOFTWARE was announced. By using ethtool_op_get_ts_info() as get_ts_info() also the SOF_TIMESTAMPING_TX_SOFTWARE is announced. Signed-off-by: Petr Kulhavy Reviewed-by: Woojung Huh Signed-off-by: David S. Miller --- drivers/net/usb/smsc95xx.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 2dfca96a63b6..340c13484e5c 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -898,6 +898,7 @@ static const struct ethtool_ops smsc95xx_ethtool_ops = { .set_wol = smsc95xx_ethtool_set_wol, .get_link_ksettings = smsc95xx_get_link_ksettings, .set_link_ksettings = smsc95xx_set_link_ksettings, + .get_ts_info = ethtool_op_get_ts_info, }; static int smsc95xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) -- cgit v1.2.3-59-g8ed1b From c98b0537f0d962b46c62c27b6c2d783257f7400f Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Thu, 13 Jul 2017 15:45:41 -0500 Subject: net: qcom/emac: fix double free of SGMII IRQ during shutdown If the interface is not up, then don't try to close it during a shutdown. This avoids possible double free of the IRQ, which can happen during a shutdown. Fixes: 03eb3eb4d4d5 ("net: qcom/emac: add shutdown function") Signed-off-by: Timur Tabi Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/emac/emac.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index 746d94e28470..60850bfa3d32 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -766,11 +766,13 @@ static void emac_shutdown(struct platform_device *pdev) struct emac_adapter *adpt = netdev_priv(netdev); struct emac_sgmii *sgmii = &adpt->phy; - /* Closing the SGMII turns off its interrupts */ - sgmii->close(adpt); + if (netdev->flags & IFF_UP) { + /* Closing the SGMII turns off its interrupts */ + sgmii->close(adpt); - /* Resetting the MAC turns off all DMA and its interrupts */ - emac_mac_reset(adpt); + /* Resetting the MAC turns off all DMA and its interrupts */ + emac_mac_reset(adpt); + } } static struct platform_driver emac_platform_driver = { -- cgit v1.2.3-59-g8ed1b From 45e0b4b3d532ea67bf90701e6162f31855ab3c98 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 14 Jul 2017 14:07:00 +0200 Subject: isdn: divert: fix sprintf buffer overflow warning One string we pass into the cs->info buffer might be too long, as pointed out by gcc: drivers/isdn/divert/isdn_divert.c: In function 'll_callback': drivers/isdn/divert/isdn_divert.c:488:22: error: '%d' directive writing between 1 and 3 bytes into a region of size between 1 and 69 [-Werror=format-overflow=] sprintf(cs->info, "%d 0x%lx %s %s %s %s 0x%x 0x%x %d %d %s\n", ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/isdn/divert/isdn_divert.c:488:22: note: directive argument in the range [0, 255] drivers/isdn/divert/isdn_divert.c:488:4: note: 'sprintf' output 25 or more bytes (assuming 129) into a destination of size 90 This is unlikely to actually cause problems, so let's use snprintf as a simple workaround to shut up the warning and truncate the buffer instead. Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/isdn/divert/isdn_divert.c | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) diff --git a/drivers/isdn/divert/isdn_divert.c b/drivers/isdn/divert/isdn_divert.c index 060d357f107f..6f423bc49d0d 100644 --- a/drivers/isdn/divert/isdn_divert.c +++ b/drivers/isdn/divert/isdn_divert.c @@ -485,18 +485,19 @@ static int isdn_divert_icall(isdn_ctrl *ic) cs->deflect_dest[0] = '\0'; retval = 4; /* only proceed */ } - sprintf(cs->info, "%d 0x%lx %s %s %s %s 0x%x 0x%x %d %d %s\n", - cs->akt_state, - cs->divert_id, - divert_if.drv_to_name(cs->ics.driver), - (ic->command == ISDN_STAT_ICALLW) ? "1" : "0", - cs->ics.parm.setup.phone, - cs->ics.parm.setup.eazmsn, - cs->ics.parm.setup.si1, - cs->ics.parm.setup.si2, - cs->ics.parm.setup.screen, - dv->rule.waittime, - cs->deflect_dest); + snprintf(cs->info, sizeof(cs->info), + "%d 0x%lx %s %s %s %s 0x%x 0x%x %d %d %s\n", + cs->akt_state, + cs->divert_id, + divert_if.drv_to_name(cs->ics.driver), + (ic->command == ISDN_STAT_ICALLW) ? "1" : "0", + cs->ics.parm.setup.phone, + cs->ics.parm.setup.eazmsn, + cs->ics.parm.setup.si1, + cs->ics.parm.setup.si2, + cs->ics.parm.setup.screen, + dv->rule.waittime, + cs->deflect_dest); if ((dv->rule.action == DEFLECT_REPORT) || (dv->rule.action == DEFLECT_REJECT)) { put_info_buffer(cs->info); -- cgit v1.2.3-59-g8ed1b From 73066f6c53fea76f95caadd70d802d24db747303 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 14 Jul 2017 14:07:01 +0200 Subject: net: niu: fix format string overflow warning: We get a warning for the port_name string that might be longer than six characters if we had more than 10 ports: drivers/net/ethernet/sun/niu.c: In function 'niu_put_parent': drivers/net/ethernet/sun/niu.c:9563:21: error: '%d' directive writing between 1 and 3 bytes into a region of size 2 [-Werror=format-overflow=] sprintf(port_name, "port%d", port); ^~~~~~~~ drivers/net/ethernet/sun/niu.c:9563:21: note: directive argument in the range [0, 255] drivers/net/ethernet/sun/niu.c:9563:2: note: 'sprintf' output between 6 and 8 bytes into a destination of size 6 sprintf(port_name, "port%d", port); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/net/ethernet/sun/niu.c: In function 'niu_pci_init_one': drivers/net/ethernet/sun/niu.c:9538:22: error: '%d' directive writing between 1 and 3 bytes into a region of size 2 [-Werror=format-overflow=] sprintf(port_name, "port%d", port); ^~~~~~~~ drivers/net/ethernet/sun/niu.c:9538:22: note: directive argument in the range [0, 255] drivers/net/ethernet/sun/niu.c:9538:3: note: 'sprintf' output between 6 and 8 bytes into a destination of size 6 While we know that the port number is small, there is no harm in making the format string two bytes longer to avoid the warning. Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/ethernet/sun/niu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 46cb7f8955a2..4bb04aaf9650 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -9532,7 +9532,7 @@ static struct niu_parent *niu_get_parent(struct niu *np, p = niu_new_parent(np, id, ptype); if (p) { - char port_name[6]; + char port_name[8]; int err; sprintf(port_name, "port%d", port); @@ -9553,7 +9553,7 @@ static void niu_put_parent(struct niu *np) { struct niu_parent *p = np->parent; u8 port = np->port; - char port_name[6]; + char port_name[8]; BUG_ON(!p || p->ports[port] != np); -- cgit v1.2.3-59-g8ed1b From be9cdf1b97023cf5548bd4f6920bb546272ebabc Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 14 Jul 2017 14:07:02 +0200 Subject: bnx2x: fix format overflow warning gcc notices that large queue numbers would overflow the queue name string: drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c: In function 'bnx2x_get_strings': drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c:3165:25: error: '%d' directive writing between 1 and 10 bytes into a region of size 5 [-Werror=format-overflow=] drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c:3165:25: note: directive argument in the range [0, 2147483647] drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c:3165:5: note: 'sprintf' output between 2 and 11 bytes into a destination of size 5 There is a hard limit in place that makes the number at most two digits, so the code is fine. This changes it to use snprintf() to truncate instead of overflowing, which shuts up that warning. Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index 21bc4bed6b26..1e33abde4a3e 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -3162,7 +3162,8 @@ static void bnx2x_get_strings(struct net_device *dev, u32 stringset, u8 *buf) if (is_multi(bp)) { for_each_eth_queue(bp, i) { memset(queue_name, 0, sizeof(queue_name)); - sprintf(queue_name, "%d", i); + snprintf(queue_name, sizeof(queue_name), + "%d", i); for (j = 0; j < BNX2X_NUM_Q_STATS; j++) snprintf(buf + (k + j)*ETH_GSTRING_LEN, ETH_GSTRING_LEN, -- cgit v1.2.3-59-g8ed1b From c41626ce3113eb2d40b5aa1c4fc2b0cd2785367b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 14 Jul 2017 14:07:03 +0200 Subject: net: thunder_bgx: avoid format string overflow warning gcc warns that the temporary buffer might be too small here: drivers/net/ethernet/cavium/thunder/thunder_bgx.c: In function 'bgx_probe': drivers/net/ethernet/cavium/thunder/thunder_bgx.c:1020:16: error: '%d' directive writing between 1 and 10 bytes into a region of size between 9 and 11 [-Werror=format-overflow=] sprintf(str, "BGX%d LMAC%d mode", bgx->bgx_id, lmacid); ^~~~~~~~~~~~~~~~~~~ drivers/net/ethernet/cavium/thunder/thunder_bgx.c:1020:16: note: directive argument in the range [0, 2147483647] drivers/net/ethernet/cavium/thunder/thunder_bgx.c:1020:3: note: 'sprintf' output between 16 and 27 bytes into a destination of size 20 This probably can't happen, but it can't hurt to make it long enough for the theoretical limit. Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/thunder/thunder_bgx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index a0ca68ce3fbb..79112563a25a 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1008,7 +1008,7 @@ static void bgx_print_qlm_mode(struct bgx *bgx, u8 lmacid) { struct device *dev = &bgx->pdev->dev; struct lmac *lmac; - char str[20]; + char str[27]; if (!bgx->is_dlm && lmacid) return; -- cgit v1.2.3-59-g8ed1b From c7673e4dea9a338e00fa26cdd42d3697e8e22319 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 14 Jul 2017 14:07:04 +0200 Subject: vmxnet3: avoid format strint overflow warning gcc-7 notices that "-event-%d" could be more than 11 characters long if we had larger 'vector' numbers: drivers/net/vmxnet3/vmxnet3_drv.c: In function 'vmxnet3_activate_dev': drivers/net/vmxnet3/vmxnet3_drv.c:2095:40: error: 'sprintf' may write a terminating nul past the end of the destination [-Werror=format-overflow=] sprintf(intr->event_msi_vector_name, "%s-event-%d", ^~~~~~~~~~~~~ drivers/net/vmxnet3/vmxnet3_drv.c:2095:3: note: 'sprintf' output between 9 and 33 bytes into a destination of size 32 The current code is safe, but making the string a little longer is harmless and lets gcc see that it's ok. Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/vmxnet3/vmxnet3_int.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h index ba1c9f93592b..9c51b8be0038 100644 --- a/drivers/net/vmxnet3/vmxnet3_int.h +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -311,7 +311,7 @@ struct vmxnet3_intr { u8 num_intrs; /* # of intr vectors */ u8 event_intr_idx; /* idx of the intr vector for event */ u8 mod_levels[VMXNET3_LINUX_MAX_MSIX_VECT]; /* moderation level */ - char event_msi_vector_name[IFNAMSIZ+11]; + char event_msi_vector_name[IFNAMSIZ+17]; #ifdef CONFIG_PCI_MSI struct msix_entry msix_entries[VMXNET3_LINUX_MAX_MSIX_VECT]; #endif -- cgit v1.2.3-59-g8ed1b From 56c0da495a0b38f8ac0c0c0e3fcc750ea449daea Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 14 Jul 2017 14:07:05 +0200 Subject: liquidio: fix possible eeprom format string overflow gcc reports that the temporary buffer for computing the string length may be too small here: drivers/net/ethernet/cavium/liquidio/lio_ethtool.c: In function 'lio_get_eeprom_len': /drivers/net/ethernet/cavium/liquidio/lio_ethtool.c:345:21: error: 'sprintf' may write a terminating nul past the end of the destination [-Werror=format-overflow=] len = sprintf(buf, "boardname:%s serialnum:%s maj:%lld min:%lld\n", ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/net/ethernet/cavium/liquidio/lio_ethtool.c:345:6: note: 'sprintf' output between 35 and 167 bytes into a destination of size 128 len = sprintf(buf, "boardname:%s serialnum:%s maj:%lld min:%lld\n", This extends it to 192 bytes, which is certainly enough. As far as I could tell, there are no other constraints that require a specific maximum size. Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/liquidio/lio_ethtool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c index 28ecda3d3404..ebd353bc78ff 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c @@ -335,7 +335,7 @@ lio_ethtool_get_channels(struct net_device *dev, static int lio_get_eeprom_len(struct net_device *netdev) { - u8 buf[128]; + u8 buf[192]; struct lio *lio = GET_LIO(netdev); struct octeon_device *oct_dev = lio->oct_dev; struct octeon_board_info *board_info; -- cgit v1.2.3-59-g8ed1b From 10b3bf54406bb7f4e78da9bb2a485c5c986678ad Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 14 Jul 2017 22:07:33 +0800 Subject: sctp: fix an array overflow when all ext chunks are set Marcelo noticed an array overflow caused by commit c28445c3cb07 ("sctp: add reconf_enable in asoc ep and netns"), in which sctp would add SCTP_CID_RECONF into extensions when reconf_enable is set in sctp_make_init and sctp_make_init_ack. Then now when all ext chunks are set, 4 ext chunk ids can be put into extensions array while extensions array size is 3. It would cause a kernel panic because of this overflow. This patch is to fix it by defining extensions array size is 4 in both sctp_make_init and sctp_make_init_ack. Fixes: c28445c3cb07 ("sctp: add reconf_enable in asoc ep and netns") Signed-off-by: Xin Long Signed-off-by: David S. Miller --- net/sctp/sm_make_chunk.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 4e16b02ed832..6110447fe51d 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -228,7 +228,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, sctp_adaptation_ind_param_t aiparam; sctp_supported_ext_param_t ext_param; int num_ext = 0; - __u8 extensions[3]; + __u8 extensions[4]; struct sctp_paramhdr *auth_chunks = NULL, *auth_hmacs = NULL; @@ -396,7 +396,7 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc, sctp_adaptation_ind_param_t aiparam; sctp_supported_ext_param_t ext_param; int num_ext = 0; - __u8 extensions[3]; + __u8 extensions[4]; struct sctp_paramhdr *auth_chunks = NULL, *auth_hmacs = NULL, *auth_random = NULL; -- cgit v1.2.3-59-g8ed1b From 9d53caec84c7c5700e7c1ed744ea584fff55f9ac Mon Sep 17 00:00:00 2001 From: Jane Chu Date: Tue, 11 Jul 2017 12:00:54 -0600 Subject: sparc64: Measure receiver forward progress to avoid send mondo timeout A large sun4v SPARC system may have moments of intensive xcall activities, usually caused by unmapping many pages on many CPUs concurrently. This can flood receivers with CPU mondo interrupts for an extended period, causing some unlucky senders to hit send-mondo timeout. This problem gets worse as cpu count increases because sometimes mappings must be invalidated on all CPUs, and sometimes all CPUs may gang up on a single CPU. But a busy system is not a broken system. In the above scenario, as long as the receiver is making forward progress processing mondo interrupts, the sender should continue to retry. This patch implements the receiver's forward progress meter by introducing a per cpu counter 'cpu_mondo_counter[cpu]' where 'cpu' is in the range of 0..NR_CPUS. The receiver increments its counter as soon as it receives a mondo and the sender tracks the receiver's counter. If the receiver has stopped making forward progress when the retry limit is reached, the sender declares send-mondo-timeout and panic; otherwise, the receiver is allowed to keep making forward progress. In addition, it's been observed that PCIe hotplug events generate Correctable Errors that are handled by hypervisor and then OS. Hypervisor 'borrows' a guest cpu strand briefly to provide the service. If the cpu strand is simultaneously the only cpu targeted by a mondo, it may not be available for the mondo in 20msec, causing SUN4V mondo timeout. It appears that 1 second is the agreed wait time between hypervisor and guest OS, this patch makes the adjustment. Orabug: 25476541 Orabug: 26417466 Signed-off-by: Jane Chu Reviewed-by: Steve Sistare Reviewed-by: Anthony Yznaga Reviewed-by: Rob Gardner Reviewed-by: Thomas Tai Signed-off-by: David S. Miller --- arch/sparc/include/asm/trap_block.h | 1 + arch/sparc/kernel/smp_64.c | 185 ++++++++++++++++++++++-------------- arch/sparc/kernel/sun4v_ivec.S | 15 +++ arch/sparc/kernel/traps_64.c | 1 + 4 files changed, 132 insertions(+), 70 deletions(-) diff --git a/arch/sparc/include/asm/trap_block.h b/arch/sparc/include/asm/trap_block.h index ec9c04de3664..ff05992dae7a 100644 --- a/arch/sparc/include/asm/trap_block.h +++ b/arch/sparc/include/asm/trap_block.h @@ -54,6 +54,7 @@ extern struct trap_per_cpu trap_block[NR_CPUS]; void init_cur_cpu_trap(struct thread_info *); void setup_tba(void); extern int ncpus_probed; +extern u64 cpu_mondo_counter[NR_CPUS]; unsigned long real_hard_smp_processor_id(void); diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index fdf31040a7dc..3218bc43302e 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -622,22 +622,48 @@ retry: } } -/* Multi-cpu list version. */ +#define CPU_MONDO_COUNTER(cpuid) (cpu_mondo_counter[cpuid]) +#define MONDO_USEC_WAIT_MIN 2 +#define MONDO_USEC_WAIT_MAX 100 +#define MONDO_RETRY_LIMIT 500000 + +/* Multi-cpu list version. + * + * Deliver xcalls to 'cnt' number of cpus in 'cpu_list'. + * Sometimes not all cpus receive the mondo, requiring us to re-send + * the mondo until all cpus have received, or cpus are truly stuck + * unable to receive mondo, and we timeout. + * Occasionally a target cpu strand is borrowed briefly by hypervisor to + * perform guest service, such as PCIe error handling. Consider the + * service time, 1 second overall wait is reasonable for 1 cpu. + * Here two in-between mondo check wait time are defined: 2 usec for + * single cpu quick turn around and up to 100usec for large cpu count. + * Deliver mondo to large number of cpus could take longer, we adjusts + * the retry count as long as target cpus are making forward progress. + */ static void hypervisor_xcall_deliver(struct trap_per_cpu *tb, int cnt) { - int retries, this_cpu, prev_sent, i, saw_cpu_error; + int this_cpu, tot_cpus, prev_sent, i, rem; + int usec_wait, retries, tot_retries; + u16 first_cpu = 0xffff; + unsigned long xc_rcvd = 0; unsigned long status; + int ecpuerror_id = 0; + int enocpu_id = 0; u16 *cpu_list; + u16 cpu; this_cpu = smp_processor_id(); - cpu_list = __va(tb->cpu_list_pa); - - saw_cpu_error = 0; - retries = 0; + usec_wait = cnt * MONDO_USEC_WAIT_MIN; + if (usec_wait > MONDO_USEC_WAIT_MAX) + usec_wait = MONDO_USEC_WAIT_MAX; + retries = tot_retries = 0; + tot_cpus = cnt; prev_sent = 0; + do { - int forward_progress, n_sent; + int n_sent, mondo_delivered, target_cpu_busy; status = sun4v_cpu_mondo_send(cnt, tb->cpu_list_pa, @@ -645,94 +671,113 @@ static void hypervisor_xcall_deliver(struct trap_per_cpu *tb, int cnt) /* HV_EOK means all cpus received the xcall, we're done. */ if (likely(status == HV_EOK)) - break; + goto xcall_done; + + /* If not these non-fatal errors, panic */ + if (unlikely((status != HV_EWOULDBLOCK) && + (status != HV_ECPUERROR) && + (status != HV_ENOCPU))) + goto fatal_errors; /* First, see if we made any forward progress. + * + * Go through the cpu_list, count the target cpus that have + * received our mondo (n_sent), and those that did not (rem). + * Re-pack cpu_list with the cpus remain to be retried in the + * front - this simplifies tracking the truly stalled cpus. * * The hypervisor indicates successful sends by setting * cpu list entries to the value 0xffff. + * + * EWOULDBLOCK means some target cpus did not receive the + * mondo and retry usually helps. + * + * ECPUERROR means at least one target cpu is in error state, + * it's usually safe to skip the faulty cpu and retry. + * + * ENOCPU means one of the target cpu doesn't belong to the + * domain, perhaps offlined which is unexpected, but not + * fatal and it's okay to skip the offlined cpu. */ + rem = 0; n_sent = 0; for (i = 0; i < cnt; i++) { - if (likely(cpu_list[i] == 0xffff)) + cpu = cpu_list[i]; + if (likely(cpu == 0xffff)) { n_sent++; + } else if ((status == HV_ECPUERROR) && + (sun4v_cpu_state(cpu) == HV_CPU_STATE_ERROR)) { + ecpuerror_id = cpu + 1; + } else if (status == HV_ENOCPU && !cpu_online(cpu)) { + enocpu_id = cpu + 1; + } else { + cpu_list[rem++] = cpu; + } } - forward_progress = 0; - if (n_sent > prev_sent) - forward_progress = 1; + /* No cpu remained, we're done. */ + if (rem == 0) + break; - prev_sent = n_sent; + /* Otherwise, update the cpu count for retry. */ + cnt = rem; - /* If we get a HV_ECPUERROR, then one or more of the cpus - * in the list are in error state. Use the cpu_state() - * hypervisor call to find out which cpus are in error state. + /* Record the overall number of mondos received by the + * first of the remaining cpus. */ - if (unlikely(status == HV_ECPUERROR)) { - for (i = 0; i < cnt; i++) { - long err; - u16 cpu; + if (first_cpu != cpu_list[0]) { + first_cpu = cpu_list[0]; + xc_rcvd = CPU_MONDO_COUNTER(first_cpu); + } - cpu = cpu_list[i]; - if (cpu == 0xffff) - continue; + /* Was any mondo delivered successfully? */ + mondo_delivered = (n_sent > prev_sent); + prev_sent = n_sent; - err = sun4v_cpu_state(cpu); - if (err == HV_CPU_STATE_ERROR) { - saw_cpu_error = (cpu + 1); - cpu_list[i] = 0xffff; - } - } - } else if (unlikely(status != HV_EWOULDBLOCK)) - goto fatal_mondo_error; + /* or, was any target cpu busy processing other mondos? */ + target_cpu_busy = (xc_rcvd < CPU_MONDO_COUNTER(first_cpu)); + xc_rcvd = CPU_MONDO_COUNTER(first_cpu); - /* Don't bother rewriting the CPU list, just leave the - * 0xffff and non-0xffff entries in there and the - * hypervisor will do the right thing. - * - * Only advance timeout state if we didn't make any - * forward progress. + /* Retry count is for no progress. If we're making progress, + * reset the retry count. */ - if (unlikely(!forward_progress)) { - if (unlikely(++retries > 10000)) - goto fatal_mondo_timeout; - - /* Delay a little bit to let other cpus catch up - * on their cpu mondo queue work. - */ - udelay(2 * cnt); + if (likely(mondo_delivered || target_cpu_busy)) { + tot_retries += retries; + retries = 0; + } else if (unlikely(retries > MONDO_RETRY_LIMIT)) { + goto fatal_mondo_timeout; } - } while (1); - if (unlikely(saw_cpu_error)) - goto fatal_mondo_cpu_error; + /* Delay a little bit to let other cpus catch up on + * their cpu mondo queue work. + */ + if (!mondo_delivered) + udelay(usec_wait); - return; + retries++; + } while (1); -fatal_mondo_cpu_error: - printk(KERN_CRIT "CPU[%d]: SUN4V mondo cpu error, some target cpus " - "(including %d) were in error state\n", - this_cpu, saw_cpu_error - 1); +xcall_done: + if (unlikely(ecpuerror_id > 0)) { + pr_crit("CPU[%d]: SUN4V mondo cpu error, target cpu(%d) was in error state\n", + this_cpu, ecpuerror_id - 1); + } else if (unlikely(enocpu_id > 0)) { + pr_crit("CPU[%d]: SUN4V mondo cpu error, target cpu(%d) does not belong to the domain\n", + this_cpu, enocpu_id - 1); + } return; +fatal_errors: + /* fatal errors include bad alignment, etc */ + pr_crit("CPU[%d]: Args were cnt(%d) cpulist_pa(%lx) mondo_block_pa(%lx)\n", + this_cpu, tot_cpus, tb->cpu_list_pa, tb->cpu_mondo_block_pa); + panic("Unexpected SUN4V mondo error %lu\n", status); + fatal_mondo_timeout: - printk(KERN_CRIT "CPU[%d]: SUN4V mondo timeout, no forward " - " progress after %d retries.\n", - this_cpu, retries); - goto dump_cpu_list_and_out; - -fatal_mondo_error: - printk(KERN_CRIT "CPU[%d]: Unexpected SUN4V mondo error %lu\n", - this_cpu, status); - printk(KERN_CRIT "CPU[%d]: Args were cnt(%d) cpulist_pa(%lx) " - "mondo_block_pa(%lx)\n", - this_cpu, cnt, tb->cpu_list_pa, tb->cpu_mondo_block_pa); - -dump_cpu_list_and_out: - printk(KERN_CRIT "CPU[%d]: CPU list [ ", this_cpu); - for (i = 0; i < cnt; i++) - printk("%u ", cpu_list[i]); - printk("]\n"); + /* some cpus being non-responsive to the cpu mondo */ + pr_crit("CPU[%d]: SUN4V mondo timeout, cpu(%d) made no forward progress after %d retries. Total target cpus(%d).\n", + this_cpu, first_cpu, (tot_retries + retries), tot_cpus); + panic("SUN4V mondo timeout panic\n"); } static void (*xcall_deliver_impl)(struct trap_per_cpu *, int); diff --git a/arch/sparc/kernel/sun4v_ivec.S b/arch/sparc/kernel/sun4v_ivec.S index 559bc5e9c199..34631995859a 100644 --- a/arch/sparc/kernel/sun4v_ivec.S +++ b/arch/sparc/kernel/sun4v_ivec.S @@ -26,6 +26,21 @@ sun4v_cpu_mondo: ldxa [%g0] ASI_SCRATCHPAD, %g4 sub %g4, TRAP_PER_CPU_FAULT_INFO, %g4 + /* Get smp_processor_id() into %g3 */ + sethi %hi(trap_block), %g5 + or %g5, %lo(trap_block), %g5 + sub %g4, %g5, %g3 + srlx %g3, TRAP_BLOCK_SZ_SHIFT, %g3 + + /* Increment cpu_mondo_counter[smp_processor_id()] */ + sethi %hi(cpu_mondo_counter), %g5 + or %g5, %lo(cpu_mondo_counter), %g5 + sllx %g3, 3, %g3 + add %g5, %g3, %g5 + ldx [%g5], %g3 + add %g3, 1, %g3 + stx %g3, [%g5] + /* Get CPU mondo queue base phys address into %g7. */ ldx [%g4 + TRAP_PER_CPU_CPU_MONDO_PA], %g7 diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index 196ee5eb4d48..ad31af1dd726 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -2733,6 +2733,7 @@ void do_getpsr(struct pt_regs *regs) } } +u64 cpu_mondo_counter[NR_CPUS] = {0}; struct trap_per_cpu trap_block[NR_CPUS]; EXPORT_SYMBOL(trap_block); -- cgit v1.2.3-59-g8ed1b From c09abff87f90c81d74b6483837a665f97448a475 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Thu, 13 Jul 2017 18:10:07 +0200 Subject: btrfs: cloned bios must not be iterated by bio_for_each_segment_all We've started using cloned bios more in 4.13, there are some specifics regarding the iteration. Filipe found [1] that the raid56 iterated a cloned bio using bio_for_each_segment_all, which is incorrect. The cloned bios have wrong bi_vcnt and this could lead to silent corruptions. This patch adds assertions to all remaining bio_for_each_segment_all cases. [1] https://patchwork.kernel.org/patch/9838535/ Reviewed-by: Liu Bo Signed-off-by: David Sterba --- fs/btrfs/compression.c | 1 + fs/btrfs/disk-io.c | 1 + fs/btrfs/extent_io.c | 3 +++ fs/btrfs/inode.c | 2 ++ 4 files changed, 7 insertions(+) diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index fcd323eceb5b..8ba1b86c9b72 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -152,6 +152,7 @@ csum_failed: * we have verified the checksum already, set page * checked so the end_io handlers know about it */ + ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, cb->orig_bio, i) SetPageChecked(bvec->bv_page); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b6758892874f..075beedb4352 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -964,6 +964,7 @@ static int btree_csum_one_bio(struct bio *bio) struct btrfs_root *root; int i, ret = 0; + ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, bio, i) { root = BTRFS_I(bvec->bv_page->mapping->host)->root; ret = csum_dirty_buffer(root->fs_info, bvec->bv_page); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 2e6f69908303..a3122fba54e8 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2452,6 +2452,7 @@ static void end_bio_extent_writepage(struct bio *bio) u64 end; int i; + ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; struct inode *inode = page->mapping->host; @@ -2522,6 +2523,7 @@ static void end_bio_extent_readpage(struct bio *bio) int ret; int i; + ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; struct inode *inode = page->mapping->host; @@ -3675,6 +3677,7 @@ static void end_bio_extent_buffer_writepage(struct bio *bio) struct extent_buffer *eb; int i, done; + ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 5d3c6ac960fd..529437c337b4 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8060,6 +8060,7 @@ static void btrfs_retry_endio_nocsum(struct bio *bio) ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(inode)); done->uptodate = 1; + ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, bio, i) clean_io_failure(BTRFS_I(inode)->root->fs_info, failure_tree, io_tree, done->start, bvec->bv_page, @@ -8151,6 +8152,7 @@ static void btrfs_retry_endio(struct bio *bio) io_tree = &BTRFS_I(inode)->io_tree; failure_tree = &BTRFS_I(inode)->io_failure_tree; + ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, bio, i) { ret = __readpage_endio_check(inode, io_bio, i, bvec->bv_page, bvec->bv_offset, done->start, -- cgit v1.2.3-59-g8ed1b From e8f5b395d5332b5d720d62d33d6e06836392fd85 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Thu, 13 Jul 2017 17:42:15 +0200 Subject: btrfs: btrfs_create_repair_bio never fails, skip error handling As the function uses the non-failing bio allocation, we can remove error handling from the callers as well. Signed-off-by: David Sterba Reviewed-by: Liu Bo Signed-off-by: David Sterba --- fs/btrfs/extent_io.c | 4 ---- fs/btrfs/inode.c | 4 ---- 2 files changed, 8 deletions(-) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index a3122fba54e8..3a9ef02cad49 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2394,10 +2394,6 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset, start - page_offset(page), (int)phy_offset, failed_bio->bi_end_io, NULL); - if (!bio) { - free_io_failure(failure_tree, tree, failrec); - return -EIO; - } bio_set_op_attrs(bio, REQ_OP_READ, read_mode); btrfs_debug(btrfs_sb(inode->i_sb), diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 529437c337b4..eb495e956d53 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8017,10 +8017,6 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio, isector >>= inode->i_sb->s_blocksize_bits; bio = btrfs_create_repair_bio(inode, failed_bio, failrec, page, pgoff, isector, repair_endio, repair_arg); - if (!bio) { - free_io_failure(failure_tree, io_tree, failrec); - return -EIO; - } bio_set_op_attrs(bio, REQ_OP_READ, read_mode); btrfs_debug(BTRFS_I(inode)->root->fs_info, -- cgit v1.2.3-59-g8ed1b From c3cfb656307583ddfea45375c10183737593c195 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Thu, 13 Jul 2017 15:00:50 -0700 Subject: Btrfs: fix unexpected return value of bio_readpage_error With blk_status_t conversion (that are now present in master), bio_readpage_error() may return 1 as now ->submit_bio_hook() may not set %ret if it runs without problems. This fixes that unexpected return value by changing btrfs_check_repairable() to return a bool instead of updating %ret, and patch is applicable to both codebases with and without blk_status_t. Signed-off-by: Liu Bo Reviewed-by: Nikolay Borisov Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/extent_io.c | 12 ++++++------ fs/btrfs/extent_io.h | 4 ++-- 2 files changed, 8 insertions(+), 8 deletions(-) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 3a9ef02cad49..eb484a0d1320 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2257,7 +2257,7 @@ int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end, return 0; } -int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio, +bool btrfs_check_repairable(struct inode *inode, struct bio *failed_bio, struct io_failure_record *failrec, int failed_mirror) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); @@ -2273,7 +2273,7 @@ int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio, btrfs_debug(fs_info, "Check Repairable: cannot repair, num_copies=%d, next_mirror %d, failed_mirror %d", num_copies, failrec->this_mirror, failed_mirror); - return 0; + return false; } /* @@ -2314,10 +2314,10 @@ int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio, btrfs_debug(fs_info, "Check Repairable: (fail) num_copies=%d, next_mirror %d, failed_mirror %d", num_copies, failrec->this_mirror, failed_mirror); - return 0; + return false; } - return 1; + return true; } @@ -2380,8 +2380,8 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset, if (ret) return ret; - ret = btrfs_check_repairable(inode, failed_bio, failrec, failed_mirror); - if (!ret) { + if (!btrfs_check_repairable(inode, failed_bio, failrec, + failed_mirror)) { free_io_failure(failure_tree, tree, failrec); return -EIO; } diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index aeafdb35d90b..cfdbb9efaaed 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -539,8 +539,8 @@ void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start, u64 end); int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end, struct io_failure_record **failrec_ret); -int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio, - struct io_failure_record *failrec, int fail_mirror); +bool btrfs_check_repairable(struct inode *inode, struct bio *failed_bio, + struct io_failure_record *failrec, int fail_mirror); struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio, struct io_failure_record *failrec, struct page *page, int pg_offset, int icsum, -- cgit v1.2.3-59-g8ed1b From a966ac73d7772a2b067c50fa16bbbfe418fc6374 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sun, 14 May 2017 07:49:15 -0300 Subject: bcache.txt: standardize document format Each text file under Documentation follows a different format. Some doesn't even have titles! Change its representation to follow the adopted standard, using ReST markups for it to be parseable by Sphinx: - Add a title for the document; - Use a list for the listed URLs; - mark literal blocks; - adjust whitespaces; - Don't capitalize section titles. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Jonathan Corbet --- Documentation/bcache.txt | 190 ++++++++++++++++++++++++++--------------------- 1 file changed, 107 insertions(+), 83 deletions(-) diff --git a/Documentation/bcache.txt b/Documentation/bcache.txt index a9259b562d5c..c0ce64d75bbf 100644 --- a/Documentation/bcache.txt +++ b/Documentation/bcache.txt @@ -1,10 +1,15 @@ +============================ +A block layer cache (bcache) +============================ + Say you've got a big slow raid 6, and an ssd or three. Wouldn't it be nice if you could use them as cache... Hence bcache. Wiki and git repositories are at: - http://bcache.evilpiepirate.org - http://evilpiepirate.org/git/linux-bcache.git - http://evilpiepirate.org/git/bcache-tools.git + + - http://bcache.evilpiepirate.org + - http://evilpiepirate.org/git/linux-bcache.git + - http://evilpiepirate.org/git/bcache-tools.git It's designed around the performance characteristics of SSDs - it only allocates in erase block sized buckets, and it uses a hybrid btree/log to track cached @@ -37,17 +42,19 @@ to be flushed. Getting started: You'll need make-bcache from the bcache-tools repository. Both the cache device -and backing device must be formatted before use. +and backing device must be formatted before use:: + make-bcache -B /dev/sdb make-bcache -C /dev/sdc make-bcache has the ability to format multiple devices at the same time - if you format your backing devices and cache device at the same time, you won't -have to manually attach: +have to manually attach:: + make-bcache -B /dev/sda /dev/sdb -C /dev/sdc bcache-tools now ships udev rules, and bcache devices are known to the kernel -immediately. Without udev, you can manually register devices like this: +immediately. Without udev, you can manually register devices like this:: echo /dev/sdb > /sys/fs/bcache/register echo /dev/sdc > /sys/fs/bcache/register @@ -60,16 +67,16 @@ slow devices as bcache backing devices without a cache, and you can choose to ad a caching device later. See 'ATTACHING' section below. -The devices show up as: +The devices show up as:: /dev/bcache -As well as (with udev): +As well as (with udev):: /dev/bcache/by-uuid/ /dev/bcache/by-label/