diff options
Diffstat (limited to '')
40 files changed, 1208 insertions, 474 deletions
diff --git a/lib/Kconfig b/lib/Kconfig index 8cc8e8722a3f..c7ad7a5b3535 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -29,6 +29,13 @@ config CRC16 the kernel tree does. Such modules that use library CRC16 functions require M here. +config CRC_T10DIF + tristate "CRC calculation for the T10 Data Integrity Field" + help + This option is only needed if a module that's not in the + kernel tree needs to calculate CRC checks for use with the + SCSI data integrity subsystem. + config CRC_ITU_T tristate "CRC ITU-T V.41 functions" help diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index d2099f41aa1e..e1d4764435ed 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -74,6 +74,9 @@ config DEBUG_FS debugging files into. Enable this option to be able to read and write to these files. + For detailed documentation on the debugfs API, see + Documentation/DocBook/filesystems. + If unsure, say N. config HEADERS_CHECK @@ -147,7 +150,7 @@ config DETECT_SOFTLOCKUP help Say Y here to enable the kernel to detect "soft lockups", which are bugs that cause the kernel to loop in kernel - mode for more than 10 seconds, without giving other tasks a + mode for more than 60 seconds, without giving other tasks a chance to run. When a soft-lockup is detected, the kernel will print the @@ -159,6 +162,30 @@ config DETECT_SOFTLOCKUP can be detected via the NMI-watchdog, on platforms that support it.) +config BOOTPARAM_SOFTLOCKUP_PANIC + bool "Panic (Reboot) On Soft Lockups" + depends on DETECT_SOFTLOCKUP + help + Say Y here to enable the kernel to panic on "soft lockups", + which are bugs that cause the kernel to loop in kernel + mode for more than 60 seconds, without giving other tasks a + chance to run. + + The panic can be used in combination with panic_timeout, + to cause the system to reboot automatically after a + lockup has been detected. This feature is useful for + high-availability systems that have uptime guarantees and + where a lockup must be resolved ASAP. + + Say N if unsure. + +config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE + int + depends on DETECT_SOFTLOCKUP + range 0 1 + default 0 if !BOOTPARAM_SOFTLOCKUP_PANIC + default 1 if BOOTPARAM_SOFTLOCKUP_PANIC + config SCHED_DEBUG bool "Collect scheduler debugging info" depends on DEBUG_KERNEL && PROC_FS @@ -419,7 +446,6 @@ config DEBUG_LOCKING_API_SELFTESTS config STACKTRACE bool - depends on DEBUG_KERNEL depends on STACKTRACE_SUPPORT config DEBUG_KOBJECT @@ -479,6 +505,18 @@ config DEBUG_WRITECOUNT If unsure, say N. +config DEBUG_MEMORY_INIT + bool "Debug memory initialisation" if EMBEDDED + default !EMBEDDED + help + Enable this for additional checks during memory initialisation. + The sanity checks verify aspects of the VM such as the memory model + and other information provided by the architecture. Verbose + information will be printed at KERN_DEBUG loglevel depending + on the mminit_loglevel= command-line option. + + If unsure, say Y + config DEBUG_LIST bool "Debug linked list manipulation" depends on DEBUG_KERNEL @@ -531,16 +569,34 @@ config BOOT_PRINTK_DELAY config RCU_TORTURE_TEST tristate "torture tests for RCU" depends on DEBUG_KERNEL - depends on m default n help This option provides a kernel module that runs torture tests on the RCU infrastructure. The kernel module may be built after the fact on the running kernel to be tested, if desired. + Say Y here if you want RCU torture tests to be built into + the kernel. Say M if you want the RCU torture tests to build as a module. Say N if you are unsure. +config RCU_TORTURE_TEST_RUNNABLE + bool "torture tests for RCU runnable by default" + depends on RCU_TORTURE_TEST = y + default n + help + This option provides a way to build the RCU torture tests + directly into the kernel without them starting up at boot + time. You can use /proc/sys/kernel/rcutorture_runnable + to manually override this setting. This /proc file is + available only when the RCU torture tests have been built + into the kernel. + + Say Y here if you want the RCU torture tests to start during + boot (you probably don't). + Say N here if you want the RCU torture tests to start only + after being manually enabled via /proc. + config KPROBES_SANITY_TEST bool "Kprobes sanity tests" depends on DEBUG_KERNEL @@ -563,6 +619,9 @@ config BACKTRACE_SELF_TEST for distributions or general kernels, but only for kernel developers working on architecture code. + Note that if you want to also test saved backtraces, you will + have to enable STACKTRACE as well. + Say N if you are unsure. config LKDTM @@ -634,6 +693,8 @@ config LATENCYTOP Enable this option if you want to use the LatencyTOP tool to find out which userspace is blocking on what kernel operations. +source kernel/trace/Kconfig + config PROVIDE_OHCI1394_DMA_INIT bool "Remote debugging over FireWire early on boot" depends on PCI && X86 diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb index f2e01ac5ab09..2cfd2721f7ed 100644 --- a/lib/Kconfig.kgdb +++ b/lib/Kconfig.kgdb @@ -1,4 +1,7 @@ +config HAVE_ARCH_KGDB + bool + menuconfig KGDB bool "KGDB: kernel debugging with remote gdb" select FRAME_POINTER @@ -10,15 +13,10 @@ menuconfig KGDB at http://kgdb.sourceforge.net as well as in DocBook form in Documentation/DocBook/. If unsure, say N. -config HAVE_ARCH_KGDB_SHADOW_INFO - bool - -config HAVE_ARCH_KGDB - bool +if KGDB config KGDB_SERIAL_CONSOLE tristate "KGDB: use kgdb over the serial console" - depends on KGDB select CONSOLE_POLL select MAGIC_SYSRQ default y @@ -28,7 +26,6 @@ config KGDB_SERIAL_CONSOLE config KGDB_TESTS bool "KGDB: internal test suite" - depends on KGDB default n help This is a kgdb I/O module specifically designed to test @@ -56,3 +53,5 @@ config KGDB_TESTS_BOOT_STRING boot. See the drivers/misc/kgdbts.c for detailed information about other strings you could use beyond the default of V1F100. + +endif # KGDB diff --git a/lib/Makefile b/lib/Makefile index 74b0cfb1fcc3..3b1f94bbe9de 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -2,18 +2,23 @@ # Makefile for some libs needed in the kernel. # +ifdef CONFIG_FTRACE +ORIG_CFLAGS := $(KBUILD_CFLAGS) +KBUILD_CFLAGS = $(subst -pg,,$(ORIG_CFLAGS)) +endif + lib-y := ctype.o string.o vsprintf.o cmdline.o \ rbtree.o radix-tree.o dump_stack.o \ idr.o int_sqrt.o extable.o prio_tree.o \ sha1.o irq_regs.o reciprocal_div.o argv_split.o \ - proportions.o prio_heap.o ratelimit.o + proportions.o prio_heap.o ratelimit.o show_mem.o lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o lib-y += kobject.o kref.o klist.o -obj-y += div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \ +obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \ bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o ifeq ($(CONFIG_DEBUG_KOBJECT),y) @@ -45,6 +50,7 @@ endif obj-$(CONFIG_BITREVERSE) += bitrev.o obj-$(CONFIG_CRC_CCITT) += crc-ccitt.o obj-$(CONFIG_CRC16) += crc16.o +obj-$(CONFIG_CRC_T10DIF)+= crc-t10dif.o obj-$(CONFIG_CRC_ITU_T) += crc-itu-t.o obj-$(CONFIG_CRC32) += crc32.o obj-$(CONFIG_CRC7) += crc7.o @@ -72,6 +78,8 @@ lib-$(CONFIG_GENERIC_BUG) += bug.o obj-$(CONFIG_HAVE_LMB) += lmb.o +obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o + hostprogs-y := gen_crc32table clean-files := crc32table.h diff --git a/lib/bcd.c b/lib/bcd.c new file mode 100644 index 000000000000..d74257fd0fe7 --- /dev/null +++ b/lib/bcd.c @@ -0,0 +1,14 @@ +#include <linux/bcd.h> +#include <linux/module.h> + +unsigned bcd2bin(unsigned char val) +{ + return (val & 0x0f) + (val >> 4) * 10; +} +EXPORT_SYMBOL(bcd2bin); + +unsigned char bin2bcd(unsigned val) +{ + return ((val / 10) << 4) + val % 10; +} +EXPORT_SYMBOL(bin2bcd); diff --git a/lib/bitmap.c b/lib/bitmap.c index c4cb48f77f0c..482df94ea21e 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -316,22 +316,6 @@ int bitmap_scnprintf(char *buf, unsigned int buflen, EXPORT_SYMBOL(bitmap_scnprintf); /** - * bitmap_scnprintf_len - return buffer length needed to convert - * bitmap to an ASCII hex string. - * @len: number of bits to be converted - */ -int bitmap_scnprintf_len(unsigned int len) -{ - /* we need 9 chars per word for 32 bit words (8 hexdigits + sep/null) */ - int bitslen = ALIGN(len, CHUNKSZ); - int wordlen = CHUNKSZ / 4; - int buflen = (bitslen / wordlen) * (wordlen + 1) * sizeof(char); - - return buflen; -} -EXPORT_SYMBOL(bitmap_scnprintf_len); - -/** * __bitmap_parse - convert an ASCII hex string into a bitmap. * @buf: pointer to buffer containing string. * @buflen: buffer size in bytes. If string is smaller than this diff --git a/lib/bitrev.c b/lib/bitrev.c index 989aff73f881..3956203456d4 100644 --- a/lib/bitrev.c +++ b/lib/bitrev.c @@ -42,10 +42,11 @@ const u8 byte_rev_table[256] = { }; EXPORT_SYMBOL_GPL(byte_rev_table); -static __always_inline u16 bitrev16(u16 x) +u16 bitrev16(u16 x) { return (bitrev8(x & 0xff) << 8) | bitrev8(x >> 8); } +EXPORT_SYMBOL(bitrev16); /** * bitrev32 - reverse the order of bits in a u32 value diff --git a/lib/bug.c b/lib/bug.c index 530f38f55787..bfeafd60ee9f 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -37,6 +37,7 @@ */ #include <linux/list.h> #include <linux/module.h> +#include <linux/kernel.h> #include <linux/bug.h> #include <linux/sched.h> @@ -149,6 +150,7 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs) (void *)bugaddr); show_regs(regs); + add_taint(TAINT_WARN); return BUG_TRAP_TYPE_WARN; } diff --git a/lib/cmdline.c b/lib/cmdline.c index f596c08d213a..5ba8a942a478 100644 --- a/lib/cmdline.c +++ b/lib/cmdline.c @@ -116,7 +116,7 @@ char *get_options(const char *str, int nints, int *ints) /** * memparse - parse a string with mem suffixes into a number * @ptr: Where parse begins - * @retptr: (output) Pointer to next char after parse completes + * @retptr: (output) Optional pointer to next char after parse completes * * Parses a string into a number. The number stored at @ptr is * potentially suffixed with %K (for kilobytes, or 1024 bytes), @@ -126,11 +126,13 @@ char *get_options(const char *str, int nints, int *ints) * megabyte, or one gigabyte, respectively. */ -unsigned long long memparse (char *ptr, char **retptr) +unsigned long long memparse(char *ptr, char **retptr) { - unsigned long long ret = simple_strtoull (ptr, retptr, 0); + char *endptr; /* local pointer to end of parsed string */ - switch (**retptr) { + unsigned long long ret = simple_strtoull(ptr, &endptr, 0); + + switch (*endptr) { case 'G': case 'g': ret <<= 10; @@ -140,10 +142,14 @@ unsigned long long memparse (char *ptr, char **retptr) case 'K': case 'k': ret <<= 10; - (*retptr)++; + endptr++; default: break; } + + if (retptr) + *retptr = endptr; + return ret; } diff --git a/lib/cpumask.c b/lib/cpumask.c index bb4f76d3c3e7..5f97dc25ef9c 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -15,6 +15,15 @@ int __next_cpu(int n, const cpumask_t *srcp) } EXPORT_SYMBOL(__next_cpu); +#if NR_CPUS > 64 +int __next_cpu_nr(int n, const cpumask_t *srcp) +{ + return min_t(int, nr_cpu_ids, + find_next_bit(srcp->bits, nr_cpu_ids, n+1)); +} +EXPORT_SYMBOL(__next_cpu_nr); +#endif + int __any_online_cpu(const cpumask_t *mask) { int cpu; diff --git a/lib/crc-t10dif.c b/lib/crc-t10dif.c new file mode 100644 index 000000000000..fbbd66ed86cd --- /dev/null +++ b/lib/crc-t10dif.c @@ -0,0 +1,67 @@ +/* + * T10 Data Integrity Field CRC16 calculation + * + * Copyright (c) 2007 Oracle Corporation. All rights reserved. + * Written by Martin K. Petersen <martin.petersen@oracle.com> + * + * This source code is licensed under the GNU General Public License, + * Version 2. See the file COPYING for more details. + */ + +#include <linux/types.h> +#include <linux/module.h> +#include <linux/crc-t10dif.h> + +/* Table generated using the following polynomium: + * x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x + 1 + * gt: 0x8bb7 + */ +static const __u16 t10_dif_crc_table[256] = { + 0x0000, 0x8BB7, 0x9CD9, 0x176E, 0xB205, 0x39B2, 0x2EDC, 0xA56B, + 0xEFBD, 0x640A, 0x7364, 0xF8D3, 0x5DB8, 0xD60F, 0xC161, 0x4AD6, + 0x54CD, 0xDF7A, 0xC814, 0x43A3, 0xE6C8, 0x6D7F, 0x7A11, 0xF1A6, + 0xBB70, 0x30C7, 0x27A9, 0xAC1E, 0x0975, 0x82C2, 0x95AC, 0x1E1B, + 0xA99A, 0x222D, 0x3543, 0xBEF4, 0x1B9F, 0x9028, 0x8746, 0x0CF1, + 0x4627, 0xCD90, 0xDAFE, 0x5149, 0xF422, 0x7F95, 0x68FB, 0xE34C, + 0xFD57, 0x76E0, 0x618E, 0xEA39, 0x4F52, 0xC4E5, 0xD38B, 0x583C, + 0x12EA, 0x995D, 0x8E33, 0x0584, 0xA0EF, 0x2B58, 0x3C36, 0xB781, + 0xD883, 0x5334, 0x445A, 0xCFED, 0x6A86, 0xE131, 0xF65F, 0x7DE8, + 0x373E, 0xBC89, 0xABE7, 0x2050, 0x853B, 0x0E8C, 0x19E2, 0x9255, + 0x8C4E, 0x07F9, 0x1097, 0x9B20, 0x3E4B, 0xB5FC, 0xA292, 0x2925, + 0x63F3, 0xE844, 0xFF2A, 0x749D, 0xD1F6, 0x5A41, 0x4D2F, 0xC698, + 0x7119, 0xFAAE, 0xEDC0, 0x6677, 0xC31C, 0x48AB, 0x5FC5, 0xD472, + 0x9EA4, 0x1513, 0x027D, 0x89CA, 0x2CA1, 0xA716, 0xB078, 0x3BCF, + 0x25D4, 0xAE63, 0xB90D, 0x32BA, 0x97D1, 0x1C66, 0x0B08, 0x80BF, + 0xCA69, 0x41DE, 0x56B0, 0xDD07, 0x786C, 0xF3DB, 0xE4B5, 0x6F02, + 0x3AB1, 0xB106, 0xA668, 0x2DDF, 0x88B4, 0x0303, 0x146D, 0x9FDA, + 0xD50C, 0x5EBB, 0x49D5, 0xC262, 0x6709, 0xECBE, 0xFBD0, 0x7067, + 0x6E7C, 0xE5CB, 0xF2A5, 0x7912, 0xDC79, 0x57CE, 0x40A0, 0xCB17, + 0x81C1, 0x0A76, 0x1D18, 0x96AF, 0x33C4, 0xB873, 0xAF1D, 0x24AA, + 0x932B, 0x189C, 0x0FF2, 0x8445, 0x212E, 0xAA99, 0xBDF7, 0x3640, + 0x7C96, 0xF721, 0xE04F, 0x6BF8, 0xCE93, 0x4524, 0x524A, 0xD9FD, + 0xC7E6, 0x4C51, 0x5B3F, 0xD088, 0x75E3, 0xFE54, 0xE93A, 0x628D, + 0x285B, 0xA3EC, 0xB482, 0x3F35, 0x9A5E, 0x11E9, 0x0687, 0x8D30, + 0xE232, 0x6985, 0x7EEB, 0xF55C, 0x5037, 0xDB80, 0xCCEE, 0x4759, + 0x0D8F, 0x8638, 0x9156, 0x1AE1, 0xBF8A, 0x343D, 0x2353, 0xA8E4, + 0xB6FF, 0x3D48, 0x2A26, 0xA191, 0x04FA, 0x8F4D, 0x9823, 0x1394, + 0x5942, 0xD2F5, 0xC59B, 0x4E2C, 0xEB47, 0x60F0, 0x779E, 0xFC29, + 0x4BA8, 0xC01F, 0xD771, 0x5CC6, 0xF9AD, 0x721A, 0x6574, 0xEEC3, + 0xA415, 0x2FA2, 0x38CC, 0xB37B, 0x1610, 0x9DA7, 0x8AC9, 0x017E, + 0x1F65, 0x94D2, 0x83BC, 0x080B, 0xAD60, 0x26D7, 0x31B9, 0xBA0E, + 0xF0D8, 0x7B6F, 0x6C01, 0xE7B6, 0x42DD, 0xC96A, 0xDE04, 0x55B3 +}; + +__u16 crc_t10dif(const unsigned char *buffer, size_t len) +{ + __u16 crc = 0; + unsigned int i; + + for (i = 0 ; i < len ; i++) + crc = (crc << 8) ^ t10_dif_crc_table[((crc >> 8) ^ buffer[i]) & 0xff]; + + return crc; +} +EXPORT_SYMBOL(crc_t10dif); + +MODULE_DESCRIPTION("T10 DIF CRC calculation"); +MODULE_LICENSE("GPL"); diff --git a/lib/debugobjects.c b/lib/debugobjects.c index a76a5e122ae1..45a6bde762d1 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -68,6 +68,7 @@ static int fill_pool(void) { gfp_t gfp = GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN; struct debug_obj *new; + unsigned long flags; if (likely(obj_pool_free >= ODEBUG_POOL_MIN_LEVEL)) return obj_pool_free; @@ -81,10 +82,10 @@ static int fill_pool(void) if (!new) return obj_pool_free; - spin_lock(&pool_lock); + spin_lock_irqsave(&pool_lock, flags); hlist_add_head(&new->node, &obj_pool); obj_pool_free++; - spin_unlock(&pool_lock); + spin_unlock_irqrestore(&pool_lock, flags); } return obj_pool_free; } @@ -110,16 +111,13 @@ static struct debug_obj *lookup_object(void *addr, struct debug_bucket *b) } /* - * Allocate a new object. If the pool is empty and no refill possible, - * switch off the debugger. + * Allocate a new object. If the pool is empty, switch off the debugger. */ static struct debug_obj * alloc_object(void *addr, struct debug_bucket *b, struct debug_obj_descr *descr) { struct debug_obj *obj = NULL; - int retry = 0; -repeat: spin_lock(&pool_lock); if (obj_pool.first) { obj = hlist_entry(obj_pool.first, typeof(*obj), node); @@ -141,9 +139,6 @@ repeat: } spin_unlock(&pool_lock); - if (fill_pool() && !obj && !retry++) - goto repeat; - return obj; } @@ -210,9 +205,8 @@ static void debug_print_object(struct debug_obj *obj, char *msg) if (limit < 5 && obj->descr != descr_test) { limit++; - printk(KERN_ERR "ODEBUG: %s %s object type: %s\n", msg, + WARN(1, KERN_ERR "ODEBUG: %s %s object type: %s\n", msg, obj_states[obj->state], obj->descr->name); - WARN_ON(1); } debug_objects_warnings++; } @@ -231,15 +225,13 @@ debug_object_fixup(int (*fixup)(void *addr, enum debug_obj_state state), static void debug_object_is_on_stack(void *addr, int onstack) { - void *stack = current->stack; int is_on_stack; static int limit; if (limit > 4) return; - is_on_stack = (addr >= stack && addr < (stack + THREAD_SIZE)); - + is_on_stack = object_is_on_stack(addr); if (is_on_stack == onstack) return; @@ -261,6 +253,8 @@ __debug_object_init(void *addr, struct debug_obj_descr *descr, int onstack) struct debug_obj *obj; unsigned long flags; + fill_pool(); + db = get_bucket((unsigned long) addr); spin_lock_irqsave(&db->lock, flags); @@ -738,26 +732,22 @@ check_results(void *addr, enum debug_obj_state state, int fixups, int warnings) obj = lookup_object(addr, db); if (!obj && state != ODEBUG_STATE_NONE) { - printk(KERN_ERR "ODEBUG: selftest object not found\n"); - WARN_ON(1); + WARN(1, KERN_ERR "ODEBUG: selftest object not found\n"); goto out; } if (obj && obj->state != state) { - printk(KERN_ERR "ODEBUG: selftest wrong state: %d != %d\n", + WARN(1, KERN_ERR "ODEBUG: selftest wrong state: %d != %d\n", obj->state, state); - WARN_ON(1); goto out; } if (fixups != debug_objects_fixups) { - printk(KERN_ERR "ODEBUG: selftest fixups failed %d != %d\n", + WARN(1, KERN_ERR "ODEBUG: selftest fixups failed %d != %d\n", fixups, debug_objects_fixups); - WARN_ON(1); goto out; } if (warnings != debug_objects_warnings) { - printk(KERN_ERR "ODEBUG: selftest warnings failed %d != %d\n", + WARN(1, KERN_ERR "ODEBUG: selftest warnings failed %d != %d\n", warnings, debug_objects_warnings); - WARN_ON(1); goto out; } res = 0; diff --git a/lib/devres.c b/lib/devres.c index 26c87c49d776..72c8909006da 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -2,7 +2,7 @@ #include <linux/io.h> #include <linux/module.h> -static void devm_ioremap_release(struct device *dev, void *res) +void devm_ioremap_release(struct device *dev, void *res) { iounmap(*(void __iomem **)res); } diff --git a/lib/div64.c b/lib/div64.c index bb5bd0c0f030..a111eb8de9cf 100644 --- a/lib/div64.c +++ b/lib/div64.c @@ -98,3 +98,13 @@ EXPORT_SYMBOL(div64_u64); #endif #endif /* BITS_PER_LONG == 32 */ + +/* + * Iterative div/mod for use when dividend is not expected to be much + * bigger than divisor. + */ +u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder) +{ + return __iter_div_u64_rem(dividend, divisor, remainder); +} +EXPORT_SYMBOL(iter_div_u64_rem); diff --git a/lib/hexdump.c b/lib/hexdump.c index 343546550dc9..f07c0db81d26 100644 --- a/lib/hexdump.c +++ b/lib/hexdump.c @@ -12,6 +12,9 @@ #include <linux/kernel.h> #include <linux/module.h> +const char hex_asc[] = "0123456789abcdef"; +EXPORT_SYMBOL(hex_asc); + /** * hex_dump_to_buffer - convert a blob of data to "hex ASCII" in memory * @buf: data blob to dump @@ -93,8 +96,8 @@ void hex_dump_to_buffer(const void *buf, size_t len, int rowsize, for (j = 0; (j < rowsize) && (j < len) && (lx + 4) < linebuflen; j++) { ch = ptr[j]; - linebuf[lx++] = hex_asc(ch >> 4); - linebuf[lx++] = hex_asc(ch & 0x0f); + linebuf[lx++] = hex_asc_hi(ch); + linebuf[lx++] = hex_asc_lo(ch); linebuf[lx++] = ' '; } ascii_column = 3 * rowsize + 2; diff --git a/lib/idr.c b/lib/idr.c index 7a02e173f027..e728c7fccc4d 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -6,6 +6,8 @@ * Modified by George Anzinger to reuse immediately and to use * find bit instructions. Also removed _irq on spinlocks. * + * Modified by Nadia Derbey to make it RCU safe. + * * Small id to pointer translation service. * * It uses a radix tree like structure as a sparse array indexed @@ -35,7 +37,7 @@ static struct kmem_cache *idr_layer_cache; -static struct idr_layer *alloc_layer(struct idr *idp) +static struct idr_layer *get_from_free_list(struct idr *idp) { struct idr_layer *p; unsigned long flags; @@ -50,15 +52,28 @@ static struct idr_layer *alloc_layer(struct idr *idp) return(p); } +static void idr_layer_rcu_free(struct rcu_head *head) +{ + struct idr_layer *layer; + + layer = container_of(head, struct idr_layer, rcu_head); + kmem_cache_free(idr_layer_cache, layer); +} + +static inline void free_layer(struct idr_layer *p) +{ + call_rcu(&p->rcu_head, idr_layer_rcu_free); +} + /* only called when idp->lock is held */ -static void __free_layer(struct idr *idp, struct idr_layer *p) +static void __move_to_free_list(struct idr *idp, struct idr_layer *p) { p->ary[0] = idp->id_free; idp->id_free = p; idp->id_free_cnt++; } -static void free_layer(struct idr *idp, struct idr_layer *p) +static void move_to_free_list(struct idr *idp, struct idr_layer *p) { unsigned long flags; @@ -66,7 +81,7 @@ static void free_layer(struct idr *idp, struct idr_layer *p) * Depends on the return element being zeroed. */ spin_lock_irqsave(&idp->lock, flags); - __free_layer(idp, p); + __move_to_free_list(idp, p); spin_unlock_irqrestore(&idp->lock, flags); } @@ -96,7 +111,7 @@ static void idr_mark_full(struct idr_layer **pa, int id) * @gfp_mask: memory allocation flags * * This function should be called prior to locking and calling the - * following function. It preallocates enough memory to satisfy + * idr_get_new* functions. It preallocates enough memory to satisfy * the worst possible allocation. * * If the system is REALLY out of memory this function returns 0, @@ -109,7 +124,7 @@ int idr_pre_get(struct idr *idp, gfp_t gfp_mask) new = kmem_cache_alloc(idr_layer_cache, gfp_mask); if (new == NULL) return (0); - free_layer(idp, new); + move_to_free_list(idp, new); } return 1; } @@ -143,7 +158,7 @@ static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa) /* if already at the top layer, we need to grow */ if (!(p = pa[l])) { *starting_id = id; - return -2; + return IDR_NEED_TO_GROW; } /* If we need to go up one layer, continue the @@ -160,16 +175,17 @@ static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa) id = ((id >> sh) ^ n ^ m) << sh; } if ((id >= MAX_ID_BIT) || (id < 0)) - return -3; + return IDR_NOMORE_SPACE; if (l == 0) break; /* * Create the layer below if it is missing. */ if (!p->ary[m]) { - if (!(new = alloc_layer(idp))) + new = get_from_free_list(idp); + if (!new) return -1; - p->ary[m] = new; + rcu_assign_pointer(p->ary[m], new); p->count++; } pa[l--] = p; @@ -192,7 +208,7 @@ build_up: p = idp->top; layers = idp->layers; if (unlikely(!p)) { - if (!(p = alloc_layer(idp))) + if (!(p = get_from_free_list(idp))) return -1; layers = 1; } @@ -204,7 +220,7 @@ build_up: layers++; if (!p->count) continue; - if (!(new = alloc_layer(idp))) { + if (!(new = get_from_free_list(idp))) { /* * The allocation failed. If we built part of * the structure tear it down. @@ -214,7 +230,7 @@ build_up: p = p->ary[0]; new->ary[0] = NULL; new->bitmap = new->count = 0; - __free_layer(idp, new); + __move_to_free_list(idp, new); } spin_unlock_irqrestore(&idp->lock, flags); return -1; @@ -225,10 +241,10 @@ build_up: __set_bit(0, &new->bitmap); p = new; } - idp->top = p; + rcu_assign_pointer(idp->top, p); idp->layers = layers; v = sub_alloc(idp, &id, pa); - if (v == -2) + if (v == IDR_NEED_TO_GROW) goto build_up; return(v); } @@ -244,7 +260,8 @@ static int idr_get_new_above_int(struct idr *idp, void *ptr, int starting_id) * Successfully found an empty slot. Install the user * pointer and mark the slot full. */ - pa[0]->ary[id & IDR_MASK] = (struct idr_layer *)ptr; + rcu_assign_pointer(pa[0]->ary[id & IDR_MASK], + (struct idr_layer *)ptr); pa[0]->count++; idr_mark_full(pa, id); } @@ -277,12 +294,8 @@ int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id) * This is a cheap hack until the IDR code can be fixed to * return proper error values. */ - if (rv < 0) { - if (rv == -1) - return -EAGAIN; - else /* Will be -3 */ - return -ENOSPC; - } + if (rv < 0) + return _idr_rc_to_errno(rv); *id = rv; return 0; } @@ -312,12 +325,8 @@ int idr_get_new(struct idr *idp, void *ptr, int *id) * This is a cheap hack until the IDR code can be fixed to * return proper error values. */ - if (rv < 0) { - if (rv == -1) - return -EAGAIN; - else /* Will be -3 */ - return -ENOSPC; - } + if (rv < 0) + return _idr_rc_to_errno(rv); *id = rv; return 0; } @@ -325,7 +334,8 @@ EXPORT_SYMBOL(idr_get_new); static void idr_remove_warning(int id) { - printk("idr_remove called for id=%d which is not allocated.\n", id); + printk(KERN_WARNING + "idr_remove called for id=%d which is not allocated.\n", id); dump_stack(); } @@ -334,6 +344,7 @@ static void sub_remove(struct idr *idp, int shift, int id) struct idr_layer *p = idp->top; struct idr_layer **pa[MAX_LEVEL]; struct idr_layer ***paa = &pa[0]; + struct idr_layer *to_free; int n; *paa = NULL; @@ -349,13 +360,18 @@ static void sub_remove(struct idr *idp, int shift, int id) n = id & IDR_MASK; if (likely(p != NULL && test_bit(n, &p->bitmap))){ __clear_bit(n, &p->bitmap); - p->ary[n] = NULL; + rcu_assign_pointer(p->ary[n], NULL); + to_free = NULL; while(*paa && ! --((**paa)->count)){ - free_layer(idp, **paa); + if (to_free) + free_layer(to_free); + to_free = **paa; **paa-- = NULL; } if (!*paa) idp->layers = 0; + if (to_free) + free_layer(to_free); } else idr_remove_warning(id); } @@ -368,22 +384,34 @@ static void sub_remove(struct idr *idp, int shift, int id) void idr_remove(struct idr *idp, int id) { struct idr_layer *p; + struct idr_layer *to_free; /* Mask off upper bits we don't use for the search. */ id &= MAX_ID_MASK; sub_remove(idp, (idp->layers - 1) * IDR_BITS, id); if (idp->top && idp->top->count == 1 && (idp->layers > 1) && - idp->top->ary[0]) { // We can drop a layer - + idp->top->ary[0]) { + /* + * Single child at leftmost slot: we can shrink the tree. + * This level is not needed anymore since when layers are + * inserted, they are inserted at the top of the existing + * tree. + */ + to_free = idp->top; p = idp->top->ary[0]; - idp->top->bitmap = idp->top->count = 0; - free_layer(idp, idp->top); - idp->top = p; + rcu_assign_pointer(idp->top, p); --idp->layers; + to_free->bitmap = to_free->count = 0; + free_layer(to_free); } while (idp->id_free_cnt >= IDR_FREE_MAX) { - p = alloc_layer(idp); + p = get_from_free_list(idp); + /* + * Note: we don't call the rcu callback here, since the only + * layers that fall into the freelist are those that have been + * preallocated. + */ kmem_cache_free(idr_layer_cache, p); } return; @@ -424,15 +452,13 @@ void idr_remove_all(struct idr *idp) id += 1 << n; while (n < fls(id)) { - if (p) { - memset(p, 0, sizeof *p); - free_layer(idp, p); - } + if (p) + free_layer(p); n += IDR_BITS; p = *--paa; } } - idp->top = NULL; + rcu_assign_pointer(idp->top, NULL); idp->layers = 0; } EXPORT_SYMBOL(idr_remove_all); @@ -444,7 +470,7 @@ EXPORT_SYMBOL(idr_remove_all); void idr_destroy(struct idr *idp) { while (idp->id_free_cnt) { - struct idr_layer *p = alloc_layer(idp); + struct idr_layer *p = get_from_free_list(idp); kmem_cache_free(idr_layer_cache, p); } } @@ -459,7 +485,8 @@ EXPORT_SYMBOL(idr_destroy); * return indicates that @id is not valid or you passed %NULL in * idr_get_new(). * - * The caller must serialize idr_find() vs idr_get_new() and idr_remove(). + * This function can be called under rcu_read_lock(), given that the leaf + * pointers lifetimes are correctly managed. */ void *idr_find(struct idr *idp, int id) { @@ -467,7 +494,7 @@ void *idr_find(struct idr *idp, int id) struct idr_layer *p; n = idp->layers * IDR_BITS; - p = idp->top; + p = rcu_dereference(idp->top); /* Mask off upper bits we don't use for the search. */ id &= MAX_ID_MASK; @@ -477,7 +504,7 @@ void *idr_find(struct idr *idp, int id) while (n > 0 && p) { n -= IDR_BITS; - p = p->ary[(id >> n) & IDR_MASK]; + p = rcu_dereference(p->ary[(id >> n) & IDR_MASK]); } return((void *)p); } @@ -510,7 +537,7 @@ int idr_for_each(struct idr *idp, struct idr_layer **paa = &pa[0]; n = idp->layers * IDR_BITS; - p = idp->top; + p = rcu_dereference(idp->top); max = 1 << n; id = 0; @@ -518,7 +545,7 @@ int idr_for_each(struct idr *idp, while (n > 0 && p) { n -= IDR_BITS; *paa++ = p; - p = p->ary[(id >> n) & IDR_MASK]; + p = rcu_dereference(p->ary[(id >> n) & IDR_MASK]); } if (p) { @@ -548,7 +575,7 @@ EXPORT_SYMBOL(idr_for_each); * A -ENOENT return indicates that @id was not found. * A -EINVAL return indicates that @id was not within valid constraints. * - * The caller must serialize vs idr_find(), idr_get_new(), and idr_remove(). + * The caller must serialize with writers. */ void *idr_replace(struct idr *idp, void *ptr, int id) { @@ -574,13 +601,13 @@ void *idr_replace(struct idr *idp, void *ptr, int id) return ERR_PTR(-ENOENT); old_p = p->ary[n]; - p->ary[n] = ptr; + rcu_assign_pointer(p->ary[n], ptr); return old_p; } EXPORT_SYMBOL(idr_replace); -static void idr_cache_ctor(struct kmem_cache *idr_layer_cache, void *idr_layer) +static void idr_cache_ctor(void *idr_layer) { memset(idr_layer, 0, sizeof(struct idr_layer)); } @@ -694,12 +721,8 @@ int ida_get_new_above(struct ida *ida, int starting_id, int *p_id) restart: /* get vacant slot */ t = idr_get_empty_slot(&ida->idr, idr_id, pa); - if (t < 0) { - if (t == -1) - return -EAGAIN; - else /* will be -3 */ - return -ENOSPC; - } + if (t < 0) + return _idr_rc_to_errno(t); if (t * IDA_BITMAP_BITS >= MAX_ID_BIT) return -ENOSPC; @@ -720,7 +743,8 @@ int ida_get_new_above(struct ida *ida, int starting_id, int *p_id) return -EAGAIN; memset(bitmap, 0, sizeof(struct ida_bitmap)); - pa[0]->ary[idr_id & IDR_MASK] = (void *)bitmap; + rcu_assign_pointer(pa[0]->ary[idr_id & IDR_MASK], + (void *)bitmap); pa[0]->count++; } @@ -749,7 +773,7 @@ int ida_get_new_above(struct ida *ida, int starting_id, int *p_id) * allocation. */ if (ida->idr.id_free_cnt || ida->free_bitmap) { - struct idr_layer *p = alloc_layer(&ida->idr); + struct idr_layer *p = get_from_free_list(&ida->idr); if (p) kmem_cache_free(idr_layer_cache, p); } diff --git a/lib/inflate.c b/lib/inflate.c index 9762294be062..1a8e8a978128 100644 --- a/lib/inflate.c +++ b/lib/inflate.c @@ -230,6 +230,45 @@ STATIC const ush mask_bits[] = { #define NEEDBITS(n) {while(k<(n)){b|=((ulg)NEXTBYTE())<<k;k+=8;}} #define DUMPBITS(n) {b>>=(n);k-=(n);} +#ifndef NO_INFLATE_MALLOC +/* A trivial malloc implementation, adapted from + * malloc by Hannu Savolainen 1993 and Matthias Urlichs 1994 + */ + +static unsigned long malloc_ptr; +static int malloc_count; + +static void *malloc(int size) +{ + void *p; + + if (size < 0) + error("Malloc error"); + if (!malloc_ptr) + malloc_ptr = free_mem_ptr; + + malloc_ptr = (malloc_ptr + 3) & ~3; /* Align */ + + p = (void *)malloc_ptr; + malloc_ptr += size; + + if (free_mem_end_ptr && malloc_ptr >= free_mem_end_ptr) + error("Out of memory"); + + malloc_count++; + return p; +} + +static void free(void *where) +{ + malloc_count--; + if (!malloc_count) + malloc_ptr = free_mem_ptr; +} +#else +#define malloc(a) kmalloc(a, GFP_KERNEL) +#define free(a) kfree(a) +#endif /* Huffman code decoding is performed using a multi-level table lookup. @@ -1045,7 +1084,6 @@ STATIC int INIT inflate(void) int e; /* last block flag */ int r; /* result code */ unsigned h; /* maximum struct huft's malloc'ed */ - void *ptr; /* initialize window, bit buffer */ wp = 0; @@ -1057,12 +1095,12 @@ STATIC int INIT inflate(void) h = 0; do { hufts = 0; - gzip_mark(&ptr); - if ((r = inflate_block(&e)) != 0) { - gzip_release(&ptr); - return r; - } - gzip_release(&ptr); +#ifdef ARCH_HAS_DECOMP_WDOG + arch_decomp_wdog(); +#endif + r = inflate_block(&e); + if (r) + return r; if (hufts > h) h = hufts; } while (!e); diff --git a/lib/iomap.c b/lib/iomap.c index 37a3ea4cac9f..d32229385151 100644 --- a/lib/iomap.c +++ b/lib/iomap.c @@ -40,8 +40,7 @@ static void bad_io_access(unsigned long port, const char *access) static int count = 10; if (count) { count--; - printk(KERN_ERR "Bad IO access at port %#lx (%s)\n", port, access); - WARN_ON(1); + WARN(1, KERN_ERR "Bad IO access at port %#lx (%s)\n", port, access); } } diff --git a/lib/iommu-helper.c b/lib/iommu-helper.c index a3b8d4c3f77a..889ddce2021e 100644 --- a/lib/iommu-helper.c +++ b/lib/iommu-helper.c @@ -80,3 +80,11 @@ void iommu_area_free(unsigned long *map, unsigned long start, unsigned int nr) } } EXPORT_SYMBOL(iommu_area_free); + +unsigned long iommu_num_pages(unsigned long addr, unsigned long len) +{ + unsigned long size = roundup((addr & ~PAGE_MASK) + len, PAGE_SIZE); + + return size >> PAGE_SHIFT; +} +EXPORT_SYMBOL(iommu_num_pages); diff --git a/lib/kernel_lock.c b/lib/kernel_lock.c index cd3e82530b03..01a3c22c1b5a 100644 --- a/lib/kernel_lock.c +++ b/lib/kernel_lock.c @@ -11,79 +11,121 @@ #include <linux/semaphore.h> /* - * The 'big kernel semaphore' + * The 'big kernel lock' * - * This mutex is taken and released recursively by lock_kernel() + * This spinlock is taken and released recursively by lock_kernel() * and unlock_kernel(). It is transparently dropped and reacquired * over schedule(). It is used to protect legacy code that hasn't * been migrated to a proper locking design yet. * - * Note: code locked by this semaphore will only be serialized against - * other code using the same locking facility. The code guarantees that - * the task remains on the same CPU. - * * Don't use in new code. */ -static DECLARE_MUTEX(kernel_sem); +static __cacheline_aligned_in_smp DEFINE_SPINLOCK(kernel_flag); + /* - * Re-acquire the kernel semaphore. + * Acquire/release the underlying lock from the scheduler. * - * This function is called with preemption off. + * This is called with preemption disabled, and should + * return an error value if it cannot get the lock and + * TIF_NEED_RESCHED gets set. * - * We are executing in schedule() so the code must be extremely careful - * about recursion, both due to the down() and due to the enabling of - * preemption. schedule() will re-check the preemption flag after - * reacquiring the semaphore. + * If it successfully gets the lock, it should increment + * the preemption count like any spinlock does. + * + * (This works on UP too - _raw_spin_trylock will never + * return false in that case) */ int __lockfunc __reacquire_kernel_lock(void) { - struct task_struct *task = current; - int saved_lock_depth = task->lock_depth; - - BUG_ON(saved_lock_depth < 0); - - task->lock_depth = -1; - preempt_enable_no_resched(); - - down(&kernel_sem); - + while (!_raw_spin_trylock(&kernel_flag)) { + if (test_thread_flag(TIF_NEED_RESCHED)) + return -EAGAIN; + cpu_relax(); + } preempt_disable(); - task->lock_depth = saved_lock_depth; - return 0; } void __lockfunc __release_kernel_lock(void) { - up(&kernel_sem); + _raw_spin_unlock(&kernel_flag); + preempt_enable_no_resched(); } /* - * Getting the big kernel semaphore. + * These are the BKL spinlocks - we try to be polite about preemption. + * If SMP is not on (ie UP preemption), this all goes away because the + * _raw_spin_trylock() will always succeed. */ -void __lockfunc lock_kernel(void) +#ifdef CONFIG_PREEMPT +static inline void __lock_kernel(void) { - struct task_struct *task = current; - int depth = task->lock_depth + 1; + preempt_disable(); + if (unlikely(!_raw_spin_trylock(&kernel_flag))) { + /* + * If preemption was disabled even before this + * was called, there's nothing we can be polite + * about - just spin. + */ + if (preempt_count() > 1) { + _raw_spin_lock(&kernel_flag); + return; + } - if (likely(!depth)) /* - * No recursion worries - we set up lock_depth _after_ + * Otherwise, let's wait for the kernel lock + * with preemption enabled.. */ - down(&kernel_sem); + do { + preempt_enable(); + while (spin_is_locked(&kernel_flag)) + cpu_relax(); + preempt_disable(); + } while (!_raw_spin_trylock(&kernel_flag)); + } +} - task->lock_depth = depth; +#else + +/* + * Non-preemption case - just get the spinlock + */ +static inline void __lock_kernel(void) +{ + _raw_spin_lock(&kernel_flag); } +#endif -void __lockfunc unlock_kernel(void) +static inline void __unlock_kernel(void) { - struct task_struct *task = current; + /* + * the BKL is not covered by lockdep, so we open-code the + * unlocking sequence (and thus avoid the dep-chain ops): + */ + _raw_spin_unlock(&kernel_flag); + preempt_enable(); +} - BUG_ON(task->lock_depth < 0); +/* + * Getting the big kernel lock. + * + * This cannot happen asynchronously, so we only need to + * worry about other CPU's. + */ +void __lockfunc lock_kernel(void) +{ + int depth = current->lock_depth+1; + if (likely(!depth)) + __lock_kernel(); + current->lock_depth = depth; +} - if (likely(--task->lock_depth < 0)) - up(&kernel_sem); +void __lockfunc unlock_kernel(void) +{ + BUG_ON(current->lock_depth < 0); + if (likely(--current->lock_depth < 0)) + __unlock_kernel(); } EXPORT_SYMBOL(lock_kernel); diff --git a/lib/kobject.c b/lib/kobject.c index 718e5101c263..bd732ffebc85 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -164,9 +164,8 @@ static int kobject_add_internal(struct kobject *kobj) return -ENOENT; if (!kobj->name || !kobj->name[0]) { - pr_debug("kobject: (%p): attempted to be registered with empty " + WARN(1, "kobject: (%p): attempted to be registered with empty " "name!\n", kobj); - WARN_ON(1); return -EINVAL; } @@ -216,13 +215,19 @@ static int kobject_add_internal(struct kobject *kobj) static int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, va_list vargs) { - /* Free the old name, if necessary. */ - kfree(kobj->name); + const char *old_name = kobj->name; + char *s; kobj->name = kvasprintf(GFP_KERNEL, fmt, vargs); if (!kobj->name) return -ENOMEM; + /* ewww... some of these buggers have '/' in the name ... */ + s = strchr(kobj->name, '/'); + if (s) + s[0] = '!'; + + kfree(old_name); return 0; } @@ -439,6 +444,7 @@ out: return error; } +EXPORT_SYMBOL_GPL(kobject_rename); /** * kobject_move - move object to another parent @@ -576,12 +582,10 @@ static void kobject_release(struct kref *kref) void kobject_put(struct kobject *kobj) { if (kobj) { - if (!kobj->state_initialized) { - printk(KERN_WARNING "kobject: '%s' (%p): is not " + if (!kobj->state_initialized) + WARN(1, KERN_WARNING "kobject: '%s' (%p): is not " "initialized, yet kobject_put() is being " "called.\n", kobject_name(kobj), kobj); - WARN_ON(1); - } kref_put(&kobj->kref, kobject_release); } } diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index 2fa545a63160..3f914725bda8 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -245,7 +245,8 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, if (retval) goto exit; - call_usermodehelper(argv[0], argv, env->envp, UMH_WAIT_EXEC); + retval = call_usermodehelper(argv[0], argv, + env->envp, UMH_WAIT_EXEC); } exit: @@ -284,8 +285,7 @@ int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...) int len; if (env->envp_idx >= ARRAY_SIZE(env->envp)) { - printk(KERN_ERR "add_uevent_var: too many keys\n"); - WARN_ON(1); + WARN(1, KERN_ERR "add_uevent_var: too many keys\n"); return -ENOMEM; } @@ -296,8 +296,7 @@ int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...) va_end(args); if (len >= (sizeof(env->buf) - env->buflen)) { - printk(KERN_ERR "add_uevent_var: buffer size too small\n"); - WARN_ON(1); + WARN(1, KERN_ERR "add_uevent_var: buffer size too small\n"); return -ENOMEM; } diff --git a/lib/list_debug.c b/lib/list_debug.c index 4350ba9655bd..1a39f4e3ae1f 100644 --- a/lib/list_debug.c +++ b/lib/list_debug.c @@ -20,18 +20,14 @@ void __list_add(struct list_head *new, struct list_head *prev, struct list_head *next) { - if (unlikely(next->prev != prev)) { - printk(KERN_ERR "list_add corruption. next->prev should be " - "prev (%p), but was %p. (next=%p).\n", - prev, next->prev, next); - BUG(); - } - if (unlikely(prev->next != next)) { - printk(KERN_ERR "list_add corruption. prev->next should be " - "next (%p), but was %p. (prev=%p).\n", - next, prev->next, prev); - BUG(); - } + WARN(next->prev != prev, + "list_add corruption. next->prev should be " + "prev (%p), but was %p. (next=%p).\n", + prev, next->prev, next); + WARN(prev->next != next, + "list_add corruption. prev->next should be " + "next (%p), but was %p. (prev=%p).\n", + next, prev->next, prev); next->prev = new; new->next = next; new->prev = prev; @@ -40,20 +36,6 @@ void __list_add(struct list_head *new, EXPORT_SYMBOL(__list_add); /** - * list_add - add a new entry - * @new: new entry to be added - * @head: list head to add it after - * - * Insert a new entry after the specified head. - * This is good for implementing stacks. - */ -void list_add(struct list_head *new, struct list_head *head) -{ - __list_add(new, head, head->next); -} -EXPORT_SYMBOL(list_add); - -/** * list_del - deletes entry from list. * @entry: the element to delete from the list. * Note: list_empty on entry does not return true after this, the entry is @@ -61,16 +43,12 @@ EXPORT_SYMBOL(list_add); */ void list_del(struct list_head *entry) { - if (unlikely(entry->prev->next != entry)) { - printk(KERN_ERR "list_del corruption. prev->next should be %p, " - "but was %p\n", entry, entry->prev->next); - BUG(); - } - if (unlikely(entry->next->prev != entry)) { - printk(KERN_ERR "list_del corruption. next->prev should be %p, " - "but was %p\n", entry, entry->next->prev); - BUG(); - } + WARN(entry->prev->next != entry, + "list_del corruption. prev->next should be %p, " + "but was %p\n", entry, entry->prev->next); + WARN(entry->next->prev != entry, + "list_del corruption. next->prev should be %p, " + "but was %p\n", entry, entry->next->prev); __list_del(entry->prev, entry->next); entry->next = LIST_POISON1; entry->prev = LIST_POISON2; diff --git a/lib/lmb.c b/lib/lmb.c index 83287d3869a3..5d7b9286503e 100644 --- a/lib/lmb.c +++ b/lib/lmb.c @@ -19,31 +19,43 @@ struct lmb lmb; +static int lmb_debug; + +static int __init early_lmb(char *p) +{ + if (p && strstr(p, "debug")) + lmb_debug = 1; + return 0; +} +early_param("lmb", early_lmb); + void lmb_dump_all(void) { -#ifdef DEBUG unsigned long i; - pr_debug("lmb_dump_all:\n"); - pr_debug(" memory.cnt = 0x%lx\n", lmb.memory.cnt); - pr_debug(" memory.size = 0x%llx\n", + if (!lmb_debug) + return; + + pr_info("lmb_dump_all:\n"); + pr_info(" memory.cnt = 0x%lx\n", lmb.memory.cnt); + pr_info(" memory.size = 0x%llx\n", (unsigned long long)lmb.memory.size); for (i=0; i < lmb.memory.cnt ;i++) { - pr_debug(" memory.region[0x%x].base = 0x%llx\n", + pr_info(" memory.region[0x%lx].base = 0x%llx\n", i, (unsigned long long)lmb.memory.region[i].base); - pr_debug(" .size = 0x%llx\n", + pr_info(" .size = 0x%llx\n", (unsigned long long)lmb.memory.region[i].size); } - pr_debug(" reserved.cnt = 0x%lx\n", lmb.reserved.cnt); - pr_debug(" reserved.size = 0x%lx\n", lmb.reserved.size); + pr_info(" reserved.cnt = 0x%lx\n", lmb.reserved.cnt); + pr_info(" reserved.size = 0x%llx\n", + (unsigned long long)lmb.memory.size); for (i=0; i < lmb.reserved.cnt ;i++) { - pr_debug(" reserved.region[0x%x].base = 0x%llx\n", + pr_info(" reserved.region[0x%lx].base = 0x%llx\n", i, (unsigned long long)lmb.reserved.region[i].base); - pr_debug(" .size = 0x%llx\n", + pr_info(" .size = 0x%llx\n", (unsigned long long)lmb.reserved.region[i].size); } -#endif /* DEBUG */ } static unsigned long lmb_addrs_overlap(u64 base1, u64 size1, u64 base2, @@ -286,8 +298,7 @@ static u64 __init lmb_alloc_nid_unreserved(u64 start, u64 end, j = lmb_overlaps_region(&lmb.reserved, base, size); if (j < 0) { /* this area isn't reserved, take it */ - if (lmb_add_region(&lmb.reserved, base, - lmb_align_up(size, align)) < 0) + if (lmb_add_region(&lmb.reserved, base, size) < 0) base = ~(u64)0; return base; } @@ -333,6 +344,10 @@ u64 __init lmb_alloc_nid(u64 size, u64 align, int nid, struct lmb_region *mem = &lmb.memory; int i; + BUG_ON(0 == size); + + size = lmb_align_up(size, align); + for (i = 0; i < mem->cnt; i++) { u64 ret = lmb_alloc_nid_region(&mem->region[i], nid_range, @@ -370,6 +385,8 @@ u64 __init __lmb_alloc_base(u64 size, u64 align, u64 max_addr) BUG_ON(0 == size); + size = lmb_align_up(size, align); + /* On some platforms, make sure we allocate lowmem */ /* Note that LMB_REAL_LIMIT may be LMB_ALLOC_ANYWHERE */ if (max_addr == LMB_ALLOC_ANYWHERE) @@ -393,8 +410,7 @@ u64 __init __lmb_alloc_base(u64 size, u64 align, u64 max_addr) j = lmb_overlaps_region(&lmb.reserved, base, size); if (j < 0) { /* this area isn't reserved, take it */ - if (lmb_add_region(&lmb.reserved, base, - lmb_align_up(size, align)) < 0) + if (lmb_add_region(&lmb.reserved, base, size) < 0) return 0; return base; } diff --git a/lib/lzo/lzo1x_decompress.c b/lib/lzo/lzo1x_decompress.c index 77f0f9b775a9..5dc6b29c1575 100644 --- a/lib/lzo/lzo1x_decompress.c +++ b/lib/lzo/lzo1x_decompress.c @@ -138,8 +138,7 @@ match: t += 31 + *ip++; } m_pos = op - 1; - m_pos -= le16_to_cpu(get_unaligned( - (const unsigned short *)ip)) >> 2; + m_pos -= get_unaligned_le16(ip) >> 2; ip += 2; } else if (t >= 16) { m_pos = op; @@ -157,8 +156,7 @@ match: } t += 7 + *ip++; } - m_pos -= le16_to_cpu(get_unaligned( - (const unsigned short *)ip)) >> 2; + m_pos -= get_unaligned_le16(ip) >> 2; ip += 2; if (m_pos == op) goto eof_found; diff --git a/lib/parser.c b/lib/parser.c index 703c8c13b346..4f0cbc03e0e8 100644 --- a/lib/parser.c +++ b/lib/parser.c @@ -182,18 +182,25 @@ int match_hex(substring_t *s, int *result) } /** - * match_strcpy: - copies the characters from a substring_t to a string - * @to: string to copy characters to. - * @s: &substring_t to copy + * match_strlcpy: - Copy the characters from a substring_t to a sized buffer + * @dest: where to copy to + * @src: &substring_t to copy + * @size: size of destination buffer * - * Description: Copies the set of characters represented by the given - * &substring_t @s to the c-style string @to. Caller guarantees that @to is - * large enough to hold the characters of @s. + * Description: Copy the characters in &substring_t @src to the + * c-style string @dest. Copy no more than @size - 1 characters, plus + * the terminating NUL. Return length of @src. */ -void match_strcpy(char *to, const substring_t *s) +size_t match_strlcpy(char *dest, const substring_t *src, size_t size) { - memcpy(to, s->from, s->to - s->from); - to[s->to - s->from] = '\0'; + size_t ret = src->to - src->from; + + if (size) { + size_t len = ret >= size ? size - 1 : ret; + memcpy(dest, src->from, len); + dest[len] = '\0'; + } + return ret; } /** @@ -206,9 +213,10 @@ void match_strcpy(char *to, const substring_t *s) */ char *match_strdup(const substring_t *s) { - char *p = kmalloc(s->to - s->from + 1, GFP_KERNEL); + size_t sz = s->to - s->from + 1; + char *p = kmalloc(sz, GFP_KERNEL); if (p) - match_strcpy(p, s); + match_strlcpy(p, s, sz); return p; } @@ -216,5 +224,5 @@ EXPORT_SYMBOL(match_token); EXPORT_SYMBOL(match_int); EXPORT_SYMBOL(match_octal); EXPORT_SYMBOL(match_hex); -EXPORT_SYMBOL(match_strcpy); +EXPORT_SYMBOL(match_strlcpy); EXPORT_SYMBOL(match_strdup); diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c index 119174494cb5..4a8ba4bf5f6f 100644 --- a/lib/percpu_counter.c +++ b/lib/percpu_counter.c @@ -52,7 +52,7 @@ EXPORT_SYMBOL(__percpu_counter_add); * Add up all the per-cpu counts, return the result. This is a more accurate * but much slower version of percpu_counter_read_positive() */ -s64 __percpu_counter_sum(struct percpu_counter *fbc) +s64 __percpu_counter_sum(struct percpu_counter *fbc, int set) { s64 ret; int cpu; @@ -62,7 +62,12 @@ s64 __percpu_counter_sum(struct percpu_counter *fbc) for_each_online_cpu(cpu) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); ret += *pcount; + if (set) + *pcount = 0; } + if (set) + fbc->count = ret; + spin_unlock(&fbc->lock); return ret; } diff --git a/lib/plist.c b/lib/plist.c index 3074a02272f3..d6c64a824e1d 100644 --- a/lib/plist.c +++ b/lib/plist.c @@ -31,12 +31,13 @@ static void plist_check_prev_next(struct list_head *t, struct list_head *p, struct list_head *n) { - if (n->prev != p || p->next != n) { - printk("top: %p, n: %p, p: %p\n", t, t->next, t->prev); - printk("prev: %p, n: %p, p: %p\n", p, p->next, p->prev); - printk("next: %p, n: %p, p: %p\n", n, n->next, n->prev); - WARN_ON(1); - } + WARN(n->prev != p || p->next != n, + "top: %p, n: %p, p: %p\n" + "prev: %p, n: %p, p: %p\n" + "next: %p, n: %p, p: %p\n", + t, t->next, t->prev, + p, p->next, p->prev, + n, n->next, n->prev); } static void plist_check_list(struct list_head *top) diff --git a/lib/radix-tree.c b/lib/radix-tree.c index bd521716ab1a..be86b32bc874 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1,7 +1,7 @@ /* * Copyright (C) 2001 Momchil Velikov * Portions Copyright (C) 2001 Christoph Hellwig - * Copyright (C) 2005 SGI, Christoph Lameter <clameter@sgi.com> + * Copyright (C) 2005 SGI, Christoph Lameter * Copyright (C) 2006 Nick Piggin * * This program is free software; you can redistribute it and/or @@ -88,6 +88,57 @@ static inline gfp_t root_gfp_mask(struct radix_tree_root *root) return root->gfp_mask & __GFP_BITS_MASK; } +static inline void tag_set(struct radix_tree_node *node, unsigned int tag, + int offset) +{ + __set_bit(offset, node->tags[tag]); +} + +static inline void tag_clear(struct radix_tree_node *node, unsigned int tag, + int offset) +{ + __clear_bit(offset, node->tags[tag]); +} + +static inline int tag_get(struct radix_tree_node *node, unsigned int tag, + int offset) +{ + return test_bit(offset, node->tags[tag]); +} + +static inline void root_tag_set(struct radix_tree_root *root, unsigned int tag) +{ + root->gfp_mask |= (__force gfp_t)(1 << (tag + __GFP_BITS_SHIFT)); +} + +static inline void root_tag_clear(struct radix_tree_root *root, unsigned int tag) +{ + root->gfp_mask &= (__force gfp_t)~(1 << (tag + __GFP_BITS_SHIFT)); +} + +static inline void root_tag_clear_all(struct radix_tree_root *root) +{ + root->gfp_mask &= __GFP_BITS_MASK; +} + +static inline int root_tag_get(struct radix_tree_root *root, unsigned int tag) +{ + return (__force unsigned)root->gfp_mask & (1 << (tag + __GFP_BITS_SHIFT)); +} + +/* + * Returns 1 if any slot in the node has this tag set. + * Otherwise returns 0. + */ +static inline int any_tag_set(struct radix_tree_node *node, unsigned int tag) +{ + int idx; + for (idx = 0; idx < RADIX_TREE_TAG_LONGS; idx++) { + if (node->tags[tag][idx]) + return 1; + } + return 0; +} /* * This assumes that the caller has performed appropriate preallocation, and * that the caller has pinned this thread of control to the current CPU. @@ -124,6 +175,17 @@ static void radix_tree_node_rcu_free(struct rcu_head *head) { struct radix_tree_node *node = container_of(head, struct radix_tree_node, rcu_head); + + /* + * must only free zeroed nodes into the slab. radix_tree_shrink + * can leave us with a non-NULL entry in the first slot, so clear + * that here to make sure. + */ + tag_clear(node, 0, 0); + tag_clear(node, 1, 0); + node->slots[0] = NULL; + node->count = 0; + kmem_cache_free(radix_tree_node_cachep, node); } @@ -165,59 +227,6 @@ out: } EXPORT_SYMBOL(radix_tree_preload); -static inline void tag_set(struct radix_tree_node *node, unsigned int tag, - int offset) -{ - __set_bit(offset, node->tags[tag]); -} - -static inline void tag_clear(struct radix_tree_node *node, unsigned int tag, - int offset) -{ - __clear_bit(offset, node->tags[tag]); -} - -static inline int tag_get(struct radix_tree_node *node, unsigned int tag, - int offset) -{ - return test_bit(offset, node->tags[tag]); -} - -static inline void root_tag_set(struct radix_tree_root *root, unsigned int tag) -{ - root->gfp_mask |= (__force gfp_t)(1 << (tag + __GFP_BITS_SHIFT)); -} - - -static inline void root_tag_clear(struct radix_tree_root *root, unsigned int tag) -{ - root->gfp_mask &= (__force gfp_t)~(1 << (tag + __GFP_BITS_SHIFT)); -} - -static inline void root_tag_clear_all(struct radix_tree_root *root) -{ - root->gfp_mask &= __GFP_BITS_MASK; -} - -static inline int root_tag_get(struct radix_tree_root *root, unsigned int tag) -{ - return (__force unsigned)root->gfp_mask & (1 << (tag + __GFP_BITS_SHIFT)); -} - -/* - * Returns 1 if any slot in the node has this tag set. - * Otherwise returns 0. - */ -static inline int any_tag_set(struct radix_tree_node *node, unsigned int tag) -{ - int idx; - for (idx = 0; idx < RADIX_TREE_TAG_LONGS; idx++) { - if (node->tags[tag][idx]) - return 1; - } - return 0; -} - /* * Return the maximum key which can be store into a * radix tree with height HEIGHT. @@ -350,18 +359,17 @@ EXPORT_SYMBOL(radix_tree_insert); * Returns: the slot corresponding to the position @index in the * radix tree @root. This is useful for update-if-exists operations. * - * This function cannot be called under rcu_read_lock, it must be - * excluded from writers, as must the returned slot for subsequent - * use by radix_tree_deref_slot() and radix_tree_replace slot. - * Caller must hold tree write locked across slot lookup and - * replace. + * This function can be called under rcu_read_lock iff the slot is not + * modified by radix_tree_replace_slot, otherwise it must be called + * exclusive from other writers. Any dereference of the slot must be done + * using radix_tree_deref_slot. */ void **radix_tree_lookup_slot(struct radix_tree_root *root, unsigned long index) { unsigned int height, shift; struct radix_tree_node *node, **slot; - node = root->rnode; + node = rcu_dereference(root->rnode); if (node == NULL) return NULL; @@ -381,7 +389,7 @@ void **radix_tree_lookup_slot(struct radix_tree_root *root, unsigned long index) do { slot = (struct radix_tree_node **) (node->slots + ((index>>shift) & RADIX_TREE_MAP_MASK)); - node = *slot; + node = rcu_dereference(*slot); if (node == NULL) return NULL; @@ -658,7 +666,7 @@ unsigned long radix_tree_next_hole(struct radix_tree_root *root, EXPORT_SYMBOL(radix_tree_next_hole); static unsigned int -__lookup(struct radix_tree_node *slot, void **results, unsigned long index, +__lookup(struct radix_tree_node *slot, void ***results, unsigned long index, unsigned int max_items, unsigned long *next_index) { unsigned int nr_found = 0; @@ -692,11 +700,9 @@ __lookup(struct radix_tree_node *slot, void **results, unsigned long index, /* Bottom level: grab some items */ for (i = index & RADIX_TREE_MAP_MASK; i < RADIX_TREE_MAP_SIZE; i++) { - struct radix_tree_node *node; index++; - node = slot->slots[i]; - if (node) { - results[nr_found++] = rcu_dereference(node); + if (slot->slots[i]) { + results[nr_found++] = &(slot->slots[i]); if (nr_found == max_items) goto out; } @@ -750,13 +756,22 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results, ret = 0; while (ret < max_items) { - unsigned int nr_found; + unsigned int nr_found, slots_found, i; unsigned long next_index; /* Index of next search */ if (cur_index > max_index) break; - nr_found = __lookup(node, results + ret, cur_index, + slots_found = __lookup(node, (void ***)results + ret, cur_index, max_items - ret, &next_index); + nr_found = 0; + for (i = 0; i < slots_found; i++) { + struct radix_tree_node *slot; + slot = *(((void ***)results)[ret + i]); + if (!slot) + continue; + results[ret + nr_found] = rcu_dereference(slot); + nr_found++; + } ret += nr_found; if (next_index == 0) break; @@ -767,12 +782,71 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results, } EXPORT_SYMBOL(radix_tree_gang_lookup); +/** + * radix_tree_gang_lookup_slot - perform multiple slot lookup on radix tree + * @root: radix tree root + * @results: where the results of the lookup are placed + * @first_index: start the lookup from this key + * @max_items: place up to this many items at *results + * + * Performs an index-ascending scan of the tree for present items. Places + * their slots at *@results and returns the number of items which were + * placed at *@results. + * + * The implementation is naive. + * + * Like radix_tree_gang_lookup as far as RCU and locking goes. Slots must + * be dereferenced with radix_tree_deref_slot, and if using only RCU + * protection, radix_tree_deref_slot may fail requiring a retry. + */ +unsigned int +radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results, + unsigned long first_index, unsigned int max_items) +{ + unsigned long max_index; + struct radix_tree_node *node; + unsigned long cur_index = first_index; + unsigned int ret; + + node = rcu_dereference(root->rnode); + if (!node) + return 0; + + if (!radix_tree_is_indirect_ptr(node)) { + if (first_index > 0) + return 0; + results[0] = (void **)&root->rnode; + return 1; + } + node = radix_tree_indirect_to_ptr(node); + + max_index = radix_tree_maxindex(node->height); + + ret = 0; + while (ret < max_items) { + unsigned int slots_found; + unsigned long next_index; /* Index of next search */ + + if (cur_index > max_index) + break; + slots_found = __lookup(node, results + ret, cur_index, + max_items - ret, &next_index); + ret += slots_found; + if (next_index == 0) + break; + cur_index = next_index; + } + + return ret; +} +EXPORT_SYMBOL(radix_tree_gang_lookup_slot); + /* * FIXME: the two tag_get()s here should use find_next_bit() instead of * open-coding the search. */ static unsigned int -__lookup_tag(struct radix_tree_node *slot, void **results, unsigned long index, +__lookup_tag(struct radix_tree_node *slot, void ***results, unsigned long index, unsigned int max_items, unsigned long *next_index, unsigned int tag) { unsigned int nr_found = 0; @@ -802,11 +876,9 @@ __lookup_tag(struct radix_tree_node *slot, void **results, unsigned long index, unsigned long j = index & RADIX_TREE_MAP_MASK; for ( ; j < RADIX_TREE_MAP_SIZE; j++) { - struct radix_tree_node *node; index++; if (!tag_get(slot, tag, j)) continue; - node = slot->slots[j]; /* * Even though the tag was found set, we need to * recheck that we have a non-NULL node, because @@ -817,9 +889,8 @@ __lookup_tag(struct radix_tree_node *slot, void **results, unsigned long index, * lookup ->slots[x] without a lock (ie. can't * rely on its value remaining the same). */ - if (node) { - node = rcu_dereference(node); - results[nr_found++] = node; + if (slot->slots[j]) { + results[nr_found++] = &(slot->slots[j]); if (nr_found == max_items) goto out; } @@ -878,13 +949,22 @@ radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results, ret = 0; while (ret < max_items) { - unsigned int nr_found; + unsigned int nr_found, slots_found, i; unsigned long next_index; /* Index of next search */ if (cur_index > max_index) break; - nr_found = __lookup_tag(node, results + ret, cur_index, - max_items - ret, &next_index, tag); + slots_found = __lookup_tag(node, (void ***)results + ret, + cur_index, max_items - ret, &next_index, tag); + nr_found = 0; + for (i = 0; i < slots_found; i++) { + struct radix_tree_node *slot; + slot = *(((void ***)results)[ret + i]); + if (!slot) + continue; + results[ret + nr_found] = rcu_dereference(slot); + nr_found++; + } ret += nr_found; if (next_index == 0) break; @@ -896,6 +976,67 @@ radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results, EXPORT_SYMBOL(radix_tree_gang_lookup_tag); /** + * radix_tree_gang_lookup_tag_slot - perform multiple slot lookup on a + * radix tree based on a tag + * @root: radix tree root + * @results: where the results of the lookup are placed + * @first_index: start the lookup from this key + * @max_items: place up to this many items at *results + * @tag: the tag index (< RADIX_TREE_MAX_TAGS) + * + * Performs an index-ascending scan of the tree for present items which + * have the tag indexed by @tag set. Places the slots at *@results and + * returns the number of slots which were placed at *@results. + */ +unsigned int +radix_tree_gang_lookup_tag_slot(struct radix_tree_root *root, void ***results, + unsigned long first_index, unsigned int max_items, + unsigned int tag) +{ + struct radix_tree_node *node; + unsigned long max_index; + unsigned long cur_index = first_index; + unsigned int ret; + + /* check the root's tag bit */ + if (!root_tag_get(root, tag)) + return 0; + + node = rcu_dereference(root->rnode); + if (!node) + return 0; + + if (!radix_tree_is_indirect_ptr(node)) { + if (first_index > 0) + return 0; + results[0] = (void **)&root->rnode; + return 1; + } + node = radix_tree_indirect_to_ptr(node); + + max_index = radix_tree_maxindex(node->height); + + ret = 0; + while (ret < max_items) { + unsigned int slots_found; + unsigned long next_index; /* Index of next search */ + + if (cur_index > max_index) + break; + slots_found = __lookup_tag(node, results + ret, + cur_index, max_items - ret, &next_index, tag); + ret += slots_found; + if (next_index == 0) + break; + cur_index = next_index; + } + + return ret; +} +EXPORT_SYMBOL(radix_tree_gang_lookup_tag_slot); + + +/** * radix_tree_shrink - shrink height of a radix tree to minimal * @root radix tree root */ @@ -930,11 +1071,6 @@ static inline void radix_tree_shrink(struct radix_tree_root *root) newptr = radix_tree_ptr_to_indirect(newptr); root->rnode = newptr; root->height--; - /* must only free zeroed nodes into the slab */ - tag_clear(to_free, 0, 0); - tag_clear(to_free, 1, 0); - to_free->slots[0] = NULL; - to_free->count = 0; radix_tree_node_free(to_free); } } @@ -1047,7 +1183,7 @@ int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag) EXPORT_SYMBOL(radix_tree_tagged); static void -radix_tree_node_ctor(struct kmem_cache *cachep, void *node) +radix_tree_node_ctor(void *node) { memset(node, 0, sizeof(struct radix_tree_node)); } diff --git a/lib/ratelimit.c b/lib/ratelimit.c index 485e3040dcd4..26187edcc7ea 100644 --- a/lib/ratelimit.c +++ b/lib/ratelimit.c @@ -3,6 +3,9 @@ * * Isolated from kernel/printk.c by Dave Young <hidave.darkstar@gmail.com> * + * 2008-05-01 rewrite the function and use a ratelimit_state data struct as + * parameter. Now every user can use their own standalone ratelimit_state. + * * This file is released under the GPLv2. * */ @@ -11,41 +14,44 @@ #include <linux/jiffies.h> #include <linux/module.h> +static DEFINE_SPINLOCK(ratelimit_lock); + /* * __ratelimit - rate limiting - * @ratelimit_jiffies: minimum time in jiffies between two callbacks - * @ratelimit_burst: number of callbacks we do before ratelimiting + * @rs: ratelimit_state data * - * This enforces a rate limit: not more than @ratelimit_burst callbacks - * in every ratelimit_jiffies + * This enforces a rate limit: not more than @rs->ratelimit_burst callbacks + * in every @rs->ratelimit_jiffies */ -int __ratelimit(int ratelimit_jiffies, int ratelimit_burst) +int __ratelimit(struct ratelimit_state *rs) { - static DEFINE_SPINLOCK(ratelimit_lock); - static unsigned toks = 10 * 5 * HZ; - static unsigned long last_msg; - static int missed; unsigned long flags; - unsigned long now = jiffies; - spin_lock_irqsave(&ratelimit_lock, flags); - toks += now - last_msg; - last_msg = now; - if (toks > (ratelimit_burst * ratelimit_jiffies)) - toks = ratelimit_burst * ratelimit_jiffies; - if (toks >= ratelimit_jiffies) { - int lost = missed; - - missed = 0; - toks -= ratelimit_jiffies; - spin_unlock_irqrestore(&ratelimit_lock, flags); - if (lost) - printk(KERN_WARNING "%s: %d messages suppressed\n", - __func__, lost); + if (!rs->interval) return 1; + + spin_lock_irqsave(&ratelimit_lock, flags); + if (!rs->begin) + rs->begin = jiffies; + + if (time_is_before_jiffies(rs->begin + rs->interval)) { + if (rs->missed) + printk(KERN_WARNING "%s: %d callbacks suppressed\n", + __func__, rs->missed); + rs->begin = 0; + rs->printed = 0; + rs->missed = 0; } - missed++; + if (rs->burst && rs->burst > rs->printed) + goto print; + + rs->missed++; spin_unlock_irqrestore(&ratelimit_lock, flags); return 0; + +print: + rs->printed++; + spin_unlock_irqrestore(&ratelimit_lock, flags); + return 1; } EXPORT_SYMBOL(__ratelimit); diff --git a/lib/scatterlist.c b/lib/scatterlist.c index b80c21100d78..876ba6d5b670 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -295,6 +295,117 @@ int sg_alloc_table(struct sg_table *table, unsigned int nents, gfp_t gfp_mask) EXPORT_SYMBOL(sg_alloc_table); /** + * sg_miter_start - start mapping iteration over a sg list + * @miter: sg mapping iter to be started + * @sgl: sg list to iterate over + * @nents: number of sg entries + * + * Description: + * Starts mapping iterator @miter. + * + * Context: + * Don't care. + */ +void sg_miter_start(struct sg_mapping_iter *miter, struct scatterlist *sgl, + unsigned int nents, unsigned int flags) +{ + memset(miter, 0, sizeof(struct sg_mapping_iter)); + + miter->__sg = sgl; + miter->__nents = nents; + miter->__offset = 0; + miter->__flags = flags; +} +EXPORT_SYMBOL(sg_miter_start); + +/** + * sg_miter_next - proceed mapping iterator to the next mapping + * @miter: sg mapping iter to proceed + * + * Description: + * Proceeds @miter@ to the next mapping. @miter@ should have been + * started using sg_miter_start(). On successful return, + * @miter@->page, @miter@->addr and @miter@->length point to the + * current mapping. + * + * Context: + * IRQ disabled if SG_MITER_ATOMIC. IRQ must stay disabled till + * @miter@ is stopped. May sleep if !SG_MITER_ATOMIC. + * + * Returns: + * true if @miter contains the next mapping. false if end of sg + * list is reached. + */ +bool sg_miter_next(struct sg_mapping_iter *miter) +{ + unsigned int off, len; + + /* check for end and drop resources from the last iteration */ + if (!miter->__nents) + return false; + + sg_miter_stop(miter); + + /* get to the next sg if necessary. __offset is adjusted by stop */ + if (miter->__offset == miter->__sg->length && --miter->__nents) { + miter->__sg = sg_next(miter->__sg); + miter->__offset = 0; + } + + /* map the next page */ + off = miter->__sg->offset + miter->__offset; + len = miter->__sg->length - miter->__offset; + + miter->page = nth_page(sg_page(miter->__sg), off >> PAGE_SHIFT); + off &= ~PAGE_MASK; + miter->length = min_t(unsigned int, len, PAGE_SIZE - off); + miter->consumed = miter->length; + + if (miter->__flags & SG_MITER_ATOMIC) + miter->addr = kmap_atomic(miter->page, KM_BIO_SRC_IRQ) + off; + else + miter->addr = kmap(miter->page) + off; + + return true; +} +EXPORT_SYMBOL(sg_miter_next); + +/** + * sg_miter_stop - stop mapping iteration + * @miter: sg mapping iter to be stopped + * + * Description: + * Stops mapping iterator @miter. @miter should have been started + * started using sg_miter_start(). A stopped iteration can be + * resumed by calling sg_miter_next() on it. This is useful when + * resources (kmap) need to be released during iteration. + * + * Context: + * IRQ disabled if the SG_MITER_ATOMIC is set. Don't care otherwise. + */ +void sg_miter_stop(struct sg_mapping_iter *miter) +{ + WARN_ON(miter->consumed > miter->length); + + /* drop resources from the last iteration */ + if (miter->addr) { + miter->__offset += miter->consumed; + + if (miter->__flags & SG_MITER_ATOMIC) { + WARN_ON(!irqs_disabled()); + kunmap_atomic(miter->addr, KM_BIO_SRC_IRQ); + } else + kunmap(miter->addr); + + miter->page = NULL; + miter->addr = NULL; + miter->length = 0; + miter->consumed = 0; + } +} +EXPORT_SYMBOL(sg_miter_stop); + +/** * sg_copy_buffer - Copy data between a linear buffer and an SG list * @sgl: The SG list * @nents: Number of SG entries @@ -309,56 +420,29 @@ EXPORT_SYMBOL(sg_alloc_table); static size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, size_t buflen, int to_buffer) { - struct scatterlist *sg; - size_t buf_off = 0; - int i; - - WARN_ON(!irqs_disabled()); - - for_each_sg(sgl, sg, nents, i) { - struct page *page; - int n = 0; - unsigned int sg_off = sg->offset; - unsigned int sg_copy = sg->length; - - if (sg_copy > buflen) - sg_copy = buflen; - buflen -= sg_copy; - - while (sg_copy > 0) { - unsigned int page_copy; - void *p; - - page_copy = PAGE_SIZE - sg_off; - if (page_copy > sg_copy) - page_copy = sg_copy; - - page = nth_page(sg_page(sg), n); - p = kmap_atomic(page, KM_BIO_SRC_IRQ); - - if (to_buffer) - memcpy(buf + buf_off, p + sg_off, page_copy); - else { - memcpy(p + sg_off, buf + buf_off, page_copy); - flush_kernel_dcache_page(page); - } - - kunmap_atomic(p, KM_BIO_SRC_IRQ); - - buf_off += page_copy; - sg_off += page_copy; - if (sg_off == PAGE_SIZE) { - sg_off = 0; - n++; - } - sg_copy -= page_copy; + unsigned int offset = 0; + struct sg_mapping_iter miter; + + sg_miter_start(&miter, sgl, nents, SG_MITER_ATOMIC); + + while (sg_miter_next(&miter) && offset < buflen) { + unsigned int len; + + len = min(miter.length, buflen - offset); + + if (to_buffer) + memcpy(buf + offset, miter.addr, len); + else { + memcpy(miter.addr, buf + offset, len); + flush_kernel_dcache_page(miter.page); } - if (!buflen) - break; + offset += len; } - return buf_off; + sg_miter_stop(&miter); + + return offset; } /** diff --git a/lib/show_mem.c b/lib/show_mem.c new file mode 100644 index 000000000000..238e72a18ce1 --- /dev/null +++ b/lib/show_mem.c @@ -0,0 +1,63 @@ +/* + * Generic show_mem() implementation + * + * Copyright (C) 2008 Johannes Weiner <hannes@saeurebad.de> + * All code subject to the GPL version 2. + */ + +#include <linux/mm.h> +#include <linux/nmi.h> +#include <linux/quicklist.h> + +void show_mem(void) +{ + pg_data_t *pgdat; + unsigned long total = 0, reserved = 0, shared = 0, + nonshared = 0, highmem = 0; + + printk(KERN_INFO "Mem-Info:\n"); + show_free_areas(); + + for_each_online_pgdat(pgdat) { + unsigned long i, flags; + + pgdat_resize_lock(pgdat, &flags); + for (i = 0; i < pgdat->node_spanned_pages; i++) { + struct page *page; + unsigned long pfn = pgdat->node_start_pfn + i; + + if (unlikely(!(i % MAX_ORDER_NR_PAGES))) + touch_nmi_watchdog(); + + if (!pfn_valid(pfn)) + continue; + + page = pfn_to_page(pfn); + + if (PageHighMem(page)) + highmem++; + + if (PageReserved(page)) + reserved++; + else if (page_count(page) == 1) + nonshared++; + else if (page_count(page) > 1) + shared += page_count(page) - 1; + + total++; + } + pgdat_resize_unlock(pgdat, &flags); + } + + printk(KERN_INFO "%lu pages RAM\n", total); +#ifdef CONFIG_HIGHMEM + printk(KERN_INFO "%lu pages HighMem\n", highmem); +#endif + printk(KERN_INFO "%lu pages reserved\n", reserved); + printk(KERN_INFO "%lu pages shared\n", shared); + printk(KERN_INFO "%lu pages non-shared\n", nonshared); +#ifdef CONFIG_QUICKLIST + printk(KERN_INFO "%lu pages in pagetable cache\n", + quicklist_total_size()); +#endif +} diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c index 6c90fb90e19c..0f8fc22ed103 100644 --- a/lib/smp_processor_id.c +++ b/lib/smp_processor_id.c @@ -7,11 +7,10 @@ #include <linux/kallsyms.h> #include <linux/sched.h> -unsigned int debug_smp_processor_id(void) +notrace unsigned int debug_smp_processor_id(void) { unsigned long preempt_count = preempt_count(); int this_cpu = raw_smp_processor_id(); - cpumask_t this_mask; if (likely(preempt_count)) goto out; @@ -23,9 +22,7 @@ unsigned int debug_smp_processor_id(void) * Kernel threads bound to a single CPU can safely use * smp_processor_id(): */ - this_mask = cpumask_of_cpu(this_cpu); - - if (cpus_equal(current->cpus_allowed, this_mask)) + if (cpus_equal(current->cpus_allowed, cpumask_of_cpu(this_cpu))) goto out; /* @@ -37,7 +34,7 @@ unsigned int debug_smp_processor_id(void) /* * Avoid recursion: */ - preempt_disable(); + preempt_disable_notrace(); if (!printk_ratelimit()) goto out_enable; @@ -49,7 +46,7 @@ unsigned int debug_smp_processor_id(void) dump_stack(); out_enable: - preempt_enable_no_resched(); + preempt_enable_no_resched_notrace(); out: return this_cpu; } diff --git a/lib/swiotlb.c b/lib/swiotlb.c index d568894df8cc..977edbdbc1de 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -492,7 +492,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size, */ dma_addr_t handle; handle = swiotlb_map_single(NULL, NULL, size, DMA_FROM_DEVICE); - if (swiotlb_dma_mapping_error(handle)) + if (swiotlb_dma_mapping_error(hwdev, handle)) return NULL; ret = bus_to_virt(handle); @@ -824,7 +824,7 @@ swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, } int -swiotlb_dma_mapping_error(dma_addr_t dma_addr) +swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr) { return (dma_addr == virt_to_bus(io_tlb_overflow_buffer)); } diff --git a/lib/syscall.c b/lib/syscall.c new file mode 100644 index 000000000000..a4f7067f72fa --- /dev/null +++ b/lib/syscall.c @@ -0,0 +1,75 @@ +#include <linux/ptrace.h> +#include <linux/sched.h> +#include <linux/module.h> +#include <asm/syscall.h> + +static int collect_syscall(struct task_struct *target, long *callno, + unsigned long args[6], unsigned int maxargs, + unsigned long *sp, unsigned long *pc) +{ + struct pt_regs *regs = task_pt_regs(target); + if (unlikely(!regs)) + return -EAGAIN; + + *sp = user_stack_pointer(regs); + *pc = instruction_pointer(regs); + + *callno = syscall_get_nr(target, regs); + if (*callno != -1L && maxargs > 0) + syscall_get_arguments(target, regs, 0, maxargs, args); + + return 0; +} + +/** + * task_current_syscall - Discover what a blocked task is doing. + * @target: thread to examine + * @callno: filled with system call number or -1 + * @args: filled with @maxargs system call arguments + * @maxargs: number of elements in @args to fill + * @sp: filled with user stack pointer + * @pc: filled with user PC + * + * If @target is blocked in a system call, returns zero with *@callno + * set to the the call's number and @args filled in with its arguments. + * Registers not used for system call arguments may not be available and + * it is not kosher to use &struct user_regset calls while the system + * call is still in progress. Note we may get this result if @target + * has finished its system call but not yet returned to user mode, such + * as when it's stopped for signal handling or syscall exit tracing. + * + * If @target is blocked in the kernel during a fault or exception, + * returns zero with *@callno set to -1 and does not fill in @args. + * If so, it's now safe to examine @target using &struct user_regset + * get() calls as long as we're sure @target won't return to user mode. + * + * Returns -%EAGAIN if @target does not remain blocked. + * + * Returns -%EINVAL if @maxargs is too large (maximum is six). + */ +int task_current_syscall(struct task_struct *target, long *callno, + unsigned long args[6], unsigned int maxargs, + unsigned long *sp, unsigned long *pc) +{ + long state; + unsigned long ncsw; + + if (unlikely(maxargs > 6)) + return -EINVAL; + + if (target == current) + return collect_syscall(target, callno, args, maxargs, sp, pc); + + state = target->state; + if (unlikely(!state)) + return -EAGAIN; + + ncsw = wait_task_inactive(target, state); + if (unlikely(!ncsw) || + unlikely(collect_syscall(target, callno, args, maxargs, sp, pc)) || + unlikely(wait_task_inactive(target, state) != ncsw)) + return -EAGAIN; + + return 0; +} +EXPORT_SYMBOL_GPL(task_current_syscall); diff --git a/lib/textsearch.c b/lib/textsearch.c index be8bda3862f5..9fbcb44c554f 100644 --- a/lib/textsearch.c +++ b/lib/textsearch.c @@ -54,10 +54,13 @@ * USAGE * * Before a search can be performed, a configuration must be created - * by calling textsearch_prepare() specyfing the searching algorithm and - * the pattern to look for. The returned configuration may then be used - * for an arbitary amount of times and even in parallel as long as a - * separate struct ts_state variable is provided to every instance. + * by calling textsearch_prepare() specifying the searching algorithm, + * the pattern to look for and flags. As a flag, you can set TS_IGNORECASE + * to perform case insensitive matching. But it might slow down + * performance of algorithm, so you should use it at own your risk. + * The returned configuration may then be used for an arbitary + * amount of times and even in parallel as long as a separate struct + * ts_state variable is provided to every instance. * * The actual search is performed by either calling textsearch_find_- * continuous() for linear data or by providing an own get_next_block() @@ -89,7 +92,6 @@ * panic("Oh my god, dancing chickens at %d\n", pos); * * textsearch_destroy(conf); - * * ========================================================================== */ @@ -97,6 +99,7 @@ #include <linux/types.h> #include <linux/string.h> #include <linux/init.h> +#include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/err.h> #include <linux/textsearch.h> @@ -264,7 +267,7 @@ struct ts_config *textsearch_prepare(const char *algo, const void *pattern, return ERR_PTR(-EINVAL); ops = lookup_ts_algo(algo); -#ifdef CONFIG_KMOD +#ifdef CONFIG_MODULES /* * Why not always autoload you may ask. Some users are * in a situation where requesting a module may deadlock, @@ -279,7 +282,7 @@ struct ts_config *textsearch_prepare(const char *algo, const void *pattern, if (ops == NULL) goto errout; - conf = ops->init(pattern, len, gfp_mask); + conf = ops->init(pattern, len, gfp_mask, flags); if (IS_ERR(conf)) { err = PTR_ERR(conf); goto errout; diff --git a/lib/ts_bm.c b/lib/ts_bm.c index d90822c378a4..9e66ee4020e9 100644 --- a/lib/ts_bm.c +++ b/lib/ts_bm.c @@ -39,6 +39,7 @@ #include <linux/module.h> #include <linux/types.h> #include <linux/string.h> +#include <linux/ctype.h> #include <linux/textsearch.h> /* Alphabet size, use ASCII */ @@ -63,7 +64,8 @@ static unsigned int bm_find(struct ts_config *conf, struct ts_state *state) struct ts_bm *bm = ts_config_priv(conf); unsigned int i, text_len, consumed = state->offset; const u8 *text; - int shift = bm->patlen, bs; + int shift = bm->patlen - 1, bs; + const u8 icase = conf->flags & TS_IGNORECASE; for (;;) { text_len = conf->get_next_block(consumed, &text, conf, state); @@ -75,7 +77,9 @@ static unsigned int bm_find(struct ts_config *conf, struct ts_state *state) DEBUGP("Searching in position %d (%c)\n", shift, text[shift]); for (i = 0; i < bm->patlen; i++) - if (text[shift-i] != bm->pattern[bm->patlen-1-i]) + if ((icase ? toupper(text[shift-i]) + : text[shift-i]) + != bm->pattern[bm->patlen-1-i]) goto next; /* London calling... */ @@ -111,14 +115,18 @@ static int subpattern(u8 *pattern, int i, int j, int g) return ret; } -static void compute_prefix_tbl(struct ts_bm *bm) +static void compute_prefix_tbl(struct ts_bm *bm, int flags) { int i, j, g; for (i = 0; i < ASIZE; i++) bm->bad_shift[i] = bm->patlen; - for (i = 0; i < bm->patlen - 1; i++) + for (i = 0; i < bm->patlen - 1; i++) { bm->bad_shift[bm->pattern[i]] = bm->patlen - 1 - i; + if (flags & TS_IGNORECASE) + bm->bad_shift[tolower(bm->pattern[i])] + = bm->patlen - 1 - i; + } /* Compute the good shift array, used to match reocurrences * of a subpattern */ @@ -135,10 +143,11 @@ static void compute_prefix_tbl(struct ts_bm *bm) } static struct ts_config *bm_init(const void *pattern, unsigned int len, - gfp_t gfp_mask) + gfp_t gfp_mask, int flags) { struct ts_config *conf; struct ts_bm *bm; + int i; unsigned int prefix_tbl_len = len * sizeof(unsigned int); size_t priv_size = sizeof(*bm) + len + prefix_tbl_len; @@ -146,11 +155,16 @@ static struct ts_config *bm_init(const void *pattern, unsigned int len, if (IS_ERR(conf)) return conf; + conf->flags = flags; bm = ts_config_priv(conf); bm->patlen = len; bm->pattern = (u8 *) bm->good_shift + prefix_tbl_len; - memcpy(bm->pattern, pattern, len); - compute_prefix_tbl(bm); + if (flags & TS_IGNORECASE) + for (i = 0; i < len; i++) + bm->pattern[i] = toupper(((u8 *)pattern)[i]); + else + memcpy(bm->pattern, pattern, len); + compute_prefix_tbl(bm, flags); return conf; } diff --git a/lib/ts_fsm.c b/lib/ts_fsm.c index af575b61526b..5696a35184e4 100644 --- a/lib/ts_fsm.c +++ b/lib/ts_fsm.c @@ -257,7 +257,7 @@ found_match: } static struct ts_config *fsm_init(const void *pattern, unsigned int len, - gfp_t gfp_mask) + gfp_t gfp_mask, int flags) { int i, err = -EINVAL; struct ts_config *conf; @@ -269,6 +269,9 @@ static struct ts_config *fsm_init(const void *pattern, unsigned int len, if (len % sizeof(struct ts_fsm_token) || ntokens < 1) goto errout; + if (flags & TS_IGNORECASE) + goto errout; + for (i = 0; i < ntokens; i++) { struct ts_fsm_token *t = &tokens[i]; @@ -284,6 +287,7 @@ static struct ts_config *fsm_init(const void *pattern, unsigned int len, if (IS_ERR(conf)) return conf; + conf->flags = flags; fsm = ts_config_priv(conf); fsm->ntokens = ntokens; memcpy(fsm->tokens, pattern, len); diff --git a/lib/ts_kmp.c b/lib/ts_kmp.c index 3ced628cab4b..632f783e65f1 100644 --- a/lib/ts_kmp.c +++ b/lib/ts_kmp.c @@ -33,6 +33,7 @@ #include <linux/module.h> #include <linux/types.h> #include <linux/string.h> +#include <linux/ctype.h> #include <linux/textsearch.h> struct ts_kmp @@ -47,6 +48,7 @@ static unsigned int kmp_find(struct ts_config *conf, struct ts_state *state) struct ts_kmp *kmp = ts_config_priv(conf); unsigned int i, q = 0, text_len, consumed = state->offset; const u8 *text; + const int icase = conf->flags & TS_IGNORECASE; for (;;) { text_len = conf->get_next_block(consumed, &text, conf, state); @@ -55,9 +57,11 @@ static unsigned int kmp_find(struct ts_config *conf, struct ts_state *state) break; for (i = 0; i < text_len; i++) { - while (q > 0 && kmp->pattern[q] != text[i]) + while (q > 0 && kmp->pattern[q] + != (icase ? toupper(text[i]) : text[i])) q = kmp->prefix_tbl[q - 1]; - if (kmp->pattern[q] == text[i]) + if (kmp->pattern[q] + == (icase ? toupper(text[i]) : text[i])) q++; if (unlikely(q == kmp->pattern_len)) { state->offset = consumed + i + 1; @@ -72,24 +76,28 @@ static unsigned int kmp_find(struct ts_config *conf, struct ts_state *state) } static inline void compute_prefix_tbl(const u8 *pattern, unsigned int len, - unsigned int *prefix_tbl) + unsigned int *prefix_tbl, int flags) { unsigned int k, q; + const u8 icase = flags & TS_IGNORECASE; for (k = 0, q = 1; q < len; q++) { - while (k > 0 && pattern[k] != pattern[q]) + while (k > 0 && (icase ? toupper(pattern[k]) : pattern[k]) + != (icase ? toupper(pattern[q]) : pattern[q])) k = prefix_tbl[k-1]; - if (pattern[k] == pattern[q]) + if ((icase ? toupper(pattern[k]) : pattern[k]) + == (icase ? toupper(pattern[q]) : pattern[q])) k++; prefix_tbl[q] = k; } } static struct ts_config *kmp_init(const void *pattern, unsigned int len, - gfp_t gfp_mask) + gfp_t gfp_mask, int flags) { struct ts_config *conf; struct ts_kmp *kmp; + int i; unsigned int prefix_tbl_len = len * sizeof(unsigned int); size_t priv_size = sizeof(*kmp) + len + prefix_tbl_len; @@ -97,11 +105,16 @@ static struct ts_config *kmp_init(const void *pattern, unsigned int len, if (IS_ERR(conf)) return conf; + conf->flags = flags; kmp = ts_config_priv(conf); kmp->pattern_len = len; - compute_prefix_tbl(pattern, len, kmp->prefix_tbl); + compute_prefix_tbl(pattern, len, kmp->prefix_tbl, flags); kmp->pattern = (u8 *) kmp->prefix_tbl + prefix_tbl_len; - memcpy(kmp->pattern, pattern, len); + if (flags & TS_IGNORECASE) + for (i = 0; i < len; i++) + kmp->pattern[i] = toupper(((u8 *)pattern)[i]); + else + memcpy(kmp->pattern, pattern, len); return conf; } diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 6021757a4496..1dc2d1d18fa8 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -22,6 +22,8 @@ #include <linux/string.h> #include <linux/ctype.h> #include <linux/kernel.h> +#include <linux/kallsyms.h> +#include <linux/uaccess.h> #include <asm/page.h> /* for PAGE_SIZE */ #include <asm/div64.h> @@ -482,6 +484,89 @@ static char *number(char *buf, char *end, unsigned long long num, int base, int return buf; } +static char *string(char *buf, char *end, char *s, int field_width, int precision, int flags) +{ + int len, i; + + if ((unsigned long)s < PAGE_SIZE) + s = "<NULL>"; + + len = strnlen(s, precision); + + if (!(flags & LEFT)) { + while (len < field_width--) { + if (buf < end) + *buf = ' '; + ++buf; + } + } + for (i = 0; i < len; ++i) { + if (buf < end) + *buf = *s; + ++buf; ++s; + } + while (len < field_width--) { + if (buf < end) + *buf = ' '; + ++buf; + } + return buf; +} + +static inline void *dereference_function_descriptor(void *ptr) +{ +#if defined(CONFIG_IA64) || defined(CONFIG_PPC64) + void *p; + if (!probe_kernel_address(ptr, p)) + ptr = p; +#endif + return ptr; +} + +static char *symbol_string(char *buf, char *end, void *ptr, int field_width, int precision, int flags) +{ + unsigned long value = (unsigned long) ptr; +#ifdef CONFIG_KALLSYMS + char sym[KSYM_SYMBOL_LEN]; + sprint_symbol(sym, value); + return string(buf, end, sym, field_width, precision, flags); +#else + field_width = 2*sizeof(void *); + flags |= SPECIAL | SMALL | ZEROPAD; + return number(buf, end, value, 16, field_width, precision, flags); +#endif +} + +/* + * Show a '%p' thing. A kernel extension is that the '%p' is followed + * by an extra set of alphanumeric characters that are extended format + * specifiers. + * + * Right now we just handle 'F' (for symbolic Function descriptor pointers) + * and 'S' (for Symbolic direct pointers), but this can easily be + * extended in the future (network address types etc). + * + * The difference between 'S' and 'F' is that on ia64 and ppc64 function + * pointers are really function descriptors, which contain a pointer the + * real address. + */ +static char *pointer(const char *fmt, char *buf, char *end, void *ptr, int field_width, int precision, int flags) +{ + switch (*fmt) { + case 'F': + ptr = dereference_function_descriptor(ptr); + /* Fallthrough */ + case 'S': + return symbol_string(buf, end, ptr, field_width, precision, flags); + } + flags |= SMALL; + if (field_width == -1) { + field_width = 2*sizeof(void *); + flags |= ZEROPAD; + } + return number(buf, end, (unsigned long) ptr, 16, field_width, precision, flags); +} + /** * vsnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into @@ -502,11 +587,9 @@ static char *number(char *buf, char *end, unsigned long long num, int base, int */ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) { - int len; unsigned long long num; - int i, base; + int base; char *str, *end, c; - const char *s; int flags; /* flags to number() */ @@ -622,43 +705,18 @@ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) continue; case 's': - s = va_arg(args, char *); - if ((unsigned long)s < PAGE_SIZE) - s = "<NULL>"; - - len = strnlen(s, precision); - - if (!(flags & LEFT)) { - while (len < field_width--) { - if (str < end) - *str = ' '; - ++str; - } - } - for (i = 0; i < len; ++i) { - if (str < end) - *str = *s; - ++str; ++s; - } - while (len < field_width--) { - if (str < end) - *str = ' '; - ++str; - } + str = string(str, end, va_arg(args, char *), field_width, precision, flags); continue; case 'p': - flags |= SMALL; - if (field_width == -1) { - field_width = 2*sizeof(void *); - flags |= ZEROPAD; - } - str = number(str, end, - (unsigned long) va_arg(args, void *), - 16, field_width, precision, flags); + str = pointer(fmt+1, str, end, + va_arg(args, void *), + field_width, precision, flags); + /* Skip all alphanumeric pointer suffixes */ + while (isalnum(fmt[1])) + fmt++; continue; - case 'n': /* FIXME: * What does C99 say about the overflow case here? */ |