From da29aa8f2ab178903a1ac23ce19442f92be4f09c Mon Sep 17 00:00:00 2001 From: Seth Jennings Date: Thu, 19 Jul 2012 09:42:39 -0500 Subject: powerpc/crypto: add compression support to arch vec This patch enables compression engine support in the architecture vector. This causes the Power hypervisor to allow access to the nx comrpession accelerator. Signed-off-by: Seth Jennings Signed-off-by: Herbert Xu --- arch/powerpc/kernel/prom_init.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 0794a3017b1b..9ec5e5525777 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -705,6 +705,7 @@ static void __init early_cmdline_parse(void) #endif #define OV5_TYPE1_AFFINITY 0x80 /* Type 1 NUMA affinity */ #define OV5_PFO_HW_RNG 0x80 /* PFO Random Number Generator */ +#define OV5_PFO_HW_842 0x40 /* PFO Compression Accelerator */ #define OV5_PFO_HW_ENCR 0x20 /* PFO Encryption Accelerator */ /* Option Vector 6: IBM PAPR hints */ @@ -774,8 +775,7 @@ static unsigned char ibm_architecture_vec[] = { 0, 0, 0, - OV5_PFO_HW_RNG | OV5_PFO_HW_ENCR, - + OV5_PFO_HW_RNG | OV5_PFO_HW_ENCR | OV5_PFO_HW_842, /* option vector 6: IBM PAPR hints */ 4 - 2, /* length */ 0, -- cgit v1.3-14-g43fede From baa36046d09ea6dbc122c795566992318663d9eb Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 18 Jun 2012 17:54:14 +0200 Subject: cputime: Consolidate vtime handling on context switch The archs that implement virtual cputime accounting all flush the cputime of a task when it gets descheduled and sometimes set up some ground initialization for the next task to account its cputime. These archs all put their own hooks in their context switch callbacks and handle the off-case themselves. Consolidate this by creating a new account_switch_vtime() callback called in generic code right after a context switch and that these archs must implement to flush the prev task cputime and initialize the next task cputime related state. Signed-off-by: Frederic Weisbecker Acked-by: Martin Schwidefsky Cc: Tony Luck Cc: Fenghua Yu Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Heiko Carstens Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra --- arch/ia64/include/asm/switch_to.h | 8 -------- arch/ia64/kernel/time.c | 4 ++-- arch/powerpc/include/asm/time.h | 6 ------ arch/powerpc/kernel/process.c | 3 --- arch/powerpc/kernel/time.c | 6 ++++++ arch/s390/include/asm/switch_to.h | 2 -- arch/s390/kernel/vtime.c | 4 ++-- include/linux/kernel_stat.h | 6 ++++++ kernel/sched/core.c | 1 + 9 files changed, 17 insertions(+), 23 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/ia64/include/asm/switch_to.h b/arch/ia64/include/asm/switch_to.h index cb2412fcd17f..d38c7ea5eea5 100644 --- a/arch/ia64/include/asm/switch_to.h +++ b/arch/ia64/include/asm/switch_to.h @@ -30,13 +30,6 @@ extern struct task_struct *ia64_switch_to (void *next_task); extern void ia64_save_extra (struct task_struct *task); extern void ia64_load_extra (struct task_struct *task); -#ifdef CONFIG_VIRT_CPU_ACCOUNTING -extern void ia64_account_on_switch (struct task_struct *prev, struct task_struct *next); -# define IA64_ACCOUNT_ON_SWITCH(p,n) ia64_account_on_switch(p,n) -#else -# define IA64_ACCOUNT_ON_SWITCH(p,n) -#endif - #ifdef CONFIG_PERFMON DECLARE_PER_CPU(unsigned long, pfm_syst_info); # define PERFMON_IS_SYSWIDE() (__get_cpu_var(pfm_syst_info) & 0x1) @@ -49,7 +42,6 @@ extern void ia64_account_on_switch (struct task_struct *prev, struct task_struct || PERFMON_IS_SYSWIDE()) #define __switch_to(prev,next,last) do { \ - IA64_ACCOUNT_ON_SWITCH(prev, next); \ if (IA64_HAS_EXTRA_STATE(prev)) \ ia64_save_extra(prev); \ if (IA64_HAS_EXTRA_STATE(next)) \ diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index ecc904b33c5f..6247197b9877 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -88,10 +88,10 @@ extern cputime_t cycle_to_cputime(u64 cyc); * accumulated times to the current process, and to prepare accounting on * the next process. */ -void ia64_account_on_switch(struct task_struct *prev, struct task_struct *next) +void account_switch_vtime(struct task_struct *prev) { struct thread_info *pi = task_thread_info(prev); - struct thread_info *ni = task_thread_info(next); + struct thread_info *ni = task_thread_info(current); cputime_t delta_stime, delta_utime; __u64 now; diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index 3b4b4a8da922..c1f267694acb 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -197,12 +197,6 @@ struct cpu_usage { DECLARE_PER_CPU(struct cpu_usage, cpu_usage_array); -#if defined(CONFIG_VIRT_CPU_ACCOUNTING) -#define account_process_vtime(tsk) account_process_tick(tsk, 0) -#else -#define account_process_vtime(tsk) do { } while (0) -#endif - extern void secondary_cpu_time_init(void); DECLARE_PER_CPU(u64, decrementers_next_tb); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 710f400476de..d73fa999b47b 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -514,9 +514,6 @@ struct task_struct *__switch_to(struct task_struct *prev, local_irq_save(flags); - account_system_vtime(current); - account_process_vtime(current); - /* * We can't take a PMU exception inside _switch() since there is a * window where the kernel stack SLB and the kernel stack are out diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index be171ee73bf8..49da7f06e643 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -366,6 +366,12 @@ void account_process_tick(struct task_struct *tsk, int user_tick) account_user_time(tsk, utime, utimescaled); } +void account_switch_vtime(struct task_struct *prev) +{ + account_system_vtime(prev); + account_process_tick(prev, 0); +} + #else /* ! CONFIG_VIRT_CPU_ACCOUNTING */ #define calc_cputime_factors() #endif diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h index f223068b7822..e7f9b3d04fa1 100644 --- a/arch/s390/include/asm/switch_to.h +++ b/arch/s390/include/asm/switch_to.h @@ -89,12 +89,10 @@ static inline void restore_access_regs(unsigned int *acrs) prev = __switch_to(prev,next); \ } while (0) -extern void account_vtime(struct task_struct *, struct task_struct *); extern void account_tick_vtime(struct task_struct *); #define finish_arch_switch(prev) do { \ set_fs(current->thread.mm_segment); \ - account_vtime(prev, current); \ } while (0) #endif /* __ASM_SWITCH_TO_H */ diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index 4fc97b40a6e1..449ac22cc71b 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -99,7 +99,7 @@ static int do_account_vtime(struct task_struct *tsk, int hardirq_offset) return virt_timer_forward(user + system); } -void account_vtime(struct task_struct *prev, struct task_struct *next) +void account_switch_vtime(struct task_struct *prev) { struct thread_info *ti; @@ -107,7 +107,7 @@ void account_vtime(struct task_struct *prev, struct task_struct *next) ti = task_thread_info(prev); ti->user_timer = S390_lowcore.user_timer; ti->system_timer = S390_lowcore.system_timer; - ti = task_thread_info(next); + ti = task_thread_info(current); S390_lowcore.user_timer = ti->user_timer; S390_lowcore.system_timer = ti->system_timer; } diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 2fbd9053c2df..bbe5d15d6597 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -130,4 +130,10 @@ extern void account_process_tick(struct task_struct *, int user); extern void account_steal_ticks(unsigned long ticks); extern void account_idle_ticks(unsigned long ticks); +#ifdef CONFIG_VIRT_CPU_ACCOUNTING +extern void account_switch_vtime(struct task_struct *prev); +#else +static inline void account_switch_vtime(struct task_struct *prev) { } +#endif + #endif /* _LINUX_KERNEL_STAT_H */ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index ae3bcaa3afbf..78d9c965433a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1796,6 +1796,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) * Manfred Spraul */ prev_state = prev->state; + account_switch_vtime(prev); finish_arch_switch(prev); #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW local_irq_disable(); -- cgit v1.3-14-g43fede From 4a727429abec31c4f5d9607cebb4fb1cc21e1167 Mon Sep 17 00:00:00 2001 From: Ashley Lai Date: Tue, 14 Aug 2012 18:34:57 -0500 Subject: PPC64: Add support for instantiating SML from Open Firmware This patch instantiate Stored Measurement Log (SML) and put the log address and size in the device tree. Signed-off-by: Ashley Lai Signed-off-by: Kent Yoder --- arch/powerpc/kernel/prom_init.c | 62 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 62 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 0794a3017b1b..e144498bcddd 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -1623,6 +1623,63 @@ static void __init prom_instantiate_rtas(void) } #ifdef CONFIG_PPC64 +/* + * Allocate room for and instantiate Stored Measurement Log (SML) + */ +static void __init prom_instantiate_sml(void) +{ + phandle ibmvtpm_node; + ihandle ibmvtpm_inst; + u32 entry = 0, size = 0; + u64 base; + + prom_debug("prom_instantiate_sml: start...\n"); + + ibmvtpm_node = call_prom("finddevice", 1, 1, ADDR("/ibm,vtpm")); + prom_debug("ibmvtpm_node: %x\n", ibmvtpm_node); + if (!PHANDLE_VALID(ibmvtpm_node)) + return; + + ibmvtpm_inst = call_prom("open", 1, 1, ADDR("/ibm,vtpm")); + if (!IHANDLE_VALID(ibmvtpm_inst)) { + prom_printf("opening vtpm package failed (%x)\n", ibmvtpm_inst); + return; + } + + if (call_prom_ret("call-method", 2, 2, &size, + ADDR("sml-get-handover-size"), + ibmvtpm_inst) != 0 || size == 0) { + prom_printf("SML get handover size failed\n"); + return; + } + + base = alloc_down(size, PAGE_SIZE, 0); + if (base == 0) + prom_panic("Could not allocate memory for sml\n"); + + prom_printf("instantiating sml at 0x%x...", base); + + if (call_prom_ret("call-method", 4, 2, &entry, + ADDR("sml-handover"), + ibmvtpm_inst, size, base) != 0 || entry == 0) { + prom_printf("SML handover failed\n"); + return; + } + prom_printf(" done\n"); + + reserve_mem(base, size); + + prom_setprop(ibmvtpm_node, "/ibm,vtpm", "linux,sml-base", + &base, sizeof(base)); + prom_setprop(ibmvtpm_node, "/ibm,vtpm", "linux,sml-size", + &size, sizeof(size)); + + prom_debug("sml base = 0x%x\n", base); + prom_debug("sml size = 0x%x\n", (long)size); + + prom_debug("prom_instantiate_sml: end...\n"); +} + /* * Allocate room for and initialize TCE tables */ @@ -2916,6 +2973,11 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, prom_instantiate_opal(); #endif +#ifdef CONFIG_PPC64 + /* instantiate sml */ + prom_instantiate_sml(); +#endif + /* * On non-powermacs, put all CPUs in spin-loops. * -- cgit v1.3-14-g43fede From 3d2675238a71545372f19723f9f066e8ad831f70 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 25 Jul 2012 21:19:56 +0000 Subject: powerpc/kernel: Remove uses of abs_to_virt() and virt_to_abs() These days they are just __va() and __pa() respectively. Signed-off-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/dma.c | 3 +-- arch/powerpc/kernel/rtas_flash.c | 7 +++---- 2 files changed, 4 insertions(+), 6 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index 355b9d84b0f8..8032b97ccdcb 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -14,7 +14,6 @@ #include #include #include -#include #include /* @@ -50,7 +49,7 @@ void *dma_direct_alloc_coherent(struct device *dev, size_t size, return NULL; ret = page_address(page); memset(ret, 0, size); - *dma_handle = virt_to_abs(ret) + get_dma_offset(dev); + *dma_handle = __pa(ret) + get_dma_offset(dev); return ret; #endif diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c index 2c0ee6405633..20b0120db0c3 100644 --- a/arch/powerpc/kernel/rtas_flash.c +++ b/arch/powerpc/kernel/rtas_flash.c @@ -21,7 +21,6 @@ #include #include #include -#include #define MODULE_VERS "1.0" #define MODULE_NAME "rtas_flash" @@ -582,7 +581,7 @@ static void rtas_flash_firmware(int reboot_type) flist = (struct flash_block_list *)&rtas_data_buf[0]; flist->num_blocks = 0; flist->next = rtas_firmware_flash_list; - rtas_block_list = virt_to_abs(flist); + rtas_block_list = __pa(flist); if (rtas_block_list >= 4UL*1024*1024*1024) { printk(KERN_ALERT "FLASH: kernel bug...flash list header addr above 4GB\n"); spin_unlock(&rtas_data_buf_lock); @@ -596,13 +595,13 @@ static void rtas_flash_firmware(int reboot_type) for (f = flist; f; f = next) { /* Translate data addrs to absolute */ for (i = 0; i < f->num_blocks; i++) { - f->blocks[i].data = (char *)virt_to_abs(f->blocks[i].data); + f->blocks[i].data = (char *)__pa(f->blocks[i].data); image_size += f->blocks[i].length; } next = f->next; /* Don't translate NULL pointer for last entry */ if (f->next) - f->next = (struct flash_block_list *)virt_to_abs(f->next); + f->next = (struct flash_block_list *)__pa(f->next); else f->next = NULL; /* make num_blocks into the version/length field */ -- cgit v1.3-14-g43fede From beacc6da8649f5c0841ac9b326dcf0c4dad823cd Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 25 Jul 2012 21:20:03 +0000 Subject: powerpc: Remove all includes of It's empty now, apart from other includes. Fixup a few files that were getting things via this header. Signed-off-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/dma-swiotlb.c | 2 +- arch/powerpc/kernel/ibmebus.c | 1 - arch/powerpc/kernel/vio.c | 1 - arch/powerpc/mm/hash_native_64.c | 2 +- arch/powerpc/mm/init_64.c | 1 - arch/powerpc/mm/pgtable_64.c | 1 - arch/powerpc/platforms/pasemi/iommu.c | 1 + arch/powerpc/platforms/powernv/pci-ioda.c | 1 - arch/powerpc/platforms/powernv/pci-p5ioc2.c | 1 - arch/powerpc/platforms/powernv/pci.c | 1 - arch/powerpc/platforms/pseries/iommu.c | 1 + arch/powerpc/platforms/pseries/lpar.c | 1 - 12 files changed, 4 insertions(+), 10 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c index 46943651da23..a720b54b971c 100644 --- a/arch/powerpc/kernel/dma-swiotlb.c +++ b/arch/powerpc/kernel/dma-swiotlb.c @@ -12,6 +12,7 @@ */ #include +#include #include #include #include @@ -20,7 +21,6 @@ #include #include #include -#include unsigned int ppc_swiotlb_enable; diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index b01d14eeca8d..8220baa46faf 100644 --- a/arch/powerpc/kernel/ibmebus.c +++ b/arch/powerpc/kernel/ibmebus.c @@ -47,7 +47,6 @@ #include #include #include -#include static struct device ibmebus_bus_device = { /* fake "parent" device */ .init_name = "ibmebus", diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index 02b32216bbc3..201ba59738be 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -33,7 +33,6 @@ #include #include #include -#include #include #include diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index 90039bc64119..f21e8ce8db33 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -14,10 +14,10 @@ #include #include +#include #include #include -#include #include #include #include diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 620b7acd2fdf..95a45293e5ac 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -62,7 +62,6 @@ #include #include #include -#include #include #include "mmu_decl.h" diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 249a0631c4db..297d49547ea8 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -51,7 +51,6 @@ #include #include #include -#include #include #include "mmu_decl.h" diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c index f03fbc2b0f59..7d2d036754b5 100644 --- a/arch/powerpc/platforms/pasemi/iommu.c +++ b/arch/powerpc/platforms/pasemi/iommu.c @@ -19,6 +19,7 @@ #undef DEBUG +#include #include #include #include diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 9cda6a1ad0cf..5e75dcfe51b9 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -30,7 +30,6 @@ #include #include #include -#include #include "powernv.h" #include "pci.h" diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c index 264967770c3a..6b4bef4e9d82 100644 --- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c +++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c @@ -30,7 +30,6 @@ #include #include #include -#include #include "powernv.h" #include "pci.h" diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index be3cfc5ceabb..1e908aef4201 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -30,7 +30,6 @@ #include #include #include -#include #include #include "powernv.h" diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index e150093d417a..6153eea27ce7 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include /* for show_stack */ #include diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 5f3ef876ded2..177055d0186b 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -31,7 +31,6 @@ #include #include #include -#include #include #include #include -- cgit v1.3-14-g43fede From d3dbeef657fdc9e870e0b01f811bbb906af052f8 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Sun, 19 Aug 2012 21:44:01 +0000 Subject: powerpc: Rename 64-bit PVR constants to PVR_foo We have an old FIXME in reg.h which points out that we should standardise on PVR_foo for our PVR #defines. Currently we use PVR_ on 32-bit and PV_ on 64-bit. So do that rename and remove the FIXME. Seeing as we're touching all but one usage of __is_processor(), rename it to something less ugly and more indicative of what it does, which is simply to check the PVR version. Signed-off-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/reg.h | 39 ++++++++++++++++----------------- arch/powerpc/kernel/prom_init.c | 2 +- arch/powerpc/oprofile/op_model_power4.c | 16 +++++++------- arch/powerpc/perf/core-book3s.c | 2 +- drivers/scsi/ipr.c | 18 +++++++-------- 5 files changed, 38 insertions(+), 39 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 638608677e2a..43bb15fc899b 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -937,7 +937,7 @@ #define PVR_VER(pvr) (((pvr) >> 16) & 0xFFFF) /* Version field */ #define PVR_REV(pvr) (((pvr) >> 0) & 0xFFFF) /* Revison field */ -#define __is_processor(pv) (PVR_VER(mfspr(SPRN_PVR)) == (pv)) +#define pvr_version_is(pvr) (PVR_VER(mfspr(SPRN_PVR)) == (pvr)) /* * IBM has further subdivided the standard PowerPC 16-bit version and @@ -1002,25 +1002,24 @@ #define PVR_476_ISS 0x00052000 /* 64-bit processors */ -/* XXX the prefix should be PVR_, we'll do a global sweep to fix it one day */ -#define PV_NORTHSTAR 0x0033 -#define PV_PULSAR 0x0034 -#define PV_POWER4 0x0035 -#define PV_ICESTAR 0x0036 -#define PV_SSTAR 0x0037 -#define PV_POWER4p 0x0038 -#define PV_970 0x0039 -#define PV_POWER5 0x003A -#define PV_POWER5p 0x003B -#define PV_970FX 0x003C -#define PV_POWER6 0x003E -#define PV_POWER7 0x003F -#define PV_630 0x0040 -#define PV_630p 0x0041 -#define PV_970MP 0x0044 -#define PV_970GX 0x0045 -#define PV_BE 0x0070 -#define PV_PA6T 0x0090 +#define PVR_NORTHSTAR 0x0033 +#define PVR_PULSAR 0x0034 +#define PVR_POWER4 0x0035 +#define PVR_ICESTAR 0x0036 +#define PVR_SSTAR 0x0037 +#define PVR_POWER4p 0x0038 +#define PVR_970 0x0039 +#define PVR_POWER5 0x003A +#define PVR_POWER5p 0x003B +#define PVR_970FX 0x003C +#define PVR_POWER6 0x003E +#define PVR_POWER7 0x003F +#define PVR_630 0x0040 +#define PVR_630p 0x0041 +#define PVR_970MP 0x0044 +#define PVR_970GX 0x0045 +#define PVR_BE 0x0070 +#define PVR_PA6T 0x0090 /* Macros for setting and retrieving special purpose registers */ #ifndef __ASSEMBLY__ diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 0794a3017b1b..ce68278a5d73 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -1691,7 +1691,7 @@ static void __init prom_initialize_tce_table(void) * else will impact performance, so we always allocate 8MB. * Anton */ - if (__is_processor(PV_POWER4) || __is_processor(PV_POWER4p)) + if (pvr_version_is(PVR_POWER4) || pvr_version_is(PVR_POWER4p)) minsize = 8UL << 20; else minsize = 4UL << 20; diff --git a/arch/powerpc/oprofile/op_model_power4.c b/arch/powerpc/oprofile/op_model_power4.c index 95ae77dec3f6..caffffa5b8f2 100644 --- a/arch/powerpc/oprofile/op_model_power4.c +++ b/arch/powerpc/oprofile/op_model_power4.c @@ -61,10 +61,10 @@ static int power4_reg_setup(struct op_counter_config *ctr, else mmcr0_val |= MMCR0_PROBLEM_DISABLE; - if (__is_processor(PV_POWER4) || __is_processor(PV_POWER4p) || - __is_processor(PV_970) || __is_processor(PV_970FX) || - __is_processor(PV_970MP) || __is_processor(PV_970GX) || - __is_processor(PV_POWER5) || __is_processor(PV_POWER5p)) + if (pvr_version_is(PVR_POWER4) || pvr_version_is(PVR_POWER4p) || + pvr_version_is(PVR_970) || pvr_version_is(PVR_970FX) || + pvr_version_is(PVR_970MP) || pvr_version_is(PVR_970GX) || + pvr_version_is(PVR_POWER5) || pvr_version_is(PVR_POWER5p)) use_slot_nums = 1; return 0; @@ -84,9 +84,9 @@ extern void ppc_enable_pmcs(void); */ static inline int mmcra_must_set_sample(void) { - if (__is_processor(PV_POWER4) || __is_processor(PV_POWER4p) || - __is_processor(PV_970) || __is_processor(PV_970FX) || - __is_processor(PV_970MP) || __is_processor(PV_970GX)) + if (pvr_version_is(PVR_POWER4) || pvr_version_is(PVR_POWER4p) || + pvr_version_is(PVR_970) || pvr_version_is(PVR_970FX) || + pvr_version_is(PVR_970MP) || pvr_version_is(PVR_970GX)) return 1; return 0; @@ -276,7 +276,7 @@ static bool pmc_overflow(unsigned long val) * PMCs because a user might set a period of less than 256 and we * don't want to mistakenly reset them. */ - if (__is_processor(PV_POWER7) && ((0x80000000 - val) <= 256)) + if (pvr_version_is(PVR_POWER7) && ((0x80000000 - val) <= 256)) return true; return false; diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 77b49ddda9d3..331cf090857d 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1396,7 +1396,7 @@ static bool pmc_overflow(unsigned long val) * PMCs because a user might set a period of less than 256 and we * don't want to mistakenly reset them. */ - if (__is_processor(PV_POWER7) && ((0x80000000 - val) <= 256)) + if (pvr_version_is(PVR_POWER7) && ((0x80000000 - val) <= 256)) return true; return false; diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 467dc38246f9..6077c43edacc 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -6304,14 +6304,14 @@ static struct ata_port_info sata_port_info = { #ifdef CONFIG_PPC_PSERIES static const u16 ipr_blocked_processors[] = { - PV_NORTHSTAR, - PV_PULSAR, - PV_POWER4, - PV_ICESTAR, - PV_SSTAR, - PV_POWER4p, - PV_630, - PV_630p + PVR_NORTHSTAR, + PVR_PULSAR, + PVR_POWER4, + PVR_ICESTAR, + PVR_SSTAR, + PVR_POWER4p, + PVR_630, + PVR_630p }; /** @@ -6331,7 +6331,7 @@ static int ipr_invalid_adapter(struct ipr_ioa_cfg *ioa_cfg) if ((ioa_cfg->type == 0x5702) && (ioa_cfg->pdev->revision < 4)) { for (i = 0; i < ARRAY_SIZE(ipr_blocked_processors); i++){ - if (__is_processor(ipr_blocked_processors[i])) + if (pvr_version_is(ipr_blocked_processors[i])) return 1; } } -- cgit v1.3-14-g43fede From 41ab5266c3622354353433618edb92ab278025fa Mon Sep 17 00:00:00 2001 From: Ananth N Mavinakayanahalli Date: Thu, 23 Aug 2012 21:27:09 +0000 Subject: powerpc: Add trap_nr to thread_struct Add thread_struct.trap_nr and use it to store the last exception the thread experienced. In this patch, we populate the field at various places where we force_sig_info() to the process. This is also used in uprobes to determine if the probed instruction caused an exception. Signed-off-by: Ananth N Mavinakayanahalli Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/processor.h | 1 + arch/powerpc/kernel/process.c | 2 ++ arch/powerpc/kernel/traps.c | 1 + arch/powerpc/mm/fault.c | 1 + 4 files changed, 5 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 53b6dfa83344..e0f6710d1983 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -219,6 +219,7 @@ struct thread_struct { #endif /* CONFIG_HAVE_HW_BREAKPOINT */ #endif unsigned long dabr; /* Data address breakpoint register */ + unsigned long trap_nr; /* last trap # on this thread */ #ifdef CONFIG_ALTIVEC /* Complete AltiVec register set */ vector128 vr[32] __attribute__((aligned(16))); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 710f400476de..8e701a4ed36b 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -258,6 +258,7 @@ void do_send_trap(struct pt_regs *regs, unsigned long address, { siginfo_t info; + current->thread.trap_nr = signal_code; if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, error_code, 11, SIGSEGV) == NOTIFY_STOP) return; @@ -275,6 +276,7 @@ void do_dabr(struct pt_regs *regs, unsigned long address, { siginfo_t info; + current->thread.trap_nr = TRAP_HWBKPT; if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, error_code, 11, SIGSEGV) == NOTIFY_STOP) return; diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 158972341a2d..8831322962d3 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -251,6 +251,7 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr) if (arch_irqs_disabled() && !arch_irq_disabled_regs(regs)) local_irq_enable(); + current->thread.trap_nr = code; memset(&info, 0, sizeof(info)); info.si_signo = signr; info.si_code = code; diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 08ffcf52a856..995f924e007f 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -133,6 +133,7 @@ static int do_sigbus(struct pt_regs *regs, unsigned long address) up_read(¤t->mm->mmap_sem); if (user_mode(regs)) { + current->thread.trap_nr = BUS_ADRERR; info.si_signo = SIGBUS; info.si_errno = 0; info.si_code = BUS_ADRERR; -- cgit v1.3-14-g43fede From 8b7b80b9ebb46dd88fbb94e918297295cf312b59 Mon Sep 17 00:00:00 2001 From: Ananth N Mavinakayanahalli Date: Thu, 23 Aug 2012 21:31:32 +0000 Subject: powerpc: Uprobes port to powerpc This is the port of uprobes to powerpc. Usage is similar to x86. [root@xxxx ~]# ./bin/perf probe -x /lib64/libc.so.6 malloc Added new event: probe_libc:malloc (on 0xb4860) You can now use it in all perf tools, such as: perf record -e probe_libc:malloc -aR sleep 1 [root@xxxx ~]# ./bin/perf record -e probe_libc:malloc -aR sleep 20 [ perf record: Woken up 22 times to write data ] [ perf record: Captured and wrote 5.843 MB perf.data (~255302 samples) ] [root@xxxx ~]# ./bin/perf report --stdio ... 69.05% tar libc-2.12.so [.] malloc 28.57% rm libc-2.12.so [.] malloc 1.32% avahi-daemon libc-2.12.so [.] malloc 0.58% bash libc-2.12.so [.] malloc 0.28% sshd libc-2.12.so [.] malloc 0.08% irqbalance libc-2.12.so [.] malloc 0.05% bzip2 libc-2.12.so [.] malloc 0.04% sleep libc-2.12.so [.] malloc 0.03% multipathd libc-2.12.so [.] malloc 0.01% sendmail libc-2.12.so [.] malloc 0.01% automount libc-2.12.so [.] malloc The trap_nr addition patch is a prereq. Signed-off-by: Ananth N Mavinakayanahalli Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/Kconfig | 3 + arch/powerpc/include/asm/thread_info.h | 4 +- arch/powerpc/include/asm/uprobes.h | 54 ++++++++++ arch/powerpc/kernel/Makefile | 1 + arch/powerpc/kernel/signal.c | 6 ++ arch/powerpc/kernel/uprobes.c | 184 +++++++++++++++++++++++++++++++++ 6 files changed, 251 insertions(+), 1 deletion(-) create mode 100644 arch/powerpc/include/asm/uprobes.h create mode 100644 arch/powerpc/kernel/uprobes.c (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 352f416269ce..98e513b62709 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -239,6 +239,9 @@ config PPC_OF_PLATFORM_PCI config ARCH_SUPPORTS_DEBUG_PAGEALLOC def_bool y +config ARCH_SUPPORTS_UPROBES + def_bool y + config PPC_ADV_DEBUG_REGS bool depends on 40x || BOOKE diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index faf93529cbf0..e942203cd4a8 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -102,6 +102,7 @@ static inline struct thread_info *current_thread_info(void) #define TIF_RESTOREALL 11 /* Restore all regs (implies NOERROR) */ #define TIF_NOERROR 12 /* Force successful syscall return */ #define TIF_NOTIFY_RESUME 13 /* callback before returning to user */ +#define TIF_UPROBE 14 /* breakpointed or single-stepping */ #define TIF_SYSCALL_TRACEPOINT 15 /* syscall tracepoint instrumentation */ /* as above, but as bit values */ @@ -118,12 +119,13 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_RESTOREALL (1< + */ + +#include +#include + +typedef opcode_t uprobe_opcode_t; + +#define MAX_UINSN_BYTES 4 +#define UPROBE_XOL_SLOT_BYTES (MAX_UINSN_BYTES) + +/* The following alias is needed for reference from arch-agnostic code */ +#define UPROBE_SWBP_INSN BREAKPOINT_INSTRUCTION +#define UPROBE_SWBP_INSN_SIZE 4 /* swbp insn size in bytes */ + +struct arch_uprobe { + union { + u8 insn[MAX_UINSN_BYTES]; + u32 ainsn; + }; +}; + +struct arch_uprobe_task { + unsigned long saved_trap_nr; +}; + +extern int arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long addr); +extern int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs); +extern int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs); +extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk); +extern int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data); +extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs); +#endif /* _ASM_UPROBES_H */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index bb282dd81612..cde12f8a4ebc 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -96,6 +96,7 @@ obj-$(CONFIG_MODULES) += ppc_ksyms.o obj-$(CONFIG_BOOTX_TEXT) += btext.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_KPROBES) += kprobes.o +obj-$(CONFIG_UPROBES) += uprobes.o obj-$(CONFIG_PPC_UDBG_16550) += legacy_serial.o udbg_16550.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_SWIOTLB) += dma-swiotlb.o diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 5c023c9cf16e..29be2712e560 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -11,6 +11,7 @@ #include #include +#include #include #include #include @@ -157,6 +158,11 @@ static int do_signal(struct pt_regs *regs) void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) { + if (thread_info_flags & _TIF_UPROBE) { + clear_thread_flag(TIF_UPROBE); + uprobe_notify_resume(regs); + } + if (thread_info_flags & _TIF_SIGPENDING) do_signal(regs); diff --git a/arch/powerpc/kernel/uprobes.c b/arch/powerpc/kernel/uprobes.c new file mode 100644 index 000000000000..d2d46d1014f8 --- /dev/null +++ b/arch/powerpc/kernel/uprobes.c @@ -0,0 +1,184 @@ +/* + * User-space Probes (UProbes) for powerpc + * + * 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 IBM Corporation, 2007-2012 + * + * Adapted from the x86 port by Ananth N Mavinakayanahalli + */ +#include +#include +#include +#include +#include +#include + +#include + +#define UPROBE_TRAP_NR UINT_MAX + +/** + * arch_uprobe_analyze_insn + * @mm: the probed address space. + * @arch_uprobe: the probepoint information. + * @addr: vaddr to probe. + * Return 0 on success or a -ve number on error. + */ +int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, + struct mm_struct *mm, unsigned long addr) +{ + if (addr & 0x03) + return -EINVAL; + + /* + * We currently don't support a uprobe on an already + * existing breakpoint instruction underneath + */ + if (is_trap(auprobe->ainsn)) + return -ENOTSUPP; + return 0; +} + +/* + * arch_uprobe_pre_xol - prepare to execute out of line. + * @auprobe: the probepoint information. + * @regs: reflects the saved user state of current task. + */ +int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + struct arch_uprobe_task *autask = ¤t->utask->autask; + + autask->saved_trap_nr = current->thread.trap_nr; + current->thread.trap_nr = UPROBE_TRAP_NR; + regs->nip = current->utask->xol_vaddr; + return 0; +} + +/** + * uprobe_get_swbp_addr - compute address of swbp given post-swbp regs + * @regs: Reflects the saved state of the task after it has hit a breakpoint + * instruction. + * Return the address of the breakpoint instruction. + */ +unsigned long uprobe_get_swbp_addr(struct pt_regs *regs) +{ + return instruction_pointer(regs); +} + +/* + * If xol insn itself traps and generates a signal (SIGILL/SIGSEGV/etc), + * then detect the case where a singlestepped instruction jumps back to its + * own address. It is assumed that anything like do_page_fault/do_trap/etc + * sets thread.trap_nr != UINT_MAX. + * + * arch_uprobe_pre_xol/arch_uprobe_post_xol save/restore thread.trap_nr, + * arch_uprobe_xol_was_trapped() simply checks that ->trap_nr is not equal to + * UPROBE_TRAP_NR == UINT_MAX set by arch_uprobe_pre_xol(). + */ +bool arch_uprobe_xol_was_trapped(struct task_struct *t) +{ + if (t->thread.trap_nr != UPROBE_TRAP_NR) + return true; + + return false; +} + +/* + * Called after single-stepping. To avoid the SMP problems that can + * occur when we temporarily put back the original opcode to + * single-step, we single-stepped a copy of the instruction. + * + * This function prepares to resume execution after the single-step. + */ +int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + struct uprobe_task *utask = current->utask; + + WARN_ON_ONCE(current->thread.trap_nr != UPROBE_TRAP_NR); + + current->thread.trap_nr = utask->autask.saved_trap_nr; + + /* + * On powerpc, except for loads and stores, most instructions + * including ones that alter code flow (branches, calls, returns) + * are emulated in the kernel. We get here only if the emulation + * support doesn't exist and have to fix-up the next instruction + * to be executed. + */ + regs->nip = utask->vaddr + MAX_UINSN_BYTES; + return 0; +} + +/* callback routine for handling exceptions. */ +int arch_uprobe_exception_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + struct die_args *args = data; + struct pt_regs *regs = args->regs; + + /* regs == NULL is a kernel bug */ + if (WARN_ON(!regs)) + return NOTIFY_DONE; + + /* We are only interested in userspace traps */ + if (!user_mode(regs)) + return NOTIFY_DONE; + + switch (val) { + case DIE_BPT: + if (uprobe_pre_sstep_notifier(regs)) + return NOTIFY_STOP; + break; + case DIE_SSTEP: + if (uprobe_post_sstep_notifier(regs)) + return NOTIFY_STOP; + default: + break; + } + return NOTIFY_DONE; +} + +/* + * This function gets called when XOL instruction either gets trapped or + * the thread has a fatal signal, so reset the instruction pointer to its + * probed address. + */ +void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + struct uprobe_task *utask = current->utask; + + current->thread.trap_nr = utask->autask.saved_trap_nr; + instruction_pointer_set(regs, utask->vaddr); +} + +/* + * See if the instruction can be emulated. + * Returns true if instruction was emulated, false otherwise. + */ +bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + int ret; + + /* + * emulate_step() returns 1 if the insn was successfully emulated. + * For all other cases, we need to single-step in hardware. + */ + ret = emulate_step(regs, auprobe->ainsn); + if (ret > 0) + return true; + + return false; +} -- cgit v1.3-14-g43fede From a1310757218e0757ee77d2ce05c43028430ed9dd Mon Sep 17 00:00:00 2001 From: Mihai Caraman Date: Mon, 6 Aug 2012 03:27:03 +0000 Subject: powerpc/booke64: Fix machine check handler to use the right prolog Machine check exception handler was using a wrong prolog. Hypervisors like KVM which are called early from the exception handler rely on the interrupt source. Signed-off-by: Mihai Caraman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/exceptions-64e.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 98be7f0cd227..0243b1b29031 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -297,7 +297,7 @@ interrupt_end_book3e: /* Machine Check Interrupt */ START_EXCEPTION(machine_check); - CRIT_EXCEPTION_PROLOG(0x200, PROLOG_ADDITION_NONE) + MC_EXCEPTION_PROLOG(0x200, PROLOG_ADDITION_NONE) // EXCEPTION_COMMON(0x200, PACA_EXMC, INTS_DISABLE) // bl special_reg_save_mc // addi r3,r1,STACK_FRAME_OVERHEAD -- cgit v1.3-14-g43fede From 5473eb1c07009956be5f4df65d51f8e24d8eb1de Mon Sep 17 00:00:00 2001 From: Mihai Caraman Date: Mon, 6 Aug 2012 03:27:04 +0000 Subject: powerpc/booke64: Use GSRR registers in Guest Doorbell interrupts Guest Doorbell interrupts use guest save and restore registers. Add a new Guest Doorbell exception type to accommodate GSRR0/1 SPRs usage in exception prolog and fix the exception handler. Signed-off-by: Mihai Caraman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/exception-64e.h | 1 + arch/powerpc/include/asm/reg.h | 1 + arch/powerpc/kernel/exceptions-64e.S | 21 +++++++++++++++++++-- 3 files changed, 21 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/exception-64e.h b/arch/powerpc/include/asm/exception-64e.h index ac13addb8495..e73452f09019 100644 --- a/arch/powerpc/include/asm/exception-64e.h +++ b/arch/powerpc/include/asm/exception-64e.h @@ -37,6 +37,7 @@ * critical data */ +#define PACA_EXGDBELL PACA_EXGEN /* We are out of SPRGs so we save some things in the PACA. The normal * exception frame is smaller than the CRIT or MC one though diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 43bb15fc899b..c195bf0e6241 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -863,6 +863,7 @@ #define SPRN_SPRG_TLB_EXFRAME SPRN_SPRG2 #define SPRN_SPRG_TLB_SCRATCH SPRN_SPRG6 #define SPRN_SPRG_GEN_SCRATCH SPRN_SPRG0 +#define SPRN_SPRG_GDBELL_SCRATCH SPRN_SPRG_GEN_SCRATCH #define SET_PACA(rX) mtspr SPRN_SPRG_PACA,rX #define GET_PACA(rX) mfspr rX,SPRN_SPRG_PACA diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 0243b1b29031..0f58a95fd216 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -59,6 +59,10 @@ #define SPRN_GEN_SRR0 SPRN_SRR0 #define SPRN_GEN_SRR1 SPRN_SRR1 +#define GDBELL_SET_KSTACK GEN_SET_KSTACK +#define SPRN_GDBELL_SRR0 SPRN_GSRR0 +#define SPRN_GDBELL_SRR1 SPRN_GSRR1 + #define CRIT_SET_KSTACK \ ld r1,PACA_CRIT_STACK(r13); \ subi r1,r1,SPECIAL_EXC_FRAME_SIZE; @@ -89,10 +93,13 @@ #define MC_EXCEPTION_PROLOG(n, addition) \ EXCEPTION_PROLOG(n, MC, addition##_MC(n)) +#define GDBELL_EXCEPTION_PROLOG(n, addition) \ + EXCEPTION_PROLOG(n, GDBELL, addition##_GDBELL(n)) /* Variants of the "addition" argument for the prolog */ #define PROLOG_ADDITION_NONE_GEN(n) +#define PROLOG_ADDITION_NONE_GDBELL(n) #define PROLOG_ADDITION_NONE_CRIT(n) #define PROLOG_ADDITION_NONE_DBG(n) #define PROLOG_ADDITION_NONE_MC(n) @@ -543,8 +550,18 @@ kernel_dbg_exc: // b ret_from_crit_except b . -/* Guest Doorbell */ - MASKABLE_EXCEPTION(0x2c0, guest_doorbell, .unknown_exception, ACK_NONE) +/* + * Guest doorbell interrupt + * This general exception use GSRRx save/restore registers + */ + START_EXCEPTION(guest_doorbell); + GDBELL_EXCEPTION_PROLOG(0x2c0, PROLOG_ADDITION_NONE) + EXCEPTION_COMMON(0x2c0, PACA_EXGEN, INTS_KEEP) + addi r3,r1,STACK_FRAME_OVERHEAD + bl .save_nvgprs + INTS_RESTORE_HARD + bl .unknown_exception + b .ret_from_except /* Guest Doorbell critical Interrupt */ START_EXCEPTION(guest_doorbell_crit); -- cgit v1.3-14-g43fede From fecff0f7243edaea33071865ee5e35839be44f10 Mon Sep 17 00:00:00 2001 From: Mihai Caraman Date: Mon, 6 Aug 2012 03:27:05 +0000 Subject: powerpc/booke64: Add DO_KVM kernel hooks Hook DO_KVM macro into 64-bit booke for KVM integration. Extend interrupt handlers' parameter list with interrupt vector numbers to accomodate the macro. Only the bolted version of tlb miss handers is addressed now. Signed-off-by: Mihai Caraman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/exceptions-64e.S | 93 +++++++++++++++++++++++------------- arch/powerpc/mm/tlb_low_64e.S | 14 ++++-- 2 files changed, 70 insertions(+), 37 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 0f58a95fd216..3b1ad1ba8c48 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -25,6 +25,8 @@ #include #include #include +#include +#include /* XXX This will ultimately add space for a special exception save * structure used to save things like SRR0/SRR1, SPRGs, MAS, etc... @@ -35,12 +37,14 @@ #define SPECIAL_EXC_FRAME_SIZE INT_FRAME_SIZE /* Exception prolog code for all exceptions */ -#define EXCEPTION_PROLOG(n, type, addition) \ +#define EXCEPTION_PROLOG(n, intnum, type, addition) \ mtspr SPRN_SPRG_##type##_SCRATCH,r13; /* get spare registers */ \ mfspr r13,SPRN_SPRG_PACA; /* get PACA */ \ std r10,PACA_EX##type+EX_R10(r13); \ std r11,PACA_EX##type+EX_R11(r13); \ mfcr r10; /* save CR */ \ + mfspr r11,SPRN_##type##_SRR1;/* what are we coming from */ \ + DO_KVM intnum,SPRN_##type##_SRR1; /* KVM hook */ \ addition; /* additional code for that exc. */ \ std r1,PACA_EX##type+EX_R1(r13); /* save old r1 in the PACA */ \ stw r10,PACA_EX##type+EX_CR(r13); /* save old CR in the PACA */ \ @@ -81,20 +85,20 @@ #define SPRN_MC_SRR0 SPRN_MCSRR0 #define SPRN_MC_SRR1 SPRN_MCSRR1 -#define NORMAL_EXCEPTION_PROLOG(n, addition) \ - EXCEPTION_PROLOG(n, GEN, addition##_GEN(n)) +#define NORMAL_EXCEPTION_PROLOG(n, intnum, addition) \ + EXCEPTION_PROLOG(n, intnum, GEN, addition##_GEN(n)) -#define CRIT_EXCEPTION_PROLOG(n, addition) \ - EXCEPTION_PROLOG(n, CRIT, addition##_CRIT(n)) +#define CRIT_EXCEPTION_PROLOG(n, intnum, addition) \ + EXCEPTION_PROLOG(n, intnum, CRIT, addition##_CRIT(n)) -#define DBG_EXCEPTION_PROLOG(n, addition) \ - EXCEPTION_PROLOG(n, DBG, addition##_DBG(n)) +#define DBG_EXCEPTION_PROLOG(n, intnum, addition) \ + EXCEPTION_PROLOG(n, intnum, DBG, addition##_DBG(n)) -#define MC_EXCEPTION_PROLOG(n, addition) \ - EXCEPTION_PROLOG(n, MC, addition##_MC(n)) +#define MC_EXCEPTION_PROLOG(n, intnum, addition) \ + EXCEPTION_PROLOG(n, intnum, MC, addition##_MC(n)) -#define GDBELL_EXCEPTION_PROLOG(n, addition) \ - EXCEPTION_PROLOG(n, GDBELL, addition##_GDBELL(n)) +#define GDBELL_EXCEPTION_PROLOG(n, intnum, addition) \ + EXCEPTION_PROLOG(n, intnum, GDBELL, addition##_GDBELL(n)) /* Variants of the "addition" argument for the prolog */ @@ -240,9 +244,9 @@ exc_##n##_bad_stack: \ 1: -#define MASKABLE_EXCEPTION(trapnum, label, hdlr, ack) \ +#define MASKABLE_EXCEPTION(trapnum, intnum, label, hdlr, ack) \ START_EXCEPTION(label); \ - NORMAL_EXCEPTION_PROLOG(trapnum, PROLOG_ADDITION_MASKABLE) \ + NORMAL_EXCEPTION_PROLOG(trapnum, intnum, PROLOG_ADDITION_MASKABLE)\ EXCEPTION_COMMON(trapnum, PACA_EXGEN, INTS_DISABLE) \ ack(r8); \ CHECK_NAPPING(); \ @@ -293,7 +297,8 @@ interrupt_end_book3e: /* Critical Input Interrupt */ START_EXCEPTION(critical_input); - CRIT_EXCEPTION_PROLOG(0x100, PROLOG_ADDITION_NONE) + CRIT_EXCEPTION_PROLOG(0x100, BOOKE_INTERRUPT_CRITICAL, + PROLOG_ADDITION_NONE) // EXCEPTION_COMMON(0x100, PACA_EXCRIT, INTS_DISABLE) // bl special_reg_save_crit // CHECK_NAPPING(); @@ -304,7 +309,8 @@ interrupt_end_book3e: /* Machine Check Interrupt */ START_EXCEPTION(machine_check); - MC_EXCEPTION_PROLOG(0x200, PROLOG_ADDITION_NONE) + MC_EXCEPTION_PROLOG(0x200, BOOKE_INTERRUPT_MACHINE_CHECK, + PROLOG_ADDITION_NONE) // EXCEPTION_COMMON(0x200, PACA_EXMC, INTS_DISABLE) // bl special_reg_save_mc // addi r3,r1,STACK_FRAME_OVERHEAD @@ -315,7 +321,8 @@ interrupt_end_book3e: /* Data Storage Interrupt */ START_EXCEPTION(data_storage) - NORMAL_EXCEPTION_PROLOG(0x300, PROLOG_ADDITION_2REGS) + NORMAL_EXCEPTION_PROLOG(0x300, BOOKE_INTERRUPT_DATA_STORAGE, + PROLOG_ADDITION_2REGS) mfspr r14,SPRN_DEAR mfspr r15,SPRN_ESR EXCEPTION_COMMON(0x300, PACA_EXGEN, INTS_DISABLE) @@ -323,18 +330,21 @@ interrupt_end_book3e: /* Instruction Storage Interrupt */ START_EXCEPTION(instruction_storage); - NORMAL_EXCEPTION_PROLOG(0x400, PROLOG_ADDITION_2REGS) + NORMAL_EXCEPTION_PROLOG(0x400, BOOKE_INTERRUPT_INST_STORAGE, + PROLOG_ADDITION_2REGS) li r15,0 mr r14,r10 EXCEPTION_COMMON(0x400, PACA_EXGEN, INTS_DISABLE) b storage_fault_common /* External Input Interrupt */ - MASKABLE_EXCEPTION(0x500, external_input, .do_IRQ, ACK_NONE) + MASKABLE_EXCEPTION(0x500, BOOKE_INTERRUPT_EXTERNAL, + external_input, .do_IRQ, ACK_NONE) /* Alignment */ START_EXCEPTION(alignment); - NORMAL_EXCEPTION_PROLOG(0x600, PROLOG_ADDITION_2REGS) + NORMAL_EXCEPTION_PROLOG(0x600, BOOKE_INTERRUPT_ALIGNMENT, + PROLOG_ADDITION_2REGS) mfspr r14,SPRN_DEAR mfspr r15,SPRN_ESR EXCEPTION_COMMON(0x600, PACA_EXGEN, INTS_KEEP) @@ -342,7 +352,8 @@ interrupt_end_book3e: /* Program Interrupt */ START_EXCEPTION(program); - NORMAL_EXCEPTION_PROLOG(0x700, PROLOG_ADDITION_1REG) + NORMAL_EXCEPTION_PROLOG(0x700, BOOKE_INTERRUPT_PROGRAM, + PROLOG_ADDITION_1REG) mfspr r14,SPRN_ESR EXCEPTION_COMMON(0x700, PACA_EXGEN, INTS_DISABLE) std r14,_DSISR(r1) @@ -354,7 +365,8 @@ interrupt_end_book3e: /* Floating Point Unavailable Interrupt */ START_EXCEPTION(fp_unavailable); - NORMAL_EXCEPTION_PROLOG(0x800, PROLOG_ADDITION_NONE) + NORMAL_EXCEPTION_PROLOG(0x800, BOOKE_INTERRUPT_FP_UNAVAIL, + PROLOG_ADDITION_NONE) /* we can probably do a shorter exception entry for that one... */ EXCEPTION_COMMON(0x800, PACA_EXGEN, INTS_KEEP) ld r12,_MSR(r1) @@ -369,14 +381,17 @@ interrupt_end_book3e: b .ret_from_except /* Decrementer Interrupt */ - MASKABLE_EXCEPTION(0x900, decrementer, .timer_interrupt, ACK_DEC) + MASKABLE_EXCEPTION(0x900, BOOKE_INTERRUPT_DECREMENTER, + decrementer, .timer_interrupt, ACK_DEC) /* Fixed Interval Timer Interrupt */ - MASKABLE_EXCEPTION(0x980, fixed_interval, .unknown_exception, ACK_FIT) + MASKABLE_EXCEPTION(0x980, BOOKE_INTERRUPT_FIT, + fixed_interval, .unknown_exception, ACK_FIT) /* Watchdog Timer Interrupt */ START_EXCEPTION(watchdog); - CRIT_EXCEPTION_PROLOG(0x9f0, PROLOG_ADDITION_NONE) + CRIT_EXCEPTION_PROLOG(0x9f0, BOOKE_INTERRUPT_WATCHDOG, + PROLOG_ADDITION_NONE) // EXCEPTION_COMMON(0x9f0, PACA_EXCRIT, INTS_DISABLE) // bl special_reg_save_crit // CHECK_NAPPING(); @@ -395,7 +410,8 @@ interrupt_end_book3e: /* Auxiliary Processor Unavailable Interrupt */ START_EXCEPTION(ap_unavailable); - NORMAL_EXCEPTION_PROLOG(0xf20, PROLOG_ADDITION_NONE) + NORMAL_EXCEPTION_PROLOG(0xf20, BOOKE_INTERRUPT_AP_UNAVAIL, + PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0xf20, PACA_EXGEN, INTS_DISABLE) bl .save_nvgprs addi r3,r1,STACK_FRAME_OVERHEAD @@ -404,7 +420,8 @@ interrupt_end_book3e: /* Debug exception as a critical interrupt*/ START_EXCEPTION(debug_crit); - CRIT_EXCEPTION_PROLOG(0xd00, PROLOG_ADDITION_2REGS) + CRIT_EXCEPTION_PROLOG(0xd00, BOOKE_INTERRUPT_DEBUG, + PROLOG_ADDITION_2REGS) /* * If there is a single step or branch-taken exception in an @@ -469,7 +486,8 @@ kernel_dbg_exc: /* Debug exception as a debug interrupt*/ START_EXCEPTION(debug_debug); - DBG_EXCEPTION_PROLOG(0xd08, PROLOG_ADDITION_2REGS) + DBG_EXCEPTION_PROLOG(0xd00, BOOKE_INTERRUPT_DEBUG, + PROLOG_ADDITION_2REGS) /* * If there is a single step or branch-taken exception in an @@ -530,18 +548,21 @@ kernel_dbg_exc: b .ret_from_except START_EXCEPTION(perfmon); - NORMAL_EXCEPTION_PROLOG(0x260, PROLOG_ADDITION_NONE) + NORMAL_EXCEPTION_PROLOG(0x260, BOOKE_INTERRUPT_PERFORMANCE_MONITOR, + PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0x260, PACA_EXGEN, INTS_DISABLE) addi r3,r1,STACK_FRAME_OVERHEAD bl .performance_monitor_exception b .ret_from_except_lite /* Doorbell interrupt */ - MASKABLE_EXCEPTION(0x280, doorbell, .doorbell_exception, ACK_NONE) + MASKABLE_EXCEPTION(0x280, BOOKE_INTERRUPT_DOORBELL, + doorbell, .doorbell_exception, ACK_NONE) /* Doorbell critical Interrupt */ START_EXCEPTION(doorbell_crit); - CRIT_EXCEPTION_PROLOG(0x2a0, PROLOG_ADDITION_NONE) + CRIT_EXCEPTION_PROLOG(0x2a0, BOOKE_INTERRUPT_DOORBELL_CRITICAL, + PROLOG_ADDITION_NONE) // EXCEPTION_COMMON(0x2a0, PACA_EXCRIT, INTS_DISABLE) // bl special_reg_save_crit // CHECK_NAPPING(); @@ -555,7 +576,8 @@ kernel_dbg_exc: * This general exception use GSRRx save/restore registers */ START_EXCEPTION(guest_doorbell); - GDBELL_EXCEPTION_PROLOG(0x2c0, PROLOG_ADDITION_NONE) + GDBELL_EXCEPTION_PROLOG(0x2c0, BOOKE_INTERRUPT_GUEST_DBELL, + PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0x2c0, PACA_EXGEN, INTS_KEEP) addi r3,r1,STACK_FRAME_OVERHEAD bl .save_nvgprs @@ -565,7 +587,8 @@ kernel_dbg_exc: /* Guest Doorbell critical Interrupt */ START_EXCEPTION(guest_doorbell_crit); - CRIT_EXCEPTION_PROLOG(0x2e0, PROLOG_ADDITION_NONE) + CRIT_EXCEPTION_PROLOG(0x2e0, BOOKE_INTERRUPT_GUEST_DBELL_CRIT, + PROLOG_ADDITION_NONE) // EXCEPTION_COMMON(0x2e0, PACA_EXCRIT, INTS_DISABLE) // bl special_reg_save_crit // CHECK_NAPPING(); @@ -576,7 +599,8 @@ kernel_dbg_exc: /* Hypervisor call */ START_EXCEPTION(hypercall); - NORMAL_EXCEPTION_PROLOG(0x310, PROLOG_ADDITION_NONE) + NORMAL_EXCEPTION_PROLOG(0x310, BOOKE_INTERRUPT_HV_SYSCALL, + PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0x310, PACA_EXGEN, INTS_KEEP) addi r3,r1,STACK_FRAME_OVERHEAD bl .save_nvgprs @@ -586,7 +610,8 @@ kernel_dbg_exc: /* Embedded Hypervisor priviledged */ START_EXCEPTION(ehpriv); - NORMAL_EXCEPTION_PROLOG(0x320, PROLOG_ADDITION_NONE) + NORMAL_EXCEPTION_PROLOG(0x320, BOOKE_INTERRUPT_HV_PRIV, + PROLOG_ADDITION_NONE) EXCEPTION_COMMON(0x320, PACA_EXGEN, INTS_KEEP) addi r3,r1,STACK_FRAME_OVERHEAD bl .save_nvgprs diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S index f09d48e3268d..d884fa44d34f 100644 --- a/arch/powerpc/mm/tlb_low_64e.S +++ b/arch/powerpc/mm/tlb_low_64e.S @@ -20,6 +20,8 @@ #include #include #include +#include +#include #ifdef CONFIG_PPC_64K_PAGES #define VPTE_PMD_SHIFT (PTE_INDEX_SIZE+1) @@ -37,12 +39,18 @@ * * **********************************************************************/ -.macro tlb_prolog_bolted addr +.macro tlb_prolog_bolted intnum addr mtspr SPRN_SPRG_TLB_SCRATCH,r13 mfspr r13,SPRN_SPRG_PACA std r10,PACA_EXTLB+EX_TLB_R10(r13) mfcr r10 std r11,PACA_EXTLB+EX_TLB_R11(r13) +#ifdef CONFIG_KVM_BOOKE_HV +BEGIN_FTR_SECTION + mfspr r11, SPRN_SRR1 +END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) +#endif + DO_KVM \intnum, SPRN_SRR1 std r16,PACA_EXTLB+EX_TLB_R16(r13) mfspr r16,\addr /* get faulting address */ std r14,PACA_EXTLB+EX_TLB_R14(r13) @@ -66,7 +74,7 @@ /* Data TLB miss */ START_EXCEPTION(data_tlb_miss_bolted) - tlb_prolog_bolted SPRN_DEAR + tlb_prolog_bolted BOOKE_INTERRUPT_DTLB_MISS SPRN_DEAR /* We need _PAGE_PRESENT and _PAGE_ACCESSED set */ @@ -214,7 +222,7 @@ itlb_miss_fault_bolted: /* Instruction TLB miss */ START_EXCEPTION(instruction_tlb_miss_bolted) - tlb_prolog_bolted SPRN_SRR0 + tlb_prolog_bolted BOOKE_INTERRUPT_ITLB_MISS SPRN_SRR0 rldicl. r10,r16,64-PGTABLE_EADDR_SIZE,PGTABLE_EADDR_SIZE+4 srdi r15,r16,60 /* get region */ -- cgit v1.3-14-g43fede From 79b5c8dbaa4528a6fd03a4d9d8a6d56a46293a3a Mon Sep 17 00:00:00 2001 From: Mihai Caraman Date: Mon, 6 Aug 2012 03:27:06 +0000 Subject: powerpc/booke64: Eemove mfspr srr1 duplicate in exception prolog Refactor exception prolog to get rid of mfspr srr1 duplicate. This was introduced by KVM integration, with DO_KVM macro logic expecting srr1 value earlier in r11. Reserve r11 to hold srr1's value also required at the end of the prolog and free up r10 to serve as spare in addition macros. For syscalls case this change does not add any performance penalty. For irq soft-disabled case the change adds a store/load of conditional register value to/from a paca slot. Paca slots fit in one 64-byte cache line so these additional operations have little impact on performance. Signed-off-by: Mihai Caraman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/exceptions-64e.S | 67 +++++++++++++++++------------------- 1 file changed, 32 insertions(+), 35 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 3b1ad1ba8c48..83c20e84a4fb 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -45,10 +45,9 @@ mfcr r10; /* save CR */ \ mfspr r11,SPRN_##type##_SRR1;/* what are we coming from */ \ DO_KVM intnum,SPRN_##type##_SRR1; /* KVM hook */ \ + stw r10,PACA_EX##type+EX_CR(r13); /* save old CR in the PACA */ \ addition; /* additional code for that exc. */ \ std r1,PACA_EX##type+EX_R1(r13); /* save old r1 in the PACA */ \ - stw r10,PACA_EX##type+EX_CR(r13); /* save old CR in the PACA */ \ - mfspr r11,SPRN_##type##_SRR1;/* what are we coming from */ \ type##_SET_KSTACK; /* get special stack if necessary */\ andi. r10,r11,MSR_PR; /* save stack pointer */ \ beq 1f; /* branch around if supervisor */ \ @@ -109,8 +108,8 @@ #define PROLOG_ADDITION_NONE_MC(n) #define PROLOG_ADDITION_MASKABLE_GEN(n) \ - lbz r11,PACASOFTIRQEN(r13); /* are irqs soft-disabled ? */ \ - cmpwi cr0,r11,0; /* yes -> go out of line */ \ + lbz r10,PACASOFTIRQEN(r13); /* are irqs soft-disabled ? */ \ + cmpwi cr0,r10,0; /* yes -> go out of line */ \ beq masked_interrupt_book3e_##n #define PROLOG_ADDITION_2REGS_GEN(n) \ @@ -624,44 +623,42 @@ kernel_dbg_exc: * accordingly and if the interrupt is level sensitive, we hard disable */ +.macro masked_interrupt_book3e paca_irq full_mask + lbz r10,PACAIRQHAPPENED(r13) + ori r10,r10,\paca_irq + stb r10,PACAIRQHAPPENED(r13) + + .if \full_mask == 1 + rldicl r10,r11,48,1 /* clear MSR_EE */ + rotldi r11,r10,16 + mtspr SPRN_SRR1,r11 + .endif + + lwz r11,PACA_EXGEN+EX_CR(r13) + mtcr r11 + ld r10,PACA_EXGEN+EX_R10(r13) + ld r11,PACA_EXGEN+EX_R11(r13) + mfspr r13,SPRN_SPRG_GEN_SCRATCH + rfi + b . +.endm + masked_interrupt_book3e_0x500: - /* XXX When adding support for EPR, use PACA_IRQ_EE_EDGE */ - li r11,PACA_IRQ_EE - b masked_interrupt_book3e_full_mask + // XXX When adding support for EPR, use PACA_IRQ_EE_EDGE + masked_interrupt_book3e PACA_IRQ_EE 1 masked_interrupt_book3e_0x900: - ACK_DEC(r11); - li r11,PACA_IRQ_DEC - b masked_interrupt_book3e_no_mask + ACK_DEC(r10); + masked_interrupt_book3e PACA_IRQ_DEC 0 + masked_interrupt_book3e_0x980: - ACK_FIT(r11); - li r11,PACA_IRQ_DEC - b masked_interrupt_book3e_no_mask + ACK_FIT(r10); + masked_interrupt_book3e PACA_IRQ_DEC 0 + masked_interrupt_book3e_0x280: masked_interrupt_book3e_0x2c0: - li r11,PACA_IRQ_DBELL - b masked_interrupt_book3e_no_mask + masked_interrupt_book3e PACA_IRQ_DBELL 0 -masked_interrupt_book3e_no_mask: - mtcr r10 - lbz r10,PACAIRQHAPPENED(r13) - or r10,r10,r11 - stb r10,PACAIRQHAPPENED(r13) - b 1f -masked_interrupt_book3e_full_mask: - mtcr r10 - lbz r10,PACAIRQHAPPENED(r13) - or r10,r10,r11 - stb r10,PACAIRQHAPPENED(r13) - mfspr r10,SPRN_SRR1 - rldicl r11,r10,48,1 /* clear MSR_EE */ - rotldi r10,r11,16 - mtspr SPRN_SRR1,r10 -1: ld r10,PACA_EXGEN+EX_R10(r13); - ld r11,PACA_EXGEN+EX_R11(r13); - mfspr r13,SPRN_SPRG_GEN_SCRATCH; - rfi - b . /* * Called from arch_local_irq_enable when an interrupt needs * to be resent. r3 contains either 0x500,0x900,0x260 or 0x280 -- cgit v1.3-14-g43fede From 8b64a9dfb091f1eca8b7e58da82f1e7d1d5fe0ad Mon Sep 17 00:00:00 2001 From: Mihai Caraman Date: Mon, 6 Aug 2012 03:27:07 +0000 Subject: powerpc/booke64: Use SPRG0/3 scratch for bolted TLB miss & crit int Embedded.Hypervisor category defines GSPRG0..3 physical registers for guests. Avoid SPRG4-7 usage as scratch in host exception handlers, otherwise guest SPRG4-7 registers will be clobbered. For bolted TLB miss exception handlers, which is the version currently supported by KVM, use SPRN_SPRG_GEN_SCRATCH aka SPRG0 instead of SPRN_SPRG_TLB_SCRATCH aka SPRG6. Keep using TLB PACA slots to fit in one 64-byte cache line. For critical exception handlers use SPRG3 instead of SPRG7. Provide a routine to store and restore user-visible SPRGs. This will be subsequently used to restore VDSO information in SPRG3. Add EX_R13 to paca slots to free up SPRG3 and change the critical exception epilog to use it. Signed-off-by: Mihai Caraman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/exception-64e.h | 5 +++-- arch/powerpc/include/asm/reg.h | 5 +++-- arch/powerpc/kernel/exceptions-64e.S | 17 +++++++++++++++-- arch/powerpc/mm/tlb_low_64e.S | 4 ++-- 4 files changed, 23 insertions(+), 8 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/exception-64e.h b/arch/powerpc/include/asm/exception-64e.h index e73452f09019..51fa43e536b9 100644 --- a/arch/powerpc/include/asm/exception-64e.h +++ b/arch/powerpc/include/asm/exception-64e.h @@ -46,8 +46,9 @@ #define EX_CR (1 * 8) #define EX_R10 (2 * 8) #define EX_R11 (3 * 8) -#define EX_R14 (4 * 8) -#define EX_R15 (5 * 8) +#define EX_R13 (4 * 8) +#define EX_R14 (5 * 8) +#define EX_R15 (6 * 8) /* * The TLB miss exception uses different slots. diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index c195bf0e6241..a391244c18e1 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -761,7 +761,8 @@ * 64-bit embedded * - SPRG0 generic exception scratch * - SPRG2 TLB exception stack - * - SPRG3 CPU and NUMA node for VDSO getcpu (user visible) + * - SPRG3 critical exception scratch and + * CPU and NUMA node for VDSO getcpu (user visible) * - SPRG4 unused (user visible) * - SPRG6 TLB miss scratch (user visible, sorry !) * - SPRG7 critical exception scratch @@ -858,7 +859,7 @@ #ifdef CONFIG_PPC_BOOK3E_64 #define SPRN_SPRG_MC_SCRATCH SPRN_SPRG8 -#define SPRN_SPRG_CRIT_SCRATCH SPRN_SPRG7 +#define SPRN_SPRG_CRIT_SCRATCH SPRN_SPRG3 #define SPRN_SPRG_DBG_SCRATCH SPRN_SPRG9 #define SPRN_SPRG_TLB_EXFRAME SPRN_SPRG2 #define SPRN_SPRG_TLB_SCRATCH SPRN_SPRG6 diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 83c20e84a4fb..7476b0ae09fb 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -42,6 +42,7 @@ mfspr r13,SPRN_SPRG_PACA; /* get PACA */ \ std r10,PACA_EX##type+EX_R10(r13); \ std r11,PACA_EX##type+EX_R11(r13); \ + PROLOG_STORE_RESTORE_SCRATCH_##type; \ mfcr r10; /* save CR */ \ mfspr r11,SPRN_##type##_SRR1;/* what are we coming from */ \ DO_KVM intnum,SPRN_##type##_SRR1; /* KVM hook */ \ @@ -99,6 +100,18 @@ #define GDBELL_EXCEPTION_PROLOG(n, intnum, addition) \ EXCEPTION_PROLOG(n, intnum, GDBELL, addition##_GDBELL(n)) +/* + * Store user-visible scratch in PACA exception slots and restore proper value + */ +#define PROLOG_STORE_RESTORE_SCRATCH_GEN +#define PROLOG_STORE_RESTORE_SCRATCH_GDBELL +#define PROLOG_STORE_RESTORE_SCRATCH_DBG +#define PROLOG_STORE_RESTORE_SCRATCH_MC + +#define PROLOG_STORE_RESTORE_SCRATCH_CRIT \ + mfspr r10,SPRN_SPRG_CRIT_SCRATCH; /* get r13 */ \ + std r10,PACA_EXCRIT+EX_R13(r13) + /* Variants of the "addition" argument for the prolog */ #define PROLOG_ADDITION_NONE_GEN(n) @@ -454,7 +467,7 @@ interrupt_end_book3e: mtcr r10 ld r10,PACA_EXCRIT+EX_R10(r13) /* restore registers */ ld r11,PACA_EXCRIT+EX_R11(r13) - mfspr r13,SPRN_SPRG_CRIT_SCRATCH + ld r13,PACA_EXCRIT+EX_R13(r13) rfci /* Normal debug exception */ @@ -467,7 +480,7 @@ interrupt_end_book3e: /* Now we mash up things to make it look like we are coming on a * normal exception */ - mfspr r15,SPRN_SPRG_CRIT_SCRATCH + ld r15,PACA_EXCRIT+EX_R13(r13) mtspr SPRN_SPRG_GEN_SCRATCH,r15 mfspr r14,SPRN_DBSR EXCEPTION_COMMON(0xd00, PACA_EXCRIT, INTS_DISABLE) diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S index d884fa44d34f..b4113bf86353 100644 --- a/arch/powerpc/mm/tlb_low_64e.S +++ b/arch/powerpc/mm/tlb_low_64e.S @@ -40,7 +40,7 @@ **********************************************************************/ .macro tlb_prolog_bolted intnum addr - mtspr SPRN_SPRG_TLB_SCRATCH,r13 + mtspr SPRN_SPRG_GEN_SCRATCH,r13 mfspr r13,SPRN_SPRG_PACA std r10,PACA_EXTLB+EX_TLB_R10(r13) mfcr r10 @@ -69,7 +69,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) ld r15,PACA_EXTLB+EX_TLB_R15(r13) TLB_MISS_RESTORE_STATS_BOLTED ld r16,PACA_EXTLB+EX_TLB_R16(r13) - mfspr r13,SPRN_SPRG_TLB_SCRATCH + mfspr r13,SPRN_SPRG_GEN_SCRATCH .endm /* Data TLB miss */ -- cgit v1.3-14-g43fede From 0127262c01f0beb485f917c720d1d95d165dfdbf Mon Sep 17 00:00:00 2001 From: Mihai Caraman Date: Thu, 6 Sep 2012 02:49:44 +0000 Subject: powerpc: Restore VDSO information on critical exception om BookE Critical exception on 64-bit booke uses user-visible SPRG3 as scratch. Restore VDSO information in SPRG3 on exception prolog. Use a common sprg3 field in PACA for all powerpc64 architectures. Signed-off-by: Mihai Caraman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/kvm_book3s_asm.h | 1 - arch/powerpc/include/asm/paca.h | 1 + arch/powerpc/kernel/asm-offsets.c | 2 +- arch/powerpc/kernel/exceptions-64e.S | 4 +++- arch/powerpc/kernel/vdso.c | 4 +--- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 2 +- 6 files changed, 7 insertions(+), 7 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h index bfcd00c1485d..88609b23b775 100644 --- a/arch/powerpc/include/asm/kvm_book3s_asm.h +++ b/arch/powerpc/include/asm/kvm_book3s_asm.h @@ -74,7 +74,6 @@ struct kvmppc_host_state { ulong vmhandler; ulong scratch0; ulong scratch1; - ulong sprg3; u8 in_guest; u8 restore_hid5; u8 napping; diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index daf813fea91f..7796519fd238 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -136,6 +136,7 @@ struct paca_struct { u8 io_sync; /* writel() needs spin_unlock sync */ u8 irq_work_pending; /* IRQ_WORK interrupt while soft-disable */ u8 nap_state_lost; /* NV GPR values lost in power7_idle */ + u64 sprg3; /* Saved user-visible sprg */ #ifdef CONFIG_PPC_POWERNV /* Pointer to OPAL machine check event structure set by the diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 85b05c463fae..72f26166007a 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -205,6 +205,7 @@ int main(void) DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time)); DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save)); DEFINE(PACA_NAPSTATELOST, offsetof(struct paca_struct, nap_state_lost)); + DEFINE(PACA_SPRG3, offsetof(struct paca_struct, sprg3)); #endif /* CONFIG_PPC64 */ /* RTAS */ @@ -533,7 +534,6 @@ int main(void) HSTATE_FIELD(HSTATE_VMHANDLER, vmhandler); HSTATE_FIELD(HSTATE_SCRATCH0, scratch0); HSTATE_FIELD(HSTATE_SCRATCH1, scratch1); - HSTATE_FIELD(HSTATE_SPRG3, sprg3); HSTATE_FIELD(HSTATE_IN_GUEST, in_guest); HSTATE_FIELD(HSTATE_RESTORE_HID5, restore_hid5); HSTATE_FIELD(HSTATE_NAPPING, napping); diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 7476b0ae09fb..87a82fbdf05a 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -110,7 +110,9 @@ #define PROLOG_STORE_RESTORE_SCRATCH_CRIT \ mfspr r10,SPRN_SPRG_CRIT_SCRATCH; /* get r13 */ \ - std r10,PACA_EXCRIT+EX_R13(r13) + std r10,PACA_EXCRIT+EX_R13(r13); \ + ld r11,PACA_SPRG3(r13); \ + mtspr SPRN_SPRG_CRIT_SCRATCH,r11; /* Variants of the "addition" argument for the prolog */ diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index b67db22e102d..1b2076f049ce 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -723,9 +723,7 @@ int __cpuinit vdso_getcpu_init(void) val = (cpu & 0xfff) | ((node & 0xffff) << 16); mtspr(SPRN_SPRG3, val); -#ifdef CONFIG_KVM_BOOK3S_HANDLER - get_paca()->kvm_hstate.sprg3 = val; -#endif + get_paca()->sprg3 = val; put_cpu(); diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 5a84c8d3d040..39a21bfb5d4b 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1065,7 +1065,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) mtspr SPRN_DABRX,r6 /* Restore SPRG3 */ - ld r3,HSTATE_SPRG3(r13) + ld r3,PACA_SPRG3(r13) mtspr SPRN_SPRG3,r3 /* -- cgit v1.3-14-g43fede From cf1a4cf8754afb248e498815c7957aeb4faca79f Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Sun, 3 Jun 2012 22:15:25 +0000 Subject: powerpc/pci: Save P2P bridge resource if possible When PCI probe flag PCI_REASSIGN_ALL_RSRC has been passed into PCI core, it's hoped that all resources to be reassigned by PCI core. As to particular P2P (PCI-to-PCI) bridge, the size of the corresponding BAR (I/O, MMIO, prefetchable MMIO) is calculated by the resources required by the PCI devices behind the P2P bridge. That means that the information like start/end address retrieved from the hardware registers of the P2P bridge is meainingless in the case. However, we still count that in and the BARs might have been configured by firmware with non-zero size. That leads to space waste. The patch explicitly sets the size of P2P bridge BARs to zero in case that resource reassignment is expected with PCI probe flag PCI_REASSIGN_ALL_RSRC. In the result, it will save overall resource required by the system without waste. Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/pci-common.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 2aa04f29e1de..4cb714792bea 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -960,13 +960,14 @@ static void __devinit pcibios_fixup_bridge(struct pci_bus *bus) if (i >= 3 && bus->self->transparent) continue; - /* If we are going to re-assign everything, mark the resource - * as unset and move it down to 0 + /* If we're going to reassign everything, we can + * shrink the P2P resource to have size as being + * of 0 in order to save space. */ if (pci_has_flag(PCI_REASSIGN_ALL_RSRC)) { res->flags |= IORESOURCE_UNSET; - res->end -= res->start; res->start = 0; + res->end = -1; continue; } @@ -1228,7 +1229,14 @@ void pcibios_allocate_bus_resources(struct pci_bus *bus) pr_warning("PCI: Cannot allocate resource region " "%d of PCI bridge %d, will remap\n", i, bus->number); clear_resource: - res->start = res->end = 0; + /* The resource might be figured out when doing + * reassignment based on the resources required + * by the downstream PCI devices. Here we set + * the size of the resource to be 0 in order to + * save more space. + */ + res->start = 0; + res->end = -1; res->flags = 0; } -- cgit v1.3-14-g43fede From a84fcd46870113e92523e1ebb9a0ec75f66e03a2 Mon Sep 17 00:00:00 2001 From: Suzuki Poulose Date: Tue, 21 Aug 2012 01:42:33 +0000 Subject: powerpc: Change memory_limit from phys_addr_t to unsigned long long There are some device-tree nodes, whose values are of type phys_addr_t. The phys_addr_t is variable sized based on the CONFIG_PHSY_T_64BIT. Change these to a fixed unsigned long long for consistency. This patch does the change only for memory_limit. The following is a list of such variables which need the change: 1) kernel_end, crashk_size - in arch/powerpc/kernel/machine_kexec.c 2) (struct resource *)crashk_res.start - We could export a local static variable from machine_kexec.c. Changing the above values might break the kexec-tools. So, I will fix kexec-tools first to handle the different sized values and then change the above. Suggested-by: Benjamin Herrenschmidt Signed-off-by: Suzuki K. Poulose Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/setup.h | 2 +- arch/powerpc/kernel/fadump.c | 3 +-- arch/powerpc/kernel/machine_kexec.c | 2 +- arch/powerpc/kernel/prom.c | 4 ++-- arch/powerpc/mm/mem.c | 2 +- 5 files changed, 6 insertions(+), 7 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index d084ce195fc3..8b9a306260b2 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -9,7 +9,7 @@ extern void ppc_printk_progress(char *s, unsigned short hex); extern unsigned int rtas_data; extern int mem_init_done; /* set on boot once kmalloc can be called */ extern int init_bootmem_done; /* set once bootmem is available */ -extern phys_addr_t memory_limit; +extern unsigned long long memory_limit; extern unsigned long klimit; extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask); diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 18bdf74fa164..06c8202a69cf 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -289,8 +289,7 @@ int __init fadump_reserve_mem(void) else memory_limit = memblock_end_of_DRAM(); printk(KERN_INFO "Adjusted memory_limit for firmware-assisted" - " dump, now %#016llx\n", - (unsigned long long)memory_limit); + " dump, now %#016llx\n", memory_limit); } if (memory_limit) memory_boundary = memory_limit; diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index 5df777794403..4074eff1e744 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -165,7 +165,7 @@ void __init reserve_crashkernel(void) if (memory_limit && memory_limit <= crashk_res.end) { memory_limit = crashk_res.end + 1; printk("Adjusted memory limit for crashkernel, now 0x%llx\n", - (unsigned long long)memory_limit); + memory_limit); } printk(KERN_INFO "Reserving %ldMB of memory at %ldMB " diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index f191bf02943a..37725e86651e 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -78,7 +78,7 @@ static int __init early_parse_mem(char *p) return 1; memory_limit = PAGE_ALIGN(memparse(p, &p)); - DBG("memory limit = 0x%llx\n", (unsigned long long)memory_limit); + DBG("memory limit = 0x%llx\n", memory_limit); return 0; } @@ -661,7 +661,7 @@ void __init early_init_devtree(void *params) /* make sure we've parsed cmdline for mem= before this */ if (memory_limit) - first_memblock_size = min(first_memblock_size, memory_limit); + first_memblock_size = min_t(u64, first_memblock_size, memory_limit); setup_initial_memory_limit(memstart_addr, first_memblock_size); /* Reserve MEMBLOCK regions used by kernel, initrd, dt, etc... */ memblock_reserve(PHYSICAL_START, __pa(klimit) - PHYSICAL_START); diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index fbdad0e3929a..44cf2b20503d 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -62,7 +62,7 @@ int init_bootmem_done; int mem_init_done; -phys_addr_t memory_limit; +unsigned long long memory_limit; #ifdef CONFIG_HIGHMEM pte_t *kmap_pte; -- cgit v1.3-14-g43fede From 4bc77a5ed215b4ec9cc39d5f55323b2e68000055 Mon Sep 17 00:00:00 2001 From: Suzuki Poulose Date: Tue, 21 Aug 2012 01:42:43 +0000 Subject: powerpc: Export memory limit via device tree The powerpc kernel doesn't export the memory limit enforced by 'mem=' kernel parameter. This is required for building the ELF header in kexec-tools to limit the vmcore to capture only the used memory. On powerpc the kexec-tools depends on the device-tree for memory related information, unlike /proc/iomem on the x86. Without this information, the kexec-tools assumes the entire System RAM and vmcore creates an unnecessarily larger dump. This patch exports the memory limit, if present, via chosen/linux,memory-limit property, so that the vmcore can be limited to the memory limit. The prom_init seems to export this value in the same node. But doesn't really appear there. Also the memory_limit gets adjusted with the processing of crashkernel= parameter. This patch makes sure we get the actual limit. The kexec-tools will use the value to limit the 'end' of the memory regions. Tested this patch on ppc64 and ppc32(ppc440) with a kexec-tools patch by Mahesh. Signed-off-by: Suzuki K. Poulose Tested-by: Mahesh J. Salgaonkar Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/machine_kexec.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index 4074eff1e744..fa9f6c72f557 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -204,6 +204,12 @@ static struct property crashk_size_prop = { .value = &crashk_size, }; +static struct property memory_limit_prop = { + .name = "linux,memory-limit", + .length = sizeof(unsigned long long), + .value = &memory_limit, +}; + static void __init export_crashk_values(struct device_node *node) { struct property *prop; @@ -223,6 +229,12 @@ static void __init export_crashk_values(struct device_node *node) crashk_size = resource_size(&crashk_res); prom_add_property(node, &crashk_size_prop); } + + /* + * memory_limit is required by the kexec-tools to limit the + * crash regions to the actual memory used. + */ + prom_update_property(node, &memory_limit_prop); } static int __init kexec_setup(void) -- cgit v1.3-14-g43fede From 3f4693eeeae45e9253031633adb0c7fde13a5026 Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Wed, 5 Sep 2012 19:17:48 +0000 Subject: powerpc: Use consistent name info for arch_hw_breakpoint Change bp_info to info to be consistent with the rest of this file. Signed-off-by: Michael Neuling Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/hw_breakpoint.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 956a4c496de9..6767445ecb45 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -294,7 +294,7 @@ int __kprobes single_step_dabr_instruction(struct die_args *args) { struct pt_regs *regs = args->regs; struct perf_event *bp = NULL; - struct arch_hw_breakpoint *bp_info; + struct arch_hw_breakpoint *info; bp = current->thread.last_hit_ubp; /* @@ -304,16 +304,16 @@ int __kprobes single_step_dabr_instruction(struct die_args *args) if (!bp) return NOTIFY_DONE; - bp_info = counter_arch_bp(bp); + info = counter_arch_bp(bp); /* * We shall invoke the user-defined callback function in the single * stepping handler to confirm to 'trigger-after-execute' semantics */ - if (!bp_info->extraneous_interrupt) + if (!info->extraneous_interrupt) perf_bp_event(bp, regs); - set_dabr(bp_info->address | bp_info->type | DABR_TRANSLATION); + set_dabr(info->address | info->type | DABR_TRANSLATION); current->thread.last_hit_ubp = NULL; /* -- cgit v1.3-14-g43fede From 407821a34fce89b4f0b031dbab5cec7d059f46bc Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 7 Sep 2012 15:31:44 +0000 Subject: powerpc: Initialise paca.data_offset with poison It's possible for the cpu_possible_mask to change between the time we initialise the pacas and the time we setup per_cpu areas. Obviously impossible cpus shouldn't ever be running, but stranger things have happened. So be paranoid and initialise data_offset with a poison value in case we don't set it up later. Based on a patch from Anton Blanchard. Signed-off-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/paca.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index fbe1a12dc7f1..cd6da855090c 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -142,6 +142,7 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu) new_paca->hw_cpu_id = 0xffff; new_paca->kexec_state = KEXEC_STATE_NONE; new_paca->__current = &init_task; + new_paca->data_offset = 0xfeeeeeeeeeeeeeeeULL; #ifdef CONFIG_PPC_STD_MMU_64 new_paca->slb_shadow_ptr = &slb_shadow[cpu]; #endif /* CONFIG_PPC_STD_MMU_64 */ -- cgit v1.3-14-g43fede From 35e5cfe27e674e4580408b34e7fc97e18460e048 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Fri, 7 Sep 2012 22:44:02 +0000 Subject: powerpc/eeh: Move EEH initialization around Currently, we have 3 phases for EEH initialization on pSeries platform. All of them are done through builtin functions: platform initialization, EEH device creation, and EEH subsystem enablement. All of them are done no later than ppc_md.setup_arch. That means that the slab/slub isn't ready yet, so we have to allocate memory chunks on basis of PAGE_SIZE for those dynamically created EEH devices. That's pretty expensive. In order to utilize slab/slub for memory allocation, we have to move the EEH initialization functions around, but all of them should be called after slab is ready. Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/eeh.h | 16 ---------------- arch/powerpc/kernel/rtas_pci.c | 3 --- arch/powerpc/platforms/pseries/eeh.c | 10 +++++++--- arch/powerpc/platforms/pseries/eeh_dev.c | 6 +++++- arch/powerpc/platforms/pseries/eeh_pseries.c | 4 +++- arch/powerpc/platforms/pseries/setup.c | 2 -- 6 files changed, 15 insertions(+), 26 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index d60f99814ffb..06dedffda129 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -117,11 +117,6 @@ extern int eeh_subsystem_enabled; void * __devinit eeh_dev_init(struct device_node *dn, void *data); void __devinit eeh_dev_phb_init_dynamic(struct pci_controller *phb); -void __init eeh_dev_phb_init(void); -void __init eeh_init(void); -#ifdef CONFIG_PPC_PSERIES -int __init eeh_pseries_init(void); -#endif int __init eeh_ops_register(struct eeh_ops *ops); int __exit eeh_ops_unregister(const char *name); unsigned long eeh_check_failure(const volatile void __iomem *token, @@ -156,17 +151,6 @@ static inline void *eeh_dev_init(struct device_node *dn, void *data) static inline void eeh_dev_phb_init_dynamic(struct pci_controller *phb) { } -static inline void eeh_dev_phb_init(void) { } - -static inline void eeh_init(void) { } - -#ifdef CONFIG_PPC_PSERIES -static inline int eeh_pseries_init(void) -{ - return 0; -} -#endif /* CONFIG_PPC_PSERIES */ - static inline unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned long val) { return val; diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index 179af906dcda..140735c18c36 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -275,9 +275,6 @@ void __init find_and_init_phbs(void) of_node_put(root); pci_devs_phb_init(); - /* Create EEH devices for all PHBs */ - eeh_dev_phb_init(); - /* * PCI_PROBE_ONLY and PCI_REASSIGN_ALL_BUS can be set via properties * in chosen. diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c index ecd394cf34e6..e819448ea3a7 100644 --- a/arch/powerpc/platforms/pseries/eeh.c +++ b/arch/powerpc/platforms/pseries/eeh.c @@ -982,7 +982,7 @@ int __exit eeh_ops_unregister(const char *name) * Even if force-off is set, the EEH hardware is still enabled, so that * newer systems can boot. */ -void __init eeh_init(void) +static int __init eeh_init(void) { struct pci_controller *hose, *tmp; struct device_node *phb; @@ -992,11 +992,11 @@ void __init eeh_init(void) if (!eeh_ops) { pr_warning("%s: Platform EEH operation not found\n", __func__); - return; + return -EEXIST; } else if ((ret = eeh_ops->init())) { pr_warning("%s: Failed to call platform init function (%d)\n", __func__, ret); - return; + return ret; } raw_spin_lock_init(&confirm_error_lock); @@ -1011,8 +1011,12 @@ void __init eeh_init(void) printk(KERN_INFO "EEH: PCI Enhanced I/O Error Handling Enabled\n"); else printk(KERN_WARNING "EEH: No capable adapters found\n"); + + return ret; } +core_initcall_sync(eeh_init); + /** * eeh_add_device_early - Enable EEH for the indicated device_node * @dn: device node for which to set up EEH diff --git a/arch/powerpc/platforms/pseries/eeh_dev.c b/arch/powerpc/platforms/pseries/eeh_dev.c index c4507d095900..ab68c5910f9f 100644 --- a/arch/powerpc/platforms/pseries/eeh_dev.c +++ b/arch/powerpc/platforms/pseries/eeh_dev.c @@ -93,10 +93,14 @@ void __devinit eeh_dev_phb_init_dynamic(struct pci_controller *phb) * Scan all the existing PHBs and create EEH devices for their OF * nodes and their children OF nodes */ -void __init eeh_dev_phb_init(void) +static int __init eeh_dev_phb_init(void) { struct pci_controller *phb, *tmp; list_for_each_entry_safe(phb, tmp, &hose_list, list_node) eeh_dev_phb_init_dynamic(phb); + + return 0; } + +core_initcall(eeh_dev_phb_init); diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index c33360ec4f4f..5e2805a019c3 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -559,7 +559,9 @@ static struct eeh_ops pseries_eeh_ops = { * EEH initialization on pseries platform. This function should be * called before any EEH related functions. */ -int __init eeh_pseries_init(void) +static int __init eeh_pseries_init(void) { return eeh_ops_register(&pseries_eeh_ops); } + +early_initcall(eeh_pseries_init); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 36b774442b5c..4a2cd48b21f6 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -388,10 +388,8 @@ static void __init pSeries_setup_arch(void) /* Find and initialize PCI host bridges */ init_pci_config_tokens(); - eeh_pseries_init(); find_and_init_phbs(); pSeries_reconfig_notifier_register(&pci_dn_reconfig_nb); - eeh_init(); pSeries_nvram_init(); -- cgit v1.3-14-g43fede From f8f7d63fd96ead101415a1302035137a866f8998 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Fri, 7 Sep 2012 22:44:22 +0000 Subject: powerpc/eeh: Trace eeh device from I/O cache The idea comes from Benjamin Herrenschmidt. The eeh cache helps fetching the pci device according to the given I/O address. Since the eeh cache is serving for eeh, it's reasonable for eeh cache to trace eeh device except pci device. The patch make eeh cache to trace eeh device. Also, the major eeh entry function eeh_dn_check_failure has been renamed to eeh_dev_check_failure since it will take eeh device as input parameter. Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/eeh.h | 7 ++----- arch/powerpc/include/asm/pci-bridge.h | 2 ++ arch/powerpc/include/asm/ppc-pci.h | 2 +- arch/powerpc/kernel/rtas_pci.c | 2 +- arch/powerpc/platforms/pseries/eeh.c | 33 +++++++++++++----------------- arch/powerpc/platforms/pseries/eeh_cache.c | 14 +++++++------ 6 files changed, 28 insertions(+), 32 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 895fd0d59ed7..ebfdb7c9d023 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -196,7 +196,7 @@ int __init eeh_ops_register(struct eeh_ops *ops); int __exit eeh_ops_unregister(const char *name); unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned long val); -int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev); +int eeh_dev_check_failure(struct eeh_dev *edev); void __init pci_addr_cache_build(void); void eeh_add_device_tree_early(struct device_node *); void eeh_add_device_tree_late(struct pci_bus *); @@ -231,10 +231,7 @@ static inline unsigned long eeh_check_failure(const volatile void __iomem *token return val; } -static inline int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev) -{ - return 0; -} +#define eeh_dev_check_failure(x) (0) static inline void pci_addr_cache_build(void) { } diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index 8cccbee61519..973df4d9d366 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -184,6 +184,8 @@ static inline struct eeh_dev *of_node_to_eeh_dev(struct device_node *dn) { return PCI_DN(dn)->edev; } +#else +#define of_node_to_eeh_dev(x) (NULL) #endif /** Find the bus corresponding to the indicated device node */ diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h index 56d55c7fed9a..962a9021cfa6 100644 --- a/arch/powerpc/include/asm/ppc-pci.h +++ b/arch/powerpc/include/asm/ppc-pci.h @@ -50,7 +50,7 @@ extern int rtas_setup_phb(struct pci_controller *phb); void pci_addr_cache_build(void); void pci_addr_cache_insert_device(struct pci_dev *dev); void pci_addr_cache_remove_device(struct pci_dev *dev); -struct pci_dev *pci_addr_cache_get_device(unsigned long addr); +struct eeh_dev *pci_addr_cache_get_device(unsigned long addr); void eeh_slot_error_detail(struct eeh_pe *pe, int severity); int eeh_pci_enable(struct eeh_pe *pe, int function); int eeh_reset_pe(struct eeh_pe *); diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index 140735c18c36..6de63e3250bb 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -81,7 +81,7 @@ int rtas_read_config(struct pci_dn *pdn, int where, int size, u32 *val) return PCIBIOS_DEVICE_NOT_FOUND; if (returnval == EEH_IO_ERROR_VALUE(size) && - eeh_dn_check_failure (pdn->node, NULL)) + eeh_dev_check_failure(of_node_to_eeh_dev(pdn->node))) return PCIBIOS_DEVICE_NOT_FOUND; return PCIBIOS_SUCCESSFUL; diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c index 4bdc278c2fd7..9e618424b187 100644 --- a/arch/powerpc/platforms/pseries/eeh.c +++ b/arch/powerpc/platforms/pseries/eeh.c @@ -270,9 +270,8 @@ static inline unsigned long eeh_token_to_phys(unsigned long token) } /** - * eeh_dn_check_failure - Check if all 1's data is due to EEH slot freeze - * @dn: device node - * @dev: pci device, if known + * eeh_dev_check_failure - Check if all 1's data is due to EEH slot freeze + * @edev: eeh device * * Check for an EEH failure for the given device node. Call this * routine if the result of a read was all 0xff's and you want to @@ -284,12 +283,13 @@ static inline unsigned long eeh_token_to_phys(unsigned long token) * * It is safe to call this routine in an interrupt context. */ -int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev) +int eeh_dev_check_failure(struct eeh_dev *edev) { int ret; unsigned long flags; + struct device_node *dn; + struct pci_dev *dev; struct eeh_pe *pe; - struct eeh_dev *edev; int rc = 0; const char *location; @@ -298,15 +298,12 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev) if (!eeh_subsystem_enabled) return 0; - if (dn) { - edev = of_node_to_eeh_dev(dn); - } else if (dev) { - edev = pci_dev_to_eeh_dev(dev); - dn = pci_device_to_OF_node(dev); - } else { + if (!edev) { eeh_stats.no_dn++; return 0; } + dn = eeh_dev_to_of_node(edev); + dev = eeh_dev_to_pci_dev(edev); pe = edev->pe; /* Access to IO BARs might get this far and still not want checking. */ @@ -393,7 +390,7 @@ dn_unlock: return rc; } -EXPORT_SYMBOL_GPL(eeh_dn_check_failure); +EXPORT_SYMBOL_GPL(eeh_dev_check_failure); /** * eeh_check_failure - Check if all 1's data is due to EEH slot freeze @@ -410,21 +407,19 @@ EXPORT_SYMBOL_GPL(eeh_dn_check_failure); unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned long val) { unsigned long addr; - struct pci_dev *dev; - struct device_node *dn; + struct eeh_dev *edev; /* Finding the phys addr + pci device; this is pretty quick. */ addr = eeh_token_to_phys((unsigned long __force) token); - dev = pci_addr_cache_get_device(addr); - if (!dev) { + edev = pci_addr_cache_get_device(addr); + if (!edev) { eeh_stats.no_device++; return val; } - dn = pci_device_to_OF_node(dev); - eeh_dn_check_failure(dn, dev); + eeh_dev_check_failure(edev); - pci_dev_put(dev); + pci_dev_put(eeh_dev_to_pci_dev(edev)); return val; } diff --git a/arch/powerpc/platforms/pseries/eeh_cache.c b/arch/powerpc/platforms/pseries/eeh_cache.c index a1910579d7aa..6c5ef757f4d4 100644 --- a/arch/powerpc/platforms/pseries/eeh_cache.c +++ b/arch/powerpc/platforms/pseries/eeh_cache.c @@ -50,6 +50,7 @@ struct pci_io_addr_range { struct rb_node rb_node; unsigned long addr_lo; unsigned long addr_hi; + struct eeh_dev *edev; struct pci_dev *pcidev; unsigned int flags; }; @@ -59,7 +60,7 @@ static struct pci_io_addr_cache { spinlock_t piar_lock; } pci_io_addr_cache_root; -static inline struct pci_dev *__pci_addr_cache_get_device(unsigned long addr) +static inline struct eeh_dev *__pci_addr_cache_get_device(unsigned long addr) { struct rb_node *n = pci_io_addr_cache_root.rb_root.rb_node; @@ -74,7 +75,7 @@ static inline struct pci_dev *__pci_addr_cache_get_device(unsigned long addr) n = n->rb_right; } else { pci_dev_get(piar->pcidev); - return piar->pcidev; + return piar->edev; } } } @@ -92,15 +93,15 @@ static inline struct pci_dev *__pci_addr_cache_get_device(unsigned long addr) * from zero (that is, they do *not* have pci_io_addr added in). * It is safe to call this function within an interrupt. */ -struct pci_dev *pci_addr_cache_get_device(unsigned long addr) +struct eeh_dev *pci_addr_cache_get_device(unsigned long addr) { - struct pci_dev *dev; + struct eeh_dev *edev; unsigned long flags; spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags); - dev = __pci_addr_cache_get_device(addr); + edev = __pci_addr_cache_get_device(addr); spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags); - return dev; + return edev; } #ifdef DEBUG @@ -158,6 +159,7 @@ pci_addr_cache_insert(struct pci_dev *dev, unsigned long alo, pci_dev_get(dev); piar->addr_lo = alo; piar->addr_hi = ahi; + piar->edev = pci_dev_to_eeh_dev(dev); piar->pcidev = dev; piar->flags = flags; -- cgit v1.3-14-g43fede From 4474ef055c5d8cb8eaf002d69e49af71e3aa3a88 Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Thu, 6 Sep 2012 21:24:56 +0000 Subject: powerpc: Rework set_dabr so it can take a DABRX value as well Rework set_dabr to take a DABRX value as well. Both the pseries and PS3 hypervisors do some checks on the DABRX values that are passed in the hcall. This patch stops bogus values from being passed to hypervisor. Also, in the case where we are clearing the breakpoint, where DABR and DABRX are zero, we modify the DABRX value to make it valid so that the hcall won't fail. Signed-off-by: Michael Neuling Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/debug.h | 2 +- arch/powerpc/include/asm/hw_breakpoint.h | 2 +- arch/powerpc/include/asm/machdep.h | 3 ++- arch/powerpc/include/asm/processor.h | 1 + arch/powerpc/include/asm/reg.h | 3 +++ arch/powerpc/kernel/hw_breakpoint.c | 12 ++++++------ arch/powerpc/kernel/process.c | 14 +++++++------- arch/powerpc/kernel/ptrace.c | 3 +++ arch/powerpc/kernel/signal.c | 2 +- arch/powerpc/platforms/cell/beat.c | 4 ++-- arch/powerpc/platforms/cell/beat.h | 2 +- arch/powerpc/platforms/ps3/setup.c | 10 +++++++--- arch/powerpc/platforms/pseries/setup.c | 14 +++++++++----- arch/powerpc/xmon/xmon.c | 4 ++-- 14 files changed, 46 insertions(+), 30 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/debug.h b/arch/powerpc/include/asm/debug.h index 716d2f089eb6..32de2577bb6d 100644 --- a/arch/powerpc/include/asm/debug.h +++ b/arch/powerpc/include/asm/debug.h @@ -44,7 +44,7 @@ static inline int debugger_dabr_match(struct pt_regs *regs) { return 0; } static inline int debugger_fault_handler(struct pt_regs *regs) { return 0; } #endif -extern int set_dabr(unsigned long dabr); +extern int set_dabr(unsigned long dabr, unsigned long dabrx); #ifdef CONFIG_PPC_ADV_DEBUG_REGS extern void do_send_trap(struct pt_regs *regs, unsigned long address, unsigned long error_code, int signal_code, int brkpt); diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h index 39b323e80c30..c6f48eb5299c 100644 --- a/arch/powerpc/include/asm/hw_breakpoint.h +++ b/arch/powerpc/include/asm/hw_breakpoint.h @@ -61,7 +61,7 @@ extern void ptrace_triggered(struct perf_event *bp, struct perf_sample_data *data, struct pt_regs *regs); static inline void hw_breakpoint_disable(void) { - set_dabr(0); + set_dabr(0, 0); } extern void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs); diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 42ce570812c1..236b4779ec4f 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -180,7 +180,8 @@ struct machdep_calls { void (*enable_pmcs)(void); /* Set DABR for this platform, leave empty for default implemenation */ - int (*set_dabr)(unsigned long dabr); + int (*set_dabr)(unsigned long dabr, + unsigned long dabrx); #ifdef CONFIG_PPC32 /* XXX for now */ /* A general init function, called by ppc_init in init/main.c. diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 7e7fa13e4667..83efc6e81543 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -219,6 +219,7 @@ struct thread_struct { #endif /* CONFIG_HAVE_HW_BREAKPOINT */ #endif unsigned long dabr; /* Data address breakpoint register */ + unsigned long dabrx; /* ... extension */ unsigned long trap_nr; /* last trap # on this thread */ #ifdef CONFIG_ALTIVEC /* Complete AltiVec register set */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index ad400a535d23..121a90bbf778 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -208,6 +208,9 @@ #define SPRN_DABRX 0x3F7 /* Data Address Breakpoint Register Extension */ #define DABRX_USER (1UL << 0) #define DABRX_KERNEL (1UL << 1) +#define DABRX_HYP (1UL << 2) +#define DABRX_BTI (1UL << 3) +#define DABRX_ALL (DABRX_BTI | DABRX_HYP | DABRX_KERNEL | DABRX_USER) #define SPRN_DAR 0x013 /* Data Address Register */ #define SPRN_DBCR 0x136 /* e300 Data Breakpoint Control Reg */ #define SPRN_DSISR 0x012 /* Data Storage Interrupt Status Register */ diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 6767445ecb45..6891d79ecef6 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -73,7 +73,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp) * If so, DABR will be populated in single_step_dabr_instruction(). */ if (current->thread.last_hit_ubp != bp) - set_dabr(info->address | info->type | DABR_TRANSLATION); + set_dabr(info->address | info->type | DABR_TRANSLATION, DABRX_ALL); return 0; } @@ -97,7 +97,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) } *slot = NULL; - set_dabr(0); + set_dabr(0, 0); } /* @@ -197,7 +197,7 @@ void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs) info = counter_arch_bp(tsk->thread.last_hit_ubp); regs->msr &= ~MSR_SE; - set_dabr(info->address | info->type | DABR_TRANSLATION); + set_dabr(info->address | info->type | DABR_TRANSLATION, DABRX_ALL); tsk->thread.last_hit_ubp = NULL; } @@ -215,7 +215,7 @@ int __kprobes hw_breakpoint_handler(struct die_args *args) unsigned long dar = regs->dar; /* Disable breakpoints during exception handling */ - set_dabr(0); + set_dabr(0, 0); /* * The counter may be concurrently released but that can only @@ -281,7 +281,7 @@ int __kprobes hw_breakpoint_handler(struct die_args *args) if (!info->extraneous_interrupt) perf_bp_event(bp, regs); - set_dabr(info->address | info->type | DABR_TRANSLATION); + set_dabr(info->address | info->type | DABR_TRANSLATION, DABRX_ALL); out: rcu_read_unlock(); return rc; @@ -313,7 +313,7 @@ int __kprobes single_step_dabr_instruction(struct die_args *args) if (!info->extraneous_interrupt) perf_bp_event(bp, regs); - set_dabr(info->address | info->type | DABR_TRANSLATION); + set_dabr(info->address | info->type | DABR_TRANSLATION, DABRX_ALL); current->thread.last_hit_ubp = NULL; /* diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 2e743de545d0..50e504c29bb9 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -285,7 +285,7 @@ void do_dabr(struct pt_regs *regs, unsigned long address, return; /* Clear the DABR */ - set_dabr(0); + set_dabr(0, 0); /* Deliver the signal to userspace */ info.si_signo = SIGTRAP; @@ -366,18 +366,19 @@ static void set_debug_reg_defaults(struct thread_struct *thread) { if (thread->dabr) { thread->dabr = 0; - set_dabr(0); + thread->dabrx = 0; + set_dabr(0, 0); } } #endif /* !CONFIG_HAVE_HW_BREAKPOINT */ #endif /* CONFIG_PPC_ADV_DEBUG_REGS */ -int set_dabr(unsigned long dabr) +int set_dabr(unsigned long dabr, unsigned long dabrx) { __get_cpu_var(current_dabr) = dabr; if (ppc_md.set_dabr) - return ppc_md.set_dabr(dabr); + return ppc_md.set_dabr(dabr, dabrx); /* XXX should we have a CPU_FTR_HAS_DABR ? */ #ifdef CONFIG_PPC_ADV_DEBUG_REGS @@ -387,9 +388,8 @@ int set_dabr(unsigned long dabr) #endif #elif defined(CONFIG_PPC_BOOK3S) mtspr(SPRN_DABR, dabr); + mtspr(SPRN_DABRX, dabrx); #endif - - return 0; } @@ -482,7 +482,7 @@ struct task_struct *__switch_to(struct task_struct *prev, */ #ifndef CONFIG_HAVE_HW_BREAKPOINT if (unlikely(__get_cpu_var(current_dabr) != new->thread.dabr)) - set_dabr(new->thread.dabr); + set_dabr(new->thread.dabr, new->thread.dabrx); #endif /* CONFIG_HAVE_HW_BREAKPOINT */ #endif diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index c10fc28b9092..79d8e56470df 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -960,6 +960,7 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, thread->ptrace_bps[0] = bp; ptrace_put_breakpoints(task); thread->dabr = data; + thread->dabrx = DABRX_ALL; return 0; } @@ -983,6 +984,7 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, /* Move contents to the DABR register */ task->thread.dabr = data; + task->thread.dabrx = DABRX_ALL; #else /* CONFIG_PPC_ADV_DEBUG_REGS */ /* As described above, it was assumed 3 bits were passed with the data * address, but we will assume only the mode bits will be passed @@ -1397,6 +1399,7 @@ static long ppc_set_hwdebug(struct task_struct *child, dabr |= DABR_DATA_WRITE; child->thread.dabr = dabr; + child->thread.dabrx = DABRX_ALL; return 1; #endif /* !CONFIG_PPC_ADV_DEBUG_DVCS */ diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 29be2712e560..a2dc75793bd5 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -131,7 +131,7 @@ static int do_signal(struct pt_regs *regs) * triggered inside the kernel. */ if (current->thread.dabr) - set_dabr(current->thread.dabr); + set_dabr(current->thread.dabr, current->thread.dabrx); #endif /* Re-enable the breakpoints for the signal stack */ thread_change_pc(current, regs); diff --git a/arch/powerpc/platforms/cell/beat.c b/arch/powerpc/platforms/cell/beat.c index 852592b2b712..affcf566d460 100644 --- a/arch/powerpc/platforms/cell/beat.c +++ b/arch/powerpc/platforms/cell/beat.c @@ -136,9 +136,9 @@ ssize_t beat_nvram_get_size(void) return BEAT_NVRAM_SIZE; } -int beat_set_xdabr(unsigned long dabr) +int beat_set_xdabr(unsigned long dabr, unsigned long dabrx) { - if (beat_set_dabr(dabr, DABRX_KERNEL | DABRX_USER)) + if (beat_set_dabr(dabr, dabrx)) return -1; return 0; } diff --git a/arch/powerpc/platforms/cell/beat.h b/arch/powerpc/platforms/cell/beat.h index 32c8efcedc80..bfcb8e351ae5 100644 --- a/arch/powerpc/platforms/cell/beat.h +++ b/arch/powerpc/platforms/cell/beat.h @@ -32,7 +32,7 @@ void beat_get_rtc_time(struct rtc_time *); ssize_t beat_nvram_get_size(void); ssize_t beat_nvram_read(char *, size_t, loff_t *); ssize_t beat_nvram_write(char *, size_t, loff_t *); -int beat_set_xdabr(unsigned long); +int beat_set_xdabr(unsigned long, unsigned long); void beat_power_save(void); void beat_kexec_cpu_down(int, int); diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c index 2d664c5a83b0..3f509f86432c 100644 --- a/arch/powerpc/platforms/ps3/setup.c +++ b/arch/powerpc/platforms/ps3/setup.c @@ -184,11 +184,15 @@ early_param("ps3flash", early_parse_ps3flash); #define prealloc_ps3flash_bounce_buffer() do { } while (0) #endif -static int ps3_set_dabr(unsigned long dabr) +static int ps3_set_dabr(unsigned long dabr, unsigned long dabrx) { - enum {DABR_USER = 1, DABR_KERNEL = 2,}; + /* Have to set at least one bit in the DABRX */ + if (dabrx == 0 && dabr == 0) + dabrx = DABRX_USER; + /* hypervisor only allows us to set BTI, Kernel and user */ + dabrx &= DABRX_BTI | DABRX_KERNEL | DABRX_USER; - return lv1_set_dabr(dabr, DABR_KERNEL | DABR_USER) ? -1 : 0; + return lv1_set_dabr(dabr, dabrx) ? -1 : 0; } static void __init ps3_setup_arch(void) diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 4a2cd48b21f6..a3a69658a6ec 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -414,16 +414,20 @@ static int __init pSeries_init_panel(void) } machine_arch_initcall(pseries, pSeries_init_panel); -static int pseries_set_dabr(unsigned long dabr) +static int pseries_set_dabr(unsigned long dabr, unsigned long dabrx) { return plpar_hcall_norets(H_SET_DABR, dabr); } -static int pseries_set_xdabr(unsigned long dabr) +static int pseries_set_xdabr(unsigned long dabr, unsigned long dabrx) { - /* We want to catch accesses from kernel and userspace */ - return plpar_hcall_norets(H_SET_XDABR, dabr, - H_DABRX_KERNEL | H_DABRX_USER); + /* Have to set at least one bit in the DABRX according to PAPR */ + if (dabrx == 0 && dabr == 0) + dabrx = DABRX_USER; + /* PAPR says we can only set kernel and user bits */ + dabrx &= H_DABRX_KERNEL | H_DABRX_USER; + + return plpar_hcall_norets(H_SET_XDABR, dabr, dabrx); } #define CMO_CHARACTERISTICS_TOKEN 44 diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 9b49c65ee7a4..987f441525cb 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -740,7 +740,7 @@ static void insert_bpts(void) static void insert_cpu_bpts(void) { if (dabr.enabled) - set_dabr(dabr.address | (dabr.enabled & 7)); + set_dabr(dabr.address | (dabr.enabled & 7), DABRX_ALL); if (iabr && cpu_has_feature(CPU_FTR_IABR)) mtspr(SPRN_IABR, iabr->address | (iabr->enabled & (BP_IABR|BP_IABR_TE))); @@ -768,7 +768,7 @@ static void remove_bpts(void) static void remove_cpu_bpts(void) { - set_dabr(0); + set_dabr(0, 0); if (cpu_has_feature(CPU_FTR_IABR)) mtspr(SPRN_IABR, 0); } -- cgit v1.3-14-g43fede From cd14457304c9d232267a3a76a2a43f1f791e545d Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Thu, 6 Sep 2012 21:24:57 +0000 Subject: powerpc: Dynamically calculate the dabrx based on kernel/user/hypervisor Currently we mark the DABRX to interrupt on all matches (hypervisor/kernel/user and then filter in software. We can be a lot smarter now that we can set the DABRX dynamically. This sets the DABRX based on the flags passed by the user. Signed-off-by: Michael Neuling Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/hw_breakpoint.h | 1 + arch/powerpc/kernel/hw_breakpoint.c | 15 +++++++++++---- arch/powerpc/platforms/pseries/setup.c | 2 +- 3 files changed, 13 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h index c6f48eb5299c..423424599dad 100644 --- a/arch/powerpc/include/asm/hw_breakpoint.h +++ b/arch/powerpc/include/asm/hw_breakpoint.h @@ -28,6 +28,7 @@ struct arch_hw_breakpoint { unsigned long address; + unsigned long dabrx; int type; u8 len; /* length of the target data symbol */ bool extraneous_interrupt; diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 6891d79ecef6..a89cae481b04 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -73,7 +73,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp) * If so, DABR will be populated in single_step_dabr_instruction(). */ if (current->thread.last_hit_ubp != bp) - set_dabr(info->address | info->type | DABR_TRANSLATION, DABRX_ALL); + set_dabr(info->address | info->type | DABR_TRANSLATION, info->dabrx); return 0; } @@ -170,6 +170,13 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) info->address = bp->attr.bp_addr; info->len = bp->attr.bp_len; + info->dabrx = DABRX_ALL; + if (bp->attr.exclude_user) + info->dabrx &= ~DABRX_USER; + if (bp->attr.exclude_kernel) + info->dabrx &= ~DABRX_KERNEL; + if (bp->attr.exclude_hv) + info->dabrx &= ~DABRX_HYP; /* * Since breakpoint length can be a maximum of HW_BREAKPOINT_LEN(8) @@ -197,7 +204,7 @@ void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs) info = counter_arch_bp(tsk->thread.last_hit_ubp); regs->msr &= ~MSR_SE; - set_dabr(info->address | info->type | DABR_TRANSLATION, DABRX_ALL); + set_dabr(info->address | info->type | DABR_TRANSLATION, info->dabrx); tsk->thread.last_hit_ubp = NULL; } @@ -281,7 +288,7 @@ int __kprobes hw_breakpoint_handler(struct die_args *args) if (!info->extraneous_interrupt) perf_bp_event(bp, regs); - set_dabr(info->address | info->type | DABR_TRANSLATION, DABRX_ALL); + set_dabr(info->address | info->type | DABR_TRANSLATION, info->dabrx); out: rcu_read_unlock(); return rc; @@ -313,7 +320,7 @@ int __kprobes single_step_dabr_instruction(struct die_args *args) if (!info->extraneous_interrupt) perf_bp_event(bp, regs); - set_dabr(info->address | info->type | DABR_TRANSLATION, DABRX_ALL); + set_dabr(info->address | info->type | DABR_TRANSLATION, info->dabrx); current->thread.last_hit_ubp = NULL; /* diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index a3a69658a6ec..e3cb7ae61658 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -425,7 +425,7 @@ static int pseries_set_xdabr(unsigned long dabr, unsigned long dabrx) if (dabrx == 0 && dabr == 0) dabrx = DABRX_USER; /* PAPR says we can only set kernel and user bits */ - dabrx &= H_DABRX_KERNEL | H_DABRX_USER; + dabrx &= DABRX_KERNEL | DABRX_USER; return plpar_hcall_norets(H_SET_XDABR, dabr, dabrx); } -- cgit v1.3-14-g43fede From 4c2245bb5c9c6e9950ee8919b4462dfa77f7a28f Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Tue, 11 Sep 2012 16:59:46 -0600 Subject: powerpc/PCI: Override pcibios_window_alignment() This patch implements pcibios_window_alignment() so powerpc platforms can force P2P bridge windows to be at larger alignments than the PCI spec requires. [bhelgaas: changelog] Signed-off-by: Gavin Shan Signed-off-by: Bjorn Helgaas --- arch/powerpc/include/asm/machdep.h | 3 +++ arch/powerpc/kernel/pci-common.c | 20 ++++++++++++++++++++ 2 files changed, 23 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 42ce570812c1..f7706d722b39 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -214,6 +214,9 @@ struct machdep_calls { /* Called after scan and before resource survey */ void (*pcibios_fixup_phb)(struct pci_controller *hose); + /* Called during PCI resource reassignment */ + resource_size_t (*pcibios_window_alignment)(struct pci_bus *, unsigned long type); + /* Called to shutdown machine specific hardware not already controlled * by other drivers. */ diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 2aa04f29e1de..43fea543d686 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -99,6 +99,26 @@ void pcibios_free_controller(struct pci_controller *phb) kfree(phb); } +/* + * The function is used to return the minimal alignment + * for memory or I/O windows of the associated P2P bridge. + * By default, 4KiB alignment for I/O windows and 1MiB for + * memory windows. + */ +resource_size_t pcibios_window_alignment(struct pci_bus *bus, + unsigned long type) +{ + if (ppc_md.pcibios_window_alignment) + return ppc_md.pcibios_window_alignment(bus, type); + + /* + * PCI core will figure out the default + * alignment: 4KiB for I/O and 1MiB for + * memory window. + */ + return 1; +} + static resource_size_t pcibios_io_size(const struct pci_controller *hose) { #ifdef CONFIG_PPC64 -- cgit v1.3-14-g43fede From ae5cab476342bc7311945cf89d5cbd8d57f4a5a9 Mon Sep 17 00:00:00 2001 From: Zhao Chenhui Date: Fri, 20 Jul 2012 20:42:34 +0800 Subject: powerpc/smp: add generic_set_cpu_up() to set cpu_state as CPU_UP_PREPARE In the case of cpu hotplug, the cpu_state should be set to CPU_UP_PREPARE when kicking cpu. Otherwise, the cpu_state is always CPU_DEAD after calling generic_set_cpu_dead(), which makes the delay in generic_cpu_die() not happen. Signed-off-by: Zhao Chenhui Signed-off-by: Kumar Gala --- arch/powerpc/include/asm/smp.h | 1 + arch/powerpc/kernel/smp.c | 12 +++++++++++- 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index ebc24dc5b1a1..ce8e2bdf84ed 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -65,6 +65,7 @@ int generic_cpu_disable(void); void generic_cpu_die(unsigned int cpu); void generic_mach_cpu_die(void); void generic_set_cpu_dead(unsigned int cpu); +void generic_set_cpu_up(unsigned int cpu); int generic_check_cpu_restart(unsigned int cpu); #endif diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 8d4214afc21d..a51ed205016e 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -102,7 +102,7 @@ int __devinit smp_generic_kick_cpu(int nr) * Ok it's not there, so it might be soft-unplugged, let's * try to bring it back */ - per_cpu(cpu_state, nr) = CPU_UP_PREPARE; + generic_set_cpu_up(nr); smp_wmb(); smp_send_reschedule(nr); #endif /* CONFIG_HOTPLUG_CPU */ @@ -413,6 +413,16 @@ void generic_set_cpu_dead(unsigned int cpu) per_cpu(cpu_state, cpu) = CPU_DEAD; } +/* + * The cpu_state should be set to CPU_UP_PREPARE in kick_cpu(), otherwise + * the cpu_state is always CPU_DEAD after calling generic_set_cpu_dead(), + * which makes the delay in generic_cpu_die() not happen. + */ +void generic_set_cpu_up(unsigned int cpu) +{ + per_cpu(cpu_state, cpu) = CPU_UP_PREPARE; +} + int generic_check_cpu_restart(unsigned int cpu) { return per_cpu(cpu_state, cpu) == CPU_UP_PREPARE; -- cgit v1.3-14-g43fede From d0832a75075b1119635e0f48549e378040cf5e67 Mon Sep 17 00:00:00 2001 From: Zhao Chenhui Date: Fri, 20 Jul 2012 20:42:36 +0800 Subject: powerpc/85xx: add HOTPLUG_CPU support Add support to disable and re-enable individual cores at runtime on MPC85xx/QorIQ SMP machines. Currently support e500v1/e500v2 core. MPC85xx machines use ePAPR spin-table in boot page for CPU kick-off. This patch uses the boot page from bootloader to boot core at runtime. It supports 32-bit and 36-bit physical address. Signed-off-by: Li Yang Signed-off-by: Jin Qing Signed-off-by: Zhao Chenhui Signed-off-by: Kumar Gala --- arch/powerpc/Kconfig | 6 ++- arch/powerpc/include/asm/cacheflush.h | 2 + arch/powerpc/include/asm/smp.h | 1 + arch/powerpc/kernel/head_fsl_booke.S | 28 +++++++++++ arch/powerpc/platforms/85xx/smp.c | 90 ++++++++++++++++++++++++++++++----- 5 files changed, 112 insertions(+), 15 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 98e513b62709..b8bab10bd0f1 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -215,7 +215,8 @@ config ARCH_HIBERNATION_POSSIBLE config ARCH_SUSPEND_POSSIBLE def_bool y depends on ADB_PMU || PPC_EFIKA || PPC_LITE5200 || PPC_83xx || \ - (PPC_85xx && !SMP) || PPC_86xx || PPC_PSERIES || 44x || 40x + (PPC_85xx && !PPC_E500MC) || PPC_86xx || PPC_PSERIES \ + || 44x || 40x config PPC_DCR_NATIVE bool @@ -328,7 +329,8 @@ config SWIOTLB config HOTPLUG_CPU bool "Support for enabling/disabling CPUs" - depends on SMP && HOTPLUG && EXPERIMENTAL && (PPC_PSERIES || PPC_PMAC || PPC_POWERNV) + depends on SMP && HOTPLUG && EXPERIMENTAL && (PPC_PSERIES || \ + PPC_PMAC || PPC_POWERNV || (PPC_85xx && !PPC_E500MC)) ---help--- Say Y here to be able to disable and re-enable individual CPUs at runtime on SMP machines. diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h index ab9e402518e8..b843e35122e8 100644 --- a/arch/powerpc/include/asm/cacheflush.h +++ b/arch/powerpc/include/asm/cacheflush.h @@ -30,6 +30,8 @@ extern void flush_dcache_page(struct page *page); #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) +extern void __flush_disable_L1(void); + extern void __flush_icache_range(unsigned long, unsigned long); static inline void flush_icache_range(unsigned long start, unsigned long stop) { diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index ce8e2bdf84ed..e807e9d8e3f7 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -191,6 +191,7 @@ extern unsigned long __secondary_hold_spinloop; extern unsigned long __secondary_hold_acknowledge; extern char __secondary_hold; +extern void __early_start(void); #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index 0f59863c3ade..b221541d9861 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -1043,6 +1043,34 @@ _GLOBAL(flush_dcache_L1) blr +/* Flush L1 d-cache, invalidate and disable d-cache and i-cache */ +_GLOBAL(__flush_disable_L1) + mflr r10 + bl flush_dcache_L1 /* Flush L1 d-cache */ + mtlr r10 + + mfspr r4, SPRN_L1CSR0 /* Invalidate and disable d-cache */ + li r5, 2 + rlwimi r4, r5, 0, 3 + + msync + isync + mtspr SPRN_L1CSR0, r4 + isync + +1: mfspr r4, SPRN_L1CSR0 /* Wait for the invalidate to finish */ + andi. r4, r4, 2 + bne 1b + + mfspr r4, SPRN_L1CSR1 /* Invalidate and disable i-cache */ + li r5, 2 + rlwimi r4, r5, 0, 3 + + mtspr SPRN_L1CSR1, r4 + isync + + blr + #ifdef CONFIG_SMP /* When we get here, r24 needs to hold the CPU # */ .globl __secondary_start diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c index 7ed52a604a13..6fcfa12e5c56 100644 --- a/arch/powerpc/platforms/85xx/smp.c +++ b/arch/powerpc/platforms/85xx/smp.c @@ -31,8 +31,6 @@ #include #include "smp.h" -extern void __early_start(void); - struct epapr_spin_table { u32 addr_h; u32 addr_l; @@ -100,15 +98,45 @@ static void mpc85xx_take_timebase(void) local_irq_restore(flags); } -static int __init -smp_85xx_kick_cpu(int nr) +#ifdef CONFIG_HOTPLUG_CPU +static void __cpuinit smp_85xx_mach_cpu_die(void) +{ + unsigned int cpu = smp_processor_id(); + u32 tmp; + + local_irq_disable(); + idle_task_exit(); + generic_set_cpu_dead(cpu); + mb(); + + mtspr(SPRN_TCR, 0); + + __flush_disable_L1(); + tmp = (mfspr(SPRN_HID0) & ~(HID0_DOZE|HID0_SLEEP)) | HID0_NAP; + mtspr(SPRN_HID0, tmp); + isync(); + + /* Enter NAP mode. */ + tmp = mfmsr(); + tmp |= MSR_WE; + mb(); + mtmsr(tmp); + isync(); + + while (1) + ; +} +#endif + +static int __cpuinit smp_85xx_kick_cpu(int nr) { unsigned long flags; const u64 *cpu_rel_addr; __iomem struct epapr_spin_table *spin_table; struct device_node *np; - int n = 0, hw_cpu = get_hard_smp_processor_id(nr); + int hw_cpu = get_hard_smp_processor_id(nr); int ioremappable; + int ret = 0; WARN_ON(nr < 0 || nr >= NR_CPUS); WARN_ON(hw_cpu < 0 || hw_cpu >= NR_CPUS); @@ -139,9 +167,34 @@ smp_85xx_kick_cpu(int nr) spin_table = phys_to_virt(*cpu_rel_addr); local_irq_save(flags); +#ifdef CONFIG_PPC32 +#ifdef CONFIG_HOTPLUG_CPU + /* Corresponding to generic_set_cpu_dead() */ + generic_set_cpu_up(nr); + + if (system_state == SYSTEM_RUNNING) { + out_be32(&spin_table->addr_l, 0); + /* + * We don't set the BPTR register here since it already points + * to the boot page properly. + */ + mpic_reset_core(hw_cpu); + + /* wait until core is ready... */ + if (!spin_event_timeout(in_be32(&spin_table->addr_l) == 1, + 10000, 100)) { + pr_err("%s: timeout waiting for core %d to reset\n", + __func__, hw_cpu); + ret = -ENOENT; + goto out; + } + + /* clear the acknowledge status */ + __secondary_hold_acknowledge = -1; + } +#endif out_be32(&spin_table->pir, hw_cpu); -#ifdef CONFIG_PPC32 out_be32(&spin_table->addr_l, __pa(__early_start)); if (!ioremappable) @@ -149,11 +202,18 @@ smp_85xx_kick_cpu(int nr) (ulong)spin_table + sizeof(struct epapr_spin_table)); /* Wait a bit for the CPU to ack. */ - while ((__secondary_hold_acknowledge != hw_cpu) && (++n < 1000)) - mdelay(1); + if (!spin_event_timeout(__secondary_hold_acknowledge == hw_cpu, + 10000, 100)) { + pr_err("%s: timeout waiting for core %d to ack\n", + __func__, hw_cpu); + ret = -ENOENT; + goto out; + } +out: #else smp_generic_kick_cpu(nr); + out_be32(&spin_table->pir, hw_cpu); out_be64((u64 *)(&spin_table->addr_h), __pa((u64)*((unsigned long long *)generic_secondary_smp_init))); @@ -167,13 +227,15 @@ smp_85xx_kick_cpu(int nr) if (ioremappable) iounmap(spin_table); - pr_debug("waited %d msecs for CPU #%d.\n", n, nr); - - return 0; + return ret; } struct smp_ops_t smp_85xx_ops = { .kick_cpu = smp_85xx_kick_cpu, +#ifdef CONFIG_HOTPLUG_CPU + .cpu_disable = generic_cpu_disable, + .cpu_die = generic_cpu_die, +#endif #ifdef CONFIG_KEXEC .give_timebase = smp_generic_give_timebase, .take_timebase = smp_generic_take_timebase, @@ -277,8 +339,7 @@ static void mpc85xx_smp_machine_kexec(struct kimage *image) } #endif /* CONFIG_KEXEC */ -static void __init -smp_85xx_setup_cpu(int cpu_nr) +static void __cpuinit smp_85xx_setup_cpu(int cpu_nr) { if (smp_85xx_ops.probe == smp_mpic_probe) mpic_setup_this_cpu(); @@ -329,6 +390,9 @@ void __init mpc85xx_smp_init(void) } smp_85xx_ops.give_timebase = mpc85xx_give_timebase; smp_85xx_ops.take_timebase = mpc85xx_take_timebase; +#ifdef CONFIG_HOTPLUG_CPU + ppc_md.cpu_die = smp_85xx_mach_cpu_die; +#endif } smp_ops = &smp_85xx_ops; -- cgit v1.3-14-g43fede From 7e0f4872a33c6da38e727cf42c939cc32294fce6 Mon Sep 17 00:00:00 2001 From: Varun Sethi Date: Mon, 9 Jul 2012 18:25:31 +0530 Subject: powepc/booke: Separate out E.HV check and ivor setup code. Move the E.HV check and CPU_FTR_EMB_HV flag manipulation to the cpu setup code. Create a separate routine for E.HV ivors setup. Signed-off-by: Varun Sethi Signed-off-by: Kumar Gala --- arch/powerpc/kernel/cpu_setup_fsl_booke.S | 29 ++++++++++++++++++++++++++--- arch/powerpc/kernel/head_fsl_booke.S | 18 ++++-------------- 2 files changed, 30 insertions(+), 17 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S index 69fdd2322a66..a55d028aa0da 100644 --- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S +++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S @@ -16,6 +16,8 @@ #include #include #include +#include +#include _GLOBAL(__e500_icache_setup) mfspr r0, SPRN_L1CSR1 @@ -73,12 +75,33 @@ _GLOBAL(__setup_cpu_e500v2) mtlr r4 blr _GLOBAL(__setup_cpu_e500mc) - mr r5, r4 - mflr r4 + mflr r5 bl __e500_icache_setup bl __e500_dcache_setup bl __setup_e500mc_ivors - mtlr r4 + /* + * We only want to touch IVOR38-41 if we're running on hardware + * that supports category E.HV. The architectural way to determine + * this is MMUCFG[LPIDSIZE]. + */ + mfspr r3, SPRN_MMUCFG + rlwinm. r3, r3, 0, MMUCFG_LPIDSIZE + beq 1f + bl __setup_ehv_ivors + b 2f +1: + lwz r3, CPU_SPEC_FEATURES(r4) + /* We need this check as cpu_setup is also called for + * the secondary cores. So, if we have already cleared + * the feature on the primary core, avoid doing it on the + * secondary core. + */ + andis. r6, r3, CPU_FTR_EMB_HV@h + beq 2f + rlwinm r3, r3, 0, ~CPU_FTR_EMB_HV + stw r3, CPU_SPEC_FEATURES(r4) +2: + mtlr r5 blr #endif /* Right now, restore and setup are the same thing */ diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index b221541d9861..6f62a737f607 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -895,15 +895,11 @@ _GLOBAL(__setup_e500mc_ivors) mtspr SPRN_IVOR36,r3 li r3,CriticalDoorbell@l mtspr SPRN_IVOR37,r3 + sync + blr - /* - * We only want to touch IVOR38-41 if we're running on hardware - * that supports category E.HV. The architectural way to determine - * this is MMUCFG[LPIDSIZE]. - */ - mfspr r3, SPRN_MMUCFG - andis. r3, r3, MMUCFG_LPIDSIZE@h - beq no_hv +/* setup ehv ivors for */ +_GLOBAL(__setup_ehv_ivors) li r3,GuestDoorbell@l mtspr SPRN_IVOR38,r3 li r3,CriticalGuestDoorbell@l @@ -912,14 +908,8 @@ _GLOBAL(__setup_e500mc_ivors) mtspr SPRN_IVOR40,r3 li r3,Ehvpriv@l mtspr SPRN_IVOR41,r3 -skip_hv_ivors: sync blr -no_hv: - lwz r3, CPU_SPEC_FEATURES(r5) - rlwinm r3, r3, 0, ~CPU_FTR_EMB_HV - stw r3, CPU_SPEC_FEATURES(r5) - b skip_hv_ivors #ifdef CONFIG_SPE /* -- cgit v1.3-14-g43fede From 2c71b0cc4a626d8bd02b88b3b92ce18be4d54c6d Mon Sep 17 00:00:00 2001 From: Varun Sethi Date: Mon, 9 Jul 2012 18:28:21 +0530 Subject: powerpc/booke: Merge the 32 bit e5500/e500mc cpu setup code. Merge the 32 bit cpu setup code for e500mc/e5500 and define the "cpu_restore" routine (for e5500/e6500) only for the 64 bit case. The cpu_restore routine is used in the 64 bit case for setting up the secondary cores. Signed-off-by: Varun Sethi Signed-off-by: Kumar Gala --- arch/powerpc/kernel/cpu_setup_fsl_booke.S | 7 +++---- arch/powerpc/kernel/cputable.c | 4 ++++ 2 files changed, 7 insertions(+), 4 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S index a55d028aa0da..021822daa8f6 100644 --- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S +++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S @@ -75,6 +75,7 @@ _GLOBAL(__setup_cpu_e500v2) mtlr r4 blr _GLOBAL(__setup_cpu_e500mc) +_GLOBAL(__setup_cpu_e5500) mflr r5 bl __e500_icache_setup bl __e500_dcache_setup @@ -104,19 +105,17 @@ _GLOBAL(__setup_cpu_e500mc) mtlr r5 blr #endif +#ifdef CONFIG_PPC_BOOK3E_64 /* Right now, restore and setup are the same thing */ _GLOBAL(__restore_cpu_e5500) _GLOBAL(__setup_cpu_e5500) mflr r4 bl __e500_icache_setup bl __e500_dcache_setup -#ifdef CONFIG_PPC_BOOK3E_64 bl .__setup_base_ivors bl .setup_perfmon_ivor bl .setup_doorbell_ivors bl .setup_ehv_ivors -#else - bl __setup_e500mc_ivors -#endif mtlr r4 blr +#endif diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 455faa389876..0514c21f138b 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -2016,7 +2016,9 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_cpu_type = "ppc/e500mc", .oprofile_type = PPC_OPROFILE_FSL_EMB, .cpu_setup = __setup_cpu_e5500, +#ifndef CONFIG_PPC32 .cpu_restore = __restore_cpu_e5500, +#endif .machine_check = machine_check_e500mc, .platform = "ppce5500", }, @@ -2034,7 +2036,9 @@ static struct cpu_spec __initdata cpu_specs[] = { .oprofile_cpu_type = "ppc/e6500", .oprofile_type = PPC_OPROFILE_FSL_EMB, .cpu_setup = __setup_cpu_e5500, +#ifndef CONFIG_PPC32 .cpu_restore = __restore_cpu_e5500, +#endif .machine_check = machine_check_e500mc, .platform = "ppce6500", }, -- cgit v1.3-14-g43fede From 0778407f836d632cce90e5d9df490a7c5e6e398a Mon Sep 17 00:00:00 2001 From: Varun Sethi Date: Mon, 9 Jul 2012 18:31:51 +0530 Subject: powerpc/booke: Separate out restore_e5500/setup_e5500 routines. For the 64 bit case separate out e5500 cpu_setup and cpu_restore functions. The cpu_setup function (for the primary core) is passed the cpu_spec pointer, which is not there in case of the cpu_restore function. Also, in our case we will have to manipulate the CPU_FTR_EMB_HV flag on the primary core. Signed-off-by: Varun Sethi Signed-off-by: Kumar Gala --- arch/powerpc/kernel/cpu_setup_fsl_booke.S | 32 +++++++++++++++++++++++++++++-- arch/powerpc/kernel/exceptions-64e.S | 18 ++--------------- 2 files changed, 32 insertions(+), 18 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S index 021822daa8f6..1345e1bc748a 100644 --- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S +++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S @@ -105,17 +105,45 @@ _GLOBAL(__setup_cpu_e5500) mtlr r5 blr #endif + #ifdef CONFIG_PPC_BOOK3E_64 -/* Right now, restore and setup are the same thing */ _GLOBAL(__restore_cpu_e5500) -_GLOBAL(__setup_cpu_e5500) mflr r4 bl __e500_icache_setup bl __e500_dcache_setup bl .__setup_base_ivors bl .setup_perfmon_ivor bl .setup_doorbell_ivors + /* + * We only want to touch IVOR38-41 if we're running on hardware + * that supports category E.HV. The architectural way to determine + * this is MMUCFG[LPIDSIZE]. + */ + mfspr r10,SPRN_MMUCFG + rlwinm. r10,r10,0,MMUCFG_LPIDSIZE + beq 1f bl .setup_ehv_ivors +1: mtlr r4 blr + +_GLOBAL(__setup_cpu_e5500) + mflr r5 + bl __e500_icache_setup + bl __e500_dcache_setup + bl .__setup_base_ivors + bl .setup_perfmon_ivor + bl .setup_doorbell_ivors + /* + * We only want to touch IVOR38-41 if we're running on hardware + * that supports category E.HV. The architectural way to determine + * this is MMUCFG[LPIDSIZE]. + */ + mfspr r10,SPRN_MMUCFG + rlwinm. r10,r10,0,MMUCFG_LPIDSIZE + beq 1f + bl .setup_ehv_ivors +1: + mtlr r5 + blr #endif diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 87a82fbdf05a..4684e33a26c3 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -1356,25 +1356,11 @@ _GLOBAL(setup_perfmon_ivor) _GLOBAL(setup_doorbell_ivors) SET_IVOR(36, 0x280) /* Processor Doorbell */ SET_IVOR(37, 0x2a0) /* Processor Doorbell Crit */ - - /* Check MMUCFG[LPIDSIZE] to determine if we have category E.HV */ - mfspr r10,SPRN_MMUCFG - rlwinm. r10,r10,0,MMUCFG_LPIDSIZE - beqlr - - SET_IVOR(38, 0x2c0) /* Guest Processor Doorbell */ - SET_IVOR(39, 0x2e0) /* Guest Processor Doorbell Crit/MC */ blr _GLOBAL(setup_ehv_ivors) - /* - * We may be running as a guest and lack E.HV even on a chip - * that normally has it. - */ - mfspr r10,SPRN_MMUCFG - rlwinm. r10,r10,0,MMUCFG_LPIDSIZE - beqlr - SET_IVOR(40, 0x300) /* Embedded Hypervisor System Call */ SET_IVOR(41, 0x320) /* Embedded Hypervisor Privilege */ + SET_IVOR(38, 0x2c0) /* Guest Processor Doorbell */ + SET_IVOR(39, 0x2e0) /* Guest Processor Doorbell Crit/MC */ blr -- cgit v1.3-14-g43fede From 39be5b4a7f232870aad0b3c130791eacd0d34347 Mon Sep 17 00:00:00 2001 From: Varun Sethi Date: Mon, 9 Jul 2012 18:34:01 +0530 Subject: powerpc/booke: Add CPU_FTR_EMB_HV check for e5500. Added CPU_FTR_EMB_HV feature check for e5500. Signed-off-by: Varun Sethi Signed-off-by: Mihai Caraman Signed-off-by: Kumar Gala --- arch/powerpc/kernel/cpu_setup_fsl_booke.S | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S index 1345e1bc748a..dcd881937f7a 100644 --- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S +++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S @@ -143,7 +143,13 @@ _GLOBAL(__setup_cpu_e5500) rlwinm. r10,r10,0,MMUCFG_LPIDSIZE beq 1f bl .setup_ehv_ivors + b 2f 1: + ld r10,CPU_SPEC_FEATURES(r4) + LOAD_REG_IMMEDIATE(r9,CPU_FTR_EMB_HV) + andc r10,r10,r9 + std r10,CPU_SPEC_FEATURES(r4) +2: mtlr r5 blr #endif -- cgit v1.3-14-g43fede From 688ba1dbee8a49a2efe507cd9ae69634d92bb640 Mon Sep 17 00:00:00 2001 From: Jia Hongtao Date: Fri, 3 Aug 2012 18:14:10 +0800 Subject: powerpc/swiotlb: Enable at early stage and disable if not necessary Remove the dependency on PCI initialization for SWIOTLB initialization. So that PCI can be initialized at proper time. SWIOTLB is partly determined by PCI inbound/outbound map which is assigned in PCI initialization. But swiotlb_init() should be done at the stage of mem_init() which is much earlier than PCI initialization. So we reserve the memory for SWIOTLB first and free it if not necessary. All boards are converted to fit this change. Signed-off-by: Jia Hongtao Signed-off-by: Li Yang Acked-by: Tony Breeds Signed-off-by: Kumar Gala --- arch/powerpc/include/asm/swiotlb.h | 6 ++++++ arch/powerpc/kernel/dma-swiotlb.c | 20 ++++++++++++++++++++ arch/powerpc/mm/mem.c | 3 +-- arch/powerpc/platforms/44x/currituck.c | 10 ++-------- arch/powerpc/platforms/85xx/mpc85xx_ds.c | 1 + arch/powerpc/platforms/85xx/qemu_e500.c | 1 + arch/powerpc/sysdev/fsl_pci.c | 5 +---- 7 files changed, 32 insertions(+), 14 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/swiotlb.h b/arch/powerpc/include/asm/swiotlb.h index 8979d4cd3d70..de99d6e29430 100644 --- a/arch/powerpc/include/asm/swiotlb.h +++ b/arch/powerpc/include/asm/swiotlb.h @@ -22,4 +22,10 @@ int __init swiotlb_setup_bus_notifier(void); extern void pci_dma_dev_setup_swiotlb(struct pci_dev *pdev); +#ifdef CONFIG_SWIOTLB +void swiotlb_detect_4g(void); +#else +static inline void swiotlb_detect_4g(void) {} +#endif + #endif /* __ASM_SWIOTLB_H */ diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c index a720b54b971c..bd1a2aba599f 100644 --- a/arch/powerpc/kernel/dma-swiotlb.c +++ b/arch/powerpc/kernel/dma-swiotlb.c @@ -105,3 +105,23 @@ int __init swiotlb_setup_bus_notifier(void) &ppc_swiotlb_plat_bus_notifier); return 0; } + +void swiotlb_detect_4g(void) +{ + if ((memblock_end_of_DRAM() - 1) > 0xffffffff) + ppc_swiotlb_enable = 1; +} + +static int __init swiotlb_late_init(void) +{ + if (ppc_swiotlb_enable) { + swiotlb_print_info(); + set_pci_dma_ops(&swiotlb_dma_ops); + ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb; + } else { + swiotlb_free(); + } + + return 0; +} +subsys_initcall(swiotlb_late_init); diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 44cf2b20503d..0dba5066c22a 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -300,8 +300,7 @@ void __init mem_init(void) unsigned long reservedpages = 0, codesize, initsize, datasize, bsssize; #ifdef CONFIG_SWIOTLB - if (ppc_swiotlb_enable) - swiotlb_init(1); + swiotlb_init(0); #endif num_physpages = memblock_phys_mem_size() >> PAGE_SHIFT; diff --git a/arch/powerpc/platforms/44x/currituck.c b/arch/powerpc/platforms/44x/currituck.c index 9f6c33d63a42..6bd89a0e0dea 100644 --- a/arch/powerpc/platforms/44x/currituck.c +++ b/arch/powerpc/platforms/44x/currituck.c @@ -21,7 +21,6 @@ */ #include -#include #include #include #include @@ -159,13 +158,8 @@ static void __init ppc47x_setup_arch(void) /* No need to check the DMA config as we /know/ our windows are all of * RAM. Lets hope that doesn't change */ -#ifdef CONFIG_SWIOTLB - if ((memblock_end_of_DRAM() - 1) > 0xffffffff) { - ppc_swiotlb_enable = 1; - set_pci_dma_ops(&swiotlb_dma_ops); - ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb; - } -#endif + swiotlb_detect_4g(); + ppc47x_smp_init(); } diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c index 6d3265fe7718..56f8c8f674df 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c @@ -159,6 +159,7 @@ static void __init mpc85xx_ds_setup_arch(void) if (ppc_md.progress) ppc_md.progress("mpc85xx_ds_setup_arch()", 0); + swiotlb_detect_4g(); mpc85xx_ds_pci_init(); mpc85xx_smp_init(); diff --git a/arch/powerpc/platforms/85xx/qemu_e500.c b/arch/powerpc/platforms/85xx/qemu_e500.c index 95a2e53af71b..3c5490c8423f 100644 --- a/arch/powerpc/platforms/85xx/qemu_e500.c +++ b/arch/powerpc/platforms/85xx/qemu_e500.c @@ -42,6 +42,7 @@ static void __init qemu_e500_setup_arch(void) ppc_md.progress("qemu_e500_setup_arch()", 0); fsl_pci_init(); + swiotlb_detect_4g(); mpc85xx_smp_init(); } diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index 6938792ccfd9..da7a3d7f54cc 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -872,11 +872,8 @@ void __devinit fsl_pci_init(void) * we need SWIOTLB to handle buffers located outside of * dma capable memory region */ - if (memblock_end_of_DRAM() - 1 > max) { + if (memblock_end_of_DRAM() - 1 > max) ppc_swiotlb_enable = 1; - set_pci_dma_ops(&swiotlb_dma_ops); - ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb; - } #endif } #endif -- cgit v1.3-14-g43fede From b92a66a65cb4480774066d9a3080c77eb34b7232 Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Mon, 10 Sep 2012 00:35:26 +0000 Subject: powerpc: Add denormalisation exception handling for POWER6/7 On POWER6 and POWER7 if the input operand to an instruction is a denormalised single precision binary floating point value we can take a denormalisation exception where it's expected that the hypervisor (HV=1) will fix up the inputs before the instruction is run. This adds code to handle this denormalisation exception for POWER6 and POWER7. It also add a CONFIG_PPC_DENORMALISATION option and sets it in pseries/ppc64_defconfig. This is useful on bare metal systems only. Based on patch from Milton Miller. Signed-off-by: Michael Neuling Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/Kconfig | 8 +++ arch/powerpc/configs/ppc64_defconfig | 1 + arch/powerpc/configs/pseries_defconfig | 1 + arch/powerpc/include/asm/ppc-opcode.h | 3 + arch/powerpc/include/asm/reg.h | 1 + arch/powerpc/kernel/exceptions-64s.S | 123 +++++++++++++++++++++++++++++++++ 6 files changed, 137 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 98e513b62709..748ccaa3b4b3 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -560,6 +560,14 @@ config SCHED_SMT when dealing with POWER5 cpus at a cost of slightly increased overhead in some places. If unsure say N here. +config PPC_DENORMALISATION + bool "PowerPC denormalisation exception handling" + depends on PPC_BOOK3S_64 + default "n" + ---help--- + Add support for handling denormalisation of single precision + values. Useful for bare metal only. If unsure say Y here. + config CMDLINE_BOOL bool "Default bootloader kernel arguments" diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index db27c82e0542..e263e6a5aca1 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -51,6 +51,7 @@ CONFIG_KEXEC=y CONFIG_IRQ_ALL_CPUS=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_SCHED_SMT=y +CONFIG_PPC_DENORMALISATION=y CONFIG_PCCARD=y CONFIG_ELECTRA_CF=y CONFIG_HOTPLUG_PCI=m diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index 1f65b3c9b59a..c169dfb3e42d 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -48,6 +48,7 @@ CONFIG_MEMORY_HOTREMOVE=y CONFIG_PPC_64K_PAGES=y CONFIG_PPC_SUBPAGE_PROT=y CONFIG_SCHED_SMT=y +CONFIG_PPC_DENORMALISATION=y CONFIG_HOTPLUG_PCI=m CONFIG_HOTPLUG_PCI_RPA=m CONFIG_HOTPLUG_PCI_RPA_DLPAR=m diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 4c25319f2fbc..5f73ce63fcae 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -126,6 +126,7 @@ #define PPC_INST_TLBIVAX 0x7c000624 #define PPC_INST_TLBSRX_DOT 0x7c0006a5 #define PPC_INST_XXLOR 0xf0000510 +#define PPC_INST_XVCPSGNDP 0xf0000780 #define PPC_INST_NAP 0x4c000364 #define PPC_INST_SLEEP 0x4c0003a4 @@ -277,6 +278,8 @@ VSX_XX1((s), a, b)) #define XXLOR(t, a, b) stringify_in_c(.long PPC_INST_XXLOR | \ VSX_XX3((t), a, b)) +#define XVCPSGNDP(t, a, b) stringify_in_c(.long (PPC_INST_XVCPSGNDP | \ + VSX_XX3((t), (a), (b)))) #define PPC_NAP stringify_in_c(.long PPC_INST_NAP) #define PPC_SLEEP stringify_in_c(.long PPC_INST_SLEEP) diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 121a90bbf778..a1096fb62816 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -524,6 +524,7 @@ #define SPRN_HSRR0 0x13A /* Save/Restore Register 0 */ #define SPRN_HSRR1 0x13B /* Save/Restore Register 1 */ +#define HSRR1_DENORM 0x00100000 /* Denorm exception */ #define SPRN_TBCTL 0x35f /* PA6T Timebase control register */ #define TBCTL_FREEZE 0x0000000000000000ull /* Freeze all tbs */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 39aa97d3ff88..5eb00569199f 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -275,6 +275,31 @@ vsx_unavailable_pSeries_1: STD_EXCEPTION_PSERIES(0x1300, 0x1300, instruction_breakpoint) KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_STD, 0x1300) + . = 0x1500 + .global denorm_Hypervisor +denorm_exception_hv: + HMT_MEDIUM + mtspr SPRN_SPRG_HSCRATCH0,r13 + mfspr r13,SPRN_SPRG_HPACA + std r9,PACA_EXGEN+EX_R9(r13) + std r10,PACA_EXGEN+EX_R10(r13) + std r11,PACA_EXGEN+EX_R11(r13) + std r12,PACA_EXGEN+EX_R12(r13) + mfspr r9,SPRN_SPRG_HSCRATCH0 + std r9,PACA_EXGEN+EX_R13(r13) + mfcr r9 + +#ifdef CONFIG_PPC_DENORMALISATION + mfspr r10,SPRN_HSRR1 + mfspr r11,SPRN_HSRR0 /* save HSRR0 */ + andis. r10,r10,(HSRR1_DENORM)@h /* denorm? */ + addi r11,r11,-4 /* HSRR0 is next instruction */ + bne+ denorm_assist +#endif + + EXCEPTION_PROLOG_PSERIES_1(denorm_common, EXC_HV) + KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x1500) + #ifdef CONFIG_CBE_RAS STD_EXCEPTION_HV(0x1600, 0x1602, cbe_maintenance) KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1602) @@ -336,6 +361,103 @@ do_stab_bolted_pSeries: KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x900) KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x982) +#ifdef CONFIG_PPC_DENORMALISATION +denorm_assist: +BEGIN_FTR_SECTION +/* + * To denormalise we need to move a copy of the register to itself. + * For POWER6 do that here for all FP regs. + */ + mfmsr r10 + ori r10,r10,(MSR_FP|MSR_FE0|MSR_FE1) + xori r10,r10,(MSR_FE0|MSR_FE1) + mtmsrd r10 + sync + fmr 0,0 + fmr 1,1 + fmr 2,2 + fmr 3,3 + fmr 4,4 + fmr 5,5 + fmr 6,6 + fmr 7,7 + fmr 8,8 + fmr 9,9 + fmr 10,10 + fmr 11,11 + fmr 12,12 + fmr 13,13 + fmr 14,14 + fmr 15,15 + fmr 16,16 + fmr 17,17 + fmr 18,18 + fmr 19,19 + fmr 20,20 + fmr 21,21 + fmr 22,22 + fmr 23,23 + fmr 24,24 + fmr 25,25 + fmr 26,26 + fmr 27,27 + fmr 28,28 + fmr 29,29 + fmr 30,30 + fmr 31,31 +FTR_SECTION_ELSE +/* + * To denormalise we need to move a copy of the register to itself. + * For POWER7 do that here for the first 32 VSX registers only. + */ + mfmsr r10 + oris r10,r10,MSR_VSX@h + mtmsrd r10 + sync + XVCPSGNDP(0,0,0) + XVCPSGNDP(1,1,1) + XVCPSGNDP(2,2,2) + XVCPSGNDP(3,3,3) + XVCPSGNDP(4,4,4) + XVCPSGNDP(5,5,5) + XVCPSGNDP(6,6,6) + XVCPSGNDP(7,7,7) + XVCPSGNDP(8,8,8) + XVCPSGNDP(9,9,9) + XVCPSGNDP(10,10,10) + XVCPSGNDP(11,11,11) + XVCPSGNDP(12,12,12) + XVCPSGNDP(13,13,13) + XVCPSGNDP(14,14,14) + XVCPSGNDP(15,15,15) + XVCPSGNDP(16,16,16) + XVCPSGNDP(17,17,17) + XVCPSGNDP(18,18,18) + XVCPSGNDP(19,19,19) + XVCPSGNDP(20,20,20) + XVCPSGNDP(21,21,21) + XVCPSGNDP(22,22,22) + XVCPSGNDP(23,23,23) + XVCPSGNDP(24,24,24) + XVCPSGNDP(25,25,25) + XVCPSGNDP(26,26,26) + XVCPSGNDP(27,27,27) + XVCPSGNDP(28,28,28) + XVCPSGNDP(29,29,29) + XVCPSGNDP(30,30,30) + XVCPSGNDP(31,31,31) +ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_206) + mtspr SPRN_HSRR0,r11 + mtcrf 0x80,r9 + ld r9,PACA_EXGEN+EX_R9(r13) + ld r10,PACA_EXGEN+EX_R10(r13) + ld r11,PACA_EXGEN+EX_R11(r13) + ld r12,PACA_EXGEN+EX_R12(r13) + ld r13,PACA_EXGEN+EX_R13(r13) + HRFID + b . +#endif + .align 7 /* moved from 0xe00 */ STD_EXCEPTION_HV(., 0xe02, h_data_storage) @@ -495,6 +617,7 @@ machine_check_common: STD_EXCEPTION_COMMON(0xe60, hmi_exception, .unknown_exception) STD_EXCEPTION_COMMON_ASYNC(0xf00, performance_monitor, .performance_monitor_exception) STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, .instruction_breakpoint_exception) + STD_EXCEPTION_COMMON(0x1502, denorm, .unknown_exception) #ifdef CONFIG_ALTIVEC STD_EXCEPTION_COMMON(0x1700, altivec_assist, .altivec_assist_exception) #else -- cgit v1.3-14-g43fede From 048ee0993ec8360abb0b51bdf8f8721e9ed62ec4 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 10 Sep 2012 02:52:55 +0000 Subject: powerpc/mm: Add 64TB support Increase max addressable range to 64TB. This is not tested on real hardware yet. Reviewed-by: Paul Mackerras Signed-off-by: Aneesh Kumar K.V Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/mmu-hash64.h | 42 ++++++++++++++++++++++------ arch/powerpc/include/asm/pgtable-ppc64-4k.h | 2 +- arch/powerpc/include/asm/pgtable-ppc64-64k.h | 2 +- arch/powerpc/include/asm/processor.h | 4 +-- arch/powerpc/include/asm/sparsemem.h | 4 +-- arch/powerpc/kernel/exceptions-64s.S | 4 ++- arch/powerpc/mm/slb_low.S | 12 ++++++++ 7 files changed, 54 insertions(+), 16 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h index 7cbd541f915f..23730ee65aa0 100644 --- a/arch/powerpc/include/asm/mmu-hash64.h +++ b/arch/powerpc/include/asm/mmu-hash64.h @@ -370,17 +370,21 @@ extern void slb_set_size(u16 size); * (head.S) and ASM_VSID_SCRAMBLE (below) are changed accordingly. */ -#define VSID_MULTIPLIER_256M ASM_CONST(200730139) /* 28-bit prime */ -#define VSID_BITS_256M 36 +/* + * This should be computed such that protovosid * vsid_mulitplier + * doesn't overflow 64 bits. It should also be co-prime to vsid_modulus + */ +#define VSID_MULTIPLIER_256M ASM_CONST(12538073) /* 24-bit prime */ +#define VSID_BITS_256M 38 #define VSID_MODULUS_256M ((1UL<= PAGE_OFFSET */ +/* + * This is only valid for addresses >= PAGE_OFFSET + * The proto-VSID space is divided into two class + * User: 0 to 2^(CONTEXT_BITS + USER_ESID_BITS) -1 + * kernel: 2^(CONTEXT_BITS + USER_ESID_BITS) to 2^(VSID_BITS) - 1 + * + * With KERNEL_START at 0xc000000000000000, the proto vsid for + * the kernel ends up with 0xc00000000 (36 bits). With 64TB + * support we need to have kernel proto-VSID in the + * [2^37 to 2^38 - 1] range due to the increased USER_ESID_BITS. + */ static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize) { - if (ssize == MMU_SEGSIZE_256M) - return vsid_scramble(ea >> SID_SHIFT, 256M); - return vsid_scramble(ea >> SID_SHIFT_1T, 1T); + unsigned long proto_vsid; + /* + * We need to make sure proto_vsid for the kernel is + * >= 2^(CONTEXT_BITS + USER_ESID_BITS[_1T]) + */ + if (ssize == MMU_SEGSIZE_256M) { + proto_vsid = ea >> SID_SHIFT; + proto_vsid |= (1UL << (CONTEXT_BITS + USER_ESID_BITS)); + return vsid_scramble(proto_vsid, 256M); + } + proto_vsid = ea >> SID_SHIFT_1T; + proto_vsid |= (1UL << (CONTEXT_BITS + USER_ESID_BITS_1T)); + return vsid_scramble(proto_vsid, 1T); } /* Returns the segment size indicator for a user address */ diff --git a/arch/powerpc/include/asm/pgtable-ppc64-4k.h b/arch/powerpc/include/asm/pgtable-ppc64-4k.h index d6489a2c64c8..12798c9d4b4b 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64-4k.h +++ b/arch/powerpc/include/asm/pgtable-ppc64-4k.h @@ -7,7 +7,7 @@ */ #define PTE_INDEX_SIZE 9 #define PMD_INDEX_SIZE 7 -#define PUD_INDEX_SIZE 7 +#define PUD_INDEX_SIZE 9 #define PGD_INDEX_SIZE 9 #ifndef __ASSEMBLY__ diff --git a/arch/powerpc/include/asm/pgtable-ppc64-64k.h b/arch/powerpc/include/asm/pgtable-ppc64-64k.h index 90533ddcd703..be4e2878fbc0 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64-64k.h +++ b/arch/powerpc/include/asm/pgtable-ppc64-64k.h @@ -7,7 +7,7 @@ #define PTE_INDEX_SIZE 12 #define PMD_INDEX_SIZE 12 #define PUD_INDEX_SIZE 0 -#define PGD_INDEX_SIZE 4 +#define PGD_INDEX_SIZE 6 #ifndef __ASSEMBLY__ #define PTE_TABLE_SIZE (sizeof(real_pte_t) << PTE_INDEX_SIZE) diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 83efc6e81543..9dc5cd1fde1a 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -97,8 +97,8 @@ extern struct task_struct *last_task_used_spe; #endif #ifdef CONFIG_PPC64 -/* 64-bit user address space is 44-bits (16TB user VM) */ -#define TASK_SIZE_USER64 (0x0000100000000000UL) +/* 64-bit user address space is 46-bits (64TB user VM) */ +#define TASK_SIZE_USER64 (0x0000400000000000UL) /* * 32-bit user address space is 4GB - 1 page diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h index 0c5fa3145615..f6fc0ee813d7 100644 --- a/arch/powerpc/include/asm/sparsemem.h +++ b/arch/powerpc/include/asm/sparsemem.h @@ -10,8 +10,8 @@ */ #define SECTION_SIZE_BITS 24 -#define MAX_PHYSADDR_BITS 44 -#define MAX_PHYSMEM_BITS 44 +#define MAX_PHYSADDR_BITS 46 +#define MAX_PHYSMEM_BITS 46 #endif /* CONFIG_SPARSEMEM */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 5eb00569199f..10b658ad65e1 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1083,7 +1083,9 @@ _GLOBAL(do_stab_bolted) rldimi r10,r11,7,52 /* r10 = first ste of the group */ /* Calculate VSID */ - /* This is a kernel address, so protovsid = ESID */ + /* This is a kernel address, so protovsid = ESID | 1 << 37 */ + li r9,0x1 + rldimi r11,r9,(CONTEXT_BITS + USER_ESID_BITS),0 ASM_VSID_SCRAMBLE(r11, r9, 256M) rldic r9,r11,12,16 /* r9 = vsid << 12 */ diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S index f6a262555ef2..1a16ca227757 100644 --- a/arch/powerpc/mm/slb_low.S +++ b/arch/powerpc/mm/slb_low.S @@ -56,6 +56,12 @@ _GLOBAL(slb_allocate_realmode) */ _GLOBAL(slb_miss_kernel_load_linear) li r11,0 + li r9,0x1 + /* + * for 1T we shift 12 bits more. slb_finish_load_1T will do + * the necessary adjustment + */ + rldimi r10,r9,(CONTEXT_BITS + USER_ESID_BITS),0 BEGIN_FTR_SECTION b slb_finish_load END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT) @@ -85,6 +91,12 @@ _GLOBAL(slb_miss_kernel_load_vmemmap) _GLOBAL(slb_miss_kernel_load_io) li r11,0 6: + li r9,0x1 + /* + * for 1T we shift 12 bits more. slb_finish_load_1T will do + * the necessary adjustment + */ + rldimi r10,r9,(CONTEXT_BITS + USER_ESID_BITS),0 BEGIN_FTR_SECTION b slb_finish_load END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT) -- cgit v1.3-14-g43fede From e72bbbab278a2e6d506bd2cf380ba9bef68e8ec1 Mon Sep 17 00:00:00 2001 From: Li Zhong Date: Mon, 10 Sep 2012 15:37:43 +0000 Subject: powerpc/trace: Fix interrupt tracepoints vs. RCU There are a few tracepoints in the interrupt code path, which is before irq_enter(), or after irq_exit(), like trace_irq_entry()/trace_irq_exit() in do_IRQ(), trace_timer_interrupt_entry()/trace_timer_interrupt_exit() in timer_interrupt(). If the interrupt is from idle(), and because tracepoint contains RCU read-side critical section, we could see following suspicious RCU usage reported: [ 145.127743] =============================== [ 145.127747] [ INFO: suspicious RCU usage. ] [ 145.127752] 3.6.0-rc3+ #1 Not tainted [ 145.127755] ------------------------------- [ 145.127759] /root/.workdir/linux/arch/powerpc/include/asm/trace.h:33 suspicious rcu_dereference_check() usage! [ 145.127765] [ 145.127765] other info that might help us debug this: [ 145.127765] [ 145.127771] [ 145.127771] RCU used illegally from idle CPU! [ 145.127771] rcu_scheduler_active = 1, debug_locks = 0 [ 145.127777] RCU used illegally from extended quiescent state! [ 145.127781] no locks held by swapper/0/0. [ 145.127785] [ 145.127785] stack backtrace: [ 145.127789] Call Trace: [ 145.127796] [c00000000108b530] [c000000000013c40] .show_stack +0x70/0x1c0 (unreliable) [ 145.127806] [c00000000108b5e0] [c0000000000f59d8] .lockdep_rcu_suspicious+0x118/0x150 [ 145.127813] [c00000000108b680] [c00000000000fc58] .do_IRQ+0x498/0x500 [ 145.127820] [c00000000108b750] [c000000000003950] hardware_interrupt_common+0x150/0x180 [ 145.127828] --- Exception: 501 at .plpar_hcall_norets+0x84/0xd4 [ 145.127828] LR = .check_and_cede_processor+0x38/0x70 [ 145.127836] [c00000000108bab0] [c0000000000665dc] .shared_cede_loop +0x5c/0x100 [ 145.127844] [c00000000108bb70] [c000000000588ab0] .cpuidle_enter +0x30/0x50 [ 145.127850] [c00000000108bbe0] [c000000000588b0c] .cpuidle_enter_state+0x3c/0xb0 [ 145.127857] [c00000000108bc60] [c000000000589730] .cpuidle_idle_call +0x150/0x6c0 [ 145.127863] [c00000000108bd30] [c000000000058440] .pSeries_idle +0x10/0x40 [ 145.127870] [c00000000108bda0] [c00000000001683c] .cpu_idle +0x18c/0x2d0 [ 145.127876] [c00000000108be60] [c00000000000b434] .rest_init +0x124/0x1b0 [ 145.127884] [c00000000108bef0] [c0000000009d0d28] .start_kernel +0x568/0x588 [ 145.127890] [c00000000108bf90] [c000000000009660] .start_here_common +0x20/0x40 This is because the RCU usage in interrupt context should be used in area marked by rcu_irq_enter()/rcu_irq_exit(), called in irq_enter()/irq_exit() respectively. Move them into the irq_enter()/irq_exit() area to avoid the reporting. Signed-off-by: Li Zhong Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/irq.c | 8 ++++---- arch/powerpc/kernel/time.c | 8 ++++---- 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 1f017bb7a7ce..71413f41278f 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -489,10 +489,10 @@ void do_IRQ(struct pt_regs *regs) struct pt_regs *old_regs = set_irq_regs(regs); unsigned int irq; - trace_irq_entry(regs); - irq_enter(); + trace_irq_entry(regs); + check_stack_overflow(); /* @@ -511,10 +511,10 @@ void do_IRQ(struct pt_regs *regs) else __get_cpu_var(irq_stat).spurious_irqs++; + trace_irq_exit(regs); + irq_exit(); set_irq_regs(old_regs); - - trace_irq_exit(regs); } void __init init_IRQ(void) diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index e49e93191b69..bd693a11d86e 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -493,8 +493,6 @@ void timer_interrupt(struct pt_regs * regs) */ may_hard_irq_enable(); - trace_timer_interrupt_entry(regs); - __get_cpu_var(irq_stat).timer_irqs++; #if defined(CONFIG_PPC32) && defined(CONFIG_PMAC) @@ -505,6 +503,8 @@ void timer_interrupt(struct pt_regs * regs) old_regs = set_irq_regs(regs); irq_enter(); + trace_timer_interrupt_entry(regs); + if (test_irq_work_pending()) { clear_irq_work_pending(); irq_work_run(); @@ -529,10 +529,10 @@ void timer_interrupt(struct pt_regs * regs) } #endif + trace_timer_interrupt_exit(regs); + irq_exit(); set_irq_regs(old_regs); - - trace_timer_interrupt_exit(regs); } /* -- cgit v1.3-14-g43fede From a9c4e541ea9b22944da356f2a9258b4eddcc953b Mon Sep 17 00:00:00 2001 From: Tiejun Chen Date: Sun, 16 Sep 2012 23:54:30 +0000 Subject: powerpc/kprobe: Complete kprobe and migrate exception frame We can't emulate stwu since that may corrupt current exception stack. So we will have to do real store operation in the exception return code. Firstly we'll allocate a trampoline exception frame below the kprobed function stack and copy the current exception frame to the trampoline. Then we can do this real store operation to implement 'stwu', and reroute the trampoline frame to r1 to complete this exception migration. Signed-off-by: Tiejun Chen Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/entry_32.S | 47 ++++++++++++++++++++++++++++++++++++------ arch/powerpc/kernel/entry_64.S | 35 +++++++++++++++++++++++++++++++ 2 files changed, 76 insertions(+), 6 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index ead5016b02d0..af37528da49f 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -831,19 +831,56 @@ restore_user: bnel- load_dbcr0 #endif -#ifdef CONFIG_PREEMPT b restore /* N.B. the only way to get here is from the beq following ret_from_except. */ resume_kernel: - /* check current_thread_info->preempt_count */ + /* check current_thread_info, _TIF_EMULATE_STACK_STORE */ CURRENT_THREAD_INFO(r9, r1) + lwz r8,TI_FLAGS(r9) + andis. r8,r8,_TIF_EMULATE_STACK_STORE@h + beq+ 1f + + addi r8,r1,INT_FRAME_SIZE /* Get the kprobed function entry */ + + lwz r3,GPR1(r1) + subi r3,r3,INT_FRAME_SIZE /* dst: Allocate a trampoline exception frame */ + mr r4,r1 /* src: current exception frame */ + mr r1,r3 /* Reroute the trampoline frame to r1 */ + + /* Copy from the original to the trampoline. */ + li r5,INT_FRAME_SIZE/4 /* size: INT_FRAME_SIZE */ + li r6,0 /* start offset: 0 */ + mtctr r5 +2: lwzx r0,r6,r4 + stwx r0,r6,r3 + addi r6,r6,4 + bdnz 2b + + /* Do real store operation to complete stwu */ + lwz r5,GPR1(r1) + stw r8,0(r5) + + /* Clear _TIF_EMULATE_STACK_STORE flag */ + lis r11,_TIF_EMULATE_STACK_STORE@h + addi r5,r9,TI_FLAGS +0: lwarx r8,0,r5 + andc r8,r8,r11 +#ifdef CONFIG_IBM405_ERR77 + dcbt 0,r5 +#endif + stwcx. r8,0,r5 + bne- 0b +1: + +#ifdef CONFIG_PREEMPT + /* check current_thread_info->preempt_count */ lwz r0,TI_PREEMPT(r9) cmpwi 0,r0,0 /* if non-zero, just restore regs and return */ bne restore - lwz r0,TI_FLAGS(r9) - andi. r0,r0,_TIF_NEED_RESCHED + andi. r8,r8,_TIF_NEED_RESCHED beq+ restore + lwz r3,_MSR(r1) andi. r0,r3,MSR_EE /* interrupts off? */ beq restore /* don't schedule if so */ #ifdef CONFIG_TRACE_IRQFLAGS @@ -864,8 +901,6 @@ resume_kernel: */ bl trace_hardirqs_on #endif -#else -resume_kernel: #endif /* CONFIG_PREEMPT */ /* interrupts are hard-disabled at this point */ diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index b40e0b4815b3..0e931aaffca2 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -593,6 +593,41 @@ _GLOBAL(ret_from_except_lite) b .ret_from_except resume_kernel: + /* check current_thread_info, _TIF_EMULATE_STACK_STORE */ + CURRENT_THREAD_INFO(r9, r1) + ld r8,TI_FLAGS(r9) + andis. r8,r8,_TIF_EMULATE_STACK_STORE@h + beq+ 1f + + addi r8,r1,INT_FRAME_SIZE /* Get the kprobed function entry */ + + lwz r3,GPR1(r1) + subi r3,r3,INT_FRAME_SIZE /* dst: Allocate a trampoline exception frame */ + mr r4,r1 /* src: current exception frame */ + mr r1,r3 /* Reroute the trampoline frame to r1 */ + + /* Copy from the original to the trampoline. */ + li r5,INT_FRAME_SIZE/8 /* size: INT_FRAME_SIZE */ + li r6,0 /* start offset: 0 */ + mtctr r5 +2: ldx r0,r6,r4 + stdx r0,r6,r3 + addi r6,r6,8 + bdnz 2b + + /* Do real store operation to complete stwu */ + lwz r5,GPR1(r1) + std r8,0(r5) + + /* Clear _TIF_EMULATE_STACK_STORE flag */ + lis r11,_TIF_EMULATE_STACK_STORE@h + addi r5,r9,TI_FLAGS + ldarx r4,0,r5 + andc r4,r4,r11 + stdcx. r4,0,r5 + bne- 0b +1: + #ifdef CONFIG_PREEMPT /* Check if we need to preempt */ andi. r0,r4,_TIF_NEED_RESCHED -- cgit v1.3-14-g43fede From e6651de9cc701ab4829b3a11a7ace85a79405d32 Mon Sep 17 00:00:00 2001 From: Zhao Chenhui Date: Fri, 20 Jul 2012 20:47:01 +0800 Subject: powerpc/smp: Do not disable IPI interrupts during suspend During suspend, all interrupts including IPI will be disabled. In this case, the suspend process will hang in SMP. To prevent this, pass the flag IRQF_NO_SUSPEND when requesting IPI irq. Signed-off-by: Zhao Chenhui Signed-off-by: Li Yang Acked-by: Benjamin Herrenschmidt Signed-off-by: Kumar Gala --- arch/powerpc/kernel/smp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index a51ed205016e..2b952b5386fd 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -171,7 +171,7 @@ int smp_request_message_ipi(int virq, int msg) } #endif err = request_irq(virq, smp_ipi_action[msg], - IRQF_PERCPU | IRQF_NO_THREAD, + IRQF_PERCPU | IRQF_NO_THREAD | IRQF_NO_SUSPEND, smp_ipi_name[msg], 0); WARN(err < 0, "unable to request_irq %d for %s (rc %d)\n", virq, smp_ipi_name[msg], err); -- cgit v1.3-14-g43fede From 189374aed657e2228ad6b39ece438c9cdafc8dae Mon Sep 17 00:00:00 2001 From: John Stultz Date: Tue, 4 Sep 2012 15:27:48 -0400 Subject: time: Move update_vsyscall definitions to timekeeper_internal.h Since users will need to include timekeeper_internal.h, move update_vsyscall definitions to timekeeper_internal.h. Cc: Tony Luck Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Cc: Andy Lutomirski Cc: Martin Schwidefsky Cc: Paul Turner Cc: Steven Rostedt Cc: Richard Cochran Cc: Prarit Bhargava Cc: Thomas Gleixner Signed-off-by: John Stultz --- arch/ia64/kernel/time.c | 2 +- arch/powerpc/kernel/time.c | 2 +- arch/s390/kernel/time.c | 2 +- arch/x86/kernel/vsyscall_64.c | 2 +- include/linux/clocksource.h | 16 ---------------- include/linux/timekeeper_internal.h | 17 +++++++++++++++++ kernel/time.c | 2 +- 7 files changed, 22 insertions(+), 21 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index ecc904b33c5f..acb688fe2354 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index e49e93191b69..613a830d9d50 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -73,7 +73,7 @@ /* powerpc clocksource/clockevent code */ #include -#include +#include static cycle_t rtc_read(struct clocksource *); static struct clocksource clocksource_rtc = { diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index dcec960fc724..bfb62ad312a6 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -34,7 +34,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 8d141b309046..6ec8411a4710 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -28,7 +28,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index fbe89e17124e..4dceaf8ae152 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -319,22 +319,6 @@ static inline void __clocksource_updatefreq_khz(struct clocksource *cs, u32 khz) __clocksource_updatefreq_scale(cs, 1000, khz); } -#ifdef CONFIG_GENERIC_TIME_VSYSCALL -extern void -update_vsyscall(struct timespec *ts, struct timespec *wtm, - struct clocksource *c, u32 mult); -extern void update_vsyscall_tz(void); -#else -static inline void -update_vsyscall(struct timespec *ts, struct timespec *wtm, - struct clocksource *c, u32 mult) -{ -} - -static inline void update_vsyscall_tz(void) -{ -} -#endif extern void timekeeping_notify(struct clocksource *clock); diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 8ba43fa8c7e6..9c1c2cf413a6 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -65,4 +65,21 @@ struct timekeeper { /* Seqlock for all timekeeper values */ seqlock_t lock; }; + + +#ifdef CONFIG_GENERIC_TIME_VSYSCALL +extern void +update_vsyscall(struct timespec *ts, struct timespec *wtm, + struct clocksource *c, u32 mult); +extern void update_vsyscall_tz(void); +#else +static inline void update_vsyscall(struct timespec *ts, struct timespec *wtm, + struct clocksource *c, u32 mult) +{ +} +static inline void update_vsyscall_tz(void) +{ +} +#endif + #endif /* _LINUX_TIMEKEEPER_INTERNAL_H */ diff --git a/kernel/time.c b/kernel/time.c index ba744cf80696..d226c6a3fd28 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -30,7 +30,7 @@ #include #include #include -#include +#include #include #include #include -- cgit v1.3-14-g43fede From 706394211648117762edfaeffd6fc04bf3b1a75d Mon Sep 17 00:00:00 2001 From: John Stultz Date: Tue, 4 Sep 2012 15:34:21 -0400 Subject: time: Convert CONFIG_GENERIC_TIME_VSYSCALL to CONFIG_GENERIC_TIME_VSYSCALL_OLD To help migrate archtectures over to the new update_vsyscall method, redfine CONFIG_GENERIC_TIME_VSYSCALL as CONFIG_GENERIC_TIME_VSYSCALL_OLD Cc: Tony Luck Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Cc: Andy Lutomirski Cc: Martin Schwidefsky Cc: Paul Turner Cc: Steven Rostedt Cc: Richard Cochran Cc: Prarit Bhargava Cc: Thomas Gleixner Signed-off-by: John Stultz --- arch/ia64/Kconfig | 2 +- arch/ia64/kernel/time.c | 2 +- arch/powerpc/Kconfig | 2 +- arch/powerpc/kernel/time.c | 2 +- arch/s390/Kconfig | 2 +- arch/s390/kernel/time.c | 2 +- arch/x86/Kconfig | 2 +- arch/x86/kernel/vsyscall_64.c | 2 +- include/linux/timekeeper_internal.h | 7 ++++--- kernel/time/Kconfig | 2 +- kernel/time/timekeeping.c | 2 +- 11 files changed, 14 insertions(+), 13 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 310cf5781fad..f9e673c252a7 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -38,7 +38,7 @@ config IA64 select ARCH_TASK_STRUCT_ALLOCATOR select ARCH_THREAD_INFO_ALLOCATOR select ARCH_CLOCKSOURCE_DATA - select GENERIC_TIME_VSYSCALL + select GENERIC_TIME_VSYSCALL_OLD default y help The Itanium Processor Family is Intel's 64-bit successor to diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index acb688fe2354..d2f4e260db40 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -454,7 +454,7 @@ void update_vsyscall_tz(void) { } -void update_vsyscall(struct timespec *wall, struct timespec *wtm, +void update_vsyscall_old(struct timespec *wall, struct timespec *wtm, struct clocksource *c, u32 mult) { write_seqcount_begin(&fsyscall_gtod_data.seq); diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 352f416269ce..0881660c9efa 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -135,7 +135,7 @@ config PPC select ARCH_HAVE_NMI_SAFE_CMPXCHG select GENERIC_SMP_IDLE_THREAD select GENERIC_CMOS_UPDATE - select GENERIC_TIME_VSYSCALL + select GENERIC_TIME_VSYSCALL_OLD select GENERIC_CLOCKEVENTS select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 613a830d9d50..c825809b92e7 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -712,7 +712,7 @@ static cycle_t timebase_read(struct clocksource *cs) return (cycle_t)get_tb(); } -void update_vsyscall(struct timespec *wall_time, struct timespec *wtm, +void update_vsyscall_old(struct timespec *wall_time, struct timespec *wtm, struct clocksource *clock, u32 mult) { u64 new_tb_to_xs, new_stamp_xsec; diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 107610e01a29..ba488aa500de 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -121,7 +121,7 @@ config S390 select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE select ARCH_WANT_IPC_PARSE_VERSION select GENERIC_SMP_IDLE_THREAD - select GENERIC_TIME_VSYSCALL + select GENERIC_TIME_VSYSCALL_OLD select GENERIC_CLOCKEVENTS select KTIME_SCALAR if 32BIT select HAVE_ARCH_SECCOMP_FILTER diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index bfb62ad312a6..c5430bf5b5e6 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -219,7 +219,7 @@ struct clocksource * __init clocksource_default_clock(void) return &clocksource_tod; } -void update_vsyscall(struct timespec *wall_time, struct timespec *wtm, +void update_vsyscall_old(struct timespec *wall_time, struct timespec *wtm, struct clocksource *clock, u32 mult) { if (clock != &clocksource_tod) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 8ec3a1aa4abd..e3f3c1a5a744 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -93,7 +93,7 @@ config X86 select GENERIC_CLOCKEVENTS select ARCH_CLOCKSOURCE_DATA if X86_64 select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC) - select GENERIC_TIME_VSYSCALL if X86_64 + select GENERIC_TIME_VSYSCALL_OLD if X86_64 select KTIME_SCALAR if X86_32 select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 6ec8411a4710..77dde2953c64 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -82,7 +82,7 @@ void update_vsyscall_tz(void) vsyscall_gtod_data.sys_tz = sys_tz; } -void update_vsyscall(struct timespec *wall_time, struct timespec *wtm, +void update_vsyscall_old(struct timespec *wall_time, struct timespec *wtm, struct clocksource *clock, u32 mult) { struct timespec monotonic; diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 9c1c2cf413a6..a904d76a5faa 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -67,13 +67,14 @@ struct timekeeper { }; -#ifdef CONFIG_GENERIC_TIME_VSYSCALL +#ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD extern void -update_vsyscall(struct timespec *ts, struct timespec *wtm, +update_vsyscall_old(struct timespec *ts, struct timespec *wtm, struct clocksource *c, u32 mult); extern void update_vsyscall_tz(void); #else -static inline void update_vsyscall(struct timespec *ts, struct timespec *wtm, +static inline void +update_vsyscall_old(struct timespec *ts, struct timespec *wtm, struct clocksource *c, u32 mult) { } diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index fd42bd452b75..489c86154d1f 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -13,7 +13,7 @@ config ARCH_CLOCKSOURCE_DATA bool # Timekeeping vsyscall support -config GENERIC_TIME_VSYSCALL +config GENERIC_TIME_VSYSCALL_OLD bool # ktime_t scalar 64bit nsec representation diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 02c19d3d8e0d..7c2851384c46 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -199,7 +199,7 @@ static void timekeeping_update(struct timekeeper *tk, bool clearntp) ntp_clear(); } xt = tk_xtime(tk); - update_vsyscall(&xt, &tk->wall_to_monotonic, tk->clock, tk->mult); + update_vsyscall_old(&xt, &tk->wall_to_monotonic, tk->clock, tk->mult); } /** -- cgit v1.3-14-g43fede From bf9fae9f5e4ca8dce4708812f9ad6281e61df109 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 8 Sep 2012 15:23:11 +0200 Subject: cputime: Use a proper subsystem naming for vtime related APIs Use a naming based on vtime as a prefix for virtual based cputime accounting APIs: - account_system_vtime() -> vtime_account() - account_switch_vtime() -> vtime_task_switch() It makes it easier to allow for further declension such as vtime_account_system(), vtime_account_idle(), ... if we want to find out the context we account to from generic code. This also make it better to know on which subsystem these APIs refer to. Signed-off-by: Frederic Weisbecker Cc: Tony Luck Cc: Fenghua Yu Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Heiko Carstens Cc: Martin Schwidefsky Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra --- arch/ia64/kernel/time.c | 6 +++--- arch/powerpc/kernel/time.c | 10 +++++----- arch/s390/kernel/vtime.c | 6 +++--- include/linux/hardirq.h | 8 ++++---- include/linux/kernel_stat.h | 4 ++-- include/linux/kvm_host.h | 4 ++-- kernel/sched/core.c | 2 +- kernel/sched/cputime.c | 8 ++++---- kernel/softirq.c | 6 +++--- 9 files changed, 27 insertions(+), 27 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index 6247197b9877..16bb6eda879d 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -88,7 +88,7 @@ extern cputime_t cycle_to_cputime(u64 cyc); * accumulated times to the current process, and to prepare accounting on * the next process. */ -void account_switch_vtime(struct task_struct *prev) +void vtime_task_switch(struct task_struct *prev) { struct thread_info *pi = task_thread_info(prev); struct thread_info *ni = task_thread_info(current); @@ -116,7 +116,7 @@ void account_switch_vtime(struct task_struct *prev) * Account time for a transition between system, hard irq or soft irq state. * Note that this function is called with interrupts enabled. */ -void account_system_vtime(struct task_struct *tsk) +void vtime_account(struct task_struct *tsk) { struct thread_info *ti = task_thread_info(tsk); unsigned long flags; @@ -138,7 +138,7 @@ void account_system_vtime(struct task_struct *tsk) local_irq_restore(flags); } -EXPORT_SYMBOL_GPL(account_system_vtime); +EXPORT_SYMBOL_GPL(vtime_account); /* * Called from the timer interrupt handler to charge accumulated user time diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 49da7f06e643..39899d7ebda0 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -291,7 +291,7 @@ static inline u64 calculate_stolen_time(u64 stop_tb) * Account time for a transition between system, hard irq * or soft irq state. */ -void account_system_vtime(struct task_struct *tsk) +void vtime_account(struct task_struct *tsk) { u64 now, nowscaled, delta, deltascaled; unsigned long flags; @@ -343,14 +343,14 @@ void account_system_vtime(struct task_struct *tsk) } local_irq_restore(flags); } -EXPORT_SYMBOL_GPL(account_system_vtime); +EXPORT_SYMBOL_GPL(vtime_account); /* * Transfer the user and system times accumulated in the paca * by the exception entry and exit code to the generic process * user and system time records. * Must be called with interrupts disabled. - * Assumes that account_system_vtime() has been called recently + * Assumes that vtime_account() has been called recently * (i.e. since the last entry from usermode) so that * get_paca()->user_time_scaled is up to date. */ @@ -366,9 +366,9 @@ void account_process_tick(struct task_struct *tsk, int user_tick) account_user_time(tsk, utime, utimescaled); } -void account_switch_vtime(struct task_struct *prev) +void vtime_task_switch(struct task_struct *prev) { - account_system_vtime(prev); + vtime_account(prev); account_process_tick(prev, 0); } diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index 449ac22cc71b..cb5093c26d16 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -99,7 +99,7 @@ static int do_account_vtime(struct task_struct *tsk, int hardirq_offset) return virt_timer_forward(user + system); } -void account_switch_vtime(struct task_struct *prev) +void vtime_task_switch(struct task_struct *prev) { struct thread_info *ti; @@ -122,7 +122,7 @@ void account_process_tick(struct task_struct *tsk, int user_tick) * Update process times based on virtual cpu times stored by entry.S * to the lowcore fields user_timer, system_timer & steal_clock. */ -void account_system_vtime(struct task_struct *tsk) +void vtime_account(struct task_struct *tsk) { struct thread_info *ti = task_thread_info(tsk); u64 timer, system; @@ -138,7 +138,7 @@ void account_system_vtime(struct task_struct *tsk) virt_timer_forward(system); } -EXPORT_SYMBOL_GPL(account_system_vtime); +EXPORT_SYMBOL_GPL(vtime_account); void __kprobes vtime_stop_cpu(void) { diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 305f23cd7cff..cab3da3d0949 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -132,11 +132,11 @@ extern void synchronize_irq(unsigned int irq); struct task_struct; #if !defined(CONFIG_VIRT_CPU_ACCOUNTING) && !defined(CONFIG_IRQ_TIME_ACCOUNTING) -static inline void account_system_vtime(struct task_struct *tsk) +static inline void vtime_account(struct task_struct *tsk) { } #else -extern void account_system_vtime(struct task_struct *tsk); +extern void vtime_account(struct task_struct *tsk); #endif #if defined(CONFIG_TINY_RCU) || defined(CONFIG_TINY_PREEMPT_RCU) @@ -162,7 +162,7 @@ extern void rcu_nmi_exit(void); */ #define __irq_enter() \ do { \ - account_system_vtime(current); \ + vtime_account(current); \ add_preempt_count(HARDIRQ_OFFSET); \ trace_hardirq_enter(); \ } while (0) @@ -178,7 +178,7 @@ extern void irq_enter(void); #define __irq_exit() \ do { \ trace_hardirq_exit(); \ - account_system_vtime(current); \ + vtime_account(current); \ sub_preempt_count(HARDIRQ_OFFSET); \ } while (0) diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index bbe5d15d6597..ca0944b92f4a 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -131,9 +131,9 @@ extern void account_steal_ticks(unsigned long ticks); extern void account_idle_ticks(unsigned long ticks); #ifdef CONFIG_VIRT_CPU_ACCOUNTING -extern void account_switch_vtime(struct task_struct *prev); +extern void vtime_task_switch(struct task_struct *prev); #else -static inline void account_switch_vtime(struct task_struct *prev) { } +static inline void vtime_task_switch(struct task_struct *prev) { } #endif #endif /* _LINUX_KERNEL_STAT_H */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index b70b48b01098..8a59e0abe5fa 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -685,7 +685,7 @@ static inline int kvm_deassign_device(struct kvm *kvm, static inline void kvm_guest_enter(void) { BUG_ON(preemptible()); - account_system_vtime(current); + vtime_account(current); current->flags |= PF_VCPU; /* KVM does not hold any references to rcu protected data when it * switches CPU into a guest mode. In fact switching to a guest mode @@ -699,7 +699,7 @@ static inline void kvm_guest_enter(void) static inline void kvm_guest_exit(void) { - account_system_vtime(current); + vtime_account(current); current->flags &= ~PF_VCPU; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index ba144b121f3d..21e4dcff18f3 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1764,7 +1764,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) * Manfred Spraul */ prev_state = prev->state; - account_switch_vtime(prev); + vtime_task_switch(prev); finish_arch_switch(prev); perf_event_task_sched_in(prev, current); finish_lock_switch(rq, prev); diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 372692bd5376..53f5b12f2821 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -10,11 +10,11 @@ /* * There are no locks covering percpu hardirq/softirq time. - * They are only modified in account_system_vtime, on corresponding CPU + * They are only modified in vtime_account, on corresponding CPU * with interrupts disabled. So, writes are safe. * They are read and saved off onto struct rq in update_rq_clock(). * This may result in other CPU reading this CPU's irq time and can - * race with irq/account_system_vtime on this CPU. We would either get old + * race with irq/vtime_account on this CPU. We would either get old * or new value with a side effect of accounting a slice of irq time to wrong * task when irq is in progress while we read rq->clock. That is a worthy * compromise in place of having locks on each irq in account_system_time. @@ -43,7 +43,7 @@ DEFINE_PER_CPU(seqcount_t, irq_time_seq); * Called before incrementing preempt_count on {soft,}irq_enter * and before decrementing preempt_count on {soft,}irq_exit. */ -void account_system_vtime(struct task_struct *curr) +void vtime_account(struct task_struct *curr) { unsigned long flags; s64 delta; @@ -73,7 +73,7 @@ void account_system_vtime(struct task_struct *curr) irq_time_write_end(); local_irq_restore(flags); } -EXPORT_SYMBOL_GPL(account_system_vtime); +EXPORT_SYMBOL_GPL(vtime_account); static int irqtime_account_hi_update(void) { diff --git a/kernel/softirq.c b/kernel/softirq.c index b73e681df09e..d55e3159f928 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -220,7 +220,7 @@ asmlinkage void __do_softirq(void) current->flags &= ~PF_MEMALLOC; pending = local_softirq_pending(); - account_system_vtime(current); + vtime_account(current); __local_bh_disable((unsigned long)__builtin_return_address(0), SOFTIRQ_OFFSET); @@ -271,7 +271,7 @@ restart: lockdep_softirq_exit(); - account_system_vtime(current); + vtime_account(current); __local_bh_enable(SOFTIRQ_OFFSET); tsk_restore_flags(current, old_flags, PF_MEMALLOC); } @@ -340,7 +340,7 @@ static inline void invoke_softirq(void) */ void irq_exit(void) { - account_system_vtime(current); + vtime_account(current); trace_hardirq_exit(); sub_preempt_count(IRQ_EXIT_OFFSET); if (!in_interrupt() && local_softirq_pending()) -- cgit v1.3-14-g43fede From a7e1a9e3af71b45ecae2dae35851f238117b317d Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 8 Sep 2012 16:14:02 +0200 Subject: vtime: Consolidate system/idle context detection Move the code that finds out to which context we account the cputime into generic layer. Archs that consider the whole time spent in the idle task as idle time (ia64, powerpc) can rely on the generic vtime_account() and implement vtime_account_system() and vtime_account_idle(), letting the generic code to decide when to call which API. Archs that have their own meaning of idle time, such as s390 that only considers the time spent in CPU low power mode as idle time, can just override vtime_account(). Signed-off-by: Frederic Weisbecker Cc: Tony Luck Cc: Fenghua Yu Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra --- arch/ia64/kernel/time.c | 25 ++++++++++++---------- arch/powerpc/kernel/time.c | 47 ++++++++++++++++++++++++----------------- arch/s390/include/asm/cputime.h | 3 +++ include/linux/kernel_stat.h | 2 ++ kernel/sched/cputime.c | 26 +++++++++++++++++++++++ 5 files changed, 73 insertions(+), 30 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index 16bb6eda879d..01cd43e491cd 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -116,29 +116,32 @@ void vtime_task_switch(struct task_struct *prev) * Account time for a transition between system, hard irq or soft irq state. * Note that this function is called with interrupts enabled. */ -void vtime_account(struct task_struct *tsk) +static cputime_t vtime_delta(struct task_struct *tsk) { struct thread_info *ti = task_thread_info(tsk); - unsigned long flags; cputime_t delta_stime; __u64 now; - local_irq_save(flags); - now = ia64_get_itc(); delta_stime = cycle_to_cputime(ti->ac_stime + (now - ti->ac_stamp)); - if (irq_count() || idle_task(smp_processor_id()) != tsk) - account_system_time(tsk, 0, delta_stime, delta_stime); - else - account_idle_time(delta_stime); ti->ac_stime = 0; - ti->ac_stamp = now; - local_irq_restore(flags); + return delta_stime; +} + +void vtime_account_system(struct task_struct *tsk) +{ + cputime_t delta = vtime_delta(tsk); + + account_system_time(tsk, 0, delta, delta); +} + +void vtime_account_idle(struct task_struct *tsk) +{ + account_idle_time(vtime_delta(tsk)); } -EXPORT_SYMBOL_GPL(vtime_account); /* * Called from the timer interrupt handler to charge accumulated user time diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 39899d7ebda0..29b6d3e1ea28 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -291,13 +291,12 @@ static inline u64 calculate_stolen_time(u64 stop_tb) * Account time for a transition between system, hard irq * or soft irq state. */ -void vtime_account(struct task_struct *tsk) +static u64 vtime_delta(struct task_struct *tsk, + u64 *sys_scaled, u64 *stolen) { - u64 now, nowscaled, delta, deltascaled; - unsigned long flags; - u64 stolen, udelta, sys_scaled, user_scaled; + u64 now, nowscaled, deltascaled; + u64 udelta, delta, user_scaled; - local_irq_save(flags); now = mftb(); nowscaled = read_spurr(now); get_paca()->system_time += now - get_paca()->starttime; @@ -305,7 +304,7 @@ void vtime_account(struct task_struct *tsk) deltascaled = nowscaled - get_paca()->startspurr; get_paca()->startspurr = nowscaled; - stolen = calculate_stolen_time(now); + *stolen = calculate_stolen_time(now); delta = get_paca()->system_time; get_paca()->system_time = 0; @@ -322,28 +321,38 @@ void vtime_account(struct task_struct *tsk) * the user ticks get saved up in paca->user_time_scaled to be * used by account_process_tick. */ - sys_scaled = delta; + *sys_scaled = delta; user_scaled = udelta; if (deltascaled != delta + udelta) { if (udelta) { - sys_scaled = deltascaled * delta / (delta + udelta); - user_scaled = deltascaled - sys_scaled; + *sys_scaled = deltascaled * delta / (delta + udelta); + user_scaled = deltascaled - *sys_scaled; } else { - sys_scaled = deltascaled; + *sys_scaled = deltascaled; } } get_paca()->user_time_scaled += user_scaled; - if (in_interrupt() || idle_task(smp_processor_id()) != tsk) { - account_system_time(tsk, 0, delta, sys_scaled); - if (stolen) - account_steal_time(stolen); - } else { - account_idle_time(delta + stolen); - } - local_irq_restore(flags); + return delta; +} + +void vtime_account_system(struct task_struct *tsk) +{ + u64 delta, sys_scaled, stolen; + + delta = vtime_delta(tsk, &sys_scaled, &stolen); + account_system_time(tsk, 0, delta, sys_scaled); + if (stolen) + account_steal_time(stolen); +} + +void vtime_account_idle(struct task_struct *tsk) +{ + u64 delta, sys_scaled, stolen; + + delta = vtime_delta(tsk, &sys_scaled, &stolen); + account_idle_time(delta + stolen); } -EXPORT_SYMBOL_GPL(vtime_account); /* * Transfer the user and system times accumulated in the paca diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h index 8709bdef233c..023d5ae24482 100644 --- a/arch/s390/include/asm/cputime.h +++ b/arch/s390/include/asm/cputime.h @@ -12,6 +12,9 @@ #include #include + +#define __ARCH_HAS_VTIME_ACCOUNT + /* We want to use full resolution of the CPU timer: 2**-12 micro-seconds. */ typedef unsigned long long __nocast cputime_t; diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index ca0944b92f4a..36d12f0884c3 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -132,6 +132,8 @@ extern void account_idle_ticks(unsigned long ticks); #ifdef CONFIG_VIRT_CPU_ACCOUNTING extern void vtime_task_switch(struct task_struct *prev); +extern void vtime_account_system(struct task_struct *tsk); +extern void vtime_account_idle(struct task_struct *tsk); #else static inline void vtime_task_switch(struct task_struct *prev) { } #endif diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 53f5b12f2821..81b763ba58a6 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -432,6 +432,32 @@ void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) *ut = cputime.utime; *st = cputime.stime; } + +/* + * Archs that account the whole time spent in the idle task + * (outside irq) as idle time can rely on this and just implement + * vtime_account_system() and vtime_account_idle(). Archs that + * have other meaning of the idle time (s390 only includes the + * time spent by the CPU when it's in low power mode) must override + * vtime_account(). + */ +#ifndef __ARCH_HAS_VTIME_ACCOUNT +void vtime_account(struct task_struct *tsk) +{ + unsigned long flags; + + local_irq_save(flags); + + if (in_interrupt() || !is_idle_task(tsk)) + vtime_account_system(tsk); + else + vtime_account_idle(tsk); + + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(vtime_account); +#endif /* __ARCH_HAS_VTIME_ACCOUNT */ + #else #ifndef nsecs_to_cputime -- cgit v1.3-14-g43fede From 466921c5a4669f4315528a25f9afd66601ce2c04 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 20 Sep 2012 22:07:58 +0000 Subject: powerpc: Set paca->data_offset = 0 for boot cpu In commit 407821a we assigned a poison value to the paca->data_offset. Unfortunately with CONFIG_LOCK_STAT=y lockdep will read & write to percpu data very early in boot, prior to us initialising the percpu areas, leading to a crash. We have been getting away with this because the data_offset was previously set to zero. This causes lockdep to read & write to the initial copy of the percpu variables, which are discarded later in boot. Although that is "fishy", it does work, and for lock statistics it is no big deal to discard the counts from early boot. So set the paca->data_offset = 0 for the boot cpu paca only. Reported-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman Tested-by: Aneesh Kumar K.V Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/setup_64.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 389bd4f0cdb1..efb6a41b3131 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -208,6 +208,8 @@ void __init early_setup(unsigned long dt_ptr) /* Fix up paca fields required for the boot cpu */ get_paca()->cpu_start = 1; + /* Allow percpu accesses to "work" until we setup percpu data */ + get_paca()->data_offset = 0; /* Probe the machine type */ probe_machine(); -- cgit v1.3-14-g43fede From 58254e1002a82eb383c5977ad9fd5a451b91fe29 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 12 Sep 2012 18:32:42 -0400 Subject: powerpc: split ret_from_fork ... and get rid of in-kernel syscalls in kernel_thread() Signed-off-by: Al Viro --- arch/powerpc/Kconfig | 1 + arch/powerpc/include/asm/processor.h | 3 --- arch/powerpc/kernel/entry_32.S | 11 +++++++++++ arch/powerpc/kernel/entry_64.S | 10 ++++++++++ arch/powerpc/kernel/misc_32.S | 33 --------------------------------- arch/powerpc/kernel/misc_64.S | 34 ---------------------------------- arch/powerpc/kernel/ppc_ksyms.c | 1 - arch/powerpc/kernel/process.c | 34 +++++++++++++++++++++------------- 8 files changed, 43 insertions(+), 84 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 352f416269ce..6e5a0979c085 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -139,6 +139,7 @@ config PPC select GENERIC_CLOCKEVENTS select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER + select GENERIC_KERNEL_THREAD config EARLY_PRINTK bool diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 54b73a28c205..5376453d90cc 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -74,9 +74,6 @@ struct task_struct; void start_thread(struct pt_regs *regs, unsigned long fdptr, unsigned long sp); void release_thread(struct task_struct *); -/* Create a new kernel thread. */ -extern long kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); - /* Lazy FPU handling on uni-processor */ extern struct task_struct *last_task_used_math; extern struct task_struct *last_task_used_altivec; diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index ead5016b02d0..6eb330a87c36 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -435,6 +435,17 @@ ret_from_fork: li r3,0 b ret_from_syscall + .globl ret_from_kernel_thread +ret_from_kernel_thread: + REST_NVGPRS(r1) + bl schedule_tail + mtlr r14 + mr r3,r15 + PPC440EP_ERR42 + blrl + li r3,0 + b do_exit # no return + /* Traced system call support */ syscall_dotrace: SAVE_NVGPRS(r1) diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index b40e0b4815b3..d7f4fafc7515 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -370,6 +370,16 @@ _GLOBAL(ret_from_fork) li r3,0 b syscall_exit +_GLOBAL(ret_from_kernel_thread) + bl .schedule_tail + REST_NVGPRS(r1) + REST_GPR(2,r1) + mtlr r14 + mr r3,r15 + blrl + li r3,0 + b .do_exit # no return + .section ".toc","aw" DSCR_DEFAULT: .tc dscr_default[TC],dscr_default diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 407e293aad2f..19e096bd0e73 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -663,39 +663,6 @@ _GLOBAL(abs) sub r3,r3,r4 blr -/* - * Create a kernel thread - * kernel_thread(fn, arg, flags) - */ -_GLOBAL(kernel_thread) - stwu r1,-16(r1) - stw r30,8(r1) - stw r31,12(r1) - mr r30,r3 /* function */ - mr r31,r4 /* argument */ - ori r3,r5,CLONE_VM /* flags */ - oris r3,r3,CLONE_UNTRACED>>16 - li r4,0 /* new sp (unused) */ - li r0,__NR_clone - sc - bns+ 1f /* did system call indicate error? */ - neg r3,r3 /* if so, make return code negative */ -1: cmpwi 0,r3,0 /* parent or child? */ - bne 2f /* return if parent */ - li r0,0 /* make top-level stack frame */ - stwu r0,-16(r1) - mtlr r30 /* fn addr in lr */ - mr r3,r31 /* load arg and call fn */ - PPC440EP_ERR42 - blrl - li r0,__NR_exit /* exit if function returns */ - li r3,0 - sc -2: lwz r30,8(r1) - lwz r31,12(r1) - addi r1,r1,16 - blr - #ifdef CONFIG_SMP _GLOBAL(start_secondary_resume) /* Reset stack */ diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 565b78625a32..5cfa8008693b 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -406,40 +406,6 @@ _GLOBAL(scom970_write) #endif /* CONFIG_CPU_FREQ_PMAC64 || CONFIG_CPU_FREQ_MAPLE */ -/* - * Create a kernel thread - * kernel_thread(fn, arg, flags) - */ -_GLOBAL(kernel_thread) - std r29,-24(r1) - std r30,-16(r1) - stdu r1,-STACK_FRAME_OVERHEAD(r1) - mr r29,r3 - mr r30,r4 - ori r3,r5,CLONE_VM /* flags */ - oris r3,r3,(CLONE_UNTRACED>>16) - li r4,0 /* new sp (unused) */ - li r0,__NR_clone - sc - bns+ 1f /* did system call indicate error? */ - neg r3,r3 /* if so, make return code negative */ -1: cmpdi 0,r3,0 /* parent or child? */ - bne 2f /* return if parent */ - li r0,0 - stdu r0,-STACK_FRAME_OVERHEAD(r1) - ld r2,8(r29) - ld r29,0(r29) - mtlr r29 /* fn addr in lr */ - mr r3,r30 /* load arg and call fn */ - blrl - li r0,__NR_exit /* exit after child exits */ - li r3,0 - sc -2: addi r1,r1,STACK_FRAME_OVERHEAD - ld r29,-24(r1) - ld r30,-16(r1) - blr - /* * disable_kernel_fp() * Disable the FPU. diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index 3e4031581c65..19e4288d8486 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -94,7 +94,6 @@ EXPORT_SYMBOL(pci_dram_offset); #endif /* CONFIG_PCI */ EXPORT_SYMBOL(start_thread); -EXPORT_SYMBOL(kernel_thread); EXPORT_SYMBOL(giveup_fpu); #ifdef CONFIG_ALTIVEC diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 1a1f2ddfb581..3b06898fa175 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -734,30 +734,39 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) extern unsigned long dscr_default; /* defined in arch/powerpc/kernel/sysfs.c */ int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long unused, struct task_struct *p, + unsigned long arg, struct task_struct *p, struct pt_regs *regs) { struct pt_regs *childregs, *kregs; extern void ret_from_fork(void); + extern void ret_from_kernel_thread(void); + void (*f)(void); unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE; - CHECK_FULL_REGS(regs); /* Copy registers */ sp -= sizeof(struct pt_regs); childregs = (struct pt_regs *) sp; - *childregs = *regs; - if ((childregs->msr & MSR_PR) == 0) { + if (!regs) { /* for kernel thread, set `current' and stackptr in new task */ + memset(childregs, 0, sizeof(struct pt_regs)); childregs->gpr[1] = sp + sizeof(struct pt_regs); -#ifdef CONFIG_PPC32 - childregs->gpr[2] = (unsigned long) p; -#else +#ifdef CONFIG_PPC64 + childregs->gpr[14] = *(unsigned long *)usp; + childregs->gpr[2] = ((unsigned long *)usp)[1], clear_tsk_thread_flag(p, TIF_32BIT); +#else + childregs->gpr[14] = usp; /* function */ + childregs->gpr[2] = (unsigned long) p; #endif + childregs->gpr[15] = arg; p->thread.regs = NULL; /* no user register state */ + f = ret_from_kernel_thread; } else { + CHECK_FULL_REGS(regs); + *childregs = *regs; childregs->gpr[1] = usp; p->thread.regs = childregs; + childregs->gpr[3] = 0; /* Result from fork() */ if (clone_flags & CLONE_SETTLS) { #ifdef CONFIG_PPC64 if (!is_32bit_task()) @@ -766,8 +775,9 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, #endif childregs->gpr[2] = childregs->gpr[6]; } + + f = ret_from_fork; } - childregs->gpr[3] = 0; /* Result from fork() */ sp -= STACK_FRAME_OVERHEAD; /* @@ -806,19 +816,17 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, p->thread.dscr = current->thread.dscr; } #endif - /* * The PPC64 ABI makes use of a TOC to contain function * pointers. The function (ret_from_except) is actually a pointer * to the TOC entry. The first entry is a pointer to the actual * function. - */ + */ #ifdef CONFIG_PPC64 - kregs->nip = *((unsigned long *)ret_from_fork); + kregs->nip = *((unsigned long *)f); #else - kregs->nip = (unsigned long)ret_from_fork; + kregs->nip = (unsigned long)f; #endif - return 0; } -- cgit v1.3-14-g43fede From be6abfa769fa07ce89ac73273360b335ae978805 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 31 Aug 2012 15:48:05 -0400 Subject: powerpc: switch to generic sys_execve()/kernel_execve() the only non-obvious part is that current_pt_regs() is really needed here - task_pt_regs() is NULL for kernel threads; it's OK for ptrace uses (the thing task_pt_regs() is intended for), but not for us. Signed-off-by: Al Viro --- arch/powerpc/include/asm/ptrace.h | 2 ++ arch/powerpc/include/asm/syscalls.h | 3 --- arch/powerpc/include/asm/unistd.h | 2 ++ arch/powerpc/kernel/entry_32.S | 5 +++++ arch/powerpc/kernel/entry_64.S | 6 ++++++ arch/powerpc/kernel/misc.S | 7 ------- arch/powerpc/kernel/process.c | 25 ++++++------------------- arch/powerpc/kernel/sys_ppc32.c | 22 ---------------------- 8 files changed, 21 insertions(+), 51 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index 9c21ed42aba6..f76b88c367d1 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -125,6 +125,8 @@ extern unsigned long ptrace_get_reg(struct task_struct *task, int regno); extern int ptrace_put_reg(struct task_struct *task, int regno, unsigned long data); +#define current_pt_regs() \ + ((struct pt_regs *)((unsigned long)current_thread_info() + THREAD_SIZE) - 1) /* * We use the least-significant bit of the trap field to indicate * whether we have saved the full set of registers, or only a diff --git a/arch/powerpc/include/asm/syscalls.h b/arch/powerpc/include/asm/syscalls.h index 4084e567d28e..329db4ec12ca 100644 --- a/arch/powerpc/include/asm/syscalls.h +++ b/arch/powerpc/include/asm/syscalls.h @@ -17,9 +17,6 @@ asmlinkage unsigned long sys_mmap(unsigned long addr, size_t len, asmlinkage unsigned long sys_mmap2(unsigned long addr, size_t len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff); -asmlinkage int sys_execve(unsigned long a0, unsigned long a1, - unsigned long a2, unsigned long a3, unsigned long a4, - unsigned long a5, struct pt_regs *regs); asmlinkage int sys_clone(unsigned long clone_flags, unsigned long usp, int __user *parent_tidp, void __user *child_threadptr, int __user *child_tidp, int p6, struct pt_regs *regs); diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index bd377a368611..26a6825909b6 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -420,6 +420,8 @@ #define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND #define __ARCH_WANT_SYS_NEWFSTATAT #endif +#define __ARCH_WANT_SYS_EXECVE +#define __ARCH_WANT_KERNEL_EXECVE /* * "Conditional" syscalls diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 6eb330a87c36..e6be75fc491a 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -446,6 +446,11 @@ ret_from_kernel_thread: li r3,0 b do_exit # no return + .globl __ret_from_kernel_execve +__ret_from_kernel_execve: + addi r1,r3,-STACK_FRAME_OVERHEAD + b ret_from_syscall + /* Traced system call support */ syscall_dotrace: SAVE_NVGPRS(r1) diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index d7f4fafc7515..1ca3d9fa48c4 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -380,6 +380,12 @@ _GLOBAL(ret_from_kernel_thread) li r3,0 b .do_exit # no return +_GLOBAL(__ret_from_kernel_execve) + addi r1,r3,-STACK_FRAME_OVERHEAD + li r10,1 + std r10,SOFTE(r1) + b syscall_exit + .section ".toc","aw" DSCR_DEFAULT: .tc dscr_default[TC],dscr_default diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S index ba16874fe294..7ce26d45777e 100644 --- a/arch/powerpc/kernel/misc.S +++ b/arch/powerpc/kernel/misc.S @@ -54,13 +54,6 @@ _GLOBAL(add_reloc_offset) .align 3 2: PPC_LONG 1b -_GLOBAL(kernel_execve) - li r0,__NR_execve - sc - bnslr - neg r3,r3 - blr - _GLOBAL(setjmp) mflr r0 PPC_STL r0,0(r3) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 3b06898fa175..6fdf044f475c 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1064,26 +1064,13 @@ int sys_vfork(unsigned long p1, unsigned long p2, unsigned long p3, regs, 0, NULL, NULL); } -int sys_execve(unsigned long a0, unsigned long a1, unsigned long a2, - unsigned long a3, unsigned long a4, unsigned long a5, - struct pt_regs *regs) +void __ret_from_kernel_execve(struct pt_regs *normal) +__noreturn; + +void ret_from_kernel_execve(struct pt_regs *normal) { - int error; - char *filename; - - filename = getname((const char __user *) a0); - error = PTR_ERR(filename); - if (IS_ERR(filename)) - goto out; - flush_fp_to_thread(current); - flush_altivec_to_thread(current); - flush_spe_to_thread(current); - error = do_execve(filename, - (const char __user *const __user *) a1, - (const char __user *const __user *) a2, regs); - putname(filename); -out: - return error; + set_thread_flag(TIF_RESTOREALL); + __ret_from_kernel_execve(normal); } static inline int valid_irq_stack(unsigned long sp, struct task_struct *p, diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index 81c570633ead..a1ae73a0f352 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -187,28 +187,6 @@ asmlinkage int compat_sys_sendfile64(int out_fd, int in_fd, compat_loff_t __user return ret; } -long compat_sys_execve(unsigned long a0, unsigned long a1, unsigned long a2, - unsigned long a3, unsigned long a4, unsigned long a5, - struct pt_regs *regs) -{ - int error; - char * filename; - - filename = getname((char __user *) a0); - error = PTR_ERR(filename); - if (IS_ERR(filename)) - goto out; - flush_fp_to_thread(current); - flush_altivec_to_thread(current); - - error = compat_do_execve(filename, compat_ptr(a1), compat_ptr(a2), regs); - - putname(filename); - -out: - return error; -} - /* Note: it is necessary to treat option as an unsigned int, * with the corresponding cast to a signed int to insure that the * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) -- cgit v1.3-14-g43fede From 3cffdc8c3a4445bb3a4b1b31b10867edeb9fa288 Mon Sep 17 00:00:00 2001 From: Richard Weinberger Date: Sat, 26 May 2012 01:57:10 +0200 Subject: Uninclude linux/freezer.h This include is no longer needed. (seems to be a leftover from try_to_freeze()) Signed-off-by: Richard Weinberger Signed-off-by: Al Viro --- arch/arm/kernel/signal.c | 1 - arch/avr32/kernel/signal.c | 1 - arch/blackfin/kernel/signal.c | 1 - arch/frv/kernel/signal.c | 1 - arch/h8300/kernel/signal.c | 1 - arch/hexagon/kernel/signal.c | 1 - arch/m32r/kernel/signal.c | 1 - arch/powerpc/kernel/signal_32.c | 1 - arch/sh/kernel/signal_32.c | 1 - arch/sh/kernel/signal_64.c | 1 - arch/unicore32/kernel/signal.c | 1 - arch/xtensa/kernel/signal.c | 1 - 12 files changed, 12 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index f27789e4e38a..56f72d257ebd 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -10,7 +10,6 @@ #include #include #include -#include #include #include diff --git a/arch/avr32/kernel/signal.c b/arch/avr32/kernel/signal.c index d552a854dacc..5e01c3a40ced 100644 --- a/arch/avr32/kernel/signal.c +++ b/arch/avr32/kernel/signal.c @@ -15,7 +15,6 @@ #include #include #include -#include #include #include diff --git a/arch/blackfin/kernel/signal.c b/arch/blackfin/kernel/signal.c index 6682b73a8523..6ed20a1a4af9 100644 --- a/arch/blackfin/kernel/signal.c +++ b/arch/blackfin/kernel/signal.c @@ -10,7 +10,6 @@ #include #include #include -#include #include #include diff --git a/arch/frv/kernel/signal.c b/arch/frv/kernel/signal.c index a03e3cccd98d..535810a3217a 100644 --- a/arch/frv/kernel/signal.c +++ b/arch/frv/kernel/signal.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/h8300/kernel/signal.c b/arch/h8300/kernel/signal.c index 5adaadaf9218..0e81b96c642f 100644 --- a/arch/h8300/kernel/signal.c +++ b/arch/h8300/kernel/signal.c @@ -38,7 +38,6 @@ #include #include #include -#include #include #include diff --git a/arch/hexagon/kernel/signal.c b/arch/hexagon/kernel/signal.c index 304b0808d072..1ea16bec7b91 100644 --- a/arch/hexagon/kernel/signal.c +++ b/arch/hexagon/kernel/signal.c @@ -20,7 +20,6 @@ #include #include -#include #include #include #include diff --git a/arch/m32r/kernel/signal.c b/arch/m32r/kernel/signal.c index c5101911b49a..6e3c26a1607c 100644 --- a/arch/m32r/kernel/signal.c +++ b/arch/m32r/kernel/signal.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 8b4c049aee20..804e323c139d 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -35,7 +35,6 @@ #include #include #include -#include #endif #include diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c index d6b7b6154f87..2f1f65356c0c 100644 --- a/arch/sh/kernel/signal_32.c +++ b/arch/sh/kernel/signal_32.c @@ -22,7 +22,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/sh/kernel/signal_64.c b/arch/sh/kernel/signal_64.c index 6b5b3dfe886b..23853814bd17 100644 --- a/arch/sh/kernel/signal_64.c +++ b/arch/sh/kernel/signal_64.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/unicore32/kernel/signal.c b/arch/unicore32/kernel/signal.c index 8adedb37720a..b8b2ffd774d6 100644 --- a/arch/unicore32/kernel/signal.c +++ b/arch/unicore32/kernel/signal.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c index 0cbe67a2248a..63c566f627bc 100644 --- a/arch/xtensa/kernel/signal.c +++ b/arch/xtensa/kernel/signal.c @@ -19,7 +19,6 @@ #include #include #include -#include #include #include -- cgit v1.3-14-g43fede From 8f9c0119d7ba94c3ad13876acc240d7f12b6d8e1 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Wed, 19 Sep 2012 12:01:52 +0100 Subject: compat: fs: Generic compat_sys_sendfile implementation This function is used by sparc, powerpc and arm64 for compat support. The patch adds a generic implementation which calls do_sendfile() directly and avoids set_fs(). The sparc architecture has wrappers for the sign extensions while powerpc relies on the compiler to do the this. The patch adds wrappers for powerpc to handle the u32->int type conversion. compat_sys_sendfile64() can be replaced by a sys_sendfile() call since compat_loff_t has the same size as off_t on a 64-bit system. On powerpc, the patch also changes the 64-bit sendfile call from sys_sendile64 to sys_sendfile. Signed-off-by: Catalin Marinas Acked-by: David S. Miller Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Alexander Viro Cc: Andrew Morton Signed-off-by: Al Viro --- arch/powerpc/include/asm/systbl.h | 4 ++-- arch/powerpc/include/asm/unistd.h | 1 + arch/powerpc/kernel/sys_ppc32.c | 45 ++++++-------------------------------- arch/sparc/include/asm/unistd.h | 1 + arch/sparc/kernel/sys32.S | 2 +- arch/sparc/kernel/sys_sparc32.c | 46 --------------------------------------- fs/compat.c | 22 +++++++++++++++++++ fs/read_write.c | 4 ++-- fs/read_write.h | 2 ++ include/linux/compat.h | 3 +++ 10 files changed, 41 insertions(+), 89 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index 559ae1ee6706..840838769853 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -189,7 +189,7 @@ SYSCALL_SPU(getcwd) SYSCALL_SPU(capget) SYSCALL_SPU(capset) COMPAT_SYS(sigaltstack) -SYSX_SPU(sys_sendfile64,compat_sys_sendfile,sys_sendfile) +SYSX_SPU(sys_sendfile,compat_sys_sendfile_wrapper,sys_sendfile) SYSCALL(ni_syscall) SYSCALL(ni_syscall) PPC_SYS(vfork) @@ -229,7 +229,7 @@ COMPAT_SYS_SPU(sched_setaffinity) COMPAT_SYS_SPU(sched_getaffinity) SYSCALL(ni_syscall) SYSCALL(ni_syscall) -SYS32ONLY(sendfile64) +SYSX(sys_ni_syscall,compat_sys_sendfile64_wrapper,sys_sendfile64) COMPAT_SYS_SPU(io_setup) SYSCALL_SPU(io_destroy) COMPAT_SYS_SPU(io_getevents) diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index bd377a368611..c683fa350add 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -419,6 +419,7 @@ #define __ARCH_WANT_COMPAT_SYS_TIME #define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND #define __ARCH_WANT_SYS_NEWFSTATAT +#define __ARCH_WANT_COMPAT_SYS_SENDFILE #endif /* diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index 81c570633ead..abd1112da54f 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -143,48 +143,17 @@ long compat_sys_ipc(u32 call, u32 first, u32 second, u32 third, compat_uptr_t pt * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) * and the register representation of a signed int (msr in 64-bit mode) is performed. */ -asmlinkage long compat_sys_sendfile(u32 out_fd, u32 in_fd, compat_off_t __user * offset, u32 count) +asmlinkage long compat_sys_sendfile_wrapper(u32 out_fd, u32 in_fd, + compat_off_t __user *offset, u32 count) { - mm_segment_t old_fs = get_fs(); - int ret; - off_t of; - off_t __user *up; - - if (offset && get_user(of, offset)) - return -EFAULT; - - /* The __user pointer cast is valid because of the set_fs() */ - set_fs(KERNEL_DS); - up = offset ? (off_t __user *) &of : NULL; - ret = sys_sendfile((int)out_fd, (int)in_fd, up, count); - set_fs(old_fs); - - if (offset && put_user(of, offset)) - return -EFAULT; - - return ret; + return compat_sys_sendfile((int)out_fd, (int)in_fd, offset, count); } -asmlinkage int compat_sys_sendfile64(int out_fd, int in_fd, compat_loff_t __user *offset, s32 count) +asmlinkage long compat_sys_sendfile64_wrapper(u32 out_fd, u32 in_fd, + compat_loff_t __user *offset, u32 count) { - mm_segment_t old_fs = get_fs(); - int ret; - loff_t lof; - loff_t __user *up; - - if (offset && get_user(lof, offset)) - return -EFAULT; - - /* The __user pointer cast is valid because of the set_fs() */ - set_fs(KERNEL_DS); - up = offset ? (loff_t __user *) &lof : NULL; - ret = sys_sendfile64(out_fd, in_fd, up, count); - set_fs(old_fs); - - if (offset && put_user(lof, offset)) - return -EFAULT; - - return ret; + return sys_sendfile((int)out_fd, (int)in_fd, + (off_t __user *)offset, count); } long compat_sys_execve(unsigned long a0, unsigned long a1, unsigned long a2, diff --git a/arch/sparc/include/asm/unistd.h b/arch/sparc/include/asm/unistd.h index fb2693464807..d9a677c51926 100644 --- a/arch/sparc/include/asm/unistd.h +++ b/arch/sparc/include/asm/unistd.h @@ -447,6 +447,7 @@ #else #define __ARCH_WANT_COMPAT_SYS_TIME #define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND +#define __ARCH_WANT_COMPAT_SYS_SENDFILE #endif /* diff --git a/arch/sparc/kernel/sys32.S b/arch/sparc/kernel/sys32.S index d97f3eb72e06..44025f4ba41f 100644 --- a/arch/sparc/kernel/sys32.S +++ b/arch/sparc/kernel/sys32.S @@ -90,7 +90,7 @@ SIGN1(sys32_mkdir, sys_mkdir, %o1) SIGN3(sys32_futex, compat_sys_futex, %o1, %o2, %o5) SIGN1(sys32_sysfs, compat_sys_sysfs, %o0) SIGN2(sys32_sendfile, compat_sys_sendfile, %o0, %o1) -SIGN2(sys32_sendfile64, compat_sys_sendfile64, %o0, %o1) +SIGN2(sys32_sendfile64, sys_sendfile, %o0, %o1) SIGN1(sys32_prctl, sys_prctl, %o0) SIGN1(sys32_sched_rr_get_interval, compat_sys_sched_rr_get_interval, %o0) SIGN2(sys32_waitpid, sys_waitpid, %o0, %o2) diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c index f7392336961f..d862499eb01c 100644 --- a/arch/sparc/kernel/sys_sparc32.c +++ b/arch/sparc/kernel/sys_sparc32.c @@ -506,52 +506,6 @@ long compat_sys_fadvise64_64(int fd, advice); } -asmlinkage long compat_sys_sendfile(int out_fd, int in_fd, - compat_off_t __user *offset, - compat_size_t count) -{ - mm_segment_t old_fs = get_fs(); - int ret; - off_t of; - - if (offset && get_user(of, offset)) - return -EFAULT; - - set_fs(KERNEL_DS); - ret = sys_sendfile(out_fd, in_fd, - offset ? (off_t __user *) &of : NULL, - count); - set_fs(old_fs); - - if (offset && put_user(of, offset)) - return -EFAULT; - - return ret; -} - -asmlinkage long compat_sys_sendfile64(int out_fd, int in_fd, - compat_loff_t __user *offset, - compat_size_t count) -{ - mm_segment_t old_fs = get_fs(); - int ret; - loff_t lof; - - if (offset && get_user(lof, offset)) - return -EFAULT; - - set_fs(KERNEL_DS); - ret = sys_sendfile64(out_fd, in_fd, - offset ? (loff_t __user *) &lof : NULL, - count); - set_fs(old_fs); - - if (offset && put_user(lof, offset)) - return -EFAULT; - - return ret; -} - /* This is just a version for 32-bit applications which does * not force O_LARGEFILE on. */ diff --git a/fs/compat.c b/fs/compat.c index d72d51e19025..b7a24d0ca30d 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1792,3 +1792,25 @@ compat_sys_open_by_handle_at(int mountdirfd, return do_handle_open(mountdirfd, handle, flags); } #endif + +#ifdef __ARCH_WANT_COMPAT_SYS_SENDFILE +asmlinkage long compat_sys_sendfile(int out_fd, int in_fd, + compat_off_t __user *offset, compat_size_t count) +{ + loff_t pos; + off_t off; + ssize_t ret; + + if (offset) { + if (unlikely(get_user(off, offset))) + return -EFAULT; + pos = off; + ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS); + if (unlikely(put_user(pos, offset))) + return -EFAULT; + return ret; + } + + return do_sendfile(out_fd, in_fd, NULL, count, 0); +} +#endif /* __ARCH_WANT_COMPAT_SYS_SENDFILE */ diff --git a/fs/read_write.c b/fs/read_write.c index 28b38279a219..d06534857e9e 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -862,8 +862,8 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, return ret; } -static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, - size_t count, loff_t max) +ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, size_t count, + loff_t max) { struct fd in, out; struct inode *in_inode, *out_inode; diff --git a/fs/read_write.h b/fs/read_write.h index d07b954c6e0c..d3e00ef67420 100644 --- a/fs/read_write.h +++ b/fs/read_write.h @@ -12,3 +12,5 @@ ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov, unsigned long nr_segs, size_t len, loff_t *ppos, iov_fn_t fn); ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov, unsigned long nr_segs, loff_t *ppos, io_fn_t fn); +ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, size_t count, + loff_t max); diff --git a/include/linux/compat.h b/include/linux/compat.h index 09b28b7369d7..fd4e29956d1c 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -590,6 +590,9 @@ asmlinkage ssize_t compat_sys_process_vm_writev(compat_pid_t pid, unsigned long liovcnt, const struct compat_iovec __user *rvec, unsigned long riovcnt, unsigned long flags); +asmlinkage long compat_sys_sendfile(int out_fd, int in_fd, + compat_off_t __user *offset, compat_size_t count); + #else #define is_compat_task() (0) -- cgit v1.3-14-g43fede From d900bd7366463fd96a907b2c212242e2b68b27d8 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Wed, 3 Oct 2012 18:57:10 +0000 Subject: powerpc/iommu: Fix multiple issues with IOMMU pools code There are a number of issues in the recent IOMMU pools code: - On a preempt kernel we might switch CPUs in the middle of building a scatter gather list. When this happens the handle hint passed in no longer falls within the local CPU's pool. Check for this and fall back to the pool hint. - We were missing a spin_unlock/spin_lock in one spot where we switch pools. - We need to provide locking around dart_tlb_invalidate_all and dart_tlb_invalidate_one now that the global lock is gone. Reported-by: Alexander Graf Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt CC: [v3.6] --- arch/powerpc/kernel/iommu.c | 5 ++++- arch/powerpc/sysdev/dart_iommu.c | 12 ++++++++++++ 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index ff5a6ce027b8..8226c6cb348a 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -215,7 +215,8 @@ static unsigned long iommu_range_alloc(struct device *dev, spin_lock_irqsave(&(pool->lock), flags); again: - if ((pass == 0) && handle && *handle) + if ((pass == 0) && handle && *handle && + (*handle >= pool->start) && (*handle < pool->end)) start = *handle; else start = pool->hint; @@ -236,7 +237,9 @@ again: * but on second pass, start at 0 in pool 0. */ if ((start & mask) >= limit || pass > 0) { + spin_unlock(&(pool->lock)); pool = &(tbl->pools[0]); + spin_lock(&(pool->lock)); start = pool->start; } else { start &= mask; diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c index 8ef63a01e345..bd968a43a48b 100644 --- a/arch/powerpc/sysdev/dart_iommu.c +++ b/arch/powerpc/sysdev/dart_iommu.c @@ -73,11 +73,16 @@ static int dart_is_u4; #define DBG(...) +static DEFINE_SPINLOCK(invalidate_lock); + static inline void dart_tlb_invalidate_all(void) { unsigned long l = 0; unsigned int reg, inv_bit; unsigned long limit; + unsigned long flags; + + spin_lock_irqsave(&invalidate_lock, flags); DBG("dart: flush\n"); @@ -110,12 +115,17 @@ retry: panic("DART: TLB did not flush after waiting a long " "time. Buggy U3 ?"); } + + spin_unlock_irqrestore(&invalidate_lock, flags); } static inline void dart_tlb_invalidate_one(unsigned long bus_rpn) { unsigned int reg; unsigned int l, limit; + unsigned long flags; + + spin_lock_irqsave(&invalidate_lock, flags); reg = DART_CNTL_U4_ENABLE | DART_CNTL_U4_IONE | (bus_rpn & DART_CNTL_U4_IONE_MASK); @@ -137,6 +147,8 @@ wait_more: panic("DART: TLB did not flush after waiting a long " "time. Buggy U4 ?"); } + + spin_unlock_irqrestore(&invalidate_lock, flags); } static void dart_flush(struct iommu_table *tbl) -- cgit v1.3-14-g43fede From 751f409db6216ebd134a94f6dcd97779933a5106 Mon Sep 17 00:00:00 2001 From: Denys Vlasenko Date: Thu, 4 Oct 2012 17:15:31 -0700 Subject: compat: move compat_siginfo_t definition to asm/compat.h This is a preparatory patch for the introduction of NT_SIGINFO elf note. Make the location of compat_siginfo_t uniform across eight architectures which have it. Now it can be pulled in by including asm/compat.h or linux/compat.h. Most of the copies are verbatim. compat_uid[32]_t had to be replaced by __compat_uid[32]_t. compat_uptr_t had to be moved up before compat_siginfo_t in asm/compat.h on a several architectures (tile already had it moved up). compat_sigval_t had to be relocated from linux/compat.h to asm/compat.h. Signed-off-by: Denys Vlasenko Cc: Oleg Nesterov Cc: Amerigo Wang Cc: "Jonathan M. Foote" Cc: Roland McGrath Cc: Pedro Alves Cc: Fengguang Wu Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/include/asm/compat.h | 60 +++++++++++++++++++++++++++- arch/arm64/kernel/signal32.c | 53 ------------------------- arch/mips/include/asm/compat-signal.h | 62 ----------------------------- arch/mips/include/asm/compat.h | 69 +++++++++++++++++++++++++++++++- arch/parisc/include/asm/compat.h | 59 ++++++++++++++++++++++++++- arch/parisc/kernel/signal32.h | 52 ------------------------ arch/powerpc/include/asm/compat.h | 60 +++++++++++++++++++++++++++- arch/powerpc/include/asm/siginfo.h | 1 - arch/powerpc/kernel/ppc32.h | 51 ------------------------ arch/s390/include/asm/compat.h | 75 ++++++++++++++++++++++++++++++++++- arch/s390/kernel/compat_linux.h | 68 ------------------------------- arch/sparc/include/asm/compat.h | 61 +++++++++++++++++++++++++++- arch/sparc/include/asm/siginfo.h | 1 - arch/sparc/kernel/signal32.c | 52 ------------------------ arch/tile/include/asm/compat.h | 62 +++++++++++++++++++++++++++++ arch/tile/kernel/compat_signal.c | 57 -------------------------- arch/x86/include/asm/compat.h | 74 +++++++++++++++++++++++++++++++++- arch/x86/include/asm/ia32.h | 67 ------------------------------- include/linux/compat.h | 5 --- 19 files changed, 513 insertions(+), 476 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h index a670a33ad736..37e610dc084e 100644 --- a/arch/arm64/include/asm/compat.h +++ b/arch/arm64/include/asm/compat.h @@ -55,6 +55,7 @@ typedef s64 compat_s64; typedef u32 compat_uint_t; typedef u32 compat_ulong_t; typedef u64 compat_u64; +typedef u32 compat_uptr_t; struct compat_timespec { compat_time_t tv_sec; @@ -130,6 +131,64 @@ typedef u32 compat_old_sigset_t; typedef u32 compat_sigset_word; +typedef union compat_sigval { + compat_int_t sival_int; + compat_uptr_t sival_ptr; +} compat_sigval_t; + +typedef struct compat_siginfo { + int si_signo; + int si_errno; + int si_code; + + union { + /* The padding is the same size as AArch64. */ + int _pad[128/sizeof(int) - 3]; + + /* kill() */ + struct { + compat_pid_t _pid; /* sender's pid */ + __compat_uid32_t _uid; /* sender's uid */ + } _kill; + + /* POSIX.1b timers */ + struct { + compat_timer_t _tid; /* timer id */ + int _overrun; /* overrun count */ + compat_sigval_t _sigval; /* same as below */ + int _sys_private; /* not to be passed to user */ + } _timer; + + /* POSIX.1b signals */ + struct { + compat_pid_t _pid; /* sender's pid */ + __compat_uid32_t _uid; /* sender's uid */ + compat_sigval_t _sigval; + } _rt; + + /* SIGCHLD */ + struct { + compat_pid_t _pid; /* which child */ + __compat_uid32_t _uid; /* sender's uid */ + int _status; /* exit code */ + compat_clock_t _utime; + compat_clock_t _stime; + } _sigchld; + + /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ + struct { + compat_uptr_t _addr; /* faulting insn/memory ref. */ + short _addr_lsb; /* LSB of the reported address */ + } _sigfault; + + /* SIGPOLL */ + struct { + compat_long_t _band; /* POLL_IN, POLL_OUT, POLL_MSG */ + int _fd; + } _sigpoll; + } _sifields; +} compat_siginfo_t; + #define COMPAT_OFF_T_MAX 0x7fffffff #define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL @@ -139,7 +198,6 @@ typedef u32 compat_sigset_word; * as pointers because the syscall entry code will have * appropriately converted them already. */ -typedef u32 compat_uptr_t; static inline void __user *compat_ptr(compat_uptr_t uptr) { diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index ac74c2f261e3..0790a87a4346 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -30,59 +30,6 @@ #include #include -typedef struct compat_siginfo { - int si_signo; - int si_errno; - int si_code; - - union { - /* The padding is the same size as AArch64. */ - int _pad[SI_PAD_SIZE]; - - /* kill() */ - struct { - compat_pid_t _pid; /* sender's pid */ - __compat_uid32_t _uid; /* sender's uid */ - } _kill; - - /* POSIX.1b timers */ - struct { - compat_timer_t _tid; /* timer id */ - int _overrun; /* overrun count */ - compat_sigval_t _sigval; /* same as below */ - int _sys_private; /* not to be passed to user */ - } _timer; - - /* POSIX.1b signals */ - struct { - compat_pid_t _pid; /* sender's pid */ - __compat_uid32_t _uid; /* sender's uid */ - compat_sigval_t _sigval; - } _rt; - - /* SIGCHLD */ - struct { - compat_pid_t _pid; /* which child */ - __compat_uid32_t _uid; /* sender's uid */ - int _status; /* exit code */ - compat_clock_t _utime; - compat_clock_t _stime; - } _sigchld; - - /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ - struct { - compat_uptr_t _addr; /* faulting insn/memory ref. */ - short _addr_lsb; /* LSB of the reported address */ - } _sigfault; - - /* SIGPOLL */ - struct { - compat_long_t _band; /* POLL_IN, POLL_OUT, POLL_MSG */ - int _fd; - } _sigpoll; - } _sifields; -} compat_siginfo_t; - struct compat_sigaction { compat_uptr_t sa_handler; compat_ulong_t sa_flags; diff --git a/arch/mips/include/asm/compat-signal.h b/arch/mips/include/asm/compat-signal.h index 368a99e5c3e1..6599a901b63e 100644 --- a/arch/mips/include/asm/compat-signal.h +++ b/arch/mips/include/asm/compat-signal.h @@ -10,68 +10,6 @@ #include -#define SI_PAD_SIZE32 ((SI_MAX_SIZE/sizeof(int)) - 3) - -typedef struct compat_siginfo { - int si_signo; - int si_code; - int si_errno; - - union { - int _pad[SI_PAD_SIZE32]; - - /* kill() */ - struct { - compat_pid_t _pid; /* sender's pid */ - compat_uid_t _uid; /* sender's uid */ - } _kill; - - /* SIGCHLD */ - struct { - compat_pid_t _pid; /* which child */ - compat_uid_t _uid; /* sender's uid */ - int _status; /* exit code */ - compat_clock_t _utime; - compat_clock_t _stime; - } _sigchld; - - /* IRIX SIGCHLD */ - struct { - compat_pid_t _pid; /* which child */ - compat_clock_t _utime; - int _status; /* exit code */ - compat_clock_t _stime; - } _irix_sigchld; - - /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ - struct { - s32 _addr; /* faulting insn/memory ref. */ - } _sigfault; - - /* SIGPOLL, SIGXFSZ (To do ...) */ - struct { - int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ - int _fd; - } _sigpoll; - - /* POSIX.1b timers */ - struct { - timer_t _tid; /* timer id */ - int _overrun; /* overrun count */ - compat_sigval_t _sigval;/* same as below */ - int _sys_private; /* not to be passed to user */ - } _timer; - - /* POSIX.1b signals */ - struct { - compat_pid_t _pid; /* sender's pid */ - compat_uid_t _uid; /* sender's uid */ - compat_sigval_t _sigval; - } _rt; - - } _sifields; -} compat_siginfo_t; - static inline int __copy_conv_sigset_to_user(compat_sigset_t __user *d, const sigset_t *s) { diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h index b77df0366ee6..58277e0e9cd4 100644 --- a/arch/mips/include/asm/compat.h +++ b/arch/mips/include/asm/compat.h @@ -43,6 +43,7 @@ typedef s64 compat_s64; typedef u32 compat_uint_t; typedef u32 compat_ulong_t; typedef u64 compat_u64; +typedef u32 compat_uptr_t; struct compat_timespec { compat_time_t tv_sec; @@ -124,6 +125,73 @@ typedef u32 compat_old_sigset_t; /* at least 32 bits */ typedef u32 compat_sigset_word; +typedef union compat_sigval { + compat_int_t sival_int; + compat_uptr_t sival_ptr; +} compat_sigval_t; + +#define SI_PAD_SIZE32 (128/sizeof(int) - 3) + +typedef struct compat_siginfo { + int si_signo; + int si_code; + int si_errno; + + union { + int _pad[SI_PAD_SIZE32]; + + /* kill() */ + struct { + compat_pid_t _pid; /* sender's pid */ + __compat_uid_t _uid; /* sender's uid */ + } _kill; + + /* SIGCHLD */ + struct { + compat_pid_t _pid; /* which child */ + __compat_uid_t _uid; /* sender's uid */ + int _status; /* exit code */ + compat_clock_t _utime; + compat_clock_t _stime; + } _sigchld; + + /* IRIX SIGCHLD */ + struct { + compat_pid_t _pid; /* which child */ + compat_clock_t _utime; + int _status; /* exit code */ + compat_clock_t _stime; + } _irix_sigchld; + + /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ + struct { + s32 _addr; /* faulting insn/memory ref. */ + } _sigfault; + + /* SIGPOLL, SIGXFSZ (To do ...) */ + struct { + int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ + int _fd; + } _sigpoll; + + /* POSIX.1b timers */ + struct { + timer_t _tid; /* timer id */ + int _overrun; /* overrun count */ + compat_sigval_t _sigval;/* same as below */ + int _sys_private; /* not to be passed to user */ + } _timer; + + /* POSIX.1b signals */ + struct { + compat_pid_t _pid; /* sender's pid */ + __compat_uid_t _uid; /* sender's uid */ + compat_sigval_t _sigval; + } _rt; + + } _sifields; +} compat_siginfo_t; + #define COMPAT_OFF_T_MAX 0x7fffffff #define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL @@ -133,7 +201,6 @@ typedef u32 compat_sigset_word; * as pointers because the syscall entry code will have * appropriately converted them already. */ -typedef u32 compat_uptr_t; static inline void __user *compat_ptr(compat_uptr_t uptr) { diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h index 760f331d4fa3..db7a662691a8 100644 --- a/arch/parisc/include/asm/compat.h +++ b/arch/parisc/include/asm/compat.h @@ -36,6 +36,7 @@ typedef s64 compat_s64; typedef u32 compat_uint_t; typedef u32 compat_ulong_t; typedef u64 compat_u64; +typedef u32 compat_uptr_t; struct compat_timespec { compat_time_t tv_sec; @@ -127,6 +128,63 @@ typedef u32 compat_old_sigset_t; /* at least 32 bits */ typedef u32 compat_sigset_word; +typedef union compat_sigval { + compat_int_t sival_int; + compat_uptr_t sival_ptr; +} compat_sigval_t; + +typedef struct compat_siginfo { + int si_signo; + int si_errno; + int si_code; + + union { + int _pad[128/sizeof(int) - 3]; + + /* kill() */ + struct { + unsigned int _pid; /* sender's pid */ + unsigned int _uid; /* sender's uid */ + } _kill; + + /* POSIX.1b timers */ + struct { + compat_timer_t _tid; /* timer id */ + int _overrun; /* overrun count */ + char _pad[sizeof(unsigned int) - sizeof(int)]; + compat_sigval_t _sigval; /* same as below */ + int _sys_private; /* not to be passed to user */ + } _timer; + + /* POSIX.1b signals */ + struct { + unsigned int _pid; /* sender's pid */ + unsigned int _uid; /* sender's uid */ + compat_sigval_t _sigval; + } _rt; + + /* SIGCHLD */ + struct { + unsigned int _pid; /* which child */ + unsigned int _uid; /* sender's uid */ + int _status; /* exit code */ + compat_clock_t _utime; + compat_clock_t _stime; + } _sigchld; + + /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ + struct { + unsigned int _addr; /* faulting insn/memory ref. */ + } _sigfault; + + /* SIGPOLL */ + struct { + int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ + int _fd; + } _sigpoll; + } _sifields; +} compat_siginfo_t; + #define COMPAT_OFF_T_MAX 0x7fffffff #define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL @@ -136,7 +194,6 @@ typedef u32 compat_sigset_word; * as pointers because the syscall entry code will have * appropriately converted them already. */ -typedef u32 compat_uptr_t; static inline void __user *compat_ptr(compat_uptr_t uptr) { diff --git a/arch/parisc/kernel/signal32.h b/arch/parisc/kernel/signal32.h index c7800846422c..08a88b5349a2 100644 --- a/arch/parisc/kernel/signal32.h +++ b/arch/parisc/kernel/signal32.h @@ -55,58 +55,6 @@ struct k_sigaction32 { struct compat_sigaction sa; }; -typedef struct compat_siginfo { - int si_signo; - int si_errno; - int si_code; - - union { - int _pad[((128/sizeof(int)) - 3)]; - - /* kill() */ - struct { - unsigned int _pid; /* sender's pid */ - unsigned int _uid; /* sender's uid */ - } _kill; - - /* POSIX.1b timers */ - struct { - compat_timer_t _tid; /* timer id */ - int _overrun; /* overrun count */ - char _pad[sizeof(unsigned int) - sizeof(int)]; - compat_sigval_t _sigval; /* same as below */ - int _sys_private; /* not to be passed to user */ - } _timer; - - /* POSIX.1b signals */ - struct { - unsigned int _pid; /* sender's pid */ - unsigned int _uid; /* sender's uid */ - compat_sigval_t _sigval; - } _rt; - - /* SIGCHLD */ - struct { - unsigned int _pid; /* which child */ - unsigned int _uid; /* sender's uid */ - int _status; /* exit code */ - compat_clock_t _utime; - compat_clock_t _stime; - } _sigchld; - - /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ - struct { - unsigned int _addr; /* faulting insn/memory ref. */ - } _sigfault; - - /* SIGPOLL */ - struct { - int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ - int _fd; - } _sigpoll; - } _sifields; -} compat_siginfo_t; - int copy_siginfo_to_user32 (compat_siginfo_t __user *to, siginfo_t *from); int copy_siginfo_from_user32 (siginfo_t *to, compat_siginfo_t __user *from); diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index 88e602f6430d..84fdf6857c31 100644 --- a/arch/powerpc/include/asm/compat.h +++ b/arch/powerpc/include/asm/compat.h @@ -38,6 +38,7 @@ typedef s64 compat_s64; typedef u32 compat_uint_t; typedef u32 compat_ulong_t; typedef u64 compat_u64; +typedef u32 compat_uptr_t; struct compat_timespec { compat_time_t tv_sec; @@ -114,6 +115,64 @@ typedef u32 compat_old_sigset_t; typedef u32 compat_sigset_word; +typedef union compat_sigval { + compat_int_t sival_int; + compat_uptr_t sival_ptr; +} compat_sigval_t; + +#define SI_PAD_SIZE32 (128/sizeof(int) - 3) + +typedef struct compat_siginfo { + int si_signo; + int si_errno; + int si_code; + + union { + int _pad[SI_PAD_SIZE32]; + + /* kill() */ + struct { + compat_pid_t _pid; /* sender's pid */ + __compat_uid_t _uid; /* sender's uid */ + } _kill; + + /* POSIX.1b timers */ + struct { + compat_timer_t _tid; /* timer id */ + int _overrun; /* overrun count */ + compat_sigval_t _sigval; /* same as below */ + int _sys_private; /* not to be passed to user */ + } _timer; + + /* POSIX.1b signals */ + struct { + compat_pid_t _pid; /* sender's pid */ + __compat_uid_t _uid; /* sender's uid */ + compat_sigval_t _sigval; + } _rt; + + /* SIGCHLD */ + struct { + compat_pid_t _pid; /* which child */ + __compat_uid_t _uid; /* sender's uid */ + int _status; /* exit code */ + compat_clock_t _utime; + compat_clock_t _stime; + } _sigchld; + + /* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGEMT */ + struct { + unsigned int _addr; /* faulting insn/memory ref. */ + } _sigfault; + + /* SIGPOLL */ + struct { + int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ + int _fd; + } _sigpoll; + } _sifields; +} compat_siginfo_t; + #define COMPAT_OFF_T_MAX 0x7fffffff #define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL @@ -123,7 +182,6 @@ typedef u32 compat_sigset_word; * as pointers because the syscall entry code will have * appropriately converted them already. */ -typedef u32 compat_uptr_t; static inline void __user *compat_ptr(compat_uptr_t uptr) { diff --git a/arch/powerpc/include/asm/siginfo.h b/arch/powerpc/include/asm/siginfo.h index 49495b0534ed..ccce3ef5cd86 100644 --- a/arch/powerpc/include/asm/siginfo.h +++ b/arch/powerpc/include/asm/siginfo.h @@ -10,7 +10,6 @@ #ifdef __powerpc64__ # define __ARCH_SI_PREAMBLE_SIZE (4 * sizeof(int)) -# define SI_PAD_SIZE32 ((SI_MAX_SIZE/sizeof(int)) - 3) #endif #include diff --git a/arch/powerpc/kernel/ppc32.h b/arch/powerpc/kernel/ppc32.h index dc16aefe1dd0..02fb0ee26093 100644 --- a/arch/powerpc/kernel/ppc32.h +++ b/arch/powerpc/kernel/ppc32.h @@ -16,57 +16,6 @@ /* These are here to support 32-bit syscalls on a 64-bit kernel. */ -typedef struct compat_siginfo { - int si_signo; - int si_errno; - int si_code; - - union { - int _pad[SI_PAD_SIZE32]; - - /* kill() */ - struct { - compat_pid_t _pid; /* sender's pid */ - compat_uid_t _uid; /* sender's uid */ - } _kill; - - /* POSIX.1b timers */ - struct { - compat_timer_t _tid; /* timer id */ - int _overrun; /* overrun count */ - compat_sigval_t _sigval; /* same as below */ - int _sys_private; /* not to be passed to user */ - } _timer; - - /* POSIX.1b signals */ - struct { - compat_pid_t _pid; /* sender's pid */ - compat_uid_t _uid; /* sender's uid */ - compat_sigval_t _sigval; - } _rt; - - /* SIGCHLD */ - struct { - compat_pid_t _pid; /* which child */ - compat_uid_t _uid; /* sender's uid */ - int _status; /* exit code */ - compat_clock_t _utime; - compat_clock_t _stime; - } _sigchld; - - /* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGEMT */ - struct { - unsigned int _addr; /* faulting insn/memory ref. */ - } _sigfault; - - /* SIGPOLL */ - struct { - int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ - int _fd; - } _sigpoll; - } _sifields; -} compat_siginfo_t; - #define __old_sigaction32 old_sigaction32 struct __old_sigaction32 { diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index 234f1d859cea..a34a9d612fc0 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -65,6 +65,7 @@ typedef s64 compat_s64; typedef u32 compat_uint_t; typedef u32 compat_ulong_t; typedef u64 compat_u64; +typedef u32 compat_uptr_t; struct compat_timespec { compat_time_t tv_sec; @@ -144,6 +145,79 @@ typedef u32 compat_old_sigset_t; /* at least 32 bits */ typedef u32 compat_sigset_word; +typedef union compat_sigval { + compat_int_t sival_int; + compat_uptr_t sival_ptr; +} compat_sigval_t; + +typedef struct compat_siginfo { + int si_signo; + int si_errno; + int si_code; + + union { + int _pad[128/sizeof(int) - 3]; + + /* kill() */ + struct { + pid_t _pid; /* sender's pid */ + uid_t _uid; /* sender's uid */ + } _kill; + + /* POSIX.1b timers */ + struct { + compat_timer_t _tid; /* timer id */ + int _overrun; /* overrun count */ + compat_sigval_t _sigval; /* same as below */ + int _sys_private; /* not to be passed to user */ + } _timer; + + /* POSIX.1b signals */ + struct { + pid_t _pid; /* sender's pid */ + uid_t _uid; /* sender's uid */ + compat_sigval_t _sigval; + } _rt; + + /* SIGCHLD */ + struct { + pid_t _pid; /* which child */ + uid_t _uid; /* sender's uid */ + int _status;/* exit code */ + compat_clock_t _utime; + compat_clock_t _stime; + } _sigchld; + + /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ + struct { + __u32 _addr; /* faulting insn/memory ref. - pointer */ + } _sigfault; + + /* SIGPOLL */ + struct { + int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ + int _fd; + } _sigpoll; + } _sifields; +} compat_siginfo_t; + +/* + * How these fields are to be accessed. + */ +#define si_pid _sifields._kill._pid +#define si_uid _sifields._kill._uid +#define si_status _sifields._sigchld._status +#define si_utime _sifields._sigchld._utime +#define si_stime _sifields._sigchld._stime +#define si_value _sifields._rt._sigval +#define si_int _sifields._rt._sigval.sival_int +#define si_ptr _sifields._rt._sigval.sival_ptr +#define si_addr _sifields._sigfault._addr +#define si_band _sifields._sigpoll._band +#define si_fd _sifields._sigpoll._fd +#define si_tid _sifields._timer._tid +#define si_overrun _sifields._timer._overrun + #define COMPAT_OFF_T_MAX 0x7fffffff #define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL @@ -153,7 +227,6 @@ typedef u32 compat_sigset_word; * as pointers because the syscall entry code will have * appropriately converted them already. */ -typedef u32 compat_uptr_t; static inline void __user *compat_ptr(compat_uptr_t uptr) { diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h index 9635d759c2b9..90887bd98cf0 100644 --- a/arch/s390/kernel/compat_linux.h +++ b/arch/s390/kernel/compat_linux.h @@ -23,74 +23,6 @@ struct old_sigaction32 { __u32 sa_flags; __u32 sa_restorer; /* Another 32 bit pointer */ }; - -typedef struct compat_siginfo { - int si_signo; - int si_errno; - int si_code; - - union { - int _pad[((128/sizeof(int)) - 3)]; - - /* kill() */ - struct { - pid_t _pid; /* sender's pid */ - uid_t _uid; /* sender's uid */ - } _kill; - - /* POSIX.1b timers */ - struct { - compat_timer_t _tid; /* timer id */ - int _overrun; /* overrun count */ - compat_sigval_t _sigval; /* same as below */ - int _sys_private; /* not to be passed to user */ - } _timer; - - /* POSIX.1b signals */ - struct { - pid_t _pid; /* sender's pid */ - uid_t _uid; /* sender's uid */ - compat_sigval_t _sigval; - } _rt; - - /* SIGCHLD */ - struct { - pid_t _pid; /* which child */ - uid_t _uid; /* sender's uid */ - int _status;/* exit code */ - compat_clock_t _utime; - compat_clock_t _stime; - } _sigchld; - - /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ - struct { - __u32 _addr; /* faulting insn/memory ref. - pointer */ - } _sigfault; - - /* SIGPOLL */ - struct { - int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ - int _fd; - } _sigpoll; - } _sifields; -} compat_siginfo_t; - -/* - * How these fields are to be accessed. - */ -#define si_pid _sifields._kill._pid -#define si_uid _sifields._kill._uid -#define si_status _sifields._sigchld._status -#define si_utime _sifields._sigchld._utime -#define si_stime _sifields._sigchld._stime -#define si_value _sifields._rt._sigval -#define si_int _sifields._rt._sigval.sival_int -#define si_ptr _sifields._rt._sigval.sival_ptr -#define si_addr _sifields._sigfault._addr -#define si_band _sifields._sigpoll._band -#define si_fd _sifields._sigpoll._fd -#define si_tid _sifields._timer._tid -#define si_overrun _sifields._timer._overrun /* asm/sigcontext.h */ typedef union diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h index b8be20d42a0a..cef99fbc0a21 100644 --- a/arch/sparc/include/asm/compat.h +++ b/arch/sparc/include/asm/compat.h @@ -36,6 +36,7 @@ typedef s64 compat_s64; typedef u32 compat_uint_t; typedef u32 compat_ulong_t; typedef u64 compat_u64; +typedef u32 compat_uptr_t; struct compat_timespec { compat_time_t tv_sec; @@ -147,6 +148,65 @@ typedef u32 compat_old_sigset_t; typedef u32 compat_sigset_word; +typedef union compat_sigval { + compat_int_t sival_int; + compat_uptr_t sival_ptr; +} compat_sigval_t; + +#define SI_PAD_SIZE32 (128/sizeof(int) - 3) + +typedef struct compat_siginfo { + int si_signo; + int si_errno; + int si_code; + + union { + int _pad[SI_PAD_SIZE32]; + + /* kill() */ + struct { + compat_pid_t _pid; /* sender's pid */ + unsigned int _uid; /* sender's uid */ + } _kill; + + /* POSIX.1b timers */ + struct { + compat_timer_t _tid; /* timer id */ + int _overrun; /* overrun count */ + compat_sigval_t _sigval; /* same as below */ + int _sys_private; /* not to be passed to user */ + } _timer; + + /* POSIX.1b signals */ + struct { + compat_pid_t _pid; /* sender's pid */ + unsigned int _uid; /* sender's uid */ + compat_sigval_t _sigval; + } _rt; + + /* SIGCHLD */ + struct { + compat_pid_t _pid; /* which child */ + unsigned int _uid; /* sender's uid */ + int _status; /* exit code */ + compat_clock_t _utime; + compat_clock_t _stime; + } _sigchld; + + /* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGEMT */ + struct { + u32 _addr; /* faulting insn/memory ref. */ + int _trapno; + } _sigfault; + + /* SIGPOLL */ + struct { + int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ + int _fd; + } _sigpoll; + } _sifields; +} compat_siginfo_t; + #define COMPAT_OFF_T_MAX 0x7fffffff #define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL @@ -156,7 +216,6 @@ typedef u32 compat_sigset_word; * as pointers because the syscall entry code will have * appropriately converted them already. */ -typedef u32 compat_uptr_t; static inline void __user *compat_ptr(compat_uptr_t uptr) { diff --git a/arch/sparc/include/asm/siginfo.h b/arch/sparc/include/asm/siginfo.h index 215900fce21b..dbc182c438b4 100644 --- a/arch/sparc/include/asm/siginfo.h +++ b/arch/sparc/include/asm/siginfo.h @@ -3,7 +3,6 @@ #if defined(__sparc__) && defined(__arch64__) -#define SI_PAD_SIZE32 ((SI_MAX_SIZE/sizeof(int)) - 3) #define __ARCH_SI_PREAMBLE_SIZE (4 * sizeof(int)) #define __ARCH_SI_BAND_T int diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c index a53e0a5fd3a3..53e48f721ce3 100644 --- a/arch/sparc/kernel/signal32.c +++ b/arch/sparc/kernel/signal32.c @@ -54,58 +54,6 @@ struct signal_frame32 { /* __siginfo_rwin_t * */u32 rwin_save; } __attribute__((aligned(8))); -typedef struct compat_siginfo{ - int si_signo; - int si_errno; - int si_code; - - union { - int _pad[SI_PAD_SIZE32]; - - /* kill() */ - struct { - compat_pid_t _pid; /* sender's pid */ - unsigned int _uid; /* sender's uid */ - } _kill; - - /* POSIX.1b timers */ - struct { - compat_timer_t _tid; /* timer id */ - int _overrun; /* overrun count */ - compat_sigval_t _sigval; /* same as below */ - int _sys_private; /* not to be passed to user */ - } _timer; - - /* POSIX.1b signals */ - struct { - compat_pid_t _pid; /* sender's pid */ - unsigned int _uid; /* sender's uid */ - compat_sigval_t _sigval; - } _rt; - - /* SIGCHLD */ - struct { - compat_pid_t _pid; /* which child */ - unsigned int _uid; /* sender's uid */ - int _status; /* exit code */ - compat_clock_t _utime; - compat_clock_t _stime; - } _sigchld; - - /* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGEMT */ - struct { - u32 _addr; /* faulting insn/memory ref. */ - int _trapno; - } _sigfault; - - /* SIGPOLL */ - struct { - int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ - int _fd; - } _sigpoll; - } _sifields; -}compat_siginfo_t; - struct rt_signal_frame32 { struct sparc_stackf32 ss; compat_siginfo_t info; diff --git a/arch/tile/include/asm/compat.h b/arch/tile/include/asm/compat.h index 6e74450ff0a1..3063e6fc8daa 100644 --- a/arch/tile/include/asm/compat.h +++ b/arch/tile/include/asm/compat.h @@ -110,6 +110,68 @@ struct compat_flock64 { typedef u32 compat_sigset_word; +typedef union compat_sigval { + compat_int_t sival_int; + compat_uptr_t sival_ptr; +} compat_sigval_t; + +#define COMPAT_SI_PAD_SIZE (128/sizeof(int) - 3) + +typedef struct compat_siginfo { + int si_signo; + int si_errno; + int si_code; + + union { + int _pad[COMPAT_SI_PAD_SIZE]; + + /* kill() */ + struct { + unsigned int _pid; /* sender's pid */ + unsigned int _uid; /* sender's uid */ + } _kill; + + /* POSIX.1b timers */ + struct { + compat_timer_t _tid; /* timer id */ + int _overrun; /* overrun count */ + compat_sigval_t _sigval; /* same as below */ + int _sys_private; /* not to be passed to user */ + int _overrun_incr; /* amount to add to overrun */ + } _timer; + + /* POSIX.1b signals */ + struct { + unsigned int _pid; /* sender's pid */ + unsigned int _uid; /* sender's uid */ + compat_sigval_t _sigval; + } _rt; + + /* SIGCHLD */ + struct { + unsigned int _pid; /* which child */ + unsigned int _uid; /* sender's uid */ + int _status; /* exit code */ + compat_clock_t _utime; + compat_clock_t _stime; + } _sigchld; + + /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ + struct { + unsigned int _addr; /* faulting insn/memory ref. */ +#ifdef __ARCH_SI_TRAPNO + int _trapno; /* TRAP # which caused the signal */ +#endif + } _sigfault; + + /* SIGPOLL */ + struct { + int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ + int _fd; + } _sigpoll; + } _sifields; +} compat_siginfo_t; + #define COMPAT_OFF_T_MAX 0x7fffffff #define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL diff --git a/arch/tile/kernel/compat_signal.c b/arch/tile/kernel/compat_signal.c index 474571b84085..7bc0859a9f5e 100644 --- a/arch/tile/kernel/compat_signal.c +++ b/arch/tile/kernel/compat_signal.c @@ -55,63 +55,6 @@ struct compat_ucontext { sigset_t uc_sigmask; /* mask last for extensibility */ }; -#define COMPAT_SI_PAD_SIZE ((SI_MAX_SIZE - 3 * sizeof(int)) / sizeof(int)) - -struct compat_siginfo { - int si_signo; - int si_errno; - int si_code; - - union { - int _pad[COMPAT_SI_PAD_SIZE]; - - /* kill() */ - struct { - unsigned int _pid; /* sender's pid */ - unsigned int _uid; /* sender's uid */ - } _kill; - - /* POSIX.1b timers */ - struct { - compat_timer_t _tid; /* timer id */ - int _overrun; /* overrun count */ - compat_sigval_t _sigval; /* same as below */ - int _sys_private; /* not to be passed to user */ - int _overrun_incr; /* amount to add to overrun */ - } _timer; - - /* POSIX.1b signals */ - struct { - unsigned int _pid; /* sender's pid */ - unsigned int _uid; /* sender's uid */ - compat_sigval_t _sigval; - } _rt; - - /* SIGCHLD */ - struct { - unsigned int _pid; /* which child */ - unsigned int _uid; /* sender's uid */ - int _status; /* exit code */ - compat_clock_t _utime; - compat_clock_t _stime; - } _sigchld; - - /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ - struct { - unsigned int _addr; /* faulting insn/memory ref. */ -#ifdef __ARCH_SI_TRAPNO - int _trapno; /* TRAP # which caused the signal */ -#endif - } _sigfault; - - /* SIGPOLL */ - struct { - int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ - int _fd; - } _sigpoll; - } _sifields; -}; - struct compat_rt_sigframe { unsigned char save_area[C_ABI_SAVE_AREA_SIZE]; /* caller save area */ struct compat_siginfo info; diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index fedf32b73e65..59c6c401f79f 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -41,6 +41,7 @@ typedef s64 __attribute__((aligned(4))) compat_s64; typedef u32 compat_uint_t; typedef u32 compat_ulong_t; typedef u64 __attribute__((aligned(4))) compat_u64; +typedef u32 compat_uptr_t; struct compat_timespec { compat_time_t tv_sec; @@ -124,6 +125,78 @@ typedef u32 compat_old_sigset_t; /* at least 32 bits */ typedef u32 compat_sigset_word; +typedef union compat_sigval { + compat_int_t sival_int; + compat_uptr_t sival_ptr; +} compat_sigval_t; + +typedef struct compat_siginfo { + int si_signo; + int si_errno; + int si_code; + + union { + int _pad[128/sizeof(int) - 3]; + + /* kill() */ + struct { + unsigned int _pid; /* sender's pid */ + unsigned int _uid; /* sender's uid */ + } _kill; + + /* POSIX.1b timers */ + struct { + compat_timer_t _tid; /* timer id */ + int _overrun; /* overrun count */ + compat_sigval_t _sigval; /* same as below */ + int _sys_private; /* not to be passed to user */ + int _overrun_incr; /* amount to add to overrun */ + } _timer; + + /* POSIX.1b signals */ + struct { + unsigned int _pid; /* sender's pid */ + unsigned int _uid; /* sender's uid */ + compat_sigval_t _sigval; + } _rt; + + /* SIGCHLD */ + struct { + unsigned int _pid; /* which child */ + unsigned int _uid; /* sender's uid */ + int _status; /* exit code */ + compat_clock_t _utime; + compat_clock_t _stime; + } _sigchld; + + /* SIGCHLD (x32 version) */ + struct { + unsigned int _pid; /* which child */ + unsigned int _uid; /* sender's uid */ + int _status; /* exit code */ + compat_s64 _utime; + compat_s64 _stime; + } _sigchld_x32; + + /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ + struct { + unsigned int _addr; /* faulting insn/memory ref. */ + } _sigfault; + + /* SIGPOLL */ + struct { + int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ + int _fd; + } _sigpoll; + + struct { + unsigned int _call_addr; /* calling insn */ + int _syscall; /* triggering system call number */ + unsigned int _arch; /* AUDIT_ARCH_* of syscall */ + } _sigsys; + } _sifields; +} compat_siginfo_t; + #define COMPAT_OFF_T_MAX 0x7fffffff #define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL @@ -209,7 +282,6 @@ typedef struct user_regs_struct32 compat_elf_gregset_t; * as pointers because the syscall entry code will have * appropriately converted them already. */ -typedef u32 compat_uptr_t; static inline void __user *compat_ptr(compat_uptr_t uptr) { diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h index b04cbdb138cd..e6232773ce49 100644 --- a/arch/x86/include/asm/ia32.h +++ b/arch/x86/include/asm/ia32.h @@ -86,73 +86,6 @@ struct stat64 { unsigned long long st_ino; } __attribute__((packed)); -typedef struct compat_siginfo { - int si_signo; - int si_errno; - int si_code; - - union { - int _pad[((128 / sizeof(int)) - 3)]; - - /* kill() */ - struct { - unsigned int _pid; /* sender's pid */ - unsigned int _uid; /* sender's uid */ - } _kill; - - /* POSIX.1b timers */ - struct { - compat_timer_t _tid; /* timer id */ - int _overrun; /* overrun count */ - compat_sigval_t _sigval; /* same as below */ - int _sys_private; /* not to be passed to user */ - int _overrun_incr; /* amount to add to overrun */ - } _timer; - - /* POSIX.1b signals */ - struct { - unsigned int _pid; /* sender's pid */ - unsigned int _uid; /* sender's uid */ - compat_sigval_t _sigval; - } _rt; - - /* SIGCHLD */ - struct { - unsigned int _pid; /* which child */ - unsigned int _uid; /* sender's uid */ - int _status; /* exit code */ - compat_clock_t _utime; - compat_clock_t _stime; - } _sigchld; - - /* SIGCHLD (x32 version) */ - struct { - unsigned int _pid; /* which child */ - unsigned int _uid; /* sender's uid */ - int _status; /* exit code */ - compat_s64 _utime; - compat_s64 _stime; - } _sigchld_x32; - - /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ - struct { - unsigned int _addr; /* faulting insn/memory ref. */ - } _sigfault; - - /* SIGPOLL */ - struct { - int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ - int _fd; - } _sigpoll; - - struct { - unsigned int _call_addr; /* calling insn */ - int _syscall; /* triggering system call number */ - unsigned int _arch; /* AUDIT_ARCH_* of syscall */ - } _sigsys; - } _sifields; -} compat_siginfo_t; - #define IA32_STACK_TOP IA32_PAGE_OFFSET #ifdef __KERNEL__ diff --git a/include/linux/compat.h b/include/linux/compat.h index fd4e29956d1c..3f53d002c7c5 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -160,11 +160,6 @@ struct compat_ustat { char f_fpack[6]; }; -typedef union compat_sigval { - compat_int_t sival_int; - compat_uptr_t sival_ptr; -} compat_sigval_t; - #define COMPAT_SIGEV_PAD_SIZE ((SIGEV_MAX_SIZE/sizeof(int)) - 3) typedef struct compat_sigevent { -- cgit v1.3-14-g43fede From 8ea959a17fe6e27f7954dddad5b17b0e33f0d7ee Mon Sep 17 00:00:00 2001 From: Deepthi Dharwar Date: Wed, 3 Oct 2012 18:42:18 +0000 Subject: cpuidle/powerpc: Fix smt_snooze_delay functionality. smt_snooze_delay was designed to delay idle loop's nap entry in the native idle code before it got ported over to use as part of the cpuidle framework. A -ve value assigned to smt_snooze_delay should result in busy looping, in other words disabling the entry to nap state. - https://lists.ozlabs.org/pipermail/linuxppc-dev/2010-May/082450.html This particular functionality can be achieved currently by echo 1 > /sys/devices/system/cpu/cpu*/state1/disable but it is broken when one assigns -ve value to the smt_snooze_delay variable either via sysfs entry or ppc64_cpu util. This patch aims to fix this, by disabling nap state when smt_snooze_delay variable is set to -ve value. Signed-off-by: Deepthi Dharwar Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/processor.h | 4 ++-- arch/powerpc/kernel/sysfs.c | 2 +- arch/powerpc/platforms/pseries/processor_idle.c | 24 +++++++++++++++++------- 3 files changed, 20 insertions(+), 10 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 8734b3855272..87502046c0dc 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -388,9 +388,9 @@ extern int powersave_nap; /* set if nap mode can be used in idle loop */ extern void power7_nap(void); #ifdef CONFIG_PSERIES_IDLE -extern void update_smt_snooze_delay(int snooze); +extern void update_smt_snooze_delay(int cpu, int residency); #else -static inline void update_smt_snooze_delay(int snooze) {} +static inline void update_smt_snooze_delay(int cpu, int residency) {} #endif extern void flush_instruction_cache(void); diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 8302af649219..cf357a059ddb 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -50,7 +50,7 @@ static ssize_t store_smt_snooze_delay(struct device *dev, return -EINVAL; per_cpu(smt_snooze_delay, cpu->dev.id) = snooze; - update_smt_snooze_delay(snooze); + update_smt_snooze_delay(cpu->dev.id, snooze); return count; } diff --git a/arch/powerpc/platforms/pseries/processor_idle.c b/arch/powerpc/platforms/pseries/processor_idle.c index 02e425aa2af8..a32d56d1f854 100644 --- a/arch/powerpc/platforms/pseries/processor_idle.c +++ b/arch/powerpc/platforms/pseries/processor_idle.c @@ -33,13 +33,6 @@ static int max_idle_state = MAX_IDLE_STATE_COUNT - 1; static struct cpuidle_device __percpu *pseries_cpuidle_devices; static struct cpuidle_state *cpuidle_state_table; -void update_smt_snooze_delay(int snooze) -{ - struct cpuidle_driver *drv = cpuidle_get_driver(); - if (drv) - drv->states[0].target_residency = snooze; -} - static inline void idle_loop_prolog(unsigned long *in_purr, ktime_t *kt_before) { @@ -190,6 +183,23 @@ static struct cpuidle_state shared_states[MAX_IDLE_STATE_COUNT] = { .enter = &shared_cede_loop }, }; +void update_smt_snooze_delay(int cpu, int residency) +{ + struct cpuidle_driver *drv = cpuidle_get_driver(); + struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu); + + if (cpuidle_state_table != dedicated_states) + return; + + if (residency < 0) { + /* Disable the Nap state on that cpu */ + if (dev) + dev->states_usage[1].disable = 1; + } else + if (drv) + drv->states[0].target_residency = residency; +} + static int pseries_cpuidle_add_cpu_notifier(struct notifier_block *n, unsigned long action, void *hcpu) { -- cgit v1.3-14-g43fede