From 9e46294dadedc0c04adcb8ce760bd2cd74f7332d Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 2 Jul 2011 15:00:52 +0200 Subject: x86: Save stack pointer in perf live regs savings In order to prepare for fetching the stack pointer from the regs when possible in dump_trace() instead of taking the local one, save the current stack pointer in perf live regs saving. Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Thomas Gleixner Cc: H. Peter Anvin Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo --- arch/x86/include/asm/perf_event.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index d9d4dae305f6..094fb30817ab 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -152,6 +152,11 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs); (regs)->bp = caller_frame_pointer(); \ (regs)->cs = __KERNEL_CS; \ regs->flags = 0; \ + asm volatile( \ + _ASM_MOV "%%"_ASM_SP ", %0\n" \ + : "=m" ((regs)->sp) \ + :: "memory" \ + ); \ } #else -- cgit v1.2.1 From e08fbb78f03fe2c4f88824faf6f51ce6af185e11 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 1 Jul 2011 23:04:36 -0400 Subject: tracing, x86/irq: Do not trace arch_local_{*,irq_*}() functions I triggered a triple fault with gcc 4.5.1 because it did not honor the inline annotation to arch_local_save_flags() function and that function was added to the pool of functions traced by the function tracer. When preempt_schedule() called arch_local_save_flags() (called by irqs_disabled()), it was traced, but the first thing the function tracer does is disable preemption. When it enables preemption, the NEED_RESCHED flag will not have been cleared and the preemption check will trigger the call to preempt_schedule() again. Although the dynamic function tracer crashed immediately, the static version of the function tracer (CONFIG_DYNAMIC_FTRACE is not set) actually was able to show where the problem was. swapper-1 3.N.. 103885us : arch_local_save_flags <-preempt_schedule swapper-1 3.N.. 103886us : arch_local_save_flags <-preempt_schedule swapper-1 3.N.. 103886us : arch_local_save_flags <-preempt_schedule swapper-1 3.N.. 103887us : arch_local_save_flags <-preempt_schedule swapper-1 3.N.. 103887us : arch_local_save_flags <-preempt_schedule swapper-1 3.N.. 103888us : arch_local_save_flags <-preempt_schedule swapper-1 3.N.. 103888us : arch_local_save_flags <-preempt_schedule It went on for a while before it triple faulted with a corrupted stack. The arch_local_save_flags and arch_local_irq_* functions should not be traced. Even though they are marked as inline, gcc may still make them a function and enable tracing of them. The simple solution is to just mark them as notrace. I had to add the for this file to include the notrace tag. Signed-off-by: Steven Rostedt Link: http://lkml.kernel.org/r/20110702033852.733414762@goodmis.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/irqflags.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index 5745ce8bf108..bba3cf88e624 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -60,23 +60,24 @@ static inline void native_halt(void) #include #else #ifndef __ASSEMBLY__ +#include -static inline unsigned long arch_local_save_flags(void) +static inline notrace unsigned long arch_local_save_flags(void) { return native_save_fl(); } -static inline void arch_local_irq_restore(unsigned long flags) +static inline notrace void arch_local_irq_restore(unsigned long flags) { native_restore_fl(flags); } -static inline void arch_local_irq_disable(void) +static inline notrace void arch_local_irq_disable(void) { native_irq_disable(); } -static inline void arch_local_irq_enable(void) +static inline notrace void arch_local_irq_enable(void) { native_irq_enable(); } @@ -102,7 +103,7 @@ static inline void halt(void) /* * For spinlocks, etc: */ -static inline unsigned long arch_local_irq_save(void) +static inline notrace unsigned long arch_local_irq_save(void) { unsigned long flags = arch_local_save_flags(); arch_local_irq_disable(); -- cgit v1.2.1 From f91298709790b9a483752ca3c967845537df2af3 Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Sat, 9 Jul 2011 00:17:12 +0400 Subject: perf, x86: P4 PMU - Introduce event alias feature Instead of hw_nmi_watchdog_set_attr() weak function and appropriate x86_pmu::hw_watchdog_set_attr() call we introduce even alias mechanism which allow us to drop this routines completely and isolate quirks of Netburst architecture inside P4 PMU code only. The main idea remains the same though -- to allow nmi-watchdog and perf top run simultaneously. Note the aliasing mechanism applies to generic PERF_COUNT_HW_CPU_CYCLES event only because arbitrary event (say passed as RAW initially) might have some additional bits set inside ESCR register changing the behaviour of event and we can't guarantee anymore that alias event will give the same result. P.S. Thanks a huge to Don and Steven for for testing and early review. Acked-by: Don Zickus Tested-by: Steven Rostedt Signed-off-by: Cyrill Gorcunov CC: Ingo Molnar CC: Peter Zijlstra CC: Stephane Eranian CC: Lin Ming CC: Arnaldo Carvalho de Melo CC: Frederic Weisbecker Link: http://lkml.kernel.org/r/20110708201712.GS23657@sun Signed-off-by: Steven Rostedt --- arch/x86/include/asm/perf_event_p4.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h index 56fd9e3abbda..4d86c86178f2 100644 --- a/arch/x86/include/asm/perf_event_p4.h +++ b/arch/x86/include/asm/perf_event_p4.h @@ -101,6 +101,14 @@ #define P4_CONFIG_HT_SHIFT 63 #define P4_CONFIG_HT (1ULL << P4_CONFIG_HT_SHIFT) +/* + * If an event has alias it should be marked + * with a special bit. (Don't forget to check + * P4_PEBS_CONFIG_MASK and related bits on + * modification.) + */ +#define P4_CONFIG_ALIASABLE (1 << 9) + /* * The bits we allow to pass for RAW events */ @@ -123,6 +131,31 @@ (p4_config_pack_escr(P4_CONFIG_MASK_ESCR)) | \ (p4_config_pack_cccr(P4_CONFIG_MASK_CCCR)) +/* + * In case of event aliasing we need to preserve some + * caller bits otherwise the mapping won't be complete. + */ +#define P4_CONFIG_EVENT_ALIAS_MASK \ + (p4_config_pack_escr(P4_CONFIG_MASK_ESCR) | \ + p4_config_pack_cccr(P4_CCCR_EDGE | \ + P4_CCCR_THRESHOLD_MASK | \ + P4_CCCR_COMPLEMENT | \ + P4_CCCR_COMPARE)) + +#define P4_CONFIG_EVENT_ALIAS_IMMUTABLE_BITS \ + ((P4_CONFIG_HT) | \ + p4_config_pack_escr(P4_ESCR_T0_OS | \ + P4_ESCR_T0_USR | \ + P4_ESCR_T1_OS | \ + P4_ESCR_T1_USR) | \ + p4_config_pack_cccr(P4_CCCR_OVF | \ + P4_CCCR_CASCADE | \ + P4_CCCR_FORCE_OVF | \ + P4_CCCR_THREAD_ANY | \ + P4_CCCR_OVF_PMI_T0 | \ + P4_CCCR_OVF_PMI_T1 | \ + P4_CONFIG_ALIASABLE)) + static inline bool p4_is_event_cascaded(u64 config) { u32 cccr = p4_config_unpack_cccr(config); -- cgit v1.2.1 From f53173e47dee5f7514d264796bec58d43ed0f67f Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Thu, 21 Jul 2011 20:06:25 +0400 Subject: x86, perf: P4 PMU - Fix typos in comments and style cleanup This patch: - fixes typos in comments and clarifies the text - renames obscure p4_event_alias::original and ::alter members to ::original and ::alternative as appropriate - drops parenthesis from the return of p4_get_alias_event() No functional changes. Reported-by: Ingo Molnar Signed-off-by: Cyrill Gorcunov Link: http://lkml.kernel.org/r/20110721160625.GX7492@sun Signed-off-by: Ingo Molnar --- arch/x86/include/asm/perf_event_p4.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h index 4d86c86178f2..4f7e67e2345e 100644 --- a/arch/x86/include/asm/perf_event_p4.h +++ b/arch/x86/include/asm/perf_event_p4.h @@ -133,7 +133,7 @@ /* * In case of event aliasing we need to preserve some - * caller bits otherwise the mapping won't be complete. + * caller bits, otherwise the mapping won't be complete. */ #define P4_CONFIG_EVENT_ALIAS_MASK \ (p4_config_pack_escr(P4_CONFIG_MASK_ESCR) | \ -- cgit v1.2.1 From 1ac2e6ca44e13a087eb7438d284f887097ee7e84 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Tue, 7 Jun 2011 11:49:55 +0200 Subject: x86, perf: Make copy_from_user_nmi() a library function copy_from_user_nmi() is used in oprofile and perf. Moving it to other library functions like copy_from_user(). As this is x86 code for 32 and 64 bits, create a new file usercopy.c for unified code. Signed-off-by: Robert Richter Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110607172413.GJ20052@erda.amd.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/uaccess.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 99ddd148a760..36361bf6fdd1 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -555,6 +555,9 @@ struct __large_struct { unsigned long buf[100]; }; #endif /* CONFIG_X86_WP_WORKS_OK */ +extern unsigned long +copy_from_user_nmi(void *to, const void __user *from, unsigned long n); + /* * movsl can be slow when source and dest are not both 8-byte aligned */ -- cgit v1.2.1