From f20093eef5f7843a25adfc0512617d4b1ff1aa6e Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 24 Jan 2013 16:10:32 +0100 Subject: perf/x86: Add memory profiling via PEBS Load Latency This patch adds support for memory profiling using the PEBS Load Latency facility. Load accesses are sampled by HW and the instruction address, data address, load latency, data source, tlb, locked information can be saved in the sampling buffer if using the PERF_SAMPLE_COST (for latency), PERF_SAMPLE_ADDR, PERF_SAMPLE_DATA_SRC types. To enable PEBS Load Latency, users have to use the model specific event: - on NHM/WSM: MEM_INST_RETIRED:LATENCY_ABOVE_THRESHOLD - on SNB/IVB: MEM_TRANS_RETIRED:LATENCY_ABOVE_THRESHOLD To make things easier, this patch also exports a generic alias via sysfs: mem-loads. It export the right event encoding based on the host CPU and can be used directly by the perf tool. Loosely based on Intel's Lin Ming patch posted on LKML in July 2011. Signed-off-by: Stephane Eranian Cc: peterz@infradead.org Cc: ak@linux.intel.com Cc: acme@redhat.com Cc: jolsa@redhat.com Cc: namhyung.kim@lge.com Link: http://lkml.kernel.org/r/1359040242-8269-9-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar Signed-off-by: Arnaldo Carvalho de Melo --- arch/x86/include/uapi/asm/msr-index.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h index 892ce40a747..b31798d5e62 100644 --- a/arch/x86/include/uapi/asm/msr-index.h +++ b/arch/x86/include/uapi/asm/msr-index.h @@ -71,6 +71,7 @@ #define MSR_IA32_PEBS_ENABLE 0x000003f1 #define MSR_IA32_DS_AREA 0x00000600 #define MSR_IA32_PERF_CAPABILITIES 0x00000345 +#define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6 #define MSR_MTRRfix64K_00000 0x00000250 #define MSR_MTRRfix16K_80000 0x00000258 -- cgit v1.2.3-18-g5258 From 791eca10107f2886c1915d91c99a3b022a75909c Mon Sep 17 00:00:00 2001 From: Anton Arapov Date: Wed, 3 Apr 2013 18:00:33 +0200 Subject: uretprobes/x86: Hijack return address Hijack the return address and replace it with a trampoline address. Signed-off-by: Anton Arapov Acked-by: Srikar Dronamraju Signed-off-by: Oleg Nesterov --- arch/x86/include/asm/uprobes.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h index 8ff8be7835a..6e5197910fd 100644 --- a/arch/x86/include/asm/uprobes.h +++ b/arch/x86/include/asm/uprobes.h @@ -55,4 +55,5 @@ 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); +extern unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs); #endif /* _ASM_UPROBES_H */ -- cgit v1.2.3-18-g5258 From c43ca5091a374c1f6778bd7e4a39a5a10735a917 Mon Sep 17 00:00:00 2001 From: Jacob Shin Date: Fri, 19 Apr 2013 16:34:28 -0500 Subject: perf/x86/amd: Add support for AMD NB and L2I "uncore" counters Add support for AMD Family 15h [and above] northbridge performance counters. MSRs 0xc0010240 ~ 0xc0010247 are shared across all cores that share a common northbridge. Add support for AMD Family 16h L2 performance counters. MSRs 0xc0010230 ~ 0xc0010237 are shared across all cores that share a common L2 cache. We do not enable counter overflow interrupts. Sampling mode and per-thread events are not supported. Signed-off-by: Jacob Shin Cc: Arnaldo Carvalho de Melo Cc: Stephane Eranian Cc: Jiri Olsa Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20130419213428.GA8229@jshin-Toonie Signed-off-by: Ingo Molnar --- arch/x86/include/asm/cpufeature.h | 2 ++ arch/x86/include/uapi/asm/msr-index.h | 4 ++++ 2 files changed, 6 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 93fe929d1ce..ac10df72925 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -168,6 +168,7 @@ #define X86_FEATURE_TOPOEXT (6*32+22) /* topology extensions CPUID leafs */ #define X86_FEATURE_PERFCTR_CORE (6*32+23) /* core performance counter extensions */ #define X86_FEATURE_PERFCTR_NB (6*32+24) /* NB performance counter extensions */ +#define X86_FEATURE_PERFCTR_L2 (6*32+28) /* L2 performance counter extensions */ /* * Auxiliary flags: Linux defined - For features scattered in various @@ -311,6 +312,7 @@ extern const char * const x86_power_flags[32]; #define cpu_has_pclmulqdq boot_cpu_has(X86_FEATURE_PCLMULQDQ) #define cpu_has_perfctr_core boot_cpu_has(X86_FEATURE_PERFCTR_CORE) #define cpu_has_perfctr_nb boot_cpu_has(X86_FEATURE_PERFCTR_NB) +#define cpu_has_perfctr_l2 boot_cpu_has(X86_FEATURE_PERFCTR_L2) #define cpu_has_cx8 boot_cpu_has(X86_FEATURE_CX8) #define cpu_has_cx16 boot_cpu_has(X86_FEATURE_CX16) #define cpu_has_eager_fpu boot_cpu_has(X86_FEATURE_EAGER_FPU) diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h index bf7bb68f43a..b5757885d7a 100644 --- a/arch/x86/include/uapi/asm/msr-index.h +++ b/arch/x86/include/uapi/asm/msr-index.h @@ -196,6 +196,10 @@ #define MSR_AMD64_IBSBRTARGET 0xc001103b #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ +/* Fam 16h MSRs */ +#define MSR_F16H_L2I_PERF_CTL 0xc0010230 +#define MSR_F16H_L2I_PERF_CTR 0xc0010231 + /* Fam 15h MSRs */ #define MSR_F15H_PERF_CTL 0xc0010200 #define MSR_F15H_PERF_CTR 0xc0010201 -- cgit v1.2.3-18-g5258 From 5ac2b5c2721501a8f5c5e1cd4116cbc31ace6886 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 24 Apr 2013 09:26:30 +0200 Subject: perf/x86/intel/P4: Robistify P4 PMU types Linus found, while extending integer type extension checks in the sparse static code checker, various fragile patterns of mixed signed/unsigned 64-bit/32-bit integer use in perf_events_p4.c. The relevant hardware register ABI is 64 bit wide on 32-bit kernels as well, so clean it all up a bit, remove unnecessary casts, and make sure we use 64-bit unsigned integers in these places. [ Unfortunately this patch was not tested on real P4 hardware, those are pretty rare already. If this patch causes any problems on P4 hardware then please holler ... ] Reported-by: Linus Torvalds Signed-off-by: Ingo Molnar Cc: David Miller Cc: Theodore Ts'o Cc: Oleg Nesterov Cc: Frederic Weisbecker Cc: Cyrill Gorcunov Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20130424072630.GB1780@gmail.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/perf_event_p4.h | 62 ++++++++++++++++++------------------ 1 file changed, 31 insertions(+), 31 deletions(-) (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 4f7e67e2345..85e13ccf15c 100644 --- a/arch/x86/include/asm/perf_event_p4.h +++ b/arch/x86/include/asm/perf_event_p4.h @@ -24,45 +24,45 @@ #define ARCH_P4_CNTRVAL_MASK ((1ULL << ARCH_P4_CNTRVAL_BITS) - 1) #define ARCH_P4_UNFLAGGED_BIT ((1ULL) << (ARCH_P4_CNTRVAL_BITS - 1)) -#define P4_ESCR_EVENT_MASK 0x7e000000U +#define P4_ESCR_EVENT_MASK 0x7e000000ULL #define P4_ESCR_EVENT_SHIFT 25 -#define P4_ESCR_EVENTMASK_MASK 0x01fffe00U +#define P4_ESCR_EVENTMASK_MASK 0x01fffe00ULL #define P4_ESCR_EVENTMASK_SHIFT 9 -#define P4_ESCR_TAG_MASK 0x000001e0U +#define P4_ESCR_TAG_MASK 0x000001e0ULL #define P4_ESCR_TAG_SHIFT 5 -#define P4_ESCR_TAG_ENABLE 0x00000010U -#define P4_ESCR_T0_OS 0x00000008U -#define P4_ESCR_T0_USR 0x00000004U -#define P4_ESCR_T1_OS 0x00000002U -#define P4_ESCR_T1_USR 0x00000001U +#define P4_ESCR_TAG_ENABLE 0x00000010ULL +#define P4_ESCR_T0_OS 0x00000008ULL +#define P4_ESCR_T0_USR 0x00000004ULL +#define P4_ESCR_T1_OS 0x00000002ULL +#define P4_ESCR_T1_USR 0x00000001ULL #define P4_ESCR_EVENT(v) ((v) << P4_ESCR_EVENT_SHIFT) #define P4_ESCR_EMASK(v) ((v) << P4_ESCR_EVENTMASK_SHIFT) #define P4_ESCR_TAG(v) ((v) << P4_ESCR_TAG_SHIFT) -#define P4_CCCR_OVF 0x80000000U -#define P4_CCCR_CASCADE 0x40000000U -#define P4_CCCR_OVF_PMI_T0 0x04000000U -#define P4_CCCR_OVF_PMI_T1 0x08000000U -#define P4_CCCR_FORCE_OVF 0x02000000U -#define P4_CCCR_EDGE 0x01000000U -#define P4_CCCR_THRESHOLD_MASK 0x00f00000U +#define P4_CCCR_OVF 0x80000000ULL +#define P4_CCCR_CASCADE 0x40000000ULL +#define P4_CCCR_OVF_PMI_T0 0x04000000ULL +#define P4_CCCR_OVF_PMI_T1 0x08000000ULL +#define P4_CCCR_FORCE_OVF 0x02000000ULL +#define P4_CCCR_EDGE 0x01000000ULL +#define P4_CCCR_THRESHOLD_MASK 0x00f00000ULL #define P4_CCCR_THRESHOLD_SHIFT 20 -#define P4_CCCR_COMPLEMENT 0x00080000U -#define P4_CCCR_COMPARE 0x00040000U -#define P4_CCCR_ESCR_SELECT_MASK 0x0000e000U +#define P4_CCCR_COMPLEMENT 0x00080000ULL +#define P4_CCCR_COMPARE 0x00040000ULL +#define P4_CCCR_ESCR_SELECT_MASK 0x0000e000ULL #define P4_CCCR_ESCR_SELECT_SHIFT 13 -#define P4_CCCR_ENABLE 0x00001000U -#define P4_CCCR_THREAD_SINGLE 0x00010000U -#define P4_CCCR_THREAD_BOTH 0x00020000U -#define P4_CCCR_THREAD_ANY 0x00030000U -#define P4_CCCR_RESERVED 0x00000fffU +#define P4_CCCR_ENABLE 0x00001000ULL +#define P4_CCCR_THREAD_SINGLE 0x00010000ULL +#define P4_CCCR_THREAD_BOTH 0x00020000ULL +#define P4_CCCR_THREAD_ANY 0x00030000ULL +#define P4_CCCR_RESERVED 0x00000fffULL #define P4_CCCR_THRESHOLD(v) ((v) << P4_CCCR_THRESHOLD_SHIFT) #define P4_CCCR_ESEL(v) ((v) << P4_CCCR_ESCR_SELECT_SHIFT) #define P4_GEN_ESCR_EMASK(class, name, bit) \ - class##__##name = ((1 << bit) << P4_ESCR_EVENTMASK_SHIFT) + class##__##name = ((1ULL << bit) << P4_ESCR_EVENTMASK_SHIFT) #define P4_ESCR_EMASK_BIT(class, name) class##__##name /* @@ -107,7 +107,7 @@ * P4_PEBS_CONFIG_MASK and related bits on * modification.) */ -#define P4_CONFIG_ALIASABLE (1 << 9) +#define P4_CONFIG_ALIASABLE (1ULL << 9) /* * The bits we allow to pass for RAW events @@ -784,17 +784,17 @@ enum P4_ESCR_EMASKS { * Note we have UOP and PEBS bits reserved for now * just in case if we will need them once */ -#define P4_PEBS_CONFIG_ENABLE (1 << 7) -#define P4_PEBS_CONFIG_UOP_TAG (1 << 8) -#define P4_PEBS_CONFIG_METRIC_MASK 0x3f -#define P4_PEBS_CONFIG_MASK 0xff +#define P4_PEBS_CONFIG_ENABLE (1ULL << 7) +#define P4_PEBS_CONFIG_UOP_TAG (1ULL << 8) +#define P4_PEBS_CONFIG_METRIC_MASK 0x3FLL +#define P4_PEBS_CONFIG_MASK 0xFFLL /* * mem: Only counters MSR_IQ_COUNTER4 (16) and * MSR_IQ_COUNTER5 (17) are allowed for PEBS sampling */ -#define P4_PEBS_ENABLE 0x02000000U -#define P4_PEBS_ENABLE_UOP_TAG 0x01000000U +#define P4_PEBS_ENABLE 0x02000000ULL +#define P4_PEBS_ENABLE_UOP_TAG 0x01000000ULL #define p4_config_unpack_metric(v) (((u64)(v)) & P4_PEBS_CONFIG_METRIC_MASK) #define p4_config_unpack_pebs(v) (((u64)(v)) & P4_PEBS_CONFIG_MASK) -- cgit v1.2.3-18-g5258