From 904cb3677f3adcd3d837be0a0d0b14251ba8d6f7 Mon Sep 17 00:00:00 2001 From: Aravind Gopalakrishnan Date: Mon, 10 Nov 2014 14:24:26 -0600 Subject: perf/x86/amd/ibs: Update IBS MSRs and feature definitions New Fam15h models carry extra feature bits and extend the MSR register space for IBS ops. Adding them here. While at it, add functionality to read IbsBrTarget and OpData4 depending on their availability if user wants a PERF_SAMPLE_RAW. Signed-off-by: Aravind Gopalakrishnan Acked-by: Borislav Petkov Cc: Paolo Bonzini Cc: Jan Kiszka Cc: Len Brown Cc: Fenghua Yu Cc: Peter Zijlstra Cc: Cc: Link: http://lkml.kernel.org/r/1415651066-13523-1-git-send-email-Aravind.Gopalakrishnan@amd.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/perf_event.h | 3 +++ arch/x86/include/uapi/asm/msr-index.h | 1 + arch/x86/kernel/cpu/perf_event_amd_ibs.c | 15 +++++++++++++++ 3 files changed, 19 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 8dfc9fd094a3..dc0f6ed35b08 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -177,6 +177,9 @@ struct x86_pmu_capability { #define IBS_CAPS_BRNTRGT (1U<<5) #define IBS_CAPS_OPCNTEXT (1U<<6) #define IBS_CAPS_RIPINVALIDCHK (1U<<7) +#define IBS_CAPS_OPBRNFUSE (1U<<8) +#define IBS_CAPS_FETCHCTLEXTD (1U<<9) +#define IBS_CAPS_OPDATA4 (1U<<10) #define IBS_CAPS_DEFAULT (IBS_CAPS_AVAIL \ | IBS_CAPS_FETCHSAM \ diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h index e21331ce368f..8f02f6990759 100644 --- a/arch/x86/include/uapi/asm/msr-index.h +++ b/arch/x86/include/uapi/asm/msr-index.h @@ -206,6 +206,7 @@ #define MSR_AMD64_IBSOP_REG_MASK ((1UL<offset_max, offset + 1); } while (offset < offset_max); + if (event->attr.sample_type & PERF_SAMPLE_RAW) { + /* + * Read IbsBrTarget and IbsOpData4 separately + * depending on their availability. + * Can't add to offset_max as they are staggered + */ + if (ibs_caps & IBS_CAPS_BRNTRGT) { + rdmsrl(MSR_AMD64_IBSBRTARGET, *buf++); + size++; + } + if (ibs_caps & IBS_CAPS_OPDATA4) { + rdmsrl(MSR_AMD64_IBSOPDATA4, *buf++); + size++; + } + } ibs_data.size = sizeof(u64) * size; regs = *iregs; -- cgit v1.2.3 From c0737ce453bdccd0d09aa4f916795533a4e02fef Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 3 Nov 2014 17:00:26 -0800 Subject: perf/x86/intel/uncore: Add scaling units to the EP iMC events Add scaling to MB/s to the memory controller read/write events for Sandy/IvyBridge/Haswell-EP similar to how the client does. This makes the events easier to use from the standard perf tool. Signed-off-by: Andi Kleen Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Link: http://lkml.kernel.org/r/1415062828-19759-2-git-send-email-andi@firstfloor.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c index f9ed429d6e4f..745b158e9a65 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c @@ -449,7 +449,11 @@ static struct attribute *snbep_uncore_qpi_formats_attr[] = { static struct uncore_event_desc snbep_uncore_imc_events[] = { INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x03"), + INTEL_UNCORE_EVENT_DESC(cas_count_read.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(cas_count_read.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"), + INTEL_UNCORE_EVENT_DESC(cas_count_write.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(cas_count_write.unit, "MiB"), { /* end: all zeroes */ }, }; @@ -2036,7 +2040,11 @@ static struct intel_uncore_type hswep_uncore_ha = { static struct uncore_event_desc hswep_uncore_imc_events[] = { INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x00,umask=0x00"), INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x03"), + INTEL_UNCORE_EVENT_DESC(cas_count_read.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(cas_count_read.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"), + INTEL_UNCORE_EVENT_DESC(cas_count_write.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(cas_count_write.unit, "MiB"), { /* end: all zeroes */ }, }; -- cgit v1.2.3 From 7550ddffe4c8040db31c66e5bd64531e2916bbf1 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 24 Sep 2014 07:34:46 -0700 Subject: perf/x86: Add INTEL_FLAGS_UEVENT_CONSTRAINT Add a FLAGS_UEVENT_CONSTRAINT macro that allows us to match on event+umask, and in additional all flags. This is needed to ensure the INV and CMASK fields are zero for specific events, as this can cause undefined behavior. Signed-off-by: Andi Kleen Signed-off-by: Peter Zijlstra (Intel) Cc: Kan Liang Cc: Maria Dimakopoulou Cc: Mark Davies Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1411569288-5627-1-git-send-email-andi@firstfloor.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index fc5eb390b368..4e6cdb0ddc70 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -253,6 +253,10 @@ struct cpu_hw_events { #define INTEL_UEVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK) +/* Like UEVENT_CONSTRAINT, but match flags too */ +#define INTEL_FLAGS_UEVENT_CONSTRAINT(c, n) \ + EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS) + #define INTEL_PLD_CONSTRAINT(c, n) \ __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT) -- cgit v1.2.3 From 0dbc94796d8714f78446245ef0f080d2c0b7ff0e Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 24 Sep 2014 07:34:47 -0700 Subject: perf/x86/intel: Use INTEL_FLAGS_UEVENT_CONSTRAINT for PRECDIST My earlier commit: 86a04461a99f ("perf/x86: Revamp PEBS event selection") made nearly all PEBS on Sandy/IvyBridge/Haswell to reject non zero flags. However this wasn't done for the INST_RETIRED.PREC_DIST event because no suitable macro existed. Now that we have INTEL_FLAGS_UEVENT_CONSTRAINT enforce zero flags for INST_RETIRED.PREC_DIST too. Signed-off-by: Andi Kleen Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Link: http://lkml.kernel.org/r/1411569288-5627-2-git-send-email-andi@firstfloor.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_intel_ds.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 46211bcc813e..12fe1dc6f875 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -606,7 +606,7 @@ struct event_constraint intel_westmere_pebs_event_constraints[] = { }; struct event_constraint intel_snb_pebs_event_constraints[] = { - INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */ INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ @@ -617,7 +617,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = { }; struct event_constraint intel_ivb_pebs_event_constraints[] = { - INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */ INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ @@ -628,7 +628,7 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = { }; struct event_constraint intel_hsw_pebs_event_constraints[] = { - INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ INTEL_PLD_CONSTRAINT(0x01cd, 0xf), /* MEM_TRANS_RETIRED.* */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), -- cgit v1.2.3 From af4bdcf675cf768dc3558682fc178e0e3e70bb52 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 24 Sep 2014 07:34:48 -0700 Subject: perf/x86/intel: Disallow flags for most Core2/Atom/Nehalem/Westmere events Disallow setting inv/cmask/etc. flags for all PEBS events on these CPUs, except for the UOPS_RETIRED.* events on Nehalem/Westmere, which are needed for cycles:p. This avoids an undefined situation strongly discouraged by the Intle SDM. The PLD_* events were already covered. This follows the earlier changes for Sandy Bridge and alter. Signed-off-by: Andi Kleen Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Link: http://lkml.kernel.org/r/1411569288-5627-3-git-send-email-andi@firstfloor.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_intel_ds.c | 52 +++++++++++++++---------------- 1 file changed, 26 insertions(+), 26 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 12fe1dc6f875..3c5d5c10b8a9 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -552,18 +552,18 @@ int intel_pmu_drain_bts_buffer(void) * PEBS */ struct event_constraint intel_core2_pebs_event_constraints[] = { - INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */ - INTEL_UEVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */ - INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */ - INTEL_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */ - INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ EVENT_CONSTRAINT_END }; struct event_constraint intel_atom_pebs_event_constraints[] = { - INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */ - INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */ - INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ EVENT_CONSTRAINT_END }; @@ -577,31 +577,31 @@ struct event_constraint intel_slm_pebs_event_constraints[] = { struct event_constraint intel_nehalem_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ - INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */ - INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INST_RETIRED.ANY */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xf), /* INST_RETIRED.ANY */ INTEL_EVENT_CONSTRAINT(0xc2, 0xf), /* UOPS_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ - INTEL_UEVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */ - INTEL_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */ - INTEL_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */ - INTEL_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ EVENT_CONSTRAINT_END }; struct event_constraint intel_westmere_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ - INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */ - INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INSTR_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xf), /* INSTR_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0xc2, 0xf), /* UOPS_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */ - INTEL_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */ - INTEL_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ EVENT_CONSTRAINT_END }; -- cgit v1.2.3 From aea48559ac454a065244d3eff0c94cc8af9c553e Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Wed, 24 Sep 2014 13:48:38 +0200 Subject: perf/x86: Add support for sampling PEBS machine state registers PEBS can capture machine state regs at retiremnt of the sampled instructions. When precise sampling is enabled on an event, PEBS is used, so substitute the interrupted state with the PEBS state. Note that not all registers are captured by PEBS. Those missing are replaced by the interrupt state counter-parts. Signed-off-by: Stephane Eranian Signed-off-by: Peter Zijlstra (Intel) Link: http://lkml.kernel.org/r/1411559322-16548-3-git-send-email-eranian@google.com Cc: cebbert.lkml@gmail.com Cc: jolsa@redhat.com Cc: Arnaldo Carvalho de Melo Cc: Linus Torvalds Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_intel_ds.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 3c5d5c10b8a9..495ae9793628 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -886,6 +886,29 @@ static void __intel_pmu_pebs_event(struct perf_event *event, regs.bp = pebs->bp; regs.sp = pebs->sp; + if (sample_type & PERF_SAMPLE_REGS_INTR) { + regs.ax = pebs->ax; + regs.bx = pebs->bx; + regs.cx = pebs->cx; + regs.dx = pebs->dx; + regs.si = pebs->si; + regs.di = pebs->di; + regs.bp = pebs->bp; + regs.sp = pebs->sp; + + regs.flags = pebs->flags; +#ifndef CONFIG_X86_32 + regs.r8 = pebs->r8; + regs.r9 = pebs->r9; + regs.r10 = pebs->r10; + regs.r11 = pebs->r11; + regs.r12 = pebs->r12; + regs.r13 = pebs->r13; + regs.r14 = pebs->r14; + regs.r15 = pebs->r15; +#endif + } + if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) { regs.ip = pebs->real_ip; regs.flags |= PERF_EFLAGS_EXACT; -- cgit v1.2.3 From d6d55f0b9d900673548515614b56ab55aa2c51f8 Mon Sep 17 00:00:00 2001 From: Jacob Shin Date: Thu, 29 May 2014 17:26:50 +0200 Subject: perf/x86/amd: AMD support for bp_len > HW_BREAKPOINT_LEN_8 Implement hardware breakpoint address mask for AMD Family 16h and above processors. CPUID feature bit indicates hardware support for DRn_ADDR_MASK MSRs. These masks further qualify DRn/DR7 hardware breakpoint addresses to allow matching of larger addresses ranges. Valuable advice and pseudo code from Oleg Nesterov Signed-off-by: Jacob Shin Signed-off-by: Suravee Suthikulpanit Acked-by: Jiri Olsa Reviewed-by: Oleg Nesterov Cc: Arnaldo Carvalho de Melo Cc: Ingo Molnar Cc: Namhyung Kim Cc: Peter Zijlstra Cc: xiakaixu Signed-off-by: Frederic Weisbecker --- arch/x86/include/asm/cpufeature.h | 2 ++ arch/x86/include/asm/debugreg.h | 5 +++++ arch/x86/include/asm/hw_breakpoint.h | 1 + arch/x86/include/uapi/asm/msr-index.h | 4 ++++ arch/x86/kernel/cpu/amd.c | 19 +++++++++++++++++++ arch/x86/kernel/hw_breakpoint.c | 20 ++++++++++++++++---- 6 files changed, 47 insertions(+), 4 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 0bb1335313b2..53966d65591e 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -174,6 +174,7 @@ #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_BPEXT (6*32+26) /* data breakpoint extension */ #define X86_FEATURE_PERFCTR_L2 ( 6*32+28) /* L2 performance counter extensions */ /* @@ -383,6 +384,7 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; #define cpu_has_cx16 boot_cpu_has(X86_FEATURE_CX16) #define cpu_has_eager_fpu boot_cpu_has(X86_FEATURE_EAGER_FPU) #define cpu_has_topoext boot_cpu_has(X86_FEATURE_TOPOEXT) +#define cpu_has_bpext boot_cpu_has(X86_FEATURE_BPEXT) #if __GNUC__ >= 4 extern void warn_pre_alternatives(void); diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index 61fd18b83b6c..12cb66f6d3a5 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -114,5 +114,10 @@ static inline void debug_stack_usage_inc(void) { } static inline void debug_stack_usage_dec(void) { } #endif /* X86_64 */ +#ifdef CONFIG_CPU_SUP_AMD +extern void set_dr_addr_mask(unsigned long mask, int dr); +#else +static inline void set_dr_addr_mask(unsigned long mask, int dr) { } +#endif #endif /* _ASM_X86_DEBUGREG_H */ diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h index ef1c4d2d41ec..6c98be864a75 100644 --- a/arch/x86/include/asm/hw_breakpoint.h +++ b/arch/x86/include/asm/hw_breakpoint.h @@ -12,6 +12,7 @@ */ struct arch_hw_breakpoint { unsigned long address; + unsigned long mask; u8 len; u8 type; }; diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h index 8f02f6990759..b1fb4fae03d3 100644 --- a/arch/x86/include/uapi/asm/msr-index.h +++ b/arch/x86/include/uapi/asm/msr-index.h @@ -212,6 +212,10 @@ /* Fam 16h MSRs */ #define MSR_F16H_L2I_PERF_CTL 0xc0010230 #define MSR_F16H_L2I_PERF_CTR 0xc0010231 +#define MSR_F16H_DR1_ADDR_MASK 0xc0011019 +#define MSR_F16H_DR2_ADDR_MASK 0xc001101a +#define MSR_F16H_DR3_ADDR_MASK 0xc001101b +#define MSR_F16H_DR0_ADDR_MASK 0xc0011027 /* Fam 15h MSRs */ #define MSR_F15H_PERF_CTL 0xc0010200 diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 813d29d00a17..abe4ec760db3 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -870,3 +870,22 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) return false; } + +void set_dr_addr_mask(unsigned long mask, int dr) +{ + if (!cpu_has_bpext) + return; + + switch (dr) { + case 0: + wrmsr(MSR_F16H_DR0_ADDR_MASK, mask, 0); + break; + case 1: + case 2: + case 3: + wrmsr(MSR_F16H_DR1_ADDR_MASK - 1 + dr, mask, 0); + break; + default: + break; + } +} diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 3d5fb509bdeb..b5cb0c59ea87 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -126,6 +126,8 @@ int arch_install_hw_breakpoint(struct perf_event *bp) *dr7 |= encode_dr7(i, info->len, info->type); set_debugreg(*dr7, 7); + if (info->mask) + set_dr_addr_mask(info->mask, i); return 0; } @@ -161,6 +163,8 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) *dr7 &= ~__encode_dr7(i, info->len, info->type); set_debugreg(*dr7, 7); + if (info->mask) + set_dr_addr_mask(0, i); } static int get_hbp_len(u8 hbp_len) @@ -277,6 +281,8 @@ static int arch_build_bp_info(struct perf_event *bp) } /* Len */ + info->mask = 0; + switch (bp->attr.bp_len) { case HW_BREAKPOINT_LEN_1: info->len = X86_BREAKPOINT_LEN_1; @@ -293,11 +299,17 @@ static int arch_build_bp_info(struct perf_event *bp) break; #endif default: - return -EINVAL; + if (!is_power_of_2(bp->attr.bp_len)) + return -EINVAL; + if (!cpu_has_bpext) + return -EOPNOTSUPP; + info->mask = bp->attr.bp_len - 1; + info->len = X86_BREAKPOINT_LEN_1; } return 0; } + /* * Validate the arch-specific HW Breakpoint register settings */ @@ -312,11 +324,11 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) if (ret) return ret; - ret = -EINVAL; - switch (info->len) { case X86_BREAKPOINT_LEN_1: align = 0; + if (info->mask) + align = info->mask; break; case X86_BREAKPOINT_LEN_2: align = 1; @@ -330,7 +342,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) break; #endif default: - return ret; + WARN_ON_ONCE(1); } /* -- cgit v1.2.3 From 36748b9518a2437beffe861b47dff6d12b736b3f Mon Sep 17 00:00:00 2001 From: Jacob Shin Date: Thu, 29 May 2014 17:26:53 +0200 Subject: perf/x86: Remove get_hbp_len and replace with bp_len Clean up the logic for determining the breakpoint length Signed-off-by: Jacob Shin Signed-off-by: Suravee Suthikulpanit Acked-by: Jiri Olsa Reviewed-by: Oleg Nesterov Cc: Arnaldo Carvalho de Melo Cc: Ingo Molnar Cc: Namhyung Kim Cc: Peter Zijlstra Cc: xiakaixu Signed-off-by: Frederic Weisbecker --- arch/x86/kernel/hw_breakpoint.c | 25 +------------------------ 1 file changed, 1 insertion(+), 24 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index b5cb0c59ea87..7114ba220fd4 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -167,29 +167,6 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) set_dr_addr_mask(0, i); } -static int get_hbp_len(u8 hbp_len) -{ - unsigned int len_in_bytes = 0; - - switch (hbp_len) { - case X86_BREAKPOINT_LEN_1: - len_in_bytes = 1; - break; - case X86_BREAKPOINT_LEN_2: - len_in_bytes = 2; - break; - case X86_BREAKPOINT_LEN_4: - len_in_bytes = 4; - break; -#ifdef CONFIG_X86_64 - case X86_BREAKPOINT_LEN_8: - len_in_bytes = 8; - break; -#endif - } - return len_in_bytes; -} - /* * Check for virtual address in kernel space. */ @@ -200,7 +177,7 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp) struct arch_hw_breakpoint *info = counter_arch_bp(bp); va = info->address; - len = get_hbp_len(info->len); + len = bp->attr.bp_len; return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE); } -- cgit v1.2.3