diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-07-03 12:40:46 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-07-03 12:40:46 -0700 |
commit | 7447d56217e215e50317f308aee1ed293ac4f749 (patch) | |
tree | 903832ecb206ae83160992c6aec40c624821941f /arch | |
parent | 892ad5acca0b2ddb514fae63fa4686bf726d2471 (diff) | |
parent | 23acd3e1a0a377cf3730ccb753aa1fdc50378396 (diff) |
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Ingo Molnar:
"Most of the changes are for tooling, the main changes in this cycle were:
- Improve Intel-PT hardware tracing support, both on the kernel and
on the tooling side: PTWRITE instruction support, power events for
C-state tracing, etc. (Adrian Hunter)
- Add support to measure SMI cost to the x86 architecture, with
tooling support in 'perf stat' (Kan Liang)
- Support function filtering in 'perf ftrace', plus related
improvements (Namhyung Kim)
- Allow adding and removing fields to the default 'perf script'
columns, using + or - as field prefixes to do so (Andi Kleen)
- Allow resolving the DSO name with 'perf script -F brstack{sym,off},dso'
(Mark Santaniello)
- Add perf tooling unwind support for PowerPC (Paolo Bonzini)
- ... and various other improvements as well"
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (84 commits)
perf auxtrace: Add CPU filter support
perf intel-pt: Do not use TSC packets for calculating CPU cycles to TSC
perf intel-pt: Update documentation to include new ptwrite and power events
perf intel-pt: Add example script for power events and PTWRITE
perf intel-pt: Synthesize new power and "ptwrite" events
perf intel-pt: Move code in intel_pt_synth_events() to simplify attr setting
perf intel-pt: Factor out intel_pt_set_event_name()
perf intel-pt: Tidy messages into called function intel_pt_synth_event()
perf intel-pt: Tidy Intel PT evsel lookup into separate function
perf intel-pt: Join needlessly wrapped lines
perf intel-pt: Remove unused instructions_sample_period
perf intel-pt: Factor out common code synthesizing event samples
perf script: Add synthesized Intel PT power and ptwrite events
perf/x86/intel: Constify the 'lbr_desc[]' array and make a function static
perf script: Add 'synth' field for synthesized event payloads
perf auxtrace: Add itrace option to output power events
perf auxtrace: Add itrace option to output ptwrite events
tools include: Add byte-swapping macros to kernel.h
perf script: Add 'synth' event type for synthesized events
x86/insn: perf tools: Add new ptwrite instruction
...
Diffstat (limited to 'arch')
-rw-r--r-- | arch/x86/events/core.c | 10 | ||||
-rw-r--r-- | arch/x86/events/intel/core.c | 63 | ||||
-rw-r--r-- | arch/x86/events/intel/lbr.c | 4 | ||||
-rw-r--r-- | arch/x86/events/perf_event.h | 3 | ||||
-rw-r--r-- | arch/x86/include/asm/msr-index.h | 2 | ||||
-rw-r--r-- | arch/x86/lib/x86-opcode-map.txt | 2 |
6 files changed, 81 insertions, 3 deletions
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 580b60f5ac83..e6f5e4b163ac 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1750,6 +1750,8 @@ ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event) return ret; } +static struct attribute_group x86_pmu_attr_group; + static int __init init_hw_perf_events(void) { struct x86_pmu_quirk *quirk; @@ -1813,6 +1815,14 @@ static int __init init_hw_perf_events(void) x86_pmu_events_group.attrs = tmp; } + if (x86_pmu.attrs) { + struct attribute **tmp; + + tmp = merge_attr(x86_pmu_attr_group.attrs, x86_pmu.attrs); + if (!WARN_ON(!tmp)) + x86_pmu_attr_group.attrs = tmp; + } + pr_info("... version: %d\n", x86_pmu.version); pr_info("... bit width: %d\n", x86_pmu.cntval_bits); pr_info("... generic registers: %d\n", x86_pmu.num_counters); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 110ce8238466..31acf2a98394 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3160,6 +3160,19 @@ err: return -ENOMEM; } +static void flip_smm_bit(void *data) +{ + unsigned long set = *(unsigned long *)data; + + if (set > 0) { + msr_set_bit(MSR_IA32_DEBUGCTLMSR, + DEBUGCTLMSR_FREEZE_IN_SMM_BIT); + } else { + msr_clear_bit(MSR_IA32_DEBUGCTLMSR, + DEBUGCTLMSR_FREEZE_IN_SMM_BIT); + } +} + static void intel_pmu_cpu_starting(int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); @@ -3174,6 +3187,8 @@ static void intel_pmu_cpu_starting(int cpu) cpuc->lbr_sel = NULL; + flip_smm_bit(&x86_pmu.attr_freeze_on_smi); + if (!cpuc->shared_regs) return; @@ -3595,6 +3610,52 @@ static struct attribute *hsw_events_attrs[] = { NULL }; +static ssize_t freeze_on_smi_show(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, "%lu\n", x86_pmu.attr_freeze_on_smi); +} + +static DEFINE_MUTEX(freeze_on_smi_mutex); + +static ssize_t freeze_on_smi_store(struct device *cdev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + unsigned long val; + ssize_t ret; + + ret = kstrtoul(buf, 0, &val); + if (ret) + return ret; + + if (val > 1) + return -EINVAL; + + mutex_lock(&freeze_on_smi_mutex); + + if (x86_pmu.attr_freeze_on_smi == val) + goto done; + + x86_pmu.attr_freeze_on_smi = val; + + get_online_cpus(); + on_each_cpu(flip_smm_bit, &val, 1); + put_online_cpus(); +done: + mutex_unlock(&freeze_on_smi_mutex); + + return count; +} + +static DEVICE_ATTR_RW(freeze_on_smi); + +static struct attribute *intel_pmu_attrs[] = { + &dev_attr_freeze_on_smi.attr, + NULL, +}; + __init int intel_pmu_init(void) { union cpuid10_edx edx; @@ -3641,6 +3702,8 @@ __init int intel_pmu_init(void) x86_pmu.max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, x86_pmu.num_counters); + + x86_pmu.attrs = intel_pmu_attrs; /* * Quirk: v2 perfmon does not report fixed-purpose events, so * assume at least 3 events, when not running in a hypervisor: diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index f924629836a8..eb261656a320 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -18,7 +18,7 @@ enum { LBR_FORMAT_MAX_KNOWN = LBR_FORMAT_TIME, }; -static enum { +static const enum { LBR_EIP_FLAGS = 1, LBR_TSX = 2, } lbr_desc[LBR_FORMAT_MAX_KNOWN + 1] = { @@ -287,7 +287,7 @@ inline u64 lbr_from_signext_quirk_wr(u64 val) /* * If quirk is needed, ensure sign extension is 61 bits: */ -u64 lbr_from_signext_quirk_rd(u64 val) +static u64 lbr_from_signext_quirk_rd(u64 val) { if (static_branch_unlikely(&lbr_from_quirk_key)) { /* diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index be3d36254040..53728eea1bed 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -562,6 +562,9 @@ struct x86_pmu { ssize_t (*events_sysfs_show)(char *page, u64 config); struct attribute **cpu_events; + unsigned long attr_freeze_on_smi; + struct attribute **attrs; + /* * CPU Hotplug hooks */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 673f9ac50f6d..18b162322eff 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -137,6 +137,8 @@ #define DEBUGCTLMSR_BTS_OFF_OS (1UL << 9) #define DEBUGCTLMSR_BTS_OFF_USR (1UL << 10) #define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI (1UL << 11) +#define DEBUGCTLMSR_FREEZE_IN_SMM_BIT 14 +#define DEBUGCTLMSR_FREEZE_IN_SMM (1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT) #define MSR_PEBS_FRONTEND 0x000003f7 diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index 767be7c76034..12e377184ee4 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -1009,7 +1009,7 @@ GrpTable: Grp15 1: fxstor | RDGSBASE Ry (F3),(11B) 2: vldmxcsr Md (v1) | WRFSBASE Ry (F3),(11B) 3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B) -4: XSAVE +4: XSAVE | ptwrite Ey (F3),(11B) 5: XRSTOR | lfence (11B) 6: XSAVEOPT | clwb (66) | mfence (11B) 7: clflush | clflushopt (66) | sfence (11B) |