diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2013-07-02 16:15:23 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2013-07-02 16:15:23 -0700 |
commit | f0bb4c0ab064a8aeeffbda1cee380151a594eaab (patch) | |
tree | 14d55a89c5db455aa10ff9a96ca14c474a9c4d55 /arch/x86/kernel/cpu/perf_event_intel_lbr.c | |
parent | a4883ef6af5e513a1e8c2ab9aab721604aa3a4f5 (diff) | |
parent | 983433b5812c5cf33a9008fa38c6f9b407fedb76 (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:
"Kernel improvements:
- watchdog driver improvements by Li Zefan
- Power7 CPI stack events related improvements by Sukadev Bhattiprolu
- event multiplexing via hrtimers and other improvements by Stephane
Eranian
- kernel stack use optimization by Andrew Hunter
- AMD IOMMU uncore PMU support by Suravee Suthikulpanit
- NMI handling rate-limits by Dave Hansen
- various hw_breakpoint fixes by Oleg Nesterov
- hw_breakpoint overflow period sampling and related signal handling
fixes by Jiri Olsa
- Intel Haswell PMU support by Andi Kleen
Tooling improvements:
- Reset SIGTERM handler in workload child process, fix from David
Ahern.
- Makefile reorganization, prep work for Kconfig patches, from Jiri
Olsa.
- Add automated make test suite, from Jiri Olsa.
- Add --percent-limit option to 'top' and 'report', from Namhyung
Kim.
- Sorting improvements, from Namhyung Kim.
- Expand definition of sysfs format attribute, from Michael Ellerman.
Tooling fixes:
- 'perf tests' fixes from Jiri Olsa.
- Make Power7 CPI stack events available in sysfs, from Sukadev
Bhattiprolu.
- Handle death by SIGTERM in 'perf record', fix from David Ahern.
- Fix printing of perf_event_paranoid message, from David Ahern.
- Handle realloc failures in 'perf kvm', from David Ahern.
- Fix divide by 0 in variance, from David Ahern.
- Save parent pid in thread struct, from David Ahern.
- Handle JITed code in shared memory, from Andi Kleen.
- Fixes for 'perf diff', from Jiri Olsa.
- Remove some unused struct members, from Jiri Olsa.
- Add missing liblk.a dependency for python/perf.so, fix from Jiri
Olsa.
- Respect CROSS_COMPILE in liblk.a, from Rabin Vincent.
- No need to do locking when adding hists in perf report, only 'top'
needs that, from Namhyung Kim.
- Fix alignment of symbol column in in the hists browser (top,
report) when -v is given, from NAmhyung Kim.
- Fix 'perf top' -E option behavior, from Namhyung Kim.
- Fix bug in isupper() and islower(), from Sukadev Bhattiprolu.
- Fix compile errors in bp_signal 'perf test', from Sukadev
Bhattiprolu.
... and more things"
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (102 commits)
perf/x86: Disable PEBS-LL in intel_pmu_pebs_disable()
perf/x86: Fix shared register mutual exclusion enforcement
perf/x86/intel: Support full width counting
x86: Add NMI duration tracepoints
perf: Drop sample rate when sampling is too slow
x86: Warn when NMI handlers take large amounts of time
hw_breakpoint: Introduce "struct bp_cpuinfo"
hw_breakpoint: Simplify *register_wide_hw_breakpoint()
hw_breakpoint: Introduce cpumask_of_bp()
hw_breakpoint: Simplify the "weight" usage in toggle_bp_slot() paths
hw_breakpoint: Simplify list/idx mess in toggle_bp_slot() paths
perf/x86/intel: Add mem-loads/stores support for Haswell
perf/x86/intel: Support Haswell/v4 LBR format
perf/x86/intel: Move NMI clearing to end of PMI handler
perf/x86/intel: Add Haswell PEBS support
perf/x86/intel: Add simple Haswell PMU support
perf/x86/intel: Add Haswell PEBS record support
perf/x86/intel: Fix sparse warning
perf/x86/amd: AMD IOMMU Performance Counter PERF uncore PMU implementation
perf/x86/amd: Add IOMMU Performance Counter resource management
...
Diffstat (limited to 'arch/x86/kernel/cpu/perf_event_intel_lbr.c')
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel_lbr.c | 69 |
1 files changed, 54 insertions, 15 deletions
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index d978353c939..d5be06a5005 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -12,6 +12,16 @@ enum { LBR_FORMAT_LIP = 0x01, LBR_FORMAT_EIP = 0x02, LBR_FORMAT_EIP_FLAGS = 0x03, + LBR_FORMAT_EIP_FLAGS2 = 0x04, + LBR_FORMAT_MAX_KNOWN = LBR_FORMAT_EIP_FLAGS2, +}; + +static enum { + LBR_EIP_FLAGS = 1, + LBR_TSX = 2, +} lbr_desc[LBR_FORMAT_MAX_KNOWN + 1] = { + [LBR_FORMAT_EIP_FLAGS] = LBR_EIP_FLAGS, + [LBR_FORMAT_EIP_FLAGS2] = LBR_EIP_FLAGS | LBR_TSX, }; /* @@ -56,6 +66,8 @@ enum { LBR_FAR) #define LBR_FROM_FLAG_MISPRED (1ULL << 63) +#define LBR_FROM_FLAG_IN_TX (1ULL << 62) +#define LBR_FROM_FLAG_ABORT (1ULL << 61) #define for_each_branch_sample_type(x) \ for ((x) = PERF_SAMPLE_BRANCH_USER; \ @@ -81,9 +93,13 @@ enum { X86_BR_JMP = 1 << 9, /* jump */ X86_BR_IRQ = 1 << 10,/* hw interrupt or trap or fault */ X86_BR_IND_CALL = 1 << 11,/* indirect calls */ + X86_BR_ABORT = 1 << 12,/* transaction abort */ + X86_BR_IN_TX = 1 << 13,/* in transaction */ + X86_BR_NO_TX = 1 << 14,/* not in transaction */ }; #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL) +#define X86_BR_ANYTX (X86_BR_NO_TX | X86_BR_IN_TX) #define X86_BR_ANY \ (X86_BR_CALL |\ @@ -95,6 +111,7 @@ enum { X86_BR_JCC |\ X86_BR_JMP |\ X86_BR_IRQ |\ + X86_BR_ABORT |\ X86_BR_IND_CALL) #define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY) @@ -270,21 +287,31 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) for (i = 0; i < x86_pmu.lbr_nr; i++) { unsigned long lbr_idx = (tos - i) & mask; - u64 from, to, mis = 0, pred = 0; + u64 from, to, mis = 0, pred = 0, in_tx = 0, abort = 0; + int skip = 0; + int lbr_flags = lbr_desc[lbr_format]; rdmsrl(x86_pmu.lbr_from + lbr_idx, from); rdmsrl(x86_pmu.lbr_to + lbr_idx, to); - if (lbr_format == LBR_FORMAT_EIP_FLAGS) { + if (lbr_flags & LBR_EIP_FLAGS) { mis = !!(from & LBR_FROM_FLAG_MISPRED); pred = !mis; - from = (u64)((((s64)from) << 1) >> 1); + skip = 1; + } + if (lbr_flags & LBR_TSX) { + in_tx = !!(from & LBR_FROM_FLAG_IN_TX); + abort = !!(from & LBR_FROM_FLAG_ABORT); + skip = 3; } + from = (u64)((((s64)from) << skip) >> skip); cpuc->lbr_entries[i].from = from; cpuc->lbr_entries[i].to = to; cpuc->lbr_entries[i].mispred = mis; cpuc->lbr_entries[i].predicted = pred; + cpuc->lbr_entries[i].in_tx = in_tx; + cpuc->lbr_entries[i].abort = abort; cpuc->lbr_entries[i].reserved = 0; } cpuc->lbr_stack.nr = i; @@ -310,7 +337,7 @@ void intel_pmu_lbr_read(void) * - in case there is no HW filter * - in case the HW filter has errata or limitations */ -static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event) +static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event) { u64 br_type = event->attr.branch_sample_type; int mask = 0; @@ -318,11 +345,8 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event) if (br_type & PERF_SAMPLE_BRANCH_USER) mask |= X86_BR_USER; - if (br_type & PERF_SAMPLE_BRANCH_KERNEL) { - if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN)) - return -EACCES; + if (br_type & PERF_SAMPLE_BRANCH_KERNEL) mask |= X86_BR_KERNEL; - } /* we ignore BRANCH_HV here */ @@ -337,13 +361,21 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event) if (br_type & PERF_SAMPLE_BRANCH_IND_CALL) mask |= X86_BR_IND_CALL; + + if (br_type & PERF_SAMPLE_BRANCH_ABORT_TX) + mask |= X86_BR_ABORT; + + if (br_type & PERF_SAMPLE_BRANCH_IN_TX) + mask |= X86_BR_IN_TX; + + if (br_type & PERF_SAMPLE_BRANCH_NO_TX) + mask |= X86_BR_NO_TX; + /* * stash actual user request into reg, it may * be used by fixup code for some CPU */ event->hw.branch_reg.reg = mask; - - return 0; } /* @@ -391,9 +423,7 @@ int intel_pmu_setup_lbr_filter(struct perf_event *event) /* * setup SW LBR filter */ - ret = intel_pmu_setup_sw_lbr_filter(event); - if (ret) - return ret; + intel_pmu_setup_sw_lbr_filter(event); /* * setup HW LBR filter, if any @@ -415,7 +445,7 @@ int intel_pmu_setup_lbr_filter(struct perf_event *event) * decoded (e.g., text page not present), then X86_BR_NONE is * returned. */ -static int branch_type(unsigned long from, unsigned long to) +static int branch_type(unsigned long from, unsigned long to, int abort) { struct insn insn; void *addr; @@ -435,6 +465,9 @@ static int branch_type(unsigned long from, unsigned long to) if (from == 0 || to == 0) return X86_BR_NONE; + if (abort) + return X86_BR_ABORT | to_plm; + if (from_plm == X86_BR_USER) { /* * can happen if measuring at the user level only @@ -581,7 +614,13 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc) from = cpuc->lbr_entries[i].from; to = cpuc->lbr_entries[i].to; - type = branch_type(from, to); + type = branch_type(from, to, cpuc->lbr_entries[i].abort); + if (type != X86_BR_NONE && (br_sel & X86_BR_ANYTX)) { + if (cpuc->lbr_entries[i].in_tx) + type |= X86_BR_IN_TX; + else + type |= X86_BR_NO_TX; + } /* if type does not correspond, then discard */ if (type == X86_BR_NONE || (br_sel & type) != type) { |