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
  ...
This commit is contained in:
Linus Torvalds
2013-07-02 16:15:23 -07:00
71 changed files with 2949 additions and 1055 deletions

View File

@@ -62,6 +62,29 @@
#define PME_PM_BRU_FIN 0x10068
#define PME_PM_BRU_MPRED 0x400f6
#define PME_PM_CMPLU_STALL_FXU 0x20014
#define PME_PM_CMPLU_STALL_DIV 0x40014
#define PME_PM_CMPLU_STALL_SCALAR 0x40012
#define PME_PM_CMPLU_STALL_SCALAR_LONG 0x20018
#define PME_PM_CMPLU_STALL_VECTOR 0x2001c
#define PME_PM_CMPLU_STALL_VECTOR_LONG 0x4004a
#define PME_PM_CMPLU_STALL_LSU 0x20012
#define PME_PM_CMPLU_STALL_REJECT 0x40016
#define PME_PM_CMPLU_STALL_ERAT_MISS 0x40018
#define PME_PM_CMPLU_STALL_DCACHE_MISS 0x20016
#define PME_PM_CMPLU_STALL_STORE 0x2004a
#define PME_PM_CMPLU_STALL_THRD 0x1001c
#define PME_PM_CMPLU_STALL_IFU 0x4004c
#define PME_PM_CMPLU_STALL_BRU 0x4004e
#define PME_PM_GCT_NOSLOT_IC_MISS 0x2001a
#define PME_PM_GCT_NOSLOT_BR_MPRED 0x4001a
#define PME_PM_GCT_NOSLOT_BR_MPRED_IC_MISS 0x4001c
#define PME_PM_GRP_CMPL 0x30004
#define PME_PM_1PLUS_PPC_CMPL 0x100f2
#define PME_PM_CMPLU_STALL_DFU 0x2003c
#define PME_PM_RUN_CYC 0x200f4
#define PME_PM_RUN_INST_CMPL 0x400fa
/*
* Layout of constraint bits:
* 6666555555555544444444443333333333222222222211111111110000000000
@@ -393,6 +416,31 @@ POWER_EVENT_ATTR(LD_MISS_L1, LD_MISS_L1);
POWER_EVENT_ATTR(BRU_FIN, BRU_FIN)
POWER_EVENT_ATTR(BRU_MPRED, BRU_MPRED);
POWER_EVENT_ATTR(CMPLU_STALL_FXU, CMPLU_STALL_FXU);
POWER_EVENT_ATTR(CMPLU_STALL_DIV, CMPLU_STALL_DIV);
POWER_EVENT_ATTR(CMPLU_STALL_SCALAR, CMPLU_STALL_SCALAR);
POWER_EVENT_ATTR(CMPLU_STALL_SCALAR_LONG, CMPLU_STALL_SCALAR_LONG);
POWER_EVENT_ATTR(CMPLU_STALL_VECTOR, CMPLU_STALL_VECTOR);
POWER_EVENT_ATTR(CMPLU_STALL_VECTOR_LONG, CMPLU_STALL_VECTOR_LONG);
POWER_EVENT_ATTR(CMPLU_STALL_LSU, CMPLU_STALL_LSU);
POWER_EVENT_ATTR(CMPLU_STALL_REJECT, CMPLU_STALL_REJECT);
POWER_EVENT_ATTR(CMPLU_STALL_ERAT_MISS, CMPLU_STALL_ERAT_MISS);
POWER_EVENT_ATTR(CMPLU_STALL_DCACHE_MISS, CMPLU_STALL_DCACHE_MISS);
POWER_EVENT_ATTR(CMPLU_STALL_STORE, CMPLU_STALL_STORE);
POWER_EVENT_ATTR(CMPLU_STALL_THRD, CMPLU_STALL_THRD);
POWER_EVENT_ATTR(CMPLU_STALL_IFU, CMPLU_STALL_IFU);
POWER_EVENT_ATTR(CMPLU_STALL_BRU, CMPLU_STALL_BRU);
POWER_EVENT_ATTR(GCT_NOSLOT_IC_MISS, GCT_NOSLOT_IC_MISS);
POWER_EVENT_ATTR(GCT_NOSLOT_BR_MPRED, GCT_NOSLOT_BR_MPRED);
POWER_EVENT_ATTR(GCT_NOSLOT_BR_MPRED_IC_MISS, GCT_NOSLOT_BR_MPRED_IC_MISS);
POWER_EVENT_ATTR(GRP_CMPL, GRP_CMPL);
POWER_EVENT_ATTR(1PLUS_PPC_CMPL, 1PLUS_PPC_CMPL);
POWER_EVENT_ATTR(CMPLU_STALL_DFU, CMPLU_STALL_DFU);
POWER_EVENT_ATTR(RUN_CYC, RUN_CYC);
POWER_EVENT_ATTR(RUN_INST_CMPL, RUN_INST_CMPL);
static struct attribute *power7_events_attr[] = {
GENERIC_EVENT_PTR(CYC),
GENERIC_EVENT_PTR(GCT_NOSLOT_CYC),
@@ -411,6 +459,31 @@ static struct attribute *power7_events_attr[] = {
POWER_EVENT_PTR(LD_MISS_L1),
POWER_EVENT_PTR(BRU_FIN),
POWER_EVENT_PTR(BRU_MPRED),
POWER_EVENT_PTR(CMPLU_STALL_FXU),
POWER_EVENT_PTR(CMPLU_STALL_DIV),
POWER_EVENT_PTR(CMPLU_STALL_SCALAR),
POWER_EVENT_PTR(CMPLU_STALL_SCALAR_LONG),
POWER_EVENT_PTR(CMPLU_STALL_VECTOR),
POWER_EVENT_PTR(CMPLU_STALL_VECTOR_LONG),
POWER_EVENT_PTR(CMPLU_STALL_LSU),
POWER_EVENT_PTR(CMPLU_STALL_REJECT),
POWER_EVENT_PTR(CMPLU_STALL_ERAT_MISS),
POWER_EVENT_PTR(CMPLU_STALL_DCACHE_MISS),
POWER_EVENT_PTR(CMPLU_STALL_STORE),
POWER_EVENT_PTR(CMPLU_STALL_THRD),
POWER_EVENT_PTR(CMPLU_STALL_IFU),
POWER_EVENT_PTR(CMPLU_STALL_BRU),
POWER_EVENT_PTR(GCT_NOSLOT_IC_MISS),
POWER_EVENT_PTR(GCT_NOSLOT_BR_MPRED),
POWER_EVENT_PTR(GCT_NOSLOT_BR_MPRED_IC_MISS),
POWER_EVENT_PTR(GRP_CMPL),
POWER_EVENT_PTR(1PLUS_PPC_CMPL),
POWER_EVENT_PTR(CMPLU_STALL_DFU),
POWER_EVENT_PTR(RUN_CYC),
POWER_EVENT_PTR(RUN_INST_CMPL),
NULL
};