diff options
author | Peter Zijlstra <a.p.zijlstra@chello.nl> | 2010-03-03 13:12:23 +0100 |
---|---|---|
committer | Ingo Molnar <mingo@elte.hu> | 2010-03-10 13:23:32 +0100 |
commit | ef21f683a045a79b6aa86ad81e5fdfc0d5ddd250 (patch) | |
tree | ccf39f5051608c1eccac9171259c2d7bc381cc96 /arch/x86/kernel/cpu/perf_event_intel_ds.c | |
parent | caff2befffe899e63df5cc760b7ed01cfd902685 (diff) | |
download | kernel_samsung_smdk4412-ef21f683a045a79b6aa86ad81e5fdfc0d5ddd250.zip kernel_samsung_smdk4412-ef21f683a045a79b6aa86ad81e5fdfc0d5ddd250.tar.gz kernel_samsung_smdk4412-ef21f683a045a79b6aa86ad81e5fdfc0d5ddd250.tar.bz2 |
perf, x86: use LBR for PEBS IP+1 fixup
Use the LBR to fix up the PEBS IP+1 issue.
As said, PEBS reports the next instruction, here we use the LBR to find
the last branch and from that construct the actual IP. If the IP matches
the LBR-TO, we use LBR-FROM, otherwise we use the LBR-TO address as the
beginning of the last basic block and decode forward.
Once we find a match to the current IP, we use the previous location.
This patch introduces a new ABI element: PERF_RECORD_MISC_EXACT, which
conveys that the reported IP (PERF_SAMPLE_IP) is the exact instruction
that caused the event (barring CPU errata).
The fixup can fail due to various reasons:
1) LBR contains invalid data (quite possible)
2) part of the basic block got paged out
3) the reported IP isn't part of the basic block (see 1)
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: "Zhang, Yanmin" <yanmin_zhang@linux.intel.com>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.619375431@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'arch/x86/kernel/cpu/perf_event_intel_ds.c')
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel_ds.c | 84 |
1 files changed, 82 insertions, 2 deletions
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 0d994ef..50e6ff3 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -331,26 +331,32 @@ intel_pebs_constraints(struct perf_event *event) return &emptyconstraint; } -static void intel_pmu_pebs_enable(struct hw_perf_event *hwc) +static void intel_pmu_pebs_enable(struct perf_event *event) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; u64 val = cpuc->pebs_enabled; hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT; val |= 1ULL << hwc->idx; wrmsrl(MSR_IA32_PEBS_ENABLE, val); + + intel_pmu_lbr_enable(event); } -static void intel_pmu_pebs_disable(struct hw_perf_event *hwc) +static void intel_pmu_pebs_disable(struct perf_event *event) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; u64 val = cpuc->pebs_enabled; val &= ~(1ULL << hwc->idx); wrmsrl(MSR_IA32_PEBS_ENABLE, val); hwc->config |= ARCH_PERFMON_EVENTSEL_INT; + + intel_pmu_lbr_disable(event); } static void intel_pmu_pebs_enable_all(void) @@ -369,6 +375,70 @@ static void intel_pmu_pebs_disable_all(void) wrmsrl(MSR_IA32_PEBS_ENABLE, 0); } +#include <asm/insn.h> + +#define MAX_INSN_SIZE 16 + +static inline bool kernel_ip(unsigned long ip) +{ +#ifdef CONFIG_X86_32 + return ip > PAGE_OFFSET; +#else + return (long)ip < 0; +#endif +} + +static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + unsigned long from = cpuc->lbr_entries[0].from; + unsigned long old_to, to = cpuc->lbr_entries[0].to; + unsigned long ip = regs->ip; + + if (!cpuc->lbr_stack.nr || !from || !to) + return 0; + + if (ip < to) + return 0; + + /* + * We sampled a branch insn, rewind using the LBR stack + */ + if (ip == to) { + regs->ip = from; + return 1; + } + + do { + struct insn insn; + u8 buf[MAX_INSN_SIZE]; + void *kaddr; + + old_to = to; + if (!kernel_ip(ip)) { + int bytes, size = min_t(int, MAX_INSN_SIZE, ip - to); + + bytes = copy_from_user_nmi(buf, (void __user *)to, size); + if (bytes != size) + return 0; + + kaddr = buf; + } else + kaddr = (void *)to; + + kernel_insn_init(&insn, kaddr); + insn_get_length(&insn); + to += insn.length; + } while (to < ip); + + if (to == ip) { + regs->ip = old_to; + return 1; + } + + return 0; +} + static int intel_pmu_save_and_restart(struct perf_event *event); static void intel_pmu_disable_event(struct perf_event *event); @@ -424,6 +494,11 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) regs.bp = at->bp; regs.sp = at->sp; + if (intel_pmu_pebs_fixup_ip(®s)) + regs.flags |= PERF_EFLAGS_EXACT; + else + regs.flags &= ~PERF_EFLAGS_EXACT; + if (perf_event_overflow(event, 1, &data, ®s)) intel_pmu_disable_event(event); @@ -487,6 +562,11 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) regs.bp = at->bp; regs.sp = at->sp; + if (intel_pmu_pebs_fixup_ip(®s)) + regs.flags |= PERF_EFLAGS_EXACT; + else + regs.flags &= ~PERF_EFLAGS_EXACT; + if (perf_event_overflow(event, 1, &data, ®s)) intel_pmu_disable_event(event); } |