diff options
author | Peter Zijlstra <a.p.zijlstra@chello.nl> | 2012-07-10 09:42:15 +0200 |
---|---|---|
committer | Ingo Molnar <mingo@kernel.org> | 2012-07-31 17:02:04 +0200 |
commit | d07bdfd322d307789f15b427dbcc39257665356f (patch) | |
tree | 1e9e06794e454202513ba133d7eafd1f1966553e /arch/x86/kernel/cpu/perf_event_intel_ds.c | |
parent | 7740dfc0363a70546ef25c0383aca252f95a91d2 (diff) | |
download | kernel_goldelico_gta04-d07bdfd322d307789f15b427dbcc39257665356f.zip kernel_goldelico_gta04-d07bdfd322d307789f15b427dbcc39257665356f.tar.gz kernel_goldelico_gta04-d07bdfd322d307789f15b427dbcc39257665356f.tar.bz2 |
perf/x86: Fix USER/KERNEL tagging of samples properly
Some PMUs don't provide a full register set for their sample,
specifically 'advanced' PMUs like AMD IBS and Intel PEBS which provide
'better' than regular interrupt accuracy.
In this case we use the interrupt regs as basis and over-write some
fields (typically IP) with different information.
The perf core however uses user_mode() to distinguish user/kernel
samples, user_mode() relies on regs->cs. If the interrupt skid pushed
us over a boundary the new IP might not be in the same domain as the
interrupt.
Commit ce5c1fe9a9e ("perf/x86: Fix USER/KERNEL tagging of samples")
tried to fix this by making the perf core use kernel_ip(). This
however is wrong (TM), as pointed out by Linus, since it doesn't allow
for VM86 and non-zero based segments in IA32 mode.
Therefore, provide a new helper to set the regs->ip field,
set_linear_ip(), which massages the regs into a suitable state
assuming the provided IP is in fact a linear address.
Also modify perf_instruction_pointer() and perf_callchain_user() to
deal with segments base offsets.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1341910954.3462.102.camel@twins
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'arch/x86/kernel/cpu/perf_event_intel_ds.c')
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel_ds.c | 7 |
1 files changed, 4 insertions, 3 deletions
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 629ae0b..e38d97b 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -499,7 +499,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) * We sampled a branch insn, rewind using the LBR stack */ if (ip == to) { - regs->ip = from; + set_linear_ip(regs, from); return 1; } @@ -529,7 +529,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) } while (to < ip); if (to == ip) { - regs->ip = old_to; + set_linear_ip(regs, old_to); return 1; } @@ -569,7 +569,8 @@ static void __intel_pmu_pebs_event(struct perf_event *event, * A possible PERF_SAMPLE_REGS will have to transfer all regs. */ regs = *iregs; - regs.ip = pebs->ip; + regs.flags = pebs->flags; + set_linear_ip(®s, pebs->ip); regs.bp = pebs->bp; regs.sp = pebs->sp; |