summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/cpu/perf_event_intel_ds.c
diff options
context:
space:
mode:
authorDaniel Vetter <daniel.vetter@ffwll.ch>2015-11-23 09:04:05 +0100
committerDaniel Vetter <daniel.vetter@ffwll.ch>2015-11-23 09:04:05 +0100
commit92907cbbef8625bb3998d1eb385fc88f23c97a3f (patch)
tree15626ff9287e37c3cb81c7286d6db5a7fd77c854 /arch/x86/kernel/cpu/perf_event_intel_ds.c
parent15fbfccfe92c62ae8d1ecc647c44157ed01ac02e (diff)
parent1ec218373b8ebda821aec00bb156a9c94fad9cd4 (diff)
Merge tag 'v4.4-rc2' into drm-intel-next-queued
Linux 4.4-rc2 Backmerge to get at commit 1b0e3a049efe471c399674fd954500ce97438d30 Author: Imre Deak <imre.deak@intel.com> Date: Thu Nov 5 23:04:11 2015 +0200 drm/i915/skl: disable display side power well support for now so that we can proplery re-eanble skl power wells in -next. Conflicts are just adjacent lines changed, except for intel_fbdev.c where we need to interleave the changs. Nothing nefarious. Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Diffstat (limited to 'arch/x86/kernel/cpu/perf_event_intel_ds.c')
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c40
1 files changed, 34 insertions, 6 deletions
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 84f236ab96b0..5db1c7755548 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -510,10 +510,11 @@ int intel_pmu_drain_bts_buffer(void)
u64 flags;
};
struct perf_event *event = cpuc->events[INTEL_PMC_IDX_FIXED_BTS];
- struct bts_record *at, *top;
+ struct bts_record *at, *base, *top;
struct perf_output_handle handle;
struct perf_event_header header;
struct perf_sample_data data;
+ unsigned long skip = 0;
struct pt_regs regs;
if (!event)
@@ -522,10 +523,10 @@ int intel_pmu_drain_bts_buffer(void)
if (!x86_pmu.bts_active)
return 0;
- at = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
- top = (struct bts_record *)(unsigned long)ds->bts_index;
+ base = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
+ top = (struct bts_record *)(unsigned long)ds->bts_index;
- if (top <= at)
+ if (top <= base)
return 0;
memset(&regs, 0, sizeof(regs));
@@ -535,16 +536,43 @@ int intel_pmu_drain_bts_buffer(void)
perf_sample_data_init(&data, 0, event->hw.last_period);
/*
+ * BTS leaks kernel addresses in branches across the cpl boundary,
+ * such as traps or system calls, so unless the user is asking for
+ * kernel tracing (and right now it's not possible), we'd need to
+ * filter them out. But first we need to count how many of those we
+ * have in the current batch. This is an extra O(n) pass, however,
+ * it's much faster than the other one especially considering that
+ * n <= 2560 (BTS_BUFFER_SIZE / BTS_RECORD_SIZE * 15/16; see the
+ * alloc_bts_buffer()).
+ */
+ for (at = base; at < top; at++) {
+ /*
+ * Note that right now *this* BTS code only works if
+ * attr::exclude_kernel is set, but let's keep this extra
+ * check here in case that changes.
+ */
+ if (event->attr.exclude_kernel &&
+ (kernel_ip(at->from) || kernel_ip(at->to)))
+ skip++;
+ }
+
+ /*
* Prepare a generic sample, i.e. fill in the invariant fields.
* We will overwrite the from and to address before we output
* the sample.
*/
perf_prepare_sample(&header, &data, event, &regs);
- if (perf_output_begin(&handle, event, header.size * (top - at)))
+ if (perf_output_begin(&handle, event, header.size *
+ (top - base - skip)))
return 1;
- for (; at < top; at++) {
+ for (at = base; at < top; at++) {
+ /* Filter out any records that contain kernel addresses. */
+ if (event->attr.exclude_kernel &&
+ (kernel_ip(at->from) || kernel_ip(at->to)))
+ continue;
+
data.ip = at->from;
data.addr = at->to;