summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorAndi Kleen <ak@linux.intel.com>2015-05-10 22:22:40 +0300
committerIngo Molnar <mingo@kernel.org>2015-08-04 11:16:56 +0300
commit2f7ebf2ec2a7b311318aae10b8373b0bd93001a7 (patch)
tree0ce9ba09a02e8fdcc30ac9fba2e2c254bdd5b610
parenta94cab2376cb35f236be14e2833cef63a8762a31 (diff)
downloadlinux-2f7ebf2ec2a7b311318aae10b8373b0bd93001a7.tar.xz
perf/x86/intel: Add support for PEBSv3 profiling
PEBSv3 is the same as the existing PEBSv2 used on Haswell, but it adds a new TSC field. Add support to the generic PEBS handler to handle the new format, and overwrite the perf time stamp using the new native_sched_clock_from_tsc(). Right now the time stamp is just slightly more accurate, as it is nearer the actual event trigger point. With the PEBS threshold > 1 patchkit it will be much more accurate, avoid the problems with MMAP mismatches earlier. The accurate time stamping is only implemented for the default trace clock for now. v2: Use _skl prefix. Check for default clock_id. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: eranian@google.com Link: http://lkml.kernel.org/r/1431285767-27027-3-git-send-email-andi@firstfloor.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c36
1 files changed, 33 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 71fc40238843..410270a9078f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -224,6 +224,19 @@ union hsw_tsx_tuning {
#define PEBS_HSW_TSX_FLAGS 0xff00000000ULL
+/* Same as HSW, plus TSC */
+
+struct pebs_record_skl {
+ u64 flags, ip;
+ u64 ax, bx, cx, dx;
+ u64 si, di, bp, sp;
+ u64 r8, r9, r10, r11;
+ u64 r12, r13, r14, r15;
+ u64 status, dla, dse, lat;
+ u64 real_ip, tsx_tuning;
+ u64 tsc;
+};
+
void init_debug_store_on_cpu(int cpu)
{
struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
@@ -885,7 +898,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
return 0;
}
-static inline u64 intel_hsw_weight(struct pebs_record_hsw *pebs)
+static inline u64 intel_hsw_weight(struct pebs_record_skl *pebs)
{
if (pebs->tsx_tuning) {
union hsw_tsx_tuning tsx = { .value = pebs->tsx_tuning };
@@ -894,7 +907,7 @@ static inline u64 intel_hsw_weight(struct pebs_record_hsw *pebs)
return 0;
}
-static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs)
+static inline u64 intel_hsw_transaction(struct pebs_record_skl *pebs)
{
u64 txn = (pebs->tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32;
@@ -918,7 +931,7 @@ static void setup_pebs_sample_data(struct perf_event *event,
* unconditionally access the 'extra' entries.
*/
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
- struct pebs_record_hsw *pebs = __pebs;
+ struct pebs_record_skl *pebs = __pebs;
u64 sample_type;
int fll, fst, dsrc;
int fl = event->hw.flags;
@@ -1016,6 +1029,16 @@ static void setup_pebs_sample_data(struct perf_event *event,
data->txn = intel_hsw_transaction(pebs);
}
+ /*
+ * v3 supplies an accurate time stamp, so we use that
+ * for the time stamp.
+ *
+ * We can only do this for the default trace clock.
+ */
+ if (x86_pmu.intel_cap.pebs_format >= 3 &&
+ event->attr.use_clockid == 0)
+ data->time = native_sched_clock_from_tsc(pebs->tsc);
+
if (has_branch_stack(event))
data->br_stack = &cpuc->lbr_stack;
}
@@ -1245,6 +1268,13 @@ void __init intel_ds_init(void)
x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
break;
+ case 3:
+ pr_cont("PEBS fmt3%c, ", pebs_type);
+ x86_pmu.pebs_record_size =
+ sizeof(struct pebs_record_skl);
+ x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
+ break;
+
default:
printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type);
x86_pmu.pebs = 0;