lkml.org 
[lkml]   [2019]   [Oct]   [23]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Subject[PATCH v5 4/4] perf/core,x86: synchronize PMU task contexts on optimized context switches
From
Date

Install Intel specific PMU task context synchronization adapter and
extend optimized context switch path with PMU specific task context
synchronization to fix LBR callstack virtualization on context switches.

Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com>
---
arch/x86/events/intel/core.c | 7 +++++++
kernel/events/core.c | 13 ++++++++++++-
2 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index bbf6588d47ee..dc64b16e6b71 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3820,6 +3820,12 @@ static void intel_pmu_sched_task(struct perf_event_context *ctx,
intel_pmu_lbr_sched_task(ctx, sched_in);
}

+static void intel_pmu_swap_task_ctx(struct perf_event_context *prev,
+ struct perf_event_context *next)
+{
+ intel_pmu_lbr_swap_task_ctx(prev, next);
+}
+
static int intel_pmu_check_period(struct perf_event *event, u64 value)
{
return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0;
@@ -3955,6 +3961,7 @@ static __initconst const struct x86_pmu intel_pmu = {

.guest_get_msrs = intel_guest_get_msrs,
.sched_task = intel_pmu_sched_task,
+ .swap_task_ctx = intel_pmu_swap_task_ctx,

.check_period = intel_pmu_check_period,

diff --git a/kernel/events/core.c b/kernel/events/core.c
index f9a5d4356562..ed31aa849161 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3204,10 +3204,21 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
raw_spin_lock(&ctx->lock);
raw_spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING);
if (context_equiv(ctx, next_ctx)) {
+ struct pmu *pmu = ctx->pmu;
+
WRITE_ONCE(ctx->task, next);
WRITE_ONCE(next_ctx->task, task);

- swap(ctx->task_ctx_data, next_ctx->task_ctx_data);
+ /*
+ * PMU specific parts of task perf context can require
+ * additional synchronization. As an example of such
+ * synchronization see implementation details of Intel
+ * LBR call stack data profiling;
+ */
+ if (pmu->swap_task_ctx)
+ pmu->swap_task_ctx(ctx, next_ctx);
+ else
+ swap(ctx->task_ctx_data, next_ctx->task_ctx_data);

/*
* RCU_INIT_POINTER here is safe because we've not
--
2.20.1
\
 
 \ /
  Last update: 2019-10-23 09:14    [W:0.075 / U:2.452 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site