perf/x86: Fix LBR call stack save/restore

This fixes a bug I added in the following commit:

  90405aa02247 ("perf/x86/intel/lbr: Limit LBR accesses to TOS in callstack mode")

The bug could lead to lost LBR call stacks. When restoring the LBR state
we need to use the TOS of the previous context, not the current context.
To do that we need to save/restore the TOS.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: jolsa@kernel.org
Link: http://lkml.kernel.org/r/1445366797-30894-1-git-send-email-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 4 insertions, 1 deletions

diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 499f533dd3cc..ffa7a92025e1 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -627,6 +627,7 @@ struct x86_perf_task_context {
         u64 lbr_from[MAX_LBR_ENTRIES];
         u64 lbr_to[MAX_LBR_ENTRIES];
         u64 lbr_info[MAX_LBR_ENTRIES];
+        int tos;
         int lbr_callstack_users;
         int lbr_stack_state;
 };
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index bfd0b717e944..659f01e165d5 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -239,7 +239,7 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
         }
 
         mask = x86_pmu.lbr_nr - 1;
-        tos = intel_pmu_lbr_tos();
+        tos = task_ctx->tos;
         for (i = 0; i < tos; i++) {
                 lbr_idx = (tos - i) & mask;
                 wrmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]);
@@ -247,6 +247,7 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
                 if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
                         wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
         }
+        wrmsrl(x86_pmu.lbr_tos, tos);
         task_ctx->lbr_stack_state = LBR_NONE;
 }
 
@@ -270,6 +271,7 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
                 if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
                         rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
         }
+        task_ctx->tos = tos;
         task_ctx->lbr_stack_state = LBR_VALID;
 }