perf/x86/intel: Add MSR_LAST_BRANCH_FROM_x quirk for ctx switch

Add quirk for context switch to save/restore the value of
MSR_LAST_BRANCH_FROM_x when LBR is enabled and there is potential for
kernel addresses to be in the lbr_from register.

To test this patch, use a perf tool and kernel with the patch
next in this series. That patch removes the work around that masked
the hw bug:

  $ ./lbr_perf record --call-graph lbr -e cycles:k sleep 1

where lbr_perf is the patched perf tool, that allows to specify :k
on lbr mode. The above command will trigger a #GPF :

 WARNING: CPU: 28 PID: 14096 at arch/x86/mm/extable.c:65 ex_handler_wrmsr_unsafe+0x70/0x80
 unchecked MSR access error: WRMSR to 0x681 (tried to write 0x1fffffff81010794)
 ...
 Call Trace:
  [<ffffffff8167af49>] dump_stack+0x4d/0x63
  [<ffffffff810b9b15>] __warn+0xe5/0x100
  [<ffffffff810b9be9>] warn_slowpath_fmt+0x49/0x50
  [<ffffffff810abb40>] ex_handler_wrmsr_unsafe+0x70/0x80
  [<ffffffff810abc42>] fixup_exception+0x42/0x50
  [<ffffffff81079d1a>] do_general_protection+0x8a/0x160
  [<ffffffff81684ec2>] general_protection+0x22/0x30
  [<ffffffff810101b9>] ? intel_pmu_lbr_sched_task+0xc9/0x380
  [<ffffffff81009d7c>] intel_pmu_sched_task+0x3c/0x60
  [<ffffffff81003a2b>] x86_pmu_sched_task+0x1b/0x20
  [<ffffffff81192a5b>] perf_pmu_sched_task+0x6b/0xb0
  [<ffffffff8119746d>] __perf_event_task_sched_in+0x7d/0x150
  [<ffffffff810dd9dc>] finish_task_switch+0x15c/0x200
  [<ffffffff8167f894>] __schedule+0x274/0x6cc
  [<ffffffff8167fdd9>] schedule+0x39/0x90
  [<ffffffff81675398>] exit_to_usermode_loop+0x39/0x89
  [<ffffffff810028ce>] prepare_exit_to_usermode+0x2e/0x30
  [<ffffffff81683c1b>] retint_user+0x8/0x10

Signed-off-by: David Carrillo-Cisneros <davidcc@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Stephane Eranian <eranian@google.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Link: http://lkml.kernel.org/r/1466533874-52003-5-git-send-email-davidcc@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 21 insertions, 3 deletions

diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 0da0eb0d875d..52bef15c7615 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -284,6 +284,20 @@ inline u64 lbr_from_signext_quirk_wr(u64 val)
         return val;
 }
 
+/*
+ * If quirk is needed, ensure sign extension is 61 bits:
+ */
+u64 lbr_from_signext_quirk_rd(u64 val)
+{
+        if (static_branch_unlikely(&lbr_from_quirk_key))
+                /*
+                 * Quirk is on when TSX is not enabled. Therefore TSX
+                 * flags must be read as OFF.
+                 */
+                val &= ~(LBR_FROM_FLAG_IN_TX | LBR_FROM_FLAG_ABORT);
+        return val;
+}
+
 static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 {
         int i;
@@ -300,7 +314,8 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
         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]);
+                wrmsrl(x86_pmu.lbr_from + lbr_idx,
+                        lbr_from_signext_quirk_wr(task_ctx->lbr_from[i]));
                 wrmsrl(x86_pmu.lbr_to + lbr_idx, task_ctx->lbr_to[i]);
                 if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
                         wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
@@ -313,7 +328,7 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 {
         int i;
         unsigned lbr_idx, mask;
-        u64 tos;
+        u64 tos, val;
 
         if (task_ctx->lbr_callstack_users == 0) {
                 task_ctx->lbr_stack_state = LBR_NONE;
@@ -324,7 +339,8 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
         tos = intel_pmu_lbr_tos();
         for (i = 0; i < tos; i++) {
                 lbr_idx = (tos - i) & mask;
-                rdmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]);
+                rdmsrl(x86_pmu.lbr_from + lbr_idx, val);
+                task_ctx->lbr_from[i] = lbr_from_signext_quirk_rd(val);
                 rdmsrl(x86_pmu.lbr_to + lbr_idx, task_ctx->lbr_to[i]);
                 if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
                         rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
@@ -502,6 +518,8 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
                 int lbr_flags = lbr_desc[lbr_format];
 
                 rdmsrl(x86_pmu.lbr_from + lbr_idx, from);
+                from = lbr_from_signext_quirk_rd(from);
+
                 rdmsrl(x86_pmu.lbr_to   + lbr_idx, to);
 
                 if (lbr_format == LBR_FORMAT_INFO && need_info) {