This patch removes a redundant store on regs->flags introduced
by commit:
71eb9ee9596d ("perf/x86/intel: Fix linear IP of PEBS real_ip on Haswell and later CPUs")
We were clearing the PERF_EFLAGS_EXACT but it was overwritten by
regs->flags = pebs->flags later on.
The PERF_EFLAGS_EXACT is a software flag using bit 3 of regs->flags.
X86 marks this bit as Reserved. To make sure this bit is zero before
we do any IP processing, we clear it explicitly.
Patch also removes the following assignment:
regs->flags = pebs->flags | (regs->flags & PERF_EFLAGS_VM);
Because there is no regs->flags to preserve anymore because
set_linear_ip() is not called until later.
Patch also clarifies comment for intel_pmu_pebs_fixup_ip().
Signed-off-by: Stephane Eranian <[email protected]>
---
arch/x86/events/intel/ds.c | 23 ++++++++++++++---------
1 file changed, 14 insertions(+), 9 deletions(-)
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index da6780122786..41b44a4fff51 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1153,7 +1153,6 @@ static void setup_pebs_sample_data(struct perf_event *event,
if (pebs == NULL)
return;
- regs->flags &= ~PERF_EFLAGS_EXACT;
sample_type = event->attr.sample_type;
dsrc = sample_type & PERF_SAMPLE_DATA_SRC;
@@ -1197,7 +1196,13 @@ static void setup_pebs_sample_data(struct perf_event *event,
* and PMI.
*/
*regs = *iregs;
- regs->flags = pebs->flags;
+
+ /*
+ * initialize regs_>flags from pebs
+ * clear exact bit (which uses Reserved bit 3),
+ * i.e, do not rely on it being zero.
+ */
+ regs->flags = pebs->flags & ~PERF_EFLAGS_EXACT;
if (sample_type & PERF_SAMPLE_REGS_INTR) {
regs->ax = pebs->ax;
@@ -1217,10 +1222,6 @@ static void setup_pebs_sample_data(struct perf_event *event,
regs->sp = pebs->sp;
}
- /*
- * Preserve PERF_EFLAGS_VM from set_linear_ip().
- */
- regs->flags = pebs->flags | (regs->flags & PERF_EFLAGS_VM);
#ifndef CONFIG_X86_32
regs->r8 = pebs->r8;
regs->r9 = pebs->r9;
@@ -1234,15 +1235,19 @@ static void setup_pebs_sample_data(struct perf_event *event,
}
if (event->attr.precise_ip > 1) {
- /* Haswell and later have the eventing IP, so use it: */
+ /* Haswell and later have the eventing IP, so use it */
if (x86_pmu.intel_cap.pebs_format >= 2) {
set_linear_ip(regs, pebs->real_ip);
regs->flags |= PERF_EFLAGS_EXACT;
} else {
- /* Otherwise use PEBS off-by-1 IP: */
+ /* Otherwise use PEBS off-by-1 IP */
set_linear_ip(regs, pebs->ip);
- /* ... and try to fix it up using the LBR entries: */
+ /*
+ * ... and try to fix it up using the LBR entries
+ * if successful, regs->ip modified and regs patch
+ * via set_linear_ip()
+ */
if (intel_pmu_pebs_fixup_ip(regs))
regs->flags |= PERF_EFLAGS_EXACT;
}
--
2.7.4
* Stephane Eranian <[email protected]> wrote:
> This patch removes a redundant store on regs->flags introduced
> by commit:
>
> 71eb9ee9596d ("perf/x86/intel: Fix linear IP of PEBS real_ip on Haswell and later CPUs")
>
> We were clearing the PERF_EFLAGS_EXACT but it was overwritten by
> regs->flags = pebs->flags later on.
>
> The PERF_EFLAGS_EXACT is a software flag using bit 3 of regs->flags.
> X86 marks this bit as Reserved. To make sure this bit is zero before
> we do any IP processing, we clear it explicitly.
>
> Patch also removes the following assignment:
> regs->flags = pebs->flags | (regs->flags & PERF_EFLAGS_VM);
>
> Because there is no regs->flags to preserve anymore because
> set_linear_ip() is not called until later.
>
> Patch also clarifies comment for intel_pmu_pebs_fixup_ip().
>
> Signed-off-by: Stephane Eranian <[email protected]>
> ---
> arch/x86/events/intel/ds.c | 23 ++++++++++++++---------
> 1 file changed, 14 insertions(+), 9 deletions(-)
>
> diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
> index da6780122786..41b44a4fff51 100644
> --- a/arch/x86/events/intel/ds.c
> +++ b/arch/x86/events/intel/ds.c
> @@ -1153,7 +1153,6 @@ static void setup_pebs_sample_data(struct perf_event *event,
> if (pebs == NULL)
> return;
>
> - regs->flags &= ~PERF_EFLAGS_EXACT;
> sample_type = event->attr.sample_type;
> dsrc = sample_type & PERF_SAMPLE_DATA_SRC;
>
> @@ -1197,7 +1196,13 @@ static void setup_pebs_sample_data(struct perf_event *event,
> * and PMI.
> */
> *regs = *iregs;
> - regs->flags = pebs->flags;
> +
> + /*
> + * initialize regs_>flags from pebs
> + * clear exact bit (which uses Reserved bit 3),
> + * i.e, do not rely on it being zero.
> + */
> + regs->flags = pebs->flags & ~PERF_EFLAGS_EXACT;
Please use consistent capitalization and spelling to make comments more readable:
s/initialize
/Initialize
s/pebs
/PEBS
s/i.e
/i.e.
Also, please put a comma after 'PEBS', to make it more clear what the sentence
says.
> - /* Haswell and later have the eventing IP, so use it: */
> + /* Haswell and later have the eventing IP, so use it */
So that's a step backwards in readability ...
> - /* Otherwise use PEBS off-by-1 IP: */
> + /* Otherwise use PEBS off-by-1 IP */
Ditto.
> set_linear_ip(regs, pebs->ip);
>
> - /* ... and try to fix it up using the LBR entries: */
> + /*
> + * ... and try to fix it up using the LBR entries
> + * if successful, regs->ip modified and regs patch
> + * via set_linear_ip()
> + */
> if (intel_pmu_pebs_fixup_ip(regs))
> regs->flags |= PERF_EFLAGS_EXACT;
And it's unclear to me what this tries to say:
"try to fix it up using the LBR entries if successful",
or:
"try to fix it up using the LBR entries, and if successful, regs->ip modified
and regs patch via set_linear_ip()",
?
Please improve readability.
Thanks,
Ingo