perf/x86/lbr: Enable the branch type for the Arch LBR by default
Subsystems (3)
PATCH 1/2 perf/x86/lbr: Enable the branch type for the Arch LBR by default
From: Kan Liang <[email protected]>
On the platform with Arch LBR, the HW raw branch type encoding may leak to the perf tool when the SAVE_TYPE option is not set.
In the intel_pmu_store_lbr(), the HW raw branch type is stored in lbr_entries[].type. If the SAVE_TYPE option is set, the lbr_entries[].type will be converted into the generic PERF_BR_* type in the intel_pmu_lbr_filter() and exposed to the user tools. But if the SAVE_TYPE option is NOT set by the user, the current perf kernel doesn't clear the field. The HW raw branch type leaks.
There are two solutions to fix the issue for the Arch LBR. One is to clear the field if the SAVE_TYPE option is NOT set. The other solution is to unconditionally convert the branch type and expose the generic type to the user tools.
The latter is implemented here, because
- The branch type is valuable information. I don't see a case where you would not benefit from the branch type. (Stephane Eranian)
- Not having the branch type DOES NOT save any space in the branch record (Stephane Eranian)
- The Arch LBR HW can retrieve the common branch types from the LBR_INFO. It doesn't require the high overhead SW disassemble.
--- arch/x86/events/intel/lbr.c | 8 ++++++++ 1 file changed, 8 insertions(+)
arch/x86/events/intel/lbr.c +8 -0
@@ -1149,6 +1149,14 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)if (static_cpu_has (X86_FEATURE_ARCH_LBR )) { reg->config = mask; + +/* +* The Arch LBR HW can retrieve the common branch types +* from the LBR_INFO. It doesn't require the high overhead +* SW disassemble. +* Enable the branch type by default for the Arch LBR. +*/ + reg->reg |=X86_BR_TYPE_SAVE ;return 0 ; }
Signature · 1 line
2.35.1
PATCH 2/2 perf docs: Update the documentation for the save_type filter
From: Kan Liang <[email protected]>
Update the documentation to reflect the kernel changes.
--- tools/perf/Documentation/perf-record.txt | 3 +++ 1 file changed, 3 insertions(+)
tools/perf/Documentation/perf-record.txt +3 -0
@@ -397,6 +397,9 @@ following filters are defined: - abort_tx: only when the target is a hardware transaction abort - cond: conditional branches - save_type: save branch type during sampling in case binary is not available later + For the platforms with Intel Arch LBR support (12th-Gen+ client or + 4th-Gen Xeon+ server), the save branch type is unconditionally enabled + when the taken branch stack sampling is enabled. + The option requires at least one branch type among any, any_call, any_ret, ind_call, cond.
Signature · 1 line
2.35.1
Re: [PATCH 2/2] perf docs: Update the documentation for the save_type filter
Hi Arnaldo,
The kernel change has been merged into the tip perf/urgent branch.
Do you have any comments for the patch?
If it's OK for you, could you please pull this patch?
Thanks,
Kan
Quoted 23 lines · On 2022-08-16 8:56 a.m., [email protected] wrote:
From: Kan Liang <[email protected]>
Update the documentation to reflect the kernel changes.
Signed-off-by Kan Liang <[email protected]>--- tools/perf/Documentation/perf-record.txt | 3 +++ 1 file changed, 3 insertions(+)tools/perf/Documentation/perf-record.txt +3
-0@@ -397,6 +397,9 @@ following filters are defined: - abort_tx: only when the target is a hardware transaction abort - cond: conditional branches - save_type: save branch type during sampling in case binary is not available later + For the platforms with Intel Arch LBR support (12th-Gen+ client or + 4th-Gen Xeon+ server), the save branch type is unconditionally enabled + when the taken branch stack sampling is enabled. + The option requires at least one branch type among any, any_call, any_ret, ind_call, cond.
The following commit has been merged into the perf/urgent branch of tip:
The following commit has been merged into the perf/urgent branch of tip:
Commit-ID: 32ba156df1b1c8804a4e5be5339616945eafea22 Gitweb: https://git.kernel.org/tip/32ba156df1b1c8804a4e5be5339616945eafea22 Author: Kan Liang <[email protected]> AuthorDate: Tue, 16 Aug 2022 05:56:11 -07:00 Committer: Peter Zijlstra <[email protected]> CommitterDate: Fri, 19 Aug 2022 19:47:30 +02:00
perf/x86/lbr: Enable the branch type for the Arch LBR by default
On the platform with Arch LBR, the HW raw branch type encoding may leak to the perf tool when the SAVE_TYPE option is not set.
In the intel_pmu_store_lbr(), the HW raw branch type is stored in lbr_entries[].type. If the SAVE_TYPE option is set, the lbr_entries[].type will be converted into the generic PERF_BR_* type in the intel_pmu_lbr_filter() and exposed to the user tools. But if the SAVE_TYPE option is NOT set by the user, the current perf kernel doesn't clear the field. The HW raw branch type leaks.
There are two solutions to fix the issue for the Arch LBR. One is to clear the field if the SAVE_TYPE option is NOT set. The other solution is to unconditionally convert the branch type and expose the generic type to the user tools.
The latter is implemented here, because
- The branch type is valuable information. I don't see a case where you would not benefit from the branch type. (Stephane Eranian)
- Not having the branch type DOES NOT save any space in the branch record (Stephane Eranian)
- The Arch LBR HW can retrieve the common branch types from the LBR_INFO. It doesn't require the high overhead SW disassemble.
--- arch/x86/events/intel/lbr.c | 8 ++++++++ 1 file changed, 8 insertions(+)
arch/x86/events/intel/lbr.c +8 -0
@@ -1097,6 +1097,14 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)if (static_cpu_has (X86_FEATURE_ARCH_LBR )) { reg->config = mask; + +/* +* The Arch LBR HW can retrieve the common branch types +* from the LBR_INFO. It doesn't require the high overhead +* SW disassemble. +* Enable the branch type by default for the Arch LBR. +*/ + reg->reg |=X86_BR_TYPE_SAVE ;return 0 ; }