diff options
| author | Sandipan Das <sandipan.das@amd.com> | 2024-03-25 13:01:45 +0530 |
|---|---|---|
| committer | Ingo Molnar <mingo@kernel.org> | 2024-03-25 11:16:55 +0100 |
| commit | 598c2fafc06fe5c56a1a415fb7b544b31453d637 (patch) | |
| tree | 0379b121fa2d7f0d56ce09f2800d9b38d6ee6785 /arch/x86/events | |
| parent | 7f274e609f3d5f45c22b1dd59053f6764458b492 (diff) | |
| download | linux-stable-598c2fafc06fe5c56a1a415fb7b544b31453d637.tar.gz linux-stable-598c2fafc06fe5c56a1a415fb7b544b31453d637.tar.bz2 linux-stable-598c2fafc06fe5c56a1a415fb7b544b31453d637.zip | |
perf/x86/amd/lbr: Use freeze based on availability
Currently, the LBR code assumes that LBR Freeze is supported on all processors
when X86_FEATURE_AMD_LBR_V2 is available i.e. CPUID leaf 0x80000022[EAX]
bit 1 is set. This is incorrect as the availability of the feature is
additionally dependent on CPUID leaf 0x80000022[EAX] bit 2 being set,
which may not be set for all Zen 4 processors.
Define a new feature bit for LBR and PMC freeze and set the freeze enable bit
(FLBRI) in DebugCtl (MSR 0x1d9) conditionally.
It should still be possible to use LBR without freeze for profile-guided
optimization of user programs by using an user-only branch filter during
profiling. When the user-only filter is enabled, branches are no longer
recorded after the transition to CPL 0 upon PMI arrival. When branch
entries are read in the PMI handler, the branch stack does not change.
E.g.
$ perf record -j any,u -e ex_ret_brn_tkn ./workload
Since the feature bit is visible under flags in /proc/cpuinfo, it can be
used to determine the feasibility of use-cases which require LBR Freeze
to be supported by the hardware such as profile-guided optimization of
kernels.
Fixes: ca5b7c0d9621 ("perf/x86/amd/lbr: Add LbrExtV2 branch record support")
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/69a453c97cfd11c6f2584b19f937fe6df741510f.1711091584.git.sandipan.das@amd.com
Diffstat (limited to 'arch/x86/events')
| -rw-r--r-- | arch/x86/events/amd/core.c | 4 | ||||
| -rw-r--r-- | arch/x86/events/amd/lbr.c | 16 |
2 files changed, 12 insertions, 8 deletions
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index aec16e581f5b..5692e827afef 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -904,8 +904,8 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs) if (!status) goto done; - /* Read branch records before unfreezing */ - if (status & GLOBAL_STATUS_LBRS_FROZEN) { + /* Read branch records */ + if (x86_pmu.lbr_nr) { amd_pmu_lbr_read(); status &= ~GLOBAL_STATUS_LBRS_FROZEN; } diff --git a/arch/x86/events/amd/lbr.c b/arch/x86/events/amd/lbr.c index 4a1e600314d5..5149830c7c4f 100644 --- a/arch/x86/events/amd/lbr.c +++ b/arch/x86/events/amd/lbr.c @@ -402,10 +402,12 @@ void amd_pmu_lbr_enable_all(void) wrmsrl(MSR_AMD64_LBR_SELECT, lbr_select); } - rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl); - rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg); + if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) { + rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl); + wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + } - wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg); wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg | DBG_EXTN_CFG_LBRV2EN); } @@ -418,10 +420,12 @@ void amd_pmu_lbr_disable_all(void) return; rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg); - rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl); - wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg & ~DBG_EXTN_CFG_LBRV2EN); - wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + + if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) { + rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl); + wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + } } __init int amd_pmu_lbr_init(void) |