mirror of
https://github.com/torvalds/linux.git
synced 2026-06-04 20:46:48 +02:00
598c2fafc0
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: ca5b7c0d96 ("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
78 lines
2.6 KiB
C
78 lines
2.6 KiB
C
/*
|
|
* Routines to identify additional cpu features that are scattered in
|
|
* cpuid space.
|
|
*/
|
|
#include <linux/cpu.h>
|
|
|
|
#include <asm/memtype.h>
|
|
#include <asm/apic.h>
|
|
#include <asm/processor.h>
|
|
|
|
#include "cpu.h"
|
|
|
|
struct cpuid_bit {
|
|
u16 feature;
|
|
u8 reg;
|
|
u8 bit;
|
|
u32 level;
|
|
u32 sub_leaf;
|
|
};
|
|
|
|
/*
|
|
* Please keep the leaf sorted by cpuid_bit.level for faster search.
|
|
* X86_FEATURE_MBA is supported by both Intel and AMD. But the CPUID
|
|
* levels are different and there is a separate entry for each.
|
|
*/
|
|
static const struct cpuid_bit cpuid_bits[] = {
|
|
{ X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 },
|
|
{ X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 },
|
|
{ X86_FEATURE_INTEL_PPIN, CPUID_EBX, 0, 0x00000007, 1 },
|
|
{ X86_FEATURE_RRSBA_CTRL, CPUID_EDX, 2, 0x00000007, 2 },
|
|
{ X86_FEATURE_CQM_LLC, CPUID_EDX, 1, 0x0000000f, 0 },
|
|
{ X86_FEATURE_CQM_OCCUP_LLC, CPUID_EDX, 0, 0x0000000f, 1 },
|
|
{ X86_FEATURE_CQM_MBM_TOTAL, CPUID_EDX, 1, 0x0000000f, 1 },
|
|
{ X86_FEATURE_CQM_MBM_LOCAL, CPUID_EDX, 2, 0x0000000f, 1 },
|
|
{ X86_FEATURE_CAT_L3, CPUID_EBX, 1, 0x00000010, 0 },
|
|
{ X86_FEATURE_CAT_L2, CPUID_EBX, 2, 0x00000010, 0 },
|
|
{ X86_FEATURE_CDP_L3, CPUID_ECX, 2, 0x00000010, 1 },
|
|
{ X86_FEATURE_CDP_L2, CPUID_ECX, 2, 0x00000010, 2 },
|
|
{ X86_FEATURE_MBA, CPUID_EBX, 3, 0x00000010, 0 },
|
|
{ X86_FEATURE_PER_THREAD_MBA, CPUID_ECX, 0, 0x00000010, 3 },
|
|
{ X86_FEATURE_SGX1, CPUID_EAX, 0, 0x00000012, 0 },
|
|
{ X86_FEATURE_SGX2, CPUID_EAX, 1, 0x00000012, 0 },
|
|
{ X86_FEATURE_SGX_EDECCSSA, CPUID_EAX, 11, 0x00000012, 0 },
|
|
{ X86_FEATURE_HW_PSTATE, CPUID_EDX, 7, 0x80000007, 0 },
|
|
{ X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 },
|
|
{ X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 },
|
|
{ X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 },
|
|
{ X86_FEATURE_SMBA, CPUID_EBX, 2, 0x80000020, 0 },
|
|
{ X86_FEATURE_BMEC, CPUID_EBX, 3, 0x80000020, 0 },
|
|
{ X86_FEATURE_PERFMON_V2, CPUID_EAX, 0, 0x80000022, 0 },
|
|
{ X86_FEATURE_AMD_LBR_V2, CPUID_EAX, 1, 0x80000022, 0 },
|
|
{ X86_FEATURE_AMD_LBR_PMC_FREEZE, CPUID_EAX, 2, 0x80000022, 0 },
|
|
{ 0, 0, 0, 0, 0 }
|
|
};
|
|
|
|
void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
|
|
{
|
|
u32 max_level;
|
|
u32 regs[4];
|
|
const struct cpuid_bit *cb;
|
|
|
|
for (cb = cpuid_bits; cb->feature; cb++) {
|
|
|
|
/* Verify that the level is valid */
|
|
max_level = cpuid_eax(cb->level & 0xffff0000);
|
|
if (max_level < cb->level ||
|
|
max_level > (cb->level | 0xffff))
|
|
continue;
|
|
|
|
cpuid_count(cb->level, cb->sub_leaf, ®s[CPUID_EAX],
|
|
®s[CPUID_EBX], ®s[CPUID_ECX],
|
|
®s[CPUID_EDX]);
|
|
|
|
if (regs[cb->reg] & (1 << cb->bit))
|
|
set_cpu_cap(c, cb->feature);
|
|
}
|
|
}
|