diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-05-24 10:59:38 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-05-24 10:59:38 -0700 |
commit | cfeb2522c3777923c2bd24772b914195dc93c86b (patch) | |
tree | 126e7bd990742c7aed4e4880351c4f5a8267d7bb /arch/x86/include/asm | |
parent | Merge tag 'objtool-core-2022-05-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip (diff) | |
parent | perf/x86/amd/core: Fix reloading events for SVM (diff) | |
download | linux-dev-cfeb2522c3777923c2bd24772b914195dc93c86b.tar.xz linux-dev-cfeb2522c3777923c2bd24772b914195dc93c86b.zip |
Merge tag 'perf-core-2022-05-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf events updates from Ingo Molnar:
"Platform PMU changes:
- x86/intel:
- Add new Intel Alder Lake and Raptor Lake support
- x86/amd:
- AMD Zen4 IBS extensions support
- Add AMD PerfMonV2 support
- Add AMD Fam19h Branch Sampling support
Generic changes:
- signal: Deliver SIGTRAP on perf event asynchronously if blocked
Perf instrumentation can be driven via SIGTRAP, but this causes a
problem when SIGTRAP is blocked by a task & terminate the task.
Allow user-space to request these signals asynchronously (after
they get unblocked) & also give the information to the signal
handler when this happens:
"To give user space the ability to clearly distinguish
synchronous from asynchronous signals, introduce
siginfo_t::si_perf_flags and TRAP_PERF_FLAG_ASYNC (opted for
flags in case more binary information is required in future).
The resolution to the problem is then to (a) no longer force the
signal (avoiding the terminations), but (b) tell user space via
si_perf_flags if the signal was synchronous or not, so that such
signals can be handled differently (e.g. let user space decide
to ignore or consider the data imprecise). "
- Unify/standardize the /sys/devices/cpu/events/* output format.
- Misc fixes & cleanups"
* tag 'perf-core-2022-05-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (32 commits)
perf/x86/amd/core: Fix reloading events for SVM
perf/x86/amd: Run AMD BRS code only on supported hw
perf/x86/amd: Fix AMD BRS period adjustment
perf/x86/amd: Remove unused variable 'hwc'
perf/ibs: Fix comment
perf/amd/ibs: Advertise zen4_ibs_extensions as pmu capability attribute
perf/amd/ibs: Add support for L3 miss filtering
perf/amd/ibs: Use ->is_visible callback for dynamic attributes
perf/amd/ibs: Cascade pmu init functions' return value
perf/x86/uncore: Add new Alder Lake and Raptor Lake support
perf/x86/uncore: Clean up uncore_pci_ids[]
perf/x86/cstate: Add new Alder Lake and Raptor Lake support
perf/x86/msr: Add new Alder Lake and Raptor Lake support
perf/x86: Add new Alder Lake and Raptor Lake support
perf/amd/ibs: Use interrupt regs ip for stack unwinding
perf/x86/amd/core: Add PerfMonV2 overflow handling
perf/x86/amd/core: Add PerfMonV2 counter control
perf/x86/amd/core: Detect available counters
perf/x86/amd/core: Detect PerfMonV2 support
x86/msr: Add PerfCntrGlobal* registers
...
Diffstat (limited to 'arch/x86/include/asm')
-rw-r--r-- | arch/x86/include/asm/amd-ibs.h | 2 | ||||
-rw-r--r-- | arch/x86/include/asm/cpufeatures.h | 3 | ||||
-rw-r--r-- | arch/x86/include/asm/msr-index.h | 9 | ||||
-rw-r--r-- | arch/x86/include/asm/perf_event.h | 43 |
4 files changed, 55 insertions, 2 deletions
diff --git a/arch/x86/include/asm/amd-ibs.h b/arch/x86/include/asm/amd-ibs.h index 46e1df45efc0..aabdbb5ab920 100644 --- a/arch/x86/include/asm/amd-ibs.h +++ b/arch/x86/include/asm/amd-ibs.h @@ -49,7 +49,7 @@ union ibs_op_ctl { }; }; -/* MSR 0xc0011035: IBS Op Data 2 */ +/* MSR 0xc0011035: IBS Op Data 1 */ union ibs_op_data { __u64 val; struct { diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 6e0dbbf847f3..21bb78dfd41d 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -211,7 +211,7 @@ #define X86_FEATURE_SSBD ( 7*32+17) /* Speculative Store Bypass Disable */ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ #define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ -/* FREE! ( 7*32+20) */ +#define X86_FEATURE_PERFMON_V2 ( 7*32+20) /* AMD Performance Monitoring Version 2 */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ #define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */ @@ -316,6 +316,7 @@ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ #define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */ +#define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index a51208d10df4..14154b8b1720 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -533,6 +533,11 @@ #define AMD_CPPC_DES_PERF(x) (((x) & 0xff) << 16) #define AMD_CPPC_ENERGY_PERF_PREF(x) (((x) & 0xff) << 24) +/* AMD Performance Counter Global Status and Control MSRs */ +#define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS 0xc0000300 +#define MSR_AMD64_PERF_CNTR_GLOBAL_CTL 0xc0000301 +#define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR 0xc0000302 + /* Fam 17h MSRs */ #define MSR_F17H_IRPERF 0xc00000e9 @@ -697,6 +702,10 @@ #define MSR_IA32_PERF_CTL 0x00000199 #define INTEL_PERF_CTL_MASK 0xffff +/* AMD Branch Sampling configuration */ +#define MSR_AMD_DBG_EXTN_CFG 0xc000010f +#define MSR_AMD_SAMP_BR_FROM 0xc0010300 + #define MSR_IA32_MPERF 0x000000e7 #define MSR_IA32_APERF 0x000000e8 diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index b06e4c573add..409725e86f42 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_PERF_EVENT_H #define _ASM_X86_PERF_EVENT_H +#include <linux/static_call.h> + /* * Performance event hw details: */ @@ -184,6 +186,18 @@ union cpuid28_ecx { unsigned int full; }; +/* + * AMD "Extended Performance Monitoring and Debug" CPUID + * detection/enumeration details: + */ +union cpuid_0x80000022_ebx { + struct { + /* Number of Core Performance Counters */ + unsigned int num_core_pmc:4; + } split; + unsigned int full; +}; + struct x86_pmu_capability { int version; int num_counters_gp; @@ -371,6 +385,11 @@ struct pebs_xmm { }; /* + * AMD Extended Performance Monitoring and Debug cpuid feature detection + */ +#define EXT_PERFMON_DEBUG_FEATURES 0x80000022 + +/* * IBS cpuid feature detection */ @@ -391,6 +410,7 @@ struct pebs_xmm { #define IBS_CAPS_OPBRNFUSE (1U<<8) #define IBS_CAPS_FETCHCTLEXTD (1U<<9) #define IBS_CAPS_OPDATA4 (1U<<10) +#define IBS_CAPS_ZEN4 (1U<<11) #define IBS_CAPS_DEFAULT (IBS_CAPS_AVAIL \ | IBS_CAPS_FETCHSAM \ @@ -404,6 +424,7 @@ struct pebs_xmm { #define IBSCTL_LVT_OFFSET_MASK 0x0F /* IBS fetch bits/masks */ +#define IBS_FETCH_L3MISSONLY (1ULL<<59) #define IBS_FETCH_RAND_EN (1ULL<<57) #define IBS_FETCH_VAL (1ULL<<49) #define IBS_FETCH_ENABLE (1ULL<<48) @@ -420,6 +441,7 @@ struct pebs_xmm { #define IBS_OP_CNT_CTL (1ULL<<19) #define IBS_OP_VAL (1ULL<<18) #define IBS_OP_ENABLE (1ULL<<17) +#define IBS_OP_L3MISSONLY (1ULL<<16) #define IBS_OP_MAX_CNT 0x0000FFFFULL #define IBS_OP_MAX_CNT_EXT 0x007FFFFFULL /* not a register bit mask */ #define IBS_OP_MAX_CNT_EXT_MASK (0x7FULL<<20) /* separate upper 7 bits */ @@ -518,6 +540,27 @@ static inline void intel_pt_handle_vmx(int on) #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD) extern void amd_pmu_enable_virt(void); extern void amd_pmu_disable_virt(void); + +#if defined(CONFIG_PERF_EVENTS_AMD_BRS) + +#define PERF_NEEDS_LOPWR_CB 1 + +/* + * architectural low power callback impacts + * drivers/acpi/processor_idle.c + * drivers/acpi/acpi_pad.c + */ +extern void perf_amd_brs_lopwr_cb(bool lopwr_in); + +DECLARE_STATIC_CALL(perf_lopwr_cb, perf_amd_brs_lopwr_cb); + +static inline void perf_lopwr_cb(bool lopwr_in) +{ + static_call_mod(perf_lopwr_cb)(lopwr_in); +} + +#endif /* PERF_NEEDS_LOPWR_CB */ + #else static inline void amd_pmu_enable_virt(void) { } static inline void amd_pmu_disable_virt(void) { } |