diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-08-07 13:17:46 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-08-07 13:17:46 +0000 |
commit | 7f3a4257159dea8e7ef66d1a539dc6df708b8ed3 (patch) | |
tree | bcc69b5f4609f348fac49e2f59e210b29eaea783 /arch/x86/events | |
parent | Adding upstream version 6.9.12. (diff) | |
download | linux-7f3a4257159dea8e7ef66d1a539dc6df708b8ed3.tar.xz linux-7f3a4257159dea8e7ef66d1a539dc6df708b8ed3.zip |
Adding upstream version 6.10.3.upstream/6.10.3
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'arch/x86/events')
-rw-r--r-- | arch/x86/events/amd/core.c | 37 | ||||
-rw-r--r-- | arch/x86/events/amd/lbr.c | 13 | ||||
-rw-r--r-- | arch/x86/events/amd/uncore.c | 28 | ||||
-rw-r--r-- | arch/x86/events/core.c | 3 | ||||
-rw-r--r-- | arch/x86/events/intel/core.c | 13 | ||||
-rw-r--r-- | arch/x86/events/intel/cstate.c | 158 | ||||
-rw-r--r-- | arch/x86/events/intel/ds.c | 8 | ||||
-rw-r--r-- | arch/x86/events/intel/lbr.c | 3 | ||||
-rw-r--r-- | arch/x86/events/intel/pt.c | 16 | ||||
-rw-r--r-- | arch/x86/events/intel/pt.h | 4 | ||||
-rw-r--r-- | arch/x86/events/intel/uncore.c | 101 | ||||
-rw-r--r-- | arch/x86/events/intel/uncore_nhmex.c | 3 | ||||
-rw-r--r-- | arch/x86/events/intel/uncore_snbep.c | 11 | ||||
-rw-r--r-- | arch/x86/events/msr.c | 132 | ||||
-rw-r--r-- | arch/x86/events/perf_event.h | 13 | ||||
-rw-r--r-- | arch/x86/events/rapl.c | 22 |
16 files changed, 304 insertions, 261 deletions
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 985ef3b479..1fc4ce44e7 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -647,7 +647,7 @@ static void amd_pmu_cpu_dead(int cpu) } } -static inline void amd_pmu_set_global_ctl(u64 ctl) +static __always_inline void amd_pmu_set_global_ctl(u64 ctl) { wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, ctl); } @@ -907,6 +907,37 @@ static int amd_pmu_handle_irq(struct pt_regs *regs) return amd_pmu_adjust_nmi_window(handled); } +/* + * AMD-specific callback invoked through perf_snapshot_branch_stack static + * call, defined in include/linux/perf_event.h. See its definition for API + * details. It's up to caller to provide enough space in *entries* to fit all + * LBR records, otherwise returned result will be truncated to *cnt* entries. + */ +static int amd_pmu_v2_snapshot_branch_stack(struct perf_branch_entry *entries, unsigned int cnt) +{ + struct cpu_hw_events *cpuc; + unsigned long flags; + + /* + * The sequence of steps to freeze LBR should be completely inlined + * and contain no branches to minimize contamination of LBR snapshot + */ + local_irq_save(flags); + amd_pmu_core_disable_all(); + __amd_pmu_lbr_disable(); + + cpuc = this_cpu_ptr(&cpu_hw_events); + + amd_pmu_lbr_read(); + cnt = min(cnt, x86_pmu.lbr_nr); + memcpy(entries, cpuc->lbr_entries, sizeof(struct perf_branch_entry) * cnt); + + amd_pmu_v2_enable_all(0); + local_irq_restore(flags); + + return cnt; +} + static int amd_pmu_v2_handle_irq(struct pt_regs *regs) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); @@ -1443,6 +1474,10 @@ static int __init amd_core_pmu_init(void) static_call_update(amd_pmu_branch_reset, amd_pmu_lbr_reset); static_call_update(amd_pmu_branch_add, amd_pmu_lbr_add); static_call_update(amd_pmu_branch_del, amd_pmu_lbr_del); + + /* Only support branch_stack snapshot on perfmon v2 */ + if (x86_pmu.handle_irq == amd_pmu_v2_handle_irq) + static_call_update(perf_snapshot_branch_stack, amd_pmu_v2_snapshot_branch_stack); } else if (!amd_brs_init()) { /* * BRS requires special event constraints and flushing on ctxsw. diff --git a/arch/x86/events/amd/lbr.c b/arch/x86/events/amd/lbr.c index 5149830c7c..19c7b76e21 100644 --- a/arch/x86/events/amd/lbr.c +++ b/arch/x86/events/amd/lbr.c @@ -310,10 +310,6 @@ int amd_pmu_lbr_hw_config(struct perf_event *event) { int ret = 0; - /* LBR is not recommended in counting mode */ - if (!is_sampling_event(event)) - return -EINVAL; - ret = amd_pmu_lbr_setup_filter(event); if (!ret) event->attach_state |= PERF_ATTACH_SCHED_CB; @@ -414,18 +410,11 @@ void amd_pmu_lbr_enable_all(void) void amd_pmu_lbr_disable_all(void) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - u64 dbg_ctl, dbg_extn_cfg; if (!cpuc->lbr_users || !x86_pmu.lbr_nr) return; - rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg); - wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg & ~DBG_EXTN_CFG_LBRV2EN); - - 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); - } + __amd_pmu_lbr_disable(); } __init int amd_pmu_lbr_init(void) diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index 4ccb8fa483..5a4bfe9aea 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -639,7 +639,7 @@ void amd_uncore_df_ctx_scan(struct amd_uncore *uncore, unsigned int cpu) info.split.aux_data = 0; info.split.num_pmcs = NUM_COUNTERS_NB; info.split.gid = 0; - info.split.cid = topology_die_id(cpu); + info.split.cid = topology_logical_package_id(cpu); if (pmu_version >= 2) { ebx.full = cpuid_ebx(EXT_PERFMON_DEBUG_FEATURES); @@ -654,17 +654,20 @@ int amd_uncore_df_ctx_init(struct amd_uncore *uncore, unsigned int cpu) { struct attribute **df_attr = amd_uncore_df_format_attr; struct amd_uncore_pmu *pmu; + int num_counters; /* Run just once */ if (uncore->init_done) return amd_uncore_ctx_init(uncore, cpu); + num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu); + if (!num_counters) + goto done; + /* No grouping, single instance for a system */ uncore->pmus = kzalloc(sizeof(*uncore->pmus), GFP_KERNEL); - if (!uncore->pmus) { - uncore->num_pmus = 0; + if (!uncore->pmus) goto done; - } /* * For Family 17h and above, the Northbridge counters are repurposed @@ -674,7 +677,7 @@ int amd_uncore_df_ctx_init(struct amd_uncore *uncore, unsigned int cpu) pmu = &uncore->pmus[0]; strscpy(pmu->name, boot_cpu_data.x86 >= 0x17 ? "amd_df" : "amd_nb", sizeof(pmu->name)); - pmu->num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu); + pmu->num_counters = num_counters; pmu->msr_base = MSR_F15H_NB_PERF_CTL; pmu->rdpmc_base = RDPMC_BASE_NB; pmu->group = amd_uncore_ctx_gid(uncore, cpu); @@ -785,17 +788,20 @@ int amd_uncore_l3_ctx_init(struct amd_uncore *uncore, unsigned int cpu) { struct attribute **l3_attr = amd_uncore_l3_format_attr; struct amd_uncore_pmu *pmu; + int num_counters; /* Run just once */ if (uncore->init_done) return amd_uncore_ctx_init(uncore, cpu); + num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu); + if (!num_counters) + goto done; + /* No grouping, single instance for a system */ uncore->pmus = kzalloc(sizeof(*uncore->pmus), GFP_KERNEL); - if (!uncore->pmus) { - uncore->num_pmus = 0; + if (!uncore->pmus) goto done; - } /* * For Family 17h and above, L3 cache counters are available instead @@ -805,7 +811,7 @@ int amd_uncore_l3_ctx_init(struct amd_uncore *uncore, unsigned int cpu) pmu = &uncore->pmus[0]; strscpy(pmu->name, boot_cpu_data.x86 >= 0x17 ? "amd_l3" : "amd_l2", sizeof(pmu->name)); - pmu->num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu); + pmu->num_counters = num_counters; pmu->msr_base = MSR_F16H_L2I_PERF_CTL; pmu->rdpmc_base = RDPMC_BASE_LLC; pmu->group = amd_uncore_ctx_gid(uncore, cpu); @@ -893,8 +899,8 @@ void amd_uncore_umc_ctx_scan(struct amd_uncore *uncore, unsigned int cpu) cpuid(EXT_PERFMON_DEBUG_FEATURES, &eax, &ebx.full, &ecx, &edx); info.split.aux_data = ecx; /* stash active mask */ info.split.num_pmcs = ebx.split.num_umc_pmc; - info.split.gid = topology_die_id(cpu); - info.split.cid = topology_die_id(cpu); + info.split.gid = topology_logical_package_id(cpu); + info.split.cid = topology_logical_package_id(cpu); *per_cpu_ptr(uncore->info, cpu) = info; } diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 5b0dd07b1e..acd367c453 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2547,6 +2547,7 @@ static ssize_t set_attr_rdpmc(struct device *cdev, struct device_attribute *attr, const char *buf, size_t count) { + static DEFINE_MUTEX(rdpmc_mutex); unsigned long val; ssize_t ret; @@ -2560,6 +2561,8 @@ static ssize_t set_attr_rdpmc(struct device *cdev, if (x86_pmu.attr_rdpmc_broken) return -ENOTSUPP; + guard(mutex)(&rdpmc_mutex); + if (val != x86_pmu.attr_rdpmc) { /* * Changing into or out of never available or always available, diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 768d141489..38c1b1f1de 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -5645,18 +5645,11 @@ lbr_is_visible(struct kobject *kobj, struct attribute *attr, int i) static char pmu_name_str[30]; -static ssize_t pmu_name_show(struct device *cdev, - struct device_attribute *attr, - char *buf) -{ - return snprintf(buf, PAGE_SIZE, "%s\n", pmu_name_str); -} - -static DEVICE_ATTR_RO(pmu_name); +static DEVICE_STRING_ATTR_RO(pmu_name, 0444, pmu_name_str); static struct attribute *intel_pmu_caps_attrs[] = { - &dev_attr_pmu_name.attr, - NULL + &dev_attr_pmu_name.attr.attr, + NULL }; static DEVICE_ATTR(allow_tsx_force_abort, 0644, diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 326c8cd5aa..dd18320558 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -81,7 +81,7 @@ * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL, - * KBL,CML,ICL,TGL,RKL,ADL,RPL,MTL + * KBL,CML,ICL,TGL,RKL * Scope: Package (physical package) * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter. * perf code: 0x04 @@ -90,8 +90,7 @@ * Scope: Package (physical package) * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter. * perf code: 0x05 - * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL,RPL,MTL + * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 @@ -114,6 +113,7 @@ #include "../perf_event.h" #include "../probe.h" +MODULE_DESCRIPTION("Support for Intel cstate performance events"); MODULE_LICENSE("GPL"); #define DEFINE_CSTATE_FORMAT_ATTR(_var, _name, _format) \ @@ -143,12 +143,6 @@ struct cstate_model { #define SLM_PKG_C6_USE_C7_MSR (1UL << 0) #define KNL_CORE_C6_MSR (1UL << 1) -struct perf_cstate_msr { - u64 msr; - struct perf_pmu_events_attr *attr; -}; - - /* cstate_core PMU */ static struct pmu cstate_core_pmu; static bool has_cstate_core; @@ -642,9 +636,7 @@ static const struct cstate_model adl_cstates __initconst = { .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) | BIT(PERF_CSTATE_PKG_C3_RES) | BIT(PERF_CSTATE_PKG_C6_RES) | - BIT(PERF_CSTATE_PKG_C7_RES) | BIT(PERF_CSTATE_PKG_C8_RES) | - BIT(PERF_CSTATE_PKG_C9_RES) | BIT(PERF_CSTATE_PKG_C10_RES), }; @@ -696,78 +688,78 @@ static const struct cstate_model srf_cstates __initconst = { static const struct x86_cpu_id intel_cstates_match[] __initconst = { - X86_MATCH_INTEL_FAM6_MODEL(NEHALEM, &nhm_cstates), - X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EP, &nhm_cstates), - X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EX, &nhm_cstates), - - X86_MATCH_INTEL_FAM6_MODEL(WESTMERE, &nhm_cstates), - X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EP, &nhm_cstates), - X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EX, &nhm_cstates), - - X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE, &snb_cstates), - X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE_X, &snb_cstates), - - X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE, &snb_cstates), - X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X, &snb_cstates), - - X86_MATCH_INTEL_FAM6_MODEL(HASWELL, &snb_cstates), - X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, &snb_cstates), - X86_MATCH_INTEL_FAM6_MODEL(HASWELL_G, &snb_cstates), - - X86_MATCH_INTEL_FAM6_MODEL(HASWELL_L, &hswult_cstates), - - X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT, &slm_cstates), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_D, &slm_cstates), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT, &slm_cstates), - - X86_MATCH_INTEL_FAM6_MODEL(BROADWELL, &snb_cstates), - X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D, &snb_cstates), - X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_G, &snb_cstates), - X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, &snb_cstates), - - X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L, &snb_cstates), - X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE, &snb_cstates), - X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, &snb_cstates), - - X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L, &hswult_cstates), - X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE, &hswult_cstates), - X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L, &hswult_cstates), - X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &hswult_cstates), - - X86_MATCH_INTEL_FAM6_MODEL(CANNONLAKE_L, &cnl_cstates), - - X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL, &knl_cstates), - X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM, &knl_cstates), - - X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, &glm_cstates), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D, &glm_cstates), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS, &glm_cstates), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &glm_cstates), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT, &glm_cstates), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L, &glm_cstates), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT, &adl_cstates), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT_X, &srf_cstates), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT, &grr_cstates), - - X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, &icl_cstates), - X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &icl_cstates), - X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &icx_cstates), - X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &icx_cstates), - X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &icx_cstates), - X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &icx_cstates), - X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_X, &icx_cstates), - X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_D, &icx_cstates), - - X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &icl_cstates), - X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &icl_cstates), - X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &icl_cstates), - X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &adl_cstates), - X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &adl_cstates), - X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_cstates), - X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_cstates), - X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_cstates), - X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, &adl_cstates), - X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &adl_cstates), + X86_MATCH_VFM(INTEL_NEHALEM, &nhm_cstates), + X86_MATCH_VFM(INTEL_NEHALEM_EP, &nhm_cstates), + X86_MATCH_VFM(INTEL_NEHALEM_EX, &nhm_cstates), + + X86_MATCH_VFM(INTEL_WESTMERE, &nhm_cstates), + X86_MATCH_VFM(INTEL_WESTMERE_EP, &nhm_cstates), + X86_MATCH_VFM(INTEL_WESTMERE_EX, &nhm_cstates), + + X86_MATCH_VFM(INTEL_SANDYBRIDGE, &snb_cstates), + X86_MATCH_VFM(INTEL_SANDYBRIDGE_X, &snb_cstates), + + X86_MATCH_VFM(INTEL_IVYBRIDGE, &snb_cstates), + X86_MATCH_VFM(INTEL_IVYBRIDGE_X, &snb_cstates), + + X86_MATCH_VFM(INTEL_HASWELL, &snb_cstates), + X86_MATCH_VFM(INTEL_HASWELL_X, &snb_cstates), + X86_MATCH_VFM(INTEL_HASWELL_G, &snb_cstates), + + X86_MATCH_VFM(INTEL_HASWELL_L, &hswult_cstates), + + X86_MATCH_VFM(INTEL_ATOM_SILVERMONT, &slm_cstates), + X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_D, &slm_cstates), + X86_MATCH_VFM(INTEL_ATOM_AIRMONT, &slm_cstates), + + X86_MATCH_VFM(INTEL_BROADWELL, &snb_cstates), + X86_MATCH_VFM(INTEL_BROADWELL_D, &snb_cstates), + X86_MATCH_VFM(INTEL_BROADWELL_G, &snb_cstates), + X86_MATCH_VFM(INTEL_BROADWELL_X, &snb_cstates), + + X86_MATCH_VFM(INTEL_SKYLAKE_L, &snb_cstates), + X86_MATCH_VFM(INTEL_SKYLAKE, &snb_cstates), + X86_MATCH_VFM(INTEL_SKYLAKE_X, &snb_cstates), + + X86_MATCH_VFM(INTEL_KABYLAKE_L, &hswult_cstates), + X86_MATCH_VFM(INTEL_KABYLAKE, &hswult_cstates), + X86_MATCH_VFM(INTEL_COMETLAKE_L, &hswult_cstates), + X86_MATCH_VFM(INTEL_COMETLAKE, &hswult_cstates), + + X86_MATCH_VFM(INTEL_CANNONLAKE_L, &cnl_cstates), + + X86_MATCH_VFM(INTEL_XEON_PHI_KNL, &knl_cstates), + X86_MATCH_VFM(INTEL_XEON_PHI_KNM, &knl_cstates), + + X86_MATCH_VFM(INTEL_ATOM_GOLDMONT, &glm_cstates), + X86_MATCH_VFM(INTEL_ATOM_GOLDMONT_D, &glm_cstates), + X86_MATCH_VFM(INTEL_ATOM_GOLDMONT_PLUS, &glm_cstates), + X86_MATCH_VFM(INTEL_ATOM_TREMONT_D, &glm_cstates), + X86_MATCH_VFM(INTEL_ATOM_TREMONT, &glm_cstates), + X86_MATCH_VFM(INTEL_ATOM_TREMONT_L, &glm_cstates), + X86_MATCH_VFM(INTEL_ATOM_GRACEMONT, &adl_cstates), + X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X, &srf_cstates), + X86_MATCH_VFM(INTEL_ATOM_CRESTMONT, &grr_cstates), + + X86_MATCH_VFM(INTEL_ICELAKE_L, &icl_cstates), + X86_MATCH_VFM(INTEL_ICELAKE, &icl_cstates), + X86_MATCH_VFM(INTEL_ICELAKE_X, &icx_cstates), + X86_MATCH_VFM(INTEL_ICELAKE_D, &icx_cstates), + X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, &icx_cstates), + X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, &icx_cstates), + X86_MATCH_VFM(INTEL_GRANITERAPIDS_X, &icx_cstates), + X86_MATCH_VFM(INTEL_GRANITERAPIDS_D, &icx_cstates), + + X86_MATCH_VFM(INTEL_TIGERLAKE_L, &icl_cstates), + X86_MATCH_VFM(INTEL_TIGERLAKE, &icl_cstates), + X86_MATCH_VFM(INTEL_ROCKETLAKE, &icl_cstates), + X86_MATCH_VFM(INTEL_ALDERLAKE, &adl_cstates), + X86_MATCH_VFM(INTEL_ALDERLAKE_L, &adl_cstates), + X86_MATCH_VFM(INTEL_RAPTORLAKE, &adl_cstates), + X86_MATCH_VFM(INTEL_RAPTORLAKE_P, &adl_cstates), + X86_MATCH_VFM(INTEL_RAPTORLAKE_S, &adl_cstates), + X86_MATCH_VFM(INTEL_METEORLAKE, &adl_cstates), + X86_MATCH_VFM(INTEL_METEORLAKE_L, &adl_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index e010bfed84..80a4f71221 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1831,8 +1831,12 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, set_linear_ip(regs, basic->ip); regs->flags = PERF_EFLAGS_EXACT; - if ((sample_type & PERF_SAMPLE_WEIGHT_STRUCT) && (x86_pmu.flags & PMU_FL_RETIRE_LATENCY)) - data->weight.var3_w = format_size >> PEBS_RETIRE_LATENCY_OFFSET & PEBS_LATENCY_MASK; + if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) { + if (x86_pmu.flags & PMU_FL_RETIRE_LATENCY) + data->weight.var3_w = format_size >> PEBS_RETIRE_LATENCY_OFFSET & PEBS_LATENCY_MASK; + else + data->weight.var3_w = 0; + } /* * The record for MEMINFO is in front of GP diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 4367aa77cb..dc641b5081 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -2,6 +2,7 @@ #include <linux/perf_event.h> #include <linux/types.h> +#include <asm/cpu_device_id.h> #include <asm/perf_event.h> #include <asm/msr.h> @@ -1457,7 +1458,7 @@ void __init intel_pmu_lbr_init_atom(void) * to have an operational LBR which can freeze * on PMU interrupt */ - if (boot_cpu_data.x86_model == 28 + if (boot_cpu_data.x86_vfm == INTEL_ATOM_BONNELL && boot_cpu_data.x86_stepping < 10) { pr_cont("LBR disabled due to erratum"); return; diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 8e2a12235e..b4aa8daa47 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -22,7 +22,7 @@ #include <asm/insn.h> #include <asm/io.h> #include <asm/intel_pt.h> -#include <asm/intel-family.h> +#include <asm/cpu_device_id.h> #include "../perf_event.h" #include "pt.h" @@ -211,11 +211,11 @@ static int __init pt_pmu_hw_init(void) } /* model-specific quirks */ - switch (boot_cpu_data.x86_model) { - case INTEL_FAM6_BROADWELL: - case INTEL_FAM6_BROADWELL_D: - case INTEL_FAM6_BROADWELL_G: - case INTEL_FAM6_BROADWELL_X: + switch (boot_cpu_data.x86_vfm) { + case INTEL_BROADWELL: + case INTEL_BROADWELL_D: + case INTEL_BROADWELL_G: + case INTEL_BROADWELL_X: /* not setting BRANCH_EN will #GP, erratum BDM106 */ pt_pmu.branch_en_always_on = true; break; @@ -878,7 +878,7 @@ static void pt_update_head(struct pt *pt) */ static void *pt_buffer_region(struct pt_buffer *buf) { - return phys_to_virt(TOPA_ENTRY(buf->cur, buf->cur_idx)->base << TOPA_SHIFT); + return phys_to_virt((phys_addr_t)TOPA_ENTRY(buf->cur, buf->cur_idx)->base << TOPA_SHIFT); } /** @@ -990,7 +990,7 @@ pt_topa_entry_for_page(struct pt_buffer *buf, unsigned int pg) * order allocations, there shouldn't be many of these. */ list_for_each_entry(topa, &buf->tables, list) { - if (topa->offset + topa->size > pg << PAGE_SHIFT) + if (topa->offset + topa->size > (unsigned long)pg << PAGE_SHIFT) goto found; } diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h index 96906a62aa..f5e46c04c1 100644 --- a/arch/x86/events/intel/pt.h +++ b/arch/x86/events/intel/pt.h @@ -33,8 +33,8 @@ struct topa_entry { u64 rsvd2 : 1; u64 size : 4; u64 rsvd3 : 2; - u64 base : 36; - u64 rsvd4 : 16; + u64 base : 40; + u64 rsvd4 : 12; }; /* TSC to Core Crystal Clock Ratio */ diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 258e2cdf28..c68f5b3995 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -34,6 +34,7 @@ static struct event_constraint uncore_constraint_fixed = struct event_constraint uncore_constraint_empty = EVENT_CONSTRAINT(0, 0, 0); +MODULE_DESCRIPTION("Support for Intel uncore performance events"); MODULE_LICENSE("GPL"); int uncore_pcibus_to_dieid(struct pci_bus *bus) @@ -1829,56 +1830,56 @@ static const struct intel_uncore_init_fun generic_uncore_init __initconst = { }; static const struct x86_cpu_id intel_uncore_match[] __initconst = { - X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EP, &nhm_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(NEHALEM, &nhm_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(WESTMERE, &nhm_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EP, &nhm_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE, &snb_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE, &ivb_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(HASWELL, &hsw_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(HASWELL_L, &hsw_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(HASWELL_G, &hsw_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(BROADWELL, &bdw_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_G, &bdw_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE_X, &snbep_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EX, &nhmex_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EX, &nhmex_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X, &ivbep_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, &hswep_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, &bdx_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D, &bdx_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL, &knl_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM, &knl_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE, &skl_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L, &skl_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, &skx_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L, &skl_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE, &skl_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L, &skl_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &skl_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, &icl_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_NNPI, &icl_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &icl_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &icx_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &icx_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &tgl_l_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &tgl_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &rkl_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &adl_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &adl_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, &mtl_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &mtl_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &spr_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &spr_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_X, &gnr_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_D, &gnr_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT, &adl_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT_X, &gnr_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT, &gnr_uncore_init), + X86_MATCH_VFM(INTEL_NEHALEM_EP, &nhm_uncore_init), + X86_MATCH_VFM(INTEL_NEHALEM, &nhm_uncore_init), + X86_MATCH_VFM(INTEL_WESTMERE, &nhm_uncore_init), + X86_MATCH_VFM(INTEL_WESTMERE_EP, &nhm_uncore_init), + X86_MATCH_VFM(INTEL_SANDYBRIDGE, &snb_uncore_init), + X86_MATCH_VFM(INTEL_IVYBRIDGE, &ivb_uncore_init), + X86_MATCH_VFM(INTEL_HASWELL, &hsw_uncore_init), + X86_MATCH_VFM(INTEL_HASWELL_L, &hsw_uncore_init), + X86_MATCH_VFM(INTEL_HASWELL_G, &hsw_uncore_init), + X86_MATCH_VFM(INTEL_BROADWELL, &bdw_uncore_init), + X86_MATCH_VFM(INTEL_BROADWELL_G, &bdw_uncore_init), + X86_MATCH_VFM(INTEL_SANDYBRIDGE_X, &snbep_uncore_init), + X86_MATCH_VFM(INTEL_NEHALEM_EX, &nhmex_uncore_init), + X86_MATCH_VFM(INTEL_WESTMERE_EX, &nhmex_uncore_init), + X86_MATCH_VFM(INTEL_IVYBRIDGE_X, &ivbep_uncore_init), + X86_MATCH_VFM(INTEL_HASWELL_X, &hswep_uncore_init), + X86_MATCH_VFM(INTEL_BROADWELL_X, &bdx_uncore_init), + X86_MATCH_VFM(INTEL_BROADWELL_D, &bdx_uncore_init), + X86_MATCH_VFM(INTEL_XEON_PHI_KNL, &knl_uncore_init), + X86_MATCH_VFM(INTEL_XEON_PHI_KNM, &knl_uncore_init), + X86_MATCH_VFM(INTEL_SKYLAKE, &skl_uncore_init), + X86_MATCH_VFM(INTEL_SKYLAKE_L, &skl_uncore_init), + X86_MATCH_VFM(INTEL_SKYLAKE_X, &skx_uncore_init), + X86_MATCH_VFM(INTEL_KABYLAKE_L, &skl_uncore_init), + X86_MATCH_VFM(INTEL_KABYLAKE, &skl_uncore_init), + X86_MATCH_VFM(INTEL_COMETLAKE_L, &skl_uncore_init), + X86_MATCH_VFM(INTEL_COMETLAKE, &skl_uncore_init), + X86_MATCH_VFM(INTEL_ICELAKE_L, &icl_uncore_init), + X86_MATCH_VFM(INTEL_ICELAKE_NNPI, &icl_uncore_init), + X86_MATCH_VFM(INTEL_ICELAKE, &icl_uncore_init), + X86_MATCH_VFM(INTEL_ICELAKE_D, &icx_uncore_init), + X86_MATCH_VFM(INTEL_ICELAKE_X, &icx_uncore_init), + X86_MATCH_VFM(INTEL_TIGERLAKE_L, &tgl_l_uncore_init), + X86_MATCH_VFM(INTEL_TIGERLAKE, &tgl_uncore_init), + X86_MATCH_VFM(INTEL_ROCKETLAKE, &rkl_uncore_init), + X86_MATCH_VFM(INTEL_ALDERLAKE, &adl_uncore_init), + X86_MATCH_VFM(INTEL_ALDERLAKE_L, &adl_uncore_init), + X86_MATCH_VFM(INTEL_RAPTORLAKE, &adl_uncore_init), + X86_MATCH_VFM(INTEL_RAPTORLAKE_P, &adl_uncore_init), + X86_MATCH_VFM(INTEL_RAPTORLAKE_S, &adl_uncore_init), + X86_MATCH_VFM(INTEL_METEORLAKE, &mtl_uncore_init), + X86_MATCH_VFM(INTEL_METEORLAKE_L, &mtl_uncore_init), + X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, &spr_uncore_init), + X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, &spr_uncore_init), + X86_MATCH_VFM(INTEL_GRANITERAPIDS_X, &gnr_uncore_init), + X86_MATCH_VFM(INTEL_GRANITERAPIDS_D, &gnr_uncore_init), + X86_MATCH_VFM(INTEL_ATOM_TREMONT_D, &snr_uncore_init), + X86_MATCH_VFM(INTEL_ATOM_GRACEMONT, &adl_uncore_init), + X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X, &gnr_uncore_init), + X86_MATCH_VFM(INTEL_ATOM_CRESTMONT, &gnr_uncore_init), {}, }; MODULE_DEVICE_TABLE(x86cpu, intel_uncore_match); diff --git a/arch/x86/events/intel/uncore_nhmex.c b/arch/x86/events/intel/uncore_nhmex.c index 92da8aaa59..466833478e 100644 --- a/arch/x86/events/intel/uncore_nhmex.c +++ b/arch/x86/events/intel/uncore_nhmex.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* Nehalem-EX/Westmere-EX uncore support */ +#include <asm/cpu_device_id.h> #include "uncore.h" /* NHM-EX event control */ @@ -1217,7 +1218,7 @@ static struct intel_uncore_type *nhmex_msr_uncores[] = { void nhmex_uncore_cpu_init(void) { - if (boot_cpu_data.x86_model == 46) + if (boot_cpu_data.x86_vfm == INTEL_NEHALEM_EX) uncore_nhmex = true; else nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events; diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 2eaf0f3398..1891c2c782 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* SandyBridge-EP/IvyTown uncore support */ +#include <asm/cpu_device_id.h> #include "uncore.h" #include "uncore_discovery.h" @@ -461,6 +462,7 @@ #define SPR_UBOX_DID 0x3250 /* SPR CHA */ +#define SPR_CHA_EVENT_MASK_EXT 0xffffffff #define SPR_CHA_PMON_CTL_TID_EN (1 << 16) #define SPR_CHA_PMON_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \ SPR_CHA_PMON_CTL_TID_EN) @@ -477,6 +479,7 @@ DEFINE_UNCORE_FORMAT_ATTR(umask_ext, umask, "config:8-15,32-43,45-55"); DEFINE_UNCORE_FORMAT_ATTR(umask_ext2, umask, "config:8-15,32-57"); DEFINE_UNCORE_FORMAT_ATTR(umask_ext3, umask, "config:8-15,32-39"); DEFINE_UNCORE_FORMAT_ATTR(umask_ext4, umask, "config:8-15,32-55"); +DEFINE_UNCORE_FORMAT_ATTR(umask_ext5, umask, "config:8-15,32-63"); DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); @@ -3285,7 +3288,7 @@ void bdx_uncore_cpu_init(void) uncore_msr_uncores = bdx_msr_uncores; /* Detect systems with no SBOXes */ - if ((boot_cpu_data.x86_model == 86) || hswep_has_limit_sbox(BDX_PCU_DID)) + if (boot_cpu_data.x86_vfm == INTEL_BROADWELL_D || hswep_has_limit_sbox(BDX_PCU_DID)) uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL; hswep_uncore_pcu.constraints = bdx_uncore_pcu_constraints; @@ -5394,7 +5397,7 @@ static int icx_iio_get_topology(struct intel_uncore_type *type) static void icx_iio_set_mapping(struct intel_uncore_type *type) { /* Detect ICX-D system. This case is not supported */ - if (boot_cpu_data.x86_model == INTEL_FAM6_ICELAKE_D) { + if (boot_cpu_data.x86_vfm == INTEL_ICELAKE_D) { pmu_clear_mapping_attr(type->attr_update, &icx_iio_mapping_group); return; } @@ -5957,7 +5960,7 @@ static struct intel_uncore_ops spr_uncore_chabox_ops = { static struct attribute *spr_uncore_cha_formats_attr[] = { &format_attr_event.attr, - &format_attr_umask_ext4.attr, + &format_attr_umask_ext5.attr, &format_attr_tid_en2.attr, &format_attr_edge.attr, &format_attr_inv.attr, @@ -5993,7 +5996,7 @@ ATTRIBUTE_GROUPS(uncore_alias); static struct intel_uncore_type spr_uncore_chabox = { .name = "cha", .event_mask = SPR_CHA_PMON_EVENT_MASK, - .event_mask_ext = SPR_RAW_EVENT_MASK_EXT, + .event_mask_ext = SPR_CHA_EVENT_MASK_EXT, .num_shared_regs = 1, .constraints = skx_uncore_chabox_constraints, .ops = &spr_uncore_chabox_ops, diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index 9e237b30f0..45b1866ff0 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -2,7 +2,7 @@ #include <linux/perf_event.h> #include <linux/sysfs.h> #include <linux/nospec.h> -#include <asm/intel-family.h> +#include <asm/cpu_device_id.h> #include "probe.h" enum perf_msr_id { @@ -43,75 +43,75 @@ static bool test_intel(int idx, void *data) boot_cpu_data.x86 != 6) return false; - switch (boot_cpu_data.x86_model) { - case INTEL_FAM6_NEHALEM: - case INTEL_FAM6_NEHALEM_G: - case INTEL_FAM6_NEHALEM_EP: - case INTEL_FAM6_NEHALEM_EX: - - case INTEL_FAM6_WESTMERE: - case INTEL_FAM6_WESTMERE_EP: - case INTEL_FAM6_WESTMERE_EX: - - case INTEL_FAM6_SANDYBRIDGE: - case INTEL_FAM6_SANDYBRIDGE_X: - - case INTEL_FAM6_IVYBRIDGE: - case INTEL_FAM6_IVYBRIDGE_X: - - case INTEL_FAM6_HASWELL: - case INTEL_FAM6_HASWELL_X: - case INTEL_FAM6_HASWELL_L: - case INTEL_FAM6_HASWELL_G: - - case INTEL_FAM6_BROADWELL: - case INTEL_FAM6_BROADWELL_D: - case INTEL_FAM6_BROADWELL_G: - case INTEL_FAM6_BROADWELL_X: - case INTEL_FAM6_SAPPHIRERAPIDS_X: - case INTEL_FAM6_EMERALDRAPIDS_X: - case INTEL_FAM6_GRANITERAPIDS_X: - case INTEL_FAM6_GRANITERAPIDS_D: - - case INTEL_FAM6_ATOM_SILVERMONT: - case INTEL_FAM6_ATOM_SILVERMONT_D: - case INTEL_FAM6_ATOM_AIRMONT: - - case INTEL_FAM6_ATOM_GOLDMONT: - case INTEL_FAM6_ATOM_GOLDMONT_D: - case INTEL_FAM6_ATOM_GOLDMONT_PLUS: - case INTEL_FAM6_ATOM_TREMONT_D: - case INTEL_FAM6_ATOM_TREMONT: - case INTEL_FAM6_ATOM_TREMONT_L: - - case INTEL_FAM6_XEON_PHI_KNL: - case INTEL_FAM6_XEON_PHI_KNM: + switch (boot_cpu_data.x86_vfm) { + case INTEL_NEHALEM: + case INTEL_NEHALEM_G: + case INTEL_NEHALEM_EP: + case INTEL_NEHALEM_EX: + + case INTEL_WESTMERE: + case INTEL_WESTMERE_EP: + case INTEL_WESTMERE_EX: + + case INTEL_SANDYBRIDGE: + case INTEL_SANDYBRIDGE_X: + + case INTEL_IVYBRIDGE: + case INTEL_IVYBRIDGE_X: + + case INTEL_HASWELL: + case INTEL_HASWELL_X: + case INTEL_HASWELL_L: + case INTEL_HASWELL_G: + + case INTEL_BROADWELL: + case INTEL_BROADWELL_D: + case INTEL_BROADWELL_G: + case INTEL_BROADWELL_X: + case INTEL_SAPPHIRERAPIDS_X: + case INTEL_EMERALDRAPIDS_X: + case INTEL_GRANITERAPIDS_X: + case INTEL_GRANITERAPIDS_D: + + case INTEL_ATOM_SILVERMONT: + case INTEL_ATOM_SILVERMONT_D: + case INTEL_ATOM_AIRMONT: + + case INTEL_ATOM_GOLDMONT: + case INTEL_ATOM_GOLDMONT_D: + case INTEL_ATOM_GOLDMONT_PLUS: + case INTEL_ATOM_TREMONT_D: + case INTEL_ATOM_TREMONT: + case INTEL_ATOM_TREMONT_L: + + case INTEL_XEON_PHI_KNL: + case INTEL_XEON_PHI_KNM: if (idx == PERF_MSR_SMI) return true; break; - case INTEL_FAM6_SKYLAKE_L: - case INTEL_FAM6_SKYLAKE: - case INTEL_FAM6_SKYLAKE_X: - case INTEL_FAM6_KABYLAKE_L: - case INTEL_FAM6_KABYLAKE: - case INTEL_FAM6_COMETLAKE_L: - case INTEL_FAM6_COMETLAKE: - case INTEL_FAM6_ICELAKE_L: - case INTEL_FAM6_ICELAKE: - case INTEL_FAM6_ICELAKE_X: - case INTEL_FAM6_ICELAKE_D: - case INTEL_FAM6_TIGERLAKE_L: - case INTEL_FAM6_TIGERLAKE: - case INTEL_FAM6_ROCKETLAKE: - case INTEL_FAM6_ALDERLAKE: - case INTEL_FAM6_ALDERLAKE_L: - case INTEL_FAM6_ATOM_GRACEMONT: - case INTEL_FAM6_RAPTORLAKE: - case INTEL_FAM6_RAPTORLAKE_P: - case INTEL_FAM6_RAPTORLAKE_S: - case INTEL_FAM6_METEORLAKE: - case INTEL_FAM6_METEORLAKE_L: + case INTEL_SKYLAKE_L: + case INTEL_SKYLAKE: + case INTEL_SKYLAKE_X: + case INTEL_KABYLAKE_L: + case INTEL_KABYLAKE: + case INTEL_COMETLAKE_L: + case INTEL_COMETLAKE: + case INTEL_ICELAKE_L: + case INTEL_ICELAKE: + case INTEL_ICELAKE_X: + case INTEL_ICELAKE_D: + case INTEL_TIGERLAKE_L: + case INTEL_TIGERLAKE: + case INTEL_ROCKETLAKE: + case INTEL_ALDERLAKE: + case INTEL_ALDERLAKE_L: + case INTEL_ATOM_GRACEMONT: + case INTEL_RAPTORLAKE: + case INTEL_RAPTORLAKE_P: + case INTEL_RAPTORLAKE_S: + case INTEL_METEORLAKE: + case INTEL_METEORLAKE_L: if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF) return true; break; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index fb56518356..72b022a1e1 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -1329,6 +1329,19 @@ void amd_pmu_lbr_enable_all(void); void amd_pmu_lbr_disable_all(void); int amd_pmu_lbr_hw_config(struct perf_event *event); +static __always_inline void __amd_pmu_lbr_disable(void) +{ + u64 dbg_ctl, dbg_extn_cfg; + + rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg); + wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg & ~DBG_EXTN_CFG_LBRV2EN); + + 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); + } +} + #ifdef CONFIG_PERF_EVENTS_AMD_BRS #define AMD_FAM19H_BRS_EVENT 0xc4 /* RETIRED_TAKEN_BRANCH_INSTRUCTIONS */ diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index fb2b1961e5..0c5e7a7c43 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -64,6 +64,7 @@ #include "perf_event.h" #include "probe.h" +MODULE_DESCRIPTION("Support Intel/AMD RAPL energy consumption counters"); MODULE_LICENSE("GPL"); /* @@ -114,8 +115,8 @@ struct rapl_pmu { struct rapl_pmus { struct pmu pmu; - unsigned int maxdie; - struct rapl_pmu *pmus[] __counted_by(maxdie); + unsigned int nr_rapl_pmu; + struct rapl_pmu *pmus[] __counted_by(nr_rapl_pmu); }; enum rapl_unit_quirk { @@ -141,13 +142,13 @@ static struct perf_msr *rapl_msrs; static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu) { - unsigned int dieid = topology_logical_die_id(cpu); + unsigned int rapl_pmu_idx = topology_logical_die_id(cpu); /* * The unsigned check also catches the '-1' return value for non * existent mappings in the topology map. */ - return dieid < rapl_pmus->maxdie ? rapl_pmus->pmus[dieid] : NULL; + return rapl_pmu_idx < rapl_pmus->nr_rapl_pmu ? rapl_pmus->pmus[rapl_pmu_idx] : NULL; } static inline u64 rapl_read_counter(struct perf_event *event) @@ -658,7 +659,7 @@ static void cleanup_rapl_pmus(void) { int i; - for (i = 0; i < rapl_pmus->maxdie; i++) + for (i = 0; i < rapl_pmus->nr_rapl_pmu; i++) kfree(rapl_pmus->pmus[i]); kfree(rapl_pmus); } @@ -674,15 +675,13 @@ static const struct attribute_group *rapl_attr_update[] = { static int __init init_rapl_pmus(void) { - int maxdie = topology_max_packages() * topology_max_dies_per_package(); - size_t size; + int nr_rapl_pmu = topology_max_packages() * topology_max_dies_per_package(); - size = sizeof(*rapl_pmus) + maxdie * sizeof(struct rapl_pmu *); - rapl_pmus = kzalloc(size, GFP_KERNEL); + rapl_pmus = kzalloc(struct_size(rapl_pmus, pmus, nr_rapl_pmu), GFP_KERNEL); if (!rapl_pmus) return -ENOMEM; - rapl_pmus->maxdie = maxdie; + rapl_pmus->nr_rapl_pmu = nr_rapl_pmu; rapl_pmus->pmu.attr_groups = rapl_attr_groups; rapl_pmus->pmu.attr_update = rapl_attr_update; rapl_pmus->pmu.task_ctx_nr = perf_invalid_context; @@ -808,6 +807,9 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(ARROWLAKE_H, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(ARROWLAKE, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(LUNARLAKE_M, &model_skl), {}, }; MODULE_DEVICE_TABLE(x86cpu, rapl_model_match); |