diff options
Diffstat (limited to 'arch/x86/events/intel')
| -rw-r--r-- | arch/x86/events/intel/core.c | 39 | ||||
| -rw-r--r-- | arch/x86/events/intel/cqm.c | 27 | ||||
| -rw-r--r-- | arch/x86/events/intel/cstate.c | 16 | ||||
| -rw-r--r-- | arch/x86/events/intel/ds.c | 6 | ||||
| -rw-r--r-- | arch/x86/events/intel/rapl.c | 5 | ||||
| -rw-r--r-- | arch/x86/events/intel/uncore.c | 11 | ||||
| -rw-r--r-- | arch/x86/events/intel/uncore_snbep.c | 4 |
7 files changed, 56 insertions, 52 deletions
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index cb8522290e6a..eb1484c86bb4 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2110,6 +2110,27 @@ again: GLOBAL_STATUS_LBRS_FROZEN); if (!status) goto done; + /* + * In case multiple PEBS events are sampled at the same time, + * it is possible to have GLOBAL_STATUS bit 62 set indicating + * PEBS buffer overflow and also seeing at most 3 PEBS counters + * having their bits set in the status register. This is a sign + * that there was at least one PEBS record pending at the time + * of the PMU interrupt. PEBS counters must only be processed + * via the drain_pebs() calls and not via the regular sample + * processing loop coming after that the function, otherwise + * phony regular samples may be generated in the sampling buffer + * not marked with the EXACT tag. Another possibility is to have + * one PEBS event and at least one non-PEBS event whic hoverflows + * while PEBS has armed. In this case, bit 62 of GLOBAL_STATUS will + * not be set, yet the overflow status bit for the PEBS counter will + * be on Skylake. + * + * To avoid this problem, we systematically ignore the PEBS-enabled + * counters from the GLOBAL_STATUS mask and we always process PEBS + * events via drain_pebs(). + */ + status &= ~cpuc->pebs_enabled; /* * PEBS overflow sets bit 62 in the global status register @@ -2117,15 +2138,6 @@ again: if (__test_and_clear_bit(62, (unsigned long *)&status)) { handled++; x86_pmu.drain_pebs(regs); - /* - * There are cases where, even though, the PEBS ovfl bit is set - * in GLOBAL_OVF_STATUS, the PEBS events may also have their - * overflow bits set for their counters. We must clear them - * here because they have been processed as exact samples in - * the drain_pebs() routine. They must not be processed again - * in the for_each_bit_set() loop for regular samples below. - */ - status &= ~cpuc->pebs_enabled; status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI; } @@ -3164,13 +3176,16 @@ static void intel_pmu_cpu_starting(int cpu) if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) { for_each_cpu(i, topology_sibling_cpumask(cpu)) { + struct cpu_hw_events *sibling; struct intel_excl_cntrs *c; - c = per_cpu(cpu_hw_events, i).excl_cntrs; + sibling = &per_cpu(cpu_hw_events, i); + c = sibling->excl_cntrs; if (c && c->core_id == core_id) { cpuc->kfree_on_online[1] = cpuc->excl_cntrs; cpuc->excl_cntrs = c; - cpuc->excl_thread_id = 1; + if (!sibling->excl_thread_id) + cpuc->excl_thread_id = 1; break; } } @@ -3975,7 +3990,7 @@ __init int intel_pmu_init(void) x86_pmu.num_counters, INTEL_PMC_MAX_GENERIC); x86_pmu.num_counters = INTEL_PMC_MAX_GENERIC; } - x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1; + x86_pmu.intel_ctrl = (1ULL << x86_pmu.num_counters) - 1; if (x86_pmu.num_counters_fixed > INTEL_PMC_MAX_FIXED) { WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!", diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c index 8f82b02934fa..8c00dc09a5d2 100644 --- a/arch/x86/events/intel/cqm.c +++ b/arch/x86/events/intel/cqm.c @@ -7,9 +7,9 @@ #include <linux/perf_event.h> #include <linux/slab.h> #include <asm/cpu_device_id.h> +#include <asm/intel_rdt_common.h> #include "../perf_event.h" -#define MSR_IA32_PQR_ASSOC 0x0c8f #define MSR_IA32_QM_CTR 0x0c8e #define MSR_IA32_QM_EVTSEL 0x0c8d @@ -24,32 +24,13 @@ static unsigned int cqm_l3_scale; /* supposedly cacheline size */ static bool cqm_enabled, mbm_enabled; unsigned int mbm_socket_max; -/** - * struct intel_pqr_state - State cache for the PQR MSR - * @rmid: The cached Resource Monitoring ID - * @closid: The cached Class Of Service ID - * @rmid_usecnt: The usage counter for rmid - * - * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the - * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always - * contains both parts, so we need to cache them. - * - * The cache also helps to avoid pointless updates if the value does - * not change. - */ -struct intel_pqr_state { - u32 rmid; - u32 closid; - int rmid_usecnt; -}; - /* * The cached intel_pqr_state is strictly per CPU and can never be * updated from a remote CPU. Both functions which modify the state * (intel_cqm_event_start and intel_cqm_event_stop) are called with * interrupts disabled, which is sufficient for the protection. */ -static DEFINE_PER_CPU(struct intel_pqr_state, pqr_state); +DEFINE_PER_CPU(struct intel_pqr_state, pqr_state); static struct hrtimer *mbm_timers; /** * struct sample - mbm event's (local or total) data @@ -1766,9 +1747,9 @@ static int __init intel_cqm_init(void) * is enabled to avoid notifier leak. */ cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_STARTING, - "AP_PERF_X86_CQM_STARTING", + "perf/x86/cqm:starting", intel_cqm_cpu_starting, NULL); - cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_ONLINE, "AP_PERF_X86_CQM_ONLINE", + cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_ONLINE, "perf/x86/cqm:online", NULL, intel_cqm_cpu_exit); out: diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index da51e5a3e2ff..1076c9a77292 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -434,6 +434,7 @@ static struct pmu cstate_core_pmu = { .stop = cstate_pmu_event_stop, .read = cstate_pmu_event_update, .capabilities = PERF_PMU_CAP_NO_INTERRUPT, + .module = THIS_MODULE, }; static struct pmu cstate_pkg_pmu = { @@ -447,6 +448,7 @@ static struct pmu cstate_pkg_pmu = { .stop = cstate_pmu_event_stop, .read = cstate_pmu_event_update, .capabilities = PERF_PMU_CAP_NO_INTERRUPT, + .module = THIS_MODULE, }; static const struct cstate_model nhm_cstates __initconst = { @@ -594,6 +596,9 @@ static int __init cstate_probe(const struct cstate_model *cm) static inline void cstate_cleanup(void) { + cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_CSTATE_ONLINE); + cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_CSTATE_STARTING); + if (has_cstate_core) perf_pmu_unregister(&cstate_core_pmu); @@ -606,16 +611,16 @@ static int __init cstate_init(void) int err; cpuhp_setup_state(CPUHP_AP_PERF_X86_CSTATE_STARTING, - "AP_PERF_X86_CSTATE_STARTING", cstate_cpu_init, - NULL); + "perf/x86/cstate:starting", cstate_cpu_init, NULL); cpuhp_setup_state(CPUHP_AP_PERF_X86_CSTATE_ONLINE, - "AP_PERF_X86_CSTATE_ONLINE", NULL, cstate_cpu_exit); + "perf/x86/cstate:online", NULL, cstate_cpu_exit); if (has_cstate_core) { err = perf_pmu_register(&cstate_core_pmu, cstate_core_pmu.name, -1); if (err) { has_cstate_core = false; pr_info("Failed to register cstate core pmu\n"); + cstate_cleanup(); return err; } } @@ -629,8 +634,7 @@ static int __init cstate_init(void) return err; } } - - return err; + return 0; } static int __init cstate_pmu_init(void) @@ -655,8 +659,6 @@ module_init(cstate_pmu_init); static void __exit cstate_pmu_exit(void) { - cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_CSTATE_ONLINE); - cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_CSTATE_STARTING); cstate_cleanup(); } module_exit(cstate_pmu_exit); diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index be202390bbd3..9dfeeeca0ea8 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1389,9 +1389,13 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) continue; /* log dropped samples number */ - if (error[bit]) + if (error[bit]) { perf_log_lost_samples(event, error[bit]); + if (perf_event_account_interrupt(event)) + x86_pmu_stop(event, 0); + } + if (counts[bit]) { __intel_pmu_pebs_event(event, iregs, base, top, bit, counts[bit]); diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 0a535cea8ff3..17c3564d087a 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -697,6 +697,7 @@ static int __init init_rapl_pmus(void) rapl_pmus->pmu.start = rapl_pmu_event_start; rapl_pmus->pmu.stop = rapl_pmu_event_stop; rapl_pmus->pmu.read = rapl_pmu_event_read; + rapl_pmus->pmu.module = THIS_MODULE; return 0; } @@ -803,13 +804,13 @@ static int __init rapl_pmu_init(void) * Install callbacks. Core will call them for each online cpu. */ - ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "PERF_X86_RAPL_PREP", + ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "perf/x86/rapl:prepare", rapl_cpu_prepare, NULL); if (ret) goto out; ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE, - "AP_PERF_X86_RAPL_ONLINE", + "perf/x86/rapl:online", rapl_cpu_online, rapl_cpu_offline); if (ret) goto out1; diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index dbaaf7dc8373..8c4ccdc3a3f3 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -733,6 +733,7 @@ static int uncore_pmu_register(struct intel_uncore_pmu *pmu) .start = uncore_pmu_event_start, .stop = uncore_pmu_event_stop, .read = uncore_pmu_event_read, + .module = THIS_MODULE, }; } else { pmu->pmu = *pmu->type->pmu; @@ -1398,22 +1399,22 @@ static int __init intel_uncore_init(void) */ if (!cret) { ret = cpuhp_setup_state(CPUHP_PERF_X86_UNCORE_PREP, - "PERF_X86_UNCORE_PREP", - uncore_cpu_prepare, NULL); + "perf/x86/intel/uncore:prepare", + uncore_cpu_prepare, NULL); if (ret) goto err; } else { cpuhp_setup_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP, - "PERF_X86_UNCORE_PREP", + "perf/x86/intel/uncore:prepare", uncore_cpu_prepare, NULL); } first_init = 1; cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_STARTING, - "AP_PERF_X86_UNCORE_STARTING", + "perf/x86/uncore:starting", uncore_cpu_starting, uncore_cpu_dying); first_init = 0; cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE, - "AP_PERF_X86_UNCORE_ONLINE", + "perf/x86/uncore:online", uncore_event_cpu_online, uncore_event_cpu_offline); return 0; diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 272427700d48..dae2fedc1601 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -669,7 +669,7 @@ static struct event_constraint snbep_uncore_cbox_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x1c, 0xc), UNCORE_EVENT_CONSTRAINT(0x1d, 0xc), UNCORE_EVENT_CONSTRAINT(0x1e, 0xc), - EVENT_CONSTRAINT_OVERLAP(0x1f, 0xe, 0xff), + UNCORE_EVENT_CONSTRAINT(0x1f, 0xe), UNCORE_EVENT_CONSTRAINT(0x21, 0x3), UNCORE_EVENT_CONSTRAINT(0x23, 0x3), UNCORE_EVENT_CONSTRAINT(0x31, 0x3), @@ -2686,7 +2686,7 @@ static struct intel_uncore_type *hswep_msr_uncores[] = { void hswep_uncore_cpu_init(void) { - int pkg = topology_phys_to_logical_pkg(0); + int pkg = boot_cpu_data.logical_proc_id; if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; |