summaryrefslogtreecommitdiffstats
path: root/arch/x86/events
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/events')
-rw-r--r--arch/x86/events/amd/core.c65
-rw-r--r--arch/x86/events/amd/lbr.c13
-rw-r--r--arch/x86/events/amd/uncore.c36
-rw-r--r--arch/x86/events/core.c119
-rw-r--r--arch/x86/events/intel/core.c339
-rw-r--r--arch/x86/events/intel/cstate.c193
-rw-r--r--arch/x86/events/intel/ds.c42
-rw-r--r--arch/x86/events/intel/knc.c2
-rw-r--r--arch/x86/events/intel/lbr.c3
-rw-r--r--arch/x86/events/intel/p4.c10
-rw-r--r--arch/x86/events/intel/p6.c2
-rw-r--r--arch/x86/events/intel/pt.c16
-rw-r--r--arch/x86/events/intel/pt.h4
-rw-r--r--arch/x86/events/intel/uncore.c101
-rw-r--r--arch/x86/events/intel/uncore_nhmex.c3
-rw-r--r--arch/x86/events/intel/uncore_snbep.c11
-rw-r--r--arch/x86/events/msr.c132
-rw-r--r--arch/x86/events/perf_event.h75
-rw-r--r--arch/x86/events/rapl.c22
-rw-r--r--arch/x86/events/zhaoxin/core.c12
20 files changed, 652 insertions, 548 deletions
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 985ef3b479..920e3a640c 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -432,8 +432,10 @@ static void __amd_put_nb_event_constraints(struct cpu_hw_events *cpuc,
* be removed on one CPU at a time AND PMU is disabled
* when we come here
*/
- for (i = 0; i < x86_pmu.num_counters; i++) {
- if (cmpxchg(nb->owners + i, event, NULL) == event)
+ for_each_set_bit(i, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
+ struct perf_event *tmp = event;
+
+ if (try_cmpxchg(nb->owners + i, &tmp, NULL))
break;
}
}
@@ -499,7 +501,7 @@ __amd_get_nb_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *ev
* because of successive calls to x86_schedule_events() from
* hw_perf_group_sched_in() without hw_perf_enable()
*/
- for_each_set_bit(idx, c->idxmsk, x86_pmu.num_counters) {
+ for_each_set_bit(idx, c->idxmsk, x86_pmu_max_num_counters(NULL)) {
if (new == -1 || hwc->idx == idx)
/* assign free slot, prefer hwc->idx */
old = cmpxchg(nb->owners + idx, NULL, event);
@@ -542,7 +544,7 @@ static struct amd_nb *amd_alloc_nb(int cpu)
/*
* initialize all possible NB constraints
*/
- for (i = 0; i < x86_pmu.num_counters; i++) {
+ for_each_set_bit(i, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
__set_bit(i, nb->event_constraints[i].idxmsk);
nb->event_constraints[i].weight = 1;
}
@@ -647,7 +649,7 @@ 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);
}
@@ -735,7 +737,7 @@ static void amd_pmu_check_overflow(void)
* counters are always enabled when this function is called and
* ARCH_PERFMON_EVENTSEL_INT is always set.
*/
- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
if (!test_bit(idx, cpuc->active_mask))
continue;
@@ -755,7 +757,7 @@ static void amd_pmu_enable_all(int added)
amd_brs_enable_all();
- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
/* only activate events which are marked as active */
if (!test_bit(idx, cpuc->active_mask))
continue;
@@ -907,6 +909,37 @@ 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);
@@ -947,7 +980,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
/* Clear any reserved bits set by buggy microcode */
status &= amd_pmu_global_cntr_mask;
- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
if (!test_bit(idx, cpuc->active_mask))
continue;
@@ -1282,7 +1315,7 @@ static __initconst const struct x86_pmu amd_pmu = {
.addr_offset = amd_pmu_addr_offset,
.event_map = amd_pmu_event_map,
.max_events = ARRAY_SIZE(amd_perfmon_event_map),
- .num_counters = AMD64_NUM_COUNTERS,
+ .cntr_mask64 = GENMASK_ULL(AMD64_NUM_COUNTERS - 1, 0),
.add = amd_pmu_add_event,
.del = amd_pmu_del_event,
.cntval_bits = 48,
@@ -1381,7 +1414,7 @@ static int __init amd_core_pmu_init(void)
*/
x86_pmu.eventsel = MSR_F15H_PERF_CTL;
x86_pmu.perfctr = MSR_F15H_PERF_CTR;
- x86_pmu.num_counters = AMD64_NUM_COUNTERS_CORE;
+ x86_pmu.cntr_mask64 = GENMASK_ULL(AMD64_NUM_COUNTERS_CORE - 1, 0);
/* Check for Performance Monitoring v2 support */
if (boot_cpu_has(X86_FEATURE_PERFMON_V2)) {
@@ -1391,9 +1424,9 @@ static int __init amd_core_pmu_init(void)
x86_pmu.version = 2;
/* Find the number of available Core PMCs */
- x86_pmu.num_counters = ebx.split.num_core_pmc;
+ x86_pmu.cntr_mask64 = GENMASK_ULL(ebx.split.num_core_pmc - 1, 0);
- amd_pmu_global_cntr_mask = (1ULL << x86_pmu.num_counters) - 1;
+ amd_pmu_global_cntr_mask = x86_pmu.cntr_mask64;
/* Update PMC handling functions */
x86_pmu.enable_all = amd_pmu_v2_enable_all;
@@ -1421,12 +1454,12 @@ static int __init amd_core_pmu_init(void)
* even numbered counter that has a consecutive adjacent odd
* numbered counter following it.
*/
- for (i = 0; i < x86_pmu.num_counters - 1; i += 2)
+ for (i = 0; i < x86_pmu_max_num_counters(NULL) - 1; i += 2)
even_ctr_mask |= BIT_ULL(i);
pair_constraint = (struct event_constraint)
__EVENT_CONSTRAINT(0, even_ctr_mask, 0,
- x86_pmu.num_counters / 2, 0,
+ x86_pmu_max_num_counters(NULL) / 2, 0,
PERF_X86_EVENT_PAIR);
x86_pmu.get_event_constraints = amd_get_event_constraints_f17h;
@@ -1443,6 +1476,10 @@ 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..0bfde2ea5c 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -162,7 +162,9 @@ static int amd_uncore_add(struct perf_event *event, int flags)
/* if not, take the first available counter */
hwc->idx = -1;
for (i = 0; i < pmu->num_counters; i++) {
- if (cmpxchg(&ctx->events[i], NULL, event) == NULL) {
+ struct perf_event *tmp = NULL;
+
+ if (try_cmpxchg(&ctx->events[i], &tmp, event)) {
hwc->idx = i;
break;
}
@@ -196,7 +198,9 @@ static void amd_uncore_del(struct perf_event *event, int flags)
event->pmu->stop(event, PERF_EF_UPDATE);
for (i = 0; i < pmu->num_counters; i++) {
- if (cmpxchg(&ctx->events[i], event, NULL) == event)
+ struct perf_event *tmp = event;
+
+ if (try_cmpxchg(&ctx->events[i], &tmp, NULL))
break;
}
@@ -639,7 +643,7 @@ 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 +658,20 @@ 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 +681,7 @@ 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 +792,20 @@ 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 +815,7 @@ 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 +903,8 @@ 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..83d12dd3f8 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -189,29 +189,31 @@ static DEFINE_MUTEX(pmc_reserve_mutex);
#ifdef CONFIG_X86_LOCAL_APIC
-static inline int get_possible_num_counters(void)
+static inline u64 get_possible_counter_mask(void)
{
- int i, num_counters = x86_pmu.num_counters;
+ u64 cntr_mask = x86_pmu.cntr_mask64;
+ int i;
if (!is_hybrid())
- return num_counters;
+ return cntr_mask;
for (i = 0; i < x86_pmu.num_hybrid_pmus; i++)
- num_counters = max_t(int, num_counters, x86_pmu.hybrid_pmu[i].num_counters);
+ cntr_mask |= x86_pmu.hybrid_pmu[i].cntr_mask64;
- return num_counters;
+ return cntr_mask;
}
static bool reserve_pmc_hardware(void)
{
- int i, num_counters = get_possible_num_counters();
+ u64 cntr_mask = get_possible_counter_mask();
+ int i, end;
- for (i = 0; i < num_counters; i++) {
+ for_each_set_bit(i, (unsigned long *)&cntr_mask, X86_PMC_IDX_MAX) {
if (!reserve_perfctr_nmi(x86_pmu_event_addr(i)))
goto perfctr_fail;
}
- for (i = 0; i < num_counters; i++) {
+ for_each_set_bit(i, (unsigned long *)&cntr_mask, X86_PMC_IDX_MAX) {
if (!reserve_evntsel_nmi(x86_pmu_config_addr(i)))
goto eventsel_fail;
}
@@ -219,13 +221,14 @@ static bool reserve_pmc_hardware(void)
return true;
eventsel_fail:
- for (i--; i >= 0; i--)
+ end = i;
+ for_each_set_bit(i, (unsigned long *)&cntr_mask, end)
release_evntsel_nmi(x86_pmu_config_addr(i));
-
- i = num_counters;
+ i = X86_PMC_IDX_MAX;
perfctr_fail:
- for (i--; i >= 0; i--)
+ end = i;
+ for_each_set_bit(i, (unsigned long *)&cntr_mask, end)
release_perfctr_nmi(x86_pmu_event_addr(i));
return false;
@@ -233,9 +236,10 @@ perfctr_fail:
static void release_pmc_hardware(void)
{
- int i, num_counters = get_possible_num_counters();
+ u64 cntr_mask = get_possible_counter_mask();
+ int i;
- for (i = 0; i < num_counters; i++) {
+ for_each_set_bit(i, (unsigned long *)&cntr_mask, X86_PMC_IDX_MAX) {
release_perfctr_nmi(x86_pmu_event_addr(i));
release_evntsel_nmi(x86_pmu_config_addr(i));
}
@@ -248,7 +252,8 @@ static void release_pmc_hardware(void) {}
#endif
-bool check_hw_exists(struct pmu *pmu, int num_counters, int num_counters_fixed)
+bool check_hw_exists(struct pmu *pmu, unsigned long *cntr_mask,
+ unsigned long *fixed_cntr_mask)
{
u64 val, val_fail = -1, val_new= ~0;
int i, reg, reg_fail = -1, ret = 0;
@@ -259,7 +264,7 @@ bool check_hw_exists(struct pmu *pmu, int num_counters, int num_counters_fixed)
* Check to see if the BIOS enabled any of the counters, if so
* complain and bail.
*/
- for (i = 0; i < num_counters; i++) {
+ for_each_set_bit(i, cntr_mask, X86_PMC_IDX_MAX) {
reg = x86_pmu_config_addr(i);
ret = rdmsrl_safe(reg, &val);
if (ret)
@@ -273,12 +278,12 @@ bool check_hw_exists(struct pmu *pmu, int num_counters, int num_counters_fixed)
}
}
- if (num_counters_fixed) {
+ if (*(u64 *)fixed_cntr_mask) {
reg = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
ret = rdmsrl_safe(reg, &val);
if (ret)
goto msr_fail;
- for (i = 0; i < num_counters_fixed; i++) {
+ for_each_set_bit(i, fixed_cntr_mask, X86_PMC_IDX_MAX) {
if (fixed_counter_disabled(i, pmu))
continue;
if (val & (0x03ULL << i*4)) {
@@ -679,7 +684,7 @@ void x86_pmu_disable_all(void)
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int idx;
- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
struct hw_perf_event *hwc = &cpuc->events[idx]->hw;
u64 val;
@@ -736,7 +741,7 @@ void x86_pmu_enable_all(int added)
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int idx;
- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
struct hw_perf_event *hwc = &cpuc->events[idx]->hw;
if (!test_bit(idx, cpuc->active_mask))
@@ -975,7 +980,6 @@ EXPORT_SYMBOL_GPL(perf_assign_events);
int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
{
- int num_counters = hybrid(cpuc->pmu, num_counters);
struct event_constraint *c;
struct perf_event *e;
int n0, i, wmin, wmax, unsched = 0;
@@ -1051,7 +1055,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
/* slow path */
if (i != n) {
- int gpmax = num_counters;
+ int gpmax = x86_pmu_max_num_counters(cpuc->pmu);
/*
* Do not allow scheduling of more than half the available
@@ -1072,7 +1076,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
* the extra Merge events needed by large increment events.
*/
if (x86_pmu.flags & PMU_FL_PAIR) {
- gpmax = num_counters - cpuc->n_pair;
+ gpmax -= cpuc->n_pair;
WARN_ON(gpmax <= 0);
}
@@ -1157,12 +1161,10 @@ static int collect_event(struct cpu_hw_events *cpuc, struct perf_event *event,
*/
static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, bool dogrp)
{
- int num_counters = hybrid(cpuc->pmu, num_counters);
- int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
struct perf_event *event;
int n, max_count;
- max_count = num_counters + num_counters_fixed;
+ max_count = x86_pmu_num_counters(cpuc->pmu) + x86_pmu_num_counters_fixed(cpuc->pmu);
/* current number of events already accepted */
n = cpuc->n_events;
@@ -1519,19 +1521,22 @@ static void x86_pmu_start(struct perf_event *event, int flags)
void perf_event_print_debug(void)
{
u64 ctrl, status, overflow, pmc_ctrl, pmc_count, prev_left, fixed;
+ unsigned long *cntr_mask, *fixed_cntr_mask;
+ struct event_constraint *pebs_constraints;
+ struct cpu_hw_events *cpuc;
u64 pebs, debugctl;
- int cpu = smp_processor_id();
- struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
- int num_counters = hybrid(cpuc->pmu, num_counters);
- int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
- struct event_constraint *pebs_constraints = hybrid(cpuc->pmu, pebs_constraints);
- unsigned long flags;
- int idx;
+ int cpu, idx;
- if (!num_counters)
- return;
+ guard(irqsave)();
- local_irq_save(flags);
+ cpu = smp_processor_id();
+ cpuc = &per_cpu(cpu_hw_events, cpu);
+ cntr_mask = hybrid(cpuc->pmu, cntr_mask);
+ fixed_cntr_mask = hybrid(cpuc->pmu, fixed_cntr_mask);
+ pebs_constraints = hybrid(cpuc->pmu, pebs_constraints);
+
+ if (!*(u64 *)cntr_mask)
+ return;
if (x86_pmu.version >= 2) {
rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, ctrl);
@@ -1555,7 +1560,7 @@ void perf_event_print_debug(void)
}
pr_info("CPU#%d: active: %016llx\n", cpu, *(u64 *)cpuc->active_mask);
- for (idx = 0; idx < num_counters; idx++) {
+ for_each_set_bit(idx, cntr_mask, X86_PMC_IDX_MAX) {
rdmsrl(x86_pmu_config_addr(idx), pmc_ctrl);
rdmsrl(x86_pmu_event_addr(idx), pmc_count);
@@ -1568,7 +1573,7 @@ void perf_event_print_debug(void)
pr_info("CPU#%d: gen-PMC%d left: %016llx\n",
cpu, idx, prev_left);
}
- for (idx = 0; idx < num_counters_fixed; idx++) {
+ for_each_set_bit(idx, fixed_cntr_mask, X86_PMC_IDX_MAX) {
if (fixed_counter_disabled(idx, cpuc->pmu))
continue;
rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, pmc_count);
@@ -1576,7 +1581,6 @@ void perf_event_print_debug(void)
pr_info("CPU#%d: fixed-PMC%d count: %016llx\n",
cpu, idx, pmc_count);
}
- local_irq_restore(flags);
}
void x86_pmu_stop(struct perf_event *event, int flags)
@@ -1682,7 +1686,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
*/
apic_write(APIC_LVTPC, APIC_DM_NMI);
- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
if (!test_bit(idx, cpuc->active_mask))
continue;
@@ -2038,18 +2042,15 @@ static void _x86_pmu_read(struct perf_event *event)
static_call(x86_pmu_update)(event);
}
-void x86_pmu_show_pmu_cap(int num_counters, int num_counters_fixed,
- u64 intel_ctrl)
+void x86_pmu_show_pmu_cap(struct pmu *pmu)
{
pr_info("... version: %d\n", x86_pmu.version);
pr_info("... bit width: %d\n", x86_pmu.cntval_bits);
- pr_info("... generic registers: %d\n", num_counters);
+ pr_info("... generic registers: %d\n", x86_pmu_num_counters(pmu));
pr_info("... value mask: %016Lx\n", x86_pmu.cntval_mask);
pr_info("... max period: %016Lx\n", x86_pmu.max_period);
- pr_info("... fixed-purpose events: %lu\n",
- hweight64((((1ULL << num_counters_fixed) - 1)
- << INTEL_PMC_IDX_FIXED) & intel_ctrl));
- pr_info("... event mask: %016Lx\n", intel_ctrl);
+ pr_info("... fixed-purpose events: %d\n", x86_pmu_num_counters_fixed(pmu));
+ pr_info("... event mask: %016Lx\n", hybrid(pmu, intel_ctrl));
}
static int __init init_hw_perf_events(void)
@@ -2086,7 +2087,7 @@ static int __init init_hw_perf_events(void)
pmu_check_apic();
/* sanity check that the hardware exists or is emulated */
- if (!check_hw_exists(&pmu, x86_pmu.num_counters, x86_pmu.num_counters_fixed))
+ if (!check_hw_exists(&pmu, x86_pmu.cntr_mask, x86_pmu.fixed_cntr_mask))
goto out_bad_pmu;
pr_cont("%s PMU driver.\n", x86_pmu.name);
@@ -2097,14 +2098,14 @@ static int __init init_hw_perf_events(void)
quirk->func();
if (!x86_pmu.intel_ctrl)
- x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
+ x86_pmu.intel_ctrl = x86_pmu.cntr_mask64;
perf_events_lapic_init();
register_nmi_handler(NMI_LOCAL, perf_event_nmi_handler, 0, "PMI");
unconstrained = (struct event_constraint)
- __EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1,
- 0, x86_pmu.num_counters, 0, 0);
+ __EVENT_CONSTRAINT(0, x86_pmu.cntr_mask64,
+ 0, x86_pmu_num_counters(NULL), 0, 0);
x86_pmu_format_group.attrs = x86_pmu.format_attrs;
@@ -2113,11 +2114,8 @@ static int __init init_hw_perf_events(void)
pmu.attr_update = x86_pmu.attr_update;
- if (!is_hybrid()) {
- x86_pmu_show_pmu_cap(x86_pmu.num_counters,
- x86_pmu.num_counters_fixed,
- x86_pmu.intel_ctrl);
- }
+ if (!is_hybrid())
+ x86_pmu_show_pmu_cap(NULL);
if (!x86_pmu.read)
x86_pmu.read = _x86_pmu_read;
@@ -2481,7 +2479,7 @@ void perf_clear_dirty_counters(void)
for_each_set_bit(i, cpuc->dirty, X86_PMC_IDX_MAX) {
if (i >= INTEL_PMC_IDX_FIXED) {
/* Metrics and fake events don't have corresponding HW counters. */
- if ((i - INTEL_PMC_IDX_FIXED) >= hybrid(cpuc->pmu, num_counters_fixed))
+ if (!test_bit(i - INTEL_PMC_IDX_FIXED, hybrid(cpuc->pmu, fixed_cntr_mask)))
continue;
wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + (i - INTEL_PMC_IDX_FIXED), 0);
@@ -2547,6 +2545,7 @@ 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 +2559,8 @@ 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,
@@ -2983,8 +2984,8 @@ void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
* base PMU holds the correct number of counters for P-cores.
*/
cap->version = x86_pmu.version;
- cap->num_counters_gp = x86_pmu.num_counters;
- cap->num_counters_fixed = x86_pmu.num_counters_fixed;
+ cap->num_counters_gp = x86_pmu_num_counters(NULL);
+ cap->num_counters_fixed = x86_pmu_num_counters_fixed(NULL);
cap->bit_width_gp = x86_pmu.cntval_bits;
cap->bit_width_fixed = x86_pmu.cntval_bits;
cap->events_mask = (unsigned int)x86_pmu.events_maskl;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 768d141489..f25205d047 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2874,23 +2874,23 @@ static void intel_pmu_reset(void)
{
struct debug_store *ds = __this_cpu_read(cpu_hw_events.ds);
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
- int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
- int num_counters = hybrid(cpuc->pmu, num_counters);
+ unsigned long *cntr_mask = hybrid(cpuc->pmu, cntr_mask);
+ unsigned long *fixed_cntr_mask = hybrid(cpuc->pmu, fixed_cntr_mask);
unsigned long flags;
int idx;
- if (!num_counters)
+ if (!*(u64 *)cntr_mask)
return;
local_irq_save(flags);
pr_info("clearing PMU state on CPU#%d\n", smp_processor_id());
- for (idx = 0; idx < num_counters; idx++) {
+ for_each_set_bit(idx, cntr_mask, INTEL_PMC_MAX_GENERIC) {
wrmsrl_safe(x86_pmu_config_addr(idx), 0ull);
wrmsrl_safe(x86_pmu_event_addr(idx), 0ull);
}
- for (idx = 0; idx < num_counters_fixed; idx++) {
+ for_each_set_bit(idx, fixed_cntr_mask, INTEL_PMC_MAX_FIXED) {
if (fixed_counter_disabled(idx, cpuc->pmu))
continue;
wrmsrl_safe(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
@@ -2940,8 +2940,7 @@ static void x86_pmu_handle_guest_pebs(struct pt_regs *regs,
!guest_pebs_idxs)
return;
- for_each_set_bit(bit, (unsigned long *)&guest_pebs_idxs,
- INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed) {
+ for_each_set_bit(bit, (unsigned long *)&guest_pebs_idxs, X86_PMC_IDX_MAX) {
event = cpuc->events[bit];
if (!event->attr.precise_ip)
continue;
@@ -4199,7 +4198,7 @@ static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr, void *data)
struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs;
int idx;
- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
struct perf_event *event = cpuc->events[idx];
arr[idx].msr = x86_pmu_config_addr(idx);
@@ -4217,7 +4216,7 @@ static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr, void *data)
arr[idx].guest &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
}
- *nr = x86_pmu.num_counters;
+ *nr = x86_pmu_max_num_counters(cpuc->pmu);
return arr;
}
@@ -4232,7 +4231,7 @@ static void core_pmu_enable_all(int added)
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int idx;
- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
struct hw_perf_event *hwc = &cpuc->events[idx]->hw;
if (!test_bit(idx, cpuc->active_mask) ||
@@ -4684,13 +4683,33 @@ static void flip_smm_bit(void *data)
}
}
-static void intel_pmu_check_num_counters(int *num_counters,
- int *num_counters_fixed,
- u64 *intel_ctrl, u64 fixed_mask);
+static void intel_pmu_check_counters_mask(u64 *cntr_mask,
+ u64 *fixed_cntr_mask,
+ u64 *intel_ctrl)
+{
+ unsigned int bit;
+
+ bit = fls64(*cntr_mask);
+ if (bit > INTEL_PMC_MAX_GENERIC) {
+ WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
+ bit, INTEL_PMC_MAX_GENERIC);
+ *cntr_mask &= GENMASK_ULL(INTEL_PMC_MAX_GENERIC - 1, 0);
+ }
+ *intel_ctrl = *cntr_mask;
+
+ bit = fls64(*fixed_cntr_mask);
+ if (bit > INTEL_PMC_MAX_FIXED) {
+ WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",
+ bit, INTEL_PMC_MAX_FIXED);
+ *fixed_cntr_mask &= GENMASK_ULL(INTEL_PMC_MAX_FIXED - 1, 0);
+ }
+
+ *intel_ctrl |= *fixed_cntr_mask << INTEL_PMC_IDX_FIXED;
+}
static void intel_pmu_check_event_constraints(struct event_constraint *event_constraints,
- int num_counters,
- int num_counters_fixed,
+ u64 cntr_mask,
+ u64 fixed_cntr_mask,
u64 intel_ctrl);
static void intel_pmu_check_extra_regs(struct extra_reg *extra_regs);
@@ -4698,8 +4717,8 @@ static void intel_pmu_check_extra_regs(struct extra_reg *extra_regs);
static inline bool intel_pmu_broken_perf_cap(void)
{
/* The Perf Metric (Bit 15) is always cleared */
- if ((boot_cpu_data.x86_model == INTEL_FAM6_METEORLAKE) ||
- (boot_cpu_data.x86_model == INTEL_FAM6_METEORLAKE_L))
+ if (boot_cpu_data.x86_vfm == INTEL_METEORLAKE ||
+ boot_cpu_data.x86_vfm == INTEL_METEORLAKE_L)
return true;
return false;
@@ -4713,11 +4732,10 @@ static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
if (sub_bitmaps & ARCH_PERFMON_NUM_COUNTER_LEAF_BIT) {
cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_NUM_COUNTER_LEAF,
&eax, &ebx, &ecx, &edx);
- pmu->num_counters = fls(eax);
- pmu->num_counters_fixed = fls(ebx);
+ pmu->cntr_mask64 = eax;
+ pmu->fixed_cntr_mask64 = ebx;
}
-
if (!intel_pmu_broken_perf_cap()) {
/* Perf Metric (Bit 15) and PEBS via PT (Bit 16) are hybrid enumeration */
rdmsrl(MSR_IA32_PERF_CAPABILITIES, pmu->intel_cap.capabilities);
@@ -4726,12 +4744,12 @@ static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
{
- intel_pmu_check_num_counters(&pmu->num_counters, &pmu->num_counters_fixed,
- &pmu->intel_ctrl, (1ULL << pmu->num_counters_fixed) - 1);
- pmu->max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_counters);
+ intel_pmu_check_counters_mask(&pmu->cntr_mask64, &pmu->fixed_cntr_mask64,
+ &pmu->intel_ctrl);
+ pmu->pebs_events_mask = intel_pmu_pebs_mask(pmu->cntr_mask64);
pmu->unconstrained = (struct event_constraint)
- __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1,
- 0, pmu->num_counters, 0, 0);
+ __EVENT_CONSTRAINT(0, pmu->cntr_mask64,
+ 0, x86_pmu_num_counters(&pmu->pmu), 0, 0);
if (pmu->intel_cap.perf_metrics)
pmu->intel_ctrl |= 1ULL << GLOBAL_CTRL_EN_PERF_METRICS;
@@ -4744,8 +4762,8 @@ static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
pmu->pmu.capabilities &= ~PERF_PMU_CAP_AUX_OUTPUT;
intel_pmu_check_event_constraints(pmu->event_constraints,
- pmu->num_counters,
- pmu->num_counters_fixed,
+ pmu->cntr_mask64,
+ pmu->fixed_cntr_mask64,
pmu->intel_ctrl);
intel_pmu_check_extra_regs(pmu->extra_regs);
@@ -4806,7 +4824,7 @@ static bool init_hybrid_pmu(int cpu)
intel_pmu_check_hybrid_pmus(pmu);
- if (!check_hw_exists(&pmu->pmu, pmu->num_counters, pmu->num_counters_fixed))
+ if (!check_hw_exists(&pmu->pmu, pmu->cntr_mask, pmu->fixed_cntr_mask))
return false;
pr_info("%s PMU driver: ", pmu->name);
@@ -4816,8 +4834,7 @@ static bool init_hybrid_pmu(int cpu)
pr_cont("\n");
- x86_pmu_show_pmu_cap(pmu->num_counters, pmu->num_counters_fixed,
- pmu->intel_ctrl);
+ x86_pmu_show_pmu_cap(&pmu->pmu);
end:
cpumask_set_cpu(cpu, &pmu->supported_cpus);
@@ -5645,18 +5662,11 @@ 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,
@@ -5962,29 +5972,9 @@ static const struct attribute_group *hybrid_attr_update[] = {
static struct attribute *empty_attrs;
-static void intel_pmu_check_num_counters(int *num_counters,
- int *num_counters_fixed,
- u64 *intel_ctrl, u64 fixed_mask)
-{
- if (*num_counters > INTEL_PMC_MAX_GENERIC) {
- WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
- *num_counters, INTEL_PMC_MAX_GENERIC);
- *num_counters = INTEL_PMC_MAX_GENERIC;
- }
- *intel_ctrl = (1ULL << *num_counters) - 1;
-
- if (*num_counters_fixed > INTEL_PMC_MAX_FIXED) {
- WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",
- *num_counters_fixed, INTEL_PMC_MAX_FIXED);
- *num_counters_fixed = INTEL_PMC_MAX_FIXED;
- }
-
- *intel_ctrl |= fixed_mask << INTEL_PMC_IDX_FIXED;
-}
-
static void intel_pmu_check_event_constraints(struct event_constraint *event_constraints,
- int num_counters,
- int num_counters_fixed,
+ u64 cntr_mask,
+ u64 fixed_cntr_mask,
u64 intel_ctrl)
{
struct event_constraint *c;
@@ -6021,10 +6011,9 @@ static void intel_pmu_check_event_constraints(struct event_constraint *event_con
* generic counters
*/
if (!use_fixed_pseudo_encoding(c->code))
- c->idxmsk64 |= (1ULL << num_counters) - 1;
+ c->idxmsk64 |= cntr_mask;
}
- c->idxmsk64 &=
- ~(~0ULL << (INTEL_PMC_IDX_FIXED + num_counters_fixed));
+ c->idxmsk64 &= cntr_mask | (fixed_cntr_mask << INTEL_PMC_IDX_FIXED);
c->weight = hweight64(c->idxmsk64);
}
}
@@ -6075,12 +6064,12 @@ static __always_inline int intel_pmu_init_hybrid(enum hybrid_pmu_type pmus)
pmu->pmu_type = intel_hybrid_pmu_type_map[bit].id;
pmu->name = intel_hybrid_pmu_type_map[bit].name;
- pmu->num_counters = x86_pmu.num_counters;
- pmu->num_counters_fixed = x86_pmu.num_counters_fixed;
- pmu->max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_counters);
+ pmu->cntr_mask64 = x86_pmu.cntr_mask64;
+ pmu->fixed_cntr_mask64 = x86_pmu.fixed_cntr_mask64;
+ pmu->pebs_events_mask = intel_pmu_pebs_mask(pmu->cntr_mask64);
pmu->unconstrained = (struct event_constraint)
- __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1,
- 0, pmu->num_counters, 0, 0);
+ __EVENT_CONSTRAINT(0, pmu->cntr_mask64,
+ 0, x86_pmu_num_counters(&pmu->pmu), 0, 0);
pmu->intel_cap.capabilities = x86_pmu.intel_cap.capabilities;
if (pmu->pmu_type & hybrid_small) {
@@ -6193,14 +6182,14 @@ __init int intel_pmu_init(void)
x86_pmu = intel_pmu;
x86_pmu.version = version;
- x86_pmu.num_counters = eax.split.num_counters;
+ x86_pmu.cntr_mask64 = GENMASK_ULL(eax.split.num_counters - 1, 0);
x86_pmu.cntval_bits = eax.split.bit_width;
x86_pmu.cntval_mask = (1ULL << eax.split.bit_width) - 1;
x86_pmu.events_maskl = ebx.full;
x86_pmu.events_mask_len = eax.split.mask_length;
- x86_pmu.max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, x86_pmu.num_counters);
+ x86_pmu.pebs_events_mask = intel_pmu_pebs_mask(x86_pmu.cntr_mask64);
x86_pmu.pebs_capable = PEBS_COUNTER_MASK;
/*
@@ -6210,12 +6199,10 @@ __init int intel_pmu_init(void)
if (version > 1 && version < 5) {
int assume = 3 * !boot_cpu_has(X86_FEATURE_HYPERVISOR);
- x86_pmu.num_counters_fixed =
- max((int)edx.split.num_counters_fixed, assume);
-
- fixed_mask = (1L << x86_pmu.num_counters_fixed) - 1;
+ x86_pmu.fixed_cntr_mask64 =
+ GENMASK_ULL(max((int)edx.split.num_counters_fixed, assume) - 1, 0);
} else if (version >= 5)
- x86_pmu.num_counters_fixed = fls(fixed_mask);
+ x86_pmu.fixed_cntr_mask64 = fixed_mask;
if (boot_cpu_has(X86_FEATURE_PDCM)) {
u64 capabilities;
@@ -6245,19 +6232,19 @@ __init int intel_pmu_init(void)
/*
* Install the hw-cache-events table:
*/
- switch (boot_cpu_data.x86_model) {
- case INTEL_FAM6_CORE_YONAH:
+ switch (boot_cpu_data.x86_vfm) {
+ case INTEL_CORE_YONAH:
pr_cont("Core events, ");
name = "core";
break;
- case INTEL_FAM6_CORE2_MEROM:
+ case INTEL_CORE2_MEROM:
x86_add_quirk(intel_clovertown_quirk);
fallthrough;
- case INTEL_FAM6_CORE2_MEROM_L:
- case INTEL_FAM6_CORE2_PENRYN:
- case INTEL_FAM6_CORE2_DUNNINGTON:
+ case INTEL_CORE2_MEROM_L:
+ case INTEL_CORE2_PENRYN:
+ case INTEL_CORE2_DUNNINGTON:
memcpy(hw_cache_event_ids, core2_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -6269,9 +6256,9 @@ __init int intel_pmu_init(void)
name = "core2";
break;
- case INTEL_FAM6_NEHALEM:
- case INTEL_FAM6_NEHALEM_EP:
- case INTEL_FAM6_NEHALEM_EX:
+ case INTEL_NEHALEM:
+ case INTEL_NEHALEM_EP:
+ case INTEL_NEHALEM_EX:
memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
@@ -6303,11 +6290,11 @@ __init int intel_pmu_init(void)
name = "nehalem";
break;
- case INTEL_FAM6_ATOM_BONNELL:
- case INTEL_FAM6_ATOM_BONNELL_MID:
- case INTEL_FAM6_ATOM_SALTWELL:
- case INTEL_FAM6_ATOM_SALTWELL_MID:
- case INTEL_FAM6_ATOM_SALTWELL_TABLET:
+ case INTEL_ATOM_BONNELL:
+ case INTEL_ATOM_BONNELL_MID:
+ case INTEL_ATOM_SALTWELL:
+ case INTEL_ATOM_SALTWELL_MID:
+ case INTEL_ATOM_SALTWELL_TABLET:
memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -6320,11 +6307,11 @@ __init int intel_pmu_init(void)
name = "bonnell";
break;
- case INTEL_FAM6_ATOM_SILVERMONT:
- case INTEL_FAM6_ATOM_SILVERMONT_D:
- case INTEL_FAM6_ATOM_SILVERMONT_MID:
- case INTEL_FAM6_ATOM_AIRMONT:
- case INTEL_FAM6_ATOM_AIRMONT_MID:
+ case INTEL_ATOM_SILVERMONT:
+ case INTEL_ATOM_SILVERMONT_D:
+ case INTEL_ATOM_SILVERMONT_MID:
+ case INTEL_ATOM_AIRMONT:
+ case INTEL_ATOM_AIRMONT_MID:
memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
@@ -6342,8 +6329,8 @@ __init int intel_pmu_init(void)
name = "silvermont";
break;
- case INTEL_FAM6_ATOM_GOLDMONT:
- case INTEL_FAM6_ATOM_GOLDMONT_D:
+ case INTEL_ATOM_GOLDMONT:
+ case INTEL_ATOM_GOLDMONT_D:
memcpy(hw_cache_event_ids, glm_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, glm_hw_cache_extra_regs,
@@ -6369,7 +6356,7 @@ __init int intel_pmu_init(void)
name = "goldmont";
break;
- case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+ case INTEL_ATOM_GOLDMONT_PLUS:
memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, glp_hw_cache_extra_regs,
@@ -6398,9 +6385,9 @@ __init int intel_pmu_init(void)
name = "goldmont_plus";
break;
- case INTEL_FAM6_ATOM_TREMONT_D:
- case INTEL_FAM6_ATOM_TREMONT:
- case INTEL_FAM6_ATOM_TREMONT_L:
+ case INTEL_ATOM_TREMONT_D:
+ case INTEL_ATOM_TREMONT:
+ case INTEL_ATOM_TREMONT_L:
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -6427,7 +6414,7 @@ __init int intel_pmu_init(void)
name = "Tremont";
break;
- case INTEL_FAM6_ATOM_GRACEMONT:
+ case INTEL_ATOM_GRACEMONT:
intel_pmu_init_grt(NULL);
intel_pmu_pebs_data_source_grt();
x86_pmu.pebs_latency_data = adl_latency_data_small;
@@ -6439,8 +6426,8 @@ __init int intel_pmu_init(void)
name = "gracemont";
break;
- case INTEL_FAM6_ATOM_CRESTMONT:
- case INTEL_FAM6_ATOM_CRESTMONT_X:
+ case INTEL_ATOM_CRESTMONT:
+ case INTEL_ATOM_CRESTMONT_X:
intel_pmu_init_grt(NULL);
x86_pmu.extra_regs = intel_cmt_extra_regs;
intel_pmu_pebs_data_source_cmt();
@@ -6453,9 +6440,9 @@ __init int intel_pmu_init(void)
name = "crestmont";
break;
- case INTEL_FAM6_WESTMERE:
- case INTEL_FAM6_WESTMERE_EP:
- case INTEL_FAM6_WESTMERE_EX:
+ case INTEL_WESTMERE:
+ case INTEL_WESTMERE_EP:
+ case INTEL_WESTMERE_EX:
memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
@@ -6484,8 +6471,8 @@ __init int intel_pmu_init(void)
name = "westmere";
break;
- case INTEL_FAM6_SANDYBRIDGE:
- case INTEL_FAM6_SANDYBRIDGE_X:
+ case INTEL_SANDYBRIDGE:
+ case INTEL_SANDYBRIDGE_X:
x86_add_quirk(intel_sandybridge_quirk);
x86_add_quirk(intel_ht_bug);
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
@@ -6498,7 +6485,7 @@ __init int intel_pmu_init(void)
x86_pmu.event_constraints = intel_snb_event_constraints;
x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
- if (boot_cpu_data.x86_model == INTEL_FAM6_SANDYBRIDGE_X)
+ if (boot_cpu_data.x86_vfm == INTEL_SANDYBRIDGE_X)
x86_pmu.extra_regs = intel_snbep_extra_regs;
else
x86_pmu.extra_regs = intel_snb_extra_regs;
@@ -6524,8 +6511,8 @@ __init int intel_pmu_init(void)
name = "sandybridge";
break;
- case INTEL_FAM6_IVYBRIDGE:
- case INTEL_FAM6_IVYBRIDGE_X:
+ case INTEL_IVYBRIDGE:
+ case INTEL_IVYBRIDGE_X:
x86_add_quirk(intel_ht_bug);
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -6541,7 +6528,7 @@ __init int intel_pmu_init(void)
x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints;
x86_pmu.pebs_aliases = intel_pebs_aliases_ivb;
x86_pmu.pebs_prec_dist = true;
- if (boot_cpu_data.x86_model == INTEL_FAM6_IVYBRIDGE_X)
+ if (boot_cpu_data.x86_vfm == INTEL_IVYBRIDGE_X)
x86_pmu.extra_regs = intel_snbep_extra_regs;
else
x86_pmu.extra_regs = intel_snb_extra_regs;
@@ -6563,10 +6550,10 @@ __init int intel_pmu_init(void)
break;
- case INTEL_FAM6_HASWELL:
- case INTEL_FAM6_HASWELL_X:
- case INTEL_FAM6_HASWELL_L:
- case INTEL_FAM6_HASWELL_G:
+ case INTEL_HASWELL:
+ case INTEL_HASWELL_X:
+ case INTEL_HASWELL_L:
+ case INTEL_HASWELL_G:
x86_add_quirk(intel_ht_bug);
x86_add_quirk(intel_pebs_isolation_quirk);
x86_pmu.late_ack = true;
@@ -6596,10 +6583,10 @@ __init int intel_pmu_init(void)
name = "haswell";
break;
- case INTEL_FAM6_BROADWELL:
- case INTEL_FAM6_BROADWELL_D:
- case INTEL_FAM6_BROADWELL_G:
- case INTEL_FAM6_BROADWELL_X:
+ case INTEL_BROADWELL:
+ case INTEL_BROADWELL_D:
+ case INTEL_BROADWELL_G:
+ case INTEL_BROADWELL_X:
x86_add_quirk(intel_pebs_isolation_quirk);
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
@@ -6638,8 +6625,8 @@ __init int intel_pmu_init(void)
name = "broadwell";
break;
- case INTEL_FAM6_XEON_PHI_KNL:
- case INTEL_FAM6_XEON_PHI_KNM:
+ case INTEL_XEON_PHI_KNL:
+ case INTEL_XEON_PHI_KNM:
memcpy(hw_cache_event_ids,
slm_hw_cache_event_ids, sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs,
@@ -6658,15 +6645,15 @@ __init int intel_pmu_init(void)
name = "knights-landing";
break;
- case INTEL_FAM6_SKYLAKE_X:
+ case INTEL_SKYLAKE_X:
pmem = true;
fallthrough;
- case INTEL_FAM6_SKYLAKE_L:
- case INTEL_FAM6_SKYLAKE:
- case INTEL_FAM6_KABYLAKE_L:
- case INTEL_FAM6_KABYLAKE:
- case INTEL_FAM6_COMETLAKE_L:
- case INTEL_FAM6_COMETLAKE:
+ case INTEL_SKYLAKE_L:
+ case INTEL_SKYLAKE:
+ case INTEL_KABYLAKE_L:
+ case INTEL_KABYLAKE:
+ case INTEL_COMETLAKE_L:
+ case INTEL_COMETLAKE:
x86_add_quirk(intel_pebs_isolation_quirk);
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
@@ -6715,16 +6702,16 @@ __init int intel_pmu_init(void)
name = "skylake";
break;
- case INTEL_FAM6_ICELAKE_X:
- case INTEL_FAM6_ICELAKE_D:
+ case INTEL_ICELAKE_X:
+ case INTEL_ICELAKE_D:
x86_pmu.pebs_ept = 1;
pmem = true;
fallthrough;
- case INTEL_FAM6_ICELAKE_L:
- case INTEL_FAM6_ICELAKE:
- case INTEL_FAM6_TIGERLAKE_L:
- case INTEL_FAM6_TIGERLAKE:
- case INTEL_FAM6_ROCKETLAKE:
+ case INTEL_ICELAKE_L:
+ case INTEL_ICELAKE:
+ case INTEL_TIGERLAKE_L:
+ case INTEL_TIGERLAKE:
+ case INTEL_ROCKETLAKE:
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -6759,16 +6746,22 @@ __init int intel_pmu_init(void)
name = "icelake";
break;
- case INTEL_FAM6_SAPPHIRERAPIDS_X:
- case INTEL_FAM6_EMERALDRAPIDS_X:
+ case INTEL_SAPPHIRERAPIDS_X:
+ case INTEL_EMERALDRAPIDS_X:
x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
x86_pmu.extra_regs = intel_glc_extra_regs;
- fallthrough;
- case INTEL_FAM6_GRANITERAPIDS_X:
- case INTEL_FAM6_GRANITERAPIDS_D:
+ pr_cont("Sapphire Rapids events, ");
+ name = "sapphire_rapids";
+ goto glc_common;
+
+ case INTEL_GRANITERAPIDS_X:
+ case INTEL_GRANITERAPIDS_D:
+ x86_pmu.extra_regs = intel_rwc_extra_regs;
+ pr_cont("Granite Rapids events, ");
+ name = "granite_rapids";
+
+ glc_common:
intel_pmu_init_glc(NULL);
- if (!x86_pmu.extra_regs)
- x86_pmu.extra_regs = intel_rwc_extra_regs;
x86_pmu.pebs_ept = 1;
x86_pmu.hw_config = hsw_hw_config;
x86_pmu.get_event_constraints = glc_get_event_constraints;
@@ -6779,15 +6772,13 @@ __init int intel_pmu_init(void)
td_attr = glc_td_events_attrs;
tsx_attr = glc_tsx_events_attrs;
intel_pmu_pebs_data_source_skl(true);
- pr_cont("Sapphire Rapids events, ");
- name = "sapphire_rapids";
break;
- case INTEL_FAM6_ALDERLAKE:
- case INTEL_FAM6_ALDERLAKE_L:
- case INTEL_FAM6_RAPTORLAKE:
- case INTEL_FAM6_RAPTORLAKE_P:
- case INTEL_FAM6_RAPTORLAKE_S:
+ case INTEL_ALDERLAKE:
+ case INTEL_ALDERLAKE_L:
+ case INTEL_RAPTORLAKE:
+ case INTEL_RAPTORLAKE_P:
+ case INTEL_RAPTORLAKE_S:
/*
* Alder Lake has 2 types of CPU, core and atom.
*
@@ -6810,11 +6801,13 @@ __init int intel_pmu_init(void)
pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX];
intel_pmu_init_glc(&pmu->pmu);
if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) {
- pmu->num_counters = x86_pmu.num_counters + 2;
- pmu->num_counters_fixed = x86_pmu.num_counters_fixed + 1;
+ pmu->cntr_mask64 <<= 2;
+ pmu->cntr_mask64 |= 0x3;
+ pmu->fixed_cntr_mask64 <<= 1;
+ pmu->fixed_cntr_mask64 |= 0x1;
} else {
- pmu->num_counters = x86_pmu.num_counters;
- pmu->num_counters_fixed = x86_pmu.num_counters_fixed;
+ pmu->cntr_mask64 = x86_pmu.cntr_mask64;
+ pmu->fixed_cntr_mask64 = x86_pmu.fixed_cntr_mask64;
}
/*
@@ -6824,15 +6817,16 @@ __init int intel_pmu_init(void)
* mistakenly add extra counters for P-cores. Correct the number of
* counters here.
*/
- if ((pmu->num_counters > 8) || (pmu->num_counters_fixed > 4)) {
- pmu->num_counters = x86_pmu.num_counters;
- pmu->num_counters_fixed = x86_pmu.num_counters_fixed;
+ if ((x86_pmu_num_counters(&pmu->pmu) > 8) || (x86_pmu_num_counters_fixed(&pmu->pmu) > 4)) {
+ pmu->cntr_mask64 = x86_pmu.cntr_mask64;
+ pmu->fixed_cntr_mask64 = x86_pmu.fixed_cntr_mask64;
}
- pmu->max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_counters);
+ pmu->pebs_events_mask = intel_pmu_pebs_mask(pmu->cntr_mask64);
pmu->unconstrained = (struct event_constraint)
- __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1,
- 0, pmu->num_counters, 0, 0);
+ __EVENT_CONSTRAINT(0, pmu->cntr_mask64,
+ 0, x86_pmu_num_counters(&pmu->pmu), 0, 0);
+
pmu->extra_regs = intel_glc_extra_regs;
/* Initialize Atom core specific PerfMon capabilities.*/
@@ -6845,8 +6839,8 @@ __init int intel_pmu_init(void)
name = "alderlake_hybrid";
break;
- case INTEL_FAM6_METEORLAKE:
- case INTEL_FAM6_METEORLAKE_L:
+ case INTEL_METEORLAKE:
+ case INTEL_METEORLAKE_L:
intel_pmu_init_hybrid(hybrid_big_small);
x86_pmu.pebs_latency_data = mtl_latency_data_small;
@@ -6899,9 +6893,9 @@ __init int intel_pmu_init(void)
* The constraints may be cut according to the CPUID enumeration
* by inserting the EVENT_CONSTRAINT_END.
*/
- if (x86_pmu.num_counters_fixed > INTEL_PMC_MAX_FIXED)
- x86_pmu.num_counters_fixed = INTEL_PMC_MAX_FIXED;
- intel_v5_gen_event_constraints[x86_pmu.num_counters_fixed].weight = -1;
+ if (fls64(x86_pmu.fixed_cntr_mask64) > INTEL_PMC_MAX_FIXED)
+ x86_pmu.fixed_cntr_mask64 &= GENMASK_ULL(INTEL_PMC_MAX_FIXED - 1, 0);
+ intel_v5_gen_event_constraints[fls64(x86_pmu.fixed_cntr_mask64)].weight = -1;
x86_pmu.event_constraints = intel_v5_gen_event_constraints;
pr_cont("generic architected perfmon, ");
name = "generic_arch_v5+";
@@ -6928,18 +6922,17 @@ __init int intel_pmu_init(void)
x86_pmu.attr_update = hybrid_attr_update;
}
- intel_pmu_check_num_counters(&x86_pmu.num_counters,
- &x86_pmu.num_counters_fixed,
- &x86_pmu.intel_ctrl,
- (u64)fixed_mask);
+ intel_pmu_check_counters_mask(&x86_pmu.cntr_mask64,
+ &x86_pmu.fixed_cntr_mask64,
+ &x86_pmu.intel_ctrl);
/* AnyThread may be deprecated on arch perfmon v5 or later */
if (x86_pmu.intel_cap.anythread_deprecated)
x86_pmu.format_attrs = intel_arch_formats_attr;
intel_pmu_check_event_constraints(x86_pmu.event_constraints,
- x86_pmu.num_counters,
- x86_pmu.num_counters_fixed,
+ x86_pmu.cntr_mask64,
+ x86_pmu.fixed_cntr_mask64,
x86_pmu.intel_ctrl);
/*
* Access LBR MSR may cause #GP under certain circumstances.
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 326c8cd5aa..9f116dfc47 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -41,7 +41,7 @@
* MSR_CORE_C1_RES: CORE C1 Residency Counter
* perf code: 0x00
* Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL
- * MTL,SRF,GRR
+ * MTL,SRF,GRR,ARL,LNL
* Scope: Core (each processor core has a MSR)
* MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
* perf code: 0x01
@@ -53,50 +53,50 @@
* Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
* SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
* TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF,
- * GRR
+ * GRR,ARL,LNL
* Scope: Core
* MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
* perf code: 0x03
* Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML,
- * ICL,TGL,RKL,ADL,RPL,MTL
+ * ICL,TGL,RKL,ADL,RPL,MTL,ARL,LNL
* Scope: Core
* MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter.
* perf code: 0x00
* Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
* KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL,
- * RPL,SPR,MTL
+ * RPL,SPR,MTL,ARL,LNL,SRF
* Scope: Package (physical package)
* MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter.
* perf code: 0x01
* Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL,
* GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL,
- * ADL,RPL,MTL
+ * ADL,RPL,MTL,ARL,LNL
* Scope: Package (physical package)
* MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter.
* perf code: 0x02
* Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
* SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
- * TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF
+ * TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF,
+ * ARL,LNL
* Scope: Package (physical package)
* 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
* Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL,
- * ADL,RPL,MTL
+ * ADL,RPL,MTL,ARL
* 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
* Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL,
- * TNT,RKL,ADL,RPL,MTL
+ * TNT,RKL,ADL,RPL,MTL,ARL,LNL
* Scope: Package (physical package)
* MSR_MODULE_C6_RES_MS: Module C6 Residency Counter.
* perf code: 0x00
@@ -114,6 +114,7 @@
#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 +144,6 @@ 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 +637,18 @@ 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),
+};
+
+static const struct cstate_model lnl_cstates __initconst = {
+ .core_events = BIT(PERF_CSTATE_CORE_C1_RES) |
+ BIT(PERF_CSTATE_CORE_C6_RES) |
+ BIT(PERF_CSTATE_CORE_C7_RES),
+
+ .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) |
+ BIT(PERF_CSTATE_PKG_C3_RES) |
+ BIT(PERF_CSTATE_PKG_C6_RES) |
BIT(PERF_CSTATE_PKG_C10_RES),
};
@@ -689,85 +693,90 @@ static const struct cstate_model srf_cstates __initconst = {
.core_events = BIT(PERF_CSTATE_CORE_C1_RES) |
BIT(PERF_CSTATE_CORE_C6_RES),
- .pkg_events = BIT(PERF_CSTATE_PKG_C6_RES),
+ .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) |
+ BIT(PERF_CSTATE_PKG_C6_RES),
.module_events = BIT(PERF_CSTATE_MODULE_C6_RES),
};
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),
+ X86_MATCH_VFM(INTEL_ARROWLAKE, &adl_cstates),
+ X86_MATCH_VFM(INTEL_ARROWLAKE_H, &adl_cstates),
+ X86_MATCH_VFM(INTEL_ARROWLAKE_U, &adl_cstates),
+ X86_MATCH_VFM(INTEL_LUNARLAKE_M, &lnl_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..9212053f6f 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1137,8 +1137,7 @@ void intel_pmu_pebs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sche
static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
{
struct debug_store *ds = cpuc->ds;
- int max_pebs_events = hybrid(cpuc->pmu, max_pebs_events);
- int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
+ int max_pebs_events = intel_pmu_max_num_pebs(cpuc->pmu);
u64 threshold;
int reserved;
@@ -1146,7 +1145,7 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
return;
if (x86_pmu.flags & PMU_FL_PEBS_ALL)
- reserved = max_pebs_events + num_counters_fixed;
+ reserved = max_pebs_events + x86_pmu_max_num_counters_fixed(cpuc->pmu);
else
reserved = max_pebs_events;
@@ -1831,8 +1830,12 @@ 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
@@ -2157,6 +2160,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
void *base, *at, *top;
short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
short error[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+ int max_pebs_events = intel_pmu_max_num_pebs(NULL);
int bit, i, size;
u64 mask;
@@ -2168,11 +2172,11 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
ds->pebs_index = ds->pebs_buffer_base;
- mask = (1ULL << x86_pmu.max_pebs_events) - 1;
- size = x86_pmu.max_pebs_events;
+ mask = x86_pmu.pebs_events_mask;
+ size = max_pebs_events;
if (x86_pmu.flags & PMU_FL_PEBS_ALL) {
- mask |= ((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED;
- size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed;
+ mask |= x86_pmu.fixed_cntr_mask64 << INTEL_PMC_IDX_FIXED;
+ size = INTEL_PMC_IDX_FIXED + x86_pmu_max_num_counters_fixed(NULL);
}
if (unlikely(base >= top)) {
@@ -2208,8 +2212,9 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
pebs_status = p->status = cpuc->pebs_enabled;
bit = find_first_bit((unsigned long *)&pebs_status,
- x86_pmu.max_pebs_events);
- if (bit >= x86_pmu.max_pebs_events)
+ max_pebs_events);
+
+ if (!(x86_pmu.pebs_events_mask & (1 << bit)))
continue;
/*
@@ -2267,12 +2272,10 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
{
short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
- int max_pebs_events = hybrid(cpuc->pmu, max_pebs_events);
- int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
struct debug_store *ds = cpuc->ds;
struct perf_event *event;
void *base, *at, *top;
- int bit, size;
+ int bit;
u64 mask;
if (!x86_pmu.pebs_active)
@@ -2283,12 +2286,11 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
ds->pebs_index = ds->pebs_buffer_base;
- mask = ((1ULL << max_pebs_events) - 1) |
- (((1ULL << num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED);
- size = INTEL_PMC_IDX_FIXED + num_counters_fixed;
+ mask = hybrid(cpuc->pmu, pebs_events_mask) |
+ (hybrid(cpuc->pmu, fixed_cntr_mask64) << INTEL_PMC_IDX_FIXED);
if (unlikely(base >= top)) {
- intel_pmu_pebs_event_update_no_drain(cpuc, size);
+ intel_pmu_pebs_event_update_no_drain(cpuc, X86_PMC_IDX_MAX);
return;
}
@@ -2298,11 +2300,11 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
pebs_status = get_pebs_status(at) & cpuc->pebs_enabled;
pebs_status &= mask;
- for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
+ for_each_set_bit(bit, (unsigned long *)&pebs_status, X86_PMC_IDX_MAX)
counts[bit]++;
}
- for_each_set_bit(bit, (unsigned long *)&mask, size) {
+ for_each_set_bit(bit, (unsigned long *)&mask, X86_PMC_IDX_MAX) {
if (counts[bit] == 0)
continue;
diff --git a/arch/x86/events/intel/knc.c b/arch/x86/events/intel/knc.c
index 618001c208..034a1f6a45 100644
--- a/arch/x86/events/intel/knc.c
+++ b/arch/x86/events/intel/knc.c
@@ -303,7 +303,7 @@ static const struct x86_pmu knc_pmu __initconst = {
.apic = 1,
.max_period = (1ULL << 39) - 1,
.version = 0,
- .num_counters = 2,
+ .cntr_mask64 = 0x3,
.cntval_bits = 40,
.cntval_mask = (1ULL << 40) - 1,
.get_event_constraints = x86_get_event_constraints,
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/p4.c b/arch/x86/events/intel/p4.c
index 35936188db..844bc4fc47 100644
--- a/arch/x86/events/intel/p4.c
+++ b/arch/x86/events/intel/p4.c
@@ -919,7 +919,7 @@ static void p4_pmu_disable_all(void)
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int idx;
- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
struct perf_event *event = cpuc->events[idx];
if (!test_bit(idx, cpuc->active_mask))
continue;
@@ -998,7 +998,7 @@ static void p4_pmu_enable_all(int added)
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int idx;
- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
struct perf_event *event = cpuc->events[idx];
if (!test_bit(idx, cpuc->active_mask))
continue;
@@ -1040,7 +1040,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
cpuc = this_cpu_ptr(&cpu_hw_events);
- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
int overflow;
if (!test_bit(idx, cpuc->active_mask)) {
@@ -1353,7 +1353,7 @@ static __initconst const struct x86_pmu p4_pmu = {
* though leave it restricted at moment assuming
* HT is on
*/
- .num_counters = ARCH_P4_MAX_CCCR,
+ .cntr_mask64 = GENMASK_ULL(ARCH_P4_MAX_CCCR - 1, 0),
.apic = 1,
.cntval_bits = ARCH_P4_CNTRVAL_BITS,
.cntval_mask = ARCH_P4_CNTRVAL_MASK,
@@ -1395,7 +1395,7 @@ __init int p4_pmu_init(void)
*
* Solve this by zero'ing out the registers to mimic a reset.
*/
- for (i = 0; i < x86_pmu.num_counters; i++) {
+ for_each_set_bit(i, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
reg = x86_pmu_config_addr(i);
wrmsrl_safe(reg, 0ULL);
}
diff --git a/arch/x86/events/intel/p6.c b/arch/x86/events/intel/p6.c
index 408879b0c0..a6cffb4f4e 100644
--- a/arch/x86/events/intel/p6.c
+++ b/arch/x86/events/intel/p6.c
@@ -214,7 +214,7 @@ static __initconst const struct x86_pmu p6_pmu = {
.apic = 1,
.max_period = (1ULL << 31) - 1,
.version = 0,
- .num_counters = 2,
+ .cntr_mask64 = 0x3,
/*
* Events have 40 bits implemented. However they are designed such
* that bits [32-39] are sign extensions of bit 31. As such the
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..745c174fc8 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -684,9 +684,15 @@ struct x86_hybrid_pmu {
cpumask_t supported_cpus;
union perf_capabilities intel_cap;
u64 intel_ctrl;
- int max_pebs_events;
- int num_counters;
- int num_counters_fixed;
+ u64 pebs_events_mask;
+ union {
+ u64 cntr_mask64;
+ unsigned long cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+ };
+ union {
+ u64 fixed_cntr_mask64;
+ unsigned long fixed_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+ };
struct event_constraint unconstrained;
u64 hw_cache_event_ids
@@ -774,8 +780,14 @@ struct x86_pmu {
int (*rdpmc_index)(int index);
u64 (*event_map)(int);
int max_events;
- int num_counters;
- int num_counters_fixed;
+ union {
+ u64 cntr_mask64;
+ unsigned long cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+ };
+ union {
+ u64 fixed_cntr_mask64;
+ unsigned long fixed_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+ };
int cntval_bits;
u64 cntval_mask;
union {
@@ -852,7 +864,7 @@ struct x86_pmu {
pebs_ept :1;
int pebs_record_size;
int pebs_buffer_size;
- int max_pebs_events;
+ u64 pebs_events_mask;
void (*drain_pebs)(struct pt_regs *regs, struct perf_sample_data *data);
struct event_constraint *pebs_constraints;
void (*pebs_aliases)(struct perf_event *event);
@@ -1125,8 +1137,8 @@ static inline int x86_pmu_rdpmc_index(int index)
return x86_pmu.rdpmc_index ? x86_pmu.rdpmc_index(index) : index;
}
-bool check_hw_exists(struct pmu *pmu, int num_counters,
- int num_counters_fixed);
+bool check_hw_exists(struct pmu *pmu, unsigned long *cntr_mask,
+ unsigned long *fixed_cntr_mask);
int x86_add_exclusive(unsigned int what);
@@ -1197,8 +1209,27 @@ void x86_pmu_enable_event(struct perf_event *event);
int x86_pmu_handle_irq(struct pt_regs *regs);
-void x86_pmu_show_pmu_cap(int num_counters, int num_counters_fixed,
- u64 intel_ctrl);
+void x86_pmu_show_pmu_cap(struct pmu *pmu);
+
+static inline int x86_pmu_num_counters(struct pmu *pmu)
+{
+ return hweight64(hybrid(pmu, cntr_mask64));
+}
+
+static inline int x86_pmu_max_num_counters(struct pmu *pmu)
+{
+ return fls64(hybrid(pmu, cntr_mask64));
+}
+
+static inline int x86_pmu_num_counters_fixed(struct pmu *pmu)
+{
+ return hweight64(hybrid(pmu, fixed_cntr_mask64));
+}
+
+static inline int x86_pmu_max_num_counters_fixed(struct pmu *pmu)
+{
+ return fls64(hybrid(pmu, fixed_cntr_mask64));
+}
extern struct event_constraint emptyconstraint;
@@ -1329,6 +1360,19 @@ 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 */
@@ -1648,6 +1692,17 @@ static inline int is_ht_workaround_enabled(void)
return !!(x86_pmu.flags & PMU_FL_EXCL_ENABLED);
}
+static inline u64 intel_pmu_pebs_mask(u64 cntr_mask)
+{
+ return MAX_PEBS_EVENTS_MASK & cntr_mask;
+}
+
+static inline int intel_pmu_max_num_pebs(struct pmu *pmu)
+{
+ static_assert(MAX_PEBS_EVENTS == 32);
+ return fls((u32)hybrid(pmu, pebs_events_mask));
+}
+
#else /* CONFIG_CPU_SUP_INTEL */
static inline void reserve_ds_buffers(void)
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);
diff --git a/arch/x86/events/zhaoxin/core.c b/arch/x86/events/zhaoxin/core.c
index 3e9acdaeed..2fd9b0cf9a 100644
--- a/arch/x86/events/zhaoxin/core.c
+++ b/arch/x86/events/zhaoxin/core.c
@@ -530,13 +530,13 @@ __init int zhaoxin_pmu_init(void)
pr_info("Version check pass!\n");
x86_pmu.version = version;
- x86_pmu.num_counters = eax.split.num_counters;
+ x86_pmu.cntr_mask64 = GENMASK_ULL(eax.split.num_counters - 1, 0);
x86_pmu.cntval_bits = eax.split.bit_width;
x86_pmu.cntval_mask = (1ULL << eax.split.bit_width) - 1;
x86_pmu.events_maskl = ebx.full;
x86_pmu.events_mask_len = eax.split.mask_length;
- x86_pmu.num_counters_fixed = edx.split.num_counters_fixed;
+ x86_pmu.fixed_cntr_mask64 = GENMASK_ULL(edx.split.num_counters_fixed - 1, 0);
x86_add_quirk(zhaoxin_arch_events_quirk);
switch (boot_cpu_data.x86) {
@@ -604,13 +604,13 @@ __init int zhaoxin_pmu_init(void)
return -ENODEV;
}
- x86_pmu.intel_ctrl = (1 << (x86_pmu.num_counters)) - 1;
- x86_pmu.intel_ctrl |= ((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED;
+ x86_pmu.intel_ctrl = x86_pmu.cntr_mask64;
+ x86_pmu.intel_ctrl |= x86_pmu.fixed_cntr_mask64 << INTEL_PMC_IDX_FIXED;
if (x86_pmu.event_constraints) {
for_each_event_constraint(c, x86_pmu.event_constraints) {
- c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
- c->weight += x86_pmu.num_counters;
+ c->idxmsk64 |= x86_pmu.cntr_mask64;
+ c->weight += x86_pmu_num_counters(NULL);
}
}
generated by cgit v1.2.3 (git 2.39.1) at 2024-10-10 10:56:21 +0000