projects/linux·commit aac4de46

Merge tag 'perf-core-2024-01-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

aac4de46 · Linus Torvalds <[email protected]> · 2024-01-08 19:37:20 -08:00

Pull performance events updates from Ingo Molnar:

 - Add branch stack counters ABI extension to better capture the growing
   amount of information the PMU exposes via branch stack sampling.
   There's matching tooling support.

 - Fix race when creating the nr_addr_filters sysfs file

 - Add Intel Sierra Forest and Grand Ridge intel/cstate PMU support

 - Add Intel Granite Rapids, Sierra Forest and Grand Ridge uncore PMU
   support

 - Misc cleanups & fixes

* tag 'perf-core-2024-01-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/intel/uncore: Factor out topology_gidnid_map()
  perf/x86/intel/uncore: Fix NULL pointer dereference issue in upi_fill_topology()
  perf/x86/amd: Reject branch stack for IBS events
  perf/x86/intel/uncore: Support Sierra Forest and Grand Ridge
  perf/x86/intel/uncore: Support IIO free-running counters on GNR
  perf/x86/intel/uncore: Support Granite Rapids
  perf/x86/uncore: Use u64 to replace unsigned for the uncore offsets array
  perf/x86/intel/uncore: Generic uncore_get_uncores and MMIO format of SPR
  perf: Fix the nr_addr_filters fix
  perf/x86/intel/cstate: Add Grand Ridge support
  perf/x86/intel/cstate: Add Sierra Forest support
  x86/smp: Export symbol cpu_clustergroup_mask()
  perf/x86/intel/cstate: Cleanup duplicate attr_groups
  perf/core: Fix narrow startup race when creating the perf nr_addr_filters sysfs file
  perf/x86/intel: Support branch counters logging
  perf/x86/intel: Reorganize attrs and is_visible
  perf: Add branch_sample_call_stack
  perf/x86: Add PERF_X86_EVENT_NEEDS_BRANCH_STACK flag
  perf: Add branch stack counters
Commit
aac4de465af08ccec90ef47bdcc13435e48a7223
Parents
0bdf0621 · fdd04102

Merge commit. Changes below are compared with the first parent: 0bdf0621.

Changes

23 files changed · +625 −128

Only the first 600 diff lines are shown. Download the complete patch.

Documentation/ABI/testing/sysfs-bus-event_source-devices-caps

View file
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-caps b/Documentation/ABI/testing/sysfs-bus-event_source-devices-caps
index 8757dcf..a5f506f 100644
--- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-caps
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-caps
@@ -16,3 +16,9 @@ Description:
Example output in powerpc:
grep . /sys/bus/event_source/devices/cpu/caps/*
/sys/bus/event_source/devices/cpu/caps/pmu_name:POWER9
+
+ The "branch_counter_nr" in the supported platform exposes the
+ maximum number of counters which can be shown in the u64 counters
+ of PERF_SAMPLE_BRANCH_COUNTERS, while the "branch_counter_width"
+ exposes the width of each counter. Both of them can be used by
+ the perf tool to parse the logged counters in each branch.

arch/powerpc/perf/core-book3s.c

View file
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 10b946e..b7ff680 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2312,7 +2312,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
struct cpu_hw_events *cpuhw;
cpuhw = this_cpu_ptr(&cpu_hw_events);
power_pmu_bhrb_read(event, cpuhw);
- perf_sample_save_brstack(&data, event, &cpuhw->bhrb_stack);
+ perf_sample_save_brstack(&data, event, &cpuhw->bhrb_stack, NULL);
}
if (event->attr.sample_type & PERF_SAMPLE_DATA_SRC &&

arch/x86/events/amd/core.c

View file
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 25ad6fd..81f6d82 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -940,7 +940,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
continue;
if (has_branch_stack(event))
- perf_sample_save_brstack(&data, event, &cpuc->lbr_stack);
+ perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
if (perf_event_overflow(event, &data, regs))
x86_pmu_stop(event, 0);

arch/x86/events/amd/ibs.c

View file
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 6911c53..e91970b 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -287,6 +287,9 @@ static int perf_ibs_init(struct perf_event *event)
if (config & ~perf_ibs->config_mask)
return -EINVAL;
+ if (has_branch_stack(event))
+ return -EOPNOTSUPP;
+
ret = validate_group(event);
if (ret)
return ret;

arch/x86/events/core.c

View file
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 40ad142..0905064 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -601,7 +601,7 @@ int x86_pmu_hw_config(struct perf_event *event)
}
}
- if (event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK)
+ if (branch_sample_call_stack(event))
event->attach_state |= PERF_ATTACH_TASK_DATA;
/*
@@ -1702,7 +1702,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
perf_sample_data_init(&data, 0, event->hw.last_period);
if (has_branch_stack(event))
- perf_sample_save_brstack(&data, event, &cpuc->lbr_stack);
+ perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
if (perf_event_overflow(event, &data, regs))
x86_pmu_stop(event, 0);

arch/x86/events/intel/core.c

View file
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index d50b3e0..3804f21 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2527,9 +2527,14 @@ static void intel_pmu_assign_event(struct perf_event *event, int idx)
perf_report_aux_output_id(event, idx);
}
+static __always_inline bool intel_pmu_needs_branch_stack(struct perf_event *event)
+{
+ return event->hw.flags & PERF_X86_EVENT_NEEDS_BRANCH_STACK;
+}
+
static void intel_pmu_del_event(struct perf_event *event)
{
- if (needs_branch_stack(event))
+ if (intel_pmu_needs_branch_stack(event))
intel_pmu_lbr_del(event);
if (event->attr.precise_ip)
intel_pmu_pebs_del(event);
@@ -2787,6 +2792,7 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
static void intel_pmu_enable_event(struct perf_event *event)
{
+ u64 enable_mask = ARCH_PERFMON_EVENTSEL_ENABLE;
struct hw_perf_event *hwc = &event->hw;
int idx = hwc->idx;
@@ -2795,8 +2801,10 @@ static void intel_pmu_enable_event(struct perf_event *event)
switch (idx) {
case 0 ... INTEL_PMC_IDX_FIXED - 1:
+ if (branch_sample_counters(event))
+ enable_mask |= ARCH_PERFMON_EVENTSEL_BR_CNTR;
intel_set_masks(event, idx);
- __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
+ __x86_pmu_enable_event(hwc, enable_mask);
break;
case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS - 1:
case INTEL_PMC_IDX_METRIC_BASE ... INTEL_PMC_IDX_METRIC_END:
@@ -2820,7 +2828,7 @@ static void intel_pmu_add_event(struct perf_event *event)
{
if (event->attr.precise_ip)
intel_pmu_pebs_add(event);
- if (needs_branch_stack(event))
+ if (intel_pmu_needs_branch_stack(event))
intel_pmu_lbr_add(event);
}
@@ -3047,7 +3055,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
perf_sample_data_init(&data, 0, event->hw.last_period);
if (has_branch_stack(event))
- perf_sample_save_brstack(&data, event, &cpuc->lbr_stack);
+ intel_pmu_lbr_save_brstack(&data, cpuc, event);
if (perf_event_overflow(event, &data, regs))
x86_pmu_stop(event, 0);
@@ -3612,6 +3620,13 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
if (cpuc->excl_cntrs)
return intel_get_excl_constraints(cpuc, event, idx, c2);
+ /* Not all counters support the branch counter feature. */
+ if (branch_sample_counters(event)) {
+ c2 = dyn_constraint(cpuc, c2, idx);
+ c2->idxmsk64 &= x86_pmu.lbr_counters;
+ c2->weight = hweight64(c2->idxmsk64);
+ }
+
return c2;
}
@@ -3897,7 +3912,62 @@ static int intel_pmu_hw_config(struct perf_event *event)
x86_pmu.pebs_aliases(event);
}
- if (needs_branch_stack(event)) {
+ if (needs_branch_stack(event) && is_sampling_event(event))
+ event->hw.flags |= PERF_X86_EVENT_NEEDS_BRANCH_STACK;
+
+ if (branch_sample_counters(event)) {
+ struct perf_event *leader, *sibling;
+ int num = 0;
+
+ if (!(x86_pmu.flags & PMU_FL_BR_CNTR) ||
+ (event->attr.config & ~INTEL_ARCH_EVENT_MASK))
+ return -EINVAL;
+
+ /*
+ * The branch counter logging is not supported in the call stack
+ * mode yet, since we cannot simply flush the LBR during e.g.,
+ * multiplexing. Also, there is no obvious usage with the call
+ * stack mode. Simply forbids it for now.
+ *
+ * If any events in the group enable the branch counter logging
+ * feature, the group is treated as a branch counter logging
+ * group, which requires the extra space to store the counters.
+ */
+ leader = event->group_leader;
+ if (branch_sample_call_stack(leader))
+ return -EINVAL;
+ if (branch_sample_counters(leader))
+ num++;
+ leader->hw.flags |= PERF_X86_EVENT_BRANCH_COUNTERS;
+
+ for_each_sibling_event(sibling, leader) {
+ if (branch_sample_call_stack(sibling))
+ return -EINVAL;
+ if (branch_sample_counters(sibling))
+ num++;
+ }
+
+ if (num > fls(x86_pmu.lbr_counters))
+ return -EINVAL;
+ /*
+ * Only applying the PERF_SAMPLE_BRANCH_COUNTERS doesn't
+ * require any branch stack setup.
+ * Clear the bit to avoid unnecessary branch stack setup.
+ */
+ if (0 == (event->attr.branch_sample_type &
+ ~(PERF_SAMPLE_BRANCH_PLM_ALL |
+ PERF_SAMPLE_BRANCH_COUNTERS)))
+ event->hw.flags &= ~PERF_X86_EVENT_NEEDS_BRANCH_STACK;
+
+ /*
+ * Force the leader to be a LBR event. So LBRs can be reset
+ * with the leader event. See intel_pmu_lbr_del() for details.
+ */
+ if (!intel_pmu_needs_branch_stack(leader))
+ return -EINVAL;
+ }
+
+ if (intel_pmu_needs_branch_stack(event)) {
ret = intel_pmu_setup_lbr_filter(event);
if (ret)
return ret;
@@ -4380,8 +4450,13 @@ cmt_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
*/
if (event->attr.precise_ip == 3) {
/* Force instruction:ppp on PMC0, 1 and Fixed counter 0 */
- if (constraint_match(&fixed0_constraint, event->hw.config))
- return &fixed0_counter0_1_constraint;
+ if (constraint_match(&fixed0_constraint, event->hw.config)) {
+ /* The fixed counter 0 doesn't support LBR event logging. */
+ if (branch_sample_counters(event))
+ return &counter0_1_constraint;
+ else
+ return &fixed0_counter0_1_constraint;
+ }
switch (c->idxmsk64 & 0x3ull) {
case 0x1:
@@ -4560,7 +4635,7 @@ int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
goto err;
}
- if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA)) {
+ if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA | PMU_FL_BR_CNTR)) {
size_t sz = X86_PMC_IDX_MAX * sizeof(struct event_constraint);
cpuc->constraint_list = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu));
@@ -5532,11 +5607,41 @@ static ssize_t branches_show(struct device *cdev,
static DEVICE_ATTR_RO(branches);
+static ssize_t branch_counter_nr_show(struct device *cdev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "%d\n", fls(x86_pmu.lbr_counters));
+}
+
+static DEVICE_ATTR_RO(branch_counter_nr);
+
+static ssize_t branch_counter_width_show(struct device *cdev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "%d\n", LBR_INFO_BR_CNTR_BITS);
+}
+
+static DEVICE_ATTR_RO(branch_counter_width);
+
static struct attribute *lbr_attrs[] = {
&dev_attr_branches.attr,
+ &dev_attr_branch_counter_nr.attr,
+ &dev_attr_branch_counter_width.attr,
NULL
};
+static umode_t
+lbr_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ /* branches */
+ if (i == 0)
+ return x86_pmu.lbr_nr ? attr->mode : 0;
+
+ return (x86_pmu.flags & PMU_FL_BR_CNTR) ? attr->mode : 0;
+}
+
static char pmu_name_str[30];
static ssize_t pmu_name_show(struct device *cdev,
@@ -5564,6 +5669,15 @@ static struct attribute *intel_pmu_attrs[] = {
};
static umode_t
+default_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ if (attr == &dev_attr_allow_tsx_force_abort.attr)
+ return x86_pmu.flags & PMU_FL_TFA ? attr->mode : 0;
+
+ return attr->mode;
+}
+
+static umode_t
tsx_is_visible(struct kobject *kobj, struct attribute *attr, int i)
{
return boot_cpu_has(X86_FEATURE_RTM) ? attr->mode : 0;
@@ -5585,26 +5699,11 @@ mem_is_visible(struct kobject *kobj, struct attribute *attr, int i)
}
static umode_t
-lbr_is_visible(struct kobject *kobj, struct attribute *attr, int i)
-{
- return x86_pmu.lbr_nr ? attr->mode : 0;
-}
-
-static umode_t
exra_is_visible(struct kobject *kobj, struct attribute *attr, int i)
{
return x86_pmu.version >= 2 ? attr->mode : 0;
}
-static umode_t
-default_is_visible(struct kobject *kobj, struct attribute *attr, int i)
-{
- if (attr == &dev_attr_allow_tsx_force_abort.attr)
- return x86_pmu.flags & PMU_FL_TFA ? attr->mode : 0;
-
- return attr->mode;
-}
-
static struct attribute_group group_events_td = {
.name = "events",
};

arch/x86/events/intel/cstate.c

View file
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index cbeb6d2..4b50a3a 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
+ * MTL,SRF,GRR
* Scope: Core (each processor core has a MSR)
* MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
* perf code: 0x01
@@ -52,7 +52,8 @@
* 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
+ * TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF,
+ * GRR
* Scope: Core
* MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
* perf code: 0x03
@@ -75,7 +76,7 @@
* 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
+ * TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF
* Scope: Package (physical package)
* MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter.
* perf code: 0x03
@@ -97,6 +98,10 @@
* Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL,
* TNT,RKL,ADL,RPL,MTL
* Scope: Package (physical package)
+ * MSR_MODULE_C6_RES_MS: Module C6 Residency Counter.
+ * perf code: 0x00
+ * Available model: SRF,GRR
+ * Scope: A cluster of cores shared L2 cache
*
*/
@@ -130,6 +135,7 @@ static ssize_t cstate_get_attr_cpumask(struct device *dev,
struct cstate_model {
unsigned long core_events;
unsigned long pkg_events;
+ unsigned long module_events;
unsigned long quirks;
};
@@ -189,20 +195,20 @@ static struct attribute *attrs_empty[] = {
* "events" group (with empty attrs) before updating
* it with detected events.
*/
-static struct attribute_group core_events_attr_group = {
+static struct attribute_group cstate_events_attr_group = {
.name = "events",
.attrs = attrs_empty,
};
-DEFINE_CSTATE_FORMAT_ATTR(core_event, event, "config:0-63");
-static struct attribute *core_format_attrs[] = {
- &format_attr_core_event.attr,
+DEFINE_CSTATE_FORMAT_ATTR(cstate_event, event, "config:0-63");
+static struct attribute *cstate_format_attrs[] = {
+ &format_attr_cstate_event.attr,
NULL,
};
-static struct attribute_group core_format_attr_group = {
+static struct attribute_group cstate_format_attr_group = {
.name = "format",
- .attrs = core_format_attrs,
+ .attrs = cstate_format_attrs,
};
static cpumask_t cstate_core_cpu_mask;
@@ -217,9 +223,9 @@ static struct attribute_group cpumask_attr_group = {
.attrs = cstate_cpumask_attrs,
};
-static const struct attribute_group *core_attr_groups[] = {
- &core_events_attr_group,
- &core_format_attr_group,
+static const struct attribute_group *cstate_attr_groups[] = {
+ &cstate_events_attr_group,
+ &cstate_format_attr_group,
&cpumask_attr_group,
NULL,
};
@@ -268,30 +274,30 @@ static struct perf_msr pkg_msr[] = {
[PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY, &group_cstate_pkg_c10, test_msr },
};
-static struct attribute_group pkg_events_attr_group = {
- .name = "events",
- .attrs = attrs_empty,
-};
+static cpumask_t cstate_pkg_cpu_mask;
-DEFINE_CSTATE_FORMAT_ATTR(pkg_event, event, "config:0-63");
-static struct attribute *pkg_format_attrs[] = {
- &format_attr_pkg_event.attr,
- NULL,
-};
-static struct attribute_group pkg_format_attr_group = {
- .name = "format",
- .attrs = pkg_format_attrs,
+/* cstate_module PMU */
+static struct pmu cstate_module_pmu;
+static bool has_cstate_module;
+
+enum perf_cstate_module_events {
+ PERF_CSTATE_MODULE_C6_RES = 0,
+
+ PERF_CSTATE_MODULE_EVENT_MAX,
};
-static cpumask_t cstate_pkg_cpu_mask;
+PMU_EVENT_ATTR_STRING(c6-residency, attr_cstate_module_c6, "event=0x00");
-static const struct attribute_group *pkg_attr_groups[] = {
- &pkg_events_attr_group,
- &pkg_format_attr_group,
- &cpumask_attr_group,
- NULL,
+static unsigned long module_msr_mask;
+
+PMU_EVENT_GROUP(events, cstate_module_c6);
+
+static struct perf_msr module_msr[] = {
+ [PERF_CSTATE_MODULE_C6_RES] = { MSR_MODULE_C6_RES_MS, &group_cstate_module_c6, test_msr },
};
+static cpumask_t cstate_module_cpu_mask;
+
static ssize_t cstate_get_attr_cpumask(struct device *dev,
struct device_attribute *attr,
char *buf)
@@ -302,6 +308,8 @@ static ssize_t cstate_get_attr_cpumask(struct device *dev,
return cpumap_print_to_pagebuf(true, buf, &cstate_core_cpu_mask);
else if (pmu == &cstate_pkg_pmu)
return cpumap_print_to_pagebuf(true, buf, &cstate_pkg_cpu_mask);
+ else if (pmu == &cstate_module_pmu)
+ return cpumap_print_to_pagebuf(true, buf, &cstate_module_cpu_mask);
else
return 0;
}
@@ -342,6 +350,15 @@ static int cstate_pmu_event_init(struct perf_event *event)
event->hw.event_base = pkg_msr[cfg].msr;
cpu = cpumask_any_and(&cstate_pkg_cpu_mask,
topology_die_cpumask(event->cpu));
+ } else if (event->pmu == &cstate_module_pmu) {
+ if (cfg >= PERF_CSTATE_MODULE_EVENT_MAX)
+ return -EINVAL;
+ cfg = array_index_nospec((unsigned long)cfg, PERF_CSTATE_MODULE_EVENT_MAX);
+ if (!(module_msr_mask & (1 << cfg)))
+ return -EINVAL;
+ event->hw.event_base = module_msr[cfg].msr;
+ cpu = cpumask_any_and(&cstate_module_cpu_mask,
+ topology_cluster_cpumask(event->cpu));
} else {
return -ENOENT;
}
@@ -429,6 +446,17 @@ static int cstate_cpu_exit(unsigned int cpu)
perf_pmu_migrate_context(&cstate_pkg_pmu, cpu, target);
}
}
+
+ if (has_cstate_module &&
+ cpumask_test_and_clear_cpu(cpu, &cstate_module_cpu_mask)) {
+
+ target = cpumask_any_but(topology_cluster_cpumask(cpu), cpu);
+ /* Migrate events if there is a valid target */
+ if (target < nr_cpu_ids) {
+ cpumask_set_cpu(target, &cstate_module_cpu_mask);
+ perf_pmu_migrate_context(&cstate_module_pmu, cpu, target);
+ }
+ }
return 0;
}
@@ -455,6 +483,15 @@ static int cstate_cpu_init(unsigned int cpu)
if (has_cstate_pkg && target >= nr_cpu_ids)
cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask);
+ /*
+ * If this is the first online thread of that cluster, set it
+ * in the cluster cpu mask as the designated reader.
+ */
+ target = cpumask_any_and(&cstate_module_cpu_mask,
+ topology_cluster_cpumask(cpu));
+ if (has_cstate_module && target >= nr_cpu_ids)
+ cpumask_set_cpu(cpu, &cstate_module_cpu_mask);
+
return 0;
}
@@ -477,8 +514,13 @@ static const struct attribute_group *pkg_attr_update[] = {
NULL,
};
+static const struct attribute_group *module_attr_update[] = {
+ &group_cstate_module_c6,
+ NULL
+};
+
static struct pmu cstate_core_pmu = {
- .attr_groups = core_attr_groups,
+ .attr_groups = cstate_attr_groups,
.attr_update = core_attr_update,
.name = "cstate_core",
.task_ctx_nr = perf_invalid_context,
@@ -493,7 +535,7 @@ static struct pmu cstate_core_pmu = {
};
static struct pmu cstate_pkg_pmu = {
- .attr_groups = pkg_attr_groups,
+ .attr_groups = cstate_attr_groups,
.attr_update = pkg_attr_update,
.name = "cstate_pkg",
.task_ctx_nr = perf_invalid_context,
@@ -507,6 +549,21 @@ static struct pmu cstate_pkg_pmu = {
.module = THIS_MODULE,
};
+static struct pmu cstate_module_pmu = {
+ .attr_groups = cstate_attr_groups,
+ .attr_update = module_attr_update,
+ .name = "cstate_module",
+ .task_ctx_nr = perf_invalid_context,
+ .event_init = cstate_pmu_event_init,
+ .add = cstate_pmu_event_add,
+ .del = cstate_pmu_event_del,
+ .start = cstate_pmu_event_start,
+ .stop = cstate_pmu_event_stop,
+ .read = cstate_pmu_event_update,
+ .capabilities = PERF_PMU_CAP_NO_INTERRUPT | PERF_PMU_CAP_NO_EXCLUDE,
+ .module = THIS_MODULE,
+};
+
static const struct cstate_model nhm_cstates __initconst = {
.core_events = BIT(PERF_CSTATE_CORE_C3_RES) |
BIT(PERF_CSTATE_CORE_C6_RES),
@@ -621,6 +678,22 @@ static const struct cstate_model glm_cstates __initconst = {
BIT(PERF_CSTATE_PKG_C10_RES),
};
+static const struct cstate_model grr_cstates __initconst = {
+ .core_events = BIT(PERF_CSTATE_CORE_C1_RES) |
+ BIT(PERF_CSTATE_CORE_C6_RES),
+
+ .module_events = BIT(PERF_CSTATE_MODULE_C6_RES),
+};
+
+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),
+
+ .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),
@@ -673,6 +746,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
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),
@@ -714,10 +789,14 @@ static int __init cstate_probe(const struct cstate_model *cm)

This diff is incomplete. Download the complete patch.

arch/x86/events/intel/ds.c

View file

This diff is incomplete. Download the complete patch.

arch/x86/events/intel/lbr.c

View file

This diff is incomplete. Download the complete patch.

arch/x86/events/intel/uncore.c

View file

This diff is incomplete. Download the complete patch.

arch/x86/events/intel/uncore.h

View file

This diff is incomplete. Download the complete patch.

arch/x86/events/intel/uncore_discovery.c

View file

This diff is incomplete. Download the complete patch.

arch/x86/events/intel/uncore_discovery.h

View file

This diff is incomplete. Download the complete patch.

arch/x86/events/intel/uncore_nhmex.c

View file

This diff is incomplete. Download the complete patch.

arch/x86/events/intel/uncore_snbep.c

View file

This diff is incomplete. Download the complete patch.

arch/x86/events/perf_event.h

View file

This diff is incomplete. Download the complete patch.

arch/x86/events/perf_event_flags.h

View file

This diff is incomplete. Download the complete patch.

arch/x86/include/asm/msr-index.h

View file

This diff is incomplete. Download the complete patch.

arch/x86/include/asm/perf_event.h

View file

This diff is incomplete. Download the complete patch.

arch/x86/kernel/smpboot.c

View file

This diff is incomplete. Download the complete patch.

include/linux/perf_event.h

View file

This diff is incomplete. Download the complete patch.

include/uapi/linux/perf_event.h

View file

This diff is incomplete. Download the complete patch.

kernel/events/core.c

View file

This diff is incomplete. Download the complete patch.