summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/events/intel/core.c103
-rw-r--r--arch/x86/events/intel/ds.c2
-rw-r--r--arch/x86/events/intel/lbr.c85
-rw-r--r--arch/x86/events/perf_event.h12
-rw-r--r--arch/x86/events/perf_event_flags.h1
-rw-r--r--arch/x86/include/asm/msr-index.h5
-rw-r--r--arch/x86/include/asm/perf_event.h4
7 files changed, 204 insertions, 8 deletions
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 584b58df7bf6..e068a96aeb54 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2792,6 +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;
@@ -2800,8 +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:
@@ -3052,7 +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, NULL);
+ intel_pmu_lbr_save_brstack(&data, cpuc, event);
if (perf_event_overflow(event, &data, regs))
x86_pmu_stop(event, 0);
@@ -3617,6 +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;
}
@@ -3905,6 +3915,58 @@ static int intel_pmu_hw_config(struct perf_event *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)
@@ -4383,8 +4445,13 @@ 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:
@@ -4563,7 +4630,7 @@ 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));
@@ -5535,15 +5602,39 @@ 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)
{
- return x86_pmu.lbr_nr ? attr->mode : 0;
+ /* 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];
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index cb3f329f8fa4..d49d661ec0a7 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1912,7 +1912,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
if (has_branch_stack(event)) {
intel_pmu_store_pebs_lbrs(lbr);
- perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL);
+ intel_pmu_lbr_save_brstack(data, cpuc, event);
}
}
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index c3b0d15a9841..78cd5084104e 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -676,6 +676,25 @@ void intel_pmu_lbr_del(struct perf_event *event)
WARN_ON_ONCE(cpuc->lbr_users < 0);
WARN_ON_ONCE(cpuc->lbr_pebs_users < 0);
perf_sched_cb_dec(event->pmu);
+
+ /*
+ * The logged occurrences information is only valid for the
+ * current LBR group. If another LBR group is scheduled in
+ * later, the information from the stale LBRs will be wrongly
+ * interpreted. Reset the LBRs here.
+ *
+ * Only clear once for a branch counter group with the leader
+ * event. Because
+ * - Cannot simply reset the LBRs with the !cpuc->lbr_users.
+ * Because it's possible that the last LBR user is not in a
+ * branch counter group, e.g., a branch_counters group +
+ * several normal LBR events.
+ * - The LBR reset can be done with any one of the events in a
+ * branch counter group, since they are always scheduled together.
+ * It's easy to force the leader event an LBR event.
+ */
+ if (is_branch_counters_group(event) && event == event->group_leader)
+ intel_pmu_lbr_reset();
}
static inline bool vlbr_exclude_host(void)
@@ -866,6 +885,8 @@ static __always_inline u16 get_lbr_cycles(u64 info)
return cycles;
}
+static_assert((64 - PERF_BRANCH_ENTRY_INFO_BITS_MAX) > LBR_INFO_BR_CNTR_NUM * LBR_INFO_BR_CNTR_BITS);
+
static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc,
struct lbr_entry *entries)
{
@@ -898,11 +919,67 @@ static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc,
e->abort = !!(info & LBR_INFO_ABORT);
e->cycles = get_lbr_cycles(info);
e->type = get_lbr_br_type(info);
+
+ /*
+ * Leverage the reserved field of cpuc->lbr_entries[i] to
+ * temporarily store the branch counters information.
+ * The later code will decide what content can be disclosed
+ * to the perf tool. Pleae see intel_pmu_lbr_counters_reorder().
+ */
+ e->reserved = (info >> LBR_INFO_BR_CNTR_OFFSET) & LBR_INFO_BR_CNTR_FULL_MASK;
}
cpuc->lbr_stack.nr = i;
}
+/*
+ * The enabled order may be different from the counter order.
+ * Update the lbr_counters with the enabled order.
+ */
+static void intel_pmu_lbr_counters_reorder(struct cpu_hw_events *cpuc,
+ struct perf_event *event)
+{
+ int i, j, pos = 0, order[X86_PMC_IDX_MAX];
+ struct perf_event *leader, *sibling;
+ u64 src, dst, cnt;
+
+ leader = event->group_leader;
+ if (branch_sample_counters(leader))
+ order[pos++] = leader->hw.idx;
+
+ for_each_sibling_event(sibling, leader) {
+ if (!branch_sample_counters(sibling))
+ continue;
+ order[pos++] = sibling->hw.idx;
+ }
+
+ WARN_ON_ONCE(!pos);
+
+ for (i = 0; i < cpuc->lbr_stack.nr; i++) {
+ src = cpuc->lbr_entries[i].reserved;
+ dst = 0;
+ for (j = 0; j < pos; j++) {
+ cnt = (src >> (order[j] * LBR_INFO_BR_CNTR_BITS)) & LBR_INFO_BR_CNTR_MASK;
+ dst |= cnt << j * LBR_INFO_BR_CNTR_BITS;
+ }
+ cpuc->lbr_counters[i] = dst;
+ cpuc->lbr_entries[i].reserved = 0;
+ }
+}
+
+void intel_pmu_lbr_save_brstack(struct perf_sample_data *data,
+ struct cpu_hw_events *cpuc,
+ struct perf_event *event)
+{
+ if (is_branch_counters_group(event)) {
+ intel_pmu_lbr_counters_reorder(cpuc, event);
+ perf_sample_save_brstack(data, event, &cpuc->lbr_stack, cpuc->lbr_counters);
+ return;
+ }
+
+ perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL);
+}
+
static void intel_pmu_arch_lbr_read(struct cpu_hw_events *cpuc)
{
intel_pmu_store_lbr(cpuc, NULL);
@@ -1173,8 +1250,10 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
for (i = 0; i < cpuc->lbr_stack.nr; ) {
if (!cpuc->lbr_entries[i].from) {
j = i;
- while (++j < cpuc->lbr_stack.nr)
+ while (++j < cpuc->lbr_stack.nr) {
cpuc->lbr_entries[j-1] = cpuc->lbr_entries[j];
+ cpuc->lbr_counters[j-1] = cpuc->lbr_counters[j];
+ }
cpuc->lbr_stack.nr--;
if (!cpuc->lbr_entries[i].from)
continue;
@@ -1525,8 +1604,12 @@ void __init intel_pmu_arch_lbr_init(void)
x86_pmu.lbr_mispred = ecx.split.lbr_mispred;
x86_pmu.lbr_timed_lbr = ecx.split.lbr_timed_lbr;
x86_pmu.lbr_br_type = ecx.split.lbr_br_type;
+ x86_pmu.lbr_counters = ecx.split.lbr_counters;
x86_pmu.lbr_nr = lbr_nr;
+ if (!!x86_pmu.lbr_counters)
+ x86_pmu.flags |= PMU_FL_BR_CNTR;
+
if (x86_pmu.lbr_mispred)
static_branch_enable(&x86_lbr_mispred);
if (x86_pmu.lbr_timed_lbr)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 53dd5d495ba6..fb56518356ec 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -110,6 +110,11 @@ static inline bool is_topdown_event(struct perf_event *event)
return is_metric_event(event) || is_slots_event(event);
}
+static inline bool is_branch_counters_group(struct perf_event *event)
+{
+ return event->group_leader->hw.flags & PERF_X86_EVENT_BRANCH_COUNTERS;
+}
+
struct amd_nb {
int nb_id; /* NorthBridge id */
int refcnt; /* reference count */
@@ -283,6 +288,7 @@ struct cpu_hw_events {
int lbr_pebs_users;
struct perf_branch_stack lbr_stack;
struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES];
+ u64 lbr_counters[MAX_LBR_ENTRIES]; /* branch stack extra */
union {
struct er_account *lbr_sel;
struct er_account *lbr_ctl;
@@ -888,6 +894,7 @@ struct x86_pmu {
unsigned int lbr_mispred:1;
unsigned int lbr_timed_lbr:1;
unsigned int lbr_br_type:1;
+ unsigned int lbr_counters:4;
void (*lbr_reset)(void);
void (*lbr_read)(struct cpu_hw_events *cpuc);
@@ -1012,6 +1019,7 @@ do { \
#define PMU_FL_INSTR_LATENCY 0x80 /* Support Instruction Latency in PEBS Memory Info Record */
#define PMU_FL_MEM_LOADS_AUX 0x100 /* Require an auxiliary event for the complete memory info */
#define PMU_FL_RETIRE_LATENCY 0x200 /* Support Retire Latency in PEBS */
+#define PMU_FL_BR_CNTR 0x400 /* Support branch counter logging */
#define EVENT_VAR(_id) event_attr_##_id
#define EVENT_PTR(_id) &event_attr_##_id.attr.attr
@@ -1552,6 +1560,10 @@ void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr);
void intel_ds_init(void);
+void intel_pmu_lbr_save_brstack(struct perf_sample_data *data,
+ struct cpu_hw_events *cpuc,
+ struct perf_event *event);
+
void intel_pmu_lbr_swap_task_ctx(struct perf_event_pmu_context *prev_epc,
struct perf_event_pmu_context *next_epc);
diff --git a/arch/x86/events/perf_event_flags.h b/arch/x86/events/perf_event_flags.h
index a1685981c520..6c977c19f2cd 100644
--- a/arch/x86/events/perf_event_flags.h
+++ b/arch/x86/events/perf_event_flags.h
@@ -21,3 +21,4 @@ PERF_ARCH(PEBS_STLAT, 0x08000) /* st+stlat data address sampling */
PERF_ARCH(AMD_BRS, 0x10000) /* AMD Branch Sampling */
PERF_ARCH(PEBS_LAT_HYBRID, 0x20000) /* ld and st lat for hybrid */
PERF_ARCH(NEEDS_BRANCH_STACK, 0x40000) /* require branch stack setup */
+PERF_ARCH(BRANCH_COUNTERS, 0x80000) /* logs the counters in the extra space of each branch */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index f8b502867dd1..a5b0a19ccdf2 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -236,6 +236,11 @@
#define LBR_INFO_CYCLES 0xffff
#define LBR_INFO_BR_TYPE_OFFSET 56
#define LBR_INFO_BR_TYPE (0xfull << LBR_INFO_BR_TYPE_OFFSET)
+#define LBR_INFO_BR_CNTR_OFFSET 32
+#define LBR_INFO_BR_CNTR_NUM 4
+#define LBR_INFO_BR_CNTR_BITS 2
+#define LBR_INFO_BR_CNTR_MASK GENMASK_ULL(LBR_INFO_BR_CNTR_BITS - 1, 0)
+#define LBR_INFO_BR_CNTR_FULL_MASK GENMASK_ULL(LBR_INFO_BR_CNTR_NUM * LBR_INFO_BR_CNTR_BITS - 1, 0)
#define MSR_ARCH_LBR_CTL 0x000014ce
#define ARCH_LBR_CTL_LBREN BIT(0)
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 2618ec7c3d1d..3736b8a46c04 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -31,6 +31,7 @@
#define ARCH_PERFMON_EVENTSEL_ENABLE (1ULL << 22)
#define ARCH_PERFMON_EVENTSEL_INV (1ULL << 23)
#define ARCH_PERFMON_EVENTSEL_CMASK 0xFF000000ULL
+#define ARCH_PERFMON_EVENTSEL_BR_CNTR (1ULL << 35)
#define INTEL_FIXED_BITS_MASK 0xFULL
#define INTEL_FIXED_BITS_STRIDE 4
@@ -223,6 +224,9 @@ union cpuid28_ecx {
unsigned int lbr_timed_lbr:1;
/* Branch Type Field Supported */
unsigned int lbr_br_type:1;
+ unsigned int reserved:13;
+ /* Branch counters (Event Logging) Supported */
+ unsigned int lbr_counters:4;
} split;
unsigned int full;
};
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-28 21:21:23 +0100