summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--arch/s390/kernel/perf_cpum_cf.c2
-rw-r--r--arch/s390/kernel/perf_pai_crypto.c2
-rw-r--r--arch/s390/kernel/perf_pai_ext.c2
-rw-r--r--arch/x86/events/amd/core.c3
-rw-r--r--arch/x86/events/amd/ibs.c5
-rw-r--r--arch/x86/events/core.c3
-rw-r--r--arch/x86/events/intel/ds.c9
-rw-r--r--include/linux/perf_event.h26
-rw-r--r--kernel/events/core.c35
-rw-r--r--kernel/trace/bpf_trace.c11
10 files changed, 55 insertions, 43 deletions
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index b0bc68da6a11..33205dd410e4 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -981,7 +981,7 @@ static int cfdiag_push_sample(struct perf_event *event,
if (event->attr.sample_type & PERF_SAMPLE_RAW) {
raw.frag.size = cpuhw->usedss;
raw.frag.data = cpuhw->stop;
- perf_sample_save_raw_data(&data, &raw);
+ perf_sample_save_raw_data(&data, event, &raw);
}
overflow = perf_event_overflow(event, &data, &regs);
diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c
index fa7325454266..10725f5a6f0f 100644
--- a/arch/s390/kernel/perf_pai_crypto.c
+++ b/arch/s390/kernel/perf_pai_crypto.c
@@ -478,7 +478,7 @@ static int paicrypt_push_sample(size_t rawsize, struct paicrypt_map *cpump,
if (event->attr.sample_type & PERF_SAMPLE_RAW) {
raw.frag.size = rawsize;
raw.frag.data = cpump->save;
- perf_sample_save_raw_data(&data, &raw);
+ perf_sample_save_raw_data(&data, event, &raw);
}
overflow = perf_event_overflow(event, &data, &regs);
diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c
index 7f462bef1fc0..a8f0bad99cf0 100644
--- a/arch/s390/kernel/perf_pai_ext.c
+++ b/arch/s390/kernel/perf_pai_ext.c
@@ -503,7 +503,7 @@ static int paiext_push_sample(size_t rawsize, struct paiext_map *cpump,
if (event->attr.sample_type & PERF_SAMPLE_RAW) {
raw.frag.size = rawsize;
raw.frag.data = cpump->save;
- perf_sample_save_raw_data(&data, &raw);
+ perf_sample_save_raw_data(&data, event, &raw);
}
overflow = perf_event_overflow(event, &data, &regs);
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index b4a1a2576510..30d6ceb4c8ad 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -1001,8 +1001,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
if (!x86_perf_event_set_period(event))
continue;
- if (has_branch_stack(event))
- perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
+ perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
if (perf_event_overflow(event, &data, regs))
x86_pmu_stop(event, 0);
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index e91970b01d62..f02939655b2a 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -1118,7 +1118,7 @@ fail:
.data = ibs_data.data,
},
};
- perf_sample_save_raw_data(&data, &raw);
+ perf_sample_save_raw_data(&data, event, &raw);
}
if (perf_ibs == &perf_ibs_op)
@@ -1129,8 +1129,7 @@ fail:
* recorded as part of interrupt regs. Thus we need to use rip from
* interrupt regs while unwinding call stack.
*/
- if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
- perf_sample_save_callchain(&data, event, iregs);
+ perf_sample_save_callchain(&data, event, iregs);
throttle = perf_event_overflow(event, &data, &regs);
out:
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index c75c482d4c52..8f218ac0d445 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1707,8 +1707,7 @@ 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, NULL);
+ perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
if (perf_event_overflow(event, &data, regs))
x86_pmu_stop(event, 0);
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 1a4b326ca2ce..34cba39f6e70 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1789,8 +1789,7 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
* previous PMI context or an (I)RET happened between the record and
* PMI.
*/
- if (sample_type & PERF_SAMPLE_CALLCHAIN)
- perf_sample_save_callchain(data, event, iregs);
+ perf_sample_save_callchain(data, event, iregs);
/*
* We use the interrupt regs as a base because the PEBS record does not
@@ -1889,8 +1888,7 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
if (x86_pmu.intel_cap.pebs_format >= 3)
setup_pebs_time(event, data, pebs->tsc);
- if (has_branch_stack(event))
- perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL);
+ perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL);
}
static void adaptive_pebs_save_regs(struct pt_regs *regs,
@@ -1957,8 +1955,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
* previous PMI context or an (I)RET happened between the record and
* PMI.
*/
- if (sample_type & PERF_SAMPLE_CALLCHAIN)
- perf_sample_save_callchain(data, event, iregs);
+ perf_sample_save_callchain(data, event, iregs);
*regs = *iregs;
/* The ip in basic is EventingIP */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index cb99ec8c9e96..bf831b1485ff 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1279,6 +1279,11 @@ static inline void perf_sample_save_callchain(struct perf_sample_data *data,
{
int size = 1;
+ if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN))
+ return;
+ if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_CALLCHAIN))
+ return;
+
data->callchain = perf_callchain(event, regs);
size += data->callchain->nr;
@@ -1287,12 +1292,18 @@ static inline void perf_sample_save_callchain(struct perf_sample_data *data,
}
static inline void perf_sample_save_raw_data(struct perf_sample_data *data,
+ struct perf_event *event,
struct perf_raw_record *raw)
{
struct perf_raw_frag *frag = &raw->frag;
u32 sum = 0;
int size;
+ if (!(event->attr.sample_type & PERF_SAMPLE_RAW))
+ return;
+ if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_RAW))
+ return;
+
do {
sum += frag->size;
if (perf_raw_frag_last(frag))
@@ -1309,6 +1320,11 @@ static inline void perf_sample_save_raw_data(struct perf_sample_data *data,
data->sample_flags |= PERF_SAMPLE_RAW;
}
+static inline bool has_branch_stack(struct perf_event *event)
+{
+ return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK;
+}
+
static inline void perf_sample_save_brstack(struct perf_sample_data *data,
struct perf_event *event,
struct perf_branch_stack *brs,
@@ -1316,6 +1332,11 @@ static inline void perf_sample_save_brstack(struct perf_sample_data *data,
{
int size = sizeof(u64); /* nr */
+ if (!has_branch_stack(event))
+ return;
+ if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_BRANCH_STACK))
+ return;
+
if (branch_sample_hw_index(event))
size += sizeof(u64);
size += brs->nr * sizeof(struct perf_branch_entry);
@@ -1705,11 +1726,6 @@ static inline unsigned long perf_arch_guest_misc_flags(struct pt_regs *regs)
# define perf_arch_guest_misc_flags(regs) perf_arch_guest_misc_flags(regs)
#endif
-static inline bool has_branch_stack(struct perf_event *event)
-{
- return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK;
-}
-
static inline bool needs_branch_stack(struct perf_event *event)
{
return event->attr.branch_sample_type != 0;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 065f9188b44a..e9f698c08dc1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10425,9 +10425,9 @@ static struct pmu perf_tracepoint = {
};
static int perf_tp_filter_match(struct perf_event *event,
- struct perf_sample_data *data)
+ struct perf_raw_record *raw)
{
- void *record = data->raw->frag.data;
+ void *record = raw->frag.data;
/* only top level events have filters set */
if (event->parent)
@@ -10439,7 +10439,7 @@ static int perf_tp_filter_match(struct perf_event *event,
}
static int perf_tp_event_match(struct perf_event *event,
- struct perf_sample_data *data,
+ struct perf_raw_record *raw,
struct pt_regs *regs)
{
if (event->hw.state & PERF_HES_STOPPED)
@@ -10450,7 +10450,7 @@ static int perf_tp_event_match(struct perf_event *event,
if (event->attr.exclude_kernel && !user_mode(regs))
return 0;
- if (!perf_tp_filter_match(event, data))
+ if (!perf_tp_filter_match(event, raw))
return 0;
return 1;
@@ -10476,6 +10476,7 @@ EXPORT_SYMBOL_GPL(perf_trace_run_bpf_submit);
static void __perf_tp_event_target_task(u64 count, void *record,
struct pt_regs *regs,
struct perf_sample_data *data,
+ struct perf_raw_record *raw,
struct perf_event *event)
{
struct trace_entry *entry = record;
@@ -10485,13 +10486,17 @@ static void __perf_tp_event_target_task(u64 count, void *record,
/* Cannot deliver synchronous signal to other task. */
if (event->attr.sigtrap)
return;
- if (perf_tp_event_match(event, data, regs))
+ if (perf_tp_event_match(event, raw, regs)) {
+ perf_sample_data_init(data, 0, 0);
+ perf_sample_save_raw_data(data, event, raw);
perf_swevent_event(event, count, data, regs);
+ }
}
static void perf_tp_event_target_task(u64 count, void *record,
struct pt_regs *regs,
struct perf_sample_data *data,
+ struct perf_raw_record *raw,
struct perf_event_context *ctx)
{
unsigned int cpu = smp_processor_id();
@@ -10499,15 +10504,15 @@ static void perf_tp_event_target_task(u64 count, void *record,
struct perf_event *event, *sibling;
perf_event_groups_for_cpu_pmu(event, &ctx->pinned_groups, cpu, pmu) {
- __perf_tp_event_target_task(count, record, regs, data, event);
+ __perf_tp_event_target_task(count, record, regs, data, raw, event);
for_each_sibling_event(sibling, event)
- __perf_tp_event_target_task(count, record, regs, data, sibling);
+ __perf_tp_event_target_task(count, record, regs, data, raw, sibling);
}
perf_event_groups_for_cpu_pmu(event, &ctx->flexible_groups, cpu, pmu) {
- __perf_tp_event_target_task(count, record, regs, data, event);
+ __perf_tp_event_target_task(count, record, regs, data, raw, event);
for_each_sibling_event(sibling, event)
- __perf_tp_event_target_task(count, record, regs, data, sibling);
+ __perf_tp_event_target_task(count, record, regs, data, raw, sibling);
}
}
@@ -10525,15 +10530,10 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
},
};
- perf_sample_data_init(&data, 0, 0);
- perf_sample_save_raw_data(&data, &raw);
-
perf_trace_buf_update(record, event_type);
hlist_for_each_entry_rcu(event, head, hlist_entry) {
- if (perf_tp_event_match(event, &data, regs)) {
- perf_swevent_event(event, count, &data, regs);
-
+ if (perf_tp_event_match(event, &raw, regs)) {
/*
* Here use the same on-stack perf_sample_data,
* some members in data are event-specific and
@@ -10543,7 +10543,8 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
* because data->sample_flags is set.
*/
perf_sample_data_init(&data, 0, 0);
- perf_sample_save_raw_data(&data, &raw);
+ perf_sample_save_raw_data(&data, event, &raw);
+ perf_swevent_event(event, count, &data, regs);
}
}
@@ -10560,7 +10561,7 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
goto unlock;
raw_spin_lock(&ctx->lock);
- perf_tp_event_target_task(count, record, regs, &data, ctx);
+ perf_tp_event_target_task(count, record, regs, &data, &raw, ctx);
raw_spin_unlock(&ctx->lock);
unlock:
rcu_read_unlock();
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 949a3870946c..fe57dfbf2a86 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -619,7 +619,8 @@ static const struct bpf_func_proto bpf_perf_event_read_value_proto = {
static __always_inline u64
__bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
- u64 flags, struct perf_sample_data *sd)
+ u64 flags, struct perf_raw_record *raw,
+ struct perf_sample_data *sd)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
unsigned int cpu = smp_processor_id();
@@ -644,6 +645,8 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
if (unlikely(event->oncpu != cpu))
return -EOPNOTSUPP;
+ perf_sample_save_raw_data(sd, event, raw);
+
return perf_event_output(event, sd, regs);
}
@@ -687,9 +690,8 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
}
perf_sample_data_init(sd, 0, 0);
- perf_sample_save_raw_data(sd, &raw);
- err = __bpf_perf_event_output(regs, map, flags, sd);
+ err = __bpf_perf_event_output(regs, map, flags, &raw, sd);
out:
this_cpu_dec(bpf_trace_nest_level);
preempt_enable();
@@ -748,9 +750,8 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
perf_fetch_caller_regs(regs);
perf_sample_data_init(sd, 0, 0);
- perf_sample_save_raw_data(sd, &raw);
- ret = __bpf_perf_event_output(regs, map, flags, sd);
+ ret = __bpf_perf_event_output(regs, map, flags, &raw, sd);
out:
this_cpu_dec(bpf_event_output_nest_level);
preempt_enable();
generated by cgit (git 2.34.1) at 2025-03-26 01:06:31 +0000