summaryrefslogtreecommitdiff
path: root/tools/perf/util
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/util')
-rw-r--r--tools/perf/util/arm-spe.c8
-rw-r--r--tools/perf/util/bpf-event.c10
-rw-r--r--tools/perf/util/bpf-filter.l2
-rw-r--r--tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c11
-rw-r--r--tools/perf/util/build-id.c2
-rw-r--r--tools/perf/util/comm.c2
-rw-r--r--tools/perf/util/debug.c2
-rw-r--r--tools/perf/util/dso.h4
-rw-r--r--tools/perf/util/env.c13
-rw-r--r--tools/perf/util/env.h4
-rw-r--r--tools/perf/util/evlist.c13
-rw-r--r--tools/perf/util/evsel.c11
-rw-r--r--tools/perf/util/evsel.h2
-rw-r--r--tools/perf/util/expr.c5
-rw-r--r--tools/perf/util/header.c8
-rw-r--r--tools/perf/util/intel-pt.c205
-rw-r--r--tools/perf/util/intel-tpebs.c2
-rw-r--r--tools/perf/util/machine.c8
-rw-r--r--tools/perf/util/maps.c7
-rw-r--r--tools/perf/util/mem-events.c2
-rw-r--r--tools/perf/util/namespaces.c7
-rw-r--r--tools/perf/util/namespaces.h3
-rw-r--r--tools/perf/util/pmu.c11
-rw-r--r--tools/perf/util/pmu.h5
-rw-r--r--tools/perf/util/pmus.c20
-rw-r--r--tools/perf/util/print-events.c1
-rw-r--r--tools/perf/util/python.c17
-rw-r--r--tools/perf/util/stat-shadow.c3
-rw-r--r--tools/perf/util/symbol-minimal.c160
-rw-r--r--tools/perf/util/symbol.c1
-rw-r--r--tools/perf/util/thread.c8
-rw-r--r--tools/perf/util/thread.h2
-rw-r--r--tools/perf/util/units.c2
33 files changed, 406 insertions, 155 deletions
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 138ffc71b32d..2c06f2a85400 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -37,6 +37,8 @@
#include "../../arch/arm64/include/asm/cputype.h"
#define MAX_TIMESTAMP (~0ULL)
+#define is_ldst_op(op) (!!((op) & ARM_SPE_OP_LDST))
+
struct arm_spe {
struct auxtrace auxtrace;
struct auxtrace_queues queues;
@@ -520,6 +522,10 @@ static u64 arm_spe__synth_data_source(const struct arm_spe_record *record, u64 m
union perf_mem_data_src data_src = { .mem_op = PERF_MEM_OP_NA };
bool is_neoverse = is_midr_in_range_list(midr, neoverse_spe);
+ /* Only synthesize data source for LDST operations */
+ if (!is_ldst_op(record->op))
+ return 0;
+
if (record->op & ARM_SPE_OP_LD)
data_src.mem_op = PERF_MEM_OP_LOAD;
else if (record->op & ARM_SPE_OP_ST)
@@ -619,7 +625,7 @@ static int arm_spe_sample(struct arm_spe_queue *speq)
* When data_src is zero it means the record is not a memory operation,
* skip to synthesize memory sample for this case.
*/
- if (spe->sample_memory && data_src) {
+ if (spe->sample_memory && is_ldst_op(record->op)) {
err = arm_spe__synth_mem_sample(speq, spe->memory_id, data_src);
if (err)
return err;
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 13608237c50e..c81444059ad0 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -289,7 +289,10 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session,
}
info_node->info_linear = info_linear;
- perf_env__insert_bpf_prog_info(env, info_node);
+ if (!perf_env__insert_bpf_prog_info(env, info_node)) {
+ free(info_linear);
+ free(info_node);
+ }
info_linear = NULL;
/*
@@ -480,7 +483,10 @@ static void perf_env__add_bpf_info(struct perf_env *env, u32 id)
info_node = malloc(sizeof(struct bpf_prog_info_node));
if (info_node) {
info_node->info_linear = info_linear;
- perf_env__insert_bpf_prog_info(env, info_node);
+ if (!perf_env__insert_bpf_prog_info(env, info_node)) {
+ free(info_linear);
+ free(info_node);
+ }
} else
free(info_linear);
diff --git a/tools/perf/util/bpf-filter.l b/tools/perf/util/bpf-filter.l
index f313404f95a9..6aa65ade3385 100644
--- a/tools/perf/util/bpf-filter.l
+++ b/tools/perf/util/bpf-filter.l
@@ -76,7 +76,7 @@ static int path_or_error(void)
num_dec [0-9]+
num_hex 0[Xx][0-9a-fA-F]+
space [ \t]+
-path [^ \t\n]+
+path [^ \t\n,]+
ident [_a-zA-Z][_a-zA-Z0-9]+
%%
diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
index 4a62ed593e84..e4352881e3fa 100644
--- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
+++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
@@ -431,9 +431,9 @@ static bool pid_filter__has(struct pids_filtered *pids, pid_t pid)
static int augment_sys_enter(void *ctx, struct syscall_enter_args *args)
{
bool augmented, do_output = false;
- int zero = 0, size, aug_size, index,
- value_size = sizeof(struct augmented_arg) - offsetof(struct augmented_arg, value);
+ int zero = 0, index, value_size = sizeof(struct augmented_arg) - offsetof(struct augmented_arg, value);
u64 output = 0; /* has to be u64, otherwise it won't pass the verifier */
+ s64 aug_size, size;
unsigned int nr, *beauty_map;
struct beauty_payload_enter *payload;
void *arg, *payload_offset;
@@ -484,14 +484,11 @@ static int augment_sys_enter(void *ctx, struct syscall_enter_args *args)
} else if (size > 0 && size <= value_size) { /* struct */
if (!bpf_probe_read_user(((struct augmented_arg *)payload_offset)->value, size, arg))
augmented = true;
- } else if (size < 0 && size >= -6) { /* buffer */
+ } else if ((int)size < 0 && size >= -6) { /* buffer */
index = -(size + 1);
barrier_var(index); // Prevent clang (noticed with v18) from removing the &= 7 trick.
index &= 7; // Satisfy the bounds checking with the verifier in some kernels.
- aug_size = args->args[index];
-
- if (aug_size > TRACE_AUG_MAX_BUF)
- aug_size = TRACE_AUG_MAX_BUF;
+ aug_size = args->args[index] > TRACE_AUG_MAX_BUF ? TRACE_AUG_MAX_BUF : args->args[index];
if (aug_size > 0) {
if (!bpf_probe_read_user(((struct augmented_arg *)payload_offset)->value, aug_size, arg))
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index e763e8d99a43..ee00313d5d7e 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -864,7 +864,7 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine,
char *allocated_name = NULL;
int ret = 0;
- if (!dso__has_build_id(dso))
+ if (!dso__has_build_id(dso) || !dso__hit(dso))
return 0;
if (dso__is_kcore(dso)) {
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index 49b79cf0c5cc..8aa456d7c2cd 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -5,6 +5,8 @@
#include <internal/rc_check.h>
#include <linux/refcount.h>
#include <linux/zalloc.h>
+#include <tools/libc_compat.h> // reallocarray
+
#include "rwsem.h"
DECLARE_RC_STRUCT(comm_str) {
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index d633d15329fa..e56330c85fe7 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -46,8 +46,8 @@ int debug_type_profile;
FILE *debug_file(void)
{
if (!_debug_file) {
- pr_warning_once("debug_file not set");
debug_set_file(stderr);
+ pr_warning_once("debug_file not set");
}
return _debug_file;
}
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index bb8e8f444054..c0472a41147c 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -808,7 +808,9 @@ static inline bool dso__is_kcore(const struct dso *dso)
static inline bool dso__is_kallsyms(const struct dso *dso)
{
- return RC_CHK_ACCESS(dso)->kernel && RC_CHK_ACCESS(dso)->long_name[0] != '/';
+ enum dso_binary_type bt = dso__binary_type(dso);
+
+ return bt == DSO_BINARY_TYPE__KALLSYMS || bt == DSO_BINARY_TYPE__GUEST_KALLSYMS;
}
bool dso__is_object_file(const struct dso *dso);
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 1edbccfc3281..d981b6f4bc5e 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -22,15 +22,19 @@ struct perf_env perf_env;
#include "bpf-utils.h"
#include <bpf/libbpf.h>
-void perf_env__insert_bpf_prog_info(struct perf_env *env,
+bool perf_env__insert_bpf_prog_info(struct perf_env *env,
struct bpf_prog_info_node *info_node)
{
+ bool ret;
+
down_write(&env->bpf_progs.lock);
- __perf_env__insert_bpf_prog_info(env, info_node);
+ ret = __perf_env__insert_bpf_prog_info(env, info_node);
up_write(&env->bpf_progs.lock);
+
+ return ret;
}
-void __perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node)
+bool __perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node)
{
__u32 prog_id = info_node->info_linear->info.id;
struct bpf_prog_info_node *node;
@@ -48,13 +52,14 @@ void __perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info
p = &(*p)->rb_right;
} else {
pr_debug("duplicated bpf prog info %u\n", prog_id);
- return;
+ return false;
}
}
rb_link_node(&info_node->rb_node, parent, p);
rb_insert_color(&info_node->rb_node, &env->bpf_progs.infos);
env->bpf_progs.infos_cnt++;
+ return true;
}
struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 51b36c36019b..38de0af2a680 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -176,9 +176,9 @@ const char *perf_env__raw_arch(struct perf_env *env);
int perf_env__nr_cpus_avail(struct perf_env *env);
void perf_env__init(struct perf_env *env);
-void __perf_env__insert_bpf_prog_info(struct perf_env *env,
+bool __perf_env__insert_bpf_prog_info(struct perf_env *env,
struct bpf_prog_info_node *info_node);
-void perf_env__insert_bpf_prog_info(struct perf_env *env,
+bool perf_env__insert_bpf_prog_info(struct perf_env *env,
struct bpf_prog_info_node *info_node);
struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
__u32 prog_id);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index a9df84692d4a..dac87dccaaaa 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1434,19 +1434,18 @@ static int evlist__create_syswide_maps(struct evlist *evlist)
*/
cpus = perf_cpu_map__new_online_cpus();
if (!cpus)
- goto out;
+ return -ENOMEM;
threads = perf_thread_map__new_dummy();
- if (!threads)
- goto out_put;
+ if (!threads) {
+ perf_cpu_map__put(cpus);
+ return -ENOMEM;
+ }
perf_evlist__set_maps(&evlist->core, cpus, threads);
-
perf_thread_map__put(threads);
-out_put:
perf_cpu_map__put(cpus);
-out:
- return -ENOMEM;
+ return 0;
}
int evlist__open(struct evlist *evlist)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index dbf9c8cee3c5..6d7249cc1a99 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1477,6 +1477,15 @@ static void evsel__free_config_terms(struct evsel *evsel)
free_config_terms(&evsel->config_terms);
}
+static void (*evsel__priv_destructor)(void *priv);
+
+void evsel__set_priv_destructor(void (*destructor)(void *priv))
+{
+ assert(evsel__priv_destructor == NULL);
+
+ evsel__priv_destructor = destructor;
+}
+
void evsel__exit(struct evsel *evsel)
{
assert(list_empty(&evsel->core.node));
@@ -1502,6 +1511,8 @@ void evsel__exit(struct evsel *evsel)
hashmap__free(evsel->per_pkg_mask);
evsel->per_pkg_mask = NULL;
zfree(&evsel->metric_events);
+ if (evsel__priv_destructor)
+ evsel__priv_destructor(evsel->priv);
perf_evsel__object.fini(evsel);
if (evsel__tool_event(evsel) == PERF_TOOL_SYSTEM_TIME ||
evsel__tool_event(evsel) == PERF_TOOL_USER_TIME)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 15e745a9a798..26574a33a725 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -282,6 +282,8 @@ void evsel__init(struct evsel *evsel, struct perf_event_attr *attr, int idx);
void evsel__exit(struct evsel *evsel);
void evsel__delete(struct evsel *evsel);
+void evsel__set_priv_destructor(void (*destructor)(void *priv));
+
struct callchain_param;
void evsel__config(struct evsel *evsel, struct record_opts *opts,
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index b2536a59c44e..90c6ce2212e4 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -288,7 +288,7 @@ struct expr_parse_ctx *expr__ctx_new(void)
{
struct expr_parse_ctx *ctx;
- ctx = malloc(sizeof(struct expr_parse_ctx));
+ ctx = calloc(1, sizeof(struct expr_parse_ctx));
if (!ctx)
return NULL;
@@ -297,9 +297,6 @@ struct expr_parse_ctx *expr__ctx_new(void)
free(ctx);
return NULL;
}
- ctx->sctx.user_requested_cpu_list = NULL;
- ctx->sctx.runtime = 0;
- ctx->sctx.system_wide = false;
return ctx;
}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index a6386d12afd7..7b99f58f7bf2 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3188,7 +3188,10 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused)
/* after reading from file, translate offset to address */
bpil_offs_to_addr(info_linear);
info_node->info_linear = info_linear;
- __perf_env__insert_bpf_prog_info(env, info_node);
+ if (!__perf_env__insert_bpf_prog_info(env, info_node)) {
+ free(info_linear);
+ free(info_node);
+ }
}
up_write(&env->bpf_progs.lock);
@@ -3235,7 +3238,8 @@ static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused)
if (__do_read(ff, node->data, data_size))
goto out;
- __perf_env__insert_btf(env, node);
+ if (!__perf_env__insert_btf(env, node))
+ free(node);
node = NULL;
}
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index fd2597613f3d..61f10578e121 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -127,6 +127,7 @@ struct intel_pt {
bool single_pebs;
bool sample_pebs;
+ int pebs_data_src_fmt;
struct evsel *pebs_evsel;
u64 evt_sample_type;
@@ -175,6 +176,7 @@ enum switch_state {
struct intel_pt_pebs_event {
struct evsel *evsel;
u64 id;
+ int data_src_fmt;
};
struct intel_pt_queue {
@@ -2232,7 +2234,146 @@ static void intel_pt_add_lbrs(struct branch_stack *br_stack,
}
}
-static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evsel *evsel, u64 id)
+#define P(a, b) PERF_MEM_S(a, b)
+#define OP_LH (P(OP, LOAD) | P(LVL, HIT))
+#define LEVEL(x) P(LVLNUM, x)
+#define REM P(REMOTE, REMOTE)
+#define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS))
+
+#define PERF_PEBS_DATA_SOURCE_GRT_MAX 0x10
+#define PERF_PEBS_DATA_SOURCE_GRT_MASK (PERF_PEBS_DATA_SOURCE_GRT_MAX - 1)
+
+/* Based on kernel __intel_pmu_pebs_data_source_grt() and pebs_data_source */
+static const u64 pebs_data_source_grt[PERF_PEBS_DATA_SOURCE_GRT_MAX] = {
+ P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA), /* L3 miss|SNP N/A */
+ OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* L1 hit|SNP None */
+ OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE), /* LFB/MAB hit|SNP None */
+ OP_LH | P(LVL, L2) | LEVEL(L2) | P(SNOOP, NONE), /* L2 hit|SNP None */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, NONE), /* L3 hit|SNP None */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT), /* L3 hit|SNP Hit */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* L3 hit|SNP HitM */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* L3 hit|SNP HitM */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD), /* L3 hit|SNP Fwd */
+ OP_LH | P(LVL, REM_CCE1) | REM | LEVEL(L3) | P(SNOOP, HITM), /* Remote L3 hit|SNP HitM */
+ OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | P(SNOOP, HIT), /* RAM hit|SNP Hit */
+ OP_LH | P(LVL, REM_RAM1) | REM | LEVEL(L3) | P(SNOOP, HIT), /* Remote L3 hit|SNP Hit */
+ OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | SNOOP_NONE_MISS, /* RAM hit|SNP None or Miss */
+ OP_LH | P(LVL, REM_RAM1) | LEVEL(RAM) | REM | SNOOP_NONE_MISS, /* Remote RAM hit|SNP None or Miss */
+ OP_LH | P(LVL, IO) | LEVEL(NA) | P(SNOOP, NONE), /* I/O hit|SNP None */
+ OP_LH | P(LVL, UNC) | LEVEL(NA) | P(SNOOP, NONE), /* Uncached hit|SNP None */
+};
+
+/* Based on kernel __intel_pmu_pebs_data_source_cmt() and pebs_data_source */
+static const u64 pebs_data_source_cmt[PERF_PEBS_DATA_SOURCE_GRT_MAX] = {
+ P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA), /* L3 miss|SNP N/A */
+ OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* L1 hit|SNP None */
+ OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE), /* LFB/MAB hit|SNP None */
+ OP_LH | P(LVL, L2) | LEVEL(L2) | P(SNOOP, NONE), /* L2 hit|SNP None */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, NONE), /* L3 hit|SNP None */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, MISS), /* L3 hit|SNP Hit */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT), /* L3 hit|SNP HitM */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD), /* L3 hit|SNP HitM */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* L3 hit|SNP Fwd */
+ OP_LH | P(LVL, REM_CCE1) | REM | LEVEL(L3) | P(SNOOP, HITM), /* Remote L3 hit|SNP HitM */
+ OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | P(SNOOP, NONE), /* RAM hit|SNP Hit */
+ OP_LH | LEVEL(RAM) | REM | P(SNOOP, NONE), /* Remote L3 hit|SNP Hit */
+ OP_LH | LEVEL(RAM) | REM | P(SNOOPX, FWD), /* RAM hit|SNP None or Miss */
+ OP_LH | LEVEL(RAM) | REM | P(SNOOP, HITM), /* Remote RAM hit|SNP None or Miss */
+ OP_LH | P(LVL, IO) | LEVEL(NA) | P(SNOOP, NONE), /* I/O hit|SNP None */
+ OP_LH | P(LVL, UNC) | LEVEL(NA) | P(SNOOP, NONE), /* Uncached hit|SNP None */
+};
+
+/* Based on kernel pebs_set_tlb_lock() */
+static inline void pebs_set_tlb_lock(u64 *val, bool tlb, bool lock)
+{
+ /*
+ * TLB access
+ * 0 = did not miss 2nd level TLB
+ * 1 = missed 2nd level TLB
+ */
+ if (tlb)
+ *val |= P(TLB, MISS) | P(TLB, L2);
+ else
+ *val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2);
+
+ /* locked prefix */
+ if (lock)
+ *val |= P(LOCK, LOCKED);
+}
+
+/* Based on kernel __grt_latency_data() */
+static u64 intel_pt_grt_latency_data(u8 dse, bool tlb, bool lock, bool blk,
+ const u64 *pebs_data_source)
+{
+ u64 val;
+
+ dse &= PERF_PEBS_DATA_SOURCE_GRT_MASK;
+ val = pebs_data_source[dse];
+
+ pebs_set_tlb_lock(&val, tlb, lock);
+
+ if (blk)
+ val |= P(BLK, DATA);
+ else
+ val |= P(BLK, NA);
+
+ return val;
+}
+
+/* Default value for data source */
+#define PERF_MEM_NA (PERF_MEM_S(OP, NA) |\
+ PERF_MEM_S(LVL, NA) |\
+ PERF_MEM_S(SNOOP, NA) |\
+ PERF_MEM_S(LOCK, NA) |\
+ PERF_MEM_S(TLB, NA) |\
+ PERF_MEM_S(LVLNUM, NA))
+
+enum DATA_SRC_FORMAT {
+ DATA_SRC_FORMAT_ERR = -1,
+ DATA_SRC_FORMAT_NA = 0,
+ DATA_SRC_FORMAT_GRT = 1,
+ DATA_SRC_FORMAT_CMT = 2,
+};
+
+/* Based on kernel grt_latency_data() and cmt_latency_data */
+static u64 intel_pt_get_data_src(u64 mem_aux_info, int data_src_fmt)
+{
+ switch (data_src_fmt) {
+ case DATA_SRC_FORMAT_GRT: {
+ union {
+ u64 val;
+ struct {
+ unsigned int dse:4;
+ unsigned int locked:1;
+ unsigned int stlb_miss:1;
+ unsigned int fwd_blk:1;
+ unsigned int reserved:25;
+ };
+ } x = {.val = mem_aux_info};
+ return intel_pt_grt_latency_data(x.dse, x.stlb_miss, x.locked, x.fwd_blk,
+ pebs_data_source_grt);
+ }
+ case DATA_SRC_FORMAT_CMT: {
+ union {
+ u64 val;
+ struct {
+ unsigned int dse:5;
+ unsigned int locked:1;
+ unsigned int stlb_miss:1;
+ unsigned int fwd_blk:1;
+ unsigned int reserved:24;
+ };
+ } x = {.val = mem_aux_info};
+ return intel_pt_grt_latency_data(x.dse, x.stlb_miss, x.locked, x.fwd_blk,
+ pebs_data_source_cmt);
+ }
+ default:
+ return PERF_MEM_NA;
+ }
+}
+
+static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evsel *evsel,
+ u64 id, int data_src_fmt)
{
const struct intel_pt_blk_items *items = &ptq->state->items;
struct perf_sample sample = { .ip = 0, };
@@ -2350,6 +2491,18 @@ static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evse
}
}
+ if (sample_type & PERF_SAMPLE_DATA_SRC) {
+ if (items->has_mem_aux_info && data_src_fmt) {
+ if (data_src_fmt < 0) {
+ pr_err("Intel PT missing data_src info\n");
+ return -1;
+ }
+ sample.data_src = intel_pt_get_data_src(items->mem_aux_info, data_src_fmt);
+ } else {
+ sample.data_src = PERF_MEM_NA;
+ }
+ }
+
if (sample_type & PERF_SAMPLE_TRANSACTION && items->has_tsx_aux_info) {
u64 ax = items->has_rax ? items->rax : 0;
/* Refer kernel's intel_hsw_transaction() */
@@ -2368,9 +2521,10 @@ static int intel_pt_synth_single_pebs_sample(struct intel_pt_queue *ptq)
{
struct intel_pt *pt = ptq->pt;
struct evsel *evsel = pt->pebs_evsel;
+ int data_src_fmt = pt->pebs_data_src_fmt;
u64 id = evsel->core.id[0];
- return intel_pt_do_synth_pebs_sample(ptq, evsel, id);
+ return intel_pt_do_synth_pebs_sample(ptq, evsel, id, data_src_fmt);
}
static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
@@ -2395,7 +2549,7 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
hw_id);
return intel_pt_synth_single_pebs_sample(ptq);
}
- err = intel_pt_do_synth_pebs_sample(ptq, pe->evsel, pe->id);
+ err = intel_pt_do_synth_pebs_sample(ptq, pe->evsel, pe->id, pe->data_src_fmt);
if (err)
return err;
}
@@ -3355,6 +3509,49 @@ static int intel_pt_process_itrace_start(struct intel_pt *pt,
event->itrace_start.tid);
}
+/*
+ * Events with data_src are identified by L1_Hit_Indication
+ * refer https://github.com/intel/perfmon
+ */
+static int intel_pt_data_src_fmt(struct intel_pt *pt, struct evsel *evsel)
+{
+ struct perf_env *env = pt->machine->env;
+ int fmt = DATA_SRC_FORMAT_NA;
+
+ if (!env->cpuid)
+ return DATA_SRC_FORMAT_ERR;
+
+ /*
+ * PEBS-via-PT is only supported on E-core non-hybrid. Of those only
+ * Gracemont and Crestmont have data_src. Check for:
+ * Alderlake N (Gracemont)
+ * Sierra Forest (Crestmont)
+ * Grand Ridge (Crestmont)
+ */
+
+ if (!strncmp(env->cpuid, "GenuineIntel,6,190,", 19))
+ fmt = DATA_SRC_FORMAT_GRT;
+
+ if (!strncmp(env->cpuid, "GenuineIntel,6,175,", 19) ||
+ !strncmp(env->cpuid, "GenuineIntel,6,182,", 19))
+ fmt = DATA_SRC_FORMAT_CMT;
+
+ if (fmt == DATA_SRC_FORMAT_NA)
+ return fmt;
+
+ /*
+ * Only data_src events are:
+ * mem-loads event=0xd0,umask=0x5
+ * mem-stores event=0xd0,umask=0x6
+ */
+ if (evsel->core.attr.type == PERF_TYPE_RAW &&
+ ((evsel->core.attr.config & 0xffff) == 0x5d0 ||
+ (evsel->core.attr.config & 0xffff) == 0x6d0))
+ return fmt;
+
+ return DATA_SRC_FORMAT_NA;
+}
+
static int intel_pt_process_aux_output_hw_id(struct intel_pt *pt,
union perf_event *event,
struct perf_sample *sample)
@@ -3375,6 +3572,7 @@ static int intel_pt_process_aux_output_hw_id(struct intel_pt *pt,
ptq->pebs[hw_id].evsel = evsel;
ptq->pebs[hw_id].id = sample->id;
+ ptq->pebs[hw_id].data_src_fmt = intel_pt_data_src_fmt(pt, evsel);
return 0;
}
@@ -3924,6 +4122,7 @@ static void intel_pt_setup_pebs_events(struct intel_pt *pt)
}
pt->single_pebs = true;
pt->sample_pebs = true;
+ pt->pebs_data_src_fmt = intel_pt_data_src_fmt(pt, evsel);
pt->pebs_evsel = evsel;
}
}
diff --git a/tools/perf/util/intel-tpebs.c b/tools/perf/util/intel-tpebs.c
index 50a3c3e07160..2c421b475b3b 100644
--- a/tools/perf/util/intel-tpebs.c
+++ b/tools/perf/util/intel-tpebs.c
@@ -254,7 +254,7 @@ int tpebs_start(struct evlist *evsel_list)
new = zalloc(sizeof(*new));
if (!new) {
ret = -1;
- zfree(name);
+ zfree(&name);
goto err;
}
new->name = name;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 27d5345d2b30..20fd742984e3 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1003,7 +1003,7 @@ static int machine__get_running_kernel_start(struct machine *machine,
err = kallsyms__get_symbol_start(filename, "_edata", &addr);
if (err)
- err = kallsyms__get_function_start(filename, "_etext", &addr);
+ err = kallsyms__get_symbol_start(filename, "_etext", &addr);
if (!err)
*end = addr;
@@ -1974,7 +1974,7 @@ static void ip__resolve_ams(struct thread *thread,
* Thus, we have to try consecutively until we find a match
* or else, the symbol is unknown
*/
- thread__find_cpumode_addr_location(thread, ip, &al);
+ thread__find_cpumode_addr_location(thread, ip, /*symbols=*/true, &al);
ams->addr = ip;
ams->al_addr = al.addr;
@@ -2076,7 +2076,7 @@ static int add_callchain_ip(struct thread *thread,
al.sym = NULL;
al.srcline = NULL;
if (!cpumode) {
- thread__find_cpumode_addr_location(thread, ip, &al);
+ thread__find_cpumode_addr_location(thread, ip, symbols, &al);
} else {
if (ip >= PERF_CONTEXT_MAX) {
switch (ip) {
@@ -2104,6 +2104,8 @@ static int add_callchain_ip(struct thread *thread,
}
if (symbols)
thread__find_symbol(thread, *cpumode, ip, &al);
+ else
+ thread__find_map(thread, *cpumode, ip, &al);
}
if (al.sym != NULL) {
diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c
index 432399cbe5dd..09c9cc326c08 100644
--- a/tools/perf/util/maps.c
+++ b/tools/perf/util/maps.c
@@ -1136,8 +1136,13 @@ struct map *maps__find_next_entry(struct maps *maps, struct map *map)
struct map *result = NULL;
down_read(maps__lock(maps));
+ while (!maps__maps_by_address_sorted(maps)) {
+ up_read(maps__lock(maps));
+ maps__sort_by_address(maps);
+ down_read(maps__lock(maps));
+ }
i = maps__by_address_index(maps, map);
- if (i < maps__nr_maps(maps))
+ if (++i < maps__nr_maps(maps))
result = map__get(maps__maps_by_address(maps)[i]);
up_read(maps__lock(maps));
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index bf5090f5220b..9c4adfb45f62 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -189,7 +189,7 @@ static bool perf_pmu__mem_events_supported(const char *mnt, struct perf_pmu *pmu
if (!e->event_name)
return true;
- scnprintf(path, PATH_MAX, "%s/devices/%s/events/%s", mnt, pmu->name, e->event_name);
+ scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/events/%s", mnt, pmu->name, e->event_name);
return !stat(path, &st);
}
diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c
index cb185c5659d6..68f5de2d79c7 100644
--- a/tools/perf/util/namespaces.c
+++ b/tools/perf/util/namespaces.c
@@ -266,11 +266,16 @@ pid_t nsinfo__pid(const struct nsinfo *nsi)
return RC_CHK_ACCESS(nsi)->pid;
}
-pid_t nsinfo__in_pidns(const struct nsinfo *nsi)
+bool nsinfo__in_pidns(const struct nsinfo *nsi)
{
return RC_CHK_ACCESS(nsi)->in_pidns;
}
+void nsinfo__set_in_pidns(struct nsinfo *nsi)
+{
+ RC_CHK_ACCESS(nsi)->in_pidns = true;
+}
+
void nsinfo__mountns_enter(struct nsinfo *nsi,
struct nscookie *nc)
{
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
index 8c0731c6cbb7..e95c79b80e27 100644
--- a/tools/perf/util/namespaces.h
+++ b/tools/perf/util/namespaces.h
@@ -58,7 +58,8 @@ void nsinfo__clear_need_setns(struct nsinfo *nsi);
pid_t nsinfo__tgid(const struct nsinfo *nsi);
pid_t nsinfo__nstgid(const struct nsinfo *nsi);
pid_t nsinfo__pid(const struct nsinfo *nsi);
-pid_t nsinfo__in_pidns(const struct nsinfo *nsi);
+bool nsinfo__in_pidns(const struct nsinfo *nsi);
+void nsinfo__set_in_pidns(struct nsinfo *nsi);
void nsinfo__mountns_enter(struct nsinfo *nsi, struct nscookie *nc);
void nsinfo__mountns_exit(struct nscookie *nc);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 61bdda01a05a..8b4e346808b4 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -33,12 +33,12 @@
#define UNIT_MAX_LEN 31 /* max length for event unit name */
enum event_source {
- /* An event loaded from /sys/devices/<pmu>/events. */
+ /* An event loaded from /sys/bus/event_source/devices/<pmu>/events. */
EVENT_SRC_SYSFS,
/* An event loaded from a CPUID matched json file. */
EVENT_SRC_CPU_JSON,
/*
- * An event loaded from a /sys/devices/<pmu>/identifier matched json
+ * An event loaded from a /sys/bus/event_source/devices/<pmu>/identifier matched json
* file.
*/
EVENT_SRC_SYS_JSON,
@@ -593,7 +593,7 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name,
};
if (pmu_events_table__find_event(pmu->events_table, pmu, name,
update_alias, &data) == 0)
- pmu->cpu_json_aliases++;
+ pmu->cpu_common_json_aliases++;
}
pmu->sysfs_aliases++;
break;
@@ -1807,9 +1807,10 @@ size_t perf_pmu__num_events(struct perf_pmu *pmu)
if (pmu->cpu_aliases_added)
nr += pmu->cpu_json_aliases;
else if (pmu->events_table)
- nr += pmu_events_table__num_events(pmu->events_table, pmu) - pmu->cpu_json_aliases;
+ nr += pmu_events_table__num_events(pmu->events_table, pmu) -
+ pmu->cpu_common_json_aliases;
else
- assert(pmu->cpu_json_aliases == 0);
+ assert(pmu->cpu_json_aliases == 0 && pmu->cpu_common_json_aliases == 0);
return pmu->selectable ? nr + 1 : nr;
}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 4397c48ad569..bcd278b9b546 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -131,6 +131,11 @@ struct perf_pmu {
uint32_t cpu_json_aliases;
/** @sys_json_aliases: Number of json event aliases loaded matching the PMU's identifier. */
uint32_t sys_json_aliases;
+ /**
+ * @cpu_common_json_aliases: Number of json events that overlapped with sysfs when
+ * loading all sysfs events.
+ */
+ uint32_t cpu_common_json_aliases;
/** @sysfs_aliases_loaded: Are sysfs aliases loaded from disk? */
bool sysfs_aliases_loaded;
/**
diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
index d7d67e09d759..362596ed2729 100644
--- a/tools/perf/util/pmus.c
+++ b/tools/perf/util/pmus.c
@@ -701,11 +701,25 @@ char *perf_pmus__default_pmu_name(void)
struct perf_pmu *evsel__find_pmu(const struct evsel *evsel)
{
struct perf_pmu *pmu = evsel->pmu;
+ bool legacy_core_type;
- if (!pmu) {
- pmu = perf_pmus__find_by_type(evsel->core.attr.type);
- ((struct evsel *)evsel)->pmu = pmu;
+ if (pmu)
+ return pmu;
+
+ pmu = perf_pmus__find_by_type(evsel->core.attr.type);
+ legacy_core_type =
+ evsel->core.attr.type == PERF_TYPE_HARDWARE ||
+ evsel->core.attr.type == PERF_TYPE_HW_CACHE;
+ if (!pmu && legacy_core_type) {
+ if (perf_pmus__supports_extended_type()) {
+ u32 type = evsel->core.attr.config >> PERF_PMU_TYPE_SHIFT;
+
+ pmu = perf_pmus__find_by_type(type);
+ } else {
+ pmu = perf_pmus__find_core_pmu();
+ }
}
+ ((struct evsel *)evsel)->pmu = pmu;
return pmu;
}
diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c
index 81e0135cddf0..a1c71d9793bd 100644
--- a/tools/perf/util/print-events.c
+++ b/tools/perf/util/print-events.c
@@ -282,6 +282,7 @@ bool is_event_supported(u8 type, u64 config)
ret = evsel__open(evsel, NULL, tmap) >= 0;
}
+ evsel__close(evsel);
evsel__delete(evsel);
}
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index ee3d43a7ba45..e7f36ea9e2fa 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -79,7 +79,7 @@ struct pyrf_event {
};
#define sample_members \
- sample_member_def(sample_ip, ip, T_ULONGLONG, "event type"), \
+ sample_member_def(sample_ip, ip, T_ULONGLONG, "event ip"), \
sample_member_def(sample_pid, pid, T_INT, "event pid"), \
sample_member_def(sample_tid, tid, T_INT, "event tid"), \
sample_member_def(sample_time, time, T_ULONGLONG, "event timestamp"), \
@@ -512,6 +512,11 @@ static PyObject *pyrf_event__new(union perf_event *event)
event->header.type == PERF_RECORD_SWITCH_CPU_WIDE))
return NULL;
+ // FIXME this better be dynamic or we need to parse everything
+ // before calling perf_mmap__consume(), including tracepoint fields.
+ if (sizeof(pevent->event) < event->header.size)
+ return NULL;
+
ptype = pyrf_event__type[event->header.type];
pevent = PyObject_New(struct pyrf_event, ptype);
if (pevent != NULL)
@@ -1011,20 +1016,22 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
evsel = evlist__event2evsel(evlist, event);
if (!evsel) {
+ Py_DECREF(pyevent);
Py_INCREF(Py_None);
return Py_None;
}
pevent->evsel = evsel;
- err = evsel__parse_sample(evsel, event, &pevent->sample);
-
- /* Consume the even only after we parsed it out. */
perf_mmap__consume(&md->core);
- if (err)
+ err = evsel__parse_sample(evsel, &pevent->event, &pevent->sample);
+ if (err) {
+ Py_DECREF(pyevent);
return PyErr_Format(PyExc_OSError,
"perf: can't parse sample, err=%d", err);
+ }
+
return pyevent;
}
end:
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 99376c12dd8e..7c49997fab3a 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -154,6 +154,7 @@ static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type
{
const struct evsel *cur;
int evsel_ctx = evsel_context(evsel);
+ struct perf_pmu *evsel_pmu = evsel__find_pmu(evsel);
evlist__for_each_entry(evsel->evlist, cur) {
struct perf_stat_aggr *aggr;
@@ -180,7 +181,7 @@ static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type
* Except the SW CLOCK events,
* ignore if not the PMU we're looking for.
*/
- if ((type != STAT_NSECS) && (evsel->pmu != cur->pmu))
+ if ((type != STAT_NSECS) && (evsel_pmu != evsel__find_pmu(cur)))
continue;
aggr = &cur->stats->aggr[aggr_idx];
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index c6f369b5d893..36c1d3090689 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -90,11 +90,23 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
{
FILE *fp;
int ret = -1;
- bool need_swap = false;
+ bool need_swap = false, elf32;
u8 e_ident[EI_NIDENT];
- size_t buf_size;
- void *buf;
int i;
+ union {
+ struct {
+ Elf32_Ehdr ehdr32;
+ Elf32_Phdr *phdr32;
+ };
+ struct {
+ Elf64_Ehdr ehdr64;
+ Elf64_Phdr *phdr64;
+ };
+ } hdrs;
+ void *phdr;
+ size_t phdr_size;
+ void *buf = NULL;
+ size_t buf_size = 0;
fp = fopen(filename, "r");
if (fp == NULL)
@@ -108,117 +120,79 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
goto out;
need_swap = check_need_swap(e_ident[EI_DATA]);
+ elf32 = e_ident[EI_CLASS] == ELFCLASS32;
- /* for simplicity */
- fseek(fp, 0, SEEK_SET);
-
- if (e_ident[EI_CLASS] == ELFCLASS32) {
- Elf32_Ehdr ehdr;
- Elf32_Phdr *phdr;
-
- if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1)
- goto out;
+ if (fread(elf32 ? (void *)&hdrs.ehdr32 : (void *)&hdrs.ehdr64,
+ elf32 ? sizeof(hdrs.ehdr32) : sizeof(hdrs.ehdr64),
+ 1, fp) != 1)
+ goto out;
- if (need_swap) {
- ehdr.e_phoff = bswap_32(ehdr.e_phoff);
- ehdr.e_phentsize = bswap_16(ehdr.e_phentsize);
- ehdr.e_phnum = bswap_16(ehdr.e_phnum);
+ if (need_swap) {
+ if (elf32) {
+ hdrs.ehdr32.e_phoff = bswap_32(hdrs.ehdr32.e_phoff);
+ hdrs.ehdr32.e_phentsize = bswap_16(hdrs.ehdr32.e_phentsize);
+ hdrs.ehdr32.e_phnum = bswap_16(hdrs.ehdr32.e_phnum);
+ } else {
+ hdrs.ehdr64.e_phoff = bswap_64(hdrs.ehdr64.e_phoff);
+ hdrs.ehdr64.e_phentsize = bswap_16(hdrs.ehdr64.e_phentsize);
+ hdrs.ehdr64.e_phnum = bswap_16(hdrs.ehdr64.e_phnum);
}
+ }
+ phdr_size = elf32 ? hdrs.ehdr32.e_phentsize * hdrs.ehdr32.e_phnum
+ : hdrs.ehdr64.e_phentsize * hdrs.ehdr64.e_phnum;
+ phdr = malloc(phdr_size);
+ if (phdr == NULL)
+ goto out;
- buf_size = ehdr.e_phentsize * ehdr.e_phnum;
- buf = malloc(buf_size);
- if (buf == NULL)
- goto out;
-
- fseek(fp, ehdr.e_phoff, SEEK_SET);
- if (fread(buf, buf_size, 1, fp) != 1)
- goto out_free;
-
- for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) {
- void *tmp;
- long offset;
-
- if (need_swap) {
- phdr->p_type = bswap_32(phdr->p_type);
- phdr->p_offset = bswap_32(phdr->p_offset);
- phdr->p_filesz = bswap_32(phdr->p_filesz);
- }
-
- if (phdr->p_type != PT_NOTE)
- continue;
-
- buf_size = phdr->p_filesz;
- offset = phdr->p_offset;
- tmp = realloc(buf, buf_size);
- if (tmp == NULL)
- goto out_free;
-
- buf = tmp;
- fseek(fp, offset, SEEK_SET);
- if (fread(buf, buf_size, 1, fp) != 1)
- goto out_free;
+ fseek(fp, elf32 ? hdrs.ehdr32.e_phoff : hdrs.ehdr64.e_phoff, SEEK_SET);
+ if (fread(phdr, phdr_size, 1, fp) != 1)
+ goto out_free;
- ret = read_build_id(buf, buf_size, bid, need_swap);
- if (ret == 0) {
- ret = bid->size;
- break;
- }
- }
- } else {
- Elf64_Ehdr ehdr;
- Elf64_Phdr *phdr;
+ if (elf32)
+ hdrs.phdr32 = phdr;
+ else
+ hdrs.phdr64 = phdr;
- if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1)
- goto out;
+ for (i = 0; i < elf32 ? hdrs.ehdr32.e_phnum : hdrs.ehdr64.e_phnum; i++) {
+ size_t p_filesz;
if (need_swap) {
- ehdr.e_phoff = bswap_64(ehdr.e_phoff);
- ehdr.e_phentsize = bswap_16(ehdr.e_phentsize);
- ehdr.e_phnum = bswap_16(ehdr.e_phnum);
+ if (elf32) {
+ hdrs.phdr32[i].p_type = bswap_32(hdrs.phdr32[i].p_type);
+ hdrs.phdr32[i].p_offset = bswap_32(hdrs.phdr32[i].p_offset);
+ hdrs.phdr32[i].p_filesz = bswap_32(hdrs.phdr32[i].p_offset);
+ } else {
+ hdrs.phdr64[i].p_type = bswap_32(hdrs.phdr64[i].p_type);
+ hdrs.phdr64[i].p_offset = bswap_64(hdrs.phdr64[i].p_offset);
+ hdrs.phdr64[i].p_filesz = bswap_64(hdrs.phdr64[i].p_filesz);
+ }
}
+ if ((elf32 ? hdrs.phdr32[i].p_type : hdrs.phdr64[i].p_type) != PT_NOTE)
+ continue;
- buf_size = ehdr.e_phentsize * ehdr.e_phnum;
- buf = malloc(buf_size);
- if (buf == NULL)
- goto out;
-
- fseek(fp, ehdr.e_phoff, SEEK_SET);
- if (fread(buf, buf_size, 1, fp) != 1)
- goto out_free;
-
- for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) {
+ p_filesz = elf32 ? hdrs.phdr32[i].p_filesz : hdrs.phdr64[i].p_filesz;
+ if (p_filesz > buf_size) {
void *tmp;
- long offset;
-
- if (need_swap) {
- phdr->p_type = bswap_32(phdr->p_type);
- phdr->p_offset = bswap_64(phdr->p_offset);
- phdr->p_filesz = bswap_64(phdr->p_filesz);
- }
- if (phdr->p_type != PT_NOTE)
- continue;
-
- buf_size = phdr->p_filesz;
- offset = phdr->p_offset;
+ buf_size = p_filesz;
tmp = realloc(buf, buf_size);
if (tmp == NULL)
goto out_free;
-
buf = tmp;
- fseek(fp, offset, SEEK_SET);
- if (fread(buf, buf_size, 1, fp) != 1)
- goto out_free;
+ }
+ fseek(fp, elf32 ? hdrs.phdr32[i].p_offset : hdrs.phdr64[i].p_offset, SEEK_SET);
+ if (fread(buf, p_filesz, 1, fp) != 1)
+ goto out_free;
- ret = read_build_id(buf, buf_size, bid, need_swap);
- if (ret == 0) {
- ret = bid->size;
- break;
- }
+ ret = read_build_id(buf, p_filesz, bid, need_swap);
+ if (ret == 0) {
+ ret = bid->size;
+ break;
}
}
out_free:
free(buf);
+ free(phdr);
out:
fclose(fp);
return ret;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 3bbf173ad822..c0ec5ed4f1aa 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1405,6 +1405,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
goto out_err;
}
}
+ map__zput(new_node->map);
free(new_node);
}
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 0ffdd52d86d7..309d573eac9a 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -406,7 +406,7 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bo
}
void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
- struct addr_location *al)
+ bool symbols, struct addr_location *al)
{
size_t i;
const u8 cpumodes[] = {
@@ -417,7 +417,11 @@ void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
};
for (i = 0; i < ARRAY_SIZE(cpumodes); i++) {
- thread__find_symbol(thread, cpumodes[i], addr, al);
+ if (symbols)
+ thread__find_symbol(thread, cpumodes[i], addr, al);
+ else
+ thread__find_map(thread, cpumodes[i], addr, al);
+
if (al->map)
break;
}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 6cbf6eb2812e..1fb32e7d62a4 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -122,7 +122,7 @@ struct symbol *thread__find_symbol_fb(struct thread *thread, u8 cpumode,
u64 addr, struct addr_location *al);
void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
- struct addr_location *al);
+ bool symbols, struct addr_location *al);
int thread__memcpy(struct thread *thread, struct machine *machine,
void *buf, u64 ip, int len, bool *is64bit);
diff --git a/tools/perf/util/units.c b/tools/perf/util/units.c
index 32c39cfe209b..4c6a86e1cb54 100644
--- a/tools/perf/util/units.c
+++ b/tools/perf/util/units.c
@@ -64,7 +64,7 @@ unsigned long convert_unit(unsigned long value, char *unit)
int unit_number__scnprintf(char *buf, size_t size, u64 n)
{
- char unit[4] = "BKMG";
+ char unit[] = "BKMG";
int i = 0;
while (((n / 1024) > 1) && (i < 3)) {