summaryrefslogtreecommitdiffstats
path: root/tools
diff options
context:
space:
mode:
authorFrederic Weisbecker <fweisbec@gmail.com>2009-09-12 02:43:45 +0200
committerIngo Molnar <mingo@elte.hu>2009-09-13 10:22:41 +0200
commit46538818023e8ea94f656acfa1e38297e2df20e2 (patch)
tree1cac2198d1b90036cbec61639ebee6a80d6238a3 /tools
parentbcd3279f465cdcc1e0454b5f605f021c4ff4dbb5 (diff)
downloadlinux-46538818023e8ea94f656acfa1e38297e2df20e2.tar.bz2
perf sched: Fix bad event alignment
perf sched raises the following error when it meets a sched switch event: perf: builtin-sched.c:286: register_pid: Assertion `!(pid >= 65536)' failed. Abandon Currently in x86-64, the sched switch events have a hole in the middle of the structure: u16 common_type; u8 common_flags; u8 common_preempt_count; u32 common_pid; u32 common_tgid; char prev_comm[16]; u32 prev_pid; u32 prev_prio; <--- there u64 prev_state; char next_comm[16]; u32 next_pid; u32 next_prio; Gcc inserts a 4 bytes hole there for prev_state to be u64 aligned. And the events are exported to userspace with this hole. But in userspace, from perf sched, we fetch it using a structure that has a new field in the beginning: u32 size. This is because our trace is exported with its size as a field. But now that we have this new field, the hole in the middle disappears because it makes prev_state becoming well aligned. And since we are using a pointer to the raw trace using this struct, instead of reading prev_state, we are reading the hole. We could fix it by keeping the size seperate from the struct but actually there a lot of other potential problems: some fields may be saved as long in a 64 bits system and later read as long in a 32 bits system. Also this direct cast doesn't care about the endianness differences between the host traced machine and the machine in which we do the post processing. So instead of using such dangerous direct casts, fetch the values using the trace parsing API that already takes care of all these problems. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'tools')
-rw-r--r--tools/perf/builtin-sched.c101
-rw-r--r--tools/perf/util/trace-event-parse.c23
-rw-r--r--tools/perf/util/trace-event.h3
3 files changed, 102 insertions, 25 deletions
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index de93a2604528..0215936696ed 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -653,6 +653,30 @@ process_comm_event(event_t *event, unsigned long offset, unsigned long head)
return 0;
}
+
+struct raw_event_sample {
+ u32 size;
+ char data[0];
+};
+
+#define FILL_FIELD(ptr, field, event, data) \
+ ptr.field = (typeof(ptr.field)) raw_field_value(event, #field, data)
+
+#define FILL_ARRAY(ptr, array, event, data) \
+do { \
+ void *__array = raw_field_ptr(event, #array, data); \
+ memcpy(ptr.array, __array, sizeof(ptr.array)); \
+} while(0)
+
+#define FILL_COMMON_FIELDS(ptr, event, data) \
+do { \
+ FILL_FIELD(ptr, common_type, event, data); \
+ FILL_FIELD(ptr, common_flags, event, data); \
+ FILL_FIELD(ptr, common_preempt_count, event, data); \
+ FILL_FIELD(ptr, common_pid, event, data); \
+ FILL_FIELD(ptr, common_tgid, event, data); \
+} while (0)
+
struct trace_wakeup_event {
u32 size;
@@ -671,22 +695,32 @@ struct trace_wakeup_event {
};
static void
-process_sched_wakeup_event(struct trace_wakeup_event *wakeup_event, struct event *event,
+process_sched_wakeup_event(struct raw_event_sample *raw, struct event *event,
int cpu __used, u64 timestamp __used, struct thread *thread __used)
{
struct task_desc *waker, *wakee;
+ struct trace_wakeup_event wakeup_event;
+
+ FILL_COMMON_FIELDS(wakeup_event, event, raw->data);
+
+ FILL_ARRAY(wakeup_event, comm, event, raw->data);
+ FILL_FIELD(wakeup_event, pid, event, raw->data);
+ FILL_FIELD(wakeup_event, prio, event, raw->data);
+ FILL_FIELD(wakeup_event, success, event, raw->data);
+ FILL_FIELD(wakeup_event, cpu, event, raw->data);
+
if (verbose) {
printf("sched_wakeup event %p\n", event);
printf(" ... pid %d woke up %s/%d\n",
- wakeup_event->common_pid,
- wakeup_event->comm,
- wakeup_event->pid);
+ wakeup_event.common_pid,
+ wakeup_event.comm,
+ wakeup_event.pid);
}
- waker = register_pid(wakeup_event->common_pid, "<unknown>");
- wakee = register_pid(wakeup_event->pid, wakeup_event->comm);
+ waker = register_pid(wakeup_event.common_pid, "<unknown>");
+ wakee = register_pid(wakeup_event.pid, wakeup_event.comm);
add_sched_event_wakeup(waker, timestamp, wakee);
}
@@ -714,13 +748,24 @@ struct trace_switch_event {
unsigned long cpu_last_switched[MAX_CPUS];
static void
-process_sched_switch_event(struct trace_switch_event *switch_event, struct event *event,
+process_sched_switch_event(struct raw_event_sample *raw, struct event *event,
int cpu __used, u64 timestamp __used, struct thread *thread __used)
{
+ struct trace_switch_event switch_event;
struct task_desc *prev, *next;
u64 timestamp0;
s64 delta;
+ FILL_COMMON_FIELDS(switch_event, event, raw->data);
+
+ FILL_ARRAY(switch_event, prev_comm, event, raw->data);
+ FILL_FIELD(switch_event, prev_pid, event, raw->data);
+ FILL_FIELD(switch_event, prev_prio, event, raw->data);
+ FILL_FIELD(switch_event, prev_state, event, raw->data);
+ FILL_ARRAY(switch_event, next_comm, event, raw->data);
+ FILL_FIELD(switch_event, next_pid, event, raw->data);
+ FILL_FIELD(switch_event, next_prio, event, raw->data);
+
if (verbose)
printf("sched_switch event %p\n", event);
@@ -738,18 +783,18 @@ process_sched_switch_event(struct trace_switch_event *switch_event, struct event
if (verbose) {
printf(" ... switch from %s/%d to %s/%d [ran %Ld nsecs]\n",
- switch_event->prev_comm, switch_event->prev_pid,
- switch_event->next_comm, switch_event->next_pid,
+ switch_event.prev_comm, switch_event.prev_pid,
+ switch_event.next_comm, switch_event.next_pid,
delta);
}
- prev = register_pid(switch_event->prev_pid, switch_event->prev_comm);
- next = register_pid(switch_event->next_pid, switch_event->next_comm);
+ prev = register_pid(switch_event.prev_pid, switch_event.prev_comm);
+ next = register_pid(switch_event.next_pid, switch_event.next_comm);
cpu_last_switched[cpu] = timestamp;
add_sched_event_run(prev, timestamp, delta);
- add_sched_event_sleep(prev, timestamp, switch_event->prev_state);
+ add_sched_event_sleep(prev, timestamp, switch_event.prev_state);
}
struct trace_fork_event {
@@ -768,16 +813,25 @@ struct trace_fork_event {
};
static void
-process_sched_fork_event(struct trace_fork_event *fork_event, struct event *event,
+process_sched_fork_event(struct raw_event_sample *raw, struct event *event,
int cpu __used, u64 timestamp __used, struct thread *thread __used)
{
+ struct trace_fork_event fork_event;
+
+ FILL_COMMON_FIELDS(fork_event, event, raw->data);
+
+ FILL_ARRAY(fork_event, parent_comm, event, raw->data);
+ FILL_FIELD(fork_event, parent_pid, event, raw->data);
+ FILL_ARRAY(fork_event, child_comm, event, raw->data);
+ FILL_FIELD(fork_event, child_pid, event, raw->data);
+
if (verbose) {
printf("sched_fork event %p\n", event);
- printf("... parent: %s/%d\n", fork_event->parent_comm, fork_event->parent_pid);
- printf("... child: %s/%d\n", fork_event->child_comm, fork_event->child_pid);
+ printf("... parent: %s/%d\n", fork_event.parent_comm, fork_event.parent_pid);
+ printf("... child: %s/%d\n", fork_event.child_comm, fork_event.child_pid);
}
- register_pid(fork_event->parent_pid, fork_event->parent_comm);
- register_pid(fork_event->child_pid, fork_event->child_comm);
+ register_pid(fork_event.parent_pid, fork_event.parent_comm);
+ register_pid(fork_event.child_pid, fork_event.child_comm);
}
static void process_sched_exit_event(struct event *event,
@@ -791,10 +845,7 @@ static void
process_raw_event(event_t *raw_event __used, void *more_data,
int cpu, u64 timestamp, struct thread *thread)
{
- struct {
- u32 size;
- char data[0];
- } *raw = more_data;
+ struct raw_event_sample *raw = more_data;
struct event *event;
int type;
@@ -802,13 +853,13 @@ process_raw_event(event_t *raw_event __used, void *more_data,
event = trace_find_event(type);
if (!strcmp(event->name, "sched_switch"))
- process_sched_switch_event(more_data, event, cpu, timestamp, thread);
+ process_sched_switch_event(raw, event, cpu, timestamp, thread);
if (!strcmp(event->name, "sched_wakeup"))
- process_sched_wakeup_event(more_data, event, cpu, timestamp, thread);
+ process_sched_wakeup_event(raw, event, cpu, timestamp, thread);
if (!strcmp(event->name, "sched_wakeup_new"))
- process_sched_wakeup_event(more_data, event, cpu, timestamp, thread);
+ process_sched_wakeup_event(raw, event, cpu, timestamp, thread);
if (!strcmp(event->name, "sched_process_fork"))
- process_sched_fork_event(more_data, event, cpu, timestamp, thread);
+ process_sched_fork_event(raw, event, cpu, timestamp, thread);
if (!strcmp(event->name, "sched_process_exit"))
process_sched_exit_event(event, cpu, timestamp, thread);
}
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 16cf2d51c4e1..64d6e302751a 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -1776,6 +1776,29 @@ static unsigned long long read_size(void *ptr, int size)
}
}
+unsigned long long
+raw_field_value(struct event *event, const char *name, void *data)
+{
+ struct format_field *field;
+
+ field = find_any_field(event, name);
+ if (!field)
+ return 0ULL;
+
+ return read_size(data + field->offset, field->size);
+}
+
+void *raw_field_ptr(struct event *event, const char *name, void *data)
+{
+ struct format_field *field;
+
+ field = find_any_field(event, name);
+ if (!field)
+ return NULL;
+
+ return data + field->offset;
+}
+
static int get_common_info(const char *type, int *offset, int *size)
{
struct event *event;
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index bc81612fd244..d35ebf1e29ff 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -236,6 +236,9 @@ extern int header_page_data_size;
int parse_header_page(char *buf, unsigned long size);
int trace_parse_common_type(void *data);
struct event *trace_find_event(int id);
+unsigned long long
+raw_field_value(struct event *event, const char *name, void *data);
+void *raw_field_ptr(struct event *event, const char *name, void *data);
void read_tracing_data(struct perf_counter_attr *pattrs, int nb_counters);