Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar.

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  ftrace: Make all inline tags also include notrace
  perf: Use css_tryget() to avoid propping up css refcount
  perf tools: Fix synthesizing tracepoint names from the perf.data headers
  perf stat: Fix default output file
  perf tools: Fix endianity swapping for adds_features bitmask
This commit is contained in:
Linus Torvalds 2012-06-22 10:58:57 -07:00
commit a11637194a
7 changed files with 71 additions and 14 deletions

View file

@ -47,9 +47,9 @@
*/ */
#if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ #if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \
!defined(CONFIG_OPTIMIZE_INLINING) || (__GNUC__ < 4) !defined(CONFIG_OPTIMIZE_INLINING) || (__GNUC__ < 4)
# define inline inline __attribute__((always_inline)) # define inline inline __attribute__((always_inline)) notrace
# define __inline__ __inline__ __attribute__((always_inline)) # define __inline__ __inline__ __attribute__((always_inline)) notrace
# define __inline __inline __attribute__((always_inline)) # define __inline __inline __attribute__((always_inline)) notrace
#else #else
/* A lot of inline functions can cause havoc with function tracing */ /* A lot of inline functions can cause havoc with function tracing */
# define inline inline notrace # define inline inline notrace

View file

@ -253,9 +253,9 @@ perf_cgroup_match(struct perf_event *event)
return !event->cgrp || event->cgrp == cpuctx->cgrp; return !event->cgrp || event->cgrp == cpuctx->cgrp;
} }
static inline void perf_get_cgroup(struct perf_event *event) static inline bool perf_tryget_cgroup(struct perf_event *event)
{ {
css_get(&event->cgrp->css); return css_tryget(&event->cgrp->css);
} }
static inline void perf_put_cgroup(struct perf_event *event) static inline void perf_put_cgroup(struct perf_event *event)
@ -484,7 +484,11 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
event->cgrp = cgrp; event->cgrp = cgrp;
/* must be done before we fput() the file */ /* must be done before we fput() the file */
perf_get_cgroup(event); if (!perf_tryget_cgroup(event)) {
event->cgrp = NULL;
ret = -ENOENT;
goto out;
}
/* /*
* all events in a group must monitor * all events in a group must monitor

View file

@ -1179,6 +1179,12 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
fprintf(stderr, "cannot use both --output and --log-fd\n"); fprintf(stderr, "cannot use both --output and --log-fd\n");
usage_with_options(stat_usage, options); usage_with_options(stat_usage, options);
} }
if (output_fd < 0) {
fprintf(stderr, "argument to --log-fd must be a > 0\n");
usage_with_options(stat_usage, options);
}
if (!output) { if (!output) {
struct timespec tm; struct timespec tm;
mode = append_file ? "a" : "w"; mode = append_file ? "a" : "w";
@ -1190,7 +1196,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
} }
clock_gettime(CLOCK_REALTIME, &tm); clock_gettime(CLOCK_REALTIME, &tm);
fprintf(output, "# started on %s\n", ctime(&tm.tv_sec)); fprintf(output, "# started on %s\n", ctime(&tm.tv_sec));
} else if (output_fd != 2) { } else if (output_fd > 0) {
mode = append_file ? "a" : "w"; mode = append_file ? "a" : "w";
output = fdopen(output_fd, mode); output = fdopen(output_fd, mode);
if (!output) { if (!output) {

View file

@ -1942,7 +1942,6 @@ int perf_file_header__read(struct perf_file_header *header,
else else
return -1; return -1;
} else if (ph->needs_swap) { } else if (ph->needs_swap) {
unsigned int i;
/* /*
* feature bitmap is declared as an array of unsigned longs -- * feature bitmap is declared as an array of unsigned longs --
* not good since its size can differ between the host that * not good since its size can differ between the host that
@ -1958,14 +1957,17 @@ int perf_file_header__read(struct perf_file_header *header,
* file), punt and fallback to the original behavior -- * file), punt and fallback to the original behavior --
* clearing all feature bits and setting buildid. * clearing all feature bits and setting buildid.
*/ */
for (i = 0; i < BITS_TO_LONGS(HEADER_FEAT_BITS); ++i) mem_bswap_64(&header->adds_features,
header->adds_features[i] = bswap_64(header->adds_features[i]); BITS_TO_U64(HEADER_FEAT_BITS));
if (!test_bit(HEADER_HOSTNAME, header->adds_features)) { if (!test_bit(HEADER_HOSTNAME, header->adds_features)) {
for (i = 0; i < BITS_TO_LONGS(HEADER_FEAT_BITS); ++i) { /* unswap as u64 */
header->adds_features[i] = bswap_64(header->adds_features[i]); mem_bswap_64(&header->adds_features,
header->adds_features[i] = bswap_32(header->adds_features[i]); BITS_TO_U64(HEADER_FEAT_BITS));
}
/* unswap as u32 */
mem_bswap_32(&header->adds_features,
BITS_TO_U32(HEADER_FEAT_BITS));
} }
if (!test_bit(HEADER_HOSTNAME, header->adds_features)) { if (!test_bit(HEADER_HOSTNAME, header->adds_features)) {
@ -2091,6 +2093,35 @@ static int read_attr(int fd, struct perf_header *ph,
return ret <= 0 ? -1 : 0; return ret <= 0 ? -1 : 0;
} }
static int perf_evsel__set_tracepoint_name(struct perf_evsel *evsel)
{
struct event_format *event = trace_find_event(evsel->attr.config);
char bf[128];
if (event == NULL)
return -1;
snprintf(bf, sizeof(bf), "%s:%s", event->system, event->name);
evsel->name = strdup(bf);
if (event->name == NULL)
return -1;
return 0;
}
static int perf_evlist__set_tracepoint_names(struct perf_evlist *evlist)
{
struct perf_evsel *pos;
list_for_each_entry(pos, &evlist->entries, node) {
if (pos->attr.type == PERF_TYPE_TRACEPOINT &&
perf_evsel__set_tracepoint_name(pos))
return -1;
}
return 0;
}
int perf_session__read_header(struct perf_session *session, int fd) int perf_session__read_header(struct perf_session *session, int fd)
{ {
struct perf_header *header = &session->header; struct perf_header *header = &session->header;
@ -2172,6 +2203,9 @@ int perf_session__read_header(struct perf_session *session, int fd)
lseek(fd, header->data_offset, SEEK_SET); lseek(fd, header->data_offset, SEEK_SET);
if (perf_evlist__set_tracepoint_names(session->evlist))
goto out_delete_evlist;
header->frozen = 1; header->frozen = 1;
return 0; return 0;
out_errno: out_errno:

View file

@ -8,6 +8,8 @@
#define BITS_PER_LONG __WORDSIZE #define BITS_PER_LONG __WORDSIZE
#define BITS_PER_BYTE 8 #define BITS_PER_BYTE 8
#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
#define BITS_TO_U64(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64))
#define BITS_TO_U32(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
#define for_each_set_bit(bit, addr, size) \ #define for_each_set_bit(bit, addr, size) \
for ((bit) = find_first_bit((addr), (size)); \ for ((bit) = find_first_bit((addr), (size)); \

View file

@ -442,6 +442,16 @@ static void perf_tool__fill_defaults(struct perf_tool *tool)
tool->finished_round = process_finished_round_stub; tool->finished_round = process_finished_round_stub;
} }
} }
void mem_bswap_32(void *src, int byte_size)
{
u32 *m = src;
while (byte_size > 0) {
*m = bswap_32(*m);
byte_size -= sizeof(u32);
++m;
}
}
void mem_bswap_64(void *src, int byte_size) void mem_bswap_64(void *src, int byte_size)
{ {

View file

@ -80,6 +80,7 @@ struct branch_info *machine__resolve_bstack(struct machine *self,
bool perf_session__has_traces(struct perf_session *self, const char *msg); bool perf_session__has_traces(struct perf_session *self, const char *msg);
void mem_bswap_64(void *src, int byte_size); void mem_bswap_64(void *src, int byte_size);
void mem_bswap_32(void *src, int byte_size);
void perf_event__attr_swap(struct perf_event_attr *attr); void perf_event__attr_swap(struct perf_event_attr *attr);
int perf_session__create_kernel_maps(struct perf_session *self); int perf_session__create_kernel_maps(struct perf_session *self);