From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932960Ab2FVNg6 (ORCPT ); Fri, 22 Jun 2012 09:36:58 -0400 Received: from mail-bk0-f46.google.com ([209.85.214.46]:43378 "EHLO mail-bk0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932888Ab2FVNg4 (ORCPT ); Fri, 22 Jun 2012 09:36:56 -0400 Date: Fri, 22 Jun 2012 15:36:50 +0200 From: Ingo Molnar To: Linus Torvalds Cc: linux-kernel@vger.kernel.org, Peter Zijlstra , Arnaldo Carvalho de Melo , Thomas Gleixner , Andrew Morton Subject: [GIT PULL] perf fixes Message-ID: <20120622133650.GA24136@gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Linus, Please pull the latest perf-urgent-for-linus git tree from: git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus HEAD: 6921a575c9f26f7ea274aaea3b78967810ce5513 Merge branch 'tip/perf/urgent-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace into perf/urgent Thanks, Ingo ------------------> Arnaldo Carvalho de Melo (1): perf tools: Fix synthesizing tracepoint names from the perf.data headers David Ahern (1): perf tools: Fix endianity swapping for adds_features bitmask Salman Qazi (1): perf: Use css_tryget() to avoid propping up css refcount Stephane Eranian (1): perf stat: Fix default output file Steven Rostedt (1): ftrace: Make all inline tags also include notrace include/linux/compiler-gcc.h | 6 ++-- kernel/events/core.c | 10 +++++-- tools/perf/builtin-stat.c | 8 +++++- tools/perf/util/header.c | 48 +++++++++++++++++++++++++++----- tools/perf/util/include/linux/bitops.h | 2 ++ tools/perf/util/session.c | 10 +++++++ tools/perf/util/session.h | 1 + 7 files changed, 71 insertions(+), 14 deletions(-) diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index e5834aa..6a6d7ae 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -47,9 +47,9 @@ */ #if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ !defined(CONFIG_OPTIMIZE_INLINING) || (__GNUC__ < 4) -# define inline inline __attribute__((always_inline)) -# define __inline__ __inline__ __attribute__((always_inline)) -# define __inline __inline __attribute__((always_inline)) +# define inline inline __attribute__((always_inline)) notrace +# define __inline__ __inline__ __attribute__((always_inline)) notrace +# define __inline __inline __attribute__((always_inline)) notrace #else /* A lot of inline functions can cause havoc with function tracing */ # define inline inline notrace diff --git a/kernel/events/core.c b/kernel/events/core.c index f85c015..d7d71d6 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -253,9 +253,9 @@ perf_cgroup_match(struct perf_event *event) 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) @@ -484,7 +484,11 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event, event->cgrp = cgrp; /* 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 diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 2625899..07b5c77 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -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"); 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) { struct timespec tm; 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); 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"; output = fdopen(output_fd, mode); if (!output) { diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 2dd5edf..e909d43 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1942,7 +1942,6 @@ int perf_file_header__read(struct perf_file_header *header, else return -1; } else if (ph->needs_swap) { - unsigned int i; /* * feature bitmap is declared as an array of unsigned longs -- * 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 -- * clearing all feature bits and setting buildid. */ - for (i = 0; i < BITS_TO_LONGS(HEADER_FEAT_BITS); ++i) - header->adds_features[i] = bswap_64(header->adds_features[i]); + mem_bswap_64(&header->adds_features, + BITS_TO_U64(HEADER_FEAT_BITS)); if (!test_bit(HEADER_HOSTNAME, header->adds_features)) { - for (i = 0; i < BITS_TO_LONGS(HEADER_FEAT_BITS); ++i) { - header->adds_features[i] = bswap_64(header->adds_features[i]); - header->adds_features[i] = bswap_32(header->adds_features[i]); - } + /* unswap as u64 */ + mem_bswap_64(&header->adds_features, + 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)) { @@ -2091,6 +2093,35 @@ static int read_attr(int fd, struct perf_header *ph, 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) { 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); + if (perf_evlist__set_tracepoint_names(session->evlist)) + goto out_delete_evlist; + header->frozen = 1; return 0; out_errno: diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h index f1584833..587a230 100644 --- a/tools/perf/util/include/linux/bitops.h +++ b/tools/perf/util/include/linux/bitops.h @@ -8,6 +8,8 @@ #define BITS_PER_LONG __WORDSIZE #define BITS_PER_BYTE 8 #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) \ for ((bit) = find_first_bit((addr), (size)); \ diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 2600916..c3e399b 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -442,6 +442,16 @@ static void perf_tool__fill_defaults(struct perf_tool *tool) 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) { diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 7a5434c..0c702e3 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -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); 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); int perf_session__create_kernel_maps(struct perf_session *self);