From d59892017c5f6de2fdee221f2a7788696e9f2cda Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 4 Oct 2011 19:45:04 +0900 Subject: perf probe: Fix to show correct error string commit 44a56040a0037a845d5fa218dffde464579f0cab upstream. Fix perf probe to show correct error string when it fails to delete an event. The write(2) returns -1 if failed, and errno stores real error number. Signed-off-by: Masami Hiramatsu Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Paul Mackerras Cc: Ingo Molnar Link: http://lkml.kernel.org/r/20111004104504.14591.41266.stgit@fedora15 Signed-off-by: Steven Rostedt Signed-off-by: Greg Kroah-Hartman --- tools/perf/util/probe-event.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'tools/perf') diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index f022316..8c50da8 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -1869,8 +1869,10 @@ static int __del_trace_probe_event(int fd, struct str_node *ent) pr_debug("Writing event: %s\n", buf); ret = write(fd, buf, strlen(buf)); - if (ret < 0) + if (ret < 0) { + ret = -errno; goto error; + } printf("Remove event: %s\n", ent->s); return 0; -- cgit v1.1 From 248f3235861683bb1ffc7316b56bf783b162666f Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 4 Nov 2011 16:32:25 -0400 Subject: perf: Fix parsing of __print_flags() in TP_printk() commit d06c27b22aa66e48e32f03f9387328a9af9b0625 upstream. A update is made to the sched:sched_switch event that adds some logic to the first parameter of the __print_flags() that shows the state of tasks. This change cause perf to fail parsing the flags. A simple fix is needed to have the parser be able to process ops within the argument. Reported-by: Andrew Vagin Signed-off-by: Steven Rostedt Signed-off-by: Greg Kroah-Hartman --- tools/perf/util/trace-event-parse.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools/perf') diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 0a7ed5b..6c164dc 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -1537,6 +1537,8 @@ process_flags(struct event *event, struct print_arg *arg, char **tok) field = malloc_or_die(sizeof(*field)); type = process_arg(event, field, &token); + while (type == EVENT_OP) + type = process_op(event, field, &token); if (test_type_token(type, token, EVENT_DELIM, ",")) goto out_free; -- cgit v1.1 From 2431496fbdd142ccc83138d94f3f510a36ce9270 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 4 Nov 2011 16:32:25 -0400 Subject: perf: Fix parsing of __print_flags() in TP_printk() commit 49908a1b25d448d68fd26faca260e1850201575f upstream. A update is made to the sched:sched_switch event that adds some logic to the first parameter of the __print_flags() that shows the state of tasks. This change cause perf to fail parsing the flags. A simple fix is needed to have the parser be able to process ops within the argument. Reported-by: Andrew Vagin Signed-off-by: Steven Rostedt Signed-off-by: Greg Kroah-Hartman --- tools/perf/util/trace-event-parse.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools/perf') diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 6c164dc..bf54c48 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -1582,6 +1582,8 @@ process_symbols(struct event *event, struct print_arg *arg, char **tok) field = malloc_or_die(sizeof(*field)); type = process_arg(event, field, &token); + while (type == EVENT_OP) + type = process_op(event, field, &token); if (test_type_token(type, token, EVENT_DELIM, ",")) goto out_free; -- cgit v1.1 From 795f18956b547f0cfbcaa6d907d2bb05726a6a3e Mon Sep 17 00:00:00 2001 From: "Naveen N. Rao" Date: Fri, 3 Feb 2012 22:31:13 +0530 Subject: perf evsel: Fix an issue where perf report fails to show the proper percentage commit a4a03fc7ef89020baca4f19174e6a43767c6d78a upstream. This patch fixes an issue where perf report shows nan% for certain perf.data files. The below is from a report for a do_fork probe: -nan% sshd [kernel.kallsyms] [k] do_fork -nan% packagekitd [kernel.kallsyms] [k] do_fork -nan% dbus-daemon [kernel.kallsyms] [k] do_fork -nan% bash [kernel.kallsyms] [k] do_fork A git bisect shows commit f3bda2c as the cause. However, looking back through the git history, I saw commit 640c03c which seems to have removed the required initialization for perf_sample->period. The problem only started showing after commit f3bda2c. The below patch re-introduces the initialization and it fixes the problem for me. With the below patch, for the same perf.data: 73.08% bash [kernel.kallsyms] [k] do_fork 8.97% 11-dhclient [kernel.kallsyms] [k] do_fork 6.41% sshd [kernel.kallsyms] [k] do_fork 3.85% 20-chrony [kernel.kallsyms] [k] do_fork 2.56% sendmail [kernel.kallsyms] [k] do_fork This patch applies over current linux-tip commit 9949284. Problem introduced in: $ git describe 640c03c v2.6.37-rc3-83-g640c03c Cc: Ananth N Mavinakayanahalli Cc: Ingo Molnar Cc: Robert Richter Cc: Srikar Dronamraju Link: http://lkml.kernel.org/r/20120203170113.5190.25558.stgit@localhost6.localdomain6 Signed-off-by: Naveen N. Rao Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Greg Kroah-Hartman --- tools/perf/util/evsel.c | 1 + 1 file changed, 1 insertion(+) (limited to 'tools/perf') diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 0239eb8..ad2183c 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -348,6 +348,7 @@ int perf_event__parse_sample(const union perf_event *event, u64 type, data->cpu = data->pid = data->tid = -1; data->stream_id = data->id = data->time = -1ULL; + data->period = 1; if (event->header.type != PERF_RECORD_SAMPLE) { if (!sample_id_all) -- cgit v1.1 From f021e004b62bf213e3dfa70f747f1d3d6304fa6b Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 6 Feb 2012 18:54:06 -0200 Subject: perf tools: Fix perf stack to non executable on x86_64 commit 7a0153ee15575a4d07b5da8c96b79e0b0fd41a12 upstream. By adding following objects: bench/mem-memcpy-x86-64-asm.o the x86_64 perf binary ended up with executable stack. The reason was that above object are assembler sourced and is missing the GNU-stack note section. In such case the linker assumes that the final binary should not be restricted at all and mark the stack as RWX. Adding section ".note.GNU-stack" definition to mentioned object, with all flags disabled, thus omiting this object from linker stack flags decision. Problem introduced in: $ git describe ea7872b v2.6.37-rc2-19-gea7872b Reported-at: https://bugzilla.redhat.com/show_bug.cgi?id=783570 Reported-by: Clark Williams Acked-by: Eric Dumazet Cc: Corey Ashford Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1328100848-5630-1-git-send-email-jolsa@redhat.com Signed-off-by: Jiri Olsa [ committer note: Backported fix to perf/urgent (3.3-rc2+) ] Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Greg Kroah-Hartman --- tools/perf/bench/mem-memcpy-x86-64-asm.S | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'tools/perf') diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S index a57b66e..185a96d 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S @@ -1,2 +1,8 @@ #include "../../../arch/x86/lib/memcpy_64.S" +/* + * We need to provide note.GNU-stack section, saying that we want + * NOT executable stack. Otherwise the final linking will assume that + * the ELF stack should not be restricted at all and set it RWX. + */ +.section .note.GNU-stack,"",@progbits -- cgit v1.1 From 2f54cf2cb91a3efadeaae555baed47eac660d53c Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Wed, 7 Mar 2012 11:42:49 +1100 Subject: perf tools: Incorrect use of snprintf results in SEGV commit b832796caa1fda8516464a003c8c7cc547bc20c2 upstream. I have a workload where perf top scribbles over the stack and we SEGV. What makes it interesting is that an snprintf is causing this. The workload is a c++ gem that has method names over 3000 characters long, but snprintf is designed to avoid overrunning buffers. So what went wrong? The problem is we assume snprintf returns the number of characters written: ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", self->level); ... ret += repsep_snprintf(bf + ret, size - ret, "%s", self->ms.sym->name); Unfortunately this is not how snprintf works. snprintf returns the number of characters that would have been written if there was enough space. In the above case, if the first snprintf returns a value larger than size, we pass a negative size into the second snprintf and happily scribble over the stack. If you have 3000 character c++ methods thats a lot of stack to trample. This patch fixes repsep_snprintf by clamping the value at size - 1 which is the maximum snprintf can write before adding the NULL terminator. I get the sinking feeling that there are a lot of other uses of snprintf that have this same bug, we should audit them all. Cc: David Ahern Cc: Eric B Munson Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Yanmin Zhang Link: http://lkml.kernel.org/r/20120307114249.44275ca3@kryten Signed-off-by: Anton Blanchard Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Greg Kroah-Hartman --- tools/perf/util/sort.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'tools/perf') diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index f44fa54..0ffbc8e 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -122,6 +122,9 @@ static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...) } } va_end(ap); + + if (n >= (int)size) + return size - 1; return n; } -- cgit v1.1