From 314672a2c2780212fb770bb02d2fffaa1019823f Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Wed, 9 Apr 2014 17:24:16 -0700 Subject: Tools: hv: Handle the case when the target file exists correctly Return the appropriate error code and handle the case when the target file exists correctly. This fixes a bug. Signed-off-by: K. Y. Srinivasan Cc: [3.14] Signed-off-by: Greg Kroah-Hartman --- tools/hv/hv_fcopy_daemon.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/hv/hv_fcopy_daemon.c b/tools/hv/hv_fcopy_daemon.c index 4ecc4fd0bc1b..fba1c75aa484 100644 --- a/tools/hv/hv_fcopy_daemon.c +++ b/tools/hv/hv_fcopy_daemon.c @@ -82,8 +82,10 @@ static int hv_start_fcopy(struct hv_start_fcopy *smsg) if (!access(target_fname, F_OK)) { syslog(LOG_INFO, "File: %s exists", target_fname); - if (!smsg->copy_flags & OVER_WRITE) + if (!(smsg->copy_flags & OVER_WRITE)) { + error = HV_ERROR_ALREADY_EXISTS; goto done; + } } target_fd = open(target_fname, O_RDWR | O_CREAT | O_CLOEXEC, 0744); -- cgit v1.2.3 From acb61fc8ed73eb477a9044272d7a1b1f5a572f91 Mon Sep 17 00:00:00 2001 From: Alexander Yarygin Date: Wed, 9 Apr 2014 16:21:59 +0200 Subject: perf kvm: Fix 'Min time' counting in report command Every event in the perf-kvm has a 'stats' structure, which contains max/min/average/etc times of handling this event. The problem is that the 'perf-kvm stat report' command always shows that 'min time' is 0us for every event. Example: # perf kvm stat report Analyze events for all VCPUs: VM-EXIT Samples Samples% Time% Min Time Max Time Avg time [..] 0xB2 MSCH 12 0.07% 0.00% 0us 8us 7.31us ( +- 2.11% ) 0xB2 CHSC 12 0.07% 0.00% 0us 18us 9.39us ( +- 9.49% ) 0xB2 STPX 8 0.05% 0.00% 0us 2us 1.88us ( +- 7.18% ) 0xB2 STSI 7 0.04% 0.00% 0us 44us 16.49us ( +- 38.20% ) [..] This happens because the 'stats' structure is not initialized and stats->min equals to 0. Lets initialize the structure for every event after its allocation using init_stats() function. This initializes stats->min to -1 and makes 'Min time' statistics counting work: # perf kvm stat report Analyze events for all VCPUs: VM-EXIT Samples Samples% Time% Min Time Max Time Avg time [..] 0xB2 MSCH 12 0.07% 0.00% 6us 8us 7.31us ( +- 2.11% ) 0xB2 CHSC 12 0.07% 0.00% 7us 18us 9.39us ( +- 9.49% ) 0xB2 STPX 8 0.05% 0.00% 1us 2us 1.88us ( +- 7.18% ) 0xB2 STSI 7 0.04% 0.00% 1us 44us 16.49us ( +- 38.20% ) [..] Signed-off-by: Alexander Yarygin Signed-off-by: Christian Borntraeger Reviewed-by: David Ahern Link: http://lkml.kernel.org/r/1397053319-2130-3-git-send-email-borntraeger@de.ibm.com [ Fixing the perf examples changelog output ] Signed-off-by: Jiri Olsa --- tools/perf/builtin-kvm.c | 1 + 1 file changed, 1 insertion(+) (limited to 'tools') diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 21c164b8f9db..0f1e5a2f6ad7 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -404,6 +404,7 @@ static struct kvm_event *kvm_alloc_init_event(struct event_key *key) } event->key = *key; + init_stats(&event->total.stats); return event; } -- cgit v1.2.3 From 922d0e4d9f042f68baea28e5b3bd7bb708875f2e Mon Sep 17 00:00:00 2001 From: Vladimir Nikulichev Date: Thu, 17 Apr 2014 08:27:01 -0700 Subject: perf tools: Adjust symbols in VDSO pert-report doesn't resolve function names in VDSO: $ perf report --stdio -g flat,0.0,15,callee --sort pid ... 8.76% 0x7fff6b1fe861 __gettimeofday ACE_OS::gettimeofday() ... In this case symbol values should be adjusted the same way as for executables, relocatable objects and prelinked libraries. After fix: $ perf report --stdio -g flat,0.0,15,callee --sort pid ... 8.76% __vdso_gettimeofday __gettimeofday ACE_OS::gettimeofday() Signed-off-by: Vladimir Nikulichev Tested-by: Namhyung Kim Reviewed-by: Adrian Hunter Link: http://lkml.kernel.org/r/969812.163009436-sendEmail@nvs Signed-off-by: Jiri Olsa --- tools/perf/util/symbol-elf.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 3b7dbf51d4a9..6864661a79dd 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -6,6 +6,7 @@ #include #include "symbol.h" +#include "vdso.h" #include #include "debug.h" @@ -618,6 +619,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, GElf_Shdr shdr; ss->adjust_symbols = (ehdr.e_type == ET_EXEC || ehdr.e_type == ET_REL || + is_vdso_map(dso->short_name) || elf_section_by_name(elf, &ehdr, &shdr, ".gnu.prelink_undo", NULL) != NULL); -- cgit v1.2.3 From ffa91880a992ec1aaee4b4f7c9ddffda0c277ba9 Mon Sep 17 00:00:00 2001 From: Adrien BAK Date: Fri, 18 Apr 2014 11:00:43 +0900 Subject: perf tools: Improve error reporting In the current version, when using perf record, if something goes wrong in tools/perf/builtin-record.c:375 session = perf_session__new(file, false, NULL); The error message: "Not enough memory for reading per file header" is issued. This error message seems to be outdated and is not very helpful. This patch proposes to replace this error message by "Perf session creation failed" I believe this issue has been brought to lkml: https://lkml.org/lkml/2014/2/24/458 although this patch only tackles a (small) part of the issue. Additionnaly, this patch improves error reporting in tools/perf/util/data.c open_file_write. Currently, if the call to open fails, the user is unaware of it. This patch logs the error, before returning the error code to the caller. Reported-by: Will Deacon Signed-off-by: Adrien BAK Link: http://lkml.kernel.org/r/1397786443.3093.4.camel@beast [ Reorganize the changelog into paragraphs ] [ Added empty line after fd declaration in open_file_write ] Signed-off-by: Jiri Olsa --- tools/perf/builtin-record.c | 2 +- tools/perf/util/data.c | 9 ++++++++- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index eb524f91bffe..8ce62ef7f6c3 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -374,7 +374,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) session = perf_session__new(file, false, NULL); if (session == NULL) { - pr_err("Not enough memory for reading perf file header\n"); + pr_err("Perf session creation failed.\n"); return -1; } diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index 1fbcd8bdc11b..55de44ecebef 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -86,10 +86,17 @@ static int open_file_read(struct perf_data_file *file) static int open_file_write(struct perf_data_file *file) { + int fd; + if (check_backup(file)) return -1; - return open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR); + fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR); + + if (fd < 0) + pr_err("failed to open %s : %s\n", file->path, strerror(errno)); + + return fd; } static int open_file(struct perf_data_file *file) -- cgit v1.2.3 From 763d7f5f2718f085bab5a9e63308349728f3ad12 Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Sun, 20 Apr 2014 00:16:41 +0900 Subject: perf tests x86: Fix memory leak in sample_ustack() The buf is not freed, when kernel failed to get stack map and return. Signed-off-by: Masanari Iida Link: http://lkml.kernel.org/r/1398091024-7901-1-git-send-email-standby24x7@gmail.com Signed-off-by: Jiri Olsa --- tools/perf/arch/x86/tests/dwarf-unwind.c | 1 + 1 file changed, 1 insertion(+) (limited to 'tools') diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c index b602ad93ce63..b8c0102c70c8 100644 --- a/tools/perf/arch/x86/tests/dwarf-unwind.c +++ b/tools/perf/arch/x86/tests/dwarf-unwind.c @@ -26,6 +26,7 @@ static int sample_ustack(struct perf_sample *sample, map = map_groups__find(&thread->mg, MAP__FUNCTION, (u64) sp); if (!map) { pr_debug("failed to get stack map\n"); + free(buf); return -1; } -- cgit v1.2.3 From 4dc549e58b6ebf63554cd466d5ceb0e9c70ab859 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sun, 20 Apr 2014 10:50:00 +0200 Subject: perf tools: Disable libdw unwind for all but x86 arch So far there's only x86 libdw unwind support merged in perf. Disable it on all other architectures in case libdw unwind support is detected in system. Cc: Arnaldo Carvalho de Melo Cc: Corey Ashford Cc: David Ahern Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Jean Pihet Cc: Josh Boyer Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1397988006-14158-1-git-send-email-jolsa@redhat.com Signed-off-by: Jiri Olsa --- tools/perf/config/Makefile | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'tools') diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index ee21fa95ebcf..a71fb395e38f 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -34,6 +34,14 @@ ifeq ($(ARCH),arm) LIBUNWIND_LIBS = -lunwind -lunwind-arm endif +# So far there's only x86 libdw unwind support merged in perf. +# Disable it on all other architectures in case libdw unwind +# support is detected in system. Add supported architectures +# to the check. +ifneq ($(ARCH),x86) + NO_LIBDW_DWARF_UNWIND := 1 +endif + ifeq ($(LIBUNWIND_LIBS),) NO_LIBUNWIND := 1 else -- cgit v1.2.3 From 4508793541140723ab862d83095f6b5141d24e49 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 21 Apr 2014 22:23:46 -0400 Subject: tools lib traceevent: Fix backward compatibility macros for pevent filter enums The return value for pevent_filter_match() is suppose to return FILTER_NONE if the event doesn't have a filter, and FILTER_NOEXIST if there is no filter at all. But the change 41e12e580a7 "tools lib traceevent: Refactor pevent_filter_match() to get rid of die()" replaced the return value with PEVENT_ERRNO__* values and added "backward compatibility" macros that used the old names. Unfortunately, the NOEXIST and NONE macros were swapped, and this broke users that use the old return names. Signed-off-by: Steven Rostedt Link: http://lkml.kernel.org/r/20140421222346.0351ced4@gandalf.local.home Signed-off-by: Jiri Olsa --- tools/lib/traceevent/event-parse.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h index 791c539374c7..feab94281634 100644 --- a/tools/lib/traceevent/event-parse.h +++ b/tools/lib/traceevent/event-parse.h @@ -876,8 +876,8 @@ struct event_filter { struct event_filter *pevent_filter_alloc(struct pevent *pevent); /* for backward compatibility */ -#define FILTER_NONE PEVENT_ERRNO__FILTER_NOT_FOUND -#define FILTER_NOEXIST PEVENT_ERRNO__NO_FILTER +#define FILTER_NONE PEVENT_ERRNO__NO_FILTER +#define FILTER_NOEXIST PEVENT_ERRNO__FILTER_NOT_FOUND #define FILTER_MISS PEVENT_ERRNO__FILTER_MISS #define FILTER_MATCH PEVENT_ERRNO__FILTER_MATCH -- cgit v1.2.3 From de04f8657de9d3351a2d5880f1f7080b23b798cf Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 22 Apr 2014 19:23:30 -0400 Subject: tools lib traceevent: Fix memory leak in pretty_print() Commit 12e55569a244 "tools lib traceevent: Use helper trace-seq in print functions like kernel does" added a extra trace_seq helper to process string arguments like the kernel does it. But the difference between the kernel and the userspace library is that the kernel's trace_seq structure has a static allocated buffer. The userspace one has a dynamically allocated one. It requires a trace_seq_destroy(), otherwise it produces a nasty memory leak. Cc: stable@vger.kernel.org # 3.14+ Signed-off-by: Steven Rostedt Link: http://lkml.kernel.org/r/20140422192330.6bb09bf8@gandalf.local.home Signed-off-by: Jiri Olsa --- tools/lib/traceevent/event-parse.c | 1 + 1 file changed, 1 insertion(+) (limited to 'tools') diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index baec7d887da4..b83184f2d484 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -4344,6 +4344,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event format, len_arg, arg); trace_seq_terminate(&p); trace_seq_puts(s, p.buffer); + trace_seq_destroy(&p); arg = arg->next; break; default: -- cgit v1.2.3