From 70b01dfd765dd2196d51f33a49df23954416f34a Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 13 Oct 2017 10:37:28 +0200 Subject: perf hists: Fix crash in perf_hpp__reset_output_field() Du Changbin reported crash [1] when calling perf_hpp__reset_output_field() after unregistering field via perf_hpp__column_unregister(). This ends up in calling following list_del* sequence on the same format: perf_hpp__column_unregister: list_del(&format->list); perf_hpp__reset_output_field: list_del_init(&fmt->list); where the later list_del_init might touch already freed formats. Fixing this by replacing list_del() with list_del_init() in perf_hpp__column_unregister(). [1] http://marc.info/?l=linux-kernel&m=149059595826019&w=2 Reported-by: Changbin Du Signed-off-by: Jiri Olsa Cc: Andi Kleen Cc: David Ahern Cc: Jin Yao Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/20171013083736.15037-2-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/hist.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index ddb2c6fbdf91..6ee6b36bbc76 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -532,7 +532,7 @@ void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list, void perf_hpp__column_unregister(struct perf_hpp_fmt *format) { - list_del(&format->list); + list_del_init(&format->list); } void perf_hpp__cancel_cumulate(void) -- cgit From d0e35234f647631ddfa5fa8c8ec66c9bc698f0ab Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 13 Oct 2017 10:37:29 +0200 Subject: perf hists: Add extra integrity checks to fmt_free() Make sure the struct perf_hpp_fmt is properly unhooked before we free it. Signed-off-by: Jiri Olsa Cc: Andi Kleen Cc: Changbin Du Cc: David Ahern Cc: Jin Yao Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/20171013083736.15037-3-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/hist.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'tools') diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 6ee6b36bbc76..db79017a6e56 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -606,6 +606,13 @@ next: static void fmt_free(struct perf_hpp_fmt *fmt) { + /* + * At this point fmt should be completely + * unhooked, if not it's a bug. + */ + BUG_ON(!list_empty(&fmt->list)); + BUG_ON(!list_empty(&fmt->sort_list)); + if (fmt->free) fmt->free(fmt); } -- cgit From 29479bfe83bafb8aa37f36ca132ee8349d11da0c Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 13 Oct 2017 10:37:35 +0200 Subject: perf tools: Check wether the eBPF file exists in event parsing Adding the check wether the eBPF file exists, to consider it as eBPF input file. This way we can differentiate eBPF events from events that end up with same suffix as eBPF file. Before: $ perf stat -e 'cpu/uops_executed.core/' true bpf: builtin compilation failed: -95, try external compiler WARNING: unable to get correct kernel building directory. Hint: Set correct kbuild directory using 'kbuild-dir' option in [llvm] section of ~/.perfconfig or set it to "" to suppress kbuild detection. event syntax error: 'cpu/uops_executed.core/' \___ Failed to load cpu/uops_executed.c from source: 'version' section incorrect or lost After: $ perf stat -e 'cpu/uops_executed.core/' true Performance counter stats for 'true': 181,533 cpu/uops_executed.core/:u 0.002795447 seconds time elapsed If user makes type in the eBPF file, we prioritize the event syntax and show following warning: $ perf stat -e 'krava.c//' true event syntax error: 'krava.c//' \___ Cannot find PMU `krava.c'. Missing kernel support? Reported-and-Tested-by: Andi Kleen Signed-off-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Changbin Du Cc: David Ahern Cc: Jin Yao Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/20171013083736.15037-9-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.l | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index c42edeac451f..dcfdafdc2f1c 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -8,6 +8,9 @@ %{ #include +#include +#include +#include #include "../perf.h" #include "parse-events.h" #include "parse-events-bison.h" @@ -53,9 +56,8 @@ static int str(yyscan_t scanner, int token) return token; } -static bool isbpf(yyscan_t scanner) +static bool isbpf_suffix(char *text) { - char *text = parse_events_get_text(scanner); int len = strlen(text); if (len < 2) @@ -68,6 +70,17 @@ static bool isbpf(yyscan_t scanner) return false; } +static bool isbpf(yyscan_t scanner) +{ + char *text = parse_events_get_text(scanner); + struct stat st; + + if (!isbpf_suffix(text)) + return false; + + return stat(text, &st) == 0; +} + /* * This function is called when the parser gets two kind of input: * -- cgit From 3f50f614d61f91ad30b1947c429d1f235493a7f9 Mon Sep 17 00:00:00 2001 From: Taeung Song Date: Sat, 14 Oct 2017 00:10:12 +0900 Subject: perf record: Fix documentation for a inexistent option '-l' 'perf record' had a '-l' option that meant "scale counter values" a very long time ago, but it currently belongs to 'perf stat' as '-c'. So remove it. I found this problem in the below case. $ perf record -e cycles -l sleep 3 Error: unknown switch `l Signed-off-by: Taeung Song Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1507907412-19813-1-git-send-email-treeze.taeung@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-record.txt | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index e397453e5a46..63526f4416ea 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -8,8 +8,8 @@ perf-record - Run a command and record its profile into perf.data SYNOPSIS -------- [verse] -'perf record' [-e | --event=EVENT] [-l] [-a] -'perf record' [-e | --event=EVENT] [-l] [-a] -- [] +'perf record' [-e | --event=EVENT] [-a] +'perf record' [-e | --event=EVENT] [-a] -- [] DESCRIPTION ----------- -- cgit From 7f0cd23615040b9e53bb4980c986b721cba08bbc Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 17 Oct 2017 22:29:00 +0900 Subject: perf buildid-list: Fix crash when processing PERF_RECORD_NAMESPACE Thomas reported that 'perf buildid-list' gets a SEGFAULT due to NULL pointer deref when he ran it on a data with namespace events. It was because the buildid_id__mark_dso_hit_ops lacks the namespace event handler and perf_too__fill_default() didn't set it. Program received signal SIGSEGV, Segmentation fault. 0x0000000000000000 in ?? () Missing separate debuginfos, use: dnf debuginfo-install audit-libs-2.7.7-1.fc25.s390x bzip2-libs-1.0.6-21.fc25.s390x elfutils-libelf-0.169-1.fc25.s390x +elfutils-libs-0.169-1.fc25.s390x libcap-ng-0.7.8-1.fc25.s390x numactl-libs-2.0.11-2.ibm.fc25.s390x openssl-libs-1.1.0e-1.1.ibm.fc25.s390x perl-libs-5.24.1-386.fc25.s390x +python-libs-2.7.13-2.fc25.s390x slang-2.3.0-7.fc25.s390x xz-libs-5.2.3-2.fc25.s390x zlib-1.2.8-10.fc25.s390x (gdb) where #0 0x0000000000000000 in ?? () #1 0x00000000010fad6a in machines__deliver_event (machines=, machines@entry=0x2c6fd18, evlist=, event=event@entry=0x3fffdf00470, sample=0x3ffffffe880, sample@entry=0x3ffffffe888, tool=tool@entry=0x1312968 , file_offset=1136) at util/session.c:1287 #2 0x00000000010fbf4e in perf_session__deliver_event (file_offset=1136, tool=0x1312968 , sample=0x3ffffffe888, event=0x3fffdf00470, session=0x2c6fc30) at util/session.c:1340 #3 perf_session__process_event (session=0x2c6fc30, session@entry=0x0, event=event@entry=0x3fffdf00470, file_offset=file_offset@entry=1136) at util/session.c:1522 #4 0x00000000010fddde in __perf_session__process_events (file_size=11880, data_size=, data_offset=, session=0x0) at util/session.c:1899 #5 perf_session__process_events (session=0x0, session@entry=0x2c6fc30) at util/session.c:1953 #6 0x000000000103b2ac in perf_session__list_build_ids (with_hits=, force=) at builtin-buildid-list.c:83 #7 cmd_buildid_list (argc=, argv=) at builtin-buildid-list.c:115 #8 0x00000000010a026c in run_builtin (p=0x1311f78 , argc=argc@entry=2, argv=argv@entry=0x3fffffff3c0) at perf.c:296 #9 0x000000000102bc00 in handle_internal_command (argv=, argc=2) at perf.c:348 #10 run_argv (argcp=, argv=) at perf.c:392 #11 main (argc=, argv=0x3fffffff3c0) at perf.c:536 (gdb) Fix it by adding a stub event handler for namespace event. Committer testing: Further clarifying, plain using 'perf buildid-list' will not end up in a SEGFAULT when processing a perf.data file with namespace info: # perf record -a --namespaces sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 2.024 MB perf.data (1058 samples) ] # perf buildid-list | wc -l 38 # perf buildid-list | head -5 e2a171c7b905826fc8494f0711ba76ab6abbd604 /lib/modules/4.14.0-rc3+/build/vmlinux 874840a02d8f8a31cedd605d0b8653145472ced3 /lib/modules/4.14.0-rc3+/kernel/arch/x86/kvm/kvm-intel.ko ea7223776730cd8a22f320040aae4d54312984bc /lib/modules/4.14.0-rc3+/kernel/drivers/gpu/drm/i915/i915.ko 5961535e6732a8edb7f22b3f148bb2fa2e0be4b9 /lib/modules/4.14.0-rc3+/kernel/drivers/gpu/drm/drm.ko f045f54aa78cf1931cc893f78b6cbc52c72a8cb1 /usr/lib64/libc-2.25.so # It is only when one asks for checking what of those entries actually had samples, i.e. when we use either -H or --with-hits, that we will process all the PERF_RECORD_ events, and since tools/perf/builtin-buildid-list.c neither explicitely set a perf_tool.namespaces() callback nor the default stub was set that we end up, when processing a PERF_RECORD_NAMESPACE record, causing a SEGFAULT: # perf buildid-list -H Segmentation fault (core dumped) ^C # Reported-and-Tested-by: Thomas-Mich Richter Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Hari Bathini Cc: Hendrik Brueckner Cc: Jiri Olsa Cc: Peter Zijlstra Cc: Thomas-Mich Richter Fixes: f3b3614a284d ("perf tools: Add PERF_RECORD_NAMESPACES to include namespaces related info") Link: http://lkml.kernel.org/r/20171017132900.11043-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/session.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index a7ebd9fe8e40..76ab0709a20c 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -374,6 +374,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool) tool->mmap2 = process_event_stub; if (tool->comm == NULL) tool->comm = process_event_stub; + if (tool->namespaces == NULL) + tool->namespaces = process_event_stub; if (tool->fork == NULL) tool->fork = process_event_stub; if (tool->exit == NULL) -- cgit From 3d8bba9535ac6e79453c769dd0c8ea852a51ad60 Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Wed, 18 Oct 2017 23:11:18 +0800 Subject: perf xyarray: Fix wrong processing when closing evsel fd In current xyarray code, xyarray__max_x() returns max_y, and xyarray__max_y() returns max_x. It's confusing and for code logic it looks not correct. Error happens when closing evsel fd. Let's see this scenario: 1. Allocate an fd (pseudo-code) perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) { evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int)); } xyarray__new(int xlen, int ylen, size_t entry_size) { size_t row_size = ylen * entry_size; struct xyarray *xy = zalloc(sizeof(*xy) + xlen * row_size); xy->entry_size = entry_size; xy->row_size = row_size; xy->entries = xlen * ylen; xy->max_x = xlen; xy->max_y = ylen; ...... } So max_x is ncpus, max_y is nthreads and row_size = nthreads * 4. 2. Use perf syscall and get the fd int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, struct thread_map *threads) { for (cpu = 0; cpu < cpus->nr; cpu++) { for (thread = 0; thread < nthreads; thread++) { int fd, group_fd; fd = sys_perf_event_open(&evsel->attr, pid, cpus->map[cpu], group_fd, flags); FD(evsel, cpu, thread) = fd; } } static inline void *xyarray__entry(struct xyarray *xy, int x, int y) { return &xy->contents[x * xy->row_size + y * xy->entry_size]; } These codes don't have issues. The issue happens in the closing of fd. 3. Close fd. void perf_evsel__close_fd(struct perf_evsel *evsel) { int cpu, thread; for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) { close(FD(evsel, cpu, thread)); FD(evsel, cpu, thread) = -1; } } Since xyarray__max_x() returns max_y (nthreads) and xyarry__max_y() returns max_x (ncpus), so above code is actually to be: for (cpu = 0; cpu < nthreads; cpu++) for (thread = 0; thread < ncpus; ++thread) { close(FD(evsel, cpu, thread)); FD(evsel, cpu, thread) = -1; } It's not correct! This change is introduced by "475fb533fb7d" ("perf evsel: Fix buffer overflow while freeing events") This fix is to let xyarray__max_x() return max_x (ncpus) and let xyarry__max_y() return max_y (nthreads) Committer note: This was also fixed by Ravi Bangoria, who provided the same patch, noticing the problem with 'perf record': I see 'perf record -p ' crashes with following log: *** Error in `./perf': free(): invalid next size (normal): 0x000000000298b340 *** ======= Backtrace: ========= /lib/x86_64-linux-gnu/libc.so.6(+0x777e5)[0x7f7fd85c87e5] /lib/x86_64-linux-gnu/libc.so.6(+0x8037a)[0x7f7fd85d137a] /lib/x86_64-linux-gnu/libc.so.6(cfree+0x4c)[0x7f7fd85d553c] ./perf(perf_evsel__close+0xb4)[0x4b7614] ./perf(perf_evlist__delete+0x100)[0x4ab180] ./perf(cmd_record+0x1d9)[0x43a5a9] ./perf[0x49aa2f] ./perf(main+0x631)[0x427841] /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf0)[0x7f7fd8571830] ./perf(_start+0x29)[0x427a59] Signed-off-by: Jin Yao Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Kan Liang Cc: Peter Zijlstra Cc: Ravi Bangoria Fixes: d74be4767367 ("perf xyarray: Save max_x, max_y") Link: http://lkml.kernel.org/r/1508339478-26674-1-git-send-email-yao.jin@linux.intel.com Link: http://lkml.kernel.org/r/1508327446-15302-1-git-send-email-ravi.bangoria@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/xyarray.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/xyarray.h b/tools/perf/util/xyarray.h index 4ba726c90870..54af60462130 100644 --- a/tools/perf/util/xyarray.h +++ b/tools/perf/util/xyarray.h @@ -23,12 +23,12 @@ static inline void *xyarray__entry(struct xyarray *xy, int x, int y) static inline int xyarray__max_y(struct xyarray *xy) { - return xy->max_x; + return xy->max_y; } static inline int xyarray__max_x(struct xyarray *xy) { - return xy->max_y; + return xy->max_x; } #endif /* _PERF_XYARRAY_H_ */ -- cgit From 74f8e22c153f4464060a0c2e4cfd1d6e51af2109 Mon Sep 17 00:00:00 2001 From: Li Zhijian Date: Wed, 18 Oct 2017 16:34:09 +0800 Subject: perf test shell trace+probe_libc_inet_pton.sh: Be compatible with Debian/Ubuntu In debian/ubuntu, libc.so is located at a different place, /lib/x86_64-linux-gnu/libc-2.23.so, so it outputs like this when testing: PING ::1(::1) 56 data bytes 64 bytes from ::1: icmp_seq=1 ttl=64 time=0.040 ms --- ::1 ping statistics --- 1 packets transmitted, 1 received, 0% packet loss, time 0ms rtt min/avg/max/mdev = 0.040/0.040/0.040/0.000 ms 0.000 probe_libc:inet_pton:(7f0e2db741c0)) __GI___inet_pton (/lib/x86_64-linux-gnu/libc-2.23.so) getaddrinfo (/lib/x86_64-linux-gnu/libc-2.23.so) [0xffffa9d40f34ff4d] (/bin/ping) Fix up the libc path to make sure this test works in more OSes. Committer testing: When this test fails one can use 'perf test -v', i.e. in verbose mode, where it'll show the expected backtrace, so, after applying this test: On Fedora 26: # perf test -v ping 62: probe libc's inet_pton & backtrace it with ping : --- start --- test child forked, pid 23322 PING ::1(::1) 56 data bytes 64 bytes from ::1: icmp_seq=1 ttl=64 time=0.058 ms --- ::1 ping statistics --- 1 packets transmitted, 1 received, 0% packet loss, time 0ms rtt min/avg/max/mdev = 0.058/0.058/0.058/0.000 ms 0.000 probe_libc:inet_pton:(7fe344310d80)) __GI___inet_pton (/usr/lib64/libc-2.25.so) getaddrinfo (/usr/lib64/libc-2.25.so) _init (/usr/bin/ping) test child finished with 0 ---- end ---- probe libc's inet_pton & backtrace it with ping: Ok # Signed-off-by: Li Zhijian Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Kim Phillips Cc: Li Zhijian Cc: Peter Zijlstra Cc: Philip Li Link: http://lkml.kernel.org/r/1508315649-18836-1-git-send-email-lizhijian@cn.fujitsu.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/trace+probe_libc_inet_pton.sh | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'tools') diff --git a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh index 462fc755092e..7a84d73324e3 100755 --- a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh @@ -10,6 +10,9 @@ . $(dirname $0)/lib/probe.sh +ld=$(realpath /lib64/ld*.so.* | uniq) +libc=$(echo $ld | sed 's/ld/libc/g') + trace_libc_inet_pton_backtrace() { idx=0 expected[0]="PING.*bytes" @@ -18,8 +21,8 @@ trace_libc_inet_pton_backtrace() { expected[3]=".*packets transmitted.*" expected[4]="rtt min.*" expected[5]="[0-9]+\.[0-9]+[[:space:]]+probe_libc:inet_pton:\([[:xdigit:]]+\)" - expected[6]=".*inet_pton[[:space:]]\(/usr/lib.*/libc-[0-9]+\.[0-9]+\.so\)$" - expected[7]="getaddrinfo[[:space:]]\(/usr/lib.*/libc-[0-9]+\.[0-9]+\.so\)$" + expected[6]=".*inet_pton[[:space:]]\($libc\)$" + expected[7]="getaddrinfo[[:space:]]\($libc\)$" expected[8]=".*\(.*/bin/ping.*\)$" perf trace --no-syscalls -e probe_libc:inet_pton/max-stack=3/ ping -6 -c 1 ::1 2>&1 | grep -v ^$ | while read line ; do @@ -35,7 +38,7 @@ trace_libc_inet_pton_backtrace() { } skip_if_no_perf_probe && \ -perf probe -q /lib64/libc-*.so inet_pton && \ +perf probe -q $libc inet_pton && \ trace_libc_inet_pton_backtrace err=$? rm -f ${file} -- cgit