From 01766229533f9bdb1144a41b4345c8c7286da7b4 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Mon, 11 Jun 2018 09:31:52 +0200
Subject: [PATCH 01/21] perf record: Support s390 random socket_id assignment
On s390 the socket identifier assigned to a CPU identifier is random and
(depending on the configuration of the LPAR) may be higher than the CPU
identifier. This is currently not supported.
Fix this by allowing arbitrary socket identifiers being assigned to
CPU id.
Output before:
[root@p23lp27 perf]# ./perf report --header -I -v
...
socket_id number is too big.You may need to upgrade the perf tool.
Error:
The perf.data file has no samples!
# ========
# captured on : Tue May 29 09:29:57 2018
# header version : 1
...
# Core ID and Socket ID information is not available
...
[root@p23lp27 perf]#
Output after:
[root@p23lp27 perf]# ./perf report --header -I -v
...
Error:
The perf.data file has no samples!
# ========
# captured on : Tue May 29 09:29:57 2018
# header version : 1
...
# CPU 0: Core ID 0, Socket ID 6
# CPU 1: Core ID 1, Socket ID 3
# CPU 2: Core ID -1, Socket ID -1
...
[root@p23lp27 perf]#
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Link: http://lkml.kernel.org/r/20180611073153.15592-1-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/header.c | 10 +++++++++-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 540cd2dcd3e7..59fcc790c865 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2129,6 +2129,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
int cpu_nr = ff->ph->env.nr_cpus_avail;
u64 size = 0;
struct perf_header *ph = ff->ph;
+ bool do_core_id_test = true;
ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu));
if (!ph->env.cpu)
@@ -2183,6 +2184,13 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
return 0;
}
+ /* On s390 the socket_id number is not related to the numbers of cpus.
+ * The socket_id number might be higher than the numbers of cpus.
+ * This depends on the configuration.
+ */
+ if (ph->env.arch && !strncmp(ph->env.arch, "s390", 4))
+ do_core_id_test = false;
+
for (i = 0; i < (u32)cpu_nr; i++) {
if (do_read_u32(ff, &nr))
goto free_cpu;
@@ -2192,7 +2200,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused)
if (do_read_u32(ff, &nr))
goto free_cpu;
- if (nr != (u32)-1 && nr > (u32)cpu_nr) {
+ if (do_core_id_test && nr != (u32)-1 && nr > (u32)cpu_nr) {
pr_debug("socket_id number is too big."
"You may need to upgrade the perf tool.\n");
goto free_cpu;
From b930e62ecd362843002bdf84c2940439822af321 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Mon, 11 Jun 2018 09:31:53 +0200
Subject: [PATCH 02/21] perf test session topology: Fix test on s390
On s390 this test case fails because the socket identifiction numbers
assigned to the CPU are higher than the CPU identification numbers.
F/ix this by adding the platform architecture into the perf data header
flag information. This helps identifiing the test platform and handles
s390 specifics in process_cpu_topology().
Before:
[root@p23lp27 perf]# perf test -vvvvv -F 39
39: Session topology :
--- start ---
templ file: /tmp/perf-test-iUv755
socket_id number is too big.You may need to upgrade the perf tool.
---- end ----
Session topology: Skip
[root@p23lp27 perf]#
After:
[root@p23lp27 perf]# perf test -vvvvv -F 39
39: Session topology :
--- start ---
templ file: /tmp/perf-test-8X8VTs
CPU 0, core 0, socket 6
CPU 1, core 1, socket 3
---- end ----
Session topology: Ok
[root@p23lp27 perf]#
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Fixes: c84974ed9fb6 ("perf test: Add entry to test cpu topology")
Link: http://lkml.kernel.org/r/20180611073153.15592-2-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/tests/topology.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 40e30a26b23c..9497d02f69e6 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -45,6 +45,7 @@ static int session_write_header(char *path)
perf_header__set_feat(&session->header, HEADER_CPU_TOPOLOGY);
perf_header__set_feat(&session->header, HEADER_NRCPUS);
+ perf_header__set_feat(&session->header, HEADER_ARCH);
session->header.data_size += DATA_SIZE;
From 143c99f6ac6812d23254e80844d6e34be897d3e1 Mon Sep 17 00:00:00 2001
From: Sandipan Das <sandipan@linux.ibm.com>
Date: Mon, 11 Jun 2018 16:10:49 +0530
Subject: [PATCH 03/21] perf report powerpc: Fix crash if callchain is empty
For some cases, the callchain provided by the kernel may be empty. So,
the callchain ip filtering code will cause a crash if we do not check
whether the struct ip_callchain pointer is NULL before accessing any
members.
This can be observed on a powerpc64le system running Fedora 27 as shown
below.
# perf record -b -e cycles:u ls
Before:
# perf report --branch-history
perf: Segmentation fault
-------- backtrace --------
perf[0x1027615c]
linux-vdso64.so.1(__kernel_sigtramp_rt64+0x0)[0x7fff856304d8]
perf(arch_skip_callchain_idx+0x44)[0x10257c58]
perf[0x1017f2e4]
perf(thread__resolve_callchain+0x124)[0x1017ff5c]
perf(sample__resolve_callchain+0xf0)[0x10172788]
...
After:
# perf report --branch-history
Samples: 25 of event 'cycles:u', Event count (approx.): 2306870
Overhead Source:Line Symbol Shared Object
+ 11.60% _init+35736 [.] _init ls
+ 9.84% strcoll_l.c:137 [.] __strcoll_l libc-2.26.so
+ 9.16% memcpy.S:175 [.] __memcpy_power7 libc-2.26.so
+ 9.01% gconv_charset.h:54 [.] _nl_find_locale libc-2.26.so
+ 8.87% dl-addr.c:52 [.] _dl_addr libc-2.26.so
+ 8.83% _init+236 [.] _init ls
...
Reported-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Signed-off-by: Sandipan Das <sandipan@linux.ibm.com>
Acked-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/20180611104049.11048-1-sandipan@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/arch/powerpc/util/skip-callchain-idx.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index 3598b8b75d27..ef5d59a5742e 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -243,7 +243,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
u64 ip;
u64 skip_slot = -1;
- if (chain->nr < 3)
+ if (!chain || chain->nr < 3)
return skip_slot;
ip = chain->ips[2];
From 933ccf2002aaef1037cb676622a694f5390c3d59 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 11 Jun 2018 11:34:21 +0200
Subject: [PATCH 04/21] perf tests: Add event parsing error handling to parse
events test
Add missing error handling for parse_events calls in test_event function
that led to following segfault on s390:
running test 52 'intel_pt//u'
perf: Segmentation fault
...
/lib64/libc.so.6(vasprintf+0xe6) [0x3fffca3f106]
/lib64/libc.so.6(asprintf+0x46) [0x3fffca1aa96]
./perf(parse_events_add_pmu+0xb8) [0x80132088]
./perf(parse_events_parse+0xc62) [0x8019529a]
./perf(parse_events+0x98) [0x801341c0]
./perf(test__parse_events+0x48) [0x800cd140]
./perf(cmd_test+0x26a) [0x800bd44a]
test child interrupted
Adding the struct parse_events_error argument to parse_events call. Also
adding parse_events_print_error to get more details on the parsing
failures, like:
# perf test 6 -v
running test 52 'intel_pt//u'failed to parse event 'intel_pt//u', err 1, str 'Cannot find PMU `intel_pt'. Missing kernel support?'
event syntax error: 'intel_pt//u'
\___ Cannot find PMU `intel_pt'. Missing kernel support?
Committer note:
Use named initializers in the struct parse_events_error variable to
avoid breaking the build on centos5, 6 and others with a similar gcc:
cc1: warnings being treated as errors
tests/parse-events.c: In function 'test_event':
tests/parse-events.c:1696: error: missing initializer
tests/parse-events.c:1696: error: (near initialization for 'err.str')
Reported-by: Kim Phillips <kim.phillips@arm.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Kim Phillips <kim.phillips@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Link: http://lkml.kernel.org/r/20180611093422.1005-1-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/tests/parse-events.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 7d4077068454..9751e7563a45 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1686,6 +1686,7 @@ static struct terms_test test__terms[] = {
static int test_event(struct evlist_test *e)
{
+ struct parse_events_error err = { .idx = 0, };
struct perf_evlist *evlist;
int ret;
@@ -1693,10 +1694,11 @@ static int test_event(struct evlist_test *e)
if (evlist == NULL)
return -ENOMEM;
- ret = parse_events(evlist, e->name, NULL);
+ ret = parse_events(evlist, e->name, &err);
if (ret) {
- pr_debug("failed to parse event '%s', err %d\n",
- e->name, ret);
+ pr_debug("failed to parse event '%s', err %d, str '%s'\n",
+ e->name, ret, err.str);
+ parse_events_print_error(&err, e->name);
} else {
ret = e->check(evlist);
}
From 16ddcfbf7f3d07aa781e26b39f2c28636a4ed2fd Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 11 Jun 2018 11:34:22 +0200
Subject: [PATCH 05/21] perf tests: Add valid callback for parse-events test
Adding optional 'valid' callback for events tests in parse-events
object, so we don't try to parse PMUs, which are not supported.
Following line is displayed for skipped test:
running test 52 'intel_pt//u'... SKIP
Committer note:
Use named initializers in the struct evlist_test variable to avoid
breaking the build on centos:5, 6 and others with a similar gcc:
cc1: warnings being treated as errors
tests/parse-events.c: In function 'test_pmu_events':
tests/parse-events.c:1817: error: missing initializer
tests/parse-events.c:1817: error: (near initialization for 'e.type')
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Kim Phillips <kim.phillips@arm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Link: http://lkml.kernel.org/r/20180611093422.1005-2-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/tests/parse-events.c | 17 +++++++++++++++--
1 file changed, 15 insertions(+), 2 deletions(-)
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 9751e7563a45..61211918bfba 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1309,6 +1309,11 @@ static int test__checkevent_config_cache(struct perf_evlist *evlist)
return 0;
}
+static bool test__intel_pt_valid(void)
+{
+ return !!perf_pmu__find("intel_pt");
+}
+
static int test__intel_pt(struct perf_evlist *evlist)
{
struct perf_evsel *evsel = perf_evlist__first(evlist);
@@ -1375,6 +1380,7 @@ struct evlist_test {
const char *name;
__u32 type;
const int id;
+ bool (*valid)(void);
int (*check)(struct perf_evlist *evlist);
};
@@ -1648,6 +1654,7 @@ static struct evlist_test test__events[] = {
},
{
.name = "intel_pt//u",
+ .valid = test__intel_pt_valid,
.check = test__intel_pt,
.id = 52,
},
@@ -1690,6 +1697,11 @@ static int test_event(struct evlist_test *e)
struct perf_evlist *evlist;
int ret;
+ if (e->valid && !e->valid()) {
+ pr_debug("... SKIP");
+ return 0;
+ }
+
evlist = perf_evlist__new();
if (evlist == NULL)
return -ENOMEM;
@@ -1716,10 +1728,11 @@ static int test_events(struct evlist_test *events, unsigned cnt)
for (i = 0; i < cnt; i++) {
struct evlist_test *e = &events[i];
- pr_debug("running test %d '%s'\n", e->id, e->name);
+ pr_debug("running test %d '%s'", e->id, e->name);
ret1 = test_event(e);
if (ret1)
ret2 = ret1;
+ pr_debug("\n");
}
return ret2;
@@ -1801,7 +1814,7 @@ static int test_pmu_events(void)
}
while (!ret && (ent = readdir(dir))) {
- struct evlist_test e;
+ struct evlist_test e = { .id = 0, };
char name[2 * NAME_MAX + 1 + 12 + 3];
/* Names containing . are special and cannot be used directly */
From 621a5a327c1e36ffd7bb567f44a559f64f76358f Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Thu, 7 Jun 2018 14:30:02 +0300
Subject: [PATCH 06/21] perf intel-pt: Fix packet decoding of CYC packets
Use a 64-bit type so that the cycle count is not limited to 32-bits.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/1528371002-8862-1-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
index ba4c9dd18643..d426761a549d 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
@@ -366,7 +366,7 @@ static int intel_pt_get_cyc(unsigned int byte, const unsigned char *buf,
if (len < offs)
return INTEL_PT_NEED_MORE_BYTES;
byte = buf[offs++];
- payload |= (byte >> 1) << shift;
+ payload |= ((uint64_t)byte >> 1) << shift;
}
packet->type = INTEL_PT_CYC;
From 7b818dc57230bf050bbc4218cd4df8ec59b9945d Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 15 Jun 2018 11:33:35 -0300
Subject: [PATCH 07/21] tools headers uapi: Synchronize drm/drm.h
To pick up the new ioctls added in these csets:
7595bda2fb43 ("drm: Add DRM client cap for aspect-ratio")
The DRM caps are not yet being decoded in 'perf trace', so this sync
doesn't incur in any change in behaviour in any tools, just silencing
this tools/perf/ build warning:
Warning: Kernel ABI header at 'tools/include/uapi/drm/drm.h' differs from latest version at 'include/uapi/drm/drm.h'
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-atwz0arwanq1npu8pptwkoxt@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/include/uapi/drm/drm.h | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 6fdff5945c8a..9c660e1688ab 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -680,6 +680,13 @@ struct drm_get_cap {
*/
#define DRM_CLIENT_CAP_ATOMIC 3
+/**
+ * DRM_CLIENT_CAP_ASPECT_RATIO
+ *
+ * If set to 1, the DRM core will provide aspect ratio information in modes.
+ */
+#define DRM_CLIENT_CAP_ASPECT_RATIO 4
+
/** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
struct drm_set_client_cap {
__u64 capability;
From b1494ec029af6d6ea189cbc96ad66463f8df3579 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 15 Jun 2018 11:48:43 -0300
Subject: [PATCH 08/21] perf tools: Update x86's syscall_64.tbl, adding
'io_pgetevents' and 'rseq'
This updates the tools/perf/ copy of the system call table for x86 which makes
'perf trace' become aware of the new 'io_pgetevents' and 'rseq' syscalls, no
matter in which system it gets built, i.e. older systems where the syscalls are
not available in the running kernel (via tracefs) or in the system headers will
still be aware of these syscalls/.
These are the csets introducing the source drift:
05c17cedf85b ("x86: Wire up restartable sequence system call")
7a074e96dee6 ("aio: implement io_pgetevents")
This results in this build time change:
$ diff -u /tmp/build/perf/arch/x86/include/generated/asm/syscalls_64.c.old /tmp/build/perf/arch/x86/include/generated/asm/syscalls_64.c
--- /tmp/build/perf/arch/x86/include/generated/asm/syscalls_64.c.old 2018-06-15 11:48:17.648948094 -0300
+++ /tmp/build/perf/arch/x86/include/generated/asm/syscalls_64.c 2018-06-15 11:48:22.133942480 -0300
@@ -332,5 +332,7 @@
[330] = "pkey_alloc",
[331] = "pkey_free",
[332] = "statx",
+ [333] = "io_pgetevents",
+ [334] = "rseq",
};
-#define SYSCALLTBL_x86_64_MAX_ID 332
+#define SYSCALLTBL_x86_64_MAX_ID 334
$
This silences the following tools/perf/ build warning:
Warning: Kernel ABI header at 'tools/perf/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl'
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-tfvyz51sabuzemrszbrhzxni@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/arch/x86/entry/syscalls/syscall_64.tbl | 2 ++
1 file changed, 2 insertions(+)
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 4dfe42666d0c..f0b1709a5ffb 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -341,6 +341,8 @@
330 common pkey_alloc __x64_sys_pkey_alloc
331 common pkey_free __x64_sys_pkey_free
332 common statx __x64_sys_statx
+333 common io_pgetevents __x64_sys_io_pgetevents
+334 common rseq __x64_sys_rseq
#
# x32-specific system call numbers start at 512 to avoid cache impact
From 801f5e1ac783df9fafff8899ef2d5511bd4dbdcb Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 15 Jun 2018 12:04:32 -0300
Subject: [PATCH 09/21] tools include powerpc: Update
arch/powerpc/include/uapi/asm/unistd.h copy to get 'rseq' syscall
This updates the tools/perf/ copy of the powerpc file used to generate
the syscall table file used to make 'perf trace' become aware of the new
'rseq' syscall, no matter in which system it gets built, i.e. older
systems where the syscalls are not available in the running kernel (via
tracefs) or in the system headers will still be aware of these
syscalls/.
From this commit:
bb862b021d75 ("powerpc: Wire up restartable sequences system call")
Silencing this tools/perf build warning:
Warning: Kernel ABI header at 'tools/arch/powerpc/include/uapi/asm/unistd.h' differs from latest version at 'arch/powerpc/include/uapi/asm/unistd.h'
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-adtgz6u3apd76tghiu9w0k19@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/arch/powerpc/include/uapi/asm/unistd.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/arch/powerpc/include/uapi/asm/unistd.h b/tools/arch/powerpc/include/uapi/asm/unistd.h
index 389c36fd8299..ac5ba55066dd 100644
--- a/tools/arch/powerpc/include/uapi/asm/unistd.h
+++ b/tools/arch/powerpc/include/uapi/asm/unistd.h
@@ -398,5 +398,6 @@
#define __NR_pkey_alloc 384
#define __NR_pkey_free 385
#define __NR_pkey_mprotect 386
+#define __NR_rseq 387
#endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
From bb9a33cb8a807e5ae9906563f5c1533904651b8b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 15 Jun 2018 16:46:57 -0300
Subject: [PATCH 10/21] tools include uapi: Update if_link.h to pick
IFLA_{BRPORT_ISOLATED,VXLAN_TTL_INHERIT}
The IFLA_BRPORT_ISOLATED and IFLA_VXLAN_TTL_INHERIT defines were added in:
7d850abd5f4e ("net: bridge: add support for port isolation")
72f6d71e491e ("vxlan: add ttl inherit support")
Pick them, silencing this build warning:
Warning: Kernel ABI header at 'tools/include/uapi/linux/if_link.h' differs from latest version at 'include/uapi/linux/if_link.h'
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Eric Leblond <eric@regit.org>
Cc: Hangbin Liu <liuhangbin@gmail.com>
Cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Link: https://lkml.kernel.org/n/tip-ezi5u0mmdqm0wfm0y2y8176r@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/include/uapi/linux/if_link.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 68699f654118..cf01b6824244 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -333,6 +333,7 @@ enum {
IFLA_BRPORT_BCAST_FLOOD,
IFLA_BRPORT_GROUP_FWD_MASK,
IFLA_BRPORT_NEIGH_SUPPRESS,
+ IFLA_BRPORT_ISOLATED,
__IFLA_BRPORT_MAX
};
#define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -516,6 +517,7 @@ enum {
IFLA_VXLAN_COLLECT_METADATA,
IFLA_VXLAN_LABEL,
IFLA_VXLAN_GPE,
+ IFLA_VXLAN_TTL_INHERIT,
__IFLA_VXLAN_MAX
};
#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)
From f568b472815fd6c34fe4cc30dde4572ee300d6c4 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 15 Jun 2018 16:55:32 -0300
Subject: [PATCH 11/21] tools include uapi: Synchronize bpf.h with the kernel
To pick the rename in:
bd3a08aaa9a3 ("bpf: flowlabel in bpf_fib_lookup should be flowinfo")
Silencing this build warning:
Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-zd1sgtbybtjrrt7bqdybu0s0@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/include/uapi/linux/bpf.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e0b06784f227..59b19b6a40d7 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2630,7 +2630,7 @@ struct bpf_fib_lookup {
union {
/* inputs to lookup */
__u8 tos; /* AF_INET */
- __be32 flowlabel; /* AF_INET6 */
+ __be32 flowinfo; /* AF_INET6, flow_label + priority */
/* output: metric of fib result (IPv4/IPv6 only) */
__u32 rt_metric;
From c6555c14572aeadf4fe2819abd971c4e7608b926 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Sat, 16 Jun 2018 10:47:39 -0700
Subject: [PATCH 12/21] perf tools: Fix a clang 7.0 compilation error
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Arnaldo reported the perf build failure with latest llvm/clang compiler
(7.0).
$ make LIBCLANGLLVM=1 -C tools/perf/
<SNIP>
CC /tmp/tmp.t53Qo38zci/tests/kmod-path.o
util/c++/clang.cpp: In function ‘std::unique_ptr<llvm::SmallVectorImpl<char> >
perf::getBPFObjectFromModule(llvm::Module*)’:
util/c++/clang.cpp:150:43: error: no matching function for call to
‘llvm::TargetMachine::addPassesToEmitFile(llvm::legacy::PassManager&,
llvm::raw_svector_ostream&, llvm::TargetMachine::CodeGenFileType)’
TargetMachine::CGFT_ObjectFile)) {
^
In file included from util/c++/clang.cpp:25:0:
/usr/local/include/llvm/Target/TargetMachine.h:254:16: note: candidate:
virtual bool llvm::TargetMachine::addPassesToEmitFile(
llvm::legacy::PassManagerBase&, llvm::raw_pwrite_stream&,
llvm::raw_pwrite_stream*, llvm::TargetMachine::CodeGenFileType, bool,
llvm::MachineModuleInfo*)
virtual bool addPassesToEmitFile(PassManagerBase &, raw_pwrite_stream &,
^~~~~~~~~~~~~~~~~~~
/usr/local/include/llvm/Target/TargetMachine.h:254:16: note:
candidate expects 6 arguments, 3 provided
mv: cannot stat '/tmp/tmp.t53Qo38zci/util/c++/.clang.o.tmp': No such file or directory
make[7]: *** [/home/acme/git/perf/tools/build/Makefile.build:101:
/tmp/tmp.t53Qo38zci/util/c++/clang.o] Error 1
make[6]: *** [/home/acme/git/perf/tools/build/Makefile.build:139: c++] Error 2
make[5]: *** [/home/acme/git/perf/tools/build/Makefile.build:139: util] Error 2
make[5]: *** Waiting for unfinished jobs....
CC /tmp/tmp.t53Qo38zci/tests/thread-map.o
The function addPassesToEmitFile signature changed in llvm 7.0 and such
a change caused the failure. This patch fixed the issue with using
proper function signatures under different compiler versions.
Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexei Starovoitov <ast@fb.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/20180616174739.1076733-1-yhs@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/c++/clang.cpp | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp
index bf31ceab33bd..89512504551b 100644
--- a/tools/perf/util/c++/clang.cpp
+++ b/tools/perf/util/c++/clang.cpp
@@ -146,8 +146,15 @@ getBPFObjectFromModule(llvm::Module *Module)
raw_svector_ostream ostream(*Buffer);
legacy::PassManager PM;
- if (TargetMachine->addPassesToEmitFile(PM, ostream,
- TargetMachine::CGFT_ObjectFile)) {
+ bool NotAdded;
+#if CLANG_VERSION_MAJOR < 7
+ NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream,
+ TargetMachine::CGFT_ObjectFile);
+#else
+ NotAdded = TargetMachine->addPassesToEmitFile(PM, ostream, nullptr,
+ TargetMachine::CGFT_ObjectFile);
+#endif
+ if (NotAdded) {
llvm::errs() << "TargetMachine can't emit a file of this type\n";
return std::unique_ptr<llvm::SmallVectorImpl<char>>(nullptr);;
}
From ea23ac73085743a4f1682d6605fe019577c82e1e Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Fri, 15 Jun 2018 12:11:03 +0200
Subject: [PATCH 13/21] perf alias: Remove trailing newline when reading sysfs
files
Remove a trailing newline when reading sysfs file contents such as
/sys/devices/cpum_cf/events/TX_NC_TEND. This shows when verbose option
-v is used.
Output before:
tx_nc_tend -> 'cpum_cf'/'event=0x008d
'/
Output after:
tx_nc_tend -> 'cpum_cf'/'event=0x8d'/
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Link: http://lkml.kernel.org/r/20180615101105.47047-1-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/pmu.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index d2fb597c9a8c..2738fc8d200d 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -303,6 +303,9 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
buf[ret] = 0;
+ /* Remove trailing newline from sysfs file */
+ rtrim(buf);
+
return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL,
NULL, NULL, NULL);
}
From 0c24d6fb7bd3578e5b9e4972d01bbe3d087ded33 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Fri, 15 Jun 2018 12:11:04 +0200
Subject: [PATCH 14/21] perf alias: Rebuild alias expression string to make it
comparable
PMU alias definitions in sysfs files may have spaces, newlines and
numbers with leading zeroes. Some alias definitions may also appear in
JSON files without spaces, etc.
Scan alias definitions and remove leading zeroes, spaces, newlines, etc
and rebuild string to make alias->str member comparable.
s390 for example has terms specified as event=0x0091 (read from files
../<PMU>/events/<FILE> and terms specified as event=0x91 (read from JSON
files).
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Link: http://lkml.kernel.org/r/20180615101105.47047-2-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/pmu.c | 25 ++++++++++++++++++++++++-
1 file changed, 24 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 2738fc8d200d..f321ce97d9ec 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -241,9 +241,11 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
char *metric_expr,
char *metric_name)
{
+ struct parse_events_term *term;
struct perf_pmu_alias *alias;
int ret;
int num;
+ char newval[256];
alias = malloc(sizeof(*alias));
if (!alias)
@@ -262,6 +264,27 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
return ret;
}
+ /* Scan event and remove leading zeroes, spaces, newlines, some
+ * platforms have terms specified as
+ * event=0x0091 (read from files ../<PMU>/events/<FILE>
+ * and terms specified as event=0x91 (read from JSON files).
+ *
+ * Rebuild string to make alias->str member comparable.
+ */
+ memset(newval, 0, sizeof(newval));
+ ret = 0;
+ list_for_each_entry(term, &alias->terms, list) {
+ if (ret)
+ ret += scnprintf(newval + ret, sizeof(newval) - ret,
+ ",");
+ if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM)
+ ret += scnprintf(newval + ret, sizeof(newval) - ret,
+ "%s=%#x", term->config, term->val.num);
+ else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR)
+ ret += scnprintf(newval + ret, sizeof(newval) - ret,
+ "%s=%s", term->config, term->val.str);
+ }
+
alias->name = strdup(name);
if (dir) {
/*
@@ -285,7 +308,7 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
snprintf(alias->unit, sizeof(alias->unit), "%s", unit);
}
alias->per_pkg = perpkg && sscanf(perpkg, "%d", &num) == 1 && num == 1;
- alias->str = strdup(val);
+ alias->str = strdup(newval);
list_add_tail(&alias->list, list);
From 6dde6429c5ff5b38d6d40a14a6ee105117e6364d Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Fri, 15 Jun 2018 12:11:05 +0200
Subject: [PATCH 15/21] perf stat: Remove duplicate event counting
'perf stat' shows a mismatch in perf stat regarding counter names on
s390:
Run command:
[root@s35lp76 perf]# ./perf stat -e tx_nc_tend -v --
~/mytesttx 1 >/tmp/111
tx_nc_tend: 1 573146 573146
tx_nc_tend: 1 573146 573146
Performance counter stats for '/root/mytesttx 1':
3 tx_nc_tend
0.001037252 seconds time elapsed
[root@s35lp76 perf]#
shows transaction counter tx_nc_tend with value 3 but it was triggered
only once as seen by the output of mytesttx.
When looking up the event name tx_nc_tend the following function
sequence is called:
parse_events_multi_pmu_add()
+--> perf_pmu__scan() being called with NULL argument
+--> pmu_read_sysfs() scans directory ../devices/ for
all PMUs
+--> perf_pmu__find() tries to find a PMU in the
global pmu list.
+--> pmu_lookup() called to read all file
entries when not in global
list.
pmu_lookup() causes the issue. It calls
+---> pmu_aliases() to read all the entries in the PMU directory.
On s390 this is named
/sys/devices/cpum_cf/events.
+--> pmu_aliases_parse() reads all files and creates an
alias for each file name.
So we end up with first entry created by
reading the sysfs file
[root@s35lp76 perf]# cat /sys/devices/cpum_cf
/events/TX_NC_TEND
event=0x008d
[root@s35lp76 perf]#
Debug output shows this entry
tx_nc_tend -> 'cpum_cf'/'event=0x008d
'/
After all files in this directory have been
read and aliases created this function is called:
+--> pmu_add_cpu_aliases()
This function looks up the CPU tables
created by the json files.
With json files for s390 now available all
the aliases are added to
the PMU alias list a second time.
The second entry is added by
reading the json file converted by jevent
resulting in file pmu-events/pmu-events.c:
{
.name = "tx_nc_tend",
.event = "event=0x8d",
.desc = "Unit: cpum_cf Completed TEND \
instructions \
in non-constrained TX mode",
.topic = "extended",
.long_desc = "A TEND instruction has \
completed in a \
non-constrained \
transactional-execution mode",
.pmu = "cpum_cf",
},
Debug output shows this entry
tx_nc_tend -> 'cpum_cf'/'event=0x8d'/
Function pmu_aliases_parse() and pmu_add_cpu_aliases() both use
__perf_pmu__new_alias() to add an alias to the PMU alias list. There is
no check if an alias already exist
So we end up with 2 entries for tx_nc_tend in the PMU alias list.
Having set up the PMU alias list for this PMU now
parse_events_multi_add_pmu() reads the complete alias list and adds each
alias with parse_events_add_pmu() to the global perfev_list. This
causes the alias to be added multiple times to the event list.
Fix this by making __perf_pmu__new_alias() to merge alias definitions if
an alias is already on the alias list. Also print a debug message when
the alias has mismatches in some fields.
Output before:
[root@s35lp76 perf]# ./perf stat -e tx_nc_tend -v \
-- ~/mytesttx 1 >/tmp/111
tx_nc_tend: 1 551446 551446
Performance counter stats for '/root/mytesttx 1':
3 tx_nc_tend
0.000961134 seconds time elapsed
[root@s35lp76 perf]#
Output after:
[root@s35lp76 perf]# ./perf stat -e tx_nc_tend -v \
-- ~/mytesttx 1 >/tmp/111
tx_nc_tend: 1 551446 551446
Performance counter stats for '/root/mytesttx 1':
1 tx_nc_tend
0.000961134 seconds time elapsed
[root@s35lp76 perf]#
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Link: http://lkml.kernel.org/r/20180615101105.47047-3-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/pmu.c | 71 ++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 70 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index f321ce97d9ec..3ba6a1742f91 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -234,6 +234,74 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
return 0;
}
+static void perf_pmu_assign_str(char *name, const char *field, char **old_str,
+ char **new_str)
+{
+ if (!*old_str)
+ goto set_new;
+
+ if (*new_str) { /* Have new string, check with old */
+ if (strcasecmp(*old_str, *new_str))
+ pr_debug("alias %s differs in field '%s'\n",
+ name, field);
+ zfree(old_str);
+ } else /* Nothing new --> keep old string */
+ return;
+set_new:
+ *old_str = *new_str;
+ *new_str = NULL;
+}
+
+static void perf_pmu_update_alias(struct perf_pmu_alias *old,
+ struct perf_pmu_alias *newalias)
+{
+ perf_pmu_assign_str(old->name, "desc", &old->desc, &newalias->desc);
+ perf_pmu_assign_str(old->name, "long_desc", &old->long_desc,
+ &newalias->long_desc);
+ perf_pmu_assign_str(old->name, "topic", &old->topic, &newalias->topic);
+ perf_pmu_assign_str(old->name, "metric_expr", &old->metric_expr,
+ &newalias->metric_expr);
+ perf_pmu_assign_str(old->name, "metric_name", &old->metric_name,
+ &newalias->metric_name);
+ perf_pmu_assign_str(old->name, "value", &old->str, &newalias->str);
+ old->scale = newalias->scale;
+ old->per_pkg = newalias->per_pkg;
+ old->snapshot = newalias->snapshot;
+ memcpy(old->unit, newalias->unit, sizeof(old->unit));
+}
+
+/* Delete an alias entry. */
+static void perf_pmu_free_alias(struct perf_pmu_alias *newalias)
+{
+ zfree(&newalias->name);
+ zfree(&newalias->desc);
+ zfree(&newalias->long_desc);
+ zfree(&newalias->topic);
+ zfree(&newalias->str);
+ zfree(&newalias->metric_expr);
+ zfree(&newalias->metric_name);
+ parse_events_terms__purge(&newalias->terms);
+ free(newalias);
+}
+
+/* Merge an alias, search in alias list. If this name is already
+ * present merge both of them to combine all information.
+ */
+static bool perf_pmu_merge_alias(struct perf_pmu_alias *newalias,
+ struct list_head *alist)
+{
+ struct perf_pmu_alias *a;
+
+ list_for_each_entry(a, alist, list) {
+ if (!strcasecmp(newalias->name, a->name)) {
+ perf_pmu_update_alias(a, newalias);
+ perf_pmu_free_alias(newalias);
+ return true;
+ }
+ }
+ return false;
+}
+
static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
char *desc, char *val,
char *long_desc, char *topic,
@@ -310,7 +378,8 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
alias->per_pkg = perpkg && sscanf(perpkg, "%d", &num) == 1 && num == 1;
alias->str = strdup(newval);
- list_add_tail(&alias->list, list);
+ if (!perf_pmu_merge_alias(alias, list))
+ list_add_tail(&alias->list, list);
return 0;
}
From 983107072be1a39cbde67d45cb0059138190e015 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 20 Jun 2018 11:40:36 +0200
Subject: [PATCH 16/21] perf bench: Fix numa report output code
Currently we can hit following assert when running numa bench:
$ perf bench numa mem -p 3 -t 1 -P 512 -s 100 -zZ0cm --thp 1
perf: bench/numa.c:1577: __bench_numa: Assertion `!(!(((wait_stat) & 0x7f) == 0))' failed.
The assertion is correct, because we hit the SIGFPE in following line:
Thread 2.2 "thread 0/0" received signal SIGFPE, Arithmetic exception.
[Switching to Thread 0x7fffd28c6700 (LWP 11750)]
0x000.. in worker_thread (__tdata=0x7.. ) at bench/numa.c:1257
1257 td->speed_gbs = bytes_done / (td->runtime_ns / NSEC_PER_SEC) / 1e9;
We don't check if the runtime is actually bigger than 1 second,
and thus this might end up with zero division within FPU.
Adding the check to prevent this.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180620094036.17278-1-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/bench/numa.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 63eb49082774..44195514b19e 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -1098,7 +1098,7 @@ static void *worker_thread(void *__tdata)
u8 *global_data;
u8 *process_data;
u8 *thread_data;
- u64 bytes_done;
+ u64 bytes_done, secs;
long work_done;
u32 l;
struct rusage rusage;
@@ -1254,7 +1254,8 @@ static void *worker_thread(void *__tdata)
timersub(&stop, &start0, &diff);
td->runtime_ns = diff.tv_sec * NSEC_PER_SEC;
td->runtime_ns += diff.tv_usec * NSEC_PER_USEC;
- td->speed_gbs = bytes_done / (td->runtime_ns / NSEC_PER_SEC) / 1e9;
+ secs = td->runtime_ns / NSEC_PER_SEC;
+ td->speed_gbs = secs ? bytes_done / secs / 1e9 : 0;
getrusage(RUSAGE_THREAD, &rusage);
td->system_time_ns = rusage.ru_stime.tv_sec * NSEC_PER_SEC;
From 10e9cec905f96fdf47f398be70726e2931b376cd Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Date: Mon, 25 Jun 2018 18:12:18 +0530
Subject: [PATCH 17/21] perf script: Add missing output fields in a hint
A few fields are missing in a perf script -F hint. Add them.
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: David Carrillo-Cisneros <davidcc@google.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/20180625124220.6434-2-ravi.bangoria@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-script.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index a31d7082188e..f3fefbcc4503 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -3125,8 +3125,9 @@ int cmd_script(int argc, const char **argv)
"+field to add and -field to remove."
"Valid types: hw,sw,trace,raw,synth. "
"Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
- "addr,symoff,period,iregs,uregs,brstack,brstacksym,flags,"
- "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr",
+ "addr,symoff,srcline,period,iregs,uregs,brstack,"
+ "brstacksym,flags,bpf-output,brstackinsn,brstackoff,"
+ "callindent,insn,insnlen,synth,phys_addr,metric,misc",
parse_output_fields),
OPT_BOOLEAN('a', "all-cpus", &system_wide,
"system-wide collection from all CPUs"),
From a3af66f51bd0bca72881ead4bf2bd19cb366582b Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Date: Mon, 25 Jun 2018 18:12:19 +0530
Subject: [PATCH 18/21] perf script: Fix crash because of missing evsel->priv
'perf script' in piped mode is crashing because evsel->priv is not set
properly. Fix it.
Before:
# perf record -o - -- ls | perf script
<SNIP 'ls' output>
Segmentation fault (core dumped)
#
After:
# perf record -o - -- ls | perf script
<SNIP 'ls' output>
ls 2282 1031.731974: 250000 cpu-clock:uhH: 7effe4b3d29e
ls 2282 1031.732222: 250000 cpu-clock:uhH: 7effe4b3a650
#
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: David Carrillo-Cisneros <davidcc@google.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Fixes: a14390fde64e ("perf script: Allow creating per-event dump files")
Link: http://lkml.kernel.org/r/20180625124220.6434-3-ravi.bangoria@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-script.c | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index f3fefbcc4503..ad2ac1300420 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1834,6 +1834,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
struct perf_evlist *evlist;
struct perf_evsel *evsel, *pos;
int err;
+ static struct perf_evsel_script *es;
err = perf_event__process_attr(tool, event, pevlist);
if (err)
@@ -1842,6 +1843,19 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
evlist = *pevlist;
evsel = perf_evlist__last(*pevlist);
+ if (!evsel->priv) {
+ if (scr->per_event_dump) {
+ evsel->priv = perf_evsel_script__new(evsel,
+ scr->session->data);
+ } else {
+ es = zalloc(sizeof(*es));
+ if (!es)
+ return -ENOMEM;
+ es->fp = stdout;
+ evsel->priv = es;
+ }
+ }
+
if (evsel->attr.type >= PERF_TYPE_MAX &&
evsel->attr.type != PERF_TYPE_SYNTH)
return 0;
From 92ead7ee30c80f8852d28735cbcb9d79bc85f715 Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Date: Mon, 25 Jun 2018 18:12:20 +0530
Subject: [PATCH 19/21] perf tools: Fix crash caused by accessing
feat_ops[HEADER_LAST_FEATURE]
perf_event__process_feature() accesses feat_ops[HEADER_LAST_FEATURE]
which is not defined and thus perf is crashing. HEADER_LAST_FEATURE is
used as an end marker for the perf report but it's unused for perf
script/annotate. Ignore HEADER_LAST_FEATURE for perf script/annotate,
just like it is done in 'perf report'.
Before:
# perf record -o - ls | perf script
<SNIP 'ls' output>
Segmentation fault (core dumped)
#
After:
# perf record -o - ls | perf script
<SNIP 'ls' output>
Segmentation fault (core dumped)
ls 7031 4392.099856: 250000 cpu-clock:uhH: 7f5e0ce7cd60
ls 7031 4392.100355: 250000 cpu-clock:uhH: 7f5e0c706ef7
#
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: David Carrillo-Cisneros <davidcc@google.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Fixes: 57b5de463925 ("perf report: Support forced leader feature in pipe mode")
Link: http://lkml.kernel.org/r/20180625124220.6434-4-ravi.bangoria@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-annotate.c | 11 ++++++++++-
tools/perf/builtin-report.c | 3 ++-
tools/perf/builtin-script.c | 11 ++++++++++-
tools/perf/util/header.c | 2 +-
4 files changed, 23 insertions(+), 4 deletions(-)
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 5eb22cc56363..8180319285af 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -283,6 +283,15 @@ out_put:
return ret;
}
+static int process_feature_event(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session)
+{
+ if (event->feat.feat_id < HEADER_LAST_FEATURE)
+ return perf_event__process_feature(tool, event, session);
+ return 0;
+}
+
static int hist_entry__tty_annotate(struct hist_entry *he,
struct perf_evsel *evsel,
struct perf_annotate *ann)
@@ -471,7 +480,7 @@ int cmd_annotate(int argc, const char **argv)
.attr = perf_event__process_attr,
.build_id = perf_event__process_build_id,
.tracing_data = perf_event__process_tracing_data,
- .feature = perf_event__process_feature,
+ .feature = process_feature_event,
.ordered_events = true,
.ordering_requires_timestamps = true,
},
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index cdb5b6949832..c04dc7b53797 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -217,7 +217,8 @@ static int process_feature_event(struct perf_tool *tool,
}
/*
- * All features are received, we can force the
+ * (feat_id = HEADER_LAST_FEATURE) is the end marker which
+ * means all features are received, now we can force the
* group if needed.
*/
setup_forced_leader(rep, session->evlist);
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index ad2ac1300420..568ddfac3213 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -3044,6 +3044,15 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
return set_maps(script);
}
+static int process_feature_event(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session)
+{
+ if (event->feat.feat_id < HEADER_LAST_FEATURE)
+ return perf_event__process_feature(tool, event, session);
+ return 0;
+}
+
#ifdef HAVE_AUXTRACE_SUPPORT
static int perf_script__process_auxtrace_info(struct perf_tool *tool,
union perf_event *event,
@@ -3088,7 +3097,7 @@ int cmd_script(int argc, const char **argv)
.attr = process_attr,
.event_update = perf_event__process_event_update,
.tracing_data = perf_event__process_tracing_data,
- .feature = perf_event__process_feature,
+ .feature = process_feature_event,
.build_id = perf_event__process_build_id,
.id_index = perf_event__process_id_index,
.auxtrace_info = perf_script__process_auxtrace_info,
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 59fcc790c865..653ff65aa2c3 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3464,7 +3464,7 @@ int perf_event__process_feature(struct perf_tool *tool,
pr_warning("invalid record type %d in pipe-mode\n", type);
return 0;
}
- if (feat == HEADER_RESERVED || feat > HEADER_LAST_FEATURE) {
+ if (feat == HEADER_RESERVED || feat >= HEADER_LAST_FEATURE) {
pr_warning("invalid record type %d in pipe-mode\n", type);
return -1;
}
From 32fdbd90cc03f01d452138bab4d8a120873d6acf Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Tue, 26 Jun 2018 08:43:14 +0200
Subject: [PATCH 20/21] tools/headers: Pick up latest kernel ABIs
Sync KVM ABI additions and x86 CPU features additions - neither of which
has any impact on the tooling build.
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
tools/arch/arm/include/uapi/asm/kvm.h | 1 +
tools/arch/arm64/include/uapi/asm/kvm.h | 1 +
tools/arch/powerpc/include/uapi/asm/kvm.h | 1 +
tools/arch/x86/include/asm/cpufeatures.h | 2 ++
tools/include/uapi/linux/kvm.h | 1 +
5 files changed, 6 insertions(+)
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index caae4843cb70..16e006f708ca 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -91,6 +91,7 @@ struct kvm_regs {
#define KVM_VGIC_V3_ADDR_TYPE_DIST 2
#define KVM_VGIC_V3_ADDR_TYPE_REDIST 3
#define KVM_VGIC_ITS_ADDR_TYPE 4
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION 5
#define KVM_VGIC_V3_DIST_SIZE SZ_64K
#define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K)
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 04b3256f8e6d..4e76630dd655 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -91,6 +91,7 @@ struct kvm_regs {
#define KVM_VGIC_V3_ADDR_TYPE_DIST 2
#define KVM_VGIC_V3_ADDR_TYPE_REDIST 3
#define KVM_VGIC_ITS_ADDR_TYPE 4
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION 5
#define KVM_VGIC_V3_DIST_SIZE SZ_64K
#define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K)
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 833ed9a16adf..1b32b56a03d3 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -633,6 +633,7 @@ struct kvm_ppc_cpu_char {
#define KVM_REG_PPC_PSSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
#define KVM_REG_PPC_DEC_EXPIRY (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe)
+#define KVM_REG_PPC_ONLINE (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbf)
/* Transactional Memory checkpointed state:
* This is all GPRs, all VSX regs and a subset of SPRs
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index fb00a2fca990..5701f5cecd31 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -282,7 +282,9 @@
#define X86_FEATURE_AMD_IBPB (13*32+12) /* "" Indirect Branch Prediction Barrier */
#define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */
#define X86_FEATURE_AMD_STIBP (13*32+15) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_AMD_SSBD (13*32+24) /* "" Speculative Store Bypass Disable */
#define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */
+#define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 39e364c70caf..b6270a3b38e9 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -948,6 +948,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_S390_BPB 152
#define KVM_CAP_GET_MSR_FEATURES 153
#define KVM_CAP_HYPERV_EVENTFD 154
+#define KVM_CAP_HYPERV_TLBFLUSH 155
#ifdef KVM_CAP_IRQ_ROUTING
From 9331510135640429711afbd0c810686100824a79 Mon Sep 17 00:00:00 2001
From: Mathieu Malaterre <malat@debian.org>
Date: Tue, 26 Jun 2018 22:23:00 +0200
Subject: [PATCH 21/21] perf/core: Move inline keyword at the beginning of
declaration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Fix non-fatal warning triggered during compilation with W=1:
kernel/events/core.c:6106:1: warning: ‘inline’ is not at beginning of declaration [-Wold-style-declaration]
static void __always_inline
^~~~~~
Signed-off-by: Mathieu Malaterre <malat@debian.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20180626202301.20270-1-malat@debian.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
kernel/events/core.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 80cca2b30c4f..8f0434a9951a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6482,7 +6482,7 @@ void perf_prepare_sample(struct perf_event_header *header,
data->phys_addr = perf_virt_to_phys(data->addr);
}
-static void __always_inline
+static __always_inline void
__perf_event_output(struct perf_event *event,
struct perf_sample_data *data,
struct pt_regs *regs,