linux/tools/perf/util/evsel.c

3074 lines
75 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
*
* Parts came from builtin-{top,stat,record}.c, see those files for further
* copyright notes.
*/
perf tool: Fix endianness handling of u32 data in samples Currently, analyzing PPC data files on x86 the cpu field is always 0 and the tid and pid are backwards. For example, analyzing a PPC file on PPC the pid/tid fields show: rsyslogd 1210/1212 and analyzing the same PPC file using an x86 perf binary shows: rsyslogd 1212/1210 The problem is that the swap_op method for samples is perf_event__all64_swap which assumes all elements in the sample_data struct are u64s. cpu, tid and pid are u32s and need to be handled individually. Given that the swap is done before the sample is parsed, the simplest solution is to undo the 64-bit swap of those elements when the sample is parsed and do the proper swap. The RAW data field is generic and perf cannot have programmatic knowledge of how to treat that data. Instead a warning is given to the user. Thanks to Anton Blanchard for providing a data file for a mult-CPU PPC system so I could verify the fix for the CPU fields. v3 -> v4: - fixed use of WARN_ONCE v2 -> v3: - used WARN_ONCE for message regarding raw data - removed struct wrapper around union - fixed whitespace issues v1 -> v2: - added a union for undoing the byte-swap on u64 and redoing swap on u32's to address compiler errors (see git commit 65014ab3) Cc: Anton Blanchard <anton@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1315321946-16993-1-git-send-email-dsahern@gmail.com Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-09-06 15:12:26 +00:00
#include <byteswap.h>
#include <errno.h>
#include <inttypes.h>
#include <linux/bitops.h>
#include <api/fs/fs.h>
#include <api/fs/tracing_path.h>
#include <traceevent/event-parse.h>
#include <linux/hw_breakpoint.h>
#include <linux/perf_event.h>
#include <linux/compiler.h>
#include <linux/err.h>
#include <linux/zalloc.h>
#include <sys/ioctl.h>
#include <sys/resource.h>
#include <sys/types.h>
#include <dirent.h>
#include "asm/bug.h"
#include "callchain.h"
#include "cgroup.h"
#include "event.h"
#include "evsel.h"
#include "evlist.h"
#include "cpumap.h"
#include "thread_map.h"
#include "target.h"
perf tools: Support for DWARF mode callchain This patch enables perf to use the DWARF unwind code. It extends the perf record '-g' option with following arguments: 'fp' - provides framepointer based user stack backtrace 'dwarf[,size]' - provides DWARF (libunwind) based user stack backtrace. The size specifies the size of the user stack dump. If omitted it is 8192 by default. If libunwind is found during the perf build, then the 'dwarf' argument becomes available for record command. The 'fp' stays as default option in any case. Examples: (perf compiled with libunwind) perf record -g dwarf ls - provides dwarf unwind with 8192 as stack dump size perf record -g dwarf,4096 ls - provides dwarf unwind with 4096 as stack dump size perf record -g -- ls perf record -g fp ls - provides frame pointer unwind Signed-off-by: Jiri Olsa <jolsa@redhat.com> Original-patch-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: "Frank Ch. Eigler" <fche@redhat.com> Cc: Arun Sharma <asharma@fb.com> Cc: Benjamin Redelings <benjamin.redelings@nescent.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Frank Ch. Eigler <fche@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Ulrich Drepper <drepper@gmail.com> Link: http://lkml.kernel.org/r/1344345647-11536-13-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-08-07 13:20:47 +00:00
#include "perf_regs.h"
#include "debug.h"
#include "trace-event.h"
#include "stat.h"
#include "string2.h"
#include "memswap.h"
#include "util/parse-branch-options.h"
#include <linux/ctype.h>
struct perf_missing_features perf_missing_features;
static clockid_t clockid;
static int perf_evsel__no_extra_init(struct perf_evsel *evsel __maybe_unused)
{
return 0;
}
void __weak test_attr__ready(void) { }
static void perf_evsel__no_extra_fini(struct perf_evsel *evsel __maybe_unused)
{
}
static struct {
size_t size;
int (*init)(struct perf_evsel *evsel);
void (*fini)(struct perf_evsel *evsel);
} perf_evsel__object = {
.size = sizeof(struct perf_evsel),
.init = perf_evsel__no_extra_init,
.fini = perf_evsel__no_extra_fini,
};
int perf_evsel__object_config(size_t object_size,
int (*init)(struct perf_evsel *evsel),
void (*fini)(struct perf_evsel *evsel))
{
if (object_size == 0)
goto set_methods;
if (perf_evsel__object.size > object_size)
return -EINVAL;
perf_evsel__object.size = object_size;
set_methods:
if (init != NULL)
perf_evsel__object.init = init;
if (fini != NULL)
perf_evsel__object.fini = fini;
return 0;
}
#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
int __perf_evsel__sample_size(u64 sample_type)
{
u64 mask = sample_type & PERF_SAMPLE_MASK;
int size = 0;
int i;
for (i = 0; i < 64; i++) {
if (mask & (1ULL << i))
size++;
}
size *= sizeof(u64);
return size;
}
/**
* __perf_evsel__calc_id_pos - calculate id_pos.
* @sample_type: sample type
*
* This function returns the position of the event id (PERF_SAMPLE_ID or
* PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of struct
* sample_event.
*/
static int __perf_evsel__calc_id_pos(u64 sample_type)
{
int idx = 0;
if (sample_type & PERF_SAMPLE_IDENTIFIER)
return 0;
if (!(sample_type & PERF_SAMPLE_ID))
return -1;
if (sample_type & PERF_SAMPLE_IP)
idx += 1;
if (sample_type & PERF_SAMPLE_TID)
idx += 1;
if (sample_type & PERF_SAMPLE_TIME)
idx += 1;
if (sample_type & PERF_SAMPLE_ADDR)
idx += 1;
return idx;
}
/**
* __perf_evsel__calc_is_pos - calculate is_pos.
* @sample_type: sample type
*
* This function returns the position (counting backwards) of the event id
* (PERF_SAMPLE_ID or PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if
* sample_id_all is used there is an id sample appended to non-sample events.
*/
static int __perf_evsel__calc_is_pos(u64 sample_type)
{
int idx = 1;
if (sample_type & PERF_SAMPLE_IDENTIFIER)
return 1;
if (!(sample_type & PERF_SAMPLE_ID))
return -1;
if (sample_type & PERF_SAMPLE_CPU)
idx += 1;
if (sample_type & PERF_SAMPLE_STREAM_ID)
idx += 1;
return idx;
}
void perf_evsel__calc_id_pos(struct perf_evsel *evsel)
{
evsel->id_pos = __perf_evsel__calc_id_pos(evsel->attr.sample_type);
evsel->is_pos = __perf_evsel__calc_is_pos(evsel->attr.sample_type);
}
void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
enum perf_event_sample_format bit)
{
if (!(evsel->attr.sample_type & bit)) {
evsel->attr.sample_type |= bit;
evsel->sample_size += sizeof(u64);
perf_evsel__calc_id_pos(evsel);
}
}
void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel,
enum perf_event_sample_format bit)
{
if (evsel->attr.sample_type & bit) {
evsel->attr.sample_type &= ~bit;
evsel->sample_size -= sizeof(u64);
perf_evsel__calc_id_pos(evsel);
}
}
void perf_evsel__set_sample_id(struct perf_evsel *evsel,
bool can_sample_identifier)
{
if (can_sample_identifier) {
perf_evsel__reset_sample_bit(evsel, ID);
perf_evsel__set_sample_bit(evsel, IDENTIFIER);
} else {
perf_evsel__set_sample_bit(evsel, ID);
}
evsel->attr.read_format |= PERF_FORMAT_ID;
}
/**
* perf_evsel__is_function_event - Return whether given evsel is a function
* trace event
*
* @evsel - evsel selector to be tested
*
* Return %true if event is function trace event
*/
bool perf_evsel__is_function_event(struct perf_evsel *evsel)
{
#define FUNCTION_EVENT "ftrace:function"
return evsel->name &&
!strncmp(FUNCTION_EVENT, evsel->name, sizeof(FUNCTION_EVENT));
#undef FUNCTION_EVENT
}
void perf_evsel__init(struct perf_evsel *evsel,
struct perf_event_attr *attr, int idx)
{
evsel->idx = idx;
evsel->tracking = !idx;
evsel->attr = *attr;
evsel->leader = evsel;
tools/perf/stat: Add event unit and scale support This patch adds perf stat support for handling event units and scales as exported by the kernel. The kernel can export PMU events actual unit and scaling factor via sysfs: $ ls -1 /sys/devices/power/events/energy-* /sys/devices/power/events/energy-cores /sys/devices/power/events/energy-cores.scale /sys/devices/power/events/energy-cores.unit /sys/devices/power/events/energy-pkg /sys/devices/power/events/energy-pkg.scale /sys/devices/power/events/energy-pkg.unit $ cat /sys/devices/power/events/energy-cores.scale 2.3283064365386962890625e-10 $ cat cat /sys/devices/power/events/energy-cores.unit Joules This patch modifies the pmu event alias code to check for the presence of the .unit and .scale files to load the corresponding values. They are then used by perf stat transparently: # perf stat -a -e power/energy-pkg/,power/energy-cores/,cycles -I 1000 sleep 1000 # time counts unit events 1.000214717 3.07 Joules power/energy-pkg/ [100.00%] 1.000214717 0.53 Joules power/energy-cores/ 1.000214717 12965028 cycles [100.00%] 2.000749289 3.01 Joules power/energy-pkg/ 2.000749289 0.52 Joules power/energy-cores/ 2.000749289 15817043 cycles When the event does not have an explicit unit exported by the kernel, nothing is printed. In csv output mode, there will be an empty field. Special thanks to Jiri for providing the supporting code in the parser to trigger reading of the scale and unit files. Signed-off-by: Stephane Eranian <eranian@google.com> Reviewed-by: Jiri Olsa <jolsa@redhat.com> Reviewed-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: zheng.z.yan@intel.com Cc: bp@alien8.de Cc: maria.n.dimakopoulou@gmail.com Cc: acme@redhat.com Link: http://lkml.kernel.org/r/1384275531-10892-3-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-12 16:58:49 +00:00
evsel->unit = "";
evsel->scale = 1.0;
perf evsel: Introduce per event max_events property This simply adds the field to 'struct perf_evsel' and allows setting it via the event parser, to test it lets trace trace: First look at where in a function that receives an evsel we can put a probe to read how evsel->max_events was setup: # perf probe -x ~/bin/perf -L trace__event_handler <trace__event_handler@/home/acme/git/perf/tools/perf/builtin-trace.c:0> 0 static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel, union perf_event *event __maybe_unused, struct perf_sample *sample) 3 { 4 struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid); 5 int callchain_ret = 0; 7 if (sample->callchain) { 8 callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor); 9 if (callchain_ret == 0) { 10 if (callchain_cursor.nr < trace->min_stack) 11 goto out; 12 callchain_ret = 1; } } See what variables we can probe at line 7: # perf probe -x ~/bin/perf -V trace__event_handler:7 Available variables at trace__event_handler:7 @<trace__event_handler+89> int callchain_ret struct perf_evsel* evsel struct perf_sample* sample struct thread* thread struct trace* trace union perf_event* event Add a probe at that line asking for evsel->max_events to be collected and named as "max_events": # perf probe -x ~/bin/perf trace__event_handler:7 'max_events=evsel->max_events' Added new event: probe_perf:trace__event_handler (on trace__event_handler:7 in /home/acme/bin/perf with max_events=evsel->max_events) You can now use it in all perf tools, such as: perf record -e probe_perf:trace__event_handler -aR sleep 1 Now use 'perf trace', here aliased to just 'trace' and trace trace, i.e. the first 'trace' is tracing just that 'probe_perf:trace__event_handler' event, while the traced trace is tracing all scheduler tracepoints, will stop at two events (--max-events 2) and will just set evsel->max_events for all the sched tracepoints to 9, we will see the output of both traces intermixed: # trace -e *perf:*event_handler trace --max-events 2 -e sched:*/nr=9/ 0.000 :0/0 sched:sched_waking:comm=rcu_sched pid=10 prio=120 target_cpu=000 0.009 :0/0 sched:sched_wakeup:comm=rcu_sched pid=10 prio=120 target_cpu=000 0.000 trace/23949 probe_perf:trace__event_handler:(48c34a) max_events=0x9 0.046 trace/23949 probe_perf:trace__event_handler:(48c34a) max_events=0x9 # Now, if the traced trace sends its output to /dev/null, we'll see just what the first level trace outputs: that evsel->max_events is indeed being set to 9: # trace -e *perf:*event_handler trace -o /dev/null --max-events 2 -e sched:*/nr=9/ 0.000 trace/23961 probe_perf:trace__event_handler:(48c34a) max_events=0x9 0.030 trace/23961 probe_perf:trace__event_handler:(48c34a) max_events=0x9 # Now that we can set evsel->max_events, we can go to the next step, honour that per-event property in 'perf trace'. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Milian Wolff <milian.wolff@kdab.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-og00yasj276joem6e14l1eas@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-10-19 18:47:34 +00:00
evsel->max_events = ULONG_MAX;
evsel->evlist = NULL;
evsel->bpf_obj = NULL;
perf bpf: Attach eBPF filter to perf event This is the final patch which makes basic BPF filter work. After applying this patch, users are allowed to use BPF filter like: # perf record --event ./hello_world.o ls A bpf_fd field is appended to 'struct evsel', and setup during the callback function add_bpf_event() for each 'probe_trace_event'. PERF_EVENT_IOC_SET_BPF ioctl is used to attach eBPF program to a newly created perf event. The file descriptor of the eBPF program is passed to perf record using previous patches, and stored into evsel->bpf_fd. It is possible that different perf event are created for one kprobe events for different CPUs. In this case, when trying to call the ioctl, EEXIST will be return. This patch doesn't treat it as an error. Committer note: The bpf proggie used so far: __attribute__((section("fork=_do_fork"), used)) int fork(void *ctx) { return 0; } char _license[] __attribute__((section("license"), used)) = "GPL"; int _version __attribute__((section("version"), used)) = 0x40300; failed to produce any samples, even with forks happening and it being running in system wide mode. That is because now the filter is being associated, and the code above always returns zero, meaning that all forks will be probed but filtered away ;-/ Change it to 'return 1;' instead and after that: # trace --no-syscalls --event /tmp/foo.o 0.000 perf_bpf_probe:fork:(ffffffff8109be30)) 2.333 perf_bpf_probe:fork:(ffffffff8109be30)) 3.725 perf_bpf_probe:fork:(ffffffff8109be30)) 4.550 perf_bpf_probe:fork:(ffffffff8109be30)) ^C# And it works with all tools, including 'perf trace'. Signed-off-by: Wang Nan <wangnan0@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexei Starovoitov <ast@plumgrid.com> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: David Ahern <dsahern@gmail.com> Cc: He Kuang <hekuang@huawei.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kaixu Xia <xiakaixu@huawei.com> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1444826502-49291-8-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-10-14 12:41:18 +00:00
evsel->bpf_fd = -1;
INIT_LIST_HEAD(&evsel->node);
INIT_LIST_HEAD(&evsel->config_terms);
perf_evsel__object.init(evsel);
evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
perf_evsel__calc_id_pos(evsel);
perf record: Apply filter to all events in a glob matching There is an old problem in perf's filter applying which first posted at Sep. 2014 at https://lkml.org/lkml/2014/9/9/944 that, if passing multiple events in a glob matching expression in cmdline then add '--filter' after them, the filter will be applied on only the last one. For example: # dd if=/dev/zero of=/dev/null & [1] 464 # perf record -a -e 'syscalls:sys_*_read' --filter 'common_pid != 464' sleep 0.1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.239 MB perf.data (2094 samples) ] # perf report --stdio | tee ... # Samples: 2K of event 'syscalls:sys_enter_read' # Event count (approx.): 2092 ... # Samples: 2 of event 'syscalls:sys_exit_read' # Event count (approx.): 2 ... In this example, filter only applied on 'syscalls:sys_exit_read', and there's no way to set filter for ''syscalls:sys_enter_read'. This patch adds a 'cmdline_group_boundary' for 'struct evsel', and apply filter on all events between two boundary marks. After applying this patch: # perf record -a -e 'syscalls:sys_*_read' --filter 'common_pid != 464' sleep 0.1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.031 MB perf.data (3 samples) ] # perf report --stdio | tee ... # Samples: 1 of event 'syscalls:sys_enter_read' # Event count (approx.): 1 ... # Samples: 2 of event 'syscalls:sys_exit_read' # Event count (approx.): 2 ... Signed-off-by: Wang Nan <wangnan0@huawei.com> Reported-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1436513770-8896-1-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-10 07:36:09 +00:00
evsel->cmdline_group_boundary = false;
perf stat: Output JSON MetricExpr metric Add generic infrastructure to perf stat to output ratios for "MetricExpr" entries in the event lists. Many events are more useful as ratios than in raw form, typically some count in relation to total ticks. Transfer the MetricExpr information from the alias to the evsel. We mark the events that need to be collected for MetricExpr, and also link the events using them with a pointer. The code is careful to always prefer the right event in the same group to minimize multiplexing errors. At the moment only a single relation is supported. Then add a rblist to the stat shadow code that remembers stats based on the cpu and context. Then finally update and retrieve and print these values similarly to the existing hardcoded perf metrics. We use the simple expression parser added earlier to evaluate the expression. Normally we just output the result without further commentary, but for --metric-only this would lead to empty columns. So for this case use the original event as description. There is no attempt to automatically add the MetricExpr event, if it is missing, however we suggest it to the user, because the user tool doesn't have enough information to reliably construct a group that is guaranteed to schedule. So we leave that to the user. % perf stat -a -I 1000 -e '{unc_p_clockticks,unc_p_freq_max_os_cycles}' 1.000147889 800,085,181 unc_p_clockticks 1.000147889 93,126,241 unc_p_freq_max_os_cycles # 11.6 2.000448381 800,218,217 unc_p_clockticks 2.000448381 142,516,095 unc_p_freq_max_os_cycles # 17.8 3.000639852 800,243,057 unc_p_clockticks 3.000639852 162,292,689 unc_p_freq_max_os_cycles # 20.3 % perf stat -a -I 1000 -e '{unc_p_clockticks,unc_p_freq_max_os_cycles}' --metric-only # time freq_max_os_cycles % 1.000127077 0.9 2.000301436 0.7 3.000456379 0.0 v2: Change from DivideBy to MetricExpr v3: Use expr__ prefix. Support more than one other event. v4: Update description v5: Only print warning message once for multiple PMUs. Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170320201711.14142-11-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-20 20:17:08 +00:00
evsel->metric_expr = NULL;
evsel->metric_name = NULL;
perf stat: Output JSON MetricExpr metric Add generic infrastructure to perf stat to output ratios for "MetricExpr" entries in the event lists. Many events are more useful as ratios than in raw form, typically some count in relation to total ticks. Transfer the MetricExpr information from the alias to the evsel. We mark the events that need to be collected for MetricExpr, and also link the events using them with a pointer. The code is careful to always prefer the right event in the same group to minimize multiplexing errors. At the moment only a single relation is supported. Then add a rblist to the stat shadow code that remembers stats based on the cpu and context. Then finally update and retrieve and print these values similarly to the existing hardcoded perf metrics. We use the simple expression parser added earlier to evaluate the expression. Normally we just output the result without further commentary, but for --metric-only this would lead to empty columns. So for this case use the original event as description. There is no attempt to automatically add the MetricExpr event, if it is missing, however we suggest it to the user, because the user tool doesn't have enough information to reliably construct a group that is guaranteed to schedule. So we leave that to the user. % perf stat -a -I 1000 -e '{unc_p_clockticks,unc_p_freq_max_os_cycles}' 1.000147889 800,085,181 unc_p_clockticks 1.000147889 93,126,241 unc_p_freq_max_os_cycles # 11.6 2.000448381 800,218,217 unc_p_clockticks 2.000448381 142,516,095 unc_p_freq_max_os_cycles # 17.8 3.000639852 800,243,057 unc_p_clockticks 3.000639852 162,292,689 unc_p_freq_max_os_cycles # 20.3 % perf stat -a -I 1000 -e '{unc_p_clockticks,unc_p_freq_max_os_cycles}' --metric-only # time freq_max_os_cycles % 1.000127077 0.9 2.000301436 0.7 3.000456379 0.0 v2: Change from DivideBy to MetricExpr v3: Use expr__ prefix. Support more than one other event. v4: Update description v5: Only print warning message once for multiple PMUs. Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170320201711.14142-11-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-20 20:17:08 +00:00
evsel->metric_events = NULL;
evsel->collect_stat = false;
perf pmu: Display pmu name when printing unmerged events in stat To simplify creation of events accross multiple instances of the same type of PMU stat supports two methods for creating multiple events from a single event specification: 1. A prefix or glob can be used in the PMU name. 2. Aliases, which are listed immediately after the Kernel PMU events by perf list, are used. When the --no-merge option is passed and these events are displayed individually the PMU name is lost and it's not possible to see which count corresponds to which pmu: $ perf stat -a -e l3cache/read-miss/ --no-merge ls > /dev/null Performance counter stats for 'system wide': 67 l3cache/read-miss/ 67 l3cache/read-miss/ 63 l3cache/read-miss/ 60 l3cache/read-miss/ 0.001675706 seconds time elapsed $ perf stat -a -e l3cache_read_miss --no-merge ls > /dev/null Performance counter stats for 'system wide': 12 l3cache_read_miss 17 l3cache_read_miss 10 l3cache_read_miss 8 l3cache_read_miss 0.001661305 seconds time elapsed This change adds the original pmu name to the event. For dynamic pmu events the pmu name is restored in the event name: $ perf stat -a -e l3cache/read-miss/ --no-merge ls > /dev/null Performance counter stats for 'system wide': 63 l3cache_0_3/read-miss/ 74 l3cache_0_1/read-miss/ 64 l3cache_0_2/read-miss/ 74 l3cache_0_0/read-miss/ 0.001675706 seconds time elapsed For alias events the name is added after the event name: $ perf stat -a -e l3cache_read_miss --no-merge ls > /dev/null Performance counter stats for 'system wide': 10 l3cache_read_miss [l3cache_0_3] 12 l3cache_read_miss [l3cache_0_1] 10 l3cache_read_miss [l3cache_0_2] 17 l3cache_read_miss [l3cache_0_0] 0.001661305 seconds time elapsed Signed-off-by: Agustin Vega-Frias <agustinv@codeaurora.org> Acked-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Timur Tabi <timur@codeaurora.org> Cc: linux-arm-kernel@lists.infradead.org Change-Id: I8056b9eda74bda33e95065056167ad96e97cb1fb Link: http://lkml.kernel.org/r/1520345084-42646-3-git-send-email-agustinv@codeaurora.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-06 14:04:43 +00:00
evsel->pmu_name = NULL;
}
struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
{
struct perf_evsel *evsel = zalloc(perf_evsel__object.size);
if (!evsel)
return NULL;
perf_evsel__init(evsel, attr, idx);
perf tools: Introduce bpf-output event Commit a43eec304259 ("bpf: introduce bpf_perf_event_output() helper") adds a helper to enable a BPF program to output data to a perf ring buffer through a new type of perf event, PERF_COUNT_SW_BPF_OUTPUT. This patch enables perf to create events of that type. Now a perf user can use the following cmdline to receive output data from BPF programs: # perf record -a -e bpf-output/no-inherit,name=evt/ \ -e ./test_bpf_output.c/map:channel.event=evt/ ls / # perf script perf 1560 [004] 347747.086295: evt: ffffffff811fd201 sys_write ... perf 1560 [004] 347747.086300: evt: ffffffff811fd201 sys_write ... perf 1560 [004] 347747.086315: evt: ffffffff811fd201 sys_write ... ... Test result: # cat test_bpf_output.c /************************ BEGIN **************************/ #include <uapi/linux/bpf.h> struct bpf_map_def { unsigned int type; unsigned int key_size; unsigned int value_size; unsigned int max_entries; }; #define SEC(NAME) __attribute__((section(NAME), used)) static u64 (*ktime_get_ns)(void) = (void *)BPF_FUNC_ktime_get_ns; static int (*trace_printk)(const char *fmt, int fmt_size, ...) = (void *)BPF_FUNC_trace_printk; static int (*get_smp_processor_id)(void) = (void *)BPF_FUNC_get_smp_processor_id; static int (*perf_event_output)(void *, struct bpf_map_def *, int, void *, unsigned long) = (void *)BPF_FUNC_perf_event_output; struct bpf_map_def SEC("maps") channel = { .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, .key_size = sizeof(int), .value_size = sizeof(u32), .max_entries = __NR_CPUS__, }; SEC("func_write=sys_write") int func_write(void *ctx) { struct { u64 ktime; int cpuid; } __attribute__((packed)) output_data; char error_data[] = "Error: failed to output: %d\n"; output_data.cpuid = get_smp_processor_id(); output_data.ktime = ktime_get_ns(); int err = perf_event_output(ctx, &channel, get_smp_processor_id(), &output_data, sizeof(output_data)); if (err) trace_printk(error_data, sizeof(error_data), err); return 0; } char _license[] SEC("license") = "GPL"; int _version SEC("version") = LINUX_VERSION_CODE; /************************ END ***************************/ # perf record -a -e bpf-output/no-inherit,name=evt/ \ -e ./test_bpf_output.c/map:channel.event=evt/ ls / # perf script | grep ls ls 2242 [003] 347851.557563: evt: ffffffff811fd201 sys_write ... ls 2242 [003] 347851.557571: evt: ffffffff811fd201 sys_write ... Signed-off-by: Wang Nan <wangnan0@huawei.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Cody P Schafer <dev@codyps.com> Cc: He Kuang <hekuang@huawei.com> Cc: Jeremie Galarneau <jeremie.galarneau@efficios.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kirill Smelkov <kirr@nexedi.com> Cc: Li Zefan <lizefan@huawei.com> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1456132275-98875-11-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-22 09:10:37 +00:00
if (perf_evsel__is_bpf_output(evsel)) {
perf bpf: Add sample types for 'bpf-output' event Before this patch we can see very large time in the events before the 'bpf-output' event. For example: # perf trace -vv -T --ev sched:sched_switch \ --ev bpf-output/no-inherit,name=evt/ \ --ev ./test_bpf_trace.c/map:channel.event=evt/ \ usleep 10 ... 18446744073709.551 (18446564645918.480 ms): usleep/4157 nanosleep(rqtp: 0x7ffd3f0dc4e0) ... 18446744073709.551 ( ): evt:Raise a BPF event!..) 179427791.076 ( ): perf_bpf_probe:func_begin:(ffffffff810eb9a0)) 179427791.081 ( ): sched:sched_switch:usleep:4157 [120] S ==> swapper/2:0 [120]) ... We can also see the differences between bpf-output events and breakpoint events: For bpf output event: sample_type IP|TID|RAW|IDENTIFIER For tracepoint events: sample_type IP|TID|TIME|CPU|PERIOD|RAW|IDENTIFIER This patch fix this differences by adding more sample type for bpf-output events. After this patch: # perf trace -vv -T --ev sched:sched_switch \ --ev bpf-output/no-inherit,name=evt/ \ --ev ./test_bpf_trace.c/map:channel.event=evt/ \ usleep 10 ... 179877370.878 ( 0.003 ms): usleep/5336 nanosleep(rqtp: 0x7ffff866c450) ... 179877370.878 ( ): evt:Raise a BPF event!..) 179877370.878 ( ): perf_bpf_probe:func_begin:(ffffffff810eb9a0)) 179877370.882 ( ): sched:sched_switch:usleep:5336 [120] S ==> swapper/4:0 [120]) 179877370.945 ( ): evt:Raise a BPF event!..) ... # ./perf trace -vv -T --ev sched:sched_switch \ --ev bpf-output/no-inherit,name=evt/ \ --ev ./test_bpf_trace.c/map:channel.event=evt/ \ usleep 10 2>&1 | grep sample_type sample_type IP|TID|TIME|ID|CPU|PERIOD|RAW sample_type IP|TID|TIME|ID|CPU|PERIOD|RAW sample_type IP|TID|TIME|ID|CPU|PERIOD|RAW sample_type IP|TID|TIME|ID|CPU|PERIOD|RAW sample_type IP|TID|TIME|ID|CPU|PERIOD|RAW sample_type IP|TID|TIME|ID|CPU|PERIOD|RAW The 'IDENTIFIER' info is not required because all events have the same sample_type. Committer notes: Further testing, on top of the changes making 'perf trace' avoid samples from events without PERF_SAMPLE_TIME: Before: # trace --ev bpf-output/no-inherit,name=evt/ --ev /home/acme/bpf/test_bpf_trace.c/map:channel.event=evt/ usleep 10 <SNIP> 0.560 ( 0.001 ms): brk( ) = 0x55e5a1df8000 18446640227439.430 (18446640227438.859 ms): nanosleep(rqtp: 0x7ffc96643370) ... 18446640227439.430 ( ): evt:Raise a BPF event!..) 0.576 ( ): perf_bpf_probe:func_begin:(ffffffff81112460)) 18446640227439.430 ( ): evt:Raise a BPF event!..) 0.645 ( ): perf_bpf_probe:func_end:(ffffffff81112460 <- ffffffff81003d92)) 0.646 ( 0.076 ms): ... [continued]: nanosleep()) = 0 # After: # trace --ev bpf-output/no-inherit,name=evt/ --ev /home/acme/bpf/test_bpf_trace.c/map:channel.event=evt/ usleep 10 <SNIP> 0.292 ( 0.001 ms): brk( ) = 0x55c7cd6e1000 0.302 ( 0.004 ms): nanosleep(rqtp: 0x7ffedd8bc0f0) ... 0.302 ( ): evt:Raise a BPF event!..) 0.303 ( ): perf_bpf_probe:func_begin:(ffffffff81112460)) 0.397 ( ): evt:Raise a BPF event!..) 0.397 ( ): perf_bpf_probe:func_end:(ffffffff81112460 <- ffffffff81003d92)) 0.398 ( 0.100 ms): ... [continued]: nanosleep()) = 0 Signed-off-by: Wang Nan <wangnan0@huawei.com> Reported-and-Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Milian Wolff <milian.wolff@kdab.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1459517202-42320-1-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-01 13:26:42 +00:00
evsel->attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD),
perf tools: Introduce bpf-output event Commit a43eec304259 ("bpf: introduce bpf_perf_event_output() helper") adds a helper to enable a BPF program to output data to a perf ring buffer through a new type of perf event, PERF_COUNT_SW_BPF_OUTPUT. This patch enables perf to create events of that type. Now a perf user can use the following cmdline to receive output data from BPF programs: # perf record -a -e bpf-output/no-inherit,name=evt/ \ -e ./test_bpf_output.c/map:channel.event=evt/ ls / # perf script perf 1560 [004] 347747.086295: evt: ffffffff811fd201 sys_write ... perf 1560 [004] 347747.086300: evt: ffffffff811fd201 sys_write ... perf 1560 [004] 347747.086315: evt: ffffffff811fd201 sys_write ... ... Test result: # cat test_bpf_output.c /************************ BEGIN **************************/ #include <uapi/linux/bpf.h> struct bpf_map_def { unsigned int type; unsigned int key_size; unsigned int value_size; unsigned int max_entries; }; #define SEC(NAME) __attribute__((section(NAME), used)) static u64 (*ktime_get_ns)(void) = (void *)BPF_FUNC_ktime_get_ns; static int (*trace_printk)(const char *fmt, int fmt_size, ...) = (void *)BPF_FUNC_trace_printk; static int (*get_smp_processor_id)(void) = (void *)BPF_FUNC_get_smp_processor_id; static int (*perf_event_output)(void *, struct bpf_map_def *, int, void *, unsigned long) = (void *)BPF_FUNC_perf_event_output; struct bpf_map_def SEC("maps") channel = { .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, .key_size = sizeof(int), .value_size = sizeof(u32), .max_entries = __NR_CPUS__, }; SEC("func_write=sys_write") int func_write(void *ctx) { struct { u64 ktime; int cpuid; } __attribute__((packed)) output_data; char error_data[] = "Error: failed to output: %d\n"; output_data.cpuid = get_smp_processor_id(); output_data.ktime = ktime_get_ns(); int err = perf_event_output(ctx, &channel, get_smp_processor_id(), &output_data, sizeof(output_data)); if (err) trace_printk(error_data, sizeof(error_data), err); return 0; } char _license[] SEC("license") = "GPL"; int _version SEC("version") = LINUX_VERSION_CODE; /************************ END ***************************/ # perf record -a -e bpf-output/no-inherit,name=evt/ \ -e ./test_bpf_output.c/map:channel.event=evt/ ls / # perf script | grep ls ls 2242 [003] 347851.557563: evt: ffffffff811fd201 sys_write ... ls 2242 [003] 347851.557571: evt: ffffffff811fd201 sys_write ... Signed-off-by: Wang Nan <wangnan0@huawei.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Cody P Schafer <dev@codyps.com> Cc: He Kuang <hekuang@huawei.com> Cc: Jeremie Galarneau <jeremie.galarneau@efficios.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kirill Smelkov <kirr@nexedi.com> Cc: Li Zefan <lizefan@huawei.com> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1456132275-98875-11-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-22 09:10:37 +00:00
evsel->attr.sample_period = 1;
}
perf stat: Get rid of extra clock display function There's no reason to have separate function to display clock events. It's only purpose was to convert the nanosecond value into microseconds. We do that now in generic code, if the unit and scale values are properly set, which this patch do for clock events. The output differs in the unit field being displayed in its columns rather than having it added as a suffix of the event name. Plus the value is rounded into 2 decimal numbers as for any other event. Before: # perf stat -e cpu-clock,task-clock -C 0 sleep 3 Performance counter stats for 'CPU(s) 0': 3001.123137 cpu-clock (msec) # 1.000 CPUs utilized 3001.133250 task-clock (msec) # 1.000 CPUs utilized 3.001159813 seconds time elapsed Now: # perf stat -e cpu-clock,task-clock -C 0 sleep 3 Performance counter stats for 'CPU(s) 0': 3,001.05 msec cpu-clock # 1.000 CPUs utilized 3,001.05 msec task-clock # 1.000 CPUs utilized 3.001077794 seconds time elapsed There's a small difference in csv output, as we now output the unit field, which was empty before. It's in the proper spot, so there's no compatibility issue. Before: # perf stat -e cpu-clock,task-clock -C 0 -x, sleep 3 3001.065177,,cpu-clock,3001064187,100.00,1.000,CPUs utilized 3001.077085,,task-clock,3001077085,100.00,1.000,CPUs utilized # perf stat -e cpu-clock,task-clock -C 0 -x, sleep 3 3000.80,msec,cpu-clock,3000799026,100.00,1.000,CPUs utilized 3000.80,msec,task-clock,3000799550,100.00,1.000,CPUs utilized Add perf_evsel__is_clock to replace nsec_counter. Signed-off-by: Jiri Olsa <jolsa@kernel.org> 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: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20180720110036.32251-2-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-07-20 11:00:34 +00:00
if (perf_evsel__is_clock(evsel)) {
/*
* The evsel->unit points to static alias->unit
* so it's ok to use static string in here.
*/
static const char *unit = "msec";
evsel->unit = unit;
evsel->scale = 1e-6;
}
return evsel;
}
perf evsel: Fix attr.exclude_kernel setting for default cycles:p Yet another fix for probing the max attr.precise_ip setting: it is not enough settting attr.exclude_kernel for !root users, as they _can_ profile the kernel if the kernel.perf_event_paranoid sysctl is set to -1, so check that as well. Testing it: As non root: $ sysctl kernel.perf_event_paranoid kernel.perf_event_paranoid = 2 $ perf record sleep 1 $ perf evlist -v cycles:uppp: ..., exclude_kernel: 1, ... precise_ip: 3, ... Now as non-root, but with kernel.perf_event_paranoid set set to the most permissive value, -1: $ sysctl kernel.perf_event_paranoid kernel.perf_event_paranoid = -1 $ perf record sleep 1 $ perf evlist -v cycles:ppp: ..., exclude_kernel: 0, ... precise_ip: 3, ... $ I.e. non-root, default kernel.perf_event_paranoid: :uppp modifier = not allowed to sample the kernel, non-root, most permissible kernel.perf_event_paranoid: :ppp = allowed to sample the kernel. In both cases, use the highest available precision: attr.precise_ip = 3. Reported-and-Tested-by: Ingo Molnar <mingo@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andy Lutomirski <luto@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> Fixes: d37a36979077 ("perf evsel: Fix attr.exclude_kernel setting for default cycles:p") Link: http://lkml.kernel.org/n/tip-nj2qkf75xsd6pw6hhjzfqqdx@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-09-22 18:41:44 +00:00
static bool perf_event_can_profile_kernel(void)
{
return geteuid() == 0 || perf_event_paranoid() == -1;
}
struct perf_evsel *perf_evsel__new_cycles(bool precise)
{
struct perf_event_attr attr = {
.type = PERF_TYPE_HARDWARE,
.config = PERF_COUNT_HW_CPU_CYCLES,
perf evsel: Fix attr.exclude_kernel setting for default cycles:p Yet another fix for probing the max attr.precise_ip setting: it is not enough settting attr.exclude_kernel for !root users, as they _can_ profile the kernel if the kernel.perf_event_paranoid sysctl is set to -1, so check that as well. Testing it: As non root: $ sysctl kernel.perf_event_paranoid kernel.perf_event_paranoid = 2 $ perf record sleep 1 $ perf evlist -v cycles:uppp: ..., exclude_kernel: 1, ... precise_ip: 3, ... Now as non-root, but with kernel.perf_event_paranoid set set to the most permissive value, -1: $ sysctl kernel.perf_event_paranoid kernel.perf_event_paranoid = -1 $ perf record sleep 1 $ perf evlist -v cycles:ppp: ..., exclude_kernel: 0, ... precise_ip: 3, ... $ I.e. non-root, default kernel.perf_event_paranoid: :uppp modifier = not allowed to sample the kernel, non-root, most permissible kernel.perf_event_paranoid: :ppp = allowed to sample the kernel. In both cases, use the highest available precision: attr.precise_ip = 3. Reported-and-Tested-by: Ingo Molnar <mingo@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andy Lutomirski <luto@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> Fixes: d37a36979077 ("perf evsel: Fix attr.exclude_kernel setting for default cycles:p") Link: http://lkml.kernel.org/n/tip-nj2qkf75xsd6pw6hhjzfqqdx@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-09-22 18:41:44 +00:00
.exclude_kernel = !perf_event_can_profile_kernel(),
};
struct perf_evsel *evsel;
event_attr_init(&attr);
if (!precise)
goto new_event;
perf evsel: Fix probing of precise_ip level for default cycles event Since commit 18e7a45af91a ("perf/x86: Reject non sampling events with precise_ip") returns -EINVAL for sys_perf_event_open() with an attribute with (attr.precise_ip > 0 && attr.sample_period == 0), just like is done in the routine used to probe the max precise level when no events were passed to 'perf record' or 'perf top', i.e.: perf_evsel__new_cycles() perf_event_attr__set_max_precise_ip() The x86 code, in x86_pmu_hw_config(), which is called all the way from sys_perf_event_open() did, starting with the aforementioned commit: /* There's no sense in having PEBS for non sampling events: */ if (!is_sampling_event(event)) return -EINVAL; Which makes it fail for cycles:ppp, cycles:pp and cycles:p, always using just the non precise cycles variant. To make sure that this is the case, I tested it, before this patch, with: # perf probe -L x86_pmu_hw_config <x86_pmu_hw_config@/home/acme/git/linux/arch/x86/events/core.c:0> 0 int x86_pmu_hw_config(struct perf_event *event) 1 { 2 if (event->attr.precise_ip) { <SNIP> 17 if (event->attr.precise_ip > precise) 18 return -EOPNOTSUPP; /* There's no sense in having PEBS for non sampling events: */ 21 if (!is_sampling_event(event)) 22 return -EINVAL; } <SNIP> # perf probe x86_pmu_hw_config:22 Added new events: probe:x86_pmu_hw_config (on x86_pmu_hw_config:22) probe:x86_pmu_hw_config_1 (on x86_pmu_hw_config:22) You can now use it in all perf tools, such as: perf record -e probe:x86_pmu_hw_config_1 -aR sleep 1 # perf trace -e perf_event_open,probe:x86_pmu_hwconfig*/max-stack=16/ perf record usleep 1 0.000 ( 0.015 ms): perf/4150 perf_event_open(attr_uptr: 0x7ffebc8ba110, cpu: -1, group_fd: -1 ) ... 0.015 ( ): probe:x86_pmu_hw_config:(ffffffff9c0065e1)) x86_pmu_hw_config ([kernel.kallsyms]) hsw_hw_config ([kernel.kallsyms]) x86_pmu_event_init ([kernel.kallsyms]) perf_try_init_event ([kernel.kallsyms]) perf_event_alloc ([kernel.kallsyms]) SYSC_perf_event_open ([kernel.kallsyms]) sys_perf_event_open ([kernel.kallsyms]) do_syscall_64 ([kernel.kallsyms]) return_from_SYSCALL_64 ([kernel.kallsyms]) syscall (/usr/lib64/libc-2.24.so) perf_event_attr__set_max_precise_ip (/home/acme/bin/perf) perf_evsel__new_cycles (/home/acme/bin/perf) perf_evlist__add_default (/home/acme/bin/perf) cmd_record (/home/acme/bin/perf) run_builtin (/home/acme/bin/perf) handle_internal_command (/home/acme/bin/perf) 0.000 ( 0.021 ms): perf/4150 ... [continued]: perf_event_open()) = -1 EINVAL Invalid argument 0.023 ( 0.002 ms): perf/4150 perf_event_open(attr_uptr: 0x7ffebc8ba110, cpu: -1, group_fd: -1 ) ... 0.025 ( ): probe:x86_pmu_hw_config:(ffffffff9c0065e1)) x86_pmu_hw_config ([kernel.kallsyms]) hsw_hw_config ([kernel.kallsyms]) x86_pmu_event_init ([kernel.kallsyms]) perf_try_init_event ([kernel.kallsyms]) perf_event_alloc ([kernel.kallsyms]) SYSC_perf_event_open ([kernel.kallsyms]) sys_perf_event_open ([kernel.kallsyms]) do_syscall_64 ([kernel.kallsyms]) return_from_SYSCALL_64 ([kernel.kallsyms]) syscall (/usr/lib64/libc-2.24.so) perf_event_attr__set_max_precise_ip (/home/acme/bin/perf) perf_evsel__new_cycles (/home/acme/bin/perf) perf_evlist__add_default (/home/acme/bin/perf) cmd_record (/home/acme/bin/perf) run_builtin (/home/acme/bin/perf) handle_internal_command (/home/acme/bin/perf) 0.023 ( 0.004 ms): perf/4150 ... [continued]: perf_event_open()) = -1 EINVAL Invalid argument 0.028 ( 0.002 ms): perf/4150 perf_event_open(attr_uptr: 0x7ffebc8ba110, cpu: -1, group_fd: -1 ) ... 0.030 ( ): probe:x86_pmu_hw_config:(ffffffff9c0065e1)) x86_pmu_hw_config ([kernel.kallsyms]) hsw_hw_config ([kernel.kallsyms]) x86_pmu_event_init ([kernel.kallsyms]) perf_try_init_event ([kernel.kallsyms]) perf_event_alloc ([kernel.kallsyms]) SYSC_perf_event_open ([kernel.kallsyms]) sys_perf_event_open ([kernel.kallsyms]) do_syscall_64 ([kernel.kallsyms]) return_from_SYSCALL_64 ([kernel.kallsyms]) syscall (/usr/lib64/libc-2.24.so) perf_event_attr__set_max_precise_ip (/home/acme/bin/perf) perf_evsel__new_cycles (/home/acme/bin/perf) perf_evlist__add_default (/home/acme/bin/perf) cmd_record (/home/acme/bin/perf) run_builtin (/home/acme/bin/perf) handle_internal_command (/home/acme/bin/perf) 0.028 ( 0.004 ms): perf/4150 ... [continued]: perf_event_open()) = -1 EINVAL Invalid argument 41.018 ( 0.012 ms): perf/4150 perf_event_open(attr_uptr: 0x7ffebc8b5dd0, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 4 41.065 ( 0.011 ms): perf/4150 perf_event_open(attr_uptr: 0x3c7db78, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 4 41.080 ( 0.006 ms): perf/4150 perf_event_open(attr_uptr: 0x3c7db78, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 4 41.103 ( 0.010 ms): perf/4150 perf_event_open(attr_uptr: 0x3c4e748, pid: 4151 (perf), group_fd: -1, flags: FD_CLOEXEC) = 4 41.115 ( 0.006 ms): perf/4150 perf_event_open(attr_uptr: 0x3c4e748, pid: 4151 (perf), cpu: 1, group_fd: -1, flags: FD_CLOEXEC) = 5 41.122 ( 0.004 ms): perf/4150 perf_event_open(attr_uptr: 0x3c4e748, pid: 4151 (perf), cpu: 2, group_fd: -1, flags: FD_CLOEXEC) = 6 41.128 ( 0.008 ms): perf/4150 perf_event_open(attr_uptr: 0x3c4e748, pid: 4151 (perf), cpu: 3, group_fd: -1, flags: FD_CLOEXEC) = 8 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.017 MB perf.data (2 samples) ] # I.e. that return -EINVAL in x86_pmu_hw_config() is hit three times. So fix it by just setting attr.sample_period Now, after this patch: # perf trace --max-stack=2 -e perf_event_open,probe:x86_pmu_hw_config* perf record usleep 1 [ perf record: Woken up 1 times to write data ] 0.000 ( 0.017 ms): perf/8469 perf_event_open(attr_uptr: 0x7ffe36c27d10, pid: -1, cpu: 3, group_fd: -1, flags: FD_CLOEXEC) = 4 syscall (/usr/lib64/libc-2.24.so) perf_event_open_cloexec_flag (/home/acme/bin/perf) 0.050 ( 0.031 ms): perf/8469 perf_event_open(attr_uptr: 0x24ebb78, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 4 syscall (/usr/lib64/libc-2.24.so) perf_evlist__config (/home/acme/bin/perf) 0.092 ( 0.040 ms): perf/8469 perf_event_open(attr_uptr: 0x24ebb78, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 4 syscall (/usr/lib64/libc-2.24.so) perf_evlist__config (/home/acme/bin/perf) 0.143 ( 0.007 ms): perf/8469 perf_event_open(attr_uptr: 0x24bc748, cpu: -1, group_fd: -1 ) = 4 syscall (/usr/lib64/libc-2.24.so) perf_event_attr__set_max_precise_ip (/home/acme/bin/perf) 0.161 ( 0.007 ms): perf/8469 perf_event_open(attr_uptr: 0x24bc748, pid: 8470 (perf), group_fd: -1, flags: FD_CLOEXEC) = 4 syscall (/usr/lib64/libc-2.24.so) perf_evsel__open (/home/acme/bin/perf) 0.171 ( 0.005 ms): perf/8469 perf_event_open(attr_uptr: 0x24bc748, pid: 8470 (perf), cpu: 1, group_fd: -1, flags: FD_CLOEXEC) = 5 syscall (/usr/lib64/libc-2.24.so) perf_evsel__open (/home/acme/bin/perf) 0.180 ( 0.007 ms): perf/8469 perf_event_open(attr_uptr: 0x24bc748, pid: 8470 (perf), cpu: 2, group_fd: -1, flags: FD_CLOEXEC) = 6 syscall (/usr/lib64/libc-2.24.so) perf_evsel__open (/home/acme/bin/perf) 0.190 ( 0.005 ms): perf/8469 perf_event_open(attr_uptr: 0x24bc748, pid: 8470 (perf), cpu: 3, group_fd: -1, flags: FD_CLOEXEC) = 8 syscall (/usr/lib64/libc-2.24.so) perf_evsel__open (/home/acme/bin/perf) [ perf record: Captured and wrote 0.017 MB perf.data (7 samples) ] # The probe one called from perf_event_attr__set_max_precise_ip() works the first time, with attr.precise_ip = 3, wit hthe next ones being the per cpu ones for the cycles:ppp event. And here is the text from a report and alternative proposed patch by Thomas-Mich Richter: --- On s390 the counter and sampling facility do not support a precise IP skid level and sometimes returns EOPNOTSUPP when structure member precise_ip in struct perf_event_attr is not set to zero. On s390 commnd 'perf record -- true' fails with error EOPNOTSUPP. This happens only when no events are specified on command line. The functions called are ... --> perf_evlist__add_default --> perf_evsel__new_cycles --> perf_event_attr__set_max_precise_ip The last function determines the value of structure member precise_ip by invoking the perf_event_open() system call and checking the return code. The first successful open is the value for precise_ip. However the value is determined without setting member sample_period and indicates no sampling. On s390 the counter facility and sampling facility are different. The above procedure determines a precise_ip value of 3 using the counter facility. Later it uses the sampling facility with a value of 3 and fails with EOPNOTSUPP. --- v2: Older compilers (e.g. gcc 4.4.7) don't support referencing members of unnamed union members in the container struct initialization, so move from: struct perf_event_attr attr = { ... .sample_period = 1, }; to right after it as: struct perf_event_attr attr = { ... }; attr.sample_period = 1; v3: We need to reset .sample_period to 0 to let the users of perf_evsel__new_cycles() to properly setup attr.sample_period or attr.sample_freq. Reported by Ingo Molnar. Reported-and-Acked-by: Thomas-Mich Richter <tmricht@linux.vnet.ibm.com> Acked-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> 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> Cc: Wang Nan <wangnan0@huawei.com> Fixes: 18e7a45af91a ("perf/x86: Reject non sampling events with precise_ip") Link: http://lkml.kernel.org/n/tip-yv6nnkl7tzqocrm0hl3x7vf1@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-06-09 19:54:28 +00:00
/*
* Now let the usual logic to set up the perf_event_attr defaults
* to kick in when we return and before perf_evsel__open() is called.
*/
new_event:
evsel = perf_evsel__new(&attr);
if (evsel == NULL)
goto out;
perf evsel: Fix max perf_event_attr.precise_ip detection After a discussion with Andi, move the perf_event_attr.precise_ip detection for maximum precise config (via :P modifier or for default cycles event) to perf_evsel__open(). The current detection in perf_event_attr__set_max_precise_ip() is tricky, because precise_ip config is specific for given event and it currently checks only hw cycles. We now check for valid precise_ip value right after failing sys_perf_event_open() for specific event, before any of the perf_event_attr fallback code gets executed. This way we get the proper config in perf_event_attr together with allowed precise_ip settings. We can see that code activity with -vv, like: $ perf record -vv ls ... ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 ... precise_ip 3 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 ------------------------------------------------------------ sys_perf_event_open: pid 9926 cpu 0 group_fd -1 flags 0x8 sys_perf_event_open failed, error -95 decreasing precise_ip by one (2) ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 ... precise_ip 2 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 ------------------------------------------------------------ sys_perf_event_open: pid 9926 cpu 0 group_fd -1 flags 0x8 = 4 ... Suggested-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/n/tip-dkvxxbeg7lu74155d4jhlmc9@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-14 14:00:10 +00:00
evsel->precise_max = true;
/* use asprintf() because free(evsel) assumes name is allocated */
if (asprintf(&evsel->name, "cycles%s%s%.*s",
(attr.precise_ip || attr.exclude_kernel) ? ":" : "",
attr.exclude_kernel ? "u" : "",
attr.precise_ip ? attr.precise_ip + 1 : 0, "ppp") < 0)
goto error_free;
out:
return evsel;
error_free:
perf_evsel__delete(evsel);
evsel = NULL;
goto out;
}
/*
* Returns pointer with encoded error via <linux/err.h> interface.
*/
struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx)
{
struct perf_evsel *evsel = zalloc(perf_evsel__object.size);
int err = -ENOMEM;
if (evsel == NULL) {
goto out_err;
} else {
struct perf_event_attr attr = {
.type = PERF_TYPE_TRACEPOINT,
.sample_type = (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD),
};
if (asprintf(&evsel->name, "%s:%s", sys, name) < 0)
goto out_free;
evsel->tp_format = trace_event__tp_format(sys, name);
if (IS_ERR(evsel->tp_format)) {
err = PTR_ERR(evsel->tp_format);
goto out_free;
}
event_attr_init(&attr);
attr.config = evsel->tp_format->id;
attr.sample_period = 1;
perf_evsel__init(evsel, &attr, idx);
}
return evsel;
out_free:
zfree(&evsel->name);
free(evsel);
out_err:
return ERR_PTR(err);
}
const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX] = {
"cycles",
"instructions",
"cache-references",
"cache-misses",
"branches",
"branch-misses",
"bus-cycles",
"stalled-cycles-frontend",
"stalled-cycles-backend",
"ref-cycles",
};
static const char *__perf_evsel__hw_name(u64 config)
{
if (config < PERF_COUNT_HW_MAX && perf_evsel__hw_names[config])
return perf_evsel__hw_names[config];
return "unknown-hardware";
}
static int perf_evsel__add_modifiers(struct perf_evsel *evsel, char *bf, size_t size)
{
int colon = 0, r = 0;
struct perf_event_attr *attr = &evsel->attr;
bool exclude_guest_default = false;
#define MOD_PRINT(context, mod) do { \
if (!attr->exclude_##context) { \
if (!colon) colon = ++r; \
r += scnprintf(bf + r, size - r, "%c", mod); \
} } while(0)
if (attr->exclude_kernel || attr->exclude_user || attr->exclude_hv) {
MOD_PRINT(kernel, 'k');
MOD_PRINT(user, 'u');
MOD_PRINT(hv, 'h');
exclude_guest_default = true;
}
if (attr->precise_ip) {
if (!colon)
colon = ++r;
r += scnprintf(bf + r, size - r, "%.*s", attr->precise_ip, "ppp");
exclude_guest_default = true;
}
if (attr->exclude_host || attr->exclude_guest == exclude_guest_default) {
MOD_PRINT(host, 'H');
MOD_PRINT(guest, 'G');
}
#undef MOD_PRINT
if (colon)
bf[colon - 1] = ':';
return r;
}
static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size)
{
int r = scnprintf(bf, size, "%s", __perf_evsel__hw_name(evsel->attr.config));
return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
}
const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX] = {
"cpu-clock",
"task-clock",
"page-faults",
"context-switches",
"cpu-migrations",
"minor-faults",
"major-faults",
"alignment-faults",
"emulation-faults",
"dummy",
};
static const char *__perf_evsel__sw_name(u64 config)
{
if (config < PERF_COUNT_SW_MAX && perf_evsel__sw_names[config])
return perf_evsel__sw_names[config];
return "unknown-software";
}
static int perf_evsel__sw_name(struct perf_evsel *evsel, char *bf, size_t size)
{
int r = scnprintf(bf, size, "%s", __perf_evsel__sw_name(evsel->attr.config));
return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
}
static int __perf_evsel__bp_name(char *bf, size_t size, u64 addr, u64 type)
{
int r;
r = scnprintf(bf, size, "mem:0x%" PRIx64 ":", addr);
if (type & HW_BREAKPOINT_R)
r += scnprintf(bf + r, size - r, "r");
if (type & HW_BREAKPOINT_W)
r += scnprintf(bf + r, size - r, "w");
if (type & HW_BREAKPOINT_X)
r += scnprintf(bf + r, size - r, "x");
return r;
}
static int perf_evsel__bp_name(struct perf_evsel *evsel, char *bf, size_t size)
{
struct perf_event_attr *attr = &evsel->attr;
int r = __perf_evsel__bp_name(bf, size, attr->bp_addr, attr->bp_type);
return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
}
const char *perf_evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX]
[PERF_EVSEL__MAX_ALIASES] = {
{ "L1-dcache", "l1-d", "l1d", "L1-data", },
{ "L1-icache", "l1-i", "l1i", "L1-instruction", },
{ "LLC", "L2", },
{ "dTLB", "d-tlb", "Data-TLB", },
{ "iTLB", "i-tlb", "Instruction-TLB", },
{ "branch", "branches", "bpu", "btb", "bpc", },
{ "node", },
};
const char *perf_evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_EVSEL__MAX_ALIASES] = {
{ "load", "loads", "read", },
{ "store", "stores", "write", },
{ "prefetch", "prefetches", "speculative-read", "speculative-load", },
};
const char *perf_evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX]
[PERF_EVSEL__MAX_ALIASES] = {
{ "refs", "Reference", "ops", "access", },
{ "misses", "miss", },
};
#define C(x) PERF_COUNT_HW_CACHE_##x
#define CACHE_READ (1 << C(OP_READ))
#define CACHE_WRITE (1 << C(OP_WRITE))
#define CACHE_PREFETCH (1 << C(OP_PREFETCH))
#define COP(x) (1 << x)
/*
* cache operartion stat
* L1I : Read and prefetch only
* ITLB and BPU : Read-only
*/
static unsigned long perf_evsel__hw_cache_stat[C(MAX)] = {
[C(L1D)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
[C(L1I)] = (CACHE_READ | CACHE_PREFETCH),
[C(LL)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
[C(DTLB)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
[C(ITLB)] = (CACHE_READ),
[C(BPU)] = (CACHE_READ),
[C(NODE)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
};
bool perf_evsel__is_cache_op_valid(u8 type, u8 op)
{
if (perf_evsel__hw_cache_stat[type] & COP(op))
return true; /* valid */
else
return false; /* invalid */
}
int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
char *bf, size_t size)
{
if (result) {
return scnprintf(bf, size, "%s-%s-%s", perf_evsel__hw_cache[type][0],
perf_evsel__hw_cache_op[op][0],
perf_evsel__hw_cache_result[result][0]);
}
return scnprintf(bf, size, "%s-%s", perf_evsel__hw_cache[type][0],
perf_evsel__hw_cache_op[op][1]);
}
static int __perf_evsel__hw_cache_name(u64 config, char *bf, size_t size)
{
u8 op, result, type = (config >> 0) & 0xff;
const char *err = "unknown-ext-hardware-cache-type";
perf evsel: Do not access outside hw cache name arrays We have to check if the values are >= *_MAX, not just >, fix it. From the bugzilla report: ''In file /tools/perf/util/evsel.c function __perf_evsel__hw_cache_name it appears that there is a bug that reads beyond the end of the buffer. The statement "if (type > PERF_COUNT_HW_CACHE_MAX)" allows type to be equal to the maximum value. Later, when statement "if (!perf_evsel__is_cache_op_valid(type, op))" is executed, the function can access array perf_evsel__hw_cache_stat[type] beyond the end of the buffer. It appears to me that the statement "if (type > PERF_COUNT_HW_CACHE_MAX)" should be "if (type >= PERF_COUNT_HW_CACHE_MAX)" Bug found with Coverity and manual code review. No attempts were made to execute the code with a maximum type value.'' Committer note: Testing it: $ perf record -e $(echo $(perf list cache | cut -d \[ -f1) | sed 's/ /,/g') usleep 1 [ perf record: Woken up 16 times to write data ] [ perf record: Captured and wrote 0.023 MB perf.data (34 samples) ] $ perf evlist L1-dcache-load-misses L1-dcache-loads L1-dcache-stores L1-icache-load-misses LLC-load-misses LLC-loads LLC-store-misses LLC-stores branch-load-misses branch-loads dTLB-load-misses dTLB-loads dTLB-store-misses dTLB-stores iTLB-load-misses iTLB-loads node-load-misses node-loads node-store-misses node-stores $ perf list cache List of pre-defined events (to be used in -e): L1-dcache-load-misses [Hardware cache event] L1-dcache-loads [Hardware cache event] L1-dcache-stores [Hardware cache event] L1-icache-load-misses [Hardware cache event] LLC-load-misses [Hardware cache event] LLC-loads [Hardware cache event] LLC-store-misses [Hardware cache event] LLC-stores [Hardware cache event] branch-load-misses [Hardware cache event] branch-loads [Hardware cache event] dTLB-load-misses [Hardware cache event] dTLB-loads [Hardware cache event] dTLB-store-misses [Hardware cache event] dTLB-stores [Hardware cache event] iTLB-load-misses [Hardware cache event] iTLB-loads [Hardware cache event] node-load-misses [Hardware cache event] node-loads [Hardware cache event] node-store-misses [Hardware cache event] node-stores [Hardware cache event] $ Reported-by: Brian Sweeney <bsweeney@lgsinnovations.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=153351 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-08-18 19:30:28 +00:00
if (type >= PERF_COUNT_HW_CACHE_MAX)
goto out_err;
op = (config >> 8) & 0xff;
err = "unknown-ext-hardware-cache-op";
perf evsel: Do not access outside hw cache name arrays We have to check if the values are >= *_MAX, not just >, fix it. From the bugzilla report: ''In file /tools/perf/util/evsel.c function __perf_evsel__hw_cache_name it appears that there is a bug that reads beyond the end of the buffer. The statement "if (type > PERF_COUNT_HW_CACHE_MAX)" allows type to be equal to the maximum value. Later, when statement "if (!perf_evsel__is_cache_op_valid(type, op))" is executed, the function can access array perf_evsel__hw_cache_stat[type] beyond the end of the buffer. It appears to me that the statement "if (type > PERF_COUNT_HW_CACHE_MAX)" should be "if (type >= PERF_COUNT_HW_CACHE_MAX)" Bug found with Coverity and manual code review. No attempts were made to execute the code with a maximum type value.'' Committer note: Testing it: $ perf record -e $(echo $(perf list cache | cut -d \[ -f1) | sed 's/ /,/g') usleep 1 [ perf record: Woken up 16 times to write data ] [ perf record: Captured and wrote 0.023 MB perf.data (34 samples) ] $ perf evlist L1-dcache-load-misses L1-dcache-loads L1-dcache-stores L1-icache-load-misses LLC-load-misses LLC-loads LLC-store-misses LLC-stores branch-load-misses branch-loads dTLB-load-misses dTLB-loads dTLB-store-misses dTLB-stores iTLB-load-misses iTLB-loads node-load-misses node-loads node-store-misses node-stores $ perf list cache List of pre-defined events (to be used in -e): L1-dcache-load-misses [Hardware cache event] L1-dcache-loads [Hardware cache event] L1-dcache-stores [Hardware cache event] L1-icache-load-misses [Hardware cache event] LLC-load-misses [Hardware cache event] LLC-loads [Hardware cache event] LLC-store-misses [Hardware cache event] LLC-stores [Hardware cache event] branch-load-misses [Hardware cache event] branch-loads [Hardware cache event] dTLB-load-misses [Hardware cache event] dTLB-loads [Hardware cache event] dTLB-store-misses [Hardware cache event] dTLB-stores [Hardware cache event] iTLB-load-misses [Hardware cache event] iTLB-loads [Hardware cache event] node-load-misses [Hardware cache event] node-loads [Hardware cache event] node-store-misses [Hardware cache event] node-stores [Hardware cache event] $ Reported-by: Brian Sweeney <bsweeney@lgsinnovations.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=153351 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-08-18 19:30:28 +00:00
if (op >= PERF_COUNT_HW_CACHE_OP_MAX)
goto out_err;
result = (config >> 16) & 0xff;
err = "unknown-ext-hardware-cache-result";
perf evsel: Do not access outside hw cache name arrays We have to check if the values are >= *_MAX, not just >, fix it. From the bugzilla report: ''In file /tools/perf/util/evsel.c function __perf_evsel__hw_cache_name it appears that there is a bug that reads beyond the end of the buffer. The statement "if (type > PERF_COUNT_HW_CACHE_MAX)" allows type to be equal to the maximum value. Later, when statement "if (!perf_evsel__is_cache_op_valid(type, op))" is executed, the function can access array perf_evsel__hw_cache_stat[type] beyond the end of the buffer. It appears to me that the statement "if (type > PERF_COUNT_HW_CACHE_MAX)" should be "if (type >= PERF_COUNT_HW_CACHE_MAX)" Bug found with Coverity and manual code review. No attempts were made to execute the code with a maximum type value.'' Committer note: Testing it: $ perf record -e $(echo $(perf list cache | cut -d \[ -f1) | sed 's/ /,/g') usleep 1 [ perf record: Woken up 16 times to write data ] [ perf record: Captured and wrote 0.023 MB perf.data (34 samples) ] $ perf evlist L1-dcache-load-misses L1-dcache-loads L1-dcache-stores L1-icache-load-misses LLC-load-misses LLC-loads LLC-store-misses LLC-stores branch-load-misses branch-loads dTLB-load-misses dTLB-loads dTLB-store-misses dTLB-stores iTLB-load-misses iTLB-loads node-load-misses node-loads node-store-misses node-stores $ perf list cache List of pre-defined events (to be used in -e): L1-dcache-load-misses [Hardware cache event] L1-dcache-loads [Hardware cache event] L1-dcache-stores [Hardware cache event] L1-icache-load-misses [Hardware cache event] LLC-load-misses [Hardware cache event] LLC-loads [Hardware cache event] LLC-store-misses [Hardware cache event] LLC-stores [Hardware cache event] branch-load-misses [Hardware cache event] branch-loads [Hardware cache event] dTLB-load-misses [Hardware cache event] dTLB-loads [Hardware cache event] dTLB-store-misses [Hardware cache event] dTLB-stores [Hardware cache event] iTLB-load-misses [Hardware cache event] iTLB-loads [Hardware cache event] node-load-misses [Hardware cache event] node-loads [Hardware cache event] node-store-misses [Hardware cache event] node-stores [Hardware cache event] $ Reported-by: Brian Sweeney <bsweeney@lgsinnovations.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=153351 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-08-18 19:30:28 +00:00
if (result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
goto out_err;
err = "invalid-cache";
if (!perf_evsel__is_cache_op_valid(type, op))
goto out_err;
return __perf_evsel__hw_cache_type_op_res_name(type, op, result, bf, size);
out_err:
return scnprintf(bf, size, "%s", err);
}
static int perf_evsel__hw_cache_name(struct perf_evsel *evsel, char *bf, size_t size)
{
int ret = __perf_evsel__hw_cache_name(evsel->attr.config, bf, size);
return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
}
static int perf_evsel__raw_name(struct perf_evsel *evsel, char *bf, size_t size)
{
int ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->attr.config);
return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
}
static int perf_evsel__tool_name(char *bf, size_t size)
{
int ret = scnprintf(bf, size, "duration_time");
return ret;
}
const char *perf_evsel__name(struct perf_evsel *evsel)
{
char bf[128];
if (!evsel)
goto out_unknown;
if (evsel->name)
return evsel->name;
switch (evsel->attr.type) {
case PERF_TYPE_RAW:
perf_evsel__raw_name(evsel, bf, sizeof(bf));
break;
case PERF_TYPE_HARDWARE:
perf_evsel__hw_name(evsel, bf, sizeof(bf));
break;
case PERF_TYPE_HW_CACHE:
perf_evsel__hw_cache_name(evsel, bf, sizeof(bf));
break;
case PERF_TYPE_SOFTWARE:
if (evsel->tool_event)
perf_evsel__tool_name(bf, sizeof(bf));
else
perf_evsel__sw_name(evsel, bf, sizeof(bf));
break;
case PERF_TYPE_TRACEPOINT:
scnprintf(bf, sizeof(bf), "%s", "unknown tracepoint");
break;
case PERF_TYPE_BREAKPOINT:
perf_evsel__bp_name(evsel, bf, sizeof(bf));
break;
default:
scnprintf(bf, sizeof(bf), "unknown attr type: %d",
evsel->attr.type);
break;
}
evsel->name = strdup(bf);
if (evsel->name)
return evsel->name;
out_unknown:
return "unknown";
}
const char *perf_evsel__group_name(struct perf_evsel *evsel)
{
return evsel->group_name ?: "anon group";
}
/*
* Returns the group details for the specified leader,
* with following rules.
*
* For record -e '{cycles,instructions}'
* 'anon group { cycles:u, instructions:u }'
*
* For record -e 'cycles,instructions' and report --group
* 'cycles:u, instructions:u'
*/
int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size)
{
int ret = 0;
struct perf_evsel *pos;
const char *group_name = perf_evsel__group_name(evsel);
if (!evsel->forced_leader)
ret = scnprintf(buf, size, "%s { ", group_name);
ret += scnprintf(buf + ret, size - ret, "%s",
perf_evsel__name(evsel));
for_each_group_member(pos, evsel)
ret += scnprintf(buf + ret, size - ret, ", %s",
perf_evsel__name(pos));
if (!evsel->forced_leader)
ret += scnprintf(buf + ret, size - ret, " }");
return ret;
}
static void __perf_evsel__config_callchain(struct perf_evsel *evsel,
struct record_opts *opts,
struct callchain_param *param)
{
bool function = perf_evsel__is_function_event(evsel);
struct perf_event_attr *attr = &evsel->attr;
perf_evsel__set_sample_bit(evsel, CALLCHAIN);
perf tools: Per event max-stack settings The tooling counterpart, now it is possible to do: # perf record -e sched:sched_switch/max-stack=10/ -e cycles/call-graph=dwarf,max-stack=4/ -e cpu-cycles/call-graph=dwarf,max-stack=1024/ usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.052 MB perf.data (5 samples) ] # perf evlist -v sched:sched_switch: type: 2, size: 112, config: 0x110, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CALLCHAIN|CPU|PERIOD|RAW|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, sample_max_stack: 10 cycles/call-graph=dwarf,max-stack=4/: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|PERIOD|REGS_USER|STACK_USER|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, freq: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1, exclude_callchain_user: 1, sample_regs_user: 0xff0fff, sample_stack_user: 8192, sample_max_stack: 4 cpu-cycles/call-graph=dwarf,max-stack=1024/: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|PERIOD|REGS_USER|STACK_USER|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, freq: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1, exclude_callchain_user: 1, sample_regs_user: 0xff0fff, sample_stack_user: 8192, sample_max_stack: 1024 # Tip: use 'perf evlist --trace-fields' to show fields for tracepoint events Using just /max-stack=N/ means /call-graph=fp,max-stack=N/, that should be further configurable by means of some .perfconfig knob. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: He Kuang <hekuang@huawei.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Milian Wolff <milian.wolff@kdab.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: Wang Nan <wangnan0@huawei.com> Cc: Zefan Li <lizefan@huawei.com> Link: http://lkml.kernel.org/n/tip-kolmn1yo40p7jhswxwrc7rrd@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-28 22:03:42 +00:00
attr->sample_max_stack = param->max_stack;
if (opts->kernel_callchains)
attr->exclude_callchain_user = 1;
if (opts->user_callchains)
attr->exclude_callchain_kernel = 1;
if (param->record_mode == CALLCHAIN_LBR) {
perf tools: Enable LBR call stack support Currently, there are two call chain recording options, fp and dwarf. Haswell has a new feature that utilizes the existing LBR facility to record call chains. Kernel side LBR support code provides this as a third option to record call chains. This patch enables the lbr call stack support on the tooling side. LBR call stack has some limitations: - It reuses current LBR facility, so LBR call stack and branch record can not be enabled at the same time. - It is only available for user-space callchains. However, it also offers some advantages: - LBR call stack can work on user apps which don't have frame-pointers or dwarf debug info compiled. It is a good alternative when nothing else works. Tested-by: Jiri Olsa <jolsa@kernel.org> Signed-off-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Cody P Schafer <cody@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Jacob Shin <jacob.w.shin@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masanari Iida <standby24x7@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Rodrigo Campos <rodrigo@sdfg.com.ar> Cc: Stephane Eranian <eranian@google.com> Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1420482185-29830-2-git-send-email-kan.liang@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-05 18:23:04 +00:00
if (!opts->branch_stack) {
if (attr->exclude_user) {
pr_warning("LBR callstack option is only available "
"to get user callchain information. "
"Falling back to framepointers.\n");
} else {
perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
attr->branch_sample_type = PERF_SAMPLE_BRANCH_USER |
PERF_SAMPLE_BRANCH_CALL_STACK |
PERF_SAMPLE_BRANCH_NO_CYCLES |
PERF_SAMPLE_BRANCH_NO_FLAGS;
perf tools: Enable LBR call stack support Currently, there are two call chain recording options, fp and dwarf. Haswell has a new feature that utilizes the existing LBR facility to record call chains. Kernel side LBR support code provides this as a third option to record call chains. This patch enables the lbr call stack support on the tooling side. LBR call stack has some limitations: - It reuses current LBR facility, so LBR call stack and branch record can not be enabled at the same time. - It is only available for user-space callchains. However, it also offers some advantages: - LBR call stack can work on user apps which don't have frame-pointers or dwarf debug info compiled. It is a good alternative when nothing else works. Tested-by: Jiri Olsa <jolsa@kernel.org> Signed-off-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Cody P Schafer <cody@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Jacob Shin <jacob.w.shin@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masanari Iida <standby24x7@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Rodrigo Campos <rodrigo@sdfg.com.ar> Cc: Stephane Eranian <eranian@google.com> Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/1420482185-29830-2-git-send-email-kan.liang@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-05 18:23:04 +00:00
}
} else
pr_warning("Cannot use LBR callstack with branch stack. "
"Falling back to framepointers.\n");
}
if (param->record_mode == CALLCHAIN_DWARF) {
if (!function) {
perf_evsel__set_sample_bit(evsel, REGS_USER);
perf_evsel__set_sample_bit(evsel, STACK_USER);
perf record: Allow mixing --user-regs with --call-graph=dwarf When DWARF stacks were requested and at the same time that the user specifies a register set using the --user-regs option the full register context was being captured on samples: $ perf record -g --call-graph dwarf,1024 --user-regs=IP,SP,BP -- stack_test2.g.O3 188143843893585 0x6b48 [0x4f8]: PERF_RECORD_SAMPLE(IP, 0x4002): 23828/23828: 0x401236 period: 1363819 addr: 0x7ffedbdd51ac ... FP chain: nr:0 ... user regs: mask 0xff0fff ABI 64-bit .... AX 0x53b .... BX 0x7ffedbdd3cc0 .... CX 0xffffffff .... DX 0x33d3a .... SI 0x7f09b74c38d0 .... DI 0x0 .... BP 0x401260 .... SP 0x7ffedbdd3cc0 .... IP 0x401236 .... FLAGS 0x20a .... CS 0x33 .... SS 0x2b .... R8 0x7f09b74c3800 .... R9 0x7f09b74c2da0 .... R10 0xfffffffffffff3ce .... R11 0x246 .... R12 0x401070 .... R13 0x7ffedbdd5db0 .... R14 0x0 .... R15 0x0 ... ustack: size 1024, offset 0xe0 . data_src: 0x5080021 ... thread: stack_test2.g.O:23828 ...... dso: /root/abudanko/stacks/stack_test2.g.O3 I.e. the --user-regs=IP,SP,BP was being ignored, being overridden by the needs of --call-graph=dwarf. After applying the change in this patch the sample data contains the user specified register, but making sure that at least the minimal set of register needed for DWARF unwinding (DWARF_MINIMAL_REGS) is requested. The user is warned that DWARF unwinding may not work if extra registers end up being needed. -g call-graph dwarf,K full_regs --user-regs=user_regs user_regs -g call-graph dwarf,K --user-regs=user_regs user_regs + DWARF_MINIMAL_REGS $ perf record -g --call-graph dwarf,1024 --user-regs=BP -- ls WARNING: The use of --call-graph=dwarf may require all the user registers, specifying a subset with --user-regs may render DWARF unwinding unreliable, so the minimal registers set (IP, SP) is explicitly forced. arch COPYING Documentation include Kbuild lbuild MAINTAINERS modules.builtin Module.symvers perf.data.old scripts System.map virt block CREDITS drivers init Kconfig lib Makefile modules.builtin.modinfo net README security tools vmlinux certs crypto fs ipc kernel LICENSES mm modules.order perf.data samples sound usr vmlinux.o [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.030 MB perf.data (10 samples) ] 188368474305373 0x5e40 [0x470]: PERF_RECORD_SAMPLE(IP, 0x4002): 23839/23839: 0x401236 period: 1260507 addr: 0x7ffd3d85e96c ... FP chain: nr:0 ... user regs: mask 0x1c0 ABI 64-bit .... BP 0x401260 .... SP 0x7ffd3d85cc20 .... IP 0x401236 ... ustack: size 1024, offset 0x58 . data_src: 0x5080021 Committer notes: Detected build failures on arches where PERF_REGS_ is not available, such as debian:experimental-x-{mips,mips64,mipsel}, fedora 24 and 30 for ARC uClibc and glibc, reported to Alexey that provided a patch moving the DWARF_MINIMAL_REGS from evsel.c to util/perf_regs.h, where it is guarded by an HAVE_PERF_REGS_SUPPORT ifdef. Committer testing: # perf record --user-regs=bp,ax -a sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 1.955 MB perf.data (1773 samples) ] # perf script -F+uregs | grep AX: | head -5 perf 1719 [000] 181.272398: 1 cycles: ffffffffba06a7c4 native_write_msr+0x4 (/lib/modules/5.2.0-rc1+/build/vmlinux) ABI:2 AX:0xffffffffffffffda BP:0x7ffef828fb00 perf 1719 [000] 181.272402: 1 cycles: ffffffffba06a7c4 native_write_msr+0x4 (/lib/modules/5.2.0-rc1+/build/vmlinux) ABI:2 AX:0xffffffffffffffda BP:0x7ffef828fb00 perf 1719 [000] 181.272403: 8 cycles: ffffffffba06a7c4 native_write_msr+0x4 (/lib/modules/5.2.0-rc1+/build/vmlinux) ABI:2 AX:0xffffffffffffffda BP:0x7ffef828fb00 perf 1719 [000] 181.272405: 181 cycles: ffffffffba06a7c6 native_write_msr+0x6 (/lib/modules/5.2.0-rc1+/build/vmlinux) ABI:2 AX:0xffffffffffffffda BP:0x7ffef828fb00 perf 1719 [000] 181.272406: 4405 cycles: ffffffffba06a7c4 native_write_msr+0x4 (/lib/modules/5.2.0-rc1+/build/vmlinux) ABI:2 AX:0xffffffffffffffda BP:0x7ffef828fb00 # perf record --call-graph=dwarf --user-regs=bp,ax -a sleep 1 WARNING: The use of --call-graph=dwarf may require all the user registers, specifying a subset with --user-regs may render DWARF unwinding unreliable, so the minimal registers set (IP, SP) is explicitly forced. [ perf record: Woken up 55 times to write data ] [ perf record: Captured and wrote 24.184 MB perf.data (2841 samples) ] [root@quaco ~]# perf script --hide-call-graph -F+uregs | grep AX: | head -5 perf 1729 [000] 211.268006: 1 cycles: ffffffffba06a7c4 native_write_msr+0x4 (/lib/modules/5.2.0-rc1+/build/vmlinux) ABI:2 AX:0xffffffffffffffda BP:0x7ffc8679abb0 SP:0x7ffc8679ab78 IP:0x7fa75223a0db perf 1729 [000] 211.268014: 1 cycles: ffffffffba06a7c4 native_write_msr+0x4 (/lib/modules/5.2.0-rc1+/build/vmlinux) ABI:2 AX:0xffffffffffffffda BP:0x7ffc8679abb0 SP:0x7ffc8679ab78 IP:0x7fa75223a0db perf 1729 [000] 211.268017: 5 cycles: ffffffffba06a7c4 native_write_msr+0x4 (/lib/modules/5.2.0-rc1+/build/vmlinux) ABI:2 AX:0xffffffffffffffda BP:0x7ffc8679abb0 SP:0x7ffc8679ab78 IP:0x7fa75223a0db perf 1729 [000] 211.268020: 48 cycles: ffffffffba06a7c6 native_write_msr+0x6 (/lib/modules/5.2.0-rc1+/build/vmlinux) ABI:2 AX:0xffffffffffffffda BP:0x7ffc8679abb0 SP:0x7ffc8679ab78 IP:0x7fa75223a0db perf 1729 [000] 211.268024: 490 cycles: ffffffffba00e471 intel_bts_enable_local+0x21 (/lib/modules/5.2.0-rc1+/build/vmlinux) ABI:2 AX:0xffffffffffffffda BP:0x7ffc8679abb0 SP:0x7ffc8679ab78 IP:0x7fa75223a0db # Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.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: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/e7fd37b1-af22-0d94-a0dc-5895e803bbfe@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-05-30 19:03:36 +00:00
if (opts->sample_user_regs && DWARF_MINIMAL_REGS != PERF_REGS_MASK) {
attr->sample_regs_user |= DWARF_MINIMAL_REGS;
pr_warning("WARNING: The use of --call-graph=dwarf may require all the user registers, "
"specifying a subset with --user-regs may render DWARF unwinding unreliable, "
"so the minimal registers set (IP, SP) is explicitly forced.\n");
} else {
attr->sample_regs_user |= PERF_REGS_MASK;
}
attr->sample_stack_user = param->dump_size;
attr->exclude_callchain_user = 1;
} else {
pr_info("Cannot use DWARF unwind for function trace event,"
" falling back to framepointers.\n");
}
}
if (function) {
pr_info("Disabling user space callchains for function trace event.\n");
attr->exclude_callchain_user = 1;
}
}
void perf_evsel__config_callchain(struct perf_evsel *evsel,
struct record_opts *opts,
struct callchain_param *param)
{
if (param->enabled)
return __perf_evsel__config_callchain(evsel, opts, param);
}
static void
perf_evsel__reset_callgraph(struct perf_evsel *evsel,
struct callchain_param *param)
{
struct perf_event_attr *attr = &evsel->attr;
perf_evsel__reset_sample_bit(evsel, CALLCHAIN);
if (param->record_mode == CALLCHAIN_LBR) {
perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
attr->branch_sample_type &= ~(PERF_SAMPLE_BRANCH_USER |
PERF_SAMPLE_BRANCH_CALL_STACK);
}
if (param->record_mode == CALLCHAIN_DWARF) {
perf_evsel__reset_sample_bit(evsel, REGS_USER);
perf_evsel__reset_sample_bit(evsel, STACK_USER);
}
}
static void apply_config_terms(struct perf_evsel *evsel,
struct record_opts *opts, bool track)
{
struct perf_evsel_config_term *term;
struct list_head *config_terms = &evsel->config_terms;
struct perf_event_attr *attr = &evsel->attr;
perf callchain: Fix attr.sample_max_stack setting When setting the "dwarf" unwinder for a specific event and not specifying the max-stack, the attr.sample_max_stack ended up using an uninitialized callchain_param.max_stack, fix it by using designated initializers for that callchain_param variable, zeroing all non explicitely initialized struct members. Here is what happened: # perf trace -vv --no-syscalls --max-stack 4 -e probe_libc:inet_pton/call-graph=dwarf/ ping -6 -c 1 ::1 callchain: type DWARF callchain: stack dump size 8192 perf_event_attr: type 2 size 112 config 0x730 { sample_period, sample_freq } 1 sample_type IP|TID|TIME|ADDR|CALLCHAIN|CPU|PERIOD|RAW|REGS_USER|STACK_USER|DATA_SRC exclude_callchain_user 1 { wakeup_events, wakeup_watermark } 1 sample_regs_user 0xff0fff sample_stack_user 8192 sample_max_stack 50656 sys_perf_event_open failed, error -75 Value too large for defined data type # perf trace -vv --no-syscalls --max-stack 4 -e probe_libc:inet_pton/call-graph=dwarf/ ping -6 -c 1 ::1 callchain: type DWARF callchain: stack dump size 8192 perf_event_attr: type 2 size 112 config 0x730 sample_type IP|TID|TIME|ADDR|CALLCHAIN|CPU|PERIOD|RAW|REGS_USER|STACK_USER|DATA_SRC exclude_callchain_user 1 sample_regs_user 0xff0fff sample_stack_user 8192 sample_max_stack 30448 sys_perf_event_open failed, error -75 Value too large for defined data type # Now the attr.sample_max_stack is set to zero and the above works as expected: # perf trace --no-syscalls --max-stack 4 -e probe_libc:inet_pton/call-graph=dwarf/ ping -6 -c 1 ::1 PING ::1(::1) 56 data bytes 64 bytes from ::1: icmp_seq=1 ttl=64 time=0.072 ms --- ::1 ping statistics --- 1 packets transmitted, 1 received, 0% packet loss, time 0ms rtt min/avg/max/mdev = 0.072/0.072/0.072/0.000 ms 0.000 probe_libc:inet_pton:(7feb7a998350)) __inet_pton (inlined) gaih_inet.constprop.7 (/usr/lib64/libc-2.26.so) __GI_getaddrinfo (inlined) [0xffffaa39b6108f3f] (/usr/bin/ping) # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Hendrick Brueckner <brueckner@linux.vnet.ibm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Thomas Richter <tmricht@linux.vnet.ibm.com> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-is9tramondqa9jlxxsgcm9iz@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-01-15 14:07:58 +00:00
/* callgraph default */
struct callchain_param param = {
.record_mode = callchain_param.record_mode,
};
u32 dump_size = 0;
perf tools: Per event max-stack settings The tooling counterpart, now it is possible to do: # perf record -e sched:sched_switch/max-stack=10/ -e cycles/call-graph=dwarf,max-stack=4/ -e cpu-cycles/call-graph=dwarf,max-stack=1024/ usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.052 MB perf.data (5 samples) ] # perf evlist -v sched:sched_switch: type: 2, size: 112, config: 0x110, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CALLCHAIN|CPU|PERIOD|RAW|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, sample_max_stack: 10 cycles/call-graph=dwarf,max-stack=4/: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|PERIOD|REGS_USER|STACK_USER|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, freq: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1, exclude_callchain_user: 1, sample_regs_user: 0xff0fff, sample_stack_user: 8192, sample_max_stack: 4 cpu-cycles/call-graph=dwarf,max-stack=1024/: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|PERIOD|REGS_USER|STACK_USER|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, freq: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1, exclude_callchain_user: 1, sample_regs_user: 0xff0fff, sample_stack_user: 8192, sample_max_stack: 1024 # Tip: use 'perf evlist --trace-fields' to show fields for tracepoint events Using just /max-stack=N/ means /call-graph=fp,max-stack=N/, that should be further configurable by means of some .perfconfig knob. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: He Kuang <hekuang@huawei.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Milian Wolff <milian.wolff@kdab.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: Wang Nan <wangnan0@huawei.com> Cc: Zefan Li <lizefan@huawei.com> Link: http://lkml.kernel.org/n/tip-kolmn1yo40p7jhswxwrc7rrd@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-28 22:03:42 +00:00
int max_stack = 0;
const char *callgraph_buf = NULL;
list_for_each_entry(term, config_terms, list) {
switch (term->type) {
case PERF_EVSEL__CONFIG_TERM_PERIOD:
if (!(term->weak && opts->user_interval != ULLONG_MAX)) {
attr->sample_period = term->val.period;
attr->freq = 0;
perf_evsel__reset_sample_bit(evsel, PERIOD);
}
break;
case PERF_EVSEL__CONFIG_TERM_FREQ:
if (!(term->weak && opts->user_freq != UINT_MAX)) {
attr->sample_freq = term->val.freq;
attr->freq = 1;
perf_evsel__set_sample_bit(evsel, PERIOD);
}
break;
case PERF_EVSEL__CONFIG_TERM_TIME:
if (term->val.time)
perf_evsel__set_sample_bit(evsel, TIME);
else
perf_evsel__reset_sample_bit(evsel, TIME);
break;
case PERF_EVSEL__CONFIG_TERM_CALLGRAPH:
callgraph_buf = term->val.callgraph;
break;
case PERF_EVSEL__CONFIG_TERM_BRANCH:
if (term->val.branch && strcmp(term->val.branch, "no")) {
perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
parse_branch_str(term->val.branch,
&attr->branch_sample_type);
} else
perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
break;
case PERF_EVSEL__CONFIG_TERM_STACK_USER:
dump_size = term->val.stack_user;
break;
perf tools: Per event max-stack settings The tooling counterpart, now it is possible to do: # perf record -e sched:sched_switch/max-stack=10/ -e cycles/call-graph=dwarf,max-stack=4/ -e cpu-cycles/call-graph=dwarf,max-stack=1024/ usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.052 MB perf.data (5 samples) ] # perf evlist -v sched:sched_switch: type: 2, size: 112, config: 0x110, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CALLCHAIN|CPU|PERIOD|RAW|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, sample_max_stack: 10 cycles/call-graph=dwarf,max-stack=4/: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|PERIOD|REGS_USER|STACK_USER|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, freq: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1, exclude_callchain_user: 1, sample_regs_user: 0xff0fff, sample_stack_user: 8192, sample_max_stack: 4 cpu-cycles/call-graph=dwarf,max-stack=1024/: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|PERIOD|REGS_USER|STACK_USER|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, freq: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1, exclude_callchain_user: 1, sample_regs_user: 0xff0fff, sample_stack_user: 8192, sample_max_stack: 1024 # Tip: use 'perf evlist --trace-fields' to show fields for tracepoint events Using just /max-stack=N/ means /call-graph=fp,max-stack=N/, that should be further configurable by means of some .perfconfig knob. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: He Kuang <hekuang@huawei.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Milian Wolff <milian.wolff@kdab.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: Wang Nan <wangnan0@huawei.com> Cc: Zefan Li <lizefan@huawei.com> Link: http://lkml.kernel.org/n/tip-kolmn1yo40p7jhswxwrc7rrd@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-28 22:03:42 +00:00
case PERF_EVSEL__CONFIG_TERM_MAX_STACK:
max_stack = term->val.max_stack;
break;
perf evsel: Introduce per event max_events property This simply adds the field to 'struct perf_evsel' and allows setting it via the event parser, to test it lets trace trace: First look at where in a function that receives an evsel we can put a probe to read how evsel->max_events was setup: # perf probe -x ~/bin/perf -L trace__event_handler <trace__event_handler@/home/acme/git/perf/tools/perf/builtin-trace.c:0> 0 static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel, union perf_event *event __maybe_unused, struct perf_sample *sample) 3 { 4 struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid); 5 int callchain_ret = 0; 7 if (sample->callchain) { 8 callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor); 9 if (callchain_ret == 0) { 10 if (callchain_cursor.nr < trace->min_stack) 11 goto out; 12 callchain_ret = 1; } } See what variables we can probe at line 7: # perf probe -x ~/bin/perf -V trace__event_handler:7 Available variables at trace__event_handler:7 @<trace__event_handler+89> int callchain_ret struct perf_evsel* evsel struct perf_sample* sample struct thread* thread struct trace* trace union perf_event* event Add a probe at that line asking for evsel->max_events to be collected and named as "max_events": # perf probe -x ~/bin/perf trace__event_handler:7 'max_events=evsel->max_events' Added new event: probe_perf:trace__event_handler (on trace__event_handler:7 in /home/acme/bin/perf with max_events=evsel->max_events) You can now use it in all perf tools, such as: perf record -e probe_perf:trace__event_handler -aR sleep 1 Now use 'perf trace', here aliased to just 'trace' and trace trace, i.e. the first 'trace' is tracing just that 'probe_perf:trace__event_handler' event, while the traced trace is tracing all scheduler tracepoints, will stop at two events (--max-events 2) and will just set evsel->max_events for all the sched tracepoints to 9, we will see the output of both traces intermixed: # trace -e *perf:*event_handler trace --max-events 2 -e sched:*/nr=9/ 0.000 :0/0 sched:sched_waking:comm=rcu_sched pid=10 prio=120 target_cpu=000 0.009 :0/0 sched:sched_wakeup:comm=rcu_sched pid=10 prio=120 target_cpu=000 0.000 trace/23949 probe_perf:trace__event_handler:(48c34a) max_events=0x9 0.046 trace/23949 probe_perf:trace__event_handler:(48c34a) max_events=0x9 # Now, if the traced trace sends its output to /dev/null, we'll see just what the first level trace outputs: that evsel->max_events is indeed being set to 9: # trace -e *perf:*event_handler trace -o /dev/null --max-events 2 -e sched:*/nr=9/ 0.000 trace/23961 probe_perf:trace__event_handler:(48c34a) max_events=0x9 0.030 trace/23961 probe_perf:trace__event_handler:(48c34a) max_events=0x9 # Now that we can set evsel->max_events, we can go to the next step, honour that per-event property in 'perf trace'. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Milian Wolff <milian.wolff@kdab.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: https://lkml.kernel.org/n/tip-og00yasj276joem6e14l1eas@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-10-19 18:47:34 +00:00
case PERF_EVSEL__CONFIG_TERM_MAX_EVENTS:
evsel->max_events = term->val.max_events;
break;
perf tools: Enable pre-event inherit setting by config terms This patch allows perf record setting event's attr.inherit bit by config terms like: # perf record -e cycles/no-inherit/ ... # perf record -e cycles/inherit/ ... So user can control inherit bit for each event separately. In following example, a.out fork()s in main then do some complex CPU intensive computations in both of its children. Basic result with and without inherit: # perf record -e cycles -e instructions ./a.out [ perf record: Woken up 9 times to write data ] [ perf record: Captured and wrote 2.205 MB perf.data (47920 samples) ] # perf report --stdio # ... # Samples: 23K of event 'cycles' # Event count (approx.): 23641752891 ... # Samples: 24K of event 'instructions' # Event count (approx.): 30428312415 # perf record -i -e cycles -e instructions ./a.out [ perf record: Woken up 5 times to write data ] [ perf record: Captured and wrote 1.111 MB perf.data (24019 samples) ] ... # Samples: 12K of event 'cycles' # Event count (approx.): 11699501775 ... # Samples: 12K of event 'instructions' # Event count (approx.): 15058023559 Cancel inherit for one event when globally enable: # perf record -e cycles/no-inherit/ -e instructions ./a.out [ perf record: Woken up 7 times to write data ] [ perf record: Captured and wrote 1.660 MB perf.data (36004 samples) ] ... # Samples: 12K of event 'cycles/no-inherit/' # Event count (approx.): 11895759282 ... # Samples: 24K of event 'instructions' # Event count (approx.): 30668000441 Enable inherit for one event when globally disable: # perf record -i -e cycles/inherit/ -e instructions ./a.out [ perf record: Woken up 7 times to write data ] [ perf record: Captured and wrote 1.654 MB perf.data (35868 samples) ] ... # Samples: 23K of event 'cycles/inherit/' # Event count (approx.): 23285400229 ... # Samples: 11K of event 'instructions' # Event count (approx.): 14969050259 Committer note: One can check if the bit was set, in addition to seeing the result in the perf.data file size as above by doing one of: # perf record -e cycles -e instructions -a usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.911 MB perf.data (63 samples) ] # perf evlist -v cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ID|CPU|PERIOD, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 instructions: size: 112, config: 0x1, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ID|CPU|PERIOD, read_format: ID, disabled: 1, inherit: 1, freq: 1, sample_id_all: 1, exclude_guest: 1 # So, the inherit bit was set in both, now, if we disable it globally using --no-inherit: # perf record --no-inherit -e cycles -e instructions -a usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.910 MB perf.data (56 samples) ] # perf evlist -v cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ID|CPU|PERIOD, read_format: ID, disabled: 1, mmap: 1, comm: 1, freq: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 instructions: size: 112, config: 0x1, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ID|CPU|PERIOD, read_format: ID, disabled: 1, freq: 1, sample_id_all: 1, exclude_guest: 1 No inherit bit set, then disabling it and setting just on the cycles event: # perf record --no-inherit -e cycles/inherit/ -e instructions -a usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.909 MB perf.data (48 samples) ] # perf evlist -v cycles/inherit/: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ID|CPU|PERIOD, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 instructions: size: 112, config: 0x1, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ID|CPU|PERIOD, read_format: ID, disabled: 1, freq: 1, sample_id_all: 1, exclude_guest: 1 # We can see it as well in by using a more verbose level of debug messages in the tool that sets up the perf_event_attr, 'perf record' in this case: [root@zoo ~]# perf record -vv --no-inherit -e cycles/inherit/ -e instructions -a usleep 1 ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|ID|CPU|PERIOD read_format ID disabled 1 inherit 1 mmap 1 comm 1 freq 1 task 1 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ------------------------------------------------------------ sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8 sys_perf_event_open: pid -1 cpu 1 group_fd -1 flags 0x8 sys_perf_event_open: pid -1 cpu 2 group_fd -1 flags 0x8 sys_perf_event_open: pid -1 cpu 3 group_fd -1 flags 0x8 ------------------------------------------------------------ perf_event_attr: size 112 config 0x1 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|ID|CPU|PERIOD read_format ID disabled 1 freq 1 sample_id_all 1 exclude_guest 1 ------------------------------------------------------------ sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8 <SNIP> Signed-off-by: Wang Nan <wangnan0@huawei.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexei Starovoitov <ast@plumgrid.com> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: David S. Miller <davem@davemloft.net> Cc: Li Zefan <lizefan@huawei.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1446029705-199659-2-git-send-email-wangnan0@huawei.com [ s/u64/bool/ for the perf_evsel_config_term inherit field - jolsa] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-10-28 10:55:02 +00:00
case PERF_EVSEL__CONFIG_TERM_INHERIT:
/*
* attr->inherit should has already been set by
* perf_evsel__config. If user explicitly set
* inherit using config terms, override global
* opt->no_inherit setting.
*/
attr->inherit = term->val.inherit ? 1 : 0;
break;
perf tools: Enable overwrite settings This patch allows following config terms and option: Globally setting events to overwrite; # perf record --overwrite ... Set specific events to be overwrite or no-overwrite. # perf record --event cycles/overwrite/ ... # perf record --event cycles/no-overwrite/ ... Add missing config terms and update the config term array size because the longest string length has changed. For overwritable events, it automatically selects attr.write_backward since perf requires it to be backward for reading. Test result: # perf record --overwrite -e syscalls:*enter_nanosleep* usleep 1 [ perf record: Woken up 2 times to write data ] [ perf record: Captured and wrote 0.011 MB perf.data (1 samples) ] # perf evlist -v syscalls:sys_enter_nanosleep: type: 2, size: 112, config: 0x134, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CPU|PERIOD|RAW, disabled: 1, inherit: 1, mmap: 1, comm: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, write_backward: 1 # Tip: use 'perf evlist --trace-fields' to show fields for tracepoint events Signed-off-by: Wang Nan <wangnan0@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Nilay Vaish <nilayvaish@gmail.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1468485287-33422-14-git-send-email-wangnan0@huawei.com Signed-off-by: He Kuang <hekuang@huawei.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-07-14 08:34:45 +00:00
case PERF_EVSEL__CONFIG_TERM_OVERWRITE:
attr->write_backward = term->val.overwrite ? 1 : 0;
break;
case PERF_EVSEL__CONFIG_TERM_DRV_CFG:
break;
case PERF_EVSEL__CONFIG_TERM_PERCORE:
break;
default:
break;
}
}
/* User explicitly set per-event callgraph, clear the old setting and reset. */
perf tools: Per event max-stack settings The tooling counterpart, now it is possible to do: # perf record -e sched:sched_switch/max-stack=10/ -e cycles/call-graph=dwarf,max-stack=4/ -e cpu-cycles/call-graph=dwarf,max-stack=1024/ usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.052 MB perf.data (5 samples) ] # perf evlist -v sched:sched_switch: type: 2, size: 112, config: 0x110, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CALLCHAIN|CPU|PERIOD|RAW|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, sample_max_stack: 10 cycles/call-graph=dwarf,max-stack=4/: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|PERIOD|REGS_USER|STACK_USER|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, freq: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1, exclude_callchain_user: 1, sample_regs_user: 0xff0fff, sample_stack_user: 8192, sample_max_stack: 4 cpu-cycles/call-graph=dwarf,max-stack=1024/: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|PERIOD|REGS_USER|STACK_USER|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, freq: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1, exclude_callchain_user: 1, sample_regs_user: 0xff0fff, sample_stack_user: 8192, sample_max_stack: 1024 # Tip: use 'perf evlist --trace-fields' to show fields for tracepoint events Using just /max-stack=N/ means /call-graph=fp,max-stack=N/, that should be further configurable by means of some .perfconfig knob. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: He Kuang <hekuang@huawei.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Milian Wolff <milian.wolff@kdab.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: Wang Nan <wangnan0@huawei.com> Cc: Zefan Li <lizefan@huawei.com> Link: http://lkml.kernel.org/n/tip-kolmn1yo40p7jhswxwrc7rrd@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-28 22:03:42 +00:00
if ((callgraph_buf != NULL) || (dump_size > 0) || max_stack) {
bool sample_address = false;
perf tools: Per event max-stack settings The tooling counterpart, now it is possible to do: # perf record -e sched:sched_switch/max-stack=10/ -e cycles/call-graph=dwarf,max-stack=4/ -e cpu-cycles/call-graph=dwarf,max-stack=1024/ usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.052 MB perf.data (5 samples) ] # perf evlist -v sched:sched_switch: type: 2, size: 112, config: 0x110, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CALLCHAIN|CPU|PERIOD|RAW|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, sample_max_stack: 10 cycles/call-graph=dwarf,max-stack=4/: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|PERIOD|REGS_USER|STACK_USER|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, freq: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1, exclude_callchain_user: 1, sample_regs_user: 0xff0fff, sample_stack_user: 8192, sample_max_stack: 4 cpu-cycles/call-graph=dwarf,max-stack=1024/: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|PERIOD|REGS_USER|STACK_USER|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, freq: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1, exclude_callchain_user: 1, sample_regs_user: 0xff0fff, sample_stack_user: 8192, sample_max_stack: 1024 # Tip: use 'perf evlist --trace-fields' to show fields for tracepoint events Using just /max-stack=N/ means /call-graph=fp,max-stack=N/, that should be further configurable by means of some .perfconfig knob. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: He Kuang <hekuang@huawei.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Milian Wolff <milian.wolff@kdab.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: Wang Nan <wangnan0@huawei.com> Cc: Zefan Li <lizefan@huawei.com> Link: http://lkml.kernel.org/n/tip-kolmn1yo40p7jhswxwrc7rrd@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-28 22:03:42 +00:00
if (max_stack) {
param.max_stack = max_stack;
if (callgraph_buf == NULL)
callgraph_buf = "fp";
}
/* parse callgraph parameters */
if (callgraph_buf != NULL) {
perf callchain: Allow disabling call graphs per event This patch introduce "call-graph=no" to disable per-event callgraph. Here is an example. perf record -e 'cpu/cpu-cycles,call-graph=fp/,cpu/instructions,call-graph=no/' sleep 1 perf report --stdio # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 6 of event 'cpu/cpu-cycles,call-graph=fp/' # Event count (approx.): 774218 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................ ........................................ # 61.94% 0.00% sleep [kernel.vmlinux] [k] entry_SYSCALL_64_fastpath | ---entry_SYSCALL_64_fastpath | |--97.30%-- __brk | --2.70%-- mmap64 _dl_check_map_versions _dl_check_all_versions 61.94% 0.00% sleep [kernel.vmlinux] [k] perf_event_mmap | ---perf_event_mmap | |--97.30%-- do_brk | sys_brk | entry_SYSCALL_64_fastpath | __brk | --2.70%-- mmap_region do_mmap_pgoff vm_mmap_pgoff sys_mmap_pgoff sys_mmap entry_SYSCALL_64_fastpath mmap64 _dl_check_map_versions _dl_check_all_versions ...... # Samples: 6 of event 'cpu/instructions,call-graph=no/' # Event count (approx.): 359692 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................ ................................. # 89.03% 0.00% sleep [unknown] [.] 0xffff6598ffff6598 89.03% 0.00% sleep ld-2.17.so [.] _dl_resolve_conflicts 89.03% 0.00% sleep [kernel.vmlinux] [k] page_fault Signed-off-by: Kan Liang <kan.liang@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/1439289050-40510-2-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-11 10:30:48 +00:00
if (!strcmp(callgraph_buf, "no")) {
param.enabled = false;
param.record_mode = CALLCHAIN_NONE;
} else {
param.enabled = true;
if (parse_callchain_record(callgraph_buf, &param)) {
pr_err("per-event callgraph setting for %s failed. "
"Apply callgraph global setting for it\n",
evsel->name);
return;
}
if (param.record_mode == CALLCHAIN_DWARF)
sample_address = true;
}
}
if (dump_size > 0) {
dump_size = round_up(dump_size, sizeof(u64));
param.dump_size = dump_size;
}
/* If global callgraph set, clear it */
if (callchain_param.enabled)
perf_evsel__reset_callgraph(evsel, &callchain_param);
/* set perf-event callgraph */
if (param.enabled) {
if (sample_address) {
perf_evsel__set_sample_bit(evsel, ADDR);
perf_evsel__set_sample_bit(evsel, DATA_SRC);
evsel->attr.mmap_data = track;
}
perf_evsel__config_callchain(evsel, opts, &param);
}
}
}
static bool is_dummy_event(struct perf_evsel *evsel)
{
return (evsel->attr.type == PERF_TYPE_SOFTWARE) &&
(evsel->attr.config == PERF_COUNT_SW_DUMMY);
}
perf tools: Fix 'disabled' attribute config for record command Currently the record command sets all events initially as disabled. There's non conditional perf_evlist__enable call, that enables all events before we exec tracee program. That actually screws whole enable_on_exec logic, because the event is enabled before the traced program got executed. What we actually want is: 1) For any type of traced program: - all independent events and group leaders are disabled - all group members are enabled Group members are ruled by group leaders. They need to be enabled, because the group scheduling relies on that. 2) For traced programs executed by perf: - all independent events and group leaders have enable_on_exec set - we don't specifically enable or disable any event during the record command Independent events and group leaders are initially disabled and get enabled by exec. Group members are ruled by group leaders as stated in 1). 3) For traced programs attached by perf (pid/tid): - we specifically enable or disable all events during the record command When attaching events to already running traced we enable/disable events specifically, as there's no initial traced exec call. Fixing appropriate perf_event_attr test case to cover this change. Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1352741644-16809-3-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-11-12 17:34:01 +00:00
/*
* The enable_on_exec/disabled value strategy:
*
* 1) For any type of traced program:
* - all independent events and group leaders are disabled
* - all group members are enabled
*
* Group members are ruled by group leaders. They need to
* be enabled, because the group scheduling relies on that.
*
* 2) For traced programs executed by perf:
* - all independent events and group leaders have
* enable_on_exec set
* - we don't specifically enable or disable any event during
* the record command
*
* Independent events and group leaders are initially disabled
* and get enabled by exec. Group members are ruled by group
* leaders as stated in 1).
*
* 3) For traced programs attached by perf (pid/tid):
* - we specifically enable or disable all events during
* the record command
*
* When attaching events to already running traced we
* enable/disable events specifically, as there's no
* initial traced exec call.
*/
void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
struct callchain_param *callchain)
{
perf tools: Add 'S' event/group modifier to read sample value Adding 'S' event/group modifier to specify that the event value/s are read by PERF_SAMPLE_READ sample type processing, instead of the period value offered by lower layers. There's additional behaviour change for 'S' modifier being specified on event group: Currently all the events within a group makes samples. If user now specifies 'S' within group modifier, only the leader will trigger samples. The rest of events in the group will have sampling disabled. And same as for single events, values of all events within the group (including leader) are read by PERF_SAMPLE_READ sample type processing. Following example will create event group with cycles and cache-misses events, setting the cycles as group leader and the only event to actually sample. Both cycles and cache-misses event period values are read by PERF_SAMPLE_READ sample type processing with PERF_FORMAT_GROUP read format. Example: $ perf record -e '{cycles,cache-misses}:S' ls ... $ perf report --group --show-total-period --stdio ... # Samples: 36 of event 'anon group { cycles, cache-misses }' # Event count (approx.): 12585593 # # Overhead Period Command Shared Object Symbol # .............. .............. ....... ................. .......................... # 19.92% 1.20% 2505936 31 ls [kernel.kallsyms] [k] mark_held_locks 13.74% 0.47% 1729327 12 ls [kernel.kallsyms] [k] sched_clock_local 13.64% 23.72% 1716147 612 ls ld-2.14.90.so [.] check_match.10805 13.12% 23.22% 1650778 599 ls libc-2.14.90.so [.] _nl_intern_locale_data 11.24% 29.19% 1414554 753 ls [kernel.kallsyms] [k] sched_clock_cpu 8.50% 0.35% 1070150 9 ls [kernel.kallsyms] [k] check_chain_key ... Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/n/tip-iyoinu3axi11mymwnh2b7fxj@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-10 15:39:03 +00:00
struct perf_evsel *leader = evsel->leader;
struct perf_event_attr *attr = &evsel->attr;
int track = evsel->tracking;
bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread;
attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1;
attr->inherit = !opts->no_inherit;
perf tools: Enable overwrite settings This patch allows following config terms and option: Globally setting events to overwrite; # perf record --overwrite ... Set specific events to be overwrite or no-overwrite. # perf record --event cycles/overwrite/ ... # perf record --event cycles/no-overwrite/ ... Add missing config terms and update the config term array size because the longest string length has changed. For overwritable events, it automatically selects attr.write_backward since perf requires it to be backward for reading. Test result: # perf record --overwrite -e syscalls:*enter_nanosleep* usleep 1 [ perf record: Woken up 2 times to write data ] [ perf record: Captured and wrote 0.011 MB perf.data (1 samples) ] # perf evlist -v syscalls:sys_enter_nanosleep: type: 2, size: 112, config: 0x134, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CPU|PERIOD|RAW, disabled: 1, inherit: 1, mmap: 1, comm: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, write_backward: 1 # Tip: use 'perf evlist --trace-fields' to show fields for tracepoint events Signed-off-by: Wang Nan <wangnan0@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Nilay Vaish <nilayvaish@gmail.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1468485287-33422-14-git-send-email-wangnan0@huawei.com Signed-off-by: He Kuang <hekuang@huawei.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-07-14 08:34:45 +00:00
attr->write_backward = opts->overwrite ? 1 : 0;
perf_evsel__set_sample_bit(evsel, IP);
perf_evsel__set_sample_bit(evsel, TID);
perf tools: Add 'S' event/group modifier to read sample value Adding 'S' event/group modifier to specify that the event value/s are read by PERF_SAMPLE_READ sample type processing, instead of the period value offered by lower layers. There's additional behaviour change for 'S' modifier being specified on event group: Currently all the events within a group makes samples. If user now specifies 'S' within group modifier, only the leader will trigger samples. The rest of events in the group will have sampling disabled. And same as for single events, values of all events within the group (including leader) are read by PERF_SAMPLE_READ sample type processing. Following example will create event group with cycles and cache-misses events, setting the cycles as group leader and the only event to actually sample. Both cycles and cache-misses event period values are read by PERF_SAMPLE_READ sample type processing with PERF_FORMAT_GROUP read format. Example: $ perf record -e '{cycles,cache-misses}:S' ls ... $ perf report --group --show-total-period --stdio ... # Samples: 36 of event 'anon group { cycles, cache-misses }' # Event count (approx.): 12585593 # # Overhead Period Command Shared Object Symbol # .............. .............. ....... ................. .......................... # 19.92% 1.20% 2505936 31 ls [kernel.kallsyms] [k] mark_held_locks 13.74% 0.47% 1729327 12 ls [kernel.kallsyms] [k] sched_clock_local 13.64% 23.72% 1716147 612 ls ld-2.14.90.so [.] check_match.10805 13.12% 23.22% 1650778 599 ls libc-2.14.90.so [.] _nl_intern_locale_data 11.24% 29.19% 1414554 753 ls [kernel.kallsyms] [k] sched_clock_cpu 8.50% 0.35% 1070150 9 ls [kernel.kallsyms] [k] check_chain_key ... Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/n/tip-iyoinu3axi11mymwnh2b7fxj@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-10 15:39:03 +00:00
if (evsel->sample_read) {
perf_evsel__set_sample_bit(evsel, READ);
/*
* We need ID even in case of single event, because
* PERF_SAMPLE_READ process ID specific data.
*/
perf_evsel__set_sample_id(evsel, false);
perf tools: Add 'S' event/group modifier to read sample value Adding 'S' event/group modifier to specify that the event value/s are read by PERF_SAMPLE_READ sample type processing, instead of the period value offered by lower layers. There's additional behaviour change for 'S' modifier being specified on event group: Currently all the events within a group makes samples. If user now specifies 'S' within group modifier, only the leader will trigger samples. The rest of events in the group will have sampling disabled. And same as for single events, values of all events within the group (including leader) are read by PERF_SAMPLE_READ sample type processing. Following example will create event group with cycles and cache-misses events, setting the cycles as group leader and the only event to actually sample. Both cycles and cache-misses event period values are read by PERF_SAMPLE_READ sample type processing with PERF_FORMAT_GROUP read format. Example: $ perf record -e '{cycles,cache-misses}:S' ls ... $ perf report --group --show-total-period --stdio ... # Samples: 36 of event 'anon group { cycles, cache-misses }' # Event count (approx.): 12585593 # # Overhead Period Command Shared Object Symbol # .............. .............. ....... ................. .......................... # 19.92% 1.20% 2505936 31 ls [kernel.kallsyms] [k] mark_held_locks 13.74% 0.47% 1729327 12 ls [kernel.kallsyms] [k] sched_clock_local 13.64% 23.72% 1716147 612 ls ld-2.14.90.so [.] check_match.10805 13.12% 23.22% 1650778 599 ls libc-2.14.90.so [.] _nl_intern_locale_data 11.24% 29.19% 1414554 753 ls [kernel.kallsyms] [k] sched_clock_cpu 8.50% 0.35% 1070150 9 ls [kernel.kallsyms] [k] check_chain_key ... Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/n/tip-iyoinu3axi11mymwnh2b7fxj@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-10 15:39:03 +00:00
/*
* Apply group format only if we belong to group
* with more than one members.
*/
if (leader->nr_members > 1) {
attr->read_format |= PERF_FORMAT_GROUP;
attr->inherit = 0;
}
}
/*
* We default some events to have a default interval. But keep
* it a weak assumption overridable by the user.
*/
if (!attr->sample_period || (opts->user_freq != UINT_MAX ||
opts->user_interval != ULLONG_MAX)) {
if (opts->freq) {
perf_evsel__set_sample_bit(evsel, PERIOD);
attr->freq = 1;
attr->sample_freq = opts->freq;
} else {
attr->sample_period = opts->default_interval;
}
}
perf tools: Add 'S' event/group modifier to read sample value Adding 'S' event/group modifier to specify that the event value/s are read by PERF_SAMPLE_READ sample type processing, instead of the period value offered by lower layers. There's additional behaviour change for 'S' modifier being specified on event group: Currently all the events within a group makes samples. If user now specifies 'S' within group modifier, only the leader will trigger samples. The rest of events in the group will have sampling disabled. And same as for single events, values of all events within the group (including leader) are read by PERF_SAMPLE_READ sample type processing. Following example will create event group with cycles and cache-misses events, setting the cycles as group leader and the only event to actually sample. Both cycles and cache-misses event period values are read by PERF_SAMPLE_READ sample type processing with PERF_FORMAT_GROUP read format. Example: $ perf record -e '{cycles,cache-misses}:S' ls ... $ perf report --group --show-total-period --stdio ... # Samples: 36 of event 'anon group { cycles, cache-misses }' # Event count (approx.): 12585593 # # Overhead Period Command Shared Object Symbol # .............. .............. ....... ................. .......................... # 19.92% 1.20% 2505936 31 ls [kernel.kallsyms] [k] mark_held_locks 13.74% 0.47% 1729327 12 ls [kernel.kallsyms] [k] sched_clock_local 13.64% 23.72% 1716147 612 ls ld-2.14.90.so [.] check_match.10805 13.12% 23.22% 1650778 599 ls libc-2.14.90.so [.] _nl_intern_locale_data 11.24% 29.19% 1414554 753 ls [kernel.kallsyms] [k] sched_clock_cpu 8.50% 0.35% 1070150 9 ls [kernel.kallsyms] [k] check_chain_key ... Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/n/tip-iyoinu3axi11mymwnh2b7fxj@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-10 15:39:03 +00:00
/*
* Disable sampling for all group members other
* than leader in case leader 'leads' the sampling.
*/
if ((leader != evsel) && leader->sample_read) {
attr->freq = 0;
attr->sample_freq = 0;
attr->sample_period = 0;
attr->write_backward = 0;
/*
* We don't get sample for slave events, we make them
* when delivering group leader sample. Set the slave
* event to follow the master sample_type to ease up
* report.
*/
attr->sample_type = leader->attr.sample_type;
perf tools: Add 'S' event/group modifier to read sample value Adding 'S' event/group modifier to specify that the event value/s are read by PERF_SAMPLE_READ sample type processing, instead of the period value offered by lower layers. There's additional behaviour change for 'S' modifier being specified on event group: Currently all the events within a group makes samples. If user now specifies 'S' within group modifier, only the leader will trigger samples. The rest of events in the group will have sampling disabled. And same as for single events, values of all events within the group (including leader) are read by PERF_SAMPLE_READ sample type processing. Following example will create event group with cycles and cache-misses events, setting the cycles as group leader and the only event to actually sample. Both cycles and cache-misses event period values are read by PERF_SAMPLE_READ sample type processing with PERF_FORMAT_GROUP read format. Example: $ perf record -e '{cycles,cache-misses}:S' ls ... $ perf report --group --show-total-period --stdio ... # Samples: 36 of event 'anon group { cycles, cache-misses }' # Event count (approx.): 12585593 # # Overhead Period Command Shared Object Symbol # .............. .............. ....... ................. .......................... # 19.92% 1.20% 2505936 31 ls [kernel.kallsyms] [k] mark_held_locks 13.74% 0.47% 1729327 12 ls [kernel.kallsyms] [k] sched_clock_local 13.64% 23.72% 1716147 612 ls ld-2.14.90.so [.] check_match.10805 13.12% 23.22% 1650778 599 ls libc-2.14.90.so [.] _nl_intern_locale_data 11.24% 29.19% 1414554 753 ls [kernel.kallsyms] [k] sched_clock_cpu 8.50% 0.35% 1070150 9 ls [kernel.kallsyms] [k] check_chain_key ... Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/n/tip-iyoinu3axi11mymwnh2b7fxj@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-10 15:39:03 +00:00
}
if (opts->no_samples)
attr->sample_freq = 0;
if (opts->inherit_stat) {
evsel->attr.read_format |=
PERF_FORMAT_TOTAL_TIME_ENABLED |
PERF_FORMAT_TOTAL_TIME_RUNNING |
PERF_FORMAT_ID;
attr->inherit_stat = 1;
}
if (opts->sample_address) {
perf_evsel__set_sample_bit(evsel, ADDR);
attr->mmap_data = track;
}
/*
* We don't allow user space callchains for function trace
* event, due to issues with page faults while tracing page
* fault handler and its overall trickiness nature.
*/
if (perf_evsel__is_function_event(evsel))
evsel->attr.exclude_callchain_user = 1;
if (callchain && callchain->enabled && !evsel->no_aux_samples)
perf_evsel__config_callchain(evsel, opts, callchain);
perf tools: Support for DWARF mode callchain This patch enables perf to use the DWARF unwind code. It extends the perf record '-g' option with following arguments: 'fp' - provides framepointer based user stack backtrace 'dwarf[,size]' - provides DWARF (libunwind) based user stack backtrace. The size specifies the size of the user stack dump. If omitted it is 8192 by default. If libunwind is found during the perf build, then the 'dwarf' argument becomes available for record command. The 'fp' stays as default option in any case. Examples: (perf compiled with libunwind) perf record -g dwarf ls - provides dwarf unwind with 8192 as stack dump size perf record -g dwarf,4096 ls - provides dwarf unwind with 4096 as stack dump size perf record -g -- ls perf record -g fp ls - provides frame pointer unwind Signed-off-by: Jiri Olsa <jolsa@redhat.com> Original-patch-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: "Frank Ch. Eigler" <fche@redhat.com> Cc: Arun Sharma <asharma@fb.com> Cc: Benjamin Redelings <benjamin.redelings@nescent.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Frank Ch. Eigler <fche@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Ulrich Drepper <drepper@gmail.com> Link: http://lkml.kernel.org/r/1344345647-11536-13-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-08-07 13:20:47 +00:00
if (opts->sample_intr_regs) {
perf record: Add ability to name registers to record This patch modifies the -I/--int-regs option to enablepassing the name of the registers to sample on interrupt. Registers can be specified by their symbolic names. For instance on x86, --intr-regs=ax,si. The motivation is to reduce the size of the perf.data file and the overhead of sampling by only collecting the registers useful to a specific analysis. For instance, for value profiling, sampling only the registers used to passed arguements to functions. With no parameter, the --intr-regs still records all possible registers based on the architecture. To name registers, it is necessary to use the long form of the option, i.e., --intr-regs: $ perf record --intr-regs=si,di,r8,r9 ..... To record any possible registers: $ perf record -I ..... $ perf report --intr-regs ... To display the register, one can use perf report -D To list the available registers: $ perf record --intr-regs=\? available registers: AX BX CX DX SI DI BP SP IP FLAGS CS SS R8 R9 R10 R11 R12 R13 R14 R15 Signed-off-by: Stephane Eranian <eranian@google.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1441039273-16260-4-git-send-email-eranian@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-31 16:41:12 +00:00
attr->sample_regs_intr = opts->sample_intr_regs;
perf_evsel__set_sample_bit(evsel, REGS_INTR);
}
if (opts->sample_user_regs) {
attr->sample_regs_user |= opts->sample_user_regs;
perf_evsel__set_sample_bit(evsel, REGS_USER);
}
if (target__has_cpu(&opts->target) || opts->sample_cpu)
perf_evsel__set_sample_bit(evsel, CPU);
/*
* When the user explicitly disabled time don't force it here.
*/
if (opts->sample_time &&
(!perf_missing_features.sample_id_all &&
(!opts->no_inherit || target__has_cpu(&opts->target) || per_cpu ||
opts->sample_time_set)))
perf_evsel__set_sample_bit(evsel, TIME);
if (opts->raw_samples && !evsel->no_aux_samples) {
perf_evsel__set_sample_bit(evsel, TIME);
perf_evsel__set_sample_bit(evsel, RAW);
perf_evsel__set_sample_bit(evsel, CPU);
}
if (opts->sample_address)
perf_evsel__set_sample_bit(evsel, DATA_SRC);
if (opts->sample_phys_addr)
perf_evsel__set_sample_bit(evsel, PHYS_ADDR);
if (opts->no_buffering) {
attr->watermark = 0;
attr->wakeup_events = 1;
}
if (opts->branch_stack && !evsel->no_aux_samples) {
perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
attr->branch_sample_type = opts->branch_stack;
}
if (opts->sample_weight)
perf_evsel__set_sample_bit(evsel, WEIGHT);
attr->task = track;
attr->mmap = track;
attr->mmap2 = track && !perf_missing_features.mmap2;
attr->comm = track;
attr->ksymbol = track && !perf_missing_features.ksymbol;
attr->bpf_event = track && !opts->no_bpf_event &&
perf tools: Handle PERF_RECORD_BPF_EVENT This patch adds basic handling of PERF_RECORD_BPF_EVENT. Tracking of PERF_RECORD_BPF_EVENT is OFF by default. Option --bpf-event is added to turn it on. Committer notes: Add dummy machine__process_bpf_event() variant that returns zero for systems without HAVE_LIBBPF_SUPPORT, such as Alpine Linux, unbreaking the build in such systems. Remove the needless include <machine.h> from bpf->event.h, provide just forward declarations for the structs and unions in the parameters, to reduce compilation time and needless rebuilds when machine.h gets changed. Committer testing: When running with: # perf record --bpf-event On an older kernel where PERF_RECORD_BPF_EVENT and PERF_RECORD_KSYMBOL is not present, we fallback to removing those two bits from perf_event_attr, making the tool to continue to work on older kernels: perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD read_format ID disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 precise_ip 3 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 bpf_event 1 ------------------------------------------------------------ sys_perf_event_open: pid 5779 cpu 0 group_fd -1 flags 0x8 sys_perf_event_open failed, error -22 switching off bpf_event ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD read_format ID disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 precise_ip 3 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 ------------------------------------------------------------ sys_perf_event_open: pid 5779 cpu 0 group_fd -1 flags 0x8 sys_perf_event_open failed, error -22 switching off ksymbol ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD read_format ID disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 precise_ip 3 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ------------------------------------------------------------ And then proceeds to work without those two features. As passing --bpf-event is an explicit action performed by the user, perhaps we should emit a warning telling that the kernel has no such feature, but this can be done on top of this patch. Now with a kernel that supports these events, start the 'record --bpf-event -a' and then run 'perf trace sleep 10000' that will use the BPF augmented_raw_syscalls.o prebuilt (for another kernel version even) and thus should generate PERF_RECORD_BPF_EVENT events: [root@quaco ~]# perf record -e dummy -a --bpf-event ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.713 MB perf.data ] [root@quaco ~]# bpftool prog 13: cgroup_skb tag 7be49e3934a125ba gpl loaded_at 2019-01-19T09:09:43-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 13,14 14: cgroup_skb tag 2a142ef67aaad174 gpl loaded_at 2019-01-19T09:09:43-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 13,14 15: cgroup_skb tag 7be49e3934a125ba gpl loaded_at 2019-01-19T09:09:43-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 15,16 16: cgroup_skb tag 2a142ef67aaad174 gpl loaded_at 2019-01-19T09:09:43-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 15,16 17: cgroup_skb tag 7be49e3934a125ba gpl loaded_at 2019-01-19T09:09:44-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 17,18 18: cgroup_skb tag 2a142ef67aaad174 gpl loaded_at 2019-01-19T09:09:44-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 17,18 21: cgroup_skb tag 7be49e3934a125ba gpl loaded_at 2019-01-19T09:09:45-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 21,22 22: cgroup_skb tag 2a142ef67aaad174 gpl loaded_at 2019-01-19T09:09:45-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 21,22 31: tracepoint name sys_enter tag 12504ba9402f952f gpl loaded_at 2019-01-19T09:19:56-0300 uid 0 xlated 512B jited 374B memlock 4096B map_ids 30,29,28 32: tracepoint name sys_exit tag c1bd85c092d6e4aa gpl loaded_at 2019-01-19T09:19:56-0300 uid 0 xlated 256B jited 191B memlock 4096B map_ids 30,29 # perf report -D | grep PERF_RECORD_BPF_EVENT | nl 1 0 55834574849 0x4fc8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 13 2 0 60129542145 0x5118 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 14 3 0 64424509441 0x5268 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 15 4 0 68719476737 0x53b8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 16 5 0 73014444033 0x5508 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 17 6 0 77309411329 0x5658 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 18 7 0 90194313217 0x57a8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 21 8 0 94489280513 0x58f8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 22 9 7 620922484360 0xb6390 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 29 10 7 620922486018 0xb6410 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 2, flags 0, id 29 11 7 620922579199 0xb6490 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 30 12 7 620922580240 0xb6510 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 2, flags 0, id 30 13 7 620922765207 0xb6598 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 31 14 7 620922874543 0xb6620 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 32 # There, the 31 and 32 tracepoint BPF programs put in place by 'perf trace'. Signed-off-by: Song Liu <songliubraving@fb.com> Reviewed-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: kernel-team@fb.com Cc: netdev@vger.kernel.org Link: http://lkml.kernel.org/r/20190117161521.1341602-7-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-01-17 16:15:18 +00:00
!perf_missing_features.bpf_event;
perf tools: Add PERF_RECORD_NAMESPACES to include namespaces related info Introduce a new option to record PERF_RECORD_NAMESPACES events emitted by the kernel when fork, clone, setns or unshare are invoked. And update perf-record documentation with the new option to record namespace events. Committer notes: Combined it with a later patch to allow printing it via 'perf report -D' and be able to test the feature introduced in this patch. Had to move here also perf_ns__name(), that was introduced in another later patch. Also used PRIu64 and PRIx64 to fix the build in some enfironments wrt: util/event.c:1129:39: error: format '%lx' expects argument of type 'long unsigned int', but argument 6 has type 'long long unsigned int' [-Werror=format=] ret += fprintf(fp, "%u/%s: %lu/0x%lx%s", idx ^ Testing it: # perf record --namespaces -a ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 1.083 MB perf.data (423 samples) ] # # perf report -D <SNIP> 3 2028902078892 0x115140 [0xa0]: PERF_RECORD_NAMESPACES 14783/14783 - nr_namespaces: 7 [0/net: 3/0xf0000081, 1/uts: 3/0xeffffffe, 2/ipc: 3/0xefffffff, 3/pid: 3/0xeffffffc, 4/user: 3/0xeffffffd, 5/mnt: 3/0xf0000000, 6/cgroup: 3/0xeffffffb] 0x1151e0 [0x30]: event: 9 . . ... raw event: size 48 bytes . 0000: 09 00 00 00 02 00 30 00 c4 71 82 68 0c 7f 00 00 ......0..q.h.... . 0010: a9 39 00 00 a9 39 00 00 94 28 fe 63 d8 01 00 00 .9...9...(.c.... . 0020: 03 00 00 00 00 00 00 00 ce c4 02 00 00 00 00 00 ................ <SNIP> NAMESPACES events: 1 <SNIP> # Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Starovoitov <ast@fb.com> Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com> Cc: Aravinda Prasad <aravinda@linux.vnet.ibm.com> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Eric Biederman <ebiederm@xmission.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sargun Dhillon <sargun@sargun.me> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/148891930386.25309.18412039920746995488.stgit@hbathini.in.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-07 20:41:43 +00:00
if (opts->record_namespaces)
attr->namespaces = track;
if (opts->record_switch_events)
attr->context_switch = track;
if (opts->sample_transaction)
perf_evsel__set_sample_bit(evsel, TRANSACTION);
if (opts->running_time) {
evsel->attr.read_format |=
PERF_FORMAT_TOTAL_TIME_ENABLED |
PERF_FORMAT_TOTAL_TIME_RUNNING;
}
perf tools: Fix 'disabled' attribute config for record command Currently the record command sets all events initially as disabled. There's non conditional perf_evlist__enable call, that enables all events before we exec tracee program. That actually screws whole enable_on_exec logic, because the event is enabled before the traced program got executed. What we actually want is: 1) For any type of traced program: - all independent events and group leaders are disabled - all group members are enabled Group members are ruled by group leaders. They need to be enabled, because the group scheduling relies on that. 2) For traced programs executed by perf: - all independent events and group leaders have enable_on_exec set - we don't specifically enable or disable any event during the record command Independent events and group leaders are initially disabled and get enabled by exec. Group members are ruled by group leaders as stated in 1). 3) For traced programs attached by perf (pid/tid): - we specifically enable or disable all events during the record command When attaching events to already running traced we enable/disable events specifically, as there's no initial traced exec call. Fixing appropriate perf_event_attr test case to cover this change. Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1352741644-16809-3-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-11-12 17:34:01 +00:00
/*
* XXX see the function comment above
*
* Disabling only independent events or group leaders,
* keeping group members enabled.
*/
if (perf_evsel__is_group_leader(evsel))
perf tools: Fix 'disabled' attribute config for record command Currently the record command sets all events initially as disabled. There's non conditional perf_evlist__enable call, that enables all events before we exec tracee program. That actually screws whole enable_on_exec logic, because the event is enabled before the traced program got executed. What we actually want is: 1) For any type of traced program: - all independent events and group leaders are disabled - all group members are enabled Group members are ruled by group leaders. They need to be enabled, because the group scheduling relies on that. 2) For traced programs executed by perf: - all independent events and group leaders have enable_on_exec set - we don't specifically enable or disable any event during the record command Independent events and group leaders are initially disabled and get enabled by exec. Group members are ruled by group leaders as stated in 1). 3) For traced programs attached by perf (pid/tid): - we specifically enable or disable all events during the record command When attaching events to already running traced we enable/disable events specifically, as there's no initial traced exec call. Fixing appropriate perf_event_attr test case to cover this change. Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1352741644-16809-3-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-11-12 17:34:01 +00:00
attr->disabled = 1;
/*
* Setting enable_on_exec for independent events and
* group leaders for traced executed by perf.
*/
if (target__none(&opts->target) && perf_evsel__is_group_leader(evsel) &&
!opts->initial_delay)
attr->enable_on_exec = 1;
if (evsel->immediate) {
attr->disabled = 0;
attr->enable_on_exec = 0;
}
clockid = opts->clockid;
if (opts->use_clockid) {
attr->use_clockid = 1;
attr->clockid = opts->clockid;
}
if (evsel->precise_max)
perf evsel: Fix max perf_event_attr.precise_ip detection After a discussion with Andi, move the perf_event_attr.precise_ip detection for maximum precise config (via :P modifier or for default cycles event) to perf_evsel__open(). The current detection in perf_event_attr__set_max_precise_ip() is tricky, because precise_ip config is specific for given event and it currently checks only hw cycles. We now check for valid precise_ip value right after failing sys_perf_event_open() for specific event, before any of the perf_event_attr fallback code gets executed. This way we get the proper config in perf_event_attr together with allowed precise_ip settings. We can see that code activity with -vv, like: $ perf record -vv ls ... ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 ... precise_ip 3 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 ------------------------------------------------------------ sys_perf_event_open: pid 9926 cpu 0 group_fd -1 flags 0x8 sys_perf_event_open failed, error -95 decreasing precise_ip by one (2) ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 ... precise_ip 2 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 ------------------------------------------------------------ sys_perf_event_open: pid 9926 cpu 0 group_fd -1 flags 0x8 = 4 ... Suggested-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/n/tip-dkvxxbeg7lu74155d4jhlmc9@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-14 14:00:10 +00:00
attr->precise_ip = 3;
perf record: Add --all-user/--all-kernel options Allow user to easily switch all events to user or kernel space with simple --all-user or --all-kernel options. This will be handy within perf mem/c2c wrappers to switch easily monitoring modes. Committer note: Testing it: # perf record --all-kernel --all-user -a sleep 2 Error: option `all-user' cannot be used with all-kernel Usage: perf record [<options>] [<command>] or: perf record [<options>] -- <command> [<options>] --all-user Configure all used events to run in user space. --all-kernel Configure all used events to run in kernel space. # perf record --all-user --all-kernel -a sleep 2 Error: option `all-kernel' cannot be used with all-user Usage: perf record [<options>] [<command>] or: perf record [<options>] -- <command> [<options>] --all-kernel Configure all used events to run in kernel space. --all-user Configure all used events to run in user space. # perf record --all-user -a sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 1.416 MB perf.data (162 samples) ] # perf report | grep '\[k\]' # perf record --all-kernel -a sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 1.423 MB perf.data (296 samples) ] # perf report | grep '\[\.\]' # Signed-off-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1455525293-8671-2-git-send-email-jolsa@kernel.org [ Made those options to be mutually exclusive ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-15 08:34:31 +00:00
if (opts->all_user) {
attr->exclude_kernel = 1;
attr->exclude_user = 0;
}
if (opts->all_kernel) {
attr->exclude_kernel = 0;
attr->exclude_user = 1;
}
if (evsel->own_cpus || evsel->unit)
evsel->attr.read_format |= PERF_FORMAT_ID;
/*
* Apply event specific term settings,
* it overloads any global configuration.
*/
apply_config_terms(evsel, opts, track);
evsel->ignore_missing_thread = opts->ignore_missing_thread;
perf record: Fix period option handling Stephan reported we don't unset PERIOD sample type when --no-period is specified. Adding the unset check and reset PERIOD if --no-period is specified. Committer notes: Check the sample_type, it shouldn't have PERF_SAMPLE_PERIOD there when --no-period is used. Before: # perf record --no-period sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.018 MB perf.data (7 samples) ] # perf evlist -v cycles:ppp: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, precise_ip: 3, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 # After: [root@jouet ~]# perf record --no-period sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.019 MB perf.data (17 samples) ] [root@jouet ~]# perf evlist -v cycles:ppp: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, precise_ip: 3, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 [root@jouet ~]# Reported-by: Stephane Eranian <eranian@google.com> Signed-off-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Stephane Eranian <eranian@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@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/20180201083812.11359-3-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-02-01 08:38:11 +00:00
/* The --period option takes the precedence. */
if (opts->period_set) {
if (opts->period)
perf_evsel__set_sample_bit(evsel, PERIOD);
else
perf_evsel__reset_sample_bit(evsel, PERIOD);
}
/*
* For initial_delay, a dummy event is added implicitly.
* The software event will trigger -EOPNOTSUPP error out,
* if BRANCH_STACK bit is set.
*/
if (opts->initial_delay && is_dummy_event(evsel))
perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
}
static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
{
evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
if (evsel->fd) {
int cpu, thread;
for (cpu = 0; cpu < ncpus; cpu++) {
for (thread = 0; thread < nthreads; thread++) {
FD(evsel, cpu, thread) = -1;
}
}
}
return evsel->fd != NULL ? 0 : -ENOMEM;
}
perf evsel: Fix buffer overflow while freeing events Fix buffer overflow for: % perf stat -e msr/tsc/,cstate_core/c7-residency/ true that causes glibc free list corruption. For some reason it doesn't trigger in valgrind, but it is visible in AS: ================================================================= ==32681==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x603000003f5c at pc 0x0000005671ef bp 0x7ffdaaac9ac0 sp 0x7ffdaaac9ab0 READ of size 4 at 0x603000003f5c thread T0 #0 0x5671ee in perf_evsel__close_fd util/evsel.c:1196 #1 0x56c57a in perf_evsel__close util/evsel.c:1717 #2 0x55ed5f in perf_evlist__close util/evlist.c:1631 #3 0x4647e1 in __run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:749 #4 0x4648e3 in run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:767 #5 0x46e1bc in cmd_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:2785 #6 0x52f83d in run_builtin /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:296 #7 0x52fd49 in handle_internal_command /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:348 #8 0x5300de in run_argv /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:392 #9 0x5308f3 in main /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:530 #10 0x7f0672d13400 in __libc_start_main (/lib64/libc.so.6+0x20400) #11 0x428419 in _start (/home/ak/hle/obj-perf/perf+0x428419) 0x603000003f5c is located 0 bytes to the right of 28-byte region [0x603000003f40,0x603000003f5c) allocated by thread T0 here: #0 0x7f0675139020 in calloc (/lib64/libasan.so.3+0xc7020) #1 0x648a2d in zalloc util/util.h:23 #2 0x648a88 in xyarray__new util/xyarray.c:9 #3 0x566419 in perf_evsel__alloc_fd util/evsel.c:1039 #4 0x56b427 in perf_evsel__open util/evsel.c:1529 #5 0x56c620 in perf_evsel__open_per_thread util/evsel.c:1730 #6 0x461dea in create_perf_stat_counter /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:263 #7 0x4637d7 in __run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:600 #8 0x4648e3 in run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:767 #9 0x46e1bc in cmd_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:2785 #10 0x52f83d in run_builtin /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:296 #11 0x52fd49 in handle_internal_command /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:348 #12 0x5300de in run_argv /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:392 #13 0x5308f3 in main /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:530 #14 0x7f0672d13400 in __libc_start_main (/lib64/libc.so.6+0x20400) The event is allocated with cpus == 1, but freed with cpus == real number When the evsel close function walks the file descriptors it exceeds the fd xyarray boundaries and reads random memory. v2: Now that xyarrays save their original dimensions we can use these to iterate the two dimensional fd arrays. Fix some users (close, ioctl) in evsel.c to use these fields directly. This allows simplifying the code and dropping quite a few function arguments. Adjust all callers by removing the unneeded arguments. The actual perf event reading still uses the original values from the evsel list. Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170811232634.30465-2-andi@firstfloor.org [ Fix up xy_max_[xy]() -> xyarray__max_[xy]() ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-11 23:26:17 +00:00
static int perf_evsel__run_ioctl(struct perf_evsel *evsel,
int ioc, void *arg)
{
int cpu, thread;
perf evsel: Fix buffer overflow while freeing events Fix buffer overflow for: % perf stat -e msr/tsc/,cstate_core/c7-residency/ true that causes glibc free list corruption. For some reason it doesn't trigger in valgrind, but it is visible in AS: ================================================================= ==32681==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x603000003f5c at pc 0x0000005671ef bp 0x7ffdaaac9ac0 sp 0x7ffdaaac9ab0 READ of size 4 at 0x603000003f5c thread T0 #0 0x5671ee in perf_evsel__close_fd util/evsel.c:1196 #1 0x56c57a in perf_evsel__close util/evsel.c:1717 #2 0x55ed5f in perf_evlist__close util/evlist.c:1631 #3 0x4647e1 in __run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:749 #4 0x4648e3 in run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:767 #5 0x46e1bc in cmd_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:2785 #6 0x52f83d in run_builtin /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:296 #7 0x52fd49 in handle_internal_command /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:348 #8 0x5300de in run_argv /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:392 #9 0x5308f3 in main /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:530 #10 0x7f0672d13400 in __libc_start_main (/lib64/libc.so.6+0x20400) #11 0x428419 in _start (/home/ak/hle/obj-perf/perf+0x428419) 0x603000003f5c is located 0 bytes to the right of 28-byte region [0x603000003f40,0x603000003f5c) allocated by thread T0 here: #0 0x7f0675139020 in calloc (/lib64/libasan.so.3+0xc7020) #1 0x648a2d in zalloc util/util.h:23 #2 0x648a88 in xyarray__new util/xyarray.c:9 #3 0x566419 in perf_evsel__alloc_fd util/evsel.c:1039 #4 0x56b427 in perf_evsel__open util/evsel.c:1529 #5 0x56c620 in perf_evsel__open_per_thread util/evsel.c:1730 #6 0x461dea in create_perf_stat_counter /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:263 #7 0x4637d7 in __run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:600 #8 0x4648e3 in run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:767 #9 0x46e1bc in cmd_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:2785 #10 0x52f83d in run_builtin /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:296 #11 0x52fd49 in handle_internal_command /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:348 #12 0x5300de in run_argv /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:392 #13 0x5308f3 in main /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:530 #14 0x7f0672d13400 in __libc_start_main (/lib64/libc.so.6+0x20400) The event is allocated with cpus == 1, but freed with cpus == real number When the evsel close function walks the file descriptors it exceeds the fd xyarray boundaries and reads random memory. v2: Now that xyarrays save their original dimensions we can use these to iterate the two dimensional fd arrays. Fix some users (close, ioctl) in evsel.c to use these fields directly. This allows simplifying the code and dropping quite a few function arguments. Adjust all callers by removing the unneeded arguments. The actual perf event reading still uses the original values from the evsel list. Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170811232634.30465-2-andi@firstfloor.org [ Fix up xy_max_[xy]() -> xyarray__max_[xy]() ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-11 23:26:17 +00:00
for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
int fd = FD(evsel, cpu, thread),
err = ioctl(fd, ioc, arg);
if (err)
return err;
}
}
return 0;
}
perf evsel: Fix buffer overflow while freeing events Fix buffer overflow for: % perf stat -e msr/tsc/,cstate_core/c7-residency/ true that causes glibc free list corruption. For some reason it doesn't trigger in valgrind, but it is visible in AS: ================================================================= ==32681==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x603000003f5c at pc 0x0000005671ef bp 0x7ffdaaac9ac0 sp 0x7ffdaaac9ab0 READ of size 4 at 0x603000003f5c thread T0 #0 0x5671ee in perf_evsel__close_fd util/evsel.c:1196 #1 0x56c57a in perf_evsel__close util/evsel.c:1717 #2 0x55ed5f in perf_evlist__close util/evlist.c:1631 #3 0x4647e1 in __run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:749 #4 0x4648e3 in run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:767 #5 0x46e1bc in cmd_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:2785 #6 0x52f83d in run_builtin /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:296 #7 0x52fd49 in handle_internal_command /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:348 #8 0x5300de in run_argv /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:392 #9 0x5308f3 in main /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:530 #10 0x7f0672d13400 in __libc_start_main (/lib64/libc.so.6+0x20400) #11 0x428419 in _start (/home/ak/hle/obj-perf/perf+0x428419) 0x603000003f5c is located 0 bytes to the right of 28-byte region [0x603000003f40,0x603000003f5c) allocated by thread T0 here: #0 0x7f0675139020 in calloc (/lib64/libasan.so.3+0xc7020) #1 0x648a2d in zalloc util/util.h:23 #2 0x648a88 in xyarray__new util/xyarray.c:9 #3 0x566419 in perf_evsel__alloc_fd util/evsel.c:1039 #4 0x56b427 in perf_evsel__open util/evsel.c:1529 #5 0x56c620 in perf_evsel__open_per_thread util/evsel.c:1730 #6 0x461dea in create_perf_stat_counter /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:263 #7 0x4637d7 in __run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:600 #8 0x4648e3 in run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:767 #9 0x46e1bc in cmd_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:2785 #10 0x52f83d in run_builtin /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:296 #11 0x52fd49 in handle_internal_command /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:348 #12 0x5300de in run_argv /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:392 #13 0x5308f3 in main /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:530 #14 0x7f0672d13400 in __libc_start_main (/lib64/libc.so.6+0x20400) The event is allocated with cpus == 1, but freed with cpus == real number When the evsel close function walks the file descriptors it exceeds the fd xyarray boundaries and reads random memory. v2: Now that xyarrays save their original dimensions we can use these to iterate the two dimensional fd arrays. Fix some users (close, ioctl) in evsel.c to use these fields directly. This allows simplifying the code and dropping quite a few function arguments. Adjust all callers by removing the unneeded arguments. The actual perf event reading still uses the original values from the evsel list. Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170811232634.30465-2-andi@firstfloor.org [ Fix up xy_max_[xy]() -> xyarray__max_[xy]() ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-11 23:26:17 +00:00
int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter)
{
perf evsel: Fix buffer overflow while freeing events Fix buffer overflow for: % perf stat -e msr/tsc/,cstate_core/c7-residency/ true that causes glibc free list corruption. For some reason it doesn't trigger in valgrind, but it is visible in AS: ================================================================= ==32681==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x603000003f5c at pc 0x0000005671ef bp 0x7ffdaaac9ac0 sp 0x7ffdaaac9ab0 READ of size 4 at 0x603000003f5c thread T0 #0 0x5671ee in perf_evsel__close_fd util/evsel.c:1196 #1 0x56c57a in perf_evsel__close util/evsel.c:1717 #2 0x55ed5f in perf_evlist__close util/evlist.c:1631 #3 0x4647e1 in __run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:749 #4 0x4648e3 in run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:767 #5 0x46e1bc in cmd_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:2785 #6 0x52f83d in run_builtin /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:296 #7 0x52fd49 in handle_internal_command /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:348 #8 0x5300de in run_argv /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:392 #9 0x5308f3 in main /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:530 #10 0x7f0672d13400 in __libc_start_main (/lib64/libc.so.6+0x20400) #11 0x428419 in _start (/home/ak/hle/obj-perf/perf+0x428419) 0x603000003f5c is located 0 bytes to the right of 28-byte region [0x603000003f40,0x603000003f5c) allocated by thread T0 here: #0 0x7f0675139020 in calloc (/lib64/libasan.so.3+0xc7020) #1 0x648a2d in zalloc util/util.h:23 #2 0x648a88 in xyarray__new util/xyarray.c:9 #3 0x566419 in perf_evsel__alloc_fd util/evsel.c:1039 #4 0x56b427 in perf_evsel__open util/evsel.c:1529 #5 0x56c620 in perf_evsel__open_per_thread util/evsel.c:1730 #6 0x461dea in create_perf_stat_counter /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:263 #7 0x4637d7 in __run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:600 #8 0x4648e3 in run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:767 #9 0x46e1bc in cmd_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:2785 #10 0x52f83d in run_builtin /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:296 #11 0x52fd49 in handle_internal_command /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:348 #12 0x5300de in run_argv /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:392 #13 0x5308f3 in main /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:530 #14 0x7f0672d13400 in __libc_start_main (/lib64/libc.so.6+0x20400) The event is allocated with cpus == 1, but freed with cpus == real number When the evsel close function walks the file descriptors it exceeds the fd xyarray boundaries and reads random memory. v2: Now that xyarrays save their original dimensions we can use these to iterate the two dimensional fd arrays. Fix some users (close, ioctl) in evsel.c to use these fields directly. This allows simplifying the code and dropping quite a few function arguments. Adjust all callers by removing the unneeded arguments. The actual perf event reading still uses the original values from the evsel list. Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170811232634.30465-2-andi@firstfloor.org [ Fix up xy_max_[xy]() -> xyarray__max_[xy]() ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-11 23:26:17 +00:00
return perf_evsel__run_ioctl(evsel,
PERF_EVENT_IOC_SET_FILTER,
(void *)filter);
}
int perf_evsel__set_filter(struct perf_evsel *evsel, const char *filter)
{
char *new_filter = strdup(filter);
if (new_filter != NULL) {
free(evsel->filter);
evsel->filter = new_filter;
return 0;
}
return -1;
}
static int perf_evsel__append_filter(struct perf_evsel *evsel,
const char *fmt, const char *filter)
{
char *new_filter;
if (evsel->filter == NULL)
return perf_evsel__set_filter(evsel, filter);
if (asprintf(&new_filter, fmt, evsel->filter, filter) > 0) {
free(evsel->filter);
evsel->filter = new_filter;
return 0;
}
return -1;
}
int perf_evsel__append_tp_filter(struct perf_evsel *evsel, const char *filter)
{
return perf_evsel__append_filter(evsel, "(%s) && (%s)", filter);
}
int perf_evsel__append_addr_filter(struct perf_evsel *evsel, const char *filter)
{
return perf_evsel__append_filter(evsel, "%s,%s", filter);
}
int perf_evsel__enable(struct perf_evsel *evsel)
{
int err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, 0);
if (!err)
evsel->disabled = false;
return err;
}
int perf_evsel__disable(struct perf_evsel *evsel)
{
int err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, 0);
/*
* We mark it disabled here so that tools that disable a event can
* ignore events after they disable it. I.e. the ring buffer may have
* already a few more events queued up before the kernel got the stop
* request.
*/
if (!err)
evsel->disabled = true;
return err;
}
int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
{
if (ncpus == 0 || nthreads == 0)
return 0;
if (evsel->system_wide)
nthreads = 1;
evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id));
if (evsel->sample_id == NULL)
return -ENOMEM;
evsel->id = zalloc(ncpus * nthreads * sizeof(u64));
if (evsel->id == NULL) {
xyarray__delete(evsel->sample_id);
evsel->sample_id = NULL;
return -ENOMEM;
}
return 0;
}
static void perf_evsel__free_fd(struct perf_evsel *evsel)
{
xyarray__delete(evsel->fd);
evsel->fd = NULL;
}
static void perf_evsel__free_id(struct perf_evsel *evsel)
{
xyarray__delete(evsel->sample_id);
evsel->sample_id = NULL;
zfree(&evsel->id);
evsel->ids = 0;
}
static void perf_evsel__free_config_terms(struct perf_evsel *evsel)
{
struct perf_evsel_config_term *term, *h;
list_for_each_entry_safe(term, h, &evsel->config_terms, list) {
list_del_init(&term->list);
free(term);
}
}
perf evsel: Fix buffer overflow while freeing events Fix buffer overflow for: % perf stat -e msr/tsc/,cstate_core/c7-residency/ true that causes glibc free list corruption. For some reason it doesn't trigger in valgrind, but it is visible in AS: ================================================================= ==32681==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x603000003f5c at pc 0x0000005671ef bp 0x7ffdaaac9ac0 sp 0x7ffdaaac9ab0 READ of size 4 at 0x603000003f5c thread T0 #0 0x5671ee in perf_evsel__close_fd util/evsel.c:1196 #1 0x56c57a in perf_evsel__close util/evsel.c:1717 #2 0x55ed5f in perf_evlist__close util/evlist.c:1631 #3 0x4647e1 in __run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:749 #4 0x4648e3 in run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:767 #5 0x46e1bc in cmd_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:2785 #6 0x52f83d in run_builtin /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:296 #7 0x52fd49 in handle_internal_command /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:348 #8 0x5300de in run_argv /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:392 #9 0x5308f3 in main /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:530 #10 0x7f0672d13400 in __libc_start_main (/lib64/libc.so.6+0x20400) #11 0x428419 in _start (/home/ak/hle/obj-perf/perf+0x428419) 0x603000003f5c is located 0 bytes to the right of 28-byte region [0x603000003f40,0x603000003f5c) allocated by thread T0 here: #0 0x7f0675139020 in calloc (/lib64/libasan.so.3+0xc7020) #1 0x648a2d in zalloc util/util.h:23 #2 0x648a88 in xyarray__new util/xyarray.c:9 #3 0x566419 in perf_evsel__alloc_fd util/evsel.c:1039 #4 0x56b427 in perf_evsel__open util/evsel.c:1529 #5 0x56c620 in perf_evsel__open_per_thread util/evsel.c:1730 #6 0x461dea in create_perf_stat_counter /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:263 #7 0x4637d7 in __run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:600 #8 0x4648e3 in run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:767 #9 0x46e1bc in cmd_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:2785 #10 0x52f83d in run_builtin /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:296 #11 0x52fd49 in handle_internal_command /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:348 #12 0x5300de in run_argv /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:392 #13 0x5308f3 in main /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:530 #14 0x7f0672d13400 in __libc_start_main (/lib64/libc.so.6+0x20400) The event is allocated with cpus == 1, but freed with cpus == real number When the evsel close function walks the file descriptors it exceeds the fd xyarray boundaries and reads random memory. v2: Now that xyarrays save their original dimensions we can use these to iterate the two dimensional fd arrays. Fix some users (close, ioctl) in evsel.c to use these fields directly. This allows simplifying the code and dropping quite a few function arguments. Adjust all callers by removing the unneeded arguments. The actual perf event reading still uses the original values from the evsel list. Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170811232634.30465-2-andi@firstfloor.org [ Fix up xy_max_[xy]() -> xyarray__max_[xy]() ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-11 23:26:17 +00:00
void perf_evsel__close_fd(struct perf_evsel *evsel)
{
int cpu, thread;
perf evsel: Fix buffer overflow while freeing events Fix buffer overflow for: % perf stat -e msr/tsc/,cstate_core/c7-residency/ true that causes glibc free list corruption. For some reason it doesn't trigger in valgrind, but it is visible in AS: ================================================================= ==32681==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x603000003f5c at pc 0x0000005671ef bp 0x7ffdaaac9ac0 sp 0x7ffdaaac9ab0 READ of size 4 at 0x603000003f5c thread T0 #0 0x5671ee in perf_evsel__close_fd util/evsel.c:1196 #1 0x56c57a in perf_evsel__close util/evsel.c:1717 #2 0x55ed5f in perf_evlist__close util/evlist.c:1631 #3 0x4647e1 in __run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:749 #4 0x4648e3 in run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:767 #5 0x46e1bc in cmd_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:2785 #6 0x52f83d in run_builtin /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:296 #7 0x52fd49 in handle_internal_command /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:348 #8 0x5300de in run_argv /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:392 #9 0x5308f3 in main /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:530 #10 0x7f0672d13400 in __libc_start_main (/lib64/libc.so.6+0x20400) #11 0x428419 in _start (/home/ak/hle/obj-perf/perf+0x428419) 0x603000003f5c is located 0 bytes to the right of 28-byte region [0x603000003f40,0x603000003f5c) allocated by thread T0 here: #0 0x7f0675139020 in calloc (/lib64/libasan.so.3+0xc7020) #1 0x648a2d in zalloc util/util.h:23 #2 0x648a88 in xyarray__new util/xyarray.c:9 #3 0x566419 in perf_evsel__alloc_fd util/evsel.c:1039 #4 0x56b427 in perf_evsel__open util/evsel.c:1529 #5 0x56c620 in perf_evsel__open_per_thread util/evsel.c:1730 #6 0x461dea in create_perf_stat_counter /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:263 #7 0x4637d7 in __run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:600 #8 0x4648e3 in run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:767 #9 0x46e1bc in cmd_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:2785 #10 0x52f83d in run_builtin /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:296 #11 0x52fd49 in handle_internal_command /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:348 #12 0x5300de in run_argv /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:392 #13 0x5308f3 in main /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:530 #14 0x7f0672d13400 in __libc_start_main (/lib64/libc.so.6+0x20400) The event is allocated with cpus == 1, but freed with cpus == real number When the evsel close function walks the file descriptors it exceeds the fd xyarray boundaries and reads random memory. v2: Now that xyarrays save their original dimensions we can use these to iterate the two dimensional fd arrays. Fix some users (close, ioctl) in evsel.c to use these fields directly. This allows simplifying the code and dropping quite a few function arguments. Adjust all callers by removing the unneeded arguments. The actual perf event reading still uses the original values from the evsel list. Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170811232634.30465-2-andi@firstfloor.org [ Fix up xy_max_[xy]() -> xyarray__max_[xy]() ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-11 23:26:17 +00:00
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;
}
}
void perf_evsel__exit(struct perf_evsel *evsel)
{
assert(list_empty(&evsel->node));
assert(evsel->evlist == NULL);
perf evsel: Free evsel->counts in perf_evsel__exit() Using gcc's ASan, Changbin reports: ================================================================= ==7494==ERROR: LeakSanitizer: detected memory leaks Direct leak of 48 byte(s) in 1 object(s) allocated from: #0 0x7f0333a89138 in calloc (/usr/lib/x86_64-linux-gnu/libasan.so.5+0xee138) #1 0x5625e5330a5e in zalloc util/util.h:23 #2 0x5625e5330a9b in perf_counts__new util/counts.c:10 #3 0x5625e5330ca0 in perf_evsel__alloc_counts util/counts.c:47 #4 0x5625e520d8e5 in __perf_evsel__read_on_cpu util/evsel.c:1505 #5 0x5625e517a985 in perf_evsel__read_on_cpu /home/work/linux/tools/perf/util/evsel.h:347 #6 0x5625e517ad1a in test__openat_syscall_event tests/openat-syscall.c:47 #7 0x5625e51528e6 in run_test tests/builtin-test.c:358 #8 0x5625e5152baf in test_and_print tests/builtin-test.c:388 #9 0x5625e51543fe in __cmd_test tests/builtin-test.c:583 #10 0x5625e515572f in cmd_test tests/builtin-test.c:722 #11 0x5625e51c3fb8 in run_builtin /home/changbin/work/linux/tools/perf/perf.c:302 #12 0x5625e51c44f7 in handle_internal_command /home/changbin/work/linux/tools/perf/perf.c:354 #13 0x5625e51c48fb in run_argv /home/changbin/work/linux/tools/perf/perf.c:398 #14 0x5625e51c5069 in main /home/changbin/work/linux/tools/perf/perf.c:520 #15 0x7f033214d09a in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x2409a) Indirect leak of 72 byte(s) in 1 object(s) allocated from: #0 0x7f0333a89138 in calloc (/usr/lib/x86_64-linux-gnu/libasan.so.5+0xee138) #1 0x5625e532560d in zalloc util/util.h:23 #2 0x5625e532566b in xyarray__new util/xyarray.c:10 #3 0x5625e5330aba in perf_counts__new util/counts.c:15 #4 0x5625e5330ca0 in perf_evsel__alloc_counts util/counts.c:47 #5 0x5625e520d8e5 in __perf_evsel__read_on_cpu util/evsel.c:1505 #6 0x5625e517a985 in perf_evsel__read_on_cpu /home/work/linux/tools/perf/util/evsel.h:347 #7 0x5625e517ad1a in test__openat_syscall_event tests/openat-syscall.c:47 #8 0x5625e51528e6 in run_test tests/builtin-test.c:358 #9 0x5625e5152baf in test_and_print tests/builtin-test.c:388 #10 0x5625e51543fe in __cmd_test tests/builtin-test.c:583 #11 0x5625e515572f in cmd_test tests/builtin-test.c:722 #12 0x5625e51c3fb8 in run_builtin /home/changbin/work/linux/tools/perf/perf.c:302 #13 0x5625e51c44f7 in handle_internal_command /home/changbin/work/linux/tools/perf/perf.c:354 #14 0x5625e51c48fb in run_argv /home/changbin/work/linux/tools/perf/perf.c:398 #15 0x5625e51c5069 in main /home/changbin/work/linux/tools/perf/perf.c:520 #16 0x7f033214d09a in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x2409a) His patch took care of evsel->prev_raw_counts, but the above backtraces are about evsel->counts, so fix that instead. Reported-by: Changbin Du <changbin.du@gmail.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Link: https://lkml.kernel.org/n/tip-hd1x13g59f0nuhe4anxhsmfp@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-18 19:41:28 +00:00
perf_evsel__free_counts(evsel);
perf_evsel__free_fd(evsel);
perf_evsel__free_id(evsel);
perf_evsel__free_config_terms(evsel);
cgroup__put(evsel->cgrp);
cpu_map__put(evsel->cpus);
cpu_map__put(evsel->own_cpus);
thread_map__put(evsel->threads);
zfree(&evsel->group_name);
zfree(&evsel->name);
perf_evsel__object.fini(evsel);
}
void perf_evsel__delete(struct perf_evsel *evsel)
{
perf_evsel__exit(evsel);
free(evsel);
}
void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, int thread,
struct perf_counts_values *count)
{
struct perf_counts_values tmp;
if (!evsel->prev_raw_counts)
return;
if (cpu == -1) {
tmp = evsel->prev_raw_counts->aggr;
evsel->prev_raw_counts->aggr = *count;
} else {
tmp = *perf_counts(evsel->prev_raw_counts, cpu, thread);
*perf_counts(evsel->prev_raw_counts, cpu, thread) = *count;
}
count->val = count->val - tmp.val;
count->ena = count->ena - tmp.ena;
count->run = count->run - tmp.run;
}
void perf_counts_values__scale(struct perf_counts_values *count,
bool scale, s8 *pscaled)
{
s8 scaled = 0;
if (scale) {
if (count->run == 0) {
scaled = -1;
count->val = 0;
} else if (count->run < count->ena) {
scaled = 1;
count->val = (u64)((double) count->val * count->ena / count->run);
}
}
if (pscaled)
*pscaled = scaled;
}
static int perf_evsel__read_size(struct perf_evsel *evsel)
{
u64 read_format = evsel->attr.read_format;
int entry = sizeof(u64); /* value */
int size = 0;
int nr = 1;
if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
size += sizeof(u64);
if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
size += sizeof(u64);
if (read_format & PERF_FORMAT_ID)
entry += sizeof(u64);
if (read_format & PERF_FORMAT_GROUP) {
nr = evsel->nr_members;
size += sizeof(u64);
}
size += entry * nr;
return size;
}
int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
struct perf_counts_values *count)
{
size_t size = perf_evsel__read_size(evsel);
memset(count, 0, sizeof(*count));
if (FD(evsel, cpu, thread) < 0)
return -EINVAL;
if (readn(FD(evsel, cpu, thread), count->values, size) <= 0)
return -errno;
return 0;
}
static int
perf_evsel__read_one(struct perf_evsel *evsel, int cpu, int thread)
{
struct perf_counts_values *count = perf_counts(evsel->counts, cpu, thread);
return perf_evsel__read(evsel, cpu, thread, count);
}
static void
perf_evsel__set_count(struct perf_evsel *counter, int cpu, int thread,
u64 val, u64 ena, u64 run)
{
struct perf_counts_values *count;
count = perf_counts(counter->counts, cpu, thread);
count->val = val;
count->ena = ena;
count->run = run;
count->loaded = true;
}
static int
perf_evsel__process_group_data(struct perf_evsel *leader,
int cpu, int thread, u64 *data)
{
u64 read_format = leader->attr.read_format;
struct sample_read_value *v;
u64 nr, ena = 0, run = 0, i;
nr = *data++;
if (nr != (u64) leader->nr_members)
return -EINVAL;
if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
ena = *data++;
if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
run = *data++;
v = (struct sample_read_value *) data;
perf_evsel__set_count(leader, cpu, thread,
v[0].value, ena, run);
for (i = 1; i < nr; i++) {
struct perf_evsel *counter;
counter = perf_evlist__id2evsel(leader->evlist, v[i].id);
if (!counter)
return -EINVAL;
perf_evsel__set_count(counter, cpu, thread,
v[i].value, ena, run);
}
return 0;
}
static int
perf_evsel__read_group(struct perf_evsel *leader, int cpu, int thread)
{
struct perf_stat_evsel *ps = leader->stats;
u64 read_format = leader->attr.read_format;
int size = perf_evsel__read_size(leader);
u64 *data = ps->group_data;
if (!(read_format & PERF_FORMAT_ID))
return -EINVAL;
if (!perf_evsel__is_group_leader(leader))
return -EINVAL;
if (!data) {
data = zalloc(size);
if (!data)
return -ENOMEM;
ps->group_data = data;
}
if (FD(leader, cpu, thread) < 0)
return -EINVAL;
if (readn(FD(leader, cpu, thread), data, size) <= 0)
return -errno;
return perf_evsel__process_group_data(leader, cpu, thread, data);
}
int perf_evsel__read_counter(struct perf_evsel *evsel, int cpu, int thread)
{
u64 read_format = evsel->attr.read_format;
if (read_format & PERF_FORMAT_GROUP)
return perf_evsel__read_group(evsel, cpu, thread);
else
return perf_evsel__read_one(evsel, cpu, thread);
}
int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
int cpu, int thread, bool scale)
{
struct perf_counts_values count;
size_t nv = scale ? 3 : 1;
if (FD(evsel, cpu, thread) < 0)
return -EINVAL;
if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1, thread + 1) < 0)
return -ENOMEM;
if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) <= 0)
return -errno;
perf_evsel__compute_deltas(evsel, cpu, thread, &count);
perf_counts_values__scale(&count, scale, NULL);
*perf_counts(evsel->counts, cpu, thread) = count;
return 0;
}
perf tools: Enable grouping logic for parsed events This patch adds a functionality that allows to create event groups based on the way they are specified on the command line. Adding functionality to the '{}' group syntax introduced in earlier patch. The current '--group/-g' option behaviour remains intact. If you specify it for record/stat/top command, all the specified events become members of a single group with the first event as a group leader. With the new '{}' group syntax you can create group like: # perf record -e '{cycles,faults}' ls resulting in single event group containing 'cycles' and 'faults' events, with cycles event as group leader. All groups are created with regards to threads and cpus. Thus recording an event group within a 2 threads on server with 4 CPUs will create 8 separate groups. Examples (first event in brackets is group leader): # 1 group (cpu-clock,task-clock) perf record --group -e cpu-clock,task-clock ls perf record -e '{cpu-clock,task-clock}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock},{minor-faults,major-faults}' ls # 1 group (cpu-clock,task-clock,minor-faults,major-faults) perf record --group -e cpu-clock,task-clock -e minor-faults,major-faults ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock} -e '{minor-faults,major-faults}' \ -e instructions ls # 1 group # (cpu-clock,task-clock,minor-faults,major-faults,instructions) perf record --group -e cpu-clock,task-clock \ -e minor-faults,major-faults -e instructions ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults,instructions}' ls It's possible to use standard event modifier for a group, which spans over all events in the group and updates each event modifier settings, for example: # perf record -r '{faults:k,cache-references}:p' resulting in ':kp' modifier being used for 'faults' and ':p' modifier being used for 'cache-references' event. Reviewed-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Drepper <drepper@gmail.com> Link: http://lkml.kernel.org/n/tip-ho42u0wcr8mn1otkalqi13qp@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-08-08 10:22:36 +00:00
static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread)
{
struct perf_evsel *leader = evsel->leader;
int fd;
if (perf_evsel__is_group_leader(evsel))
perf tools: Enable grouping logic for parsed events This patch adds a functionality that allows to create event groups based on the way they are specified on the command line. Adding functionality to the '{}' group syntax introduced in earlier patch. The current '--group/-g' option behaviour remains intact. If you specify it for record/stat/top command, all the specified events become members of a single group with the first event as a group leader. With the new '{}' group syntax you can create group like: # perf record -e '{cycles,faults}' ls resulting in single event group containing 'cycles' and 'faults' events, with cycles event as group leader. All groups are created with regards to threads and cpus. Thus recording an event group within a 2 threads on server with 4 CPUs will create 8 separate groups. Examples (first event in brackets is group leader): # 1 group (cpu-clock,task-clock) perf record --group -e cpu-clock,task-clock ls perf record -e '{cpu-clock,task-clock}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock},{minor-faults,major-faults}' ls # 1 group (cpu-clock,task-clock,minor-faults,major-faults) perf record --group -e cpu-clock,task-clock -e minor-faults,major-faults ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock} -e '{minor-faults,major-faults}' \ -e instructions ls # 1 group # (cpu-clock,task-clock,minor-faults,major-faults,instructions) perf record --group -e cpu-clock,task-clock \ -e minor-faults,major-faults -e instructions ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults,instructions}' ls It's possible to use standard event modifier for a group, which spans over all events in the group and updates each event modifier settings, for example: # perf record -r '{faults:k,cache-references}:p' resulting in ':kp' modifier being used for 'faults' and ':p' modifier being used for 'cache-references' event. Reviewed-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Drepper <drepper@gmail.com> Link: http://lkml.kernel.org/n/tip-ho42u0wcr8mn1otkalqi13qp@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-08-08 10:22:36 +00:00
return -1;
/*
* Leader must be already processed/open,
* if not it's a bug.
*/
BUG_ON(!leader->fd);
fd = FD(leader, cpu, thread);
BUG_ON(fd == -1);
return fd;
}
perf tools: Merge all perf_event_attr print functions Currently there's 3 (that I found) different and incomplete implementations of printing perf_event_attr. This is quite silly. Merge the lot. While this patch does not retain the exact form all printing that I found is debug output and thus it should not be critical. Also, I cannot find a single print_event_desc() caller. Pre: $ perf record -vv -e cycles -- sleep 1 ------------------------------------------------------------ perf_event_attr: type 0 size 104 config 0 sample_period 4000 sample_freq 4000 sample_type 0x107 read_format 0 disabled 1 inherit 1 pinned 0 exclusive 0 exclude_user 0 exclude_kernel 0 exclude_hv 0 exclude_idle 0 mmap 1 comm 1 mmap2 1 comm_exec 1 freq 1 inherit_stat 0 enable_on_exec 1 task 1 watermark 0 precise_ip 0 mmap_data 0 sample_id_all 1 exclude_host 0 exclude_guest 1 excl.callchain_kern 0 excl.callchain_user 0 wakeup_events 0 wakeup_watermark 0 bp_type 0 bp_addr 0 config1 0 bp_len 0 config2 0 branch_sample_type 0 sample_regs_user 0 sample_stack_user 0 sample_regs_intr 0 ------------------------------------------------------------ $ perf evlist -vv cycles: sample_freq=4000, size: 104, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, mmap2: 1, comm: 1, comm_exec: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1 Post: $ ./perf record -vv -e cycles -- sleep 1 ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ------------------------------------------------------------ $ ./perf evlist -vv cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: David Ahern <dsahern@gmail.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20150407091150.644238729@infradead.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-07 09:09:54 +00:00
struct bit_names {
int bit;
const char *name;
};
static void __p_bits(char *buf, size_t size, u64 value, struct bit_names *bits)
{
bool first_bit = true;
int i = 0;
do {
if (value & bits[i].bit) {
buf += scnprintf(buf, size, "%s%s", first_bit ? "" : "|", bits[i].name);
first_bit = false;
}
} while (bits[++i].name != NULL);
}
static void __p_sample_type(char *buf, size_t size, u64 value)
{
#define bit_name(n) { PERF_SAMPLE_##n, #n }
struct bit_names bits[] = {
bit_name(IP), bit_name(TID), bit_name(TIME), bit_name(ADDR),
bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU),
bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC),
bit_name(WEIGHT), bit_name(PHYS_ADDR),
perf tools: Merge all perf_event_attr print functions Currently there's 3 (that I found) different and incomplete implementations of printing perf_event_attr. This is quite silly. Merge the lot. While this patch does not retain the exact form all printing that I found is debug output and thus it should not be critical. Also, I cannot find a single print_event_desc() caller. Pre: $ perf record -vv -e cycles -- sleep 1 ------------------------------------------------------------ perf_event_attr: type 0 size 104 config 0 sample_period 4000 sample_freq 4000 sample_type 0x107 read_format 0 disabled 1 inherit 1 pinned 0 exclusive 0 exclude_user 0 exclude_kernel 0 exclude_hv 0 exclude_idle 0 mmap 1 comm 1 mmap2 1 comm_exec 1 freq 1 inherit_stat 0 enable_on_exec 1 task 1 watermark 0 precise_ip 0 mmap_data 0 sample_id_all 1 exclude_host 0 exclude_guest 1 excl.callchain_kern 0 excl.callchain_user 0 wakeup_events 0 wakeup_watermark 0 bp_type 0 bp_addr 0 config1 0 bp_len 0 config2 0 branch_sample_type 0 sample_regs_user 0 sample_stack_user 0 sample_regs_intr 0 ------------------------------------------------------------ $ perf evlist -vv cycles: sample_freq=4000, size: 104, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, mmap2: 1, comm: 1, comm_exec: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1 Post: $ ./perf record -vv -e cycles -- sleep 1 ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ------------------------------------------------------------ $ ./perf evlist -vv cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: David Ahern <dsahern@gmail.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20150407091150.644238729@infradead.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-07 09:09:54 +00:00
{ .name = NULL, }
};
#undef bit_name
__p_bits(buf, size, value, bits);
}
static void __p_branch_sample_type(char *buf, size_t size, u64 value)
{
#define bit_name(n) { PERF_SAMPLE_BRANCH_##n, #n }
struct bit_names bits[] = {
bit_name(USER), bit_name(KERNEL), bit_name(HV), bit_name(ANY),
bit_name(ANY_CALL), bit_name(ANY_RETURN), bit_name(IND_CALL),
bit_name(ABORT_TX), bit_name(IN_TX), bit_name(NO_TX),
bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP),
bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES),
{ .name = NULL, }
};
#undef bit_name
__p_bits(buf, size, value, bits);
}
perf tools: Merge all perf_event_attr print functions Currently there's 3 (that I found) different and incomplete implementations of printing perf_event_attr. This is quite silly. Merge the lot. While this patch does not retain the exact form all printing that I found is debug output and thus it should not be critical. Also, I cannot find a single print_event_desc() caller. Pre: $ perf record -vv -e cycles -- sleep 1 ------------------------------------------------------------ perf_event_attr: type 0 size 104 config 0 sample_period 4000 sample_freq 4000 sample_type 0x107 read_format 0 disabled 1 inherit 1 pinned 0 exclusive 0 exclude_user 0 exclude_kernel 0 exclude_hv 0 exclude_idle 0 mmap 1 comm 1 mmap2 1 comm_exec 1 freq 1 inherit_stat 0 enable_on_exec 1 task 1 watermark 0 precise_ip 0 mmap_data 0 sample_id_all 1 exclude_host 0 exclude_guest 1 excl.callchain_kern 0 excl.callchain_user 0 wakeup_events 0 wakeup_watermark 0 bp_type 0 bp_addr 0 config1 0 bp_len 0 config2 0 branch_sample_type 0 sample_regs_user 0 sample_stack_user 0 sample_regs_intr 0 ------------------------------------------------------------ $ perf evlist -vv cycles: sample_freq=4000, size: 104, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, mmap2: 1, comm: 1, comm_exec: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1 Post: $ ./perf record -vv -e cycles -- sleep 1 ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ------------------------------------------------------------ $ ./perf evlist -vv cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: David Ahern <dsahern@gmail.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20150407091150.644238729@infradead.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-07 09:09:54 +00:00
static void __p_read_format(char *buf, size_t size, u64 value)
{
#define bit_name(n) { PERF_FORMAT_##n, #n }
struct bit_names bits[] = {
bit_name(TOTAL_TIME_ENABLED), bit_name(TOTAL_TIME_RUNNING),
bit_name(ID), bit_name(GROUP),
{ .name = NULL, }
};
#undef bit_name
__p_bits(buf, size, value, bits);
}
#define BUF_SIZE 1024
#define p_hex(val) snprintf(buf, BUF_SIZE, "%#"PRIx64, (uint64_t)(val))
perf tools: Merge all perf_event_attr print functions Currently there's 3 (that I found) different and incomplete implementations of printing perf_event_attr. This is quite silly. Merge the lot. While this patch does not retain the exact form all printing that I found is debug output and thus it should not be critical. Also, I cannot find a single print_event_desc() caller. Pre: $ perf record -vv -e cycles -- sleep 1 ------------------------------------------------------------ perf_event_attr: type 0 size 104 config 0 sample_period 4000 sample_freq 4000 sample_type 0x107 read_format 0 disabled 1 inherit 1 pinned 0 exclusive 0 exclude_user 0 exclude_kernel 0 exclude_hv 0 exclude_idle 0 mmap 1 comm 1 mmap2 1 comm_exec 1 freq 1 inherit_stat 0 enable_on_exec 1 task 1 watermark 0 precise_ip 0 mmap_data 0 sample_id_all 1 exclude_host 0 exclude_guest 1 excl.callchain_kern 0 excl.callchain_user 0 wakeup_events 0 wakeup_watermark 0 bp_type 0 bp_addr 0 config1 0 bp_len 0 config2 0 branch_sample_type 0 sample_regs_user 0 sample_stack_user 0 sample_regs_intr 0 ------------------------------------------------------------ $ perf evlist -vv cycles: sample_freq=4000, size: 104, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, mmap2: 1, comm: 1, comm_exec: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1 Post: $ ./perf record -vv -e cycles -- sleep 1 ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ------------------------------------------------------------ $ ./perf evlist -vv cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: David Ahern <dsahern@gmail.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20150407091150.644238729@infradead.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-07 09:09:54 +00:00
#define p_unsigned(val) snprintf(buf, BUF_SIZE, "%"PRIu64, (uint64_t)(val))
#define p_signed(val) snprintf(buf, BUF_SIZE, "%"PRId64, (int64_t)(val))
#define p_sample_type(val) __p_sample_type(buf, BUF_SIZE, val)
#define p_branch_sample_type(val) __p_branch_sample_type(buf, BUF_SIZE, val)
perf tools: Merge all perf_event_attr print functions Currently there's 3 (that I found) different and incomplete implementations of printing perf_event_attr. This is quite silly. Merge the lot. While this patch does not retain the exact form all printing that I found is debug output and thus it should not be critical. Also, I cannot find a single print_event_desc() caller. Pre: $ perf record -vv -e cycles -- sleep 1 ------------------------------------------------------------ perf_event_attr: type 0 size 104 config 0 sample_period 4000 sample_freq 4000 sample_type 0x107 read_format 0 disabled 1 inherit 1 pinned 0 exclusive 0 exclude_user 0 exclude_kernel 0 exclude_hv 0 exclude_idle 0 mmap 1 comm 1 mmap2 1 comm_exec 1 freq 1 inherit_stat 0 enable_on_exec 1 task 1 watermark 0 precise_ip 0 mmap_data 0 sample_id_all 1 exclude_host 0 exclude_guest 1 excl.callchain_kern 0 excl.callchain_user 0 wakeup_events 0 wakeup_watermark 0 bp_type 0 bp_addr 0 config1 0 bp_len 0 config2 0 branch_sample_type 0 sample_regs_user 0 sample_stack_user 0 sample_regs_intr 0 ------------------------------------------------------------ $ perf evlist -vv cycles: sample_freq=4000, size: 104, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, mmap2: 1, comm: 1, comm_exec: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1 Post: $ ./perf record -vv -e cycles -- sleep 1 ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ------------------------------------------------------------ $ ./perf evlist -vv cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: David Ahern <dsahern@gmail.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20150407091150.644238729@infradead.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-07 09:09:54 +00:00
#define p_read_format(val) __p_read_format(buf, BUF_SIZE, val)
#define PRINT_ATTRn(_n, _f, _p) \
do { \
if (attr->_f) { \
_p(attr->_f); \
ret += attr__fprintf(fp, _n, buf, priv);\
} \
} while (0)
#define PRINT_ATTRf(_f, _p) PRINT_ATTRn(#_f, _f, _p)
int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
attr__fprintf_f attr__fprintf, void *priv)
{
char buf[BUF_SIZE];
int ret = 0;
PRINT_ATTRf(type, p_unsigned);
PRINT_ATTRf(size, p_unsigned);
PRINT_ATTRf(config, p_hex);
PRINT_ATTRn("{ sample_period, sample_freq }", sample_period, p_unsigned);
PRINT_ATTRf(sample_type, p_sample_type);
PRINT_ATTRf(read_format, p_read_format);
PRINT_ATTRf(disabled, p_unsigned);
PRINT_ATTRf(inherit, p_unsigned);
PRINT_ATTRf(pinned, p_unsigned);
PRINT_ATTRf(exclusive, p_unsigned);
PRINT_ATTRf(exclude_user, p_unsigned);
PRINT_ATTRf(exclude_kernel, p_unsigned);
PRINT_ATTRf(exclude_hv, p_unsigned);
PRINT_ATTRf(exclude_idle, p_unsigned);
PRINT_ATTRf(mmap, p_unsigned);
PRINT_ATTRf(comm, p_unsigned);
PRINT_ATTRf(freq, p_unsigned);
PRINT_ATTRf(inherit_stat, p_unsigned);
PRINT_ATTRf(enable_on_exec, p_unsigned);
PRINT_ATTRf(task, p_unsigned);
PRINT_ATTRf(watermark, p_unsigned);
PRINT_ATTRf(precise_ip, p_unsigned);
PRINT_ATTRf(mmap_data, p_unsigned);
PRINT_ATTRf(sample_id_all, p_unsigned);
PRINT_ATTRf(exclude_host, p_unsigned);
PRINT_ATTRf(exclude_guest, p_unsigned);
PRINT_ATTRf(exclude_callchain_kernel, p_unsigned);
PRINT_ATTRf(exclude_callchain_user, p_unsigned);
PRINT_ATTRf(mmap2, p_unsigned);
PRINT_ATTRf(comm_exec, p_unsigned);
PRINT_ATTRf(use_clockid, p_unsigned);
PRINT_ATTRf(context_switch, p_unsigned);
PRINT_ATTRf(write_backward, p_unsigned);
PRINT_ATTRf(namespaces, p_unsigned);
PRINT_ATTRf(ksymbol, p_unsigned);
perf tools: Handle PERF_RECORD_BPF_EVENT This patch adds basic handling of PERF_RECORD_BPF_EVENT. Tracking of PERF_RECORD_BPF_EVENT is OFF by default. Option --bpf-event is added to turn it on. Committer notes: Add dummy machine__process_bpf_event() variant that returns zero for systems without HAVE_LIBBPF_SUPPORT, such as Alpine Linux, unbreaking the build in such systems. Remove the needless include <machine.h> from bpf->event.h, provide just forward declarations for the structs and unions in the parameters, to reduce compilation time and needless rebuilds when machine.h gets changed. Committer testing: When running with: # perf record --bpf-event On an older kernel where PERF_RECORD_BPF_EVENT and PERF_RECORD_KSYMBOL is not present, we fallback to removing those two bits from perf_event_attr, making the tool to continue to work on older kernels: perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD read_format ID disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 precise_ip 3 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 bpf_event 1 ------------------------------------------------------------ sys_perf_event_open: pid 5779 cpu 0 group_fd -1 flags 0x8 sys_perf_event_open failed, error -22 switching off bpf_event ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD read_format ID disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 precise_ip 3 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 ------------------------------------------------------------ sys_perf_event_open: pid 5779 cpu 0 group_fd -1 flags 0x8 sys_perf_event_open failed, error -22 switching off ksymbol ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD read_format ID disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 precise_ip 3 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ------------------------------------------------------------ And then proceeds to work without those two features. As passing --bpf-event is an explicit action performed by the user, perhaps we should emit a warning telling that the kernel has no such feature, but this can be done on top of this patch. Now with a kernel that supports these events, start the 'record --bpf-event -a' and then run 'perf trace sleep 10000' that will use the BPF augmented_raw_syscalls.o prebuilt (for another kernel version even) and thus should generate PERF_RECORD_BPF_EVENT events: [root@quaco ~]# perf record -e dummy -a --bpf-event ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.713 MB perf.data ] [root@quaco ~]# bpftool prog 13: cgroup_skb tag 7be49e3934a125ba gpl loaded_at 2019-01-19T09:09:43-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 13,14 14: cgroup_skb tag 2a142ef67aaad174 gpl loaded_at 2019-01-19T09:09:43-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 13,14 15: cgroup_skb tag 7be49e3934a125ba gpl loaded_at 2019-01-19T09:09:43-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 15,16 16: cgroup_skb tag 2a142ef67aaad174 gpl loaded_at 2019-01-19T09:09:43-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 15,16 17: cgroup_skb tag 7be49e3934a125ba gpl loaded_at 2019-01-19T09:09:44-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 17,18 18: cgroup_skb tag 2a142ef67aaad174 gpl loaded_at 2019-01-19T09:09:44-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 17,18 21: cgroup_skb tag 7be49e3934a125ba gpl loaded_at 2019-01-19T09:09:45-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 21,22 22: cgroup_skb tag 2a142ef67aaad174 gpl loaded_at 2019-01-19T09:09:45-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 21,22 31: tracepoint name sys_enter tag 12504ba9402f952f gpl loaded_at 2019-01-19T09:19:56-0300 uid 0 xlated 512B jited 374B memlock 4096B map_ids 30,29,28 32: tracepoint name sys_exit tag c1bd85c092d6e4aa gpl loaded_at 2019-01-19T09:19:56-0300 uid 0 xlated 256B jited 191B memlock 4096B map_ids 30,29 # perf report -D | grep PERF_RECORD_BPF_EVENT | nl 1 0 55834574849 0x4fc8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 13 2 0 60129542145 0x5118 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 14 3 0 64424509441 0x5268 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 15 4 0 68719476737 0x53b8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 16 5 0 73014444033 0x5508 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 17 6 0 77309411329 0x5658 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 18 7 0 90194313217 0x57a8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 21 8 0 94489280513 0x58f8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 22 9 7 620922484360 0xb6390 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 29 10 7 620922486018 0xb6410 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 2, flags 0, id 29 11 7 620922579199 0xb6490 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 30 12 7 620922580240 0xb6510 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 2, flags 0, id 30 13 7 620922765207 0xb6598 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 31 14 7 620922874543 0xb6620 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 32 # There, the 31 and 32 tracepoint BPF programs put in place by 'perf trace'. Signed-off-by: Song Liu <songliubraving@fb.com> Reviewed-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: kernel-team@fb.com Cc: netdev@vger.kernel.org Link: http://lkml.kernel.org/r/20190117161521.1341602-7-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-01-17 16:15:18 +00:00
PRINT_ATTRf(bpf_event, p_unsigned);
perf tools: Merge all perf_event_attr print functions Currently there's 3 (that I found) different and incomplete implementations of printing perf_event_attr. This is quite silly. Merge the lot. While this patch does not retain the exact form all printing that I found is debug output and thus it should not be critical. Also, I cannot find a single print_event_desc() caller. Pre: $ perf record -vv -e cycles -- sleep 1 ------------------------------------------------------------ perf_event_attr: type 0 size 104 config 0 sample_period 4000 sample_freq 4000 sample_type 0x107 read_format 0 disabled 1 inherit 1 pinned 0 exclusive 0 exclude_user 0 exclude_kernel 0 exclude_hv 0 exclude_idle 0 mmap 1 comm 1 mmap2 1 comm_exec 1 freq 1 inherit_stat 0 enable_on_exec 1 task 1 watermark 0 precise_ip 0 mmap_data 0 sample_id_all 1 exclude_host 0 exclude_guest 1 excl.callchain_kern 0 excl.callchain_user 0 wakeup_events 0 wakeup_watermark 0 bp_type 0 bp_addr 0 config1 0 bp_len 0 config2 0 branch_sample_type 0 sample_regs_user 0 sample_stack_user 0 sample_regs_intr 0 ------------------------------------------------------------ $ perf evlist -vv cycles: sample_freq=4000, size: 104, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, mmap2: 1, comm: 1, comm_exec: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1 Post: $ ./perf record -vv -e cycles -- sleep 1 ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ------------------------------------------------------------ $ ./perf evlist -vv cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: David Ahern <dsahern@gmail.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20150407091150.644238729@infradead.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-07 09:09:54 +00:00
PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned);
PRINT_ATTRf(bp_type, p_unsigned);
PRINT_ATTRn("{ bp_addr, config1 }", bp_addr, p_hex);
PRINT_ATTRn("{ bp_len, config2 }", bp_len, p_hex);
PRINT_ATTRf(branch_sample_type, p_branch_sample_type);
perf tools: Merge all perf_event_attr print functions Currently there's 3 (that I found) different and incomplete implementations of printing perf_event_attr. This is quite silly. Merge the lot. While this patch does not retain the exact form all printing that I found is debug output and thus it should not be critical. Also, I cannot find a single print_event_desc() caller. Pre: $ perf record -vv -e cycles -- sleep 1 ------------------------------------------------------------ perf_event_attr: type 0 size 104 config 0 sample_period 4000 sample_freq 4000 sample_type 0x107 read_format 0 disabled 1 inherit 1 pinned 0 exclusive 0 exclude_user 0 exclude_kernel 0 exclude_hv 0 exclude_idle 0 mmap 1 comm 1 mmap2 1 comm_exec 1 freq 1 inherit_stat 0 enable_on_exec 1 task 1 watermark 0 precise_ip 0 mmap_data 0 sample_id_all 1 exclude_host 0 exclude_guest 1 excl.callchain_kern 0 excl.callchain_user 0 wakeup_events 0 wakeup_watermark 0 bp_type 0 bp_addr 0 config1 0 bp_len 0 config2 0 branch_sample_type 0 sample_regs_user 0 sample_stack_user 0 sample_regs_intr 0 ------------------------------------------------------------ $ perf evlist -vv cycles: sample_freq=4000, size: 104, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, mmap2: 1, comm: 1, comm_exec: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1 Post: $ ./perf record -vv -e cycles -- sleep 1 ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ------------------------------------------------------------ $ ./perf evlist -vv cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: David Ahern <dsahern@gmail.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20150407091150.644238729@infradead.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-07 09:09:54 +00:00
PRINT_ATTRf(sample_regs_user, p_hex);
PRINT_ATTRf(sample_stack_user, p_unsigned);
PRINT_ATTRf(clockid, p_signed);
PRINT_ATTRf(sample_regs_intr, p_hex);
PRINT_ATTRf(aux_watermark, p_unsigned);
perf tools: Per event max-stack settings The tooling counterpart, now it is possible to do: # perf record -e sched:sched_switch/max-stack=10/ -e cycles/call-graph=dwarf,max-stack=4/ -e cpu-cycles/call-graph=dwarf,max-stack=1024/ usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.052 MB perf.data (5 samples) ] # perf evlist -v sched:sched_switch: type: 2, size: 112, config: 0x110, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CALLCHAIN|CPU|PERIOD|RAW|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, sample_max_stack: 10 cycles/call-graph=dwarf,max-stack=4/: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|PERIOD|REGS_USER|STACK_USER|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, freq: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1, exclude_callchain_user: 1, sample_regs_user: 0xff0fff, sample_stack_user: 8192, sample_max_stack: 4 cpu-cycles/call-graph=dwarf,max-stack=1024/: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CALLCHAIN|PERIOD|REGS_USER|STACK_USER|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, freq: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1, exclude_callchain_user: 1, sample_regs_user: 0xff0fff, sample_stack_user: 8192, sample_max_stack: 1024 # Tip: use 'perf evlist --trace-fields' to show fields for tracepoint events Using just /max-stack=N/ means /call-graph=fp,max-stack=N/, that should be further configurable by means of some .perfconfig knob. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: He Kuang <hekuang@huawei.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Milian Wolff <milian.wolff@kdab.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: Wang Nan <wangnan0@huawei.com> Cc: Zefan Li <lizefan@huawei.com> Link: http://lkml.kernel.org/n/tip-kolmn1yo40p7jhswxwrc7rrd@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-28 22:03:42 +00:00
PRINT_ATTRf(sample_max_stack, p_unsigned);
return ret;
}
perf tools: Merge all perf_event_attr print functions Currently there's 3 (that I found) different and incomplete implementations of printing perf_event_attr. This is quite silly. Merge the lot. While this patch does not retain the exact form all printing that I found is debug output and thus it should not be critical. Also, I cannot find a single print_event_desc() caller. Pre: $ perf record -vv -e cycles -- sleep 1 ------------------------------------------------------------ perf_event_attr: type 0 size 104 config 0 sample_period 4000 sample_freq 4000 sample_type 0x107 read_format 0 disabled 1 inherit 1 pinned 0 exclusive 0 exclude_user 0 exclude_kernel 0 exclude_hv 0 exclude_idle 0 mmap 1 comm 1 mmap2 1 comm_exec 1 freq 1 inherit_stat 0 enable_on_exec 1 task 1 watermark 0 precise_ip 0 mmap_data 0 sample_id_all 1 exclude_host 0 exclude_guest 1 excl.callchain_kern 0 excl.callchain_user 0 wakeup_events 0 wakeup_watermark 0 bp_type 0 bp_addr 0 config1 0 bp_len 0 config2 0 branch_sample_type 0 sample_regs_user 0 sample_stack_user 0 sample_regs_intr 0 ------------------------------------------------------------ $ perf evlist -vv cycles: sample_freq=4000, size: 104, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, mmap2: 1, comm: 1, comm_exec: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1 Post: $ ./perf record -vv -e cycles -- sleep 1 ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ------------------------------------------------------------ $ ./perf evlist -vv cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: David Ahern <dsahern@gmail.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20150407091150.644238729@infradead.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-07 09:09:54 +00:00
static int __open_attr__fprintf(FILE *fp, const char *name, const char *val,
void *priv __maybe_unused)
perf tools: Merge all perf_event_attr print functions Currently there's 3 (that I found) different and incomplete implementations of printing perf_event_attr. This is quite silly. Merge the lot. While this patch does not retain the exact form all printing that I found is debug output and thus it should not be critical. Also, I cannot find a single print_event_desc() caller. Pre: $ perf record -vv -e cycles -- sleep 1 ------------------------------------------------------------ perf_event_attr: type 0 size 104 config 0 sample_period 4000 sample_freq 4000 sample_type 0x107 read_format 0 disabled 1 inherit 1 pinned 0 exclusive 0 exclude_user 0 exclude_kernel 0 exclude_hv 0 exclude_idle 0 mmap 1 comm 1 mmap2 1 comm_exec 1 freq 1 inherit_stat 0 enable_on_exec 1 task 1 watermark 0 precise_ip 0 mmap_data 0 sample_id_all 1 exclude_host 0 exclude_guest 1 excl.callchain_kern 0 excl.callchain_user 0 wakeup_events 0 wakeup_watermark 0 bp_type 0 bp_addr 0 config1 0 bp_len 0 config2 0 branch_sample_type 0 sample_regs_user 0 sample_stack_user 0 sample_regs_intr 0 ------------------------------------------------------------ $ perf evlist -vv cycles: sample_freq=4000, size: 104, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, mmap2: 1, comm: 1, comm_exec: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1 Post: $ ./perf record -vv -e cycles -- sleep 1 ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ------------------------------------------------------------ $ ./perf evlist -vv cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: David Ahern <dsahern@gmail.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20150407091150.644238729@infradead.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-07 09:09:54 +00:00
{
return fprintf(fp, " %-32s %s\n", name, val);
}
perf evsel: Enable ignore_missing_thread for pid option While monitoring a multithread process with pid option, perf sometimes may return sys_perf_event_open failure with 3(No such process) if any of the process's threads die before we open the event. However, we want perf continue monitoring the remaining threads and do not exit with error. Here, the patch enables perf_evsel::ignore_missing_thread for -p option to ignore complete failure if any of threads die before we open the event. But it may still return sys_perf_event_open failure with 22(Invalid) if we monitors several event groups. sys_perf_event_open: pid 28960 cpu 40 group_fd 118202 flags 0x8 sys_perf_event_open: pid 28961 cpu 40 group_fd 118203 flags 0x8 WARNING: Ignored open failure for pid 28962 sys_perf_event_open: pid 28962 cpu 40 group_fd [118203] flags 0x8 sys_perf_event_open failed, error -22 That is because when we ignore a missing thread, we change the thread_idx without dealing with its fds, FD(evsel, cpu, thread). Then get_group_fd() may return a wrong group_fd for the next thread and sys_perf_event_open() return with 22. sys_perf_event_open(){ ... if (group_fd != -1) perf_fget_light()//to get corresponding group_leader by group_fd ... if (group_leader) if (group_leader->ctx->task != ctx->task)//should on the same task goto err_context ... } This patch also fixes this bug by introducing perf_evsel__remove_fd() and update_fds to allow removing fds for the missing thread. Changes since v1: - Change group_fd__remove() into a more genetic way without changing code logic - Remove redundant condition Changes since v2: - Use a proper function name and add some comment. - Multiline comment style fixes. Committer testing: Before this patch the recently added 'perf stat --per-thread' for system wide counting would race while enumerating all threads using /proc: [root@jouet ~]# perf stat --per-thread failed to parse CPUs map: No such file or directory Usage: perf stat [<options>] [<command>] -C, --cpu <cpu> list of cpus to monitor in system-wide -a, --all-cpus system-wide collection from all CPUs [root@jouet ~]# perf stat --per-thread failed to parse CPUs map: No such file or directory Usage: perf stat [<options>] [<command>] -C, --cpu <cpu> list of cpus to monitor in system-wide -a, --all-cpus system-wide collection from all CPUs [root@jouet ~]# When, say, the kernel was being built, so lots of shortlived threads, after this patch this doesn't happen. Signed-off-by: Mengting Zhang <zhangmengting@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Cheng Jian <cj.chengjian@huawei.com> Cc: Li Bin <huawei.libin@huawei.com> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1513148513-6974-1-git-send-email-zhangmengting@huawei.com [ Remove one use 'evlist' alias variable ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-12-13 07:01:53 +00:00
static void perf_evsel__remove_fd(struct perf_evsel *pos,
int nr_cpus, int nr_threads,
int thread_idx)
{
for (int cpu = 0; cpu < nr_cpus; cpu++)
for (int thread = thread_idx; thread < nr_threads - 1; thread++)
FD(pos, cpu, thread) = FD(pos, cpu, thread + 1);
}
static int update_fds(struct perf_evsel *evsel,
int nr_cpus, int cpu_idx,
int nr_threads, int thread_idx)
{
struct perf_evsel *pos;
if (cpu_idx >= nr_cpus || thread_idx >= nr_threads)
return -EINVAL;
evlist__for_each_entry(evsel->evlist, pos) {
nr_cpus = pos != evsel ? nr_cpus : cpu_idx;
perf_evsel__remove_fd(pos, nr_cpus, nr_threads, thread_idx);
/*
* Since fds for next evsel has not been created,
* there is no need to iterate whole event list.
*/
if (pos == evsel)
break;
}
return 0;
}
static bool ignore_missing_thread(struct perf_evsel *evsel,
perf evsel: Enable ignore_missing_thread for pid option While monitoring a multithread process with pid option, perf sometimes may return sys_perf_event_open failure with 3(No such process) if any of the process's threads die before we open the event. However, we want perf continue monitoring the remaining threads and do not exit with error. Here, the patch enables perf_evsel::ignore_missing_thread for -p option to ignore complete failure if any of threads die before we open the event. But it may still return sys_perf_event_open failure with 22(Invalid) if we monitors several event groups. sys_perf_event_open: pid 28960 cpu 40 group_fd 118202 flags 0x8 sys_perf_event_open: pid 28961 cpu 40 group_fd 118203 flags 0x8 WARNING: Ignored open failure for pid 28962 sys_perf_event_open: pid 28962 cpu 40 group_fd [118203] flags 0x8 sys_perf_event_open failed, error -22 That is because when we ignore a missing thread, we change the thread_idx without dealing with its fds, FD(evsel, cpu, thread). Then get_group_fd() may return a wrong group_fd for the next thread and sys_perf_event_open() return with 22. sys_perf_event_open(){ ... if (group_fd != -1) perf_fget_light()//to get corresponding group_leader by group_fd ... if (group_leader) if (group_leader->ctx->task != ctx->task)//should on the same task goto err_context ... } This patch also fixes this bug by introducing perf_evsel__remove_fd() and update_fds to allow removing fds for the missing thread. Changes since v1: - Change group_fd__remove() into a more genetic way without changing code logic - Remove redundant condition Changes since v2: - Use a proper function name and add some comment. - Multiline comment style fixes. Committer testing: Before this patch the recently added 'perf stat --per-thread' for system wide counting would race while enumerating all threads using /proc: [root@jouet ~]# perf stat --per-thread failed to parse CPUs map: No such file or directory Usage: perf stat [<options>] [<command>] -C, --cpu <cpu> list of cpus to monitor in system-wide -a, --all-cpus system-wide collection from all CPUs [root@jouet ~]# perf stat --per-thread failed to parse CPUs map: No such file or directory Usage: perf stat [<options>] [<command>] -C, --cpu <cpu> list of cpus to monitor in system-wide -a, --all-cpus system-wide collection from all CPUs [root@jouet ~]# When, say, the kernel was being built, so lots of shortlived threads, after this patch this doesn't happen. Signed-off-by: Mengting Zhang <zhangmengting@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Cheng Jian <cj.chengjian@huawei.com> Cc: Li Bin <huawei.libin@huawei.com> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1513148513-6974-1-git-send-email-zhangmengting@huawei.com [ Remove one use 'evlist' alias variable ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-12-13 07:01:53 +00:00
int nr_cpus, int cpu,
struct thread_map *threads,
int thread, int err)
{
perf evsel: Enable ignore_missing_thread for pid option While monitoring a multithread process with pid option, perf sometimes may return sys_perf_event_open failure with 3(No such process) if any of the process's threads die before we open the event. However, we want perf continue monitoring the remaining threads and do not exit with error. Here, the patch enables perf_evsel::ignore_missing_thread for -p option to ignore complete failure if any of threads die before we open the event. But it may still return sys_perf_event_open failure with 22(Invalid) if we monitors several event groups. sys_perf_event_open: pid 28960 cpu 40 group_fd 118202 flags 0x8 sys_perf_event_open: pid 28961 cpu 40 group_fd 118203 flags 0x8 WARNING: Ignored open failure for pid 28962 sys_perf_event_open: pid 28962 cpu 40 group_fd [118203] flags 0x8 sys_perf_event_open failed, error -22 That is because when we ignore a missing thread, we change the thread_idx without dealing with its fds, FD(evsel, cpu, thread). Then get_group_fd() may return a wrong group_fd for the next thread and sys_perf_event_open() return with 22. sys_perf_event_open(){ ... if (group_fd != -1) perf_fget_light()//to get corresponding group_leader by group_fd ... if (group_leader) if (group_leader->ctx->task != ctx->task)//should on the same task goto err_context ... } This patch also fixes this bug by introducing perf_evsel__remove_fd() and update_fds to allow removing fds for the missing thread. Changes since v1: - Change group_fd__remove() into a more genetic way without changing code logic - Remove redundant condition Changes since v2: - Use a proper function name and add some comment. - Multiline comment style fixes. Committer testing: Before this patch the recently added 'perf stat --per-thread' for system wide counting would race while enumerating all threads using /proc: [root@jouet ~]# perf stat --per-thread failed to parse CPUs map: No such file or directory Usage: perf stat [<options>] [<command>] -C, --cpu <cpu> list of cpus to monitor in system-wide -a, --all-cpus system-wide collection from all CPUs [root@jouet ~]# perf stat --per-thread failed to parse CPUs map: No such file or directory Usage: perf stat [<options>] [<command>] -C, --cpu <cpu> list of cpus to monitor in system-wide -a, --all-cpus system-wide collection from all CPUs [root@jouet ~]# When, say, the kernel was being built, so lots of shortlived threads, after this patch this doesn't happen. Signed-off-by: Mengting Zhang <zhangmengting@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Cheng Jian <cj.chengjian@huawei.com> Cc: Li Bin <huawei.libin@huawei.com> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1513148513-6974-1-git-send-email-zhangmengting@huawei.com [ Remove one use 'evlist' alias variable ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-12-13 07:01:53 +00:00
pid_t ignore_pid = thread_map__pid(threads, thread);
if (!evsel->ignore_missing_thread)
return false;
/* The system wide setup does not work with threads. */
if (evsel->system_wide)
return false;
/* The -ESRCH is perf event syscall errno for pid's not found. */
if (err != -ESRCH)
return false;
/* If there's only one thread, let it fail. */
if (threads->nr == 1)
return false;
perf evsel: Enable ignore_missing_thread for pid option While monitoring a multithread process with pid option, perf sometimes may return sys_perf_event_open failure with 3(No such process) if any of the process's threads die before we open the event. However, we want perf continue monitoring the remaining threads and do not exit with error. Here, the patch enables perf_evsel::ignore_missing_thread for -p option to ignore complete failure if any of threads die before we open the event. But it may still return sys_perf_event_open failure with 22(Invalid) if we monitors several event groups. sys_perf_event_open: pid 28960 cpu 40 group_fd 118202 flags 0x8 sys_perf_event_open: pid 28961 cpu 40 group_fd 118203 flags 0x8 WARNING: Ignored open failure for pid 28962 sys_perf_event_open: pid 28962 cpu 40 group_fd [118203] flags 0x8 sys_perf_event_open failed, error -22 That is because when we ignore a missing thread, we change the thread_idx without dealing with its fds, FD(evsel, cpu, thread). Then get_group_fd() may return a wrong group_fd for the next thread and sys_perf_event_open() return with 22. sys_perf_event_open(){ ... if (group_fd != -1) perf_fget_light()//to get corresponding group_leader by group_fd ... if (group_leader) if (group_leader->ctx->task != ctx->task)//should on the same task goto err_context ... } This patch also fixes this bug by introducing perf_evsel__remove_fd() and update_fds to allow removing fds for the missing thread. Changes since v1: - Change group_fd__remove() into a more genetic way without changing code logic - Remove redundant condition Changes since v2: - Use a proper function name and add some comment. - Multiline comment style fixes. Committer testing: Before this patch the recently added 'perf stat --per-thread' for system wide counting would race while enumerating all threads using /proc: [root@jouet ~]# perf stat --per-thread failed to parse CPUs map: No such file or directory Usage: perf stat [<options>] [<command>] -C, --cpu <cpu> list of cpus to monitor in system-wide -a, --all-cpus system-wide collection from all CPUs [root@jouet ~]# perf stat --per-thread failed to parse CPUs map: No such file or directory Usage: perf stat [<options>] [<command>] -C, --cpu <cpu> list of cpus to monitor in system-wide -a, --all-cpus system-wide collection from all CPUs [root@jouet ~]# When, say, the kernel was being built, so lots of shortlived threads, after this patch this doesn't happen. Signed-off-by: Mengting Zhang <zhangmengting@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Cheng Jian <cj.chengjian@huawei.com> Cc: Li Bin <huawei.libin@huawei.com> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1513148513-6974-1-git-send-email-zhangmengting@huawei.com [ Remove one use 'evlist' alias variable ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-12-13 07:01:53 +00:00
/*
* We should remove fd for missing_thread first
* because thread_map__remove() will decrease threads->nr.
*/
if (update_fds(evsel, nr_cpus, cpu, threads->nr, thread))
return false;
if (thread_map__remove(threads, thread))
return false;
pr_warning("WARNING: Ignored open failure for pid %d\n",
perf evsel: Enable ignore_missing_thread for pid option While monitoring a multithread process with pid option, perf sometimes may return sys_perf_event_open failure with 3(No such process) if any of the process's threads die before we open the event. However, we want perf continue monitoring the remaining threads and do not exit with error. Here, the patch enables perf_evsel::ignore_missing_thread for -p option to ignore complete failure if any of threads die before we open the event. But it may still return sys_perf_event_open failure with 22(Invalid) if we monitors several event groups. sys_perf_event_open: pid 28960 cpu 40 group_fd 118202 flags 0x8 sys_perf_event_open: pid 28961 cpu 40 group_fd 118203 flags 0x8 WARNING: Ignored open failure for pid 28962 sys_perf_event_open: pid 28962 cpu 40 group_fd [118203] flags 0x8 sys_perf_event_open failed, error -22 That is because when we ignore a missing thread, we change the thread_idx without dealing with its fds, FD(evsel, cpu, thread). Then get_group_fd() may return a wrong group_fd for the next thread and sys_perf_event_open() return with 22. sys_perf_event_open(){ ... if (group_fd != -1) perf_fget_light()//to get corresponding group_leader by group_fd ... if (group_leader) if (group_leader->ctx->task != ctx->task)//should on the same task goto err_context ... } This patch also fixes this bug by introducing perf_evsel__remove_fd() and update_fds to allow removing fds for the missing thread. Changes since v1: - Change group_fd__remove() into a more genetic way without changing code logic - Remove redundant condition Changes since v2: - Use a proper function name and add some comment. - Multiline comment style fixes. Committer testing: Before this patch the recently added 'perf stat --per-thread' for system wide counting would race while enumerating all threads using /proc: [root@jouet ~]# perf stat --per-thread failed to parse CPUs map: No such file or directory Usage: perf stat [<options>] [<command>] -C, --cpu <cpu> list of cpus to monitor in system-wide -a, --all-cpus system-wide collection from all CPUs [root@jouet ~]# perf stat --per-thread failed to parse CPUs map: No such file or directory Usage: perf stat [<options>] [<command>] -C, --cpu <cpu> list of cpus to monitor in system-wide -a, --all-cpus system-wide collection from all CPUs [root@jouet ~]# When, say, the kernel was being built, so lots of shortlived threads, after this patch this doesn't happen. Signed-off-by: Mengting Zhang <zhangmengting@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Cheng Jian <cj.chengjian@huawei.com> Cc: Li Bin <huawei.libin@huawei.com> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1513148513-6974-1-git-send-email-zhangmengting@huawei.com [ Remove one use 'evlist' alias variable ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-12-13 07:01:53 +00:00
ignore_pid);
return true;
}
perf evsel: Fix max perf_event_attr.precise_ip detection After a discussion with Andi, move the perf_event_attr.precise_ip detection for maximum precise config (via :P modifier or for default cycles event) to perf_evsel__open(). The current detection in perf_event_attr__set_max_precise_ip() is tricky, because precise_ip config is specific for given event and it currently checks only hw cycles. We now check for valid precise_ip value right after failing sys_perf_event_open() for specific event, before any of the perf_event_attr fallback code gets executed. This way we get the proper config in perf_event_attr together with allowed precise_ip settings. We can see that code activity with -vv, like: $ perf record -vv ls ... ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 ... precise_ip 3 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 ------------------------------------------------------------ sys_perf_event_open: pid 9926 cpu 0 group_fd -1 flags 0x8 sys_perf_event_open failed, error -95 decreasing precise_ip by one (2) ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 ... precise_ip 2 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 ------------------------------------------------------------ sys_perf_event_open: pid 9926 cpu 0 group_fd -1 flags 0x8 = 4 ... Suggested-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/n/tip-dkvxxbeg7lu74155d4jhlmc9@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-14 14:00:10 +00:00
static void display_attr(struct perf_event_attr *attr)
{
if (verbose >= 2) {
fprintf(stderr, "%.60s\n", graph_dotted_line);
fprintf(stderr, "perf_event_attr:\n");
perf_event_attr__fprintf(stderr, attr, __open_attr__fprintf, NULL);
fprintf(stderr, "%.60s\n", graph_dotted_line);
}
}
static int perf_event_open(struct perf_evsel *evsel,
pid_t pid, int cpu, int group_fd,
unsigned long flags)
{
int precise_ip = evsel->attr.precise_ip;
int fd;
while (1) {
pr_debug2("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx",
pid, cpu, group_fd, flags);
fd = sys_perf_event_open(&evsel->attr, pid, cpu, group_fd, flags);
if (fd >= 0)
break;
/* Do not try less precise if not requested. */
if (!evsel->precise_max)
perf evsel: Fix max perf_event_attr.precise_ip detection After a discussion with Andi, move the perf_event_attr.precise_ip detection for maximum precise config (via :P modifier or for default cycles event) to perf_evsel__open(). The current detection in perf_event_attr__set_max_precise_ip() is tricky, because precise_ip config is specific for given event and it currently checks only hw cycles. We now check for valid precise_ip value right after failing sys_perf_event_open() for specific event, before any of the perf_event_attr fallback code gets executed. This way we get the proper config in perf_event_attr together with allowed precise_ip settings. We can see that code activity with -vv, like: $ perf record -vv ls ... ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 ... precise_ip 3 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 ------------------------------------------------------------ sys_perf_event_open: pid 9926 cpu 0 group_fd -1 flags 0x8 sys_perf_event_open failed, error -95 decreasing precise_ip by one (2) ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 ... precise_ip 2 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 ------------------------------------------------------------ sys_perf_event_open: pid 9926 cpu 0 group_fd -1 flags 0x8 = 4 ... Suggested-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/n/tip-dkvxxbeg7lu74155d4jhlmc9@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-14 14:00:10 +00:00
break;
/*
* We tried all the precise_ip values, and it's
* still failing, so leave it to standard fallback.
*/
if (!evsel->attr.precise_ip) {
evsel->attr.precise_ip = precise_ip;
break;
}
pr_debug2("\nsys_perf_event_open failed, error %d\n", -ENOTSUP);
evsel->attr.precise_ip--;
pr_debug2("decreasing precise_ip by one (%d)\n", evsel->attr.precise_ip);
display_attr(&evsel->attr);
}
return fd;
}
int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
struct thread_map *threads)
{
int cpu, thread, nthreads;
unsigned long flags = PERF_FLAG_FD_CLOEXEC;
int pid = -1, err;
enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE;
if (perf_missing_features.write_backward && evsel->attr.write_backward)
return -EINVAL;
if (cpus == NULL) {
static struct cpu_map *empty_cpu_map;
if (empty_cpu_map == NULL) {
empty_cpu_map = cpu_map__dummy_new();
if (empty_cpu_map == NULL)
return -ENOMEM;
}
cpus = empty_cpu_map;
}
if (threads == NULL) {
static struct thread_map *empty_thread_map;
if (empty_thread_map == NULL) {
empty_thread_map = thread_map__new_by_tid(-1);
if (empty_thread_map == NULL)
return -ENOMEM;
}
threads = empty_thread_map;
}
if (evsel->system_wide)
nthreads = 1;
else
nthreads = threads->nr;
if (evsel->fd == NULL &&
perf_evsel__alloc_fd(evsel, cpus->nr, nthreads) < 0)
return -ENOMEM;
if (evsel->cgrp) {
flags |= PERF_FLAG_PID_CGROUP;
pid = evsel->cgrp->fd;
}
fallback_missing_features:
if (perf_missing_features.clockid_wrong)
evsel->attr.clockid = CLOCK_MONOTONIC; /* should always work */
if (perf_missing_features.clockid) {
evsel->attr.use_clockid = 0;
evsel->attr.clockid = 0;
}
if (perf_missing_features.cloexec)
flags &= ~(unsigned long)PERF_FLAG_FD_CLOEXEC;
if (perf_missing_features.mmap2)
evsel->attr.mmap2 = 0;
if (perf_missing_features.exclude_guest)
evsel->attr.exclude_guest = evsel->attr.exclude_host = 0;
if (perf_missing_features.lbr_flags)
evsel->attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS |
PERF_SAMPLE_BRANCH_NO_CYCLES);
if (perf_missing_features.group_read && evsel->attr.inherit)
evsel->attr.read_format &= ~(PERF_FORMAT_GROUP|PERF_FORMAT_ID);
if (perf_missing_features.ksymbol)
evsel->attr.ksymbol = 0;
perf tools: Handle PERF_RECORD_BPF_EVENT This patch adds basic handling of PERF_RECORD_BPF_EVENT. Tracking of PERF_RECORD_BPF_EVENT is OFF by default. Option --bpf-event is added to turn it on. Committer notes: Add dummy machine__process_bpf_event() variant that returns zero for systems without HAVE_LIBBPF_SUPPORT, such as Alpine Linux, unbreaking the build in such systems. Remove the needless include <machine.h> from bpf->event.h, provide just forward declarations for the structs and unions in the parameters, to reduce compilation time and needless rebuilds when machine.h gets changed. Committer testing: When running with: # perf record --bpf-event On an older kernel where PERF_RECORD_BPF_EVENT and PERF_RECORD_KSYMBOL is not present, we fallback to removing those two bits from perf_event_attr, making the tool to continue to work on older kernels: perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD read_format ID disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 precise_ip 3 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 bpf_event 1 ------------------------------------------------------------ sys_perf_event_open: pid 5779 cpu 0 group_fd -1 flags 0x8 sys_perf_event_open failed, error -22 switching off bpf_event ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD read_format ID disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 precise_ip 3 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 ------------------------------------------------------------ sys_perf_event_open: pid 5779 cpu 0 group_fd -1 flags 0x8 sys_perf_event_open failed, error -22 switching off ksymbol ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD read_format ID disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 precise_ip 3 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ------------------------------------------------------------ And then proceeds to work without those two features. As passing --bpf-event is an explicit action performed by the user, perhaps we should emit a warning telling that the kernel has no such feature, but this can be done on top of this patch. Now with a kernel that supports these events, start the 'record --bpf-event -a' and then run 'perf trace sleep 10000' that will use the BPF augmented_raw_syscalls.o prebuilt (for another kernel version even) and thus should generate PERF_RECORD_BPF_EVENT events: [root@quaco ~]# perf record -e dummy -a --bpf-event ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.713 MB perf.data ] [root@quaco ~]# bpftool prog 13: cgroup_skb tag 7be49e3934a125ba gpl loaded_at 2019-01-19T09:09:43-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 13,14 14: cgroup_skb tag 2a142ef67aaad174 gpl loaded_at 2019-01-19T09:09:43-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 13,14 15: cgroup_skb tag 7be49e3934a125ba gpl loaded_at 2019-01-19T09:09:43-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 15,16 16: cgroup_skb tag 2a142ef67aaad174 gpl loaded_at 2019-01-19T09:09:43-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 15,16 17: cgroup_skb tag 7be49e3934a125ba gpl loaded_at 2019-01-19T09:09:44-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 17,18 18: cgroup_skb tag 2a142ef67aaad174 gpl loaded_at 2019-01-19T09:09:44-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 17,18 21: cgroup_skb tag 7be49e3934a125ba gpl loaded_at 2019-01-19T09:09:45-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 21,22 22: cgroup_skb tag 2a142ef67aaad174 gpl loaded_at 2019-01-19T09:09:45-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 21,22 31: tracepoint name sys_enter tag 12504ba9402f952f gpl loaded_at 2019-01-19T09:19:56-0300 uid 0 xlated 512B jited 374B memlock 4096B map_ids 30,29,28 32: tracepoint name sys_exit tag c1bd85c092d6e4aa gpl loaded_at 2019-01-19T09:19:56-0300 uid 0 xlated 256B jited 191B memlock 4096B map_ids 30,29 # perf report -D | grep PERF_RECORD_BPF_EVENT | nl 1 0 55834574849 0x4fc8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 13 2 0 60129542145 0x5118 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 14 3 0 64424509441 0x5268 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 15 4 0 68719476737 0x53b8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 16 5 0 73014444033 0x5508 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 17 6 0 77309411329 0x5658 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 18 7 0 90194313217 0x57a8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 21 8 0 94489280513 0x58f8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 22 9 7 620922484360 0xb6390 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 29 10 7 620922486018 0xb6410 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 2, flags 0, id 29 11 7 620922579199 0xb6490 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 30 12 7 620922580240 0xb6510 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 2, flags 0, id 30 13 7 620922765207 0xb6598 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 31 14 7 620922874543 0xb6620 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 32 # There, the 31 and 32 tracepoint BPF programs put in place by 'perf trace'. Signed-off-by: Song Liu <songliubraving@fb.com> Reviewed-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: kernel-team@fb.com Cc: netdev@vger.kernel.org Link: http://lkml.kernel.org/r/20190117161521.1341602-7-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-01-17 16:15:18 +00:00
if (perf_missing_features.bpf_event)
evsel->attr.bpf_event = 0;
retry_sample_id:
if (perf_missing_features.sample_id_all)
evsel->attr.sample_id_all = 0;
perf evsel: Fix max perf_event_attr.precise_ip detection After a discussion with Andi, move the perf_event_attr.precise_ip detection for maximum precise config (via :P modifier or for default cycles event) to perf_evsel__open(). The current detection in perf_event_attr__set_max_precise_ip() is tricky, because precise_ip config is specific for given event and it currently checks only hw cycles. We now check for valid precise_ip value right after failing sys_perf_event_open() for specific event, before any of the perf_event_attr fallback code gets executed. This way we get the proper config in perf_event_attr together with allowed precise_ip settings. We can see that code activity with -vv, like: $ perf record -vv ls ... ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 ... precise_ip 3 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 ------------------------------------------------------------ sys_perf_event_open: pid 9926 cpu 0 group_fd -1 flags 0x8 sys_perf_event_open failed, error -95 decreasing precise_ip by one (2) ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 ... precise_ip 2 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 ------------------------------------------------------------ sys_perf_event_open: pid 9926 cpu 0 group_fd -1 flags 0x8 = 4 ... Suggested-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/n/tip-dkvxxbeg7lu74155d4jhlmc9@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-14 14:00:10 +00:00
display_attr(&evsel->attr);
for (cpu = 0; cpu < cpus->nr; cpu++) {
for (thread = 0; thread < nthreads; thread++) {
int fd, group_fd;
if (!evsel->cgrp && !evsel->system_wide)
pid = thread_map__pid(threads, thread);
perf tools: Enable grouping logic for parsed events This patch adds a functionality that allows to create event groups based on the way they are specified on the command line. Adding functionality to the '{}' group syntax introduced in earlier patch. The current '--group/-g' option behaviour remains intact. If you specify it for record/stat/top command, all the specified events become members of a single group with the first event as a group leader. With the new '{}' group syntax you can create group like: # perf record -e '{cycles,faults}' ls resulting in single event group containing 'cycles' and 'faults' events, with cycles event as group leader. All groups are created with regards to threads and cpus. Thus recording an event group within a 2 threads on server with 4 CPUs will create 8 separate groups. Examples (first event in brackets is group leader): # 1 group (cpu-clock,task-clock) perf record --group -e cpu-clock,task-clock ls perf record -e '{cpu-clock,task-clock}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock},{minor-faults,major-faults}' ls # 1 group (cpu-clock,task-clock,minor-faults,major-faults) perf record --group -e cpu-clock,task-clock -e minor-faults,major-faults ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock} -e '{minor-faults,major-faults}' \ -e instructions ls # 1 group # (cpu-clock,task-clock,minor-faults,major-faults,instructions) perf record --group -e cpu-clock,task-clock \ -e minor-faults,major-faults -e instructions ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults,instructions}' ls It's possible to use standard event modifier for a group, which spans over all events in the group and updates each event modifier settings, for example: # perf record -r '{faults:k,cache-references}:p' resulting in ':kp' modifier being used for 'faults' and ':p' modifier being used for 'cache-references' event. Reviewed-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Drepper <drepper@gmail.com> Link: http://lkml.kernel.org/n/tip-ho42u0wcr8mn1otkalqi13qp@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-08-08 10:22:36 +00:00
group_fd = get_group_fd(evsel, cpu, thread);
retry_open:
test_attr__ready();
perf evsel: Fix max perf_event_attr.precise_ip detection After a discussion with Andi, move the perf_event_attr.precise_ip detection for maximum precise config (via :P modifier or for default cycles event) to perf_evsel__open(). The current detection in perf_event_attr__set_max_precise_ip() is tricky, because precise_ip config is specific for given event and it currently checks only hw cycles. We now check for valid precise_ip value right after failing sys_perf_event_open() for specific event, before any of the perf_event_attr fallback code gets executed. This way we get the proper config in perf_event_attr together with allowed precise_ip settings. We can see that code activity with -vv, like: $ perf record -vv ls ... ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 ... precise_ip 3 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 ------------------------------------------------------------ sys_perf_event_open: pid 9926 cpu 0 group_fd -1 flags 0x8 sys_perf_event_open failed, error -95 decreasing precise_ip by one (2) ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 ... precise_ip 2 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 ------------------------------------------------------------ sys_perf_event_open: pid 9926 cpu 0 group_fd -1 flags 0x8 = 4 ... Suggested-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/n/tip-dkvxxbeg7lu74155d4jhlmc9@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-14 14:00:10 +00:00
fd = perf_event_open(evsel, pid, cpus->map[cpu],
group_fd, flags);
FD(evsel, cpu, thread) = fd;
if (fd < 0) {
err = -errno;
perf evsel: Enable ignore_missing_thread for pid option While monitoring a multithread process with pid option, perf sometimes may return sys_perf_event_open failure with 3(No such process) if any of the process's threads die before we open the event. However, we want perf continue monitoring the remaining threads and do not exit with error. Here, the patch enables perf_evsel::ignore_missing_thread for -p option to ignore complete failure if any of threads die before we open the event. But it may still return sys_perf_event_open failure with 22(Invalid) if we monitors several event groups. sys_perf_event_open: pid 28960 cpu 40 group_fd 118202 flags 0x8 sys_perf_event_open: pid 28961 cpu 40 group_fd 118203 flags 0x8 WARNING: Ignored open failure for pid 28962 sys_perf_event_open: pid 28962 cpu 40 group_fd [118203] flags 0x8 sys_perf_event_open failed, error -22 That is because when we ignore a missing thread, we change the thread_idx without dealing with its fds, FD(evsel, cpu, thread). Then get_group_fd() may return a wrong group_fd for the next thread and sys_perf_event_open() return with 22. sys_perf_event_open(){ ... if (group_fd != -1) perf_fget_light()//to get corresponding group_leader by group_fd ... if (group_leader) if (group_leader->ctx->task != ctx->task)//should on the same task goto err_context ... } This patch also fixes this bug by introducing perf_evsel__remove_fd() and update_fds to allow removing fds for the missing thread. Changes since v1: - Change group_fd__remove() into a more genetic way without changing code logic - Remove redundant condition Changes since v2: - Use a proper function name and add some comment. - Multiline comment style fixes. Committer testing: Before this patch the recently added 'perf stat --per-thread' for system wide counting would race while enumerating all threads using /proc: [root@jouet ~]# perf stat --per-thread failed to parse CPUs map: No such file or directory Usage: perf stat [<options>] [<command>] -C, --cpu <cpu> list of cpus to monitor in system-wide -a, --all-cpus system-wide collection from all CPUs [root@jouet ~]# perf stat --per-thread failed to parse CPUs map: No such file or directory Usage: perf stat [<options>] [<command>] -C, --cpu <cpu> list of cpus to monitor in system-wide -a, --all-cpus system-wide collection from all CPUs [root@jouet ~]# When, say, the kernel was being built, so lots of shortlived threads, after this patch this doesn't happen. Signed-off-by: Mengting Zhang <zhangmengting@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Cheng Jian <cj.chengjian@huawei.com> Cc: Li Bin <huawei.libin@huawei.com> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1513148513-6974-1-git-send-email-zhangmengting@huawei.com [ Remove one use 'evlist' alias variable ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-12-13 07:01:53 +00:00
if (ignore_missing_thread(evsel, cpus->nr, cpu, threads, thread, err)) {
/*
* We just removed 1 thread, so take a step
* back on thread index and lower the upper
* nthreads limit.
*/
nthreads--;
thread--;
/* ... and pretend like nothing have happened. */
err = 0;
continue;
}
pr_debug2("\nsys_perf_event_open failed, error %d\n",
err);
goto try_fallback;
}
perf bpf: Attach eBPF filter to perf event This is the final patch which makes basic BPF filter work. After applying this patch, users are allowed to use BPF filter like: # perf record --event ./hello_world.o ls A bpf_fd field is appended to 'struct evsel', and setup during the callback function add_bpf_event() for each 'probe_trace_event'. PERF_EVENT_IOC_SET_BPF ioctl is used to attach eBPF program to a newly created perf event. The file descriptor of the eBPF program is passed to perf record using previous patches, and stored into evsel->bpf_fd. It is possible that different perf event are created for one kprobe events for different CPUs. In this case, when trying to call the ioctl, EEXIST will be return. This patch doesn't treat it as an error. Committer note: The bpf proggie used so far: __attribute__((section("fork=_do_fork"), used)) int fork(void *ctx) { return 0; } char _license[] __attribute__((section("license"), used)) = "GPL"; int _version __attribute__((section("version"), used)) = 0x40300; failed to produce any samples, even with forks happening and it being running in system wide mode. That is because now the filter is being associated, and the code above always returns zero, meaning that all forks will be probed but filtered away ;-/ Change it to 'return 1;' instead and after that: # trace --no-syscalls --event /tmp/foo.o 0.000 perf_bpf_probe:fork:(ffffffff8109be30)) 2.333 perf_bpf_probe:fork:(ffffffff8109be30)) 3.725 perf_bpf_probe:fork:(ffffffff8109be30)) 4.550 perf_bpf_probe:fork:(ffffffff8109be30)) ^C# And it works with all tools, including 'perf trace'. Signed-off-by: Wang Nan <wangnan0@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexei Starovoitov <ast@plumgrid.com> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: David Ahern <dsahern@gmail.com> Cc: He Kuang <hekuang@huawei.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kaixu Xia <xiakaixu@huawei.com> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1444826502-49291-8-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-10-14 12:41:18 +00:00
pr_debug2(" = %d\n", fd);
perf bpf: Attach eBPF filter to perf event This is the final patch which makes basic BPF filter work. After applying this patch, users are allowed to use BPF filter like: # perf record --event ./hello_world.o ls A bpf_fd field is appended to 'struct evsel', and setup during the callback function add_bpf_event() for each 'probe_trace_event'. PERF_EVENT_IOC_SET_BPF ioctl is used to attach eBPF program to a newly created perf event. The file descriptor of the eBPF program is passed to perf record using previous patches, and stored into evsel->bpf_fd. It is possible that different perf event are created for one kprobe events for different CPUs. In this case, when trying to call the ioctl, EEXIST will be return. This patch doesn't treat it as an error. Committer note: The bpf proggie used so far: __attribute__((section("fork=_do_fork"), used)) int fork(void *ctx) { return 0; } char _license[] __attribute__((section("license"), used)) = "GPL"; int _version __attribute__((section("version"), used)) = 0x40300; failed to produce any samples, even with forks happening and it being running in system wide mode. That is because now the filter is being associated, and the code above always returns zero, meaning that all forks will be probed but filtered away ;-/ Change it to 'return 1;' instead and after that: # trace --no-syscalls --event /tmp/foo.o 0.000 perf_bpf_probe:fork:(ffffffff8109be30)) 2.333 perf_bpf_probe:fork:(ffffffff8109be30)) 3.725 perf_bpf_probe:fork:(ffffffff8109be30)) 4.550 perf_bpf_probe:fork:(ffffffff8109be30)) ^C# And it works with all tools, including 'perf trace'. Signed-off-by: Wang Nan <wangnan0@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexei Starovoitov <ast@plumgrid.com> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: David Ahern <dsahern@gmail.com> Cc: He Kuang <hekuang@huawei.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kaixu Xia <xiakaixu@huawei.com> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1444826502-49291-8-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-10-14 12:41:18 +00:00
if (evsel->bpf_fd >= 0) {
int evt_fd = fd;
perf bpf: Attach eBPF filter to perf event This is the final patch which makes basic BPF filter work. After applying this patch, users are allowed to use BPF filter like: # perf record --event ./hello_world.o ls A bpf_fd field is appended to 'struct evsel', and setup during the callback function add_bpf_event() for each 'probe_trace_event'. PERF_EVENT_IOC_SET_BPF ioctl is used to attach eBPF program to a newly created perf event. The file descriptor of the eBPF program is passed to perf record using previous patches, and stored into evsel->bpf_fd. It is possible that different perf event are created for one kprobe events for different CPUs. In this case, when trying to call the ioctl, EEXIST will be return. This patch doesn't treat it as an error. Committer note: The bpf proggie used so far: __attribute__((section("fork=_do_fork"), used)) int fork(void *ctx) { return 0; } char _license[] __attribute__((section("license"), used)) = "GPL"; int _version __attribute__((section("version"), used)) = 0x40300; failed to produce any samples, even with forks happening and it being running in system wide mode. That is because now the filter is being associated, and the code above always returns zero, meaning that all forks will be probed but filtered away ;-/ Change it to 'return 1;' instead and after that: # trace --no-syscalls --event /tmp/foo.o 0.000 perf_bpf_probe:fork:(ffffffff8109be30)) 2.333 perf_bpf_probe:fork:(ffffffff8109be30)) 3.725 perf_bpf_probe:fork:(ffffffff8109be30)) 4.550 perf_bpf_probe:fork:(ffffffff8109be30)) ^C# And it works with all tools, including 'perf trace'. Signed-off-by: Wang Nan <wangnan0@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexei Starovoitov <ast@plumgrid.com> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: David Ahern <dsahern@gmail.com> Cc: He Kuang <hekuang@huawei.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kaixu Xia <xiakaixu@huawei.com> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1444826502-49291-8-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-10-14 12:41:18 +00:00
int bpf_fd = evsel->bpf_fd;
err = ioctl(evt_fd,
PERF_EVENT_IOC_SET_BPF,
bpf_fd);
if (err && errno != EEXIST) {
pr_err("failed to attach bpf fd %d: %s\n",
bpf_fd, strerror(errno));
err = -EINVAL;
goto out_close;
}
}
set_rlimit = NO_CHANGE;
/*
* If we succeeded but had to kill clockid, fail and
* have perf_evsel__open_strerror() print us a nice
* error.
*/
if (perf_missing_features.clockid ||
perf_missing_features.clockid_wrong) {
err = -EINVAL;
goto out_close;
}
}
}
return 0;
try_fallback:
/*
* perf stat needs between 5 and 22 fds per CPU. When we run out
* of them try to increase the limits.
*/
if (err == -EMFILE && set_rlimit < INCREASED_MAX) {
struct rlimit l;
int old_errno = errno;
if (getrlimit(RLIMIT_NOFILE, &l) == 0) {
if (set_rlimit == NO_CHANGE)
l.rlim_cur = l.rlim_max;
else {
l.rlim_cur = l.rlim_max + 1000;
l.rlim_max = l.rlim_cur;
}
if (setrlimit(RLIMIT_NOFILE, &l) == 0) {
set_rlimit++;
errno = old_errno;
goto retry_open;
}
}
errno = old_errno;
}
if (err != -EINVAL || cpu > 0 || thread > 0)
goto out_close;
/*
* Must probe features in the order they were added to the
* perf_event_attr interface.
*/
perf tools: Handle PERF_RECORD_BPF_EVENT This patch adds basic handling of PERF_RECORD_BPF_EVENT. Tracking of PERF_RECORD_BPF_EVENT is OFF by default. Option --bpf-event is added to turn it on. Committer notes: Add dummy machine__process_bpf_event() variant that returns zero for systems without HAVE_LIBBPF_SUPPORT, such as Alpine Linux, unbreaking the build in such systems. Remove the needless include <machine.h> from bpf->event.h, provide just forward declarations for the structs and unions in the parameters, to reduce compilation time and needless rebuilds when machine.h gets changed. Committer testing: When running with: # perf record --bpf-event On an older kernel where PERF_RECORD_BPF_EVENT and PERF_RECORD_KSYMBOL is not present, we fallback to removing those two bits from perf_event_attr, making the tool to continue to work on older kernels: perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD read_format ID disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 precise_ip 3 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 bpf_event 1 ------------------------------------------------------------ sys_perf_event_open: pid 5779 cpu 0 group_fd -1 flags 0x8 sys_perf_event_open failed, error -22 switching off bpf_event ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD read_format ID disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 precise_ip 3 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ksymbol 1 ------------------------------------------------------------ sys_perf_event_open: pid 5779 cpu 0 group_fd -1 flags 0x8 sys_perf_event_open failed, error -22 switching off ksymbol ------------------------------------------------------------ perf_event_attr: size 112 { sample_period, sample_freq } 4000 sample_type IP|TID|TIME|PERIOD read_format ID disabled 1 inherit 1 mmap 1 comm 1 freq 1 enable_on_exec 1 task 1 precise_ip 3 sample_id_all 1 exclude_guest 1 mmap2 1 comm_exec 1 ------------------------------------------------------------ And then proceeds to work without those two features. As passing --bpf-event is an explicit action performed by the user, perhaps we should emit a warning telling that the kernel has no such feature, but this can be done on top of this patch. Now with a kernel that supports these events, start the 'record --bpf-event -a' and then run 'perf trace sleep 10000' that will use the BPF augmented_raw_syscalls.o prebuilt (for another kernel version even) and thus should generate PERF_RECORD_BPF_EVENT events: [root@quaco ~]# perf record -e dummy -a --bpf-event ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.713 MB perf.data ] [root@quaco ~]# bpftool prog 13: cgroup_skb tag 7be49e3934a125ba gpl loaded_at 2019-01-19T09:09:43-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 13,14 14: cgroup_skb tag 2a142ef67aaad174 gpl loaded_at 2019-01-19T09:09:43-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 13,14 15: cgroup_skb tag 7be49e3934a125ba gpl loaded_at 2019-01-19T09:09:43-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 15,16 16: cgroup_skb tag 2a142ef67aaad174 gpl loaded_at 2019-01-19T09:09:43-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 15,16 17: cgroup_skb tag 7be49e3934a125ba gpl loaded_at 2019-01-19T09:09:44-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 17,18 18: cgroup_skb tag 2a142ef67aaad174 gpl loaded_at 2019-01-19T09:09:44-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 17,18 21: cgroup_skb tag 7be49e3934a125ba gpl loaded_at 2019-01-19T09:09:45-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 21,22 22: cgroup_skb tag 2a142ef67aaad174 gpl loaded_at 2019-01-19T09:09:45-0300 uid 0 xlated 296B jited 229B memlock 4096B map_ids 21,22 31: tracepoint name sys_enter tag 12504ba9402f952f gpl loaded_at 2019-01-19T09:19:56-0300 uid 0 xlated 512B jited 374B memlock 4096B map_ids 30,29,28 32: tracepoint name sys_exit tag c1bd85c092d6e4aa gpl loaded_at 2019-01-19T09:19:56-0300 uid 0 xlated 256B jited 191B memlock 4096B map_ids 30,29 # perf report -D | grep PERF_RECORD_BPF_EVENT | nl 1 0 55834574849 0x4fc8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 13 2 0 60129542145 0x5118 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 14 3 0 64424509441 0x5268 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 15 4 0 68719476737 0x53b8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 16 5 0 73014444033 0x5508 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 17 6 0 77309411329 0x5658 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 18 7 0 90194313217 0x57a8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 21 8 0 94489280513 0x58f8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 22 9 7 620922484360 0xb6390 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 29 10 7 620922486018 0xb6410 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 2, flags 0, id 29 11 7 620922579199 0xb6490 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 30 12 7 620922580240 0xb6510 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 2, flags 0, id 30 13 7 620922765207 0xb6598 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 31 14 7 620922874543 0xb6620 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 32 # There, the 31 and 32 tracepoint BPF programs put in place by 'perf trace'. Signed-off-by: Song Liu <songliubraving@fb.com> Reviewed-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Peter Zijlstra <peterz@infradead.org> Cc: kernel-team@fb.com Cc: netdev@vger.kernel.org Link: http://lkml.kernel.org/r/20190117161521.1341602-7-songliubraving@fb.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-01-17 16:15:18 +00:00
if (!perf_missing_features.bpf_event && evsel->attr.bpf_event) {
perf_missing_features.bpf_event = true;
pr_debug2("switching off bpf_event\n");
goto fallback_missing_features;
} else if (!perf_missing_features.ksymbol && evsel->attr.ksymbol) {
perf_missing_features.ksymbol = true;
pr_debug2("switching off ksymbol\n");
goto fallback_missing_features;
} else if (!perf_missing_features.write_backward && evsel->attr.write_backward) {
perf_missing_features.write_backward = true;
perf evsel: Add verbose output for sys_perf_event_open fallback Adding info about what is being switched off in the sys_perf_event_open fallback. New output (notice the 'switching off' lines): $ perf stat -e '{cycles,instructions}' -vvv ls Using CPUID GenuineIntel-6-3D intel_pt default config: tsc ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 exclude_guest 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0x8 sys_perf_event_open failed, error -22 switching off cloexec flag ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 exclude_guest 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0 sys_perf_event_open failed, error -22 switching off exclude_guest, exclude_host ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0 sys_perf_event_open failed, error -22 switching off sample_id_all ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 ... Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20170721121212.21414-2-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-07-21 12:12:09 +00:00
pr_debug2("switching off write_backward\n");
goto out_close;
} else if (!perf_missing_features.clockid_wrong && evsel->attr.use_clockid) {
perf_missing_features.clockid_wrong = true;
perf evsel: Add verbose output for sys_perf_event_open fallback Adding info about what is being switched off in the sys_perf_event_open fallback. New output (notice the 'switching off' lines): $ perf stat -e '{cycles,instructions}' -vvv ls Using CPUID GenuineIntel-6-3D intel_pt default config: tsc ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 exclude_guest 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0x8 sys_perf_event_open failed, error -22 switching off cloexec flag ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 exclude_guest 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0 sys_perf_event_open failed, error -22 switching off exclude_guest, exclude_host ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0 sys_perf_event_open failed, error -22 switching off sample_id_all ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 ... Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20170721121212.21414-2-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-07-21 12:12:09 +00:00
pr_debug2("switching off clockid\n");
goto fallback_missing_features;
} else if (!perf_missing_features.clockid && evsel->attr.use_clockid) {
perf_missing_features.clockid = true;
perf evsel: Add verbose output for sys_perf_event_open fallback Adding info about what is being switched off in the sys_perf_event_open fallback. New output (notice the 'switching off' lines): $ perf stat -e '{cycles,instructions}' -vvv ls Using CPUID GenuineIntel-6-3D intel_pt default config: tsc ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 exclude_guest 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0x8 sys_perf_event_open failed, error -22 switching off cloexec flag ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 exclude_guest 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0 sys_perf_event_open failed, error -22 switching off exclude_guest, exclude_host ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0 sys_perf_event_open failed, error -22 switching off sample_id_all ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 ... Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20170721121212.21414-2-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-07-21 12:12:09 +00:00
pr_debug2("switching off use_clockid\n");
goto fallback_missing_features;
} else if (!perf_missing_features.cloexec && (flags & PERF_FLAG_FD_CLOEXEC)) {
perf_missing_features.cloexec = true;
perf evsel: Add verbose output for sys_perf_event_open fallback Adding info about what is being switched off in the sys_perf_event_open fallback. New output (notice the 'switching off' lines): $ perf stat -e '{cycles,instructions}' -vvv ls Using CPUID GenuineIntel-6-3D intel_pt default config: tsc ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 exclude_guest 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0x8 sys_perf_event_open failed, error -22 switching off cloexec flag ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 exclude_guest 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0 sys_perf_event_open failed, error -22 switching off exclude_guest, exclude_host ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0 sys_perf_event_open failed, error -22 switching off sample_id_all ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 ... Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20170721121212.21414-2-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-07-21 12:12:09 +00:00
pr_debug2("switching off cloexec flag\n");
goto fallback_missing_features;
} else if (!perf_missing_features.mmap2 && evsel->attr.mmap2) {
perf_missing_features.mmap2 = true;
perf evsel: Add verbose output for sys_perf_event_open fallback Adding info about what is being switched off in the sys_perf_event_open fallback. New output (notice the 'switching off' lines): $ perf stat -e '{cycles,instructions}' -vvv ls Using CPUID GenuineIntel-6-3D intel_pt default config: tsc ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 exclude_guest 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0x8 sys_perf_event_open failed, error -22 switching off cloexec flag ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 exclude_guest 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0 sys_perf_event_open failed, error -22 switching off exclude_guest, exclude_host ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0 sys_perf_event_open failed, error -22 switching off sample_id_all ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 ... Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20170721121212.21414-2-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-07-21 12:12:09 +00:00
pr_debug2("switching off mmap2\n");
goto fallback_missing_features;
} else if (!perf_missing_features.exclude_guest &&
(evsel->attr.exclude_guest || evsel->attr.exclude_host)) {
perf_missing_features.exclude_guest = true;
perf evsel: Add verbose output for sys_perf_event_open fallback Adding info about what is being switched off in the sys_perf_event_open fallback. New output (notice the 'switching off' lines): $ perf stat -e '{cycles,instructions}' -vvv ls Using CPUID GenuineIntel-6-3D intel_pt default config: tsc ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 exclude_guest 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0x8 sys_perf_event_open failed, error -22 switching off cloexec flag ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 exclude_guest 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0 sys_perf_event_open failed, error -22 switching off exclude_guest, exclude_host ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0 sys_perf_event_open failed, error -22 switching off sample_id_all ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 ... Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20170721121212.21414-2-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-07-21 12:12:09 +00:00
pr_debug2("switching off exclude_guest, exclude_host\n");
goto fallback_missing_features;
} else if (!perf_missing_features.sample_id_all) {
perf_missing_features.sample_id_all = true;
perf evsel: Add verbose output for sys_perf_event_open fallback Adding info about what is being switched off in the sys_perf_event_open fallback. New output (notice the 'switching off' lines): $ perf stat -e '{cycles,instructions}' -vvv ls Using CPUID GenuineIntel-6-3D intel_pt default config: tsc ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 exclude_guest 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0x8 sys_perf_event_open failed, error -22 switching off cloexec flag ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 exclude_guest 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0 sys_perf_event_open failed, error -22 switching off exclude_guest, exclude_host ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0 sys_perf_event_open failed, error -22 switching off sample_id_all ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 ... Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20170721121212.21414-2-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-07-21 12:12:09 +00:00
pr_debug2("switching off sample_id_all\n");
goto retry_sample_id;
} else if (!perf_missing_features.lbr_flags &&
(evsel->attr.branch_sample_type &
(PERF_SAMPLE_BRANCH_NO_CYCLES |
PERF_SAMPLE_BRANCH_NO_FLAGS))) {
perf_missing_features.lbr_flags = true;
perf evsel: Add verbose output for sys_perf_event_open fallback Adding info about what is being switched off in the sys_perf_event_open fallback. New output (notice the 'switching off' lines): $ perf stat -e '{cycles,instructions}' -vvv ls Using CPUID GenuineIntel-6-3D intel_pt default config: tsc ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 exclude_guest 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0x8 sys_perf_event_open failed, error -22 switching off cloexec flag ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 exclude_guest 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0 sys_perf_event_open failed, error -22 switching off exclude_guest, exclude_host ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 ------------------------------------------------------------ sys_perf_event_open: pid 3591 cpu -1 group_fd -1 flags 0 sys_perf_event_open failed, error -22 switching off sample_id_all ------------------------------------------------------------ perf_event_attr: size 112 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING|ID|GROUP disabled 1 inherit 1 enable_on_exec 1 ... Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20170721121212.21414-2-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-07-21 12:12:09 +00:00
pr_debug2("switching off branch sample type no (cycles/flags)\n");
goto fallback_missing_features;
} else if (!perf_missing_features.group_read &&
evsel->attr.inherit &&
perf evsel: Only fall back group read for leader Perf doesn't support mixed events from different PMUs (except software event) in a group. The perf stat should output <not counted>/<not supported> for all events, but it doesn't. For example, perf stat -e '{cycles,uncore_imc_5/umask=0xF,event=0x4/,instructions}' <not counted> cycles <not supported> uncore_imc_5/umask=0xF,event=0x4/ 1,024,300 instructions If perf fails to open an event, it doesn't error out directly. It will disable some features and retry, until the event is opened or all features are disabled. The disabled features will not be re-enabled. The group read is one of these features. For the example as above, the IMC event and the leader event "cycles" are from different PMUs. Opening the IMC event must fail. The group read feature must be disabled for IMC event and the followed event "instructions". The "instructions" event has the same PMU as the leader "cycles". It can be opened successfully. Since the group read feature has been disabled, the "instructions" event will be read as a single event, which definitely has a value. The group read fallback is still useful for the case which kernel doesn't support group read. It is good enough to be handled only by the leader. For the fallback request from members, it must be caused by an error. The fallback only breaks the semantics of group. Limit the group read fallback only for the leader. Committer testing: On a broadwell t450s notebook: Before: # perf stat -e '{cycles,unc_cbo_cache_lookup.read_i,instructions}' sleep 1 Performance counter stats for 'sleep 1': <not counted> cycles <not supported> unc_cbo_cache_lookup.read_i 818,206 instructions 1.003170887 seconds time elapsed Some events weren't counted. Try disabling the NMI watchdog: echo 0 > /proc/sys/kernel/nmi_watchdog perf stat ... echo 1 > /proc/sys/kernel/nmi_watchdog After: # perf stat -e '{cycles,unc_cbo_cache_lookup.read_i,instructions}' sleep 1 Performance counter stats for 'sleep 1': <not counted> cycles <not supported> unc_cbo_cache_lookup.read_i <not counted> instructions 1.001380511 seconds time elapsed Some events weren't counted. Try disabling the NMI watchdog: echo 0 > /proc/sys/kernel/nmi_watchdog perf stat ... echo 1 > /proc/sys/kernel/nmi_watchdog # Reported-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Agustin Vega-Frias <agustinv@codeaurora.org> Cc: Ganapatrao Kulkarni <ganapatrao.kulkarni@cavium.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Shaokun Zhang <zhangshaokun@hisilicon.com> Cc: Will Deacon <will.deacon@arm.com> Fixes: 82bf311e15d2 ("perf stat: Use group read for event groups") Link: http://lkml.kernel.org/r/1524594014-79243-3-git-send-email-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-04-24 18:20:12 +00:00
(evsel->attr.read_format & PERF_FORMAT_GROUP) &&
perf_evsel__is_group_leader(evsel)) {
perf_missing_features.group_read = true;
pr_debug2("switching off group read\n");
goto fallback_missing_features;
}
out_close:
perf stat: Ignore error thread when enabling system-wide --per-thread If we execute 'perf stat --per-thread' with non-root account (even set kernel.perf_event_paranoid = -1 yet), it reports the error: jinyao@skl:~$ perf stat --per-thread Error: You may not have permission to collect system-wide stats. Consider tweaking /proc/sys/kernel/perf_event_paranoid, which controls use of the performance events system by unprivileged users (without CAP_SYS_ADMIN). The current value is 2: -1: Allow use of (almost) all events by all users Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK >= 0: Disallow ftrace function tracepoint by users without CAP_SYS_ADMIN Disallow raw tracepoint access by users without CAP_SYS_ADMIN >= 1: Disallow CPU event access by users without CAP_SYS_ADMIN >= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN To make this setting permanent, edit /etc/sysctl.conf too, e.g.: kernel.perf_event_paranoid = -1 Perhaps the ptrace rule doesn't allow to trace some processes. But anyway the global --per-thread mode had better ignore such errors and continue working on other threads. This patch will record the index of error thread in perf_evsel__open() and remove this thread before retrying. For example (run with non-root, kernel.perf_event_paranoid isn't set): jinyao@skl:~$ perf stat --per-thread ^C Performance counter stats for 'system wide': vmstat-3458 6.171984 cpu-clock:u (msec) # 0.000 CPUs utilized perf-3670 0.515599 cpu-clock:u (msec) # 0.000 CPUs utilized vmstat-3458 1,163,643 cycles:u # 0.189 GHz perf-3670 40,881 cycles:u # 0.079 GHz vmstat-3458 1,410,238 instructions:u # 1.21 insn per cycle perf-3670 3,536 instructions:u # 0.09 insn per cycle vmstat-3458 288,937 branches:u # 46.814 M/sec perf-3670 936 branches:u # 1.815 M/sec vmstat-3458 15,195 branch-misses:u # 5.26% of all branches perf-3670 76 branch-misses:u # 8.12% of all branches 12.651675247 seconds time elapsed Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> 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: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1516117388-10120-1-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-01-16 15:43:08 +00:00
if (err)
threads->err_thread = thread;
do {
while (--thread >= 0) {
close(FD(evsel, cpu, thread));
FD(evsel, cpu, thread) = -1;
}
thread = nthreads;
} while (--cpu >= 0);
return err;
}
perf evsel: Fix buffer overflow while freeing events Fix buffer overflow for: % perf stat -e msr/tsc/,cstate_core/c7-residency/ true that causes glibc free list corruption. For some reason it doesn't trigger in valgrind, but it is visible in AS: ================================================================= ==32681==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x603000003f5c at pc 0x0000005671ef bp 0x7ffdaaac9ac0 sp 0x7ffdaaac9ab0 READ of size 4 at 0x603000003f5c thread T0 #0 0x5671ee in perf_evsel__close_fd util/evsel.c:1196 #1 0x56c57a in perf_evsel__close util/evsel.c:1717 #2 0x55ed5f in perf_evlist__close util/evlist.c:1631 #3 0x4647e1 in __run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:749 #4 0x4648e3 in run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:767 #5 0x46e1bc in cmd_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:2785 #6 0x52f83d in run_builtin /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:296 #7 0x52fd49 in handle_internal_command /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:348 #8 0x5300de in run_argv /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:392 #9 0x5308f3 in main /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:530 #10 0x7f0672d13400 in __libc_start_main (/lib64/libc.so.6+0x20400) #11 0x428419 in _start (/home/ak/hle/obj-perf/perf+0x428419) 0x603000003f5c is located 0 bytes to the right of 28-byte region [0x603000003f40,0x603000003f5c) allocated by thread T0 here: #0 0x7f0675139020 in calloc (/lib64/libasan.so.3+0xc7020) #1 0x648a2d in zalloc util/util.h:23 #2 0x648a88 in xyarray__new util/xyarray.c:9 #3 0x566419 in perf_evsel__alloc_fd util/evsel.c:1039 #4 0x56b427 in perf_evsel__open util/evsel.c:1529 #5 0x56c620 in perf_evsel__open_per_thread util/evsel.c:1730 #6 0x461dea in create_perf_stat_counter /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:263 #7 0x4637d7 in __run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:600 #8 0x4648e3 in run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:767 #9 0x46e1bc in cmd_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:2785 #10 0x52f83d in run_builtin /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:296 #11 0x52fd49 in handle_internal_command /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:348 #12 0x5300de in run_argv /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:392 #13 0x5308f3 in main /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:530 #14 0x7f0672d13400 in __libc_start_main (/lib64/libc.so.6+0x20400) The event is allocated with cpus == 1, but freed with cpus == real number When the evsel close function walks the file descriptors it exceeds the fd xyarray boundaries and reads random memory. v2: Now that xyarrays save their original dimensions we can use these to iterate the two dimensional fd arrays. Fix some users (close, ioctl) in evsel.c to use these fields directly. This allows simplifying the code and dropping quite a few function arguments. Adjust all callers by removing the unneeded arguments. The actual perf event reading still uses the original values from the evsel list. Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170811232634.30465-2-andi@firstfloor.org [ Fix up xy_max_[xy]() -> xyarray__max_[xy]() ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-11 23:26:17 +00:00
void perf_evsel__close(struct perf_evsel *evsel)
{
if (evsel->fd == NULL)
return;
perf evsel: Fix buffer overflow while freeing events Fix buffer overflow for: % perf stat -e msr/tsc/,cstate_core/c7-residency/ true that causes glibc free list corruption. For some reason it doesn't trigger in valgrind, but it is visible in AS: ================================================================= ==32681==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x603000003f5c at pc 0x0000005671ef bp 0x7ffdaaac9ac0 sp 0x7ffdaaac9ab0 READ of size 4 at 0x603000003f5c thread T0 #0 0x5671ee in perf_evsel__close_fd util/evsel.c:1196 #1 0x56c57a in perf_evsel__close util/evsel.c:1717 #2 0x55ed5f in perf_evlist__close util/evlist.c:1631 #3 0x4647e1 in __run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:749 #4 0x4648e3 in run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:767 #5 0x46e1bc in cmd_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:2785 #6 0x52f83d in run_builtin /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:296 #7 0x52fd49 in handle_internal_command /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:348 #8 0x5300de in run_argv /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:392 #9 0x5308f3 in main /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:530 #10 0x7f0672d13400 in __libc_start_main (/lib64/libc.so.6+0x20400) #11 0x428419 in _start (/home/ak/hle/obj-perf/perf+0x428419) 0x603000003f5c is located 0 bytes to the right of 28-byte region [0x603000003f40,0x603000003f5c) allocated by thread T0 here: #0 0x7f0675139020 in calloc (/lib64/libasan.so.3+0xc7020) #1 0x648a2d in zalloc util/util.h:23 #2 0x648a88 in xyarray__new util/xyarray.c:9 #3 0x566419 in perf_evsel__alloc_fd util/evsel.c:1039 #4 0x56b427 in perf_evsel__open util/evsel.c:1529 #5 0x56c620 in perf_evsel__open_per_thread util/evsel.c:1730 #6 0x461dea in create_perf_stat_counter /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:263 #7 0x4637d7 in __run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:600 #8 0x4648e3 in run_perf_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:767 #9 0x46e1bc in cmd_stat /home/ak/hle/linux-hle-2.6/tools/perf/builtin-stat.c:2785 #10 0x52f83d in run_builtin /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:296 #11 0x52fd49 in handle_internal_command /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:348 #12 0x5300de in run_argv /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:392 #13 0x5308f3 in main /home/ak/hle/linux-hle-2.6/tools/perf/perf.c:530 #14 0x7f0672d13400 in __libc_start_main (/lib64/libc.so.6+0x20400) The event is allocated with cpus == 1, but freed with cpus == real number When the evsel close function walks the file descriptors it exceeds the fd xyarray boundaries and reads random memory. v2: Now that xyarrays save their original dimensions we can use these to iterate the two dimensional fd arrays. Fix some users (close, ioctl) in evsel.c to use these fields directly. This allows simplifying the code and dropping quite a few function arguments. Adjust all callers by removing the unneeded arguments. The actual perf event reading still uses the original values from the evsel list. Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170811232634.30465-2-andi@firstfloor.org [ Fix up xy_max_[xy]() -> xyarray__max_[xy]() ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-11 23:26:17 +00:00
perf_evsel__close_fd(evsel);
perf_evsel__free_fd(evsel);
perf_evsel__free_id(evsel);
}
int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
perf tools: Enable grouping logic for parsed events This patch adds a functionality that allows to create event groups based on the way they are specified on the command line. Adding functionality to the '{}' group syntax introduced in earlier patch. The current '--group/-g' option behaviour remains intact. If you specify it for record/stat/top command, all the specified events become members of a single group with the first event as a group leader. With the new '{}' group syntax you can create group like: # perf record -e '{cycles,faults}' ls resulting in single event group containing 'cycles' and 'faults' events, with cycles event as group leader. All groups are created with regards to threads and cpus. Thus recording an event group within a 2 threads on server with 4 CPUs will create 8 separate groups. Examples (first event in brackets is group leader): # 1 group (cpu-clock,task-clock) perf record --group -e cpu-clock,task-clock ls perf record -e '{cpu-clock,task-clock}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock},{minor-faults,major-faults}' ls # 1 group (cpu-clock,task-clock,minor-faults,major-faults) perf record --group -e cpu-clock,task-clock -e minor-faults,major-faults ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock} -e '{minor-faults,major-faults}' \ -e instructions ls # 1 group # (cpu-clock,task-clock,minor-faults,major-faults,instructions) perf record --group -e cpu-clock,task-clock \ -e minor-faults,major-faults -e instructions ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults,instructions}' ls It's possible to use standard event modifier for a group, which spans over all events in the group and updates each event modifier settings, for example: # perf record -r '{faults:k,cache-references}:p' resulting in ':kp' modifier being used for 'faults' and ':p' modifier being used for 'cache-references' event. Reviewed-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Drepper <drepper@gmail.com> Link: http://lkml.kernel.org/n/tip-ho42u0wcr8mn1otkalqi13qp@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-08-08 10:22:36 +00:00
struct cpu_map *cpus)
{
return perf_evsel__open(evsel, cpus, NULL);
}
int perf_evsel__open_per_thread(struct perf_evsel *evsel,
perf tools: Enable grouping logic for parsed events This patch adds a functionality that allows to create event groups based on the way they are specified on the command line. Adding functionality to the '{}' group syntax introduced in earlier patch. The current '--group/-g' option behaviour remains intact. If you specify it for record/stat/top command, all the specified events become members of a single group with the first event as a group leader. With the new '{}' group syntax you can create group like: # perf record -e '{cycles,faults}' ls resulting in single event group containing 'cycles' and 'faults' events, with cycles event as group leader. All groups are created with regards to threads and cpus. Thus recording an event group within a 2 threads on server with 4 CPUs will create 8 separate groups. Examples (first event in brackets is group leader): # 1 group (cpu-clock,task-clock) perf record --group -e cpu-clock,task-clock ls perf record -e '{cpu-clock,task-clock}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock},{minor-faults,major-faults}' ls # 1 group (cpu-clock,task-clock,minor-faults,major-faults) perf record --group -e cpu-clock,task-clock -e minor-faults,major-faults ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock} -e '{minor-faults,major-faults}' \ -e instructions ls # 1 group # (cpu-clock,task-clock,minor-faults,major-faults,instructions) perf record --group -e cpu-clock,task-clock \ -e minor-faults,major-faults -e instructions ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults,instructions}' ls It's possible to use standard event modifier for a group, which spans over all events in the group and updates each event modifier settings, for example: # perf record -r '{faults:k,cache-references}:p' resulting in ':kp' modifier being used for 'faults' and ':p' modifier being used for 'cache-references' event. Reviewed-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Drepper <drepper@gmail.com> Link: http://lkml.kernel.org/n/tip-ho42u0wcr8mn1otkalqi13qp@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-08-08 10:22:36 +00:00
struct thread_map *threads)
{
return perf_evsel__open(evsel, NULL, threads);
}
static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel,
const union perf_event *event,
struct perf_sample *sample)
{
u64 type = evsel->attr.sample_type;
const u64 *array = event->sample.array;
bool swapped = evsel->needs_swap;
perf evsel: Fix 32 bit values endianity swap for sample_id_all header We swap the sample_id_all header by u64 pointers. Some members of the header happen to be 32 bit values. We need to handle them separatelly. Together with other endianity patches, this change fixies perf report discrepancies on origin and target systems as described in test 1 below, e.g. following perf report diff: ... 0.12% ps [kernel.kallsyms] [k] clear_page - 0.12% awk bash [.] alloc_word_desc + 0.12% awk bash [.] yyparse 0.11% beah-rhts-task libpython2.6.so.1.0 [.] 0x5560e 0.10% perf libc-2.12.so [.] __ctype_toupper_loc - 0.09% rhts-test-runne bash [.] maybe_make_export_env + 0.09% rhts-test-runne bash [.] 0x385a0 0.09% ps [kernel.kallsyms] [k] page_fault ... Note, running following to test perf endianity handling: test 1) - origin system: # perf record -a -- sleep 10 (any perf record will do) # perf report > report.origin # perf archive perf.data - copy the perf.data, report.origin and perf.data.tar.bz2 to a target system and run: # tar xjvf perf.data.tar.bz2 -C ~/.debug # perf report > report.target # diff -u report.origin report.target - the diff should produce no output (besides some white space stuff and possibly different date/TZ output) test 2) - origin system: # perf record -ag -fo /tmp/perf.data -- sleep 1 - mount origin system root to the target system on /mnt/origin - target system: # perf script --symfs /mnt/origin -I -i /mnt/origin/tmp/perf.data \ --kallsyms /mnt/origin/proc/kallsyms - complete perf.data header is displayed Signed-off-by: Jiri Olsa <jolsa@redhat.com> Reviewed-by: David Ahern <dsahern@gmail.com> Tested-by: David Ahern <dsahern@gmail.com> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1338380624-7443-4-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-05-30 12:23:44 +00:00
union u64_swap u;
array += ((event->header.size -
sizeof(event->header)) / sizeof(u64)) - 1;
if (type & PERF_SAMPLE_IDENTIFIER) {
sample->id = *array;
array--;
}
if (type & PERF_SAMPLE_CPU) {
perf evsel: Fix 32 bit values endianity swap for sample_id_all header We swap the sample_id_all header by u64 pointers. Some members of the header happen to be 32 bit values. We need to handle them separatelly. Together with other endianity patches, this change fixies perf report discrepancies on origin and target systems as described in test 1 below, e.g. following perf report diff: ... 0.12% ps [kernel.kallsyms] [k] clear_page - 0.12% awk bash [.] alloc_word_desc + 0.12% awk bash [.] yyparse 0.11% beah-rhts-task libpython2.6.so.1.0 [.] 0x5560e 0.10% perf libc-2.12.so [.] __ctype_toupper_loc - 0.09% rhts-test-runne bash [.] maybe_make_export_env + 0.09% rhts-test-runne bash [.] 0x385a0 0.09% ps [kernel.kallsyms] [k] page_fault ... Note, running following to test perf endianity handling: test 1) - origin system: # perf record -a -- sleep 10 (any perf record will do) # perf report > report.origin # perf archive perf.data - copy the perf.data, report.origin and perf.data.tar.bz2 to a target system and run: # tar xjvf perf.data.tar.bz2 -C ~/.debug # perf report > report.target # diff -u report.origin report.target - the diff should produce no output (besides some white space stuff and possibly different date/TZ output) test 2) - origin system: # perf record -ag -fo /tmp/perf.data -- sleep 1 - mount origin system root to the target system on /mnt/origin - target system: # perf script --symfs /mnt/origin -I -i /mnt/origin/tmp/perf.data \ --kallsyms /mnt/origin/proc/kallsyms - complete perf.data header is displayed Signed-off-by: Jiri Olsa <jolsa@redhat.com> Reviewed-by: David Ahern <dsahern@gmail.com> Tested-by: David Ahern <dsahern@gmail.com> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1338380624-7443-4-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-05-30 12:23:44 +00:00
u.val64 = *array;
if (swapped) {
/* undo swap of u64, then swap on individual u32s */
u.val64 = bswap_64(u.val64);
u.val32[0] = bswap_32(u.val32[0]);
}
sample->cpu = u.val32[0];
array--;
}
if (type & PERF_SAMPLE_STREAM_ID) {
sample->stream_id = *array;
array--;
}
if (type & PERF_SAMPLE_ID) {
sample->id = *array;
array--;
}
if (type & PERF_SAMPLE_TIME) {
sample->time = *array;
array--;
}
if (type & PERF_SAMPLE_TID) {
perf evsel: Fix 32 bit values endianity swap for sample_id_all header We swap the sample_id_all header by u64 pointers. Some members of the header happen to be 32 bit values. We need to handle them separatelly. Together with other endianity patches, this change fixies perf report discrepancies on origin and target systems as described in test 1 below, e.g. following perf report diff: ... 0.12% ps [kernel.kallsyms] [k] clear_page - 0.12% awk bash [.] alloc_word_desc + 0.12% awk bash [.] yyparse 0.11% beah-rhts-task libpython2.6.so.1.0 [.] 0x5560e 0.10% perf libc-2.12.so [.] __ctype_toupper_loc - 0.09% rhts-test-runne bash [.] maybe_make_export_env + 0.09% rhts-test-runne bash [.] 0x385a0 0.09% ps [kernel.kallsyms] [k] page_fault ... Note, running following to test perf endianity handling: test 1) - origin system: # perf record -a -- sleep 10 (any perf record will do) # perf report > report.origin # perf archive perf.data - copy the perf.data, report.origin and perf.data.tar.bz2 to a target system and run: # tar xjvf perf.data.tar.bz2 -C ~/.debug # perf report > report.target # diff -u report.origin report.target - the diff should produce no output (besides some white space stuff and possibly different date/TZ output) test 2) - origin system: # perf record -ag -fo /tmp/perf.data -- sleep 1 - mount origin system root to the target system on /mnt/origin - target system: # perf script --symfs /mnt/origin -I -i /mnt/origin/tmp/perf.data \ --kallsyms /mnt/origin/proc/kallsyms - complete perf.data header is displayed Signed-off-by: Jiri Olsa <jolsa@redhat.com> Reviewed-by: David Ahern <dsahern@gmail.com> Tested-by: David Ahern <dsahern@gmail.com> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1338380624-7443-4-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-05-30 12:23:44 +00:00
u.val64 = *array;
if (swapped) {
/* undo swap of u64, then swap on individual u32s */
u.val64 = bswap_64(u.val64);
u.val32[0] = bswap_32(u.val32[0]);
u.val32[1] = bswap_32(u.val32[1]);
}
sample->pid = u.val32[0];
sample->tid = u.val32[1];
array--;
}
return 0;
}
static inline bool overflow(const void *endp, u16 max_size, const void *offset,
u64 size)
{
return size > max_size || offset + size > endp;
}
#define OVERFLOW_CHECK(offset, size, max_size) \
do { \
if (overflow(endp, (max_size), (offset), (size))) \
return -EFAULT; \
} while (0)
#define OVERFLOW_CHECK_u64(offset) \
OVERFLOW_CHECK(offset, sizeof(u64), sizeof(u64))
static int
perf_event__check_size(union perf_event *event, unsigned int sample_size)
{
/*
* The evsel's sample_size is based on PERF_SAMPLE_MASK which includes
* up to PERF_SAMPLE_PERIOD. After that overflow() must be used to
* check the format does not go past the end of the event.
*/
if (sample_size + sizeof(event->header) > event->header.size)
return -EFAULT;
return 0;
}
int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
struct perf_sample *data)
{
u64 type = evsel->attr.sample_type;
bool swapped = evsel->needs_swap;
const u64 *array;
u16 max_size = event->header.size;
const void *endp = (void *)event + max_size;
u64 sz;
perf tool: Fix endianness handling of u32 data in samples Currently, analyzing PPC data files on x86 the cpu field is always 0 and the tid and pid are backwards. For example, analyzing a PPC file on PPC the pid/tid fields show: rsyslogd 1210/1212 and analyzing the same PPC file using an x86 perf binary shows: rsyslogd 1212/1210 The problem is that the swap_op method for samples is perf_event__all64_swap which assumes all elements in the sample_data struct are u64s. cpu, tid and pid are u32s and need to be handled individually. Given that the swap is done before the sample is parsed, the simplest solution is to undo the 64-bit swap of those elements when the sample is parsed and do the proper swap. The RAW data field is generic and perf cannot have programmatic knowledge of how to treat that data. Instead a warning is given to the user. Thanks to Anton Blanchard for providing a data file for a mult-CPU PPC system so I could verify the fix for the CPU fields. v3 -> v4: - fixed use of WARN_ONCE v2 -> v3: - used WARN_ONCE for message regarding raw data - removed struct wrapper around union - fixed whitespace issues v1 -> v2: - added a union for undoing the byte-swap on u64 and redoing swap on u32's to address compiler errors (see git commit 65014ab3) Cc: Anton Blanchard <anton@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1315321946-16993-1-git-send-email-dsahern@gmail.com Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-09-06 15:12:26 +00:00
/*
* used for cross-endian analysis. See git commit 65014ab3
* for why this goofiness is needed.
*/
union u64_swap u;
perf tool: Fix endianness handling of u32 data in samples Currently, analyzing PPC data files on x86 the cpu field is always 0 and the tid and pid are backwards. For example, analyzing a PPC file on PPC the pid/tid fields show: rsyslogd 1210/1212 and analyzing the same PPC file using an x86 perf binary shows: rsyslogd 1212/1210 The problem is that the swap_op method for samples is perf_event__all64_swap which assumes all elements in the sample_data struct are u64s. cpu, tid and pid are u32s and need to be handled individually. Given that the swap is done before the sample is parsed, the simplest solution is to undo the 64-bit swap of those elements when the sample is parsed and do the proper swap. The RAW data field is generic and perf cannot have programmatic knowledge of how to treat that data. Instead a warning is given to the user. Thanks to Anton Blanchard for providing a data file for a mult-CPU PPC system so I could verify the fix for the CPU fields. v3 -> v4: - fixed use of WARN_ONCE v2 -> v3: - used WARN_ONCE for message regarding raw data - removed struct wrapper around union - fixed whitespace issues v1 -> v2: - added a union for undoing the byte-swap on u64 and redoing swap on u32's to address compiler errors (see git commit 65014ab3) Cc: Anton Blanchard <anton@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1315321946-16993-1-git-send-email-dsahern@gmail.com Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-09-06 15:12:26 +00:00
memset(data, 0, sizeof(*data));
data->cpu = data->pid = data->tid = -1;
data->stream_id = data->id = data->time = -1ULL;
data->period = evsel->attr.sample_period;
data->cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
data->misc = event->header.misc;
data->id = -1ULL;
data->data_src = PERF_MEM_DATA_SRC_NONE;
if (event->header.type != PERF_RECORD_SAMPLE) {
if (!evsel->attr.sample_id_all)
return 0;
return perf_evsel__parse_id_sample(evsel, event, data);
}
array = event->sample.array;
if (perf_event__check_size(event, evsel->sample_size))
return -EFAULT;
if (type & PERF_SAMPLE_IDENTIFIER) {
data->id = *array;
array++;
}
if (type & PERF_SAMPLE_IP) {
data->ip = *array;
array++;
}
if (type & PERF_SAMPLE_TID) {
perf tool: Fix endianness handling of u32 data in samples Currently, analyzing PPC data files on x86 the cpu field is always 0 and the tid and pid are backwards. For example, analyzing a PPC file on PPC the pid/tid fields show: rsyslogd 1210/1212 and analyzing the same PPC file using an x86 perf binary shows: rsyslogd 1212/1210 The problem is that the swap_op method for samples is perf_event__all64_swap which assumes all elements in the sample_data struct are u64s. cpu, tid and pid are u32s and need to be handled individually. Given that the swap is done before the sample is parsed, the simplest solution is to undo the 64-bit swap of those elements when the sample is parsed and do the proper swap. The RAW data field is generic and perf cannot have programmatic knowledge of how to treat that data. Instead a warning is given to the user. Thanks to Anton Blanchard for providing a data file for a mult-CPU PPC system so I could verify the fix for the CPU fields. v3 -> v4: - fixed use of WARN_ONCE v2 -> v3: - used WARN_ONCE for message regarding raw data - removed struct wrapper around union - fixed whitespace issues v1 -> v2: - added a union for undoing the byte-swap on u64 and redoing swap on u32's to address compiler errors (see git commit 65014ab3) Cc: Anton Blanchard <anton@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1315321946-16993-1-git-send-email-dsahern@gmail.com Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-09-06 15:12:26 +00:00
u.val64 = *array;
if (swapped) {
/* undo swap of u64, then swap on individual u32s */
u.val64 = bswap_64(u.val64);
u.val32[0] = bswap_32(u.val32[0]);
u.val32[1] = bswap_32(u.val32[1]);
}
data->pid = u.val32[0];
data->tid = u.val32[1];
array++;
}
if (type & PERF_SAMPLE_TIME) {
data->time = *array;
array++;
}
if (type & PERF_SAMPLE_ADDR) {
data->addr = *array;
array++;
}
if (type & PERF_SAMPLE_ID) {
data->id = *array;
array++;
}
if (type & PERF_SAMPLE_STREAM_ID) {
data->stream_id = *array;
array++;
}
if (type & PERF_SAMPLE_CPU) {
perf tool: Fix endianness handling of u32 data in samples Currently, analyzing PPC data files on x86 the cpu field is always 0 and the tid and pid are backwards. For example, analyzing a PPC file on PPC the pid/tid fields show: rsyslogd 1210/1212 and analyzing the same PPC file using an x86 perf binary shows: rsyslogd 1212/1210 The problem is that the swap_op method for samples is perf_event__all64_swap which assumes all elements in the sample_data struct are u64s. cpu, tid and pid are u32s and need to be handled individually. Given that the swap is done before the sample is parsed, the simplest solution is to undo the 64-bit swap of those elements when the sample is parsed and do the proper swap. The RAW data field is generic and perf cannot have programmatic knowledge of how to treat that data. Instead a warning is given to the user. Thanks to Anton Blanchard for providing a data file for a mult-CPU PPC system so I could verify the fix for the CPU fields. v3 -> v4: - fixed use of WARN_ONCE v2 -> v3: - used WARN_ONCE for message regarding raw data - removed struct wrapper around union - fixed whitespace issues v1 -> v2: - added a union for undoing the byte-swap on u64 and redoing swap on u32's to address compiler errors (see git commit 65014ab3) Cc: Anton Blanchard <anton@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1315321946-16993-1-git-send-email-dsahern@gmail.com Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-09-06 15:12:26 +00:00
u.val64 = *array;
if (swapped) {
/* undo swap of u64, then swap on individual u32s */
u.val64 = bswap_64(u.val64);
u.val32[0] = bswap_32(u.val32[0]);
}
data->cpu = u.val32[0];
array++;
}
if (type & PERF_SAMPLE_PERIOD) {
data->period = *array;
array++;
}
if (type & PERF_SAMPLE_READ) {
u64 read_format = evsel->attr.read_format;
OVERFLOW_CHECK_u64(array);
if (read_format & PERF_FORMAT_GROUP)
data->read.group.nr = *array;
else
data->read.one.value = *array;
array++;
if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
OVERFLOW_CHECK_u64(array);
data->read.time_enabled = *array;
array++;
}
if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
OVERFLOW_CHECK_u64(array);
data->read.time_running = *array;
array++;
}
/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
if (read_format & PERF_FORMAT_GROUP) {
const u64 max_group_nr = UINT64_MAX /
sizeof(struct sample_read_value);
if (data->read.group.nr > max_group_nr)
return -EFAULT;
sz = data->read.group.nr *
sizeof(struct sample_read_value);
OVERFLOW_CHECK(array, sz, max_size);
data->read.group.values =
(struct sample_read_value *)array;
array = (void *)array + sz;
} else {
OVERFLOW_CHECK_u64(array);
data->read.one.id = *array;
array++;
}
}
if (evsel__has_callchain(evsel)) {
const u64 max_callchain_nr = UINT64_MAX / sizeof(u64);
OVERFLOW_CHECK_u64(array);
data->callchain = (struct ip_callchain *)array++;
if (data->callchain->nr > max_callchain_nr)
return -EFAULT;
sz = data->callchain->nr * sizeof(u64);
OVERFLOW_CHECK(array, sz, max_size);
array = (void *)array + sz;
}
if (type & PERF_SAMPLE_RAW) {
OVERFLOW_CHECK_u64(array);
perf tool: Fix endianness handling of u32 data in samples Currently, analyzing PPC data files on x86 the cpu field is always 0 and the tid and pid are backwards. For example, analyzing a PPC file on PPC the pid/tid fields show: rsyslogd 1210/1212 and analyzing the same PPC file using an x86 perf binary shows: rsyslogd 1212/1210 The problem is that the swap_op method for samples is perf_event__all64_swap which assumes all elements in the sample_data struct are u64s. cpu, tid and pid are u32s and need to be handled individually. Given that the swap is done before the sample is parsed, the simplest solution is to undo the 64-bit swap of those elements when the sample is parsed and do the proper swap. The RAW data field is generic and perf cannot have programmatic knowledge of how to treat that data. Instead a warning is given to the user. Thanks to Anton Blanchard for providing a data file for a mult-CPU PPC system so I could verify the fix for the CPU fields. v3 -> v4: - fixed use of WARN_ONCE v2 -> v3: - used WARN_ONCE for message regarding raw data - removed struct wrapper around union - fixed whitespace issues v1 -> v2: - added a union for undoing the byte-swap on u64 and redoing swap on u32's to address compiler errors (see git commit 65014ab3) Cc: Anton Blanchard <anton@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1315321946-16993-1-git-send-email-dsahern@gmail.com Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-09-06 15:12:26 +00:00
u.val64 = *array;
/*
* Undo swap of u64, then swap on individual u32s,
* get the size of the raw area and undo all of the
* swap. The pevent interface handles endianity by
* itself.
*/
if (swapped) {
perf tool: Fix endianness handling of u32 data in samples Currently, analyzing PPC data files on x86 the cpu field is always 0 and the tid and pid are backwards. For example, analyzing a PPC file on PPC the pid/tid fields show: rsyslogd 1210/1212 and analyzing the same PPC file using an x86 perf binary shows: rsyslogd 1212/1210 The problem is that the swap_op method for samples is perf_event__all64_swap which assumes all elements in the sample_data struct are u64s. cpu, tid and pid are u32s and need to be handled individually. Given that the swap is done before the sample is parsed, the simplest solution is to undo the 64-bit swap of those elements when the sample is parsed and do the proper swap. The RAW data field is generic and perf cannot have programmatic knowledge of how to treat that data. Instead a warning is given to the user. Thanks to Anton Blanchard for providing a data file for a mult-CPU PPC system so I could verify the fix for the CPU fields. v3 -> v4: - fixed use of WARN_ONCE v2 -> v3: - used WARN_ONCE for message regarding raw data - removed struct wrapper around union - fixed whitespace issues v1 -> v2: - added a union for undoing the byte-swap on u64 and redoing swap on u32's to address compiler errors (see git commit 65014ab3) Cc: Anton Blanchard <anton@samba.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1315321946-16993-1-git-send-email-dsahern@gmail.com Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-09-06 15:12:26 +00:00
u.val64 = bswap_64(u.val64);
u.val32[0] = bswap_32(u.val32[0]);
u.val32[1] = bswap_32(u.val32[1]);
}
data->raw_size = u.val32[0];
/*
* The raw data is aligned on 64bits including the
* u32 size, so it's safe to use mem_bswap_64.
*/
if (swapped)
mem_bswap_64((void *) array, data->raw_size);
array = (void *)array + sizeof(u32);
OVERFLOW_CHECK(array, data->raw_size, max_size);
data->raw_data = (void *)array;
array = (void *)array + data->raw_size;
}
if (type & PERF_SAMPLE_BRANCH_STACK) {
const u64 max_branch_nr = UINT64_MAX /
sizeof(struct branch_entry);
OVERFLOW_CHECK_u64(array);
data->branch_stack = (struct branch_stack *)array++;
if (data->branch_stack->nr > max_branch_nr)
return -EFAULT;
sz = data->branch_stack->nr * sizeof(struct branch_entry);
OVERFLOW_CHECK(array, sz, max_size);
array = (void *)array + sz;
}
if (type & PERF_SAMPLE_REGS_USER) {
OVERFLOW_CHECK_u64(array);
data->user_regs.abi = *array;
array++;
if (data->user_regs.abi) {
u64 mask = evsel->attr.sample_regs_user;
sz = hweight64(mask) * sizeof(u64);
OVERFLOW_CHECK(array, sz, max_size);
data->user_regs.mask = mask;
data->user_regs.regs = (u64 *)array;
array = (void *)array + sz;
}
}
if (type & PERF_SAMPLE_STACK_USER) {
OVERFLOW_CHECK_u64(array);
sz = *array++;
data->user_stack.offset = ((char *)(array - 1)
- (char *) event);
if (!sz) {
data->user_stack.size = 0;
} else {
OVERFLOW_CHECK(array, sz, max_size);
data->user_stack.data = (char *)array;
array = (void *)array + sz;
OVERFLOW_CHECK_u64(array);
data->user_stack.size = *array++;
if (WARN_ONCE(data->user_stack.size > sz,
"user stack dump failure\n"))
return -EFAULT;
}
}
if (type & PERF_SAMPLE_WEIGHT) {
OVERFLOW_CHECK_u64(array);
data->weight = *array;
array++;
}
if (type & PERF_SAMPLE_DATA_SRC) {
OVERFLOW_CHECK_u64(array);
data->data_src = *array;
array++;
}
if (type & PERF_SAMPLE_TRANSACTION) {
OVERFLOW_CHECK_u64(array);
data->transaction = *array;
array++;
}
data->intr_regs.abi = PERF_SAMPLE_REGS_ABI_NONE;
if (type & PERF_SAMPLE_REGS_INTR) {
OVERFLOW_CHECK_u64(array);
data->intr_regs.abi = *array;
array++;
if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) {
u64 mask = evsel->attr.sample_regs_intr;
sz = hweight64(mask) * sizeof(u64);
OVERFLOW_CHECK(array, sz, max_size);
data->intr_regs.mask = mask;
data->intr_regs.regs = (u64 *)array;
array = (void *)array + sz;
}
}
data->phys_addr = 0;
if (type & PERF_SAMPLE_PHYS_ADDR) {
data->phys_addr = *array;
array++;
}
return 0;
}
int perf_evsel__parse_sample_timestamp(struct perf_evsel *evsel,
union perf_event *event,
u64 *timestamp)
{
u64 type = evsel->attr.sample_type;
const u64 *array;
if (!(type & PERF_SAMPLE_TIME))
return -1;
if (event->header.type != PERF_RECORD_SAMPLE) {
struct perf_sample data = {
.time = -1ULL,
};
if (!evsel->attr.sample_id_all)
return -1;
if (perf_evsel__parse_id_sample(evsel, event, &data))
return -1;
*timestamp = data.time;
return 0;
}
array = event->sample.array;
if (perf_event__check_size(event, evsel->sample_size))
return -EFAULT;
if (type & PERF_SAMPLE_IDENTIFIER)
array++;
if (type & PERF_SAMPLE_IP)
array++;
if (type & PERF_SAMPLE_TID)
array++;
if (type & PERF_SAMPLE_TIME)
*timestamp = *array;
return 0;
}
size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
u64 read_format)
{
size_t sz, result = sizeof(struct sample_event);
if (type & PERF_SAMPLE_IDENTIFIER)
result += sizeof(u64);
if (type & PERF_SAMPLE_IP)
result += sizeof(u64);
if (type & PERF_SAMPLE_TID)
result += sizeof(u64);
if (type & PERF_SAMPLE_TIME)
result += sizeof(u64);
if (type & PERF_SAMPLE_ADDR)
result += sizeof(u64);
if (type & PERF_SAMPLE_ID)
result += sizeof(u64);
if (type & PERF_SAMPLE_STREAM_ID)
result += sizeof(u64);
if (type & PERF_SAMPLE_CPU)
result += sizeof(u64);
if (type & PERF_SAMPLE_PERIOD)
result += sizeof(u64);
if (type & PERF_SAMPLE_READ) {
result += sizeof(u64);
if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
result += sizeof(u64);
if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
result += sizeof(u64);
/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
if (read_format & PERF_FORMAT_GROUP) {
sz = sample->read.group.nr *
sizeof(struct sample_read_value);
result += sz;
} else {
result += sizeof(u64);
}
}
if (type & PERF_SAMPLE_CALLCHAIN) {
sz = (sample->callchain->nr + 1) * sizeof(u64);
result += sz;
}
if (type & PERF_SAMPLE_RAW) {
result += sizeof(u32);
result += sample->raw_size;
}
if (type & PERF_SAMPLE_BRANCH_STACK) {
sz = sample->branch_stack->nr * sizeof(struct branch_entry);
sz += sizeof(u64);
result += sz;
}
if (type & PERF_SAMPLE_REGS_USER) {
if (sample->user_regs.abi) {
result += sizeof(u64);
sz = hweight64(sample->user_regs.mask) * sizeof(u64);
result += sz;
} else {
result += sizeof(u64);
}
}
if (type & PERF_SAMPLE_STACK_USER) {
sz = sample->user_stack.size;
result += sizeof(u64);
if (sz) {
result += sz;
result += sizeof(u64);
}
}
if (type & PERF_SAMPLE_WEIGHT)
result += sizeof(u64);
if (type & PERF_SAMPLE_DATA_SRC)
result += sizeof(u64);
if (type & PERF_SAMPLE_TRANSACTION)
result += sizeof(u64);
if (type & PERF_SAMPLE_REGS_INTR) {
if (sample->intr_regs.abi) {
result += sizeof(u64);
sz = hweight64(sample->intr_regs.mask) * sizeof(u64);
result += sz;
} else {
result += sizeof(u64);
}
}
if (type & PERF_SAMPLE_PHYS_ADDR)
result += sizeof(u64);
return result;
}
int perf_event__synthesize_sample(union perf_event *event, u64 type,
u64 read_format,
const struct perf_sample *sample)
{
u64 *array;
size_t sz;
/*
* used for cross-endian analysis. See git commit 65014ab3
* for why this goofiness is needed.
*/
union u64_swap u;
array = event->sample.array;
if (type & PERF_SAMPLE_IDENTIFIER) {
*array = sample->id;
array++;
}
if (type & PERF_SAMPLE_IP) {
*array = sample->ip;
array++;
}
if (type & PERF_SAMPLE_TID) {
u.val32[0] = sample->pid;
u.val32[1] = sample->tid;
*array = u.val64;
array++;
}
if (type & PERF_SAMPLE_TIME) {
*array = sample->time;
array++;
}
if (type & PERF_SAMPLE_ADDR) {
*array = sample->addr;
array++;
}
if (type & PERF_SAMPLE_ID) {
*array = sample->id;
array++;
}
if (type & PERF_SAMPLE_STREAM_ID) {
*array = sample->stream_id;
array++;
}
if (type & PERF_SAMPLE_CPU) {
u.val32[0] = sample->cpu;
u.val32[1] = 0;
*array = u.val64;
array++;
}
if (type & PERF_SAMPLE_PERIOD) {
*array = sample->period;
array++;
}
if (type & PERF_SAMPLE_READ) {
if (read_format & PERF_FORMAT_GROUP)
*array = sample->read.group.nr;
else
*array = sample->read.one.value;
array++;
if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
*array = sample->read.time_enabled;
array++;
}
if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
*array = sample->read.time_running;
array++;
}
/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
if (read_format & PERF_FORMAT_GROUP) {
sz = sample->read.group.nr *
sizeof(struct sample_read_value);
memcpy(array, sample->read.group.values, sz);
array = (void *)array + sz;
} else {
*array = sample->read.one.id;
array++;
}
}
if (type & PERF_SAMPLE_CALLCHAIN) {
sz = (sample->callchain->nr + 1) * sizeof(u64);
memcpy(array, sample->callchain, sz);
array = (void *)array + sz;
}
if (type & PERF_SAMPLE_RAW) {
u.val32[0] = sample->raw_size;
*array = u.val64;
array = (void *)array + sizeof(u32);
memcpy(array, sample->raw_data, sample->raw_size);
array = (void *)array + sample->raw_size;
}
if (type & PERF_SAMPLE_BRANCH_STACK) {
sz = sample->branch_stack->nr * sizeof(struct branch_entry);
sz += sizeof(u64);
memcpy(array, sample->branch_stack, sz);
array = (void *)array + sz;
}
if (type & PERF_SAMPLE_REGS_USER) {
if (sample->user_regs.abi) {
*array++ = sample->user_regs.abi;
sz = hweight64(sample->user_regs.mask) * sizeof(u64);
memcpy(array, sample->user_regs.regs, sz);
array = (void *)array + sz;
} else {
*array++ = 0;
}
}
if (type & PERF_SAMPLE_STACK_USER) {
sz = sample->user_stack.size;
*array++ = sz;
if (sz) {
memcpy(array, sample->user_stack.data, sz);
array = (void *)array + sz;
*array++ = sz;
}
}
if (type & PERF_SAMPLE_WEIGHT) {
*array = sample->weight;
array++;
}
if (type & PERF_SAMPLE_DATA_SRC) {
*array = sample->data_src;
array++;
}
if (type & PERF_SAMPLE_TRANSACTION) {
*array = sample->transaction;
array++;
}
if (type & PERF_SAMPLE_REGS_INTR) {
if (sample->intr_regs.abi) {
*array++ = sample->intr_regs.abi;
sz = hweight64(sample->intr_regs.mask) * sizeof(u64);
memcpy(array, sample->intr_regs.regs, sz);
array = (void *)array + sz;
} else {
*array++ = 0;
}
}
if (type & PERF_SAMPLE_PHYS_ADDR) {
*array = sample->phys_addr;
array++;
}
return 0;
}
struct tep_format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name)
{
return tep_find_field(evsel->tp_format, name);
}
void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
const char *name)
{
struct tep_format_field *field = perf_evsel__field(evsel, name);
int offset;
if (!field)
return NULL;
offset = field->offset;
if (field->flags & TEP_FIELD_IS_DYNAMIC) {
offset = *(int *)(sample->raw_data + field->offset);
offset &= 0xffff;
}
return sample->raw_data + offset;
}
u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sample,
bool needs_swap)
{
u64 value;
void *ptr = sample->raw_data + field->offset;
switch (field->size) {
case 1:
return *(u8 *)ptr;
case 2:
value = *(u16 *)ptr;
break;
case 4:
value = *(u32 *)ptr;
break;
case 8:
perf timechart: Fix SIBGUS error on sparc64 perf timechart -T on sparc64 is terminating due to SIGBUS. Backtrace: Program received signal SIGBUS, Bus error. 0x0000000000173d7c in perf_evsel__intval (evsel=<value optimized out>, sample=0x7feffffda28, name=0x289b28 "prev_state") at util/evsel.c:1918 1918 util/evsel.c: No such file or directory. in util/evsel.c Missing separate debuginfos, use: debuginfo-install audit-libs-2.3.7-1.0.1.el6.sparc64 bzip2-libs-1.0.5-7.el6_0.sparc64 elfutils-libelf-0.155-2.0.3.el6.sparc64 elfutils-libs-0.155-2.0.3.el6.sparc64 glibc-2.12-1.132.0.8.el6_5.sparc64 numactl-2.0.7-8.el6.sparc64 python-libs-2.6.6-52.0.2.el6.sparc64 slang-2.2.1-1.el6.sparc64 xz-libs-4.999.9-0.3.beta.20091007git.el6.sparc64 zlib-1.2.3-29.el6.sparc64 (gdb) bt 0 0x0000000000173d7c in perf_evsel__intval (evsel=<value optimized out>, sample=0x7feffffda28, name=0x289b28 "prev_state") at util/evsel.c:1918 1 0x0000000000123b94 in process_sample_sched_switch (tchart=0x7feffffe040, evsel=0x4ca850, sample=0x7feffffda28, backtrace=0xc39010 "") at builtin-timechart.c:627 2 0x0000000000122828 in process_sample_event (tool=0x7feffffe040, event=<value optimized out>, sample=0x7feffffda28, evsel=0x4ca850, machine=0x4c9c88) at builtin-timechart.c:569 Another extended load on unaligned pointer. As before fix by copying to a temporary variable using memcpy. Signed-off-by: David Ahern <david.ahern@oracle.com> Link: http://lkml.kernel.org/r/1427228049-51893-1-git-send-email-david.ahern@oracle.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-03-24 20:14:09 +00:00
memcpy(&value, ptr, sizeof(u64));
break;
default:
return 0;
}
if (!needs_swap)
return value;
switch (field->size) {
case 2:
return bswap_16(value);
case 4:
return bswap_32(value);
case 8:
return bswap_64(value);
default:
return 0;
}
return 0;
}
u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
const char *name)
{
struct tep_format_field *field = perf_evsel__field(evsel, name);
if (!field)
return 0;
return field ? format_field__intval(field, sample, evsel->needs_swap) : 0;
}
bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
char *msg, size_t msgsize)
{
perf evsel: Handle EACCESS + perf_event_paranoid=2 in fallback() Now with the default for the kernel.perf_event_paranoid sysctl being 2 [1] we need to fall back to :u, i.e. to set perf_event_attr.exclude_kernel to 1. Before: [acme@jouet linux]$ perf record usleep 1 Error: You may not have permission to collect stats. Consider tweaking /proc/sys/kernel/perf_event_paranoid, which controls use of the performance events system by unprivileged users (without CAP_SYS_ADMIN). The current value is 2: -1: Allow use of (almost) all events by all users >= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK >= 1: Disallow CPU event access by users without CAP_SYS_ADMIN >= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN [acme@jouet linux]$ After: [acme@jouet linux]$ perf record usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.016 MB perf.data (7 samples) ] [acme@jouet linux]$ perf evlist cycles:u [acme@jouet linux]$ perf evlist -v cycles:u: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, exclude_kernel: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 [acme@jouet linux]$ And if the user turns on verbose mode, an explanation will appear: [acme@jouet linux]$ perf record -v usleep 1 Warning: kernel.perf_event_paranoid=2, trying to fall back to excluding kernel samples mmap size 528384B [ perf record: Woken up 1 times to write data ] Looking at the vmlinux_path (8 entries long) Using /lib/modules/4.6.0-rc7+/build/vmlinux for symbols [ perf record: Captured and wrote 0.016 MB perf.data (7 samples) ] [acme@jouet linux]$ [1] 0161028b7c8a ("perf/core: Change the default paranoia level to 2") Reported-by: Ingo Molnar <mingo@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kees Cook <keescook@chromium.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-b20jmx4dxt5hpaa9t2rroi0o@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-05-12 19:07:47 +00:00
int paranoid;
if ((err == ENOENT || err == ENXIO || err == ENODEV) &&
evsel->attr.type == PERF_TYPE_HARDWARE &&
evsel->attr.config == PERF_COUNT_HW_CPU_CYCLES) {
/*
* If it's cycles then fall back to hrtimer based
* cpu-clock-tick sw counter, which is always available even if
* no PMU support.
*
* PPC returns ENXIO until 2.6.37 (behavior changed with commit
* b0a873e).
*/
scnprintf(msg, msgsize, "%s",
"The cycles event is not supported, trying to fall back to cpu-clock-ticks");
evsel->attr.type = PERF_TYPE_SOFTWARE;
evsel->attr.config = PERF_COUNT_SW_CPU_CLOCK;
zfree(&evsel->name);
perf evsel: Handle EACCESS + perf_event_paranoid=2 in fallback() Now with the default for the kernel.perf_event_paranoid sysctl being 2 [1] we need to fall back to :u, i.e. to set perf_event_attr.exclude_kernel to 1. Before: [acme@jouet linux]$ perf record usleep 1 Error: You may not have permission to collect stats. Consider tweaking /proc/sys/kernel/perf_event_paranoid, which controls use of the performance events system by unprivileged users (without CAP_SYS_ADMIN). The current value is 2: -1: Allow use of (almost) all events by all users >= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK >= 1: Disallow CPU event access by users without CAP_SYS_ADMIN >= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN [acme@jouet linux]$ After: [acme@jouet linux]$ perf record usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.016 MB perf.data (7 samples) ] [acme@jouet linux]$ perf evlist cycles:u [acme@jouet linux]$ perf evlist -v cycles:u: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, exclude_kernel: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 [acme@jouet linux]$ And if the user turns on verbose mode, an explanation will appear: [acme@jouet linux]$ perf record -v usleep 1 Warning: kernel.perf_event_paranoid=2, trying to fall back to excluding kernel samples mmap size 528384B [ perf record: Woken up 1 times to write data ] Looking at the vmlinux_path (8 entries long) Using /lib/modules/4.6.0-rc7+/build/vmlinux for symbols [ perf record: Captured and wrote 0.016 MB perf.data (7 samples) ] [acme@jouet linux]$ [1] 0161028b7c8a ("perf/core: Change the default paranoia level to 2") Reported-by: Ingo Molnar <mingo@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kees Cook <keescook@chromium.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-b20jmx4dxt5hpaa9t2rroi0o@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-05-12 19:07:47 +00:00
return true;
} else if (err == EACCES && !evsel->attr.exclude_kernel &&
(paranoid = perf_event_paranoid()) > 1) {
const char *name = perf_evsel__name(evsel);
char *new_name;
const char *sep = ":";
perf evsel: Handle EACCESS + perf_event_paranoid=2 in fallback() Now with the default for the kernel.perf_event_paranoid sysctl being 2 [1] we need to fall back to :u, i.e. to set perf_event_attr.exclude_kernel to 1. Before: [acme@jouet linux]$ perf record usleep 1 Error: You may not have permission to collect stats. Consider tweaking /proc/sys/kernel/perf_event_paranoid, which controls use of the performance events system by unprivileged users (without CAP_SYS_ADMIN). The current value is 2: -1: Allow use of (almost) all events by all users >= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK >= 1: Disallow CPU event access by users without CAP_SYS_ADMIN >= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN [acme@jouet linux]$ After: [acme@jouet linux]$ perf record usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.016 MB perf.data (7 samples) ] [acme@jouet linux]$ perf evlist cycles:u [acme@jouet linux]$ perf evlist -v cycles:u: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, exclude_kernel: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 [acme@jouet linux]$ And if the user turns on verbose mode, an explanation will appear: [acme@jouet linux]$ perf record -v usleep 1 Warning: kernel.perf_event_paranoid=2, trying to fall back to excluding kernel samples mmap size 528384B [ perf record: Woken up 1 times to write data ] Looking at the vmlinux_path (8 entries long) Using /lib/modules/4.6.0-rc7+/build/vmlinux for symbols [ perf record: Captured and wrote 0.016 MB perf.data (7 samples) ] [acme@jouet linux]$ [1] 0161028b7c8a ("perf/core: Change the default paranoia level to 2") Reported-by: Ingo Molnar <mingo@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kees Cook <keescook@chromium.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-b20jmx4dxt5hpaa9t2rroi0o@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-05-12 19:07:47 +00:00
/* Is there already the separator in the name. */
if (strchr(name, '/') ||
strchr(name, ':'))
sep = "";
if (asprintf(&new_name, "%s%su", name, sep) < 0)
perf evsel: Handle EACCESS + perf_event_paranoid=2 in fallback() Now with the default for the kernel.perf_event_paranoid sysctl being 2 [1] we need to fall back to :u, i.e. to set perf_event_attr.exclude_kernel to 1. Before: [acme@jouet linux]$ perf record usleep 1 Error: You may not have permission to collect stats. Consider tweaking /proc/sys/kernel/perf_event_paranoid, which controls use of the performance events system by unprivileged users (without CAP_SYS_ADMIN). The current value is 2: -1: Allow use of (almost) all events by all users >= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK >= 1: Disallow CPU event access by users without CAP_SYS_ADMIN >= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN [acme@jouet linux]$ After: [acme@jouet linux]$ perf record usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.016 MB perf.data (7 samples) ] [acme@jouet linux]$ perf evlist cycles:u [acme@jouet linux]$ perf evlist -v cycles:u: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, exclude_kernel: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 [acme@jouet linux]$ And if the user turns on verbose mode, an explanation will appear: [acme@jouet linux]$ perf record -v usleep 1 Warning: kernel.perf_event_paranoid=2, trying to fall back to excluding kernel samples mmap size 528384B [ perf record: Woken up 1 times to write data ] Looking at the vmlinux_path (8 entries long) Using /lib/modules/4.6.0-rc7+/build/vmlinux for symbols [ perf record: Captured and wrote 0.016 MB perf.data (7 samples) ] [acme@jouet linux]$ [1] 0161028b7c8a ("perf/core: Change the default paranoia level to 2") Reported-by: Ingo Molnar <mingo@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kees Cook <keescook@chromium.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-b20jmx4dxt5hpaa9t2rroi0o@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-05-12 19:07:47 +00:00
return false;
if (evsel->name)
free(evsel->name);
evsel->name = new_name;
scnprintf(msg, msgsize,
"kernel.perf_event_paranoid=%d, trying to fall back to excluding kernel samples", paranoid);
evsel->attr.exclude_kernel = 1;
return true;
}
return false;
}
static bool find_process(const char *name)
{
size_t len = strlen(name);
DIR *dir;
struct dirent *d;
int ret = -1;
dir = opendir(procfs__mountpoint());
if (!dir)
return false;
/* Walk through the directory. */
while (ret && (d = readdir(dir)) != NULL) {
char path[PATH_MAX];
char *data;
size_t size;
if ((d->d_type != DT_DIR) ||
!strcmp(".", d->d_name) ||
!strcmp("..", d->d_name))
continue;
scnprintf(path, sizeof(path), "%s/%s/comm",
procfs__mountpoint(), d->d_name);
if (filename__read_str(path, &data, &size))
continue;
ret = strncmp(name, data, len);
free(data);
}
closedir(dir);
return ret ? false : true;
}
int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
int err, char *msg, size_t size)
{
char sbuf[STRERR_BUFSIZE];
perf evsel: Return exact sub event which failed with EPERM for wildcards The kernel has a special check for a specific irq_vectors trace event. TRACE_EVENT_PERF_PERM(irq_work_exit, is_sampling_event(p_event) ? -EPERM : 0); The perf-record fails for this irq_vectors event when it is present, like when using a wildcard: root@skl:/tmp# perf record -a -e irq_vectors:* sleep 2 Error: You may not have permission to collect system-wide stats. Consider tweaking /proc/sys/kernel/perf_event_paranoid, which controls use of the performance events system by unprivileged users (without CAP_SYS_ADMIN). The current value is 2: -1: Allow use of (almost) all events by all users >= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK >= 1: Disallow CPU event access by users without CAP_SYS_ADMIN >= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN To make this setting permanent, edit /etc/sysctl.conf too, e.g.: kernel.perf_event_paranoid = -1 This patch prints out the exact sub event that failed with EPERM for wildcards to help in understanding what went wrong when this event is present: After the patch: root@skl:/tmp# perf record -a -e irq_vectors:* sleep 2 Error: No permission to enable irq_vectors:irq_work_exit event. You may not have permission to collect system-wide stats. ...... Committer notes: So we have a lot of irq_vectors events: [root@jouet ~]# perf list irq_vectors:* List of pre-defined events (to be used in -e): irq_vectors:call_function_entry [Tracepoint event] irq_vectors:call_function_exit [Tracepoint event] irq_vectors:call_function_single_entry [Tracepoint event] irq_vectors:call_function_single_exit [Tracepoint event] irq_vectors:deferred_error_apic_entry [Tracepoint event] irq_vectors:deferred_error_apic_exit [Tracepoint event] irq_vectors:error_apic_entry [Tracepoint event] irq_vectors:error_apic_exit [Tracepoint event] irq_vectors:irq_work_entry [Tracepoint event] irq_vectors:irq_work_exit [Tracepoint event] irq_vectors:local_timer_entry [Tracepoint event] irq_vectors:local_timer_exit [Tracepoint event] irq_vectors:reschedule_entry [Tracepoint event] irq_vectors:reschedule_exit [Tracepoint event] irq_vectors:spurious_apic_entry [Tracepoint event] irq_vectors:spurious_apic_exit [Tracepoint event] irq_vectors:thermal_apic_entry [Tracepoint event] irq_vectors:thermal_apic_exit [Tracepoint event] irq_vectors:threshold_apic_entry [Tracepoint event] irq_vectors:threshold_apic_exit [Tracepoint event] irq_vectors:x86_platform_ipi_entry [Tracepoint event] irq_vectors:x86_platform_ipi_exit [Tracepoint event] # And some may be sampled: [root@jouet ~]# perf record -e irq_vectors:local* sleep 20s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.020 MB perf.data (2 samples) ] [root@jouet ~]# perf report -D | egrep 'stats:|events:' Aggregated stats: TOTAL events: 155 MMAP events: 144 COMM events: 2 EXIT events: 1 SAMPLE events: 2 MMAP2 events: 4 FINISHED_ROUND events: 1 TIME_CONV events: 1 irq_vectors:local_timer_entry stats: TOTAL events: 1 SAMPLE events: 1 irq_vectors:local_timer_exit stats: TOTAL events: 1 SAMPLE events: 1 [root@jouet ~]# But, as shown in the tracepoint definition at the start of this message, some, like "irq_vectors:irq_work_exit", may not be sampled, just counted, i.e. if we try to sample, as when using 'perf record', we get an error: [root@jouet ~]# perf record -e irq_vectors:irq_work_exit Error: You may not have permission to collect system-wide stats. Consider tweaking /proc/sys/kernel/perf_event_paranoid, <SNIP> The error message is misleading, this patch will help in pointing out what is the event causing such an error, but the error message needs improvement, i.e. we need to figure out a way to check if a tracepoint is counting only, like this one, when all we can do is to count it with 'perf stat', at most printing the delta using interval printing, as in: [root@jouet ~]# perf stat -I 5000 -e irq_vectors:irq_work_* # time counts unit events 5.000168871 0 irq_vectors:irq_work_entry 5.000168871 0 irq_vectors:irq_work_exit 10.000676730 0 irq_vectors:irq_work_entry 10.000676730 0 irq_vectors:irq_work_exit 15.001122415 0 irq_vectors:irq_work_entry 15.001122415 0 irq_vectors:irq_work_exit 20.001298051 0 irq_vectors:irq_work_entry 20.001298051 0 irq_vectors:irq_work_exit 25.001485020 1 irq_vectors:irq_work_entry 25.001485020 1 irq_vectors:irq_work_exit 30.001658706 0 irq_vectors:irq_work_entry 30.001658706 0 irq_vectors:irq_work_exit ^C 32.045711878 0 irq_vectors:irq_work_entry 32.045711878 0 irq_vectors:irq_work_exit [root@jouet ~]# But at least, when we use a wildcard, this patch helps a bit. Signed-off-by: Yao Jin <yao.jin@linux.intel.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: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1491566932-503-1-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-04-07 12:08:52 +00:00
int printed = 0;
switch (err) {
case EPERM:
case EACCES:
perf evsel: Return exact sub event which failed with EPERM for wildcards The kernel has a special check for a specific irq_vectors trace event. TRACE_EVENT_PERF_PERM(irq_work_exit, is_sampling_event(p_event) ? -EPERM : 0); The perf-record fails for this irq_vectors event when it is present, like when using a wildcard: root@skl:/tmp# perf record -a -e irq_vectors:* sleep 2 Error: You may not have permission to collect system-wide stats. Consider tweaking /proc/sys/kernel/perf_event_paranoid, which controls use of the performance events system by unprivileged users (without CAP_SYS_ADMIN). The current value is 2: -1: Allow use of (almost) all events by all users >= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK >= 1: Disallow CPU event access by users without CAP_SYS_ADMIN >= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN To make this setting permanent, edit /etc/sysctl.conf too, e.g.: kernel.perf_event_paranoid = -1 This patch prints out the exact sub event that failed with EPERM for wildcards to help in understanding what went wrong when this event is present: After the patch: root@skl:/tmp# perf record -a -e irq_vectors:* sleep 2 Error: No permission to enable irq_vectors:irq_work_exit event. You may not have permission to collect system-wide stats. ...... Committer notes: So we have a lot of irq_vectors events: [root@jouet ~]# perf list irq_vectors:* List of pre-defined events (to be used in -e): irq_vectors:call_function_entry [Tracepoint event] irq_vectors:call_function_exit [Tracepoint event] irq_vectors:call_function_single_entry [Tracepoint event] irq_vectors:call_function_single_exit [Tracepoint event] irq_vectors:deferred_error_apic_entry [Tracepoint event] irq_vectors:deferred_error_apic_exit [Tracepoint event] irq_vectors:error_apic_entry [Tracepoint event] irq_vectors:error_apic_exit [Tracepoint event] irq_vectors:irq_work_entry [Tracepoint event] irq_vectors:irq_work_exit [Tracepoint event] irq_vectors:local_timer_entry [Tracepoint event] irq_vectors:local_timer_exit [Tracepoint event] irq_vectors:reschedule_entry [Tracepoint event] irq_vectors:reschedule_exit [Tracepoint event] irq_vectors:spurious_apic_entry [Tracepoint event] irq_vectors:spurious_apic_exit [Tracepoint event] irq_vectors:thermal_apic_entry [Tracepoint event] irq_vectors:thermal_apic_exit [Tracepoint event] irq_vectors:threshold_apic_entry [Tracepoint event] irq_vectors:threshold_apic_exit [Tracepoint event] irq_vectors:x86_platform_ipi_entry [Tracepoint event] irq_vectors:x86_platform_ipi_exit [Tracepoint event] # And some may be sampled: [root@jouet ~]# perf record -e irq_vectors:local* sleep 20s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.020 MB perf.data (2 samples) ] [root@jouet ~]# perf report -D | egrep 'stats:|events:' Aggregated stats: TOTAL events: 155 MMAP events: 144 COMM events: 2 EXIT events: 1 SAMPLE events: 2 MMAP2 events: 4 FINISHED_ROUND events: 1 TIME_CONV events: 1 irq_vectors:local_timer_entry stats: TOTAL events: 1 SAMPLE events: 1 irq_vectors:local_timer_exit stats: TOTAL events: 1 SAMPLE events: 1 [root@jouet ~]# But, as shown in the tracepoint definition at the start of this message, some, like "irq_vectors:irq_work_exit", may not be sampled, just counted, i.e. if we try to sample, as when using 'perf record', we get an error: [root@jouet ~]# perf record -e irq_vectors:irq_work_exit Error: You may not have permission to collect system-wide stats. Consider tweaking /proc/sys/kernel/perf_event_paranoid, <SNIP> The error message is misleading, this patch will help in pointing out what is the event causing such an error, but the error message needs improvement, i.e. we need to figure out a way to check if a tracepoint is counting only, like this one, when all we can do is to count it with 'perf stat', at most printing the delta using interval printing, as in: [root@jouet ~]# perf stat -I 5000 -e irq_vectors:irq_work_* # time counts unit events 5.000168871 0 irq_vectors:irq_work_entry 5.000168871 0 irq_vectors:irq_work_exit 10.000676730 0 irq_vectors:irq_work_entry 10.000676730 0 irq_vectors:irq_work_exit 15.001122415 0 irq_vectors:irq_work_entry 15.001122415 0 irq_vectors:irq_work_exit 20.001298051 0 irq_vectors:irq_work_entry 20.001298051 0 irq_vectors:irq_work_exit 25.001485020 1 irq_vectors:irq_work_entry 25.001485020 1 irq_vectors:irq_work_exit 30.001658706 0 irq_vectors:irq_work_entry 30.001658706 0 irq_vectors:irq_work_exit ^C 32.045711878 0 irq_vectors:irq_work_entry 32.045711878 0 irq_vectors:irq_work_exit [root@jouet ~]# But at least, when we use a wildcard, this patch helps a bit. Signed-off-by: Yao Jin <yao.jin@linux.intel.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: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1491566932-503-1-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-04-07 12:08:52 +00:00
if (err == EPERM)
printed = scnprintf(msg, size,
"No permission to enable %s event.\n\n",
perf_evsel__name(evsel));
return scnprintf(msg + printed, size - printed,
"You may not have permission to collect %sstats.\n\n"
"Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n"
"which controls use of the performance events system by\n"
"unprivileged users (without CAP_SYS_ADMIN).\n\n"
"The current value is %d:\n\n"
" -1: Allow use of (almost) all events by all users\n"
" Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK\n"
">= 0: Disallow ftrace function tracepoint by users without CAP_SYS_ADMIN\n"
" Disallow raw tracepoint access by users without CAP_SYS_ADMIN\n"
">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n"
">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN\n\n"
"To make this setting permanent, edit /etc/sysctl.conf too, e.g.:\n\n"
" kernel.perf_event_paranoid = -1\n" ,
target->system_wide ? "system-wide " : "",
perf_event_paranoid());
case ENOENT:
return scnprintf(msg, size, "The %s event is not supported.",
perf_evsel__name(evsel));
case EMFILE:
return scnprintf(msg, size, "%s",
"Too many events are opened.\n"
"Probably the maximum number of open file descriptors has been reached.\n"
"Hint: Try again after reducing the number of events.\n"
"Hint: Try increasing the limit with 'ulimit -n <limit>'");
case ENOMEM:
if (evsel__has_callchain(evsel) &&
access("/proc/sys/kernel/perf_event_max_stack", F_OK) == 0)
return scnprintf(msg, size,
"Not enough memory to setup event with callchain.\n"
"Hint: Try tweaking /proc/sys/kernel/perf_event_max_stack\n"
"Hint: Current value: %d", sysctl__max_stack());
break;
case ENODEV:
if (target->cpu_list)
return scnprintf(msg, size, "%s",
"No such device - did you specify an out-of-range profile CPU?");
break;
case EOPNOTSUPP:
if (evsel->attr.sample_period != 0)
return scnprintf(msg, size,
"%s: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat'",
perf_evsel__name(evsel));
if (evsel->attr.precise_ip)
return scnprintf(msg, size, "%s",
"\'precise\' request may not be supported. Try removing 'p' modifier.");
#if defined(__i386__) || defined(__x86_64__)
if (evsel->attr.type == PERF_TYPE_HARDWARE)
return scnprintf(msg, size, "%s",
"No hardware sampling interrupt available.\n");
#endif
break;
perf tools: Show better error message in case we fail to open counters due to EBUSY error Showing better error message in case we fail to open counters due to the EBUSY error. If we detect oprofile daemon process running, we now display following message for EBUSY error: $ perf record ls Error: The PMU counters are busy/taken by another profiler. We found oprofile daemon running, please stop it and try again. In case oprofiled was not detected the current error message stays: $ perf record ls Error: The sys_perf_event_open() syscall returned with 16 (Device or resource busy) for event (cycles). /bin/dmesg may provide additional information. No CONFIG_PERF_EVENTS=y kernel support configured? Also changing PERF_FLAG_FD_CLOEXEC detection code not to display error in case of EBUSY error, as it currently does: $ perf record ls Error: perf_event_open(..., PERF_FLAG_FD_CLOEXEC) failed with unexpected error 16 (Device or resource busy) perf_event_open(..., 0) failed unexpectedly with error 16 (Device or resource busy) The PMU counters are busy/taken by another profiler. We found oprofile daemon running, please stop it and try again. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: William Cohen <wcohen@redhat.com> Cc: Yann Droneaud <ydroneaud@opteya.com> Link: http://lkml.kernel.org/r/1406908014-8312-1-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-08-01 15:46:54 +00:00
case EBUSY:
if (find_process("oprofiled"))
return scnprintf(msg, size,
"The PMU counters are busy/taken by another profiler.\n"
"We found oprofile daemon running, please stop it and try again.");
break;
case EINVAL:
if (evsel->attr.write_backward && perf_missing_features.write_backward)
return scnprintf(msg, size, "Reading from overwrite event is not supported by this kernel.");
if (perf_missing_features.clockid)
return scnprintf(msg, size, "clockid feature not supported.");
if (perf_missing_features.clockid_wrong)
return scnprintf(msg, size, "wrong clockid (%d).", clockid);
break;
default:
break;
}
return scnprintf(msg, size,
"The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n"
"/bin/dmesg | grep -i perf may provide additional information.\n",
err, str_error_r(err, sbuf, sizeof(sbuf)),
perf_evsel__name(evsel));
}
struct perf_env *perf_evsel__env(struct perf_evsel *evsel)
perf annotate: Check for fused instructions Macro fusion merges two instructions to a single micro-op. Intel core platform performs this hardware optimization under limited circumstances. For example, CMP + JCC can be "fused" and executed /retired together. While with sampling this can result in the sample sometimes being on the JCC and sometimes on the CMP. So for the fused instruction pair, they could be considered together. On Nehalem, fused instruction pairs: cmp/test + jcc. On other new CPU: cmp/test/add/sub/and/inc/dec + jcc. This patch adds an x86-specific function which checks if 2 instructions are in a "fused" pair. For non-x86 arch, the function is just NULL. Changelog: v4: Move the CPU model checking to symbol__disassemble and save the CPU family/model in arch structure. It avoids checking every time when jump arrow printed. v3: Add checking for Nehalem (CMP, TEST). For other newer Intel CPUs just check it by default (CMP, TEST, ADD, SUB, AND, INC, DEC). v2: Remove the original weak function. Arnaldo points out that doing it as a weak function that will be overridden by the host arch doesn't work. So now it's implemented as an arch-specific function. Committer fix: Do not access evsel->evlist->env->cpuid, ->env can be null, introduce perf_evsel__env_cpuid(), just like perf_evsel__env_arch(), also used in this function call. The original patch was segfaulting 'perf top' + annotation. But this essentially disables this fused instructions augmentation in 'perf top', the right thing is to get the cpuid from the running kernel, left for a later patch tho. Signed-off-by: Yao Jin <yao.jin@linux.intel.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: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1499403995-19857-2-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-07-07 05:06:34 +00:00
{
if (evsel && evsel->evlist)
return evsel->evlist->env;
perf annotate: Check for fused instructions Macro fusion merges two instructions to a single micro-op. Intel core platform performs this hardware optimization under limited circumstances. For example, CMP + JCC can be "fused" and executed /retired together. While with sampling this can result in the sample sometimes being on the JCC and sometimes on the CMP. So for the fused instruction pair, they could be considered together. On Nehalem, fused instruction pairs: cmp/test + jcc. On other new CPU: cmp/test/add/sub/and/inc/dec + jcc. This patch adds an x86-specific function which checks if 2 instructions are in a "fused" pair. For non-x86 arch, the function is just NULL. Changelog: v4: Move the CPU model checking to symbol__disassemble and save the CPU family/model in arch structure. It avoids checking every time when jump arrow printed. v3: Add checking for Nehalem (CMP, TEST). For other newer Intel CPUs just check it by default (CMP, TEST, ADD, SUB, AND, INC, DEC). v2: Remove the original weak function. Arnaldo points out that doing it as a weak function that will be overridden by the host arch doesn't work. So now it's implemented as an arch-specific function. Committer fix: Do not access evsel->evlist->env->cpuid, ->env can be null, introduce perf_evsel__env_cpuid(), just like perf_evsel__env_arch(), also used in this function call. The original patch was segfaulting 'perf top' + annotation. But this essentially disables this fused instructions augmentation in 'perf top', the right thing is to get the cpuid from the running kernel, left for a later patch tho. Signed-off-by: Yao Jin <yao.jin@linux.intel.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: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1499403995-19857-2-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-07-07 05:06:34 +00:00
return NULL;
}
static int store_evsel_ids(struct perf_evsel *evsel, struct perf_evlist *evlist)
{
int cpu, thread;
for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
for (thread = 0; thread < xyarray__max_y(evsel->fd);
thread++) {
int fd = FD(evsel, cpu, thread);
if (perf_evlist__id_add_fd(evlist, evsel,
cpu, thread, fd) < 0)
return -1;
}
}
return 0;
}
int perf_evsel__store_ids(struct perf_evsel *evsel, struct perf_evlist *evlist)
{
struct cpu_map *cpus = evsel->cpus;
struct thread_map *threads = evsel->threads;
if (perf_evsel__alloc_id(evsel, cpus->nr, threads->nr))
return -ENOMEM;
return store_evsel_ids(evsel, evlist);
}