summaryrefslogtreecommitdiff
path: root/tools/perf
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf')
-rw-r--r--tools/perf/.gitignore1
-rw-r--r--tools/perf/Documentation/perf-bench.txt4
-rw-r--r--tools/perf/Documentation/perf-inject.txt3
-rw-r--r--tools/perf/Documentation/perf-kvm.txt16
-rw-r--r--tools/perf/Documentation/perf-probe.txt3
-rw-r--r--tools/perf/Documentation/perf-report.txt5
-rw-r--r--tools/perf/Documentation/perf-timechart.txt38
-rw-r--r--tools/perf/Documentation/perf-top.txt9
-rw-r--r--tools/perf/Documentation/perf-trace.txt46
-rw-r--r--tools/perf/Documentation/perf.txt10
-rw-r--r--tools/perf/MANIFEST3
-rw-r--r--tools/perf/Makefile.perf15
-rw-r--r--tools/perf/arch/arm/tests/dwarf-unwind.c1
-rw-r--r--tools/perf/arch/arm/util/unwind-libunwind.c1
-rw-r--r--tools/perf/arch/arm64/include/perf_regs.h2
-rw-r--r--tools/perf/arch/arm64/util/unwind-libunwind.c1
-rw-r--r--tools/perf/arch/common.c9
-rw-r--r--tools/perf/arch/powerpc/Makefile1
-rw-r--r--tools/perf/arch/powerpc/util/header.c4
-rw-r--r--tools/perf/arch/powerpc/util/skip-callchain-idx.c267
-rw-r--r--tools/perf/arch/s390/Makefile3
-rw-r--r--tools/perf/arch/s390/util/header.c28
-rw-r--r--tools/perf/arch/s390/util/kvm-stat.c105
-rw-r--r--tools/perf/arch/x86/Makefile2
-rw-r--r--tools/perf/arch/x86/tests/dwarf-unwind.c1
-rw-r--r--tools/perf/arch/x86/util/kvm-stat.c156
-rw-r--r--tools/perf/arch/x86/util/tsc.c31
-rw-r--r--tools/perf/arch/x86/util/tsc.h3
-rw-r--r--tools/perf/arch/x86/util/unwind-libunwind.c1
-rw-r--r--tools/perf/bench/bench.h1
-rw-r--r--tools/perf/bench/futex-hash.c7
-rw-r--r--tools/perf/bench/futex-requeue.c38
-rw-r--r--tools/perf/bench/futex-wake.c25
-rw-r--r--tools/perf/bench/mem-memcpy.c9
-rw-r--r--tools/perf/bench/mem-memset.c9
-rw-r--r--tools/perf/bench/sched-messaging.c49
-rw-r--r--tools/perf/builtin-annotate.c77
-rw-r--r--tools/perf/builtin-bench.c7
-rw-r--r--tools/perf/builtin-buildid-cache.c52
-rw-r--r--tools/perf/builtin-diff.c6
-rw-r--r--tools/perf/builtin-evlist.c3
-rw-r--r--tools/perf/builtin-help.c21
-rw-r--r--tools/perf/builtin-inject.c38
-rw-r--r--tools/perf/builtin-kmem.c56
-rw-r--r--tools/perf/builtin-kvm.c512
-rw-r--r--tools/perf/builtin-lock.c7
-rw-r--r--tools/perf/builtin-mem.c6
-rw-r--r--tools/perf/builtin-probe.c10
-rw-r--r--tools/perf/builtin-record.c153
-rw-r--r--tools/perf/builtin-report.c23
-rw-r--r--tools/perf/builtin-sched.c25
-rw-r--r--tools/perf/builtin-script.c134
-rw-r--r--tools/perf/builtin-stat.c13
-rw-r--r--tools/perf/builtin-timechart.c702
-rw-r--r--tools/perf/builtin-top.c87
-rw-r--r--tools/perf/builtin-trace.c323
-rw-r--r--tools/perf/config/Makefile58
-rw-r--r--tools/perf/config/feature-checks/Makefile22
-rw-r--r--tools/perf/config/feature-checks/test-all.c5
-rw-r--r--tools/perf/config/feature-checks/test-sync-compare-and-swap.c14
-rw-r--r--tools/perf/config/utilities.mak2
-rw-r--r--tools/perf/perf-sys.h1
-rw-r--r--tools/perf/perf-with-kcore.sh259
-rw-r--r--tools/perf/perf.c23
-rw-r--r--tools/perf/perf.h3
-rw-r--r--tools/perf/scripts/perl/bin/failed-syscalls-record3
-rw-r--r--tools/perf/scripts/perl/failed-syscalls.pl5
-rw-r--r--tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py3
-rw-r--r--tools/perf/scripts/python/bin/failed-syscalls-by-pid-record3
-rw-r--r--tools/perf/scripts/python/bin/sctop-record3
-rw-r--r--tools/perf/scripts/python/bin/syscall-counts-by-pid-record3
-rw-r--r--tools/perf/scripts/python/bin/syscall-counts-record3
-rw-r--r--tools/perf/scripts/python/check-perf-trace.py4
-rw-r--r--tools/perf/scripts/python/failed-syscalls-by-pid.py7
-rw-r--r--tools/perf/scripts/python/futex-contention.py4
-rwxr-xr-xtools/perf/scripts/python/net_dropmonitor.py2
-rw-r--r--tools/perf/scripts/python/netdev-times.py26
-rw-r--r--tools/perf/scripts/python/sched-migration.py41
-rw-r--r--tools/perf/scripts/python/sctop.py7
-rw-r--r--tools/perf/scripts/python/syscall-counts-by-pid.py7
-rw-r--r--tools/perf/scripts/python/syscall-counts.py7
-rw-r--r--tools/perf/tests/attr/base-record3
-rw-r--r--tools/perf/tests/attr/base-stat3
-rw-r--r--tools/perf/tests/bp_signal.c4
-rw-r--r--tools/perf/tests/bp_signal_overflow.c4
-rw-r--r--tools/perf/tests/builtin-test.c18
-rw-r--r--tools/perf/tests/dso-data.c1
-rw-r--r--tools/perf/tests/evsel-roundtrip-name.c1
-rw-r--r--tools/perf/tests/evsel-tp-sched.c1
-rw-r--r--tools/perf/tests/fdarray.c174
-rw-r--r--tools/perf/tests/mmap-basic.c7
-rw-r--r--tools/perf/tests/open-syscall-all-cpus.c5
-rw-r--r--tools/perf/tests/open-syscall-tp-fields.c10
-rw-r--r--tools/perf/tests/open-syscall.c3
-rw-r--r--tools/perf/tests/parse-events.c1
-rw-r--r--tools/perf/tests/parse-no-sample-id-all.c1
-rw-r--r--tools/perf/tests/perf-record.c15
-rw-r--r--tools/perf/tests/perf-time-to-tsc.c12
-rw-r--r--tools/perf/tests/pmu.c2
-rw-r--r--tools/perf/tests/rdpmc.c10
-rw-r--r--tools/perf/tests/sample-parsing.c1
-rw-r--r--tools/perf/tests/sw-clock.c6
-rw-r--r--tools/perf/tests/switch-tracking.c572
-rw-r--r--tools/perf/tests/task-exit.c8
-rw-r--r--tools/perf/tests/tests.h3
-rw-r--r--tools/perf/tests/thread-mg-share.c1
-rw-r--r--tools/perf/ui/browser.c39
-rw-r--r--tools/perf/ui/browser.h3
-rw-r--r--tools/perf/ui/browsers/hists.c519
-rw-r--r--tools/perf/ui/gtk/hists.c18
-rw-r--r--tools/perf/ui/hist.c284
-rw-r--r--tools/perf/ui/stdio/hist.c6
-rw-r--r--tools/perf/util/annotate.c21
-rw-r--r--tools/perf/util/cache.h1
-rw-r--r--tools/perf/util/callchain.c242
-rw-r--r--tools/perf/util/callchain.h19
-rw-r--r--tools/perf/util/cloexec.c74
-rw-r--r--tools/perf/util/cloexec.h6
-rw-r--r--tools/perf/util/color.c16
-rw-r--r--tools/perf/util/color.h1
-rw-r--r--tools/perf/util/comm.c7
-rw-r--r--tools/perf/util/comm.h6
-rw-r--r--tools/perf/util/config.c53
-rw-r--r--tools/perf/util/data.c11
-rw-r--r--tools/perf/util/debug.c90
-rw-r--r--tools/perf/util/debug.h33
-rw-r--r--tools/perf/util/dso.c192
-rw-r--r--tools/perf/util/dso.h42
-rw-r--r--tools/perf/util/event.c66
-rw-r--r--tools/perf/util/event.h12
-rw-r--r--tools/perf/util/evlist.c287
-rw-r--r--tools/perf/util/evlist.h21
-rw-r--r--tools/perf/util/evsel.c91
-rw-r--r--tools/perf/util/evsel.h4
-rw-r--r--tools/perf/util/header.c79
-rw-r--r--tools/perf/util/header.h2
-rw-r--r--tools/perf/util/hist.c22
-rw-r--r--tools/perf/util/hist.h18
-rw-r--r--tools/perf/util/include/linux/kernel.h21
-rw-r--r--tools/perf/util/kvm-stat.h139
-rw-r--r--tools/perf/util/machine.c235
-rw-r--r--tools/perf/util/machine.h34
-rw-r--r--tools/perf/util/map.c48
-rw-r--r--tools/perf/util/map.h15
-rw-r--r--tools/perf/util/ordered-events.c245
-rw-r--r--tools/perf/util/ordered-events.h51
-rw-r--r--tools/perf/util/parse-events.c29
-rw-r--r--tools/perf/util/parse-events.y10
-rw-r--r--tools/perf/util/parse-options.h5
-rw-r--r--tools/perf/util/pmu.c121
-rw-r--r--tools/perf/util/pmu.h25
-rw-r--r--tools/perf/util/probe-event.c181
-rw-r--r--tools/perf/util/probe-event.h3
-rw-r--r--tools/perf/util/probe-finder.c24
-rw-r--r--tools/perf/util/pstack.c1
-rw-r--r--tools/perf/util/python.c10
-rw-r--r--tools/perf/util/record.c57
-rw-r--r--tools/perf/util/run-command.c9
-rw-r--r--tools/perf/util/scripting-engines/trace-event-perl.c7
-rw-r--r--tools/perf/util/scripting-engines/trace-event-python.c301
-rw-r--r--tools/perf/util/session.c337
-rw-r--r--tools/perf/util/session.h35
-rw-r--r--tools/perf/util/sort.c119
-rw-r--r--tools/perf/util/sort.h1
-rw-r--r--tools/perf/util/string.c90
-rw-r--r--tools/perf/util/svghelper.c168
-rw-r--r--tools/perf/util/svghelper.h6
-rw-r--r--tools/perf/util/symbol-elf.c72
-rw-r--r--tools/perf/util/symbol-minimal.c43
-rw-r--r--tools/perf/util/symbol.c64
-rw-r--r--tools/perf/util/symbol.h23
-rw-r--r--tools/perf/util/thread.c37
-rw-r--r--tools/perf/util/thread.h11
-rw-r--r--tools/perf/util/tool.h2
-rw-r--r--tools/perf/util/trace-event-info.c13
-rw-r--r--tools/perf/util/trace-event-read.c2
-rw-r--r--tools/perf/util/trace-event-scripting.c7
-rw-r--r--tools/perf/util/trace-event.h1
-rw-r--r--tools/perf/util/tsc.c30
-rw-r--r--tools/perf/util/tsc.h12
-rw-r--r--tools/perf/util/unwind-libdw.c1
-rw-r--r--tools/perf/util/unwind-libunwind.c1
-rw-r--r--tools/perf/util/util.c64
-rw-r--r--tools/perf/util/util.h23
-rw-r--r--tools/perf/util/vdso.c97
-rw-r--r--tools/perf/util/vdso.h13
186 files changed, 7342 insertions, 2329 deletions
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index 782d86e961b9..717221e98450 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -15,6 +15,7 @@ perf.data
perf.data.old
output.svg
perf-archive
+perf-with-kcore
tags
TAGS
cscope*
diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index 4464ad770d51..f6480cbf309b 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -16,6 +16,10 @@ This 'perf bench' command is a general framework for benchmark suites.
COMMON OPTIONS
--------------
+-r::
+--repeat=::
+Specify amount of times to repeat the run (default 10).
+
-f::
--format=::
Specify format style.
diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt
index a00a34276c54..dc7442cf3d7f 100644
--- a/tools/perf/Documentation/perf-inject.txt
+++ b/tools/perf/Documentation/perf-inject.txt
@@ -41,6 +41,9 @@ OPTIONS
tasks slept. sched_switch contains a callchain where a task slept and
sched_stat contains a timeslice how long a task slept.
+--kallsyms=<file>::
+ kallsyms pathname
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1]
diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
index 52276a6d2b75..6e689dc89a2f 100644
--- a/tools/perf/Documentation/perf-kvm.txt
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -51,9 +51,9 @@ There are a couple of variants of perf kvm:
'perf kvm stat <command>' to run a command and gather performance counter
statistics.
Especially, perf 'kvm stat record/report' generates a statistical analysis
- of KVM events. Currently, vmexit, mmio and ioport events are supported.
- 'perf kvm stat record <command>' records kvm events and the events between
- start and end <command>.
+ of KVM events. Currently, vmexit, mmio (x86 only) and ioport (x86 only)
+ events are supported. 'perf kvm stat record <command>' records kvm events
+ and the events between start and end <command>.
And this command produces a file which contains tracing results of kvm
events.
@@ -103,8 +103,8 @@ STAT REPORT OPTIONS
analyze events which occures on this vcpu. (default: all vcpus)
--event=<value>::
- event to be analyzed. Possible values: vmexit, mmio, ioport.
- (default: vmexit)
+ event to be analyzed. Possible values: vmexit, mmio (x86 only),
+ ioport (x86 only). (default: vmexit)
-k::
--key=<value>::
Sorting key. Possible values: sample (default, sort by samples
@@ -138,7 +138,8 @@ STAT LIVE OPTIONS
--event=<value>::
- event to be analyzed. Possible values: vmexit, mmio, ioport.
+ event to be analyzed. Possible values: vmexit,
+ mmio (x86 only), ioport (x86 only).
(default: vmexit)
-k::
@@ -147,7 +148,8 @@ STAT LIVE OPTIONS
number), time (sort by average time).
--duration=<value>::
- Show events other than HLT that take longer than duration usecs.
+ Show events other than HLT (x86 only) or Wait state (s390 only)
+ that take longer than duration usecs.
SEE ALSO
--------
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 1513935c399b..aaa869be3dc1 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -104,6 +104,9 @@ OPTIONS
Specify path to the executable or shared library file for user
space tracing. Can also be used with --funcs option.
+--demangle-kernel::
+ Demangle kernel symbols.
+
In absence of -m/-x options, perf probe checks if the first argument after
the options is an absolute path name. If its an absolute path, perf probe
uses it as a target module/target user space binary to probe.
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index d2b59af62bc0..0927bf4e6c2a 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -147,7 +147,7 @@ OPTIONS
-w::
--column-widths=<width[,width...]>::
Force each column width to the provided list, for large terminal
- readability.
+ readability. 0 means no limit (default behavior).
-t::
--field-separator=::
@@ -276,6 +276,9 @@ OPTIONS
Demangle symbol names to human readable form. It's enabled by default,
disable with --no-demangle.
+--demangle-kernel::
+ Demangle kernel symbol names to human readable form (for C++ kernels).
+
--mem-mode::
Use the data addresses of samples in addition to instruction addresses
to build the histograms. To generate meaningful output, the perf.data
diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt
index 5e0f986dff38..df98d1c82688 100644
--- a/tools/perf/Documentation/perf-timechart.txt
+++ b/tools/perf/Documentation/perf-timechart.txt
@@ -15,10 +15,20 @@ DESCRIPTION
There are two variants of perf timechart:
'perf timechart record <command>' to record the system level events
- of an arbitrary workload.
+ of an arbitrary workload. By default timechart records only scheduler
+ and CPU events (task switches, running times, CPU power states, etc),
+ but it's possible to record IO (disk, network) activity using -I argument.
'perf timechart' to turn a trace into a Scalable Vector Graphics file,
- that can be viewed with popular SVG viewers such as 'Inkscape'.
+ that can be viewed with popular SVG viewers such as 'Inkscape'. Depending
+ on the events in the perf.data file, timechart will contain scheduler/cpu
+ events or IO events.
+
+ In IO mode, every bar has two charts: upper and lower.
+ Upper bar shows incoming events (disk reads, ingress network packets).
+ Lower bar shows outgoing events (disk writes, egress network packets).
+ There are also poll bars which show how much time application spent
+ in poll/epoll/select syscalls.
TIMECHART OPTIONS
-----------------
@@ -54,6 +64,19 @@ TIMECHART OPTIONS
duration or tasks with given name. If number is given it's interpreted
as number of nanoseconds. If non-numeric string is given it's
interpreted as task name.
+--io-skip-eagain::
+ Don't draw EAGAIN IO events.
+--io-min-time=<nsecs>::
+ Draw small events as if they lasted min-time. Useful when you need
+ to see very small and fast IO. It's possible to specify ms or us
+ suffix to specify time in milliseconds or microseconds.
+ Default value is 1ms.
+--io-merge-dist=<nsecs>::
+ Merge events that are merge-dist nanoseconds apart.
+ Reduces number of figures on the SVG and makes it more render-friendly.
+ It's possible to specify ms or us suffix to specify time in
+ milliseconds or microseconds.
+ Default value is 1us.
RECORD OPTIONS
--------------
@@ -63,6 +86,9 @@ RECORD OPTIONS
-T::
--tasks-only::
Record only tasks-related events
+-I::
+--io-only::
+ Record only io-related events
-g::
--callchain::
Do call-graph (stack chain/backtrace) recording
@@ -87,6 +113,14 @@ Record system-wide timechart:
$ perf timechart --highlight gcc
+Record system-wide IO events:
+
+ $ perf timechart record -I
+
+ then generate timechart:
+
+ $ perf timechart
+
SEE ALSO
--------
linkperf:perf-record[1]
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 180ae02137a5..3265b1070518 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -98,6 +98,9 @@ Default is to monitor all CPUS.
--hide_user_symbols::
Hide user symbols.
+--demangle-kernel::
+ Demangle kernel symbols.
+
-D::
--dump-symtab::
Dump the symbol table used for profiling.
@@ -193,6 +196,12 @@ Default is to monitor all CPUS.
sum of shown entries will be always 100%. "absolute" means it retains
the original value before and after the filter is applied.
+-w::
+--column-widths=<width[,width...]>::
+ Force each column width to the provided list, for large terminal
+ readability. 0 means no limit (default behavior).
+
+
INTERACTIVE PROMPTING KEYS
--------------------------
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index fae38d9a44a4..02aac831bdd9 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -107,6 +107,52 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
Show tool stats such as number of times fd->pathname was discovered thru
hooking the open syscall return + vfs_getname or via reading /proc/pid/fd, etc.
+-F=[all|min|maj]::
+--pf=[all|min|maj]::
+ Trace pagefaults. Optionally, you can specify whether you want minor,
+ major or all pagefaults. Default value is maj.
+
+--syscalls::
+ Trace system calls. This options is enabled by default.
+
+PAGEFAULTS
+----------
+
+When tracing pagefaults, the format of the trace is as follows:
+
+<min|maj>fault [<ip.symbol>+<ip.offset>] => <addr.dso@addr.offset> (<map type><addr level>).
+
+- min/maj indicates whether fault event is minor or major;
+- ip.symbol shows symbol for instruction pointer (the code that generated the
+ fault); if no debug symbols available, perf trace will print raw IP;
+- addr.dso shows DSO for the faulted address;
+- map type is either 'd' for non-executable maps or 'x' for executable maps;
+- addr level is either 'k' for kernel dso or '.' for user dso.
+
+For symbols resolution you may need to install debugging symbols.
+
+Please be aware that duration is currently always 0 and doesn't reflect actual
+time it took for fault to be handled!
+
+When --verbose specified, perf trace tries to print all available information
+for both IP and fault address in the form of dso@symbol+offset.
+
+EXAMPLES
+--------
+
+Trace only major pagefaults:
+
+ $ perf trace --no-syscalls -F
+
+Trace syscalls, major and minor pagefaults:
+
+ $ perf trace -F all
+
+ 1416.547 ( 0.000 ms): python/20235 majfault [CRYPTO_push_info_+0x0] => /lib/x86_64-linux-gnu/libcrypto.so.1.0.0@0x61be0 (x.)
+
+ As you can see, there was major pagefault in python process, from
+ CRYPTO_push_info_ routine which faulted somewhere in libcrypto.so.
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-script[1]
diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt
index 0eeb247dc7d2..d240bb2e5b22 100644
--- a/tools/perf/Documentation/perf.txt
+++ b/tools/perf/Documentation/perf.txt
@@ -8,7 +8,15 @@ perf - Performance analysis tools for Linux
SYNOPSIS
--------
[verse]
-'perf' [--version] [--help] COMMAND [ARGS]
+'perf' [--version] [--help] [OPTIONS] COMMAND [ARGS]
+
+OPTIONS
+-------
+--debug::
+ Setup debug variable (just verbose for now) in value
+ range (0, 10). Use like:
+ --debug verbose # sets verbose = 1
+ --debug verbose=2 # sets verbose = 2
DESCRIPTION
-----------
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 45da209b6ed3..344c4d3d0a4a 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -37,3 +37,6 @@ arch/x86/include/asm/kvm_host.h
arch/x86/include/uapi/asm/svm.h
arch/x86/include/uapi/asm/vmx.h
arch/x86/include/uapi/asm/kvm.h
+arch/x86/include/uapi/asm/kvm_perf.h
+arch/s390/include/uapi/asm/sie.h
+arch/s390/include/uapi/asm/kvm_perf.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 9670a16fa577..262916f4a377 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -126,6 +126,7 @@ PYRF_OBJS =
SCRIPT_SH =
SCRIPT_SH += perf-archive.sh
+SCRIPT_SH += perf-with-kcore.sh
grep-libs = $(filter -l%,$(1))
strip-libs = $(filter-out -l%,$(1))
@@ -263,6 +264,7 @@ LIB_H += util/xyarray.h
LIB_H += util/header.h
LIB_H += util/help.h
LIB_H += util/session.h
+LIB_H += util/ordered-events.h
LIB_H += util/strbuf.h
LIB_H += util/strlist.h
LIB_H += util/strfilter.h
@@ -295,11 +297,13 @@ LIB_H += util/intlist.h
LIB_H += util/perf_regs.h
LIB_H += util/unwind.h
LIB_H += util/vdso.h
+LIB_H += util/tsc.h
LIB_H += ui/helpline.h
LIB_H += ui/progress.h
LIB_H += ui/util.h
LIB_H += ui/ui.h
LIB_H += util/data.h
+LIB_H += util/kvm-stat.h
LIB_OBJS += $(OUTPUT)util/abspath.o
LIB_OBJS += $(OUTPUT)util/alias.o
@@ -345,6 +349,7 @@ LIB_OBJS += $(OUTPUT)util/machine.o
LIB_OBJS += $(OUTPUT)util/map.o
LIB_OBJS += $(OUTPUT)util/pstack.o
LIB_OBJS += $(OUTPUT)util/session.o
+LIB_OBJS += $(OUTPUT)util/ordered-events.o
LIB_OBJS += $(OUTPUT)util/comm.o
LIB_OBJS += $(OUTPUT)util/thread.o
LIB_OBJS += $(OUTPUT)util/thread_map.o
@@ -373,6 +378,8 @@ LIB_OBJS += $(OUTPUT)util/stat.o
LIB_OBJS += $(OUTPUT)util/record.o
LIB_OBJS += $(OUTPUT)util/srcline.o
LIB_OBJS += $(OUTPUT)util/data.o
+LIB_OBJS += $(OUTPUT)util/tsc.o
+LIB_OBJS += $(OUTPUT)util/cloexec.o
LIB_OBJS += $(OUTPUT)ui/setup.o
LIB_OBJS += $(OUTPUT)ui/helpline.o
@@ -395,6 +402,7 @@ LIB_OBJS += $(OUTPUT)tests/perf-record.o
LIB_OBJS += $(OUTPUT)tests/rdpmc.o
LIB_OBJS += $(OUTPUT)tests/evsel-roundtrip-name.o
LIB_OBJS += $(OUTPUT)tests/evsel-tp-sched.o
+LIB_OBJS += $(OUTPUT)tests/fdarray.o
LIB_OBJS += $(OUTPUT)tests/pmu.o
LIB_OBJS += $(OUTPUT)tests/hists_common.o
LIB_OBJS += $(OUTPUT)tests/hists_link.o
@@ -419,6 +427,7 @@ endif
endif
LIB_OBJS += $(OUTPUT)tests/mmap-thread-lookup.o
LIB_OBJS += $(OUTPUT)tests/thread-mg-share.o
+LIB_OBJS += $(OUTPUT)tests/switch-tracking.o
BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
@@ -761,7 +770,7 @@ $(LIBTRACEEVENT)-clean:
install-traceevent-plugins: $(LIBTRACEEVENT)
$(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) install_plugins
-LIBAPIKFS_SOURCES = $(wildcard $(LIB_PATH)fs/*.[ch])
+LIBAPIKFS_SOURCES = $(wildcard $(LIB_PATH)fs/*.[ch] $(LIB_PATH)fd/*.[ch])
# if subdir is set, we've been called from above so target has been built
# already
@@ -871,6 +880,8 @@ install-bin: all install-gtk
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
$(call QUIET_INSTALL, perf-archive) \
$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
+ $(call QUIET_INSTALL, perf-with-kcore) \
+ $(INSTALL) $(OUTPUT)perf-with-kcore -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
ifndef NO_LIBPERL
$(call QUIET_INSTALL, perl-scripts) \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \
@@ -916,7 +927,7 @@ config-clean:
@$(MAKE) -C config/feature-checks clean >/dev/null
clean: $(LIBTRACEEVENT)-clean $(LIBAPIKFS)-clean config-clean
- $(call QUIET_CLEAN, core-objs) $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS)
+ $(call QUIET_CLEAN, core-objs) $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS)
$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf
$(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)PERF-FEATURES $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
diff --git a/tools/perf/arch/arm/tests/dwarf-unwind.c b/tools/perf/arch/arm/tests/dwarf-unwind.c
index 9f870d27cb39..62eff847f91c 100644
--- a/tools/perf/arch/arm/tests/dwarf-unwind.c
+++ b/tools/perf/arch/arm/tests/dwarf-unwind.c
@@ -3,6 +3,7 @@
#include "thread.h"
#include "map.h"
#include "event.h"
+#include "debug.h"
#include "tests/tests.h"
#define STACK_SIZE 8192
diff --git a/tools/perf/arch/arm/util/unwind-libunwind.c b/tools/perf/arch/arm/util/unwind-libunwind.c
index 729ed69a6664..62c397ed3d97 100644
--- a/tools/perf/arch/arm/util/unwind-libunwind.c
+++ b/tools/perf/arch/arm/util/unwind-libunwind.c
@@ -3,6 +3,7 @@
#include <libunwind.h>
#include "perf_regs.h"
#include "../../util/unwind.h"
+#include "../../util/debug.h"
int libunwind__arch_reg_id(int regnum)
{
diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h
index e9441b9e2a30..1d3f39c3aa56 100644
--- a/tools/perf/arch/arm64/include/perf_regs.h
+++ b/tools/perf/arch/arm64/include/perf_regs.h
@@ -6,6 +6,8 @@
#include <asm/perf_regs.h>
#define PERF_REGS_MASK ((1ULL << PERF_REG_ARM64_MAX) - 1)
+#define PERF_REGS_MAX PERF_REG_ARM64_MAX
+
#define PERF_REG_IP PERF_REG_ARM64_PC
#define PERF_REG_SP PERF_REG_ARM64_SP
diff --git a/tools/perf/arch/arm64/util/unwind-libunwind.c b/tools/perf/arch/arm64/util/unwind-libunwind.c
index 436ee43859dc..a87afa91a99e 100644
--- a/tools/perf/arch/arm64/util/unwind-libunwind.c
+++ b/tools/perf/arch/arm64/util/unwind-libunwind.c
@@ -3,6 +3,7 @@
#include <libunwind.h>
#include "perf_regs.h"
#include "../../util/unwind.h"
+#include "../../util/debug.h"
int libunwind__arch_reg_id(int regnum)
{
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index 42faf369211c..49776f190abf 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -12,6 +12,11 @@ const char *const arm_triplets[] = {
NULL
};
+const char *const arm64_triplets[] = {
+ "aarch64-linux-android-",
+ NULL
+};
+
const char *const powerpc_triplets[] = {
"powerpc-unknown-linux-gnu-",
"powerpc64-unknown-linux-gnu-",
@@ -105,6 +110,8 @@ static const char *normalize_arch(char *arch)
return "x86";
if (!strcmp(arch, "sun4u") || !strncmp(arch, "sparc", 5))
return "sparc";
+ if (!strcmp(arch, "aarch64") || !strcmp(arch, "arm64"))
+ return "arm64";
if (!strncmp(arch, "arm", 3) || !strcmp(arch, "sa110"))
return "arm";
if (!strncmp(arch, "s390", 4))
@@ -159,6 +166,8 @@ static int perf_session_env__lookup_binutils_path(struct perf_session_env *env,
if (!strcmp(arch, "arm"))
path_list = arm_triplets;
+ else if (!strcmp(arch, "arm64"))
+ path_list = arm64_triplets;
else if (!strcmp(arch, "powerpc"))
path_list = powerpc_triplets;
else if (!strcmp(arch, "sh"))
diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index 744e629797be..6f7782bea5dd 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -1,5 +1,6 @@
ifndef NO_DWARF
PERF_HAVE_DWARF_REGS := 1
LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/skip-callchain-idx.o
endif
LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
index 2f7073d107fd..6c1b8a75db09 100644
--- a/tools/perf/arch/powerpc/util/header.c
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -5,9 +5,7 @@
#include <string.h>
#include "../../util/header.h"
-
-#define __stringify_1(x) #x
-#define __stringify(x) __stringify_1(x)
+#include "../../util/util.h"
#define mfspr(rn) ({unsigned long rval; \
asm volatile("mfspr %0," __stringify(rn) \
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
new file mode 100644
index 000000000000..d73ef8bb08c7
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -0,0 +1,267 @@
+/*
+ * Use DWARF Debug information to skip unnecessary callchain entries.
+ *
+ * Copyright (C) 2014 Sukadev Bhattiprolu, IBM Corporation.
+ * Copyright (C) 2014 Ulrich Weigand, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <inttypes.h>
+#include <dwarf.h>
+#include <elfutils/libdwfl.h>
+
+#include "util/thread.h"
+#include "util/callchain.h"
+#include "util/debug.h"
+
+/*
+ * When saving the callchain on Power, the kernel conservatively saves
+ * excess entries in the callchain. A few of these entries are needed
+ * in some cases but not others. If the unnecessary entries are not
+ * ignored, we end up with duplicate arcs in the call-graphs. Use
+ * DWARF debug information to skip over any unnecessary callchain
+ * entries.
+ *
+ * See function header for arch_adjust_callchain() below for more details.
+ *
+ * The libdwfl code in this file is based on code from elfutils
+ * (libdwfl/argp-std.c, libdwfl/tests/addrcfi.c, etc).
+ */
+static char *debuginfo_path;
+
+static const Dwfl_Callbacks offline_callbacks = {
+ .debuginfo_path = &debuginfo_path,
+ .find_debuginfo = dwfl_standard_find_debuginfo,
+ .section_address = dwfl_offline_section_address,
+};
+
+
+/*
+ * Use the DWARF expression for the Call-frame-address and determine
+ * if return address is in LR and if a new frame was allocated.
+ */
+static int check_return_reg(int ra_regno, Dwarf_Frame *frame)
+{
+ Dwarf_Op ops_mem[2];
+ Dwarf_Op dummy;
+ Dwarf_Op *ops = &dummy;
+ size_t nops;
+ int result;
+
+ result = dwarf_frame_register(frame, ra_regno, ops_mem, &ops, &nops);
+ if (result < 0) {
+ pr_debug("dwarf_frame_register() %s\n", dwarf_errmsg(-1));
+ return -1;
+ }
+
+ /*
+ * Check if return address is on the stack.
+ */
+ if (nops != 0 || ops != NULL)
+ return 0;
+
+ /*
+ * Return address is in LR. Check if a frame was allocated
+ * but not-yet used.
+ */
+ result = dwarf_frame_cfa(frame, &ops, &nops);
+ if (result < 0) {
+ pr_debug("dwarf_frame_cfa() returns %d, %s\n", result,
+ dwarf_errmsg(-1));
+ return -1;
+ }
+
+ /*
+ * If call frame address is in r1, no new frame was allocated.
+ */
+ if (nops == 1 && ops[0].atom == DW_OP_bregx && ops[0].number == 1 &&
+ ops[0].number2 == 0)
+ return 1;
+
+ /*
+ * A new frame was allocated but has not yet been used.
+ */
+ return 2;
+}
+
+/*
+ * Get the DWARF frame from the .eh_frame section.
+ */
+static Dwarf_Frame *get_eh_frame(Dwfl_Module *mod, Dwarf_Addr pc)
+{
+ int result;
+ Dwarf_Addr bias;
+ Dwarf_CFI *cfi;
+ Dwarf_Frame *frame;
+
+ cfi = dwfl_module_eh_cfi(mod, &bias);
+ if (!cfi) {
+ pr_debug("%s(): no CFI - %s\n", __func__, dwfl_errmsg(-1));
+ return NULL;
+ }
+
+ result = dwarf_cfi_addrframe(cfi, pc, &frame);
+ if (result) {
+ pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1));
+ return NULL;
+ }
+
+ return frame;
+}
+
+/*
+ * Get the DWARF frame from the .debug_frame section.
+ */
+static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc)
+{
+ Dwarf_CFI *cfi;
+ Dwarf_Addr bias;
+ Dwarf_Frame *frame;
+ int result;
+
+ cfi = dwfl_module_dwarf_cfi(mod, &bias);
+ if (!cfi) {
+ pr_debug("%s(): no CFI - %s\n", __func__, dwfl_errmsg(-1));
+ return NULL;
+ }
+
+ result = dwarf_cfi_addrframe(cfi, pc, &frame);
+ if (result) {
+ pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1));
+ return NULL;
+ }
+
+ return frame;
+}
+
+/*
+ * Return:
+ * 0 if return address for the program counter @pc is on stack
+ * 1 if return address is in LR and no new stack frame was allocated
+ * 2 if return address is in LR and a new frame was allocated (but not
+ * yet used)
+ * -1 in case of errors
+ */
+static int check_return_addr(const char *exec_file, Dwarf_Addr pc)
+{
+ int rc = -1;
+ Dwfl *dwfl;
+ Dwfl_Module *mod;
+ Dwarf_Frame *frame;
+ int ra_regno;
+ Dwarf_Addr start = pc;
+ Dwarf_Addr end = pc;
+ bool signalp;
+
+ dwfl = dwfl_begin(&offline_callbacks);
+ if (!dwfl) {
+ pr_debug("dwfl_begin() failed: %s\n", dwarf_errmsg(-1));
+ return -1;
+ }
+
+ if (dwfl_report_offline(dwfl, "", exec_file, -1) == NULL) {
+ pr_debug("dwfl_report_offline() failed %s\n", dwarf_errmsg(-1));
+ goto out;
+ }
+
+ mod = dwfl_addrmodule(dwfl, pc);
+ if (!mod) {
+ pr_debug("dwfl_addrmodule() failed, %s\n", dwarf_errmsg(-1));
+ goto out;
+ }
+
+ /*
+ * To work with split debug info files (eg: glibc), check both
+ * .eh_frame and .debug_frame sections of the ELF header.
+ */
+ frame = get_eh_frame(mod, pc);
+ if (!frame) {
+ frame = get_dwarf_frame(mod, pc);
+ if (!frame)
+ goto out;
+ }
+
+ ra_regno = dwarf_frame_info(frame, &start, &end, &signalp);
+ if (ra_regno < 0) {
+ pr_debug("Return address register unavailable: %s\n",
+ dwarf_errmsg(-1));
+ goto out;
+ }
+
+ rc = check_return_reg(ra_regno, frame);
+
+out:
+ dwfl_end(dwfl);
+ return rc;
+}
+
+/*
+ * The callchain saved by the kernel always includes the link register (LR).
+ *
+ * 0: PERF_CONTEXT_USER
+ * 1: Program counter (Next instruction pointer)
+ * 2: LR value
+ * 3: Caller's caller
+ * 4: ...
+ *
+ * The value in LR is only needed when it holds a return address. If the
+ * return address is on the stack, we should ignore the LR value.
+ *
+ * Further, when the return address is in the LR, if a new frame was just
+ * allocated but the LR was not saved into it, then the LR contains the
+ * caller, slot 4: contains the caller's caller and the contents of slot 3:
+ * (chain->ips[3]) is undefined and must be ignored.
+ *
+ * Use DWARF debug information to determine if any entries need to be skipped.
+ *
+ * Return:
+ * index: of callchain entry that needs to be ignored (if any)
+ * -1 if no entry needs to be ignored or in case of errors
+ */
+int arch_skip_callchain_idx(struct machine *machine, struct thread *thread,
+ struct ip_callchain *chain)
+{
+ struct addr_location al;
+ struct dso *dso = NULL;
+ int rc;
+ u64 ip;
+ u64 skip_slot = -1;
+
+ if (chain->nr < 3)
+ return skip_slot;
+
+ ip = chain->ips[2];
+
+ thread__find_addr_location(thread, machine, PERF_RECORD_MISC_USER,
+ MAP__FUNCTION, ip, &al);
+
+ if (al.map)
+ dso = al.map->dso;
+
+ if (!dso) {
+ pr_debug("%" PRIx64 " dso is NULL\n", ip);
+ return skip_slot;
+ }
+
+ rc = check_return_addr(dso->long_name, ip);
+
+ pr_debug("DSO %s, nr %" PRIx64 ", ip 0x%" PRIx64 "rc %d\n",
+ dso->long_name, chain->nr, ip, rc);
+
+ if (rc == 0) {
+ /*
+ * Return address on stack. Ignore LR value in callchain
+ */
+ skip_slot = 2;
+ } else if (rc == 2) {
+ /*
+ * New frame allocated but return address still in LR.
+ * Ignore the caller's caller entry in callchain.
+ */
+ skip_slot = 3;
+ }
+ return skip_slot;
+}
diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile
index 15130b50dfe3..798ac7379c5f 100644
--- a/tools/perf/arch/s390/Makefile
+++ b/tools/perf/arch/s390/Makefile
@@ -2,3 +2,6 @@ ifndef NO_DWARF
PERF_HAVE_DWARF_REGS := 1
LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
endif
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
+HAVE_KVM_STAT_SUPPORT := 1
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/kvm-stat.o
diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c
new file mode 100644
index 000000000000..9fa6c3e5782c
--- /dev/null
+++ b/tools/perf/arch/s390/util/header.c
@@ -0,0 +1,28 @@
+/*
+ * Implementation of get_cpuid().
+ *
+ * Copyright 2014 IBM Corp.
+ * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+
+#include <sys/types.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+
+#include "../../util/header.h"
+
+int get_cpuid(char *buffer, size_t sz)
+{
+ const char *cpuid = "IBM/S390";
+
+ if (strlen(cpuid) + 1 > sz)
+ return -1;
+
+ strcpy(buffer, cpuid);
+ return 0;
+}
diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c
new file mode 100644
index 000000000000..a5dbc07ec9dc
--- /dev/null
+++ b/tools/perf/arch/s390/util/kvm-stat.c
@@ -0,0 +1,105 @@
+/*
+ * Arch specific functions for perf kvm stat.
+ *
+ * Copyright 2014 IBM Corp.
+ * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+
+#include "../../util/kvm-stat.h"
+#include <asm/kvm_perf.h>
+
+define_exit_reasons_table(sie_exit_reasons, sie_intercept_code);
+define_exit_reasons_table(sie_icpt_insn_codes, icpt_insn_codes);
+define_exit_reasons_table(sie_sigp_order_codes, sigp_order_codes);
+define_exit_reasons_table(sie_diagnose_codes, diagnose_codes);
+define_exit_reasons_table(sie_icpt_prog_codes, icpt_prog_codes);
+
+static void event_icpt_insn_get_key(struct perf_evsel *evsel,
+ struct perf_sample *sample,
+ struct event_key *key)
+{
+ unsigned long insn;
+
+ insn = perf_evsel__intval(evsel, sample, "instruction");
+ key->key = icpt_insn_decoder(insn);
+ key->exit_reasons = sie_icpt_insn_codes;
+}
+
+static void event_sigp_get_key(struct perf_evsel *evsel,
+ struct perf_sample *sample,
+ struct event_key *key)
+{
+ key->key = perf_evsel__intval(evsel, sample, "order_code");
+ key->exit_reasons = sie_sigp_order_codes;
+}
+
+static void event_diag_get_key(struct perf_evsel *evsel,
+ struct perf_sample *sample,
+ struct event_key *key)
+{
+ key->key = perf_evsel__intval(evsel, sample, "code");
+ key->exit_reasons = sie_diagnose_codes;
+}
+
+static void event_icpt_prog_get_key(struct perf_evsel *evsel,
+ struct perf_sample *sample,
+ struct event_key *key)
+{
+ key->key = perf_evsel__intval(evsel, sample, "code");
+ key->exit_reasons = sie_icpt_prog_codes;
+}
+
+static struct child_event_ops child_events[] = {
+ { .name = "kvm:kvm_s390_intercept_instruction",
+ .get_key = event_icpt_insn_get_key },
+ { .name = "kvm:kvm_s390_handle_sigp",
+ .get_key = event_sigp_get_key },
+ { .name = "kvm:kvm_s390_handle_diag",
+ .get_key = event_diag_get_key },
+ { .name = "kvm:kvm_s390_intercept_prog",
+ .get_key = event_icpt_prog_get_key },
+ { NULL, NULL },
+};
+
+static struct kvm_events_ops exit_events = {
+ .is_begin_event = exit_event_begin,
+ .is_end_event = exit_event_end,
+ .child_ops = child_events,
+ .decode_key = exit_event_decode_key,
+ .name = "VM-EXIT"
+};
+
+const char * const kvm_events_tp[] = {
+ "kvm:kvm_s390_sie_enter",
+ "kvm:kvm_s390_sie_exit",
+ "kvm:kvm_s390_intercept_instruction",
+ "kvm:kvm_s390_handle_sigp",
+ "kvm:kvm_s390_handle_diag",
+ "kvm:kvm_s390_intercept_prog",
+ NULL,
+};
+
+struct kvm_reg_events_ops kvm_reg_events_ops[] = {
+ { .name = "vmexit", .ops = &exit_events },
+ { NULL, NULL },
+};
+
+const char * const kvm_skip_events[] = {
+ "Wait state",
+ NULL,
+};
+
+int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid)
+{
+ if (strstr(cpuid, "IBM/S390")) {
+ kvm->exit_reasons = sie_exit_reasons;
+ kvm->exit_reasons_isa = "SIE";
+ } else
+ return -ENOTSUP;
+
+ return 0;
+}
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 1641542e3636..9b21881db52f 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -15,3 +15,5 @@ endif
LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/tsc.o
LIB_H += arch/$(ARCH)/util/tsc.h
+HAVE_KVM_STAT_SUPPORT := 1
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/kvm-stat.o
diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c
index 9f89f899ccc7..d8bbf7ad1681 100644
--- a/tools/perf/arch/x86/tests/dwarf-unwind.c
+++ b/tools/perf/arch/x86/tests/dwarf-unwind.c
@@ -3,6 +3,7 @@
#include "thread.h"
#include "map.h"
#include "event.h"
+#include "debug.h"
#include "tests/tests.h"
#define STACK_SIZE 8192
diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c
new file mode 100644
index 000000000000..14e4e668fad7
--- /dev/null
+++ b/tools/perf/arch/x86/util/kvm-stat.c
@@ -0,0 +1,156 @@
+#include "../../util/kvm-stat.h"
+#include <asm/kvm_perf.h>
+
+define_exit_reasons_table(vmx_exit_reasons, VMX_EXIT_REASONS);
+define_exit_reasons_table(svm_exit_reasons, SVM_EXIT_REASONS);
+
+static struct kvm_events_ops exit_events = {
+ .is_begin_event = exit_event_begin,
+ .is_end_event = exit_event_end,
+ .decode_key = exit_event_decode_key,
+ .name = "VM-EXIT"
+};
+
+/*
+ * For the mmio events, we treat:
+ * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry
+ * the time of MMIO read: kvm_exit -> kvm_mmio(KVM_TRACE_MMIO_READ...).
+ */
+static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample,
+ struct event_key *key)
+{
+ key->key = perf_evsel__intval(evsel, sample, "gpa");
+ key->info = perf_evsel__intval(evsel, sample, "type");
+}
+
+#define KVM_TRACE_MMIO_READ_UNSATISFIED 0
+#define KVM_TRACE_MMIO_READ 1
+#define KVM_TRACE_MMIO_WRITE 2
+
+static bool mmio_event_begin(struct perf_evsel *evsel,
+ struct perf_sample *sample, struct event_key *key)
+{
+ /* MMIO read begin event in kernel. */
+ if (kvm_exit_event(evsel))
+ return true;
+
+ /* MMIO write begin event in kernel. */
+ if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
+ perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) {
+ mmio_event_get_key(evsel, sample, key);
+ return true;
+ }
+
+ return false;
+}
+
+static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample,
+ struct event_key *key)
+{
+ /* MMIO write end event in kernel. */
+ if (kvm_entry_event(evsel))
+ return true;
+
+ /* MMIO read end event in kernel.*/
+ if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
+ perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) {
+ mmio_event_get_key(evsel, sample, key);
+ return true;
+ }
+
+ return false;
+}
+
+static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
+ struct event_key *key,
+ char *decode)
+{
+ scnprintf(decode, DECODE_STR_LEN, "%#lx:%s",
+ (unsigned long)key->key,
+ key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R");
+}
+
+static struct kvm_events_ops mmio_events = {
+ .is_begin_event = mmio_event_begin,
+ .is_end_event = mmio_event_end,
+ .decode_key = mmio_event_decode_key,
+ .name = "MMIO Access"
+};
+
+ /* The time of emulation pio access is from kvm_pio to kvm_entry. */
+static void ioport_event_get_key(struct perf_evsel *evsel,
+ struct perf_sample *sample,
+ struct event_key *key)
+{
+ key->key = perf_evsel__intval(evsel, sample, "port");
+ key->info = perf_evsel__intval(evsel, sample, "rw");
+}
+
+static bool ioport_event_begin(struct perf_evsel *evsel,
+ struct perf_sample *sample,
+ struct event_key *key)
+{
+ if (!strcmp(evsel->name, "kvm:kvm_pio")) {
+ ioport_event_get_key(evsel, sample, key);
+ return true;
+ }
+
+ return false;
+}
+
+static bool ioport_event_end(struct perf_evsel *evsel,
+ struct perf_sample *sample __maybe_unused,
+ struct event_key *key __maybe_unused)
+{
+ return kvm_entry_event(evsel);
+}
+
+static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
+ struct event_key *key,
+ char *decode)
+{
+ scnprintf(decode, DECODE_STR_LEN, "%#llx:%s",
+ (unsigned long long)key->key,
+ key->info ? "POUT" : "PIN");
+}
+
+static struct kvm_events_ops ioport_events = {
+ .is_begin_event = ioport_event_begin,
+ .is_end_event = ioport_event_end,
+ .decode_key = ioport_event_decode_key,
+ .name = "IO Port Access"
+};
+
+const char * const kvm_events_tp[] = {
+ "kvm:kvm_entry",
+ "kvm:kvm_exit",
+ "kvm:kvm_mmio",
+ "kvm:kvm_pio",
+ NULL,
+};
+
+struct kvm_reg_events_ops kvm_reg_events_ops[] = {
+ { .name = "vmexit", .ops = &exit_events },
+ { .name = "mmio", .ops = &mmio_events },
+ { .name = "ioport", .ops = &ioport_events },
+ { NULL, NULL },
+};
+
+const char * const kvm_skip_events[] = {
+ "HLT",
+ NULL,
+};
+
+int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid)
+{
+ if (strstr(cpuid, "Intel")) {
+ kvm->exit_reasons = vmx_exit_reasons;
+ kvm->exit_reasons_isa = "VMX";
+ } else if (strstr(cpuid, "AMD")) {
+ kvm->exit_reasons = svm_exit_reasons;
+ kvm->exit_reasons_isa = "SVM";
+ } else
+ return -ENOTSUP;
+
+ return 0;
+}
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
index 40021fa3129b..fd2868490d00 100644
--- a/tools/perf/arch/x86/util/tsc.c
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -6,29 +6,9 @@
#include "../../perf.h"
#include <linux/types.h>
#include "../../util/debug.h"
+#include "../../util/tsc.h"
#include "tsc.h"
-u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc)
-{
- u64 t, quot, rem;
-
- t = ns - tc->time_zero;
- quot = t / tc->time_mult;
- rem = t % tc->time_mult;
- return (quot << tc->time_shift) +
- (rem << tc->time_shift) / tc->time_mult;
-}
-
-u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc)
-{
- u64 quot, rem;
-
- quot = cyc >> tc->time_shift;
- rem = cyc & ((1 << tc->time_shift) - 1);
- return tc->time_zero + quot * tc->time_mult +
- ((rem * tc->time_mult) >> tc->time_shift);
-}
-
int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
struct perf_tsc_conversion *tc)
{
@@ -57,3 +37,12 @@ int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
return 0;
}
+
+u64 rdtsc(void)
+{
+ unsigned int low, high;
+
+ asm volatile("rdtsc" : "=a" (low), "=d" (high));
+
+ return low | ((u64)high) << 32;
+}
diff --git a/tools/perf/arch/x86/util/tsc.h b/tools/perf/arch/x86/util/tsc.h
index 2affe0366b59..2edc4d31065c 100644
--- a/tools/perf/arch/x86/util/tsc.h
+++ b/tools/perf/arch/x86/util/tsc.h
@@ -14,7 +14,4 @@ struct perf_event_mmap_page;
int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
struct perf_tsc_conversion *tc);
-u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc);
-u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc);
-
#endif /* TOOLS_PERF_ARCH_X86_UTIL_TSC_H__ */
diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c
index 3261f68c6a7c..db25e93d989c 100644
--- a/tools/perf/arch/x86/util/unwind-libunwind.c
+++ b/tools/perf/arch/x86/util/unwind-libunwind.c
@@ -3,6 +3,7 @@
#include <libunwind.h>
#include "perf_regs.h"
#include "../../util/unwind.h"
+#include "../../util/debug.h"
#ifdef HAVE_ARCH_X86_64_SUPPORT
int libunwind__arch_reg_id(int regnum)
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index eba46709b279..3c4dd44d45cb 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -43,5 +43,6 @@ extern int bench_futex_requeue(int argc, const char **argv, const char *prefix);
#define BENCH_FORMAT_UNKNOWN -1
extern int bench_format;
+extern unsigned int bench_repeat;
#endif
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index a84206e9c4aa..fc9bebd2cca0 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -26,6 +26,7 @@ static unsigned int nsecs = 10;
/* amount of futexes per thread */
static unsigned int nfutexes = 1024;
static bool fshared = false, done = false, silent = false;
+static int futex_flag = 0;
struct timeval start, end, runtime;
static pthread_mutex_t thread_lock;
@@ -75,8 +76,7 @@ static void *workerfn(void *arg)
* such as internal waitqueue handling, thus enlarging
* the critical region protected by hb->lock.
*/
- ret = futex_wait(&w->futex[i], 1234, NULL,
- fshared ? 0 : FUTEX_PRIVATE_FLAG);
+ ret = futex_wait(&w->futex[i], 1234, NULL, futex_flag);
if (!silent &&
(!ret || errno != EAGAIN || errno != EWOULDBLOCK))
warn("Non-expected futex return call");
@@ -135,6 +135,9 @@ int bench_futex_hash(int argc, const char **argv,
if (!worker)
goto errmem;
+ if (!fshared)
+ futex_flag = FUTEX_PRIVATE_FLAG;
+
printf("Run summary [PID %d]: %d threads, each operating on %d [%s] futexes for %d secs.\n\n",
getpid(), nthreads, nfutexes, fshared ? "shared":"private", nsecs);
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index a16255876f1d..bedff6b5b3cf 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -29,25 +29,19 @@ static u_int32_t futex1 = 0, futex2 = 0;
*/
static unsigned int nrequeue = 1;
-/*
- * There can be significant variance from run to run,
- * the more repeats, the more exact the overall avg and
- * the better idea of the futex latency.
- */
-static unsigned int repeat = 10;
-
static pthread_t *worker;
-static bool done = 0, silent = 0;
+static bool done = false, silent = false, fshared = false;
static pthread_mutex_t thread_lock;
static pthread_cond_t thread_parent, thread_worker;
static struct stats requeuetime_stats, requeued_stats;
static unsigned int ncpus, threads_starting, nthreads = 0;
+static int futex_flag = 0;
static const struct option options[] = {
OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
OPT_UINTEGER('q', "nrequeue", &nrequeue, "Specify amount of threads to requeue at once"),
- OPT_UINTEGER('r', "repeat", &repeat, "Specify amount of times to repeat the run"),
OPT_BOOLEAN( 's', "silent", &silent, "Silent mode: do not display data/details"),
+ OPT_BOOLEAN( 'S', "shared", &fshared, "Use shared futexes instead of private ones"),
OPT_END()
};
@@ -78,7 +72,7 @@ static void *workerfn(void *arg __maybe_unused)
pthread_cond_wait(&thread_worker, &thread_lock);
pthread_mutex_unlock(&thread_lock);
- futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG);
+ futex_wait(&futex1, 0, NULL, futex_flag);
return NULL;
}
@@ -135,9 +129,12 @@ int bench_futex_requeue(int argc, const char **argv,
if (!worker)
err(EXIT_FAILURE, "calloc");
- printf("Run summary [PID %d]: Requeuing %d threads (from %p to %p), "
- "%d at a time.\n\n",
- getpid(), nthreads, &futex1, &futex2, nrequeue);
+ if (!fshared)
+ futex_flag = FUTEX_PRIVATE_FLAG;
+
+ printf("Run summary [PID %d]: Requeuing %d threads (from [%s] %p to %p), "
+ "%d at a time.\n\n", getpid(), nthreads,
+ fshared ? "shared":"private", &futex1, &futex2, nrequeue);
init_stats(&requeued_stats);
init_stats(&requeuetime_stats);
@@ -146,7 +143,7 @@ int bench_futex_requeue(int argc, const char **argv,
pthread_cond_init(&thread_parent, NULL);
pthread_cond_init(&thread_worker, NULL);
- for (j = 0; j < repeat && !done; j++) {
+ for (j = 0; j < bench_repeat && !done; j++) {
unsigned int nrequeued = 0;
struct timeval start, end, runtime;
@@ -164,16 +161,20 @@ int bench_futex_requeue(int argc, const char **argv,
/* Ok, all threads are patiently blocked, start requeueing */
gettimeofday(&start, NULL);
- for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue)
+ for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue) {
/*
* Do not wakeup any tasks blocked on futex1, allowing
* us to really measure futex_wait functionality.
*/
- futex_cmp_requeue(&futex1, 0, &futex2, 0, nrequeue,
- FUTEX_PRIVATE_FLAG);
+ futex_cmp_requeue(&futex1, 0, &futex2, 0,
+ nrequeue, futex_flag);
+ }
gettimeofday(&end, NULL);
timersub(&end, &start, &runtime);
+ if (nrequeued > nthreads)
+ nrequeued = nthreads;
+
update_stats(&requeued_stats, nrequeued);
update_stats(&requeuetime_stats, runtime.tv_usec);
@@ -183,7 +184,7 @@ int bench_futex_requeue(int argc, const char **argv,
}
/* everybody should be blocked on futex2, wake'em up */
- nrequeued = futex_wake(&futex2, nthreads, FUTEX_PRIVATE_FLAG);
+ nrequeued = futex_wake(&futex2, nthreads, futex_flag);
if (nthreads != nrequeued)
warnx("couldn't wakeup all tasks (%d/%d)", nrequeued, nthreads);
@@ -192,7 +193,6 @@ int bench_futex_requeue(int argc, const char **argv,
if (ret)
err(EXIT_FAILURE, "pthread_join");
}
-
}
/* cleanup & report results */
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index d096169b161e..929f762be47e 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -30,25 +30,19 @@ static u_int32_t futex1 = 0;
*/
static unsigned int nwakes = 1;
-/*
- * There can be significant variance from run to run,
- * the more repeats, the more exact the overall avg and
- * the better idea of the futex latency.
- */
-static unsigned int repeat = 10;
-
pthread_t *worker;
-static bool done = 0, silent = 0;
+static bool done = false, silent = false, fshared = false;
static pthread_mutex_t thread_lock;
static pthread_cond_t thread_parent, thread_worker;
static struct stats waketime_stats, wakeup_stats;
static unsigned int ncpus, threads_starting, nthreads = 0;
+static int futex_flag = 0;
static const struct option options[] = {
OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
OPT_UINTEGER('w', "nwakes", &nwakes, "Specify amount of threads to wake at once"),
- OPT_UINTEGER('r', "repeat", &repeat, "Specify amount of times to repeat the run"),
OPT_BOOLEAN( 's', "silent", &silent, "Silent mode: do not display data/details"),
+ OPT_BOOLEAN( 'S', "shared", &fshared, "Use shared futexes instead of private ones"),
OPT_END()
};
@@ -66,7 +60,7 @@ static void *workerfn(void *arg __maybe_unused)
pthread_cond_wait(&thread_worker, &thread_lock);
pthread_mutex_unlock(&thread_lock);
- futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG);
+ futex_wait(&futex1, 0, NULL, futex_flag);
return NULL;
}
@@ -138,9 +132,12 @@ int bench_futex_wake(int argc, const char **argv,
if (!worker)
err(EXIT_FAILURE, "calloc");
- printf("Run summary [PID %d]: blocking on %d threads (at futex %p), "
+ if (!fshared)
+ futex_flag = FUTEX_PRIVATE_FLAG;
+
+ printf("Run summary [PID %d]: blocking on %d threads (at [%s] futex %p), "
"waking up %d at a time.\n\n",
- getpid(), nthreads, &futex1, nwakes);
+ getpid(), nthreads, fshared ? "shared":"private", &futex1, nwakes);
init_stats(&wakeup_stats);
init_stats(&waketime_stats);
@@ -149,7 +146,7 @@ int bench_futex_wake(int argc, const char **argv,
pthread_cond_init(&thread_parent, NULL);
pthread_cond_init(&thread_worker, NULL);
- for (j = 0; j < repeat && !done; j++) {
+ for (j = 0; j < bench_repeat && !done; j++) {
unsigned int nwoken = 0;
struct timeval start, end, runtime;
@@ -168,7 +165,7 @@ int bench_futex_wake(int argc, const char **argv,
/* Ok, all threads are patiently blocked, start waking folks up */
gettimeofday(&start, NULL);
while (nwoken != nthreads)
- nwoken += futex_wake(&futex1, nwakes, FUTEX_PRIVATE_FLAG);
+ nwoken += futex_wake(&futex1, nwakes, futex_flag);
gettimeofday(&end, NULL);
timersub(&end, &start, &runtime);
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 5ce71d3b72cf..2465141b554b 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -10,6 +10,7 @@
#include "../util/util.h"
#include "../util/parse-options.h"
#include "../util/header.h"
+#include "../util/cloexec.h"
#include "bench.h"
#include "mem-memcpy-arch.h"
@@ -83,7 +84,8 @@ static struct perf_event_attr cycle_attr = {
static void init_cycle(void)
{
- cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, 0);
+ cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1,
+ perf_event_open_cloexec_flag());
if (cycle_fd < 0 && errno == ENOSYS)
die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
@@ -189,6 +191,11 @@ int bench_mem_memcpy(int argc, const char **argv,
argc = parse_options(argc, argv, options,
bench_mem_memcpy_usage, 0);
+ if (no_prefault && only_prefault) {
+ fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n");
+ return 1;
+ }
+
if (use_cycle)
init_cycle();
diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c
index 9af79d2b18e5..75fc3e65fb2a 100644
--- a/tools/perf/bench/mem-memset.c
+++ b/tools/perf/bench/mem-memset.c
@@ -10,6 +10,7 @@
#include "../util/util.h"
#include "../util/parse-options.h"
#include "../util/header.h"
+#include "../util/cloexec.h"
#include "bench.h"
#include "mem-memset-arch.h"
@@ -83,7 +84,8 @@ static struct perf_event_attr cycle_attr = {
static void init_cycle(void)
{
- cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, 0);
+ cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1,
+ perf_event_open_cloexec_flag());
if (cycle_fd < 0 && errno == ENOSYS)
die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
@@ -181,6 +183,11 @@ int bench_mem_memset(int argc, const char **argv,
argc = parse_options(argc, argv, options,
bench_mem_memset_usage, 0);
+ if (no_prefault && only_prefault) {
+ fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n");
+ return 1;
+ }
+
if (use_cycle)
init_cycle();
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index cc1190a0849b..d7f281c2828d 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -26,8 +26,9 @@
#include <sys/socket.h>
#include <sys/wait.h>
#include <sys/time.h>
-#include <sys/poll.h>
+#include <poll.h>
#include <limits.h>
+#include <err.h>
#define DATASIZE 100
@@ -50,12 +51,6 @@ struct receiver_context {
int wakefd;
};
-static void barf(const char *msg)
-{
- fprintf(stderr, "%s (error: %s)\n", msg, strerror(errno));
- exit(1);
-}
-
static void fdpair(int fds[2])
{
if (use_pipes) {
@@ -66,7 +61,7 @@ static void fdpair(int fds[2])
return;
}
- barf(use_pipes ? "pipe()" : "socketpair()");
+ err(EXIT_FAILURE, use_pipes ? "pipe()" : "socketpair()");
}
/* Block until we're ready to go */
@@ -77,11 +72,11 @@ static void ready(int ready_out, int wakefd)
/* Tell them we're ready. */
if (write(ready_out, &dummy, 1) != 1)
- barf("CLIENT: ready write");
+ err(EXIT_FAILURE, "CLIENT: ready write");
/* Wait for "GO" signal */
if (poll(&pollfd, 1, -1) != 1)
- barf("poll");
+ err(EXIT_FAILURE, "poll");
}
/* Sender sprays loops messages down each file descriptor */
@@ -101,7 +96,7 @@ again:
ret = write(ctx->out_fds[j], data + done,
sizeof(data)-done);
if (ret < 0)
- barf("SENDER: write");
+ err(EXIT_FAILURE, "SENDER: write");
done += ret;
if (done < DATASIZE)
goto again;
@@ -131,7 +126,7 @@ static void *receiver(struct receiver_context* ctx)
again:
ret = read(ctx->in_fds[0], data + done, DATASIZE - done);
if (ret < 0)
- barf("SERVER: read");
+ err(EXIT_FAILURE, "SERVER: read");
done += ret;
if (done < DATASIZE)
goto again;
@@ -144,14 +139,14 @@ static pthread_t create_worker(void *ctx, void *(*func)(void *))
{
pthread_attr_t attr;
pthread_t childid;
- int err;
+ int ret;
if (!thread_mode) {
/* process mode */
/* Fork the receiver. */
switch (fork()) {
case -1:
- barf("fork()");
+ err(EXIT_FAILURE, "fork()");
break;
case 0:
(*func) (ctx);
@@ -165,19 +160,17 @@ static pthread_t create_worker(void *ctx, void *(*func)(void *))
}
if (pthread_attr_init(&attr) != 0)
- barf("pthread_attr_init:");
+ err(EXIT_FAILURE, "pthread_attr_init:");
#ifndef __ia64__
if (pthread_attr_setstacksize(&attr, PTHREAD_STACK_MIN) != 0)
- barf("pthread_attr_setstacksize");
+ err(EXIT_FAILURE, "pthread_attr_setstacksize");
#endif
- err = pthread_create(&childid, &attr, func, ctx);
- if (err != 0) {
- fprintf(stderr, "pthread_create failed: %s (%d)\n",
- strerror(err), err);
- exit(-1);
- }
+ ret = pthread_create(&childid, &attr, func, ctx);
+ if (ret != 0)
+ err(EXIT_FAILURE, "pthread_create failed");
+
return childid;
}
@@ -207,14 +200,14 @@ static unsigned int group(pthread_t *pth,
+ num_fds * sizeof(int));
if (!snd_ctx)
- barf("malloc()");
+ err(EXIT_FAILURE, "malloc()");
for (i = 0; i < num_fds; i++) {
int fds[2];
struct receiver_context *ctx = malloc(sizeof(*ctx));
if (!ctx)
- barf("malloc()");
+ err(EXIT_FAILURE, "malloc()");
/* Create the pipe between client and server */
@@ -281,7 +274,7 @@ int bench_sched_messaging(int argc, const char **argv,
pth_tab = malloc(num_fds * 2 * num_groups * sizeof(pthread_t));
if (!pth_tab)
- barf("main:malloc()");
+ err(EXIT_FAILURE, "main:malloc()");
fdpair(readyfds);
fdpair(wakefds);
@@ -294,13 +287,13 @@ int bench_sched_messaging(int argc, const char **argv,
/* Wait for everyone to be ready */
for (i = 0; i < total_children; i++)
if (read(readyfds[0], &dummy, 1) != 1)
- barf("Reading for readyfds");
+ err(EXIT_FAILURE, "Reading for readyfds");
gettimeofday(&start, NULL);
/* Kick them off */
if (write(wakefds[1], &dummy, 1) != 1)
- barf("Writing to start them");
+ err(EXIT_FAILURE, "Writing to start them");
/* Reap them all */
for (i = 0; i < total_children; i++)
@@ -332,5 +325,7 @@ int bench_sched_messaging(int argc, const char **argv,
break;
}
+ free(pth_tab);
+
return 0;
}
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 1ec429fef2be..be5939418425 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -36,7 +36,8 @@
struct perf_annotate {
struct perf_tool tool;
- bool force, use_tui, use_stdio, use_gtk;
+ struct perf_session *session;
+ bool use_tui, use_stdio, use_gtk;
bool full_paths;
bool print_line;
bool skip_missing;
@@ -188,18 +189,9 @@ find_next:
static int __cmd_annotate(struct perf_annotate *ann)
{
int ret;
- struct perf_session *session;
+ struct perf_session *session = ann->session;
struct perf_evsel *pos;
u64 total_nr_samples;
- struct perf_data_file file = {
- .path = input_name,
- .mode = PERF_DATA_MODE_READ,
- .force = ann->force,
- };
-
- session = perf_session__new(&file, false, &ann->tool);
- if (session == NULL)
- return -ENOMEM;
machines__set_symbol_filter(&session->machines, symbol__annotate_init);
@@ -207,22 +199,22 @@ static int __cmd_annotate(struct perf_annotate *ann)
ret = perf_session__cpu_bitmap(session, ann->cpu_list,
ann->cpu_bitmap);
if (ret)
- goto out_delete;
+ goto out;
}
if (!objdump_path) {
ret = perf_session_env__lookup_objdump(&session->header.env);
if (ret)
- goto out_delete;
+ goto out;
}
ret = perf_session__process_events(session, &ann->tool);
if (ret)
- goto out_delete;
+ goto out;
if (dump_trace) {
perf_session__fprintf_nr_events(session, stdout);
- goto out_delete;
+ goto out;
}
if (verbose > 3)
@@ -250,8 +242,8 @@ static int __cmd_annotate(struct perf_annotate *ann)
}
if (total_nr_samples == 0) {
- ui__error("The %s file has no samples!\n", file.path);
- goto out_delete;
+ ui__error("The %s file has no samples!\n", session->file->path);
+ goto out;
}
if (use_browser == 2) {
@@ -261,24 +253,12 @@ static int __cmd_annotate(struct perf_annotate *ann)
"perf_gtk__show_annotations");
if (show_annotations == NULL) {
ui__error("GTK browser not found!\n");
- goto out_delete;
+ goto out;
}
show_annotations();
}
-out_delete:
- /*
- * Speed up the exit process, for large files this can
- * take quite a while.
- *
- * XXX Enable this when using valgrind or if we ever
- * librarize this command.
- *
- * Also experiment with obstacks to see how much speed
- * up we'll get here.
- *
- * perf_session__delete(session);
- */
+out:
return ret;
}
@@ -297,10 +277,14 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
.comm = perf_event__process_comm,
.exit = perf_event__process_exit,
.fork = perf_event__process_fork,
- .ordered_samples = true,
+ .ordered_events = true,
.ordering_requires_timestamps = true,
},
};
+ struct perf_data_file file = {
+ .path = input_name,
+ .mode = PERF_DATA_MODE_READ,
+ };
const struct option options[] = {
OPT_STRING('i', "input", &input_name, "file",
"input file name"),
@@ -308,7 +292,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
"only consider symbols in these dsos"),
OPT_STRING('s', "symbol", &annotate.sym_hist_filter, "symbol",
"symbol to annotate"),
- OPT_BOOLEAN('f', "force", &annotate.force, "don't complain, do it"),
+ OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show symbol address, etc)"),
OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
@@ -341,6 +325,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
"Show event group information together"),
OPT_END()
};
+ int ret;
argc = parse_options(argc, argv, options, annotate_usage, 0);
@@ -353,11 +338,16 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
setup_browser(true);
+ annotate.session = perf_session__new(&file, false, &annotate.tool);
+ if (annotate.session == NULL)
+ return -1;
+
symbol_conf.priv_size = sizeof(struct annotation);
symbol_conf.try_vmlinux_path = true;
- if (symbol__init() < 0)
- return -1;
+ ret = symbol__init(&annotate.session->header.env);
+ if (ret < 0)
+ goto out_delete;
if (setup_sorting() < 0)
usage_with_options(annotate_usage, options);
@@ -373,5 +363,20 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
annotate.sym_hist_filter = argv[0];
}
- return __cmd_annotate(&annotate);
+ ret = __cmd_annotate(&annotate);
+
+out_delete:
+ /*
+ * Speed up the exit process, for large files this can
+ * take quite a while.
+ *
+ * XXX Enable this when using valgrind or if we ever
+ * librarize this command.
+ *
+ * Also experiment with obstacks to see how much speed
+ * up we'll get here.
+ *
+ * perf_session__delete(session);
+ */
+ return ret;
}
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index 1e6e77710545..b9a56fa83330 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -104,9 +104,11 @@ static const char *bench_format_str;
/* Output/formatting style, exported to benchmark modules: */
int bench_format = BENCH_FORMAT_DEFAULT;
+unsigned int bench_repeat = 10; /* default number of times to repeat the run */
static const struct option bench_options[] = {
OPT_STRING('f', "format", &bench_format_str, "default", "Specify format style"),
+ OPT_UINTEGER('r', "repeat", &bench_repeat, "Specify amount of times to repeat the run"),
OPT_END()
};
@@ -226,6 +228,11 @@ int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused)
goto end;
}
+ if (bench_repeat == 0) {
+ printf("Invalid repeat option: Must specify a positive value\n");
+ goto end;
+ }
+
if (argc < 1) {
print_usage();
goto end;
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index b22dbb16f877..70385756da63 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -125,7 +125,8 @@ static int build_id_cache__kcore_existing(const char *from_dir, char *to_dir,
return ret;
}
-static int build_id_cache__add_kcore(const char *filename, const char *debugdir)
+static int build_id_cache__add_kcore(const char *filename, const char *debugdir,
+ bool force)
{
char dir[32], sbuildid[BUILD_ID_SIZE * 2 + 1];
char from_dir[PATH_MAX], to_dir[PATH_MAX];
@@ -144,7 +145,8 @@ static int build_id_cache__add_kcore(const char *filename, const char *debugdir)
scnprintf(to_dir, sizeof(to_dir), "%s/[kernel.kcore]/%s",
debugdir, sbuildid);
- if (!build_id_cache__kcore_existing(from_dir, to_dir, sizeof(to_dir))) {
+ if (!force &&
+ !build_id_cache__kcore_existing(from_dir, to_dir, sizeof(to_dir))) {
pr_debug("same kcore found in %s\n", to_dir);
return 0;
}
@@ -244,20 +246,9 @@ static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused)
return true;
}
-static int build_id_cache__fprintf_missing(const char *filename, bool force, FILE *fp)
+static int build_id_cache__fprintf_missing(struct perf_session *session, FILE *fp)
{
- struct perf_data_file file = {
- .path = filename,
- .mode = PERF_DATA_MODE_READ,
- .force = force,
- };
- struct perf_session *session = perf_session__new(&file, false, NULL);
- if (session == NULL)
- return -1;
-
perf_session__fprintf_dsos_buildid(session, fp, dso__missing_buildid_cache, 0);
- perf_session__delete(session);
-
return 0;
}
@@ -300,6 +291,12 @@ int cmd_buildid_cache(int argc, const char **argv,
*missing_filename = NULL,
*update_name_list_str = NULL,
*kcore_filename;
+ char sbuf[STRERR_BUFSIZE];
+
+ struct perf_data_file file = {
+ .mode = PERF_DATA_MODE_READ,
+ };
+ struct perf_session *session = NULL;
const struct option buildid_cache_options[] = {
OPT_STRING('a', "add", &add_name_list_str,
@@ -324,8 +321,17 @@ int cmd_buildid_cache(int argc, const char **argv,
argc = parse_options(argc, argv, buildid_cache_options,
buildid_cache_usage, 0);
- if (symbol__init() < 0)
- return -1;
+ if (missing_filename) {
+ file.path = missing_filename;
+ file.force = force;
+
+ session = perf_session__new(&file, false, NULL);
+ if (session == NULL)
+ return -1;
+ }
+
+ if (symbol__init(session ? &session->header.env : NULL) < 0)
+ goto out;
setup_pager();
@@ -342,7 +348,7 @@ int cmd_buildid_cache(int argc, const char **argv,
continue;
}
pr_warning("Couldn't add %s: %s\n",
- pos->s, strerror(errno));
+ pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
}
strlist__delete(list);
@@ -360,7 +366,7 @@ int cmd_buildid_cache(int argc, const char **argv,
continue;
}
pr_warning("Couldn't remove %s: %s\n",
- pos->s, strerror(errno));
+ pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
}
strlist__delete(list);
@@ -368,7 +374,7 @@ int cmd_buildid_cache(int argc, const char **argv,
}
if (missing_filename)
- ret = build_id_cache__fprintf_missing(missing_filename, force, stdout);
+ ret = build_id_cache__fprintf_missing(session, stdout);
if (update_name_list_str) {
list = strlist__new(true, update_name_list_str);
@@ -381,7 +387,7 @@ int cmd_buildid_cache(int argc, const char **argv,
continue;
}
pr_warning("Couldn't update %s: %s\n",
- pos->s, strerror(errno));
+ pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
}
strlist__delete(list);
@@ -389,8 +395,12 @@ int cmd_buildid_cache(int argc, const char **argv,
}
if (kcore_filename &&
- build_id_cache__add_kcore(kcore_filename, debugdir))
+ build_id_cache__add_kcore(kcore_filename, debugdir, force))
pr_warning("Couldn't add %s\n", kcore_filename);
+out:
+ if (session)
+ perf_session__delete(session);
+
return ret;
}
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 9a5a035cb426..a3ce19f7aebd 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -360,7 +360,7 @@ static struct perf_tool tool = {
.exit = perf_event__process_exit,
.fork = perf_event__process_fork,
.lost = perf_event__process_lost,
- .ordered_samples = true,
+ .ordered_events = true,
.ordering_requires_timestamps = true,
};
@@ -683,7 +683,7 @@ static int __cmd_diff(void)
d->session = perf_session__new(&d->file, false, &tool);
if (!d->session) {
pr_err("Failed to open %s\n", d->file.path);
- ret = -ENOMEM;
+ ret = -1;
goto out_delete;
}
@@ -1143,7 +1143,7 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
argc = parse_options(argc, argv, options, diff_usage, 0);
- if (symbol__init() < 0)
+ if (symbol__init(NULL) < 0)
return -1;
if (data_init(argc, argv) < 0)
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index c99e0de7e54a..0f93f859b782 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -15,6 +15,7 @@
#include "util/parse-options.h"
#include "util/session.h"
#include "util/data.h"
+#include "util/debug.h"
static int __cmd_evlist(const char *file_name, struct perf_attr_details *details)
{
@@ -27,7 +28,7 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details
session = perf_session__new(&file, 0, NULL);
if (session == NULL)
- return -ENOMEM;
+ return -1;
evlist__for_each(session->evlist, pos)
perf_evsel__fprintf(pos, details, stdout);
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 178b88ae3d2f..25d20628212e 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -11,6 +11,7 @@
#include "util/parse-options.h"
#include "util/run-command.h"
#include "util/help.h"
+#include "util/debug.h"
static struct man_viewer_list {
struct man_viewer_list *next;
@@ -102,6 +103,8 @@ static int check_emacsclient_version(void)
static void exec_woman_emacs(const char *path, const char *page)
{
+ char sbuf[STRERR_BUFSIZE];
+
if (!check_emacsclient_version()) {
/* This works only with emacsclient version >= 22. */
struct strbuf man_page = STRBUF_INIT;
@@ -110,16 +113,19 @@ static void exec_woman_emacs(const char *path, const char *page)
path = "emacsclient";
strbuf_addf(&man_page, "(woman \"%s\")", page);
execlp(path, "emacsclient", "-e", man_page.buf, NULL);
- warning("failed to exec '%s': %s", path, strerror(errno));
+ warning("failed to exec '%s': %s", path,
+ strerror_r(errno, sbuf, sizeof(sbuf)));
}
}
static void exec_man_konqueror(const char *path, const char *page)
{
const char *display = getenv("DISPLAY");
+
if (display && *display) {
struct strbuf man_page = STRBUF_INIT;
const char *filename = "kfmclient";
+ char sbuf[STRERR_BUFSIZE];
/* It's simpler to launch konqueror using kfmclient. */
if (path) {
@@ -138,24 +144,31 @@ static void exec_man_konqueror(const char *path, const char *page)
path = "kfmclient";
strbuf_addf(&man_page, "man:%s(1)", page);
execlp(path, filename, "newTab", man_page.buf, NULL);
- warning("failed to exec '%s': %s", path, strerror(errno));
+ warning("failed to exec '%s': %s", path,
+ strerror_r(errno, sbuf, sizeof(sbuf)));
}
}
static void exec_man_man(const char *path, const char *page)
{
+ char sbuf[STRERR_BUFSIZE];
+
if (!path)
path = "man";
execlp(path, "man", page, NULL);
- warning("failed to exec '%s': %s", path, strerror(errno));
+ warning("failed to exec '%s': %s", path,
+ strerror_r(errno, sbuf, sizeof(sbuf)));
}
static void exec_man_cmd(const char *cmd, const char *page)
{
struct strbuf shell_cmd = STRBUF_INIT;
+ char sbuf[STRERR_BUFSIZE];
+
strbuf_addf(&shell_cmd, "%s %s", cmd, page);
execl("/bin/sh", "sh", "-c", shell_cmd.buf, NULL);
- warning("failed to exec '%s': %s", cmd, strerror(errno));
+ warning("failed to exec '%s': %s", cmd,
+ strerror_r(errno, sbuf, sizeof(sbuf)));
}
static void add_man_viewer(const char *name)
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 16c7c11ad06e..de99ca1bb942 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -23,6 +23,7 @@
struct perf_inject {
struct perf_tool tool;
+ struct perf_session *session;
bool build_ids;
bool sched_stat;
const char *input_name;
@@ -340,12 +341,8 @@ static int perf_evsel__check_stype(struct perf_evsel *evsel,
static int __cmd_inject(struct perf_inject *inject)
{
- struct perf_session *session;
int ret = -EINVAL;
- struct perf_data_file file = {
- .path = inject->input_name,
- .mode = PERF_DATA_MODE_READ,
- };
+ struct perf_session *session = inject->session;
struct perf_data_file *file_out = &inject->output;
signal(SIGINT, sig_handler);
@@ -357,16 +354,12 @@ static int __cmd_inject(struct perf_inject *inject)
inject->tool.tracing_data = perf_event__repipe_tracing_data;
}
- session = perf_session__new(&file, true, &inject->tool);
- if (session == NULL)
- return -ENOMEM;
-
if (inject->build_ids) {
inject->tool.sample = perf_event__inject_buildid;
} else if (inject->sched_stat) {
struct perf_evsel *evsel;
- inject->tool.ordered_samples = true;
+ inject->tool.ordered_events = true;
evlist__for_each(session->evlist, evsel) {
const char *name = perf_evsel__name(evsel);
@@ -389,12 +382,13 @@ static int __cmd_inject(struct perf_inject *inject)
ret = perf_session__process_events(session, &inject->tool);
if (!file_out->is_pipe) {
+ if (inject->build_ids)
+ perf_header__set_feat(&session->header,
+ HEADER_BUILD_ID);
session->header.data_size = inject->bytes_written;
perf_session__write_header(session, session->evlist, file_out->fd, true);
}
- perf_session__delete(session);
-
return ret;
}
@@ -424,6 +418,11 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
.mode = PERF_DATA_MODE_WRITE,
},
};
+ struct perf_data_file file = {
+ .mode = PERF_DATA_MODE_READ,
+ };
+ int ret;
+
const struct option options[] = {
OPT_BOOLEAN('b', "build-ids", &inject.build_ids,
"Inject build-ids into the output stream"),
@@ -436,6 +435,8 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
"where and how long tasks slept"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show build ids, etc)"),
+ OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file",
+ "kallsyms pathname"),
OPT_END()
};
const char * const inject_usage[] = {
@@ -456,8 +457,17 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
return -1;
}
- if (symbol__init() < 0)
+ file.path = inject.input_name;
+ inject.session = perf_session__new(&file, true, &inject.tool);
+ if (inject.session == NULL)
+ return -1;
+
+ if (symbol__init(&inject.session->header.env) < 0)
return -1;
- return __cmd_inject(&inject);
+ ret = __cmd_inject(&inject);
+
+ perf_session__delete(inject.session);
+
+ return ret;
}
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index bef3376bfaf3..f295141025bc 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -256,7 +256,9 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
static struct perf_tool perf_kmem = {
.sample = process_sample_event,
.comm = perf_event__process_comm,
- .ordered_samples = true,
+ .mmap = perf_event__process_mmap,
+ .mmap2 = perf_event__process_mmap2,
+ .ordered_events = true,
};
static double fragmentation(unsigned long n_req, unsigned long n_alloc)
@@ -403,10 +405,9 @@ static void sort_result(void)
__sort_result(&root_caller_stat, &root_caller_sorted, &caller_sort);
}
-static int __cmd_kmem(void)
+static int __cmd_kmem(struct perf_session *session)
{
int err = -EINVAL;
- struct perf_session *session;
const struct perf_evsel_str_handler kmem_tracepoints[] = {
{ "kmem:kmalloc", perf_evsel__process_alloc_event, },
{ "kmem:kmem_cache_alloc", perf_evsel__process_alloc_event, },
@@ -415,34 +416,22 @@ static int __cmd_kmem(void)
{ "kmem:kfree", perf_evsel__process_free_event, },
{ "kmem:kmem_cache_free", perf_evsel__process_free_event, },
};
- struct perf_data_file file = {
- .path = input_name,
- .mode = PERF_DATA_MODE_READ,
- };
-
- session = perf_session__new(&file, false, &perf_kmem);
- if (session == NULL)
- return -ENOMEM;
-
- if (perf_session__create_kernel_maps(session) < 0)
- goto out_delete;
if (!perf_session__has_traces(session, "kmem record"))
- goto out_delete;
+ goto out;
if (perf_session__set_tracepoints_handlers(session, kmem_tracepoints)) {
pr_err("Initializing perf session tracepoint handlers failed\n");
- return -1;
+ goto out;
}
setup_pager();
err = perf_session__process_events(session, &perf_kmem);
if (err != 0)
- goto out_delete;
+ goto out;
sort_result();
print_result(session);
-out_delete:
- perf_session__delete(session);
+out:
return err;
}
@@ -689,29 +678,46 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
NULL,
NULL
};
+ struct perf_session *session;
+ struct perf_data_file file = {
+ .path = input_name,
+ .mode = PERF_DATA_MODE_READ,
+ };
+ int ret = -1;
+
argc = parse_options_subcommand(argc, argv, kmem_options,
kmem_subcommands, kmem_usage, 0);
if (!argc)
usage_with_options(kmem_usage, kmem_options);
- symbol__init();
-
if (!strncmp(argv[0], "rec", 3)) {
+ symbol__init(NULL);
return __cmd_record(argc, argv);
- } else if (!strcmp(argv[0], "stat")) {
+ }
+
+ session = perf_session__new(&file, false, &perf_kmem);
+ if (session == NULL)
+ return -1;
+
+ symbol__init(&session->header.env);
+
+ if (!strcmp(argv[0], "stat")) {
if (cpu__setup_cpunode_map())
- return -1;
+ goto out_delete;
if (list_empty(&caller_sort))
setup_sorting(&caller_sort, default_sort_order);
if (list_empty(&alloc_sort))
setup_sorting(&alloc_sort, default_sort_order);
- return __cmd_kmem();
+ ret = __cmd_kmem(session);
} else
usage_with_options(kmem_usage, kmem_options);
- return 0;
+out_delete:
+ perf_session__delete(session);
+
+ return ret;
}
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 0f1e5a2f6ad7..d8bf2271f4ea 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -29,114 +29,25 @@
#include <pthread.h>
#include <math.h>
-#if defined(__i386__) || defined(__x86_64__)
-#include <asm/svm.h>
-#include <asm/vmx.h>
-#include <asm/kvm.h>
-
-struct event_key {
- #define INVALID_KEY (~0ULL)
- u64 key;
- int info;
-};
-
-struct kvm_event_stats {
- u64 time;
- struct stats stats;
-};
-
-struct kvm_event {
- struct list_head hash_entry;
- struct rb_node rb;
-
- struct event_key key;
-
- struct kvm_event_stats total;
-
- #define DEFAULT_VCPU_NUM 8
- int max_vcpu;
- struct kvm_event_stats *vcpu;
-};
-
-typedef int (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int);
-
-struct kvm_event_key {
- const char *name;
- key_cmp_fun key;
-};
-
-
-struct perf_kvm_stat;
-
-struct kvm_events_ops {
- bool (*is_begin_event)(struct perf_evsel *evsel,
- struct perf_sample *sample,
- struct event_key *key);
- bool (*is_end_event)(struct perf_evsel *evsel,
- struct perf_sample *sample, struct event_key *key);
- void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key,
- char decode[20]);
- const char *name;
-};
-
-struct exit_reasons_table {
- unsigned long exit_code;
- const char *reason;
-};
-
-#define EVENTS_BITS 12
-#define EVENTS_CACHE_SIZE (1UL << EVENTS_BITS)
-
-struct perf_kvm_stat {
- struct perf_tool tool;
- struct record_opts opts;
- struct perf_evlist *evlist;
- struct perf_session *session;
+#ifdef HAVE_KVM_STAT_SUPPORT
+#include <asm/kvm_perf.h>
+#include "util/kvm-stat.h"
- const char *file_name;
- const char *report_event;
- const char *sort_key;
- int trace_vcpu;
-
- struct exit_reasons_table *exit_reasons;
- int exit_reasons_size;
- const char *exit_reasons_isa;
-
- struct kvm_events_ops *events_ops;
- key_cmp_fun compare;
- struct list_head kvm_events_cache[EVENTS_CACHE_SIZE];
-
- u64 total_time;
- u64 total_count;
- u64 lost_events;
- u64 duration;
-
- const char *pid_str;
- struct intlist *pid_list;
-
- struct rb_root result;
-
- int timerfd;
- unsigned int display_time;
- bool live;
-};
-
-
-static void exit_event_get_key(struct perf_evsel *evsel,
- struct perf_sample *sample,
- struct event_key *key)
+void exit_event_get_key(struct perf_evsel *evsel,
+ struct perf_sample *sample,
+ struct event_key *key)
{
key->info = 0;
- key->key = perf_evsel__intval(evsel, sample, "exit_reason");
+ key->key = perf_evsel__intval(evsel, sample, KVM_EXIT_REASON);
}
-static bool kvm_exit_event(struct perf_evsel *evsel)
+bool kvm_exit_event(struct perf_evsel *evsel)
{
- return !strcmp(evsel->name, "kvm:kvm_exit");
+ return !strcmp(evsel->name, KVM_EXIT_TRACE);
}
-static bool exit_event_begin(struct perf_evsel *evsel,
- struct perf_sample *sample, struct event_key *key)
+bool exit_event_begin(struct perf_evsel *evsel,
+ struct perf_sample *sample, struct event_key *key)
{
if (kvm_exit_event(evsel)) {
exit_event_get_key(evsel, sample, key);
@@ -146,32 +57,23 @@ static bool exit_event_begin(struct perf_evsel *evsel,
return false;
}
-static bool kvm_entry_event(struct perf_evsel *evsel)
+bool kvm_entry_event(struct perf_evsel *evsel)
{
- return !strcmp(evsel->name, "kvm:kvm_entry");
+ return !strcmp(evsel->name, KVM_ENTRY_TRACE);
}
-static bool exit_event_end(struct perf_evsel *evsel,
- struct perf_sample *sample __maybe_unused,
- struct event_key *key __maybe_unused)
+bool exit_event_end(struct perf_evsel *evsel,
+ struct perf_sample *sample __maybe_unused,
+ struct event_key *key __maybe_unused)
{
return kvm_entry_event(evsel);
}
-static struct exit_reasons_table vmx_exit_reasons[] = {
- VMX_EXIT_REASONS
-};
-
-static struct exit_reasons_table svm_exit_reasons[] = {
- SVM_EXIT_REASONS
-};
-
-static const char *get_exit_reason(struct perf_kvm_stat *kvm, u64 exit_code)
+static const char *get_exit_reason(struct perf_kvm_stat *kvm,
+ struct exit_reasons_table *tbl,
+ u64 exit_code)
{
- int i = kvm->exit_reasons_size;
- struct exit_reasons_table *tbl = kvm->exit_reasons;
-
- while (i--) {
+ while (tbl->reason != NULL) {
if (tbl->exit_code == exit_code)
return tbl->reason;
tbl++;
@@ -182,148 +84,30 @@ static const char *get_exit_reason(struct perf_kvm_stat *kvm, u64 exit_code)
return "UNKNOWN";
}
-static void exit_event_decode_key(struct perf_kvm_stat *kvm,
- struct event_key *key,
- char decode[20])
-{
- const char *exit_reason = get_exit_reason(kvm, key->key);
-
- scnprintf(decode, 20, "%s", exit_reason);
-}
-
-static struct kvm_events_ops exit_events = {
- .is_begin_event = exit_event_begin,
- .is_end_event = exit_event_end,
- .decode_key = exit_event_decode_key,
- .name = "VM-EXIT"
-};
-
-/*
- * For the mmio events, we treat:
- * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry
- * the time of MMIO read: kvm_exit -> kvm_mmio(KVM_TRACE_MMIO_READ...).
- */
-static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample,
- struct event_key *key)
-{
- key->key = perf_evsel__intval(evsel, sample, "gpa");
- key->info = perf_evsel__intval(evsel, sample, "type");
-}
-
-#define KVM_TRACE_MMIO_READ_UNSATISFIED 0
-#define KVM_TRACE_MMIO_READ 1
-#define KVM_TRACE_MMIO_WRITE 2
-
-static bool mmio_event_begin(struct perf_evsel *evsel,
- struct perf_sample *sample, struct event_key *key)
+void exit_event_decode_key(struct perf_kvm_stat *kvm,
+ struct event_key *key,
+ char *decode)
{
- /* MMIO read begin event in kernel. */
- if (kvm_exit_event(evsel))
- return true;
-
- /* MMIO write begin event in kernel. */
- if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
- perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) {
- mmio_event_get_key(evsel, sample, key);
- return true;
- }
-
- return false;
-}
-
-static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample,
- struct event_key *key)
-{
- /* MMIO write end event in kernel. */
- if (kvm_entry_event(evsel))
- return true;
-
- /* MMIO read end event in kernel.*/
- if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
- perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) {
- mmio_event_get_key(evsel, sample, key);
- return true;
- }
+ const char *exit_reason = get_exit_reason(kvm, key->exit_reasons,
+ key->key);
- return false;
-}
-
-static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
- struct event_key *key,
- char decode[20])
-{
- scnprintf(decode, 20, "%#lx:%s", (unsigned long)key->key,
- key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R");
+ scnprintf(decode, DECODE_STR_LEN, "%s", exit_reason);
}
-static struct kvm_events_ops mmio_events = {
- .is_begin_event = mmio_event_begin,
- .is_end_event = mmio_event_end,
- .decode_key = mmio_event_decode_key,
- .name = "MMIO Access"
-};
-
- /* The time of emulation pio access is from kvm_pio to kvm_entry. */
-static void ioport_event_get_key(struct perf_evsel *evsel,
- struct perf_sample *sample,
- struct event_key *key)
+static bool register_kvm_events_ops(struct perf_kvm_stat *kvm)
{
- key->key = perf_evsel__intval(evsel, sample, "port");
- key->info = perf_evsel__intval(evsel, sample, "rw");
-}
+ struct kvm_reg_events_ops *events_ops = kvm_reg_events_ops;
-static bool ioport_event_begin(struct perf_evsel *evsel,
- struct perf_sample *sample,
- struct event_key *key)
-{
- if (!strcmp(evsel->name, "kvm:kvm_pio")) {
- ioport_event_get_key(evsel, sample, key);
- return true;
+ for (events_ops = kvm_reg_events_ops; events_ops->name; events_ops++) {
+ if (!strcmp(events_ops->name, kvm->report_event)) {
+ kvm->events_ops = events_ops->ops;
+ return true;
+ }
}
return false;
}
-static bool ioport_event_end(struct perf_evsel *evsel,
- struct perf_sample *sample __maybe_unused,
- struct event_key *key __maybe_unused)
-{
- return kvm_entry_event(evsel);
-}
-
-static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
- struct event_key *key,
- char decode[20])
-{
- scnprintf(decode, 20, "%#llx:%s", (unsigned long long)key->key,
- key->info ? "POUT" : "PIN");
-}
-
-static struct kvm_events_ops ioport_events = {
- .is_begin_event = ioport_event_begin,
- .is_end_event = ioport_event_end,
- .decode_key = ioport_event_decode_key,
- .name = "IO Port Access"
-};
-
-static bool register_kvm_events_ops(struct perf_kvm_stat *kvm)
-{
- bool ret = true;
-
- if (!strcmp(kvm->report_event, "vmexit"))
- kvm->events_ops = &exit_events;
- else if (!strcmp(kvm->report_event, "mmio"))
- kvm->events_ops = &mmio_events;
- else if (!strcmp(kvm->report_event, "ioport"))
- kvm->events_ops = &ioport_events;
- else {
- pr_err("Unknown report event:%s\n", kvm->report_event);
- ret = false;
- }
-
- return ret;
-}
-
struct vcpu_event_record {
int vcpu_id;
u64 start_time;
@@ -477,6 +261,54 @@ static bool update_kvm_event(struct kvm_event *event, int vcpu_id,
return true;
}
+static bool is_child_event(struct perf_kvm_stat *kvm,
+ struct perf_evsel *evsel,
+ struct perf_sample *sample,
+ struct event_key *key)
+{
+ struct child_event_ops *child_ops;
+
+ child_ops = kvm->events_ops->child_ops;
+
+ if (!child_ops)
+ return false;
+
+ for (; child_ops->name; child_ops++) {
+ if (!strcmp(evsel->name, child_ops->name)) {
+ child_ops->get_key(evsel, sample, key);
+ return true;
+ }
+ }
+
+ return false;
+}
+
+static bool handle_child_event(struct perf_kvm_stat *kvm,
+ struct vcpu_event_record *vcpu_record,
+ struct event_key *key,
+ struct perf_sample *sample __maybe_unused)
+{
+ struct kvm_event *event = NULL;
+
+ if (key->key != INVALID_KEY)
+ event = find_create_kvm_event(kvm, key);
+
+ vcpu_record->last_event = event;
+
+ return true;
+}
+
+static bool skip_event(const char *event)
+{
+ const char * const *skip_events;
+
+ for (skip_events = kvm_skip_events; *skip_events; skip_events++)
+ if (!strcmp(event, *skip_events))
+ return true;
+
+ return false;
+}
+
static bool handle_end_event(struct perf_kvm_stat *kvm,
struct vcpu_event_record *vcpu_record,
struct event_key *key,
@@ -525,10 +357,10 @@ static bool handle_end_event(struct perf_kvm_stat *kvm,
time_diff = sample->time - time_begin;
if (kvm->duration && time_diff > kvm->duration) {
- char decode[32];
+ char decode[DECODE_STR_LEN];
kvm->events_ops->decode_key(kvm, &event->key, decode);
- if (strcmp(decode, "HLT")) {
+ if (!skip_event(decode)) {
pr_info("%" PRIu64 " VM %d, vcpu %d: %s event took %" PRIu64 "usec\n",
sample->time, sample->pid, vcpu_record->vcpu_id,
decode, time_diff/1000);
@@ -553,7 +385,7 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread,
return NULL;
}
- vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, "vcpu_id");
+ vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, VCPU_ID);
thread->priv = vcpu_record;
}
@@ -566,7 +398,8 @@ static bool handle_kvm_event(struct perf_kvm_stat *kvm,
struct perf_sample *sample)
{
struct vcpu_event_record *vcpu_record;
- struct event_key key = {.key = INVALID_KEY};
+ struct event_key key = { .key = INVALID_KEY,
+ .exit_reasons = kvm->exit_reasons };
vcpu_record = per_vcpu_record(thread, evsel, sample);
if (!vcpu_record)
@@ -580,6 +413,9 @@ static bool handle_kvm_event(struct perf_kvm_stat *kvm,
if (kvm->events_ops->is_begin_event(evsel, sample, &key))
return handle_begin_event(kvm, vcpu_record, &key, sample->time);
+ if (is_child_event(kvm, evsel, sample, &key))
+ return handle_child_event(kvm, vcpu_record, &key, sample);
+
if (kvm->events_ops->is_end_event(evsel, sample, &key))
return handle_end_event(kvm, vcpu_record, &key, sample);
@@ -707,14 +543,12 @@ static void print_vcpu_info(struct perf_kvm_stat *kvm)
pr_info("Analyze events for ");
- if (kvm->live) {
- if (kvm->opts.target.system_wide)
- pr_info("all VMs, ");
- else if (kvm->opts.target.pid)
- pr_info("pid(s) %s, ", kvm->opts.target.pid);
- else
- pr_info("dazed and confused on what is monitored, ");
- }
+ if (kvm->opts.target.system_wide)
+ pr_info("all VMs, ");
+ else if (kvm->opts.target.pid)
+ pr_info("pid(s) %s, ", kvm->opts.target.pid);
+ else
+ pr_info("dazed and confused on what is monitored, ");
if (vcpu == -1)
pr_info("all VCPUs:\n\n");
@@ -740,7 +574,7 @@ static void show_timeofday(void)
static void print_result(struct perf_kvm_stat *kvm)
{
- char decode[20];
+ char decode[DECODE_STR_LEN];
struct kvm_event *event;
int vcpu = kvm->trace_vcpu;
@@ -751,13 +585,13 @@ static void print_result(struct perf_kvm_stat *kvm)
pr_info("\n\n");
print_vcpu_info(kvm);
- pr_info("%20s ", kvm->events_ops->name);
+ pr_info("%*s ", DECODE_STR_LEN, kvm->events_ops->name);
pr_info("%10s ", "Samples");
pr_info("%9s ", "Samples%");
pr_info("%9s ", "Time%");
- pr_info("%10s ", "Min Time");
- pr_info("%10s ", "Max Time");
+ pr_info("%11s ", "Min Time");
+ pr_info("%11s ", "Max Time");
pr_info("%16s ", "Avg time");
pr_info("\n\n");
@@ -770,12 +604,12 @@ static void print_result(struct perf_kvm_stat *kvm)
min = get_event_min(event, vcpu);
kvm->events_ops->decode_key(kvm, &event->key, decode);
- pr_info("%20s ", decode);
+ pr_info("%*s ", DECODE_STR_LEN, decode);
pr_info("%10llu ", (unsigned long long)ecount);
pr_info("%8.2f%% ", (double)ecount / kvm->total_count * 100);
pr_info("%8.2f%% ", (double)etime / kvm->total_time * 100);
- pr_info("%8" PRIu64 "us ", min / 1000);
- pr_info("%8" PRIu64 "us ", max / 1000);
+ pr_info("%9.2fus ", (double)min / 1e3);
+ pr_info("%9.2fus ", (double)max / 1e3);
pr_info("%9.2fus ( +-%7.2f%% )", (double)etime / ecount/1e3,
kvm_event_rel_stddev(vcpu, event));
pr_info("\n");
@@ -839,34 +673,28 @@ static int process_sample_event(struct perf_tool *tool,
static int cpu_isa_config(struct perf_kvm_stat *kvm)
{
char buf[64], *cpuid;
- int err, isa;
+ int err;
if (kvm->live) {
err = get_cpuid(buf, sizeof(buf));
if (err != 0) {
- pr_err("Failed to look up CPU type (Intel or AMD)\n");
+ pr_err("Failed to look up CPU type\n");
return err;
}
cpuid = buf;
} else
cpuid = kvm->session->header.env.cpuid;
- if (strstr(cpuid, "Intel"))
- isa = 1;
- else if (strstr(cpuid, "AMD"))
- isa = 0;
- else {
- pr_err("CPU %s is not supported.\n", cpuid);
- return -ENOTSUP;
+ if (!cpuid) {
+ pr_err("Failed to look up CPU type\n");
+ return -EINVAL;
}
- if (isa == 1) {
- kvm->exit_reasons = vmx_exit_reasons;
- kvm->exit_reasons_size = ARRAY_SIZE(vmx_exit_reasons);
- kvm->exit_reasons_isa = "VMX";
- }
+ err = cpu_isa_init(kvm, cpuid);
+ if (err == -ENOTSUP)
+ pr_err("CPU %s is not supported.\n", cpuid);
- return 0;
+ return err;
}
static bool verify_vcpu(int vcpu)
@@ -902,7 +730,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
return -1;
}
- err = perf_session_queue_event(kvm->session, event, &sample, 0);
+ err = perf_session_queue_event(kvm->session, event, &kvm->tool, &sample, 0);
/*
* FIXME: Here we can't consume the event, as perf_session_queue_event will
* point to it, and it'll get possibly overwritten by the kernel.
@@ -955,7 +783,7 @@ static int perf_kvm__mmap_read(struct perf_kvm_stat *kvm)
/* flush queue after each round in which we processed events */
if (ntotal) {
- kvm->session->ordered_samples.next_flush = flush_time;
+ kvm->session->ordered_events.next_flush = flush_time;
err = kvm->tool.finished_round(&kvm->tool, NULL, kvm->session);
if (err) {
if (kvm->lost_events)
@@ -1055,15 +883,11 @@ static int fd_set_nonblock(int fd)
return 0;
}
-static
-int perf_kvm__handle_stdin(struct termios *tc_now, struct termios *tc_save)
+static int perf_kvm__handle_stdin(void)
{
int c;
- tcsetattr(0, TCSANOW, tc_now);
c = getc(stdin);
- tcsetattr(0, TCSAFLUSH, tc_save);
-
if (c == 'q')
return 1;
@@ -1074,7 +898,7 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm)
{
struct pollfd *pollfds = NULL;
int nr_fds, nr_stdin, ret, err = -EINVAL;
- struct termios tc, save;
+ struct termios save;
/* live flag must be set first */
kvm->live = true;
@@ -1089,26 +913,14 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm)
goto out;
}
+ set_term_quiet_input(&save);
init_kvm_event_record(kvm);
- tcgetattr(0, &save);
- tc = save;
- tc.c_lflag &= ~(ICANON | ECHO);
- tc.c_cc[VMIN] = 0;
- tc.c_cc[VTIME] = 0;
-
signal(SIGINT, sig_handler);
signal(SIGTERM, sig_handler);
- /* copy pollfds -- need to add timerfd and stdin */
- nr_fds = kvm->evlist->nr_fds;
- pollfds = zalloc(sizeof(struct pollfd) * (nr_fds + 2));
- if (!pollfds) {
- err = -ENOMEM;
- goto out;
- }
- memcpy(pollfds, kvm->evlist->pollfd,
- sizeof(struct pollfd) * kvm->evlist->nr_fds);
+ /* use pollfds -- need to add timerfd and stdin */
+ nr_fds = kvm->evlist->pollfd.nr;
/* add timer fd */
if (perf_kvm__timerfd_create(kvm) < 0) {
@@ -1116,17 +928,21 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm)
goto out;
}
- pollfds[nr_fds].fd = kvm->timerfd;
- pollfds[nr_fds].events = POLLIN;
+ if (perf_evlist__add_pollfd(kvm->evlist, kvm->timerfd))
+ goto out;
+
nr_fds++;
- pollfds[nr_fds].fd = fileno(stdin);
- pollfds[nr_fds].events = POLLIN;
+ if (perf_evlist__add_pollfd(kvm->evlist, fileno(stdin)))
+ goto out;
+
nr_stdin = nr_fds;
nr_fds++;
if (fd_set_nonblock(fileno(stdin)) != 0)
goto out;
+ pollfds = kvm->evlist->pollfd.entries;
+
/* everything is good - enable the events and process */
perf_evlist__enable(kvm->evlist);
@@ -1142,7 +958,7 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm)
goto out;
if (pollfds[nr_stdin].revents & POLLIN)
- done = perf_kvm__handle_stdin(&tc, &save);
+ done = perf_kvm__handle_stdin();
if (!rc && !done)
err = poll(pollfds, nr_fds, 100);
@@ -1159,7 +975,7 @@ out:
if (kvm->timerfd >= 0)
close(kvm->timerfd);
- free(pollfds);
+ tcsetattr(0, TCSAFLUSH, &save);
return err;
}
@@ -1168,6 +984,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
int err, rc = -1;
struct perf_evsel *pos;
struct perf_evlist *evlist = kvm->evlist;
+ char sbuf[STRERR_BUFSIZE];
perf_evlist__config(evlist, &kvm->opts);
@@ -1204,12 +1021,14 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
err = perf_evlist__open(evlist);
if (err < 0) {
- printf("Couldn't create the events: %s\n", strerror(errno));
+ printf("Couldn't create the events: %s\n",
+ strerror_r(errno, sbuf, sizeof(sbuf)));
goto out;
}
if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages, false) < 0) {
- ui__error("Failed to mmap the events: %s\n", strerror(errno));
+ ui__error("Failed to mmap the events: %s\n",
+ strerror_r(errno, sbuf, sizeof(sbuf)));
perf_evlist__close(evlist);
goto out;
}
@@ -1228,7 +1047,7 @@ static int read_events(struct perf_kvm_stat *kvm)
struct perf_tool eops = {
.sample = process_sample_event,
.comm = perf_event__process_comm,
- .ordered_samples = true,
+ .ordered_events = true,
};
struct perf_data_file file = {
.path = kvm->file_name,
@@ -1239,9 +1058,11 @@ static int read_events(struct perf_kvm_stat *kvm)
kvm->session = perf_session__new(&file, false, &kvm->tool);
if (!kvm->session) {
pr_err("Initializing perf session failed\n");
- return -EINVAL;
+ return -1;
}
+ symbol__init(&kvm->session->header.env);
+
if (!perf_session__has_traces(kvm->session, "kvm record"))
return -EINVAL;
@@ -1258,8 +1079,8 @@ static int read_events(struct perf_kvm_stat *kvm)
static int parse_target_str(struct perf_kvm_stat *kvm)
{
- if (kvm->pid_str) {
- kvm->pid_list = intlist__new(kvm->pid_str);
+ if (kvm->opts.target.pid) {
+ kvm->pid_list = intlist__new(kvm->opts.target.pid);
if (kvm->pid_list == NULL) {
pr_err("Error parsing process id string\n");
return -EINVAL;
@@ -1300,13 +1121,6 @@ exit:
return ret;
}
-static const char * const kvm_events_tp[] = {
- "kvm:kvm_entry",
- "kvm:kvm_exit",
- "kvm:kvm_mmio",
- "kvm:kvm_pio",
-};
-
#define STRDUP_FAIL_EXIT(s) \
({ char *_p; \
_p = strdup(s); \
@@ -1318,7 +1132,7 @@ static const char * const kvm_events_tp[] = {
static int
kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
{
- unsigned int rec_argc, i, j;
+ unsigned int rec_argc, i, j, events_tp_size;
const char **rec_argv;
const char * const record_args[] = {
"record",
@@ -1326,9 +1140,14 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
"-m", "1024",
"-c", "1",
};
+ const char * const *events_tp;
+ events_tp_size = 0;
+
+ for (events_tp = kvm_events_tp; *events_tp; events_tp++)
+ events_tp_size++;
rec_argc = ARRAY_SIZE(record_args) + argc + 2 +
- 2 * ARRAY_SIZE(kvm_events_tp);
+ 2 * events_tp_size;
rec_argv = calloc(rec_argc + 1, sizeof(char *));
if (rec_argv == NULL)
@@ -1337,7 +1156,7 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
for (i = 0; i < ARRAY_SIZE(record_args); i++)
rec_argv[i] = STRDUP_FAIL_EXIT(record_args[i]);
- for (j = 0; j < ARRAY_SIZE(kvm_events_tp); j++) {
+ for (j = 0; j < events_tp_size; j++) {
rec_argv[i++] = "-e";
rec_argv[i++] = STRDUP_FAIL_EXIT(kvm_events_tp[j]);
}
@@ -1356,13 +1175,14 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv)
{
const struct option kvm_events_report_options[] = {
OPT_STRING(0, "event", &kvm->report_event, "report event",
- "event for reporting: vmexit, mmio, ioport"),
+ "event for reporting: vmexit, "
+ "mmio (x86 only), ioport (x86 only)"),
OPT_INTEGER(0, "vcpu", &kvm->trace_vcpu,
"vcpu id to report"),
OPT_STRING('k', "key", &kvm->sort_key, "sort-key",
"key for sorting: sample(sort by samples number)"
" time (sort by avg time)"),
- OPT_STRING('p', "pid", &kvm->pid_str, "pid",
+ OPT_STRING('p', "pid", &kvm->opts.target.pid, "pid",
"analyze events only for given process id(s)"),
OPT_END()
};
@@ -1372,8 +1192,6 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv)
NULL
};
- symbol__init();
-
if (argc) {
argc = parse_options(argc, argv,
kvm_events_report_options,
@@ -1383,6 +1201,9 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv)
kvm_events_report_options);
}
+ if (!kvm->opts.target.pid)
+ kvm->opts.target.system_wide = true;
+
return kvm_events_report_vcpu(kvm);
}
@@ -1391,16 +1212,16 @@ static struct perf_evlist *kvm_live_event_list(void)
{
struct perf_evlist *evlist;
char *tp, *name, *sys;
- unsigned int j;
int err = -1;
+ const char * const *events_tp;
evlist = perf_evlist__new();
if (evlist == NULL)
return NULL;
- for (j = 0; j < ARRAY_SIZE(kvm_events_tp); j++) {
+ for (events_tp = kvm_events_tp; *events_tp; events_tp++) {
- tp = strdup(kvm_events_tp[j]);
+ tp = strdup(*events_tp);
if (tp == NULL)
goto out;
@@ -1409,7 +1230,7 @@ static struct perf_evlist *kvm_live_event_list(void)
name = strchr(tp, ':');
if (name == NULL) {
pr_err("Error parsing %s tracepoint: subsystem delimiter not found\n",
- kvm_events_tp[j]);
+ *events_tp);
free(tp);
goto out;
}
@@ -1417,7 +1238,7 @@ static struct perf_evlist *kvm_live_event_list(void)
name++;
if (perf_evlist__add_newtp(evlist, sys, name, NULL)) {
- pr_err("Failed to add %s tracepoint to the list\n", kvm_events_tp[j]);
+ pr_err("Failed to add %s tracepoint to the list\n", *events_tp);
free(tp);
goto out;
}
@@ -1462,7 +1283,9 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
"key for sorting: sample(sort by samples number)"
" time (sort by avg time)"),
OPT_U64(0, "duration", &kvm->duration,
- "show events other than HALT that take longer than duration usecs"),
+ "show events other than"
+ " HLT (x86 only) or Wait state (s390 only)"
+ " that take longer than duration usecs"),
OPT_END()
};
const char * const live_usage[] = {
@@ -1480,7 +1303,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
kvm->tool.exit = perf_event__process_exit;
kvm->tool.fork = perf_event__process_fork;
kvm->tool.lost = process_lost_event;
- kvm->tool.ordered_samples = true;
+ kvm->tool.ordered_events = true;
perf_tool__fill_defaults(&kvm->tool);
/* set defaults */
@@ -1491,7 +1314,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
kvm->opts.target.uid_str = NULL;
kvm->opts.target.uid = UINT_MAX;
- symbol__init();
+ symbol__init(NULL);
disable_buildid_cache();
use_browser = 0;
@@ -1538,7 +1361,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
*/
kvm->session = perf_session__new(&file, false, &kvm->tool);
if (kvm->session == NULL) {
- err = -ENOMEM;
+ err = -1;
goto out;
}
kvm->session->evlist = kvm->evlist;
@@ -1585,9 +1408,6 @@ static int kvm_cmd_stat(const char *file_name, int argc, const char **argv)
.report_event = "vmexit",
.sort_key = "sample",
- .exit_reasons = svm_exit_reasons,
- .exit_reasons_size = ARRAY_SIZE(svm_exit_reasons),
- .exit_reasons_isa = "SVM",
};
if (argc == 1) {
@@ -1609,7 +1429,7 @@ static int kvm_cmd_stat(const char *file_name, int argc, const char **argv)
perf_stat:
return cmd_stat(argc, argv, NULL);
}
-#endif
+#endif /* HAVE_KVM_STAT_SUPPORT */
static int __cmd_record(const char *file_name, int argc, const char **argv)
{
@@ -1726,7 +1546,7 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
return cmd_top(argc, argv, NULL);
else if (!strncmp(argv[0], "buildid-list", 12))
return __cmd_buildid_list(file_name, argc, argv);
-#if defined(__i386__) || defined(__x86_64__)
+#ifdef HAVE_KVM_STAT_SUPPORT
else if (!strncmp(argv[0], "stat", 4))
return kvm_cmd_stat(file_name, argc, argv);
#endif
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 6148afc995c6..e7ec71589da6 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -852,7 +852,7 @@ static int __cmd_report(bool display_info)
struct perf_tool eops = {
.sample = process_sample_event,
.comm = perf_event__process_comm,
- .ordered_samples = true,
+ .ordered_events = true,
};
struct perf_data_file file = {
.path = input_name,
@@ -862,9 +862,11 @@ static int __cmd_report(bool display_info)
session = perf_session__new(&file, false, &eops);
if (!session) {
pr_err("Initializing perf session failed\n");
- return -ENOMEM;
+ return -1;
}
+ symbol__init(&session->header.env);
+
if (!perf_session__has_traces(session, "lock record"))
goto out_delete;
@@ -974,7 +976,6 @@ int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused)
unsigned int i;
int rc = 0;
- symbol__init();
for (i = 0; i < LOCKHASH_SIZE; i++)
INIT_LIST_HEAD(lockhash_table + i);
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 4a1a6c94a5eb..24db6ffe2957 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -124,7 +124,7 @@ static int report_raw_events(struct perf_mem *mem)
&mem->tool);
if (session == NULL)
- return -ENOMEM;
+ return -1;
if (mem->cpu_list) {
ret = perf_session__cpu_bitmap(session, mem->cpu_list,
@@ -133,7 +133,7 @@ static int report_raw_events(struct perf_mem *mem)
goto out_delete;
}
- if (symbol__init() < 0)
+ if (symbol__init(&session->header.env) < 0)
return -1;
printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
@@ -194,7 +194,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
.lost = perf_event__process_lost,
.fork = perf_event__process_fork,
.build_id = perf_event__process_build_id,
- .ordered_samples = true,
+ .ordered_events = true,
},
.input_name = "perf.data",
};
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index c63fa2925075..04412b4770a2 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -290,8 +290,11 @@ static void cleanup_params(void)
static void pr_err_with_code(const char *msg, int err)
{
+ char sbuf[STRERR_BUFSIZE];
+
pr_err("%s", msg);
- pr_debug(" Reason: %s (Code: %d)", strerror(-err), err);
+ pr_debug(" Reason: %s (Code: %d)",
+ strerror_r(-err, sbuf, sizeof(sbuf)), err);
pr_err("\n");
}
@@ -373,6 +376,8 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
"target executable name or path", opt_set_target),
OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
"Disable symbol demangling"),
+ OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
+ "Enable kernel symbol demangling"),
OPT_END()
};
int ret;
@@ -467,7 +472,8 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
usage_with_options(probe_usage, options);
}
- ret = show_line_range(&params.line_range, params.target);
+ ret = show_line_range(&params.line_range, params.target,
+ params.uprobes);
if (ret < 0)
pr_err_with_code(" Error: Failed to show lines.", ret);
return ret;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 378b85b731a7..44c6f3d55ce7 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -65,8 +65,9 @@ static int process_synthesized_event(struct perf_tool *tool,
return record__write(rec, event, event->header.size);
}
-static int record__mmap_read(struct record *rec, struct perf_mmap *md)
+static int record__mmap_read(struct record *rec, int idx)
{
+ struct perf_mmap *md = &rec->evlist->mmap[idx];
unsigned int head = perf_mmap__read_head(md);
unsigned int old = md->prev;
unsigned char *data = md->base + page_size;
@@ -102,8 +103,7 @@ static int record__mmap_read(struct record *rec, struct perf_mmap *md)
}
md->prev = old;
- perf_mmap__write_tail(md, old);
-
+ perf_evlist__mmap_consume(rec->evlist, idx);
out:
return rc;
}
@@ -161,7 +161,7 @@ try_again:
if (perf_evlist__apply_filters(evlist)) {
error("failed to set filter with %d (%s)\n", errno,
- strerror(errno));
+ strerror_r(errno, msg, sizeof(msg)));
rc = -1;
goto out;
}
@@ -175,7 +175,8 @@ try_again:
"(current value: %u)\n", opts->mmap_pages);
rc = -errno;
} else {
- pr_err("failed to mmap with %d (%s)\n", errno, strerror(errno));
+ pr_err("failed to mmap with %d (%s)\n", errno,
+ strerror_r(errno, msg, sizeof(msg)));
rc = -errno;
}
goto out;
@@ -238,19 +239,24 @@ static struct perf_event_header finished_round_event = {
static int record__mmap_read_all(struct record *rec)
{
+ u64 bytes_written = rec->bytes_written;
int i;
int rc = 0;
for (i = 0; i < rec->evlist->nr_mmaps; i++) {
if (rec->evlist->mmap[i].base) {
- if (record__mmap_read(rec, &rec->evlist->mmap[i]) != 0) {
+ if (record__mmap_read(rec, i) != 0) {
rc = -1;
goto out;
}
}
}
- if (perf_header__has_feat(&rec->session->header, HEADER_TRACING_DATA))
+ /*
+ * Mark the round finished in case we wrote
+ * at least one event.
+ */
+ if (bytes_written != rec->bytes_written)
rc = record__write(rec, &finished_round_event, sizeof(finished_round_event));
out:
@@ -302,7 +308,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
struct record_opts *opts = &rec->opts;
struct perf_data_file *file = &rec->file;
struct perf_session *session;
- bool disabled = false;
+ bool disabled = false, draining = false;
rec->progname = argv[0];
@@ -451,9 +457,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
}
if (hits == rec->samples) {
- if (done)
+ if (done || draining)
break;
- err = poll(rec->evlist->pollfd, rec->evlist->nr_fds, -1);
+ err = perf_evlist__poll(rec->evlist, -1);
/*
* Propagate error, only if there's any. Ignore positive
* number of returned events and interrupt error.
@@ -461,6 +467,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
if (err > 0 || (err < 0 && errno == EINTR))
err = 0;
waking++;
+
+ if (perf_evlist__filter_pollfd(rec->evlist, POLLERR | POLLHUP) == 0)
+ draining = true;
}
/*
@@ -475,7 +484,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
}
if (forks && workload_exec_errno) {
- char msg[512];
+ char msg[STRERR_BUFSIZE];
const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg));
pr_err("Workload failed: %s\n", emsg);
err = -1;
@@ -615,145 +624,56 @@ error:
return ret;
}
-#ifdef HAVE_DWARF_UNWIND_SUPPORT
-static int get_stack_size(char *str, unsigned long *_size)
-{
- char *endptr;
- unsigned long size;
- unsigned long max_size = round_down(USHRT_MAX, sizeof(u64));
-
- size = strtoul(str, &endptr, 0);
-
- do {
- if (*endptr)
- break;
-
- size = round_up(size, sizeof(u64));
- if (!size || size > max_size)
- break;
-
- *_size = size;
- return 0;
-
- } while (0);
-
- pr_err("callchain: Incorrect stack dump size (max %ld): %s\n",
- max_size, str);
- return -1;
-}
-#endif /* HAVE_DWARF_UNWIND_SUPPORT */
-
-int record_parse_callchain(const char *arg, struct record_opts *opts)
-{
- char *tok, *name, *saveptr = NULL;
- char *buf;
- int ret = -1;
-
- /* We need buffer that we know we can write to. */
- buf = malloc(strlen(arg) + 1);
- if (!buf)
- return -ENOMEM;
-
- strcpy(buf, arg);
-
- tok = strtok_r((char *)buf, ",", &saveptr);
- name = tok ? : (char *)buf;
-
- do {
- /* Framepointer style */
- if (!strncmp(name, "fp", sizeof("fp"))) {
- if (!strtok_r(NULL, ",", &saveptr)) {
- opts->call_graph = CALLCHAIN_FP;
- ret = 0;
- } else
- pr_err("callchain: No more arguments "
- "needed for -g fp\n");
- break;
-
-#ifdef HAVE_DWARF_UNWIND_SUPPORT
- /* Dwarf style */
- } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
- const unsigned long default_stack_dump_size = 8192;
-
- ret = 0;
- opts->call_graph = CALLCHAIN_DWARF;
- opts->stack_dump_size = default_stack_dump_size;
-
- tok = strtok_r(NULL, ",", &saveptr);
- if (tok) {
- unsigned long size = 0;
-
- ret = get_stack_size(tok, &size);
- opts->stack_dump_size = size;
- }
-#endif /* HAVE_DWARF_UNWIND_SUPPORT */
- } else {
- pr_err("callchain: Unknown --call-graph option "
- "value: %s\n", arg);
- break;
- }
-
- } while (0);
-
- free(buf);
- return ret;
-}
-
-static void callchain_debug(struct record_opts *opts)
+static void callchain_debug(void)
{
static const char *str[CALLCHAIN_MAX] = { "NONE", "FP", "DWARF" };
- pr_debug("callchain: type %s\n", str[opts->call_graph]);
+ pr_debug("callchain: type %s\n", str[callchain_param.record_mode]);
- if (opts->call_graph == CALLCHAIN_DWARF)
+ if (callchain_param.record_mode == CALLCHAIN_DWARF)
pr_debug("callchain: stack dump size %d\n",
- opts->stack_dump_size);
+ callchain_param.dump_size);
}
-int record_parse_callchain_opt(const struct option *opt,
+int record_parse_callchain_opt(const struct option *opt __maybe_unused,
const char *arg,
int unset)
{
- struct record_opts *opts = opt->value;
int ret;
- opts->call_graph_enabled = !unset;
+ callchain_param.enabled = !unset;
/* --no-call-graph */
if (unset) {
- opts->call_graph = CALLCHAIN_NONE;
+ callchain_param.record_mode = CALLCHAIN_NONE;
pr_debug("callchain: disabled\n");
return 0;
}
- ret = record_parse_callchain(arg, opts);
+ ret = parse_callchain_record_opt(arg);
if (!ret)
- callchain_debug(opts);
+ callchain_debug();
return ret;
}
-int record_callchain_opt(const struct option *opt,
+int record_callchain_opt(const struct option *opt __maybe_unused,
const char *arg __maybe_unused,
int unset __maybe_unused)
{
- struct record_opts *opts = opt->value;
+ callchain_param.enabled = true;
- opts->call_graph_enabled = !unset;
+ if (callchain_param.record_mode == CALLCHAIN_NONE)
+ callchain_param.record_mode = CALLCHAIN_FP;
- if (opts->call_graph == CALLCHAIN_NONE)
- opts->call_graph = CALLCHAIN_FP;
-
- callchain_debug(opts);
+ callchain_debug();
return 0;
}
static int perf_record_config(const char *var, const char *value, void *cb)
{
- struct record *rec = cb;
-
if (!strcmp(var, "record.call-graph"))
- return record_parse_callchain(value, &rec->opts);
+ var = "call-graph.record-mode"; /* fall-through */
return perf_default_config(var, value, cb);
}
@@ -776,6 +696,7 @@ static const char * const record_usage[] = {
*/
static struct record record = {
.opts = {
+ .sample_time = true,
.mmap_pages = UINT_MAX,
.user_freq = UINT_MAX,
.user_interval = ULLONG_MAX,
@@ -902,7 +823,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
usage_with_options(record_usage, record_options);
}
- symbol__init();
+ symbol__init(NULL);
if (symbol_conf.kptr_restrict)
pr_warning(
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 21d830bafff3..ac145fae0521 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -58,17 +58,19 @@ struct report {
const char *symbol_filter_str;
float min_percent;
u64 nr_entries;
+ u64 queue_size;
DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
};
static int report__config(const char *var, const char *value, void *cb)
{
+ struct report *rep = cb;
+
if (!strcmp(var, "report.group")) {
symbol_conf.event_group = perf_config_bool(var, value);
return 0;
}
if (!strcmp(var, "report.percent-limit")) {
- struct report *rep = cb;
rep->min_percent = strtof(value, NULL);
return 0;
}
@@ -76,6 +78,10 @@ static int report__config(const char *var, const char *value, void *cb)
symbol_conf.cumulate_callchain = perf_config_bool(var, value);
return 0;
}
+ if (!strcmp(var, "report.queue-size")) {
+ rep->queue_size = perf_config_u64(var, value);
+ return 0;
+ }
return perf_default_config(var, value, cb);
}
@@ -578,7 +584,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
.attr = perf_event__process_attr,
.tracing_data = perf_event__process_tracing_data,
.build_id = perf_event__process_build_id,
- .ordered_samples = true,
+ .ordered_events = true,
.ordering_requires_timestamps = true,
},
.max_stack = PERF_MAX_STACK_DEPTH,
@@ -674,6 +680,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
"objdump binary to use for disassembly and annotations"),
OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
"Disable symbol demangling"),
+ OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
+ "Enable kernel symbol demangling"),
OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"),
OPT_CALLBACK(0, "percent-limit", &report, "percent",
"Don't show entries under that percent", parse_percent_limit),
@@ -712,14 +720,19 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
repeat:
session = perf_session__new(&file, false, &report.tool);
if (session == NULL)
- return -ENOMEM;
+ return -1;
+
+ if (report.queue_size) {
+ ordered_events__set_alloc_size(&session->ordered_events,
+ report.queue_size);
+ }
report.session = session;
has_br_stack = perf_header__has_feat(&session->header,
HEADER_BRANCH_STACK);
- if (branch_mode == -1 && has_br_stack) {
+ if ((branch_mode == -1 && has_br_stack) || branch_mode == 1) {
sort__mode = SORT_MODE__BRANCH;
symbol_conf.cumulate_callchain = false;
}
@@ -787,7 +800,7 @@ repeat:
}
}
- if (symbol__init() < 0)
+ if (symbol__init(&session->header.env) < 0)
goto error;
if (argc) {
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index c38d06c04775..9c9287fbf8e9 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -10,6 +10,7 @@
#include "util/header.h"
#include "util/session.h"
#include "util/tool.h"
+#include "util/cloexec.h"
#include "util/parse-options.h"
#include "util/trace-event.h"
@@ -427,6 +428,7 @@ static u64 get_cpu_usage_nsec_parent(void)
static int self_open_counters(void)
{
struct perf_event_attr attr;
+ char sbuf[STRERR_BUFSIZE];
int fd;
memset(&attr, 0, sizeof(attr));
@@ -434,11 +436,13 @@ static int self_open_counters(void)
attr.type = PERF_TYPE_SOFTWARE;
attr.config = PERF_COUNT_SW_TASK_CLOCK;
- fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
+ fd = sys_perf_event_open(&attr, 0, -1, -1,
+ perf_event_open_cloexec_flag());
if (fd < 0)
pr_err("Error: sys_perf_event_open() syscall returned "
- "with %d (%s)\n", fd, strerror(errno));
+ "with %d (%s)\n", fd,
+ strerror_r(errno, sbuf, sizeof(sbuf)));
return fd;
}
@@ -935,8 +939,8 @@ static int latency_switch_event(struct perf_sched *sched,
return -1;
}
- sched_out = machine__findnew_thread(machine, 0, prev_pid);
- sched_in = machine__findnew_thread(machine, 0, next_pid);
+ sched_out = machine__findnew_thread(machine, -1, prev_pid);
+ sched_in = machine__findnew_thread(machine, -1, next_pid);
out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid);
if (!out_events) {
@@ -979,7 +983,7 @@ static int latency_runtime_event(struct perf_sched *sched,
{
const u32 pid = perf_evsel__intval(evsel, sample, "pid");
const u64 runtime = perf_evsel__intval(evsel, sample, "runtime");
- struct thread *thread = machine__findnew_thread(machine, 0, pid);
+ struct thread *thread = machine__findnew_thread(machine, -1, pid);
struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
u64 timestamp = sample->time;
int cpu = sample->cpu;
@@ -1012,7 +1016,7 @@ static int latency_wakeup_event(struct perf_sched *sched,
struct thread *wakee;
u64 timestamp = sample->time;
- wakee = machine__findnew_thread(machine, 0, pid);
+ wakee = machine__findnew_thread(machine, -1, pid);
atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid);
if (!atoms) {
if (thread_atoms_insert(sched, wakee))
@@ -1072,7 +1076,7 @@ static int latency_migrate_task_event(struct perf_sched *sched,
if (sched->profile_cpu == -1)
return 0;
- migrant = machine__findnew_thread(machine, 0, pid);
+ migrant = machine__findnew_thread(machine, -1, pid);
atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
if (!atoms) {
if (thread_atoms_insert(sched, migrant))
@@ -1290,7 +1294,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
return -1;
}
- sched_in = machine__findnew_thread(machine, 0, next_pid);
+ sched_in = machine__findnew_thread(machine, -1, next_pid);
sched->curr_thread[this_cpu] = sched_in;
@@ -1460,6 +1464,8 @@ static int perf_sched__read_events(struct perf_sched *sched,
return -1;
}
+ symbol__init(&session->header.env);
+
if (perf_session__set_tracepoints_handlers(session, handlers))
goto out_delete;
@@ -1660,7 +1666,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
.comm = perf_event__process_comm,
.lost = perf_event__process_lost,
.fork = perf_sched__process_fork_event,
- .ordered_samples = true,
+ .ordered_events = true,
},
.cmp_pid = LIST_HEAD_INIT(sched.cmp_pid),
.sort_list = LIST_HEAD_INIT(sched.sort_list),
@@ -1745,7 +1751,6 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
if (!strcmp(argv[0], "script"))
return cmd_script(argc, argv, prefix);
- symbol__init();
if (!strncmp(argv[0], "rec", 3)) {
return __cmd_record(argc, argv);
} else if (!strncmp(argv[0], "lat", 3)) {
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 9e9c91f5b7fa..b9b9e58a6c39 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -184,10 +184,6 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
if (perf_evsel__check_stype(evsel, PERF_SAMPLE_IP, "IP",
PERF_OUTPUT_IP))
return -EINVAL;
-
- if (!no_callchain &&
- !(attr->sample_type & PERF_SAMPLE_CALLCHAIN))
- symbol_conf.use_callchain = false;
}
if (PRINT_FIELD(ADDR) &&
@@ -290,6 +286,19 @@ static int perf_session__check_output_opt(struct perf_session *session)
set_print_ip_opts(&evsel->attr);
}
+ if (!no_callchain) {
+ bool use_callchain = false;
+
+ evlist__for_each(session->evlist, evsel) {
+ if (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
+ use_callchain = true;
+ break;
+ }
+ }
+ if (!use_callchain)
+ symbol_conf.use_callchain = false;
+ }
+
/*
* set default for tracepoints to print symbols only
* if callchains are present
@@ -358,27 +367,6 @@ static void print_sample_start(struct perf_sample *sample,
}
}
-static bool is_bts_event(struct perf_event_attr *attr)
-{
- return ((attr->type == PERF_TYPE_HARDWARE) &&
- (attr->config & PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
- (attr->sample_period == 1));
-}
-
-static bool sample_addr_correlates_sym(struct perf_event_attr *attr)
-{
- if ((attr->type == PERF_TYPE_SOFTWARE) &&
- ((attr->config == PERF_COUNT_SW_PAGE_FAULTS) ||
- (attr->config == PERF_COUNT_SW_PAGE_FAULTS_MIN) ||
- (attr->config == PERF_COUNT_SW_PAGE_FAULTS_MAJ)))
- return true;
-
- if (is_bts_event(attr))
- return true;
-
- return false;
-}
-
static void print_sample_addr(union perf_event *event,
struct perf_sample *sample,
struct machine *machine,
@@ -386,24 +374,13 @@ static void print_sample_addr(union perf_event *event,
struct perf_event_attr *attr)
{
struct addr_location al;
- u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
printf("%16" PRIx64, sample->addr);
if (!sample_addr_correlates_sym(attr))
return;
- thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
- sample->addr, &al);
- if (!al.map)
- thread__find_addr_map(thread, machine, cpumode, MAP__VARIABLE,
- sample->addr, &al);
-
- al.cpu = sample->cpu;
- al.sym = NULL;
-
- if (al.map)
- al.sym = map__find_symbol(al.map, al.addr, NULL);
+ perf_event__preprocess_sample_addr(event, sample, machine, thread, &al);
if (PRINT_FIELD(SYM)) {
printf(" ");
@@ -427,25 +404,35 @@ static void print_sample_bts(union perf_event *event,
struct addr_location *al)
{
struct perf_event_attr *attr = &evsel->attr;
+ bool print_srcline_last = false;
/* print branch_from information */
if (PRINT_FIELD(IP)) {
- if (!symbol_conf.use_callchain)
- printf(" ");
- else
+ unsigned int print_opts = output[attr->type].print_ip_opts;
+
+ if (symbol_conf.use_callchain && sample->callchain) {
printf("\n");
- perf_evsel__print_ip(evsel, sample, al,
- output[attr->type].print_ip_opts,
+ } else {
+ printf(" ");
+ if (print_opts & PRINT_IP_OPT_SRCLINE) {
+ print_srcline_last = true;
+ print_opts &= ~PRINT_IP_OPT_SRCLINE;
+ }
+ }
+ perf_evsel__print_ip(evsel, sample, al, print_opts,
PERF_MAX_STACK_DEPTH);
}
- printf(" => ");
-
/* print branch_to information */
if (PRINT_FIELD(ADDR) ||
((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
- !output[attr->type].user_set))
+ !output[attr->type].user_set)) {
+ printf(" => ");
print_sample_addr(event, sample, al->machine, thread, attr);
+ }
+
+ if (print_srcline_last)
+ map__fprintf_srcline(al->map, al->addr, "\n ", stdout);
printf("\n");
}
@@ -498,6 +485,11 @@ static int default_start_script(const char *script __maybe_unused,
return 0;
}
+static int default_flush_script(void)
+{
+ return 0;
+}
+
static int default_stop_script(void)
{
return 0;
@@ -511,6 +503,7 @@ static int default_generate_script(struct pevent *pevent __maybe_unused,
static struct scripting_ops default_scripting_ops = {
.start_script = default_start_script,
+ .flush_script = default_flush_script,
.stop_script = default_stop_script,
.process_event = process_event,
.generate_script = default_generate_script,
@@ -526,6 +519,11 @@ static void setup_scripting(void)
scripting_ops = &default_scripting_ops;
}
+static int flush_scripting(void)
+{
+ return scripting_ops->flush_script();
+}
+
static int cleanup_scripting(void)
{
pr_debug("\nperf script stopped\n");
@@ -1493,12 +1491,13 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
bool show_full_info = false;
bool header = false;
bool header_only = false;
+ bool script_started = false;
char *rec_script_path = NULL;
char *rep_script_path = NULL;
struct perf_session *session;
char *script_path = NULL;
const char **__argv;
- int i, j, err;
+ int i, j, err = 0;
struct perf_script script = {
.tool = {
.sample = process_sample_event,
@@ -1510,7 +1509,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
.attr = process_attr,
.tracing_data = perf_event__process_tracing_data,
.build_id = perf_event__process_build_id,
- .ordered_samples = true,
+ .ordered_events = true,
.ordering_requires_timestamps = true,
},
};
@@ -1740,26 +1739,28 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
exit(-1);
}
- if (symbol__init() < 0)
- return -1;
if (!script_name)
setup_pager();
session = perf_session__new(&file, false, &script.tool);
if (session == NULL)
- return -ENOMEM;
+ return -1;
if (header || header_only) {
perf_session__fprintf_info(session, stdout, show_full_info);
if (header_only)
- return 0;
+ goto out_delete;
}
+ if (symbol__init(&session->header.env) < 0)
+ goto out_delete;
+
script.session = session;
if (cpu_list) {
- if (perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap))
- return -1;
+ err = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap);
+ if (err < 0)
+ goto out_delete;
}
if (!no_callchain)
@@ -1774,53 +1775,62 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
if (output_set_by_user()) {
fprintf(stderr,
"custom fields not supported for generated scripts");
- return -1;
+ err = -EINVAL;
+ goto out_delete;
}
input = open(file.path, O_RDONLY); /* input_name */
if (input < 0) {
+ err = -errno;
perror("failed to open file");
- return -1;
+ goto out_delete;
}
err = fstat(input, &perf_stat);
if (err < 0) {
perror("failed to stat file");
- return -1;
+ goto out_delete;
}
if (!perf_stat.st_size) {
fprintf(stderr, "zero-sized file, nothing to do!\n");
- return 0;
+ goto out_delete;
}
scripting_ops = script_spec__lookup(generate_script_lang);
if (!scripting_ops) {
fprintf(stderr, "invalid language specifier");
- return -1;
+ err = -ENOENT;
+ goto out_delete;
}
err = scripting_ops->generate_script(session->tevent.pevent,
"perf-script");
- goto out;
+ goto out_delete;
}
if (script_name) {
err = scripting_ops->start_script(script_name, argc, argv);
if (err)
- goto out;
+ goto out_delete;
pr_debug("perf script started with script %s\n\n", script_name);
+ script_started = true;
}
err = perf_session__check_output_opt(session);
if (err < 0)
- goto out;
+ goto out_delete;
err = __cmd_script(&script);
+ flush_scripting();
+
+out_delete:
perf_session__delete(session);
- cleanup_scripting();
+
+ if (script_started)
+ cleanup_scripting();
out:
return err;
}
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 65a151e36067..b22c62f80078 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -184,7 +184,7 @@ static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
{
evsel->priv = zalloc(sizeof(struct perf_stat));
- if (evsel == NULL)
+ if (evsel->priv == NULL)
return -ENOMEM;
perf_evsel__reset_stat_priv(evsel);
return 0;
@@ -593,7 +593,7 @@ static int __run_perf_stat(int argc, const char **argv)
if (perf_evlist__apply_filters(evsel_list)) {
error("failed to set filter with %d (%s)\n", errno,
- strerror(errno));
+ strerror_r(errno, msg, sizeof(msg)));
return -1;
}
@@ -732,7 +732,7 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
}
}
-static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
+static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
{
double msecs = avg / 1e6;
const char *fmt_v, *fmt_n;
@@ -741,7 +741,7 @@ static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
fmt_v = csv_output ? "%.6f%s" : "%18.6f%s";
fmt_n = csv_output ? "%s" : "%-25s";
- aggr_printout(evsel, cpu, nr);
+ aggr_printout(evsel, id, nr);
scnprintf(name, sizeof(name), "%s%s",
perf_evsel__name(evsel), csv_output ? "" : " (msec)");
@@ -947,11 +947,12 @@ static void print_ll_cache_misses(int cpu,
fprintf(output, " of all LL-cache hits ");
}
-static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
+static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
{
double total, ratio = 0.0, total2;
double sc = evsel->scale;
const char *fmt;
+ int cpu = cpu_map__id_to_cpu(id);
if (csv_output) {
fmt = sc != 1.0 ? "%.2f%s" : "%.0f%s";
@@ -962,7 +963,7 @@ static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
fmt = sc != 1.0 ? "%18.2f%s" : "%18.0f%s";
}
- aggr_printout(evsel, cpu, nr);
+ aggr_printout(evsel, id, nr);
if (aggr_mode == AGGR_GLOBAL)
cpu = 0;
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 74db2568b867..35b425b6293f 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -37,6 +37,7 @@
#include "util/svghelper.h"
#include "util/tool.h"
#include "util/data.h"
+#include "util/debug.h"
#define SUPPORT_OLD_POWER_EVENTS 1
#define PWR_EVENT_EXIT -1
@@ -60,10 +61,17 @@ struct timechart {
tasks_only,
with_backtrace,
topology;
+ /* IO related settings */
+ u64 io_events;
+ bool io_only,
+ skip_eagain;
+ u64 min_time,
+ merge_dist;
};
struct per_pidcomm;
struct cpu_sample;
+struct io_sample;
/*
* Datastructure layout:
@@ -84,6 +92,7 @@ struct per_pid {
u64 start_time;
u64 end_time;
u64 total_time;
+ u64 total_bytes;
int display;
struct per_pidcomm *all;
@@ -97,6 +106,8 @@ struct per_pidcomm {
u64 start_time;
u64 end_time;
u64 total_time;
+ u64 max_bytes;
+ u64 total_bytes;
int Y;
int display;
@@ -107,6 +118,7 @@ struct per_pidcomm {
char *comm;
struct cpu_sample *samples;
+ struct io_sample *io_samples;
};
struct sample_wrapper {
@@ -131,6 +143,27 @@ struct cpu_sample {
const char *backtrace;
};
+enum {
+ IOTYPE_READ,
+ IOTYPE_WRITE,
+ IOTYPE_SYNC,
+ IOTYPE_TX,
+ IOTYPE_RX,
+ IOTYPE_POLL,
+};
+
+struct io_sample {
+ struct io_sample *next;
+
+ u64 start_time;
+ u64 end_time;
+ u64 bytes;
+ int type;
+ int fd;
+ int err;
+ int merges;
+};
+
#define CSTATE 1
#define PSTATE 2
@@ -213,7 +246,7 @@ static void pid_fork(struct timechart *tchart, int pid, int ppid, u64 timestamp)
pid_set_comm(tchart, pid, pp->current->comm);
p->start_time = timestamp;
- if (p->current) {
+ if (p->current && !p->current->start_time) {
p->current->start_time = timestamp;
p->current->state_since = timestamp;
}
@@ -682,6 +715,249 @@ static void end_sample_processing(struct timechart *tchart)
}
}
+static int pid_begin_io_sample(struct timechart *tchart, int pid, int type,
+ u64 start, int fd)
+{
+ struct per_pid *p = find_create_pid(tchart, pid);
+ struct per_pidcomm *c = p->current;
+ struct io_sample *sample;
+ struct io_sample *prev;
+
+ if (!c) {
+ c = zalloc(sizeof(*c));
+ if (!c)
+ return -ENOMEM;
+ p->current = c;
+ c->next = p->all;
+ p->all = c;
+ }
+
+ prev = c->io_samples;
+
+ if (prev && prev->start_time && !prev->end_time) {
+ pr_warning("Skip invalid start event: "
+ "previous event already started!\n");
+
+ /* remove previous event that has been started,
+ * we are not sure we will ever get an end for it */
+ c->io_samples = prev->next;
+ free(prev);
+ return 0;
+ }
+
+ sample = zalloc(sizeof(*sample));
+ if (!sample)
+ return -ENOMEM;
+ sample->start_time = start;
+ sample->type = type;
+ sample->fd = fd;
+ sample->next = c->io_samples;
+ c->io_samples = sample;
+
+ if (c->start_time == 0 || c->start_time > start)
+ c->start_time = start;
+
+ return 0;
+}
+
+static int pid_end_io_sample(struct timechart *tchart, int pid, int type,
+ u64 end, long ret)
+{
+ struct per_pid *p = find_create_pid(tchart, pid);
+ struct per_pidcomm *c = p->current;
+ struct io_sample *sample, *prev;
+
+ if (!c) {
+ pr_warning("Invalid pidcomm!\n");
+ return -1;
+ }
+
+ sample = c->io_samples;
+
+ if (!sample) /* skip partially captured events */
+ return 0;
+
+ if (sample->end_time) {
+ pr_warning("Skip invalid end event: "
+ "previous event already ended!\n");
+ return 0;
+ }
+
+ if (sample->type != type) {
+ pr_warning("Skip invalid end event: invalid event type!\n");
+ return 0;
+ }
+
+ sample->end_time = end;
+ prev = sample->next;
+
+ /* we want to be able to see small and fast transfers, so make them
+ * at least min_time long, but don't overlap them */
+ if (sample->end_time - sample->start_time < tchart->min_time)
+ sample->end_time = sample->start_time + tchart->min_time;
+ if (prev && sample->start_time < prev->end_time) {
+ if (prev->err) /* try to make errors more visible */
+ sample->start_time = prev->end_time;
+ else
+ prev->end_time = sample->start_time;
+ }
+
+ if (ret < 0) {
+ sample->err = ret;
+ } else if (type == IOTYPE_READ || type == IOTYPE_WRITE ||
+ type == IOTYPE_TX || type == IOTYPE_RX) {
+
+ if ((u64)ret > c->max_bytes)
+ c->max_bytes = ret;
+
+ c->total_bytes += ret;
+ p->total_bytes += ret;
+ sample->bytes = ret;
+ }
+
+ /* merge two requests to make svg smaller and render-friendly */
+ if (prev &&
+ prev->type == sample->type &&
+ prev->err == sample->err &&
+ prev->fd == sample->fd &&
+ prev->end_time + tchart->merge_dist >= sample->start_time) {
+
+ sample->bytes += prev->bytes;
+ sample->merges += prev->merges + 1;
+
+ sample->start_time = prev->start_time;
+ sample->next = prev->next;
+ free(prev);
+
+ if (!sample->err && sample->bytes > c->max_bytes)
+ c->max_bytes = sample->bytes;
+ }
+
+ tchart->io_events++;
+
+ return 0;
+}
+
+static int
+process_enter_read(struct timechart *tchart,
+ struct perf_evsel *evsel,
+ struct perf_sample *sample)
+{
+ long fd = perf_evsel__intval(evsel, sample, "fd");
+ return pid_begin_io_sample(tchart, sample->tid, IOTYPE_READ,
+ sample->time, fd);
+}
+
+static int
+process_exit_read(struct timechart *tchart,
+ struct perf_evsel *evsel,
+ struct perf_sample *sample)
+{
+ long ret = perf_evsel__intval(evsel, sample, "ret");
+ return pid_end_io_sample(tchart, sample->tid, IOTYPE_READ,
+ sample->time, ret);
+}
+
+static int
+process_enter_write(struct timechart *tchart,
+ struct perf_evsel *evsel,
+ struct perf_sample *sample)
+{
+ long fd = perf_evsel__intval(evsel, sample, "fd");
+ return pid_begin_io_sample(tchart, sample->tid, IOTYPE_WRITE,
+ sample->time, fd);
+}
+
+static int
+process_exit_write(struct timechart *tchart,
+ struct perf_evsel *evsel,
+ struct perf_sample *sample)
+{
+ long ret = perf_evsel__intval(evsel, sample, "ret");
+ return pid_end_io_sample(tchart, sample->tid, IOTYPE_WRITE,
+ sample->time, ret);
+}
+
+static int
+process_enter_sync(struct timechart *tchart,
+ struct perf_evsel *evsel,
+ struct perf_sample *sample)
+{
+ long fd = perf_evsel__intval(evsel, sample, "fd");
+ return pid_begin_io_sample(tchart, sample->tid, IOTYPE_SYNC,
+ sample->time, fd);
+}
+
+static int
+process_exit_sync(struct timechart *tchart,
+ struct perf_evsel *evsel,
+ struct perf_sample *sample)
+{
+ long ret = perf_evsel__intval(evsel, sample, "ret");
+ return pid_end_io_sample(tchart, sample->tid, IOTYPE_SYNC,
+ sample->time, ret);
+}
+
+static int
+process_enter_tx(struct timechart *tchart,
+ struct perf_evsel *evsel,
+ struct perf_sample *sample)
+{
+ long fd = perf_evsel__intval(evsel, sample, "fd");
+ return pid_begin_io_sample(tchart, sample->tid, IOTYPE_TX,
+ sample->time, fd);
+}
+
+static int
+process_exit_tx(struct timechart *tchart,
+ struct perf_evsel *evsel,
+ struct perf_sample *sample)
+{
+ long ret = perf_evsel__intval(evsel, sample, "ret");
+ return pid_end_io_sample(tchart, sample->tid, IOTYPE_TX,
+ sample->time, ret);
+}
+
+static int
+process_enter_rx(struct timechart *tchart,
+ struct perf_evsel *evsel,
+ struct perf_sample *sample)
+{
+ long fd = perf_evsel__intval(evsel, sample, "fd");
+ return pid_begin_io_sample(tchart, sample->tid, IOTYPE_RX,
+ sample->time, fd);
+}
+
+static int
+process_exit_rx(struct timechart *tchart,
+ struct perf_evsel *evsel,
+ struct perf_sample *sample)
+{
+ long ret = perf_evsel__intval(evsel, sample, "ret");
+ return pid_end_io_sample(tchart, sample->tid, IOTYPE_RX,
+ sample->time, ret);
+}
+
+static int
+process_enter_poll(struct timechart *tchart,
+ struct perf_evsel *evsel,
+ struct perf_sample *sample)
+{
+ long fd = perf_evsel__intval(evsel, sample, "fd");
+ return pid_begin_io_sample(tchart, sample->tid, IOTYPE_POLL,
+ sample->time, fd);
+}
+
+static int
+process_exit_poll(struct timechart *tchart,
+ struct perf_evsel *evsel,
+ struct perf_sample *sample)
+{
+ long ret = perf_evsel__intval(evsel, sample, "ret");
+ return pid_end_io_sample(tchart, sample->tid, IOTYPE_POLL,
+ sample->time, ret);
+}
+
/*
* Sort the pid datastructure
*/
@@ -852,6 +1128,121 @@ static void draw_cpu_usage(struct timechart *tchart)
}
}
+static void draw_io_bars(struct timechart *tchart)
+{
+ const char *suf;
+ double bytes;
+ char comm[256];
+ struct per_pid *p;
+ struct per_pidcomm *c;
+ struct io_sample *sample;
+ int Y = 1;
+
+ p = tchart->all_data;
+ while (p) {
+ c = p->all;
+ while (c) {
+ if (!c->display) {
+ c->Y = 0;
+ c = c->next;
+ continue;
+ }
+
+ svg_box(Y, c->start_time, c->end_time, "process3");
+ sample = c->io_samples;
+ for (sample = c->io_samples; sample; sample = sample->next) {
+ double h = (double)sample->bytes / c->max_bytes;
+
+ if (tchart->skip_eagain &&
+ sample->err == -EAGAIN)
+ continue;
+
+ if (sample->err)
+ h = 1;
+
+ if (sample->type == IOTYPE_SYNC)
+ svg_fbox(Y,
+ sample->start_time,
+ sample->end_time,
+ 1,
+ sample->err ? "error" : "sync",
+ sample->fd,
+ sample->err,
+ sample->merges);
+ else if (sample->type == IOTYPE_POLL)
+ svg_fbox(Y,
+ sample->start_time,
+ sample->end_time,
+ 1,
+ sample->err ? "error" : "poll",
+ sample->fd,
+ sample->err,
+ sample->merges);
+ else if (sample->type == IOTYPE_READ)
+ svg_ubox(Y,
+ sample->start_time,
+ sample->end_time,
+ h,
+ sample->err ? "error" : "disk",
+ sample->fd,
+ sample->err,
+ sample->merges);
+ else if (sample->type == IOTYPE_WRITE)
+ svg_lbox(Y,
+ sample->start_time,
+ sample->end_time,
+ h,
+ sample->err ? "error" : "disk",
+ sample->fd,
+ sample->err,
+ sample->merges);
+ else if (sample->type == IOTYPE_RX)
+ svg_ubox(Y,
+ sample->start_time,
+ sample->end_time,
+ h,
+ sample->err ? "error" : "net",
+ sample->fd,
+ sample->err,
+ sample->merges);
+ else if (sample->type == IOTYPE_TX)
+ svg_lbox(Y,
+ sample->start_time,
+ sample->end_time,
+ h,
+ sample->err ? "error" : "net",
+ sample->fd,
+ sample->err,
+ sample->merges);
+ }
+
+ suf = "";
+ bytes = c->total_bytes;
+ if (bytes > 1024) {
+ bytes = bytes / 1024;
+ suf = "K";
+ }
+ if (bytes > 1024) {
+ bytes = bytes / 1024;
+ suf = "M";
+ }
+ if (bytes > 1024) {
+ bytes = bytes / 1024;
+ suf = "G";
+ }
+
+
+ sprintf(comm, "%s:%i (%3.1f %sbytes)", c->comm ?: "", p->pid, bytes, suf);
+ svg_text(Y, c->start_time, comm);
+
+ c->Y = Y;
+ Y++;
+ c = c->next;
+ }
+ p = p->next;
+ }
+}
+
static void draw_process_bars(struct timechart *tchart)
{
struct per_pid *p;
@@ -987,9 +1378,6 @@ static int determine_display_tasks(struct timechart *tchart, u64 threshold)
struct per_pidcomm *c;
int count = 0;
- if (process_filter)
- return determine_display_tasks_filtered(tchart);
-
p = tchart->all_data;
while (p) {
p->display = 0;
@@ -1025,15 +1413,46 @@ static int determine_display_tasks(struct timechart *tchart, u64 threshold)
return count;
}
+static int determine_display_io_tasks(struct timechart *timechart, u64 threshold)
+{
+ struct per_pid *p;
+ struct per_pidcomm *c;
+ int count = 0;
+ p = timechart->all_data;
+ while (p) {
+ /* no exit marker, task kept running to the end */
+ if (p->end_time == 0)
+ p->end_time = timechart->last_time;
+
+ c = p->all;
+ while (c) {
+ c->display = 0;
+
+ if (c->total_bytes >= threshold) {
+ c->display = 1;
+ count++;
+ }
+
+ if (c->end_time == 0)
+ c->end_time = timechart->last_time;
+
+ c = c->next;
+ }
+ p = p->next;
+ }
+ return count;
+}
+
+#define BYTES_THRESH (1 * 1024 * 1024)
#define TIME_THRESH 10000000
static void write_svg_file(struct timechart *tchart, const char *filename)
{
u64 i;
int count;
- int thresh = TIME_THRESH;
+ int thresh = tchart->io_events ? BYTES_THRESH : TIME_THRESH;
if (tchart->power_only)
tchart->proc_num = 0;
@@ -1041,28 +1460,43 @@ static void write_svg_file(struct timechart *tchart, const char *filename)
/* We'd like to show at least proc_num tasks;
* be less picky if we have fewer */
do {
- count = determine_display_tasks(tchart, thresh);
+ if (process_filter)
+ count = determine_display_tasks_filtered(tchart);
+ else if (tchart->io_events)
+ count = determine_display_io_tasks(tchart, thresh);
+ else
+ count = determine_display_tasks(tchart, thresh);
thresh /= 10;
} while (!process_filter && thresh && count < tchart->proc_num);
if (!tchart->proc_num)
count = 0;
- open_svg(filename, tchart->numcpus, count, tchart->first_time, tchart->last_time);
+ if (tchart->io_events) {
+ open_svg(filename, 0, count, tchart->first_time, tchart->last_time);
+
+ svg_time_grid(0.5);
+ svg_io_legenda();
- svg_time_grid();
- svg_legenda();
+ draw_io_bars(tchart);
+ } else {
+ open_svg(filename, tchart->numcpus, count, tchart->first_time, tchart->last_time);
+
+ svg_time_grid(0);
- for (i = 0; i < tchart->numcpus; i++)
- svg_cpu_box(i, tchart->max_freq, tchart->turbo_frequency);
+ svg_legenda();
- draw_cpu_usage(tchart);
- if (tchart->proc_num)
- draw_process_bars(tchart);
- if (!tchart->tasks_only)
- draw_c_p_states(tchart);
- if (tchart->proc_num)
- draw_wakeups(tchart);
+ for (i = 0; i < tchart->numcpus; i++)
+ svg_cpu_box(i, tchart->max_freq, tchart->turbo_frequency);
+
+ draw_cpu_usage(tchart);
+ if (tchart->proc_num)
+ draw_process_bars(tchart);
+ if (!tchart->tasks_only)
+ draw_c_p_states(tchart);
+ if (tchart->proc_num)
+ draw_wakeups(tchart);
+ }
svg_close();
}
@@ -1110,6 +1544,56 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name)
{ "power:power_end", process_sample_power_end },
{ "power:power_frequency", process_sample_power_frequency },
#endif
+
+ { "syscalls:sys_enter_read", process_enter_read },
+ { "syscalls:sys_enter_pread64", process_enter_read },
+ { "syscalls:sys_enter_readv", process_enter_read },
+ { "syscalls:sys_enter_preadv", process_enter_read },
+ { "syscalls:sys_enter_write", process_enter_write },
+ { "syscalls:sys_enter_pwrite64", process_enter_write },
+ { "syscalls:sys_enter_writev", process_enter_write },
+ { "syscalls:sys_enter_pwritev", process_enter_write },
+ { "syscalls:sys_enter_sync", process_enter_sync },
+ { "syscalls:sys_enter_sync_file_range", process_enter_sync },
+ { "syscalls:sys_enter_fsync", process_enter_sync },
+ { "syscalls:sys_enter_msync", process_enter_sync },
+ { "syscalls:sys_enter_recvfrom", process_enter_rx },
+ { "syscalls:sys_enter_recvmmsg", process_enter_rx },
+ { "syscalls:sys_enter_recvmsg", process_enter_rx },
+ { "syscalls:sys_enter_sendto", process_enter_tx },
+ { "syscalls:sys_enter_sendmsg", process_enter_tx },
+ { "syscalls:sys_enter_sendmmsg", process_enter_tx },
+ { "syscalls:sys_enter_epoll_pwait", process_enter_poll },
+ { "syscalls:sys_enter_epoll_wait", process_enter_poll },
+ { "syscalls:sys_enter_poll", process_enter_poll },
+ { "syscalls:sys_enter_ppoll", process_enter_poll },
+ { "syscalls:sys_enter_pselect6", process_enter_poll },
+ { "syscalls:sys_enter_select", process_enter_poll },
+
+ { "syscalls:sys_exit_read", process_exit_read },
+ { "syscalls:sys_exit_pread64", process_exit_read },
+ { "syscalls:sys_exit_readv", process_exit_read },
+ { "syscalls:sys_exit_preadv", process_exit_read },
+ { "syscalls:sys_exit_write", process_exit_write },
+ { "syscalls:sys_exit_pwrite64", process_exit_write },
+ { "syscalls:sys_exit_writev", process_exit_write },
+ { "syscalls:sys_exit_pwritev", process_exit_write },
+ { "syscalls:sys_exit_sync", process_exit_sync },
+ { "syscalls:sys_exit_sync_file_range", process_exit_sync },
+ { "syscalls:sys_exit_fsync", process_exit_sync },
+ { "syscalls:sys_exit_msync", process_exit_sync },
+ { "syscalls:sys_exit_recvfrom", process_exit_rx },
+ { "syscalls:sys_exit_recvmmsg", process_exit_rx },
+ { "syscalls:sys_exit_recvmsg", process_exit_rx },
+ { "syscalls:sys_exit_sendto", process_exit_tx },
+ { "syscalls:sys_exit_sendmsg", process_exit_tx },
+ { "syscalls:sys_exit_sendmmsg", process_exit_tx },
+ { "syscalls:sys_exit_epoll_pwait", process_exit_poll },
+ { "syscalls:sys_exit_epoll_wait", process_exit_poll },
+ { "syscalls:sys_exit_poll", process_exit_poll },
+ { "syscalls:sys_exit_ppoll", process_exit_poll },
+ { "syscalls:sys_exit_pselect6", process_exit_poll },
+ { "syscalls:sys_exit_select", process_exit_poll },
};
struct perf_data_file file = {
.path = input_name,
@@ -1121,7 +1605,9 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name)
int ret = -EINVAL;
if (session == NULL)
- return -ENOMEM;
+ return -1;
+
+ symbol__init(&session->header.env);
(void)perf_header__process_sections(&session->header,
perf_data_file__fd(session->file),
@@ -1154,6 +1640,139 @@ out_delete:
return ret;
}
+static int timechart__io_record(int argc, const char **argv)
+{
+ unsigned int rec_argc, i;
+ const char **rec_argv;
+ const char **p;
+ char *filter = NULL;
+
+ const char * const common_args[] = {
+ "record", "-a", "-R", "-c", "1",
+ };
+ unsigned int common_args_nr = ARRAY_SIZE(common_args);
+
+ const char * const disk_events[] = {
+ "syscalls:sys_enter_read",
+ "syscalls:sys_enter_pread64",
+ "syscalls:sys_enter_readv",
+ "syscalls:sys_enter_preadv",
+ "syscalls:sys_enter_write",
+ "syscalls:sys_enter_pwrite64",
+ "syscalls:sys_enter_writev",
+ "syscalls:sys_enter_pwritev",
+ "syscalls:sys_enter_sync",
+ "syscalls:sys_enter_sync_file_range",
+ "syscalls:sys_enter_fsync",
+ "syscalls:sys_enter_msync",
+
+ "syscalls:sys_exit_read",
+ "syscalls:sys_exit_pread64",
+ "syscalls:sys_exit_readv",
+ "syscalls:sys_exit_preadv",
+ "syscalls:sys_exit_write",
+ "syscalls:sys_exit_pwrite64",
+ "syscalls:sys_exit_writev",
+ "syscalls:sys_exit_pwritev",
+ "syscalls:sys_exit_sync",
+ "syscalls:sys_exit_sync_file_range",
+ "syscalls:sys_exit_fsync",
+ "syscalls:sys_exit_msync",
+ };
+ unsigned int disk_events_nr = ARRAY_SIZE(disk_events);
+
+ const char * const net_events[] = {
+ "syscalls:sys_enter_recvfrom",
+ "syscalls:sys_enter_recvmmsg",
+ "syscalls:sys_enter_recvmsg",
+ "syscalls:sys_enter_sendto",
+ "syscalls:sys_enter_sendmsg",
+ "syscalls:sys_enter_sendmmsg",
+
+ "syscalls:sys_exit_recvfrom",
+ "syscalls:sys_exit_recvmmsg",
+ "syscalls:sys_exit_recvmsg",
+ "syscalls:sys_exit_sendto",
+ "syscalls:sys_exit_sendmsg",
+ "syscalls:sys_exit_sendmmsg",
+ };
+ unsigned int net_events_nr = ARRAY_SIZE(net_events);
+
+ const char * const poll_events[] = {
+ "syscalls:sys_enter_epoll_pwait",
+ "syscalls:sys_enter_epoll_wait",
+ "syscalls:sys_enter_poll",
+ "syscalls:sys_enter_ppoll",
+ "syscalls:sys_enter_pselect6",
+ "syscalls:sys_enter_select",
+
+ "syscalls:sys_exit_epoll_pwait",
+ "syscalls:sys_exit_epoll_wait",
+ "syscalls:sys_exit_poll",
+ "syscalls:sys_exit_ppoll",
+ "syscalls:sys_exit_pselect6",
+ "syscalls:sys_exit_select",
+ };
+ unsigned int poll_events_nr = ARRAY_SIZE(poll_events);
+
+ rec_argc = common_args_nr +
+ disk_events_nr * 4 +
+ net_events_nr * 4 +
+ poll_events_nr * 4 +
+ argc;
+ rec_argv = calloc(rec_argc + 1, sizeof(char *));
+
+ if (rec_argv == NULL)
+ return -ENOMEM;
+
+ if (asprintf(&filter, "common_pid != %d", getpid()) < 0)
+ return -ENOMEM;
+
+ p = rec_argv;
+ for (i = 0; i < common_args_nr; i++)
+ *p++ = strdup(common_args[i]);
+
+ for (i = 0; i < disk_events_nr; i++) {
+ if (!is_valid_tracepoint(disk_events[i])) {
+ rec_argc -= 4;
+ continue;
+ }
+
+ *p++ = "-e";
+ *p++ = strdup(disk_events[i]);
+ *p++ = "--filter";
+ *p++ = filter;
+ }
+ for (i = 0; i < net_events_nr; i++) {
+ if (!is_valid_tracepoint(net_events[i])) {
+ rec_argc -= 4;
+ continue;
+ }
+
+ *p++ = "-e";
+ *p++ = strdup(net_events[i]);
+ *p++ = "--filter";
+ *p++ = filter;
+ }
+ for (i = 0; i < poll_events_nr; i++) {
+ if (!is_valid_tracepoint(poll_events[i])) {
+ rec_argc -= 4;
+ continue;
+ }
+
+ *p++ = "-e";
+ *p++ = strdup(poll_events[i]);
+ *p++ = "--filter";
+ *p++ = filter;
+ }
+
+ for (i = 0; i < (unsigned int)argc; i++)
+ *p++ = argv[i];
+
+ return cmd_record(rec_argc, rec_argv, NULL);
+}
+
+
static int timechart__record(struct timechart *tchart, int argc, const char **argv)
{
unsigned int rec_argc, i, j;
@@ -1270,6 +1889,30 @@ parse_highlight(const struct option *opt __maybe_unused, const char *arg,
return 0;
}
+static int
+parse_time(const struct option *opt, const char *arg, int __maybe_unused unset)
+{
+ char unit = 'n';
+ u64 *value = opt->value;
+
+ if (sscanf(arg, "%" PRIu64 "%cs", value, &unit) > 0) {
+ switch (unit) {
+ case 'm':
+ *value *= 1000000;
+ break;
+ case 'u':
+ *value *= 1000;
+ break;
+ case 'n':
+ break;
+ default:
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
int cmd_timechart(int argc, const char **argv,
const char *prefix __maybe_unused)
{
@@ -1279,9 +1922,11 @@ int cmd_timechart(int argc, const char **argv,
.fork = process_fork_event,
.exit = process_exit_event,
.sample = process_sample_event,
- .ordered_samples = true,
+ .ordered_events = true,
},
.proc_num = 15,
+ .min_time = 1000000,
+ .merge_dist = 1000,
};
const char *output_name = "output.svg";
const struct option timechart_options[] = {
@@ -1303,6 +1948,14 @@ int cmd_timechart(int argc, const char **argv,
"min. number of tasks to print"),
OPT_BOOLEAN('t', "topology", &tchart.topology,
"sort CPUs according to topology"),
+ OPT_BOOLEAN(0, "io-skip-eagain", &tchart.skip_eagain,
+ "skip EAGAIN errors"),
+ OPT_CALLBACK(0, "io-min-time", &tchart.min_time, "time",
+ "all IO faster than min-time will visually appear longer",
+ parse_time),
+ OPT_CALLBACK(0, "io-merge-dist", &tchart.merge_dist, "time",
+ "merge events that are merge-dist us apart",
+ parse_time),
OPT_END()
};
const char * const timechart_usage[] = {
@@ -1314,6 +1967,8 @@ int cmd_timechart(int argc, const char **argv,
OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only,
"output processes data only"),
+ OPT_BOOLEAN('I', "io-only", &tchart.io_only,
+ "record only IO data"),
OPT_BOOLEAN('g', "callchain", &tchart.with_backtrace, "record callchain"),
OPT_END()
};
@@ -1329,8 +1984,6 @@ int cmd_timechart(int argc, const char **argv,
return -1;
}
- symbol__init();
-
if (argc && !strncmp(argv[0], "rec", 3)) {
argc = parse_options(argc, argv, record_options, record_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
@@ -1340,7 +1993,10 @@ int cmd_timechart(int argc, const char **argv,
return -1;
}
- return timechart__record(&tchart, argc, argv);
+ if (tchart.io_only)
+ return timechart__io_record(argc, argv);
+ else
+ return timechart__record(&tchart, argc, argv);
} else if (argc)
usage_with_options(timechart_usage, timechart_options);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 377971dc89a3..fc3d55f832ac 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -59,7 +59,7 @@
#include <sys/syscall.h>
#include <sys/ioctl.h>
-#include <sys/poll.h>
+#include <poll.h>
#include <sys/prctl.h>
#include <sys/wait.h>
#include <sys/uio.h>
@@ -276,11 +276,17 @@ static void perf_top__print_sym_table(struct perf_top *top)
return;
}
+ if (top->zero) {
+ hists__delete_entries(&top->sym_evsel->hists);
+ } else {
+ hists__decay_entries(&top->sym_evsel->hists,
+ top->hide_user_symbols,
+ top->hide_kernel_symbols);
+ }
+
hists__collapse_resort(&top->sym_evsel->hists, NULL);
hists__output_resort(&top->sym_evsel->hists);
- hists__decay_entries(&top->sym_evsel->hists,
- top->hide_user_symbols,
- top->hide_kernel_symbols);
+
hists__output_recalc_col_len(&top->sym_evsel->hists,
top->print_entries - printed);
putchar('\n');
@@ -427,18 +433,13 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
if (!perf_top__key_mapped(top, c)) {
struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
- struct termios tc, save;
+ struct termios save;
perf_top__print_mapped_keys(top);
fprintf(stdout, "\nEnter selection, or unmapped key to continue: ");
fflush(stdout);
- tcgetattr(0, &save);
- tc = save;
- tc.c_lflag &= ~(ICANON | ECHO);
- tc.c_cc[VMIN] = 0;
- tc.c_cc[VTIME] = 0;
- tcsetattr(0, TCSANOW, &tc);
+ set_term_quiet_input(&save);
poll(&stdin_poll, 1, -1);
c = getc(stdin);
@@ -542,11 +543,16 @@ static void perf_top__sort_new_samples(void *arg)
if (t->evlist->selected != NULL)
t->sym_evsel = t->evlist->selected;
+ if (t->zero) {
+ hists__delete_entries(&t->sym_evsel->hists);
+ } else {
+ hists__decay_entries(&t->sym_evsel->hists,
+ t->hide_user_symbols,
+ t->hide_kernel_symbols);
+ }
+
hists__collapse_resort(&t->sym_evsel->hists, NULL);
hists__output_resort(&t->sym_evsel->hists);
- hists__decay_entries(&t->sym_evsel->hists,
- t->hide_user_symbols,
- t->hide_kernel_symbols);
}
static void *display_thread_tui(void *arg)
@@ -577,23 +583,32 @@ static void *display_thread_tui(void *arg)
return NULL;
}
+static void display_sig(int sig __maybe_unused)
+{
+ done = 1;
+}
+
+static void display_setup_sig(void)
+{
+ signal(SIGSEGV, display_sig);
+ signal(SIGFPE, display_sig);
+ signal(SIGINT, display_sig);
+ signal(SIGQUIT, display_sig);
+ signal(SIGTERM, display_sig);
+}
+
static void *display_thread(void *arg)
{
struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
- struct termios tc, save;
+ struct termios save;
struct perf_top *top = arg;
int delay_msecs, c;
- tcgetattr(0, &save);
- tc = save;
- tc.c_lflag &= ~(ICANON | ECHO);
- tc.c_cc[VMIN] = 0;
- tc.c_cc[VTIME] = 0;
-
+ display_setup_sig();
pthread__unblock_sigwinch();
repeat:
delay_msecs = top->delay_secs * 1000;
- tcsetattr(0, TCSANOW, &tc);
+ set_term_quiet_input(&save);
/* trash return*/
getc(stdin);
@@ -620,13 +635,16 @@ repeat:
}
}
+ tcsetattr(0, TCSAFLUSH, &save);
return NULL;
}
-static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym)
+static int symbol_filter(struct map *map, struct symbol *sym)
{
const char *name = sym->name;
+ if (!map->dso->kernel)
+ return 0;
/*
* ppc64 uses function descriptors and appends a '.' to the
* start of every instruction address. Remove it.
@@ -876,7 +894,7 @@ try_again:
if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
ui__error("Failed to mmap with %d (%s)\n",
- errno, strerror(errno));
+ errno, strerror_r(errno, msg, sizeof(msg)));
goto out_err;
}
@@ -911,7 +929,7 @@ static int __cmd_top(struct perf_top *top)
top->session = perf_session__new(NULL, false, NULL);
if (top->session == NULL)
- return -ENOMEM;
+ return -1;
machines__set_symbol_filter(&top->session->machines, symbol_filter);
@@ -946,7 +964,7 @@ static int __cmd_top(struct perf_top *top)
perf_evlist__enable(top->evlist);
/* Wait for a minimal set of events before starting the snapshot */
- poll(top->evlist->pollfd, top->evlist->nr_fds, 100);
+ perf_evlist__poll(top->evlist, 100);
perf_top__mmap_read(top);
@@ -963,7 +981,7 @@ static int __cmd_top(struct perf_top *top)
param.sched_priority = top->realtime_prio;
if (sched_setscheduler(0, SCHED_FIFO, &param)) {
ui__error("Could not set realtime priority.\n");
- goto out_delete;
+ goto out_join;
}
}
@@ -973,10 +991,12 @@ static int __cmd_top(struct perf_top *top)
perf_top__mmap_read(top);
if (hits == top->samples)
- ret = poll(top->evlist->pollfd, top->evlist->nr_fds, 100);
+ ret = perf_evlist__poll(top->evlist, 100);
}
ret = 0;
+out_join:
+ pthread_join(thread, NULL);
out_delete:
perf_session__delete(top->session);
top->session = NULL;
@@ -1000,10 +1020,8 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset)
static int perf_top_config(const char *var, const char *value, void *cb)
{
- struct perf_top *top = cb;
-
if (!strcmp(var, "top.call-graph"))
- return record_parse_callchain(value, &top->record_opts);
+ var = "call-graph.record-mode"; /* fall-through */
if (!strcmp(var, "top.children")) {
symbol_conf.cumulate_callchain = perf_config_bool(var, value);
return 0;
@@ -1122,6 +1140,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
"Interleave source code with assembly code (default)"),
OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw,
"Display raw encoding of assembly instructions (default)"),
+ OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
+ "Enable kernel symbol demangling"),
OPT_STRING(0, "objdump", &objdump_path, "path",
"objdump binary to use for disassembly and annotations"),
OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
@@ -1131,6 +1151,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
"Don't show entries under that percent", parse_percent_limit),
OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
"How to display percentage of filtered entries", parse_filter_percentage),
+ OPT_STRING('w', "column-widths", &symbol_conf.col_width_list_str,
+ "width[,width...]",
+ "don't try to adjust column width, use these fixed values"),
OPT_END()
};
const char * const top_usage[] = {
@@ -1217,7 +1240,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
symbol_conf.priv_size = sizeof(struct annotation);
symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
- if (symbol__init() < 0)
+ if (symbol__init(NULL) < 0)
return -1;
sort__setup_elide(stdout);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index f954c26de231..09bcf2393910 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -402,6 +402,31 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
#define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags
+static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
+ struct syscall_arg *arg)
+{
+ int printed = 0, flags = arg->val;
+
+#define P_MREMAP_FLAG(n) \
+ if (flags & MREMAP_##n) { \
+ printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+ flags &= ~MREMAP_##n; \
+ }
+
+ P_MREMAP_FLAG(MAYMOVE);
+#ifdef MREMAP_FIXED
+ P_MREMAP_FLAG(FIXED);
+#endif
+#undef P_MREMAP_FLAG
+
+ if (flags)
+ printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+ return printed;
+}
+
+#define SCA_MREMAP_FLAGS syscall_arg__scnprintf_mremap_flags
+
static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
struct syscall_arg *arg)
{
@@ -1004,6 +1029,7 @@ static struct syscall_fmt {
[2] = SCA_MMAP_PROT, /* prot */ }, },
{ .name = "mremap", .hexret = true,
.arg_scnprintf = { [0] = SCA_HEX, /* addr */
+ [3] = SCA_MREMAP_FLAGS, /* flags */
[4] = SCA_HEX, /* new_addr */ }, },
{ .name = "munlock", .errmsg = true,
.arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
@@ -1108,6 +1134,7 @@ struct syscall {
struct event_format *tp_format;
const char *name;
bool filtered;
+ bool is_exit;
struct syscall_fmt *fmt;
size_t (**arg_scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
void **arg_parm;
@@ -1132,6 +1159,7 @@ struct thread_trace {
u64 exit_time;
bool entry_pending;
unsigned long nr_events;
+ unsigned long pfmaj, pfmin;
char *entry_str;
double runtime_ms;
struct {
@@ -1177,6 +1205,9 @@ fail:
return NULL;
}
+#define TRACE_PFMAJ (1 << 0)
+#define TRACE_PFMIN (1 << 1)
+
struct trace {
struct perf_tool tool;
struct {
@@ -1211,6 +1242,8 @@ struct trace {
bool summary_only;
bool show_comm;
bool show_tool_stats;
+ bool trace_syscalls;
+ int trace_pgfaults;
};
static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname)
@@ -1276,11 +1309,11 @@ static const char *thread__fd_path(struct thread *thread, int fd,
if (fd < 0)
return NULL;
- if ((fd > ttrace->paths.max || ttrace->paths.table[fd] == NULL))
+ if ((fd > ttrace->paths.max || ttrace->paths.table[fd] == NULL)) {
if (!trace->live)
return NULL;
++trace->stats.proc_getname;
- if (thread__read_fd_path(thread, fd)) {
+ if (thread__read_fd_path(thread, fd))
return NULL;
}
@@ -1378,7 +1411,7 @@ static int trace__tool_process(struct perf_tool *tool,
static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
{
- int err = symbol__init();
+ int err = symbol__init(NULL);
if (err)
return err;
@@ -1473,6 +1506,8 @@ static int trace__read_syscall_info(struct trace *trace, int id)
if (sc->tp_format == NULL)
return -1;
+ sc->is_exit = !strcmp(name, "exit_group") || !strcmp(name, "exit");
+
return syscall__set_arg_fmts(sc);
}
@@ -1535,6 +1570,7 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
}
typedef int (*tracepoint_handler)(struct trace *trace, struct perf_evsel *evsel,
+ union perf_event *event,
struct perf_sample *sample);
static struct syscall *trace__syscall_info(struct trace *trace,
@@ -1607,6 +1643,7 @@ static void thread__update_stats(struct thread_trace *ttrace,
}
static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
+ union perf_event *event __maybe_unused,
struct perf_sample *sample)
{
char *msg;
@@ -1629,7 +1666,6 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
return -1;
args = perf_evsel__sc_tp_ptr(evsel, args, sample);
- ttrace = thread->priv;
if (ttrace->entry_str == NULL) {
ttrace->entry_str = malloc(1024);
@@ -1644,7 +1680,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
printed += syscall__scnprintf_args(sc, msg + printed, 1024 - printed,
args, trace, thread);
- if (!strcmp(sc->name, "exit_group") || !strcmp(sc->name, "exit")) {
+ if (sc->is_exit) {
if (!trace->duration_filter && !trace->summary_only) {
trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output);
fprintf(trace->output, "%-70s\n", ttrace->entry_str);
@@ -1656,9 +1692,10 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
}
static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
+ union perf_event *event __maybe_unused,
struct perf_sample *sample)
{
- int ret;
+ long ret;
u64 duration = 0;
struct thread *thread;
int id = perf_evsel__sc_tp_uint(evsel, id, sample);
@@ -1687,8 +1724,6 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
++trace->stats.vfs_getname;
}
- ttrace = thread->priv;
-
ttrace->exit_time = sample->time;
if (ttrace->entry_time) {
@@ -1713,9 +1748,9 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
if (sc->fmt == NULL) {
signed_print:
- fprintf(trace->output, ") = %d", ret);
+ fprintf(trace->output, ") = %ld", ret);
} else if (ret < 0 && sc->fmt->errmsg) {
- char bf[256];
+ char bf[STRERR_BUFSIZE];
const char *emsg = strerror_r(-ret, bf, sizeof(bf)),
*e = audit_errno_to_name(-ret);
@@ -1723,7 +1758,7 @@ signed_print:
} else if (ret == 0 && sc->fmt->timeout)
fprintf(trace->output, ") = 0 Timeout");
else if (sc->fmt->hexret)
- fprintf(trace->output, ") = %#x", ret);
+ fprintf(trace->output, ") = %#lx", ret);
else
goto signed_print;
@@ -1735,6 +1770,7 @@ out:
}
static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
+ union perf_event *event __maybe_unused,
struct perf_sample *sample)
{
trace->last_vfs_getname = perf_evsel__rawptr(evsel, sample, "pathname");
@@ -1742,6 +1778,7 @@ static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
}
static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evsel,
+ union perf_event *event __maybe_unused,
struct perf_sample *sample)
{
u64 runtime = perf_evsel__intval(evsel, sample, "runtime");
@@ -1768,6 +1805,80 @@ out_dump:
return 0;
}
+static void print_location(FILE *f, struct perf_sample *sample,
+ struct addr_location *al,
+ bool print_dso, bool print_sym)
+{
+
+ if ((verbose || print_dso) && al->map)
+ fprintf(f, "%s@", al->map->dso->long_name);
+
+ if ((verbose || print_sym) && al->sym)
+ fprintf(f, "%s+0x%" PRIx64, al->sym->name,
+ al->addr - al->sym->start);
+ else if (al->map)
+ fprintf(f, "0x%" PRIx64, al->addr);
+ else
+ fprintf(f, "0x%" PRIx64, sample->addr);
+}
+
+static int trace__pgfault(struct trace *trace,
+ struct perf_evsel *evsel,
+ union perf_event *event,
+ struct perf_sample *sample)
+{
+ struct thread *thread;
+ u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+ struct addr_location al;
+ char map_type = 'd';
+ struct thread_trace *ttrace;
+
+ thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
+ ttrace = thread__trace(thread, trace->output);
+ if (ttrace == NULL)
+ return -1;
+
+ if (evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ)
+ ttrace->pfmaj++;
+ else
+ ttrace->pfmin++;
+
+ if (trace->summary_only)
+ return 0;
+
+ thread__find_addr_location(thread, trace->host, cpumode, MAP__FUNCTION,
+ sample->ip, &al);
+
+ trace__fprintf_entry_head(trace, thread, 0, sample->time, trace->output);
+
+ fprintf(trace->output, "%sfault [",
+ evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ ?
+ "maj" : "min");
+
+ print_location(trace->output, sample, &al, false, true);
+
+ fprintf(trace->output, "] => ");
+
+ thread__find_addr_location(thread, trace->host, cpumode, MAP__VARIABLE,
+ sample->addr, &al);
+
+ if (!al.map) {
+ thread__find_addr_location(thread, trace->host, cpumode,
+ MAP__FUNCTION, sample->addr, &al);
+
+ if (al.map)
+ map_type = 'x';
+ else
+ map_type = '?';
+ }
+
+ print_location(trace->output, sample, &al, true, false);
+
+ fprintf(trace->output, " (%c%c)\n", map_type, al.level);
+
+ return 0;
+}
+
static bool skip_sample(struct trace *trace, struct perf_sample *sample)
{
if ((trace->pid_list && intlist__find(trace->pid_list, sample->pid)) ||
@@ -1781,7 +1892,7 @@ static bool skip_sample(struct trace *trace, struct perf_sample *sample)
}
static int trace__process_sample(struct perf_tool *tool,
- union perf_event *event __maybe_unused,
+ union perf_event *event,
struct perf_sample *sample,
struct perf_evsel *evsel,
struct machine *machine __maybe_unused)
@@ -1799,7 +1910,7 @@ static int trace__process_sample(struct perf_tool *tool,
if (handler) {
++trace->nr_events;
- handler(trace, evsel, sample);
+ handler(trace, evsel, event, sample);
}
return err;
@@ -1826,7 +1937,7 @@ static int parse_target_str(struct trace *trace)
return 0;
}
-static int trace__record(int argc, const char **argv)
+static int trace__record(struct trace *trace, int argc, const char **argv)
{
unsigned int rec_argc, i, j;
const char **rec_argv;
@@ -1835,34 +1946,54 @@ static int trace__record(int argc, const char **argv)
"-R",
"-m", "1024",
"-c", "1",
- "-e",
};
+ const char * const sc_args[] = { "-e", };
+ unsigned int sc_args_nr = ARRAY_SIZE(sc_args);
+ const char * const majpf_args[] = { "-e", "major-faults" };
+ unsigned int majpf_args_nr = ARRAY_SIZE(majpf_args);
+ const char * const minpf_args[] = { "-e", "minor-faults" };
+ unsigned int minpf_args_nr = ARRAY_SIZE(minpf_args);
+
/* +1 is for the event string below */
- rec_argc = ARRAY_SIZE(record_args) + 1 + argc;
+ rec_argc = ARRAY_SIZE(record_args) + sc_args_nr + 1 +
+ majpf_args_nr + minpf_args_nr + argc;
rec_argv = calloc(rec_argc + 1, sizeof(char *));
if (rec_argv == NULL)
return -ENOMEM;
+ j = 0;
for (i = 0; i < ARRAY_SIZE(record_args); i++)
- rec_argv[i] = record_args[i];
-
- /* event string may be different for older kernels - e.g., RHEL6 */
- if (is_valid_tracepoint("raw_syscalls:sys_enter"))
- rec_argv[i] = "raw_syscalls:sys_enter,raw_syscalls:sys_exit";
- else if (is_valid_tracepoint("syscalls:sys_enter"))
- rec_argv[i] = "syscalls:sys_enter,syscalls:sys_exit";
- else {
- pr_err("Neither raw_syscalls nor syscalls events exist.\n");
- return -1;
+ rec_argv[j++] = record_args[i];
+
+ if (trace->trace_syscalls) {
+ for (i = 0; i < sc_args_nr; i++)
+ rec_argv[j++] = sc_args[i];
+
+ /* event string may be different for older kernels - e.g., RHEL6 */
+ if (is_valid_tracepoint("raw_syscalls:sys_enter"))
+ rec_argv[j++] = "raw_syscalls:sys_enter,raw_syscalls:sys_exit";
+ else if (is_valid_tracepoint("syscalls:sys_enter"))
+ rec_argv[j++] = "syscalls:sys_enter,syscalls:sys_exit";
+ else {
+ pr_err("Neither raw_syscalls nor syscalls events exist.\n");
+ return -1;
+ }
}
- i++;
- for (j = 0; j < (unsigned int)argc; j++, i++)
- rec_argv[i] = argv[j];
+ if (trace->trace_pgfaults & TRACE_PFMAJ)
+ for (i = 0; i < majpf_args_nr; i++)
+ rec_argv[j++] = majpf_args[i];
+
+ if (trace->trace_pgfaults & TRACE_PFMIN)
+ for (i = 0; i < minpf_args_nr; i++)
+ rec_argv[j++] = minpf_args[i];
- return cmd_record(i, rec_argv, NULL);
+ for (i = 0; i < (unsigned int)argc; i++)
+ rec_argv[j++] = argv[i];
+
+ return cmd_record(j, rec_argv, NULL);
}
static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);
@@ -1882,6 +2013,30 @@ static void perf_evlist__add_vfs_getname(struct perf_evlist *evlist)
perf_evlist__add(evlist, evsel);
}
+static int perf_evlist__add_pgfault(struct perf_evlist *evlist,
+ u64 config)
+{
+ struct perf_evsel *evsel;
+ struct perf_event_attr attr = {
+ .type = PERF_TYPE_SOFTWARE,
+ .mmap_data = 1,
+ };
+
+ attr.config = config;
+ attr.sample_period = 1;
+
+ event_attr_init(&attr);
+
+ evsel = perf_evsel__new(&attr);
+ if (!evsel)
+ return -ENOMEM;
+
+ evsel->handler = trace__pgfault;
+ perf_evlist__add(evlist, evsel);
+
+ return 0;
+}
+
static int trace__run(struct trace *trace, int argc, const char **argv)
{
struct perf_evlist *evlist = perf_evlist__new();
@@ -1889,6 +2044,8 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
int err = -1, i;
unsigned long before;
const bool forks = argc > 0;
+ bool draining = false;
+ char sbuf[STRERR_BUFSIZE];
trace->live = true;
@@ -1897,10 +2054,21 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
goto out;
}
- if (perf_evlist__add_syscall_newtp(evlist, trace__sys_enter, trace__sys_exit))
+ if (trace->trace_syscalls &&
+ perf_evlist__add_syscall_newtp(evlist, trace__sys_enter,
+ trace__sys_exit))
+ goto out_error_tp;
+
+ if (trace->trace_syscalls)
+ perf_evlist__add_vfs_getname(evlist);
+
+ if ((trace->trace_pgfaults & TRACE_PFMAJ) &&
+ perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MAJ))
goto out_error_tp;
- perf_evlist__add_vfs_getname(evlist);
+ if ((trace->trace_pgfaults & TRACE_PFMIN) &&
+ perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MIN))
+ goto out_error_tp;
if (trace->sched &&
perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
@@ -1939,7 +2107,8 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
if (err < 0) {
- fprintf(trace->output, "Couldn't mmap the events: %s\n", strerror(errno));
+ fprintf(trace->output, "Couldn't mmap the events: %s\n",
+ strerror_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
}
@@ -1982,7 +2151,8 @@ again:
goto next_event;
}
- if (sample.raw_data == NULL) {
+ if (evsel->attr.type == PERF_TYPE_TRACEPOINT &&
+ sample.raw_data == NULL) {
fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
perf_evsel__name(evsel), sample.tid,
sample.cpu, sample.raw_size);
@@ -1990,7 +2160,7 @@ again:
}
handler = evsel->handler;
- handler(trace, evsel, &sample);
+ handler(trace, evsel, event, &sample);
next_event:
perf_evlist__mmap_consume(evlist, i);
@@ -2002,8 +2172,12 @@ next_event:
if (trace->nr_events == before) {
int timeout = done ? 100 : -1;
- if (poll(evlist->pollfd, evlist->nr_fds, timeout) > 0)
+ if (!draining && perf_evlist__poll(evlist, timeout) > 0) {
+ if (perf_evlist__filter_pollfd(evlist, POLLERR | POLLHUP) == 0)
+ draining = true;
+
goto again;
+ }
} else {
goto again;
}
@@ -2068,18 +2242,18 @@ static int trace__replay(struct trace *trace)
trace->tool.tracing_data = perf_event__process_tracing_data;
trace->tool.build_id = perf_event__process_build_id;
- trace->tool.ordered_samples = true;
+ trace->tool.ordered_events = true;
trace->tool.ordering_requires_timestamps = true;
/* add tid to output */
trace->multiple_threads = true;
- if (symbol__init() < 0)
- return -1;
-
session = perf_session__new(&file, false, &trace->tool);
if (session == NULL)
- return -ENOMEM;
+ return -1;
+
+ if (symbol__init(&session->header.env) < 0)
+ goto out;
trace->host = &session->machines.host;
@@ -2093,13 +2267,10 @@ static int trace__replay(struct trace *trace)
if (evsel == NULL)
evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
"syscalls:sys_enter");
- if (evsel == NULL) {
- pr_err("Data file does not have raw_syscalls:sys_enter event\n");
- goto out;
- }
- if (perf_evsel__init_syscall_tp(evsel, trace__sys_enter) < 0 ||
- perf_evsel__init_sc_tp_ptr_field(evsel, args)) {
+ if (evsel &&
+ (perf_evsel__init_syscall_tp(evsel, trace__sys_enter) < 0 ||
+ perf_evsel__init_sc_tp_ptr_field(evsel, args))) {
pr_err("Error during initialize raw_syscalls:sys_enter event\n");
goto out;
}
@@ -2109,15 +2280,19 @@ static int trace__replay(struct trace *trace)
if (evsel == NULL)
evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
"syscalls:sys_exit");
- if (evsel == NULL) {
- pr_err("Data file does not have raw_syscalls:sys_exit event\n");
+ if (evsel &&
+ (perf_evsel__init_syscall_tp(evsel, trace__sys_exit) < 0 ||
+ perf_evsel__init_sc_tp_uint_field(evsel, ret))) {
+ pr_err("Error during initialize raw_syscalls:sys_exit event\n");
goto out;
}
- if (perf_evsel__init_syscall_tp(evsel, trace__sys_exit) < 0 ||
- perf_evsel__init_sc_tp_uint_field(evsel, ret)) {
- pr_err("Error during initialize raw_syscalls:sys_exit event\n");
- goto out;
+ evlist__for_each(session->evlist, evsel) {
+ if (evsel->attr.type == PERF_TYPE_SOFTWARE &&
+ (evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ ||
+ evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MIN ||
+ evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS))
+ evsel->handler = trace__pgfault;
}
err = parse_target_str(trace);
@@ -2217,6 +2392,10 @@ static int trace__fprintf_one_thread(struct thread *thread, void *priv)
printed += fprintf(fp, " %s (%d), ", thread__comm_str(thread), thread->tid);
printed += fprintf(fp, "%lu events, ", ttrace->nr_events);
printed += fprintf(fp, "%.1f%%", ratio);
+ if (ttrace->pfmaj)
+ printed += fprintf(fp, ", %lu majfaults", ttrace->pfmaj);
+ if (ttrace->pfmin)
+ printed += fprintf(fp, ", %lu minfaults", ttrace->pfmin);
printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms);
printed += thread__dump_stats(ttrace, trace, fp);
@@ -2264,6 +2443,23 @@ static int trace__open_output(struct trace *trace, const char *filename)
return trace->output == NULL ? -errno : 0;
}
+static int parse_pagefaults(const struct option *opt, const char *str,
+ int unset __maybe_unused)
+{
+ int *trace_pgfaults = opt->value;
+
+ if (strcmp(str, "all") == 0)
+ *trace_pgfaults |= TRACE_PFMAJ | TRACE_PFMIN;
+ else if (strcmp(str, "maj") == 0)
+ *trace_pgfaults |= TRACE_PFMAJ;
+ else if (strcmp(str, "min") == 0)
+ *trace_pgfaults |= TRACE_PFMIN;
+ else
+ return -1;
+
+ return 0;
+}
+
int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
{
const char * const trace_usage[] = {
@@ -2293,6 +2489,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
},
.output = stdout,
.show_comm = true,
+ .trace_syscalls = true,
};
const char *output_name = NULL;
const char *ev_qualifier_str = NULL;
@@ -2330,20 +2527,34 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
"Show only syscall summary with statistics"),
OPT_BOOLEAN('S', "with-summary", &trace.summary,
"Show all syscalls and summary with statistics"),
+ OPT_CALLBACK_DEFAULT('F', "pf", &trace.trace_pgfaults, "all|maj|min",
+ "Trace pagefaults", parse_pagefaults, "maj"),
+ OPT_BOOLEAN(0, "syscalls", &trace.trace_syscalls, "Trace syscalls"),
OPT_END()
};
int err;
char bf[BUFSIZ];
- if ((argc > 1) && (strcmp(argv[1], "record") == 0))
- return trace__record(argc-2, &argv[2]);
+ argc = parse_options(argc, argv, trace_options, trace_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+
+ if (trace.trace_pgfaults) {
+ trace.opts.sample_address = true;
+ trace.opts.sample_time = true;
+ }
- argc = parse_options(argc, argv, trace_options, trace_usage, 0);
+ if ((argc >= 1) && (strcmp(argv[0], "record") == 0))
+ return trace__record(&trace, argc-1, &argv[1]);
/* summary_only implies summary option, but don't overwrite summary if set */
if (trace.summary_only)
trace.summary = trace.summary_only;
+ if (!trace.trace_syscalls && !trace.trace_pgfaults) {
+ pr_err("Please specify something to trace.\n");
+ return -1;
+ }
+
if (output_name != NULL) {
err = trace__open_output(&trace, output_name);
if (err < 0) {
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index f30ac5e5d271..58f609198c6d 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -116,6 +116,29 @@ ifdef PARSER_DEBUG
CFLAGS += -DPARSER_DEBUG
endif
+ifndef NO_LIBPYTHON
+ # Try different combinations to accommodate systems that only have
+ # python[2][-config] in weird combinations but always preferring
+ # python2 and python2-config as per pep-0394. If we catch a
+ # python[-config] in version 3, the version check will kill it.
+ PYTHON2 := $(if $(call get-executable,python2),python2,python)
+ override PYTHON := $(call get-executable-or-default,PYTHON,$(PYTHON2))
+ PYTHON2_CONFIG := \
+ $(if $(call get-executable,$(PYTHON)-config),$(PYTHON)-config,python-config)
+ override PYTHON_CONFIG := \
+ $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON2_CONFIG))
+
+ PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
+
+ PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
+ PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+
+ FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
+ FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
+ FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS)
+ FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
+endif
+
CFLAGS += -fno-omit-frame-pointer
CFLAGS += -ggdb3
CFLAGS += -funwind-tables
@@ -160,6 +183,7 @@ CORE_FEATURE_TESTS = \
backtrace \
dwarf \
fortify-source \
+ sync-compare-and-swap \
glibc \
gtk2 \
gtk2-infobar \
@@ -195,6 +219,7 @@ LIB_FEATURE_TESTS = \
VF_FEATURE_TESTS = \
backtrace \
fortify-source \
+ sync-compare-and-swap \
gtk2-infobar \
libelf-getphdrnum \
libelf-mmap \
@@ -268,6 +293,10 @@ CFLAGS += -I$(LIB_INCLUDE)
CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
+ifeq ($(feature-sync-compare-and-swap), 1)
+ CFLAGS += -DHAVE_SYNC_COMPARE_AND_SWAP_SUPPORT
+endif
+
ifndef NO_BIONIC
$(call feature_check,bionic)
ifeq ($(feature-bionic), 1)
@@ -345,6 +374,12 @@ ifndef NO_LIBELF
endif # NO_DWARF
endif # NO_LIBELF
+ifeq ($(ARCH),powerpc)
+ ifndef NO_DWARF
+ CFLAGS += -DHAVE_SKIP_CALLCHAIN_IDX
+ endif
+endif
+
ifndef NO_LIBUNWIND
ifneq ($(feature-libunwind), 1)
msg := $(warning No libunwind found. Please install libunwind-dev[el] >= 1.1 and/or set LIBUNWIND_DIR);
@@ -472,21 +507,14 @@ define disable-python_code
NO_LIBPYTHON := 1
endef
-override PYTHON := \
- $(call get-executable-or-default,PYTHON,python)
-
-ifndef PYTHON
- $(call disable-python,python interpreter)
+ifdef NO_LIBPYTHON
+ $(call disable-python)
else
- PYTHON_WORD := $(call shell-wordify,$(PYTHON))
-
- ifdef NO_LIBPYTHON
- $(call disable-python)
+ ifndef PYTHON
+ $(call disable-python,python interpreter)
else
-
- override PYTHON_CONFIG := \
- $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON)-config)
+ PYTHON_WORD := $(call shell-wordify,$(PYTHON))
ifndef PYTHON_CONFIG
$(call disable-python,python-config tool)
@@ -590,6 +618,10 @@ ifndef NO_LIBNUMA
endif
endif
+ifdef HAVE_KVM_STAT_SUPPORT
+ CFLAGS += -DHAVE_KVM_STAT_SUPPORT
+endif
+
# Among the variables below, these:
# perfexecdir
# template_dir
@@ -621,11 +653,13 @@ else
sysconfdir = $(prefix)/etc
ETC_PERFCONFIG = etc/perfconfig
endif
+ifndef lib
ifeq ($(IS_X86_64),1)
lib = lib64
else
lib = lib
endif
+endif # lib
libdir = $(prefix)/$(lib)
# Shell quote (do not use $(call) to accommodate ancient setups);
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index 64c84e5f0514..72ab2984718e 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -5,6 +5,7 @@ FILES= \
test-bionic.bin \
test-dwarf.bin \
test-fortify-source.bin \
+ test-sync-compare-and-swap.bin \
test-glibc.bin \
test-gtk2.bin \
test-gtk2-infobar.bin \
@@ -100,25 +101,11 @@ FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
test-libperl.bin:
$(BUILD) $(FLAGS_PERL_EMBED)
-override PYTHON := python
-override PYTHON_CONFIG := python-config
-
-escape-for-shell-sq = $(subst ','\'',$(1))
-shell-sq = '$(escape-for-shell-sq)'
-
-PYTHON_CONFIG_SQ = $(call shell-sq,$(PYTHON_CONFIG))
-
-PYTHON_EMBED_LDOPTS = $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
-PYTHON_EMBED_LDFLAGS = $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
-PYTHON_EMBED_LIBADD = $(call grep-libs,$(PYTHON_EMBED_LDOPTS))
-PYTHON_EMBED_CCOPTS = $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
-FLAGS_PYTHON_EMBED = $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
-
test-libpython.bin:
- $(BUILD) $(FLAGS_PYTHON_EMBED)
+ $(BUILD)
test-libpython-version.bin:
- $(BUILD) $(FLAGS_PYTHON_EMBED)
+ $(BUILD)
test-libbfd.bin:
$(BUILD) -DPACKAGE='"perf"' -lbfd -lz -liberty -ldl
@@ -141,6 +128,9 @@ test-timerfd.bin:
test-libdw-dwarf-unwind.bin:
$(BUILD)
+test-sync-compare-and-swap.bin:
+ $(BUILD) -Werror
+
-include *.d
###############################
diff --git a/tools/perf/config/feature-checks/test-all.c b/tools/perf/config/feature-checks/test-all.c
index fe5c1e5c952f..a7d022e161c0 100644
--- a/tools/perf/config/feature-checks/test-all.c
+++ b/tools/perf/config/feature-checks/test-all.c
@@ -89,6 +89,10 @@
# include "test-libdw-dwarf-unwind.c"
#undef main
+#define main main_test_sync_compare_and_swap
+# include "test-sync-compare-and-swap.c"
+#undef main
+
int main(int argc, char *argv[])
{
main_test_libpython();
@@ -111,6 +115,7 @@ int main(int argc, char *argv[])
main_test_timerfd();
main_test_stackprotector_all();
main_test_libdw_dwarf_unwind();
+ main_test_sync_compare_and_swap(argc, argv);
return 0;
}
diff --git a/tools/perf/config/feature-checks/test-sync-compare-and-swap.c b/tools/perf/config/feature-checks/test-sync-compare-and-swap.c
new file mode 100644
index 000000000000..c34d4ca4af56
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-sync-compare-and-swap.c
@@ -0,0 +1,14 @@
+#include <stdint.h>
+
+volatile uint64_t x;
+
+int main(int argc, char *argv[])
+{
+ uint64_t old, new = argc;
+
+ argv = argv;
+ do {
+ old = __sync_val_compare_and_swap(&x, 0, 0);
+ } while (!__sync_bool_compare_and_swap(&x, old, new));
+ return old == new;
+}
diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak
index 4d985e0f03f5..7076a62d0ff7 100644
--- a/tools/perf/config/utilities.mak
+++ b/tools/perf/config/utilities.mak
@@ -132,7 +132,7 @@ endef
#
# Usage: bool-value = $(call is-absolute,path)
#
-is-absolute = $(shell echo $(shell-sq) | grep ^/ -q && echo y)
+is-absolute = $(shell echo $(shell-sq) | grep -q ^/ && echo y)
# lookup
#
diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h
index 5268a1481d23..937e4324ad94 100644
--- a/tools/perf/perf-sys.h
+++ b/tools/perf/perf-sys.h
@@ -54,6 +54,7 @@
#define mb() asm volatile("bcr 15,0" ::: "memory")
#define wmb() asm volatile("bcr 15,0" ::: "memory")
#define rmb() asm volatile("bcr 15,0" ::: "memory")
+#define CPUINFO_PROC "vendor_id"
#endif
#ifdef __sh__
diff --git a/tools/perf/perf-with-kcore.sh b/tools/perf/perf-with-kcore.sh
new file mode 100644
index 000000000000..c7ff90a90e4e
--- /dev/null
+++ b/tools/perf/perf-with-kcore.sh
@@ -0,0 +1,259 @@
+#!/bin/bash
+# perf-with-kcore: use perf with a copy of kcore
+# Copyright (c) 2014, Intel Corporation.
+#
+# This program is free software; you can redistribute it and/or modify it
+# under the terms and conditions of the GNU General Public License,
+# version 2, as published by the Free Software Foundation.
+#
+# This program is distributed in the hope it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+# more details.
+
+set -e
+
+usage()
+{
+ echo "Usage: perf-with-kcore <perf sub-command> <perf.data directory> [<sub-command options> [ -- <workload>]]" >&2
+ echo " <perf sub-command> can be record, script, report or inject" >&2
+ echo " or: perf-with-kcore fix_buildid_cache_permissions" >&2
+ exit 1
+}
+
+find_perf()
+{
+ if [ -n "$PERF" ] ; then
+ return
+ fi
+ PERF=`which perf || true`
+ if [ -z "$PERF" ] ; then
+ echo "Failed to find perf" >&2
+ exit 1
+ fi
+ if [ ! -x "$PERF" ] ; then
+ echo "Failed to find perf" >&2
+ exit 1
+ fi
+ echo "Using $PERF"
+ "$PERF" version
+}
+
+copy_kcore()
+{
+ echo "Copying kcore"
+
+ if [ $EUID -eq 0 ] ; then
+ SUDO=""
+ else
+ SUDO="sudo"
+ fi
+
+ rm -f perf.data.junk
+ ("$PERF" record -o perf.data.junk $PERF_OPTIONS -- sleep 60) >/dev/null 2>/dev/null &
+ PERF_PID=$!
+
+ # Need to make sure that perf has started
+ sleep 1
+
+ KCORE=$(($SUDO "$PERF" buildid-cache -v -f -k /proc/kcore >/dev/null) 2>&1)
+ case "$KCORE" in
+ "kcore added to build-id cache directory "*)
+ KCORE_DIR=${KCORE#"kcore added to build-id cache directory "}
+ ;;
+ *)
+ kill $PERF_PID
+ wait >/dev/null 2>/dev/null || true
+ rm perf.data.junk
+ echo "$KCORE"
+ echo "Failed to find kcore" >&2
+ exit 1
+ ;;
+ esac
+
+ kill $PERF_PID
+ wait >/dev/null 2>/dev/null || true
+ rm perf.data.junk
+
+ $SUDO cp -a "$KCORE_DIR" "$(pwd)/$PERF_DATA_DIR"
+ $SUDO rm -f "$KCORE_DIR/kcore"
+ $SUDO rm -f "$KCORE_DIR/kallsyms"
+ $SUDO rm -f "$KCORE_DIR/modules"
+ $SUDO rmdir "$KCORE_DIR"
+
+ KCORE_DIR_BASENAME=$(basename "$KCORE_DIR")
+ KCORE_DIR="$(pwd)/$PERF_DATA_DIR/$KCORE_DIR_BASENAME"
+
+ $SUDO chown $UID "$KCORE_DIR"
+ $SUDO chown $UID "$KCORE_DIR/kcore"
+ $SUDO chown $UID "$KCORE_DIR/kallsyms"
+ $SUDO chown $UID "$KCORE_DIR/modules"
+
+ $SUDO chgrp $GROUPS "$KCORE_DIR"
+ $SUDO chgrp $GROUPS "$KCORE_DIR/kcore"
+ $SUDO chgrp $GROUPS "$KCORE_DIR/kallsyms"
+ $SUDO chgrp $GROUPS "$KCORE_DIR/modules"
+
+ ln -s "$KCORE_DIR_BASENAME" "$PERF_DATA_DIR/kcore_dir"
+}
+
+fix_buildid_cache_permissions()
+{
+ if [ $EUID -ne 0 ] ; then
+ echo "This script must be run as root via sudo " >&2
+ exit 1
+ fi
+
+ if [ -z "$SUDO_USER" ] ; then
+ echo "This script must be run via sudo" >&2
+ exit 1
+ fi
+
+ USER_HOME=$(bash <<< "echo ~$SUDO_USER")
+
+ if [ "$HOME" != "$USER_HOME" ] ; then
+ echo "Fix unnecessary because root has a home: $HOME" >&2
+ exit 1
+ fi
+
+ echo "Fixing buildid cache permissions"
+
+ find "$USER_HOME/.debug" -xdev -type d ! -user "$SUDO_USER" -ls -exec chown "$SUDO_USER" \{\} \;
+ find "$USER_HOME/.debug" -xdev -type f -links 1 ! -user "$SUDO_USER" -ls -exec chown "$SUDO_USER" \{\} \;
+ find "$USER_HOME/.debug" -xdev -type l ! -user "$SUDO_USER" -ls -exec chown -h "$SUDO_USER" \{\} \;
+
+ if [ -n "$SUDO_GID" ] ; then
+ find "$USER_HOME/.debug" -xdev -type d ! -group "$SUDO_GID" -ls -exec chgrp "$SUDO_GID" \{\} \;
+ find "$USER_HOME/.debug" -xdev -type f -links 1 ! -group "$SUDO_GID" -ls -exec chgrp "$SUDO_GID" \{\} \;
+ find "$USER_HOME/.debug" -xdev -type l ! -group "$SUDO_GID" -ls -exec chgrp -h "$SUDO_GID" \{\} \;
+ fi
+
+ echo "Done"
+}
+
+check_buildid_cache_permissions()
+{
+ if [ $EUID -eq 0 ] ; then
+ return
+ fi
+
+ PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type d ! -user "$USER" -print -quit)
+ PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type f -links 1 ! -user "$USER" -print -quit)
+ PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type l ! -user "$USER" -print -quit)
+
+ PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type d ! -group "$GROUPS" -print -quit)
+ PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type f -links 1 ! -group "$GROUPS" -print -quit)
+ PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type l ! -group "$GROUPS" -print -quit)
+
+ if [ -n "$PERMISSIONS_OK" ] ; then
+ echo "*** WARNING *** buildid cache permissions may need fixing" >&2
+ fi
+}
+
+record()
+{
+ echo "Recording"
+
+ if [ $EUID -ne 0 ] ; then
+
+ if [ "$(cat /proc/sys/kernel/kptr_restrict)" -ne 0 ] ; then
+ echo "*** WARNING *** /proc/sys/kernel/kptr_restrict prevents access to kernel addresses" >&2
+ fi
+
+ if echo "$PERF_OPTIONS" | grep -q ' -a \|^-a \| -a$\|^-a$\| --all-cpus \|^--all-cpus \| --all-cpus$\|^--all-cpus$' ; then
+ echo "*** WARNING *** system-wide tracing without root access will not be able to read all necessary information from /proc" >&2
+ fi
+
+ if echo "$PERF_OPTIONS" | grep -q 'intel_pt\|intel_bts\| -I\|^-I' ; then
+ if [ "$(cat /proc/sys/kernel/perf_event_paranoid)" -gt -1 ] ; then
+ echo "*** WARNING *** /proc/sys/kernel/perf_event_paranoid restricts buffer size and tracepoint (sched_switch) use" >&2
+ fi
+
+ if echo "$PERF_OPTIONS" | grep -q ' --per-thread \|^--per-thread \| --per-thread$\|^--per-thread$' ; then
+ true
+ elif echo "$PERF_OPTIONS" | grep -q ' -t \|^-t \| -t$\|^-t$' ; then
+ true
+ elif [ ! -r /sys/kernel/debug -o ! -x /sys/kernel/debug ] ; then
+ echo "*** WARNING *** /sys/kernel/debug permissions prevent tracepoint (sched_switch) use" >&2
+ fi
+ fi
+ fi
+
+ if [ -z "$1" ] ; then
+ echo "Workload is required for recording" >&2
+ usage
+ fi
+
+ if [ -e "$PERF_DATA_DIR" ] ; then
+ echo "'$PERF_DATA_DIR' exists" >&2
+ exit 1
+ fi
+
+ find_perf
+
+ mkdir "$PERF_DATA_DIR"
+
+ echo "$PERF record -o $PERF_DATA_DIR/perf.data $PERF_OPTIONS -- $*"
+ "$PERF" record -o "$PERF_DATA_DIR/perf.data" $PERF_OPTIONS -- $* || true
+
+ if rmdir "$PERF_DATA_DIR" > /dev/null 2>/dev/null ; then
+ exit 1
+ fi
+
+ copy_kcore
+
+ echo "Done"
+}
+
+subcommand()
+{
+ find_perf
+ check_buildid_cache_permissions
+ echo "$PERF $PERF_SUB_COMMAND -i $PERF_DATA_DIR/perf.data --kallsyms=$PERF_DATA_DIR/kcore_dir/kallsyms $*"
+ "$PERF" $PERF_SUB_COMMAND -i "$PERF_DATA_DIR/perf.data" "--kallsyms=$PERF_DATA_DIR/kcore_dir/kallsyms" $*
+}
+
+if [ "$1" = "fix_buildid_cache_permissions" ] ; then
+ fix_buildid_cache_permissions
+ exit 0
+fi
+
+PERF_SUB_COMMAND=$1
+PERF_DATA_DIR=$2
+shift || true
+shift || true
+
+if [ -z "$PERF_SUB_COMMAND" ] ; then
+ usage
+fi
+
+if [ -z "$PERF_DATA_DIR" ] ; then
+ usage
+fi
+
+case "$PERF_SUB_COMMAND" in
+"record")
+ while [ "$1" != "--" ] ; do
+ PERF_OPTIONS+="$1 "
+ shift || break
+ done
+ if [ "$1" != "--" ] ; then
+ echo "Options and workload are required for recording" >&2
+ usage
+ fi
+ shift
+ record $*
+;;
+"script")
+ subcommand $*
+;;
+"report")
+ subcommand $*
+;;
+"inject")
+ subcommand $*
+;;
+*)
+ usage
+;;
+esac
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 95c58fc15284..452a8474d29d 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -13,11 +13,12 @@
#include "util/quote.h"
#include "util/run-command.h"
#include "util/parse-events.h"
+#include "util/debug.h"
#include <api/fs/debugfs.h>
#include <pthread.h>
const char perf_usage_string[] =
- "perf [--version] [--help] COMMAND [ARGS]";
+ "perf [--version] [--help] [OPTIONS] COMMAND [ARGS]";
const char perf_more_info_string[] =
"See 'perf help COMMAND' for more information on a specific command.";
@@ -212,6 +213,16 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
printf("%s ", p->cmd);
}
exit(0);
+ } else if (!strcmp(cmd, "--debug")) {
+ if (*argc < 2) {
+ fprintf(stderr, "No variable specified for --debug.\n");
+ usage(perf_usage_string);
+ }
+ if (perf_debug_option((*argv)[1]))
+ usage(perf_usage_string);
+
+ (*argv)++;
+ (*argc)--;
} else {
fprintf(stderr, "Unknown option: %s\n", cmd);
usage(perf_usage_string);
@@ -302,6 +313,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
int status;
struct stat st;
const char *prefix;
+ char sbuf[STRERR_BUFSIZE];
prefix = NULL;
if (p->option & RUN_SETUP)
@@ -332,7 +344,8 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
status = 1;
/* Check for ENOSPC and EIO errors.. */
if (fflush(stdout)) {
- fprintf(stderr, "write failure on standard output: %s", strerror(errno));
+ fprintf(stderr, "write failure on standard output: %s",
+ strerror_r(errno, sbuf, sizeof(sbuf)));
goto out;
}
if (ferror(stdout)) {
@@ -340,7 +353,8 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
goto out;
}
if (fclose(stdout)) {
- fprintf(stderr, "close failed on standard output: %s", strerror(errno));
+ fprintf(stderr, "close failed on standard output: %s",
+ strerror_r(errno, sbuf, sizeof(sbuf)));
goto out;
}
status = 0;
@@ -455,6 +469,7 @@ void pthread__unblock_sigwinch(void)
int main(int argc, const char **argv)
{
const char *cmd;
+ char sbuf[STRERR_BUFSIZE];
/* The page_size is placed in util object. */
page_size = sysconf(_SC_PAGE_SIZE);
@@ -550,7 +565,7 @@ int main(int argc, const char **argv)
}
fprintf(stderr, "Failed to run command '%s': %s\n",
- cmd, strerror(errno));
+ cmd, strerror_r(errno, sbuf, sizeof(sbuf)));
out:
return 1;
}
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 510c65f72858..220d44e44c1b 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -41,8 +41,6 @@ void pthread__unblock_sigwinch(void);
struct record_opts {
struct target target;
- int call_graph;
- bool call_graph_enabled;
bool group;
bool inherit_stat;
bool no_buffering;
@@ -60,7 +58,6 @@ struct record_opts {
u64 branch_stack;
u64 default_interval;
u64 user_interval;
- u16 stack_dump_size;
bool sample_transaction;
unsigned initial_delay;
};
diff --git a/tools/perf/scripts/perl/bin/failed-syscalls-record b/tools/perf/scripts/perl/bin/failed-syscalls-record
index 8104895a7b67..74685f318379 100644
--- a/tools/perf/scripts/perl/bin/failed-syscalls-record
+++ b/tools/perf/scripts/perl/bin/failed-syscalls-record
@@ -1,2 +1,3 @@
#!/bin/bash
-perf record -e raw_syscalls:sys_exit $@
+(perf record -e raw_syscalls:sys_exit $@ || \
+ perf record -e syscalls:sys_exit $@) 2> /dev/null
diff --git a/tools/perf/scripts/perl/failed-syscalls.pl b/tools/perf/scripts/perl/failed-syscalls.pl
index 94bc25a347eb..55e7ae4c5c88 100644
--- a/tools/perf/scripts/perl/failed-syscalls.pl
+++ b/tools/perf/scripts/perl/failed-syscalls.pl
@@ -26,6 +26,11 @@ sub raw_syscalls::sys_exit
}
}
+sub syscalls::sys_exit
+{
+ raw_syscalls::sys_exit(@_)
+}
+
sub trace_end
{
printf("\nfailed syscalls by comm:\n\n");
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
index de7211e4fa47..38dfb720fb6f 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
@@ -107,12 +107,13 @@ def taskState(state):
class EventHeaders:
def __init__(self, common_cpu, common_secs, common_nsecs,
- common_pid, common_comm):
+ common_pid, common_comm, common_callchain):
self.cpu = common_cpu
self.secs = common_secs
self.nsecs = common_nsecs
self.pid = common_pid
self.comm = common_comm
+ self.callchain = common_callchain
def ts(self):
return (self.secs * (10 ** 9)) + self.nsecs
diff --git a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
index 8104895a7b67..74685f318379 100644
--- a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
+++ b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
@@ -1,2 +1,3 @@
#!/bin/bash
-perf record -e raw_syscalls:sys_exit $@
+(perf record -e raw_syscalls:sys_exit $@ || \
+ perf record -e syscalls:sys_exit $@) 2> /dev/null
diff --git a/tools/perf/scripts/python/bin/sctop-record b/tools/perf/scripts/python/bin/sctop-record
index 4efbfaa7f6a5..d6940841e54f 100644
--- a/tools/perf/scripts/python/bin/sctop-record
+++ b/tools/perf/scripts/python/bin/sctop-record
@@ -1,2 +1,3 @@
#!/bin/bash
-perf record -e raw_syscalls:sys_enter $@
+(perf record -e raw_syscalls:sys_enter $@ || \
+ perf record -e syscalls:sys_enter $@) 2> /dev/null
diff --git a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
index 4efbfaa7f6a5..d6940841e54f 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
+++ b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
@@ -1,2 +1,3 @@
#!/bin/bash
-perf record -e raw_syscalls:sys_enter $@
+(perf record -e raw_syscalls:sys_enter $@ || \
+ perf record -e syscalls:sys_enter $@) 2> /dev/null
diff --git a/tools/perf/scripts/python/bin/syscall-counts-record b/tools/perf/scripts/python/bin/syscall-counts-record
index 4efbfaa7f6a5..d6940841e54f 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-record
+++ b/tools/perf/scripts/python/bin/syscall-counts-record
@@ -1,2 +1,3 @@
#!/bin/bash
-perf record -e raw_syscalls:sys_enter $@
+(perf record -e raw_syscalls:sys_enter $@ || \
+ perf record -e syscalls:sys_enter $@) 2> /dev/null
diff --git a/tools/perf/scripts/python/check-perf-trace.py b/tools/perf/scripts/python/check-perf-trace.py
index 4647a7694cf6..334599c6032c 100644
--- a/tools/perf/scripts/python/check-perf-trace.py
+++ b/tools/perf/scripts/python/check-perf-trace.py
@@ -27,7 +27,7 @@ def trace_end():
def irq__softirq_entry(event_name, context, common_cpu,
common_secs, common_nsecs, common_pid, common_comm,
- vec):
+ common_callchain, vec):
print_header(event_name, common_cpu, common_secs, common_nsecs,
common_pid, common_comm)
@@ -38,7 +38,7 @@ def irq__softirq_entry(event_name, context, common_cpu,
def kmem__kmalloc(event_name, context, common_cpu,
common_secs, common_nsecs, common_pid, common_comm,
- call_site, ptr, bytes_req, bytes_alloc,
+ common_callchain, call_site, ptr, bytes_req, bytes_alloc,
gfp_flags):
print_header(event_name, common_cpu, common_secs, common_nsecs,
common_pid, common_comm)
diff --git a/tools/perf/scripts/python/failed-syscalls-by-pid.py b/tools/perf/scripts/python/failed-syscalls-by-pid.py
index 85805fac4116..cafeff3d74db 100644
--- a/tools/perf/scripts/python/failed-syscalls-by-pid.py
+++ b/tools/perf/scripts/python/failed-syscalls-by-pid.py
@@ -39,7 +39,7 @@ def trace_end():
def raw_syscalls__sys_exit(event_name, context, common_cpu,
common_secs, common_nsecs, common_pid, common_comm,
- id, ret):
+ common_callchain, id, ret):
if (for_comm and common_comm != for_comm) or \
(for_pid and common_pid != for_pid ):
return
@@ -50,6 +50,11 @@ def raw_syscalls__sys_exit(event_name, context, common_cpu,
except TypeError:
syscalls[common_comm][common_pid][id][ret] = 1
+def syscalls__sys_exit(event_name, context, common_cpu,
+ common_secs, common_nsecs, common_pid, common_comm,
+ id, ret):
+ raw_syscalls__sys_exit(**locals())
+
def print_error_totals():
if for_comm is not None:
print "\nsyscall errors for %s:\n\n" % (for_comm),
diff --git a/tools/perf/scripts/python/futex-contention.py b/tools/perf/scripts/python/futex-contention.py
index 11e70a388d41..0f5cf437b602 100644
--- a/tools/perf/scripts/python/futex-contention.py
+++ b/tools/perf/scripts/python/futex-contention.py
@@ -21,7 +21,7 @@ thread_blocktime = {}
lock_waits = {} # long-lived stats on (tid,lock) blockage elapsed time
process_names = {} # long-lived pid-to-execname mapping
-def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm,
+def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm, callchain,
nr, uaddr, op, val, utime, uaddr2, val3):
cmd = op & FUTEX_CMD_MASK
if cmd != FUTEX_WAIT:
@@ -31,7 +31,7 @@ def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm,
thread_thislock[tid] = uaddr
thread_blocktime[tid] = nsecs(s, ns)
-def syscalls__sys_exit_futex(event, ctxt, cpu, s, ns, tid, comm,
+def syscalls__sys_exit_futex(event, ctxt, cpu, s, ns, tid, comm, callchain,
nr, ret):
if thread_blocktime.has_key(tid):
elapsed = nsecs(s, ns) - thread_blocktime[tid]
diff --git a/tools/perf/scripts/python/net_dropmonitor.py b/tools/perf/scripts/python/net_dropmonitor.py
index b5740599aabd..0b6ce8c253e8 100755
--- a/tools/perf/scripts/python/net_dropmonitor.py
+++ b/tools/perf/scripts/python/net_dropmonitor.py
@@ -66,7 +66,7 @@ def trace_end():
print_drop_table()
# called from perf, when it finds a correspoinding event
-def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm,
+def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, callchain,
skbaddr, location, protocol):
slocation = str(location)
try:
diff --git a/tools/perf/scripts/python/netdev-times.py b/tools/perf/scripts/python/netdev-times.py
index 9aa0a32972e8..4d21ef2d601d 100644
--- a/tools/perf/scripts/python/netdev-times.py
+++ b/tools/perf/scripts/python/netdev-times.py
@@ -224,75 +224,75 @@ def trace_end():
(len(rx_skb_list), of_count_rx_skb_list)
# called from perf, when it finds a correspoinding event
-def irq__softirq_entry(name, context, cpu, sec, nsec, pid, comm, vec):
+def irq__softirq_entry(name, context, cpu, sec, nsec, pid, comm, callchain, vec):
if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
return
event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
all_event_list.append(event_info)
-def irq__softirq_exit(name, context, cpu, sec, nsec, pid, comm, vec):
+def irq__softirq_exit(name, context, cpu, sec, nsec, pid, comm, callchain, vec):
if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
return
event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
all_event_list.append(event_info)
-def irq__softirq_raise(name, context, cpu, sec, nsec, pid, comm, vec):
+def irq__softirq_raise(name, context, cpu, sec, nsec, pid, comm, callchain, vec):
if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
return
event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
all_event_list.append(event_info)
def irq__irq_handler_entry(name, context, cpu, sec, nsec, pid, comm,
- irq, irq_name):
+ callchain, irq, irq_name):
event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
irq, irq_name)
all_event_list.append(event_info)
-def irq__irq_handler_exit(name, context, cpu, sec, nsec, pid, comm, irq, ret):
+def irq__irq_handler_exit(name, context, cpu, sec, nsec, pid, comm, callchain, irq, ret):
event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, irq, ret)
all_event_list.append(event_info)
-def napi__napi_poll(name, context, cpu, sec, nsec, pid, comm, napi, dev_name):
+def napi__napi_poll(name, context, cpu, sec, nsec, pid, comm, callchain, napi, dev_name):
event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
napi, dev_name)
all_event_list.append(event_info)
-def net__netif_receive_skb(name, context, cpu, sec, nsec, pid, comm, skbaddr,
+def net__netif_receive_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr,
skblen, dev_name):
event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
skbaddr, skblen, dev_name)
all_event_list.append(event_info)
-def net__netif_rx(name, context, cpu, sec, nsec, pid, comm, skbaddr,
+def net__netif_rx(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr,
skblen, dev_name):
event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
skbaddr, skblen, dev_name)
all_event_list.append(event_info)
-def net__net_dev_queue(name, context, cpu, sec, nsec, pid, comm,
+def net__net_dev_queue(name, context, cpu, sec, nsec, pid, comm, callchain,
skbaddr, skblen, dev_name):
event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
skbaddr, skblen, dev_name)
all_event_list.append(event_info)
-def net__net_dev_xmit(name, context, cpu, sec, nsec, pid, comm,
+def net__net_dev_xmit(name, context, cpu, sec, nsec, pid, comm, callchain,
skbaddr, skblen, rc, dev_name):
event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
skbaddr, skblen, rc ,dev_name)
all_event_list.append(event_info)
-def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm,
+def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, callchain,
skbaddr, protocol, location):
event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
skbaddr, protocol, location)
all_event_list.append(event_info)
-def skb__consume_skb(name, context, cpu, sec, nsec, pid, comm, skbaddr):
+def skb__consume_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr):
event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
skbaddr)
all_event_list.append(event_info)
-def skb__skb_copy_datagram_iovec(name, context, cpu, sec, nsec, pid, comm,
+def skb__skb_copy_datagram_iovec(name, context, cpu, sec, nsec, pid, comm, callchain,
skbaddr, skblen):
event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
skbaddr, skblen)
diff --git a/tools/perf/scripts/python/sched-migration.py b/tools/perf/scripts/python/sched-migration.py
index 74d55ec08aed..de66cb3b72c9 100644
--- a/tools/perf/scripts/python/sched-migration.py
+++ b/tools/perf/scripts/python/sched-migration.py
@@ -369,93 +369,92 @@ def trace_end():
def sched__sched_stat_runtime(event_name, context, common_cpu,
common_secs, common_nsecs, common_pid, common_comm,
- comm, pid, runtime, vruntime):
+ common_callchain, comm, pid, runtime, vruntime):
pass
def sched__sched_stat_iowait(event_name, context, common_cpu,
common_secs, common_nsecs, common_pid, common_comm,
- comm, pid, delay):
+ common_callchain, comm, pid, delay):
pass
def sched__sched_stat_sleep(event_name, context, common_cpu,
common_secs, common_nsecs, common_pid, common_comm,
- comm, pid, delay):
+ common_callchain, comm, pid, delay):
pass
def sched__sched_stat_wait(event_name, context, common_cpu,
common_secs, common_nsecs, common_pid, common_comm,
- comm, pid, delay):
+ common_callchain, comm, pid, delay):
pass
def sched__sched_process_fork(event_name, context, common_cpu,
common_secs, common_nsecs, common_pid, common_comm,
- parent_comm, parent_pid, child_comm, child_pid):
+ common_callchain, parent_comm, parent_pid, child_comm, child_pid):
pass
def sched__sched_process_wait(event_name, context, common_cpu,
common_secs, common_nsecs, common_pid, common_comm,
- comm, pid, prio):
+ common_callchain, comm, pid, prio):
pass
def sched__sched_process_exit(event_name, context, common_cpu,
common_secs, common_nsecs, common_pid, common_comm,
- comm, pid, prio):
+ common_callchain, comm, pid, prio):
pass
def sched__sched_process_free(event_name, context, common_cpu,
common_secs, common_nsecs, common_pid, common_comm,
- comm, pid, prio):
+ common_callchain, comm, pid, prio):
pass
def sched__sched_migrate_task(event_name, context, common_cpu,
common_secs, common_nsecs, common_pid, common_comm,
- comm, pid, prio, orig_cpu,
+ common_callchain, comm, pid, prio, orig_cpu,
dest_cpu):
headers = EventHeaders(common_cpu, common_secs, common_nsecs,
- common_pid, common_comm)
+ common_pid, common_comm, common_callchain)
parser.migrate(headers, pid, prio, orig_cpu, dest_cpu)
def sched__sched_switch(event_name, context, common_cpu,
- common_secs, common_nsecs, common_pid, common_comm,
+ common_secs, common_nsecs, common_pid, common_comm, common_callchain,
prev_comm, prev_pid, prev_prio, prev_state,
next_comm, next_pid, next_prio):
headers = EventHeaders(common_cpu, common_secs, common_nsecs,
- common_pid, common_comm)
+ common_pid, common_comm, common_callchain)
parser.sched_switch(headers, prev_comm, prev_pid, prev_prio, prev_state,
next_comm, next_pid, next_prio)
def sched__sched_wakeup_new(event_name, context, common_cpu,
common_secs, common_nsecs, common_pid, common_comm,
- comm, pid, prio, success,
+ common_callchain, comm, pid, prio, success,
target_cpu):
headers = EventHeaders(common_cpu, common_secs, common_nsecs,
- common_pid, common_comm)
+ common_pid, common_comm, common_callchain)
parser.wake_up(headers, comm, pid, success, target_cpu, 1)
def sched__sched_wakeup(event_name, context, common_cpu,
common_secs, common_nsecs, common_pid, common_comm,
- comm, pid, prio, success,
+ common_callchain, comm, pid, prio, success,
target_cpu):
headers = EventHeaders(common_cpu, common_secs, common_nsecs,
- common_pid, common_comm)
+ common_pid, common_comm, common_callchain)
parser.wake_up(headers, comm, pid, success, target_cpu, 0)
def sched__sched_wait_task(event_name, context, common_cpu,
common_secs, common_nsecs, common_pid, common_comm,
- comm, pid, prio):
+ common_callchain, comm, pid, prio):
pass
def sched__sched_kthread_stop_ret(event_name, context, common_cpu,
common_secs, common_nsecs, common_pid, common_comm,
- ret):
+ common_callchain, ret):
pass
def sched__sched_kthread_stop(event_name, context, common_cpu,
common_secs, common_nsecs, common_pid, common_comm,
- comm, pid):
+ common_callchain, comm, pid):
pass
-def trace_unhandled(event_name, context, common_cpu, common_secs, common_nsecs,
- common_pid, common_comm):
+def trace_unhandled(event_name, context, event_fields_dict):
pass
diff --git a/tools/perf/scripts/python/sctop.py b/tools/perf/scripts/python/sctop.py
index 42c267e292fa..61621b93affb 100644
--- a/tools/perf/scripts/python/sctop.py
+++ b/tools/perf/scripts/python/sctop.py
@@ -44,7 +44,7 @@ def trace_begin():
def raw_syscalls__sys_enter(event_name, context, common_cpu,
common_secs, common_nsecs, common_pid, common_comm,
- id, args):
+ common_callchain, id, args):
if for_comm is not None:
if common_comm != for_comm:
return
@@ -53,6 +53,11 @@ def raw_syscalls__sys_enter(event_name, context, common_cpu,
except TypeError:
syscalls[id] = 1
+def syscalls__sys_enter(event_name, context, common_cpu,
+ common_secs, common_nsecs, common_pid, common_comm,
+ id, args):
+ raw_syscalls__sys_enter(**locals())
+
def print_syscall_totals(interval):
while 1:
clear_term()
diff --git a/tools/perf/scripts/python/syscall-counts-by-pid.py b/tools/perf/scripts/python/syscall-counts-by-pid.py
index c64d1c55d745..daf314cc5dd3 100644
--- a/tools/perf/scripts/python/syscall-counts-by-pid.py
+++ b/tools/perf/scripts/python/syscall-counts-by-pid.py
@@ -38,7 +38,7 @@ def trace_end():
def raw_syscalls__sys_enter(event_name, context, common_cpu,
common_secs, common_nsecs, common_pid, common_comm,
- id, args):
+ common_callchain, id, args):
if (for_comm and common_comm != for_comm) or \
(for_pid and common_pid != for_pid ):
@@ -48,6 +48,11 @@ def raw_syscalls__sys_enter(event_name, context, common_cpu,
except TypeError:
syscalls[common_comm][common_pid][id] = 1
+def syscalls__sys_enter(event_name, context, common_cpu,
+ common_secs, common_nsecs, common_pid, common_comm,
+ id, args):
+ raw_syscalls__sys_enter(**locals())
+
def print_syscall_totals():
if for_comm is not None:
print "\nsyscall events for %s:\n\n" % (for_comm),
diff --git a/tools/perf/scripts/python/syscall-counts.py b/tools/perf/scripts/python/syscall-counts.py
index b435d3f188e8..e66a7730aeb5 100644
--- a/tools/perf/scripts/python/syscall-counts.py
+++ b/tools/perf/scripts/python/syscall-counts.py
@@ -35,7 +35,7 @@ def trace_end():
def raw_syscalls__sys_enter(event_name, context, common_cpu,
common_secs, common_nsecs, common_pid, common_comm,
- id, args):
+ common_callchain, id, args):
if for_comm is not None:
if common_comm != for_comm:
return
@@ -44,6 +44,11 @@ def raw_syscalls__sys_enter(event_name, context, common_cpu,
except TypeError:
syscalls[id] = 1
+def syscalls__sys_enter(event_name, context, common_cpu,
+ common_secs, common_nsecs, common_pid, common_comm,
+ id, args):
+ raw_syscalls__sys_enter(**locals())
+
def print_syscall_totals():
if for_comm is not None:
print "\nsyscall events for %s:\n\n" % (for_comm),
diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record
index e9bd6391f2ae..f710b92ccff6 100644
--- a/tools/perf/tests/attr/base-record
+++ b/tools/perf/tests/attr/base-record
@@ -1,7 +1,8 @@
[event]
fd=1
group_fd=-1
-flags=0
+# 0 or PERF_FLAG_FD_CLOEXEC flag
+flags=0|8
cpu=*
type=0|1
size=96
diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat
index 91cd48b399f3..dc3ada2470c0 100644
--- a/tools/perf/tests/attr/base-stat
+++ b/tools/perf/tests/attr/base-stat
@@ -1,7 +1,8 @@
[event]
fd=1
group_fd=-1
-flags=0
+# 0 or PERF_FLAG_FD_CLOEXEC flag
+flags=0|8
cpu=*
type=0
size=96
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index aba095489193..a02b035fd5aa 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -25,6 +25,7 @@
#include "tests.h"
#include "debug.h"
#include "perf.h"
+#include "cloexec.h"
static int fd1;
static int fd2;
@@ -78,7 +79,8 @@ static int bp_event(void *fn, int setup_signal)
pe.exclude_kernel = 1;
pe.exclude_hv = 1;
- fd = sys_perf_event_open(&pe, 0, -1, -1, 0);
+ fd = sys_perf_event_open(&pe, 0, -1, -1,
+ perf_event_open_cloexec_flag());
if (fd < 0) {
pr_debug("failed opening event %llx\n", pe.config);
return TEST_FAIL;
diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c
index 44ac82179708..e76537724491 100644
--- a/tools/perf/tests/bp_signal_overflow.c
+++ b/tools/perf/tests/bp_signal_overflow.c
@@ -24,6 +24,7 @@
#include "tests.h"
#include "debug.h"
#include "perf.h"
+#include "cloexec.h"
static int overflows;
@@ -91,7 +92,8 @@ int test__bp_signal_overflow(void)
pe.exclude_kernel = 1;
pe.exclude_hv = 1;
- fd = sys_perf_event_open(&pe, 0, -1, -1, 0);
+ fd = sys_perf_event_open(&pe, 0, -1, -1,
+ perf_event_open_cloexec_flag());
if (fd < 0) {
pr_debug("failed opening event %llx\n", pe.config);
return TEST_FAIL;
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 6f8b01bc6033..ac655b0700e7 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -154,6 +154,18 @@ static struct test {
.func = test__hists_cumulate,
},
{
+ .desc = "Test tracking with sched_switch",
+ .func = test__switch_tracking,
+ },
+ {
+ .desc = "Filter fds with revents mask in a fdarray",
+ .func = test__fdarray__filter,
+ },
+ {
+ .desc = "Add fd to a fdarray, making it autogrow",
+ .func = test__fdarray__add,
+ },
+ {
.func = NULL,
},
};
@@ -185,9 +197,11 @@ static bool perf_test__matches(int curr, int argc, const char *argv[])
static int run_test(struct test *test)
{
int status, err = -1, child = fork();
+ char sbuf[STRERR_BUFSIZE];
if (child < 0) {
- pr_err("failed to fork test: %s\n", strerror(errno));
+ pr_err("failed to fork test: %s\n",
+ strerror_r(errno, sbuf, sizeof(sbuf)));
return -1;
}
@@ -297,7 +311,7 @@ int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused)
symbol_conf.sort_by_name = true;
symbol_conf.try_vmlinux_path = true;
- if (symbol__init() < 0)
+ if (symbol__init(NULL) < 0)
return -1;
if (skip != NULL)
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index 630808cd7cc2..caaf37f079b1 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -10,6 +10,7 @@
#include "machine.h"
#include "symbol.h"
#include "tests.h"
+#include "debug.h"
static char *test_file(int size)
{
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index 465cdbc345cf..b8d8341b383e 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -2,6 +2,7 @@
#include "evsel.h"
#include "parse-events.h"
#include "tests.h"
+#include "debug.h"
static int perf_evsel__roundtrip_cache_name_test(void)
{
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index 35d7fdb2328d..52162425c969 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -1,6 +1,7 @@
#include <traceevent/event-parse.h>
#include "evsel.h"
#include "tests.h"
+#include "debug.h"
static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
int size, bool should_be_signed)
diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c
new file mode 100644
index 000000000000..d24b837951d4
--- /dev/null
+++ b/tools/perf/tests/fdarray.c
@@ -0,0 +1,174 @@
+#include <api/fd/array.h>
+#include "util/debug.h"
+#include "tests/tests.h"
+
+static void fdarray__init_revents(struct fdarray *fda, short revents)
+{
+ int fd;
+
+ fda->nr = fda->nr_alloc;
+
+ for (fd = 0; fd < fda->nr; ++fd) {
+ fda->entries[fd].fd = fda->nr - fd;
+ fda->entries[fd].revents = revents;
+ }
+}
+
+static int fdarray__fprintf_prefix(struct fdarray *fda, const char *prefix, FILE *fp)
+{
+ int printed = 0;
+
+ if (!verbose)
+ return 0;
+
+ printed += fprintf(fp, "\n%s: ", prefix);
+ return printed + fdarray__fprintf(fda, fp);
+}
+
+int test__fdarray__filter(void)
+{
+ int nr_fds, expected_fd[2], fd, err = TEST_FAIL;
+ struct fdarray *fda = fdarray__new(5, 5);
+
+ if (fda == NULL) {
+ pr_debug("\nfdarray__new() failed!");
+ goto out;
+ }
+
+ fdarray__init_revents(fda, POLLIN);
+ nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+ if (nr_fds != fda->nr_alloc) {
+ pr_debug("\nfdarray__filter()=%d != %d shouldn't have filtered anything",
+ nr_fds, fda->nr_alloc);
+ goto out_delete;
+ }
+
+ fdarray__init_revents(fda, POLLHUP);
+ nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+ if (nr_fds != 0) {
+ pr_debug("\nfdarray__filter()=%d != %d, should have filtered all fds",
+ nr_fds, fda->nr_alloc);
+ goto out_delete;
+ }
+
+ fdarray__init_revents(fda, POLLHUP);
+ fda->entries[2].revents = POLLIN;
+ expected_fd[0] = fda->entries[2].fd;
+
+ pr_debug("\nfiltering all but fda->entries[2]:");
+ fdarray__fprintf_prefix(fda, "before", stderr);
+ nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+ fdarray__fprintf_prefix(fda, " after", stderr);
+ if (nr_fds != 1) {
+ pr_debug("\nfdarray__filter()=%d != 1, should have left just one event", nr_fds);
+ goto out_delete;
+ }
+
+ if (fda->entries[0].fd != expected_fd[0]) {
+ pr_debug("\nfda->entries[0].fd=%d != %d\n",
+ fda->entries[0].fd, expected_fd[0]);
+ goto out_delete;
+ }
+
+ fdarray__init_revents(fda, POLLHUP);
+ fda->entries[0].revents = POLLIN;
+ expected_fd[0] = fda->entries[0].fd;
+ fda->entries[3].revents = POLLIN;
+ expected_fd[1] = fda->entries[3].fd;
+
+ pr_debug("\nfiltering all but (fda->entries[0], fda->entries[3]):");
+ fdarray__fprintf_prefix(fda, "before", stderr);
+ nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+ fdarray__fprintf_prefix(fda, " after", stderr);
+ if (nr_fds != 2) {
+ pr_debug("\nfdarray__filter()=%d != 2, should have left just two events",
+ nr_fds);
+ goto out_delete;
+ }
+
+ for (fd = 0; fd < 2; ++fd) {
+ if (fda->entries[fd].fd != expected_fd[fd]) {
+ pr_debug("\nfda->entries[%d].fd=%d != %d\n", fd,
+ fda->entries[fd].fd, expected_fd[fd]);
+ goto out_delete;
+ }
+ }
+
+ pr_debug("\n");
+
+ err = 0;
+out_delete:
+ fdarray__delete(fda);
+out:
+ return err;
+}
+
+int test__fdarray__add(void)
+{
+ int err = TEST_FAIL;
+ struct fdarray *fda = fdarray__new(2, 2);
+
+ if (fda == NULL) {
+ pr_debug("\nfdarray__new() failed!");
+ goto out;
+ }
+
+#define FDA_CHECK(_idx, _fd, _revents) \
+ if (fda->entries[_idx].fd != _fd) { \
+ pr_debug("\n%d: fda->entries[%d](%d) != %d!", \
+ __LINE__, _idx, fda->entries[1].fd, _fd); \
+ goto out_delete; \
+ } \
+ if (fda->entries[_idx].events != (_revents)) { \
+ pr_debug("\n%d: fda->entries[%d].revents(%d) != %d!", \
+ __LINE__, _idx, fda->entries[_idx].fd, _revents); \
+ goto out_delete; \
+ }
+
+#define FDA_ADD(_idx, _fd, _revents, _nr) \
+ if (fdarray__add(fda, _fd, _revents) < 0) { \
+ pr_debug("\n%d: fdarray__add(fda, %d, %d) failed!", \
+ __LINE__,_fd, _revents); \
+ goto out_delete; \
+ } \
+ if (fda->nr != _nr) { \
+ pr_debug("\n%d: fdarray__add(fda, %d, %d)=%d != %d", \
+ __LINE__,_fd, _revents, fda->nr, _nr); \
+ goto out_delete; \
+ } \
+ FDA_CHECK(_idx, _fd, _revents)
+
+ FDA_ADD(0, 1, POLLIN, 1);
+ FDA_ADD(1, 2, POLLERR, 2);
+
+ fdarray__fprintf_prefix(fda, "before growing array", stderr);
+
+ FDA_ADD(2, 35, POLLHUP, 3);
+
+ if (fda->entries == NULL) {
+ pr_debug("\nfdarray__add(fda, 35, POLLHUP) should have allocated fda->pollfd!");
+ goto out_delete;
+ }
+
+ fdarray__fprintf_prefix(fda, "after 3rd add", stderr);
+
+ FDA_ADD(3, 88, POLLIN | POLLOUT, 4);
+
+ fdarray__fprintf_prefix(fda, "after 4th add", stderr);
+
+ FDA_CHECK(0, 1, POLLIN);
+ FDA_CHECK(1, 2, POLLERR);
+ FDA_CHECK(2, 35, POLLHUP);
+ FDA_CHECK(3, 88, POLLIN | POLLOUT);
+
+#undef FDA_ADD
+#undef FDA_CHECK
+
+ pr_debug("\n");
+
+ err = 0;
+out_delete:
+ fdarray__delete(fda);
+out:
+ return err;
+}
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 142263492f6f..9b9622a33932 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -31,6 +31,7 @@ int test__basic_mmap(void)
unsigned int nr_events[nsyscalls],
expected_nr_events[nsyscalls], i, j;
struct perf_evsel *evsels[nsyscalls], *evsel;
+ char sbuf[STRERR_BUFSIZE];
threads = thread_map__new(-1, getpid(), UINT_MAX);
if (threads == NULL) {
@@ -49,7 +50,7 @@ int test__basic_mmap(void)
sched_setaffinity(0, sizeof(cpu_set), &cpu_set);
if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
pr_debug("sched_setaffinity() failed on CPU %d: %s ",
- cpus->map[0], strerror(errno));
+ cpus->map[0], strerror_r(errno, sbuf, sizeof(sbuf)));
goto out_free_cpus;
}
@@ -79,7 +80,7 @@ int test__basic_mmap(void)
if (perf_evsel__open(evsels[i], cpus, threads) < 0) {
pr_debug("failed to open counter: %s, "
"tweak /proc/sys/kernel/perf_event_paranoid?\n",
- strerror(errno));
+ strerror_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
}
@@ -89,7 +90,7 @@ int test__basic_mmap(void)
if (perf_evlist__mmap(evlist, 128, true) < 0) {
pr_debug("failed to mmap events: %d (%s)\n", errno,
- strerror(errno));
+ strerror_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
}
diff --git a/tools/perf/tests/open-syscall-all-cpus.c b/tools/perf/tests/open-syscall-all-cpus.c
index 5fecdbd2f5f7..8fa82d1700c7 100644
--- a/tools/perf/tests/open-syscall-all-cpus.c
+++ b/tools/perf/tests/open-syscall-all-cpus.c
@@ -12,6 +12,7 @@ int test__open_syscall_event_on_all_cpus(void)
unsigned int nr_open_calls = 111, i;
cpu_set_t cpu_set;
struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
+ char sbuf[STRERR_BUFSIZE];
if (threads == NULL) {
pr_debug("thread_map__new\n");
@@ -35,7 +36,7 @@ int test__open_syscall_event_on_all_cpus(void)
if (perf_evsel__open(evsel, cpus, threads) < 0) {
pr_debug("failed to open counter: %s, "
"tweak /proc/sys/kernel/perf_event_paranoid?\n",
- strerror(errno));
+ strerror_r(errno, sbuf, sizeof(sbuf)));
goto out_evsel_delete;
}
@@ -56,7 +57,7 @@ int test__open_syscall_event_on_all_cpus(void)
if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
pr_debug("sched_setaffinity() failed on CPU %d: %s ",
cpus->map[cpu],
- strerror(errno));
+ strerror_r(errno, sbuf, sizeof(sbuf)));
goto out_close_fd;
}
for (i = 0; i < ncalls; ++i) {
diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c
index c505ef2af245..127dcae0b760 100644
--- a/tools/perf/tests/open-syscall-tp-fields.c
+++ b/tools/perf/tests/open-syscall-tp-fields.c
@@ -3,6 +3,7 @@
#include "evsel.h"
#include "thread_map.h"
#include "tests.h"
+#include "debug.h"
int test__syscall_open_tp_fields(void)
{
@@ -21,6 +22,7 @@ int test__syscall_open_tp_fields(void)
struct perf_evlist *evlist = perf_evlist__new();
struct perf_evsel *evsel;
int err = -1, i, nr_events = 0, nr_polls = 0;
+ char sbuf[STRERR_BUFSIZE];
if (evlist == NULL) {
pr_debug("%s: perf_evlist__new\n", __func__);
@@ -47,13 +49,15 @@ int test__syscall_open_tp_fields(void)
err = perf_evlist__open(evlist);
if (err < 0) {
- pr_debug("perf_evlist__open: %s\n", strerror(errno));
+ pr_debug("perf_evlist__open: %s\n",
+ strerror_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
}
err = perf_evlist__mmap(evlist, UINT_MAX, false);
if (err < 0) {
- pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
+ pr_debug("perf_evlist__mmap: %s\n",
+ strerror_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
}
@@ -101,7 +105,7 @@ int test__syscall_open_tp_fields(void)
}
if (nr_events == before)
- poll(evlist->pollfd, evlist->nr_fds, 10);
+ perf_evlist__poll(evlist, 10);
if (++nr_polls > 5) {
pr_debug("%s: no events!\n", __func__);
diff --git a/tools/perf/tests/open-syscall.c b/tools/perf/tests/open-syscall.c
index c1dc7d25f38c..a33b2daae40f 100644
--- a/tools/perf/tests/open-syscall.c
+++ b/tools/perf/tests/open-syscall.c
@@ -9,6 +9,7 @@ int test__open_syscall_event(void)
struct perf_evsel *evsel;
unsigned int nr_open_calls = 111, i;
struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
+ char sbuf[STRERR_BUFSIZE];
if (threads == NULL) {
pr_debug("thread_map__new\n");
@@ -24,7 +25,7 @@ int test__open_syscall_event(void)
if (perf_evsel__open_per_thread(evsel, threads) < 0) {
pr_debug("failed to open counter: %s, "
"tweak /proc/sys/kernel/perf_event_paranoid?\n",
- strerror(errno));
+ strerror_r(errno, sbuf, sizeof(sbuf)));
goto out_evsel_delete;
}
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index deba66955f8c..5941927a4b7f 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -5,6 +5,7 @@
#include <api/fs/fs.h>
#include <api/fs/debugfs.h>
#include "tests.h"
+#include "debug.h"
#include <linux/hw_breakpoint.h>
#define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
index 905019f9b740..2c63ea658541 100644
--- a/tools/perf/tests/parse-no-sample-id-all.c
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -7,6 +7,7 @@
#include "evlist.h"
#include "header.h"
#include "util.h"
+#include "debug.h"
static int process_event(struct perf_evlist **pevlist, union perf_event *event)
{
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index aca1a83dd13a..7a228a2a070b 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -59,6 +59,7 @@ int test__PERF_RECORD(void)
int err = -1, errs = 0, i, wakeups = 0;
u32 cpu;
int total_events = 0, nr_events[PERF_RECORD_MAX] = { 0, };
+ char sbuf[STRERR_BUFSIZE];
if (evlist == NULL || argv == NULL) {
pr_debug("Not enough memory to create evlist\n");
@@ -100,7 +101,8 @@ int test__PERF_RECORD(void)
err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask);
if (err < 0) {
- pr_debug("sched__get_first_possible_cpu: %s\n", strerror(errno));
+ pr_debug("sched__get_first_possible_cpu: %s\n",
+ strerror_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
}
@@ -110,7 +112,8 @@ int test__PERF_RECORD(void)
* So that we can check perf_sample.cpu on all the samples.
*/
if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, &cpu_mask) < 0) {
- pr_debug("sched_setaffinity: %s\n", strerror(errno));
+ pr_debug("sched_setaffinity: %s\n",
+ strerror_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
}
@@ -120,7 +123,8 @@ int test__PERF_RECORD(void)
*/
err = perf_evlist__open(evlist);
if (err < 0) {
- pr_debug("perf_evlist__open: %s\n", strerror(errno));
+ pr_debug("perf_evlist__open: %s\n",
+ strerror_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
}
@@ -131,7 +135,8 @@ int test__PERF_RECORD(void)
*/
err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
if (err < 0) {
- pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
+ pr_debug("perf_evlist__mmap: %s\n",
+ strerror_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
}
@@ -263,7 +268,7 @@ int test__PERF_RECORD(void)
* perf_event_attr.wakeup_events, just PERF_EVENT_SAMPLE does.
*/
if (total_events == before && false)
- poll(evlist->pollfd, evlist->nr_fds, -1);
+ perf_evlist__poll(evlist, -1);
sleep(1);
if (++wakeups > 5) {
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index 3b7cd4d32dcb..f238442b238a 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -8,10 +8,9 @@
#include "evsel.h"
#include "thread_map.h"
#include "cpumap.h"
+#include "tsc.h"
#include "tests.h"
-#include "../arch/x86/util/tsc.h"
-
#define CHECK__(x) { \
while ((x) < 0) { \
pr_debug(#x " failed!\n"); \
@@ -26,15 +25,6 @@
} \
}
-static u64 rdtsc(void)
-{
- unsigned int low, high;
-
- asm volatile("rdtsc" : "=a" (low), "=d" (high));
-
- return low | ((u64)high) << 32;
-}
-
/**
* test__perf_time_to_tsc - test converting perf time to TSC.
*
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index 12b322fa3475..eeb68bb1972d 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -152,7 +152,7 @@ int test__pmu(void)
if (ret)
break;
- ret = perf_pmu__config_terms(&formats, &attr, terms);
+ ret = perf_pmu__config_terms(&formats, &attr, terms, false);
if (ret)
break;
diff --git a/tools/perf/tests/rdpmc.c b/tools/perf/tests/rdpmc.c
index e59143fd9e71..d31f2c4d9f64 100644
--- a/tools/perf/tests/rdpmc.c
+++ b/tools/perf/tests/rdpmc.c
@@ -6,6 +6,7 @@
#include "perf.h"
#include "debug.h"
#include "tests.h"
+#include "cloexec.h"
#if defined(__x86_64__) || defined(__i386__)
@@ -99,22 +100,25 @@ static int __test__rdpmc(void)
};
u64 delta_sum = 0;
struct sigaction sa;
+ char sbuf[STRERR_BUFSIZE];
sigfillset(&sa.sa_mask);
sa.sa_sigaction = segfault_handler;
sigaction(SIGSEGV, &sa, NULL);
- fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
+ fd = sys_perf_event_open(&attr, 0, -1, -1,
+ perf_event_open_cloexec_flag());
if (fd < 0) {
pr_err("Error: sys_perf_event_open() syscall returned "
- "with %d (%s)\n", fd, strerror(errno));
+ "with %d (%s)\n", fd,
+ strerror_r(errno, sbuf, sizeof(sbuf)));
return -1;
}
addr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, fd, 0);
if (addr == (void *)(-1)) {
pr_err("Error: mmap() syscall returned with (%s)\n",
- strerror(errno));
+ strerror_r(errno, sbuf, sizeof(sbuf)));
goto out_close;
}
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 7ae8d17db3d9..ca292f9a4ae2 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -4,6 +4,7 @@
#include "util.h"
#include "event.h"
#include "evsel.h"
+#include "debug.h"
#include "tests.h"
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 983d6b8562a8..1aa21c90731b 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -22,6 +22,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
volatile int tmp = 0;
u64 total_periods = 0;
int nr_samples = 0;
+ char sbuf[STRERR_BUFSIZE];
union perf_event *event;
struct perf_evsel *evsel;
struct perf_evlist *evlist;
@@ -62,14 +63,15 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
err = -errno;
pr_debug("Couldn't open evlist: %s\nHint: check %s, using %" PRIu64 " in this test.\n",
- strerror(errno), knob, (u64)attr.sample_freq);
+ strerror_r(errno, sbuf, sizeof(sbuf)),
+ knob, (u64)attr.sample_freq);
goto out_delete_evlist;
}
err = perf_evlist__mmap(evlist, 128, true);
if (err < 0) {
pr_debug("failed to mmap event: %d (%s)\n", errno,
- strerror(errno));
+ strerror_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
}
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
new file mode 100644
index 000000000000..cc68648c7c55
--- /dev/null
+++ b/tools/perf/tests/switch-tracking.c
@@ -0,0 +1,572 @@
+#include <sys/time.h>
+#include <sys/prctl.h>
+#include <time.h>
+#include <stdlib.h>
+
+#include "parse-events.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "tests.h"
+
+static int spin_sleep(void)
+{
+ struct timeval start, now, diff, maxtime;
+ struct timespec ts;
+ int err, i;
+
+ maxtime.tv_sec = 0;
+ maxtime.tv_usec = 50000;
+
+ err = gettimeofday(&start, NULL);
+ if (err)
+ return err;
+
+ /* Spin for 50ms */
+ while (1) {
+ for (i = 0; i < 1000; i++)
+ barrier();
+
+ err = gettimeofday(&now, NULL);
+ if (err)
+ return err;
+
+ timersub(&now, &start, &diff);
+ if (timercmp(&diff, &maxtime, > /* For checkpatch */))
+ break;
+ }
+
+ ts.tv_nsec = 50 * 1000 * 1000;
+ ts.tv_sec = 0;
+
+ /* Sleep for 50ms */
+ err = nanosleep(&ts, NULL);
+ if (err == EINTR)
+ err = 0;
+
+ return err;
+}
+
+struct switch_tracking {
+ struct perf_evsel *switch_evsel;
+ struct perf_evsel *cycles_evsel;
+ pid_t *tids;
+ int nr_tids;
+ int comm_seen[4];
+ int cycles_before_comm_1;
+ int cycles_between_comm_2_and_comm_3;
+ int cycles_after_comm_4;
+};
+
+static int check_comm(struct switch_tracking *switch_tracking,
+ union perf_event *event, const char *comm, int nr)
+{
+ if (event->header.type == PERF_RECORD_COMM &&
+ (pid_t)event->comm.pid == getpid() &&
+ (pid_t)event->comm.tid == getpid() &&
+ strcmp(event->comm.comm, comm) == 0) {
+ if (switch_tracking->comm_seen[nr]) {
+ pr_debug("Duplicate comm event\n");
+ return -1;
+ }
+ switch_tracking->comm_seen[nr] = 1;
+ pr_debug3("comm event: %s nr: %d\n", event->comm.comm, nr);
+ return 1;
+ }
+ return 0;
+}
+
+static int check_cpu(struct switch_tracking *switch_tracking, int cpu)
+{
+ int i, nr = cpu + 1;
+
+ if (cpu < 0)
+ return -1;
+
+ if (!switch_tracking->tids) {
+ switch_tracking->tids = calloc(nr, sizeof(pid_t));
+ if (!switch_tracking->tids)
+ return -1;
+ for (i = 0; i < nr; i++)
+ switch_tracking->tids[i] = -1;
+ switch_tracking->nr_tids = nr;
+ return 0;
+ }
+
+ if (cpu >= switch_tracking->nr_tids) {
+ void *addr;
+
+ addr = realloc(switch_tracking->tids, nr * sizeof(pid_t));
+ if (!addr)
+ return -1;
+ switch_tracking->tids = addr;
+ for (i = switch_tracking->nr_tids; i < nr; i++)
+ switch_tracking->tids[i] = -1;
+ switch_tracking->nr_tids = nr;
+ return 0;
+ }
+
+ return 0;
+}
+
+static int process_sample_event(struct perf_evlist *evlist,
+ union perf_event *event,
+ struct switch_tracking *switch_tracking)
+{
+ struct perf_sample sample;
+ struct perf_evsel *evsel;
+ pid_t next_tid, prev_tid;
+ int cpu, err;
+
+ if (perf_evlist__parse_sample(evlist, event, &sample)) {
+ pr_debug("perf_evlist__parse_sample failed\n");
+ return -1;
+ }
+
+ evsel = perf_evlist__id2evsel(evlist, sample.id);
+ if (evsel == switch_tracking->switch_evsel) {
+ next_tid = perf_evsel__intval(evsel, &sample, "next_pid");
+ prev_tid = perf_evsel__intval(evsel, &sample, "prev_pid");
+ cpu = sample.cpu;
+ pr_debug3("sched_switch: cpu: %d prev_tid %d next_tid %d\n",
+ cpu, prev_tid, next_tid);
+ err = check_cpu(switch_tracking, cpu);
+ if (err)
+ return err;
+ /*
+ * Check for no missing sched_switch events i.e. that the
+ * evsel->system_wide flag has worked.
+ */
+ if (switch_tracking->tids[cpu] != -1 &&
+ switch_tracking->tids[cpu] != prev_tid) {
+ pr_debug("Missing sched_switch events\n");
+ return -1;
+ }
+ switch_tracking->tids[cpu] = next_tid;
+ }
+
+ if (evsel == switch_tracking->cycles_evsel) {
+ pr_debug3("cycles event\n");
+ if (!switch_tracking->comm_seen[0])
+ switch_tracking->cycles_before_comm_1 = 1;
+ if (switch_tracking->comm_seen[1] &&
+ !switch_tracking->comm_seen[2])
+ switch_tracking->cycles_between_comm_2_and_comm_3 = 1;
+ if (switch_tracking->comm_seen[3])
+ switch_tracking->cycles_after_comm_4 = 1;
+ }
+
+ return 0;
+}
+
+static int process_event(struct perf_evlist *evlist, union perf_event *event,
+ struct switch_tracking *switch_tracking)
+{
+ if (event->header.type == PERF_RECORD_SAMPLE)
+ return process_sample_event(evlist, event, switch_tracking);
+
+ if (event->header.type == PERF_RECORD_COMM) {
+ int err, done = 0;
+
+ err = check_comm(switch_tracking, event, "Test COMM 1", 0);
+ if (err < 0)
+ return -1;
+ done += err;
+ err = check_comm(switch_tracking, event, "Test COMM 2", 1);
+ if (err < 0)
+ return -1;
+ done += err;
+ err = check_comm(switch_tracking, event, "Test COMM 3", 2);
+ if (err < 0)
+ return -1;
+ done += err;
+ err = check_comm(switch_tracking, event, "Test COMM 4", 3);
+ if (err < 0)
+ return -1;
+ done += err;
+ if (done != 1) {
+ pr_debug("Unexpected comm event\n");
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
+struct event_node {
+ struct list_head list;
+ union perf_event *event;
+ u64 event_time;
+};
+
+static int add_event(struct perf_evlist *evlist, struct list_head *events,
+ union perf_event *event)
+{
+ struct perf_sample sample;
+ struct event_node *node;
+
+ node = malloc(sizeof(struct event_node));
+ if (!node) {
+ pr_debug("malloc failed\n");
+ return -1;
+ }
+ node->event = event;
+ list_add(&node->list, events);
+
+ if (perf_evlist__parse_sample(evlist, event, &sample)) {
+ pr_debug("perf_evlist__parse_sample failed\n");
+ return -1;
+ }
+
+ if (!sample.time) {
+ pr_debug("event with no time\n");
+ return -1;
+ }
+
+ node->event_time = sample.time;
+
+ return 0;
+}
+
+static void free_event_nodes(struct list_head *events)
+{
+ struct event_node *node;
+
+ while (!list_empty(events)) {
+ node = list_entry(events->next, struct event_node, list);
+ list_del(&node->list);
+ free(node);
+ }
+}
+
+static int compar(const void *a, const void *b)
+{
+ const struct event_node *nodea = a;
+ const struct event_node *nodeb = b;
+ s64 cmp = nodea->event_time - nodeb->event_time;
+
+ return cmp;
+}
+
+static int process_events(struct perf_evlist *evlist,
+ struct switch_tracking *switch_tracking)
+{
+ union perf_event *event;
+ unsigned pos, cnt = 0;
+ LIST_HEAD(events);
+ struct event_node *events_array, *node;
+ int i, ret;
+
+ for (i = 0; i < evlist->nr_mmaps; i++) {
+ while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+ cnt += 1;
+ ret = add_event(evlist, &events, event);
+ perf_evlist__mmap_consume(evlist, i);
+ if (ret < 0)
+ goto out_free_nodes;
+ }
+ }
+
+ events_array = calloc(cnt, sizeof(struct event_node));
+ if (!events_array) {
+ pr_debug("calloc failed\n");
+ ret = -1;
+ goto out_free_nodes;
+ }
+
+ pos = 0;
+ list_for_each_entry(node, &events, list)
+ events_array[pos++] = *node;
+
+ qsort(events_array, cnt, sizeof(struct event_node), compar);
+
+ for (pos = 0; pos < cnt; pos++) {
+ ret = process_event(evlist, events_array[pos].event,
+ switch_tracking);
+ if (ret < 0)
+ goto out_free;
+ }
+
+ ret = 0;
+out_free:
+ pr_debug("%u events recorded\n", cnt);
+ free(events_array);
+out_free_nodes:
+ free_event_nodes(&events);
+ return ret;
+}
+
+/**
+ * test__switch_tracking - test using sched_switch and tracking events.
+ *
+ * This function implements a test that checks that sched_switch events and
+ * tracking events can be recorded for a workload (current process) using the
+ * evsel->system_wide and evsel->tracking flags (respectively) with other events
+ * sometimes enabled or disabled.
+ */
+int test__switch_tracking(void)
+{
+ const char *sched_switch = "sched:sched_switch";
+ struct switch_tracking switch_tracking = { .tids = NULL, };
+ struct record_opts opts = {
+ .mmap_pages = UINT_MAX,
+ .user_freq = UINT_MAX,
+ .user_interval = ULLONG_MAX,
+ .freq = 4000,
+ .target = {
+ .uses_mmap = true,
+ },
+ };
+ struct thread_map *threads = NULL;
+ struct cpu_map *cpus = NULL;
+ struct perf_evlist *evlist = NULL;
+ struct perf_evsel *evsel, *cpu_clocks_evsel, *cycles_evsel;
+ struct perf_evsel *switch_evsel, *tracking_evsel;
+ const char *comm;
+ int err = -1;
+
+ threads = thread_map__new(-1, getpid(), UINT_MAX);
+ if (!threads) {
+ pr_debug("thread_map__new failed!\n");
+ goto out_err;
+ }
+
+ cpus = cpu_map__new(NULL);
+ if (!cpus) {
+ pr_debug("cpu_map__new failed!\n");
+ goto out_err;
+ }
+
+ evlist = perf_evlist__new();
+ if (!evlist) {
+ pr_debug("perf_evlist__new failed!\n");
+ goto out_err;
+ }
+
+ perf_evlist__set_maps(evlist, cpus, threads);
+
+ /* First event */
+ err = parse_events(evlist, "cpu-clock:u");
+ if (err) {
+ pr_debug("Failed to parse event dummy:u\n");
+ goto out_err;
+ }
+
+ cpu_clocks_evsel = perf_evlist__last(evlist);
+
+ /* Second event */
+ err = parse_events(evlist, "cycles:u");
+ if (err) {
+ pr_debug("Failed to parse event cycles:u\n");
+ goto out_err;
+ }
+
+ cycles_evsel = perf_evlist__last(evlist);
+
+ /* Third event */
+ if (!perf_evlist__can_select_event(evlist, sched_switch)) {
+ fprintf(stderr, " (no sched_switch)");
+ err = 0;
+ goto out;
+ }
+
+ err = parse_events(evlist, sched_switch);
+ if (err) {
+ pr_debug("Failed to parse event %s\n", sched_switch);
+ goto out_err;
+ }
+
+ switch_evsel = perf_evlist__last(evlist);
+
+ perf_evsel__set_sample_bit(switch_evsel, CPU);
+ perf_evsel__set_sample_bit(switch_evsel, TIME);
+
+ switch_evsel->system_wide = true;
+ switch_evsel->no_aux_samples = true;
+ switch_evsel->immediate = true;
+
+ /* Test moving an event to the front */
+ if (cycles_evsel == perf_evlist__first(evlist)) {
+ pr_debug("cycles event already at front");
+ goto out_err;
+ }
+ perf_evlist__to_front(evlist, cycles_evsel);
+ if (cycles_evsel != perf_evlist__first(evlist)) {
+ pr_debug("Failed to move cycles event to front");
+ goto out_err;
+ }
+
+ perf_evsel__set_sample_bit(cycles_evsel, CPU);
+ perf_evsel__set_sample_bit(cycles_evsel, TIME);
+
+ /* Fourth event */
+ err = parse_events(evlist, "dummy:u");
+ if (err) {
+ pr_debug("Failed to parse event dummy:u\n");
+ goto out_err;
+ }
+
+ tracking_evsel = perf_evlist__last(evlist);
+
+ perf_evlist__set_tracking_event(evlist, tracking_evsel);
+
+ tracking_evsel->attr.freq = 0;
+ tracking_evsel->attr.sample_period = 1;
+
+ perf_evsel__set_sample_bit(tracking_evsel, TIME);
+
+ /* Config events */
+ perf_evlist__config(evlist, &opts);
+
+ /* Check moved event is still at the front */
+ if (cycles_evsel != perf_evlist__first(evlist)) {
+ pr_debug("Front event no longer at front");
+ goto out_err;
+ }
+
+ /* Check tracking event is tracking */
+ if (!tracking_evsel->attr.mmap || !tracking_evsel->attr.comm) {
+ pr_debug("Tracking event not tracking\n");
+ goto out_err;
+ }
+
+ /* Check non-tracking events are not tracking */
+ evlist__for_each(evlist, evsel) {
+ if (evsel != tracking_evsel) {
+ if (evsel->attr.mmap || evsel->attr.comm) {
+ pr_debug("Non-tracking event is tracking\n");
+ goto out_err;
+ }
+ }
+ }
+
+ if (perf_evlist__open(evlist) < 0) {
+ fprintf(stderr, " (not supported)");
+ err = 0;
+ goto out;
+ }
+
+ err = perf_evlist__mmap(evlist, UINT_MAX, false);
+ if (err) {
+ pr_debug("perf_evlist__mmap failed!\n");
+ goto out_err;
+ }
+
+ perf_evlist__enable(evlist);
+
+ err = perf_evlist__disable_event(evlist, cpu_clocks_evsel);
+ if (err) {
+ pr_debug("perf_evlist__disable_event failed!\n");
+ goto out_err;
+ }
+
+ err = spin_sleep();
+ if (err) {
+ pr_debug("spin_sleep failed!\n");
+ goto out_err;
+ }
+
+ comm = "Test COMM 1";
+ err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+ if (err) {
+ pr_debug("PR_SET_NAME failed!\n");
+ goto out_err;
+ }
+
+ err = perf_evlist__disable_event(evlist, cycles_evsel);
+ if (err) {
+ pr_debug("perf_evlist__disable_event failed!\n");
+ goto out_err;
+ }
+
+ comm = "Test COMM 2";
+ err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+ if (err) {
+ pr_debug("PR_SET_NAME failed!\n");
+ goto out_err;
+ }
+
+ err = spin_sleep();
+ if (err) {
+ pr_debug("spin_sleep failed!\n");
+ goto out_err;
+ }
+
+ comm = "Test COMM 3";
+ err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+ if (err) {
+ pr_debug("PR_SET_NAME failed!\n");
+ goto out_err;
+ }
+
+ err = perf_evlist__enable_event(evlist, cycles_evsel);
+ if (err) {
+ pr_debug("perf_evlist__disable_event failed!\n");
+ goto out_err;
+ }
+
+ comm = "Test COMM 4";
+ err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+ if (err) {
+ pr_debug("PR_SET_NAME failed!\n");
+ goto out_err;
+ }
+
+ err = spin_sleep();
+ if (err) {
+ pr_debug("spin_sleep failed!\n");
+ goto out_err;
+ }
+
+ perf_evlist__disable(evlist);
+
+ switch_tracking.switch_evsel = switch_evsel;
+ switch_tracking.cycles_evsel = cycles_evsel;
+
+ err = process_events(evlist, &switch_tracking);
+
+ zfree(&switch_tracking.tids);
+
+ if (err)
+ goto out_err;
+
+ /* Check all 4 comm events were seen i.e. that evsel->tracking works */
+ if (!switch_tracking.comm_seen[0] || !switch_tracking.comm_seen[1] ||
+ !switch_tracking.comm_seen[2] || !switch_tracking.comm_seen[3]) {
+ pr_debug("Missing comm events\n");
+ goto out_err;
+ }
+
+ /* Check cycles event got enabled */
+ if (!switch_tracking.cycles_before_comm_1) {
+ pr_debug("Missing cycles events\n");
+ goto out_err;
+ }
+
+ /* Check cycles event got disabled */
+ if (switch_tracking.cycles_between_comm_2_and_comm_3) {
+ pr_debug("cycles events even though event was disabled\n");
+ goto out_err;
+ }
+
+ /* Check cycles event got enabled again */
+ if (!switch_tracking.cycles_after_comm_4) {
+ pr_debug("Missing cycles events\n");
+ goto out_err;
+ }
+out:
+ if (evlist) {
+ perf_evlist__disable(evlist);
+ perf_evlist__delete(evlist);
+ } else {
+ cpu_map__delete(cpus);
+ thread_map__delete(threads);
+ }
+
+ return err;
+
+out_err:
+ err = -1;
+ goto out;
+}
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 5ff3db318f12..3a8fedef83bc 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -42,6 +42,7 @@ int test__task_exit(void)
.uses_mmap = true,
};
const char *argv[] = { "true", NULL };
+ char sbuf[STRERR_BUFSIZE];
signal(SIGCHLD, sig_handler);
@@ -82,13 +83,14 @@ int test__task_exit(void)
err = perf_evlist__open(evlist);
if (err < 0) {
- pr_debug("Couldn't open the evlist: %s\n", strerror(-err));
+ pr_debug("Couldn't open the evlist: %s\n",
+ strerror_r(-err, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
}
if (perf_evlist__mmap(evlist, 128, true) < 0) {
pr_debug("failed to mmap events: %d (%s)\n", errno,
- strerror(errno));
+ strerror_r(errno, sbuf, sizeof(sbuf)));
goto out_delete_evlist;
}
@@ -103,7 +105,7 @@ retry:
}
if (!exited || !nr_exit) {
- poll(evlist->pollfd, evlist->nr_fds, -1);
+ perf_evlist__poll(evlist, -1);
goto retry;
}
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index ed64790a395f..00e776a87a9c 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -48,6 +48,9 @@ int test__mmap_thread_lookup(void);
int test__thread_mg_share(void);
int test__hists_output(void);
int test__hists_cumulate(void);
+int test__switch_tracking(void);
+int test__fdarray__filter(void);
+int test__fdarray__add(void);
#if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
#ifdef HAVE_DWARF_UNWIND_SUPPORT
diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c
index 2b2e0dbe114f..b028499dd3cf 100644
--- a/tools/perf/tests/thread-mg-share.c
+++ b/tools/perf/tests/thread-mg-share.c
@@ -2,6 +2,7 @@
#include "machine.h"
#include "thread.h"
#include "map.h"
+#include "debug.h"
int test__thread_mg_share(void)
{
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index 3ccf6e14f89b..6680fa5cb9dd 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -150,7 +150,7 @@ unsigned int ui_browser__rb_tree_refresh(struct ui_browser *browser)
while (nd != NULL) {
ui_browser__gotorc(browser, row, 0);
browser->write(browser, nd, row);
- if (++row == browser->height)
+ if (++row == browser->rows)
break;
nd = rb_next(nd);
}
@@ -166,7 +166,7 @@ bool ui_browser__is_current_entry(struct ui_browser *browser, unsigned row)
void ui_browser__refresh_dimensions(struct ui_browser *browser)
{
browser->width = SLtt_Screen_Cols - 1;
- browser->height = SLtt_Screen_Rows - 2;
+ browser->height = browser->rows = SLtt_Screen_Rows - 2;
browser->y = 1;
browser->x = 0;
}
@@ -250,7 +250,10 @@ int ui_browser__show(struct ui_browser *browser, const char *title,
int err;
va_list ap;
- ui_browser__refresh_dimensions(browser);
+ if (browser->refresh_dimensions == NULL)
+ browser->refresh_dimensions = ui_browser__refresh_dimensions;
+
+ browser->refresh_dimensions(browser);
pthread_mutex_lock(&ui__lock);
__ui_browser__show_title(browser, title);
@@ -279,7 +282,7 @@ static void ui_browser__scrollbar_set(struct ui_browser *browser)
{
int height = browser->height, h = 0, pct = 0,
col = browser->width,
- row = browser->y - 1;
+ row = 0;
if (browser->nr_entries > 1) {
pct = ((browser->index * (browser->height - 1)) /
@@ -367,7 +370,7 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs)
if (key == K_RESIZE) {
ui__refresh_dimensions(false);
- ui_browser__refresh_dimensions(browser);
+ browser->refresh_dimensions(browser);
__ui_browser__show_title(browser, browser->title);
ui_helpline__puts(browser->helpline);
continue;
@@ -389,7 +392,7 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs)
if (browser->index == browser->nr_entries - 1)
break;
++browser->index;
- if (browser->index == browser->top_idx + browser->height) {
+ if (browser->index == browser->top_idx + browser->rows) {
++browser->top_idx;
browser->seek(browser, +1, SEEK_CUR);
}
@@ -405,10 +408,10 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs)
break;
case K_PGDN:
case ' ':
- if (browser->top_idx + browser->height > browser->nr_entries - 1)
+ if (browser->top_idx + browser->rows > browser->nr_entries - 1)
break;
- offset = browser->height;
+ offset = browser->rows;
if (browser->index + offset > browser->nr_entries - 1)
offset = browser->nr_entries - 1 - browser->index;
browser->index += offset;
@@ -419,10 +422,10 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs)
if (browser->top_idx == 0)
break;
- if (browser->top_idx < browser->height)
+ if (browser->top_idx < browser->rows)
offset = browser->top_idx;
else
- offset = browser->height;
+ offset = browser->rows;
browser->index -= offset;
browser->top_idx -= offset;
@@ -432,7 +435,7 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs)
ui_browser__reset_index(browser);
break;
case K_END:
- offset = browser->height - 1;
+ offset = browser->rows - 1;
if (offset >= browser->nr_entries)
offset = browser->nr_entries - 1;
@@ -462,7 +465,7 @@ unsigned int ui_browser__list_head_refresh(struct ui_browser *browser)
if (!browser->filter || !browser->filter(browser, pos)) {
ui_browser__gotorc(browser, row, 0);
browser->write(browser, pos, row);
- if (++row == browser->height)
+ if (++row == browser->rows)
break;
}
}
@@ -587,7 +590,7 @@ unsigned int ui_browser__argv_refresh(struct ui_browser *browser)
if (!browser->filter || !browser->filter(browser, *pos)) {
ui_browser__gotorc(browser, row, 0);
browser->write(browser, pos, row);
- if (++row == browser->height)
+ if (++row == browser->rows)
break;
}
@@ -623,7 +626,7 @@ static void __ui_browser__line_arrow_up(struct ui_browser *browser,
SLsmg_set_char_set(1);
- if (start < browser->top_idx + browser->height) {
+ if (start < browser->top_idx + browser->rows) {
row = start - browser->top_idx;
ui_browser__gotorc(browser, row, column);
SLsmg_write_char(SLSMG_LLCORN_CHAR);
@@ -633,7 +636,7 @@ static void __ui_browser__line_arrow_up(struct ui_browser *browser,
if (row-- == 0)
goto out;
} else
- row = browser->height - 1;
+ row = browser->rows - 1;
if (end > browser->top_idx)
end_row = end - browser->top_idx;
@@ -675,8 +678,8 @@ static void __ui_browser__line_arrow_down(struct ui_browser *browser,
} else
row = 0;
- if (end >= browser->top_idx + browser->height)
- end_row = browser->height - 1;
+ if (end >= browser->top_idx + browser->rows)
+ end_row = browser->rows - 1;
else
end_row = end - browser->top_idx;
@@ -684,7 +687,7 @@ static void __ui_browser__line_arrow_down(struct ui_browser *browser,
SLsmg_draw_vline(end_row - row + 1);
ui_browser__gotorc(browser, end_row, column);
- if (end < browser->top_idx + browser->height) {
+ if (end < browser->top_idx + browser->rows) {
SLsmg_write_char(SLSMG_LLCORN_CHAR);
ui_browser__gotorc(browser, end_row, column + 1);
SLsmg_write_char(SLSMG_HLINE_CHAR);
diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h
index 03d4d6295f10..92ae72113965 100644
--- a/tools/perf/ui/browser.h
+++ b/tools/perf/ui/browser.h
@@ -14,11 +14,12 @@
struct ui_browser {
u64 index, top_idx;
void *top, *entries;
- u16 y, x, width, height;
+ u16 y, x, width, height, rows;
int current_color;
void *priv;
const char *title;
char *helpline;
+ void (*refresh_dimensions)(struct ui_browser *browser);
unsigned int (*refresh)(struct ui_browser *browser);
void (*write)(struct ui_browser *browser, void *entry, int row);
void (*seek)(struct ui_browser *browser, off_t offset, int whence);
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 04a229aa5c0f..8f60a970404f 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -10,6 +10,7 @@
#include "../../util/pstack.h"
#include "../../util/sort.h"
#include "../../util/util.h"
+#include "../../util/top.h"
#include "../../arch/common.h"
#include "../browser.h"
@@ -26,6 +27,7 @@ struct hist_browser {
struct map_symbol *selection;
int print_seq;
bool show_dso;
+ bool show_headers;
float min_pcnt;
u64 nr_non_filtered_entries;
u64 nr_callchain_rows;
@@ -33,8 +35,7 @@ struct hist_browser {
extern void hist_browser__init_hpp(void);
-static int hists__browser_title(struct hists *hists, char *bf, size_t size,
- const char *ev_name);
+static int hists__browser_title(struct hists *hists, char *bf, size_t size);
static void hist_browser__update_nr_entries(struct hist_browser *hb);
static struct rb_node *hists__filter_entries(struct rb_node *nd,
@@ -57,11 +58,42 @@ static u32 hist_browser__nr_entries(struct hist_browser *hb)
return nr_entries + hb->nr_callchain_rows;
}
-static void hist_browser__refresh_dimensions(struct hist_browser *browser)
+static void hist_browser__update_rows(struct hist_browser *hb)
{
+ struct ui_browser *browser = &hb->b;
+ u16 header_offset = hb->show_headers ? 1 : 0, index_row;
+
+ browser->rows = browser->height - header_offset;
+ /*
+ * Verify if we were at the last line and that line isn't
+ * visibe because we now show the header line(s).
+ */
+ index_row = browser->index - browser->top_idx;
+ if (index_row >= browser->rows)
+ browser->index -= index_row - browser->rows + 1;
+}
+
+static void hist_browser__refresh_dimensions(struct ui_browser *browser)
+{
+ struct hist_browser *hb = container_of(browser, struct hist_browser, b);
+
/* 3 == +/- toggle symbol before actual hist_entry rendering */
- browser->b.width = 3 + (hists__sort_list_width(browser->hists) +
- sizeof("[k]"));
+ browser->width = 3 + (hists__sort_list_width(hb->hists) + sizeof("[k]"));
+ /*
+ * FIXME: Just keeping existing behaviour, but this really should be
+ * before updating browser->width, as it will invalidate the
+ * calculation above. Fix this and the fallout in another
+ * changeset.
+ */
+ ui_browser__refresh_dimensions(browser);
+ hist_browser__update_rows(hb);
+}
+
+static void hist_browser__gotorc(struct hist_browser *browser, int row, int column)
+{
+ u16 header_offset = browser->show_headers ? 1 : 0;
+
+ ui_browser__gotorc(&browser->b, row + header_offset, column);
}
static void hist_browser__reset(struct hist_browser *browser)
@@ -74,7 +106,7 @@ static void hist_browser__reset(struct hist_browser *browser)
hist_browser__update_nr_entries(browser);
browser->b.nr_entries = hist_browser__nr_entries(browser);
- hist_browser__refresh_dimensions(browser);
+ hist_browser__refresh_dimensions(&browser->b);
ui_browser__reset_index(&browser->b);
}
@@ -197,8 +229,10 @@ static void callchain_node__init_have_children(struct callchain_node *node)
{
struct callchain_list *chain;
- list_for_each_entry(chain, &node->val, list)
+ if (!list_empty(&node->val)) {
+ chain = list_entry(node->val.prev, struct callchain_list, list);
chain->ms.has_children = !RB_EMPTY_ROOT(&node->rb_root);
+ }
callchain_node__init_have_children_rb_tree(node);
}
@@ -346,7 +380,7 @@ static void ui_browser__warn_lost_events(struct ui_browser *browser)
"Or reduce the sampling frequency.");
}
-static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
+static int hist_browser__run(struct hist_browser *browser,
struct hist_browser_timer *hbt)
{
int key;
@@ -356,8 +390,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
browser->b.entries = &browser->hists->entries;
browser->b.nr_entries = hist_browser__nr_entries(browser);
- hist_browser__refresh_dimensions(browser);
- hists__browser_title(browser->hists, title, sizeof(title), ev_name);
+ hists__browser_title(browser->hists, title, sizeof(title));
if (ui_browser__show(&browser->b, title,
"Press '?' for help on key bindings") < 0)
@@ -384,7 +417,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
ui_browser__warn_lost_events(&browser->b);
}
- hists__browser_title(browser->hists, title, sizeof(title), ev_name);
+ hists__browser_title(browser->hists, title, sizeof(title));
ui_browser__show_title(&browser->b, title);
continue;
}
@@ -393,10 +426,10 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
struct hist_entry *h = rb_entry(browser->b.top,
struct hist_entry, rb_node);
ui_helpline__pop();
- ui_helpline__fpush("%d: nr_ent=(%d,%d), height=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d",
+ ui_helpline__fpush("%d: nr_ent=(%d,%d), rows=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d",
seq++, browser->b.nr_entries,
browser->hists->nr_entries,
- browser->b.height,
+ browser->b.rows,
browser->b.index,
browser->b.top_idx,
h->row_offset, h->nr_rows);
@@ -410,6 +443,10 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
/* Expand the whole world. */
hist_browser__set_folding(browser, true);
break;
+ case 'H':
+ browser->show_headers = !browser->show_headers;
+ hist_browser__update_rows(browser);
+ break;
case K_ENTER:
if (hist_browser__toggle_fold(browser))
break;
@@ -440,26 +477,87 @@ static char *callchain_list__sym_name(struct callchain_list *cl,
return bf;
}
+struct callchain_print_arg {
+ /* for hists browser */
+ off_t row_offset;
+ bool is_current_entry;
+
+ /* for file dump */
+ FILE *fp;
+ int printed;
+};
+
+typedef void (*print_callchain_entry_fn)(struct hist_browser *browser,
+ struct callchain_list *chain,
+ const char *str, int offset,
+ unsigned short row,
+ struct callchain_print_arg *arg);
+
+static void hist_browser__show_callchain_entry(struct hist_browser *browser,
+ struct callchain_list *chain,
+ const char *str, int offset,
+ unsigned short row,
+ struct callchain_print_arg *arg)
+{
+ int color, width;
+ char folded_sign = callchain_list__folded(chain);
+
+ color = HE_COLORSET_NORMAL;
+ width = browser->b.width - (offset + 2);
+ if (ui_browser__is_current_entry(&browser->b, row)) {
+ browser->selection = &chain->ms;
+ color = HE_COLORSET_SELECTED;
+ arg->is_current_entry = true;
+ }
+
+ ui_browser__set_color(&browser->b, color);
+ hist_browser__gotorc(browser, row, 0);
+ slsmg_write_nstring(" ", offset);
+ slsmg_printf("%c ", folded_sign);
+ slsmg_write_nstring(str, width);
+}
+
+static void hist_browser__fprintf_callchain_entry(struct hist_browser *b __maybe_unused,
+ struct callchain_list *chain,
+ const char *str, int offset,
+ unsigned short row __maybe_unused,
+ struct callchain_print_arg *arg)
+{
+ char folded_sign = callchain_list__folded(chain);
+
+ arg->printed += fprintf(arg->fp, "%*s%c %s\n", offset, " ",
+ folded_sign, str);
+}
+
+typedef bool (*check_output_full_fn)(struct hist_browser *browser,
+ unsigned short row);
+
+static bool hist_browser__check_output_full(struct hist_browser *browser,
+ unsigned short row)
+{
+ return browser->b.rows == row;
+}
+
+static bool hist_browser__check_dump_full(struct hist_browser *browser __maybe_unused,
+ unsigned short row __maybe_unused)
+{
+ return false;
+}
+
#define LEVEL_OFFSET_STEP 3
-static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *browser,
- struct callchain_node *chain_node,
- u64 total, int level,
- unsigned short row,
- off_t *row_offset,
- bool *is_current_entry)
+static int hist_browser__show_callchain(struct hist_browser *browser,
+ struct rb_root *root, int level,
+ unsigned short row, u64 total,
+ print_callchain_entry_fn print,
+ struct callchain_print_arg *arg,
+ check_output_full_fn is_output_full)
{
struct rb_node *node;
- int first_row = row, width, offset = level * LEVEL_OFFSET_STEP;
- u64 new_total, remaining;
+ int first_row = row, offset = level * LEVEL_OFFSET_STEP;
+ u64 new_total;
- if (callchain_param.mode == CHAIN_GRAPH_REL)
- new_total = chain_node->children_hit;
- else
- new_total = total;
-
- remaining = new_total;
- node = rb_first(&chain_node->rb_root);
+ node = rb_first(root);
while (node) {
struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
struct rb_node *next = rb_next(node);
@@ -469,30 +567,28 @@ static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *browse
int first = true;
int extra_offset = 0;
- remaining -= cumul;
-
list_for_each_entry(chain, &child->val, list) {
char bf[1024], *alloc_str;
const char *str;
- int color;
bool was_first = first;
if (first)
first = false;
- else
+ else if (level > 1)
extra_offset = LEVEL_OFFSET_STEP;
folded_sign = callchain_list__folded(chain);
- if (*row_offset != 0) {
- --*row_offset;
+ if (arg->row_offset != 0) {
+ arg->row_offset--;
goto do_next;
}
alloc_str = NULL;
str = callchain_list__sym_name(chain, bf, sizeof(bf),
browser->show_dso);
- if (was_first) {
- double percent = cumul * 100.0 / new_total;
+
+ if (was_first && level > 1) {
+ double percent = cumul * 100.0 / total;
if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0)
str = "Not enough memory!";
@@ -500,22 +596,11 @@ static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *browse
str = alloc_str;
}
- color = HE_COLORSET_NORMAL;
- width = browser->b.width - (offset + extra_offset + 2);
- if (ui_browser__is_current_entry(&browser->b, row)) {
- browser->selection = &chain->ms;
- color = HE_COLORSET_SELECTED;
- *is_current_entry = true;
- }
+ print(browser, chain, str, offset + extra_offset, row, arg);
- ui_browser__set_color(&browser->b, color);
- ui_browser__gotorc(&browser->b, row, 0);
- slsmg_write_nstring(" ", offset + extra_offset);
- slsmg_printf("%c ", folded_sign);
- slsmg_write_nstring(str, width);
free(alloc_str);
- if (++row == browser->b.height)
+ if (is_output_full(browser, ++row))
goto out;
do_next:
if (folded_sign == '+')
@@ -524,89 +609,21 @@ do_next:
if (folded_sign == '-') {
const int new_level = level + (extra_offset ? 2 : 1);
- row += hist_browser__show_callchain_node_rb_tree(browser, child, new_total,
- new_level, row, row_offset,
- is_current_entry);
- }
- if (row == browser->b.height)
- goto out;
- node = next;
- }
-out:
- return row - first_row;
-}
-
-static int hist_browser__show_callchain_node(struct hist_browser *browser,
- struct callchain_node *node,
- int level, unsigned short row,
- off_t *row_offset,
- bool *is_current_entry)
-{
- struct callchain_list *chain;
- int first_row = row,
- offset = level * LEVEL_OFFSET_STEP,
- width = browser->b.width - offset;
- char folded_sign = ' ';
-
- list_for_each_entry(chain, &node->val, list) {
- char bf[1024], *s;
- int color;
-
- folded_sign = callchain_list__folded(chain);
- if (*row_offset != 0) {
- --*row_offset;
- continue;
- }
+ if (callchain_param.mode == CHAIN_GRAPH_REL)
+ new_total = child->children_hit;
+ else
+ new_total = total;
- color = HE_COLORSET_NORMAL;
- if (ui_browser__is_current_entry(&browser->b, row)) {
- browser->selection = &chain->ms;
- color = HE_COLORSET_SELECTED;
- *is_current_entry = true;
+ row += hist_browser__show_callchain(browser, &child->rb_root,
+ new_level, row, new_total,
+ print, arg, is_output_full);
}
-
- s = callchain_list__sym_name(chain, bf, sizeof(bf),
- browser->show_dso);
- ui_browser__gotorc(&browser->b, row, 0);
- ui_browser__set_color(&browser->b, color);
- slsmg_write_nstring(" ", offset);
- slsmg_printf("%c ", folded_sign);
- slsmg_write_nstring(s, width - 2);
-
- if (++row == browser->b.height)
- goto out;
- }
-
- if (folded_sign == '-')
- row += hist_browser__show_callchain_node_rb_tree(browser, node,
- browser->hists->stats.total_period,
- level + 1, row,
- row_offset,
- is_current_entry);
-out:
- return row - first_row;
-}
-
-static int hist_browser__show_callchain(struct hist_browser *browser,
- struct rb_root *chain,
- int level, unsigned short row,
- off_t *row_offset,
- bool *is_current_entry)
-{
- struct rb_node *nd;
- int first_row = row;
-
- for (nd = rb_first(chain); nd; nd = rb_next(nd)) {
- struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
-
- row += hist_browser__show_callchain_node(browser, node, level,
- row, row_offset,
- is_current_entry);
- if (row == browser->b.height)
+ if (is_output_full(browser, row))
break;
+ node = next;
}
-
+out:
return row - first_row;
}
@@ -619,17 +636,18 @@ struct hpp_arg {
static int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...)
{
struct hpp_arg *arg = hpp->ptr;
- int ret;
+ int ret, len;
va_list args;
double percent;
va_start(args, fmt);
+ len = va_arg(args, int);
percent = va_arg(args, double);
va_end(args);
ui_browser__set_percent_color(arg->b, percent, arg->current_entry);
- ret = scnprintf(hpp->buf, hpp->size, fmt, percent);
+ ret = scnprintf(hpp->buf, hpp->size, fmt, len, percent);
slsmg_printf("%s", hpp->buf);
advance_hpp(hpp, ret);
@@ -643,12 +661,12 @@ static u64 __hpp_get_##_field(struct hist_entry *he) \
} \
\
static int \
-hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,\
+hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt, \
struct perf_hpp *hpp, \
struct hist_entry *he) \
{ \
- return __hpp__fmt(hpp, he, __hpp_get_##_field, " %6.2f%%", \
- __hpp__slsmg_color_printf, true); \
+ return hpp__fmt(fmt, hpp, he, __hpp_get_##_field, " %*.2f%%", \
+ __hpp__slsmg_color_printf, true); \
}
#define __HPP_COLOR_ACC_PERCENT_FN(_type, _field) \
@@ -658,18 +676,20 @@ static u64 __hpp_get_acc_##_field(struct hist_entry *he) \
} \
\
static int \
-hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,\
+hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt, \
struct perf_hpp *hpp, \
struct hist_entry *he) \
{ \
if (!symbol_conf.cumulate_callchain) { \
- int ret = scnprintf(hpp->buf, hpp->size, "%8s", "N/A"); \
+ int len = fmt->user_len ?: fmt->len; \
+ int ret = scnprintf(hpp->buf, hpp->size, \
+ "%*s", len, "N/A"); \
slsmg_printf("%s", hpp->buf); \
\
return ret; \
} \
- return __hpp__fmt(hpp, he, __hpp_get_acc_##_field, " %6.2f%%", \
- __hpp__slsmg_color_printf, true); \
+ return hpp__fmt(fmt, hpp, he, __hpp_get_acc_##_field, \
+ " %*.2f%%", __hpp__slsmg_color_printf, true); \
}
__HPP_COLOR_PERCENT_FN(overhead, period)
@@ -733,7 +753,7 @@ static int hist_browser__show_entry(struct hist_browser *browser,
.ptr = &arg,
};
- ui_browser__gotorc(&browser->b, row, 0);
+ hist_browser__gotorc(browser, row, 0);
perf_hpp__for_each_format(fmt) {
if (perf_hpp__should_skip(fmt))
@@ -777,17 +797,72 @@ static int hist_browser__show_entry(struct hist_browser *browser,
} else
--row_offset;
- if (folded_sign == '-' && row != browser->b.height) {
- printed += hist_browser__show_callchain(browser, &entry->sorted_chain,
- 1, row, &row_offset,
- &current_entry);
- if (current_entry)
+ if (folded_sign == '-' && row != browser->b.rows) {
+ u64 total = hists__total_period(entry->hists);
+ struct callchain_print_arg arg = {
+ .row_offset = row_offset,
+ .is_current_entry = current_entry,
+ };
+
+ printed += hist_browser__show_callchain(browser,
+ &entry->sorted_chain, 1, row, total,
+ hist_browser__show_callchain_entry, &arg,
+ hist_browser__check_output_full);
+
+ if (arg.is_current_entry)
browser->he_selection = entry;
}
return printed;
}
+static int advance_hpp_check(struct perf_hpp *hpp, int inc)
+{
+ advance_hpp(hpp, inc);
+ return hpp->size <= 0;
+}
+
+static int hists__scnprintf_headers(char *buf, size_t size, struct hists *hists)
+{
+ struct perf_hpp dummy_hpp = {
+ .buf = buf,
+ .size = size,
+ };
+ struct perf_hpp_fmt *fmt;
+ size_t ret = 0;
+
+ if (symbol_conf.use_callchain) {
+ ret = scnprintf(buf, size, " ");
+ if (advance_hpp_check(&dummy_hpp, ret))
+ return ret;
+ }
+
+ perf_hpp__for_each_format(fmt) {
+ if (perf_hpp__should_skip(fmt))
+ continue;
+
+ ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
+ if (advance_hpp_check(&dummy_hpp, ret))
+ break;
+
+ ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, " ");
+ if (advance_hpp_check(&dummy_hpp, ret))
+ break;
+ }
+
+ return ret;
+}
+
+static void hist_browser__show_headers(struct hist_browser *browser)
+{
+ char headers[1024];
+
+ hists__scnprintf_headers(headers, sizeof(headers), browser->hists);
+ ui_browser__gotorc(&browser->b, 0, 0);
+ ui_browser__set_color(&browser->b, HE_COLORSET_ROOT);
+ slsmg_write_nstring(headers, browser->b.width + 1);
+}
+
static void ui_browser__hists_init_top(struct ui_browser *browser)
{
if (browser->top == NULL) {
@@ -801,9 +876,15 @@ static void ui_browser__hists_init_top(struct ui_browser *browser)
static unsigned int hist_browser__refresh(struct ui_browser *browser)
{
unsigned row = 0;
+ u16 header_offset = 0;
struct rb_node *nd;
struct hist_browser *hb = container_of(browser, struct hist_browser, b);
+ if (hb->show_headers) {
+ hist_browser__show_headers(hb);
+ header_offset = 1;
+ }
+
ui_browser__hists_init_top(browser);
for (nd = browser->top; nd; nd = rb_next(nd)) {
@@ -818,11 +899,11 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser)
continue;
row += hist_browser__show_entry(hb, h, row);
- if (row == browser->height)
+ if (row == browser->rows)
break;
}
- return row;
+ return row + header_offset;
}
static struct rb_node *hists__filter_entries(struct rb_node *nd,
@@ -984,113 +1065,21 @@ do_offset:
}
}
-static int hist_browser__fprintf_callchain_node_rb_tree(struct hist_browser *browser,
- struct callchain_node *chain_node,
- u64 total, int level,
- FILE *fp)
-{
- struct rb_node *node;
- int offset = level * LEVEL_OFFSET_STEP;
- u64 new_total, remaining;
- int printed = 0;
-
- if (callchain_param.mode == CHAIN_GRAPH_REL)
- new_total = chain_node->children_hit;
- else
- new_total = total;
-
- remaining = new_total;
- node = rb_first(&chain_node->rb_root);
- while (node) {
- struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
- struct rb_node *next = rb_next(node);
- u64 cumul = callchain_cumul_hits(child);
- struct callchain_list *chain;
- char folded_sign = ' ';
- int first = true;
- int extra_offset = 0;
-
- remaining -= cumul;
-
- list_for_each_entry(chain, &child->val, list) {
- char bf[1024], *alloc_str;
- const char *str;
- bool was_first = first;
-
- if (first)
- first = false;
- else
- extra_offset = LEVEL_OFFSET_STEP;
-
- folded_sign = callchain_list__folded(chain);
-
- alloc_str = NULL;
- str = callchain_list__sym_name(chain, bf, sizeof(bf),
- browser->show_dso);
- if (was_first) {
- double percent = cumul * 100.0 / new_total;
-
- if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0)
- str = "Not enough memory!";
- else
- str = alloc_str;
- }
-
- printed += fprintf(fp, "%*s%c %s\n", offset + extra_offset, " ", folded_sign, str);
- free(alloc_str);
- if (folded_sign == '+')
- break;
- }
-
- if (folded_sign == '-') {
- const int new_level = level + (extra_offset ? 2 : 1);
- printed += hist_browser__fprintf_callchain_node_rb_tree(browser, child, new_total,
- new_level, fp);
- }
-
- node = next;
- }
-
- return printed;
-}
-
-static int hist_browser__fprintf_callchain_node(struct hist_browser *browser,
- struct callchain_node *node,
- int level, FILE *fp)
-{
- struct callchain_list *chain;
- int offset = level * LEVEL_OFFSET_STEP;
- char folded_sign = ' ';
- int printed = 0;
-
- list_for_each_entry(chain, &node->val, list) {
- char bf[1024], *s;
-
- folded_sign = callchain_list__folded(chain);
- s = callchain_list__sym_name(chain, bf, sizeof(bf), browser->show_dso);
- printed += fprintf(fp, "%*s%c %s\n", offset, " ", folded_sign, s);
- }
-
- if (folded_sign == '-')
- printed += hist_browser__fprintf_callchain_node_rb_tree(browser, node,
- browser->hists->stats.total_period,
- level + 1, fp);
- return printed;
-}
-
static int hist_browser__fprintf_callchain(struct hist_browser *browser,
- struct rb_root *chain, int level, FILE *fp)
+ struct hist_entry *he, FILE *fp)
{
- struct rb_node *nd;
- int printed = 0;
-
- for (nd = rb_first(chain); nd; nd = rb_next(nd)) {
- struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
+ u64 total = hists__total_period(he->hists);
+ struct callchain_print_arg arg = {
+ .fp = fp,
+ };
- printed += hist_browser__fprintf_callchain_node(browser, node, level, fp);
- }
+ if (symbol_conf.cumulate_callchain)
+ total = he->stat_acc->period;
- return printed;
+ hist_browser__show_callchain(browser, &he->sorted_chain, 1, 0, total,
+ hist_browser__fprintf_callchain_entry, &arg,
+ hist_browser__check_dump_full);
+ return arg.printed;
}
static int hist_browser__fprintf_entry(struct hist_browser *browser,
@@ -1129,7 +1118,7 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser,
printed += fprintf(fp, "%s\n", rtrim(s));
if (folded_sign == '-')
- printed += hist_browser__fprintf_callchain(browser, &he->sorted_chain, 1, fp);
+ printed += hist_browser__fprintf_callchain(browser, he, fp);
return printed;
}
@@ -1191,8 +1180,10 @@ static struct hist_browser *hist_browser__new(struct hists *hists)
if (browser) {
browser->hists = hists;
browser->b.refresh = hist_browser__refresh;
+ browser->b.refresh_dimensions = hist_browser__refresh_dimensions;
browser->b.seek = ui_browser__hists_seek;
browser->b.use_navkeypressed = true;
+ browser->show_headers = symbol_conf.show_hist_headers;
}
return browser;
@@ -1213,8 +1204,7 @@ static struct thread *hist_browser__selected_thread(struct hist_browser *browser
return browser->he_selection->thread;
}
-static int hists__browser_title(struct hists *hists, char *bf, size_t size,
- const char *ev_name)
+static int hists__browser_title(struct hists *hists, char *bf, size_t size)
{
char unit;
int printed;
@@ -1223,6 +1213,7 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size,
unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
u64 nr_events = hists->stats.total_period;
struct perf_evsel *evsel = hists_to_evsel(hists);
+ const char *ev_name = perf_evsel__name(evsel);
char buf[512];
size_t buflen = sizeof(buf);
@@ -1390,7 +1381,7 @@ static void hist_browser__update_nr_entries(struct hist_browser *hb)
}
static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
- const char *helpline, const char *ev_name,
+ const char *helpline,
bool left_exits,
struct hist_browser_timer *hbt,
float min_pcnt,
@@ -1406,6 +1397,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
char buf[64];
char script_opt[64];
int delay_secs = hbt ? hbt->refresh : 0;
+ struct perf_hpp_fmt *fmt;
#define HIST_BROWSER_HELP_COMMON \
"h/?/F1 Show this window\n" \
@@ -1422,6 +1414,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
"d Zoom into current DSO\n" \
"E Expand all callchains\n" \
"F Toggle percentage of filtered entries\n" \
+ "H Display column headers\n" \
/* help messages are sorted by lexical order of the hotkey */
const char report_help[] = HIST_BROWSER_HELP_COMMON
@@ -1436,6 +1429,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
"P Print histograms to perf.hist.N\n"
"t Zoom into current Thread\n"
"V Verbose (DSO names in callchains, etc)\n"
+ "z Toggle zeroing of samples\n"
"/ Filter symbol by name";
if (browser == NULL)
@@ -1454,6 +1448,12 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
memset(options, 0, sizeof(options));
+ perf_hpp__for_each_format(fmt)
+ perf_hpp__reset_width(fmt, hists);
+
+ if (symbol_conf.col_width_list_str)
+ perf_hpp__set_user_width(symbol_conf.col_width_list_str);
+
while (1) {
const struct thread *thread = NULL;
const struct dso *dso = NULL;
@@ -1465,7 +1465,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
nr_options = 0;
- key = hist_browser__run(browser, ev_name, hbt);
+ key = hist_browser__run(browser, hbt);
if (browser->he_selection != NULL) {
thread = hist_browser__selected_thread(browser);
@@ -1530,6 +1530,13 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
case 'F':
symbol_conf.filter_relative ^= 1;
continue;
+ case 'z':
+ if (!is_report_browser(hbt)) {
+ struct perf_top *top = hbt->arg;
+
+ top->zero = !top->zero;
+ }
+ continue;
case K_F1:
case 'h':
case '?':
@@ -1843,7 +1850,7 @@ static int perf_evsel_menu__run(struct perf_evsel_menu *menu,
{
struct perf_evlist *evlist = menu->b.priv;
struct perf_evsel *pos;
- const char *ev_name, *title = "Available samples";
+ const char *title = "Available samples";
int delay_secs = hbt ? hbt->refresh : 0;
int key;
@@ -1876,9 +1883,8 @@ browse_hists:
*/
if (hbt)
hbt->timer(hbt->arg);
- ev_name = perf_evsel__name(pos);
key = perf_evsel__hists_browse(pos, nr_events, help,
- ev_name, true, hbt,
+ true, hbt,
menu->min_pcnt,
menu->env);
ui_browser__show_title(&menu->b, title);
@@ -1982,10 +1988,9 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
single_entry:
if (nr_entries == 1) {
struct perf_evsel *first = perf_evlist__first(evlist);
- const char *ev_name = perf_evsel__name(first);
return perf_evsel__hists_browse(first, nr_entries, help,
- ev_name, false, hbt, min_pcnt,
+ false, hbt, min_pcnt,
env);
}
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 6ca60e482cdc..f3fa4258b256 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -11,6 +11,7 @@
static int __percent_color_snprintf(struct perf_hpp *hpp, const char *fmt, ...)
{
int ret = 0;
+ int len;
va_list args;
double percent;
const char *markup;
@@ -18,6 +19,7 @@ static int __percent_color_snprintf(struct perf_hpp *hpp, const char *fmt, ...)
size_t size = hpp->size;
va_start(args, fmt);
+ len = va_arg(args, int);
percent = va_arg(args, double);
va_end(args);
@@ -25,7 +27,7 @@ static int __percent_color_snprintf(struct perf_hpp *hpp, const char *fmt, ...)
if (markup)
ret += scnprintf(buf, size, markup);
- ret += scnprintf(buf + ret, size - ret, fmt, percent);
+ ret += scnprintf(buf + ret, size - ret, fmt, len, percent);
if (markup)
ret += scnprintf(buf + ret, size - ret, "</span>");
@@ -39,12 +41,12 @@ static u64 he_get_##_field(struct hist_entry *he) \
return he->stat._field; \
} \
\
-static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \
+static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt, \
struct perf_hpp *hpp, \
struct hist_entry *he) \
{ \
- return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%", \
- __percent_color_snprintf, true); \
+ return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%", \
+ __percent_color_snprintf, true); \
}
#define __HPP_COLOR_ACC_PERCENT_FN(_type, _field) \
@@ -57,8 +59,8 @@ static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,
struct perf_hpp *hpp, \
struct hist_entry *he) \
{ \
- return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, " %6.2f%%", \
- __percent_color_snprintf, true); \
+ return hpp__fmt_acc(fmt, hpp, he, he_get_acc_##_field, " %*.2f%%", \
+ __percent_color_snprintf, true); \
}
__HPP_COLOR_PERCENT_FN(overhead, period)
@@ -205,10 +207,8 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
if (perf_hpp__is_sort_entry(fmt))
sym_col = col_idx;
- fmt->header(fmt, &hpp, hists_to_evsel(hists));
-
gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
- -1, ltrim(s),
+ -1, fmt->name,
renderer, "markup",
col_idx++, NULL);
}
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 498adb23c02e..2af18376b077 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -15,9 +15,9 @@
__ret; \
})
-int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
- hpp_field_fn get_field, const char *fmt,
- hpp_snprint_fn print_fn, bool fmt_percent)
+static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
+ hpp_field_fn get_field, const char *fmt, int len,
+ hpp_snprint_fn print_fn, bool fmt_percent)
{
int ret;
struct hists *hists = he->hists;
@@ -32,9 +32,9 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
if (total)
percent = 100.0 * get_field(he) / total;
- ret = hpp__call_print_fn(hpp, print_fn, fmt, percent);
+ ret = hpp__call_print_fn(hpp, print_fn, fmt, len, percent);
} else
- ret = hpp__call_print_fn(hpp, print_fn, fmt, get_field(he));
+ ret = hpp__call_print_fn(hpp, print_fn, fmt, len, get_field(he));
if (perf_evsel__is_group_event(evsel)) {
int prev_idx, idx_delta;
@@ -60,19 +60,19 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
*/
if (fmt_percent) {
ret += hpp__call_print_fn(hpp, print_fn,
- fmt, 0.0);
+ fmt, len, 0.0);
} else {
ret += hpp__call_print_fn(hpp, print_fn,
- fmt, 0ULL);
+ fmt, len, 0ULL);
}
}
if (fmt_percent) {
- ret += hpp__call_print_fn(hpp, print_fn, fmt,
+ ret += hpp__call_print_fn(hpp, print_fn, fmt, len,
100.0 * period / total);
} else {
ret += hpp__call_print_fn(hpp, print_fn, fmt,
- period);
+ len, period);
}
prev_idx = perf_evsel__group_idx(evsel);
@@ -86,10 +86,10 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
*/
if (fmt_percent) {
ret += hpp__call_print_fn(hpp, print_fn,
- fmt, 0.0);
+ fmt, len, 0.0);
} else {
ret += hpp__call_print_fn(hpp, print_fn,
- fmt, 0ULL);
+ fmt, len, 0ULL);
}
}
}
@@ -104,16 +104,35 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
return ret;
}
-int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he,
- hpp_field_fn get_field, const char *fmt,
- hpp_snprint_fn print_fn, bool fmt_percent)
+int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he, hpp_field_fn get_field,
+ const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent)
+{
+ int len = fmt->user_len ?: fmt->len;
+
+ if (symbol_conf.field_sep) {
+ return __hpp__fmt(hpp, he, get_field, fmtstr, 1,
+ print_fn, fmt_percent);
+ }
+
+ if (fmt_percent)
+ len -= 2; /* 2 for a space and a % sign */
+ else
+ len -= 1;
+
+ return __hpp__fmt(hpp, he, get_field, fmtstr, len, print_fn, fmt_percent);
+}
+
+int hpp__fmt_acc(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he, hpp_field_fn get_field,
+ const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent)
{
if (!symbol_conf.cumulate_callchain) {
- return snprintf(hpp->buf, hpp->size, "%*s",
- fmt_percent ? 8 : 12, "N/A");
+ int len = fmt->user_len ?: fmt->len;
+ return snprintf(hpp->buf, hpp->size, " %*s", len - 1, "N/A");
}
- return __hpp__fmt(hpp, he, get_field, fmt, print_fn, fmt_percent);
+ return hpp__fmt(fmt, hpp, he, get_field, fmtstr, print_fn, fmt_percent);
}
static int field_cmp(u64 field_a, u64 field_b)
@@ -190,30 +209,26 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b,
return ret;
}
-#define __HPP_HEADER_FN(_type, _str, _min_width, _unit_width) \
-static int hpp__header_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \
- struct perf_hpp *hpp, \
- struct perf_evsel *evsel) \
-{ \
- int len = _min_width; \
- \
- if (symbol_conf.event_group) \
- len = max(len, evsel->nr_members * _unit_width); \
- \
- return scnprintf(hpp->buf, hpp->size, "%*s", len, _str); \
-}
-
-#define __HPP_WIDTH_FN(_type, _min_width, _unit_width) \
-static int hpp__width_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \
- struct perf_hpp *hpp __maybe_unused, \
- struct perf_evsel *evsel) \
-{ \
- int len = _min_width; \
- \
- if (symbol_conf.event_group) \
- len = max(len, evsel->nr_members * _unit_width); \
- \
- return len; \
+static int hpp__width_fn(struct perf_hpp_fmt *fmt,
+ struct perf_hpp *hpp __maybe_unused,
+ struct perf_evsel *evsel)
+{
+ int len = fmt->user_len ?: fmt->len;
+
+ if (symbol_conf.event_group)
+ len = max(len, evsel->nr_members * fmt->len);
+
+ if (len < (int)strlen(fmt->name))
+ len = strlen(fmt->name);
+
+ return len;
+}
+
+static int hpp__header_fn(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct perf_evsel *evsel)
+{
+ int len = hpp__width_fn(fmt, hpp, evsel);
+ return scnprintf(hpp->buf, hpp->size, "%*s", len, fmt->name);
}
static int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
@@ -221,11 +236,12 @@ static int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
va_list args;
ssize_t ssize = hpp->size;
double percent;
- int ret;
+ int ret, len;
va_start(args, fmt);
+ len = va_arg(args, int);
percent = va_arg(args, double);
- ret = value_color_snprintf(hpp->buf, hpp->size, fmt, percent);
+ ret = percent_color_len_snprintf(hpp->buf, hpp->size, fmt, len, percent);
va_end(args);
return (ret >= ssize) ? (ssize - 1) : ret;
@@ -250,20 +266,19 @@ static u64 he_get_##_field(struct hist_entry *he) \
return he->stat._field; \
} \
\
-static int hpp__color_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \
+static int hpp__color_##_type(struct perf_hpp_fmt *fmt, \
struct perf_hpp *hpp, struct hist_entry *he) \
{ \
- return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%", \
- hpp_color_scnprintf, true); \
+ return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%", \
+ hpp_color_scnprintf, true); \
}
#define __HPP_ENTRY_PERCENT_FN(_type, _field) \
-static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused, \
+static int hpp__entry_##_type(struct perf_hpp_fmt *fmt, \
struct perf_hpp *hpp, struct hist_entry *he) \
{ \
- const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%"; \
- return __hpp__fmt(hpp, he, he_get_##_field, fmt, \
- hpp_entry_scnprintf, true); \
+ return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%", \
+ hpp_entry_scnprintf, true); \
}
#define __HPP_SORT_FN(_type, _field) \
@@ -278,20 +293,19 @@ static u64 he_get_acc_##_field(struct hist_entry *he) \
return he->stat_acc->_field; \
} \
\
-static int hpp__color_##_type(struct perf_hpp_fmt *fmt __maybe_unused, \
+static int hpp__color_##_type(struct perf_hpp_fmt *fmt, \
struct perf_hpp *hpp, struct hist_entry *he) \
{ \
- return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, " %6.2f%%", \
- hpp_color_scnprintf, true); \
+ return hpp__fmt_acc(fmt, hpp, he, he_get_acc_##_field, " %*.2f%%", \
+ hpp_color_scnprintf, true); \
}
#define __HPP_ENTRY_ACC_PERCENT_FN(_type, _field) \
-static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused, \
+static int hpp__entry_##_type(struct perf_hpp_fmt *fmt, \
struct perf_hpp *hpp, struct hist_entry *he) \
{ \
- const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%"; \
- return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, fmt, \
- hpp_entry_scnprintf, true); \
+ return hpp__fmt_acc(fmt, hpp, he, he_get_acc_##_field, " %*.2f%%", \
+ hpp_entry_scnprintf, true); \
}
#define __HPP_SORT_ACC_FN(_type, _field) \
@@ -306,12 +320,11 @@ static u64 he_get_raw_##_field(struct hist_entry *he) \
return he->stat._field; \
} \
\
-static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused, \
+static int hpp__entry_##_type(struct perf_hpp_fmt *fmt, \
struct perf_hpp *hpp, struct hist_entry *he) \
{ \
- const char *fmt = symbol_conf.field_sep ? " %"PRIu64 : " %11"PRIu64; \
- return __hpp__fmt(hpp, he, he_get_raw_##_field, fmt, \
- hpp_entry_scnprintf, false); \
+ return hpp__fmt(fmt, hpp, he, he_get_raw_##_field, " %*"PRIu64, \
+ hpp_entry_scnprintf, false); \
}
#define __HPP_SORT_RAW_FN(_type, _field) \
@@ -321,37 +334,29 @@ static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b) \
}
-#define HPP_PERCENT_FNS(_type, _str, _field, _min_width, _unit_width) \
-__HPP_HEADER_FN(_type, _str, _min_width, _unit_width) \
-__HPP_WIDTH_FN(_type, _min_width, _unit_width) \
+#define HPP_PERCENT_FNS(_type, _field) \
__HPP_COLOR_PERCENT_FN(_type, _field) \
__HPP_ENTRY_PERCENT_FN(_type, _field) \
__HPP_SORT_FN(_type, _field)
-#define HPP_PERCENT_ACC_FNS(_type, _str, _field, _min_width, _unit_width)\
-__HPP_HEADER_FN(_type, _str, _min_width, _unit_width) \
-__HPP_WIDTH_FN(_type, _min_width, _unit_width) \
+#define HPP_PERCENT_ACC_FNS(_type, _field) \
__HPP_COLOR_ACC_PERCENT_FN(_type, _field) \
__HPP_ENTRY_ACC_PERCENT_FN(_type, _field) \
__HPP_SORT_ACC_FN(_type, _field)
-#define HPP_RAW_FNS(_type, _str, _field, _min_width, _unit_width) \
-__HPP_HEADER_FN(_type, _str, _min_width, _unit_width) \
-__HPP_WIDTH_FN(_type, _min_width, _unit_width) \
+#define HPP_RAW_FNS(_type, _field) \
__HPP_ENTRY_RAW_FN(_type, _field) \
__HPP_SORT_RAW_FN(_type, _field)
-__HPP_HEADER_FN(overhead_self, "Self", 8, 8)
-
-HPP_PERCENT_FNS(overhead, "Overhead", period, 8, 8)
-HPP_PERCENT_FNS(overhead_sys, "sys", period_sys, 8, 8)
-HPP_PERCENT_FNS(overhead_us, "usr", period_us, 8, 8)
-HPP_PERCENT_FNS(overhead_guest_sys, "guest sys", period_guest_sys, 9, 8)
-HPP_PERCENT_FNS(overhead_guest_us, "guest usr", period_guest_us, 9, 8)
-HPP_PERCENT_ACC_FNS(overhead_acc, "Children", period, 8, 8)
+HPP_PERCENT_FNS(overhead, period)
+HPP_PERCENT_FNS(overhead_sys, period_sys)
+HPP_PERCENT_FNS(overhead_us, period_us)
+HPP_PERCENT_FNS(overhead_guest_sys, period_guest_sys)
+HPP_PERCENT_FNS(overhead_guest_us, period_guest_us)
+HPP_PERCENT_ACC_FNS(overhead_acc, period)
-HPP_RAW_FNS(samples, "Samples", nr_events, 12, 12)
-HPP_RAW_FNS(period, "Period", period, 12, 12)
+HPP_RAW_FNS(samples, nr_events)
+HPP_RAW_FNS(period, period)
static int64_t hpp__nop_cmp(struct hist_entry *a __maybe_unused,
struct hist_entry *b __maybe_unused)
@@ -359,47 +364,50 @@ static int64_t hpp__nop_cmp(struct hist_entry *a __maybe_unused,
return 0;
}
-#define HPP__COLOR_PRINT_FNS(_name) \
+#define HPP__COLOR_PRINT_FNS(_name, _fn) \
{ \
- .header = hpp__header_ ## _name, \
- .width = hpp__width_ ## _name, \
- .color = hpp__color_ ## _name, \
- .entry = hpp__entry_ ## _name, \
+ .name = _name, \
+ .header = hpp__header_fn, \
+ .width = hpp__width_fn, \
+ .color = hpp__color_ ## _fn, \
+ .entry = hpp__entry_ ## _fn, \
.cmp = hpp__nop_cmp, \
.collapse = hpp__nop_cmp, \
- .sort = hpp__sort_ ## _name, \
+ .sort = hpp__sort_ ## _fn, \
}
-#define HPP__COLOR_ACC_PRINT_FNS(_name) \
+#define HPP__COLOR_ACC_PRINT_FNS(_name, _fn) \
{ \
- .header = hpp__header_ ## _name, \
- .width = hpp__width_ ## _name, \
- .color = hpp__color_ ## _name, \
- .entry = hpp__entry_ ## _name, \
+ .name = _name, \
+ .header = hpp__header_fn, \
+ .width = hpp__width_fn, \
+ .color = hpp__color_ ## _fn, \
+ .entry = hpp__entry_ ## _fn, \
.cmp = hpp__nop_cmp, \
.collapse = hpp__nop_cmp, \
- .sort = hpp__sort_ ## _name, \
+ .sort = hpp__sort_ ## _fn, \
}
-#define HPP__PRINT_FNS(_name) \
+#define HPP__PRINT_FNS(_name, _fn) \
{ \
- .header = hpp__header_ ## _name, \
- .width = hpp__width_ ## _name, \
- .entry = hpp__entry_ ## _name, \
+ .name = _name, \
+ .header = hpp__header_fn, \
+ .width = hpp__width_fn, \
+ .entry = hpp__entry_ ## _fn, \
.cmp = hpp__nop_cmp, \
.collapse = hpp__nop_cmp, \
- .sort = hpp__sort_ ## _name, \
+ .sort = hpp__sort_ ## _fn, \
}
struct perf_hpp_fmt perf_hpp__format[] = {
- HPP__COLOR_PRINT_FNS(overhead),
- HPP__COLOR_PRINT_FNS(overhead_sys),
- HPP__COLOR_PRINT_FNS(overhead_us),
- HPP__COLOR_PRINT_FNS(overhead_guest_sys),
- HPP__COLOR_PRINT_FNS(overhead_guest_us),
- HPP__COLOR_ACC_PRINT_FNS(overhead_acc),
- HPP__PRINT_FNS(samples),
- HPP__PRINT_FNS(period)
+ HPP__COLOR_PRINT_FNS("Overhead", overhead),
+ HPP__COLOR_PRINT_FNS("sys", overhead_sys),
+ HPP__COLOR_PRINT_FNS("usr", overhead_us),
+ HPP__COLOR_PRINT_FNS("guest sys", overhead_guest_sys),
+ HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us),
+ HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc),
+ HPP__PRINT_FNS("Samples", samples),
+ HPP__PRINT_FNS("Period", period)
};
LIST_HEAD(perf_hpp__list);
@@ -444,14 +452,12 @@ void perf_hpp__init(void)
/*
* If user specified field order, no need to setup default fields.
*/
- if (field_order)
+ if (is_strict_order(field_order))
return;
if (symbol_conf.cumulate_callchain) {
perf_hpp__column_enable(PERF_HPP__OVERHEAD_ACC);
-
- perf_hpp__format[PERF_HPP__OVERHEAD].header =
- hpp__header_overhead_self;
+ perf_hpp__format[PERF_HPP__OVERHEAD].name = "Self";
}
perf_hpp__column_enable(PERF_HPP__OVERHEAD);
@@ -513,11 +519,11 @@ void perf_hpp__column_disable(unsigned col)
void perf_hpp__cancel_cumulate(void)
{
- if (field_order)
+ if (is_strict_order(field_order))
return;
perf_hpp__column_disable(PERF_HPP__OVERHEAD_ACC);
- perf_hpp__format[PERF_HPP__OVERHEAD].header = hpp__header_overhead;
+ perf_hpp__format[PERF_HPP__OVERHEAD].name = "Overhead";
}
void perf_hpp__setup_output_field(void)
@@ -622,3 +628,59 @@ unsigned int hists__sort_list_width(struct hists *hists)
return ret;
}
+
+void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
+{
+ int idx;
+
+ if (perf_hpp__is_sort_entry(fmt))
+ return perf_hpp__reset_sort_width(fmt, hists);
+
+ for (idx = 0; idx < PERF_HPP__MAX_INDEX; idx++) {
+ if (fmt == &perf_hpp__format[idx])
+ break;
+ }
+
+ if (idx == PERF_HPP__MAX_INDEX)
+ return;
+
+ switch (idx) {
+ case PERF_HPP__OVERHEAD:
+ case PERF_HPP__OVERHEAD_SYS:
+ case PERF_HPP__OVERHEAD_US:
+ case PERF_HPP__OVERHEAD_ACC:
+ fmt->len = 8;
+ break;
+
+ case PERF_HPP__OVERHEAD_GUEST_SYS:
+ case PERF_HPP__OVERHEAD_GUEST_US:
+ fmt->len = 9;
+ break;
+
+ case PERF_HPP__SAMPLES:
+ case PERF_HPP__PERIOD:
+ fmt->len = 12;
+ break;
+
+ default:
+ break;
+ }
+}
+
+void perf_hpp__set_user_width(const char *width_list_str)
+{
+ struct perf_hpp_fmt *fmt;
+ const char *ptr = width_list_str;
+
+ perf_hpp__for_each_format(fmt) {
+ char *p;
+
+ int len = strtol(ptr, &p, 10);
+ fmt->user_len = len;
+
+ if (*p == ',')
+ ptr = p + 1;
+ else
+ break;
+ }
+}
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 90122abd3721..15b451acbde6 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -395,10 +395,12 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
init_rem_hits();
-
perf_hpp__for_each_format(fmt)
perf_hpp__reset_width(fmt, hists);
+ if (symbol_conf.col_width_list_str)
+ perf_hpp__set_user_width(symbol_conf.col_width_list_str);
+
if (!show_header)
goto print_entries;
@@ -479,7 +481,7 @@ print_entries:
if (h->ms.map == NULL && verbose > 1) {
__map_groups__fprintf_maps(h->thread->mg,
- MAP__FUNCTION, verbose, fp);
+ MAP__FUNCTION, fp);
fprintf(fp, "%.10s end\n", graph_dotted_line);
}
}
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 809b4c50beae..36437527dbb3 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -232,9 +232,16 @@ static int mov__parse(struct ins_operands *ops)
return -1;
target = ++s;
+ comment = strchr(s, '#');
- while (s[0] != '\0' && !isspace(s[0]))
- ++s;
+ if (comment != NULL)
+ s = comment - 1;
+ else
+ s = strchr(s, '\0') - 1;
+
+ while (s > target && isspace(s[0]))
+ --s;
+ s++;
prev = *s;
*s = '\0';
@@ -244,7 +251,6 @@ static int mov__parse(struct ins_operands *ops)
if (ops->target.raw == NULL)
goto out_free_source;
- comment = strchr(s, '#');
if (comment == NULL)
return 0;
@@ -899,10 +905,8 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
struct kcore_extract kce;
bool delete_extract = false;
- if (filename) {
- snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
- symbol_conf.symfs, filename);
- }
+ if (filename)
+ symbol__join_symfs(symfs_filename, filename);
if (filename == NULL) {
if (dso->has_build_id) {
@@ -922,8 +926,7 @@ fallback:
* DSO is the same as when 'perf record' ran.
*/
filename = (char *)dso->long_name;
- snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
- symbol_conf.symfs, filename);
+ symbol__join_symfs(symfs_filename, filename);
free_filename = false;
}
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 7b176dd02e1a..5cf9e1b5989d 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -22,6 +22,7 @@ typedef int (*config_fn_t)(const char *, const char *, void *);
extern int perf_default_config(const char *, const char *, void *);
extern int perf_config(config_fn_t fn, void *);
extern int perf_config_int(const char *, const char *);
+extern u64 perf_config_u64(const char *, const char *);
extern int perf_config_bool(const char *, const char *);
extern int config_error_nonbool(const char *);
extern const char *perf_config_dirname(const char *, const char *);
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 48b6d3f50012..c84d3f8dcb75 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -25,77 +25,172 @@
__thread struct callchain_cursor callchain_cursor;
-int
-parse_callchain_report_opt(const char *arg)
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+static int get_stack_size(const char *str, unsigned long *_size)
{
- char *tok, *tok2;
char *endptr;
+ unsigned long size;
+ unsigned long max_size = round_down(USHRT_MAX, sizeof(u64));
- symbol_conf.use_callchain = true;
+ size = strtoul(str, &endptr, 0);
- if (!arg)
+ do {
+ if (*endptr)
+ break;
+
+ size = round_up(size, sizeof(u64));
+ if (!size || size > max_size)
+ break;
+
+ *_size = size;
return 0;
- tok = strtok((char *)arg, ",");
- if (!tok)
- return -1;
+ } while (0);
- /* get the output mode */
- if (!strncmp(tok, "graph", strlen(arg))) {
- callchain_param.mode = CHAIN_GRAPH_ABS;
+ pr_err("callchain: Incorrect stack dump size (max %ld): %s\n",
+ max_size, str);
+ return -1;
+}
+#endif /* HAVE_DWARF_UNWIND_SUPPORT */
- } else if (!strncmp(tok, "flat", strlen(arg))) {
- callchain_param.mode = CHAIN_FLAT;
- } else if (!strncmp(tok, "fractal", strlen(arg))) {
- callchain_param.mode = CHAIN_GRAPH_REL;
- } else if (!strncmp(tok, "none", strlen(arg))) {
- callchain_param.mode = CHAIN_NONE;
- symbol_conf.use_callchain = false;
- return 0;
- } else {
- return -1;
- }
+int parse_callchain_record_opt(const char *arg)
+{
+ char *tok, *name, *saveptr = NULL;
+ char *buf;
+ int ret = -1;
+
+ /* We need buffer that we know we can write to. */
+ buf = malloc(strlen(arg) + 1);
+ if (!buf)
+ return -ENOMEM;
+
+ strcpy(buf, arg);
+
+ tok = strtok_r((char *)buf, ",", &saveptr);
+ name = tok ? : (char *)buf;
+
+ do {
+ /* Framepointer style */
+ if (!strncmp(name, "fp", sizeof("fp"))) {
+ if (!strtok_r(NULL, ",", &saveptr)) {
+ callchain_param.record_mode = CALLCHAIN_FP;
+ ret = 0;
+ } else
+ pr_err("callchain: No more arguments "
+ "needed for -g fp\n");
+ break;
- /* get the min percentage */
- tok = strtok(NULL, ",");
- if (!tok)
- goto setup;
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+ /* Dwarf style */
+ } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
+ const unsigned long default_stack_dump_size = 8192;
- callchain_param.min_percent = strtod(tok, &endptr);
- if (tok == endptr)
- return -1;
+ ret = 0;
+ callchain_param.record_mode = CALLCHAIN_DWARF;
+ callchain_param.dump_size = default_stack_dump_size;
- /* get the print limit */
- tok2 = strtok(NULL, ",");
- if (!tok2)
- goto setup;
+ tok = strtok_r(NULL, ",", &saveptr);
+ if (tok) {
+ unsigned long size = 0;
- if (tok2[0] != 'c') {
- callchain_param.print_limit = strtoul(tok2, &endptr, 0);
- tok2 = strtok(NULL, ",");
- if (!tok2)
- goto setup;
+ ret = get_stack_size(tok, &size);
+ callchain_param.dump_size = size;
+ }
+#endif /* HAVE_DWARF_UNWIND_SUPPORT */
+ } else {
+ pr_err("callchain: Unknown --call-graph option "
+ "value: %s\n", arg);
+ break;
+ }
+
+ } while (0);
+
+ free(buf);
+ return ret;
+}
+
+static int parse_callchain_mode(const char *value)
+{
+ if (!strncmp(value, "graph", strlen(value))) {
+ callchain_param.mode = CHAIN_GRAPH_ABS;
+ return 0;
+ }
+ if (!strncmp(value, "flat", strlen(value))) {
+ callchain_param.mode = CHAIN_FLAT;
+ return 0;
}
+ if (!strncmp(value, "fractal", strlen(value))) {
+ callchain_param.mode = CHAIN_GRAPH_REL;
+ return 0;
+ }
+ return -1;
+}
- /* get the call chain order */
- if (!strncmp(tok2, "caller", strlen("caller")))
+static int parse_callchain_order(const char *value)
+{
+ if (!strncmp(value, "caller", strlen(value))) {
callchain_param.order = ORDER_CALLER;
- else if (!strncmp(tok2, "callee", strlen("callee")))
+ return 0;
+ }
+ if (!strncmp(value, "callee", strlen(value))) {
callchain_param.order = ORDER_CALLEE;
- else
- return -1;
+ return 0;
+ }
+ return -1;
+}
- /* Get the sort key */
- tok2 = strtok(NULL, ",");
- if (!tok2)
- goto setup;
- if (!strncmp(tok2, "function", strlen("function")))
+static int parse_callchain_sort_key(const char *value)
+{
+ if (!strncmp(value, "function", strlen(value))) {
callchain_param.key = CCKEY_FUNCTION;
- else if (!strncmp(tok2, "address", strlen("address")))
+ return 0;
+ }
+ if (!strncmp(value, "address", strlen(value))) {
callchain_param.key = CCKEY_ADDRESS;
- else
- return -1;
-setup:
+ return 0;
+ }
+ return -1;
+}
+
+int
+parse_callchain_report_opt(const char *arg)
+{
+ char *tok;
+ char *endptr;
+ bool minpcnt_set = false;
+
+ symbol_conf.use_callchain = true;
+
+ if (!arg)
+ return 0;
+
+ while ((tok = strtok((char *)arg, ",")) != NULL) {
+ if (!strncmp(tok, "none", strlen(tok))) {
+ callchain_param.mode = CHAIN_NONE;
+ symbol_conf.use_callchain = false;
+ return 0;
+ }
+
+ if (!parse_callchain_mode(tok) ||
+ !parse_callchain_order(tok) ||
+ !parse_callchain_sort_key(tok)) {
+ /* parsing ok - move on to the next */
+ } else if (!minpcnt_set) {
+ /* try to get the min percent */
+ callchain_param.min_percent = strtod(tok, &endptr);
+ if (tok == endptr)
+ return -1;
+ minpcnt_set = true;
+ } else {
+ /* try print limit at last */
+ callchain_param.print_limit = strtoul(tok, &endptr, 0);
+ if (tok == endptr)
+ return -1;
+ }
+
+ arg = NULL;
+ }
+
if (callchain_register_param(&callchain_param) < 0) {
pr_err("Can't register callchain params\n");
return -1;
@@ -103,6 +198,47 @@ setup:
return 0;
}
+int perf_callchain_config(const char *var, const char *value)
+{
+ char *endptr;
+
+ if (prefixcmp(var, "call-graph."))
+ return 0;
+ var += sizeof("call-graph.") - 1;
+
+ if (!strcmp(var, "record-mode"))
+ return parse_callchain_record_opt(value);
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+ if (!strcmp(var, "dump-size")) {
+ unsigned long size = 0;
+ int ret;
+
+ ret = get_stack_size(value, &size);
+ callchain_param.dump_size = size;
+
+ return ret;
+ }
+#endif
+ if (!strcmp(var, "print-type"))
+ return parse_callchain_mode(value);
+ if (!strcmp(var, "order"))
+ return parse_callchain_order(value);
+ if (!strcmp(var, "sort-key"))
+ return parse_callchain_sort_key(value);
+ if (!strcmp(var, "threshold")) {
+ callchain_param.min_percent = strtod(value, &endptr);
+ if (value == endptr)
+ return -1;
+ }
+ if (!strcmp(var, "print-limit")) {
+ callchain_param.print_limit = strtod(value, &endptr);
+ if (value == endptr)
+ return -1;
+ }
+
+ return 0;
+}
+
static void
rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
enum chain_mode mode)
@@ -626,7 +762,7 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent
int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample)
{
- if (!symbol_conf.use_callchain)
+ if (!symbol_conf.use_callchain || sample->callchain == NULL)
return 0;
return callchain_append(he->callchain, &callchain_cursor, sample->period);
}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 8f84423a75da..2a1f5a46543a 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -54,6 +54,9 @@ enum chain_key {
};
struct callchain_param {
+ bool enabled;
+ enum perf_call_graph_mode record_mode;
+ u32 dump_size;
enum chain_mode mode;
u32 print_limit;
double min_percent;
@@ -154,7 +157,6 @@ static inline void callchain_cursor_advance(struct callchain_cursor *cursor)
struct option;
struct hist_entry;
-int record_parse_callchain(const char *arg, struct record_opts *opts);
int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset);
int record_callchain_opt(const struct option *opt, const char *arg, int unset);
@@ -166,7 +168,9 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *
bool hide_unresolved);
extern const char record_callchain_help[];
+int parse_callchain_record_opt(const char *arg);
int parse_callchain_report_opt(const char *arg);
+int perf_callchain_config(const char *var, const char *value);
static inline void callchain_cursor_snapshot(struct callchain_cursor *dest,
struct callchain_cursor *src)
@@ -176,4 +180,17 @@ static inline void callchain_cursor_snapshot(struct callchain_cursor *dest,
dest->first = src->curr;
dest->nr -= src->pos;
}
+
+#ifdef HAVE_SKIP_CALLCHAIN_IDX
+extern int arch_skip_callchain_idx(struct machine *machine,
+ struct thread *thread, struct ip_callchain *chain);
+#else
+static inline int arch_skip_callchain_idx(struct machine *machine __maybe_unused,
+ struct thread *thread __maybe_unused,
+ struct ip_callchain *chain __maybe_unused)
+{
+ return -1;
+}
+#endif
+
#endif /* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
new file mode 100644
index 000000000000..47b78b3f0325
--- /dev/null
+++ b/tools/perf/util/cloexec.c
@@ -0,0 +1,74 @@
+#include <sched.h>
+#include "util.h"
+#include "../perf.h"
+#include "cloexec.h"
+#include "asm/bug.h"
+#include "debug.h"
+
+static unsigned long flag = PERF_FLAG_FD_CLOEXEC;
+
+static int perf_flag_probe(void)
+{
+ /* use 'safest' configuration as used in perf_evsel__fallback() */
+ struct perf_event_attr attr = {
+ .type = PERF_TYPE_SOFTWARE,
+ .config = PERF_COUNT_SW_CPU_CLOCK,
+ .exclude_kernel = 1,
+ };
+ int fd;
+ int err;
+ int cpu;
+ pid_t pid = -1;
+ char sbuf[STRERR_BUFSIZE];
+
+ cpu = sched_getcpu();
+ if (cpu < 0)
+ cpu = 0;
+
+ while (1) {
+ /* check cloexec flag */
+ fd = sys_perf_event_open(&attr, pid, cpu, -1,
+ PERF_FLAG_FD_CLOEXEC);
+ if (fd < 0 && pid == -1 && errno == EACCES) {
+ pid = 0;
+ continue;
+ }
+ break;
+ }
+ err = errno;
+
+ if (fd >= 0) {
+ close(fd);
+ return 1;
+ }
+
+ WARN_ONCE(err != EINVAL && err != EBUSY,
+ "perf_event_open(..., PERF_FLAG_FD_CLOEXEC) failed with unexpected error %d (%s)\n",
+ err, strerror_r(err, sbuf, sizeof(sbuf)));
+
+ /* not supported, confirm error related to PERF_FLAG_FD_CLOEXEC */
+ fd = sys_perf_event_open(&attr, pid, cpu, -1, 0);
+ err = errno;
+
+ if (WARN_ONCE(fd < 0 && err != EBUSY,
+ "perf_event_open(..., 0) failed unexpectedly with error %d (%s)\n",
+ err, strerror_r(err, sbuf, sizeof(sbuf))))
+ return -1;
+
+ close(fd);
+
+ return 0;
+}
+
+unsigned long perf_event_open_cloexec_flag(void)
+{
+ static bool probed;
+
+ if (!probed) {
+ if (perf_flag_probe() <= 0)
+ flag = 0;
+ probed = true;
+ }
+
+ return flag;
+}
diff --git a/tools/perf/util/cloexec.h b/tools/perf/util/cloexec.h
new file mode 100644
index 000000000000..94a5a7d829d5
--- /dev/null
+++ b/tools/perf/util/cloexec.h
@@ -0,0 +1,6 @@
+#ifndef __PERF_CLOEXEC_H
+#define __PERF_CLOEXEC_H
+
+unsigned long perf_event_open_cloexec_flag(void);
+
+#endif /* __PERF_CLOEXEC_H */
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index 87b8672eb413..f4654183d391 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -335,3 +335,19 @@ int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...)
va_end(args);
return value_color_snprintf(bf, size, fmt, percent);
}
+
+int percent_color_len_snprintf(char *bf, size_t size, const char *fmt, ...)
+{
+ va_list args;
+ int len;
+ double percent;
+ const char *color;
+
+ va_start(args, fmt);
+ len = va_arg(args, int);
+ percent = va_arg(args, double);
+ va_end(args);
+
+ color = get_percent_color(percent);
+ return color_snprintf(bf, size, color, fmt, len, percent);
+}
diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h
index 7ff30a62a132..0a594b8a0c26 100644
--- a/tools/perf/util/color.h
+++ b/tools/perf/util/color.h
@@ -41,6 +41,7 @@ int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...);
int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf);
int value_color_snprintf(char *bf, size_t size, const char *fmt, double value);
int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...);
+int percent_color_len_snprintf(char *bf, size_t size, const char *fmt, ...);
int percent_color_fprintf(FILE *fp, const char *fmt, double percent);
const char *get_percent_color(double percent);
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index f9e777629e21..b2bb59df65e1 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -74,7 +74,7 @@ static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root)
return new;
}
-struct comm *comm__new(const char *str, u64 timestamp)
+struct comm *comm__new(const char *str, u64 timestamp, bool exec)
{
struct comm *comm = zalloc(sizeof(*comm));
@@ -82,6 +82,7 @@ struct comm *comm__new(const char *str, u64 timestamp)
return NULL;
comm->start = timestamp;
+ comm->exec = exec;
comm->comm_str = comm_str__findnew(str, &comm_str_root);
if (!comm->comm_str) {
@@ -94,7 +95,7 @@ struct comm *comm__new(const char *str, u64 timestamp)
return comm;
}
-int comm__override(struct comm *comm, const char *str, u64 timestamp)
+int comm__override(struct comm *comm, const char *str, u64 timestamp, bool exec)
{
struct comm_str *new, *old = comm->comm_str;
@@ -106,6 +107,8 @@ int comm__override(struct comm *comm, const char *str, u64 timestamp)
comm_str__put(old);
comm->comm_str = new;
comm->start = timestamp;
+ if (exec)
+ comm->exec = true;
return 0;
}
diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h
index fac5bd51befc..51c10ab257f8 100644
--- a/tools/perf/util/comm.h
+++ b/tools/perf/util/comm.h
@@ -11,11 +11,13 @@ struct comm {
struct comm_str *comm_str;
u64 start;
struct list_head list;
+ bool exec;
};
void comm__free(struct comm *comm);
-struct comm *comm__new(const char *str, u64 timestamp);
+struct comm *comm__new(const char *str, u64 timestamp, bool exec);
const char *comm__str(const struct comm *comm);
-int comm__override(struct comm *comm, const char *str, u64 timestamp);
+int comm__override(struct comm *comm, const char *str, u64 timestamp,
+ bool exec);
#endif /* __PERF_COMM_H */
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 24519e14ac56..57ff826f150b 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -222,7 +222,8 @@ static int perf_parse_file(config_fn_t fn, void *data)
const unsigned char *bomptr = utf8_bom;
for (;;) {
- int c = get_next_char();
+ int line, c = get_next_char();
+
if (bomptr && *bomptr) {
/* We are at the file beginning; skip UTF8-encoded BOM
* if present. Sane editors won't put this in on their
@@ -261,8 +262,16 @@ static int perf_parse_file(config_fn_t fn, void *data)
if (!isalpha(c))
break;
var[baselen] = tolower(c);
- if (get_value(fn, data, var, baselen+1) < 0)
+
+ /*
+ * The get_value function might or might not reach the '\n',
+ * so saving the current line number for error reporting.
+ */
+ line = config_linenr;
+ if (get_value(fn, data, var, baselen+1) < 0) {
+ config_linenr = line;
break;
+ }
}
die("bad config file line %d in %s", config_linenr, config_file_name);
}
@@ -286,6 +295,21 @@ static int parse_unit_factor(const char *end, unsigned long *val)
return 0;
}
+static int perf_parse_llong(const char *value, long long *ret)
+{
+ if (value && *value) {
+ char *end;
+ long long val = strtoll(value, &end, 0);
+ unsigned long factor = 1;
+
+ if (!parse_unit_factor(end, &factor))
+ return 0;
+ *ret = val * factor;
+ return 1;
+ }
+ return 0;
+}
+
static int perf_parse_long(const char *value, long *ret)
{
if (value && *value) {
@@ -307,6 +331,15 @@ static void die_bad_config(const char *name)
die("bad config value for '%s'", name);
}
+u64 perf_config_u64(const char *name, const char *value)
+{
+ long long ret = 0;
+
+ if (!perf_parse_llong(value, &ret))
+ die_bad_config(name);
+ return (u64) ret;
+}
+
int perf_config_int(const char *name, const char *value)
{
long ret = 0;
@@ -350,6 +383,16 @@ static int perf_default_core_config(const char *var __maybe_unused,
return 0;
}
+static int perf_ui_config(const char *var, const char *value)
+{
+ /* Add other config variables here. */
+ if (!strcmp(var, "ui.show-headers")) {
+ symbol_conf.show_hist_headers = perf_config_bool(var, value);
+ return 0;
+ }
+ return 0;
+}
+
int perf_default_config(const char *var, const char *value,
void *dummy __maybe_unused)
{
@@ -359,6 +402,12 @@ int perf_default_config(const char *var, const char *value,
if (!prefixcmp(var, "hist."))
return perf_hist_config(var, value);
+ if (!prefixcmp(var, "ui."))
+ return perf_ui_config(var, value);
+
+ if (!prefixcmp(var, "call-graph."))
+ return perf_callchain_config(var, value);
+
/* Add other config variables here. */
return 0;
}
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index 55de44ecebef..1921942fc2e0 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -7,6 +7,7 @@
#include "data.h"
#include "util.h"
+#include "debug.h"
static bool check_pipe(struct perf_data_file *file)
{
@@ -49,12 +50,14 @@ static int open_file_read(struct perf_data_file *file)
{
struct stat st;
int fd;
+ char sbuf[STRERR_BUFSIZE];
fd = open(file->path, O_RDONLY);
if (fd < 0) {
int err = errno;
- pr_err("failed to open %s: %s", file->path, strerror(err));
+ pr_err("failed to open %s: %s", file->path,
+ strerror_r(err, sbuf, sizeof(sbuf)));
if (err == ENOENT && !strcmp(file->path, "perf.data"))
pr_err(" (try 'perf record' first)");
pr_err("\n");
@@ -65,7 +68,7 @@ static int open_file_read(struct perf_data_file *file)
goto out_close;
if (!file->force && st.st_uid && (st.st_uid != geteuid())) {
- pr_err("file %s not owned by current user or root\n",
+ pr_err("File %s not owned by current user or root (use -f to override)\n",
file->path);
goto out_close;
}
@@ -87,6 +90,7 @@ static int open_file_read(struct perf_data_file *file)
static int open_file_write(struct perf_data_file *file)
{
int fd;
+ char sbuf[STRERR_BUFSIZE];
if (check_backup(file))
return -1;
@@ -94,7 +98,8 @@ static int open_file_write(struct perf_data_file *file)
fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR);
if (fd < 0)
- pr_err("failed to open %s : %s\n", file->path, strerror(errno));
+ pr_err("failed to open %s : %s\n", file->path,
+ strerror_r(errno, sbuf, sizeof(sbuf)));
return fd;
}
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 299b55586502..ba357f3226c6 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -13,14 +13,18 @@
#include "util.h"
#include "target.h"
+#define NSECS_PER_SEC 1000000000ULL
+#define NSECS_PER_USEC 1000ULL
+
int verbose;
bool dump_trace = false, quiet = false;
+int debug_ordered_events;
-static int _eprintf(int level, const char *fmt, va_list args)
+static int _eprintf(int level, int var, const char *fmt, va_list args)
{
int ret = 0;
- if (verbose >= level) {
+ if (var >= level) {
if (use_browser >= 1)
ui_helpline__vshow(fmt, args);
else
@@ -30,18 +34,47 @@ static int _eprintf(int level, const char *fmt, va_list args)
return ret;
}
-int eprintf(int level, const char *fmt, ...)
+int eprintf(int level, int var, const char *fmt, ...)
{
va_list args;
int ret;
va_start(args, fmt);
- ret = _eprintf(level, fmt, args);
+ ret = _eprintf(level, var, fmt, args);
va_end(args);
return ret;
}
+static int __eprintf_time(u64 t, const char *fmt, va_list args)
+{
+ int ret = 0;
+ u64 secs, usecs, nsecs = t;
+
+ secs = nsecs / NSECS_PER_SEC;
+ nsecs -= secs * NSECS_PER_SEC;
+ usecs = nsecs / NSECS_PER_USEC;
+
+ ret = fprintf(stderr, "[%13" PRIu64 ".%06" PRIu64 "] ",
+ secs, usecs);
+ ret += vfprintf(stderr, fmt, args);
+ return ret;
+}
+
+int eprintf_time(int level, int var, u64 t, const char *fmt, ...)
+{
+ int ret = 0;
+ va_list args;
+
+ if (var >= level) {
+ va_start(args, fmt);
+ ret = __eprintf_time(t, fmt, args);
+ va_end(args);
+ }
+
+ return ret;
+}
+
/*
* Overloading libtraceevent standard info print
* function, display with -v in perf.
@@ -51,9 +84,9 @@ void pr_stat(const char *fmt, ...)
va_list args;
va_start(args, fmt);
- _eprintf(1, fmt, args);
+ _eprintf(1, verbose, fmt, args);
va_end(args);
- eprintf(1, "\n");
+ eprintf(1, verbose, "\n");
}
int dump_printf(const char *fmt, ...)
@@ -105,3 +138,48 @@ void trace_event(union perf_event *event)
}
printf(".\n");
}
+
+static struct debug_variable {
+ const char *name;
+ int *ptr;
+} debug_variables[] = {
+ { .name = "verbose", .ptr = &verbose },
+ { .name = "ordered-events", .ptr = &debug_ordered_events},
+ { .name = NULL, }
+};
+
+int perf_debug_option(const char *str)
+{
+ struct debug_variable *var = &debug_variables[0];
+ char *vstr, *s = strdup(str);
+ int v = 1;
+
+ vstr = strchr(s, '=');
+ if (vstr)
+ *vstr++ = 0;
+
+ while (var->name) {
+ if (!strcmp(s, var->name))
+ break;
+ var++;
+ }
+
+ if (!var->name) {
+ pr_err("Unknown debug variable name '%s'\n", s);
+ free(s);
+ return -1;
+ }
+
+ if (vstr) {
+ v = atoi(vstr);
+ /*
+ * Allow only values in range (0, 10),
+ * otherwise set 0.
+ */
+ v = (v < 0) || (v > 10) ? 0 : v;
+ }
+
+ *var->ptr = v;
+ free(s);
+ return 0;
+}
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 443694c36b03..be264d6f3b30 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -3,6 +3,7 @@
#define __PERF_DEBUG_H
#include <stdbool.h>
+#include <string.h>
#include "event.h"
#include "../ui/helpline.h"
#include "../ui/progress.h"
@@ -10,6 +11,33 @@
extern int verbose;
extern bool quiet, dump_trace;
+extern int debug_ordered_events;
+
+#ifndef pr_fmt
+#define pr_fmt(fmt) fmt
+#endif
+
+#define pr_err(fmt, ...) \
+ eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_warning(fmt, ...) \
+ eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_info(fmt, ...) \
+ eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug(fmt, ...) \
+ eprintf(1, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debugN(n, fmt, ...) \
+ eprintf(n, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__)
+
+#define pr_time_N(n, var, t, fmt, ...) \
+ eprintf_time(n, var, t, fmt, ##__VA_ARGS__)
+
+#define pr_oe_time(t, fmt, ...) pr_time_N(1, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_oe_time2(t, fmt, ...) pr_time_N(2, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__)
+
+#define STRERR_BUFSIZE 128 /* For the buffer size of strerror_r */
int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
void trace_event(union perf_event *event);
@@ -19,4 +47,9 @@ int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
void pr_stat(const char *fmt, ...);
+int eprintf(int level, int var, const char *fmt, ...) __attribute__((format(printf, 3, 4)));
+int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __attribute__((format(printf, 4, 5)));
+
+int perf_debug_option(const char *str);
+
#endif /* __PERF_DEBUG_H */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 819f10414f08..0247acfdfaca 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -37,6 +37,7 @@ int dso__read_binary_type_filename(const struct dso *dso,
{
char build_id_hex[BUILD_ID_SIZE * 2 + 1];
int ret = 0;
+ size_t len;
switch (type) {
case DSO_BINARY_TYPE__DEBUGLINK: {
@@ -60,26 +61,25 @@ int dso__read_binary_type_filename(const struct dso *dso,
break;
case DSO_BINARY_TYPE__FEDORA_DEBUGINFO:
- snprintf(filename, size, "%s/usr/lib/debug%s.debug",
- symbol_conf.symfs, dso->long_name);
+ len = __symbol__join_symfs(filename, size, "/usr/lib/debug");
+ snprintf(filename + len, size - len, "%s.debug", dso->long_name);
break;
case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO:
- snprintf(filename, size, "%s/usr/lib/debug%s",
- symbol_conf.symfs, dso->long_name);
+ len = __symbol__join_symfs(filename, size, "/usr/lib/debug");
+ snprintf(filename + len, size - len, "%s", dso->long_name);
break;
case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
{
const char *last_slash;
- size_t len;
size_t dir_size;
last_slash = dso->long_name + dso->long_name_len;
while (last_slash != dso->long_name && *last_slash != '/')
last_slash--;
- len = scnprintf(filename, size, "%s", symbol_conf.symfs);
+ len = __symbol__join_symfs(filename, size, "");
dir_size = last_slash - dso->long_name + 2;
if (dir_size > (size - len)) {
ret = -1;
@@ -100,26 +100,24 @@ int dso__read_binary_type_filename(const struct dso *dso,
build_id__sprintf(dso->build_id,
sizeof(dso->build_id),
build_id_hex);
- snprintf(filename, size,
- "%s/usr/lib/debug/.build-id/%.2s/%s.debug",
- symbol_conf.symfs, build_id_hex, build_id_hex + 2);
+ len = __symbol__join_symfs(filename, size, "/usr/lib/debug/.build-id/");
+ snprintf(filename + len, size - len, "%.2s/%s.debug",
+ build_id_hex, build_id_hex + 2);
break;
case DSO_BINARY_TYPE__VMLINUX:
case DSO_BINARY_TYPE__GUEST_VMLINUX:
case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
- snprintf(filename, size, "%s%s",
- symbol_conf.symfs, dso->long_name);
+ __symbol__join_symfs(filename, size, dso->long_name);
break;
case DSO_BINARY_TYPE__GUEST_KMODULE:
- snprintf(filename, size, "%s%s%s", symbol_conf.symfs,
- root_dir, dso->long_name);
+ path__join3(filename, size, symbol_conf.symfs,
+ root_dir, dso->long_name);
break;
case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
- snprintf(filename, size, "%s%s", symbol_conf.symfs,
- dso->long_name);
+ __symbol__join_symfs(filename, size, dso->long_name);
break;
case DSO_BINARY_TYPE__KCORE:
@@ -164,13 +162,15 @@ static void close_first_dso(void);
static int do_open(char *name)
{
int fd;
+ char sbuf[STRERR_BUFSIZE];
do {
fd = open(name, O_RDONLY);
if (fd >= 0)
return fd;
- pr_debug("dso open failed, mmap: %s\n", strerror(errno));
+ pr_debug("dso open failed, mmap: %s\n",
+ strerror_r(errno, sbuf, sizeof(sbuf)));
if (!dso__data_open_cnt || errno != EMFILE)
break;
@@ -216,7 +216,7 @@ static int open_dso(struct dso *dso, struct machine *machine)
{
int fd = __open_dso(dso, machine);
- if (fd > 0) {
+ if (fd >= 0) {
dso__list_add(dso);
/*
* Check if we crossed the allowed number
@@ -331,26 +331,44 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
};
int i = 0;
+ if (dso->data.status == DSO_DATA_STATUS_ERROR)
+ return -1;
+
if (dso->data.fd >= 0)
- return dso->data.fd;
+ goto out;
if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) {
dso->data.fd = open_dso(dso, machine);
- return dso->data.fd;
+ goto out;
}
do {
- int fd;
-
dso->binary_type = binary_type_data[i++];
- fd = open_dso(dso, machine);
- if (fd >= 0)
- return dso->data.fd = fd;
+ dso->data.fd = open_dso(dso, machine);
+ if (dso->data.fd >= 0)
+ goto out;
} while (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND);
+out:
+ if (dso->data.fd >= 0)
+ dso->data.status = DSO_DATA_STATUS_OK;
+ else
+ dso->data.status = DSO_DATA_STATUS_ERROR;
+
+ return dso->data.fd;
+}
+
+bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by)
+{
+ u32 flag = 1 << by;
+
+ if (dso->data.status_seen & flag)
+ return true;
+
+ dso->data.status_seen |= flag;
- return -EINVAL;
+ return false;
}
static void
@@ -514,10 +532,12 @@ static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
static int data_file_size(struct dso *dso)
{
struct stat st;
+ char sbuf[STRERR_BUFSIZE];
if (!dso->data.file_size) {
if (fstat(dso->data.fd, &st)) {
- pr_err("dso mmap failed, fstat: %s\n", strerror(errno));
+ pr_err("dso mmap failed, fstat: %s\n",
+ strerror_r(errno, sbuf, sizeof(sbuf)));
return -1;
}
dso->data.file_size = st.st_size;
@@ -526,6 +546,28 @@ static int data_file_size(struct dso *dso)
return 0;
}
+/**
+ * dso__data_size - Return dso data size
+ * @dso: dso object
+ * @machine: machine object
+ *
+ * Return: dso data size
+ */
+off_t dso__data_size(struct dso *dso, struct machine *machine)
+{
+ int fd;
+
+ fd = dso__data_fd(dso, machine);
+ if (fd < 0)
+ return fd;
+
+ if (data_file_size(dso))
+ return -1;
+
+ /* For now just estimate dso data size is close to file size */
+ return dso->data.file_size;
+}
+
static ssize_t data_read_offset(struct dso *dso, u64 offset,
u8 *data, ssize_t size)
{
@@ -611,6 +653,65 @@ struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
return dso;
}
+/*
+ * Find a matching entry and/or link current entry to RB tree.
+ * Either one of the dso or name parameter must be non-NULL or the
+ * function will not work.
+ */
+static struct dso *dso__findlink_by_longname(struct rb_root *root,
+ struct dso *dso, const char *name)
+{
+ struct rb_node **p = &root->rb_node;
+ struct rb_node *parent = NULL;
+
+ if (!name)
+ name = dso->long_name;
+ /*
+ * Find node with the matching name
+ */
+ while (*p) {
+ struct dso *this = rb_entry(*p, struct dso, rb_node);
+ int rc = strcmp(name, this->long_name);
+
+ parent = *p;
+ if (rc == 0) {
+ /*
+ * In case the new DSO is a duplicate of an existing
+ * one, print an one-time warning & put the new entry
+ * at the end of the list of duplicates.
+ */
+ if (!dso || (dso == this))
+ return this; /* Find matching dso */
+ /*
+ * The core kernel DSOs may have duplicated long name.
+ * In this case, the short name should be different.
+ * Comparing the short names to differentiate the DSOs.
+ */
+ rc = strcmp(dso->short_name, this->short_name);
+ if (rc == 0) {
+ pr_err("Duplicated dso name: %s\n", name);
+ return NULL;
+ }
+ }
+ if (rc < 0)
+ p = &parent->rb_left;
+ else
+ p = &parent->rb_right;
+ }
+ if (dso) {
+ /* Add new node and rebalance tree */
+ rb_link_node(&dso->rb_node, parent, p);
+ rb_insert_color(&dso->rb_node, root);
+ }
+ return NULL;
+}
+
+static inline struct dso *
+dso__find_by_longname(const struct rb_root *root, const char *name)
+{
+ return dso__findlink_by_longname((struct rb_root *)root, NULL, name);
+}
+
void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated)
{
if (name == NULL)
@@ -701,8 +802,10 @@ struct dso *dso__new(const char *name)
dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
dso->data.cache = RB_ROOT;
dso->data.fd = -1;
+ dso->data.status = DSO_DATA_STATUS_UNKNOWN;
dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
dso->binary_type = DSO_BINARY_TYPE__NOT_FOUND;
+ dso->is_64_bit = (sizeof(void *) == 8);
dso->loaded = 0;
dso->rel = 0;
dso->sorted_by_name = 0;
@@ -711,6 +814,7 @@ struct dso *dso__new(const char *name)
dso->a2l_fails = 1;
dso->kernel = DSO_TYPE_USER;
dso->needs_swap = DSO_SWAP__UNSET;
+ RB_CLEAR_NODE(&dso->rb_node);
INIT_LIST_HEAD(&dso->node);
INIT_LIST_HEAD(&dso->data.open_entry);
}
@@ -721,6 +825,10 @@ struct dso *dso__new(const char *name)
void dso__delete(struct dso *dso)
{
int i;
+
+ if (!RB_EMPTY_NODE(&dso->rb_node))
+ pr_err("DSO %s is still in rbtree when being deleted!\n",
+ dso->long_name);
for (i = 0; i < MAP__NR_TYPES; ++i)
symbols__delete(&dso->symbols[i]);
@@ -807,35 +915,34 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
return have_build_id;
}
-void dsos__add(struct list_head *head, struct dso *dso)
+void dsos__add(struct dsos *dsos, struct dso *dso)
{
- list_add_tail(&dso->node, head);
+ list_add_tail(&dso->node, &dsos->head);
+ dso__findlink_by_longname(&dsos->root, dso, NULL);
}
-struct dso *dsos__find(const struct list_head *head, const char *name, bool cmp_short)
+struct dso *dsos__find(const struct dsos *dsos, const char *name,
+ bool cmp_short)
{
struct dso *pos;
if (cmp_short) {
- list_for_each_entry(pos, head, node)
+ list_for_each_entry(pos, &dsos->head, node)
if (strcmp(pos->short_name, name) == 0)
return pos;
return NULL;
}
- list_for_each_entry(pos, head, node)
- if (strcmp(pos->long_name, name) == 0)
- return pos;
- return NULL;
+ return dso__find_by_longname(&dsos->root, name);
}
-struct dso *__dsos__findnew(struct list_head *head, const char *name)
+struct dso *__dsos__findnew(struct dsos *dsos, const char *name)
{
- struct dso *dso = dsos__find(head, name, false);
+ struct dso *dso = dsos__find(dsos, name, false);
if (!dso) {
dso = dso__new(name);
if (dso != NULL) {
- dsos__add(head, dso);
+ dsos__add(dsos, dso);
dso__set_basename(dso);
}
}
@@ -898,3 +1005,14 @@ size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp)
return ret;
}
+
+enum dso_type dso__type(struct dso *dso, struct machine *machine)
+{
+ int fd;
+
+ fd = dso__data_fd(dso, machine);
+ if (fd < 0)
+ return DSO__TYPE_UNKNOWN;
+
+ return dso__type_fd(fd);
+}
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index ad553ba257bf..acb651acc7fd 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -5,6 +5,7 @@
#include <linux/rbtree.h>
#include <stdbool.h>
#include <linux/types.h>
+#include <linux/bitops.h>
#include "map.h"
#include "build-id.h"
@@ -40,6 +41,23 @@ enum dso_swap_type {
DSO_SWAP__YES,
};
+enum dso_data_status {
+ DSO_DATA_STATUS_ERROR = -1,
+ DSO_DATA_STATUS_UNKNOWN = 0,
+ DSO_DATA_STATUS_OK = 1,
+};
+
+enum dso_data_status_seen {
+ DSO_DATA_STATUS_SEEN_ITRACE,
+};
+
+enum dso_type {
+ DSO__TYPE_UNKNOWN,
+ DSO__TYPE_64BIT,
+ DSO__TYPE_32BIT,
+ DSO__TYPE_X32BIT,
+};
+
#define DSO__SWAP(dso, type, val) \
({ \
type ____r = val; \
@@ -72,8 +90,18 @@ struct dso_cache {
char data[0];
};
+/*
+ * DSOs are put into both a list for fast iteration and rbtree for fast
+ * long name lookup.
+ */
+struct dsos {
+ struct list_head head;
+ struct rb_root root; /* rbtree root sorted by long name */
+};
+
struct dso {
struct list_head node;
+ struct rb_node rb_node; /* rbtree node sorted by long name */
struct rb_root symbols[MAP__NR_TYPES];
struct rb_root symbol_names[MAP__NR_TYPES];
void *a2l;
@@ -90,6 +118,7 @@ struct dso {
u8 annotate_warned:1;
u8 short_name_allocated:1;
u8 long_name_allocated:1;
+ u8 is_64_bit:1;
u8 sorted_by_name;
u8 loaded;
u8 rel;
@@ -103,6 +132,8 @@ struct dso {
struct {
struct rb_root cache;
int fd;
+ int status;
+ u32 status_seen;
size_t file_size;
struct list_head open_entry;
} data;
@@ -153,6 +184,7 @@ int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type t
* The dso__data_* external interface provides following functions:
* dso__data_fd
* dso__data_close
+ * dso__data_size
* dso__data_read_offset
* dso__data_read_addr
*
@@ -190,20 +222,22 @@ int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type t
int dso__data_fd(struct dso *dso, struct machine *machine);
void dso__data_close(struct dso *dso);
+off_t dso__data_size(struct dso *dso, struct machine *machine);
ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
u64 offset, u8 *data, ssize_t size);
ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
struct machine *machine, u64 addr,
u8 *data, ssize_t size);
+bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by);
struct map *dso__new_map(const char *name);
struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
const char *short_name, int dso_type);
-void dsos__add(struct list_head *head, struct dso *dso);
-struct dso *dsos__find(const struct list_head *head, const char *name,
+void dsos__add(struct dsos *dsos, struct dso *dso);
+struct dso *dsos__find(const struct dsos *dsos, const char *name,
bool cmp_short);
-struct dso *__dsos__findnew(struct list_head *head, const char *name);
+struct dso *__dsos__findnew(struct dsos *dsos, const char *name);
bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
@@ -229,4 +263,6 @@ static inline bool dso__is_kcore(struct dso *dso)
void dso__free_a2l(struct dso *dso);
+enum dso_type dso__type(struct dso *dso, struct machine *machine);
+
#endif /* __PERF_DSO */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index d0281bdfa582..4af6b279e34a 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -558,13 +558,17 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
struct map *map;
struct kmap *kmap;
int err;
+ union perf_event *event;
+
+ if (machine->vmlinux_maps[0] == NULL)
+ return -1;
+
/*
* We should get this from /sys/kernel/sections/.text, but till that is
* available use this, and after it is use this as a fallback for older
* kernels.
*/
- union perf_event *event = zalloc((sizeof(event->mmap) +
- machine->id_hdr_size));
+ event = zalloc((sizeof(event->mmap) + machine->id_hdr_size));
if (event == NULL) {
pr_debug("Not enough memory synthesizing mmap event "
"for kernel modules\n");
@@ -603,7 +607,14 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp)
{
- return fprintf(fp, ": %s:%d\n", event->comm.comm, event->comm.tid);
+ const char *s;
+
+ if (event->header.misc & PERF_RECORD_MISC_COMM_EXEC)
+ s = " exec";
+ else
+ s = "";
+
+ return fprintf(fp, "%s: %s:%d\n", s, event->comm.comm, event->comm.tid);
}
int perf_event__process_comm(struct perf_tool *tool __maybe_unused,
@@ -777,10 +788,11 @@ try_again:
* "[vdso]" dso, but for now lets use the old trick of looking
* in the whole kernel symbol list.
*/
- if ((long long)al->addr < 0 &&
- cpumode == PERF_RECORD_MISC_USER &&
- machine && mg != &machine->kmaps) {
+ if (cpumode == PERF_RECORD_MISC_USER && machine &&
+ mg != &machine->kmaps &&
+ machine__kernel_ip(machine, al->addr)) {
mg = &machine->kmaps;
+ load_map = true;
goto try_again;
}
} else {
@@ -866,3 +878,45 @@ int perf_event__preprocess_sample(const union perf_event *event,
return 0;
}
+
+bool is_bts_event(struct perf_event_attr *attr)
+{
+ return attr->type == PERF_TYPE_HARDWARE &&
+ (attr->config & PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
+ attr->sample_period == 1;
+}
+
+bool sample_addr_correlates_sym(struct perf_event_attr *attr)
+{
+ if (attr->type == PERF_TYPE_SOFTWARE &&
+ (attr->config == PERF_COUNT_SW_PAGE_FAULTS ||
+ attr->config == PERF_COUNT_SW_PAGE_FAULTS_MIN ||
+ attr->config == PERF_COUNT_SW_PAGE_FAULTS_MAJ))
+ return true;
+
+ if (is_bts_event(attr))
+ return true;
+
+ return false;
+}
+
+void perf_event__preprocess_sample_addr(union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine,
+ struct thread *thread,
+ struct addr_location *al)
+{
+ u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+
+ thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
+ sample->addr, al);
+ if (!al->map)
+ thread__find_addr_map(thread, machine, cpumode, MAP__VARIABLE,
+ sample->addr, al);
+
+ al->cpu = sample->cpu;
+ al->sym = NULL;
+
+ if (al->map)
+ al->sym = map__find_symbol(al->map, al->addr, NULL);
+}
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index e5dd40addb30..7eb7107731ec 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -156,6 +156,8 @@ struct perf_sample {
u32 cpu;
u32 raw_size;
u64 data_src;
+ u32 flags;
+ u16 insn_len;
void *raw_data;
struct ip_callchain *callchain;
struct branch_stack *branch_stack;
@@ -288,6 +290,16 @@ int perf_event__preprocess_sample(const union perf_event *event,
struct addr_location *al,
struct perf_sample *sample);
+struct thread;
+
+bool is_bts_event(struct perf_event_attr *attr);
+bool sample_addr_correlates_sym(struct perf_event_attr *attr);
+void perf_event__preprocess_sample_addr(union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine,
+ struct thread *thread,
+ struct addr_location *al);
+
const char *perf_event__name(unsigned int id);
size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 59ef2802fcf6..3cebc9a8d52e 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -25,6 +25,9 @@
#include <linux/bitops.h>
#include <linux/hash.h>
+static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx);
+static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx);
+
#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
#define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
@@ -37,6 +40,7 @@ void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
INIT_HLIST_HEAD(&evlist->heads[i]);
INIT_LIST_HEAD(&evlist->entries);
perf_evlist__set_maps(evlist, cpus, threads);
+ fdarray__init(&evlist->pollfd, 64);
evlist->workload.pid = -1;
}
@@ -102,7 +106,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
void perf_evlist__exit(struct perf_evlist *evlist)
{
zfree(&evlist->mmap);
- zfree(&evlist->pollfd);
+ fdarray__exit(&evlist->pollfd);
}
void perf_evlist__delete(struct perf_evlist *evlist)
@@ -122,6 +126,7 @@ void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
{
list_add_tail(&entry->node, &evlist->entries);
entry->idx = evlist->nr_entries;
+ entry->tracking = !entry->idx;
if (!evlist->nr_entries++)
perf_evlist__set_id_pos(evlist);
@@ -265,17 +270,27 @@ int perf_evlist__add_newtp(struct perf_evlist *evlist,
return 0;
}
+static int perf_evlist__nr_threads(struct perf_evlist *evlist,
+ struct perf_evsel *evsel)
+{
+ if (evsel->system_wide)
+ return 1;
+ else
+ return thread_map__nr(evlist->threads);
+}
+
void perf_evlist__disable(struct perf_evlist *evlist)
{
int cpu, thread;
struct perf_evsel *pos;
int nr_cpus = cpu_map__nr(evlist->cpus);
- int nr_threads = thread_map__nr(evlist->threads);
+ int nr_threads;
for (cpu = 0; cpu < nr_cpus; cpu++) {
evlist__for_each(evlist, pos) {
if (!perf_evsel__is_group_leader(pos) || !pos->fd)
continue;
+ nr_threads = perf_evlist__nr_threads(evlist, pos);
for (thread = 0; thread < nr_threads; thread++)
ioctl(FD(pos, cpu, thread),
PERF_EVENT_IOC_DISABLE, 0);
@@ -288,12 +303,13 @@ void perf_evlist__enable(struct perf_evlist *evlist)
int cpu, thread;
struct perf_evsel *pos;
int nr_cpus = cpu_map__nr(evlist->cpus);
- int nr_threads = thread_map__nr(evlist->threads);
+ int nr_threads;
for (cpu = 0; cpu < nr_cpus; cpu++) {
evlist__for_each(evlist, pos) {
if (!perf_evsel__is_group_leader(pos) || !pos->fd)
continue;
+ nr_threads = perf_evlist__nr_threads(evlist, pos);
for (thread = 0; thread < nr_threads; thread++)
ioctl(FD(pos, cpu, thread),
PERF_EVENT_IOC_ENABLE, 0);
@@ -305,12 +321,14 @@ int perf_evlist__disable_event(struct perf_evlist *evlist,
struct perf_evsel *evsel)
{
int cpu, thread, err;
+ int nr_cpus = cpu_map__nr(evlist->cpus);
+ int nr_threads = perf_evlist__nr_threads(evlist, evsel);
if (!evsel->fd)
return 0;
- for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
- for (thread = 0; thread < evlist->threads->nr; thread++) {
+ for (cpu = 0; cpu < nr_cpus; cpu++) {
+ for (thread = 0; thread < nr_threads; thread++) {
err = ioctl(FD(evsel, cpu, thread),
PERF_EVENT_IOC_DISABLE, 0);
if (err)
@@ -324,12 +342,14 @@ int perf_evlist__enable_event(struct perf_evlist *evlist,
struct perf_evsel *evsel)
{
int cpu, thread, err;
+ int nr_cpus = cpu_map__nr(evlist->cpus);
+ int nr_threads = perf_evlist__nr_threads(evlist, evsel);
if (!evsel->fd)
return -EINVAL;
- for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
- for (thread = 0; thread < evlist->threads->nr; thread++) {
+ for (cpu = 0; cpu < nr_cpus; cpu++) {
+ for (thread = 0; thread < nr_threads; thread++) {
err = ioctl(FD(evsel, cpu, thread),
PERF_EVENT_IOC_ENABLE, 0);
if (err)
@@ -339,21 +359,111 @@ int perf_evlist__enable_event(struct perf_evlist *evlist,
return 0;
}
-static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
+static int perf_evlist__enable_event_cpu(struct perf_evlist *evlist,
+ struct perf_evsel *evsel, int cpu)
+{
+ int thread, err;
+ int nr_threads = perf_evlist__nr_threads(evlist, evsel);
+
+ if (!evsel->fd)
+ return -EINVAL;
+
+ for (thread = 0; thread < nr_threads; thread++) {
+ err = ioctl(FD(evsel, cpu, thread),
+ PERF_EVENT_IOC_ENABLE, 0);
+ if (err)
+ return err;
+ }
+ return 0;
+}
+
+static int perf_evlist__enable_event_thread(struct perf_evlist *evlist,
+ struct perf_evsel *evsel,
+ int thread)
+{
+ int cpu, err;
+ int nr_cpus = cpu_map__nr(evlist->cpus);
+
+ if (!evsel->fd)
+ return -EINVAL;
+
+ for (cpu = 0; cpu < nr_cpus; cpu++) {
+ err = ioctl(FD(evsel, cpu, thread), PERF_EVENT_IOC_ENABLE, 0);
+ if (err)
+ return err;
+ }
+ return 0;
+}
+
+int perf_evlist__enable_event_idx(struct perf_evlist *evlist,
+ struct perf_evsel *evsel, int idx)
+{
+ bool per_cpu_mmaps = !cpu_map__empty(evlist->cpus);
+
+ if (per_cpu_mmaps)
+ return perf_evlist__enable_event_cpu(evlist, evsel, idx);
+ else
+ return perf_evlist__enable_event_thread(evlist, evsel, idx);
+}
+
+int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
{
int nr_cpus = cpu_map__nr(evlist->cpus);
int nr_threads = thread_map__nr(evlist->threads);
- int nfds = nr_cpus * nr_threads * evlist->nr_entries;
- evlist->pollfd = malloc(sizeof(struct pollfd) * nfds);
- return evlist->pollfd != NULL ? 0 : -ENOMEM;
+ int nfds = 0;
+ struct perf_evsel *evsel;
+
+ list_for_each_entry(evsel, &evlist->entries, node) {
+ if (evsel->system_wide)
+ nfds += nr_cpus;
+ else
+ nfds += nr_cpus * nr_threads;
+ }
+
+ if (fdarray__available_entries(&evlist->pollfd) < nfds &&
+ fdarray__grow(&evlist->pollfd, nfds) < 0)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, int idx)
+{
+ int pos = fdarray__add(&evlist->pollfd, fd, POLLIN | POLLERR | POLLHUP);
+ /*
+ * Save the idx so that when we filter out fds POLLHUP'ed we can
+ * close the associated evlist->mmap[] entry.
+ */
+ if (pos >= 0) {
+ evlist->pollfd.priv[pos].idx = idx;
+
+ fcntl(fd, F_SETFL, O_NONBLOCK);
+ }
+
+ return pos;
+}
+
+int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd)
+{
+ return __perf_evlist__add_pollfd(evlist, fd, -1);
+}
+
+static void perf_evlist__munmap_filtered(struct fdarray *fda, int fd)
+{
+ struct perf_evlist *evlist = container_of(fda, struct perf_evlist, pollfd);
+
+ perf_evlist__mmap_put(evlist, fda->priv[fd].idx);
}
-void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd)
+int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mask)
{
- fcntl(fd, F_SETFL, O_NONBLOCK);
- evlist->pollfd[evlist->nr_fds].fd = fd;
- evlist->pollfd[evlist->nr_fds].events = POLLIN;
- evlist->nr_fds++;
+ return fdarray__filter(&evlist->pollfd, revents_and_mask,
+ perf_evlist__munmap_filtered);
+}
+
+int perf_evlist__poll(struct perf_evlist *evlist, int timeout)
+{
+ return fdarray__poll(&evlist->pollfd, timeout);
}
static void perf_evlist__id_hash(struct perf_evlist *evlist,
@@ -566,14 +676,36 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
return event;
}
+static bool perf_mmap__empty(struct perf_mmap *md)
+{
+ return perf_mmap__read_head(md) != md->prev;
+}
+
+static void perf_evlist__mmap_get(struct perf_evlist *evlist, int idx)
+{
+ ++evlist->mmap[idx].refcnt;
+}
+
+static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx)
+{
+ BUG_ON(evlist->mmap[idx].refcnt == 0);
+
+ if (--evlist->mmap[idx].refcnt == 0)
+ __perf_evlist__munmap(evlist, idx);
+}
+
void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
{
+ struct perf_mmap *md = &evlist->mmap[idx];
+
if (!evlist->overwrite) {
- struct perf_mmap *md = &evlist->mmap[idx];
unsigned int old = md->prev;
perf_mmap__write_tail(md, old);
}
+
+ if (md->refcnt == 1 && perf_mmap__empty(md))
+ perf_evlist__mmap_put(evlist, idx);
}
static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
@@ -581,6 +713,7 @@ static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
if (evlist->mmap[idx].base != NULL) {
munmap(evlist->mmap[idx].base, evlist->mmap_len);
evlist->mmap[idx].base = NULL;
+ evlist->mmap[idx].refcnt = 0;
}
}
@@ -606,12 +739,31 @@ static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
return evlist->mmap != NULL ? 0 : -ENOMEM;
}
-static int __perf_evlist__mmap(struct perf_evlist *evlist,
- int idx, int prot, int mask, int fd)
+struct mmap_params {
+ int prot;
+ int mask;
+};
+
+static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
+ struct mmap_params *mp, int fd)
{
+ /*
+ * The last one will be done at perf_evlist__mmap_consume(), so that we
+ * make sure we don't prevent tools from consuming every last event in
+ * the ring buffer.
+ *
+ * I.e. we can get the POLLHUP meaning that the fd doesn't exist
+ * anymore, but the last events for it are still in the ring buffer,
+ * waiting to be consumed.
+ *
+ * Tools can chose to ignore this at their own discretion, but the
+ * evlist layer can't just drop it when filtering events in
+ * perf_evlist__filter_pollfd().
+ */
+ evlist->mmap[idx].refcnt = 2;
evlist->mmap[idx].prev = 0;
- evlist->mmap[idx].mask = mask;
- evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot,
+ evlist->mmap[idx].mask = mp->mask;
+ evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, mp->prot,
MAP_SHARED, fd, 0);
if (evlist->mmap[idx].base == MAP_FAILED) {
pr_debug2("failed to mmap perf event ring buffer, error %d\n",
@@ -620,27 +772,37 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist,
return -1;
}
- perf_evlist__add_pollfd(evlist, fd);
return 0;
}
static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
- int prot, int mask, int cpu, int thread,
- int *output)
+ struct mmap_params *mp, int cpu,
+ int thread, int *output)
{
struct perf_evsel *evsel;
evlist__for_each(evlist, evsel) {
- int fd = FD(evsel, cpu, thread);
+ int fd;
+
+ if (evsel->system_wide && thread)
+ continue;
+
+ fd = FD(evsel, cpu, thread);
if (*output == -1) {
*output = fd;
- if (__perf_evlist__mmap(evlist, idx, prot, mask,
- *output) < 0)
+ if (__perf_evlist__mmap(evlist, idx, mp, *output) < 0)
return -1;
} else {
if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
return -1;
+
+ perf_evlist__mmap_get(evlist, idx);
+ }
+
+ if (__perf_evlist__add_pollfd(evlist, fd, idx) < 0) {
+ perf_evlist__mmap_put(evlist, idx);
+ return -1;
}
if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
@@ -651,8 +813,8 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
return 0;
}
-static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot,
- int mask)
+static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist,
+ struct mmap_params *mp)
{
int cpu, thread;
int nr_cpus = cpu_map__nr(evlist->cpus);
@@ -663,8 +825,8 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot,
int output = -1;
for (thread = 0; thread < nr_threads; thread++) {
- if (perf_evlist__mmap_per_evsel(evlist, cpu, prot, mask,
- cpu, thread, &output))
+ if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu,
+ thread, &output))
goto out_unmap;
}
}
@@ -677,8 +839,8 @@ out_unmap:
return -1;
}
-static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot,
- int mask)
+static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist,
+ struct mmap_params *mp)
{
int thread;
int nr_threads = thread_map__nr(evlist->threads);
@@ -687,8 +849,8 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot,
for (thread = 0; thread < nr_threads; thread++) {
int output = -1;
- if (perf_evlist__mmap_per_evsel(evlist, thread, prot, mask, 0,
- thread, &output))
+ if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread,
+ &output))
goto out_unmap;
}
@@ -793,18 +955,20 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
struct perf_evsel *evsel;
const struct cpu_map *cpus = evlist->cpus;
const struct thread_map *threads = evlist->threads;
- int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE), mask;
+ struct mmap_params mp = {
+ .prot = PROT_READ | (overwrite ? 0 : PROT_WRITE),
+ };
if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
return -ENOMEM;
- if (evlist->pollfd == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
+ if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
return -ENOMEM;
evlist->overwrite = overwrite;
evlist->mmap_len = perf_evlist__mmap_size(pages);
pr_debug("mmap size %zuB\n", evlist->mmap_len);
- mask = evlist->mmap_len - page_size - 1;
+ mp.mask = evlist->mmap_len - page_size - 1;
evlist__for_each(evlist, evsel) {
if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
@@ -814,9 +978,9 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
}
if (cpu_map__empty(cpus))
- return perf_evlist__mmap_per_thread(evlist, prot, mask);
+ return perf_evlist__mmap_per_thread(evlist, &mp);
- return perf_evlist__mmap_per_cpu(evlist, prot, mask);
+ return perf_evlist__mmap_per_cpu(evlist, &mp);
}
int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
@@ -1055,6 +1219,8 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar
}
if (!evlist->workload.pid) {
+ int ret;
+
if (pipe_output)
dup2(2, 1);
@@ -1072,8 +1238,22 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar
/*
* Wait until the parent tells us to go.
*/
- if (read(go_pipe[0], &bf, 1) == -1)
- perror("unable to read pipe");
+ ret = read(go_pipe[0], &bf, 1);
+ /*
+ * The parent will ask for the execvp() to be performed by
+ * writing exactly one byte, in workload.cork_fd, usually via
+ * perf_evlist__start_workload().
+ *
+ * For cancelling the workload without actuallin running it,
+ * the parent will just close workload.cork_fd, without writing
+ * anything, i.e. read will return zero and we just exit()
+ * here.
+ */
+ if (ret != 1) {
+ if (ret == -1)
+ perror("unable to read pipe");
+ exit(ret);
+ }
execvp(argv[0], (char **)argv);
@@ -1196,7 +1376,7 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
int err, char *buf, size_t size)
{
int printed, value;
- char sbuf[128], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
+ char sbuf[STRERR_BUFSIZE], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
switch (err) {
case EACCES:
@@ -1214,10 +1394,11 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
"For your workloads it needs to be <= 1\nHint:\t");
}
printed += scnprintf(buf + printed, size - printed,
- "For system wide tracing it needs to be set to -1");
+ "For system wide tracing it needs to be set to -1.\n");
printed += scnprintf(buf + printed, size - printed,
- ".\nHint:\tThe current value is %d.", value);
+ "Hint:\tTry: 'sudo sh -c \"echo -1 > /proc/sys/kernel/perf_event_paranoid\"'\n"
+ "Hint:\tThe current value is %d.", value);
break;
default:
scnprintf(buf, size, "%s", emsg);
@@ -1243,3 +1424,19 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
list_splice(&move, &evlist->entries);
}
+
+void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
+ struct perf_evsel *tracking_evsel)
+{
+ struct perf_evsel *evsel;
+
+ if (tracking_evsel->tracking)
+ return;
+
+ evlist__for_each(evlist, evsel) {
+ if (evsel != tracking_evsel)
+ evsel->tracking = false;
+ }
+
+ tracking_evsel->tracking = true;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index f5173cd63693..bd312b01e876 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -2,6 +2,7 @@
#define __PERF_EVLIST_H 1
#include <linux/list.h>
+#include <api/fd/array.h>
#include <stdio.h>
#include "../perf.h"
#include "event.h"
@@ -17,9 +18,15 @@ struct record_opts;
#define PERF_EVLIST__HLIST_BITS 8
#define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS)
+/**
+ * struct perf_mmap - perf's ring buffer mmap details
+ *
+ * @refcnt - e.g. code using PERF_EVENT_IOC_SET_OUTPUT to share this
+ */
struct perf_mmap {
void *base;
int mask;
+ int refcnt;
unsigned int prev;
char event_copy[PERF_SAMPLE_MAX_SIZE];
};
@@ -29,7 +36,6 @@ struct perf_evlist {
struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
int nr_entries;
int nr_groups;
- int nr_fds;
int nr_mmaps;
size_t mmap_len;
int id_pos;
@@ -40,8 +46,8 @@ struct perf_evlist {
pid_t pid;
} workload;
bool overwrite;
+ struct fdarray pollfd;
struct perf_mmap *mmap;
- struct pollfd *pollfd;
struct thread_map *threads;
struct cpu_map *cpus;
struct perf_evsel *selected;
@@ -82,7 +88,11 @@ perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
int cpu, int thread, u64 id);
-void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
+int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
+int perf_evlist__alloc_pollfd(struct perf_evlist *evlist);
+int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mask);
+
+int perf_evlist__poll(struct perf_evlist *evlist, int timeout);
struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
@@ -122,6 +132,8 @@ int perf_evlist__disable_event(struct perf_evlist *evlist,
struct perf_evsel *evsel);
int perf_evlist__enable_event(struct perf_evlist *evlist,
struct perf_evsel *evsel);
+int perf_evlist__enable_event_idx(struct perf_evlist *evlist,
+ struct perf_evsel *evsel, int idx);
void perf_evlist__set_selected(struct perf_evlist *evlist,
struct perf_evsel *evsel);
@@ -262,4 +274,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
#define evlist__for_each_safe(evlist, tmp, evsel) \
__evlist__for_each_safe(&(evlist)->entries, tmp, evsel)
+void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
+ struct perf_evsel *tracking_evsel);
+
#endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 8606175fe1e8..e0868a901c4a 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -29,6 +29,7 @@ static struct {
bool sample_id_all;
bool exclude_guest;
bool mmap2;
+ bool cloexec;
} perf_missing_features;
#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
@@ -161,6 +162,7 @@ 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;
evsel->unit = "";
@@ -501,20 +503,19 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size)
}
static void
-perf_evsel__config_callgraph(struct perf_evsel *evsel,
- struct record_opts *opts)
+perf_evsel__config_callgraph(struct perf_evsel *evsel)
{
bool function = perf_evsel__is_function_event(evsel);
struct perf_event_attr *attr = &evsel->attr;
perf_evsel__set_sample_bit(evsel, CALLCHAIN);
- if (opts->call_graph == CALLCHAIN_DWARF) {
+ if (callchain_param.record_mode == CALLCHAIN_DWARF) {
if (!function) {
perf_evsel__set_sample_bit(evsel, REGS_USER);
perf_evsel__set_sample_bit(evsel, STACK_USER);
attr->sample_regs_user = PERF_REGS_MASK;
- attr->sample_stack_user = opts->stack_dump_size;
+ attr->sample_stack_user = callchain_param.dump_size;
attr->exclude_callchain_user = 1;
} else {
pr_info("Cannot use DWARF unwind for function trace event,"
@@ -560,7 +561,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
{
struct perf_evsel *leader = evsel->leader;
struct perf_event_attr *attr = &evsel->attr;
- int track = !evsel->idx; /* only the first counter needs these */
+ 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;
@@ -623,8 +624,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
attr->mmap_data = track;
}
- if (opts->call_graph_enabled)
- perf_evsel__config_callgraph(evsel, opts);
+ if (callchain_param.enabled && !evsel->no_aux_samples)
+ perf_evsel__config_callgraph(evsel);
if (target__has_cpu(&opts->target))
perf_evsel__set_sample_bit(evsel, CPU);
@@ -632,12 +633,15 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
if (opts->period)
perf_evsel__set_sample_bit(evsel, PERIOD);
- if (!perf_missing_features.sample_id_all &&
- (opts->sample_time || !opts->no_inherit ||
- target__has_cpu(&opts->target) || per_cpu))
+ /*
+ * When the user explicitely 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)))
perf_evsel__set_sample_bit(evsel, TIME);
- if (opts->raw_samples) {
+ 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);
@@ -650,7 +654,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
attr->watermark = 0;
attr->wakeup_events = 1;
}
- if (opts->branch_stack) {
+ if (opts->branch_stack && !evsel->no_aux_samples) {
perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
attr->branch_sample_type = opts->branch_stack;
}
@@ -681,11 +685,20 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
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;
+ }
}
int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
{
int cpu, thread;
+
+ if (evsel->system_wide)
+ nthreads = 1;
+
evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
if (evsel->fd) {
@@ -704,6 +717,9 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthrea
{
int cpu, thread;
+ if (evsel->system_wide)
+ nthreads = 1;
+
for (cpu = 0; cpu < ncpus; cpu++) {
for (thread = 0; thread < nthreads; thread++) {
int fd = FD(evsel, cpu, thread),
@@ -734,6 +750,9 @@ int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads)
int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
{
+ 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;
@@ -778,6 +797,9 @@ void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
{
int cpu, thread;
+ if (evsel->system_wide)
+ nthreads = 1;
+
for (cpu = 0; cpu < ncpus; cpu++)
for (thread = 0; thread < nthreads; ++thread) {
close(FD(evsel, cpu, thread));
@@ -866,6 +888,9 @@ int __perf_evsel__read(struct perf_evsel *evsel,
int cpu, thread;
struct perf_counts_values *aggr = &evsel->counts->aggr, count;
+ if (evsel->system_wide)
+ nthreads = 1;
+
aggr->val = aggr->ena = aggr->run = 0;
for (cpu = 0; cpu < ncpus; cpu++) {
@@ -960,6 +985,7 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp)
ret += PRINT_ATTR2(exclude_user, exclude_kernel);
ret += PRINT_ATTR2(exclude_hv, exclude_idle);
ret += PRINT_ATTR2(mmap, comm);
+ ret += PRINT_ATTR2(mmap2, comm_exec);
ret += PRINT_ATTR2(freq, inherit_stat);
ret += PRINT_ATTR2(enable_on_exec, task);
ret += PRINT_ATTR2(watermark, precise_ip);
@@ -967,7 +993,6 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp)
ret += PRINT_ATTR2(exclude_host, exclude_guest);
ret += PRINT_ATTR2N("excl.callchain_kern", exclude_callchain_kernel,
"excl.callchain_user", exclude_callchain_user);
- ret += PRINT_ATTR_U32(mmap2);
ret += PRINT_ATTR_U32(wakeup_events);
ret += PRINT_ATTR_U32(wakeup_watermark);
@@ -988,21 +1013,28 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp)
static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
struct thread_map *threads)
{
- int cpu, thread;
- unsigned long flags = 0;
+ 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 (evsel->system_wide)
+ nthreads = 1;
+ else
+ nthreads = threads->nr;
+
if (evsel->fd == NULL &&
- perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0)
+ perf_evsel__alloc_fd(evsel, cpus->nr, nthreads) < 0)
return -ENOMEM;
if (evsel->cgrp) {
- flags = PERF_FLAG_PID_CGROUP;
+ flags |= PERF_FLAG_PID_CGROUP;
pid = evsel->cgrp->fd;
}
fallback_missing_features:
+ 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)
@@ -1016,10 +1048,10 @@ retry_sample_id:
for (cpu = 0; cpu < cpus->nr; cpu++) {
- for (thread = 0; thread < threads->nr; thread++) {
+ for (thread = 0; thread < nthreads; thread++) {
int group_fd;
- if (!evsel->cgrp)
+ if (!evsel->cgrp && !evsel->system_wide)
pid = threads->map[thread];
group_fd = get_group_fd(evsel, cpu, thread);
@@ -1071,7 +1103,10 @@ try_fallback:
if (err != -EINVAL || cpu > 0 || thread > 0)
goto out_close;
- if (!perf_missing_features.mmap2 && evsel->attr.mmap2) {
+ if (!perf_missing_features.cloexec && (flags & PERF_FLAG_FD_CLOEXEC)) {
+ perf_missing_features.cloexec = true;
+ goto fallback_missing_features;
+ } else if (!perf_missing_features.mmap2 && evsel->attr.mmap2) {
perf_missing_features.mmap2 = true;
goto fallback_missing_features;
} else if (!perf_missing_features.exclude_guest &&
@@ -1089,7 +1124,7 @@ out_close:
close(FD(evsel, cpu, thread));
FD(evsel, cpu, thread) = -1;
}
- thread = threads->nr;
+ thread = nthreads;
} while (--cpu >= 0);
return err;
}
@@ -1940,6 +1975,7 @@ int perf_evsel__fprintf(struct perf_evsel *evsel,
if_print(mmap);
if_print(mmap2);
if_print(comm);
+ if_print(comm_exec);
if_print(freq);
if_print(inherit_stat);
if_print(enable_on_exec);
@@ -1990,6 +2026,8 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
int err, char *msg, size_t size)
{
+ char sbuf[STRERR_BUFSIZE];
+
switch (err) {
case EPERM:
case EACCES:
@@ -2024,13 +2062,20 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
"No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it.");
#endif
break;
+ 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;
default:
break;
}
return scnprintf(msg, size,
- "The sys_perf_event_open() syscall returned with %d (%s) for event (%s). \n"
+ "The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n"
"/bin/dmesg may provide additional information.\n"
"No CONFIG_PERF_EVENTS=y kernel support configured?\n",
- err, strerror(err), perf_evsel__name(evsel));
+ err, strerror_r(err, sbuf, sizeof(sbuf)),
+ perf_evsel__name(evsel));
}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index a52e9a5bb2d0..7bc314be6a7b 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -83,6 +83,10 @@ struct perf_evsel {
int is_pos;
bool supported;
bool needs_swap;
+ bool no_aux_samples;
+ bool immediate;
+ bool system_wide;
+ bool tracking;
/* parse modifier helper */
int exclude_GH;
int nr_members;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 893f8e2df928..ce0de00399da 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -200,6 +200,47 @@ static int write_buildid(const char *name, size_t name_len, u8 *build_id,
return write_padded(fd, name, name_len + 1, len);
}
+static int __dsos__hit_all(struct list_head *head)
+{
+ struct dso *pos;
+
+ list_for_each_entry(pos, head, node)
+ pos->hit = true;
+
+ return 0;
+}
+
+static int machine__hit_all_dsos(struct machine *machine)
+{
+ int err;
+
+ err = __dsos__hit_all(&machine->kernel_dsos.head);
+ if (err)
+ return err;
+
+ return __dsos__hit_all(&machine->user_dsos.head);
+}
+
+int dsos__hit_all(struct perf_session *session)
+{
+ struct rb_node *nd;
+ int err;
+
+ err = machine__hit_all_dsos(&session->machines.host);
+ if (err)
+ return err;
+
+ for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+ struct machine *pos = rb_entry(nd, struct machine, rb_node);
+
+ err = machine__hit_all_dsos(pos);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
static int __dsos__write_buildid_table(struct list_head *head,
struct machine *machine,
pid_t pid, u16 misc, int fd)
@@ -215,9 +256,9 @@ static int __dsos__write_buildid_table(struct list_head *head,
if (!pos->hit)
continue;
- if (is_vdso_map(pos->short_name)) {
- name = (char *) VDSO__MAP_NAME;
- name_len = sizeof(VDSO__MAP_NAME) + 1;
+ if (dso__is_vdso(pos)) {
+ name = pos->short_name;
+ name_len = pos->short_name_len + 1;
} else if (dso__is_kcore(pos)) {
machine__mmap_name(machine, nm, sizeof(nm));
name = nm;
@@ -247,11 +288,12 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
umisc = PERF_RECORD_MISC_GUEST_USER;
}
- err = __dsos__write_buildid_table(&machine->kernel_dsos, machine,
+ err = __dsos__write_buildid_table(&machine->kernel_dsos.head, machine,
machine->pid, kmisc, fd);
if (err == 0)
- err = __dsos__write_buildid_table(&machine->user_dsos, machine,
- machine->pid, umisc, fd);
+ err = __dsos__write_buildid_table(&machine->user_dsos.head,
+ machine, machine->pid, umisc,
+ fd);
return err;
}
@@ -298,7 +340,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
len = scnprintf(filename, size, "%s%s%s",
debugdir, slash ? "/" : "",
- is_vdso ? VDSO__MAP_NAME : realname);
+ is_vdso ? DSO__NAME_VDSO : realname);
if (mkdir_p(filename, 0755))
goto out_free;
@@ -386,7 +428,7 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine,
const char *debugdir)
{
bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
- bool is_vdso = is_vdso_map(dso->short_name);
+ bool is_vdso = dso__is_vdso(dso);
const char *name = dso->long_name;
char nm[PATH_MAX];
@@ -414,9 +456,10 @@ static int __dsos__cache_build_ids(struct list_head *head,
static int machine__cache_build_ids(struct machine *machine, const char *debugdir)
{
- int ret = __dsos__cache_build_ids(&machine->kernel_dsos, machine,
+ int ret = __dsos__cache_build_ids(&machine->kernel_dsos.head, machine,
debugdir);
- ret |= __dsos__cache_build_ids(&machine->user_dsos, machine, debugdir);
+ ret |= __dsos__cache_build_ids(&machine->user_dsos.head, machine,
+ debugdir);
return ret;
}
@@ -442,8 +485,10 @@ static int perf_session__cache_build_ids(struct perf_session *session)
static bool machine__read_build_ids(struct machine *machine, bool with_hits)
{
- bool ret = __dsos__read_build_ids(&machine->kernel_dsos, with_hits);
- ret |= __dsos__read_build_ids(&machine->user_dsos, with_hits);
+ bool ret;
+
+ ret = __dsos__read_build_ids(&machine->kernel_dsos.head, with_hits);
+ ret |= __dsos__read_build_ids(&machine->user_dsos.head, with_hits);
return ret;
}
@@ -1507,7 +1552,7 @@ static int __event_process_build_id(struct build_id_event *bev,
struct perf_session *session)
{
int err = -1;
- struct list_head *head;
+ struct dsos *dsos;
struct machine *machine;
u16 misc;
struct dso *dso;
@@ -1522,22 +1567,22 @@ static int __event_process_build_id(struct build_id_event *bev,
switch (misc) {
case PERF_RECORD_MISC_KERNEL:
dso_type = DSO_TYPE_KERNEL;
- head = &machine->kernel_dsos;
+ dsos = &machine->kernel_dsos;
break;
case PERF_RECORD_MISC_GUEST_KERNEL:
dso_type = DSO_TYPE_GUEST_KERNEL;
- head = &machine->kernel_dsos;
+ dsos = &machine->kernel_dsos;
break;
case PERF_RECORD_MISC_USER:
case PERF_RECORD_MISC_GUEST_USER:
dso_type = DSO_TYPE_USER;
- head = &machine->user_dsos;
+ dsos = &machine->user_dsos;
break;
default:
goto out;
}
- dso = __dsos__findnew(head, filename);
+ dso = __dsos__findnew(dsos, filename);
if (dso != NULL) {
char sbuild_id[BUILD_ID_SIZE * 2 + 1];
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index d08cfe499404..8f5cbaea64a5 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -151,6 +151,8 @@ int perf_event__process_build_id(struct perf_tool *tool,
struct perf_session *session);
bool is_perf_magic(u64 magic);
+int dsos__hit_all(struct perf_session *session);
+
/*
* arch specific callback
*/
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 30df6187ee02..86569fa3651d 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -277,6 +277,28 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
}
}
+void hists__delete_entries(struct hists *hists)
+{
+ struct rb_node *next = rb_first(&hists->entries);
+ struct hist_entry *n;
+
+ while (next) {
+ n = rb_entry(next, struct hist_entry, rb_node);
+ next = rb_next(&n->rb_node);
+
+ rb_erase(&n->rb_node, &hists->entries);
+
+ if (sort__need_collapse)
+ rb_erase(&n->rb_node_in, &hists->entries_collapsed);
+
+ --hists->nr_entries;
+ if (!n->filtered)
+ --hists->nr_non_filtered_entries;
+
+ hist_entry__free(n);
+ }
+}
+
/*
* histogram, sorted on item, collects periods
*/
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 742f49a85725..8c9c70e18cbb 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -152,6 +152,7 @@ void hists__output_resort(struct hists *hists);
void hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
+void hists__delete_entries(struct hists *hists);
void hists__output_recalc_col_len(struct hists *hists, int max_rows);
u64 hists__total_period(struct hists *hists);
@@ -192,6 +193,7 @@ struct perf_hpp {
};
struct perf_hpp_fmt {
+ const char *name;
int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
struct perf_evsel *evsel);
int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
@@ -207,6 +209,8 @@ struct perf_hpp_fmt {
struct list_head list;
struct list_head sort_list;
bool elide;
+ int len;
+ int user_len;
};
extern struct list_head perf_hpp__list;
@@ -261,17 +265,19 @@ static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format)
}
void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists);
+void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists);
+void perf_hpp__set_user_width(const char *width_list_str);
typedef u64 (*hpp_field_fn)(struct hist_entry *he);
typedef int (*hpp_callback_fn)(struct perf_hpp *hpp, bool front);
typedef int (*hpp_snprint_fn)(struct perf_hpp *hpp, const char *fmt, ...);
-int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
- hpp_field_fn get_field, const char *fmt,
- hpp_snprint_fn print_fn, bool fmt_percent);
-int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he,
- hpp_field_fn get_field, const char *fmt,
- hpp_snprint_fn print_fn, bool fmt_percent);
+int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he, hpp_field_fn get_field,
+ const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent);
+int hpp__fmt_acc(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+ struct hist_entry *he, hpp_field_fn get_field,
+ const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent);
static inline void advance_hpp(struct perf_hpp *hpp, int inc)
{
diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h
index 9844c31b7c2b..09e8e7aea7c6 100644
--- a/tools/perf/util/include/linux/kernel.h
+++ b/tools/perf/util/include/linux/kernel.h
@@ -94,27 +94,6 @@ static inline int scnprintf(char * buf, size_t size, const char * fmt, ...)
return (i >= ssize) ? (ssize - 1) : i;
}
-int eprintf(int level,
- const char *fmt, ...) __attribute__((format(printf, 2, 3)));
-
-#ifndef pr_fmt
-#define pr_fmt(fmt) fmt
-#endif
-
-#define pr_err(fmt, ...) \
- eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_warning(fmt, ...) \
- eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_info(fmt, ...) \
- eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_debug(fmt, ...) \
- eprintf(1, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_debugN(n, fmt, ...) \
- eprintf(n, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__)
-
/*
* This looks more complex than it should be. But we need to
* get the type for the ~ right in round_down (it needs to be
diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h
new file mode 100644
index 000000000000..cf1d7913783b
--- /dev/null
+++ b/tools/perf/util/kvm-stat.h
@@ -0,0 +1,139 @@
+#ifndef __PERF_KVM_STAT_H
+#define __PERF_KVM_STAT_H
+
+#include "../perf.h"
+#include "evsel.h"
+#include "evlist.h"
+#include "session.h"
+#include "tool.h"
+#include "stat.h"
+
+struct event_key {
+ #define INVALID_KEY (~0ULL)
+ u64 key;
+ int info;
+ struct exit_reasons_table *exit_reasons;
+};
+
+struct kvm_event_stats {
+ u64 time;
+ struct stats stats;
+};
+
+struct kvm_event {
+ struct list_head hash_entry;
+ struct rb_node rb;
+
+ struct event_key key;
+
+ struct kvm_event_stats total;
+
+ #define DEFAULT_VCPU_NUM 8
+ int max_vcpu;
+ struct kvm_event_stats *vcpu;
+};
+
+typedef int (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int);
+
+struct kvm_event_key {
+ const char *name;
+ key_cmp_fun key;
+};
+
+struct perf_kvm_stat;
+
+struct child_event_ops {
+ void (*get_key)(struct perf_evsel *evsel,
+ struct perf_sample *sample,
+ struct event_key *key);
+ const char *name;
+};
+
+struct kvm_events_ops {
+ bool (*is_begin_event)(struct perf_evsel *evsel,
+ struct perf_sample *sample,
+ struct event_key *key);
+ bool (*is_end_event)(struct perf_evsel *evsel,
+ struct perf_sample *sample, struct event_key *key);
+ struct child_event_ops *child_ops;
+ void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key,
+ char *decode);
+ const char *name;
+};
+
+struct exit_reasons_table {
+ unsigned long exit_code;
+ const char *reason;
+};
+
+#define EVENTS_BITS 12
+#define EVENTS_CACHE_SIZE (1UL << EVENTS_BITS)
+
+struct perf_kvm_stat {
+ struct perf_tool tool;
+ struct record_opts opts;
+ struct perf_evlist *evlist;
+ struct perf_session *session;
+
+ const char *file_name;
+ const char *report_event;
+ const char *sort_key;
+ int trace_vcpu;
+
+ struct exit_reasons_table *exit_reasons;
+ const char *exit_reasons_isa;
+
+ struct kvm_events_ops *events_ops;
+ key_cmp_fun compare;
+ struct list_head kvm_events_cache[EVENTS_CACHE_SIZE];
+
+ u64 total_time;
+ u64 total_count;
+ u64 lost_events;
+ u64 duration;
+
+ struct intlist *pid_list;
+
+ struct rb_root result;
+
+ int timerfd;
+ unsigned int display_time;
+ bool live;
+};
+
+struct kvm_reg_events_ops {
+ const char *name;
+ struct kvm_events_ops *ops;
+};
+
+void exit_event_get_key(struct perf_evsel *evsel,
+ struct perf_sample *sample,
+ struct event_key *key);
+bool exit_event_begin(struct perf_evsel *evsel,
+ struct perf_sample *sample,
+ struct event_key *key);
+bool exit_event_end(struct perf_evsel *evsel,
+ struct perf_sample *sample,
+ struct event_key *key);
+void exit_event_decode_key(struct perf_kvm_stat *kvm,
+ struct event_key *key,
+ char *decode);
+
+bool kvm_exit_event(struct perf_evsel *evsel);
+bool kvm_entry_event(struct perf_evsel *evsel);
+
+#define define_exit_reasons_table(name, symbols) \
+ static struct exit_reasons_table name[] = { \
+ symbols, { -1, NULL } \
+ }
+
+/*
+ * arch specific callbacks and data structures
+ */
+int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid);
+
+extern const char * const kvm_events_tp[];
+extern struct kvm_reg_events_ops kvm_reg_events_ops[];
+extern const char * const kvm_skip_events[];
+
+#endif /* __PERF_KVM_STAT_H */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index c73e1fc12e53..b7d477fbda02 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -8,6 +8,7 @@
#include "sort.h"
#include "strlist.h"
#include "thread.h"
+#include "vdso.h"
#include <stdbool.h>
#include <symbol/kallsyms.h>
#include "unwind.h"
@@ -16,25 +17,29 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
{
map_groups__init(&machine->kmaps);
RB_CLEAR_NODE(&machine->rb_node);
- INIT_LIST_HEAD(&machine->user_dsos);
- INIT_LIST_HEAD(&machine->kernel_dsos);
+ INIT_LIST_HEAD(&machine->user_dsos.head);
+ INIT_LIST_HEAD(&machine->kernel_dsos.head);
machine->threads = RB_ROOT;
INIT_LIST_HEAD(&machine->dead_threads);
machine->last_match = NULL;
+ machine->vdso_info = NULL;
+
machine->kmaps.machine = machine;
machine->pid = pid;
machine->symbol_filter = NULL;
machine->id_hdr_size = 0;
+ machine->comm_exec = false;
+ machine->kernel_start = 0;
machine->root_dir = strdup(root_dir);
if (machine->root_dir == NULL)
return -ENOMEM;
if (pid != HOST_KERNEL_ID) {
- struct thread *thread = machine__findnew_thread(machine, 0,
+ struct thread *thread = machine__findnew_thread(machine, -1,
pid);
char comm[64];
@@ -45,6 +50,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
thread__set_comm(thread, comm, 0);
}
+ machine->current_tid = NULL;
+
return 0;
}
@@ -65,11 +72,12 @@ out_delete:
return NULL;
}
-static void dsos__delete(struct list_head *dsos)
+static void dsos__delete(struct dsos *dsos)
{
struct dso *pos, *n;
- list_for_each_entry_safe(pos, n, dsos, node) {
+ list_for_each_entry_safe(pos, n, &dsos->head, node) {
+ RB_CLEAR_NODE(&pos->rb_node);
list_del(&pos->node);
dso__delete(pos);
}
@@ -103,7 +111,9 @@ void machine__exit(struct machine *machine)
map_groups__exit(&machine->kmaps);
dsos__delete(&machine->user_dsos);
dsos__delete(&machine->kernel_dsos);
+ vdso__exit(machine);
zfree(&machine->root_dir);
+ zfree(&machine->current_tid);
}
void machine__delete(struct machine *machine)
@@ -172,6 +182,19 @@ void machines__set_symbol_filter(struct machines *machines,
}
}
+void machines__set_comm_exec(struct machines *machines, bool comm_exec)
+{
+ struct rb_node *nd;
+
+ machines->host.comm_exec = comm_exec;
+
+ for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+ struct machine *machine = rb_entry(nd, struct machine, rb_node);
+
+ machine->comm_exec = comm_exec;
+ }
+}
+
struct machine *machines__find(struct machines *machines, pid_t pid)
{
struct rb_node **p = &machines->guests.rb_node;
@@ -272,6 +295,52 @@ void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size)
return;
}
+static void machine__update_thread_pid(struct machine *machine,
+ struct thread *th, pid_t pid)
+{
+ struct thread *leader;
+
+ if (pid == th->pid_ || pid == -1 || th->pid_ != -1)
+ return;
+
+ th->pid_ = pid;
+
+ if (th->pid_ == th->tid)
+ return;
+
+ leader = machine__findnew_thread(machine, th->pid_, th->pid_);
+ if (!leader)
+ goto out_err;
+
+ if (!leader->mg)
+ leader->mg = map_groups__new();
+
+ if (!leader->mg)
+ goto out_err;
+
+ if (th->mg == leader->mg)
+ return;
+
+ if (th->mg) {
+ /*
+ * Maps are created from MMAP events which provide the pid and
+ * tid. Consequently there never should be any maps on a thread
+ * with an unknown pid. Just print an error if there are.
+ */
+ if (!map_groups__empty(th->mg))
+ pr_err("Discarding thread maps for %d:%d\n",
+ th->pid_, th->tid);
+ map_groups__delete(th->mg);
+ }
+
+ th->mg = map_groups__get(leader->mg);
+
+ return;
+
+out_err:
+ pr_err("Failed to join map groups for %d:%d\n", th->pid_, th->tid);
+}
+
static struct thread *__machine__findnew_thread(struct machine *machine,
pid_t pid, pid_t tid,
bool create)
@@ -285,10 +354,10 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
* so most of the time we dont have to look up
* the full rbtree:
*/
- if (machine->last_match && machine->last_match->tid == tid) {
- if (pid && pid != machine->last_match->pid_)
- machine->last_match->pid_ = pid;
- return machine->last_match;
+ th = machine->last_match;
+ if (th && th->tid == tid) {
+ machine__update_thread_pid(machine, th, pid);
+ return th;
}
while (*p != NULL) {
@@ -297,8 +366,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
if (th->tid == tid) {
machine->last_match = th;
- if (pid && pid != th->pid_)
- th->pid_ = pid;
+ machine__update_thread_pid(machine, th, pid);
return th;
}
@@ -325,8 +393,10 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
* within thread__init_map_groups to find the thread
* leader and that would screwed the rb tree.
*/
- if (thread__init_map_groups(th, machine))
+ if (thread__init_map_groups(th, machine)) {
+ thread__delete(th);
return NULL;
+ }
}
return th;
@@ -344,17 +414,31 @@ struct thread *machine__find_thread(struct machine *machine, pid_t pid,
return __machine__findnew_thread(machine, pid, tid, false);
}
+struct comm *machine__thread_exec_comm(struct machine *machine,
+ struct thread *thread)
+{
+ if (machine->comm_exec)
+ return thread__exec_comm(thread);
+ else
+ return thread__comm(thread);
+}
+
int machine__process_comm_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample)
{
struct thread *thread = machine__findnew_thread(machine,
event->comm.pid,
event->comm.tid);
+ bool exec = event->header.misc & PERF_RECORD_MISC_COMM_EXEC;
+
+ if (exec)
+ machine->comm_exec = true;
if (dump_trace)
perf_event__fprintf_comm(event, stdout);
- if (thread == NULL || thread__set_comm(thread, event->comm.comm, sample->time)) {
+ if (thread == NULL ||
+ __thread__set_comm(thread, event->comm.comm, sample->time, exec)) {
dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
return -1;
}
@@ -394,23 +478,23 @@ struct map *machine__new_module(struct machine *machine, u64 start,
size_t machines__fprintf_dsos(struct machines *machines, FILE *fp)
{
struct rb_node *nd;
- size_t ret = __dsos__fprintf(&machines->host.kernel_dsos, fp) +
- __dsos__fprintf(&machines->host.user_dsos, fp);
+ size_t ret = __dsos__fprintf(&machines->host.kernel_dsos.head, fp) +
+ __dsos__fprintf(&machines->host.user_dsos.head, fp);
for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
struct machine *pos = rb_entry(nd, struct machine, rb_node);
- ret += __dsos__fprintf(&pos->kernel_dsos, fp);
- ret += __dsos__fprintf(&pos->user_dsos, fp);
+ ret += __dsos__fprintf(&pos->kernel_dsos.head, fp);
+ ret += __dsos__fprintf(&pos->user_dsos.head, fp);
}
return ret;
}
-size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp,
+size_t machine__fprintf_dsos_buildid(struct machine *m, FILE *fp,
bool (skip)(struct dso *dso, int parm), int parm)
{
- return __dsos__fprintf_buildid(&machine->kernel_dsos, fp, skip, parm) +
- __dsos__fprintf_buildid(&machine->user_dsos, fp, skip, parm);
+ return __dsos__fprintf_buildid(&m->kernel_dsos.head, fp, skip, parm) +
+ __dsos__fprintf_buildid(&m->user_dsos.head, fp, skip, parm);
}
size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp,
@@ -511,8 +595,8 @@ const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL};
* Returns the name of the start symbol in *symbol_name. Pass in NULL as
* symbol_name if it's not that important.
*/
-static u64 machine__get_kernel_start_addr(struct machine *machine,
- const char **symbol_name)
+static u64 machine__get_running_kernel_start(struct machine *machine,
+ const char **symbol_name)
{
char filename[PATH_MAX];
int i;
@@ -539,7 +623,7 @@ static u64 machine__get_kernel_start_addr(struct machine *machine,
int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
{
enum map_type type;
- u64 start = machine__get_kernel_start_addr(machine, NULL);
+ u64 start = machine__get_running_kernel_start(machine, NULL);
for (type = 0; type < MAP__NR_TYPES; ++type) {
struct kmap *kmap;
@@ -858,7 +942,7 @@ int machine__create_kernel_maps(struct machine *machine)
{
struct dso *kernel = machine__get_kernel(machine);
const char *name;
- u64 addr = machine__get_kernel_start_addr(machine, &name);
+ u64 addr = machine__get_running_kernel_start(machine, &name);
if (!addr)
return -1;
@@ -911,7 +995,7 @@ static bool machine__uses_kcore(struct machine *machine)
{
struct dso *dso;
- list_for_each_entry(dso, &machine->kernel_dsos, node) {
+ list_for_each_entry(dso, &machine->kernel_dsos.head, node) {
if (dso__is_kcore(dso))
return true;
}
@@ -1045,14 +1129,14 @@ int machine__process_mmap2_event(struct machine *machine,
else
type = MAP__FUNCTION;
- map = map__new(&machine->user_dsos, event->mmap2.start,
+ map = map__new(machine, event->mmap2.start,
event->mmap2.len, event->mmap2.pgoff,
event->mmap2.pid, event->mmap2.maj,
event->mmap2.min, event->mmap2.ino,
event->mmap2.ino_generation,
event->mmap2.prot,
event->mmap2.flags,
- event->mmap2.filename, type);
+ event->mmap2.filename, type, thread);
if (map == NULL)
goto out_problem;
@@ -1095,11 +1179,11 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
else
type = MAP__FUNCTION;
- map = map__new(&machine->user_dsos, event->mmap.start,
+ map = map__new(machine, event->mmap.start,
event->mmap.len, event->mmap.pgoff,
event->mmap.pid, 0, 0, 0, 0, 0, 0,
event->mmap.filename,
- type);
+ type, thread);
if (map == NULL)
goto out_problem;
@@ -1231,6 +1315,16 @@ static void ip__resolve_data(struct machine *machine, struct thread *thread,
thread__find_addr_location(thread, machine, m, MAP__VARIABLE, addr,
&al);
+ if (al.map == NULL) {
+ /*
+ * some shared data regions have execute bit set which puts
+ * their mapping in the MAP__FUNCTION type array.
+ * Check there as a fallback option before dropping the sample.
+ */
+ thread__find_addr_location(thread, machine, m, MAP__FUNCTION, addr,
+ &al);
+ }
+
ams->addr = addr;
ams->al_addr = al.addr;
ams->sym = al.sym;
@@ -1281,7 +1375,9 @@ static int machine__resolve_callchain_sample(struct machine *machine,
u8 cpumode = PERF_RECORD_MISC_USER;
int chain_nr = min(max_stack, (int)chain->nr);
int i;
+ int j;
int err;
+ int skip_idx __maybe_unused;
callchain_cursor_reset(&callchain_cursor);
@@ -1290,14 +1386,26 @@ static int machine__resolve_callchain_sample(struct machine *machine,
return 0;
}
+ /*
+ * Based on DWARF debug information, some architectures skip
+ * a callchain entry saved by the kernel.
+ */
+ skip_idx = arch_skip_callchain_idx(machine, thread, chain);
+
for (i = 0; i < chain_nr; i++) {
u64 ip;
struct addr_location al;
if (callchain_param.order == ORDER_CALLEE)
- ip = chain->ips[i];
+ j = i;
else
- ip = chain->ips[chain->nr - i - 1];
+ j = chain->nr - i - 1;
+
+#ifdef HAVE_SKIP_CALLCHAIN_IDX
+ if (j == skip_idx)
+ continue;
+#endif
+ ip = chain->ips[j];
if (ip >= PERF_CONTEXT_MAX) {
switch (ip) {
@@ -1420,3 +1528,68 @@ int __machine__synthesize_threads(struct machine *machine, struct perf_tool *too
/* command specified */
return 0;
}
+
+pid_t machine__get_current_tid(struct machine *machine, int cpu)
+{
+ if (cpu < 0 || cpu >= MAX_NR_CPUS || !machine->current_tid)
+ return -1;
+
+ return machine->current_tid[cpu];
+}
+
+int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
+ pid_t tid)
+{
+ struct thread *thread;
+
+ if (cpu < 0)
+ return -EINVAL;
+
+ if (!machine->current_tid) {
+ int i;
+
+ machine->current_tid = calloc(MAX_NR_CPUS, sizeof(pid_t));
+ if (!machine->current_tid)
+ return -ENOMEM;
+ for (i = 0; i < MAX_NR_CPUS; i++)
+ machine->current_tid[i] = -1;
+ }
+
+ if (cpu >= MAX_NR_CPUS) {
+ pr_err("Requested CPU %d too large. ", cpu);
+ pr_err("Consider raising MAX_NR_CPUS\n");
+ return -EINVAL;
+ }
+
+ machine->current_tid[cpu] = tid;
+
+ thread = machine__findnew_thread(machine, pid, tid);
+ if (!thread)
+ return -ENOMEM;
+
+ thread->cpu = cpu;
+
+ return 0;
+}
+
+int machine__get_kernel_start(struct machine *machine)
+{
+ struct map *map = machine__kernel_map(machine, MAP__FUNCTION);
+ int err = 0;
+
+ /*
+ * The only addresses above 2^63 are kernel addresses of a 64-bit
+ * kernel. Note that addresses are unsigned so that on a 32-bit system
+ * all addresses including kernel addresses are less than 2^32. In
+ * that case (32-bit system), if the kernel mapping is unknown, all
+ * addresses will be assumed to be in user space - see
+ * machine__kernel_ip().
+ */
+ machine->kernel_start = 1ULL << 63;
+ if (map) {
+ err = map__load(map, machine->symbol_filter);
+ if (map->start)
+ machine->kernel_start = map->start;
+ }
+ return err;
+}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index c8c74a119398..2b651a7f5d0d 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -4,6 +4,7 @@
#include <sys/types.h>
#include <linux/rbtree.h>
#include "map.h"
+#include "dso.h"
#include "event.h"
struct addr_location;
@@ -20,19 +21,25 @@ union perf_event;
extern const char *ref_reloc_sym_names[];
+struct vdso_info;
+
struct machine {
struct rb_node rb_node;
pid_t pid;
u16 id_hdr_size;
+ bool comm_exec;
char *root_dir;
struct rb_root threads;
struct list_head dead_threads;
struct thread *last_match;
- struct list_head user_dsos;
- struct list_head kernel_dsos;
+ struct vdso_info *vdso_info;
+ struct dsos user_dsos;
+ struct dsos kernel_dsos;
struct map_groups kmaps;
struct map *vmlinux_maps[MAP__NR_TYPES];
+ u64 kernel_start;
symbol_filter_t symbol_filter;
+ pid_t *current_tid;
};
static inline
@@ -41,8 +48,26 @@ struct map *machine__kernel_map(struct machine *machine, enum map_type type)
return machine->vmlinux_maps[type];
}
+int machine__get_kernel_start(struct machine *machine);
+
+static inline u64 machine__kernel_start(struct machine *machine)
+{
+ if (!machine->kernel_start)
+ machine__get_kernel_start(machine);
+ return machine->kernel_start;
+}
+
+static inline bool machine__kernel_ip(struct machine *machine, u64 ip)
+{
+ u64 kernel_start = machine__kernel_start(machine);
+
+ return ip >= kernel_start;
+}
+
struct thread *machine__find_thread(struct machine *machine, pid_t pid,
pid_t tid);
+struct comm *machine__thread_exec_comm(struct machine *machine,
+ struct thread *thread);
int machine__process_comm_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample);
@@ -84,6 +109,7 @@ char *machine__mmap_name(struct machine *machine, char *bf, size_t size);
void machines__set_symbol_filter(struct machines *machines,
symbol_filter_t symbol_filter);
+void machines__set_comm_exec(struct machines *machines, bool comm_exec);
struct machine *machine__new_host(void);
int machine__init(struct machine *machine, const char *root_dir, pid_t pid);
@@ -191,4 +217,8 @@ int machine__synthesize_threads(struct machine *machine, struct target *target,
perf_event__process, data_mmap);
}
+pid_t machine__get_current_tid(struct machine *machine, int cpu);
+int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
+ pid_t tid);
+
#endif /* __PERF_MACHINE_H */
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 25c571f4cba6..b7090596ac50 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -12,6 +12,8 @@
#include "vdso.h"
#include "build-id.h"
#include "util.h"
+#include "debug.h"
+#include "machine.h"
#include <linux/string.h>
const char *map_type__name[MAP__NR_TYPES] = {
@@ -29,6 +31,7 @@ static inline int is_anon_memory(const char *filename)
static inline int is_no_dso_memory(const char *filename)
{
return !strncmp(filename, "[stack", 6) ||
+ !strncmp(filename, "/SYSV",5) ||
!strcmp(filename, "[heap]");
}
@@ -136,10 +139,10 @@ void map__init(struct map *map, enum map_type type,
map->erange_warned = false;
}
-struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
+struct map *map__new(struct machine *machine, u64 start, u64 len,
u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
u64 ino_gen, u32 prot, u32 flags, char *filename,
- enum map_type type)
+ enum map_type type, struct thread *thread)
{
struct map *map = malloc(sizeof(*map));
@@ -172,9 +175,9 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
if (vdso) {
pgoff = 0;
- dso = vdso__dso_findnew(dsos__list);
+ dso = vdso__dso_findnew(machine, thread);
} else
- dso = __dsos__findnew(dsos__list, filename);
+ dso = __dsos__findnew(&machine->user_dsos, filename);
if (dso == NULL)
goto out_delete;
@@ -454,6 +457,20 @@ void map_groups__exit(struct map_groups *mg)
}
}
+bool map_groups__empty(struct map_groups *mg)
+{
+ int i;
+
+ for (i = 0; i < MAP__NR_TYPES; ++i) {
+ if (maps__first(&mg->maps[i]))
+ return false;
+ if (!list_empty(&mg->removed_maps[i]))
+ return false;
+ }
+
+ return true;
+}
+
struct map_groups *map_groups__new(void)
{
struct map_groups *mg = malloc(sizeof(*mg));
@@ -554,8 +571,8 @@ int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter)
return ams->sym ? 0 : -1;
}
-size_t __map_groups__fprintf_maps(struct map_groups *mg,
- enum map_type type, int verbose, FILE *fp)
+size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
+ FILE *fp)
{
size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
struct rb_node *nd;
@@ -573,17 +590,16 @@ size_t __map_groups__fprintf_maps(struct map_groups *mg,
return printed;
}
-size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp)
+static size_t map_groups__fprintf_maps(struct map_groups *mg, FILE *fp)
{
size_t printed = 0, i;
for (i = 0; i < MAP__NR_TYPES; ++i)
- printed += __map_groups__fprintf_maps(mg, i, verbose, fp);
+ printed += __map_groups__fprintf_maps(mg, i, fp);
return printed;
}
static size_t __map_groups__fprintf_removed_maps(struct map_groups *mg,
- enum map_type type,
- int verbose, FILE *fp)
+ enum map_type type, FILE *fp)
{
struct map *pos;
size_t printed = 0;
@@ -600,23 +616,23 @@ static size_t __map_groups__fprintf_removed_maps(struct map_groups *mg,
}
static size_t map_groups__fprintf_removed_maps(struct map_groups *mg,
- int verbose, FILE *fp)
+ FILE *fp)
{
size_t printed = 0, i;
for (i = 0; i < MAP__NR_TYPES; ++i)
- printed += __map_groups__fprintf_removed_maps(mg, i, verbose, fp);
+ printed += __map_groups__fprintf_removed_maps(mg, i, fp);
return printed;
}
-size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp)
+size_t map_groups__fprintf(struct map_groups *mg, FILE *fp)
{
- size_t printed = map_groups__fprintf_maps(mg, verbose, fp);
+ size_t printed = map_groups__fprintf_maps(mg, fp);
printed += fprintf(fp, "Removed maps:\n");
- return printed + map_groups__fprintf_removed_maps(mg, verbose, fp);
+ return printed + map_groups__fprintf_removed_maps(mg, fp);
}
int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
- int verbose, FILE *fp)
+ FILE *fp)
{
struct rb_root *root = &mg->maps[map->type];
struct rb_node *next = rb_first(root);
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 7758c72522ef..2f83954af050 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -66,6 +66,7 @@ struct map_groups {
struct map_groups *map_groups__new(void);
void map_groups__delete(struct map_groups *mg);
+bool map_groups__empty(struct map_groups *mg);
static inline struct map_groups *map_groups__get(struct map_groups *mg)
{
@@ -103,6 +104,7 @@ u64 map__rip_2objdump(struct map *map, u64 rip);
u64 map__objdump_2mem(struct map *map, u64 ip);
struct symbol;
+struct thread;
/* map__for_each_symbol - iterate over the symbols in the given map
*
@@ -118,10 +120,10 @@ typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
void map__init(struct map *map, enum map_type type,
u64 start, u64 end, u64 pgoff, struct dso *dso);
-struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
+struct map *map__new(struct machine *machine, u64 start, u64 len,
u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
u64 ino_gen, u32 prot, u32 flags,
- char *filename, enum map_type type);
+ char *filename, enum map_type type, struct thread *thread);
struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
void map__delete(struct map *map);
struct map *map__clone(struct map *map);
@@ -141,8 +143,8 @@ void map__fixup_end(struct map *map);
void map__reloc_vmlinux(struct map *map);
-size_t __map_groups__fprintf_maps(struct map_groups *mg,
- enum map_type type, int verbose, FILE *fp);
+size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
+ FILE *fp);
void maps__insert(struct rb_root *maps, struct map *map);
void maps__remove(struct rb_root *maps, struct map *map);
struct map *maps__find(struct rb_root *maps, u64 addr);
@@ -152,8 +154,7 @@ void map_groups__init(struct map_groups *mg);
void map_groups__exit(struct map_groups *mg);
int map_groups__clone(struct map_groups *mg,
struct map_groups *parent, enum map_type type);
-size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp);
-size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp);
+size_t map_groups__fprintf(struct map_groups *mg, FILE *fp);
int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name,
u64 addr);
@@ -210,7 +211,7 @@ struct symbol *map_groups__find_function_by_name(struct map_groups *mg,
}
int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
- int verbose, FILE *fp);
+ FILE *fp);
struct map *map_groups__find_by_name(struct map_groups *mg,
enum map_type type, const char *name);
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
new file mode 100644
index 000000000000..706ce1a66169
--- /dev/null
+++ b/tools/perf/util/ordered-events.c
@@ -0,0 +1,245 @@
+#include <linux/list.h>
+#include <linux/compiler.h>
+#include "ordered-events.h"
+#include "evlist.h"
+#include "session.h"
+#include "asm/bug.h"
+#include "debug.h"
+
+#define pr_N(n, fmt, ...) \
+ eprintf(n, debug_ordered_events, fmt, ##__VA_ARGS__)
+
+#define pr(fmt, ...) pr_N(1, pr_fmt(fmt), ##__VA_ARGS__)
+
+static void queue_event(struct ordered_events *oe, struct ordered_event *new)
+{
+ struct ordered_event *last = oe->last;
+ u64 timestamp = new->timestamp;
+ struct list_head *p;
+
+ ++oe->nr_events;
+ oe->last = new;
+
+ pr_oe_time2(timestamp, "queue_event nr_events %u\n", oe->nr_events);
+
+ if (!last) {
+ list_add(&new->list, &oe->events);
+ oe->max_timestamp = timestamp;
+ return;
+ }
+
+ /*
+ * last event might point to some random place in the list as it's
+ * the last queued event. We expect that the new event is close to
+ * this.
+ */
+ if (last->timestamp <= timestamp) {
+ while (last->timestamp <= timestamp) {
+ p = last->list.next;
+ if (p == &oe->events) {
+ list_add_tail(&new->list, &oe->events);
+ oe->max_timestamp = timestamp;
+ return;
+ }
+ last = list_entry(p, struct ordered_event, list);
+ }
+ list_add_tail(&new->list, &last->list);
+ } else {
+ while (last->timestamp > timestamp) {
+ p = last->list.prev;
+ if (p == &oe->events) {
+ list_add(&new->list, &oe->events);
+ return;
+ }
+ last = list_entry(p, struct ordered_event, list);
+ }
+ list_add(&new->list, &last->list);
+ }
+}
+
+#define MAX_SAMPLE_BUFFER (64 * 1024 / sizeof(struct ordered_event))
+static struct ordered_event *alloc_event(struct ordered_events *oe)
+{
+ struct list_head *cache = &oe->cache;
+ struct ordered_event *new = NULL;
+
+ if (!list_empty(cache)) {
+ new = list_entry(cache->next, struct ordered_event, list);
+ list_del(&new->list);
+ } else if (oe->buffer) {
+ new = oe->buffer + oe->buffer_idx;
+ if (++oe->buffer_idx == MAX_SAMPLE_BUFFER)
+ oe->buffer = NULL;
+ } else if (oe->cur_alloc_size < oe->max_alloc_size) {
+ size_t size = MAX_SAMPLE_BUFFER * sizeof(*new);
+
+ oe->buffer = malloc(size);
+ if (!oe->buffer)
+ return NULL;
+
+ pr("alloc size %" PRIu64 "B (+%zu), max %" PRIu64 "B\n",
+ oe->cur_alloc_size, size, oe->max_alloc_size);
+
+ oe->cur_alloc_size += size;
+ list_add(&oe->buffer->list, &oe->to_free);
+
+ /* First entry is abused to maintain the to_free list. */
+ oe->buffer_idx = 2;
+ new = oe->buffer + 1;
+ } else {
+ pr("allocation limit reached %" PRIu64 "B\n", oe->max_alloc_size);
+ }
+
+ return new;
+}
+
+struct ordered_event *
+ordered_events__new(struct ordered_events *oe, u64 timestamp)
+{
+ struct ordered_event *new;
+
+ new = alloc_event(oe);
+ if (new) {
+ new->timestamp = timestamp;
+ queue_event(oe, new);
+ }
+
+ return new;
+}
+
+void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event)
+{
+ list_move(&event->list, &oe->cache);
+ oe->nr_events--;
+}
+
+static int __ordered_events__flush(struct perf_session *s,
+ struct perf_tool *tool)
+{
+ struct ordered_events *oe = &s->ordered_events;
+ struct list_head *head = &oe->events;
+ struct ordered_event *tmp, *iter;
+ struct perf_sample sample;
+ u64 limit = oe->next_flush;
+ u64 last_ts = oe->last ? oe->last->timestamp : 0ULL;
+ bool show_progress = limit == ULLONG_MAX;
+ struct ui_progress prog;
+ int ret;
+
+ if (!tool->ordered_events || !limit)
+ return 0;
+
+ if (show_progress)
+ ui_progress__init(&prog, oe->nr_events, "Processing time ordered events...");
+
+ list_for_each_entry_safe(iter, tmp, head, list) {
+ if (session_done())
+ return 0;
+
+ if (iter->timestamp > limit)
+ break;
+
+ ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample);
+ if (ret)
+ pr_err("Can't parse sample, err = %d\n", ret);
+ else {
+ ret = perf_session__deliver_event(s, iter->event, &sample, tool,
+ iter->file_offset);
+ if (ret)
+ return ret;
+ }
+
+ ordered_events__delete(oe, iter);
+ oe->last_flush = iter->timestamp;
+
+ if (show_progress)
+ ui_progress__update(&prog, 1);
+ }
+
+ if (list_empty(head))
+ oe->last = NULL;
+ else if (last_ts <= limit)
+ oe->last = list_entry(head->prev, struct ordered_event, list);
+
+ return 0;
+}
+
+int ordered_events__flush(struct perf_session *s, struct perf_tool *tool,
+ enum oe_flush how)
+{
+ struct ordered_events *oe = &s->ordered_events;
+ static const char * const str[] = {
+ "NONE",
+ "FINAL",
+ "ROUND",
+ "HALF ",
+ };
+ int err;
+
+ switch (how) {
+ case OE_FLUSH__FINAL:
+ oe->next_flush = ULLONG_MAX;
+ break;
+
+ case OE_FLUSH__HALF:
+ {
+ struct ordered_event *first, *last;
+ struct list_head *head = &oe->events;
+
+ first = list_entry(head->next, struct ordered_event, list);
+ last = oe->last;
+
+ /* Warn if we are called before any event got allocated. */
+ if (WARN_ONCE(!last || list_empty(head), "empty queue"))
+ return 0;
+
+ oe->next_flush = first->timestamp;
+ oe->next_flush += (last->timestamp - first->timestamp) / 2;
+ break;
+ }
+
+ case OE_FLUSH__ROUND:
+ case OE_FLUSH__NONE:
+ default:
+ break;
+ };
+
+ pr_oe_time(oe->next_flush, "next_flush - ordered_events__flush PRE %s, nr_events %u\n",
+ str[how], oe->nr_events);
+ pr_oe_time(oe->max_timestamp, "max_timestamp\n");
+
+ err = __ordered_events__flush(s, tool);
+
+ if (!err) {
+ if (how == OE_FLUSH__ROUND)
+ oe->next_flush = oe->max_timestamp;
+
+ oe->last_flush_type = how;
+ }
+
+ pr_oe_time(oe->next_flush, "next_flush - ordered_events__flush POST %s, nr_events %u\n",
+ str[how], oe->nr_events);
+ pr_oe_time(oe->last_flush, "last_flush\n");
+
+ return err;
+}
+
+void ordered_events__init(struct ordered_events *oe)
+{
+ INIT_LIST_HEAD(&oe->events);
+ INIT_LIST_HEAD(&oe->cache);
+ INIT_LIST_HEAD(&oe->to_free);
+ oe->max_alloc_size = (u64) -1;
+ oe->cur_alloc_size = 0;
+}
+
+void ordered_events__free(struct ordered_events *oe)
+{
+ while (!list_empty(&oe->to_free)) {
+ struct ordered_event *event;
+
+ event = list_entry(oe->to_free.next, struct ordered_event, list);
+ list_del(&event->list);
+ free(event);
+ }
+}
diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h
new file mode 100644
index 000000000000..3b2f20542a01
--- /dev/null
+++ b/tools/perf/util/ordered-events.h
@@ -0,0 +1,51 @@
+#ifndef __ORDERED_EVENTS_H
+#define __ORDERED_EVENTS_H
+
+#include <linux/types.h>
+#include "tool.h"
+
+struct perf_session;
+
+struct ordered_event {
+ u64 timestamp;
+ u64 file_offset;
+ union perf_event *event;
+ struct list_head list;
+};
+
+enum oe_flush {
+ OE_FLUSH__NONE,
+ OE_FLUSH__FINAL,
+ OE_FLUSH__ROUND,
+ OE_FLUSH__HALF,
+};
+
+struct ordered_events {
+ u64 last_flush;
+ u64 next_flush;
+ u64 max_timestamp;
+ u64 max_alloc_size;
+ u64 cur_alloc_size;
+ struct list_head events;
+ struct list_head cache;
+ struct list_head to_free;
+ struct ordered_event *buffer;
+ struct ordered_event *last;
+ int buffer_idx;
+ unsigned int nr_events;
+ enum oe_flush last_flush_type;
+};
+
+struct ordered_event *ordered_events__new(struct ordered_events *oe, u64 timestamp);
+void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event);
+int ordered_events__flush(struct perf_session *s, struct perf_tool *tool,
+ enum oe_flush how);
+void ordered_events__init(struct ordered_events *oe);
+void ordered_events__free(struct ordered_events *oe);
+
+static inline
+void ordered_events__set_alloc_size(struct ordered_events *oe, u64 size)
+{
+ oe->max_alloc_size = size;
+}
+#endif /* __ORDERED_EVENTS_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 1e15df10a88c..d76aa30cb1fb 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -10,6 +10,7 @@
#include "symbol.h"
#include "cache.h"
#include "header.h"
+#include "debug.h"
#include <api/fs/debugfs.h>
#include "parse-events-bison.h"
#define YY_EXTRA_TYPE int
@@ -633,18 +634,28 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
char *name, struct list_head *head_config)
{
struct perf_event_attr attr;
+ struct perf_pmu_info info;
struct perf_pmu *pmu;
struct perf_evsel *evsel;
- const char *unit;
- double scale;
pmu = perf_pmu__find(name);
if (!pmu)
return -EINVAL;
- memset(&attr, 0, sizeof(attr));
+ if (pmu->default_config) {
+ memcpy(&attr, pmu->default_config,
+ sizeof(struct perf_event_attr));
+ } else {
+ memset(&attr, 0, sizeof(attr));
+ }
+
+ if (!head_config) {
+ attr.type = pmu->type;
+ evsel = __add_event(list, idx, &attr, NULL, pmu->cpus);
+ return evsel ? 0 : -ENOMEM;
+ }
- if (perf_pmu__check_alias(pmu, head_config, &unit, &scale))
+ if (perf_pmu__check_alias(pmu, head_config, &info))
return -EINVAL;
/*
@@ -659,8 +670,8 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
evsel = __add_event(list, idx, &attr, pmu_event_name(head_config),
pmu->cpus);
if (evsel) {
- evsel->unit = unit;
- evsel->scale = scale;
+ evsel->unit = info.unit;
+ evsel->scale = info.scale;
}
return evsel ? 0 : -ENOMEM;
@@ -973,7 +984,7 @@ int parse_filter(const struct option *opt, const char *str,
if (last == NULL || last->attr.type != PERF_TYPE_TRACEPOINT) {
fprintf(stderr,
- "-F option should follow a -e tracepoint option\n");
+ "--filter option should follow a -e tracepoint option\n");
return -1;
}
@@ -1006,9 +1017,11 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
char evt_path[MAXPATHLEN];
char dir_path[MAXPATHLEN];
+ char sbuf[STRERR_BUFSIZE];
if (debugfs_valid_mountpoint(tracing_events_path)) {
- printf(" [ Tracepoints not available: %s ]\n", strerror(errno));
+ printf(" [ Tracepoints not available: %s ]\n",
+ strerror_r(errno, sbuf, sizeof(sbuf)));
return;
}
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 0bc87ba46bf3..55fab6ad609a 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -210,6 +210,16 @@ PE_NAME '/' event_config '/'
parse_events__free_terms($3);
$$ = list;
}
+|
+PE_NAME '/' '/'
+{
+ struct parse_events_evlist *data = _data;
+ struct list_head *list;
+
+ ALLOC_LIST(list);
+ ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, NULL));
+ $$ = list;
+}
value_sym:
PE_VALUE_SYM_HW
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index d8dac8ac5f37..b59ba858e73d 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -98,6 +98,7 @@ struct option {
parse_opt_cb *callback;
intptr_t defval;
bool *set;
+ void *data;
};
#define check_vtype(v, type) ( BUILD_BUG_ON_ZERO(!__builtin_types_compatible_p(typeof(v), type)) + v )
@@ -131,6 +132,10 @@ struct option {
{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l),\
.value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\
.flags = PARSE_OPT_LASTARG_DEFAULT | PARSE_OPT_NOARG}
+#define OPT_CALLBACK_OPTARG(s, l, v, d, a, h, f) \
+ { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), \
+ .value = (v), (a), .help = (h), .callback = (f), \
+ .flags = PARSE_OPT_OPTARG, .data = (d) }
/* parse_options() will filter out the processed options and leave the
* non-option argments in argv[].
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 7a811eb61f75..93a41ca96b8e 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -2,6 +2,8 @@
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
+#include <stdbool.h>
+#include <stdarg.h>
#include <dirent.h>
#include <api/fs/fs.h>
#include <locale.h>
@@ -14,8 +16,8 @@
struct perf_pmu_alias {
char *name;
- struct list_head terms;
- struct list_head list;
+ struct list_head terms; /* HEAD struct parse_events_term -> list */
+ struct list_head list; /* ELEM */
char unit[UNIT_MAX_LEN+1];
double scale;
};
@@ -208,6 +210,19 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
return 0;
}
+static inline bool pmu_alias_info_file(char *name)
+{
+ size_t len;
+
+ len = strlen(name);
+ if (len > 5 && !strcmp(name + len - 5, ".unit"))
+ return true;
+ if (len > 6 && !strcmp(name + len - 6, ".scale"))
+ return true;
+
+ return false;
+}
+
/*
* Process all the sysfs attributes located under the directory
* specified in 'dir' parameter.
@@ -216,7 +231,6 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
{
struct dirent *evt_ent;
DIR *event_dir;
- size_t len;
int ret = 0;
event_dir = opendir(dir);
@@ -232,13 +246,9 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
continue;
/*
- * skip .unit and .scale info files
- * parsed in perf_pmu__new_alias()
+ * skip info files parsed in perf_pmu__new_alias()
*/
- len = strlen(name);
- if (len > 5 && !strcmp(name + len - 5, ".unit"))
- continue;
- if (len > 6 && !strcmp(name + len - 6, ".scale"))
+ if (pmu_alias_info_file(name))
continue;
snprintf(path, PATH_MAX, "%s/%s", dir, name);
@@ -387,6 +397,12 @@ static struct cpu_map *pmu_cpumask(const char *name)
return cpus;
}
+struct perf_event_attr *__attribute__((weak))
+perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
+{
+ return NULL;
+}
+
static struct perf_pmu *pmu_lookup(const char *name)
{
struct perf_pmu *pmu;
@@ -421,6 +437,9 @@ static struct perf_pmu *pmu_lookup(const char *name)
pmu->name = strdup(name);
pmu->type = type;
list_add_tail(&pmu->list, &pmus);
+
+ pmu->default_config = perf_pmu__get_default_config(pmu);
+
return pmu;
}
@@ -479,28 +498,24 @@ pmu_find_format(struct list_head *formats, char *name)
}
/*
- * Returns value based on the format definition (format parameter)
+ * Sets value based on the format definition (format parameter)
* and unformated value (value parameter).
- *
- * TODO maybe optimize a little ;)
*/
-static __u64 pmu_format_value(unsigned long *format, __u64 value)
+static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v,
+ bool zero)
{
unsigned long fbit, vbit;
- __u64 v = 0;
for (fbit = 0, vbit = 0; fbit < PERF_PMU_FORMAT_BITS; fbit++) {
if (!test_bit(fbit, format))
continue;
- if (!(value & (1llu << vbit++)))
- continue;
-
- v |= (1llu << fbit);
+ if (value & (1llu << vbit++))
+ *v |= (1llu << fbit);
+ else if (zero)
+ *v &= ~(1llu << fbit);
}
-
- return v;
}
/*
@@ -509,7 +524,8 @@ static __u64 pmu_format_value(unsigned long *format, __u64 value)
*/
static int pmu_config_term(struct list_head *formats,
struct perf_event_attr *attr,
- struct parse_events_term *term)
+ struct parse_events_term *term,
+ bool zero)
{
struct perf_pmu_format *format;
__u64 *vp;
@@ -548,18 +564,19 @@ static int pmu_config_term(struct list_head *formats,
* non-hardcoded terms, here's the place to translate
* them into value.
*/
- *vp |= pmu_format_value(format->bits, term->val.num);
+ pmu_format_value(format->bits, term->val.num, vp, zero);
return 0;
}
int perf_pmu__config_terms(struct list_head *formats,
struct perf_event_attr *attr,
- struct list_head *head_terms)
+ struct list_head *head_terms,
+ bool zero)
{
struct parse_events_term *term;
list_for_each_entry(term, head_terms, list)
- if (pmu_config_term(formats, attr, term))
+ if (pmu_config_term(formats, attr, term, zero))
return -EINVAL;
return 0;
@@ -573,8 +590,10 @@ int perf_pmu__config_terms(struct list_head *formats,
int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
struct list_head *head_terms)
{
+ bool zero = !!pmu->default_config;
+
attr->type = pmu->type;
- return perf_pmu__config_terms(&pmu->format, attr, head_terms);
+ return perf_pmu__config_terms(&pmu->format, attr, head_terms, zero);
}
static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
@@ -634,7 +653,7 @@ static int check_unit_scale(struct perf_pmu_alias *alias,
* defined for the alias
*/
int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
- const char **unit, double *scale)
+ struct perf_pmu_info *info)
{
struct parse_events_term *term, *h;
struct perf_pmu_alias *alias;
@@ -644,8 +663,8 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
* Mark unit and scale as not set
* (different from default values, see below)
*/
- *unit = NULL;
- *scale = 0.0;
+ info->unit = NULL;
+ info->scale = 0.0;
list_for_each_entry_safe(term, h, head_terms, list) {
alias = pmu_find_alias(pmu, term);
@@ -655,7 +674,7 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
if (ret)
return ret;
- ret = check_unit_scale(alias, unit, scale);
+ ret = check_unit_scale(alias, &info->unit, &info->scale);
if (ret)
return ret;
@@ -668,11 +687,11 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
* set defaults as for evsel
* unit cannot left to NULL
*/
- if (*unit == NULL)
- *unit = "";
+ if (info->unit == NULL)
+ info->unit = "";
- if (*scale == 0.0)
- *scale = 1.0;
+ if (info->scale == 0.0)
+ info->scale = 1.0;
return 0;
}
@@ -794,3 +813,39 @@ bool pmu_have_event(const char *pname, const char *name)
}
return false;
}
+
+static FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name)
+{
+ struct stat st;
+ char path[PATH_MAX];
+ const char *sysfs;
+
+ sysfs = sysfs__mountpoint();
+ if (!sysfs)
+ return NULL;
+
+ snprintf(path, PATH_MAX,
+ "%s" EVENT_SOURCE_DEVICE_PATH "%s/%s", sysfs, pmu->name, name);
+
+ if (stat(path, &st) < 0)
+ return NULL;
+
+ return fopen(path, "r");
+}
+
+int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,
+ ...)
+{
+ va_list args;
+ FILE *file;
+ int ret = EOF;
+
+ va_start(args, fmt);
+ file = perf_pmu__open_file(pmu, name);
+ if (file) {
+ ret = vfscanf(file, fmt, args);
+ fclose(file);
+ }
+ va_end(args);
+ return ret;
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index c14a543ce1f3..fe90a012c003 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -13,13 +13,21 @@ enum {
#define PERF_PMU_FORMAT_BITS 64
+struct perf_event_attr;
+
struct perf_pmu {
char *name;
__u32 type;
+ struct perf_event_attr *default_config;
struct cpu_map *cpus;
- struct list_head format;
- struct list_head aliases;
- struct list_head list;
+ struct list_head format; /* HEAD struct perf_pmu_format -> list */
+ struct list_head aliases; /* HEAD struct perf_pmu_alias -> list */
+ struct list_head list; /* ELEM */
+};
+
+struct perf_pmu_info {
+ const char *unit;
+ double scale;
};
struct perf_pmu *perf_pmu__find(const char *name);
@@ -27,9 +35,10 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
struct list_head *head_terms);
int perf_pmu__config_terms(struct list_head *formats,
struct perf_event_attr *attr,
- struct list_head *head_terms);
+ struct list_head *head_terms,
+ bool zero);
int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
- const char **unit, double *scale);
+ struct perf_pmu_info *info);
struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
struct list_head *head_terms);
int perf_pmu_wrap(void);
@@ -45,5 +54,11 @@ struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
void print_pmu_events(const char *event_glob, bool name_only);
bool pmu_have_event(const char *pname, const char *name);
+int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,
+ ...) __attribute__((format(scanf, 3, 4)));
+
int perf_pmu__test(void);
+
+struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu);
+
#endif /* __PMU_H */
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 9a0a1839a377..c150ca4343eb 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -79,7 +79,7 @@ static int init_symbol_maps(bool user_only)
int ret;
symbol_conf.sort_by_name = true;
- ret = symbol__init();
+ ret = symbol__init(NULL);
if (ret < 0) {
pr_debug("Failed to init symbol map.\n");
goto out;
@@ -184,7 +184,8 @@ static struct dso *kernel_get_module_dso(const char *module)
const char *vmlinux_name;
if (module) {
- list_for_each_entry(dso, &host_machine->kernel_dsos, node) {
+ list_for_each_entry(dso, &host_machine->kernel_dsos.head,
+ node) {
if (strncmp(dso->short_name + 1, module,
dso->short_name_len - 2) == 0)
goto found;
@@ -258,21 +259,33 @@ static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
#ifdef HAVE_DWARF_SUPPORT
/* Open new debuginfo of given module */
-static struct debuginfo *open_debuginfo(const char *module)
+static struct debuginfo *open_debuginfo(const char *module, bool silent)
{
const char *path = module;
+ struct debuginfo *ret;
if (!module || !strchr(module, '/')) {
path = kernel_get_module_path(module);
if (!path) {
- pr_err("Failed to find path of %s module.\n",
- module ?: "kernel");
+ if (!silent)
+ pr_err("Failed to find path of %s module.\n",
+ module ?: "kernel");
return NULL;
}
}
- return debuginfo__new(path);
+ ret = debuginfo__new(path);
+ if (!ret && !silent) {
+ pr_warning("The %s file has no debug information.\n", path);
+ if (!module || !strtailcmp(path, ".ko"))
+ pr_warning("Rebuild with CONFIG_DEBUG_INFO=y, ");
+ else
+ pr_warning("Rebuild with -g, ");
+ pr_warning("or install an appropriate debuginfo package.\n");
+ }
+ return ret;
}
+
static int get_text_start_address(const char *exec, unsigned long *address)
{
Elf *elf;
@@ -333,15 +346,13 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp,
pr_debug("try to find information at %" PRIx64 " in %s\n", addr,
tp->module ? : "kernel");
- dinfo = open_debuginfo(tp->module);
+ dinfo = open_debuginfo(tp->module, verbose == 0);
if (dinfo) {
ret = debuginfo__find_probe_point(dinfo,
(unsigned long)addr, pp);
debuginfo__delete(dinfo);
- } else {
- pr_debug("Failed to open debuginfo at 0x%" PRIx64 "\n", addr);
+ } else
ret = -ENOENT;
- }
if (ret > 0) {
pp->retprobe = tp->retprobe;
@@ -457,13 +468,11 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
struct debuginfo *dinfo;
int ntevs, ret = 0;
- dinfo = open_debuginfo(target);
+ dinfo = open_debuginfo(target, !need_dwarf);
if (!dinfo) {
- if (need_dwarf) {
- pr_warning("Failed to open debuginfo file.\n");
+ if (need_dwarf)
return -ENOENT;
- }
pr_debug("Could not open debuginfo. Try to use symbols.\n");
return 0;
}
@@ -565,7 +574,7 @@ static int get_real_path(const char *raw_path, const char *comp_dir,
static int __show_one_line(FILE *fp, int l, bool skip, bool show_num)
{
- char buf[LINEBUF_SIZE];
+ char buf[LINEBUF_SIZE], sbuf[STRERR_BUFSIZE];
const char *color = show_num ? "" : PERF_COLOR_BLUE;
const char *prefix = NULL;
@@ -585,7 +594,8 @@ static int __show_one_line(FILE *fp, int l, bool skip, bool show_num)
return 1;
error:
if (ferror(fp)) {
- pr_warning("File read error: %s\n", strerror(errno));
+ pr_warning("File read error: %s\n",
+ strerror_r(errno, sbuf, sizeof(sbuf)));
return -1;
}
return 0;
@@ -618,13 +628,12 @@ static int __show_line_range(struct line_range *lr, const char *module)
FILE *fp;
int ret;
char *tmp;
+ char sbuf[STRERR_BUFSIZE];
/* Search a line range */
- dinfo = open_debuginfo(module);
- if (!dinfo) {
- pr_warning("Failed to open debuginfo file.\n");
+ dinfo = open_debuginfo(module, false);
+ if (!dinfo)
return -ENOENT;
- }
ret = debuginfo__find_line_range(dinfo, lr);
debuginfo__delete(dinfo);
@@ -656,7 +665,7 @@ static int __show_line_range(struct line_range *lr, const char *module)
fp = fopen(lr->path, "r");
if (fp == NULL) {
pr_warning("Failed to open %s: %s\n", lr->path,
- strerror(errno));
+ strerror_r(errno, sbuf, sizeof(sbuf)));
return -errno;
}
/* Skip to starting line number */
@@ -689,11 +698,11 @@ end:
return ret;
}
-int show_line_range(struct line_range *lr, const char *module)
+int show_line_range(struct line_range *lr, const char *module, bool user)
{
int ret;
- ret = init_symbol_maps(false);
+ ret = init_symbol_maps(user);
if (ret < 0)
return ret;
ret = __show_line_range(lr, module);
@@ -768,13 +777,12 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
int i, ret = 0;
struct debuginfo *dinfo;
- ret = init_symbol_maps(false);
+ ret = init_symbol_maps(pevs->uprobes);
if (ret < 0)
return ret;
- dinfo = open_debuginfo(module);
+ dinfo = open_debuginfo(module, false);
if (!dinfo) {
- pr_warning("Failed to open debuginfo file.\n");
ret = -ENOENT;
goto out;
}
@@ -815,7 +823,8 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
}
int show_line_range(struct line_range *lr __maybe_unused,
- const char *module __maybe_unused)
+ const char *module __maybe_unused,
+ bool user __maybe_unused)
{
pr_warning("Debuginfo-analysis is not supported.\n");
return -ENOSYS;
@@ -1405,8 +1414,7 @@ int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len)
return tmp - buf;
error:
- pr_debug("Failed to synthesize perf probe argument: %s\n",
- strerror(-ret));
+ pr_debug("Failed to synthesize perf probe argument: %d\n", ret);
return ret;
}
@@ -1455,8 +1463,7 @@ static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
return buf;
error:
- pr_debug("Failed to synthesize perf probe point: %s\n",
- strerror(-ret));
+ pr_debug("Failed to synthesize perf probe point: %d\n", ret);
free(buf);
return NULL;
}
@@ -1780,10 +1787,11 @@ static void clear_probe_trace_event(struct probe_trace_event *tev)
memset(tev, 0, sizeof(*tev));
}
-static void print_warn_msg(const char *file, bool is_kprobe)
+static void print_open_warning(int err, bool is_kprobe)
{
+ char sbuf[STRERR_BUFSIZE];
- if (errno == ENOENT) {
+ if (err == -ENOENT) {
const char *config;
if (!is_kprobe)
@@ -1791,25 +1799,43 @@ static void print_warn_msg(const char *file, bool is_kprobe)
else
config = "CONFIG_KPROBE_EVENTS";
- pr_warning("%s file does not exist - please rebuild kernel"
- " with %s.\n", file, config);
- } else
- pr_warning("Failed to open %s file: %s\n", file,
- strerror(errno));
+ pr_warning("%cprobe_events file does not exist"
+ " - please rebuild kernel with %s.\n",
+ is_kprobe ? 'k' : 'u', config);
+ } else if (err == -ENOTSUP)
+ pr_warning("Debugfs is not mounted.\n");
+ else
+ pr_warning("Failed to open %cprobe_events: %s\n",
+ is_kprobe ? 'k' : 'u',
+ strerror_r(-err, sbuf, sizeof(sbuf)));
+}
+
+static void print_both_open_warning(int kerr, int uerr)
+{
+ /* Both kprobes and uprobes are disabled, warn it. */
+ if (kerr == -ENOTSUP && uerr == -ENOTSUP)
+ pr_warning("Debugfs is not mounted.\n");
+ else if (kerr == -ENOENT && uerr == -ENOENT)
+ pr_warning("Please rebuild kernel with CONFIG_KPROBE_EVENTS "
+ "or/and CONFIG_UPROBE_EVENTS.\n");
+ else {
+ char sbuf[STRERR_BUFSIZE];
+ pr_warning("Failed to open kprobe events: %s.\n",
+ strerror_r(-kerr, sbuf, sizeof(sbuf)));
+ pr_warning("Failed to open uprobe events: %s.\n",
+ strerror_r(-uerr, sbuf, sizeof(sbuf)));
+ }
}
-static int open_probe_events(const char *trace_file, bool readwrite,
- bool is_kprobe)
+static int open_probe_events(const char *trace_file, bool readwrite)
{
char buf[PATH_MAX];
const char *__debugfs;
int ret;
__debugfs = debugfs_find_mountpoint();
- if (__debugfs == NULL) {
- pr_warning("Debugfs is not mounted.\n");
- return -ENOENT;
- }
+ if (__debugfs == NULL)
+ return -ENOTSUP;
ret = e_snprintf(buf, PATH_MAX, "%s/%s", __debugfs, trace_file);
if (ret >= 0) {
@@ -1820,19 +1846,19 @@ static int open_probe_events(const char *trace_file, bool readwrite,
ret = open(buf, O_RDONLY, 0);
if (ret < 0)
- print_warn_msg(buf, is_kprobe);
+ ret = -errno;
}
return ret;
}
static int open_kprobe_events(bool readwrite)
{
- return open_probe_events("tracing/kprobe_events", readwrite, true);
+ return open_probe_events("tracing/kprobe_events", readwrite);
}
static int open_uprobe_events(bool readwrite)
{
- return open_probe_events("tracing/uprobe_events", readwrite, false);
+ return open_probe_events("tracing/uprobe_events", readwrite);
}
/* Get raw string list of current kprobe_events or uprobe_events */
@@ -1857,7 +1883,7 @@ static struct strlist *get_probe_trace_command_rawlist(int fd)
p[idx] = '\0';
ret = strlist__add(sl, buf);
if (ret < 0) {
- pr_debug("strlist__add failed: %s\n", strerror(-ret));
+ pr_debug("strlist__add failed (%d)\n", ret);
strlist__delete(sl);
return NULL;
}
@@ -1916,7 +1942,7 @@ static int __show_perf_probe_events(int fd, bool is_kprobe)
rawlist = get_probe_trace_command_rawlist(fd);
if (!rawlist)
- return -ENOENT;
+ return -ENOMEM;
strlist__for_each(ent, rawlist) {
ret = parse_probe_trace_command(ent->s, &tev);
@@ -1940,27 +1966,34 @@ static int __show_perf_probe_events(int fd, bool is_kprobe)
/* List up current perf-probe events */
int show_perf_probe_events(void)
{
- int fd, ret;
+ int kp_fd, up_fd, ret;
setup_pager();
- fd = open_kprobe_events(false);
-
- if (fd < 0)
- return fd;
ret = init_symbol_maps(false);
if (ret < 0)
return ret;
- ret = __show_perf_probe_events(fd, true);
- close(fd);
+ kp_fd = open_kprobe_events(false);
+ if (kp_fd >= 0) {
+ ret = __show_perf_probe_events(kp_fd, true);
+ close(kp_fd);
+ if (ret < 0)
+ goto out;
+ }
- fd = open_uprobe_events(false);
- if (fd >= 0) {
- ret = __show_perf_probe_events(fd, false);
- close(fd);
+ up_fd = open_uprobe_events(false);
+ if (kp_fd < 0 && up_fd < 0) {
+ print_both_open_warning(kp_fd, up_fd);
+ ret = kp_fd;
+ goto out;
}
+ if (up_fd >= 0) {
+ ret = __show_perf_probe_events(up_fd, false);
+ close(up_fd);
+ }
+out:
exit_symbol_maps();
return ret;
}
@@ -1976,6 +2009,8 @@ static struct strlist *get_probe_trace_event_names(int fd, bool include_group)
memset(&tev, 0, sizeof(tev));
rawlist = get_probe_trace_command_rawlist(fd);
+ if (!rawlist)
+ return NULL;
sl = strlist__new(true, NULL);
strlist__for_each(ent, rawlist) {
ret = parse_probe_trace_command(ent->s, &tev);
@@ -2005,6 +2040,7 @@ static int write_probe_trace_event(int fd, struct probe_trace_event *tev)
{
int ret = 0;
char *buf = synthesize_probe_trace_command(tev);
+ char sbuf[STRERR_BUFSIZE];
if (!buf) {
pr_debug("Failed to synthesize probe trace event.\n");
@@ -2016,7 +2052,7 @@ static int write_probe_trace_event(int fd, struct probe_trace_event *tev)
ret = write(fd, buf, strlen(buf));
if (ret <= 0)
pr_warning("Failed to write event: %s\n",
- strerror(errno));
+ strerror_r(errno, sbuf, sizeof(sbuf)));
}
free(buf);
return ret;
@@ -2030,7 +2066,7 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
/* Try no suffix */
ret = e_snprintf(buf, len, "%s", base);
if (ret < 0) {
- pr_debug("snprintf() failed: %s\n", strerror(-ret));
+ pr_debug("snprintf() failed: %d\n", ret);
return ret;
}
if (!strlist__has_entry(namelist, buf))
@@ -2046,7 +2082,7 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
for (i = 1; i < MAX_EVENT_INDEX; i++) {
ret = e_snprintf(buf, len, "%s_%d", base, i);
if (ret < 0) {
- pr_debug("snprintf() failed: %s\n", strerror(-ret));
+ pr_debug("snprintf() failed: %d\n", ret);
return ret;
}
if (!strlist__has_entry(namelist, buf))
@@ -2075,8 +2111,11 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
else
fd = open_kprobe_events(true);
- if (fd < 0)
+ if (fd < 0) {
+ print_open_warning(fd, !pev->uprobes);
return fd;
+ }
+
/* Get current event names */
namelist = get_probe_trace_event_names(fd, false);
if (!namelist) {
@@ -2408,7 +2447,8 @@ static int __del_trace_probe_event(int fd, struct str_node *ent)
printf("Removed event: %s\n", ent->s);
return 0;
error:
- pr_warning("Failed to delete event: %s\n", strerror(-ret));
+ pr_warning("Failed to delete event: %s\n",
+ strerror_r(-ret, buf, sizeof(buf)));
return ret;
}
@@ -2449,15 +2489,18 @@ int del_perf_probe_events(struct strlist *dellist)
/* Get current event names */
kfd = open_kprobe_events(true);
- if (kfd < 0)
- return kfd;
+ if (kfd >= 0)
+ namelist = get_probe_trace_event_names(kfd, true);
- namelist = get_probe_trace_event_names(kfd, true);
ufd = open_uprobe_events(true);
-
if (ufd >= 0)
unamelist = get_probe_trace_event_names(ufd, true);
+ if (kfd < 0 && ufd < 0) {
+ print_both_open_warning(kfd, ufd);
+ goto error;
+ }
+
if (namelist == NULL && unamelist == NULL)
goto error;
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 776c9347a3b6..e01e9943139f 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -128,7 +128,8 @@ extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
bool force_add);
extern int del_perf_probe_events(struct strlist *dellist);
extern int show_perf_probe_events(void);
-extern int show_line_range(struct line_range *lr, const char *module);
+extern int show_line_range(struct line_range *lr, const char *module,
+ bool user);
extern int show_available_vars(struct perf_probe_event *pevs, int npevs,
int max_probe_points, const char *module,
struct strfilter *filter, bool externs);
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 98e304766416..c7918f83b300 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -26,7 +26,6 @@
#include <errno.h>
#include <stdio.h>
#include <unistd.h>
-#include <getopt.h>
#include <stdlib.h>
#include <string.h>
#include <stdarg.h>
@@ -282,6 +281,7 @@ static int convert_variable_type(Dwarf_Die *vr_die,
struct probe_trace_arg_ref **ref_ptr = &tvar->ref;
Dwarf_Die type;
char buf[16];
+ char sbuf[STRERR_BUFSIZE];
int bsize, boffs, total;
int ret;
@@ -368,7 +368,7 @@ formatted:
if (ret >= 16)
ret = -E2BIG;
pr_warning("Failed to convert variable type: %s\n",
- strerror(-ret));
+ strerror_r(-ret, sbuf, sizeof(sbuf)));
return ret;
}
tvar->type = strdup(buf);
@@ -609,14 +609,18 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod,
return -EINVAL;
}
- /* Get an appropriate symbol from symtab */
- symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL);
+ symbol = dwarf_diename(sp_die);
if (!symbol) {
- pr_warning("Failed to find symbol at 0x%lx\n",
- (unsigned long)paddr);
- return -ENOENT;
+ /* Try to get the symbol name from symtab */
+ symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL);
+ if (!symbol) {
+ pr_warning("Failed to find symbol at 0x%lx\n",
+ (unsigned long)paddr);
+ return -ENOENT;
+ }
+ eaddr = sym.st_value;
}
- tp->offset = (unsigned long)(paddr - sym.st_value);
+ tp->offset = (unsigned long)(paddr - eaddr);
tp->address = (unsigned long)paddr;
tp->symbol = strdup(symbol);
if (!tp->symbol)
@@ -780,10 +784,12 @@ static int find_lazy_match_lines(struct intlist *list,
size_t line_len;
ssize_t len;
int count = 0, linenum = 1;
+ char sbuf[STRERR_BUFSIZE];
fp = fopen(fname, "r");
if (!fp) {
- pr_warning("Failed to open %s: %s\n", fname, strerror(errno));
+ pr_warning("Failed to open %s: %s\n", fname,
+ strerror_r(errno, sbuf, sizeof(sbuf)));
return -errno;
}
diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c
index daa17aeb6c63..a126e6cc6e73 100644
--- a/tools/perf/util/pstack.c
+++ b/tools/perf/util/pstack.c
@@ -6,6 +6,7 @@
#include "util.h"
#include "pstack.h"
+#include "debug.h"
#include <linux/kernel.h>
#include <stdlib.h>
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 122669c18ff4..3dda85ca50c1 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -14,12 +14,12 @@
*/
int verbose;
-int eprintf(int level, const char *fmt, ...)
+int eprintf(int level, int var, const char *fmt, ...)
{
va_list args;
int ret = 0;
- if (verbose >= level) {
+ if (var >= level) {
va_start(args, fmt);
ret = vfprintf(stderr, fmt, args);
va_end(args);
@@ -736,7 +736,7 @@ static PyObject *pyrf_evlist__poll(struct pyrf_evlist *pevlist,
if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|i", kwlist, &timeout))
return NULL;
- n = poll(evlist->pollfd, evlist->nr_fds, timeout);
+ n = perf_evlist__poll(evlist, timeout);
if (n < 0) {
PyErr_SetFromErrno(PyExc_OSError);
return NULL;
@@ -753,9 +753,9 @@ static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist,
PyObject *list = PyList_New(0);
int i;
- for (i = 0; i < evlist->nr_fds; ++i) {
+ for (i = 0; i < evlist->pollfd.nr; ++i) {
PyObject *file;
- FILE *fp = fdopen(evlist->pollfd[i].fd, "r");
+ FILE *fp = fdopen(evlist->pollfd.entries[i].fd, "r");
if (fp == NULL)
goto free_list;
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 049e0a09ccd3..cf69325b985f 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -4,6 +4,7 @@
#include "parse-events.h"
#include <api/fs/fs.h>
#include "util.h"
+#include "cloexec.h"
typedef void (*setup_probe_fn_t)(struct perf_evsel *evsel);
@@ -11,7 +12,9 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
{
struct perf_evlist *evlist;
struct perf_evsel *evsel;
+ unsigned long flags = perf_event_open_cloexec_flag();
int err = -EAGAIN, fd;
+ static pid_t pid = -1;
evlist = perf_evlist__new();
if (!evlist)
@@ -22,14 +25,22 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
evsel = perf_evlist__first(evlist);
- fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0);
- if (fd < 0)
- goto out_delete;
+ while (1) {
+ fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, flags);
+ if (fd < 0) {
+ if (pid == -1 && errno == EACCES) {
+ pid = 0;
+ continue;
+ }
+ goto out_delete;
+ }
+ break;
+ }
close(fd);
fn(evsel);
- fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0);
+ fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, flags);
if (fd < 0) {
if (errno == EINVAL)
err = -EINVAL;
@@ -45,7 +56,7 @@ out_delete:
static bool perf_probe_api(setup_probe_fn_t fn)
{
- const char *try[] = {"cycles:u", "instructions:u", "cpu-clock", NULL};
+ const char *try[] = {"cycles:u", "instructions:u", "cpu-clock:u", NULL};
struct cpu_map *cpus;
int cpu, ret, i = 0;
@@ -69,15 +80,26 @@ static void perf_probe_sample_identifier(struct perf_evsel *evsel)
evsel->attr.sample_type |= PERF_SAMPLE_IDENTIFIER;
}
+static void perf_probe_comm_exec(struct perf_evsel *evsel)
+{
+ evsel->attr.comm_exec = 1;
+}
+
bool perf_can_sample_identifier(void)
{
return perf_probe_api(perf_probe_sample_identifier);
}
+static bool perf_can_comm_exec(void)
+{
+ return perf_probe_api(perf_probe_comm_exec);
+}
+
void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
{
struct perf_evsel *evsel;
bool use_sample_identifier = false;
+ bool use_comm_exec;
/*
* Set the evsel leader links before we configure attributes,
@@ -89,8 +111,13 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
if (evlist->cpus->map[0] < 0)
opts->no_inherit = true;
- evlist__for_each(evlist, evsel)
+ use_comm_exec = perf_can_comm_exec();
+
+ evlist__for_each(evlist, evsel) {
perf_evsel__config(evsel, opts);
+ if (evsel->tracking && use_comm_exec)
+ evsel->attr.comm_exec = 1;
+ }
if (evlist->nr_entries > 1) {
struct perf_evsel *first = perf_evlist__first(evlist);
@@ -183,6 +210,7 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str)
struct perf_evsel *evsel;
int err, fd, cpu;
bool ret = false;
+ pid_t pid = -1;
temp_evlist = perf_evlist__new();
if (!temp_evlist)
@@ -203,11 +231,20 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str)
cpu = evlist->cpus->map[0];
}
- fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0);
- if (fd >= 0) {
- close(fd);
- ret = true;
+ while (1) {
+ fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1,
+ perf_event_open_cloexec_flag());
+ if (fd < 0) {
+ if (pid == -1 && errno == EACCES) {
+ pid = 0;
+ continue;
+ }
+ goto out_delete;
+ }
+ break;
}
+ close(fd);
+ ret = true;
out_delete:
perf_evlist__delete(temp_evlist);
diff --git a/tools/perf/util/run-command.c b/tools/perf/util/run-command.c
index da8e9b285f51..34622b53e733 100644
--- a/tools/perf/util/run-command.c
+++ b/tools/perf/util/run-command.c
@@ -1,6 +1,7 @@
#include "cache.h"
#include "run-command.h"
#include "exec_cmd.h"
+#include "debug.h"
static inline void close_pair(int fd[2])
{
@@ -19,6 +20,7 @@ int start_command(struct child_process *cmd)
{
int need_in, need_out, need_err;
int fdin[2], fdout[2], fderr[2];
+ char sbuf[STRERR_BUFSIZE];
/*
* In case of errors we must keep the promise to close FDs
@@ -99,7 +101,7 @@ int start_command(struct child_process *cmd)
if (cmd->dir && chdir(cmd->dir))
die("exec %s: cd to %s failed (%s)", cmd->argv[0],
- cmd->dir, strerror(errno));
+ cmd->dir, strerror_r(errno, sbuf, sizeof(sbuf)));
if (cmd->env) {
for (; *cmd->env; cmd->env++) {
if (strchr(*cmd->env, '='))
@@ -153,6 +155,8 @@ int start_command(struct child_process *cmd)
static int wait_or_whine(pid_t pid)
{
+ char sbuf[STRERR_BUFSIZE];
+
for (;;) {
int status, code;
pid_t waiting = waitpid(pid, &status, 0);
@@ -160,7 +164,8 @@ static int wait_or_whine(pid_t pid)
if (waiting < 0) {
if (errno == EINTR)
continue;
- error("waitpid failed (%s)", strerror(errno));
+ error("waitpid failed (%s)",
+ strerror_r(errno, sbuf, sizeof(sbuf)));
return -ERR_RUN_COMMAND_WAITPID;
}
if (waiting != pid)
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index af7da565a750..0a01bac4ce02 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -34,6 +34,7 @@
#include "../event.h"
#include "../trace-event.h"
#include "../evsel.h"
+#include "../debug.h"
void boot_Perf__Trace__Context(pTHX_ CV *cv);
void boot_DynaLoader(pTHX_ CV *cv);
@@ -431,6 +432,11 @@ error:
return err;
}
+static int perl_flush_script(void)
+{
+ return 0;
+}
+
/*
* Stop trace script
*/
@@ -632,6 +638,7 @@ static int perl_generate_script(struct pevent *pevent, const char *outfile)
struct scripting_ops perl_scripting_ops = {
.name = "Perl",
.start_script = perl_start_script,
+ .flush_script = perl_flush_script,
.stop_script = perl_stop_script,
.process_event = perl_process_event,
.generate_script = perl_generate_script,
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 1c419321f707..56ba07cce549 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -27,11 +27,13 @@
#include <errno.h>
#include "../../perf.h"
+#include "../debug.h"
#include "../evsel.h"
#include "../util.h"
#include "../event.h"
#include "../thread.h"
#include "../trace-event.h"
+#include "../machine.h"
PyMODINIT_FUNC initperf_trace_context(void);
@@ -50,10 +52,14 @@ static int zero_flag_atom;
static PyObject *main_module, *main_dict;
+static void handler_call_die(const char *handler_name) NORETURN;
static void handler_call_die(const char *handler_name)
{
PyErr_Print();
Py_FatalError("problem in Python trace event handler");
+ // Py_FatalError does not return
+ // but we have to make the compiler happy
+ abort();
}
/*
@@ -67,6 +73,35 @@ static void pydict_set_item_string_decref(PyObject *dict, const char *key, PyObj
Py_DECREF(val);
}
+static PyObject *get_handler(const char *handler_name)
+{
+ PyObject *handler;
+
+ handler = PyDict_GetItemString(main_dict, handler_name);
+ if (handler && !PyCallable_Check(handler))
+ return NULL;
+ return handler;
+}
+
+static void call_object(PyObject *handler, PyObject *args, const char *die_msg)
+{
+ PyObject *retval;
+
+ retval = PyObject_CallObject(handler, args);
+ if (retval == NULL)
+ handler_call_die(die_msg);
+ Py_DECREF(retval);
+}
+
+static void try_call_object(const char *handler_name, PyObject *args)
+{
+ PyObject *handler;
+
+ handler = get_handler(handler_name);
+ if (handler)
+ call_object(handler, args, handler_name);
+}
+
static void define_value(enum print_arg_type field_type,
const char *ev_name,
const char *field_name,
@@ -74,7 +109,7 @@ static void define_value(enum print_arg_type field_type,
const char *field_str)
{
const char *handler_name = "define_flag_value";
- PyObject *handler, *t, *retval;
+ PyObject *t;
unsigned long long value;
unsigned n = 0;
@@ -92,12 +127,7 @@ static void define_value(enum print_arg_type field_type,
PyTuple_SetItem(t, n++, PyInt_FromLong(value));
PyTuple_SetItem(t, n++, PyString_FromString(field_str));
- handler = PyDict_GetItemString(main_dict, handler_name);
- if (handler && PyCallable_Check(handler)) {
- retval = PyObject_CallObject(handler, t);
- if (retval == NULL)
- handler_call_die(handler_name);
- }
+ try_call_object(handler_name, t);
Py_DECREF(t);
}
@@ -120,7 +150,7 @@ static void define_field(enum print_arg_type field_type,
const char *delim)
{
const char *handler_name = "define_flag_field";
- PyObject *handler, *t, *retval;
+ PyObject *t;
unsigned n = 0;
if (field_type == PRINT_SYMBOL)
@@ -138,12 +168,7 @@ static void define_field(enum print_arg_type field_type,
if (field_type == PRINT_FLAGS)
PyTuple_SetItem(t, n++, PyString_FromString(delim));
- handler = PyDict_GetItemString(main_dict, handler_name);
- if (handler && PyCallable_Check(handler)) {
- retval = PyObject_CallObject(handler, t);
- if (retval == NULL)
- handler_call_die(handler_name);
- }
+ try_call_object(handler_name, t);
Py_DECREF(t);
}
@@ -231,15 +256,133 @@ static inline struct event_format *find_cache_event(struct perf_evsel *evsel)
return event;
}
+static PyObject *get_field_numeric_entry(struct event_format *event,
+ struct format_field *field, void *data)
+{
+ bool is_array = field->flags & FIELD_IS_ARRAY;
+ PyObject *obj, *list = NULL;
+ unsigned long long val;
+ unsigned int item_size, n_items, i;
+
+ if (is_array) {
+ list = PyList_New(field->arraylen);
+ item_size = field->size / field->arraylen;
+ n_items = field->arraylen;
+ } else {
+ item_size = field->size;
+ n_items = 1;
+ }
+
+ for (i = 0; i < n_items; i++) {
+
+ val = read_size(event, data + field->offset + i * item_size,
+ item_size);
+ if (field->flags & FIELD_IS_SIGNED) {
+ if ((long long)val >= LONG_MIN &&
+ (long long)val <= LONG_MAX)
+ obj = PyInt_FromLong(val);
+ else
+ obj = PyLong_FromLongLong(val);
+ } else {
+ if (val <= LONG_MAX)
+ obj = PyInt_FromLong(val);
+ else
+ obj = PyLong_FromUnsignedLongLong(val);
+ }
+ if (is_array)
+ PyList_SET_ITEM(list, i, obj);
+ }
+ if (is_array)
+ obj = list;
+ return obj;
+}
+
+
+static PyObject *python_process_callchain(struct perf_sample *sample,
+ struct perf_evsel *evsel,
+ struct addr_location *al)
+{
+ PyObject *pylist;
+
+ pylist = PyList_New(0);
+ if (!pylist)
+ Py_FatalError("couldn't create Python list");
+
+ if (!symbol_conf.use_callchain || !sample->callchain)
+ goto exit;
+
+ if (machine__resolve_callchain(al->machine, evsel, al->thread,
+ sample, NULL, NULL,
+ PERF_MAX_STACK_DEPTH) != 0) {
+ pr_err("Failed to resolve callchain. Skipping\n");
+ goto exit;
+ }
+ callchain_cursor_commit(&callchain_cursor);
+
+
+ while (1) {
+ PyObject *pyelem;
+ struct callchain_cursor_node *node;
+ node = callchain_cursor_current(&callchain_cursor);
+ if (!node)
+ break;
+
+ pyelem = PyDict_New();
+ if (!pyelem)
+ Py_FatalError("couldn't create Python dictionary");
+
+
+ pydict_set_item_string_decref(pyelem, "ip",
+ PyLong_FromUnsignedLongLong(node->ip));
+
+ if (node->sym) {
+ PyObject *pysym = PyDict_New();
+ if (!pysym)
+ Py_FatalError("couldn't create Python dictionary");
+ pydict_set_item_string_decref(pysym, "start",
+ PyLong_FromUnsignedLongLong(node->sym->start));
+ pydict_set_item_string_decref(pysym, "end",
+ PyLong_FromUnsignedLongLong(node->sym->end));
+ pydict_set_item_string_decref(pysym, "binding",
+ PyInt_FromLong(node->sym->binding));
+ pydict_set_item_string_decref(pysym, "name",
+ PyString_FromStringAndSize(node->sym->name,
+ node->sym->namelen));
+ pydict_set_item_string_decref(pyelem, "sym", pysym);
+ }
+
+ if (node->map) {
+ struct map *map = node->map;
+ const char *dsoname = "[unknown]";
+ if (map && map->dso && (map->dso->name || map->dso->long_name)) {
+ if (symbol_conf.show_kernel_path && map->dso->long_name)
+ dsoname = map->dso->long_name;
+ else if (map->dso->name)
+ dsoname = map->dso->name;
+ }
+ pydict_set_item_string_decref(pyelem, "dso",
+ PyString_FromString(dsoname));
+ }
+
+ callchain_cursor_advance(&callchain_cursor);
+ PyList_Append(pylist, pyelem);
+ Py_DECREF(pyelem);
+ }
+
+exit:
+ return pylist;
+}
+
+
static void python_process_tracepoint(struct perf_sample *sample,
struct perf_evsel *evsel,
struct thread *thread,
struct addr_location *al)
{
- PyObject *handler, *retval, *context, *t, *obj, *dict = NULL;
+ PyObject *handler, *context, *t, *obj, *callchain;
+ PyObject *dict = NULL;
static char handler_name[256];
struct format_field *field;
- unsigned long long val;
unsigned long s, ns;
struct event_format *event;
unsigned n = 0;
@@ -261,9 +404,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
sprintf(handler_name, "%s__%s", event->system, event->name);
- handler = PyDict_GetItemString(main_dict, handler_name);
- if (handler && !PyCallable_Check(handler))
- handler = NULL;
+ handler = get_handler(handler_name);
if (!handler) {
dict = PyDict_New();
if (!dict)
@@ -280,18 +421,23 @@ static void python_process_tracepoint(struct perf_sample *sample,
PyTuple_SetItem(t, n++, PyString_FromString(handler_name));
PyTuple_SetItem(t, n++, context);
+ /* ip unwinding */
+ callchain = python_process_callchain(sample, evsel, al);
+
if (handler) {
PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
PyTuple_SetItem(t, n++, PyInt_FromLong(s));
PyTuple_SetItem(t, n++, PyInt_FromLong(ns));
PyTuple_SetItem(t, n++, PyInt_FromLong(pid));
PyTuple_SetItem(t, n++, PyString_FromString(comm));
+ PyTuple_SetItem(t, n++, callchain);
} else {
pydict_set_item_string_decref(dict, "common_cpu", PyInt_FromLong(cpu));
pydict_set_item_string_decref(dict, "common_s", PyInt_FromLong(s));
pydict_set_item_string_decref(dict, "common_ns", PyInt_FromLong(ns));
pydict_set_item_string_decref(dict, "common_pid", PyInt_FromLong(pid));
pydict_set_item_string_decref(dict, "common_comm", PyString_FromString(comm));
+ pydict_set_item_string_decref(dict, "common_callchain", callchain);
}
for (field = event->format.fields; field; field = field->next) {
if (field->flags & FIELD_IS_STRING) {
@@ -303,20 +449,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
offset = field->offset;
obj = PyString_FromString((char *)data + offset);
} else { /* FIELD_IS_NUMERIC */
- val = read_size(event, data + field->offset,
- field->size);
- if (field->flags & FIELD_IS_SIGNED) {
- if ((long long)val >= LONG_MIN &&
- (long long)val <= LONG_MAX)
- obj = PyInt_FromLong(val);
- else
- obj = PyLong_FromLongLong(val);
- } else {
- if (val <= LONG_MAX)
- obj = PyInt_FromLong(val);
- else
- obj = PyLong_FromUnsignedLongLong(val);
- }
+ obj = get_field_numeric_entry(event, field, data);
}
if (handler)
PyTuple_SetItem(t, n++, obj);
@@ -324,6 +457,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
pydict_set_item_string_decref(dict, field->name, obj);
}
+
if (!handler)
PyTuple_SetItem(t, n++, dict);
@@ -331,17 +465,9 @@ static void python_process_tracepoint(struct perf_sample *sample,
Py_FatalError("error resizing Python tuple");
if (handler) {
- retval = PyObject_CallObject(handler, t);
- if (retval == NULL)
- handler_call_die(handler_name);
+ call_object(handler, t, handler_name);
} else {
- handler = PyDict_GetItemString(main_dict, "trace_unhandled");
- if (handler && PyCallable_Check(handler)) {
-
- retval = PyObject_CallObject(handler, t);
- if (retval == NULL)
- handler_call_die("trace_unhandled");
- }
+ try_call_object("trace_unhandled", t);
Py_DECREF(dict);
}
@@ -353,7 +479,7 @@ static void python_process_general_event(struct perf_sample *sample,
struct thread *thread,
struct addr_location *al)
{
- PyObject *handler, *retval, *t, *dict;
+ PyObject *handler, *t, *dict, *callchain, *dict_sample;
static char handler_name[64];
unsigned n = 0;
@@ -369,17 +495,34 @@ static void python_process_general_event(struct perf_sample *sample,
if (!dict)
Py_FatalError("couldn't create Python dictionary");
+ dict_sample = PyDict_New();
+ if (!dict_sample)
+ Py_FatalError("couldn't create Python dictionary");
+
snprintf(handler_name, sizeof(handler_name), "%s", "process_event");
- handler = PyDict_GetItemString(main_dict, handler_name);
- if (!handler || !PyCallable_Check(handler))
+ handler = get_handler(handler_name);
+ if (!handler)
goto exit;
pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize(
(const char *)&evsel->attr, sizeof(evsel->attr)));
- pydict_set_item_string_decref(dict, "sample", PyString_FromStringAndSize(
- (const char *)sample, sizeof(*sample)));
+
+ pydict_set_item_string_decref(dict_sample, "pid",
+ PyInt_FromLong(sample->pid));
+ pydict_set_item_string_decref(dict_sample, "tid",
+ PyInt_FromLong(sample->tid));
+ pydict_set_item_string_decref(dict_sample, "cpu",
+ PyInt_FromLong(sample->cpu));
+ pydict_set_item_string_decref(dict_sample, "ip",
+ PyLong_FromUnsignedLongLong(sample->ip));
+ pydict_set_item_string_decref(dict_sample, "time",
+ PyLong_FromUnsignedLongLong(sample->time));
+ pydict_set_item_string_decref(dict_sample, "period",
+ PyLong_FromUnsignedLongLong(sample->period));
+ pydict_set_item_string_decref(dict, "sample", dict_sample);
+
pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize(
(const char *)sample->raw_data, sample->raw_size));
pydict_set_item_string_decref(dict, "comm",
@@ -393,13 +536,15 @@ static void python_process_general_event(struct perf_sample *sample,
PyString_FromString(al->sym->name));
}
+ /* ip unwinding */
+ callchain = python_process_callchain(sample, evsel, al);
+ pydict_set_item_string_decref(dict, "callchain", callchain);
+
PyTuple_SetItem(t, n++, dict);
if (_PyTuple_Resize(&t, n) == -1)
Py_FatalError("error resizing Python tuple");
- retval = PyObject_CallObject(handler, t);
- if (retval == NULL)
- handler_call_die(handler_name);
+ call_object(handler, t, handler_name);
exit:
Py_DECREF(dict);
Py_DECREF(t);
@@ -423,36 +568,24 @@ static void python_process_event(union perf_event *event __maybe_unused,
static int run_start_sub(void)
{
- PyObject *handler, *retval;
- int err = 0;
-
main_module = PyImport_AddModule("__main__");
if (main_module == NULL)
return -1;
Py_INCREF(main_module);
main_dict = PyModule_GetDict(main_module);
- if (main_dict == NULL) {
- err = -1;
+ if (main_dict == NULL)
goto error;
- }
Py_INCREF(main_dict);
- handler = PyDict_GetItemString(main_dict, "trace_begin");
- if (handler == NULL || !PyCallable_Check(handler))
- goto out;
+ try_call_object("trace_begin", NULL);
- retval = PyObject_CallObject(handler, NULL);
- if (retval == NULL)
- handler_call_die("trace_begin");
+ return 0;
- Py_DECREF(retval);
- return err;
error:
Py_XDECREF(main_dict);
Py_XDECREF(main_module);
-out:
- return err;
+ return -1;
}
/*
@@ -506,29 +639,23 @@ error:
return err;
}
+static int python_flush_script(void)
+{
+ return 0;
+}
+
/*
* Stop trace script
*/
static int python_stop_script(void)
{
- PyObject *handler, *retval;
- int err = 0;
-
- handler = PyDict_GetItemString(main_dict, "trace_end");
- if (handler == NULL || !PyCallable_Check(handler))
- goto out;
+ try_call_object("trace_end", NULL);
- retval = PyObject_CallObject(handler, NULL);
- if (retval == NULL)
- handler_call_die("trace_end");
- else
- Py_DECREF(retval);
-out:
Py_XDECREF(main_dict);
Py_XDECREF(main_module);
Py_Finalize();
- return err;
+ return 0;
}
static int python_generate_script(struct pevent *pevent, const char *outfile)
@@ -589,6 +716,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
fprintf(ofp, "common_nsecs, ");
fprintf(ofp, "common_pid, ");
fprintf(ofp, "common_comm,\n\t");
+ fprintf(ofp, "common_callchain, ");
not_first = 0;
count = 0;
@@ -632,7 +760,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
fprintf(ofp, "%%u");
}
- fprintf(ofp, "\\n\" %% \\\n\t\t(");
+ fprintf(ofp, "\" %% \\\n\t\t(");
not_first = 0;
count = 0;
@@ -668,7 +796,15 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
fprintf(ofp, "%s", f->name);
}
- fprintf(ofp, "),\n\n");
+ fprintf(ofp, ")\n\n");
+
+ fprintf(ofp, "\t\tfor node in common_callchain:");
+ fprintf(ofp, "\n\t\t\tif 'sym' in node:");
+ fprintf(ofp, "\n\t\t\t\tprint \"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name'])");
+ fprintf(ofp, "\n\t\t\telse:");
+ fprintf(ofp, "\n\t\t\t\tprint \"\t[%%x]\" %% (node['ip'])\n\n");
+ fprintf(ofp, "\t\tprint \"\\n\"\n\n");
+
}
fprintf(ofp, "def trace_unhandled(event_name, context, "
@@ -692,6 +828,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
struct scripting_ops python_scripting_ops = {
.name = "Python",
.start_script = python_start_script,
+ .flush_script = python_flush_script,
.stop_script = python_stop_script,
.process_event = python_process_event,
.generate_script = python_generate_script,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 64a186edc7be..883406f4b381 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -14,7 +14,7 @@
#include "util.h"
#include "cpumap.h"
#include "perf_regs.h"
-#include "vdso.h"
+#include "asm/bug.h"
static int perf_session__open(struct perf_session *session)
{
@@ -67,6 +67,25 @@ static void perf_session__destroy_kernel_maps(struct perf_session *session)
machines__destroy_kernel_maps(&session->machines);
}
+static bool perf_session__has_comm_exec(struct perf_session *session)
+{
+ struct perf_evsel *evsel;
+
+ evlist__for_each(session->evlist, evsel) {
+ if (evsel->attr.comm_exec)
+ return true;
+ }
+
+ return false;
+}
+
+static void perf_session__set_comm_exec(struct perf_session *session)
+{
+ bool comm_exec = perf_session__has_comm_exec(session);
+
+ machines__set_comm_exec(&session->machines, comm_exec);
+}
+
struct perf_session *perf_session__new(struct perf_data_file *file,
bool repipe, struct perf_tool *tool)
{
@@ -76,9 +95,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
goto out;
session->repipe = repipe;
- INIT_LIST_HEAD(&session->ordered_samples.samples);
- INIT_LIST_HEAD(&session->ordered_samples.sample_cache);
- INIT_LIST_HEAD(&session->ordered_samples.to_free);
+ ordered_events__init(&session->ordered_events);
machines__init(&session->machines);
if (file) {
@@ -92,6 +109,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
goto out_close;
perf_session__set_id_hdr_size(session);
+ perf_session__set_comm_exec(session);
}
}
@@ -101,13 +119,13 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
* kernel MMAP event, in perf_event__process_mmap().
*/
if (perf_session__create_kernel_maps(session) < 0)
- goto out_delete;
+ pr_warning("Cannot read kernel map\n");
}
if (tool && tool->ordering_requires_timestamps &&
- tool->ordered_samples && !perf_evlist__sample_id_all(session->evlist)) {
+ tool->ordered_events && !perf_evlist__sample_id_all(session->evlist)) {
dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
- tool->ordered_samples = false;
+ tool->ordered_events = false;
}
return session;
@@ -156,7 +174,6 @@ void perf_session__delete(struct perf_session *session)
if (session->file)
perf_data_file__close(session->file);
free(session);
- vdso__exit();
}
static int process_event_synth_tracing_data_stub(struct perf_tool *tool
@@ -240,7 +257,7 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
if (tool->build_id == NULL)
tool->build_id = process_finished_round_stub;
if (tool->finished_round == NULL) {
- if (tool->ordered_samples)
+ if (tool->ordered_events)
tool->finished_round = process_finished_round;
else
tool->finished_round = process_finished_round_stub;
@@ -446,88 +463,6 @@ static perf_event__swap_op perf_event__swap_ops[] = {
[PERF_RECORD_HEADER_MAX] = NULL,
};
-struct sample_queue {
- u64 timestamp;
- u64 file_offset;
- union perf_event *event;
- struct list_head list;
-};
-
-static void perf_session_free_sample_buffers(struct perf_session *session)
-{
- struct ordered_samples *os = &session->ordered_samples;
-
- while (!list_empty(&os->to_free)) {
- struct sample_queue *sq;
-
- sq = list_entry(os->to_free.next, struct sample_queue, list);
- list_del(&sq->list);
- free(sq);
- }
-}
-
-static int perf_session_deliver_event(struct perf_session *session,
- union perf_event *event,
- struct perf_sample *sample,
- struct perf_tool *tool,
- u64 file_offset);
-
-static int flush_sample_queue(struct perf_session *s,
- struct perf_tool *tool)
-{
- struct ordered_samples *os = &s->ordered_samples;
- struct list_head *head = &os->samples;
- struct sample_queue *tmp, *iter;
- struct perf_sample sample;
- u64 limit = os->next_flush;
- u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
- bool show_progress = limit == ULLONG_MAX;
- struct ui_progress prog;
- int ret;
-
- if (!tool->ordered_samples || !limit)
- return 0;
-
- if (show_progress)
- ui_progress__init(&prog, os->nr_samples, "Processing time ordered events...");
-
- list_for_each_entry_safe(iter, tmp, head, list) {
- if (session_done())
- return 0;
-
- if (iter->timestamp > limit)
- break;
-
- ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample);
- if (ret)
- pr_err("Can't parse sample, err = %d\n", ret);
- else {
- ret = perf_session_deliver_event(s, iter->event, &sample, tool,
- iter->file_offset);
- if (ret)
- return ret;
- }
-
- os->last_flush = iter->timestamp;
- list_del(&iter->list);
- list_add(&iter->list, &os->sample_cache);
-
- if (show_progress)
- ui_progress__update(&prog, 1);
- }
-
- if (list_empty(head)) {
- os->last_sample = NULL;
- } else if (last_ts <= limit) {
- os->last_sample =
- list_entry(head->prev, struct sample_queue, list);
- }
-
- os->nr_samples = 0;
-
- return 0;
-}
-
/*
* When perf record finishes a pass on every buffers, it records this pseudo
* event.
@@ -571,99 +506,43 @@ static int process_finished_round(struct perf_tool *tool,
union perf_event *event __maybe_unused,
struct perf_session *session)
{
- int ret = flush_sample_queue(session, tool);
- if (!ret)
- session->ordered_samples.next_flush = session->ordered_samples.max_timestamp;
-
- return ret;
-}
-
-/* The queue is ordered by time */
-static void __queue_event(struct sample_queue *new, struct perf_session *s)
-{
- struct ordered_samples *os = &s->ordered_samples;
- struct sample_queue *sample = os->last_sample;
- u64 timestamp = new->timestamp;
- struct list_head *p;
-
- ++os->nr_samples;
- os->last_sample = new;
-
- if (!sample) {
- list_add(&new->list, &os->samples);
- os->max_timestamp = timestamp;
- return;
- }
-
- /*
- * last_sample might point to some random place in the list as it's
- * the last queued event. We expect that the new event is close to
- * this.
- */
- if (sample->timestamp <= timestamp) {
- while (sample->timestamp <= timestamp) {
- p = sample->list.next;
- if (p == &os->samples) {
- list_add_tail(&new->list, &os->samples);
- os->max_timestamp = timestamp;
- return;
- }
- sample = list_entry(p, struct sample_queue, list);
- }
- list_add_tail(&new->list, &sample->list);
- } else {
- while (sample->timestamp > timestamp) {
- p = sample->list.prev;
- if (p == &os->samples) {
- list_add(&new->list, &os->samples);
- return;
- }
- sample = list_entry(p, struct sample_queue, list);
- }
- list_add(&new->list, &sample->list);
- }
+ return ordered_events__flush(session, tool, OE_FLUSH__ROUND);
}
-#define MAX_SAMPLE_BUFFER (64 * 1024 / sizeof(struct sample_queue))
-
int perf_session_queue_event(struct perf_session *s, union perf_event *event,
- struct perf_sample *sample, u64 file_offset)
+ struct perf_tool *tool, struct perf_sample *sample,
+ u64 file_offset)
{
- struct ordered_samples *os = &s->ordered_samples;
- struct list_head *sc = &os->sample_cache;
+ struct ordered_events *oe = &s->ordered_events;
u64 timestamp = sample->time;
- struct sample_queue *new;
+ struct ordered_event *new;
if (!timestamp || timestamp == ~0ULL)
return -ETIME;
- if (timestamp < s->ordered_samples.last_flush) {
- printf("Warning: Timestamp below last timeslice flush\n");
- return -EINVAL;
+ if (timestamp < oe->last_flush) {
+ WARN_ONCE(1, "Timestamp below last timeslice flush\n");
+
+ pr_oe_time(timestamp, "out of order event");
+ pr_oe_time(oe->last_flush, "last flush, last_flush_type %d\n",
+ oe->last_flush_type);
+
+ /* We could get out of order messages after forced flush. */
+ if (oe->last_flush_type != OE_FLUSH__HALF)
+ return -EINVAL;
}
- if (!list_empty(sc)) {
- new = list_entry(sc->next, struct sample_queue, list);
- list_del(&new->list);
- } else if (os->sample_buffer) {
- new = os->sample_buffer + os->sample_buffer_idx;
- if (++os->sample_buffer_idx == MAX_SAMPLE_BUFFER)
- os->sample_buffer = NULL;
- } else {
- os->sample_buffer = malloc(MAX_SAMPLE_BUFFER * sizeof(*new));
- if (!os->sample_buffer)
- return -ENOMEM;
- list_add(&os->sample_buffer->list, &os->to_free);
- os->sample_buffer_idx = 2;
- new = os->sample_buffer + 1;
+ new = ordered_events__new(oe, timestamp);
+ if (!new) {
+ ordered_events__flush(s, tool, OE_FLUSH__HALF);
+ new = ordered_events__new(oe, timestamp);
}
- new->timestamp = timestamp;
+ if (!new)
+ return -ENOMEM;
+
new->file_offset = file_offset;
new->event = event;
-
- __queue_event(new, s);
-
return 0;
}
@@ -923,11 +802,10 @@ perf_session__deliver_sample(struct perf_session *session,
&sample->read.one, machine);
}
-static int perf_session_deliver_event(struct perf_session *session,
- union perf_event *event,
- struct perf_sample *sample,
- struct perf_tool *tool,
- u64 file_offset)
+int perf_session__deliver_event(struct perf_session *session,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_tool *tool, u64 file_offset)
{
struct perf_evsel *evsel;
struct machine *machine;
@@ -994,8 +872,10 @@ static int perf_session_deliver_event(struct perf_session *session,
}
}
-static int perf_session__process_user_event(struct perf_session *session, union perf_event *event,
- struct perf_tool *tool, u64 file_offset)
+static s64 perf_session__process_user_event(struct perf_session *session,
+ union perf_event *event,
+ struct perf_tool *tool,
+ u64 file_offset)
{
int fd = perf_data_file__fd(session->file);
int err;
@@ -1006,8 +886,10 @@ static int perf_session__process_user_event(struct perf_session *session, union
switch (event->header.type) {
case PERF_RECORD_HEADER_ATTR:
err = tool->attr(tool, event, &session->evlist);
- if (err == 0)
+ if (err == 0) {
perf_session__set_id_hdr_size(session);
+ perf_session__set_comm_exec(session);
+ }
return err;
case PERF_RECORD_HEADER_EVENT_TYPE:
/*
@@ -1037,7 +919,62 @@ static void event_swap(union perf_event *event, bool sample_id_all)
swap(event, sample_id_all);
}
-static int perf_session__process_event(struct perf_session *session,
+int perf_session__peek_event(struct perf_session *session, off_t file_offset,
+ void *buf, size_t buf_sz,
+ union perf_event **event_ptr,
+ struct perf_sample *sample)
+{
+ union perf_event *event;
+ size_t hdr_sz, rest;
+ int fd;
+
+ if (session->one_mmap && !session->header.needs_swap) {
+ event = file_offset - session->one_mmap_offset +
+ session->one_mmap_addr;
+ goto out_parse_sample;
+ }
+
+ if (perf_data_file__is_pipe(session->file))
+ return -1;
+
+ fd = perf_data_file__fd(session->file);
+ hdr_sz = sizeof(struct perf_event_header);
+
+ if (buf_sz < hdr_sz)
+ return -1;
+
+ if (lseek(fd, file_offset, SEEK_SET) == (off_t)-1 ||
+ readn(fd, &buf, hdr_sz) != (ssize_t)hdr_sz)
+ return -1;
+
+ event = (union perf_event *)buf;
+
+ if (session->header.needs_swap)
+ perf_event_header__bswap(&event->header);
+
+ if (event->header.size < hdr_sz)
+ return -1;
+
+ rest = event->header.size - hdr_sz;
+
+ if (readn(fd, &buf, rest) != (ssize_t)rest)
+ return -1;
+
+ if (session->header.needs_swap)
+ event_swap(event, perf_evlist__sample_id_all(session->evlist));
+
+out_parse_sample:
+
+ if (sample && event->header.type < PERF_RECORD_USER_TYPE_START &&
+ perf_evlist__parse_sample(session->evlist, event, sample))
+ return -1;
+
+ *event_ptr = event;
+
+ return 0;
+}
+
+static s64 perf_session__process_event(struct perf_session *session,
union perf_event *event,
struct perf_tool *tool,
u64 file_offset)
@@ -1063,15 +1000,15 @@ static int perf_session__process_event(struct perf_session *session,
if (ret)
return ret;
- if (tool->ordered_samples) {
- ret = perf_session_queue_event(session, event, &sample,
+ if (tool->ordered_events) {
+ ret = perf_session_queue_event(session, event, tool, &sample,
file_offset);
if (ret != -ETIME)
return ret;
}
- return perf_session_deliver_event(session, event, &sample, tool,
- file_offset);
+ return perf_session__deliver_event(session, event, &sample, tool,
+ file_offset);
}
void perf_event_header__bswap(struct perf_event_header *hdr)
@@ -1083,13 +1020,14 @@ void perf_event_header__bswap(struct perf_event_header *hdr)
struct thread *perf_session__findnew(struct perf_session *session, pid_t pid)
{
- return machine__findnew_thread(&session->machines.host, 0, pid);
+ return machine__findnew_thread(&session->machines.host, -1, pid);
}
static struct thread *perf_session__register_idle_thread(struct perf_session *session)
{
- struct thread *thread = perf_session__findnew(session, 0);
+ struct thread *thread;
+ thread = machine__findnew_thread(&session->machines.host, 0, 0);
if (thread == NULL || thread__set_comm(thread, "swapper", 0)) {
pr_err("problem inserting idle task.\n");
thread = NULL;
@@ -1147,7 +1085,7 @@ static int __perf_session__process_pipe_events(struct perf_session *session,
union perf_event *event;
uint32_t size, cur_size = 0;
void *buf = NULL;
- int skip = 0;
+ s64 skip = 0;
u64 head;
ssize_t err;
void *p;
@@ -1222,12 +1160,11 @@ more:
goto more;
done:
/* do the final flush for ordered samples */
- session->ordered_samples.next_flush = ULLONG_MAX;
- err = flush_sample_queue(session, tool);
+ err = ordered_events__flush(session, tool, OE_FLUSH__FINAL);
out_err:
free(buf);
perf_session__warn_about_errors(session, tool);
- perf_session_free_sample_buffers(session);
+ ordered_events__free(&session->ordered_events);
return err;
}
@@ -1276,13 +1213,13 @@ int __perf_session__process_events(struct perf_session *session,
u64 file_size, struct perf_tool *tool)
{
int fd = perf_data_file__fd(session->file);
- u64 head, page_offset, file_offset, file_pos;
+ u64 head, page_offset, file_offset, file_pos, size;
int err, mmap_prot, mmap_flags, map_idx = 0;
size_t mmap_size;
char *buf, *mmaps[NUM_MMAPS];
union perf_event *event;
- uint32_t size;
struct ui_progress prog;
+ s64 skip;
perf_tool__fill_defaults(tool);
@@ -1296,8 +1233,10 @@ int __perf_session__process_events(struct perf_session *session,
ui_progress__init(&prog, file_size, "Processing events...");
mmap_size = MMAP_SIZE;
- if (mmap_size > file_size)
+ if (mmap_size > file_size) {
mmap_size = file_size;
+ session->one_mmap = true;
+ }
memset(mmaps, 0, sizeof(mmaps));
@@ -1319,6 +1258,10 @@ remap:
mmaps[map_idx] = buf;
map_idx = (map_idx + 1) & (ARRAY_SIZE(mmaps) - 1);
file_pos = file_offset + head;
+ if (session->one_mmap) {
+ session->one_mmap_addr = buf;
+ session->one_mmap_offset = file_offset;
+ }
more:
event = fetch_mmaped_event(session, head, mmap_size, buf);
@@ -1337,7 +1280,8 @@ more:
size = event->header.size;
if (size < sizeof(struct perf_event_header) ||
- perf_session__process_event(session, event, tool, file_pos) < 0) {
+ (skip = perf_session__process_event(session, event, tool, file_pos))
+ < 0) {
pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
file_offset + head, event->header.size,
event->header.type);
@@ -1345,6 +1289,9 @@ more:
goto out_err;
}
+ if (skip)
+ size += skip;
+
head += size;
file_pos += size;
@@ -1358,12 +1305,12 @@ more:
out:
/* do the final flush for ordered samples */
- session->ordered_samples.next_flush = ULLONG_MAX;
- err = flush_sample_queue(session, tool);
+ err = ordered_events__flush(session, tool, OE_FLUSH__FINAL);
out_err:
ui_progress__finish();
perf_session__warn_about_errors(session, tool);
- perf_session_free_sample_buffers(session);
+ ordered_events__free(&session->ordered_events);
+ session->one_mmap = false;
return err;
}
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 3140f8ae6148..ffb440462008 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -9,26 +9,13 @@
#include "symbol.h"
#include "thread.h"
#include "data.h"
+#include "ordered-events.h"
#include <linux/rbtree.h>
#include <linux/perf_event.h>
-struct sample_queue;
struct ip_callchain;
struct thread;
-struct ordered_samples {
- u64 last_flush;
- u64 next_flush;
- u64 max_timestamp;
- struct list_head samples;
- struct list_head sample_cache;
- struct list_head to_free;
- struct sample_queue *sample_buffer;
- struct sample_queue *last_sample;
- int sample_buffer_idx;
- unsigned int nr_samples;
-};
-
struct perf_session {
struct perf_header header;
struct machines machines;
@@ -36,7 +23,10 @@ struct perf_session {
struct trace_event tevent;
struct events_stats stats;
bool repipe;
- struct ordered_samples ordered_samples;
+ bool one_mmap;
+ void *one_mmap_addr;
+ u64 one_mmap_offset;
+ struct ordered_events ordered_events;
struct perf_data_file *file;
};
@@ -55,6 +45,11 @@ void perf_session__delete(struct perf_session *session);
void perf_event_header__bswap(struct perf_event_header *hdr);
+int perf_session__peek_event(struct perf_session *session, off_t file_offset,
+ void *buf, size_t buf_sz,
+ union perf_event **event_ptr,
+ struct perf_sample *sample);
+
int __perf_session__process_events(struct perf_session *session,
u64 data_offset, u64 data_size, u64 size,
struct perf_tool *tool);
@@ -62,10 +57,16 @@ int perf_session__process_events(struct perf_session *session,
struct perf_tool *tool);
int perf_session_queue_event(struct perf_session *s, union perf_event *event,
- struct perf_sample *sample, u64 file_offset);
+ struct perf_tool *tool, struct perf_sample *sample,
+ u64 file_offset);
void perf_tool__fill_defaults(struct perf_tool *tool);
+int perf_session__deliver_event(struct perf_session *session,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_tool *tool, u64 file_offset);
+
int perf_session__resolve_callchain(struct perf_session *session,
struct perf_evsel *evsel,
struct thread *thread,
@@ -125,5 +126,5 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session,
extern volatile int session_done;
-#define session_done() (*(volatile int *)(&session_done))
+#define session_done() ACCESS_ONCE(session_done)
#endif /* __PERF_SESSION_H */
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 1ec57dd82284..289df9d1e65a 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -70,12 +70,14 @@ static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
const char *comm = thread__comm_str(he->thread);
- return repsep_snprintf(bf, size, "%*s:%5d", width - 6,
- comm ?: "", he->thread->tid);
+
+ width = max(7U, width) - 6;
+ return repsep_snprintf(bf, size, "%5d:%-*.*s", he->thread->tid,
+ width, width, comm ?: "");
}
struct sort_entry sort_thread = {
- .se_header = "Command: Pid",
+ .se_header = " Pid:Command",
.se_cmp = sort__thread_cmp,
.se_snprintf = hist_entry__thread_snprintf,
.se_width_idx = HISTC_THREAD,
@@ -106,7 +108,7 @@ sort__comm_sort(struct hist_entry *left, struct hist_entry *right)
static int hist_entry__comm_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
- return repsep_snprintf(bf, size, "%*s", width, comm__str(he->comm));
+ return repsep_snprintf(bf, size, "%-*.*s", width, width, comm__str(he->comm));
}
struct sort_entry sort_comm = {
@@ -152,10 +154,10 @@ static int _hist_entry__dso_snprintf(struct map *map, char *bf,
if (map && map->dso) {
const char *dso_name = !verbose ? map->dso->short_name :
map->dso->long_name;
- return repsep_snprintf(bf, size, "%-*s", width, dso_name);
+ return repsep_snprintf(bf, size, "%-*.*s", width, width, dso_name);
}
- return repsep_snprintf(bf, size, "%-*s", width, "[unknown]");
+ return repsep_snprintf(bf, size, "%-*.*s", width, width, "[unknown]");
}
static int hist_entry__dso_snprintf(struct hist_entry *he, char *bf,
@@ -257,7 +259,10 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
width - ret, "");
}
- return ret;
+ if (ret > width)
+ bf[width] = '\0';
+
+ return width;
}
static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf,
@@ -302,10 +307,9 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
}
static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf,
- size_t size,
- unsigned int width __maybe_unused)
+ size_t size, unsigned int width)
{
- return repsep_snprintf(bf, size, "%s", he->srcline);
+ return repsep_snprintf(bf, size, "%*.*-s", width, width, he->srcline);
}
struct sort_entry sort_srcline = {
@@ -332,7 +336,7 @@ sort__parent_cmp(struct hist_entry *left, struct hist_entry *right)
static int hist_entry__parent_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
- return repsep_snprintf(bf, size, "%-*s", width,
+ return repsep_snprintf(bf, size, "%-*.*s", width, width,
he->parent ? he->parent->name : "[other]");
}
@@ -354,7 +358,7 @@ sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right)
static int hist_entry__cpu_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
- return repsep_snprintf(bf, size, "%*d", width, he->cpu);
+ return repsep_snprintf(bf, size, "%*.*d", width, width, he->cpu);
}
struct sort_entry sort_cpu = {
@@ -484,7 +488,7 @@ static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf,
else if (he->branch_info->flags.mispred)
out = "Y";
- return repsep_snprintf(bf, size, "%-*s", width, out);
+ return repsep_snprintf(bf, size, "%-*.*s", width, width, out);
}
/* --sort daddr_sym */
@@ -1194,7 +1198,7 @@ bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
return hse_a->se == hse_b->se;
}
-void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
+void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists)
{
struct hpp_sort_entry *hse;
@@ -1202,20 +1206,21 @@ void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
return;
hse = container_of(fmt, struct hpp_sort_entry, hpp);
- hists__new_col_len(hists, hse->se->se_width_idx,
- strlen(hse->se->se_header));
+ hists__new_col_len(hists, hse->se->se_width_idx, strlen(fmt->name));
}
static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
struct perf_evsel *evsel)
{
struct hpp_sort_entry *hse;
- size_t len;
+ size_t len = fmt->user_len;
hse = container_of(fmt, struct hpp_sort_entry, hpp);
- len = hists__col_len(&evsel->hists, hse->se->se_width_idx);
- return scnprintf(hpp->buf, hpp->size, "%*s", len, hse->se->se_header);
+ if (!len)
+ len = hists__col_len(&evsel->hists, hse->se->se_width_idx);
+
+ return scnprintf(hpp->buf, hpp->size, "%-*.*s", len, len, fmt->name);
}
static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
@@ -1223,20 +1228,26 @@ static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
struct perf_evsel *evsel)
{
struct hpp_sort_entry *hse;
+ size_t len = fmt->user_len;
hse = container_of(fmt, struct hpp_sort_entry, hpp);
- return hists__col_len(&evsel->hists, hse->se->se_width_idx);
+ if (!len)
+ len = hists__col_len(&evsel->hists, hse->se->se_width_idx);
+
+ return len;
}
static int __sort__hpp_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
struct hist_entry *he)
{
struct hpp_sort_entry *hse;
- size_t len;
+ size_t len = fmt->user_len;
hse = container_of(fmt, struct hpp_sort_entry, hpp);
- len = hists__col_len(he->hists, hse->se->se_width_idx);
+
+ if (!len)
+ len = hists__col_len(he->hists, hse->se->se_width_idx);
return hse->se->se_snprintf(he, hpp->buf, hpp->size, len);
}
@@ -1253,6 +1264,7 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd)
}
hse->se = sd->entry;
+ hse->hpp.name = sd->entry->se_header;
hse->hpp.header = __sort__hpp_header;
hse->hpp.width = __sort__hpp_width;
hse->hpp.entry = __sort__hpp_entry;
@@ -1265,6 +1277,8 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd)
INIT_LIST_HEAD(&hse->hpp.list);
INIT_LIST_HEAD(&hse->hpp.sort_list);
hse->hpp.elide = false;
+ hse->hpp.len = 0;
+ hse->hpp.user_len = 0;
return hse;
}
@@ -1432,14 +1446,49 @@ static const char *get_default_sort_order(void)
return default_sort_orders[sort__mode];
}
+static int setup_sort_order(void)
+{
+ char *new_sort_order;
+
+ /*
+ * Append '+'-prefixed sort order to the default sort
+ * order string.
+ */
+ if (!sort_order || is_strict_order(sort_order))
+ return 0;
+
+ if (sort_order[1] == '\0') {
+ error("Invalid --sort key: `+'");
+ return -EINVAL;
+ }
+
+ /*
+ * We allocate new sort_order string, but we never free it,
+ * because it's checked over the rest of the code.
+ */
+ if (asprintf(&new_sort_order, "%s,%s",
+ get_default_sort_order(), sort_order + 1) < 0) {
+ error("Not enough memory to set up --sort");
+ return -ENOMEM;
+ }
+
+ sort_order = new_sort_order;
+ return 0;
+}
+
static int __setup_sorting(void)
{
char *tmp, *tok, *str;
- const char *sort_keys = sort_order;
+ const char *sort_keys;
int ret = 0;
+ ret = setup_sort_order();
+ if (ret)
+ return ret;
+
+ sort_keys = sort_order;
if (sort_keys == NULL) {
- if (field_order) {
+ if (is_strict_order(field_order)) {
/*
* If user specified field order but no sort order,
* we'll honor it and not add default sort orders.
@@ -1625,23 +1674,36 @@ static void reset_dimensions(void)
memory_sort_dimensions[i].taken = 0;
}
+bool is_strict_order(const char *order)
+{
+ return order && (*order != '+');
+}
+
static int __setup_output_field(void)
{
- char *tmp, *tok, *str;
- int ret = 0;
+ char *tmp, *tok, *str, *strp;
+ int ret = -EINVAL;
if (field_order == NULL)
return 0;
reset_dimensions();
- str = strdup(field_order);
+ strp = str = strdup(field_order);
if (str == NULL) {
error("Not enough memory to setup output fields");
return -ENOMEM;
}
- for (tok = strtok_r(str, ", ", &tmp);
+ if (!is_strict_order(field_order))
+ strp++;
+
+ if (!strlen(strp)) {
+ error("Invalid --fields key: `+'");
+ goto out;
+ }
+
+ for (tok = strtok_r(strp, ", ", &tmp);
tok; tok = strtok_r(NULL, ", ", &tmp)) {
ret = output_field_add(tok);
if (ret == -EINVAL) {
@@ -1653,6 +1715,7 @@ static int __setup_output_field(void)
}
}
+out:
free(str);
return ret;
}
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 041f0c9cea2b..c03e4ff8beff 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -218,4 +218,5 @@ void perf_hpp__set_elide(int idx, bool elide);
int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset);
+bool is_strict_order(const char *order);
#endif /* __PERF_SORT_H */
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index 2553e5b55b89..d87767f76903 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -9,78 +9,48 @@
*/
s64 perf_atoll(const char *str)
{
- unsigned int i;
- s64 length = -1, unit = 1;
+ s64 length;
+ char *p;
+ char c;
if (!isdigit(str[0]))
goto out_err;
- for (i = 1; i < strlen(str); i++) {
- switch (str[i]) {
- case 'B':
- case 'b':
- break;
- case 'K':
- if (str[i + 1] != 'B')
- goto out_err;
- else
- goto kilo;
- case 'k':
- if (str[i + 1] != 'b')
- goto out_err;
-kilo:
- unit = K;
- break;
- case 'M':
- if (str[i + 1] != 'B')
- goto out_err;
- else
- goto mega;
- case 'm':
- if (str[i + 1] != 'b')
+ length = strtoll(str, &p, 10);
+ switch (c = *p++) {
+ case 'b': case 'B':
+ if (*p)
goto out_err;
-mega:
- unit = K * K;
+ case '\0':
+ return length;
+ default:
+ goto out_err;
+ /* two-letter suffices */
+ case 'k': case 'K':
+ length <<= 10;
break;
- case 'G':
- if (str[i + 1] != 'B')
- goto out_err;
- else
- goto giga;
- case 'g':
- if (str[i + 1] != 'b')
- goto out_err;
-giga:
- unit = K * K * K;
+ case 'm': case 'M':
+ length <<= 20;
break;
- case 'T':
- if (str[i + 1] != 'B')
- goto out_err;
- else
- goto tera;
- case 't':
- if (str[i + 1] != 'b')
- goto out_err;
-tera:
- unit = K * K * K * K;
+ case 'g': case 'G':
+ length <<= 30;
break;
- case '\0': /* only specified figures */
- unit = 1;
+ case 't': case 'T':
+ length <<= 40;
break;
- default:
- if (!isdigit(str[i]))
- goto out_err;
- break;
- }
}
-
- length = atoll(str) * unit;
- goto out;
+ /* we want the cases to match */
+ if (islower(c)) {
+ if (strcmp(p, "b") != 0)
+ goto out_err;
+ } else {
+ if (strcmp(p, "B") != 0)
+ goto out_err;
+ }
+ return length;
out_err:
- length = -1;
-out:
- return length;
+ return -1;
}
/*
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 6a0a13d07a28..283d3e73e2f2 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -30,6 +30,7 @@ static u64 turbo_frequency, max_freq;
#define SLOT_MULT 30.0
#define SLOT_HEIGHT 25.0
+#define SLOT_HALF (SLOT_HEIGHT / 2)
int svg_page_width = 1000;
u64 svg_highlight;
@@ -114,8 +115,14 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end)
fprintf(svgfile, " rect { stroke-width: 1; }\n");
fprintf(svgfile, " rect.process { fill:rgb(180,180,180); fill-opacity:0.9; stroke-width:1; stroke:rgb( 0, 0, 0); } \n");
fprintf(svgfile, " rect.process2 { fill:rgb(180,180,180); fill-opacity:0.9; stroke-width:0; stroke:rgb( 0, 0, 0); } \n");
+ fprintf(svgfile, " rect.process3 { fill:rgb(180,180,180); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n");
fprintf(svgfile, " rect.sample { fill:rgb( 0, 0,255); fill-opacity:0.8; stroke-width:0; stroke:rgb( 0, 0, 0); } \n");
fprintf(svgfile, " rect.sample_hi{ fill:rgb(255,128, 0); fill-opacity:0.8; stroke-width:0; stroke:rgb( 0, 0, 0); } \n");
+ fprintf(svgfile, " rect.error { fill:rgb(255, 0, 0); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n");
+ fprintf(svgfile, " rect.net { fill:rgb( 0,128, 0); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n");
+ fprintf(svgfile, " rect.disk { fill:rgb( 0, 0,255); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n");
+ fprintf(svgfile, " rect.sync { fill:rgb(128,128, 0); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n");
+ fprintf(svgfile, " rect.poll { fill:rgb( 0,128,128); fill-opacity:0.2; stroke-width:0; stroke:rgb( 0, 0, 0); } \n");
fprintf(svgfile, " rect.blocked { fill:rgb(255, 0, 0); fill-opacity:0.5; stroke-width:0; stroke:rgb( 0, 0, 0); } \n");
fprintf(svgfile, " rect.waiting { fill:rgb(224,214, 0); fill-opacity:0.8; stroke-width:0; stroke:rgb( 0, 0, 0); } \n");
fprintf(svgfile, " rect.WAITING { fill:rgb(255,214, 48); fill-opacity:0.6; stroke-width:0; stroke:rgb( 0, 0, 0); } \n");
@@ -132,12 +139,81 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end)
fprintf(svgfile, " ]]>\n </style>\n</defs>\n");
}
+static double normalize_height(double height)
+{
+ if (height < 0.25)
+ return 0.25;
+ else if (height < 0.50)
+ return 0.50;
+ else if (height < 0.75)
+ return 0.75;
+ else
+ return 0.100;
+}
+
+void svg_ubox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges)
+{
+ double w = time2pixels(end) - time2pixels(start);
+ height = normalize_height(height);
+
+ if (!svgfile)
+ return;
+
+ fprintf(svgfile, "<g>\n");
+ fprintf(svgfile, "<title>fd=%d error=%d merges=%d</title>\n", fd, err, merges);
+ fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n",
+ time2pixels(start),
+ w,
+ Yslot * SLOT_MULT,
+ SLOT_HALF * height,
+ type);
+ fprintf(svgfile, "</g>\n");
+}
+
+void svg_lbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges)
+{
+ double w = time2pixels(end) - time2pixels(start);
+ height = normalize_height(height);
+
+ if (!svgfile)
+ return;
+
+ fprintf(svgfile, "<g>\n");
+ fprintf(svgfile, "<title>fd=%d error=%d merges=%d</title>\n", fd, err, merges);
+ fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n",
+ time2pixels(start),
+ w,
+ Yslot * SLOT_MULT + SLOT_HEIGHT - SLOT_HALF * height,
+ SLOT_HALF * height,
+ type);
+ fprintf(svgfile, "</g>\n");
+}
+
+void svg_fbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges)
+{
+ double w = time2pixels(end) - time2pixels(start);
+ height = normalize_height(height);
+
+ if (!svgfile)
+ return;
+
+ fprintf(svgfile, "<g>\n");
+ fprintf(svgfile, "<title>fd=%d error=%d merges=%d</title>\n", fd, err, merges);
+ fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n",
+ time2pixels(start),
+ w,
+ Yslot * SLOT_MULT + SLOT_HEIGHT - SLOT_HEIGHT * height,
+ SLOT_HEIGHT * height,
+ type);
+ fprintf(svgfile, "</g>\n");
+}
+
void svg_box(int Yslot, u64 start, u64 end, const char *type)
{
if (!svgfile)
return;
- fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"%s\"/>\n",
+ fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n",
time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT, type);
}
@@ -174,7 +250,7 @@ void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
cpu, time_to_string(end - start));
if (backtrace)
fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace);
- fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"%s\"/>\n",
+ fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n",
time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT,
type);
@@ -186,7 +262,7 @@ void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
text_size = round_text_size(text_size);
if (text_size > MIN_TEXT_SIZE)
- fprintf(svgfile, "<text x=\"%1.8f\" y=\"%1.8f\" font-size=\"%1.8fpt\">%i</text>\n",
+ fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\" font-size=\"%.8fpt\">%i</text>\n",
time2pixels(start), Yslot * SLOT_MULT + SLOT_HEIGHT - 1, text_size, cpu + 1);
fprintf(svgfile, "</g>\n");
@@ -202,10 +278,10 @@ static char *time_to_string(u64 duration)
return text;
if (duration < 1000 * 1000) { /* less than 1 msec */
- sprintf(text, "%4.1f us", duration / 1000.0);
+ sprintf(text, "%.1f us", duration / 1000.0);
return text;
}
- sprintf(text, "%4.1f ms", duration / 1000.0 / 1000);
+ sprintf(text, "%.1f ms", duration / 1000.0 / 1000);
return text;
}
@@ -233,14 +309,14 @@ void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
font_size = round_text_size(font_size);
- fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), Yslot * SLOT_MULT);
+ fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\">\n", time2pixels(start), Yslot * SLOT_MULT);
fprintf(svgfile, "<title>#%d waiting %s</title>\n", cpu, time_to_string(end - start));
if (backtrace)
fprintf(svgfile, "<desc>Waiting on:\n%s</desc>\n", backtrace);
- fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
+ fprintf(svgfile, "<rect x=\"0\" width=\"%.8f\" y=\"0\" height=\"%.1f\" class=\"%s\"/>\n",
time2pixels(end)-time2pixels(start), SLOT_HEIGHT, style);
if (font_size > MIN_TEXT_SIZE)
- fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%1.8fpt\"> %s</text>\n",
+ fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%.8fpt\"> %s</text>\n",
font_size, text);
fprintf(svgfile, "</g>\n");
}
@@ -289,16 +365,16 @@ void svg_cpu_box(int cpu, u64 __max_freq, u64 __turbo_freq)
fprintf(svgfile, "<g>\n");
- fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"cpu\"/>\n",
+ fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"cpu\"/>\n",
time2pixels(first_time),
time2pixels(last_time)-time2pixels(first_time),
cpu2y(cpu), SLOT_MULT+SLOT_HEIGHT);
sprintf(cpu_string, "CPU %i", (int)cpu);
- fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\">%s</text>\n",
+ fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\">%s</text>\n",
10+time2pixels(first_time), cpu2y(cpu) + SLOT_HEIGHT/2, cpu_string);
- fprintf(svgfile, "<text transform=\"translate(%4.8f,%4.8f)\" font-size=\"1.25pt\">%s</text>\n",
+ fprintf(svgfile, "<text transform=\"translate(%.8f,%.8f)\" font-size=\"1.25pt\">%s</text>\n",
10+time2pixels(first_time), cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - 4, cpu_model());
fprintf(svgfile, "</g>\n");
@@ -319,11 +395,11 @@ void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const c
else
type = "sample";
- fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), cpu2y(cpu));
+ fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\">\n", time2pixels(start), cpu2y(cpu));
fprintf(svgfile, "<title>%d %s running %s</title>\n", pid, name, time_to_string(end - start));
if (backtrace)
fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace);
- fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
+ fprintf(svgfile, "<rect x=\"0\" width=\"%.8f\" y=\"0\" height=\"%.1f\" class=\"%s\"/>\n",
time2pixels(end)-time2pixels(start), SLOT_MULT+SLOT_HEIGHT, type);
width = time2pixels(end)-time2pixels(start);
if (width > 6)
@@ -332,7 +408,7 @@ void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const c
width = round_text_size(width);
if (width > MIN_TEXT_SIZE)
- fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%3.8fpt\">%s</text>\n",
+ fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%.8fpt\">%s</text>\n",
width, name);
fprintf(svgfile, "</g>\n");
@@ -353,7 +429,7 @@ void svg_cstate(int cpu, u64 start, u64 end, int type)
type = 6;
sprintf(style, "c%i", type);
- fprintf(svgfile, "<rect class=\"%s\" x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\"/>\n",
+ fprintf(svgfile, "<rect class=\"%s\" x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\"/>\n",
style,
time2pixels(start), time2pixels(end)-time2pixels(start),
cpu2y(cpu), SLOT_MULT+SLOT_HEIGHT);
@@ -365,7 +441,7 @@ void svg_cstate(int cpu, u64 start, u64 end, int type)
width = round_text_size(width);
if (width > MIN_TEXT_SIZE)
- fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"%3.8fpt\">C%i</text>\n",
+ fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\" font-size=\"%.8fpt\">C%i</text>\n",
time2pixels(start), cpu2y(cpu)+width, width, type);
fprintf(svgfile, "</g>\n");
@@ -407,9 +483,9 @@ void svg_pstate(int cpu, u64 start, u64 end, u64 freq)
if (max_freq)
height = freq * 1.0 / max_freq * (SLOT_HEIGHT + SLOT_MULT);
height = 1 + cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - height;
- fprintf(svgfile, "<line x1=\"%4.8f\" x2=\"%4.8f\" y1=\"%4.1f\" y2=\"%4.1f\" class=\"pstate\"/>\n",
+ fprintf(svgfile, "<line x1=\"%.8f\" x2=\"%.8f\" y1=\"%.1f\" y2=\"%.1f\" class=\"pstate\"/>\n",
time2pixels(start), time2pixels(end), height, height);
- fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"0.25pt\">%s</text>\n",
+ fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\" font-size=\"0.25pt\">%s</text>\n",
time2pixels(start), height+0.9, HzToHuman(freq));
fprintf(svgfile, "</g>\n");
@@ -435,32 +511,32 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc
if (row1 < row2) {
if (row1) {
- fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
+ fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT, time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT + SLOT_MULT/32);
if (desc2)
- fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &gt;</text></g>\n",
+ fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &gt;</text></g>\n",
time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT + SLOT_HEIGHT/48, desc2);
}
if (row2) {
- fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
+ fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
time2pixels(start), row2 * SLOT_MULT - SLOT_MULT/32, time2pixels(start), row2 * SLOT_MULT);
if (desc1)
- fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &gt;</text></g>\n",
+ fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &gt;</text></g>\n",
time2pixels(start), row2 * SLOT_MULT - SLOT_MULT/32, desc1);
}
} else {
if (row2) {
- fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
+ fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT, time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT + SLOT_MULT/32);
if (desc1)
- fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &lt;</text></g>\n",
+ fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &lt;</text></g>\n",
time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT + SLOT_MULT/48, desc1);
}
if (row1) {
- fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
+ fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
time2pixels(start), row1 * SLOT_MULT - SLOT_MULT/32, time2pixels(start), row1 * SLOT_MULT);
if (desc2)
- fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &lt;</text></g>\n",
+ fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &lt;</text></g>\n",
time2pixels(start), row1 * SLOT_MULT - SLOT_HEIGHT/32, desc2);
}
}
@@ -468,7 +544,7 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc
if (row2 > row1)
height += SLOT_HEIGHT;
if (row1)
- fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(32,255,32)\"/>\n",
+ fprintf(svgfile, "<circle cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\" style=\"fill:rgb(32,255,32)\"/>\n",
time2pixels(start), height);
fprintf(svgfile, "</g>\n");
@@ -488,16 +564,16 @@ void svg_wakeline(u64 start, int row1, int row2, const char *backtrace)
fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
if (row1 < row2)
- fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
+ fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT, time2pixels(start), row2 * SLOT_MULT);
else
- fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
+ fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT, time2pixels(start), row1 * SLOT_MULT);
height = row1 * SLOT_MULT;
if (row2 > row1)
height += SLOT_HEIGHT;
- fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(32,255,32)\"/>\n",
+ fprintf(svgfile, "<circle cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\" style=\"fill:rgb(32,255,32)\"/>\n",
time2pixels(start), height);
fprintf(svgfile, "</g>\n");
@@ -515,9 +591,9 @@ void svg_interrupt(u64 start, int row, const char *backtrace)
if (backtrace)
fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
- fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(255,128,128)\"/>\n",
+ fprintf(svgfile, "<circle cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\" style=\"fill:rgb(255,128,128)\"/>\n",
time2pixels(start), row * SLOT_MULT);
- fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(255,128,128)\"/>\n",
+ fprintf(svgfile, "<circle cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\" style=\"fill:rgb(255,128,128)\"/>\n",
time2pixels(start), row * SLOT_MULT + SLOT_HEIGHT);
fprintf(svgfile, "</g>\n");
@@ -528,7 +604,7 @@ void svg_text(int Yslot, u64 start, const char *text)
if (!svgfile)
return;
- fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\">%s</text>\n",
+ fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\">%s</text>\n",
time2pixels(start), Yslot * SLOT_MULT+SLOT_HEIGHT/2, text);
}
@@ -537,12 +613,26 @@ static void svg_legenda_box(int X, const char *text, const char *style)
double boxsize;
boxsize = SLOT_HEIGHT / 2;
- fprintf(svgfile, "<rect x=\"%i\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
+ fprintf(svgfile, "<rect x=\"%i\" width=\"%.8f\" y=\"0\" height=\"%.1f\" class=\"%s\"/>\n",
X, boxsize, boxsize, style);
- fprintf(svgfile, "<text transform=\"translate(%4.8f, %4.8f)\" font-size=\"%4.8fpt\">%s</text>\n",
+ fprintf(svgfile, "<text transform=\"translate(%.8f, %.8f)\" font-size=\"%.8fpt\">%s</text>\n",
X + boxsize + 5, boxsize, 0.8 * boxsize, text);
}
+void svg_io_legenda(void)
+{
+ if (!svgfile)
+ return;
+
+ fprintf(svgfile, "<g>\n");
+ svg_legenda_box(0, "Disk", "disk");
+ svg_legenda_box(100, "Network", "net");
+ svg_legenda_box(200, "Sync", "sync");
+ svg_legenda_box(300, "Poll", "poll");
+ svg_legenda_box(400, "Error", "error");
+ fprintf(svgfile, "</g>\n");
+}
+
void svg_legenda(void)
{
if (!svgfile)
@@ -559,7 +649,7 @@ void svg_legenda(void)
fprintf(svgfile, "</g>\n");
}
-void svg_time_grid(void)
+void svg_time_grid(double min_thickness)
{
u64 i;
@@ -579,8 +669,10 @@ void svg_time_grid(void)
color = 128;
}
- fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%" PRIu64 "\" style=\"stroke:rgb(%i,%i,%i);stroke-width:%1.3f\"/>\n",
- time2pixels(i), SLOT_MULT/2, time2pixels(i), total_height, color, color, color, thickness);
+ if (thickness >= min_thickness)
+ fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%" PRIu64 "\" style=\"stroke:rgb(%i,%i,%i);stroke-width:%.3f\"/>\n",
+ time2pixels(i), SLOT_MULT/2, time2pixels(i),
+ total_height, color, color, color, thickness);
i += 10000000;
}
diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h
index e3aff5332e30..9292a5291445 100644
--- a/tools/perf/util/svghelper.h
+++ b/tools/perf/util/svghelper.h
@@ -4,6 +4,9 @@
#include <linux/types.h>
extern void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end);
+extern void svg_ubox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
+extern void svg_lbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
+extern void svg_fbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
extern void svg_box(int Yslot, u64 start, u64 end, const char *type);
extern void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
extern void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
@@ -16,7 +19,8 @@ extern void svg_cstate(int cpu, u64 start, u64 end, int type);
extern void svg_pstate(int cpu, u64 start, u64 end, u64 freq);
-extern void svg_time_grid(void);
+extern void svg_time_grid(double min_thickness);
+extern void svg_io_legenda(void);
extern void svg_legenda(void);
extern void svg_wakeline(u64 start, int row1, int row2, const char *backtrace);
extern void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace);
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 6864661a79dd..1e23a5bfb044 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -6,6 +6,7 @@
#include <inttypes.h>
#include "symbol.h"
+#include "machine.h"
#include "vdso.h"
#include <symbol/kallsyms.h>
#include "debug.h"
@@ -49,7 +50,8 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym)
static inline int elf_sym__is_function(const GElf_Sym *sym)
{
- return elf_sym__type(sym) == STT_FUNC &&
+ return (elf_sym__type(sym) == STT_FUNC ||
+ elf_sym__type(sym) == STT_GNU_IFUNC) &&
sym->st_name != 0 &&
sym->st_shndx != SHN_UNDEF;
}
@@ -598,6 +600,8 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
goto out_elf_end;
}
+ ss->is_64_bit = (gelf_getclass(elf) == ELFCLASS64);
+
ss->symtab = elf_section_by_name(elf, &ehdr, &ss->symshdr, ".symtab",
NULL);
if (ss->symshdr.sh_type != SHT_SYMTAB)
@@ -619,7 +623,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
GElf_Shdr shdr;
ss->adjust_symbols = (ehdr.e_type == ET_EXEC ||
ehdr.e_type == ET_REL ||
- is_vdso_map(dso->short_name) ||
+ dso__is_vdso(dso) ||
elf_section_by_name(elf, &ehdr, &shdr,
".gnu.prelink_undo",
NULL) != NULL);
@@ -677,6 +681,11 @@ static u64 ref_reloc(struct kmap *kmap)
return 0;
}
+static bool want_demangle(bool is_kernel_sym)
+{
+ return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
+}
+
int dso__load_sym(struct dso *dso, struct map *map,
struct symsrc *syms_ss, struct symsrc *runtime_ss,
symbol_filter_t filter, int kmodule)
@@ -698,6 +707,7 @@ int dso__load_sym(struct dso *dso, struct map *map,
bool remap_kernel = false, adjust_kernel_syms = false;
dso->symtab_type = syms_ss->type;
+ dso->is_64_bit = syms_ss->is_64_bit;
dso->rel = syms_ss->ehdr.e_type == ET_REL;
/*
@@ -708,6 +718,14 @@ int dso__load_sym(struct dso *dso, struct map *map,
symbols__delete(&dso->symbols[map->type]);
if (!syms_ss->symtab) {
+ /*
+ * If the vmlinux is stripped, fail so we will fall back
+ * to using kallsyms. The vmlinux runtime symbols aren't
+ * of much use.
+ */
+ if (dso->kernel)
+ goto out_elf_end;
+
syms_ss->symtab = syms_ss->dynsym;
syms_ss->symshdr = syms_ss->dynshdr;
}
@@ -732,7 +750,7 @@ int dso__load_sym(struct dso *dso, struct map *map,
if (symstrs == NULL)
goto out_elf_end;
- sec_strndx = elf_getscn(elf, ehdr.e_shstrndx);
+ sec_strndx = elf_getscn(runtime_ss->elf, runtime_ss->ehdr.e_shstrndx);
if (sec_strndx == NULL)
goto out_elf_end;
@@ -912,7 +930,11 @@ int dso__load_sym(struct dso *dso, struct map *map,
}
curr_dso->symtab_type = dso->symtab_type;
map_groups__insert(kmap->kmaps, curr_map);
- dsos__add(&dso->node, curr_dso);
+ /*
+ * The new DSO should go to the kernel DSOS
+ */
+ dsos__add(&map->groups->machine->kernel_dsos,
+ curr_dso);
dso__set_loaded(curr_dso, map->type);
} else
curr_dso = curr_map->dso;
@@ -934,9 +956,12 @@ new_symbol:
* DWARF DW_compile_unit has this, but we don't always have access
* to it...
*/
- if (symbol_conf.demangle) {
- demangled = bfd_demangle(NULL, elf_name,
- DMGL_PARAMS | DMGL_ANSI);
+ if (want_demangle(dso->kernel || kmodule)) {
+ int demangle_flags = DMGL_NO_OPTS;
+ if (verbose)
+ demangle_flags = DMGL_PARAMS | DMGL_ANSI;
+
+ demangled = bfd_demangle(NULL, elf_name, demangle_flags);
if (demangled != NULL)
elf_name = demangled;
}
@@ -1024,6 +1049,39 @@ int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data,
return err;
}
+enum dso_type dso__type_fd(int fd)
+{
+ enum dso_type dso_type = DSO__TYPE_UNKNOWN;
+ GElf_Ehdr ehdr;
+ Elf_Kind ek;
+ Elf *elf;
+
+ elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+ if (elf == NULL)
+ goto out;
+
+ ek = elf_kind(elf);
+ if (ek != ELF_K_ELF)
+ goto out_end;
+
+ if (gelf_getclass(elf) == ELFCLASS64) {
+ dso_type = DSO__TYPE_64BIT;
+ goto out_end;
+ }
+
+ if (gelf_getehdr(elf, &ehdr) == NULL)
+ goto out_end;
+
+ if (ehdr.e_machine == EM_X86_64)
+ dso_type = DSO__TYPE_X32BIT;
+ else
+ dso_type = DSO__TYPE_32BIT;
+out_end:
+ elf_end(elf);
+out:
+ return dso_type;
+}
+
static int copy_bytes(int from, off_t from_offs, int to, off_t to_offs, u64 len)
{
ssize_t r;
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index bd15f490d04f..c9541fea9514 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -288,6 +288,44 @@ int dso__synthesize_plt_symbols(struct dso *dso __maybe_unused,
return 0;
}
+static int fd__is_64_bit(int fd)
+{
+ u8 e_ident[EI_NIDENT];
+
+ if (lseek(fd, 0, SEEK_SET))
+ return -1;
+
+ if (readn(fd, e_ident, sizeof(e_ident)) != sizeof(e_ident))
+ return -1;
+
+ if (memcmp(e_ident, ELFMAG, SELFMAG) ||
+ e_ident[EI_VERSION] != EV_CURRENT)
+ return -1;
+
+ return e_ident[EI_CLASS] == ELFCLASS64;
+}
+
+enum dso_type dso__type_fd(int fd)
+{
+ Elf64_Ehdr ehdr;
+ int ret;
+
+ ret = fd__is_64_bit(fd);
+ if (ret < 0)
+ return DSO__TYPE_UNKNOWN;
+
+ if (ret)
+ return DSO__TYPE_64BIT;
+
+ if (readn(fd, &ehdr, sizeof(ehdr)) != sizeof(ehdr))
+ return DSO__TYPE_UNKNOWN;
+
+ if (ehdr.e_machine == EM_X86_64)
+ return DSO__TYPE_X32BIT;
+
+ return DSO__TYPE_32BIT;
+}
+
int dso__load_sym(struct dso *dso, struct map *map __maybe_unused,
struct symsrc *ss,
struct symsrc *runtime_ss __maybe_unused,
@@ -295,6 +333,11 @@ int dso__load_sym(struct dso *dso, struct map *map __maybe_unused,
int kmodule __maybe_unused)
{
unsigned char *build_id[BUILD_ID_SIZE];
+ int ret;
+
+ ret = fd__is_64_bit(ss->fd);
+ if (ret >= 0)
+ dso->is_64_bit = ret;
if (filename__read_build_id(ss->name, build_id, BUILD_ID_SIZE) > 0) {
dso__set_build_id(dso, build_id);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 7b9096f29cdb..be84f7a9838b 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -15,6 +15,7 @@
#include "machine.h"
#include "symbol.h"
#include "strlist.h"
+#include "header.h"
#include <elf.h>
#include <limits.h>
@@ -33,7 +34,9 @@ struct symbol_conf symbol_conf = {
.try_vmlinux_path = true,
.annotate_src = true,
.demangle = true,
+ .demangle_kernel = false,
.cumulate_callchain = true,
+ .show_hist_headers = true,
.symfs = "",
};
@@ -341,6 +344,16 @@ static struct symbol *symbols__first(struct rb_root *symbols)
return NULL;
}
+static struct symbol *symbols__next(struct symbol *sym)
+{
+ struct rb_node *n = rb_next(&sym->rb_node);
+
+ if (n)
+ return rb_entry(n, struct symbol, rb_node);
+
+ return NULL;
+}
+
struct symbol_name_rb_node {
struct rb_node rb_node;
struct symbol sym;
@@ -411,11 +424,16 @@ struct symbol *dso__find_symbol(struct dso *dso,
return symbols__find(&dso->symbols[type], addr);
}
-static struct symbol *dso__first_symbol(struct dso *dso, enum map_type type)
+struct symbol *dso__first_symbol(struct dso *dso, enum map_type type)
{
return symbols__first(&dso->symbols[type]);
}
+struct symbol *dso__next_symbol(struct symbol *sym)
+{
+ return symbols__next(sym);
+}
+
struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
const char *name)
{
@@ -507,10 +525,15 @@ struct process_kallsyms_args {
struct dso *dso;
};
+/*
+ * These are symbols in the kernel image, so make sure that
+ * sym is from a kernel DSO.
+ */
bool symbol__is_idle(struct symbol *sym)
{
const char * const idle_symbols[] = {
"cpu_idle",
+ "cpu_startup_entry",
"intel_idle",
"default_idle",
"native_safe_halt",
@@ -1064,6 +1087,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
&is_64_bit);
if (err)
goto out_err;
+ dso->is_64_bit = is_64_bit;
if (list_empty(&md.maps)) {
err = -EINVAL;
@@ -1451,8 +1475,7 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
if (vmlinux[0] == '/')
snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s", vmlinux);
else
- snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s%s",
- symbol_conf.symfs, vmlinux);
+ symbol__join_symfs(symfs_vmlinux, vmlinux);
if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
symtab_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
@@ -1662,6 +1685,7 @@ do_kallsyms:
free(kallsyms_allocated_filename);
if (err > 0 && !dso__is_kcore(dso)) {
+ dso->binary_type = DSO_BINARY_TYPE__KALLSYMS;
dso__set_long_name(dso, "[kernel.kallsyms]", false);
map__fixup_start(map);
map__fixup_end(map);
@@ -1709,6 +1733,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
if (err > 0)
pr_debug("Using %s for symbols\n", kallsyms_filename);
if (err > 0 && !dso__is_kcore(dso)) {
+ dso->binary_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
machine__mmap_name(machine, path, sizeof(path));
dso__set_long_name(dso, strdup(path), true);
map__fixup_start(map);
@@ -1726,12 +1751,13 @@ static void vmlinux_path__exit(void)
zfree(&vmlinux_path);
}
-static int vmlinux_path__init(void)
+static int vmlinux_path__init(struct perf_session_env *env)
{
struct utsname uts;
char bf[PATH_MAX];
+ char *kernel_version;
- vmlinux_path = malloc(sizeof(char *) * 5);
+ vmlinux_path = malloc(sizeof(char *) * 6);
if (vmlinux_path == NULL)
return -1;
@@ -1744,25 +1770,37 @@ static int vmlinux_path__init(void)
goto out_fail;
++vmlinux_path__nr_entries;
- /* only try running kernel version if no symfs was given */
+ /* only try kernel version if no symfs was given */
if (symbol_conf.symfs[0] != 0)
return 0;
- if (uname(&uts) < 0)
- return -1;
+ if (env) {
+ kernel_version = env->os_release;
+ } else {
+ if (uname(&uts) < 0)
+ goto out_fail;
- snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", uts.release);
+ kernel_version = uts.release;
+ }
+
+ snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", kernel_version);
vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
goto out_fail;
++vmlinux_path__nr_entries;
- snprintf(bf, sizeof(bf), "/lib/modules/%s/build/vmlinux", uts.release);
+ snprintf(bf, sizeof(bf), "/usr/lib/debug/boot/vmlinux-%s",
+ kernel_version);
+ vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
+ if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
+ goto out_fail;
+ ++vmlinux_path__nr_entries;
+ snprintf(bf, sizeof(bf), "/lib/modules/%s/build/vmlinux", kernel_version);
vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
goto out_fail;
++vmlinux_path__nr_entries;
snprintf(bf, sizeof(bf), "/usr/lib/debug/lib/modules/%s/vmlinux",
- uts.release);
+ kernel_version);
vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
goto out_fail;
@@ -1808,7 +1846,7 @@ static bool symbol__read_kptr_restrict(void)
return value;
}
-int symbol__init(void)
+int symbol__init(struct perf_session_env *env)
{
const char *symfs;
@@ -1823,7 +1861,7 @@ int symbol__init(void)
symbol_conf.priv_size += (sizeof(struct symbol_name_rb_node) -
sizeof(struct symbol));
- if (symbol_conf.try_vmlinux_path && vmlinux_path__init() < 0)
+ if (symbol_conf.try_vmlinux_path && vmlinux_path__init(env) < 0)
return -1;
if (symbol_conf.field_sep && *symbol_conf.field_sep == '.') {
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 615c752dd767..bec4b7bd09de 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -13,6 +13,7 @@
#include <libgen.h>
#include "build-id.h"
#include "event.h"
+#include "util.h"
#ifdef HAVE_LIBELF_SUPPORT
#include <libelf.h>
@@ -59,6 +60,7 @@ extern Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
#endif
#ifndef DMGL_PARAMS
+#define DMGL_NO_OPTS 0 /* For readability... */
#define DMGL_PARAMS (1 << 0) /* Include function args */
#define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */
#endif
@@ -118,7 +120,9 @@ struct symbol_conf {
annotate_src,
event_group,
demangle,
- filter_relative;
+ demangle_kernel,
+ filter_relative,
+ show_hist_headers;
const char *vmlinux_name,
*kallsyms_name,
*source_prefix,
@@ -142,6 +146,14 @@ struct symbol_conf {
};
extern struct symbol_conf symbol_conf;
+
+static inline int __symbol__join_symfs(char *bf, size_t size, const char *path)
+{
+ return path__join(bf, size, symbol_conf.symfs, path);
+}
+
+#define symbol__join_symfs(bf, path) __symbol__join_symfs(bf, sizeof(bf), path)
+
extern int vmlinux_path__nr_entries;
extern char **vmlinux_path;
@@ -215,6 +227,7 @@ struct symsrc {
GElf_Shdr dynshdr;
bool adjust_symbols;
+ bool is_64_bit;
#endif
};
@@ -238,6 +251,11 @@ struct symbol *dso__find_symbol(struct dso *dso, enum map_type type,
struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
const char *name);
+struct symbol *dso__first_symbol(struct dso *dso, enum map_type type);
+struct symbol *dso__next_symbol(struct symbol *sym);
+
+enum dso_type dso__type_fd(int fd);
+
int filename__read_build_id(const char *filename, void *bf, size_t size);
int sysfs__read_build_id(const char *filename, void *bf, size_t size);
int modules__parse(const char *filename, void *arg,
@@ -246,7 +264,8 @@ int modules__parse(const char *filename, void *arg,
int filename__read_debuglink(const char *filename, char *debuglink,
size_t size);
-int symbol__init(void);
+struct perf_session_env;
+int symbol__init(struct perf_session_env *env);
void symbol__exit(void);
void symbol__elf_init(void);
struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 2fde0d5e40b5..a9df7f2c6dc9 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -13,7 +13,7 @@ int thread__init_map_groups(struct thread *thread, struct machine *machine)
struct thread *leader;
pid_t pid = thread->pid_;
- if (pid == thread->tid) {
+ if (pid == thread->tid || pid == -1) {
thread->mg = map_groups__new();
} else {
leader = machine__findnew_thread(machine, pid, pid);
@@ -34,6 +34,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
thread->pid_ = pid;
thread->tid = tid;
thread->ppid = -1;
+ thread->cpu = -1;
INIT_LIST_HEAD(&thread->comm_list);
comm_str = malloc(32);
@@ -41,7 +42,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
goto err_thread;
snprintf(comm_str, 32, ":%d", tid);
- comm = comm__new(comm_str, 0);
+ comm = comm__new(comm_str, 0, false);
free(comm_str);
if (!comm)
goto err_thread;
@@ -60,8 +61,10 @@ void thread__delete(struct thread *thread)
{
struct comm *comm, *tmp;
- map_groups__put(thread->mg);
- thread->mg = NULL;
+ if (thread->mg) {
+ map_groups__put(thread->mg);
+ thread->mg = NULL;
+ }
list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) {
list_del(&comm->list);
comm__free(comm);
@@ -78,19 +81,33 @@ struct comm *thread__comm(const struct thread *thread)
return list_first_entry(&thread->comm_list, struct comm, list);
}
+struct comm *thread__exec_comm(const struct thread *thread)
+{
+ struct comm *comm, *last = NULL;
+
+ list_for_each_entry(comm, &thread->comm_list, list) {
+ if (comm->exec)
+ return comm;
+ last = comm;
+ }
+
+ return last;
+}
+
/* CHECKME: time should always be 0 if event aren't ordered */
-int thread__set_comm(struct thread *thread, const char *str, u64 timestamp)
+int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp,
+ bool exec)
{
struct comm *new, *curr = thread__comm(thread);
int err;
/* Override latest entry if it had no specific time coverage */
- if (!curr->start) {
- err = comm__override(curr, str, timestamp);
+ if (!curr->start && !curr->exec) {
+ err = comm__override(curr, str, timestamp, exec);
if (err)
return err;
} else {
- new = comm__new(str, timestamp);
+ new = comm__new(str, timestamp, exec);
if (!new)
return -ENOMEM;
list_add(&new->list, &thread->comm_list);
@@ -127,12 +144,12 @@ int thread__comm_len(struct thread *thread)
size_t thread__fprintf(struct thread *thread, FILE *fp)
{
return fprintf(fp, "Thread %d %s\n", thread->tid, thread__comm_str(thread)) +
- map_groups__fprintf(thread->mg, verbose, fp);
+ map_groups__fprintf(thread->mg, fp);
}
void thread__insert_map(struct thread *thread, struct map *map)
{
- map_groups__fixup_overlappings(thread->mg, map, verbose, stderr);
+ map_groups__fixup_overlappings(thread->mg, map, stderr);
map_groups__insert(thread->mg, map);
}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 3c0c2724f82c..8c75fa774706 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -17,6 +17,7 @@ struct thread {
pid_t pid_; /* Not all tools update this */
pid_t tid;
pid_t ppid;
+ int cpu;
char shortname[3];
bool comm_set;
bool dead; /* if set thread has exited */
@@ -37,9 +38,17 @@ static inline void thread__exited(struct thread *thread)
thread->dead = true;
}
-int thread__set_comm(struct thread *thread, const char *comm, u64 timestamp);
+int __thread__set_comm(struct thread *thread, const char *comm, u64 timestamp,
+ bool exec);
+static inline int thread__set_comm(struct thread *thread, const char *comm,
+ u64 timestamp)
+{
+ return __thread__set_comm(thread, comm, timestamp, false);
+}
+
int thread__comm_len(struct thread *thread);
struct comm *thread__comm(const struct thread *thread);
+struct comm *thread__exec_comm(const struct thread *thread);
const char *thread__comm_str(const struct thread *thread);
void thread__insert_map(struct thread *thread, struct map *map);
int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 4385816d3d49..f11636966a0f 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -40,7 +40,7 @@ struct perf_tool {
event_op2 tracing_data;
event_op2 finished_round,
build_id;
- bool ordered_samples;
+ bool ordered_events;
bool ordering_requires_timestamps;
};
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index 7e6fcfe8b438..eb72716017ac 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -40,6 +40,7 @@
#include "trace-event.h"
#include <api/fs/debugfs.h>
#include "evsel.h"
+#include "debug.h"
#define VERSION "0.5"
@@ -191,12 +192,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps)
strcmp(dent->d_name, "..") == 0 ||
!name_in_tp_list(dent->d_name, tps))
continue;
- format = malloc(strlen(sys) + strlen(dent->d_name) + 10);
- if (!format) {
+ if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) {
err = -ENOMEM;
goto out;
}
- sprintf(format, "%s/%s/format", sys, dent->d_name);
ret = stat(format, &st);
free(format);
if (ret < 0)
@@ -217,12 +216,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps)
strcmp(dent->d_name, "..") == 0 ||
!name_in_tp_list(dent->d_name, tps))
continue;
- format = malloc(strlen(sys) + strlen(dent->d_name) + 10);
- if (!format) {
+ if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) {
err = -ENOMEM;
goto out;
}
- sprintf(format, "%s/%s/format", sys, dent->d_name);
ret = stat(format, &st);
if (ret >= 0) {
@@ -317,12 +314,10 @@ static int record_event_files(struct tracepoint_path *tps)
strcmp(dent->d_name, "ftrace") == 0 ||
!system_in_tp_list(dent->d_name, tps))
continue;
- sys = malloc(strlen(path) + strlen(dent->d_name) + 2);
- if (!sys) {
+ if (asprintf(&sys, "%s/%s", path, dent->d_name) < 0) {
err = -ENOMEM;
goto out;
}
- sprintf(sys, "%s/%s", path, dent->d_name);
ret = stat(sys, &st);
if (ret >= 0) {
ssize_t size = strlen(dent->d_name) + 1;
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index e113e180c48f..54d9e9b548a8 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -22,7 +22,6 @@
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
-#include <getopt.h>
#include <stdarg.h>
#include <sys/types.h>
#include <sys/stat.h>
@@ -36,6 +35,7 @@
#include "../perf.h"
#include "util.h"
#include "trace-event.h"
+#include "debug.h"
static int input_fd;
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index 57aaccc1692e..5c9bdd1591a9 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -30,6 +30,11 @@
struct scripting_context *scripting_context;
+static int flush_script_unsupported(void)
+{
+ return 0;
+}
+
static int stop_script_unsupported(void)
{
return 0;
@@ -74,6 +79,7 @@ static int python_generate_script_unsupported(struct pevent *pevent
struct scripting_ops python_scripting_unsupported_ops = {
.name = "Python",
.start_script = python_start_script_unsupported,
+ .flush_script = flush_script_unsupported,
.stop_script = stop_script_unsupported,
.process_event = process_event_unsupported,
.generate_script = python_generate_script_unsupported,
@@ -137,6 +143,7 @@ static int perl_generate_script_unsupported(struct pevent *pevent
struct scripting_ops perl_scripting_unsupported_ops = {
.name = "Perl",
.start_script = perl_start_script_unsupported,
+ .flush_script = flush_script_unsupported,
.stop_script = stop_script_unsupported,
.process_event = process_event_unsupported,
.generate_script = perl_generate_script_unsupported,
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 7b6d68688327..52aaa19e1eb1 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -64,6 +64,7 @@ struct perf_session;
struct scripting_ops {
const char *name;
int (*start_script) (const char *script, int argc, const char **argv);
+ int (*flush_script) (void);
int (*stop_script) (void);
void (*process_event) (union perf_event *event,
struct perf_sample *sample,
diff --git a/tools/perf/util/tsc.c b/tools/perf/util/tsc.c
new file mode 100644
index 000000000000..4d4210d4e13d
--- /dev/null
+++ b/tools/perf/util/tsc.c
@@ -0,0 +1,30 @@
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+#include "tsc.h"
+
+u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc)
+{
+ u64 t, quot, rem;
+
+ t = ns - tc->time_zero;
+ quot = t / tc->time_mult;
+ rem = t % tc->time_mult;
+ return (quot << tc->time_shift) +
+ (rem << tc->time_shift) / tc->time_mult;
+}
+
+u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc)
+{
+ u64 quot, rem;
+
+ quot = cyc >> tc->time_shift;
+ rem = cyc & ((1 << tc->time_shift) - 1);
+ return tc->time_zero + quot * tc->time_mult +
+ ((rem * tc->time_mult) >> tc->time_shift);
+}
+
+u64 __weak rdtsc(void)
+{
+ return 0;
+}
diff --git a/tools/perf/util/tsc.h b/tools/perf/util/tsc.h
new file mode 100644
index 000000000000..a8b78f1b3243
--- /dev/null
+++ b/tools/perf/util/tsc.h
@@ -0,0 +1,12 @@
+#ifndef __PERF_TSC_H
+#define __PERF_TSC_H
+
+#include <linux/types.h>
+
+#include "../arch/x86/util/tsc.h"
+
+u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc);
+u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc);
+u64 rdtsc(void);
+
+#endif
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 5ec80a575b50..7419768c38b1 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -3,6 +3,7 @@
#include <elfutils/libdwfl.h>
#include <inttypes.h>
#include <errno.h>
+#include "debug.h"
#include "unwind.h"
#include "unwind-libdw.h"
#include "machine.h"
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 25578b98f5c5..92b56db52471 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -30,6 +30,7 @@
#include "unwind.h"
#include "symbol.h"
#include "util.h"
+#include "debug.h"
extern int
UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 95aefa78bb07..24e8d871b74e 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -1,5 +1,6 @@
#include "../perf.h"
#include "util.h"
+#include "debug.h"
#include <api/fs/fs.h>
#include <sys/mman.h>
#ifdef HAVE_BACKTRACE_SUPPORT
@@ -12,6 +13,7 @@
#include <limits.h>
#include <byteswap.h>
#include <linux/kernel.h>
+#include <unistd.h>
/*
* XXX We need to find a better place for these things...
@@ -281,6 +283,18 @@ void get_term_dimensions(struct winsize *ws)
ws->ws_col = 80;
}
+void set_term_quiet_input(struct termios *old)
+{
+ struct termios tc;
+
+ tcgetattr(0, old);
+ tc = *old;
+ tc.c_lflag &= ~(ICANON | ECHO);
+ tc.c_cc[VMIN] = 0;
+ tc.c_cc[VTIME] = 0;
+ tcsetattr(0, TCSANOW, &tc);
+}
+
static void set_tracing_events_path(const char *mountpoint)
{
snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s",
@@ -333,12 +347,9 @@ const char *find_tracing_dir(void)
if (!debugfs)
return NULL;
- tracing = malloc(strlen(debugfs) + 9);
- if (!tracing)
+ if (asprintf(&tracing, "%s/tracing", debugfs) < 0)
return NULL;
- sprintf(tracing, "%s/tracing", debugfs);
-
tracing_found = 1;
return tracing;
}
@@ -352,11 +363,9 @@ char *get_tracing_file(const char *name)
if (!tracing)
return NULL;
- file = malloc(strlen(tracing) + strlen(name) + 2);
- if (!file)
+ if (asprintf(&file, "%s/%s", tracing, name) < 0)
return NULL;
- sprintf(file, "%s/%s", tracing, name);
return file;
}
@@ -447,6 +456,7 @@ int filename__read_str(const char *filename, char **buf, size_t *sizep)
size_t size = 0, alloc_size = 0;
void *bf = NULL, *nbf;
int fd, n, err = 0;
+ char sbuf[STRERR_BUFSIZE];
fd = open(filename, O_RDONLY);
if (fd < 0)
@@ -467,8 +477,8 @@ int filename__read_str(const char *filename, char **buf, size_t *sizep)
n = read(fd, bf + size, alloc_size - size);
if (n < 0) {
if (size) {
- pr_warning("read failed %d: %s\n",
- errno, strerror(errno));
+ pr_warning("read failed %d: %s\n", errno,
+ strerror_r(errno, sbuf, sizeof(sbuf)));
err = 0;
} else
err = -errno;
@@ -540,3 +550,39 @@ void mem_bswap_64(void *src, int byte_size)
++m;
}
}
+
+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 -1;
+
+ /* 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;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 66864364ccb4..80bfdaa0e2a4 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -39,6 +39,8 @@
#define _ALL_SOURCE 1
#define _BSD_SOURCE 1
+/* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */
+#define _DEFAULT_SOURCE 1
#define HAS_BOOL
#include <unistd.h>
@@ -64,16 +66,18 @@
#include <regex.h>
#include <utime.h>
#include <sys/wait.h>
-#include <sys/poll.h>
+#include <poll.h>
#include <sys/socket.h>
#include <sys/ioctl.h>
#include <inttypes.h>
+#include <linux/kernel.h>
#include <linux/magic.h>
#include <linux/types.h>
#include <sys/ttydefaults.h>
#include <api/fs/debugfs.h>
#include <termios.h>
#include <linux/bitops.h>
+#include <termios.h>
extern const char *graph_line;
extern const char *graph_dotted_line;
@@ -307,6 +311,7 @@ extern unsigned int page_size;
extern int cacheline_size;
void get_term_dimensions(struct winsize *ws);
+void set_term_quiet_input(struct termios *old);
struct parse_tag {
char tag;
@@ -317,6 +322,21 @@ unsigned long parse_tag_value(const char *str, struct parse_tag *tags);
#define SRCLINE_UNKNOWN ((char *) "??:0")
+static inline int path__join(char *bf, size_t size,
+ const char *path1, const char *path2)
+{
+ return scnprintf(bf, size, "%s%s%s", path1, path1[0] ? "/" : "", path2);
+}
+
+static inline int path__join3(char *bf, size_t size,
+ const char *path1, const char *path2,
+ const char *path3)
+{
+ return scnprintf(bf, size, "%s%s%s%s%s",
+ path1, path1[0] ? "/" : "",
+ path2, path2[0] ? "/" : "", path3);
+}
+
struct dso;
char *get_srcline(struct dso *dso, unsigned long addr);
@@ -330,4 +350,5 @@ void mem_bswap_64(void *src, int byte_size);
void mem_bswap_32(void *src, int byte_size);
const char *get_filename_for_perf_kvm(void);
+bool find_process(const char *name);
#endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 0ddb3b8a89ec..adca69384fcc 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -11,10 +11,34 @@
#include "vdso.h"
#include "util.h"
#include "symbol.h"
+#include "machine.h"
#include "linux/string.h"
+#include "debug.h"
-static bool vdso_found;
-static char vdso_file[] = "/tmp/perf-vdso.so-XXXXXX";
+#define VDSO__TEMP_FILE_NAME "/tmp/perf-vdso.so-XXXXXX"
+
+struct vdso_file {
+ bool found;
+ bool error;
+ char temp_file_name[sizeof(VDSO__TEMP_FILE_NAME)];
+ const char *dso_name;
+};
+
+struct vdso_info {
+ struct vdso_file vdso;
+};
+
+static struct vdso_info *vdso_info__new(void)
+{
+ static const struct vdso_info vdso_info_init = {
+ .vdso = {
+ .temp_file_name = VDSO__TEMP_FILE_NAME,
+ .dso_name = DSO__NAME_VDSO,
+ },
+ };
+
+ return memdup(&vdso_info_init, sizeof(vdso_info_init));
+}
static int find_vdso_map(void **start, void **end)
{
@@ -47,7 +71,7 @@ static int find_vdso_map(void **start, void **end)
return !found;
}
-static char *get_file(void)
+static char *get_file(struct vdso_file *vdso_file)
{
char *vdso = NULL;
char *buf = NULL;
@@ -55,10 +79,10 @@ static char *get_file(void)
size_t size;
int fd;
- if (vdso_found)
- return vdso_file;
+ if (vdso_file->found)
+ return vdso_file->temp_file_name;
- if (find_vdso_map(&start, &end))
+ if (vdso_file->error || find_vdso_map(&start, &end))
return NULL;
size = end - start;
@@ -67,45 +91,78 @@ static char *get_file(void)
if (!buf)
return NULL;
- fd = mkstemp(vdso_file);
+ fd = mkstemp(vdso_file->temp_file_name);
if (fd < 0)
goto out;
if (size == (size_t) write(fd, buf, size))
- vdso = vdso_file;
+ vdso = vdso_file->temp_file_name;
close(fd);
out:
free(buf);
- vdso_found = (vdso != NULL);
+ vdso_file->found = (vdso != NULL);
+ vdso_file->error = !vdso_file->found;
return vdso;
}
-void vdso__exit(void)
+void vdso__exit(struct machine *machine)
{
- if (vdso_found)
- unlink(vdso_file);
+ struct vdso_info *vdso_info = machine->vdso_info;
+
+ if (!vdso_info)
+ return;
+
+ if (vdso_info->vdso.found)
+ unlink(vdso_info->vdso.temp_file_name);
+
+ zfree(&machine->vdso_info);
}
-struct dso *vdso__dso_findnew(struct list_head *head)
+static struct dso *vdso__new(struct machine *machine, const char *short_name,
+ const char *long_name)
{
- struct dso *dso = dsos__find(head, VDSO__MAP_NAME, true);
+ struct dso *dso;
+ dso = dso__new(short_name);
+ if (dso != NULL) {
+ dsos__add(&machine->user_dsos, dso);
+ dso__set_long_name(dso, long_name, false);
+ }
+
+ return dso;
+}
+
+struct dso *vdso__dso_findnew(struct machine *machine,
+ struct thread *thread __maybe_unused)
+{
+ struct vdso_info *vdso_info;
+ struct dso *dso;
+
+ if (!machine->vdso_info)
+ machine->vdso_info = vdso_info__new();
+
+ vdso_info = machine->vdso_info;
+ if (!vdso_info)
+ return NULL;
+
+ dso = dsos__find(&machine->user_dsos, DSO__NAME_VDSO, true);
if (!dso) {
char *file;
- file = get_file();
+ file = get_file(&vdso_info->vdso);
if (!file)
return NULL;
- dso = dso__new(VDSO__MAP_NAME);
- if (dso != NULL) {
- dsos__add(head, dso);
- dso__set_long_name(dso, file, false);
- }
+ dso = vdso__new(machine, DSO__NAME_VDSO, file);
}
return dso;
}
+
+bool dso__is_vdso(struct dso *dso)
+{
+ return !strcmp(dso->short_name, DSO__NAME_VDSO);
+}
diff --git a/tools/perf/util/vdso.h b/tools/perf/util/vdso.h
index 0f76e7caf6f8..af9d6929a215 100644
--- a/tools/perf/util/vdso.h
+++ b/tools/perf/util/vdso.h
@@ -7,12 +7,21 @@
#define VDSO__MAP_NAME "[vdso]"
+#define DSO__NAME_VDSO "[vdso]"
+
static inline bool is_vdso_map(const char *filename)
{
return !strcmp(filename, VDSO__MAP_NAME);
}
-struct dso *vdso__dso_findnew(struct list_head *head);
-void vdso__exit(void);
+struct dso;
+
+bool dso__is_vdso(struct dso *dso);
+
+struct machine;
+struct thread;
+
+struct dso *vdso__dso_findnew(struct machine *machine, struct thread *thread);
+void vdso__exit(struct machine *machine);
#endif /* __PERF_VDSO__ */