diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-11-03 18:13:43 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-11-03 18:13:43 -0700 |
commit | 01897f3e05ede4d66c0f9df465fde1d67a1d733f (patch) | |
tree | 3c0f1e0fb8bc352e6821d16e46f335484cc3868a /tools/perf | |
parent | e9ebc2151f88600e726e51e5f7ca9c33ad53b35f (diff) | |
parent | 29995d296e3e9ce4f9767963ecbef143ade26c36 (diff) |
Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates and fixes from Ingo Molnar:
"These are almost all tooling updates: 'perf top', 'perf trace' and
'perf script' fixes and updates, an UAPI header sync with the merge
window versions, license marker updates, much improved Sparc support
from David Miller, and a number of fixes"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (66 commits)
perf intel-pt/bts: Calculate cpumode for synthesized samples
perf intel-pt: Insert callchain context into synthesized callchains
perf tools: Don't clone maps from parent when synthesizing forks
perf top: Start display thread earlier
tools headers uapi: Update linux/if_link.h header copy
tools headers uapi: Update linux/netlink.h header copy
tools headers: Sync the various kvm.h header copies
tools include uapi: Update linux/mmap.h copy
perf trace beauty: Use the mmap flags table generated from headers
perf beauty: Wire up the mmap flags table generator to the Makefile
perf beauty: Add a generator for MAP_ mmap's flag constants
tools include uapi: Update asound.h copy
tools arch uapi: Update asm-generic/unistd.h and arm64 unistd.h copies
tools include uapi: Update linux/fs.h copy
perf callchain: Honour the ordering of PERF_CONTEXT_{USER,KERNEL,etc}
perf cs-etm: Correct CPU mode for samples
perf unwind: Take pgoff into account when reporting elf to libdwfl
perf top: Do not use overwrite mode by default
perf top: Allow disabling the overwrite mode
perf trace: Beautify mount's first pathname arg
...
Diffstat (limited to 'tools/perf')
86 files changed, 3165 insertions, 531 deletions
diff --git a/tools/perf/Documentation/build-xed.txt b/tools/perf/Documentation/build-xed.txt new file mode 100644 index 000000000000..6222c1e7231f --- /dev/null +++ b/tools/perf/Documentation/build-xed.txt @@ -0,0 +1,19 @@ + +For --xed the xed tool is needed. Here is how to install it: + + $ git clone https://github.com/intelxed/mbuild.git mbuild + $ git clone https://github.com/intelxed/xed + $ cd xed + $ ./mfile.py --share + $ ./mfile.py examples + $ sudo ./mfile.py --prefix=/usr/local install + $ sudo ldconfig + $ sudo cp obj/examples/xed /usr/local/bin + +Basic xed testing: + + $ xed | head -3 + ERROR: required argument(s) were missing + Copyright (C) 2017, Intel Corporation. All rights reserved. + XED version: [v10.0-328-g7d62c8c49b7b] + $ diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt index 76971d2e4164..115eaacc455f 100644 --- a/tools/perf/Documentation/intel-pt.txt +++ b/tools/perf/Documentation/intel-pt.txt @@ -106,7 +106,7 @@ in transaction, respectively. While it is possible to create scripts to analyze the data, an alternative approach is available to export the data to a sqlite or postgresql database. Refer to script export-to-sqlite.py or export-to-postgresql.py for more details, -and to script call-graph-from-sql.py for an example of using the database. +and to script exported-sql-viewer.py for an example of using the database. There is also script intel-pt-events.py which provides an example of how to unpack the raw data for power events and PTWRITE. diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt index a3abe04c779d..c2182cbabde3 100644 --- a/tools/perf/Documentation/itrace.txt +++ b/tools/perf/Documentation/itrace.txt @@ -11,10 +11,11 @@ l synthesize last branch entries (use with i or x) s skip initial number of events - The default is all events i.e. the same as --itrace=ibxwpe + The default is all events i.e. the same as --itrace=ibxwpe, + except for perf script where it is --itrace=ce - In addition, the period (default 100000) for instructions events - can be specified in units of: + In addition, the period (default 100000, except for perf script where it is 1) + for instructions events can be specified in units of: i instructions t ticks diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index afdafe2110a1..a2b37ce48094 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -383,6 +383,24 @@ include::itrace.txt[] will be printed. Each entry has function name and file/line. Enabled by default, disable with --no-inline. +--insn-trace:: + Show instruction stream for intel_pt traces. Combine with --xed to + show disassembly. + +--xed:: + Run xed disassembler on output. Requires installing the xed disassembler. + +--call-trace:: + Show call stream for intel_pt traces. The CPUs are interleaved, but + can be filtered with -C. + +--call-ret-trace:: + Show call and return stream for intel_pt traces. + +--graph-function:: + For itrace only show specified functions and their callees for + itrace. Multiple functions can be separated by comma. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-script-perl[1], diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 114fda12aa49..808b664343c9 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -242,6 +242,16 @@ Default is to monitor all CPUS. --hierarchy:: Enable hierarchy output. +--overwrite:: + Enable this to use just the most recent records, which helps in high core count + machines such as Knights Landing/Mill, but right now is disabled by default as + the pausing used in this technique is leading to loss of metadata events such + as PERF_RECORD_MMAP which makes 'perf top' unable to resolve samples, leading + to lots of unknown samples appearing on the UI. Enable this if you are in such + machines and profiling a workload that doesn't creates short lived threads and/or + doesn't uses many executable mmap operations. Work is being planed to solve + this situation, till then, this will remain disabled by default. + --force:: Don't do ownership validation. diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index 115db9e06ecd..e113450503d2 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -171,6 +171,11 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs. --kernel-syscall-graph:: Show the kernel callchains on the syscall exit path. +--max-events=N:: + Stop after processing N events. Note that strace-like events are considered + only at exit time or when a syscall is interrupted, i.e. in those cases this + option is equivalent to the number of lines printed. + --max-stack:: Set the stack depth limit when parsing the callchain, anything beyond the specified depth will be ignored. Note that at this point @@ -238,6 +243,68 @@ Trace syscalls, major and minor pagefaults: As you can see, there was major pagefault in python process, from CRYPTO_push_info_ routine which faulted somewhere in libcrypto.so. +Trace the first 4 open, openat or open_by_handle_at syscalls (in the future more syscalls may match here): + + $ perf trace -e open* --max-events 4 + [root@jouet perf]# trace -e open* --max-events 4 + 2272.992 ( 0.037 ms): gnome-shell/1370 openat(dfd: CWD, filename: /proc/self/stat) = 31 + 2277.481 ( 0.139 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65 + 3026.398 ( 0.076 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65 + 4294.665 ( 0.015 ms): sed/15879 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3 + $ + +Trace the first minor page fault when running a workload: + + # perf trace -F min --max-stack=7 --max-events 1 sleep 1 + 0.000 ( 0.000 ms): sleep/18006 minfault [__clear_user+0x1a] => 0x5626efa56080 (?k) + __clear_user ([kernel.kallsyms]) + load_elf_binary ([kernel.kallsyms]) + search_binary_handler ([kernel.kallsyms]) + __do_execve_file.isra.33 ([kernel.kallsyms]) + __x64_sys_execve ([kernel.kallsyms]) + do_syscall_64 ([kernel.kallsyms]) + entry_SYSCALL_64 ([kernel.kallsyms]) + # + +Trace the next min page page fault to take place on the first CPU: + + # perf trace -F min --call-graph=dwarf --max-events 1 --cpu 0 + 0.000 ( 0.000 ms): Web Content/17136 minfault [js::gc::Chunk::fetchNextDecommittedArena+0x4b] => 0x7fbe6181b000 (?.) + js::gc::FreeSpan::initAsEmpty (inlined) + js::gc::Arena::setAsNotAllocated (inlined) + js::gc::Chunk::fetchNextDecommittedArena (/usr/lib64/firefox/libxul.so) + js::gc::Chunk::allocateArena (/usr/lib64/firefox/libxul.so) + js::gc::GCRuntime::allocateArena (/usr/lib64/firefox/libxul.so) + js::gc::ArenaLists::allocateFromArena (/usr/lib64/firefox/libxul.so) + js::gc::GCRuntime::tryNewTenuredThing<JSString, (js::AllowGC)1> (inlined) + js::AllocateString<JSString, (js::AllowGC)1> (/usr/lib64/firefox/libxul.so) + js::Allocate<JSThinInlineString, (js::AllowGC)1> (inlined) + JSThinInlineString::new_<(js::AllowGC)1> (inlined) + AllocateInlineString<(js::AllowGC)1, unsigned char> (inlined) + js::ConcatStrings<(js::AllowGC)1> (/usr/lib64/firefox/libxul.so) + [0x18b26e6bc2bd] (/tmp/perf-17136.map) + # + +Trace the next two sched:sched_switch events, four block:*_plug events, the +next block:*_unplug and the next three net:*dev_queue events, this last one +with a backtrace of at most 16 entries, system wide: + + # perf trace -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/ + 0.000 :0/0 sched:sched_switch:swapper/2:0 [120] S ==> rcu_sched:10 [120] + 0.015 rcu_sched/10 sched:sched_switch:rcu_sched:10 [120] R ==> swapper/2:0 [120] + 254.198 irq/50-iwlwifi/680 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051f600 len=66 + __dev_queue_xmit ([kernel.kallsyms]) + 273.977 :0/0 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051f600 len=78 + __dev_queue_xmit ([kernel.kallsyms]) + 274.007 :0/0 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051ff00 len=78 + __dev_queue_xmit ([kernel.kallsyms]) + 2930.140 kworker/u16:58/2722 block:block_plug:[kworker/u16:58] + 2930.162 kworker/u16:58/2722 block:block_unplug:[kworker/u16:58] 1 + 4466.094 jbd2/dm-2-8/748 block:block_plug:[jbd2/dm-2-8] + 8050.123 kworker/u16:30/2694 block:block_plug:[kworker/u16:30] + 8050.271 kworker/u16:30/2694 block:block_plug:[kworker/u16:30] + # + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-script[1] diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 2f3bf025e305..3ccb4f0bf088 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -1,4 +1,5 @@ include ../scripts/Makefile.include +include ../scripts/Makefile.arch # The default target of this Makefile is... all: @@ -385,6 +386,8 @@ export INSTALL SHELL_PATH SHELL = $(SHELL_PATH) linux_uapi_dir := $(srctree)/tools/include/uapi/linux +asm_generic_uapi_dir := $(srctree)/tools/include/uapi/asm-generic +arch_asm_uapi_dir := $(srctree)/tools/arch/$(ARCH)/include/uapi/asm/ beauty_outdir := $(OUTPUT)trace/beauty/generated beauty_ioctl_outdir := $(beauty_outdir)/ioctl @@ -460,6 +463,18 @@ madvise_behavior_tbl := $(srctree)/tools/perf/trace/beauty/madvise_behavior.sh $(madvise_behavior_array): $(madvise_hdr_dir)/mman-common.h $(madvise_behavior_tbl) $(Q)$(SHELL) '$(madvise_behavior_tbl)' $(madvise_hdr_dir) > $@ +mmap_flags_array := $(beauty_outdir)/mmap_flags_array.c +mmap_flags_tbl := $(srctree)/tools/perf/trace/beauty/mmap_flags.sh + +$(mmap_flags_array): $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(arch_asm_uapi_dir)/mman.h $(mmap_flags_tbl) + $(Q)$(SHELL) '$(mmap_flags_tbl)' $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@ + +mount_flags_array := $(beauty_outdir)/mount_flags_array.c +mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/mount_flags.sh + +$(mount_flags_array): $(linux_uapi_dir)/fs.h $(mount_flags_tbl) + $(Q)$(SHELL) '$(mount_flags_tbl)' $(linux_uapi_dir) > $@ + prctl_option_array := $(beauty_outdir)/prctl_option_array.c prctl_hdr_dir := $(srctree)/tools/include/uapi/linux/ prctl_option_tbl := $(srctree)/tools/perf/trace/beauty/prctl_option.sh @@ -577,6 +592,8 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc $(socket_ipproto_array) \ $(vhost_virtio_ioctl_array) \ $(madvise_behavior_array) \ + $(mmap_flags_array) \ + $(mount_flags_array) \ $(perf_ioctl_array) \ $(prctl_option_array) \ $(arch_errno_name_array) @@ -863,6 +880,8 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea $(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \ $(OUTPUT)pmu-events/pmu-events.c \ $(OUTPUT)$(madvise_behavior_array) \ + $(OUTPUT)$(mmap_flags_array) \ + $(OUTPUT)$(mount_flags_array) \ $(OUTPUT)$(drm_ioctl_array) \ $(OUTPUT)$(pkey_alloc_access_rights_array) \ $(OUTPUT)$(sndrv_ctl_ioctl_array) \ diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl index 2dbb8cade048..c88fd32563eb 100755 --- a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl +++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl @@ -23,7 +23,7 @@ create_table_from_c() { local sc nr last_sc - create_table_exe=`mktemp /tmp/create-table-XXXXXX` + create_table_exe=`mktemp ${TMPDIR:-/tmp}/create-table-XXXXXX` { diff --git a/tools/perf/arch/sparc/Makefile b/tools/perf/arch/sparc/Makefile index 7fbca175099e..275dea7ff59a 100644 --- a/tools/perf/arch/sparc/Makefile +++ b/tools/perf/arch/sparc/Makefile @@ -1,3 +1,5 @@ ifndef NO_DWARF PERF_HAVE_DWARF_REGS := 1 endif + +PERF_HAVE_JITDUMP := 1 diff --git a/tools/perf/arch/sparc/annotate/instructions.c b/tools/perf/arch/sparc/annotate/instructions.c new file mode 100644 index 000000000000..2614c010c235 --- /dev/null +++ b/tools/perf/arch/sparc/annotate/instructions.c @@ -0,0 +1,169 @@ +// SPDX-License-Identifier: GPL-2.0 + +static int is_branch_cond(const char *cond) +{ + if (cond[0] == '\0') + return 1; + + if (cond[0] == 'a' && cond[1] == '\0') + return 1; + + if (cond[0] == 'c' && + (cond[1] == 'c' || cond[1] == 's') && + cond[2] == '\0') + return 1; + + if (cond[0] == |