1
linux/tools/perf
Linus Torvalds 654443e20d Merge branch 'perf-uprobes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull user-space probe instrumentation from Ingo Molnar:
 "The uprobes code originates from SystemTap and has been used for years
  in Fedora and RHEL kernels.  This version is much rewritten, reviews
  from PeterZ, Oleg and myself shaped the end result.

  This tree includes uprobes support in 'perf probe' - but SystemTap
  (and other tools) can take advantage of user probe points as well.

  Sample usage of uprobes via perf, for example to profile malloc()
  calls without modifying user-space binaries.

  First boot a new kernel with CONFIG_UPROBE_EVENT=y enabled.

  If you don't know which function you want to probe you can pick one
  from 'perf top' or can get a list all functions that can be probed
  within libc (binaries can be specified as well):

	$ perf probe -F -x /lib/libc.so.6

  To probe libc's malloc():

	$ perf probe -x /lib64/libc.so.6 malloc
	Added new event:
	probe_libc:malloc    (on 0x7eac0)

  You can now use it in all perf tools, such as:

	perf record -e probe_libc:malloc -aR sleep 1

  Make use of it to create a call graph (as the flat profile is going to
  look very boring):

	$ perf record -e probe_libc:malloc -gR make
	[ perf record: Woken up 173 times to write data ]
	[ perf record: Captured and wrote 44.190 MB perf.data (~1930712

	$ perf report | less

	  32.03%            git  libc-2.15.so   [.] malloc
	                    |
	                    --- malloc

	  29.49%            cc1  libc-2.15.so   [.] malloc
	                    |
	                    --- malloc
	                       |
	                       |--0.95%-- 0x208eb1000000000
	                       |
	                       |--0.63%-- htab_traverse_noresize

	  11.04%             as  libc-2.15.so   [.] malloc
	                     |
	                     --- malloc
	                        |

	   7.15%             ld  libc-2.15.so   [.] malloc
	                     |
	                     --- malloc
	                        |

	   5.07%             sh  libc-2.15.so   [.] malloc
	                     |
	                     --- malloc
	                        |
	   4.99%  python-config  libc-2.15.so   [.] malloc
	          |
	          --- malloc
	             |
	   4.54%           make  libc-2.15.so   [.] malloc
	                   |
	                   --- malloc
	                      |
	                      |--7.34%-- glob
	                      |          |
	                      |          |--93.18%-- 0x41588f
	                      |          |
	                      |           --6.82%-- glob
	                      |                     0x41588f

	   ...

  Or:

	$ perf report -g flat | less

	# Overhead        Command  Shared Object      Symbol
	# ........  .............  .............  ..........
	#
	  32.03%            git  libc-2.15.so   [.] malloc
	          27.19%
	              malloc

	  29.49%            cc1  libc-2.15.so   [.] malloc
	          24.77%
	              malloc

	  11.04%             as  libc-2.15.so   [.] malloc
	          11.02%
	              malloc

	   7.15%             ld  libc-2.15.so   [.] malloc
	           6.57%
	              malloc

	 ...

  The core uprobes design is fairly straightforward: uprobes probe
  points register themselves at (inode:offset) addresses of
  libraries/binaries, after which all existing (or new) vmas that map
  that address will have a software breakpoint injected at that address.
  vmas are COW-ed to preserve original content.  The probe points are
  kept in an rbtree.

  If user-space executes the probed inode:offset instruction address
  then an event is generated which can be recovered from the regular
  perf event channels and mmap-ed ring-buffer.

  Multiple probes at the same address are supported, they create a
  dynamic callback list of event consumers.

  The basic model is further complicated by the XOL speedup: the
  original instruction that is probed is copied (in an architecture
  specific fashion) and executed out of line when the probe triggers.
  The XOL area is a single vma per process, with a fixed number of
  entries (which limits probe execution parallelism).

  The API: uprobes are installed/removed via
  /sys/kernel/debug/tracing/uprobe_events, the API is integrated to
  align with the kprobes interface as much as possible, but is separate
  to it.

  Injecting a probe point is privileged operation, which can be relaxed
  by setting perf_paranoid to -1.

  You can use multiple probes as well and mix them with kprobes and
  regular PMU events or tracepoints, when instrumenting a task."

Fix up trivial conflicts in mm/memory.c due to previous cleanup of
unmap_single_vma().

* 'perf-uprobes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (21 commits)
  perf probe: Detect probe target when m/x options are absent
  perf probe: Provide perf interface for uprobes
  tracing: Fix kconfig warning due to a typo
  tracing: Provide trace events interface for uprobes
  tracing: Extract out common code for kprobes/uprobes trace events
  tracing: Modify is_delete, is_return from int to bool
  uprobes/core: Decrement uprobe count before the pages are unmapped
  uprobes/core: Make background page replacement logic account for rss_stat counters
  uprobes/core: Optimize probe hits with the help of a counter
  uprobes/core: Allocate XOL slots for uprobes use
  uprobes/core: Handle breakpoint and singlestep exceptions
  uprobes/core: Rename bkpt to swbp
  uprobes/core: Make order of function parameters consistent across functions
  uprobes/core: Make macro names consistent
  uprobes: Update copyright notices
  uprobes/core: Move insn to arch specific structure
  uprobes/core: Remove uprobe_opcode_sz
  uprobes/core: Make instruction tables volatile
  uprobes: Move to kernel/events/
  uprobes/core: Clean up, refactor and improve the code
  ...
2012-05-24 11:39:34 -07:00
..
arch perf tools: Use scnprintf where applicable 2012-03-14 12:36:19 -03:00
bench perf tool: Fix perf stack to non executable on x86_64 2012-02-06 19:14:17 -02:00
config perf report: Add a simple GTK2-based 'perf report' browser 2012-03-19 15:13:29 -03:00
Documentation Merge branch 'perf-uprobes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2012-05-24 11:39:34 -07:00
python perf python: Use attr.watermark in twatch.py 2012-01-30 18:38:23 -02:00
scripts
ui perf annotate browser: Add key bindings help window 2012-05-12 16:36:55 -03:00
util Merge branch 'perf-uprobes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2012-05-24 11:39:34 -07:00
.gitignore perf tools: Ignore auto-generated bison/flex files 2012-04-14 13:50:39 -03:00
builtin-annotate.c perf annotate: Get rid of field_sep check 2012-01-08 13:29:34 -02:00
builtin-bench.c perf bench: Also allow measuring memset() 2012-01-24 20:25:32 -02:00
builtin-buildid-cache.c
builtin-buildid-list.c perf buildid-list: Work better with pipe mode 2012-05-22 13:03:54 -03:00
builtin-diff.c perf diff: Fix to work with new hists design 2012-03-22 15:12:09 -03:00
builtin-evlist.c perf evlist: Show event attribute details 2012-05-22 14:30:11 -03:00
builtin-help.c
builtin-inject.c perf inject: Fix broken perf inject -b 2012-05-22 12:59:28 -03:00
builtin-kmem.c perf: Have perf use the new libtraceevent.a library 2012-04-25 13:28:48 +02:00
builtin-kvm.c perf kvm: Do guest-only counting by default 2012-01-06 15:47:37 -02:00
builtin-list.c
builtin-lock.c perf: Have perf use the new libtraceevent.a library 2012-04-25 13:28:48 +02:00
builtin-probe.c perf probe: Detect probe target when m/x options are absent 2012-05-11 13:58:53 -03:00
builtin-record.c perf tools: Bump default sample freq to 4 kHz 2012-05-22 13:14:18 -03:00
builtin-report.c Merge remote-tracking branch 'tip/perf/urgent' into perf/core 2012-05-18 13:13:33 -03:00
builtin-sched.c perf: Have perf use the new libtraceevent.a library 2012-04-25 13:28:48 +02:00
builtin-script.c perf: Have perf use the new libtraceevent.a library 2012-04-25 13:28:48 +02:00
builtin-stat.c Merge remote-tracking branch 'tip/perf/urgent' into perf/core 2012-05-18 13:13:33 -03:00
builtin-test.c perf test: Move parse event automated tests to separated object 2012-05-22 11:19:16 -03:00
builtin-timechart.c perf report: Accept fifos as input file 2011-12-23 17:01:03 -02:00
builtin-top.c perf tools: Bump default sample freq to 4 kHz 2012-05-22 13:14:18 -03:00
builtin.h
command-list.txt
CREDITS
design.txt
Makefile perf tools: Always try to build libtraceevent 2012-05-22 12:35:29 -03:00
MANIFEST perf tools: Fix out of tree compiles 2012-02-13 22:46:41 -02:00
perf-archive.sh perf archive: Correct cutting of symbolic link 2012-04-14 13:52:15 -03:00
perf.c
perf.h perf target: Split out perf_target handling code 2012-05-02 15:41:11 -03:00