Steven Rostedt [Tue, 15 Nov 2011 23:47:48 +0000 (18:47 -0500)]
tools lib traceevent: Add support for "%.*s" in bprintk events
The arg notation of '*' in bprintks is not handled by the parser.
Implement it so that they show up properly in the output and do not
kill the tracer from reporting events.
Steven Rostedt [Tue, 22 May 2012 05:45:21 +0000 (14:45 +0900)]
tools lib traceevent: Let filtering numbers by string use function names
As a pointer can be converted into a function name, let the filters
work with the function name as well as with the pointer number. If
the comparison expects a string, then convert numbers into functions,
but only when the number is the same size as a long.
perf bench: Fix confused variable namings and descriptions in mem subsystem
As Namhyung Kim pointed, there are confused namings and descriptions of words
"cycle" and "clock" in mem-memset.c and mem-memcpy.c.
With the option "-c" (or "--clock", now renamed as "--cycle"), mem subsystem
measures cost of memset() and memcpy() with cpu-cycles event.
But current mem subsystem source code contains lots of confused variable
namings and descriptions with "clock" (e.g. the variable use_clock). This is a
very bad style because there is another software event named "cpu-clock". This
patch replaces wrong usage of "clock" to "cycle".
v2: modified Documentation/perf-bench.txt for the descriptions of
--cycle option
Robert Richter [Thu, 14 Jun 2012 20:38:37 +0000 (22:38 +0200)]
perf tools: Fix generation of pmu list
The internal pmu list was never used. With each perf_pmu__find() call
the pmu structure was created new by parsing sysfs. Beside this it
caused memory leaks. We now keep all pmus by adding them to the list.
Also, pmu_lookup() should return pmus that do not expose the format
specifier in sysfs.
We need a valid internal pmu list in a later patch to iterate over all
pmus that exist in the system.
Signed-off-by: Robert Richter <robert.richter@amd.com> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1339706321-8802-3-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Namhyung Kim [Wed, 27 Jun 2012 00:41:41 +0000 (09:41 +0900)]
tools lib traceevent: Add support for __print_hex()
Since the __print_hex() function is used in print fmt now, add
corresponding parser routines. This makes the output of perf script on
the kvm_emulate_insn event not to fail any more.
before:
kvm_emulate_insn: [FAILED TO PARSE] rip=3238197797 ...
Namhyung Kim [Fri, 22 Jun 2012 08:10:15 +0000 (17:10 +0900)]
tools lib traceevent: Check string is really printable
When libtraceevent parses format fields, it assumes that array of 1 byte
is string but it's not always true. The kvm_emulate_insn contains 15 u8
array of insn that contains (binary) instructions. Thus when it's
printed, it'll have broken output like below:
Namhyung Kim [Fri, 22 Jun 2012 05:37:36 +0000 (14:37 +0900)]
tools lib traceevent: Make dependency files regeneratable
Ingo reported that libtraceevent doesn't clean out dependency (.d) files
and it can cause a build error when the libgcc package upgraded:
comet:~/tip/tools/perf> make -j
SUBDIR ../lib/traceevent/
make[1]: *** No rule to make target `/usr/lib/gcc/x86_64-redhat-linux/4.7.0/include/stddef.h',
needed by `event-parse.o'. Stop.
make: *** [../lib/traceevent//libtraceevent.a] Error 2
So this patch makes the .d files depends on the source and header files
also, so that it can be re-generated as needed.
NOTE: This code is copied from the GNU make manual page
(4.14 Generating Prerequisites Automatically).
Reported-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1340343462-15556-3-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
David Ahern [Mon, 11 Jun 2012 19:48:41 +0000 (13:48 -0600)]
perf report: Delay sample_type checks in pipe mode
The pipeline:
perf record -a -g -o - sleep 5 |perf inject -v -b | perf report -g -i -
generates the warning:
Selected -g but no callchain data. Did you call 'perf record' without -g?
The problem is that the header data is not written to the pipe, so the
sample_type has not been available when perf_report__setup_sample_type
is called. For pipe mode, record dumps the sample type as part of the
synthesized events stream -- perf_event__synthesize_attrs(). Handle this
be detecting pipe mode and not doing early sanity checks on sample_type.
Signed-off-by: David Ahern <dsahern@gmail.com> Tested-by: Tim Chen <tim.c.chen@linux.intel.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tim Chen <tim.c.chen@linux.intel.com> Link: http://lkml.kernel.org/r/1339444121-26236-1-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf tools: Stop using a global trace events description list
The pevent thing is per perf.data file, so I made it stop being static
and become a perf_session member, so tools processing perf.data files
use perf_session and _there_ we read the trace events description into
session->pevent and then change everywhere to stop using that single
global pevent variable and use the per session one.
Note that it _doesn't_ fall backs to trace__event_id, as we're not
interested at all in what is present in the
/sys/kernel/debug/tracing/events in the workstation doing the analysis,
just in what is in the perf.data file.
This patch also introduces perf_session__set_tracepoints_handlers that
is the perf perf.data/session way to associate handlers to tracepoint
events by resolving their IDs using the events descriptions stored in a
perf.data file. Make 'perf sched' use it.
Reported-by: Dmitry Antipov <dmitry.antipov@linaro.org> Tested-by: Dmitry Antipov <dmitry.antipov@linaro.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: linaro-dev@lists.linaro.org Cc: patches@linaro.org Link: http://lkml.kernel.org/r/20120625232016.GA28525@infradead.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Jiri Olsa [Thu, 21 Jun 2012 10:25:16 +0000 (12:25 +0200)]
perf test: Fix parse events test to follow proper raw event name
Following commit changed raw event names to carry event modificator.
perf evsel: Reconstruct raw event with modifiers from perf_event_attr
commit 6eef3d9c2bcf52b7a3c18e609f5838c007b989a4
Author: Arnaldo Carvalho de Melo <acme@redhat.com>
The perf_evsel__name function now returns ':mod' suffix for raw events,
so we need to follow that in current tests.
All tests pass now for 'perf test parse' suite.
Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1340274316-5161-1-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Namhyung Kim [Thu, 21 Jun 2012 08:52:52 +0000 (17:52 +0900)]
perf evsel: Fix a build failure on cross compilation
The commit c410431cefefd ("perf tools: Reconstruct event with modifiers
from perf_event_attr") added the line, but it's broken since it needs to
go up 3 directories to get to the kernel root directory, not 2.
However host gcc contains /usr/local/include in its search path, so that
it can find the perf_event.h in /usr/include. This why we didn't notice
the problem yet. But when I tried to cross compile it appears like:
CC util/evsel.o
util/evsel.c:18:44: error: ../../include/linux/perf_event.h: No such file or directory
make: *** [util/evsel.o] Error 1
Looking at the source, it isn't needed at all as evsel.h already
included the perf_event.h. So simply remove it would solve the problem.
Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1340268772-5737-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Robert Richter [Wed, 20 Jun 2012 16:39:27 +0000 (18:39 +0200)]
perf/x86: Fix section mismatch in uncore_pci_init()
Fix section mismatch in uncore_pci_init():
WARNING: vmlinux.o(.init.text+0x9246): Section mismatch in reference from the function uncore_pci_init() to the function .devexit.text:uncore_pci_remove()
The function __init uncore_pci_init() references
a function __devexit uncore_pci_remove().
[...]
Jiri Olsa [Mon, 11 Jun 2012 13:20:03 +0000 (15:20 +0200)]
perf tools: Remove unused evsel parameter from machine__resolve_callchain
Removing unused evsel parameter from machine__resolve_callchain
function. Plus related header file and callers changes.
The evsel parameter is unused since following commit:
perf callchain: Make callchain cursors TLS
commit 472606458f3e1ced5fe3cc5f04e90a6b5a4732cf
Author: Namhyung Kim <namhyung.kim@lge.com>
Date: Thu May 31 14:43:26 2012 +0900
Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Arun Sharma <asharma@fb.com> Cc: Benjamin Redelings <benjamin.redelings@nescent.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Frank Ch. Eigler <fche@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Robert Richter <robert.richter@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Ulrich Drepper <drepper@gmail.com> Link: http://lkml.kernel.org/r/1339420814-7379-9-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Not needed anymore, the parsing code can just leave evsel->name as NULL
and the first call to perf_evsel__name() will do exactly what was being
pre-cached using __event_name().
Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-cn2eiijcinnc97buod8cs34m@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
One needs to use perf_evsel__name() so that if needed the name gets
synthesized and stored in evsel->name, from where perf_evsel__name()
will serve from them on.
Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-ml7zbenjmri9bghmrea0jm0d@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf tools: Reconstruct sw event with modifiers from perf_event_attr
[root@sandy ~]# perf record -e task-clock:u -a usleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.482 MB perf.data (~21073 samples) ]
[root@sandy ~]#
perf tools: Reconstruct hw cache event with modifiers from perf_event_attr
[root@sandy ~]# perf record -a -e dTLB-load-misses:u usleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.486 MB perf.data (~21216 samples) ]
perf hists browser: Implement printing snapshots to files
To avoid having to resort to --stdio, that expands everything, instead
allow the user to go on expanding the relevant callchains and then press
'P' to print that view.
As the hists browser is used for both static (report) and dynamic (top)
views, it prints to a 'perf.hists.N' sequence, i.e. multiple snapshots
can be taken in report and top.
Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-wr9xx4ba0utrynu5j6wotd79@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Namhyung Kim [Tue, 29 May 2012 04:23:02 +0000 (13:23 +0900)]
perf ui/gtk: Use struct perf_error_ops
Define and use perf_gtk_eops to provide a GTK2 message dialog for error
reporting and a info_bar for warning.
As GtkInfoBar requires recent GTK+ libraries, provides a fallback
implementation using statusbar widget too.
Signed-off-by: Namhyung Kim <namhyung@gmail.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1338265382-6872-8-git-send-email-namhyung@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Namhyung Kim [Tue, 29 May 2012 04:23:01 +0000 (13:23 +0900)]
perf ui/gtk: Add GTK info_bar widget to browser window
The GtkInfoBar is a modern UI component to display messages without
bothering the main window. It'll be used for showing a warning message.
As the GtkInfoBar requires 2.18 (or newer) version of GTK+ library, add
availability check to Makefile too.
Suggested-by: Sunjin Yang <fan4326@gmail.com> Signed-off-by: Namhyung Kim <namhyung@gmail.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1338265382-6872-7-git-send-email-namhyung@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Namhyung Kim [Tue, 29 May 2012 04:23:00 +0000 (13:23 +0900)]
perf ui/gtk: Add GTK statusbar widget to browser window
Add statusbar widget to display non-critical messages at the bottom of
the window. This can be used for showing a status change, warning or
help message.
Signed-off-by: Namhyung Kim <namhyung@gmail.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1338265382-6872-6-git-send-email-namhyung@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Namhyung Kim [Tue, 29 May 2012 04:22:59 +0000 (13:22 +0900)]
perf ui/gtk: Introduce struct perf_gtk_context
The struct perf_gtk_context is for tracking current state of GTK window
and/or other things. This is a preparation of next changes.
Signed-off-by: Namhyung Kim <namhyung@gmail.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1338265382-6872-5-git-send-email-namhyung@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Namhyung Kim [Tue, 29 May 2012 04:22:58 +0000 (13:22 +0900)]
perf ui: Introduce struct perf_error_ops
The struct perf_error_ops is for flexible error logging.
We can register appropriate functions based on front-end.
Signed-off-by: Namhyung Kim <namhyung.kim@lge.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1338265382-6872-4-git-send-email-namhyung@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Jiri Olsa [Fri, 15 Jun 2012 06:31:42 +0000 (14:31 +0800)]
perf/tool: Add automated test for pure terms parsing
Adding automated test for parsing terms out of the event grammar.
Also slightly changing current event parsing test functions to
follow up more generic namespace.
Jiri Olsa [Fri, 15 Jun 2012 06:31:40 +0000 (14:31 +0800)]
perf/tool: Add support to reuse event grammar to parse out terms
We want to reuse the event grammar for parsing aliased terms.
The obvious reason is we dont need to add new code when there's
already support for this in event grammar.
Doing this by adding terms and event start entries into event
parse grammar. The grammar forks on the begining based on the
starting token, which is supplied via bison interface into the
lexer. The lexer then returns the starting token as the first
token, thus making the grammar switch accordingly.
Currently 2 starting tokens/grammars are supported:
PE_START_TERMS, PE_START_EVENTS
The PE_START_TERMS related grammar uses 'event_config' part
of the grammar for term parsing.
Yan, Zheng [Fri, 15 Jun 2012 06:31:34 +0000 (14:31 +0800)]
perf/x86: Add generic Intel uncore PMU support
This patch adds the generic Intel uncore PMU support, including helper
functions that add/delete uncore events, a hrtimer that periodically
polls the counters to avoid overflow and code that places all events
for a particular socket onto a single cpu.
The code design is based on the structure of Sandy Bridge-EP's uncore
subsystem, which consists of a variety of components, each component
contains one or more "boxes".
(Tooling support follows in the next patches.)
Signed-off-by: Zheng Yan <zheng.z.yan@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1339741902-8449-6-git-send-email-zheng.z.yan@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Yan, Zheng [Fri, 15 Jun 2012 06:31:31 +0000 (14:31 +0800)]
perf: Avoid race between cpu hotplug and installing event
perf_event_open() requires the cpu on which to install event is online,
but the cpu can go offline after perf_event_open checks that. Add a
get_online_cpus()/put_online_cpus() pair to avoid the race.
Salman Qazi [Thu, 14 Jun 2012 22:31:09 +0000 (15:31 -0700)]
perf: Use css_tryget() to avoid propping up css refcount
An rmdir pushes css's ref count to zero. However, if the associated
directory is open at the time, the dentry ref count is non-zero. If
the fd for this directory is then passed into perf_event_open, it
does a css_get(). This bounces the ref count back up from zero. This
is a problem by itself. But what makes it turn into a crash is the
fact that we end up doing an extra dput, since we perform a dput
when css_put sees the ref count go down to zero.
css_tryget() does not fall into that trap. So, we use that instead.
Oleg Nesterov [Fri, 15 Jun 2012 15:43:50 +0000 (17:43 +0200)]
uprobes: Move BUG_ON(UPROBE_SWBP_INSN_SIZE) from write_opcode() to install_breakpoint()
write_opcode() ensures that UPROBE_SWBP_INSN doesn't cross the
page boundary. This looks a bit confusing, the check does not
depend on vaddr and it is enough to do it only once right after
install_breakpoint()->arch_uprobe_analyze_insn().
Signed-off-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Acked-by: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Anton Arapov <anton@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20120615154350.GA9611@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Oleg Nesterov [Fri, 15 Jun 2012 15:43:47 +0000 (17:43 +0200)]
uprobes: No need to re-check vma_address() in write_opcode()
write_opcode() is called by register_for_each_vma() and
uprobe_mmap() paths. In both cases the caller has already
verified this vaddr under mmap_sem, no need to re-check.
Note also that this check is wrong anyway, we should not
truncate loff_t returned by vma_address() if we do not trust
this mapping.
Signed-off-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Acked-by: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Anton Arapov <anton@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20120615154347.GA9604@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Oleg Nesterov [Fri, 15 Jun 2012 15:43:36 +0000 (17:43 +0200)]
uprobes: Change build_map_info() to try kmalloc(GFP_NOWAIT) first
build_map_info() doesn't allocate the memory under i_mmap_mutex
to avoid the deadlock with page reclaim. But it can try
GFP_NOWAIT first, it should work in the likely case and thus we
almost never need the pre-alloc-and-retry path.
Signed-off-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Anton Arapov <anton@redhat.com> Link: http://lkml.kernel.org/r/20120615154336.GA9588@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Oleg Nesterov [Fri, 15 Jun 2012 15:43:33 +0000 (17:43 +0200)]
uprobes: Rework register_for_each_vma() to make it O(n)
Currently register_for_each_vma() is O(n ** 2) + O(n ** 3),
every time find_next_vma_info() "restarts" the
vma_prio_tree_foreach() loop and each iteration rechecks the
whole try_list. This also means that try_list can grow
"indefinitely" if register/unregister races with munmap/mmap
activity even if the number of mapping is bounded at any time.
With this patch register_for_each_vma() builds the list of
mm/vaddr structures only once and does install_breakpoint() for
each entry.
We do not care about the new mappings which can be created after
build_map_info() drops mapping->i_mmap_mutex, uprobe_mmap()
should do its work.
Note that we do not allocate map_info under i_mmap_mutex, this
can deadlock with page reclaim (but see the next patch). So we
use 2 lists, "curr" which we are going to return, and "prev"
which holds the already allocated memory. The main loop deques
the entry from "prev" (initially it is empty), and if "prev"
becomes empty again it counts the number of entries we need to
pre-allocate outside of i_mmap_mutex.
Signed-off-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Anton Arapov <anton@redhat.com> Link: http://lkml.kernel.org/r/20120615154333.GA9581@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Oleg Nesterov [Fri, 15 Jun 2012 15:43:31 +0000 (17:43 +0200)]
uprobes: Install_breakpoint() should fail if is_swbp_insn() == T
install_breakpoint() returns -EEXIST if is_swbp_insn(orig_insn)
== T, the caller treats this code as success.
This is doubly wrong. The successful return should set
UPROBE_COPY_INSN, but the real problem is that it shouldn't
succeed. If the probed insn is int3 the application should get
SIGTRAP, this won't happen with uprobe.
Probably we can fix this, we can add the UPROBE_SHARED_BP flag
and teach handle_swbp/set_orig_insn to handle this case
correctly. But this needs some complications and we have other
insns which can't be probed, lets make a simple fix for now.
I think this needs a cleanup. UPROBE_COPY_INSN should die,
copy_insn() should be called by alloc_uprobe().
arch_uprobe_analyze_insn() depends on ->mm (ia32_compat) but it
is called only once.
Signed-off-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Anton Arapov <anton@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20120615154331.GA9578@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Oleg Nesterov [Fri, 15 Jun 2012 15:43:28 +0000 (17:43 +0200)]
uprobes: Write_opcode()->__replace_page() can race with try_to_unmap()
write_opcode() gets old_page via get_user_pages() and then calls
__replace_page() which assumes that this old_page is still
mapped after pte_offset_map_lock().
This is not true if this old_page was already try_to_unmap()'ed,
and in this case everything __replace_page() does with old_page
is wrong. Just for example, put_page() is not balanced.
I think it is possible to teach __replace_page() to handle this
unlikely case correctly, but this patch simply changes it to use
page_check_address() and return -EAGAIN if it fails. The caller
should notice this error code and retry.
Note: write_opcode() asks for the cleanups, I'll try to do this
in a separate patch.
Signed-off-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Anton Arapov <anton@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20120615154328.GA9571@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Oleg Nesterov [Fri, 15 Jun 2012 15:43:25 +0000 (17:43 +0200)]
uprobes: __copy_insn() should ensure a_ops->readpage != NULL
__copy_insn() blindly calls read_mapping_page(), this will crash
the kernel if ->readpage == NULL, add the necessary check. For
example, hugetlbfs_aops->readpage is NULL. Perhaps we should
change read_mapping_page() instead.
Signed-off-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Anton Arapov <anton@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20120615154325.GA9568@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Oleg Nesterov [Fri, 15 Jun 2012 15:43:22 +0000 (17:43 +0200)]
uprobes: Valid_vma() should reject VM_HUGETLB
__replace_page() obviously can't work with the hugetlbfs
mappings, uprobe_register() will likely crash the kernel. Change
valid_vma() to check VM_HUGETLB as well.
As for PageTransHuge() no need to worry, vma->vm_file != NULL.
Signed-off-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Anton Arapov <anton@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20120615154322.GA9561@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Steven Rostedt [Fri, 1 Jun 2012 01:40:05 +0000 (21:40 -0400)]
tracing: Register the ftrace internal events during early boot
All trace events including ftrace internel events (like trace_printk
and function tracing), register functions that describe how to print
their output. The events may be recorded as soon as the ring buffer
is allocated, but they are just raw binary in the buffer. The mapping
of event ids to how to print them are held within a structure that
is registered on system boot.
If a crash happens in boot up before these functions are registered
then their output (via ftrace_dump_on_oops) will be useless:
do not, making them second class citizens. To prevent another
class warfare, these bits have protested for their right to be
commented. And By Golly! I'll give them what they want!
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Don Zickus [Wed, 13 Jun 2012 13:35:48 +0000 (09:35 -0400)]
watchdog: Quiet down the boot messages
A bunch of bugzillas have complained how noisy the nmi_watchdog
is during boot-up especially with its expected failure cases
(like virt and bios resource contention).
This is my attempt to quiet them down and keep it less confusing
for the end user. What I did is print the message for cpu0 and
save it for future comparisons. If future cpus have an
identical message as cpu0, then don't print the redundant info.
However, if a future cpu has a different message, happily print
that loudly.
Before the change, you would see something like:
..TIMER: vector=0x30 apic1=0 pin1=2 apic2=-1 pin2=-1
CPU0: Intel(R) Core(TM)2 Quad CPU Q9550 @ 2.83GHz stepping 0a
Performance Events: PEBS fmt0+, Core2 events, Intel PMU driver.
... version: 2
... bit width: 40
... generic registers: 2
... value mask: 000000ffffffffff
... max period: 000000007fffffff
... fixed-purpose events: 3
... event mask: 0000000700000003
NMI watchdog enabled, takes one hw-pmu counter.
Booting Node 0, Processors #1
NMI watchdog enabled, takes one hw-pmu counter.
#2
NMI watchdog enabled, takes one hw-pmu counter.
#3 Ok.
NMI watchdog enabled, takes one hw-pmu counter.
Brought up 4 CPUs
Total of 4 processors activated (22607.24 BogoMIPS).
After the change, it is simplified to:
..TIMER: vector=0x30 apic1=0 pin1=2 apic2=-1 pin2=-1
CPU0: Intel(R) Core(TM)2 Quad CPU Q9550 @ 2.83GHz stepping 0a
Performance Events: PEBS fmt0+, Core2 events, Intel PMU driver.
... version: 2
... bit width: 40
... generic registers: 2
... value mask: 000000ffffffffff
... max period: 000000007fffffff
... fixed-purpose events: 3
... event mask: 0000000700000003
NMI watchdog: enabled on all CPUs, permanently consumes one hw-PMU counter.
Booting Node 0, Processors #1 #2 #3 Ok.
Brought up 4 CPUs
V2: little changes based on Joe Perches' feedback
V3: printk cleanup based on Ingo's feedback; checkpatch fix
V4: keep printk as one long line
V5: Ingo fix ups
Stephane Eranian [Mon, 11 Jun 2012 13:44:26 +0000 (15:44 +0200)]
perf/x86: Fix broken LBR fixup code
I noticed that the LBR fixups were not working anymore
on programs where they used to. I tracked this down to
a recent change to copy_from_user_nmi():
db0dc75d640 ("perf/x86: Check user address explicitly in copy_from_user_nmi()")
This commit added a call to __range_not_ok() to the
copy_from_user_nmi() routine. The problem is that the logic
of the test must be reversed. __range_not_ok() returns 0 if the
range is VALID. We want to return early from copy_from_user_nmi()
if the range is NOT valid.
perf tools: Fix synthesizing tracepoint names from the perf.data headers
We need to use the per event info snapshoted at record time to
synthesize the events name, so do it just after reading the perf.data
headers, when we already processed the /sys events data, otherwise we'll
end up using the local /sys that only by sheer luck will have the same
tracepoint ID -> real event association.
Example:
# uname -a
Linux felicio.ghostprotocols.net 3.4.0-rc5+ #1 SMP Sat May 19 15:27:11 BRT 2012 x86_64 x86_64 x86_64 GNU/Linux
# perf record -e sched:sched_switch usleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.015 MB perf.data (~648 samples) ]
# cat /t/events/sched/sched_switch/id
279
# perf evlist -v
sched:sched_switch: sample_freq=1, type: 2, config: 279, size: 80, sample_type: 1159, read_format: 7, disabled: 1, inherit: 1, mmap: 1, comm: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1
#
So on the above machine the sched:sched_switch has tracepoint id 279, but on
the machine were we'll analyse it it has a different id:
perf stat: Add --log-fd <N> option to redirect stderr elsewhere
introduced a bug in the way perf stat outputs the results by default,
i.e., without the --log-fd or --output option. It would default to
writing to file descriptor 0, i.e., stdin. Writing to stdin is allowed
and is equivalent to writing to stdout. However, there is a major
difference for any script that was already capturing the output of perf
stat via redirection:
perf stat >/tmp/log .... or perf stat 2>/tmp/log ....
They would not capture anything anymore. They would have to do:
perf stat 0>/tmp/log ...
This breaks compatibility with existing scripts and does not look very
natural.
This patch fixes the problem by looking at output_fd only when it was
modified by user (> 0). It also checks that the value if positive.
Passing --log-fd 0 is ignored.
I would also argue that defaulting to stderr for the results is not the
right thing to do, though this patch does not address this specific
issue.
Signed-off-by: Stephane Eranian <eranian@google.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Jim Cromie <jim.cromie@gmail.com> Link: http://lkml.kernel.org/r/20120515111111.GA9870@quad Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
David Rientjes [Fri, 8 Jun 2012 20:21:26 +0000 (13:21 -0700)]
mm, oom: fix badness score underflow
If the privileges given to root threads (3% of allowable memory) or a
negative value of /proc/pid/oom_score_adj happen to exceed the amount of
rss of a thread, its badness score overflows as a result of commit a7f638f999ff ("mm, oom: normalize oom scores to oom_score_adj scale only
for userspace").
Fix this by making the type signed and return 1, meaning the thread is
still eligible for kill, if the value is negative.
Reported-by: Dave Jones <davej@redhat.com> Acked-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Randy Dunlap [Fri, 8 Jun 2012 20:18:33 +0000 (13:18 -0700)]
sched/fair: fix lots of kernel-doc warnings
Fix lots of new kernel-doc warnings in kernel/sched/fair.c:
Warning(kernel/sched/fair.c:3625): No description found for parameter 'env'
Warning(kernel/sched/fair.c:3625): Excess function parameter 'sd' description in 'update_sg_lb_stats'
Warning(kernel/sched/fair.c:3735): No description found for parameter 'env'
Warning(kernel/sched/fair.c:3735): Excess function parameter 'sd' description in 'update_sd_pick_busiest'
Warning(kernel/sched/fair.c:3735): Excess function parameter 'this_cpu' description in 'update_sd_pick_busiest'
.. more warnings
Signed-off-by: Randy Dunlap <rdunlap@xenotime.net> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
It incorrectly finds VGA connectors where none are attached, apparently
not noticing that nothing replied to the EDID queries, and happily using
the default EDID modes that have nothing to do with actual hardware.
That in turn then causes X to fall down to the lowest common
denominator, which is usually the default 1024x768 mode that is in the
default EDID and pretty much anything supports).
I'd suggest that if not relying on the HDP pin, the code should at least
check whether it gets valid EDID data back, rather than just assume
there's something on the VGA connector.
Cc: Dave Airlie <airlied@linux.ie> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Linus Torvalds [Fri, 8 Jun 2012 18:15:31 +0000 (11:15 -0700)]
Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4
Pull ext4 bug fixes from Theodore Ts'o:
"This update contains two bug fixes, both destined for the stable tree.
Perhaps the most important is one which fixes ext4 when used with file
systems originally formatted for use with ext3, but then later
converted to take advantage of ext4."
* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
ext4: don't set i_flags in EXT4_IOC_SETFLAGS
ext4: fix the free blocks calculation for ext3 file systems w/ uninit_bg
Linus Torvalds [Fri, 8 Jun 2012 18:06:01 +0000 (11:06 -0700)]
Merge branch 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc
Pull powerpc fixes from Paul Mackerras:
"Two small fixes for powerpc:
- a fix for a regression since 3.2 that causes 4-second (or longer)
pauses
- a fix for a potential oops when loading kernel modules on 32-bit
embedded systems."
* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc:
powerpc: Fix kernel panic during kernel module load
powerpc/time: Sanity check of decrementer expiration is necessary
Linus Torvalds [Fri, 8 Jun 2012 18:04:06 +0000 (11:04 -0700)]
Merge tag 'upstream-3.5-rc2' of git://git.infradead.org/linux-ubifs
Pull UBI/UBIFS fixes from Artem Bityutskiy:
"Fix UBI and UBIFS - they refuse to work without debugfs. This was
broken by the 3.5-rc1 UBI/UBIFS changes when we removed the debugging
Kconfig switches.
Also, correct locking in 'ubi_wl_flush()' - it was extended to support
flushing a specific LEB in 3.5-rc1, and the locking was sub-optimal."
* tag 'upstream-3.5-rc2' of git://git.infradead.org/linux-ubifs:
UBI: correct ubi_wl_flush locking
UBIFS: fix debugfs-less systems support
UBI: fix debugfs-less systems support
We're chasing an elusive bug that Dave Jones can apparently reproduce
using his system call fuzzer tool, and that looks like some kind of
locking ordering problem on the directory i_mutex chain. Our i_mutex
locking is rather complex, and depends on the topological ordering of
the directories, which is why we have been very wary of splicing
directory entries around.
Of course, we really don't want to ever see aliased unconnected
directories anyway, so none of this should ever happen, but this revert
aims to basically get us back to a known older state.
Bruce points to some of the previous discussion at
It should be noted that it's possible that Dave's problems come from
other changes altohgether, including possibly just the fact that Dave
constantly is teachning his fuzzer new tricks. So what appears to be a
new bug could in fact be an old one that just gets newly triggered, but
reverting these patches as "still under heavy discussion" is the right
thing regardless.
Requested-by: Al Viro <viro@zeniv.linux.org.uk> Acked-by: J. Bruce Fields <bfields@fieldses.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Linus Torvalds [Fri, 8 Jun 2012 16:26:55 +0000 (09:26 -0700)]
Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 fixes from Ingo Molnar.
* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/nmi: Fix section mismatch warnings on 32-bit
x86/uv: Fix UV2 BAU legacy mode
x86/mm: Only add extra pages count for the first memory range during pre-allocation early page table space
x86, efi stub: Add .reloc section back into image
x86/ioapic: Fix NULL pointer dereference on CPU hotplug after disabling irqs
x86/reboot: Fix a warning message triggered by stop_other_cpus()
x86/intel/moorestown: Change intel_scu_devices_create() to __devinit
x86/numa: Set numa_nodes_parsed at acpi_numa_memory_affinity_init()
x86/gart: Fix kmemleak warning
x86: mce: Add the dropped timer interval init back
x86/mce: Fix the MCE poll timer logic
Linus Torvalds [Fri, 8 Jun 2012 16:14:46 +0000 (09:14 -0700)]
Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf fixes from Ingo Molnar:
"A bit larger than what I'd wish for - half of it is due to hw driver
updates to Intel Ivy-Bridge which info got recently released,
cycles:pp should work there now too, amongst other things. (but we
are generally making exceptions for hardware enablement of this type.)
There are also callchain fixes in it - responding to mostly
theoretical (but valid) concerns. The tooling side sports perf.data
endianness/portability fixes which did not make it for the merge
window - and various other fixes as well."
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (26 commits)
perf/x86: Check user address explicitly in copy_from_user_nmi()
perf/x86: Check if user fp is valid
perf: Limit callchains to 127
perf/x86: Allow multiple stacks
perf/x86: Update SNB PEBS constraints
perf/x86: Enable/Add IvyBridge hardware support
perf/x86: Implement cycles:p for SNB/IVB
perf/x86: Fix Intel shared extra MSR allocation
x86/decoder: Fix bsr/bsf/jmpe decoding with operand-size prefix
perf: Remove duplicate invocation on perf_event_for_each
perf uprobes: Remove unnecessary check before strlist__delete
perf symbols: Check for valid dso before creating map
perf evsel: Fix 32 bit values endianity swap for sample_id_all header
perf session: Handle endianity swap on sample_id_all header data
perf symbols: Handle different endians properly during symbol load
perf evlist: Pass third argument to ioctl explicitly
perf tools: Update ioctl documentation for PERF_IOC_FLAG_GROUP
perf tools: Make --version show kernel version instead of pull req tag
perf tools: Check if callchain is corrupted
perf callchain: Make callchain cursors TLS
...