Peter Zijlstra [Mon, 30 Mar 2009 17:07:03 +0000 (19:07 +0200)]
perf_counter: fix update_userpage()
It just occured to me it is possible to have multiple contending
updates of the userpage (mmap information vs overflow vs counter).
This would break the seqlock logic.
It appear the arch code uses this from NMI context, so we cannot
possibly serialize its use, therefore separate the data_head update
from it and let it return to its original use.
The arch code needs to make sure there are no contending callers by
disabling the counter before using it -- powerpc appears to do this
nicely.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org>
Orig-LKML-Reference: <20090330171023.241410660@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Peter Zijlstra [Mon, 30 Mar 2009 17:07:02 +0000 (19:07 +0200)]
perf_counter: unify and fix delayed counter wakeup
While going over the wakeup code I noticed delayed wakeups only work
for hardware counters but basically all software counters rely on
them.
This patch unifies and generalizes the delayed wakeup to fix this
issue.
Since we're dealing with NMI context bits here, use a cmpxchg() based
single link list implementation to track counters that have pending
wakeups.
[ This should really be generic code for delayed wakeups, but since we
cannot use cmpxchg()/xchg() in generic code, I've let it live in the
perf_counter code. -- Eric Dumazet could use it to aggregate the
network wakeups. ]
Furthermore, the x86 method of using TIF flags was flawed in that its
quite possible to end up setting the bit on the idle task, loosing the
wakeup.
The powerpc method uses per-cpu storage and does appear to be
sufficient.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org>
Orig-LKML-Reference: <20090330171023.153932974@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Paul Mackerras [Wed, 25 Mar 2009 11:46:58 +0000 (22:46 +1100)]
perf_counter: record time running and time enabled for each counter
Impact: new functionality
Currently, if there are more counters enabled than can fit on the CPU,
the kernel will multiplex the counters on to the hardware using
round-robin scheduling. That isn't too bad for sampling counters, but
for counting counters it means that the value read from a counter
represents some unknown fraction of the true count of events that
occurred while the counter was enabled.
This remedies the situation by keeping track of how long each counter
is enabled for, and how long it is actually on the cpu and counting
events. These times are recorded in nanoseconds using the task clock
for per-task counters and the cpu clock for per-cpu counters.
These values can be supplied to userspace on a read from the counter.
Userspace requests that they be supplied after the counter value by
setting the PERF_FORMAT_TOTAL_TIME_ENABLED and/or
PERF_FORMAT_TOTAL_TIME_RUNNING bits in the hw_event.read_format field
when creating the counter. (There is no way to change the read format
after the counter is created, though it would be possible to add some
way to do that.)
Using this information it is possible for userspace to scale the count
it reads from the counter to get an estimate of the true count:
This also lets userspace detect the situation where the counter never
got to go on the cpu: total_time_running == 0.
This functionality has been requested by the PAPI developers, and will
be generally needed for interpreting the count values from counting
counters correctly.
In the implementation, this keeps 5 time values (in nanoseconds) for
each counter: total_time_enabled and total_time_running are used when
the counter is in state OFF or ERROR and for reporting back to
userspace. When the counter is in state INACTIVE or ACTIVE, it is the
tstamp_enabled, tstamp_running and tstamp_stopped values that are
relevant, and total_time_enabled and total_time_running are determined
from them. (tstamp_stopped is only used in INACTIVE state.) The
reason for doing it like this is that it means that only counters
being enabled or disabled at sched-in and sched-out time need to be
updated. There are no new loops that iterate over all counters to
update total_time_enabled or total_time_running.
This also keeps separate child_total_time_running and
child_total_time_enabled fields that get added in when reporting the
totals to userspace. They are separate fields so that they can be
atomic. We don't want to use atomics for total_time_running,
total_time_enabled etc., because then we would have to use atomic
sequences to update them, which are slower than regular arithmetic and
memory accesses.
It is possible to measure total_time_running by adding a task_clock
counter to each group of counters, and total_time_enabled can be
measured approximately with a top-level task_clock counter (though
inaccuracies will creep in if you need to disable and enable groups
since it is not possible in general to disable/enable the top-level
task_clock counter simultaneously with another group). However, that
adds extra overhead - I measured around 15% increase in the context
switch latency reported by lat_ctx (from lmbench) when a task_clock
counter was added to each of 2 groups, and around 25% increase when a
task_clock counter was added to each of 4 groups. (In both cases a
top-level task-clock counter was also added.)
In contrast, the code added in this commit gives better information
with no overhead that I could measure (in fact in some cases I
measured lower times with this code, but the differences were all less
than one standard deviation).
[ v2: address review comments by Andrew Morton. ]
Signed-off-by: Paul Mackerras <paulus@samba.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrew Morton <akpm@linux-foundation.org>
Orig-LKML-Reference: <18890.6578.728637.139402@cargo.ozlabs.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Peter Zijlstra [Wed, 25 Mar 2009 11:30:27 +0000 (12:30 +0100)]
perf_counter: kerneltop: output event support
Teach kerneltop about the new output ABI.
XXX: anybody fancy integrating the PID/TID data into the output?
Bump the mmap_data pages a little because we bloated the output and
have to be more careful about overruns with structured data.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Wu Fengguang <fengguang.wu@intel.com>
Orig-LKML-Reference: <20090325113317.192910290@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Peter Zijlstra [Wed, 25 Mar 2009 11:30:26 +0000 (12:30 +0100)]
perf_counter: kerneltop: mmap_pages argument
provide a knob to set the number of mmap data pages.
Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Wu Fengguang <fengguang.wu@intel.com>
Orig-LKML-Reference: <20090325113317.104545398@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Peter Zijlstra [Wed, 25 Mar 2009 11:30:25 +0000 (12:30 +0100)]
perf_counter: optionally provide the pid/tid of the sampled task
Allow cpu wide counters to profile userspace by providing what process
the sample belongs to.
This raises the first issue with the output type, lots of these
options: group, tid, callchain, etc.. are non-exclusive and could be
combined, suggesting a bitfield.
However, things like the mmap() data stream doesn't fit in that.
How to split the type field...
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Wu Fengguang <fengguang.wu@intel.com>
Orig-LKML-Reference: <20090325113317.013775235@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Peter Zijlstra [Wed, 25 Mar 2009 11:30:24 +0000 (12:30 +0100)]
perf_counter: sanity check on the output API
Ensure we never write more than we said we would.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Wu Fengguang <fengguang.wu@intel.com>
Orig-LKML-Reference: <20090325113316.921433024@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Peter Zijlstra [Wed, 25 Mar 2009 11:30:23 +0000 (12:30 +0100)]
perf_counter: output objects
Provide a {type,size} header for each output entry.
This should provide extensible output, and the ability to mix multiple streams.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Wu Fengguang <fengguang.wu@intel.com>
Orig-LKML-Reference: <20090325113316.831607932@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Peter Zijlstra [Wed, 25 Mar 2009 11:30:22 +0000 (12:30 +0100)]
perf_counter: more elaborate write API
Provide a begin, copy, end interface to the output buffer.
begin() reserves the space,
copy() copies the data over, considering page boundaries,
end() finalizes the event and does the wakeup.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Wu Fengguang <fengguang.wu@intel.com>
Orig-LKML-Reference: <20090325113316.740550870@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Peter Zijlstra [Tue, 24 Mar 2009 12:18:16 +0000 (13:18 +0100)]
perf_counter: fix perf_poll()
Impact: fix kerneltop 100% CPU usage
Only return a poll event when there's actually been one, poll_wait()
doesn't actually wait for the waitq you pass it, it only enqueues
you on it.
Only once all FDs have been iterated and none of thm returned a
poll-event will it schedule().
Also make it return POLL_HUP when there's not mmap() area to read from.
Further, fix a silly bug in the write code.
Reported-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arjan van de Ven <arjan@infradead.org>
Orig-LKML-Reference: <1237897096.24918.181.camel@twins> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Peter Zijlstra [Tue, 24 Mar 2009 09:50:24 +0000 (10:50 +0100)]
perf_counter tools: remove glib dependency and fix bugs in kerneltop.c, fix poll()
Paul Mackerras wrote:
> I noticed the poll stuff is bogus - we have a 2D array of struct
> pollfds (MAX_NR_CPUS x MAX_COUNTERS), we fill in a sub-array (with the
> rest being uninitialized, since the array is on the stack) and then
> pass the first nr_cpus elements to poll. Not what we really meant, I
> suspect. :) Not even if we only have one counter, since it's the
> counter dimension that varies fastest.
This should fix the most obvious poll fubar.. not enough to fix the
full problem though..
Reported-by: Paul Mackerras <paulus@samba.org> Reported-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arjan van de Ven <arjan@linux.intel.com>
Orig-LKML-Reference: <18888.29986.340328.540512@cargo.ozlabs.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Paul Mackerras [Tue, 24 Mar 2009 05:52:34 +0000 (16:52 +1100)]
perf_counter tools: remove glib dependency and fix bugs in kerneltop.c
The glib dependency in kerneltop.c is only for a little bit of list
manipulation, and I find it inconvenient. This adds a 'next' field to
struct source_line, which lets us link them together into a list. The
code to do the linking ourselves turns out to be no longer or more
difficult than using glib.
This also fixes a few other problems:
- We need to #include <limits.h> to get PATH_MAX on powerpc.
- We need to #include <linux/types.h> rather than have our own
definitions of __u64 and __s64; on powerpc the installed headers
define them to be unsigned long and long respectively, and if we
have our own, different definition here that causes a compile error.
- This takes out the x86 setting of errno from -ret in
sys_perf_counter_open. My experiments on x86 indicate that the
glibc syscall() does this for us already.
- We had two CPU migration counters in the default set, which seems
unnecessary; I changed one of them to a context switch counter.
- In perfstat mode we were printing CPU cycles and instructions as
milliseconds, and the cpu clock and task clock counters as events.
This fixes that.
- In perfstat mode we were still printing a blank line after the first
counter, which was a holdover from when a task clock counter was
automatically included as the first counter. This removes the blank
line.
- On a test machine here, parse_symbols() and parse_vmlinux() were
taking long enough (almost 0.5 seconds) for the mmap buffer to
overflow before we got to the first mmap_read() call, so this moves
them before we open all the counters.
- The error message if sys_perf_counter_open fails needs to use errno,
not -fd[i][counter].
Signed-off-by: Paul Mackerras <paulus@samba.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Mike Galbraith <efault@gmx.de> Cc: Arjan van de Ven <arjan@linux.intel.com>
Orig-LKML-Reference: <18888.29986.340328.540512@cargo.ozlabs.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Ingo Molnar [Mon, 23 Mar 2009 21:23:16 +0000 (22:23 +0100)]
perf_counter tools: fix build warning in kerneltop.c
Fix:
kerneltop.c: In function ‘record_ip’:
kerneltop.c:1005: warning: format ‘%016llx’ expects type ‘long long unsigned int’, but argument 2 has type ‘uint64_t’
Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Paul Mackerras <paulus@samba.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Orig-LKML-Reference: <20090323172417.677932499@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Peter Zijlstra [Mon, 23 Mar 2009 17:22:10 +0000 (18:22 +0100)]
perf_counter: new output ABI - part 1
Impact: Rework the perfcounter output ABI
use sys_read() only for instant data and provide mmap() output for all
async overflow data.
The first mmap() determines the size of the output buffer. The mmap()
size must be a PAGE_SIZE multiple of 1+pages, where pages must be a
power of 2 or 0. Further mmap()s of the same fd must have the same
size. Once all maps are gone, you can again mmap() with a new size.
In case of 0 extra pages there is no data output and the first page
only contains meta data.
When there are data pages, a poll() event will be generated for each
full page of data. Furthermore, the output is circular. This means
that although 1 page is a valid configuration, its useless, since
we'll start overwriting it the instant we report a full page.
Future work will focus on the output format (currently maintained)
where we'll likey want each entry denoted by a header which includes a
type and length.
Further future work will allow to splice() the fd, also containing the
async overflow data -- splice() would be mutually exclusive with
mmap() of the data.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org>
Orig-LKML-Reference: <20090323172417.470536358@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
H. Peter Anvin [Thu, 2 Apr 2009 00:21:56 +0000 (17:21 -0700)]
mutex: drop "inline" from mutex_lock() inside kernel/mutex.c
Impact: build fix
mutex_lock() is was defined inline in kernel/mutex.c, but wasn't
declared so not in <linux/mutex.h>. This didn't cause a problem until
checkin 3a2d367d9aabac486ac4444c6c7ec7a1dab16267 added the
atomic_dec_and_mutex_lock() inline in between declaration and
definion.
This broke building with CONFIG_ALLOW_WARNINGS=n, e.g. make
allnoconfig.
Either from the source code nor the allnoconfig binary output I cannot
find any internal references to mutex_lock() in kernel/mutex.c, so
presumably this "inline" is now-useless legacy.
Cc: Eric Paris <eparis@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org>
Orig-LKML-Reference: <tip-3a2d367d9aabac486ac4444c6c7ec7a1dab16267@git.kernel.org> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Eric Paris [Mon, 23 Mar 2009 17:22:09 +0000 (18:22 +0100)]
mutex: add atomic_dec_and_mutex_lock()
Much like the atomic_dec_and_lock() function in which we take an hold a
spin_lock if we drop the atomic to 0 this function takes and holds the
mutex if we dec the atomic to 0.
Signed-off-by: Eric Paris <eparis@redhat.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org>
Orig-LKML-Reference: <20090323172417.410913479@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Paul Mackerras [Mon, 23 Mar 2009 17:22:08 +0000 (18:22 +0100)]
perf_counter: add an mmap method to allow userspace to read hardware counters
Impact: new feature giving performance improvement
This adds the ability for userspace to do an mmap on a hardware counter
fd and get access to a read-only page that contains the information
needed to translate a hardware counter value to the full 64-bit
counter value that would be returned by a read on the fd. This is
useful on architectures that allow user programs to read the hardware
counters, such as PowerPC.
The mmap will only succeed if the counter is a hardware counter
monitoring the current process.
On my quad 2.5GHz PowerPC 970MP machine, userspace can read a counter
and translate it to the full 64-bit value in about 30ns using the
mmapped page, compared to about 830ns for the read syscall on the
counter, so this does give a significant performance improvement.
Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Orig-LKML-Reference: <20090323172417.297057964@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Wu Fengguang [Fri, 20 Mar 2009 02:08:09 +0000 (10:08 +0800)]
perf_counter tools: cut down default count for cpu-cycles
In my system, it takes kerneltop dozens of minutes to
show up usable numbers. Make the default count 100 times
smaller fixed this long startup latency.
I'm not sure if it's the right solution though.
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Wu Fengguang [Fri, 20 Mar 2009 02:08:06 +0000 (10:08 +0800)]
perf_counter tools: move remaining code into kerneltop.c
- perfstat.c can be safely removed now
- perfstat: -s => -a for system wide accounting
- kerneltop: add -S/--stat for perfstat mode
- minor adjustments to kerneltop --help, perfstat --help
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Wu Fengguang [Fri, 20 Mar 2009 02:08:04 +0000 (10:08 +0800)]
perf_counter tools: support symbolic event names in kerneltop
- kerneltop: --event_id => --event
- kerneltop: can accept SW event types now
- perfstat: it used to implicitly add event -2(task-clock),
the new code no longer does this. Shall we?
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Paul Mackerras [Sat, 21 Mar 2009 04:31:47 +0000 (15:31 +1100)]
perf_counter: fix type/event_id layout on big-endian systems
Impact: build fix for powerpc
Commit db3a944aca35ae61 ("perf_counter: revamp syscall input ABI")
expanded the hw_event.type field into a union of structs containing
bitfields. In particular it introduced a type field and a raw_type
field, with the intention that the 1-bit raw_type field should
overlay the most-significant bit of the 8-bit type field, and in fact
perf_counter_alloc() now assumes that (or at least, assumes that
raw_type doesn't overlay any of the bits that are 1 in the values of
PERF_TYPE_{HARDWARE,SOFTWARE,TRACEPOINT}).
Unfortunately this is not true on big-endian systems such as PowerPC,
where bitfields are laid out from left to right, i.e. from most
significant bit to least significant. This means that setting
hw_event.type = PERF_TYPE_SOFTWARE will set hw_event.raw_type to 1.
This fixes it by making the layout depend on whether or not
__BIG_ENDIAN_BITFIELD is defined. It's a bit ugly, but that's what
we get for using bitfields in a user/kernel ABI.
Also, that commit didn't fix up some places in arch/powerpc/kernel/
perf_counter.c where hw_event.raw and hw_event.event_id were used.
This fixes them too.
Paul Mackerras [Thu, 19 Mar 2009 19:26:20 +0000 (20:26 +0100)]
perf_counter: powerpc: clean up perc_counter_interrupt
Impact: cleanup
This updates the powerpc perf_counter_interrupt following on from the
"perf_counter: unify irq output code" patch. Since we now use the
generic perf_counter_output code, which sets the perf_counter_pending
flag directly, we no longer need the need_wakeup variable.
This removes need_wakeup and makes perf_counter_interrupt use
get_perf_counter_pending() instead.
Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org>
Orig-LKML-Reference: <20090319194234.024464535@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Peter Zijlstra [Thu, 19 Mar 2009 19:26:18 +0000 (20:26 +0100)]
perf_counter: revamp syscall input ABI
Impact: modify ABI
The hardware/software classification in hw_event->type became a little
strained due to the addition of tracepoint tracing.
Instead split up the field and provide a type field to explicitly specify
the counter type, while using the event_id field to specify which event to
use.
Raw counters still work as before, only the raw config now goes into
raw_event.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Steven Rostedt <rostedt@goodmis.org>
Orig-LKML-Reference: <20090319194233.836807573@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Paul Mackerras [Mon, 16 Mar 2009 10:00:00 +0000 (21:00 +1100)]
perf_counter: abstract wakeup flag setting in core to fix powerpc build
Impact: build fix for powerpc
Commit bd753921015e7905 ("perf_counter: software counter event
infrastructure") introduced a use of TIF_PERF_COUNTERS into the core
perfcounter code. This breaks the build on powerpc because we use
a flag in a per-cpu area to signal wakeups on powerpc rather than
a thread_info flag, because the thread_info flags have to be
manipulated with atomic operations and are thus slower than per-cpu
flags.
This fixes the by changing the core to use an abstracted
set_perf_counter_pending() function, which is defined on x86 to set
the TIF_PERF_COUNTERS flag and on powerpc to set the per-cpu flag
(paca->perf_counter_pending). It changes the previous powerpc
definition of set_perf_counter_pending to not take an argument and
adds a clear_perf_counter_pending, so as to simplify the definition
on x86.
On x86, set_perf_counter_pending() is defined as a macro. Defining
it as a static inline in arch/x86/include/asm/perf_counters.h causes
compile failures because <asm/perf_counters.h> gets included early in
<linux/sched.h>, and the definitions of set_tsk_thread_flag etc. are
therefore not available in <asm/perf_counters.h>. (On powerpc this
problem is avoided by defining set_perf_counter_pending etc. in
<asm/hw_irq.h>.)
Tim Blechmann [Sat, 14 Mar 2009 13:29:25 +0000 (14:29 +0100)]
perf_counter: include missing header
Impact: build fix
In order to compile a kernel with performance counter patches,
<asm/irq_regs.h> has to be included to provide the declaration of
struct pt_regs *get_irq_regs(void);
[ This bug was masked by unrelated x86 header file changes in the
x86 tree, but occurs in the tip:perfcounters/core standalone
tree. ]
Signed-off-by: Tim Blechmann <tim@klingt.org>
Orig-LKML-Reference: <20090314142925.49c29c17@thinkpad> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Peter Zijlstra [Fri, 13 Mar 2009 11:21:36 +0000 (12:21 +0100)]
perf_counter: add an event_list
I noticed that the counter_list only includes top-level counters, thus
perf_swcounter_event() will miss sw-counters in groups.
Since perf_swcounter_event() also wants an RCU safe list, create a new
event_list that includes all counters and uses RCU list ops and use call_rcu
to free the counter structure.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Provide generic software counter infrastructure that supports
software events.
This will be used to allow sample based profiling based on software
events such as pagefaults. The current infrastructure can only
provide a count of such events, no place information.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Peter Zijlstra [Fri, 13 Mar 2009 11:21:30 +0000 (12:21 +0100)]
perf_counter: add comment to barrier
We need to ensure the enabled=0 write happens before we
start disabling the actual counters, so that a pcm_amd_enable()
will not enable one underneath us.
I think the race is impossible anyway, we always balance the
ops within any one context and perform enable() with IRQs disabled.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Merge branch 'audit.b62' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/audit-current
* 'audit.b62' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/audit-current:
Audit: remove spaces from audit_log_d_path
audit: audit_set_auditable defined but not used
audit: incorrect ref counting in audit tree tag_chunk
audit: Fix possible return value truncation in audit_get_context()
audit: ignore terminating NUL in AUDIT_USER_TTY messages
Audit: fix handling of 'strings' with NULL characters
make the e->rule.xxx shorter in kernel auditfilter.c
auditsc: fix kernel-doc notation
audit: EXECVE record - removed bogus newline
Merge branch 'for-next' of git://git.o-hand.com/linux-mfd
* 'for-next' of git://git.o-hand.com/linux-mfd:
mfd: fix da903x warning
mfd: fix MAINTAINERS entry
mfd: Use the value of the final spin when reading the AUXADC
mfd: Storage class should be before const qualifier
mfd: PASIC3: supply clock_rate to DS1WM via driver_data
mfd: remove DS1WM clock handling
mfd: remove unused PASIC3 bus_shift field
pxa/magician: remove deprecated .bus_shift from PASIC3 platform_data
mfd: convert PASIC3 to use MFD core
mfd: convert DS1WM to use MFD core
mfd: Support active high IRQs on WM835x
mfd: Use bulk read to fill WM8350 register cache
mfd: remove duplicated #include from pcf50633
Merge branch 'for-linus' of git://repo.or.cz/cris-mirror
* 'for-linus' of git://repo.or.cz/cris-mirror:
CRISv32: Remove extraneous space between -I and the path.
cris: convert obsolete hw_interrupt_type to struct irq_chip
BUG to BUG_ON changes
cpumask: use mm_cpumask() wrapper: cris
cpumask: Use accessors code.: cris
cpumask: prepare for iterators to only go to nr_cpu_ids/nr_cpumask_bits.: cris
* git://git.kernel.org/pub/scm/linux/kernel/git/lethal/sh-2.6: (23 commits)
sh: sh7785lcr: Map whole PCI address space.
sh: Fix up DSP context save/restore.
sh: Fix up number of on-chip DMA channels on SH7091.
sh: update defconfigs.
sh: Kill off broken direct-mapped cache mode.
sh: Wire up ARCH_HAS_DEFAULT_IDLE for cpuidle.
sh: Add a command line option for disabling I/O trapping.
sh: Select ARCH_HIBERNATION_POSSIBLE.
sh: migor: Fix up CEU use flags.
input: migor_ts: add wakeup support
rtc: rtc-sh: use set_irq_wake()
input: sh_keysc: use enable/disable_irq_wake()
sh: intc: set_irq_wake() support
sh: intc: install enable, disable and shutdown callbacks
clocksource: sh_cmt: use remove_irq() and remove clockevent workaround
sh: ap325 and Migo-R use new sh_mobile_ceu_info flags
sh: Fix up -Wformat-security whining.
sh: ap325rxa: Add ov772x support, again.
sh: Sanitize asm/mmu.h for assembly use.
sh: Tidy up sh7786 pinmux table.
...
Merge branch 'avr32-arch' of git://git.kernel.org/pub/scm/linux/kernel/git/hskinnemoen/avr32-2.6
* 'avr32-arch' of git://git.kernel.org/pub/scm/linux/kernel/git/hskinnemoen/avr32-2.6:
avr32: add hardware handshake support to atmel_serial
avr32: add RTS/CTS/CLK pin selection for the USARTs
Add RTC support for Merisc boards
avr32: at32ap700x: setup DMA for AC97C in the machine code
avr32: at32ap700x: setup DMA for ABDAC in the machine code
Add Merisc board support
avr32: use gpio_is_valid() to check USBA vbus_pin I/O line
atmel-usba-udc: use gpio_is_valid() to check vbus_pin I/O line
avr32: fix timing LCD parameters for EVKLCD10X boards
avr32: use GPIO line PB15 on EVKLCD10x boards for backlight
avr32: configure MCI detect and write protect pins for EVKLCD10x boards
avr32: set pin mask to alternative 18 bpp for EVKLCD10x boards
avr32: add pin mask for 18-bit color on the LCD controller
avr32: fix 15-bit LCDC pin mask to use MSB lines
Merge branch 'tracing-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'tracing-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (413 commits)
tracing, net: fix net tree and tracing tree merge interaction
tracing, powerpc: fix powerpc tree and tracing tree interaction
ring-buffer: do not remove reader page from list on ring buffer free
function-graph: allow unregistering twice
trace: make argument 'mem' of trace_seq_putmem() const
tracing: add missing 'extern' keywords to trace_output.h
tracing: provide trace_seq_reserve()
blktrace: print out BLK_TN_MESSAGE properly
blktrace: extract duplidate code
blktrace: fix memory leak when freeing struct blk_io_trace
blktrace: fix blk_probes_ref chaos
blktrace: make classic output more classic
blktrace: fix off-by-one bug
blktrace: fix the original blktrace
blktrace: fix a race when creating blk_tree_root in debugfs
blktrace: fix timestamp in binary output
tracing, Text Edit Lock: cleanup
tracing: filter fix for TRACE_EVENT_FORMAT events
ftrace: Using FTRACE_WARN_ON() to check "freed record" in ftrace_release()
x86: kretprobe-booster interrupt emulation code fix
...
Fix up trivial conflicts in
arch/parisc/include/asm/ftrace.h
include/linux/memory.h
kernel/extable.c
kernel/module.c
Eric Paris [Tue, 10 Mar 2009 22:00:14 +0000 (18:00 -0400)]
Audit: remove spaces from audit_log_d_path
audit_log_d_path had spaces in the strings which would be emitted on the
error paths. This patch simply replaces those spaces with an _ or removes
the needless spaces entirely.
Signed-off-by: Eric Paris <eparis@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Eric Paris [Mon, 26 Jan 2009 23:09:45 +0000 (18:09 -0500)]
audit: audit_set_auditable defined but not used
after 0590b9335a1c72a3f0defcc6231287f7817e07c8 audit_set_auditable() is now only
used by the audit tree code. If CONFIG_AUDIT_TREE is unset it will be defined
but unused. This patch simply moves the function inside a CONFIG_AUDIT_TREE
block.
cc1: warnings being treated as errors
/home/acme_unencrypted/git/linux-2.6-tip/kernel/auditsc.c:745: error: ‘audit_set_auditable’ defined but not used
make[2]: *** [kernel/auditsc.o] Error 1
make[1]: *** [kernel] Error 2
make[1]: *** Waiting for unfinished jobs....
Signed-off-by: Eric Paris <eparis@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Eric Paris [Tue, 13 Jan 2009 22:32:40 +0000 (17:32 -0500)]
audit: incorrect ref counting in audit tree tag_chunk
tag_chunk has bad exit paths in which the inotify ref counting is wrong.
At the top of the function we found &old_watch using inotify_find_watch().
inotify_find_watch takes a reference to the watch. This is never dropped
on an error path.
Signed-off-by: Eric Paris <eparis@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Paul Moore [Wed, 1 Apr 2009 19:47:27 +0000 (15:47 -0400)]
audit: Fix possible return value truncation in audit_get_context()
The audit subsystem treats syscall return codes as type long, unfortunately
the audit_get_context() function mistakenly converts the return code to an
int type in the parameters which could cause problems on systems where the
sizeof(int) != sizeof(long).
Signed-off-by: Paul Moore <paul.moore@hp.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Miloslav Trmac [Thu, 19 Mar 2009 13:52:47 +0000 (09:52 -0400)]
audit: ignore terminating NUL in AUDIT_USER_TTY messages
AUDIT_USER_TTY, like all other messages sent from user-space, is sent
NUL-terminated. Unlike other user-space audit messages, which come only
from trusted sources, AUDIT_USER_TTY messages are processed using
audit_log_n_untrustedstring().
This patch modifies AUDIT_USER_TTY handling to ignore the trailing NUL
and use the "quoted_string" representation of the message if possible.
Signed-off-by: Miloslav Trmac <mitr@redhat.com> Cc: Eric Paris <eparis@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Steve Grubb <sgrubb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Miloslav Trmac [Thu, 19 Mar 2009 13:48:27 +0000 (09:48 -0400)]
Audit: fix handling of 'strings' with NULL characters
currently audit_log_n_untrustedstring() uses audit_string_contains_control()
to check if the 'string' has any control characters. If the 'string' has an
embedded NULL audit_string_contains_control() will return that the data has
no control characters and will then pass the string to audit_log_n_string
with the total length, not the length up to the first NULL.
audit_log_n_string() does a memcpy of the entire length and so the actual
audit record emitted may then contain a NULL and then whatever random memory
is after the NULL.
Since we want to log the entire octet stream (if we can't trust the data
to be a string we can't trust that a NULL isn't actually a part of it)
we should just consider NULL as a control character. If the caller is
certain they want to stop at the first NULL they should be using
audit_log_untrustedstring.
Signed-off-by: Eric Paris <eparis@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Zhenwen Xu [Thu, 12 Mar 2009 14:16:12 +0000 (22:16 +0800)]
make the e->rule.xxx shorter in kernel auditfilter.c
make the e->rule.xxx shorter in kernel/auditfilter.c
--
---------------------------------
Zhenwen Xu - Open and Free
Home Page: http://zhwen.org
My Studio: http://dim4.cn
>From 99692dc640b278f1cb1a15646ce42f22e89c0f77 Mon Sep 17 00:00:00 2001
From: Zhenwen Xu <Helight.Xu@gmail.com>
Date: Thu, 12 Mar 2009 22:04:59 +0800
Subject: [PATCH] make the e->rule.xxx shorter in kernel/auditfilter.c
Signed-off-by: Zhenwen Xu <Helight.Xu@gmail.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Randy Dunlap [Mon, 5 Jan 2009 21:41:13 +0000 (13:41 -0800)]
auditsc: fix kernel-doc notation
Fix auditsc kernel-doc notation:
Warning(linux-2.6.28-git7//kernel/auditsc.c:2156): No description found for parameter 'attr'
Warning(linux-2.6.28-git7//kernel/auditsc.c:2156): Excess function parameter 'u_attr' description in '__audit_mq_open'
Warning(linux-2.6.28-git7//kernel/auditsc.c:2204): No description found for parameter 'notification'
Warning(linux-2.6.28-git7//kernel/auditsc.c:2204): Excess function parameter 'u_notification' description in '__audit_mq_notify'
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
cc: Al Viro <viro@zeniv.linux.org.uk>
cc: Eric Paris <eparis@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Jiri Pirko [Fri, 9 Jan 2009 15:44:16 +0000 (16:44 +0100)]
audit: EXECVE record - removed bogus newline
(updated)
Added hunk that changes the comment, the rest is the same.
EXECVE records contain a newline after every argument. auditd converts
"\n" to " " so you cannot see newlines even in raw logs, but they're
there nevertheless. If you're not using auditd, you need to work round
them. These '\n' chars are can be easily replaced by spaces when
creating record in kernel. Note there is no need for trailing '\n' in
an audit record.
record before this patch:
"type=EXECVE msg=audit(1231421801.566:31): argc=4 a0=\"./test\"\na1=\"a\"\na2=\"b\"\na3=\"c\"\n"
record after this patch:
"type=EXECVE msg=audit(1231421801.566:31): argc=4 a0=\"./test\" a1=\"a\" a2=\"b\" a3=\"c\""
Signed-off-by: Jiri Pirko <jpirko@redhat.com> Acked-by: Eric Paris <eparis@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Merge branch 'bzip2-lzma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-tip
* 'bzip2-lzma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-tip:
bzip2/lzma: quiet Kconfig warning for INITRAMFS_COMPRESSION_NONE
* git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-cpumask: (36 commits)
cpumask: remove cpumask allocation from idle_balance, fix
numa, cpumask: move numa_node_id default implementation to topology.h, fix
cpumask: remove cpumask allocation from idle_balance
x86: cpumask: x86 mmio-mod.c use cpumask_var_t for downed_cpus
x86: cpumask: update 32-bit APM not to mug current->cpus_allowed
x86: microcode: cleanup
x86: cpumask: use work_on_cpu in arch/x86/kernel/microcode_core.c
cpumask: fix CONFIG_CPUMASK_OFFSTACK=y cpu hotunplug crash
numa, cpumask: move numa_node_id default implementation to topology.h
cpumask: convert node_to_cpumask_map[] to cpumask_var_t
cpumask: remove x86 cpumask_t uses.
cpumask: use cpumask_var_t in uv_flush_tlb_others.
cpumask: remove cpumask_t assignment from vector_allocation_domain()
cpumask: make Xen use the new operators.
cpumask: clean up summit's send_IPI functions
cpumask: use new cpumask functions throughout x86
x86: unify cpu_callin_mask/cpu_callout_mask/cpu_initialized_mask/cpu_sibling_setup_mask
cpumask: convert struct cpuinfo_x86's llc_shared_map to cpumask_var_t
cpumask: convert node_to_cpumask_map[] to cpumask_var_t
x86: unify 32 and 64-bit node_to_cpumask_map
...
* git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-module-and-param:
module: use strstarts()
strstarts: helper function for !strncmp(str, prefix, strlen(prefix))
arm: allow usage of string functions in linux/string.h
module: don't use stop_machine on module load
module: create a request_module_nowait()
module: include other structures in module version check
module: remove the SHF_ALLOC flag on the __versions section.
module: clarify the force-loading taint message.
module: Export symbols needed for Ksplice
Ksplice: Add functions for walking kallsyms symbols
module: remove module_text_address()
module: __module_address
module: Make find_symbol return a struct kernel_symbol
kernel/module.c: fix an unused goto label
param: fix charp parameters set via sysfs
Fix trivial conflicts in kernel/extable.c manually.
Merge branch 'core/debugobjects' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'core/debugobjects' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
debugobjects: delay free of internal objects
debugobjects: replace static objects when slab cache becomes available
debug_objects: add boot-parameter toggle to turn object debugging off again
Merge branch 'printk-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'printk-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
printk: correct the behavior of printk_timed_ratelimit()
vsprintf: unify the format decoding layer for its 3 users, cleanup
fix regression from "vsprintf: unify the format decoding layer for its 3 users"
vsprintf: fix bug in negative value printing
vsprintf: unify the format decoding layer for its 3 users
vsprintf: add binary printf
printk: introduce printk_once()
Fix trivial conflicts (printk_once vs log_buf_kexec_setup() added near
each other) in include/linux/kernel.h.
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/drzeus/mmc
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/drzeus/mmc: (42 commits)
atmel-mci: fix sdc_reg typo
tmio_mmc: add maintainer
mmc: Add OpenFirmware bindings for SDHCI driver
sdhci: Add quirk for forcing maximum block size to 2048 bytes
sdhci: Add quirk for controllers that need IRQ re-init after reset
sdhci: Add quirk for controllers that need small delays for PIO
sdhci: Add set_clock callback and a quirk for nonstandard clocks
sdhci: Add get_{max,timeout}_clock callbacks
sdhci: Add support for hosts reporting inverted write-protect state
sdhci: Add support for card-detection polling
sdhci: Enable only relevant (DMA/PIO) interrupts during transfers
sdhci: Split card-detection IRQs management from sdhci_init()
sdhci: Add support for bus-specific IO memory accessors
mmc_spi: adjust for delayed data token response
omap_hsmmc: Wait for SDBP
omap_hsmmc: Fix MMC3 dma
omap_hsmmc: Disable SDBP at suspend
omap_hsmmc: Do not prefix slot name
omap_hsmmc: Allow cover switch to cause rescan
omap_hsmmc: Add 8-bit bus width mode support
...
Bjorn Helgaas [Mon, 30 Mar 2009 17:48:24 +0000 (17:48 +0000)]
ACPI: processor: use .notify method instead of installing handler directly
This patch adds a .notify() method. The presence of .notify() causes
Linux/ACPI to manage event handlers and notify handlers on our behalf,
so we don't have to install and remove them ourselves.
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com> CC: Zhang Rui <rui.zhang@intel.com> CC: Zhao Yakui <yakui.zhao@intel.com> CC: Venki Pallipadi <venkatesh.pallipadi@intel.com> CC: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> Signed-off-by: Len Brown <len.brown@intel.com>
Bjorn Helgaas [Mon, 30 Mar 2009 17:48:18 +0000 (17:48 +0000)]
ACPI: button: use .notify method instead of installing handler directly
This patch adds a .notify() method. The presence of .notify() causes
Linux/ACPI to manage event handlers and notify handlers on our behalf,
so we don't have to install and remove them ourselves.
Note that events from fixed hardware buttons now show up as a special
notify event, so to preserve user-space backward compatibility, we
convert that back to ACPI_BUTTON_NOTIFY_STATUS.
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com> Reviewed-by: Alex Chiang <achiang@hp.com> CC: Alexey Starikovskiy <alexey.y.starikovskiy@linux.intel.com> Signed-off-by: Len Brown <len.brown@intel.com>
Bjorn Helgaas [Mon, 30 Mar 2009 17:48:13 +0000 (17:48 +0000)]
ACPI: support acpi_device_ops .notify methods
This patch adds support for ACPI device driver .notify() methods. If
such a method is present, Linux/ACPI installs a handler for device
notifications (but not for system notifications such as Bus Check,
Device Check, etc). When a device notification occurs, Linux/ACPI
passes it on to the driver's .notify() method.
In most cases, this removes the need for drivers to install their own
handlers for device-specific notifications.
For fixed hardware devices like some power and sleep buttons, there's
no notification value because there's no control method to execute a
Notify opcode. When a fixed hardware device generates an event, we
handle it the same as a regular device notification, except we send
a ACPI_FIXED_HARDWARE_EVENT value. This is outside the normal 0x0-0xff
range used by Notify opcodes.
Several drivers install their own handlers for system Bus Check and
Device Check notifications so they can support hot-plug. This patch
doesn't affect that usage.
Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com> Reviewed-by: Alex Chiang <achiang@hp.com> Signed-off-by: Len Brown <len.brown@intel.com>
projects / karo-tx-linux.git / log