02 Jul, 2009
6 commits
-
Add infrastructure for module path discovery and section load addresses.
Signed-off-by: Mike Galbraith
Cc: Peter Zijlstra
Cc: Paul Mackerras
Cc: Arnaldo Carvalho de Melo
LKML-Reference:
Signed-off-by: Ingo Molnar -
perf_counter tools: Make symbol loading consistently return number of loaded symbols.
Signed-off-by: Mike Galbraith
Cc: Peter Zijlstra
Cc: Paul Mackerras
Cc: Arnaldo Carvalho de Melo
LKML-Reference:
Signed-off-by: Ingo Molnar -
Building builtin-stat.c reports the following errors:
cc1: warnings being treated as errors
builtin-stat.c: In function ‘run_perf_stat’:
builtin-stat.c:242: erreur: ignoring return value of ‘read’, declared with attribute warn_unused_result
builtin-stat.c:255: erreur: ignoring return value of ‘read’, declared with attribute warn_unused_result
make: *** [builtin-stat.o] Erreur 1This patch handles the possible pipe read failures.
Signed-off-by: Frederic Weisbecker
Cc: Peter Zijlstra
Cc: Mike Galbraith
Cc: Paul Mackerras
Cc: Anton Blanchard
Cc: Arnaldo Carvalho de Melo
LKML-Reference:
Signed-off-by: Ingo Molnar -
About every callchains recorded with perf record are filled up
including the internal perfcounter nmi frame:perf_callchain
perf_counter_overflow
intel_pmu_handle_irq
perf_counter_nmi_handler
notifier_call_chain
atomic_notifier_call_chain
notify_die
do_nmi
nmiWe want ignore this frame as it's not interesting for
instrumentation. To solve this, we simply ignore every frames
from nmi context.New example of "perf report -s sym -c" after this patch:
9.59% [k] search_by_key
4.88%
search_by_key
reiserfs_read_locked_inode
reiserfs_iget
reiserfs_lookup
do_lookup
__link_path_walk
path_walk
do_path_lookup
user_path_at
vfs_fstatat
vfs_lstat
sys_newlstat
system_call_fastpath
__lxstat
0x406fb13.19%
search_by_key
search_by_entry_key
reiserfs_find_entry
reiserfs_lookup
do_lookup
__link_path_walk
path_walk
do_path_lookup
user_path_at
vfs_fstatat
vfs_lstat
sys_newlstat
system_call_fastpath
__lxstat
0x406fb1
[...]For now this patch only solves the problem in x86-64.
Signed-off-by: Frederic Weisbecker
Cc: Peter Zijlstra
Cc: Mike Galbraith
Cc: Paul Mackerras
Cc: Anton Blanchard
Cc: Arnaldo Carvalho de Melo
LKML-Reference:
Signed-off-by: Ingo Molnar -
The copy we were using came from another copy I did for the dwarves
(pahole) package, that came from the kernel years ago.The only function that is used by the perf tools and that isn't in the
kernel is list_del_range, that I'm leaving in the perf tools only for
now.Signed-off-by: Arnaldo Carvalho de Melo
Cc: Frederic Weisbecker
Cc: Mike Galbraith
Cc: Peter Zijlstra
Cc: Paul Mackerras
LKML-Reference:
Signed-off-by: Ingo Molnar -
The tools/perf/util/rbtree.c copy already drifted by three
csets:4b324126e0c6c3a5080ca3ec0981e8766ed6f1ee
4c60117811171d867d4f27f17ea07d7419d45dae
16c047add3ceaf0ab882e3e094d1ec904d02312dSo remove the copy and use the lib/rbtree.c directly, sharing
the source code while still generating a separate object file,
since tools/perf uses a far more agressive -O6 switch.Signed-off-by: Arnaldo Carvalho de Melo
Cc: Mike Galbraith
Cc: Peter Zijlstra
Cc: Paul Mackerras
Cc: Frederic Weisbecker
LKML-Reference:
Signed-off-by: Ingo Molnar
01 Jul, 2009
34 commits
-
After:
$ ./perf list
List of pre-defined events (to be used in -e):
cpu-cycles OR cycles [Hardware event]
instructions [Hardware event]
cache-references [Hardware event]
cache-misses [Hardware event]
branch-instructions OR branches [Hardware event]
branch-misses [Hardware event]
bus-cycles [Hardware event]cpu-clock [Software event]
task-clock [Software event]
page-faults OR faults [Software event]
minor-faults [Software event]
major-faults [Software event]
context-switches OR cs [Software event]
cpu-migrations OR migrations [Software event]L1-d$-loads [Hardware cache event]
L1-d$-load-misses [Hardware cache event]
L1-d$-stores [Hardware cache event]
L1-d$-store-misses [Hardware cache event]
L1-d$-prefetches [Hardware cache event]
L1-d$-prefetch-misses [Hardware cache event]
L1-i$-loads [Hardware cache event]
L1-i$-load-misses [Hardware cache event]
L1-i$-prefetches [Hardware cache event]
L1-i$-prefetch-misses [Hardware cache event]
LLC-loads [Hardware cache event]
LLC-load-misses [Hardware cache event]
LLC-stores [Hardware cache event]
LLC-store-misses [Hardware cache event]
LLC-prefetches [Hardware cache event]
LLC-prefetch-misses [Hardware cache event]
dTLB-loads [Hardware cache event]
dTLB-load-misses [Hardware cache event]
dTLB-stores [Hardware cache event]
dTLB-store-misses [Hardware cache event]
dTLB-prefetches [Hardware cache event]
dTLB-prefetch-misses [Hardware cache event]
iTLB-loads [Hardware cache event]
iTLB-load-misses [Hardware cache event]
branch-loads [Hardware cache event]
branch-load-misses [Hardware cache event]rNNN [raw hardware event descriptor]
Signed-off-by: Jaswinder Singh Rajput
Cc: Peter Zijlstra
Cc: Mike Galbraith
Cc: Paul Mackerras
Cc: Arnaldo Carvalho de Melo
Cc: Frederic Weisbecker
LKML-Reference:
Signed-off-by: Ingo Molnar -
MATCH_EVENT is useful:
1. for multiple attrs checking
2. avoid repetition of PERF_TYPE_ and PERF_COUNT_ and save space
3. avoids line breakageSigned-off-by: Jaswinder Singh Rajput
Cc: Peter Zijlstra
LKML-Reference:
Signed-off-by: Ingo Molnar -
Enable -Wextra. This found a few real bugs plus a number
of signed/unsigned type mismatches/uncleanlinesses. It
also required a few annotationsAll things considered it was still worth it so lets try with
this enabled for now.Cc: Peter Zijlstra
Cc: Mike Galbraith
Cc: Paul Mackerras
Cc: Arnaldo Carvalho de Melo
Cc: Frederic Weisbecker
LKML-Reference:
Signed-off-by: Ingo Molnar -
Fix:
builtin-report.c: In function ‘hist_entry__add’:
builtin-report.c:1015: error: case label not within a switch statement
builtin-report.c:1017: error: break statement not within loop or switchCc: Peter Zijlstra
Cc: Mike Galbraith
Cc: Paul Mackerras
Cc: Arnaldo Carvalho de Melo
Cc: Frederic Weisbecker
LKML-Reference:
Signed-off-by: Ingo Molnar -
This reworks the parser for event descriptors to make it more
consistent in what it accepts. It is now structured as a
recursive descent parser for the following grammar:events ::= event ( ("," | space) space* event )*
event ::= ( raw_event | numeric_event | symbolic_event |
generic_hw_event ) [ event_modifier ]
raw_event ::= "r" hex_number
numeric_event ::= number ":" number
number ::= decimal_number | "0x" hex_number | "0" octal_number
symbolic_event ::= string_from_event_symbols_array
generic_hw_event::= cache_type ( "-" ( cache_op | cache_result ) )*
event_modifier ::= ":" ( "u" | "k" | "h" )+with the extra restriction that you can have at most one
cache_op and at most one cache_result.We pass the current string pointer by reference (i.e. as a
const char **) to the various parsing functions so that they
can advance the pointer to indicate how much they consumed.
They return 0 if they didn't recognize the thing at the pointer
or 1 if they did (and advance the pointer past it).This also fixes parse_aliases to take the longest matching
alias from the table, not the first one. Otherwise "l1-data"
would match the "l1-d" alias and the "ata" would not be
consumed.This allows event modifiers indicating what processor modes to
count in to be applied to any event, not just numeric events,
and adds a ":h" modifier to indicate counting in hypervisor
mode. Specifying ":u" now sets both exclude_kernel and
exclude_hv, and so on. Multiple modes can be specified, e.g.
":uk" will count in user or hypervisor mode (i.e. only
exclude_kernel will be set).Signed-off-by: Paul Mackerras
Cc: Peter Zijlstra
Cc: Mike Galbraith
Cc: Paul Mackerras
Cc: Arnaldo Carvalho de Melo
Cc: Frederic Weisbecker
LKML-Reference:
Signed-off-by: Ingo Molnar -
POWER7 has the same PR/HV bit layout as POWER6, so set the flag.
Signed-off-by: Anton Blanchard
Acked-by: Paul Mackerras
Cc: a.p.zijlstra@chello.nl
Cc: benh@kernel.crashing.org
LKML-Reference:
Signed-off-by: Ingo Molnar -
The symbol resolving has of course revealed some bugs in the
callchain tree handling. This patch fixes some of them,
including:- inherit the children from the parents while splitting a node
- fix list range moving
- fix indexes setting in callchains
- create a child on the current node if the path doesn't match in
the existent children (was only done on the root)
- compare using symbols when possible so that we can match a function
using any ip inside by referring to its start address.The practical effects are:
- remove double callchains
- fix upside down or any random order of callchains
- fix wrong paths
- fix bad hits and percentage accountsSigned-off-by: Frederic Weisbecker
Cc: Peter Zijlstra
Cc: Mike Galbraith
Cc: Paul Mackerras
Cc: Anton Blanchard
Cc: Arnaldo Carvalho de Melo
LKML-Reference:
Signed-off-by: Ingo Molnar -
This patch resolves the names, when possible, of each ip
present in the callchains while using the -c option with perf
report.Example:
5.40% [k] __d_lookup
5.37%
perf_callchain
perf_counter_overflow
intel_pmu_handle_irq
perf_counter_nmi_handler
notifier_call_chain
atomic_notifier_call_chain
notify_die
do_nmi
nmi
do_lookup
__link_path_walk
path_walk
do_path_lookup
user_path_at
sys_faccessat
sys_access
system_call_fastpath
0x7fb609846f770.01%
perf_callchain
perf_counter_overflow
intel_pmu_handle_irq
perf_counter_nmi_handler
notifier_call_chain
atomic_notifier_call_chain
notify_die
do_nmi
nmi
do_lookup
__link_path_walk
path_walk
do_path_lookup
user_path_at
sys_faccessatSigned-off-by: Frederic Weisbecker
Cc: Peter Zijlstra
Cc: Mike Galbraith
Cc: Paul Mackerras
Cc: Anton Blanchard
Cc: Arnaldo Carvalho de Melo
LKML-Reference:
Signed-off-by: Ingo Molnar -
Fix a confusion while giving the size of a callchain list
during its allocation. We are using the wrong structure size.Signed-off-by: Frederic Weisbecker
Cc: Peter Zijlstra
Cc: Mike Galbraith
Cc: Paul Mackerras
Cc: Anton Blanchard
Cc: Arnaldo Carvalho de Melo
LKML-Reference:
Signed-off-by: Ingo Molnar -
Merge reason: this branch was on a .30-ish base before, update
it to an almost-.31-rc2 upstream base to pick up fixes.Signed-off-by: Ingo Molnar
-
* 'kmemleak' of git://linux-arm.org/linux-2.6:
kmemleak: Inform kmemleak about pid_hash
kmemleak: Do not warn if an unknown object is freed
kmemleak: Do not report new leaked objects if the scanning was stopped
kmemleak: Slightly change the policy on newly allocated objects
kmemleak: Do not trigger a scan when reading the debug/kmemleak file
kmemleak: Simplify the reports logged by the scanning thread
kmemleak: Enable task stacks scanning by default
kmemleak: Allow the early log buffer to be configurable. -
* git://git.kernel.org/pub/scm/linux/kernel/git/agk/linux-2.6-dm:
dm table: fix blk_stack_limits arg to use bytes not sectors
dm exception store: really fix type lookup -
…x/kernel/git/tip/linux-2.6-tip
* 'perfcounters-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (47 commits)
perf report: Add --symbols parameter
perf report: Add --comms parameter
perf report: Add --dsos parameter
perf_counter tools: Adjust only prelinked symbol's addresses
perf_counter: Provide a way to enable counters on exec
perf_counter tools: Reduce perf stat measurement overhead/skew
perf stat: Use percentages for scaling output
perf_counter, x86: Update x86_pmu after WARN()
perf stat: Micro-optimize the code: memcpy is only required if no event is selected and !null_run
perf stat: Improve output
perf stat: Fix multi-run stats
perf stat: Add -n/--null option to run without counters
perf_counter tools: Remove dead code
perf_counter: Complete counter swap
perf report: Print sorted callchains per histogram entries
perf_counter tools: Prepare a small callchain framework
perf record: Fix unhandled io return value
perf_counter tools: Add alias for 'l1d' and 'l1i'
perf-report: Add bare minimum PERF_EVENT_READ parsing
perf-report: Add modes for inherited stats and no-samples
... -
* 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6:
Add Fenghua Yu as temporary co-maintainer for ia64
[IA64] address compiler warnings perfmon.c/salinfo.c
[IA64] Remove unnecessary semicolons
[IA64] sprintf should not be used with same source & destination address -
Wire up new syscalls rt_tgsigqueueinfo and perf_counter_open.
Signed-off-by: David Howells
Signed-off-by: Linus Torvalds -
Wire up new syscalls rt_tgsigqueueinfo and perf_counter_open.
Signed-off-by: David Howells
Signed-off-by: Linus Torvalds -
Maximum file size for hostfs mounts defaults to 2GB, so bigger files cannot be
read/written through hostfs. This patch initializes the maximum file size to
MAX_LFS_SIZE.Addresses http://bugzilla.kernel.org/show_bug.cgi?id=13531
Signed-off-by: Wolfgang Illmeyer
Cc: Jeff Dike
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
A crappy macro prevents us unlocking on a fail path.
Expand the macro and unlock appropriatelly.
Signed-off-by: Jiri Slaby
Cc: Jens Axboe
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Make sure we do not actually request the RTC IRQ until the device driver
is fully ready to handle and process any interrupt. This way a spurious
interrupt won't crash the system (which may happen if the bootloader was
poking the RTC right before booting Linux).Signed-off-by: Mike Frysinger
Signed-off-by: Alessandro Zummo
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Block writes require 64 byte alignment. Since block writes could be used
with SGRAM or WRAM also refine the memory type detection to check for
either type before deciding to use the 64 byte alignment.Signed-off-by: Ville Syrjala
Tested-by: Mikulas Patocka
Cc: Krzysztof Helt
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Apparently HP OmniBook 500's BIOS doesn't like the way atyfb reprograms
the hardware. The BIOS will simply hang after a reboot. Fix the problem
by restoring the hardware to it's original state on reboot.Signed-off-by: Ville Syrjala
Cc: Mikulas Patocka
Cc: Krzysztof Helt
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
IRQ handling is wrong for any GPIO >= PL061_GPIO_NR.
Fix this by implementing and using a proper .to_irq method.
Signed-off-by: Baruch Siach
Cc: David Brownell
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Note that IRQ has not been initialized when kmalloc() fails.
Also, use DECLARE_BITMAP() to make the code clearer.
Signed-off-by: Baruch Siach
Cc: David Brownell
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Nathan reported that
| commit 73d60b7f747176dbdff826c4127d22e1fd3f9f74
| Author: Yinghai Lu
| Date: Tue Jun 16 15:33:00 2009 -0700
|
| page-allocator: clear N_HIGH_MEMORY map before we set it again
|
| SRAT tables may contains nodes of very small size. The arch code may
| decide to not activate such a node. However, currently the early boot
| code sets N_HIGH_MEMORY for such nodes. These nodes therefore seem to be
| active although these nodes have no present pages.
|
| For 64bit N_HIGH_MEMORY == N_NORMAL_MEMORY, so that works for 64 bit toounintentionally and incorrectly clears the cpuset.mems cgroup attribute on
an i386 kvm guest, meaning that cpuset.mems can not be used.Fix this by only clearing node_states[N_NORMAL_MEMORY] for 64bit only.
and need to do save/restore for that in find_zone_movable_pfnReported-by: Nathan Lynch
Tested-by: Nathan Lynch
Signed-off-by: Yinghai Lu
Cc: Christoph Lameter
Cc: Ingo Molnar ,
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
By writing a tasks's pid to the file, a process adds that task to that
cgroup/cpuset. But to add a cpu/mem to a cpuset, the new list of cpus
should be written to the cpuset.mems file which would replace the old list
of cpus. Make this clearer in the documentation.Signed-off-by: Nikanth Karthikesan
Signed-off-by: Li Zefan
Acked-by: Paul Menage
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
balance_dirty_pages can overreact and move all of the dirty pages to
writeback unnecessarily.balance_dirty_pages makes its decision to throttle based on the number of
dirty plus writeback pages that are over the calculated limit,so it will
continue to move pages even when there are plenty of pages in writeback
and less than the threshold still dirty.This allows it to overshoot its limits and move all the dirty pages to
writeback while waiting for the drives to catch up and empty the writeback
list.A simple fio test easily demonstrates this problem.
fio --name=f1 --directory=/disk1 --size=2G -rw=write --name=f2 --directory=/disk2 --size=1G --rw=write --startdelay=10
This is the simplest fix I could find, but I'm not entirely sure that it
alone will be enough for all cases. But it certainly is an improvement on
my desktop machine writing to 2 disks.Do we need something more for machines with large arrays where
bdi_threshold * number_of_drives is greater than the dirty_ratio ?Signed-off-by: Richard Kennedy
Acked-by: Peter Zijlstra
Cc: Jens Axboe
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
The file opened in acct_on and freshly stored in the ns->bacct struct can
be closed in acct_file_reopen by a concurrent call after we release
acct_lock and before we call mntput(file->f_path.mnt).Record file->f_path.mnt in a local variable and use this variable only.
Signed-off-by: Renaud Lottiaux
Signed-off-by: Louis Rilling
Cc: Al Viro
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Ion's cs.columbia.edu email address no longer works.
Signed-off-by: Joe Perches
Acked-by: Ion Badulescu
Cc: "David S. Miller"
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
When the 32-bit signed quantities get assigned to the u64 resource_size_t,
they are incorrectly sign-extended.Addresses http://bugzilla.kernel.org/show_bug.cgi?id=13253
Addresses http://bugzilla.kernel.org/show_bug.cgi?id=9905Signed-off-by: Zhang Rui
Reported-by: Leann Ogasawara
Cc: Pierre Ossman
Reported-by:
Tested-by:
Cc:
Cc: Jesse Barnes
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Bugfix to spi_bitbang infrastructure: make sure to always set transfer
parameters on the first pass through the message's per-transfer loop.
This can matter with drivers that replace the per-word or per-buffer
transfer primitives, on busses with multiple SPI devices.Previously, this could have started messages using the settings left after
previous messages. The problem was observed when a high speed chip
(m25p80 type flash) was running very slowly because a low speed device
(avr8 microcontroller) had previously used the bus. Similar faults could
have driven the low speed device too fast, or used an unexpected word
size.Acked-by: Steven A. Falco
Signed-off-by: David Brownell
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Add a mutex to avoid a circular locking problem between the mm layer
semaphore and fbdev ioctl mutex through the fb_mmap() call.Also, add mutex to all places where smem_start and smem_len fields change
so the mutex inside the fb_mmap() is actually used. Changing of these
fields before calling the framebuffer_register() are not mutexed.This is 2.6.31 material. It removes one lockdep (fb_mmap() and
register_framebuffer()) but there is still another one (fb_release() and
register_framebuffer()). It also cleans up handling of the smem_start and
smem_len fields used by mutexed section of the fb_mmap().Signed-off-by: Krzysztof Helt
Cc: Peter Zijlstra
Cc: "Rafael J. Wysocki"
Cc:
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Add a new spi_master.flags word listing constraints relevant to that
controller. Define the first constraint bit: a half duplex restriction.
Include that constraint in the OMAP1 MicroWire controller driver.Have the mmc_spi host be the first customer of this flag. Its coding
relies heavily on full duplex transfers, so it must fail when the
underlying controller driver won't perform them.(The spi_write_then_read routine could use it too: use the
temporarily-withdrawn full-duplex speedup unless this flag is set, in
which case the existing code applies. Similarly, any spi_master
implementing only SPI_3WIRE should set the flag.)Signed-off-by: David Brownell
Cc: Marek Szyprowski
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Add two new spi_device.mode bits to accomodate more protocol options, and
pass them through to usermode drivers:* SPI_NO_CS ... a second 3-wire variant, where the chipselect
line is removed instead of a data line; transfers are still
full duplex.This obviously has STRONG protocol implications since the
chipselect transitions can't be used to synchronize state
transitions with the SPI master.* SPI_READY ... defines open drain signal that's pulled low
to pause the clock. This defines a 5-wire variant (normal
4-wire SPI plus READY) and two 4-wire variants (READY plus
each of the 3-wire flavors).Such hardware flow control can be a big win. There are ADC
converters and flash chips that expose READY signals, but not
many host controllers support it today.The spi_bitbang code should be changed to use SPI_NO_CS instead of its
current nonportable hack. That's a mode most hardware can easily support
(unlike SPI_READY).Signed-off-by: David Brownell
Cc: "Paulraj, Sandeep"
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
show_pools() walks the page_list of a pool w/o protection against the list
modifications in alloc/free. Take pool->lock to avoid stomping into
nirvana.Signed-off-by: Thomas Gleixner
Signed-off-by: Matthew Wilcox
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
