08 Aug, 2010
1 commit
-
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ieee1394/linux1394-2.6: (82 commits)
firewire: core: add forgotten dummy driver methods, remove unused ones
firewire: add isochronous multichannel reception
firewire: core: small clarifications in core-cdev
firewire: core: remove unused code
firewire: ohci: release channel in error path
firewire: ohci: use memory barriers to order descriptor updates
tools/firewire: nosy-dump: increment program version
tools/firewire: nosy-dump: remove unused code
tools/firewire: nosy-dump: use linux/firewire-constants.h
tools/firewire: nosy-dump: break up a deeply nested function
tools/firewire: nosy-dump: make some symbols static or const
tools/firewire: nosy-dump: change to kernel coding style
tools/firewire: nosy-dump: work around segfault in decode_fcp
tools/firewire: nosy-dump: fix it on x86-64
tools/firewire: add userspace front-end of nosy
firewire: nosy: note ioctls in ioctl-number.txt
firewire: nosy: use generic printk macros
firewire: nosy: endianess fixes and annotations
firewire: nosy: annotate __user pointers and __iomem pointers
firewire: nosy: fix device shutdown with active client
...
07 Aug, 2010
1 commit
-
…git/tip/linux-2.6-tip
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (162 commits)
tracing/kprobes: unregister_trace_probe needs to be called under mutex
perf: expose event__process function
perf events: Fix mmap offset determination
perf, powerpc: fsl_emb: Restore setting perf_sample_data.period
perf, powerpc: Convert the FSL driver to use local64_t
perf tools: Don't keep unreferenced maps when unmaps are detected
perf session: Invalidate last_match when removing threads from rb_tree
perf session: Free the ref_reloc_sym memory at the right place
x86,mmiotrace: Add support for tracing STOS instruction
perf, sched migration: Librarize task states and event headers helpers
perf, sched migration: Librarize the GUI class
perf, sched migration: Make the GUI class client agnostic
perf, sched migration: Make it vertically scrollable
perf, sched migration: Parameterize cpu height and spacing
perf, sched migration: Fix key bindings
perf, sched migration: Ignore unhandled task states
perf, sched migration: Handle ignored migrate out events
perf: New migration tool overview
tracing: Drop cpparg() macro
perf: Use tracepoint_synchronize_unregister() to flush any pending tracepoint call
...Fix up trivial conflicts in Makefile and drivers/cpufreq/cpufreq.c
05 Aug, 2010
1 commit
-
* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/davej/cpufreq:
[CPUFREQ] Remove pointless printk from p4-clockmod.
[CPUFREQ] Fix section mismatch for powernow_cpu_init in powernow-k7.c
[CPUFREQ] Fix section mismatch for longhaul_cpu_init.
[CPUFREQ] Fix section mismatch for longrun_cpu_init.
[CPUFREQ] powernow-k8: Fix misleading variable naming
[CPUFREQ] Convert pci_table entries to PCI_VDEVICE (if PCI_ANY_ID is used)
[CPUFREQ] arch/x86/kernel/cpu/cpufreq: use for_each_pci_dev()
[CPUFREQ] fix brace coding style issue.
[CPUFREQ] x86 cpufreq: Make trace_power_frequency cpufreq driver independent
[CPUFREQ] acpi-cpufreq: Fix CPU_ANY CPUFREQ_{PRE,POST}CHANGE notification
[CPUFREQ] ondemand: don't synchronize sample rate unless multiple cpus present
[CPUFREQ] unexport (un)lock_policy_rwsem* functions
[CPUFREQ] ondemand: Refactor frequency increase code
[CPUFREQ] powernow-k8: On load failure, remind the user to enable support in BIOS setup
[CPUFREQ] powernow-k8: Limit Pstate transition latency check
[CPUFREQ] Fix PCC driver error path
[CPUFREQ] fix double freeing in error path of pcc-cpufreq
[CPUFREQ] pcc driver should check for pcch method before calling _OSC
[CPUFREQ] fix memory leak in cpufreq_add_dev
[CPUFREQ] revert "[CPUFREQ] remove rwsem lock from CPUFREQ_GOV_STOP call (second call site)"Manually fix up non-data merge conflict introduced by new calling
conventions for trace_power_start() in commit 6f4f2723d085 ("x86
cpufreq: Make trace_power_frequency cpufreq driver independent"), which
didn't update the intel_idle native hardware cpuidle driver.
04 Aug, 2010
3 commits
-
The event__process function is useful in processing /proc//maps. All of
the functions that are called from event__process are defined in util/event.c.
Though its defined in builtin-top.c, it could be reused for perf probe for
uprobes. Hence moving it to util/event.c and exporting the function.LKML-Reference:
Signed-off-by: Srikar Dronamraju
Signed-off-by: Arnaldo Carvalho de Melo -
Fix buggy-looking code which unnecessarily adjusts the file offset
fields read from /proc/*/maps.This may have gone unnoticed since the offset is usually 0 (and the
logic in util/symbol.c may work incorrectly for other offset values).Commiter note:
This fixes a bug introduced in 4af8b35, there is no need to shift pgoff
twice, the show_map_vma routine in fs/proc/task_mmu.c already converts
it from the number of pages to the size in bytes, and that is what
appears in /proc/PID/map.Cc: Nicolas Pitre
Cc: Will Deacon
LKML-Reference:
Signed-off-by: Dave Martin
Signed-off-by: Arnaldo Carvalho de Melo -
and fix the broken case if a core's frequency depends on others.
trace_power_frequency was only implemented in a rather ungeneric way
in acpi-cpufreq driver's target() function only.
-> Move the call to trace_power_frequency to
cpufreq.c:cpufreq_notify_transition() where CPUFREQ_POSTCHANGE
notifier is triggered.
This will support power frequency tracing by all cpufreq driverstrace_power_frequency did not trace frequency changes correctly when
the userspace governor was used or when CPU cores' frequency depend
on each other.
-> Moving this into the CPUFREQ_POSTCHANGE notifier and pass the cpu
which gets switched automatically fixes this.Robert Schoene provided some important fixes on top of my initial
quick shot version which are integrated in this patch:
- Forgot some changes in power_end trace (TP_printk/variable names)
- Variable dummy in power_end must now be cpu_id
- Use static 64 bit variable instead of unsigned int for cpu_idSigned-off-by: Thomas Renninger
CC: davej@redhat.com
CC: arjan@infradead.org
CC: linux-kernel@vger.kernel.org
CC: robert.schoene@tu-dresden.de
Tested-by: robert.schoene@tu-dresden.de
Signed-off-by: Dave Jones
03 Aug, 2010
3 commits
-
For a file with:
[root@emilia linux-2.6-tip]# perf report -D -fi allmodconfig-j32.perf.data | grep events:
TOTAL events: 36933
MMAP events: 9056
LOST events: 0
COMM events: 1702
EXIT events: 1887
THROTTLE events: 8
UNTHROTTLE events: 8
FORK events: 1894
READ events: 0
SAMPLE events: 22378
ATTR events: 0
EVENT_TYPE events: 0
TRACING_DATA events: 0
BUILD_ID events: 0
[root@emilia linux-2.6-tip]#Testing with valgrind and making perf_session__delete() a nop, so that
we can notice how many maps were actually deleted due to not having any
samples on it:==== HEAP SUMMARY:
Before:
==10339== in use at exit: 8,909,997 bytes in 68,690 blocks
==10339== total heap usage: 78,696 allocs, 10,007 frees, 11,925,853 bytes allocatedAfter:
==10506== in use at exit: 8,902,605 bytes in 68,606 blocks
==10506== total heap usage: 78,696 allocs, 10,091 frees, 11,925,853 bytes allocatedI.e. just 84 detected unmaps with no hits out of 9056 for this workload,
not much, but in some other long running workload this may save more
bytes.Cc: Frederic Weisbecker
Cc: Mike Galbraith
Cc: Peter Zijlstra
Cc: Stephane Eranian
LKML-Reference:
Signed-off-by: Arnaldo Carvalho de Melo -
If we receive two PERF_RECORD_EXIT for the same thread, we can end up
reusing session->last_match and trying to remove the thread twice from
the rb_tree, causing a segfault, so invalidade last_match in
perf_session__remove_thread.Receiving two PERF_RECORD_EXIT for the same thread is a bug, but its a
harmless one if we make the tool more robust, like this patch does.Cc: Frederic Weisbecker
Cc: Mike Galbraith
Cc: Peter Zijlstra
Cc: Stephane Eranian
LKML-Reference:
Signed-off-by: Arnaldo Carvalho de Melo -
Which is at perf_session__destroy_kernel_maps, counterpart to the
perf_session__create_kernel_maps where the kmap structure is located, just
after the vmlinux_maps.Make it also check if the kernel maps were actually created, which may not
be the case if, for instance, perf_session__new can't complete due to
permission problems in, for instance, a 'perf report' case, when a
segfault will take place, that is how this was noticed.The problem was introduced in d65a458, thus post .35.
This also adds code to release guest machines as them are also created
in perf_session__create_kernel_maps, so should be deleted on this newly
introduced counterpart, perf_session__destroy_kernel_maps.Cc: Frederic Weisbecker
Cc: Mike Galbraith
Cc: Peter Zijlstra
Cc: Stephane Eranian
LKML-Reference:
Signed-off-by: Arnaldo Carvalho de Melo
02 Aug, 2010
12 commits
-
Conflicts:
drivers/firewire/core-card.c
drivers/firewire/core-cdev.cand forgotten #include in drivers/firewire/ohci.c
Signed-off-by: Stefan Richter
-
Conflicts:
tools/perf/Makefile
tools/perf/util/hist.cMerge reason: Resolve the conflicts and update to latest upstream.
Signed-off-by: Ingo Molnar
-
…ic/random-tracing into perf/core
-
Librarize the task state and event headers helpers as they can
be generally useful.Signed-off-by: Frederic Weisbecker
Cc: Ingo Molnar
Cc: Peter Zijlstra
Cc: Arnaldo Carvalho de Melo
Cc: Paul Mackerras
Cc: Nikhil Rao
Cc: Tom Zanussi -
Export the GUI facility in the common library path. It is
going to be useful for other scheduler views.Signed-off-by: Frederic Weisbecker
Cc: Ingo Molnar
Cc: Peter Zijlstra
Cc: Arnaldo Carvalho de Melo
Cc: Paul Mackerras
Cc: Nikhil Rao
Cc: Tom Zanussi -
Make the perf migration GUI generic so that it can be reused for
other kinds of trace painting. No more notion of CPUs or runqueue
from the GUI class, it's now used as a library by the trace parser.Signed-off-by: Frederic Weisbecker
Cc: Ingo Molnar
Cc: Peter Zijlstra
Cc: Arnaldo Carvalho de Melo
Cc: Paul Mackerras
Cc: Nikhil Rao
Cc: Tom Zanussi -
With scheduler traces covering more than two cpus, rectangles
of the CPUs 3 and more are not visibles.This makes the vertical navigation scrollable so that all of the
CPUs rectangles are available.We also want to be able to zoom vertically, so that we can fit at
best the screen with CPU rectangles, but that's for later.Signed-off-by: Frederic Weisbecker
Cc: Ingo Molnar
Cc: Peter Zijlstra
Cc: Arnaldo Carvalho de Melo
Cc: Paul Mackerras
Cc: Nikhil Rao
Cc: Tom Zanussi -
Without vertical zoom, it is not possible to see all CPUs in a trace
taken on a larger machine. This patch parameterizes the height and
spacing of CPUs so that you can fit more cpus into the screen.Ideally we should dynamically size/space the CPU rectangles with some
minimum threshold. Until then, this patch is a stop-gap.Signed-off-by: Nikhil Rao
Cc: Ingo Molnar
Cc: Peter Zijlstra
Cc: Arnaldo Carvalho de Melo
Cc: Paul Mackerras
Cc: Tom Zanussi
Signed-off-by: Frederic Weisbecker -
EVT_KEY_DOWN and EVT_LEFT_DOWN events are not bound to the RootFrame
event handler. As a result, zoom/scroll via keyboard events do not
work. This patch adds the missing bindings.Signed-off-by: Nikhil Rao
Cc: Ingo Molnar
Cc: Peter Zijlstra
Cc: Arnaldo Carvalho de Melo
Cc: Paul Mackerras
Cc: Tom Zanussi
Signed-off-by: Frederic Weisbecker -
Stop printing an error message when we don't have the letter
for a given task state. All we need to know is if the task is
in the TASK_RUNNING state.Signed-off-by: Frederic Weisbecker
Cc: Ingo Molnar
Cc: Peter Zijlstra
Cc: Arnaldo Carvalho de Melo
Cc: Paul Mackerras
Cc: Nikhil Rao
Cc: Tom Zanussi -
Migrate out events may happen on tasks that are not in the
runqueue, for example this is the case for tasks that are
sleeping. In this case, we don't want to log the migrate out
event in the source runqueue because the task is not eventually
in the runqueue and we have already logged its sleep event.This fixes timeslices that spuriously propagate a sleep event
from the previous timeslice.Signed-off-by: Frederic Weisbecker
Cc: Ingo Molnar
Cc: Peter Zijlstra
Cc: Arnaldo Carvalho de Melo
Cc: Paul Mackerras
Cc: Nikhil Rao
Cc: Tom Zanussi -
This brings a GUI tool that displays an overview of the load
of tasks proportion in each CPUs.The CPUs forward progress is cut in timeslices. A new timeslice
is created for every runqueue event: a task gets pushed out or
pulled in the runqueue.For each timeslice, every CPUs rectangle is colored with a red
power that describes the local load against the total load.
This more red is the rectangle, the higher is the given CPU load.
This load is the number of tasks running on the CPU, without
any distinction against the scheduler policy of the tasks, for
now.Also for each timeslice, the event origin is depicted on the
CPUs that triggered it using a thin colored line on top of the
rectangle timeslice.These events are:
* sleep: a task went to sleep and has then been pulled out the
runqueue. The origin color in the thin line is dark blue.* wake up: a task woke up and has then been pushed in the
runqueue. The origin color is yellow.* wake up new: a new task woke up and has then been pushed in the
runqueue. The origin color is green.* migrate in: a task migrated in the runqueue due to a load
balancing operation. The origin color is violet.* migrate out: reverse of the previous one. Migrate in events
usually have paired migrate out events in another runqueue.
The origin color is light blue.Clicking on a timeslice provides the runqueue event details
and the runqueue state.The CPU rectangles can be navigated using the usual arrow
controls. Horizontal zooming in/out is possible with the
"+" and "-" buttons.Signed-off-by: Frederic Weisbecker
Cc: Peter Zijlstra
Cc: Arnaldo Carvalho de Melo
Cc: Li Zefan
Cc: Steven Rostedt
Cc: Tom Zanussi
Cc: Mike Galbraith
Cc: Venkatesh Pallipadi
Cc: Pierre Tardy
Cc: Nikhil Rao
Cc: Li Zefan
31 Jul, 2010
3 commits
-
…'spear' and 'versatile' into devel
-
So that we reduce the noise when looking for leaks using tools such as
valgrind.Cc: Frederic Weisbecker
Cc: Mike Galbraith
Cc: Peter Zijlstra
Cc: Stephane Eranian
LKML-Reference:
Signed-off-by: Arnaldo Carvalho de Melo -
For long running sessions with many threads with short lifetimes the
amount of memory that the buildid process takes is too much.Since we don't have hist_entries that may be pointing to them, we can
just release the resources associated with each thread when the exit
(PERF_RECORD_EXIT) event is received.For normal processing we need to annotate maps with hits, and thus
hist_entries pointing to it and drop the ones that had none. Will be
done in a followup patch.Cc: David S. Miller
Cc: Frederic Weisbecker
Cc: Ingo Molnar
Cc: Mike Galbraith
Cc: Paul Mackerras
Cc: Peter Zijlstra
Cc: Stephane Eranian
Cc: Tom Zanussi
LKML-Reference:
Signed-off-by: Arnaldo Carvalho de Melo
30 Jul, 2010
7 commits
-
As a precursor for perf to support uprobes, rename fields/functions
that had kprobe in their name but can be shared across perf-kprobes
and perf-uprobes to probe.Cc: Ananth N Mavinakayanahalli
Cc: Andrew Morton
Cc: Christoph Hellwig
Cc: "Frank Ch. Eigler"
Cc: Frederic Weisbecker
Cc: Ingo Molnar
Cc: Jim Keniston
Cc: Linus Torvalds
Cc: Mark Wielaard
Cc: Mathieu Desnoyers
Cc: Naren A Devaiah
Cc: Oleg Nesterov
Cc: "Paul E. McKenney"
Cc: Peter Zijlstra
Cc: Randy Dunlap
Cc: Steven Rostedt
LKML-Reference:
Signed-off-by: Srikar Dronamraju
Signed-off-by: Arnaldo Carvalho de Melo -
Cc: Frederic Weisbecker
Cc: Mike Galbraith
Cc: Peter Zijlstra
Cc: Stephane Eranian
LKML-Reference:
Signed-off-by: Arnaldo Carvalho de Melo -
Changes:
* Simplification of the main search loop on dso__load()
* Replace the search with a 2-pass search:
* First, try to find an image with a proper symtab.
* Second, repeat the search, accepting dynsym.A second scan should only ever happen when needed debug images are
missing from the buildid cache or stale, i.e., when the cache is out of
sync.Currently, the second scan also happens when using separated debug
images, since the caching logic doesn't currently know how to cache
those. Improvements to the cache behaviour ought to solve that.Signed-off-by: Dave Martin
LKML-Reference:
Signed-off-by: Arnaldo Carvalho de Melo -
Signed-off-by: Dave Martin
LKML-Reference:
Signed-off-by: Arnaldo Carvalho de Melo -
If we have a buildid, then we never want to load an image which has no buildid,
or which has a different buildid, so it makes sense for the check to be built
into dso__load and not done separately. This is fine for old distros which
don't use buildid at all since we do no check in that case.This refactoring also alleviates some subtle race condition issues by not
opening ELF images twice to check the buildid and then load the symbols, which
could lead to weirdness if an image is replaced under our feet.Signed-off-by: Dave Martin
LKML-Reference:
Signed-off-by: Arnaldo Carvalho de Melo -
Cc: Frederic Weisbecker
Cc: Mike Galbraith
Cc: Peter Zijlstra
Cc: Stephane Eranian
LKML-Reference:
Signed-off-by: Arnaldo Carvalho de Melo -
So that we can reduce the noise on valgrind when looking for memory
leaks.Cc: Frederic Weisbecker
Cc: Mike Galbraith
Cc: Peter Zijlstra
Cc: Stephane Eranian
LKML-Reference:
Signed-off-by: Arnaldo Carvalho de Melo
28 Jul, 2010
1 commit
-
We remove files _from_ the cache.
Cc: Frederic Weisbecker
Cc: Mike Galbraith
Cc: Peter Zijlstra
Cc: Stephane Eranian
LKML-Reference:
Signed-off-by: Arnaldo Carvalho de Melo
27 Jul, 2010
8 commits
-
Tidy-up patch to remove some code and struct perf_session data members
which are no longer needed due to the previous patch: "perf tools: Don't
abbreviate file paths relative to the cwd".LKML-Reference:
Signed-off-by: Dave Martin
Signed-off-by: Arnaldo Carvalho de Melo -
This avoids around some problems where the full path is executables and DSOs it
needed for finding debug symbols on platforms with separated debug symbol files
such as Ubuntu. This is simpler than tracking an extra name for each image.The only impact should be that paths in verbose output from the perf tools
become absolute, instead of relative to .LKML-Reference:
Signed-off-by: Dave Martin
Signed-off-by: Arnaldo Carvalho de Melo -
The stock newt checkbox tree widget we were using was not really
suitable for hist entry + callchain browsing.The problems with it were manifold:
- We needed to traverse the whole hist_entry rb_tree to add each entry +
callchains beforehand.- No control over the colors used for each row
So a new tree widget, based mostly on slang, was written.
It extends the ui_browser class already used for annotate to allow the
user to fold/unfold branches in the callchains tree, using extra fields
in the symbol_map class that is embedded in hist_entry and
callchain_node instances to store the folding state and when changing
this state calculates the number of rows that are produced when showing
a particular hist_entry instance.This greatly speeds up browsing as we don't have to upfront touch all
the entries and only calculate callchain related operations when some
callchain branch is actually unfolded.The memory footprint is also reduced as the data structure is not
duplicated, just some extra fields for controling callchain state and to
simplify the process of seeking thru entries (nr_rows, row_offset) were
added.Cc: Frederic Weisbecker
Cc: Mike Galbraith
Cc: Peter Zijlstra
Cc: Stephane Eranian
LKML-Reference:
Signed-off-by: Arnaldo Carvalho de Melo -
So that we gain two columns and look more like classical (at least in
TUIs) scroll bars bars.Cc: Frederic Weisbecker
Cc: Mike Galbraith
Cc: Peter Zijlstra
Cc: Stephane Eranian
LKML-Reference:
Signed-off-by: Arnaldo Carvalho de Melo -
When we call ui_browser__show we may have called
ui_browser__refresh_dimensions to check if the maximum lenght for the
contained entries changed, such as when zooming in and out DSOs or
threads in the hist browser.For that to happen we must delete the old form, that will take care of
deleting the vertical scrollbar, etc, and then recreate them, with the
new dimensions.Cc: Frederic Weisbecker
Cc: Mike Galbraith
Cc: Peter Zijlstra
Cc: Stephane Eranian
LKML-Reference:
Signed-off-by: Arnaldo Carvalho de Melo -
Will be used to figure out the window width needed in the new tree
widget.Cc: Frederic Weisbecker
Cc: Mike Galbraith
Cc: Peter Zijlstra
Cc: Stephane Eranian
LKML-Reference:
Signed-off-by: Arnaldo Carvalho de Melo -
Cc: Frederic Weisbecker
Cc: Mike Galbraith
Cc: Peter Zijlstra
Cc: Stephane Eranian
LKML-Reference:
Signed-off-by: Arnaldo Carvalho de Melo -
Since version 0.3 from Kristian's repository, there should actually be
no change in functionality except for the x86-64 fix. Nevertheless,
make it distinct from the original nosy-dump --- just in case and also
because of potential future changes.Signed-off-by: Stefan Richter