Impact: new feature
Problem on distro kernels: irq_desc[NR_IRQS] takes megabytes of RAM with
NR_CPUS set to large values. The goal is to be able to scale up to much
larger NR_IRQS value without impacting the (important) common case.
To solve this, we generalize irq_desc[NR_IRQS] to an (optional) array of
irq_desc pointers.
When CONFIG_SPARSE_IRQ=y is used, we use kzalloc_node to get irq_desc,
this also makes the IRQ descriptors NUMA-local (to the site that calls
request_irq()).
This gets rid of the irq_cfg[] static array on x86 as well: irq_cfg now
uses desc->chip_data for x86 to store irq_cfg.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: optimize the sched domains tree some more
The addition of SD_SERIALIZE flag added to SD_NODE_INIT prevented top level
dummy numa sched_domain to be properly degenerated on non-numa smp machine.
The reason is that in sd_parent_degenerate(), it found that the child and
parent does not have comon sched_domain flags due to SD_SERIALIZE. However,
for non-numa smp box, the top level is a dummy with a single sched_group.
Filter out SD_SERIALIZE if it is on non-numa machine to properly degenerate
top level node sched_domain. this will cut back some of the sd domain walk
in the load balancer code.
Signed-off-by: Ken Chen <kenchen@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: provide trace headers to explain a bit the output
This patch implements the print_headers callback for the function graph
tracer. These headers are output according to the current trace options.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
While ideally CLONE_NEWUSER will eventually require no
privilege, the required permission checks are currently
not there. As a result, CLONE_NEWUSER has the same effect
as a setuid(0)+setgroups(1,"0"). While we already require
CAP_SYS_ADMIN, requiring CAP_SETUID and CAP_SETGID seems
appropriate.
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: James Morris <jmorris@namei.org>
(These two patches are in the next-unacked branch of
git://git.kernel.org/pub/scm/linux/kernel/git/sergeh/userns-2.6.
If they get some ACKs, then I hope to feed this into security-next.
After these two, I think we're ready to tackle userns+capabilities)
Fairsched creates a per-uid directory under /sys/kernel/uids/.
So when you clone(CLONE_NEWUSER), it tries to create
/sys/kernel/uids/0, which already exists, and you get back
-ENOMEM.
This was supposed to be fixed by sysfs tagging, but that
was postponed (ok, rejected until sysfs locking is fixed).
So, just as with network namespaces, we just don't create
those directories for user namespaces other than the init.
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Signed-off-by: James Morris <jmorris@namei.org>
Impact: clean up
Using (struct pid *)-1 as the pointer for ftrace_swapper_pid is
a little confusing for others. This patch uses the address of the
actual init pid structure instead. This change is only for
clarity. It does not affect the code itself. Hopefully soon the
swapper tasks will all have their own pid structure and then
we can clean up the code a bit more.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: cleanup
As suggested by Steven Rostedt, this patch provide a new macro
task_curr_ret_stack() to move the cpp conditionnal CONFIG into
the linux/ftrace.h headers.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: fix default empty traces on function-graph-tracer
The actual ftrace_trace_task() checks if ftrace_pid_trace is allocated
and return 1 if it is true.
If it is NULL, it will check the bit of pid tracing flag for the current
task (which are not set by default).
So by default, a task is not traced.
Actually all tasks should be traced by default and filter_by_pid when
ftrace_pid_trace is allocated.
The appropriate condition should be to return 1 if filter_by_pid is
set.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Acke-dby: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: fix tracer selfstests false results
After setting a ftrace_printk somewhere in th kernel, I saw the
Function tracer selftest failing.
When a selftest occurs, the ring buffer is lurked to see if
some entries were inserted. But concurrent insertion such as
ftrace_printk could occured at the same time and could give
false positive or negative results.
This patch prevent prevent from TRACE_PRINT entries insertion
during selftests.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/bdev:
[PATCH] fix bogus argument of blkdev_put() in pktcdvd
[PATCH 2/2] documnt FMODE_ constants
[PATCH 1/2] kill FMODE_NDELAY_NOW
[PATCH] clean up blkdev_get a little bit
[PATCH] Fix block dev compat ioctl handling
[PATCH] kill obsolete temporary comment in swsusp_close()
* 'timers-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
time: catch xtime_nsec underflows and fix them
posix-cpu-timers: fix clock_gettime with CLOCK_PROCESS_CPUTIME_ID
* 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
check_hung_task(): unsigned sysctl_hung_task_warnings cannot be less than 0
documentation: local_ops fix on_each_cpu
Add a sysctl to tweak the RSS limit used to decide when to grow
the TSB for an address space.
In order to avoid expensive divides and multiplies only simply
positive and negative powers of two are supported.
The function computed takes the number of TSB translations that will
fit at one time in the TSB of a given size, and either adds or
subtracts a percentage of entries. This final value is the
RSS limit.
See tsb_size_to_rss_limit().
Signed-off-by: David S. Miller <davem@davemloft.net>
Impact: fix hrtimer locking (reported by lockdep) in the CPU hotplug case
This addition fixes the hotplug locking issue on my machine
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
it had been put there to mark the call of blkdev_put() that
needed proper argument propagated to it; later patch in the
same series had done just that.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Handle the TRACE_PRINT entries from the function grapg tracer
and output them as a C comment just below the function that called
it, as if it was a comment inside this function.
Example with an ftrace_printk inside might_sleep() function:
void __might_sleep(char *file, int line)
{
static unsigned long prev_jiffy; /* ratelimiting */
ftrace_printk("Hi I'm a comment in might_sleep() :-)");
A chunk of a resulting trace:
0) | _reiserfs_free_block() {
0) | reiserfs_read_bitmap_block() {
0) | __bread() {
0) | __getblk() {
0) | __find_get_block() {
0) 0.698 us | mark_page_accessed();
0) 2.267 us | }
0) | __might_sleep() {
0) | /* Hi I'm a comment in might_sleep() :-) */
0) 1.321 us | }
0) 5.872 us | }
0) 7.313 us | }
0) 8.718 us | }
And this patch brings two minor fixes:
- The newline after a switch-out task has disappeared
- The "|" sign just before the cpu number on task-switch has been deleted.
0) 0.616 us | pick_next_task_rt();
0) 1.457 us | _spin_trylock();
0) 0.653 us | _spin_unlock();
0) 0.728 us | _spin_trylock();
0) 0.631 us | _spin_unlock();
0) 0.729 us | native_load_sp0();
0) 0.593 us | native_load_tls();
------------------------------------------
0) cat-2834 => migrati-3
------------------------------------------
0) | finish_task_switch() {
0) 0.841 us | _spin_unlock_irq();
0) 0.616 us | post_schedule_rt();
0) 3.882 us | }
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: introduce new lockdep API
Allow to change a held lock's class. Basically the same as the existing
code to change a subclass therefore reuse all that.
The XFS code will be able to use this to annotate their inode locking.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: fix a bug in function filter setting
when writing function to set_graph_function, we should check whether it
has existed in set_graph_function to avoid duplicating.
Signed-off-by: Liming Wang <liming.wang@windriver.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: new feature
This patch lets the swapper tasks of all CPUS be filtered by the
set_ftrace_pid file.
If '0' is echoed into this file, then all the idle tasks (aka swapper)
is flagged to be traced. This affects all CPU idle tasks.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: clean up, extend PID filtering to PID namespaces
Eric Biederman suggested using the struct pid for filtering on
pids in the kernel. This patch is based off of a demonstration
of an implementation that Eric sent me in an email.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: New feature
This patch makes the changes to set_ftrace_pid apply to the function
graph tracer.
# echo $$ > /debugfs/tracing/set_ftrace_pid
# echo function_graph > /debugfs/tracing/current_tracer
Will cause only the current task to be traced. Note, the trace flags are
also inherited by child processes, so the children of the shell
will also be traced.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: clean up
Use the new task struct trace flags to determine if a process should be
traced or not.
Note: this moves the searching of the pid to the slow path of setting
the pid field. This needs to be converted to the pid name space.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This patch adds the file:
/debugfs/tracing/set_graph_function
which can be used along with the function graph tracer.
When this file is empty, the function graph tracer will act as
usual. When the file has a function in it, the function graph
tracer will only trace that function.
For example:
# echo blk_unplug > /debugfs/tracing/set_graph_function
# cat /debugfs/tracing/trace
[...]
------------------------------------------
| 2) make-19003 => kjournald-2219
------------------------------------------
2) | blk_unplug() {
2) | dm_unplug_all() {
2) | dm_get_table() {
2) 1.381 us | _read_lock();
2) 0.911 us | dm_table_get();
2) 1. 76 us | _read_unlock();
2) + 12.912 us | }
2) | dm_table_unplug_all() {
2) | blk_unplug() {
2) 0.778 us | generic_unplug_device();
2) 2.409 us | }
2) 5.992 us | }
2) 0.813 us | dm_table_put();
2) + 29. 90 us | }
2) + 34.532 us | }
You can add up to 32 functions into this file. Currently we limit it
to 32, but this may change with later improvements.
To add another function, use the append '>>':
# echo sys_read >> /debugfs/tracing/set_graph_function
# cat /debugfs/tracing/set_graph_function
blk_unplug
sys_read
Using the '>' will clear out the function and write anew:
# echo sys_write > /debug/tracing/set_graph_function
# cat /debug/tracing/set_graph_function
sys_write
Note, if you have function graph running while doing this, the small
time between clearing it and updating it will cause the graph to
record all functions. This should not be an issue because after
it sets the filter, only those functions will be recorded from then on.
If you need to only record a particular function then set this
file first before starting the function graph tracer. In the future
this side effect may be corrected.
The set_graph_function file is similar to the set_ftrace_filter but
it does not take wild cards nor does it allow for more than one
function to be set with a single write. There is no technical reason why
this is the case, I just do not have the time yet to implement that.
Note, dynamic ftrace must be enabled for this to appear because it
uses the dynamic ftrace records to match the name to the mcount
call sites.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: fix time warp bug
Alex Shi, along with Yanmin Zhang have been noticing occasional time
inconsistencies recently. Through their great diagnosis, they found that
the xtime_nsec value used in update_wall_time was occasionally going
negative. After looking through the code for awhile, I realized we have
the possibility for an underflow when three conditions are met in
update_wall_time():
1) We have accumulated a second's worth of nanoseconds, so we
incremented xtime.tv_sec and appropriately decrement xtime_nsec.
(This doesn't cause xtime_nsec to go negative, but it can cause it
to be small).
2) The remaining offset value is large, but just slightly less then
cycle_interval.
3) clocksource_adjust() is speeding up the clock, causing a
corrective amount (compensating for the increase in the multiplier
being multiplied against the unaccumulated offset value) to be
subtracted from xtime_nsec.
This can cause xtime_nsec to underflow.
Unfortunately, since we notify the NTP subsystem via second_overflow()
whenever we accumulate a full second, and this effects the error
accumulation that has already occured, we cannot simply revert the
accumulated second from xtime nor move the second accumulation to after
the clocksource_adjust call without a change in behavior.
This leaves us with (at least) two options:
1) Simply return from clocksource_adjust() without making a change if we
notice the adjustment would cause xtime_nsec to go negative.
This would work, but I'm concerned that if a large adjustment was needed
(due to the error being large), it may be possible to get stuck with an
ever increasing error that becomes too large to correct (since it may
always force xtime_nsec negative). This may just be paranoia on my part.
2) Catch xtime_nsec if it is negative, then add back the amount its
negative to both xtime_nsec and the error.
This second method is consistent with how we've handled earlier rounding
issues, and also has the benefit that the error being added is always in
the oposite direction also always equal or smaller then the correction
being applied. So the risk of a corner case where things get out of
control is lessened.
This patch fixes bug 11970, as tested by Yanmin Zhang
http://bugzilla.kernel.org/show_bug.cgi?id=11970
Reported-by: alex.shi@intel.com
Signed-off-by: John Stultz <johnstul@us.ibm.com>
Acked-by: "Zhang, Yanmin" <yanmin_zhang@linux.intel.com>
Tested-by: "Zhang, Yanmin" <yanmin_zhang@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Conflicts:
fs/nfsd/nfs4recover.c
Manually fixed above to use new creds API functions, e.g.
nfs4_save_creds().
Signed-off-by: James Morris <jmorris@namei.org>
Impact: graph tracer race/crash fix
There is a nasy race in startup of a new process running the
function graph tracer. In fork.c:
total_forks++;
spin_unlock(¤t->sighand->siglock);
write_unlock_irq(&tasklist_lock);
ftrace_graph_init_task(p);
proc_fork_connector(p);
cgroup_post_fork(p);
return p;
The new task is free to run as soon as the tasklist_lock is released.
This is before the ftrace_graph_init_task. If the task does run
it will be using the same ret_stack and curr_ret_stack as the parent.
This will cause crashes that are difficult to debug.
This patch moves the ftrace_graph_init_task to just after the alloc_pid
code. This fixes the above race.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: fix to output of stack trace
If a function is not found in the stack of the stack tracer, the
number printed is quite strange. This fixes the algorithm to handle
missing functions better.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
CONFIG_FUNCTION_GRAPH_TRACER depends on FUNCTION_TRACER already,
(turning it non-default) so it so making it default-n is pointless.
So enable it by default - it's a nice extension of the function tracer.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: better trace output of duration for long calls
The old duration output didn't exceeded 9999.999 us to fit the column
and the nanosecs were always 3 numbers. As Ingo suggested, it's better
to have the whole microseconds elapsed time and shift the nanosecs precision
if needed to fit the maximum 7 numbers. And usec need more number, the case
should be rare and important enough to break a bit the column alignment to
show it.
So, depending of the duration value, we now have these patterns:
u.nnn us
uu.nnn us
uuu.nnn us
uuuu.nnn us
uuuuu.nn us
uuuuuu.n us
uuuuuuuu..... us
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: extend function-graph output: let one know which thread called a function
This patch implements a helper function to print the couple cmdline/pid.
Its output is provided during task switching and on each row if the new
"funcgraph-proc" defualt-off option is set through trace_options file.
The output is center aligned and never exceeds 14 characters. The cmdline
is truncated over 7 chars.
But note that if the pid exceeds 6 characters, the column will overflow (but
the situation is abnormal).
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: feature, let entry function decide to trace or not
This patch lets the graph tracer entry function decide if the tracing
should be done at the end as well. This requires all function graph
entry functions return 1 if it should trace, or 0 if the return should
not be traced.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: clean up
Andrew Morton pointed out that the kernel convention of a variable
named page should be of type page struct. The ring buffer uses
a variable named "page" for a pointer to something else.
This patch converts those to be called "bpage" (as in "buffer page").
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: new ftrace_graph_stop function
While developing more features of function graph, I hit a bug that
caused the WARN_ON to trigger in the prepare_ftrace_return function.
Well, it was hard for me to find out that was happening because the
bug would not print, it would just cause a hard lockup or reboot.
The reason is that it is not safe to call printk from this function.
Looking further, I also found that it calls unregister_ftrace_graph,
which grabs a mutex and calls kstop machine. This would definitely
lock the box up if it were to trigger.
This patch adds a fast and safe ftrace_graph_stop() which will
stop the function tracer. Then it is safe to call the WARN ON.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: new API to ring buffer
This patch adds a new interface into the ring buffer that allows a
page to be read from the ring buffer on a given CPU. For every page
read, one must also be given to allow for a "swap" of the pages.
rpage = ring_buffer_alloc_read_page(buffer);
if (!rpage)
goto err;
ret = ring_buffer_read_page(buffer, &rpage, cpu, full);
if (!ret)
goto empty;
process_page(rpage);
ring_buffer_free_read_page(rpage);
The caller of these functions must handle any waits that are
needed to wait for new data. The ring_buffer_read_page will simply
return 0 if there is no data, or if "full" is set and the writer
is still on the current page.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: get ready for splice changes
This patch moves the commit and timestamp into the beginning of each
data page of the buffer. This change will allow the page to be moved
to another location (disk, network, etc) and still have information
in the page to be able to read it.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: fix for lockdep and ftrace
The raw_local_irq_save/restore confuses lockdep. This patch
converts them to the local_irq_save/restore variants.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Merge x86/dumpstack into tracing/ftrace because upcoming ftrace changes
depend on cleanups already in x86/dumpstack.
Also merge to latest upstream -rc.
Impact: emit new warning
We periodically waste time tracking down problems from the genirq
framework not respecting IRQF_DISABLED for some shared IRQ cases. Linus
views this as "will not fix", but we're still left with the bugs caused by
this misbehavior.
This patch adds a nag message in request_irq(), so that drivers can fix
their IRQ handlers to avoid this problem.
Note that developers will never see the relevant bugs when they run with
LOCKDEP, so it's no wonder these bugs are hard to find. (That also means
LOCKDEP is overlooking some IRQ-related bugs involving IRQ handlers that
don't set IRQF_DISABLED...)
Signed-off-by: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: fix __irq_set_trigger() for IRQ_LEVEL
When recording the irq trigger type, let's also make sure
that IRQ_LEVEL gets set correctly.
Signed-off-by: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
