Impact: cleanup

Move blktrace.c to kernel/trace, also move its config entry.
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Acked-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: NJens Axboe <jens.axboe@oracle.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

list.h provides a dedicated primitive for
"list_del followed by list_add_tail"... list_move_tail.
Signed-off-by: NArjan van de Ven <arjan@linux.intel.com>
Signed-off-by: NStefan Richter <stefanr@s5r6.in-berlin.de>

Rename the async_*_special() functions to async_*_domain(), which
describes the purpose of these functions much better.
[Broke up long lines to silence checkpatch]
Signed-off-by: NCornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: NArjan van de Ven <arjan@linux.intel.com>

Add some kerneldoc to the async interface.
Signed-off-by: NCornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: NArjan van de Ven <arjan@linux.intel.com>

If we fail to create the manager thread, fall back to non-fastboot.
If we fail to create an async thread, try again after waiting for
a bit.
Signed-off-by: NCornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: NArjan van de Ven <arjan@linux.intel.com>

async_schedule() should pass in async_running as the running
list, and run_one_entry() should put the entry to be run on
the provided running list instead of always on the generic one.
Reported-by: NJonathan Corbet <corbet@lwn.net>
Signed-off-by: NCornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: NArjan van de Ven <arjan@linux.intel.com>

Impact: clean up

Fixed several typos in the comments.
Signed-off-by: NWenji Huang <wenji.huang@oracle.com>
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>

Impact: clean up

Now that a generic in_nmi is available, this patch removes the
special code in the ring_buffer and implements the in_nmi generic
version instead.

With this change, I was also able to rename the "arch_ftrace_nmi_enter"
back to "ftrace_nmi_enter" and remove the code from the ring buffer.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>

Impact: prevent deadlock in NMI

The ring buffers are not yet totally lockless with writing to
the buffer. When a writer crosses a page, it grabs a per cpu spinlock
to protect against a reader. The spinlocks taken by a writer are not
to protect against other writers, since a writer can only write to
its own per cpu buffer. The spinlocks protect against readers that
can touch any cpu buffer. The writers are made to be reentrant
with the spinlocks disabling interrupts.

The problem arises when an NMI writes to the buffer, and that write
crosses a page boundary. If it grabs a spinlock, it can be racing
with another writer (since disabling interrupts does not protect
against NMIs) or with a reader on the same CPU. Luckily, most of the
users are not reentrant and protects against this issue. But if a
user of the ring buffer becomes reentrant (which is what the ring
buffers do allow), if the NMI also writes to the ring buffer then
we risk the chance of a deadlock.

This patch moves the ftrace_nmi_enter called by nmi_enter() to the
ring buffer code. It replaces the current ftrace_nmi_enter that is
used by arch specific code to arch_ftrace_nmi_enter and updates
the Kconfig to handle it.

When an NMI is called, it will set a per cpu variable in the ring buffer
code and will clear it when the NMI exits. If a write to the ring buffer
crosses page boundaries inside an NMI, a trylock is used on the spin
lock instead. If the spinlock fails to be acquired, then the entry
is discarded.

This bug appeared in the ftrace work in the RT tree, where event tracing
is reentrant. This workaround solved the deadlocks that appeared there.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>

Impact: fix to prevent developers from using entry->cpu

With the new ring buffer infrastructure, the cpu for the entry is
implicit with which CPU buffer it is on.

The original code use to record the current cpu into the generic
entry header, which can be retrieved by entry->cpu. When the
ring buffer was introduced, the users were convert to use the
the cpu number of which cpu ring buffer was in use (this was passed
to the tracers by the iterator: iter->cpu).

Unfortunately, the cpu item in the entry structure was never removed.
This allowed for developers to use it instead of the proper iter->cpu,
unknowingly, using an uninitialized variable. This was not the fault
of the developers, since it would seem like the logical place to
retrieve the cpu identifier.

This patch removes the cpu item from the entry structure and fixes
all the users that should have been using iter->cpu.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>

I happened to forked lots of processes, and hit NULL pointer dereference.
It is because in copy_process() after checking max_threads, 0 is returned
but not -EAGAIN.

The bug is introduced by "CRED: Detach the credentials from task_struct"
(commit f1752eec).
Signed-off-by: NLi Zefan <lizf@cn.fujitsu.com>
Signed-off-by: NDavid Howells <dhowells@redhat.com>
Acked-by: NJames Morris <jmorris@namei.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Impact: cleanup

To make it easy for ftrace plugin writers, as this was open coded in
the existing plugins
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: NFrédéric Weisbecker <fweisbec@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: new API

These new functions do what previously was being open coded, reducing
the number of details ftrace plugin writers have to worry about.

It also standardizes the handling of stacktrace, userstacktrace and
other trace options we may introduce in the future.

With this patch, for instance, the blk tracer (and some others already
in the tree) can use the "userstacktrace" /d/tracing/trace_options
facility.

$ codiff /tmp/vmlinux.before /tmp/vmlinux.after
linux-2.6-tip/kernel/trace/trace.c:
  trace_vprintk              |   -5
  trace_graph_return         |  -22
  trace_graph_entry          |  -26
  trace_function             |  -45
  __ftrace_trace_stack       |  -27
  ftrace_trace_userstack     |  -29
  tracing_sched_switch_trace |  -66
  tracing_stop               |   +1
  trace_seq_to_user          |   -1
  ftrace_trace_special       |  -63
  ftrace_special             |   +1
  tracing_sched_wakeup_trace |  -70
  tracing_reset_online_cpus  |   -1
 13 functions changed, 2 bytes added, 355 bytes removed, diff: -353

linux-2.6-tip/block/blktrace.c:
  __blk_add_trace |  -58
 1 function changed, 58 bytes removed, diff: -58

linux-2.6-tip/kernel/trace/trace.c:
  trace_buffer_lock_reserve  |  +88
  trace_buffer_unlock_commit |  +86
 2 functions changed, 174 bytes added, diff: +174

/tmp/vmlinux.after:
 16 functions changed, 176 bytes added, 413 bytes removed, diff: -237
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: NFrédéric Weisbecker <fweisbec@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: API change, cleanup

>From ring_buffer_{lock_reserve,unlock_commit}.

$ codiff /tmp/vmlinux.before /tmp/vmlinux.after
linux-2.6-tip/kernel/trace/trace.c:
  trace_vprintk              |  -14
  trace_graph_return         |  -14
  trace_graph_entry          |  -10
  trace_function             |   -8
  __ftrace_trace_stack       |   -8
  ftrace_trace_userstack     |   -8
  tracing_sched_switch_trace |   -8
  ftrace_trace_special       |  -12
  tracing_sched_wakeup_trace |   -8
 9 functions changed, 90 bytes removed, diff: -90

linux-2.6-tip/block/blktrace.c:
  __blk_add_trace |   -1
 1 function changed, 1 bytes removed, diff: -1

/tmp/vmlinux.after:
 10 functions changed, 91 bytes removed, diff: -91
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: NFrédéric Weisbecker <fweisbec@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

With exclusive waiters, every process woken up through the wait queue must
ensure that the next waiter down the line is woken when it has finished.

Interruptible waiters don't do that when aborting due to a signal.  And if
an aborting waiter is concurrently woken up through the waitqueue, noone
will ever wake up the next waiter.

This has been observed with __wait_on_bit_lock() used by
lock_page_killable(): the first contender on the queue was aborting when
the actual lock holder woke it up concurrently.  The aborted contender
didn't acquire the lock and therefor never did an unlock followed by
waking up the next waiter.

Add abort_exclusive_wait() which removes the process' wait descriptor from
the waitqueue, iff still queued, or wakes up the next waiter otherwise.
It does so under the waitqueue lock.  Racing with a wake up means the
aborting process is either already woken (removed from the queue) and will
wake up the next waiter, or it will remove itself from the queue and the
concurrent wake up will apply to the next waiter after it.

Use abort_exclusive_wait() in __wait_event_interruptible_exclusive() and
__wait_on_bit_lock() when they were interrupted by other means than a wake
up through the queue.

[akpm@linux-foundation.org: coding-style fixes]
Reported-by: NChris Mason <chris.mason@oracle.com>
Signed-off-by: NJohannes Weiner <hannes@cmpxchg.org>
Mentored-by: NOleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Matthew Wilcox <matthew@wil.cx>
Cc: Chuck Lever <cel@citi.umich.edu>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: <stable@kernel.org>		["after some testing"]
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Revert commit 0c2d64fb because it causes
(arguably poorly designed) existing userspace to spend interminable
periods closing billions of not-open file descriptors.

We could bring this back, with some sort of opt-in tunable in /proc, which
defaults to "off".

Peter's alanysis follows:

: I spent several hours trying to get to the bottom of a serious
: performance issue that appeared on one of our servers after upgrading to
: 2.6.28.  In the end it's what could be considered a userspace bug that
: was triggered by a change in 2.6.28.  Since this might also affect other
: people I figured I'd at least document what I found here, and maybe we
: can even do something about it:
:
:
: So, I upgraded some of debian.org's machines to 2.6.28.1 and immediately
: the team maintaining our ftp archive complained that one of their
: scripts that previously ran in a few minutes still hadn't even come
: close to being done after an hour or so.  Downgrading to 2.6.27 fixed
: that.
:
: Turns out that script is forking a lot and something in it or python or
: whereever closes all the file descriptors it doesn't want to pass on.
: That is, it starts at zero and goes up to ulimit -n/RLIMIT_NOFILE and
: closes them all with a few exceptions.
:
: Turns out that takes a long time when your limit -n is now 2^20 (1048576).
:
: With 2.6.27.* the ulimit -n was the standard 1024, but with 2.6.28 it is
: now a thousand times that.
:
: 2.6.28 included a patch titled "rlimit: permit setting RLIMIT_NOFILE to
: RLIM_INFINITY" (0c2d64fb)[1] that
: allows, as the title implies, to set the limit for number of files to
: infinity.
:
: Closer investigation showed that the broken default ulimit did not apply
: to "system" processes (like stuff started from init).  In the end I
: could establish that all processes that passed through pam_limit at one
: point had the bad resource limit.
:
: Apparently the pam library in Debian etch (4.0) initializes the limits
: to some default values when it doesn't have any settings in limit.conf
: to override them.  Turns out that for nofiles this is RLIM_INFINITY.
: Commenting out "case RLIMIT_NOFILE" in pam_limit.c:267 of our pam
: package version 0.79-5 fixes that - tho I'm not sure what side effects
: that has.
:
: Debian lenny (the upcoming 5.0 version) doesn't have this issue as it
: uses a different pam (version).
Reported-by: NPeter Palfrader <weasel@debian.org>
Cc: Adam Tkac <vonsch@gmail.com>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: <stable@kernel.org>		[2.6.28.x]
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

alpha:

kernel/async.c: In function 'run_one_entry':
kernel/async.c:141: warning: format '%lli' expects type 'long long int', but argument 2 has type 'async_cookie_t'
kernel/async.c:149: warning: format '%lli' expects type 'long long int', but argument 2 has type 'async_cookie_t'
kernel/async.c:149: warning: format '%lld' expects type 'long long int', but argument 4 has type 's64'
kernel/async.c: In function 'async_synchronize_cookie_special':
kernel/async.c:250: warning: format '%lli' expects type 'long long int', but argument 3 has type 's64'

Cc: Arjan van de Ven <arjan@infradead.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Ingo Molnar suggested using goto logic to keep the indentation
down and to be able to remove the nasty line breaks. This actually
makes the code a bit more readable.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: simplification of tracers

As all tracers are doing this we might as well do it in
register_ftrace_event and save one branch each time we call these
callbacks.
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: NFrederic Weisbecker <fweisbec@gmail.com>
Acked-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

As they actually all return these enumerators.
Reported-by: NFrederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: NFrederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: bugfix and cleanup

Some callsites were returning either TRACE_ITER_PARTIAL_LINE if the
trace_seq routines (trace_seq_printf, etc) returned 0 meaning its buffer
was full, or zero otherwise.

But...

/* Return values for print_line callback */
enum print_line_t {
        TRACE_TYPE_PARTIAL_LINE = 0,    /* Retry after flushing the seq */
        TRACE_TYPE_HANDLED      = 1,
        TRACE_TYPE_UNHANDLED    = 2     /* Relay to other output functions */
};

In other cases the return value was not being relayed at all.

Most of the time it didn't hurt because the page wasn't get filled, but
for correctness sake, handle the return values everywhere.
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: NFrederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

"ftrace: use struct pid" commit 978f3a45
converted ftrace_pid_trace to "struct pid*".

But we can't use do_each_pid_task() without rcu_read_lock() even if
we know the pid itself can't go away (it was pinned in ftrace_pid_write).
The exiting task can detach itself from this pid at any moment.
Signed-off-by: NOleg Nesterov <oleg@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: API change

The trace_seq and trace_entry are in trace_iterator, where there are
more fields that may be needed by tracers, so just pass the
tracer_iterator as is already the case for struct tracer->print_line.
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: make trace_event more convenient for tracers

All tracers (for the moment) that use the struct trace_event want to
have the context info printed before their own output: the pid/cmdline,
cpu, and timestamp.

But some other tracers that want to implement their trace_event
callbacks will not necessary need these information or they may want to
format them as they want.

This patch adds a new default-enabled trace option:
TRACE_ITER_CONTEXT_INFO When disabled through:

echo nocontext-info > /debugfs/tracing/trace_options

The pid, cpu and timestamps headers will not be printed.

IE with the sched_switch tracer with context-info (default):

     bash-2935 [001] 100.356561: 2935:120:S ==> [001]  0:140:R <idle>
   <idle>-0    [000] 100.412804:    0:140:R   + [000] 11:115:S events/0
   <idle>-0    [000] 100.412816:    0:140:R ==> [000] 11:115:R events/0
 events/0-11   [000] 100.412829:   11:115:S ==> [000]  0:140:R <idle>

Without context-info:

 2935:120:S ==> [001]  0:140:R <idle>
    0:140:R   + [000] 11:115:S events/0
    0:140:R ==> [000] 11:115:R events/0
   11:115:S ==> [000]  0:140:R <idle>

A tracer can disable it at runtime by clearing the bit
TRACE_ITER_CONTEXT_INFO in trace_flags.

The print routines were renamed to trace_print_context and
trace_print_lat_context, so that they can be used by tracers if they
want to use them for one of the trace_event callbacks.
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Now that we have a working ftrace=<tracer> function, make the boot
tracer get activated by it. This way we can turn it on or off without
recompiling the kernel, as well as keeping the selftests on. The
selftests are disabled whenever a default tracer starts running.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Peter Zijlstra started the functionality to start up a default
tracing at bootup. This patch finishes the work.

Now if you add 'ftrace=<tracer>' to the command line, when that tracer
is registered on bootup, that tracer is selected and starts tracing.

Note, all selftests for tracers that are registered after this tracer
is disabled. This prevents the selftests from disturbing the running
tracer, or the running tracer from disturbing the selftest.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Current refcounting for modules (done if CONFIG_MODULE_UNLOAD=y) is
using a lot of memory.

Each 'struct module' contains an [NR_CPUS] array of full cache lines.

This patch uses existing infrastructure (percpu_modalloc() &
percpu_modfree()) to allocate percpu space for the refcount storage.

Instead of wasting NR_CPUS*128 bytes (on i386), we now use
nr_cpu_ids*sizeof(local_t) bytes.

On a typical distro, where NR_CPUS=8, shiping 2000 modules, we reduce
size of module files by about 2 Mbytes. (1Kb per module)

Instead of having all refcounters in the same memory node - with TLB misses
because of vmalloc() - this new implementation permits to have better
NUMA properties, since each  CPU will use storage on its preferred node,
thanks to percpu storage.
Signed-off-by: NEric Dumazet <dada1@cosmosbay.com>
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Eric Paris reported:

> I have an hp dl785g5 which is unable to successfully run
> 2.6.29-0.66.rc3.fc11.x86_64 or 2.6.29-rc2-next-20090126.  During bootup
> (early in userspace daemons starting) I get the below BUG, which quickly
> renders the machine dead.  I assume it is because sparse_irq_lock never
> gets released when the BUG kills that task.

Adjust lock sequence when migrating a descriptor with
CONFIG_NUMA_MIGRATE_IRQ_DESC enabled.
Signed-off-by: NYinghai Lu <yinghai@kernel.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

cpumask_and() only initializes nr_cpu_ids bits, so the (deprecated)
first_cpu() might find one of those uninitialized bits if nr_cpu_ids
is less than NR_CPUS (as it can be for CONFIG_CPUMASK_OFFSTACK).
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Similar to the previous patch, by not clearing buddies we can select entities
past their run quota, which can increase latency. This means we have to clear
group buddies as well.

Do not use the group clear for pick_next_task(), otherwise that'll get O(n^2).
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

It was noticed that a task could get re-elected past its run quota due to buddy
affinities. This could increase latency a little. Cure it by more aggresively
clearing buddy state.

We do so in two situations:
 - when we force preempt
 - when we select a buddy to run
Signed-off-by: NMike Galbraith <efault@gmx.de>
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Reinstate the weakening of the sync hint if set. This yields a more
symmetric usage of avg_overlap.
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Pawel Dziekonski reported that the openssl benchmark and his
quantum chemistry application both show slowdowns due to the
scheduler under-parallelizing execution.

The reason are pipe wakeups still doing 'sync' wakeups which
overrides the normal buddy wakeup logic - even if waker and
wakee are loosely coupled.

Fix an inversion of logic in the buddy wakeup code.
Reported-by: NPawel Dziekonski <dzieko@gmail.com>
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: prevent false positive WARN_ON() in clockevents_program_event()

clock_was_set() changes the base->offset of CLOCK_REALTIME and
enforces the reprogramming of the clockevent device to expire timers
which are based on CLOCK_REALTIME. If the clock change is large enough
then the subtraction of the timer expiry value and base->offset can
become negative which triggers the warning in
clockevents_program_event().

Check the subtraction result and set a negative value to 0.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Impact: fix CPU hotplug hang on Power6 testbox

On architectures that support offlining all cpus (at least powerpc/pseries),
hot-unpluging the tick_do_timer_cpu can result in a system hang.

This comes from the fact that if the cpu going down happens to be the
cpu doing the tick, then as the tick_do_timer_cpu handover happens after the
cpu is dead (via the CPU_DEAD notification), we're left without ticks,
jiffies are frozen and any task relying on timers (msleep, ...) is stuck.
That's particularly the case for the cpu looping in __cpu_die() waiting
for the dying cpu to be dead.

This patch addresses this by having the tick_do_timer_cpu handover happen
earlier during the CPU_DYING notification. For this, a new clockevent
notification type is introduced (CLOCK_EVT_NOTIFY_CPU_DYING) which is triggered
in hrtimer_cpu_notify().
Signed-off-by: NSebastien Dugue <sebastien.dugue@bull.net>
Cc: <stable@kernel.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: avoid timer IRQ hanging slow systems

While using the function graph tracer on a virtualized system, the
hrtimer_interrupt can hang the system on an infinite loop.

This can be caused in several situations:

 - the hardware is very slow and HZ is set too high

 - something intrusive is slowing the system down (tracing under emulation)

... and the next clock events to program are always before the current time.

This patch implements a reasonable compromise: if such a situation is
detected, we share the CPUs time in 1/4 to process the hrtimer interrupts.
This is enough to let the system running without serious starvation.

It has been successfully tested under VirtualBox with 1000 HZ and 100 HZ
with function graph tracer launched. On both cases, the clock events were
increased until about 25 ms periodic ticks, which means 40 HZ.

So we change a hard to debug hang into a warning message and a system that
still manages to limp along.
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

The smp_call_function can be passed a wait parameter telling it to
wait for all the functions running on other CPUs to complete before
returning, or to return without waiting. Unfortunately, this is
currently just a suggestion and not manditory. That is, the
smp_call_function can decide not to return and wait instead.

The reason for this is because it uses kmalloc to allocate storage
to send to the called CPU and that CPU will free it when it is done.
But if we fail to allocate the storage, the stack is used instead.
This means we must wait for the called CPU to finish before
continuing.

Unfortunatly, some callers do no abide by this hint and act as if
the non-wait option is mandatory. The MTRR code for instance will
deadlock if the smp_call_function is set to wait. This is because
the smp_call_function will wait for the other CPUs to finish their
called functions, but those functions are waiting on the caller to
continue.

This patch changes the generic smp_call_function code to use per cpu
variables if the allocation of the data fails for a single CPU call. The
smp_call_function_many will fall back to the smp_call_function_single
if it fails its alloc. The smp_call_function_single is modified
to not force the wait state.

Since we now are using a single data per cpu we must synchronize the
callers to prevent a second caller modifying the data before the
first called IPI functions complete. To do so, I added a flag to
the call_single_data called CSD_FLAG_LOCK. When the single CPU is
called (which can be called when a many call fails an alloc), we
set the LOCK bit on this per cpu data. When the caller finishes
it clears the LOCK bit.

The caller must wait till the LOCK bit is cleared before setting
it. When it is cleared, there is no IPI function using it.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: NJens Axboe <jens.axboe@oracle.com>
Acked-by: NLinus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Geert Uytterhoeven wrote:

> %4zu?
Reported-by: NGeert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: NRandy Dunlap <randy.dunlap@oracle.com>
Acked-by: NEduard - Gabriel Munteanu <eduard.munteanu@linux360.ro>
Signed-off-by: NIngo Molnar <mingo@elte.hu>