linux/arch
Stefan Bader 76eaca031f xen: Send spinlock IPI to all waiters
There is a loophole between Xen's current implementation of
pv-spinlocks and the scheduler. This was triggerable through
a testcase until v3.6 changed the TLB flushing code. The
problem potentially is still there just not observable in the
same way.

What could happen was (is):

1. CPU n tries to schedule task x away and goes into a slow
   wait for the runq lock of CPU n-# (must be one with a lower
   number).
2. CPU n-#, while processing softirqs, tries to balance domains
   and goes into a slow wait for its own runq lock (for updating
   some records). Since this is a spin_lock_irqsave in softirq
   context, interrupts will be re-enabled for the duration of
   the poll_irq hypercall used by Xen.
3. Before the runq lock of CPU n-# is unlocked, CPU n-1 receives
   an interrupt (e.g. endio) and when processing the interrupt,
   tries to wake up task x. But that is in schedule and still
   on_cpu, so try_to_wake_up goes into a tight loop.
4. The runq lock of CPU n-# gets unlocked, but the message only
   gets sent to the first waiter, which is CPU n-# and that is
   busily stuck.
5. CPU n-# never returns from the nested interruption to take and
   release the lock because the scheduler uses a busy wait.
   And CPU n never finishes the task migration because the unlock
   notification only went to CPU n-#.

To avoid this and since the unlocking code has no real sense of
which waiter is best suited to grab the lock, just send the IPI
to all of them. This causes the waiters to return from the hyper-
call (those not interrupted at least) and do active spinlocking.

BugLink: http://bugs.launchpad.net/bugs/1011792

Acked-by: Jan Beulich <JBeulich@suse.com>
Signed-off-by: Stefan Bader <stefan.bader@canonical.com>
Cc: stable@vger.kernel.org
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2013-02-19 22:03:29 -05:00
..
alpha ALPHA: drivers: remove __dev* attributes. 2013-01-03 15:57:13 -08:00
arm xen: introduce xen_remap, use it instead of ioremap 2013-02-19 22:02:34 -05:00
arm64 arm64: elf: fix core dumping to match what glibc expects 2013-01-22 17:50:59 +00:00
avr32 ARCH: drivers remove __dev* attributes. 2013-01-03 15:57:13 -08:00
blackfin ARCH: drivers remove __dev* attributes. 2013-01-03 15:57:13 -08:00
c6x These are a few cleanups for asm-generic: 2012-12-21 16:39:08 -08:00
cris ARCH: drivers remove __dev* attributes. 2013-01-03 15:57:13 -08:00
frv ARCH: drivers remove __dev* attributes. 2013-01-03 15:57:13 -08:00
h8300 These are a few cleanups for asm-generic: 2012-12-21 16:39:08 -08:00
hexagon Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/signal 2012-12-20 18:05:28 -08:00
ia64 ia64: kill thread_matches(), unexport ptrace_check_attach() 2013-01-20 12:26:05 -08:00
m32r ARCH: drivers remove __dev* attributes. 2013-01-03 15:57:13 -08:00
m68k Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/geert/linux-m68k 2013-01-23 13:31:15 -08:00
microblaze Merge branch 'next' of git://git.monstr.eu/linux-2.6-microblaze 2013-01-07 07:39:32 -08:00
mips Merge branch 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus 2013-01-07 07:50:41 -08:00
mn10300 arch/mn10300/Kconfig: select CONFIG_GENERIC_ATOMIC64 2013-01-11 14:54:55 -08:00
openrisc ARCH: drivers remove __dev* attributes. 2013-01-03 15:57:13 -08:00
parisc parisc: sigaltstack doesn't round ss.ss_sp as required 2013-01-07 23:06:27 +01:00
powerpc KVM: PPC: Emulate dcbf 2013-01-18 00:40:49 +01:00
s390 Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux 2013-01-17 08:56:30 -08:00
score ARCH: drivers remove __dev* attributes. 2013-01-03 15:57:13 -08:00
sh sh: ecovec: add sample amixer settings 2013-01-16 18:30:44 +09:00
sparc sparc: remove __devinit, __devexit annotations 2013-01-12 15:28:45 -08:00
tile ARCH: drivers remove __dev* attributes. 2013-01-03 15:57:13 -08:00
um Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/signal 2012-12-20 18:05:28 -08:00
unicore32 ARCH: drivers remove __dev* attributes. 2013-01-03 15:57:13 -08:00
x86 xen: Send spinlock IPI to all waiters 2013-02-19 22:03:29 -05:00
xtensa These are a few cleanups for asm-generic: 2012-12-21 16:39:08 -08:00
.gitignore
Kconfig Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/signal 2012-12-20 18:05:28 -08:00