Paul Mackerras 242fa18ad8 powerpc: Make sure IPI handlers see data written by IPI senders ... commit 9fb1b36ca1 upstream. We have been observing hangs, both of KVM guest vcpu tasks and more generally, where a process that is woken doesn't properly wake up and continue to run, but instead sticks in TASK_WAKING state. This happens because the update of rq->wake_list in ttwu_queue_remote() is not ordered with the update of ipi_message in smp_muxed_ipi_message_pass(), and the reading of rq->wake_list in scheduler_ipi() is not ordered with the reading of ipi_message in smp_ipi_demux(). Thus it is possible for the IPI receiver not to see the updated rq->wake_list and therefore conclude that there is nothing for it to do. In order to make sure that anything done before smp_send_reschedule() is ordered before anything done in the resulting call to scheduler_ipi(), this adds barriers in smp_muxed_message_pass() and smp_ipi_demux(). The barrier in smp_muxed_message_pass() is a full barrier to ensure that there is a full ordering between the smp_send_reschedule() caller and scheduler_ipi(). In smp_ipi_demux(), we use xchg() rather than xchg_local() because xchg() includes release and acquire barriers. Using xchg() rather than xchg_local() makes sense given that ipi_message is not just accessed locally. This moves the barrier between setting the message and calling the cause_ipi() function into the individual cause_ipi implementations. Most of them -- those that used outb, out_8 or similar -- already had a full barrier because out_8 etc. include a sync before the MMIO store. This adds an explicit barrier in the two remaining cases. These changes made no measurable difference to the speed of IPIs as measured using a simple ping-pong latency test across two CPUs on different cores of a POWER7 machine. The analysis of the reason why processes were not waking up properly is due to Milton Miller. Reported-by: Milton Miller <miltonm@bga.com> Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>		2012-09-14 10:00:22 -07:00
..
boot	powerpc/85xx: use the BRx registers to enable indirect mode on the P1022DS	2012-08-09 08:31:27 -07:00
configs	Merge remote-tracking branch 'kumar/next' into merge	2012-04-02 13:57:46 +10:00
include/asm	powerpc: Add "memory" attribute for mfmsr()	2012-08-09 08:31:27 -07:00
kernel	powerpc: Make sure IPI handlers see data written by IPI senders	2012-09-14 10:00:22 -07:00
kvm	powerpc/kvm: sldi should be sld	2012-07-16 09:03:22 -07:00
lib	Disintegrate asm/system.h for PowerPC	2012-03-28 18:30:02 +01:00
math-emu
mm	powerpc: Fix uninitialised error in numa.c	2012-07-16 09:03:21 -07:00
net	bpf jit: Let the powerpc jit handle negative offsets	2012-04-30 13:40:50 -04:00
oprofile	Disintegrate asm/system.h for PowerPC	2012-03-28 18:30:02 +01:00
perf	powerpc/perf: Fix instruction address sampling on 970 and Power4	2012-03-28 11:33:24 +11:00
platforms	powerpc/85xx: use the BRx registers to enable indirect mode on the P1022DS	2012-08-09 08:31:27 -07:00
sysdev	powerpc: Make sure IPI handlers see data written by IPI senders	2012-09-14 10:00:22 -07:00
xmon	powerpc/xmon: Use cpumask iterator to avoid warning	2012-07-16 09:03:23 -07:00
Kconfig	Merge branch 'for-linus' of git://git.linaro.org/people/rmk/linux-arm	2012-03-29 16:53:48 -07:00
Kconfig.debug	irqdomain: Remove powerpc dependency from debugfs file	2012-03-29 14:31:02 -06:00
Makefile	powerpc/perf: Move perf core & PMU code into a subdirectory	2012-02-23 10:50:04 +11:00
relocs_check.pl	powerpc: Process dynamic relocations for kernel	2011-12-20 10:21:08 -05:00