Milton Miller ff3af58772 seqlock: Don't smp_rmb in seqlock reader spin loop ... commit 5db1256a51 upstream. Move the smp_rmb after cpu_relax loop in read_seqlock and add ACCESS_ONCE to make sure the test and return are consistent. A multi-threaded core in the lab didn't like the update from 2.6.35 to 2.6.36, to the point it would hang during boot when multiple threads were active. Bisection showed af5ab277de (clockevents: Remove the per cpu tick skew) as the culprit and it is supported with stack traces showing xtime_lock waits including tick_do_update_jiffies64 and/or update_vsyscall. Experimentation showed the combination of cpu_relax and smp_rmb was significantly slowing the progress of other threads sharing the core, and this patch is effective in avoiding the hang. A theory is the rmb is affecting the whole core while the cpu_relax is causing a resource rebalance flush, together they cause an interfernce cadance that is unbroken when the seqlock reader has interrupts disabled. At first I was confused why the refactor in 3c22cd5709 (kernel: optimise seqlock) didn't affect this patch application, but after some study that affected seqcount not seqlock. The new seqcount was not factored back into the seqlock. I defer that the future. While the removal of the timer interrupt offset created contention for the xtime lock while a cpu does the additonal work to update the system clock, the seqlock implementation with the tight rmb spin loop goes back much further, and is just waiting for the right trigger. Signed-off-by: Milton Miller <miltonm@bga.com> Cc: <linuxppc-dev@lists.ozlabs.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Anton Blanchard <anton@samba.org> Cc: Paul McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Eric Dumazet <eric.dumazet@gmail.com> Link: http://lkml.kernel.org/r/%3Cseqlock-rmb%40mdm.bga.com%3E Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>		2011-06-23 15:24:02 -07:00
..
acpi	ACPI: skip checking BM_STS if the BIOS doesn't ask for it	2010-08-02 10:21:24 -07:00
asm-generic	dma-mapping: fix dma_sync_single_range_*	2010-05-26 14:29:14 -07:00
crypto	Merge git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6	2009-09-11 09:38:37 -07:00
drm	drm: fix unsigned vs signed comparison issue in modeset ctl ioctl.	2011-03-07 15:17:52 -08:00
keys	RxRPC: Fix v1 keys	2011-03-14 14:29:53 -07:00
linux	seqlock: Don't smp_rmb in seqlock reader spin loop	2011-06-23 15:24:02 -07:00
math-emu	math-emu: correct test for downshifting fraction in _FP_FROM_INT()	2010-08-02 10:20:44 -07:00
media	V4L/DVB (13019): video: initial support for ADV7180	2009-09-19 00:53:39 -03:00
mtd
net	af_unix: limit recursion level	2011-05-09 15:55:36 -07:00
pcmcia	PM / yenta: Split resume into early and late parts (rev. 4)	2009-11-03 10:54:58 +01:00
rdma	trivial: fix typo "to to" in multiple files	2009-09-21 15:14:55 +02:00
rxrpc
scsi	ses: Avoid kernel panic when lun 0 is not mapped	2011-04-14 16:53:20 -07:00
sound	ASoC: Explicitly say registerless widgets have no register	2011-04-14 16:53:26 -07:00
trace	tracing: Fix ftrace_event_call alignment for use with gcc 4.5	2010-05-12 14:57:14 -07:00
video	davinci-fb-frame-buffer-driver-for-ti-da8xx-omap-l1xx-v4	2009-09-23 07:39:51 -07:00
xen
Kbuild