OpenCloudOS-Kernel/arch/x86
Linus Torvalds b91e1302ad mm: optimize PageWaiters bit use for unlock_page()
In commit 6290602709 ("mm: add PageWaiters indicating tasks are
waiting for a page bit") Nick Piggin made our page locking no longer
unconditionally touch the hashed page waitqueue, which not only helps
performance in general, but is particularly helpful on NUMA machines
where the hashed wait queues can bounce around a lot.

However, the "clear lock bit atomically and then test the waiters bit"
sequence turns out to be much more expensive than it needs to be,
because you get a nasty stall when trying to access the same word that
just got updated atomically.

On architectures where locking is done with LL/SC, this would be trivial
to fix with a new primitive that clears one bit and tests another
atomically, but that ends up not working on x86, where the only atomic
operations that return the result end up being cmpxchg and xadd.  The
atomic bit operations return the old value of the same bit we changed,
not the value of an unrelated bit.

On x86, we could put the lock bit in the high bit of the byte, and use
"xadd" with that bit (where the overflow ends up not touching other
bits), and look at the other bits of the result.  However, an even
simpler model is to just use a regular atomic "and" to clear the lock
bit, and then the sign bit in eflags will indicate the resulting state
of the unrelated bit #7.

So by moving the PageWaiters bit up to bit #7, we can atomically clear
the lock bit and test the waiters bit on x86 too.  And architectures
with LL/SC (which is all the usual RISC suspects), the particular bit
doesn't matter, so they are fine with this approach too.

This avoids the extra access to the same atomic word, and thus avoids
the costly stall at page unlock time.

The only downside is that the interface ends up being a bit odd and
specialized: clear a bit in a byte, and test the sign bit.  Nick doesn't
love the resulting name of the new primitive, but I'd rather make the
name be descriptive and very clear about the limitation imposed by
trying to work across all relevant architectures than make it be some
generic thing that doesn't make the odd semantics explicit.

So this introduces the new architecture primitive

    clear_bit_unlock_is_negative_byte();

and adds the trivial implementation for x86.  We have a generic
non-optimized fallback (that just does a "clear_bit()"+"test_bit(7)"
combination) which can be overridden by any architecture that can do
better.  According to Nick, Power has the same hickup x86 has, for
example, but some other architectures may not even care.

All these optimizations mean that my page locking stress-test (which is
just executing a lot of small short-lived shell scripts: "make test" in
the git source tree) no longer makes our page locking look horribly bad.
Before all these optimizations, just the unlock_page() costs were just
over 3% of all CPU overhead on "make test".  After this, it's down to
0.66%, so just a quarter of the cost it used to be.

(The difference on NUMA is bigger, but there this micro-optimization is
likely less noticeable, since the big issue on NUMA was not the accesses
to 'struct page', but the waitqueue accesses that were already removed
by Nick's earlier commit).

Acked-by: Nick Piggin <npiggin@gmail.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Bob Peterson <rpeterso@redhat.com>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Cc: Andrew Lutomirski <luto@kernel.org>
Cc: Andreas Gruenbacher <agruenba@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-12-29 11:03:15 -08:00
..
boot Revert "x86/boot: Fail the boot if !M486 and CPUID is missing" 2016-12-19 11:54:20 +01:00
configs IOMMU Updates for Linux v4.9 2016-10-11 12:52:41 -07:00
crypto Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6 2016-12-14 13:31:29 -08:00
entry Merge branch 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2016-12-25 14:30:04 -08:00
events cpu/hotplug: Cleanup state names 2016-12-25 10:47:44 +01:00
ia32 Replace <asm/uaccess.h> with <linux/uaccess.h> globally 2016-12-24 11:46:01 -08:00
include mm: optimize PageWaiters bit use for unlock_page() 2016-12-29 11:03:15 -08:00
kernel x86/mce/AMD: Make the init code more robust 2016-12-26 17:30:24 -08:00
kvm Merge branch 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2016-12-25 14:30:04 -08:00
lguest clocksource: Use a plain u64 instead of cycle_t 2016-12-25 11:04:12 +01:00
lib Replace <asm/uaccess.h> with <linux/uaccess.h> globally 2016-12-24 11:46:01 -08:00
math-emu Replace <asm/uaccess.h> with <linux/uaccess.h> globally 2016-12-24 11:46:01 -08:00
mm Replace <asm/uaccess.h> with <linux/uaccess.h> globally 2016-12-24 11:46:01 -08:00
net bpf: xdp: Allow head adjustment in XDP prog 2016-12-08 14:25:13 -05:00
oprofile x86/oprofile/nmi: Convert to hotplug state machine 2016-11-22 23:34:43 +01:00
pci xen: features and fixes for 4.10 rc0 2016-12-13 16:07:55 -08:00
platform clocksource: Use a plain u64 instead of cycle_t 2016-12-25 11:04:12 +01:00
power Merge branch 'x86-timers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2016-12-18 13:59:10 -08:00
purgatory x86/kexec: add -fno-PIE 2016-11-09 22:28:09 +01:00
ras x86/RAS: Add TSC timestamp to the injected MCE 2016-11-08 17:10:13 +01:00
realmode x86/build: Don't use $(LINUXINCLUDE) twice 2016-11-28 07:49:17 +01:00
tools x86/tools: Fix gcc-7 warning in relocs.c 2016-12-19 11:50:24 +01:00
um Replace <asm/uaccess.h> with <linux/uaccess.h> globally 2016-12-24 11:46:01 -08:00
video x86/video: Don't assume all FB devices are PCI devices 2016-03-15 11:08:26 +01:00
xen Merge branch 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2016-12-25 14:30:04 -08:00
.gitignore
Kbuild perf/x86: Move perf_event.c ............... => x86/events/core.c 2016-02-09 10:23:49 +01:00
Kconfig Merge branch 'x86-cache-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2016-12-22 09:25:45 -08:00
Kconfig.cpu x86/Kconfig/cpus: Fix/complete CPU type help texts 2015-10-21 11:12:56 +02:00
Kconfig.debug Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2016-03-15 09:32:27 -07:00
Makefile lib/raid6: Add AVX512 optimized gen_syndrome functions 2016-09-21 09:09:44 -07:00
Makefile.um
Makefile_32.cpu