locking/pvqspinlock: Don't wait if vCPU is preempted
authorPan Xinhui <xinhui.pan@linux.vnet.ibm.com>
Tue, 10 Jan 2017 07:56:46 +0000 (02:56 -0500)
committerIngo Molnar <mingo@kernel.org>
Thu, 12 Jan 2017 08:35:57 +0000 (09:35 +0100)
commit75437bb304b20a2b350b9a8e9f9238d5e24e12ba
treed8c179d3b1194a8eb7ce8ff9a0c5326dbcc0a01d
parent607904c357c61adf20b8fd18af765e501d61a385
locking/pvqspinlock: Don't wait if vCPU is preempted

If prev node is not in running state or its vCPU is preempted, we can give
up our vCPU slices in pv_wait_node() ASAP.

Signed-off-by: Pan Xinhui <xinhui.pan@linux.vnet.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: longman@redhat.com
Link: http://lkml.kernel.org/r/1484035006-6787-1-git-send-email-xinhui.pan@linux.vnet.ibm.com
[ Fixed typos in the changelog, removed ugly linebreak from the code. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
kernel/locking/qspinlock_paravirt.h