]> Git Repo - linux.git/commit
locking/pvqspinlock: Don't wait if vCPU is preempted
authorPan Xinhui <[email protected]>
Tue, 10 Jan 2017 07:56:46 +0000 (02:56 -0500)
committerIngo Molnar <[email protected]>
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 <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
[ Fixed typos in the changelog, removed ugly linebreak from the code. ]
Signed-off-by: Ingo Molnar <[email protected]>
kernel/locking/qspinlock_paravirt.h
This page took 0.054106 seconds and 4 git commands to generate.