Add the "timers: do not raise softirq unconditionally" temporarily 26/1226/7
authorYunhong Jiang <yunhong.jiang@intel.com>
Tue, 18 Aug 2015 18:07:48 +0000 (11:07 -0700)
committerYunhong Jiang <yunhong.jiang@linux.intel.com>
Fri, 22 Jul 2016 00:48:26 +0000 (17:48 -0700)
commitef4e798bc8761c401451649ed17a52e3e1c638e8
tree84993bd865ba6e65be526af0259ca25f33c9d662
parentc715b6029fd5b4eaf323f5efde4ec5db5ba0a9b4
Add the "timers: do not raise softirq unconditionally" temporarily

This patch enable the nohz_full and is important for RT. Bring it back
temporarily, while waiting for more work on RT community.

Please refer to https://lkml.org/lkml/2015/3/17/783 for more information
of the revert.

A little rebase needed because it's reverted on old code base.

Please notice that we change the rt_mutex_trylock() so that we can get
the tvec_base lock there. This is sure to be wrong, and should be fixed
cleanly. And that's the major reason the original patch are reverted on the
upstream RT linux. Will discuss with upstream on how to achieve the
solution.

Upstream status: pending

Change-Id: I2747e087faf4145b69b800a60b8d9414bc71e206
Signed-off-by: Yunhong Jiang <yunhong.jiang@linux.intel.com>
kernel/kernel/locking/rtmutex.c
kernel/kernel/time/timer.c