diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-03-19 14:48:35 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-03-19 14:48:35 -0700 |
commit | 0d707a2f24c4a962313cffc980e2d74df460e45a (patch) | |
tree | 3db3487e147c1c6482edfe3ae22f0c8ec0857978 /kernel | |
parent | efac2483e8f289cd879e750075e63a9d16897e65 (diff) | |
parent | b3a5d111994450909158929560906f2c1c6c1d85 (diff) | |
download | linux-0d707a2f24c4a962313cffc980e2d74df460e45a.tar.bz2 |
Merge branch 'for-4.16-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu
Pull percpu fixes from Tejun Heo:
"Late percpu pull request for v4.16-rc6.
- percpu allocator pool replenishing no longer triggers OOM or
warning messages.
Also, the alloc interface now understands __GFP_NORETRY and
__GFP_NOWARN. This is to allow avoiding OOMs from userland
triggered actions like bpf map creation.
Also added cond_resched() in alloc loop.
- perpcu allocation now can be interrupted by kill sigs to avoid
deadlocking OOM killer.
- Added Dennis Zhou as a co-maintainer.
He has rewritten the area map allocator, understands most of the
code base and has been responsive for all bug reports"
* 'for-4.16-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu:
percpu_ref: Update doc to dissuade users from depending on internal RCU grace periods
mm: Allow to kill tasks doing pcpu_alloc() and waiting for pcpu_balance_workfn()
percpu: include linux/sched.h for cond_resched()
percpu: add a schedule point in pcpu_balance_workfn()
percpu: allow select gfp to be passed to underlying allocators
percpu: add __GFP_NORETRY semantics to the percpu balancing path
percpu: match chunk allocator declarations with definitions
percpu: add Dennis Zhou as a percpu co-maintainer
Diffstat (limited to 'kernel')
0 files changed, 0 insertions, 0 deletions