Skip to content

locking: Percpu-rwsem rewrite

Peter Zijlstra lkml 1 version Applied

Status from this message: The following commit has been merged into the locking/core branch of tip:

Get series with b4
b4 am [email protected]

Versions newest first

  1. v1 Latest7 patches 12 repliesApplied

Patches in v1 Applied

#Subject and filesSizeRepliesApplied
1/7locking/percpu-rwsem, lockdep: Make percpu-rwsem use its own lockdep_mapinclude/linux/percpu-rwsem.h kernel/cpu.c kernel/locking/percpu-rwsem.c +2 more+37 -180 replies
2/7locking/percpu-rwsem: Convert to boolinclude/linux/percpu-rwsem.h kernel/locking/percpu-rwsem.c+7 -70 replies
3/7locking/percpu-rwsem: Move __this_cpu_inc() into the slowpathinclude/linux/percpu-rwsem.h kernel/locking/percpu-rwsem.c+8 -40 replies
4/7locking/percpu-rwsem: Extract __percpu_down_read_trylock()kernel/locking/percpu-rwsem.c+13 -60 replies
5/7locking/percpu-rwsem: Remove the embedded rwseminclude/linux/percpu-rwsem.h include/linux/rwsem.h include/linux/wait.h +3 more+123 -798 replies
5/7locking/percpu-rwsem: Remove the embedded rwseminclude/linux/percpu-rwsem.h include/linux/wait.h kernel/locking/percpu-rwsem.c +2 more+123 -710 replies
6/7locking/percpu-rwsem: Fold __percpu_up_read()include/linux/percpu-rwsem.h kernel/exit.c kernel/locking/percpu-rwsem.c+16 -190 replies
7/7locking/percpu-rwsem: Add might_sleep() for writer lockingkernel/locking/percpu-rwsem.c+1 -00 replies

Reviews trailers per patch

2 of 8 patches have a Reviewed-by or Acked-by of their own; the series has one for all of them.

PatchJuri LelliWaiman LongDavidlohr BuesoWill DeaconChristoph Hellwig
SeriesT-b A-b R-b A-b
1/7T-b
2/7T-b
3/7T-b
4/7T-b
5/7T-b T-b A-b R-b A-b Requested-by
5/7T-b T-b A-b R-b A-b Requested-by
6/7
7/7

Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes. Scroll the table sideways for all 5 reviewers.

Read the v1 thread

Cover letter [PATCH -v2 0/7] locking: Percpu-rwsem rewrite

Hi all,

This is the long awaited report of the percpu-rwsem rework (sorry Juri).

IIRC (I really have trouble keeping up momentum on this series) I've addressed all previous comments by Oleg and Davidlohr and Waiman and hope we can stick this in tip/locking/core for inclusion in the next merge.

It has been cooked (thoroughly) in PREEMPT_RT, and not found wanting.

Any objections to me stuffing it in so we can all forget about it properly?