Skip to content

mm: Preemptibility -v5

Peter Zijlstra linux-arch lkml 1 version In review

Get series with b4
b4 am [email protected]

Versions newest first

  1. v1 Latest20 patches 1 replyIn review

Patches in v1 No applies recorded yet

#Subject and filesSizeRepliesApplied
1/20powerpc: Use call_rcu_sched() for pagetablesarch/powerpc/mm/pgtable.c+1 -10 replies
2/20mm: Improve page_lock_anon_vma() commentmm/rmap.c+16 -20 replies
3/20mm: Rename drop_anon_vma to put_anon_vmainclude/linux/rmap.h mm/ksm.c mm/migrate.c +1 more+10 -100 replies
4/20mm: Move anon_vma ref out from under CONFIG_KSMinclude/linux/rmap.h mm/rmap.c+10 -440 replies
5/20mm: Simplify anon_vma refcountsinclude/linux/rmap.h mm/ksm.c mm/rmap.c+38 -560 replies
6/20mm: Use refcounts for page_lock_anon_vma()mm/rmap.c+24 -100 replies
7/20mm: Preemptible mmu_gatherfs/exec.c include/asm-generic/tlb.h include/linux/mm.h +2 more+53 -530 replies
8/20powerpc: Preemptible mmu_gatherarch/powerpc/include/asm/pgalloc.h arch/powerpc/include/asm/thread_info.h arch/powerpc/include/asm/tlb.h +5 more+47 -200 replies
9/20sparc: Preemptible mmu_gatherarch/sparc/include/asm/pgalloc_64.h arch/sparc/include/asm/tlb_64.h arch/sparc/include/asm/tlbflush_64.h +2 more+51 -1120 replies
10/20s390: preemptible mmu_gatherarch/s390/include/asm/tlb.h+25 -180 replies
11/20arm: Preemptible mmu_gatherarch/arm/include/asm/tlb.h+2 -100 replies
12/20sh: Preemptible mmu_gatherarch/sh/include/asm/tlb.h+2 -100 replies
13/20um: Preemptible mmu_gatherarch/um/include/asm/tlb.h+2 -140 replies
14/20ia64: Preemptible mmu_gatherarch/ia64/include/asm/tlb.h+24 -150 replies
15/20mm, powerpc: Move the RCU page-table freeing into generic codearch/Kconfig arch/powerpc/Kconfig arch/powerpc/include/asm/pgalloc.h +7 more+151 -1250 replies
16/20lockdep, mutex: Provide mutex_lock_nest_lockinclude/linux/lockdep.h include/linux/mutex.h kernel/mutex.c+29 -80 replies
17/20mutex: Provide mutex_is_contendedinclude/linux/mutex.h+5 -00 replies
18/20mm: Convert i_mmap_lock and anon_vma->lock to mutexesarch/x86/mm/hugetlbpage.c fs/gfs2/main.c fs/hugetlbfs/inode.c +14 more+58 -580 replies
19/20mm: Extended batches for generic mmu_gatherinclude/asm-generic/tlb.h+82 -400 replies
20/20mm: Optimize page_lock_anon_vma() fast-pathmm/rmap.c+67 -40 replies

Reviews trailers per patch

3 of 20 patches have a Reviewed-by or Acked-by.

PatchBenjamin HerrenschmidtMel GormanDavid MillerNick PigginKOSAKI Motohiro
1/20A-b
2/20A-b R-b
3/20
4/20A-b
5/20
6/20
7/20
8/20
9/20
10/20
11/20
12/20
13/20
14/20
15/20Requested-by
16/20
17/20
18/20
19/20Requested-by
20/20

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 00/20] mm: Preemptibility -v5

This patch-set makes part of the mm a lot more preemptible. It converts i_mmap_lock and anon_vma->lock to mutexes and makes mmu_gather fully preemptible.

The main motivation was making mm_take_all_locks() preemptible, since it appears people are nesting hundreds of spinlocks there.

The side-effects are that can finally make mmu_gather preemptible, something which lots of people have wanted to do for a long time.

It also gets us anon_vma refcounting, which seems to result in a nice cleanup of the anon_vma lifetime rules wrt KSM and compaction.

This patch-set it build and boot-tested on x86_64 (a previous version was also tested on Dave's Niagra2 machines, and I suppose s390 was too when Martin provided the conversion patch for his arch).

There are no known architectures left unconverted.

Yanmin ran the -v3 posting through the comprehensive Intel test farm and didn't find any regressions.

( Not included in this posting are the 4 Sparc64 patches that implement
gup_fast, those can be applied separately after this series gets anywhere. )

The full series (including the Sparc64 gup_fast bits) also available in -git form from (against Linus' tree as of about an hour ago):

git://git.kernel.org/pub/scm/linux/kernel/git/peterz/linux-2.6-mmu_preempt.git mmu_preempt

DaveM mentioned some sparc64 trouble with the -v4 posting, this turned out to be a false positive as unpatched kernels also are having trouble on his machines.

Linus, Andrew, Stephen, can we add this to -next for .37?