Re: [PATCH] arch, mm: introduce arch_tlb_gather_mmu_exit

2017-12-14 Thread Michal Hocko
On Tue 05-12-17 20:14:37, Michal Hocko wrote: > On Tue 05-12-17 10:31:12, Linus Torvalds wrote: > > On Tue, Dec 5, 2017 at 6:58 AM, Michal Hocko wrote: > > > > > > This all is nice but tlb_gather users are not aware of that and this can > > > actually cause some real problems. E.g. the oom_reaper

Re: [PATCH] arch, mm: introduce arch_tlb_gather_mmu_exit

2017-12-05 Thread Michal Hocko
On Tue 05-12-17 10:31:12, Linus Torvalds wrote: > On Tue, Dec 5, 2017 at 6:58 AM, Michal Hocko wrote: > > > > This all is nice but tlb_gather users are not aware of that and this can > > actually cause some real problems. E.g. the oom_reaper tries to reap the > > whole address space but it might r

Re: [PATCH] arch, mm: introduce arch_tlb_gather_mmu_exit

2017-12-05 Thread Linus Torvalds
On Tue, Dec 5, 2017 at 6:58 AM, Michal Hocko wrote: > > This all is nice but tlb_gather users are not aware of that and this can > actually cause some real problems. E.g. the oom_reaper tries to reap the > whole address space but it might race with threads accessing the memory [1]. > It is possibl

[PATCH] arch, mm: introduce arch_tlb_gather_mmu_exit

2017-12-05 Thread Michal Hocko
From: Michal Hocko 5a7862e83000 ("arm64: tlbflush: avoid flushing when fullmm == 1") has introduced an optimization to not flush tlb when we are tearing the whole address space down. Will goes on to explain : Basically, we tag each address space with an ASID (PCID on x86) which : is resident in

Re: [RFC PATCH] arch, mm: introduce arch_tlb_gather_mmu_exit

2017-11-28 Thread Michal Hocko
On Tue 28-11-17 19:00:01, Will Deacon wrote: > On Thu, Nov 23, 2017 at 10:02:36AM +0100, Michal Hocko wrote: > > From: Michal Hocko > > > > 5a7862e83000 ("arm64: tlbflush: avoid flushing when fullmm == 1") has > > introduced an optimization to not flush tlb when we are tearing the > > whole addre

Re: [RFC PATCH] arch, mm: introduce arch_tlb_gather_mmu_exit

2017-11-28 Thread Will Deacon
On Thu, Nov 23, 2017 at 10:02:36AM +0100, Michal Hocko wrote: > From: Michal Hocko > > 5a7862e83000 ("arm64: tlbflush: avoid flushing when fullmm == 1") has > introduced an optimization to not flush tlb when we are tearing the > whole address space down. Will goes on to explain > > : Basically,

[RFC PATCH] arch, mm: introduce arch_tlb_gather_mmu_exit

2017-11-23 Thread Michal Hocko
From: Michal Hocko 5a7862e83000 ("arm64: tlbflush: avoid flushing when fullmm == 1") has introduced an optimization to not flush tlb when we are tearing the whole address space down. Will goes on to explain : Basically, we tag each address space with an ASID (PCID on x86) which : is resident in