Re: [RFC 01/20] mm/tlb: fix fullmm semantics

2021-02-03 Thread Nadav Amit
> On Feb 3, 2021, at 1:44 AM, Will Deacon wrote: > > On Tue, Feb 02, 2021 at 01:35:38PM -0800, Nadav Amit wrote: >>> On Feb 2, 2021, at 3:00 AM, Peter Zijlstra wrote: >>> >>> On Tue, Feb 02, 2021 at 01:32:36AM -0800, Nadav Amit wrote: > On Feb 1, 2021, at 3:36 AM, Peter Zijlstra wrote: >>>

Re: [RFC 01/20] mm/tlb: fix fullmm semantics

2021-02-03 Thread Will Deacon
On Tue, Feb 02, 2021 at 01:35:38PM -0800, Nadav Amit wrote: > > On Feb 2, 2021, at 3:00 AM, Peter Zijlstra wrote: > > > > On Tue, Feb 02, 2021 at 01:32:36AM -0800, Nadav Amit wrote: > >>> On Feb 1, 2021, at 3:36 AM, Peter Zijlstra wrote: > >>> > >>> > >>> https://lkml.kernel.org/r/202101272353

Re: [RFC 01/20] mm/tlb: fix fullmm semantics

2021-02-02 Thread Nadav Amit
> On Feb 2, 2021, at 3:00 AM, Peter Zijlstra wrote: > > On Tue, Feb 02, 2021 at 01:32:36AM -0800, Nadav Amit wrote: >>> On Feb 1, 2021, at 3:36 AM, Peter Zijlstra wrote: >>> >>> >>> https://lkml.kernel.org/r/20210127235347.1402-1-w...@kernel.org >> >> I have seen this series, and applied my p

Re: [RFC 01/20] mm/tlb: fix fullmm semantics

2021-02-02 Thread Peter Zijlstra
On Tue, Feb 02, 2021 at 01:32:36AM -0800, Nadav Amit wrote: > > On Feb 1, 2021, at 3:36 AM, Peter Zijlstra wrote: > > > > > > https://lkml.kernel.org/r/20210127235347.1402-1-w...@kernel.org > > I have seen this series, and applied my patches on it. > > Despite Will’s patches, there were still

Re: [RFC 01/20] mm/tlb: fix fullmm semantics

2021-02-02 Thread Nadav Amit
> On Feb 1, 2021, at 3:36 AM, Peter Zijlstra wrote: > > > https://lkml.kernel.org/r/20210127235347.1402-1-w...@kernel.org I have seen this series, and applied my patches on it. Despite Will’s patches, there were still inconsistencies between fullmm and need_flush_all. Am I missing something?

Re: [RFC 01/20] mm/tlb: fix fullmm semantics

2021-02-01 Thread Peter Zijlstra
https://lkml.kernel.org/r/20210127235347.1402-1-w...@kernel.org

Re: [RFC 01/20] mm/tlb: fix fullmm semantics

2021-01-31 Thread Nadav Amit
> On Jan 30, 2021, at 6:57 PM, Andy Lutomirski wrote: > > On Sat, Jan 30, 2021 at 5:19 PM Nadav Amit wrote: >>> On Jan 30, 2021, at 5:02 PM, Andy Lutomirski wrote: >>> >>> On Sat, Jan 30, 2021 at 4:16 PM Nadav Amit wrote: From: Nadav Amit fullmm in mmu_gather is supposed to i

Re: [RFC 01/20] mm/tlb: fix fullmm semantics

2021-01-30 Thread Andy Lutomirski
On Sat, Jan 30, 2021 at 5:19 PM Nadav Amit wrote: > > > On Jan 30, 2021, at 5:02 PM, Andy Lutomirski wrote: > > > > On Sat, Jan 30, 2021 at 4:16 PM Nadav Amit wrote: > >> From: Nadav Amit > >> > >> fullmm in mmu_gather is supposed to indicate that the mm is torn-down > >> (e.g., on process exit

Re: [RFC 01/20] mm/tlb: fix fullmm semantics

2021-01-30 Thread Nadav Amit
> On Jan 30, 2021, at 5:02 PM, Andy Lutomirski wrote: > > On Sat, Jan 30, 2021 at 4:16 PM Nadav Amit wrote: >> From: Nadav Amit >> >> fullmm in mmu_gather is supposed to indicate that the mm is torn-down >> (e.g., on process exit) and can therefore allow certain optimizations. >> However, tlb_

Re: [RFC 01/20] mm/tlb: fix fullmm semantics

2021-01-30 Thread Andy Lutomirski
On Sat, Jan 30, 2021 at 4:16 PM Nadav Amit wrote: > > From: Nadav Amit > > fullmm in mmu_gather is supposed to indicate that the mm is torn-down > (e.g., on process exit) and can therefore allow certain optimizations. > However, tlb_finish_mmu() sets fullmm, when in fact it want to say that > the

[RFC 01/20] mm/tlb: fix fullmm semantics

2021-01-30 Thread Nadav Amit
From: Nadav Amit fullmm in mmu_gather is supposed to indicate that the mm is torn-down (e.g., on process exit) and can therefore allow certain optimizations. However, tlb_finish_mmu() sets fullmm, when in fact it want to say that the TLB should be fully flushed. Change tlb_finish_mmu() to set ne