mbox series

[0/2] riscv: asid: switch to alternative way to fix stale TLB entries

Message ID 20230226150137.1919750-1-geomatsi@gmail.com (mailing list archive)
Headers show
Series riscv: asid: switch to alternative way to fix stale TLB entries | expand

Message

Sergey Matyukevich Feb. 26, 2023, 3:01 p.m. UTC 
Hi all,

Some time ago two different patches have been posted to fix stale TLB
entries that caused applications crashes.

The patch [0] suggested 'aggregating' mm_cpumask, i.e. current cpu is not
cleared for the switched-out task in switch_mm function. For additional
explanations see the commit message by Guo Ren. The same approach is
used by arc architecture, so another good comment is for switch_mm
in arch/arc/include/asm/mmu_context.h.

The patch [1] attempted to reduce the number of TLB flushes by deferring
(and possibly avoiding) them for CPUs not running the task.

Patch [1] has been merged. However we already have two bug reports from
different vendors. So apparently something is missing in the approach
suggested in [1]. In both cases the patch [0] fixed the issue.

This patch series reverts [1] and replaces it by [0].

Regards,
Sergey

[0] https://lore.kernel.org/linux-riscv/20221111075902.798571-1-guoren@kernel.org/
[1] https://lore.kernel.org/linux-riscv/20220829205219.283543-1-geomatsi@gmail.com/


Guo Ren (1):
  riscv: asid: Fixup stale TLB entry cause application crash

Sergey Matyukevich (1):
  Revert "riscv: mm: notify remote harts about mmu cache updates"

 arch/riscv/include/asm/mmu.h      |  2 --
 arch/riscv/include/asm/tlbflush.h | 18 --------------
 arch/riscv/mm/context.c           | 40 +++++++++++++++----------------
 arch/riscv/mm/tlbflush.c          | 28 +++++++++++++---------
 4 files changed, 37 insertions(+), 51 deletions(-)

Comments

patchwork-bot+linux-riscv@kernel.org March 10, 2023, 2:30 a.m. UTC | #1 
Hello:

This series was applied to riscv/linux.git (fixes)
by Palmer Dabbelt <palmer@rivosinc.com>:

On Sun, 26 Feb 2023 18:01:35 +0300 you wrote:
> Hi all,
> 
> Some time ago two different patches have been posted to fix stale TLB
> entries that caused applications crashes.
> 
> The patch [0] suggested 'aggregating' mm_cpumask, i.e. current cpu is not
> cleared for the switched-out task in switch_mm function. For additional
> explanations see the commit message by Guo Ren. The same approach is
> used by arc architecture, so another good comment is for switch_mm
> in arch/arc/include/asm/mmu_context.h.
> 
> [...]

Here is the summary with links:
  - [1/2] Revert "riscv: mm: notify remote harts about mmu cache updates"
    https://git.kernel.org/riscv/c/e921050022f1
  - [2/2] riscv: asid: Fixup stale TLB entry cause application crash
    https://git.kernel.org/riscv/c/82dd33fde026

You are awesome, thank you!