* Re: [External] [PATCH -fixes] riscv: Flush the tlb when a page directory is freed
2024-01-28 12:04 [PATCH -fixes] riscv: Flush the tlb when a page directory is freed Alexandre Ghiti
@ 2024-01-29 3:06 ` yunhui cui
2024-01-29 8:28 ` Alexandre Ghiti
2024-02-05 23:53 ` Charlie Jenkins
` (2 subsequent siblings)
3 siblings, 1 reply; 6+ messages in thread
From: yunhui cui @ 2024-01-29 3:06 UTC (permalink / raw)
To: Alexandre Ghiti
Cc: Will Deacon, Aneesh Kumar K . V, Andrew Morton, Nick Piggin,
Peter Zijlstra, Paul Walmsley, Palmer Dabbelt, Albert Ou,
Samuel Holland, Andrew Jones, linux-arch, linux-mm, linux-riscv,
linux-kernel
Hi Alexandre,
On Sun, Jan 28, 2024 at 8:04 PM Alexandre Ghiti <alexghiti@rivosinc.com> wrote:
>
> The riscv privileged specification mandates to flush the TLB whenever a
> page directory is modified, so add that to tlb_flush().
>
> Fixes: c5e9b2c2ae82 ("riscv: Improve tlb_flush()")
> Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
> ---
> arch/riscv/include/asm/tlb.h | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
> index 1eb5682b2af6..50b63b5c15bd 100644
> --- a/arch/riscv/include/asm/tlb.h
> +++ b/arch/riscv/include/asm/tlb.h
> @@ -16,7 +16,7 @@ static void tlb_flush(struct mmu_gather *tlb);
> static inline void tlb_flush(struct mmu_gather *tlb)
> {
> #ifdef CONFIG_MMU
> - if (tlb->fullmm || tlb->need_flush_all)
> + if (tlb->fullmm || tlb->need_flush_all || tlb->freed_tables)
> flush_tlb_mm(tlb->mm);
Why is it necessary to flush all TLB entries of the process?
Thanks,
Yunhui
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [External] [PATCH -fixes] riscv: Flush the tlb when a page directory is freed
2024-01-29 3:06 ` [External] " yunhui cui
@ 2024-01-29 8:28 ` Alexandre Ghiti
0 siblings, 0 replies; 6+ messages in thread
From: Alexandre Ghiti @ 2024-01-29 8:28 UTC (permalink / raw)
To: yunhui cui
Cc: Will Deacon, Aneesh Kumar K . V, Andrew Morton, Nick Piggin,
Peter Zijlstra, Paul Walmsley, Palmer Dabbelt, Albert Ou,
Samuel Holland, Andrew Jones, linux-arch, linux-mm, linux-riscv,
linux-kernel
Hi Yunhui,
On Mon, Jan 29, 2024 at 4:07 AM yunhui cui <cuiyunhui@bytedance.com> wrote:
>
> Hi Alexandre,
>
> On Sun, Jan 28, 2024 at 8:04 PM Alexandre Ghiti <alexghiti@rivosinc.com> wrote:
> >
> > The riscv privileged specification mandates to flush the TLB whenever a
> > page directory is modified, so add that to tlb_flush().
> >
> > Fixes: c5e9b2c2ae82 ("riscv: Improve tlb_flush()")
> > Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
> > ---
> > arch/riscv/include/asm/tlb.h | 2 +-
> > 1 file changed, 1 insertion(+), 1 deletion(-)
> >
> > diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
> > index 1eb5682b2af6..50b63b5c15bd 100644
> > --- a/arch/riscv/include/asm/tlb.h
> > +++ b/arch/riscv/include/asm/tlb.h
> > @@ -16,7 +16,7 @@ static void tlb_flush(struct mmu_gather *tlb);
> > static inline void tlb_flush(struct mmu_gather *tlb)
> > {
> > #ifdef CONFIG_MMU
> > - if (tlb->fullmm || tlb->need_flush_all)
> > + if (tlb->fullmm || tlb->need_flush_all || tlb->freed_tables)
> > flush_tlb_mm(tlb->mm);
>
> Why is it necessary to flush all TLB entries of the process?
That's quite heavy but that's the only to flush any "intermediate"
cache that would cache non-leaf PTEs, the specification mentions this:
"If software modifies a non-leaf PTE, it should execute SFENCE.VMA
with rs1=x0. If any PTE along the traversal path had its G bit set,
rs2 must be x0; otherwise, rs2 should be set to the ASID for which the
translation is being modified."
That was the behaviour before commit c5e9b2c2ae82 ("riscv: Improve
tlb_flush()").
>
> Thanks,
> Yunhui
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH -fixes] riscv: Flush the tlb when a page directory is freed
2024-01-28 12:04 [PATCH -fixes] riscv: Flush the tlb when a page directory is freed Alexandre Ghiti
2024-01-29 3:06 ` [External] " yunhui cui
@ 2024-02-05 23:53 ` Charlie Jenkins
2024-02-07 19:27 ` Samuel Holland
2024-02-08 1:30 ` patchwork-bot+linux-riscv
3 siblings, 0 replies; 6+ messages in thread
From: Charlie Jenkins @ 2024-02-05 23:53 UTC (permalink / raw)
To: Alexandre Ghiti
Cc: Will Deacon, Aneesh Kumar K . V, Andrew Morton, Nick Piggin,
Peter Zijlstra, Paul Walmsley, Palmer Dabbelt, Albert Ou,
Samuel Holland, Andrew Jones, linux-arch, linux-mm, linux-riscv,
linux-kernel
On Sun, Jan 28, 2024 at 01:04:05PM +0100, Alexandre Ghiti wrote:
> The riscv privileged specification mandates to flush the TLB whenever a
> page directory is modified, so add that to tlb_flush().
>
> Fixes: c5e9b2c2ae82 ("riscv: Improve tlb_flush()")
> Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
> ---
> arch/riscv/include/asm/tlb.h | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
> index 1eb5682b2af6..50b63b5c15bd 100644
> --- a/arch/riscv/include/asm/tlb.h
> +++ b/arch/riscv/include/asm/tlb.h
> @@ -16,7 +16,7 @@ static void tlb_flush(struct mmu_gather *tlb);
> static inline void tlb_flush(struct mmu_gather *tlb)
> {
> #ifdef CONFIG_MMU
> - if (tlb->fullmm || tlb->need_flush_all)
> + if (tlb->fullmm || tlb->need_flush_all || tlb->freed_tables)
> flush_tlb_mm(tlb->mm);
> else
> flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end,
> --
> 2.39.2
>
>
> _______________________________________________
> linux-riscv mailing list
> linux-riscv@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-riscv
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [PATCH -fixes] riscv: Flush the tlb when a page directory is freed
2024-01-28 12:04 [PATCH -fixes] riscv: Flush the tlb when a page directory is freed Alexandre Ghiti
2024-01-29 3:06 ` [External] " yunhui cui
2024-02-05 23:53 ` Charlie Jenkins
@ 2024-02-07 19:27 ` Samuel Holland
2024-02-08 1:30 ` patchwork-bot+linux-riscv
3 siblings, 0 replies; 6+ messages in thread
From: Samuel Holland @ 2024-02-07 19:27 UTC (permalink / raw)
To: Alexandre Ghiti
Cc: Will Deacon, Aneesh Kumar K . V, Andrew Morton, Nick Piggin,
Peter Zijlstra, Paul Walmsley, Palmer Dabbelt, Albert Ou,
Andrew Jones, linux-arch, linux-mm, linux-riscv, linux-kernel
On 2024-01-28 6:04 AM, Alexandre Ghiti wrote:
> The riscv privileged specification mandates to flush the TLB whenever a
> page directory is modified, so add that to tlb_flush().
>
> Fixes: c5e9b2c2ae82 ("riscv: Improve tlb_flush()")
> Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
> ---
> arch/riscv/include/asm/tlb.h | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
Reviewed-by: Samuel Holland <samuel.holland@sifive.com>
Tested-by: Samuel Holland <samuel.holland@sifive.com>
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [PATCH -fixes] riscv: Flush the tlb when a page directory is freed
2024-01-28 12:04 [PATCH -fixes] riscv: Flush the tlb when a page directory is freed Alexandre Ghiti
` (2 preceding siblings ...)
2024-02-07 19:27 ` Samuel Holland
@ 2024-02-08 1:30 ` patchwork-bot+linux-riscv
3 siblings, 0 replies; 6+ messages in thread
From: patchwork-bot+linux-riscv @ 2024-02-08 1:30 UTC (permalink / raw)
To: Alexandre Ghiti
Cc: linux-riscv, will, aneesh.kumar, akpm, npiggin, peterz,
paul.walmsley, palmer, aou, samuel.holland, ajones, linux-arch,
linux-mm, linux-kernel
Hello:
This patch was applied to riscv/linux.git (fixes)
by Palmer Dabbelt <palmer@rivosinc.com>:
On Sun, 28 Jan 2024 13:04:05 +0100 you wrote:
> The riscv privileged specification mandates to flush the TLB whenever a
> page directory is modified, so add that to tlb_flush().
>
> Fixes: c5e9b2c2ae82 ("riscv: Improve tlb_flush()")
> Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
> ---
> arch/riscv/include/asm/tlb.h | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
Here is the summary with links:
- [-fixes] riscv: Flush the tlb when a page directory is freed
https://git.kernel.org/riscv/c/97cf301fa42e
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
^ permalink raw reply [flat|nested] 6+ messages in thread