* [PATCH] arm64: mm: Fix the break-before-make flush range for erratum 2645198
@ 2026-09-23 14:36 Andrea Parri
2026-09-24 4:45 ` Dev Jain
` (2 more replies)
0 siblings, 3 replies; 4+ messages in thread
From: Andrea Parri @ 2026-09-23 14:36 UTC (permalink / raw)
To: Catalin Marinas, Will Deacon
Cc: Andrea Parri, Mark Rutland, Ryan Roberts, Ard Biesheuvel,
Kevin Brodsky, Anshuman Khandual, Andrew Morton, Dev Jain,
linux-arm-kernel, linux-kernel, stable
modify_prot_start_ptes() performs the break-before-make TLB invalidation
required by erratum 2645198 with __flush_tlb_range(), whose third
argument is the end address of the range. It passes nr * PAGE_SIZE
instead of addr + nr * PAGE_SIZE, so __do_flush_tlb_range() computes the
page count as (nr * PAGE_SIZE - addr) >> PAGE_SHIFT.
For addr > nr * PAGE_SIZE that subtraction underflows, the page count
exceeds the batching limit and the flush degenerates to flush_tlb_mm(),
so a single-page mprotect broadcasts an ASID-wide invalidation and a
full-range mmu notifier call.
For addr <= nr * PAGE_SIZE only [addr, nr * PAGE_SIZE) is invalidated,
and when the cleared batch starts below nr * PAGE_SIZE the tail is left
in the TLB. The workaround then no longer covers the whole batch, and
for addr == nr * PAGE_SIZE the flush is empty.
On affected Cortex-A715 CPUs, this can corrupt ESR_ELx and FAR_ELx on the
next instruction abort caused by a permission fault.
Pass addr + nr * PAGE_SIZE as the end address.
Fixes: 7efa1cd5f89b5 ("arm64: add batched versions of ptep_modify_prot_start/commit")
Cc: stable@vger.kernel.org
Assisted-by: LLM
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
---
arch/arm64/mm/mmu.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 79d90226fd5dc..d4384131e10d8 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -2295,7 +2295,7 @@ pte_t modify_prot_start_ptes(struct vm_area_struct *vma, unsigned long addr,
* in cases where cpu is affected with errata #2645198.
*/
if (pte_accessible(vma->vm_mm, pte) && pte_user_exec(pte))
- __flush_tlb_range(vma, addr, nr * PAGE_SIZE,
+ __flush_tlb_range(vma, addr, addr + nr * PAGE_SIZE,
PAGE_SIZE, 3, TLBF_NOWALKCACHE);
}
--
2.53.0
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] arm64: mm: Fix the break-before-make flush range for erratum 2645198
2026-09-23 14:36 [PATCH] arm64: mm: Fix the break-before-make flush range for erratum 2645198 Andrea Parri
@ 2026-09-24 4:45 ` Dev Jain
2026-09-24 9:41 ` Catalin Marinas
2026-09-24 10:31 ` Will Deacon
2 siblings, 0 replies; 4+ messages in thread
From: Dev Jain @ 2026-09-24 4:45 UTC (permalink / raw)
To: Andrea Parri, Catalin Marinas, Will Deacon
Cc: Mark Rutland, Ryan Roberts, Ard Biesheuvel, Kevin Brodsky,
Anshuman Khandual, Andrew Morton, linux-arm-kernel, linux-kernel,
stable
On 23/09/26 8:06 pm, Andrea Parri wrote:
> modify_prot_start_ptes() performs the break-before-make TLB invalidation
> required by erratum 2645198 with __flush_tlb_range(), whose third
> argument is the end address of the range. It passes nr * PAGE_SIZE
> instead of addr + nr * PAGE_SIZE, so __do_flush_tlb_range() computes the
> page count as (nr * PAGE_SIZE - addr) >> PAGE_SHIFT.
>
> For addr > nr * PAGE_SIZE that subtraction underflows, the page count
> exceeds the batching limit and the flush degenerates to flush_tlb_mm(),
> so a single-page mprotect broadcasts an ASID-wide invalidation and a
> full-range mmu notifier call.
>
> For addr <= nr * PAGE_SIZE only [addr, nr * PAGE_SIZE) is invalidated,
> and when the cleared batch starts below nr * PAGE_SIZE the tail is left
> in the TLB. The workaround then no longer covers the whole batch, and
> for addr == nr * PAGE_SIZE the flush is empty.
>
> On affected Cortex-A715 CPUs, this can corrupt ESR_ELx and FAR_ELx on the
> next instruction abort caused by a permission fault.
>
> Pass addr + nr * PAGE_SIZE as the end address.
>
> Fixes: 7efa1cd5f89b5 ("arm64: add batched versions of ptep_modify_prot_start/commit")
> Cc: stable@vger.kernel.org
> Assisted-by: LLM
> Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
> ---
Thanks, such typos should be filtered out by LLMs nowadays : )
Reviewed-by: Dev Jain <dev.jain@arm.com>
> arch/arm64/mm/mmu.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
> index 79d90226fd5dc..d4384131e10d8 100644
> --- a/arch/arm64/mm/mmu.c
> +++ b/arch/arm64/mm/mmu.c
> @@ -2295,7 +2295,7 @@ pte_t modify_prot_start_ptes(struct vm_area_struct *vma, unsigned long addr,
> * in cases where cpu is affected with errata #2645198.
> */
> if (pte_accessible(vma->vm_mm, pte) && pte_user_exec(pte))
> - __flush_tlb_range(vma, addr, nr * PAGE_SIZE,
> + __flush_tlb_range(vma, addr, addr + nr * PAGE_SIZE,
> PAGE_SIZE, 3, TLBF_NOWALKCACHE);
> }
>
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] arm64: mm: Fix the break-before-make flush range for erratum 2645198
2026-09-23 14:36 [PATCH] arm64: mm: Fix the break-before-make flush range for erratum 2645198 Andrea Parri
2026-09-24 4:45 ` Dev Jain
@ 2026-09-24 9:41 ` Catalin Marinas
2026-09-24 10:31 ` Will Deacon
2 siblings, 0 replies; 4+ messages in thread
From: Catalin Marinas @ 2026-09-24 9:41 UTC (permalink / raw)
To: Andrea Parri
Cc: Will Deacon, Mark Rutland, Ryan Roberts, Ard Biesheuvel,
Kevin Brodsky, Anshuman Khandual, Andrew Morton, Dev Jain,
linux-arm-kernel, linux-kernel, stable
On Wed, Sep 23, 2026 at 04:36:32PM +0200, Andrea Parri wrote:
> modify_prot_start_ptes() performs the break-before-make TLB invalidation
> required by erratum 2645198 with __flush_tlb_range(), whose third
> argument is the end address of the range. It passes nr * PAGE_SIZE
> instead of addr + nr * PAGE_SIZE, so __do_flush_tlb_range() computes the
> page count as (nr * PAGE_SIZE - addr) >> PAGE_SHIFT.
>
> For addr > nr * PAGE_SIZE that subtraction underflows, the page count
> exceeds the batching limit and the flush degenerates to flush_tlb_mm(),
> so a single-page mprotect broadcasts an ASID-wide invalidation and a
> full-range mmu notifier call.
>
> For addr <= nr * PAGE_SIZE only [addr, nr * PAGE_SIZE) is invalidated,
> and when the cleared batch starts below nr * PAGE_SIZE the tail is left
> in the TLB. The workaround then no longer covers the whole batch, and
> for addr == nr * PAGE_SIZE the flush is empty.
>
> On affected Cortex-A715 CPUs, this can corrupt ESR_ELx and FAR_ELx on the
> next instruction abort caused by a permission fault.
>
> Pass addr + nr * PAGE_SIZE as the end address.
>
> Fixes: 7efa1cd5f89b5 ("arm64: add batched versions of ptep_modify_prot_start/commit")
> Cc: stable@vger.kernel.org
> Assisted-by: LLM
> Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
> ---
> arch/arm64/mm/mmu.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
> index 79d90226fd5dc..d4384131e10d8 100644
> --- a/arch/arm64/mm/mmu.c
> +++ b/arch/arm64/mm/mmu.c
> @@ -2295,7 +2295,7 @@ pte_t modify_prot_start_ptes(struct vm_area_struct *vma, unsigned long addr,
> * in cases where cpu is affected with errata #2645198.
> */
> if (pte_accessible(vma->vm_mm, pte) && pte_user_exec(pte))
> - __flush_tlb_range(vma, addr, nr * PAGE_SIZE,
> + __flush_tlb_range(vma, addr, addr + nr * PAGE_SIZE,
> PAGE_SIZE, 3, TLBF_NOWALKCACHE);
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] arm64: mm: Fix the break-before-make flush range for erratum 2645198
2026-09-23 14:36 [PATCH] arm64: mm: Fix the break-before-make flush range for erratum 2645198 Andrea Parri
2026-09-24 4:45 ` Dev Jain
2026-09-24 9:41 ` Catalin Marinas
@ 2026-09-24 10:31 ` Will Deacon
2 siblings, 0 replies; 4+ messages in thread
From: Will Deacon @ 2026-09-24 10:31 UTC (permalink / raw)
To: Catalin Marinas, Andrea Parri
Cc: mark.rutland, kernel-team, Will Deacon, Ryan Roberts,
Ard Biesheuvel, Kevin Brodsky, Anshuman Khandual, Andrew Morton,
Dev Jain, linux-arm-kernel, linux-kernel, stable
On Wed, 23 Sep 2026 16:36:32 +0200, Andrea Parri wrote:
> modify_prot_start_ptes() performs the break-before-make TLB invalidation
> required by erratum 2645198 with __flush_tlb_range(), whose third
> argument is the end address of the range. It passes nr * PAGE_SIZE
> instead of addr + nr * PAGE_SIZE, so __do_flush_tlb_range() computes the
> page count as (nr * PAGE_SIZE - addr) >> PAGE_SHIFT.
>
> For addr > nr * PAGE_SIZE that subtraction underflows, the page count
> exceeds the batching limit and the flush degenerates to flush_tlb_mm(),
> so a single-page mprotect broadcasts an ASID-wide invalidation and a
> full-range mmu notifier call.
>
> [...]
Applied to arm64 (for-next/fixes), thanks!
[1/1] arm64: mm: Fix the break-before-make flush range for erratum 2645198
https://git.kernel.org/arm64/c/1fef81669147
Cheers,
--
Will
https://fixes.arm64.dev
https://next.arm64.dev
https://will.arm64.dev
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2026-09-24 10:31 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2026-09-23 14:36 [PATCH] arm64: mm: Fix the break-before-make flush range for erratum 2645198 Andrea Parri
2026-09-24 4:45 ` Dev Jain
2026-09-24 9:41 ` Catalin Marinas
2026-09-24 10:31 ` Will Deacon
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®