[PATCH 20/19] ARM: LPAE: Invalidate the TLB before freeing the PMD

Sergei Shtylyov sshtylyov at mvista.com
Wed May 11 06:31:47 EDT 2011


Hello.

On 11-05-2011 14:23, Catalin Marinas wrote:

> Similar to the PTE freeing, this patch introduced __pmd_free_tlb() which
> invalidates the TLB before freeing a PMD page. This is needed because on
> newer processors the entry in the upper page table may be cached by the
> TLB and point to random data after the PMD has been freed.

> Signed-off-by: Catalin Marinas<catalin.marinas at arm.com>
> ---

> This patch should be part of the LPAE series but I haven't included it in the
> latest series post.

>   arch/arm/include/asm/tlb.h |   12 +++++++++++-
>   1 files changed, 11 insertions(+), 1 deletions(-)

> diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
> index f9f6ecd..ef72f19 100644
> --- a/arch/arm/include/asm/tlb.h
> +++ b/arch/arm/include/asm/tlb.h
> @@ -181,8 +181,18 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
>   	tlb_remove_page(tlb, pte);
>   }
>
> +static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
> +				  unsigned long addr)
> +{
> +#ifdef CONFIG_ARM_LPAE
> +	tlb_add_flush(tlb, addr);
> +	tlb_flush(tlb);
> +	pmd_free((tlb)->mm, pmdp);

    This is not a macro, so parens around 'tlb' are not needed.

> +#endif
> +}
> +

    Perhaps a better style would be (as SubmittingPatches suggest):

+#ifdef CONFIG_ARM_LPAE
+static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
+				  unsigned long addr)
+{
+	tlb_add_flush(tlb, addr);
+	tlb_flush(tlb);
+	pmd_free(tlb->mm, pmdp);
+}
+#else
+static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
+				  unsigned long addr) {}
+#endif
+

WBR, Sergei



More information about the linux-arm-kernel mailing list