Re: [PATCH v5 15/22] powerpc/mm: Avoid useless lock with single page fragments

From: Aneesh Kumar K.V
Date: Tue Sep 25 2018 - 22:44:06 EST


Christophe Leroy <christophe.leroy@xxxxxx> writes:

> There is no point in taking the page table lock as pte_frag or
> pmd_frag are always NULL when we have only one fragment.
>

Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxx>

> Signed-off-by: Christophe Leroy <christophe.leroy@xxxxxx>
> ---
> arch/powerpc/mm/pgtable-book3s64.c | 3 +++
> arch/powerpc/mm/pgtable-frag.c | 3 +++
> 2 files changed, 6 insertions(+)
>
> diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c
> index 723cd324fa34..c43e225e124d 100644
> --- a/arch/powerpc/mm/pgtable-book3s64.c
> +++ b/arch/powerpc/mm/pgtable-book3s64.c
> @@ -239,6 +239,9 @@ static pmd_t *get_pmd_from_cache(struct mm_struct *mm)
> {
> void *pmd_frag, *ret;
>
> + if (PMD_FRAG_NR == 1)
> + return NULL;
> +
> spin_lock(&mm->page_table_lock);
> ret = mm->context.pmd_frag;
> if (ret) {
> diff --git a/arch/powerpc/mm/pgtable-frag.c b/arch/powerpc/mm/pgtable-frag.c
> index d61e7c2a9a79..7544d0d7177d 100644
> --- a/arch/powerpc/mm/pgtable-frag.c
> +++ b/arch/powerpc/mm/pgtable-frag.c
> @@ -34,6 +34,9 @@ static pte_t *get_pte_from_cache(struct mm_struct *mm)
> {
> void *pte_frag, *ret;
>
> + if (PTE_FRAG_NR == 1)
> + return NULL;
> +
> spin_lock(&mm->page_table_lock);
> ret = mm->context.pte_frag;
> if (ret) {
> --
> 2.13.3