| Message ID | 20240202080756.1453939-25-ryan.roberts@arm.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | Transparent Contiguous PTEs for User Mappings | expand |
On Fri, Feb 02, 2024 at 08:07:55AM +0000, Ryan Roberts wrote: > As set_ptes() and wrprotect_ptes() become a bit more complex, the > compiler may choose not to inline them. But this is critical for fork() > performance. So mark the functions, along with contpte_try_unfold() > which is called by them, as __always_inline. This is worth ~1% on the > fork() microbenchmark with order-0 folios (the common case). > > Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> I have no strong feelings either way on this, so: Acked-by: Mark Rutland <mark.rutland@arm.com> Mark. > --- > arch/arm64/include/asm/pgtable.h | 10 +++++----- > 1 file changed, 5 insertions(+), 5 deletions(-) > > diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h > index 353ea67b5d75..cdc310880a3b 100644 > --- a/arch/arm64/include/asm/pgtable.h > +++ b/arch/arm64/include/asm/pgtable.h > @@ -1213,8 +1213,8 @@ extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma, > unsigned long addr, pte_t *ptep, > pte_t entry, int dirty); > > -static inline void contpte_try_unfold(struct mm_struct *mm, unsigned long addr, > - pte_t *ptep, pte_t pte) > +static __always_inline void contpte_try_unfold(struct mm_struct *mm, > + unsigned long addr, pte_t *ptep, pte_t pte) > { > if (unlikely(pte_valid_cont(pte))) > __contpte_try_unfold(mm, addr, ptep, pte); > @@ -1279,7 +1279,7 @@ static inline void set_pte(pte_t *ptep, pte_t pte) > } > > #define set_ptes set_ptes > -static inline void set_ptes(struct mm_struct *mm, unsigned long addr, > +static __always_inline void set_ptes(struct mm_struct *mm, unsigned long addr, > pte_t *ptep, pte_t pte, unsigned int nr) > { > pte = pte_mknoncont(pte); > @@ -1361,8 +1361,8 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, > } > > #define wrprotect_ptes wrprotect_ptes > -static inline void wrprotect_ptes(struct mm_struct *mm, unsigned long addr, > - pte_t *ptep, unsigned int nr) > +static __always_inline void wrprotect_ptes(struct mm_struct *mm, > + unsigned long addr, pte_t *ptep, unsigned int nr) > { > if (likely(nr == 1)) { > /* > -- > 2.25.1 >
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 353ea67b5d75..cdc310880a3b 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -1213,8 +1213,8 @@ extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t entry, int dirty); -static inline void contpte_try_unfold(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) +static __always_inline void contpte_try_unfold(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, pte_t pte) { if (unlikely(pte_valid_cont(pte))) __contpte_try_unfold(mm, addr, ptep, pte); @@ -1279,7 +1279,7 @@ static inline void set_pte(pte_t *ptep, pte_t pte) } #define set_ptes set_ptes -static inline void set_ptes(struct mm_struct *mm, unsigned long addr, +static __always_inline void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned int nr) { pte = pte_mknoncont(pte); @@ -1361,8 +1361,8 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, } #define wrprotect_ptes wrprotect_ptes -static inline void wrprotect_ptes(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, unsigned int nr) +static __always_inline void wrprotect_ptes(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, unsigned int nr) { if (likely(nr == 1)) { /*
As set_ptes() and wrprotect_ptes() become a bit more complex, the compiler may choose not to inline them. But this is critical for fork() performance. So mark the functions, along with contpte_try_unfold() which is called by them, as __always_inline. This is worth ~1% on the fork() microbenchmark with order-0 folios (the common case). Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> --- arch/arm64/include/asm/pgtable.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)