From b972fc6afba002319fe23bc698ce6431ee43868c Mon Sep 17 00:00:00 2001 From: Ryan Roberts Date: Thu, 15 Feb 2024 10:32:04 +0000 Subject: [PATCH] arm64/mm: __always_inline to improve fork() perf 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). Link: https://lkml.kernel.org/r/20240215103205.2607016-18-ryan.roberts@arm.com Signed-off-by: Ryan Roberts Acked-by: Mark Rutland Acked-by: Catalin Marinas Cc: Alistair Popple Cc: Andrey Ryabinin Cc: Ard Biesheuvel Cc: Barry Song <21cnbao@gmail.com> Cc: Borislav Petkov (AMD) Cc: Dave Hansen Cc: David Hildenbrand Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: James Morse Cc: John Hubbard Cc: Kefeng Wang Cc: Marc Zyngier Cc: Matthew Wilcox (Oracle) Cc: Thomas Gleixner Cc: Will Deacon Cc: Yang Shi Cc: Zi Yan Signed-off-by: Andrew Morton --- 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 d759a20d2929..8310875133ff 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -1206,8 +1206,8 @@ 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); @@ -1278,7 +1278,7 @@ 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); @@ -1360,8 +1360,8 @@ 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