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 <ryan.roberts@arm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Barry Song <21cnbao@gmail.com>
Cc: Borislav Petkov (AMD) <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Morse <james.morse@arm.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index d759a20d2929ab60875672b646c2fc1deaf7809f..8310875133ffc54f60750081ae2abe864825af07 100644 (file)
--- 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)) {
                /*