From 142dd975911fdd82b1b6f6617cd20ac90a8ccf00 Mon Sep 17 00:00:00 2001 From: Zachary Amsden Date: Wed, 2 May 2007 19:27:19 +0200 Subject: [PATCH] i386: pte xchg optimization In situations where page table updates need only be made locally, and there is no cross-processor A/D bit races involved, we need not use the heavyweight xchg instruction to atomically fetch and clear page table entries. Instead, we can just read and clear them directly. This introduces a neat optimization for non-SMP kernels; drop the atomic xchg operations from page table updates. Thanks to Michel Lespinasse for noting this potential optimization. Signed-off-by: Zachary Amsden Signed-off-by: Andrew Morton Signed-off-by: Andi Kleen --- include/asm-i386/pgtable-2level.h | 14 ++++++++++++++ include/asm-i386/pgtable-3level.h | 14 ++++++++++++++ 2 files changed, 28 insertions(+) diff --git a/include/asm-i386/pgtable-2level.h b/include/asm-i386/pgtable-2level.h index 85d9005c0cdf..3daab67cd366 100644 --- a/include/asm-i386/pgtable-2level.h +++ b/include/asm-i386/pgtable-2level.h @@ -41,10 +41,24 @@ static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, pt *xp = __pte(0); } +/* local pte updates need not use xchg for locking */ +static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep) +{ + pte_t res; + + res = *ptep; + native_pte_clear(NULL, 0, ptep); + return res; +} + +#ifdef CONFIG_SMP static inline pte_t native_ptep_get_and_clear(pte_t *xp) { return __pte(xchg(&xp->pte_low, 0)); } +#else +#define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp) +#endif #define pte_page(x) pfn_to_page(pte_pfn(x)) #define pte_none(x) (!(x).pte_low) diff --git a/include/asm-i386/pgtable-3level.h b/include/asm-i386/pgtable-3level.h index 664bfee5a2f2..45b024181507 100644 --- a/include/asm-i386/pgtable-3level.h +++ b/include/asm-i386/pgtable-3level.h @@ -139,6 +139,17 @@ static inline void pud_clear (pud_t * pud) { } #define pmd_offset(pud, address) ((pmd_t *) pud_page(*(pud)) + \ pmd_index(address)) +/* local pte updates need not use xchg for locking */ +static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep) +{ + pte_t res; + + res = *ptep; + native_pte_clear(NULL, 0, ptep); + return res; +} + +#ifdef CONFIG_SMP static inline pte_t native_ptep_get_and_clear(pte_t *ptep) { pte_t res; @@ -150,6 +161,9 @@ static inline pte_t native_ptep_get_and_clear(pte_t *ptep) return res; } +#else +#define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp) +#endif #define __HAVE_ARCH_PTE_SAME static inline int pte_same(pte_t a, pte_t b) -- cgit v1.2.1