From: Shaohua Li Date: Mon, 16 Aug 2010 01:16:55 +0000 (+0800) Subject: x86, mm: Avoid unnecessary TLB flush X-Git-Tag: v2.6.37-rc1~203^2~16 X-Git-Url: https://git.openpandora.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=61c77326d1df079f202fa79403c3ccd8c5966a81;p=pandora-kernel.git x86, mm: Avoid unnecessary TLB flush In x86, access and dirty bits are set automatically by CPU when CPU accesses memory. When we go into the code path of below flush_tlb_fix_spurious_fault(), we already set dirty bit for pte and don't need flush tlb. This might mean tlb entry in some CPUs hasn't dirty bit set, but this doesn't matter. When the CPUs do page write, they will automatically check the bit and no software involved. On the other hand, flush tlb in below position is harmful. Test creates CPU number of threads, each thread writes to a same but random address in same vma range and we measure the total time. Under a 4 socket system, original time is 1.96s, while with the patch, the time is 0.8s. Under a 2 socket system, there is 20% time cut too. perf shows a lot of time are taking to send ipi/handle ipi for tlb flush. Signed-off-by: Shaohua Li LKML-Reference: <20100816011655.GA362@sli10-desk.sh.intel.com> Acked-by: Suresh Siddha Cc: Andrea Archangeli Signed-off-by: H. Peter Anvin --- diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index a34c785c5a63..2d0a33bd2971 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -603,6 +603,8 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, pte_update(mm, addr, ptep); } +#define flush_tlb_fix_spurious_fault(vma, address) + /* * clone_pgd_range(pgd_t *dst, pgd_t *src, int count); * diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index e2bd73e8f9c0..f4d4120e5128 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -129,6 +129,10 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres #define move_pte(pte, prot, old_addr, new_addr) (pte) #endif +#ifndef flush_tlb_fix_spurious_fault +#define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address) +#endif + #ifndef pgprot_noncached #define pgprot_noncached(prot) (prot) #endif diff --git a/mm/memory.c b/mm/memory.c index 2ed2267439df..a40da6983961 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3147,7 +3147,7 @@ static inline int handle_pte_fault(struct mm_struct *mm, * with threads. */ if (flags & FAULT_FLAG_WRITE) - flush_tlb_page(vma, address); + flush_tlb_fix_spurious_fault(vma, address); } unlock: pte_unmap_unlock(pte, ptl);