From 7df676974359f927056b882e10a5b24d2033169b Mon Sep 17 00:00:00 2001 From: Bibo Mao Date: Wed, 27 May 2020 10:25:18 +0800 Subject: mm/memory.c: Update local TLB if PTE entry exists If two threads concurrently fault at the same page, the thread that won the race updates the PTE and its local TLB. For now, the other thread gives up, simply does nothing, and continues. It could happen that this second thread triggers another fault, whereby it only updates its local TLB while handling the fault. Instead of triggering another fault, let's directly update the local TLB of the second thread. Function update_mmu_tlb is used here to update local TLB on the second thread, and it is defined as empty on other arches. Signed-off-by: Bibo Mao Acked-by: Andrew Morton Signed-off-by: Thomas Bogendoerfer --- mm/memory.c | 27 +++++++++++++++++++-------- 1 file changed, 19 insertions(+), 8 deletions(-) (limited to 'mm/memory.c') diff --git a/mm/memory.c b/mm/memory.c index f703fe8c8346..8bb31c4d94d0 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2436,10 +2436,9 @@ static inline bool cow_user_page(struct page *dst, struct page *src, if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { /* * Other thread has already handled the fault - * and we don't need to do anything. If it's - * not the case, the fault will be triggered - * again on the same address. + * and update local tlb only */ + update_mmu_tlb(vma, addr, vmf->pte); ret = false; goto pte_unlock; } @@ -2463,7 +2462,8 @@ static inline bool cow_user_page(struct page *dst, struct page *src, vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); locked = true; if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { - /* The PTE changed under us. Retry page fault. */ + /* The PTE changed under us, update local tlb */ + update_mmu_tlb(vma, addr, vmf->pte); ret = false; goto pte_unlock; } @@ -2752,6 +2752,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) new_page = old_page; page_copied = 1; } else { + update_mmu_tlb(vma, vmf->address, vmf->pte); mem_cgroup_cancel_charge(new_page, memcg, false); } @@ -2812,6 +2813,7 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf) * pte_offset_map_lock. */ if (!pte_same(*vmf->pte, vmf->orig_pte)) { + update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); return VM_FAULT_NOPAGE; } @@ -2936,6 +2938,7 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!pte_same(*vmf->pte, vmf->orig_pte)) { + update_mmu_tlb(vma, vmf->address, vmf->pte); unlock_page(vmf->page); pte_unmap_unlock(vmf->pte, vmf->ptl); put_page(vmf->page); @@ -3341,8 +3344,10 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) vma->vm_page_prot)); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); - if (!pte_none(*vmf->pte)) + if (!pte_none(*vmf->pte)) { + update_mmu_tlb(vma, vmf->address, vmf->pte); goto unlock; + } ret = check_stable_address_space(vma->vm_mm); if (ret) goto unlock; @@ -3378,8 +3383,10 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); - if (!pte_none(*vmf->pte)) + if (!pte_none(*vmf->pte)) { + update_mmu_cache(vma, vmf->address, vmf->pte); goto release; + } ret = check_stable_address_space(vma->vm_mm); if (ret) @@ -3646,8 +3653,10 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, } /* Re-check under ptl */ - if (unlikely(!pte_none(*vmf->pte))) + if (unlikely(!pte_none(*vmf->pte))) { + update_mmu_tlb(vma, vmf->address, vmf->pte); return VM_FAULT_NOPAGE; + } flush_icache_page(vma, page); entry = mk_pte(page, vma->vm_page_prot); @@ -4224,8 +4233,10 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd); spin_lock(vmf->ptl); entry = vmf->orig_pte; - if (unlikely(!pte_same(*vmf->pte, entry))) + if (unlikely(!pte_same(*vmf->pte, entry))) { + update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); goto unlock; + } if (vmf->flags & FAULT_FLAG_WRITE) { if (!pte_write(entry)) return do_wp_page(vmf); -- cgit v1.2.3 From 44bf431b47b4298d8aaba7b02d0ad29fc609a03c Mon Sep 17 00:00:00 2001 From: Bibo Mao Date: Wed, 27 May 2020 10:25:19 +0800 Subject: mm/memory.c: Add memory read privilege on page fault handling Here add pte_sw_mkyoung function to make page readable on MIPS platform during page fault handling. This patch improves page fault latency about 10% on my MIPS machine with lmbench lat_pagefault case. It is noop function on other arches, there is no negative influence on those architectures. Signed-off-by: Bibo Mao Acked-by: Andrew Morton Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/pgtable.h | 2 ++ include/asm-generic/pgtable.h | 16 ++++++++++++++++ mm/memory.c | 3 +++ 3 files changed, 21 insertions(+) (limited to 'mm/memory.c') diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 6f40612b3152..d9772aff2f02 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -414,6 +414,8 @@ static inline pte_t pte_mkyoung(pte_t pte) return pte; } +#define pte_sw_mkyoung pte_mkyoung + #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT static inline int pte_huge(pte_t pte) { return pte_val(pte) & _PAGE_HUGE; } diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index fa5c73ff8226..b5278ec627db 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -244,6 +244,22 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres } #endif +/* + * On some architectures hardware does not set page access bit when accessing + * memory page, it is responsibilty of software setting this bit. It brings + * out extra page fault penalty to track page access bit. For optimization page + * access bit can be set during all page fault flow on these arches. + * To be differentiate with macro pte_mkyoung, this macro is used on platforms + * where software maintains page access bit. + */ +#ifndef pte_sw_mkyoung +static inline pte_t pte_sw_mkyoung(pte_t pte) +{ + return pte; +} +#define pte_sw_mkyoung pte_sw_mkyoung +#endif + #ifndef pte_savedwrite #define pte_savedwrite pte_write #endif diff --git a/mm/memory.c b/mm/memory.c index 8bb31c4d94d0..c7c8960bdd1e 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2704,6 +2704,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) } flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = mk_pte(new_page, vma->vm_page_prot); + entry = pte_sw_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); /* * Clear the pte entry and flush it first, before updating the @@ -3378,6 +3379,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) __SetPageUptodate(page); entry = mk_pte(page, vma->vm_page_prot); + entry = pte_sw_mkyoung(entry); if (vma->vm_flags & VM_WRITE) entry = pte_mkwrite(pte_mkdirty(entry)); @@ -3660,6 +3662,7 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, flush_icache_page(vma, page); entry = mk_pte(page, vma->vm_page_prot); + entry = pte_sw_mkyoung(entry); if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); /* copy-on-write page */ -- cgit v1.2.3