From 1a44e149084d772a1bcf4cdbdde8a013a8a1cfde Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Sat, 29 Oct 2005 18:16:48 -0700 Subject: [PATCH] [PATCH] .text page fault SMP scalability optimization We had a problem on ppc64 where with more than 4 threads a large system wouldn't scale well while faulting in the .text (most of the time was spent in the kernel despite it was an userland compute intensive app). The reason is the useless overwrite of the same pte from all cpu. I fixed it this way (verified on an older kernel but the forward port is almost identical). This will benefit all archs not just ppc64. Signed-off-by: Andrea Arcangeli Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index d68421dd64..0f60baf6f6 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1980,9 +1980,10 @@ static inline int handle_pte_fault(struct mm_struct *mm, pte_t *pte, pmd_t *pmd, int write_access) { pte_t entry; + pte_t old_entry; spinlock_t *ptl; - entry = *pte; + old_entry = entry = *pte; if (!pte_present(entry)) { if (pte_none(entry)) { if (!vma->vm_ops || !vma->vm_ops->nopage) @@ -2009,9 +2010,20 @@ static inline int handle_pte_fault(struct mm_struct *mm, entry = pte_mkdirty(entry); } entry = pte_mkyoung(entry); - ptep_set_access_flags(vma, address, pte, entry, write_access); - update_mmu_cache(vma, address, entry); - lazy_mmu_prot_update(entry); + if (!pte_same(old_entry, entry)) { + ptep_set_access_flags(vma, address, pte, entry, write_access); + update_mmu_cache(vma, address, entry); + lazy_mmu_prot_update(entry); + } else { + /* + * This is needed only for protection faults but the arch code + * is not yet telling us if this is a protection fault or not. + * This still avoids useless tlb flushes for .text page faults + * with threads. + */ + if (write_access) + flush_tlb_page(vma, address); + } unlock: pte_unmap_unlock(pte, ptl); return VM_FAULT_MINOR; -- 2.39.5