[PATCH v4 2/4] mm/memory.c: Update local TLB if PTE entry exists
From: Bibo Mao
Date: Tue May 19 2020 - 06:04:05 EST
If two threads concurrently fault at the same address, 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.
It is only useful to architectures where software can update TLB, it may
bring out some negative effect if update_mmu_cache is used for other
purpose also. It seldom happens where multiple threads access the same
page at the same time, so the negative effect is limited on other arches.
Signed-off-by: Bibo Mao <maobibo@xxxxxxxxxxx>
---
mm/memory.c | 44 +++++++++++++++++++++++++++-----------------
1 file changed, 27 insertions(+), 17 deletions(-)
diff --git a/mm/memory.c b/mm/memory.c
index f703fe8..2eb59a9 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1770,8 +1770,8 @@ static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr,
}
entry = pte_mkyoung(*pte);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
- if (ptep_set_access_flags(vma, addr, pte, entry, 1))
- update_mmu_cache(vma, addr, pte);
+ ptep_set_access_flags(vma, addr, pte, entry, 1);
+ update_mmu_cache(vma, addr, pte);
}
goto out_unlock;
}
@@ -2436,17 +2436,16 @@ 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_cache(vma, addr, vmf->pte);
ret = false;
goto pte_unlock;
}
entry = pte_mkyoung(vmf->orig_pte);
- if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0))
- update_mmu_cache(vma, addr, vmf->pte);
+ ptep_set_access_flags(vma, addr, vmf->pte, entry, 0);
+ update_mmu_cache(vma, addr, vmf->pte);
}
/*
@@ -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_cache(vma, addr, vmf->pte);
ret = false;
goto pte_unlock;
}
@@ -2618,8 +2618,8 @@ static inline void wp_page_reuse(struct vm_fault *vmf)
flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
entry = pte_mkyoung(vmf->orig_pte);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
- if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1))
- update_mmu_cache(vma, vmf->address, vmf->pte);
+ ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1);
+ update_mmu_cache(vma, vmf->address, vmf->pte);
pte_unmap_unlock(vmf->pte, vmf->ptl);
}
@@ -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_cache(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_cache(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_cache(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_cache(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_cache(vma, vmf->address, vmf->pte);
return VM_FAULT_NOPAGE;
+ }
flush_icache_page(vma, page);
entry = mk_pte(page, vma->vm_page_prot);
@@ -4224,18 +4233,18 @@ 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_cache(vmf->vma, vmf->address, vmf->pte);
goto unlock;
+ }
if (vmf->flags & FAULT_FLAG_WRITE) {
if (!pte_write(entry))
return do_wp_page(vmf);
entry = pte_mkdirty(entry);
}
entry = pte_mkyoung(entry);
- if (ptep_set_access_flags(vmf->vma, vmf->address, vmf->pte, entry,
+ if (!ptep_set_access_flags(vmf->vma, vmf->address, vmf->pte, entry,
vmf->flags & FAULT_FLAG_WRITE)) {
- update_mmu_cache(vmf->vma, vmf->address, vmf->pte);
- } 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.
@@ -4245,6 +4254,7 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
if (vmf->flags & FAULT_FLAG_WRITE)
flush_tlb_fix_spurious_fault(vmf->vma, vmf->address);
}
+ update_mmu_cache(vmf->vma, vmf->address, vmf->pte);
unlock:
pte_unmap_unlock(vmf->pte, vmf->ptl);
return 0;
--
1.8.3.1