summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/khugepaged.c6
-rw-r--r--mm/memory.c38
2 files changed, 17 insertions, 27 deletions
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 04c22b5309d7..d1951ed572f8 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1003,6 +1003,7 @@ static int __collapse_huge_page_swapin(struct mm_struct *mm,
unsigned long address, end = haddr + (HPAGE_PMD_NR * PAGE_SIZE);
int result;
pte_t *pte = NULL;
+ spinlock_t *ptl;
for (address = haddr; address < end; address += PAGE_SIZE) {
struct vm_fault vmf = {
@@ -1014,7 +1015,7 @@ static int __collapse_huge_page_swapin(struct mm_struct *mm,
};
if (!pte++) {
- pte = pte_offset_map(pmd, address);
+ pte = pte_offset_map_nolock(mm, pmd, address, &ptl);
if (!pte) {
mmap_read_unlock(mm);
result = SCAN_PMD_NULL;
@@ -1022,11 +1023,12 @@ static int __collapse_huge_page_swapin(struct mm_struct *mm,
}
}
- vmf.orig_pte = *pte;
+ vmf.orig_pte = ptep_get_lockless(pte);
if (!is_swap_pte(vmf.orig_pte))
continue;
vmf.pte = pte;
+ vmf.ptl = ptl;
ret = do_swap_page(&vmf);
/* Which unmaps pte (after perhaps re-checking the entry) */
pte = NULL;
diff --git a/mm/memory.c b/mm/memory.c
index 4ab4de234b76..11f221953690 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2786,10 +2786,9 @@ static inline int pte_unmap_same(struct vm_fault *vmf)
int same = 1;
#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPTION)
if (sizeof(pte_t) > sizeof(unsigned long)) {
- spinlock_t *ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd);
- spin_lock(ptl);
+ spin_lock(vmf->ptl);
same = pte_same(*vmf->pte, vmf->orig_pte);
- spin_unlock(ptl);
+ spin_unlock(vmf->ptl);
}
#endif
pte_unmap(vmf->pte);
@@ -4697,7 +4696,6 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
* validation through pte_unmap_same(). It's of NUMA type but
* the pfn may be screwed if the read is non atomic.
*/
- vmf->ptl = pte_lockptr(vma->vm_mm, vmf->pmd);
spin_lock(vmf->ptl);
if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) {
pte_unmap_unlock(vmf->pte, vmf->ptl);
@@ -4768,8 +4766,10 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
flags |= TNF_MIGRATED;
} else {
flags |= TNF_MIGRATE_FAIL;
- vmf->pte = pte_offset_map(vmf->pmd, vmf->address);
- spin_lock(vmf->ptl);
+ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
+ vmf->address, &vmf->ptl);
+ if (unlikely(!vmf->pte))
+ goto out;
if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) {
pte_unmap_unlock(vmf->pte, vmf->ptl);
goto out;
@@ -4899,26 +4899,15 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
vmf->flags &= ~FAULT_FLAG_ORIG_PTE_VALID;
} else {
/*
- * If a huge pmd materialized under us just retry later. Use
- * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead
- * of pmd_trans_huge() to ensure the pmd didn't become
- * pmd_trans_huge under us and then back to pmd_none, as a
- * result of MADV_DONTNEED running immediately after a huge pmd
- * fault in a different thread of this mm, in turn leading to a
- * misleading pmd_trans_huge() retval. All we have to ensure is
- * that it is a regular pmd that we can walk with
- * pte_offset_map() and we can do that through an atomic read
- * in C, which is what pmd_trans_unstable() provides.
- */
- if (pmd_devmap_trans_unstable(vmf->pmd))
- return 0;
- /*
* A regular pmd is established and it can't morph into a huge
- * pmd from under us anymore at this point because we hold the
- * mmap_lock read mode and khugepaged takes it in write mode.
- * So now it's safe to run pte_offset_map().
+ * pmd by anon khugepaged, since that takes mmap_lock in write
+ * mode; but shmem or file collapse to THP could still morph
+ * it into a huge pmd: just retry later if so.
*/
- vmf->pte = pte_offset_map(vmf->pmd, vmf->address);
+ vmf->pte = pte_offset_map_nolock(vmf->vma->vm_mm, vmf->pmd,
+ vmf->address, &vmf->ptl);
+ if (unlikely(!vmf->pte))
+ return 0;
vmf->orig_pte = ptep_get_lockless(vmf->pte);
vmf->flags |= FAULT_FLAG_ORIG_PTE_VALID;
@@ -4937,7 +4926,6 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
if (pte_protnone(vmf->orig_pte) && vma_is_accessible(vmf->vma))
return do_numa_page(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))) {