mm/memory: handle_pte_fault() use pte_offset_map_nolock()

handle_pte_fault() use pte_offset_map_nolock() to get the vmf.ptl which
corresponds to vmf.pte, instead of pte_lockptr() being used later, when
there's a chance that the pmd entry might have changed, perhaps to none,
or to a huge pmd, with no split ptlock in its struct page.

Remove its pmd_devmap_trans_unstable() call: pte_offset_map_nolock() will
handle that case by failing.  Update the "morph" comment above, looking
forward to when shmem or file collapse to THP may not take mmap_lock for
write (or not at all).

do_numa_page() use the vmf->ptl from handle_pte_fault() at first, but
refresh it when refreshing vmf->pte.

do_swap_page()'s pte_unmap_same() (the thing that takes ptl to verify a
two-part PAE orig_pte) use the vmf->ptl from handle_pte_fault() too; but
do_swap_page() is also used by anon THP's __collapse_huge_page_swapin(),
so adjust that to set vmf->ptl by pte_offset_map_nolock().

Link: https://lkml.kernel.org/r/c1107654-3929-60ac-223e-6877cbb86065@google.com
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Song Liu <song@kernel.org>
Cc: Steven Price <steven.price@arm.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Zack Rusin <zackr@vmware.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

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))) {