mm/pagewalkers: ACTION_AGAIN if pte_offset_map_lock() fails

Simple walk_page_range() users should set ACTION_AGAIN to retry when
pte_offset_map_lock() fails.

No need to check pmd_trans_unstable(): that was precisely to avoid the
possiblity of calling pte_offset_map() on a racily removed or inserted THP
entry, but such cases are now safely handled inside it.  Likewise there is
no need to check pmd_none() or pmd_bad() before calling it.

Link: https://lkml.kernel.org/r/c77d9d10-3aad-e3ce-4896-99e91c7947f3@google.com
Signed-off-by: Hugh Dickins <hughd@google.com>
Reviewed-by: SeongJae Park <sj@kernel.org> for mm/damon part
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: 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>

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 6259dd432eebc948fd807b19832a9ec3f3b6d351..0d63b6a0f0d81ac00ec4256572d2b32b592a07cd 100644 (file)
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -631,14 +631,11 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
                goto out;
        }
 
-       if (pmd_trans_unstable(pmd))
-               goto out;
-       /*
-        * The mmap_lock held all the way back in m_start() is what
-        * keeps khugepaged out of here and from collapsing things
-        * in here.
-        */
        pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+       if (!pte) {
+               walk->action = ACTION_AGAIN;
+               return 0;
+       }
        for (; addr != end; pte++, addr += PAGE_SIZE)
                smaps_pte_entry(pte, addr, walk);
        pte_unmap_unlock(pte - 1, ptl);
@@ -1191,10 +1188,11 @@ out:
                return 0;
        }
 
-       if (pmd_trans_unstable(pmd))
-               return 0;
-
        pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+       if (!pte) {
+               walk->action = ACTION_AGAIN;
+               return 0;
+       }
        for (; addr != end; pte++, addr += PAGE_SIZE) {
                ptent = *pte;
 
@@ -1538,9 +1536,6 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
                spin_unlock(ptl);
                return err;
        }
-
-       if (pmd_trans_unstable(pmdp))
-               return 0;
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
        /*
@@ -1548,6 +1543,10 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
         * goes beyond vma->vm_end.
         */
        orig_pte = pte = pte_offset_map_lock(walk->mm, pmdp, addr, &ptl);
+       if (!pte) {
+               walk->action = ACTION_AGAIN;
+               return err;
+       }
        for (; addr < end; pte++, addr += PAGE_SIZE) {
                pagemap_entry_t pme;
 
@@ -1887,11 +1886,12 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
                spin_unlock(ptl);
                return 0;
        }
-
-       if (pmd_trans_unstable(pmd))
-               return 0;
 #endif
        orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+       if (!pte) {
+               walk->action = ACTION_AGAIN;
+               return 0;
+       }
        do {
                struct page *page = can_gather_numa_stats(*pte, vma, addr);
                if (!page)

diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
index 37994fb6120cbac8e78ffe18e63a5a9b58d1f9f4..e814f66dfc2e5dfd67faad56b213c65c3ef76de5 100644 (file)
--- a/mm/damon/vaddr.c
+++ b/mm/damon/vaddr.c
@@ -318,9 +318,11 @@ static int damon_mkold_pmd_entry(pmd_t *pmd, unsigned long addr,
                spin_unlock(ptl);
        }
 
-       if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
-               return 0;
        pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+       if (!pte) {
+               walk->action = ACTION_AGAIN;
+               return 0;
+       }
        if (!pte_present(*pte))
                goto out;
        damon_ptep_mkold(pte, walk->vma, addr);
@@ -464,9 +466,11 @@ huge_out:
 regular_page:
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-       if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
-               return -EINVAL;
        pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+       if (!pte) {
+               walk->action = ACTION_AGAIN;
+               return 0;
+       }
        if (!pte_present(*pte))
                goto out;
        folio = damon_get_folio(pte_pfn(*pte));

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index f06ca8c18e62841fff049ba3c118cb6f8951ca4b..0241bb64978bf1031ec734e0afb5cbf95a2f7b90 100644 (file)
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -514,10 +514,11 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr,
        if (ptl)
                return queue_folios_pmd(pmd, ptl, addr, end, walk);
 
-       if (pmd_trans_unstable(pmd))
-               return 0;
-
        mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+       if (!pte) {
+               walk->action = ACTION_AGAIN;
+               return 0;
+       }
        for (; addr != end; pte++, addr += PAGE_SIZE) {
                if (!pte_present(*pte))
                        continue;

diff --git a/mm/mincore.c b/mm/mincore.c
index 2d5be013a25a0ad9f941d4c9376102c2cb7b06a2..f33f6a0b1ded7fbf3a82ca3c01a0cdce6d5e500c 100644 (file)
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -113,12 +113,11 @@ static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
                goto out;
        }
 
-       if (pmd_trans_unstable(pmd)) {
-               __mincore_unmapped_range(addr, end, vma, vec);
-               goto out;
-       }
-
        ptep = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+       if (!ptep) {
+               walk->action = ACTION_AGAIN;
+               return 0;
+       }
        for (; addr != end; ptep++, addr += PAGE_SIZE) {
                pte_t pte = *ptep;
 

diff --git a/mm/mlock.c b/mm/mlock.c
index 40b43f8740dfbc1fca2a805b5c6db45e2a8a26b2..9f2b1173b1b1223dd3b4efb22608d4e7c9209bcd 100644 (file)
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -329,6 +329,10 @@ static int mlock_pte_range(pmd_t *pmd, unsigned long addr,
        }
 
        start_pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+       if (!start_pte) {
+               walk->action = ACTION_AGAIN;
+               return 0;
+       }
        for (pte = start_pte; addr != end; pte++, addr += PAGE_SIZE) {
                if (!pte_present(*pte))
                        continue;