summaryrefslogtreecommitdiff
path: root/mm/migrate_device.c
diff options
context:
space:
mode:
authorHugh Dickins <hughd@google.com>2023-06-08 18:38:17 -0700
committerAndrew Morton <akpm@linux-foundation.org>2023-06-19 16:19:17 -0700
commit4b56069c95d69bfce0c0ffb2531d08216268a972 (patch)
treecc7a980f70f5751ca3eaababf69f71251682ee70 /mm/migrate_device.c
parent52fc048320adf1b1c07a2627461dca9f7d7956ff (diff)
downloadlwn-4b56069c95d69bfce0c0ffb2531d08216268a972.tar.gz
lwn-4b56069c95d69bfce0c0ffb2531d08216268a972.zip
mm/migrate_device: allow pte_offset_map_lock() to fail
migrate_vma_collect_pmd(): remove the pmd_trans_unstable() handling after splitting huge zero pmd, and the pmd_none() handling after successfully splitting huge page: those are now managed inside pte_offset_map_lock(), and by "goto again" when it fails. But the skip after unsuccessful split_huge_page() must stay: it avoids an endless loop. The skip when pmd_bad()? Remove that: it will be treated as a hole rather than a skip once cleared by pte_offset_map_lock(), but with different timing that would be so anyway; and it's arguably best to leave the pmd_bad() handling centralized there. migrate_vma_insert_page(): remove comment on the old pte_offset_map() and old locking limitations; remove the pmd_trans_unstable() check and just proceed to pte_offset_map_lock(), aborting when it fails (page has been charged to memcg, but as in other cases, it's uncharged when freed). Link: https://lkml.kernel.org/r/1131be62-2e84-da2f-8f45-807b2cbeeec5@google.com Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: 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>
Diffstat (limited to 'mm/migrate_device.c')
-rw-r--r--mm/migrate_device.c31
1 files changed, 4 insertions, 27 deletions
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index d30c9de60b0d..a14af6b12b04 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -83,9 +83,6 @@ again:
if (is_huge_zero_page(page)) {
spin_unlock(ptl);
split_huge_pmd(vma, pmdp, addr);
- if (pmd_trans_unstable(pmdp))
- return migrate_vma_collect_skip(start, end,
- walk);
} else {
int ret;
@@ -100,16 +97,12 @@ again:
if (ret)
return migrate_vma_collect_skip(start, end,
walk);
- if (pmd_none(*pmdp))
- return migrate_vma_collect_hole(start, end, -1,
- walk);
}
}
- if (unlikely(pmd_bad(*pmdp)))
- return migrate_vma_collect_skip(start, end, walk);
-
ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
+ if (!ptep)
+ goto again;
arch_enter_lazy_mmu_mode();
for (; addr < end; addr += PAGE_SIZE, ptep++) {
@@ -595,27 +588,10 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
pmdp = pmd_alloc(mm, pudp, addr);
if (!pmdp)
goto abort;
-
if (pmd_trans_huge(*pmdp) || pmd_devmap(*pmdp))
goto abort;
-
- /*
- * Use pte_alloc() instead of pte_alloc_map(). We can't run
- * pte_offset_map() on pmds where a huge pmd might be created
- * from a different thread.
- *
- * pte_alloc_map() is safe to use under mmap_write_lock(mm) or when
- * parallel threads are excluded by other means.
- *
- * Here we only have mmap_read_lock(mm).
- */
if (pte_alloc(mm, pmdp))
goto abort;
-
- /* See the comment in pte_alloc_one_map() */
- if (unlikely(pmd_trans_unstable(pmdp)))
- goto abort;
-
if (unlikely(anon_vma_prepare(vma)))
goto abort;
if (mem_cgroup_charge(page_folio(page), vma->vm_mm, GFP_KERNEL))
@@ -650,7 +626,8 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
}
ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
-
+ if (!ptep)
+ goto abort;
if (check_stable_address_space(mm))
goto unlock_abort;