diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-06-28 10:28:11 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-06-28 10:28:11 -0700 |
commit | 6e17c6de3ddf3073741d9c91a796ee696914d8a0 (patch) | |
tree | 2c425707f78642625dbe2c824c7fded2021e3dc7 /mm/mremap.c | |
parent | 6aeadf7896bff4ca230702daba8788455e6b866e (diff) | |
parent | acc72d59c7509540c27c49625cb4b5a8db1f1a84 (diff) |
Merge tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull mm updates from Andrew Morton:
- Yosry Ahmed brought back some cgroup v1 stats in OOM logs
- Yosry has also eliminated cgroup's atomic rstat flushing
- Nhat Pham adds the new cachestat() syscall. It provides userspace
with the ability to query pagecache status - a similar concept to
mincore() but more powerful and with improved usability
- Mel Gorman provides more optimizations for compaction, reducing the
prevalence of page rescanning
- Lorenzo Stoakes has done some maintanance work on the
get_user_pages() interface
- Liam Howlett continues with cleanups and maintenance work to the
maple tree code. Peng Zhang also does some work on maple tree
- Johannes Weiner has done some cleanup work on the compaction code
- David Hildenbrand has contributed additional selftests for
get_user_pages()
- Thomas Gleixner has contributed some maintenance and optimization
work for the vmalloc code
- Baolin Wang has provided some compaction cleanups,
- SeongJae Park continues maintenance work on the DAMON code
- Huang Ying has done some maintenance on the swap code's usage of
device refcounting
- Christoph Hellwig has some cleanups for the filemap/directio code
- Ryan Roberts provides two patch series which yield some
rationalization of the kernel's access to pte entries - use the
provided APIs rather than open-coding accesses
- Lorenzo Stoakes has some fixes to the interaction between pagecache
and directio access to file mappings
- John Hubbard has a series of fixes to the MM selftesting code
- ZhangPeng continues the folio conversion campaign
- Hugh Dickins has been working on the pagetable handling code, mainly
with a view to reducing the load on the mmap_lock
- Catalin Marinas has reduced the arm64 kmalloc() minimum alignment
from 128 to 8
- Domenico Cerasuolo has improved the zswap reclaim mechanism by
reorganizing the LRU management
- Matthew Wilcox provides some fixups to make gfs2 work better with the
buffer_head code
- Vishal Moola also has done some folio conversion work
- Matthew Wilcox has removed the remnants of the pagevec code - their
functionality is migrated over to struct folio_batch
* tag 'mm-stable-2023-06-24-19-15' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (380 commits)
mm/hugetlb: remove hugetlb_set_page_subpool()
mm: nommu: correct the range of mmap_sem_read_lock in task_mem()
hugetlb: revert use of page_cache_next_miss()
Revert "page cache: fix page_cache_next/prev_miss off by one"
mm/vmscan: fix root proactive reclaim unthrottling unbalanced node
mm: memcg: rename and document global_reclaim()
mm: kill [add|del]_page_to_lru_list()
mm: compaction: convert to use a folio in isolate_migratepages_block()
mm: zswap: fix double invalidate with exclusive loads
mm: remove unnecessary pagevec includes
mm: remove references to pagevec
mm: rename invalidate_mapping_pagevec to mapping_try_invalidate
mm: remove struct pagevec
net: convert sunrpc from pagevec to folio_batch
i915: convert i915_gpu_error to use a folio_batch
pagevec: rename fbatch_count()
mm: remove check_move_unevictable_pages()
drm: convert drm_gem_put_pages() to use a folio_batch
i915: convert shmem_sg_free_table() to use a folio_batch
scatterlist: add sg_set_folio()
...
Diffstat (limited to 'mm/mremap.c')
-rw-r--r-- | mm/mremap.c | 32 |
1 files changed, 22 insertions, 10 deletions
diff --git a/mm/mremap.c b/mm/mremap.c index 3185724d8b13..fe6b722ae633 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -133,7 +133,7 @@ static pte_t move_soft_dirty_pte(pte_t pte) return pte; } -static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, +static int move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, unsigned long old_addr, unsigned long old_end, struct vm_area_struct *new_vma, pmd_t *new_pmd, unsigned long new_addr, bool need_rmap_locks) @@ -143,6 +143,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, spinlock_t *old_ptl, *new_ptl; bool force_flush = false; unsigned long len = old_end - old_addr; + int err = 0; /* * When need_rmap_locks is true, we take the i_mmap_rwsem and anon_vma @@ -170,8 +171,16 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, * pte locks because exclusive mmap_lock prevents deadlock. */ old_pte = pte_offset_map_lock(mm, old_pmd, old_addr, &old_ptl); - new_pte = pte_offset_map(new_pmd, new_addr); - new_ptl = pte_lockptr(mm, new_pmd); + if (!old_pte) { + err = -EAGAIN; + goto out; + } + new_pte = pte_offset_map_nolock(mm, new_pmd, new_addr, &new_ptl); + if (!new_pte) { + pte_unmap_unlock(old_pte, old_ptl); + err = -EAGAIN; + goto out; + } if (new_ptl != old_ptl) spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); flush_tlb_batched_pending(vma->vm_mm); @@ -179,7 +188,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, for (; old_addr < old_end; old_pte++, old_addr += PAGE_SIZE, new_pte++, new_addr += PAGE_SIZE) { - if (pte_none(*old_pte)) + if (pte_none(ptep_get(old_pte))) continue; pte = ptep_get_and_clear(mm, old_addr, old_pte); @@ -208,8 +217,10 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, spin_unlock(new_ptl); pte_unmap(new_pte - 1); pte_unmap_unlock(old_pte - 1, old_ptl); +out: if (need_rmap_locks) drop_rmap_locks(vma); + return err; } #ifndef arch_supports_page_table_move @@ -537,6 +548,7 @@ unsigned long move_page_tables(struct vm_area_struct *vma, new_pmd = alloc_new_pmd(vma->vm_mm, vma, new_addr); if (!new_pmd) break; +again: if (is_swap_pmd(*old_pmd) || pmd_trans_huge(*old_pmd) || pmd_devmap(*old_pmd)) { if (extent == HPAGE_PMD_SIZE && @@ -544,8 +556,6 @@ unsigned long move_page_tables(struct vm_area_struct *vma, old_pmd, new_pmd, need_rmap_locks)) continue; split_huge_pmd(vma, old_pmd, old_addr); - if (pmd_trans_unstable(old_pmd)) - continue; } else if (IS_ENABLED(CONFIG_HAVE_MOVE_PMD) && extent == PMD_SIZE) { /* @@ -556,11 +566,13 @@ unsigned long move_page_tables(struct vm_area_struct *vma, old_pmd, new_pmd, true)) continue; } - + if (pmd_none(*old_pmd)) + continue; if (pte_alloc(new_vma->vm_mm, new_pmd)) break; - move_ptes(vma, old_pmd, old_addr, old_addr + extent, new_vma, - new_pmd, new_addr, need_rmap_locks); + if (move_ptes(vma, old_pmd, old_addr, old_addr + extent, + new_vma, new_pmd, new_addr, need_rmap_locks) < 0) + goto again; } mmu_notifier_invalidate_range_end(&range); @@ -775,7 +787,7 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr, if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP)) return ERR_PTR(-EFAULT); - if (mlock_future_check(mm, vma->vm_flags, new_len - old_len)) + if (!mlock_future_ok(mm, vma->vm_flags, new_len - old_len)) return ERR_PTR(-EAGAIN); if (!may_expand_vm(mm, vma->vm_flags, |