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 /fs/userfaultfd.c | |
| parent | 6aeadf7896bff4ca230702daba8788455e6b866e (diff) | |
| parent | acc72d59c7509540c27c49625cb4b5a8db1f1a84 (diff) | |
| download | linux-6e17c6de3ddf3073741d9c91a796ee696914d8a0.tar.gz | |
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 'fs/userfaultfd.c')
| -rw-r--r-- | fs/userfaultfd.c | 62 |
1 files changed, 26 insertions, 36 deletions
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 4e800bb7d2ab61..7cecd49e078b3d 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -335,6 +335,7 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx, pud_t *pud; pmd_t *pmd, _pmd; pte_t *pte; + pte_t ptent; bool ret = true; mmap_assert_locked(mm); @@ -349,20 +350,13 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx, if (!pud_present(*pud)) goto out; pmd = pmd_offset(pud, address); - /* - * READ_ONCE must function as a barrier with narrower scope - * and it must be equivalent to: - * _pmd = *pmd; barrier(); - * - * This is to deal with the instability (as in - * pmd_trans_unstable) of the pmd. - */ - _pmd = READ_ONCE(*pmd); +again: + _pmd = pmdp_get_lockless(pmd); if (pmd_none(_pmd)) goto out; ret = false; - if (!pmd_present(_pmd)) + if (!pmd_present(_pmd) || pmd_devmap(_pmd)) goto out; if (pmd_trans_huge(_pmd)) { @@ -371,19 +365,20 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx, goto out; } - /* - * the pmd is stable (as in !pmd_trans_unstable) so we can re-read it - * and use the standard pte_offset_map() instead of parsing _pmd. - */ pte = pte_offset_map(pmd, address); + if (!pte) { + ret = true; + goto again; + } /* * Lockless access: we're in a wait_event so it's ok if it * changes under us. PTE markers should be handled the same as none * ptes here. */ - if (pte_none_mostly(*pte)) + ptent = ptep_get(pte); + if (pte_none_mostly(ptent)) ret = true; - if (!pte_write(*pte) && (reason & VM_UFFD_WP)) + if (!pte_write(ptent) && (reason & VM_UFFD_WP)) ret = true; pte_unmap(pte); @@ -857,31 +852,26 @@ static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps, return false; } -int userfaultfd_unmap_prep(struct mm_struct *mm, unsigned long start, +int userfaultfd_unmap_prep(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *unmaps) { - VMA_ITERATOR(vmi, mm, start); - struct vm_area_struct *vma; - - for_each_vma_range(vmi, vma, end) { - struct userfaultfd_unmap_ctx *unmap_ctx; - struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx; + struct userfaultfd_unmap_ctx *unmap_ctx; + struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx; - if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_UNMAP) || - has_unmap_ctx(ctx, unmaps, start, end)) - continue; + if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_UNMAP) || + has_unmap_ctx(ctx, unmaps, start, end)) + return 0; - unmap_ctx = kzalloc(sizeof(*unmap_ctx), GFP_KERNEL); - if (!unmap_ctx) - return -ENOMEM; + unmap_ctx = kzalloc(sizeof(*unmap_ctx), GFP_KERNEL); + if (!unmap_ctx) + return -ENOMEM; - userfaultfd_ctx_get(ctx); - atomic_inc(&ctx->mmap_changing); - unmap_ctx->ctx = ctx; - unmap_ctx->start = start; - unmap_ctx->end = end; - list_add_tail(&unmap_ctx->list, unmaps); - } + userfaultfd_ctx_get(ctx); + atomic_inc(&ctx->mmap_changing); + unmap_ctx->ctx = ctx; + unmap_ctx->start = start; + unmap_ctx->end = end; + list_add_tail(&unmap_ctx->list, unmaps); return 0; } |