diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 1 | ||||
| -rw-r--r-- | mm/damon/Kconfig | 1 | ||||
| -rw-r--r-- | mm/damon/modules-common.c | 2 | ||||
| -rw-r--r-- | mm/damon/modules-common.h | 2 | ||||
| -rw-r--r-- | mm/damon/ops-common.c | 2 | ||||
| -rw-r--r-- | mm/damon/ops-common.h | 2 | ||||
| -rw-r--r-- | mm/damon/paddr.c | 2 | ||||
| -rw-r--r-- | mm/damon/sysfs-common.c | 2 | ||||
| -rw-r--r-- | mm/damon/sysfs-common.h | 2 | ||||
| -rw-r--r-- | mm/damon/vaddr.c | 2 | ||||
| -rw-r--r-- | mm/execmem.c | 40 | ||||
| -rw-r--r-- | mm/gup.c | 14 | ||||
| -rw-r--r-- | mm/hugetlb.c | 67 | ||||
| -rw-r--r-- | mm/kmsan/kmsan_test.c | 1 | ||||
| -rw-r--r-- | mm/madvise.c | 7 | ||||
| -rw-r--r-- | mm/memory.c | 20 | ||||
| -rw-r--r-- | mm/mempolicy.c | 4 | ||||
| -rw-r--r-- | mm/mremap.c | 2 | ||||
| -rw-r--r-- | mm/page-writeback.c | 4 | ||||
| -rw-r--r-- | mm/shmem.c | 6 | ||||
| -rw-r--r-- | mm/slub.c | 15 | ||||
| -rw-r--r-- | mm/swap.h | 23 | ||||
| -rw-r--r-- | mm/userfaultfd.c | 33 | ||||
| -rw-r--r-- | mm/util.c | 40 | ||||
| -rw-r--r-- | mm/vma.c | 50 | ||||
| -rw-r--r-- | mm/vma.h | 54 | ||||
| -rw-r--r-- | mm/vmstat.c | 1 |
27 files changed, 275 insertions, 124 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index f8bb8f070d0d..781be3240e21 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -1355,6 +1355,7 @@ config NUMA_MEMBLKS config NUMA_EMU bool "NUMA emulation" depends on NUMA_MEMBLKS + depends on X86 || GENERIC_ARCH_NUMA help Enable NUMA emulation. A flat machine will be split into virtual nodes when booted with "numa=fake=N", where N is the diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig index 551745df011b..c93d0c56b963 100644 --- a/mm/damon/Kconfig +++ b/mm/damon/Kconfig @@ -4,7 +4,6 @@ menu "Data Access Monitoring" config DAMON bool "DAMON: Data Access Monitoring Framework" - default y help This builds a framework that allows kernel subsystems to monitor access frequency of each memory region. The information can be useful diff --git a/mm/damon/modules-common.c b/mm/damon/modules-common.c index 7cf96574cde7..86d58f8c4f63 100644 --- a/mm/damon/modules-common.c +++ b/mm/damon/modules-common.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Common Primitives for DAMON Modules + * Common Code for DAMON Modules * * Author: SeongJae Park <sj@kernel.org> */ diff --git a/mm/damon/modules-common.h b/mm/damon/modules-common.h index f49cdb417005..f103ad556368 100644 --- a/mm/damon/modules-common.h +++ b/mm/damon/modules-common.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * Common Primitives for DAMON Modules + * Common Code for DAMON Modules * * Author: SeongJae Park <sj@kernel.org> */ diff --git a/mm/damon/ops-common.c b/mm/damon/ops-common.c index 0db1fc70c84d..b43620fee6bb 100644 --- a/mm/damon/ops-common.c +++ b/mm/damon/ops-common.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Common Primitives for Data Access Monitoring + * Common Code for Data Access Monitoring * * Author: SeongJae Park <sj@kernel.org> */ diff --git a/mm/damon/ops-common.h b/mm/damon/ops-common.h index 18d837d11bce..cc9f5da9c012 100644 --- a/mm/damon/ops-common.h +++ b/mm/damon/ops-common.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * Common Primitives for Data Access Monitoring + * Common Code for Data Access Monitoring * * Author: SeongJae Park <sj@kernel.org> */ diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index e8464f7e0014..4102a8c5f992 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * DAMON Primitives for The Physical Address Space + * DAMON Code for The Physical Address Space * * Author: SeongJae Park <sj@kernel.org> */ diff --git a/mm/damon/sysfs-common.c b/mm/damon/sysfs-common.c index 70edf45c2174..ffaf285e241a 100644 --- a/mm/damon/sysfs-common.c +++ b/mm/damon/sysfs-common.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Common Primitives for DAMON Sysfs Interface + * Common Code for DAMON Sysfs Interface * * Author: SeongJae Park <sj@kernel.org> */ diff --git a/mm/damon/sysfs-common.h b/mm/damon/sysfs-common.h index 70d84bdc9f5f..2099adee11d0 100644 --- a/mm/damon/sysfs-common.h +++ b/mm/damon/sysfs-common.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * Common Primitives for DAMON Sysfs Interface + * Common Code for DAMON Sysfs Interface * * Author: SeongJae Park <sj@kernel.org> */ diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index e6d99106a7f9..46554e49a478 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * DAMON Primitives for Virtual Address Spaces + * DAMON Code for Virtual Address Spaces * * Author: SeongJae Park <sj@kernel.org> */ diff --git a/mm/execmem.c b/mm/execmem.c index 9720ac2dfa41..2b683e7d864d 100644 --- a/mm/execmem.c +++ b/mm/execmem.c @@ -254,34 +254,6 @@ out_unlock: return ptr; } -static bool execmem_cache_rox = false; - -void execmem_cache_make_ro(void) -{ - struct maple_tree *free_areas = &execmem_cache.free_areas; - struct maple_tree *busy_areas = &execmem_cache.busy_areas; - MA_STATE(mas_free, free_areas, 0, ULONG_MAX); - MA_STATE(mas_busy, busy_areas, 0, ULONG_MAX); - struct mutex *mutex = &execmem_cache.mutex; - void *area; - - execmem_cache_rox = true; - - mutex_lock(mutex); - - mas_for_each(&mas_free, area, ULONG_MAX) { - unsigned long pages = mas_range_len(&mas_free) >> PAGE_SHIFT; - set_memory_ro(mas_free.index, pages); - } - - mas_for_each(&mas_busy, area, ULONG_MAX) { - unsigned long pages = mas_range_len(&mas_busy) >> PAGE_SHIFT; - set_memory_ro(mas_busy.index, pages); - } - - mutex_unlock(mutex); -} - static int execmem_cache_populate(struct execmem_range *range, size_t size) { unsigned long vm_flags = VM_ALLOW_HUGE_VMAP; @@ -302,15 +274,9 @@ static int execmem_cache_populate(struct execmem_range *range, size_t size) /* fill memory with instructions that will trap */ execmem_fill_trapping_insns(p, alloc_size, /* writable = */ true); - if (execmem_cache_rox) { - err = set_memory_rox((unsigned long)p, vm->nr_pages); - if (err) - goto err_free_mem; - } else { - err = set_memory_x((unsigned long)p, vm->nr_pages); - if (err) - goto err_free_mem; - } + err = set_memory_rox((unsigned long)p, vm->nr_pages); + if (err) + goto err_free_mem; err = execmem_cache_add(p, alloc_size); if (err) @@ -2303,13 +2303,13 @@ static void pofs_unpin(struct pages_or_folios *pofs) /* * Returns the number of collected folios. Return value is always >= 0. */ -static void collect_longterm_unpinnable_folios( +static unsigned long collect_longterm_unpinnable_folios( struct list_head *movable_folio_list, struct pages_or_folios *pofs) { + unsigned long i, collected = 0; struct folio *prev_folio = NULL; bool drain_allow = true; - unsigned long i; for (i = 0; i < pofs->nr_entries; i++) { struct folio *folio = pofs_get_folio(pofs, i); @@ -2321,6 +2321,8 @@ static void collect_longterm_unpinnable_folios( if (folio_is_longterm_pinnable(folio)) continue; + collected++; + if (folio_is_device_coherent(folio)) continue; @@ -2342,6 +2344,8 @@ static void collect_longterm_unpinnable_folios( NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); } + + return collected; } /* @@ -2418,9 +2422,11 @@ static long check_and_migrate_movable_pages_or_folios(struct pages_or_folios *pofs) { LIST_HEAD(movable_folio_list); + unsigned long collected; - collect_longterm_unpinnable_folios(&movable_folio_list, pofs); - if (list_empty(&movable_folio_list)) + collected = collect_longterm_unpinnable_folios(&movable_folio_list, + pofs); + if (!collected) return 0; return migrate_longterm_unpinnable_folios(&movable_folio_list, pofs); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f0b1d53079f9..8746ed2fec13 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -121,7 +121,7 @@ static void hugetlb_vma_lock_free(struct vm_area_struct *vma); static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma); static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma); static void hugetlb_unshare_pmds(struct vm_area_struct *vma, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, bool take_locks); static struct resv_map *vma_resv_map(struct vm_area_struct *vma); static void hugetlb_free_folio(struct folio *folio) @@ -5426,26 +5426,40 @@ static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr) { if (addr & ~(huge_page_mask(hstate_vma(vma)))) return -EINVAL; + return 0; +} +void hugetlb_split(struct vm_area_struct *vma, unsigned long addr) +{ /* * PMD sharing is only possible for PUD_SIZE-aligned address ranges * in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this * split, unshare PMDs in the PUD_SIZE interval surrounding addr now. + * This function is called in the middle of a VMA split operation, with + * MM, VMA and rmap all write-locked to prevent concurrent page table + * walks (except hardware and gup_fast()). */ + vma_assert_write_locked(vma); + i_mmap_assert_write_locked(vma->vm_file->f_mapping); + if (addr & ~PUD_MASK) { - /* - * hugetlb_vm_op_split is called right before we attempt to - * split the VMA. We will need to unshare PMDs in the old and - * new VMAs, so let's unshare before we split. - */ unsigned long floor = addr & PUD_MASK; unsigned long ceil = floor + PUD_SIZE; - if (floor >= vma->vm_start && ceil <= vma->vm_end) - hugetlb_unshare_pmds(vma, floor, ceil); + if (floor >= vma->vm_start && ceil <= vma->vm_end) { + /* + * Locking: + * Use take_locks=false here. + * The file rmap lock is already held. + * The hugetlb VMA lock can't be taken when we already + * hold the file rmap lock, and we don't need it because + * its purpose is to synchronize against concurrent page + * table walks, which are not possible thanks to the + * locks held by our caller. + */ + hugetlb_unshare_pmds(vma, floor, ceil, /* take_locks = */ false); + } } - - return 0; } static unsigned long hugetlb_vm_op_pagesize(struct vm_area_struct *vma) @@ -7615,6 +7629,13 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, return 0; pud_clear(pud); + /* + * Once our caller drops the rmap lock, some other process might be + * using this page table as a normal, non-hugetlb page table. + * Wait for pending gup_fast() in other threads to finish before letting + * that happen. + */ + tlb_remove_table_sync_one(); ptdesc_pmd_pts_dec(virt_to_ptdesc(ptep)); mm_dec_nr_pmds(mm); return 1; @@ -7885,9 +7906,16 @@ void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int re spin_unlock_irq(&hugetlb_lock); } +/* + * If @take_locks is false, the caller must ensure that no concurrent page table + * access can happen (except for gup_fast() and hardware page walks). + * If @take_locks is true, we take the hugetlb VMA lock (to lock out things like + * concurrent page fault handling) and the file rmap lock. + */ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long start, - unsigned long end) + unsigned long end, + bool take_locks) { struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); @@ -7911,8 +7939,12 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, start, end); mmu_notifier_invalidate_range_start(&range); - hugetlb_vma_lock_write(vma); - i_mmap_lock_write(vma->vm_file->f_mapping); + if (take_locks) { + hugetlb_vma_lock_write(vma); + i_mmap_lock_write(vma->vm_file->f_mapping); + } else { + i_mmap_assert_write_locked(vma->vm_file->f_mapping); + } for (address = start; address < end; address += PUD_SIZE) { ptep = hugetlb_walk(vma, address, sz); if (!ptep) @@ -7922,8 +7954,10 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, spin_unlock(ptl); } flush_hugetlb_tlb_range(vma, start, end); - i_mmap_unlock_write(vma->vm_file->f_mapping); - hugetlb_vma_unlock_write(vma); + if (take_locks) { + i_mmap_unlock_write(vma->vm_file->f_mapping); + hugetlb_vma_unlock_write(vma); + } /* * No need to call mmu_notifier_arch_invalidate_secondary_tlbs(), see * Documentation/mm/mmu_notifier.rst. @@ -7938,7 +7972,8 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE), - ALIGN_DOWN(vma->vm_end, PUD_SIZE)); + ALIGN_DOWN(vma->vm_end, PUD_SIZE), + /* take_locks = */ true); } /* diff --git a/mm/kmsan/kmsan_test.c b/mm/kmsan/kmsan_test.c index 9733a22c46c1..c6c5b2bbede0 100644 --- a/mm/kmsan/kmsan_test.c +++ b/mm/kmsan/kmsan_test.c @@ -732,3 +732,4 @@ kunit_test_suites(&kmsan_test_suite); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Alexander Potapenko <glider@google.com>"); +MODULE_DESCRIPTION("Test cases for KMSAN"); diff --git a/mm/madvise.c b/mm/madvise.c index 8433ac9b27e0..1d44a35ae85c 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -508,6 +508,7 @@ restart: pte_offset_map_lock(mm, pmd, addr, &ptl); if (!start_pte) break; + flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); if (!err) nr = 0; @@ -741,6 +742,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, start_pte = pte; if (!start_pte) break; + flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); if (!err) nr = 0; @@ -1881,7 +1883,9 @@ static ssize_t vector_madvise(struct mm_struct *mm, struct iov_iter *iter, /* Drop and reacquire lock to unwind race. */ madvise_finish_tlb(&madv_behavior); madvise_unlock(mm, behavior); - madvise_lock(mm, behavior); + ret = madvise_lock(mm, behavior); + if (ret) + goto out; madvise_init_tlb(&madv_behavior, mm); continue; } @@ -1892,6 +1896,7 @@ static ssize_t vector_madvise(struct mm_struct *mm, struct iov_iter *iter, madvise_finish_tlb(&madv_behavior); madvise_unlock(mm, behavior); +out: ret = (total_len - iov_iter_count(iter)) ? : ret; return ret; diff --git a/mm/memory.c b/mm/memory.c index 8eba595056fe..b0cda5aab398 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4315,26 +4315,6 @@ static struct folio *__alloc_swap_folio(struct vm_fault *vmf) } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -static inline int non_swapcache_batch(swp_entry_t entry, int max_nr) -{ - struct swap_info_struct *si = swp_swap_info(entry); - pgoff_t offset = swp_offset(entry); - int i; - - /* - * While allocating a large folio and doing swap_read_folio, which is - * the case the being faulted pte doesn't have swapcache. We need to - * ensure all PTEs have no cache as well, otherwise, we might go to - * swap devices while the content is in swapcache. - */ - for (i = 0; i < max_nr; i++) { - if ((si->swap_map[offset + i] & SWAP_HAS_CACHE)) - return i; - } - - return i; -} - /* * Check if the PTEs within a range are contiguous swap entries * and have consistent swapcache, zeromap. diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 72fd72e156b1..3b1dfd08338b 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -3708,15 +3708,13 @@ static void wi_state_free(void) lockdep_is_held(&wi_state_lock)); if (!old_wi_state) { mutex_unlock(&wi_state_lock); - goto out; + return; } rcu_assign_pointer(wi_state, NULL); mutex_unlock(&wi_state_lock); synchronize_rcu(); kfree(old_wi_state); -out: - kfree(&wi_group->wi_kobj); } static struct kobj_attribute wi_auto_attr = diff --git a/mm/mremap.c b/mm/mremap.c index 83e359754961..60f6b8d0d5f0 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -237,6 +237,8 @@ static int move_ptes(struct pagetable_move_control *pmc, for (; old_addr < old_end; old_pte++, old_addr += PAGE_SIZE, new_pte++, new_addr += PAGE_SIZE) { + VM_WARN_ON_ONCE(!pte_none(*new_pte)); + if (pte_none(ptep_get(old_pte))) continue; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index b8eea5b3c064..72b0ff0d4bae 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -608,7 +608,7 @@ EXPORT_SYMBOL_GPL(wb_writeout_inc); */ static void writeout_period(struct timer_list *t) { - struct wb_domain *dom = from_timer(dom, t, period_timer); + struct wb_domain *dom = timer_container_of(dom, t, period_timer); int miss_periods = (jiffies - dom->period_time) / VM_COMPLETIONS_PERIOD_LEN; @@ -2203,7 +2203,7 @@ static int dirty_writeback_centisecs_handler(const struct ctl_table *table, int void laptop_mode_timer_fn(struct timer_list *t) { struct backing_dev_info *backing_dev_info = - from_timer(backing_dev_info, t, laptop_mode_wb_timer); + timer_container_of(backing_dev_info, t, laptop_mode_wb_timer); wakeup_flusher_threads_bdi(backing_dev_info, WB_REASON_LAPTOP_TIMER); } diff --git a/mm/shmem.c b/mm/shmem.c index 0c5fb4ffa03a..3a5a65b1f41a 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2259,6 +2259,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, folio = swap_cache_get_folio(swap, NULL, 0); order = xa_get_order(&mapping->i_pages, index); if (!folio) { + int nr_pages = 1 << order; bool fallback_order0 = false; /* Or update major stats only when swapin succeeds?? */ @@ -2272,9 +2273,12 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, * If uffd is active for the vma, we need per-page fault * fidelity to maintain the uffd semantics, then fallback * to swapin order-0 folio, as well as for zswap case. + * Any existing sub folio in the swap cache also blocks + * mTHP swapin. */ if (order > 0 && ((vma && unlikely(userfaultfd_armed(vma))) || - !zswap_never_enabled())) + !zswap_never_enabled() || + non_swapcache_batch(swap, nr_pages) != nr_pages)) fallback_order0 = true; /* Skip swapcache for synchronous device. */ diff --git a/mm/slub.c b/mm/slub.c index be8b09e09d30..31e11ef256f9 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2084,10 +2084,11 @@ prepare_slab_obj_exts_hook(struct kmem_cache *s, gfp_t flags, void *p) slab = virt_to_slab(p); if (!slab_obj_exts(slab) && - WARN(alloc_slab_obj_exts(slab, s, flags, false), - "%s, %s: Failed to create slab extension vector!\n", - __func__, s->name)) + alloc_slab_obj_exts(slab, s, flags, false)) { + pr_warn_once("%s, %s: Failed to create slab extension vector!\n", + __func__, s->name); return NULL; + } return slab_obj_exts(slab) + obj_to_index(s, slab, p); } @@ -4968,14 +4969,16 @@ static gfp_t kmalloc_gfp_adjust(gfp_t flags, size_t size) * We want to attempt a large physically contiguous block first because * it is less likely to fragment multiple larger blocks and therefore * contribute to a long term fragmentation less than vmalloc fallback. - * However make sure that larger requests are not too disruptive - no - * OOM killer and no allocation failure warnings as we have a fallback. + * However make sure that larger requests are not too disruptive - i.e. + * do not direct reclaim unless physically continuous memory is preferred + * (__GFP_RETRY_MAYFAIL mode). We still kick in kswapd/kcompactd to + * start working in the background */ if (size > PAGE_SIZE) { flags |= __GFP_NOWARN; if (!(flags & __GFP_RETRY_MAYFAIL)) - flags |= __GFP_NORETRY; + flags &= ~__GFP_DIRECT_RECLAIM; /* nofail semantic is implemented by the vmalloc fallback */ flags &= ~__GFP_NOFAIL; diff --git a/mm/swap.h b/mm/swap.h index 2269eb9df0af..9096082a915e 100644 --- a/mm/swap.h +++ b/mm/swap.h @@ -106,6 +106,25 @@ static inline int swap_zeromap_batch(swp_entry_t entry, int max_nr, return find_next_bit(sis->zeromap, end, start) - start; } +static inline int non_swapcache_batch(swp_entry_t entry, int max_nr) +{ + struct swap_info_struct *si = swp_swap_info(entry); + pgoff_t offset = swp_offset(entry); + int i; + + /* + * While allocating a large folio and doing mTHP swapin, we need to + * ensure all entries are not cached, otherwise, the mTHP folio will + * be in conflict with the folio in swap cache. + */ + for (i = 0; i < max_nr; i++) { + if ((si->swap_map[offset + i] & SWAP_HAS_CACHE)) + return i; + } + + return i; +} + #else /* CONFIG_SWAP */ struct swap_iocb; static inline void swap_read_folio(struct folio *folio, struct swap_iocb **plug) @@ -199,6 +218,10 @@ static inline int swap_zeromap_batch(swp_entry_t entry, int max_nr, return 0; } +static inline int non_swapcache_batch(swp_entry_t entry, int max_nr) +{ + return 0; +} #endif /* CONFIG_SWAP */ /** diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index bc473ad21202..8253978ee0fb 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -1084,8 +1084,18 @@ static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma, pte_t orig_dst_pte, pte_t orig_src_pte, pmd_t *dst_pmd, pmd_t dst_pmdval, spinlock_t *dst_ptl, spinlock_t *src_ptl, - struct folio *src_folio) + struct folio *src_folio, + struct swap_info_struct *si, swp_entry_t entry) { + /* + * Check if the folio still belongs to the target swap entry after + * acquiring the lock. Folio can be freed in the swap cache while + * not locked. + */ + if (src_folio && unlikely(!folio_test_swapcache(src_folio) || + entry.val != src_folio->swap.val)) + return -EAGAIN; + double_pt_lock(dst_ptl, src_ptl); if (!is_pte_pages_stable(dst_pte, src_pte, orig_dst_pte, orig_src_pte, @@ -1102,6 +1112,25 @@ static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma, if (src_folio) { folio_move_anon_rmap(src_folio, dst_vma); src_folio->index = linear_page_index(dst_vma, dst_addr); + } else { + /* + * Check if the swap entry is cached after acquiring the src_pte + * lock. Otherwise, we might miss a newly loaded swap cache folio. + * + * Check swap_map directly to minimize overhead, READ_ONCE is sufficient. + * We are trying to catch newly added swap cache, the only possible case is + * when a folio is swapped in and out again staying in swap cache, using the + * same entry before the PTE check above. The PTL is acquired and released + * twice, each time after updating the swap_map's flag. So holding + * the PTL here ensures we see the updated value. False positive is possible, + * e.g. SWP_SYNCHRONOUS_IO swapin may set the flag without touching the + * cache, or during the tiny synchronization window between swap cache and + * swap_map, but it will be gone very quickly, worst result is retry jitters. + */ + if (READ_ONCE(si->swap_map[swp_offset(entry)]) & SWAP_HAS_CACHE) { + double_pt_unlock(dst_ptl, src_ptl); + return -EAGAIN; + } } orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte); @@ -1412,7 +1441,7 @@ retry: } err = move_swap_pte(mm, dst_vma, dst_addr, src_addr, dst_pte, src_pte, orig_dst_pte, orig_src_pte, dst_pmd, dst_pmdval, - dst_ptl, src_ptl, src_folio); + dst_ptl, src_ptl, src_folio, si, entry); } out: diff --git a/mm/util.c b/mm/util.c index 448117da071f..0b270c43d7d1 100644 --- a/mm/util.c +++ b/mm/util.c @@ -1131,3 +1131,43 @@ void flush_dcache_folio(struct folio *folio) } EXPORT_SYMBOL(flush_dcache_folio); #endif + +/** + * compat_vma_mmap_prepare() - Apply the file's .mmap_prepare() hook to an + * existing VMA + * @file: The file which possesss an f_op->mmap_prepare() hook + * @vma: The VMA to apply the .mmap_prepare() hook to. + * + * Ordinarily, .mmap_prepare() is invoked directly upon mmap(). However, certain + * 'wrapper' file systems invoke a nested mmap hook of an underlying file. + * + * Until all filesystems are converted to use .mmap_prepare(), we must be + * conservative and continue to invoke these 'wrapper' filesystems using the + * deprecated .mmap() hook. + * + * However we have a problem if the underlying file system possesses an + * .mmap_prepare() hook, as we are in a different context when we invoke the + * .mmap() hook, already having a VMA to deal with. + * + * compat_vma_mmap_prepare() is a compatibility function that takes VMA state, + * establishes a struct vm_area_desc descriptor, passes to the underlying + * .mmap_prepare() hook and applies any changes performed by it. + * + * Once the conversion of filesystems is complete this function will no longer + * be required and will be removed. + * + * Returns: 0 on success or error. + */ +int compat_vma_mmap_prepare(struct file *file, struct vm_area_struct *vma) +{ + struct vm_area_desc desc; + int err; + + err = file->f_op->mmap_prepare(vma_to_desc(vma, &desc)); + if (err) + return err; + set_vma_from_desc(vma, &desc); + + return 0; +} +EXPORT_SYMBOL(compat_vma_mmap_prepare); @@ -169,6 +169,9 @@ static void init_multi_vma_prep(struct vma_prepare *vp, vp->file = vma->vm_file; if (vp->file) vp->mapping = vma->vm_file->f_mapping; + + if (vmg && vmg->skip_vma_uprobe) + vp->skip_vma_uprobe = true; } /* @@ -358,10 +361,13 @@ static void vma_complete(struct vma_prepare *vp, struct vma_iterator *vmi, if (vp->file) { i_mmap_unlock_write(vp->mapping); - uprobe_mmap(vp->vma); - if (vp->adj_next) - uprobe_mmap(vp->adj_next); + if (!vp->skip_vma_uprobe) { + uprobe_mmap(vp->vma); + + if (vp->adj_next) + uprobe_mmap(vp->adj_next); + } } if (vp->remove) { @@ -539,7 +545,14 @@ __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, init_vma_prep(&vp, vma); vp.insert = new; vma_prepare(&vp); + + /* + * Get rid of huge pages and shared page tables straddling the split + * boundary. + */ vma_adjust_trans_huge(vma, vma->vm_start, addr, NULL); + if (is_vm_hugetlb_page(vma)) + hugetlb_split(vma, addr); if (new_below) { vma->vm_start = addr; @@ -954,26 +967,9 @@ static __must_check struct vm_area_struct *vma_merge_existing_range( err = dup_anon_vma(next, middle, &anon_dup); } - if (err) + if (err || commit_merge(vmg)) goto abort; - err = commit_merge(vmg); - if (err) { - VM_WARN_ON(err != -ENOMEM); - - if (anon_dup) - unlink_anon_vmas(anon_dup); - - /* - * We've cleaned up any cloned anon_vma's, no VMAs have been - * modified, no harm no foul if the user requests that we not - * report this and just give up, leaving the VMAs unmerged. - */ - if (!vmg->give_up_on_oom) - vmg->state = VMA_MERGE_ERROR_NOMEM; - return NULL; - } - khugepaged_enter_vma(vmg->target, vmg->flags); vmg->state = VMA_MERGE_SUCCESS; return vmg->target; @@ -982,6 +978,9 @@ abort: vma_iter_set(vmg->vmi, start); vma_iter_load(vmg->vmi); + if (anon_dup) + unlink_anon_vmas(anon_dup); + /* * This means we have failed to clone anon_vma's correctly, but no * actual changes to VMAs have occurred, so no harm no foul - if the @@ -1823,6 +1822,14 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, faulted_in_anon_vma = false; } + /* + * If the VMA we are copying might contain a uprobe PTE, ensure + * that we do not establish one upon merge. Otherwise, when mremap() + * moves page tables, it will orphan the newly created PTE. + */ + if (vma->vm_file) + vmg.skip_vma_uprobe = true; + new_vma = find_vma_prev(mm, addr, &vmg.prev); if (new_vma && new_vma->vm_start < addr + len) return NULL; /* should never get here */ @@ -3106,7 +3113,6 @@ int __vm_munmap(unsigned long start, size_t len, bool unlock) return ret; } - /* Insert vm structure into process list sorted by address * and into the inode's i_mmap tree. If vm_file is non-NULL * then i_mmap_rwsem is taken here. @@ -19,6 +19,8 @@ struct vma_prepare { struct vm_area_struct *insert; struct vm_area_struct *remove; struct vm_area_struct *remove2; + + bool skip_vma_uprobe :1; }; struct unlink_vma_file_batch { @@ -120,6 +122,11 @@ struct vma_merge_struct { */ bool give_up_on_oom :1; + /* + * If set, skip uprobe_mmap upon merged vma. + */ + bool skip_vma_uprobe :1; + /* Internal flags set during merge process: */ /* @@ -215,6 +222,53 @@ static inline int vma_iter_store_gfp(struct vma_iterator *vmi, return 0; } + +/* + * Temporary helper functions for file systems which wrap an invocation of + * f_op->mmap() but which might have an underlying file system which implements + * f_op->mmap_prepare(). + */ + +static inline struct vm_area_desc *vma_to_desc(struct vm_area_struct *vma, + struct vm_area_desc *desc) +{ + desc->mm = vma->vm_mm; + desc->start = vma->vm_start; + desc->end = vma->vm_end; + + desc->pgoff = vma->vm_pgoff; + desc->file = vma->vm_file; + desc->vm_flags = vma->vm_flags; + desc->page_prot = vma->vm_page_prot; + + desc->vm_ops = NULL; + desc->private_data = NULL; + + return desc; +} + +static inline void set_vma_from_desc(struct vm_area_struct *vma, + struct vm_area_desc *desc) +{ + /* + * Since we're invoking .mmap_prepare() despite having a partially + * established VMA, we must take care to handle setting fields + * correctly. + */ + + /* Mutable fields. Populated with initial state. */ + vma->vm_pgoff = desc->pgoff; + if (vma->vm_file != desc->file) + vma_set_file(vma, desc->file); + if (vma->vm_flags != desc->vm_flags) + vm_flags_set(vma, desc->vm_flags); + vma->vm_page_prot = desc->page_prot; + + /* User-defined fields. */ + vma->vm_ops = desc->vm_ops; + vma->vm_private_data = desc->private_data; +} + int do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, struct mm_struct *mm, unsigned long start, diff --git a/mm/vmstat.c b/mm/vmstat.c index 6f740f070b3d..429ae5339bfe 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1201,7 +1201,6 @@ const char * const vmstat_text[] = { "nr_zone_unevictable", "nr_zone_write_pending", "nr_mlock", - "nr_bounce", #if IS_ENABLED(CONFIG_ZSMALLOC) "nr_zspages", #endif |