diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/compaction.c | 3 | ||||
| -rw-r--r-- | mm/filemap.c | 93 | ||||
| -rw-r--r-- | mm/hugetlb.c | 8 | ||||
| -rw-r--r-- | mm/internal.h | 5 | ||||
| -rw-r--r-- | mm/kmsan/hooks.c | 1 | ||||
| -rw-r--r-- | mm/memory-failure.c | 63 | ||||
| -rw-r--r-- | mm/memory.c | 40 | ||||
| -rw-r--r-- | mm/memory_hotplug.c | 26 | ||||
| -rw-r--r-- | mm/nommu.c | 7 | ||||
| -rw-r--r-- | mm/page_alloc.c | 4 | ||||
| -rw-r--r-- | mm/page_isolation.c | 10 | ||||
| -rw-r--r-- | mm/readahead.c | 14 | ||||
| -rw-r--r-- | mm/shmem.c | 39 | ||||
| -rw-r--r-- | mm/slab_common.c | 14 | ||||
| -rw-r--r-- | mm/swapfile.c | 12 | ||||
| -rw-r--r-- | mm/userfaultfd.c | 107 | ||||
| -rw-r--r-- | mm/util.c | 3 | ||||
| -rw-r--r-- | mm/vma.c | 12 | ||||
| -rw-r--r-- | mm/vmalloc.c | 4 | ||||
| -rw-r--r-- | mm/zswap.c | 2 |
20 files changed, 242 insertions, 225 deletions
diff --git a/mm/compaction.c b/mm/compaction.c index 12ed8425fa17..a3203d97123e 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -3181,6 +3181,7 @@ static int kcompactd(void *p) long default_timeout = msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC); long timeout = default_timeout; + current->flags |= PF_KCOMPACTD; set_freezable(); pgdat->kcompactd_max_order = 0; @@ -3237,6 +3238,8 @@ static int kcompactd(void *p) pgdat->proactive_compact_trigger = false; } + current->flags &= ~PF_KCOMPACTD; + return 0; } diff --git a/mm/filemap.c b/mm/filemap.c index d4564a79eb35..6d616bb9001e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -47,7 +47,6 @@ #include <linux/splice.h> #include <linux/rcupdate_wait.h> #include <linux/sched/mm.h> -#include <linux/fsnotify.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> #include "internal.h" @@ -2897,8 +2896,7 @@ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, size = min(size, folio_size(folio) - offset); offset %= PAGE_SIZE; - while (spliced < size && - !pipe_full(pipe->head, pipe->tail, pipe->max_usage)) { + while (spliced < size && !pipe_is_full(pipe)) { struct pipe_buffer *buf = pipe_head_buf(pipe); size_t part = min_t(size_t, PAGE_SIZE - offset, size - spliced); @@ -2955,7 +2953,7 @@ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, iocb.ki_pos = *ppos; /* Work out how much data we can actually add into the pipe */ - used = pipe_occupancy(pipe->head, pipe->tail); + used = pipe_buf_usage(pipe); npages = max_t(ssize_t, pipe->max_usage - used, 0); len = min_t(size_t, len, npages * PAGE_SIZE); @@ -3015,7 +3013,7 @@ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, total_spliced += n; *ppos += n; in->f_ra.prev_pos = *ppos; - if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) + if (pipe_is_full(pipe)) goto out; } @@ -3199,14 +3197,6 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) unsigned long vm_flags = vmf->vma->vm_flags; unsigned int mmap_miss; - /* - * If we have pre-content watches we need to disable readahead to make - * sure that we don't populate our mapping with 0 filled pages that we - * never emitted an event for. - */ - if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) - return fpin; - #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* Use the readahead code, even if readahead is disabled */ if ((vm_flags & VM_HUGEPAGE) && HPAGE_PMD_ORDER <= MAX_PAGECACHE_ORDER) { @@ -3275,10 +3265,6 @@ static struct file *do_async_mmap_readahead(struct vm_fault *vmf, struct file *fpin = NULL; unsigned int mmap_miss; - /* See comment in do_sync_mmap_readahead. */ - if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) - return fpin; - /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages) return fpin; @@ -3338,48 +3324,6 @@ static vm_fault_t filemap_fault_recheck_pte_none(struct vm_fault *vmf) } /** - * filemap_fsnotify_fault - maybe emit a pre-content event. - * @vmf: struct vm_fault containing details of the fault. - * - * If we have a pre-content watch on this file we will emit an event for this - * range. If we return anything the fault caller should return immediately, we - * will return VM_FAULT_RETRY if we had to emit an event, which will trigger the - * fault again and then the fault handler will run the second time through. - * - * Return: a bitwise-OR of %VM_FAULT_ codes, 0 if nothing happened. - */ -vm_fault_t filemap_fsnotify_fault(struct vm_fault *vmf) -{ - struct file *fpin = NULL; - int mask = (vmf->flags & FAULT_FLAG_WRITE) ? MAY_WRITE : MAY_ACCESS; - loff_t pos = vmf->pgoff >> PAGE_SHIFT; - size_t count = PAGE_SIZE; - int err; - - /* - * We already did this and now we're retrying with everything locked, - * don't emit the event and continue. - */ - if (vmf->flags & FAULT_FLAG_TRIED) - return 0; - - /* No watches, we're done. */ - if (likely(!FMODE_FSNOTIFY_HSM(vmf->vma->vm_file->f_mode))) - return 0; - - fpin = maybe_unlock_mmap_for_io(vmf, fpin); - if (!fpin) - return VM_FAULT_SIGBUS; - - err = fsnotify_file_area_perm(fpin, mask, &pos, count); - fput(fpin); - if (err) - return VM_FAULT_SIGBUS; - return VM_FAULT_RETRY; -} -EXPORT_SYMBOL_GPL(filemap_fsnotify_fault); - -/** * filemap_fault - read in file data for page fault handling * @vmf: struct vm_fault containing details of the fault * @@ -3483,37 +3427,6 @@ retry_find: */ if (unlikely(!folio_test_uptodate(folio))) { /* - * If this is a precontent file we have can now emit an event to - * try and populate the folio. - */ - if (!(vmf->flags & FAULT_FLAG_TRIED) && - unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) { - loff_t pos = folio_pos(folio); - size_t count = folio_size(folio); - - /* We're NOWAIT, we have to retry. */ - if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) { - folio_unlock(folio); - goto out_retry; - } - - if (mapping_locked) - filemap_invalidate_unlock_shared(mapping); - mapping_locked = false; - - folio_unlock(folio); - fpin = maybe_unlock_mmap_for_io(vmf, fpin); - if (!fpin) - goto out_retry; - - error = fsnotify_file_area_perm(fpin, MAY_ACCESS, &pos, - count); - if (error) - ret = VM_FAULT_SIGBUS; - goto out_retry; - } - - /* * If the invalidate lock is not held, the folio was in cache * and uptodate and now it is not. Strange but possible since we * didn't hold the page lock all the time. Let's drop diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 09d6673040ed..97930d44d460 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2943,6 +2943,14 @@ int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn) return ret; } +void wait_for_freed_hugetlb_folios(void) +{ + if (llist_empty(&hpage_freelist)) + return; + + flush_work(&free_hpage_work); +} + typedef enum { /* * For either 0/1: we checked the per-vma resv map, and one resv diff --git a/mm/internal.h b/mm/internal.h index 109ef30fee11..20b3535935a3 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -1115,7 +1115,7 @@ static inline int find_next_best_node(int node, nodemask_t *used_node_mask) * mm/memory-failure.c */ #ifdef CONFIG_MEMORY_FAILURE -void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu); +int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill); void shake_folio(struct folio *folio); extern int hwpoison_filter(struct page *p); @@ -1138,8 +1138,9 @@ unsigned long page_mapped_in_vma(const struct page *page, struct vm_area_struct *vma); #else -static inline void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu) +static inline int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill) { + return -EBUSY; } #endif diff --git a/mm/kmsan/hooks.c b/mm/kmsan/hooks.c index 3ea50f09311f..3df45c25c1f6 100644 --- a/mm/kmsan/hooks.c +++ b/mm/kmsan/hooks.c @@ -357,6 +357,7 @@ void kmsan_handle_dma(struct page *page, size_t offset, size_t size, size -= to_go; } } +EXPORT_SYMBOL_GPL(kmsan_handle_dma); void kmsan_handle_dma_sg(struct scatterlist *sg, int nents, enum dma_data_direction dir) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 995a15eb67e2..327e02fdc029 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1556,11 +1556,35 @@ static int get_hwpoison_page(struct page *p, unsigned long flags) return ret; } -void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu) +int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill) { - if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) { - struct address_space *mapping; + enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_HWPOISON; + struct address_space *mapping; + + if (folio_test_swapcache(folio)) { + pr_err("%#lx: keeping poisoned page in swap cache\n", pfn); + ttu &= ~TTU_HWPOISON; + } + /* + * Propagate the dirty bit from PTEs to struct page first, because we + * need this to decide if we should kill or just drop the page. + * XXX: the dirty test could be racy: set_page_dirty() may not always + * be called inside page lock (it's recommended but not enforced). + */ + mapping = folio_mapping(folio); + if (!must_kill && !folio_test_dirty(folio) && mapping && + mapping_can_writeback(mapping)) { + if (folio_mkclean(folio)) { + folio_set_dirty(folio); + } else { + ttu &= ~TTU_HWPOISON; + pr_info("%#lx: corrupted page was clean: dropped without side effects\n", + pfn); + } + } + + if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) { /* * For hugetlb folios in shared mappings, try_to_unmap * could potentially call huge_pmd_unshare. Because of @@ -1572,7 +1596,7 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu) if (!mapping) { pr_info("%#lx: could not lock mapping for mapped hugetlb folio\n", folio_pfn(folio)); - return; + return -EBUSY; } try_to_unmap(folio, ttu|TTU_RMAP_LOCKED); @@ -1580,6 +1604,8 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu) } else { try_to_unmap(folio, ttu); } + + return folio_mapped(folio) ? -EBUSY : 0; } /* @@ -1589,8 +1615,6 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu) static bool hwpoison_user_mappings(struct folio *folio, struct page *p, unsigned long pfn, int flags) { - enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_HWPOISON; - struct address_space *mapping; LIST_HEAD(tokill); bool unmap_success; int forcekill; @@ -1613,29 +1637,6 @@ static bool hwpoison_user_mappings(struct folio *folio, struct page *p, if (!folio_mapped(folio)) return true; - if (folio_test_swapcache(folio)) { - pr_err("%#lx: keeping poisoned page in swap cache\n", pfn); - ttu &= ~TTU_HWPOISON; - } - - /* - * Propagate the dirty bit from PTEs to struct page first, because we - * need this to decide if we should kill or just drop the page. - * XXX: the dirty test could be racy: set_page_dirty() may not always - * be called inside page lock (it's recommended but not enforced). - */ - mapping = folio_mapping(folio); - if (!(flags & MF_MUST_KILL) && !folio_test_dirty(folio) && mapping && - mapping_can_writeback(mapping)) { - if (folio_mkclean(folio)) { - folio_set_dirty(folio); - } else { - ttu &= ~TTU_HWPOISON; - pr_info("%#lx: corrupted page was clean: dropped without side effects\n", - pfn); - } - } - /* * First collect all the processes that have the page * mapped in dirty form. This has to be done before try_to_unmap, @@ -1643,9 +1644,7 @@ static bool hwpoison_user_mappings(struct folio *folio, struct page *p, */ collect_procs(folio, p, &tokill, flags & MF_ACTION_REQUIRED); - unmap_poisoned_folio(folio, ttu); - - unmap_success = !folio_mapped(folio); + unmap_success = !unmap_poisoned_folio(folio, pfn, flags & MF_MUST_KILL); if (!unmap_success) pr_err("%#lx: failed to unmap page (folio mapcount=%d)\n", pfn, folio_mapcount(folio)); diff --git a/mm/memory.c b/mm/memory.c index b4d3d4893267..fb7b8dc75167 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -76,7 +76,6 @@ #include <linux/ptrace.h> #include <linux/vmalloc.h> #include <linux/sched/sysctl.h> -#include <linux/fsnotify.h> #include <trace/events/kmem.h> @@ -3051,8 +3050,10 @@ static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr, next = pgd_addr_end(addr, end); if (pgd_none(*pgd) && !create) continue; - if (WARN_ON_ONCE(pgd_leaf(*pgd))) - return -EINVAL; + if (WARN_ON_ONCE(pgd_leaf(*pgd))) { + err = -EINVAL; + break; + } if (!pgd_none(*pgd) && WARN_ON_ONCE(pgd_bad(*pgd))) { if (!create) continue; @@ -5183,7 +5184,11 @@ vm_fault_t finish_fault(struct vm_fault *vmf) bool is_cow = (vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED); int type, nr_pages; - unsigned long addr = vmf->address; + unsigned long addr; + bool needs_fallback = false; + +fallback: + addr = vmf->address; /* Did we COW the page? */ if (is_cow) @@ -5222,7 +5227,8 @@ vm_fault_t finish_fault(struct vm_fault *vmf) * approach also applies to non-anonymous-shmem faults to avoid * inflating the RSS of the process. */ - if (!vma_is_anon_shmem(vma) || unlikely(userfaultfd_armed(vma))) { + if (!vma_is_anon_shmem(vma) || unlikely(userfaultfd_armed(vma)) || + unlikely(needs_fallback)) { nr_pages = 1; } else if (nr_pages > 1) { pgoff_t idx = folio_page_idx(folio, page); @@ -5258,9 +5264,9 @@ vm_fault_t finish_fault(struct vm_fault *vmf) ret = VM_FAULT_NOPAGE; goto unlock; } else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) { - update_mmu_tlb_range(vma, addr, vmf->pte, nr_pages); - ret = VM_FAULT_NOPAGE; - goto unlock; + needs_fallback = true; + pte_unmap_unlock(vmf->pte, vmf->ptl); + goto fallback; } folio_ref_add(folio, nr_pages - 1); @@ -5743,17 +5749,8 @@ out_map: static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; - if (vma_is_anonymous(vma)) return do_huge_pmd_anonymous_page(vmf); - /* - * Currently we just emit PAGE_SIZE for our fault events, so don't allow - * a huge fault if we have a pre content watch on this file. This would - * be trivial to support, but there would need to be tests to ensure - * this works properly and those don't exist currently. - */ - if (unlikely(FMODE_FSNOTIFY_HSM(vma->vm_file->f_mode))) - return VM_FAULT_FALLBACK; if (vma->vm_ops->huge_fault) return vma->vm_ops->huge_fault(vmf, PMD_ORDER); return VM_FAULT_FALLBACK; @@ -5777,9 +5774,6 @@ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf) } if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) { - /* See comment in create_huge_pmd. */ - if (unlikely(FMODE_FSNOTIFY_HSM(vma->vm_file->f_mode))) - goto split; if (vma->vm_ops->huge_fault) { ret = vma->vm_ops->huge_fault(vmf, PMD_ORDER); if (!(ret & VM_FAULT_FALLBACK)) @@ -5802,9 +5796,6 @@ static vm_fault_t create_huge_pud(struct vm_fault *vmf) /* No support for anonymous transparent PUD pages yet */ if (vma_is_anonymous(vma)) return VM_FAULT_FALLBACK; - /* See comment in create_huge_pmd. */ - if (unlikely(FMODE_FSNOTIFY_HSM(vma->vm_file->f_mode))) - return VM_FAULT_FALLBACK; if (vma->vm_ops->huge_fault) return vma->vm_ops->huge_fault(vmf, PUD_ORDER); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -5822,9 +5813,6 @@ static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) if (vma_is_anonymous(vma)) goto split; if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) { - /* See comment in create_huge_pmd. */ - if (unlikely(FMODE_FSNOTIFY_HSM(vma->vm_file->f_mode))) - goto split; if (vma->vm_ops->huge_fault) { ret = vma->vm_ops->huge_fault(vmf, PUD_ORDER); if (!(ret & VM_FAULT_FALLBACK)) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index e3655f07dd6e..16cf9e17077e 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1822,26 +1822,24 @@ static void do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) if (folio_test_large(folio)) pfn = folio_pfn(folio) + folio_nr_pages(folio) - 1; - /* - * HWPoison pages have elevated reference counts so the migration would - * fail on them. It also doesn't make any sense to migrate them in the - * first place. Still try to unmap such a page in case it is still mapped - * (keep the unmap as the catch all safety net). - */ + if (!folio_try_get(folio)) + continue; + + if (unlikely(page_folio(page) != folio)) + goto put_folio; + if (folio_test_hwpoison(folio) || (folio_test_large(folio) && folio_test_has_hwpoisoned(folio))) { if (WARN_ON(folio_test_lru(folio))) folio_isolate_lru(folio); - if (folio_mapped(folio)) - unmap_poisoned_folio(folio, TTU_IGNORE_MLOCK); - continue; - } - - if (!folio_try_get(folio)) - continue; + if (folio_mapped(folio)) { + folio_lock(folio); + unmap_poisoned_folio(folio, pfn, false); + folio_unlock(folio); + } - if (unlikely(page_folio(page) != folio)) goto put_folio; + } if (!isolate_folio_to_list(folio, &source)) { if (__ratelimit(&migrate_rs)) { diff --git a/mm/nommu.c b/mm/nommu.c index baa79abdaf03..9cb6e99215e2 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1613,13 +1613,6 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, } EXPORT_SYMBOL(remap_vmalloc_range); -vm_fault_t filemap_fsnotify_fault(struct vm_fault *vmf) -{ - BUG(); - return 0; -} -EXPORT_SYMBOL_GPL(filemap_fsnotify_fault); - vm_fault_t filemap_fault(struct vm_fault *vmf) { BUG(); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 579789600a3c..94917c729120 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4243,6 +4243,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, restart: compaction_retries = 0; no_progress_loops = 0; + compact_result = COMPACT_SKIPPED; compact_priority = DEF_COMPACT_PRIORITY; cpuset_mems_cookie = read_mems_allowed_begin(); zonelist_iter_cookie = zonelist_iter_begin(); @@ -5849,11 +5850,10 @@ static void setup_per_zone_lowmem_reserve(void) for (j = i + 1; j < MAX_NR_ZONES; j++) { struct zone *upper_zone = &pgdat->node_zones[j]; - bool empty = !zone_managed_pages(upper_zone); managed_pages += zone_managed_pages(upper_zone); - if (clear || empty) + if (clear) zone->lowmem_reserve[j] = 0; else zone->lowmem_reserve[j] = managed_pages / ratio; diff --git a/mm/page_isolation.c b/mm/page_isolation.c index c608e9d72865..a051a29e95ad 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -608,6 +608,16 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, int ret; /* + * Due to the deferred freeing of hugetlb folios, the hugepage folios may + * not immediately release to the buddy system. This can cause PageBuddy() + * to fail in __test_page_isolated_in_pageblock(). To ensure that the + * hugetlb folios are properly released back to the buddy system, we + * invoke the wait_for_freed_hugetlb_folios() function to wait for the + * release to complete. + */ + wait_for_freed_hugetlb_folios(); + + /* * Note: pageblock_nr_pages != MAX_PAGE_ORDER. Then, chunks of free * pages are not aligned to pageblock_nr_pages. * Then we just check migratetype first. diff --git a/mm/readahead.c b/mm/readahead.c index 220155a5c964..6a4e96b69702 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -128,7 +128,6 @@ #include <linux/blk-cgroup.h> #include <linux/fadvise.h> #include <linux/sched/mm.h> -#include <linux/fsnotify.h> #include "internal.h" @@ -559,15 +558,6 @@ void page_cache_sync_ra(struct readahead_control *ractl, pgoff_t prev_index, miss; /* - * If we have pre-content watches we need to disable readahead to make - * sure that we don't find 0 filled pages in cache that we never emitted - * events for. Filesystems supporting HSM must make sure to not call - * this function with ractl->file unset for files handled by HSM. - */ - if (ractl->file && unlikely(FMODE_FSNOTIFY_HSM(ractl->file->f_mode))) - return; - - /* * Even if readahead is disabled, issue this request as readahead * as we'll need it to satisfy the requested range. The forced * readahead will do the right thing and limit the read to just the @@ -645,10 +635,6 @@ void page_cache_async_ra(struct readahead_control *ractl, if (!ra->ra_pages) return; - /* See the comment in page_cache_sync_ra. */ - if (ractl->file && unlikely(FMODE_FSNOTIFY_HSM(ractl->file->f_mode))) - return; - /* * Same bit is used for PG_readahead and PG_reclaim. */ diff --git a/mm/shmem.c b/mm/shmem.c index 4ea6109a8043..1ede0800e846 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1548,7 +1548,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) if (WARN_ON_ONCE(!wbc->for_reclaim)) goto redirty; - if (WARN_ON_ONCE((info->flags & VM_LOCKED) || sbinfo->noswap)) + if ((info->flags & VM_LOCKED) || sbinfo->noswap) goto redirty; if (!total_swap_pages) @@ -2253,7 +2253,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, struct folio *folio = NULL; bool skip_swapcache = false; swp_entry_t swap; - int error, nr_pages; + int error, nr_pages, order, split_order; VM_BUG_ON(!*foliop || !xa_is_value(*foliop)); swap = radix_to_swp_entry(*foliop); @@ -2272,10 +2272,9 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, /* Look it up and read it in.. */ folio = swap_cache_get_folio(swap, NULL, 0); + order = xa_get_order(&mapping->i_pages, index); if (!folio) { - int order = xa_get_order(&mapping->i_pages, index); bool fallback_order0 = false; - int split_order; /* Or update major stats only when swapin succeeds?? */ if (fault_type) { @@ -2339,6 +2338,29 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, error = -ENOMEM; goto failed; } + } else if (order != folio_order(folio)) { + /* + * Swap readahead may swap in order 0 folios into swapcache + * asynchronously, while the shmem mapping can still stores + * large swap entries. In such cases, we should split the + * large swap entry to prevent possible data corruption. + */ + split_order = shmem_split_large_entry(inode, index, swap, gfp); + if (split_order < 0) { + error = split_order; + goto failed; + } + + /* + * If the large swap entry has already been split, it is + * necessary to recalculate the new swap entry based on + * the old order alignment. + */ + if (split_order > 0) { + pgoff_t offset = index - round_down(index, 1 << split_order); + + swap = swp_entry(swp_type(swap), swp_offset(swap) + offset); + } } alloced: @@ -2346,7 +2368,8 @@ alloced: folio_lock(folio); if ((!skip_swapcache && !folio_test_swapcache(folio)) || folio->swap.val != swap.val || - !shmem_confirm_swap(mapping, index, swap)) { + !shmem_confirm_swap(mapping, index, swap) || + xa_get_order(&mapping->i_pages, index) != folio_order(folio)) { error = -EEXIST; goto unlock; } @@ -3487,7 +3510,7 @@ static size_t splice_zeropage_into_pipe(struct pipe_inode_info *pipe, size = min_t(size_t, size, PAGE_SIZE - offset); - if (!pipe_full(pipe->head, pipe->tail, pipe->max_usage)) { + if (!pipe_is_full(pipe)) { struct pipe_buffer *buf = pipe_head_buf(pipe); *buf = (struct pipe_buffer) { @@ -3514,7 +3537,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, int error = 0; /* Work out how much data we can actually add into the pipe */ - used = pipe_occupancy(pipe->head, pipe->tail); + used = pipe_buf_usage(pipe); npages = max_t(ssize_t, pipe->max_usage - used, 0); len = min_t(size_t, len, npages * PAGE_SIZE); @@ -3601,7 +3624,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, total_spliced += n; *ppos += n; in->f_ra.prev_pos = *ppos; - if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) + if (pipe_is_full(pipe)) break; cond_resched(); diff --git a/mm/slab_common.c b/mm/slab_common.c index 4030907b6b7d..4c9f0a87f733 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -1304,6 +1304,8 @@ module_param(rcu_min_cached_objs, int, 0444); static int rcu_delay_page_cache_fill_msec = 5000; module_param(rcu_delay_page_cache_fill_msec, int, 0444); +static struct workqueue_struct *rcu_reclaim_wq; + /* Maximum number of jiffies to wait before draining a batch. */ #define KFREE_DRAIN_JIFFIES (5 * HZ) #define KFREE_N_BATCHES 2 @@ -1632,10 +1634,10 @@ __schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp) if (delayed_work_pending(&krcp->monitor_work)) { delay_left = krcp->monitor_work.timer.expires - jiffies; if (delay < delay_left) - mod_delayed_work(system_unbound_wq, &krcp->monitor_work, delay); + mod_delayed_work(rcu_reclaim_wq, &krcp->monitor_work, delay); return; } - queue_delayed_work(system_unbound_wq, &krcp->monitor_work, delay); + queue_delayed_work(rcu_reclaim_wq, &krcp->monitor_work, delay); } static void @@ -1733,7 +1735,7 @@ kvfree_rcu_queue_batch(struct kfree_rcu_cpu *krcp) // "free channels", the batch can handle. Break // the loop since it is done with this CPU thus // queuing an RCU work is _always_ success here. - queued = queue_rcu_work(system_unbound_wq, &krwp->rcu_work); + queued = queue_rcu_work(rcu_reclaim_wq, &krwp->rcu_work); WARN_ON_ONCE(!queued); break; } @@ -1883,7 +1885,7 @@ run_page_cache_worker(struct kfree_rcu_cpu *krcp) if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING && !atomic_xchg(&krcp->work_in_progress, 1)) { if (atomic_read(&krcp->backoff_page_cache_fill)) { - queue_delayed_work(system_unbound_wq, + queue_delayed_work(rcu_reclaim_wq, &krcp->page_cache_work, msecs_to_jiffies(rcu_delay_page_cache_fill_msec)); } else { @@ -2120,6 +2122,10 @@ void __init kvfree_rcu_init(void) int i, j; struct shrinker *kfree_rcu_shrinker; + rcu_reclaim_wq = alloc_workqueue("kvfree_rcu_reclaim", + WQ_UNBOUND | WQ_MEM_RECLAIM, 0); + WARN_ON(!rcu_reclaim_wq); + /* Clamp it to [0:100] seconds interval. */ if (rcu_delay_page_cache_fill_msec < 0 || rcu_delay_page_cache_fill_msec > 100 * MSEC_PER_SEC) { diff --git a/mm/swapfile.c b/mm/swapfile.c index ba19430dd4ea..df7c4e8b089c 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -653,7 +653,8 @@ static void relocate_cluster(struct swap_info_struct *si, return; if (!ci->count) { - free_cluster(si, ci); + if (ci->flags != CLUSTER_FLAG_FREE) + free_cluster(si, ci); } else if (ci->count != SWAPFILE_CLUSTER) { if (ci->flags != CLUSTER_FLAG_FRAG) move_cluster(si, ci, &si->frag_clusters[ci->order], @@ -858,6 +859,10 @@ static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force) offset++; } + /* in case no swap cache is reclaimed */ + if (ci->flags == CLUSTER_FLAG_NONE) + relocate_cluster(si, ci); + unlock_cluster(ci); if (to_scan <= 0) break; @@ -2641,7 +2646,6 @@ static void wait_for_allocation(struct swap_info_struct *si) for (offset = 0; offset < end; offset += SWAPFILE_CLUSTER) { ci = lock_cluster(si, offset); unlock_cluster(ci); - offset += SWAPFILE_CLUSTER; } } @@ -3542,6 +3546,10 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr) int err, i; si = swp_swap_info(entry); + if (WARN_ON_ONCE(!si)) { + pr_err("%s%08lx\n", Bad_file, entry.val); + return -EINVAL; + } offset = swp_offset(entry); VM_WARN_ON(nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index af3dfc3633db..d06453fa8aba 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -18,6 +18,7 @@ #include <asm/tlbflush.h> #include <asm/tlb.h> #include "internal.h" +#include "swap.h" static __always_inline bool validate_dst_vma(struct vm_area_struct *dst_vma, unsigned long dst_end) @@ -1076,16 +1077,14 @@ out: return err; } -static int move_swap_pte(struct mm_struct *mm, +static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, pte_t *dst_pte, pte_t *src_pte, 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) + spinlock_t *dst_ptl, spinlock_t *src_ptl, + struct folio *src_folio) { - if (!pte_swp_exclusive(orig_src_pte)) - return -EBUSY; - double_pt_lock(dst_ptl, src_ptl); if (!is_pte_pages_stable(dst_pte, src_pte, orig_dst_pte, orig_src_pte, @@ -1094,6 +1093,16 @@ static int move_swap_pte(struct mm_struct *mm, return -EAGAIN; } + /* + * The src_folio resides in the swapcache, requiring an update to its + * index and mapping to align with the dst_vma, where a swap-in may + * occur and hit the swapcache after moving the PTE. + */ + if (src_folio) { + folio_move_anon_rmap(src_folio, dst_vma); + src_folio->index = linear_page_index(dst_vma, dst_addr); + } + orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte); set_pte_at(mm, dst_addr, dst_pte, orig_src_pte); double_pt_unlock(dst_ptl, src_ptl); @@ -1141,6 +1150,7 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, __u64 mode) { swp_entry_t entry; + struct swap_info_struct *si = NULL; pte_t orig_src_pte, orig_dst_pte; pte_t src_folio_pte; spinlock_t *src_ptl, *dst_ptl; @@ -1240,6 +1250,7 @@ retry: */ if (!src_folio) { struct folio *folio; + bool locked; /* * Pin the page while holding the lock to be sure the @@ -1259,14 +1270,28 @@ retry: goto out; } + locked = folio_trylock(folio); + /* + * We avoid waiting for folio lock with a raised + * refcount for large folios because extra refcounts + * will result in split_folio() failing later and + * retrying. If multiple tasks are trying to move a + * large folio we can end up livelocking. + */ + if (!locked && folio_test_large(folio)) { + spin_unlock(src_ptl); + err = -EAGAIN; + goto out; + } + folio_get(folio); src_folio = folio; src_folio_pte = orig_src_pte; spin_unlock(src_ptl); - if (!folio_trylock(src_folio)) { - pte_unmap(&orig_src_pte); - pte_unmap(&orig_dst_pte); + if (!locked) { + pte_unmap(src_pte); + pte_unmap(dst_pte); src_pte = dst_pte = NULL; /* now we can block and wait */ folio_lock(src_folio); @@ -1282,8 +1307,8 @@ retry: /* at this point we have src_folio locked */ if (folio_test_large(src_folio)) { /* split_folio() can block */ - pte_unmap(&orig_src_pte); - pte_unmap(&orig_dst_pte); + pte_unmap(src_pte); + pte_unmap(dst_pte); src_pte = dst_pte = NULL; err = split_folio(src_folio); if (err) @@ -1308,8 +1333,8 @@ retry: goto out; } if (!anon_vma_trylock_write(src_anon_vma)) { - pte_unmap(&orig_src_pte); - pte_unmap(&orig_dst_pte); + pte_unmap(src_pte); + pte_unmap(dst_pte); src_pte = dst_pte = NULL; /* now we can block and wait */ anon_vma_lock_write(src_anon_vma); @@ -1322,11 +1347,13 @@ retry: orig_dst_pte, orig_src_pte, dst_pmd, dst_pmdval, dst_ptl, src_ptl, src_folio); } else { + struct folio *folio = NULL; + entry = pte_to_swp_entry(orig_src_pte); if (non_swap_entry(entry)) { if (is_migration_entry(entry)) { - pte_unmap(&orig_src_pte); - pte_unmap(&orig_dst_pte); + pte_unmap(src_pte); + pte_unmap(dst_pte); src_pte = dst_pte = NULL; migration_entry_wait(mm, src_pmd, src_addr); err = -EAGAIN; @@ -1335,9 +1362,53 @@ retry: goto out; } - err = move_swap_pte(mm, dst_addr, src_addr, dst_pte, src_pte, - orig_dst_pte, orig_src_pte, dst_pmd, - dst_pmdval, dst_ptl, src_ptl); + if (!pte_swp_exclusive(orig_src_pte)) { + err = -EBUSY; + goto out; + } + + si = get_swap_device(entry); + if (unlikely(!si)) { + err = -EAGAIN; + goto out; + } + /* + * Verify the existence of the swapcache. If present, the folio's + * index and mapping must be updated even when the PTE is a swap + * entry. The anon_vma lock is not taken during this process since + * the folio has already been unmapped, and the swap entry is + * exclusive, preventing rmap walks. + * + * For large folios, return -EBUSY immediately, as split_folio() + * also returns -EBUSY when attempting to split unmapped large + * folios in the swapcache. This issue needs to be resolved + * separately to allow proper handling. + */ + if (!src_folio) + folio = filemap_get_folio(swap_address_space(entry), + swap_cache_index(entry)); + if (!IS_ERR_OR_NULL(folio)) { + if (folio_test_large(folio)) { + err = -EBUSY; + folio_put(folio); + goto out; + } + src_folio = folio; + src_folio_pte = orig_src_pte; + if (!folio_trylock(src_folio)) { + pte_unmap(src_pte); + pte_unmap(dst_pte); + src_pte = dst_pte = NULL; + put_swap_device(si); + si = NULL; + /* now we can block and wait */ + folio_lock(src_folio); + goto 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); } out: @@ -1354,6 +1425,8 @@ out: if (src_pte) pte_unmap(src_pte); mmu_notifier_invalidate_range_end(&range); + if (si) + put_swap_device(si); return err; } diff --git a/mm/util.c b/mm/util.c index b6b9684a1438..8c965474d329 100644 --- a/mm/util.c +++ b/mm/util.c @@ -23,6 +23,7 @@ #include <linux/processor.h> #include <linux/sizes.h> #include <linux/compat.h> +#include <linux/fsnotify.h> #include <linux/uaccess.h> @@ -569,6 +570,8 @@ unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr, LIST_HEAD(uf); ret = security_mmap_file(file, prot, flag); + if (!ret) + ret = fsnotify_mmap_perm(file, prot, pgoff >> PAGE_SHIFT, len); if (!ret) { if (mmap_write_lock_killable(mm)) return -EINTR; @@ -1509,24 +1509,28 @@ int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, static struct vm_area_struct *vma_modify(struct vma_merge_struct *vmg) { struct vm_area_struct *vma = vmg->vma; + unsigned long start = vmg->start; + unsigned long end = vmg->end; struct vm_area_struct *merged; /* First, try to merge. */ merged = vma_merge_existing_range(vmg); if (merged) return merged; + if (vmg_nomem(vmg)) + return ERR_PTR(-ENOMEM); /* Split any preceding portion of the VMA. */ - if (vma->vm_start < vmg->start) { - int err = split_vma(vmg->vmi, vma, vmg->start, 1); + if (vma->vm_start < start) { + int err = split_vma(vmg->vmi, vma, start, 1); if (err) return ERR_PTR(err); } /* Split any trailing portion of the VMA. */ - if (vma->vm_end > vmg->end) { - int err = split_vma(vmg->vmi, vma, vmg->end, 0); + if (vma->vm_end > end) { + int err = split_vma(vmg->vmi, vma, end, 0); if (err) return ERR_PTR(err); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index a6e7acebe9ad..61981ee1c9d2 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -586,13 +586,13 @@ static int vmap_small_pages_range_noflush(unsigned long addr, unsigned long end, mask |= PGTBL_PGD_MODIFIED; err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr, &mask); if (err) - return err; + break; } while (pgd++, addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, end); - return 0; + return err; } /* diff --git a/mm/zswap.c b/mm/zswap.c index ac9d299e7d0c..23365e76a3ce 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -43,7 +43,7 @@ * statistics **********************************/ /* The number of compressed pages currently stored in zswap */ -atomic_long_t zswap_stored_pages = ATOMIC_INIT(0); +atomic_long_t zswap_stored_pages = ATOMIC_LONG_INIT(0); /* * The statistics below are not protected from concurrent access for |