diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 6a33288bd6a1..83d3ac97f826 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -170,6 +170,21 @@ static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, return fsnotify_path(&file->f_path, FS_ACCESS_PERM); } +/* + * fsnotify_mmap_perm - permission hook before mmap of file range + */ +static inline int fsnotify_mmap_perm(struct file *file, int prot, + const loff_t off, size_t len) +{ + /* + * mmap() generates only pre-content events. + */ + if (!file || likely(!FMODE_FSNOTIFY_HSM(file->f_mode))) + return 0; + + return fsnotify_pre_content(&file->f_path, &off, len); +} + /* * fsnotify_truncate_perm - permission hook before file truncate */ @@ -223,6 +238,12 @@ static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, return 0; } +static inline int fsnotify_mmap_perm(struct file *file, int prot, + const loff_t off, size_t len) +{ + return 0; +} + static inline int fsnotify_truncate_perm(const struct path *path, loff_t length) { return 0; 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 #include #include +#include #include @@ -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; -- knotmirror 0.0.1 From bc71aab4513f7fecd23c051703ef5adea2230a54 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 12 Mar 2025 08:38:48 +0100 Subject: [PATCH 2/6] Revert "ext4: add pre-content fsnotify hook for DAX faults" This reverts commit bb480760ffc7018e21ee6f60241c2b99ff26ee0e. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara Link: https://patch.msgid.link/20250312073852.2123409-3-amir73il@gmail.com --- fs/ext4/file.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/fs/ext4/file.c b/fs/ext4/file.c index a5205149adba..3bd96c3d4cd0 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -756,9 +756,6 @@ retry: return VM_FAULT_SIGBUS; } } else { - result = filemap_fsnotify_fault(vmf); - if (unlikely(result)) - return result; filemap_invalidate_lock_shared(mapping); } result = dax_iomap_fault(vmf, order, &pfn, &error, &ext4_iomap_ops); -- knotmirror 0.0.1 From 27773ce1776279ed3220a34d2e6bfcecaee7fc66 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 12 Mar 2025 08:38:49 +0100 Subject: [PATCH 3/6] Revert "xfs: add pre-content fsnotify hook for DAX faults" This reverts commit 7f4796a46571ced5d3d5b0942e1bfea1eedaaecd. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara Link: https://patch.msgid.link/20250312073852.2123409-4-amir73il@gmail.com --- fs/xfs/xfs_file.c | 13 ------------- 1 file changed, 13 deletions(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index f7a7d89c345e..9a435b1ff264 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1451,9 +1451,6 @@ xfs_dax_read_fault( trace_xfs_read_fault(ip, order); - ret = filemap_fsnotify_fault(vmf); - if (unlikely(ret)) - return ret; xfs_ilock(ip, XFS_MMAPLOCK_SHARED); ret = xfs_dax_fault_locked(vmf, order, false); xfs_iunlock(ip, XFS_MMAPLOCK_SHARED); @@ -1482,16 +1479,6 @@ xfs_write_fault( vm_fault_t ret; trace_xfs_write_fault(ip, order); - /* - * Usually we get here from ->page_mkwrite callback but in case of DAX - * we will get here also for ordinary write fault. Handle HSM - * notifications for that case. - */ - if (IS_DAX(inode)) { - ret = filemap_fsnotify_fault(vmf); - if (unlikely(ret)) - return ret; - } sb_start_pagefault(inode->i_sb); file_update_time(vmf->vma->vm_file); -- knotmirror 0.0.1 From 955fbe0ef19df4197595a98d0906c94025c4beef Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 12 Mar 2025 08:38:50 +0100 Subject: [PATCH 4/6] Revert "fsnotify: generate pre-content permission event on page fault" This reverts commit 8392bc2ff8c8bf7c4c5e6dfa71ccd893a3c046f6. In the use case of buffered write whose input buffer is mmapped file on a filesystem with a pre-content mark, the prefaulting of the buffer can happen under the filesystem freeze protection (obtained in vfs_write()) which breaks assumptions of pre-content hook and introduces potential deadlock of HSM handler in userspace with filesystem freezing. Now that we have pre-content hooks at file mmap() time, disable the pre-content event hooks on page fault to avoid the potential deadlock. Reported-by: syzbot+7229071b47908b19d5b7@syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-fsdevel/7ehxrhbvehlrjwvrduoxsao5k3x4aw275patsb3krkwuq573yv@o2hskrfawbnc/ Fixes: 8392bc2ff8c8 ("fsnotify: generate pre-content permission event on page fault") Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara Link: https://patch.msgid.link/20250312073852.2123409-5-amir73il@gmail.com --- include/linux/mm.h | 1 - mm/filemap.c | 74 ---------------------------------------------- mm/nommu.c | 7 ----- 3 files changed, 82 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 7b1068ddcbb7..8483e09aeb2c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3420,7 +3420,6 @@ extern vm_fault_t filemap_fault(struct vm_fault *vmf); extern vm_fault_t filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf); -extern vm_fault_t filemap_fsnotify_fault(struct vm_fault *vmf); extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ diff --git a/mm/filemap.c b/mm/filemap.c index 2974691fdfad..ff5fcdd96136 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -47,7 +47,6 @@ #include #include #include -#include #include #include #include "internal.h" @@ -3336,48 +3335,6 @@ static vm_fault_t filemap_fault_recheck_pte_none(struct vm_fault *vmf) return ret; } -/** - * 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 @@ -3481,37 +3438,6 @@ retry_find: * or because readahead was otherwise unable to retrieve it. */ 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 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(); -- knotmirror 0.0.1 From 4f4dc3a9378bc2e6bcf331ee9e65a21abf67e7e0 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 12 Mar 2025 08:38:51 +0100 Subject: [PATCH 5/6] Revert "mm: don't allow huge faults for files with pre content watches" This reverts commit 20bf82a898b65c129af76deb96a1b415d3098a28. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara Link: https://patch.msgid.link/20250312073852.2123409-6-amir73il@gmail.com --- mm/memory.c | 19 ------------------- 1 file changed, 19 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index b9661ccfa64f..fb7b8dc75167 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -76,7 +76,6 @@ #include #include #include -#include #include @@ -5750,17 +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; @@ -5784,9 +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)) @@ -5809,9 +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 */ @@ -5829,9 +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)) -- knotmirror 0.0.1 From 252256e416deb255607f0c4a69e7cfec079e5d61 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 12 Mar 2025 08:38:52 +0100 Subject: [PATCH 6/6] Revert "fanotify: disable readahead if we have pre-content watches" This reverts commit fac84846a28c0950d4433118b3dffd44306df62d. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara Link: https://patch.msgid.link/20250312073852.2123409-7-amir73il@gmail.com --- mm/filemap.c | 12 ------------ mm/readahead.c | 14 -------------- 2 files changed, 26 deletions(-) diff --git a/mm/filemap.c b/mm/filemap.c index ff5fcdd96136..6d616bb9001e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3197,14 +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) { @@ -3273,10 +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; 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 #include #include -#include #include "internal.h" @@ -558,15 +557,6 @@ void page_cache_sync_ra(struct readahead_control *ractl, unsigned long max_pages, contig_count; 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 @@ -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. */