From 00a7d39898c8010bfd5ff62af31ca5db34421b38 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 6 Mar 2025 18:25:35 -1000 Subject: fs/pipe: add simpler helpers for common cases The fix to atomically read the pipe head and tail state when not holding the pipe mutex has caused a number of headaches due to the size change of the involved types. It turns out that we don't have _that_ many places that access these fields directly and were affected, but we have more than we strictly should have, because our low-level helper functions have been designed to have intimate knowledge of how the pipes work. And as a result, that random noise of direct 'pipe->head' and 'pipe->tail' accesses makes it harder to pinpoint any actual potential problem spots remaining. For example, we didn't have a "is the pipe full" helper function, but instead had a "given these pipe buffer indexes and this pipe size, is the pipe full". That's because some low-level pipe code does actually want that much more complicated interface. But most other places literally just want a "is the pipe full" helper, and not having it meant that those places ended up being unnecessarily much too aware of this all. It would have been much better if only the very core pipe code that cared had been the one aware of this all. So let's fix it - better late than never. This just introduces the trivial wrappers for "is this pipe full or empty" and to get how many pipe buffers are used, so that instead of writing if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) the places that literally just want to know if a pipe is full can just say if (pipe_is_full(pipe)) instead. The existing trivial cases were converted with a 'sed' script. This cuts down on the places that access pipe->head and pipe->tail directly outside of the pipe code (and core splice code) quite a lot. The splice code in particular still revels in doing the direct low-level accesses, and the fuse fuse_dev_splice_write() code also seems a bit unnecessarily eager to go very low-level, but it's at least a bit better than it used to be. Signed-off-by: Linus Torvalds --- mm/filemap.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index d4564a79eb35..2974691fdfad 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2897,8 +2897,7 @@ 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 +2954,7 @@ 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 +3014,7 @@ 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; } -- cgit v1.2.3 From 955fbe0ef19df4197595a98d0906c94025c4beef Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 12 Mar 2025 08:38:50 +0100 Subject: 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(-) (limited to 'mm/filemap.c') 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(); -- cgit v1.2.3 From 252256e416deb255607f0c4a69e7cfec079e5d61 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 12 Mar 2025 08:38:52 +0100 Subject: 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(-) (limited to 'mm/filemap.c') 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. */ -- cgit v1.2.3