From 8f0346e65d22136372207b6507bc646f9efb2804 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Sun, 4 Jan 2009 12:00:53 -0800 Subject: fs: symlink write_begin allocation context fix commit 54566b2c1594c2326a645a3551f9d989f7ba3c5e upstream. With the write_begin/write_end aops, page_symlink was broken because it could no longer pass a GFP_NOFS type mask into the point where the allocations happened. They are done in write_begin, which would always assume that the filesystem can be entered from reclaim. This bug could cause filesystem deadlocks. The funny thing with having a gfp_t mask there is that it doesn't really allow the caller to arbitrarily tinker with the context in which it can be called. It couldn't ever be GFP_ATOMIC, for example, because it needs to take the page lock. The only thing any callers care about is __GFP_FS anyway, so turn that into a single flag. Add a new flag for write_begin, AOP_FLAG_NOFS. Filesystems can now act on this flag in their write_begin function. Change __grab_cache_page to accept a nofs argument as well, to honour that flag (while we're there, change the name to grab_cache_page_write_begin which is more instructive and does away with random leading underscores). This is really a more flexible way to go in the end anyway -- if a filesystem happens to want any extra allocations aside from the pagecache ones in ints write_begin function, it may now use GFP_KERNEL (rather than GFP_NOFS) for common case allocations (eg. ocfs2_alloc_write_ctxt, for a random example). [kosaki.motohiro@jp.fujitsu.com: fix ubifs] [kosaki.motohiro@jp.fujitsu.com: fix fuse] Signed-off-by: Nick Piggin Reviewed-by: KOSAKI Motohiro Cc: Signed-off-by: KOSAKI Motohiro Signed-off-by: Andrew Morton [ Cleaned up the calling convention: just pass in the AOP flags untouched to the grab_cache_page_write_begin() function. That just simplifies everybody, and may even allow future expansion of the logic. - Linus ] Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/filemap.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'mm') diff --git a/mm/filemap.c b/mm/filemap.c index 1cd0b87861b..f3033d0f5e5 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2033,7 +2033,7 @@ int pagecache_write_begin(struct file *file, struct address_space *mapping, struct inode *inode = mapping->host; struct page *page; again: - page = __grab_cache_page(mapping, index); + page = grab_cache_page_write_begin(mapping, index, flags); *pagep = page; if (!page) return -ENOMEM; @@ -2197,19 +2197,24 @@ EXPORT_SYMBOL(generic_file_direct_write); * Find or create a page at the given pagecache position. Return the locked * page. This function is specifically for buffered writes. */ -struct page *__grab_cache_page(struct address_space *mapping, pgoff_t index) +struct page *grab_cache_page_write_begin(struct address_space *mapping, + pgoff_t index, unsigned flags) { int status; struct page *page; + gfp_t gfp_notmask = 0; + if (flags & AOP_FLAG_NOFS) + gfp_notmask = __GFP_FS; repeat: page = find_lock_page(mapping, index); if (likely(page)) return page; - page = page_cache_alloc(mapping); + page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~gfp_notmask); if (!page) return NULL; - status = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL); + status = add_to_page_cache_lru(page, mapping, index, + GFP_KERNEL & ~gfp_notmask); if (unlikely(status)) { page_cache_release(page); if (status == -EEXIST) @@ -2218,7 +2223,7 @@ repeat: } return page; } -EXPORT_SYMBOL(__grab_cache_page); +EXPORT_SYMBOL(grab_cache_page_write_begin); static ssize_t generic_perform_write_2copy(struct file *file, struct iov_iter *i, loff_t pos) @@ -2263,7 +2268,7 @@ static ssize_t generic_perform_write_2copy(struct file *file, break; } - page = __grab_cache_page(mapping, index); + page = grab_cache_page_write_begin(mapping, index, 0); if (!page) { status = -ENOMEM; break; -- cgit v1.2.3-18-g5258