From 54566b2c1594c2326a645a3551f9d989f7ba3c5e 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 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: [2.6.28.x] 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 --- include/linux/fs.h | 5 ++++- include/linux/pagemap.h | 3 ++- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index e2170ee21e18..f2a3010140e3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -423,6 +423,9 @@ enum positive_aop_returns { #define AOP_FLAG_UNINTERRUPTIBLE 0x0001 /* will not do a short write */ #define AOP_FLAG_CONT_EXPAND 0x0002 /* called from cont_expand */ +#define AOP_FLAG_NOFS 0x0004 /* used by filesystem to direct + * helper code (eg buffer layer) + * to clear GFP_FS from alloc */ /* * oh the beauties of C type declarations. @@ -2035,7 +2038,7 @@ extern int page_readlink(struct dentry *, char __user *, int); extern void *page_follow_link_light(struct dentry *, struct nameidata *); extern void page_put_link(struct dentry *, struct nameidata *, void *); extern int __page_symlink(struct inode *inode, const char *symname, int len, - gfp_t gfp_mask); + int nofs); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern int generic_readlink(struct dentry *, char __user *, int); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 709742be02f0..01ca0856caff 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -241,7 +241,8 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index, int tag, unsigned int nr_pages, struct page **pages); -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); /* * Returns locked page at given index in given cache, creating it if needed. -- cgit v1.2.3-59-g8ed1b