From 623e3db9f9b7d6e7b2a99180f9cf0825c936ab7a Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 28 Mar 2012 14:42:40 -0700 Subject: mm for fs: add truncate_pagecache_range() Holepunching filesystems ext4 and xfs are using truncate_inode_pages_range but forgetting to unmap pages first (ocfs2 remembers). This is not really a bug, since races already require truncate_inode_page() to handle that case once the page is locked; but it can be very inefficient if the file being punched happens to be mapped into many vmas. Provide a drop-in replacement truncate_pagecache_range() which does the unmapping pass first, handling the awkward mismatch between arguments to truncate_inode_pages_range() and arguments to unmap_mapping_range(). Note that holepunching does not unmap privately COWed pages in the range: POSIX requires that we do so when truncating, but it's hard to justify, difficult to implement without an i_size cutoff, and no filesystem is attempting to implement it. Signed-off-by: Hugh Dickins Cc: "Theodore Ts'o" Cc: Andreas Dilger Cc: Mark Fasheh Cc: Joel Becker Cc: Ben Myers Cc: Alex Elder Cc: Christoph Hellwig Cc: Dave Chinner Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- mm/truncate.c | 40 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 41 insertions(+), 1 deletion(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index cf7982336103..630068184265 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -954,7 +954,7 @@ extern void truncate_pagecache(struct inode *inode, loff_t old, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); extern int vmtruncate(struct inode *inode, loff_t offset); extern int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end); - +void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end); int truncate_inode_page(struct address_space *mapping, struct page *page); int generic_error_remove_page(struct address_space *mapping, struct page *page); diff --git a/mm/truncate.c b/mm/truncate.c index 18aded3a89fc..61a183b89df6 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -626,3 +626,43 @@ int vmtruncate_range(struct inode *inode, loff_t lstart, loff_t lend) return 0; } + +/** + * truncate_pagecache_range - unmap and remove pagecache that is hole-punched + * @inode: inode + * @lstart: offset of beginning of hole + * @lend: offset of last byte of hole + * + * This function should typically be called before the filesystem + * releases resources associated with the freed range (eg. deallocates + * blocks). This way, pagecache will always stay logically coherent + * with on-disk format, and the filesystem would not have to deal with + * situations such as writepage being called for a page that has already + * had its underlying blocks deallocated. + */ +void truncate_pagecache_range(struct inode *inode, loff_t lstart, loff_t lend) +{ + struct address_space *mapping = inode->i_mapping; + loff_t unmap_start = round_up(lstart, PAGE_SIZE); + loff_t unmap_end = round_down(1 + lend, PAGE_SIZE) - 1; + /* + * This rounding is currently just for example: unmap_mapping_range + * expands its hole outwards, whereas we want it to contract the hole + * inwards. However, existing callers of truncate_pagecache_range are + * doing their own page rounding first; and truncate_inode_pages_range + * currently BUGs if lend is not pagealigned-1 (it handles partial + * page at start of hole, but not partial page at end of hole). Note + * unmap_mapping_range allows holelen 0 for all, and we allow lend -1. + */ + + /* + * Unlike in truncate_pagecache, unmap_mapping_range is called only + * once (before truncating pagecache), and without "even_cows" flag: + * hole-punching should not remove private COWed pages from the hole. + */ + if ((u64)unmap_end > (u64)unmap_start) + unmap_mapping_range(mapping, unmap_start, + 1 + unmap_end - unmap_start, 0); + truncate_inode_pages_range(mapping, lstart, lend); +} +EXPORT_SYMBOL(truncate_pagecache_range); -- cgit v1.2.3-59-g8ed1b