From 66e9c6a86b800f60b1e1ea1ff7271f9e6ed1fa96 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 14 Jun 2021 14:13:41 +0100 Subject: [PATCH 1/2] afs: Fix afs_write_end() to handle short writes Fix afs_write_end() to correctly handle a short copy into the intended write region of the page. Two things are necessary: (1) If the page is not up to date, then we should just return 0 (ie. indicating a zero-length copy). The loop in generic_perform_write() will go around again, possibly breaking up the iterator into discrete chunks[1]. This is analogous to commit b9de313cf05fe08fa59efaf19756ec5283af672a for ceph. (2) The page should not have been set uptodate if it wasn't completely set up by netfs_write_begin() (this will be fixed in the next patch), so we need to set uptodate here in such a case. Also remove the assertion that was checking that the page was set uptodate since it's now set uptodate if it wasn't already a few lines above. The assertion was from when uptodate was set elsewhere. Changes: v3: Remove the handling of len exceeding the end of the page. Fixes: 3003bbd0697b ("afs: Use the netfs_write_begin() helper") Reported-by: Jeff Layton Signed-off-by: David Howells Acked-by: Jeff Layton Reviewed-by: Matthew Wilcox (Oracle) cc: Al Viro cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/YMwVp268KTzTf8cN@zeniv-ca.linux.org.uk/ [1] Link: https://lore.kernel.org/r/162367682522.460125.5652091227576721609.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/162391825688.1173366.3437507255136307904.stgit@warthog.procyon.org.uk/ # v2 --- fs/afs/write.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/fs/afs/write.c b/fs/afs/write.c index a523bb86915d..641c54679399 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -118,6 +118,15 @@ int afs_write_end(struct file *file, struct address_space *mapping, _enter("{%llx:%llu},{%lx}", vnode->fid.vid, vnode->fid.vnode, page->index); + if (!PageUptodate(page)) { + if (copied < len) { + copied = 0; + goto out; + } + + SetPageUptodate(page); + } + if (copied == 0) goto out; @@ -132,8 +141,6 @@ int afs_write_end(struct file *file, struct address_space *mapping, write_sequnlock(&vnode->cb_lock); } - ASSERT(PageUptodate(page)); - if (PagePrivate(page)) { priv = page_private(page); f = afs_page_dirty_from(page, priv); From 827a746f405d25f79560c7868474aec5aee174e1 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Sun, 13 Jun 2021 19:33:45 -0400 Subject: [PATCH 2/2] netfs: fix test for whether we can skip read when writing beyond EOF It's not sufficient to skip reading when the pos is beyond the EOF. There may be data at the head of the page that we need to fill in before the write. Add a new helper function that corrects and clarifies the logic of when we can skip reads, and have it only zero out the part of the page that won't have data copied in for the write. Finally, don't set the page Uptodate after zeroing. It's not up to date since the write data won't have been copied in yet. [DH made the following changes: - Prefixed the new function with "netfs_". - Don't call zero_user_segments() for a full-page write. - Altered the beyond-last-page check to avoid a DIV instruction and got rid of then-redundant zero-length file check. ] Fixes: e1b1240c1ff5f ("netfs: Add write_begin helper") Reported-by: Andrew W Elble Signed-off-by: Jeff Layton Signed-off-by: David Howells Reviewed-by: Matthew Wilcox (Oracle) cc: ceph-devel@vger.kernel.org Link: https://lore.kernel.org/r/20210613233345.113565-1-jlayton@kernel.org/ Link: https://lore.kernel.org/r/162367683365.460125.4467036947364047314.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/162391826758.1173366.11794946719301590013.stgit@warthog.procyon.org.uk/ # v2 --- fs/netfs/read_helper.c | 49 +++++++++++++++++++++++++++++++----------- 1 file changed, 36 insertions(+), 13 deletions(-) diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c index 725614625ed4..0b6cd3b8734c 100644 --- a/fs/netfs/read_helper.c +++ b/fs/netfs/read_helper.c @@ -1011,12 +1011,42 @@ out: } EXPORT_SYMBOL(netfs_readpage); -static void netfs_clear_thp(struct page *page) +/** + * netfs_skip_page_read - prep a page for writing without reading first + * @page: page being prepared + * @pos: starting position for the write + * @len: length of write + * + * In some cases, write_begin doesn't need to read at all: + * - full page write + * - write that lies in a page that is completely beyond EOF + * - write that covers the the page from start to EOF or beyond it + * + * If any of these criteria are met, then zero out the unwritten parts + * of the page and return true. Otherwise, return false. + */ +static bool netfs_skip_page_read(struct page *page, loff_t pos, size_t len) { - unsigned int i; + struct inode *inode = page->mapping->host; + loff_t i_size = i_size_read(inode); + size_t offset = offset_in_thp(page, pos); - for (i = 0; i < thp_nr_pages(page); i++) - clear_highpage(page + i); + /* Full page write */ + if (offset == 0 && len >= thp_size(page)) + return true; + + /* pos beyond last page in the file */ + if (pos - offset >= i_size) + goto zero_out; + + /* Write that covers from the start of the page to EOF or beyond */ + if (offset == 0 && (pos + len) >= i_size) + goto zero_out; + + return false; +zero_out: + zero_user_segments(page, 0, offset, offset + len, thp_size(page)); + return true; } /** @@ -1024,7 +1054,7 @@ static void netfs_clear_thp(struct page *page) * @file: The file to read from * @mapping: The mapping to read from * @pos: File position at which the write will begin - * @len: The length of the write in this page + * @len: The length of the write (may extend beyond the end of the page chosen) * @flags: AOP_* flags * @_page: Where to put the resultant page * @_fsdata: Place for the netfs to store a cookie @@ -1061,8 +1091,6 @@ int netfs_write_begin(struct file *file, struct address_space *mapping, struct inode *inode = file_inode(file); unsigned int debug_index = 0; pgoff_t index = pos >> PAGE_SHIFT; - int pos_in_page = pos & ~PAGE_MASK; - loff_t size; int ret; DEFINE_READAHEAD(ractl, file, NULL, mapping, index); @@ -1090,13 +1118,8 @@ retry: * within the cache granule containing the EOF, in which case we need * to preload the granule. */ - size = i_size_read(inode); if (!ops->is_cache_enabled(inode) && - ((pos_in_page == 0 && len == thp_size(page)) || - (pos >= size) || - (pos_in_page == 0 && (pos + len) >= size))) { - netfs_clear_thp(page); - SetPageUptodate(page); + netfs_skip_page_read(page, pos, len)) { netfs_stat(&netfs_n_rh_write_zskip); goto have_page_no_wait; }