From 5bb89b4702e22981445ae01af733a57d1cae2018 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 25 Mar 2015 14:14:42 -0400 Subject: NFSv4.1/pnfs: Separate out metadata and data consistency for pNFS The LAYOUTCOMMIT operation means different things to different layout types. For blocks and objects, it is both a data and metadata consistency operation. For files and flexfiles, it is only a metadata consistency operation. This patch separates out the 2 cases, allowing the files/flexfiles layout drivers to optimise away the data consistency calls to layoutcommit. Signed-off-by: Trond Myklebust --- fs/nfs/write.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'fs/nfs/write.c') diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 849ed784d6ac..7f933a39f385 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1840,17 +1840,16 @@ EXPORT_SYMBOL_GPL(nfs_write_inode); */ int nfs_wb_all(struct inode *inode) { - struct writeback_control wbc = { - .sync_mode = WB_SYNC_ALL, - .nr_to_write = LONG_MAX, - .range_start = 0, - .range_end = LLONG_MAX, - }; int ret; trace_nfs_writeback_inode_enter(inode); - ret = sync_inode(inode, &wbc); + ret = filemap_write_and_wait(inode->i_mapping); + if (!ret) { + ret = nfs_commit_inode(inode, FLUSH_SYNC); + if (!ret) + pnfs_sync_inode(inode, true); + } trace_nfs_writeback_inode_exit(inode, ret); return ret; -- cgit v1.2.3 From b9ea25152e56365ce149b9a39637cd7a16eec556 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Tue, 14 Apr 2015 15:45:27 -0700 Subject: page_writeback: clean up mess around cancel_dirty_page() This patch replaces cancel_dirty_page() with a helper function account_page_cleaned() which only updates counters. It's called from truncate_complete_page() and from try_to_free_buffers() (hack for ext3). Page is locked in both cases, page-lock protects against concurrent dirtiers: see commit 2d6d7f982846 ("mm: protect set_page_dirty() from ongoing truncation"). Delete_from_page_cache() shouldn't be called for dirty pages, they must be handled by caller (either written or truncated). This patch treats final dirty accounting fixup at the end of __delete_from_page_cache() as a debug check and adds WARN_ON_ONCE() around it. If something removes dirty pages without proper handling that might be a bug and unwritten data might be lost. Hugetlbfs has no dirty pages accounting, ClearPageDirty() is enough here. cancel_dirty_page() in nfs_wb_page_cancel() is redundant. This is helper for nfs_invalidate_page() and it's called only in case complete invalidation. The mess was started in v2.6.20 after commits 46d2277c796f ("Clean up and make try_to_free_buffers() not race with dirty pages") and 3e67c0987d75 ("truncate: clear page dirtiness before running try_to_free_buffers()") first was reverted right in v2.6.20 in commit ecdfc9787fe5 ("Resurrect 'try_to_free_buffers()' VM hackery"), second in v2.6.25 commit a2b345642f53 ("Fix dirty page accounting leak with ext3 data=journal"). Custom fixes were introduced between these points. NFS in v2.6.23, commit 1b3b4a1a2deb ("NFS: Fix a write request leak in nfs_invalidate_page()"). Kludge in __delete_from_page_cache() in v2.6.24, commit 3a6927906f1b ("Do dirty page accounting when removing a page from the page cache"). Since v2.6.25 all of them are redundant. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Konstantin Khlebnikov Cc: Tejun Heo Cc: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/nfs/write.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'fs/nfs/write.c') diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 849ed784d6ac..759931088094 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1876,11 +1876,6 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page) * request from the inode / page_private pointer and * release it */ nfs_inode_remove_request(req); - /* - * In case nfs_inode_remove_request has marked the - * page as being dirty - */ - cancel_dirty_page(page, PAGE_CACHE_SIZE); nfs_unlock_and_release_request(req); } -- cgit v1.2.3 From 2b0143b5c986be1ce8408b3aadc4709e0a94429d Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 17 Mar 2015 22:25:59 +0000 Subject: VFS: normal filesystems (and lustre): d_inode() annotations that's the bulk of filesystem drivers dealing with inodes of their own Signed-off-by: David Howells Signed-off-by: Al Viro --- fs/nfs/write.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'fs/nfs/write.c') diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 849ed784d6ac..e8f675d4b2fb 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -702,7 +702,7 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req) */ static void nfs_inode_remove_request(struct nfs_page *req) { - struct inode *inode = req->wb_context->dentry->d_inode; + struct inode *inode = d_inode(req->wb_context->dentry); struct nfs_inode *nfsi = NFS_I(inode); struct nfs_page *head; @@ -861,7 +861,7 @@ static void nfs_clear_request_commit(struct nfs_page *req) { if (test_bit(PG_CLEAN, &req->wb_flags)) { - struct inode *inode = req->wb_context->dentry->d_inode; + struct inode *inode = d_inode(req->wb_context->dentry); struct nfs_commit_info cinfo; nfs_init_cinfo_from_inode(&cinfo, inode); @@ -1591,7 +1591,7 @@ void nfs_init_commit(struct nfs_commit_data *data, struct nfs_commit_info *cinfo) { struct nfs_page *first = nfs_list_entry(head->next); - struct inode *inode = first->wb_context->dentry->d_inode; + struct inode *inode = d_inode(first->wb_context->dentry); /* Set up the RPC argument and reply structs * NB: take care not to mess about with data->commit et al. */ @@ -1690,7 +1690,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) dprintk("NFS: commit (%s/%llu %d@%lld)", req->wb_context->dentry->d_sb->s_id, - (unsigned long long)NFS_FILEID(req->wb_context->dentry->d_inode), + (unsigned long long)NFS_FILEID(d_inode(req->wb_context->dentry)), req->wb_bytes, (long long)req_offset(req)); if (status < 0) { -- cgit v1.2.3 From 3708f842e107b9b79d54a75d152e666b693649e8 Mon Sep 17 00:00:00 2001 From: Nicolas Iooss Date: Thu, 16 Apr 2015 18:48:39 +0800 Subject: Revert "nfs: replace nfs_add_stats with nfs_inc_stats when add one" This reverts commit 5a254d08b086d80cbead2ebcee6d2a4b3a15587a. Since commit 5a254d08b086 ("nfs: replace nfs_add_stats with nfs_inc_stats when add one"), nfs_readpage and nfs_do_writepage use nfs_inc_stats to increment NFSIOS_READPAGES and NFSIOS_WRITEPAGES instead of nfs_add_stats. However nfs_inc_stats does not do the same thing as nfs_add_stats with value 1 because these functions work on distinct stats: nfs_inc_stats increments stats from "enum nfs_stat_eventcounters" (in server->io_stats->events) and nfs_add_stats those from "enum nfs_stat_bytecounters" (in server->io_stats->bytes). Signed-off-by: Nicolas Iooss Fixes: 5a254d08b086 ("nfs: replace nfs_add_stats with nfs_inc_stats...") Cc: stable@vger.kernel.org # 3.19+ Signed-off-by: Trond Myklebust --- fs/nfs/write.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/nfs/write.c') diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 7f933a39f385..36d0c0a6e68a 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -580,7 +580,7 @@ static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, st int ret; nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE); - nfs_inc_stats(inode, NFSIOS_WRITEPAGES); + nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1); nfs_pageio_cond_complete(pgio, page_file_index(page)); ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE); -- cgit v1.2.3 From 6b19687563fa6f385ac314afa30b7579e8c3174c Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 6 May 2015 18:26:58 -0400 Subject: nfs: stat(2) fails during cthon04 basic test5 on NFSv4.0 When running the Connectathon basic tests against a Solaris NFS server over NFSv4.0, test5 reports that stat(2) returns a file size of zero instead of 1MB. On success, nfs_commit_inode() can return a positive result; see other call sites such as nfs_file_fsync_commit() and nfs_commit_unstable_pages(). The call site recently added in nfs_wb_all() does not prevent that positive return value from leaking to its callers. If it leaks through nfs_sync_inode() back to nfs_getattr(), that causes stat(2) to return a positive return value to user space while also not filling in the passed-in struct stat. Additional clean up: the new logic in nfs_wb_all() is rewritten in bfields-normal form. Fixes: 5bb89b4702e2 ("NFSv4.1/pnfs: Separate out metadata . . .") Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/write.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'fs/nfs/write.c') diff --git a/fs/nfs/write.c b/fs/nfs/write.c index d12a4be613a5..dfc19f1575a1 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1845,12 +1845,15 @@ int nfs_wb_all(struct inode *inode) trace_nfs_writeback_inode_enter(inode); ret = filemap_write_and_wait(inode->i_mapping); - if (!ret) { - ret = nfs_commit_inode(inode, FLUSH_SYNC); - if (!ret) - pnfs_sync_inode(inode, true); - } + if (ret) + goto out; + ret = nfs_commit_inode(inode, FLUSH_SYNC); + if (ret < 0) + goto out; + pnfs_sync_inode(inode, true); + ret = 0; +out: trace_nfs_writeback_inode_exit(inode, ret); return ret; } -- cgit v1.2.3