From: Trond Myklebust trond.myklebust@hammerspace.com
commit 67f4b5dc49913abcdb5cc736e73674e2f352f81d upstream.
Currently, when the writeback code detects a server reboot, it redirties any pages that were not committed to disk, and it sets the flag NFS_CONTEXT_RESEND_WRITES in the nfs_open_context of the file descriptor that dirtied the file. While this allows the file descriptor in question to redrive its own writes, it violates the fsync() requirement that we should be synchronising all writes to disk. While the problem is infrequent, we do see corner cases where an untimely server reboot causes the fsync() call to abandon its attempt to sync data to disk and causing data corruption issues due to missed error conditions or similar.
In order to tighted up the client's ability to deal with this situation without introducing livelocks, add a counter that records the number of times pages are redirtied due to a server reboot-like condition, and use that in fsync() to redrive the sync to disk.
Fixes: 2197e9b06c22 ("NFS: Fix up fsync() when the server rebooted") Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/nfs/file.c | 15 ++++++--------- fs/nfs/inode.c | 1 + fs/nfs/write.c | 6 ++++-- include/linux/nfs_fs.h | 1 + 4 files changed, 12 insertions(+), 11 deletions(-)
--- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -221,8 +221,10 @@ nfs_file_fsync_commit(struct file *file, int nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) { - struct nfs_open_context *ctx = nfs_file_open_context(file); struct inode *inode = file_inode(file); + struct nfs_inode *nfsi = NFS_I(inode); + long save_nredirtied = atomic_long_read(&nfsi->redirtied_pages); + long nredirtied; int ret;
trace_nfs_fsync_enter(inode); @@ -237,15 +239,10 @@ nfs_file_fsync(struct file *file, loff_t ret = pnfs_sync_inode(inode, !!datasync); if (ret != 0) break; - if (!test_and_clear_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags)) + nredirtied = atomic_long_read(&nfsi->redirtied_pages); + if (nredirtied == save_nredirtied) break; - /* - * If nfs_file_fsync_commit detected a server reboot, then - * resend all dirty pages that might have been covered by - * the NFS_CONTEXT_RESEND_WRITES flag - */ - start = 0; - end = LLONG_MAX; + save_nredirtied = nredirtied; }
trace_nfs_fsync_exit(inode, ret); --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -426,6 +426,7 @@ nfs_ilookup(struct super_block *sb, stru static void nfs_inode_init_regular(struct nfs_inode *nfsi) { atomic_long_set(&nfsi->nrequests, 0); + atomic_long_set(&nfsi->redirtied_pages, 0); INIT_LIST_HEAD(&nfsi->commit_info.list); atomic_long_set(&nfsi->commit_info.ncommit, 0); atomic_set(&nfsi->commit_info.rpcs_out, 0); --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1419,10 +1419,12 @@ static void nfs_initiate_write(struct nf */ static void nfs_redirty_request(struct nfs_page *req) { + struct nfs_inode *nfsi = NFS_I(page_file_mapping(req->wb_page)->host); + /* Bump the transmission count */ req->wb_nio++; nfs_mark_request_dirty(req); - set_bit(NFS_CONTEXT_RESEND_WRITES, &nfs_req_openctx(req)->flags); + atomic_long_inc(&nfsi->redirtied_pages); nfs_end_page_writeback(req); nfs_release_request(req); } @@ -1892,7 +1894,7 @@ static void nfs_commit_release_pages(str /* We have a mismatch. Write the page again */ dprintk_cont(" mismatch\n"); nfs_mark_request_dirty(req); - set_bit(NFS_CONTEXT_RESEND_WRITES, &nfs_req_openctx(req)->flags); + atomic_long_inc(&NFS_I(data->inode)->redirtied_pages); next: nfs_unlock_and_release_request(req); /* Latency breaker */ --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -182,6 +182,7 @@ struct nfs_inode { /* Regular file */ struct { atomic_long_t nrequests; + atomic_long_t redirtied_pages; struct nfs_mds_commit_info commit_info; struct mutex commit_mutex; };