From: Trond Myklebust <trond.myklebust@hammerspace.com> mainline inclusion from mainline-v6.19-rc6 commit cce0be6eb4971456b703aaeafd571650d314bcca category: bugfix bugzilla: https://gitcode.com/openeuler/kernel/issues/8332 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Wang Zhaolong reports a deadlock involving NFSv4.1 state recovery waiting on kthreadd, which is attempting to reclaim memory by calling nfs_release_folio(). The latter cannot make progress due to state recovery being needed. It seems that the only safe thing to do here is to kick off a writeback of the folio, without waiting for completion, or else kicking off an asynchronous commit. Reported-by: Wang Zhaolong <wangzhaolong@huaweicloud.com> Fixes: 96780ca55e3c ("NFS: fix up nfs_release_folio() to try to release the page") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Conflicts: fs/nfs/file.c [Conflicts with mainline commit 7e8e78a0ba00 ("nfs: remove dead code for the old swap over NFS implementation").] Signed-off-by: Wang Zhaolong <wangzhaolong@huaweicloud.com> Signed-off-by: Li Lingfeng <lilingfeng3@huawei.com> --- fs/nfs/file.c | 3 ++- fs/nfs/nfstrace.h | 3 +++ fs/nfs/write.c | 33 +++++++++++++++++++++++++++++++++ include/linux/nfs_fs.h | 1 + 4 files changed, 39 insertions(+), 1 deletion(-) diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 4994b2873970..9a2a54eb0e7a 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -453,7 +453,8 @@ static bool nfs_release_folio(struct folio *folio, gfp_t gfp) if ((current_gfp_context(gfp) & GFP_KERNEL) != GFP_KERNEL || current_is_kswapd() || current_is_kcompactd()) return false; - if (nfs_wb_folio(folio_file_mapping(folio)->host, folio) < 0) + if (nfs_wb_folio_reclaim(folio->mapping->host, folio) < 0 || + folio_test_private(folio)) return false; } return nfs_fscache_release_folio(folio, gfp); diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 004c25f0782b..85224e9369e7 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -1033,6 +1033,9 @@ DECLARE_EVENT_CLASS(nfs_folio_event_done, DEFINE_NFS_FOLIO_EVENT(nfs_aop_readpage); DEFINE_NFS_FOLIO_EVENT_DONE(nfs_aop_readpage_done); +DEFINE_NFS_FOLIO_EVENT(nfs_writeback_folio_reclaim); +DEFINE_NFS_FOLIO_EVENT_DONE(nfs_writeback_folio_reclaim_done); + DEFINE_NFS_FOLIO_EVENT(nfs_writeback_folio); DEFINE_NFS_FOLIO_EVENT_DONE(nfs_writeback_folio_done); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index edd6a8ba71b7..0148719cc6dc 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -2120,6 +2120,39 @@ int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio) return ret; } +/** + * nfs_wb_folio_reclaim - Write back all requests on one page + * @inode: pointer to page + * @folio: pointer to folio + * + * Assumes that the folio has been locked by the caller + */ +int nfs_wb_folio_reclaim(struct inode *inode, struct folio *folio) +{ + loff_t range_start = folio_pos(folio); + size_t len = folio_size(folio); + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = 0, + .range_start = range_start, + .range_end = range_start + len - 1, + .for_sync = 1, + }; + int ret; + + if (folio_test_writeback(folio)) + return -EBUSY; + if (folio_clear_dirty_for_io(folio)) { + trace_nfs_writeback_folio_reclaim(inode, range_start, len); + ret = nfs_writepage_locked(folio, &wbc); + trace_nfs_writeback_folio_reclaim_done(inode, range_start, len, + ret); + return ret; + } + nfs_commit_inode(inode, 0); + return 0; +} + /** * nfs_wb_folio - Write back all requests on one page * @inode: pointer to page diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index aef98dd1b9e1..e4c78ac0ad5b 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -611,6 +611,7 @@ extern int nfs_update_folio(struct file *file, struct folio *folio, extern int nfs_sync_inode(struct inode *inode); extern int nfs_wb_all(struct inode *inode); extern int nfs_wb_folio(struct inode *inode, struct folio *folio); +extern int nfs_wb_folio_reclaim(struct inode *inode, struct folio *folio); int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio); extern int nfs_commit_inode(struct inode *, int); extern struct nfs_commit_data *nfs_commitdata_alloc(void); -- 2.52.0