Received-SPF: pass (google.com: best guess record for domain of linux-nfs-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Trond Myklebust <trondmy@gmail.com>
To:     "J. Bruce Fields" <bfields@redhat.com>
Cc:     linux-nfs@vger.kernel.org
Subject: [PATCH 3/3] nfsd: Don't garbage collect files that might contain write errors
Date:   Mon, 26 Aug 2019 12:50:21 -0400
Message-Id: <20190826165021.81075-4-trond.myklebust@hammerspace.com>
In-Reply-To: <20190826165021.81075-3-trond.myklebust@hammerspace.com>
References: <20190826165021.81075-1-trond.myklebust@hammerspace.com>
 <20190826165021.81075-2-trond.myklebust@hammerspace.com>
 <20190826165021.81075-3-trond.myklebust@hammerspace.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-nfs-owner@vger.kernel.org
Precedence: bulk

If a file may contain unstable writes that can error out, then we want
to avoid garbage collecting the struct nfsd_file that may be
tracking those errors.
So in the garbage collector, we try to avoid collecting files that aren't
clean. Furthermore, we avoid immediately kicking off the garbage collector
in the case where the reference drops to zero for the case where there
is a write error that is being tracked.

If the file is unhashed while an error is pending, then declare a
reboot, to ensure the client resends any unstable writes.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfsd/filecache.c | 43 ++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 42 insertions(+), 1 deletion(-)

diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index d229fd3c825d..92d0998824a0 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -216,6 +216,36 @@ nfsd_file_free(struct nfsd_file *nf)
 	return flush;
 }
 
+static bool
+nfsd_file_check_writeback(struct nfsd_file *nf)
+{
+	struct file *file = nf->nf_file;
+	struct address_space *mapping;
+
+	if (!file || !(file->f_mode & FMODE_WRITE))
+		return false;
+	mapping = file->f_mapping;
+	return mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) ||
+		mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK);
+}
+
+static int
+nfsd_file_check_write_error(struct nfsd_file *nf)
+{
+	struct file *file = nf->nf_file;
+
+	if (!file || !(file->f_mode & FMODE_WRITE))
+		return 0;
+	return filemap_check_wb_err(file->f_mapping, READ_ONCE(file->f_wb_err));
+}
+
+static bool
+nfsd_file_in_use(struct nfsd_file *nf)
+{
+	return nfsd_file_check_writeback(nf) ||
+			nfsd_file_check_write_error(nf);
+}
+
 static void
 nfsd_file_do_unhash(struct nfsd_file *nf)
 {
@@ -223,6 +253,8 @@ nfsd_file_do_unhash(struct nfsd_file *nf)
 
 	trace_nfsd_file_unhash(nf);
 
+	if (nfsd_file_check_write_error(nf))
+		nfsd_reset_boot_verifier(net_generic(nf->nf_net, nfsd_net_id));
 	--nfsd_file_hashtbl[nf->nf_hashval].nfb_count;
 	hlist_del_rcu(&nf->nf_node);
 	if (!list_empty(&nf->nf_lru))
@@ -277,9 +309,10 @@ void
 nfsd_file_put(struct nfsd_file *nf)
 {
 	bool is_hashed = test_bit(NFSD_FILE_HASHED, &nf->nf_flags) != 0;
+	bool unused = !nfsd_file_in_use(nf);
 
 	set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags);
-	if (nfsd_file_put_noref(nf) == 1 && is_hashed)
+	if (nfsd_file_put_noref(nf) == 1 && is_hashed && unused)
 		nfsd_file_schedule_laundrette(NFSD_FILE_LAUNDRETTE_MAY_FLUSH);
 }
 
@@ -345,6 +378,14 @@ nfsd_file_lru_cb(struct list_head *item, struct list_lru_one *lru,
 	 */
 	if (atomic_read(&nf->nf_ref) > 1)
 		goto out_skip;
+
+	/*
+	 * Don't throw out files that are still undergoing I/O or
+	 * that have uncleared errors pending.
+	 */
+	if (nfsd_file_check_writeback(nf))
+		goto out_skip;
+
 	if (test_and_clear_bit(NFSD_FILE_REFERENCED, &nf->nf_flags))
 		goto out_rescan;
 
-- 
2.21.0