nfsd: Replace use of rwsem with errseq_t

The nfsd_file nf_rwsem is currently being used to separate file write
and commit instances to ensure that we catch errors and apply them to
the correct write/commit.
We can improve scalability at the expense of a little accuracy (some
extra false positives) by replacing the nf_rwsem with more careful
use of the errseq_t mechanism to track errors across the different
operations.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
[ cel: rebased on zero-verifier fix ]

1 files changed, 15 insertions, 25 deletions

diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 74c3451c2089..316ed702d518 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -522,10 +522,11 @@ __be32 nfsd4_clone_file_range(struct nfsd_file *nf_src, u64 src_pos,
 {
 	struct file *src = nf_src->nf_file;
 	struct file *dst = nf_dst->nf_file;
+	errseq_t since;
 	loff_t cloned;
 	__be32 ret = 0;
 
-	down_write(&nf_dst->nf_rwsem);
+	since = READ_ONCE(dst->f_wb_err);
 	cloned = vfs_clone_file_range(src, src_pos, dst, dst_pos, count, 0);
 	if (cloned < 0) {
 		ret = nfserrno(cloned);
@@ -540,6 +541,8 @@ __be32 nfsd4_clone_file_range(struct nfsd_file *nf_src, u64 src_pos,
 		int status = vfs_fsync_range(dst, dst_pos, dst_end, 0);
 
 		if (!status)
+			status = filemap_check_wb_err(dst->f_mapping, since);
+		if (!status)
 			status = commit_inode_metadata(file_inode(src));
 		if (status < 0) {
 			nfsd_reset_boot_verifier(net_generic(nf_dst->nf_net,
@@ -548,7 +551,6 @@ __be32 nfsd4_clone_file_range(struct nfsd_file *nf_src, u64 src_pos,
 		}
 	}
 out_err:
-	up_write(&nf_dst->nf_rwsem);
 	return ret;
 }
 
@@ -956,6 +958,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
 	struct super_block	*sb = file_inode(file)->i_sb;
 	struct svc_export	*exp;
 	struct iov_iter		iter;
+	errseq_t		since;
 	__be32			nfserr;
 	int			host_err;
 	int			use_wgather;
@@ -993,8 +996,8 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
 		flags |= RWF_SYNC;
 
 	iov_iter_kvec(&iter, WRITE, vec, vlen, *cnt);
+	since = READ_ONCE(file->f_wb_err);
 	if (flags & RWF_SYNC) {
-		down_write(&nf->nf_rwsem);
 		if (verf)
 			nfsd_copy_boot_verifier(verf,
 					net_generic(SVC_NET(rqstp),
@@ -1003,15 +1006,12 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
 		if (host_err < 0)
 			nfsd_reset_boot_verifier(net_generic(SVC_NET(rqstp),
 						 nfsd_net_id));
-		up_write(&nf->nf_rwsem);
 	} else {
-		down_read(&nf->nf_rwsem);
 		if (verf)
 			nfsd_copy_boot_verifier(verf,
 					net_generic(SVC_NET(rqstp),
 					nfsd_net_id));
 		host_err = vfs_iter_write(file, &iter, &pos, flags);
-		up_read(&nf->nf_rwsem);
 	}
 	if (host_err < 0) {
 		nfsd_reset_boot_verifier(net_generic(SVC_NET(rqstp),
@@ -1021,6 +1021,9 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
 	*cnt = host_err;
 	nfsd_stats_io_write_add(exp, *cnt);
 	fsnotify_modify(file);
+	host_err = filemap_check_wb_err(file->f_mapping, since);
+	if (host_err < 0)
+		goto out_nfserr;
 
 	if (stable && use_wgather) {
 		host_err = wait_for_concurrent_writes(file);
@@ -1101,19 +1104,6 @@ out:
 }
 
 #ifdef CONFIG_NFSD_V3
-static int
-nfsd_filemap_write_and_wait_range(struct nfsd_file *nf, loff_t offset,
-				  loff_t end)
-{
-	struct address_space *mapping = nf->nf_file->f_mapping;
-	int ret = filemap_fdatawrite_range(mapping, offset, end);
-
-	if (ret)
-		return ret;
-	filemap_fdatawait_range_keep_errors(mapping, offset, end);
-	return 0;
-}
-
 /*
  * Commit all pending writes to stable storage.
  *
@@ -1144,25 +1134,25 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	if (err)
 		goto out;
 	if (EX_ISSYNC(fhp->fh_export)) {
-		int err2 = nfsd_filemap_write_and_wait_range(nf, offset, end);
+		errseq_t since = READ_ONCE(nf->nf_file->f_wb_err);
+		int err2;
 
-		down_write(&nf->nf_rwsem);
-		if (!err2)
-			err2 = vfs_fsync_range(nf->nf_file, offset, end, 0);
+		err2 = vfs_fsync_range(nf->nf_file, offset, end, 0);
 		switch (err2) {
 		case 0:
 			nfsd_copy_boot_verifier(verf, net_generic(nf->nf_net,
 						nfsd_net_id));
+			err2 = filemap_check_wb_err(nf->nf_file->f_mapping,
+						    since);
 			break;
 		case -EINVAL:
 			err = nfserr_notsupp;
 			break;
 		default:
-			err = nfserrno(err2);
 			nfsd_reset_boot_verifier(net_generic(nf->nf_net,
 						 nfsd_net_id));
 		}
-		up_write(&nf->nf_rwsem);
+		err = nfserrno(err2);
 	} else
 		nfsd_copy_boot_verifier(verf, net_generic(nf->nf_net,
 					nfsd_net_id));