Merge tag 'nfs-for-5.10-1' of git://git.linux-nfs.org/projects/anna/l…

…inux-nfs

Pull NFS client updates from Anna Schumaker:
 "Stable Fixes:
   - Wait for stateid updates after CLOSE/OPEN_DOWNGRADE # v5.4+
   - Fix nfs_path in case of a rename retry
   - Support EXCHID4_FLAG_SUPP_FENCE_OPS v4.2 EXCHANGE_ID flag

  New features and improvements:
   - Replace dprintk() calls with tracepoints
   - Make cache consistency bitmap dynamic
   - Added support for the NFS v4.2 READ_PLUS operation
   - Improvements to net namespace uniquifier

  Other bugfixes and cleanups:
   - Remove redundant clnt pointer
   - Don't update timeout values on connection resets
   - Remove redundant tracepoints
   - Various cleanups to comments
   - Fix oops when trying to use copy_file_range with v4.0 source server
   - Improvements to flexfiles mirrors
   - Add missing 'local_lock=posix' mount option"

* tag 'nfs-for-5.10-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (55 commits)
  NFSv4.2: support EXCHGID4_FLAG_SUPP_FENCE_OPS 4.2 EXCHANGE_ID flag
  NFSv4: Fix up RCU annotations for struct nfs_netns_client
  NFS: Only reference user namespace from nfs4idmap struct instead of cred
  nfs: add missing "posix" local_lock constant table definition
  NFSv4: Use the net namespace uniquifier if it is set
  NFSv4: Clean up initialisation of uniquified client id strings
  NFS: Decode a full READ_PLUS reply
  SUNRPC: Add an xdr_align_data() function
  NFS: Add READ_PLUS hole segment decoding
  SUNRPC: Add the ability to expand holes in data pages
  SUNRPC: Split out _shift_data_right_tail()
  SUNRPC: Split out xdr_realign_pages() from xdr_align_pages()
  NFS: Add READ_PLUS data segment support
  NFS: Use xdr_page_pos() in NFSv4 decode_getacl()
  SUNRPC: Implement a xdr_page_pos() function
  SUNRPC: Split out a function for setting current page
  NFS: fix nfs_path in case of a rename retry
  fs: nfs: return per memcg count for xattr shrinkers
  NFSv4: Wait for stateid updates after CLOSE/OPEN_DOWNGRADE
  nfs: remove incorrect fallthrough label
  ...

fs/lockd/mon.c

@@ -417,7 +417,7 @@ void nsm_release(struct nsm_handle *nsm)
 /*
  * XDR functions for NSM.
  *
- * See http://www.opengroup.org/ for details on the Network
+ * See https://www.opengroup.org/ for details on the Network
  * Status Monitor wire protocol.
  */
 

fs/nfs/fs_context.c

@@ -94,6 +94,7 @@ enum {
 static const struct constant_table nfs_param_enums_local_lock[] = {
 	{ "all",		Opt_local_lock_all },
 	{ "flock",	Opt_local_lock_flock },
+	{ "posix",	Opt_local_lock_posix },
 	{ "none",		Opt_local_lock_none },
 	{}
 };

fs/nfs/namespace.c

@@ -32,9 +32,9 @@ int nfs_mountpoint_expiry_timeout = 500 * HZ;
 /*
  * nfs_path - reconstruct the path given an arbitrary dentry
  * @base - used to return pointer to the end of devname part of path
- * @dentry - pointer to dentry
+ * @dentry_in - pointer to dentry
  * @buffer - result buffer
- * @buflen - length of buffer
+ * @buflen_in - length of buffer
  * @flags - options (see below)
  *
  * Helper function for constructing the server pathname
@@ -49,15 +49,19 @@ int nfs_mountpoint_expiry_timeout = 500 * HZ;
  *		       the original device (export) name
  *		       (if unset, the original name is returned verbatim)
  */
-char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen,
-	       unsigned flags)
+char *nfs_path(char **p, struct dentry *dentry_in, char *buffer,
+	       ssize_t buflen_in, unsigned flags)
 {
 	char *end;
 	int namelen;
 	unsigned seq;
 	const char *base;
+	struct dentry *dentry;
+	ssize_t buflen;
 
 rename_retry:
+	buflen = buflen_in;
+	dentry = dentry_in;
 	end = buffer+buflen;
 	*--end = '\0';
 	buflen--;

fs/nfs/nfs42xattr.c

@@ -67,7 +67,6 @@ struct nfs4_xattr_bucket {
 
 struct nfs4_xattr_cache {
 	struct kref ref;
-	spinlock_t hash_lock;	/* protects hashtable and lru */
 	struct nfs4_xattr_bucket buckets[NFS4_XATTR_HASH_SIZE];
 	struct list_head lru;
 	struct list_head dispose;
@@ -882,7 +881,7 @@ nfs4_xattr_cache_count(struct shrinker *shrink, struct shrink_control *sc)
 {
 	unsigned long count;
 
-	count = list_lru_count(&nfs4_xattr_cache_lru);
+	count = list_lru_shrink_count(&nfs4_xattr_cache_lru, sc);
 	return vfs_pressure_ratio(count);
 }
 
@@ -976,7 +975,7 @@ nfs4_xattr_entry_count(struct shrinker *shrink, struct shrink_control *sc)
 	lru = (shrink == &nfs4_xattr_large_entry_shrinker) ?
 	    &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru;
 
-	count = list_lru_count(lru);
+	count = list_lru_shrink_count(lru, sc);
 	return vfs_pressure_ratio(count);
 }
 

fs/nfs/nfs42xdr.c

@@ -45,6 +45,15 @@
 #define encode_deallocate_maxsz		(op_encode_hdr_maxsz + \
 					 encode_fallocate_maxsz)
 #define decode_deallocate_maxsz		(op_decode_hdr_maxsz)
+#define encode_read_plus_maxsz		(op_encode_hdr_maxsz + \
+					 encode_stateid_maxsz + 3)
+#define NFS42_READ_PLUS_SEGMENT_SIZE	(1 /* data_content4 */ + \
+					 2 /* data_info4.di_offset */ + \
+					 2 /* data_info4.di_length */)
+#define decode_read_plus_maxsz		(op_decode_hdr_maxsz + \
+					 1 /* rpr_eof */ + \
+					 1 /* rpr_contents count */ + \
+					 2 * NFS42_READ_PLUS_SEGMENT_SIZE)
 #define encode_seek_maxsz		(op_encode_hdr_maxsz + \
 					 encode_stateid_maxsz + \
 					 2 /* offset */ + \
@@ -128,6 +137,14 @@
 					 decode_putfh_maxsz + \
 					 decode_deallocate_maxsz + \
 					 decode_getattr_maxsz)
+#define NFS4_enc_read_plus_sz		(compound_encode_hdr_maxsz + \
+					 encode_sequence_maxsz + \
+					 encode_putfh_maxsz + \
+					 encode_read_plus_maxsz)
+#define NFS4_dec_read_plus_sz		(compound_decode_hdr_maxsz + \
+					 decode_sequence_maxsz + \
+					 decode_putfh_maxsz + \
+					 decode_read_plus_maxsz)
 #define NFS4_enc_seek_sz		(compound_encode_hdr_maxsz + \
 					 encode_sequence_maxsz + \
 					 encode_putfh_maxsz + \
@@ -324,6 +341,16 @@ static void encode_deallocate(struct xdr_stream *xdr,
 	encode_fallocate(xdr, args);
 }
 
+static void encode_read_plus(struct xdr_stream *xdr,
+			     const struct nfs_pgio_args *args,
+			     struct compound_hdr *hdr)
+{
+	encode_op_hdr(xdr, OP_READ_PLUS, decode_read_plus_maxsz, hdr);
+	encode_nfs4_stateid(xdr, &args->stateid);
+	encode_uint64(xdr, args->offset);
+	encode_uint32(xdr, args->count);
+}
+
 static void encode_seek(struct xdr_stream *xdr,
 			const struct nfs42_seek_args *args,
 			struct compound_hdr *hdr)
@@ -722,6 +749,28 @@ static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req,
 	encode_nops(&hdr);
 }
 
+/*
+ * Encode READ_PLUS request
+ */
+static void nfs4_xdr_enc_read_plus(struct rpc_rqst *req,
+				   struct xdr_stream *xdr,
+				   const void *data)
+{
+	const struct nfs_pgio_args *args = data;
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, args->fh, &hdr);
+	encode_read_plus(xdr, args, &hdr);
+
+	rpc_prepare_reply_pages(req, args->pages, args->pgbase,
+				args->count, hdr.replen);
+	encode_nops(&hdr);
+}
+
 /*
  * Encode SEEK request
  */
@@ -970,6 +1019,97 @@ static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res *re
 	return decode_op_hdr(xdr, OP_DEALLOCATE);
 }
 
+static int decode_read_plus_data(struct xdr_stream *xdr, struct nfs_pgio_res *res,
+				 uint32_t *eof)
+{
+	uint32_t count, recvd;
+	uint64_t offset;
+	__be32 *p;
+
+	p = xdr_inline_decode(xdr, 8 + 4);
+	if (unlikely(!p))
+		return -EIO;
+
+	p = xdr_decode_hyper(p, &offset);
+	count = be32_to_cpup(p);
+	recvd = xdr_align_data(xdr, res->count, count);
+	res->count += recvd;
+
+	if (count > recvd) {
+		dprintk("NFS: server cheating in read reply: "
+				"count %u > recvd %u\n", count, recvd);
+		*eof = 0;
+		return 1;
+	}
+
+	return 0;
+}
+
+static int decode_read_plus_hole(struct xdr_stream *xdr, struct nfs_pgio_res *res,
+				 uint32_t *eof)
+{
+	uint64_t offset, length, recvd;
+	__be32 *p;
+
+	p = xdr_inline_decode(xdr, 8 + 8);
+	if (unlikely(!p))
+		return -EIO;
+
+	p = xdr_decode_hyper(p, &offset);
+	p = xdr_decode_hyper(p, &length);
+	recvd = xdr_expand_hole(xdr, res->count, length);
+	res->count += recvd;
+
+	if (recvd < length) {
+		*eof = 0;
+		return 1;
+	}
+	return 0;
+}
+
+static int decode_read_plus(struct xdr_stream *xdr, struct nfs_pgio_res *res)
+{
+	uint32_t eof, segments, type;
+	int status, i;
+	__be32 *p;
+
+	status = decode_op_hdr(xdr, OP_READ_PLUS);
+	if (status)
+		return status;
+
+	p = xdr_inline_decode(xdr, 4 + 4);
+	if (unlikely(!p))
+		return -EIO;
+
+	eof = be32_to_cpup(p++);
+	segments = be32_to_cpup(p++);
+	if (segments == 0)
+		goto out;
+
+	for (i = 0; i < segments; i++) {
+		p = xdr_inline_decode(xdr, 4);
+		if (unlikely(!p))
+			return -EIO;
+
+		type = be32_to_cpup(p++);
+		if (type == NFS4_CONTENT_DATA)
+			status = decode_read_plus_data(xdr, res, &eof);
+		else if (type == NFS4_CONTENT_HOLE)
+			status = decode_read_plus_hole(xdr, res, &eof);
+		else
+			return -EINVAL;
+
+		if (status < 0)
+			return status;
+		if (status > 0)
+			break;
+	}
+
+out:
+	res->eof = eof;
+	return 0;
+}
+
 static int decode_seek(struct xdr_stream *xdr, struct nfs42_seek_res *res)
 {
 	int status;
@@ -1146,6 +1286,33 @@ static int nfs4_xdr_dec_deallocate(struct rpc_rqst *rqstp,
 	return status;
 }
 
+/*
+ * Decode READ_PLUS request
+ */
+static int nfs4_xdr_dec_read_plus(struct rpc_rqst *rqstp,
+				  struct xdr_stream *xdr,
+				  void *data)
+{
+	struct nfs_pgio_res *res = data;
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_read_plus(xdr, res);
+	if (!status)
+		status = res->count;
+out:
+	return status;
+}
+
 /*
  * Decode SEEK request
  */

fs/nfs/nfs4_fs.h

@@ -599,6 +599,14 @@ static inline bool nfs4_stateid_is_newer(const nfs4_stateid *s1, const nfs4_stat
 	return (s32)(be32_to_cpu(s1->seqid) - be32_to_cpu(s2->seqid)) > 0;
 }
 
+static inline bool nfs4_stateid_is_next(const nfs4_stateid *s1, const nfs4_stateid *s2)
+{
+	u32 seq1 = be32_to_cpu(s1->seqid);
+	u32 seq2 = be32_to_cpu(s2->seqid);
+
+	return seq2 == seq1 + 1U || (seq2 == 1U && seq1 == 0xffffffffU);
+}
+
 static inline bool nfs4_stateid_match_or_older(const nfs4_stateid *dst, const nfs4_stateid *src)
 {
 	return nfs4_stateid_match_other(dst, src) &&

fs/nfs/nfs4client.c

@@ -1045,6 +1045,8 @@ static int nfs4_server_common_setup(struct nfs_server *server,
 	server->caps |= server->nfs_client->cl_mvops->init_caps;
 	if (server->flags & NFS_MOUNT_NORDIRPLUS)
 			server->caps &= ~NFS_CAP_READDIRPLUS;
+	if (server->nfs_client->cl_proto == XPRT_TRANSPORT_RDMA)
+		server->caps &= ~NFS_CAP_READ_PLUS;
 	/*
 	 * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower
 	 * authentication.

fs/nfs/nfs4file.c

@@ -145,7 +145,8 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
 	/* Only offload copy if superblock is the same */
 	if (file_in->f_op != &nfs4_file_operations)
 		return -EXDEV;
-	if (!nfs_server_capable(file_inode(file_out), NFS_CAP_COPY))
+	if (!nfs_server_capable(file_inode(file_out), NFS_CAP_COPY) ||
+	    !nfs_server_capable(file_inode(file_in), NFS_CAP_COPY))
 		return -EOPNOTSUPP;
 	if (file_inode(file_in) == file_inode(file_out))
 		return -EOPNOTSUPP;

fs/nfs/nfs4idmap.c

@@ -46,6 +46,7 @@
 #include <keys/user-type.h>
 #include <keys/request_key_auth-type.h>
 #include <linux/module.h>
+#include <linux/user_namespace.h>
 
 #include "internal.h"
 #include "netns.h"
@@ -69,13 +70,13 @@ struct idmap {
 	struct rpc_pipe		*idmap_pipe;
 	struct idmap_legacy_upcalldata *idmap_upcall_data;
 	struct mutex		idmap_mutex;
-	const struct cred	*cred;
+	struct user_namespace	*user_ns;
 };
 
 static struct user_namespace *idmap_userns(const struct idmap *idmap)
 {
-	if (idmap && idmap->cred)
-		return idmap->cred->user_ns;
+	if (idmap && idmap->user_ns)
+		return idmap->user_ns;
 	return &init_user_ns;
 }
 
@@ -286,7 +287,7 @@ static struct key *nfs_idmap_request_key(const char *name, size_t namelen,
 	if (ret < 0)
 		return ERR_PTR(ret);
 
-	if (!idmap->cred || idmap->cred->user_ns == &init_user_ns)
+	if (!idmap->user_ns || idmap->user_ns == &init_user_ns)
 		rkey = request_key(&key_type_id_resolver, desc, "");
 	if (IS_ERR(rkey)) {
 		mutex_lock(&idmap->idmap_mutex);
@@ -462,7 +463,7 @@ nfs_idmap_new(struct nfs_client *clp)
 		return -ENOMEM;
 
 	mutex_init(&idmap->idmap_mutex);
-	idmap->cred = get_cred(clp->cl_rpcclient->cl_cred);
+	idmap->user_ns = get_user_ns(clp->cl_rpcclient->cl_cred->user_ns);
 
 	rpc_init_pipe_dir_object(&idmap->idmap_pdo,
 			&nfs_idmap_pipe_dir_object_ops,
@@ -486,7 +487,7 @@ nfs_idmap_new(struct nfs_client *clp)
 err_destroy_pipe:
 	rpc_destroy_pipe_data(idmap->idmap_pipe);
 err:
-	put_cred(idmap->cred);
+	get_user_ns(idmap->user_ns);
 	kfree(idmap);
 	return error;
 }
@@ -503,7 +504,7 @@ nfs_idmap_delete(struct nfs_client *clp)
 			&clp->cl_rpcclient->cl_pipedir_objects,
 			&idmap->idmap_pdo);
 	rpc_destroy_pipe_data(idmap->idmap_pipe);
-	put_cred(idmap->cred);
+	put_user_ns(idmap->user_ns);
 	kfree(idmap);
 }