Merge tag 'nfs-for-4.2-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Highlights include:

  Stable patches:
   - Fix a crash in the NFSv4 file locking code.
   - Fix an fsync() regression, where we were failing to retry I/O in
     some circumstances.
   - Fix an infinite loop in NFSv4.0 OPEN stateid recovery
   - Fix a memory leak when an attempted pnfs fails.
   - Fix a memory leak in the backchannel code
   - Large hostnames were not supported correctly in NFSv4.1
   - Fix a pNFS/flexfiles bug that was impeding error reporting on I/O.
   - Fix a couple of credential issues in pNFS/flexfiles

  Bugfixes + cleanups:
   - Open flag sanity checks in the NFSv4 atomic open codepath
   - More NFSv4 delegation related bugfixes
   - Various NFSv4.1 backchannel bugfixes and cleanups
   - Fix the NFS swap socket code
   - Various cleanups of the NFSv4 SETCLIENTID and EXCHANGE_ID code
   - Fix a UDP transport deadlock issue

  Features:
   - More RDMA client transport improvements
   - NFSv4.2 LAYOUTSTATS functionality for pnfs flexfiles"

* tag 'nfs-for-4.2-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (87 commits)
  nfs: Remove invalid tk_pid from debug message
  nfs: Remove invalid NFS_ATTR_FATTR_V4_REFERRAL checking in nfs4_get_rootfh
  nfs: Drop bad comment in nfs41_walk_client_list()
  nfs: Remove unneeded micro checking of CONFIG_PROC_FS
  nfs: Don't setting FILE_CREATED flags always
  nfs: Use remove_proc_subtree() instead remove_proc_entry()
  nfs: Remove unused argument in nfs_server_set_fsinfo()
  nfs: Fix a memory leak when meeting an unsupported state protect
  nfs: take extra reference to fl->fl_file when running a LOCKU operation
  NFSv4: When returning a delegation, don't reclaim an incompatible open mode.
  NFSv4.2: LAYOUTSTATS is optional to implement
  NFSv4.2: Fix up a decoding error in layoutstats
  pNFS/flexfiles: Fix the reset of struct pgio_header when resending
  pNFS/flexfiles: Turn off layoutcommit for servers that don't need it
  pnfs/flexfiles: protect ktime manipulation with mirror lock
  nfs: provide pnfs_report_layoutstat when NFS42 is disabled
  nfs: verify open flags before allowing open
  nfs: always update creds in mirror, even when we have an already connected ds
  nfs: fix potential credential leak in ff_layout_update_mirror_cred
  pnfs/flexfiles: report layoutstat regularly
  ...

10 files changed, 103 insertions, 15 deletions

diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 32201c269890..b8e72aad919c 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -500,6 +500,7 @@ enum {
 	NFSPROC4_CLNT_SEEK,
 	NFSPROC4_CLNT_ALLOCATE,
 	NFSPROC4_CLNT_DEALLOCATE,
+	NFSPROC4_CLNT_LAYOUTSTATS,
 };
 
 /* nfs41 types */
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index b95f914ce083..f91b5ade30c9 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -219,6 +219,7 @@ struct nfs_inode {
 #define NFS_INO_COMMIT		(7)		/* inode is committing unstable writes */
 #define NFS_INO_LAYOUTCOMMIT	(9)		/* layoutcommit required */
 #define NFS_INO_LAYOUTCOMMITTING (10)		/* layoutcommit inflight */
+#define NFS_INO_LAYOUTSTATS	(11)		/* layoutstats inflight */
 
 static inline struct nfs_inode *NFS_I(const struct inode *inode)
 {
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 5e1273d4de14..a2ea1491d3df 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -237,5 +237,6 @@ struct nfs_server {
 #define NFS_CAP_SEEK		(1U << 19)
 #define NFS_CAP_ALLOCATE	(1U << 20)
 #define NFS_CAP_DEALLOCATE	(1U << 21)
+#define NFS_CAP_LAYOUTSTATS	(1U << 22)
 
 #endif
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index 3eb072dbce83..f2f650f136ee 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -67,7 +67,6 @@ struct nfs_rw_ops {
 	const fmode_t rw_mode;
 	struct nfs_pgio_header *(*rw_alloc_header)(void);
 	void (*rw_free_header)(struct nfs_pgio_header *);
-	void (*rw_release)(struct nfs_pgio_header *);
 	int  (*rw_done)(struct rpc_task *, struct nfs_pgio_header *,
 			struct inode *);
 	void (*rw_result)(struct rpc_task *, struct nfs_pgio_header *);
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 93ab6071bbe9..7bbe50504211 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -316,6 +316,49 @@ struct nfs4_layoutreturn {
 	int rpc_status;
 };
 
+#define PNFS_LAYOUTSTATS_MAXSIZE 256
+
+struct nfs42_layoutstat_args;
+struct nfs42_layoutstat_devinfo;
+typedef	void (*layoutstats_encode_t)(struct xdr_stream *,
+		struct nfs42_layoutstat_args *,
+		struct nfs42_layoutstat_devinfo *);
+
+/* Per file per deviceid layoutstats */
+struct nfs42_layoutstat_devinfo {
+	struct nfs4_deviceid dev_id;
+	__u64 offset;
+	__u64 length;
+	__u64 read_count;
+	__u64 read_bytes;
+	__u64 write_count;
+	__u64 write_bytes;
+	__u32 layout_type;
+	layoutstats_encode_t layoutstats_encode;
+	void *layout_private;
+};
+
+struct nfs42_layoutstat_args {
+	struct nfs4_sequence_args seq_args;
+	struct nfs_fh *fh;
+	struct inode *inode;
+	nfs4_stateid stateid;
+	int num_dev;
+	struct nfs42_layoutstat_devinfo *devinfo;
+};
+
+struct nfs42_layoutstat_res {
+	struct nfs4_sequence_res seq_res;
+	int num_dev;
+	int rpc_status;
+};
+
+struct nfs42_layoutstat_data {
+	struct inode *inode;
+	struct nfs42_layoutstat_args args;
+	struct nfs42_layoutstat_res res;
+};
+
 struct stateowner_id {
 	__u64	create_time;
 	__u32	uniquifier;
@@ -984,17 +1027,14 @@ struct nfs4_readlink_res {
 	struct nfs4_sequence_res	seq_res;
 };
 
-#define NFS4_SETCLIENTID_NAMELEN	(127)
 struct nfs4_setclientid {
 	const nfs4_verifier *		sc_verifier;
-	unsigned int			sc_name_len;
-	char				sc_name[NFS4_SETCLIENTID_NAMELEN + 1];
 	u32				sc_prog;
 	unsigned int			sc_netid_len;
 	char				sc_netid[RPCBIND_MAXNETIDLEN + 1];
 	unsigned int			sc_uaddr_len;
 	char				sc_uaddr[RPCBIND_MAXUADDRLEN + 1];
-	u32				sc_cb_ident;
+	struct nfs_client		*sc_clnt;
 	struct rpc_cred			*sc_cred;
 };
 
@@ -1142,12 +1182,9 @@ struct nfs41_state_protection {
 	struct nfs4_op_map allow;
 };
 
-#define NFS4_EXCHANGE_ID_LEN	(48)
 struct nfs41_exchange_id_args {
 	struct nfs_client		*client;
 	nfs4_verifier			*verifier;
-	unsigned int 			id_len;
-	char 				id[NFS4_EXCHANGE_ID_LEN];
 	u32				flags;
 	struct nfs41_state_protection	state_protect;
 };
diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h
index 2ca67b55e0fe..8df43c9f11dc 100644
--- a/include/linux/sunrpc/bc_xprt.h
+++ b/include/linux/sunrpc/bc_xprt.h
@@ -37,7 +37,6 @@ void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied);
 void xprt_free_bc_request(struct rpc_rqst *req);
 int xprt_setup_backchannel(struct rpc_xprt *, unsigned int min_reqs);
 void xprt_destroy_backchannel(struct rpc_xprt *, unsigned int max_reqs);
-int bc_send(struct rpc_rqst *req);
 
 /*
  * Determine if a shared backchannel is in use
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 598ba80ec30c..131032f15cc1 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -56,6 +56,7 @@ struct rpc_clnt {
 	struct rpc_rtt *	cl_rtt;		/* RTO estimator data */
 	const struct rpc_timeout *cl_timeout;	/* Timeout strategy */
 
+	atomic_t		cl_swapper;	/* swapfile count */
 	int			cl_nodelen;	/* nodename length */
 	char 			cl_nodename[UNX_MAXNODENAME+1];
 	struct rpc_pipe_dir_head cl_pipedir_objects;
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 5f1e6bd4c316..d703f0ef37d8 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -205,8 +205,7 @@ struct rpc_wait_queue {
  */
 struct rpc_task *rpc_new_task(const struct rpc_task_setup *);
 struct rpc_task *rpc_run_task(const struct rpc_task_setup *);
-struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req,
-				const struct rpc_call_ops *ops);
+struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req);
 void		rpc_put_task(struct rpc_task *);
 void		rpc_put_task_async(struct rpc_task *);
 void		rpc_exit_task(struct rpc_task *);
@@ -269,4 +268,20 @@ static inline void rpc_assign_waitqueue_name(struct rpc_wait_queue *q,
 }
 #endif
 
+#if IS_ENABLED(CONFIG_SUNRPC_SWAP)
+int rpc_clnt_swap_activate(struct rpc_clnt *clnt);
+void rpc_clnt_swap_deactivate(struct rpc_clnt *clnt);
+#else
+static inline int
+rpc_clnt_swap_activate(struct rpc_clnt *clnt)
+{
+	return -EINVAL;
+}
+
+static inline void
+rpc_clnt_swap_deactivate(struct rpc_clnt *clnt)
+{
+}
+#endif /* CONFIG_SUNRPC_SWAP */
+
 #endif /* _LINUX_SUNRPC_SCHED_H_ */
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 8b93ef53df3c..0fb9acbb4780 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -133,6 +133,9 @@ struct rpc_xprt_ops {
 	void		(*close)(struct rpc_xprt *xprt);
 	void		(*destroy)(struct rpc_xprt *xprt);
 	void		(*print_stats)(struct rpc_xprt *xprt, struct seq_file *seq);
+	int		(*enable_swap)(struct rpc_xprt *xprt);
+	void		(*disable_swap)(struct rpc_xprt *xprt);
+	void		(*inject_disconnect)(struct rpc_xprt *xprt);
 };
 
 /*
@@ -180,7 +183,7 @@ struct rpc_xprt {
 	atomic_t		num_reqs;	/* total slots */
 	unsigned long		state;		/* transport state */
 	unsigned char		resvport   : 1; /* use a reserved port */
-	unsigned int		swapper;	/* we're swapping over this
+	atomic_t		swapper;	/* we're swapping over this
 						   transport */
 	unsigned int		bind_index;	/* bind function index */
 
@@ -212,7 +215,8 @@ struct rpc_xprt {
 #if defined(CONFIG_SUNRPC_BACKCHANNEL)
 	struct svc_serv		*bc_serv;       /* The RPC service which will */
 						/* process the callback */
-	unsigned int		bc_alloc_count;	/* Total number of preallocs */
+	int			bc_alloc_count;	/* Total number of preallocs */
+	atomic_t		bc_free_slots;
 	spinlock_t		bc_pa_lock;	/* Protects the preallocated
 						 * items */
 	struct list_head	bc_pa_list;	/* List of preallocated
@@ -241,6 +245,7 @@ struct rpc_xprt {
 	const char		*address_strings[RPC_DISPLAY_MAX];
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	struct dentry		*debugfs;		/* debugfs directory */
+	atomic_t		inject_disconnect;
 #endif
 };
 
@@ -327,6 +332,18 @@ static inline __be32 *xprt_skip_transport_header(struct rpc_xprt *xprt, __be32 *
 	return p + xprt->tsh_size;
 }
 
+static inline int
+xprt_enable_swap(struct rpc_xprt *xprt)
+{
+	return xprt->ops->enable_swap(xprt);
+}
+
+static inline void
+xprt_disable_swap(struct rpc_xprt *xprt)
+{
+	xprt->ops->disable_swap(xprt);
+}
+
 /*
  * Transport switch helper functions
  */
@@ -345,7 +362,6 @@ void			xprt_release_rqst_cong(struct rpc_task *task);
 void			xprt_disconnect_done(struct rpc_xprt *xprt);
 void			xprt_force_disconnect(struct rpc_xprt *xprt);
 void			xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie);
-int			xs_swapper(struct rpc_xprt *xprt, int enable);
 
 bool			xprt_lock_connect(struct rpc_xprt *, struct rpc_task *, void *);
 void			xprt_unlock_connect(struct rpc_xprt *, void *);
@@ -431,6 +447,23 @@ static inline int xprt_test_and_set_binding(struct rpc_xprt *xprt)
 	return test_and_set_bit(XPRT_BINDING, &xprt->state);
 }
 
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
+extern unsigned int rpc_inject_disconnect;
+static inline void xprt_inject_disconnect(struct rpc_xprt *xprt)
+{
+	if (!rpc_inject_disconnect)
+		return;
+	if (atomic_dec_return(&xprt->inject_disconnect))
+		return;
+	atomic_set(&xprt->inject_disconnect, rpc_inject_disconnect);
+	xprt->ops->inject_disconnect(xprt);
+}
+#else
+static inline void xprt_inject_disconnect(struct rpc_xprt *xprt)
+{
+}
+#endif
+
 #endif /* __KERNEL__*/
 
 #endif /* _LINUX_SUNRPC_XPRT_H */
diff --git a/include/linux/sunrpc/xprtrdma.h b/include/linux/sunrpc/xprtrdma.h
index c984c85981ea..b17613052cc3 100644
--- a/include/linux/sunrpc/xprtrdma.h
+++ b/include/linux/sunrpc/xprtrdma.h
@@ -56,7 +56,8 @@
 
 #define RPCRDMA_INLINE_PAD_THRESH  (512)/* payload threshold to pad (bytes) */
 
-/* memory registration strategies */
+/* Memory registration strategies, by number.
+ * This is part of a kernel / user space API. Do not remove. */
 enum rpcrdma_memreg {
 	RPCRDMA_BOUNCEBUFFERS = 0,
 	RPCRDMA_REGISTER,