Merge tag 'nfs-for-4.9-1' of git://git.linux-nfs.org/projects/anna/linux-nfs

Pull NFS client updates from Anna Schumaker:
 "Highlights include:

  Stable bugfixes:
   - sunrpc: fix writ espace race causing stalls
   - NFS: Fix inode corruption in nfs_prime_dcache()
   - NFSv4: Don't report revoked delegations as valid in nfs_have_delegation()
   - NFSv4: nfs4_copy_delegation_stateid() must fail if the delegation is invalid
   - NFSv4: Open state recovery must account for file permission changes
   - NFSv4.2: Fix a reference leak in nfs42_proc_layoutstats_generic

  Features:
   - Add support for tracking multiple layout types with an ordered list
   - Add support for using multiple backchannel threads on the client
   - Add support for pNFS file layout session trunking
   - Delay xprtrdma use of DMA API (for device driver removal)
   - Add support for xprtrdma remote invalidation
   - Add support for larger xprtrdma inline thresholds
   - Use a scatter/gather list for sending xprtrdma RPC calls
   - Add support for the CB_NOTIFY_LOCK callback
   - Improve hashing sunrpc auth_creds by using both uid and gid

  Bugfixes:
   - Fix xprtrdma use of DMA API
   - Validate filenames before adding to the dcache
   - Fix corruption of xdr->nwords in xdr_copy_to_scratch
   - Fix setting buffer length in xdr_set_next_buffer()
   - Don't deadlock the state manager on the SEQUENCE status flags
   - Various delegation and stateid related fixes
   - Retry operations if an interrupted slot receives EREMOTEIO
   - Make nfs boot time y2038 safe"

* tag 'nfs-for-4.9-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (100 commits)
  NFSv4.2: Fix a reference leak in nfs42_proc_layoutstats_generic
  fs: nfs: Make nfs boot time y2038 safe
  sunrpc: replace generic auth_cred hash with auth-specific function
  sunrpc: add RPCSEC_GSS hash_cred() function
  sunrpc: add auth_unix hash_cred() function
  sunrpc: add generic_auth hash_cred() function
  sunrpc: add hash_cred() function to rpc_authops struct
  Retry operation on EREMOTEIO on an interrupted slot
  pNFS: Fix atime updates on pNFS clients
  sunrpc: queue work on system_power_efficient_wq
  NFSv4.1: Even if the stateid is OK, we may need to recover the open modes
  NFSv4: If recovery failed for a specific open stateid, then don't retry
  NFSv4: Fix retry issues with nfs41_test/free_stateid
  NFSv4: Open state recovery must account for file permission changes
  NFSv4: Mark the lock and open stateids as invalid after freeing them
  NFSv4: Don't test open_stateid unless it is set
  NFSv4: nfs4_do_handle_exception() handle revoke/expiry of a single stateid
  NFS: Always call nfs_inode_find_state_and_recover() when revoking a delegation
  NFSv4: Fix a race when updating an open_stateid
  NFSv4: Fix a race in nfs_inode_reclaim_delegation()
  ...

11 files changed, 58 insertions, 10 deletions

diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index c6564ada9beb..9094faf0699d 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -67,6 +67,7 @@ struct nfs4_stateid_struct {
 		NFS4_DELEGATION_STATEID_TYPE,
 		NFS4_LAYOUT_STATEID_TYPE,
 		NFS4_PNFS_DS_STATEID_TYPE,
+		NFS4_REVOKED_STATEID_TYPE,
 	} type;
 };
 
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 14a762d2734d..b34097c67848 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -103,6 +103,9 @@ struct nfs_client {
 #define NFS_SP4_MACH_CRED_WRITE    5	/* WRITE */
 #define NFS_SP4_MACH_CRED_COMMIT   6	/* COMMIT */
 #define NFS_SP4_MACH_CRED_PNFS_CLEANUP  7 /* LAYOUTRETURN */
+#if IS_ENABLED(CONFIG_NFS_V4_1)
+	wait_queue_head_t	cl_lock_waitq;
+#endif /* CONFIG_NFS_V4_1 */
 #endif /* CONFIG_NFS_V4 */
 
 	/* Our own IP address, as a null-terminated string.
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 7cc0deee5bde..beb1e10f446e 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -125,6 +125,11 @@ struct nfs_fattr {
 		| NFS_ATTR_FATTR_V4_SECURITY_LABEL)
 
 /*
+ * Maximal number of supported layout drivers.
+ */
+#define NFS_MAX_LAYOUT_TYPES 8
+
+/*
  * Info on the file system
  */
 struct nfs_fsinfo {
@@ -139,7 +144,8 @@ struct nfs_fsinfo {
 	__u64			maxfilesize;
 	struct timespec		time_delta; /* server time granularity */
 	__u32			lease_time; /* in seconds */
-	__u32			layouttype; /* supported pnfs layout driver */
+	__u32			nlayouttypes; /* number of layouttypes */
+	__u32			layouttype[NFS_MAX_LAYOUT_TYPES]; /* supported pnfs layout driver */
 	__u32			blksize; /* preferred pnfs io block size */
 	__u32			clone_blksize; /* granularity of a CLONE operation */
 };
diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h
index 4ccf184e971f..b1bc62ba20a2 100644
--- a/include/linux/sunrpc/auth.h
+++ b/include/linux/sunrpc/auth.h
@@ -131,6 +131,7 @@ struct rpc_authops {
 	struct rpc_auth *	(*create)(struct rpc_auth_create_args *, struct rpc_clnt *);
 	void			(*destroy)(struct rpc_auth *);
 
+	int			(*hash_cred)(struct auth_cred *, unsigned int);
 	struct rpc_cred *	(*lookup_cred)(struct rpc_auth *, struct auth_cred *, int);
 	struct rpc_cred *	(*crcreate)(struct rpc_auth*, struct auth_cred *, int, gfp_t);
 	int			(*list_pseudoflavors)(rpc_authflavor_t *, int);
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 5c02b0691587..85cc819676e8 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -125,6 +125,13 @@ struct rpc_create_args {
 	struct svc_xprt		*bc_xprt;	/* NFSv4.1 backchannel */
 };
 
+struct rpc_add_xprt_test {
+	int (*add_xprt_test)(struct rpc_clnt *,
+		struct rpc_xprt *,
+		void *calldata);
+	void *data;
+};
+
 /* Values for "flags" field */
 #define RPC_CLNT_CREATE_HARDRTRY	(1UL << 0)
 #define RPC_CLNT_CREATE_AUTOBIND	(1UL << 2)
@@ -198,6 +205,16 @@ int		rpc_clnt_add_xprt(struct rpc_clnt *, struct xprt_create *,
 void		rpc_cap_max_reconnect_timeout(struct rpc_clnt *clnt,
 			unsigned long timeo);
 
+int		rpc_clnt_setup_test_and_add_xprt(struct rpc_clnt *,
+			struct rpc_xprt_switch *,
+			struct rpc_xprt *,
+			void *);
+
 const char *rpc_proc_name(const struct rpc_task *task);
+
+void rpc_clnt_xprt_switch_put(struct rpc_clnt *);
+void rpc_clnt_xprt_switch_add_xprt(struct rpc_clnt *, struct rpc_xprt *);
+bool rpc_clnt_xprt_switch_has_addr(struct rpc_clnt *clnt,
+			const struct sockaddr *sap);
 #endif /* __KERNEL__ */
 #endif /* _LINUX_SUNRPC_CLNT_H */
diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h
index a7da6bf56610..cfda6adcf33c 100644
--- a/include/linux/sunrpc/rpc_rdma.h
+++ b/include/linux/sunrpc/rpc_rdma.h
@@ -46,6 +46,10 @@
 #define RPCRDMA_VERSION		1
 #define rpcrdma_version		cpu_to_be32(RPCRDMA_VERSION)
 
+enum {
+	RPCRDMA_V1_DEF_INLINE_SIZE	= 1024,
+};
+
 struct rpcrdma_segment {
 	__be32 rs_handle;	/* Registered memory handle */
 	__be32 rs_length;	/* Length of the chunk in bytes */
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 817af0b4385e..7ba040c797ec 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -239,8 +239,8 @@ struct rpc_task *rpc_wake_up_first(struct rpc_wait_queue *,
 					void *);
 void		rpc_wake_up_status(struct rpc_wait_queue *, int);
 void		rpc_delay(struct rpc_task *, unsigned long);
-void *		rpc_malloc(struct rpc_task *, size_t);
-void		rpc_free(void *);
+int		rpc_malloc(struct rpc_task *);
+void		rpc_free(struct rpc_task *);
 int		rpciod_up(void);
 void		rpciod_down(void);
 int		__rpc_wait_for_completion_task(struct rpc_task *task, wait_bit_action_f *);
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 70c6b92e15a7..56c48c884a24 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -67,6 +67,18 @@ struct xdr_buf {
 			len;		/* Length of XDR encoded message */
 };
 
+static inline void
+xdr_buf_init(struct xdr_buf *buf, void *start, size_t len)
+{
+	buf->head[0].iov_base = start;
+	buf->head[0].iov_len = len;
+	buf->tail[0].iov_len = 0;
+	buf->page_len = 0;
+	buf->flags = 0;
+	buf->len = 0;
+	buf->buflen = len;
+}
+
 /*
  * pre-xdr'ed macros.
  */
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index a16070dd03ee..a5da60b24d83 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -83,9 +83,11 @@ struct rpc_rqst {
 	void (*rq_release_snd_buf)(struct rpc_rqst *); /* release rq_enc_pages */
 	struct list_head	rq_list;
 
-	__u32 *			rq_buffer;	/* XDR encode buffer */
-	size_t			rq_callsize,
-				rq_rcvsize;
+	void			*rq_xprtdata;	/* Per-xprt private data */
+	void			*rq_buffer;	/* Call XDR encode buffer */
+	size_t			rq_callsize;
+	void			*rq_rbuffer;	/* Reply XDR decode buffer */
+	size_t			rq_rcvsize;
 	size_t			rq_xmit_bytes_sent;	/* total bytes sent */
 	size_t			rq_reply_bytes_recvd;	/* total reply bytes */
 							/* received */
@@ -127,8 +129,8 @@ struct rpc_xprt_ops {
 	void		(*rpcbind)(struct rpc_task *task);
 	void		(*set_port)(struct rpc_xprt *xprt, unsigned short port);
 	void		(*connect)(struct rpc_xprt *xprt, struct rpc_task *task);
-	void *		(*buf_alloc)(struct rpc_task *task, size_t size);
-	void		(*buf_free)(void *buffer);
+	int		(*buf_alloc)(struct rpc_task *task);
+	void		(*buf_free)(struct rpc_task *task);
 	int		(*send_request)(struct rpc_task *task);
 	void		(*set_retrans_timeout)(struct rpc_task *task);
 	void		(*timer)(struct rpc_xprt *xprt, struct rpc_task *task);
diff --git a/include/linux/sunrpc/xprtmultipath.h b/include/linux/sunrpc/xprtmultipath.h
index 5a9acffa41be..507418c1c69e 100644
--- a/include/linux/sunrpc/xprtmultipath.h
+++ b/include/linux/sunrpc/xprtmultipath.h
@@ -66,4 +66,6 @@ extern struct rpc_xprt *xprt_iter_xprt(struct rpc_xprt_iter *xpi);
 extern struct rpc_xprt *xprt_iter_get_xprt(struct rpc_xprt_iter *xpi);
 extern struct rpc_xprt *xprt_iter_get_next(struct rpc_xprt_iter *xpi);
 
+extern bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps,
+		const struct sockaddr *sap);
 #endif
diff --git a/include/linux/sunrpc/xprtrdma.h b/include/linux/sunrpc/xprtrdma.h
index 39267dc3486a..221b7a2e5406 100644
--- a/include/linux/sunrpc/xprtrdma.h
+++ b/include/linux/sunrpc/xprtrdma.h
@@ -53,8 +53,8 @@
 #define RPCRDMA_MAX_SLOT_TABLE	(256U)
 
 #define RPCRDMA_MIN_INLINE  (1024)	/* min inline thresh */
-#define RPCRDMA_DEF_INLINE  (1024)	/* default inline thresh */
-#define RPCRDMA_MAX_INLINE  (3068)	/* max inline thresh */
+#define RPCRDMA_DEF_INLINE  (4096)	/* default inline thresh */
+#define RPCRDMA_MAX_INLINE  (65536)	/* max inline thresh */
 
 /* Memory registration strategies, by number.
  * This is part of a kernel / user space API. Do not remove. */