Merge tag 'nfs-for-4.3-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

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

  Stable patches:
   - Fix atomicity of pNFS commit list updates
   - Fix NFSv4 handling of open(O_CREAT|O_EXCL|O_RDONLY)
   - nfs_set_pgio_error sometimes misses errors
   - Fix a thinko in xs_connect()
   - Fix borkage in _same_data_server_addrs_locked()
   - Fix a NULL pointer dereference of migration recovery ops for v4.2
     client
   - Don't let the ctime override attribute barriers.
   - Revert "NFSv4: Remove incorrect check in can_open_delegated()"
   - Ensure flexfiles pNFS driver updates the inode after write finishes
   - flexfiles must not pollute the attribute cache with attrbutes from
     the DS
   - Fix a protocol error in layoutreturn
   - Fix a protocol issue with NFSv4.1 CLOSE stateids

  Bugfixes + cleanups
   - pNFS blocks bugfixes from Christoph
   - Various cleanups from Anna
   - More fixes for delegation corner cases
   - Don't fsync twice for O_SYNC/IS_SYNC files
   - Fix pNFS and flexfiles layoutstats bugs
   - pnfs/flexfiles: avoid duplicate tracking of mirror data
   - pnfs: Fix layoutget/layoutreturn/return-on-close serialisation
     issues
   - pnfs/flexfiles: error handling retries a layoutget before fallback
     to MDS

  Features:
   - Full support for the OPEN NFS4_CREATE_EXCLUSIVE4_1 mode from
     Kinglong
   - More RDMA client transport improvements from Chuck
   - Removal of the deprecated ib_reg_phys_mr() and ib_rereg_phys_mr()
     verbs from the SUNRPC, Lustre and core infiniband tree.
   - Optimise away the close-to-open getattr if there is no cached data"

* tag 'nfs-for-4.3-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (108 commits)
  NFSv4: Respect the server imposed limit on how many changes we may cache
  NFSv4: Express delegation limit in units of pages
  Revert "NFS: Make close(2) asynchronous when closing NFS O_DIRECT files"
  NFS: Optimise away the close-to-open getattr if there is no cached data
  NFSv4.1/flexfiles: Clean up ff_layout_write_done_cb/ff_layout_commit_done_cb
  NFSv4.1/flexfiles: Mark the layout for return in ff_layout_io_track_ds_error()
  nfs: Remove unneeded checking of the return value from scnprintf
  nfs: Fix truncated client owner id without proto type
  NFSv4.1/flexfiles: Mark layout for return if the mirrors are invalid
  NFSv4.1/flexfiles: RW layouts are valid only if all mirrors are valid
  NFSv4.1/flexfiles: Fix incorrect usage of pnfs_generic_mark_devid_invalid()
  NFSv4.1/flexfiles: Fix freeing of mirrors
  NFSv4.1/pNFS: Don't request a minimal read layout beyond the end of file
  NFSv4.1/pnfs: Handle LAYOUTGET return values correctly
  NFSv4.1/pnfs: Don't ask for a read layout for an empty file.
  NFSv4.1: Fix a protocol issue with CLOSE stateids
  NFSv4.1/flexfiles: Don't mark the entire deviceid as bad for file errors
  SUNRPC: Prevent SYN+SYNACK+RST storms
  SUNRPC: xs_reset_transport must mark the connection as disconnected
  NFSv4.1/pnfs: Ensure layoutreturn reserves space for the opaque payload
  ...

9 files changed, 57 insertions, 61 deletions

diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index b8e72aad919c..00121f298269 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -547,6 +547,24 @@ enum pnfs_notify_deviceid_type4 {
 	NOTIFY_DEVICEID4_DELETE = 1 << 2,
 };
 
+enum pnfs_block_volume_type {
+	PNFS_BLOCK_VOLUME_SIMPLE	= 0,
+	PNFS_BLOCK_VOLUME_SLICE		= 1,
+	PNFS_BLOCK_VOLUME_CONCAT	= 2,
+	PNFS_BLOCK_VOLUME_STRIPE	= 3,
+};
+
+enum pnfs_block_extent_state {
+	PNFS_BLOCK_READWRITE_DATA	= 0,
+	PNFS_BLOCK_READ_DATA		= 1,
+	PNFS_BLOCK_INVALID_DATA		= 2,
+	PNFS_BLOCK_NONE_DATA		= 3,
+};
+
+/* on the wire size of a block layout extent */
+#define PNFS_BLOCK_EXTENT_SIZE \
+	(7 * sizeof(__be32) + NFS4_DEVICEID4_SIZE)
+
 #define NFL4_UFLG_MASK			0x0000003F
 #define NFL4_UFLG_DENSE			0x00000001
 #define NFL4_UFLG_COMMIT_THRU_MDS	0x00000002
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 874b77228fb9..c0e961474a52 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -353,7 +353,6 @@ extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *);
 extern void nfs_access_set_mask(struct nfs_access_entry *, u32);
 extern int nfs_permission(struct inode *, int);
 extern int nfs_open(struct inode *, struct file *);
-extern int nfs_release(struct inode *, struct file *);
 extern int nfs_attribute_timeout(struct inode *inode);
 extern int nfs_attribute_cache_expired(struct inode *inode);
 extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode);
@@ -371,6 +370,7 @@ extern struct nfs_open_context *nfs_find_open_context(struct inode *inode, struc
 extern struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f_mode);
 extern void nfs_inode_attach_open_context(struct nfs_open_context *ctx);
 extern void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx);
+extern void nfs_file_clear_open_context(struct file *flip);
 extern struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx);
 extern void nfs_put_lock_context(struct nfs_lock_context *l_ctx);
 extern u64 nfs_compat_user_ino64(u64 fileid);
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 20bc8e51b161..570a7df2775b 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -173,6 +173,11 @@ struct nfs_server {
 						   set of attributes supported
 						   on this filesystem excluding
 						   the label support bit. */
+	u32			exclcreat_bitmask[3];
+						/* V4 bitmask representing the
+						   set of attributes supported
+						   on this filesystem for the
+						   exclusive create. */
 	u32			cache_consistency_bitmask[3];
 						/* V4 bitmask representing the subset
 						   of change attribute, size, ctime
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 7bbe50504211..52faf7e96c65 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -379,7 +379,7 @@ struct nfs_openargs {
 	struct stateowner_id	id;
 	union {
 		struct {
-			struct iattr *  attrs;    /* UNCHECKED, GUARDED */
+			struct iattr *  attrs;    /* UNCHECKED, GUARDED, EXCLUSIVE4_1 */
 			nfs4_verifier   verifier; /* EXCLUSIVE */
 		};
 		nfs4_stateid	delegation;		/* CLAIM_DELEGATE_CUR */
@@ -389,7 +389,7 @@ struct nfs_openargs {
 	const struct nfs_server *server;	 /* Needed for ID mapping */
 	const u32 *		bitmask;
 	const u32 *		open_bitmap;
-	__u32			claim;
+	enum open_claim_type4	claim;
 	enum createmode4	createmode;
 	const struct nfs4_label *label;
 };
@@ -406,8 +406,8 @@ struct nfs_openres {
 	const struct nfs_server *server;
 	fmode_t			delegation_type;
 	nfs4_stateid		delegation;
+	unsigned long		pagemod_limit;
 	__u32			do_recall;
-	__u64			maxsize;
 	__u32			attrset[NFS4_BITMAP_SIZE];
 	struct nfs4_string	*owner;
 	struct nfs4_string	*group_owner;
@@ -1057,11 +1057,13 @@ struct nfs4_statfs_res {
 struct nfs4_server_caps_arg {
 	struct nfs4_sequence_args	seq_args;
 	struct nfs_fh		       *fhandle;
+	const u32 *			bitmask;
 };
 
 struct nfs4_server_caps_res {
 	struct nfs4_sequence_res	seq_res;
 	u32				attr_bitmask[3];
+	u32				exclcreat_bitmask[3];
 	u32				acl_bitmask;
 	u32				has_links;
 	u32				has_symlinks;
diff --git a/include/linux/sunrpc/addr.h b/include/linux/sunrpc/addr.h
index 07d8e53bedfc..5c9c6cd08d3b 100644
--- a/include/linux/sunrpc/addr.h
+++ b/include/linux/sunrpc/addr.h
@@ -46,8 +46,8 @@ static inline void rpc_set_port(struct sockaddr *sap,
 #define IPV6_SCOPE_DELIMITER		'%'
 #define IPV6_SCOPE_ID_LEN		sizeof("%nnnnnnnnnn")
 
-static inline bool __rpc_cmp_addr4(const struct sockaddr *sap1,
-				   const struct sockaddr *sap2)
+static inline bool rpc_cmp_addr4(const struct sockaddr *sap1,
+				 const struct sockaddr *sap2)
 {
 	const struct sockaddr_in *sin1 = (const struct sockaddr_in *)sap1;
 	const struct sockaddr_in *sin2 = (const struct sockaddr_in *)sap2;
@@ -67,8 +67,8 @@ static inline bool __rpc_copy_addr4(struct sockaddr *dst,
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
-static inline bool __rpc_cmp_addr6(const struct sockaddr *sap1,
-				   const struct sockaddr *sap2)
+static inline bool rpc_cmp_addr6(const struct sockaddr *sap1,
+				 const struct sockaddr *sap2)
 {
 	const struct sockaddr_in6 *sin1 = (const struct sockaddr_in6 *)sap1;
 	const struct sockaddr_in6 *sin2 = (const struct sockaddr_in6 *)sap2;
@@ -93,7 +93,7 @@ static inline bool __rpc_copy_addr6(struct sockaddr *dst,
 	return true;
 }
 #else	/* !(IS_ENABLED(CONFIG_IPV6) */
-static inline bool __rpc_cmp_addr6(const struct sockaddr *sap1,
+static inline bool rpc_cmp_addr6(const struct sockaddr *sap1,
 				   const struct sockaddr *sap2)
 {
 	return false;
@@ -122,15 +122,28 @@ static inline bool rpc_cmp_addr(const struct sockaddr *sap1,
 	if (sap1->sa_family == sap2->sa_family) {
 		switch (sap1->sa_family) {
 		case AF_INET:
-			return __rpc_cmp_addr4(sap1, sap2);
+			return rpc_cmp_addr4(sap1, sap2);
 		case AF_INET6:
-			return __rpc_cmp_addr6(sap1, sap2);
+			return rpc_cmp_addr6(sap1, sap2);
 		}
 	}
 	return false;
 }
 
 /**
+ * rpc_cmp_addr_port - compare the address and port number of two sockaddrs.
+ * @sap1: first sockaddr
+ * @sap2: second sockaddr
+ */
+static inline bool rpc_cmp_addr_port(const struct sockaddr *sap1,
+				     const struct sockaddr *sap2)
+{
+	if (!rpc_cmp_addr(sap1, sap2))
+		return false;
+	return rpc_get_port(sap1) == rpc_get_port(sap2);
+}
+
+/**
  * rpc_copy_addr - copy the address portion of one sockaddr to another
  * @dst: destination sockaddr
  * @src: source sockaddr
diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h
index a7cbb570cc5c..1ecf13e148b8 100644
--- a/include/linux/sunrpc/auth.h
+++ b/include/linux/sunrpc/auth.h
@@ -18,9 +18,13 @@
 #include <linux/atomic.h>
 #include <linux/rcupdate.h>
 #include <linux/uidgid.h>
+#include <linux/utsname.h>
 
-/* size of the nodename buffer */
-#define UNX_MAXNODENAME	32
+/*
+ * Size of the nodename buffer. RFC1831 specifies a hard limit of 255 bytes,
+ * but Linux hostnames are actually limited to __NEW_UTS_LEN bytes.
+ */
+#define UNX_MAXNODENAME	__NEW_UTS_LEN
 
 struct rpcsec_gss_info;
 
diff --git a/include/linux/sunrpc/xprtrdma.h b/include/linux/sunrpc/xprtrdma.h
index b17613052cc3..b7b279b54504 100644
--- a/include/linux/sunrpc/xprtrdma.h
+++ b/include/linux/sunrpc/xprtrdma.h
@@ -49,7 +49,7 @@
  * a single chunk type per message is supported currently.
  */
 #define RPCRDMA_MIN_SLOT_TABLE	(2U)
-#define RPCRDMA_DEF_SLOT_TABLE	(32U)
+#define RPCRDMA_DEF_SLOT_TABLE	(128U)
 #define RPCRDMA_MAX_SLOT_TABLE	(256U)
 
 #define RPCRDMA_DEF_INLINE  (1024)	/* default inline max */
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index b0f898e3b2e7..43c1cf01c84b 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2760,52 +2760,6 @@ static inline void ib_dma_free_coherent(struct ib_device *dev,
 }
 
 /**
- * ib_reg_phys_mr - Prepares a virtually addressed memory region for use
- *   by an HCA.
- * @pd: The protection domain associated assigned to the registered region.
- * @phys_buf_array: Specifies a list of physical buffers to use in the
- *   memory region.
- * @num_phys_buf: Specifies the size of the phys_buf_array.
- * @mr_access_flags: Specifies the memory access rights.
- * @iova_start: The offset of the region's starting I/O virtual address.
- */
-struct ib_mr *ib_reg_phys_mr(struct ib_pd *pd,
-			     struct ib_phys_buf *phys_buf_array,
-			     int num_phys_buf,
-			     int mr_access_flags,
-			     u64 *iova_start);
-
-/**
- * ib_rereg_phys_mr - Modifies the attributes of an existing memory region.
- *   Conceptually, this call performs the functions deregister memory region
- *   followed by register physical memory region.  Where possible,
- *   resources are reused instead of deallocated and reallocated.
- * @mr: The memory region to modify.
- * @mr_rereg_mask: A bit-mask used to indicate which of the following
- *   properties of the memory region are being modified.
- * @pd: If %IB_MR_REREG_PD is set in mr_rereg_mask, this field specifies
- *   the new protection domain to associated with the memory region,
- *   otherwise, this parameter is ignored.
- * @phys_buf_array: If %IB_MR_REREG_TRANS is set in mr_rereg_mask, this
- *   field specifies a list of physical buffers to use in the new
- *   translation, otherwise, this parameter is ignored.
- * @num_phys_buf: If %IB_MR_REREG_TRANS is set in mr_rereg_mask, this
- *   field specifies the size of the phys_buf_array, otherwise, this
- *   parameter is ignored.
- * @mr_access_flags: If %IB_MR_REREG_ACCESS is set in mr_rereg_mask, this
- *   field specifies the new memory access rights, otherwise, this
- *   parameter is ignored.
- * @iova_start: The offset of the region's starting I/O virtual address.
- */
-int ib_rereg_phys_mr(struct ib_mr *mr,
-		     int mr_rereg_mask,
-		     struct ib_pd *pd,
-		     struct ib_phys_buf *phys_buf_array,
-		     int num_phys_buf,
-		     int mr_access_flags,
-		     u64 *iova_start);
-
-/**
  * ib_query_mr - Retrieves information about a specific memory region.
  * @mr: The memory region to retrieve information about.
  * @mr_attr: The attributes of the specified memory region.
diff --git a/include/uapi/linux/nfs4.h b/include/uapi/linux/nfs4.h
index 2119c7c274d7..2b871e0858d9 100644
--- a/include/uapi/linux/nfs4.h
+++ b/include/uapi/linux/nfs4.h
@@ -15,7 +15,7 @@
 
 #include <linux/types.h>
 
-#define NFS4_BITMAP_SIZE	2
+#define NFS4_BITMAP_SIZE	3
 #define NFS4_VERIFIER_SIZE	8
 #define NFS4_STATEID_SEQID_SIZE 4
 #define NFS4_STATEID_OTHER_SIZE 12