Merge tag 'nfs-for-4.4-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

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

  New features:
   - RDMA client backchannel from Chuck
   - Support for NFSv4.2 file CLONE using the btrfs ioctl

  Bugfixes + cleanups:
   - Move socket data receive out of the bottom halves and into a
     workqueue
   - Refactor NFSv4 error handling so synchronous and asynchronous RPC
     handles errors identically.
   - Fix a panic when blocks or object layouts reads return a bad data
     length
   - Fix nfsroot so it can handle a 1024 byte long path.
   - Fix bad usage of page offset in bl_read_pagelist
   - Various NFSv4 callback cleanups+fixes
   - Fix GETATTR bitmap verification
   - Support hexadecimal number for sunrpc debug sysctl files"

* tag 'nfs-for-4.4-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (53 commits)
  Sunrpc: Supports hexadecimal number for sysctl files of sunrpc debug
  nfs: Fix GETATTR bitmap verification
  nfs: Remove unused xdr page offsets in getacl/setacl arguments
  fs/nfs: remove unnecessary new_valid_dev check
  SUNRPC: fix variable type
  NFS: Enable client side NFSv4.1 backchannel to use other transports
  pNFS/flexfiles: Add support for FF_FLAGS_NO_IO_THRU_MDS
  pNFS/flexfiles: When mirrored, retry failed reads by switching mirrors
  SUNRPC: Remove the TCP-only restriction in bc_svc_process()
  svcrdma: Add backward direction service for RPC/RDMA transport
  xprtrdma: Handle incoming backward direction RPC calls
  xprtrdma: Add support for sending backward direction RPC replies
  xprtrdma: Pre-allocate Work Requests for backchannel
  xprtrdma: Pre-allocate backward rpc_rqst and send/receive buffers
  SUNRPC: Abstract backchannel operations
  xprtrdma: Saving IRQs no longer needed for rb_lock
  xprtrdma: Remove reply tasklet
  xprtrdma: Use workqueue to process RPC/RDMA replies
  xprtrdma: Replace send and receive arrays
  xprtrdma: Refactor reply handler error handling
  ...

include/linux/nfs4.h

@@ -130,6 +130,7 @@ enum nfs_opnum4 {
 	OP_READ_PLUS = 68,
 	OP_SEEK = 69,
 	OP_WRITE_SAME = 70,
+	OP_CLONE = 71,
 
 	OP_ILLEGAL = 10044,
 };
@@ -421,6 +422,7 @@ enum lock_type4 {
 #define FATTR4_WORD2_LAYOUT_TYPES       (1UL << 0)
 #define FATTR4_WORD2_LAYOUT_BLKSIZE     (1UL << 1)
 #define FATTR4_WORD2_MDSTHRESHOLD       (1UL << 4)
+#define FATTR4_WORD2_CLONE_BLKSIZE	(1UL << 13)
 #define FATTR4_WORD2_SECURITY_LABEL     (1UL << 16)
 
 /* MDS threshold bitmap bits */
@@ -501,6 +503,7 @@ enum {
 	NFSPROC4_CLNT_ALLOCATE,
 	NFSPROC4_CLNT_DEALLOCATE,
 	NFSPROC4_CLNT_LAYOUTSTATS,
+	NFSPROC4_CLNT_CLONE,
 };
 
 /* nfs41 types */

include/linux/nfs_fs_sb.h

@@ -147,6 +147,7 @@ struct nfs_server {
 	unsigned int		acdirmax;
 	unsigned int		namelen;
 	unsigned int		options;	/* extra options enabled by mount */
+	unsigned int		clone_blksize;	/* granularity of a CLONE operation */
 #define NFS_OPTION_FSCACHE	0x00000001	/* - local caching enabled */
 #define NFS_OPTION_MIGRATION	0x00000002	/* - NFSv4 migration enabled */
 
@@ -243,5 +244,6 @@ struct nfs_server {
 #define NFS_CAP_ALLOCATE	(1U << 20)
 #define NFS_CAP_DEALLOCATE	(1U << 21)
 #define NFS_CAP_LAYOUTSTATS	(1U << 22)
+#define NFS_CAP_CLONE		(1U << 23)
 
 #endif

include/linux/nfs_xdr.h

@@ -141,6 +141,7 @@ struct nfs_fsinfo {
 	__u32			lease_time; /* in seconds */
 	__u32			layouttype; /* supported pnfs layout driver */
 	__u32			blksize; /* preferred pnfs io block size */
+	__u32			clone_blksize; /* granularity of a CLONE operation */
 };
 
 struct nfs_fsstat {
@@ -359,6 +360,25 @@ struct nfs42_layoutstat_data {
 	struct nfs42_layoutstat_res res;
 };
 
+struct nfs42_clone_args {
+	struct nfs4_sequence_args	seq_args;
+	struct nfs_fh			*src_fh;
+	struct nfs_fh			*dst_fh;
+	nfs4_stateid			src_stateid;
+	nfs4_stateid			dst_stateid;
+	__u64				src_offset;
+	__u64				dst_offset;
+	__u64				count;
+	const u32			*dst_bitmask;
+};
+
+struct nfs42_clone_res {
+	struct nfs4_sequence_res	seq_res;
+	unsigned int			rpc_status;
+	struct nfs_fattr		*dst_fattr;
+	const struct nfs_server		*server;
+};
+
 struct stateowner_id {
 	__u64	create_time;
 	__u32	uniquifier;
@@ -528,7 +548,7 @@ struct nfs4_delegreturnargs {
 struct nfs4_delegreturnres {
 	struct nfs4_sequence_res	seq_res;
 	struct nfs_fattr * fattr;
-	const struct nfs_server *server;
+	struct nfs_server *server;
 };
 
 /*
@@ -601,7 +621,7 @@ struct nfs_removeargs {
 
 struct nfs_removeres {
 	struct nfs4_sequence_res 	seq_res;
-	const struct nfs_server *server;
+	struct nfs_server *server;
 	struct nfs_fattr	*dir_attr;
 	struct nfs4_change_info	cinfo;
 };
@@ -619,7 +639,7 @@ struct nfs_renameargs {
 
 struct nfs_renameres {
 	struct nfs4_sequence_res	seq_res;
-	const struct nfs_server		*server;
+	struct nfs_server		*server;
 	struct nfs4_change_info		old_cinfo;
 	struct nfs_fattr		*old_fattr;
 	struct nfs4_change_info		new_cinfo;
@@ -685,7 +705,6 @@ struct nfs_setaclargs {
 	struct nfs4_sequence_args	seq_args;
 	struct nfs_fh *			fh;
 	size_t				acl_len;
-	unsigned int			acl_pgbase;
 	struct page **			acl_pages;
 };
 
@@ -697,7 +716,6 @@ struct nfs_getaclargs {
 	struct nfs4_sequence_args 	seq_args;
 	struct nfs_fh *			fh;
 	size_t				acl_len;
-	unsigned int			acl_pgbase;
 	struct page **			acl_pages;
 };
 

include/linux/sunrpc/bc_xprt.h

@@ -38,6 +38,11 @@ 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);
 
+/* Socket backchannel transport methods */
+int xprt_setup_bc(struct rpc_xprt *xprt, unsigned int min_reqs);
+void xprt_destroy_bc(struct rpc_xprt *xprt, unsigned int max_reqs);
+void xprt_free_bc_rqst(struct rpc_rqst *req);
+
 /*
  * Determine if a shared backchannel is in use
  */

include/linux/sunrpc/svc_rdma.h

@@ -226,9 +226,13 @@ extern void svc_rdma_put_frmr(struct svcxprt_rdma *,
 			      struct svc_rdma_fastreg_mr *);
 extern void svc_sq_reap(struct svcxprt_rdma *);
 extern void svc_rq_reap(struct svcxprt_rdma *);
-extern struct svc_xprt_class svc_rdma_class;
 extern void svc_rdma_prep_reply_hdr(struct svc_rqst *);
 
+extern struct svc_xprt_class svc_rdma_class;
+#ifdef CONFIG_SUNRPC_BACKCHANNEL
+extern struct svc_xprt_class svc_rdma_bc_class;
+#endif
+
 /* svc_rdma.c */
 extern int svc_rdma_init(void);
 extern void svc_rdma_cleanup(void);

include/linux/sunrpc/xprt.h

@@ -54,6 +54,8 @@ enum rpc_display_format_t {
 struct rpc_task;
 struct rpc_xprt;
 struct seq_file;
+struct svc_serv;
+struct net;
 
 /*
  * This describes a complete RPC request
@@ -136,6 +138,12 @@ struct rpc_xprt_ops {
 	int		(*enable_swap)(struct rpc_xprt *xprt);
 	void		(*disable_swap)(struct rpc_xprt *xprt);
 	void		(*inject_disconnect)(struct rpc_xprt *xprt);
+	int		(*bc_setup)(struct rpc_xprt *xprt,
+				    unsigned int min_reqs);
+	int		(*bc_up)(struct svc_serv *serv, struct net *net);
+	void		(*bc_free_rqst)(struct rpc_rqst *rqst);
+	void		(*bc_destroy)(struct rpc_xprt *xprt,
+				      unsigned int max_reqs);
 };
 
 /*
@@ -153,6 +161,7 @@ enum xprt_transports {
 	XPRT_TRANSPORT_TCP	= IPPROTO_TCP,
 	XPRT_TRANSPORT_BC_TCP	= IPPROTO_TCP | XPRT_TRANSPORT_BC,
 	XPRT_TRANSPORT_RDMA	= 256,
+	XPRT_TRANSPORT_BC_RDMA	= XPRT_TRANSPORT_RDMA | XPRT_TRANSPORT_BC,
 	XPRT_TRANSPORT_LOCAL	= 257,
 };
 

include/linux/sunrpc/xprtsock.h

@@ -44,6 +44,8 @@ struct sock_xprt {
 	 */
 	unsigned long		sock_state;
 	struct delayed_work	connect_worker;
+	struct work_struct	recv_worker;
+	struct mutex		recv_mutex;
 	struct sockaddr_storage	srcaddr;
 	unsigned short		srcport;
 

include/uapi/linux/nfs.h

@@ -7,6 +7,8 @@
 #ifndef _UAPI_LINUX_NFS_H
 #define _UAPI_LINUX_NFS_H
 
+#include <linux/types.h>
+
 #define NFS_PROGRAM	100003
 #define NFS_PORT	2049
 #define NFS_MAXDATA	8192
@@ -31,6 +33,17 @@
 
 #define NFS_PIPE_DIRNAME "nfs"
 
+/* NFS ioctls */
+/* Let's follow btrfs lead on CLONE to avoid messing userspace */
+#define NFS_IOC_CLONE		_IOW(0x94, 9, int)
+#define NFS_IOC_CLONE_RANGE	_IOW(0x94, 13, int)
+
+struct nfs_ioctl_clone_range_args {
+	__s64 src_fd;
+	__u64 src_off, count;
+	__u64 dst_off;
+};
+
 /*
  * NFS stats. The good thing with these values is that NFSv3 errors are
  * a superset of NFSv2 errors (with the exception of NFSERR_WFLUSH which