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
  ...

1 files changed, 44 insertions, 10 deletions

diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index c82abf44e39d..ac7f8d4f632a 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -77,9 +77,6 @@ struct rpcrdma_ia {
  * RDMA Endpoint -- one per transport instance
  */
 
-#define RPCRDMA_WC_BUDGET	(128)
-#define RPCRDMA_POLLSIZE	(16)
-
 struct rpcrdma_ep {
 	atomic_t		rep_cqcount;
 	int			rep_cqinit;
@@ -89,8 +86,6 @@ struct rpcrdma_ep {
 	struct rdma_conn_param	rep_remote_cma;
 	struct sockaddr_storage	rep_remote_addr;
 	struct delayed_work	rep_connect_worker;
-	struct ib_wc		rep_send_wcs[RPCRDMA_POLLSIZE];
-	struct ib_wc		rep_recv_wcs[RPCRDMA_POLLSIZE];
 };
 
 /*
@@ -106,6 +101,16 @@ struct rpcrdma_ep {
  */
 #define RPCRDMA_IGNORE_COMPLETION	(0ULL)
 
+/* Pre-allocate extra Work Requests for handling backward receives
+ * and sends. This is a fixed value because the Work Queues are
+ * allocated when the forward channel is set up.
+ */
+#if defined(CONFIG_SUNRPC_BACKCHANNEL)
+#define RPCRDMA_BACKWARD_WRS		(8)
+#else
+#define RPCRDMA_BACKWARD_WRS		(0)
+#endif
+
 /* Registered buffer -- registered kmalloc'd memory for RDMA SEND/RECV
  *
  * The below structure appears at the front of a large region of kmalloc'd
@@ -169,10 +174,13 @@ struct rpcrdma_rep {
 	unsigned int		rr_len;
 	struct ib_device	*rr_device;
 	struct rpcrdma_xprt	*rr_rxprt;
+	struct work_struct	rr_work;
 	struct list_head	rr_list;
 	struct rpcrdma_regbuf	*rr_rdmabuf;
 };
 
+#define RPCRDMA_BAD_LEN		(~0U)
+
 /*
  * struct rpcrdma_mw - external memory region metadata
  *
@@ -256,6 +264,7 @@ struct rpcrdma_mr_seg {		/* chunk descriptors */
 #define RPCRDMA_MAX_IOVS	(2)
 
 struct rpcrdma_req {
+	struct list_head	rl_free;
 	unsigned int		rl_niovs;
 	unsigned int		rl_nchunks;
 	unsigned int		rl_connect_cookie;
@@ -265,6 +274,9 @@ struct rpcrdma_req {
 	struct rpcrdma_regbuf	*rl_rdmabuf;
 	struct rpcrdma_regbuf	*rl_sendbuf;
 	struct rpcrdma_mr_seg	rl_segments[RPCRDMA_MAX_SEGS];
+
+	struct list_head	rl_all;
+	bool			rl_backchannel;
 };
 
 static inline struct rpcrdma_req *
@@ -289,12 +301,14 @@ struct rpcrdma_buffer {
 	struct list_head	rb_all;
 	char			*rb_pool;
 
-	spinlock_t		rb_lock;	/* protect buf arrays */
+	spinlock_t		rb_lock;	/* protect buf lists */
+	struct list_head	rb_send_bufs;
+	struct list_head	rb_recv_bufs;
 	u32			rb_max_requests;
-	int			rb_send_index;
-	int			rb_recv_index;
-	struct rpcrdma_req	**rb_send_bufs;
-	struct rpcrdma_rep	**rb_recv_bufs;
+
+	u32			rb_bc_srv_max_requests;
+	spinlock_t		rb_reqslock;	/* protect rb_allreqs */
+	struct list_head	rb_allreqs;
 };
 #define rdmab_to_ia(b) (&container_of((b), struct rpcrdma_xprt, rx_buf)->rx_ia)
 
@@ -340,6 +354,7 @@ struct rpcrdma_stats {
 	unsigned long		failed_marshal_count;
 	unsigned long		bad_reply_count;
 	unsigned long		nomsg_call_count;
+	unsigned long		bcall_count;
 };
 
 /*
@@ -415,6 +430,9 @@ int rpcrdma_ep_post_recv(struct rpcrdma_ia *, struct rpcrdma_ep *,
 /*
  * Buffer calls - xprtrdma/verbs.c
  */
+struct rpcrdma_req *rpcrdma_create_req(struct rpcrdma_xprt *);
+struct rpcrdma_rep *rpcrdma_create_rep(struct rpcrdma_xprt *);
+void rpcrdma_destroy_req(struct rpcrdma_ia *, struct rpcrdma_req *);
 int rpcrdma_buffer_create(struct rpcrdma_xprt *);
 void rpcrdma_buffer_destroy(struct rpcrdma_buffer *);
 
@@ -431,10 +449,14 @@ void rpcrdma_free_regbuf(struct rpcrdma_ia *,
 			 struct rpcrdma_regbuf *);
 
 unsigned int rpcrdma_max_segments(struct rpcrdma_xprt *);
+int rpcrdma_ep_post_extra_recv(struct rpcrdma_xprt *, unsigned int);
 
 int frwr_alloc_recovery_wq(void);
 void frwr_destroy_recovery_wq(void);
 
+int rpcrdma_alloc_wq(void);
+void rpcrdma_destroy_wq(void);
+
 /*
  * Wrappers for chunk registration, shared by read/write chunk code.
  */
@@ -495,6 +517,18 @@ int rpcrdma_marshal_req(struct rpc_rqst *);
 int xprt_rdma_init(void);
 void xprt_rdma_cleanup(void);
 
+/* Backchannel calls - xprtrdma/backchannel.c
+ */
+#if defined(CONFIG_SUNRPC_BACKCHANNEL)
+int xprt_rdma_bc_setup(struct rpc_xprt *, unsigned int);
+int xprt_rdma_bc_up(struct svc_serv *, struct net *);
+int rpcrdma_bc_post_recv(struct rpcrdma_xprt *, unsigned int);
+void rpcrdma_bc_receive_call(struct rpcrdma_xprt *, struct rpcrdma_rep *);
+int rpcrdma_bc_marshal_reply(struct rpc_rqst *);
+void xprt_rdma_bc_free_rqst(struct rpc_rqst *);
+void xprt_rdma_bc_destroy(struct rpc_xprt *, unsigned int);
+#endif	/* CONFIG_SUNRPC_BACKCHANNEL */
+
 /* Temporary NFS request map cache. Created in svc_rdma.c  */
 extern struct kmem_cache *svc_rdma_map_cachep;
 /* WR context cache. Created in svc_rdma.c  */