Merge branch 'nfs-for-3.1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

* 'nfs-for-3.1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (44 commits)
  NFSv4: Don't use the delegation->inode in nfs_mark_return_delegation()
  nfs: don't use d_move in nfs_async_rename_done
  RDMA: Increasing RPCRDMA_MAX_DATA_SEGS
  SUNRPC: Replace xprt->resend and xprt->sending with a priority queue
  SUNRPC: Allow caller of rpc_sleep_on() to select priority levels
  SUNRPC: Support dynamic slot allocation for TCP connections
  SUNRPC: Clean up the slot table allocation
  SUNRPC: Initalise the struct xprt upon allocation
  SUNRPC: Ensure that we grab the XPRT_LOCK before calling xprt_alloc_slot
  pnfs: simplify pnfs files module autoloading
  nfs: document nfsv4 sillyrename issues
  NFS: Convert nfs4_set_ds_client to EXPORT_SYMBOL_GPL
  SUNRPC: Convert the backchannel exports to EXPORT_SYMBOL_GPL
  SUNRPC: sunrpc should not explicitly depend on NFS config options
  NFS: Clean up - simplify the switch to read/write-through-MDS
  NFS: Move the pnfs write code into pnfs.c
  NFS: Move the pnfs read code into pnfs.c
  NFS: Allow the nfs_pageio_descriptor to signal that a re-coalesce is needed
  NFS: Use the nfs_pageio_descriptor->pg_bsize in the read/write request
  NFS: Cache rpc_ops in struct nfs_pageio_descriptor
  ...

9 files changed, 81 insertions, 57 deletions

diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 504b289ba680..a3c4bc800dce 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -563,6 +563,9 @@ enum {
         NFSPROC4_CLNT_GETDEVICEINFO,
         NFSPROC4_CLNT_LAYOUTCOMMIT,
         NFSPROC4_CLNT_LAYOUTRETURN,
+        NFSPROC4_CLNT_SECINFO_NO_NAME,
+        NFSPROC4_CLNT_TEST_STATEID,
+        NFSPROC4_CLNT_FREE_STATEID,
 };
 
 /* nfs41 types */
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 08c444aa0411..50a661f8b45a 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -16,6 +16,7 @@ struct nfs4_sequence_args;
 struct nfs4_sequence_res;
 struct nfs_server;
 struct nfs4_minor_version_ops;
+struct server_scope;
 
 /*
  * The nfs_client identifies our client state to the server.
@@ -77,12 +78,13 @@ struct nfs_client {
         /* The flags used for obtaining the clientid during EXCHANGE_ID */
         u32                     cl_exchange_flags;
         struct nfs4_session     *cl_session;    /* sharred session */
-        struct list_head        cl_layouts;
 #endif /* CONFIG_NFS_V4 */
 
 #ifdef CONFIG_NFS_FSCACHE
         struct fscache_cookie   *fscache;       /* client index cache cookie */
 #endif
+
+        struct server_scope     *server_scope;  /* from exchange_id */
 };
 
 /*
@@ -149,6 +151,7 @@ struct nfs_server {
         struct rb_root          openowner_id;
         struct rb_root          lockowner_id;
 #endif
+        struct list_head        layouts;
         struct list_head        delegations;
         void (*destroy)(struct nfs_server *);
 
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index 25311b3bedf8..e2791a27a901 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -55,20 +55,28 @@ struct nfs_page {
         struct nfs_writeverf    wb_verf;        /* Commit cookie */
 };
 
+struct nfs_pageio_descriptor;
+struct nfs_pageio_ops {
+        void    (*pg_init)(struct nfs_pageio_descriptor *, struct nfs_page *);
+        bool    (*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *, struct nfs_page *);
+        int     (*pg_doio)(struct nfs_pageio_descriptor *);
+};
+
 struct nfs_pageio_descriptor {
         struct list_head        pg_list;
         unsigned long           pg_bytes_written;
         size_t                  pg_count;
         size_t                  pg_bsize;
         unsigned int            pg_base;
-        char                    pg_moreio;
+        unsigned char           pg_moreio : 1,
+                                pg_recoalesce : 1;
 
         struct inode            *pg_inode;
-        int                     (*pg_doio)(struct nfs_pageio_descriptor *);
+        const struct nfs_pageio_ops *pg_ops;
         int                     pg_ioflags;
         int                     pg_error;
+        const struct rpc_call_ops *pg_rpc_callops;
         struct pnfs_layout_segment *pg_lseg;
-        bool                    (*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *, struct nfs_page *);
 };
 
 #define NFS_WBACK_BUSY(req)     (test_bit(PG_BUSY,&(req)->wb_flags))
@@ -85,7 +93,7 @@ extern	int nfs_scan_list(struct nfs_inode *nfsi, struct list_head *dst,
                           pgoff_t idx_start, unsigned int npages, int tag);
 extern  void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
                              struct inode *inode,
-                             int (*doio)(struct nfs_pageio_descriptor *desc),
+                             const struct nfs_pageio_ops *pg_ops,
                              size_t bsize,
                              int how);
 extern  int nfs_pageio_add_request(struct nfs_pageio_descriptor *,
@@ -100,7 +108,6 @@ extern	void nfs_unlock_request(struct nfs_page *req);
 extern  int nfs_set_page_tag_locked(struct nfs_page *req);
 extern  void nfs_clear_page_tag_locked(struct nfs_page *req);
 
-
 /*
  * Lock the page of an asynchronous request without getting a new reference
  */
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 00848d86ffb2..5b115956abac 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -269,9 +269,10 @@ struct nfs4_layoutcommit_data {
 };
 
 struct nfs4_layoutreturn_args {
-        __u32   layout_type;
+        struct pnfs_layout_hdr *layout;
         struct inode *inode;
         nfs4_stateid stateid;
+        __u32   layout_type;
         struct nfs4_sequence_args seq_args;
 };
 
@@ -1060,6 +1061,7 @@ struct server_scope {
 struct nfs41_exchange_id_res {
         struct nfs_client               *client;
         u32                             flags;
+        struct server_scope             *server_scope;
 };
 
 struct nfs41_create_session_args {
@@ -1083,6 +1085,34 @@ struct nfs41_reclaim_complete_args {
 struct nfs41_reclaim_complete_res {
         struct nfs4_sequence_res        seq_res;
 };
+
+#define SECINFO_STYLE_CURRENT_FH 0
+#define SECINFO_STYLE_PARENT 1
+struct nfs41_secinfo_no_name_args {
+        int                             style;
+        struct nfs4_sequence_args       seq_args;
+};
+
+struct nfs41_test_stateid_args {
+        nfs4_stateid                    *stateid;
+        struct nfs4_sequence_args       seq_args;
+};
+
+struct nfs41_test_stateid_res {
+        unsigned int                    status;
+        struct nfs4_sequence_res        seq_res;
+};
+
+struct nfs41_free_stateid_args {
+        nfs4_stateid                    *stateid;
+        struct nfs4_sequence_args       seq_args;
+};
+
+struct nfs41_free_stateid_res {
+        unsigned int                    status;
+        struct nfs4_sequence_res        seq_res;
+};
+
 #endif /* CONFIG_NFS_V4_1 */
 
 struct nfs_page;
@@ -1096,6 +1126,7 @@ struct nfs_read_data {
         struct rpc_cred         *cred;
         struct nfs_fattr        fattr;  /* fattr storage */
         struct list_head        pages;  /* Coalesced read requests */
+        struct list_head        list;   /* lists of struct nfs_read_data */
         struct nfs_page         *req;   /* multi ops per nfs_page */
         struct page             **pagevec;
         unsigned int            npages; /* Max length of pagevec */
@@ -1119,6 +1150,7 @@ struct nfs_write_data {
         struct nfs_fattr        fattr;
         struct nfs_writeverf    verf;
         struct list_head        pages;          /* Coalesced requests we wish to flush */
+        struct list_head        list;           /* lists of struct nfs_write_data */
         struct nfs_page         *req;           /* multi ops per nfs_page */
         struct page             **pagevec;
         unsigned int            npages;         /* Max length of pagevec */
diff --git a/include/linux/pnfs_osd_xdr.h b/include/linux/pnfs_osd_xdr.h
index 76efbdd01622..435dd5fa7453 100644
--- a/include/linux/pnfs_osd_xdr.h
+++ b/include/linux/pnfs_osd_xdr.h
@@ -41,9 +41,6 @@
 
 #include <linux/nfs_fs.h>
 #include <linux/nfs_page.h>
-#include <scsi/osd_protocol.h>
-
-#define PNFS_OSD_OSDNAME_MAXSIZE 256
 
 /*
  * draft-ietf-nfsv4-minorversion-22
@@ -99,12 +96,6 @@ struct pnfs_osd_objid {
 #define _DEVID_HI(oid_device_id) \
         (unsigned long long)be64_to_cpup(((__be64 *)(oid_device_id)->data) + 1)
 
-static inline int
-pnfs_osd_objid_xdr_sz(void)
-{
-        return (NFS4_DEVICEID4_SIZE / 4) + 2 + 2;
-}
-
 enum pnfs_osd_version {
         PNFS_OSD_MISSING              = 0,
         PNFS_OSD_VERSION_1            = 1,
@@ -189,8 +180,6 @@ struct pnfs_osd_targetid {
         struct nfs4_string              oti_scsi_device_id;
 };
 
-enum { PNFS_OSD_TARGETID_MAX = 1 + PNFS_OSD_OSDNAME_MAXSIZE / 4 };
-
 /*   struct netaddr4 {
  *       // see struct rpcb in RFC1833
  *       string r_netid<>;    // network id
@@ -207,12 +196,6 @@ struct pnfs_osd_targetaddr {
         struct pnfs_osd_net_addr        ota_netaddr;
 };
 
-enum {
-        NETWORK_ID_MAX = 16 / 4,
-        UNIVERSAL_ADDRESS_MAX = 64 / 4,
-        PNFS_OSD_TARGETADDR_MAX = 3 +  NETWORK_ID_MAX + UNIVERSAL_ADDRESS_MAX,
-};
-
 struct pnfs_osd_deviceaddr {
         struct pnfs_osd_targetid        oda_targetid;
         struct pnfs_osd_targetaddr      oda_targetaddr;
@@ -222,15 +205,6 @@ struct pnfs_osd_deviceaddr {
         struct nfs4_string              oda_osdname;
 };
 
-enum {
-        ODA_OSDNAME_MAX = PNFS_OSD_OSDNAME_MAXSIZE / 4,
-        PNFS_OSD_DEVICEADDR_MAX =
-                PNFS_OSD_TARGETID_MAX + PNFS_OSD_TARGETADDR_MAX +
-                2 /*oda_lun*/ +
-                1 + OSD_SYSTEMID_LEN +
-                1 + ODA_OSDNAME_MAX,
-};
-
 /* LAYOUTCOMMIT: layoutupdate */
 
 /*   union pnfs_osd_deltaspaceused4 switch (bool dsu_valid) {
@@ -279,7 +253,7 @@ struct pnfs_osd_ioerr {
         u32                     oer_errno;
 };
 
-/* OSD XDR API */
+/* OSD XDR Client API */
 /* Layout helpers */
 /* Layout decoding is done in two parts:
  * 1. First Call pnfs_osd_xdr_decode_layout_map to read in only the header part
@@ -337,8 +311,7 @@ extern int
 pnfs_osd_xdr_encode_layoutupdate(struct xdr_stream *xdr,
                                  struct pnfs_osd_layoutupdate *lou);
 
-/* osd_ioerror encoding/decoding (layout_return) */
-/* Client */
+/* osd_ioerror encoding (layout_return) */
 extern __be32 *pnfs_osd_xdr_ioerr_reserve_space(struct xdr_stream *xdr);
 extern void pnfs_osd_xdr_encode_ioerr(__be32 *p, struct pnfs_osd_ioerr *ioerr);
 
diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h
index 082884295f80..f7f3ce340c08 100644
--- a/include/linux/sunrpc/bc_xprt.h
+++ b/include/linux/sunrpc/bc_xprt.h
@@ -31,7 +31,7 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #include <linux/sunrpc/xprt.h>
 #include <linux/sunrpc/sched.h>
 
-#ifdef CONFIG_NFS_V4_1
+#ifdef CONFIG_SUNRPC_BACKCHANNEL
 struct rpc_rqst *xprt_alloc_bc_request(struct rpc_xprt *xprt);
 void xprt_free_bc_request(struct rpc_rqst *req);
 int xprt_setup_backchannel(struct rpc_xprt *, unsigned int min_reqs);
@@ -47,7 +47,7 @@ static inline int svc_is_backchannel(const struct svc_rqst *rqstp)
                 return 1;
         return 0;
 }
-#else /* CONFIG_NFS_V4_1 */
+#else /* CONFIG_SUNRPC_BACKCHANNEL */
 static inline int xprt_setup_backchannel(struct rpc_xprt *xprt,
                                          unsigned int min_reqs)
 {
@@ -62,6 +62,6 @@ static inline int svc_is_backchannel(const struct svc_rqst *rqstp)
 static inline void xprt_free_bc_request(struct rpc_rqst *req)
 {
 }
-#endif /* CONFIG_NFS_V4_1 */
+#endif /* CONFIG_SUNRPC_BACKCHANNEL */
 #endif /* _LINUX_SUNRPC_BC_XPRT_H */
 
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index fe2d8e6b923b..e7756896f3ca 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -227,6 +227,10 @@ void		rpc_init_wait_queue(struct rpc_wait_queue *, const char *);
 void            rpc_destroy_wait_queue(struct rpc_wait_queue *);
 void            rpc_sleep_on(struct rpc_wait_queue *, struct rpc_task *,
                                         rpc_action action);
+void            rpc_sleep_on_priority(struct rpc_wait_queue *,
+                                        struct rpc_task *,
+                                        rpc_action action,
+                                        int priority);
 void            rpc_wake_up_queued_task(struct rpc_wait_queue *,
                                         struct rpc_task *);
 void            rpc_wake_up(struct rpc_wait_queue *);
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 2f1e5186e049..223588a976a0 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -92,7 +92,7 @@ struct svc_serv {
         struct module *         sv_module;      /* optional module to count when
                                                  * adding threads */
         svc_thread_fn           sv_function;    /* main function for threads */
-#if defined(CONFIG_NFS_V4_1)
+#if defined(CONFIG_SUNRPC_BACKCHANNEL)
         struct list_head        sv_cb_list;     /* queue for callback requests
                                                  * that arrive over the same
                                                  * connection */
@@ -100,7 +100,7 @@ struct svc_serv {
         wait_queue_head_t       sv_cb_waitq;    /* sleep here if there are no
                                                  * entries in the svc_cb_list */
         struct svc_xprt         *sv_bc_xprt;    /* callback on fore channel */
-#endif /* CONFIG_NFS_V4_1 */
+#endif /* CONFIG_SUNRPC_BACKCHANNEL */
 };
 
 /*
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 81cce3b3ee66..15518a152ac3 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -22,6 +22,7 @@
 #define RPC_MIN_SLOT_TABLE      (2U)
 #define RPC_DEF_SLOT_TABLE      (16U)
 #define RPC_MAX_SLOT_TABLE      (128U)
+#define RPC_MAX_SLOT_TABLE_LIMIT        (65536U)
 
 /*
  * This describes a timeout strategy
@@ -100,18 +101,18 @@ struct rpc_rqst {
         ktime_t                 rq_xtime;       /* transmit time stamp */
         int                     rq_ntrans;
 
-#if defined(CONFIG_NFS_V4_1)
+#if defined(CONFIG_SUNRPC_BACKCHANNEL)
         struct list_head        rq_bc_list;     /* Callback service list */
         unsigned long           rq_bc_pa_state; /* Backchannel prealloc state */
         struct list_head        rq_bc_pa_list;  /* Backchannel prealloc list */
-#endif /* CONFIG_NFS_V4_1 */
+#endif /* CONFIG_SUNRPC_BACKCHANEL */
 };
 #define rq_svec                 rq_snd_buf.head
 #define rq_slen                 rq_snd_buf.len
 
 struct rpc_xprt_ops {
         void            (*set_buffer_size)(struct rpc_xprt *xprt, size_t sndsize, size_t rcvsize);
-        int             (*reserve_xprt)(struct rpc_task *task);
+        int             (*reserve_xprt)(struct rpc_xprt *xprt, struct rpc_task *task);
         void            (*release_xprt)(struct rpc_xprt *xprt, struct rpc_task *task);
         void            (*rpcbind)(struct rpc_task *task);
         void            (*set_port)(struct rpc_xprt *xprt, unsigned short port);
@@ -164,12 +165,12 @@ struct rpc_xprt {
 
         struct rpc_wait_queue   binding;        /* requests waiting on rpcbind */
         struct rpc_wait_queue   sending;        /* requests waiting to send */
-        struct rpc_wait_queue   resend;         /* requests waiting to resend */
         struct rpc_wait_queue   pending;        /* requests in flight */
         struct rpc_wait_queue   backlog;        /* waiting for slot */
         struct list_head        free;           /* free slots */
-        struct rpc_rqst *       slot;           /* slot table storage */
-        unsigned int            max_reqs;       /* total slots */
+        unsigned int            max_reqs;       /* max number of slots */
+        unsigned int            min_reqs;       /* min number of slots */
+        atomic_t                num_reqs;       /* total slots */
         unsigned long           state;          /* transport state */
         unsigned char           shutdown   : 1, /* being shut down */
                                 resvport   : 1; /* use a reserved port */
@@ -200,7 +201,7 @@ struct rpc_xprt {
         u32                     xid;            /* Next XID value to use */
         struct rpc_task *       snd_task;       /* Task blocked in send */
         struct svc_xprt         *bc_xprt;       /* NFSv4.1 backchannel */
-#if defined(CONFIG_NFS_V4_1)
+#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 */
@@ -208,7 +209,7 @@ struct rpc_xprt {
                                                  * items */
         struct list_head        bc_pa_list;     /* List of preallocated
                                                  * backchannel rpc_rqst's */
-#endif /* CONFIG_NFS_V4_1 */
+#endif /* CONFIG_SUNRPC_BACKCHANNEL */
         struct list_head        recv;
 
         struct {
@@ -228,15 +229,15 @@ struct rpc_xprt {
         const char              *address_strings[RPC_DISPLAY_MAX];
 };
 
-#if defined(CONFIG_NFS_V4_1)
+#if defined(CONFIG_SUNRPC_BACKCHANNEL)
 /*
  * Backchannel flags
  */
 #define RPC_BC_PA_IN_USE        0x0001          /* Preallocated backchannel */
                                                 /* buffer in use */
-#endif /* CONFIG_NFS_V4_1 */
+#endif /* CONFIG_SUNRPC_BACKCHANNEL */
 
-#if defined(CONFIG_NFS_V4_1)
+#if defined(CONFIG_SUNRPC_BACKCHANNEL)
 static inline int bc_prealloc(struct rpc_rqst *req)
 {
         return test_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state);
@@ -246,7 +247,7 @@ static inline int bc_prealloc(struct rpc_rqst *req)
 {
         return 0;
 }
-#endif /* CONFIG_NFS_V4_1 */
+#endif /* CONFIG_SUNRPC_BACKCHANNEL */
 
 struct xprt_create {
         int                     ident;          /* XPRT_TRANSPORT identifier */
@@ -271,8 +272,8 @@ struct xprt_class {
 struct rpc_xprt         *xprt_create_transport(struct xprt_create *args);
 void                    xprt_connect(struct rpc_task *task);
 void                    xprt_reserve(struct rpc_task *task);
-int                     xprt_reserve_xprt(struct rpc_task *task);
-int                     xprt_reserve_xprt_cong(struct rpc_task *task);
+int                     xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task);
+int                     xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task);
 int                     xprt_prepare_transmit(struct rpc_task *task);
 void                    xprt_transmit(struct rpc_task *task);
 void                    xprt_end_transmit(struct rpc_task *task);
@@ -282,7 +283,9 @@ void			xprt_release_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task);
 void                    xprt_release(struct rpc_task *task);
 struct rpc_xprt *       xprt_get(struct rpc_xprt *xprt);
 void                    xprt_put(struct rpc_xprt *xprt);
-struct rpc_xprt *       xprt_alloc(struct net *net, int size, int max_req);
+struct rpc_xprt *       xprt_alloc(struct net *net, size_t size,
+                                unsigned int num_prealloc,
+                                unsigned int max_req);
 void                    xprt_free(struct rpc_xprt *);
 
 static inline __be32 *xprt_skip_transport_header(struct rpc_xprt *xprt, __be32 *p)
@@ -321,7 +324,6 @@ void			xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie);
 #define XPRT_CLOSING            (6)
 #define XPRT_CONNECTION_ABORT   (7)
 #define XPRT_CONNECTION_CLOSE   (8)
-#define XPRT_INITIALIZED        (9)
 
 static inline void xprt_set_connected(struct rpc_xprt *xprt)
 {