Merge tag 'nfs-for-5.2-1' of git://git.linux-nfs.org/projects/anna/linux-nfs

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

  Stable bugfixes:
   - Fall back to MDS if no deviceid is found rather than aborting   # v4.11+
   - NFS4: Fix v4.0 client state corruption when mount

  Features:
   - Much improved handling of soft mounts with NFS v4.0:
       - Reduce risk of false positive timeouts
       - Faster failover of reads and writes after a timeout
       - Added a "softerr" mount option to return ETIMEDOUT instead of
         EIO to the application after a timeout
   - Increase number of xprtrdma backchannel requests
   - Add additional xprtrdma tracepoints
   - Improved send completion batching for xprtrdma

  Other bugfixes and cleanups:
   - Return -EINVAL when NFS v4.2 is passed an invalid dedup mode
   - Reduce usage of GFP_ATOMIC pages in SUNRPC
   - Various minor NFS over RDMA cleanups and bugfixes
   - Use the correct container namespace for upcalls
   - Don't share superblocks between user namespaces
   - Various other container fixes
   - Make nfs_match_client() killable to prevent soft lockups
   - Don't mark all open state for recovery when handling recallable
     state revoked flag"

* tag 'nfs-for-5.2-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (69 commits)
  SUNRPC: Rebalance a kref in auth_gss.c
  NFS: Fix a double unlock from nfs_match,get_client
  nfs: pass the correct prototype to read_cache_page
  NFSv4: don't mark all open state for recovery when handling recallable state revoked flag
  SUNRPC: Fix an error code in gss_alloc_msg()
  SUNRPC: task should be exit if encode return EKEYEXPIRED more times
  NFS4: Fix v4.0 client state corruption when mount
  PNFS fallback to MDS if no deviceid found
  NFS: make nfs_match_client killable
  lockd: Store the lockd client credential in struct nlm_host
  NFS: When mounting, don't share filesystems between different user namespaces
  NFS: Convert NFSv2 to use the container user namespace
  NFSv4: Convert the NFS client idmapper to use the container user namespace
  NFS: Convert NFSv3 to use the container user namespace
  SUNRPC: Use namespace of listening daemon in the client AUTH_GSS upcall
  SUNRPC: Use the client user namespace when encoding creds
  NFS: Store the credential of the mount process in the nfs_server
  SUNRPC: Cache cred of process creating the rpc_client
  xprtrdma: Remove stale comment
  xprtrdma: Update comments that reference ib_drain_qp
  ...

11 files changed, 79 insertions, 26 deletions

diff --git a/include/linux/lockd/bind.h b/include/linux/lockd/bind.h
index 053a4ef3d431..8c0cf1059443 100644
--- a/include/linux/lockd/bind.h
+++ b/include/linux/lockd/bind.h
@@ -46,6 +46,7 @@ struct nlmclnt_initdata {
         int                     noresvport;
         struct net              *net;
         const struct nlmclnt_operations *nlmclnt_ops;
+        const struct cred       *cred;
 };
 
 /*
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index b065ef406770..c9b422dde542 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -70,6 +70,7 @@ struct nlm_host {
         struct nsm_handle       *h_nsmhandle;   /* NSM status handle */
         char                    *h_addrbuf;     /* address eyecatcher */
         struct net              *net;           /* host net */
+        const struct cred       *h_cred;
         char                    nodename[UNX_MAXNODENAME + 1];
         const struct nlmclnt_operations *h_nlmclnt_ops; /* Callback ops for NLM users */
 };
@@ -229,7 +230,8 @@ struct nlm_host  *nlmclnt_lookup_host(const struct sockaddr *sap,
                                         const u32 version,
                                         const char *hostname,
                                         int noresvport,
-                                        struct net *net);
+                                        struct net *net,
+                                        const struct cred *cred);
 void              nlmclnt_release_host(struct nlm_host *);
 struct nlm_host  *nlmsvc_lookup_host(const struct svc_rqst *rqstp,
                                         const char *hostname,
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 40e30376130b..d363d5765cdf 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -76,7 +76,6 @@ struct nfs_open_context {
         fmode_t mode;
 
         unsigned long flags;
-#define NFS_CONTEXT_ERROR_WRITE         (0)
 #define NFS_CONTEXT_RESEND_WRITES       (1)
 #define NFS_CONTEXT_BAD                 (2)
 #define NFS_CONTEXT_UNLOCK      (3)
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index c827d31298cc..1e78032a174b 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -139,6 +139,16 @@ struct nfs_server {
         struct nfs_iostats __percpu *io_stats;  /* I/O statistics */
         atomic_long_t           writeback;      /* number of writeback pages */
         int                     flags;          /* various flags */
+
+/* The following are for internal use only. Also see uapi/linux/nfs_mount.h */
+#define NFS_MOUNT_LOOKUP_CACHE_NONEG    0x10000
+#define NFS_MOUNT_LOOKUP_CACHE_NONE     0x20000
+#define NFS_MOUNT_NORESVPORT            0x40000
+#define NFS_MOUNT_LEGACY_INTERFACE      0x80000
+#define NFS_MOUNT_LOCAL_FLOCK           0x100000
+#define NFS_MOUNT_LOCAL_FCNTL           0x200000
+#define NFS_MOUNT_SOFTERR               0x400000
+
         unsigned int            caps;           /* server capabilities */
         unsigned int            rsize;          /* read size */
         unsigned int            rpages;         /* read size (in pages) */
@@ -231,6 +241,9 @@ struct nfs_server {
 
         /* XDR related information */
         unsigned int            read_hdrsize;
+
+        /* User namespace info */
+        const struct cred       *cred;
 };
 
 /* Server capabilities */
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index ad69430fd0eb..0bbd587fac6a 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -42,7 +42,6 @@ struct nfs_inode;
 struct nfs_page {
         struct list_head        wb_list;        /* Defines state of page: */
         struct page             *wb_page;       /* page to read in/write out */
-        struct nfs_open_context *wb_context;    /* File state context info */
         struct nfs_lock_context *wb_lock_context;       /* lock context info */
         pgoff_t                 wb_index;       /* Offset >> PAGE_SHIFT */
         unsigned int            wb_offset,      /* Offset & ~PAGE_MASK */
@@ -53,6 +52,7 @@ struct nfs_page {
         struct nfs_write_verifier       wb_verf;        /* Commit cookie */
         struct nfs_page         *wb_this_page;  /* list of reqs for this page */
         struct nfs_page         *wb_head;       /* head pointer for req list */
+        unsigned short          wb_nio;         /* Number of I/O attempts */
 };
 
 struct nfs_pageio_descriptor;
@@ -87,7 +87,6 @@ struct nfs_pgio_mirror {
 };
 
 struct nfs_pageio_descriptor {
-        unsigned char           pg_moreio : 1;
         struct inode            *pg_inode;
         const struct nfs_pageio_ops *pg_ops;
         const struct nfs_rw_ops *pg_rw_ops;
@@ -105,6 +104,8 @@ struct nfs_pageio_descriptor {
         struct nfs_pgio_mirror  pg_mirrors_static[1];
         struct nfs_pgio_mirror  *pg_mirrors_dynamic;
         u32                     pg_mirror_idx;  /* current mirror */
+        unsigned short          pg_maxretrans;
+        unsigned char           pg_moreio : 1;
 };
 
 /* arbitrarily selected limit to number of mirrors */
@@ -114,7 +115,6 @@ struct nfs_pageio_descriptor {
 
 extern  struct nfs_page *nfs_create_request(struct nfs_open_context *ctx,
                                             struct page *page,
-                                            struct nfs_page *last,
                                             unsigned int offset,
                                             unsigned int count);
 extern  void nfs_release_request(struct nfs_page *);
@@ -199,4 +199,10 @@ loff_t req_offset(struct nfs_page *req)
         return (((loff_t)req->wb_index) << PAGE_SHIFT) + req->wb_offset;
 }
 
+static inline struct nfs_open_context *
+nfs_req_openctx(struct nfs_page *req)
+{
+        return req->wb_lock_context->open_context;
+}
+
 #endif /* _LINUX_NFS_PAGE_H */
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 98bc9883b230..6e8073140a5d 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -50,6 +50,7 @@ struct rpc_clnt {
         struct rpc_iostats *    cl_metrics;     /* per-client statistics */
 
         unsigned int            cl_softrtry : 1,/* soft timeouts */
+                                cl_softerr  : 1,/* Timeouts return errors */
                                 cl_discrtry : 1,/* disconnect before retry */
                                 cl_noretranstimeo: 1,/* No retransmit timeouts */
                                 cl_autobind : 1,/* use getport() */
@@ -71,6 +72,7 @@ struct rpc_clnt {
         struct dentry           *cl_debugfs;    /* debugfs directory */
 #endif
         struct rpc_xprt_iter    cl_xpi;
+        const struct cred       *cl_cred;
 };
 
 /*
@@ -125,6 +127,7 @@ struct rpc_create_args {
         unsigned long           flags;
         char                    *client_name;
         struct svc_xprt         *bc_xprt;       /* NFSv4.1 backchannel */
+        const struct cred       *cred;
 };
 
 struct rpc_add_xprt_test {
@@ -144,6 +147,7 @@ struct rpc_add_xprt_test {
 #define RPC_CLNT_CREATE_INFINITE_SLOTS  (1UL << 7)
 #define RPC_CLNT_CREATE_NO_IDLE_TIMEOUT (1UL << 8)
 #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT      (1UL << 9)
+#define RPC_CLNT_CREATE_SOFTERR         (1UL << 10)
 
 struct rpc_clnt *rpc_create(struct rpc_create_args *args);
 struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *,
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 52d41d0c1ae1..d0e451868f02 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -35,7 +35,6 @@ struct rpc_wait {
         struct list_head        list;           /* wait queue links */
         struct list_head        links;          /* Links to related tasks */
         struct list_head        timer_list;     /* Timer list */
-        unsigned long           expires;
 };
 
 /*
@@ -62,6 +61,8 @@ struct rpc_task {
                 struct rpc_wait         tk_wait;        /* RPC wait */
         } u;
 
+        int                     tk_rpc_status;  /* Result of last RPC operation */
+
         /*
          * RPC call state
          */
@@ -125,7 +126,6 @@ struct rpc_task_setup {
 #define RPC_CALL_MAJORSEEN      0x0020          /* major timeout seen */
 #define RPC_TASK_ROOTCREDS      0x0040          /* force root creds */
 #define RPC_TASK_DYNAMIC        0x0080          /* task was kmalloc'ed */
-#define RPC_TASK_KILLED         0x0100          /* task was killed */
 #define RPC_TASK_SOFT           0x0200          /* Use soft timeouts */
 #define RPC_TASK_SOFTCONN       0x0400          /* Fail if can't connect */
 #define RPC_TASK_SENT           0x0800          /* message was sent */
@@ -135,7 +135,6 @@ struct rpc_task_setup {
 
 #define RPC_IS_ASYNC(t)         ((t)->tk_flags & RPC_TASK_ASYNC)
 #define RPC_IS_SWAPPER(t)       ((t)->tk_flags & RPC_TASK_SWAPPER)
-#define RPC_ASSASSINATED(t)     ((t)->tk_flags & RPC_TASK_KILLED)
 #define RPC_IS_SOFT(t)          ((t)->tk_flags & (RPC_TASK_SOFT|RPC_TASK_TIMEOUT))
 #define RPC_IS_SOFTCONN(t)      ((t)->tk_flags & RPC_TASK_SOFTCONN)
 #define RPC_WAS_SENT(t)         ((t)->tk_flags & RPC_TASK_SENT)
@@ -146,6 +145,7 @@ struct rpc_task_setup {
 #define RPC_TASK_NEED_XMIT      3
 #define RPC_TASK_NEED_RECV      4
 #define RPC_TASK_MSG_PIN_WAIT   5
+#define RPC_TASK_SIGNALLED      6
 
 #define RPC_IS_RUNNING(t)       test_bit(RPC_TASK_RUNNING, &(t)->tk_runstate)
 #define rpc_set_running(t)      set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate)
@@ -169,6 +169,8 @@ struct rpc_task_setup {
 
 #define RPC_IS_ACTIVATED(t)     test_bit(RPC_TASK_ACTIVE, &(t)->tk_runstate)
 
+#define RPC_SIGNALLED(t)        test_bit(RPC_TASK_SIGNALLED, &(t)->tk_runstate)
+
 /*
  * Task priorities.
  * Note: if you change these, you must also change
@@ -183,7 +185,6 @@ struct rpc_task_setup {
 struct rpc_timer {
         struct timer_list timer;
         struct list_head list;
-        unsigned long expires;
 };
 
 /*
@@ -217,6 +218,7 @@ struct rpc_task *rpc_run_task(const struct rpc_task_setup *);
 struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req);
 void            rpc_put_task(struct rpc_task *);
 void            rpc_put_task_async(struct rpc_task *);
+void            rpc_signal_task(struct rpc_task *);
 void            rpc_exit_task(struct rpc_task *);
 void            rpc_exit(struct rpc_task *, int);
 void            rpc_release_calldata(const struct rpc_call_ops *, void *);
@@ -225,11 +227,19 @@ void		rpc_execute(struct rpc_task *);
 void            rpc_init_priority_wait_queue(struct rpc_wait_queue *, const char *);
 void            rpc_init_wait_queue(struct rpc_wait_queue *, const char *);
 void            rpc_destroy_wait_queue(struct rpc_wait_queue *);
+unsigned long   rpc_task_timeout(const struct rpc_task *task);
+void            rpc_sleep_on_timeout(struct rpc_wait_queue *queue,
+                                        struct rpc_task *task,
+                                        rpc_action action,
+                                        unsigned long timeout);
 void            rpc_sleep_on(struct rpc_wait_queue *, struct rpc_task *,
                                         rpc_action action);
+void            rpc_sleep_on_priority_timeout(struct rpc_wait_queue *queue,
+                                        struct rpc_task *task,
+                                        unsigned long timeout,
+                                        int priority);
 void            rpc_sleep_on_priority(struct rpc_wait_queue *,
                                         struct rpc_task *,
-                                        rpc_action action,
                                         int priority);
 void rpc_wake_up_queued_task_on_wq(struct workqueue_struct *wq,
                 struct rpc_wait_queue *queue,
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 3a391544299e..a6d9fce7f20e 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -143,7 +143,7 @@ struct rpc_xprt_ops {
         void            (*buf_free)(struct rpc_task *task);
         void            (*prepare_request)(struct rpc_rqst *req);
         int             (*send_request)(struct rpc_rqst *req);
-        void            (*set_retrans_timeout)(struct rpc_task *task);
+        void            (*wait_for_reply_request)(struct rpc_task *task);
         void            (*timer)(struct rpc_xprt *xprt, struct rpc_task *task);
         void            (*release_request)(struct rpc_task *task);
         void            (*close)(struct rpc_xprt *xprt);
@@ -378,8 +378,8 @@ xprt_disable_swap(struct rpc_xprt *xprt)
 int                     xprt_register_transport(struct xprt_class *type);
 int                     xprt_unregister_transport(struct xprt_class *type);
 int                     xprt_load_transport(const char *);
-void                    xprt_set_retrans_timeout_def(struct rpc_task *task);
-void                    xprt_set_retrans_timeout_rtt(struct rpc_task *task);
+void                    xprt_wait_for_reply_request_def(struct rpc_task *task);
+void                    xprt_wait_for_reply_request_rtt(struct rpc_task *task);
 void                    xprt_wake_pending_tasks(struct rpc_xprt *xprt, int status);
 void                    xprt_wait_for_buffer_space(struct rpc_xprt *xprt);
 bool                    xprt_write_space(struct rpc_xprt *xprt);
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index 962975b4313f..df9851cb82b2 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -511,6 +511,33 @@ TRACE_EVENT(xprtrdma_marshal,
         )
 );
 
+TRACE_EVENT(xprtrdma_marshal_failed,
+        TP_PROTO(const struct rpc_rqst *rqst,
+                 int ret
+        ),
+
+        TP_ARGS(rqst, ret),
+
+        TP_STRUCT__entry(
+                __field(unsigned int, task_id)
+                __field(unsigned int, client_id)
+                __field(u32, xid)
+                __field(int, ret)
+        ),
+
+        TP_fast_assign(
+                __entry->task_id = rqst->rq_task->tk_pid;
+                __entry->client_id = rqst->rq_task->tk_client->cl_clid;
+                __entry->xid = be32_to_cpu(rqst->rq_xid);
+                __entry->ret = ret;
+        ),
+
+        TP_printk("task:%u@%u xid=0x%08x: ret=%d",
+                __entry->task_id, __entry->client_id, __entry->xid,
+                __entry->ret
+        )
+);
+
 TRACE_EVENT(xprtrdma_post_send,
         TP_PROTO(
                 const struct rpcrdma_req *req,
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index f0a6f0c5549c..ffa3c51dbb1a 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -82,7 +82,6 @@ TRACE_DEFINE_ENUM(RPC_TASK_SWAPPER);
 TRACE_DEFINE_ENUM(RPC_CALL_MAJORSEEN);
 TRACE_DEFINE_ENUM(RPC_TASK_ROOTCREDS);
 TRACE_DEFINE_ENUM(RPC_TASK_DYNAMIC);
-TRACE_DEFINE_ENUM(RPC_TASK_KILLED);
 TRACE_DEFINE_ENUM(RPC_TASK_SOFT);
 TRACE_DEFINE_ENUM(RPC_TASK_SOFTCONN);
 TRACE_DEFINE_ENUM(RPC_TASK_SENT);
@@ -97,7 +96,6 @@ TRACE_DEFINE_ENUM(RPC_TASK_NO_RETRANS_TIMEOUT);
                 { RPC_CALL_MAJORSEEN, "MAJORSEEN" },                    \
                 { RPC_TASK_ROOTCREDS, "ROOTCREDS" },                    \
                 { RPC_TASK_DYNAMIC, "DYNAMIC" },                        \
-                { RPC_TASK_KILLED, "KILLED" },                          \
                 { RPC_TASK_SOFT, "SOFT" },                              \
                 { RPC_TASK_SOFTCONN, "SOFTCONN" },                      \
                 { RPC_TASK_SENT, "SENT" },                              \
@@ -111,6 +109,7 @@ TRACE_DEFINE_ENUM(RPC_TASK_ACTIVE);
 TRACE_DEFINE_ENUM(RPC_TASK_NEED_XMIT);
 TRACE_DEFINE_ENUM(RPC_TASK_NEED_RECV);
 TRACE_DEFINE_ENUM(RPC_TASK_MSG_PIN_WAIT);
+TRACE_DEFINE_ENUM(RPC_TASK_SIGNALLED);
 
 #define rpc_show_runstate(flags)                                        \
         __print_flags(flags, "|",                                       \
@@ -119,7 +118,8 @@ TRACE_DEFINE_ENUM(RPC_TASK_MSG_PIN_WAIT);
                 { (1UL << RPC_TASK_ACTIVE), "ACTIVE" },                 \
                 { (1UL << RPC_TASK_NEED_XMIT), "NEED_XMIT" },           \
                 { (1UL << RPC_TASK_NEED_RECV), "NEED_RECV" },           \
-                { (1UL << RPC_TASK_MSG_PIN_WAIT), "MSG_PIN_WAIT" })
+                { (1UL << RPC_TASK_MSG_PIN_WAIT), "MSG_PIN_WAIT" },     \
+                { (1UL << RPC_TASK_SIGNALLED), "SIGNALLED" })
 
 DECLARE_EVENT_CLASS(rpc_task_running,
 
@@ -186,7 +186,7 @@ DECLARE_EVENT_CLASS(rpc_task_queued,
                 __entry->client_id = task->tk_client ?
                                      task->tk_client->cl_clid : -1;
                 __entry->task_id = task->tk_pid;
-                __entry->timeout = task->tk_timeout;
+                __entry->timeout = rpc_task_timeout(task);
                 __entry->runstate = task->tk_runstate;
                 __entry->status = task->tk_status;
                 __entry->flags = task->tk_flags;
diff --git a/include/uapi/linux/nfs_mount.h b/include/uapi/linux/nfs_mount.h
index e44e00616ab5..e3bcfc6aa3b0 100644
--- a/include/uapi/linux/nfs_mount.h
+++ b/include/uapi/linux/nfs_mount.h
@@ -66,13 +66,4 @@ struct nfs_mount_data {
 #define NFS_MOUNT_UNSHARED      0x8000  /* 5 */
 #define NFS_MOUNT_FLAGMASK      0xFFFF
 
-/* The following are for internal use only */
-#define NFS_MOUNT_LOOKUP_CACHE_NONEG    0x10000
-#define NFS_MOUNT_LOOKUP_CACHE_NONE     0x20000
-#define NFS_MOUNT_NORESVPORT            0x40000
-#define NFS_MOUNT_LEGACY_INTERFACE      0x80000
-
-#define NFS_MOUNT_LOCAL_FLOCK   0x100000
-#define NFS_MOUNT_LOCAL_FCNTL   0x200000
-
 #endif