Merge tag 'afs-next-20171113' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs

Pull AFS updates from David Howells:
 "kAFS filesystem driver overhaul.

  The major points of the overhaul are:

   (1) Preliminary groundwork is laid for supporting network-namespacing
       of kAFS. The remainder of the namespacing work requires some way
       to pass namespace information to submounts triggered by an
       automount. This requires something like the mount overhaul that's
       in progress.

   (2) sockaddr_rxrpc is used in preference to in_addr for holding
       addresses internally and add support for talking to the YFS VL
       server. With this, kAFS can do everything over IPv6 as well as
       IPv4 if it's talking to servers that support it.

   (3) Callback handling is overhauled to be generally passive rather
       than active. 'Callbacks' are promises by the server to tell us
       about data and metadata changes. Callbacks are now checked when
       we next touch an inode rather than actively going and looking for
       it where possible.

   (4) File access permit caching is overhauled to store the caching
       information per-inode rather than per-directory, shared over
       subordinate files. Whilst older AFS servers only allow ACLs on
       directories (shared to the files in that directory), newer AFS
       servers break that restriction.

       To improve memory usage and to make it easier to do mass-key
       removal, permit combinations are cached and shared.

   (5) Cell database management is overhauled to allow lighter locks to
       be used and to make cell records autonomous state machines that
       look after getting their own DNS records and cleaning themselves
       up, in particular preventing races in acquiring and relinquishing
       the fscache token for the cell.

   (6) Volume caching is overhauled. The afs_vlocation record is got rid
       of to simplify things and the superblock is now keyed on the cell
       and the numeric volume ID only. The volume record is tied to a
       superblock and normal superblock management is used to mediate
       the lifetime of the volume fscache token.

   (7) File server record caching is overhauled to make server records
       independent of cells and volumes. A server can be in multiple
       cells (in such a case, the administrator must make sure that the
       VL services for all cells correctly reflect the volumes shared
       between those cells).

       Server records are now indexed using the UUID of the server
       rather than the address since a server can have multiple
       addresses.

   (8) File server rotation is overhauled to handle VMOVED, VBUSY (and
       similar), VOFFLINE and VNOVOL indications and to handle rotation
       both of servers and addresses of those servers. The rotation will
       also wait and retry if the server says it is busy.

   (9) Data writeback is overhauled. Each inode no longer stores a list
       of modified sections tagged with the key that authorised it in
       favour of noting the modified region of a page in page->private
       and storing a list of keys that made modifications in the inode.

       This simplifies things and allows other keys to be used to
       actually write to the server if a key that made a modification
       becomes useless.

  (10) Writable mmap() is implemented. This allows a kernel to be build
       entirely on AFS.

  Note that Pre AFS-3.4 servers are no longer supported, though this can
  be added back if necessary (AFS-3.4 was released in 1998)"

* tag 'afs-next-20171113' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs: (35 commits)
  afs: Protect call->state changes against signals
  afs: Trace page dirty/clean
  afs: Implement shared-writeable mmap
  afs: Get rid of the afs_writeback record
  afs: Introduce a file-private data record
  afs: Use a dynamic port if 7001 is in use
  afs: Fix directory read/modify race
  afs: Trace the sending of pages
  afs: Trace the initiation and completion of client calls
  afs: Fix documentation on # vs % prefix in mount source specification
  afs: Fix total-length calculation for multiple-page send
  afs: Only progress call state at end of Tx phase from rxrpc callback
  afs: Make use of the YFS service upgrade to fully support IPv6
  afs: Overhaul volume and server record caching and fileserver rotation
  afs: Move server rotation code into its own file
  afs: Add an address list concept
  afs: Overhaul cell database management
  afs: Overhaul permit caching
  afs: Overhaul the callback handling
  afs: Rename struct afs_call server member to cm_server
  ...

3 files changed, 303 insertions, 6 deletions

diff --git a/include/linux/wait_bit.h b/include/linux/wait_bit.h
index af0d495430d7..61b39eaf7cad 100644
--- a/include/linux/wait_bit.h
+++ b/include/linux/wait_bit.h
@@ -26,6 +26,8 @@ struct wait_bit_queue_entry {
         { .flags = p, .bit_nr = WAIT_ATOMIC_T_BIT_NR, }
 
 typedef int wait_bit_action_f(struct wait_bit_key *key, int mode);
+typedef int wait_atomic_t_action_f(atomic_t *counter, unsigned int mode);
+
 void __wake_up_bit(struct wait_queue_head *wq_head, void *word, int bit);
 int __wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode);
 int __wait_on_bit_lock(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode);
@@ -34,7 +36,7 @@ void wake_up_atomic_t(atomic_t *p);
 int out_of_line_wait_on_bit(void *word, int, wait_bit_action_f *action, unsigned int mode);
 int out_of_line_wait_on_bit_timeout(void *word, int, wait_bit_action_f *action, unsigned int mode, unsigned long timeout);
 int out_of_line_wait_on_bit_lock(void *word, int, wait_bit_action_f *action, unsigned int mode);
-int out_of_line_wait_on_atomic_t(atomic_t *p, int (*)(atomic_t *), unsigned int mode);
+int out_of_line_wait_on_atomic_t(atomic_t *p, wait_atomic_t_action_f action, unsigned int mode);
 struct wait_queue_head *bit_waitqueue(void *word, int bit);
 extern void __init wait_bit_init(void);
 
@@ -51,10 +53,11 @@ int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync
                 },                                                              \
         }
 
-extern int bit_wait(struct wait_bit_key *key, int bit);
-extern int bit_wait_io(struct wait_bit_key *key, int bit);
-extern int bit_wait_timeout(struct wait_bit_key *key, int bit);
-extern int bit_wait_io_timeout(struct wait_bit_key *key, int bit);
+extern int bit_wait(struct wait_bit_key *key, int mode);
+extern int bit_wait_io(struct wait_bit_key *key, int mode);
+extern int bit_wait_timeout(struct wait_bit_key *key, int mode);
+extern int bit_wait_io_timeout(struct wait_bit_key *key, int mode);
+extern int atomic_t_wait(atomic_t *counter, unsigned int mode);
 
 /**
  * wait_on_bit - wait for a bit to be cleared
@@ -251,7 +254,7 @@ wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action,
  * outside of the target 'word'.
  */
 static inline
-int wait_on_atomic_t(atomic_t *val, int (*action)(atomic_t *), unsigned mode)
+int wait_on_atomic_t(atomic_t *val, wait_atomic_t_action_f action, unsigned mode)
 {
         might_sleep();
         if (atomic_read(val) == 0)
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 8b95c16b7045..6b59c63a8e51 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -30,6 +30,38 @@ enum afs_call_trace {
         afs_call_trace_work,
 };
 
+enum afs_fs_operation {
+        afs_FS_FetchData                = 130,  /* AFS Fetch file data */
+        afs_FS_FetchStatus              = 132,  /* AFS Fetch file status */
+        afs_FS_StoreData                = 133,  /* AFS Store file data */
+        afs_FS_StoreStatus              = 135,  /* AFS Store file status */
+        afs_FS_RemoveFile               = 136,  /* AFS Remove a file */
+        afs_FS_CreateFile               = 137,  /* AFS Create a file */
+        afs_FS_Rename                   = 138,  /* AFS Rename or move a file or directory */
+        afs_FS_Symlink                  = 139,  /* AFS Create a symbolic link */
+        afs_FS_Link                     = 140,  /* AFS Create a hard link */
+        afs_FS_MakeDir                  = 141,  /* AFS Create a directory */
+        afs_FS_RemoveDir                = 142,  /* AFS Remove a directory */
+        afs_FS_GetVolumeInfo            = 148,  /* AFS Get information about a volume */
+        afs_FS_GetVolumeStatus          = 149,  /* AFS Get volume status information */
+        afs_FS_GetRootVolume            = 151,  /* AFS Get root volume name */
+        afs_FS_SetLock                  = 156,  /* AFS Request a file lock */
+        afs_FS_ExtendLock               = 157,  /* AFS Extend a file lock */
+        afs_FS_ReleaseLock              = 158,  /* AFS Release a file lock */
+        afs_FS_Lookup                   = 161,  /* AFS lookup file in directory */
+        afs_FS_FetchData64              = 65537, /* AFS Fetch file data */
+        afs_FS_StoreData64              = 65538, /* AFS Store file data */
+        afs_FS_GiveUpAllCallBacks       = 65539, /* AFS Give up all our callbacks on a server */
+        afs_FS_GetCapabilities          = 65540, /* AFS Get FS server capabilities */
+};
+
+enum afs_vl_operation {
+        afs_VL_GetEntryByNameU  = 527,          /* AFS Get Vol Entry By Name operation ID */
+        afs_VL_GetAddrsU        = 533,          /* AFS Get FS server addresses */
+        afs_YFSVL_GetEndpoints  = 64002,        /* YFS Get FS & Vol server addresses */
+        afs_VL_GetCapabilities  = 65537,        /* AFS Get VL server capabilities */
+};
+
 #endif /* end __AFS_DECLARE_TRACE_ENUMS_ONCE_ONLY */
 
 /*
@@ -42,6 +74,37 @@ enum afs_call_trace {
         EM(afs_call_trace_wake,                 "WAKE ") \
         E_(afs_call_trace_work,                 "WORK ")
 
+#define afs_fs_operations \
+        EM(afs_FS_FetchData,                    "FS.FetchData") \
+        EM(afs_FS_FetchStatus,                  "FS.FetchStatus") \
+        EM(afs_FS_StoreData,                    "FS.StoreData") \
+        EM(afs_FS_StoreStatus,                  "FS.StoreStatus") \
+        EM(afs_FS_RemoveFile,                   "FS.RemoveFile") \
+        EM(afs_FS_CreateFile,                   "FS.CreateFile") \
+        EM(afs_FS_Rename,                       "FS.Rename") \
+        EM(afs_FS_Symlink,                      "FS.Symlink") \
+        EM(afs_FS_Link,                         "FS.Link") \
+        EM(afs_FS_MakeDir,                      "FS.MakeDir") \
+        EM(afs_FS_RemoveDir,                    "FS.RemoveDir") \
+        EM(afs_FS_GetVolumeInfo,                "FS.GetVolumeInfo") \
+        EM(afs_FS_GetVolumeStatus,              "FS.GetVolumeStatus") \
+        EM(afs_FS_GetRootVolume,                "FS.GetRootVolume") \
+        EM(afs_FS_SetLock,                      "FS.SetLock") \
+        EM(afs_FS_ExtendLock,                   "FS.ExtendLock") \
+        EM(afs_FS_ReleaseLock,                  "FS.ReleaseLock") \
+        EM(afs_FS_Lookup,                       "FS.Lookup") \
+        EM(afs_FS_FetchData64,                  "FS.FetchData64") \
+        EM(afs_FS_StoreData64,                  "FS.StoreData64") \
+        EM(afs_FS_GiveUpAllCallBacks,           "FS.GiveUpAllCallBacks") \
+        E_(afs_FS_GetCapabilities,              "FS.GetCapabilities")
+
+#define afs_vl_operations \
+        EM(afs_VL_GetEntryByNameU,              "VL.GetEntryByNameU") \
+        EM(afs_VL_GetAddrsU,                    "VL.GetAddrsU") \
+        EM(afs_YFSVL_GetEndpoints,              "YFSVL.GetEndpoints") \
+        E_(afs_VL_GetCapabilities,              "VL.GetCapabilities")
+
+
 /*
  * Export enum symbols via userspace.
  */
@@ -51,6 +114,8 @@ enum afs_call_trace {
 #define E_(a, b) TRACE_DEFINE_ENUM(a);
 
 afs_call_traces;
+afs_fs_operations;
+afs_vl_operations;
 
 /*
  * Now redefine the EM() and E_() macros to map the enums to the strings that
@@ -178,6 +243,234 @@ TRACE_EVENT(afs_call,
                       __entry->where)
             );
 
+TRACE_EVENT(afs_make_fs_call,
+            TP_PROTO(struct afs_call *call, const struct afs_fid *fid),
+
+            TP_ARGS(call, fid),
+
+            TP_STRUCT__entry(
+                    __field(struct afs_call *,          call            )
+                    __field(enum afs_fs_operation,      op              )
+                    __field_struct(struct afs_fid,      fid             )
+                             ),
+
+            TP_fast_assign(
+                    __entry->call = call;
+                    __entry->op = call->operation_ID;
+                    if (fid) {
+                            __entry->fid = *fid;
+                    } else {
+                            __entry->fid.vid = 0;
+                            __entry->fid.vnode = 0;
+                            __entry->fid.unique = 0;
+                    }
+                           ),
+
+            TP_printk("c=%p %06x:%06x:%06x %s",
+                      __entry->call,
+                      __entry->fid.vid,
+                      __entry->fid.vnode,
+                      __entry->fid.unique,
+                      __print_symbolic(__entry->op, afs_fs_operations))
+            );
+
+TRACE_EVENT(afs_make_vl_call,
+            TP_PROTO(struct afs_call *call),
+
+            TP_ARGS(call),
+
+            TP_STRUCT__entry(
+                    __field(struct afs_call *,          call            )
+                    __field(enum afs_vl_operation,      op              )
+                             ),
+
+            TP_fast_assign(
+                    __entry->call = call;
+                    __entry->op = call->operation_ID;
+                           ),
+
+            TP_printk("c=%p %s",
+                      __entry->call,
+                      __print_symbolic(__entry->op, afs_vl_operations))
+            );
+
+TRACE_EVENT(afs_call_done,
+            TP_PROTO(struct afs_call *call),
+
+            TP_ARGS(call),
+
+            TP_STRUCT__entry(
+                    __field(struct afs_call *,          call            )
+                    __field(struct rxrpc_call *,        rx_call         )
+                    __field(int,                        ret             )
+                    __field(u32,                        abort_code      )
+                             ),
+
+            TP_fast_assign(
+                    __entry->call = call;
+                    __entry->rx_call = call->rxcall;
+                    __entry->ret = call->error;
+                    __entry->abort_code = call->abort_code;
+                           ),
+
+            TP_printk("   c=%p ret=%d ab=%d [%p]",
+                      __entry->call,
+                      __entry->ret,
+                      __entry->abort_code,
+                      __entry->rx_call)
+            );
+
+TRACE_EVENT(afs_send_pages,
+            TP_PROTO(struct afs_call *call, struct msghdr *msg,
+                     pgoff_t first, pgoff_t last, unsigned int offset),
+
+            TP_ARGS(call, msg, first, last, offset),
+
+            TP_STRUCT__entry(
+                    __field(struct afs_call *,          call            )
+                    __field(pgoff_t,                    first           )
+                    __field(pgoff_t,                    last            )
+                    __field(unsigned int,               nr              )
+                    __field(unsigned int,               bytes           )
+                    __field(unsigned int,               offset          )
+                    __field(unsigned int,               flags           )
+                             ),
+
+            TP_fast_assign(
+                    __entry->call = call;
+                    __entry->first = first;
+                    __entry->last = last;
+                    __entry->nr = msg->msg_iter.nr_segs;
+                    __entry->bytes = msg->msg_iter.count;
+                    __entry->offset = offset;
+                    __entry->flags = msg->msg_flags;
+                           ),
+
+            TP_printk(" c=%p %lx-%lx-%lx b=%x o=%x f=%x",
+                      __entry->call,
+                      __entry->first, __entry->first + __entry->nr - 1, __entry->last,
+                      __entry->bytes, __entry->offset,
+                      __entry->flags)
+            );
+
+TRACE_EVENT(afs_sent_pages,
+            TP_PROTO(struct afs_call *call, pgoff_t first, pgoff_t last,
+                     pgoff_t cursor, int ret),
+
+            TP_ARGS(call, first, last, cursor, ret),
+
+            TP_STRUCT__entry(
+                    __field(struct afs_call *,          call            )
+                    __field(pgoff_t,                    first           )
+                    __field(pgoff_t,                    last            )
+                    __field(pgoff_t,                    cursor          )
+                    __field(int,                        ret             )
+                             ),
+
+            TP_fast_assign(
+                    __entry->call = call;
+                    __entry->first = first;
+                    __entry->last = last;
+                    __entry->cursor = cursor;
+                    __entry->ret = ret;
+                           ),
+
+            TP_printk(" c=%p %lx-%lx c=%lx r=%d",
+                      __entry->call,
+                      __entry->first, __entry->last,
+                      __entry->cursor, __entry->ret)
+            );
+
+TRACE_EVENT(afs_dir_check_failed,
+            TP_PROTO(struct afs_vnode *vnode, loff_t off, loff_t i_size),
+
+            TP_ARGS(vnode, off, i_size),
+
+            TP_STRUCT__entry(
+                    __field(struct afs_vnode *,         vnode           )
+                    __field(loff_t,                     off             )
+                    __field(loff_t,                     i_size          )
+                             ),
+
+            TP_fast_assign(
+                    __entry->vnode = vnode;
+                    __entry->off = off;
+                    __entry->i_size = i_size;
+                           ),
+
+            TP_printk("vn=%p %llx/%llx",
+                      __entry->vnode, __entry->off, __entry->i_size)
+            );
+
+/*
+ * We use page->private to hold the amount of the page that we've written to,
+ * splitting the field into two parts.  However, we need to represent a range
+ * 0...PAGE_SIZE inclusive, so we can't support 64K pages on a 32-bit system.
+ */
+#if PAGE_SIZE > 32768
+#define AFS_PRIV_MAX    0xffffffff
+#define AFS_PRIV_SHIFT  32
+#else
+#define AFS_PRIV_MAX    0xffff
+#define AFS_PRIV_SHIFT  16
+#endif
+
+TRACE_EVENT(afs_page_dirty,
+            TP_PROTO(struct afs_vnode *vnode, const char *where,
+                     pgoff_t page, unsigned long priv),
+
+            TP_ARGS(vnode, where, page, priv),
+
+            TP_STRUCT__entry(
+                    __field(struct afs_vnode *,         vnode           )
+                    __field(const char *,               where           )
+                    __field(pgoff_t,                    page            )
+                    __field(unsigned long,              priv            )
+                             ),
+
+            TP_fast_assign(
+                    __entry->vnode = vnode;
+                    __entry->where = where;
+                    __entry->page = page;
+                    __entry->priv = priv;
+                           ),
+
+            TP_printk("vn=%p %lx %s %lu-%lu",
+                      __entry->vnode, __entry->page, __entry->where,
+                      __entry->priv & AFS_PRIV_MAX,
+                      __entry->priv >> AFS_PRIV_SHIFT)
+            );
+
+TRACE_EVENT(afs_call_state,
+            TP_PROTO(struct afs_call *call,
+                     enum afs_call_state from,
+                     enum afs_call_state to,
+                     int ret, u32 remote_abort),
+
+            TP_ARGS(call, from, to, ret, remote_abort),
+
+            TP_STRUCT__entry(
+                    __field(struct afs_call *,          call            )
+                    __field(enum afs_call_state,        from            )
+                    __field(enum afs_call_state,        to              )
+                    __field(int,                        ret             )
+                    __field(u32,                        abort           )
+                             ),
+
+            TP_fast_assign(
+                    __entry->call = call;
+                    __entry->from = from;
+                    __entry->to = to;
+                    __entry->ret = ret;
+                    __entry->abort = remote_abort;
+                           ),
+
+            TP_printk("c=%p %u->%u r=%d ab=%d",
+                      __entry->call,
+                      __entry->from, __entry->to,
+                      __entry->ret, __entry->abort)
+            );
+
 #endif /* _TRACE_AFS_H */
 
 /* This part must be outside protection */
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index aa50113ebe5b..1a6fee974116 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -47,6 +47,7 @@
 #define OPENPROM_SUPER_MAGIC    0x9fa1
 #define QNX4_SUPER_MAGIC        0x002f          /* qnx4 fs detection */
 #define QNX6_SUPER_MAGIC        0x68191122      /* qnx6 fs detection */
+#define AFS_FS_MAGIC            0x6B414653
 
 #define REISERFS_SUPER_MAGIC    0x52654973      /* used by gcc */
                                         /* used by file system utilities that