5 files changed, 151 insertions, 4 deletions

diff --git a/Documentation/filesystems/nfs/00-INDEX b/Documentation/filesystems/nfs/00-INDEX
index 3225a5662114..a57e12411d2a 100644
--- a/Documentation/filesystems/nfs/00-INDEX
+++ b/Documentation/filesystems/nfs/00-INDEX
@@ -12,6 +12,8 @@ nfs-rdma.txt
         - how to install and setup the Linux NFS/RDMA client and server software
 nfsroot.txt
         - short guide on setting up a diskless box with NFS root filesystem.
+pnfs.txt
+        - short explanation of some of the internals of the pnfs client code
 rpc-cache.txt
         - introduction to the caching mechanisms in the sunrpc layer.
 idmapper.txt
diff --git a/Documentation/filesystems/nfs/pnfs.txt b/Documentation/filesystems/nfs/pnfs.txt
new file mode 100644
index 000000000000..bc0b9cfe095b
--- /dev/null
+++ b/Documentation/filesystems/nfs/pnfs.txt
@@ -0,0 +1,48 @@
+Reference counting in pnfs:
+==========================
+
+The are several inter-related caches.  We have layouts which can
+reference multiple devices, each of which can reference multiple data servers.
+Each data server can be referenced by multiple devices.  Each device
+can be referenced by multiple layouts.  To keep all of this straight,
+we need to reference count.
+
+
+struct pnfs_layout_hdr
+----------------------
+The on-the-wire command LAYOUTGET corresponds to struct
+pnfs_layout_segment, usually referred to by the variable name lseg.
+Each nfs_inode may hold a pointer to a cache of of these layout
+segments in nfsi->layout, of type struct pnfs_layout_hdr.
+
+We reference the header for the inode pointing to it, across each
+outstanding RPC call that references it (LAYOUTGET, LAYOUTRETURN,
+LAYOUTCOMMIT), and for each lseg held within.
+
+Each header is also (when non-empty) put on a list associated with
+struct nfs_client (cl_layouts).  Being put on this list does not bump
+the reference count, as the layout is kept around by the lseg that
+keeps it in the list.
+
+deviceid_cache
+--------------
+lsegs reference device ids, which are resolved per nfs_client and
+layout driver type.  The device ids are held in a RCU cache (struct
+nfs4_deviceid_cache).  The cache itself is referenced across each
+mount.  The entries (struct nfs4_deviceid) themselves are held across
+the lifetime of each lseg referencing them.
+
+RCU is used because the deviceid is basically a write once, read many
+data structure.  The hlist size of 32 buckets needs better
+justification, but seems reasonable given that we can have multiple
+deviceid's per filesystem, and multiple filesystems per nfs_client.
+
+The hash code is copied from the nfsd code base.  A discussion of
+hashing and variations of this algorithm can be found at:
+http://groups.google.com/group/comp.lang.c/browse_thread/thread/9522965e2b8d3809
+
+data server cache
+-----------------
+file driver devices refer to data servers, which are kept in a module
+level cache.  Its reference is held over the lifetime of the deviceid
+pointing to it.
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 3f69752d6f18..d94311943ec6 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -75,13 +75,17 @@ config NFS_V4
 
 config NFS_V4_1
         bool "NFS client support for NFSv4.1 (EXPERIMENTAL)"
-        depends on NFS_V4 && EXPERIMENTAL
+        depends on NFS_FS && NFS_V4 && EXPERIMENTAL
+        select PNFS_FILE_LAYOUT
         help
           This option enables support for minor version 1 of the NFSv4 protocol
-          (draft-ietf-nfsv4-minorversion1) in the kernel's NFS client.
+          (RFC 5661) in the kernel's NFS client.
 
           If unsure, say N.
 
+config PNFS_FILE_LAYOUT
+        tristate
+
 config ROOT_NFS
         bool "Root file system on NFS"
         depends on NFS_FS=y && IP_PNP
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index b483026e82aa..cf795625610e 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -32,16 +32,51 @@
 
 #define NFSDBG_FACILITY         NFSDBG_PNFS
 
-/* STUB that returns the equivalent of "no module found" */
+/* Locking:
+ *
+ * pnfs_spinlock:
+ *      protects pnfs_modules_tbl.
+ */
+static DEFINE_SPINLOCK(pnfs_spinlock);
+
+/*
+ * pnfs_modules_tbl holds all pnfs modules
+ */
+static LIST_HEAD(pnfs_modules_tbl);
+
+/* Return the registered pnfs layout driver module matching given id */
+static struct pnfs_layoutdriver_type *
+find_pnfs_driver_locked(u32 id)
+{
+        struct pnfs_layoutdriver_type *local;
+
+        list_for_each_entry(local, &pnfs_modules_tbl, pnfs_tblid)
+                if (local->id == id)
+                        goto out;
+        local = NULL;
+out:
+        dprintk("%s: Searching for id %u, found %p\n", __func__, id, local);
+        return local;
+}
+
 static struct pnfs_layoutdriver_type *
 find_pnfs_driver(u32 id)
 {
-        return NULL;
+        struct pnfs_layoutdriver_type *local;
+
+        spin_lock(&pnfs_spinlock);
+        local = find_pnfs_driver_locked(id);
+        spin_unlock(&pnfs_spinlock);
+        return local;
 }
 
 void
 unset_pnfs_layoutdriver(struct nfs_server *nfss)
 {
+        if (nfss->pnfs_curr_ld) {
+                nfss->pnfs_curr_ld->uninitialize_mountpoint(nfss);
+                module_put(nfss->pnfs_curr_ld->owner);
+        }
         nfss->pnfs_curr_ld = NULL;
 }
 
@@ -74,7 +109,18 @@ set_pnfs_layoutdriver(struct nfs_server *server, u32 id)
                         goto out_no_driver;
                 }
         }
+        if (!try_module_get(ld_type->owner)) {
+                dprintk("%s: Could not grab reference on module\n", __func__);
+                goto out_no_driver;
+        }
         server->pnfs_curr_ld = ld_type;
+        if (ld_type->initialize_mountpoint(server)) {
+                printk(KERN_ERR
+                       "%s: Error initializing mount point for layout driver %u.\n",
+                       __func__, id);
+                module_put(ld_type->owner);
+                goto out_no_driver;
+        }
         dprintk("%s: pNFS module for %u set\n", __func__, id);
         return;
 
@@ -82,3 +128,41 @@ out_no_driver:
         dprintk("%s: Using NFSv4 I/O\n", __func__);
         server->pnfs_curr_ld = NULL;
 }
+
+int
+pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *ld_type)
+{
+        int status = -EINVAL;
+        struct pnfs_layoutdriver_type *tmp;
+
+        if (ld_type->id == 0) {
+                printk(KERN_ERR "%s id 0 is reserved\n", __func__);
+                return status;
+        }
+
+        spin_lock(&pnfs_spinlock);
+        tmp = find_pnfs_driver_locked(ld_type->id);
+        if (!tmp) {
+                list_add(&ld_type->pnfs_tblid, &pnfs_modules_tbl);
+                status = 0;
+                dprintk("%s Registering id:%u name:%s\n", __func__, ld_type->id,
+                        ld_type->name);
+        } else {
+                printk(KERN_ERR "%s Module with id %d already loaded!\n",
+                        __func__, ld_type->id);
+        }
+        spin_unlock(&pnfs_spinlock);
+
+        return status;
+}
+EXPORT_SYMBOL_GPL(pnfs_register_layoutdriver);
+
+void
+pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *ld_type)
+{
+        dprintk("%s Deregistering id:%u\n", __func__, ld_type->id);
+        spin_lock(&pnfs_spinlock);
+        list_del(&ld_type->pnfs_tblid);
+        spin_unlock(&pnfs_spinlock);
+}
+EXPORT_SYMBOL_GPL(pnfs_unregister_layoutdriver);
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index c628ef131d83..61531f338576 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -36,8 +36,17 @@
 
 /* Per-layout driver specific registration structure */
 struct pnfs_layoutdriver_type {
+        struct list_head pnfs_tblid;
+        const u32 id;
+        const char *name;
+        struct module *owner;
+        int (*initialize_mountpoint) (struct nfs_server *);
+        int (*uninitialize_mountpoint) (struct nfs_server *);
 };
 
+extern int pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *);
+extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *);
+
 void set_pnfs_layoutdriver(struct nfs_server *, u32 id);
 void unset_pnfs_layoutdriver(struct nfs_server *);