linux/fs/nfs/internal.h

469 lines
13 KiB
C
Raw Normal View History

/*
* NFS internal definitions
*/
#include "nfs4_fs.h"
#include <linux/mount.h>
#include <linux/security.h>
NFS: Define and create superblock-level objects Define and create superblock-level cache index objects (as managed by nfs_server structs). Each superblock object is created in a server level index object and is itself an index into which inode-level objects are inserted. Ideally there would be one superblock-level object per server, and the former would be folded into the latter; however, since the "nosharecache" option exists this isn't possible. The superblock object key is a sequence consisting of: (1) Certain superblock s_flags. (2) Various connection parameters that serve to distinguish superblocks for sget(). (3) The volume FSID. (4) The security flavour. (5) The uniquifier length. (6) The uniquifier text. This is normally an empty string, unless the fsc=xyz mount option was used to explicitly specify a uniquifier. The key blob is of variable length, depending on the length of (6). The superblock object is given no coherency data to carry in the auxiliary data permitted by the cache. It is assumed that the superblock is always coherent. This patch also adds uniquification handling such that two otherwise identical superblocks, at least one of which is marked "nosharecache", won't end up trying to share the on-disk cache. It will be possible to manually provide a uniquifier through a mount option with a later patch to avoid the error otherwise produced. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Steve Dickson <steved@redhat.com> Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Tested-by: Daire Byrne <Daire.Byrne@framestore.com>
2009-04-03 15:42:42 +00:00
#define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS)
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 00:06:13 +00:00
struct nfs_string;
/* Maximum number of readahead requests
* FIXME: this should really be a sysctl so that users may tune it to suit
* their needs. People that do NFS over a slow network, might for
* instance want to reduce it to something closer to 1 for improved
* interactive response.
*/
#define NFS_MAX_READAHEAD (RPC_DEF_SLOT_TABLE - 1)
/*
* Determine if sessions are in use.
*/
static inline int nfs4_has_session(const struct nfs_client *clp)
{
#ifdef CONFIG_NFS_V4_1
if (clp->cl_session)
return 1;
#endif /* CONFIG_NFS_V4_1 */
return 0;
}
static inline int nfs4_has_persistent_session(const struct nfs_client *clp)
{
#ifdef CONFIG_NFS_V4_1
if (nfs4_has_session(clp))
return (clp->cl_session->flags & SESSION4_PERSIST);
#endif /* CONFIG_NFS_V4_1 */
return 0;
}
static inline void nfs_attr_check_mountpoint(struct super_block *parent, struct nfs_fattr *fattr)
{
if (!nfs_fsid_equal(&NFS_SB(parent)->fsid, &fattr->fsid))
fattr->valid |= NFS_ATTR_FATTR_MOUNTPOINT;
}
static inline int nfs_attr_use_mounted_on_fileid(struct nfs_fattr *fattr)
{
if (((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) == 0) ||
(((fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT) == 0) &&
((fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) == 0)))
return 0;
fattr->fileid = fattr->mounted_on_fileid;
return 1;
}
struct nfs_clone_mount {
const struct super_block *sb;
const struct dentry *dentry;
struct nfs_fh *fh;
struct nfs_fattr *fattr;
char *hostname;
char *mnt_path;
struct sockaddr *addr;
size_t addrlen;
rpc_authflavor_t authflavor;
};
/*
* Note: RFC 1813 doesn't limit the number of auth flavors that
* a server can return, so make something up.
*/
#define NFS_MAX_SECFLAVORS (12)
/*
* Value used if the user did not specify a port value.
*/
#define NFS_UNSPEC_PORT (-1)
/*
* Maximum number of pages that readdir can use for creating
* a vmapped array of pages.
*/
#define NFS_MAX_READDIR_PAGES 8
/*
* In-kernel mount arguments
*/
struct nfs_parsed_mount_data {
int flags;
int rsize, wsize;
int timeo, retrans;
int acregmin, acregmax,
acdirmin, acdirmax;
int namlen;
unsigned int options;
unsigned int bsize;
unsigned int auth_flavor_len;
rpc_authflavor_t auth_flavors[1];
char *client_address;
unsigned int version;
unsigned int minorversion;
NFS: Define and create superblock-level objects Define and create superblock-level cache index objects (as managed by nfs_server structs). Each superblock object is created in a server level index object and is itself an index into which inode-level objects are inserted. Ideally there would be one superblock-level object per server, and the former would be folded into the latter; however, since the "nosharecache" option exists this isn't possible. The superblock object key is a sequence consisting of: (1) Certain superblock s_flags. (2) Various connection parameters that serve to distinguish superblocks for sget(). (3) The volume FSID. (4) The security flavour. (5) The uniquifier length. (6) The uniquifier text. This is normally an empty string, unless the fsc=xyz mount option was used to explicitly specify a uniquifier. The key blob is of variable length, depending on the length of (6). The superblock object is given no coherency data to carry in the auxiliary data permitted by the cache. It is assumed that the superblock is always coherent. This patch also adds uniquification handling such that two otherwise identical superblocks, at least one of which is marked "nosharecache", won't end up trying to share the on-disk cache. It will be possible to manually provide a uniquifier through a mount option with a later patch to avoid the error otherwise produced. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Steve Dickson <steved@redhat.com> Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Tested-by: Daire Byrne <Daire.Byrne@framestore.com>
2009-04-03 15:42:42 +00:00
char *fscache_uniq;
struct {
struct sockaddr_storage address;
size_t addrlen;
char *hostname;
u32 version;
int port;
unsigned short protocol;
} mount_server;
struct {
struct sockaddr_storage address;
size_t addrlen;
char *hostname;
char *export_path;
int port;
unsigned short protocol;
} nfs_server;
struct security_mnt_opts lsm_opts;
struct net *net;
};
/* mount_clnt.c */
struct nfs_mount_request {
struct sockaddr *sap;
size_t salen;
char *hostname;
char *dirpath;
u32 version;
unsigned short protocol;
struct nfs_fh *fh;
int noresvport;
unsigned int *auth_flav_len;
rpc_authflavor_t *auth_flavs;
struct net *net;
};
extern int nfs_mount(struct nfs_mount_request *info);
extern void nfs_umount(const struct nfs_mount_request *info);
/* client.c */
extern const struct rpc_program nfs_program;
extern void nfs_clients_init(struct net *net);
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 00:06:13 +00:00
extern void nfs_cleanup_cb_ident_idr(struct net *);
extern void nfs_put_client(struct nfs_client *);
extern struct nfs_client *nfs4_find_client_ident(struct net *, int);
NFS refactor nfs_find_client and reference client across callback processing Fixes a bug where the nfs_client could be freed during callback processing. Refactor nfs_find_client to use minorversion specific means to locate the correct nfs_client structure. In the NFS layer, V4.0 clients are found using the callback_ident field in the CB_COMPOUND header. V4.1 clients are found using the sessionID in the CB_SEQUENCE operation which is also compared against the sessionID associated with the back channel thread after a successful CREATE_SESSION. Each of these methods finds the one an only nfs_client associated with the incoming callback request - so nfs_find_client_next is not needed. In the RPC layer, the pg_authenticate call needs to find the nfs_client. For the v4.0 callback service, the callback identifier has not been decoded so a search by address, version, and minorversion is used. The sessionid for the sessions based callback service has (usually) not been set for the pg_authenticate on a CB_NULL call which can be sent prior to the return of a CREATE_SESSION call, so the sessionid associated with the back channel thread is not used to find the client in pg_authenticate for CB_NULL calls. Pass the referenced nfs_client to each CB_COMPOUND operation being proceesed via the new cb_process_state structure. The reference is held across cb_compound processing. Use the new cb_process_state struct to move the NFS4ERR_RETRY_UNCACHED_REP processing from process_op into nfs4_callback_sequence where it belongs. Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-01-06 02:04:32 +00:00
extern struct nfs_client *
nfs4_find_client_sessionid(struct net *, const struct sockaddr *,
struct nfs4_sessionid *);
extern struct nfs_server *nfs_create_server(
const struct nfs_parsed_mount_data *,
struct nfs_fh *);
extern struct nfs_server *nfs4_create_server(
const struct nfs_parsed_mount_data *,
struct nfs_fh *);
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 00:06:13 +00:00
extern struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *,
struct nfs_fh *);
extern void nfs_free_server(struct nfs_server *server);
extern struct nfs_server *nfs_clone_server(struct nfs_server *,
struct nfs_fh *,
struct nfs_fattr *);
nfs41: add session setup to the state manager At mount, nfs_alloc_client sets the cl_state NFS4CLNT_LEASE_EXPIRED bit and nfs4_alloc_session sets the NFS4CLNT_SESSION_SETUP bit, so both bits are set when nfs4_lookup_root calls nfs4_recover_expired_lease which schedules the nfs4_state_manager and waits for it to complete. Place the session setup after the clientid establishment in nfs4_state_manager so that the session is setup right after the clientid has been established without rescheduling the state manager. Unlike nfsv4.0, the nfs_client struct is not ready to use until the session has been established. Postpone marking the nfs_client struct to NFS_CS_READY until after a successful CREATE_SESSION call so that other threads cannot use the client until the session is established. If the EXCHANGE_ID call fails and the session has not been setup (the NFS4CLNT_SESSION_SETUP bit is set), mark the client with the error and return. If the session setup CREATE_SESSION call fails with NFS4ERR_STALE_CLIENTID which could occur due to server reboot or network partition inbetween the EXCHANGE_ID and CREATE_SESSION call, reset the NFS4CLNT_LEASE_EXPIRED and NFS4CLNT_SESSION_SETUP bits and try again. If the CREATE_SESSION call fails with other errors, mark the client with the error and return. Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfs41: NFS_CS_SESSION_SETUP cl_cons_state for back channel setup] On session setup, the CREATE_SESSION reply races with the server back channel probe which needs to succeed to setup the back channel. Set a new cl_cons_state NFS_CS_SESSION_SETUP just prior to the CREATE_SESSION call and add it as a valid state to nfs_find_client so that the client back channel can find the nfs_client struct and won't drop the server backchannel probe. Use a new cl_cons_state so that NFSv4.0 back channel behaviour which only sets NFS_CS_READY is unchanged. Adjust waiting on the nfs_client_active_wq accordingly. Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfs41: rename NFS_CS_SESSION_SETUP to NFS_CS_SESSION_INITING] Signed-off-by: Andy Adamson <andros@netapp.com> [nfs41: set NFS_CL_SESSION_INITING in alloc_session] Signed-off-by: Andy Adamson <andros@netapp.com> [nfs41: move session setup into a function] Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [moved nfs4_proc_create_session declaration here] Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-04-01 13:22:38 +00:00
extern void nfs_mark_client_ready(struct nfs_client *clp, int state);
extern int nfs4_check_client_ready(struct nfs_client *clp);
extern struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
const struct sockaddr *ds_addr,
int ds_addrlen, int ds_proto);
#ifdef CONFIG_PROC_FS
extern int __init nfs_fs_proc_init(void);
extern void nfs_fs_proc_exit(void);
#else
static inline int nfs_fs_proc_init(void)
{
return 0;
}
static inline void nfs_fs_proc_exit(void)
{
}
#endif
/* nfs4namespace.c */
#ifdef CONFIG_NFS_V4
extern struct vfsmount *nfs_do_refmount(struct dentry *dentry);
#else
static inline
struct vfsmount *nfs_do_refmount(struct dentry *dentry)
{
return ERR_PTR(-ENOENT);
}
#endif
/* callback_xdr.c */
extern struct svc_version nfs4_callback_version1;
extern struct svc_version nfs4_callback_version4;
/* pagelist.c */
extern int __init nfs_init_nfspagecache(void);
extern void nfs_destroy_nfspagecache(void);
extern int __init nfs_init_readpagecache(void);
extern void nfs_destroy_readpagecache(void);
extern int __init nfs_init_writepagecache(void);
extern void nfs_destroy_writepagecache(void);
extern int __init nfs_init_directcache(void);
extern void nfs_destroy_directcache(void);
/* nfs2xdr.c */
extern int nfs_stat_to_errno(enum nfs_stat);
extern struct rpc_procinfo nfs_procedures[];
extern int nfs2_decode_dirent(struct xdr_stream *,
struct nfs_entry *, int);
/* nfs3xdr.c */
extern struct rpc_procinfo nfs3_procedures[];
extern int nfs3_decode_dirent(struct xdr_stream *,
struct nfs_entry *, int);
/* nfs4xdr.c */
#ifdef CONFIG_NFS_V4
extern int nfs4_decode_dirent(struct xdr_stream *,
struct nfs_entry *, int);
#endif
#ifdef CONFIG_NFS_V4_1
extern const u32 nfs41_maxread_overhead;
extern const u32 nfs41_maxwrite_overhead;
#endif
/* nfs4proc.c */
git-nfs-build-fixes Fix various problems with nfs4 disabled. And various other things. In file included from fs/nfs/inode.c:50: fs/nfs/internal.h:24: error: static declaration of 'nfs_do_refmount' follows non-static declaration include/linux/nfs_fs.h:320: error: previous declaration of 'nfs_do_refmount' was here fs/nfs/internal.h:65: warning: 'struct nfs4_fs_locations' declared inside parameter list fs/nfs/internal.h:65: warning: its scope is only this definition or declaration, which is probably not what you want fs/nfs/internal.h: In function 'nfs4_path': fs/nfs/internal.h:97: error: 'struct nfs_server' has no member named 'mnt_path' fs/nfs/inode.c: In function 'init_once': fs/nfs/inode.c:1116: error: 'struct nfs_inode' has no member named 'open_states' fs/nfs/inode.c:1116: error: 'struct nfs_inode' has no member named 'delegation' fs/nfs/inode.c:1116: error: 'struct nfs_inode' has no member named 'delegation_state' fs/nfs/inode.c:1116: error: 'struct nfs_inode' has no member named 'rwsem' distcc[26452] ERROR: compile fs/nfs/inode.c on g5/64 failed make[1]: *** [fs/nfs/inode.o] Error 1 make: *** [fs/nfs/inode.o] Error 2 make: *** Waiting for unfinished jobs.... In file included from fs/nfs/nfs3xdr.c:26: fs/nfs/internal.h:24: error: static declaration of 'nfs_do_refmount' follows non-static declaration include/linux/nfs_fs.h:320: error: previous declaration of 'nfs_do_refmount' was here fs/nfs/internal.h:65: warning: 'struct nfs4_fs_locations' declared inside parameter list fs/nfs/internal.h:65: warning: its scope is only this definition or declaration, which is probably not what you want fs/nfs/internal.h: In function 'nfs4_path': fs/nfs/internal.h:97: error: 'struct nfs_server' has no member named 'mnt_path' distcc[26486] ERROR: compile fs/nfs/nfs3xdr.c on g5/64 failed make[1]: *** [fs/nfs/nfs3xdr.o] Error 1 make: *** [fs/nfs/nfs3xdr.o] Error 2 In file included from fs/nfs/nfs3proc.c:24: fs/nfs/internal.h:24: error: static declaration of 'nfs_do_refmount' follows non-static declaration include/linux/nfs_fs.h:320: error: previous declaration of 'nfs_do_refmount' was here fs/nfs/internal.h:65: warning: 'struct nfs4_fs_locations' declared inside parameter list fs/nfs/internal.h:65: warning: its scope is only this definition or declaration, which is probably not what you want fs/nfs/internal.h: In function 'nfs4_path': fs/nfs/internal.h:97: error: 'struct nfs_server' has no member named 'mnt_path' distcc[26469] ERROR: compile fs/nfs/nfs3proc.c on bix/32 failed make[1]: *** [fs/nfs/nfs3proc.o] Error 1 make: *** [fs/nfs/nfs3proc.o] Error 2 **FAILED** Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Andreas Gruenbacher <agruen@suse.de> Cc: Andy Adamson <andros@citi.umich.edu> Cc: Chuck Lever <cel@netapp.com> Cc: David Howells <dhowells@redhat.com> Cc: J. Bruce Fields <bfields@fieldses.org> Cc: Manoj Naik <manoj@almaden.ibm.com> Cc: Marc Eshel <eshel@almaden.ibm.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-06-25 09:41:26 +00:00
#ifdef CONFIG_NFS_V4
extern struct rpc_procinfo nfs4_procedures[];
void nfs_fixup_secinfo_attributes(struct nfs_fattr *, struct nfs_fh *);
git-nfs-build-fixes Fix various problems with nfs4 disabled. And various other things. In file included from fs/nfs/inode.c:50: fs/nfs/internal.h:24: error: static declaration of 'nfs_do_refmount' follows non-static declaration include/linux/nfs_fs.h:320: error: previous declaration of 'nfs_do_refmount' was here fs/nfs/internal.h:65: warning: 'struct nfs4_fs_locations' declared inside parameter list fs/nfs/internal.h:65: warning: its scope is only this definition or declaration, which is probably not what you want fs/nfs/internal.h: In function 'nfs4_path': fs/nfs/internal.h:97: error: 'struct nfs_server' has no member named 'mnt_path' fs/nfs/inode.c: In function 'init_once': fs/nfs/inode.c:1116: error: 'struct nfs_inode' has no member named 'open_states' fs/nfs/inode.c:1116: error: 'struct nfs_inode' has no member named 'delegation' fs/nfs/inode.c:1116: error: 'struct nfs_inode' has no member named 'delegation_state' fs/nfs/inode.c:1116: error: 'struct nfs_inode' has no member named 'rwsem' distcc[26452] ERROR: compile fs/nfs/inode.c on g5/64 failed make[1]: *** [fs/nfs/inode.o] Error 1 make: *** [fs/nfs/inode.o] Error 2 make: *** Waiting for unfinished jobs.... In file included from fs/nfs/nfs3xdr.c:26: fs/nfs/internal.h:24: error: static declaration of 'nfs_do_refmount' follows non-static declaration include/linux/nfs_fs.h:320: error: previous declaration of 'nfs_do_refmount' was here fs/nfs/internal.h:65: warning: 'struct nfs4_fs_locations' declared inside parameter list fs/nfs/internal.h:65: warning: its scope is only this definition or declaration, which is probably not what you want fs/nfs/internal.h: In function 'nfs4_path': fs/nfs/internal.h:97: error: 'struct nfs_server' has no member named 'mnt_path' distcc[26486] ERROR: compile fs/nfs/nfs3xdr.c on g5/64 failed make[1]: *** [fs/nfs/nfs3xdr.o] Error 1 make: *** [fs/nfs/nfs3xdr.o] Error 2 In file included from fs/nfs/nfs3proc.c:24: fs/nfs/internal.h:24: error: static declaration of 'nfs_do_refmount' follows non-static declaration include/linux/nfs_fs.h:320: error: previous declaration of 'nfs_do_refmount' was here fs/nfs/internal.h:65: warning: 'struct nfs4_fs_locations' declared inside parameter list fs/nfs/internal.h:65: warning: its scope is only this definition or declaration, which is probably not what you want fs/nfs/internal.h: In function 'nfs4_path': fs/nfs/internal.h:97: error: 'struct nfs_server' has no member named 'mnt_path' distcc[26469] ERROR: compile fs/nfs/nfs3proc.c on bix/32 failed make[1]: *** [fs/nfs/nfs3proc.o] Error 1 make: *** [fs/nfs/nfs3proc.o] Error 2 **FAILED** Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Andreas Gruenbacher <agruen@suse.de> Cc: Andy Adamson <andros@citi.umich.edu> Cc: Chuck Lever <cel@netapp.com> Cc: David Howells <dhowells@redhat.com> Cc: J. Bruce Fields <bfields@fieldses.org> Cc: Manoj Naik <manoj@almaden.ibm.com> Cc: Marc Eshel <eshel@almaden.ibm.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-06-25 09:41:26 +00:00
#endif
extern int nfs4_init_ds_session(struct nfs_client *clp);
/* proc.c */
void nfs_close_context(struct nfs_open_context *ctx, int is_sync);
extern int nfs_init_client(struct nfs_client *clp,
const struct rpc_timeout *timeparms,
const char *ip_addr, rpc_authflavor_t authflavour,
int noresvport);
/* dir.c */
extern int nfs_access_cache_shrinker(struct shrinker *shrink,
struct shrink_control *sc);
/* inode.c */
extern struct workqueue_struct *nfsiod_workqueue;
extern struct inode *nfs_alloc_inode(struct super_block *sb);
extern void nfs_destroy_inode(struct inode *);
extern int nfs_write_inode(struct inode *, struct writeback_control *);
extern void nfs_evict_inode(struct inode *);
#ifdef CONFIG_NFS_V4
extern void nfs4_evict_inode(struct inode *);
#endif
void nfs_zap_acl_cache(struct inode *inode);
2009-03-11 18:10:30 +00:00
extern int nfs_wait_bit_killable(void *word);
/* super.c */
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 00:06:13 +00:00
extern struct file_system_type nfs_xdev_fs_type;
#ifdef CONFIG_NFS_V4
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 00:06:13 +00:00
extern struct file_system_type nfs4_xdev_fs_type;
extern struct file_system_type nfs4_referral_fs_type;
#endif
extern struct rpc_stat nfs_rpcstat;
extern int __init register_nfs_fs(void);
extern void __exit unregister_nfs_fs(void);
extern void nfs_sb_active(struct super_block *sb);
extern void nfs_sb_deactive(struct super_block *sb);
/* namespace.c */
extern char *nfs_path(char **p, struct dentry *dentry,
char *buffer, ssize_t buflen);
extern struct vfsmount *nfs_d_automount(struct path *path);
#ifdef CONFIG_NFS_V4
rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *);
#endif
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 00:06:13 +00:00
/* getroot.c */
extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *,
const char *);
#ifdef CONFIG_NFS_V4
extern struct dentry *nfs4_get_root(struct super_block *, struct nfs_fh *,
const char *);
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 00:06:13 +00:00
extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh);
#endif
struct nfs_pageio_descriptor;
/* read.c */
extern int nfs_initiate_read(struct nfs_read_data *data, struct rpc_clnt *clnt,
const struct rpc_call_ops *call_ops);
extern void nfs_read_prepare(struct rpc_task *task, void *calldata);
extern int nfs_generic_pagein(struct nfs_pageio_descriptor *desc,
struct list_head *head);
extern void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio,
struct inode *inode);
extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
extern void nfs_readdata_release(struct nfs_read_data *rdata);
/* write.c */
extern int nfs_scan_commit_list(struct list_head *src, struct list_head *dst,
int max);
extern int nfs_generic_flush(struct nfs_pageio_descriptor *desc,
struct list_head *head);
extern void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio,
struct inode *inode, int ioflags);
extern void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio);
extern void nfs_writedata_release(struct nfs_write_data *wdata);
extern void nfs_commit_free(struct nfs_write_data *p);
extern int nfs_initiate_write(struct nfs_write_data *data,
struct rpc_clnt *clnt,
const struct rpc_call_ops *call_ops,
int how);
extern void nfs_write_prepare(struct rpc_task *task, void *calldata);
extern int nfs_initiate_commit(struct nfs_write_data *data,
struct rpc_clnt *clnt,
const struct rpc_call_ops *call_ops,
int how);
extern void nfs_init_commit(struct nfs_write_data *data,
struct list_head *head,
struct pnfs_layout_segment *lseg);
void nfs_retry_commit(struct list_head *page_list,
struct pnfs_layout_segment *lseg);
void nfs_commit_clear_lock(struct nfs_inode *nfsi);
void nfs_commitdata_release(void *data);
void nfs_commit_release_pages(struct nfs_write_data *data);
#ifdef CONFIG_MIGRATION
extern int nfs_migrate_page(struct address_space *,
struct page *, struct page *, enum migrate_mode);
#else
#define nfs_migrate_page NULL
#endif
nfs41: introduce nfs4_call_sync Use nfs4_call_sync rather than rpc_call_sync to provide for a nfs41 sessions-enabled interface for sessions manipulation. The nfs41 rpc logic uses the rpc_call_prepare method to recover and create the session, as well as selecting a free slot id and the rpc_call_done to free the slot and update slot table related metadata. In the coming patches we'll add rpc prepare and done routines for setting up the sequence op and processing the sequence result. Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfs41: nfs4_call_sync] As per 11-14-08 review. Squash into "nfs41: introduce nfs4_call_sync" and "nfs41: nfs4_setup_sequence" Define two functions one for v4 and one for v41 add a pointer to struct nfs4_client to the correct one. Signed-off-by: Andy Adamson <andros@netapp.com> [added BUG() in _nfs4_call_sync_session if !CONFIG_NFS_V4_1] Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfs41: check for session not minorversion] Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [group minorversion specific stuff together] Signed-off-by: Alexandros Batsakis <Alexandros.Batsakis@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Andy Adamson <andros@netapp.com> [nfs41: fixup nfs4_clear_client_minor_version] [introduce nfs4_init_client_minor_version() in this patch] Signed-off-by: Benny Halevy <bhalevy@panasas.com> [cleaned-up patch: got rid of nfs_call_sync_t, dprintks, cosmetics, extra server defs] Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-04-01 13:22:03 +00:00
/* nfs4proc.c */
extern void __nfs4_read_done_cb(struct nfs_read_data *);
extern void nfs4_reset_read(struct rpc_task *task, struct nfs_read_data *data);
extern int nfs4_init_client(struct nfs_client *clp,
const struct rpc_timeout *timeparms,
const char *ip_addr,
rpc_authflavor_t authflavour,
int noresvport);
extern void nfs4_reset_write(struct rpc_task *task, struct nfs_write_data *data);
extern int _nfs4_call_sync(struct rpc_clnt *clnt,
struct nfs_server *server,
nfs41: introduce nfs4_call_sync Use nfs4_call_sync rather than rpc_call_sync to provide for a nfs41 sessions-enabled interface for sessions manipulation. The nfs41 rpc logic uses the rpc_call_prepare method to recover and create the session, as well as selecting a free slot id and the rpc_call_done to free the slot and update slot table related metadata. In the coming patches we'll add rpc prepare and done routines for setting up the sequence op and processing the sequence result. Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfs41: nfs4_call_sync] As per 11-14-08 review. Squash into "nfs41: introduce nfs4_call_sync" and "nfs41: nfs4_setup_sequence" Define two functions one for v4 and one for v41 add a pointer to struct nfs4_client to the correct one. Signed-off-by: Andy Adamson <andros@netapp.com> [added BUG() in _nfs4_call_sync_session if !CONFIG_NFS_V4_1] Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfs41: check for session not minorversion] Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [group minorversion specific stuff together] Signed-off-by: Alexandros Batsakis <Alexandros.Batsakis@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Andy Adamson <andros@netapp.com> [nfs41: fixup nfs4_clear_client_minor_version] [introduce nfs4_init_client_minor_version() in this patch] Signed-off-by: Benny Halevy <bhalevy@panasas.com> [cleaned-up patch: got rid of nfs_call_sync_t, dprintks, cosmetics, extra server defs] Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-04-01 13:22:03 +00:00
struct rpc_message *msg,
struct nfs4_sequence_args *args,
struct nfs4_sequence_res *res,
int cache_reply);
extern int _nfs4_call_sync_session(struct rpc_clnt *clnt,
struct nfs_server *server,
nfs41: introduce nfs4_call_sync Use nfs4_call_sync rather than rpc_call_sync to provide for a nfs41 sessions-enabled interface for sessions manipulation. The nfs41 rpc logic uses the rpc_call_prepare method to recover and create the session, as well as selecting a free slot id and the rpc_call_done to free the slot and update slot table related metadata. In the coming patches we'll add rpc prepare and done routines for setting up the sequence op and processing the sequence result. Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfs41: nfs4_call_sync] As per 11-14-08 review. Squash into "nfs41: introduce nfs4_call_sync" and "nfs41: nfs4_setup_sequence" Define two functions one for v4 and one for v41 add a pointer to struct nfs4_client to the correct one. Signed-off-by: Andy Adamson <andros@netapp.com> [added BUG() in _nfs4_call_sync_session if !CONFIG_NFS_V4_1] Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfs41: check for session not minorversion] Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [group minorversion specific stuff together] Signed-off-by: Alexandros Batsakis <Alexandros.Batsakis@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Andy Adamson <andros@netapp.com> [nfs41: fixup nfs4_clear_client_minor_version] [introduce nfs4_init_client_minor_version() in this patch] Signed-off-by: Benny Halevy <bhalevy@panasas.com> [cleaned-up patch: got rid of nfs_call_sync_t, dprintks, cosmetics, extra server defs] Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-04-01 13:22:03 +00:00
struct rpc_message *msg,
struct nfs4_sequence_args *args,
struct nfs4_sequence_res *res,
int cache_reply);
/*
* Determine the device name as a string
*/
static inline char *nfs_devname(struct dentry *dentry,
NFS: Share NFS superblocks per-protocol per-server per-FSID The attached patch makes NFS share superblocks between mounts from the same server and FSID over the same protocol. It does this by creating each superblock with a false root and returning the real root dentry in the vfsmount presented by get_sb(). The root dentry set starts off as an anonymous dentry if we don't already have the dentry for its inode, otherwise it simply returns the dentry we already have. We may thus end up with several trees of dentries in the superblock, and if at some later point one of anonymous tree roots is discovered by normal filesystem activity to be located in another tree within the superblock, the anonymous root is named and materialises attached to the second tree at the appropriate point. Why do it this way? Why not pass an extra argument to the mount() syscall to indicate the subpath and then pathwalk from the server root to the desired directory? You can't guarantee this will work for two reasons: (1) The root and intervening nodes may not be accessible to the client. With NFS2 and NFS3, for instance, mountd is called on the server to get the filehandle for the tip of a path. mountd won't give us handles for anything we don't have permission to access, and so we can't set up NFS inodes for such nodes, and so can't easily set up dentries (we'd have to have ghost inodes or something). With this patch we don't actually create dentries until we get handles from the server that we can use to set up their inodes, and we don't actually bind them into the tree until we know for sure where they go. (2) Inaccessible symbolic links. If we're asked to mount two exports from the server, eg: mount warthog:/warthog/aaa/xxx /mmm mount warthog:/warthog/bbb/yyy /nnn We may not be able to access anything nearer the root than xxx and yyy, but we may find out later that /mmm/www/yyy, say, is actually the same directory as the one mounted on /nnn. What we might then find out, for example, is that /warthog/bbb was actually a symbolic link to /warthog/aaa/xxx/www, but we can't actually determine that by talking to the server until /warthog is made available by NFS. This would lead to having constructed an errneous dentry tree which we can't easily fix. We can end up with a dentry marked as a directory when it should actually be a symlink, or we could end up with an apparently hardlinked directory. With this patch we need not make assumptions about the type of a dentry for which we can't retrieve information, nor need we assume we know its place in the grand scheme of things until we actually see that place. This patch reduces the possibility of aliasing in the inode and page caches for inodes that may be accessed by more than one NFS export. It also reduces the number of superblocks required for NFS where there are many NFS exports being used from a server (home directory server + autofs for example). This in turn makes it simpler to do local caching of network filesystems, as it can then be guaranteed that there won't be links from multiple inodes in separate superblocks to the same cache file. Obviously, cache aliasing between different levels of NFS protocol could still be a problem, but at least that gives us another key to use when indexing the cache. This patch makes the following changes: (1) The server record construction/destruction has been abstracted out into its own set of functions to make things easier to get right. These have been moved into fs/nfs/client.c. All the code in fs/nfs/client.c has to do with the management of connections to servers, and doesn't touch superblocks in any way; the remaining code in fs/nfs/super.c has to do with VFS superblock management. (2) The sequence of events undertaken by NFS mount is now reordered: (a) A volume representation (struct nfs_server) is allocated. (b) A server representation (struct nfs_client) is acquired. This may be allocated or shared, and is keyed on server address, port and NFS version. (c) If allocated, the client representation is initialised. The state member variable of nfs_client is used to prevent a race during initialisation from two mounts. (d) For NFS4 a simple pathwalk is performed, walking from FH to FH to find the root filehandle for the mount (fs/nfs/getroot.c). For NFS2/3 we are given the root FH in advance. (e) The volume FSID is probed for on the root FH. (f) The volume representation is initialised from the FSINFO record retrieved on the root FH. (g) sget() is called to acquire a superblock. This may be allocated or shared, keyed on client pointer and FSID. (h) If allocated, the superblock is initialised. (i) If the superblock is shared, then the new nfs_server record is discarded. (j) The root dentry for this mount is looked up from the root FH. (k) The root dentry for this mount is assigned to the vfsmount. (3) nfs_readdir_lookup() creates dentries for each of the entries readdir() returns; this function now attaches disconnected trees from alternate roots that happen to be discovered attached to a directory being read (in the same way nfs_lookup() is made to do for lookup ops). The new d_materialise_unique() function is now used to do this, thus permitting the whole thing to be done under one set of locks, and thus avoiding any race between mount and lookup operations on the same directory. (4) The client management code uses a new debug facility: NFSDBG_CLIENT which is set by echoing 1024 to /proc/net/sunrpc/nfs_debug. (5) Clone mounts are now called xdev mounts. (6) Use the dentry passed to the statfs() op as the handle for retrieving fs statistics rather than the root dentry of the superblock (which is now a dummy). Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2006-08-23 00:06:13 +00:00
char *buffer, ssize_t buflen)
{
char *dummy;
return nfs_path(&dummy, dentry, buffer, buflen);
}
/*
* Determine the actual block size (and log2 thereof)
*/
static inline
unsigned long nfs_block_bits(unsigned long bsize, unsigned char *nrbitsp)
{
/* make sure blocksize is a power of two */
if ((bsize & (bsize - 1)) || nrbitsp) {
unsigned char nrbits;
for (nrbits = 31; nrbits && !(bsize & (1 << nrbits)); nrbits--)
;
bsize = 1 << nrbits;
if (nrbitsp)
*nrbitsp = nrbits;
}
return bsize;
}
/*
* Calculate the number of 512byte blocks used.
*/
static inline blkcnt_t nfs_calc_block_size(u64 tsize)
{
blkcnt_t used = (tsize + 511) >> 9;
return (used > ULONG_MAX) ? ULONG_MAX : used;
}
/*
* Compute and set NFS server blocksize
*/
static inline
unsigned long nfs_block_size(unsigned long bsize, unsigned char *nrbitsp)
{
if (bsize < NFS_MIN_FILE_IO_SIZE)
bsize = NFS_DEF_FILE_IO_SIZE;
else if (bsize >= NFS_MAX_FILE_IO_SIZE)
bsize = NFS_MAX_FILE_IO_SIZE;
return nfs_block_bits(bsize, nrbitsp);
}
/*
* Determine the maximum file size for a superblock
*/
static inline
void nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize)
{
sb->s_maxbytes = (loff_t)maxfilesize;
if (sb->s_maxbytes > MAX_LFS_FILESIZE || sb->s_maxbytes <= 0)
sb->s_maxbytes = MAX_LFS_FILESIZE;
}
/*
* Determine the number of bytes of data the page contains
*/
static inline
unsigned int nfs_page_length(struct page *page)
{
loff_t i_size = i_size_read(page->mapping->host);
if (i_size > 0) {
pgoff_t end_index = (i_size - 1) >> PAGE_CACHE_SHIFT;
if (page->index < end_index)
return PAGE_CACHE_SIZE;
if (page->index == end_index)
return ((i_size - 1) & ~PAGE_CACHE_MASK) + 1;
}
return 0;
}
/*
* Convert a umode to a dirent->d_type
*/
static inline
unsigned char nfs_umode_to_dtype(umode_t mode)
{
return (mode >> 12) & 15;
}
/*
* Determine the number of pages in an array of length 'len' and
* with a base offset of 'base'
*/
static inline
unsigned int nfs_page_array_len(unsigned int base, size_t len)
{
return ((unsigned long)len + (unsigned long)base +
PAGE_SIZE - 1) >> PAGE_SHIFT;
}