OpenCloudOS-Kernel/include/net/9p/client.h

273 lines
9.0 KiB
C
Raw Normal View History

/*
* include/net/9p/client.h
*
* 9P Client Definitions
*
* Copyright (C) 2008 by Eric Van Hensbergen <ericvh@gmail.com>
* Copyright (C) 2007 by Latchesar Ionkov <lucho@ionkov.net>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2
* as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to:
* Free Software Foundation
* 51 Franklin Street, Fifth Floor
* Boston, MA 02111-1301 USA
*
*/
#ifndef NET_9P_CLIENT_H
#define NET_9P_CLIENT_H
#include <linux/utsname.h>
/* Number of requests per row */
#define P9_ROW_MAXTAG 255
/** enum p9_proto_versions - 9P protocol versions
* @p9_proto_legacy: 9P Legacy mode, pre-9P2000.u
* @p9_proto_2000u: 9P2000.u extension
* @p9_proto_2000L: 9P2000.L extension
*/
enum p9_proto_versions{
p9_proto_legacy,
p9_proto_2000u,
p9_proto_2000L,
};
/**
* enum p9_trans_status - different states of underlying transports
* @Connected: transport is connected and healthy
* @Disconnected: transport has been disconnected
* @Hung: transport is connected by wedged
*
* This enumeration details the various states a transport
* instatiation can be in.
*/
enum p9_trans_status {
Connected,
BeginDisconnect,
Disconnected,
Hung,
};
/**
* enum p9_req_status_t - status of a request
* @REQ_STATUS_IDLE: request slot unused
* @REQ_STATUS_ALLOC: request has been allocated but not sent
* @REQ_STATUS_UNSENT: request waiting to be sent
* @REQ_STATUS_SENT: request sent to server
* @REQ_STATUS_RCVD: response received from server
* @REQ_STATUS_FLSHD: request has been flushed
* @REQ_STATUS_ERROR: request encountered an error on the client side
*
* The @REQ_STATUS_IDLE state is used to mark a request slot as unused
* but use is actually tracked by the idpool structure which handles tag
* id allocation.
*
*/
enum p9_req_status_t {
REQ_STATUS_IDLE,
REQ_STATUS_ALLOC,
REQ_STATUS_UNSENT,
REQ_STATUS_SENT,
REQ_STATUS_RCVD,
REQ_STATUS_FLSHD,
REQ_STATUS_ERROR,
};
/**
* struct p9_req_t - request slots
* @status: status of this request slot
* @t_err: transport error
* @flush_tag: tag of request being flushed (for flush requests)
* @wq: wait_queue for the client to block on for this request
* @tc: the request fcall structure
* @rc: the response fcall structure
* @aux: transport specific data (provided for trans_fd migration)
* @req_list: link for higher level objects to chain requests
*
* Transport use an array to track outstanding requests
* instead of a list. While this may incurr overhead during initial
* allocation or expansion, it makes request lookup much easier as the
* tag id is a index into an array. (We use tag+1 so that we can accommodate
* the -1 tag for the T_VERSION request).
* This also has the nice effect of only having to allocate wait_queues
* once, instead of constantly allocating and freeing them. Its possible
* other resources could benefit from this scheme as well.
*
*/
struct p9_req_t {
int status;
int t_err;
wait_queue_head_t *wq;
struct p9_fcall *tc;
struct p9_fcall *rc;
void *aux;
struct list_head req_list;
};
/**
* struct p9_client - per client instance state
* @lock: protect @fidlist
* @msize: maximum data size negotiated by protocol
* @dotu: extension flags negotiated by protocol
* @proto_version: 9P protocol version to use
* @trans_mod: module API instantiated with this client
* @trans: tranport instance state and API
* @fidpool: fid handle accounting for session
* @fidlist: List of active fid handles
* @tagpool - transaction id accounting for session
* @reqs - 2D array of requests
* @max_tag - current maximum tag id allocated
* @name - node name used as client id
*
* The client structure is used to keep track of various per-client
* state that has been instantiated.
* In order to minimize per-transaction overhead we use a
* simple array to lookup requests instead of a hash table
* or linked list. In order to support larger number of
* transactions, we make this a 2D array, allocating new rows
* when we need to grow the total number of the transactions.
*
* Each row is 256 requests and we'll support up to 256 rows for
* a total of 64k concurrent requests per session.
*
* Bugs: duplicated data and potentially unnecessary elements.
*/
struct p9_client {
spinlock_t lock; /* protect client structure */
unsigned int msize;
unsigned char proto_version;
struct p9_trans_module *trans_mod;
enum p9_trans_status status;
void *trans;
struct p9_idpool *fidpool;
struct list_head fidlist;
struct p9_idpool *tagpool;
struct p9_req_t *reqs[P9_ROW_MAXTAG];
int max_tag;
char name[__NEW_UTS_LEN + 1];
};
/**
* struct p9_fid - file system entity handle
* @clnt: back pointer to instantiating &p9_client
* @fid: numeric identifier for this handle
* @mode: current mode of this fid (enum?)
* @qid: the &p9_qid server identifier this handle points to
* @iounit: the server reported maximum transaction size for this file
* @uid: the numeric uid of the local user who owns this handle
* @rdir: readdir accounting structure (allocated on demand)
* @flist: per-client-instance fid tracking
* @dlist: per-dentry fid tracking
*
* TODO: This needs lots of explanation.
*/
struct p9_fid {
struct p9_client *clnt;
u32 fid;
int mode;
struct p9_qid qid;
u32 iounit;
kuid_t uid;
void *rdir;
struct list_head flist;
struct hlist_node dlist; /* list of all fids attached to a dentry */
};
9p: readdir implementation for 9p2000.L This patch implements the kernel part of readdir() implementation for 9p2000.L Change from V3: Instead of inode, server now sends qids for each dirent SYNOPSIS size[4] Treaddir tag[2] fid[4] offset[8] count[4] size[4] Rreaddir tag[2] count[4] data[count] DESCRIPTION The readdir request asks the server to read the directory specified by 'fid' at an offset specified by 'offset' and return as many dirent structures as possible that fit into count bytes. Each dirent structure is laid out as follows. qid.type[1] the type of the file (directory, etc.), represented as a bit vector corresponding to the high 8 bits of the file's mode word. qid.vers[4] version number for given path qid.path[8] the file server's unique identification for the file offset[8] offset into the next dirent. type[1] type of this directory entry. name[256] name of this directory entry. This patch adds v9fs_dir_readdir_dotl() as the readdir() call for 9p2000.L. This function sends P9_TREADDIR command to the server. In response the server sends a buffer filled with dirent structures. This is different from the existing v9fs_dir_readdir() call which receives stat structures from the server. This results in significant speedup of readdir() on large directories. For example, doing 'ls >/dev/null' on a directory with 10000 files on my laptop takes 1.088 seconds with the existing code, but only takes 0.339 seconds with the new readdir. Signed-off-by: Sripathi Kodi <sripathik@in.ibm.com> Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-06-04 21:41:26 +08:00
/**
* struct p9_dirent - directory entry structure
* @qid: The p9 server qid for this dirent
* @d_off: offset to the next dirent
* @d_type: type of file
* @d_name: file name
*/
struct p9_dirent {
struct p9_qid qid;
u64 d_off;
unsigned char d_type;
char d_name[256];
};
int p9_client_statfs(struct p9_fid *fid, struct p9_rstatfs *sb);
int p9_client_rename(struct p9_fid *fid, struct p9_fid *newdirfid,
const char *name);
int p9_client_renameat(struct p9_fid *olddirfid, const char *old_name,
struct p9_fid *newdirfid, const char *new_name);
struct p9_client *p9_client_create(const char *dev_name, char *options);
void p9_client_destroy(struct p9_client *clnt);
void p9_client_disconnect(struct p9_client *clnt);
void p9_client_begin_disconnect(struct p9_client *clnt);
struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid,
char *uname, kuid_t n_uname, char *aname);
struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname,
char **wnames, int clone);
int p9_client_open(struct p9_fid *fid, int mode);
int p9_client_fcreate(struct p9_fid *fid, char *name, u32 perm, int mode,
char *extension);
int p9_client_link(struct p9_fid *fid, struct p9_fid *oldfid, char *newname);
int p9_client_symlink(struct p9_fid *fid, char *name, char *symname, kgid_t gid,
struct p9_qid *qid);
int p9_client_create_dotl(struct p9_fid *ofid, char *name, u32 flags, u32 mode,
kgid_t gid, struct p9_qid *qid);
int p9_client_clunk(struct p9_fid *fid);
int p9_client_fsync(struct p9_fid *fid, int datasync);
int p9_client_remove(struct p9_fid *fid);
int p9_client_unlinkat(struct p9_fid *dfid, const char *name, int flags);
int p9_client_read(struct p9_fid *fid, char *data, char __user *udata,
u64 offset, u32 count);
int p9_client_write(struct p9_fid *fid, char *data, const char __user *udata,
u64 offset, u32 count);
9p: readdir implementation for 9p2000.L This patch implements the kernel part of readdir() implementation for 9p2000.L Change from V3: Instead of inode, server now sends qids for each dirent SYNOPSIS size[4] Treaddir tag[2] fid[4] offset[8] count[4] size[4] Rreaddir tag[2] count[4] data[count] DESCRIPTION The readdir request asks the server to read the directory specified by 'fid' at an offset specified by 'offset' and return as many dirent structures as possible that fit into count bytes. Each dirent structure is laid out as follows. qid.type[1] the type of the file (directory, etc.), represented as a bit vector corresponding to the high 8 bits of the file's mode word. qid.vers[4] version number for given path qid.path[8] the file server's unique identification for the file offset[8] offset into the next dirent. type[1] type of this directory entry. name[256] name of this directory entry. This patch adds v9fs_dir_readdir_dotl() as the readdir() call for 9p2000.L. This function sends P9_TREADDIR command to the server. In response the server sends a buffer filled with dirent structures. This is different from the existing v9fs_dir_readdir() call which receives stat structures from the server. This results in significant speedup of readdir() on large directories. For example, doing 'ls >/dev/null' on a directory with 10000 files on my laptop takes 1.088 seconds with the existing code, but only takes 0.339 seconds with the new readdir. Signed-off-by: Sripathi Kodi <sripathik@in.ibm.com> Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-06-04 21:41:26 +08:00
int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset);
int p9dirent_read(struct p9_client *clnt, char *buf, int len,
struct p9_dirent *dirent);
struct p9_wstat *p9_client_stat(struct p9_fid *fid);
int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst);
9p: Implement client side of setattr for 9P2000.L protocol. SYNOPSIS size[4] Tsetattr tag[2] attr[n] size[4] Rsetattr tag[2] DESCRIPTION The setattr command changes some of the file status information. attr resembles the iattr structure used in Linux kernel. It specifies which status parameter is to be changed and to what value. It is laid out as follows: valid[4] specifies which status information is to be changed. Possible values are: ATTR_MODE (1 << 0) ATTR_UID (1 << 1) ATTR_GID (1 << 2) ATTR_SIZE (1 << 3) ATTR_ATIME (1 << 4) ATTR_MTIME (1 << 5) ATTR_ATIME_SET (1 << 7) ATTR_MTIME_SET (1 << 8) The last two bits represent whether the time information is being sent by the client's user space. In the absense of these bits the server always uses server's time. mode[4] File permission bits uid[4] Owner id of file gid[4] Group id of the file size[8] File size atime_sec[8] Time of last file access, seconds atime_nsec[8] Time of last file access, nanoseconds mtime_sec[8] Time of last file modification, seconds mtime_nsec[8] Time of last file modification, nanoseconds Explanation of the patches: -------------------------- *) The kernel just copies relevent contents of iattr structure to p9_iattr_dotl structure and passes it down to the client. The only check it has is calling inode_change_ok() *) The p9_iattr_dotl structure does not have ctime and ia_file parameters because I don't think these are needed in our case. The client user space can request updating just ctime by calling chown(fd, -1, -1). This is handled on server side without a need for putting ctime on the wire. *) The server currently supports changing mode, time, ownership and size of the file. *) 9P RFC says "Either all the changes in wstat request happen, or none of them does: if the request succeeds, all changes were made; if it fails, none were." I have not done anything to implement this specifically because I don't see a reason. Signed-off-by: Sripathi Kodi <sripathik@in.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-06-18 14:20:10 +08:00
int p9_client_setattr(struct p9_fid *fid, struct p9_iattr_dotl *attr);
9p: getattr client implementation for 9P2000.L protocol. SYNOPSIS size[4] Tgetattr tag[2] fid[4] request_mask[8] size[4] Rgetattr tag[2] lstat[n] DESCRIPTION The getattr transaction inquires about the file identified by fid. request_mask is a bit mask that specifies which fields of the stat structure is the client interested in. The reply will contain a machine-independent directory entry, laid out as follows: st_result_mask[8] Bit mask that indicates which fields in the stat structure have been populated by the server qid.type[1] the type of the file (directory, etc.), represented as a bit vector corresponding to the high 8 bits of the file's mode word. qid.vers[4] version number for given path qid.path[8] the file server's unique identification for the file st_mode[4] Permission and flags st_uid[4] User id of owner st_gid[4] Group ID of owner st_nlink[8] Number of hard links st_rdev[8] Device ID (if special file) st_size[8] Size, in bytes st_blksize[8] Block size for file system IO st_blocks[8] Number of file system blocks allocated st_atime_sec[8] Time of last access, seconds st_atime_nsec[8] Time of last access, nanoseconds st_mtime_sec[8] Time of last modification, seconds st_mtime_nsec[8] Time of last modification, nanoseconds st_ctime_sec[8] Time of last status change, seconds st_ctime_nsec[8] Time of last status change, nanoseconds st_btime_sec[8] Time of creation (birth) of file, seconds st_btime_nsec[8] Time of creation (birth) of file, nanoseconds st_gen[8] Inode generation st_data_version[8] Data version number request_mask and result_mask bit masks contain the following bits #define P9_STATS_MODE 0x00000001ULL #define P9_STATS_NLINK 0x00000002ULL #define P9_STATS_UID 0x00000004ULL #define P9_STATS_GID 0x00000008ULL #define P9_STATS_RDEV 0x00000010ULL #define P9_STATS_ATIME 0x00000020ULL #define P9_STATS_MTIME 0x00000040ULL #define P9_STATS_CTIME 0x00000080ULL #define P9_STATS_INO 0x00000100ULL #define P9_STATS_SIZE 0x00000200ULL #define P9_STATS_BLOCKS 0x00000400ULL #define P9_STATS_BTIME 0x00000800ULL #define P9_STATS_GEN 0x00001000ULL #define P9_STATS_DATA_VERSION 0x00002000ULL #define P9_STATS_BASIC 0x000007ffULL #define P9_STATS_ALL 0x00003fffULL This patch implements the client side of getattr implementation for 9P2000.L. It introduces a new structure p9_stat_dotl for getting Linux stat information along with QID. The data layout is similar to stat structure in Linux user space with the following major differences: inode (st_ino) is not part of data. Instead qid is. device (st_dev) is not part of data because this doesn't make sense on the client. All time variables are 64 bit wide on the wire. The kernel seems to use 32 bit variables for these variables. However, some of the architectures have used 64 bit variables and glibc exposes 64 bit variables to user space on some architectures. Hence to be on the safer side we have made these 64 bit in the protocol. Refer to the comments in include/asm-generic/stat.h There are some additional fields: st_btime_sec, st_btime_nsec, st_gen, st_data_version apart from the bitmask, st_result_mask. The bit mask is filled by the server to indicate which stat fields have been populated by the server. Currently there is no clean way for the server to obtain these additional fields, so it sends back just the basic fields. Signed-off-by: Sripathi Kodi <sripathik@in.ibm.com> Signed-off-by: Eric Van Hensbegren <ericvh@gmail.com>
2010-07-12 22:37:23 +08:00
struct p9_stat_dotl *p9_client_getattr_dotl(struct p9_fid *fid,
u64 request_mask);
int p9_client_mknod_dotl(struct p9_fid *oldfid, char *name, int mode,
dev_t rdev, kgid_t gid, struct p9_qid *);
int p9_client_mkdir_dotl(struct p9_fid *fid, char *name, int mode,
kgid_t gid, struct p9_qid *);
9p: Implement TLOCK Synopsis size[4] TLock tag[2] fid[4] flock[n] size[4] RLock tag[2] status[1] Description Tlock is used to acquire/release byte range posix locks on a file identified by given fid. The reply contains status of the lock request flock structure: type[1] - Type of lock: F_RDLCK, F_WRLCK, F_UNLCK flags[4] - Flags could be either of P9_LOCK_FLAGS_BLOCK - Blocked lock request, if there is a conflicting lock exists, wait for that lock to be released. P9_LOCK_FLAGS_RECLAIM - Reclaim lock request, used when client is trying to reclaim a lock after a server restrart (due to crash) start[8] - Starting offset for lock length[8] - Number of bytes to lock If length is 0, lock all bytes starting at the location 'start' through to the end of file pid[4] - PID of the process that wants to take lock client_id[4] - Unique client id status[1] - Status of the lock request, can be P9_LOCK_SUCCESS(0), P9_LOCK_BLOCKED(1), P9_LOCK_ERROR(2) or P9_LOCK_GRACE(3) P9_LOCK_SUCCESS - Request was successful P9_LOCK_BLOCKED - A conflicting lock is held by another process P9_LOCK_ERROR - Error while processing the lock request P9_LOCK_GRACE - Server is in grace period, it can't accept new lock requests in this period (except locks with P9_LOCK_FLAGS_RECLAIM flag set) Signed-off-by: M. Mohan Kumar <mohan@in.ibm.com> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Venkateswararao Jujjuri <jvrao@linux.vnet.ibm.com> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2010-09-27 14:04:24 +08:00
int p9_client_lock_dotl(struct p9_fid *fid, struct p9_flock *flock, u8 *status);
int p9_client_getlock_dotl(struct p9_fid *fid, struct p9_getlock *fl);
struct p9_req_t *p9_tag_lookup(struct p9_client *, u16);
void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status);
int p9_parse_header(struct p9_fcall *, int32_t *, int8_t *, int16_t *, int);
int p9stat_read(struct p9_client *, char *, int, struct p9_wstat *);
void p9stat_free(struct p9_wstat *);
int p9_is_proto_dotu(struct p9_client *clnt);
int p9_is_proto_dotl(struct p9_client *clnt);
struct p9_fid *p9_client_xattrwalk(struct p9_fid *, const char *, u64 *);
int p9_client_xattrcreate(struct p9_fid *, const char *, u64, int);
int p9_client_readlink(struct p9_fid *fid, char **target);
#endif /* NET_9P_CLIENT_H */