diff options
Diffstat (limited to 'Documentation/filesystems/pohmelfs/network_protocol.txt')
-rw-r--r-- | Documentation/filesystems/pohmelfs/network_protocol.txt | 227 |
1 files changed, 227 insertions, 0 deletions
diff --git a/Documentation/filesystems/pohmelfs/network_protocol.txt b/Documentation/filesystems/pohmelfs/network_protocol.txt new file mode 100644 index 00000000000..40ea6c295af --- /dev/null +++ b/Documentation/filesystems/pohmelfs/network_protocol.txt | |||
@@ -0,0 +1,227 @@ | |||
1 | POHMELFS network protocol. | ||
2 | |||
3 | Basic structure used in network communication is following command: | ||
4 | |||
5 | struct netfs_cmd | ||
6 | { | ||
7 | __u16 cmd; /* Command number */ | ||
8 | __u16 csize; /* Attached crypto information size */ | ||
9 | __u16 cpad; /* Attached padding size */ | ||
10 | __u16 ext; /* External flags */ | ||
11 | __u32 size; /* Size of the attached data */ | ||
12 | __u32 trans; /* Transaction id */ | ||
13 | __u64 id; /* Object ID to operate on. Used for feedback.*/ | ||
14 | __u64 start; /* Start of the object. */ | ||
15 | __u64 iv; /* IV sequence */ | ||
16 | __u8 data[0]; | ||
17 | }; | ||
18 | |||
19 | Commands can be embedded into transaction command (which in turn has own command), | ||
20 | so one can extend protocol as needed without breaking backward compatibility as long | ||
21 | as old commands are supported. All string lengths include tail 0 byte. | ||
22 | |||
23 | All commans are transfered over the network in big-endian. CPU endianess is used at the end peers. | ||
24 | |||
25 | @cmd - command number, which specifies command to be processed. Following | ||
26 | commands are used currently: | ||
27 | |||
28 | NETFS_READDIR = 1, /* Read directory for given inode number */ | ||
29 | NETFS_READ_PAGE, /* Read data page from the server */ | ||
30 | NETFS_WRITE_PAGE, /* Write data page to the server */ | ||
31 | NETFS_CREATE, /* Create directory entry */ | ||
32 | NETFS_REMOVE, /* Remove directory entry */ | ||
33 | NETFS_LOOKUP, /* Lookup single object */ | ||
34 | NETFS_LINK, /* Create a link */ | ||
35 | NETFS_TRANS, /* Transaction */ | ||
36 | NETFS_OPEN, /* Open intent */ | ||
37 | NETFS_INODE_INFO, /* Metadata cache coherency synchronization message */ | ||
38 | NETFS_PAGE_CACHE, /* Page cache invalidation message */ | ||
39 | NETFS_READ_PAGES, /* Read multiple contiguous pages in one go */ | ||
40 | NETFS_RENAME, /* Rename object */ | ||
41 | NETFS_CAPABILITIES, /* Capabilities of the client, for example supported crypto */ | ||
42 | NETFS_LOCK, /* Distributed lock message */ | ||
43 | NETFS_XATTR_SET, /* Set extended attribute */ | ||
44 | NETFS_XATTR_GET, /* Get extended attribute */ | ||
45 | |||
46 | @ext - external flags. Used by different commands to specify some extra arguments | ||
47 | like partial size of the embedded objects or creation flags. | ||
48 | |||
49 | @size - size of the attached data. For NETFS_READ_PAGE and NETFS_READ_PAGES no data is attached, | ||
50 | but size of the requested data is incorporated here. It does not include size of the command | ||
51 | header (struct netfs_cmd) itself. | ||
52 | |||
53 | @id - id of the object this command operates on. Each command can use it for own purpose. | ||
54 | |||
55 | @start - start of the object this command operates on. Each command can use it for own purpose. | ||
56 | |||
57 | @csize, @cpad - size and padding size of the (attached if needed) crypto information. | ||
58 | |||
59 | Command specifications. | ||
60 | |||
61 | @NETFS_READDIR | ||
62 | This command is used to sync content of the remote dir to the client. | ||
63 | |||
64 | @ext - length of the path to object. | ||
65 | @size - the same. | ||
66 | @id - local inode number of the directory to read. | ||
67 | @start - zero. | ||
68 | |||
69 | |||
70 | @NETFS_READ_PAGE | ||
71 | This command is used to read data from remote server. | ||
72 | Data size does not exceed local page cache size. | ||
73 | |||
74 | @id - inode number. | ||
75 | @start - first byte offset. | ||
76 | @size - number of bytes to read plus length of the path to object. | ||
77 | @ext - object path length. | ||
78 | |||
79 | |||
80 | @NETFS_CREATE | ||
81 | Used to create object. | ||
82 | It does not require that all directories on top of the object were | ||
83 | already created, it will create them automatically. Each object has | ||
84 | associated @netfs_path_entry data structure, which contains creation | ||
85 | mode (permissions and type) and length of the name as long as name itself. | ||
86 | |||
87 | @start - 0 | ||
88 | @size - size of the all data structures needed to create a path | ||
89 | @id - local inode number | ||
90 | @ext - 0 | ||
91 | |||
92 | |||
93 | @NETFS_REMOVE | ||
94 | Used to remove object. | ||
95 | |||
96 | @ext - length of the path to object. | ||
97 | @size - the same. | ||
98 | @id - local inode number. | ||
99 | @start - zero. | ||
100 | |||
101 | |||
102 | @NETFS_LOOKUP | ||
103 | Lookup information about object on server. | ||
104 | |||
105 | @ext - length of the path to object. | ||
106 | @size - the same. | ||
107 | @id - local inode number of the directory to look object in. | ||
108 | @start - local inode number of the object to look at. | ||
109 | |||
110 | |||
111 | @NETFS_LINK | ||
112 | Create hard of symlink. | ||
113 | Command is sent as "object_path|target_path". | ||
114 | |||
115 | @size - size of the above string. | ||
116 | @id - parent local inode number. | ||
117 | @start - 1 for symlink, 0 for hardlink. | ||
118 | @ext - size of the "object_path" above. | ||
119 | |||
120 | |||
121 | @NETFS_TRANS | ||
122 | Transaction header. | ||
123 | |||
124 | @size - incorporates all embedded command sizes including theirs header sizes. | ||
125 | @start - transaction generation number - unique id used to find transaction. | ||
126 | @ext - transaction flags. Unused at the moment. | ||
127 | @id - 0. | ||
128 | |||
129 | |||
130 | @NETFS_OPEN | ||
131 | Open intent for given transaction. | ||
132 | |||
133 | @id - local inode number. | ||
134 | @start - 0. | ||
135 | @size - path length to the object. | ||
136 | @ext - open flags (O_RDWR and so on). | ||
137 | |||
138 | |||
139 | @NETFS_INODE_INFO | ||
140 | Metadata update command. | ||
141 | It is sent to servers when attributes of the object are changed and received | ||
142 | when data or metadata were updated. It operates with the following structure: | ||
143 | |||
144 | struct netfs_inode_info | ||
145 | { | ||
146 | unsigned int mode; | ||
147 | unsigned int nlink; | ||
148 | unsigned int uid; | ||
149 | unsigned int gid; | ||
150 | unsigned int blocksize; | ||
151 | unsigned int padding; | ||
152 | __u64 ino; | ||
153 | __u64 blocks; | ||
154 | __u64 rdev; | ||
155 | __u64 size; | ||
156 | __u64 version; | ||
157 | }; | ||
158 | |||
159 | It effectively mirrors stat(2) returned data. | ||
160 | |||
161 | |||
162 | @ext - path length to the object. | ||
163 | @size - the same plus size of the netfs_inode_info structure. | ||
164 | @id - local inode number. | ||
165 | @start - 0. | ||
166 | |||
167 | |||
168 | @NETFS_PAGE_CACHE | ||
169 | Command is only received by clients. It contains information about | ||
170 | page to be marked as not up-to-date. | ||
171 | |||
172 | @id - client's inode number. | ||
173 | @start - last byte of the page to be invalidated. If it is not equal to | ||
174 | current inode size, it will be vmtruncated(). | ||
175 | @size - 0 | ||
176 | @ext - 0 | ||
177 | |||
178 | |||
179 | @NETFS_READ_PAGES | ||
180 | Used to read multiple contiguous pages in one go. | ||
181 | |||
182 | @start - first byte of the contiguous region to read. | ||
183 | @size - contains of two fields: lower 8 bits are used to represent page cache shift | ||
184 | used by client, another 3 bytes are used to get number of pages. | ||
185 | @id - local inode number. | ||
186 | @ext - path length to the object. | ||
187 | |||
188 | |||
189 | @NETFS_RENAME | ||
190 | Used to rename object. | ||
191 | Attached data is formed into following string: "old_path|new_path". | ||
192 | |||
193 | @id - local inode number. | ||
194 | @start - parent inode number. | ||
195 | @size - length of the above string. | ||
196 | @ext - length of the old path part. | ||
197 | |||
198 | |||
199 | @NETFS_CAPABILITIES | ||
200 | Used to exchange crypto capabilities with server. | ||
201 | If crypto capabilities are not supported by server, then client will disable it | ||
202 | or fail (if 'crypto_fail_unsupported' mount options was specified). | ||
203 | |||
204 | @id - superblock index. Used to specify crypto information for group of servers. | ||
205 | @size - size of the attached capabilities structure. | ||
206 | @start - 0. | ||
207 | @size - 0. | ||
208 | @scsize - 0. | ||
209 | |||
210 | @NETFS_LOCK | ||
211 | Used to send lock request/release messages. Although it sends byte range request | ||
212 | and is capable of flushing pages based on that, it is not used, since all Linux | ||
213 | filesystems lock the whole inode. | ||
214 | |||
215 | @id - lock generation number. | ||
216 | @start - start of the locked range. | ||
217 | @size - size of the locked range. | ||
218 | @ext - lock type: read/write. Not used actually. 15'th bit is used to determine, | ||
219 | if it is lock request (1) or release (0). | ||
220 | |||
221 | @NETFS_XATTR_SET | ||
222 | @NETFS_XATTR_GET | ||
223 | Used to set/get extended attributes for given inode. | ||
224 | @id - attribute generation number or xattr setting type | ||
225 | @start - size of the attribute (request or attached) | ||
226 | @size - name length, path len and data size for given attribute | ||
227 | @ext - path length for given object | ||