view Documentation/filesystems/relay.txt @ 524:7f8b544237bf

netfront: Allow netfront in domain 0.

This is useful if your physical network device is in a utility domain.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
author Keir Fraser <keir.fraser@citrix.com>
date Tue Apr 15 15:18:58 2008 +0100 (2008-04-15)
parents 831230e53067
line source
1 relay interface (formerly relayfs)
2 ==================================
4 The relay interface provides a means for kernel applications to
5 efficiently log and transfer large quantities of data from the kernel
6 to userspace via user-defined 'relay channels'.
8 A 'relay channel' is a kernel->user data relay mechanism implemented
9 as a set of per-cpu kernel buffers ('channel buffers'), each
10 represented as a regular file ('relay file') in user space. Kernel
11 clients write into the channel buffers using efficient write
12 functions; these automatically log into the current cpu's channel
13 buffer. User space applications mmap() or read() from the relay files
14 and retrieve the data as it becomes available. The relay files
15 themselves are files created in a host filesystem, e.g. debugfs, and
16 are associated with the channel buffers using the API described below.
18 The format of the data logged into the channel buffers is completely
19 up to the kernel client; the relay interface does however provide
20 hooks which allow kernel clients to impose some structure on the
21 buffer data. The relay interface doesn't implement any form of data
22 filtering - this also is left to the kernel client. The purpose is to
23 keep things as simple as possible.
25 This document provides an overview of the relay interface API. The
26 details of the function parameters are documented along with the
27 functions in the relay interface code - please see that for details.
29 Semantics
30 =========
32 Each relay channel has one buffer per CPU, each buffer has one or more
33 sub-buffers. Messages are written to the first sub-buffer until it is
34 too full to contain a new message, in which case it it is written to
35 the next (if available). Messages are never split across sub-buffers.
36 At this point, userspace can be notified so it empties the first
37 sub-buffer, while the kernel continues writing to the next.
39 When notified that a sub-buffer is full, the kernel knows how many
40 bytes of it are padding i.e. unused space occurring because a complete
41 message couldn't fit into a sub-buffer. Userspace can use this
42 knowledge to copy only valid data.
44 After copying it, userspace can notify the kernel that a sub-buffer
45 has been consumed.
47 A relay channel can operate in a mode where it will overwrite data not
48 yet collected by userspace, and not wait for it to be consumed.
50 The relay channel itself does not provide for communication of such
51 data between userspace and kernel, allowing the kernel side to remain
52 simple and not impose a single interface on userspace. It does
53 provide a set of examples and a separate helper though, described
54 below.
56 The read() interface both removes padding and internally consumes the
57 read sub-buffers; thus in cases where read(2) is being used to drain
58 the channel buffers, special-purpose communication between kernel and
59 user isn't necessary for basic operation.
61 One of the major goals of the relay interface is to provide a low
62 overhead mechanism for conveying kernel data to userspace. While the
63 read() interface is easy to use, it's not as efficient as the mmap()
64 approach; the example code attempts to make the tradeoff between the
65 two approaches as small as possible.
67 klog and relay-apps example code
68 ================================
70 The relay interface itself is ready to use, but to make things easier,
71 a couple simple utility functions and a set of examples are provided.
73 The relay-apps example tarball, available on the relay sourceforge
74 site, contains a set of self-contained examples, each consisting of a
75 pair of .c files containing boilerplate code for each of the user and
76 kernel sides of a relay application. When combined these two sets of
77 boilerplate code provide glue to easily stream data to disk, without
78 having to bother with mundane housekeeping chores.
80 The 'klog debugging functions' patch (klog.patch in the relay-apps
81 tarball) provides a couple of high-level logging functions to the
82 kernel which allow writing formatted text or raw data to a channel,
83 regardless of whether a channel to write into exists or not, or even
84 whether the relay interface is compiled into the kernel or not. These
85 functions allow you to put unconditional 'trace' statements anywhere
86 in the kernel or kernel modules; only when there is a 'klog handler'
87 registered will data actually be logged (see the klog and kleak
88 examples for details).
90 It is of course possible to use the relay interface from scratch,
91 i.e. without using any of the relay-apps example code or klog, but
92 you'll have to implement communication between userspace and kernel,
93 allowing both to convey the state of buffers (full, empty, amount of
94 padding). The read() interface both removes padding and internally
95 consumes the read sub-buffers; thus in cases where read(2) is being
96 used to drain the channel buffers, special-purpose communication
97 between kernel and user isn't necessary for basic operation. Things
98 such as buffer-full conditions would still need to be communicated via
99 some channel though.
101 klog and the relay-apps examples can be found in the relay-apps
102 tarball on http://relayfs.sourceforge.net
104 The relay interface user space API
105 ==================================
107 The relay interface implements basic file operations for user space
108 access to relay channel buffer data. Here are the file operations
109 that are available and some comments regarding their behavior:
111 open() enables user to open an _existing_ channel buffer.
113 mmap() results in channel buffer being mapped into the caller's
114 memory space. Note that you can't do a partial mmap - you
115 must map the entire file, which is NRBUF * SUBBUFSIZE.
117 read() read the contents of a channel buffer. The bytes read are
118 'consumed' by the reader, i.e. they won't be available
119 again to subsequent reads. If the channel is being used
120 in no-overwrite mode (the default), it can be read at any
121 time even if there's an active kernel writer. If the
122 channel is being used in overwrite mode and there are
123 active channel writers, results may be unpredictable -
124 users should make sure that all logging to the channel has
125 ended before using read() with overwrite mode. Sub-buffer
126 padding is automatically removed and will not be seen by
127 the reader.
129 sendfile() transfer data from a channel buffer to an output file
130 descriptor. Sub-buffer padding is automatically removed
131 and will not be seen by the reader.
133 poll() POLLIN/POLLRDNORM/POLLERR supported. User applications are
134 notified when sub-buffer boundaries are crossed.
136 close() decrements the channel buffer's refcount. When the refcount
137 reaches 0, i.e. when no process or kernel client has the
138 buffer open, the channel buffer is freed.
140 In order for a user application to make use of relay files, the
141 host filesystem must be mounted. For example,
143 mount -t debugfs debugfs /debug
145 NOTE: the host filesystem doesn't need to be mounted for kernel
146 clients to create or use channels - it only needs to be
147 mounted when user space applications need access to the buffer
148 data.
151 The relay interface kernel API
152 ==============================
154 Here's a summary of the API the relay interface provides to in-kernel clients:
156 TBD(curr. line MT:/API/)
157 channel management functions:
159 relay_open(base_filename, parent, subbuf_size, n_subbufs,
160 callbacks)
161 relay_close(chan)
162 relay_flush(chan)
163 relay_reset(chan)
165 channel management typically called on instigation of userspace:
167 relay_subbufs_consumed(chan, cpu, subbufs_consumed)
169 write functions:
171 relay_write(chan, data, length)
172 __relay_write(chan, data, length)
173 relay_reserve(chan, length)
175 callbacks:
177 subbuf_start(buf, subbuf, prev_subbuf, prev_padding)
178 buf_mapped(buf, filp)
179 buf_unmapped(buf, filp)
180 create_buf_file(filename, parent, mode, buf, is_global)
181 remove_buf_file(dentry)
183 helper functions:
185 relay_buf_full(buf)
186 subbuf_start_reserve(buf, length)
189 Creating a channel
190 ------------------
192 relay_open() is used to create a channel, along with its per-cpu
193 channel buffers. Each channel buffer will have an associated file
194 created for it in the host filesystem, which can be and mmapped or
195 read from in user space. The files are named basename0...basenameN-1
196 where N is the number of online cpus, and by default will be created
197 in the root of the filesystem (if the parent param is NULL). If you
198 want a directory structure to contain your relay files, you should
199 create it using the host filesystem's directory creation function,
200 e.g. debugfs_create_dir(), and pass the parent directory to
201 relay_open(). Users are responsible for cleaning up any directory
202 structure they create, when the channel is closed - again the host
203 filesystem's directory removal functions should be used for that,
204 e.g. debugfs_remove().
206 In order for a channel to be created and the host filesystem's files
207 associated with its channel buffers, the user must provide definitions
208 for two callback functions, create_buf_file() and remove_buf_file().
209 create_buf_file() is called once for each per-cpu buffer from
210 relay_open() and allows the user to create the file which will be used
211 to represent the corresponding channel buffer. The callback should
212 return the dentry of the file created to represent the channel buffer.
213 remove_buf_file() must also be defined; it's responsible for deleting
214 the file(s) created in create_buf_file() and is called during
215 relay_close().
217 Here are some typical definitions for these callbacks, in this case
218 using debugfs:
220 /*
221 * create_buf_file() callback. Creates relay file in debugfs.
222 */
223 static struct dentry *create_buf_file_handler(const char *filename,
224 struct dentry *parent,
225 int mode,
226 struct rchan_buf *buf,
227 int *is_global)
228 {
229 return debugfs_create_file(filename, mode, parent, buf,
230 &relay_file_operations);
231 }
233 /*
234 * remove_buf_file() callback. Removes relay file from debugfs.
235 */
236 static int remove_buf_file_handler(struct dentry *dentry)
237 {
238 debugfs_remove(dentry);
240 return 0;
241 }
243 /*
244 * relay interface callbacks
245 */
246 static struct rchan_callbacks relay_callbacks =
247 {
248 .create_buf_file = create_buf_file_handler,
249 .remove_buf_file = remove_buf_file_handler,
250 };
252 And an example relay_open() invocation using them:
254 chan = relay_open("cpu", NULL, SUBBUF_SIZE, N_SUBBUFS, &relay_callbacks);
256 If the create_buf_file() callback fails, or isn't defined, channel
257 creation and thus relay_open() will fail.
259 The total size of each per-cpu buffer is calculated by multiplying the
260 number of sub-buffers by the sub-buffer size passed into relay_open().
261 The idea behind sub-buffers is that they're basically an extension of
262 double-buffering to N buffers, and they also allow applications to
263 easily implement random-access-on-buffer-boundary schemes, which can
264 be important for some high-volume applications. The number and size
265 of sub-buffers is completely dependent on the application and even for
266 the same application, different conditions will warrant different
267 values for these parameters at different times. Typically, the right
268 values to use are best decided after some experimentation; in general,
269 though, it's safe to assume that having only 1 sub-buffer is a bad
270 idea - you're guaranteed to either overwrite data or lose events
271 depending on the channel mode being used.
273 The create_buf_file() implementation can also be defined in such a way
274 as to allow the creation of a single 'global' buffer instead of the
275 default per-cpu set. This can be useful for applications interested
276 mainly in seeing the relative ordering of system-wide events without
277 the need to bother with saving explicit timestamps for the purpose of
278 merging/sorting per-cpu files in a postprocessing step.
280 To have relay_open() create a global buffer, the create_buf_file()
281 implementation should set the value of the is_global outparam to a
282 non-zero value in addition to creating the file that will be used to
283 represent the single buffer. In the case of a global buffer,
284 create_buf_file() and remove_buf_file() will be called only once. The
285 normal channel-writing functions, e.g. relay_write(), can still be
286 used - writes from any cpu will transparently end up in the global
287 buffer - but since it is a global buffer, callers should make sure
288 they use the proper locking for such a buffer, either by wrapping
289 writes in a spinlock, or by copying a write function from relay.h and
290 creating a local version that internally does the proper locking.
292 Channel 'modes'
293 ---------------
295 relay channels can be used in either of two modes - 'overwrite' or
296 'no-overwrite'. The mode is entirely determined by the implementation
297 of the subbuf_start() callback, as described below. The default if no
298 subbuf_start() callback is defined is 'no-overwrite' mode. If the
299 default mode suits your needs, and you plan to use the read()
300 interface to retrieve channel data, you can ignore the details of this
301 section, as it pertains mainly to mmap() implementations.
303 In 'overwrite' mode, also known as 'flight recorder' mode, writes
304 continuously cycle around the buffer and will never fail, but will
305 unconditionally overwrite old data regardless of whether it's actually
306 been consumed. In no-overwrite mode, writes will fail, i.e. data will
307 be lost, if the number of unconsumed sub-buffers equals the total
308 number of sub-buffers in the channel. It should be clear that if
309 there is no consumer or if the consumer can't consume sub-buffers fast
310 enough, data will be lost in either case; the only difference is
311 whether data is lost from the beginning or the end of a buffer.
313 As explained above, a relay channel is made of up one or more
314 per-cpu channel buffers, each implemented as a circular buffer
315 subdivided into one or more sub-buffers. Messages are written into
316 the current sub-buffer of the channel's current per-cpu buffer via the
317 write functions described below. Whenever a message can't fit into
318 the current sub-buffer, because there's no room left for it, the
319 client is notified via the subbuf_start() callback that a switch to a
320 new sub-buffer is about to occur. The client uses this callback to 1)
321 initialize the next sub-buffer if appropriate 2) finalize the previous
322 sub-buffer if appropriate and 3) return a boolean value indicating
323 whether or not to actually move on to the next sub-buffer.
325 To implement 'no-overwrite' mode, the userspace client would provide
326 an implementation of the subbuf_start() callback something like the
327 following:
329 static int subbuf_start(struct rchan_buf *buf,
330 void *subbuf,
331 void *prev_subbuf,
332 unsigned int prev_padding)
333 {
334 if (prev_subbuf)
335 *((unsigned *)prev_subbuf) = prev_padding;
337 if (relay_buf_full(buf))
338 return 0;
340 subbuf_start_reserve(buf, sizeof(unsigned int));
342 return 1;
343 }
345 If the current buffer is full, i.e. all sub-buffers remain unconsumed,
346 the callback returns 0 to indicate that the buffer switch should not
347 occur yet, i.e. until the consumer has had a chance to read the
348 current set of ready sub-buffers. For the relay_buf_full() function
349 to make sense, the consumer is reponsible for notifying the relay
350 interface when sub-buffers have been consumed via
351 relay_subbufs_consumed(). Any subsequent attempts to write into the
352 buffer will again invoke the subbuf_start() callback with the same
353 parameters; only when the consumer has consumed one or more of the
354 ready sub-buffers will relay_buf_full() return 0, in which case the
355 buffer switch can continue.
357 The implementation of the subbuf_start() callback for 'overwrite' mode
358 would be very similar:
360 static int subbuf_start(struct rchan_buf *buf,
361 void *subbuf,
362 void *prev_subbuf,
363 unsigned int prev_padding)
364 {
365 if (prev_subbuf)
366 *((unsigned *)prev_subbuf) = prev_padding;
368 subbuf_start_reserve(buf, sizeof(unsigned int));
370 return 1;
371 }
373 In this case, the relay_buf_full() check is meaningless and the
374 callback always returns 1, causing the buffer switch to occur
375 unconditionally. It's also meaningless for the client to use the
376 relay_subbufs_consumed() function in this mode, as it's never
377 consulted.
379 The default subbuf_start() implementation, used if the client doesn't
380 define any callbacks, or doesn't define the subbuf_start() callback,
381 implements the simplest possible 'no-overwrite' mode, i.e. it does
382 nothing but return 0.
384 Header information can be reserved at the beginning of each sub-buffer
385 by calling the subbuf_start_reserve() helper function from within the
386 subbuf_start() callback. This reserved area can be used to store
387 whatever information the client wants. In the example above, room is
388 reserved in each sub-buffer to store the padding count for that
389 sub-buffer. This is filled in for the previous sub-buffer in the
390 subbuf_start() implementation; the padding value for the previous
391 sub-buffer is passed into the subbuf_start() callback along with a
392 pointer to the previous sub-buffer, since the padding value isn't
393 known until a sub-buffer is filled. The subbuf_start() callback is
394 also called for the first sub-buffer when the channel is opened, to
395 give the client a chance to reserve space in it. In this case the
396 previous sub-buffer pointer passed into the callback will be NULL, so
397 the client should check the value of the prev_subbuf pointer before
398 writing into the previous sub-buffer.
400 Writing to a channel
401 --------------------
403 Kernel clients write data into the current cpu's channel buffer using
404 relay_write() or __relay_write(). relay_write() is the main logging
405 function - it uses local_irqsave() to protect the buffer and should be
406 used if you might be logging from interrupt context. If you know
407 you'll never be logging from interrupt context, you can use
408 __relay_write(), which only disables preemption. These functions
409 don't return a value, so you can't determine whether or not they
410 failed - the assumption is that you wouldn't want to check a return
411 value in the fast logging path anyway, and that they'll always succeed
412 unless the buffer is full and no-overwrite mode is being used, in
413 which case you can detect a failed write in the subbuf_start()
414 callback by calling the relay_buf_full() helper function.
416 relay_reserve() is used to reserve a slot in a channel buffer which
417 can be written to later. This would typically be used in applications
418 that need to write directly into a channel buffer without having to
419 stage data in a temporary buffer beforehand. Because the actual write
420 may not happen immediately after the slot is reserved, applications
421 using relay_reserve() can keep a count of the number of bytes actually
422 written, either in space reserved in the sub-buffers themselves or as
423 a separate array. See the 'reserve' example in the relay-apps tarball
424 at http://relayfs.sourceforge.net for an example of how this can be
425 done. Because the write is under control of the client and is
426 separated from the reserve, relay_reserve() doesn't protect the buffer
427 at all - it's up to the client to provide the appropriate
428 synchronization when using relay_reserve().
430 Closing a channel
431 -----------------
433 The client calls relay_close() when it's finished using the channel.
434 The channel and its associated buffers are destroyed when there are no
435 longer any references to any of the channel buffers. relay_flush()
436 forces a sub-buffer switch on all the channel buffers, and can be used
437 to finalize and process the last sub-buffers before the channel is
438 closed.
440 Misc
441 ----
443 Some applications may want to keep a channel around and re-use it
444 rather than open and close a new channel for each use. relay_reset()
445 can be used for this purpose - it resets a channel to its initial
446 state without reallocating channel buffer memory or destroying
447 existing mappings. It should however only be called when it's safe to
448 do so, i.e. when the channel isn't currently being written to.
450 Finally, there are a couple of utility callbacks that can be used for
451 different purposes. buf_mapped() is called whenever a channel buffer
452 is mmapped from user space and buf_unmapped() is called when it's
453 unmapped. The client can use this notification to trigger actions
454 within the kernel application, such as enabling/disabling logging to
455 the channel.
458 Resources
459 =========
461 For news, example code, mailing list, etc. see the relay interface homepage:
463 http://relayfs.sourceforge.net
466 Credits
467 =======
469 The ideas and specs for the relay interface came about as a result of
470 discussions on tracing involving the following:
472 Michel Dagenais <michel.dagenais@polymtl.ca>
473 Richard Moore <richardj_moore@uk.ibm.com>
474 Bob Wisniewski <bob@watson.ibm.com>
475 Karim Yaghmour <karim@opersys.com>
476 Tom Zanussi <zanussi@us.ibm.com>
478 Also thanks to Hubertus Franke for a lot of useful suggestions and bug
479 reports.