Root/Documentation/DMA-API-HOWTO.txt

1             Dynamic DMA mapping Guide
2             =========================
3
4         David S. Miller <davem@redhat.com>
5         Richard Henderson <rth@cygnus.com>
6          Jakub Jelinek <jakub@redhat.com>
7
8This is a guide to device driver writers on how to use the DMA API
9with example pseudo-code. For a concise description of the API, see
10DMA-API.txt.
11
12Most of the 64bit platforms have special hardware that translates bus
13addresses (DMA addresses) into physical addresses. This is similar to
14how page tables and/or a TLB translates virtual addresses to physical
15addresses on a CPU. This is needed so that e.g. PCI devices can
16access with a Single Address Cycle (32bit DMA address) any page in the
1764bit physical address space. Previously in Linux those 64bit
18platforms had to set artificial limits on the maximum RAM size in the
19system, so that the virt_to_bus() static scheme works (the DMA address
20translation tables were simply filled on bootup to map each bus
21address to the physical page __pa(bus_to_virt())).
22
23So that Linux can use the dynamic DMA mapping, it needs some help from the
24drivers, namely it has to take into account that DMA addresses should be
25mapped only for the time they are actually used and unmapped after the DMA
26transfer.
27
28The following API will work of course even on platforms where no such
29hardware exists.
30
31Note that the DMA API works with any bus independent of the underlying
32microprocessor architecture. You should use the DMA API rather than
33the bus specific DMA API (e.g. pci_dma_*).
34
35First of all, you should make sure
36
37#include <linux/dma-mapping.h>
38
39is in your driver. This file will obtain for you the definition of the
40dma_addr_t (which can hold any valid DMA address for the platform)
41type which should be used everywhere you hold a DMA (bus) address
42returned from the DMA mapping functions.
43
44             What memory is DMA'able?
45
46The first piece of information you must know is what kernel memory can
47be used with the DMA mapping facilities. There has been an unwritten
48set of rules regarding this, and this text is an attempt to finally
49write them down.
50
51If you acquired your memory via the page allocator
52(i.e. __get_free_page*()) or the generic memory allocators
53(i.e. kmalloc() or kmem_cache_alloc()) then you may DMA to/from
54that memory using the addresses returned from those routines.
55
56This means specifically that you may _not_ use the memory/addresses
57returned from vmalloc() for DMA. It is possible to DMA to the
58_underlying_ memory mapped into a vmalloc() area, but this requires
59walking page tables to get the physical addresses, and then
60translating each of those pages back to a kernel address using
61something like __va(). [ EDIT: Update this when we integrate
62Gerd Knorr's generic code which does this. ]
63
64This rule also means that you may use neither kernel image addresses
65(items in data/text/bss segments), nor module image addresses, nor
66stack addresses for DMA. These could all be mapped somewhere entirely
67different than the rest of physical memory. Even if those classes of
68memory could physically work with DMA, you'd need to ensure the I/O
69buffers were cacheline-aligned. Without that, you'd see cacheline
70sharing problems (data corruption) on CPUs with DMA-incoherent caches.
71(The CPU could write to one word, DMA would write to a different one
72in the same cache line, and one of them could be overwritten.)
73
74Also, this means that you cannot take the return of a kmap()
75call and DMA to/from that. This is similar to vmalloc().
76
77What about block I/O and networking buffers? The block I/O and
78networking subsystems make sure that the buffers they use are valid
79for you to DMA from/to.
80
81            DMA addressing limitations
82
83Does your device have any DMA addressing limitations? For example, is
84your device only capable of driving the low order 24-bits of address?
85If so, you need to inform the kernel of this fact.
86
87By default, the kernel assumes that your device can address the full
8832-bits. For a 64-bit capable device, this needs to be increased.
89And for a device with limitations, as discussed in the previous
90paragraph, it needs to be decreased.
91
92Special note about PCI: PCI-X specification requires PCI-X devices to
93support 64-bit addressing (DAC) for all transactions. And at least
94one platform (SGI SN2) requires 64-bit consistent allocations to
95operate correctly when the IO bus is in PCI-X mode.
96
97For correct operation, you must interrogate the kernel in your device
98probe routine to see if the DMA controller on the machine can properly
99support the DMA addressing limitation your device has. It is good
100style to do this even if your device holds the default setting,
101because this shows that you did think about these issues wrt. your
102device.
103
104The query is performed via a call to dma_set_mask():
105
106    int dma_set_mask(struct device *dev, u64 mask);
107
108The query for consistent allocations is performed via a call to
109dma_set_coherent_mask():
110
111    int dma_set_coherent_mask(struct device *dev, u64 mask);
112
113Here, dev is a pointer to the device struct of your device, and mask
114is a bit mask describing which bits of an address your device
115supports. It returns zero if your card can perform DMA properly on
116the machine given the address mask you provided. In general, the
117device struct of your device is embedded in the bus specific device
118struct of your device. For example, a pointer to the device struct of
119your PCI device is pdev->dev (pdev is a pointer to the PCI device
120struct of your device).
121
122If it returns non-zero, your device cannot perform DMA properly on
123this platform, and attempting to do so will result in undefined
124behavior. You must either use a different mask, or not use DMA.
125
126This means that in the failure case, you have three options:
127
1281) Use another DMA mask, if possible (see below).
1292) Use some non-DMA mode for data transfer, if possible.
1303) Ignore this device and do not initialize it.
131
132It is recommended that your driver print a kernel KERN_WARNING message
133when you end up performing either #2 or #3. In this manner, if a user
134of your driver reports that performance is bad or that the device is not
135even detected, you can ask them for the kernel messages to find out
136exactly why.
137
138The standard 32-bit addressing device would do something like this:
139
140    if (dma_set_mask(dev, DMA_BIT_MASK(32))) {
141        printk(KERN_WARNING
142               "mydev: No suitable DMA available.\n");
143        goto ignore_this_device;
144    }
145
146Another common scenario is a 64-bit capable device. The approach here
147is to try for 64-bit addressing, but back down to a 32-bit mask that
148should not fail. The kernel may fail the 64-bit mask not because the
149platform is not capable of 64-bit addressing. Rather, it may fail in
150this case simply because 32-bit addressing is done more efficiently
151than 64-bit addressing. For example, Sparc64 PCI SAC addressing is
152more efficient than DAC addressing.
153
154Here is how you would handle a 64-bit capable device which can drive
155all 64-bits when accessing streaming DMA:
156
157    int using_dac;
158
159    if (!dma_set_mask(dev, DMA_BIT_MASK(64))) {
160        using_dac = 1;
161    } else if (!dma_set_mask(dev, DMA_BIT_MASK(32))) {
162        using_dac = 0;
163    } else {
164        printk(KERN_WARNING
165               "mydev: No suitable DMA available.\n");
166        goto ignore_this_device;
167    }
168
169If a card is capable of using 64-bit consistent allocations as well,
170the case would look like this:
171
172    int using_dac, consistent_using_dac;
173
174    if (!dma_set_mask(dev, DMA_BIT_MASK(64))) {
175        using_dac = 1;
176           consistent_using_dac = 1;
177        dma_set_coherent_mask(dev, DMA_BIT_MASK(64));
178    } else if (!dma_set_mask(dev, DMA_BIT_MASK(32))) {
179        using_dac = 0;
180        consistent_using_dac = 0;
181        dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
182    } else {
183        printk(KERN_WARNING
184               "mydev: No suitable DMA available.\n");
185        goto ignore_this_device;
186    }
187
188dma_set_coherent_mask() will always be able to set the same or a
189smaller mask as dma_set_mask(). However for the rare case that a
190device driver only uses consistent allocations, one would have to
191check the return value from dma_set_coherent_mask().
192
193Finally, if your device can only drive the low 24-bits of
194address you might do something like:
195
196    if (dma_set_mask(dev, DMA_BIT_MASK(24))) {
197        printk(KERN_WARNING
198               "mydev: 24-bit DMA addressing not available.\n");
199        goto ignore_this_device;
200    }
201
202When dma_set_mask() is successful, and returns zero, the kernel saves
203away this mask you have provided. The kernel will use this
204information later when you make DMA mappings.
205
206There is a case which we are aware of at this time, which is worth
207mentioning in this documentation. If your device supports multiple
208functions (for example a sound card provides playback and record
209functions) and the various different functions have _different_
210DMA addressing limitations, you may wish to probe each mask and
211only provide the functionality which the machine can handle. It
212is important that the last call to dma_set_mask() be for the
213most specific mask.
214
215Here is pseudo-code showing how this might be done:
216
217    #define PLAYBACK_ADDRESS_BITS DMA_BIT_MASK(32)
218    #define RECORD_ADDRESS_BITS DMA_BIT_MASK(24)
219
220    struct my_sound_card *card;
221    struct device *dev;
222
223    ...
224    if (!dma_set_mask(dev, PLAYBACK_ADDRESS_BITS)) {
225        card->playback_enabled = 1;
226    } else {
227        card->playback_enabled = 0;
228        printk(KERN_WARNING "%s: Playback disabled due to DMA limitations.\n",
229               card->name);
230    }
231    if (!dma_set_mask(dev, RECORD_ADDRESS_BITS)) {
232        card->record_enabled = 1;
233    } else {
234        card->record_enabled = 0;
235        printk(KERN_WARNING "%s: Record disabled due to DMA limitations.\n",
236               card->name);
237    }
238
239A sound card was used as an example here because this genre of PCI
240devices seems to be littered with ISA chips given a PCI front end,
241and thus retaining the 16MB DMA addressing limitations of ISA.
242
243            Types of DMA mappings
244
245There are two types of DMA mappings:
246
247- Consistent DMA mappings which are usually mapped at driver
248  initialization, unmapped at the end and for which the hardware should
249  guarantee that the device and the CPU can access the data
250  in parallel and will see updates made by each other without any
251  explicit software flushing.
252
253  Think of "consistent" as "synchronous" or "coherent".
254
255  The current default is to return consistent memory in the low 32
256  bits of the bus space. However, for future compatibility you should
257  set the consistent mask even if this default is fine for your
258  driver.
259
260  Good examples of what to use consistent mappings for are:
261
262    - Network card DMA ring descriptors.
263    - SCSI adapter mailbox command data structures.
264    - Device firmware microcode executed out of
265      main memory.
266
267  The invariant these examples all require is that any CPU store
268  to memory is immediately visible to the device, and vice
269  versa. Consistent mappings guarantee this.
270
271  IMPORTANT: Consistent DMA memory does not preclude the usage of
272             proper memory barriers. The CPU may reorder stores to
273         consistent memory just as it may normal memory. Example:
274         if it is important for the device to see the first word
275         of a descriptor updated before the second, you must do
276         something like:
277
278        desc->word0 = address;
279        wmb();
280        desc->word1 = DESC_VALID;
281
282             in order to get correct behavior on all platforms.
283
284         Also, on some platforms your driver may need to flush CPU write
285         buffers in much the same way as it needs to flush write buffers
286         found in PCI bridges (such as by reading a register's value
287         after writing it).
288
289- Streaming DMA mappings which are usually mapped for one DMA
290  transfer, unmapped right after it (unless you use dma_sync_* below)
291  and for which hardware can optimize for sequential accesses.
292
293  This of "streaming" as "asynchronous" or "outside the coherency
294  domain".
295
296  Good examples of what to use streaming mappings for are:
297
298    - Networking buffers transmitted/received by a device.
299    - Filesystem buffers written/read by a SCSI device.
300
301  The interfaces for using this type of mapping were designed in
302  such a way that an implementation can make whatever performance
303  optimizations the hardware allows. To this end, when using
304  such mappings you must be explicit about what you want to happen.
305
306Neither type of DMA mapping has alignment restrictions that come from
307the underlying bus, although some devices may have such restrictions.
308Also, systems with caches that aren't DMA-coherent will work better
309when the underlying buffers don't share cache lines with other data.
310
311
312         Using Consistent DMA mappings.
313
314To allocate and map large (PAGE_SIZE or so) consistent DMA regions,
315you should do:
316
317    dma_addr_t dma_handle;
318
319    cpu_addr = dma_alloc_coherent(dev, size, &dma_handle, gfp);
320
321where device is a struct device *. This may be called in interrupt
322context with the GFP_ATOMIC flag.
323
324Size is the length of the region you want to allocate, in bytes.
325
326This routine will allocate RAM for that region, so it acts similarly to
327__get_free_pages (but takes size instead of a page order). If your
328driver needs regions sized smaller than a page, you may prefer using
329the dma_pool interface, described below.
330
331The consistent DMA mapping interfaces, for non-NULL dev, will by
332default return a DMA address which is 32-bit addressable. Even if the
333device indicates (via DMA mask) that it may address the upper 32-bits,
334consistent allocation will only return > 32-bit addresses for DMA if
335the consistent DMA mask has been explicitly changed via
336dma_set_coherent_mask(). This is true of the dma_pool interface as
337well.
338
339dma_alloc_coherent returns two values: the virtual address which you
340can use to access it from the CPU and dma_handle which you pass to the
341card.
342
343The cpu return address and the DMA bus master address are both
344guaranteed to be aligned to the smallest PAGE_SIZE order which
345is greater than or equal to the requested size. This invariant
346exists (for example) to guarantee that if you allocate a chunk
347which is smaller than or equal to 64 kilobytes, the extent of the
348buffer you receive will not cross a 64K boundary.
349
350To unmap and free such a DMA region, you call:
351
352    dma_free_coherent(dev, size, cpu_addr, dma_handle);
353
354where dev, size are the same as in the above call and cpu_addr and
355dma_handle are the values dma_alloc_coherent returned to you.
356This function may not be called in interrupt context.
357
358If your driver needs lots of smaller memory regions, you can write
359custom code to subdivide pages returned by dma_alloc_coherent,
360or you can use the dma_pool API to do that. A dma_pool is like
361a kmem_cache, but it uses dma_alloc_coherent not __get_free_pages.
362Also, it understands common hardware constraints for alignment,
363like queue heads needing to be aligned on N byte boundaries.
364
365Create a dma_pool like this:
366
367    struct dma_pool *pool;
368
369    pool = dma_pool_create(name, dev, size, align, alloc);
370
371The "name" is for diagnostics (like a kmem_cache name); dev and size
372are as above. The device's hardware alignment requirement for this
373type of data is "align" (which is expressed in bytes, and must be a
374power of two). If your device has no boundary crossing restrictions,
375pass 0 for alloc; passing 4096 says memory allocated from this pool
376must not cross 4KByte boundaries (but at that time it may be better to
377go for dma_alloc_coherent directly instead).
378
379Allocate memory from a dma pool like this:
380
381    cpu_addr = dma_pool_alloc(pool, flags, &dma_handle);
382
383flags are SLAB_KERNEL if blocking is permitted (not in_interrupt nor
384holding SMP locks), SLAB_ATOMIC otherwise. Like dma_alloc_coherent,
385this returns two values, cpu_addr and dma_handle.
386
387Free memory that was allocated from a dma_pool like this:
388
389    dma_pool_free(pool, cpu_addr, dma_handle);
390
391where pool is what you passed to dma_pool_alloc, and cpu_addr and
392dma_handle are the values dma_pool_alloc returned. This function
393may be called in interrupt context.
394
395Destroy a dma_pool by calling:
396
397    dma_pool_destroy(pool);
398
399Make sure you've called dma_pool_free for all memory allocated
400from a pool before you destroy the pool. This function may not
401be called in interrupt context.
402
403            DMA Direction
404
405The interfaces described in subsequent portions of this document
406take a DMA direction argument, which is an integer and takes on
407one of the following values:
408
409 DMA_BIDIRECTIONAL
410 DMA_TO_DEVICE
411 DMA_FROM_DEVICE
412 DMA_NONE
413
414One should provide the exact DMA direction if you know it.
415
416DMA_TO_DEVICE means "from main memory to the device"
417DMA_FROM_DEVICE means "from the device to main memory"
418It is the direction in which the data moves during the DMA
419transfer.
420
421You are _strongly_ encouraged to specify this as precisely
422as you possibly can.
423
424If you absolutely cannot know the direction of the DMA transfer,
425specify DMA_BIDIRECTIONAL. It means that the DMA can go in
426either direction. The platform guarantees that you may legally
427specify this, and that it will work, but this may be at the
428cost of performance for example.
429
430The value DMA_NONE is to be used for debugging. One can
431hold this in a data structure before you come to know the
432precise direction, and this will help catch cases where your
433direction tracking logic has failed to set things up properly.
434
435Another advantage of specifying this value precisely (outside of
436potential platform-specific optimizations of such) is for debugging.
437Some platforms actually have a write permission boolean which DMA
438mappings can be marked with, much like page protections in the user
439program address space. Such platforms can and do report errors in the
440kernel logs when the DMA controller hardware detects violation of the
441permission setting.
442
443Only streaming mappings specify a direction, consistent mappings
444implicitly have a direction attribute setting of
445DMA_BIDIRECTIONAL.
446
447The SCSI subsystem tells you the direction to use in the
448'sc_data_direction' member of the SCSI command your driver is
449working on.
450
451For Networking drivers, it's a rather simple affair. For transmit
452packets, map/unmap them with the DMA_TO_DEVICE direction
453specifier. For receive packets, just the opposite, map/unmap them
454with the DMA_FROM_DEVICE direction specifier.
455
456          Using Streaming DMA mappings
457
458The streaming DMA mapping routines can be called from interrupt
459context. There are two versions of each map/unmap, one which will
460map/unmap a single memory region, and one which will map/unmap a
461scatterlist.
462
463To map a single region, you do:
464
465    struct device *dev = &my_dev->dev;
466    dma_addr_t dma_handle;
467    void *addr = buffer->ptr;
468    size_t size = buffer->len;
469
470    dma_handle = dma_map_single(dev, addr, size, direction);
471
472and to unmap it:
473
474    dma_unmap_single(dev, dma_handle, size, direction);
475
476You should call dma_unmap_single when the DMA activity is finished, e.g.
477from the interrupt which told you that the DMA transfer is done.
478
479Using cpu pointers like this for single mappings has a disadvantage,
480you cannot reference HIGHMEM memory in this way. Thus, there is a
481map/unmap interface pair akin to dma_{map,unmap}_single. These
482interfaces deal with page/offset pairs instead of cpu pointers.
483Specifically:
484
485    struct device *dev = &my_dev->dev;
486    dma_addr_t dma_handle;
487    struct page *page = buffer->page;
488    unsigned long offset = buffer->offset;
489    size_t size = buffer->len;
490
491    dma_handle = dma_map_page(dev, page, offset, size, direction);
492
493    ...
494
495    dma_unmap_page(dev, dma_handle, size, direction);
496
497Here, "offset" means byte offset within the given page.
498
499With scatterlists, you map a region gathered from several regions by:
500
501    int i, count = dma_map_sg(dev, sglist, nents, direction);
502    struct scatterlist *sg;
503
504    for_each_sg(sglist, sg, count, i) {
505        hw_address[i] = sg_dma_address(sg);
506        hw_len[i] = sg_dma_len(sg);
507    }
508
509where nents is the number of entries in the sglist.
510
511The implementation is free to merge several consecutive sglist entries
512into one (e.g. if DMA mapping is done with PAGE_SIZE granularity, any
513consecutive sglist entries can be merged into one provided the first one
514ends and the second one starts on a page boundary - in fact this is a huge
515advantage for cards which either cannot do scatter-gather or have very
516limited number of scatter-gather entries) and returns the actual number
517of sg entries it mapped them to. On failure 0 is returned.
518
519Then you should loop count times (note: this can be less than nents times)
520and use sg_dma_address() and sg_dma_len() macros where you previously
521accessed sg->address and sg->length as shown above.
522
523To unmap a scatterlist, just call:
524
525    dma_unmap_sg(dev, sglist, nents, direction);
526
527Again, make sure DMA activity has already finished.
528
529PLEASE NOTE: The 'nents' argument to the dma_unmap_sg call must be
530              the _same_ one you passed into the dma_map_sg call,
531          it should _NOT_ be the 'count' value _returned_ from the
532              dma_map_sg call.
533
534Every dma_map_{single,sg} call should have its dma_unmap_{single,sg}
535counterpart, because the bus address space is a shared resource (although
536in some ports the mapping is per each BUS so less devices contend for the
537same bus address space) and you could render the machine unusable by eating
538all bus addresses.
539
540If you need to use the same streaming DMA region multiple times and touch
541the data in between the DMA transfers, the buffer needs to be synced
542properly in order for the cpu and device to see the most uptodate and
543correct copy of the DMA buffer.
544
545So, firstly, just map it with dma_map_{single,sg}, and after each DMA
546transfer call either:
547
548    dma_sync_single_for_cpu(dev, dma_handle, size, direction);
549
550or:
551
552    dma_sync_sg_for_cpu(dev, sglist, nents, direction);
553
554as appropriate.
555
556Then, if you wish to let the device get at the DMA area again,
557finish accessing the data with the cpu, and then before actually
558giving the buffer to the hardware call either:
559
560    dma_sync_single_for_device(dev, dma_handle, size, direction);
561
562or:
563
564    dma_sync_sg_for_device(dev, sglist, nents, direction);
565
566as appropriate.
567
568After the last DMA transfer call one of the DMA unmap routines
569dma_unmap_{single,sg}. If you don't touch the data from the first dma_map_*
570call till dma_unmap_*, then you don't have to call the dma_sync_*
571routines at all.
572
573Here is pseudo code which shows a situation in which you would need
574to use the dma_sync_*() interfaces.
575
576    my_card_setup_receive_buffer(struct my_card *cp, char *buffer, int len)
577    {
578        dma_addr_t mapping;
579
580        mapping = dma_map_single(cp->dev, buffer, len, DMA_FROM_DEVICE);
581
582        cp->rx_buf = buffer;
583        cp->rx_len = len;
584        cp->rx_dma = mapping;
585
586        give_rx_buf_to_card(cp);
587    }
588
589    ...
590
591    my_card_interrupt_handler(int irq, void *devid, struct pt_regs *regs)
592    {
593        struct my_card *cp = devid;
594
595        ...
596        if (read_card_status(cp) == RX_BUF_TRANSFERRED) {
597            struct my_card_header *hp;
598
599            /* Examine the header to see if we wish
600             * to accept the data. But synchronize
601             * the DMA transfer with the CPU first
602             * so that we see updated contents.
603             */
604            dma_sync_single_for_cpu(&cp->dev, cp->rx_dma,
605                        cp->rx_len,
606                        DMA_FROM_DEVICE);
607
608            /* Now it is safe to examine the buffer. */
609            hp = (struct my_card_header *) cp->rx_buf;
610            if (header_is_ok(hp)) {
611                dma_unmap_single(&cp->dev, cp->rx_dma, cp->rx_len,
612                         DMA_FROM_DEVICE);
613                pass_to_upper_layers(cp->rx_buf);
614                make_and_setup_new_rx_buf(cp);
615            } else {
616                /* CPU should not write to
617                 * DMA_FROM_DEVICE-mapped area,
618                 * so dma_sync_single_for_device() is
619                 * not needed here. It would be required
620                 * for DMA_BIDIRECTIONAL mapping if
621                 * the memory was modified.
622                 */
623                give_rx_buf_to_card(cp);
624            }
625        }
626    }
627
628Drivers converted fully to this interface should not use virt_to_bus any
629longer, nor should they use bus_to_virt. Some drivers have to be changed a
630little bit, because there is no longer an equivalent to bus_to_virt in the
631dynamic DMA mapping scheme - you have to always store the DMA addresses
632returned by the dma_alloc_coherent, dma_pool_alloc, and dma_map_single
633calls (dma_map_sg stores them in the scatterlist itself if the platform
634supports dynamic DMA mapping in hardware) in your driver structures and/or
635in the card registers.
636
637All drivers should be using these interfaces with no exceptions. It
638is planned to completely remove virt_to_bus() and bus_to_virt() as
639they are entirely deprecated. Some ports already do not provide these
640as it is impossible to correctly support them.
641
642            Handling Errors
643
644DMA address space is limited on some architectures and an allocation
645failure can be determined by:
646
647- checking if dma_alloc_coherent returns NULL or dma_map_sg returns 0
648
649- checking the returned dma_addr_t of dma_map_single and dma_map_page
650  by using dma_mapping_error():
651
652    dma_addr_t dma_handle;
653
654    dma_handle = dma_map_single(dev, addr, size, direction);
655    if (dma_mapping_error(dev, dma_handle)) {
656        /*
657         * reduce current DMA mapping usage,
658         * delay and try again later or
659         * reset driver.
660         */
661    }
662
663Networking drivers must call dev_kfree_skb to free the socket buffer
664and return NETDEV_TX_OK if the DMA mapping fails on the transmit hook
665(ndo_start_xmit). This means that the socket buffer is just dropped in
666the failure case.
667
668SCSI drivers must return SCSI_MLQUEUE_HOST_BUSY if the DMA mapping
669fails in the queuecommand hook. This means that the SCSI subsystem
670passes the command to the driver again later.
671
672        Optimizing Unmap State Space Consumption
673
674On many platforms, dma_unmap_{single,page}() is simply a nop.
675Therefore, keeping track of the mapping address and length is a waste
676of space. Instead of filling your drivers up with ifdefs and the like
677to "work around" this (which would defeat the whole purpose of a
678portable API) the following facilities are provided.
679
680Actually, instead of describing the macros one by one, we'll
681transform some example code.
682
6831) Use DEFINE_DMA_UNMAP_{ADDR,LEN} in state saving structures.
684   Example, before:
685
686    struct ring_state {
687        struct sk_buff *skb;
688        dma_addr_t mapping;
689        __u32 len;
690    };
691
692   after:
693
694    struct ring_state {
695        struct sk_buff *skb;
696        DEFINE_DMA_UNMAP_ADDR(mapping);
697        DEFINE_DMA_UNMAP_LEN(len);
698    };
699
7002) Use dma_unmap_{addr,len}_set to set these values.
701   Example, before:
702
703    ringp->mapping = FOO;
704    ringp->len = BAR;
705
706   after:
707
708    dma_unmap_addr_set(ringp, mapping, FOO);
709    dma_unmap_len_set(ringp, len, BAR);
710
7113) Use dma_unmap_{addr,len} to access these values.
712   Example, before:
713
714    dma_unmap_single(dev, ringp->mapping, ringp->len,
715             DMA_FROM_DEVICE);
716
717   after:
718
719    dma_unmap_single(dev,
720             dma_unmap_addr(ringp, mapping),
721             dma_unmap_len(ringp, len),
722             DMA_FROM_DEVICE);
723
724It really should be self-explanatory. We treat the ADDR and LEN
725separately, because it is possible for an implementation to only
726need the address in order to perform the unmap operation.
727
728            Platform Issues
729
730If you are just writing drivers for Linux and do not maintain
731an architecture port for the kernel, you can safely skip down
732to "Closing".
733
7341) Struct scatterlist requirements.
735
736   Don't invent the architecture specific struct scatterlist; just use
737   <asm-generic/scatterlist.h>. You need to enable
738   CONFIG_NEED_SG_DMA_LENGTH if the architecture supports IOMMUs
739   (including software IOMMU).
740
7412) ARCH_DMA_MINALIGN
742
743   Architectures must ensure that kmalloc'ed buffer is
744   DMA-safe. Drivers and subsystems depend on it. If an architecture
745   isn't fully DMA-coherent (i.e. hardware doesn't ensure that data in
746   the CPU cache is identical to data in main memory),
747   ARCH_DMA_MINALIGN must be set so that the memory allocator
748   makes sure that kmalloc'ed buffer doesn't share a cache line with
749   the others. See arch/arm/include/asm/cache.h as an example.
750
751   Note that ARCH_DMA_MINALIGN is about DMA memory alignment
752   constraints. You don't need to worry about the architecture data
753   alignment constraints (e.g. the alignment constraints about 64-bit
754   objects).
755
7563) Supporting multiple types of IOMMUs
757
758   If your architecture needs to support multiple types of IOMMUs, you
759   can use include/linux/asm-generic/dma-mapping-common.h. It's a
760   library to support the DMA API with multiple types of IOMMUs. Lots
761   of architectures (x86, powerpc, sh, alpha, ia64, microblaze and
762   sparc) use it. Choose one to see how it can be used. If you need to
763   support multiple types of IOMMUs in a single system, the example of
764   x86 or powerpc helps.
765
766               Closing
767
768This document, and the API itself, would not be in its current
769form without the feedback and suggestions from numerous individuals.
770We would like to specifically mention, in no particular order, the
771following people:
772
773    Russell King <rmk@arm.linux.org.uk>
774    Leo Dagum <dagum@barrel.engr.sgi.com>
775    Ralf Baechle <ralf@oss.sgi.com>
776    Grant Grundler <grundler@cup.hp.com>
777    Jay Estabrook <Jay.Estabrook@compaq.com>
778    Thomas Sailer <sailer@ife.ee.ethz.ch>
779    Andrea Arcangeli <andrea@suse.de>
780    Jens Axboe <jens.axboe@oracle.com>
781    David Mosberger-Tang <davidm@hpl.hp.com>
782

Archive Download this file



interactive