1=========================
  2Dynamic DMA mapping Guide
  3=========================
  4
  5:Author: David S. Miller <davem@redhat.com>
  6:Author: Richard Henderson <rth@cygnus.com>
  7:Author: Jakub Jelinek <jakub@redhat.com>
  8
  9This is a guide to device driver writers on how to use the DMA API
 10with example pseudo-code.  For a concise description of the API, see
 11Documentation/core-api/dma-api.rst.
 12
 13CPU and DMA addresses
 14=====================
 15
 16There are several kinds of addresses involved in the DMA API, and it's
 17important to understand the differences.
 18
 19The kernel normally uses virtual addresses.  Any address returned by
 20kmalloc(), vmalloc(), and similar interfaces is a virtual address and can
 21be stored in a ``void *``.
 22
 23The virtual memory system (TLB, page tables, etc.) translates virtual
 24addresses to CPU physical addresses, which are stored as "phys_addr_t" or
 25"resource_size_t".  The kernel manages device resources like registers as
 26physical addresses.  These are the addresses in /proc/iomem.  The physical
 27address is not directly useful to a driver; it must use ioremap() to map
 28the space and produce a virtual address.
 29
 30I/O devices use a third kind of address: a "bus address".  If a device has
 31registers at an MMIO address, or if it performs DMA to read or write system
 32memory, the addresses used by the device are bus addresses.  In some
 33systems, bus addresses are identical to CPU physical addresses, but in
 34general they are not.  IOMMUs and host bridges can produce arbitrary
 35mappings between physical and bus addresses.
 36
 37From a device's point of view, DMA uses the bus address space, but it may
 38be restricted to a subset of that space.  For example, even if a system
 39supports 64-bit addresses for main memory and PCI BARs, it may use an IOMMU
 40so devices only need to use 32-bit DMA addresses.
 41
 42Here's a picture and some examples::
 43
 44               CPU                  CPU                  Bus
 45             Virtual              Physical             Address
 46             Address              Address               Space
 47              Space                Space
 48
 49            +-------+             +------+             +------+
 50            |       |             |MMIO  |   Offset    |      |
 51            |       |  Virtual    |Space |   applied   |      |
 52          C +-------+ --------> B +------+ ----------> +------+ A
 53            |       |  mapping    |      |   by host   |      |
 54  +-----+   |       |             |      |   bridge    |      |   +--------+
 55  |     |   |       |             +------+             |      |   |        |
 56  | CPU |   |       |             | RAM  |             |      |   | Device |
 57  |     |   |       |             |      |             |      |   |        |
 58  +-----+   +-------+             +------+             +------+   +--------+
 59            |       |  Virtual    |Buffer|   Mapping   |      |
 60          X +-------+ --------> Y +------+ <---------- +------+ Z
 61            |       |  mapping    | RAM  |   by IOMMU
 62            |       |             |      |
 63            |       |             |      |
 64            +-------+             +------+
 65
 66During the enumeration process, the kernel learns about I/O devices and
 67their MMIO space and the host bridges that connect them to the system.  For
 68example, if a PCI device has a BAR, the kernel reads the bus address (A)
 69from the BAR and converts it to a CPU physical address (B).  The address B
 70is stored in a struct resource and usually exposed via /proc/iomem.  When a
 71driver claims a device, it typically uses ioremap() to map physical address
 72B at a virtual address (C).  It can then use, e.g., ioread32(C), to access
 73the device registers at bus address A.
 74
 75If the device supports DMA, the driver sets up a buffer using kmalloc() or
 76a similar interface, which returns a virtual address (X).  The virtual
 77memory system maps X to a physical address (Y) in system RAM.  The driver
 78can use virtual address X to access the buffer, but the device itself
 79cannot because DMA doesn't go through the CPU virtual memory system.
 80
 81In some simple systems, the device can do DMA directly to physical address
 82Y.  But in many others, there is IOMMU hardware that translates DMA
 83addresses to physical addresses, e.g., it translates Z to Y.  This is part
 84of the reason for the DMA API: the driver can give a virtual address X to
 85an interface like dma_map_single(), which sets up any required IOMMU
 86mapping and returns the DMA address Z.  The driver then tells the device to
 87do DMA to Z, and the IOMMU maps it to the buffer at address Y in system
 88RAM.
 89
 90So that Linux can use the dynamic DMA mapping, it needs some help from the
 91drivers, namely it has to take into account that DMA addresses should be
 92mapped only for the time they are actually used and unmapped after the DMA
 93transfer.
 94
 95The following API will work of course even on platforms where no such
 96hardware exists.
 97
 98Note that the DMA API works with any bus independent of the underlying
 99microprocessor architecture. You should use the DMA API rather than the
100bus-specific DMA API, i.e., use the dma_map_*() interfaces rather than the
101pci_map_*() interfaces.
102
103First of all, you should make sure::
104
105	#include <linux/dma-mapping.h>
106
107is in your driver, which provides the definition of dma_addr_t.  This type
108can hold any valid DMA address for the platform and should be used
109everywhere you hold a DMA address returned from the DMA mapping functions.
110
111What memory is DMA'able?
112========================
113
114The first piece of information you must know is what kernel memory can
115be used with the DMA mapping facilities.  There has been an unwritten
116set of rules regarding this, and this text is an attempt to finally
117write them down.
118
119If you acquired your memory via the page allocator
120(i.e. __get_free_page*()) or the generic memory allocators
121(i.e. kmalloc() or kmem_cache_alloc()) then you may DMA to/from
122that memory using the addresses returned from those routines.
123
124This means specifically that you may _not_ use the memory/addresses
125returned from vmalloc() for DMA.  It is possible to DMA to the
126_underlying_ memory mapped into a vmalloc() area, but this requires
127walking page tables to get the physical addresses, and then
128translating each of those pages back to a kernel address using
129something like __va().  [ EDIT: Update this when we integrate
130Gerd Knorr's generic code which does this. ]
131
132This rule also means that you may use neither kernel image addresses
133(items in data/text/bss segments), nor module image addresses, nor
134stack addresses for DMA.  These could all be mapped somewhere entirely
135different than the rest of physical memory.  Even if those classes of
136memory could physically work with DMA, you'd need to ensure the I/O
137buffers were cacheline-aligned.  Without that, you'd see cacheline
138sharing problems (data corruption) on CPUs with DMA-incoherent caches.
139(The CPU could write to one word, DMA would write to a different one
140in the same cache line, and one of them could be overwritten.)
141
142Also, this means that you cannot take the return of a kmap()
143call and DMA to/from that.  This is similar to vmalloc().
144
145What about block I/O and networking buffers?  The block I/O and
146networking subsystems make sure that the buffers they use are valid
147for you to DMA from/to.
148
149DMA addressing capabilities
150===========================
151
152By default, the kernel assumes that your device can address 32-bits of DMA
153addressing.  For a 64-bit capable device, this needs to be increased, and for
154a device with limitations, it needs to be decreased.
155
156Special note about PCI: PCI-X specification requires PCI-X devices to support
15764-bit addressing (DAC) for all transactions.  And at least one platform (SGI
158SN2) requires 64-bit consistent allocations to operate correctly when the IO
159bus is in PCI-X mode.
160
161For correct operation, you must set the DMA mask to inform the kernel about
162your devices DMA addressing capabilities.
163
164This is performed via a call to dma_set_mask_and_coherent()::
165
166	int dma_set_mask_and_coherent(struct device *dev, u64 mask);
167
168which will set the mask for both streaming and coherent APIs together.  If you
169have some special requirements, then the following two separate calls can be
170used instead:
171
172	The setup for streaming mappings is performed via a call to
173	dma_set_mask()::
174
175		int dma_set_mask(struct device *dev, u64 mask);
176
177	The setup for consistent allocations is performed via a call
178	to dma_set_coherent_mask()::
179
180		int dma_set_coherent_mask(struct device *dev, u64 mask);
181
182Here, dev is a pointer to the device struct of your device, and mask is a bit
183mask describing which bits of an address your device supports.  Often the
184device struct of your device is embedded in the bus-specific device struct of
185your device.  For example, &pdev->dev is a pointer to the device struct of a
186PCI device (pdev is a pointer to the PCI device struct of your device).
187
188These calls usually return zero to indicate your device can perform DMA
189properly on the machine given the address mask you provided, but they might
190return an error if the mask is too small to be supportable on the given
191system.  If it returns non-zero, your device cannot perform DMA properly on
192this platform, and attempting to do so will result in undefined behavior.
193You must not use DMA on this device unless the dma_set_mask family of
194functions has returned success.
195
196This means that in the failure case, you have two options:
197
1981) Use some non-DMA mode for data transfer, if possible.
1992) Ignore this device and do not initialize it.
200
201It is recommended that your driver print a kernel KERN_WARNING message when
202setting the DMA mask fails.  In this manner, if a user of your driver reports
203that performance is bad or that the device is not even detected, you can ask
204them for the kernel messages to find out exactly why.
205
206The 24-bit addressing device would do something like this::
207
208	if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(24))) {
209		dev_warn(dev, "mydev: No suitable DMA available\n");
210		goto ignore_this_device;
211	}
212
213The standard 64-bit addressing device would do something like this::
214
215	dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64))
216
217dma_set_mask_and_coherent() never return fail when DMA_BIT_MASK(64). Typical
218error code like::
219
220	/* Wrong code */
221	if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)))
222		dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32))
223
224dma_set_mask_and_coherent() will never return failure when bigger than 32.
225So typical code like::
226
227	/* Recommended code */
228	if (support_64bit)
229		dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
230	else
231		dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
232
233If the device only supports 32-bit addressing for descriptors in the
234coherent allocations, but supports full 64-bits for streaming mappings
235it would look like this::
236
237	if (dma_set_mask(dev, DMA_BIT_MASK(64))) {
238		dev_warn(dev, "mydev: No suitable DMA available\n");
239		goto ignore_this_device;
240	}
241
242The coherent mask will always be able to set the same or a smaller mask as
243the streaming mask. However for the rare case that a device driver only
244uses consistent allocations, one would have to check the return value from
245dma_set_coherent_mask().
246
247Finally, if your device can only drive the low 24-bits of
248address you might do something like::
249
250	if (dma_set_mask(dev, DMA_BIT_MASK(24))) {
251		dev_warn(dev, "mydev: 24-bit DMA addressing not available\n");
252		goto ignore_this_device;
253	}
254
255When dma_set_mask() or dma_set_mask_and_coherent() is successful, and
256returns zero, the kernel saves away this mask you have provided.  The
257kernel will use this information later when you make DMA mappings.
258
259There is a case which we are aware of at this time, which is worth
260mentioning in this documentation.  If your device supports multiple
261functions (for example a sound card provides playback and record
262functions) and the various different functions have _different_
263DMA addressing limitations, you may wish to probe each mask and
264only provide the functionality which the machine can handle.  It
265is important that the last call to dma_set_mask() be for the
266most specific mask.
267
268Here is pseudo-code showing how this might be done::
269
270	#define PLAYBACK_ADDRESS_BITS	DMA_BIT_MASK(32)
271	#define RECORD_ADDRESS_BITS	DMA_BIT_MASK(24)
272
273	struct my_sound_card *card;
274	struct device *dev;
275
276	...
277	if (!dma_set_mask(dev, PLAYBACK_ADDRESS_BITS)) {
278		card->playback_enabled = 1;
279	} else {
280		card->playback_enabled = 0;
281		dev_warn(dev, "%s: Playback disabled due to DMA limitations\n",
282		       card->name);
283	}
284	if (!dma_set_mask(dev, RECORD_ADDRESS_BITS)) {
285		card->record_enabled = 1;
286	} else {
287		card->record_enabled = 0;
288		dev_warn(dev, "%s: Record disabled due to DMA limitations\n",
289		       card->name);
290	}
291
292A sound card was used as an example here because this genre of PCI
293devices seems to be littered with ISA chips given a PCI front end,
294and thus retaining the 16MB DMA addressing limitations of ISA.
295
296Types of DMA mappings
297=====================
298
299There are two types of DMA mappings:
300
301- Consistent DMA mappings which are usually mapped at driver
302  initialization, unmapped at the end and for which the hardware should
303  guarantee that the device and the CPU can access the data
304  in parallel and will see updates made by each other without any
305  explicit software flushing.
306
307  Think of "consistent" as "synchronous" or "coherent".
308
309  The current default is to return consistent memory in the low 32
310  bits of the DMA space.  However, for future compatibility you should
311  set the consistent mask even if this default is fine for your
312  driver.
313
314  Good examples of what to use consistent mappings for are:
315
316	- Network card DMA ring descriptors.
317	- SCSI adapter mailbox command data structures.
318	- Device firmware microcode executed out of
319	  main memory.
320
321  The invariant these examples all require is that any CPU store
322  to memory is immediately visible to the device, and vice
323  versa.  Consistent mappings guarantee this.
324
325  .. important::
326
327	     Consistent DMA memory does not preclude the usage of
328	     proper memory barriers.  The CPU may reorder stores to
329	     consistent memory just as it may normal memory.  Example:
330	     if it is important for the device to see the first word
331	     of a descriptor updated before the second, you must do
332	     something like::
333
334		desc->word0 = address;
335		wmb();
336		desc->word1 = DESC_VALID;
337
338             in order to get correct behavior on all platforms.
339
340	     Also, on some platforms your driver may need to flush CPU write
341	     buffers in much the same way as it needs to flush write buffers
342	     found in PCI bridges (such as by reading a register's value
343	     after writing it).
344
345- Streaming DMA mappings which are usually mapped for one DMA
346  transfer, unmapped right after it (unless you use dma_sync_* below)
347  and for which hardware can optimize for sequential accesses.
348
349  Think of "streaming" as "asynchronous" or "outside the coherency
350  domain".
351
352  Good examples of what to use streaming mappings for are:
353
354	- Networking buffers transmitted/received by a device.
355	- Filesystem buffers written/read by a SCSI device.
356
357  The interfaces for using this type of mapping were designed in
358  such a way that an implementation can make whatever performance
359  optimizations the hardware allows.  To this end, when using
360  such mappings you must be explicit about what you want to happen.
361
362Neither type of DMA mapping has alignment restrictions that come from
363the underlying bus, although some devices may have such restrictions.
364Also, systems with caches that aren't DMA-coherent will work better
365when the underlying buffers don't share cache lines with other data.
366
367
368Using Consistent DMA mappings
369=============================
370
371To allocate and map large (PAGE_SIZE or so) consistent DMA regions,
372you should do::
373
374	dma_addr_t dma_handle;
375
376	cpu_addr = dma_alloc_coherent(dev, size, &dma_handle, gfp);
377
378where device is a ``struct device *``. This may be called in interrupt
379context with the GFP_ATOMIC flag.
380
381Size is the length of the region you want to allocate, in bytes.
382
383This routine will allocate RAM for that region, so it acts similarly to
384__get_free_pages() (but takes size instead of a page order).  If your
385driver needs regions sized smaller than a page, you may prefer using
386the dma_pool interface, described below.
387
388The consistent DMA mapping interfaces, will by default return a DMA address
389which is 32-bit addressable.  Even if the device indicates (via the DMA mask)
390that it may address the upper 32-bits, consistent allocation will only
391return > 32-bit addresses for DMA if the consistent DMA mask has been
392explicitly changed via dma_set_coherent_mask().  This is true of the
393dma_pool interface as well.
394
395dma_alloc_coherent() returns two values: the virtual address which you
396can use to access it from the CPU and dma_handle which you pass to the
397card.
398
399The CPU virtual address and the DMA address are both
400guaranteed to be aligned to the smallest PAGE_SIZE order which
401is greater than or equal to the requested size.  This invariant
402exists (for example) to guarantee that if you allocate a chunk
403which is smaller than or equal to 64 kilobytes, the extent of the
404buffer you receive will not cross a 64K boundary.
405
406To unmap and free such a DMA region, you call::
407
408	dma_free_coherent(dev, size, cpu_addr, dma_handle);
409
410where dev, size are the same as in the above call and cpu_addr and
411dma_handle are the values dma_alloc_coherent() returned to you.
412This function may not be called in interrupt context.
413
414If your driver needs lots of smaller memory regions, you can write
415custom code to subdivide pages returned by dma_alloc_coherent(),
416or you can use the dma_pool API to do that.  A dma_pool is like
417a kmem_cache, but it uses dma_alloc_coherent(), not __get_free_pages().
418Also, it understands common hardware constraints for alignment,
419like queue heads needing to be aligned on N byte boundaries.
420
421Create a dma_pool like this::
422
423	struct dma_pool *pool;
424
425	pool = dma_pool_create(name, dev, size, align, boundary);
426
427The "name" is for diagnostics (like a kmem_cache name); dev and size
428are as above.  The device's hardware alignment requirement for this
429type of data is "align" (which is expressed in bytes, and must be a
430power of two).  If your device has no boundary crossing restrictions,
431pass 0 for boundary; passing 4096 says memory allocated from this pool
432must not cross 4KByte boundaries (but at that time it may be better to
433use dma_alloc_coherent() directly instead).
434
435Allocate memory from a DMA pool like this::
436
437	cpu_addr = dma_pool_alloc(pool, flags, &dma_handle);
438
439flags are GFP_KERNEL if blocking is permitted (not in_interrupt nor
440holding SMP locks), GFP_ATOMIC otherwise.  Like dma_alloc_coherent(),
441this returns two values, cpu_addr and dma_handle.
442
443Free memory that was allocated from a dma_pool like this::
444
445	dma_pool_free(pool, cpu_addr, dma_handle);
446
447where pool is what you passed to dma_pool_alloc(), and cpu_addr and
448dma_handle are the values dma_pool_alloc() returned. This function
449may be called in interrupt context.
450
451Destroy a dma_pool by calling::
452
453	dma_pool_destroy(pool);
454
455Make sure you've called dma_pool_free() for all memory allocated
456from a pool before you destroy the pool. This function may not
457be called in interrupt context.
458
459DMA Direction
460=============
461
462The interfaces described in subsequent portions of this document
463take a DMA direction argument, which is an integer and takes on
464one of the following values::
465
466 DMA_BIDIRECTIONAL
467 DMA_TO_DEVICE
468 DMA_FROM_DEVICE
469 DMA_NONE
470
471You should provide the exact DMA direction if you know it.
472
473DMA_TO_DEVICE means "from main memory to the device"
474DMA_FROM_DEVICE means "from the device to main memory"
475It is the direction in which the data moves during the DMA
476transfer.
477
478You are _strongly_ encouraged to specify this as precisely
479as you possibly can.
480
481If you absolutely cannot know the direction of the DMA transfer,
482specify DMA_BIDIRECTIONAL.  It means that the DMA can go in
483either direction.  The platform guarantees that you may legally
484specify this, and that it will work, but this may be at the
485cost of performance for example.
486
487The value DMA_NONE is to be used for debugging.  One can
488hold this in a data structure before you come to know the
489precise direction, and this will help catch cases where your
490direction tracking logic has failed to set things up properly.
491
492Another advantage of specifying this value precisely (outside of
493potential platform-specific optimizations of such) is for debugging.
494Some platforms actually have a write permission boolean which DMA
495mappings can be marked with, much like page protections in the user
496program address space.  Such platforms can and do report errors in the
497kernel logs when the DMA controller hardware detects violation of the
498permission setting.
499
500Only streaming mappings specify a direction, consistent mappings
501implicitly have a direction attribute setting of
502DMA_BIDIRECTIONAL.
503
504The SCSI subsystem tells you the direction to use in the
505'sc_data_direction' member of the SCSI command your driver is
506working on.
507
508For Networking drivers, it's a rather simple affair.  For transmit
509packets, map/unmap them with the DMA_TO_DEVICE direction
510specifier.  For receive packets, just the opposite, map/unmap them
511with the DMA_FROM_DEVICE direction specifier.
512
513Using Streaming DMA mappings
514============================
515
516The streaming DMA mapping routines can be called from interrupt
517context.  There are two versions of each map/unmap, one which will
518map/unmap a single memory region, and one which will map/unmap a
519scatterlist.
520
521To map a single region, you do::
522
523	struct device *dev = &my_dev->dev;
524	dma_addr_t dma_handle;
525	void *addr = buffer->ptr;
526	size_t size = buffer->len;
527
528	dma_handle = dma_map_single(dev, addr, size, direction);
529	if (dma_mapping_error(dev, dma_handle)) {
530		/*
531		 * reduce current DMA mapping usage,
532		 * delay and try again later or
533		 * reset driver.
534		 */
535		goto map_error_handling;
536	}
537
538and to unmap it::
539
540	dma_unmap_single(dev, dma_handle, size, direction);
541
542You should call dma_mapping_error() as dma_map_single() could fail and return
543error.  Doing so will ensure that the mapping code will work correctly on all
544DMA implementations without any dependency on the specifics of the underlying
545implementation. Using the returned address without checking for errors could
546result in failures ranging from panics to silent data corruption.  The same
547applies to dma_map_page() as well.
548
549You should call dma_unmap_single() when the DMA activity is finished, e.g.,
550from the interrupt which told you that the DMA transfer is done.
551
552Using CPU pointers like this for single mappings has a disadvantage:
553you cannot reference HIGHMEM memory in this way.  Thus, there is a
554map/unmap interface pair akin to dma_{map,unmap}_single().  These
555interfaces deal with page/offset pairs instead of CPU pointers.
556Specifically::
557
558	struct device *dev = &my_dev->dev;
559	dma_addr_t dma_handle;
560	struct page *page = buffer->page;
561	unsigned long offset = buffer->offset;
562	size_t size = buffer->len;
563
564	dma_handle = dma_map_page(dev, page, offset, size, direction);
565	if (dma_mapping_error(dev, dma_handle)) {
566		/*
567		 * reduce current DMA mapping usage,
568		 * delay and try again later or
569		 * reset driver.
570		 */
571		goto map_error_handling;
572	}
573
574	...
575
576	dma_unmap_page(dev, dma_handle, size, direction);
577
578Here, "offset" means byte offset within the given page.
579
580You should call dma_mapping_error() as dma_map_page() could fail and return
581error as outlined under the dma_map_single() discussion.
582
583You should call dma_unmap_page() when the DMA activity is finished, e.g.,
584from the interrupt which told you that the DMA transfer is done.
585
586With scatterlists, you map a region gathered from several regions by::
587
588	int i, count = dma_map_sg(dev, sglist, nents, direction);
589	struct scatterlist *sg;
590
591	for_each_sg(sglist, sg, count, i) {
592		hw_address[i] = sg_dma_address(sg);
593		hw_len[i] = sg_dma_len(sg);
594	}
595
596where nents is the number of entries in the sglist.
597
598The implementation is free to merge several consecutive sglist entries
599into one (e.g. if DMA mapping is done with PAGE_SIZE granularity, any
600consecutive sglist entries can be merged into one provided the first one
601ends and the second one starts on a page boundary - in fact this is a huge
602advantage for cards which either cannot do scatter-gather or have very
603limited number of scatter-gather entries) and returns the actual number
604of sg entries it mapped them to. On failure 0 is returned.
605
606Then you should loop count times (note: this can be less than nents times)
607and use sg_dma_address() and sg_dma_len() macros where you previously
608accessed sg->address and sg->length as shown above.
609
610To unmap a scatterlist, just call::
611
612	dma_unmap_sg(dev, sglist, nents, direction);
613
614Again, make sure DMA activity has already finished.
615
616.. note::
617
618	The 'nents' argument to the dma_unmap_sg call must be
619	the _same_ one you passed into the dma_map_sg call,
620	it should _NOT_ be the 'count' value _returned_ from the
621	dma_map_sg call.
622
623Every dma_map_{single,sg}() call should have its dma_unmap_{single,sg}()
624counterpart, because the DMA address space is a shared resource and
625you could render the machine unusable by consuming all DMA addresses.
626
627If you need to use the same streaming DMA region multiple times and touch
628the data in between the DMA transfers, the buffer needs to be synced
629properly in order for the CPU and device to see the most up-to-date and
630correct copy of the DMA buffer.
631
632So, firstly, just map it with dma_map_{single,sg}(), and after each DMA
633transfer call either::
634
635	dma_sync_single_for_cpu(dev, dma_handle, size, direction);
636
637or::
638
639	dma_sync_sg_for_cpu(dev, sglist, nents, direction);
640
641as appropriate.
642
643Then, if you wish to let the device get at the DMA area again,
644finish accessing the data with the CPU, and then before actually
645giving the buffer to the hardware call either::
646
647	dma_sync_single_for_device(dev, dma_handle, size, direction);
648
649or::
650
651	dma_sync_sg_for_device(dev, sglist, nents, direction);
652
653as appropriate.
654
655.. note::
656
657	      The 'nents' argument to dma_sync_sg_for_cpu() and
658	      dma_sync_sg_for_device() must be the same passed to
659	      dma_map_sg(). It is _NOT_ the count returned by
660	      dma_map_sg().
661
662After the last DMA transfer call one of the DMA unmap routines
663dma_unmap_{single,sg}(). If you don't touch the data from the first
664dma_map_*() call till dma_unmap_*(), then you don't have to call the
665dma_sync_*() routines at all.
666
667Here is pseudo code which shows a situation in which you would need
668to use the dma_sync_*() interfaces::
669
670	my_card_setup_receive_buffer(struct my_card *cp, char *buffer, int len)
671	{
672		dma_addr_t mapping;
673
674		mapping = dma_map_single(cp->dev, buffer, len, DMA_FROM_DEVICE);
675		if (dma_mapping_error(cp->dev, mapping)) {
676			/*
677			 * reduce current DMA mapping usage,
678			 * delay and try again later or
679			 * reset driver.
680			 */
681			goto map_error_handling;
682		}
683
684		cp->rx_buf = buffer;
685		cp->rx_len = len;
686		cp->rx_dma = mapping;
687
688		give_rx_buf_to_card(cp);
689	}
690
691	...
692
693	my_card_interrupt_handler(int irq, void *devid, struct pt_regs *regs)
694	{
695		struct my_card *cp = devid;
696
697		...
698		if (read_card_status(cp) == RX_BUF_TRANSFERRED) {
699			struct my_card_header *hp;
700
701			/* Examine the header to see if we wish
702			 * to accept the data.  But synchronize
703			 * the DMA transfer with the CPU first
704			 * so that we see updated contents.
705			 */
706			dma_sync_single_for_cpu(&cp->dev, cp->rx_dma,
707						cp->rx_len,
708						DMA_FROM_DEVICE);
709
710			/* Now it is safe to examine the buffer. */
711			hp = (struct my_card_header *) cp->rx_buf;
712			if (header_is_ok(hp)) {
713				dma_unmap_single(&cp->dev, cp->rx_dma, cp->rx_len,
714						 DMA_FROM_DEVICE);
715				pass_to_upper_layers(cp->rx_buf);
716				make_and_setup_new_rx_buf(cp);
717			} else {
718				/* CPU should not write to
719				 * DMA_FROM_DEVICE-mapped area,
720				 * so dma_sync_single_for_device() is
721				 * not needed here. It would be required
722				 * for DMA_BIDIRECTIONAL mapping if
723				 * the memory was modified.
724				 */
725				give_rx_buf_to_card(cp);
726			}
727		}
728	}
729
730Handling Errors
731===============
732
733DMA address space is limited on some architectures and an allocation
734failure can be determined by:
735
736- checking if dma_alloc_coherent() returns NULL or dma_map_sg returns 0
737
738- checking the dma_addr_t returned from dma_map_single() and dma_map_page()
739  by using dma_mapping_error()::
740
741	dma_addr_t dma_handle;
742
743	dma_handle = dma_map_single(dev, addr, size, direction);
744	if (dma_mapping_error(dev, dma_handle)) {
745		/*
746		 * reduce current DMA mapping usage,
747		 * delay and try again later or
748		 * reset driver.
749		 */
750		goto map_error_handling;
751	}
752
753- unmap pages that are already mapped, when mapping error occurs in the middle
754  of a multiple page mapping attempt. These example are applicable to
755  dma_map_page() as well.
756
757Example 1::
758
759	dma_addr_t dma_handle1;
760	dma_addr_t dma_handle2;
761
762	dma_handle1 = dma_map_single(dev, addr, size, direction);
763	if (dma_mapping_error(dev, dma_handle1)) {
764		/*
765		 * reduce current DMA mapping usage,
766		 * delay and try again later or
767		 * reset driver.
768		 */
769		goto map_error_handling1;
770	}
771	dma_handle2 = dma_map_single(dev, addr, size, direction);
772	if (dma_mapping_error(dev, dma_handle2)) {
773		/*
774		 * reduce current DMA mapping usage,
775		 * delay and try again later or
776		 * reset driver.
777		 */
778		goto map_error_handling2;
779	}
780
781	...
782
783	map_error_handling2:
784		dma_unmap_single(dma_handle1);
785	map_error_handling1:
786
787Example 2::
788
789	/*
790	 * if buffers are allocated in a loop, unmap all mapped buffers when
791	 * mapping error is detected in the middle
792	 */
793
794	dma_addr_t dma_addr;
795	dma_addr_t array[DMA_BUFFERS];
796	int save_index = 0;
797
798	for (i = 0; i < DMA_BUFFERS; i++) {
799
800		...
801
802		dma_addr = dma_map_single(dev, addr, size, direction);
803		if (dma_mapping_error(dev, dma_addr)) {
804			/*
805			 * reduce current DMA mapping usage,
806			 * delay and try again later or
807			 * reset driver.
808			 */
809			goto map_error_handling;
810		}
811		array[i].dma_addr = dma_addr;
812		save_index++;
813	}
814
815	...
816
817	map_error_handling:
818
819	for (i = 0; i < save_index; i++) {
820
821		...
822
823		dma_unmap_single(array[i].dma_addr);
824	}
825
826Networking drivers must call dev_kfree_skb() to free the socket buffer
827and return NETDEV_TX_OK if the DMA mapping fails on the transmit hook
828(ndo_start_xmit). This means that the socket buffer is just dropped in
829the failure case.
830
831SCSI drivers must return SCSI_MLQUEUE_HOST_BUSY if the DMA mapping
832fails in the queuecommand hook. This means that the SCSI subsystem
833passes the command to the driver again later.
834
835Optimizing Unmap State Space Consumption
836========================================
837
838On many platforms, dma_unmap_{single,page}() is simply a nop.
839Therefore, keeping track of the mapping address and length is a waste
840of space.  Instead of filling your drivers up with ifdefs and the like
841to "work around" this (which would defeat the whole purpose of a
842portable API) the following facilities are provided.
843
844Actually, instead of describing the macros one by one, we'll
845transform some example code.
846
8471) Use DEFINE_DMA_UNMAP_{ADDR,LEN} in state saving structures.
848   Example, before::
849
850	struct ring_state {
851		struct sk_buff *skb;
852		dma_addr_t mapping;
853		__u32 len;
854	};
855
856   after::
857
858	struct ring_state {
859		struct sk_buff *skb;
860		DEFINE_DMA_UNMAP_ADDR(mapping);
861		DEFINE_DMA_UNMAP_LEN(len);
862	};
863
8642) Use dma_unmap_{addr,len}_set() to set these values.
865   Example, before::
866
867	ringp->mapping = FOO;
868	ringp->len = BAR;
869
870   after::
871
872	dma_unmap_addr_set(ringp, mapping, FOO);
873	dma_unmap_len_set(ringp, len, BAR);
874
8753) Use dma_unmap_{addr,len}() to access these values.
876   Example, before::
877
878	dma_unmap_single(dev, ringp->mapping, ringp->len,
879			 DMA_FROM_DEVICE);
880
881   after::
882
883	dma_unmap_single(dev,
884			 dma_unmap_addr(ringp, mapping),
885			 dma_unmap_len(ringp, len),
886			 DMA_FROM_DEVICE);
887
888It really should be self-explanatory.  We treat the ADDR and LEN
889separately, because it is possible for an implementation to only
890need the address in order to perform the unmap operation.
891
892Platform Issues
893===============
894
895If you are just writing drivers for Linux and do not maintain
896an architecture port for the kernel, you can safely skip down
897to "Closing".
898
8991) Struct scatterlist requirements.
900
901   You need to enable CONFIG_NEED_SG_DMA_LENGTH if the architecture
902   supports IOMMUs (including software IOMMU).
903
9042) ARCH_DMA_MINALIGN
905
906   Architectures must ensure that kmalloc'ed buffer is
907   DMA-safe. Drivers and subsystems depend on it. If an architecture
908   isn't fully DMA-coherent (i.e. hardware doesn't ensure that data in
909   the CPU cache is identical to data in main memory),
910   ARCH_DMA_MINALIGN must be set so that the memory allocator
911   makes sure that kmalloc'ed buffer doesn't share a cache line with
912   the others. See arch/arm/include/asm/cache.h as an example.
913
914   Note that ARCH_DMA_MINALIGN is about DMA memory alignment
915   constraints. You don't need to worry about the architecture data
916   alignment constraints (e.g. the alignment constraints about 64-bit
917   objects).
918
919Closing
920=======
921
922This document, and the API itself, would not be in its current
923form without the feedback and suggestions from numerous individuals.
924We would like to specifically mention, in no particular order, the
925following people::
926
927	Russell King <rmk@arm.linux.org.uk>
928	Leo Dagum <dagum@barrel.engr.sgi.com>
929	Ralf Baechle <ralf@oss.sgi.com>
930	Grant Grundler <grundler@cup.hp.com>
931	Jay Estabrook <Jay.Estabrook@compaq.com>
932	Thomas Sailer <sailer@ife.ee.ethz.ch>
933	Andrea Arcangeli <andrea@suse.de>
934	Jens Axboe <jens.axboe@oracle.com>
935	David Mosberger-Tang <davidm@hpl.hp.com>