Loading...
1 Dynamic DMA mapping using the generic device
2 ============================================
3
4 James E.J. Bottomley <James.Bottomley@HansenPartnership.com>
5
6This document describes the DMA API. For a more gentle introduction
7of the API (and actual examples) see
8Documentation/DMA-API-HOWTO.txt.
9
10This API is split into two pieces. Part I describes the API. Part II
11describes the extensions to the API for supporting non-consistent
12memory machines. Unless you know that your driver absolutely has to
13support non-consistent platforms (this is usually only legacy
14platforms) you should only use the API described in part I.
15
16Part I - dma_ API
17-------------------------------------
18
19To get the dma_ API, you must #include <linux/dma-mapping.h>
20
21
22Part Ia - Using large dma-coherent buffers
23------------------------------------------
24
25void *
26dma_alloc_coherent(struct device *dev, size_t size,
27 dma_addr_t *dma_handle, gfp_t flag)
28
29Consistent memory is memory for which a write by either the device or
30the processor can immediately be read by the processor or device
31without having to worry about caching effects. (You may however need
32to make sure to flush the processor's write buffers before telling
33devices to read that memory.)
34
35This routine allocates a region of <size> bytes of consistent memory.
36It also returns a <dma_handle> which may be cast to an unsigned
37integer the same width as the bus and used as the physical address
38base of the region.
39
40Returns: a pointer to the allocated region (in the processor's virtual
41address space) or NULL if the allocation failed.
42
43Note: consistent memory can be expensive on some platforms, and the
44minimum allocation length may be as big as a page, so you should
45consolidate your requests for consistent memory as much as possible.
46The simplest way to do that is to use the dma_pool calls (see below).
47
48The flag parameter (dma_alloc_coherent only) allows the caller to
49specify the GFP_ flags (see kmalloc) for the allocation (the
50implementation may choose to ignore flags that affect the location of
51the returned memory, like GFP_DMA).
52
53void
54dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
55 dma_addr_t dma_handle)
56
57Free the region of consistent memory you previously allocated. dev,
58size and dma_handle must all be the same as those passed into the
59consistent allocate. cpu_addr must be the virtual address returned by
60the consistent allocate.
61
62Note that unlike their sibling allocation calls, these routines
63may only be called with IRQs enabled.
64
65
66Part Ib - Using small dma-coherent buffers
67------------------------------------------
68
69To get this part of the dma_ API, you must #include <linux/dmapool.h>
70
71Many drivers need lots of small dma-coherent memory regions for DMA
72descriptors or I/O buffers. Rather than allocating in units of a page
73or more using dma_alloc_coherent(), you can use DMA pools. These work
74much like a struct kmem_cache, except that they use the dma-coherent allocator,
75not __get_free_pages(). Also, they understand common hardware constraints
76for alignment, like queue heads needing to be aligned on N-byte boundaries.
77
78
79 struct dma_pool *
80 dma_pool_create(const char *name, struct device *dev,
81 size_t size, size_t align, size_t alloc);
82
83The pool create() routines initialize a pool of dma-coherent buffers
84for use with a given device. It must be called in a context which
85can sleep.
86
87The "name" is for diagnostics (like a struct kmem_cache name); dev and size
88are like what you'd pass to dma_alloc_coherent(). The device's hardware
89alignment requirement for this type of data is "align" (which is expressed
90in bytes, and must be a power of two). If your device has no boundary
91crossing restrictions, pass 0 for alloc; passing 4096 says memory allocated
92from this pool must not cross 4KByte boundaries.
93
94
95 void *dma_pool_alloc(struct dma_pool *pool, gfp_t gfp_flags,
96 dma_addr_t *dma_handle);
97
98This allocates memory from the pool; the returned memory will meet the size
99and alignment requirements specified at creation time. Pass GFP_ATOMIC to
100prevent blocking, or if it's permitted (not in_interrupt, not holding SMP locks),
101pass GFP_KERNEL to allow blocking. Like dma_alloc_coherent(), this returns
102two values: an address usable by the cpu, and the dma address usable by the
103pool's device.
104
105
106 void dma_pool_free(struct dma_pool *pool, void *vaddr,
107 dma_addr_t addr);
108
109This puts memory back into the pool. The pool is what was passed to
110the pool allocation routine; the cpu (vaddr) and dma addresses are what
111were returned when that routine allocated the memory being freed.
112
113
114 void dma_pool_destroy(struct dma_pool *pool);
115
116The pool destroy() routines free the resources of the pool. They must be
117called in a context which can sleep. Make sure you've freed all allocated
118memory back to the pool before you destroy it.
119
120
121Part Ic - DMA addressing limitations
122------------------------------------
123
124int
125dma_supported(struct device *dev, u64 mask)
126
127Checks to see if the device can support DMA to the memory described by
128mask.
129
130Returns: 1 if it can and 0 if it can't.
131
132Notes: This routine merely tests to see if the mask is possible. It
133won't change the current mask settings. It is more intended as an
134internal API for use by the platform than an external API for use by
135driver writers.
136
137int
138dma_set_mask(struct device *dev, u64 mask)
139
140Checks to see if the mask is possible and updates the device
141parameters if it is.
142
143Returns: 0 if successful and a negative error if not.
144
145int
146dma_set_coherent_mask(struct device *dev, u64 mask)
147
148Checks to see if the mask is possible and updates the device
149parameters if it is.
150
151Returns: 0 if successful and a negative error if not.
152
153u64
154dma_get_required_mask(struct device *dev)
155
156This API returns the mask that the platform requires to
157operate efficiently. Usually this means the returned mask
158is the minimum required to cover all of memory. Examining the
159required mask gives drivers with variable descriptor sizes the
160opportunity to use smaller descriptors as necessary.
161
162Requesting the required mask does not alter the current mask. If you
163wish to take advantage of it, you should issue a dma_set_mask()
164call to set the mask to the value returned.
165
166
167Part Id - Streaming DMA mappings
168--------------------------------
169
170dma_addr_t
171dma_map_single(struct device *dev, void *cpu_addr, size_t size,
172 enum dma_data_direction direction)
173
174Maps a piece of processor virtual memory so it can be accessed by the
175device and returns the physical handle of the memory.
176
177The direction for both api's may be converted freely by casting.
178However the dma_ API uses a strongly typed enumerator for its
179direction:
180
181DMA_NONE no direction (used for debugging)
182DMA_TO_DEVICE data is going from the memory to the device
183DMA_FROM_DEVICE data is coming from the device to the memory
184DMA_BIDIRECTIONAL direction isn't known
185
186Notes: Not all memory regions in a machine can be mapped by this
187API. Further, regions that appear to be physically contiguous in
188kernel virtual space may not be contiguous as physical memory. Since
189this API does not provide any scatter/gather capability, it will fail
190if the user tries to map a non-physically contiguous piece of memory.
191For this reason, it is recommended that memory mapped by this API be
192obtained only from sources which guarantee it to be physically contiguous
193(like kmalloc).
194
195Further, the physical address of the memory must be within the
196dma_mask of the device (the dma_mask represents a bit mask of the
197addressable region for the device. I.e., if the physical address of
198the memory anded with the dma_mask is still equal to the physical
199address, then the device can perform DMA to the memory). In order to
200ensure that the memory allocated by kmalloc is within the dma_mask,
201the driver may specify various platform-dependent flags to restrict
202the physical memory range of the allocation (e.g. on x86, GFP_DMA
203guarantees to be within the first 16Mb of available physical memory,
204as required by ISA devices).
205
206Note also that the above constraints on physical contiguity and
207dma_mask may not apply if the platform has an IOMMU (a device which
208supplies a physical to virtual mapping between the I/O memory bus and
209the device). However, to be portable, device driver writers may *not*
210assume that such an IOMMU exists.
211
212Warnings: Memory coherency operates at a granularity called the cache
213line width. In order for memory mapped by this API to operate
214correctly, the mapped region must begin exactly on a cache line
215boundary and end exactly on one (to prevent two separately mapped
216regions from sharing a single cache line). Since the cache line size
217may not be known at compile time, the API will not enforce this
218requirement. Therefore, it is recommended that driver writers who
219don't take special care to determine the cache line size at run time
220only map virtual regions that begin and end on page boundaries (which
221are guaranteed also to be cache line boundaries).
222
223DMA_TO_DEVICE synchronisation must be done after the last modification
224of the memory region by the software and before it is handed off to
225the driver. Once this primitive is used, memory covered by this
226primitive should be treated as read-only by the device. If the device
227may write to it at any point, it should be DMA_BIDIRECTIONAL (see
228below).
229
230DMA_FROM_DEVICE synchronisation must be done before the driver
231accesses data that may be changed by the device. This memory should
232be treated as read-only by the driver. If the driver needs to write
233to it at any point, it should be DMA_BIDIRECTIONAL (see below).
234
235DMA_BIDIRECTIONAL requires special handling: it means that the driver
236isn't sure if the memory was modified before being handed off to the
237device and also isn't sure if the device will also modify it. Thus,
238you must always sync bidirectional memory twice: once before the
239memory is handed off to the device (to make sure all memory changes
240are flushed from the processor) and once before the data may be
241accessed after being used by the device (to make sure any processor
242cache lines are updated with data that the device may have changed).
243
244void
245dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
246 enum dma_data_direction direction)
247
248Unmaps the region previously mapped. All the parameters passed in
249must be identical to those passed in (and returned) by the mapping
250API.
251
252dma_addr_t
253dma_map_page(struct device *dev, struct page *page,
254 unsigned long offset, size_t size,
255 enum dma_data_direction direction)
256void
257dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
258 enum dma_data_direction direction)
259
260API for mapping and unmapping for pages. All the notes and warnings
261for the other mapping APIs apply here. Also, although the <offset>
262and <size> parameters are provided to do partial page mapping, it is
263recommended that you never use these unless you really know what the
264cache width is.
265
266int
267dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
268
269In some circumstances dma_map_single and dma_map_page will fail to create
270a mapping. A driver can check for these errors by testing the returned
271dma address with dma_mapping_error(). A non-zero return value means the mapping
272could not be created and the driver should take appropriate action (e.g.
273reduce current DMA mapping usage or delay and try again later).
274
275 int
276 dma_map_sg(struct device *dev, struct scatterlist *sg,
277 int nents, enum dma_data_direction direction)
278
279Returns: the number of physical segments mapped (this may be shorter
280than <nents> passed in if some elements of the scatter/gather list are
281physically or virtually adjacent and an IOMMU maps them with a single
282entry).
283
284Please note that the sg cannot be mapped again if it has been mapped once.
285The mapping process is allowed to destroy information in the sg.
286
287As with the other mapping interfaces, dma_map_sg can fail. When it
288does, 0 is returned and a driver must take appropriate action. It is
289critical that the driver do something, in the case of a block driver
290aborting the request or even oopsing is better than doing nothing and
291corrupting the filesystem.
292
293With scatterlists, you use the resulting mapping like this:
294
295 int i, count = dma_map_sg(dev, sglist, nents, direction);
296 struct scatterlist *sg;
297
298 for_each_sg(sglist, sg, count, i) {
299 hw_address[i] = sg_dma_address(sg);
300 hw_len[i] = sg_dma_len(sg);
301 }
302
303where nents is the number of entries in the sglist.
304
305The implementation is free to merge several consecutive sglist entries
306into one (e.g. with an IOMMU, or if several pages just happen to be
307physically contiguous) and returns the actual number of sg entries it
308mapped them to. On failure 0, is returned.
309
310Then you should loop count times (note: this can be less than nents times)
311and use sg_dma_address() and sg_dma_len() macros where you previously
312accessed sg->address and sg->length as shown above.
313
314 void
315 dma_unmap_sg(struct device *dev, struct scatterlist *sg,
316 int nhwentries, enum dma_data_direction direction)
317
318Unmap the previously mapped scatter/gather list. All the parameters
319must be the same as those and passed in to the scatter/gather mapping
320API.
321
322Note: <nents> must be the number you passed in, *not* the number of
323physical entries returned.
324
325void
326dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size,
327 enum dma_data_direction direction)
328void
329dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t size,
330 enum dma_data_direction direction)
331void
332dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
333 enum dma_data_direction direction)
334void
335dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems,
336 enum dma_data_direction direction)
337
338Synchronise a single contiguous or scatter/gather mapping for the cpu
339and device. With the sync_sg API, all the parameters must be the same
340as those passed into the single mapping API. With the sync_single API,
341you can use dma_handle and size parameters that aren't identical to
342those passed into the single mapping API to do a partial sync.
343
344Notes: You must do this:
345
346- Before reading values that have been written by DMA from the device
347 (use the DMA_FROM_DEVICE direction)
348- After writing values that will be written to the device using DMA
349 (use the DMA_TO_DEVICE) direction
350- before *and* after handing memory to the device if the memory is
351 DMA_BIDIRECTIONAL
352
353See also dma_map_single().
354
355dma_addr_t
356dma_map_single_attrs(struct device *dev, void *cpu_addr, size_t size,
357 enum dma_data_direction dir,
358 struct dma_attrs *attrs)
359
360void
361dma_unmap_single_attrs(struct device *dev, dma_addr_t dma_addr,
362 size_t size, enum dma_data_direction dir,
363 struct dma_attrs *attrs)
364
365int
366dma_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
367 int nents, enum dma_data_direction dir,
368 struct dma_attrs *attrs)
369
370void
371dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sgl,
372 int nents, enum dma_data_direction dir,
373 struct dma_attrs *attrs)
374
375The four functions above are just like the counterpart functions
376without the _attrs suffixes, except that they pass an optional
377struct dma_attrs*.
378
379struct dma_attrs encapsulates a set of "dma attributes". For the
380definition of struct dma_attrs see linux/dma-attrs.h.
381
382The interpretation of dma attributes is architecture-specific, and
383each attribute should be documented in Documentation/DMA-attributes.txt.
384
385If struct dma_attrs* is NULL, the semantics of each of these
386functions is identical to those of the corresponding function
387without the _attrs suffix. As a result dma_map_single_attrs()
388can generally replace dma_map_single(), etc.
389
390As an example of the use of the *_attrs functions, here's how
391you could pass an attribute DMA_ATTR_FOO when mapping memory
392for DMA:
393
394#include <linux/dma-attrs.h>
395/* DMA_ATTR_FOO should be defined in linux/dma-attrs.h and
396 * documented in Documentation/DMA-attributes.txt */
397...
398
399 DEFINE_DMA_ATTRS(attrs);
400 dma_set_attr(DMA_ATTR_FOO, &attrs);
401 ....
402 n = dma_map_sg_attrs(dev, sg, nents, DMA_TO_DEVICE, &attr);
403 ....
404
405Architectures that care about DMA_ATTR_FOO would check for its
406presence in their implementations of the mapping and unmapping
407routines, e.g.:
408
409void whizco_dma_map_sg_attrs(struct device *dev, dma_addr_t dma_addr,
410 size_t size, enum dma_data_direction dir,
411 struct dma_attrs *attrs)
412{
413 ....
414 int foo = dma_get_attr(DMA_ATTR_FOO, attrs);
415 ....
416 if (foo)
417 /* twizzle the frobnozzle */
418 ....
419
420
421Part II - Advanced dma_ usage
422-----------------------------
423
424Warning: These pieces of the DMA API should not be used in the
425majority of cases, since they cater for unlikely corner cases that
426don't belong in usual drivers.
427
428If you don't understand how cache line coherency works between a
429processor and an I/O device, you should not be using this part of the
430API at all.
431
432void *
433dma_alloc_noncoherent(struct device *dev, size_t size,
434 dma_addr_t *dma_handle, gfp_t flag)
435
436Identical to dma_alloc_coherent() except that the platform will
437choose to return either consistent or non-consistent memory as it sees
438fit. By using this API, you are guaranteeing to the platform that you
439have all the correct and necessary sync points for this memory in the
440driver should it choose to return non-consistent memory.
441
442Note: where the platform can return consistent memory, it will
443guarantee that the sync points become nops.
444
445Warning: Handling non-consistent memory is a real pain. You should
446only ever use this API if you positively know your driver will be
447required to work on one of the rare (usually non-PCI) architectures
448that simply cannot make consistent memory.
449
450void
451dma_free_noncoherent(struct device *dev, size_t size, void *cpu_addr,
452 dma_addr_t dma_handle)
453
454Free memory allocated by the nonconsistent API. All parameters must
455be identical to those passed in (and returned by
456dma_alloc_noncoherent()).
457
458int
459dma_get_cache_alignment(void)
460
461Returns the processor cache alignment. This is the absolute minimum
462alignment *and* width that you must observe when either mapping
463memory or doing partial flushes.
464
465Notes: This API may return a number *larger* than the actual cache
466line, but it will guarantee that one or more cache lines fit exactly
467into the width returned by this call. It will also always be a power
468of two for easy alignment.
469
470void
471dma_cache_sync(struct device *dev, void *vaddr, size_t size,
472 enum dma_data_direction direction)
473
474Do a partial sync of memory that was allocated by
475dma_alloc_noncoherent(), starting at virtual address vaddr and
476continuing on for size. Again, you *must* observe the cache line
477boundaries when doing this.
478
479int
480dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
481 dma_addr_t device_addr, size_t size, int
482 flags)
483
484Declare region of memory to be handed out by dma_alloc_coherent when
485it's asked for coherent memory for this device.
486
487bus_addr is the physical address to which the memory is currently
488assigned in the bus responding region (this will be used by the
489platform to perform the mapping).
490
491device_addr is the physical address the device needs to be programmed
492with actually to address this memory (this will be handed out as the
493dma_addr_t in dma_alloc_coherent()).
494
495size is the size of the area (must be multiples of PAGE_SIZE).
496
497flags can be or'd together and are:
498
499DMA_MEMORY_MAP - request that the memory returned from
500dma_alloc_coherent() be directly writable.
501
502DMA_MEMORY_IO - request that the memory returned from
503dma_alloc_coherent() be addressable using read/write/memcpy_toio etc.
504
505One or both of these flags must be present.
506
507DMA_MEMORY_INCLUDES_CHILDREN - make the declared memory be allocated by
508dma_alloc_coherent of any child devices of this one (for memory residing
509on a bridge).
510
511DMA_MEMORY_EXCLUSIVE - only allocate memory from the declared regions.
512Do not allow dma_alloc_coherent() to fall back to system memory when
513it's out of memory in the declared region.
514
515The return value will be either DMA_MEMORY_MAP or DMA_MEMORY_IO and
516must correspond to a passed in flag (i.e. no returning DMA_MEMORY_IO
517if only DMA_MEMORY_MAP were passed in) for success or zero for
518failure.
519
520Note, for DMA_MEMORY_IO returns, all subsequent memory returned by
521dma_alloc_coherent() may no longer be accessed directly, but instead
522must be accessed using the correct bus functions. If your driver
523isn't prepared to handle this contingency, it should not specify
524DMA_MEMORY_IO in the input flags.
525
526As a simplification for the platforms, only *one* such region of
527memory may be declared per device.
528
529For reasons of efficiency, most platforms choose to track the declared
530region only at the granularity of a page. For smaller allocations,
531you should use the dma_pool() API.
532
533void
534dma_release_declared_memory(struct device *dev)
535
536Remove the memory region previously declared from the system. This
537API performs *no* in-use checking for this region and will return
538unconditionally having removed all the required structures. It is the
539driver's job to ensure that no parts of this memory region are
540currently in use.
541
542void *
543dma_mark_declared_memory_occupied(struct device *dev,
544 dma_addr_t device_addr, size_t size)
545
546This is used to occupy specific regions of the declared space
547(dma_alloc_coherent() will hand out the first free region it finds).
548
549device_addr is the *device* address of the region requested.
550
551size is the size (and should be a page-sized multiple).
552
553The return value will be either a pointer to the processor virtual
554address of the memory, or an error (via PTR_ERR()) if any part of the
555region is occupied.
556
557Part III - Debug drivers use of the DMA-API
558-------------------------------------------
559
560The DMA-API as described above as some constraints. DMA addresses must be
561released with the corresponding function with the same size for example. With
562the advent of hardware IOMMUs it becomes more and more important that drivers
563do not violate those constraints. In the worst case such a violation can
564result in data corruption up to destroyed filesystems.
565
566To debug drivers and find bugs in the usage of the DMA-API checking code can
567be compiled into the kernel which will tell the developer about those
568violations. If your architecture supports it you can select the "Enable
569debugging of DMA-API usage" option in your kernel configuration. Enabling this
570option has a performance impact. Do not enable it in production kernels.
571
572If you boot the resulting kernel will contain code which does some bookkeeping
573about what DMA memory was allocated for which device. If this code detects an
574error it prints a warning message with some details into your kernel log. An
575example warning message may look like this:
576
577------------[ cut here ]------------
578WARNING: at /data2/repos/linux-2.6-iommu/lib/dma-debug.c:448
579 check_unmap+0x203/0x490()
580Hardware name:
581forcedeth 0000:00:08.0: DMA-API: device driver frees DMA memory with wrong
582 function [device address=0x00000000640444be] [size=66 bytes] [mapped as
583single] [unmapped as page]
584Modules linked in: nfsd exportfs bridge stp llc r8169
585Pid: 0, comm: swapper Tainted: G W 2.6.28-dmatest-09289-g8bb99c0 #1
586Call Trace:
587 <IRQ> [<ffffffff80240b22>] warn_slowpath+0xf2/0x130
588 [<ffffffff80647b70>] _spin_unlock+0x10/0x30
589 [<ffffffff80537e75>] usb_hcd_link_urb_to_ep+0x75/0xc0
590 [<ffffffff80647c22>] _spin_unlock_irqrestore+0x12/0x40
591 [<ffffffff8055347f>] ohci_urb_enqueue+0x19f/0x7c0
592 [<ffffffff80252f96>] queue_work+0x56/0x60
593 [<ffffffff80237e10>] enqueue_task_fair+0x20/0x50
594 [<ffffffff80539279>] usb_hcd_submit_urb+0x379/0xbc0
595 [<ffffffff803b78c3>] cpumask_next_and+0x23/0x40
596 [<ffffffff80235177>] find_busiest_group+0x207/0x8a0
597 [<ffffffff8064784f>] _spin_lock_irqsave+0x1f/0x50
598 [<ffffffff803c7ea3>] check_unmap+0x203/0x490
599 [<ffffffff803c8259>] debug_dma_unmap_page+0x49/0x50
600 [<ffffffff80485f26>] nv_tx_done_optimized+0xc6/0x2c0
601 [<ffffffff80486c13>] nv_nic_irq_optimized+0x73/0x2b0
602 [<ffffffff8026df84>] handle_IRQ_event+0x34/0x70
603 [<ffffffff8026ffe9>] handle_edge_irq+0xc9/0x150
604 [<ffffffff8020e3ab>] do_IRQ+0xcb/0x1c0
605 [<ffffffff8020c093>] ret_from_intr+0x0/0xa
606 <EOI> <4>---[ end trace f6435a98e2a38c0e ]---
607
608The driver developer can find the driver and the device including a stacktrace
609of the DMA-API call which caused this warning.
610
611Per default only the first error will result in a warning message. All other
612errors will only silently counted. This limitation exist to prevent the code
613from flooding your kernel log. To support debugging a device driver this can
614be disabled via debugfs. See the debugfs interface documentation below for
615details.
616
617The debugfs directory for the DMA-API debugging code is called dma-api/. In
618this directory the following files can currently be found:
619
620 dma-api/all_errors This file contains a numeric value. If this
621 value is not equal to zero the debugging code
622 will print a warning for every error it finds
623 into the kernel log. Be careful with this
624 option, as it can easily flood your logs.
625
626 dma-api/disabled This read-only file contains the character 'Y'
627 if the debugging code is disabled. This can
628 happen when it runs out of memory or if it was
629 disabled at boot time
630
631 dma-api/error_count This file is read-only and shows the total
632 numbers of errors found.
633
634 dma-api/num_errors The number in this file shows how many
635 warnings will be printed to the kernel log
636 before it stops. This number is initialized to
637 one at system boot and be set by writing into
638 this file
639
640 dma-api/min_free_entries
641 This read-only file can be read to get the
642 minimum number of free dma_debug_entries the
643 allocator has ever seen. If this value goes
644 down to zero the code will disable itself
645 because it is not longer reliable.
646
647 dma-api/num_free_entries
648 The current number of free dma_debug_entries
649 in the allocator.
650
651 dma-api/driver-filter
652 You can write a name of a driver into this file
653 to limit the debug output to requests from that
654 particular driver. Write an empty string to
655 that file to disable the filter and see
656 all errors again.
657
658If you have this code compiled into your kernel it will be enabled by default.
659If you want to boot without the bookkeeping anyway you can provide
660'dma_debug=off' as a boot parameter. This will disable DMA-API debugging.
661Notice that you can not enable it again at runtime. You have to reboot to do
662so.
663
664If you want to see debug messages only for a special device driver you can
665specify the dma_debug_driver=<drivername> parameter. This will enable the
666driver filter at boot time. The debug code will only print errors for that
667driver afterwards. This filter can be disabled or changed later using debugfs.
668
669When the code disables itself at runtime this is most likely because it ran
670out of dma_debug_entries. These entries are preallocated at boot. The number
671of preallocated entries is defined per architecture. If it is too low for you
672boot with 'dma_debug_entries=<your_desired_number>' to overwrite the
673architectural default.
1 Dynamic DMA mapping using the generic device
2 ============================================
3
4 James E.J. Bottomley <James.Bottomley@HansenPartnership.com>
5
6This document describes the DMA API. For a more gentle introduction
7of the API (and actual examples) see
8Documentation/DMA-API-HOWTO.txt.
9
10This API is split into two pieces. Part I describes the API. Part II
11describes the extensions to the API for supporting non-consistent
12memory machines. Unless you know that your driver absolutely has to
13support non-consistent platforms (this is usually only legacy
14platforms) you should only use the API described in part I.
15
16Part I - dma_ API
17-------------------------------------
18
19To get the dma_ API, you must #include <linux/dma-mapping.h>
20
21
22Part Ia - Using large dma-coherent buffers
23------------------------------------------
24
25void *
26dma_alloc_coherent(struct device *dev, size_t size,
27 dma_addr_t *dma_handle, gfp_t flag)
28
29Consistent memory is memory for which a write by either the device or
30the processor can immediately be read by the processor or device
31without having to worry about caching effects. (You may however need
32to make sure to flush the processor's write buffers before telling
33devices to read that memory.)
34
35This routine allocates a region of <size> bytes of consistent memory.
36It also returns a <dma_handle> which may be cast to an unsigned
37integer the same width as the bus and used as the physical address
38base of the region.
39
40Returns: a pointer to the allocated region (in the processor's virtual
41address space) or NULL if the allocation failed.
42
43Note: consistent memory can be expensive on some platforms, and the
44minimum allocation length may be as big as a page, so you should
45consolidate your requests for consistent memory as much as possible.
46The simplest way to do that is to use the dma_pool calls (see below).
47
48The flag parameter (dma_alloc_coherent only) allows the caller to
49specify the GFP_ flags (see kmalloc) for the allocation (the
50implementation may choose to ignore flags that affect the location of
51the returned memory, like GFP_DMA).
52
53void *
54dma_zalloc_coherent(struct device *dev, size_t size,
55 dma_addr_t *dma_handle, gfp_t flag)
56
57Wraps dma_alloc_coherent() and also zeroes the returned memory if the
58allocation attempt succeeded.
59
60void
61dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
62 dma_addr_t dma_handle)
63
64Free the region of consistent memory you previously allocated. dev,
65size and dma_handle must all be the same as those passed into the
66consistent allocate. cpu_addr must be the virtual address returned by
67the consistent allocate.
68
69Note that unlike their sibling allocation calls, these routines
70may only be called with IRQs enabled.
71
72
73Part Ib - Using small dma-coherent buffers
74------------------------------------------
75
76To get this part of the dma_ API, you must #include <linux/dmapool.h>
77
78Many drivers need lots of small dma-coherent memory regions for DMA
79descriptors or I/O buffers. Rather than allocating in units of a page
80or more using dma_alloc_coherent(), you can use DMA pools. These work
81much like a struct kmem_cache, except that they use the dma-coherent allocator,
82not __get_free_pages(). Also, they understand common hardware constraints
83for alignment, like queue heads needing to be aligned on N-byte boundaries.
84
85
86 struct dma_pool *
87 dma_pool_create(const char *name, struct device *dev,
88 size_t size, size_t align, size_t alloc);
89
90The pool create() routines initialize a pool of dma-coherent buffers
91for use with a given device. It must be called in a context which
92can sleep.
93
94The "name" is for diagnostics (like a struct kmem_cache name); dev and size
95are like what you'd pass to dma_alloc_coherent(). The device's hardware
96alignment requirement for this type of data is "align" (which is expressed
97in bytes, and must be a power of two). If your device has no boundary
98crossing restrictions, pass 0 for alloc; passing 4096 says memory allocated
99from this pool must not cross 4KByte boundaries.
100
101
102 void *dma_pool_alloc(struct dma_pool *pool, gfp_t gfp_flags,
103 dma_addr_t *dma_handle);
104
105This allocates memory from the pool; the returned memory will meet the size
106and alignment requirements specified at creation time. Pass GFP_ATOMIC to
107prevent blocking, or if it's permitted (not in_interrupt, not holding SMP locks),
108pass GFP_KERNEL to allow blocking. Like dma_alloc_coherent(), this returns
109two values: an address usable by the cpu, and the dma address usable by the
110pool's device.
111
112
113 void dma_pool_free(struct dma_pool *pool, void *vaddr,
114 dma_addr_t addr);
115
116This puts memory back into the pool. The pool is what was passed to
117the pool allocation routine; the cpu (vaddr) and dma addresses are what
118were returned when that routine allocated the memory being freed.
119
120
121 void dma_pool_destroy(struct dma_pool *pool);
122
123The pool destroy() routines free the resources of the pool. They must be
124called in a context which can sleep. Make sure you've freed all allocated
125memory back to the pool before you destroy it.
126
127
128Part Ic - DMA addressing limitations
129------------------------------------
130
131int
132dma_supported(struct device *dev, u64 mask)
133
134Checks to see if the device can support DMA to the memory described by
135mask.
136
137Returns: 1 if it can and 0 if it can't.
138
139Notes: This routine merely tests to see if the mask is possible. It
140won't change the current mask settings. It is more intended as an
141internal API for use by the platform than an external API for use by
142driver writers.
143
144int
145dma_set_mask_and_coherent(struct device *dev, u64 mask)
146
147Checks to see if the mask is possible and updates the device
148streaming and coherent DMA mask parameters if it is.
149
150Returns: 0 if successful and a negative error if not.
151
152int
153dma_set_mask(struct device *dev, u64 mask)
154
155Checks to see if the mask is possible and updates the device
156parameters if it is.
157
158Returns: 0 if successful and a negative error if not.
159
160int
161dma_set_coherent_mask(struct device *dev, u64 mask)
162
163Checks to see if the mask is possible and updates the device
164parameters if it is.
165
166Returns: 0 if successful and a negative error if not.
167
168u64
169dma_get_required_mask(struct device *dev)
170
171This API returns the mask that the platform requires to
172operate efficiently. Usually this means the returned mask
173is the minimum required to cover all of memory. Examining the
174required mask gives drivers with variable descriptor sizes the
175opportunity to use smaller descriptors as necessary.
176
177Requesting the required mask does not alter the current mask. If you
178wish to take advantage of it, you should issue a dma_set_mask()
179call to set the mask to the value returned.
180
181
182Part Id - Streaming DMA mappings
183--------------------------------
184
185dma_addr_t
186dma_map_single(struct device *dev, void *cpu_addr, size_t size,
187 enum dma_data_direction direction)
188
189Maps a piece of processor virtual memory so it can be accessed by the
190device and returns the physical handle of the memory.
191
192The direction for both api's may be converted freely by casting.
193However the dma_ API uses a strongly typed enumerator for its
194direction:
195
196DMA_NONE no direction (used for debugging)
197DMA_TO_DEVICE data is going from the memory to the device
198DMA_FROM_DEVICE data is coming from the device to the memory
199DMA_BIDIRECTIONAL direction isn't known
200
201Notes: Not all memory regions in a machine can be mapped by this
202API. Further, regions that appear to be physically contiguous in
203kernel virtual space may not be contiguous as physical memory. Since
204this API does not provide any scatter/gather capability, it will fail
205if the user tries to map a non-physically contiguous piece of memory.
206For this reason, it is recommended that memory mapped by this API be
207obtained only from sources which guarantee it to be physically contiguous
208(like kmalloc).
209
210Further, the physical address of the memory must be within the
211dma_mask of the device (the dma_mask represents a bit mask of the
212addressable region for the device. I.e., if the physical address of
213the memory anded with the dma_mask is still equal to the physical
214address, then the device can perform DMA to the memory). In order to
215ensure that the memory allocated by kmalloc is within the dma_mask,
216the driver may specify various platform-dependent flags to restrict
217the physical memory range of the allocation (e.g. on x86, GFP_DMA
218guarantees to be within the first 16Mb of available physical memory,
219as required by ISA devices).
220
221Note also that the above constraints on physical contiguity and
222dma_mask may not apply if the platform has an IOMMU (a device which
223supplies a physical to virtual mapping between the I/O memory bus and
224the device). However, to be portable, device driver writers may *not*
225assume that such an IOMMU exists.
226
227Warnings: Memory coherency operates at a granularity called the cache
228line width. In order for memory mapped by this API to operate
229correctly, the mapped region must begin exactly on a cache line
230boundary and end exactly on one (to prevent two separately mapped
231regions from sharing a single cache line). Since the cache line size
232may not be known at compile time, the API will not enforce this
233requirement. Therefore, it is recommended that driver writers who
234don't take special care to determine the cache line size at run time
235only map virtual regions that begin and end on page boundaries (which
236are guaranteed also to be cache line boundaries).
237
238DMA_TO_DEVICE synchronisation must be done after the last modification
239of the memory region by the software and before it is handed off to
240the driver. Once this primitive is used, memory covered by this
241primitive should be treated as read-only by the device. If the device
242may write to it at any point, it should be DMA_BIDIRECTIONAL (see
243below).
244
245DMA_FROM_DEVICE synchronisation must be done before the driver
246accesses data that may be changed by the device. This memory should
247be treated as read-only by the driver. If the driver needs to write
248to it at any point, it should be DMA_BIDIRECTIONAL (see below).
249
250DMA_BIDIRECTIONAL requires special handling: it means that the driver
251isn't sure if the memory was modified before being handed off to the
252device and also isn't sure if the device will also modify it. Thus,
253you must always sync bidirectional memory twice: once before the
254memory is handed off to the device (to make sure all memory changes
255are flushed from the processor) and once before the data may be
256accessed after being used by the device (to make sure any processor
257cache lines are updated with data that the device may have changed).
258
259void
260dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
261 enum dma_data_direction direction)
262
263Unmaps the region previously mapped. All the parameters passed in
264must be identical to those passed in (and returned) by the mapping
265API.
266
267dma_addr_t
268dma_map_page(struct device *dev, struct page *page,
269 unsigned long offset, size_t size,
270 enum dma_data_direction direction)
271void
272dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
273 enum dma_data_direction direction)
274
275API for mapping and unmapping for pages. All the notes and warnings
276for the other mapping APIs apply here. Also, although the <offset>
277and <size> parameters are provided to do partial page mapping, it is
278recommended that you never use these unless you really know what the
279cache width is.
280
281int
282dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
283
284In some circumstances dma_map_single and dma_map_page will fail to create
285a mapping. A driver can check for these errors by testing the returned
286dma address with dma_mapping_error(). A non-zero return value means the mapping
287could not be created and the driver should take appropriate action (e.g.
288reduce current DMA mapping usage or delay and try again later).
289
290 int
291 dma_map_sg(struct device *dev, struct scatterlist *sg,
292 int nents, enum dma_data_direction direction)
293
294Returns: the number of physical segments mapped (this may be shorter
295than <nents> passed in if some elements of the scatter/gather list are
296physically or virtually adjacent and an IOMMU maps them with a single
297entry).
298
299Please note that the sg cannot be mapped again if it has been mapped once.
300The mapping process is allowed to destroy information in the sg.
301
302As with the other mapping interfaces, dma_map_sg can fail. When it
303does, 0 is returned and a driver must take appropriate action. It is
304critical that the driver do something, in the case of a block driver
305aborting the request or even oopsing is better than doing nothing and
306corrupting the filesystem.
307
308With scatterlists, you use the resulting mapping like this:
309
310 int i, count = dma_map_sg(dev, sglist, nents, direction);
311 struct scatterlist *sg;
312
313 for_each_sg(sglist, sg, count, i) {
314 hw_address[i] = sg_dma_address(sg);
315 hw_len[i] = sg_dma_len(sg);
316 }
317
318where nents is the number of entries in the sglist.
319
320The implementation is free to merge several consecutive sglist entries
321into one (e.g. with an IOMMU, or if several pages just happen to be
322physically contiguous) and returns the actual number of sg entries it
323mapped them to. On failure 0, is returned.
324
325Then you should loop count times (note: this can be less than nents times)
326and use sg_dma_address() and sg_dma_len() macros where you previously
327accessed sg->address and sg->length as shown above.
328
329 void
330 dma_unmap_sg(struct device *dev, struct scatterlist *sg,
331 int nhwentries, enum dma_data_direction direction)
332
333Unmap the previously mapped scatter/gather list. All the parameters
334must be the same as those and passed in to the scatter/gather mapping
335API.
336
337Note: <nents> must be the number you passed in, *not* the number of
338physical entries returned.
339
340void
341dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size,
342 enum dma_data_direction direction)
343void
344dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t size,
345 enum dma_data_direction direction)
346void
347dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
348 enum dma_data_direction direction)
349void
350dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems,
351 enum dma_data_direction direction)
352
353Synchronise a single contiguous or scatter/gather mapping for the cpu
354and device. With the sync_sg API, all the parameters must be the same
355as those passed into the single mapping API. With the sync_single API,
356you can use dma_handle and size parameters that aren't identical to
357those passed into the single mapping API to do a partial sync.
358
359Notes: You must do this:
360
361- Before reading values that have been written by DMA from the device
362 (use the DMA_FROM_DEVICE direction)
363- After writing values that will be written to the device using DMA
364 (use the DMA_TO_DEVICE) direction
365- before *and* after handing memory to the device if the memory is
366 DMA_BIDIRECTIONAL
367
368See also dma_map_single().
369
370dma_addr_t
371dma_map_single_attrs(struct device *dev, void *cpu_addr, size_t size,
372 enum dma_data_direction dir,
373 struct dma_attrs *attrs)
374
375void
376dma_unmap_single_attrs(struct device *dev, dma_addr_t dma_addr,
377 size_t size, enum dma_data_direction dir,
378 struct dma_attrs *attrs)
379
380int
381dma_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
382 int nents, enum dma_data_direction dir,
383 struct dma_attrs *attrs)
384
385void
386dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sgl,
387 int nents, enum dma_data_direction dir,
388 struct dma_attrs *attrs)
389
390The four functions above are just like the counterpart functions
391without the _attrs suffixes, except that they pass an optional
392struct dma_attrs*.
393
394struct dma_attrs encapsulates a set of "dma attributes". For the
395definition of struct dma_attrs see linux/dma-attrs.h.
396
397The interpretation of dma attributes is architecture-specific, and
398each attribute should be documented in Documentation/DMA-attributes.txt.
399
400If struct dma_attrs* is NULL, the semantics of each of these
401functions is identical to those of the corresponding function
402without the _attrs suffix. As a result dma_map_single_attrs()
403can generally replace dma_map_single(), etc.
404
405As an example of the use of the *_attrs functions, here's how
406you could pass an attribute DMA_ATTR_FOO when mapping memory
407for DMA:
408
409#include <linux/dma-attrs.h>
410/* DMA_ATTR_FOO should be defined in linux/dma-attrs.h and
411 * documented in Documentation/DMA-attributes.txt */
412...
413
414 DEFINE_DMA_ATTRS(attrs);
415 dma_set_attr(DMA_ATTR_FOO, &attrs);
416 ....
417 n = dma_map_sg_attrs(dev, sg, nents, DMA_TO_DEVICE, &attr);
418 ....
419
420Architectures that care about DMA_ATTR_FOO would check for its
421presence in their implementations of the mapping and unmapping
422routines, e.g.:
423
424void whizco_dma_map_sg_attrs(struct device *dev, dma_addr_t dma_addr,
425 size_t size, enum dma_data_direction dir,
426 struct dma_attrs *attrs)
427{
428 ....
429 int foo = dma_get_attr(DMA_ATTR_FOO, attrs);
430 ....
431 if (foo)
432 /* twizzle the frobnozzle */
433 ....
434
435
436Part II - Advanced dma_ usage
437-----------------------------
438
439Warning: These pieces of the DMA API should not be used in the
440majority of cases, since they cater for unlikely corner cases that
441don't belong in usual drivers.
442
443If you don't understand how cache line coherency works between a
444processor and an I/O device, you should not be using this part of the
445API at all.
446
447void *
448dma_alloc_noncoherent(struct device *dev, size_t size,
449 dma_addr_t *dma_handle, gfp_t flag)
450
451Identical to dma_alloc_coherent() except that the platform will
452choose to return either consistent or non-consistent memory as it sees
453fit. By using this API, you are guaranteeing to the platform that you
454have all the correct and necessary sync points for this memory in the
455driver should it choose to return non-consistent memory.
456
457Note: where the platform can return consistent memory, it will
458guarantee that the sync points become nops.
459
460Warning: Handling non-consistent memory is a real pain. You should
461only ever use this API if you positively know your driver will be
462required to work on one of the rare (usually non-PCI) architectures
463that simply cannot make consistent memory.
464
465void
466dma_free_noncoherent(struct device *dev, size_t size, void *cpu_addr,
467 dma_addr_t dma_handle)
468
469Free memory allocated by the nonconsistent API. All parameters must
470be identical to those passed in (and returned by
471dma_alloc_noncoherent()).
472
473int
474dma_get_cache_alignment(void)
475
476Returns the processor cache alignment. This is the absolute minimum
477alignment *and* width that you must observe when either mapping
478memory or doing partial flushes.
479
480Notes: This API may return a number *larger* than the actual cache
481line, but it will guarantee that one or more cache lines fit exactly
482into the width returned by this call. It will also always be a power
483of two for easy alignment.
484
485void
486dma_cache_sync(struct device *dev, void *vaddr, size_t size,
487 enum dma_data_direction direction)
488
489Do a partial sync of memory that was allocated by
490dma_alloc_noncoherent(), starting at virtual address vaddr and
491continuing on for size. Again, you *must* observe the cache line
492boundaries when doing this.
493
494int
495dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
496 dma_addr_t device_addr, size_t size, int
497 flags)
498
499Declare region of memory to be handed out by dma_alloc_coherent when
500it's asked for coherent memory for this device.
501
502bus_addr is the physical address to which the memory is currently
503assigned in the bus responding region (this will be used by the
504platform to perform the mapping).
505
506device_addr is the physical address the device needs to be programmed
507with actually to address this memory (this will be handed out as the
508dma_addr_t in dma_alloc_coherent()).
509
510size is the size of the area (must be multiples of PAGE_SIZE).
511
512flags can be or'd together and are:
513
514DMA_MEMORY_MAP - request that the memory returned from
515dma_alloc_coherent() be directly writable.
516
517DMA_MEMORY_IO - request that the memory returned from
518dma_alloc_coherent() be addressable using read/write/memcpy_toio etc.
519
520One or both of these flags must be present.
521
522DMA_MEMORY_INCLUDES_CHILDREN - make the declared memory be allocated by
523dma_alloc_coherent of any child devices of this one (for memory residing
524on a bridge).
525
526DMA_MEMORY_EXCLUSIVE - only allocate memory from the declared regions.
527Do not allow dma_alloc_coherent() to fall back to system memory when
528it's out of memory in the declared region.
529
530The return value will be either DMA_MEMORY_MAP or DMA_MEMORY_IO and
531must correspond to a passed in flag (i.e. no returning DMA_MEMORY_IO
532if only DMA_MEMORY_MAP were passed in) for success or zero for
533failure.
534
535Note, for DMA_MEMORY_IO returns, all subsequent memory returned by
536dma_alloc_coherent() may no longer be accessed directly, but instead
537must be accessed using the correct bus functions. If your driver
538isn't prepared to handle this contingency, it should not specify
539DMA_MEMORY_IO in the input flags.
540
541As a simplification for the platforms, only *one* such region of
542memory may be declared per device.
543
544For reasons of efficiency, most platforms choose to track the declared
545region only at the granularity of a page. For smaller allocations,
546you should use the dma_pool() API.
547
548void
549dma_release_declared_memory(struct device *dev)
550
551Remove the memory region previously declared from the system. This
552API performs *no* in-use checking for this region and will return
553unconditionally having removed all the required structures. It is the
554driver's job to ensure that no parts of this memory region are
555currently in use.
556
557void *
558dma_mark_declared_memory_occupied(struct device *dev,
559 dma_addr_t device_addr, size_t size)
560
561This is used to occupy specific regions of the declared space
562(dma_alloc_coherent() will hand out the first free region it finds).
563
564device_addr is the *device* address of the region requested.
565
566size is the size (and should be a page-sized multiple).
567
568The return value will be either a pointer to the processor virtual
569address of the memory, or an error (via PTR_ERR()) if any part of the
570region is occupied.
571
572Part III - Debug drivers use of the DMA-API
573-------------------------------------------
574
575The DMA-API as described above as some constraints. DMA addresses must be
576released with the corresponding function with the same size for example. With
577the advent of hardware IOMMUs it becomes more and more important that drivers
578do not violate those constraints. In the worst case such a violation can
579result in data corruption up to destroyed filesystems.
580
581To debug drivers and find bugs in the usage of the DMA-API checking code can
582be compiled into the kernel which will tell the developer about those
583violations. If your architecture supports it you can select the "Enable
584debugging of DMA-API usage" option in your kernel configuration. Enabling this
585option has a performance impact. Do not enable it in production kernels.
586
587If you boot the resulting kernel will contain code which does some bookkeeping
588about what DMA memory was allocated for which device. If this code detects an
589error it prints a warning message with some details into your kernel log. An
590example warning message may look like this:
591
592------------[ cut here ]------------
593WARNING: at /data2/repos/linux-2.6-iommu/lib/dma-debug.c:448
594 check_unmap+0x203/0x490()
595Hardware name:
596forcedeth 0000:00:08.0: DMA-API: device driver frees DMA memory with wrong
597 function [device address=0x00000000640444be] [size=66 bytes] [mapped as
598single] [unmapped as page]
599Modules linked in: nfsd exportfs bridge stp llc r8169
600Pid: 0, comm: swapper Tainted: G W 2.6.28-dmatest-09289-g8bb99c0 #1
601Call Trace:
602 <IRQ> [<ffffffff80240b22>] warn_slowpath+0xf2/0x130
603 [<ffffffff80647b70>] _spin_unlock+0x10/0x30
604 [<ffffffff80537e75>] usb_hcd_link_urb_to_ep+0x75/0xc0
605 [<ffffffff80647c22>] _spin_unlock_irqrestore+0x12/0x40
606 [<ffffffff8055347f>] ohci_urb_enqueue+0x19f/0x7c0
607 [<ffffffff80252f96>] queue_work+0x56/0x60
608 [<ffffffff80237e10>] enqueue_task_fair+0x20/0x50
609 [<ffffffff80539279>] usb_hcd_submit_urb+0x379/0xbc0
610 [<ffffffff803b78c3>] cpumask_next_and+0x23/0x40
611 [<ffffffff80235177>] find_busiest_group+0x207/0x8a0
612 [<ffffffff8064784f>] _spin_lock_irqsave+0x1f/0x50
613 [<ffffffff803c7ea3>] check_unmap+0x203/0x490
614 [<ffffffff803c8259>] debug_dma_unmap_page+0x49/0x50
615 [<ffffffff80485f26>] nv_tx_done_optimized+0xc6/0x2c0
616 [<ffffffff80486c13>] nv_nic_irq_optimized+0x73/0x2b0
617 [<ffffffff8026df84>] handle_IRQ_event+0x34/0x70
618 [<ffffffff8026ffe9>] handle_edge_irq+0xc9/0x150
619 [<ffffffff8020e3ab>] do_IRQ+0xcb/0x1c0
620 [<ffffffff8020c093>] ret_from_intr+0x0/0xa
621 <EOI> <4>---[ end trace f6435a98e2a38c0e ]---
622
623The driver developer can find the driver and the device including a stacktrace
624of the DMA-API call which caused this warning.
625
626Per default only the first error will result in a warning message. All other
627errors will only silently counted. This limitation exist to prevent the code
628from flooding your kernel log. To support debugging a device driver this can
629be disabled via debugfs. See the debugfs interface documentation below for
630details.
631
632The debugfs directory for the DMA-API debugging code is called dma-api/. In
633this directory the following files can currently be found:
634
635 dma-api/all_errors This file contains a numeric value. If this
636 value is not equal to zero the debugging code
637 will print a warning for every error it finds
638 into the kernel log. Be careful with this
639 option, as it can easily flood your logs.
640
641 dma-api/disabled This read-only file contains the character 'Y'
642 if the debugging code is disabled. This can
643 happen when it runs out of memory or if it was
644 disabled at boot time
645
646 dma-api/error_count This file is read-only and shows the total
647 numbers of errors found.
648
649 dma-api/num_errors The number in this file shows how many
650 warnings will be printed to the kernel log
651 before it stops. This number is initialized to
652 one at system boot and be set by writing into
653 this file
654
655 dma-api/min_free_entries
656 This read-only file can be read to get the
657 minimum number of free dma_debug_entries the
658 allocator has ever seen. If this value goes
659 down to zero the code will disable itself
660 because it is not longer reliable.
661
662 dma-api/num_free_entries
663 The current number of free dma_debug_entries
664 in the allocator.
665
666 dma-api/driver-filter
667 You can write a name of a driver into this file
668 to limit the debug output to requests from that
669 particular driver. Write an empty string to
670 that file to disable the filter and see
671 all errors again.
672
673If you have this code compiled into your kernel it will be enabled by default.
674If you want to boot without the bookkeeping anyway you can provide
675'dma_debug=off' as a boot parameter. This will disable DMA-API debugging.
676Notice that you can not enable it again at runtime. You have to reboot to do
677so.
678
679If you want to see debug messages only for a special device driver you can
680specify the dma_debug_driver=<drivername> parameter. This will enable the
681driver filter at boot time. The debug code will only print errors for that
682driver afterwards. This filter can be disabled or changed later using debugfs.
683
684When the code disables itself at runtime this is most likely because it ran
685out of dma_debug_entries. These entries are preallocated at boot. The number
686of preallocated entries is defined per architecture. If it is too low for you
687boot with 'dma_debug_entries=<your_desired_number>' to overwrite the
688architectural default.
689
690void debug_dmap_mapping_error(struct device *dev, dma_addr_t dma_addr);
691
692dma-debug interface debug_dma_mapping_error() to debug drivers that fail
693to check dma mapping errors on addresses returned by dma_map_single() and
694dma_map_page() interfaces. This interface clears a flag set by
695debug_dma_map_page() to indicate that dma_mapping_error() has been called by
696the driver. When driver does unmap, debug_dma_unmap() checks the flag and if
697this flag is still set, prints warning message that includes call trace that
698leads up to the unmap. This interface can be called from dma_mapping_error()
699routines to enable dma mapping error check debugging.
700