About Kernel Documentation Linux Kernel Contact Linux Resources Linux Blog

Documentation / DMA-API.txt

Custom Search

Based on kernel version 4.7.2. Page generated on 2016-08-22 22:44 EST.

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

Information is copyright its respective author. All material is available from the Linux Kernel Source distributed under a GPL License. This page is provided as a free service by mjmwired.net.