Version:  2.0.40 2.2.26 2.4.37 3.11 3.12 3.13 3.14 3.15 3.16 3.17 3.18 3.19 4.0 4.1 4.2 4.3 4.4 4.5 4.6 4.7 4.8


  1                Dynamic DMA mapping using the generic device
  2                ============================================
  4         James E.J. Bottomley <>
  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                      unsigned long 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                        unsigned long attrs)
379 int
380 dma_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
381                  int nents, enum dma_data_direction dir,
382                  unsigned long attrs)
384 void
385 dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sgl,
386                    int nents, enum dma_data_direction dir,
387                    unsigned long attrs)
389 The four functions above are just like the counterpart functions
390 without the _attrs suffixes, except that they pass an optional
391 dma_attrs.
393 The interpretation of DMA attributes is architecture-specific, and
394 each attribute should be documented in Documentation/DMA-attributes.txt.
396 If dma_attrs are 0, the semantics of each of these functions
397 is identical to those of the corresponding function
398 without the _attrs suffix. As a result dma_map_single_attrs()
399 can generally replace dma_map_single(), etc.
401 As an example of the use of the *_attrs functions, here's how
402 you could pass an attribute DMA_ATTR_FOO when mapping memory
403 for DMA:
405 #include <linux/dma-mapping.h>
406 /* DMA_ATTR_FOO should be defined in linux/dma-mapping.h and
407  * documented in Documentation/DMA-attributes.txt */
408 ...
410         unsigned long attr;
411         attr |= DMA_ATTR_FOO;
412         ....
413         n = dma_map_sg_attrs(dev, sg, nents, DMA_TO_DEVICE, attr);
414         ....
416 Architectures that care about DMA_ATTR_FOO would check for its
417 presence in their implementations of the mapping and unmapping
418 routines, e.g.:
420 void whizco_dma_map_sg_attrs(struct device *dev, dma_addr_t dma_addr,
421                              size_t size, enum dma_data_direction dir,
422                              unsigned long attrs)
423 {
424         ....
425         if (attrs & DMA_ATTR_FOO)
426                 /* twizzle the frobnozzle */
427         ....
430 Part II - Advanced dma_ usage
431 -----------------------------
433 Warning: These pieces of the DMA API should not be used in the
434 majority of cases, since they cater for unlikely corner cases that
435 don't belong in usual drivers.
437 If you don't understand how cache line coherency works between a
438 processor and an I/O device, you should not be using this part of the
439 API at all.
441 void *
442 dma_alloc_noncoherent(struct device *dev, size_t size,
443                                dma_addr_t *dma_handle, gfp_t flag)
445 Identical to dma_alloc_coherent() except that the platform will
446 choose to return either consistent or non-consistent memory as it sees
447 fit.  By using this API, you are guaranteeing to the platform that you
448 have all the correct and necessary sync points for this memory in the
449 driver should it choose to return non-consistent memory.
451 Note: where the platform can return consistent memory, it will
452 guarantee that the sync points become nops.
454 Warning:  Handling non-consistent memory is a real pain.  You should
455 only use this API if you positively know your driver will be
456 required to work on one of the rare (usually non-PCI) architectures
457 that simply cannot make consistent memory.
459 void
460 dma_free_noncoherent(struct device *dev, size_t size, void *cpu_addr,
461                               dma_addr_t dma_handle)
463 Free memory allocated by the nonconsistent API.  All parameters must
464 be identical to those passed in (and returned by
465 dma_alloc_noncoherent()).
467 int
468 dma_get_cache_alignment(void)
470 Returns the processor cache alignment.  This is the absolute minimum
471 alignment *and* width that you must observe when either mapping
472 memory or doing partial flushes.
474 Notes: This API may return a number *larger* than the actual cache
475 line, but it will guarantee that one or more cache lines fit exactly
476 into the width returned by this call.  It will also always be a power
477 of two for easy alignment.
479 void
480 dma_cache_sync(struct device *dev, void *vaddr, size_t size,
481                enum dma_data_direction direction)
483 Do a partial sync of memory that was allocated by
484 dma_alloc_noncoherent(), starting at virtual address vaddr and
485 continuing on for size.  Again, you *must* observe the cache line
486 boundaries when doing this.
488 int
489 dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
490                             dma_addr_t device_addr, size_t size, int
491                             flags)
493 Declare region of memory to be handed out by dma_alloc_coherent() when
494 it's asked for coherent memory for this device.
496 phys_addr is the CPU physical address to which the memory is currently
497 assigned (this will be ioremapped so the CPU can access the region).
499 device_addr is the DMA address the device needs to be programmed
500 with to actually address this memory (this will be handed out as the
501 dma_addr_t in dma_alloc_coherent()).
503 size is the size of the area (must be multiples of PAGE_SIZE).
505 flags can be ORed together and are:
507 DMA_MEMORY_MAP - request that the memory returned from
508 dma_alloc_coherent() be directly writable.
510 DMA_MEMORY_IO - request that the memory returned from
511 dma_alloc_coherent() be addressable using read()/write()/memcpy_toio() etc.
513 One or both of these flags must be present.
515 DMA_MEMORY_INCLUDES_CHILDREN - make the declared memory be allocated by
516 dma_alloc_coherent of any child devices of this one (for memory residing
517 on a bridge).
519 DMA_MEMORY_EXCLUSIVE - only allocate memory from the declared regions. 
520 Do not allow dma_alloc_coherent() to fall back to system memory when
521 it's out of memory in the declared region.
523 The return value will be either DMA_MEMORY_MAP or DMA_MEMORY_IO and
524 must correspond to a passed in flag (i.e. no returning DMA_MEMORY_IO
525 if only DMA_MEMORY_MAP were passed in) for success or zero for
526 failure.
528 Note, for DMA_MEMORY_IO returns, all subsequent memory returned by
529 dma_alloc_coherent() may no longer be accessed directly, but instead
530 must be accessed using the correct bus functions.  If your driver
531 isn't prepared to handle this contingency, it should not specify
532 DMA_MEMORY_IO in the input flags.
534 As a simplification for the platforms, only *one* such region of
535 memory may be declared per device.
537 For reasons of efficiency, most platforms choose to track the declared
538 region only at the granularity of a page.  For smaller allocations,
539 you should use the dma_pool() API.
541 void
542 dma_release_declared_memory(struct device *dev)
544 Remove the memory region previously declared from the system.  This
545 API performs *no* in-use checking for this region and will return
546 unconditionally having removed all the required structures.  It is the
547 driver's job to ensure that no parts of this memory region are
548 currently in use.
550 void *
551 dma_mark_declared_memory_occupied(struct device *dev,
552                                   dma_addr_t device_addr, size_t size)
554 This is used to occupy specific regions of the declared space
555 (dma_alloc_coherent() will hand out the first free region it finds).
557 device_addr is the *device* address of the region requested.
559 size is the size (and should be a page-sized multiple).
561 The return value will be either a pointer to the processor virtual
562 address of the memory, or an error (via PTR_ERR()) if any part of the
563 region is occupied.
565 Part III - Debug drivers use of the DMA-API
566 -------------------------------------------
568 The DMA-API as described above has some constraints. DMA addresses must be
569 released with the corresponding function with the same size for example. With
570 the advent of hardware IOMMUs it becomes more and more important that drivers
571 do not violate those constraints. In the worst case such a violation can
572 result in data corruption up to destroyed filesystems.
574 To debug drivers and find bugs in the usage of the DMA-API checking code can
575 be compiled into the kernel which will tell the developer about those
576 violations. If your architecture supports it you can select the "Enable
577 debugging of DMA-API usage" option in your kernel configuration. Enabling this
578 option has a performance impact. Do not enable it in production kernels.
580 If you boot the resulting kernel will contain code which does some bookkeeping
581 about what DMA memory was allocated for which device. If this code detects an
582 error it prints a warning message with some details into your kernel log. An
583 example warning message may look like this:
585 ------------[ cut here ]------------
586 WARNING: at /data2/repos/linux-2.6-iommu/lib/dma-debug.c:448
587         check_unmap+0x203/0x490()
588 Hardware name:
589 forcedeth 0000:00:08.0: DMA-API: device driver frees DMA memory with wrong
590         function [device address=0x00000000640444be] [size=66 bytes] [mapped as
591 single] [unmapped as page]
592 Modules linked in: nfsd exportfs bridge stp llc r8169
593 Pid: 0, comm: swapper Tainted: G        W  2.6.28-dmatest-09289-g8bb99c0 #1
594 Call Trace:
595  <IRQ>  [<ffffffff80240b22>] warn_slowpath+0xf2/0x130
596  [<ffffffff80647b70>] _spin_unlock+0x10/0x30
597  [<ffffffff80537e75>] usb_hcd_link_urb_to_ep+0x75/0xc0
598  [<ffffffff80647c22>] _spin_unlock_irqrestore+0x12/0x40
599  [<ffffffff8055347f>] ohci_urb_enqueue+0x19f/0x7c0
600  [<ffffffff80252f96>] queue_work+0x56/0x60
601  [<ffffffff80237e10>] enqueue_task_fair+0x20/0x50
602  [<ffffffff80539279>] usb_hcd_submit_urb+0x379/0xbc0
603  [<ffffffff803b78c3>] cpumask_next_and+0x23/0x40
604  [<ffffffff80235177>] find_busiest_group+0x207/0x8a0
605  [<ffffffff8064784f>] _spin_lock_irqsave+0x1f/0x50
606  [<ffffffff803c7ea3>] check_unmap+0x203/0x490
607  [<ffffffff803c8259>] debug_dma_unmap_page+0x49/0x50
608  [<ffffffff80485f26>] nv_tx_done_optimized+0xc6/0x2c0
609  [<ffffffff80486c13>] nv_nic_irq_optimized+0x73/0x2b0
610  [<ffffffff8026df84>] handle_IRQ_event+0x34/0x70
611  [<ffffffff8026ffe9>] handle_edge_irq+0xc9/0x150
612  [<ffffffff8020e3ab>] do_IRQ+0xcb/0x1c0
613  [<ffffffff8020c093>] ret_from_intr+0x0/0xa
614  <EOI> <4>---[ end trace f6435a98e2a38c0e ]---
616 The driver developer can find the driver and the device including a stacktrace
617 of the DMA-API call which caused this warning.
619 Per default only the first error will result in a warning message. All other
620 errors will only silently counted. This limitation exist to prevent the code
621 from flooding your kernel log. To support debugging a device driver this can
622 be disabled via debugfs. See the debugfs interface documentation below for
623 details.
625 The debugfs directory for the DMA-API debugging code is called dma-api/. In
626 this directory the following files can currently be found:
628         dma-api/all_errors      This file contains a numeric value. If this
629                                 value is not equal to zero the debugging code
630                                 will print a warning for every error it finds
631                                 into the kernel log. Be careful with this
632                                 option, as it can easily flood your logs.
634         dma-api/disabled        This read-only file contains the character 'Y'
635                                 if the debugging code is disabled. This can
636                                 happen when it runs out of memory or if it was
637                                 disabled at boot time
639         dma-api/error_count     This file is read-only and shows the total
640                                 numbers of errors found.
642         dma-api/num_errors      The number in this file shows how many
643                                 warnings will be printed to the kernel log
644                                 before it stops. This number is initialized to
645                                 one at system boot and be set by writing into
646                                 this file
648         dma-api/min_free_entries
649                                 This read-only file can be read to get the
650                                 minimum number of free dma_debug_entries the
651                                 allocator has ever seen. If this value goes
652                                 down to zero the code will disable itself
653                                 because it is not longer reliable.
655         dma-api/num_free_entries
656                                 The current number of free dma_debug_entries
657                                 in the allocator.
659         dma-api/driver-filter
660                                 You can write a name of a driver into this file
661                                 to limit the debug output to requests from that
662                                 particular driver. Write an empty string to
663                                 that file to disable the filter and see
664                                 all errors again.
666 If you have this code compiled into your kernel it will be enabled by default.
667 If you want to boot without the bookkeeping anyway you can provide
668 'dma_debug=off' as a boot parameter. This will disable DMA-API debugging.
669 Notice that you can not enable it again at runtime. You have to reboot to do
670 so.
672 If you want to see debug messages only for a special device driver you can
673 specify the dma_debug_driver=<drivername> parameter. This will enable the
674 driver filter at boot time. The debug code will only print errors for that
675 driver afterwards. This filter can be disabled or changed later using debugfs.
677 When the code disables itself at runtime this is most likely because it ran
678 out of dma_debug_entries. These entries are preallocated at boot. The number
679 of preallocated entries is defined per architecture. If it is too low for you
680 boot with 'dma_debug_entries=<your_desired_number>' to overwrite the
681 architectural default.
683 void debug_dmap_mapping_error(struct device *dev, dma_addr_t dma_addr);
685 dma-debug interface debug_dma_mapping_error() to debug drivers that fail
686 to check DMA mapping errors on addresses returned by dma_map_single() and
687 dma_map_page() interfaces. This interface clears a flag set by
688 debug_dma_map_page() to indicate that dma_mapping_error() has been called by
689 the driver. When driver does unmap, debug_dma_unmap() checks the flag and if
690 this flag is still set, prints warning message that includes call trace that
691 leads up to the unmap. This interface can be called from dma_mapping_error()
692 routines to enable DMA mapping error check debugging.

This page was automatically generated by LXR 0.3.1 (source).  •  Linux is a registered trademark of Linus Torvalds  •  Contact us