DragonFly On-Line Manual Pages


BUS_DMA(9)	      DragonFly Kernel Developer's Manual	    BUS_DMA(9)

NAME

bus_dma, bus_dma_tag_create, bus_dma_tag_destroy, bus_dmamap_create, bus_dmamap_destroy, bus_dmamap_load, bus_dmamap_load_mbuf, bus_dmamap_load_mbuf_segment, bus_dmamap_load_mbuf_defrag, bus_dmamap_load_uio, bus_dmamap_unload, bus_dmamap_sync, bus_dmamem_alloc, bus_dmamem_coherent, bus_dmamem_coherent_any, bus_dmamem_free -- Bus and Machine Independent DMA Mapping Interface

SYNOPSIS

#include <sys/bus.h> int bus_dma_tag_create(bus_dma_tag_t parent, bus_size_t alignment, bus_size_t boundary, bus_addr_t lowaddr, bus_addr_t highaddr, bus_dma_filter_t *filtfunc, void *filtfuncarg, bus_size_t maxsize, int nsegments, bus_size_t maxsegsz, int flags, bus_dma_tag_t *dmat); int bus_dma_tag_destroy(bus_dma_tag_t dmat); int bus_dmamap_create(bus_dma_tag_t dmat, int flags, bus_dmamap_t *mapp); int bus_dmamap_destroy(bus_dma_tag_t dmat, bus_dmamap_t map); int bus_dmamap_load(bus_dma_tag_t dmat, bus_dmamap_t map, void *buf, bus_size_t buflen, bus_dmamap_callback_t *callback, void *callback_arg, int flags); int bus_dmamap_load_mbuf(bus_dma_tag_t dmat, bus_dmamap_t map, struct mbuf *mbuf, bus_dmamap_callback2_t *callback, void *callback_arg, int flags); int bus_dmamap_load_mbuf_segment(bus_dma_tag_t dmat, bus_dmamap_t map, struct mbuf *mbuf, bus_dma_segment_t *segs, int maxsegs, int *nsegs, int flags); int bus_dmamap_load_mbuf_defrag(bus_dma_tag_t dmat, bus_dmamap_t map, struct mbuf **mbuf, bus_dma_segment_t *segs, int maxsegs, int *nsegs, int flags); int bus_dmamap_load_uio(bus_dma_tag_t dmat, bus_dmamap_t map, struct uio *uio, bus_dmamap_callback2_t *callback, void *callback_arg, int flags); int bus_dmamem_alloc(bus_dma_tag_t dmat, void **vaddr, int flags, bus_dmamap_t *mapp); int bus_dmamem_coherent(bus_dma_tag_t parent, bus_size_t alignment, bus_size_t boundary, bus_addr_t lowaddr, bus_addr_t highaddr, bus_size_t maxsize, int flags, bus_dmamem_t *dmem); void * bus_dmamem_coherent_any(bus_dma_tag_t parent, bus_size_t alignment, bus_size_t maxsize, int flags, bus_dma_tag_t *dtag, bus_dmamap_t *dmap, bus_addr_t *busaddr); void bus_dmamap_unload(bus_dma_tag_t dmat, bus_dmamap_t map); void bus_dmamap_sync(bus_dma_tag_t dmat, bus_dmamap_t map, bus_dmasync_op_t op); void bus_dmamem_free(bus_dma_tag_t dmat, void *vaddr, bus_dmamap_t map);

DESCRIPTION

Direct Memory Access (DMA) is a method of transferring data without involving the CPU, thus providing higher performance. A DMA transaction can be achieved between device to memory, device to device, or memory to memory. The bus_dma API is a bus, device, and machine-independent (MI) interface to DMA mechanisms. It provides the client with flexibility and simplic- ity by abstracting machine dependent issues like setting up DMA mappings, handling cache issues, bus specific features and limitations.

STRUCTURES AND TYPES

bus_dma_tag_t A machine-dependent (MD) opaque type that describes the charac- teristics of DMA transactions. DMA tags are organized into a hierarchy, with each child tag inheriting the restrictions of its parent. This allows all devices along the path of DMA transactions to contribute to the constraints of those transac- tions. bus_dma_filter_t Client specified address filter having the format: int client_filter(void *filtarg, bus_addr_t testaddr) Address filters can be specified during tag creation to allow for devices who's DMA address restrictions cannot be specified by a single window. The filtarg is client specified during tag creation to be passed to all invocations of the callback. The testaddr argument contains a potential starting address of a DMA mapping. The filter function operates on the set of addresses from testaddr to `trunc_page(testaddr) + PAGE_SIZE - 1', inclu- sive. The filter function should return zero for any mapping in this range that can be accommodated by the device and non-zero otherwise. bus_dma_segment_t A machine-dependent type that describes individual DMA segments. bus_addr_t ds_addr; bus_size_t ds_len; The ds_addr field contains the device visible address of the DMA segment, and ds_len contains the length of the DMA segment. Although the DMA segments returned by a mapping call will adhere to all restrictions necessary for a successful DMA operation, some conversion (e.g. a conversion from host byte order to the device's byte order) is almost always required when presenting segment information to the device. bus_dmamap_t A machine-dependent opaque type describing an individual map- ping. Multiple DMA maps can be associated with one DMA tag. bus_dmamem_t A machine-dependent type that describes DMA memory created by bus_dmamem_coherent(). bus_dma_tag_t dmem_tag; bus_dmamap_t dmem_map; void *dmem_addr; bus_addr_t dmem_busaddr; The dmem_tag field contains the DMA tag of the DMA memory and dmem_map field contains the DMA map of the DMA memory. The dmem_addr field points to the allocated DMA memory in kernel virtual address space. The dmem_busaddr field contains the device visible address of the DMA memory. bus_dmamap_callback_t Client specified callback for receiving mapping information resulting from the load of a bus_dmamap_t via bus_dmamap_load(). Callbacks are of the format: void client_callback(void *callback_arg, bus_dma_segment_t *segs, int nseg, int error) The callback_arg is the callback argument passed to dmamap load functions. The segs and nseg parameters describe an array of bus_dma_segment_t structures that represent the mapping. This array is only valid within the scope of the callback function. The success or failure of the mapping is indicated by the error parameter. More information on the use of callbacks can be found in the description of the individual dmamap load func- tions. bus_dmamap_callback2_t Client specified callback for receiving mapping information resulting from the load of a bus_dmamap_t via bus_dmamap_load_uio() or bus_dmamap_load_mbuf(). Callback2s are of the format: void client_callback2(void *callback_arg, bus_dma_segment_t *segs, int nseg, bus_size_t mapsize, int error) Callback2's behavior is the same as bus_dmamap_callback_t with the addition that the length of the data mapped is provided via mapsize. bus_dmasync_op_t Memory synchronization operation specifier. Bus DMA requires explicit synchronization of memory with it's device visible map- ping in order to guarantee memory coherency. The bus_dmasync_op_t allows the type of DMA operation that will be or has been performed to be communicated to the system so that the correct coherency measures are taken. All operations speci- fied below are performed from the DMA engine's point of view: BUS_DMASYNC_PREREAD Perform any synchronization required after an update of memory by the CPU but prior to DMA read operations. BUS_DMASYNC_PREWRITE Perform any synchronization required after an update of memory by the CPU but prior to DMA write operations. BUS_DMASYNC_POSTREAD Perform any synchronization required after DMA read operations, but prior to CPU access of the memory. BUS_DMASYNC_POSTWRITE Perform any synchronization required after DMA write operations, but prior to CPU access of the memory.

FUNCTIONS

bus_dma_tag_create(parent, alignment, boundary, lowaddr, highaddr, *filtfunc, *filtfuncarg, maxsize, nsegments, maxsegsz, flags, *dmat) Allocates a device specific DMA tag, and initializes it accord- ing to the arguments provided: parent Indicates restrictions between the parent bridge, CPU memory, and the device. May be NULL, if no DMA restrictions are to be inherited. alignment Alignment constraint, in bytes, of any mappings created using this tag. The alignment must be a power of 2. Hardware that can DMA starting at any address would specify 1 for byte alignment. Hard- ware requiring DMA transfers to start on a multi- ple of 4K would specify 4096. boundary Boundary constraint, in bytes, of the target DMA memory region. The boundary indicates the set of addresses, all multiples of the boundary argument, that cannot be crossed by a single bus_dma_segment_t. The boundary must be either a power of 2 or 0. `0' indicates that there are no boundary restrictions. lowaddr highaddr Bounds of the window of bus address space that cannot be directly accessed by the device. The window contains all address greater than lowaddr and less than or equal to highaddr. For example, a device incapable of DMA above 4GB, would specify a highaddr of BUS_SPACE_MAXADDR and a lowaddr of BUS_SPACE_MAXADDR_32BIT. Similarly a device that can only dma to addresses bellow 16MB would spec- ify a highaddr of BUS_SPACE_MAXADDR and a lowaddr of BUS_SPACE_MAXADDR_24BIT. Some implementations requires that some region of device visible address space, overlapping available host memory, be outside the window. This area of `safe memory' is used to bounce requests that would otherwise conflict with the exclusion window. filtfunc Optional filter function (may be NULL) to be called for any attempt to map memory into the win- dow described by lowaddr and highaddr. A filter function is only required when the single window described by lowaddr and highaddr cannot ade- quately describe the constraints of the device. The filter function will be called for every machine page that overlaps the exclusion window. filtfuncarg Argument passed to all calls to the filter func- tion for this tag. May be NULL. maxsize Maximum size, in bytes, of the sum of all segment lengths in a given DMA mapping associated with this tag. nsegments Number of discontinuities (scatter/gather seg- ments) allowed in a DMA mapped region. If there is no restriction, BUS_SPACE_UNRESTRICTED may be specified for the tag intended to be used as the parent. BUS_SPACE_UNRESTRICTED must not be speci- fied for the tags which will be used to create maps. For tags which will be used to create maps, this argument must be less than 16384 on x86_64 and i386. maxsegsz Maximum size, in bytes, of a segment in any DMA mapped region associated with dmat. flags Are as follows: BUS_DMA_ALLOCNOW Allocate the minimum resources necessary to guarantee that all map load operations associated with this tag may not block. If sufficient resources are not available, ENOMEM is returned. BUS_DMA_WAITOK Indicates that it is OK to wait for resources. However, unlike kmalloc(9), it is not guaran- teed that the resource alloca- tion will succeed. This flag is the default one, if BUS_DMA_NOWAIT is not supplied. BUS_DMA_NOWAIT If the resource allocation request cannot be immediately fulfilled, ENOMEM is returned. BUS_DMA_ONEBPAGE Allocte one bounce page at most, even if the maxsize indi- cates that multiple bounce pages are needed. BUS_DMA_ALIGNED Indicates that all memory to be loaded into the DMA maps asso- ciated with this DMA tag is properly aligned according to alignment constraint. No resources, e.g. bounce pages, will be allocated due to the alignment constraint. If unaligned memory was loaded into the DMA maps associated with this DMA tag, system will panic. BUS_DMA_PRIVBZONE Uses a private bounce zone instead of a shared one. A private bounce zone will vanish if the DMA tag is destroyed. BUS_DMA_ALLOCALL Allocate all required resources (mainly the bounce buffer). If any allocation fails, bus_dma_tag_create() fails. BUS_DMA_PROTECTED All of the functions called with the DMA tag are already protected by the caller, so the bus_dma code need not protect the internal data structures. dmat Pointer to a bus_dma_tag_t where the resulting DMA tag will be stored. Returns ENOMEM if sufficient memory is not available for tag creation or allocating mapping resources. bus_dma_tag_destroy(dmat) Deallocate the DMA tag dmat that was created by bus_dma_tag_create(). Returns EBUSY if any DMA maps remain associated with dmat or `0' on success. bus_dmamap_create(dmat, flags, *mapp) Allocates and initializes a DMA map. Arguments are as follows: dmat DMA tag. flags Are as follows: BUS_DMA_WAITOK Indicates that it is OK to wait for resources. However, unlike kmalloc(9), it is not guaranteed that the resource allocation will succeed. This flag is the default one, if BUS_DMA_NOWAIT is not sup- plied. BUS_DMA_NOWAIT If the resource allocation request cannot be immediately fulfilled, ENOMEM is returned. BUS_DMA_ONEBPAGE Allocte one bounce page at most, even if the maxsize used to create the dmat indicates that multiple bounce pages are needed. mapp Pointer to a bus_dmamap_t where the resulting DMA map will be stored. Returns ENOMEM if sufficient memory is not available for creat- ing the map or allocating mapping resources. bus_dmamap_destroy(dmat, map) Frees all resources associated with a given DMA map. Arguments are as follows: dmat DMA tag used to allocate map. map The DMA map to destroy. Returns EBUSY if a mapping is still active for map. bus_dmamap_load(dmat, map, buf, buflen, *callback, ...) Creates a mapping in device visible address space of buflen bytes of buf, associated with the DMA map map. Arguments are as follows: dmat DMA tag used to allocate map. map A DMA map without a currently active mapping. buf A kernel virtual address pointer to a contiguous (in KVA) buffer, to be mapped into device visible address space. buflen The size of the buffer. callback callback_arg The callback function, and its argument. flags The value of this argument is currently undefined, and should be specified as `0'. Return values to the caller are as follows: 0 The callback has been called and completed. The status of the mapping has been delivered to the callback. EINPROGRESS The mapping has been deferred for lack of resources. The callback will be called as soon as resources are available. Callbacks are serviced in FIFO order. DMA maps created from DMA tags that are allocated with the BUS_DMA_ALLOCNOW flag will never return this status for a load operation. EINVAL The load request was invalid. The callback has not, and will not be called. This error value may indicate that dmat, map, buf, or callback were invalid, or buslen was larger than the maxsize argument used to create the dma tag dmat. When the callback is called, it is presented with an error value indicating the disposition of the mapping. Error may be one of the following: 0 The mapping was successful and the dm_segs callback argument contains an array of bus_dma_segment_t elements describing the mapping. This array is only valid during the scope of the callback func- tion. EFBIG A mapping could not be achieved within the segment constraints provided in the tag even though the requested allocation size was less than maxsize. bus_dmamap_load_mbuf(dmat, map, mbuf, callback2, callback_arg, flags) This is a variation of bus_dmamap_load() which maps mbuf chains for DMA transfers. A bus_size_t argument is also passed to the callback routine, which contains the mbuf chain's packet header length. Mbuf chains are assumed to be in kernel virtual address space. Returns EINVAL if the size of the mbuf chain exceeds the maximum limit of the DMA tag. bus_dmamap_load_mbuf_segment(dmat, map, mbuf, *segs, maxsegs, *nsegs, flags) It is like bus_dmamap_load_mbuf() without callback. Segmenta- tion information are saved in the segs and nsegs if the loading is successful. The maxsegs, which indicates the number of ele- ments in the segs, must be set by the caller and must be at least 1 but less than the nsegments used to create the dmat. The flags must have BUS_DMA_NOWAIT turned on. This function will not block. When system is short of DMA resources, this function will return ENOMEM, instead of EINPROGRESS. bus_dmamap_load_mbuf_defrag(dmat, map, *mbuf, *segs, maxsegs, *nsegs, flags) This function is like bus_dmamap_load_mbuf_segment(), but it will call m_defrag() on the *mbuf and try reloading, if low level code indicates too many fragments in the *mbuf; the mbuf will be updated under this situation. However, *mbuf would not be freed by this function, even if m_defrag() failed. Return ENOBUFS, if the calling of m_defrag() failed. bus_dmamap_load_uio(dmat, map, uio, callback2, callback_arg, flags) This is a variation of bus_dmamap_load() which maps buffers pointed to by uio for DMA transfers. A bus_size_t argument is also passed to the callback routine, which contains the size of uio, i.e. uio->uio_resid. If uio->uio_segflg is UIO_USERSPACE, then it is assumed that the buffer, uio is in uio->uio_td->td_proc's address space. User space memory must be in-core and wired prior to attempting a map load operation. bus_dmamap_unload(dmat, map) Unloads a DMA map. Arguments are as follows: dmat DMA tag used to allocate map. map The DMA map that is to be unloaded. bus_dmamap_unload() will not perform any implicit synchroniza- tion of DMA buffers. This must be done explicitly by a call to bus_dmamap_sync() prior to unloading the map. bus_dmamap_sync(dmat, map, op) Performs synchronization of a device visible mapping with the CPU visible memory referenced by that mapping. Arguments are as follows: dmat DMA tag used to allocate map. map The DMA mapping to be synchronized. op Type of synchronization operation to perform. See the definition of bus_dmasync_op_t for a description of the acceptable values for op. bus_dmamap_sync() is the method used to ensure that CPU and device DMA access to shared memory is coherent. For example, the CPU might be used to setup the contents of a buffer that is to be DMA'ed into a device. To ensure that the data are visible via the device's mapping of that memory, the buffer must be loaded and a dma sync operation of BUS_DMASYNC_PREREAD must be performed. Additional sync operations must be performed after every CPU write to this memory if additional DMA reads are to be performed. Conversely, for the DMA write case, the buffer must be loaded, and a dma sync operation of BUS_DMASYNC_PREWRITE must be performed. The CPU will only be able to see the results of this DMA write once the DMA has completed and a BUS_DMASYNC_POSTWRITE operation has been performed. If DMA read and write operations are not preceded and followed by the appropriate synchronization operations, behavior is unde- fined. bus_dmamem_alloc(dmat, **vaddr, flags, mapp) Allocates memory that is mapped into KVA at the address returned in vaddr that is permanently loaded into the newly created bus_dmamap_t returned via mapp. Arguments are as follows: dmat DMA tag describing the constraints of the DMA map- ping. vaddr Pointer to a pointer that will hold the returned KVA mapping of the allocated region. flags Flags are defined as follows: BUS_DMA_WAITOK The routine can safely wait (sleep) for resources. BUS_DMA_NOWAIT The routine is not allowed to wait for resources. If resources are not available, ENOMEM is returned. BUS_DMA_COHERENT Attempt to map this memory such that cache sync operations are as cheap as possible. This flag is typically set on memory that will be accessed by both a CPU and a DMA engine, fre- quently. Use of this flag does not remove the requirement of using bus_dmamap_sync, but it may reduce the cost of performing these opera- tions. BUS_DMA_ZERO Causes the allocated memory to be set to all zeros. mapp Pointer to storage for the returned DMA map. The size of memory to be allocated is maxsize as specified in dmat. The current implementation of bus_dmamem_alloc() will allocate all requests as a single segment. Although no explicit loading is required to access the memory referenced by the returned map, the synchronization requirements as described in the bus_dmamap_sync() section still apply. Returns ENOMEM if sufficient memory is not available for com- pleting the operation. bus_dmamem_coherent(parent, alignment, boundary, lowaddr, highaddr, maxsize, flags, *dmem) This is a convenient function to create one segment of DMA mem- ory. It combines following bus_dma(9) function calls: bus_dma_tag_create(..., dtag); bus_dmamem_alloc(*dtag, vaddr, ..., dmap); bus_dmamap_load(*dtag, *dmap, *vaddr, ..., \ callback, busaddr, ...); The final results of the above function calls are: DMA tag, DMA map, DMA memory's kernel virtual address and its device visible address. bus_dmamem_coherent() saves the results in *dmem. The parent, alignment, boundary, lowaddr and highaddr will be passed to bus_dma_tag_create() as they are. The maxsize will be passed to bus_dma_tag_create() as its maxsize and maxsegsz and `1' will be passed to bus_dma_tag_create() as its nsegments. When bus_dmamem_alloc() is called, flags will be first or'ed with BUS_DMA_COHERENT then passed to it. The final results of the above three functions, i.e. DMA tag, DMA map, DMA memory's kernel virtual address and its device visible address, are saved in *dmem. If any of the three functions failed, this function will return the error code and the *dmem should not be used. bus_dmamem_coherent_any(parent, alignment, maxsize, flags, *dtag, *dmap, *busaddr) This function is a simplified version of bus_dmamem_coherent() with its boundary set to `0', lowaddr set to BUS_SPACE_MAXADDR and highaddr set to BUS_SPACE_MAXADDR. The parent usually should not be NULL. Return the DMA memory's kernel virtual address. The DMA tag, DMA map and device visible address are returned in *dtag, *dmap, and *busaddr. If this function failed, NULL will be returned; *dtag, *dmap, and *busaddr are left unchanged. bus_dmamem_free(dmat, *vaddr, map) Frees memory previously allocated by bus_dmamem_alloc(). Any mappings will be invalidated. Arguments are as follows: dmat DMA tag. vaddr Kernel virtual address of the memory. map DMA map to be invalidated.

RETURN VALUES

Behavior is undefined if invalid arguments are passed to any of the above functions. If sufficient resources cannot be allocated for a given transaction, ENOMEM is returned. All routines that are not of type, void, will return 0 on success or an error code, as discussed above. All void routines will succeed if provided with valid arguments.

SEE ALSO

devclass(9), device(9), driver(9), rman(9) Jason R. Thorpe, "A Machine-Independent DMA Framework for NetBSD", Proceedings of the Summer 1998 USENIX Technical Conference, USENIX Association, June 1998.

HISTORY

The bus_dma interface first appeared in NetBSD 1.3. The bus_dma API was adopted from NetBSD for use in the CAM SCSI subsys- tem. The alterations to the original API were aimed to remove the need for a bus_dma_segment_t array stored in each bus_dmamap_t while allowing callers to queue up on scarce resources.

AUTHORS

The bus_dma interface was designed and implemented by Jason R. Thorpe of the Numerical Aerospace Simulation Facility, NASA Ames Research Center. Additional input on the bus_dma design was provided by Chris Demetriou, Charles Hannum, Ross Harvey, Matthew Jacob, Jonathan Stone, and Matt Thomas. This manual page was written by Hiten Pandya and Justin T. Gibbs. DragonFly 3.7 January 11, 2010 DragonFly 3.7