linux/drivers/dma, branch v2.6.26

iop-adma: fixup some kzalloc/memset confusions

2008-05-20T20:51:20Z

1) Remove an explicit memset(.., 0, ...) to a variable allocated with kzalloc (i.e. 'dest'). 2) Allocate 'src' with kmalloc instead of kzalloc as all elements of the 'src' buffer are initialized in a 'for(...)' loop just after. 3) remove useless 'sizeof(u8)', which always returns 1, when computing the size of the memory to be allocated. Signed-off-by: Christophe Jaillet Signed-off-by: Dan Williams

DMA engine: typo fixes

2008-04-21T22:38:45Z

Spelling fixes for dmaengine.[ch] Signed-off-by: Sebastian Siewior Acked-by: Maciej Sosnowski Signed-off-by: Jesper Juhl

dmaengine: ack to flags: make use of the unused bits in the 'ack' field

2008-04-17T20:25:54Z

'ack' is currently a simple integer that flags whether or not a client is done touching fields in the given descriptor. It is effectively just a single bit of information. Converting this to a flags parameter allows the other bits to be put to use to control completion actions, like dma-unmap, and capture results, like xor-zero-sum == 0. Changes are one of: 1/ convert all open-coded ->ack manipulations to use async_tx_ack and async_tx_test_ack. 2/ set the ack bit at prep time where possible 3/ make drivers store the flags at prep time 4/ add flags to the device_prep_dma_interrupt prototype Acked-by: Maciej Sosnowski Signed-off-by: Dan Williams

iop-adma: remove the workaround for missed interrupts on iop3xx

2008-04-17T20:25:54Z

This workaround was covering the dependency submission bug in async_tx. Signed-off-by: Dan Williams

async_tx: kill ->device_dependency_added

2008-04-17T20:25:54Z

DMA drivers no longer need to be notified of dependency submission events as async_tx_run_dependencies and async_tx_channel_switch will handle the scheduling and execution of dependent operations. [sfr@canb.auug.org.au: extend this for fsldma] Acked-by: Shannon Nelson Signed-off-by: Dan Williams

async_tx: fix multiple dependency submission

2008-04-17T20:25:05Z

Shrink struct dma_async_tx_descriptor and introduce async_tx_channel_switch to properly inject a channel switch interrupt in the descriptor stream. This simplifies the locking model as drivers no longer need to handle dma_async_tx_descriptor.lock. Acked-by: Shannon Nelson Signed-off-by: Dan Williams

fsldma: Split the MPC83xx event from MPC85xx and refine irq codes.

2008-04-17T20:22:16Z

Split MPC83xx EOCDI event from MPC85xx EOLNI event, which is also need to update cookie and start the next transfer. The DMA channel irq handler function code is refined. The patch is tested on MPC8377MDS board. Signed-off-by: Zhang Wei Signed-off-by; Andrew Morton Signed-off-by: Dan Williams

fsldma: Remove CONFIG_FSL_DMA_SELFTEST, keep fsl_dma_self_test() running always.

2008-04-17T20:22:15Z

Always enabling the fsl_dma_self_test() to ensure the DMA controller should works well after the driver probed. Signed-off-by: Zhang Wei Signed-off-by: Dan Williams

[POWERPC] fsldma: Use compatiable binding as spec

2008-03-31T16:45:41Z

Documentation/powerpc/booting-without-of.txt specifies the compatiables we should bind to for this driver (elo, eloplus). Use these instead of the extremely specific 'mpc8540' and 'mpc8349' compatiables. Acked-by: Dan Williams Signed-off-by: Kumar Gala

fix the broken annotations in fsldma

2008-03-30T21:20:24Z

a) every bitwise declaration will give a unique type; use typedefs. b) no need to bother with the stuff pointed to by iomem pointers, unless it's accessed directly. noderef will force us to use helpers anyway. Signed-off-by: Al Viro Signed-off-by: Linus Torvalds