kernel/crypto/async_tx/async_memcpy.c, branch linux-5.1.y

async_tx: use GFP_NOWAIT rather than GFP_IO

2016-01-07T05:36:18Z

These async_XX functions are called from md/raid5 in an atomic section, between get_cpu() and put_cpu(), so they must not sleep. So use GFP_NOWAIT rather than GFP_IO. Dan Williams writes: Longer term async_tx needs to be merged into md directly as we can allocate this unmap data statically per-stripe rather than per request. Fixed: 7476bd79fc01 ("async_pq: convert to dmaengine_unmap_data") Cc: stable@vger.kernel.org (v3.13+) Reported-and-tested-by: Stanislav Samsonov Acked-by: Dan Williams Signed-off-by: NeilBrown Signed-off-by: Vinod Koul

dmaengine: remove DMA unmap flags

2013-11-14T19:04:38Z

Remove no longer needed DMA unmap flags: - DMA_COMPL_SKIP_SRC_UNMAP - DMA_COMPL_SKIP_DEST_UNMAP - DMA_COMPL_SRC_UNMAP_SINGLE - DMA_COMPL_DEST_UNMAP_SINGLE Cc: Vinod Koul Cc: Tomasz Figa Cc: Dave Jiang Signed-off-by: Bartlomiej Zolnierkiewicz Signed-off-by: Kyungmin Park Acked-by: Jon Mason Acked-by: Mark Brown [djbw: clean up straggling skip unmap flags in ntb] Signed-off-by: Dan Williams

async_memcpy: convert to dmaengine_unmap_data

2013-11-14T19:00:39Z

Use the generic unmap object to unmap dma buffers. Cc: Vinod Koul Cc: Tomasz Figa Cc: Dave Jiang Reported-by: Bartlomiej Zolnierkiewicz [bzolnier: add missing unmap->len initialization] [bzolnier: fix whitespace damage] Signed-off-by: Bartlomiej Zolnierkiewicz Signed-off-by: Kyungmin Park [djbw: add DMA_ENGINE=n support] Signed-off-by: Dan Williams

async_tx: add missing DMA unmap to async_memcpy()

2013-01-08T06:04:57Z

Do DMA unmap on ->device_prep_dma_memcpy failure. Cc: Dan Williams Cc: Tomasz Figa Signed-off-by: Bartlomiej Zolnierkiewicz Signed-off-by: Kyungmin Park Signed-off-by: Dan Williams

crypto: remove the second argument of k[un]map_atomic()

2012-03-20T13:48:16Z

Signed-off-by: Cong Wang

crypto: add module.h to those files that are explicitly using it

2011-10-31T23:31:11Z

Part of the include cleanups means that the implicit inclusion of module.h via device.h is going away. So fix things up in advance. Signed-off-by: Paul Gortmaker

mm: strictly nested kmap_atomic()

2010-10-26T23:52:08Z

Ensure kmap_atomic() usage is strictly nested Signed-off-by: Peter Zijlstra Reviewed-by: Rik van Riel Acked-by: Chris Metcalf Cc: David Howells Cc: Hugh Dickins Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Steven Rostedt Cc: Russell King Cc: Ralf Baechle Cc: David Miller Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

dmaengine, async_tx: support alignment checks

2009-09-09T00:42:53Z

Some engines have transfer size and address alignment restrictions. Add a per-operation alignment property to struct dma_device that the async routines and dmatest can use to check alignment capabilities. Signed-off-by: Dan Williams

dmaengine: add fence support

2009-09-09T00:42:50Z

Some engines optimize operation by reading ahead in the descriptor chain such that descriptor2 may start execution before descriptor1 completes. If descriptor2 depends on the result from descriptor1 then a fence is required (on descriptor2) to disable this optimization. The async_tx api could implicitly identify dependencies via the 'depend_tx' parameter, but that would constrain cases where the dependency chain only specifies a completion order rather than a data dependency. So, provide an ASYNC_TX_FENCE to explicitly identify data dependencies. Signed-off-by: Dan Williams

async_tx: kill needless module_{init|exit}

2009-08-30T02:09:26Z

If module_init and module_exit are nops then neither need to be defined. [ Impact: pure cleanup ] Reviewed-by: Andre Noll Acked-by: Maciej Sosnowski Signed-off-by: Dan Williams