NeilBrown b02bab6b0f async_tx: use GFP_NOWAIT rather than GFP_IO ...

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: 7476bd79fc ("async_pq: convert to dmaengine_unmap_data")
Cc: [email protected] (v3.13+)
Reported-and-tested-by: Stanislav Samsonov <[email protected]>
Acked-by: Dan Williams <[email protected]>
Signed-off-by: NeilBrown <[email protected]>
Signed-off-by: Vinod Koul <[email protected]>

2016-01-07 11:06:18 +05:30

..

async_memcpy.c

async_tx: use GFP_NOWAIT rather than GFP_IO

2016-01-07 11:06:18 +05:30

async_pq.c

async_tx: use GFP_NOWAIT rather than GFP_IO

2016-01-07 11:06:18 +05:30

async_raid6_recov.c

async_tx: use GFP_NOWAIT rather than GFP_IO

2016-01-07 11:06:18 +05:30

async_tx.c

async_tx: use DMA_COMPLETE for dma completion status

2013-10-25 11:16:18 +05:30

async_xor.c

async_tx: use GFP_NOWAIT rather than GFP_IO

2016-01-07 11:06:18 +05:30

Kconfig

drivers/dma: remove unused support for MEMSET operations

2013-07-03 16:07:42 -07:00

Makefile

drivers/dma: remove unused support for MEMSET operations

2013-07-03 16:07:42 -07:00

raid6test.c

raid6test: add new corner case for ioatdma driver

2013-11-14 11:04:42 -08:00