On Thu, Jan 07, 2016 at 11:02:34AM +1100, NeilBrown wrote: > > 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@xxxxxxxxxxxxxxx (v3.13+) > Reported-and-tested-by: Stanislav Samsonov <slava@xxxxxxxxxxxxxxxxx> > Acked-by: Dan Williams <dan.j.williams@xxxxxxxxx> > Signed-off-by: NeilBrown <neilb@xxxxxxxx> > --- > > Thanks for taking this Vinod. > It is currently in linux-next from my md tree, but I've just de-staged > it so the next linux-next won't have it from me. Okay this is not in dmaengine. But since we all agreed, I have picked and will send to Linus later today. If anyone has any objections please speak up Thanks -- ~Vinod
Attachment:
signature.asc
Description: Digital signature