swiotlb: don't dip into swiotlb pool for coherent allocations

Browse source

All architectures that support swiotlb also have a zone that backs up
these less than full addressing allocations (usually ZONE_DMA32).

Because of that it is rather pointless to fall back to the global swiotlb
buffer if the normal dma direct allocation failed - the only thing this
will do is to eat up bounce buffers that would be more useful to serve
streaming mappings.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

...

This commit is contained in:

Christoph Hellwig 2018-09-30 16:13:33 -07:00

parent c4dae36692

commit fafadcd165

3 changed files with 5 additions and 111 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download patch file Download diff file Expand all files Collapse all files

6

arch/arm64/mm/dma-mapping.c

View file

5

include/linux/swiotlb.h

View file

105

kernel/dma/swiotlb.c

View file