diff options
| author | FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> | 2011-02-25 14:44:16 -0800 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@suse.de> | 2011-03-02 09:47:04 -0500 |
| commit | 484d82b6e2e4239ba7a722e0c532e9aff64be51a (patch) | |
| tree | 45975f2ec4f971eab9f22b1de747df275c713716 /lib/swiotlb.c | |
| parent | 8216e1a0d47cae06a75c42346f19dffe14e42d57 (diff) | |
| download | lwn-484d82b6e2e4239ba7a722e0c532e9aff64be51a.tar.gz lwn-484d82b6e2e4239ba7a722e0c532e9aff64be51a.zip | |
swiotlb: fix wrong panic
commit fba99fa38b023224680308a482e12a0eca87e4e1 upstream.
swiotlb's map_page wrongly calls panic() when it can't find a buffer fit
for device's dma mask. It should return an error instead.
Devices with an odd dma mask (i.e. under 4G) like b44 network card hit
this bug (the system crashes):
http://marc.info/?l=linux-kernel&m=129648943830106&w=2
If swiotlb returns an error, b44 driver can use the own bouncing
mechanism.
Reported-by: Chuck Ebbert <cebbert@redhat.com>
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Tested-by: Arkadiusz Miskiewicz <arekm@maven.pl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Diffstat (limited to 'lib/swiotlb.c')
| -rw-r--r-- | lib/swiotlb.c | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/lib/swiotlb.c b/lib/swiotlb.c index ac25cd28e807..7740ee868399 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -631,8 +631,10 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, /* * Ensure that the address returned is DMA'ble */ - if (!dma_capable(dev, dev_addr, size)) - panic("map_single: bounce buffer is not DMA'ble"); + if (!dma_capable(dev, dev_addr, size)) { + swiotlb_tbl_unmap_single(dev, map, size, dir); + dev_addr = swiotlb_virt_to_bus(dev, io_tlb_overflow_buffer); + } return dev_addr; } |