summaryrefslogtreecommitdiffstats
path: root/drivers
diff options
context:
space:
mode:
authorAndrey Smirnov <andrew.smirnov@gmail.com>2018-08-23 19:54:21 -0700
committerSascha Hauer <s.hauer@pengutronix.de>2018-08-24 10:12:02 +0200
commit4e0112568c318b666624e51f91073bac03b6006b (patch)
tree90d6e9589e783b3bd13abd3f294c99725bcb142b /drivers
parentdd36eef35fba38972d1fcb358969d5ac5003dcb3 (diff)
downloadbarebox-4e0112568c318b666624e51f91073bac03b6006b.tar.gz
barebox-4e0112568c318b666624e51f91073bac03b6006b.tar.xz
ARM: mmu64: Don't flush freshly invalidated region
Current code for dma_sync_single_for_device(), when called with dir set to DMA_FROM_DEVICE, will first invalidate given region of memory as a first step and then clean+invalidate it as a second. While the second step should be harmless it seems to be an unnecessary no-op that could probably be avoided. Analogous code in Linux kernel (4.18) in arch/arm64/mm/cache.S: ENTRY(__dma_map_area) cmp w2, #DMA_FROM_DEVICE b.eq __dma_inv_area b __dma_clean_area ENDPIPROC(__dma_map_area) is written to only perform either invalidate or clean, depending on the direction, so change dma_sync_single_for_device() to behave in the same vein and perfom _either_ invlidate or flush of the given region. Signed-off-by: Andrey Smirnov <andrew.smirnov@gmail.com> Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Diffstat (limited to 'drivers')
0 files changed, 0 insertions, 0 deletions