提交 de0b65a7 编写于 作者: R Russell King 提交者: Chris Ball

mmc: sdhci: avoid sync'ing the SG if there's no misalignment

On read, we don't need to sync the whole scatterlist and then check
whether any segments need copying - if we check first, we avoid
potentially expensive cache handling.
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>
Tested-by: NMarkus Pargmann <mpa@pengutronix.de>
Tested-by: NStephen Warren <swarren@nvidia.com>
Signed-off-by: NUlf Hansson <ulf.hansson@linaro.org>
Signed-off-by: NChris Ball <chris@printf.net>
上级 0718e59a
......@@ -602,6 +602,7 @@ static void sdhci_adma_table_post(struct sdhci_host *host,
u8 *align;
char *buffer;
unsigned long flags;
bool has_unaligned;
if (data->flags & MMC_DATA_READ)
direction = DMA_FROM_DEVICE;
......@@ -614,7 +615,15 @@ static void sdhci_adma_table_post(struct sdhci_host *host,
dma_unmap_single(mmc_dev(host->mmc), host->align_addr,
128 * 4, direction);
if (data->flags & MMC_DATA_READ) {
/* Do a quick scan of the SG list for any unaligned mappings */
has_unaligned = false;
for_each_sg(data->sg, sg, host->sg_count, i)
if (sg_dma_address(sg) & 3) {
has_unaligned = true;
break;
}
if (has_unaligned && data->flags & MMC_DATA_READ) {
dma_sync_sg_for_cpu(mmc_dev(host->mmc), data->sg,
data->sg_len, direction);
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册