[PATCH 12/38] mmc: sdhci: avoid sync'ing the SG if there's no misalignment
Russell King
rmk+kernel at arm.linux.org.uk
Wed Apr 23 12:07:11 PDT 2014
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: Russell King <rmk+kernel at arm.linux.org.uk>
---
drivers/mmc/host/sdhci.c | 11 ++++++++++-
1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 7e2f24ac579b..078bf43b4aae 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -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);
--
1.8.3.1
More information about the linux-arm-kernel
mailing list