diff mbox

[U-Boot,03/15,v3] imx: mmc: fsl_esdhc fix dcache issue

Message ID 1437603903-2304-2-git-send-email-aalonso@freescale.com
State Superseded
Delegated to: Stefano Babic
Headers show

Commit Message

Adrian Alonso July 22, 2015, 10:24 p.m. UTC 
DCIMVAC is upgraded to DCCIMVAC for the individual processor
(Cortex-A7) that the DCIMVAC is executed on.

We should follow the linux dma follow. Before DMA read, first
invalidate dcache then after DMA read, invalidate dcache again.

With the DMA direction DMA_FROM_DEVICE, the dcache need be
invalidated again after the DMA completion. The reason is
that we need explicity make sure the dcache been invalidated
thus to get the DMA'ed memory correctly from the physical memory.
Any cache-line fill during the DMA operations such as the
pre-fetching can cause the DMA coherency issue, thus CPU get the stale data.

Signed-off-by: Peng Fan <Peng.Fan@freescale.com>
Signed-off-by: Ye.Li <B37916@freescale.com>
Signed-off-by: Nitin Garg <nitin.garg@freescale.com>
Signed-off-by: Jason Liu <r64343@freescale.com>
Signed-off-by: Adrian Alonso <aalonso@freescale.com>
---
Changes for V2: Resend
Changes for V3: Resend

 drivers/mmc/fsl_esdhc.c | 8 ++++++++
 1 file changed, 8 insertions(+)

Comments

Stefano Babic July 26, 2015, 2:05 p.m. UTC | #1 
Hi Adrian,

On 23/07/2015 00:24, Adrian Alonso wrote:
> DCIMVAC is upgraded to DCCIMVAC for the individual processor
> (Cortex-A7) that the DCIMVAC is executed on.
> 
> We should follow the linux dma follow. Before DMA read, first
> invalidate dcache then after DMA read, invalidate dcache again.
> 
> With the DMA direction DMA_FROM_DEVICE, the dcache need be
> invalidated again after the DMA completion. The reason is
> that we need explicity make sure the dcache been invalidated
> thus to get the DMA'ed memory correctly from the physical memory.
> Any cache-line fill during the DMA operations such as the
> pre-fetching can cause the DMA coherency issue, thus CPU get the stale data.
> 

Pen has already sent this patch:

	https://patchwork.ozlabs.org/patch/488273/

Please do not copy and resend patches that are already enqueded.
Instead, advise that your patches depend on some previous ones. Thanks.

Best regards,
Stefano Babic
diff mbox

Patch

diff --git a/drivers/mmc/fsl_esdhc.c b/drivers/mmc/fsl_esdhc.c
index c4719e6..0510bf0 100644
--- a/drivers/mmc/fsl_esdhc.c
+++ b/drivers/mmc/fsl_esdhc.c
@@ -341,6 +341,9 @@  esdhc_send_cmd(struct mmc *mmc, struct mmc_cmd *cmd, struct mmc_data *data)
 		err = esdhc_setup_data(mmc, data);
 		if(err)
 			return err;
+
+		if (data->flags & MMC_DATA_READ)
+			check_and_invalidate_dcache_range(cmd, data);
 	}
 
 	/* Figure out the transfer arguments */
@@ -437,6 +440,11 @@  esdhc_send_cmd(struct mmc *mmc, struct mmc_cmd *cmd, struct mmc_data *data)
 			}
 		} while ((irqstat & DATA_COMPLETE) != DATA_COMPLETE);
 
+		/*
+		 * Need invalidate the dcache here again to avoid any
+		 * cache-fill during the DMA operations such as the
+		 * speculative pre-fetching etc.
+		 */
 		if (data->flags & MMC_DATA_READ)
 			check_and_invalidate_dcache_range(cmd, data);
 #endif