Thanks for the suggestion, it works great (stress tested) and is a cleaner fix. Here is a patch the latest linux-omap-2.6 tree. Is this OK? Regards, Jean From d143f6b2e705aa4e9d2b032097fd1c82f8163262 Mon Sep 17 00:00:00 2001 From: Jean Pihet <jpihet@xxxxxxxxxx> Date: Thu, 8 Jan 2009 12:35:21 +0100 Subject: [PATCH] OMAP: MMC: recover from transfer failures Timeouts during a command that has a data phase can result in the next command issued after the command that failed not being processed, i.e. no interrupt ever occurs to indicate the command has completed. This failure can result in a deadlock. This patch resets the data state machine to clear the error in case of a command timeout. Tested on OMAP3430 chip and intensive MMC/SD device removal while transferring data. Signed-off-by: Andy Lowe <alowe@xxxxxxxxxx> Signed-off-by: Jean Pihet <jpihet@xxxxxxxxxx> Signed-off-by: Adrian Hunter <ext-adrian.hunter@xxxxxxxxx> --- drivers/mmc/host/omap_hsmmc.c | 9 ++++++++- 1 files changed, 8 insertions(+), 1 deletions(-) diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index d5c1e9d..97150c0 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -464,8 +464,15 @@ static irqreturn_t mmc_omap_irq(int irq, void *dev_id) } end_cmd = 1; } - if (host->data) + if (host->data) { mmc_dma_cleanup(host); + OMAP_HSMMC_WRITE(host->base, SYSCTL, + OMAP_HSMMC_READ(host->base, + SYSCTL) | SRD); + while (OMAP_HSMMC_READ(host->base, + SYSCTL) & SRD) + ; + } } if ((status & DATA_TIMEOUT) || (status & DATA_CRC)) { -- 1.5.4.4.21.gc4a6c On Thursday 08 January 2009 10:02:24 Adrian Hunter wrote: > Why not do the reset in mmc_omap_irq() like the other resets? > e.g. > > static irqreturn_t mmc_omap_irq(int irq, void *dev_id) > ... > if ((status & CMD_TIMEOUT) || > (status & CMD_CRC)) { > if (host->cmd) { > if (status & CMD_TIMEOUT) { > OMAP_HSMMC_WRITE(host->base, > SYSCTL, OMAP_HSMMC_READ(host->base, SYSCTL) | SRC); while > (OMAP_HSMMC_READ(host->base, SYSCTL) & SRC) ; > > host->cmd->error = -ETIMEDOUT; > } else { > host->cmd->error = -EILSEQ; > } > end_cmd = 1; > } > - if (host->data) > + if (host->data) { > mmc_dma_cleanup(host); > + OMAP_HSMMC_WRITE(host->base, SYSCTL, > + OMAP_HSMMC_READ(host->base, > + SYSCTL) | SRD); > + while (OMAP_HSMMC_READ(host->base, > + SYSCTL) & SRD) > + ; > + } > } > if ((status & DATA_TIMEOUT) || > (status & DATA_CRC)) {
From d143f6b2e705aa4e9d2b032097fd1c82f8163262 Mon Sep 17 00:00:00 2001 From: Jean Pihet <jpihet@xxxxxxxxxx> Date: Thu, 8 Jan 2009 12:35:21 +0100 Subject: [PATCH] OMAP: MMC: recover from transfer failures Timeouts during a command that has a data phase can result in the next command issued after the command that failed not being processed, i.e. no interrupt ever occurs to indicate the command has completed. This failure can result in a deadlock. This patch resets the data state machine to clear the error in case of a command timeout. Tested on OMAP3430 chip and intensive MMC/SD device removal while transferring data. Signed-off-by: Andy Lowe <alowe@xxxxxxxxxx> Signed-off-by: Jean Pihet <jpihet@xxxxxxxxxx> Signed-off-by: Adrian Hunter <ext-adrian.hunter@xxxxxxxxx> --- drivers/mmc/host/omap_hsmmc.c | 9 ++++++++- 1 files changed, 8 insertions(+), 1 deletions(-) diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index d5c1e9d..97150c0 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -464,8 +464,15 @@ static irqreturn_t mmc_omap_irq(int irq, void *dev_id) } end_cmd = 1; } - if (host->data) + if (host->data) { mmc_dma_cleanup(host); + OMAP_HSMMC_WRITE(host->base, SYSCTL, + OMAP_HSMMC_READ(host->base, + SYSCTL) | SRD); + while (OMAP_HSMMC_READ(host->base, + SYSCTL) & SRD) + ; + } } if ((status & DATA_TIMEOUT) || (status & DATA_CRC)) { -- 1.5.4.4.21.gc4a6c