mmc: core: Fix some driver hangs when dealing with broken devices

There are infinite loops in the mmc code that can be caused by bad
hardware.  The code will loop forever if the device never comes back
from program mode, R1_STATE_PRG, and it is not ready for data,
R1_READY_FOR_DATA.

A long timeout is added to prevent the code from looping forever.
The timeout will occur if the device never comes back from program
state or the device never becomes ready for data.

It's not clear whether the timeout will do more than log a pr_err()
and then start a fresh hang all over again.  We may need to extend
this patch later to perform some kind of reset of the device (is
that possible?) or rejection of new I/O to the device.

Signed-off-by: Trey Ramsay <tramsay@linux.vnet.ibm.com>
Signed-off-by: Chris Ball <cjb@laptop.org>

1 files changed, 15 insertions, 0 deletions

diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 172a768036d8..8e6050869382 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -57,6 +57,7 @@ MODULE_ALIAS("mmc:block");
 #define INAND_CMD38_ARG_SECERASE 0x80
 #define INAND_CMD38_ARG_SECTRIM1 0x81
 #define INAND_CMD38_ARG_SECTRIM2 0x88
+#define MMC_BLK_TIMEOUT_MS  (10 * 60 * 1000)        /* 10 minute timeout */
 
 static DEFINE_MUTEX(block_mutex);
 
@@ -1034,6 +1035,9 @@ static int mmc_blk_err_check(struct mmc_card *card,
          */
         if (!mmc_host_is_spi(card->host) && rq_data_dir(req) != READ) {
                 u32 status;
+                unsigned long timeout;
+
+                timeout = jiffies + msecs_to_jiffies(MMC_BLK_TIMEOUT_MS);
                 do {
                         int err = get_card_status(card, &status, 5);
                         if (err) {
@@ -1041,6 +1045,17 @@ static int mmc_blk_err_check(struct mmc_card *card,
                                        req->rq_disk->disk_name, err);
                                 return MMC_BLK_CMD_ERR;
                         }
+
+                        /* Timeout if the device never becomes ready for data
+                         * and never leaves the program state.
+                         */
+                        if (time_after(jiffies, timeout)) {
+                                pr_err("%s: Card stuck in programming state!"\
+                                        " %s %s\n", mmc_hostname(card->host),
+                                        req->rq_disk->disk_name, __func__);
+
+                                return MMC_BLK_CMD_ERR;
+                        }
                         /*
                          * Some cards mishandle the status bits,
                          * so make sure to check both the busy