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>

3 files changed, 43 insertions, 1 deletions

diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 172a768036d..8e605086938 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
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 06c42cfb7c3..bccfd1858b0 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -42,6 +42,9 @@
 #include "sd_ops.h"
 #include "sdio_ops.h"
 
+/* If the device is not responding */
+#define MMC_CORE_TIMEOUT_MS	(10 * 60 * 1000) /* 10 minute timeout */
+
 /*
  * Background operations can take a long time, depending on the housekeeping
  * operations the card has to perform.
@@ -1631,6 +1634,7 @@ static int mmc_do_erase(struct mmc_card *card, unsigned int from,
 {
 	struct mmc_command cmd = {0};
 	unsigned int qty = 0;
+	unsigned long timeout;
 	int err;
 
 	/*
@@ -1708,6 +1712,7 @@ static int mmc_do_erase(struct mmc_card *card, unsigned int from,
 	if (mmc_host_is_spi(card->host))
 		goto out;
 
+	timeout = jiffies + msecs_to_jiffies(MMC_CORE_TIMEOUT_MS);
 	do {
 		memset(&cmd, 0, sizeof(struct mmc_command));
 		cmd.opcode = MMC_SEND_STATUS;
@@ -1721,8 +1726,19 @@ static int mmc_do_erase(struct mmc_card *card, unsigned int from,
 			err = -EIO;
 			goto out;
 		}
+
+		/* 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\n",
+				mmc_hostname(card->host), __func__);
+			err =  -EIO;
+			goto out;
+		}
+
 	} while (!(cmd.resp[0] & R1_READY_FOR_DATA) ||
-		 R1_CURRENT_STATE(cmd.resp[0]) == R1_STATE_PRG);
+		 (R1_CURRENT_STATE(cmd.resp[0]) == R1_STATE_PRG));
 out:
 	return err;
 }
diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index a0e172042e6..6d8f7012d73 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -21,6 +21,8 @@
 #include "core.h"
 #include "mmc_ops.h"
 
+#define MMC_OPS_TIMEOUT_MS	(10 * 60 * 1000) /* 10 minute timeout */
+
 static int _mmc_select_card(struct mmc_host *host, struct mmc_card *card)
 {
 	int err;
@@ -409,6 +411,7 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 {
 	int err;
 	struct mmc_command cmd = {0};
+	unsigned long timeout;
 	u32 status;
 
 	BUG_ON(!card);
@@ -437,6 +440,7 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 		return 0;
 
 	/* Must check status to be sure of no errors */
+	timeout = jiffies + msecs_to_jiffies(MMC_OPS_TIMEOUT_MS);
 	do {
 		err = mmc_send_status(card, &status);
 		if (err)
@@ -445,6 +449,13 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 			break;
 		if (mmc_host_is_spi(card->host))
 			break;
+
+		/* Timeout if the device never leaves the program state. */
+		if (time_after(jiffies, timeout)) {
+			pr_err("%s: Card stuck in programming state! %s\n",
+				mmc_hostname(card->host), __func__);
+			return -ETIMEDOUT;
+		}
 	} while (R1_CURRENT_STATE(status) == R1_STATE_PRG);
 
 	if (mmc_host_is_spi(card->host)) {