Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753211Ab3GAI0G (ORCPT ); Mon, 1 Jul 2013 04:26:06 -0400 Received: from imx9.toshiba.co.jp ([202.33.96.51]:39059 "EHLO imx9.toshiba.co.jp" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752798Ab3GAI0E (ORCPT ); Mon, 1 Jul 2013 04:26:04 -0400 X-Greylist: delayed 1381 seconds by postgrey-1.27 at vger.kernel.org; Mon, 01 Jul 2013 04:26:04 EDT Content-Transfer-Encoding: 7bit From: KOBAYASHI Yoshitake To: cjb@laptop.org, gregkh@linuxfoundation.org, linux-mmc@vger.kernel.org, stable@vger.kernel.org Cc: linux-kernel@vger.kernel.org, KOBAYASHI Yoshitake Subject: [PATCH 3.4-stable] mmc: block: fix a bug of error handling in MMC driver Date: Mon, 1 Jul 2013 16:56:25 +0900 Message-Id: <1372665385-8993-1-git-send-email-yoshitake.kobayashi@toshiba.co.jp> X-Mailer: git-send-email 1.7.0.4 In-Reply-To: <1368165727-32125-1-git-send-email-yoshitake.kobayashi@toshiba.co.jp> References: <1368165727-32125-1-git-send-email-yoshitake.kobayashi@toshiba.co.jp> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5118 Lines: 140 Backport for 3.4-stable for the following patch: https://lkml.org/lkml/2013/5/10/20 This patch fixes a bug of error handling in Linux MMC driver. Current MMC driver doesn't handle generic error (bit19 of device status) in write sequence. As a result, write data gets lost when generic error occurs. For example, a generic error when updating a filesystem management information causes a loss of write data and corrupts the filesystem. In the worst case, the system will never boot. This patch includes the following functionality: 1. To enable error checking for the response of CMD12 and CMD13 in write command sequence 2. To retry write sequence when a generic error occures This patch was also posted to 3.4.46-LTSI. https://patchwork.kernel.org/patch/2726801/ Signed-off-by: KOBAYASHI Yoshitake --- drivers/mmc/card/block.c | 46 +++++++++++++++++++++++++++++++++++++++++++--- 1 files changed, 43 insertions(+), 3 deletions(-) diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index 833ff16..e77053f 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -701,7 +701,7 @@ static int mmc_blk_cmd_error(struct request *req, const char *name, int error, * Otherwise we don't understand what happened, so abort. */ static int mmc_blk_cmd_recovery(struct mmc_card *card, struct request *req, - struct mmc_blk_request *brq, int *ecc_err) + struct mmc_blk_request *brq, int *ecc_err, int *gen_err) { bool prev_cmd_status_valid = true; u32 status, stop_status = 0; @@ -739,6 +739,16 @@ static int mmc_blk_cmd_recovery(struct mmc_card *card, struct request *req, (brq->cmd.resp[0] & R1_CARD_ECC_FAILED)) *ecc_err = 1; + /* Flag General errors */ + if (!mmc_host_is_spi(card->host) && rq_data_dir(req) != READ) + if ((status & R1_ERROR) || + (brq->stop.resp[0] & R1_ERROR)) { + pr_err("%s: %s: general error sending stop or status command, stop cmd response %#x, card status %#x\n", + req->rq_disk->disk_name, __func__, + brq->stop.resp[0], status); + *gen_err = 1; + } + /* * Check the current card state. If it is in some data transfer * mode, tell it to stop (and hopefully transition back to TRAN.) @@ -758,6 +768,13 @@ static int mmc_blk_cmd_recovery(struct mmc_card *card, struct request *req, return ERR_ABORT; if (stop_status & R1_CARD_ECC_FAILED) *ecc_err = 1; + if (!mmc_host_is_spi(card->host) && rq_data_dir(req) != READ) + if (stop_status & R1_ERROR) { + pr_err("%s: %s: general error sending stop command, stop cmd response %#x\n", + req->rq_disk->disk_name, __func__, + stop_status); + *gen_err = 1; + } } /* Check for set block count errors */ @@ -1007,7 +1024,7 @@ static int mmc_blk_err_check(struct mmc_card *card, mmc_active); struct mmc_blk_request *brq = &mq_mrq->brq; struct request *req = mq_mrq->req; - int ecc_err = 0; + int ecc_err = 0, gen_err = 0; /* * sbc.error indicates a problem with the set block count @@ -1021,7 +1038,7 @@ static int mmc_blk_err_check(struct mmc_card *card, */ if (brq->sbc.error || brq->cmd.error || brq->stop.error || brq->data.error) { - switch (mmc_blk_cmd_recovery(card, req, brq, &ecc_err)) { + switch (mmc_blk_cmd_recovery(card, req, brq, &ecc_err, &gen_err)) { case ERR_RETRY: return MMC_BLK_RETRY; case ERR_ABORT: @@ -1051,6 +1068,15 @@ static int mmc_blk_err_check(struct mmc_card *card, */ if (!mmc_host_is_spi(card->host) && rq_data_dir(req) != READ) { u32 status; + + /* Check stop command response */ + if (brq->stop.resp[0] & R1_ERROR) { + pr_err("%s: %s: general error sending stop command, stop cmd response %#x\n", + req->rq_disk->disk_name, __func__, + brq->stop.resp[0]); + gen_err = 1; + } + do { int err = get_card_status(card, &status, 5); if (err) { @@ -1058,6 +1084,13 @@ static int mmc_blk_err_check(struct mmc_card *card, req->rq_disk->disk_name, err); return MMC_BLK_CMD_ERR; } + + if (status & R1_ERROR) { + pr_err("%s: %s: general error sending status command, card status %#x\n", + req->rq_disk->disk_name, __func__, + status); + gen_err = 1; + } /* * Some cards mishandle the status bits, * so make sure to check both the busy @@ -1067,6 +1100,13 @@ static int mmc_blk_err_check(struct mmc_card *card, (R1_CURRENT_STATE(status) == R1_STATE_PRG)); } + /* if general error occurs, retry the write operation. */ + if (gen_err) { + pr_warning("%s: retrying write for general error\n", + req->rq_disk->disk_name); + return MMC_BLK_RETRY; + } + if (brq->data.error) { pr_err("%s: error %d transferring data, sector %u, nr %u, cmd response %#x, card status %#x\n", req->rq_disk->disk_name, brq->data.error, -- 1.7.0.4 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/