From 774514bf977377c9137640a0310bd64eed0f7323 Mon Sep 17 00:00:00 2001 From: Yann Gautier Date: Thu, 25 Feb 2021 15:54:54 +0100 Subject: mmc: mmci: Add MMC_CAP_NEED_RSP_BUSY for the stm32 variants An issue has been observed on STM32MP157C-EV1 board, with an erase command with secure erase argument, ending up waiting for ~4 hours before timeout. The requested busy timeout from the mmc core ends up with 14784000ms (~4 hours), but the supported host->max_busy_timeout is 86767ms, which leads to that the core switch to use an R1 response in favor of the R1B and polls for busy with the host->card_busy() ops. In this case the polling doesn't work as expected, as we never detects that the card stops signaling busy, which leads to the following message: mmc1: Card stuck being busy! __mmc_poll_for_busy The problem boils done to that the stm32 variants can't use R1 responses in favor of R1B responses, as it leads to an internal state machine in the controller to get stuck. To continue to process requests, it would need to be reset. To fix this problem, let's set MMC_CAP_NEED_RSP_BUSY for the stm32 variant, which prevent the mmc core from switching to R1 responses. Additionally, let's cap the cmd->busy_timeout to the host->max_busy_timeout, thus rely on 86767ms to be sufficient (~66 seconds was need for this test case). Fixes: 94fe2580a2f3 ("mmc: core: Enable erase/discard/trim support for all mmc hosts") Signed-off-by: Yann Gautier Link: https://lore.kernel.org/r/20210225145454.12780-1-yann.gautier@foss.st.com Cc: stable@vger.kernel.org [Ulf: Simplified the code and extended the commit message] Signed-off-by: Ulf Hansson --- drivers/mmc/host/mmci.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c index 17dbc81c221e..984d35055156 100644 --- a/drivers/mmc/host/mmci.c +++ b/drivers/mmc/host/mmci.c @@ -1242,7 +1242,11 @@ mmci_start_command(struct mmci_host *host, struct mmc_command *cmd, u32 c) if (!cmd->busy_timeout) cmd->busy_timeout = 10 * MSEC_PER_SEC; - clks = (unsigned long long)cmd->busy_timeout * host->cclk; + if (cmd->busy_timeout > host->mmc->max_busy_timeout) + clks = (unsigned long long)host->mmc->max_busy_timeout * host->cclk; + else + clks = (unsigned long long)cmd->busy_timeout * host->cclk; + do_div(clks, MSEC_PER_SEC); writel_relaxed(clks, host->base + MMCIDATATIMER); } @@ -2151,6 +2155,10 @@ static int mmci_probe(struct amba_device *dev, mmc->caps |= MMC_CAP_WAIT_WHILE_BUSY; } + /* Variants with mandatory busy timeout in HW needs R1B responses. */ + if (variant->busy_timeout) + mmc->caps |= MMC_CAP_NEED_RSP_BUSY; + /* Prepare a CMD12 - needed to clear the DPSM on some variants. */ host->stop_abort.opcode = MMC_STOP_TRANSMISSION; host->stop_abort.arg = 0; -- cgit v1.2.3 From 66fbacccbab91e6e55d9c8f1fc0910a8eb6c81f7 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 3 Mar 2021 11:26:14 +0200 Subject: mmc: core: Fix partition switch time for eMMC Avoid the following warning by always defining partition switch time: [ 3.209874] mmc1: unspecified timeout for CMD6 - use generic [ 3.222780] ------------[ cut here ]------------ [ 3.233363] WARNING: CPU: 1 PID: 111 at drivers/mmc/core/mmc_ops.c:575 __mmc_switch+0x200/0x204 Reported-by: Paul Fertser Fixes: 1c447116d017 ("mmc: mmc: Fix partition switch timeout for some eMMCs") Signed-off-by: Adrian Hunter Link: https://lore.kernel.org/r/168bbfd6-0c5b-5ace-ab41-402e7937c46e@intel.com Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson --- drivers/mmc/core/mmc.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'drivers') diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index 0d80b72ddde8..8741271d3971 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -423,10 +423,6 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd) /* EXT_CSD value is in units of 10ms, but we store in ms */ card->ext_csd.part_time = 10 * ext_csd[EXT_CSD_PART_SWITCH_TIME]; - /* Some eMMC set the value too low so set a minimum */ - if (card->ext_csd.part_time && - card->ext_csd.part_time < MMC_MIN_PART_SWITCH_TIME) - card->ext_csd.part_time = MMC_MIN_PART_SWITCH_TIME; /* Sleep / awake timeout in 100ns units */ if (sa_shift > 0 && sa_shift <= 0x17) @@ -616,6 +612,17 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd) card->ext_csd.data_sector_size = 512; } + /* + * GENERIC_CMD6_TIME is to be used "unless a specific timeout is defined + * when accessing a specific field", so use it here if there is no + * PARTITION_SWITCH_TIME. + */ + if (!card->ext_csd.part_time) + card->ext_csd.part_time = card->ext_csd.generic_cmd6_time; + /* Some eMMC set the value too low so set a minimum */ + if (card->ext_csd.part_time < MMC_MIN_PART_SWITCH_TIME) + card->ext_csd.part_time = MMC_MIN_PART_SWITCH_TIME; + /* eMMC v5 or later */ if (card->ext_csd.rev >= 7) { memcpy(card->ext_csd.fwrev, &ext_csd[EXT_CSD_FIRMWARE_VERSION], -- cgit v1.2.3 From f06391c45e83f9a731045deb23df7cc3814fd795 Mon Sep 17 00:00:00 2001 From: Frank Li Date: Wed, 3 Mar 2021 11:42:48 -0600 Subject: mmc: cqhci: Fix random crash when remove mmc module/card [ 6684.493350] Unable to handle kernel paging request at virtual address ffff800011c5b0f0 [ 6684.498531] mmc0: card 0001 removed [ 6684.501556] Mem abort info: [ 6684.509681] ESR = 0x96000047 [ 6684.512786] EC = 0x25: DABT (current EL), IL = 32 bits [ 6684.518394] SET = 0, FnV = 0 [ 6684.521707] EA = 0, S1PTW = 0 [ 6684.524998] Data abort info: [ 6684.528236] ISV = 0, ISS = 0x00000047 [ 6684.532986] CM = 0, WnR = 1 [ 6684.536129] swapper pgtable: 4k pages, 48-bit VAs, pgdp=0000000081b22000 [ 6684.543923] [ffff800011c5b0f0] pgd=00000000bffff003, p4d=00000000bffff003, pud=00000000bfffe003, pmd=00000000900e1003, pte=0000000000000000 [ 6684.557915] Internal error: Oops: 96000047 [#1] PREEMPT SMP [ 6684.564240] Modules linked in: sdhci_esdhc_imx(-) sdhci_pltfm sdhci cqhci mmc_block mmc_core fsl_jr_uio caam_jr caamkeyblob_desc caamhash_desc caamalg_desc crypto_engine rng_core authenc libdes crct10dif_ce flexcan can_dev caam error [last unloaded: mmc_core] [ 6684.587281] CPU: 0 PID: 79138 Comm: kworker/0:3H Not tainted 5.10.9-01410-g3ba33182767b-dirty #10 [ 6684.596160] Hardware name: Freescale i.MX8DXL EVK (DT) [ 6684.601320] Workqueue: kblockd blk_mq_run_work_fn [ 6684.606094] pstate: 40000005 (nZcv daif -PAN -UAO -TCO BTYPE=--) [ 6684.612286] pc : cqhci_request+0x148/0x4e8 [cqhci] ^GMessage from syslogd@ at Thu Jan 1 01:51:24 1970 ...[ 6684.617085] lr : cqhci_request+0x314/0x4e8 [cqhci] [ 6684.626734] sp : ffff80001243b9f0 [ 6684.630049] x29: ffff80001243b9f0 x28: ffff00002c3dd000 [ 6684.635367] x27: 0000000000000001 x26: 0000000000000001 [ 6684.640690] x25: ffff00002c451000 x24: 000000000000000f [ 6684.646007] x23: ffff000017e71c80 x22: ffff00002c451000 [ 6684.651326] x21: ffff00002c0f3550 x20: ffff00002c0f3550 [ 6684.656651] x19: ffff000017d46880 x18: ffff00002cea1500 [ 6684.661977] x17: 0000000000000000 x16: 0000000000000000 [ 6684.667294] x15: 000001ee628e3ed1 x14: 0000000000000278 [ 6684.672610] x13: 0000000000000001 x12: 0000000000000001 [ 6684.677927] x11: 0000000000000000 x10: 0000000000000000 [ 6684.683243] x9 : 000000000000002b x8 : 0000000000001000 [ 6684.688560] x7 : 0000000000000010 x6 : ffff00002c0f3678 [ 6684.693886] x5 : 000000000000000f x4 : ffff800011c5b000 [ 6684.699211] x3 : 000000000002d988 x2 : 0000000000000008 [ 6684.704537] x1 : 00000000000000f0 x0 : 0002d9880008102f [ 6684.709854] Call trace: [ 6684.712313] cqhci_request+0x148/0x4e8 [cqhci] [ 6684.716803] mmc_cqe_start_req+0x58/0x68 [mmc_core] [ 6684.721698] mmc_blk_mq_issue_rq+0x460/0x810 [mmc_block] [ 6684.727018] mmc_mq_queue_rq+0x118/0x2b0 [mmc_block] The problem occurs when cqhci_request() get called after cqhci_disable() as it leads to access of allocated memory that has already been freed. Let's fix the problem by calling cqhci_disable() a bit later in the remove path. Signed-off-by: Frank Li Diagnosed-by: Adrian Hunter Acked-by: Adrian Hunter Link: https://lore.kernel.org/r/20210303174248.542175-1-Frank.Li@nxp.com Fixes: f690f4409ddd ("mmc: mmc: Enable CQE's") Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson --- drivers/mmc/core/bus.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'drivers') diff --git a/drivers/mmc/core/bus.c b/drivers/mmc/core/bus.c index c2e70b757dd1..4383c262b3f5 100644 --- a/drivers/mmc/core/bus.c +++ b/drivers/mmc/core/bus.c @@ -399,11 +399,6 @@ void mmc_remove_card(struct mmc_card *card) mmc_remove_card_debugfs(card); #endif - if (host->cqe_enabled) { - host->cqe_ops->cqe_disable(host); - host->cqe_enabled = false; - } - if (mmc_card_present(card)) { if (mmc_host_is_spi(card->host)) { pr_info("%s: SPI card removed\n", @@ -416,6 +411,10 @@ void mmc_remove_card(struct mmc_card *card) of_node_put(card->dev.of_node); } + if (host->cqe_enabled) { + host->cqe_ops->cqe_disable(host); + host->cqe_enabled = false; + } + put_device(&card->dev); } - -- cgit v1.2.3