From patchwork Wed Oct 8 11:24:24 2014 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Srinivas Kandagatla X-Patchwork-Id: 506636 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756135AbaJHLZQ (ORCPT ); Wed, 8 Oct 2014 07:25:16 -0400 Received: from mail-wi0-f172.google.com ([209.85.212.172]:63569 "EHLO mail-wi0-f172.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755492AbaJHLZO (ORCPT ); Wed, 8 Oct 2014 07:25:14 -0400 From: Srinivas Kandagatla To: linux-mmc@vger.kernel.org Cc: Chris Ball , Ulf Hansson , Russell King , linux-kernel@vger.kernel.org, Srinivas Kandagatla Subject: [RFC PATCH 1/2] mmc: core: fix prepared requests while doing bkops Date: Wed, 8 Oct 2014 12:24:24 +0100 Message-Id: <1412767464-6677-1-git-send-email-srinivas.kandagatla@linaro.org> X-Mailer: git-send-email 1.9.1 In-Reply-To: <1412767415-6624-1-git-send-email-srinivas.kandagatla@linaro.org> References: <1412767415-6624-1-git-send-email-srinivas.kandagatla@linaro.org> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org While starting the bkops the previously prepared request should be canceled and restarted after the bkops. As the prepared resource might already setup the dma channels and ready to be started. Now with the arrival of bkops request this prepared request can be serviced ONLY after the bkops. So holding on to the prepared request in the host driver is confusing at this point in time, so it makes sense to cleanup such dangling requests and reissue this request once bkops is done. Canceling the prepared request would give opportunity to the host drivers to perform cleanup on the prepared request. Without this patch host drivers like mmci gets confused when a blocking request like send_ext_csd(CMD8) is issued while there is already a prepared request. With the help of this patch, the driver can better manage such blocking requests and cleanup the prepared requests which are not started yet. Without this patch I hit below crash on Qualcomm APQ8064 based IFC6410 board with mmci host driver. mmci-pl18x 12400000.sdcc: error during DMA transfer! Unable to handle kernel paging request at virtual address 40000000 pgd = c0204000 [40000000] *pgd=00000000 Internal error: Oops: 805 [#1] SMP ARM Modules linked in: ipv6 ath6kl_sdio ath6kl_core CPU: 0 PID: 0 Comm: swapper/0 Tainted: G W 3.17.0-rc7-linaro-multi-v7 #1 task: c0c9d7e0 ti: c0c92000 task.ti: c0c92000 PC is at v7_dma_inv_range+0x34/0x4c LR is at __dma_page_dev_to_cpu+0x80/0x100 pc : [] lr : [] psr: 400f0193 sp : c0c93e20 ip : c0c9a478 fp : c08ea538 r10: c0c9f548 r9 : 00000002 r8 : e97d9000 r7 : 00000200 r6 : c0c9d504 r5 : c0db0880 r4 : 00000000 r3 : 0000003f r2 : 00000040 r1 : 40000200 r0 : 40000000 Flags: nZcv IRQs off FIQs on Mode SVC_32 ISA ARM Segment kernel Control: 10c5787d Table: a9ef406a DAC: 00000015 Process swapper/0 (pid: 0, stack limit = 0xc0c92250) Stack: (0xc0c93e20 to 0xc0c94000) 3e20: c021f058 e9a17178 e9a171bc e99dfd6c 00000001 00000001 e995de10 00000002 3e40: 00000000 c021b574 00000000 c04bc4a4 00000000 e9b49ac0 c0ce6e6c e99dfda4 3e60: 00000088 e9810780 c0d8291c c072ea58 00000000 c072d3fc 00000000 c072f534 3e80: 00000000 e9b49ac0 00000100 c0c9a444 00000088 c072f6b4 c072f5d4 e9d40080 3ea0: e98107dc 00000000 00000000 c0280a60 00000000 7d55bf61 e9810780 e98107dc 3ec0: 00000000 f0002000 c0d460e8 c0d460e8 c0c92000 c0280b60 e9810780 c0ce7190 3ee0: 00000000 c028369c c02835f4 00000088 00000088 c0280278 c0c8ec70 c020f080 3f00: f000200c c0c9a958 c0c93f28 c02088e4 c04bd630 c04bd5bc 200f0013 ffffffff 3f20: c0c93f5c c0212800 00000001 a987c000 c0c93f3c c04bd574 00000000 0000015b 3f40: ea7a0e40 00000000 c0d460e8 c0d460e8 c0c92000 c08ea538 29b12000 c0c93f70 3f60: c04bd630 c04bd5bc 200f0013 ffffffff c04bd574 c071bd24 7d50c9b4 c0719a44 3f80: 7d50c9b4 0000015b c0c9a498 c0c92028 c0c9a498 c0c9a4fc ea7a0e40 c0c8ee38 3fa0: c0d460e8 c0276198 00000000 c0d8291a 00000000 c0c9a400 00000000 c0be0bc4 3fc0: ffffffff ffffffff c0be05f8 00000000 00000000 c0c533d8 c0d82ed4 c0c9a47c 3fe0: c0c533d4 c0c9e870 8020406a 511f06f0 00000000 80208074 00000000 00000000 [] (v7_dma_inv_range) from [] (__dma_page_dev_to_cpu+0x80/0x100) [] (__dma_page_dev_to_cpu) from [] (arm_dma_unmap_sg+0x5c/0x84) [] (arm_dma_unmap_sg) from [] (mmci_dma_unmap.isra.16+0x60/0x74) [] (mmci_dma_unmap.isra.16) from [] (mmci_data_irq+0x1fc/0x29c) [] (mmci_data_irq) from [] (mmci_irq+0xe0/0x114) [] (mmci_irq) from [] (handle_irq_event_percpu+0x78/0x134) [] (handle_irq_event_percpu) from [] (handle_irq_event+0x44/0x64) [] (handle_irq_event) from [] (handle_fasteoi_irq+0xa8/0x1a8) [] (handle_fasteoi_irq) from [] (generic_handle_irq+0x2c/0x3c) [] (generic_handle_irq) from [] (handle_IRQ+0x40/0x90) [] (handle_IRQ) from [] (gic_handle_irq+0x38/0x68) [] (gic_handle_irq) from [] (__irq_svc+0x40/0x54) Exception stack(0xc0c93f28 to 0xc0c93f70) 3f20: 00000001 a987c000 c0c93f3c c04bd574 00000000 0000015b 3f40: ea7a0e40 00000000 c0d460e8 c0d460e8 c0c92000 c08ea538 29b12000 c0c93f70 3f60: c04bd630 c04bd5bc 200f0013 ffffffff [] (__irq_svc) from [] (msm_cpu_pm_enter_sleep+0x48/0x4c) [] (msm_cpu_pm_enter_sleep) from [] (qcom_lpm_enter_spc+0x20/0x2c) [] (qcom_lpm_enter_spc) from [] (cpuidle_enter_state+0x44/0xf0) [] (cpuidle_enter_state) from [] (cpu_startup_entry+0x1f4/0x238) [] (cpu_startup_entry) from [] (start_kernel+0x384/0x390) Code: 1e070f3e e1110003 e1c11003 1e071f3e (ee070f36) ---[ end trace cf6cb3f6432c9834 ]--- Kernel panic - not syncing: Fatal exception in interrup Reported-by: Nicolas Dechesne Signed-off-by: Srinivas Kandagatla --- drivers/mmc/core/core.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index d03a080..4d9b142 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -538,8 +538,18 @@ struct mmc_async_req *mmc_start_req(struct mmc_host *host, if (host->card && mmc_card_mmc(host->card) && ((mmc_resp_type(host->areq->mrq->cmd) == MMC_RSP_R1) || (mmc_resp_type(host->areq->mrq->cmd) == MMC_RSP_R1B)) && - (host->areq->mrq->cmd->resp[0] & R1_EXCEPTION_EVENT)) + (host->areq->mrq->cmd->resp[0] & R1_EXCEPTION_EVENT)) { + + /* Cancel the prepared request */ + if (areq) + mmc_post_req(host, areq->mrq, -EINVAL); + mmc_start_bkops(host->card, true); + + /* prepare the request again */ + if (areq) + mmc_pre_req(host, areq->mrq, !host->areq); + } } if (!err && areq)