From patchwork Tue Jul 23 07:08:41 2013 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Sujit Reddy Thumma X-Patchwork-Id: 2831747 Return-Path: X-Original-To: patchwork-linux-arm-msm@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork2.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.19.201]) by patchwork2.web.kernel.org (Postfix) with ESMTP id 93C6AC0319 for ; Tue, 23 Jul 2013 07:09:15 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id D227220113 for ; Tue, 23 Jul 2013 07:09:13 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id C4D9C20108 for ; Tue, 23 Jul 2013 07:09:11 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753406Ab3GWHJL (ORCPT ); Tue, 23 Jul 2013 03:09:11 -0400 Received: from smtp.codeaurora.org ([198.145.11.231]:42389 "EHLO smtp.codeaurora.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753133Ab3GWHJK (ORCPT ); Tue, 23 Jul 2013 03:09:10 -0400 Received: from smtp.codeaurora.org (localhost [127.0.0.1]) by smtp.codeaurora.org (Postfix) with ESMTP id 6E0BD13EF80; Tue, 23 Jul 2013 07:09:09 +0000 (UTC) Received: by smtp.codeaurora.org (Postfix, from userid 486) id 5CE9113F01B; Tue, 23 Jul 2013 07:09:09 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on mail.kernel.org X-Spam-Level: X-Spam-Status: No, score=-6.9 required=5.0 tests=BAYES_00, RCVD_IN_DNSWL_HI, RP_MATCHES_RCVD, UNPARSEABLE_RELAY autolearn=ham version=3.3.1 Received: from srthumm-ics.qualcomm.com (unknown [202.46.23.54]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) (Authenticated sender: sthumma@smtp.codeaurora.org) by smtp.codeaurora.org (Postfix) with ESMTPSA id 42F3613EF80; Tue, 23 Jul 2013 07:09:04 +0000 (UTC) From: Sujit Reddy Thumma To: Vinayak Holikatti , Santosh Y Cc: "James E.J. Bottomley" , linux-scsi@vger.kernel.org, Sujit Reddy Thumma , linux-arm-msm@vger.kernel.org Subject: [PATCH V4 3/4] scsi: ufs: Fix device and host reset methods Date: Tue, 23 Jul 2013 12:38:41 +0530 Message-Id: <1374563322-22846-4-git-send-email-sthumma@codeaurora.org> X-Mailer: git-send-email 1.7.8.3 In-Reply-To: <1374563322-22846-1-git-send-email-sthumma@codeaurora.org> References: <1374563322-22846-1-git-send-email-sthumma@codeaurora.org> X-Virus-Scanned: ClamAV using ClamSMTP Sender: linux-arm-msm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-arm-msm@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP As of now SCSI initiated error handling is broken because, the reset APIs don't try to bring back the device initialized and ready for further transfers. In case of timeouts, the scsi error handler takes care of handling aborts and resets. Improve the error handling in such scenario by resetting the device and host and re-initializing them in proper manner. Signed-off-by: Sujit Reddy Thumma --- drivers/scsi/ufs/ufshcd.c | 437 +++++++++++++++++++++++++++++++++++++++------ drivers/scsi/ufs/ufshcd.h | 2 + 2 files changed, 381 insertions(+), 58 deletions(-) diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 3f80396..1a0ceb2 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -69,9 +69,15 @@ enum { /* UFSHCD states */ enum { - UFSHCD_STATE_OPERATIONAL, UFSHCD_STATE_RESET, UFSHCD_STATE_ERROR, + UFSHCD_STATE_OPERATIONAL, +}; + +/* UFSHCD error handling flags */ +enum { + UFSHCD_EH_HOST_RESET_PENDING = (1 << 0), + UFSHCD_EH_DEVICE_RESET_PENDING = (1 << 1), }; /* Interrupt configuration options */ @@ -87,6 +93,22 @@ enum { INT_AGGR_CONFIG, }; +#define ufshcd_set_device_reset_pending(h) \ + (h->eh_flags |= UFSHCD_EH_DEVICE_RESET_PENDING) +#define ufshcd_set_host_reset_pending(h) \ + (h->eh_flags |= UFSHCD_EH_HOST_RESET_PENDING) +#define ufshcd_device_reset_pending(h) \ + (h->eh_flags & UFSHCD_EH_DEVICE_RESET_PENDING) +#define ufshcd_host_reset_pending(h) \ + (h->eh_flags & UFSHCD_EH_HOST_RESET_PENDING) +#define ufshcd_clear_device_reset_pending(h) \ + (h->eh_flags &= ~UFSHCD_EH_DEVICE_RESET_PENDING) +#define ufshcd_clear_host_reset_pending(h) \ + (h->eh_flags &= ~UFSHCD_EH_HOST_RESET_PENDING) + +static void ufshcd_tmc_handler(struct ufs_hba *hba); +static void ufshcd_async_scan(void *data, async_cookie_t cookie); + /* * ufshcd_wait_for_register - wait for register value to change * @hba - per-adapter interface @@ -840,9 +862,22 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd) tag = cmd->request->tag; - if (hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL) { + switch (hba->ufshcd_state) { + case UFSHCD_STATE_OPERATIONAL: + break; + case UFSHCD_STATE_RESET: err = SCSI_MLQUEUE_HOST_BUSY; goto out; + case UFSHCD_STATE_ERROR: + set_host_byte(cmd, DID_ERROR); + cmd->scsi_done(cmd); + goto out; + default: + dev_WARN_ONCE(hba->dev, 1, "%s: invalid state %d\n", + __func__, hba->ufshcd_state); + set_host_byte(cmd, DID_BAD_TARGET); + cmd->scsi_done(cmd); + goto out; } /* acquire the tag to make sure device cmds don't use it */ @@ -1495,8 +1530,6 @@ static int ufshcd_make_hba_operational(struct ufs_hba *hba) if (hba->ufshcd_state == UFSHCD_STATE_RESET) scsi_unblock_requests(hba->host); - hba->ufshcd_state = UFSHCD_STATE_OPERATIONAL; - out: return err; } @@ -2212,6 +2245,100 @@ out: } /** + * ufshcd_utrl_is_rsr_enabled - check if run-stop register is enabled + * @hba: per-adapter instance + */ +static bool ufshcd_utrl_is_rsr_enabled(struct ufs_hba *hba) +{ + return ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_LIST_RUN_STOP) & 0x1; +} + +/** + * ufshcd_utmrl_is_rsr_enabled - check if run-stop register is enabled + * @hba: per-adapter instance + */ +static bool ufshcd_utmrl_is_rsr_enabled(struct ufs_hba *hba) +{ + return ufshcd_readl(hba, REG_UTP_TASK_REQ_LIST_RUN_STOP) & 0x1; +} + +/** + * ufshcd_complete_pending_tasks - complete outstanding tasks + * @hba: per adapter instance + * + * Abort in-progress task management commands and wakeup + * waiting threads. + * + * Returns non-zero error value when failed to clear all the commands. + */ +static int ufshcd_complete_pending_tasks(struct ufs_hba *hba) +{ + int err = 0; + unsigned long flags; + + if (!hba->outstanding_tasks) + goto out; + + /* Clear UTMRL only when run-stop is enabled */ + if (ufshcd_utmrl_is_rsr_enabled(hba)) + ufshcd_writel(hba, ~hba->outstanding_tasks, + REG_UTP_TASK_REQ_LIST_CLEAR); + + /* poll for max. 1 sec to clear door bell register by h/w */ + err = ufshcd_wait_for_register(hba, REG_UTP_TASK_REQ_DOOR_BELL, + hba->outstanding_tasks, ~hba->outstanding_tasks, + 1000, 1000); + + spin_lock_irqsave(hba->host->host_lock, flags); + /* complete commands that were cleared out */ + ufshcd_tmc_handler(hba); + spin_unlock_irqrestore(hba->host->host_lock, flags); +out: + if (err) + dev_err(hba->dev, "%s: failed, still pending = 0x%.8x\n", + __func__, ufshcd_readl(hba, REG_UTP_TASK_REQ_DOOR_BELL)); + return err; +} + +/** + * ufshcd_complete_pending_reqs - complete outstanding requests + * @hba: per adapter instance + * + * Abort in-progress transfer request commands and return them to SCSI. + * + * Returns non-zero error value when failed to clear all the commands. + */ +static int ufshcd_complete_pending_reqs(struct ufs_hba *hba) +{ + int err = 0; + unsigned long flags; + + /* check if we completed all of them */ + if (!hba->outstanding_reqs) + goto out; + + /* Clear UTRL only when run-stop is enabled */ + if (ufshcd_utrl_is_rsr_enabled(hba)) + ufshcd_writel(hba, ~hba->outstanding_reqs, + REG_UTP_TRANSFER_REQ_LIST_CLEAR); + + /* poll for max. 1 sec to clear door bell register by h/w */ + err = ufshcd_wait_for_register(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL, + hba->outstanding_reqs, ~hba->outstanding_reqs, + 1000, 1000); + + spin_lock_irqsave(hba->host->host_lock, flags); + /* complete commands that were cleared out */ + ufshcd_transfer_req_compl(hba); + spin_unlock_irqrestore(hba->host->host_lock, flags); +out: + if (err) + dev_err(hba->dev, "%s: failed, still pending = 0x%.8x\n", + __func__, ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL)); + return err; +} + +/** * ufshcd_fatal_err_handler - handle fatal errors * @hba: per adapter instance */ @@ -2245,8 +2372,12 @@ static void ufshcd_err_handler(struct ufs_hba *hba) } return; fatal_eh: - hba->ufshcd_state = UFSHCD_STATE_ERROR; - schedule_work(&hba->feh_workq); + /* handle fatal errors only when link is functional */ + if (hba->ufshcd_state == UFSHCD_STATE_OPERATIONAL) { + /* block commands at driver layer until error is handled */ + hba->ufshcd_state = UFSHCD_STATE_ERROR; + schedule_work(&hba->feh_workq); + } } /** @@ -2411,75 +2542,155 @@ static int ufshcd_issue_tm_cmd(struct ufs_hba *hba, int lun_id, int task_id, } /** - * ufshcd_device_reset - reset device and abort all the pending commands - * @cmd: SCSI command pointer + * ufshcd_dme_end_point_reset - Notify device Unipro to perform reset + * @hba: per adapter instance * - * Returns SUCCESS/FAILED + * UIC_CMD_DME_END_PT_RST resets the UFS device completely, the UFS flags, + * attributes and descriptors are reset to default state. Callers are + * expected to initialize the whole device again after this. + * + * Returns zero on success, non-zero on failure */ -static int ufshcd_device_reset(struct scsi_cmnd *cmd) +static int ufshcd_dme_end_point_reset(struct ufs_hba *hba) { - struct Scsi_Host *host; - struct ufs_hba *hba; - unsigned int tag; - u32 pos; - int err; - u8 resp; - struct ufshcd_lrb *lrbp; + struct uic_command uic_cmd = {0}; + int ret; - host = cmd->device->host; - hba = shost_priv(host); - tag = cmd->request->tag; + uic_cmd.command = UIC_CMD_DME_END_PT_RST; - lrbp = &hba->lrb[tag]; - err = ufshcd_issue_tm_cmd(hba, lrbp->lun, lrbp->task_tag, - UFS_LOGICAL_RESET, &resp); - if (err || resp != UPIU_TASK_MANAGEMENT_FUNC_COMPL) { - err = FAILED; + ret = ufshcd_send_uic_cmd(hba, &uic_cmd); + if (ret) + dev_err(hba->dev, "%s: error code %d\n", __func__, ret); + + return ret; +} + +/** + * ufshcd_dme_reset - Local UniPro reset + * @hba: per adapter instance + * + * Returns zero on success, non-zero on failure + */ +static int ufshcd_dme_reset(struct ufs_hba *hba) +{ + struct uic_command uic_cmd = {0}; + int ret; + + uic_cmd.command = UIC_CMD_DME_RESET; + + ret = ufshcd_send_uic_cmd(hba, &uic_cmd); + if (ret) + dev_err(hba->dev, "%s: error code %d\n", __func__, ret); + + return ret; + +} + +/** + * ufshcd_dme_enable - Local UniPro DME Enable + * @hba: per adapter instance + * + * Returns zero on success, non-zero on failure + */ +static int ufshcd_dme_enable(struct ufs_hba *hba) +{ + struct uic_command uic_cmd = {0}; + int ret; + uic_cmd.command = UIC_CMD_DME_ENABLE; + + ret = ufshcd_send_uic_cmd(hba, &uic_cmd); + if (ret) + dev_err(hba->dev, "%s: error code %d\n", __func__, ret); + + return ret; + +} + +/** + * ufshcd_device_reset_and_restore - reset and restore device + * @hba: per-adapter instance + * + * Note that the device reset issues DME_END_POINT_RESET which + * may reset entire device and restore device attributes to + * default state. + * + * Returns zero on success, non-zero on failure + */ +static int ufshcd_device_reset_and_restore(struct ufs_hba *hba) +{ + int err = 0; + u32 reg; + + err = ufshcd_dme_end_point_reset(hba); + if (err) goto out; - } else { - err = SUCCESS; - } - for (pos = 0; pos < hba->nutrs; pos++) { - if (test_bit(pos, &hba->outstanding_reqs) && - (hba->lrb[tag].lun == hba->lrb[pos].lun)) { + /* restore communication with the device */ + err = ufshcd_dme_reset(hba); + if (err) + goto out; - /* clear the respective UTRLCLR register bit */ - ufshcd_utrl_clear(hba, pos); + err = ufshcd_dme_enable(hba); + if (err) + goto out; - clear_bit(pos, &hba->outstanding_reqs); + err = ufshcd_dme_link_startup(hba); + if (err) + goto out; - if (hba->lrb[pos].cmd) { - scsi_dma_unmap(hba->lrb[pos].cmd); - hba->lrb[pos].cmd->result = - DID_ABORT << 16; - hba->lrb[pos].cmd->scsi_done(cmd); - hba->lrb[pos].cmd = NULL; - clear_bit_unlock(pos, &hba->lrb_in_use); - wake_up(&hba->dev_cmd.tag_wq); - } - } - } /* end of for */ + /* check if link is up and device is detected */ + reg = ufshcd_readl(hba, REG_CONTROLLER_STATUS); + if (!ufshcd_is_device_present(reg)) { + dev_err(hba->dev, "Device not present\n"); + err = -ENXIO; + goto out; + } + + ufshcd_clear_device_reset_pending(hba); out: + dev_dbg(hba->dev, "%s: done err = %d\n", __func__, err); return err; } /** - * ufshcd_host_reset - Main reset function registered with scsi layer - * @cmd: SCSI command pointer + * ufshcd_host_reset_and_restore - reset and restore host controller + * @hba: per-adapter instance * - * Returns SUCCESS/FAILED + * Note that host controller reset may issue DME_RESET to + * local and remote (device) Uni-Pro stack and the attributes + * are reset to default state. + * + * Returns zero on success, non-zero on failure */ -static int ufshcd_host_reset(struct scsi_cmnd *cmd) +static int ufshcd_host_reset_and_restore(struct ufs_hba *hba) { - struct ufs_hba *hba; + int err; + async_cookie_t cookie; + unsigned long flags; - hba = shost_priv(cmd->device->host); + /* Reset the host controller */ + spin_lock_irqsave(hba->host->host_lock, flags); + ufshcd_hba_stop(hba); + spin_unlock_irqrestore(hba->host->host_lock, flags); - if (hba->ufshcd_state == UFSHCD_STATE_RESET) - return SUCCESS; + err = ufshcd_hba_enable(hba); + if (err) + goto out; + + /* Establish the link again and restore the device */ + cookie = async_schedule(ufshcd_async_scan, hba); + /* wait for async scan to be completed */ + async_synchronize_cookie(++cookie); + if (hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL) + err = -EIO; +out: + if (err) + dev_err(hba->dev, "%s: Host init failed %d\n", __func__, err); + else + ufshcd_clear_host_reset_pending(hba); - return ufshcd_do_reset(hba); + dev_dbg(hba->dev, "%s: done err = %d\n", __func__, err); + return err; } /** @@ -2580,6 +2791,110 @@ out: } /** + * ufshcd_reset_and_restore - resets device or host or both + * @hba: per-adapter instance + * + * Reset and recover device, host and re-establish link. This + * is helpful to recover the communication in fatal error conditions. + * + * Returns zero on success, non-zero on failure + */ +static int ufshcd_reset_and_restore(struct ufs_hba *hba) +{ + int err = 0; + + if (ufshcd_device_reset_pending(hba) && + !ufshcd_host_reset_pending(hba)) { + err = ufshcd_device_reset_and_restore(hba); + if (err) { + ufshcd_clear_device_reset_pending(hba); + ufshcd_set_host_reset_pending(hba); + } + } + + if (ufshcd_host_reset_pending(hba)) + err = ufshcd_host_reset_and_restore(hba); + + /* + * Due to reset the door-bell might be cleared, clear + * outstanding requests in s/w here. + */ + ufshcd_complete_pending_reqs(hba); + ufshcd_complete_pending_tasks(hba); + + return err; +} + +static int ufshcd_eh_reset_handler(struct scsi_cmnd *cmd, int eh_flag) +{ + int err; + unsigned long flags; + struct ufs_hba *hba; + + hba = shost_priv(cmd->device->host); + + /* + * Check if there is any race with fatal error handling. + * If so, wait for it to complete. Even though fatal error + * handling does reset and restore in some cases, don't assume + * anything out of it. We are just avoiding race here. + */ + do { + spin_lock_irqsave(hba->host->host_lock, flags); + if (!(work_pending(&hba->feh_workq) || + hba->ufshcd_state == UFSHCD_STATE_RESET)) + break; + spin_unlock_irqrestore(hba->host->host_lock, flags); + dev_dbg(hba->dev, "%s: reset in progress\n", __func__); + flush_work_sync(&hba->feh_workq); + } while (1); + + hba->ufshcd_state = UFSHCD_STATE_RESET; + if (eh_flag & UFSHCD_EH_DEVICE_RESET_PENDING) + ufshcd_set_device_reset_pending(hba); + else + ufshcd_set_host_reset_pending(hba); + spin_unlock_irqrestore(hba->host->host_lock, flags); + + err = ufshcd_reset_and_restore(hba); + + spin_lock_irqsave(hba->host->host_lock, flags); + if (!err) { + err = SUCCESS; + hba->ufshcd_state = UFSHCD_STATE_OPERATIONAL; + } else { + err = FAILED; + hba->ufshcd_state = UFSHCD_STATE_ERROR; + } + spin_unlock_irqrestore(hba->host->host_lock, flags); + + return err; +} + +/** + * ufshcd_eh_device_reset_handler - device reset handler registered to + * scsi layer. + * @cmd - SCSI command pointer + * + * Returns SUCCESS/FAILED + */ +static int ufshcd_eh_device_reset_handler(struct scsi_cmnd *cmd) +{ + return ufshcd_eh_reset_handler(cmd, UFSHCD_EH_DEVICE_RESET_PENDING); +} + +/** + * ufshcd_eh_host_reset_handler - host reset handler registered to scsi layer + * @cmd - SCSI command pointer + * + * Returns SUCCESS/FAILED + */ +static int ufshcd_eh_host_reset_handler(struct scsi_cmnd *cmd) +{ + return ufshcd_eh_reset_handler(cmd, UFSHCD_EH_HOST_RESET_PENDING); +} + +/** * ufshcd_async_scan - asynchronous execution for link startup * @data: data pointer to pass to this function * @cookie: cookie data @@ -2602,8 +2917,14 @@ static void ufshcd_async_scan(void *data, async_cookie_t cookie) goto out; ufshcd_force_reset_auto_bkops(hba); - scsi_scan_host(hba->host); - pm_runtime_put_sync(hba->dev); + hba->ufshcd_state = UFSHCD_STATE_OPERATIONAL; + + /* If we are in error handling context no need to scan the host */ + if (!(ufshcd_device_reset_pending(hba) || + ufshcd_host_reset_pending(hba))) { + scsi_scan_host(hba->host); + pm_runtime_put_sync(hba->dev); + } out: return; } @@ -2616,8 +2937,8 @@ static struct scsi_host_template ufshcd_driver_template = { .slave_alloc = ufshcd_slave_alloc, .slave_destroy = ufshcd_slave_destroy, .eh_abort_handler = ufshcd_abort, - .eh_device_reset_handler = ufshcd_device_reset, - .eh_host_reset_handler = ufshcd_host_reset, + .eh_device_reset_handler = ufshcd_eh_device_reset_handler, + .eh_host_reset_handler = ufshcd_eh_host_reset_handler, .this_id = -1, .sg_tablesize = SG_ALL, .cmd_per_lun = UFSHCD_CMD_PER_LUN, diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index fe7c947..1e0585c 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -179,6 +179,7 @@ struct ufs_dev_cmd { * @tm_condition: condition variable for task management * @tm_slots_in_use: bit map of task management request slots in use * @ufshcd_state: UFSHCD states + * @eh_flags: Error handling flags * @intr_mask: Interrupt Mask Bits * @ee_ctrl_mask: Exception event control mask * @feh_workq: Work queue for fatal controller error handling @@ -224,6 +225,7 @@ struct ufs_hba { unsigned long tm_slots_in_use; u32 ufshcd_state; + u32 eh_flags; u32 intr_mask; u16 ee_ctrl_mask;