scsi: ufs: Ungate the clock synchronously

Ungating the clock asynchronously causes ufshcd_queuecommand() to return
SCSI_MLQUEUE_HOST_BUSY and hence causes commands to be requeued.  This is
suboptimal. Allow ufshcd_queuecommand() to sleep such that clock ungating
does not trigger command requeuing. Remove the ufshcd_scsi_block_requests()
and ufshcd_scsi_unblock_requests() calls because these are no longer
needed. The flush_work(&hba->clk_gating.ungate_work) call is sufficient to
make the SCSI core wait for clock ungating to complete.

Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20230529202640.11883-6-bvanassche@acm.org
Reviewed-by: Bean Huo <beanhuo@micron.com>
Reviewed-by: Bao D. Nguyen <quic_nguyenb@quicinc.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

3 files changed, 29 insertions, 61 deletions

diff --git a/drivers/ufs/core/ufs-sysfs.c b/drivers/ufs/core/ufs-sysfs.c
index 883f0e44b54e7..cdf3d5f2b77bc 100644
--- a/drivers/ufs/core/ufs-sysfs.c
+++ b/drivers/ufs/core/ufs-sysfs.c
@@ -168,7 +168,7 @@ static ssize_t auto_hibern8_show(struct device *dev,
 	}
 
 	pm_runtime_get_sync(hba->dev);
-	ufshcd_hold(hba, false);
+	ufshcd_hold(hba);
 	ahit = ufshcd_readl(hba, REG_AUTO_HIBERNATE_IDLE_TIMER);
 	ufshcd_release(hba);
 	pm_runtime_put_sync(hba->dev);
diff --git a/drivers/ufs/core/ufshcd-crypto.c b/drivers/ufs/core/ufshcd-crypto.c
index 198360fe5e8e1..f2c4422cab864 100644
--- a/drivers/ufs/core/ufshcd-crypto.c
+++ b/drivers/ufs/core/ufshcd-crypto.c
@@ -24,7 +24,7 @@ static int ufshcd_program_key(struct ufs_hba *hba,
 	u32 slot_offset = hba->crypto_cfg_register + slot * sizeof(*cfg);
 	int err = 0;
 
-	ufshcd_hold(hba, false);
+	ufshcd_hold(hba);
 
 	if (hba->vops && hba->vops->program_key) {
 		err = hba->vops->program_key(hba, cfg, slot);
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index e093ce33887c5..92436bd827be2 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -1205,7 +1205,7 @@ static int ufshcd_wait_for_doorbell_clr(struct ufs_hba *hba,
 	bool timeout = false, do_last_check = false;
 	ktime_t start;
 
-	ufshcd_hold(hba, false);
+	ufshcd_hold(hba);
 	spin_lock_irqsave(hba->host->host_lock, flags);
 	/*
 	 * Wait for all the outstanding tasks/transfer requests.
@@ -1326,7 +1326,7 @@ static int ufshcd_clock_scaling_prepare(struct ufs_hba *hba, u64 timeout_us)
 	}
 
 	/* let's not get into low power until clock scaling is completed */
-	ufshcd_hold(hba, false);
+	ufshcd_hold(hba);
 
 out:
 	return ret;
@@ -1656,7 +1656,7 @@ static ssize_t ufshcd_clkscale_enable_store(struct device *dev,
 		goto out;
 
 	ufshcd_rpm_get_sync(hba);
-	ufshcd_hold(hba, false);
+	ufshcd_hold(hba);
 
 	hba->clk_scaling.is_enabled = value;
 
@@ -1739,7 +1739,7 @@ static void ufshcd_ungate_work(struct work_struct *work)
 	spin_lock_irqsave(hba->host->host_lock, flags);
 	if (hba->clk_gating.state == CLKS_ON) {
 		spin_unlock_irqrestore(hba->host->host_lock, flags);
-		goto unblock_reqs;
+		return;
 	}
 
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
@@ -1762,25 +1762,21 @@ static void ufshcd_ungate_work(struct work_struct *work)
 		}
 		hba->clk_gating.is_suspended = false;
 	}
-unblock_reqs:
-	ufshcd_scsi_unblock_requests(hba);
 }
 
 /**
  * ufshcd_hold - Enable clocks that were gated earlier due to ufshcd_release.
  * Also, exit from hibern8 mode and set the link as active.
  * @hba: per adapter instance
- * @async: This indicates whether caller should ungate clocks asynchronously.
  */
-int ufshcd_hold(struct ufs_hba *hba, bool async)
+void ufshcd_hold(struct ufs_hba *hba)
 {
-	int rc = 0;
 	bool flush_result;
 	unsigned long flags;
 
 	if (!ufshcd_is_clkgating_allowed(hba) ||
 	    !hba->clk_gating.is_initialized)
-		goto out;
+		return;
 	spin_lock_irqsave(hba->host->host_lock, flags);
 	hba->clk_gating.active_reqs++;
 
@@ -1797,15 +1793,10 @@ start:
 		 */
 		if (ufshcd_can_hibern8_during_gating(hba) &&
 		    ufshcd_is_link_hibern8(hba)) {
-			if (async) {
-				rc = -EAGAIN;
-				hba->clk_gating.active_reqs--;
-				break;
-			}
 			spin_unlock_irqrestore(hba->host->host_lock, flags);
 			flush_result = flush_work(&hba->clk_gating.ungate_work);
 			if (hba->clk_gating.is_suspended && !flush_result)
-				goto out;
+				return;
 			spin_lock_irqsave(hba->host->host_lock, flags);
 			goto start;
 		}
@@ -1827,21 +1818,14 @@ start:
 		hba->clk_gating.state = REQ_CLKS_ON;
 		trace_ufshcd_clk_gating(dev_name(hba->dev),
 					hba->clk_gating.state);
-		if (queue_work(hba->clk_gating.clk_gating_workq,
-			       &hba->clk_gating.ungate_work))
-			ufshcd_scsi_block_requests(hba);
+		queue_work(hba->clk_gating.clk_gating_workq,
+			   &hba->clk_gating.ungate_work);
 		/*
 		 * fall through to check if we should wait for this
 		 * work to be done or not.
 		 */
 		fallthrough;
 	case REQ_CLKS_ON:
-		if (async) {
-			rc = -EAGAIN;
-			hba->clk_gating.active_reqs--;
-			break;
-		}
-
 		spin_unlock_irqrestore(hba->host->host_lock, flags);
 		flush_work(&hba->clk_gating.ungate_work);
 		/* Make sure state is CLKS_ON before returning */
@@ -1853,8 +1837,6 @@ start:
 		break;
 	}
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
-out:
-	return rc;
 }
 EXPORT_SYMBOL_GPL(ufshcd_hold);
 
@@ -2086,7 +2068,7 @@ static void ufshcd_exit_clk_gating(struct ufs_hba *hba)
 	ufshcd_remove_clk_gating_sysfs(hba);
 
 	/* Ungate the clock if necessary. */
-	ufshcd_hold(hba, false);
+	ufshcd_hold(hba);
 	hba->clk_gating.is_initialized = false;
 	ufshcd_release(hba);
 
@@ -2482,7 +2464,7 @@ int ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd)
 	if (hba->quirks & UFSHCD_QUIRK_BROKEN_UIC_CMD)
 		return 0;
 
-	ufshcd_hold(hba, false);
+	ufshcd_hold(hba);
 	mutex_lock(&hba->uic_cmd_mutex);
 	ufshcd_add_delay_before_dme_cmd(hba);
 
@@ -2885,12 +2867,6 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 
 	WARN_ONCE(tag < 0 || tag >= hba->nutrs, "Invalid tag %d\n", tag);
 
-	/*
-	 * Allows the UFS error handler to wait for prior ufshcd_queuecommand()
-	 * calls.
-	 */
-	rcu_read_lock();
-
 	switch (hba->ufshcd_state) {
 	case UFSHCD_STATE_OPERATIONAL:
 		break;
@@ -2936,13 +2912,7 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 
 	hba->req_abort_count = 0;
 
-	err = ufshcd_hold(hba, true);
-	if (err) {
-		err = SCSI_MLQUEUE_HOST_BUSY;
-		goto out;
-	}
-	WARN_ON(ufshcd_is_clkgating_allowed(hba) &&
-		(hba->clk_gating.state != CLKS_ON));
+	ufshcd_hold(hba);
 
 	lrbp = &hba->lrb[tag];
 	WARN_ON(lrbp->cmd);
@@ -2972,8 +2942,6 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 	ufshcd_send_command(hba, tag, hwq);
 
 out:
-	rcu_read_unlock();
-
 	if (ufs_trigger_eh()) {
 		unsigned long flags;
 
@@ -3267,7 +3235,7 @@ int ufshcd_query_flag(struct ufs_hba *hba, enum query_opcode opcode,
 
 	BUG_ON(!hba);
 
-	ufshcd_hold(hba, false);
+	ufshcd_hold(hba);
 	mutex_lock(&hba->dev_cmd.lock);
 	ufshcd_init_query(hba, &request, &response, opcode, idn, index,
 			selector);
@@ -3341,7 +3309,7 @@ int ufshcd_query_attr(struct ufs_hba *hba, enum query_opcode opcode,
 		return -EINVAL;
 	}
 
-	ufshcd_hold(hba, false);
+	ufshcd_hold(hba);
 
 	mutex_lock(&hba->dev_cmd.lock);
 	ufshcd_init_query(hba, &request, &response, opcode, idn, index,
@@ -3437,7 +3405,7 @@ static int __ufshcd_query_descriptor(struct ufs_hba *hba,
 		return -EINVAL;
 	}
 
-	ufshcd_hold(hba, false);
+	ufshcd_hold(hba);
 
 	mutex_lock(&hba->dev_cmd.lock);
 	ufshcd_init_query(hba, &request, &response, opcode, idn, index,
@@ -4255,7 +4223,7 @@ int ufshcd_uic_change_pwr_mode(struct ufs_hba *hba, u8 mode)
 	uic_cmd.command = UIC_CMD_DME_SET;
 	uic_cmd.argument1 = UIC_ARG_MIB(PA_PWRMODE);
 	uic_cmd.argument3 = mode;
-	ufshcd_hold(hba, false);
+	ufshcd_hold(hba);
 	ret = ufshcd_uic_pwr_ctrl(hba, &uic_cmd);
 	ufshcd_release(hba);
 
@@ -4362,7 +4330,7 @@ void ufshcd_auto_hibern8_update(struct ufs_hba *hba, u32 ahit)
 	if (update &&
 	    !pm_runtime_suspended(&hba->ufs_device_wlun->sdev_gendev)) {
 		ufshcd_rpm_get_sync(hba);
-		ufshcd_hold(hba, false);
+		ufshcd_hold(hba);
 		ufshcd_auto_hibern8_enable(hba);
 		ufshcd_release(hba);
 		ufshcd_rpm_put_sync(hba);
@@ -4955,7 +4923,7 @@ static int ufshcd_verify_dev_init(struct ufs_hba *hba)
 	int err = 0;
 	int retries;
 
-	ufshcd_hold(hba, false);
+	ufshcd_hold(hba);
 	mutex_lock(&hba->dev_cmd.lock);
 	for (retries = NOP_OUT_RETRIES; retries > 0; retries--) {
 		err = ufshcd_exec_dev_cmd(hba, DEV_CMD_TYPE_NOP,
@@ -6241,22 +6209,22 @@ static void ufshcd_err_handling_prepare(struct ufs_hba *hba)
 		ufshcd_setup_vreg(hba, true);
 		ufshcd_config_vreg_hpm(hba, hba->vreg_info.vccq);
 		ufshcd_config_vreg_hpm(hba, hba->vreg_info.vccq2);
-		ufshcd_hold(hba, false);
+		ufshcd_hold(hba);
 		if (!ufshcd_is_clkgating_allowed(hba))
 			ufshcd_setup_clocks(hba, true);
 		ufshcd_release(hba);
 		pm_op = hba->is_sys_suspended ? UFS_SYSTEM_PM : UFS_RUNTIME_PM;
 		ufshcd_vops_resume(hba, pm_op);
 	} else {
-		ufshcd_hold(hba, false);
+		ufshcd_hold(hba);
 		if (ufshcd_is_clkscaling_supported(hba) &&
 		    hba->clk_scaling.is_enabled)
 			ufshcd_suspend_clkscaling(hba);
 		ufshcd_clk_scaling_allow(hba, false);
 	}
 	ufshcd_scsi_block_requests(hba);
-	/* Drain ufshcd_queuecommand() */
-	synchronize_rcu();
+	/* Wait for ongoing ufshcd_queuecommand() calls to finish. */
+	blk_mq_wait_quiesce_done(&hba->host->tag_set);
 	cancel_work_sync(&hba->eeh_work);
 }
 
@@ -6901,7 +6869,7 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba,
 		return PTR_ERR(req);
 
 	req->end_io_data = &wait;
-	ufshcd_hold(hba, false);
+	ufshcd_hold(hba);
 
 	spin_lock_irqsave(host->host_lock, flags);
 
@@ -7138,7 +7106,7 @@ int ufshcd_exec_raw_upiu_cmd(struct ufs_hba *hba,
 		cmd_type = DEV_CMD_TYPE_NOP;
 		fallthrough;
 	case UPIU_TRANSACTION_QUERY_REQ:
-		ufshcd_hold(hba, false);
+		ufshcd_hold(hba);
 		mutex_lock(&hba->dev_cmd.lock);
 		err = ufshcd_issue_devman_upiu_cmd(hba, req_upiu, rsp_upiu,
 						   desc_buff, buff_len,
@@ -7204,7 +7172,7 @@ int ufshcd_advanced_rpmb_req_handler(struct ufs_hba *hba, struct utp_upiu_req *r
 	u16 ehs_len;
 
 	/* Protects use of hba->reserved_slot. */
-	ufshcd_hold(hba, false);
+	ufshcd_hold(hba);
 	mutex_lock(&hba->dev_cmd.lock);
 	down_read(&hba->clk_scaling_lock);
 
@@ -7439,7 +7407,7 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 
 	WARN_ONCE(tag < 0, "Invalid tag %d\n", tag);
 
-	ufshcd_hold(hba, false);
+	ufshcd_hold(hba);
 	reg = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
 	/* If command is already aborted/completed, return FAILED. */
 	if (!(test_bit(tag, &hba->outstanding_reqs))) {
@@ -9430,7 +9398,7 @@ static int __ufshcd_wl_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 	 * If we can't transition into any of the low power modes
 	 * just gate the clocks.
 	 */
-	ufshcd_hold(hba, false);
+	ufshcd_hold(hba);
 	hba->clk_gating.is_suspended = true;
 
 	if (ufshcd_is_clkscaling_supported(hba))