scsi: ufs: add error recovery after DL NAC error (2b83d2f9) · Commits · e / devices / android_kernel_sony_msm8994

drivers/scsi/ufs/ufs_quirks.c

+2 −0

Original line number	Diff line number	Diff line
		@@ -18,6 +18,8 @@
		static struct ufs_card_fix ufs_fixups[] = {
		/* UFS cards deviations table */
		UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL, UFS_DEVICE_NO_VCCQ),
		UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL,
		UFS_DEVICE_QUIRK_RECOVERY_FROM_DL_NAC_ERRORS),
		END_FIX
		};

drivers/scsi/ufs/ufs_quirks.h

+25 −0

Original line number	Diff line number	Diff line
		@@ -74,6 +74,31 @@ struct ufs_card_fix {
		*/
		#define UFS_DEVICE_NO_VCCQ (1 << 1)

		/*
		* Some vendor's UFS device sends back to back NACs for the DL data frames
		* causing the host controller to raise the DFES error status. Sometimes
		* such UFS devices send back to back NAC without waiting for new
		* retransmitted DL frame from the host and in such cases it might be possible
		* the Host UniPro goes into bad state without raising the DFES error
		* interrupt. If this happens then all the pending commands would timeout
		* only after respective SW command (which is generally too large).
		*
		* We can workaround such device behaviour like this:
		* - As soon as SW sees the DL NAC error, it should schedule the error handler
		* - Error handler would sleep for 50ms to see if there are any fatal errors
		* raised by UFS controller.
		* - If there are fatal errors then SW does normal error recovery.
		* - If there are no fatal errors then SW sends the NOP command to device
		* to check if link is alive.
		* - If NOP command times out, SW does normal error recovery
		* - If NOP command succeed, skip the error handling.
		*
		* If DL NAC error is seen multiple times with some vendor's UFS devices then
		* enable this quirk to initiate quick error recovery and also silence related
		* error logs to reduce spamming of kernel logs.
		*/
		#define UFS_DEVICE_QUIRK_RECOVERY_FROM_DL_NAC_ERRORS (1 << 2)

		struct ufs_hba;
		void ufs_advertise_fixup_device(struct ufs_hba *hba);
		#endif /* UFS_QUIRKS_H_ */

drivers/scsi/ufs/ufshcd.c

+131 −9

Original line number	Diff line number	Diff line
		@@ -210,9 +210,11 @@ enum {
		/* UFSHCD UIC layer error flags */
		enum {
		UFSHCD_UIC_DL_PA_INIT_ERROR = (1 << 0), /* Data link layer error */
		UFSHCD_UIC_NL_ERROR = (1 << 1), /* Network layer error */
		UFSHCD_UIC_TL_ERROR = (1 << 2), /* Transport Layer error */
		UFSHCD_UIC_DME_ERROR = (1 << 3), /* DME error */
		UFSHCD_UIC_DL_NAC_RECEIVED_ERROR = (1 << 1), /* Data link layer error */
		UFSHCD_UIC_DL_TCx_REPLAY_ERROR = (1 << 2), /* Data link layer error */
		UFSHCD_UIC_NL_ERROR = (1 << 3), /* Network layer error */
		UFSHCD_UIC_TL_ERROR = (1 << 4), /* Transport Layer error */
		UFSHCD_UIC_DME_ERROR = (1 << 5), /* DME error */
		};

		/* Interrupt configuration options */
		@@ -4580,7 +4582,7 @@ ufshcd_transfer_rsp_status(struct ufs_hba hba, struct ufshcd_lrb lrbp)
		break;
		} /* end of switch */

		if (host_byte(result) != DID_OK) {
		if ((host_byte(result) != DID_OK) && !hba->silence_err_logs) {
		print_prdt = (ocs == OCS_INVALID_PRDT_ATTR \|\|
		ocs == OCS_MISMATCH_DATA_BUF_SIZE);
		ufshcd_print_trs(hba, 1 << lrbp->task_tag, print_prdt);
		@@ -4994,6 +4996,101 @@ static void ufshcd_complete_requests(struct ufs_hba *hba)
		ufshcd_transfer_req_compl(hba);
		ufshcd_tmc_handler(hba);
		}

		/**
		* ufshcd_quirk_dl_nac_errors - This function checks if error handling is
		* to recover from the DL NAC errors or not.
		* @hba: per-adapter instance
		*
		* Returns true if error handling is required, false otherwise
		*/
		static bool ufshcd_quirk_dl_nac_errors(struct ufs_hba *hba)
		{
		unsigned long flags;
		bool err_handling = true;

		spin_lock_irqsave(hba->host->host_lock, flags);
		/*
		* UFS_DEVICE_QUIRK_RECOVERY_FROM_DL_NAC_ERRORS only workaround the
		* device fatal error and/or DL NAC & REPLAY timeout errors.
		*/
		if (hba->saved_err & (CONTROLLER_FATAL_ERROR \| SYSTEM_BUS_FATAL_ERROR))
		goto out;

		if ((hba->saved_err & DEVICE_FATAL_ERROR) \|\|
		((hba->saved_err & UIC_ERROR) &&
		(hba->saved_uic_err & UFSHCD_UIC_DL_TCx_REPLAY_ERROR))) {
		/*
		* we have to do error recovery but atleast silence the error
		* logs.
		*/
		hba->silence_err_logs = true;
		goto out;
		}

		if ((hba->saved_err & UIC_ERROR) &&
		(hba->saved_uic_err & UFSHCD_UIC_DL_NAC_RECEIVED_ERROR)) {
		int err;
		/*
		* wait for 50ms to see if we can get any other errors or not.
		*/
		spin_unlock_irqrestore(hba->host->host_lock, flags);
		msleep(50);
		spin_lock_irqsave(hba->host->host_lock, flags);

		/*
		* now check if we have got any other severe errors other than
		* DL NAC error?
		*/
		if ((hba->saved_err & INT_FATAL_ERRORS) \|\|
		((hba->saved_err & UIC_ERROR) &&
		(hba->saved_uic_err & ~UFSHCD_UIC_DL_NAC_RECEIVED_ERROR))) {
		if (((hba->saved_err & INT_FATAL_ERRORS) ==
		DEVICE_FATAL_ERROR) \|\| (hba->saved_uic_err &
		~UFSHCD_UIC_DL_NAC_RECEIVED_ERROR))
		hba->silence_err_logs = true;
		goto out;
		}

		/*
		* As DL NAC is the only error received so far, send out NOP
		* command to confirm if link is still active or not.
		* - If we don't get any response then do error recovery.
		* - If we get response then clear the DL NAC error bit.
		*/

		/* silence the error logs from NOP command */
		hba->silence_err_logs = true;
		spin_unlock_irqrestore(hba->host->host_lock, flags);
		err = ufshcd_verify_dev_init(hba);
		spin_lock_irqsave(hba->host->host_lock, flags);
		hba->silence_err_logs = false;

		if (err) {
		hba->silence_err_logs = true;
		goto out;
		}

		/* Link seems to be alive hence ignore the DL NAC errors */
		if (hba->saved_uic_err == UFSHCD_UIC_DL_NAC_RECEIVED_ERROR)
		hba->saved_err &= ~UIC_ERROR;
		/* clear NAC error */
		hba->saved_uic_err &= ~UFSHCD_UIC_DL_NAC_RECEIVED_ERROR;
		if (!hba->saved_uic_err) {
		err_handling = false;
		goto out;
		}
		/*
		* there seems to be some errors other than NAC, so do error
		* recovery
		*/
		hba->silence_err_logs = true;
		}
		out:
		spin_unlock_irqrestore(hba->host->host_lock, flags);
		return err_handling;
		}

		/**
		* ufshcd_err_handler - handle UFS errors that require s/w attention
		* @work: pointer to work structure
		@@ -5023,6 +5120,17 @@ static void ufshcd_err_handler(struct work_struct *work)
		/* Complete requests that have door-bell cleared by h/w */
		ufshcd_complete_requests(hba);

		if (hba->dev_quirks & UFS_DEVICE_QUIRK_RECOVERY_FROM_DL_NAC_ERRORS) {
		bool ret;

		spin_unlock_irqrestore(hba->host->host_lock, flags);
		/* release the lock as ufshcd_quirk_dl_nac_errors() may sleep */
		ret = ufshcd_quirk_dl_nac_errors(hba);
		spin_lock_irqsave(hba->host->host_lock, flags);
		if (!ret)
		goto skip_err_handling;
		}

		/*
		* Dump controller state before resetting. Transfer requests state
		* will be dump as part of the request completion.
		@@ -5030,17 +5138,21 @@ static void ufshcd_err_handler(struct work_struct *work)
		if (hba->saved_err & (INT_FATAL_ERRORS \| UIC_ERROR)) {
		dev_err(hba->dev, "%s: saved_err 0x%x saved_uic_err 0x%x",
		__func__, hba->saved_err, hba->saved_uic_err);
		if (!hba->silence_err_logs) {
		ufshcd_print_host_regs(hba);
		ufshcd_print_pwr_info(hba);
		ufshcd_print_tmrs(hba, hba->outstanding_tasks);
		}
		}

		if (hba->vops && hba->vops->crypto_engine_get_err)
		crypto_engine_err = hba->vops->crypto_engine_get_err(hba);

		if ((hba->saved_err & INT_FATAL_ERRORS) \|\| crypto_engine_err \|\|
		((hba->saved_err & UIC_ERROR) &&
		(hba->saved_uic_err & (UFSHCD_UIC_DL_PA_INIT_ERROR))))
		(hba->saved_uic_err & (UFSHCD_UIC_DL_PA_INIT_ERROR \|
		UFSHCD_UIC_DL_NAC_RECEIVED_ERROR \|
		UFSHCD_UIC_DL_TCx_REPLAY_ERROR))))
		needs_reset = true;

		/*
		@@ -5125,6 +5237,7 @@ skip_pending_xfer_clear:
		hba->vops->crypto_engine_reset_err(hba);
		}

		skip_err_handling:
		if (!needs_reset) {
		hba->ufshcd_state = UFSHCD_STATE_OPERATIONAL;
		if (hba->saved_err \|\| hba->saved_uic_err)
		@@ -5132,6 +5245,7 @@ skip_pending_xfer_clear:
		__func__, hba->saved_err, hba->saved_uic_err);
		}

		hba->silence_err_logs = false;
		ufshcd_clear_eh_in_progress(hba);
		out:
		spin_unlock_irqrestore(hba->host->host_lock, flags);
		@@ -5175,8 +5289,16 @@ static void ufshcd_update_uic_error(struct ufs_hba *hba)
		if (reg)
		ufshcd_update_uic_reg_hist(&hba->ufs_stats.dl_err, reg);

		if (reg & UIC_DATA_LINK_LAYER_ERROR_PA_INIT)
		if (reg & UIC_DATA_LINK_LAYER_ERROR_PA_INIT) {
		hba->uic_error \|= UFSHCD_UIC_DL_PA_INIT_ERROR;
		} else if (hba->dev_quirks &
		UFS_DEVICE_QUIRK_RECOVERY_FROM_DL_NAC_ERRORS) {
		if (reg & UIC_DATA_LINK_LAYER_ERROR_NAC_RECEIVED)
		hba->uic_error \|=
		UFSHCD_UIC_DL_NAC_RECEIVED_ERROR;
		else if (reg & UIC_DATA_LINK_LAYER_ERROR_TCx_REPLAY_TIMEOUT)
		hba->uic_error \|= UFSHCD_UIC_DL_TCx_REPLAY_ERROR;
		}

		/* UIC NL/TL/DME errors needs software retry */
		reg = ufshcd_readl(hba, REG_UIC_ERROR_CODE_NETWORK_LAYER);

drivers/scsi/ufs/ufshci.h

+2 −0

Original line number	Diff line number	Diff line
		@@ -173,6 +173,8 @@ enum {
		#define UIC_DATA_LINK_LAYER_ERROR UFS_BIT(31)
		#define UIC_DATA_LINK_LAYER_ERROR_CODE_MASK 0x7FFF
		#define UIC_DATA_LINK_LAYER_ERROR_PA_INIT 0x2000
		#define UIC_DATA_LINK_LAYER_ERROR_NAC_RECEIVED 0x0001
		#define UIC_DATA_LINK_LAYER_ERROR_TCx_REPLAY_TIMEOUT 0x0002

		/* UECN - Host UIC Error Code Network Layer 40h */
		#define UIC_NETWORK_LAYER_ERROR UFS_BIT(31)

include/linux/scsi/ufs/ufshcd.h

+1 −0

Original line number	Diff line number	Diff line
		@@ -682,6 +682,7 @@ struct ufs_hba {
		u32 uic_error;
		u32 saved_err;
		u32 saved_uic_err;
		bool silence_err_logs;

		/* Device management request data */
		struct ufs_dev_cmd dev_cmd;