diff mbox series

[v4,1/1] EDAC/altera: Check previous DDR DBE during driver probe

Message ID 20230615022534.4163918-2-niravkumar.l.rabara@intel.com (mailing list archive)
State New, archived
Headers show
Series EDAC/altera: Check previous DDR DBE during driver probe | expand

Commit Message

Rabara, Niravkumar L June 15, 2023, 2:25 a.m. UTC 
From: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>

Add DDR DBE check during driver probe to notify user if previous
reboot cause by DDR DBE and print DBE error related information.

Signed-off-by: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
---
 drivers/edac/altera_edac.c                   | 29 ++++++++++++++++----
 include/linux/firmware/intel/stratix10-smc.h | 20 ++++++++++++++
 2 files changed, 44 insertions(+), 5 deletions(-)

Comments

Dinh Nguyen June 15, 2023, 6:49 p.m. UTC | #1 
On 6/14/23 21:25, niravkumar.l.rabara@intel.com wrote:
> From: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
> 
> Add DDR DBE check during driver probe to notify user if previous
> reboot cause by DDR DBE and print DBE error related information.
> 
> Signed-off-by: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
> ---
>   drivers/edac/altera_edac.c                   | 29 ++++++++++++++++----
>   include/linux/firmware/intel/stratix10-smc.h | 20 ++++++++++++++
>   2 files changed, 44 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c
> index 8b31cd54bdb6..04c0675adc8c 100644
> --- a/drivers/edac/altera_edac.c
> +++ b/drivers/edac/altera_edac.c
> @@ -2159,6 +2159,7 @@ static int altr_edac_a10_probe(struct platform_device *pdev)
>   #ifdef CONFIG_64BIT
>   	{
>   		int dberror, err_addr;
> +		struct arm_smccc_res result;
>   
>   		edac->panic_notifier.notifier_call = s10_edac_dberr_handler;
>   		atomic_notifier_chain_register(&panic_notifier_list,
> @@ -2168,11 +2169,29 @@ static int altr_edac_a10_probe(struct platform_device *pdev)
>   		regmap_read(edac->ecc_mgr_map, S10_SYSMGR_UE_VAL_OFST,
>   			    &dberror);
>   		if (dberror) {
> -			regmap_read(edac->ecc_mgr_map, S10_SYSMGR_UE_ADDR_OFST,
> -				    &err_addr);
> -			edac_printk(KERN_ERR, EDAC_DEVICE,
> -				    "Previous Boot UE detected[0x%X] @ 0x%X\n",
> -				    dberror, err_addr);
> +			/* Bit-31 is set if previous DDR UE happened */
> +			if (dberror & (1 << 31)) {
> +				/* Read previous DDR UE info */
> +				arm_smccc_smc(INTEL_SIP_SMC_READ_SEU_ERR, 0,
> +					      0, 0, 0, 0, 0, 0, &result);
> +
> +				if (!result.a0) {
> +					edac_printk(KERN_ERR, EDAC_DEVICE,
> +						    "Previous DDR UE:Count=0x%X,Address=0x%X,ErrorData=0x%X\n"
> +						    , (unsigned int)result.a1
> +						    , (unsigned int)result.a2
> +						    , (unsigned int)result.a3);
> +				} else {
> +					edac_printk(KERN_ERR, EDAC_DEVICE,
> +						    "INTEL_SIP_SMC_SEU_ERR_STATUS failed\n");
> +				}
> +			} else {
> +				regmap_read(edac->ecc_mgr_map, S10_SYSMGR_UE_ADDR_OFST,
> +					    &err_addr);
> +				edac_printk(KERN_ERR, EDAC_DEVICE,
> +					    "Previous Boot UE detected[0x%X] @ 0x%X\n",
> +					    dberror, err_addr);
> +			}
>   			/* Reset the sticky registers */
>   			regmap_write(edac->ecc_mgr_map,
>   				     S10_SYSMGR_UE_VAL_OFST, 0);
> diff --git a/include/linux/firmware/intel/stratix10-smc.h b/include/linux/firmware/intel/stratix10-smc.h
> index a718f853d457..48810c39f612 100644
> --- a/include/linux/firmware/intel/stratix10-smc.h
> +++ b/include/linux/firmware/intel/stratix10-smc.h
> @@ -595,4 +595,24 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE)
>   #define INTEL_SIP_SMC_FCS_GET_PROVISION_DATA \
>   	INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FCS_GET_PROVISION_DATA)
>   
> +/**
> + * Request INTEL_SIP_SMC_READ_SEU_ERR
> + * Sync call to get Single Event Upset Error information
> + * SEU detects both corrected and uncorrected error
> + *
> + * Call register usage:
> + * a0 INTEL_SIP_SMC_READ_SEU_ERR
> + * a1-7 not used
> + *
> + * Return status:
> + * a0 INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_STATUS_NOT_SUPPORTED or
> + *    INTEL_SIP_SMC_STATUS_ERROR
> + * a1 error count of response data
> + * a2 sector address of response data
> + * a3 error data
> + */
> +#define INTEL_SIP_SMC_FUNCID_SEU_ERR_STATUS 153
> +#define INTEL_SIP_SMC_READ_SEU_ERR \
> +		INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_SEU_ERR_STATUS)
> +
>   #endif


Acked-by: Dinh Nguyen <dinguyen@kernel.org>
diff mbox series

Patch

diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c
index 8b31cd54bdb6..04c0675adc8c 100644
--- a/drivers/edac/altera_edac.c
+++ b/drivers/edac/altera_edac.c
@@ -2159,6 +2159,7 @@  static int altr_edac_a10_probe(struct platform_device *pdev)
 #ifdef CONFIG_64BIT
 	{
 		int dberror, err_addr;
+		struct arm_smccc_res result;
 
 		edac->panic_notifier.notifier_call = s10_edac_dberr_handler;
 		atomic_notifier_chain_register(&panic_notifier_list,
@@ -2168,11 +2169,29 @@  static int altr_edac_a10_probe(struct platform_device *pdev)
 		regmap_read(edac->ecc_mgr_map, S10_SYSMGR_UE_VAL_OFST,
 			    &dberror);
 		if (dberror) {
-			regmap_read(edac->ecc_mgr_map, S10_SYSMGR_UE_ADDR_OFST,
-				    &err_addr);
-			edac_printk(KERN_ERR, EDAC_DEVICE,
-				    "Previous Boot UE detected[0x%X] @ 0x%X\n",
-				    dberror, err_addr);
+			/* Bit-31 is set if previous DDR UE happened */
+			if (dberror & (1 << 31)) {
+				/* Read previous DDR UE info */
+				arm_smccc_smc(INTEL_SIP_SMC_READ_SEU_ERR, 0,
+					      0, 0, 0, 0, 0, 0, &result);
+
+				if (!result.a0) {
+					edac_printk(KERN_ERR, EDAC_DEVICE,
+						    "Previous DDR UE:Count=0x%X,Address=0x%X,ErrorData=0x%X\n"
+						    , (unsigned int)result.a1
+						    , (unsigned int)result.a2
+						    , (unsigned int)result.a3);
+				} else {
+					edac_printk(KERN_ERR, EDAC_DEVICE,
+						    "INTEL_SIP_SMC_SEU_ERR_STATUS failed\n");
+				}
+			} else {
+				regmap_read(edac->ecc_mgr_map, S10_SYSMGR_UE_ADDR_OFST,
+					    &err_addr);
+				edac_printk(KERN_ERR, EDAC_DEVICE,
+					    "Previous Boot UE detected[0x%X] @ 0x%X\n",
+					    dberror, err_addr);
+			}
 			/* Reset the sticky registers */
 			regmap_write(edac->ecc_mgr_map,
 				     S10_SYSMGR_UE_VAL_OFST, 0);
diff --git a/include/linux/firmware/intel/stratix10-smc.h b/include/linux/firmware/intel/stratix10-smc.h
index a718f853d457..48810c39f612 100644
--- a/include/linux/firmware/intel/stratix10-smc.h
+++ b/include/linux/firmware/intel/stratix10-smc.h
@@ -595,4 +595,24 @@  INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE)
 #define INTEL_SIP_SMC_FCS_GET_PROVISION_DATA \
 	INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FCS_GET_PROVISION_DATA)
 
+/**
+ * Request INTEL_SIP_SMC_READ_SEU_ERR
+ * Sync call to get Single Event Upset Error information
+ * SEU detects both corrected and uncorrected error
+ *
+ * Call register usage:
+ * a0 INTEL_SIP_SMC_READ_SEU_ERR
+ * a1-7 not used
+ *
+ * Return status:
+ * a0 INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_STATUS_NOT_SUPPORTED or
+ *    INTEL_SIP_SMC_STATUS_ERROR
+ * a1 error count of response data
+ * a2 sector address of response data
+ * a3 error data
+ */
+#define INTEL_SIP_SMC_FUNCID_SEU_ERR_STATUS 153
+#define INTEL_SIP_SMC_READ_SEU_ERR \
+		INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_SEU_ERR_STATUS)
+
 #endif