powerpc/powernv: display reason for Malfunction Alert HMI.

index 0321a90..ab245dd 100644
@@ -428,6 +428,7 @@ struct OpalMemoryErrorData {
 /* HMI interrupt event */
 enum OpalHMI_Version {
 	OpalHMIEvt_V1 = 1,
+	OpalHMIEvt_V2 = 2,
 };
 
 enum OpalHMI_Severity {

@@ -458,6 +459,49 @@ enum OpalHMI_ErrType {
 	OpalHMI_ERROR_CAPP_RECOVERY,
 };
 
+enum OpalHMI_XstopType {
+	CHECKSTOP_TYPE_UNKNOWN	=	0,
+	CHECKSTOP_TYPE_CORE	=	1,
+	CHECKSTOP_TYPE_NX	=	2,
+};
+
+enum OpalHMI_CoreXstopReason {
+	CORE_CHECKSTOP_IFU_REGFILE		= 0x00000001,
+	CORE_CHECKSTOP_IFU_LOGIC		= 0x00000002,
+	CORE_CHECKSTOP_PC_DURING_RECOV		= 0x00000004,
+	CORE_CHECKSTOP_ISU_REGFILE		= 0x00000008,
+	CORE_CHECKSTOP_ISU_LOGIC		= 0x00000010,
+	CORE_CHECKSTOP_FXU_LOGIC		= 0x00000020,
+	CORE_CHECKSTOP_VSU_LOGIC		= 0x00000040,
+	CORE_CHECKSTOP_PC_RECOV_IN_MAINT_MODE	= 0x00000080,
+	CORE_CHECKSTOP_LSU_REGFILE		= 0x00000100,
+	CORE_CHECKSTOP_PC_FWD_PROGRESS		= 0x00000200,
+	CORE_CHECKSTOP_LSU_LOGIC		= 0x00000400,
+	CORE_CHECKSTOP_PC_LOGIC			= 0x00000800,
+	CORE_CHECKSTOP_PC_HYP_RESOURCE		= 0x00001000,
+	CORE_CHECKSTOP_PC_HANG_RECOV_FAILED	= 0x00002000,
+	CORE_CHECKSTOP_PC_AMBI_HANG_DETECTED	= 0x00004000,
+	CORE_CHECKSTOP_PC_DEBUG_TRIG_ERR_INJ	= 0x00008000,
+	CORE_CHECKSTOP_PC_SPRD_HYP_ERR_INJ	= 0x00010000,
+};
+
+enum OpalHMI_NestAccelXstopReason {
+	NX_CHECKSTOP_SHM_INVAL_STATE_ERR	= 0x00000001,
+	NX_CHECKSTOP_DMA_INVAL_STATE_ERR_1	= 0x00000002,
+	NX_CHECKSTOP_DMA_INVAL_STATE_ERR_2	= 0x00000004,
+	NX_CHECKSTOP_DMA_CH0_INVAL_STATE_ERR	= 0x00000008,
+	NX_CHECKSTOP_DMA_CH1_INVAL_STATE_ERR	= 0x00000010,
+	NX_CHECKSTOP_DMA_CH2_INVAL_STATE_ERR	= 0x00000020,
+	NX_CHECKSTOP_DMA_CH3_INVAL_STATE_ERR	= 0x00000040,
+	NX_CHECKSTOP_DMA_CH4_INVAL_STATE_ERR	= 0x00000080,
+	NX_CHECKSTOP_DMA_CH5_INVAL_STATE_ERR	= 0x00000100,
+	NX_CHECKSTOP_DMA_CH6_INVAL_STATE_ERR	= 0x00000200,
+	NX_CHECKSTOP_DMA_CH7_INVAL_STATE_ERR	= 0x00000400,
+	NX_CHECKSTOP_DMA_CRB_UE			= 0x00000800,
+	NX_CHECKSTOP_DMA_CRB_SUE		= 0x00001000,
+	NX_CHECKSTOP_PBI_ISN_UE			= 0x00002000,
+};
+
 struct OpalHMIEvent {
 	uint8_t		version;	/* 0x00 */
 	uint8_t		severity;	/* 0x01 */

@@ -468,6 +512,23 @@ struct OpalHMIEvent {
 	__be64		hmer;
 	/* TFMR register. Valid only for TFAC and TFMR_PARITY error type. */
 	__be64		tfmr;
+
+	/* version 2 and later */
+	union {
+		/*
+		 * checkstop info (Core/NX).
+		 * Valid for OpalHMI_ERROR_MALFUNC_ALERT.
+		 */
+		struct {
+			uint8_t	xstop_type;	/* enum OpalHMI_XstopType */
+			uint8_t reserved_1[3];
+			__be32  xstop_reason;
+			union {
+				__be32 pir;	/* for CHECKSTOP_TYPE_CORE */
+				__be32 chip_id;	/* for CHECKSTOP_TYPE_NX */
+			} u;
+		} xstop_error;
+	} u;
 };
 
 enum {

147 lines not on this page · raw message

index 2668225..26e0f3f 100644
@@ -235,6 +235,8 @@ static void hmi_event_handler(struct work_struct *work)
 	struct OpalHMIEvent *hmi_evt;
 	struct OpalHmiEvtNode *msg_node;
 	uint8_t disposition;
+	struct opal_msg msg;
+	int unrecoverable = 0;
 
 	spin_lock_irqsave(&opal_hmi_evt_lock, flags);
 	while (!list_empty(&opal_hmi_evt_list)) {

@@ -250,14 +252,34 @@ static void hmi_event_handler(struct work_struct *work)
 
 		/*
 		 * Check if HMI event has been recovered or not. If not
-		 * then we can't continue, invoke panic.
+		 * then kernel can't continue, we need to panic.
+		 * But before we do that, display all the HMI event
+		 * available on the list and set unrecoverable flag to 1.
 		 */
 		if (disposition != OpalHMI_DISPOSITION_RECOVERED)
-			panic("Unrecoverable HMI exception");
+			unrecoverable = 1;
 
 		spin_lock_irqsave(&opal_hmi_evt_lock, flags);
 	}
 	spin_unlock_irqrestore(&opal_hmi_evt_lock, flags);
+
+	if (unrecoverable) {
+		/* Pull all HMI events from OPAL before we panic. */
+		while (opal_get_msg(__pa(&msg), sizeof(msg)) == OPAL_SUCCESS) {
+			u32 type;
+
+			type = be32_to_cpu(msg.msg_type);
+
+			/* skip if not HMI event */
+			if (type != OPAL_MSG_HMI_EVT)
+				continue;
+
+			/* HMI event info starts from param[0] */
+			hmi_evt = (struct OpalHMIEvent *)&msg.params[0];
+			print_hmi_event_info(hmi_evt);
+		}
+		panic("Unrecoverable HMI exception");
+	}
 }
 
 static DECLARE_WORK(hmi_event_work, hmi_event_handler);