IB/qib: Mask hardware error during link reset

The HCA checks for certain hardware errors which can be falsely
triggered when the IB link is reset. The fix is to mask them rather
than report them.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

drivers/infiniband/hw/qib/qib_7322_regs.h

@@ -742,15 +742,15 @@
 #define QIB_7322_HwErrMask_IBCBusFromSPCParityErrMask_1_LSB 0xF
 #define QIB_7322_HwErrMask_IBCBusFromSPCParityErrMask_1_MSB 0xF
 #define QIB_7322_HwErrMask_IBCBusFromSPCParityErrMask_1_RMASK 0x1
-#define QIB_7322_HwErrMask_statusValidNoEopMask_1_LSB 0xE
-#define QIB_7322_HwErrMask_statusValidNoEopMask_1_MSB 0xE
-#define QIB_7322_HwErrMask_statusValidNoEopMask_1_RMASK 0x1
+#define QIB_7322_HwErrMask_IBCBusToSPCParityErrMask_1_LSB 0xE
+#define QIB_7322_HwErrMask_IBCBusToSPCParityErrMask_1_MSB 0xE
+#define QIB_7322_HwErrMask_IBCBusToSPCParityErrMask_1_RMASK 0x1
 #define QIB_7322_HwErrMask_IBCBusFromSPCParityErrMask_0_LSB 0xD
 #define QIB_7322_HwErrMask_IBCBusFromSPCParityErrMask_0_MSB 0xD
 #define QIB_7322_HwErrMask_IBCBusFromSPCParityErrMask_0_RMASK 0x1
-#define QIB_7322_HwErrMask_statusValidNoEopMask_0_LSB 0xC
-#define QIB_7322_HwErrMask_statusValidNoEopMask_0_MSB 0xC
-#define QIB_7322_HwErrMask_statusValidNoEopMask_0_RMASK 0x1
+#define QIB_7322_HwErrMask_statusValidNoEopMask_LSB 0xC
+#define QIB_7322_HwErrMask_statusValidNoEopMask_MSB 0xC
+#define QIB_7322_HwErrMask_statusValidNoEopMask_RMASK 0x1
 #define QIB_7322_HwErrMask_LATriggeredMask_LSB 0xB
 #define QIB_7322_HwErrMask_LATriggeredMask_MSB 0xB
 #define QIB_7322_HwErrMask_LATriggeredMask_RMASK 0x1
@@ -796,15 +796,15 @@
 #define QIB_7322_HwErrStatus_IBCBusFromSPCParityErr_1_LSB 0xF
 #define QIB_7322_HwErrStatus_IBCBusFromSPCParityErr_1_MSB 0xF
 #define QIB_7322_HwErrStatus_IBCBusFromSPCParityErr_1_RMASK 0x1
-#define QIB_7322_HwErrStatus_statusValidNoEop_1_LSB 0xE
-#define QIB_7322_HwErrStatus_statusValidNoEop_1_MSB 0xE
-#define QIB_7322_HwErrStatus_statusValidNoEop_1_RMASK 0x1
+#define QIB_7322_HwErrStatus_IBCBusToSPCParityErr_1_LSB 0xE
+#define QIB_7322_HwErrStatus_IBCBusToSPCParityErr_1_MSB 0xE
+#define QIB_7322_HwErrStatus_IBCBusToSPCParityErr_1_RMASK 0x1
 #define QIB_7322_HwErrStatus_IBCBusFromSPCParityErr_0_LSB 0xD
 #define QIB_7322_HwErrStatus_IBCBusFromSPCParityErr_0_MSB 0xD
 #define QIB_7322_HwErrStatus_IBCBusFromSPCParityErr_0_RMASK 0x1
-#define QIB_7322_HwErrStatus_statusValidNoEop_0_LSB 0xC
-#define QIB_7322_HwErrStatus_statusValidNoEop_0_MSB 0xC
-#define QIB_7322_HwErrStatus_statusValidNoEop_0_RMASK 0x1
+#define QIB_7322_HwErrStatus_statusValidNoEop_LSB 0xC
+#define QIB_7322_HwErrStatus_statusValidNoEop_MSB 0xC
+#define QIB_7322_HwErrStatus_statusValidNoEop_RMASK 0x1
 #define QIB_7322_HwErrStatus_LATriggered_LSB 0xB
 #define QIB_7322_HwErrStatus_LATriggered_MSB 0xB
 #define QIB_7322_HwErrStatus_LATriggered_RMASK 0x1
@@ -850,15 +850,15 @@
 #define QIB_7322_HwErrClear_IBCBusFromSPCParityErrClear_1_LSB 0xF
 #define QIB_7322_HwErrClear_IBCBusFromSPCParityErrClear_1_MSB 0xF
 #define QIB_7322_HwErrClear_IBCBusFromSPCParityErrClear_1_RMASK 0x1
-#define QIB_7322_HwErrClear_IBCBusToSPCparityErrClear_1_LSB 0xE
-#define QIB_7322_HwErrClear_IBCBusToSPCparityErrClear_1_MSB 0xE
-#define QIB_7322_HwErrClear_IBCBusToSPCparityErrClear_1_RMASK 0x1
+#define QIB_7322_HwErrClear_IBCBusToSPCParityErrClear_1_LSB 0xE
+#define QIB_7322_HwErrClear_IBCBusToSPCParityErrClear_1_MSB 0xE
+#define QIB_7322_HwErrClear_IBCBusToSPCParityErrClear_1_RMASK 0x1
 #define QIB_7322_HwErrClear_IBCBusFromSPCParityErrClear_0_LSB 0xD
 #define QIB_7322_HwErrClear_IBCBusFromSPCParityErrClear_0_MSB 0xD
 #define QIB_7322_HwErrClear_IBCBusFromSPCParityErrClear_0_RMASK 0x1
-#define QIB_7322_HwErrClear_IBCBusToSPCparityErrClear_0_LSB 0xC
-#define QIB_7322_HwErrClear_IBCBusToSPCparityErrClear_0_MSB 0xC
-#define QIB_7322_HwErrClear_IBCBusToSPCparityErrClear_0_RMASK 0x1
+#define QIB_7322_HwErrClear_statusValidNoEopClear_LSB 0xC
+#define QIB_7322_HwErrClear_statusValidNoEopClear_MSB 0xC
+#define QIB_7322_HwErrClear_statusValidNoEopClear_RMASK 0x1
 #define QIB_7322_HwErrClear_LATriggeredClear_LSB 0xB
 #define QIB_7322_HwErrClear_LATriggeredClear_MSB 0xB
 #define QIB_7322_HwErrClear_LATriggeredClear_RMASK 0x1
@@ -880,15 +880,15 @@
 #define QIB_7322_HwDiagCtrl_ForceIBCBusFromSPCParityErr_1_LSB 0xF
 #define QIB_7322_HwDiagCtrl_ForceIBCBusFromSPCParityErr_1_MSB 0xF
 #define QIB_7322_HwDiagCtrl_ForceIBCBusFromSPCParityErr_1_RMASK 0x1
-#define QIB_7322_HwDiagCtrl_ForcestatusValidNoEop_1_LSB 0xE
-#define QIB_7322_HwDiagCtrl_ForcestatusValidNoEop_1_MSB 0xE
-#define QIB_7322_HwDiagCtrl_ForcestatusValidNoEop_1_RMASK 0x1
+#define QIB_7322_HwDiagCtrl_ForceIBCBusToSPCParityErr_1_LSB 0xE
+#define QIB_7322_HwDiagCtrl_ForceIBCBusToSPCParityErr_1_MSB 0xE
+#define QIB_7322_HwDiagCtrl_ForceIBCBusToSPCParityErr_1_RMASK 0x1
 #define QIB_7322_HwDiagCtrl_ForceIBCBusFromSPCParityErr_0_LSB 0xD
 #define QIB_7322_HwDiagCtrl_ForceIBCBusFromSPCParityErr_0_MSB 0xD
 #define QIB_7322_HwDiagCtrl_ForceIBCBusFromSPCParityErr_0_RMASK 0x1
-#define QIB_7322_HwDiagCtrl_ForcestatusValidNoEop_0_LSB 0xC
-#define QIB_7322_HwDiagCtrl_ForcestatusValidNoEop_0_MSB 0xC
-#define QIB_7322_HwDiagCtrl_ForcestatusValidNoEop_0_RMASK 0x1
+#define QIB_7322_HwDiagCtrl_ForceIBCBusToSPCParityErr_0_LSB 0xC
+#define QIB_7322_HwDiagCtrl_ForceIBCBusToSPCParityErr_0_MSB 0xC
+#define QIB_7322_HwDiagCtrl_ForceIBCBusToSPCParityErr_0_RMASK 0x1
 
 #define QIB_7322_EXTStatus_OFFS 0xC0
 #define QIB_7322_EXTStatus_DEF 0x000000000000X000

drivers/infiniband/hw/qib/qib_iba7322.c

@@ -1100,9 +1100,9 @@ static const struct qib_hwerror_msgs qib_7322_hwerror_msgs[] = {
 	HWE_AUTO_P(SDmaMemReadErr, 1),
 	HWE_AUTO_P(SDmaMemReadErr, 0),
 	HWE_AUTO_P(IBCBusFromSPCParityErr, 1),
+	HWE_AUTO_P(IBCBusToSPCParityErr, 1),
 	HWE_AUTO_P(IBCBusFromSPCParityErr, 0),
-	HWE_AUTO_P(statusValidNoEop, 1),
-	HWE_AUTO_P(statusValidNoEop, 0),
+	HWE_AUTO(statusValidNoEop),
 	HWE_AUTO(LATriggered),
 	{ .mask = 0 }
 };
@@ -4763,6 +4763,8 @@ static void qib_7322_mini_pcs_reset(struct qib_pportdata *ppd)
 		SYM_MASK(IBPCSConfig_0, tx_rx_reset);
 
 	val = qib_read_kreg_port(ppd, krp_ib_pcsconfig);
+	qib_write_kreg(dd, kr_hwerrmask,
+		       dd->cspec->hwerrmask & ~HWE_MASK(statusValidNoEop));
 	qib_write_kreg_port(ppd, krp_ibcctrl_a,
 			    ppd->cpspec->ibcctrl_a &
 			    ~SYM_MASK(IBCCtrlA_0, IBLinkEn));
@@ -4772,6 +4774,9 @@ static void qib_7322_mini_pcs_reset(struct qib_pportdata *ppd)
 	qib_write_kreg_port(ppd, krp_ib_pcsconfig, val & ~reset_bits);
 	qib_write_kreg_port(ppd, krp_ibcctrl_a, ppd->cpspec->ibcctrl_a);
 	qib_write_kreg(dd, kr_scratch, 0ULL);
+	qib_write_kreg(dd, kr_hwerrclear,
+		       SYM_MASK(HwErrClear, statusValidNoEopClear));
+	qib_write_kreg(dd, kr_hwerrmask, dd->cspec->hwerrmask);
 }
 
 /*