accel/habanalabs/gaudi2: use correct registers to dump QM CQ info

The QM CQ PTR_LO/PTR_HI/TSIZE registers are for pushing a CQ entry, and
although they are updated by HW even when descriptors are fetched by PQ
and CB addresses are fed into CQ, the correct registers to use when
dumping the CQ info are the ones with the _STS suffix.
Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>

drivers/accel/habanalabs/gaudi2/gaudi2.c

@@ -7868,15 +7868,15 @@ static void handle_lower_qman_data_on_err(struct hl_device *hdev, u64 qman_base,
 	is_arc_cq = FIELD_GET(PDMA0_QM_CP_STS_CUR_CQ_MASK, cp_sts); /* 0 - legacy CQ, 1 - ARC_CQ */
 
 	if (is_arc_cq) {
-		lo = RREG32(qman_base + QM_ARC_CQ_PTR_LO_OFFSET);
-		hi = RREG32(qman_base + QM_ARC_CQ_PTR_HI_OFFSET);
+		lo = RREG32(qman_base + QM_ARC_CQ_PTR_LO_STS_OFFSET);
+		hi = RREG32(qman_base + QM_ARC_CQ_PTR_HI_STS_OFFSET);
 		cq_ptr = ((u64) hi) << 32 | lo;
-		cq_ptr_size = RREG32(qman_base + QM_ARC_CQ_TSIZE_OFFSET);
+		cq_ptr_size = RREG32(qman_base + QM_ARC_CQ_TSIZE_STS_OFFSET);
 	} else {
-		lo = RREG32(qman_base + QM_CQ_PTR_LO_4_OFFSET);
-		hi = RREG32(qman_base + QM_CQ_PTR_HI_4_OFFSET);
+		lo = RREG32(qman_base + QM_CQ_PTR_LO_STS_4_OFFSET);
+		hi = RREG32(qman_base + QM_CQ_PTR_HI_STS_4_OFFSET);
 		cq_ptr = ((u64) hi) << 32 | lo;
-		cq_ptr_size = RREG32(qman_base + QM_CQ_TSIZE_4_OFFSET);
+		cq_ptr_size = RREG32(qman_base + QM_CQ_TSIZE_STS_4_OFFSET);
 	}
 
 	lo = RREG32(qman_base + QM_CP_CURRENT_INST_LO_4_OFFSET);

drivers/accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h

@@ -242,13 +242,13 @@
 #define QM_FENCE2_OFFSET		(mmPDMA0_QM_CP_FENCE2_RDATA_0 - mmPDMA0_QM_BASE)
 #define QM_SEI_STATUS_OFFSET		(mmPDMA0_QM_SEI_STATUS - mmPDMA0_QM_BASE)
 
-#define QM_CQ_PTR_LO_4_OFFSET		(mmPDMA0_QM_CQ_PTR_LO_4 - mmPDMA0_QM_BASE)
-#define QM_CQ_PTR_HI_4_OFFSET		(mmPDMA0_QM_CQ_PTR_HI_4 - mmPDMA0_QM_BASE)
-#define QM_CQ_TSIZE_4_OFFSET		(mmPDMA0_QM_CQ_TSIZE_4 - mmPDMA0_QM_BASE)
+#define QM_CQ_TSIZE_STS_4_OFFSET	(mmPDMA0_QM_CQ_TSIZE_STS_4 - mmPDMA0_QM_BASE)
+#define QM_CQ_PTR_LO_STS_4_OFFSET	(mmPDMA0_QM_CQ_PTR_LO_STS_4 - mmPDMA0_QM_BASE)
+#define QM_CQ_PTR_HI_STS_4_OFFSET	(mmPDMA0_QM_CQ_PTR_HI_STS_4 - mmPDMA0_QM_BASE)
 
-#define QM_ARC_CQ_PTR_LO_OFFSET		(mmPDMA0_QM_ARC_CQ_PTR_LO - mmPDMA0_QM_BASE)
-#define QM_ARC_CQ_PTR_HI_OFFSET		(mmPDMA0_QM_ARC_CQ_PTR_HI - mmPDMA0_QM_BASE)
-#define QM_ARC_CQ_TSIZE_OFFSET		(mmPDMA0_QM_ARC_CQ_TSIZE - mmPDMA0_QM_BASE)
+#define QM_ARC_CQ_TSIZE_STS_OFFSET	(mmPDMA0_QM_ARC_CQ_TSIZE_STS - mmPDMA0_QM_BASE)
+#define QM_ARC_CQ_PTR_LO_STS_OFFSET	(mmPDMA0_QM_ARC_CQ_PTR_LO_STS - mmPDMA0_QM_BASE)
+#define QM_ARC_CQ_PTR_HI_STS_OFFSET	(mmPDMA0_QM_ARC_CQ_PTR_HI_STS - mmPDMA0_QM_BASE)
 
 #define QM_CP_STS_4_OFFSET		(mmPDMA0_QM_CP_STS_4 - mmPDMA0_QM_BASE)
 #define QM_CP_CURRENT_INST_LO_4_OFFSET	(mmPDMA0_QM_CP_CURRENT_INST_LO_4 - mmPDMA0_QM_BASE)