RDMA/irdma: Support 64-byte CQEs and GEN3 CQE opcode decoding

Introduce support for 64-byte CQEs in GEN3 devices. Additionally,
implement GEN3-specific CQE opcode decoding.

Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Link: https://patch.msgid.link/20250827152545.2056-12-tatyana.e.nikolova@intel.com
Tested-by: Jacob Moroni <jmoroni@google.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>

Author: shirazsaleem

drivers/infiniband/hw/irdma/hw.c

@@ -1117,13 +1117,15 @@ static int irdma_create_ccq(struct irdma_pci_f *rf)
 	struct irdma_sc_dev *dev = &rf->sc_dev;
 	struct irdma_ccq_init_info info = {};
 	struct irdma_ccq *ccq = &rf->ccq;
+	int ccq_size;
 	int status;
 
 	dev->ccq = &ccq->sc_cq;
 	dev->ccq->dev = dev;
 	info.dev = dev;
+	ccq_size = (rf->rdma_ver >= IRDMA_GEN_3) ? IW_GEN_3_CCQ_SIZE : IW_CCQ_SIZE;
 	ccq->shadow_area.size = sizeof(struct irdma_cq_shadow_area);
-	ccq->mem_cq.size = ALIGN(sizeof(struct irdma_cqe) * IW_CCQ_SIZE,
+	ccq->mem_cq.size = ALIGN(sizeof(struct irdma_cqe) * ccq_size,
 				 IRDMA_CQ0_ALIGNMENT);
 	ccq->mem_cq.va = dma_alloc_coherent(dev->hw->device, ccq->mem_cq.size,
 					    &ccq->mem_cq.pa, GFP_KERNEL);
@@ -1140,7 +1142,7 @@ static int irdma_create_ccq(struct irdma_pci_f *rf)
 	/* populate the ccq init info */
 	info.cq_base = ccq->mem_cq.va;
 	info.cq_pa = ccq->mem_cq.pa;
-	info.num_elem = IW_CCQ_SIZE;
+	info.num_elem = ccq_size;
 	info.shadow_area = ccq->shadow_area.va;
 	info.shadow_area_pa = ccq->shadow_area.pa;
 	info.ceqe_mask = false;

drivers/infiniband/hw/irdma/main.h

@@ -66,7 +66,8 @@ extern struct iidc_rdma_core_auxiliary_drv ig3rdma_core_auxiliary_drv;
 #define IRDMA_MACIP_ADD		1
 #define IRDMA_MACIP_DELETE	2
 
-#define IW_CCQ_SIZE	(IRDMA_CQP_SW_SQSIZE_2048 + 1)
+#define IW_GEN_3_CCQ_SIZE  (2 * IRDMA_CQP_SW_SQSIZE_2048 + 2)
+#define IW_CCQ_SIZE	(IRDMA_CQP_SW_SQSIZE_2048 + 2)
 #define IW_CEQ_SIZE	2048
 #define IW_AEQ_SIZE	2048
 

drivers/infiniband/hw/irdma/utils.c

@@ -2338,7 +2338,10 @@ bool irdma_cq_empty(struct irdma_cq *iwcq)
 	u8 polarity;
 
 	ukcq  = &iwcq->sc_cq.cq_uk;
-	cqe = IRDMA_GET_CURRENT_CQ_ELEM(ukcq);
+	if (ukcq->avoid_mem_cflct)
+		cqe = IRDMA_GET_CURRENT_EXTENDED_CQ_ELEM(ukcq);
+	else
+		cqe = IRDMA_GET_CURRENT_CQ_ELEM(ukcq);
 	get_64bit_val(cqe, 24, &qword3);
 	polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword3);
 

drivers/infiniband/hw/irdma/verbs.c

@@ -1971,8 +1971,13 @@ static int irdma_resize_cq(struct ib_cq *ibcq, int entries,
 
 	if (!iwcq->user_mode) {
 		entries++;
-		if (rf->sc_dev.hw_attrs.uk_attrs.hw_rev >= IRDMA_GEN_2)
+
+		if (!iwcq->sc_cq.cq_uk.avoid_mem_cflct &&
+		    dev->hw_attrs.uk_attrs.hw_rev >= IRDMA_GEN_2)
 			entries *= 2;
+
+		if (entries & 1)
+			entries += 1; /* cq size must be an even number */
 	}
 
 	info.cq_size = max(entries, 4);
@@ -2115,6 +2120,7 @@ static int irdma_create_cq(struct ib_cq *ibcq,
 	unsigned long flags;
 	int err_code;
 	int entries = attr->cqe;
+	bool cqe_64byte_ena;
 
 	err_code = cq_validate_flags(attr->flags, dev->hw_attrs.uk_attrs.hw_rev);
 	if (err_code)
@@ -2138,6 +2144,9 @@ static int irdma_create_cq(struct ib_cq *ibcq,
 	info.dev = dev;
 	ukinfo->cq_size = max(entries, 4);
 	ukinfo->cq_id = cq_num;
+	cqe_64byte_ena = dev->hw_attrs.uk_attrs.feature_flags & IRDMA_FEATURE_64_BYTE_CQE ?
+			 true : false;
+	ukinfo->avoid_mem_cflct = cqe_64byte_ena;
 	iwcq->ibcq.cqe = info.cq_uk_init_info.cq_size;
 	if (attr->comp_vector < rf->ceqs_count)
 		info.ceq_id = attr->comp_vector;
@@ -2213,11 +2222,18 @@ static int irdma_create_cq(struct ib_cq *ibcq,
 		}
 
 		entries++;
-		if (dev->hw_attrs.uk_attrs.hw_rev >= IRDMA_GEN_2)
+		if (!cqe_64byte_ena && dev->hw_attrs.uk_attrs.hw_rev >= IRDMA_GEN_2)
 			entries *= 2;
+
+		if (entries & 1)
+			entries += 1; /* cq size must be an even number */
+
 		ukinfo->cq_size = entries;
 
-		rsize = info.cq_uk_init_info.cq_size * sizeof(struct irdma_cqe);
+		if (cqe_64byte_ena)
+			rsize = info.cq_uk_init_info.cq_size * sizeof(struct irdma_extended_cqe);
+		else
+			rsize = info.cq_uk_init_info.cq_size * sizeof(struct irdma_cqe);
 		iwcq->kmem.size = ALIGN(round_up(rsize, 256), 256);
 		iwcq->kmem.va = dma_alloc_coherent(dev->hw->device,
 						   iwcq->kmem.size,
@@ -3784,8 +3800,12 @@ static void irdma_process_cqe(struct ib_wc *entry,
 	if (cq_poll_info->q_type == IRDMA_CQE_QTYPE_SQ) {
 		set_ib_wc_op_sq(cq_poll_info, entry);
 	} else {
-		set_ib_wc_op_rq(cq_poll_info, entry,
-				qp->qp_uk.qp_caps & IRDMA_SEND_WITH_IMM);
+		if (qp->dev->hw_attrs.uk_attrs.hw_rev <= IRDMA_GEN_2)
+			set_ib_wc_op_rq(cq_poll_info, entry,
+					qp->qp_uk.qp_caps & IRDMA_SEND_WITH_IMM ?
+					true : false);
+		else
+			set_ib_wc_op_rq_gen_3(cq_poll_info, entry);
 		if (qp->qp_uk.qp_type != IRDMA_QP_TYPE_ROCE_UD &&
 		    cq_poll_info->stag_invalid_set) {
 			entry->ex.invalidate_rkey = cq_poll_info->inv_stag;

drivers/infiniband/hw/irdma/verbs.h

@@ -267,6 +267,19 @@ static inline void set_ib_wc_op_sq(struct irdma_cq_poll_info *cq_poll_info,
 	}
 }
 
+static inline void set_ib_wc_op_rq_gen_3(struct irdma_cq_poll_info *info,
+					 struct ib_wc *entry)
+{
+	switch (info->op_type) {
+	case IRDMA_OP_TYPE_RDMA_WRITE:
+	case IRDMA_OP_TYPE_RDMA_WRITE_SOL:
+		entry->opcode = IB_WC_RECV_RDMA_WITH_IMM;
+		break;
+	default:
+		entry->opcode = IB_WC_RECV;
+	}
+}
+
 static inline void set_ib_wc_op_rq(struct irdma_cq_poll_info *cq_poll_info,
 				   struct ib_wc *entry, bool send_imm_support)
 {