Merge branch 'mlxsw-Introduce-support-for-CQEv1-2'

Ido Schimmel says:

====================
mlxsw: Introduce support for CQEv1/2

Jiri says:

Current SwitchX2 and Spectrum FWs support CQEv0 and that is what we
implement in mlxsw. Spectrum FW also supports CQE v1 and v2.
However, Spectrum-2 won't support CQEv0. Prepare for it and setup the
CQE versions to use according to what is queried from FW.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 208 insertions, 51 deletions

diff --git a/drivers/net/ethernet/mellanox/mlxsw/cmd.h b/drivers/net/ethernet/mellanox/mlxsw/cmd.h
index 479511cf79bc..8da91b023b13 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/cmd.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/cmd.h
@@ -424,10 +424,15 @@ MLXSW_ITEM32(cmd_mbox, query_aq_cap, log_max_rdq_sz, 0x04, 24, 8);
 MLXSW_ITEM32(cmd_mbox, query_aq_cap, max_num_rdqs, 0x04, 0, 8);
 
 /* cmd_mbox_query_aq_cap_log_max_cq_sz
- * Log (base 2) of max CQEs allowed on CQ.
+ * Log (base 2) of the Maximum CQEs allowed in a CQ for CQEv0 and CQEv1.
  */
 MLXSW_ITEM32(cmd_mbox, query_aq_cap, log_max_cq_sz, 0x08, 24, 8);
 
+/* cmd_mbox_query_aq_cap_log_max_cqv2_sz
+ * Log (base 2) of the Maximum CQEs allowed in a CQ for CQEv2.
+ */
+MLXSW_ITEM32(cmd_mbox, query_aq_cap, log_max_cqv2_sz, 0x08, 16, 8);
+
 /* cmd_mbox_query_aq_cap_max_num_cqs
  * Maximum number of CQs.
  */
@@ -662,6 +667,12 @@ MLXSW_ITEM32(cmd_mbox, config_profile, set_kvd_hash_single_size, 0x0C, 25, 1);
  */
 MLXSW_ITEM32(cmd_mbox, config_profile, set_kvd_hash_double_size, 0x0C, 26, 1);
 
+/* cmd_mbox_config_set_cqe_version
+ * Capability bit. Setting a bit to 1 configures the profile
+ * according to the mailbox contents.
+ */
+MLXSW_ITEM32(cmd_mbox, config_profile, set_cqe_version, 0x08, 0, 1);
+
 /* cmd_mbox_config_profile_max_vepa_channels
  * Maximum number of VEPA channels per port (0 through 16)
  * 0 - multi-channel VEPA is disabled
@@ -841,6 +852,14 @@ MLXSW_ITEM32_INDEXED(cmd_mbox, config_profile, swid_config_type,
 MLXSW_ITEM32_INDEXED(cmd_mbox, config_profile, swid_config_properties,
 		     0x60, 0, 8, 0x08, 0x00, false);
 
+/* cmd_mbox_config_profile_cqe_version
+ * CQE version:
+ * 0: CQE version is 0
+ * 1: CQE version is either 1 or 2
+ * CQE ver 1 or 2 is configured by Completion Queue Context field cqe_ver.
+ */
+MLXSW_ITEM32(cmd_mbox, config_profile, cqe_version, 0xB0, 0, 8);
+
 /* ACCESS_REG - Access EMAD Supported Register
  * ----------------------------------
  * OpMod == 0 (N/A), INMmod == 0 (N/A)
@@ -1032,11 +1051,15 @@ static inline int mlxsw_cmd_sw2hw_cq(struct mlxsw_core *mlxsw_core,
 				 0, cq_number, in_mbox, MLXSW_CMD_MBOX_SIZE);
 }
 
-/* cmd_mbox_sw2hw_cq_cv
+enum mlxsw_cmd_mbox_sw2hw_cq_cqe_ver {
+	MLXSW_CMD_MBOX_SW2HW_CQ_CQE_VER_1,
+	MLXSW_CMD_MBOX_SW2HW_CQ_CQE_VER_2,
+};
+
+/* cmd_mbox_sw2hw_cq_cqe_ver
  * CQE Version.
- * 0 - CQE Version 0, 1 - CQE Version 1
  */
-MLXSW_ITEM32(cmd_mbox, sw2hw_cq, cv, 0x00, 28, 4);
+MLXSW_ITEM32(cmd_mbox, sw2hw_cq, cqe_ver, 0x00, 28, 4);
 
 /* cmd_mbox_sw2hw_cq_c_eqn
  * Event Queue this CQ reports completion events to.
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index 3a9381977d6d..db794a1a3a7e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -117,6 +117,7 @@ struct mlxsw_pci_queue {
 		struct {
 			u32 comp_sdq_count;
 			u32 comp_rdq_count;
+			enum mlxsw_pci_cqe_v v;
 		} cq;
 		struct {
 			u32 ev_cmd_count;
@@ -155,6 +156,8 @@ struct mlxsw_pci {
 	} cmd;
 	struct mlxsw_bus_info bus_info;
 	const struct pci_device_id *id;
+	enum mlxsw_pci_cqe_v max_cqe_ver; /* Maximal supported CQE version */
+	u8 num_sdq_cqs; /* Number of CQs used for SDQs */
 };
 
 static void mlxsw_pci_queue_tasklet_schedule(struct mlxsw_pci_queue *q)
@@ -202,24 +205,6 @@ static bool mlxsw_pci_elem_hw_owned(struct mlxsw_pci_queue *q, bool owner_bit)
 	return owner_bit != !!(q->consumer_counter & q->count);
 }
 
-static char *
-mlxsw_pci_queue_sw_elem_get(struct mlxsw_pci_queue *q,
-			    u32 (*get_elem_owner_func)(const char *))
-{
-	struct mlxsw_pci_queue_elem_info *elem_info;
-	char *elem;
-	bool owner_bit;
-
-	elem_info = mlxsw_pci_queue_elem_info_consumer_get(q);
-	elem = elem_info->elem;
-	owner_bit = get_elem_owner_func(elem);
-	if (mlxsw_pci_elem_hw_owned(q, owner_bit))
-		return NULL;
-	q->consumer_counter++;
-	rmb(); /* make sure we read owned bit before the rest of elem */
-	return elem;
-}
-
 static struct mlxsw_pci_queue_type_group *
 mlxsw_pci_queue_type_group_get(struct mlxsw_pci *mlxsw_pci,
 			       enum mlxsw_pci_queue_type q_type)
@@ -494,6 +479,17 @@ static void mlxsw_pci_rdq_fini(struct mlxsw_pci *mlxsw_pci,
 	}
 }
 
+static void mlxsw_pci_cq_pre_init(struct mlxsw_pci *mlxsw_pci,
+				  struct mlxsw_pci_queue *q)
+{
+	q->u.cq.v = mlxsw_pci->max_cqe_ver;
+
+	/* For SDQ it is pointless to use CQEv2, so use CQEv1 instead */
+	if (q->u.cq.v == MLXSW_PCI_CQE_V2 &&
+	    q->num < mlxsw_pci->num_sdq_cqs)
+		q->u.cq.v = MLXSW_PCI_CQE_V1;
+}
+
 static int mlxsw_pci_cq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 			     struct mlxsw_pci_queue *q)
 {
@@ -505,10 +501,16 @@ static int mlxsw_pci_cq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 	for (i = 0; i < q->count; i++) {
 		char *elem = mlxsw_pci_queue_elem_get(q, i);
 
-		mlxsw_pci_cqe_owner_set(elem, 1);
+		mlxsw_pci_cqe_owner_set(q->u.cq.v, elem, 1);
 	}
 
-	mlxsw_cmd_mbox_sw2hw_cq_cv_set(mbox, 0); /* CQE ver 0 */
+	if (q->u.cq.v == MLXSW_PCI_CQE_V1)
+		mlxsw_cmd_mbox_sw2hw_cq_cqe_ver_set(mbox,
+				MLXSW_CMD_MBOX_SW2HW_CQ_CQE_VER_1);
+	else if (q->u.cq.v == MLXSW_PCI_CQE_V2)
+		mlxsw_cmd_mbox_sw2hw_cq_cqe_ver_set(mbox,
+				MLXSW_CMD_MBOX_SW2HW_CQ_CQE_VER_2);
+
 	mlxsw_cmd_mbox_sw2hw_cq_c_eqn_set(mbox, MLXSW_PCI_EQ_COMP_NUM);
 	mlxsw_cmd_mbox_sw2hw_cq_st_set(mbox, 0);
 	mlxsw_cmd_mbox_sw2hw_cq_log_cq_size_set(mbox, ilog2(q->count));
@@ -559,7 +561,7 @@ static void mlxsw_pci_cqe_sdq_handle(struct mlxsw_pci *mlxsw_pci,
 static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci,
 				     struct mlxsw_pci_queue *q,
 				     u16 consumer_counter_limit,
-				     char *cqe)
+				     enum mlxsw_pci_cqe_v cqe_v, char *cqe)
 {
 	struct pci_dev *pdev = mlxsw_pci->pdev;
 	struct mlxsw_pci_queue_elem_info *elem_info;
@@ -579,10 +581,11 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci,
 	if (q->consumer_counter++ != consumer_counter_limit)
 		dev_dbg_ratelimited(&pdev->dev, "Consumer counter does not match limit in RDQ\n");
 
-	if (mlxsw_pci_cqe_lag_get(cqe)) {
+	if (mlxsw_pci_cqe_lag_get(cqe_v, cqe)) {
 		rx_info.is_lag = true;
-		rx_info.u.lag_id = mlxsw_pci_cqe_lag_id_get(cqe);
-		rx_info.lag_port_index = mlxsw_pci_cqe_lag_port_index_get(cqe);
+		rx_info.u.lag_id = mlxsw_pci_cqe_lag_id_get(cqe_v, cqe);
+		rx_info.lag_port_index =
+			mlxsw_pci_cqe_lag_subport_get(cqe_v, cqe);
 	} else {
 		rx_info.is_lag = false;
 		rx_info.u.sys_port = mlxsw_pci_cqe_system_port_get(cqe);
@@ -591,7 +594,7 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci,
 	rx_info.trap_id = mlxsw_pci_cqe_trap_id_get(cqe);
 
 	byte_count = mlxsw_pci_cqe_byte_count_get(cqe);
-	if (mlxsw_pci_cqe_crc_get(cqe))
+	if (mlxsw_pci_cqe_crc_get(cqe_v, cqe))
 		byte_count -= ETH_FCS_LEN;
 	skb_put(skb, byte_count);
 	mlxsw_core_skb_receive(mlxsw_pci->core, skb, &rx_info);
@@ -608,7 +611,18 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci,
 
 static char *mlxsw_pci_cq_sw_cqe_get(struct mlxsw_pci_queue *q)
 {
-	return mlxsw_pci_queue_sw_elem_get(q, mlxsw_pci_cqe_owner_get);
+	struct mlxsw_pci_queue_elem_info *elem_info;
+	char *elem;
+	bool owner_bit;
+
+	elem_info = mlxsw_pci_queue_elem_info_consumer_get(q);
+	elem = elem_info->elem;
+	owner_bit = mlxsw_pci_cqe_owner_get(q->u.cq.v, elem);
+	if (mlxsw_pci_elem_hw_owned(q, owner_bit))
+		return NULL;
+	q->consumer_counter++;
+	rmb(); /* make sure we read owned bit before the rest of elem */
+	return elem;
 }
 
 static void mlxsw_pci_cq_tasklet(unsigned long data)
@@ -621,8 +635,8 @@ static void mlxsw_pci_cq_tasklet(unsigned long data)
 
 	while ((cqe = mlxsw_pci_cq_sw_cqe_get(q))) {
 		u16 wqe_counter = mlxsw_pci_cqe_wqe_counter_get(cqe);
-		u8 sendq = mlxsw_pci_cqe_sr_get(cqe);
-		u8 dqn = mlxsw_pci_cqe_dqn_get(cqe);
+		u8 sendq = mlxsw_pci_cqe_sr_get(q->u.cq.v, cqe);
+		u8 dqn = mlxsw_pci_cqe_dqn_get(q->u.cq.v, cqe);
 
 		if (sendq) {
 			struct mlxsw_pci_queue *sdq;
@@ -636,7 +650,7 @@ static void mlxsw_pci_cq_tasklet(unsigned long data)
 
 			rdq = mlxsw_pci_rdq_get(mlxsw_pci, dqn);
 			mlxsw_pci_cqe_rdq_handle(mlxsw_pci, rdq,
-						 wqe_counter, cqe);
+						 wqe_counter, q->u.cq.v, cqe);
 			q->u.cq.comp_rdq_count++;
 		}
 		if (++items == credits)
@@ -648,6 +662,18 @@ static void mlxsw_pci_cq_tasklet(unsigned long data)
 	}
 }
 
+static u16 mlxsw_pci_cq_elem_count(const struct mlxsw_pci_queue *q)
+{
+	return q->u.cq.v == MLXSW_PCI_CQE_V2 ? MLXSW_PCI_CQE2_COUNT :
+					       MLXSW_PCI_CQE01_COUNT;
+}
+
+static u8 mlxsw_pci_cq_elem_size(const struct mlxsw_pci_queue *q)
+{
+	return q->u.cq.v == MLXSW_PCI_CQE_V2 ? MLXSW_PCI_CQE2_SIZE :
+					       MLXSW_PCI_CQE01_SIZE;
+}
+
 static int mlxsw_pci_eq_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 			     struct mlxsw_pci_queue *q)
 {
@@ -696,7 +722,18 @@ static void mlxsw_pci_eq_cmd_event(struct mlxsw_pci *mlxsw_pci, char *eqe)
 
 static char *mlxsw_pci_eq_sw_eqe_get(struct mlxsw_pci_queue *q)
 {
-	return mlxsw_pci_queue_sw_elem_get(q, mlxsw_pci_eqe_owner_get);
+	struct mlxsw_pci_queue_elem_info *elem_info;
+	char *elem;
+	bool owner_bit;
+
+	elem_info = mlxsw_pci_queue_elem_info_consumer_get(q);
+	elem = elem_info->elem;
+	owner_bit = mlxsw_pci_eqe_owner_get(elem);
+	if (mlxsw_pci_elem_hw_owned(q, owner_bit))
+		return NULL;
+	q->consumer_counter++;
+	rmb(); /* make sure we read owned bit before the rest of elem */
+	return elem;
 }
 
 static void mlxsw_pci_eq_tasklet(unsigned long data)
@@ -749,11 +786,15 @@ static void mlxsw_pci_eq_tasklet(unsigned long data)
 struct mlxsw_pci_queue_ops {
 	const char *name;
 	enum mlxsw_pci_queue_type type;
+	void (*pre_init)(struct mlxsw_pci *mlxsw_pci,
+			 struct mlxsw_pci_queue *q);
 	int (*init)(struct mlxsw_pci *mlxsw_pci, char *mbox,
 		    struct mlxsw_pci_queue *q);
 	void (*fini)(struct mlxsw_pci *mlxsw_pci,
 		     struct mlxsw_pci_queue *q);
 	void (*tasklet)(unsigned long data);
+	u16 (*elem_count_f)(const struct mlxsw_pci_queue *q);
+	u8 (*elem_size_f)(const struct mlxsw_pci_queue *q);
 	u16 elem_count;
 	u8 elem_size;
 };
@@ -776,11 +817,12 @@ static const struct mlxsw_pci_queue_ops mlxsw_pci_rdq_ops = {
 
 static const struct mlxsw_pci_queue_ops mlxsw_pci_cq_ops = {
 	.type		= MLXSW_PCI_QUEUE_TYPE_CQ,
+	.pre_init	= mlxsw_pci_cq_pre_init,
 	.init		= mlxsw_pci_cq_init,
 	.fini		= mlxsw_pci_cq_fini,
 	.tasklet	= mlxsw_pci_cq_tasklet,
-	.elem_count	= MLXSW_PCI_CQE_COUNT,
-	.elem_size	= MLXSW_PCI_CQE_SIZE
+	.elem_count_f	= mlxsw_pci_cq_elem_count,
+	.elem_size_f	= mlxsw_pci_cq_elem_size
 };
 
 static const struct mlxsw_pci_queue_ops mlxsw_pci_eq_ops = {
@@ -800,10 +842,15 @@ static int mlxsw_pci_queue_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 	int i;
 	int err;
 
-	spin_lock_init(&q->lock);
 	q->num = q_num;
-	q->count = q_ops->elem_count;
-	q->elem_size = q_ops->elem_size;
+	if (q_ops->pre_init)
+		q_ops->pre_init(mlxsw_pci, q);
+
+	spin_lock_init(&q->lock);
+	q->count = q_ops->elem_count_f ? q_ops->elem_count_f(q) :
+					 q_ops->elem_count;
+	q->elem_size = q_ops->elem_size_f ? q_ops->elem_size_f(q) :
+					    q_ops->elem_size;
 	q->type = q_ops->type;
 	q->pci = mlxsw_pci;
 
@@ -832,7 +879,7 @@ static int mlxsw_pci_queue_init(struct mlxsw_pci *mlxsw_pci, char *mbox,
 
 		elem_info = mlxsw_pci_queue_elem_info_get(q, i);
 		elem_info->elem =
-			__mlxsw_pci_queue_elem_get(q, q_ops->elem_size, i);
+			__mlxsw_pci_queue_elem_get(q, q->elem_size, i);
 	}
 
 	mlxsw_cmd_mbox_zero(mbox);
@@ -912,6 +959,7 @@ static int mlxsw_pci_aqs_init(struct mlxsw_pci *mlxsw_pci, char *mbox)
 	u8 rdq_log2sz;
 	u8 num_cqs;
 	u8 cq_log2sz;
+	u8 cqv2_log2sz;
 	u8 num_eqs;
 	u8 eq_log2sz;
 	int err;
@@ -927,6 +975,7 @@ static int mlxsw_pci_aqs_init(struct mlxsw_pci *mlxsw_pci, char *mbox)
 	rdq_log2sz = mlxsw_cmd_mbox_query_aq_cap_log_max_rdq_sz_get(mbox);
 	num_cqs = mlxsw_cmd_mbox_query_aq_cap_max_num_cqs_get(mbox);
 	cq_log2sz = mlxsw_cmd_mbox_query_aq_cap_log_max_cq_sz_get(mbox);
+	cqv2_log2sz = mlxsw_cmd_mbox_query_aq_cap_log_max_cqv2_sz_get(mbox);
 	num_eqs = mlxsw_cmd_mbox_query_aq_cap_max_num_eqs_get(mbox);
 	eq_log2sz = mlxsw_cmd_mbox_query_aq_cap_log_max_eq_sz_get(mbox);
 
@@ -938,12 +987,16 @@ static int mlxsw_pci_aqs_init(struct mlxsw_pci *mlxsw_pci, char *mbox)
 
 	if ((1 << sdq_log2sz != MLXSW_PCI_WQE_COUNT) ||
 	    (1 << rdq_log2sz != MLXSW_PCI_WQE_COUNT) ||
-	    (1 << cq_log2sz != MLXSW_PCI_CQE_COUNT) ||
+	    (1 << cq_log2sz != MLXSW_PCI_CQE01_COUNT) ||
+	    (mlxsw_pci->max_cqe_ver == MLXSW_PCI_CQE_V2 &&
+	     (1 << cqv2_log2sz != MLXSW_PCI_CQE2_COUNT)) ||
 	    (1 << eq_log2sz != MLXSW_PCI_EQE_COUNT)) {
 		dev_err(&pdev->dev, "Unsupported number of async queue descriptors\n");
 		return -EINVAL;
 	}
 
+	mlxsw_pci->num_sdq_cqs = num_sdqs;
+
 	err = mlxsw_pci_queue_group_init(mlxsw_pci, mbox, &mlxsw_pci_eq_ops,
 					 num_eqs);
 	if (err) {
@@ -1184,6 +1237,11 @@ static int mlxsw_pci_config_profile(struct mlxsw_pci *mlxsw_pci, char *mbox,
 		mlxsw_pci_config_profile_swid_config(mlxsw_pci, mbox, i,
 						     &profile->swid_config[i]);
 
+	if (mlxsw_pci->max_cqe_ver > MLXSW_PCI_CQE_V0) {
+		mlxsw_cmd_mbox_config_profile_set_cqe_version_set(mbox, 1);
+		mlxsw_cmd_mbox_config_profile_cqe_version_set(mbox, 1);
+	}
+
 	return mlxsw_cmd_config_profile_set(mlxsw_pci->core, mbox);
 }
 
@@ -1378,6 +1436,21 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core,
 	if (err)
 		goto err_query_resources;
 
+	if (MLXSW_CORE_RES_VALID(mlxsw_core, CQE_V2) &&
+	    MLXSW_CORE_RES_GET(mlxsw_core, CQE_V2))
+		mlxsw_pci->max_cqe_ver = MLXSW_PCI_CQE_V2;
+	else if (MLXSW_CORE_RES_VALID(mlxsw_core, CQE_V1) &&
+		 MLXSW_CORE_RES_GET(mlxsw_core, CQE_V1))
+		mlxsw_pci->max_cqe_ver = MLXSW_PCI_CQE_V1;
+	else if ((MLXSW_CORE_RES_VALID(mlxsw_core, CQE_V0) &&
+		  MLXSW_CORE_RES_GET(mlxsw_core, CQE_V0)) ||
+		 !MLXSW_CORE_RES_VALID(mlxsw_core, CQE_V0)) {
+		mlxsw_pci->max_cqe_ver = MLXSW_PCI_CQE_V0;
+	} else {
+		dev_err(&pdev->dev, "Invalid supported CQE version combination reported\n");
+		goto err_cqe_v_check;
+	}
+
 	err = mlxsw_pci_config_profile(mlxsw_pci, mbox, profile, res);
 	if (err)
 		goto err_config_profile;
@@ -1400,6 +1473,7 @@ err_request_eq_irq:
 	mlxsw_pci_aqs_fini(mlxsw_pci);
 err_aqs_init:
 err_config_profile:
+err_cqe_v_check:
 err_query_resources:
 err_boardinfo:
 	mlxsw_pci_fw_area_fini(mlxsw_pci);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
index fb082ad21b00..963155f6a17a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
@@ -82,10 +82,12 @@
 #define MLXSW_PCI_AQ_PAGES	8
 #define MLXSW_PCI_AQ_SIZE	(MLXSW_PCI_PAGE_SIZE * MLXSW_PCI_AQ_PAGES)
 #define MLXSW_PCI_WQE_SIZE	32 /* 32 bytes per element */
-#define MLXSW_PCI_CQE_SIZE	16 /* 16 bytes per element */
+#define MLXSW_PCI_CQE01_SIZE	16 /* 16 bytes per element */
+#define MLXSW_PCI_CQE2_SIZE	32 /* 32 bytes per element */
 #define MLXSW_PCI_EQE_SIZE	16 /* 16 bytes per element */
 #define MLXSW_PCI_WQE_COUNT	(MLXSW_PCI_AQ_SIZE / MLXSW_PCI_WQE_SIZE)
-#define MLXSW_PCI_CQE_COUNT	(MLXSW_PCI_AQ_SIZE / MLXSW_PCI_CQE_SIZE)
+#define MLXSW_PCI_CQE01_COUNT	(MLXSW_PCI_AQ_SIZE / MLXSW_PCI_CQE01_SIZE)
+#define MLXSW_PCI_CQE2_COUNT	(MLXSW_PCI_AQ_SIZE / MLXSW_PCI_CQE2_SIZE)
 #define MLXSW_PCI_EQE_COUNT	(MLXSW_PCI_AQ_SIZE / MLXSW_PCI_EQE_SIZE)
 #define MLXSW_PCI_EQE_UPDATE_COUNT	0x80
 
@@ -126,10 +128,48 @@ MLXSW_ITEM16_INDEXED(pci, wqe, byte_count, 0x02, 0, 14, 0x02, 0x00, false);
  */
 MLXSW_ITEM64_INDEXED(pci, wqe, address, 0x08, 0, 64, 0x8, 0x0, false);
 
+enum mlxsw_pci_cqe_v {
+	MLXSW_PCI_CQE_V0,
+	MLXSW_PCI_CQE_V1,
+	MLXSW_PCI_CQE_V2,
+};
+
+#define mlxsw_pci_cqe_item_helpers(name, v0, v1, v2)				\
+static inline u32 mlxsw_pci_cqe_##name##_get(enum mlxsw_pci_cqe_v v, char *cqe)	\
+{										\
+	switch (v) {								\
+	default:								\
+	case MLXSW_PCI_CQE_V0:							\
+		return mlxsw_pci_cqe##v0##_##name##_get(cqe);			\
+	case MLXSW_PCI_CQE_V1:							\
+		return mlxsw_pci_cqe##v1##_##name##_get(cqe);			\
+	case MLXSW_PCI_CQE_V2:							\
+		return mlxsw_pci_cqe##v2##_##name##_get(cqe);			\
+	}									\
+}										\
+static inline void mlxsw_pci_cqe_##name##_set(enum mlxsw_pci_cqe_v v,		\
+					      char *cqe, u32 val)		\
+{										\
+	switch (v) {								\
+	default:								\
+	case MLXSW_PCI_CQE_V0:							\
+		mlxsw_pci_cqe##v0##_##name##_set(cqe, val);			\
+		break;								\
+	case MLXSW_PCI_CQE_V1:							\
+		mlxsw_pci_cqe##v1##_##name##_set(cqe, val);			\
+		break;								\
+	case MLXSW_PCI_CQE_V2:							\
+		mlxsw_pci_cqe##v2##_##name##_set(cqe, val);			\
+		break;								\
+	}									\
+}
+
 /* pci_cqe_lag
  * Packet arrives from a port which is a LAG
  */
-MLXSW_ITEM32(pci, cqe, lag, 0x00, 23, 1);
+MLXSW_ITEM32(pci, cqe0, lag, 0x00, 23, 1);
+MLXSW_ITEM32(pci, cqe12, lag, 0x00, 24, 1);
+mlxsw_pci_cqe_item_helpers(lag, 0, 12, 12);
 
 /* pci_cqe_system_port/lag_id
  * When lag=0: System port on which the packet was received
@@ -138,8 +178,12 @@ MLXSW_ITEM32(pci, cqe, lag, 0x00, 23, 1);
  * bits [3:0] sub_port on which the packet was received
  */
 MLXSW_ITEM32(pci, cqe, system_port, 0x00, 0, 16);
-MLXSW_ITEM32(pci, cqe, lag_id, 0x00, 4, 12);
-MLXSW_ITEM32(pci, cqe, lag_port_index, 0x00, 0, 4);
+MLXSW_ITEM32(pci, cqe0, lag_id, 0x00, 4, 12);
+MLXSW_ITEM32(pci, cqe12, lag_id, 0x00, 0, 16);
+mlxsw_pci_cqe_item_helpers(lag_id, 0, 12, 12);
+MLXSW_ITEM32(pci, cqe0, lag_subport, 0x00, 0, 4);
+MLXSW_ITEM32(pci, cqe12, lag_subport, 0x00, 16, 8);
+mlxsw_pci_cqe_item_helpers(lag_subport, 0, 12, 12);
 
 /* pci_cqe_wqe_counter
  * WQE count of the WQEs completed on the associated dqn
@@ -162,28 +206,38 @@ MLXSW_ITEM32(pci, cqe, trap_id, 0x08, 0, 9);
  * Length include CRC. Indicates the length field includes
  * the packet's CRC.
  */
-MLXSW_ITEM32(pci, cqe, crc, 0x0C, 8, 1);
+MLXSW_ITEM32(pci, cqe0, crc, 0x0C, 8, 1);
+MLXSW_ITEM32(pci, cqe12, crc, 0x0C, 9, 1);
+mlxsw_pci_cqe_item_helpers(crc, 0, 12, 12);
 
 /* pci_cqe_e
  * CQE with Error.
  */
-MLXSW_ITEM32(pci, cqe, e, 0x0C, 7, 1);
+MLXSW_ITEM32(pci, cqe0, e, 0x0C, 7, 1);
+MLXSW_ITEM32(pci, cqe12, e, 0x00, 27, 1);
+mlxsw_pci_cqe_item_helpers(e, 0, 12, 12);
 
 /* pci_cqe_sr
  * 1 - Send Queue
  * 0 - Receive Queue
  */
-MLXSW_ITEM32(pci, cqe, sr, 0x0C, 6, 1);
+MLXSW_ITEM32(pci, cqe0, sr, 0x0C, 6, 1);
+MLXSW_ITEM32(pci, cqe12, sr, 0x00, 26, 1);
+mlxsw_pci_cqe_item_helpers(sr, 0, 12, 12);
 
 /* pci_cqe_dqn
  * Descriptor Queue (DQ) Number.
  */
-MLXSW_ITEM32(pci, cqe, dqn, 0x0C, 1, 5);
+MLXSW_ITEM32(pci, cqe0, dqn, 0x0C, 1, 5);
+MLXSW_ITEM32(pci, cqe12, dqn, 0x0C, 1, 6);
+mlxsw_pci_cqe_item_helpers(dqn, 0, 12, 12);
 
 /* pci_cqe_owner
  * Ownership bit.
  */
-MLXSW_ITEM32(pci, cqe, owner, 0x0C, 0, 1);
+MLXSW_ITEM32(pci, cqe01, owner, 0x0C, 0, 1);
+MLXSW_ITEM32(pci, cqe2, owner, 0x1C, 0, 1);
+mlxsw_pci_cqe_item_helpers(owner, 01, 01, 2);
 
 /* pci_eqe_event_type
  * Event type.
diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h
index 087aad52c195..fd9299ccec72 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/resources.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h
@@ -43,6 +43,9 @@ enum mlxsw_res_id {
 	MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE,
 	MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE,
 	MLXSW_RES_ID_MAX_TRAP_GROUPS,
+	MLXSW_RES_ID_CQE_V0,
+	MLXSW_RES_ID_CQE_V1,
+	MLXSW_RES_ID_CQE_V2,
 	MLXSW_RES_ID_COUNTER_POOL_SIZE,
 	MLXSW_RES_ID_MAX_SPAN,
 	MLXSW_RES_ID_COUNTER_SIZE_PACKETS_BYTES,
@@ -81,6 +84,9 @@ static u16 mlxsw_res_ids[] = {
 	[MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE] = 0x1002,
 	[MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE] = 0x1003,
 	[MLXSW_RES_ID_MAX_TRAP_GROUPS] = 0x2201,
+	[MLXSW_RES_ID_CQE_V0] = 0x2210,
+	[MLXSW_RES_ID_CQE_V1] = 0x2211,
+	[MLXSW_RES_ID_CQE_V2] = 0x2212,
 	[MLXSW_RES_ID_COUNTER_POOL_SIZE] = 0x2410,
 	[MLXSW_RES_ID_MAX_SPAN] = 0x2420,
 	[MLXSW_RES_ID_COUNTER_SIZE_PACKETS_BYTES] = 0x2443,