[net-next PATCH v3 4/4] octeontx2-pf: cn20k: Use unified Halo context

[Subbaraya Sundeep <sbhatta@marvell.com>]

Use unified Halo context present in CN20K hardware for
octeontx2 netdevs instead of aura and pool contexts.

Signed-off-by: Subbaraya Sundeep <sbhatta@marvell.com>
---
 .../ethernet/marvell/octeontx2/nic/cn20k.c    | 213 +++++++++---------
 .../ethernet/marvell/octeontx2/nic/cn20k.h    |   3 +
 .../marvell/octeontx2/nic/otx2_common.h       |   3 +
 .../ethernet/marvell/octeontx2/nic/otx2_pf.c  |   6 +
 4 files changed, 122 insertions(+), 103 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c
index a5a8f4558717..08033858c59d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c
@@ -242,15 +242,6 @@ int cn20k_register_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs)
 
 #define RQ_BP_LVL_AURA   (255 - ((85 * 256) / 100)) /* BP when 85% is full */
 
-static u8 cn20k_aura_bpid_idx(struct otx2_nic *pfvf, int aura_id)
-{
-#ifdef CONFIG_DCB
-	return pfvf->queue_to_pfc_map[aura_id];
-#else
-	return 0;
-#endif
-}
-
 static int cn20k_tc_get_entry_index(struct otx2_flow_config *flow_cfg,
 				    struct otx2_tc_flow *node)
 {
@@ -517,84 +508,7 @@ int cn20k_tc_alloc_entry(struct otx2_nic *nic,
 	return 0;
 }
 
-static int cn20k_aura_aq_init(struct otx2_nic *pfvf, int aura_id,
-			      int pool_id, int numptrs)
-{
-	struct npa_cn20k_aq_enq_req *aq;
-	struct otx2_pool *pool;
-	u8 bpid_idx;
-	int err;
-
-	pool = &pfvf->qset.pool[pool_id];
-
-	/* Allocate memory for HW to update Aura count.
-	 * Alloc one cache line, so that it fits all FC_STYPE modes.
-	 */
-	if (!pool->fc_addr) {
-		err = qmem_alloc(pfvf->dev, &pool->fc_addr, 1, OTX2_ALIGN);
-		if (err)
-			return err;
-	}
-
-	/* Initialize this aura's context via AF */
-	aq = otx2_mbox_alloc_msg_npa_cn20k_aq_enq(&pfvf->mbox);
-	if (!aq) {
-		/* Shared mbox memory buffer is full, flush it and retry */
-		err = otx2_sync_mbox_msg(&pfvf->mbox);
-		if (err)
-			return err;
-		aq = otx2_mbox_alloc_msg_npa_cn20k_aq_enq(&pfvf->mbox);
-		if (!aq)
-			return -ENOMEM;
-	}
-
-	aq->aura_id = aura_id;
-
-	/* Will be filled by AF with correct pool context address */
-	aq->aura.pool_addr = pool_id;
-	aq->aura.pool_caching = 1;
-	aq->aura.shift = ilog2(numptrs) - 8;
-	aq->aura.count = numptrs;
-	aq->aura.limit = numptrs;
-	aq->aura.avg_level = 255;
-	aq->aura.ena = 1;
-	aq->aura.fc_ena = 1;
-	aq->aura.fc_addr = pool->fc_addr->iova;
-	aq->aura.fc_hyst_bits = 0; /* Store count on all updates */
-
-	/* Enable backpressure for RQ aura */
-	if (aura_id < pfvf->hw.rqpool_cnt && !is_otx2_lbkvf(pfvf->pdev)) {
-		aq->aura.bp_ena = 0;
-		/* If NIX1 LF is attached then specify NIX1_RX.
-		 *
-		 * Below NPA_AURA_S[BP_ENA] is set according to the
-		 * NPA_BPINTF_E enumeration given as:
-		 * 0x0 + a*0x1 where 'a' is 0 for NIX0_RX and 1 for NIX1_RX so
-		 * NIX0_RX is 0x0 + 0*0x1 = 0
-		 * NIX1_RX is 0x0 + 1*0x1 = 1
-		 * But in HRM it is given that
-		 * "NPA_AURA_S[BP_ENA](w1[33:32]) - Enable aura backpressure to
-		 * NIX-RX based on [BP] level. One bit per NIX-RX; index
-		 * enumerated by NPA_BPINTF_E."
-		 */
-		if (pfvf->nix_blkaddr == BLKADDR_NIX1)
-			aq->aura.bp_ena = 1;
-
-		bpid_idx = cn20k_aura_bpid_idx(pfvf, aura_id);
-		aq->aura.bpid = pfvf->bpid[bpid_idx];
-
-		/* Set backpressure level for RQ's Aura */
-		aq->aura.bp = RQ_BP_LVL_AURA;
-	}
-
-	/* Fill AQ info */
-	aq->ctype = NPA_AQ_CTYPE_AURA;
-	aq->op = NPA_AQ_INSTOP_INIT;
-
-	return 0;
-}
-
-static int cn20k_pool_aq_init(struct otx2_nic *pfvf, u16 pool_id,
+static int cn20k_halo_aq_init(struct otx2_nic *pfvf, u16 pool_id,
 			      int stack_pages, int numptrs, int buf_size,
 			      int type)
 {
@@ -610,36 +524,57 @@ static int cn20k_pool_aq_init(struct otx2_nic *pfvf, u16 pool_id,
 	if (err)
 		return err;
 
+	/* Allocate memory for HW to update Aura count.
+	 * Alloc one cache line, so that it fits all FC_STYPE modes.
+	 */
+	if (!pool->fc_addr) {
+		err = qmem_alloc(pfvf->dev, &pool->fc_addr, 1, OTX2_ALIGN);
+		if (err) {
+			qmem_free(pfvf->dev, pool->stack);
+			return err;
+		}
+	}
+
 	pool->rbsize = buf_size;
 
-	/* Initialize this pool's context via AF */
+	/* Initialize this aura's context via AF */
 	aq = otx2_mbox_alloc_msg_npa_cn20k_aq_enq(&pfvf->mbox);
 	if (!aq) {
 		/* Shared mbox memory buffer is full, flush it and retry */
 		err = otx2_sync_mbox_msg(&pfvf->mbox);
-		if (err) {
-			qmem_free(pfvf->dev, pool->stack);
-			return err;
-		}
+		if (err)
+			goto free_mem;
 		aq = otx2_mbox_alloc_msg_npa_cn20k_aq_enq(&pfvf->mbox);
 		if (!aq) {
-			qmem_free(pfvf->dev, pool->stack);
-			return -ENOMEM;
+			err = -ENOMEM;
+			goto free_mem;
 		}
 	}
 
 	aq->aura_id = pool_id;
-	aq->pool.stack_base = pool->stack->iova;
-	aq->pool.stack_caching = 1;
-	aq->pool.ena = 1;
-	aq->pool.buf_size = buf_size / 128;
-	aq->pool.stack_max_pages = stack_pages;
-	aq->pool.shift = ilog2(numptrs) - 8;
-	aq->pool.ptr_start = 0;
-	aq->pool.ptr_end = ~0ULL;
+
+	aq->halo.stack_base = pool->stack->iova;
+	aq->halo.stack_caching = 1;
+	aq->halo.ena = 1;
+	aq->halo.buf_size = buf_size / 128;
+	aq->halo.stack_max_pages = stack_pages;
+	aq->halo.shift = ilog2(numptrs) - 8;
+	aq->halo.ptr_start = 0;
+	aq->halo.ptr_end = ~0ULL;
+
+	aq->halo.avg_level = 255;
+	aq->halo.fc_ena = 1;
+	aq->halo.fc_addr = pool->fc_addr->iova;
+	aq->halo.fc_hyst_bits = 0; /* Store count on all updates */
+
+	if (pfvf->npa_dpc_valid) {
+		aq->halo.op_dpc_ena = 1;
+		aq->halo.op_dpc_set = pfvf->npa_dpc;
+	}
+	aq->halo.unified_ctx = 1;
 
 	/* Fill AQ info */
-	aq->ctype = NPA_AQ_CTYPE_POOL;
+	aq->ctype = NPA_AQ_CTYPE_HALO;
 	aq->op = NPA_AQ_INSTOP_INIT;
 
 	if (type != AURA_NIX_RQ) {
@@ -661,6 +596,78 @@ static int cn20k_pool_aq_init(struct otx2_nic *pfvf, u16 pool_id,
 	}
 
 	return 0;
+
+free_mem:
+	qmem_free(pfvf->dev, pool->stack);
+	qmem_free(pfvf->dev, pool->fc_addr);
+	return err;
+}
+
+static int cn20k_aura_aq_init(struct otx2_nic *pfvf, int aura_id,
+			      int pool_id, int numptrs)
+{
+	return 0;
+}
+
+static int cn20k_pool_aq_init(struct otx2_nic *pfvf, u16 pool_id,
+			      int stack_pages, int numptrs, int buf_size,
+			      int type)
+{
+	return cn20k_halo_aq_init(pfvf, pool_id, stack_pages,
+				  numptrs, buf_size, type);
+}
+
+int cn20k_npa_alloc_dpc(struct otx2_nic *nic)
+{
+	struct npa_cn20k_dpc_alloc_req *req;
+	struct npa_cn20k_dpc_alloc_rsp *rsp;
+	int err;
+
+	req = otx2_mbox_alloc_msg_npa_cn20k_dpc_alloc(&nic->mbox);
+	if (!req)
+		return -ENOMEM;
+
+	/* Count successful ALLOC requests only */
+	req->dpc_conf = 1ULL << 4;
+
+	err = otx2_sync_mbox_msg(&nic->mbox);
+	if (err)
+		return err;
+
+	rsp = (struct npa_cn20k_dpc_alloc_rsp *)otx2_mbox_get_rsp(&nic->mbox.mbox,
+								  0, &req->hdr);
+	if (IS_ERR(rsp))
+		return PTR_ERR(rsp);
+
+	nic->npa_dpc = rsp->cntr_id;
+	nic->npa_dpc_valid = true;
+
+	return 0;
+}
+
+int cn20k_npa_free_dpc(struct otx2_nic *nic)
+{
+	struct npa_cn20k_dpc_free_req *req;
+	int err;
+
+	if (!nic->npa_dpc_valid)
+		return 0;
+
+	mutex_lock(&nic->mbox.lock);
+
+	req = otx2_mbox_alloc_msg_npa_cn20k_dpc_free(&nic->mbox);
+	if (!req) {
+		mutex_unlock(&nic->mbox.lock);
+		return -ENOMEM;
+	}
+
+	req->cntr_id = nic->npa_dpc;
+
+	err = otx2_sync_mbox_msg(&nic->mbox);
+
+	mutex_unlock(&nic->mbox.lock);
+
+	return err;
 }
 
 static int cn20k_sq_aq_init(void *dev, u16 qidx, u8 chan_offset, u16 sqb_aura)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.h b/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.h
index b5e527f6d7eb..16a69d84ea79 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.h
@@ -28,4 +28,7 @@ int cn20k_tc_alloc_entry(struct otx2_nic *nic,
 			 struct otx2_tc_flow *new_node,
 			 struct npc_install_flow_req *dummy);
 int cn20k_tc_free_mcam_entry(struct otx2_nic *nic, u16 entry);
+int cn20k_npa_alloc_dpc(struct otx2_nic *nic);
+int cn20k_npa_free_dpc(struct otx2_nic *nic);
+
 #endif /* CN20K_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index eecee612b7b2..f997dfc0fedd 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -592,6 +592,9 @@ struct otx2_nic {
 	struct cn10k_ipsec	ipsec;
 	/* af_xdp zero-copy */
 	unsigned long		*af_xdp_zc_qidx;
+
+	bool			npa_dpc_valid;
+	u8			npa_dpc; /* NPA DPC counter id */
 };
 
 static inline bool is_otx2_lbkvf(struct pci_dev *pdev)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index ee623476e5ff..2941549d46c8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -1651,6 +1651,9 @@ int otx2_init_hw_resources(struct otx2_nic *pf)
 	if (!is_otx2_lbkvf(pf->pdev))
 		otx2_nix_config_bp(pf, true);
 
+	if (is_cn20k(pf->pdev))
+		cn20k_npa_alloc_dpc(pf);
+
 	/* Init Auras and pools used by NIX RQ, for free buffer ptrs */
 	err = otx2_rq_aura_pool_init(pf);
 	if (err) {
@@ -1790,6 +1793,9 @@ void otx2_free_hw_resources(struct otx2_nic *pf)
 
 	otx2_free_sq_res(pf);
 
+	if (is_cn20k(pf->pdev))
+		cn20k_npa_free_dpc(pf);
+
 	/* Free RQ buffer pointers*/
 	otx2_free_aura_ptr(pf, AURA_NIX_RQ);
 
-- 
2.48.1