[net-next PATCH 1/4] octeontx2-af: npa: cn20k: Add NPA Halo support

Subbaraya Sundeep posted 4 patches 3 weeks ago
There is a newer version of this series
[net-next PATCH 1/4] octeontx2-af: npa: cn20k: Add NPA Halo support
Posted by Subbaraya Sundeep 3 weeks ago
From: Linu Cherian <lcherian@marvell.com>

CN20K silicon implements unified aura and pool context
type called Halo for better resource usage. Add support to
handle Halo context type operations.

Signed-off-by: Linu Cherian <lcherian@marvell.com>
Signed-off-by: Subbaraya Sundeep <sbhatta@marvell.com>
---
 .../ethernet/marvell/octeontx2/af/cn20k/npa.c | 27 +++++++
 .../marvell/octeontx2/af/cn20k/struct.h       | 81 +++++++++++++++++++
 .../net/ethernet/marvell/octeontx2/af/mbox.h  |  6 ++
 .../net/ethernet/marvell/octeontx2/af/rvu.h   |  2 +
 .../ethernet/marvell/octeontx2/af/rvu_npa.c   | 56 +++++++++++--
 .../marvell/octeontx2/af/rvu_struct.h         |  1 +
 6 files changed, 168 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npa.c b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npa.c
index fe8f926c8b75..c963f43dc7b0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npa.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npa.c
@@ -19,3 +19,30 @@ int rvu_mbox_handler_npa_cn20k_aq_enq(struct rvu *rvu,
 				   (struct npa_aq_enq_rsp *)rsp);
 }
 EXPORT_SYMBOL(rvu_mbox_handler_npa_cn20k_aq_enq);
+
+int rvu_npa_halo_hwctx_disable(struct npa_aq_enq_req *req)
+{
+	struct npa_cn20k_aq_enq_req *hreq;
+
+	hreq = (struct npa_cn20k_aq_enq_req *)req;
+
+	hreq->halo.bp_ena_0 = 0;
+	hreq->halo.bp_ena_1 = 0;
+	hreq->halo.bp_ena_2 = 0;
+	hreq->halo.bp_ena_3 = 0;
+	hreq->halo.bp_ena_4 = 0;
+	hreq->halo.bp_ena_5 = 0;
+	hreq->halo.bp_ena_6 = 0;
+	hreq->halo.bp_ena_7 = 0;
+
+	hreq->halo_mask.bp_ena_0 = 1;
+	hreq->halo_mask.bp_ena_1 = 1;
+	hreq->halo_mask.bp_ena_2 = 1;
+	hreq->halo_mask.bp_ena_3 = 1;
+	hreq->halo_mask.bp_ena_4 = 1;
+	hreq->halo_mask.bp_ena_5 = 1;
+	hreq->halo_mask.bp_ena_6 = 1;
+	hreq->halo_mask.bp_ena_7 = 1;
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/struct.h b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/struct.h
index 763f6cabd7c2..2364bafd329d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/struct.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/struct.h
@@ -377,4 +377,85 @@ struct npa_cn20k_pool_s {
 
 static_assert(sizeof(struct npa_cn20k_pool_s) == NIX_MAX_CTX_SIZE);
 
+struct npa_cn20k_halo_s {
+	u64 stack_base                  : 64;
+	u64 ena                         :  1;
+	u64 nat_align                   :  1;
+	u64 reserved_66_67              :  2;
+	u64 stack_caching               :  1;
+	u64 reserved_69_71              :  3;
+	u64 aura_drop_ena               :  1;
+	u64 reserved_73_79              :  7;
+	u64 aura_drop                   :  8;
+	u64 buf_offset                  : 12;
+	u64 reserved_100_103            :  4;
+	u64 buf_size                    : 12;
+	u64 reserved_116_119            :  4;
+	u64 ref_cnt_prof                :  3;
+	u64 reserved_123_127            :  5;
+	u64 stack_max_pages             : 32;
+	u64 stack_pages                 : 32;
+	u64 bp_0                        :  7;
+	u64 bp_1                        :  7;
+	u64 bp_2                        :  7;
+	u64 bp_3                        :  7;
+	u64 bp_4                        :  7;
+	u64 bp_5                        :  7;
+	u64 bp_6                        :  7;
+	u64 bp_7                        :  7;
+	u64 bp_ena_0                    :  1;
+	u64 bp_ena_1                    :  1;
+	u64 bp_ena_2                    :  1;
+	u64 bp_ena_3                    :  1;
+	u64 bp_ena_4                    :  1;
+	u64 bp_ena_5                    :  1;
+	u64 bp_ena_6                    :  1;
+	u64 bp_ena_7                    :  1;
+	u64 stack_offset                :  4;
+	u64 reserved_260_263            :  4;
+	u64 shift                       :  6;
+	u64 reserved_270_271            :  2;
+	u64 avg_level                   :  8;
+	u64 avg_con                     :  9;
+	u64 fc_ena                      :  1;
+	u64 fc_stype                    :  2;
+	u64 fc_hyst_bits                :  4;
+	u64 fc_up_crossing              :  1;
+	u64 reserved_297_299            :  3;
+	u64 update_time                 : 16;
+	u64 reserved_316_319            :  4;
+	u64 fc_addr                     : 64;
+	u64 ptr_start                   : 64;
+	u64 ptr_end                     : 64;
+	u64 bpid_0                      : 12;
+	u64 reserved_524_535            : 12;
+	u64 err_int                     :  8;
+	u64 err_int_ena                 :  8;
+	u64 thresh_int                  :  1;
+	u64 thresh_int_ena              :  1;
+	u64 thresh_up                   :  1;
+	u64 reserved_555                :  1;
+	u64 thresh_qint_idx             :  7;
+	u64 reserved_563                :  1;
+	u64 err_qint_idx                :  7;
+	u64 reserved_571_575            :  5;
+	u64 thresh                      : 36;
+	u64 reserved_612_615            :  4;
+	u64 fc_msh_dst                  : 11;
+	u64 reserved_627_630            :  4;
+	u64 op_dpc_ena                  :  1;
+	u64 op_dpc_set                  :  5;
+	u64 reserved_637_637            :  1;
+	u64 stream_ctx                  :  1;
+	u64 unified_ctx                 :  1;
+	u64 reserved_640_703            : 64;
+	u64 reserved_704_767            : 64;
+	u64 reserved_768_831            : 64;
+	u64 reserved_832_895            : 64;
+	u64 reserved_896_959            : 64;
+	u64 reserved_960_1023           : 64;
+};
+
+static_assert(sizeof(struct npa_cn20k_halo_s) == NIX_MAX_CTX_SIZE);
+
 #endif
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index dc42c81c0942..4a97bd93d882 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -884,6 +884,8 @@ struct npa_cn20k_aq_enq_req {
 		struct npa_cn20k_aura_s aura;
 		/* Valid when op == WRITE/INIT and ctype == POOL */
 		struct npa_cn20k_pool_s pool;
+		/* Valid when op == WRITE/INIT and ctype == HALO */
+		struct npa_cn20k_halo_s halo;
 	};
 	/* Mask data when op == WRITE (1=write, 0=don't write) */
 	union {
@@ -891,6 +893,8 @@ struct npa_cn20k_aq_enq_req {
 		struct npa_cn20k_aura_s aura_mask;
 		/* Valid when op == WRITE and ctype == POOL */
 		struct npa_cn20k_pool_s pool_mask;
+		/* Valid when op == WRITE/INIT and ctype == HALO */
+		struct npa_cn20k_halo_s halo_mask;
 	};
 };
 
@@ -901,6 +905,8 @@ struct npa_cn20k_aq_enq_rsp {
 		struct npa_cn20k_aura_s aura;
 		/* Valid when op == READ and ctype == POOL */
 		struct npa_cn20k_pool_s pool;
+		/* Valid when op == READ and ctype == HALO */
+		struct npa_cn20k_halo_s halo;
 	};
 };
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index a466181cf908..1ffb338401ac 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -261,6 +261,7 @@ struct rvu_pfvf {
 	struct qmem	*pool_ctx;
 	struct qmem	*npa_qints_ctx;
 	unsigned long	*aura_bmap;
+	unsigned long	*halo_bmap; /* Aura and Halo bmap are mutually exclusive */
 	unsigned long	*pool_bmap;
 
 	/* NIX contexts */
@@ -1008,6 +1009,7 @@ void rvu_npa_freemem(struct rvu *rvu);
 void rvu_npa_lf_teardown(struct rvu *rvu, u16 pcifunc, int npalf);
 int rvu_npa_aq_enq_inst(struct rvu *rvu, struct npa_aq_enq_req *req,
 			struct npa_aq_enq_rsp *rsp);
+int rvu_npa_halo_hwctx_disable(struct npa_aq_enq_req *req);
 
 /* NIX APIs */
 bool is_nixlf_attached(struct rvu *rvu, u16 pcifunc);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
index e2a33e46b48a..aa2b8acf6be4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
@@ -12,6 +12,11 @@
 #include "rvu_reg.h"
 #include "rvu.h"
 
+static inline bool npa_ctype_invalid(struct rvu *rvu, int ctype)
+{
+	return !is_cn20k(rvu->pdev) && ctype == NPA_AQ_CTYPE_HALO;
+}
+
 static int npa_aq_enqueue_wait(struct rvu *rvu, struct rvu_block *block,
 			       struct npa_aq_inst_s *inst)
 {
@@ -72,13 +77,19 @@ int rvu_npa_aq_enq_inst(struct rvu *rvu, struct npa_aq_enq_req *req,
 	bool ena;
 
 	pfvf = rvu_get_pfvf(rvu, pcifunc);
-	if (!pfvf->aura_ctx || req->aura_id >= pfvf->aura_ctx->qsize)
+	if (!pfvf->aura_ctx || req->aura_id >= pfvf->aura_ctx->qsize ||
+	    npa_ctype_invalid(rvu, req->ctype))
 		return NPA_AF_ERR_AQ_ENQUEUE;
 
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPA, pcifunc);
 	if (!pfvf->npalf || blkaddr < 0)
 		return NPA_AF_ERR_AF_LF_INVALID;
 
+	/* Ensure halo bitmap is exclusive to halo ctype */
+	if (is_cn20k(rvu->pdev) && req->ctype != NPA_AQ_CTYPE_HALO &&
+	    test_bit(req->aura_id, pfvf->halo_bmap))
+		return NPA_AF_ERR_AQ_ENQUEUE;
+
 	block = &hw->block[blkaddr];
 	aq = block->aq;
 	if (!aq) {
@@ -119,7 +130,7 @@ int rvu_npa_aq_enq_inst(struct rvu *rvu, struct npa_aq_enq_req *req,
 			memcpy(mask, &req->aura_mask,
 			       sizeof(struct npa_aura_s));
 			memcpy(ctx, &req->aura, sizeof(struct npa_aura_s));
-		} else {
+		} else { /* Applies to both pool and halo as the size is compatible */
 			memcpy(mask, &req->pool_mask,
 			       sizeof(struct npa_pool_s));
 			memcpy(ctx, &req->pool, sizeof(struct npa_pool_s));
@@ -135,7 +146,7 @@ int rvu_npa_aq_enq_inst(struct rvu *rvu, struct npa_aq_enq_req *req,
 			req->aura.pool_addr = pfvf->pool_ctx->iova +
 			(req->aura.pool_addr * pfvf->pool_ctx->entry_sz);
 			memcpy(ctx, &req->aura, sizeof(struct npa_aura_s));
-		} else { /* POOL's context */
+		} else { /* Applies to both pool and halo as the size is compatible */
 			memcpy(ctx, &req->pool, sizeof(struct npa_pool_s));
 		}
 		break;
@@ -176,6 +187,20 @@ int rvu_npa_aq_enq_inst(struct rvu *rvu, struct npa_aq_enq_req *req,
 		}
 	}
 
+	if (req->ctype == NPA_AQ_CTYPE_HALO) {
+		if (req->op == NPA_AQ_INSTOP_INIT && req->aura.ena)
+			__set_bit(req->aura_id, pfvf->halo_bmap);
+		if (req->op == NPA_AQ_INSTOP_WRITE) {
+			ena = (req->aura.ena & req->aura_mask.ena) |
+				(test_bit(req->aura_id, pfvf->halo_bmap) &
+				~req->aura_mask.ena);
+			if (ena)
+				__set_bit(req->aura_id, pfvf->halo_bmap);
+			else
+				__clear_bit(req->aura_id, pfvf->halo_bmap);
+		}
+	}
+
 	/* Set pool bitmap if pool hw context is enabled */
 	if (req->ctype == NPA_AQ_CTYPE_POOL) {
 		if (req->op == NPA_AQ_INSTOP_INIT && req->pool.ena)
@@ -198,7 +223,7 @@ int rvu_npa_aq_enq_inst(struct rvu *rvu, struct npa_aq_enq_req *req,
 			if (req->ctype == NPA_AQ_CTYPE_AURA)
 				memcpy(&rsp->aura, ctx,
 				       sizeof(struct npa_aura_s));
-			else
+			else /* Applies to both pool and halo as the size is compatible */
 				memcpy(&rsp->pool, ctx,
 				       sizeof(struct npa_pool_s));
 		}
@@ -215,7 +240,8 @@ static int npa_lf_hwctx_disable(struct rvu *rvu, struct hwctx_disable_req *req)
 	int id, cnt = 0;
 	int err = 0, rc;
 
-	if (!pfvf->pool_ctx || !pfvf->aura_ctx)
+	if (!pfvf->pool_ctx || !pfvf->aura_ctx ||
+	    npa_ctype_invalid(rvu, req->ctype))
 		return NPA_AF_ERR_AQ_ENQUEUE;
 
 	memset(&aq_req, 0, sizeof(struct npa_aq_enq_req));
@@ -233,6 +259,12 @@ static int npa_lf_hwctx_disable(struct rvu *rvu, struct hwctx_disable_req *req)
 		aq_req.aura_mask.bp_ena = 1;
 		cnt = pfvf->aura_ctx->qsize;
 		bmap = pfvf->aura_bmap;
+	} else if (req->ctype == NPA_AQ_CTYPE_HALO) {
+		aq_req.aura.ena = 0;
+		aq_req.aura_mask.ena = 1;
+		rvu_npa_halo_hwctx_disable(&aq_req);
+		cnt = pfvf->aura_ctx->qsize;
+		bmap = pfvf->halo_bmap;
 	}
 
 	aq_req.ctype = req->ctype;
@@ -311,6 +343,9 @@ static void npa_ctx_free(struct rvu *rvu, struct rvu_pfvf *pfvf)
 	kfree(pfvf->aura_bmap);
 	pfvf->aura_bmap = NULL;
 
+	kfree(pfvf->halo_bmap);
+	pfvf->halo_bmap = NULL;
+
 	qmem_free(rvu->dev, pfvf->aura_ctx);
 	pfvf->aura_ctx = NULL;
 
@@ -374,6 +409,13 @@ int rvu_mbox_handler_npa_lf_alloc(struct rvu *rvu,
 	if (!pfvf->aura_bmap)
 		goto free_mem;
 
+	if (is_cn20k(rvu->pdev)) {
+		pfvf->halo_bmap = kcalloc(NPA_AURA_COUNT(req->aura_sz), sizeof(long),
+					  GFP_KERNEL);
+		if (!pfvf->halo_bmap)
+			goto free_mem;
+	}
+
 	/* Alloc memory for pool HW contexts */
 	hwctx_size = 1UL << ((ctx_cfg >> 4) & 0xF);
 	err = qmem_alloc(rvu->dev, &pfvf->pool_ctx, req->nr_pools, hwctx_size);
@@ -562,6 +604,10 @@ void rvu_npa_lf_teardown(struct rvu *rvu, u16 pcifunc, int npalf)
 	ctx_req.ctype = NPA_AQ_CTYPE_AURA;
 	npa_lf_hwctx_disable(rvu, &ctx_req);
 
+	/* Disable all Halos */
+	ctx_req.ctype = NPA_AQ_CTYPE_HALO;
+	npa_lf_hwctx_disable(rvu, &ctx_req);
+
 	npa_ctx_free(rvu, pfvf);
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
index 8e868f815de1..d37cf2cf0fee 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
@@ -130,6 +130,7 @@ enum npa_aq_comp {
 enum npa_aq_ctype {
 	NPA_AQ_CTYPE_AURA = 0x0,
 	NPA_AQ_CTYPE_POOL = 0x1,
+	NPA_AQ_CTYPE_HALO = 0x2,
 };
 
 /* NPA admin queue instruction opcodes */
-- 
2.48.1
Re: [net-next,1/4] octeontx2-af: npa: cn20k: Add NPA Halo support
Posted by Simon Horman 2 weeks, 5 days ago
This is an AI-generated review of your patch. The human sending this
email has considered the AI review valid, or at least plausible.

For local reproduction steps see https://netdev-ai.bots.linux.dev/ai-local.html
---
octeontx2-af: npa: cn20k: Add NPA Halo support

CN20K silicon implements unified aura and pool context type called Halo
for better resource usage. This patch adds support to handle Halo context
type operations.

> diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npa.c b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npa.c
> index fe8f926c8b75..c963f43dc7b0 100644
> --- a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npa.c
> +++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npa.c

[ ... ]

> diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
> index e2a33e46b48a..aa2b8acf6be4 100644
> --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
> +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c

[ ... ]

> @@ -233,6 +259,12 @@ static int npa_lf_hwctx_disable(struct rvu *rvu, struct hwctx_disable_req *req)
>  		aq_req.aura_mask.bp_ena = 1;
>  		cnt = pfvf->aura_ctx->qsize;
>  		bmap = pfvf->aura_bmap;
> +	} else if (req->ctype == NPA_AQ_CTYPE_HALO) {
> +		aq_req.aura.ena = 0;
> +		aq_req.aura_mask.ena = 1;
> +		rvu_npa_halo_hwctx_disable(&aq_req);
> +		cnt = pfvf->aura_ctx->qsize;
> +		bmap = pfvf->halo_bmap;
>  	}
>
>  	aq_req.ctype = req->ctype;
> @@ -241,8 +273,8 @@ static int npa_lf_hwctx_disable(struct rvu *rvu, struct hwctx_disable_req *req)
>  		rc = rvu_npa_aq_enq_inst(rvu, &aq_req, NULL);
>  		if (rc) {
>  			err = rc;
>  			dev_err(rvu->dev, "Failed to disable %s:%d context\n",
>  				(req->ctype == NPA_AQ_CTYPE_AURA) ?
>  				"Aura" : "Pool", id);
>  		}
>  	}

When disabling a HALO context fails, wouldn't the error message print
"Pool" instead of "Halo"? The ternary expression only checks for AURA,
so HALO failures would be logged as Pool failures, making debugging on
cn20k hardware misleading.