octeontx2-af: NPA AQ instruction enqueue support

Add support for a RVU PF/VF to submit instructions to NPA AQ
via mbox. Instructions can be to init/write/read Aura/Pool/Qint
contexts. In case of read, context will be returned as part of
response to the mbox msg received.

Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 427 insertions, 0 deletions

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h
index c64d241f4df5..24021cb110e8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h
@@ -118,4 +118,17 @@ enum npa_aura_sz {
 
 #define NPA_AURA_COUNT(x)	(1ULL << ((x) + 6))
 
+/* NPA AQ result structure for init/read/write of aura HW contexts */
+struct npa_aq_aura_res {
+	struct	npa_aq_res_s	res;
+	struct	npa_aura_s	aura_ctx;
+	struct	npa_aura_s	ctx_mask;
+};
+
+/* NPA AQ result structure for init/read/write of pool HW contexts */
+struct npa_aq_pool_res {
+	struct	npa_aq_res_s	res;
+	struct	npa_pool_s	pool_ctx;
+	struct	npa_pool_s	ctx_mask;
+};
 #endif /* COMMON_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 8135339457f2..bf11058ac30c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -141,6 +141,7 @@ M(CGX_INTLBK_DISABLE,	0x20B, msg_req, msg_rsp)			\
 /* NPA mbox IDs (range 0x400 - 0x5FF) */				\
 M(NPA_LF_ALLOC,		0x400, npa_lf_alloc_req, npa_lf_alloc_rsp)	\
 M(NPA_LF_FREE,		0x401, msg_req, msg_rsp)			\
+M(NPA_AQ_ENQ,		0x402, npa_aq_enq_req, npa_aq_enq_rsp)		\
 /* SSO/SSOW mbox IDs (range 0x600 - 0x7FF) */				\
 /* TIM mbox IDs (range 0x800 - 0x9FF) */				\
 /* CPT mbox IDs (range 0xA00 - 0xBFF) */				\
@@ -290,4 +291,38 @@ struct npa_lf_alloc_rsp {
 	u16 qints; /* NPA_AF_CONST::QINTS */
 };
 
+/* NPA AQ enqueue msg */
+struct npa_aq_enq_req {
+	struct mbox_msghdr hdr;
+	u32 aura_id;
+	u8 ctype;
+	u8 op;
+	union {
+		/* Valid when op == WRITE/INIT and ctype == AURA.
+		 * LF fills the pool_id in aura.pool_addr. AF will translate
+		 * the pool_id to pool context pointer.
+		 */
+		struct npa_aura_s aura;
+		/* Valid when op == WRITE/INIT and ctype == POOL */
+		struct npa_pool_s pool;
+	};
+	/* Mask data when op == WRITE (1=write, 0=don't write) */
+	union {
+		/* Valid when op == WRITE and ctype == AURA */
+		struct npa_aura_s aura_mask;
+		/* Valid when op == WRITE and ctype == POOL */
+		struct npa_pool_s pool_mask;
+	};
+};
+
+struct npa_aq_enq_rsp {
+	struct mbox_msghdr hdr;
+	union {
+		/* Valid when op == READ and ctype == AURA */
+		struct npa_aura_s aura;
+		/* Valid when op == READ and ctype == POOL */
+		struct npa_pool_s pool;
+	};
+};
+
 #endif /* MBOX_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index b32d1f1d7266..a70c26bfe746 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -213,6 +213,9 @@ int rvu_mbox_handler_CGX_INTLBK_DISABLE(struct rvu *rvu, struct msg_req *req,
 /* NPA APIs */
 int rvu_npa_init(struct rvu *rvu);
 void rvu_npa_freemem(struct rvu *rvu);
+int rvu_mbox_handler_NPA_AQ_ENQ(struct rvu *rvu,
+				struct npa_aq_enq_req *req,
+				struct npa_aq_enq_rsp *rsp);
 int rvu_mbox_handler_NPA_LF_ALLOC(struct rvu *rvu,
 				  struct npa_lf_alloc_req *req,
 				  struct npa_lf_alloc_rsp *rsp);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
index ea0c5e0878e4..4ff0e760eeb2 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
@@ -15,6 +15,164 @@
 #include "rvu_reg.h"
 #include "rvu.h"
 
+static int npa_aq_enqueue_wait(struct rvu *rvu, struct rvu_block *block,
+			       struct npa_aq_inst_s *inst)
+{
+	struct admin_queue *aq = block->aq;
+	struct npa_aq_res_s *result;
+	int timeout = 1000;
+	u64 reg, head;
+
+	result = (struct npa_aq_res_s *)aq->res->base;
+
+	/* Get current head pointer where to append this instruction */
+	reg = rvu_read64(rvu, block->addr, NPA_AF_AQ_STATUS);
+	head = (reg >> 4) & AQ_PTR_MASK;
+
+	memcpy((void *)(aq->inst->base + (head * aq->inst->entry_sz)),
+	       (void *)inst, aq->inst->entry_sz);
+	memset(result, 0, sizeof(*result));
+	/* sync into memory */
+	wmb();
+
+	/* Ring the doorbell and wait for result */
+	rvu_write64(rvu, block->addr, NPA_AF_AQ_DOOR, 1);
+	while (result->compcode == NPA_AQ_COMP_NOTDONE) {
+		cpu_relax();
+		udelay(1);
+		timeout--;
+		if (!timeout)
+			return -EBUSY;
+	}
+
+	if (result->compcode != NPA_AQ_COMP_GOOD)
+		/* TODO: Replace this with some error code */
+		return -EBUSY;
+
+	return 0;
+}
+
+static int rvu_npa_aq_enq_inst(struct rvu *rvu, struct npa_aq_enq_req *req,
+			       struct npa_aq_enq_rsp *rsp)
+{
+	struct rvu_hwinfo *hw = rvu->hw;
+	u16 pcifunc = req->hdr.pcifunc;
+	int blkaddr, npalf, rc = 0;
+	struct npa_aq_inst_s inst;
+	struct rvu_block *block;
+	struct admin_queue *aq;
+	struct rvu_pfvf *pfvf;
+	void *ctx, *mask;
+
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	if (!pfvf->aura_ctx || req->aura_id >= pfvf->aura_ctx->qsize)
+		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;
+
+	block = &hw->block[blkaddr];
+	aq = block->aq;
+	if (!aq) {
+		dev_warn(rvu->dev, "%s: NPA AQ not initialized\n", __func__);
+		return NPA_AF_ERR_AQ_ENQUEUE;
+	}
+
+	npalf = rvu_get_lf(rvu, block, pcifunc, 0);
+	if (npalf < 0)
+		return NPA_AF_ERR_AF_LF_INVALID;
+
+	memset(&inst, 0, sizeof(struct npa_aq_inst_s));
+	inst.cindex = req->aura_id;
+	inst.lf = npalf;
+	inst.ctype = req->ctype;
+	inst.op = req->op;
+	/* Currently we are not supporting enqueuing multiple instructions,
+	 * so always choose first entry in result memory.
+	 */
+	inst.res_addr = (u64)aq->res->iova;
+
+	/* Clean result + context memory */
+	memset(aq->res->base, 0, aq->res->entry_sz);
+	/* Context needs to be written at RES_ADDR + 128 */
+	ctx = aq->res->base + 128;
+	/* Mask needs to be written at RES_ADDR + 256 */
+	mask = aq->res->base + 256;
+
+	switch (req->op) {
+	case NPA_AQ_INSTOP_WRITE:
+		/* Copy context and write mask */
+		if (req->ctype == NPA_AQ_CTYPE_AURA) {
+			memcpy(mask, &req->aura_mask,
+			       sizeof(struct npa_aura_s));
+			memcpy(ctx, &req->aura, sizeof(struct npa_aura_s));
+		} else {
+			memcpy(mask, &req->pool_mask,
+			       sizeof(struct npa_pool_s));
+			memcpy(ctx, &req->pool, sizeof(struct npa_pool_s));
+		}
+		break;
+	case NPA_AQ_INSTOP_INIT:
+		if (req->ctype == NPA_AQ_CTYPE_AURA) {
+			if (req->aura.pool_addr >= pfvf->pool_ctx->qsize) {
+				rc = NPA_AF_ERR_AQ_FULL;
+				break;
+			}
+			/* Set pool's context address */
+			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 */
+			memcpy(ctx, &req->pool, sizeof(struct npa_pool_s));
+		}
+		break;
+	case NPA_AQ_INSTOP_NOP:
+	case NPA_AQ_INSTOP_READ:
+	case NPA_AQ_INSTOP_LOCK:
+	case NPA_AQ_INSTOP_UNLOCK:
+		break;
+	default:
+		rc = NPA_AF_ERR_AQ_FULL;
+		break;
+	}
+
+	if (rc)
+		return rc;
+
+	spin_lock(&aq->lock);
+
+	/* Submit the instruction to AQ */
+	rc = npa_aq_enqueue_wait(rvu, block, &inst);
+	if (rc) {
+		spin_unlock(&aq->lock);
+		return rc;
+	}
+
+	spin_unlock(&aq->lock);
+
+	if (rsp) {
+		/* Copy read context into mailbox */
+		if (req->op == NPA_AQ_INSTOP_READ) {
+			if (req->ctype == NPA_AQ_CTYPE_AURA)
+				memcpy(&rsp->aura, ctx,
+				       sizeof(struct npa_aura_s));
+			else
+				memcpy(&rsp->pool, ctx,
+				       sizeof(struct npa_pool_s));
+		}
+	}
+
+	return 0;
+}
+
+int rvu_mbox_handler_NPA_AQ_ENQ(struct rvu *rvu,
+				struct npa_aq_enq_req *req,
+				struct npa_aq_enq_rsp *rsp)
+{
+	return rvu_npa_aq_enq_inst(rvu, req, rsp);
+}
+
 static void npa_ctx_free(struct rvu *rvu, struct rvu_pfvf *pfvf)
 {
 	qmem_free(rvu->dev, pfvf->aura_ctx);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
index ae1c18d75cb6..6ebe1c95ea0f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
@@ -136,4 +136,222 @@ struct npa_aq_res_s {
 #endif
 	u64 reserved_64_127;		/* W1 */
 };
+
+struct npa_aura_s {
+	u64 pool_addr;			/* W0 */
+#if defined(__BIG_ENDIAN_BITFIELD)	/* W1 */
+	u64 avg_level             : 8;
+	u64 reserved_118_119      : 2;
+	u64 shift                 : 6;
+	u64 aura_drop             : 8;
+	u64 reserved_98_103       : 6;
+	u64 bp_ena                : 2;
+	u64 aura_drop_ena         : 1;
+	u64 pool_drop_ena         : 1;
+	u64 reserved_93           : 1;
+	u64 avg_con               : 9;
+	u64 pool_way_mask         : 16;
+	u64 pool_caching          : 1;
+	u64 reserved_65           : 2;
+	u64 ena                   : 1;
+#else
+	u64 ena                   : 1;
+	u64 reserved_65           : 2;
+	u64 pool_caching          : 1;
+	u64 pool_way_mask         : 16;
+	u64 avg_con               : 9;
+	u64 reserved_93           : 1;
+	u64 pool_drop_ena         : 1;
+	u64 aura_drop_ena         : 1;
+	u64 bp_ena                : 2;
+	u64 reserved_98_103       : 6;
+	u64 aura_drop             : 8;
+	u64 shift                 : 6;
+	u64 reserved_118_119      : 2;
+	u64 avg_level             : 8;
+#endif
+#if defined(__BIG_ENDIAN_BITFIELD)	/* W2 */
+	u64 reserved_189_191      : 3;
+	u64 nix1_bpid             : 9;
+	u64 reserved_177_179      : 3;
+	u64 nix0_bpid             : 9;
+	u64 reserved_164_167      : 4;
+	u64 count                 : 36;
+#else
+	u64 count                 : 36;
+	u64 reserved_164_167      : 4;
+	u64 nix0_bpid             : 9;
+	u64 reserved_177_179      : 3;
+	u64 nix1_bpid             : 9;
+	u64 reserved_189_191      : 3;
+#endif
+#if defined(__BIG_ENDIAN_BITFIELD)	/* W3 */
+	u64 reserved_252_255      : 4;
+	u64 fc_hyst_bits          : 4;
+	u64 fc_stype              : 2;
+	u64 fc_up_crossing        : 1;
+	u64 fc_ena                : 1;
+	u64 reserved_240_243      : 4;
+	u64 bp                    : 8;
+	u64 reserved_228_231      : 4;
+	u64 limit                 : 36;
+#else
+	u64 limit                 : 36;
+	u64 reserved_228_231      : 4;
+	u64 bp                    : 8;
+	u64 reserved_240_243      : 4;
+	u64 fc_ena                : 1;
+	u64 fc_up_crossing        : 1;
+	u64 fc_stype              : 2;
+	u64 fc_hyst_bits          : 4;
+	u64 reserved_252_255      : 4;
+#endif
+	u64 fc_addr;			/* W4 */
+#if defined(__BIG_ENDIAN_BITFIELD)	/* W5 */
+	u64 reserved_379_383      : 5;
+	u64 err_qint_idx          : 7;
+	u64 reserved_371          : 1;
+	u64 thresh_qint_idx       : 7;
+	u64 reserved_363          : 1;
+	u64 thresh_up             : 1;
+	u64 thresh_int_ena        : 1;
+	u64 thresh_int            : 1;
+	u64 err_int_ena           : 8;
+	u64 err_int               : 8;
+	u64 update_time           : 16;
+	u64 pool_drop             : 8;
+#else
+	u64 pool_drop             : 8;
+	u64 update_time           : 16;
+	u64 err_int               : 8;
+	u64 err_int_ena           : 8;
+	u64 thresh_int            : 1;
+	u64 thresh_int_ena        : 1;
+	u64 thresh_up             : 1;
+	u64 reserved_363          : 1;
+	u64 thresh_qint_idx       : 7;
+	u64 reserved_371          : 1;
+	u64 err_qint_idx          : 7;
+	u64 reserved_379_383      : 5;
+#endif
+#if defined(__BIG_ENDIAN_BITFIELD)	/* W6 */
+	u64 reserved_420_447      : 28;
+	u64 thresh                : 36;
+#else
+	u64 thresh                : 36;
+	u64 reserved_420_447      : 28;
+#endif
+	u64 reserved_448_511;		/* W7 */
+};
+
+struct npa_pool_s {
+	u64 stack_base;			/* W0 */
+#if defined(__BIG_ENDIAN_BITFIELD)	/* W1 */
+	u64 reserved_115_127      : 13;
+	u64 buf_size              : 11;
+	u64 reserved_100_103      : 4;
+	u64 buf_offset            : 12;
+	u64 stack_way_mask        : 16;
+	u64 reserved_70_71        : 3;
+	u64 stack_caching         : 1;
+	u64 reserved_66_67        : 2;
+	u64 nat_align             : 1;
+	u64 ena                   : 1;
+#else
+	u64 ena                   : 1;
+	u64 nat_align             : 1;
+	u64 reserved_66_67        : 2;
+	u64 stack_caching         : 1;
+	u64 reserved_70_71        : 3;
+	u64 stack_way_mask        : 16;
+	u64 buf_offset            : 12;
+	u64 reserved_100_103      : 4;
+	u64 buf_size              : 11;
+	u64 reserved_115_127      : 13;
+#endif
+#if defined(__BIG_ENDIAN_BITFIELD)	/* W2 */
+	u64 stack_pages           : 32;
+	u64 stack_max_pages       : 32;
+#else
+	u64 stack_max_pages       : 32;
+	u64 stack_pages           : 32;
+#endif
+#if defined(__BIG_ENDIAN_BITFIELD)	/* W3 */
+	u64 reserved_240_255      : 16;
+	u64 op_pc                 : 48;
+#else
+	u64 op_pc                 : 48;
+	u64 reserved_240_255      : 16;
+#endif
+#if defined(__BIG_ENDIAN_BITFIELD)	/* W4 */
+	u64 reserved_316_319      : 4;
+	u64 update_time           : 16;
+	u64 reserved_297_299      : 3;
+	u64 fc_up_crossing        : 1;
+	u64 fc_hyst_bits          : 4;
+	u64 fc_stype              : 2;
+	u64 fc_ena                : 1;
+	u64 avg_con               : 9;
+	u64 avg_level             : 8;
+	u64 reserved_270_271      : 2;
+	u64 shift                 : 6;
+	u64 reserved_260_263      : 4;
+	u64 stack_offset          : 4;
+#else
+	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;
+#endif
+	u64 fc_addr;			/* W5 */
+	u64 ptr_start;			/* W6 */
+	u64 ptr_end;			/* W7 */
+#if defined(__BIG_ENDIAN_BITFIELD)	/* W8 */
+	u64 reserved_571_575      : 5;
+	u64 err_qint_idx          : 7;
+	u64 reserved_563          : 1;
+	u64 thresh_qint_idx       : 7;
+	u64 reserved_555          : 1;
+	u64 thresh_up             : 1;
+	u64 thresh_int_ena        : 1;
+	u64 thresh_int            : 1;
+	u64 err_int_ena           : 8;
+	u64 err_int               : 8;
+	u64 reserved_512_535      : 24;
+#else
+	u64 reserved_512_535      : 24;
+	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;
+#endif
+#if defined(__BIG_ENDIAN_BITFIELD)	/* W9 */
+	u64 reserved_612_639      : 28;
+	u64 thresh                : 36;
+#else
+	u64 thresh                : 36;
+	u64 reserved_612_639      : 28;
+#endif
+	u64 reserved_640_703;		/* W10 */
+	u64 reserved_704_767;		/* W11 */
+	u64 reserved_768_831;		/* W12 */
+	u64 reserved_832_895;		/* W13 */
+	u64 reserved_896_959;		/* W14 */
+	u64 reserved_960_1023;		/* W15 */
+};
 #endif /* RVU_STRUCT_H */