[PATCH v3 13/29] crypto/cnxk: account for CPT CTX updates and flush delays

[Anoob Joseph <anoobj@marvell.com>]

CPT CTX write with microcode would require CPT flush to complete to have
DRAM updated with the SA. Since datapath requires SA direction field,
introduce a new flag for the same.

Session destroy path is also updated to clear sa.valid bit using CTX
reload operation.

Session is updated with marker to differentiate s/w immutable and s/w
mutable portions.

Signed-off-by: Anoob Joseph <anoobj@marvell.com>
---
 drivers/crypto/cnxk/cn10k_cryptodev_ops.c |  4 +--
 drivers/crypto/cnxk/cn10k_ipsec.c         | 60 ++++++++++++++++++++++++-------
 drivers/crypto/cnxk/cn10k_ipsec.h         | 27 +++++++++-----
 drivers/crypto/cnxk/cn10k_ipsec_la_ops.h  | 18 +++++-----
 4 files changed, 77 insertions(+), 32 deletions(-)

diff --git a/drivers/crypto/cnxk/cn10k_cryptodev_ops.c b/drivers/crypto/cnxk/cn10k_cryptodev_ops.c
index d25a17c..7617bdc 100644
--- a/drivers/crypto/cnxk/cn10k_cryptodev_ops.c
+++ b/drivers/crypto/cnxk/cn10k_cryptodev_ops.c
@@ -53,7 +53,6 @@ cpt_sec_inst_fill(struct rte_crypto_op *op, struct cn10k_sec_session *sess,
 		  struct cpt_inflight_req *infl_req, struct cpt_inst_s *inst)
 {
 	struct rte_crypto_sym_op *sym_op = op->sym;
-	union roc_ot_ipsec_sa_word2 *w2;
 	struct cn10k_ipsec_sa *sa;
 	int ret;
 
@@ -68,9 +67,8 @@ cpt_sec_inst_fill(struct rte_crypto_op *op, struct cn10k_sec_session *sess,
 	}
 
 	sa = &sess->sa;
-	w2 = (union roc_ot_ipsec_sa_word2 *)&sa->in_sa.w2;
 
-	if (w2->s.dir == ROC_IE_SA_DIR_OUTBOUND)
+	if (sa->is_outbound)
 		ret = process_outb_sa(op, sa, inst);
 	else {
 		infl_req->op_flags |= CPT_OP_FLAGS_IPSEC_DIR_INBOUND;
diff --git a/drivers/crypto/cnxk/cn10k_ipsec.c b/drivers/crypto/cnxk/cn10k_ipsec.c
index a11a6b7..b4acbac 100644
--- a/drivers/crypto/cnxk/cn10k_ipsec.c
+++ b/drivers/crypto/cnxk/cn10k_ipsec.c
@@ -67,7 +67,7 @@ cn10k_ipsec_outb_sa_create(struct roc_cpt *roc_cpt, struct roc_cpt_lf *lf,
 		goto sa_dptr_free;
 	}
 
-	sa->inst.w7 = ipsec_cpt_inst_w7_get(roc_cpt, sa);
+	sa->inst.w7 = ipsec_cpt_inst_w7_get(roc_cpt, out_sa);
 
 #ifdef LA_IPSEC_DEBUG
 	/* Use IV from application in debug mode */
@@ -89,6 +89,8 @@ cn10k_ipsec_outb_sa_create(struct roc_cpt *roc_cpt, struct roc_cpt_lf *lf,
 	}
 #endif
 
+	sa->is_outbound = true;
+
 	/* Get Rlen calculation data */
 	ret = cnxk_ipsec_outb_rlens_get(&rlens, ipsec_xfrm, crypto_xfrm);
 	if (ret)
@@ -127,6 +129,8 @@ cn10k_ipsec_outb_sa_create(struct roc_cpt *roc_cpt, struct roc_cpt_lf *lf,
 	/* Copy word0 from sa_dptr to populate ctx_push_sz ctx_size fields */
 	memcpy(out_sa, sa_dptr, 8);
 
+	plt_atomic_thread_fence(__ATOMIC_SEQ_CST);
+
 	/* Write session using microcode opcode */
 	ret = roc_cpt_ctx_write(lf, sa_dptr, out_sa,
 				ROC_NIX_INL_OT_IPSEC_OUTB_HW_SZ);
@@ -135,9 +139,11 @@ cn10k_ipsec_outb_sa_create(struct roc_cpt *roc_cpt, struct roc_cpt_lf *lf,
 		goto sa_dptr_free;
 	}
 
-	/* Trigger CTX flush to write dirty data back to DRAM */
+	/* Trigger CTX flush so that data is written back to DRAM */
 	roc_cpt_lf_ctx_flush(lf, out_sa, false);
 
+	plt_atomic_thread_fence(__ATOMIC_SEQ_CST);
+
 sa_dptr_free:
 	plt_free(sa_dptr);
 
@@ -178,7 +184,8 @@ cn10k_ipsec_inb_sa_create(struct roc_cpt *roc_cpt, struct roc_cpt_lf *lf,
 		goto sa_dptr_free;
 	}
 
-	sa->inst.w7 = ipsec_cpt_inst_w7_get(roc_cpt, sa);
+	sa->is_outbound = false;
+	sa->inst.w7 = ipsec_cpt_inst_w7_get(roc_cpt, in_sa);
 
 	/* pre-populate CPT INST word 4 */
 	inst_w4.u64 = 0;
@@ -214,6 +221,8 @@ cn10k_ipsec_inb_sa_create(struct roc_cpt *roc_cpt, struct roc_cpt_lf *lf,
 	/* Copy word0 from sa_dptr to populate ctx_push_sz ctx_size fields */
 	memcpy(in_sa, sa_dptr, 8);
 
+	plt_atomic_thread_fence(__ATOMIC_SEQ_CST);
+
 	/* Write session using microcode opcode */
 	ret = roc_cpt_ctx_write(lf, sa_dptr, in_sa,
 				ROC_NIX_INL_OT_IPSEC_INB_HW_SZ);
@@ -222,9 +231,11 @@ cn10k_ipsec_inb_sa_create(struct roc_cpt *roc_cpt, struct roc_cpt_lf *lf,
 		goto sa_dptr_free;
 	}
 
-	/* Trigger CTX flush to write dirty data back to DRAM */
+	/* Trigger CTX flush so that data is written back to DRAM */
 	roc_cpt_lf_ctx_flush(lf, in_sa, false);
 
+	plt_atomic_thread_fence(__ATOMIC_SEQ_CST);
+
 sa_dptr_free:
 	plt_free(sa_dptr);
 
@@ -300,21 +311,46 @@ cn10k_sec_session_create(void *device, struct rte_security_session_conf *conf,
 }
 
 static int
-cn10k_sec_session_destroy(void *device __rte_unused,
-			  struct rte_security_session *sess)
+cn10k_sec_session_destroy(void *dev, struct rte_security_session *sec_sess)
 {
-	struct cn10k_sec_session *priv;
+	struct rte_cryptodev *crypto_dev = dev;
+	union roc_ot_ipsec_sa_word2 *w2;
+	struct cn10k_sec_session *sess;
 	struct rte_mempool *sess_mp;
+	struct cn10k_ipsec_sa *sa;
+	struct cnxk_cpt_qp *qp;
+	struct roc_cpt_lf *lf;
 
-	priv = get_sec_session_private_data(sess);
+	sess = get_sec_session_private_data(sec_sess);
+	if (sess == NULL)
+		return 0;
 
-	if (priv == NULL)
+	qp = crypto_dev->data->queue_pairs[0];
+	if (qp == NULL)
 		return 0;
 
-	sess_mp = rte_mempool_from_obj(priv);
+	lf = &qp->lf;
 
-	set_sec_session_private_data(sess, NULL);
-	rte_mempool_put(sess_mp, priv);
+	sa = &sess->sa;
+
+	/* Trigger CTX flush to write dirty data back to DRAM */
+	roc_cpt_lf_ctx_flush(lf, &sa->in_sa, false);
+
+	/* Wait for 1 ms so that flush is complete */
+	rte_delay_ms(1);
+
+	w2 = (union roc_ot_ipsec_sa_word2 *)&sa->in_sa.w2;
+	w2->s.valid = 0;
+
+	plt_atomic_thread_fence(__ATOMIC_SEQ_CST);
+
+	/* Trigger CTX reload to fetch new data from DRAM */
+	roc_cpt_lf_ctx_reload(lf, &sa->in_sa);
+
+	sess_mp = rte_mempool_from_obj(sess);
+
+	set_sec_session_private_data(sec_sess, NULL);
+	rte_mempool_put(sess_mp, sess);
 
 	return 0;
 }
diff --git a/drivers/crypto/cnxk/cn10k_ipsec.h b/drivers/crypto/cnxk/cn10k_ipsec.h
index 86cd248..cc7ca19 100644
--- a/drivers/crypto/cnxk/cn10k_ipsec.h
+++ b/drivers/crypto/cnxk/cn10k_ipsec.h
@@ -7,28 +7,37 @@
 
 #include <rte_security.h>
 
+#include "roc_api.h"
+
 #include "cnxk_ipsec.h"
 
-#define CN10K_IPSEC_SA_CTX_HDR_SIZE 1
+typedef void *CN10K_SA_CONTEXT_MARKER[0];
 
 struct cn10k_ipsec_sa {
-	union {
-		/** Inbound SA */
-		struct roc_ot_ipsec_inb_sa in_sa;
-		/** Outbound SA */
-		struct roc_ot_ipsec_outb_sa out_sa;
-	};
 	/** Pre-populated CPT inst words */
 	struct cnxk_cpt_inst_tmpl inst;
 	uint16_t max_extended_len;
 	uint16_t iv_offset;
 	uint8_t iv_length;
 	bool ip_csum_enable;
-};
+	bool is_outbound;
+
+	/**
+	 * End of SW mutable area
+	 */
+	CN10K_SA_CONTEXT_MARKER sw_area_end __rte_aligned(ROC_ALIGN);
+
+	union {
+		/** Inbound SA */
+		struct roc_ot_ipsec_inb_sa in_sa;
+		/** Outbound SA */
+		struct roc_ot_ipsec_outb_sa out_sa;
+	};
+} __rte_aligned(ROC_ALIGN);
 
 struct cn10k_sec_session {
 	struct cn10k_ipsec_sa sa;
-} __rte_cache_aligned;
+} __rte_aligned(ROC_ALIGN);
 
 void cn10k_sec_ops_override(void);
 
diff --git a/drivers/crypto/cnxk/cn10k_ipsec_la_ops.h b/drivers/crypto/cnxk/cn10k_ipsec_la_ops.h
index 881fbd1..cab6a50 100644
--- a/drivers/crypto/cnxk/cn10k_ipsec_la_ops.h
+++ b/drivers/crypto/cnxk/cn10k_ipsec_la_ops.h
@@ -54,6 +54,7 @@ process_outb_sa(struct rte_crypto_op *cop, struct cn10k_ipsec_sa *sess,
 	struct rte_crypto_sym_op *sym_op = cop->sym;
 	struct rte_mbuf *m_src = sym_op->m_src;
 	uint64_t inst_w4_u64 = sess->inst.w4;
+	uint64_t dptr;
 
 	if (unlikely(rte_pktmbuf_tailroom(m_src) < sess->max_extended_len)) {
 		plt_dp_err("Not enough tail room");
@@ -76,10 +77,10 @@ process_outb_sa(struct rte_crypto_op *cop, struct cn10k_ipsec_sa *sess,
 		inst_w4_u64 &= ~BIT_ULL(32);
 
 	/* Prepare CPT instruction */
-	inst->w4.u64 = inst_w4_u64;
-	inst->w4.s.dlen = rte_pktmbuf_pkt_len(m_src);
-	inst->dptr = rte_pktmbuf_iova(m_src);
-	inst->rptr = inst->dptr;
+	inst->w4.u64 = inst_w4_u64 | rte_pktmbuf_pkt_len(m_src);
+	dptr = rte_pktmbuf_iova(m_src);
+	inst->dptr = dptr;
+	inst->rptr = dptr;
 
 	return 0;
 }
@@ -90,12 +91,13 @@ process_inb_sa(struct rte_crypto_op *cop, struct cn10k_ipsec_sa *sa,
 {
 	struct rte_crypto_sym_op *sym_op = cop->sym;
 	struct rte_mbuf *m_src = sym_op->m_src;
+	uint64_t dptr;
 
 	/* Prepare CPT instruction */
-	inst->w4.u64 = sa->inst.w4;
-	inst->w4.s.dlen = rte_pktmbuf_pkt_len(m_src);
-	inst->dptr = rte_pktmbuf_iova(m_src);
-	inst->rptr = inst->dptr;
+	inst->w4.u64 = sa->inst.w4 | rte_pktmbuf_pkt_len(m_src);
+	dptr = rte_pktmbuf_iova(m_src);
+	inst->dptr = dptr;
+	inst->rptr = dptr;
 
 	return 0;
 }
-- 
2.7.4