[PATCH v3 net-next 3/5] octeontx2-af: npc: cn20k: add subbank search order control

[Ratheesh Kannoth <rkannoth@marvell.com>]

CN20K NPC MCAM is split into 32 subbanks that are searched in a
predefined order during allocation. Lower-numbered subbanks have
higher priority than higher-numbered ones.

Add a runtime devlink parameter "srch_order" (
DEVLINK_PARAM_TYPE_U32_ARRAY) to control the order in which
subbanks are searched during MCAM allocation.

Signed-off-by: Ratheesh Kannoth <rkannoth@marvell.com>
---
 .../ethernet/marvell/octeontx2/af/cn20k/npc.c | 87 ++++++++++++++++++
 .../ethernet/marvell/octeontx2/af/cn20k/npc.h |  2 +
 .../marvell/octeontx2/af/rvu_devlink.c        | 92 +++++++++++++++++--
 3 files changed, 171 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c
index e854b85ced9e..348a72c4ee43 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c
@@ -3809,6 +3809,93 @@ static void npc_unlock_all_subbank(void)
 		mutex_unlock(&npc_priv.sb[i].lock);
 }
 
+int npc_cn20k_search_order_set(struct rvu *rvu,
+			       u32 arr[MAX_NUM_SUB_BANKS], int cnt)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	u32 fslots[MAX_NUM_SUB_BANKS][2];
+	u32 uslots[MAX_NUM_SUB_BANKS][2];
+	int fcnt = 0, ucnt = 0;
+	struct npc_subbank *sb;
+	int idx, val, rc = 0;
+
+	unsigned long index;
+	void *v;
+
+	if (cnt != npc_priv.num_subbanks) {
+		dev_err(rvu->dev, "Number of entries(%u) != %u\n",
+			cnt, npc_priv.num_subbanks);
+		return -EINVAL;
+	}
+
+	mutex_lock(&mcam->lock);
+	npc_lock_all_subbank();
+	restrict_valid = false;
+
+	for (int i = 0; i < cnt; i++)
+		subbank_srch_order[i] = arr[i];
+
+	xa_for_each(&npc_priv.xa_sb_used, index, v) {
+		val = xa_to_value(v);
+		uslots[ucnt][0] = index;
+		uslots[ucnt][1] = val;
+		xa_erase(&npc_priv.xa_sb_used, index);
+		ucnt++;
+	}
+
+	xa_for_each(&npc_priv.xa_sb_free, index, v) {
+		val = xa_to_value(v);
+		fslots[fcnt][0] = index;
+		fslots[fcnt][1] = val;
+		xa_erase(&npc_priv.xa_sb_free, index);
+		fcnt++;
+	}
+
+	/* xa_store() is done under lock. If xa_store fails
+	 * ,no rollback is planned as it might also fail.
+	 */
+	for (int i = 0; i < ucnt; i++) {
+		idx  = uslots[i][1];
+		sb = &npc_priv.sb[idx];
+		sb->arr_idx = subbank_srch_order[sb->idx];
+		rc = xa_err(xa_store(&npc_priv.xa_sb_used, sb->arr_idx,
+				     xa_mk_value(sb->idx), GFP_KERNEL));
+		if (rc) {
+			dev_err(rvu->dev,
+				"Error to insert index to used list %u\n",
+				sb->idx);
+			goto fail_used;
+		}
+	}
+
+	for (int i = 0; i < fcnt; i++) {
+		idx  = fslots[i][1];
+		sb = &npc_priv.sb[idx];
+		sb->arr_idx = subbank_srch_order[sb->idx];
+		rc = xa_err(xa_store(&npc_priv.xa_sb_free, sb->arr_idx,
+				     xa_mk_value(sb->idx), GFP_KERNEL));
+		if (rc) {
+			dev_err(rvu->dev,
+				"Error to insert index to free list %u\n",
+				sb->idx);
+			goto fail_used;
+		}
+	}
+
+fail_used:
+	npc_unlock_all_subbank();
+	mutex_unlock(&mcam->lock);
+
+	return rc;
+}
+
+const u32 *npc_cn20k_search_order_get(bool *restricted_order, u32 *sz)
+{
+	*restricted_order = restrict_valid;
+	*sz = npc_priv.num_subbanks;
+	return subbank_srch_order;
+}
+
 /* Only non-ref non-contigous mcam indexes
  * are picked for defrag process
  */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h
index 004a556c7b90..b168ecfbc5c8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h
@@ -343,5 +343,7 @@ int npc_cn20k_defrag(struct rvu *rvu);
 int npc_mcam_idx_2_subbank_idx(struct rvu *rvu, u16 mcam_idx,
 			       struct npc_subbank **sb,
 			       int *sb_off);
+const u32 *npc_cn20k_search_order_get(bool *restricted_order, u32 *sz);
+int npc_cn20k_search_order_set(struct rvu *rvu, u32 arr[32], int cnt);
 
 #endif /* NPC_CN20K_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
index 287ff0eda152..420cda6d5d5f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
@@ -1258,6 +1258,7 @@ enum rvu_af_dl_param_id {
 	RVU_AF_DEVLINK_PARAM_ID_NPC_EXACT_FEATURE_DISABLE,
 	RVU_AF_DEVLINK_PARAM_ID_NPC_DEF_RULE_CNTR_ENABLE,
 	RVU_AF_DEVLINK_PARAM_ID_NPC_DEFRAG,
+	RVU_AF_DEVLINK_PARAM_ID_NPC_SRCH_ORDER,
 	RVU_AF_DEVLINK_PARAM_ID_NIX_MAXLF,
 };
 
@@ -1619,12 +1620,83 @@ static int rvu_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 	return 0;
 }
 
+static int rvu_af_dl_npc_srch_order_set(struct devlink *devlink, u32 id,
+					struct devlink_param_gset_ctx *ctx,
+					struct netlink_ext_ack *extack)
+{
+	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
+	struct rvu *rvu = rvu_dl->rvu;
+
+	return npc_cn20k_search_order_set(rvu,
+					  ctx->val.u32arr.val,
+					  ctx->val.u32arr.size);
+}
+
+static int rvu_af_dl_npc_srch_order_get(struct devlink *devlink, u32 id,
+					struct devlink_param_gset_ctx *ctx,
+					struct netlink_ext_ack *extack)
+{
+	bool restricted_order;
+	const u32 *order;
+	u32 sz;
+
+	order = npc_cn20k_search_order_get(&restricted_order, &sz);
+	ctx->val.u32arr.size = sz;
+	for (int i = 0; i < sz; i++)
+		ctx->val.u32arr.val[i] = order[i];
+
+	return 0;
+}
+
+static int rvu_af_dl_npc_srch_order_validate(struct devlink *devlink, u32 id,
+					     union devlink_param_value val,
+					     struct netlink_ext_ack *extack)
+{
+	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
+	struct rvu *rvu = rvu_dl->rvu;
+	bool restricted_order;
+	unsigned long w = 0;
+	u32 *arr;
+	u32 sz;
+
+	npc_cn20k_search_order_get(&restricted_order, &sz);
+	if (sz != val.u32arr.size) {
+		dev_err(rvu->dev,
+			"Wrong size %u, should be %u\n",
+			val.u32arr.size, sz);
+		return -EINVAL;
+	}
+
+	arr = val.u32arr.val;
+	for (int i = 0; i < sz; i++) {
+		if (arr[i] >= sz)
+			return -EINVAL;
+
+		w |= BIT_ULL(arr[i]);
+	}
+
+	if (bitmap_weight(&w, sz) != sz) {
+		dev_err(rvu->dev,
+			"Duplicate or out-of-range subbank index. %lu\n",
+			find_first_zero_bit(&w, sz));
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static const struct devlink_ops rvu_devlink_ops = {
 	.eswitch_mode_get = rvu_devlink_eswitch_mode_get,
 	.eswitch_mode_set = rvu_devlink_eswitch_mode_set,
 };
 
-static const struct devlink_param rvu_af_dl_param_defrag[] = {
+static const struct devlink_param rvu_af_dl_cn20k_params[] = {
+	DEVLINK_PARAM_DRIVER(RVU_AF_DEVLINK_PARAM_ID_NPC_SRCH_ORDER,
+			     "npc_srch_order", DEVLINK_PARAM_TYPE_U32_ARRAY,
+			     BIT(DEVLINK_PARAM_CMODE_RUNTIME),
+			     rvu_af_dl_npc_srch_order_get,
+			     rvu_af_dl_npc_srch_order_set,
+			     rvu_af_dl_npc_srch_order_validate),
 	DEVLINK_PARAM_DRIVER(RVU_AF_DEVLINK_PARAM_ID_NPC_DEFRAG,
 			     "npc_defrag", DEVLINK_PARAM_TYPE_STRING,
 			     BIT(DEVLINK_PARAM_CMODE_RUNTIME),
@@ -1666,13 +1738,13 @@ int rvu_register_dl(struct rvu *rvu)
 	}
 
 	if (is_cn20k(rvu->pdev)) {
-		err = devlink_params_register(dl, rvu_af_dl_param_defrag,
-					      ARRAY_SIZE(rvu_af_dl_param_defrag));
+		err = devlink_params_register(dl, rvu_af_dl_cn20k_params,
+					      ARRAY_SIZE(rvu_af_dl_cn20k_params));
 		if (err) {
 			dev_err(rvu->dev,
-				"devlink defrag params register failed with error %d",
+				"devlink cn20k params register failed with error %d",
 				err);
-			goto err_dl_defrag;
+			goto err_dl_cn20k_params;
 		}
 	}
 
@@ -1695,10 +1767,10 @@ int rvu_register_dl(struct rvu *rvu)
 
 err_dl_exact_match:
 	if (is_cn20k(rvu->pdev))
-		devlink_params_unregister(dl, rvu_af_dl_param_defrag,
-					  ARRAY_SIZE(rvu_af_dl_param_defrag));
+		devlink_params_unregister(dl, rvu_af_dl_cn20k_params,
+					  ARRAY_SIZE(rvu_af_dl_cn20k_params));
 
-err_dl_defrag:
+err_dl_cn20k_params:
 	devlink_params_unregister(dl, rvu_af_dl_params, ARRAY_SIZE(rvu_af_dl_params));
 
 err_dl_health:
@@ -1717,8 +1789,8 @@ void rvu_unregister_dl(struct rvu *rvu)
 	devlink_params_unregister(dl, rvu_af_dl_params, ARRAY_SIZE(rvu_af_dl_params));
 
 	if (is_cn20k(rvu->pdev))
-		devlink_params_unregister(dl, rvu_af_dl_param_defrag,
-					  ARRAY_SIZE(rvu_af_dl_param_defrag));
+		devlink_params_unregister(dl, rvu_af_dl_cn20k_params,
+					  ARRAY_SIZE(rvu_af_dl_cn20k_params));
 
 	/* Unregister exact match devlink only for CN10K-B */
 	if (rvu_npc_exact_has_match_table(rvu))
-- 
2.43.0