octeontx2-af: npc: cn20k: add subbank search order control

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 "srch_order" to control the order in which
subbanks are searched during MCAM allocation.

Signed-off-by: Ratheesh Kannoth <rkannoth@marvell.com>
Link: https://patch.msgid.link/20260609040453.711932-6-rkannoth@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.c

@@ -3372,7 +3372,7 @@ rvu_mbox_handler_npc_cn20k_get_kex_cfg(struct rvu *rvu,
 	return 0;
 }
 
-static int *subbank_srch_order;
+static u32 *subbank_srch_order;
 
 static void npc_populate_restricted_idxs(int num_subbanks)
 {
@@ -3384,7 +3384,7 @@ static int npc_create_srch_order(int cnt)
 {
 	int val = 0;
 
-	subbank_srch_order = kcalloc(cnt, sizeof(int),
+	subbank_srch_order = kcalloc(cnt, sizeof(u32),
 				     GFP_KERNEL);
 	if (!subbank_srch_order)
 		return -ENOMEM;
@@ -3902,6 +3902,122 @@ static void npc_unlock_all_subbank(void)
 		mutex_unlock(&npc_priv.sb[i].lock);
 }
 
+int npc_cn20k_search_order_set(struct rvu *rvu,
+			       u64 narr[MAX_NUM_SUB_BANKS], int cnt)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	int rsrc[2][MAX_NUM_SUB_BANKS] = { };
+	u8 save[MAX_NUM_SUB_BANKS] = { };
+	struct npc_subbank *sb;
+	struct xarray *xa;
+	int prio, rc, err;
+	int sb_idx;
+	enum {
+		FREE = 0,
+		USED = 1,
+	};
+
+	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();
+
+	for (sb_idx = 0; sb_idx < cnt; sb_idx++) {
+		sb = &npc_priv.sb[sb_idx];
+		save[sb->idx] = sb->arr_idx;
+	}
+
+	for (prio = 0; prio < cnt; prio++) {
+		sb_idx = narr[prio];
+		sb = &npc_priv.sb[sb_idx];
+
+		if (sb->flags & NPC_SUBBANK_FLAG_USED)
+			xa = &npc_priv.xa_sb_used;
+		else
+			xa = &npc_priv.xa_sb_free;
+
+		rc = xa_err(xa_store(xa, prio,
+				     xa_mk_value(sb_idx), GFP_KERNEL));
+		if (rc) {
+			dev_err(rvu->dev,
+				"Setting arr_idx=%d for sb=%d failed\n",
+				sb->arr_idx, sb_idx);
+			goto fail;
+		}
+
+		if (sb->flags & NPC_SUBBANK_FLAG_USED) {
+			rsrc[USED][sb->arr_idx] -= 1;
+			rsrc[USED][prio] += 1;
+		} else {
+			rsrc[FREE][sb->arr_idx] -= 1;
+			rsrc[FREE][prio] += 1;
+		}
+
+		sb->arr_idx = prio;
+	}
+
+	for (prio = 0; prio < cnt; prio++) {
+		if (rsrc[FREE][prio] == -1)
+			xa_erase(&npc_priv.xa_sb_free, prio);
+
+		if (rsrc[USED][prio] == -1)
+			xa_erase(&npc_priv.xa_sb_used, prio);
+	}
+
+	for (int i = 0; i < cnt; i++)
+		subbank_srch_order[i] = (u32)narr[i];
+
+	restrict_valid = false;
+
+	npc_unlock_all_subbank();
+	mutex_unlock(&mcam->lock);
+
+	return 0;
+
+fail:
+	for (prio = 0; prio < cnt; prio++) {
+		if (rsrc[FREE][prio] == 1)
+			xa_erase(&npc_priv.xa_sb_free, prio);
+
+		if (rsrc[USED][prio] == 1)
+			xa_erase(&npc_priv.xa_sb_used, prio);
+	}
+
+	for (sb_idx = 0; sb_idx < cnt; sb_idx++) {
+		sb = &npc_priv.sb[sb_idx];
+		sb->arr_idx = save[sb_idx];
+
+		if (sb->flags & NPC_SUBBANK_FLAG_USED)
+			xa = &npc_priv.xa_sb_used;
+		else
+			xa = &npc_priv.xa_sb_free;
+
+		/* Since the entry already exists, xa_store() replaces
+		 * the value without a kmalloc(), making failure highly unlikely.
+		 */
+		err = xa_err(xa_store(xa, sb->arr_idx,
+				      xa_mk_value(sb->idx), GFP_KERNEL));
+		WARN(!!err, "Failed to rollback sb=%u idx=%u\n",
+		     sb->idx, sb->arr_idx);
+	}
+
+	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
  */

drivers/net/ethernet/marvell/octeontx2/af/cn20k/npc.h

@@ -347,5 +347,8 @@ bool npc_is_cgx_or_lbk(struct rvu *rvu, u16 pcifunc);
 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, u64 narr[MAX_NUM_SUB_BANKS],
+			       int cnt);
 
 #endif /* NPC_CN20K_H */

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.u64arr.val,
+					  ctx->val.u64arr.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.u64arr.size = sz;
+	for (int i = 0; i < sz; i++)
+		ctx->val.u64arr.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;
+	u64 *arr;
+	u32 sz;
+
+	npc_cn20k_search_order_get(&restricted_order, &sz);
+	if (sz != val->u64arr.size) {
+		dev_err(rvu->dev,
+			"Wrong size %llu, should be %u\n",
+			val->u64arr.size, sz);
+		return -EINVAL;
+	}
+
+	arr = val->u64arr.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_U64_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,
+		err = devlink_params_register(dl, rvu_af_dl_cn20k_params,
-					      ARRAY_SIZE(rvu_af_dl_param_defrag));
+					      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,
+		devlink_params_unregister(dl, rvu_af_dl_cn20k_params,
-					  ARRAY_SIZE(rvu_af_dl_param_defrag));
+					  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,
+		devlink_params_unregister(dl, rvu_af_dl_cn20k_params,
-					  ARRAY_SIZE(rvu_af_dl_param_defrag));
+					  ARRAY_SIZE(rvu_af_dl_cn20k_params));
 
 	/* Unregister exact match devlink only for CN10K-B */
 	if (rvu_npc_exact_has_match_table(rvu))