Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Here we go, another merge window full of networking and #ebpf changes:

   1) Snoop DHCPACKS in batman-adv to learn MAC/IP pairs in the DHCP
      range without dealing with floods of ARP traffic, from Linus
      Lüssing.

   2) Throttle buffered multicast packet transmission in mt76, from
      Felix Fietkau.

   3) Support adaptive interrupt moderation in ice, from Brett Creeley.

   4) A lot of struct_size conversions, from Gustavo A. R. Silva.

   5) Add peek/push/pop commands to bpftool, as well as bash completion,
      from Stanislav Fomichev.

   6) Optimize sk_msg_clone(), from Vakul Garg.

   7) Add SO_BINDTOIFINDEX, from David Herrmann.

   8) Be more conservative with local resends due to local congestion,
      from Yuchung Cheng.

   9) Allow vetoing of unsupported VXLAN FDBs, from Petr Machata.

  10) Add health buffer support to devlink, from Eran Ben Elisha.

  11) Add TXQ scheduling API to mac80211, from Toke Høiland-Jørgensen.

  12) Add statistics to basic packet scheduler filter, from Cong Wang.

  13) Add GRE tunnel support for mlxsw Spectrum-2, from Nir Dotan.

  14) Lots of new IP tunneling forwarding tests, also from Nir Dotan.

  15) Add 3ad stats to bonding, from Nikolay Aleksandrov.

  16) Lots of probing improvements for bpftool, from Quentin Monnet.

  17) Various nfp drive #ebpf JIT improvements from Jakub Kicinski.

  18) Allow #ebpf programs to access gso_segs from skb shared info, from
      Eric Dumazet.

  19) Add sock_diag support for AF_XDP sockets, from Björn Töpel.

  20) Support 22260 iwlwifi devices, from Luca Coelho.

  21) Use rbtree for ipv6 defragmentation, from Peter Oskolkov.

  22) Add JMP32 instruction class support to #ebpf, from Jiong Wang.

  23) Add spinlock support to #ebpf, from Alexei Starovoitov.

  24) Support 256-bit keys and TLS 1.3 in ktls, from Dave Watson.

  25) Add device infomation API to devlink, from Jakub Kicinski.

  26) Add new timestamping socket options which are y2038 safe, from
      Deepa Dinamani.

  27) Add RX checksum offloading for various sh_eth chips, from Sergei
      Shtylyov.

  28) Flow offload infrastructure, from Pablo Neira Ayuso.

  29) Numerous cleanups, improvements, and bug fixes to the PHY layer
      and many drivers from Heiner Kallweit.

  30) Lots of changes to try and make packet scheduler classifiers run
      lockless as much as possible, from Vlad Buslov.

  31) Support BCM957504 chip in bnxt_en driver, from Erik Burrows.

  32) Add concurrency tests to tc-tests infrastructure, from Vlad
      Buslov.

  33) Add hwmon support to aquantia, from Heiner Kallweit.

  34) Allow 64-bit values for SO_MAX_PACING_RATE, from Eric Dumazet.

  And I would be remiss if I didn't thank the various major networking
  subsystem maintainers for integrating much of this work before I even
  saw it. Alexei Starovoitov, Daniel Borkmann, Pablo Neira Ayuso,
  Johannes Berg, Kalle Valo, and many others. Thank you!"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2207 commits)
  net/sched: avoid unused-label warning
  net: ignore sysctl_devconf_inherit_init_net without SYSCTL
  phy: mdio-mux: fix Kconfig dependencies
  net: phy: use phy_modify_mmd_changed in genphy_c45_an_config_aneg
  net: dsa: mv88e6xxx: add call to mv88e6xxx_ports_cmode_init to probe for new DSA framework
  selftest/net: Remove duplicate header
  sky2: Disable MSI on Dell Inspiron 1545 and Gateway P-79
  net/mlx5e: Update tx reporter status in case channels were successfully opened
  devlink: Add support for direct reporter health state update
  devlink: Update reporter state to error even if recover aborted
  sctp: call iov_iter_revert() after sending ABORT
  team: Free BPF filter when unregistering netdev
  ip6mr: Do not call __IP6_INC_STATS() from preemptible context
  isdn: mISDN: Fix potential NULL pointer dereference of kzalloc
  net: dsa: mv88e6xxx: support in-band signalling on SGMII ports with external PHYs
  cxgb4/chtls: Prefix adapter flags with CXGB4
  net-sysfs: Switch to bitmap_zalloc()
  mellanox: Switch to bitmap_zalloc()
  bpf: add test cases for non-pointer sanitiation logic
  mlxsw: i2c: Extend initialization by querying resources data
  ...

1 files changed, 399 insertions, 106 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index d4e6fe5b9300..f2260391be5b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -40,15 +40,59 @@
 #include "en.h"
 #include "fs_core.h"
 #include "lib/devcom.h"
+#include "ecpf.h"
+#include "lib/eq.h"
 
 enum {
 	FDB_FAST_PATH = 0,
 	FDB_SLOW_PATH
 };
 
+/* There are two match-all miss flows, one for unicast dst mac and
+ * one for multicast.
+ */
+#define MLX5_ESW_MISS_FLOWS (2)
+
 #define fdb_prio_table(esw, chain, prio, level) \
 	(esw)->fdb_table.offloads.fdb_prio[(chain)][(prio)][(level)]
 
+#define UPLINK_REP_INDEX 0
+
+/* The rep getter/iterator are only valid after esw->total_vports
+ * and vport->vport are initialized in mlx5_eswitch_init.
+ */
+#define mlx5_esw_for_all_reps(esw, i, rep)			\
+	for ((i) = MLX5_VPORT_PF;				\
+	     (rep) = &(esw)->offloads.vport_reps[i],		\
+	     (i) < (esw)->total_vports; (i)++)
+
+#define mlx5_esw_for_each_vf_rep(esw, i, rep, nvfs)		\
+	for ((i) = MLX5_VPORT_FIRST_VF;				\
+	     (rep) = &(esw)->offloads.vport_reps[i],		\
+	     (i) <= (nvfs); (i)++)
+
+#define mlx5_esw_for_each_vf_rep_reverse(esw, i, rep, nvfs)	\
+	for ((i) = (nvfs);					\
+	     (rep) = &(esw)->offloads.vport_reps[i],		\
+	     (i) >= MLX5_VPORT_FIRST_VF; (i)--)
+
+#define mlx5_esw_for_each_vf_vport(esw, vport, nvfs)		\
+	for ((vport) = MLX5_VPORT_FIRST_VF;			\
+	     (vport) <= (nvfs); (vport)++)
+
+#define mlx5_esw_for_each_vf_vport_reverse(esw, vport, nvfs)	\
+	for ((vport) = (nvfs);					\
+	     (vport) >= MLX5_VPORT_FIRST_VF; (vport)--)
+
+static struct mlx5_eswitch_rep *mlx5_eswitch_get_rep(struct mlx5_eswitch *esw,
+						     u16 vport_num)
+{
+	u16 idx = mlx5_eswitch_vport_num_to_index(esw, vport_num);
+
+	WARN_ON(idx > esw->total_vports - 1);
+	return &esw->offloads.vport_reps[idx];
+}
+
 static struct mlx5_flow_table *
 esw_get_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level);
 static void
@@ -319,7 +363,7 @@ static int esw_set_global_vlan_pop(struct mlx5_eswitch *esw, u8 val)
 	esw_debug(esw->dev, "%s applying global %s policy\n", __func__, val ? "pop" : "none");
 	for (vf_vport = 1; vf_vport < esw->enabled_vports; vf_vport++) {
 		rep = &esw->offloads.vport_reps[vf_vport];
-		if (!rep->rep_if[REP_ETH].valid)
+		if (rep->rep_if[REP_ETH].state != REP_LOADED)
 			continue;
 
 		err = __mlx5_eswitch_set_vport_vlan(esw, rep->vport, 0, 0, val);
@@ -360,15 +404,15 @@ static int esw_add_vlan_action_check(struct mlx5_esw_flow_attr *attr,
 	in_rep  = attr->in_rep;
 	out_rep = attr->dests[0].rep;
 
-	if (push && in_rep->vport == FDB_UPLINK_VPORT)
+	if (push && in_rep->vport == MLX5_VPORT_UPLINK)
 		goto out_notsupp;
 
-	if (pop && out_rep->vport == FDB_UPLINK_VPORT)
+	if (pop && out_rep->vport == MLX5_VPORT_UPLINK)
 		goto out_notsupp;
 
 	/* vport has vlan push configured, can't offload VF --> wire rules w.o it */
 	if (!push && !pop && fwd)
-		if (in_rep->vlan && out_rep->vport == FDB_UPLINK_VPORT)
+		if (in_rep->vlan && out_rep->vport == MLX5_VPORT_UPLINK)
 			goto out_notsupp;
 
 	/* protects against (1) setting rules with different vlans to push and
@@ -410,7 +454,7 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
 
 	if (!push && !pop && fwd) {
 		/* tracks VF --> wire rules without vlan push action */
-		if (attr->dests[0].rep->vport == FDB_UPLINK_VPORT) {
+		if (attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) {
 			vport->vlan_refcount++;
 			attr->vlan_handled = true;
 		}
@@ -470,7 +514,7 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
 
 	if (!push && !pop && fwd) {
 		/* tracks VF --> wire rules without vlan push action */
-		if (attr->dests[0].rep->vport == FDB_UPLINK_VPORT)
+		if (attr->dests[0].rep->vport == MLX5_VPORT_UPLINK)
 			vport->vlan_refcount--;
 
 		return 0;
@@ -517,7 +561,8 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, u32 sqn
 
 	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
 	MLX5_SET(fte_match_set_misc, misc, source_sqn, sqn);
-	MLX5_SET(fte_match_set_misc, misc, source_port, 0x0); /* source vport is 0 */
+	/* source vport is the esw manager */
+	MLX5_SET(fte_match_set_misc, misc, source_port, esw->manager_vport);
 
 	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
 	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_sqn);
@@ -562,7 +607,7 @@ static void peer_miss_rules_setup(struct mlx5_core_dev *peer_dev,
 			 source_eswitch_owner_vhca_id);
 
 	dest->type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
-	dest->vport.num = 0;
+	dest->vport.num = peer_dev->priv.eswitch->manager_vport;
 	dest->vport.vhca_id = MLX5_CAP_GEN(peer_dev, vhca_id);
 	dest->vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
 }
@@ -596,14 +641,35 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
 			    misc_parameters);
 
-	for (i = 1; i < nvports; i++) {
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_PF);
+		flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
+					   spec, &flow_act, &dest, 1);
+		if (IS_ERR(flow)) {
+			err = PTR_ERR(flow);
+			goto add_pf_flow_err;
+		}
+		flows[MLX5_VPORT_PF] = flow;
+	}
+
+	if (mlx5_ecpf_vport_exists(esw->dev)) {
+		MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_ECPF);
+		flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
+					   spec, &flow_act, &dest, 1);
+		if (IS_ERR(flow)) {
+			err = PTR_ERR(flow);
+			goto add_ecpf_flow_err;
+		}
+		flows[mlx5_eswitch_ecpf_idx(esw)] = flow;
+	}
+
+	mlx5_esw_for_each_vf_vport(esw, i, mlx5_core_max_vfs(esw->dev)) {
 		MLX5_SET(fte_match_set_misc, misc, source_port, i);
 		flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
 					   spec, &flow_act, &dest, 1);
 		if (IS_ERR(flow)) {
 			err = PTR_ERR(flow);
-			esw_warn(esw->dev, "FDB: Failed to add peer miss flow rule err %d\n", err);
-			goto add_flow_err;
+			goto add_vf_flow_err;
 		}
 		flows[i] = flow;
 	}
@@ -613,9 +679,18 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 	kvfree(spec);
 	return 0;
 
-add_flow_err:
-	for (i--; i > 0; i--)
+add_vf_flow_err:
+	nvports = --i;
+	mlx5_esw_for_each_vf_vport_reverse(esw, i, nvports)
 		mlx5_del_flow_rules(flows[i]);
+
+	if (mlx5_ecpf_vport_exists(esw->dev))
+		mlx5_del_flow_rules(flows[mlx5_eswitch_ecpf_idx(esw)]);
+add_ecpf_flow_err:
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev))
+		mlx5_del_flow_rules(flows[MLX5_VPORT_PF]);
+add_pf_flow_err:
+	esw_warn(esw->dev, "FDB: Failed to add peer miss flow rule err %d\n", err);
 	kvfree(flows);
 alloc_flows_err:
 	kvfree(spec);
@@ -629,9 +704,15 @@ static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw)
 
 	flows = esw->fdb_table.offloads.peer_miss_rules;
 
-	for (i = 1; i < esw->total_vports; i++)
+	mlx5_esw_for_each_vf_vport_reverse(esw, i, mlx5_core_max_vfs(esw->dev))
 		mlx5_del_flow_rules(flows[i]);
 
+	if (mlx5_ecpf_vport_exists(esw->dev))
+		mlx5_del_flow_rules(flows[mlx5_eswitch_ecpf_idx(esw)]);
+
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev))
+		mlx5_del_flow_rules(flows[MLX5_VPORT_PF]);
+
 	kvfree(flows);
 }
 
@@ -661,7 +742,7 @@ static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw)
 	dmac_c[0] = 0x01;
 
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
-	dest.vport.num = 0;
+	dest.vport.num = esw->manager_vport;
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 
 	flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, spec,
@@ -905,8 +986,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 		esw->fdb_table.offloads.fdb_left[i] =
 			ESW_POOLS[i] <= fdb_max ? ESW_SIZE / ESW_POOLS[i] : 0;
 
-	table_size = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ + 2 +
-		esw->total_vports;
+	table_size = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ +
+		MLX5_ESW_MISS_FLOWS + esw->total_vports;
 
 	/* create the slow path fdb with encap set, so further table instances
 	 * can be created at run time while VFs are probed if the FW allows that.
@@ -1000,7 +1081,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 	dmac[0] = 0x01;
 
 	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
-	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ix + 2);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
+		 ix + MLX5_ESW_MISS_FLOWS);
 
 	g = mlx5_create_flow_group(fdb, flow_group_in);
 	if (IS_ERR(g)) {
@@ -1049,7 +1131,7 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw)
 	esw_destroy_offloads_fast_fdb_tables(esw);
 }
 
-static int esw_create_offloads_table(struct mlx5_eswitch *esw)
+static int esw_create_offloads_table(struct mlx5_eswitch *esw, int nvports)
 {
 	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_core_dev *dev = esw->dev;
@@ -1063,7 +1145,7 @@ static int esw_create_offloads_table(struct mlx5_eswitch *esw)
 		return -EOPNOTSUPP;
 	}
 
-	ft_attr.max_fte = dev->priv.sriov.num_vfs + 2;
+	ft_attr.max_fte = nvports + MLX5_ESW_MISS_FLOWS;
 
 	ft_offloads = mlx5_create_flow_table(ns, &ft_attr);
 	if (IS_ERR(ft_offloads)) {
@@ -1083,16 +1165,15 @@ static void esw_destroy_offloads_table(struct mlx5_eswitch *esw)
 	mlx5_destroy_flow_table(offloads->ft_offloads);
 }
 
-static int esw_create_vport_rx_group(struct mlx5_eswitch *esw)
+static int esw_create_vport_rx_group(struct mlx5_eswitch *esw, int nvports)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_flow_group *g;
-	struct mlx5_priv *priv = &esw->dev->priv;
 	u32 *flow_group_in;
 	void *match_criteria, *misc;
 	int err = 0;
-	int nvports = priv->sriov.num_vfs + 2;
 
+	nvports = nvports + MLX5_ESW_MISS_FLOWS;
 	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
 	if (!flow_group_in)
 		return -ENOMEM;
@@ -1169,7 +1250,8 @@ static int esw_offloads_start(struct mlx5_eswitch *esw,
 {
 	int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs;
 
-	if (esw->mode != SRIOV_LEGACY) {
+	if (esw->mode != SRIOV_LEGACY &&
+	    !mlx5_core_is_ecpf_esw_manager(esw->dev)) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Can't set offloads mode, SRIOV legacy not enabled");
 		return -EINVAL;
@@ -1207,9 +1289,8 @@ int esw_offloads_init_reps(struct mlx5_eswitch *esw)
 {
 	int total_vfs = MLX5_TOTAL_VPORTS(esw->dev);
 	struct mlx5_core_dev *dev = esw->dev;
-	struct mlx5_esw_offload *offloads;
 	struct mlx5_eswitch_rep *rep;
-	u8 hw_id[ETH_ALEN];
+	u8 hw_id[ETH_ALEN], rep_type;
 	int vport;
 
 	esw->offloads.vport_reps = kcalloc(total_vfs,
@@ -1218,75 +1299,203 @@ int esw_offloads_init_reps(struct mlx5_eswitch *esw)
 	if (!esw->offloads.vport_reps)
 		return -ENOMEM;
 
-	offloads = &esw->offloads;
 	mlx5_query_nic_vport_mac_address(dev, 0, hw_id);
 
-	for (vport = 0; vport < total_vfs; vport++) {
-		rep = &offloads->vport_reps[vport];
-
-		rep->vport = vport;
+	mlx5_esw_for_all_reps(esw, vport, rep) {
+		rep->vport = mlx5_eswitch_index_to_vport_num(esw, vport);
 		ether_addr_copy(rep->hw_id, hw_id);
-	}
 
-	offloads->vport_reps[0].vport = FDB_UPLINK_VPORT;
+		for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++)
+			rep->rep_if[rep_type].state = REP_UNREGISTERED;
+	}
 
 	return 0;
 }
 
-static void esw_offloads_unload_reps_type(struct mlx5_eswitch *esw, int nvports,
-					  u8 rep_type)
+static void __esw_offloads_unload_rep(struct mlx5_eswitch *esw,
+				      struct mlx5_eswitch_rep *rep, u8 rep_type)
+{
+	if (rep->rep_if[rep_type].state != REP_LOADED)
+		return;
+
+	rep->rep_if[rep_type].unload(rep);
+	rep->rep_if[rep_type].state = REP_REGISTERED;
+}
+
+static void __unload_reps_special_vport(struct mlx5_eswitch *esw, u8 rep_type)
 {
 	struct mlx5_eswitch_rep *rep;
-	int vport;
 
-	for (vport = nvports - 1; vport >= 0; vport--) {
-		rep = &esw->offloads.vport_reps[vport];
-		if (!rep->rep_if[rep_type].valid)
-			continue;
+	if (mlx5_ecpf_vport_exists(esw->dev)) {
+		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_ECPF);
+		__esw_offloads_unload_rep(esw, rep, rep_type);
+	}
 
-		rep->rep_if[rep_type].unload(rep);
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF);
+		__esw_offloads_unload_rep(esw, rep, rep_type);
 	}
+
+	rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
+	__esw_offloads_unload_rep(esw, rep, rep_type);
+}
+
+static void __unload_reps_vf_vport(struct mlx5_eswitch *esw, int nvports,
+				   u8 rep_type)
+{
+	struct mlx5_eswitch_rep *rep;
+	int i;
+
+	mlx5_esw_for_each_vf_rep_reverse(esw, i, rep, nvports)
+		__esw_offloads_unload_rep(esw, rep, rep_type);
 }
 
-static void esw_offloads_unload_reps(struct mlx5_eswitch *esw, int nvports)
+static void esw_offloads_unload_vf_reps(struct mlx5_eswitch *esw, int nvports)
 {
 	u8 rep_type = NUM_REP_TYPES;
 
 	while (rep_type-- > 0)
-		esw_offloads_unload_reps_type(esw, nvports, rep_type);
+		__unload_reps_vf_vport(esw, nvports, rep_type);
 }
 
-static int esw_offloads_load_reps_type(struct mlx5_eswitch *esw, int nvports,
-				       u8 rep_type)
+static void __unload_reps_all_vport(struct mlx5_eswitch *esw, int nvports,
+				    u8 rep_type)
+{
+	__unload_reps_vf_vport(esw, nvports, rep_type);
+
+	/* Special vports must be the last to unload. */
+	__unload_reps_special_vport(esw, rep_type);
+}
+
+static void esw_offloads_unload_all_reps(struct mlx5_eswitch *esw, int nvports)
+{
+	u8 rep_type = NUM_REP_TYPES;
+
+	while (rep_type-- > 0)
+		__unload_reps_all_vport(esw, nvports, rep_type);
+}
+
+static int __esw_offloads_load_rep(struct mlx5_eswitch *esw,
+				   struct mlx5_eswitch_rep *rep, u8 rep_type)
+{
+	int err = 0;
+
+	if (rep->rep_if[rep_type].state != REP_REGISTERED)
+		return 0;
+
+	err = rep->rep_if[rep_type].load(esw->dev, rep);
+	if (err)
+		return err;
+
+	rep->rep_if[rep_type].state = REP_LOADED;
+
+	return 0;
+}
+
+static int __load_reps_special_vport(struct mlx5_eswitch *esw, u8 rep_type)
 {
 	struct mlx5_eswitch_rep *rep;
-	int vport;
 	int err;
 
-	for (vport = 0; vport < nvports; vport++) {
-		rep = &esw->offloads.vport_reps[vport];
-		if (!rep->rep_if[rep_type].valid)
-			continue;
+	rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
+	err = __esw_offloads_load_rep(esw, rep, rep_type);
+	if (err)
+		return err;
 
-		err = rep->rep_if[rep_type].load(esw->dev, rep);
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF);
+		err = __esw_offloads_load_rep(esw, rep, rep_type);
 		if (err)
-			goto err_reps;
+			goto err_pf;
+	}
+
+	if (mlx5_ecpf_vport_exists(esw->dev)) {
+		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_ECPF);
+		err = __esw_offloads_load_rep(esw, rep, rep_type);
+		if (err)
+			goto err_ecpf;
 	}
 
 	return 0;
 
+err_ecpf:
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF);
+		__esw_offloads_unload_rep(esw, rep, rep_type);
+	}
+
+err_pf:
+	rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
+	__esw_offloads_unload_rep(esw, rep, rep_type);
+	return err;
+}
+
+static int __load_reps_vf_vport(struct mlx5_eswitch *esw, int nvports,
+				u8 rep_type)
+{
+	struct mlx5_eswitch_rep *rep;
+	int err, i;
+
+	mlx5_esw_for_each_vf_rep(esw, i, rep, nvports) {
+		err = __esw_offloads_load_rep(esw, rep, rep_type);
+		if (err)
+			goto err_vf;
+	}
+
+	return 0;
+
+err_vf:
+	__unload_reps_vf_vport(esw, --i, rep_type);
+	return err;
+}
+
+static int esw_offloads_load_vf_reps(struct mlx5_eswitch *esw, int nvports)
+{
+	u8 rep_type = 0;
+	int err;
+
+	for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) {
+		err = __load_reps_vf_vport(esw, nvports, rep_type);
+		if (err)
+			goto err_reps;
+	}
+
+	return err;
+
 err_reps:
-	esw_offloads_unload_reps_type(esw, vport, rep_type);
+	while (rep_type-- > 0)
+		__unload_reps_vf_vport(esw, nvports, rep_type);
 	return err;
 }
 
-static int esw_offloads_load_reps(struct mlx5_eswitch *esw, int nvports)
+static int __load_reps_all_vport(struct mlx5_eswitch *esw, int nvports,
+				 u8 rep_type)
+{
+	int err;
+
+	/* Special vports must be loaded first. */
+	err = __load_reps_special_vport(esw, rep_type);
+	if (err)
+		return err;
+
+	err = __load_reps_vf_vport(esw, nvports, rep_type);
+	if (err)
+		goto err_vfs;
+
+	return 0;
+
+err_vfs:
+	__unload_reps_special_vport(esw, rep_type);
+	return err;
+}
+
+static int esw_offloads_load_all_reps(struct mlx5_eswitch *esw, int nvports)
 {
 	u8 rep_type = 0;
 	int err;
 
 	for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) {
-		err = esw_offloads_load_reps_type(esw, nvports, rep_type);
+		err = __load_reps_all_vport(esw, nvports, rep_type);
 		if (err)
 			goto err_reps;
 	}
@@ -1295,7 +1504,7 @@ static int esw_offloads_load_reps(struct mlx5_eswitch *esw, int nvports)
 
 err_reps:
 	while (rep_type-- > 0)
-		esw_offloads_unload_reps_type(esw, nvports, rep_type);
+		__unload_reps_all_vport(esw, nvports, rep_type);
 	return err;
 }
 
@@ -1398,7 +1607,7 @@ static void esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw)
 	mlx5_devcom_unregister_component(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
 }
 
-int esw_offloads_init(struct mlx5_eswitch *esw, int nvports)
+static int esw_offloads_steering_init(struct mlx5_eswitch *esw, int nvports)
 {
 	int err;
 
@@ -1408,24 +1617,16 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int nvports)
 	if (err)
 		return err;
 
-	err = esw_create_offloads_table(esw);
+	err = esw_create_offloads_table(esw, nvports);
 	if (err)
 		goto create_ft_err;
 
-	err = esw_create_vport_rx_group(esw);
+	err = esw_create_vport_rx_group(esw, nvports);
 	if (err)
 		goto create_fg_err;
 
-	err = esw_offloads_load_reps(esw, nvports);
-	if (err)
-		goto err_reps;
-
-	esw_offloads_devcom_init(esw);
 	return 0;
 
-err_reps:
-	esw_destroy_vport_rx_group(esw);
-
 create_fg_err:
 	esw_destroy_offloads_table(esw);
 
@@ -1435,6 +1636,95 @@ create_ft_err:
 	return err;
 }
 
+static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw)
+{
+	esw_destroy_vport_rx_group(esw);
+	esw_destroy_offloads_table(esw);
+	esw_destroy_offloads_fdb_tables(esw);
+}
+
+static void esw_host_params_event_handler(struct work_struct *work)
+{
+	struct mlx5_host_work *host_work;
+	struct mlx5_eswitch *esw;
+	int err, num_vf = 0;
+
+	host_work = container_of(work, struct mlx5_host_work, work);
+	esw = host_work->esw;
+
+	err = mlx5_query_host_params_num_vfs(esw->dev, &num_vf);
+	if (err || num_vf == esw->host_info.num_vfs)
+		goto out;
+
+	/* Number of VFs can only change from "0 to x" or "x to 0". */
+	if (esw->host_info.num_vfs > 0) {
+		esw_offloads_unload_vf_reps(esw, esw->host_info.num_vfs);
+	} else {
+		err = esw_offloads_load_vf_reps(esw, num_vf);
+
+		if (err)
+			goto out;
+	}
+
+	esw->host_info.num_vfs = num_vf;
+
+out:
+	kfree(host_work);
+}
+
+static int esw_host_params_event(struct notifier_block *nb,
+				 unsigned long type, void *data)
+{
+	struct mlx5_host_work *host_work;
+	struct mlx5_host_info *host_info;
+	struct mlx5_eswitch *esw;
+
+	host_work = kzalloc(sizeof(*host_work), GFP_ATOMIC);
+	if (!host_work)
+		return NOTIFY_DONE;
+
+	host_info = mlx5_nb_cof(nb, struct mlx5_host_info, nb);
+	esw = container_of(host_info, struct mlx5_eswitch, host_info);
+
+	host_work->esw = esw;
+
+	INIT_WORK(&host_work->work, esw_host_params_event_handler);
+	queue_work(esw->work_queue, &host_work->work);
+
+	return NOTIFY_OK;
+}
+
+int esw_offloads_init(struct mlx5_eswitch *esw, int vf_nvports,
+		      int total_nvports)
+{
+	int err;
+
+	mutex_init(&esw->fdb_table.offloads.fdb_prio_lock);
+
+	err = esw_offloads_steering_init(esw, total_nvports);
+	if (err)
+		return err;
+
+	err = esw_offloads_load_all_reps(esw, vf_nvports);
+	if (err)
+		goto err_reps;
+
+	esw_offloads_devcom_init(esw);
+
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		MLX5_NB_INIT(&esw->host_info.nb, esw_host_params_event,
+			     HOST_PARAMS_CHANGE);
+		mlx5_eq_notifier_register(esw->dev, &esw->host_info.nb);
+		esw->host_info.num_vfs = vf_nvports;
+	}
+
+	return 0;
+
+err_reps:
+	esw_offloads_steering_cleanup(esw);
+	return err;
+}
+
 static int esw_offloads_stop(struct mlx5_eswitch *esw,
 			     struct netlink_ext_ack *extack)
 {
@@ -1454,13 +1744,21 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw,
 	return err;
 }
 
-void esw_offloads_cleanup(struct mlx5_eswitch *esw, int nvports)
+void esw_offloads_cleanup(struct mlx5_eswitch *esw)
 {
+	u16 num_vfs;
+
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		mlx5_eq_notifier_unregister(esw->dev, &esw->host_info.nb);
+		flush_workqueue(esw->work_queue);
+		num_vfs = esw->host_info.num_vfs;
+	} else {
+		num_vfs = esw->dev->priv.sriov.num_vfs;
+	}
+
 	esw_offloads_devcom_cleanup(esw);
-	esw_offloads_unload_reps(esw, nvports);
-	esw_destroy_vport_rx_group(esw);
-	esw_destroy_offloads_table(esw);
-	esw_destroy_offloads_fdb_tables(esw);
+	esw_offloads_unload_all_reps(esw, num_vfs);
+	esw_offloads_steering_cleanup(esw);
 }
 
 static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode)
@@ -1549,7 +1847,8 @@ static int mlx5_devlink_eswitch_check(struct devlink *devlink)
 	if(!MLX5_ESWITCH_MANAGER(dev))
 		return -EPERM;
 
-	if (dev->priv.eswitch->mode == SRIOV_NONE)
+	if (dev->priv.eswitch->mode == SRIOV_NONE &&
+	    !mlx5_core_is_ecpf_esw_manager(dev))
 		return -EOPNOTSUPP;
 
 	return 0;
@@ -1761,47 +2060,45 @@ int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, u8 *encap)
 	return 0;
 }
 
-void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw,
-				     int vport_index,
-				     struct mlx5_eswitch_rep_if *__rep_if,
-				     u8 rep_type)
+void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw,
+				      struct mlx5_eswitch_rep_if *__rep_if,
+				      u8 rep_type)
 {
-	struct mlx5_esw_offload *offloads = &esw->offloads;
 	struct mlx5_eswitch_rep_if *rep_if;
+	struct mlx5_eswitch_rep *rep;
+	int i;
 
-	rep_if = &offloads->vport_reps[vport_index].rep_if[rep_type];
-
-	rep_if->load   = __rep_if->load;
-	rep_if->unload = __rep_if->unload;
-	rep_if->get_proto_dev = __rep_if->get_proto_dev;
-	rep_if->priv = __rep_if->priv;
+	mlx5_esw_for_all_reps(esw, i, rep) {
+		rep_if = &rep->rep_if[rep_type];
+		rep_if->load   = __rep_if->load;
+		rep_if->unload = __rep_if->unload;
+		rep_if->get_proto_dev = __rep_if->get_proto_dev;
+		rep_if->priv = __rep_if->priv;
 
-	rep_if->valid = true;
+		rep_if->state = REP_REGISTERED;
+	}
 }
-EXPORT_SYMBOL(mlx5_eswitch_register_vport_rep);
+EXPORT_SYMBOL(mlx5_eswitch_register_vport_reps);
 
-void mlx5_eswitch_unregister_vport_rep(struct mlx5_eswitch *esw,
-				       int vport_index, u8 rep_type)
+void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type)
 {
-	struct mlx5_esw_offload *offloads = &esw->offloads;
+	u16 max_vf = mlx5_core_max_vfs(esw->dev);
 	struct mlx5_eswitch_rep *rep;
+	int i;
 
-	rep = &offloads->vport_reps[vport_index];
-
-	if (esw->mode == SRIOV_OFFLOADS && esw->vports[vport_index].enabled)
-		rep->rep_if[rep_type].unload(rep);
+	if (esw->mode == SRIOV_OFFLOADS)
+		__unload_reps_all_vport(esw, max_vf, rep_type);
 
-	rep->rep_if[rep_type].valid = false;
+	mlx5_esw_for_all_reps(esw, i, rep)
+		rep->rep_if[rep_type].state = REP_UNREGISTERED;
 }
-EXPORT_SYMBOL(mlx5_eswitch_unregister_vport_rep);
+EXPORT_SYMBOL(mlx5_eswitch_unregister_vport_reps);
 
 void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type)
 {
-#define UPLINK_REP_INDEX 0
-	struct mlx5_esw_offload *offloads = &esw->offloads;
 	struct mlx5_eswitch_rep *rep;
 
-	rep = &offloads->vport_reps[UPLINK_REP_INDEX];
+	rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
 	return rep->rep_if[rep_type].priv;
 }
 
@@ -1809,15 +2106,11 @@ void *mlx5_eswitch_get_proto_dev(struct mlx5_eswitch *esw,
 				 int vport,
 				 u8 rep_type)
 {
-	struct mlx5_esw_offload *offloads = &esw->offloads;
 	struct mlx5_eswitch_rep *rep;
 
-	if (vport == FDB_UPLINK_VPORT)
-		vport = UPLINK_REP_INDEX;
-
-	rep = &offloads->vport_reps[vport];
+	rep = mlx5_eswitch_get_rep(esw, vport);
 
-	if (rep->rep_if[rep_type].valid &&
+	if (rep->rep_if[rep_type].state == REP_LOADED &&
 	    rep->rep_if[rep_type].get_proto_dev)
 		return rep->rep_if[rep_type].get_proto_dev(rep);
 	return NULL;
@@ -1826,13 +2119,13 @@ EXPORT_SYMBOL(mlx5_eswitch_get_proto_dev);
 
 void *mlx5_eswitch_uplink_get_proto_dev(struct mlx5_eswitch *esw, u8 rep_type)
 {
-	return mlx5_eswitch_get_proto_dev(esw, UPLINK_REP_INDEX, rep_type);
+	return mlx5_eswitch_get_proto_dev(esw, MLX5_VPORT_UPLINK, rep_type);
 }
 EXPORT_SYMBOL(mlx5_eswitch_uplink_get_proto_dev);
 
 struct mlx5_eswitch_rep *mlx5_eswitch_vport_rep(struct mlx5_eswitch *esw,
 						int vport)
 {
-	return &esw->offloads.vport_reps[vport];
+	return mlx5_eswitch_get_rep(esw, vport);
 }
 EXPORT_SYMBOL(mlx5_eswitch_vport_rep);