Merge tag 'net-6.4-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Happy Wear a Dress Day.

  Fairly standard-sized batch of fixes, accounting for the lack of
  sub-tree submissions this week. The mlx5 IRQ fixes are notable, people
  were complaining about that. No fires burning.

  Current release - regressions:

   - eth: mlx5e:
      - multiple fixes for dynamic IRQ allocation
      - prevent encap offload when neigh update is running

   - eth: mana: fix perf regression: remove rx_cqes, tx_cqes counters

  Current release - new code bugs:

   - eth: mlx5e: DR, add missing mutex init/destroy in pattern manager

  Previous releases - always broken:

   - tcp: deny tcp_disconnect() when threads are waiting

   - sched: prevent ingress Qdiscs from getting installed in random
     locations in the hierarchy and moving around

   - sched: flower: fix possible OOB write in fl_set_geneve_opt()

   - netlink: fix NETLINK_LIST_MEMBERSHIPS length report

   - udp6: fix race condition in udp6_sendmsg & connect

   - tcp: fix mishandling when the sack compression is deferred

   - rtnetlink: validate link attributes set at creation time

   - mptcp: fix connect timeout handling

   - eth: stmmac: fix call trace when stmmac_xdp_xmit() is invoked

   - eth: amd-xgbe: fix the false linkup in xgbe_phy_status

   - eth: mlx5e:
      - fix corner cases in internal buffer configuration
      - drain health before unregistering devlink

   - usb: qmi_wwan: set DTR quirk for BroadMobi BM818

  Misc:

   - tcp: return user_mss for TCP_MAXSEG in CLOSE/LISTEN state if
     user_mss set"

* tag 'net-6.4-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (71 commits)
  mptcp: fix active subflow finalization
  mptcp: add annotations around sk->sk_shutdown accesses
  mptcp: fix data race around msk->first access
  mptcp: consolidate passive msk socket initialization
  mptcp: add annotations around msk->subflow accesses
  mptcp: fix connect timeout handling
  rtnetlink: add the missing IFLA_GRO_ tb check in validate_linkmsg
  rtnetlink: move IFLA_GSO_ tb check to validate_linkmsg
  rtnetlink: call validate_linkmsg in rtnl_create_link
  ice: recycle/free all of the fragments from multi-buffer frame
  net: phy: mxl-gpy: extend interrupt fix to all impacted variants
  net: renesas: rswitch: Fix return value in error path of xmit
  net: dsa: mv88e6xxx: Increase wait after reset deactivation
  net: ipa: Use correct value for IPA_STATUS_SIZE
  tcp: fix mishandling when the sack compression is deferred.
  net/sched: flower: fix possible OOB write in fl_set_geneve_opt()
  sfc: fix error unwinds in TC offload
  net/mlx5: Read embedded cpu after init bit cleared
  net/mlx5e: Fix error handling in mlx5e_refresh_tirs
  net/mlx5: Ensure af_desc.mask is properly initialized
  ...

33 files changed, 296 insertions, 241 deletions

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 64a2f2f83735..08a46ffd53af 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -7170,7 +7170,7 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
 		goto out;
 	}
 	if (chip->reset)
-		usleep_range(1000, 2000);
+		usleep_range(10000, 20000);
 
 	/* Detect if the device is configured in single chip addressing mode,
 	 * otherwise continue with address specific smi init/detection.
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 33a9574e9e04..32d2c6fac652 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -1329,7 +1329,7 @@ static enum xgbe_mode xgbe_phy_status_aneg(struct xgbe_prv_data *pdata)
 	return pdata->phy_if.phy_impl.an_outcome(pdata);
 }
 
-static void xgbe_phy_status_result(struct xgbe_prv_data *pdata)
+static bool xgbe_phy_status_result(struct xgbe_prv_data *pdata)
 {
 	struct ethtool_link_ksettings *lks = &pdata->phy.lks;
 	enum xgbe_mode mode;
@@ -1367,8 +1367,13 @@ static void xgbe_phy_status_result(struct xgbe_prv_data *pdata)
 
 	pdata->phy.duplex = DUPLEX_FULL;
 
-	if (xgbe_set_mode(pdata, mode) && pdata->an_again)
+	if (!xgbe_set_mode(pdata, mode))
+		return false;
+
+	if (pdata->an_again)
 		xgbe_phy_reconfig_aneg(pdata);
+
+	return true;
 }
 
 static void xgbe_phy_status(struct xgbe_prv_data *pdata)
@@ -1398,7 +1403,8 @@ static void xgbe_phy_status(struct xgbe_prv_data *pdata)
 			return;
 		}
 
-		xgbe_phy_status_result(pdata);
+		if (xgbe_phy_status_result(pdata))
+			return;
 
 		if (test_bit(XGBE_LINK_INIT, &pdata->dev_state))
 			clear_bit(XGBE_LINK_INIT, &pdata->dev_state);
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 059bd911c51d..52d0a126eb61 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1152,11 +1152,11 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 	unsigned int total_rx_bytes = 0, total_rx_pkts = 0;
 	unsigned int offset = rx_ring->rx_offset;
 	struct xdp_buff *xdp = &rx_ring->xdp;
+	u32 cached_ntc = rx_ring->first_desc;
 	struct ice_tx_ring *xdp_ring = NULL;
 	struct bpf_prog *xdp_prog = NULL;
 	u32 ntc = rx_ring->next_to_clean;
 	u32 cnt = rx_ring->count;
-	u32 cached_ntc = ntc;
 	u32 xdp_xmit = 0;
 	u32 cached_ntu;
 	bool failure;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index f40497823e65..7c0f2adbea00 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -490,7 +490,7 @@ static void poll_trace(struct mlx5_fw_tracer *tracer,
 				(u64)timestamp_low;
 		break;
 	default:
-		if (tracer_event->event_id >= tracer->str_db.first_string_trace ||
+		if (tracer_event->event_id >= tracer->str_db.first_string_trace &&
 		    tracer_event->event_id <= tracer->str_db.first_string_trace +
 					      tracer->str_db.num_string_trace) {
 			tracer_event->type = TRACER_EVENT_TYPE_STRING;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index b8987a404d75..8e999f238194 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -327,6 +327,7 @@ struct mlx5e_params {
 	unsigned int sw_mtu;
 	int hard_mtu;
 	bool ptp_rx;
+	__be32 terminate_lkey_be;
 };
 
 static inline u8 mlx5e_get_dcb_num_tc(struct mlx5e_params *params)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
index 7ac1ad9c46de..7e8e96cc5cd0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
@@ -51,7 +51,7 @@ int mlx5e_port_query_buffer(struct mlx5e_priv *priv,
 	if (err)
 		goto out;
 
-	for (i = 0; i < MLX5E_MAX_BUFFER; i++) {
+	for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) {
 		buffer = MLX5_ADDR_OF(pbmc_reg, out, buffer[i]);
 		port_buffer->buffer[i].lossy =
 			MLX5_GET(bufferx_reg, buffer, lossy);
@@ -73,14 +73,24 @@ int mlx5e_port_query_buffer(struct mlx5e_priv *priv,
 			  port_buffer->buffer[i].lossy);
 	}
 
-	port_buffer->headroom_size = total_used;
+	port_buffer->internal_buffers_size = 0;
+	for (i = MLX5E_MAX_NETWORK_BUFFER; i < MLX5E_TOTAL_BUFFERS; i++) {
+		buffer = MLX5_ADDR_OF(pbmc_reg, out, buffer[i]);
+		port_buffer->internal_buffers_size +=
+			MLX5_GET(bufferx_reg, buffer, size) * port_buff_cell_sz;
+	}
+
 	port_buffer->port_buffer_size =
 		MLX5_GET(pbmc_reg, out, port_buffer_size) * port_buff_cell_sz;
-	port_buffer->spare_buffer_size =
-		port_buffer->port_buffer_size - total_used;
-
-	mlx5e_dbg(HW, priv, "total buffer size=%d, spare buffer size=%d\n",
-		  port_buffer->port_buffer_size,
+	port_buffer->headroom_size = total_used;
+	port_buffer->spare_buffer_size = port_buffer->port_buffer_size -
+					 port_buffer->internal_buffers_size -
+					 port_buffer->headroom_size;
+
+	mlx5e_dbg(HW, priv,
+		  "total buffer size=%u, headroom buffer size=%u, internal buffers size=%u, spare buffer size=%u\n",
+		  port_buffer->port_buffer_size, port_buffer->headroom_size,
+		  port_buffer->internal_buffers_size,
 		  port_buffer->spare_buffer_size);
 out:
 	kfree(out);
@@ -206,11 +216,11 @@ static int port_update_pool_cfg(struct mlx5_core_dev *mdev,
 	if (!MLX5_CAP_GEN(mdev, sbcam_reg))
 		return 0;
 
-	for (i = 0; i < MLX5E_MAX_BUFFER; i++)
+	for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++)
 		lossless_buff_count += ((port_buffer->buffer[i].size) &&
 				       (!(port_buffer->buffer[i].lossy)));
 
-	for (i = 0; i < MLX5E_MAX_BUFFER; i++) {
+	for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) {
 		p = select_sbcm_params(&port_buffer->buffer[i], lossless_buff_count);
 		err = mlx5e_port_set_sbcm(mdev, 0, i,
 					  MLX5_INGRESS_DIR,
@@ -293,7 +303,7 @@ static int port_set_buffer(struct mlx5e_priv *priv,
 	if (err)
 		goto out;
 
-	for (i = 0; i < MLX5E_MAX_BUFFER; i++) {
+	for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) {
 		void *buffer = MLX5_ADDR_OF(pbmc_reg, in, buffer[i]);
 		u64 size = port_buffer->buffer[i].size;
 		u64 xoff = port_buffer->buffer[i].xoff;
@@ -351,7 +361,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
 {
 	int i;
 
-	for (i = 0; i < MLX5E_MAX_BUFFER; i++) {
+	for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) {
 		if (port_buffer->buffer[i].lossy) {
 			port_buffer->buffer[i].xoff = 0;
 			port_buffer->buffer[i].xon  = 0;
@@ -408,7 +418,7 @@ static int update_buffer_lossy(struct mlx5_core_dev *mdev,
 	int err;
 	int i;
 
-	for (i = 0; i < MLX5E_MAX_BUFFER; i++) {
+	for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) {
 		prio_count = 0;
 		lossy_count = 0;
 
@@ -432,11 +442,11 @@ static int update_buffer_lossy(struct mlx5_core_dev *mdev,
 	}
 
 	if (changed) {
-		err = port_update_pool_cfg(mdev, port_buffer);
+		err = update_xoff_threshold(port_buffer, xoff, max_mtu, port_buff_cell_sz);
 		if (err)
 			return err;
 
-		err = update_xoff_threshold(port_buffer, xoff, max_mtu, port_buff_cell_sz);
+		err = port_update_pool_cfg(mdev, port_buffer);
 		if (err)
 			return err;
 
@@ -515,7 +525,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 
 	if (change & MLX5E_PORT_BUFFER_PRIO2BUFFER) {
 		update_prio2buffer = true;
-		for (i = 0; i < MLX5E_MAX_BUFFER; i++)
+		for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++)
 			mlx5e_dbg(HW, priv, "%s: requested to map prio[%d] to buffer %d\n",
 				  __func__, i, prio2buffer[i]);
 
@@ -530,7 +540,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 	}
 
 	if (change & MLX5E_PORT_BUFFER_SIZE) {
-		for (i = 0; i < MLX5E_MAX_BUFFER; i++) {
+		for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) {
 			mlx5e_dbg(HW, priv, "%s: buffer[%d]=%d\n", __func__, i, buffer_size[i]);
 			if (!port_buffer.buffer[i].lossy && !buffer_size[i]) {
 				mlx5e_dbg(HW, priv, "%s: lossless buffer[%d] size cannot be zero\n",
@@ -544,7 +554,9 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 
 		mlx5e_dbg(HW, priv, "%s: total buffer requested=%d\n", __func__, total_used);
 
-		if (total_used > port_buffer.port_buffer_size)
+		if (total_used > port_buffer.headroom_size &&
+		    (total_used - port_buffer.headroom_size) >
+			    port_buffer.spare_buffer_size)
 			return -EINVAL;
 
 		update_buffer = true;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h
index a6ef118de758..f4a19ffbb641 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h
@@ -35,7 +35,8 @@
 #include "en.h"
 #include "port.h"
 
-#define MLX5E_MAX_BUFFER 8
+#define MLX5E_MAX_NETWORK_BUFFER 8
+#define MLX5E_TOTAL_BUFFERS 10
 #define MLX5E_DEFAULT_CABLE_LEN 7 /* 7 meters */
 
 #define MLX5_BUFFER_SUPPORTED(mdev) (MLX5_CAP_GEN(mdev, pcam_reg) && \
@@ -60,8 +61,9 @@ struct mlx5e_bufferx_reg {
 struct mlx5e_port_buffer {
 	u32                       port_buffer_size;
 	u32                       spare_buffer_size;
-	u32                       headroom_size;
-	struct mlx5e_bufferx_reg  buffer[MLX5E_MAX_BUFFER];
+	u32                       headroom_size;	  /* Buffers 0-7 */
+	u32                       internal_buffers_size;  /* Buffers 8-9 */
+	struct mlx5e_bufferx_reg  buffer[MLX5E_MAX_NETWORK_BUFFER];
 };
 
 int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c
index fc923a99b6a4..0380a04c3691 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c
@@ -84,7 +84,7 @@ mlx5e_tc_act_init_parse_state(struct mlx5e_tc_act_parse_state *parse_state,
 
 int
 mlx5e_tc_act_post_parse(struct mlx5e_tc_act_parse_state *parse_state,
-			struct flow_action *flow_action,
+			struct flow_action *flow_action, int from, int to,
 			struct mlx5_flow_attr *attr,
 			enum mlx5_flow_namespace_type ns_type)
 {
@@ -96,6 +96,11 @@ mlx5e_tc_act_post_parse(struct mlx5e_tc_act_parse_state *parse_state,
 	priv = parse_state->flow->priv;
 
 	flow_action_for_each(i, act, flow_action) {
+		if (i < from)
+			continue;
+		else if (i > to)
+			break;
+
 		tc_act = mlx5e_tc_act_get(act->id, ns_type);
 		if (!tc_act || !tc_act->post_parse)
 			continue;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h
index 0e6e1872ac62..d6c12d0ea55b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h
@@ -112,7 +112,7 @@ mlx5e_tc_act_init_parse_state(struct mlx5e_tc_act_parse_state *parse_state,
 
 int
 mlx5e_tc_act_post_parse(struct mlx5e_tc_act_parse_state *parse_state,
-			struct flow_action *flow_action,
+			struct flow_action *flow_action, int from, int to,
 			struct mlx5_flow_attr *attr,
 			enum mlx5_flow_namespace_type ns_type);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
index 6a052c6cfc15..f0c3464f037f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
@@ -492,6 +492,19 @@ void mlx5e_encap_put(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e)
 	mlx5e_encap_dealloc(priv, e);
 }
 
+static void mlx5e_encap_put_locked(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e)
+{
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+
+	lockdep_assert_held(&esw->offloads.encap_tbl_lock);
+
+	if (!refcount_dec_and_test(&e->refcnt))
+		return;
+	list_del(&e->route_list);
+	hash_del_rcu(&e->encap_hlist);
+	mlx5e_encap_dealloc(priv, e);
+}
+
 static void mlx5e_decap_put(struct mlx5e_priv *priv, struct mlx5e_decap_entry *d)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
@@ -816,6 +829,8 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv,
 	uintptr_t hash_key;
 	int err = 0;
 
+	lockdep_assert_held(&esw->offloads.encap_tbl_lock);
+
 	parse_attr = attr->parse_attr;
 	tun_info = parse_attr->tun_info[out_index];
 	mpls_info = &parse_attr->mpls_info[out_index];
@@ -829,7 +844,6 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv,
 
 	hash_key = hash_encap_info(&key);
 
-	mutex_lock(&esw->offloads.encap_tbl_lock);
 	e = mlx5e_encap_get(priv, &key, hash_key);
 
 	/* must verify if encap is valid or not */
@@ -840,15 +854,6 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv,
 			goto out_err;
 		}
 
-		mutex_unlock(&esw->offloads.encap_tbl_lock);
-		wait_for_completion(&e->res_ready);
-
-		/* Protect against concurrent neigh update. */
-		mutex_lock(&esw->offloads.encap_tbl_lock);
-		if (e->compl_result < 0) {
-			err = -EREMOTEIO;
-			goto out_err;
-		}
 		goto attach_flow;
 	}
 
@@ -877,15 +882,12 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv,
 	INIT_LIST_HEAD(&e->flows);
 	hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key);
 	tbl_time_before = mlx5e_route_tbl_get_last_update(priv);
-	mutex_unlock(&esw->offloads.encap_tbl_lock);
 
 	if (family == AF_INET)
 		err = mlx5e_tc_tun_create_header_ipv4(priv, mirred_dev, e);
 	else if (family == AF_INET6)
 		err = mlx5e_tc_tun_create_header_ipv6(priv, mirred_dev, e);
 
-	/* Protect against concurrent neigh update. */
-	mutex_lock(&esw->offloads.encap_tbl_lock);
 	complete_all(&e->res_ready);
 	if (err) {
 		e->compl_result = err;
@@ -920,18 +922,15 @@ attach_flow:
 	} else {
 		flow_flag_set(flow, SLOW);
 	}
-	mutex_unlock(&esw->offloads.encap_tbl_lock);
 
 	return err;
 
 out_err:
-	mutex_unlock(&esw->offloads.encap_tbl_lock);
 	if (e)
-		mlx5e_encap_put(priv, e);
+		mlx5e_encap_put_locked(priv, e);
 	return err;
 
 out_err_init:
-	mutex_unlock(&esw->offloads.encap_tbl_lock);
 	kfree(tun_info);
 	kfree(e);
 	return err;
@@ -1016,6 +1015,93 @@ out_err:
 	return err;
 }
 
+int mlx5e_tc_tun_encap_dests_set(struct mlx5e_priv *priv,
+				 struct mlx5e_tc_flow *flow,
+				 struct mlx5_flow_attr *attr,
+				 struct netlink_ext_ack *extack,
+				 bool *vf_tun)
+{
+	struct mlx5e_tc_flow_parse_attr *parse_attr;
+	struct mlx5_esw_flow_attr *esw_attr;
+	struct net_device *encap_dev = NULL;
+	struct mlx5e_rep_priv *rpriv;
+	struct mlx5e_priv *out_priv;
+	struct mlx5_eswitch *esw;
+	int out_index;
+	int err = 0;
+
+	if (!mlx5e_is_eswitch_flow(flow))
+		return 0;
+
+	parse_attr = attr->parse_attr;
+	esw_attr = attr->esw_attr;
+	*vf_tun = false;
+
+	esw = priv->mdev->priv.eswitch;
+	mutex_lock(&esw->offloads.encap_tbl_lock);
+	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) {
+		struct net_device *out_dev;
+		int mirred_ifindex;
+
+		if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP))
+			continue;
+
+		mirred_ifindex = parse_attr->mirred_ifindex[out_index];
+		out_dev = dev_get_by_index(dev_net(priv->netdev), mirred_ifindex);
+		if (!out_dev) {
+			NL_SET_ERR_MSG_MOD(extack, "Requested mirred device not found");
+			err = -ENODEV;
+			goto out;
+		}
+		err = mlx5e_attach_encap(priv, flow, attr, out_dev, out_index,
+					 extack, &encap_dev);
+		dev_put(out_dev);
+		if (err)
+			goto out;
+
+		if (esw_attr->dests[out_index].flags &
+		    MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE &&
+		    !esw_attr->dest_int_port)
+			*vf_tun = true;
+
+		out_priv = netdev_priv(encap_dev);
+		rpriv = out_priv->ppriv;
+		esw_attr->dests[out_index].rep = rpriv->rep;
+		esw_attr->dests[out_index].mdev = out_priv->mdev;
+	}
+
+	if (*vf_tun && esw_attr->out_count > 1) {
+		NL_SET_ERR_MSG_MOD(extack, "VF tunnel encap with mirroring is not supported");
+		err = -EOPNOTSUPP;
+		goto out;
+	}
+
+out:
+	mutex_unlock(&esw->offloads.encap_tbl_lock);
+	return err;
+}
+
+void mlx5e_tc_tun_encap_dests_unset(struct mlx5e_priv *priv,
+				    struct mlx5e_tc_flow *flow,
+				    struct mlx5_flow_attr *attr)
+{
+	struct mlx5_esw_flow_attr *esw_attr;
+	int out_index;
+
+	if (!mlx5e_is_eswitch_flow(flow))
+		return;
+
+	esw_attr = attr->esw_attr;
+
+	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) {
+		if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP))
+			continue;
+
+		mlx5e_detach_encap(flow->priv, flow, attr, out_index);
+		kfree(attr->parse_attr->tun_info[out_index]);
+	}
+}
+
 static int cmp_route_info(struct mlx5e_route_key *a,
 			  struct mlx5e_route_key *b)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h
index 8ad273dde40e..5d7d67687cbc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h
@@ -30,6 +30,15 @@ int mlx5e_attach_decap_route(struct mlx5e_priv *priv,
 void mlx5e_detach_decap_route(struct mlx5e_priv *priv,
 			      struct mlx5e_tc_flow *flow);
 
+int mlx5e_tc_tun_encap_dests_set(struct mlx5e_priv *priv,
+				 struct mlx5e_tc_flow *flow,
+				 struct mlx5_flow_attr *attr,
+				 struct netlink_ext_ack *extack,
+				 bool *vf_tun);
+void mlx5e_tc_tun_encap_dests_unset(struct mlx5e_priv *priv,
+				    struct mlx5e_tc_flow *flow,
+				    struct mlx5_flow_attr *attr);
+
 struct ip_tunnel_info *mlx5e_dup_tun_info(const struct ip_tunnel_info *tun_info);
 
 int mlx5e_tc_set_attr_rx_tun(struct mlx5e_tc_flow *flow,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index 1f90594499c6..41c396e76457 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -150,10 +150,8 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb,
 
 	inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
 	in = kvzalloc(inlen, GFP_KERNEL);
-	if (!in) {
-		err = -ENOMEM;
-		goto out;
-	}
+	if (!in)
+		return -ENOMEM;
 
 	if (enable_uc_lb)
 		lb_flags = MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST;
@@ -171,14 +169,13 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb,
 		tirn = tir->tirn;
 		err = mlx5_core_modify_tir(mdev, tirn, in);
 		if (err)
-			goto out;
+			break;
 	}
+	mutex_unlock(&mdev->mlx5e_res.hw_objs.td.list_lock);
 
-out:
 	kvfree(in);
 	if (err)
 		netdev_err(priv->netdev, "refresh tir(0x%x) failed, %d\n", tirn, err);
-	mutex_unlock(&mdev->mlx5e_res.hw_objs.td.list_lock);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 89de92d06483..ebee52a8361a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -926,9 +926,10 @@ static int mlx5e_dcbnl_getbuffer(struct net_device *dev,
 	if (err)
 		return err;
 
-	for (i = 0; i < MLX5E_MAX_BUFFER; i++)
+	for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++)
 		dcb_buffer->buffer_size[i] = port_buffer.buffer[i].size;
-	dcb_buffer->total_size = port_buffer.port_buffer_size;
+	dcb_buffer->total_size = port_buffer.port_buffer_size -
+				 port_buffer.internal_buffers_size;
 
 	return 0;
 }
@@ -970,7 +971,7 @@ static int mlx5e_dcbnl_setbuffer(struct net_device *dev,
 	if (err)
 		return err;
 
-	for (i = 0; i < MLX5E_MAX_BUFFER; i++) {
+	for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) {
 		if (port_buffer.buffer[i].size != dcb_buffer->buffer_size[i]) {
 			changed |= MLX5E_PORT_BUFFER_SIZE;
 			buffer_size = dcb_buffer->buffer_size;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 2944691f06ad..a7c526ee5024 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -727,26 +727,6 @@ static void mlx5e_rq_free_shampo(struct mlx5e_rq *rq)
 	mlx5e_rq_shampo_hd_free(rq);
 }
 
-static __be32 mlx5e_get_terminate_scatter_list_mkey(struct mlx5_core_dev *dev)
-{
-	u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {};
-	u32 in[MLX5_ST_SZ_DW(query_special_contexts_in)] = {};
-	int res;
-
-	if (!MLX5_CAP_GEN(dev, terminate_scatter_list_mkey))
-		return MLX5_TERMINATE_SCATTER_LIST_LKEY;
-
-	MLX5_SET(query_special_contexts_in, in, opcode,
-		 MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS);
-	res = mlx5_cmd_exec_inout(dev, query_special_contexts, in, out);
-	if (res)
-		return MLX5_TERMINATE_SCATTER_LIST_LKEY;
-
-	res = MLX5_GET(query_special_contexts_out, out,
-		       terminate_scatter_list_mkey);
-	return cpu_to_be32(res);
-}
-
 static int mlx5e_alloc_rq(struct mlx5e_params *params,
 			  struct mlx5e_xsk_param *xsk,
 			  struct mlx5e_rq_param *rqp,
@@ -908,7 +888,7 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params,
 			/* check if num_frags is not a pow of two */
 			if (rq->wqe.info.num_frags < (1 << rq->wqe.info.log_num_frags)) {
 				wqe->data[f].byte_count = 0;
-				wqe->data[f].lkey = mlx5e_get_terminate_scatter_list_mkey(mdev);
+				wqe->data[f].lkey = params->terminate_lkey_be;
 				wqe->data[f].addr = 0;
 			}
 		}
@@ -5007,6 +4987,8 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16
 	/* RQ */
 	mlx5e_build_rq_params(mdev, params);
 
+	params->terminate_lkey_be = mlx5_core_get_terminate_scatter_list_mkey(mdev);
+
 	params->packet_merge.timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
 
 	/* CQ moderation params */
@@ -5279,12 +5261,16 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
 
 	mlx5e_timestamp_init(priv);
 
+	priv->dfs_root = debugfs_create_dir("nic",
+					    mlx5_debugfs_get_dev_root(mdev));
+
 	fs = mlx5e_fs_init(priv->profile, mdev,
 			   !test_bit(MLX5E_STATE_DESTROYING, &priv->state),
 			   priv->dfs_root);
 	if (!fs) {
 		err = -ENOMEM;
 		mlx5_core_err(mdev, "FS initialization failed, %d\n", err);
+		debugfs_remove_recursive(priv->dfs_root);
 		return err;
 	}
 	priv->fs = fs;
@@ -5305,6 +5291,7 @@ static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
 	mlx5e_health_destroy_reporters(priv);
 	mlx5e_ktls_cleanup(priv);
 	mlx5e_fs_cleanup(priv->fs);
+	debugfs_remove_recursive(priv->dfs_root);
 	priv->fs = NULL;
 }
 
@@ -5851,8 +5838,8 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv)
 }
 
 static int
-mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mdev,
-			    const struct mlx5e_profile *new_profile, void *new_ppriv)
+mlx5e_netdev_init_profile(struct net_device *netdev, struct mlx5_core_dev *mdev,
+			  const struct mlx5e_profile *new_profile, void *new_ppriv)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	int err;
@@ -5868,6 +5855,25 @@ mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mde
 	err = new_profile->init(priv->mdev, priv->netdev);
 	if (err)
 		goto priv_cleanup;
+
+	return 0;
+
+priv_cleanup:
+	mlx5e_priv_cleanup(priv);
+	return err;
+}
+
+static int
+mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mdev,
+			    const struct mlx5e_profile *new_profile, void *new_ppriv)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	int err;
+
+	err = mlx5e_netdev_init_profile(netdev, mdev, new_profile, new_ppriv);
+	if (err)
+		return err;
+
 	err = mlx5e_attach_netdev(priv);
 	if (err)
 		goto profile_cleanup;
@@ -5875,7 +5881,6 @@ mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mde
 
 profile_cleanup:
 	new_profile->cleanup(priv);
-priv_cleanup:
 	mlx5e_priv_cleanup(priv);
 	return err;
 }
@@ -5894,6 +5899,12 @@ int mlx5e_netdev_change_profile(struct mlx5e_priv *priv,
 	priv->profile->cleanup(priv);
 	mlx5e_priv_cleanup(priv);
 
+	if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
+		mlx5e_netdev_init_profile(netdev, mdev, new_profile, new_ppriv);
+		set_bit(MLX5E_STATE_DESTROYING, &priv->state);
+		return -EIO;
+	}
+
 	err = mlx5e_netdev_attach_profile(netdev, mdev, new_profile, new_ppriv);
 	if (err) { /* roll back to original profile */
 		netdev_warn(netdev, "%s: new profile init failed, %d\n", __func__, err);
@@ -5955,8 +5966,11 @@ static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state)
 	struct net_device *netdev = priv->netdev;
 	struct mlx5_core_dev *mdev = priv->mdev;
 
-	if (!netif_device_present(netdev))
+	if (!netif_device_present(netdev)) {
+		if (test_bit(MLX5E_STATE_DESTROYING, &priv->state))
+			mlx5e_destroy_mdev_resources(mdev);
 		return -ENODEV;
+	}
 
 	mlx5e_detach_netdev(priv);
 	mlx5e_destroy_mdev_resources(mdev);
@@ -6002,9 +6016,6 @@ static int mlx5e_probe(struct auxiliary_device *adev,
 	priv->profile = profile;
 	priv->ppriv = NULL;
 
-	priv->dfs_root = debugfs_create_dir("nic",
-					    mlx5_debugfs_get_dev_root(priv->mdev));
-
 	err = profile->init(mdev, netdev);
 	if (err) {
 		mlx5_core_err(mdev, "mlx5e_nic_profile init failed, %d\n", err);
@@ -6033,7 +6044,6 @@ err_resume:
 err_profile_cleanup:
 	profile->cleanup(priv);
 err_destroy_netdev:
-	debugfs_remove_recursive(priv->dfs_root);
 	mlx5e_destroy_netdev(priv);
 err_devlink_port_unregister:
 	mlx5e_devlink_port_unregister(mlx5e_dev);
@@ -6053,7 +6063,6 @@ static void mlx5e_remove(struct auxiliary_device *adev)
 	unregister_netdev(priv->netdev);
 	mlx5e_suspend(adev, state);
 	priv->profile->cleanup(priv);
-	debugfs_remove_recursive(priv->dfs_root);
 	mlx5e_destroy_netdev(priv);
 	mlx5e_devlink_port_unregister(mlx5e_dev);
 	mlx5e_destroy_devlink(mlx5e_dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 1fc386eccaf8..3e7041bd5705 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -30,6 +30,7 @@
  * SOFTWARE.
  */
 
+#include <linux/debugfs.h>
 #include <linux/mlx5/fs.h>
 #include <net/switchdev.h>
 #include <net/pkt_cls.h>
@@ -812,11 +813,15 @@ static int mlx5e_init_ul_rep(struct mlx5_core_dev *mdev,
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
+	priv->dfs_root = debugfs_create_dir("nic",
+					    mlx5_debugfs_get_dev_root(mdev));
+
 	priv->fs = mlx5e_fs_init(priv->profile, mdev,
 				 !test_bit(MLX5E_STATE_DESTROYING, &priv->state),
 				 priv->dfs_root);
 	if (!priv->fs) {
 		netdev_err(priv->netdev, "FS allocation failed\n");
+		debugfs_remove_recursive(priv->dfs_root);
 		return -ENOMEM;
 	}
 
@@ -829,6 +834,7 @@ static int mlx5e_init_ul_rep(struct mlx5_core_dev *mdev,
 static void mlx5e_cleanup_rep(struct mlx5e_priv *priv)
 {
 	mlx5e_fs_cleanup(priv->fs);
+	debugfs_remove_recursive(priv->dfs_root);
 	priv->fs = NULL;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index e95414ef1f04..8a5a8703f0a3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1700,91 +1700,6 @@ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *ro
 }
 
 static int
-set_encap_dests(struct mlx5e_priv *priv,
-		struct mlx5e_tc_flow *flow,
-		struct mlx5_flow_attr *attr,
-		struct netlink_ext_ack *extack,
-		bool *vf_tun)
-{
-	struct mlx5e_tc_flow_parse_attr *parse_attr;
-	struct mlx5_esw_flow_attr *esw_attr;
-	struct net_device *encap_dev = NULL;
-	struct mlx5e_rep_priv *rpriv;
-	struct mlx5e_priv *out_priv;
-	int out_index;
-	int err = 0;
-
-	if (!mlx5e_is_eswitch_flow(flow))
-		return 0;
-
-	parse_attr = attr->parse_attr;
-	esw_attr = attr->esw_attr;
-	*vf_tun = false;
-
-	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) {
-		struct net_device *out_dev;
-		int mirred_ifindex;
-
-		if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP))
-			continue;
-
-		mirred_ifindex = parse_attr->mirred_ifindex[out_index];
-		out_dev = dev_get_by_index(dev_net(priv->netdev), mirred_ifindex);
-		if (!out_dev) {
-			NL_SET_ERR_MSG_MOD(extack, "Requested mirred device not found");
-			err = -ENODEV;
-			goto out;
-		}
-		err = mlx5e_attach_encap(priv, flow, attr, out_dev, out_index,
-					 extack, &encap_dev);
-		dev_put(out_dev);
-		if (err)
-			goto out;
-
-		if (esw_attr->dests[out_index].flags &
-		    MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE &&
-		    !esw_attr->dest_int_port)
-			*vf_tun = true;
-
-		out_priv = netdev_priv(encap_dev);
-		rpriv = out_priv->ppriv;
-		esw_attr->dests[out_index].rep = rpriv->rep;
-		esw_attr->dests[out_index].mdev = out_priv->mdev;
-	}
-
-	if (*vf_tun && esw_attr->out_count > 1) {
-		NL_SET_ERR_MSG_MOD(extack, "VF tunnel encap with mirroring is not supported");
-		err = -EOPNOTSUPP;
-		goto out;
-	}
-
-out:
-	return err;
-}
-
-static void
-clean_encap_dests(struct mlx5e_priv *priv,
-		  struct mlx5e_tc_flow *flow,
-		  struct mlx5_flow_attr *attr)
-{
-	struct mlx5_esw_flow_attr *esw_attr;
-	int out_index;
-
-	if (!mlx5e_is_eswitch_flow(flow))
-		return;
-
-	esw_attr = attr->esw_attr;
-
-	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) {
-		if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP))
-			continue;
-
-		mlx5e_detach_encap(priv, flow, attr, out_index);
-		kfree(attr->parse_attr->tun_info[out_index]);
-	}
-}
-
-static int
 verify_attr_actions(u32 actions, struct netlink_ext_ack *extack)
 {
 	if (!(actions &
@@ -1820,7 +1735,7 @@ post_process_attr(struct mlx5e_tc_flow *flow,
 	if (err)
 		goto err_out;
 
-	err = set_encap_dests(flow->priv, flow, attr, extack, &vf_tun);
+	err = mlx5e_tc_tun_encap_dests_set(flow->priv, flow, attr, extack, &vf_tun);
 	if (err)
 		goto err_out;
 
@@ -3944,8 +3859,8 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state,
 	struct mlx5_flow_attr *prev_attr;
 	struct flow_action_entry *act;
 	struct mlx5e_tc_act *tc_act;
+	int err, i, i_split = 0;
 	bool is_missable;
-	int err, i;
 
 	ns_type = mlx5e_get_flow_namespace(flow);
 	list_add(&attr->list, &flow->attrs);
@@ -3986,7 +3901,8 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state,
 		    i < flow_action->num_entries - 1)) {
 			is_missable = tc_act->is_missable ? tc_act->is_missable(act) : false;
 
-			err = mlx5e_tc_act_post_parse(parse_state, flow_action, attr, ns_type);
+			err = mlx5e_tc_act_post_parse(parse_state, flow_action, i_split, i, attr,
+						      ns_type);
 			if (err)
 				goto out_free_post_acts;
 
@@ -3996,6 +3912,7 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state,
 				goto out_free_post_acts;
 			}
 
+			i_split = i + 1;
 			list_add(&attr->list, &flow->attrs);
 		}
 
@@ -4010,7 +3927,7 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state,
 		}
 	}
 
-	err = mlx5e_tc_act_post_parse(parse_state, flow_action, attr, ns_type);
+	err = mlx5e_tc_act_post_parse(parse_state, flow_action, i_split, i, attr, ns_type);
 	if (err)
 		goto out_free_post_acts;
 
@@ -4324,7 +4241,7 @@ mlx5_free_flow_attr_actions(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *a
 	if (attr->post_act_handle)
 		mlx5e_tc_post_act_del(get_post_action(flow->priv), attr->post_act_handle);
 
-	clean_encap_dests(flow->priv, flow, attr);
+	mlx5e_tc_tun_encap_dests_unset(flow->priv, flow, attr);
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT)
 		mlx5_fc_destroy(counter_dev, attr->counter);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index fe698c79616c..3db4866d7880 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -824,7 +824,7 @@ static int comp_irqs_request_pci(struct mlx5_core_dev *dev)
 	ncomp_eqs = table->num_comp_eqs;
 	cpus = kcalloc(ncomp_eqs, sizeof(*cpus), GFP_KERNEL);
 	if (!cpus)
-		ret = -ENOMEM;
+		return -ENOMEM;
 
 	i = 0;
 	rcu_read_lock();
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index a7eb65cd0bdd..d6ee016deae1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -923,7 +923,6 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev,
 	}
 
 	mlx5_pci_vsc_init(dev);
-	dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev);
 	return 0;
 
 err_clr_master:
@@ -1155,6 +1154,7 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot, u64 timeout
 		goto err_cmd_cleanup;
 	}
 
+	dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev);
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_UP);
 
 	mlx5_start_health_poll(dev);
@@ -1802,15 +1802,16 @@ static void remove_one(struct pci_dev *pdev)
 	struct devlink *devlink = priv_to_devlink(dev);
 
 	set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state);
-	/* mlx5_drain_fw_reset() is using devlink APIs. Hence, we must drain
-	 * fw_reset before unregistering the devlink.
+	/* mlx5_drain_fw_reset() and mlx5_drain_health_wq() are using
+	 * devlink notify APIs.
+	 * Hence, we must drain them before unregistering the devlink.
 	 */
 	mlx5_drain_fw_reset(dev);
+	mlx5_drain_health_wq(dev);
 	devlink_unregister(devlink);
 	mlx5_sriov_disable(pdev);
 	mlx5_thermal_uninit(dev);
 	mlx5_crdump_disable(dev);
-	mlx5_drain_health_wq(dev);
 	mlx5_uninit_one(dev);
 	mlx5_pci_close(dev);
 	mlx5_mdev_uninit(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
index 9d735c343a3b..678f0be81375 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
@@ -32,6 +32,7 @@
 
 #include <linux/kernel.h>
 #include <linux/mlx5/driver.h>
+#include <linux/mlx5/qp.h>
 #include "mlx5_core.h"
 
 int mlx5_core_create_mkey(struct mlx5_core_dev *dev, u32 *mkey, u32 *in,
@@ -122,3 +123,23 @@ int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num)
 	return mlx5_cmd_exec_in(dev, destroy_psv, in);
 }
 EXPORT_SYMBOL(mlx5_core_destroy_psv);
+
+__be32 mlx5_core_get_terminate_scatter_list_mkey(struct mlx5_core_dev *dev)
+{
+	u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(query_special_contexts_in)] = {};
+	u32 mkey;
+
+	if (!MLX5_CAP_GEN(dev, terminate_scatter_list_mkey))
+		return MLX5_TERMINATE_SCATTER_LIST_LKEY;
+
+	MLX5_SET(query_special_contexts_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS);
+	if (mlx5_cmd_exec_inout(dev, query_special_contexts, in, out))
+		return MLX5_TERMINATE_SCATTER_LIST_LKEY;
+
+	mkey = MLX5_GET(query_special_contexts_out, out,
+			terminate_scatter_list_mkey);
+	return cpu_to_be32(mkey);
+}
+EXPORT_SYMBOL(mlx5_core_get_terminate_scatter_list_mkey);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index db5687d9fec9..843da89a9035 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -141,7 +141,7 @@ static void irq_release(struct mlx5_irq *irq)
 	irq_update_affinity_hint(irq->map.virq, NULL);
 #ifdef CONFIG_RFS_ACCEL
 	rmap = mlx5_eq_table_get_rmap(pool->dev);
-	if (rmap && irq->map.index)
+	if (rmap)
 		irq_cpu_rmap_remove(rmap, irq->map.virq);
 #endif
 
@@ -232,12 +232,13 @@ struct mlx5_irq *mlx5_irq_alloc(struct mlx5_irq_pool *pool, int i,
 	if (!irq)
 		return ERR_PTR(-ENOMEM);
 	if (!i || !pci_msix_can_alloc_dyn(dev->pdev)) {
-		/* The vector at index 0 was already allocated.
-		 * Just get the irq number. If dynamic irq is not supported
-		 * vectors have also been allocated.
+		/* The vector at index 0 is always statically allocated. If
+		 * dynamic irq is not supported all vectors are statically
+		 * allocated. In both cases just get the irq number and set
+		 * the index.
 		 */
 		irq->map.virq = pci_irq_vector(dev->pdev, i);
-		irq->map.index = 0;
+		irq->map.index = i;
 	} else {
 		irq->map = pci_msix_alloc_irq_at(dev->pdev, MSI_ANY_INDEX, af_desc);
 		if (!irq->map.virq) {
@@ -570,11 +571,11 @@ int mlx5_irqs_request_vectors(struct mlx5_core_dev *dev, u16 *cpus, int nirqs,
 
 	af_desc.is_managed = false;
 	for (i = 0; i < nirqs; i++) {
+		cpumask_clear(&af_desc.mask);
 		cpumask_set_cpu(cpus[i], &af_desc.mask);
 		irq = mlx5_irq_request(dev, i + 1, &af_desc, rmap);
 		if (IS_ERR(irq))
 			break;
-		cpumask_clear(&af_desc.mask);
 		irqs[i] = irq;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
index e2f26d0bc615..0692363cf80e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
@@ -63,6 +63,7 @@ static void mlx5_sf_dev_remove(struct auxiliary_device *adev)
 	struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev);
 	struct devlink *devlink = priv_to_devlink(sf_dev->mdev);
 
+	mlx5_drain_health_wq(sf_dev->mdev);
 	devlink_unregister(devlink);
 	mlx5_uninit_one(sf_dev->mdev);
 	iounmap(sf_dev->mdev->iseg);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c
index 13e06a6a6b22..d6947fe13d56 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c
@@ -213,6 +213,8 @@ struct mlx5dr_ptrn_mgr *mlx5dr_ptrn_mgr_create(struct mlx5dr_domain *dmn)
 	}
 
 	INIT_LIST_HEAD(&mgr->ptrn_list);
+	mutex_init(&mgr->modify_hdr_mutex);
+
 	return mgr;
 
 free_mgr:
@@ -237,5 +239,6 @@ void mlx5dr_ptrn_mgr_destroy(struct mlx5dr_ptrn_mgr *mgr)
 	}
 
 	mlx5dr_icm_pool_destroy(mgr->ptrn_icm_pool);
+	mutex_destroy(&mgr->modify_hdr_mutex);
 	kfree(mgr);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c
index afa3b92a6905..0d5a41a2ae01 100644
--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c
+++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c
@@ -245,12 +245,6 @@ static bool mlxbf_gige_rx_packet(struct mlxbf_gige *priv, int *rx_pkts)
 
 		skb = priv->rx_skb[rx_pi_rem];
 
-		skb_put(skb, datalen);
-
-		skb->ip_summed = CHECKSUM_NONE; /* device did not checksum packet */
-
-		skb->protocol = eth_type_trans(skb, netdev);
-
 		/* Alloc another RX SKB for this same index */
 		rx_skb = mlxbf_gige_alloc_skb(priv, MLXBF_GIGE_DEFAULT_BUF_SZ,
 					      &rx_buf_dma, DMA_FROM_DEVICE);
@@ -259,6 +253,13 @@ static bool mlxbf_gige_rx_packet(struct mlxbf_gige *priv, int *rx_pkts)
 		priv->rx_skb[rx_pi_rem] = rx_skb;
 		dma_unmap_single(priv->dev, *rx_wqe_addr,
 				 MLXBF_GIGE_DEFAULT_BUF_SZ, DMA_FROM_DEVICE);
+
+		skb_put(skb, datalen);
+
+		skb->ip_summed = CHECKSUM_NONE; /* device did not checksum packet */
+
+		skb->protocol = eth_type_trans(skb, netdev);
+
 		*rx_wqe_addr = rx_buf_dma;
 	} else if (rx_cqe & MLXBF_GIGE_RX_CQE_PKT_STATUS_MAC_ERR) {
 		priv->stats.rx_mac_errors++;
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 06d6292e09b3..d907727c7b7a 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1279,8 +1279,6 @@ static void mana_poll_tx_cq(struct mana_cq *cq)
 	if (comp_read < 1)
 		return;
 
-	apc->eth_stats.tx_cqes = comp_read;
-
 	for (i = 0; i < comp_read; i++) {
 		struct mana_tx_comp_oob *cqe_oob;
 
@@ -1363,8 +1361,6 @@ static void mana_poll_tx_cq(struct mana_cq *cq)
 		WARN_ON_ONCE(1);
 
 	cq->work_done = pkt_transmitted;
-
-	apc->eth_stats.tx_cqes -= pkt_transmitted;
 }
 
 static void mana_post_pkt_rxq(struct mana_rxq *rxq)
@@ -1626,15 +1622,11 @@ static void mana_poll_rx_cq(struct mana_cq *cq)
 {
 	struct gdma_comp *comp = cq->gdma_comp_buf;
 	struct mana_rxq *rxq = cq->rxq;
-	struct mana_port_context *apc;
 	int comp_read, i;
 
-	apc = netdev_priv(rxq->ndev);
-
 	comp_read = mana_gd_poll_cq(cq->gdma_cq, comp, CQE_POLLING_BUFFER);
 	WARN_ON_ONCE(comp_read > CQE_POLLING_BUFFER);
 
-	apc->eth_stats.rx_cqes = comp_read;
 	rxq->xdp_flush = false;
 
 	for (i = 0; i < comp_read; i++) {
@@ -1646,8 +1638,6 @@ static void mana_poll_rx_cq(struct mana_cq *cq)
 			return;
 
 		mana_process_rx_cqe(rxq, cq, &comp[i]);
-
-		apc->eth_stats.rx_cqes--;
 	}
 
 	if (rxq->xdp_flush)
diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
index a64c81410dc1..0dc78679f620 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
@@ -13,11 +13,9 @@ static const struct {
 } mana_eth_stats[] = {
 	{"stop_queue", offsetof(struct mana_ethtool_stats, stop_queue)},
 	{"wake_queue", offsetof(struct mana_ethtool_stats, wake_queue)},
-	{"tx_cqes", offsetof(struct mana_ethtool_stats, tx_cqes)},
 	{"tx_cq_err", offsetof(struct mana_ethtool_stats, tx_cqe_err)},
 	{"tx_cqe_unknown_type", offsetof(struct mana_ethtool_stats,
 					tx_cqe_unknown_type)},
-	{"rx_cqes", offsetof(struct mana_ethtool_stats, rx_cqes)},
 	{"rx_coalesced_err", offsetof(struct mana_ethtool_stats,
 					rx_coalesced_err)},
 	{"rx_cqe_unknown_type", offsetof(struct mana_ethtool_stats,
diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c
index 29afaddb598d..aace87139cea 100644
--- a/drivers/net/ethernet/renesas/rswitch.c
+++ b/drivers/net/ethernet/renesas/rswitch.c
@@ -1485,7 +1485,7 @@ static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *nd
 
 	if (rswitch_get_num_cur_queues(gq) >= gq->ring_size - 1) {
 		netif_stop_subqueue(ndev, 0);
-		return ret;
+		return NETDEV_TX_BUSY;
 	}
 
 	if (skb_put_padto(skb, ETH_ZLEN))
diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c
index 0327639a628a..c004443c1d58 100644
--- a/drivers/net/ethernet/sfc/tc.c
+++ b/drivers/net/ethernet/sfc/tc.c
@@ -624,13 +624,12 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx,
 	if (!found) { /* We don't care. */
 		netif_dbg(efx, drv, efx->net_dev,
 			  "Ignoring foreign filter that doesn't egdev us\n");
-		rc = -EOPNOTSUPP;
-		goto release;
+		return -EOPNOTSUPP;
 	}
 
 	rc = efx_mae_match_check_caps(efx, &match.mask, NULL);
 	if (rc)
-		goto release;
+		return rc;
 
 	if (efx_tc_match_is_encap(&match.mask)) {
 		enum efx_encap_type type;
@@ -639,8 +638,7 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx,
 		if (type == EFX_ENCAP_TYPE_NONE) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Egress encap match on unsupported tunnel device");
-			rc = -EOPNOTSUPP;
-			goto release;
+			return -EOPNOTSUPP;
 		}
 
 		rc = efx_mae_check_encap_type_supported(efx, type);
@@ -648,25 +646,24 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx,
 			NL_SET_ERR_MSG_FMT_MOD(extack,
 					       "Firmware reports no support for %s encap match",
 					       efx_tc_encap_type_name(type));
-			goto release;
+			return rc;
 		}
 
 		rc = efx_tc_flower_record_encap_match(efx, &match, type,
 						      extack);
 		if (rc)
-			goto release;
+			return rc;
 	} else {
 		/* This is not a tunnel decap rule, ignore it */
 		netif_dbg(efx, drv, efx->net_dev,
 			  "Ignoring foreign filter without encap match\n");
-		rc = -EOPNOTSUPP;
-		goto release;
+		return -EOPNOTSUPP;
 	}
 
 	rule = kzalloc(sizeof(*rule), GFP_USER);
 	if (!rule) {
 		rc = -ENOMEM;
-		goto release;
+		goto out_free;
 	}
 	INIT_LIST_HEAD(&rule->acts.list);
 	rule->cookie = tc->cookie;
@@ -678,7 +675,7 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx,
 			  "Ignoring already-offloaded rule (cookie %lx)\n",
 			  tc->cookie);
 		rc = -EEXIST;
-		goto release;
+		goto out_free;
 	}
 
 	act = kzalloc(sizeof(*act), GFP_USER);
@@ -843,6 +840,7 @@ release:
 				       efx_tc_match_action_ht_params);
 		efx_tc_free_action_set_list(efx, &rule->acts, false);
 	}
+out_free:
 	kfree(rule);
 	if (match.encap)
 		efx_tc_flower_release_encap_match(efx, match.encap);
@@ -899,8 +897,7 @@ static int efx_tc_flower_replace(struct efx_nic *efx,
 		return rc;
 	if (efx_tc_match_is_encap(&match.mask)) {
 		NL_SET_ERR_MSG_MOD(extack, "Ingress enc_key matches not supported");
-		rc = -EOPNOTSUPP;
-		goto release;
+		return -EOPNOTSUPP;
 	}
 
 	if (tc->common.chain_index) {
@@ -924,9 +921,9 @@ static int efx_tc_flower_replace(struct efx_nic *efx,
 	if (old) {
 		netif_dbg(efx, drv, efx->net_dev,
 			  "Already offloaded rule (cookie %lx)\n", tc->cookie);
-		rc = -EEXIST;
 		NL_SET_ERR_MSG_MOD(extack, "Rule already offloaded");
-		goto release;
+		kfree(rule);
+		return -EEXIST;
 	}
 
 	/* Parse actions */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 0fca81507a77..52cab9de05f2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -7233,8 +7233,7 @@ int stmmac_dvr_probe(struct device *device,
 	ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 			    NETIF_F_RXCSUM;
 	ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
-			     NETDEV_XDP_ACT_XSK_ZEROCOPY |
-			     NETDEV_XDP_ACT_NDO_XMIT;
+			     NETDEV_XDP_ACT_XSK_ZEROCOPY;
 
 	ret = stmmac_tc_init(priv, priv);
 	if (!ret) {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.c
index 9d4d8c3dad0a..aa6f16d3df64 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.c
@@ -117,6 +117,9 @@ int stmmac_xdp_set_prog(struct stmmac_priv *priv, struct bpf_prog *prog,
 		return -EOPNOTSUPP;
 	}
 
+	if (!prog)
+		xdp_features_clear_redirect_target(dev);
+
 	need_update = !!priv->xdp_prog != !!prog;
 	if (if_running && need_update)
 		stmmac_xdp_release(dev);
@@ -131,5 +134,8 @@ int stmmac_xdp_set_prog(struct stmmac_priv *priv, struct bpf_prog *prog,
 	if (if_running && need_update)
 		stmmac_xdp_open(dev);
 
+	if (prog)
+		xdp_features_set_redirect_target(dev, false);
+
 	return 0;
 }
diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c
index 2ee80ed140b7..afa1d56d9095 100644
--- a/drivers/net/ipa/ipa_endpoint.c
+++ b/drivers/net/ipa/ipa_endpoint.c
@@ -119,7 +119,7 @@ enum ipa_status_field_id {
 };
 
 /* Size in bytes of an IPA packet status structure */
-#define IPA_STATUS_SIZE			sizeof(__le32[4])
+#define IPA_STATUS_SIZE			sizeof(__le32[8])
 
 /* IPA status structure decoder; looks up field values for a structure */
 static u32 ipa_status_extract(struct ipa *ipa, const void *data,
diff --git a/drivers/net/phy/mxl-gpy.c b/drivers/net/phy/mxl-gpy.c
index 6301a9abfb95..ea1073adc5a1 100644
--- a/drivers/net/phy/mxl-gpy.c
+++ b/drivers/net/phy/mxl-gpy.c
@@ -274,13 +274,6 @@ static int gpy_config_init(struct phy_device *phydev)
 	return ret < 0 ? ret : 0;
 }
 
-static bool gpy_has_broken_mdint(struct phy_device *phydev)
-{
-	/* At least these PHYs are known to have broken interrupt handling */
-	return phydev->drv->phy_id == PHY_ID_GPY215B ||
-	       phydev->drv->phy_id == PHY_ID_GPY215C;
-}
-
 static int gpy_probe(struct phy_device *phydev)
 {
 	struct device *dev = &phydev->mdio.dev;
@@ -300,8 +293,7 @@ static int gpy_probe(struct phy_device *phydev)
 	phydev->priv = priv;
 	mutex_init(&priv->mbox_lock);
 
-	if (gpy_has_broken_mdint(phydev) &&
-	    !device_property_present(dev, "maxlinear,use-broken-interrupts"))
+	if (!device_property_present(dev, "maxlinear,use-broken-interrupts"))
 		phydev->dev_flags |= PHY_F_NO_IRQ;
 
 	fw_version = phy_read(phydev, PHY_FWV);
@@ -659,11 +651,9 @@ static irqreturn_t gpy_handle_interrupt(struct phy_device *phydev)
 	 * frame. Therefore, polling is the best we can do and won't do any more
 	 * harm.
 	 * It was observed that this bug happens on link state and link speed
-	 * changes on a GPY215B and GYP215C independent of the firmware version
-	 * (which doesn't mean that this list is exhaustive).
+	 * changes independent of the firmware version.
 	 */
-	if (gpy_has_broken_mdint(phydev) &&
-	    (reg & (PHY_IMASK_LSTC | PHY_IMASK_LSPC))) {
+	if (reg & (PHY_IMASK_LSTC | PHY_IMASK_LSPC)) {
 		reg = gpy_mbox_read(phydev, REG_GPIO0_OUT);
 		if (reg < 0) {
 			phy_error(phydev);
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 571e37e67f9c..f1865d047971 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1325,7 +1325,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x2001, 0x7e3d, 4)},	/* D-Link DWM-222 A2 */
 	{QMI_FIXED_INTF(0x2020, 0x2031, 4)},	/* Olicard 600 */
 	{QMI_FIXED_INTF(0x2020, 0x2033, 4)},	/* BroadMobi BM806U */
-	{QMI_FIXED_INTF(0x2020, 0x2060, 4)},	/* BroadMobi BM818 */
+	{QMI_QUIRK_SET_DTR(0x2020, 0x2060, 4)},	/* BroadMobi BM818 */
 	{QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)},    /* Sierra Wireless MC7700 */
 	{QMI_FIXED_INTF(0x114f, 0x68a2, 8)},    /* Sierra Wireless MC7750 */
 	{QMI_FIXED_INTF(0x1199, 0x68a2, 8)},	/* Sierra Wireless MC7710 in QMI mode */
diff --git a/drivers/nfc/nfcsim.c b/drivers/nfc/nfcsim.c
index 44eeb17ae48d..a55381f80cd6 100644
--- a/drivers/nfc/nfcsim.c
+++ b/drivers/nfc/nfcsim.c
@@ -336,10 +336,6 @@ static struct dentry *nfcsim_debugfs_root;
 static void nfcsim_debugfs_init(void)
 {
 	nfcsim_debugfs_root = debugfs_create_dir("nfcsim", NULL);
-
-	if (!nfcsim_debugfs_root)
-		pr_err("Could not create debugfs entry\n");
-
 }
 
 static void nfcsim_debugfs_remove(void)