Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from David Miller: 1) Fix type of bind option flag in af_xdp, from Baruch Siach. 2) Fix use after free in bpf_xdp_link_release(), from Xuan Zhao. 3) PM refcnt imbakance in r8152, from Takashi Iwai. 4) Sign extension ug in liquidio, from Colin Ian King. 5) Mising range check in s390 bpf jit, from Colin Ian King. 6) Uninit value in caif_seqpkt_sendmsg(), from Ziyong Xuan. 7) Fix skb page recycling race, from Ilias Apalodimas. 8) Fix memory leak in tcindex_partial_destroy_work, from Pave Skripkin. 9) netrom timer sk refcnt issues, from Nguyen Dinh Phi. 10) Fix data races aroun tcp's tfo_active_disable_stamp, from Eric Dumazet. 11) act_skbmod should only operate on ethernet packets, from Peilin Ye. 12) Fix slab out-of-bpunds in fib6_nh_flush_exceptions(),, from Psolo Abeni. 13) Fix sparx5 dependencies, from Yajun Deng. * git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (74 commits) dpaa2-switch: seed the buffer pool after allocating the swp net: sched: cls_api: Fix the the wrong parameter net: sparx5: fix unmet dependencies warning net: dsa: tag_ksz: dont let the hardware process the layer 4 checksum net: dsa: ensure linearized SKBs in case of tail taggers ravb: Remove extra TAB ravb: Fix a typo in comment net: dsa: sja1105: make VID 4095 a bridge VLAN too tcp: disable TFO blackhole logic by default sctp: do not update transport pathmtu if SPP_PMTUD_ENABLE is not set net: ixp46x: fix ptp build failure ibmvnic: Remove the proper scrq flush selftests: net: add ESP-in-UDP PMTU test udp: check encap socket in __udp_lib_err sctp: update active_key for asoc when old key is being replaced r8169: Avoid duplicate sysfs entry creation error ixgbe: Fix packet corruption due to missing DMA sync Revert "qed: fix possible unpaired spin_{un}lock_bh in _qed_mcp_cmd_and_union()" ipv6: fix another slab-out-of-bounds in fib6_nh_flush_exceptions fsl/fman: Add fibre support ...
2021-07-22 10:11:27 -07:00 · 2021-07-22 10:11:27 -07:00 · 4784dc99c7
commit 4784dc99c7
parent 5e09e197a8 7aaa0f311e
77 changed files with 1218 additions and 270 deletions
--- a/Documentation/devicetree/bindings/net/imx-dwmac.txt
+++ b/Documentation/devicetree/bindings/net/imx-dwmac.txt
@ -1,56 +0,0 @@
-IMX8 glue layer controller, NXP imx8 families support Synopsys MAC 5.10a IP.
-
-This file documents platform glue layer for IMX.
-Please see stmmac.txt for the other unchanged properties.
-
-The device node has following properties.
-
-Required properties:
- compatible:  Should be "nxp,imx8mp-dwmac-eqos" to select glue layer
-	       and "snps,dwmac-5.10a" to select IP version.
- clocks: Must contain a phandle for each entry in clock-names.
- clock-names: Should be "stmmaceth" for the host clock.
-	       Should be "pclk" for the MAC apb clock.
-	       Should be "ptp_ref" for the MAC timer clock.
-	       Should be "tx" for the MAC RGMII TX clock:
-	       Should be "mem" for EQOS MEM clock.
-		- "mem" clock is required for imx8dxl platform.
-		- "mem" clock is not required for imx8mp platform.
- interrupt-names: Should contain a list of interrupt names corresponding to
-		   the interrupts in the interrupts property, if available.
-		   Should be "macirq" for the main MAC IRQ
-		   Should be "eth_wake_irq" for the IT which wake up system
- intf_mode: Should be phandle/offset pair. The phandle to the syscon node which
-	     encompases the GPR register, and the offset of the GPR register.
-		- required for imx8mp platform.
-		- is optional for imx8dxl platform.
-
-Optional properties:
- intf_mode: is optional for imx8dxl platform.
- snps,rmii_refclk_ext: to select RMII reference clock from external.
-
-Example:
-	eqos: ethernet@30bf0000 {
-		compatible = "nxp,imx8mp-dwmac-eqos", "snps,dwmac-5.10a";
-		reg = <0x30bf0000 0x10000>;
-		interrupts = <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>;
-		interrupt-names = "eth_wake_irq", "macirq";
-		clocks = <&clk IMX8MP_CLK_ENET_QOS_ROOT>,
-			 <&clk IMX8MP_CLK_QOS_ENET_ROOT>,
-			 <&clk IMX8MP_CLK_ENET_QOS_TIMER>,
-			 <&clk IMX8MP_CLK_ENET_QOS>;
-		clock-names = "stmmaceth", "pclk", "ptp_ref", "tx";
-		assigned-clocks = <&clk IMX8MP_CLK_ENET_AXI>,
-				  <&clk IMX8MP_CLK_ENET_QOS_TIMER>,
-				  <&clk IMX8MP_CLK_ENET_QOS>;
-		assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_266M>,
-					 <&clk IMX8MP_SYS_PLL2_100M>,
-					 <&clk IMX8MP_SYS_PLL2_125M>;
-		assigned-clock-rates = <0>, <100000000>, <125000000>;
-		nvmem-cells = <&eth_mac0>;
-		nvmem-cell-names = "mac-address";
-		nvmem_macaddr_swap;
-		intf_mode = <&gpr 0x4>;
-		status = "disabled";
-	};
--- a/Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml
+++ b/Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml
@ -0,0 +1,93 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/nxp,dwmac-imx.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: NXP i.MX8 DWMAC glue layer Device Tree Bindings
+
+maintainers:
+  - Joakim Zhang <qiangqing.zhang@nxp.com>
+
+# We need a select here so we don't match all nodes with 'snps,dwmac'
+select:
+  properties:
+    compatible:
+      contains:
+        enum:
+          - nxp,imx8mp-dwmac-eqos
+          - nxp,imx8dxl-dwmac-eqos
+  required:
+    - compatible
+
+allOf:
+  - $ref: "snps,dwmac.yaml#"
+
+properties:
+  compatible:
+    oneOf:
+      - items:
+          - enum:
+              - nxp,imx8mp-dwmac-eqos
+              - nxp,imx8dxl-dwmac-eqos
+          - const: snps,dwmac-5.10a
+
+  clocks:
+    minItems: 3
+    maxItems: 5
+    items:
+      - description: MAC host clock
+      - description: MAC apb clock
+      - description: MAC timer clock
+      - description: MAC RGMII TX clock
+      - description: EQOS MEM clock
+
+  clock-names:
+    minItems: 3
+    maxItems: 5
+    contains:
+      enum:
+        - stmmaceth
+        - pclk
+        - ptp_ref
+        - tx
+        - mem
+
+  intf_mode:
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    description:
+      Should be phandle/offset pair. The phandle to the syscon node which
+      encompases the GPR register, and the offset of the GPR register.
+
+  snps,rmii_refclk_ext:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description:
+      To select RMII reference clock from external.
+
+required:
+  - compatible
+  - clocks
+  - clock-names
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
+    #include <dt-bindings/clock/imx8mp-clock.h>
+
+    eqos: ethernet@30bf0000 {
+            compatible = "nxp,imx8mp-dwmac-eqos","snps,dwmac-5.10a";
+            reg = <0x30bf0000 0x10000>;
+            interrupts = <GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>;
+            interrupt-names = "macirq", "eth_wake_irq";
+            clocks = <&clk IMX8MP_CLK_ENET_QOS_ROOT>,
+                     <&clk IMX8MP_CLK_QOS_ENET_ROOT>,
+                     <&clk IMX8MP_CLK_ENET_QOS_TIMER>,
+                     <&clk IMX8MP_CLK_ENET_QOS>;
+            clock-names = "stmmaceth", "pclk", "ptp_ref", "tx";
+            phy-mode = "rgmii";
+            status = "disabled";
+    };
--- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml
@ -28,6 +28,7 @@ select:
          - snps,dwmac-4.00
          - snps,dwmac-4.10a
          - snps,dwmac-4.20a
+          - snps,dwmac-5.10a
          - snps,dwxgmac
          - snps,dwxgmac-2.10

@ -82,6 +83,7 @@ properties:
        - snps,dwmac-4.00
        - snps,dwmac-4.10a
        - snps,dwmac-4.20a
+        - snps,dwmac-5.10a
        - snps,dwxgmac
        - snps,dwxgmac-2.10

@ -375,6 +377,7 @@ allOf:
              - snps,dwmac-4.00
              - snps,dwmac-4.10a
              - snps,dwmac-4.20a
+              - snps,dwmac-5.10a
              - snps,dwxgmac
              - snps,dwxgmac-2.10
              - st,spear600-gmac
--- a/Documentation/networking/af_xdp.rst
+++ b/Documentation/networking/af_xdp.rst
@ -243,8 +243,8 @@ Configuration Flags and Socket Options
 These are the various configuration flags that can be used to control
 and monitor the behavior of AF_XDP sockets.

-XDP_COPY and XDP_ZERO_COPY bind flags
-------------------------------------
+XDP_COPY and XDP_ZEROCOPY bind flags
+------------------------------------

 When you bind to a socket, the kernel will first try to use zero-copy
 copy. If zero-copy is not supported, it will fall back on using copy
@ -252,7 +252,7 @@ mode, i.e. copying all packets out to user space. But if you would
 like to force a certain mode, you can use the following flags. If you
 pass the XDP_COPY flag to the bind call, the kernel will force the
 socket into copy mode. If it cannot use copy mode, the bind call will
-fail with an error. Conversely, the XDP_ZERO_COPY flag will force the
+fail with an error. Conversely, the XDP_ZEROCOPY flag will force the
 socket into zero-copy mode or fail.

 XDP_SHARED_UMEM bind flag
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@ -826,7 +826,7 @@ tcp_fastopen_blackhole_timeout_sec - INTEGER
 	initial value when the blackhole issue goes away.
 	0 to disable the blackhole detection.

-	By default, it is set to 1hr.
+	By default, it is set to 0 (feature is disabled).

 tcp_fastopen_key - list of comma separated 32-digit hexadecimal INTEGERs
 	The list consists of a primary key and an optional backup key. The
--- a/1
+++ b/1
@ -11758,6 +11758,7 @@ F:	drivers/char/hw_random/mtk-rng.c
 MEDIATEK SWITCH DRIVER
 M:	Sean Wang <sean.wang@mediatek.com>
 M:	Landen Chao <Landen.Chao@mediatek.com>
+M:	DENG Qingfang <dqfext@gmail.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/dsa/mt7530.*
--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
@ -821,9 +821,9 @@
 			eqos: ethernet@30bf0000 {
 				compatible = "nxp,imx8mp-dwmac-eqos", "snps,dwmac-5.10a";
 				reg = <0x30bf0000 0x10000>;
-				interrupts = <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>,
-					     <GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>;
-				interrupt-names = "eth_wake_irq", "macirq";
+				interrupts = <GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-names = "macirq", "eth_wake_irq";
 				clocks = <&clk IMX8MP_CLK_ENET_QOS_ROOT>,
 					 <&clk IMX8MP_CLK_QOS_ENET_ROOT>,
 					 <&clk IMX8MP_CLK_ENET_QOS_TIMER>,
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@ -112,7 +112,7 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 {
 	u32 r1 = reg2hex[b1];

-	if (!jit->seen_reg[r1] && r1 >= 6 && r1 <= 15)
+	if (r1 >= 6 && r1 <= 15 && !jit->seen_reg[r1])
 		jit->seen_reg[r1] = 1;
 }

--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@ -3450,7 +3450,9 @@ static int bond_master_netdev_event(unsigned long event,
 		return bond_event_changename(event_bond);
 	case NETDEV_UNREGISTER:
 		bond_remove_proc_entry(event_bond);
+#ifdef CONFIG_XFRM_OFFLOAD
 		xfrm_dev_state_flush(dev_net(bond_dev), bond_dev, true);
+#endif /* CONFIG_XFRM_OFFLOAD */
 		break;
 	case NETDEV_REGISTER:
 		bond_create_proc_entry(event_bond);
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@ -366,6 +366,8 @@ mt7530_fdb_write(struct mt7530_priv *priv, u16 vid,
 	int i;

 	reg[1] |= vid & CVID_MASK;
+	if (vid > 1)
+		reg[1] |= ATA2_IVL;
 	reg[2] |= (aging & AGE_TIMER_MASK) << AGE_TIMER;
 	reg[2] |= (port_mask & PORT_MAP_MASK) << PORT_MAP;
 	/* STATIC_ENT indicate that entry is static wouldn't
--- a/drivers/net/dsa/mt7530.h
+++ b/drivers/net/dsa/mt7530.h
@ -79,6 +79,7 @@ enum mt753x_bpdu_port_fw {
 #define  STATIC_EMP			0
 #define  STATIC_ENT			3
 #define MT7530_ATA2			0x78
+#define  ATA2_IVL			BIT(15)

 /* Register for address table write data */
 #define MT7530_ATWD			0x7c
--- a/drivers/net/dsa/mv88e6xxx/Kconfig
+++ b/drivers/net/dsa/mv88e6xxx/Kconfig
@ -12,7 +12,7 @@ config NET_DSA_MV88E6XXX
 config NET_DSA_MV88E6XXX_PTP
 	bool "PTP support for Marvell 88E6xxx"
 	default n
-	depends on PTP_1588_CLOCK
+	depends on NET_DSA_MV88E6XXX && PTP_1588_CLOCK
 	help
 	  Say Y to enable PTP hardware timestamping on Marvell 88E6xxx switch
 	  chips that support it.
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@ -397,6 +397,12 @@ static int sja1105_init_static_vlan(struct sja1105_private *priv)
 		if (dsa_is_cpu_port(ds, port))
 			v->pvid = true;
 		list_add(&v->list, &priv->dsa_8021q_vlans);
+
+		v = kmemdup(v, sizeof(*v), GFP_KERNEL);
+		if (!v)
+			return -ENOMEM;
+
+		list_add(&v->list, &priv->bridge_vlans);
 	}

 	((struct sja1105_vlan_lookup_entry *)table->entries)[0] = pvid;
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@ -1671,11 +1671,16 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,

 	if ((tpa_info->flags2 & RX_CMP_FLAGS2_META_FORMAT_VLAN) &&
 	    (skb->dev->features & BNXT_HW_FEATURE_VLAN_ALL_RX)) {
-		u16 vlan_proto = tpa_info->metadata >>
-			RX_CMP_FLAGS2_METADATA_TPID_SFT;
+		__be16 vlan_proto = htons(tpa_info->metadata >>
+					  RX_CMP_FLAGS2_METADATA_TPID_SFT);
 		u16 vtag = tpa_info->metadata & RX_CMP_FLAGS2_METADATA_TCI_MASK;

-		__vlan_hwaccel_put_tag(skb, htons(vlan_proto), vtag);
+		if (eth_type_vlan(vlan_proto)) {
+			__vlan_hwaccel_put_tag(skb, vlan_proto, vtag);
+		} else {
+			dev_kfree_skb(skb);
+			return NULL;
+		}
 	}

 	skb_checksum_none_assert(skb);
@ -1897,9 +1902,15 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	    (skb->dev->features & BNXT_HW_FEATURE_VLAN_ALL_RX)) {
 		u32 meta_data = le32_to_cpu(rxcmp1->rx_cmp_meta_data);
 		u16 vtag = meta_data & RX_CMP_FLAGS2_METADATA_TCI_MASK;
-		u16 vlan_proto = meta_data >> RX_CMP_FLAGS2_METADATA_TPID_SFT;
+		__be16 vlan_proto = htons(meta_data >>
+					  RX_CMP_FLAGS2_METADATA_TPID_SFT);

-		__vlan_hwaccel_put_tag(skb, htons(vlan_proto), vtag);
+		if (eth_type_vlan(vlan_proto)) {
+			__vlan_hwaccel_put_tag(skb, vlan_proto, vtag);
+		} else {
+			dev_kfree_skb(skb);
+			goto next_rx;
+		}
 	}

 	skb_checksum_none_assert(skb);
@ -7563,8 +7574,12 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp)
 		bp->flags &= ~BNXT_FLAG_WOL_CAP;
 		if (flags & FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED)
 			bp->flags |= BNXT_FLAG_WOL_CAP;
-		if (flags & FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED)
+		if (flags & FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED) {
 			__bnxt_hwrm_ptp_qcfg(bp);
+		} else {
+			kfree(bp->ptp_cfg);
+			bp->ptp_cfg = NULL;
+		}
 	} else {
 #ifdef CONFIG_BNXT_SRIOV
 		struct bnxt_vf_info *vf = &bp->vf;
@ -10123,7 +10138,6 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 		}
 	}

-	bnxt_ptp_start(bp);
 	rc = bnxt_init_nic(bp, irq_re_init);
 	if (rc) {
 		netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc);
@ -10197,6 +10211,12 @@ int bnxt_half_open_nic(struct bnxt *bp)
 {
 	int rc = 0;

+	if (test_bit(BNXT_STATE_ABORT_ERR, &bp->state)) {
+		netdev_err(bp->dev, "A previous firmware reset has not completed, aborting half open\n");
+		rc = -ENODEV;
+		goto half_open_err;
+	}
+
 	rc = bnxt_alloc_mem(bp, false);
 	if (rc) {
 		netdev_err(bp->dev, "bnxt_alloc_mem err: %x\n", rc);
@ -10256,9 +10276,16 @@ static int bnxt_open(struct net_device *dev)
 	rc = bnxt_hwrm_if_change(bp, true);
 	if (rc)
 		return rc;
+
+	if (bnxt_ptp_init(bp)) {
+		netdev_warn(dev, "PTP initialization failed.\n");
+		kfree(bp->ptp_cfg);
+		bp->ptp_cfg = NULL;
+	}
 	rc = __bnxt_open_nic(bp, true, true);
 	if (rc) {
 		bnxt_hwrm_if_change(bp, false);
+		bnxt_ptp_clear(bp);
 	} else {
 		if (test_and_clear_bit(BNXT_STATE_FW_RESET_DET, &bp->state)) {
 			if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
@ -10349,6 +10376,7 @@ static int bnxt_close(struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);

+	bnxt_ptp_clear(bp);
 	bnxt_hwmon_close(bp);
 	bnxt_close_nic(bp, true, true);
 	bnxt_hwrm_shutdown_link(bp);
@ -11335,6 +11363,7 @@ static void bnxt_fw_reset_close(struct bnxt *bp)
 		bnxt_clear_int_mode(bp);
 		pci_disable_device(bp->pdev);
 	}
+	bnxt_ptp_clear(bp);
 	__bnxt_close_nic(bp, true, false);
 	bnxt_vf_reps_free(bp);
 	bnxt_clear_int_mode(bp);
@ -11959,10 +11988,21 @@ static bool bnxt_fw_reset_timeout(struct bnxt *bp)
 			  (bp->fw_reset_max_dsecs * HZ / 10));
 }

+static void bnxt_fw_reset_abort(struct bnxt *bp, int rc)
+{
+	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
+	if (bp->fw_reset_state != BNXT_FW_RESET_STATE_POLL_VF) {
+		bnxt_ulp_start(bp, rc);
+		bnxt_dl_health_status_update(bp, false);
+	}
+	bp->fw_reset_state = 0;
+	dev_close(bp->dev);
+}
+
 static void bnxt_fw_reset_task(struct work_struct *work)
 {
 	struct bnxt *bp = container_of(work, struct bnxt, fw_reset_task.work);
-	int rc;
+	int rc = 0;

 	if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
 		netdev_err(bp->dev, "bnxt_fw_reset_task() called when not in fw reset mode!\n");
@ -11992,6 +12032,11 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		}
 		bp->fw_reset_timestamp = jiffies;
 		rtnl_lock();
+		if (test_bit(BNXT_STATE_ABORT_ERR, &bp->state)) {
+			bnxt_fw_reset_abort(bp, rc);
+			rtnl_unlock();
+			return;
+		}
 		bnxt_fw_reset_close(bp);
 		if (bp->fw_cap & BNXT_FW_CAP_ERR_RECOVER_RELOAD) {
 			bp->fw_reset_state = BNXT_FW_RESET_STATE_POLL_FW_DOWN;
@ -12039,6 +12084,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 			if (val == 0xffff) {
 				if (bnxt_fw_reset_timeout(bp)) {
 					netdev_err(bp->dev, "Firmware reset aborted, PCI config space invalid\n");
+					rc = -ETIMEDOUT;
 					goto fw_reset_abort;
 				}
 				bnxt_queue_fw_reset_work(bp, HZ / 1000);
@ -12048,6 +12094,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		clear_bit(BNXT_STATE_FW_FATAL_COND, &bp->state);
 		if (pci_enable_device(bp->pdev)) {
 			netdev_err(bp->dev, "Cannot re-enable PCI device\n");
+			rc = -ENODEV;
 			goto fw_reset_abort;
 		}
 		pci_set_master(bp->pdev);
@ -12074,9 +12121,10 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		}
 		rc = bnxt_open(bp->dev);
 		if (rc) {
-			netdev_err(bp->dev, "bnxt_open_nic() failed\n");
-			clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
-			dev_close(bp->dev);
+			netdev_err(bp->dev, "bnxt_open() failed during FW reset\n");
+			bnxt_fw_reset_abort(bp, rc);
+			rtnl_unlock();
+			return;
 		}

 		bp->fw_reset_state = 0;
@ -12103,12 +12151,8 @@ fw_reset_abort_status:
 		netdev_err(bp->dev, "fw_health_status 0x%x\n", sts);
 	}
 fw_reset_abort:
-	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
-	if (bp->fw_reset_state != BNXT_FW_RESET_STATE_POLL_VF)
-		bnxt_dl_health_status_update(bp, false);
-	bp->fw_reset_state = 0;
 	rtnl_lock();
-	dev_close(bp->dev);
+	bnxt_fw_reset_abort(bp, rc);
 	rtnl_unlock();
 }

@ -12662,7 +12706,6 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	if (BNXT_PF(bp))
 		devlink_port_type_clear(&bp->dl_port);

-	bnxt_ptp_clear(bp);
 	pci_disable_pcie_error_reporting(pdev);
 	unregister_netdev(dev);
 	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
@ -13246,11 +13289,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 				   rc);
 	}

-	if (bnxt_ptp_init(bp)) {
-		netdev_warn(dev, "PTP initialization failed.\n");
-		kfree(bp->ptp_cfg);
-		bp->ptp_cfg = NULL;
-	}
 	bnxt_inv_fw_health_reg(bp);
 	bnxt_dl_register(bp);

@ -13436,7 +13474,8 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
 	if (netif_running(netdev))
 		bnxt_close(netdev);

-	pci_disable_device(pdev);
+	if (pci_is_enabled(pdev))
+		pci_disable_device(pdev);
 	bnxt_free_ctx_mem(bp);
 	kfree(bp->ctx);
 	bp->ctx = NULL;
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@ -433,6 +433,7 @@ static int bnxt_hwrm_queue_dscp2pri_cfg(struct bnxt *bp, struct dcb_app *app,
 static int bnxt_ets_validate(struct bnxt *bp, struct ieee_ets *ets, u8 *tc)
 {
 	int total_ets_bw = 0;
+	bool zero = false;
 	u8 max_tc = 0;
 	int i;

@ -453,13 +454,20 @@ static int bnxt_ets_validate(struct bnxt *bp, struct ieee_ets *ets, u8 *tc)
 			break;
 		case IEEE_8021QAZ_TSA_ETS:
 			total_ets_bw += ets->tc_tx_bw[i];
+			zero = zero || !ets->tc_tx_bw[i];
 			break;
 		default:
 			return -ENOTSUPP;
 		}
 	}
-	if (total_ets_bw > 100)
+	if (total_ets_bw > 100) {
+		netdev_warn(bp->dev, "rejecting ETS config exceeding available bandwidth\n");
 		return -EINVAL;
+	}
+	if (zero && total_ets_bw == 100) {
+		netdev_warn(bp->dev, "rejecting ETS config starving a TC\n");
+		return -EINVAL;
+	}

 	if (max_tc >= bp->max_tc)
 		*tc = bp->max_tc;
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@ -385,22 +385,6 @@ int bnxt_get_rx_ts_p5(struct bnxt *bp, u64 *ts, u32 pkt_ts)
 	return 0;
 }

-void bnxt_ptp_start(struct bnxt *bp)
-{
-	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
-
-	if (!ptp)
-		return;
-
-	if (bp->flags & BNXT_FLAG_CHIP_P5) {
-		spin_lock_bh(&ptp->ptp_lock);
-		ptp->current_time = bnxt_refclk_read(bp, NULL);
-		WRITE_ONCE(ptp->old_time, ptp->current_time);
-		spin_unlock_bh(&ptp->ptp_lock);
-		ptp_schedule_worker(ptp->ptp_clock, 0);
-	}
-}
-
 static const struct ptp_clock_info bnxt_ptp_caps = {
 	.owner		= THIS_MODULE,
 	.name		= "bnxt clock",
@ -450,7 +434,13 @@ int bnxt_ptp_init(struct bnxt *bp)
 		bnxt_unmap_ptp_regs(bp);
 		return err;
 	}
-
+	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+		spin_lock_bh(&ptp->ptp_lock);
+		ptp->current_time = bnxt_refclk_read(bp, NULL);
+		WRITE_ONCE(ptp->old_time, ptp->current_time);
+		spin_unlock_bh(&ptp->ptp_lock);
+		ptp_schedule_worker(ptp->ptp_clock, 0);
+	}
 	return 0;
 }

--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
@ -75,7 +75,6 @@ int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr);
 int bnxt_hwtstamp_get(struct net_device *dev, struct ifreq *ifr);
 int bnxt_get_tx_ts_p5(struct bnxt *bp, struct sk_buff *skb);
 int bnxt_get_rx_ts_p5(struct bnxt *bp, u64 *ts, u32 pkt_ts);
-void bnxt_ptp_start(struct bnxt *bp);
 int bnxt_ptp_init(struct bnxt *bp);
 void bnxt_ptp_clear(struct bnxt *bp);
 #endif
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@ -479,16 +479,17 @@ struct bnxt_en_dev *bnxt_ulp_probe(struct net_device *dev)
 		if (!edev)
 			return ERR_PTR(-ENOMEM);
 		edev->en_ops = &bnxt_en_ops_tbl;
-		if (bp->flags & BNXT_FLAG_ROCEV1_CAP)
-			edev->flags |= BNXT_EN_FLAG_ROCEV1_CAP;
-		if (bp->flags & BNXT_FLAG_ROCEV2_CAP)
-			edev->flags |= BNXT_EN_FLAG_ROCEV2_CAP;
 		edev->net = dev;
 		edev->pdev = bp->pdev;
 		edev->l2_db_size = bp->db_size;
 		edev->l2_db_size_nc = bp->db_size;
 		bp->edev = edev;
 	}
+	edev->flags &= ~BNXT_EN_FLAG_ROCE_CAP;
+	if (bp->flags & BNXT_FLAG_ROCEV1_CAP)
+		edev->flags |= BNXT_EN_FLAG_ROCEV1_CAP;
+	if (bp->flags & BNXT_FLAG_ROCEV2_CAP)
+		edev->flags |= BNXT_EN_FLAG_ROCEV2_CAP;
 	return bp->edev;
 }
 EXPORT_SYMBOL(bnxt_ulp_probe);
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
@ -420,7 +420,7 @@ static int cn23xx_pf_setup_global_input_regs(struct octeon_device *oct)
 	 * bits 32:47 indicate the PVF num.
 	 */
 	for (q_no = 0; q_no < ern; q_no++) {
-		reg_val = oct->pcie_port << CN23XX_PKT_INPUT_CTL_MAC_NUM_POS;
+		reg_val = (u64)oct->pcie_port << CN23XX_PKT_INPUT_CTL_MAC_NUM_POS;

 		/* for VF assigned queues. */
 		if (q_no < oct->sriov_info.pf_srn) {
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
@ -2770,32 +2770,32 @@ static int dpaa2_switch_ctrl_if_setup(struct ethsw_core *ethsw)
 	if (err)
 		return err;

-	err = dpaa2_switch_seed_bp(ethsw);
-	if (err)
-		goto err_free_dpbp;
-
 	err = dpaa2_switch_alloc_rings(ethsw);
 	if (err)
-		goto err_drain_dpbp;
+		goto err_free_dpbp;

 	err = dpaa2_switch_setup_dpio(ethsw);
 	if (err)
 		goto err_destroy_rings;

+	err = dpaa2_switch_seed_bp(ethsw);
+	if (err)
+		goto err_deregister_dpio;
+
 	err = dpsw_ctrl_if_enable(ethsw->mc_io, 0, ethsw->dpsw_handle);
 	if (err) {
 		dev_err(ethsw->dev, "dpsw_ctrl_if_enable err %d\n", err);
-		goto err_deregister_dpio;
+		goto err_drain_dpbp;
 	}

 	return 0;

+err_drain_dpbp:
+	dpaa2_switch_drain_bp(ethsw);
 err_deregister_dpio:
 	dpaa2_switch_free_dpio(ethsw);
 err_destroy_rings:
 	dpaa2_switch_destroy_rings(ethsw);
-err_drain_dpbp:
-	dpaa2_switch_drain_bp(ethsw);
 err_free_dpbp:
 	dpaa2_switch_free_dpbp(ethsw);

--- a/drivers/net/ethernet/freescale/fman/mac.c
+++ b/drivers/net/ethernet/freescale/fman/mac.c
@ -524,6 +524,7 @@ static void setup_memac(struct mac_device *mac_dev)
 	| SUPPORTED_Autoneg \
 	| SUPPORTED_Pause \
 	| SUPPORTED_Asym_Pause \
+	| SUPPORTED_FIBRE \
 	| SUPPORTED_MII)

 static DEFINE_MUTEX(eth_lock);
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@ -131,7 +131,7 @@
 /* buf unit size is cache_line_size, which is 64, so the shift is 6 */
 #define PPE_BUF_SIZE_SHIFT		6
 #define PPE_TX_BUF_HOLD			BIT(31)
-#define CACHE_LINE_MASK			0x3F
+#define SOC_CACHE_LINE_MASK		0x3F
 #else
 #define PPE_CFG_QOS_VMID_GRP_SHIFT	8
 #define PPE_CFG_RX_CTRL_ALIGN_SHIFT	11
@ -531,8 +531,8 @@ hip04_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 #if defined(CONFIG_HI13X1_GMAC)
 	desc->cfg = (__force u32)cpu_to_be32(TX_CLEAR_WB | TX_FINISH_CACHE_INV
 		| TX_RELEASE_TO_PPE | priv->port << TX_POOL_SHIFT);
-	desc->data_offset = (__force u32)cpu_to_be32(phys & CACHE_LINE_MASK);
-	desc->send_addr =  (__force u32)cpu_to_be32(phys & ~CACHE_LINE_MASK);
+	desc->data_offset = (__force u32)cpu_to_be32(phys & SOC_CACHE_LINE_MASK);
+	desc->send_addr =  (__force u32)cpu_to_be32(phys & ~SOC_CACHE_LINE_MASK);
 #else
 	desc->cfg = (__force u32)cpu_to_be32(TX_CLEAR_WB | TX_FINISH_CACHE_INV);
 	desc->send_addr = (__force u32)cpu_to_be32(phys);
--- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
@ -98,6 +98,7 @@ struct hclgevf_mbx_resp_status {
 	u32 origin_mbx_msg;
 	bool received_resp;
 	int resp_status;
+	u16 match_id;
 	u8 additional_info[HCLGE_MBX_MAX_RESP_DATA_SIZE];
 };

@ -143,7 +144,8 @@ struct hclge_mbx_vf_to_pf_cmd {
 	u8 mbx_need_resp;
 	u8 rsv1[1];
 	u8 msg_len;
-	u8 rsv2[3];
+	u8 rsv2;
+	u16 match_id;
 	struct hclge_vf_to_pf_msg msg;
 };

@ -153,7 +155,8 @@ struct hclge_mbx_pf_to_vf_cmd {
 	u8 dest_vfid;
 	u8 rsv[3];
 	u8 msg_len;
-	u8 rsv1[3];
+	u8 rsv1;
+	u16 match_id;
 	struct hclge_pf_to_vf_msg msg;
 };

--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@ -9552,13 +9552,17 @@ static int hclge_set_vport_vlan_filter(struct hclge_vport *vport, bool enable)
 	if (ret)
 		return ret;

-	if (test_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B, ae_dev->caps))
+	if (test_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B, ae_dev->caps)) {
 		ret = hclge_set_port_vlan_filter_bypass(hdev, vport->vport_id,
 							!enable);
-	else if (!vport->vport_id)
+	} else if (!vport->vport_id) {
+		if (test_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, ae_dev->caps))
+			enable = false;
+
 		ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT,
 						 HCLGE_FILTER_FE_INGRESS,
 						 enable, 0);
+	}

 	return ret;
 }
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@ -47,6 +47,7 @@ static int hclge_gen_resp_to_vf(struct hclge_vport *vport,

 	resp_pf_to_vf->dest_vfid = vf_to_pf_req->mbx_src_vfid;
 	resp_pf_to_vf->msg_len = vf_to_pf_req->msg_len;
+	resp_pf_to_vf->match_id = vf_to_pf_req->match_id;

 	resp_pf_to_vf->msg.code = HCLGE_MBX_PF_VF_RESP;
 	resp_pf_to_vf->msg.vf_mbx_msg_code = vf_to_pf_req->msg.code;
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@ -2641,6 +2641,16 @@ static int hclgevf_rss_init_hw(struct hclgevf_dev *hdev)

 static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev)
 {
+	struct hnae3_handle *nic = &hdev->nic;
+	int ret;
+
+	ret = hclgevf_en_hw_strip_rxvtag(nic, true);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed to enable rx vlan offload, ret = %d\n", ret);
+		return ret;
+	}
+
 	return hclgevf_set_vlan_filter(&hdev->nic, htons(ETH_P_8021Q), 0,
 				       false);
 }
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
@ -13,6 +13,7 @@ static int hclgevf_resp_to_errno(u16 resp_code)
 	return resp_code ? -resp_code : 0;
 }

+#define HCLGEVF_MBX_MATCH_ID_START	1
 static void hclgevf_reset_mbx_resp_status(struct hclgevf_dev *hdev)
 {
 	/* this function should be called with mbx_resp.mbx_mutex held
@ -21,6 +22,10 @@ static void hclgevf_reset_mbx_resp_status(struct hclgevf_dev *hdev)
 	hdev->mbx_resp.received_resp  = false;
 	hdev->mbx_resp.origin_mbx_msg = 0;
 	hdev->mbx_resp.resp_status    = 0;
+	hdev->mbx_resp.match_id++;
+	/* Update match_id and ensure the value of match_id is not zero */
+	if (hdev->mbx_resp.match_id == 0)
+		hdev->mbx_resp.match_id = HCLGEVF_MBX_MATCH_ID_START;
 	memset(hdev->mbx_resp.additional_info, 0, HCLGE_MBX_MAX_RESP_DATA_SIZE);
 }

@ -115,6 +120,7 @@ int hclgevf_send_mbx_msg(struct hclgevf_dev *hdev,
 	if (need_resp) {
 		mutex_lock(&hdev->mbx_resp.mbx_mutex);
 		hclgevf_reset_mbx_resp_status(hdev);
+		req->match_id = hdev->mbx_resp.match_id;
 		status = hclgevf_cmd_send(&hdev->hw, &desc, 1);
 		if (status) {
 			dev_err(&hdev->pdev->dev,
@ -211,6 +217,19 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev)
 				resp->additional_info[i] = *temp;
 				temp++;
 			}
+
+			/* If match_id is not zero, it means PF support
+			 * match_id. If the match_id is right, VF get the
+			 * right response, otherwise ignore the response.
+			 * Driver will clear hdev->mbx_resp when send
+			 * next message which need response.
+			 */
+			if (req->match_id) {
+				if (req->match_id == resp->match_id)
+					resp->received_resp = true;
+			} else {
+				resp->received_resp = true;
+			}
 			break;
 		case HCLGE_MBX_LINK_STAT_CHANGE:
 		case HCLGE_MBX_ASSERTING_RESET:
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@ -1731,7 +1731,6 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 		tx_send_failed++;
 		tx_dropped++;
 		ret = NETDEV_TX_OK;
-		ibmvnic_tx_scrq_flush(adapter, tx_scrq);
 		goto out;
 	}

@ -1753,6 +1752,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 		dev_kfree_skb_any(skb);
 		tx_send_failed++;
 		tx_dropped++;
+		ibmvnic_tx_scrq_flush(adapter, tx_scrq);
 		ret = NETDEV_TX_OK;
 		goto out;
 	}
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@ -1825,7 +1825,8 @@ static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring,
 				struct sk_buff *skb)
 {
 	if (ring_uses_build_skb(rx_ring)) {
-		unsigned long offset = (unsigned long)(skb->data) & ~PAGE_MASK;
+		unsigned long mask = (unsigned long)ixgbe_rx_pg_size(rx_ring) - 1;
+		unsigned long offset = (unsigned long)(skb->data) & mask;

 		dma_sync_single_range_for_cpu(rx_ring->dev,
 					      IXGBE_CB(skb)->dma,
--- a/drivers/net/ethernet/marvell/octeontx2/af/Makefile
+++ b/drivers/net/ethernet/marvell/octeontx2/af/Makefile
@ -10,4 +10,4 @@ obj-$(CONFIG_OCTEONTX2_AF) += rvu_af.o
 rvu_mbox-y := mbox.o rvu_trace.o
 rvu_af-y := cgx.o rvu.o rvu_cgx.o rvu_npa.o rvu_nix.o \
 		  rvu_reg.o rvu_npc.o rvu_debugfs.o ptp.o rvu_npc_fs.o \
-		  rvu_cpt.o rvu_devlink.o rpm.o rvu_cn10k.o
+		  rvu_cpt.o rvu_devlink.o rpm.o rvu_cn10k.o rvu_switch.o
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@ -1314,7 +1314,7 @@ int rvu_mbox_handler_detach_resources(struct rvu *rvu,
 	return rvu_detach_rsrcs(rvu, detach, detach->hdr.pcifunc);
 }

-static int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc)
+int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc)
 {
 	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
 	int blkaddr = BLKADDR_NIX0, vf;
@ -2859,6 +2859,12 @@ static int rvu_enable_sriov(struct rvu *rvu)
 	if (!vfs)
 		return 0;

+	/* LBK channel number 63 is used for switching packets between
+	 * CGX mapped VFs. Hence limit LBK pairs till 62 only.
+	 */
+	if (vfs > 62)
+		vfs = 62;
+
 	/* Save VFs number for reference in VF interrupts handlers.
 	 * Since interrupts might start arriving during SRIOV enablement
 	 * ordinary API cannot be used to get number of enabled VFs.
@ -3001,6 +3007,8 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	/* Initialize debugfs */
 	rvu_dbg_init(rvu);

+	mutex_init(&rvu->rswitch.switch_lock);
+
 	return 0;
 err_dl:
 	rvu_unregister_dl(rvu);
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@ -415,6 +415,16 @@ struct npc_kpu_profile_adapter {
 	size_t				kpus;
 };

+#define RVU_SWITCH_LBK_CHAN	63
+
+struct rvu_switch {
+	struct mutex switch_lock; /* Serialize flow installation */
+	u32 used_entries;
+	u16 *entry2pcifunc;
+	u16 mode;
+	u16 start_entry;
+};
+
 struct rvu {
 	void __iomem		*afreg_base;
 	void __iomem		*pfreg_base;
@ -445,6 +455,7 @@ struct rvu {

 	/* CGX */
 #define PF_CGXMAP_BASE		1 /* PF 0 is reserved for RVU PF */
+	u16			cgx_mapped_vfs; /* maximum CGX mapped VFs */
 	u8			cgx_mapped_pfs;
 	u8			cgx_cnt_max;	 /* CGX port count max */
 	u8			*pf2cgxlmac_map; /* pf to cgx_lmac map */
@ -477,6 +488,9 @@ struct rvu {
 	struct rvu_debugfs	rvu_dbg;
 #endif
 	struct rvu_devlink	*rvu_dl;
+
+	/* RVU switch implementation over NPC with DMAC rules */
+	struct rvu_switch	rswitch;
 };

 static inline void rvu_write64(struct rvu *rvu, u64 block, u64 offset, u64 val)
@ -691,6 +705,7 @@ int nix_aq_context_read(struct rvu *rvu, struct nix_hw *nix_hw,
 			struct nix_cn10k_aq_enq_req *aq_req,
 			struct nix_cn10k_aq_enq_rsp *aq_rsp,
 			u16 pcifunc, u8 ctype, u32 qidx);
+int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc);

 /* NPC APIs */
 int rvu_npc_init(struct rvu *rvu);
@ -768,4 +783,10 @@ void rvu_dbg_exit(struct rvu *rvu);
 static inline void rvu_dbg_init(struct rvu *rvu) {}
 static inline void rvu_dbg_exit(struct rvu *rvu) {}
 #endif
+
+/* RVU Switch */
+void rvu_switch_enable(struct rvu *rvu);
+void rvu_switch_disable(struct rvu *rvu);
+void rvu_switch_update_rules(struct rvu *rvu, u16 pcifunc);
+
 #endif /* RVU_H */
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@ -126,6 +126,7 @@ static int rvu_map_cgx_lmac_pf(struct rvu *rvu)
 	unsigned long lmac_bmap;
 	int size, free_pkind;
 	int cgx, lmac, iter;
+	int numvfs, hwvfs;

 	if (!cgx_cnt_max)
 		return 0;
@ -166,6 +167,8 @@ static int rvu_map_cgx_lmac_pf(struct rvu *rvu)
 			pkind->pfchan_map[free_pkind] = ((pf) & 0x3F) << 16;
 			rvu_map_cgx_nix_block(rvu, pf, cgx, lmac);
 			rvu->cgx_mapped_pfs++;
+			rvu_get_pf_numvfs(rvu, pf, &numvfs, &hwvfs);
+			rvu->cgx_mapped_vfs += numvfs;
 			pf++;
 		}
 	}
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@ -2113,9 +2113,6 @@ static void rvu_print_npc_mcam_info(struct seq_file *s,
 	int entry_acnt, entry_ecnt;
 	int cntr_acnt, cntr_ecnt;

-	/* Skip PF0 */
-	if (!pcifunc)
-		return;
 	rvu_npc_get_mcam_entry_alloc_info(rvu, pcifunc, blkaddr,
 					  &entry_acnt, &entry_ecnt);
 	rvu_npc_get_mcam_counter_alloc_info(rvu, pcifunc, blkaddr,
@ -2298,7 +2295,7 @@ static void rvu_dbg_npc_mcam_show_flows(struct seq_file *s,
 static void rvu_dbg_npc_mcam_show_action(struct seq_file *s,
 					 struct rvu_npc_mcam_rule *rule)
 {
-	if (rule->intf == NIX_INTF_TX) {
+	if (is_npc_intf_tx(rule->intf)) {
 		switch (rule->tx_action.op) {
 		case NIX_TX_ACTIONOP_DROP:
 			seq_puts(s, "\taction: Drop\n");
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
@ -1364,6 +1364,44 @@ static void rvu_health_reporters_destroy(struct rvu *rvu)
 	rvu_nix_health_reporters_destroy(rvu_dl);
 }

+static int rvu_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
+{
+	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
+	struct rvu *rvu = rvu_dl->rvu;
+	struct rvu_switch *rswitch;
+
+	rswitch = &rvu->rswitch;
+	*mode = rswitch->mode;
+
+	return 0;
+}
+
+static int rvu_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
+					struct netlink_ext_ack *extack)
+{
+	struct rvu_devlink *rvu_dl = devlink_priv(devlink);
+	struct rvu *rvu = rvu_dl->rvu;
+	struct rvu_switch *rswitch;
+
+	rswitch = &rvu->rswitch;
+	switch (mode) {
+	case DEVLINK_ESWITCH_MODE_LEGACY:
+	case DEVLINK_ESWITCH_MODE_SWITCHDEV:
+		if (rswitch->mode == mode)
+			return 0;
+		rswitch->mode = mode;
+		if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV)
+			rvu_switch_enable(rvu);
+		else
+			rvu_switch_disable(rvu);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int rvu_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
 				struct netlink_ext_ack *extack)
 {
@ -1372,6 +1410,8 @@ static int rvu_devlink_info_get(struct devlink *devlink, struct devlink_info_req

 static const struct devlink_ops rvu_devlink_ops = {
 	.info_get = rvu_devlink_info_get,
+	.eswitch_mode_get = rvu_devlink_eswitch_mode_get,
+	.eswitch_mode_set = rvu_devlink_eswitch_mode_set,
 };

 int rvu_register_dl(struct rvu *rvu)
@ -1380,14 +1420,9 @@ int rvu_register_dl(struct rvu *rvu)
 	struct devlink *dl;
 	int err;

-	rvu_dl = kzalloc(sizeof(*rvu_dl), GFP_KERNEL);
-	if (!rvu_dl)
-		return -ENOMEM;
-
 	dl = devlink_alloc(&rvu_devlink_ops, sizeof(struct rvu_devlink));
 	if (!dl) {
 		dev_warn(rvu->dev, "devlink_alloc failed\n");
-		kfree(rvu_dl);
 		return -ENOMEM;
 	}

@ -1395,10 +1430,10 @@ int rvu_register_dl(struct rvu *rvu)
 	if (err) {
 		dev_err(rvu->dev, "devlink register failed with error %d\n", err);
 		devlink_free(dl);
-		kfree(rvu_dl);
 		return err;
 	}

+	rvu_dl = devlink_priv(dl);
 	rvu_dl->dl = dl;
 	rvu_dl->rvu = rvu;
 	rvu->rvu_dl = rvu_dl;
@ -1417,5 +1452,4 @@ void rvu_unregister_dl(struct rvu *rvu)
 	rvu_health_reporters_destroy(rvu);
 	devlink_unregister(dl);
 	devlink_free(dl);
-	kfree(rvu_dl);
 }
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@ -1952,6 +1952,35 @@ static void nix_tl1_default_cfg(struct rvu *rvu, struct nix_hw *nix_hw,
 	pfvf_map[schq] = TXSCH_SET_FLAG(pfvf_map[schq], NIX_TXSCHQ_CFG_DONE);
 }

+static void rvu_nix_tx_tl2_cfg(struct rvu *rvu, int blkaddr,
+			       u16 pcifunc, struct nix_txsch *txsch)
+{
+	struct rvu_hwinfo *hw = rvu->hw;
+	int lbk_link_start, lbk_links;
+	u8 pf = rvu_get_pf(pcifunc);
+	int schq;
+
+	if (!is_pf_cgxmapped(rvu, pf))
+		return;
+
+	lbk_link_start = hw->cgx_links;
+
+	for (schq = 0; schq < txsch->schq.max; schq++) {
+		if (TXSCH_MAP_FUNC(txsch->pfvf_map[schq]) != pcifunc)
+			continue;
+		/* Enable all LBK links with channel 63 by default so that
+		 * packets can be sent to LBK with a NPC TX MCAM rule
+		 */
+		lbk_links = hw->lbk_links;
+		while (lbk_links--)
+			rvu_write64(rvu, blkaddr,
+				    NIX_AF_TL3_TL2X_LINKX_CFG(schq,
+							      lbk_link_start +
+							      lbk_links),
+				    BIT_ULL(12) | RVU_SWITCH_LBK_CHAN);
+	}
+}
+
 int rvu_mbox_handler_nix_txschq_cfg(struct rvu *rvu,
 				    struct nix_txschq_config *req,
 				    struct msg_rsp *rsp)
@ -2040,6 +2069,9 @@ int rvu_mbox_handler_nix_txschq_cfg(struct rvu *rvu,
 		rvu_write64(rvu, blkaddr, reg, regval);
 	}

+	rvu_nix_tx_tl2_cfg(rvu, blkaddr, pcifunc,
+			   &nix_hw->txsch[NIX_TXSCH_LVL_TL2]);
+
 	return 0;
 }

@ -3180,6 +3212,8 @@ int rvu_mbox_handler_nix_set_mac_addr(struct rvu *rvu,
 	if (test_bit(PF_SET_VF_TRUSTED, &pfvf->flags) && from_vf)
 		ether_addr_copy(pfvf->default_mac, req->mac_addr);

+	rvu_switch_update_rules(rvu, pcifunc);
+
 	return 0;
 }

@ -3849,6 +3883,8 @@ int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req,
 	pfvf = rvu_get_pfvf(rvu, pcifunc);
 	set_bit(NIXLF_INITIALIZED, &pfvf->flags);

+	rvu_switch_update_rules(rvu, pcifunc);
+
 	return rvu_cgx_start_stop_io(rvu, pcifunc, true);
 }

--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@ -442,7 +442,8 @@ static void npc_fixup_vf_rule(struct rvu *rvu, struct npc_mcam *mcam,
 	owner = mcam->entry2pfvf_map[index];
 	target_func = (entry->action >> 4) & 0xffff;
 	/* do nothing when target is LBK/PF or owner is not PF */
-	if (is_afvf(target_func) || (owner & RVU_PFVF_FUNC_MASK) ||
+	if (is_pffunc_af(owner) || is_afvf(target_func) ||
+	    (owner & RVU_PFVF_FUNC_MASK) ||
 	    !(target_func & RVU_PFVF_FUNC_MASK))
 		return;

@ -468,6 +469,8 @@ static void npc_config_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
 {
 	int bank = npc_get_bank(mcam, index);
 	int kw = 0, actbank, actindex;
+	u8 tx_intf_mask = ~intf & 0x3;
+	u8 tx_intf = intf;
 	u64 cam0, cam1;

 	actbank = bank; /* Save bank id, to set action later on */
@ -488,12 +491,21 @@ static void npc_config_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
 	 */
 	for (; bank < (actbank + mcam->banks_per_entry); bank++, kw = kw + 2) {
 		/* Interface should be set in all banks */
+		if (is_npc_intf_tx(intf)) {
+			/* Last bit must be set and rest don't care
+			 * for TX interfaces
+			 */
+			tx_intf_mask = 0x1;
+			tx_intf = intf & tx_intf_mask;
+			tx_intf_mask = ~tx_intf & tx_intf_mask;
+		}
+
 		rvu_write64(rvu, blkaddr,
 			    NPC_AF_MCAMEX_BANKX_CAMX_INTF(index, bank, 1),
-			    intf);
+			    tx_intf);
 		rvu_write64(rvu, blkaddr,
 			    NPC_AF_MCAMEX_BANKX_CAMX_INTF(index, bank, 0),
-			    ~intf & 0x3);
+			    tx_intf_mask);

 		/* Set the match key */
 		npc_get_keyword(entry, kw, &cam0, &cam1);
@ -650,6 +662,7 @@ void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc,
 	eth_broadcast_addr((u8 *)&req.mask.dmac);
 	req.features = BIT_ULL(NPC_DMAC);
 	req.channel = chan;
+	req.chan_mask = 0xFFFU;
 	req.intf = pfvf->nix_rx_intf;
 	req.op = action.op;
 	req.hdr.pcifunc = 0; /* AF is requester */
@ -799,6 +812,7 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
 	eth_broadcast_addr((u8 *)&req.mask.dmac);
 	req.features = BIT_ULL(NPC_DMAC);
 	req.channel = chan;
+	req.chan_mask = 0xFFFU;
 	req.intf = pfvf->nix_rx_intf;
 	req.entry = index;
 	req.hdr.pcifunc = 0; /* AF is requester */
@ -1745,6 +1759,8 @@ static int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
 	int nixlf_count = rvu_get_nixlf_count(rvu);
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	int rsvd, err;
+	u16 index;
+	int cntr;
 	u64 cfg;

 	/* Actual number of MCAM entries vary by entry size */
@ -1845,6 +1861,14 @@ static int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
 	if (!mcam->entry2target_pffunc)
 		goto free_mem;

+	for (index = 0; index < mcam->bmap_entries; index++) {
+		mcam->entry2pfvf_map[index] = NPC_MCAM_INVALID_MAP;
+		mcam->entry2cntr_map[index] = NPC_MCAM_INVALID_MAP;
+	}
+
+	for (cntr = 0; cntr < mcam->counters.max; cntr++)
+		mcam->cntr2pfvf_map[cntr] = NPC_MCAM_INVALID_MAP;
+
 	mutex_init(&mcam->lock);

 	return 0;
@ -2562,7 +2586,7 @@ int rvu_mbox_handler_npc_mcam_alloc_entry(struct rvu *rvu,
 	}

 	/* Alloc request from PFFUNC with no NIXLF attached should be denied */
-	if (!is_nixlf_attached(rvu, pcifunc))
+	if (!is_pffunc_af(pcifunc) && !is_nixlf_attached(rvu, pcifunc))
 		return NPC_MCAM_ALLOC_DENIED;

 	return npc_mcam_alloc_entries(mcam, pcifunc, req, rsp);
@ -2582,7 +2606,7 @@ int rvu_mbox_handler_npc_mcam_free_entry(struct rvu *rvu,
 		return NPC_MCAM_INVALID_REQ;

 	/* Free request from PFFUNC with no NIXLF attached, ignore */
-	if (!is_nixlf_attached(rvu, pcifunc))
+	if (!is_pffunc_af(pcifunc) && !is_nixlf_attached(rvu, pcifunc))
 		return NPC_MCAM_INVALID_REQ;

 	mutex_lock(&mcam->lock);
@ -2594,7 +2618,7 @@ int rvu_mbox_handler_npc_mcam_free_entry(struct rvu *rvu,
 	if (rc)
 		goto exit;

-	mcam->entry2pfvf_map[req->entry] = 0;
+	mcam->entry2pfvf_map[req->entry] = NPC_MCAM_INVALID_MAP;
 	mcam->entry2target_pffunc[req->entry] = 0x0;
 	npc_mcam_clear_bit(mcam, req->entry);
 	npc_enable_mcam_entry(rvu, mcam, blkaddr, req->entry, false);
@ -2679,13 +2703,14 @@ int rvu_mbox_handler_npc_mcam_write_entry(struct rvu *rvu,
 	else
 		nix_intf = pfvf->nix_rx_intf;

-	if (npc_mcam_verify_channel(rvu, pcifunc, req->intf, channel)) {
+	if (!is_pffunc_af(pcifunc) &&
+	    npc_mcam_verify_channel(rvu, pcifunc, req->intf, channel)) {
 		rc = NPC_MCAM_INVALID_REQ;
 		goto exit;
 	}

-	if (npc_mcam_verify_pf_func(rvu, &req->entry_data, req->intf,
-				    pcifunc)) {
+	if (!is_pffunc_af(pcifunc) &&
+	    npc_mcam_verify_pf_func(rvu, &req->entry_data, req->intf, pcifunc)) {
 		rc = NPC_MCAM_INVALID_REQ;
 		goto exit;
 	}
@ -2836,7 +2861,7 @@ int rvu_mbox_handler_npc_mcam_alloc_counter(struct rvu *rvu,
 		return NPC_MCAM_INVALID_REQ;

 	/* If the request is from a PFFUNC with no NIXLF attached, ignore */
-	if (!is_nixlf_attached(rvu, pcifunc))
+	if (!is_pffunc_af(pcifunc) && !is_nixlf_attached(rvu, pcifunc))
 		return NPC_MCAM_INVALID_REQ;

 	/* Since list of allocated counter IDs needs to be sent to requester,
@ -3081,7 +3106,7 @@ int rvu_mbox_handler_npc_mcam_alloc_and_write_entry(struct rvu *rvu,
 	if (rc) {
 		/* Free allocated MCAM entry */
 		mutex_lock(&mcam->lock);
-		mcam->entry2pfvf_map[entry] = 0;
+		mcam->entry2pfvf_map[entry] = NPC_MCAM_INVALID_MAP;
 		npc_mcam_clear_bit(mcam, entry);
 		mutex_unlock(&mcam->lock);
 		return rc;
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
@ -910,14 +910,17 @@ static void rvu_mcam_add_counter_to_rule(struct rvu *rvu, u16 pcifunc,

 static void npc_update_rx_entry(struct rvu *rvu, struct rvu_pfvf *pfvf,
 				struct mcam_entry *entry,
-				struct npc_install_flow_req *req, u16 target)
+				struct npc_install_flow_req *req,
+				u16 target, bool pf_set_vfs_mac)
 {
+	struct rvu_switch *rswitch = &rvu->rswitch;
 	struct nix_rx_action action;
-	u64 chan_mask;

-	chan_mask = req->chan_mask ? req->chan_mask : ~0ULL;
-	npc_update_entry(rvu, NPC_CHAN, entry, req->channel, 0, chan_mask, 0,
-			 NIX_INTF_RX);
+	if (rswitch->mode == DEVLINK_ESWITCH_MODE_SWITCHDEV && pf_set_vfs_mac)
+		req->chan_mask = 0x0; /* Do not care channel */
+
+	npc_update_entry(rvu, NPC_CHAN, entry, req->channel, 0, req->chan_mask,
+			 0, NIX_INTF_RX);

 	*(u64 *)&action = 0x00;
 	action.pf_func = target;
@ -949,9 +952,16 @@ static void npc_update_tx_entry(struct rvu *rvu, struct rvu_pfvf *pfvf,
 				struct npc_install_flow_req *req, u16 target)
 {
 	struct nix_tx_action action;
+	u64 mask = ~0ULL;
+
+	/* If AF is installing then do not care about
+	 * PF_FUNC in Send Descriptor
+	 */
+	if (is_pffunc_af(req->hdr.pcifunc))
+		mask = 0;

 	npc_update_entry(rvu, NPC_PF_FUNC, entry, (__force u16)htons(target),
-			 0, ~0ULL, 0, NIX_INTF_TX);
+			 0, mask, 0, NIX_INTF_TX);

 	*(u64 *)&action = 0x00;
 	action.op = req->op;
@ -1002,7 +1012,7 @@ static int npc_install_flow(struct rvu *rvu, int blkaddr, u16 target,
 			req->intf);

 	if (is_npc_intf_rx(req->intf))
-		npc_update_rx_entry(rvu, pfvf, entry, req, target);
+		npc_update_rx_entry(rvu, pfvf, entry, req, target, pf_set_vfs_mac);
 	else
 		npc_update_tx_entry(rvu, pfvf, entry, req, target);

@ -1164,7 +1174,9 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu,
 	if (err)
 		return err;

-	if (npc_mcam_verify_channel(rvu, target, req->intf, req->channel))
+	/* Skip channel validation if AF is installing */
+	if (!is_pffunc_af(req->hdr.pcifunc) &&
+	    npc_mcam_verify_channel(rvu, target, req->intf, req->channel))
 		return -EINVAL;

 	pfvf = rvu_get_pfvf(rvu, target);
@ -1180,6 +1192,7 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu,
 		eth_broadcast_addr((u8 *)&req->mask.dmac);
 	}

+	/* Proceed if NIXLF is attached or not for TX rules */
 	err = nix_get_nixlf(rvu, target, &nixlf, NULL);
 	if (err && is_npc_intf_rx(req->intf) && !pf_set_vfs_mac)
 		return -EINVAL;
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c
@ -0,0 +1,258 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell OcteonTx2 RVU Admin Function driver
+ *
+ * Copyright (C) 2021 Marvell.
+ */
+
+#include <linux/bitfield.h>
+#include "rvu.h"
+
+static int rvu_switch_install_rx_rule(struct rvu *rvu, u16 pcifunc,
+				      u16 chan_mask)
+{
+	struct npc_install_flow_req req = { 0 };
+	struct npc_install_flow_rsp rsp = { 0 };
+	struct rvu_pfvf *pfvf;
+
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	/* If the pcifunc is not initialized then nothing to do.
+	 * This same function will be called again via rvu_switch_update_rules
+	 * after pcifunc is initialized.
+	 */
+	if (!test_bit(NIXLF_INITIALIZED, &pfvf->flags))
+		return 0;
+
+	ether_addr_copy(req.packet.dmac, pfvf->mac_addr);
+	eth_broadcast_addr((u8 *)&req.mask.dmac);
+	req.hdr.pcifunc = 0; /* AF is requester */
+	req.vf = pcifunc;
+	req.features = BIT_ULL(NPC_DMAC);
+	req.channel = pfvf->rx_chan_base;
+	req.chan_mask = chan_mask;
+	req.intf = pfvf->nix_rx_intf;
+	req.op = NIX_RX_ACTION_DEFAULT;
+	req.default_rule = 1;
+
+	return rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp);
+}
+
+static int rvu_switch_install_tx_rule(struct rvu *rvu, u16 pcifunc, u16 entry)
+{
+	struct npc_install_flow_req req = { 0 };
+	struct npc_install_flow_rsp rsp = { 0 };
+	struct rvu_pfvf *pfvf;
+	u8 lbkid;
+
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	/* If the pcifunc is not initialized then nothing to do.
+	 * This same function will be called again via rvu_switch_update_rules
+	 * after pcifunc is initialized.
+	 */
+	if (!test_bit(NIXLF_INITIALIZED, &pfvf->flags))
+		return 0;
+
+	lbkid = pfvf->nix_blkaddr == BLKADDR_NIX0 ? 0 : 1;
+	ether_addr_copy(req.packet.dmac, pfvf->mac_addr);
+	eth_broadcast_addr((u8 *)&req.mask.dmac);
+	req.hdr.pcifunc = 0; /* AF is requester */
+	req.vf = pcifunc;
+	req.entry = entry;
+	req.features = BIT_ULL(NPC_DMAC);
+	req.intf = pfvf->nix_tx_intf;
+	req.op = NIX_TX_ACTIONOP_UCAST_CHAN;
+	req.index = (lbkid << 8) | RVU_SWITCH_LBK_CHAN;
+	req.set_cntr = 1;
+
+	return rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp);
+}
+
+static int rvu_switch_install_rules(struct rvu *rvu)
+{
+	struct rvu_switch *rswitch = &rvu->rswitch;
+	u16 start = rswitch->start_entry;
+	struct rvu_hwinfo *hw = rvu->hw;
+	int pf, vf, numvfs, hwvf;
+	u16 pcifunc, entry = 0;
+	int err;
+
+	for (pf = 1; pf < hw->total_pfs; pf++) {
+		if (!is_pf_cgxmapped(rvu, pf))
+			continue;
+
+		pcifunc = pf << 10;
+		/* rvu_get_nix_blkaddr sets up the corresponding NIX block
+		 * address and NIX RX and TX interfaces for a pcifunc.
+		 * Generally it is called during attach call of a pcifunc but it
+		 * is called here since we are pre-installing rules before
+		 * nixlfs are attached
+		 */
+		rvu_get_nix_blkaddr(rvu, pcifunc);
+
+		/* MCAM RX rule for a PF/VF already exists as default unicast
+		 * rules installed by AF. Hence change the channel in those
+		 * rules to ignore channel so that packets with the required
+		 * DMAC received from LBK(by other PF/VFs in system) or from
+		 * external world (from wire) are accepted.
+		 */
+		err = rvu_switch_install_rx_rule(rvu, pcifunc, 0x0);
+		if (err) {
+			dev_err(rvu->dev, "RX rule for PF%d failed(%d)\n",
+				pf, err);
+			return err;
+		}
+
+		err = rvu_switch_install_tx_rule(rvu, pcifunc, start + entry);
+		if (err) {
+			dev_err(rvu->dev, "TX rule for PF%d failed(%d)\n",
+				pf, err);
+			return err;
+		}
+
+		rswitch->entry2pcifunc[entry++] = pcifunc;
+
+		rvu_get_pf_numvfs(rvu, pf, &numvfs, &hwvf);
+		for (vf = 0; vf < numvfs; vf++, hwvf++) {
+			pcifunc = pf << 10 | ((vf + 1) & 0x3FF);
+			rvu_get_nix_blkaddr(rvu, pcifunc);
+
+			err = rvu_switch_install_rx_rule(rvu, pcifunc, 0x0);
+			if (err) {
+				dev_err(rvu->dev,
+					"RX rule for PF%dVF%d failed(%d)\n",
+					pf, vf, err);
+				return err;
+			}
+
+			err = rvu_switch_install_tx_rule(rvu, pcifunc,
+							 start + entry);
+			if (err) {
+				dev_err(rvu->dev,
+					"TX rule for PF%dVF%d failed(%d)\n",
+					pf, vf, err);
+				return err;
+			}
+
+			rswitch->entry2pcifunc[entry++] = pcifunc;
+		}
+	}
+
+	return 0;
+}
+
+void rvu_switch_enable(struct rvu *rvu)
+{
+	struct npc_mcam_alloc_entry_req alloc_req = { 0 };
+	struct npc_mcam_alloc_entry_rsp alloc_rsp = { 0 };
+	struct npc_delete_flow_req uninstall_req = { 0 };
+	struct npc_mcam_free_entry_req free_req = { 0 };
+	struct rvu_switch *rswitch = &rvu->rswitch;
+	struct msg_rsp rsp;
+	int ret;
+
+	alloc_req.contig = true;
+	alloc_req.count = rvu->cgx_mapped_pfs + rvu->cgx_mapped_vfs;
+	ret = rvu_mbox_handler_npc_mcam_alloc_entry(rvu, &alloc_req,
+						    &alloc_rsp);
+	if (ret) {
+		dev_err(rvu->dev,
+			"Unable to allocate MCAM entries\n");
+		goto exit;
+	}
+
+	if (alloc_rsp.count != alloc_req.count) {
+		dev_err(rvu->dev,
+			"Unable to allocate %d MCAM entries, got %d\n",
+			alloc_req.count, alloc_rsp.count);
+		goto free_entries;
+	}
+
+	rswitch->entry2pcifunc = kcalloc(alloc_req.count, sizeof(u16),
+					 GFP_KERNEL);
+	if (!rswitch->entry2pcifunc)
+		goto free_entries;
+
+	rswitch->used_entries = alloc_rsp.count;
+	rswitch->start_entry = alloc_rsp.entry;
+
+	ret = rvu_switch_install_rules(rvu);
+	if (ret)
+		goto uninstall_rules;
+
+	return;
+
+uninstall_rules:
+	uninstall_req.start = rswitch->start_entry;
+	uninstall_req.end =  rswitch->start_entry + rswitch->used_entries - 1;
+	rvu_mbox_handler_npc_delete_flow(rvu, &uninstall_req, &rsp);
+	kfree(rswitch->entry2pcifunc);
+free_entries:
+	free_req.all = 1;
+	rvu_mbox_handler_npc_mcam_free_entry(rvu, &free_req, &rsp);
+exit:
+	return;
+}
+
+void rvu_switch_disable(struct rvu *rvu)
+{
+	struct npc_delete_flow_req uninstall_req = { 0 };
+	struct npc_mcam_free_entry_req free_req = { 0 };
+	struct rvu_switch *rswitch = &rvu->rswitch;
+	struct rvu_hwinfo *hw = rvu->hw;
+	int pf, vf, numvfs, hwvf;
+	struct msg_rsp rsp;
+	u16 pcifunc;
+	int err;
+
+	if (!rswitch->used_entries)
+		return;
+
+	for (pf = 1; pf < hw->total_pfs; pf++) {
+		if (!is_pf_cgxmapped(rvu, pf))
+			continue;
+
+		pcifunc = pf << 10;
+		err = rvu_switch_install_rx_rule(rvu, pcifunc, 0xFFF);
+		if (err)
+			dev_err(rvu->dev,
+				"Reverting RX rule for PF%d failed(%d)\n",
+				pf, err);
+
+		for (vf = 0; vf < numvfs; vf++, hwvf++) {
+			pcifunc = pf << 10 | ((vf + 1) & 0x3FF);
+			err = rvu_switch_install_rx_rule(rvu, pcifunc, 0xFFF);
+			if (err)
+				dev_err(rvu->dev,
+					"Reverting RX rule for PF%dVF%d failed(%d)\n",
+					pf, vf, err);
+		}
+	}
+
+	uninstall_req.start = rswitch->start_entry;
+	uninstall_req.end =  rswitch->start_entry + rswitch->used_entries - 1;
+	free_req.all = 1;
+	rvu_mbox_handler_npc_delete_flow(rvu, &uninstall_req, &rsp);
+	rvu_mbox_handler_npc_mcam_free_entry(rvu, &free_req, &rsp);
+	rswitch->used_entries = 0;
+	kfree(rswitch->entry2pcifunc);
+}
+
+void rvu_switch_update_rules(struct rvu *rvu, u16 pcifunc)
+{
+	struct rvu_switch *rswitch = &rvu->rswitch;
+	u32 max = rswitch->used_entries;
+	u16 entry;
+
+	if (!rswitch->used_entries)
+		return;
+
+	for (entry = 0; entry < max; entry++) {
+		if (rswitch->entry2pcifunc[entry] == pcifunc)
+			break;
+	}
+
+	if (entry >= max)
+		return;
+
+	rvu_switch_install_tx_rule(rvu, pcifunc, rswitch->start_entry + entry);
+	rvu_switch_install_rx_rule(rvu, pcifunc, 0x0);
+}
--- a/drivers/net/ethernet/microchip/sparx5/Kconfig
+++ b/drivers/net/ethernet/microchip/sparx5/Kconfig
@ -3,6 +3,7 @@ config SPARX5_SWITCH
 	depends on NET_SWITCHDEV
 	depends on HAS_IOMEM
 	depends on OF
+	depends on ARCH_SPARX5 || COMPILE_TEST
 	select PHYLINK
 	select PHY_SPARX5_SERDES
 	select RESET_CONTROLLER
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@ -5084,7 +5084,8 @@ static int r8169_mdio_register(struct rtl8169_private *tp)
 	new_bus->priv = tp;
 	new_bus->parent = &pdev->dev;
 	new_bus->irq[0] = PHY_MAC_INTERRUPT;
-	snprintf(new_bus->id, MII_BUS_ID_SIZE, "r8169-%x", pci_dev_id(pdev));
+	snprintf(new_bus->id, MII_BUS_ID_SIZE, "r8169-%x-%x",
+		 pci_domain_nr(pdev->bus), pci_dev_id(pdev));

 	new_bus->read = r8169_mdio_read_reg;
 	new_bus->write = r8169_mdio_write_reg;
--- a/drivers/net/ethernet/renesas/ravb.h
+++ b/drivers/net/ethernet/renesas/ravb.h
@ -864,7 +864,7 @@ enum GECMR_BIT {

 /* The Ethernet AVB descriptor definitions. */
 struct ravb_desc {
-	__le16 ds;		/* Descriptor size */
+	__le16 ds;	/* Descriptor size */
 	u8 cc;		/* Content control MSBs (reserved) */
 	u8 die_dt;	/* Descriptor interrupt enable and type */
 	__le32 dptr;	/* Descriptor pointer */
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@ -920,7 +920,7 @@ static int ravb_poll(struct napi_struct *napi, int budget)
 	if (ravb_rx(ndev, &quota, q))
 		goto out;

-	/* Processing RX Descriptor Ring */
+	/* Processing TX Descriptor Ring */
 	spin_lock_irqsave(&priv->lock, flags);
 	/* Clear TX interrupt */
 	ravb_write(ndev, ~(mask | TIS_RESERVED), TIS);
--- a/drivers/net/ethernet/xscale/ptp_ixp46x.c
+++ b/drivers/net/ethernet/xscale/ptp_ixp46x.c
@ -14,6 +14,8 @@
 #include <linux/kernel.h>
 #include <linux/ptp_clock_kernel.h>
 #include <linux/soc/ixp4xx/cpu.h>
+#include <linux/module.h>
+#include <mach/ixp4xx-regs.h>

 #include "ixp46x_ts.h"

--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@ -2495,7 +2495,7 @@ static struct hso_device *hso_create_net_device(struct usb_interface *interface,
 			   hso_net_init);
 	if (!net) {
 		dev_err(&interface->dev, "Unable to create ethernet device\n");
-		goto exit;
+		goto err_hso_dev;
 	}

 	hso_net = netdev_priv(net);
@ -2508,13 +2508,13 @@ static struct hso_device *hso_create_net_device(struct usb_interface *interface,
 				      USB_DIR_IN);
 	if (!hso_net->in_endp) {
 		dev_err(&interface->dev, "Can't find BULK IN endpoint\n");
-		goto exit;
+		goto err_net;
 	}
 	hso_net->out_endp = hso_get_ep(interface, USB_ENDPOINT_XFER_BULK,
 				       USB_DIR_OUT);
 	if (!hso_net->out_endp) {
 		dev_err(&interface->dev, "Can't find BULK OUT endpoint\n");
-		goto exit;
+		goto err_net;
 	}
 	SET_NETDEV_DEV(net, &interface->dev);
 	SET_NETDEV_DEVTYPE(net, &hso_type);
@ -2523,18 +2523,18 @@ static struct hso_device *hso_create_net_device(struct usb_interface *interface,
 	for (i = 0; i < MUX_BULK_RX_BUF_COUNT; i++) {
 		hso_net->mux_bulk_rx_urb_pool[i] = usb_alloc_urb(0, GFP_KERNEL);
 		if (!hso_net->mux_bulk_rx_urb_pool[i])
-			goto exit;
+			goto err_mux_bulk_rx;
 		hso_net->mux_bulk_rx_buf_pool[i] = kzalloc(MUX_BULK_RX_BUF_SIZE,
 							   GFP_KERNEL);
 		if (!hso_net->mux_bulk_rx_buf_pool[i])
-			goto exit;
+			goto err_mux_bulk_rx;
 	}
 	hso_net->mux_bulk_tx_urb = usb_alloc_urb(0, GFP_KERNEL);
 	if (!hso_net->mux_bulk_tx_urb)
-		goto exit;
+		goto err_mux_bulk_rx;
 	hso_net->mux_bulk_tx_buf = kzalloc(MUX_BULK_TX_BUF_SIZE, GFP_KERNEL);
 	if (!hso_net->mux_bulk_tx_buf)
-		goto exit;
+		goto err_free_tx_urb;

 	add_net_device(hso_dev);

@ -2542,7 +2542,7 @@ static struct hso_device *hso_create_net_device(struct usb_interface *interface,
 	result = register_netdev(net);
 	if (result) {
 		dev_err(&interface->dev, "Failed to register device\n");
-		goto exit;
+		goto err_free_tx_buf;
 	}

 	hso_log_port(hso_dev);
@ -2550,8 +2550,21 @@ static struct hso_device *hso_create_net_device(struct usb_interface *interface,
 	hso_create_rfkill(hso_dev, interface);

 	return hso_dev;
-exit:
-	hso_free_net_device(hso_dev, true);
+
+err_free_tx_buf:
+	remove_net_device(hso_dev);
+	kfree(hso_net->mux_bulk_tx_buf);
+err_free_tx_urb:
+	usb_free_urb(hso_net->mux_bulk_tx_urb);
+err_mux_bulk_rx:
+	for (i = 0; i < MUX_BULK_RX_BUF_COUNT; i++) {
+		usb_free_urb(hso_net->mux_bulk_rx_urb_pool[i]);
+		kfree(hso_net->mux_bulk_rx_buf_pool[i]);
+	}
+err_net:
+	free_netdev(net);
+err_hso_dev:
+	kfree(hso_dev);
 	return NULL;
 }

--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@ -1552,7 +1552,8 @@ static int
 rtl8152_set_speed(struct r8152 *tp, u8 autoneg, u32 speed, u8 duplex,
 		  u32 advertising);

-static int rtl8152_set_mac_address(struct net_device *netdev, void *p)
+static int __rtl8152_set_mac_address(struct net_device *netdev, void *p,
+				     bool in_resume)
 {
 	struct r8152 *tp = netdev_priv(netdev);
 	struct sockaddr *addr = p;
@ -1561,9 +1562,11 @@ static int rtl8152_set_mac_address(struct net_device *netdev, void *p)
 	if (!is_valid_ether_addr(addr->sa_data))
 		goto out1;

-	ret = usb_autopm_get_interface(tp->intf);
-	if (ret < 0)
-		goto out1;
+	if (!in_resume) {
+		ret = usb_autopm_get_interface(tp->intf);
+		if (ret < 0)
+			goto out1;
+	}

 	mutex_lock(&tp->control);

@ -1575,11 +1578,17 @@ static int rtl8152_set_mac_address(struct net_device *netdev, void *p)

 	mutex_unlock(&tp->control);

-	usb_autopm_put_interface(tp->intf);
+	if (!in_resume)
+		usb_autopm_put_interface(tp->intf);
 out1:
 	return ret;
 }

+static int rtl8152_set_mac_address(struct net_device *netdev, void *p)
+{
+	return __rtl8152_set_mac_address(netdev, p, false);
+}
+
 /* Devices containing proper chips can support a persistent
 * host system provided MAC address.
 * Examples of this are Dell TB15 and Dell WD15 docks
@ -1698,7 +1707,7 @@ static int determine_ethernet_addr(struct r8152 *tp, struct sockaddr *sa)
 	return ret;
 }

-static int set_ethernet_addr(struct r8152 *tp)
+static int set_ethernet_addr(struct r8152 *tp, bool in_resume)
 {
 	struct net_device *dev = tp->netdev;
 	struct sockaddr sa;
@ -1711,7 +1720,7 @@ static int set_ethernet_addr(struct r8152 *tp)
 	if (tp->version == RTL_VER_01)
 		ether_addr_copy(dev->dev_addr, sa.sa_data);
 	else
-		ret = rtl8152_set_mac_address(dev, &sa);
+		ret = __rtl8152_set_mac_address(dev, &sa, in_resume);

 	return ret;
 }
@ -6763,10 +6772,11 @@ static int rtl8152_close(struct net_device *netdev)
 		tp->rtl_ops.down(tp);

 		mutex_unlock(&tp->control);
-
-		usb_autopm_put_interface(tp->intf);
 	}

+	if (!res)
+		usb_autopm_put_interface(tp->intf);
+
 	free_all_mem(tp);

 	return res;
@ -8443,7 +8453,7 @@ static int rtl8152_reset_resume(struct usb_interface *intf)
 	clear_bit(SELECTIVE_SUSPEND, &tp->flags);
 	tp->rtl_ops.init(tp);
 	queue_delayed_work(system_long_wq, &tp->hw_phy_work, 0);
-	set_ethernet_addr(tp);
+	set_ethernet_addr(tp, true);
 	return rtl8152_resume(intf);
 }

@ -9644,7 +9654,7 @@ static int rtl8152_probe(struct usb_interface *intf,
 	tp->rtl_fw.retry = true;
 #endif
 	queue_delayed_work(system_long_wq, &tp->hw_phy_work, 0);
-	set_ethernet_addr(tp);
+	set_ethernet_addr(tp, false);

 	usb_set_intfdata(intf, tp);

--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@ -1709,7 +1709,6 @@ struct tcp_fastopen_context {
 	struct rcu_head	rcu;
 };

-extern unsigned int sysctl_tcp_fastopen_blackhole_timeout;
 void tcp_fastopen_active_disable(struct sock *sk);
 bool tcp_fastopen_active_should_disable(struct sock *sk);
 void tcp_fastopen_active_disable_ofo_check(struct sock *sk);
--- a/include/trace/events/net.h
+++ b/include/trace/events/net.h
@ -136,7 +136,7 @@ DECLARE_EVENT_CLASS(net_dev_template,
 		__assign_str(name, skb->dev->name);
 	),

-	TP_printk("dev=%s skbaddr=%p len=%u",
+	TP_printk("dev=%s skbaddr=%px len=%u",
 		__get_str(name), __entry->skbaddr, __entry->len)
 )

--- a/include/trace/events/qdisc.h
+++ b/include/trace/events/qdisc.h
@ -41,11 +41,37 @@ TRACE_EVENT(qdisc_dequeue,
 		__entry->txq_state	= txq->state;
 	),

-	TP_printk("dequeue ifindex=%d qdisc handle=0x%X parent=0x%X txq_state=0x%lX packets=%d skbaddr=%p",
+	TP_printk("dequeue ifindex=%d qdisc handle=0x%X parent=0x%X txq_state=0x%lX packets=%d skbaddr=%px",
 		  __entry->ifindex, __entry->handle, __entry->parent,
 		  __entry->txq_state, __entry->packets, __entry->skbaddr )
 );

+TRACE_EVENT(qdisc_enqueue,
+
+	TP_PROTO(struct Qdisc *qdisc, const struct netdev_queue *txq, struct sk_buff *skb),
+
+	TP_ARGS(qdisc, txq, skb),
+
+	TP_STRUCT__entry(
+		__field(struct Qdisc *, qdisc)
+		__field(void *,	skbaddr)
+		__field(int, ifindex)
+		__field(u32, handle)
+		__field(u32, parent)
+	),
+
+	TP_fast_assign(
+		__entry->qdisc = qdisc;
+		__entry->skbaddr = skb;
+		__entry->ifindex = txq->dev ? txq->dev->ifindex : 0;
+		__entry->handle	 = qdisc->handle;
+		__entry->parent	 = qdisc->parent;
+	),
+
+	TP_printk("enqueue ifindex=%d qdisc handle=0x%X parent=0x%X skbaddr=%px",
+		  __entry->ifindex, __entry->handle, __entry->parent, __entry->skbaddr)
+);
+
 TRACE_EVENT(qdisc_reset,

 	TP_PROTO(struct Qdisc *q),
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@ -3677,6 +3677,8 @@ continue_func:
 	if (tail_call_reachable)
 		for (j = 0; j < frame; j++)
 			subprog[ret_prog[j]].tail_call_reachable = true;
+	if (subprog[0].tail_call_reachable)
+		env->prog->aux->tail_call_reachable = true;

 	/* end of for() loop means the last insn of the 'subprog'
 	 * was reached. Doesn't matter whether it was JA or EXIT
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@ -701,6 +701,9 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 	void *data;
 	int ret;

+	if (prog->expected_attach_type == BPF_XDP_DEVMAP ||
+	    prog->expected_attach_type == BPF_XDP_CPUMAP)
+		return -EINVAL;
 	if (kattr->test.ctx_in || kattr->test.ctx_out)
 		return -EINVAL;

--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@ -780,7 +780,7 @@ int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev,
 		struct net_device *dst_dev;

 		dst_dev = dst ? dst->dev : br->dev;
-		if (dst_dev != br_dev && dst_dev != dev)
+		if (dst_dev && dst_dev != dev)
 			continue;

 		err = br_fdb_replay_one(nb, fdb, dst_dev, action, ctx);
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@ -539,7 +539,8 @@ static int caif_seqpkt_sendmsg(struct socket *sock, struct msghdr *msg,
 		goto err;

 	ret = -EINVAL;
-	if (unlikely(msg->msg_iter.iov->iov_base == NULL))
+	if (unlikely(msg->msg_iter.nr_segs == 0) ||
+	    unlikely(msg->msg_iter.iov->iov_base == NULL))
 		goto err;
 	noblock = msg->msg_flags & MSG_DONTWAIT;

--- a/net/core/dev.c
+++ b/net/core/dev.c
@ -131,6 +131,7 @@
 #include <trace/events/napi.h>
 #include <trace/events/net.h>
 #include <trace/events/skb.h>
+#include <trace/events/qdisc.h>
 #include <linux/inetdevice.h>
 #include <linux/cpu_rmap.h>
 #include <linux/static_key.h>
@ -3844,6 +3845,18 @@ static void qdisc_pkt_len_init(struct sk_buff *skb)
 	}
 }

+static int dev_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *q,
+			     struct sk_buff **to_free,
+			     struct netdev_queue *txq)
+{
+	int rc;
+
+	rc = q->enqueue(skb, q, to_free) & NET_XMIT_MASK;
+	if (rc == NET_XMIT_SUCCESS)
+		trace_qdisc_enqueue(q, txq, skb);
+	return rc;
+}
+
 static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 				 struct net_device *dev,
 				 struct netdev_queue *txq)
@ -3862,8 +3875,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 			 * of q->seqlock to protect from racing with requeuing.
 			 */
 			if (unlikely(!nolock_qdisc_is_empty(q))) {
-				rc = q->enqueue(skb, q, &to_free) &
-					NET_XMIT_MASK;
+				rc = dev_qdisc_enqueue(skb, q, &to_free, txq);
 				__qdisc_run(q);
 				qdisc_run_end(q);

@ -3879,7 +3891,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 			return NET_XMIT_SUCCESS;
 		}

-		rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
+		rc = dev_qdisc_enqueue(skb, q, &to_free, txq);
 		qdisc_run(q);

 no_lock_out:
@ -3923,7 +3935,7 @@ no_lock_out:
 		qdisc_run_end(q);
 		rc = NET_XMIT_SUCCESS;
 	} else {
-		rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
+		rc = dev_qdisc_enqueue(skb, q, &to_free, txq);
 		if (qdisc_run_begin(q)) {
 			if (unlikely(contended)) {
 				spin_unlock(&q->busylock);
@ -9700,14 +9712,17 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 	struct net_device *dev;
 	int err, fd;

+	rtnl_lock();
 	dev = dev_get_by_index(net, attr->link_create.target_ifindex);
-	if (!dev)
+	if (!dev) {
+		rtnl_unlock();
 		return -EINVAL;
+	}

 	link = kzalloc(sizeof(*link), GFP_USER);
 	if (!link) {
 		err = -ENOMEM;
-		goto out_put_dev;
+		goto unlock;
 	}

 	bpf_link_init(&link->link, BPF_LINK_TYPE_XDP, &bpf_xdp_link_lops, prog);
@ -9717,14 +9732,14 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 	err = bpf_link_prime(&link->link, &link_primer);
 	if (err) {
 		kfree(link);
-		goto out_put_dev;
+		goto unlock;
 	}

-	rtnl_lock();
 	err = dev_xdp_attach_link(dev, NULL, link);
 	rtnl_unlock();

 	if (err) {
+		link->dev = NULL;
 		bpf_link_cleanup(&link_primer);
 		goto out_put_dev;
 	}
@ -9734,6 +9749,9 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 	dev_put(dev);
 	return fd;

+unlock:
+	rtnl_unlock();
+
 out_put_dev:
 	dev_put(dev);
 	return err;
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@ -663,7 +663,7 @@ static void skb_release_data(struct sk_buff *skb)
 	if (skb->cloned &&
 	    atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1,
 			      &shinfo->dataref))
-		return;
+		goto exit;

 	skb_zcopy_clear(skb, true);

@ -674,6 +674,17 @@ static void skb_release_data(struct sk_buff *skb)
 		kfree_skb_list(shinfo->frag_list);

 	skb_free_head(skb);
+exit:
+	/* When we clone an SKB we copy the reycling bit. The pp_recycle
+	 * bit is only set on the head though, so in order to avoid races
+	 * while trying to recycle fragments on __skb_frag_unref() we need
+	 * to make one SKB responsible for triggering the recycle path.
+	 * So disable the recycling bit if an SKB is cloned and we have
+	 * additional references to to the fragmented part of the SKB.
+	 * Eventually the last SKB will have the recycling bit set and it's
+	 * dataref set to 0, which will trigger the recycling
+	 */
+	skb->pp_recycle = 0;
 }

 /*
@ -3011,8 +3022,11 @@ skb_zerocopy_headlen(const struct sk_buff *from)

 	if (!from->head_frag ||
 	    skb_headlen(from) < L1_CACHE_BYTES ||
-	    skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS)
+	    skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) {
 		hlen = skb_headlen(from);
+		if (!hlen)
+			hlen = from->len;
+	}

 	if (skb_has_frag_list(from))
 		hlen = from->len;
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@ -508,10 +508,8 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
 	if (skb_linearize(skb))
 		return -EAGAIN;
 	num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len);
-	if (unlikely(num_sge < 0)) {
-		kfree(msg);
+	if (unlikely(num_sge < 0))
 		return num_sge;
-	}

 	copied = skb->len;
 	msg->sg.start = 0;
@ -530,6 +528,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
 {
 	struct sock *sk = psock->sk;
 	struct sk_msg *msg;
+	int err;

 	/* If we are receiving on the same sock skb->sk is already assigned,
 	 * skip memory accounting and owner transition seeing it already set
@ -548,7 +547,10 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
 	 * into user buffers.
 	 */
 	skb_set_owner_r(skb, sk);
-	return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+	err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+	if (err < 0)
+		kfree(msg);
+	return err;
 }

 /* Puts an skb on the ingress queue of the socket already assigned to the
@ -559,12 +561,16 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb
 {
 	struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC);
 	struct sock *sk = psock->sk;
+	int err;

 	if (unlikely(!msg))
 		return -EAGAIN;
 	sk_msg_init(msg);
 	skb_set_owner_r(skb, sk);
-	return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+	err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+	if (err < 0)
+		kfree(msg);
+	return err;
 }

 static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@ -816,7 +816,7 @@ static int dn_auto_bind(struct socket *sock)
 static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation)
 {
 	struct dn_scp *scp = DN_SK(sk);
-	DEFINE_WAIT(wait);
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	int err;

 	if (scp->state != DN_CR)
@ -826,11 +826,11 @@ static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation)
 	scp->segsize_loc = dst_metric_advmss(__sk_dst_get(sk));
 	dn_send_conn_conf(sk, allocation);

-	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+	add_wait_queue(sk_sleep(sk), &wait);
 	for(;;) {
 		release_sock(sk);
 		if (scp->state == DN_CC)
-			*timeo = schedule_timeout(*timeo);
+			*timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo);
 		lock_sock(sk);
 		err = 0;
 		if (scp->state == DN_RUN)
@ -844,9 +844,8 @@ static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation)
 		err = -EAGAIN;
 		if (!*timeo)
 			break;
-		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 	}
-	finish_wait(sk_sleep(sk), &wait);
+	remove_wait_queue(sk_sleep(sk), &wait);
 	if (err == 0) {
 		sk->sk_socket->state = SS_CONNECTED;
 	} else if (scp->state != DN_CC) {
@ -858,7 +857,7 @@ static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation)
 static int dn_wait_run(struct sock *sk, long *timeo)
 {
 	struct dn_scp *scp = DN_SK(sk);
-	DEFINE_WAIT(wait);
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	int err = 0;

 	if (scp->state == DN_RUN)
@ -867,11 +866,11 @@ static int dn_wait_run(struct sock *sk, long *timeo)
 	if (!*timeo)
 		return -EALREADY;

-	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+	add_wait_queue(sk_sleep(sk), &wait);
 	for(;;) {
 		release_sock(sk);
 		if (scp->state == DN_CI || scp->state == DN_CC)
-			*timeo = schedule_timeout(*timeo);
+			*timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo);
 		lock_sock(sk);
 		err = 0;
 		if (scp->state == DN_RUN)
@ -885,9 +884,8 @@ static int dn_wait_run(struct sock *sk, long *timeo)
 		err = -ETIMEDOUT;
 		if (!*timeo)
 			break;
-		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 	}
-	finish_wait(sk_sleep(sk), &wait);
+	remove_wait_queue(sk_sleep(sk), &wait);
 out:
 	if (err == 0) {
 		sk->sk_socket->state = SS_CONNECTED;
@ -1032,16 +1030,16 @@ static void dn_user_copy(struct sk_buff *skb, struct optdata_dn *opt)

 static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo)
 {
-	DEFINE_WAIT(wait);
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	struct sk_buff *skb = NULL;
 	int err = 0;

-	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+	add_wait_queue(sk_sleep(sk), &wait);
 	for(;;) {
 		release_sock(sk);
 		skb = skb_dequeue(&sk->sk_receive_queue);
 		if (skb == NULL) {
-			*timeo = schedule_timeout(*timeo);
+			*timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo);
 			skb = skb_dequeue(&sk->sk_receive_queue);
 		}
 		lock_sock(sk);
@ -1056,9 +1054,8 @@ static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo)
 		err = -EAGAIN;
 		if (!*timeo)
 			break;
-		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 	}
-	finish_wait(sk_sleep(sk), &wait);
+	remove_wait_queue(sk_sleep(sk), &wait);

 	return skb == NULL ? ERR_PTR(err) : skb;
 }
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@ -1808,6 +1808,7 @@ void dsa_slave_setup_tagger(struct net_device *slave)
 	struct dsa_slave_priv *p = netdev_priv(slave);
 	const struct dsa_port *cpu_dp = dp->cpu_dp;
 	struct net_device *master = cpu_dp->master;
+	const struct dsa_switch *ds = dp->ds;

 	slave->needed_headroom = cpu_dp->tag_ops->needed_headroom;
 	slave->needed_tailroom = cpu_dp->tag_ops->needed_tailroom;
@ -1819,6 +1820,14 @@ void dsa_slave_setup_tagger(struct net_device *slave)
 	slave->needed_tailroom += master->needed_tailroom;

 	p->xmit = cpu_dp->tag_ops->xmit;
+
+	slave->features = master->vlan_features | NETIF_F_HW_TC;
+	if (ds->ops->port_vlan_add && ds->ops->port_vlan_del)
+		slave->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+	slave->hw_features |= NETIF_F_HW_TC;
+	slave->features |= NETIF_F_LLTX;
+	if (slave->needed_tailroom)
+		slave->features &= ~(NETIF_F_SG | NETIF_F_FRAGLIST);
 }

 static struct lock_class_key dsa_slave_netdev_xmit_lock_key;
@ -1881,11 +1890,6 @@ int dsa_slave_create(struct dsa_port *port)
 	if (slave_dev == NULL)
 		return -ENOMEM;

-	slave_dev->features = master->vlan_features | NETIF_F_HW_TC;
-	if (ds->ops->port_vlan_add && ds->ops->port_vlan_del)
-		slave_dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
-	slave_dev->hw_features |= NETIF_F_HW_TC;
-	slave_dev->features |= NETIF_F_LLTX;
 	slave_dev->ethtool_ops = &dsa_slave_ethtool_ops;
 	if (!is_zero_ether_addr(port->mac))
 		ether_addr_copy(slave_dev->dev_addr, port->mac);
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@ -53,6 +53,9 @@ static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev)
 	u8 *tag;
 	u8 *addr;

+	if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb))
+		return NULL;
+
 	/* Tag encoding */
 	tag = skb_put(skb, KSZ_INGRESS_TAG_LEN);
 	addr = skb_mac_header(skb);
@ -114,6 +117,9 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb,
 	u8 *addr;
 	u16 val;

+	if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb))
+		return NULL;
+
 	/* Tag encoding */
 	tag = skb_put(skb, KSZ9477_INGRESS_TAG_LEN);
 	addr = skb_mac_header(skb);
@ -164,6 +170,9 @@ static struct sk_buff *ksz9893_xmit(struct sk_buff *skb,
 	u8 *addr;
 	u8 *tag;

+	if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb))
+		return NULL;
+
 	/* Tag encoding */
 	tag = skb_put(skb, KSZ_INGRESS_TAG_LEN);
 	addr = skb_mac_header(skb);
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@ -503,7 +503,7 @@ static int __init tcp_bpf_v4_build_proto(void)
 	tcp_bpf_rebuild_protos(tcp_bpf_prots[TCP_BPF_IPV4], &tcp_prot);
 	return 0;
 }
-core_initcall(tcp_bpf_v4_build_proto);
+late_initcall(tcp_bpf_v4_build_proto);

 static int tcp_bpf_assert_proto_ops(struct proto *ops)
 {
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@ -507,8 +507,18 @@ void tcp_fastopen_active_disable(struct sock *sk)
 {
 	struct net *net = sock_net(sk);

+	if (!sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout)
+		return;
+
+	/* Paired with READ_ONCE() in tcp_fastopen_active_should_disable() */
+	WRITE_ONCE(net->ipv4.tfo_active_disable_stamp, jiffies);
+
+	/* Paired with smp_rmb() in tcp_fastopen_active_should_disable().
+	 * We want net->ipv4.tfo_active_disable_stamp to be updated first.
+	 */
+	smp_mb__before_atomic();
 	atomic_inc(&net->ipv4.tfo_active_disable_times);
-	net->ipv4.tfo_active_disable_stamp = jiffies;
+
 	NET_INC_STATS(net, LINUX_MIB_TCPFASTOPENBLACKHOLE);
 }

@ -519,17 +529,27 @@ void tcp_fastopen_active_disable(struct sock *sk)
 bool tcp_fastopen_active_should_disable(struct sock *sk)
 {
 	unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout;
-	int tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times);
 	unsigned long timeout;
+	int tfo_da_times;
 	int multiplier;

+	if (!tfo_bh_timeout)
+		return false;
+
+	tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times);
 	if (!tfo_da_times)
 		return false;

+	/* Paired with smp_mb__before_atomic() in tcp_fastopen_active_disable() */
+	smp_rmb();
+
 	/* Limit timeout to max: 2^6 * initial timeout */
 	multiplier = 1 << min(tfo_da_times - 1, 6);
-	timeout = multiplier * tfo_bh_timeout * HZ;
-	if (time_before(jiffies, sock_net(sk)->ipv4.tfo_active_disable_stamp + timeout))
+
+	/* Paired with the WRITE_ONCE() in tcp_fastopen_active_disable(). */
+	timeout = READ_ONCE(sock_net(sk)->ipv4.tfo_active_disable_stamp) +
+		  multiplier * tfo_bh_timeout * HZ;
+	if (time_before(jiffies, timeout))
 		return true;

 	/* Mark check bit so we can check for successful active TFO
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@ -2965,7 +2965,7 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_comp_sack_nr = 44;
 	net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE;
 	spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock);
-	net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 60 * 60;
+	net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 0;
 	atomic_set(&net->ipv4.tfo_active_disable_times, 0);

 	/* Reno is always built in */
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@ -645,10 +645,12 @@ static struct sock *__udp4_lib_err_encap(struct net *net,
 					 const struct iphdr *iph,
 					 struct udphdr *uh,
 					 struct udp_table *udptable,
+					 struct sock *sk,
 					 struct sk_buff *skb, u32 info)
 {
+	int (*lookup)(struct sock *sk, struct sk_buff *skb);
 	int network_offset, transport_offset;
-	struct sock *sk;
+	struct udp_sock *up;

 	network_offset = skb_network_offset(skb);
 	transport_offset = skb_transport_offset(skb);
@ -659,18 +661,28 @@ static struct sock *__udp4_lib_err_encap(struct net *net,
 	/* Transport header needs to point to the UDP header */
 	skb_set_transport_header(skb, iph->ihl << 2);

+	if (sk) {
+		up = udp_sk(sk);
+
+		lookup = READ_ONCE(up->encap_err_lookup);
+		if (lookup && lookup(sk, skb))
+			sk = NULL;
+
+		goto out;
+	}
+
 	sk = __udp4_lib_lookup(net, iph->daddr, uh->source,
 			       iph->saddr, uh->dest, skb->dev->ifindex, 0,
 			       udptable, NULL);
 	if (sk) {
-		int (*lookup)(struct sock *sk, struct sk_buff *skb);
-		struct udp_sock *up = udp_sk(sk);
+		up = udp_sk(sk);

 		lookup = READ_ONCE(up->encap_err_lookup);
 		if (!lookup || lookup(sk, skb))
 			sk = NULL;
 	}

+out:
 	if (!sk)
 		sk = ERR_PTR(__udp4_lib_err_encap_no_sk(skb, info));

@ -707,15 +719,16 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 	sk = __udp4_lib_lookup(net, iph->daddr, uh->dest,
 			       iph->saddr, uh->source, skb->dev->ifindex,
 			       inet_sdif(skb), udptable, NULL);
+
 	if (!sk || udp_sk(sk)->encap_type) {
 		/* No socket for error: try tunnels before discarding */
-		sk = ERR_PTR(-ENOENT);
 		if (static_branch_unlikely(&udp_encap_needed_key)) {
-			sk = __udp4_lib_err_encap(net, iph, uh, udptable, skb,
+			sk = __udp4_lib_err_encap(net, iph, uh, udptable, sk, skb,
 						  info);
 			if (!sk)
 				return 0;
-		}
+		} else
+			sk = ERR_PTR(-ENOENT);

 		if (IS_ERR(sk)) {
 			__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@ -134,7 +134,7 @@ static int __init udp_bpf_v4_build_proto(void)
 	udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV4], &udp_prot);
 	return 0;
 }
-core_initcall(udp_bpf_v4_build_proto);
+late_initcall(udp_bpf_v4_build_proto);

 int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
 {
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@ -74,7 +74,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *

 			if (likely(nskb)) {
 				if (skb->sk)
-					skb_set_owner_w(skb, skb->sk);
+					skb_set_owner_w(nskb, skb->sk);
 				consume_skb(skb);
 			} else {
 				kfree_skb(skb);
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@ -3769,7 +3769,7 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 		err = PTR_ERR(rt->fib6_metrics);
 		/* Do not leave garbage there. */
 		rt->fib6_metrics = (struct dst_metrics *)&dst_default_metrics;
-		goto out;
+		goto out_free;
 	}

 	if (cfg->fc_flags & RTF_ADDRCONF)
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@ -502,12 +502,14 @@ static struct sock *__udp6_lib_err_encap(struct net *net,
 					 const struct ipv6hdr *hdr, int offset,
 					 struct udphdr *uh,
 					 struct udp_table *udptable,
+					 struct sock *sk,
 					 struct sk_buff *skb,
 					 struct inet6_skb_parm *opt,
 					 u8 type, u8 code, __be32 info)
 {
+	int (*lookup)(struct sock *sk, struct sk_buff *skb);
 	int network_offset, transport_offset;
-	struct sock *sk;
+	struct udp_sock *up;

 	network_offset = skb_network_offset(skb);
 	transport_offset = skb_transport_offset(skb);
@ -518,18 +520,28 @@ static struct sock *__udp6_lib_err_encap(struct net *net,
 	/* Transport header needs to point to the UDP header */
 	skb_set_transport_header(skb, offset);

+	if (sk) {
+		up = udp_sk(sk);
+
+		lookup = READ_ONCE(up->encap_err_lookup);
+		if (lookup && lookup(sk, skb))
+			sk = NULL;
+
+		goto out;
+	}
+
 	sk = __udp6_lib_lookup(net, &hdr->daddr, uh->source,
 			       &hdr->saddr, uh->dest,
 			       inet6_iif(skb), 0, udptable, skb);
 	if (sk) {
-		int (*lookup)(struct sock *sk, struct sk_buff *skb);
-		struct udp_sock *up = udp_sk(sk);
+		up = udp_sk(sk);

 		lookup = READ_ONCE(up->encap_err_lookup);
 		if (!lookup || lookup(sk, skb))
 			sk = NULL;
 	}

+out:
 	if (!sk) {
 		sk = ERR_PTR(__udp6_lib_err_encap_no_sk(skb, opt, type, code,
 							offset, info));
@ -558,16 +570,17 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,

 	sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source,
 			       inet6_iif(skb), inet6_sdif(skb), udptable, NULL);
+
 	if (!sk || udp_sk(sk)->encap_type) {
 		/* No socket for error: try tunnels before discarding */
-		sk = ERR_PTR(-ENOENT);
 		if (static_branch_unlikely(&udpv6_encap_needed_key)) {
 			sk = __udp6_lib_err_encap(net, hdr, offset, uh,
-						  udptable, skb,
+						  udptable, sk, skb,
 						  opt, type, code, info);
 			if (!sk)
 				return 0;
-		}
+		} else
+			sk = ERR_PTR(-ENOENT);

 		if (IS_ERR(sk)) {
 			__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
--- a/net/netrom/nr_timer.c
+++ b/net/netrom/nr_timer.c
@ -121,11 +121,9 @@ static void nr_heartbeat_expiry(struct timer_list *t)
 		   is accepted() it isn't 'dead' so doesn't get removed. */
 		if (sock_flag(sk, SOCK_DESTROY) ||
 		    (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) {
-			sock_hold(sk);
 			bh_unlock_sock(sk);
 			nr_destroy_socket(sk);
-			sock_put(sk);
-			return;
+			goto out;
 		}
 		break;

@ -146,6 +144,8 @@ static void nr_heartbeat_expiry(struct timer_list *t)

 	nr_start_heartbeat(sk);
 	bh_unlock_sock(sk);
+out:
+	sock_put(sk);
 }

 static void nr_t2timer_expiry(struct timer_list *t)
@ -159,6 +159,7 @@ static void nr_t2timer_expiry(struct timer_list *t)
 		nr_enquiry_response(sk);
 	}
 	bh_unlock_sock(sk);
+	sock_put(sk);
 }

 static void nr_t4timer_expiry(struct timer_list *t)
@ -169,6 +170,7 @@ static void nr_t4timer_expiry(struct timer_list *t)
 	bh_lock_sock(sk);
 	nr_sk(sk)->condition &= ~NR_COND_PEER_RX_BUSY;
 	bh_unlock_sock(sk);
+	sock_put(sk);
 }

 static void nr_idletimer_expiry(struct timer_list *t)
@ -197,6 +199,7 @@ static void nr_idletimer_expiry(struct timer_list *t)
 		sock_set_flag(sk, SOCK_DEAD);
 	}
 	bh_unlock_sock(sk);
+	sock_put(sk);
 }

 static void nr_t1timer_expiry(struct timer_list *t)
@ -209,8 +212,7 @@ static void nr_t1timer_expiry(struct timer_list *t)
 	case NR_STATE_1:
 		if (nr->n2count == nr->n2) {
 			nr_disconnect(sk, ETIMEDOUT);
-			bh_unlock_sock(sk);
-			return;
+			goto out;
 		} else {
 			nr->n2count++;
 			nr_write_internal(sk, NR_CONNREQ);
@ -220,8 +222,7 @@ static void nr_t1timer_expiry(struct timer_list *t)
 	case NR_STATE_2:
 		if (nr->n2count == nr->n2) {
 			nr_disconnect(sk, ETIMEDOUT);
-			bh_unlock_sock(sk);
-			return;
+			goto out;
 		} else {
 			nr->n2count++;
 			nr_write_internal(sk, NR_DISCREQ);
@ -231,8 +232,7 @@ static void nr_t1timer_expiry(struct timer_list *t)
 	case NR_STATE_3:
 		if (nr->n2count == nr->n2) {
 			nr_disconnect(sk, ETIMEDOUT);
-			bh_unlock_sock(sk);
-			return;
+			goto out;
 		} else {
 			nr->n2count++;
 			nr_requeue_frames(sk);
@ -241,5 +241,7 @@ static void nr_t1timer_expiry(struct timer_list *t)
 	}

 	nr_start_t1timer(sk);
+out:
 	bh_unlock_sock(sk);
+	sock_put(sk);
 }
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@ -6,6 +6,7 @@
 */

 #include <linux/module.h>
+#include <linux/if_arp.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/skbuff.h>
@ -33,6 +34,13 @@ static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a,
 	tcf_lastuse_update(&d->tcf_tm);
 	bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb);

+	action = READ_ONCE(d->tcf_action);
+	if (unlikely(action == TC_ACT_SHOT))
+		goto drop;
+
+	if (!skb->dev || skb->dev->type != ARPHRD_ETHER)
+		return action;
+
 	/* XXX: if you are going to edit more fields beyond ethernet header
 	 * (example when you add IP header replacement or vlan swap)
 	 * then MAX_EDIT_LEN needs to change appropriately
@ -41,10 +49,6 @@ static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a,
 	if (unlikely(err)) /* best policy is to drop on the floor */
 		goto drop;

-	action = READ_ONCE(d->tcf_action);
-	if (unlikely(action == TC_ACT_SHOT))
-		goto drop;
-
 	p = rcu_dereference_bh(d->skbmod_p);
 	flags = p->flags;
 	if (flags & SKBMOD_F_DMAC)
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@ -2904,7 +2904,7 @@ replay:
 		break;
 	case RTM_GETCHAIN:
 		err = tc_chain_notify(chain, skb, n->nlmsg_seq,
-				      n->nlmsg_seq, n->nlmsg_type, true);
+				      n->nlmsg_flags, n->nlmsg_type, true);
 		if (err < 0)
 			NL_SET_ERR_MSG(extack, "Failed to send chain notify message");
 		break;
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@ -278,6 +278,8 @@ static int tcindex_filter_result_init(struct tcindex_filter_result *r,
 			     TCA_TCINDEX_POLICE);
 }

+static void tcindex_free_perfect_hash(struct tcindex_data *cp);
+
 static void tcindex_partial_destroy_work(struct work_struct *work)
 {
 	struct tcindex_data *p = container_of(to_rcu_work(work),
@ -285,7 +287,8 @@ static void tcindex_partial_destroy_work(struct work_struct *work)
 					      rwork);

 	rtnl_lock();
-	kfree(p->perfect);
+	if (p->perfect)
+		tcindex_free_perfect_hash(p);
 	kfree(p);
 	rtnl_unlock();
 }
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@ -860,6 +860,8 @@ int sctp_auth_set_key(struct sctp_endpoint *ep,
 	if (replace) {
 		list_del_init(&shkey->key_list);
 		sctp_auth_shkey_release(shkey);
+		if (asoc && asoc->active_key_id == auth_key->sca_keynumber)
+			sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL);
 	}
 	list_add(&cur_key->key_list, sh_keys);

--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@ -104,8 +104,8 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag,
 		if (asoc->param_flags & SPP_PMTUD_ENABLE)
 			sctp_assoc_sync_pmtu(asoc);
 	} else if (!sctp_transport_pl_enabled(tp) &&
-		   !sctp_transport_pmtu_check(tp)) {
-		if (asoc->param_flags & SPP_PMTUD_ENABLE)
+		   asoc->param_flags & SPP_PMTUD_ENABLE) {
+		if (!sctp_transport_pmtu_check(tp))
 			sctp_assoc_sync_pmtu(asoc);
 	}

--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@ -4577,6 +4577,10 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
 	}

 	if (optlen > 0) {
+		/* Trim it to the biggest size sctp sockopt may need if necessary */
+		optlen = min_t(unsigned int, optlen,
+			       PAGE_ALIGN(USHRT_MAX +
+					  sizeof(__u16) * sizeof(struct sctp_reset_streams)));
 		kopt = memdup_sockptr(optval, optlen);
 		if (IS_ERR(kopt))
 			return PTR_ERR(kopt);
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@ -222,6 +222,11 @@ int mount_bpffs_for_pin(const char *name)
 	int err = 0;

 	file = malloc(strlen(name) + 1);
+	if (!file) {
+		p_err("mem alloc failed");
+		return -1;
+	}
+
 	strcpy(file, name);
 	dir = dirname(file);

--- a/tools/testing/selftests/net/nettest.c
+++ b/tools/testing/selftests/net/nettest.c
@ -11,9 +11,11 @@
 #include <sys/socket.h>
 #include <sys/wait.h>
 #include <linux/tcp.h>
+#include <linux/udp.h>
 #include <arpa/inet.h>
 #include <net/if.h>
 #include <netinet/in.h>
+#include <netinet/ip.h>
 #include <netdb.h>
 #include <fcntl.h>
 #include <libgen.h>
@ -27,6 +29,10 @@
 #include <time.h>
 #include <errno.h>

+#include <linux/xfrm.h>
+#include <linux/ipsec.h>
+#include <linux/pfkeyv2.h>
+
 #ifndef IPV6_UNICAST_IF
 #define IPV6_UNICAST_IF         76
 #endif
@ -114,6 +120,9 @@ struct sock_args {
 		struct in_addr  in;
 		struct in6_addr in6;
 	} expected_raddr;
+
+	/* ESP in UDP encap test */
+	int use_xfrm;
 };

 static int server_mode;
@ -1346,6 +1355,41 @@ static int bind_socket(int sd, struct sock_args *args)
 	return 0;
 }

+static int config_xfrm_policy(int sd, struct sock_args *args)
+{
+	struct xfrm_userpolicy_info policy = {};
+	int type = UDP_ENCAP_ESPINUDP;
+	int xfrm_af = IP_XFRM_POLICY;
+	int level = SOL_IP;
+
+	if (args->type != SOCK_DGRAM) {
+		log_error("Invalid socket type. Only DGRAM could be used for XFRM\n");
+		return 1;
+	}
+
+	policy.action = XFRM_POLICY_ALLOW;
+	policy.sel.family = args->version;
+	if (args->version == AF_INET6) {
+		xfrm_af = IPV6_XFRM_POLICY;
+		level = SOL_IPV6;
+	}
+
+	policy.dir = XFRM_POLICY_OUT;
+	if (setsockopt(sd, level, xfrm_af, &policy, sizeof(policy)) < 0)
+		return 1;
+
+	policy.dir = XFRM_POLICY_IN;
+	if (setsockopt(sd, level, xfrm_af, &policy, sizeof(policy)) < 0)
+		return 1;
+
+	if (setsockopt(sd, IPPROTO_UDP, UDP_ENCAP, &type, sizeof(type)) < 0) {
+		log_err_errno("Failed to set xfrm encap");
+		return 1;
+	}
+
+	return 0;
+}
+
 static int lsock_init(struct sock_args *args)
 {
 	long flags;
@ -1389,6 +1433,11 @@ static int lsock_init(struct sock_args *args)
 	if (fcntl(sd, F_SETFD, FD_CLOEXEC) < 0)
 		log_err_errno("Failed to set close-on-exec flag");

+	if (args->use_xfrm && config_xfrm_policy(sd, args)) {
+		log_err_errno("Failed to set xfrm policy");
+		goto err;
+	}
+
 out:
 	return sd;

@ -1772,7 +1821,7 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args)
 	return client_status;
 }

-#define GETOPT_STR  "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6L:0:1:2:3:Fbq"
+#define GETOPT_STR  "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6xL:0:1:2:3:Fbq"

 static void print_usage(char *prog)
 {
@ -1795,6 +1844,7 @@ static void print_usage(char *prog)
 	"    -D|R          datagram (D) / raw (R) socket (default stream)\n"
 	"    -l addr       local address to bind to in server mode\n"
 	"    -c addr       local address to bind to in client mode\n"
+	"    -x            configure XFRM policy on socket\n"
 	"\n"
 	"    -d dev        bind socket to given device name\n"
 	"    -I dev        bind socket to given device name - server mode\n"
@ -1966,6 +2016,9 @@ int main(int argc, char *argv[])
 		case 'q':
 			quiet = 1;
 			break;
+		case 'x':
+			args.use_xfrm = 1;
+			break;
 		default:
 			print_usage(argv[0]);
 			return 1;
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@ -118,6 +118,16 @@
 #	below for IPv6 doesn't apply here, because, on IPv4, administrative MTU
 #	changes alone won't affect PMTU
 #
+# - pmtu_vti4_udp_exception
+#       Same as pmtu_vti4_exception, but using ESP-in-UDP
+#
+# - pmtu_vti4_udp_routed_exception
+#       Set up vti tunnel on top of veth connected through routing namespace and
+#	add xfrm states and policies with ESP-in-UDP encapsulation. Check that
+#	route exception is not created if link layer MTU is not exceeded, then
+#	lower MTU on second part of routed environment and check that exception
+#	is created with the expected PMTU.
+#
 # - pmtu_vti6_exception
 #	Set up vti6 tunnel on top of veth, with xfrm states and policies, in two
 #	namespaces with matching endpoints. Check that route exception is
@ -125,6 +135,13 @@
 #	decrease and increase MTU of tunnel, checking that route exception PMTU
 #	changes accordingly
 #
+# - pmtu_vti6_udp_exception
+#       Same as pmtu_vti6_exception, but using ESP-in-UDP
+#
+# - pmtu_vti6_udp_routed_exception
+#	Same as pmtu_vti6_udp_routed_exception but with routing between vti
+#	endpoints
+#
 # - pmtu_vti4_default_mtu
 #	Set up vti4 tunnel on top of veth, in two namespaces with matching
 #	endpoints. Check that MTU assigned to vti interface is the MTU of the
@ -224,6 +241,10 @@ tests="
 	pmtu_ipv6_ipv6_exception	IPv6 over IPv6: PMTU exceptions		1
 	pmtu_vti6_exception		vti6: PMTU exceptions			0
 	pmtu_vti4_exception		vti4: PMTU exceptions			0
+	pmtu_vti6_udp_exception		vti6: PMTU exceptions (ESP-in-UDP)	0
+	pmtu_vti4_udp_exception		vti4: PMTU exceptions (ESP-in-UDP)	0
+	pmtu_vti6_udp_routed_exception	vti6: PMTU exceptions, routed (ESP-in-UDP)	0
+	pmtu_vti4_udp_routed_exception	vti4: PMTU exceptions, routed (ESP-in-UDP)	0
 	pmtu_vti4_default_mtu		vti4: default MTU assignment		0
 	pmtu_vti6_default_mtu		vti6: default MTU assignment		0
 	pmtu_vti4_link_add_mtu		vti4: MTU setting on link creation	0
@ -246,7 +267,6 @@ ns_b="ip netns exec ${NS_B}"
 ns_c="ip netns exec ${NS_C}"
 ns_r1="ip netns exec ${NS_R1}"
 ns_r2="ip netns exec ${NS_R2}"
-
 # Addressing and routing for tests with routers: four network segments, with
 # index SEGMENT between 1 and 4, a common prefix (PREFIX4 or PREFIX6) and an
 # identifier ID, which is 1 for hosts (A and B), 2 for routers (R1 and R2).
@ -279,7 +299,6 @@ routes="
 	A	${prefix6}:${b_r2}::1	${prefix6}:${a_r2}::2
 	B	default			${prefix6}:${b_r1}::2
 "
-
 USE_NH="no"
 #	ns	family	nh id	   destination		gateway
 nexthops="
@ -326,6 +345,7 @@ dummy6_mask="64"

 err_buf=
 tcpdump_pids=
+nettest_pids=

 err() {
 	err_buf="${err_buf}${1}
@ -548,6 +568,14 @@ setup_vti6() {
 	setup_vti 6 ${veth6_a_addr} ${veth6_b_addr} ${tunnel6_a_addr} ${tunnel6_b_addr} ${tunnel6_mask}
 }

+setup_vti4routed() {
+	setup_vti 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 ${tunnel4_a_addr} ${tunnel4_b_addr} ${tunnel4_mask}
+}
+
+setup_vti6routed() {
+	setup_vti 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 ${tunnel6_a_addr} ${tunnel6_b_addr} ${tunnel6_mask}
+}
+
 setup_vxlan_or_geneve() {
 	type="${1}"
 	a_addr="${2}"
@ -619,18 +647,36 @@ setup_xfrm() {
 	proto=${1}
 	veth_a_addr="${2}"
 	veth_b_addr="${3}"
+	encap=${4}

-	run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel || return 1
-	run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
+	run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap} || return 1
+	run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap}
 	run_cmd ${ns_a} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel
 	run_cmd ${ns_a} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel

-	run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
-	run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
+	run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap}
+	run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap}
 	run_cmd ${ns_b} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel
 	run_cmd ${ns_b} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel
 }

+setup_nettest_xfrm() {
+	which nettest >/dev/null
+	if [ $? -ne 0 ]; then
+		echo "'nettest' command not found; skipping tests"
+	        return 1
+	fi
+
+	[ ${1} -eq 6 ] && proto="-6" || proto=""
+	port=${2}
+
+	run_cmd ${ns_a} nettest ${proto} -q -D -s -x -p ${port} -t 5 &
+	nettest_pids="${nettest_pids} $!"
+
+	run_cmd ${ns_b} nettest ${proto} -q -D -s -x -p ${port} -t 5 &
+	nettest_pids="${nettest_pids} $!"
+}
+
 setup_xfrm4() {
 	setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr}
 }
@ -639,6 +685,26 @@ setup_xfrm6() {
 	setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr}
 }

+setup_xfrm4udp() {
+	setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} "encap espinudp 4500 4500 0.0.0.0"
+	setup_nettest_xfrm 4 4500
+}
+
+setup_xfrm6udp() {
+	setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} "encap espinudp 4500 4500 0.0.0.0"
+	setup_nettest_xfrm 6 4500
+}
+
+setup_xfrm4udprouted() {
+	setup_xfrm 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "encap espinudp 4500 4500 0.0.0.0"
+	setup_nettest_xfrm 4 4500
+}
+
+setup_xfrm6udprouted() {
+	setup_xfrm 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "encap espinudp 4500 4500 0.0.0.0"
+	setup_nettest_xfrm 6 4500
+}
+
 setup_routing_old() {
 	for i in ${routes}; do
 		[ "${ns}" = "" ]	&& ns="${i}"		&& continue
@ -823,6 +889,11 @@ cleanup() {
 	done
 	tcpdump_pids=

+	for pid in ${nettest_pids}; do
+		kill ${pid}
+	done
+	nettest_pids=
+
 	for n in ${NS_A} ${NS_B} ${NS_C} ${NS_R1} ${NS_R2}; do
 		ip netns del ${n} 2> /dev/null
 	done
@ -1432,6 +1503,135 @@ test_pmtu_vti6_exception() {
 	return ${fail}
 }

+test_pmtu_vti4_udp_exception() {
+	setup namespaces veth vti4 xfrm4udp || return $ksft_skip
+	trace "${ns_a}" veth_a    "${ns_b}" veth_b \
+	      "${ns_a}" vti4_a    "${ns_b}" vti4_b
+
+	veth_mtu=1500
+	vti_mtu=$((veth_mtu - 20))
+
+	#                                UDP   SPI   SN   IV  ICV   pad length   next header
+	esp_payload_rfc4106=$((vti_mtu - 8   - 4   - 4  - 8 - 16  - 1          - 1))
+	ping_payload=$((esp_payload_rfc4106 - 28))
+
+	mtu "${ns_a}" veth_a ${veth_mtu}
+	mtu "${ns_b}" veth_b ${veth_mtu}
+	mtu "${ns_a}" vti4_a ${vti_mtu}
+	mtu "${ns_b}" vti4_b ${vti_mtu}
+
+	# Send DF packet without exceeding link layer MTU, check that no
+	# exception is created
+	run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel4_b_addr}
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
+	check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1
+
+	# Now exceed link layer MTU by one byte, check that exception is created
+	# with the right PMTU value
+	run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((ping_payload + 1)) ${tunnel4_b_addr}
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
+	check_pmtu_value "${esp_payload_rfc4106}" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106 + 1)))"
+}
+
+test_pmtu_vti6_udp_exception() {
+	setup namespaces veth vti6 xfrm6udp || return $ksft_skip
+	trace "${ns_a}" veth_a    "${ns_b}" veth_b \
+	      "${ns_a}" vti6_a    "${ns_b}" vti6_b
+	fail=0
+
+	# Create route exception by exceeding link layer MTU
+	mtu "${ns_a}" veth_a 4000
+	mtu "${ns_b}" veth_b 4000
+	mtu "${ns_a}" vti6_a 5000
+	mtu "${ns_b}" vti6_b 5000
+	run_cmd ${ns_a} ${ping6} -q -i 0.1 -w 1 -s 60000 ${tunnel6_b_addr}
+
+	# Check that exception was created
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+	check_pmtu_value any "${pmtu}" "creating tunnel exceeding link layer MTU" || return 1
+
+	# Decrease tunnel MTU, check for PMTU decrease in route exception
+	mtu "${ns_a}" vti6_a 3000
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+	check_pmtu_value "3000" "${pmtu}" "decreasing tunnel MTU" || fail=1
+
+	# Increase tunnel MTU, check for PMTU increase in route exception
+	mtu "${ns_a}" vti6_a 9000
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+	check_pmtu_value "9000" "${pmtu}" "increasing tunnel MTU" || fail=1
+
+	return ${fail}
+}
+
+test_pmtu_vti4_udp_routed_exception() {
+	setup namespaces routing vti4routed xfrm4udprouted || return $ksft_skip
+	trace "${ns_a}" veth_A-R1    "${ns_b}" veth_B-R1 \
+	      "${ns_a}" vti4_a       "${ns_b}" vti4_b
+
+	veth_mtu=1500
+	vti_mtu=$((veth_mtu - 20))
+
+	#                                UDP   SPI   SN   IV  ICV   pad length   next header
+	esp_payload_rfc4106=$((vti_mtu - 8   - 4   - 4  - 8 - 16  - 1          - 1))
+	ping_payload=$((esp_payload_rfc4106 - 28))
+
+        mtu "${ns_a}"  veth_A-R1 ${veth_mtu}
+        mtu "${ns_r1}" veth_R1-A ${veth_mtu}
+        mtu "${ns_b}"  veth_B-R1 ${veth_mtu}
+        mtu "${ns_r1}" veth_R1-B ${veth_mtu}
+
+	mtu "${ns_a}" vti4_a ${vti_mtu}
+	mtu "${ns_b}" vti4_b ${vti_mtu}
+
+	# Send DF packet without exceeding link layer MTU, check that no
+	# exception is created
+	run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel4_b_addr}
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
+	check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1
+
+	# Now decrease link layer MTU by 8 bytes on R1, check that exception is created
+	# with the right PMTU value
+        mtu "${ns_r1}" veth_R1-B $((veth_mtu - 8))
+	run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((ping_payload)) ${tunnel4_b_addr}
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
+	check_pmtu_value "$((esp_payload_rfc4106 - 8))" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106)))"
+}
+
+test_pmtu_vti6_udp_routed_exception() {
+	setup namespaces routing vti6routed xfrm6udprouted || return $ksft_skip
+	trace "${ns_a}" veth_A-R1    "${ns_b}" veth_B-R1 \
+	      "${ns_a}" vti6_a       "${ns_b}" vti6_b
+
+	veth_mtu=1500
+	vti_mtu=$((veth_mtu - 40))
+
+	#                                UDP   SPI   SN   IV  ICV   pad length   next header
+	esp_payload_rfc4106=$((vti_mtu - 8   - 4   - 4  - 8 - 16  - 1          - 1))
+	ping_payload=$((esp_payload_rfc4106 - 48))
+
+        mtu "${ns_a}"  veth_A-R1 ${veth_mtu}
+        mtu "${ns_r1}" veth_R1-A ${veth_mtu}
+        mtu "${ns_b}"  veth_B-R1 ${veth_mtu}
+        mtu "${ns_r1}" veth_R1-B ${veth_mtu}
+
+	# mtu "${ns_a}" vti6_a ${vti_mtu}
+	# mtu "${ns_b}" vti6_b ${vti_mtu}
+
+	run_cmd ${ns_a} ${ping6} -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel6_b_addr}
+
+	# Check that exception was not created
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+	check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1
+
+	# Now decrease link layer MTU by 8 bytes on R1, check that exception is created
+	# with the right PMTU value
+        mtu "${ns_r1}" veth_R1-B $((veth_mtu - 8))
+	run_cmd ${ns_a} ${ping6} -q -M want -i 0.1 -w 1 -s $((ping_payload)) ${tunnel6_b_addr}
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+	check_pmtu_value "$((esp_payload_rfc4106 - 8))" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106)))"
+
+}
+
 test_pmtu_vti4_default_mtu() {
 	setup namespaces veth vti4 || return $ksft_skip