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

Pull networking updates from David Miller:

 1) Unified UDP encapsulation offload methods for drivers, from
    Alexander Duyck.

 2) Make DSA binding more sane, from Andrew Lunn.

 3) Support QCA9888 chips in ath10k, from Anilkumar Kolli.

 4) Several workqueue usage cleanups, from Bhaktipriya Shridhar.

 5) Add XDP (eXpress Data Path), essentially running BPF programs on RX
    packets as soon as the device sees them, with the option to mirror
    the packet on TX via the same interface.  From Brenden Blanco and
    others.

 6) Allow qdisc/class stats dumps to run lockless, from Eric Dumazet.

 7) Add VLAN support to b53 and bcm_sf2, from Florian Fainelli.

 8) Simplify netlink conntrack entry layout, from Florian Westphal.

 9) Add ipv4 forwarding support to mlxsw spectrum driver, from Ido
    Schimmel, Yotam Gigi, and Jiri Pirko.

10) Add SKB array infrastructure and convert tun and macvtap over to it.
    From Michael S Tsirkin and Jason Wang.

11) Support qdisc packet injection in pktgen, from John Fastabend.

12) Add neighbour monitoring framework to TIPC, from Jon Paul Maloy.

13) Add NV congestion control support to TCP, from Lawrence Brakmo.

14) Add GSO support to SCTP, from Marcelo Ricardo Leitner.

15) Allow GRO and RPS to function on macsec devices, from Paolo Abeni.

16) Support MPLS over IPV4, from Simon Horman.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1622 commits)
  xgene: Fix build warning with ACPI disabled.
  be2net: perform temperature query in adapter regardless of its interface state
  l2tp: Correctly return -EBADF from pppol2tp_getname.
  net/mlx5_core/health: Remove deprecated create_singlethread_workqueue
  net: ipmr/ip6mr: update lastuse on entry change
  macsec: ensure rx_sa is set when validation is disabled
  tipc: dump monitor attributes
  tipc: add a function to get the bearer name
  tipc: get monitor threshold for the cluster
  tipc: make cluster size threshold for monitoring configurable
  tipc: introduce constants for tipc address validation
  net: neigh: disallow transition to NUD_STALE if lladdr is unchanged in neigh_update()
  MAINTAINERS: xgene: Add driver and documentation path
  Documentation: dtb: xgene: Add MDIO node
  dtb: xgene: Add MDIO node
  drivers: net: xgene: ethtool: Use phy_ethtool_gset and sset
  drivers: net: xgene: Use exported functions
  drivers: net: xgene: Enable MDIO driver
  drivers: net: xgene: Add backward compatibility
  drivers: net: phy: xgene: Add MDIO driver
  ...

16 files changed, 382 insertions, 202 deletions

diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 52be48bbd2dd..7fa295155543 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -766,7 +766,6 @@
 			ale_entries = <1024>;
 			bd_ram_size = <0x2000>;
 			no_bd_ram = <0>;
-			rx_descs = <64>;
 			mac_control = <0x20>;
 			slaves = <2>;
 			active_slave = <0>;
@@ -789,7 +788,7 @@
 			status = "disabled";
 
 			davinci_mdio: mdio@4a101000 {
-				compatible = "ti,davinci_mdio";
+				compatible = "ti,cpsw-mdio","ti,davinci_mdio";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				ti,hwmods = "davinci_mdio";
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index 12fcde4d4d2e..cd81ecf12731 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -626,7 +626,6 @@
 			ale_entries = <1024>;
 			bd_ram_size = <0x2000>;
 			no_bd_ram = <0>;
-			rx_descs = <64>;
 			mac_control = <0x20>;
 			slaves = <2>;
 			active_slave = <0>;
@@ -636,7 +635,7 @@
 			syscon = <&scm_conf>;
 
 			davinci_mdio: mdio@4a101000 {
-				compatible = "ti,am4372-mdio","ti,davinci_mdio";
+				compatible = "ti,am4372-mdio","ti,cpsw-mdio","ti,davinci_mdio";
 				reg = <0x4a101000 0x100>;
 				#address-cells = <1>;
 				#size-cells = <0>;
diff --git a/arch/arm/boot/dts/dm814x.dtsi b/arch/arm/boot/dts/dm814x.dtsi
index d4537dc61497..f23cae0c2179 100644
--- a/arch/arm/boot/dts/dm814x.dtsi
+++ b/arch/arm/boot/dts/dm814x.dtsi
@@ -509,7 +509,6 @@
 			ale_entries = <1024>;
 			bd_ram_size = <0x2000>;
 			no_bd_ram = <0>;
-			rx_descs = <64>;
 			mac_control = <0x20>;
 			slaves = <2>;
 			active_slave = <0>;
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index 3a8f3976f6f9..de559f6e4fee 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -1628,7 +1628,6 @@
 			ale_entries = <1024>;
 			bd_ram_size = <0x2000>;
 			no_bd_ram = <0>;
-			rx_descs = <64>;
 			mac_control = <0x20>;
 			slaves = <2>;
 			active_slave = <0>;
@@ -1663,7 +1662,7 @@
 			status = "disabled";
 
 			davinci_mdio: mdio@48485000 {
-				compatible = "ti,davinci_mdio";
+				compatible = "ti,cpsw-mdio","ti,davinci_mdio";
 				#address-cells = <1>;
 				#size-cells = <0>;
 				ti,hwmods = "davinci_mdio";
diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi
index 3b44ef3cff12..3ebee530f2b0 100644
--- a/arch/arm/boot/dts/rk3288.dtsi
+++ b/arch/arm/boot/dts/rk3288.dtsi
@@ -539,8 +539,9 @@
 	gmac: ethernet@ff290000 {
 		compatible = "rockchip,rk3288-gmac";
 		reg = <0xff290000 0x10000>;
-		interrupts = <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>;
-		interrupt-names = "macirq";
+		interrupts = <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>,
+				<GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "macirq", "eth_wake_irq";
 		rockchip,grf = <&grf>;
 		clocks = <&cru SCLK_MAC>,
 			<&cru SCLK_MAC_RX>, <&cru SCLK_MAC_TX>,
diff --git a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
index 6c60b7f91104..5c1fcab4a6f7 100644
--- a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
+++ b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
@@ -85,187 +85,199 @@
 			reg = <1>;
 			#address-cells = <1>;
 			#size-cells = <0>;
+
+			switch0: switch0@0 {
+				compatible = "marvell,mv88e6085";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <0>;
+				dsa,member = <0 0>;
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					port@0 {
+						reg = <0>;
+						label = "lan0";
+					};
+
+					port@1 {
+						reg = <1>;
+						label = "lan1";
+					};
+
+					port@2 {
+						reg = <2>;
+						label = "lan2";
+					};
+
+					switch0port5: port@5 {
+						reg = <5>;
+						label = "dsa";
+						phy-mode = "rgmii-txid";
+						link = <&switch1port6
+							&switch2port9>;
+						fixed-link {
+							speed = <1000>;
+							full-duplex;
+						};
+					};
+
+					port@6 {
+						reg = <6>;
+						label = "cpu";
+						ethernet = <&fec1>;
+						fixed-link {
+							speed = <100>;
+							full-duplex;
+						};
+					};
+				};
+			};
 		};
 
 		mdio_mux_2: mdio@2 {
 			reg = <2>;
 			#address-cells = <1>;
 			#size-cells = <0>;
-		};
-
-		mdio_mux_4: mdio@4 {
-			reg = <4>;
-			#address-cells = <1>;
-			#size-cells = <0>;
-		};
-
-		mdio_mux_8: mdio@8 {
-			reg = <8>;
-			#address-cells = <1>;
-			#size-cells = <0>;
-		};
-	};
-
-	dsa {
-		compatible = "marvell,dsa";
-		#address-cells = <2>;
-		#size-cells = <0>;
-		dsa,ethernet = <&fec1>;
-		dsa,mii-bus = <&mdio_mux_1>;
-
-		/* 6352 - Primary - 7 ports */
-		switch0: switch@0-0 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			reg = <0x00 0>;
-			eeprom-length = <512>;
 
-			port@0 {
+			switch1: switch1@0 {
+				compatible = "marvell,mv88e6085";
+				#address-cells = <1>;
+				#size-cells = <0>;
 				reg = <0>;
-				label = "lan0";
-			};
-
-			port@1 {
-				reg = <1>;
-				label = "lan1";
-			};
-
-			port@2 {
-				reg = <2>;
-				label = "lan2";
-			};
-
-			switch0port5: port@5 {
-				reg = <5>;
-				label = "dsa";
-				phy-mode = "rgmii-txid";
-				link = <&switch1port6
-					&switch2port9>;
-
-				fixed-link {
-					speed = <1000>;
-					full-duplex;
+				dsa,member = <0 1>;
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					port@0 {
+						reg = <0>;
+						label = "lan3";
+						phy-handle = <&switch1phy0>;
+					};
+
+					port@1 {
+						reg = <1>;
+						label = "lan4";
+						phy-handle = <&switch1phy1>;
+					};
+
+					port@2 {
+						reg = <2>;
+						label = "lan5";
+						phy-handle = <&switch1phy2>;
+					};
+
+					switch1port5: port@5 {
+						reg = <5>;
+						label = "dsa";
+						link = <&switch2port9>;
+						phy-mode = "rgmii-txid";
+						fixed-link {
+							speed = <1000>;
+							full-duplex;
+						};
+					};
+
+					switch1port6: port@6 {
+						reg = <6>;
+						label = "dsa";
+						phy-mode = "rgmii-txid";
+						link = <&switch0port5>;
+						fixed-link {
+							speed = <1000>;
+							full-duplex;
+						};
+					};
 				};
-			};
-
-			port@6 {
-				reg = <6>;
-				label = "cpu";
-
-				fixed-link {
-					speed = <100>;
-					full-duplex;
+				mdio {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					switch1phy0: switch1phy0@0 {
+						reg = <0>;
+					};
+					switch1phy1: switch1phy0@1 {
+						reg = <1>;
+					};
+					switch1phy2: switch1phy0@2 {
+						reg = <2>;
+					};
 				};
 			};
-
 		};
 
-		/* 6352 - Secondary - 7 ports */
-		switch1: switch@0-1 {
+		mdio_mux_4: mdio@4 {
 			#address-cells = <1>;
 			#size-cells = <0>;
-			reg = <0x00 1>;
-			eeprom-length = <512>;
-			mii-bus = <&mdio_mux_2>;
+			reg = <4>;
 
-			port@0 {
+			switch2: switch2@0 {
+				compatible = "marvell,mv88e6085";
+				#address-cells = <1>;
+				#size-cells = <0>;
 				reg = <0>;
-				label = "lan3";
-			};
-
-			port@1 {
-				reg = <1>;
-				label = "lan4";
-			};
-
-			port@2 {
-				reg = <2>;
-				label = "lan5";
-			};
-
-			switch1port5: port@5 {
-				reg = <5>;
-				label = "dsa";
-				link = <&switch2port9>;
-				phy-mode = "rgmii-txid";
-
-				fixed-link {
-					speed = <1000>;
-					full-duplex;
-				};
-			};
-
-			switch1port6: port@6 {
-				reg = <6>;
-				label = "dsa";
-				phy-mode = "rgmii-txid";
-				link = <&switch0port5>;
-
-				fixed-link {
-					speed = <1000>;
-					full-duplex;
+				dsa,member = <0 2>;
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					port@0 {
+						reg = <0>;
+						label = "lan6";
+					};
+
+					port@1 {
+						reg = <1>;
+						label = "lan7";
+					};
+
+					port@2 {
+						reg = <2>;
+						label = "lan8";
+					};
+
+					port@3 {
+						reg = <3>;
+						label = "optical3";
+						fixed-link {
+							speed = <1000>;
+							full-duplex;
+							link-gpios = <&gpio6 2
+							      GPIO_ACTIVE_HIGH>;
+						};
+					};
+
+					port@4 {
+						reg = <4>;
+						label = "optical4";
+						fixed-link {
+							speed = <1000>;
+							full-duplex;
+							link-gpios = <&gpio6 3
+							      GPIO_ACTIVE_HIGH>;
+						};
+					};
+
+					switch2port9: port@9 {
+						reg = <9>;
+						label = "dsa";
+						phy-mode = "rgmii-txid";
+						link = <&switch1port5
+							&switch0port5>;
+						fixed-link {
+							speed = <1000>;
+							full-duplex;
+						};
+					};
 				};
 			};
 		};
 
-		/* 6185 - 10 ports */
-		switch2: switch@0-2 {
+		mdio_mux_8: mdio@8 {
+			reg = <8>;
 			#address-cells = <1>;
 			#size-cells = <0>;
-			reg = <0x00 2>;
-			mii-bus = <&mdio_mux_4>;
-
-			port@0 {
-				reg = <0>;
-				label = "lan6";
-			};
-
-			port@1 {
-				reg = <1>;
-				label = "lan7";
-			};
-
-			port@2 {
-				reg = <2>;
-				label = "lan8";
-			};
-
-			port@3 {
-				reg = <3>;
-				label = "optical3";
-
-				fixed-link {
-					speed = <1000>;
-					full-duplex;
-					link-gpios = <&gpio6 2
-						      GPIO_ACTIVE_HIGH>;
-				};
-			};
-
-			port@4 {
-				reg = <4>;
-				label = "optical4";
-
-				fixed-link {
-					speed = <1000>;
-					full-duplex;
-					link-gpios = <&gpio6 3
-						      GPIO_ACTIVE_HIGH>;
-				};
-			};
-
-			switch2port9: port@9 {
-				reg = <9>;
-				label = "dsa";
-				phy-mode = "rgmii-txid";
-				link = <&switch1port5
-					&switch0port5>;
-
-				fixed-link {
-					speed = <1000>;
-					full-duplex;
-				};
-			};
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/apm/apm-merlin.dts b/arch/arm64/boot/dts/apm/apm-merlin.dts
index 387c6a8d0da9..b0f64414c1b0 100644
--- a/arch/arm64/boot/dts/apm/apm-merlin.dts
+++ b/arch/arm64/boot/dts/apm/apm-merlin.dts
@@ -83,3 +83,9 @@
 		status = "ok";
 	};
 };
+
+&mdio {
+	sgenet0phy: phy@0 {
+		reg = <0x0>;
+	};
+};
diff --git a/arch/arm64/boot/dts/apm/apm-mustang.dts b/arch/arm64/boot/dts/apm/apm-mustang.dts
index 44db32ec5e9c..b7fb5d9295c2 100644
--- a/arch/arm64/boot/dts/apm/apm-mustang.dts
+++ b/arch/arm64/boot/dts/apm/apm-mustang.dts
@@ -79,3 +79,15 @@
 &mmc0 {
 	status = "ok";
 };
+
+&mdio {
+	menet0phy: phy@3 {
+		reg = <0x3>;
+	};
+	sgenet0phy: phy@4 {
+		reg = <0x4>;
+	};
+	sgenet1phy: phy@5 {
+		reg = <0x5>;
+	};
+};
diff --git a/arch/arm64/boot/dts/apm/apm-shadowcat.dtsi b/arch/arm64/boot/dts/apm/apm-shadowcat.dtsi
index c569f761d090..2e1e5daa1dc7 100644
--- a/arch/arm64/boot/dts/apm/apm-shadowcat.dtsi
+++ b/arch/arm64/boot/dts/apm/apm-shadowcat.dtsi
@@ -625,10 +625,18 @@
 			apm,irq-start = <8>;
 		};
 
+		mdio: mdio@1f610000 {
+			compatible = "apm,xgene-mdio-xfi";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x0 0x1f610000 0x0 0xd100>;
+			clocks = <&xge0clk 0>;
+		};
+
 		sgenet0: ethernet@1f610000 {
 			compatible = "apm,xgene2-sgenet";
 			status = "disabled";
-			reg = <0x0 0x1f610000 0x0 0x10000>,
+			reg = <0x0 0x1f610000 0x0 0xd100>,
 			      <0x0 0x1f600000 0x0 0Xd100>,
 			      <0x0 0x20000000 0x0 0X20000>;
 			interrupts = <0 96 4>,
@@ -637,6 +645,7 @@
 			clocks = <&xge0clk 0>;
 			local-mac-address = [00 01 73 00 00 01];
 			phy-connection-type = "sgmii";
+			phy-handle = <&sgenet0phy>;
 		};
 
 		xgenet1: ethernet@1f620000 {
diff --git a/arch/arm64/boot/dts/apm/apm-storm.dtsi b/arch/arm64/boot/dts/apm/apm-storm.dtsi
index 5147d7698924..6bf7cbe2e72d 100644
--- a/arch/arm64/boot/dts/apm/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm/apm-storm.dtsi
@@ -237,20 +237,11 @@
 				clocks = <&socplldiv2 0>;
 				reg = <0x0 0x1f21c000 0x0 0x1000>;
 				reg-names = "csr-reg";
-				csr-mask = <0x3>;
+				csr-mask = <0xa>;
+				enable-mask = <0xf>;
 				clock-output-names = "sge0clk";
 			};
 
-			sge1clk: sge1clk@1f21c000 {
-				compatible = "apm,xgene-device-clock";
-				#clock-cells = <1>;
-				clocks = <&socplldiv2 0>;
-				reg = <0x0 0x1f21c000 0x0 0x1000>;
-				reg-names = "csr-reg";
-				csr-mask = <0xc>;
-				clock-output-names = "sge1clk";
-			};
-
 			xge0clk: xge0clk@1f61c000 {
 				compatible = "apm,xgene-device-clock";
 				#clock-cells = <1>;
@@ -921,6 +912,14 @@
 			clocks = <&rtcclk 0>;
 		};
 
+		mdio: mdio@17020000 {
+			compatible = "apm,xgene-mdio-rgmii";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x0 0x17020000 0x0 0xd100>;
+			clocks = <&menetclk 0>;
+		};
+
 		menet: ethernet@17020000 {
 			compatible = "apm,xgene-enet";
 			status = "disabled";
@@ -934,7 +933,7 @@
 			/* mac address will be overwritten by the bootloader */
 			local-mac-address = [00 00 00 00 00 00];
 			phy-connection-type = "rgmii";
-			phy-handle = <&menetphy>;
+			phy-handle = <&menet0phy>,<&menetphy>;
 			mdio {
 				compatible = "apm,xgene-mdio";
 				#address-cells = <1>;
@@ -960,6 +959,7 @@
 			clocks = <&sge0clk 0>;
 			local-mac-address = [00 00 00 00 00 00];
 			phy-connection-type = "sgmii";
+			phy-handle = <&sgenet0phy>;
 		};
 
 		sgenet1: ethernet@1f210030 {
@@ -973,9 +973,9 @@
 				     <0x0 0xAD 0x4>;
 			port-id = <1>;
 			dma-coherent;
-			clocks = <&sge1clk 0>;
 			local-mac-address = [00 00 00 00 00 00];
 			phy-connection-type = "sgmii";
+			phy-handle = <&sgenet1phy>;
 		};
 
 		xgenet: ethernet@1f610000 {
diff --git a/arch/arm64/boot/dts/broadcom/ns2-svk.dts b/arch/arm64/boot/dts/broadcom/ns2-svk.dts
index 54ca40c9f711..ea5603fd106a 100644
--- a/arch/arm64/boot/dts/broadcom/ns2-svk.dts
+++ b/arch/arm64/boot/dts/broadcom/ns2-svk.dts
@@ -52,6 +52,14 @@
 	};
 };
 
+&pci_phy0 {
+	status = "ok";
+};
+
+&pci_phy1 {
+	status = "ok";
+};
+
 &pcie0 {
 	status = "ok";
 };
@@ -132,3 +140,11 @@
 		#size-cells = <1>;
 	};
 };
+
+&mdio_mux_iproc {
+	mdio@10 {
+		gphy0: eth-phy@10 {
+			reg = <0x10>;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/broadcom/ns2.dtsi b/arch/arm64/boot/dts/broadcom/ns2.dtsi
index ec68ec1a80c8..46b78fa89f4c 100644
--- a/arch/arm64/boot/dts/broadcom/ns2.dtsi
+++ b/arch/arm64/boot/dts/broadcom/ns2.dtsi
@@ -263,6 +263,45 @@
 				      IRQ_TYPE_LEVEL_HIGH)>;
 		};
 
+		mdio_mux_iproc: mdio-mux@6602023c {
+			compatible = "brcm,mdio-mux-iproc";
+			reg = <0x6602023c 0x14>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			mdio@0 {
+				reg = <0x0>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				pci_phy0: pci-phy@0 {
+					compatible = "brcm,ns2-pcie-phy";
+					reg = <0x0>;
+					#phy-cells = <0>;
+					status = "disabled";
+				};
+			};
+
+			mdio@7 {
+				reg = <0x7>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				pci_phy1: pci-phy@0 {
+					compatible = "brcm,ns2-pcie-phy";
+					reg = <0x0>;
+					#phy-cells = <0>;
+					status = "disabled";
+				};
+			};
+
+			mdio@10 {
+				reg = <0x10>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+		};
+
 		timer0: timer@66030000 {
 			compatible = "arm,sp804", "arm,primecell";
 			reg = <0x66030000 0x1000>;
diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h
index aee5637ea436..7c16e547ccb2 100644
--- a/arch/arm64/net/bpf_jit.h
+++ b/arch/arm64/net/bpf_jit.h
@@ -1,7 +1,7 @@
 /*
  * BPF JIT compiler for ARM64
  *
- * Copyright (C) 2014-2015 Zi Shen Lim <zlim.lnx@gmail.com>
+ * Copyright (C) 2014-2016 Zi Shen Lim <zlim.lnx@gmail.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -55,6 +55,7 @@
 #define A64_BL(imm26) A64_BRANCH((imm26) << 2, LINK)
 
 /* Unconditional branch (register) */
+#define A64_BR(Rn)  aarch64_insn_gen_branch_reg(Rn, AARCH64_INSN_BRANCH_NOLINK)
 #define A64_BLR(Rn) aarch64_insn_gen_branch_reg(Rn, AARCH64_INSN_BRANCH_LINK)
 #define A64_RET(Rn) aarch64_insn_gen_branch_reg(Rn, AARCH64_INSN_BRANCH_RETURN)
 
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 49ba37e4bfc0..b2fc97a2c56c 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -18,6 +18,7 @@
 
 #define pr_fmt(fmt) "bpf_jit: " fmt
 
+#include <linux/bpf.h>
 #include <linux/filter.h>
 #include <linux/printk.h>
 #include <linux/skbuff.h>
@@ -33,6 +34,7 @@ int bpf_jit_enable __read_mostly;
 
 #define TMP_REG_1 (MAX_BPF_JIT_REG + 0)
 #define TMP_REG_2 (MAX_BPF_JIT_REG + 1)
+#define TCALL_CNT (MAX_BPF_JIT_REG + 2)
 
 /* Map BPF registers to A64 registers */
 static const int bpf2a64[] = {
@@ -54,6 +56,8 @@ static const int bpf2a64[] = {
 	/* temporary registers for internal BPF JIT */
 	[TMP_REG_1] = A64_R(10),
 	[TMP_REG_2] = A64_R(11),
+	/* tail_call_cnt */
+	[TCALL_CNT] = A64_R(26),
 	/* temporary register for blinding constants */
 	[BPF_REG_AX] = A64_R(9),
 };
@@ -146,13 +150,18 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
 
 #define STACK_SIZE STACK_ALIGN(_STACK_SIZE)
 
-static void build_prologue(struct jit_ctx *ctx)
+#define PROLOGUE_OFFSET 8
+
+static int build_prologue(struct jit_ctx *ctx)
 {
 	const u8 r6 = bpf2a64[BPF_REG_6];
 	const u8 r7 = bpf2a64[BPF_REG_7];
 	const u8 r8 = bpf2a64[BPF_REG_8];
 	const u8 r9 = bpf2a64[BPF_REG_9];
 	const u8 fp = bpf2a64[BPF_REG_FP];
+	const u8 tcc = bpf2a64[TCALL_CNT];
+	const int idx0 = ctx->idx;
+	int cur_offset;
 
 	/*
 	 * BPF prog stack layout
@@ -162,8 +171,6 @@ static void build_prologue(struct jit_ctx *ctx)
 	 *                        |FP/LR|
 	 * current A64_FP =>  -16:+-----+
 	 *                        | ... | callee saved registers
-	 *                        +-----+
-	 *                        |     | x25/x26
 	 * BPF fp register => -64:+-----+ <= (BPF_FP)
 	 *                        |     |
 	 *                        | ... | BPF prog stack
@@ -183,18 +190,90 @@ static void build_prologue(struct jit_ctx *ctx)
 	emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
 	emit(A64_MOV(1, A64_FP, A64_SP), ctx);
 
-	/* Save callee-saved register */
+	/* Save callee-saved registers */
 	emit(A64_PUSH(r6, r7, A64_SP), ctx);
 	emit(A64_PUSH(r8, r9, A64_SP), ctx);
+	emit(A64_PUSH(fp, tcc, A64_SP), ctx);
 
-	/* Save fp (x25) and x26. SP requires 16 bytes alignment */
-	emit(A64_PUSH(fp, A64_R(26), A64_SP), ctx);
-
-	/* Set up BPF prog stack base register (x25) */
+	/* Set up BPF prog stack base register */
 	emit(A64_MOV(1, fp, A64_SP), ctx);
 
+	/* Initialize tail_call_cnt */
+	emit(A64_MOVZ(1, tcc, 0, 0), ctx);
+
 	/* Set up function call stack */
 	emit(A64_SUB_I(1, A64_SP, A64_SP, STACK_SIZE), ctx);
+
+	cur_offset = ctx->idx - idx0;
+	if (cur_offset != PROLOGUE_OFFSET) {
+		pr_err_once("PROLOGUE_OFFSET = %d, expected %d!\n",
+			    cur_offset, PROLOGUE_OFFSET);
+		return -1;
+	}
+	return 0;
+}
+
+static int out_offset = -1; /* initialized on the first pass of build_body() */
+static int emit_bpf_tail_call(struct jit_ctx *ctx)
+{
+	/* bpf_tail_call(void *prog_ctx, struct bpf_array *array, u64 index) */
+	const u8 r2 = bpf2a64[BPF_REG_2];
+	const u8 r3 = bpf2a64[BPF_REG_3];
+
+	const u8 tmp = bpf2a64[TMP_REG_1];
+	const u8 prg = bpf2a64[TMP_REG_2];
+	const u8 tcc = bpf2a64[TCALL_CNT];
+	const int idx0 = ctx->idx;
+#define cur_offset (ctx->idx - idx0)
+#define jmp_offset (out_offset - (cur_offset))
+	size_t off;
+
+	/* if (index >= array->map.max_entries)
+	 *     goto out;
+	 */
+	off = offsetof(struct bpf_array, map.max_entries);
+	emit_a64_mov_i64(tmp, off, ctx);
+	emit(A64_LDR32(tmp, r2, tmp), ctx);
+	emit(A64_CMP(0, r3, tmp), ctx);
+	emit(A64_B_(A64_COND_GE, jmp_offset), ctx);
+
+	/* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
+	 *     goto out;
+	 * tail_call_cnt++;
+	 */
+	emit_a64_mov_i64(tmp, MAX_TAIL_CALL_CNT, ctx);
+	emit(A64_CMP(1, tcc, tmp), ctx);
+	emit(A64_B_(A64_COND_GT, jmp_offset), ctx);
+	emit(A64_ADD_I(1, tcc, tcc, 1), ctx);
+
+	/* prog = array->ptrs[index];
+	 * if (prog == NULL)
+	 *     goto out;
+	 */
+	off = offsetof(struct bpf_array, ptrs);
+	emit_a64_mov_i64(tmp, off, ctx);
+	emit(A64_LDR64(tmp, r2, tmp), ctx);
+	emit(A64_LDR64(prg, tmp, r3), ctx);
+	emit(A64_CBZ(1, prg, jmp_offset), ctx);
+
+	/* goto *(prog->bpf_func + prologue_size); */
+	off = offsetof(struct bpf_prog, bpf_func);
+	emit_a64_mov_i64(tmp, off, ctx);
+	emit(A64_LDR64(tmp, prg, tmp), ctx);
+	emit(A64_ADD_I(1, tmp, tmp, sizeof(u32) * PROLOGUE_OFFSET), ctx);
+	emit(A64_BR(tmp), ctx);
+
+	/* out: */
+	if (out_offset == -1)
+		out_offset = cur_offset;
+	if (cur_offset != out_offset) {
+		pr_err_once("tail_call out_offset = %d, expected %d!\n",
+			    cur_offset, out_offset);
+		return -1;
+	}
+	return 0;
+#undef cur_offset
+#undef jmp_offset
 }
 
 static void build_epilogue(struct jit_ctx *ctx)
@@ -499,13 +578,15 @@ emit_cond_jmp:
 		const u64 func = (u64)__bpf_call_base + imm;
 
 		emit_a64_mov_i64(tmp, func, ctx);
-		emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
-		emit(A64_MOV(1, A64_FP, A64_SP), ctx);
 		emit(A64_BLR(tmp), ctx);
 		emit(A64_MOV(1, r0, A64_R(0)), ctx);
-		emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx);
 		break;
 	}
+	/* tail call */
+	case BPF_JMP | BPF_CALL | BPF_X:
+		if (emit_bpf_tail_call(ctx))
+			return -EFAULT;
+		break;
 	/* function return */
 	case BPF_JMP | BPF_EXIT:
 		/* Optimization: when last instruction is EXIT,
@@ -650,11 +731,8 @@ emit_cond_jmp:
 		emit_a64_mov_i64(r3, size, ctx);
 		emit(A64_SUB_I(1, r4, fp, STACK_SIZE), ctx);
 		emit_a64_mov_i64(r5, (unsigned long)bpf_load_pointer, ctx);
-		emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
-		emit(A64_MOV(1, A64_FP, A64_SP), ctx);
 		emit(A64_BLR(r5), ctx);
 		emit(A64_MOV(1, r0, A64_R(0)), ctx);
-		emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx);
 
 		jmp_offset = epilogue_offset(ctx);
 		check_imm19(jmp_offset);
@@ -780,7 +858,10 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		goto out_off;
 	}
 
-	build_prologue(&ctx);
+	if (build_prologue(&ctx)) {
+		prog = orig_prog;
+		goto out_off;
+	}
 
 	ctx.epilogue_offset = ctx.idx;
 	build_epilogue(&ctx);
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 9ea26dface38..53acf2d76fa9 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -974,12 +974,15 @@ static int perf_push_sample(struct perf_event *event, struct sf_raw_sample *sfr)
 	struct pt_regs regs;
 	struct perf_sf_sde_regs *sde_regs;
 	struct perf_sample_data data;
-	struct perf_raw_record raw;
+	struct perf_raw_record raw = {
+		.frag = {
+			.size = sfr->size,
+			.data = sfr,
+		},
+	};
 
 	/* Setup perf sample */
 	perf_sample_data_init(&data, 0, event->hw.last_period);
-	raw.size = sfr->size;
-	raw.data = sfr;
 	data.raw = &raw;
 
 	/* Setup pt_regs to look like an CPU-measurement external interrupt
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index feb90f6730e8..72dea2f40fc4 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -655,8 +655,12 @@ fail:
 	}
 
 	if (event->attr.sample_type & PERF_SAMPLE_RAW) {
-		raw.size = sizeof(u32) + ibs_data.size;
-		raw.data = ibs_data.data;
+		raw = (struct perf_raw_record){
+			.frag = {
+				.size = sizeof(u32) + ibs_data.size,
+				.data = ibs_data.data,
+			},
+		};
 		data.raw = &raw;
 	}