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

Pull networking updates from David Miller:
 "Some highlights from this development cycle:

   1) Big refactoring of ipv6 route and neigh handling to support
      nexthop objects configurable as units from userspace. From David
      Ahern.

   2) Convert explored_states in BPF verifier into a hash table,
      significantly decreased state held for programs with bpf2bpf
      calls, from Alexei Starovoitov.

   3) Implement bpf_send_signal() helper, from Yonghong Song.

   4) Various classifier enhancements to mvpp2 driver, from Maxime
      Chevallier.

   5) Add aRFS support to hns3 driver, from Jian Shen.

   6) Fix use after free in inet frags by allocating fqdirs dynamically
      and reworking how rhashtable dismantle occurs, from Eric Dumazet.

   7) Add act_ctinfo packet classifier action, from Kevin
      Darbyshire-Bryant.

   8) Add TFO key backup infrastructure, from Jason Baron.

   9) Remove several old and unused ISDN drivers, from Arnd Bergmann.

  10) Add devlink notifications for flash update status to mlxsw driver,
      from Jiri Pirko.

  11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski.

  12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes.

  13) Various enhancements to ipv6 flow label handling, from Eric
      Dumazet and Willem de Bruijn.

  14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van
      der Merwe, and others.

  15) Various improvements to axienet driver including converting it to
      phylink, from Robert Hancock.

  16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean.

  17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana
      Radulescu.

  18) Add devlink health reporting to mlx5, from Moshe Shemesh.

  19) Convert stmmac over to phylink, from Jose Abreu.

  20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from
      Shalom Toledo.

  21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera.

  22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel.

  23) Track spill/fill of constants in BPF verifier, from Alexei
      Starovoitov.

  24) Support bounded loops in BPF, from Alexei Starovoitov.

  25) Various page_pool API fixes and improvements, from Jesper Dangaard
      Brouer.

  26) Just like ipv4, support ref-countless ipv6 route handling. From
      Wei Wang.

  27) Support VLAN offloading in aquantia driver, from Igor Russkikh.

  28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy.

  29) Add flower GRE encap/decap support to nfp driver, from Pieter
      Jansen van Vuuren.

  30) Protect against stack overflow when using act_mirred, from John
      Hurley.

  31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen.

  32) Use page_pool API in netsec driver, Ilias Apalodimas.

  33) Add Google gve network driver, from Catherine Sullivan.

  34) More indirect call avoidance, from Paolo Abeni.

  35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan.

  36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek.

  37) Add MPLS manipulation actions to TC, from John Hurley.

  38) Add sending a packet to connection tracking from TC actions, and
      then allow flower classifier matching on conntrack state. From
      Paul Blakey.

  39) Netfilter hw offload support, from Pablo Neira Ayuso"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits)
  net/mlx5e: Return in default case statement in tx_post_resync_params
  mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync().
  net: dsa: add support for BRIDGE_MROUTER attribute
  pkt_sched: Include const.h
  net: netsec: remove static declaration for netsec_set_tx_de()
  net: netsec: remove superfluous if statement
  netfilter: nf_tables: add hardware offload support
  net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload
  net: flow_offload: add flow_block_cb_is_busy() and use it
  net: sched: remove tcf block API
  drivers: net: use flow block API
  net: sched: use flow block API
  net: flow_offload: add flow_block_cb_{priv, incref, decref}()
  net: flow_offload: add list handling functions
  net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free()
  net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*
  net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND
  net: flow_offload: add flow_block_cb_setup_simple()
  net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC
  net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC
  ...

32 files changed, 325 insertions, 343 deletions

diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index 976e89b116e5..de6c4df61082 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -122,6 +122,8 @@
 #define SO_RCVTIMEO_NEW         66
 #define SO_SNDTIMEO_NEW         67
 
+#define SO_DETACH_REUSEPORT_BPF 68
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index adff54c312bf..97dc386e3cb8 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -733,7 +733,8 @@ static inline void emit_a32_alu_r64(const bool is64, const s8 dst[],
 
 		/* ALU operation */
 		emit_alu_r(rd[1], rs, true, false, op, ctx);
-		emit_a32_mov_i(rd[0], 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(rd[0], 0, ctx);
 	}
 
 	arm_bpf_put_reg64(dst, rd, ctx);
@@ -755,8 +756,9 @@ static inline void emit_a32_mov_r64(const bool is64, const s8 dst[],
 				  struct jit_ctx *ctx) {
 	if (!is64) {
 		emit_a32_mov_r(dst_lo, src_lo, ctx);
-		/* Zero out high 4 bytes */
-		emit_a32_mov_i(dst_hi, 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			/* Zero out high 4 bytes */
+			emit_a32_mov_i(dst_hi, 0, ctx);
 	} else if (__LINUX_ARM_ARCH__ < 6 &&
 		   ctx->cpu_architecture < CPU_ARCH_ARMv5TE) {
 		/* complete 8 byte move */
@@ -1057,17 +1059,20 @@ static inline void emit_ldx_r(const s8 dst[], const s8 src,
 	case BPF_B:
 		/* Load a Byte */
 		emit(ARM_LDRB_I(rd[1], rm, off), ctx);
-		emit_a32_mov_i(rd[0], 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(rd[0], 0, ctx);
 		break;
 	case BPF_H:
 		/* Load a HalfWord */
 		emit(ARM_LDRH_I(rd[1], rm, off), ctx);
-		emit_a32_mov_i(rd[0], 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(rd[0], 0, ctx);
 		break;
 	case BPF_W:
 		/* Load a Word */
 		emit(ARM_LDR_I(rd[1], rm, off), ctx);
-		emit_a32_mov_i(rd[0], 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(rd[0], 0, ctx);
 		break;
 	case BPF_DW:
 		/* Load a Double Word */
@@ -1356,6 +1361,11 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_ALU64 | BPF_MOV | BPF_X:
 		switch (BPF_SRC(code)) {
 		case BPF_X:
+			if (imm == 1) {
+				/* Special mov32 for zext */
+				emit_a32_mov_i(dst_hi, 0, ctx);
+				break;
+			}
 			emit_a32_mov_r64(is64, dst, src, ctx);
 			break;
 		case BPF_K:
@@ -1435,7 +1445,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		}
 		emit_udivmod(rd_lo, rd_lo, rt, ctx, BPF_OP(code));
 		arm_bpf_put_reg32(dst_lo, rd_lo, ctx);
-		emit_a32_mov_i(dst_hi, 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(dst_hi, 0, ctx);
 		break;
 	case BPF_ALU64 | BPF_DIV | BPF_K:
 	case BPF_ALU64 | BPF_DIV | BPF_X:
@@ -1450,7 +1461,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			return -EINVAL;
 		if (imm)
 			emit_a32_alu_i(dst_lo, imm, ctx, BPF_OP(code));
-		emit_a32_mov_i(dst_hi, 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(dst_hi, 0, ctx);
 		break;
 	/* dst = dst << imm */
 	case BPF_ALU64 | BPF_LSH | BPF_K:
@@ -1485,7 +1497,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	/* dst = ~dst */
 	case BPF_ALU | BPF_NEG:
 		emit_a32_alu_i(dst_lo, 0, ctx, BPF_OP(code));
-		emit_a32_mov_i(dst_hi, 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(dst_hi, 0, ctx);
 		break;
 	/* dst = ~dst (64 bit) */
 	case BPF_ALU64 | BPF_NEG:
@@ -1541,11 +1554,13 @@ emit_bswap_uxt:
 #else /* ARMv6+ */
 			emit(ARM_UXTH(rd[1], rd[1]), ctx);
 #endif
-			emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx);
+			if (!ctx->prog->aux->verifier_zext)
+				emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx);
 			break;
 		case 32:
 			/* zero-extend 32 bits into 64 bits */
-			emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx);
+			if (!ctx->prog->aux->verifier_zext)
+				emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx);
 			break;
 		case 64:
 			/* nop */
@@ -1835,6 +1850,11 @@ void bpf_jit_compile(struct bpf_prog *prog)
 	/* Nothing to do here. We support Internal BPF. */
 }
 
+bool bpf_jit_needs_zext(void)
+{
+	return true;
+}
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
 	struct bpf_prog *tmp, *orig_prog = prog;
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
index bf7f845447ed..22a1c74dddf3 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
@@ -431,6 +431,12 @@
 				compatible = "fsl,enetc";
 				reg = <0x000100 0 0 0 0>;
 			};
+			ethernet@0,4 {
+				compatible = "fsl,enetc-ptp";
+				reg = <0x000400 0 0 0 0>;
+				clocks = <&clockgen 4 0>;
+				little-endian;
+			};
 		};
 	};
 };
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
index 661137ffa319..dacd8cf03a7f 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
@@ -609,6 +609,14 @@
 				     <GIC_SPI 209 IRQ_TYPE_LEVEL_HIGH>;
 		};
 
+		ptp-timer@8b95000 {
+			compatible = "fsl,dpaa2-ptp";
+			reg = <0x0 0x8b95000 0x0 0x100>;
+			clocks = <&clockgen 4 0>;
+			little-endian;
+			fsl,extts-fifo;
+		};
+
 		cluster1_core0_watchdog: wdt@c000000 {
 			compatible = "arm,sp805-wdt", "arm,primecell";
 			reg = <0x0 0xc000000 0x0 0x1000>;
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
index d7e78dcd153d..3ace91945b72 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
@@ -321,6 +321,14 @@
 			};
 		};
 
+		ptp-timer@8b95000 {
+			compatible = "fsl,dpaa2-ptp";
+			reg = <0x0 0x8b95000 0x0 0x100>;
+			clocks = <&clockgen 4 1>;
+			little-endian;
+			fsl,extts-fifo;
+		};
+
 		fsl_mc: fsl-mc@80c000000 {
 			compatible = "fsl,qoriq-mc";
 			reg = <0x00000008 0x0c000000 0 0x40>,	 /* MC portal base */
diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
index 125a8cc2c5b3..e6fdba39453c 100644
--- a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
@@ -848,6 +848,14 @@
 			dma-coherent;
 		};
 
+		ptp-timer@8b95000 {
+			compatible = "fsl,dpaa2-ptp";
+			reg = <0x0 0x8b95000 0x0 0x100>;
+			clocks = <&clockgen 4 1>;
+			little-endian;
+			fsl,extts-fifo;
+		};
+
 		fsl_mc: fsl-mc@80c000000 {
 			compatible = "fsl,qoriq-mc";
 			reg = <0x00000008 0x0c000000 0 0x40>,
diff --git a/arch/arm64/boot/dts/mediatek/mt7622.dtsi b/arch/arm64/boot/dts/mediatek/mt7622.dtsi
index 4b1f5ae710eb..d1e13d340e26 100644
--- a/arch/arm64/boot/dts/mediatek/mt7622.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt7622.dtsi
@@ -929,7 +929,8 @@
 	sgmiisys: sgmiisys@1b128000 {
 		compatible = "mediatek,mt7622-sgmiisys",
 			     "syscon";
-		reg = <0 0x1b128000 0 0x1000>;
+		reg = <0 0x1b128000 0 0x3000>;
 		#clock-cells = <1>;
+		mediatek,physpeed = "2500";
 	};
 };
diff --git a/arch/mips/boot/dts/mscc/ocelot.dtsi b/arch/mips/boot/dts/mscc/ocelot.dtsi
index 90c60d42f571..33ae74aaa1bb 100644
--- a/arch/mips/boot/dts/mscc/ocelot.dtsi
+++ b/arch/mips/boot/dts/mscc/ocelot.dtsi
@@ -132,11 +132,12 @@
 			      <0x1270000 0x100>,
 			      <0x1280000 0x100>,
 			      <0x1800000 0x80000>,
-			      <0x1880000 0x10000>;
+			      <0x1880000 0x10000>,
+			      <0x1060000 0x10000>;
 			reg-names = "sys", "rew", "qs", "port0", "port1",
 				    "port2", "port3", "port4", "port5", "port6",
 				    "port7", "port8", "port9", "port10", "qsys",
-				    "ana";
+				    "ana", "s2";
 			interrupts = <21 22>;
 			interrupt-names = "xtr", "inj";
 
diff --git a/arch/mips/boot/dts/qca/ar9331.dtsi b/arch/mips/boot/dts/qca/ar9331.dtsi
index 2bae201aa365..63a9f33aa43e 100644
--- a/arch/mips/boot/dts/qca/ar9331.dtsi
+++ b/arch/mips/boot/dts/qca/ar9331.dtsi
@@ -116,6 +116,32 @@
 			};
 		};
 
+		eth0: ethernet@19000000 {
+			compatible = "qca,ar9330-eth";
+			reg = <0x19000000 0x200>;
+			interrupts = <4>;
+
+			resets = <&rst 9>, <&rst 22>;
+			reset-names = "mac", "mdio";
+			clocks = <&pll ATH79_CLK_AHB>, <&pll ATH79_CLK_AHB>;
+			clock-names = "eth", "mdio";
+
+			status = "disabled";
+		};
+
+		eth1: ethernet@1a000000 {
+			compatible = "qca,ar9330-eth";
+			reg = <0x1a000000 0x200>;
+			interrupts = <5>;
+
+			resets = <&rst 13>, <&rst 23>;
+			reset-names = "mac", "mdio";
+			clocks = <&pll ATH79_CLK_AHB>, <&pll ATH79_CLK_AHB>;
+			clock-names = "eth", "mdio";
+
+			status = "disabled";
+		};
+
 		usb: usb@1b000100 {
 			compatible = "chipidea,usb2";
 			reg = <0x1b000000 0x200>;
diff --git a/arch/mips/boot/dts/qca/ar9331_dpt_module.dts b/arch/mips/boot/dts/qca/ar9331_dpt_module.dts
index e7af2cf5f4c1..77bab823eb3b 100644
--- a/arch/mips/boot/dts/qca/ar9331_dpt_module.dts
+++ b/arch/mips/boot/dts/qca/ar9331_dpt_module.dts
@@ -76,3 +76,11 @@
 		reg = <0>;
 	};
 };
+
+&eth0 {
+	status = "okay";
+};
+
+&eth1 {
+	status = "okay";
+};
diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig
index 0ee5e677662e..0de92ac1ca64 100644
--- a/arch/mips/configs/malta_defconfig
+++ b/arch/mips/configs/malta_defconfig
@@ -210,7 +210,6 @@ CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
 CONFIG_NET_ACT_SKBEDIT=m
-CONFIG_NET_CLS_IND=y
 CONFIG_CFG80211=m
 CONFIG_MAC80211=m
 CONFIG_MAC80211_MESH=y
diff --git a/arch/mips/configs/malta_kvm_defconfig b/arch/mips/configs/malta_kvm_defconfig
index 041bffac043b..efc3abace048 100644
--- a/arch/mips/configs/malta_kvm_defconfig
+++ b/arch/mips/configs/malta_kvm_defconfig
@@ -215,7 +215,6 @@ CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
 CONFIG_NET_ACT_SKBEDIT=m
-CONFIG_NET_CLS_IND=y
 CONFIG_CFG80211=m
 CONFIG_MAC80211=m
 CONFIG_MAC80211_MESH=y
diff --git a/arch/mips/configs/malta_kvm_guest_defconfig b/arch/mips/configs/malta_kvm_guest_defconfig
index 511065e62182..c6ceeca4394d 100644
--- a/arch/mips/configs/malta_kvm_guest_defconfig
+++ b/arch/mips/configs/malta_kvm_guest_defconfig
@@ -212,7 +212,6 @@ CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
 CONFIG_NET_ACT_SKBEDIT=m
-CONFIG_NET_CLS_IND=y
 CONFIG_CFG80211=m
 CONFIG_MAC80211=m
 CONFIG_MAC80211_MESH=y
diff --git a/arch/mips/configs/malta_qemu_32r6_defconfig b/arch/mips/configs/malta_qemu_32r6_defconfig
index 299088043164..e6c600dc1814 100644
--- a/arch/mips/configs/malta_qemu_32r6_defconfig
+++ b/arch/mips/configs/malta_qemu_32r6_defconfig
@@ -74,7 +74,6 @@ CONFIG_NET_CLS_RSVP=m
 CONFIG_NET_CLS_RSVP6=m
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_ACT_POLICE=y
-CONFIG_NET_CLS_IND=y
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 CONFIG_BLK_DEV_LOOP=y
diff --git a/arch/mips/configs/maltaaprp_defconfig b/arch/mips/configs/maltaaprp_defconfig
index 2b4b3a24f637..82b44b774553 100644
--- a/arch/mips/configs/maltaaprp_defconfig
+++ b/arch/mips/configs/maltaaprp_defconfig
@@ -76,7 +76,6 @@ CONFIG_NET_CLS_RSVP=m
 CONFIG_NET_CLS_RSVP6=m
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_ACT_POLICE=y
-CONFIG_NET_CLS_IND=y
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 CONFIG_BLK_DEV_LOOP=y
diff --git a/arch/mips/configs/maltasmvp_defconfig b/arch/mips/configs/maltasmvp_defconfig
index 425ddfd7cd78..4190fc6189a0 100644
--- a/arch/mips/configs/maltasmvp_defconfig
+++ b/arch/mips/configs/maltasmvp_defconfig
@@ -77,7 +77,6 @@ CONFIG_NET_CLS_RSVP=m
 CONFIG_NET_CLS_RSVP6=m
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_ACT_POLICE=y
-CONFIG_NET_CLS_IND=y
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 CONFIG_BLK_DEV_LOOP=y
diff --git a/arch/mips/configs/maltasmvp_eva_defconfig b/arch/mips/configs/maltasmvp_eva_defconfig
index 8beaa7ba1e52..a13c10e910ec 100644
--- a/arch/mips/configs/maltasmvp_eva_defconfig
+++ b/arch/mips/configs/maltasmvp_eva_defconfig
@@ -78,7 +78,6 @@ CONFIG_NET_CLS_RSVP=m
 CONFIG_NET_CLS_RSVP6=m
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_ACT_POLICE=y
-CONFIG_NET_CLS_IND=y
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 CONFIG_BLK_DEV_LOOP=y
diff --git a/arch/mips/configs/maltaup_defconfig b/arch/mips/configs/maltaup_defconfig
index 6e8b95ceb54a..b35f1fc690fb 100644
--- a/arch/mips/configs/maltaup_defconfig
+++ b/arch/mips/configs/maltaup_defconfig
@@ -75,7 +75,6 @@ CONFIG_NET_CLS_RSVP=m
 CONFIG_NET_CLS_RSVP6=m
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_ACT_POLICE=y
-CONFIG_NET_CLS_IND=y
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 CONFIG_BLK_DEV_LOOP=y
diff --git a/arch/mips/configs/maltaup_xpa_defconfig b/arch/mips/configs/maltaup_xpa_defconfig
index 6c026db96ff9..56861aef2756 100644
--- a/arch/mips/configs/maltaup_xpa_defconfig
+++ b/arch/mips/configs/maltaup_xpa_defconfig
@@ -212,7 +212,6 @@ CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
 CONFIG_NET_ACT_SKBEDIT=m
-CONFIG_NET_CLS_IND=y
 CONFIG_CFG80211=m
 CONFIG_MAC80211=m
 CONFIG_MAC80211_MESH=y
diff --git a/arch/mips/configs/rb532_defconfig b/arch/mips/configs/rb532_defconfig
index 50632a3103dd..864c70fbe668 100644
--- a/arch/mips/configs/rb532_defconfig
+++ b/arch/mips/configs/rb532_defconfig
@@ -103,7 +103,6 @@ CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
 CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_PEDIT=m
-CONFIG_NET_CLS_IND=y
 CONFIG_HAMRADIO=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_MTD=y
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index d41765cfbc6e..d0a9ed2ca2d6 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -133,6 +133,8 @@
 #define SO_RCVTIMEO_NEW         66
 #define SO_SNDTIMEO_NEW         67
 
+#define SO_DETACH_REUSEPORT_BPF 68
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index 66c5dd245ac7..10173c32195e 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -114,6 +114,8 @@
 #define SO_RCVTIMEO_NEW         0x4040
 #define SO_SNDTIMEO_NEW         0x4041
 
+#define SO_DETACH_REUSEPORT_BPF 0x4042
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index 7c6baf6df139..aa51b9b66fa2 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -301,7 +301,6 @@ CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
 CONFIG_NET_ACT_SKBEDIT=m
-CONFIG_NET_CLS_IND=y
 CONFIG_IRDA=m
 CONFIG_IRLAN=m
 CONFIG_IRNET=m
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index c2ee6041f02c..02a59946a78a 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -500,6 +500,9 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		case BPF_ALU | BPF_LSH | BPF_X: /* (u32) dst <<= (u32) src */
 			/* slw clears top 32 bits */
 			PPC_SLW(dst_reg, dst_reg, src_reg);
+			/* skip zero extension move, but set address map. */
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		case BPF_ALU64 | BPF_LSH | BPF_X: /* dst <<= src; */
 			PPC_SLD(dst_reg, dst_reg, src_reg);
@@ -507,6 +510,8 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		case BPF_ALU | BPF_LSH | BPF_K: /* (u32) dst <<== (u32) imm */
 			/* with imm 0, we still need to clear top 32 bits */
 			PPC_SLWI(dst_reg, dst_reg, imm);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		case BPF_ALU64 | BPF_LSH | BPF_K: /* dst <<== imm */
 			if (imm != 0)
@@ -514,12 +519,16 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			break;
 		case BPF_ALU | BPF_RSH | BPF_X: /* (u32) dst >>= (u32) src */
 			PPC_SRW(dst_reg, dst_reg, src_reg);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		case BPF_ALU64 | BPF_RSH | BPF_X: /* dst >>= src */
 			PPC_SRD(dst_reg, dst_reg, src_reg);
 			break;
 		case BPF_ALU | BPF_RSH | BPF_K: /* (u32) dst >>= (u32) imm */
 			PPC_SRWI(dst_reg, dst_reg, imm);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		case BPF_ALU64 | BPF_RSH | BPF_K: /* dst >>= imm */
 			if (imm != 0)
@@ -544,6 +553,11 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		 */
 		case BPF_ALU | BPF_MOV | BPF_X: /* (u32) dst = src */
 		case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */
+			if (imm == 1) {
+				/* special mov32 for zext */
+				PPC_RLWINM(dst_reg, dst_reg, 0, 0, 31);
+				break;
+			}
 			PPC_MR(dst_reg, src_reg);
 			goto bpf_alu32_trunc;
 		case BPF_ALU | BPF_MOV | BPF_K: /* (u32) dst = imm */
@@ -551,11 +565,13 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			PPC_LI32(dst_reg, imm);
 			if (imm < 0)
 				goto bpf_alu32_trunc;
+			else if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 
 bpf_alu32_trunc:
 		/* Truncate to 32-bits */
-		if (BPF_CLASS(code) == BPF_ALU)
+		if (BPF_CLASS(code) == BPF_ALU && !fp->aux->verifier_zext)
 			PPC_RLWINM(dst_reg, dst_reg, 0, 0, 31);
 		break;
 
@@ -614,10 +630,13 @@ emit_clear:
 			case 16:
 				/* zero-extend 16 bits into 64 bits */
 				PPC_RLDICL(dst_reg, dst_reg, 0, 48);
+				if (insn_is_zext(&insn[i + 1]))
+					addrs[++i] = ctx->idx * 4;
 				break;
 			case 32:
-				/* zero-extend 32 bits into 64 bits */
-				PPC_RLDICL(dst_reg, dst_reg, 0, 32);
+				if (!fp->aux->verifier_zext)
+					/* zero-extend 32 bits into 64 bits */
+					PPC_RLDICL(dst_reg, dst_reg, 0, 32);
 				break;
 			case 64:
 				/* nop */
@@ -694,14 +713,20 @@ emit_clear:
 		/* dst = *(u8 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_B:
 			PPC_LBZ(dst_reg, src_reg, off);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		/* dst = *(u16 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_H:
 			PPC_LHZ(dst_reg, src_reg, off);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		/* dst = *(u32 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_W:
 			PPC_LWZ(dst_reg, src_reg, off);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		/* dst = *(u64 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_DW:
@@ -1042,6 +1067,11 @@ struct powerpc64_jit_data {
 	struct codegen_context ctx;
 };
 
+bool bpf_jit_needs_zext(void)
+{
+	return true;
+}
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 {
 	u32 proglen;
diff --git a/arch/riscv/net/bpf_jit_comp.c b/arch/riscv/net/bpf_jit_comp.c
index 426d5c33ea90..5451ef3845f2 100644
--- a/arch/riscv/net/bpf_jit_comp.c
+++ b/arch/riscv/net/bpf_jit_comp.c
@@ -731,6 +731,7 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 {
 	bool is64 = BPF_CLASS(insn->code) == BPF_ALU64 ||
 		    BPF_CLASS(insn->code) == BPF_JMP;
+	struct bpf_prog_aux *aux = ctx->prog->aux;
 	int rvoff, i = insn - ctx->prog->insnsi;
 	u8 rd = -1, rs = -1, code = insn->code;
 	s16 off = insn->off;
@@ -742,8 +743,13 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	/* dst = src */
 	case BPF_ALU | BPF_MOV | BPF_X:
 	case BPF_ALU64 | BPF_MOV | BPF_X:
+		if (imm == 1) {
+			/* Special mov32 for zext */
+			emit_zext_32(rd, ctx);
+			break;
+		}
 		emit(is64 ? rv_addi(rd, rs, 0) : rv_addiw(rd, rs, 0), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 
@@ -751,49 +757,49 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_ALU | BPF_ADD | BPF_X:
 	case BPF_ALU64 | BPF_ADD | BPF_X:
 		emit(is64 ? rv_add(rd, rd, rs) : rv_addw(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_SUB | BPF_X:
 	case BPF_ALU64 | BPF_SUB | BPF_X:
 		emit(is64 ? rv_sub(rd, rd, rs) : rv_subw(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_AND | BPF_X:
 	case BPF_ALU64 | BPF_AND | BPF_X:
 		emit(rv_and(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_OR | BPF_X:
 	case BPF_ALU64 | BPF_OR | BPF_X:
 		emit(rv_or(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_XOR | BPF_X:
 	case BPF_ALU64 | BPF_XOR | BPF_X:
 		emit(rv_xor(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_MUL | BPF_X:
 	case BPF_ALU64 | BPF_MUL | BPF_X:
 		emit(is64 ? rv_mul(rd, rd, rs) : rv_mulw(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_DIV | BPF_X:
 	case BPF_ALU64 | BPF_DIV | BPF_X:
 		emit(is64 ? rv_divu(rd, rd, rs) : rv_divuw(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_MOD | BPF_X:
 	case BPF_ALU64 | BPF_MOD | BPF_X:
 		emit(is64 ? rv_remu(rd, rd, rs) : rv_remuw(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_LSH | BPF_X:
@@ -805,13 +811,13 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_ALU | BPF_RSH | BPF_X:
 	case BPF_ALU64 | BPF_RSH | BPF_X:
 		emit(is64 ? rv_srl(rd, rd, rs) : rv_srlw(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_ARSH | BPF_X:
 	case BPF_ALU64 | BPF_ARSH | BPF_X:
 		emit(is64 ? rv_sra(rd, rd, rs) : rv_sraw(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 
@@ -820,7 +826,7 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_ALU64 | BPF_NEG:
 		emit(is64 ? rv_sub(rd, RV_REG_ZERO, rd) :
 		     rv_subw(rd, RV_REG_ZERO, rd), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 
@@ -885,7 +891,7 @@ out_be:
 	case BPF_ALU | BPF_MOV | BPF_K:
 	case BPF_ALU64 | BPF_MOV | BPF_K:
 		emit_imm(rd, imm, ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 
@@ -900,7 +906,7 @@ out_be:
 			emit(is64 ? rv_add(rd, rd, RV_REG_T1) :
 			     rv_addw(rd, rd, RV_REG_T1), ctx);
 		}
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_SUB | BPF_K:
@@ -913,7 +919,7 @@ out_be:
 			emit(is64 ? rv_sub(rd, rd, RV_REG_T1) :
 			     rv_subw(rd, rd, RV_REG_T1), ctx);
 		}
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_AND | BPF_K:
@@ -924,7 +930,7 @@ out_be:
 			emit_imm(RV_REG_T1, imm, ctx);
 			emit(rv_and(rd, rd, RV_REG_T1), ctx);
 		}
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_OR | BPF_K:
@@ -935,7 +941,7 @@ out_be:
 			emit_imm(RV_REG_T1, imm, ctx);
 			emit(rv_or(rd, rd, RV_REG_T1), ctx);
 		}
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_XOR | BPF_K:
@@ -946,7 +952,7 @@ out_be:
 			emit_imm(RV_REG_T1, imm, ctx);
 			emit(rv_xor(rd, rd, RV_REG_T1), ctx);
 		}
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_MUL | BPF_K:
@@ -954,7 +960,7 @@ out_be:
 		emit_imm(RV_REG_T1, imm, ctx);
 		emit(is64 ? rv_mul(rd, rd, RV_REG_T1) :
 		     rv_mulw(rd, rd, RV_REG_T1), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_DIV | BPF_K:
@@ -962,7 +968,7 @@ out_be:
 		emit_imm(RV_REG_T1, imm, ctx);
 		emit(is64 ? rv_divu(rd, rd, RV_REG_T1) :
 		     rv_divuw(rd, rd, RV_REG_T1), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_MOD | BPF_K:
@@ -970,7 +976,7 @@ out_be:
 		emit_imm(RV_REG_T1, imm, ctx);
 		emit(is64 ? rv_remu(rd, rd, RV_REG_T1) :
 		     rv_remuw(rd, rd, RV_REG_T1), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_LSH | BPF_K:
@@ -1263,6 +1269,8 @@ out_be:
 		emit_imm(RV_REG_T1, off, ctx);
 		emit(rv_add(RV_REG_T1, RV_REG_T1, rs), ctx);
 		emit(rv_lbu(rd, 0, RV_REG_T1), ctx);
+		if (insn_is_zext(&insn[1]))
+			return 1;
 		break;
 	case BPF_LDX | BPF_MEM | BPF_H:
 		if (is_12b_int(off)) {
@@ -1273,6 +1281,8 @@ out_be:
 		emit_imm(RV_REG_T1, off, ctx);
 		emit(rv_add(RV_REG_T1, RV_REG_T1, rs), ctx);
 		emit(rv_lhu(rd, 0, RV_REG_T1), ctx);
+		if (insn_is_zext(&insn[1]))
+			return 1;
 		break;
 	case BPF_LDX | BPF_MEM | BPF_W:
 		if (is_12b_int(off)) {
@@ -1283,6 +1293,8 @@ out_be:
 		emit_imm(RV_REG_T1, off, ctx);
 		emit(rv_add(RV_REG_T1, RV_REG_T1, rs), ctx);
 		emit(rv_lwu(rd, 0, RV_REG_T1), ctx);
+		if (insn_is_zext(&insn[1]))
+			return 1;
 		break;
 	case BPF_LDX | BPF_MEM | BPF_DW:
 		if (is_12b_int(off)) {
@@ -1527,6 +1539,11 @@ static void bpf_flush_icache(void *start, void *end)
 	flush_icache_range((unsigned long)start, (unsigned long)end);
 }
 
+bool bpf_jit_needs_zext(void)
+{
+	return true;
+}
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
 	bool tmp_blinded = false, extra_pass = false;
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 5e7c63033159..e636728ab452 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -299,9 +299,11 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 
 #define EMIT_ZERO(b1)						\
 ({								\
-	/* llgfr %dst,%dst (zero extend to 64 bit) */		\
-	EMIT4(0xb9160000, b1, b1);				\
-	REG_SET_SEEN(b1);					\
+	if (!fp->aux->verifier_zext) {				\
+		/* llgfr %dst,%dst (zero extend to 64 bit) */	\
+		EMIT4(0xb9160000, b1, b1);			\
+		REG_SET_SEEN(b1);				\
+	}							\
 })
 
 /*
@@ -520,6 +522,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 	case BPF_ALU | BPF_MOV | BPF_X: /* dst = (u32) src */
 		/* llgfr %dst,%src */
 		EMIT4(0xb9160000, dst_reg, src_reg);
+		if (insn_is_zext(&insn[1]))
+			insn_count = 2;
 		break;
 	case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */
 		/* lgr %dst,%src */
@@ -528,6 +532,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 	case BPF_ALU | BPF_MOV | BPF_K: /* dst = (u32) imm */
 		/* llilf %dst,imm */
 		EMIT6_IMM(0xc00f0000, dst_reg, imm);
+		if (insn_is_zext(&insn[1]))
+			insn_count = 2;
 		break;
 	case BPF_ALU64 | BPF_MOV | BPF_K: /* dst = imm */
 		/* lgfi %dst,imm */
@@ -639,6 +645,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 		EMIT4(0xb9970000, REG_W0, src_reg);
 		/* llgfr %dst,%rc */
 		EMIT4(0xb9160000, dst_reg, rc_reg);
+		if (insn_is_zext(&insn[1]))
+			insn_count = 2;
 		break;
 	}
 	case BPF_ALU64 | BPF_DIV | BPF_X: /* dst = dst / src */
@@ -676,6 +684,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 			      EMIT_CONST_U32(imm));
 		/* llgfr %dst,%rc */
 		EMIT4(0xb9160000, dst_reg, rc_reg);
+		if (insn_is_zext(&insn[1]))
+			insn_count = 2;
 		break;
 	}
 	case BPF_ALU64 | BPF_DIV | BPF_K: /* dst = dst / imm */
@@ -864,10 +874,13 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 		case 16: /* dst = (u16) cpu_to_be16(dst) */
 			/* llghr %dst,%dst */
 			EMIT4(0xb9850000, dst_reg, dst_reg);
+			if (insn_is_zext(&insn[1]))
+				insn_count = 2;
 			break;
 		case 32: /* dst = (u32) cpu_to_be32(dst) */
-			/* llgfr %dst,%dst */
-			EMIT4(0xb9160000, dst_reg, dst_reg);
+			if (!fp->aux->verifier_zext)
+				/* llgfr %dst,%dst */
+				EMIT4(0xb9160000, dst_reg, dst_reg);
 			break;
 		case 64: /* dst = (u64) cpu_to_be64(dst) */
 			break;
@@ -882,12 +895,15 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 			EMIT4_DISP(0x88000000, dst_reg, REG_0, 16);
 			/* llghr %dst,%dst */
 			EMIT4(0xb9850000, dst_reg, dst_reg);
+			if (insn_is_zext(&insn[1]))
+				insn_count = 2;
 			break;
 		case 32: /* dst = (u32) cpu_to_le32(dst) */
 			/* lrvr %dst,%dst */
 			EMIT4(0xb91f0000, dst_reg, dst_reg);
-			/* llgfr %dst,%dst */
-			EMIT4(0xb9160000, dst_reg, dst_reg);
+			if (!fp->aux->verifier_zext)
+				/* llgfr %dst,%dst */
+				EMIT4(0xb9160000, dst_reg, dst_reg);
 			break;
 		case 64: /* dst = (u64) cpu_to_le64(dst) */
 			/* lrvgr %dst,%dst */
@@ -968,16 +984,22 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 		/* llgc %dst,0(off,%src) */
 		EMIT6_DISP_LH(0xe3000000, 0x0090, dst_reg, src_reg, REG_0, off);
 		jit->seen |= SEEN_MEM;
+		if (insn_is_zext(&insn[1]))
+			insn_count = 2;
 		break;
 	case BPF_LDX | BPF_MEM | BPF_H: /* dst = *(u16 *)(ul) (src + off) */
 		/* llgh %dst,0(off,%src) */
 		EMIT6_DISP_LH(0xe3000000, 0x0091, dst_reg, src_reg, REG_0, off);
 		jit->seen |= SEEN_MEM;
+		if (insn_is_zext(&insn[1]))
+			insn_count = 2;
 		break;
 	case BPF_LDX | BPF_MEM | BPF_W: /* dst = *(u32 *)(ul) (src + off) */
 		/* llgf %dst,off(%src) */
 		jit->seen |= SEEN_MEM;
 		EMIT6_DISP_LH(0xe3000000, 0x0016, dst_reg, src_reg, REG_0, off);
+		if (insn_is_zext(&insn[1]))
+			insn_count = 2;
 		break;
 	case BPF_LDX | BPF_MEM | BPF_DW: /* dst = *(u64 *)(ul) (src + off) */
 		/* lg %dst,0(off,%src) */
@@ -1282,6 +1304,11 @@ static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp)
 	return 0;
 }
 
+bool bpf_jit_needs_zext(void)
+{
+	return true;
+}
+
 /*
  * Compile eBPF program "fp"
  */
diff --git a/arch/sh/configs/se7712_defconfig b/arch/sh/configs/se7712_defconfig
index 5a1097641247..1e116529735f 100644
--- a/arch/sh/configs/se7712_defconfig
+++ b/arch/sh/configs/se7712_defconfig
@@ -63,7 +63,6 @@ CONFIG_NET_SCH_NETEM=y
 CONFIG_NET_CLS_TCINDEX=y
 CONFIG_NET_CLS_ROUTE4=y
 CONFIG_NET_CLS_FW=y
-CONFIG_NET_CLS_IND=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_MTD=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/sh/configs/se7721_defconfig b/arch/sh/configs/se7721_defconfig
index 9c0ef13bee10..c66e512719ab 100644
--- a/arch/sh/configs/se7721_defconfig
+++ b/arch/sh/configs/se7721_defconfig
@@ -62,7 +62,6 @@ CONFIG_NET_SCH_NETEM=y
 CONFIG_NET_CLS_TCINDEX=y
 CONFIG_NET_CLS_ROUTE4=y
 CONFIG_NET_CLS_FW=y
-CONFIG_NET_CLS_IND=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_MTD=y
 CONFIG_MTD_BLOCK=y
diff --git a/arch/sh/configs/titan_defconfig b/arch/sh/configs/titan_defconfig
index 822fa9e96f74..171ab05ce4fc 100644
--- a/arch/sh/configs/titan_defconfig
+++ b/arch/sh/configs/titan_defconfig
@@ -142,7 +142,6 @@ CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
 CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_PEDIT=m
-CONFIG_NET_CLS_IND=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_FW_LOADER=m
 CONFIG_CONNECTOR=m
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index 9265a9eece15..8029b681fc7c 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -115,6 +115,8 @@
 #define SO_RCVTIMEO_NEW          0x0044
 #define SO_SNDTIMEO_NEW          0x0045
 
+#define SO_DETACH_REUSEPORT_BPF  0x0047
+
 #if !defined(__KERNEL__)
 
 
diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c
index 65428e79b2f3..3364e2a00989 100644
--- a/arch/sparc/net/bpf_jit_comp_64.c
+++ b/arch/sparc/net/bpf_jit_comp_64.c
@@ -908,6 +908,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	/* dst = src */
 	case BPF_ALU | BPF_MOV | BPF_X:
 		emit_alu3_K(SRL, src, 0, dst, ctx);
+		if (insn_is_zext(&insn[1]))
+			return 1;
 		break;
 	case BPF_ALU64 | BPF_MOV | BPF_X:
 		emit_reg_move(src, dst, ctx);
@@ -942,6 +944,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_ALU | BPF_DIV | BPF_X:
 		emit_write_y(G0, ctx);
 		emit_alu(DIV, src, dst, ctx);
+		if (insn_is_zext(&insn[1]))
+			return 1;
 		break;
 	case BPF_ALU64 | BPF_DIV | BPF_X:
 		emit_alu(UDIVX, src, dst, ctx);
@@ -975,6 +979,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		break;
 	case BPF_ALU | BPF_RSH | BPF_X:
 		emit_alu(SRL, src, dst, ctx);
+		if (insn_is_zext(&insn[1]))
+			return 1;
 		break;
 	case BPF_ALU64 | BPF_RSH | BPF_X:
 		emit_alu(SRLX, src, dst, ctx);
@@ -997,9 +1003,12 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		case 16:
 			emit_alu_K(SLL, dst, 16, ctx);
 			emit_alu_K(SRL, dst, 16, ctx);
+			if (insn_is_zext(&insn[1]))
+				return 1;
 			break;
 		case 32:
-			emit_alu_K(SRL, dst, 0, ctx);
+			if (!ctx->prog->aux->verifier_zext)
+				emit_alu_K(SRL, dst, 0, ctx);
 			break;
 		case 64:
 			/* nop */
@@ -1021,6 +1030,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			emit_alu3_K(AND, dst, 0xff, dst, ctx);
 			emit_alu3_K(SLL, tmp, 8, tmp, ctx);
 			emit_alu(OR, tmp, dst, ctx);
+			if (insn_is_zext(&insn[1]))
+				return 1;
 			break;
 
 		case 32:
@@ -1037,6 +1048,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			emit_alu3_K(AND, dst, 0xff, dst, ctx);	/* dst	= dst & 0xff */
 			emit_alu3_K(SLL, dst, 24, dst, ctx);	/* dst  = dst << 24 */
 			emit_alu(OR, tmp, dst, ctx);		/* dst  = dst | tmp */
+			if (insn_is_zext(&insn[1]))
+				return 1;
 			break;
 
 		case 64:
@@ -1050,6 +1063,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	/* dst = imm */
 	case BPF_ALU | BPF_MOV | BPF_K:
 		emit_loadimm32(imm, dst, ctx);
+		if (insn_is_zext(&insn[1]))
+			return 1;
 		break;
 	case BPF_ALU64 | BPF_MOV | BPF_K:
 		emit_loadimm_sext(imm, dst, ctx);
@@ -1132,6 +1147,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		break;
 	case BPF_ALU | BPF_RSH | BPF_K:
 		emit_alu_K(SRL, dst, imm, ctx);
+		if (insn_is_zext(&insn[1]))
+			return 1;
 		break;
 	case BPF_ALU64 | BPF_RSH | BPF_K:
 		emit_alu_K(SRLX, dst, imm, ctx);
@@ -1144,7 +1161,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		break;
 
 	do_alu32_trunc:
-		if (BPF_CLASS(code) == BPF_ALU)
+		if (BPF_CLASS(code) == BPF_ALU &&
+		    !ctx->prog->aux->verifier_zext)
 			emit_alu_K(SRL, dst, 0, ctx);
 		break;
 
@@ -1265,6 +1283,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			rs2 = RS2(tmp);
 		}
 		emit(opcode | RS1(src) | rs2 | RD(dst), ctx);
+		if (opcode != LD64 && insn_is_zext(&insn[1]))
+			return 1;
 		break;
 	}
 	/* ST: *(size *)(dst + off) = imm */
@@ -1432,6 +1452,11 @@ static void jit_fill_hole(void *area, unsigned int size)
 		*ptr++ = 0x91d02005; /* ta 5 */
 }
 
+bool bpf_jit_needs_zext(void)
+{
+	return true;
+}
+
 struct sparc64_jit_data {
 	struct bpf_binary_header *header;
 	u8 *image;
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index b29e82f190c7..393d251798c0 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -253,13 +253,14 @@ static inline void emit_ia32_mov_r(const u8 dst, const u8 src, bool dstk,
 /* dst = src */
 static inline void emit_ia32_mov_r64(const bool is64, const u8 dst[],
 				     const u8 src[], bool dstk,
-				     bool sstk, u8 **pprog)
+				     bool sstk, u8 **pprog,
+				     const struct bpf_prog_aux *aux)
 {
 	emit_ia32_mov_r(dst_lo, src_lo, dstk, sstk, pprog);
 	if (is64)
 		/* complete 8 byte move */
 		emit_ia32_mov_r(dst_hi, src_hi, dstk, sstk, pprog);
-	else
+	else if (!aux->verifier_zext)
 		/* zero out high 4 bytes */
 		emit_ia32_mov_i(dst_hi, 0, dstk, pprog);
 }
@@ -313,7 +314,8 @@ static inline void emit_ia32_mul_r(const u8 dst, const u8 src, bool dstk,
 }
 
 static inline void emit_ia32_to_le_r64(const u8 dst[], s32 val,
-					 bool dstk, u8 **pprog)
+					 bool dstk, u8 **pprog,
+					 const struct bpf_prog_aux *aux)
 {
 	u8 *prog = *pprog;
 	int cnt = 0;
@@ -334,12 +336,14 @@ static inline void emit_ia32_to_le_r64(const u8 dst[], s32 val,
 		 */
 		EMIT2(0x0F, 0xB7);
 		EMIT1(add_2reg(0xC0, dreg_lo, dreg_lo));
-		/* xor dreg_hi,dreg_hi */
-		EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+		if (!aux->verifier_zext)
+			/* xor dreg_hi,dreg_hi */
+			EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
 		break;
 	case 32:
-		/* xor dreg_hi,dreg_hi */
-		EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+		if (!aux->verifier_zext)
+			/* xor dreg_hi,dreg_hi */
+			EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
 		break;
 	case 64:
 		/* nop */
@@ -358,7 +362,8 @@ static inline void emit_ia32_to_le_r64(const u8 dst[], s32 val,
 }
 
 static inline void emit_ia32_to_be_r64(const u8 dst[], s32 val,
-				       bool dstk, u8 **pprog)
+				       bool dstk, u8 **pprog,
+				       const struct bpf_prog_aux *aux)
 {
 	u8 *prog = *pprog;
 	int cnt = 0;
@@ -380,16 +385,18 @@ static inline void emit_ia32_to_be_r64(const u8 dst[], s32 val,
 		EMIT2(0x0F, 0xB7);
 		EMIT1(add_2reg(0xC0, dreg_lo, dreg_lo));
 
-		/* xor dreg_hi,dreg_hi */
-		EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+		if (!aux->verifier_zext)
+			/* xor dreg_hi,dreg_hi */
+			EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
 		break;
 	case 32:
 		/* Emit 'bswap eax' to swap lower 4 bytes */
 		EMIT1(0x0F);
 		EMIT1(add_1reg(0xC8, dreg_lo));
 
-		/* xor dreg_hi,dreg_hi */
-		EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
+		if (!aux->verifier_zext)
+			/* xor dreg_hi,dreg_hi */
+			EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
 		break;
 	case 64:
 		/* Emit 'bswap eax' to swap lower 4 bytes */
@@ -569,7 +576,7 @@ static inline void emit_ia32_alu_r(const bool is64, const bool hi, const u8 op,
 static inline void emit_ia32_alu_r64(const bool is64, const u8 op,
 				     const u8 dst[], const u8 src[],
 				     bool dstk,  bool sstk,
-				     u8 **pprog)
+				     u8 **pprog, const struct bpf_prog_aux *aux)
 {
 	u8 *prog = *pprog;
 
@@ -577,7 +584,7 @@ static inline void emit_ia32_alu_r64(const bool is64, const u8 op,
 	if (is64)
 		emit_ia32_alu_r(is64, true, op, dst_hi, src_hi, dstk, sstk,
 				&prog);
-	else
+	else if (!aux->verifier_zext)
 		emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
 	*pprog = prog;
 }
@@ -668,7 +675,8 @@ static inline void emit_ia32_alu_i(const bool is64, const bool hi, const u8 op,
 /* ALU operation (64 bit) */
 static inline void emit_ia32_alu_i64(const bool is64, const u8 op,
 				     const u8 dst[], const u32 val,
-				     bool dstk, u8 **pprog)
+				     bool dstk, u8 **pprog,
+				     const struct bpf_prog_aux *aux)
 {
 	u8 *prog = *pprog;
 	u32 hi = 0;
@@ -679,7 +687,7 @@ static inline void emit_ia32_alu_i64(const bool is64, const u8 op,
 	emit_ia32_alu_i(is64, false, op, dst_lo, val, dstk, &prog);
 	if (is64)
 		emit_ia32_alu_i(is64, true, op, dst_hi, hi, dstk, &prog);
-	else
+	else if (!aux->verifier_zext)
 		emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
 
 	*pprog = prog;
@@ -724,9 +732,6 @@ static inline void emit_ia32_lsh_r64(const u8 dst[], const u8 src[],
 {
 	u8 *prog = *pprog;
 	int cnt = 0;
-	static int jmp_label1 = -1;
-	static int jmp_label2 = -1;
-	static int jmp_label3 = -1;
 	u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
 	u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
 
@@ -745,78 +750,22 @@ static inline void emit_ia32_lsh_r64(const u8 dst[], const u8 src[],
 		/* mov ecx,src_lo */
 		EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_ECX));
 
-	/* cmp ecx,32 */
-	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
-	/* Jumps when >= 32 */
-	if (is_imm8(jmp_label(jmp_label1, 2)))
-		EMIT2(IA32_JAE, jmp_label(jmp_label1, 2));
-	else
-		EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label1, 6));
-
-	/* < 32 */
-	/* shl dreg_hi,cl */
-	EMIT2(0xD3, add_1reg(0xE0, dreg_hi));
-	/* mov ebx,dreg_lo */
-	EMIT2(0x8B, add_2reg(0xC0, dreg_lo, IA32_EBX));
+	/* shld dreg_hi,dreg_lo,cl */
+	EMIT3(0x0F, 0xA5, add_2reg(0xC0, dreg_hi, dreg_lo));
 	/* shl dreg_lo,cl */
 	EMIT2(0xD3, add_1reg(0xE0, dreg_lo));
 
-	/* IA32_ECX = -IA32_ECX + 32 */
-	/* neg ecx */
-	EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
-	/* add ecx,32 */
-	EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
+	/* if ecx >= 32, mov dreg_lo into dreg_hi and clear dreg_lo */
 
-	/* shr ebx,cl */
-	EMIT2(0xD3, add_1reg(0xE8, IA32_EBX));
-	/* or dreg_hi,ebx */
-	EMIT2(0x09, add_2reg(0xC0, dreg_hi, IA32_EBX));
-
-	/* goto out; */
-	if (is_imm8(jmp_label(jmp_label3, 2)))
-		EMIT2(0xEB, jmp_label(jmp_label3, 2));
-	else
-		EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
-
-	/* >= 32 */
-	if (jmp_label1 == -1)
-		jmp_label1 = cnt;
-
-	/* cmp ecx,64 */
-	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 64);
-	/* Jumps when >= 64 */
-	if (is_imm8(jmp_label(jmp_label2, 2)))
-		EMIT2(IA32_JAE, jmp_label(jmp_label2, 2));
-	else
-		EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label2, 6));
+	/* cmp ecx,32 */
+	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
+	/* skip the next two instructions (4 bytes) when < 32 */
+	EMIT2(IA32_JB, 4);
 
-	/* >= 32 && < 64 */
-	/* sub ecx,32 */
-	EMIT3(0x83, add_1reg(0xE8, IA32_ECX), 32);
-	/* shl dreg_lo,cl */
-	EMIT2(0xD3, add_1reg(0xE0, dreg_lo));
 	/* mov dreg_hi,dreg_lo */
 	EMIT2(0x89, add_2reg(0xC0, dreg_hi, dreg_lo));
-
-	/* xor dreg_lo,dreg_lo */
-	EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo));
-
-	/* goto out; */
-	if (is_imm8(jmp_label(jmp_label3, 2)))
-		EMIT2(0xEB, jmp_label(jmp_label3, 2));
-	else
-		EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
-
-	/* >= 64 */
-	if (jmp_label2 == -1)
-		jmp_label2 = cnt;
 	/* xor dreg_lo,dreg_lo */
 	EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo));
-	/* xor dreg_hi,dreg_hi */
-	EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
-
-	if (jmp_label3 == -1)
-		jmp_label3 = cnt;
 
 	if (dstk) {
 		/* mov dword ptr [ebp+off],dreg_lo */
@@ -836,9 +785,6 @@ static inline void emit_ia32_arsh_r64(const u8 dst[], const u8 src[],
 {
 	u8 *prog = *pprog;
 	int cnt = 0;
-	static int jmp_label1 = -1;
-	static int jmp_label2 = -1;
-	static int jmp_label3 = -1;
 	u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
 	u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
 
@@ -857,79 +803,23 @@ static inline void emit_ia32_arsh_r64(const u8 dst[], const u8 src[],
 		/* mov ecx,src_lo */
 		EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_ECX));
 
-	/* cmp ecx,32 */
-	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
-	/* Jumps when >= 32 */
-	if (is_imm8(jmp_label(jmp_label1, 2)))
-		EMIT2(IA32_JAE, jmp_label(jmp_label1, 2));
-	else
-		EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label1, 6));
-
-	/* < 32 */
-	/* lshr dreg_lo,cl */
-	EMIT2(0xD3, add_1reg(0xE8, dreg_lo));
-	/* mov ebx,dreg_hi */
-	EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX));
-	/* ashr dreg_hi,cl */
+	/* shrd dreg_lo,dreg_hi,cl */
+	EMIT3(0x0F, 0xAD, add_2reg(0xC0, dreg_lo, dreg_hi));
+	/* sar dreg_hi,cl */
 	EMIT2(0xD3, add_1reg(0xF8, dreg_hi));
 
-	/* IA32_ECX = -IA32_ECX + 32 */
-	/* neg ecx */
-	EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
-	/* add ecx,32 */
-	EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
-
-	/* shl ebx,cl */
-	EMIT2(0xD3, add_1reg(0xE0, IA32_EBX));
-	/* or dreg_lo,ebx */
-	EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX));
-
-	/* goto out; */
-	if (is_imm8(jmp_label(jmp_label3, 2)))
-		EMIT2(0xEB, jmp_label(jmp_label3, 2));
-	else
-		EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
-
-	/* >= 32 */
-	if (jmp_label1 == -1)
-		jmp_label1 = cnt;
+	/* if ecx >= 32, mov dreg_hi to dreg_lo and set/clear dreg_hi depending on sign */
 
-	/* cmp ecx,64 */
-	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 64);
-	/* Jumps when >= 64 */
-	if (is_imm8(jmp_label(jmp_label2, 2)))
-		EMIT2(IA32_JAE, jmp_label(jmp_label2, 2));
-	else
-		EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label2, 6));
+	/* cmp ecx,32 */
+	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
+	/* skip the next two instructions (5 bytes) when < 32 */
+	EMIT2(IA32_JB, 5);
 
-	/* >= 32 && < 64 */
-	/* sub ecx,32 */
-	EMIT3(0x83, add_1reg(0xE8, IA32_ECX), 32);
-	/* ashr dreg_hi,cl */
-	EMIT2(0xD3, add_1reg(0xF8, dreg_hi));
 	/* mov dreg_lo,dreg_hi */
 	EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi));
-
-	/* ashr dreg_hi,imm8 */
+	/* sar dreg_hi,31 */
 	EMIT3(0xC1, add_1reg(0xF8, dreg_hi), 31);
 
-	/* goto out; */
-	if (is_imm8(jmp_label(jmp_label3, 2)))
-		EMIT2(0xEB, jmp_label(jmp_label3, 2));
-	else
-		EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
-
-	/* >= 64 */
-	if (jmp_label2 == -1)
-		jmp_label2 = cnt;
-	/* ashr dreg_hi,imm8 */
-	EMIT3(0xC1, add_1reg(0xF8, dreg_hi), 31);
-	/* mov dreg_lo,dreg_hi */
-	EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi));
-
-	if (jmp_label3 == -1)
-		jmp_label3 = cnt;
-
 	if (dstk) {
 		/* mov dword ptr [ebp+off],dreg_lo */
 		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
@@ -948,9 +838,6 @@ static inline void emit_ia32_rsh_r64(const u8 dst[], const u8 src[], bool dstk,
 {
 	u8 *prog = *pprog;
 	int cnt = 0;
-	static int jmp_label1 = -1;
-	static int jmp_label2 = -1;
-	static int jmp_label3 = -1;
 	u8 dreg_lo = dstk ? IA32_EAX : dst_lo;
 	u8 dreg_hi = dstk ? IA32_EDX : dst_hi;
 
@@ -969,77 +856,23 @@ static inline void emit_ia32_rsh_r64(const u8 dst[], const u8 src[], bool dstk,
 		/* mov ecx,src_lo */
 		EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_ECX));
 
-	/* cmp ecx,32 */
-	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
-	/* Jumps when >= 32 */
-	if (is_imm8(jmp_label(jmp_label1, 2)))
-		EMIT2(IA32_JAE, jmp_label(jmp_label1, 2));
-	else
-		EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label1, 6));
-
-	/* < 32 */
-	/* lshr dreg_lo,cl */
-	EMIT2(0xD3, add_1reg(0xE8, dreg_lo));
-	/* mov ebx,dreg_hi */
-	EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX));
+	/* shrd dreg_lo,dreg_hi,cl */
+	EMIT3(0x0F, 0xAD, add_2reg(0xC0, dreg_lo, dreg_hi));
 	/* shr dreg_hi,cl */
 	EMIT2(0xD3, add_1reg(0xE8, dreg_hi));
 
-	/* IA32_ECX = -IA32_ECX + 32 */
-	/* neg ecx */
-	EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
-	/* add ecx,32 */
-	EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
-
-	/* shl ebx,cl */
-	EMIT2(0xD3, add_1reg(0xE0, IA32_EBX));
-	/* or dreg_lo,ebx */
-	EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX));
-
-	/* goto out; */
-	if (is_imm8(jmp_label(jmp_label3, 2)))
-		EMIT2(0xEB, jmp_label(jmp_label3, 2));
-	else
-		EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
+	/* if ecx >= 32, mov dreg_hi to dreg_lo and clear dreg_hi */
 
-	/* >= 32 */
-	if (jmp_label1 == -1)
-		jmp_label1 = cnt;
-	/* cmp ecx,64 */
-	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 64);
-	/* Jumps when >= 64 */
-	if (is_imm8(jmp_label(jmp_label2, 2)))
-		EMIT2(IA32_JAE, jmp_label(jmp_label2, 2));
-	else
-		EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label2, 6));
+	/* cmp ecx,32 */
+	EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32);
+	/* skip the next two instructions (4 bytes) when < 32 */
+	EMIT2(IA32_JB, 4);
 
-	/* >= 32 && < 64 */
-	/* sub ecx,32 */
-	EMIT3(0x83, add_1reg(0xE8, IA32_ECX), 32);
-	/* shr dreg_hi,cl */
-	EMIT2(0xD3, add_1reg(0xE8, dreg_hi));
 	/* mov dreg_lo,dreg_hi */
 	EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi));
 	/* xor dreg_hi,dreg_hi */
 	EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
 
-	/* goto out; */
-	if (is_imm8(jmp_label(jmp_label3, 2)))
-		EMIT2(0xEB, jmp_label(jmp_label3, 2));
-	else
-		EMIT1_off32(0xE9, jmp_label(jmp_label3, 5));
-
-	/* >= 64 */
-	if (jmp_label2 == -1)
-		jmp_label2 = cnt;
-	/* xor dreg_lo,dreg_lo */
-	EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo));
-	/* xor dreg_hi,dreg_hi */
-	EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));
-
-	if (jmp_label3 == -1)
-		jmp_label3 = cnt;
-
 	if (dstk) {
 		/* mov dword ptr [ebp+off],dreg_lo */
 		EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo),
@@ -1069,27 +902,10 @@ static inline void emit_ia32_lsh_i64(const u8 dst[], const u32 val,
 	}
 	/* Do LSH operation */
 	if (val < 32) {
-		/* shl dreg_hi,imm8 */
-		EMIT3(0xC1, add_1reg(0xE0, dreg_hi), val);
-		/* mov ebx,dreg_lo */
-		EMIT2(0x8B, add_2reg(0xC0, dreg_lo, IA32_EBX));
+		/* shld dreg_hi,dreg_lo,imm8 */
+		EMIT4(0x0F, 0xA4, add_2reg(0xC0, dreg_hi, dreg_lo), val);
 		/* shl dreg_lo,imm8 */
 		EMIT3(0xC1, add_1reg(0xE0, dreg_lo), val);
-
-		/* IA32_ECX = 32 - val */
-		/* mov ecx,val */
-		EMIT2(0xB1, val);
-		/* movzx ecx,ecx */
-		EMIT3(0x0F, 0xB6, add_2reg(0xC0, IA32_ECX, IA32_ECX));
-		/* neg ecx */
-		EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
-		/* add ecx,32 */
-		EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
-
-		/* shr ebx,cl */
-		EMIT2(0xD3, add_1reg(0xE8, IA32_EBX));
-		/* or dreg_hi,ebx */
-		EMIT2(0x09, add_2reg(0xC0, dreg_hi, IA32_EBX));
 	} else if (val >= 32 && val < 64) {
 		u32 value = val - 32;
 
@@ -1135,27 +951,10 @@ static inline void emit_ia32_rsh_i64(const u8 dst[], const u32 val,
 
 	/* Do RSH operation */
 	if (val < 32) {
-		/* shr dreg_lo,imm8 */
-		EMIT3(0xC1, add_1reg(0xE8, dreg_lo), val);
-		/* mov ebx,dreg_hi */
-		EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX));
+		/* shrd dreg_lo,dreg_hi,imm8 */
+		EMIT4(0x0F, 0xAC, add_2reg(0xC0, dreg_lo, dreg_hi), val);
 		/* shr dreg_hi,imm8 */
 		EMIT3(0xC1, add_1reg(0xE8, dreg_hi), val);
-
-		/* IA32_ECX = 32 - val */
-		/* mov ecx,val */
-		EMIT2(0xB1, val);
-		/* movzx ecx,ecx */
-		EMIT3(0x0F, 0xB6, add_2reg(0xC0, IA32_ECX, IA32_ECX));
-		/* neg ecx */
-		EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
-		/* add ecx,32 */
-		EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
-
-		/* shl ebx,cl */
-		EMIT2(0xD3, add_1reg(0xE0, IA32_EBX));
-		/* or dreg_lo,ebx */
-		EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX));
 	} else if (val >= 32 && val < 64) {
 		u32 value = val - 32;
 
@@ -1200,27 +999,10 @@ static inline void emit_ia32_arsh_i64(const u8 dst[], const u32 val,
 	}
 	/* Do RSH operation */
 	if (val < 32) {
-		/* shr dreg_lo,imm8 */
-		EMIT3(0xC1, add_1reg(0xE8, dreg_lo), val);
-		/* mov ebx,dreg_hi */
-		EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX));
+		/* shrd dreg_lo,dreg_hi,imm8 */
+		EMIT4(0x0F, 0xAC, add_2reg(0xC0, dreg_lo, dreg_hi), val);
 		/* ashr dreg_hi,imm8 */
 		EMIT3(0xC1, add_1reg(0xF8, dreg_hi), val);
-
-		/* IA32_ECX = 32 - val */
-		/* mov ecx,val */
-		EMIT2(0xB1, val);
-		/* movzx ecx,ecx */
-		EMIT3(0x0F, 0xB6, add_2reg(0xC0, IA32_ECX, IA32_ECX));
-		/* neg ecx */
-		EMIT2(0xF7, add_1reg(0xD8, IA32_ECX));
-		/* add ecx,32 */
-		EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32);
-
-		/* shl ebx,cl */
-		EMIT2(0xD3, add_1reg(0xE0, IA32_EBX));
-		/* or dreg_lo,ebx */
-		EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX));
 	} else if (val >= 32 && val < 64) {
 		u32 value = val - 32;
 
@@ -1713,8 +1495,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_ALU64 | BPF_MOV | BPF_X:
 			switch (BPF_SRC(code)) {
 			case BPF_X:
-				emit_ia32_mov_r64(is64, dst, src, dstk,
-						  sstk, &prog);
+				if (imm32 == 1) {
+					/* Special mov32 for zext. */
+					emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+					break;
+				}
+				emit_ia32_mov_r64(is64, dst, src, dstk, sstk,
+						  &prog, bpf_prog->aux);
 				break;
 			case BPF_K:
 				/* Sign-extend immediate value to dst reg */
@@ -1754,11 +1541,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			switch (BPF_SRC(code)) {
 			case BPF_X:
 				emit_ia32_alu_r64(is64, BPF_OP(code), dst,
-						  src, dstk, sstk, &prog);
+						  src, dstk, sstk, &prog,
+						  bpf_prog->aux);
 				break;
 			case BPF_K:
 				emit_ia32_alu_i64(is64, BPF_OP(code), dst,
-						  imm32, dstk, &prog);
+						  imm32, dstk, &prog,
+						  bpf_prog->aux);
 				break;
 			}
 			break;
@@ -1777,7 +1566,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 						false, &prog);
 				break;
 			}
-			emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+			if (!bpf_prog->aux->verifier_zext)
+				emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
 			break;
 		case BPF_ALU | BPF_LSH | BPF_X:
 		case BPF_ALU | BPF_RSH | BPF_X:
@@ -1797,7 +1587,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 						  &prog);
 				break;
 			}
-			emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+			if (!bpf_prog->aux->verifier_zext)
+				emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
 			break;
 		/* dst = dst / src(imm) */
 		/* dst = dst % src(imm) */
@@ -1819,7 +1610,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 						    &prog);
 				break;
 			}
-			emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+			if (!bpf_prog->aux->verifier_zext)
+				emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
 			break;
 		case BPF_ALU64 | BPF_DIV | BPF_K:
 		case BPF_ALU64 | BPF_DIV | BPF_X:
@@ -1836,7 +1628,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX), imm32);
 			emit_ia32_shift_r(BPF_OP(code), dst_lo, IA32_ECX, dstk,
 					  false, &prog);
-			emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+			if (!bpf_prog->aux->verifier_zext)
+				emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
 			break;
 		/* dst = dst << imm */
 		case BPF_ALU64 | BPF_LSH | BPF_K:
@@ -1872,7 +1665,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_ALU | BPF_NEG:
 			emit_ia32_alu_i(is64, false, BPF_OP(code),
 					dst_lo, 0, dstk, &prog);
-			emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
+			if (!bpf_prog->aux->verifier_zext)
+				emit_ia32_mov_i(dst_hi, 0, dstk, &prog);
 			break;
 		/* dst = ~dst (64 bit) */
 		case BPF_ALU64 | BPF_NEG:
@@ -1892,11 +1686,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			break;
 		/* dst = htole(dst) */
 		case BPF_ALU | BPF_END | BPF_FROM_LE:
-			emit_ia32_to_le_r64(dst, imm32, dstk, &prog);
+			emit_ia32_to_le_r64(dst, imm32, dstk, &prog,
+					    bpf_prog->aux);
 			break;
 		/* dst = htobe(dst) */
 		case BPF_ALU | BPF_END | BPF_FROM_BE:
-			emit_ia32_to_be_r64(dst, imm32, dstk, &prog);
+			emit_ia32_to_be_r64(dst, imm32, dstk, &prog,
+					    bpf_prog->aux);
 			break;
 		/* dst = imm64 */
 		case BPF_LD | BPF_IMM | BPF_DW: {
@@ -2051,6 +1847,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			case BPF_B:
 			case BPF_H:
 			case BPF_W:
+				if (!bpf_prog->aux->verifier_zext)
+					break;
 				if (dstk) {
 					EMIT3(0xC7, add_1reg(0x40, IA32_EBP),
 					      STACK_VAR(dst_hi));
@@ -2475,6 +2273,11 @@ notyet:
 	return proglen;
 }
 
+bool bpf_jit_needs_zext(void)
+{
+	return true;
+}
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
 	struct bpf_binary_header *header = NULL;