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

Pull networking updates from David Miller: 1) Seccomp BPF filters can now be JIT'd, from Alexei Starovoitov. 2) Multiqueue support in xen-netback and xen-netfront, from Andrew J Benniston. 3) Allow tweaking of aggregation settings in cdc_ncm driver, from Bjørn Mork. 4) BPF now has a "random" opcode, from Chema Gonzalez. 5) Add more BPF documentation and improve test framework, from Daniel Borkmann. 6) Support TCP fastopen over ipv6, from Daniel Lee. 7) Add software TSO helper functions and use them to support software TSO in mvneta and mv643xx_eth drivers. From Ezequiel Garcia. 8) Support software TSO in fec driver too, from Nimrod Andy. 9) Add Broadcom SYSTEMPORT driver, from Florian Fainelli. 10) Handle broadcasts more gracefully over macvlan when there are large numbers of interfaces configured, from Herbert Xu. 11) Allow more control over fwmark used for non-socket based responses, from Lorenzo Colitti. 12) Do TCP congestion window limiting based upon measurements, from Neal Cardwell. 13) Support busy polling in SCTP, from Neal Horman. 14) Allow RSS key to be configured via ethtool, from Venkata Duvvuru. 15) Bridge promisc mode handling improvements from Vlad Yasevich. 16) Don't use inetpeer entries to implement ID generation any more, it performs poorly, from Eric Dumazet. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1522 commits) rtnetlink: fix userspace API breakage for iproute2 < v3.9.0 tcp: fixing TLP's FIN recovery net: fec: Add software TSO support net: fec: Add Scatter/gather support net: fec: Increase buffer descriptor entry number net: fec: Factorize feature setting net: fec: Enable IP header hardware checksum net: fec: Factorize the .xmit transmit function bridge: fix compile error when compiling without IPv6 support bridge: fix smatch warning / potential null pointer dereference via-rhine: fix full-duplex with autoneg disable bnx2x: Enlarge the dorq threshold for VFs bnx2x: Check for UNDI in uncommon branch bnx2x: Fix 1G-baseT link bnx2x: Fix link for KR with swapped polarity lane sctp: Fix sk_ack_backlog wrap-around problem net/core: Add VF link state control policy net/fsl: xgmac_mdio is dependent on OF_MDIO net/fsl: Make xgmac_mdio read error message useful net_sched: drr: warn when qdisc is not work conserving ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2014-06-12 21:27:40 (GMT)
committer: Linus Torvalds <torvalds@linux-foundation.org> 2014-06-12 21:27:40 (GMT)
commit: f9da455b93f6ba076935b4ef4589f61e529ae046 (patch)
tree: 3c4e69ce1ba1d6bf65915b97a76ca2172105b278 /arch
parent: 0e04c641b199435f3779454055f6a7de258ecdfc (diff)
parent: e5eca6d41f53db48edd8cf88a3f59d2c30227f8e (diff)
download: linux-f9da455b93f6ba076935b4ef4589f61e529ae046.tar.xz
19 files changed, 1151 insertions, 1044 deletions
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 9f53e82..4a4e02d 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -662,6 +662,8 @@
 		mac: ethernet@4a100000 {
 			compatible = "ti,cpsw";
 			ti,hwmods = "cpgmac0";
+			clocks = <&cpsw_125mhz_gclk>, <&cpsw_cpts_rft_clk>;
+			clock-names = "fck", "cpts";
 			cpdma_channels = <8>;
 			ale_entries = <1024>;
 			bd_ram_size = <0x2000>;
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index db464d7..49fa596 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -490,6 +490,8 @@
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ti,hwmods = "cpgmac0";
+			clocks = <&cpsw_125mhz_gclk>, <&cpsw_cpts_rft_clk>;
+			clock-names = "fck", "cpts";
 			status = "disabled";
 			cpdma_channels = <8>;
 			ale_entries = <1024>;
diff --git a/arch/arm/boot/dts/armada-xp-matrix.dts b/arch/arm/boot/dts/armada-xp-matrix.dts
index 25674fe..7e291e2 100644
--- a/arch/arm/boot/dts/armada-xp-matrix.dts
+++ b/arch/arm/boot/dts/armada-xp-matrix.dts
@@ -57,6 +57,10 @@
 			ethernet@30000 {
 				status = "okay";
 				phy-mode = "sgmii";
+				fixed-link {
+					speed = <1000>;
+					full-duplex;
+				};
 			};
 
 			pcie-controller {
diff --git a/arch/arm/boot/dts/vt8500.dtsi b/arch/arm/boot/dts/vt8500.dtsi
index 51d0e91..1929ad3 100644
--- a/arch/arm/boot/dts/vt8500.dtsi
+++ b/arch/arm/boot/dts/vt8500.dtsi
@@ -165,5 +165,11 @@
 			reg = <0xd8100000 0x10000>;
 			interrupts = <48>;
 		};
+
+		ethernet@d8004000 {
+			compatible = "via,vt8500-rhine";
+			reg = <0xd8004000 0x100>;
+			interrupts = <10>;
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/wm8650.dtsi b/arch/arm/boot/dts/wm8650.dtsi
index 7525982..b1c59a7 100644
--- a/arch/arm/boot/dts/wm8650.dtsi
+++ b/arch/arm/boot/dts/wm8650.dtsi
@@ -218,5 +218,11 @@
 			reg = <0xd8100000 0x10000>;
 			interrupts = <48>;
 		};
+
+		ethernet@d8004000 {
+			compatible = "via,vt8500-rhine";
+			reg = <0xd8004000 0x100>;
+			interrupts = <10>;
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/wm8850.dtsi b/arch/arm/boot/dts/wm8850.dtsi
index d98386d..8fbccfbe 100644
--- a/arch/arm/boot/dts/wm8850.dtsi
+++ b/arch/arm/boot/dts/wm8850.dtsi
@@ -298,5 +298,11 @@
 			bus-width = <4>;
 			sdon-inverted;
 		};
+
+		ethernet@d8004000 {
+			compatible = "via,vt8500-rhine";
+			reg = <0xd8004000 0x100>;
+			interrupts = <10>;
+                };
 	};
 };
diff --git a/arch/arm/mach-tegra/board-paz00.c b/arch/arm/mach-tegra/board-paz00.c
index e4dec9f..9c6029b 100644
--- a/arch/arm/mach-tegra/board-paz00.c
+++ b/arch/arm/mach-tegra/board-paz00.c
@@ -23,9 +23,7 @@
 #include "board.h"
 
 static struct rfkill_gpio_platform_data wifi_rfkill_platform_data = {
-	.name		= "wifi_rfkill",
-	.reset_gpio	= 25, /* PD1 */
-	.shutdown_gpio	= 85, /* PK5 */
+	.name	= "wifi_rfkill",
 	.type	= RFKILL_TYPE_WLAN,
 };
 
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 6f879c3..fb5503c 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -136,7 +136,7 @@ static u16 saved_regs(struct jit_ctx *ctx)
 	u16 ret = 0;
 
 	if ((ctx->skf->len > 1) ||
-	    (ctx->skf->insns[0].code == BPF_S_RET_A))
+	    (ctx->skf->insns[0].code == (BPF_RET | BPF_A)))
 		ret |= 1 << r_A;
 
 #ifdef CONFIG_FRAME_POINTER
@@ -164,18 +164,10 @@ static inline int mem_words_used(struct jit_ctx *ctx)
 static inline bool is_load_to_a(u16 inst)
 {
 	switch (inst) {
-	case BPF_S_LD_W_LEN:
-	case BPF_S_LD_W_ABS:
-	case BPF_S_LD_H_ABS:
-	case BPF_S_LD_B_ABS:
-	case BPF_S_ANC_CPU:
-	case BPF_S_ANC_IFINDEX:
-	case BPF_S_ANC_MARK:
-	case BPF_S_ANC_PROTOCOL:
-	case BPF_S_ANC_RXHASH:
-	case BPF_S_ANC_VLAN_TAG:
-	case BPF_S_ANC_VLAN_TAG_PRESENT:
-	case BPF_S_ANC_QUEUE:
+	case BPF_LD | BPF_W | BPF_LEN:
+	case BPF_LD | BPF_W | BPF_ABS:
+	case BPF_LD | BPF_H | BPF_ABS:
+	case BPF_LD | BPF_B | BPF_ABS:
 		return true;
 	default:
 		return false;
@@ -215,7 +207,7 @@ static void build_prologue(struct jit_ctx *ctx)
 		emit(ARM_MOV_I(r_X, 0), ctx);
 
 	/* do not leak kernel data to userspace */
-	if ((first_inst != BPF_S_RET_K) && !(is_load_to_a(first_inst)))
+	if ((first_inst != (BPF_RET | BPF_K)) && !(is_load_to_a(first_inst)))
 		emit(ARM_MOV_I(r_A, 0), ctx);
 
 	/* stack space for the BPF_MEM words */
@@ -480,36 +472,39 @@ static int build_body(struct jit_ctx *ctx)
 	u32 k;
 
 	for (i = 0; i < prog->len; i++) {
+		u16 code;
+
 		inst = &(prog->insns[i]);
 		/* K as an immediate value operand */
 		k = inst->k;
+		code = bpf_anc_helper(inst);
 
 		/* compute offsets only in the fake pass */
 		if (ctx->target == NULL)
 			ctx->offsets[i] = ctx->idx * 4;
 
-		switch (inst->code) {
-		case BPF_S_LD_IMM:
+		switch (code) {
+		case BPF_LD | BPF_IMM:
 			emit_mov_i(r_A, k, ctx);
 			break;
-		case BPF_S_LD_W_LEN:
+		case BPF_LD | BPF_W | BPF_LEN:
 			ctx->seen |= SEEN_SKB;
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4);
 			emit(ARM_LDR_I(r_A, r_skb,
 				       offsetof(struct sk_buff, len)), ctx);
 			break;
-		case BPF_S_LD_MEM:
+		case BPF_LD | BPF_MEM:
 			/* A = scratch[k] */
 			ctx->seen |= SEEN_MEM_WORD(k);
 			emit(ARM_LDR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx);
 			break;
-		case BPF_S_LD_W_ABS:
+		case BPF_LD | BPF_W | BPF_ABS:
 			load_order = 2;
 			goto load;
-		case BPF_S_LD_H_ABS:
+		case BPF_LD | BPF_H | BPF_ABS:
 			load_order = 1;
 			goto load;
-		case BPF_S_LD_B_ABS:
+		case BPF_LD | BPF_B | BPF_ABS:
 			load_order = 0;
 load:
 			/* the interpreter will deal with the negative K */
@@ -552,31 +547,31 @@ load_common:
 			emit_err_ret(ARM_COND_NE, ctx);
 			emit(ARM_MOV_R(r_A, ARM_R0), ctx);
 			break;
-		case BPF_S_LD_W_IND:
+		case BPF_LD | BPF_W | BPF_IND:
 			load_order = 2;
 			goto load_ind;
-		case BPF_S_LD_H_IND:
+		case BPF_LD | BPF_H | BPF_IND:
 			load_order = 1;
 			goto load_ind;
-		case BPF_S_LD_B_IND:
+		case BPF_LD | BPF_B | BPF_IND:
 			load_order = 0;
 load_ind:
 			OP_IMM3(ARM_ADD, r_off, r_X, k, ctx);
 			goto load_common;
-		case BPF_S_LDX_IMM:
+		case BPF_LDX | BPF_IMM:
 			ctx->seen |= SEEN_X;
 			emit_mov_i(r_X, k, ctx);
 			break;
-		case BPF_S_LDX_W_LEN:
+		case BPF_LDX | BPF_W | BPF_LEN:
 			ctx->seen |= SEEN_X | SEEN_SKB;
 			emit(ARM_LDR_I(r_X, r_skb,
 				       offsetof(struct sk_buff, len)), ctx);
 			break;
-		case BPF_S_LDX_MEM:
+		case BPF_LDX | BPF_MEM:
 			ctx->seen |= SEEN_X | SEEN_MEM_WORD(k);
 			emit(ARM_LDR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx);
 			break;
-		case BPF_S_LDX_B_MSH:
+		case BPF_LDX | BPF_B | BPF_MSH:
 			/* x = ((*(frame + k)) & 0xf) << 2; */
 			ctx->seen |= SEEN_X | SEEN_DATA | SEEN_CALL;
 			/* the interpreter should deal with the negative K */
@@ -606,113 +601,113 @@ load_ind:
 			emit(ARM_AND_I(r_X, ARM_R0, 0x00f), ctx);
 			emit(ARM_LSL_I(r_X, r_X, 2), ctx);
 			break;
-		case BPF_S_ST:
+		case BPF_ST:
 			ctx->seen |= SEEN_MEM_WORD(k);
 			emit(ARM_STR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx);
 			break;
-		case BPF_S_STX:
+		case BPF_STX:
 			update_on_xread(ctx);
 			ctx->seen |= SEEN_MEM_WORD(k);
 			emit(ARM_STR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx);
 			break;
-		case BPF_S_ALU_ADD_K:
+		case BPF_ALU | BPF_ADD | BPF_K:
 			/* A += K */
 			OP_IMM3(ARM_ADD, r_A, r_A, k, ctx);
 			break;
-		case BPF_S_ALU_ADD_X:
+		case BPF_ALU | BPF_ADD | BPF_X:
 			update_on_xread(ctx);
 			emit(ARM_ADD_R(r_A, r_A, r_X), ctx);
 			break;
-		case BPF_S_ALU_SUB_K:
+		case BPF_ALU | BPF_SUB | BPF_K:
 			/* A -= K */
 			OP_IMM3(ARM_SUB, r_A, r_A, k, ctx);
 			break;
-		case BPF_S_ALU_SUB_X:
+		case BPF_ALU | BPF_SUB | BPF_X:
 			update_on_xread(ctx);
 			emit(ARM_SUB_R(r_A, r_A, r_X), ctx);
 			break;
-		case BPF_S_ALU_MUL_K:
+		case BPF_ALU | BPF_MUL | BPF_K:
 			/* A *= K */
 			emit_mov_i(r_scratch, k, ctx);
 			emit(ARM_MUL(r_A, r_A, r_scratch), ctx);
 			break;
-		case BPF_S_ALU_MUL_X:
+		case BPF_ALU | BPF_MUL | BPF_X:
 			update_on_xread(ctx);
 			emit(ARM_MUL(r_A, r_A, r_X), ctx);
 			break;
-		case BPF_S_ALU_DIV_K:
+		case BPF_ALU | BPF_DIV | BPF_K:
 			if (k == 1)
 				break;
 			emit_mov_i(r_scratch, k, ctx);
 			emit_udiv(r_A, r_A, r_scratch, ctx);
 			break;
-		case BPF_S_ALU_DIV_X:
+		case BPF_ALU | BPF_DIV | BPF_X:
 			update_on_xread(ctx);
 			emit(ARM_CMP_I(r_X, 0), ctx);
 			emit_err_ret(ARM_COND_EQ, ctx);
 			emit_udiv(r_A, r_A, r_X, ctx);
 			break;
-		case BPF_S_ALU_OR_K:
+		case BPF_ALU | BPF_OR | BPF_K:
 			/* A |= K */
 			OP_IMM3(ARM_ORR, r_A, r_A, k, ctx);
 			break;
-		case BPF_S_ALU_OR_X:
+		case BPF_ALU | BPF_OR | BPF_X:
 			update_on_xread(ctx);
 			emit(ARM_ORR_R(r_A, r_A, r_X), ctx);
 			break;
-		case BPF_S_ALU_XOR_K:
+		case BPF_ALU | BPF_XOR | BPF_K:
 			/* A ^= K; */
 			OP_IMM3(ARM_EOR, r_A, r_A, k, ctx);
 			break;
-		case BPF_S_ANC_ALU_XOR_X:
-		case BPF_S_ALU_XOR_X:
+		case BPF_ANC | SKF_AD_ALU_XOR_X:
+		case BPF_ALU | BPF_XOR | BPF_X:
 			/* A ^= X */
 			update_on_xread(ctx);
 			emit(ARM_EOR_R(r_A, r_A, r_X), ctx);
 			break;
-		case BPF_S_ALU_AND_K:
+		case BPF_ALU | BPF_AND | BPF_K:
 			/* A &= K */
 			OP_IMM3(ARM_AND, r_A, r_A, k, ctx);
 			break;
-		case BPF_S_ALU_AND_X:
+		case BPF_ALU | BPF_AND | BPF_X:
 			update_on_xread(ctx);
 			emit(ARM_AND_R(r_A, r_A, r_X), ctx);
 			break;
-		case BPF_S_ALU_LSH_K:
+		case BPF_ALU | BPF_LSH | BPF_K:
 			if (unlikely(k > 31))
 				return -1;
 			emit(ARM_LSL_I(r_A, r_A, k), ctx);
 			break;
-		case BPF_S_ALU_LSH_X:
+		case BPF_ALU | BPF_LSH | BPF_X:
 			update_on_xread(ctx);
 			emit(ARM_LSL_R(r_A, r_A, r_X), ctx);
 			break;
-		case BPF_S_ALU_RSH_K:
+		case BPF_ALU | BPF_RSH | BPF_K:
 			if (unlikely(k > 31))
 				return -1;
 			emit(ARM_LSR_I(r_A, r_A, k), ctx);
 			break;
-		case BPF_S_ALU_RSH_X:
+		case BPF_ALU | BPF_RSH | BPF_X:
 			update_on_xread(ctx);
 			emit(ARM_LSR_R(r_A, r_A, r_X), ctx);
 			break;
-		case BPF_S_ALU_NEG:
+		case BPF_ALU | BPF_NEG:
 			/* A = -A */
 			emit(ARM_RSB_I(r_A, r_A, 0), ctx);
 			break;
-		case BPF_S_JMP_JA:
+		case BPF_JMP | BPF_JA:
 			/* pc += K */
 			emit(ARM_B(b_imm(i + k + 1, ctx)), ctx);
 			break;
-		case BPF_S_JMP_JEQ_K:
+		case BPF_JMP | BPF_JEQ | BPF_K:
 			/* pc += (A == K) ? pc->jt : pc->jf */
 			condt  = ARM_COND_EQ;
 			goto cmp_imm;
-		case BPF_S_JMP_JGT_K:
+		case BPF_JMP | BPF_JGT | BPF_K:
 			/* pc += (A > K) ? pc->jt : pc->jf */
 			condt  = ARM_COND_HI;
 			goto cmp_imm;
-		case BPF_S_JMP_JGE_K:
+		case BPF_JMP | BPF_JGE | BPF_K:
 			/* pc += (A >= K) ? pc->jt : pc->jf */
 			condt  = ARM_COND_HS;
 cmp_imm:
@@ -731,22 +726,22 @@ cond_jump:
 				_emit(condt ^ 1, ARM_B(b_imm(i + inst->jf + 1,
 							     ctx)), ctx);
 			break;
-		case BPF_S_JMP_JEQ_X:
+		case BPF_JMP | BPF_JEQ | BPF_X:
 			/* pc += (A == X) ? pc->jt : pc->jf */
 			condt   = ARM_COND_EQ;
 			goto cmp_x;
-		case BPF_S_JMP_JGT_X:
+		case BPF_JMP | BPF_JGT | BPF_X:
 			/* pc += (A > X) ? pc->jt : pc->jf */
 			condt   = ARM_COND_HI;
 			goto cmp_x;
-		case BPF_S_JMP_JGE_X:
+		case BPF_JMP | BPF_JGE | BPF_X:
 			/* pc += (A >= X) ? pc->jt : pc->jf */
 			condt   = ARM_COND_CS;
 cmp_x:
 			update_on_xread(ctx);
 			emit(ARM_CMP_R(r_A, r_X), ctx);
 			goto cond_jump;
-		case BPF_S_JMP_JSET_K:
+		case BPF_JMP | BPF_JSET | BPF_K:
 			/* pc += (A & K) ? pc->jt : pc->jf */
 			condt  = ARM_COND_NE;
 			/* not set iff all zeroes iff Z==1 iff EQ */
@@ -759,16 +754,16 @@ cmp_x:
 				emit(ARM_TST_I(r_A, imm12), ctx);
 			}
 			goto cond_jump;
-		case BPF_S_JMP_JSET_X:
+		case BPF_JMP | BPF_JSET | BPF_X:
 			/* pc += (A & X) ? pc->jt : pc->jf */
 			update_on_xread(ctx);
 			condt  = ARM_COND_NE;
 			emit(ARM_TST_R(r_A, r_X), ctx);
 			goto cond_jump;
-		case BPF_S_RET_A:
+		case BPF_RET | BPF_A:
 			emit(ARM_MOV_R(ARM_R0, r_A), ctx);
 			goto b_epilogue;
-		case BPF_S_RET_K:
+		case BPF_RET | BPF_K:
 			if ((k == 0) && (ctx->ret0_fp_idx < 0))
 				ctx->ret0_fp_idx = i;
 			emit_mov_i(ARM_R0, k, ctx);
@@ -776,17 +771,17 @@ b_epilogue:
 			if (i != ctx->skf->len - 1)
 				emit(ARM_B(b_imm(prog->len, ctx)), ctx);
 			break;
-		case BPF_S_MISC_TAX:
+		case BPF_MISC | BPF_TAX:
 			/* X = A */
 			ctx->seen |= SEEN_X;
 			emit(ARM_MOV_R(r_X, r_A), ctx);
 			break;
-		case BPF_S_MISC_TXA:
+		case BPF_MISC | BPF_TXA:
 			/* A = X */
 			update_on_xread(ctx);
 			emit(ARM_MOV_R(r_A, r_X), ctx);
 			break;
-		case BPF_S_ANC_PROTOCOL:
+		case BPF_ANC | SKF_AD_PROTOCOL:
 			/* A = ntohs(skb->protocol) */
 			ctx->seen |= SEEN_SKB;
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
@@ -795,7 +790,7 @@ b_epilogue:
 			emit(ARM_LDRH_I(r_scratch, r_skb, off), ctx);
 			emit_swap16(r_A, r_scratch, ctx);
 			break;
-		case BPF_S_ANC_CPU:
+		case BPF_ANC | SKF_AD_CPU:
 			/* r_scratch = current_thread_info() */
 			OP_IMM3(ARM_BIC, r_scratch, ARM_SP, THREAD_SIZE - 1, ctx);
 			/* A = current_thread_info()->cpu */
@@ -803,7 +798,7 @@ b_epilogue:
 			off = offsetof(struct thread_info, cpu);
 			emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
 			break;
-		case BPF_S_ANC_IFINDEX:
+		case BPF_ANC | SKF_AD_IFINDEX:
 			/* A = skb->dev->ifindex */
 			ctx->seen |= SEEN_SKB;
 			off = offsetof(struct sk_buff, dev);
@@ -817,30 +812,30 @@ b_epilogue:
 			off = offsetof(struct net_device, ifindex);
 			emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
 			break;
-		case BPF_S_ANC_MARK:
+		case BPF_ANC | SKF_AD_MARK:
 			ctx->seen |= SEEN_SKB;
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
 			off = offsetof(struct sk_buff, mark);
 			emit(ARM_LDR_I(r_A, r_skb, off), ctx);
 			break;
-		case BPF_S_ANC_RXHASH:
+		case BPF_ANC | SKF_AD_RXHASH:
 			ctx->seen |= SEEN_SKB;
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
 			off = offsetof(struct sk_buff, hash);
 			emit(ARM_LDR_I(r_A, r_skb, off), ctx);
 			break;
-		case BPF_S_ANC_VLAN_TAG:
-		case BPF_S_ANC_VLAN_TAG_PRESENT:
+		case BPF_ANC | SKF_AD_VLAN_TAG:
+		case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
 			ctx->seen |= SEEN_SKB;
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
 			off = offsetof(struct sk_buff, vlan_tci);
 			emit(ARM_LDRH_I(r_A, r_skb, off), ctx);
-			if (inst->code == BPF_S_ANC_VLAN_TAG)
+			if (code == (BPF_ANC | SKF_AD_VLAN_TAG))
 				OP_IMM3(ARM_AND, r_A, r_A, VLAN_VID_MASK, ctx);
 			else
 				OP_IMM3(ARM_AND, r_A, r_A, VLAN_TAG_PRESENT, ctx);
 			break;
-		case BPF_S_ANC_QUEUE:
+		case BPF_ANC | SKF_AD_QUEUE:
 			ctx->seen |= SEEN_SKB;
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
 						  queue_mapping) != 2);
diff --git a/arch/mips/bcm47xx/sprom.c b/arch/mips/bcm47xx/sprom.c
index a8b5408..da4cdb1 100644
--- a/arch/mips/bcm47xx/sprom.c
+++ b/arch/mips/bcm47xx/sprom.c
@@ -168,6 +168,7 @@ static void nvram_read_alpha2(const char *prefix, const char *name,
 static void bcm47xx_fill_sprom_r1234589(struct ssb_sprom *sprom,
 					const char *prefix, bool fallback)
 {
+	nvram_read_u16(prefix, NULL, "devid", &sprom->dev_id, 0, fallback);
 	nvram_read_u8(prefix, NULL, "ledbh0", &sprom->gpio0, 0xff, fallback);
 	nvram_read_u8(prefix, NULL, "ledbh1", &sprom->gpio1, 0xff, fallback);
 	nvram_read_u8(prefix, NULL, "ledbh2", &sprom->gpio2, 0xff, fallback);
diff --git a/arch/powerpc/net/bpf_jit_64.S b/arch/powerpc/net/bpf_jit_64.S
index e76eba7..8f87d92 100644
--- a/arch/powerpc/net/bpf_jit_64.S
+++ b/arch/powerpc/net/bpf_jit_64.S
@@ -78,7 +78,7 @@ sk_load_byte_positive_offset:
 	blr
 
 /*
- * BPF_S_LDX_B_MSH: ldxb  4*([offset]&0xf)
+ * BPF_LDX | BPF_B | BPF_MSH: ldxb  4*([offset]&0xf)
  * r_addr is the offset value
  */
 	.globl sk_load_byte_msh
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 808ce1c..6dcdade 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -79,19 +79,11 @@ static void bpf_jit_build_prologue(struct sk_filter *fp, u32 *image,
 	}
 
 	switch (filter[0].code) {
-	case BPF_S_RET_K:
-	case BPF_S_LD_W_LEN:
-	case BPF_S_ANC_PROTOCOL:
-	case BPF_S_ANC_IFINDEX:
-	case BPF_S_ANC_MARK:
-	case BPF_S_ANC_RXHASH:
-	case BPF_S_ANC_VLAN_TAG:
-	case BPF_S_ANC_VLAN_TAG_PRESENT:
-	case BPF_S_ANC_CPU:
-	case BPF_S_ANC_QUEUE:
-	case BPF_S_LD_W_ABS:
-	case BPF_S_LD_H_ABS:
-	case BPF_S_LD_B_ABS:
+	case BPF_RET | BPF_K:
+	case BPF_LD | BPF_W | BPF_LEN:
+	case BPF_LD | BPF_W | BPF_ABS:
+	case BPF_LD | BPF_H | BPF_ABS:
+	case BPF_LD | BPF_B | BPF_ABS:
 		/* first instruction sets A register (or is RET 'constant') */
 		break;
 	default:
@@ -144,6 +136,7 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 
 	for (i = 0; i < flen; i++) {
 		unsigned int K = filter[i].k;
+		u16 code = bpf_anc_helper(&filter[i]);
 
 		/*
 		 * addrs[] maps a BPF bytecode address into a real offset from
@@ -151,35 +144,35 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 		 */
 		addrs[i] = ctx->idx * 4;
 
-		switch (filter[i].code) {
+		switch (code) {
 			/*** ALU ops ***/
-		case BPF_S_ALU_ADD_X: /* A += X; */
+		case BPF_ALU | BPF_ADD | BPF_X: /* A += X; */
 			ctx->seen |= SEEN_XREG;
 			PPC_ADD(r_A, r_A, r_X);
 			break;
-		case BPF_S_ALU_ADD_K: /* A += K; */
+		case BPF_ALU | BPF_ADD | BPF_K: /* A += K; */
 			if (!K)
 				break;
 			PPC_ADDI(r_A, r_A, IMM_L(K));
 			if (K >= 32768)
 				PPC_ADDIS(r_A, r_A, IMM_HA(K));
 			break;
-		case BPF_S_ALU_SUB_X: /* A -= X; */
+		case BPF_ALU | BPF_SUB | BPF_X: /* A -= X; */
 			ctx->seen |= SEEN_XREG;
 			PPC_SUB(r_A, r_A, r_X);
 			break;
-		case BPF_S_ALU_SUB_K: /* A -= K */
+		case BPF_ALU | BPF_SUB | BPF_K: /* A -= K */
 			if (!K)
 				break;
 			PPC_ADDI(r_A, r_A, IMM_L(-K));
 			if (K >= 32768)
 				PPC_ADDIS(r_A, r_A, IMM_HA(-K));
 			break;
-		case BPF_S_ALU_MUL_X: /* A *= X; */
+		case BPF_ALU | BPF_MUL | BPF_X: /* A *= X; */
 			ctx->seen |= SEEN_XREG;
 			PPC_MUL(r_A, r_A, r_X);
 			break;
-		case BPF_S_ALU_MUL_K: /* A *= K */
+		case BPF_ALU | BPF_MUL | BPF_K: /* A *= K */
 			if (K < 32768)
 				PPC_MULI(r_A, r_A, K);
 			else {
@@ -187,7 +180,7 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 				PPC_MUL(r_A, r_A, r_scratch1);
 			}
 			break;
-		case BPF_S_ALU_MOD_X: /* A %= X; */
+		case BPF_ALU | BPF_MOD | BPF_X: /* A %= X; */
 			ctx->seen |= SEEN_XREG;
 			PPC_CMPWI(r_X, 0);
 			if (ctx->pc_ret0 != -1) {
@@ -201,13 +194,13 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 			PPC_MUL(r_scratch1, r_X, r_scratch1);
 			PPC_SUB(r_A, r_A, r_scratch1);
 			break;
-		case BPF_S_ALU_MOD_K: /* A %= K; */
+		case BPF_ALU | BPF_MOD | BPF_K: /* A %= K; */
 			PPC_LI32(r_scratch2, K);
 			PPC_DIVWU(r_scratch1, r_A, r_scratch2);
 			PPC_MUL(r_scratch1, r_scratch2, r_scratch1);
 			PPC_SUB(r_A, r_A, r_scratch1);
 			break;
-		case BPF_S_ALU_DIV_X: /* A /= X; */
+		case BPF_ALU | BPF_DIV | BPF_X: /* A /= X; */
 			ctx->seen |= SEEN_XREG;
 			PPC_CMPWI(r_X, 0);
 			if (ctx->pc_ret0 != -1) {
@@ -223,17 +216,17 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 			}
 			PPC_DIVWU(r_A, r_A, r_X);
 			break;
-		case BPF_S_ALU_DIV_K: /* A /= K */
+		case BPF_ALU | BPF_DIV | BPF_K: /* A /= K */
 			if (K == 1)
 				break;
 			PPC_LI32(r_scratch1, K);
 			PPC_DIVWU(r_A, r_A, r_scratch1);
 			break;
-		case BPF_S_ALU_AND_X:
+		case BPF_ALU | BPF_AND | BPF_X:
 			ctx->seen |= SEEN_XREG;
 			PPC_AND(r_A, r_A, r_X);
 			break;
-		case BPF_S_ALU_AND_K:
+		case BPF_ALU | BPF_AND | BPF_K:
 			if (!IMM_H(K))
 				PPC_ANDI(r_A, r_A, K);
 			else {
@@ -241,51 +234,51 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 				PPC_AND(r_A, r_A, r_scratch1);
 			}
 			break;
-		case BPF_S_ALU_OR_X:
+		case BPF_ALU | BPF_OR | BPF_X:
 			ctx->seen |= SEEN_XREG;
 			PPC_OR(r_A, r_A, r_X);
 			break;
-		case BPF_S_ALU_OR_K:
+		case BPF_ALU | BPF_OR | BPF_K:
 			if (IMM_L(K))
 				PPC_ORI(r_A, r_A, IMM_L(K));
 			if (K >= 65536)
 				PPC_ORIS(r_A, r_A, IMM_H(K));
 			break;
-		case BPF_S_ANC_ALU_XOR_X:
-		case BPF_S_ALU_XOR_X: /* A ^= X */
+		case BPF_ANC | SKF_AD_ALU_XOR_X:
+		case BPF_ALU | BPF_XOR | BPF_X: /* A ^= X */
 			ctx->seen |= SEEN_XREG;
 			PPC_XOR(r_A, r_A, r_X);
 			break;
-		case BPF_S_ALU_XOR_K: /* A ^= K */
+		case BPF_ALU | BPF_XOR | BPF_K: /* A ^= K */
 			if (IMM_L(K))
 				PPC_XORI(r_A, r_A, IMM_L(K));
 			if (K >= 65536)
 				PPC_XORIS(r_A, r_A, IMM_H(K));
 			break;
-		case BPF_S_ALU_LSH_X: /* A <<= X; */
+		case BPF_ALU | BPF_LSH | BPF_X: /* A <<= X; */
 			ctx->seen |= SEEN_XREG;
 			PPC_SLW(r_A, r_A, r_X);
 			break;
-		case BPF_S_ALU_LSH_K:
+		case BPF_ALU | BPF_LSH | BPF_K:
 			if (K == 0)
 				break;
 			else
 				PPC_SLWI(r_A, r_A, K);
 			break;
-		case BPF_S_ALU_RSH_X: /* A >>= X; */
+		case BPF_ALU | BPF_RSH | BPF_X: /* A >>= X; */
 			ctx->seen |= SEEN_XREG;
 			PPC_SRW(r_A, r_A, r_X);
 			break;
-		case BPF_S_ALU_RSH_K: /* A >>= K; */
+		case BPF_ALU | BPF_RSH | BPF_K: /* A >>= K; */
 			if (K == 0)
 				break;
 			else
 				PPC_SRWI(r_A, r_A, K);
 			break;
-		case BPF_S_ALU_NEG:
+		case BPF_ALU | BPF_NEG:
 			PPC_NEG(r_A, r_A);
 			break;
-		case BPF_S_RET_K:
+		case BPF_RET | BPF_K:
 			PPC_LI32(r_ret, K);
 			if (!K) {
 				if (ctx->pc_ret0 == -1)
@@ -312,7 +305,7 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 					PPC_BLR();
 			}
 			break;
-		case BPF_S_RET_A:
+		case BPF_RET | BPF_A:
 			PPC_MR(r_ret, r_A);
 			if (i != flen - 1) {
 				if (ctx->seen)
@@ -321,53 +314,53 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 					PPC_BLR();
 			}
 			break;
-		case BPF_S_MISC_TAX: /* X = A */
+		case BPF_MISC | BPF_TAX: /* X = A */
 			PPC_MR(r_X, r_A);
 			break;
-		case BPF_S_MISC_TXA: /* A = X */
+		case BPF_MISC | BPF_TXA: /* A = X */
 			ctx->seen |= SEEN_XREG;
 			PPC_MR(r_A, r_X);
 			break;
 
 			/*** Constant loads/M[] access ***/
-		case BPF_S_LD_IMM: /* A = K */
+		case BPF_LD | BPF_IMM: /* A = K */
 			PPC_LI32(r_A, K);
 			break;
-		case BPF_S_LDX_IMM: /* X = K */
+		case BPF_LDX | BPF_IMM: /* X = K */
 			PPC_LI32(r_X, K);
 			break;
-		case BPF_S_LD_MEM: /* A = mem[K] */
+		case BPF_LD | BPF_MEM: /* A = mem[K] */
 			PPC_MR(r_A, r_M + (K & 0xf));
 			ctx->seen |= SEEN_MEM | (1<<(K & 0xf));
 			break;
-		case BPF_S_LDX_MEM: /* X = mem[K] */
+		case BPF_LDX | BPF_MEM: /* X = mem[K] */
 			PPC_MR(r_X, r_M + (K & 0xf));
 			ctx->seen |= SEEN_MEM | (1<<(K & 0xf));
 			break;
-		case BPF_S_ST: /* mem[K] = A */
+		case BPF_ST: /* mem[K] = A */
 			PPC_MR(r_M + (K & 0xf), r_A);
 			ctx->seen |= SEEN_MEM | (1<<(K & 0xf));
 			break;
-		case BPF_S_STX: /* mem[K] = X */
+		case BPF_STX: /* mem[K] = X */
 			PPC_MR(r_M + (K & 0xf), r_X);
 			ctx->seen |= SEEN_XREG | SEEN_MEM | (1<<(K & 0xf));
 			break;
-		case BPF_S_LD_W_LEN: /*	A = skb->len; */
+		case BPF_LD | BPF_W | BPF_LEN: /*	A = skb->len; */
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4);
 			PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, len));
 			break;
-		case BPF_S_LDX_W_LEN: /* X = skb->len; */
+		case BPF_LDX | BPF_W | BPF_LEN: /* X = skb->len; */
 			PPC_LWZ_OFFS(r_X, r_skb, offsetof(struct sk_buff, len));
 			break;
 
 			/*** Ancillary info loads ***/
-		case BPF_S_ANC_PROTOCOL: /* A = ntohs(skb->protocol); */
+		case BPF_ANC | SKF_AD_PROTOCOL: /* A = ntohs(skb->protocol); */
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
 						  protocol) != 2);
 			PPC_NTOHS_OFFS(r_A, r_skb, offsetof(struct sk_buff,
 							    protocol));
 			break;
-		case BPF_S_ANC_IFINDEX:
+		case BPF_ANC | SKF_AD_IFINDEX:
 			PPC_LD_OFFS(r_scratch1, r_skb, offsetof(struct sk_buff,
 								dev));
 			PPC_CMPDI(r_scratch1, 0);
@@ -384,33 +377,33 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 			PPC_LWZ_OFFS(r_A, r_scratch1,
 				     offsetof(struct net_device, ifindex));
 			break;
-		case BPF_S_ANC_MARK:
+		case BPF_ANC | SKF_AD_MARK:
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
 			PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
 							  mark));
 			break;
-		case BPF_S_ANC_RXHASH:
+		case BPF_ANC | SKF_AD_RXHASH:
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
 			PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
 							  hash));
 			break;
-		case BPF_S_ANC_VLAN_TAG:
-		case BPF_S_ANC_VLAN_TAG_PRESENT:
+		case BPF_ANC | SKF_AD_VLAN_TAG:
+		case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
 			PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
 							  vlan_tci));
-			if (filter[i].code == BPF_S_ANC_VLAN_TAG)
+			if (code == (BPF_ANC | SKF_AD_VLAN_TAG))
 				PPC_ANDI(r_A, r_A, VLAN_VID_MASK);
 			else
 				PPC_ANDI(r_A, r_A, VLAN_TAG_PRESENT);
 			break;
-		case BPF_S_ANC_QUEUE:
+		case BPF_ANC | SKF_AD_QUEUE:
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
 						  queue_mapping) != 2);
 			PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
 							  queue_mapping));
 			break;
-		case BPF_S_ANC_CPU:
+		case BPF_ANC | SKF_AD_CPU:
 #ifdef CONFIG_SMP
 			/*
 			 * PACA ptr is r13:
@@ -426,13 +419,13 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 			break;
 
 			/*** Absolute loads from packet header/data ***/
-		case BPF_S_LD_W_ABS:
+		case BPF_LD | BPF_W | BPF_ABS:
 			func = CHOOSE_LOAD_FUNC(K, sk_load_word);
 			goto common_load;
-		case BPF_S_LD_H_ABS:
+		case BPF_LD | BPF_H | BPF_ABS:
 			func = CHOOSE_LOAD_FUNC(K, sk_load_half);
 			goto common_load;
-		case BPF_S_LD_B_ABS:
+		case BPF_LD | BPF_B | BPF_ABS:
 			func = CHOOSE_LOAD_FUNC(K, sk_load_byte);
 		common_load:
 			/* Load from [K]. */
@@ -449,13 +442,13 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 			break;
 
 			/*** Indirect loads from packet header/data ***/
-		case BPF_S_LD_W_IND:
+		case BPF_LD | BPF_W | BPF_IND:
 			func = sk_load_word;
 			goto common_load_ind;
-		case BPF_S_LD_H_IND:
+		case BPF_LD | BPF_H | BPF_IND:
 			func = sk_load_half;
 			goto common_load_ind;
-		case BPF_S_LD_B_IND:
+		case BPF_LD | BPF_B | BPF_IND:
 			func = sk_load_byte;
 		common_load_ind:
 			/*
@@ -473,31 +466,31 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 			PPC_BCC(COND_LT, exit_addr);
 			break;
 
-		case BPF_S_LDX_B_MSH:
+		case BPF_LDX | BPF_B | BPF_MSH:
 			func = CHOOSE_LOAD_FUNC(K, sk_load_byte_msh);
 			goto common_load;
 			break;
 
 			/*** Jump and branches ***/
-		case BPF_S_JMP_JA:
+		case BPF_JMP | BPF_JA:
 			if (K != 0)
 				PPC_JMP(addrs[i + 1 + K]);
 			break;
 
-		case BPF_S_JMP_JGT_K:
-		case BPF_S_JMP_JGT_X:
+		case BPF_JMP | BPF_JGT | BPF_K:
+		case BPF_JMP | BPF_JGT | BPF_X:
 			true_cond = COND_GT;
 			goto cond_branch;
-		case BPF_S_JMP_JGE_K:
-		case BPF_S_JMP_JGE_X:
+		case BPF_JMP | BPF_JGE | BPF_K:
+		case BPF_JMP | BPF_JGE | BPF_X:
 			true_cond = COND_GE;
 			goto cond_branch;
-		case BPF_S_JMP_JEQ_K:
-		case BPF_S_JMP_JEQ_X:
+		case BPF_JMP | BPF_JEQ | BPF_K:
+		case BPF_JMP | BPF_JEQ | BPF_X:
 			true_cond = COND_EQ;
 			goto cond_branch;
-		case BPF_S_JMP_JSET_K:
-		case BPF_S_JMP_JSET_X:
+		case BPF_JMP | BPF_JSET | BPF_K:
+		case BPF_JMP | BPF_JSET | BPF_X:
 			true_cond = COND_NE;
 			/* Fall through */
 		cond_branch:
@@ -508,20 +501,20 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 				break;
 			}
 
-			switch (filter[i].code) {
-			case BPF_S_JMP_JGT_X:
-			case BPF_S_JMP_JGE_X:
-			case BPF_S_JMP_JEQ_X:
+			switch (code) {
+			case BPF_JMP | BPF_JGT | BPF_X:
+			case BPF_JMP | BPF_JGE | BPF_X:
+			case BPF_JMP | BPF_JEQ | BPF_X:
 				ctx->seen |= SEEN_XREG;
 				PPC_CMPLW(r_A, r_X);
 				break;
-			case BPF_S_JMP_JSET_X:
+			case BPF_JMP | BPF_JSET | BPF_X:
 				ctx->seen |= SEEN_XREG;
 				PPC_AND_DOT(r_scratch1, r_A, r_X);
 				break;
-			case BPF_S_JMP_JEQ_K:
-			case BPF_S_JMP_JGT_K:
-			case BPF_S_JMP_JGE_K:
+			case BPF_JMP | BPF_JEQ | BPF_K:
+			case BPF_JMP | BPF_JGT | BPF_K:
+			case BPF_JMP | BPF_JGE | BPF_K:
 				if (K < 32768)
 					PPC_CMPLWI(r_A, K);
 				else {
@@ -529,7 +522,7 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 					PPC_CMPLW(r_A, r_scratch1);
 				}
 				break;
-			case BPF_S_JMP_JSET_K:
+			case BPF_JMP | BPF_JSET | BPF_K:
 				if (K < 32768)
 					/* PPC_ANDI is /only/ dot-form */
 					PPC_ANDI(r_scratch1, r_A, K);
diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c
index 228cf91..ffd1169 100644
--- a/arch/powerpc/sysdev/fsl_soc.c
+++ b/arch/powerpc/sysdev/fsl_soc.c
@@ -25,7 +25,6 @@
 #include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/phy.h>
-#include <linux/phy_fixed.h>
 #include <linux/spi/spi.h>
 #include <linux/fsl_devices.h>
 #include <linux/fs_enet_pd.h>
@@ -178,37 +177,6 @@ u32 get_baudrate(void)
 EXPORT_SYMBOL(get_baudrate);
 #endif /* CONFIG_CPM2 */
 
-#ifdef CONFIG_FIXED_PHY
-static int __init of_add_fixed_phys(void)
-{
-	int ret;
-	struct device_node *np;
-	u32 *fixed_link;
-	struct fixed_phy_status status = {};
-
-	for_each_node_by_name(np, "ethernet") {
-		fixed_link  = (u32 *)of_get_property(np, "fixed-link", NULL);
-		if (!fixed_link)
-			continue;
-
-		status.link = 1;
-		status.duplex = fixed_link[1];
-		status.speed = fixed_link[2];
-		status.pause = fixed_link[3];
-		status.asym_pause = fixed_link[4];
-
-		ret = fixed_phy_add(PHY_POLL, fixed_link[0], &status);
-		if (ret) {
-			of_node_put(np);
-			return ret;
-		}
-	}
-
-	return 0;
-}
-arch_initcall(of_add_fixed_phys);
-#endif /* CONFIG_FIXED_PHY */
-
 #if defined(CONFIG_FSL_SOC_BOOKE) || defined(CONFIG_PPC_86xx)
 static __be32 __iomem *rstcr;
 
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index e9f8fa9..a2cbd87 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -269,27 +269,17 @@ static void bpf_jit_noleaks(struct bpf_jit *jit, struct sock_filter *filter)
 		EMIT4(0xa7c80000);
 	/* Clear A if the first register does not set it. */
 	switch (filter[0].code) {
-	case BPF_S_LD_W_ABS:
-	case BPF_S_LD_H_ABS:
-	case BPF_S_LD_B_ABS:
-	case BPF_S_LD_W_LEN:
-	case BPF_S_LD_W_IND:
-	case BPF_S_LD_H_IND:
-	case BPF_S_LD_B_IND:
-	case BPF_S_LD_IMM:
-	case BPF_S_LD_MEM:
-	case BPF_S_MISC_TXA:
-	case BPF_S_ANC_PROTOCOL:
-	case BPF_S_ANC_PKTTYPE:
-	case BPF_S_ANC_IFINDEX:
-	case BPF_S_ANC_MARK:
-	case BPF_S_ANC_QUEUE:
-	case BPF_S_ANC_HATYPE:
-	case BPF_S_ANC_RXHASH:
-	case BPF_S_ANC_CPU:
-	case BPF_S_ANC_VLAN_TAG:
-	case BPF_S_ANC_VLAN_TAG_PRESENT:
-	case BPF_S_RET_K:
+	case BPF_LD | BPF_W | BPF_ABS:
+	case BPF_LD | BPF_H | BPF_ABS:
+	case BPF_LD | BPF_B | BPF_ABS:
+	case BPF_LD | BPF_W | BPF_LEN:
+	case BPF_LD | BPF_W | BPF_IND:
+	case BPF_LD | BPF_H | BPF_IND:
+	case BPF_LD | BPF_B | BPF_IND:
+	case BPF_LD | BPF_IMM:
+	case BPF_LD | BPF_MEM:
+	case BPF_MISC | BPF_TXA:
+	case BPF_RET | BPF_K:
 		/* first instruction sets A register */
 		break;
 	default: /* A = 0 */
@@ -304,15 +294,18 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 	unsigned int K;
 	int offset;
 	unsigned int mask;
+	u16 code;
 
 	K = filter->k;
-	switch (filter->code) {
-	case BPF_S_ALU_ADD_X: /* A += X */
+	code = bpf_anc_helper(filter);
+
+	switch (code) {
+	case BPF_ALU | BPF_ADD | BPF_X: /* A += X */
 		jit->seen |= SEEN_XREG;
 		/* ar %r5,%r12 */
 		EMIT2(0x1a5c);
 		break;
-	case BPF_S_ALU_ADD_K: /* A += K */
+	case BPF_ALU | BPF_ADD | BPF_K: /* A += K */
 		if (!K)
 			break;
 		if (K <= 16383)
@@ -325,12 +318,12 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 			/* a %r5,<d(K)>(%r13) */
 			EMIT4_DISP(0x5a50d000, EMIT_CONST(K));
 		break;
-	case BPF_S_ALU_SUB_X: /* A -= X */
+	case BPF_ALU | BPF_SUB | BPF_X: /* A -= X */
 		jit->seen |= SEEN_XREG;
 		/* sr %r5,%r12 */
 		EMIT2(0x1b5c);
 		break;
-	case BPF_S_ALU_SUB_K: /* A -= K */
+	case BPF_ALU | BPF_SUB | BPF_K: /* A -= K */
 		if (!K)
 			break;
 		if (K <= 16384)
@@ -343,12 +336,12 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 			/* s %r5,<d(K)>(%r13) */
 			EMIT4_DISP(0x5b50d000, EMIT_CONST(K));
 		break;
-	case BPF_S_ALU_MUL_X: /* A *= X */
+	case BPF_ALU | BPF_MUL | BPF_X: /* A *= X */
 		jit->seen |= SEEN_XREG;
 		/* msr %r5,%r12 */
 		EMIT4(0xb252005c);
 		break;
-	case BPF_S_ALU_MUL_K: /* A *= K */
+	case BPF_ALU | BPF_MUL | BPF_K: /* A *= K */
 		if (K <= 16383)
 			/* mhi %r5,K */
 			EMIT4_IMM(0xa75c0000, K);
@@ -359,7 +352,7 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 			/* ms %r5,<d(K)>(%r13) */
 			EMIT4_DISP(0x7150d000, EMIT_CONST(K));
 		break;
-	case BPF_S_ALU_DIV_X: /* A /= X */
+	case BPF_ALU | BPF_DIV | BPF_X: /* A /= X */
 		jit->seen |= SEEN_XREG | SEEN_RET0;
 		/* ltr %r12,%r12 */
 		EMIT2(0x12cc);
@@ -370,7 +363,7 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		/* dlr %r4,%r12 */
 		EMIT4(0xb997004c);
 		break;
-	case BPF_S_ALU_DIV_K: /* A /= K */
+	case BPF_ALU | BPF_DIV | BPF_K: /* A /= K */
 		if (K == 1)
 			break;
 		/* lhi %r4,0 */
@@ -378,7 +371,7 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		/* dl %r4,<d(K)>(%r13) */
 		EMIT6_DISP(0xe340d000, 0x0097, EMIT_CONST(K));
 		break;
-	case BPF_S_ALU_MOD_X: /* A %= X */
+	case BPF_ALU | BPF_MOD | BPF_X: /* A %= X */
 		jit->seen |= SEEN_XREG | SEEN_RET0;
 		/* ltr %r12,%r12 */
 		EMIT2(0x12cc);
@@ -391,7 +384,7 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		/* lr %r5,%r4 */
 		EMIT2(0x1854);
 		break;
-	case BPF_S_ALU_MOD_K: /* A %= K */
+	case BPF_ALU | BPF_MOD | BPF_K: /* A %= K */
 		if (K == 1) {
 			/* lhi %r5,0 */
 			EMIT4(0xa7580000);
@@ -404,12 +397,12 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		/* lr %r5,%r4 */
 		EMIT2(0x1854);
 		break;
-	case BPF_S_ALU_AND_X: /* A &= X */
+	case BPF_ALU | BPF_AND | BPF_X: /* A &= X */
 		jit->seen |= SEEN_XREG;
 		/* nr %r5,%r12 */
 		EMIT2(0x145c);
 		break;
-	case BPF_S_ALU_AND_K: /* A &= K */
+	case BPF_ALU | BPF_AND | BPF_K: /* A &= K */
 		if (test_facility(21))
 			/* nilf %r5,<K> */
 			EMIT6_IMM(0xc05b0000, K);
@@ -417,12 +410,12 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 			/* n %r5,<d(K)>(%r13) */
 			EMIT4_DISP(0x5450d000, EMIT_CONST(K));
 		break;
-	case BPF_S_ALU_OR_X: /* A |= X */
+	case BPF_ALU | BPF_OR | BPF_X: /* A |= X */
 		jit->seen |= SEEN_XREG;
 		/* or %r5,%r12 */
 		EMIT2(0x165c);
 		break;
-	case BPF_S_ALU_OR_K: /* A |= K */
+	case BPF_ALU | BPF_OR | BPF_K: /* A |= K */
 		if (test_facility(21))
 			/* oilf %r5,<K> */
 			EMIT6_IMM(0xc05d0000, K);
@@ -430,55 +423,55 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 			/* o %r5,<d(K)>(%r13) */
 			EMIT4_DISP(0x5650d000, EMIT_CONST(K));
 		break;
-	case BPF_S_ANC_ALU_XOR_X: /* A ^= X; */
-	case BPF_S_ALU_XOR_X:
+	case BPF_ANC | SKF_AD_ALU_XOR_X: /* A ^= X; */
+	case BPF_ALU | BPF_XOR | BPF_X:
 		jit->seen |= SEEN_XREG;
 		/* xr %r5,%r12 */
 		EMIT2(0x175c);
 		break;
-	case BPF_S_ALU_XOR_K: /* A ^= K */
+	case BPF_ALU | BPF_XOR | BPF_K: /* A ^= K */
 		if (!K)
 			break;
 		/* x %r5,<d(K)>(%r13) */
 		EMIT4_DISP(0x5750d000, EMIT_CONST(K));
 		break;
-	case BPF_S_ALU_LSH_X: /* A <<= X; */
+	case BPF_ALU | BPF_LSH | BPF_X: /* A <<= X; */
 		jit->seen |= SEEN_XREG;
 		/* sll %r5,0(%r12) */
 		EMIT4(0x8950c000);
 		break;
-	case BPF_S_ALU_LSH_K: /* A <<= K */
+	case BPF_ALU | BPF_LSH | BPF_K: /* A <<= K */
 		if (K == 0)
 			break;
 		/* sll %r5,K */
 		EMIT4_DISP(0x89500000, K);
 		break;
-	case BPF_S_ALU_RSH_X: /* A >>= X; */
+	case BPF_ALU | BPF_RSH | BPF_X: /* A >>= X; */
 		jit->seen |= SEEN_XREG;
 		/* srl %r5,0(%r12) */
 		EMIT4(0x8850c000);
 		break;
-	case BPF_S_ALU_RSH_K: /* A >>= K; */
+	case BPF_ALU | BPF_RSH | BPF_K: /* A >>= K; */
 		if (K == 0)
 			break;
 		/* srl %r5,K */
 		EMIT4_DISP(0x88500000, K);
 		break;
-	case BPF_S_ALU_NEG: /* A = -A */
+	case BPF_ALU | BPF_NEG: /* A = -A */
 		/* lnr %r5,%r5 */
 		EMIT2(0x1155);
 		break;
-	case BPF_S_JMP_JA: /* ip += K */
+	case BPF_JMP | BPF_JA: /* ip += K */
 		offset = addrs[i + K] + jit->start - jit->prg;
 		EMIT4_PCREL(0xa7f40000, offset);
 		break;
-	case BPF_S_JMP_JGT_K: /* ip += (A > K) ? jt : jf */
+	case BPF_JMP | BPF_JGT | BPF_K: /* ip += (A > K) ? jt : jf */
 		mask = 0x200000; /* jh */
 		goto kbranch;
-	case BPF_S_JMP_JGE_K: /* ip += (A >= K) ? jt : jf */
+	case BPF_JMP | BPF_JGE | BPF_K: /* ip += (A >= K) ? jt : jf */
 		mask = 0xa00000; /* jhe */
 		goto kbranch;
-	case BPF_S_JMP_JEQ_K: /* ip += (A == K) ? jt : jf */
+	case BPF_JMP | BPF_JEQ | BPF_K: /* ip += (A == K) ? jt : jf */
 		mask = 0x800000; /* je */
 kbranch:	/* Emit compare if the branch targets are different */
 		if (filter->jt != filter->jf) {
@@ -511,7 +504,7 @@ branch:		if (filter->jt == filter->jf) {
 			EMIT4_PCREL(0xa7040000 | (mask ^ 0xf00000), offset);
 		}
 		break;
-	case BPF_S_JMP_JSET_K: /* ip += (A & K) ? jt : jf */
+	case BPF_JMP | BPF_JSET | BPF_K: /* ip += (A & K) ? jt : jf */
 		mask = 0x700000; /* jnz */
 		/* Emit test if the branch targets are different */
 		if (filter->jt != filter->jf) {
@@ -525,13 +518,13 @@ branch:		if (filter->jt == filter->jf) {
 				EMIT4_IMM(0xa7510000, K);
 		}
 		goto branch;
-	case BPF_S_JMP_JGT_X: /* ip += (A > X) ? jt : jf */
+	case BPF_JMP | BPF_JGT | BPF_X: /* ip += (A > X) ? jt : jf */
 		mask = 0x200000; /* jh */
 		goto xbranch;
-	case BPF_S_JMP_JGE_X: /* ip += (A >= X) ? jt : jf */
+	case BPF_JMP | BPF_JGE | BPF_X: /* ip += (A >= X) ? jt : jf */
 		mask = 0xa00000; /* jhe */
 		goto xbranch;
-	case BPF_S_JMP_JEQ_X: /* ip += (A == X) ? jt : jf */
+	case BPF_JMP | BPF_JEQ | BPF_X: /* ip += (A == X) ? jt : jf */
 		mask = 0x800000; /* je */
 xbranch:	/* Emit compare if the branch targets are different */
 		if (filter->jt != filter->jf) {
@@ -540,7 +533,7 @@ xbranch:	/* Emit compare if the branch targets are different */
 			EMIT2(0x195c);
 		}
 		goto branch;
-	case BPF_S_JMP_JSET_X: /* ip += (A & X) ? jt : jf */
+	case BPF_JMP | BPF_JSET | BPF_X: /* ip += (A & X) ? jt : jf */
 		mask = 0x700000; /* jnz */
 		/* Emit test if the branch targets are different */
 		if (filter->jt != filter->jf) {
@@ -551,15 +544,15 @@ xbranch:	/* Emit compare if the branch targets are different */
 			EMIT2(0x144c);
 		}
 		goto branch;
-	case BPF_S_LD_W_ABS: /* A = *(u32 *) (skb->data+K) */
+	case BPF_LD | BPF_W | BPF_ABS: /* A = *(u32 *) (skb->data+K) */
 		jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_WORD;
 		offset = jit->off_load_word;
 		goto load_abs;
-	case BPF_S_LD_H_ABS: /* A = *(u16 *) (skb->data+K) */
+	case BPF_LD | BPF_H | BPF_ABS: /* A = *(u16 *) (skb->data+K) */
 		jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_HALF;
 		offset = jit->off_load_half;
 		goto load_abs;
-	case BPF_S_LD_B_ABS: /* A = *(u8 *) (skb->data+K) */
+	case BPF_LD | BPF_B | BPF_ABS: /* A = *(u8 *) (skb->data+K) */
 		jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_BYTE;
 		offset = jit->off_load_byte;
 load_abs:	if ((int) K < 0)
@@ -573,19 +566,19 @@ call_fn:	/* lg %r1,<d(function)>(%r13) */
 		/* jnz <ret0> */
 		EMIT4_PCREL(0xa7740000, (jit->ret0_ip - jit->prg));
 		break;
-	case BPF_S_LD_W_IND: /* A = *(u32 *) (skb->data+K+X) */
+	case BPF_LD | BPF_W | BPF_IND: /* A = *(u32 *) (skb->data+K+X) */
 		jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_IWORD;
 		offset = jit->off_load_iword;
 		goto call_fn;
-	case BPF_S_LD_H_IND: /* A = *(u16 *) (skb->data+K+X) */
+	case BPF_LD | BPF_H | BPF_IND: /* A = *(u16 *) (skb->data+K+X) */
 		jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_IHALF;
 		offset = jit->off_load_ihalf;
 		goto call_fn;
-	case BPF_S_LD_B_IND: /* A = *(u8 *) (skb->data+K+X) */
+	case BPF_LD | BPF_B | BPF_IND: /* A = *(u8 *) (skb->data+K+X) */
 		jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_IBYTE;
 		offset = jit->off_load_ibyte;
 		goto call_fn;
-	case BPF_S_LDX_B_MSH:
+	case BPF_LDX | BPF_B | BPF_MSH:
 		/* X = (*(u8 *)(skb->data+K) & 0xf) << 2 */
 		jit->seen |= SEEN_RET0;
 		if ((int) K < 0) {
@@ -596,17 +589,17 @@ call_fn:	/* lg %r1,<d(function)>(%r13) */
 		jit->seen |= SEEN_DATAREF | SEEN_LOAD_BMSH;
 		offset = jit->off_load_bmsh;
 		goto call_fn;
-	case BPF_S_LD_W_LEN: /*	A = skb->len; */
+	case BPF_LD | BPF_W | BPF_LEN: /*	A = skb->len; */
 		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4);
 		/* l %r5,<d(len)>(%r2) */
 		EMIT4_DISP(0x58502000, offsetof(struct sk_buff, len));
 		break;
-	case BPF_S_LDX_W_LEN: /* X = skb->len; */
+	case BPF_LDX | BPF_W | BPF_LEN: /* X = skb->len; */
 		jit->seen |= SEEN_XREG;
 		/* l %r12,<d(len)>(%r2) */
 		EMIT4_DISP(0x58c02000, offsetof(struct sk_buff, len));
 		break;
-	case BPF_S_LD_IMM: /* A = K */
+	case BPF_LD | BPF_IMM: /* A = K */
 		if (K <= 16383)
 			/* lhi %r5,K */
 			EMIT4_IMM(0xa7580000, K);
@@ -617,7 +610,7 @@ call_fn:	/* lg %r1,<d(function)>(%r13) */
 			/* l %r5,<d(K)>(%r13) */
 			EMIT4_DISP(0x5850d000, EMIT_CONST(K));
 		break;
-	case BPF_S_LDX_IMM: /* X = K */
+	case BPF_LDX | BPF_IMM: /* X = K */
 		jit->seen |= SEEN_XREG;
 		if (K <= 16383)
 			/* lhi %r12,<K> */
@@ -629,29 +622,29 @@ call_fn:	/* lg %r1,<d(function)>(%r13) */
 			/* l %r12,<d(K)>(%r13) */
 			EMIT4_DISP(0x58c0d000, EMIT_CONST(K));
 		break;
-	case BPF_S_LD_MEM: /* A = mem[K] */
+	case BPF_LD | BPF_MEM: /* A = mem[K] */
 		jit->seen |= SEEN_MEM;
 		/* l %r5,<K>(%r15) */
 		EMIT4_DISP(0x5850f000,
 			   (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4);
 		break;
-	case BPF_S_LDX_MEM: /* X = mem[K] */
+	case BPF_LDX | BPF_MEM: /* X = mem[K] */
 		jit->seen |= SEEN_XREG | SEEN_MEM;
 		/* l %r12,<K>(%r15) */
 		EMIT4_DISP(0x58c0f000,
 			   (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4);
 		break;
-	case BPF_S_MISC_TAX: /* X = A */
+	case BPF_MISC | BPF_TAX: /* X = A */
 		jit->seen |= SEEN_XREG;
 		/* lr %r12,%r5 */
 		EMIT2(0x18c5);
 		break;
-	case BPF_S_MISC_TXA: /* A = X */
+	case BPF_MISC | BPF_TXA: /* A = X */
 		jit->seen |= SEEN_XREG;
 		/* lr %r5,%r12 */
 		EMIT2(0x185c);
 		break;
-	case BPF_S_RET_K:
+	case BPF_RET | BPF_K:
 		if (K == 0) {
 			jit->seen |= SEEN_RET0;
 			if (last)
@@ -671,33 +664,33 @@ call_fn:	/* lg %r1,<d(function)>(%r13) */
 			EMIT4_PCREL(0xa7f40000, jit->exit_ip - jit->prg);
 		}
 		break;
-	case BPF_S_RET_A:
+	case BPF_RET | BPF_A:
 		/* llgfr %r2,%r5 */
 		EMIT4(0xb9160025);
 		/* j <exit> */
 		EMIT4_PCREL(0xa7f40000, jit->exit_ip - jit->prg);
 		break;
-	case BPF_S_ST: /* mem[K] = A */
+	case BPF_ST: /* mem[K] = A */
 		jit->seen |= SEEN_MEM;
 		/* st %r5,<K>(%r15) */
 		EMIT4_DISP(0x5050f000,
 			   (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4);
 		break;
-	case BPF_S_STX: /* mem[K] = X : mov %ebx,off8(%rbp) */
+	case BPF_STX: /* mem[K] = X : mov %ebx,off8(%rbp) */
 		jit->seen |= SEEN_XREG | SEEN_MEM;
 		/* st %r12,<K>(%r15) */
 		EMIT4_DISP(0x50c0f000,
 			   (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4);
 		break;
-	case BPF_S_ANC_PROTOCOL: /* A = ntohs(skb->protocol); */
+	case BPF_ANC | SKF_AD_PROTOCOL: /* A = ntohs(skb->protocol); */
 		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2);
 		/* lhi %r5,0 */
 		EMIT4(0xa7580000);
 		/* icm	%r5,3,<d(protocol)>(%r2) */
 		EMIT4_DISP(0xbf532000, offsetof(struct sk_buff, protocol));
 		break;
-	case BPF_S_ANC_IFINDEX:	/* if (!skb->dev) return 0;
-				 * A = skb->dev->ifindex */
+	case BPF_ANC | SKF_AD_IFINDEX:	/* if (!skb->dev) return 0;
+					 * A = skb->dev->ifindex */
 		BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4);
 		jit->seen |= SEEN_RET0;
 		/* lg %r1,<d(dev)>(%r2) */
@@ -709,20 +702,20 @@ call_fn:	/* lg %r1,<d(function)>(%r13) */
 		/* l %r5,<d(ifindex)>(%r1) */
 		EMIT4_DISP(0x58501000, offsetof(struct net_device, ifindex));
 		break;
-	case BPF_S_ANC_MARK: /* A = skb->mark */
+	case BPF_ANC | SKF_AD_MARK: /* A = skb->mark */
 		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
 		/* l %r5,<d(mark)>(%r2) */
 		EMIT4_DISP(0x58502000, offsetof(struct sk_buff, mark));
 		break;
-	case BPF_S_ANC_QUEUE: /* A = skb->queue_mapping */
+	case BPF_ANC | SKF_AD_QUEUE: /* A = skb->queue_mapping */
 		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2);
 		/* lhi %r5,0 */
 		EMIT4(0xa7580000);
 		/* icm	%r5,3,<d(queue_mapping)>(%r2) */
 		EMIT4_DISP(0xbf532000, offsetof(struct sk_buff, queue_mapping));
 		break;
-	case BPF_S_ANC_HATYPE:	/* if (!skb->dev) return 0;
-				 * A = skb->dev->type */
+	case BPF_ANC | SKF_AD_HATYPE:	/* if (!skb->dev) return 0;
+					 * A = skb->dev->type */
 		BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2);
 		jit->seen |= SEEN_RET0;
 		/* lg %r1,<d(dev)>(%r2) */
@@ -736,20 +729,20 @@ call_fn:	/* lg %r1,<d(function)>(%r13) */
 		/* icm	%r5,3,<d(type)>(%r1) */
 		EMIT4_DISP(0xbf531000, offsetof(struct net_device, type));
 		break;
-	case BPF_S_ANC_RXHASH: /* A = skb->hash */
+	case BPF_ANC | SKF_AD_RXHASH: /* A = skb->hash */
 		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
 		/* l %r5,<d(hash)>(%r2) */
 		EMIT4_DISP(0x58502000, offsetof(struct sk_buff, hash));
 		break;
-	case BPF_S_ANC_VLAN_TAG:
-	case BPF_S_ANC_VLAN_TAG_PRESENT:
+	case BPF_ANC | SKF_AD_VLAN_TAG:
+	case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
 		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
 		BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
 		/* lhi %r5,0 */
 		EMIT4(0xa7580000);
 		/* icm	%r5,3,<d(vlan_tci)>(%r2) */
 		EMIT4_DISP(0xbf532000, offsetof(struct sk_buff, vlan_tci));
-		if (filter->code == BPF_S_ANC_VLAN_TAG) {
+		if (code == (BPF_ANC | SKF_AD_VLAN_TAG)) {
 			/* nill %r5,0xefff */
 			EMIT4_IMM(0xa5570000, ~VLAN_TAG_PRESENT);
 		} else {
@@ -759,7 +752,7 @@ call_fn:	/* lg %r1,<d(function)>(%r13) */
 			EMIT4_DISP(0x88500000, 12);
 		}
 		break;
-	case BPF_S_ANC_PKTTYPE:
+	case BPF_ANC | SKF_AD_PKTTYPE:
 		if (pkt_type_offset < 0)
 			goto out;
 		/* lhi %r5,0 */
@@ -769,7 +762,7 @@ call_fn:	/* lg %r1,<d(function)>(%r13) */
 		/* srl %r5,5 */
 		EMIT4_DISP(0x88500000, 5);
 		break;
-	case BPF_S_ANC_CPU: /* A = smp_processor_id() */
+	case BPF_ANC | SKF_AD_CPU: /* A = smp_processor_id() */
 #ifdef CONFIG_SMP
 		/* l %r5,<d(cpu_nr)> */
 		EMIT4_DISP(0x58500000, offsetof(struct _lowcore, cpu_nr));
diff --git a/arch/sparc/include/asm/checksum_32.h b/arch/sparc/include/asm/checksum_32.h
index bdbda14..04471dc 100644
--- a/arch/sparc/include/asm/checksum_32.h
+++ b/arch/sparc/include/asm/checksum_32.h
@@ -238,4 +238,16 @@ static inline __sum16 ip_compute_csum(const void *buff, int len)
 	return csum_fold(csum_partial(buff, len, 0));
 }
 
+#define HAVE_ARCH_CSUM_ADD
+static inline __wsum csum_add(__wsum csum, __wsum addend)
+{
+	__asm__ __volatile__(
+		"addcc   %0, %1, %0\n"
+		"addx    %0, %%g0, %0"
+		: "=r" (csum)
+		: "r" (addend), "0" (csum));
+
+	return csum;
+}
+
 #endif /* !(__SPARC_CHECKSUM_H) */
diff --git a/arch/sparc/include/asm/checksum_64.h b/arch/sparc/include/asm/checksum_64.h
index 019b961..2ff81ae 100644
--- a/arch/sparc/include/asm/checksum_64.h
+++ b/arch/sparc/include/asm/checksum_64.h
@@ -164,4 +164,16 @@ static inline __sum16 ip_compute_csum(const void *buff, int len)
 	return csum_fold(csum_partial(buff, len, 0));
 }
 
+#define HAVE_ARCH_CSUM_ADD
+static inline __wsum csum_add(__wsum csum, __wsum addend)
+{
+	__asm__ __volatile__(
+		"addcc   %0, %1, %0\n"
+		"addx    %0, %%g0, %0"
+		: "=r" (csum)
+		: "r" (addend), "0" (csum));
+
+	return csum;
+}
+
 #endif /* !(__SPARC64_CHECKSUM_H) */
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c
index a82c6b2..892a102 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp.c
@@ -83,9 +83,9 @@ static void bpf_flush_icache(void *start_, void *end_)
 #define BNE		(F2(0, 2) | CONDNE)
 
 #ifdef CONFIG_SPARC64
-#define BNE_PTR		(F2(0, 1) | CONDNE | (2 << 20))
+#define BE_PTR		(F2(0, 1) | CONDE | (2 << 20))
 #else
-#define BNE_PTR		BNE
+#define BE_PTR		BE
 #endif
 
 #define SETHI(K, REG)	\
@@ -415,20 +415,11 @@ void bpf_jit_compile(struct sk_filter *fp)
 		emit_reg_move(O7, r_saved_O7);
 
 		switch (filter[0].code) {
-		case BPF_S_RET_K:
-		case BPF_S_LD_W_LEN:
-		case BPF_S_ANC_PROTOCOL:
-		case BPF_S_ANC_PKTTYPE:
-		case BPF_S_ANC_IFINDEX:
-		case BPF_S_ANC_MARK:
-		case BPF_S_ANC_RXHASH:
-		case BPF_S_ANC_VLAN_TAG:
-		case BPF_S_ANC_VLAN_TAG_PRESENT:
-		case BPF_S_ANC_CPU:
-		case BPF_S_ANC_QUEUE:
-		case BPF_S_LD_W_ABS:
-		case BPF_S_LD_H_ABS:
-		case BPF_S_LD_B_ABS:
+		case BPF_RET | BPF_K:
+		case BPF_LD | BPF_W | BPF_LEN:
+		case BPF_LD | BPF_W | BPF_ABS:
+		case BPF_LD | BPF_H | BPF_ABS:
+		case BPF_LD | BPF_B | BPF_ABS:
 			/* The first instruction sets the A register (or is
 			 * a "RET 'constant'")
 			 */
@@ -445,59 +436,60 @@ void bpf_jit_compile(struct sk_filter *fp)
 			unsigned int t_offset;
 			unsigned int f_offset;
 			u32 t_op, f_op;
+			u16 code = bpf_anc_helper(&filter[i]);
 			int ilen;
 
-			switch (filter[i].code) {
-			case BPF_S_ALU_ADD_X:	/* A += X; */
+			switch (code) {
+			case BPF_ALU | BPF_ADD | BPF_X:	/* A += X; */
 				emit_alu_X(ADD);
 				break;
-			case BPF_S_ALU_ADD_K:	/* A += K; */
+			case BPF_ALU | BPF_ADD | BPF_K:	/* A += K; */
 				emit_alu_K(ADD, K);
 				break;
-			case BPF_S_ALU_SUB_X:	/* A -= X; */
+			case BPF_ALU | BPF_SUB | BPF_X:	/* A -= X; */
 				emit_alu_X(SUB);
 				break;
-			case BPF_S_ALU_SUB_K:	/* A -= K */
+			case BPF_ALU | BPF_SUB | BPF_K:	/* A -= K */
 				emit_alu_K(SUB, K);
 				break;
-			case BPF_S_ALU_AND_X:	/* A &= X */
+			case BPF_ALU | BPF_AND | BPF_X:	/* A &= X */
 				emit_alu_X(AND);
 				break;
-			case BPF_S_ALU_AND_K:	/* A &= K */
+			case BPF_ALU | BPF_AND | BPF_K:	/* A &= K */
 				emit_alu_K(AND, K);
 				break;
-			case BPF_S_ALU_OR_X:	/* A |= X */
+			case BPF_ALU | BPF_OR | BPF_X:	/* A |= X */
 				emit_alu_X(OR);
 				break;
-			case BPF_S_ALU_OR_K:	/* A |= K */
+			case BPF_ALU | BPF_OR | BPF_K:	/* A |= K */
 				emit_alu_K(OR, K);
 				break;
-			case BPF_S_ANC_ALU_XOR_X: /* A ^= X; */
-			case BPF_S_ALU_XOR_X:
+			case BPF_ANC | SKF_AD_ALU_XOR_X: /* A ^= X; */
+			case BPF_ALU | BPF_XOR | BPF_X:
 				emit_alu_X(XOR);
 				break;
-			case BPF_S_ALU_XOR_K:	/* A ^= K */
+			case BPF_ALU | BPF_XOR | BPF_K:	/* A ^= K */
 				emit_alu_K(XOR, K);
 				break;
-			case BPF_S_ALU_LSH_X:	/* A <<= X */
+			case BPF_ALU | BPF_LSH | BPF_X:	/* A <<= X */
 				emit_alu_X(SLL);
 				break;
-			case BPF_S_ALU_LSH_K:	/* A <<= K */
+			case BPF_ALU | BPF_LSH | BPF_K:	/* A <<= K */
 				emit_alu_K(SLL, K);
 				break;
-			case BPF_S_ALU_RSH_X:	/* A >>= X */
+			case BPF_ALU | BPF_RSH | BPF_X:	/* A >>= X */
 				emit_alu_X(SRL);
 				break;
-			case BPF_S_ALU_RSH_K:	/* A >>= K */
+			case BPF_ALU | BPF_RSH | BPF_K:	/* A >>= K */
 				emit_alu_K(SRL, K);
 				break;
-			case BPF_S_ALU_MUL_X:	/* A *= X; */
+			case BPF_ALU | BPF_MUL | BPF_X:	/* A *= X; */
 				emit_alu_X(MUL);
 				break;
-			case BPF_S_ALU_MUL_K:	/* A *= K */
+			case BPF_ALU | BPF_MUL | BPF_K:	/* A *= K */
 				emit_alu_K(MUL, K);
 				break;
-			case BPF_S_ALU_DIV_K:	/* A /= K with K != 0*/
+			case BPF_ALU | BPF_DIV | BPF_K:	/* A /= K with K != 0*/
 				if (K == 1)
 					break;
 				emit_write_y(G0);
@@ -512,7 +504,7 @@ void bpf_jit_compile(struct sk_filter *fp)
 #endif
 				emit_alu_K(DIV, K);
 				break;
-			case BPF_S_ALU_DIV_X:	/* A /= X; */
+			case BPF_ALU | BPF_DIV | BPF_X:	/* A /= X; */
 				emit_cmpi(r_X, 0);
 				if (pc_ret0 > 0) {
 					t_offset = addrs[pc_ret0 - 1];
@@ -544,10 +536,10 @@ void bpf_jit_compile(struct sk_filter *fp)
 #endif
 				emit_alu_X(DIV);
 				break;
-			case BPF_S_ALU_NEG:
+			case BPF_ALU | BPF_NEG:
 				emit_neg();
 				break;
-			case BPF_S_RET_K:
+			case BPF_RET | BPF_K:
 				if (!K) {
 					if (pc_ret0 == -1)
 						pc_ret0 = i;
@@ -556,7 +548,7 @@ void bpf_jit_compile(struct sk_filter *fp)
 					emit_loadimm(K, r_A);
 				}
 				/* Fallthrough */
-			case BPF_S_RET_A:
+			case BPF_RET | BPF_A:
 				if (seen_or_pass0) {
 					if (i != flen - 1) {
 						emit_jump(cleanup_addr);
@@ -573,18 +565,18 @@ void bpf_jit_compile(struct sk_filter *fp)
 				emit_jmpl(r_saved_O7, 8, G0);
 				emit_reg_move(r_A, O0); /* delay slot */
 				break;
-			case BPF_S_MISC_TAX:
+			case BPF_MISC | BPF_TAX:
 				seen |= SEEN_XREG;
 				emit_reg_move(r_A, r_X);
 				break;
-			case BPF_S_MISC_TXA:
+			case BPF_MISC | BPF_TXA:
 				seen |= SEEN_XREG;
 				emit_reg_move(r_X, r_A);
 				break;
-			case BPF_S_ANC_CPU:
+			case BPF_ANC | SKF_AD_CPU:
 				emit_load_cpu(r_A);
 				break;
-			case BPF_S_ANC_PROTOCOL:
+			case BPF_ANC | SKF_AD_PROTOCOL:
 				emit_skb_load16(protocol, r_A);
 				break;
 #if 0
@@ -592,38 +584,38 @@ void bpf_jit_compile(struct sk_filter *fp)
 				 * a bit field even though we very much
 				 * know what we are doing here.
 				 */
-			case BPF_S_ANC_PKTTYPE:
+			case BPF_ANC | SKF_AD_PKTTYPE:
 				__emit_skb_load8(pkt_type, r_A);
 				emit_alu_K(SRL, 5);
 				break;
 #endif
-			case BPF_S_ANC_IFINDEX:
+			case BPF_ANC | SKF_AD_IFINDEX:
 				emit_skb_loadptr(dev, r_A);
 				emit_cmpi(r_A, 0);
-				emit_branch(BNE_PTR, cleanup_addr + 4);
+				emit_branch(BE_PTR, cleanup_addr + 4);
 				emit_nop();
 				emit_load32(r_A, struct net_device, ifindex, r_A);
 				break;
-			case BPF_S_ANC_MARK:
+			case BPF_ANC | SKF_AD_MARK:
 				emit_skb_load32(mark, r_A);
 				break;
-			case BPF_S_ANC_QUEUE:
+			case BPF_ANC | SKF_AD_QUEUE:
 				emit_skb_load16(queue_mapping, r_A);
 				break;
-			case BPF_S_ANC_HATYPE:
+			case BPF_ANC | SKF_AD_HATYPE:
 				emit_skb_loadptr(dev, r_A);
 				emit_cmpi(r_A, 0);
-				emit_branch(BNE_PTR, cleanup_addr + 4);
+				emit_branch(BE_PTR, cleanup_addr + 4);
 				emit_nop();
 				emit_load16(r_A, struct net_device, type, r_A);
 				break;
-			case BPF_S_ANC_RXHASH:
+			case BPF_ANC | SKF_AD_RXHASH:
 				emit_skb_load32(hash, r_A);
 				break;
-			case BPF_S_ANC_VLAN_TAG:
-			case BPF_S_ANC_VLAN_TAG_PRESENT:
+			case BPF_ANC | SKF_AD_VLAN_TAG:
+			case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
 				emit_skb_load16(vlan_tci, r_A);
-				if (filter[i].code == BPF_S_ANC_VLAN_TAG) {
+				if (code == (BPF_ANC | SKF_AD_VLAN_TAG)) {
 					emit_andi(r_A, VLAN_VID_MASK, r_A);
 				} else {
 					emit_loadimm(VLAN_TAG_PRESENT, r_TMP);
@@ -631,44 +623,44 @@ void bpf_jit_compile(struct sk_filter *fp)
 				}
 				break;
 
-			case BPF_S_LD_IMM:
+			case BPF_LD | BPF_IMM:
 				emit_loadimm(K, r_A);
 				break;
-			case BPF_S_LDX_IMM:
+			case BPF_LDX | BPF_IMM:
 				emit_loadimm(K, r_X);
 				break;
-			case BPF_S_LD_MEM:
+			case BPF_LD | BPF_MEM:
 				emit_ldmem(K * 4, r_A);
 				break;
-			case BPF_S_LDX_MEM:
+			case BPF_LDX | BPF_MEM:
 				emit_ldmem(K * 4, r_X);
 				break;
-			case BPF_S_ST:
+			case BPF_ST:
 				emit_stmem(K * 4, r_A);
 				break;
-			case BPF_S_STX:
+			case BPF_STX:
 				emit_stmem(K * 4, r_X);
 				break;
 
 #define CHOOSE_LOAD_FUNC(K, func) \
 	((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
 
-			case BPF_S_LD_W_ABS:
+			case BPF_LD | BPF_W | BPF_ABS:
 				func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_word);
 common_load:			seen |= SEEN_DATAREF;
 				emit_loadimm(K, r_OFF);
 				emit_call(func);
 				break;
-			case BPF_S_LD_H_ABS:
+			case BPF_LD | BPF_H | BPF_ABS:
 				func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_half);
 				goto common_load;
-			case BPF_S_LD_B_ABS:
+			case BPF_LD | BPF_B | BPF_ABS:
 				func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_byte);
 				goto common_load;
-			case BPF_S_LDX_B_MSH:
+			case BPF_LDX | BPF_B | BPF_MSH:
 				func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_byte_msh);
 				goto common_load;
-			case BPF_S_LD_W_IND:
+			case BPF_LD | BPF_W | BPF_IND:
 				func = bpf_jit_load_word;
 common_load_ind:		seen |= SEEN_DATAREF | SEEN_XREG;
 				if (K) {
@@ -683,13 +675,13 @@ common_load_ind:		seen |= SEEN_DATAREF | SEEN_XREG;
 				}
 				emit_call(func);
 				break;
-			case BPF_S_LD_H_IND:
+			case BPF_LD | BPF_H | BPF_IND:
 				func = bpf_jit_load_half;
 				goto common_load_ind;
-			case BPF_S_LD_B_IND:
+			case BPF_LD | BPF_B | BPF_IND:
 				func = bpf_jit_load_byte;
 				goto common_load_ind;
-			case BPF_S_JMP_JA:
+			case BPF_JMP | BPF_JA:
 				emit_jump(addrs[i + K]);
 				emit_nop();
 				break;
@@ -700,14 +692,14 @@ common_load_ind:		seen |= SEEN_DATAREF | SEEN_XREG;
 		f_op = FOP;		\
 		goto cond_branch
 
-			COND_SEL(BPF_S_JMP_JGT_K, BGU, BLEU);
-			COND_SEL(BPF_S_JMP_JGE_K, BGEU, BLU);
-			COND_SEL(BPF_S_JMP_JEQ_K, BE, BNE);
-			COND_SEL(BPF_S_JMP_JSET_K, BNE, BE);
-			COND_SEL(BPF_S_JMP_JGT_X, BGU, BLEU);
-			COND_SEL(BPF_S_JMP_JGE_X, BGEU, BLU);
-			COND_SEL(BPF_S_JMP_JEQ_X, BE, BNE);
-			COND_SEL(BPF_S_JMP_JSET_X, BNE, BE);
+			COND_SEL(BPF_JMP | BPF_JGT | BPF_K, BGU, BLEU);
+			COND_SEL(BPF_JMP | BPF_JGE | BPF_K, BGEU, BLU);
+			COND_SEL(BPF_JMP | BPF_JEQ | BPF_K, BE, BNE);
+			COND_SEL(BPF_JMP | BPF_JSET | BPF_K, BNE, BE);
+			COND_SEL(BPF_JMP | BPF_JGT | BPF_X, BGU, BLEU);
+			COND_SEL(BPF_JMP | BPF_JGE | BPF_X, BGEU, BLU);
+			COND_SEL(BPF_JMP | BPF_JEQ | BPF_X, BE, BNE);
+			COND_SEL(BPF_JMP | BPF_JSET | BPF_X, BNE, BE);
 
 cond_branch:			f_offset = addrs[i + filter[i].jf];
 				t_offset = addrs[i + filter[i].jt];
@@ -719,20 +711,20 @@ cond_branch:			f_offset = addrs[i + filter[i].jf];
 					break;
 				}
 
-				switch (filter[i].code) {
-				case BPF_S_JMP_JGT_X:
-				case BPF_S_JMP_JGE_X:
-				case BPF_S_JMP_JEQ_X:
+				switch (code) {
+				case BPF_JMP | BPF_JGT | BPF_X:
+				case BPF_JMP | BPF_JGE | BPF_X:
+				case BPF_JMP | BPF_JEQ | BPF_X:
 					seen |= SEEN_XREG;
 					emit_cmp(r_A, r_X);
 					break;
-				case BPF_S_JMP_JSET_X:
+				case BPF_JMP | BPF_JSET | BPF_X:
 					seen |= SEEN_XREG;
 					emit_btst(r_A, r_X);
 					break;
-				case BPF_S_JMP_JEQ_K:
-				case BPF_S_JMP_JGT_K:
-				case BPF_S_JMP_JGE_K:
+				case BPF_JMP | BPF_JEQ | BPF_K:
+				case BPF_JMP | BPF_JGT | BPF_K:
+				case BPF_JMP | BPF_JGE | BPF_K:
 					if (is_simm13(K)) {
 						emit_cmpi(r_A, K);
 					} else {
@@ -740,7 +732,7 @@ cond_branch:			f_offset = addrs[i + filter[i].jf];
 						emit_cmp(r_A, r_TMP);
 					}
 					break;
-				case BPF_S_JMP_JSET_K:
+				case BPF_JMP | BPF_JSET | BPF_K:
 					if (is_simm13(K)) {
 						emit_btsti(r_A, K);
 					} else {
diff --git a/arch/x86/include/asm/checksum_64.h b/arch/x86/include/asm/checksum_64.h
index e6fd8a0..cd00e17 100644
--- a/arch/x86/include/asm/checksum_64.h
+++ b/arch/x86/include/asm/checksum_64.h
@@ -184,8 +184,15 @@ static inline unsigned add32_with_carry(unsigned a, unsigned b)
 	asm("addl %2,%0\n\t"
 	    "adcl $0,%0"
 	    : "=r" (a)
-	    : "0" (a), "r" (b));
+	    : "0" (a), "rm" (b));
 	return a;
 }
 
+#define HAVE_ARCH_CSUM_ADD
+static inline __wsum csum_add(__wsum csum, __wsum addend)
+{
+	return (__force __wsum)add32_with_carry((__force unsigned)csum,
+						(__force unsigned)addend);
+}
+
 #endif /* _ASM_X86_CHECKSUM_64_H */
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 0149575..6440221 100644
--- a/arch/x86/net/bpf_jit.S
+++ b/arch/x86/net/bpf_jit.S
@@ -12,13 +12,16 @@
 
 /*
  * Calling convention :
- * rdi : skb pointer
+ * rbx : skb pointer (callee saved)
  * esi : offset of byte(s) to fetch in skb (can be scratched)
- * r8  : copy of skb->data
+ * r10 : copy of skb->data
  * r9d : hlen = skb->len - skb->data_len
  */
-#define SKBDATA	%r8
+#define SKBDATA	%r10
 #define SKF_MAX_NEG_OFF    $(-0x200000) /* SKF_LL_OFF from filter.h */
+#define MAX_BPF_STACK (512 /* from filter.h */ + \
+	32 /* space for rbx,r13,r14,r15 */ + \
+	8 /* space for skb_copy_bits */)
 
 sk_load_word:
 	.globl	sk_load_word
@@ -68,53 +71,31 @@ sk_load_byte_positive_offset:
 	movzbl	(SKBDATA,%rsi),%eax
 	ret
 
-/**
- * sk_load_byte_msh - BPF_S_LDX_B_MSH helper
- *
- * Implements BPF_S_LDX_B_MSH : ldxb  4*([offset]&0xf)
- * Must preserve A accumulator (%eax)
- * Inputs : %esi is the offset value
- */
-sk_load_byte_msh:
-	.globl	sk_load_byte_msh
-	test	%esi,%esi
-	js	bpf_slow_path_byte_msh_neg
-
-sk_load_byte_msh_positive_offset:
-	.globl	sk_load_byte_msh_positive_offset
-	cmp	%esi,%r9d      /* if (offset >= hlen) goto bpf_slow_path_byte_msh */
-	jle	bpf_slow_path_byte_msh
-	movzbl	(SKBDATA,%rsi),%ebx
-	and	$15,%bl
-	shl	$2,%bl
-	ret
-
 /* rsi contains offset and can be scratched */
 #define bpf_slow_path_common(LEN)		\
-	push	%rdi;    /* save skb */		\
+	mov	%rbx, %rdi; /* arg1 == skb */	\
 	push	%r9;				\
 	push	SKBDATA;			\
 /* rsi already has offset */			\
 	mov	$LEN,%ecx;	/* len */	\
-	lea	-12(%rbp),%rdx;			\
+	lea	- MAX_BPF_STACK + 32(%rbp),%rdx;			\
 	call	skb_copy_bits;			\
 	test    %eax,%eax;			\
 	pop	SKBDATA;			\
-	pop	%r9;				\
-	pop	%rdi
+	pop	%r9;
 
 
 bpf_slow_path_word:
 	bpf_slow_path_common(4)
 	js	bpf_error
-	mov	-12(%rbp),%eax
+	mov	- MAX_BPF_STACK + 32(%rbp),%eax
 	bswap	%eax
 	ret
 
 bpf_slow_path_half:
 	bpf_slow_path_common(2)
 	js	bpf_error
-	mov	-12(%rbp),%ax
+	mov	- MAX_BPF_STACK + 32(%rbp),%ax
 	rol	$8,%ax
 	movzwl	%ax,%eax
 	ret
@@ -122,21 +103,11 @@ bpf_slow_path_half:
 bpf_slow_path_byte:
 	bpf_slow_path_common(1)
 	js	bpf_error
-	movzbl	-12(%rbp),%eax
-	ret
-
-bpf_slow_path_byte_msh:
-	xchg	%eax,%ebx /* dont lose A , X is about to be scratched */
-	bpf_slow_path_common(1)
-	js	bpf_error
-	movzbl	-12(%rbp),%eax
-	and	$15,%al
-	shl	$2,%al
-	xchg	%eax,%ebx
+	movzbl	- MAX_BPF_STACK + 32(%rbp),%eax
 	ret
 
 #define sk_negative_common(SIZE)				\
-	push	%rdi;	/* save skb */				\
+	mov	%rbx, %rdi; /* arg1 == skb */			\
 	push	%r9;						\
 	push	SKBDATA;					\
 /* rsi already has offset */					\
@@ -145,10 +116,8 @@ bpf_slow_path_byte_msh:
 	test	%rax,%rax;					\
 	pop	SKBDATA;					\
 	pop	%r9;						\
-	pop	%rdi;						\
 	jz	bpf_error
 
-
 bpf_slow_path_word_neg:
 	cmp	SKF_MAX_NEG_OFF, %esi	/* test range */
 	jl	bpf_error	/* offset lower -> error  */
@@ -179,22 +148,12 @@ sk_load_byte_negative_offset:
 	movzbl	(%rax), %eax
 	ret
 
-bpf_slow_path_byte_msh_neg:
-	cmp	SKF_MAX_NEG_OFF, %esi
-	jl	bpf_error
-sk_load_byte_msh_negative_offset:
-	.globl	sk_load_byte_msh_negative_offset
-	xchg	%eax,%ebx /* dont lose A , X is about to be scratched */
-	sk_negative_common(1)
-	movzbl	(%rax),%eax
-	and	$15,%al
-	shl	$2,%al
-	xchg	%eax,%ebx
-	ret
-
 bpf_error:
 # force a return 0 from jit handler
-	xor		%eax,%eax
-	mov		-8(%rbp),%rbx
+	xor	%eax,%eax
+	mov	- MAX_BPF_STACK(%rbp),%rbx
+	mov	- MAX_BPF_STACK + 8(%rbp),%r13
+	mov	- MAX_BPF_STACK + 16(%rbp),%r14
+	mov	- MAX_BPF_STACK + 24(%rbp),%r15
 	leaveq
 	ret
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 6d5663a..99bef86 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1,6 +1,7 @@
 /* bpf_jit_comp.c : BPF JIT compiler
  *
  * Copyright (C) 2011-2013 Eric Dumazet (eric.dumazet@gmail.com)
+ * Internal BPF Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -14,28 +15,16 @@
 #include <linux/if_vlan.h>
 #include <linux/random.h>
 
-/*
- * Conventions :
- *  EAX : BPF A accumulator
- *  EBX : BPF X accumulator
- *  RDI : pointer to skb   (first argument given to JIT function)
- *  RBP : frame pointer (even if CONFIG_FRAME_POINTER=n)
- *  ECX,EDX,ESI : scratch registers
- *  r9d : skb->len - skb->data_len (headlen)
- *  r8  : skb->data
- * -8(RBP) : saved RBX value
- * -16(RBP)..-80(RBP) : BPF_MEMWORDS values
- */
 int bpf_jit_enable __read_mostly;
 
 /*
  * assembly code in arch/x86/net/bpf_jit.S
  */
-extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[];
+extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
 extern u8 sk_load_word_positive_offset[], sk_load_half_positive_offset[];
-extern u8 sk_load_byte_positive_offset[], sk_load_byte_msh_positive_offset[];
+extern u8 sk_load_byte_positive_offset[];
 extern u8 sk_load_word_negative_offset[], sk_load_half_negative_offset[];
-extern u8 sk_load_byte_negative_offset[], sk_load_byte_msh_negative_offset[];
+extern u8 sk_load_byte_negative_offset[];
 
 static inline u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 {
@@ -56,30 +45,44 @@ static inline u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 #define EMIT2(b1, b2)		EMIT((b1) + ((b2) << 8), 2)
 #define EMIT3(b1, b2, b3)	EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3)
 #define EMIT4(b1, b2, b3, b4)   EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4)
-#define EMIT1_off32(b1, off)	do { EMIT1(b1); EMIT(off, 4);} while (0)
-
-#define CLEAR_A() EMIT2(0x31, 0xc0) /* xor %eax,%eax */
-#define CLEAR_X() EMIT2(0x31, 0xdb) /* xor %ebx,%ebx */
+#define EMIT1_off32(b1, off) \
+	do {EMIT1(b1); EMIT(off, 4); } while (0)
+#define EMIT2_off32(b1, b2, off) \
+	do {EMIT2(b1, b2); EMIT(off, 4); } while (0)
+#define EMIT3_off32(b1, b2, b3, off) \
+	do {EMIT3(b1, b2, b3); EMIT(off, 4); } while (0)
+#define EMIT4_off32(b1, b2, b3, b4, off) \
+	do {EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0)
 
 static inline bool is_imm8(int value)
 {
 	return value <= 127 && value >= -128;
 }
 
-static inline bool is_near(int offset)
+static inline bool is_simm32(s64 value)
 {
-	return offset <= 127 && offset >= -128;
+	return value == (s64) (s32) value;
 }
 
-#define EMIT_JMP(offset)						\
-do {									\
-	if (offset) {							\
-		if (is_near(offset))					\
-			EMIT2(0xeb, offset); /* jmp .+off8 */		\
-		else							\
-			EMIT1_off32(0xe9, offset); /* jmp .+off32 */	\
-	}								\
-} while (0)
+/* mov dst, src */
+#define EMIT_mov(DST, SRC) \
+	do {if (DST != SRC) \
+		EMIT3(add_2mod(0x48, DST, SRC), 0x89, add_2reg(0xC0, DST, SRC)); \
+	} while (0)
+
+static int bpf_size_to_x86_bytes(int bpf_size)
+{
+	if (bpf_size == BPF_W)
+		return 4;
+	else if (bpf_size == BPF_H)
+		return 2;
+	else if (bpf_size == BPF_B)
+		return 1;
+	else if (bpf_size == BPF_DW)
+		return 4; /* imm32 */
+	else
+		return 0;
+}
 
 /* list of x86 cond jumps opcodes (. + s8)
  * Add 0x10 (and an extra 0x0f) to generate far jumps (. + s32)
@@ -90,27 +93,8 @@ do {									\
 #define X86_JNE 0x75
 #define X86_JBE 0x76
 #define X86_JA  0x77
-
-#define EMIT_COND_JMP(op, offset)				\
-do {								\
-	if (is_near(offset))					\
-		EMIT2(op, offset); /* jxx .+off8 */		\
-	else {							\
-		EMIT2(0x0f, op + 0x10);				\
-		EMIT(offset, 4); /* jxx .+off32 */		\
-	}							\
-} while (0)
-
-#define COND_SEL(CODE, TOP, FOP)	\
-	case CODE:			\
-		t_op = TOP;		\
-		f_op = FOP;		\
-		goto cond_branch
-
-
-#define SEEN_DATAREF 1 /* might call external helpers */
-#define SEEN_XREG    2 /* ebx is used */
-#define SEEN_MEM     4 /* use mem[] for temporary storage */
+#define X86_JGE 0x7D
+#define X86_JG  0x7F
 
 static inline void bpf_flush_icache(void *start, void *end)
 {
@@ -125,26 +109,6 @@ static inline void bpf_flush_icache(void *start, void *end)
 #define CHOOSE_LOAD_FUNC(K, func) \
 	((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
 
-/* Helper to find the offset of pkt_type in sk_buff
- * We want to make sure its still a 3bit field starting at a byte boundary.
- */
-#define PKT_TYPE_MAX 7
-static int pkt_type_offset(void)
-{
-	struct sk_buff skb_probe = {
-		.pkt_type = ~0,
-	};
-	char *ct = (char *)&skb_probe;
-	unsigned int off;
-
-	for (off = 0; off < sizeof(struct sk_buff); off++) {
-		if (ct[off] == PKT_TYPE_MAX)
-			return off;
-	}
-	pr_err_once("Please fix pkt_type_offset(), as pkt_type couldn't be found\n");
-	return -1;
-}
-
 struct bpf_binary_header {
 	unsigned int	pages;
 	/* Note : for security reasons, bpf code will follow a randomly
@@ -178,583 +142,771 @@ static struct bpf_binary_header *bpf_alloc_binary(unsigned int proglen,
 	return header;
 }
 
-void bpf_jit_compile(struct sk_filter *fp)
+/* pick a register outside of BPF range for JIT internal work */
+#define AUX_REG (MAX_BPF_REG + 1)
+
+/* the following table maps BPF registers to x64 registers.
+ * x64 register r12 is unused, since if used as base address register
+ * in load/store instructions, it always needs an extra byte of encoding
+ */
+static const int reg2hex[] = {
+	[BPF_REG_0] = 0,  /* rax */
+	[BPF_REG_1] = 7,  /* rdi */
+	[BPF_REG_2] = 6,  /* rsi */
+	[BPF_REG_3] = 2,  /* rdx */
+	[BPF_REG_4] = 1,  /* rcx */
+	[BPF_REG_5] = 0,  /* r8 */
+	[BPF_REG_6] = 3,  /* rbx callee saved */
+	[BPF_REG_7] = 5,  /* r13 callee saved */
+	[BPF_REG_8] = 6,  /* r14 callee saved */
+	[BPF_REG_9] = 7,  /* r15 callee saved */
+	[BPF_REG_FP] = 5, /* rbp readonly */
+	[AUX_REG] = 3,    /* r11 temp register */
+};
+
+/* is_ereg() == true if BPF register 'reg' maps to x64 r8..r15
+ * which need extra byte of encoding.
+ * rax,rcx,...,rbp have simpler encoding
+ */
+static inline bool is_ereg(u32 reg)
 {
-	u8 temp[64];
-	u8 *prog;
-	unsigned int proglen, oldproglen = 0;
-	int ilen, i;
-	int t_offset, f_offset;
-	u8 t_op, f_op, seen = 0, pass;
-	u8 *image = NULL;
-	struct bpf_binary_header *header = NULL;
-	u8 *func;
-	int pc_ret0 = -1; /* bpf index of first RET #0 instruction (if any) */
-	unsigned int cleanup_addr; /* epilogue code offset */
-	unsigned int *addrs;
-	const struct sock_filter *filter = fp->insns;
-	int flen = fp->len;
+	if (reg == BPF_REG_5 || reg == AUX_REG ||
+	    (reg >= BPF_REG_7 && reg <= BPF_REG_9))
+		return true;
+	else
+		return false;
+}
 
-	if (!bpf_jit_enable)
-		return;
+/* add modifiers if 'reg' maps to x64 registers r8..r15 */
+static inline u8 add_1mod(u8 byte, u32 reg)
+{
+	if (is_ereg(reg))
+		byte |= 1;
+	return byte;
+}
 
-	addrs = kmalloc(flen * sizeof(*addrs), GFP_KERNEL);
-	if (addrs == NULL)
-		return;
+static inline u8 add_2mod(u8 byte, u32 r1, u32 r2)
+{
+	if (is_ereg(r1))
+		byte |= 1;
+	if (is_ereg(r2))
+		byte |= 4;
+	return byte;
+}
 
-	/* Before first pass, make a rough estimation of addrs[]
-	 * each bpf instruction is translated to less than 64 bytes
+/* encode 'dst_reg' register into x64 opcode 'byte' */
+static inline u8 add_1reg(u8 byte, u32 dst_reg)
+{
+	return byte + reg2hex[dst_reg];
+}
+
+/* encode 'dst_reg' and 'src_reg' registers into x64 opcode 'byte' */
+static inline u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg)
+{
+	return byte + reg2hex[dst_reg] + (reg2hex[src_reg] << 3);
+}
+
+struct jit_context {
+	unsigned int cleanup_addr; /* epilogue code offset */
+	bool seen_ld_abs;
+};
+
+static int do_jit(struct sk_filter *bpf_prog, int *addrs, u8 *image,
+		  int oldproglen, struct jit_context *ctx)
+{
+	struct sock_filter_int *insn = bpf_prog->insnsi;
+	int insn_cnt = bpf_prog->len;
+	u8 temp[64];
+	int i;
+	int proglen = 0;
+	u8 *prog = temp;
+	int stacksize = MAX_BPF_STACK +
+		32 /* space for rbx, r13, r14, r15 */ +
+		8 /* space for skb_copy_bits() buffer */;
+
+	EMIT1(0x55); /* push rbp */
+	EMIT3(0x48, 0x89, 0xE5); /* mov rbp,rsp */
+
+	/* sub rsp, stacksize */
+	EMIT3_off32(0x48, 0x81, 0xEC, stacksize);
+
+	/* all classic BPF filters use R6(rbx) save it */
+
+	/* mov qword ptr [rbp-X],rbx */
+	EMIT3_off32(0x48, 0x89, 0x9D, -stacksize);
+
+	/* sk_convert_filter() maps classic BPF register X to R7 and uses R8
+	 * as temporary, so all tcpdump filters need to spill/fill R7(r13) and
+	 * R8(r14). R9(r15) spill could be made conditional, but there is only
+	 * one 'bpf_error' return path out of helper functions inside bpf_jit.S
+	 * The overhead of extra spill is negligible for any filter other
+	 * than synthetic ones. Therefore not worth adding complexity.
 	 */
-	for (proglen = 0, i = 0; i < flen; i++) {
-		proglen += 64;
-		addrs[i] = proglen;
+
+	/* mov qword ptr [rbp-X],r13 */
+	EMIT3_off32(0x4C, 0x89, 0xAD, -stacksize + 8);
+	/* mov qword ptr [rbp-X],r14 */
+	EMIT3_off32(0x4C, 0x89, 0xB5, -stacksize + 16);
+	/* mov qword ptr [rbp-X],r15 */
+	EMIT3_off32(0x4C, 0x89, 0xBD, -stacksize + 24);
+
+	/* clear A and X registers */
+	EMIT2(0x31, 0xc0); /* xor eax, eax */
+	EMIT3(0x4D, 0x31, 0xED); /* xor r13, r13 */
+
+	if (ctx->seen_ld_abs) {
+		/* r9d : skb->len - skb->data_len (headlen)
+		 * r10 : skb->data
+		 */
+		if (is_imm8(offsetof(struct sk_buff, len)))
+			/* mov %r9d, off8(%rdi) */
+			EMIT4(0x44, 0x8b, 0x4f,
+			      offsetof(struct sk_buff, len));
+		else
+			/* mov %r9d, off32(%rdi) */
+			EMIT3_off32(0x44, 0x8b, 0x8f,
+				    offsetof(struct sk_buff, len));
+
+		if (is_imm8(offsetof(struct sk_buff, data_len)))
+			/* sub %r9d, off8(%rdi) */
+			EMIT4(0x44, 0x2b, 0x4f,
+			      offsetof(struct sk_buff, data_len));
+		else
+			EMIT3_off32(0x44, 0x2b, 0x8f,
+				    offsetof(struct sk_buff, data_len));
+
+		if (is_imm8(offsetof(struct sk_buff, data)))
+			/* mov %r10, off8(%rdi) */
+			EMIT4(0x4c, 0x8b, 0x57,
+			      offsetof(struct sk_buff, data));
+		else
+			/* mov %r10, off32(%rdi) */
+			EMIT3_off32(0x4c, 0x8b, 0x97,
+				    offsetof(struct sk_buff, data));
 	}
-	cleanup_addr = proglen; /* epilogue address */
 
-	for (pass = 0; pass < 10; pass++) {
-		u8 seen_or_pass0 = (pass == 0) ? (SEEN_XREG | SEEN_DATAREF | SEEN_MEM) : seen;
-		/* no prologue/epilogue for trivial filters (RET something) */
-		proglen = 0;
-		prog = temp;
+	for (i = 0; i < insn_cnt; i++, insn++) {
+		const s32 imm32 = insn->imm;
+		u32 dst_reg = insn->dst_reg;
+		u32 src_reg = insn->src_reg;
+		u8 b1 = 0, b2 = 0, b3 = 0;
+		s64 jmp_offset;
+		u8 jmp_cond;
+		int ilen;
+		u8 *func;
+
+		switch (insn->code) {
+			/* ALU */
+		case BPF_ALU | BPF_ADD | BPF_X:
+		case BPF_ALU | BPF_SUB | BPF_X:
+		case BPF_ALU | BPF_AND | BPF_X:
+		case BPF_ALU | BPF_OR | BPF_X:
+		case BPF_ALU | BPF_XOR | BPF_X:
+		case BPF_ALU64 | BPF_ADD | BPF_X:
+		case BPF_ALU64 | BPF_SUB | BPF_X:
+		case BPF_ALU64 | BPF_AND | BPF_X:
+		case BPF_ALU64 | BPF_OR | BPF_X:
+		case BPF_ALU64 | BPF_XOR | BPF_X:
+			switch (BPF_OP(insn->code)) {
+			case BPF_ADD: b2 = 0x01; break;
+			case BPF_SUB: b2 = 0x29; break;
+			case BPF_AND: b2 = 0x21; break;
+			case BPF_OR: b2 = 0x09; break;
+			case BPF_XOR: b2 = 0x31; break;
+			}
+			if (BPF_CLASS(insn->code) == BPF_ALU64)
+				EMIT1(add_2mod(0x48, dst_reg, src_reg));
+			else if (is_ereg(dst_reg) || is_ereg(src_reg))
+				EMIT1(add_2mod(0x40, dst_reg, src_reg));
+			EMIT2(b2, add_2reg(0xC0, dst_reg, src_reg));
+			break;
 
-		if (seen_or_pass0) {
-			EMIT4(0x55, 0x48, 0x89, 0xe5); /* push %rbp; mov %rsp,%rbp */
-			EMIT4(0x48, 0x83, 0xec, 96);	/* subq  $96,%rsp	*/
-			/* note : must save %rbx in case bpf_error is hit */
-			if (seen_or_pass0 & (SEEN_XREG | SEEN_DATAREF))
-				EMIT4(0x48, 0x89, 0x5d, 0xf8); /* mov %rbx, -8(%rbp) */
-			if (seen_or_pass0 & SEEN_XREG)
-				CLEAR_X(); /* make sure we dont leek kernel memory */
-
-			/*
-			 * If this filter needs to access skb data,
-			 * loads r9 and r8 with :
-			 *  r9 = skb->len - skb->data_len
-			 *  r8 = skb->data
+			/* mov dst, src */
+		case BPF_ALU64 | BPF_MOV | BPF_X:
+			EMIT_mov(dst_reg, src_reg);
+			break;
+
+			/* mov32 dst, src */
+		case BPF_ALU | BPF_MOV | BPF_X:
+			if (is_ereg(dst_reg) || is_ereg(src_reg))
+				EMIT1(add_2mod(0x40, dst_reg, src_reg));
+			EMIT2(0x89, add_2reg(0xC0, dst_reg, src_reg));
+			break;
+
+			/* neg dst */
+		case BPF_ALU | BPF_NEG:
+		case BPF_ALU64 | BPF_NEG:
+			if (BPF_CLASS(insn->code) == BPF_ALU64)
+				EMIT1(add_1mod(0x48, dst_reg));
+			else if (is_ereg(dst_reg))
+				EMIT1(add_1mod(0x40, dst_reg));
+			EMIT2(0xF7, add_1reg(0xD8, dst_reg));
+			break;
+
+		case BPF_ALU | BPF_ADD | BPF_K:
+		case BPF_ALU | BPF_SUB | BPF_K:
+		case BPF_ALU | BPF_AND | BPF_K:
+		case BPF_ALU | BPF_OR | BPF_K:
+		case BPF_ALU | BPF_XOR | BPF_K:
+		case BPF_ALU64 | BPF_ADD | BPF_K:
+		case BPF_ALU64 | BPF_SUB | BPF_K:
+		case BPF_ALU64 | BPF_AND | BPF_K:
+		case BPF_ALU64 | BPF_OR | BPF_K:
+		case BPF_ALU64 | BPF_XOR | BPF_K:
+			if (BPF_CLASS(insn->code) == BPF_ALU64)
+				EMIT1(add_1mod(0x48, dst_reg));
+			else if (is_ereg(dst_reg))
+				EMIT1(add_1mod(0x40, dst_reg));
+
+			switch (BPF_OP(insn->code)) {
+			case BPF_ADD: b3 = 0xC0; break;
+			case BPF_SUB: b3 = 0xE8; break;
+			case BPF_AND: b3 = 0xE0; break;
+			case BPF_OR: b3 = 0xC8; break;
+			case BPF_XOR: b3 = 0xF0; break;
+			}
+
+			if (is_imm8(imm32))
+				EMIT3(0x83, add_1reg(b3, dst_reg), imm32);
+			else
+				EMIT2_off32(0x81, add_1reg(b3, dst_reg), imm32);
+			break;
+
+		case BPF_ALU64 | BPF_MOV | BPF_K:
+			/* optimization: if imm32 is positive,
+			 * use 'mov eax, imm32' (which zero-extends imm32)
+			 * to save 2 bytes
 			 */
-			if (seen_or_pass0 & SEEN_DATAREF) {
-				if (offsetof(struct sk_buff, len) <= 127)
-					/* mov    off8(%rdi),%r9d */
-					EMIT4(0x44, 0x8b, 0x4f, offsetof(struct sk_buff, len));
-				else {
-					/* mov    off32(%rdi),%r9d */
-					EMIT3(0x44, 0x8b, 0x8f);
-					EMIT(offsetof(struct sk_buff, len), 4);
-				}
-				if (is_imm8(offsetof(struct sk_buff, data_len)))
-					/* sub    off8(%rdi),%r9d */
-					EMIT4(0x44, 0x2b, 0x4f, offsetof(struct sk_buff, data_len));
-				else {
-					EMIT3(0x44, 0x2b, 0x8f);
-					EMIT(offsetof(struct sk_buff, data_len), 4);
-				}
+			if (imm32 < 0) {
+				/* 'mov rax, imm32' sign extends imm32 */
+				b1 = add_1mod(0x48, dst_reg);
+				b2 = 0xC7;
+				b3 = 0xC0;
+				EMIT3_off32(b1, b2, add_1reg(b3, dst_reg), imm32);
+				break;
+			}
 
-				if (is_imm8(offsetof(struct sk_buff, data)))
-					/* mov off8(%rdi),%r8 */
-					EMIT4(0x4c, 0x8b, 0x47, offsetof(struct sk_buff, data));
-				else {
-					/* mov off32(%rdi),%r8 */
-					EMIT3(0x4c, 0x8b, 0x87);
-					EMIT(offsetof(struct sk_buff, data), 4);
-				}
+		case BPF_ALU | BPF_MOV | BPF_K:
+			/* mov %eax, imm32 */
+			if (is_ereg(dst_reg))
+				EMIT1(add_1mod(0x40, dst_reg));
+			EMIT1_off32(add_1reg(0xB8, dst_reg), imm32);
+			break;
+
+			/* dst %= src, dst /= src, dst %= imm32, dst /= imm32 */
+		case BPF_ALU | BPF_MOD | BPF_X:
+		case BPF_ALU | BPF_DIV | BPF_X:
+		case BPF_ALU | BPF_MOD | BPF_K:
+		case BPF_ALU | BPF_DIV | BPF_K:
+		case BPF_ALU64 | BPF_MOD | BPF_X:
+		case BPF_ALU64 | BPF_DIV | BPF_X:
+		case BPF_ALU64 | BPF_MOD | BPF_K:
+		case BPF_ALU64 | BPF_DIV | BPF_K:
+			EMIT1(0x50); /* push rax */
+			EMIT1(0x52); /* push rdx */
+
+			if (BPF_SRC(insn->code) == BPF_X)
+				/* mov r11, src_reg */
+				EMIT_mov(AUX_REG, src_reg);
+			else
+				/* mov r11, imm32 */
+				EMIT3_off32(0x49, 0xC7, 0xC3, imm32);
+
+			/* mov rax, dst_reg */
+			EMIT_mov(BPF_REG_0, dst_reg);
+
+			/* xor edx, edx
+			 * equivalent to 'xor rdx, rdx', but one byte less
+			 */
+			EMIT2(0x31, 0xd2);
+
+			if (BPF_SRC(insn->code) == BPF_X) {
+				/* if (src_reg == 0) return 0 */
+
+				/* cmp r11, 0 */
+				EMIT4(0x49, 0x83, 0xFB, 0x00);
+
+				/* jne .+9 (skip over pop, pop, xor and jmp) */
+				EMIT2(X86_JNE, 1 + 1 + 2 + 5);
+				EMIT1(0x5A); /* pop rdx */
+				EMIT1(0x58); /* pop rax */
+				EMIT2(0x31, 0xc0); /* xor eax, eax */
+
+				/* jmp cleanup_addr
+				 * addrs[i] - 11, because there are 11 bytes
+				 * after this insn: div, mov, pop, pop, mov
+				 */
+				jmp_offset = ctx->cleanup_addr - (addrs[i] - 11);
+				EMIT1_off32(0xE9, jmp_offset);
 			}
-		}
 
-		switch (filter[0].code) {
-		case BPF_S_RET_K:
-		case BPF_S_LD_W_LEN:
-		case BPF_S_ANC_PROTOCOL:
-		case BPF_S_ANC_IFINDEX:
-		case BPF_S_ANC_MARK:
-		case BPF_S_ANC_RXHASH:
-		case BPF_S_ANC_CPU:
-		case BPF_S_ANC_VLAN_TAG:
-		case BPF_S_ANC_VLAN_TAG_PRESENT:
-		case BPF_S_ANC_QUEUE:
-		case BPF_S_ANC_PKTTYPE:
-		case BPF_S_LD_W_ABS:
-		case BPF_S_LD_H_ABS:
-		case BPF_S_LD_B_ABS:
-			/* first instruction sets A register (or is RET 'constant') */
+			if (BPF_CLASS(insn->code) == BPF_ALU64)
+				/* div r11 */
+				EMIT3(0x49, 0xF7, 0xF3);
+			else
+				/* div r11d */
+				EMIT3(0x41, 0xF7, 0xF3);
+
+			if (BPF_OP(insn->code) == BPF_MOD)
+				/* mov r11, rdx */
+				EMIT3(0x49, 0x89, 0xD3);
+			else
+				/* mov r11, rax */
+				EMIT3(0x49, 0x89, 0xC3);
+
+			EMIT1(0x5A); /* pop rdx */
+			EMIT1(0x58); /* pop rax */
+
+			/* mov dst_reg, r11 */
+			EMIT_mov(dst_reg, AUX_REG);
 			break;
-		default:
-			/* make sure we dont leak kernel information to user */
-			CLEAR_A(); /* A = 0 */
-		}
 
-		for (i = 0; i < flen; i++) {
-			unsigned int K = filter[i].k;
+		case BPF_ALU | BPF_MUL | BPF_K:
+		case BPF_ALU | BPF_MUL | BPF_X:
+		case BPF_ALU64 | BPF_MUL | BPF_K:
+		case BPF_ALU64 | BPF_MUL | BPF_X:
+			EMIT1(0x50); /* push rax */
+			EMIT1(0x52); /* push rdx */
+
+			/* mov r11, dst_reg */
+			EMIT_mov(AUX_REG, dst_reg);
+
+			if (BPF_SRC(insn->code) == BPF_X)
+				/* mov rax, src_reg */
+				EMIT_mov(BPF_REG_0, src_reg);
+			else
+				/* mov rax, imm32 */
+				EMIT3_off32(0x48, 0xC7, 0xC0, imm32);
+
+			if (BPF_CLASS(insn->code) == BPF_ALU64)
+				EMIT1(add_1mod(0x48, AUX_REG));
+			else if (is_ereg(AUX_REG))
+				EMIT1(add_1mod(0x40, AUX_REG));
+			/* mul(q) r11 */
+			EMIT2(0xF7, add_1reg(0xE0, AUX_REG));
+
+			/* mov r11, rax */
+			EMIT_mov(AUX_REG, BPF_REG_0);
+
+			EMIT1(0x5A); /* pop rdx */
+			EMIT1(0x58); /* pop rax */
+
+			/* mov dst_reg, r11 */
+			EMIT_mov(dst_reg, AUX_REG);
+			break;
 
-			switch (filter[i].code) {
-			case BPF_S_ALU_ADD_X: /* A += X; */
-				seen |= SEEN_XREG;
-				EMIT2(0x01, 0xd8);		/* add %ebx,%eax */
-				break;
-			case BPF_S_ALU_ADD_K: /* A += K; */
-				if (!K)
-					break;
-				if (is_imm8(K))
-					EMIT3(0x83, 0xc0, K);	/* add imm8,%eax */
-				else
-					EMIT1_off32(0x05, K);	/* add imm32,%eax */
-				break;
-			case BPF_S_ALU_SUB_X: /* A -= X; */
-				seen |= SEEN_XREG;
-				EMIT2(0x29, 0xd8);		/* sub    %ebx,%eax */
-				break;
-			case BPF_S_ALU_SUB_K: /* A -= K */
-				if (!K)
-					break;
-				if (is_imm8(K))
-					EMIT3(0x83, 0xe8, K); /* sub imm8,%eax */
-				else
-					EMIT1_off32(0x2d, K); /* sub imm32,%eax */
-				break;
-			case BPF_S_ALU_MUL_X: /* A *= X; */
-				seen |= SEEN_XREG;
-				EMIT3(0x0f, 0xaf, 0xc3);	/* imul %ebx,%eax */
-				break;
-			case BPF_S_ALU_MUL_K: /* A *= K */
-				if (is_imm8(K))
-					EMIT3(0x6b, 0xc0, K); /* imul imm8,%eax,%eax */
-				else {
-					EMIT2(0x69, 0xc0);		/* imul imm32,%eax */
-					EMIT(K, 4);
-				}
-				break;
-			case BPF_S_ALU_DIV_X: /* A /= X; */
-				seen |= SEEN_XREG;
-				EMIT2(0x85, 0xdb);	/* test %ebx,%ebx */
-				if (pc_ret0 > 0) {
-					/* addrs[pc_ret0 - 1] is start address of target
-					 * (addrs[i] - 4) is the address following this jmp
-					 * ("xor %edx,%edx; div %ebx" being 4 bytes long)
-					 */
-					EMIT_COND_JMP(X86_JE, addrs[pc_ret0 - 1] -
-								(addrs[i] - 4));
-				} else {
-					EMIT_COND_JMP(X86_JNE, 2 + 5);
-					CLEAR_A();
-					EMIT1_off32(0xe9, cleanup_addr - (addrs[i] - 4)); /* jmp .+off32 */
-				}
-				EMIT4(0x31, 0xd2, 0xf7, 0xf3); /* xor %edx,%edx; div %ebx */
-				break;
-			case BPF_S_ALU_MOD_X: /* A %= X; */
-				seen |= SEEN_XREG;
-				EMIT2(0x85, 0xdb);	/* test %ebx,%ebx */
-				if (pc_ret0 > 0) {
-					/* addrs[pc_ret0 - 1] is start address of target
-					 * (addrs[i] - 6) is the address following this jmp
-					 * ("xor %edx,%edx; div %ebx;mov %edx,%eax" being 6 bytes long)
-					 */
-					EMIT_COND_JMP(X86_JE, addrs[pc_ret0 - 1] -
-								(addrs[i] - 6));
-				} else {
-					EMIT_COND_JMP(X86_JNE, 2 + 5);
-					CLEAR_A();
-					EMIT1_off32(0xe9, cleanup_addr - (addrs[i] - 6)); /* jmp .+off32 */
-				}
-				EMIT2(0x31, 0xd2);	/* xor %edx,%edx */
-				EMIT2(0xf7, 0xf3);	/* div %ebx */
-				EMIT2(0x89, 0xd0);	/* mov %edx,%eax */
-				break;
-			case BPF_S_ALU_MOD_K: /* A %= K; */
-				if (K == 1) {
-					CLEAR_A();
-					break;
-				}
-				EMIT2(0x31, 0xd2);	/* xor %edx,%edx */
-				EMIT1(0xb9);EMIT(K, 4);	/* mov imm32,%ecx */
-				EMIT2(0xf7, 0xf1);	/* div %ecx */
-				EMIT2(0x89, 0xd0);	/* mov %edx,%eax */
-				break;
-			case BPF_S_ALU_DIV_K: /* A /= K */
-				if (K == 1)
-					break;
-				EMIT2(0x31, 0xd2);	/* xor %edx,%edx */
-				EMIT1(0xb9);EMIT(K, 4);	/* mov imm32,%ecx */
-				EMIT2(0xf7, 0xf1);	/* div %ecx */
-				break;
-			case BPF_S_ALU_AND_X:
-				seen |= SEEN_XREG;
-				EMIT2(0x21, 0xd8);		/* and %ebx,%eax */
-				break;
-			case BPF_S_ALU_AND_K:
-				if (K >= 0xFFFFFF00) {
-					EMIT2(0x24, K & 0xFF); /* and imm8,%al */
-				} else if (K >= 0xFFFF0000) {
-					EMIT2(0x66, 0x25);	/* and imm16,%ax */
-					EMIT(K, 2);
-				} else {
-					EMIT1_off32(0x25, K);	/* and imm32,%eax */
-				}
-				break;
-			case BPF_S_ALU_OR_X:
-				seen |= SEEN_XREG;
-				EMIT2(0x09, 0xd8);		/* or %ebx,%eax */
-				break;
-			case BPF_S_ALU_OR_K:
-				if (is_imm8(K))
-					EMIT3(0x83, 0xc8, K); /* or imm8,%eax */
-				else
-					EMIT1_off32(0x0d, K);	/* or imm32,%eax */
-				break;
-			case BPF_S_ANC_ALU_XOR_X: /* A ^= X; */
-			case BPF_S_ALU_XOR_X:
-				seen |= SEEN_XREG;
-				EMIT2(0x31, 0xd8);		/* xor %ebx,%eax */
-				break;
-			case BPF_S_ALU_XOR_K: /* A ^= K; */
-				if (K == 0)
-					break;
-				if (is_imm8(K))
-					EMIT3(0x83, 0xf0, K);	/* xor imm8,%eax */
-				else
-					EMIT1_off32(0x35, K);	/* xor imm32,%eax */
-				break;
-			case BPF_S_ALU_LSH_X: /* A <<= X; */
-				seen |= SEEN_XREG;
-				EMIT4(0x89, 0xd9, 0xd3, 0xe0);	/* mov %ebx,%ecx; shl %cl,%eax */
-				break;
-			case BPF_S_ALU_LSH_K:
-				if (K == 0)
-					break;
-				else if (K == 1)
-					EMIT2(0xd1, 0xe0); /* shl %eax */
-				else
-					EMIT3(0xc1, 0xe0, K);
-				break;
-			case BPF_S_ALU_RSH_X: /* A >>= X; */
-				seen |= SEEN_XREG;
-				EMIT4(0x89, 0xd9, 0xd3, 0xe8);	/* mov %ebx,%ecx; shr %cl,%eax */
-				break;
-			case BPF_S_ALU_RSH_K: /* A >>= K; */
-				if (K == 0)
-					break;
-				else if (K == 1)
-					EMIT2(0xd1, 0xe8); /* shr %eax */
-				else
-					EMIT3(0xc1, 0xe8, K);
-				break;
-			case BPF_S_ALU_NEG:
-				EMIT2(0xf7, 0xd8);		/* neg %eax */
-				break;
-			case BPF_S_RET_K:
-				if (!K) {
-					if (pc_ret0 == -1)
-						pc_ret0 = i;
-					CLEAR_A();
-				} else {
-					EMIT1_off32(0xb8, K);	/* mov $imm32,%eax */
-				}
-				/* fallinto */
-			case BPF_S_RET_A:
-				if (seen_or_pass0) {
-					if (i != flen - 1) {
-						EMIT_JMP(cleanup_addr - addrs[i]);
-						break;
-					}
-					if (seen_or_pass0 & SEEN_XREG)
-						EMIT4(0x48, 0x8b, 0x5d, 0xf8);  /* mov  -8(%rbp),%rbx */
-					EMIT1(0xc9);		/* leaveq */
-				}
-				EMIT1(0xc3);		/* ret */
-				break;
-			case BPF_S_MISC_TAX: /* X = A */
-				seen |= SEEN_XREG;
-				EMIT2(0x89, 0xc3);	/* mov    %eax,%ebx */
-				break;
-			case BPF_S_MISC_TXA: /* A = X */
-				seen |= SEEN_XREG;
-				EMIT2(0x89, 0xd8);	/* mov    %ebx,%eax */
-				break;
-			case BPF_S_LD_IMM: /* A = K */
-				if (!K)
-					CLEAR_A();
-				else
-					EMIT1_off32(0xb8, K); /* mov $imm32,%eax */
-				break;
-			case BPF_S_LDX_IMM: /* X = K */
-				seen |= SEEN_XREG;
-				if (!K)
-					CLEAR_X();
+			/* shifts */
+		case BPF_ALU | BPF_LSH | BPF_K:
+		case BPF_ALU | BPF_RSH | BPF_K:
+		case BPF_ALU | BPF_ARSH | BPF_K:
+		case BPF_ALU64 | BPF_LSH | BPF_K:
+		case BPF_ALU64 | BPF_RSH | BPF_K:
+		case BPF_ALU64 | BPF_ARSH | BPF_K:
+			if (BPF_CLASS(insn->code) == BPF_ALU64)
+				EMIT1(add_1mod(0x48, dst_reg));
+			else if (is_ereg(dst_reg))
+				EMIT1(add_1mod(0x40, dst_reg));
+
+			switch (BPF_OP(insn->code)) {
+			case BPF_LSH: b3 = 0xE0; break;
+			case BPF_RSH: b3 = 0xE8; break;
+			case BPF_ARSH: b3 = 0xF8; break;
+			}
+			EMIT3(0xC1, add_1reg(b3, dst_reg), imm32);
+			break;
+
+		case BPF_ALU | BPF_END | BPF_FROM_BE:
+			switch (imm32) {
+			case 16:
+				/* emit 'ror %ax, 8' to swap lower 2 bytes */
+				EMIT1(0x66);
+				if (is_ereg(dst_reg))
+					EMIT1(0x41);
+				EMIT3(0xC1, add_1reg(0xC8, dst_reg), 8);
+				break;
+			case 32:
+				/* emit 'bswap eax' to swap lower 4 bytes */
+				if (is_ereg(dst_reg))
+					EMIT2(0x41, 0x0F);
 				else
-					EMIT1_off32(0xbb, K); /* mov $imm32,%ebx */
-				break;
-			case BPF_S_LD_MEM: /* A = mem[K] : mov off8(%rbp),%eax */
-				seen |= SEEN_MEM;
-				EMIT3(0x8b, 0x45, 0xf0 - K*4);
-				break;
-			case BPF_S_LDX_MEM: /* X = mem[K] : mov off8(%rbp),%ebx */
-				seen |= SEEN_XREG | SEEN_MEM;
-				EMIT3(0x8b, 0x5d, 0xf0 - K*4);
-				break;
-			case BPF_S_ST: /* mem[K] = A : mov %eax,off8(%rbp) */
-				seen |= SEEN_MEM;
-				EMIT3(0x89, 0x45, 0xf0 - K*4);
-				break;
-			case BPF_S_STX: /* mem[K] = X : mov %ebx,off8(%rbp) */
-				seen |= SEEN_XREG | SEEN_MEM;
-				EMIT3(0x89, 0x5d, 0xf0 - K*4);
-				break;
-			case BPF_S_LD_W_LEN: /*	A = skb->len; */
-				BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4);
-				if (is_imm8(offsetof(struct sk_buff, len)))
-					/* mov    off8(%rdi),%eax */
-					EMIT3(0x8b, 0x47, offsetof(struct sk_buff, len));
-				else {
-					EMIT2(0x8b, 0x87);
-					EMIT(offsetof(struct sk_buff, len), 4);
-				}
-				break;
-			case BPF_S_LDX_W_LEN: /* X = skb->len; */
-				seen |= SEEN_XREG;
-				if (is_imm8(offsetof(struct sk_buff, len)))
-					/* mov off8(%rdi),%ebx */
-					EMIT3(0x8b, 0x5f, offsetof(struct sk_buff, len));
-				else {
-					EMIT2(0x8b, 0x9f);
-					EMIT(offsetof(struct sk_buff, len), 4);
-				}
-				break;
-			case BPF_S_ANC_PROTOCOL: /* A = ntohs(skb->protocol); */
-				BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2);
-				if (is_imm8(offsetof(struct sk_buff, protocol))) {
-					/* movzwl off8(%rdi),%eax */
-					EMIT4(0x0f, 0xb7, 0x47, offsetof(struct sk_buff, protocol));
-				} else {
-					EMIT3(0x0f, 0xb7, 0x87); /* movzwl off32(%rdi),%eax */
-					EMIT(offsetof(struct sk_buff, protocol), 4);
-				}
-				EMIT2(0x86, 0xc4); /* ntohs() : xchg   %al,%ah */
-				break;
-			case BPF_S_ANC_IFINDEX:
-				if (is_imm8(offsetof(struct sk_buff, dev))) {
-					/* movq off8(%rdi),%rax */
-					EMIT4(0x48, 0x8b, 0x47, offsetof(struct sk_buff, dev));
-				} else {
-					EMIT3(0x48, 0x8b, 0x87); /* movq off32(%rdi),%rax */
-					EMIT(offsetof(struct sk_buff, dev), 4);
-				}
-				EMIT3(0x48, 0x85, 0xc0);	/* test %rax,%rax */
-				EMIT_COND_JMP(X86_JE, cleanup_addr - (addrs[i] - 6));
-				BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4);
-				EMIT2(0x8b, 0x80);	/* mov off32(%rax),%eax */
-				EMIT(offsetof(struct net_device, ifindex), 4);
-				break;
-			case BPF_S_ANC_MARK:
-				BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
-				if (is_imm8(offsetof(struct sk_buff, mark))) {
-					/* mov off8(%rdi),%eax */
-					EMIT3(0x8b, 0x47, offsetof(struct sk_buff, mark));
-				} else {
-					EMIT2(0x8b, 0x87);
-					EMIT(offsetof(struct sk_buff, mark), 4);
-				}
-				break;
-			case BPF_S_ANC_RXHASH:
-				BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
-				if (is_imm8(offsetof(struct sk_buff, hash))) {
-					/* mov off8(%rdi),%eax */
-					EMIT3(0x8b, 0x47, offsetof(struct sk_buff, hash));
-				} else {
-					EMIT2(0x8b, 0x87);
-					EMIT(offsetof(struct sk_buff, hash), 4);
-				}
-				break;
-			case BPF_S_ANC_QUEUE:
-				BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2);
-				if (is_imm8(offsetof(struct sk_buff, queue_mapping))) {
-					/* movzwl off8(%rdi),%eax */
-					EMIT4(0x0f, 0xb7, 0x47, offsetof(struct sk_buff, queue_mapping));
-				} else {
-					EMIT3(0x0f, 0xb7, 0x87); /* movzwl off32(%rdi),%eax */
-					EMIT(offsetof(struct sk_buff, queue_mapping), 4);
-				}
-				break;
-			case BPF_S_ANC_CPU:
-#ifdef CONFIG_SMP
-				EMIT4(0x65, 0x8b, 0x04, 0x25); /* mov %gs:off32,%eax */
-				EMIT((u32)(unsigned long)&cpu_number, 4); /* A = smp_processor_id(); */
-#else
-				CLEAR_A();
-#endif
+					EMIT1(0x0F);
+				EMIT1(add_1reg(0xC8, dst_reg));
 				break;
-			case BPF_S_ANC_VLAN_TAG:
-			case BPF_S_ANC_VLAN_TAG_PRESENT:
-				BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
-				if (is_imm8(offsetof(struct sk_buff, vlan_tci))) {
-					/* movzwl off8(%rdi),%eax */
-					EMIT4(0x0f, 0xb7, 0x47, offsetof(struct sk_buff, vlan_tci));
-				} else {
-					EMIT3(0x0f, 0xb7, 0x87); /* movzwl off32(%rdi),%eax */
-					EMIT(offsetof(struct sk_buff, vlan_tci), 4);
-				}
-				BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
-				if (filter[i].code == BPF_S_ANC_VLAN_TAG) {
-					EMIT3(0x80, 0xe4, 0xef); /* and    $0xef,%ah */
-				} else {
-					EMIT3(0xc1, 0xe8, 0x0c); /* shr    $0xc,%eax */
-					EMIT3(0x83, 0xe0, 0x01); /* and    $0x1,%eax */
-				}
-				break;
-			case BPF_S_ANC_PKTTYPE:
-			{
-				int off = pkt_type_offset();
-
-				if (off < 0)
-					goto out;
-				if (is_imm8(off)) {
-					/* movzbl off8(%rdi),%eax */
-					EMIT4(0x0f, 0xb6, 0x47, off);
-				} else {
-					/* movbl off32(%rdi),%eax */
-					EMIT3(0x0f, 0xb6, 0x87);
-					EMIT(off, 4);
-				}
-				EMIT3(0x83, 0xe0, PKT_TYPE_MAX); /* and    $0x7,%eax */
+			case 64:
+				/* emit 'bswap rax' to swap 8 bytes */
+				EMIT3(add_1mod(0x48, dst_reg), 0x0F,
+				      add_1reg(0xC8, dst_reg));
 				break;
 			}
-			case BPF_S_LD_W_ABS:
-				func = CHOOSE_LOAD_FUNC(K, sk_load_word);
-common_load:			seen |= SEEN_DATAREF;
-				t_offset = func - (image + addrs[i]);
-				EMIT1_off32(0xbe, K); /* mov imm32,%esi */
-				EMIT1_off32(0xe8, t_offset); /* call */
-				break;
-			case BPF_S_LD_H_ABS:
-				func = CHOOSE_LOAD_FUNC(K, sk_load_half);
-				goto common_load;
-			case BPF_S_LD_B_ABS:
-				func = CHOOSE_LOAD_FUNC(K, sk_load_byte);
-				goto common_load;
-			case BPF_S_LDX_B_MSH:
-				func = CHOOSE_LOAD_FUNC(K, sk_load_byte_msh);
-				seen |= SEEN_DATAREF | SEEN_XREG;
-				t_offset = func - (image + addrs[i]);
-				EMIT1_off32(0xbe, K);	/* mov imm32,%esi */
-				EMIT1_off32(0xe8, t_offset); /* call sk_load_byte_msh */
-				break;
-			case BPF_S_LD_W_IND:
-				func = sk_load_word;
-common_load_ind:		seen |= SEEN_DATAREF | SEEN_XREG;
-				t_offset = func - (image + addrs[i]);
-				if (K) {
-					if (is_imm8(K)) {
-						EMIT3(0x8d, 0x73, K); /* lea imm8(%rbx), %esi */
-					} else {
-						EMIT2(0x8d, 0xb3); /* lea imm32(%rbx),%esi */
-						EMIT(K, 4);
-					}
-				} else {
-					EMIT2(0x89,0xde); /* mov %ebx,%esi */
-				}
-				EMIT1_off32(0xe8, t_offset);	/* call sk_load_xxx_ind */
-				break;
-			case BPF_S_LD_H_IND:
-				func = sk_load_half;
-				goto common_load_ind;
-			case BPF_S_LD_B_IND:
-				func = sk_load_byte;
-				goto common_load_ind;
-			case BPF_S_JMP_JA:
-				t_offset = addrs[i + K] - addrs[i];
-				EMIT_JMP(t_offset);
-				break;
-			COND_SEL(BPF_S_JMP_JGT_K, X86_JA, X86_JBE);
-			COND_SEL(BPF_S_JMP_JGE_K, X86_JAE, X86_JB);
-			COND_SEL(BPF_S_JMP_JEQ_K, X86_JE, X86_JNE);
-			COND_SEL(BPF_S_JMP_JSET_K,X86_JNE, X86_JE);
-			COND_SEL(BPF_S_JMP_JGT_X, X86_JA, X86_JBE);
-			COND_SEL(BPF_S_JMP_JGE_X, X86_JAE, X86_JB);
-			COND_SEL(BPF_S_JMP_JEQ_X, X86_JE, X86_JNE);
-			COND_SEL(BPF_S_JMP_JSET_X,X86_JNE, X86_JE);
-
-cond_branch:			f_offset = addrs[i + filter[i].jf] - addrs[i];
-				t_offset = addrs[i + filter[i].jt] - addrs[i];
-
-				/* same targets, can avoid doing the test :) */
-				if (filter[i].jt == filter[i].jf) {
-					EMIT_JMP(t_offset);
-					break;
-				}
+			break;
+
+		case BPF_ALU | BPF_END | BPF_FROM_LE:
+			break;
+
+			/* ST: *(u8*)(dst_reg + off) = imm */
+		case BPF_ST | BPF_MEM | BPF_B:
+			if (is_ereg(dst_reg))
+				EMIT2(0x41, 0xC6);
+			else
+				EMIT1(0xC6);
+			goto st;
+		case BPF_ST | BPF_MEM | BPF_H:
+			if (is_ereg(dst_reg))
+				EMIT3(0x66, 0x41, 0xC7);
+			else
+				EMIT2(0x66, 0xC7);
+			goto st;
+		case BPF_ST | BPF_MEM | BPF_W:
+			if (is_ereg(dst_reg))
+				EMIT2(0x41, 0xC7);
+			else
+				EMIT1(0xC7);
+			goto st;
+		case BPF_ST | BPF_MEM | BPF_DW:
+			EMIT2(add_1mod(0x48, dst_reg), 0xC7);
+
+st:			if (is_imm8(insn->off))
+				EMIT2(add_1reg(0x40, dst_reg), insn->off);
+			else
+				EMIT1_off32(add_1reg(0x80, dst_reg), insn->off);
+
+			EMIT(imm32, bpf_size_to_x86_bytes(BPF_SIZE(insn->code)));
+			break;
+
+			/* STX: *(u8*)(dst_reg + off) = src_reg */
+		case BPF_STX | BPF_MEM | BPF_B:
+			/* emit 'mov byte ptr [rax + off], al' */
+			if (is_ereg(dst_reg) || is_ereg(src_reg) ||
+			    /* have to add extra byte for x86 SIL, DIL regs */
+			    src_reg == BPF_REG_1 || src_reg == BPF_REG_2)
+				EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88);
+			else
+				EMIT1(0x88);
+			goto stx;
+		case BPF_STX | BPF_MEM | BPF_H:
+			if (is_ereg(dst_reg) || is_ereg(src_reg))
+				EMIT3(0x66, add_2mod(0x40, dst_reg, src_reg), 0x89);
+			else
+				EMIT2(0x66, 0x89);
+			goto stx;
+		case BPF_STX | BPF_MEM | BPF_W:
+			if (is_ereg(dst_reg) || is_ereg(src_reg))
+				EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x89);
+			else
+				EMIT1(0x89);
+			goto stx;
+		case BPF_STX | BPF_MEM | BPF_DW:
+			EMIT2(add_2mod(0x48, dst_reg, src_reg), 0x89);
+stx:			if (is_imm8(insn->off))
+				EMIT2(add_2reg(0x40, dst_reg, src_reg), insn->off);
+			else
+				EMIT1_off32(add_2reg(0x80, dst_reg, src_reg),
+					    insn->off);
+			break;
+
+			/* LDX: dst_reg = *(u8*)(src_reg + off) */
+		case BPF_LDX | BPF_MEM | BPF_B:
+			/* emit 'movzx rax, byte ptr [rax + off]' */
+			EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB6);
+			goto ldx;
+		case BPF_LDX | BPF_MEM | BPF_H:
+			/* emit 'movzx rax, word ptr [rax + off]' */
+			EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB7);
+			goto ldx;
+		case BPF_LDX | BPF_MEM | BPF_W:
+			/* emit 'mov eax, dword ptr [rax+0x14]' */
+			if (is_ereg(dst_reg) || is_ereg(src_reg))
+				EMIT2(add_2mod(0x40, src_reg, dst_reg), 0x8B);
+			else
+				EMIT1(0x8B);
+			goto ldx;
+		case BPF_LDX | BPF_MEM | BPF_DW:
+			/* emit 'mov rax, qword ptr [rax+0x14]' */
+			EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x8B);
+ldx:			/* if insn->off == 0 we can save one extra byte, but
+			 * special case of x86 r13 which always needs an offset
+			 * is not worth the hassle
+			 */
+			if (is_imm8(insn->off))
+				EMIT2(add_2reg(0x40, src_reg, dst_reg), insn->off);
+			else
+				EMIT1_off32(add_2reg(0x80, src_reg, dst_reg),
+					    insn->off);
+			break;
+
+			/* STX XADD: lock *(u32*)(dst_reg + off) += src_reg */
+		case BPF_STX | BPF_XADD | BPF_W:
+			/* emit 'lock add dword ptr [rax + off], eax' */
+			if (is_ereg(dst_reg) || is_ereg(src_reg))
+				EMIT3(0xF0, add_2mod(0x40, dst_reg, src_reg), 0x01);
+			else
+				EMIT2(0xF0, 0x01);
+			goto xadd;
+		case BPF_STX | BPF_XADD | BPF_DW:
+			EMIT3(0xF0, add_2mod(0x48, dst_reg, src_reg), 0x01);
+xadd:			if (is_imm8(insn->off))
+				EMIT2(add_2reg(0x40, dst_reg, src_reg), insn->off);
+			else
+				EMIT1_off32(add_2reg(0x80, dst_reg, src_reg),
+					    insn->off);
+			break;
+
+			/* call */
+		case BPF_JMP | BPF_CALL:
+			func = (u8 *) __bpf_call_base + imm32;
+			jmp_offset = func - (image + addrs[i]);
+			if (ctx->seen_ld_abs) {
+				EMIT2(0x41, 0x52); /* push %r10 */
+				EMIT2(0x41, 0x51); /* push %r9 */
+				/* need to adjust jmp offset, since
+				 * pop %r9, pop %r10 take 4 bytes after call insn
+				 */
+				jmp_offset += 4;
+			}
+			if (!imm32 || !is_simm32(jmp_offset)) {
+				pr_err("unsupported bpf func %d addr %p image %p\n",
+				       imm32, func, image);
+				return -EINVAL;
+			}
+			EMIT1_off32(0xE8, jmp_offset);
+			if (ctx->seen_ld_abs) {
+				EMIT2(0x41, 0x59); /* pop %r9 */
+				EMIT2(0x41, 0x5A); /* pop %r10 */
+			}
+			break;
+
+			/* cond jump */
+		case BPF_JMP | BPF_JEQ | BPF_X:
+		case BPF_JMP | BPF_JNE | BPF_X:
+		case BPF_JMP | BPF_JGT | BPF_X:
+		case BPF_JMP | BPF_JGE | BPF_X:
+		case BPF_JMP | BPF_JSGT | BPF_X:
+		case BPF_JMP | BPF_JSGE | BPF_X:
+			/* cmp dst_reg, src_reg */
+			EMIT3(add_2mod(0x48, dst_reg, src_reg), 0x39,
+			      add_2reg(0xC0, dst_reg, src_reg));
+			goto emit_cond_jmp;
+
+		case BPF_JMP | BPF_JSET | BPF_X:
+			/* test dst_reg, src_reg */
+			EMIT3(add_2mod(0x48, dst_reg, src_reg), 0x85,
+			      add_2reg(0xC0, dst_reg, src_reg));
+			goto emit_cond_jmp;
+
+		case BPF_JMP | BPF_JSET | BPF_K:
+			/* test dst_reg, imm32 */
+			EMIT1(add_1mod(0x48, dst_reg));
+			EMIT2_off32(0xF7, add_1reg(0xC0, dst_reg), imm32);
+			goto emit_cond_jmp;
+
+		case BPF_JMP | BPF_JEQ | BPF_K:
+		case BPF_JMP | BPF_JNE | BPF_K:
+		case BPF_JMP | BPF_JGT | BPF_K:
+		case BPF_JMP | BPF_JGE | BPF_K:
+		case BPF_JMP | BPF_JSGT | BPF_K:
+		case BPF_JMP | BPF_JSGE | BPF_K:
+			/* cmp dst_reg, imm8/32 */
+			EMIT1(add_1mod(0x48, dst_reg));
+
+			if (is_imm8(imm32))
+				EMIT3(0x83, add_1reg(0xF8, dst_reg), imm32);
+			else
+				EMIT2_off32(0x81, add_1reg(0xF8, dst_reg), imm32);
+
+emit_cond_jmp:		/* convert BPF opcode to x86 */
+			switch (BPF_OP(insn->code)) {
+			case BPF_JEQ:
+				jmp_cond = X86_JE;
+				break;
+			case BPF_JSET:
+			case BPF_JNE:
+				jmp_cond = X86_JNE;
+				break;
+			case BPF_JGT:
+				/* GT is unsigned '>', JA in x86 */
+				jmp_cond = X86_JA;
+				break;
+			case BPF_JGE:
+				/* GE is unsigned '>=', JAE in x86 */
+				jmp_cond = X86_JAE;
+				break;
+			case BPF_JSGT:
+				/* signed '>', GT in x86 */
+				jmp_cond = X86_JG;
+				break;
+			case BPF_JSGE:
+				/* signed '>=', GE in x86 */
+				jmp_cond = X86_JGE;
+				break;
+			default: /* to silence gcc warning */
+				return -EFAULT;
+			}
+			jmp_offset = addrs[i + insn->off] - addrs[i];
+			if (is_imm8(jmp_offset)) {
+				EMIT2(jmp_cond, jmp_offset);
+			} else if (is_simm32(jmp_offset)) {
+				EMIT2_off32(0x0F, jmp_cond + 0x10, jmp_offset);
+			} else {
+				pr_err("cond_jmp gen bug %llx\n", jmp_offset);
+				return -EFAULT;
+			}
+
+			break;
 
-				switch (filter[i].code) {
-				case BPF_S_JMP_JGT_X:
-				case BPF_S_JMP_JGE_X:
-				case BPF_S_JMP_JEQ_X:
-					seen |= SEEN_XREG;
-					EMIT2(0x39, 0xd8); /* cmp %ebx,%eax */
-					break;
-				case BPF_S_JMP_JSET_X:
-					seen |= SEEN_XREG;
-					EMIT2(0x85, 0xd8); /* test %ebx,%eax */
-					break;
-				case BPF_S_JMP_JEQ_K:
-					if (K == 0) {
-						EMIT2(0x85, 0xc0); /* test   %eax,%eax */
-						break;
-					}
-				case BPF_S_JMP_JGT_K:
-				case BPF_S_JMP_JGE_K:
-					if (K <= 127)
-						EMIT3(0x83, 0xf8, K); /* cmp imm8,%eax */
+		case BPF_JMP | BPF_JA:
+			jmp_offset = addrs[i + insn->off] - addrs[i];
+			if (!jmp_offset)
+				/* optimize out nop jumps */
+				break;
+emit_jmp:
+			if (is_imm8(jmp_offset)) {
+				EMIT2(0xEB, jmp_offset);
+			} else if (is_simm32(jmp_offset)) {
+				EMIT1_off32(0xE9, jmp_offset);
+			} else {
+				pr_err("jmp gen bug %llx\n", jmp_offset);
+				return -EFAULT;
+			}
+			break;
+
+		case BPF_LD | BPF_IND | BPF_W:
+			func = sk_load_word;
+			goto common_load;
+		case BPF_LD | BPF_ABS | BPF_W:
+			func = CHOOSE_LOAD_FUNC(imm32, sk_load_word);
+common_load:		ctx->seen_ld_abs = true;
+			jmp_offset = func - (image + addrs[i]);
+			if (!func || !is_simm32(jmp_offset)) {
+				pr_err("unsupported bpf func %d addr %p image %p\n",
+				       imm32, func, image);
+				return -EINVAL;
+			}
+			if (BPF_MODE(insn->code) == BPF_ABS) {
+				/* mov %esi, imm32 */
+				EMIT1_off32(0xBE, imm32);
+			} else {
+				/* mov %rsi, src_reg */
+				EMIT_mov(BPF_REG_2, src_reg);
+				if (imm32) {
+					if (is_imm8(imm32))
+						/* add %esi, imm8 */
+						EMIT3(0x83, 0xC6, imm32);
 					else
-						EMIT1_off32(0x3d, K); /* cmp imm32,%eax */
-					break;
-				case BPF_S_JMP_JSET_K:
-					if (K <= 0xFF)
-						EMIT2(0xa8, K); /* test imm8,%al */
-					else if (!(K & 0xFFFF00FF))
-						EMIT3(0xf6, 0xc4, K >> 8); /* test imm8,%ah */
-					else if (K <= 0xFFFF) {
-						EMIT2(0x66, 0xa9); /* test imm16,%ax */
-						EMIT(K, 2);
-					} else {
-						EMIT1_off32(0xa9, K); /* test imm32,%eax */
-					}
-					break;
+						/* add %esi, imm32 */
+						EMIT2_off32(0x81, 0xC6, imm32);
 				}
-				if (filter[i].jt != 0) {
-					if (filter[i].jf && f_offset)
-						t_offset += is_near(f_offset) ? 2 : 5;
-					EMIT_COND_JMP(t_op, t_offset);
-					if (filter[i].jf)
-						EMIT_JMP(f_offset);
-					break;
-				}
-				EMIT_COND_JMP(f_op, f_offset);
-				break;
-			default:
-				/* hmm, too complex filter, give up with jit compiler */
-				goto out;
 			}
-			ilen = prog - temp;
-			if (image) {
-				if (unlikely(proglen + ilen > oldproglen)) {
-					pr_err("bpb_jit_compile fatal error\n");
-					kfree(addrs);
-					module_free(NULL, header);
-					return;
-				}
-				memcpy(image + proglen, temp, ilen);
+			/* skb pointer is in R6 (%rbx), it will be copied into
+			 * %rdi if skb_copy_bits() call is necessary.
+			 * sk_load_* helpers also use %r10 and %r9d.
+			 * See bpf_jit.S
+			 */
+			EMIT1_off32(0xE8, jmp_offset); /* call */
+			break;
+
+		case BPF_LD | BPF_IND | BPF_H:
+			func = sk_load_half;
+			goto common_load;
+		case BPF_LD | BPF_ABS | BPF_H:
+			func = CHOOSE_LOAD_FUNC(imm32, sk_load_half);
+			goto common_load;
+		case BPF_LD | BPF_IND | BPF_B:
+			func = sk_load_byte;
+			goto common_load;
+		case BPF_LD | BPF_ABS | BPF_B:
+			func = CHOOSE_LOAD_FUNC(imm32, sk_load_byte);
+			goto common_load;
+
+		case BPF_JMP | BPF_EXIT:
+			if (i != insn_cnt - 1) {
+				jmp_offset = ctx->cleanup_addr - addrs[i];
+				goto emit_jmp;
 			}
-			proglen += ilen;
-			addrs[i] = proglen;
-			prog = temp;
+			/* update cleanup_addr */
+			ctx->cleanup_addr = proglen;
+			/* mov rbx, qword ptr [rbp-X] */
+			EMIT3_off32(0x48, 0x8B, 0x9D, -stacksize);
+			/* mov r13, qword ptr [rbp-X] */
+			EMIT3_off32(0x4C, 0x8B, 0xAD, -stacksize + 8);
+			/* mov r14, qword ptr [rbp-X] */
+			EMIT3_off32(0x4C, 0x8B, 0xB5, -stacksize + 16);
+			/* mov r15, qword ptr [rbp-X] */
+			EMIT3_off32(0x4C, 0x8B, 0xBD, -stacksize + 24);
+
+			EMIT1(0xC9); /* leave */
+			EMIT1(0xC3); /* ret */
+			break;
+
+		default:
+			/* By design x64 JIT should support all BPF instructions
+			 * This error will be seen if new instruction was added
+			 * to interpreter, but not to JIT
+			 * or if there is junk in sk_filter
+			 */
+			pr_err("bpf_jit: unknown opcode %02x\n", insn->code);
+			return -EINVAL;
 		}
-		/* last bpf instruction is always a RET :
-		 * use it to give the cleanup instruction(s) addr
-		 */
-		cleanup_addr = proglen - 1; /* ret */
-		if (seen_or_pass0)
-			cleanup_addr -= 1; /* leaveq */
-		if (seen_or_pass0 & SEEN_XREG)
-			cleanup_addr -= 4; /* mov  -8(%rbp),%rbx */
 
+		ilen = prog - temp;
+		if (image) {
+			if (unlikely(proglen + ilen > oldproglen)) {
+				pr_err("bpf_jit_compile fatal error\n");
+				return -EFAULT;
+			}
+			memcpy(image + proglen, temp, ilen);
+		}
+		proglen += ilen;
+		addrs[i] = proglen;
+		prog = temp;
+	}
+	return proglen;
+}
+
+void bpf_jit_compile(struct sk_filter *prog)
+{
+}
+
+void bpf_int_jit_compile(struct sk_filter *prog)
+{
+	struct bpf_binary_header *header = NULL;
+	int proglen, oldproglen = 0;
+	struct jit_context ctx = {};
+	u8 *image = NULL;
+	int *addrs;
+	int pass;
+	int i;
+
+	if (!bpf_jit_enable)
+		return;
+
+	if (!prog || !prog->len)
+		return;
+
+	addrs = kmalloc(prog->len * sizeof(*addrs), GFP_KERNEL);
+	if (!addrs)
+		return;
+
+	/* Before first pass, make a rough estimation of addrs[]
+	 * each bpf instruction is translated to less than 64 bytes
+	 */
+	for (proglen = 0, i = 0; i < prog->len; i++) {
+		proglen += 64;
+		addrs[i] = proglen;
+	}
+	ctx.cleanup_addr = proglen;
+
+	for (pass = 0; pass < 10; pass++) {
+		proglen = do_jit(prog, addrs, image, oldproglen, &ctx);
+		if (proglen <= 0) {
+			image = NULL;
+			if (header)
+				module_free(NULL, header);
+			goto out;
+		}
 		if (image) {
 			if (proglen != oldproglen)
-				pr_err("bpb_jit_compile proglen=%u != oldproglen=%u\n", proglen, oldproglen);
+				pr_err("bpf_jit: proglen=%d != oldproglen=%d\n",
+				       proglen, oldproglen);
 			break;
 		}
 		if (proglen == oldproglen) {
@@ -766,17 +918,16 @@ cond_branch:			f_offset = addrs[i + filter[i].jf] - addrs[i];
 	}
 
 	if (bpf_jit_enable > 1)
-		bpf_jit_dump(flen, proglen, pass, image);
+		bpf_jit_dump(prog->len, proglen, 0, image);
 
 	if (image) {
 		bpf_flush_icache(header, image + proglen);
 		set_memory_ro((unsigned long)header, header->pages);
-		fp->bpf_func = (void *)image;
-		fp->jited = 1;
+		prog->bpf_func = (void *)image;
+		prog->jited = 1;
 	}
 out:
 	kfree(addrs);
-	return;
 }
 
 static void bpf_jit_free_deferred(struct work_struct *work)
author	Linus Torvalds <torvalds@linux-foundation.org>	2014-06-12 21:27:40 (GMT)
committer	Linus Torvalds <torvalds@linux-foundation.org>	2014-06-12 21:27:40 (GMT)
commit	f9da455b93f6ba076935b4ef4589f61e529ae046 (patch)
tree	3c4e69ce1ba1d6bf65915b97a76ca2172105b278 /arch
parent	0e04c641b199435f3779454055f6a7de258ecdfc (diff)
parent	e5eca6d41f53db48edd8cf88a3f59d2c30227f8e (diff)
download	linux-f9da455b93f6ba076935b4ef4589f61e529ae046.tar.xz