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

Pull networking updates from David Miller:
 "Another merge window, another set of networking changes.  I've heard
  rumblings that the lightweight tunnels infrastructure has been voted
  networking change of the year.  But what do I know?

   1) Add conntrack support to openvswitch, from Joe Stringer.

   2) Initial support for VRF (Virtual Routing and Forwarding), which
      allows the segmentation of routing paths without using multiple
      devices.  There are some semantic kinks to work out still, but
      this is a reasonably strong foundation.  From David Ahern.

   3) Remove spinlock fro act_bpf fast path, from Alexei Starovoitov.

   4) Ignore route nexthops with a link down state in ipv6, just like
      ipv4.  From Andy Gospodarek.

   5) Remove spinlock from fast path of act_gact and act_mirred, from
      Eric Dumazet.

   6) Document the DSA layer, from Florian Fainelli.

   7) Add netconsole support to bcmgenet, systemport, and DSA.  Also
      from Florian Fainelli.

   8) Add Mellanox Switch Driver and core infrastructure, from Jiri
      Pirko.

   9) Add support for "light weight tunnels", which allow for
      encapsulation and decapsulation without bearing the overhead of a
      full blown netdevice.  From Thomas Graf, Jiri Benc, and a cast of
      others.

  10) Add Identifier Locator Addressing support for ipv6, from Tom
      Herbert.

  11) Support fragmented SKBs in iwlwifi, from Johannes Berg.

  12) Allow perf PMUs to be accessed from eBPF programs, from Kaixu Xia.

  13) Add BQL support to 3c59x driver, from Loganaden Velvindron.

  14) Stop using a zero TX queue length to mean that a device shouldn't
      have a qdisc attached, use an explicit flag instead.  From Phil
      Sutter.

  15) Use generic geneve netdevice infrastructure in openvswitch, from
      Pravin B Shelar.

  16) Add infrastructure to avoid re-forwarding a packet in software
      that was already forwarded by a hardware switch.  From Scott
      Feldman.

  17) Allow AF_PACKET fanout function to be implemented in a bpf
      program, from Willem de Bruijn"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1458 commits)
  netfilter: nf_conntrack: make nf_ct_zone_dflt built-in
  netfilter: nf_dup{4, 6}: fix build error when nf_conntrack disabled
  net: fec: clear receive interrupts before processing a packet
  ipv6: fix exthdrs offload registration in out_rt path
  xen-netback: add support for multicast control
  bgmac: Update fixed_phy_register()
  sock, diag: fix panic in sock_diag_put_filterinfo
  flow_dissector: Use 'const' where possible.
  flow_dissector: Fix function argument ordering dependency
  ixgbe: Resolve "initialized field overwritten" warnings
  ixgbe: Remove bimodal SR-IOV disabling
  ixgbe: Add support for reporting 2.5G link speed
  ixgbe: fix bounds checking in ixgbe_setup_tc for 82598
  ixgbe: support for ethtool set_rxfh
  ixgbe: Avoid needless PHY access on copper phys
  ixgbe: cleanup to use cached mask value
  ixgbe: Remove second instance of lan_id variable
  ixgbe: use kzalloc for allocating one thing
  flow: Move __get_hash_from_flowi{4,6} into flow_dissector.c
  ixgbe: Remove unused PCI bus types
  ...

11 files changed, 151 insertions, 94 deletions

diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 9117c1a1a4e2..d23e2524d694 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -717,7 +717,7 @@
 		};
 
 		mac: ethernet@4a100000 {
-			compatible = "ti,cpsw";
+			compatible = "ti,am335x-cpsw","ti,cpsw";
 			ti,hwmods = "cpgmac0";
 			clocks = <&cpsw_125mhz_gclk>, <&cpsw_cpts_rft_clk>;
 			clock-names = "fck", "cpts";
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index a0d3d4bfe9cb..5d65db9ebc2b 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -1418,7 +1418,7 @@
 		};
 
 		mac: ethernet@4a100000 {
-			compatible = "ti,cpsw";
+			compatible = "ti,dra7-cpsw","ti,cpsw";
 			ti,hwmods = "gmac";
 			clocks = <&dpll_gmac_ck>, <&gmac_gmii_ref_clk_div>;
 			clock-names = "fck", "cpts";
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index c011e2296cb1..876060bcceeb 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -857,7 +857,9 @@ b_epilogue:
 			emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
 			break;
 		case BPF_ANC | SKF_AD_IFINDEX:
+		case BPF_ANC | SKF_AD_HATYPE:
 			/* A = skb->dev->ifindex */
+			/* A = skb->dev->type */
 			ctx->seen |= SEEN_SKB;
 			off = offsetof(struct sk_buff, dev);
 			emit(ARM_LDR_I(r_scratch, r_skb, off), ctx);
@@ -867,8 +869,24 @@ b_epilogue:
 
 			BUILD_BUG_ON(FIELD_SIZEOF(struct net_device,
 						  ifindex) != 4);
-			off = offsetof(struct net_device, ifindex);
-			emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
+			BUILD_BUG_ON(FIELD_SIZEOF(struct net_device,
+						  type) != 2);
+
+			if (code == (BPF_ANC | SKF_AD_IFINDEX)) {
+				off = offsetof(struct net_device, ifindex);
+				emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
+			} else {
+				/*
+				 * offset of field "type" in "struct
+				 * net_device" is above what can be
+				 * used in the ldrh rd, [rn, #imm]
+				 * instruction, so load the offset in
+				 * a register and use ldrh rd, [rn, rm]
+				 */
+				off = offsetof(struct net_device, type);
+				emit_mov_i(ARM_R3, off, ctx);
+				emit(ARM_LDRH_R(r_A, r_scratch, ARM_R3), ctx);
+			}
 			break;
 		case BPF_ANC | SKF_AD_MARK:
 			ctx->seen |= SEEN_SKB;
@@ -895,6 +913,17 @@ b_epilogue:
 				OP_IMM3(ARM_AND, r_A, r_A, 0x1, ctx);
 			}
 			break;
+		case BPF_ANC | SKF_AD_PKTTYPE:
+			ctx->seen |= SEEN_SKB;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
+						  __pkt_type_offset[0]) != 1);
+			off = PKT_TYPE_OFFSET();
+			emit(ARM_LDRB_I(r_A, r_skb, off), ctx);
+			emit(ARM_AND_I(r_A, r_A, PKT_TYPE_MAX), ctx);
+#ifdef __BIG_ENDIAN_BITFIELD
+			emit(ARM_LSR_I(r_A, r_A, 5), ctx);
+#endif
+			break;
 		case BPF_ANC | SKF_AD_QUEUE:
 			ctx->seen |= SEEN_SKB;
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
@@ -904,6 +933,14 @@ b_epilogue:
 			off = offsetof(struct sk_buff, queue_mapping);
 			emit(ARM_LDRH_I(r_A, r_skb, off), ctx);
 			break;
+		case BPF_ANC | SKF_AD_PAY_OFFSET:
+			ctx->seen |= SEEN_SKB | SEEN_CALL;
+
+			emit(ARM_MOV_R(ARM_R0, r_skb), ctx);
+			emit_mov_i(ARM_R3, (unsigned int)skb_get_poff, ctx);
+			emit_blx_r(ARM_R3, ctx);
+			emit(ARM_MOV_R(r_A, ARM_R0), ctx);
+			break;
 		case BPF_LDX | BPF_W | BPF_ABS:
 			/*
 			 * load a 32bit word from struct seccomp_data.
diff --git a/arch/arm/net/bpf_jit_32.h b/arch/arm/net/bpf_jit_32.h
index b2d7d92859d3..4b17d5ab652a 100644
--- a/arch/arm/net/bpf_jit_32.h
+++ b/arch/arm/net/bpf_jit_32.h
@@ -74,6 +74,7 @@
 #define ARM_INST_LDRB_I		0x05d00000
 #define ARM_INST_LDRB_R		0x07d00000
 #define ARM_INST_LDRH_I		0x01d000b0
+#define ARM_INST_LDRH_R		0x019000b0
 #define ARM_INST_LDR_I		0x05900000
 
 #define ARM_INST_LDM		0x08900000
@@ -160,6 +161,8 @@
 				 | (rm))
 #define ARM_LDRH_I(rt, rn, off)	(ARM_INST_LDRH_I | (rt) << 12 | (rn) << 16 \
 				 | (((off) & 0xf0) << 4) | ((off) & 0xf))
+#define ARM_LDRH_R(rt, rn, rm)	(ARM_INST_LDRH_R | (rt) << 12 | (rn) << 16 \
+				 | (rm))
 
 #define ARM_LDM(rn, regs)	(ARM_INST_LDM | (rn) << 16 | (regs))
 
diff --git a/arch/m68k/coldfire/m5272.c b/arch/m68k/coldfire/m5272.c
index b15219ed22bf..c525e4c08f84 100644
--- a/arch/m68k/coldfire/m5272.c
+++ b/arch/m68k/coldfire/m5272.c
@@ -126,7 +126,7 @@ static struct fixed_phy_status nettel_fixed_phy_status __initdata = {
 static int __init init_BSP(void)
 {
 	m5272_uarts_init();
-	fixed_phy_add(PHY_POLL, 0, &nettel_fixed_phy_status);
+	fixed_phy_add(PHY_POLL, 0, &nettel_fixed_phy_status, -1);
 	return 0;
 }
 
diff --git a/arch/mips/ar7/platform.c b/arch/mips/ar7/platform.c
index be9ff1673ded..298b97715d5f 100644
--- a/arch/mips/ar7/platform.c
+++ b/arch/mips/ar7/platform.c
@@ -679,7 +679,8 @@ static int __init ar7_register_devices(void)
 	}
 
 	if (ar7_has_high_cpmac()) {
-		res = fixed_phy_add(PHY_POLL, cpmac_high.id, &fixed_phy_status);
+		res = fixed_phy_add(PHY_POLL, cpmac_high.id,
+				    &fixed_phy_status, -1);
 		if (!res) {
 			cpmac_get_mac(1, cpmac_high_data.dev_addr);
 
@@ -692,7 +693,7 @@ static int __init ar7_register_devices(void)
 	} else
 		cpmac_low_data.phy_mask = 0xffffffff;
 
-	res = fixed_phy_add(PHY_POLL, cpmac_low.id, &fixed_phy_status);
+	res = fixed_phy_add(PHY_POLL, cpmac_low.id, &fixed_phy_status, -1);
 	if (!res) {
 		cpmac_get_mac(0, cpmac_low_data.dev_addr);
 		res = platform_device_register(&cpmac_low);
diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c
index 98c075f81795..17503a05938e 100644
--- a/arch/mips/bcm47xx/setup.c
+++ b/arch/mips/bcm47xx/setup.c
@@ -263,7 +263,7 @@ static int __init bcm47xx_register_bus_complete(void)
 	bcm47xx_leds_register();
 	bcm47xx_workarounds();
 
-	fixed_phy_add(PHY_POLL, 0, &bcm47xx_fixed_phy_status);
+	fixed_phy_add(PHY_POLL, 0, &bcm47xx_fixed_phy_status, -1);
 	return 0;
 }
 device_initcall(bcm47xx_register_bus_complete);
diff --git a/arch/s390/net/bpf_jit.h b/arch/s390/net/bpf_jit.h
index f6498eec9ee1..f010c93a88b1 100644
--- a/arch/s390/net/bpf_jit.h
+++ b/arch/s390/net/bpf_jit.h
@@ -36,6 +36,8 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
  *	      |   BPF stack   |     |
  *	      |		      |     |
  *	      +---------------+     |
+ *	      | 8 byte skbp   |     |
+ * R15+170 -> +---------------+     |
  *	      | 8 byte hlen   |     |
  * R15+168 -> +---------------+     |
  *	      | 4 byte align  |     |
@@ -51,11 +53,12 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
  * We get 160 bytes stack space from calling function, but only use
  * 12 * 8 byte for old backchain, r15..r6, and tail_call_cnt.
  */
-#define STK_SPACE	(MAX_BPF_STACK + 8 + 4 + 4 + 160)
+#define STK_SPACE	(MAX_BPF_STACK + 8 + 8 + 4 + 4 + 160)
 #define STK_160_UNUSED	(160 - 12 * 8)
 #define STK_OFF		(STK_SPACE - STK_160_UNUSED)
 #define STK_OFF_TMP	160	/* Offset of tmp buffer on stack */
 #define STK_OFF_HLEN	168	/* Offset of SKB header length on stack */
+#define STK_OFF_SKBP	170	/* Offset of SKB pointer on stack */
 
 #define STK_OFF_R6	(160 - 11 * 8)	/* Offset of r6 on stack */
 #define STK_OFF_TCCNT	(160 - 12 * 8)	/* Offset of tail_call_cnt on stack */
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 8d2e5165865f..eeda051442c3 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -45,7 +45,7 @@ struct bpf_jit {
 	int labels[1];		/* Labels for local jumps */
 };
 
-#define BPF_SIZE_MAX	4096	/* Max size for program */
+#define BPF_SIZE_MAX	0x7ffff	/* Max size for program (20 bit signed displ) */
 
 #define SEEN_SKB	1	/* skb access */
 #define SEEN_MEM	2	/* use mem[] for temporary storage */
@@ -53,6 +53,7 @@ struct bpf_jit {
 #define SEEN_LITERAL	8	/* code uses literals */
 #define SEEN_FUNC	16	/* calls C functions */
 #define SEEN_TAIL_CALL	32	/* code uses tail calls */
+#define SEEN_SKB_CHANGE	64	/* code changes skb data */
 #define SEEN_STACK	(SEEN_FUNC | SEEN_MEM | SEEN_SKB)
 
 /*
@@ -203,19 +204,11 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 	_EMIT6(op1 | __disp, op2);				\
 })
 
-#define EMIT6_DISP(op1, op2, b1, b2, b3, disp)			\
-({								\
-	_EMIT6_DISP(op1 | reg(b1, b2) << 16 |			\
-		    reg_high(b3) << 8, op2, disp);		\
-	REG_SET_SEEN(b1);					\
-	REG_SET_SEEN(b2);					\
-	REG_SET_SEEN(b3);					\
-})
-
 #define _EMIT6_DISP_LH(op1, op2, disp)				\
 ({								\
-	unsigned int __disp_h = ((u32)disp) & 0xff000;		\
-	unsigned int __disp_l = ((u32)disp) & 0x00fff;		\
+	u32 _disp = (u32) disp;					\
+	unsigned int __disp_h = _disp & 0xff000;		\
+	unsigned int __disp_l = _disp & 0x00fff;		\
 	_EMIT6(op1 | __disp_l, op2 | __disp_h >> 4);		\
 })
 
@@ -390,12 +383,32 @@ static void save_restore_regs(struct bpf_jit *jit, int op)
 }
 
 /*
+ * For SKB access %b1 contains the SKB pointer. For "bpf_jit.S"
+ * we store the SKB header length on the stack and the SKB data
+ * pointer in REG_SKB_DATA.
+ */
+static void emit_load_skb_data_hlen(struct bpf_jit *jit)
+{
+	/* Header length: llgf %w1,<len>(%b1) */
+	EMIT6_DISP_LH(0xe3000000, 0x0016, REG_W1, REG_0, BPF_REG_1,
+		      offsetof(struct sk_buff, len));
+	/* s %w1,<data_len>(%b1) */
+	EMIT4_DISP(0x5b000000, REG_W1, BPF_REG_1,
+		   offsetof(struct sk_buff, data_len));
+	/* stg %w1,ST_OFF_HLEN(%r0,%r15) */
+	EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15, STK_OFF_HLEN);
+	/* lg %skb_data,data_off(%b1) */
+	EMIT6_DISP_LH(0xe3000000, 0x0004, REG_SKB_DATA, REG_0,
+		      BPF_REG_1, offsetof(struct sk_buff, data));
+}
+
+/*
  * Emit function prologue
  *
  * Save registers and create stack frame if necessary.
  * See stack frame layout desription in "bpf_jit.h"!
  */
-static void bpf_jit_prologue(struct bpf_jit *jit)
+static void bpf_jit_prologue(struct bpf_jit *jit, bool is_classic)
 {
 	if (jit->seen & SEEN_TAIL_CALL) {
 		/* xc STK_OFF_TCCNT(4,%r15),STK_OFF_TCCNT(%r15) */
@@ -429,32 +442,21 @@ static void bpf_jit_prologue(struct bpf_jit *jit)
 			EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0,
 				      REG_15, 152);
 	}
-	/*
-	 * For SKB access %b1 contains the SKB pointer. For "bpf_jit.S"
-	 * we store the SKB header length on the stack and the SKB data
-	 * pointer in REG_SKB_DATA.
-	 */
-	if (jit->seen & SEEN_SKB) {
-		/* Header length: llgf %w1,<len>(%b1) */
-		EMIT6_DISP_LH(0xe3000000, 0x0016, REG_W1, REG_0, BPF_REG_1,
-			      offsetof(struct sk_buff, len));
-		/* s %w1,<data_len>(%b1) */
-		EMIT4_DISP(0x5b000000, REG_W1, BPF_REG_1,
-			   offsetof(struct sk_buff, data_len));
-		/* stg %w1,ST_OFF_HLEN(%r0,%r15) */
+	if (jit->seen & SEEN_SKB)
+		emit_load_skb_data_hlen(jit);
+	if (jit->seen & SEEN_SKB_CHANGE)
+		/* stg %b1,ST_OFF_SKBP(%r0,%r15) */
 		EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15,
-			      STK_OFF_HLEN);
-		/* lg %skb_data,data_off(%b1) */
-		EMIT6_DISP_LH(0xe3000000, 0x0004, REG_SKB_DATA, REG_0,
-			      BPF_REG_1, offsetof(struct sk_buff, data));
+			      STK_OFF_SKBP);
+	/* Clear A (%b0) and X (%b7) registers for converted BPF programs */
+	if (is_classic) {
+		if (REG_SEEN(BPF_REG_A))
+			/* lghi %ba,0 */
+			EMIT4_IMM(0xa7090000, BPF_REG_A, 0);
+		if (REG_SEEN(BPF_REG_X))
+			/* lghi %bx,0 */
+			EMIT4_IMM(0xa7090000, BPF_REG_X, 0);
 	}
-	/* BPF compatibility: clear A (%b0) and X (%b7) registers */
-	if (REG_SEEN(BPF_REG_A))
-		/* lghi %ba,0 */
-		EMIT4_IMM(0xa7090000, BPF_REG_A, 0);
-	if (REG_SEEN(BPF_REG_X))
-		/* lghi %bx,0 */
-		EMIT4_IMM(0xa7090000, BPF_REG_X, 0);
 }
 
 /*
@@ -976,12 +978,19 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 		REG_SET_SEEN(BPF_REG_5);
 		jit->seen |= SEEN_FUNC;
 		/* lg %w1,<d(imm)>(%l) */
-		EMIT6_DISP(0xe3000000, 0x0004, REG_W1, REG_0, REG_L,
-			   EMIT_CONST_U64(func));
+		EMIT6_DISP_LH(0xe3000000, 0x0004, REG_W1, REG_0, REG_L,
+			      EMIT_CONST_U64(func));
 		/* basr %r14,%w1 */
 		EMIT2(0x0d00, REG_14, REG_W1);
 		/* lgr %b0,%r2: load return value into %b0 */
 		EMIT4(0xb9040000, BPF_REG_0, REG_2);
+		if (bpf_helper_changes_skb_data((void *)func)) {
+			jit->seen |= SEEN_SKB_CHANGE;
+			/* lg %b1,ST_OFF_SKBP(%r15) */
+			EMIT6_DISP_LH(0xe3000000, 0x0004, BPF_REG_1, REG_0,
+				      REG_15, STK_OFF_SKBP);
+			emit_load_skb_data_hlen(jit);
+		}
 		break;
 	}
 	case BPF_JMP | BPF_CALL | BPF_X:
@@ -1023,7 +1032,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 				      MAX_TAIL_CALL_CNT, 0, 0x2);
 
 		/*
-		 * prog = array->prog[index];
+		 * prog = array->ptrs[index];
 		 * if (prog == NULL)
 		 *         goto out;
 		 */
@@ -1032,7 +1041,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 		EMIT6_DISP_LH(0xeb000000, 0x000d, REG_1, BPF_REG_3, REG_0, 3);
 		/* lg %r1,prog(%b2,%r1) */
 		EMIT6_DISP_LH(0xe3000000, 0x0004, REG_1, BPF_REG_2,
-			      REG_1, offsetof(struct bpf_array, prog));
+			      REG_1, offsetof(struct bpf_array, ptrs));
 		/* clgij %r1,0,0x8,label0 */
 		EMIT6_PCREL_IMM_LABEL(0xec000000, 0x007d, REG_1, 0, 0, 0x8);
 
@@ -1236,7 +1245,7 @@ static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp)
 	jit->lit = jit->lit_start;
 	jit->prg = 0;
 
-	bpf_jit_prologue(jit);
+	bpf_jit_prologue(jit, bpf_prog_was_classic(fp));
 	for (i = 0; i < fp->len; i += insn_count) {
 		insn_count = bpf_jit_insn(jit, fp, i);
 		if (insn_count < 0)
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c
index 7931eeeb649a..f8b9f71b9a2b 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp.c
@@ -807,7 +807,7 @@ cond_branch:			f_offset = addrs[i + filter[i].jf];
 	}
 
 	if (bpf_jit_enable > 1)
-		bpf_jit_dump(flen, proglen, pass, image);
+		bpf_jit_dump(flen, proglen, pass + 1, image);
 
 	if (image) {
 		bpf_flush_icache(image, image + proglen);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index be2e7a2b10d7..70efcd0940f9 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -246,7 +246,7 @@ static void emit_prologue(u8 **pprog)
  *     goto out;
  *   if (++tail_call_cnt > MAX_TAIL_CALL_CNT)
  *     goto out;
- *   prog = array->prog[index];
+ *   prog = array->ptrs[index];
  *   if (prog == NULL)
  *     goto out;
  *   goto *(prog->bpf_func + prologue_size);
@@ -284,9 +284,9 @@ static void emit_bpf_tail_call(u8 **pprog)
 	EMIT3(0x83, 0xC0, 0x01);                  /* add eax, 1 */
 	EMIT2_off32(0x89, 0x85, -STACKSIZE + 36); /* mov dword ptr [rbp - 516], eax */
 
-	/* prog = array->prog[index]; */
+	/* prog = array->ptrs[index]; */
 	EMIT4_off32(0x48, 0x8D, 0x84, 0xD6,       /* lea rax, [rsi + rdx * 8 + offsetof(...)] */
-		    offsetof(struct bpf_array, prog));
+		    offsetof(struct bpf_array, ptrs));
 	EMIT3(0x48, 0x8B, 0x00);                  /* mov rax, qword ptr [rax] */
 
 	/* if (prog == NULL)
@@ -315,6 +315,26 @@ static void emit_bpf_tail_call(u8 **pprog)
 	*pprog = prog;
 }
 
+
+static void emit_load_skb_data_hlen(u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	/* r9d = skb->len - skb->data_len (headlen)
+	 * r10 = skb->data
+	 */
+	/* mov %r9d, off32(%rdi) */
+	EMIT3_off32(0x44, 0x8b, 0x8f, offsetof(struct sk_buff, len));
+
+	/* sub %r9d, off32(%rdi) */
+	EMIT3_off32(0x44, 0x2b, 0x8f, offsetof(struct sk_buff, data_len));
+
+	/* mov %r10, off32(%rdi) */
+	EMIT3_off32(0x4c, 0x8b, 0x97, offsetof(struct sk_buff, data));
+	*pprog = prog;
+}
+
 static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		  int oldproglen, struct jit_context *ctx)
 {
@@ -329,36 +349,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 
 	emit_prologue(&prog);
 
-	if (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));
-	}
+	if (seen_ld_abs)
+		emit_load_skb_data_hlen(&prog);
 
 	for (i = 0; i < insn_cnt; i++, insn++) {
 		const s32 imm32 = insn->imm;
@@ -367,6 +359,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		u8 b1 = 0, b2 = 0, b3 = 0;
 		s64 jmp_offset;
 		u8 jmp_cond;
+		bool reload_skb_data;
 		int ilen;
 		u8 *func;
 
@@ -818,12 +811,18 @@ xadd:			if (is_imm8(insn->off))
 			func = (u8 *) __bpf_call_base + imm32;
 			jmp_offset = func - (image + addrs[i]);
 			if (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;
+				reload_skb_data = bpf_helper_changes_skb_data(func);
+				if (reload_skb_data) {
+					EMIT1(0x57); /* push %rdi */
+					jmp_offset += 22; /* pop, mov, sub, mov */
+				} else {
+					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",
@@ -832,8 +831,13 @@ xadd:			if (is_imm8(insn->off))
 			}
 			EMIT1_off32(0xE8, jmp_offset);
 			if (seen_ld_abs) {
-				EMIT2(0x41, 0x59); /* pop %r9 */
-				EMIT2(0x41, 0x5A); /* pop %r10 */
+				if (reload_skb_data) {
+					EMIT1(0x5F); /* pop %rdi */
+					emit_load_skb_data_hlen(&prog);
+				} else {
+					EMIT2(0x41, 0x59); /* pop %r9 */
+					EMIT2(0x41, 0x5A); /* pop %r10 */
+				}
 			}
 			break;
 
@@ -1099,7 +1103,7 @@ void bpf_int_jit_compile(struct bpf_prog *prog)
 	}
 
 	if (bpf_jit_enable > 1)
-		bpf_jit_dump(prog->len, proglen, 0, image);
+		bpf_jit_dump(prog->len, proglen, pass + 1, image);
 
 	if (image) {
 		bpf_flush_icache(header, image + proglen);