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

Pull networking updates from David Miller:
 "Another merge window, another pull full of stuff:

   1) Support alternative names for network devices, from Jiri Pirko.

   2) Introduce per-netns netdev notifiers, also from Jiri Pirko.

   3) Support MSG_PEEK in vsock/virtio, from Matias Ezequiel Vara
      Larsen.

   4) Allow compiling out the TLS TOE code, from Jakub Kicinski.

   5) Add several new tracepoints to the kTLS code, also from Jakub.

   6) Support set channels ethtool callback in ena driver, from Sameeh
      Jubran.

   7) New SCTP events SCTP_ADDR_ADDED, SCTP_ADDR_REMOVED,
      SCTP_ADDR_MADE_PRIM, and SCTP_SEND_FAILED_EVENT. From Xin Long.

   8) Add XDP support to mvneta driver, from Lorenzo Bianconi.

   9) Lots of netfilter hw offload fixes, cleanups and enhancements,
      from Pablo Neira Ayuso.

  10) PTP support for aquantia chips, from Egor Pomozov.

  11) Add UDP segmentation offload support to igb, ixgbe, and i40e. From
      Josh Hunt.

  12) Add smart nagle to tipc, from Jon Maloy.

  13) Support L2 field rewrite by TC offloads in bnxt_en, from Venkat
      Duvvuru.

  14) Add a flow mask cache to OVS, from Tonghao Zhang.

  15) Add XDP support to ice driver, from Maciej Fijalkowski.

  16) Add AF_XDP support to ice driver, from Krzysztof Kazimierczak.

  17) Support UDP GSO offload in atlantic driver, from Igor Russkikh.

  18) Support it in stmmac driver too, from Jose Abreu.

  19) Support TIPC encryption and auth, from Tuong Lien.

  20) Introduce BPF trampolines, from Alexei Starovoitov.

  21) Make page_pool API more numa friendly, from Saeed Mahameed.

  22) Introduce route hints to ipv4 and ipv6, from Paolo Abeni.

  23) Add UDP segmentation offload to cxgb4, Rahul Lakkireddy"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1857 commits)
  libbpf: Fix usage of u32 in userspace code
  mm: Implement no-MMU variant of vmalloc_user_node_flags
  slip: Fix use-after-free Read in slip_open
  net: dsa: sja1105: fix sja1105_parse_rgmii_delays()
  macvlan: schedule bc_work even if error
  enetc: add support Credit Based Shaper(CBS) for hardware offload
  net: phy: add helpers phy_(un)lock_mdio_bus
  mdio_bus: don't use managed reset-controller
  ax88179_178a: add ethtool_op_get_ts_info()
  mlxsw: spectrum_router: Fix use of uninitialized adjacency index
  mlxsw: spectrum_router: After underlay moves, demote conflicting tunnels
  bpf: Simplify __bpf_arch_text_poke poke type handling
  bpf: Introduce BPF_TRACE_x helper for the tracing tests
  bpf: Add bpf_jit_blinding_enabled for !CONFIG_BPF_JIT
  bpf, testing: Add various tail call test cases
  bpf, x86: Emit patchable direct jump as tail call
  bpf: Constant map key tracking for prog array pokes
  bpf: Add poke dependency tracking for prog array maps
  bpf: Add initial poke descriptor table for jit images
  bpf: Move owner type, jited info into array auxiliary data
  ...

17 files changed, 1200 insertions, 258 deletions

diff --git a/arch/arm/boot/dts/am571x-idk.dts b/arch/arm/boot/dts/am571x-idk.dts
index 0aaacea1d887..820ce3b60bb6 100644
--- a/arch/arm/boot/dts/am571x-idk.dts
+++ b/arch/arm/boot/dts/am571x-idk.dts
@@ -186,3 +186,30 @@
 	pinctrl-1 = <&mmc2_pins_hs>;
 	pinctrl-2 = <&mmc2_pins_ddr_rev20 &mmc2_iodelay_ddr_conf>;
 };
+
+&mac_sw {
+	pinctrl-names = "default", "sleep";
+	status = "okay";
+};
+
+&cpsw_port1 {
+	phy-handle = <&ethphy0_sw>;
+	phy-mode = "rgmii";
+	ti,dual-emac-pvid = <1>;
+};
+
+&cpsw_port2 {
+	phy-handle = <&ethphy1_sw>;
+	phy-mode = "rgmii";
+	ti,dual-emac-pvid = <2>;
+};
+
+&davinci_mdio_sw {
+	ethphy0_sw: ethernet-phy@0 {
+		reg = <0>;
+	};
+
+	ethphy1_sw: ethernet-phy@1 {
+		reg = <1>;
+	};
+};
diff --git a/arch/arm/boot/dts/am572x-idk.dts b/arch/arm/boot/dts/am572x-idk.dts
index ea1c119feaa5..c3d966904d64 100644
--- a/arch/arm/boot/dts/am572x-idk.dts
+++ b/arch/arm/boot/dts/am572x-idk.dts
@@ -27,3 +27,8 @@
 	pinctrl-1 = <&mmc2_pins_hs>;
 	pinctrl-2 = <&mmc2_pins_ddr_rev20>;
 };
+
+&mac {
+	status = "okay";
+	dual_emac;
+};
diff --git a/arch/arm/boot/dts/am574x-idk.dts b/arch/arm/boot/dts/am574x-idk.dts
index 7935d70874ce..fa0088025b2c 100644
--- a/arch/arm/boot/dts/am574x-idk.dts
+++ b/arch/arm/boot/dts/am574x-idk.dts
@@ -35,3 +35,8 @@
 	pinctrl-1 = <&mmc2_pins_default>;
 	pinctrl-2 = <&mmc2_pins_default>;
 };
+
+&mac {
+	status = "okay";
+	dual_emac;
+};
diff --git a/arch/arm/boot/dts/am57xx-idk-common.dtsi b/arch/arm/boot/dts/am57xx-idk-common.dtsi
index 423855a2a2d6..398721c7201c 100644
--- a/arch/arm/boot/dts/am57xx-idk-common.dtsi
+++ b/arch/arm/boot/dts/am57xx-idk-common.dtsi
@@ -363,11 +363,6 @@
 	ext-clk-src;
 };
 
-&mac {
-	status = "okay";
-	dual_emac;
-};
-
 &cpsw_emac0 {
 	phy-handle = <&ethphy0>;
 	phy-mode = "rgmii";
diff --git a/arch/arm/boot/dts/dra7-l4.dtsi b/arch/arm/boot/dts/dra7-l4.dtsi
index 5cac2dd58241..37e048771b0f 100644
--- a/arch/arm/boot/dts/dra7-l4.dtsi
+++ b/arch/arm/boot/dts/dra7-l4.dtsi
@@ -3079,6 +3079,58 @@
 					phys = <&phy_gmii_sel 2>;
 				};
 			};
+
+			mac_sw: switch@0 {
+				compatible = "ti,dra7-cpsw-switch","ti,cpsw-switch";
+				reg = <0x0 0x4000>;
+				ranges = <0 0 0x4000>;
+				clocks = <&gmac_main_clk>;
+				clock-names = "fck";
+				#address-cells = <1>;
+				#size-cells = <1>;
+				syscon = <&scm_conf>;
+				status = "disabled";
+
+				interrupts = <GIC_SPI 334 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 335 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 336 IRQ_TYPE_LEVEL_HIGH>,
+					     <GIC_SPI 337 IRQ_TYPE_LEVEL_HIGH>;
+				interrupt-names = "rx_thresh", "rx", "tx", "misc";
+
+				ethernet-ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+
+					cpsw_port1: port@1 {
+						reg = <1>;
+						label = "port1";
+						mac-address = [ 00 00 00 00 00 00 ];
+						phys = <&phy_gmii_sel 1>;
+					};
+
+					cpsw_port2: port@2 {
+						reg = <2>;
+						label = "port2";
+						mac-address = [ 00 00 00 00 00 00 ];
+						phys = <&phy_gmii_sel 2>;
+					};
+				};
+
+				davinci_mdio_sw: mdio@1000 {
+					compatible = "ti,cpsw-mdio","ti,davinci_mdio";
+					clocks = <&gmac_main_clk>;
+					clock-names = "fck";
+					#address-cells = <1>;
+					#size-cells = <0>;
+					bus_freq = <1000000>;
+					reg = <0x1000 0x100>;
+				};
+
+				cpts {
+					clocks = <&gmac_clkctrl DRA7_GMAC_GMAC_CLKCTRL 25>;
+					clock-names = "cpts";
+				};
+			};
 		};
 	};
 };
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 40d7f1a4fc45..89cce8d4bc6b 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -554,3 +554,4 @@ CONFIG_DEBUG_INFO_DWARF4=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_SCHEDSTATS=y
 # CONFIG_DEBUG_BUGVERBOSE is not set
+CONFIG_TI_CPSW_SWITCHDEV=y
diff --git a/arch/arm/mach-pxa/icontrol.c b/arch/arm/mach-pxa/icontrol.c
index 865b10344ea2..0474a4b1394d 100644
--- a/arch/arm/mach-pxa/icontrol.c
+++ b/arch/arm/mach-pxa/icontrol.c
@@ -12,6 +12,7 @@
 
 #include <linux/irq.h>
 #include <linux/platform_device.h>
+#include <linux/property.h>
 #include <linux/gpio.h>
 
 #include <asm/mach-types.h>
@@ -22,7 +23,6 @@
 
 #include <linux/spi/spi.h>
 #include <linux/spi/pxa2xx_spi.h>
-#include <linux/can/platform/mcp251x.h>
 #include <linux/regulator/machine.h>
 
 #include "generic.h"
@@ -69,8 +69,9 @@ static struct pxa2xx_spi_chip mcp251x_chip_info4 = {
 	.gpio_cs        = ICONTROL_MCP251x_nCS4
 };
 
-static struct mcp251x_platform_data mcp251x_info = {
-	.oscillator_frequency = 16E6,
+static const struct property_entry mcp251x_properties[] = {
+	PROPERTY_ENTRY_U32("clock-frequency", 16000000),
+	{}
 };
 
 static struct spi_board_info mcp251x_board_info[] = {
@@ -79,7 +80,7 @@ static struct spi_board_info mcp251x_board_info[] = {
 		.max_speed_hz    = 6500000,
 		.bus_num         = 3,
 		.chip_select     = 0,
-		.platform_data   = &mcp251x_info,
+		.properties      = mcp251x_properties,
 		.controller_data = &mcp251x_chip_info1,
 		.irq             = PXA_GPIO_TO_IRQ(ICONTROL_MCP251x_nIRQ1)
 	},
diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c
index da113c8eefbf..b27fc7ac9cea 100644
--- a/arch/arm/mach-pxa/zeus.c
+++ b/arch/arm/mach-pxa/zeus.c
@@ -13,6 +13,7 @@
 #include <linux/leds.h>
 #include <linux/irq.h>
 #include <linux/pm.h>
+#include <linux/property.h>
 #include <linux/gpio.h>
 #include <linux/gpio/machine.h>
 #include <linux/serial_8250.h>
@@ -27,7 +28,6 @@
 #include <linux/platform_data/i2c-pxa.h>
 #include <linux/platform_data/pca953x.h>
 #include <linux/apm-emulation.h>
-#include <linux/can/platform/mcp251x.h>
 #include <linux/regulator/fixed.h>
 #include <linux/regulator/machine.h>
 
@@ -428,14 +428,15 @@ static struct gpiod_lookup_table can_regulator_gpiod_table = {
 	},
 };
 
-static struct mcp251x_platform_data zeus_mcp2515_pdata = {
-	.oscillator_frequency	= 16*1000*1000,
+static const struct property_entry mcp251x_properties[] = {
+	PROPERTY_ENTRY_U32("clock-frequency", 16000000),
+	{}
 };
 
 static struct spi_board_info zeus_spi_board_info[] = {
 	[0] = {
 		.modalias	= "mcp2515",
-		.platform_data	= &zeus_mcp2515_pdata,
+		.properties	= mcp251x_properties,
 		.irq		= PXA_GPIO_TO_IRQ(ZEUS_CAN_GPIO),
 		.max_speed_hz	= 1*1000*1000,
 		.bus_num	= 3,
diff --git a/arch/powerpc/include/asm/local.h b/arch/powerpc/include/asm/local.h
index fdd00939270b..bc4bd19b7fc2 100644
--- a/arch/powerpc/include/asm/local.h
+++ b/arch/powerpc/include/asm/local.h
@@ -17,7 +17,7 @@ typedef struct
 
 #define LOCAL_INIT(i)	{ (i) }
 
-static __inline__ long local_read(local_t *l)
+static __inline__ long local_read(const local_t *l)
 {
 	return READ_ONCE(l->v);
 }
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index ce88211b9c6c..8d2134136290 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -23,6 +23,8 @@
 #include <linux/filter.h>
 #include <linux/init.h>
 #include <linux/bpf.h>
+#include <linux/mm.h>
+#include <linux/kernel.h>
 #include <asm/cacheflush.h>
 #include <asm/dis.h>
 #include <asm/facility.h>
@@ -38,10 +40,11 @@ struct bpf_jit {
 	int size;		/* Size of program and literal pool */
 	int size_prg;		/* Size of program */
 	int prg;		/* Current position in program */
-	int lit_start;		/* Start of literal pool */
-	int lit;		/* Current position in literal pool */
+	int lit32_start;	/* Start of 32-bit literal pool */
+	int lit32;		/* Current position in 32-bit literal pool */
+	int lit64_start;	/* Start of 64-bit literal pool */
+	int lit64;		/* Current position in 64-bit literal pool */
 	int base_ip;		/* Base address for literal pool */
-	int ret0_ip;		/* Address of return 0 */
 	int exit_ip;		/* Address of exit */
 	int r1_thunk_ip;	/* Address of expoline thunk for 'br %r1' */
 	int r14_thunk_ip;	/* Address of expoline thunk for 'br %r14' */
@@ -49,14 +52,10 @@ struct bpf_jit {
 	int labels[1];		/* Labels for local jumps */
 };
 
-#define BPF_SIZE_MAX	0xffff	/* Max size for program (16 bit branches) */
-
-#define SEEN_MEM	(1 << 0)	/* use mem[] for temporary storage */
-#define SEEN_RET0	(1 << 1)	/* ret0_ip points to a valid return 0 */
-#define SEEN_LITERAL	(1 << 2)	/* code uses literals */
-#define SEEN_FUNC	(1 << 3)	/* calls C functions */
-#define SEEN_TAIL_CALL	(1 << 4)	/* code uses tail calls */
-#define SEEN_REG_AX	(1 << 5)	/* code uses constant blinding */
+#define SEEN_MEM	BIT(0)		/* use mem[] for temporary storage */
+#define SEEN_LITERAL	BIT(1)		/* code uses literals */
+#define SEEN_FUNC	BIT(2)		/* calls C functions */
+#define SEEN_TAIL_CALL	BIT(3)		/* code uses tail calls */
 #define SEEN_STACK	(SEEN_FUNC | SEEN_MEM)
 
 /*
@@ -131,13 +130,13 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 #define _EMIT2(op)						\
 ({								\
 	if (jit->prg_buf)					\
-		*(u16 *) (jit->prg_buf + jit->prg) = op;	\
+		*(u16 *) (jit->prg_buf + jit->prg) = (op);	\
 	jit->prg += 2;						\
 })
 
 #define EMIT2(op, b1, b2)					\
 ({								\
-	_EMIT2(op | reg(b1, b2));				\
+	_EMIT2((op) | reg(b1, b2));				\
 	REG_SET_SEEN(b1);					\
 	REG_SET_SEEN(b2);					\
 })
@@ -145,20 +144,20 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 #define _EMIT4(op)						\
 ({								\
 	if (jit->prg_buf)					\
-		*(u32 *) (jit->prg_buf + jit->prg) = op;	\
+		*(u32 *) (jit->prg_buf + jit->prg) = (op);	\
 	jit->prg += 4;						\
 })
 
 #define EMIT4(op, b1, b2)					\
 ({								\
-	_EMIT4(op | reg(b1, b2));				\
+	_EMIT4((op) | reg(b1, b2));				\
 	REG_SET_SEEN(b1);					\
 	REG_SET_SEEN(b2);					\
 })
 
 #define EMIT4_RRF(op, b1, b2, b3)				\
 ({								\
-	_EMIT4(op | reg_high(b3) << 8 | reg(b1, b2));		\
+	_EMIT4((op) | reg_high(b3) << 8 | reg(b1, b2));		\
 	REG_SET_SEEN(b1);					\
 	REG_SET_SEEN(b2);					\
 	REG_SET_SEEN(b3);					\
@@ -167,13 +166,13 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 #define _EMIT4_DISP(op, disp)					\
 ({								\
 	unsigned int __disp = (disp) & 0xfff;			\
-	_EMIT4(op | __disp);					\
+	_EMIT4((op) | __disp);					\
 })
 
 #define EMIT4_DISP(op, b1, b2, disp)				\
 ({								\
-	_EMIT4_DISP(op | reg_high(b1) << 16 |			\
-		    reg_high(b2) << 8, disp);			\
+	_EMIT4_DISP((op) | reg_high(b1) << 16 |			\
+		    reg_high(b2) << 8, (disp));			\
 	REG_SET_SEEN(b1);					\
 	REG_SET_SEEN(b2);					\
 })
@@ -181,21 +180,27 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 #define EMIT4_IMM(op, b1, imm)					\
 ({								\
 	unsigned int __imm = (imm) & 0xffff;			\
-	_EMIT4(op | reg_high(b1) << 16 | __imm);		\
+	_EMIT4((op) | reg_high(b1) << 16 | __imm);		\
 	REG_SET_SEEN(b1);					\
 })
 
 #define EMIT4_PCREL(op, pcrel)					\
 ({								\
 	long __pcrel = ((pcrel) >> 1) & 0xffff;			\
-	_EMIT4(op | __pcrel);					\
+	_EMIT4((op) | __pcrel);					\
+})
+
+#define EMIT4_PCREL_RIC(op, mask, target)			\
+({								\
+	int __rel = ((target) - jit->prg) / 2;			\
+	_EMIT4((op) | (mask) << 20 | (__rel & 0xffff));		\
 })
 
 #define _EMIT6(op1, op2)					\
 ({								\
 	if (jit->prg_buf) {					\
-		*(u32 *) (jit->prg_buf + jit->prg) = op1;	\
-		*(u16 *) (jit->prg_buf + jit->prg + 4) = op2;	\
+		*(u32 *) (jit->prg_buf + jit->prg) = (op1);	\
+		*(u16 *) (jit->prg_buf + jit->prg + 4) = (op2);	\
 	}							\
 	jit->prg += 6;						\
 })
@@ -203,20 +208,20 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 #define _EMIT6_DISP(op1, op2, disp)				\
 ({								\
 	unsigned int __disp = (disp) & 0xfff;			\
-	_EMIT6(op1 | __disp, op2);				\
+	_EMIT6((op1) | __disp, op2);				\
 })
 
 #define _EMIT6_DISP_LH(op1, op2, disp)				\
 ({								\
-	u32 _disp = (u32) disp;					\
+	u32 _disp = (u32) (disp);				\
 	unsigned int __disp_h = _disp & 0xff000;		\
 	unsigned int __disp_l = _disp & 0x00fff;		\
-	_EMIT6(op1 | __disp_l, op2 | __disp_h >> 4);		\
+	_EMIT6((op1) | __disp_l, (op2) | __disp_h >> 4);	\
 })
 
 #define EMIT6_DISP_LH(op1, op2, b1, b2, b3, disp)		\
 ({								\
-	_EMIT6_DISP_LH(op1 | reg(b1, b2) << 16 |		\
+	_EMIT6_DISP_LH((op1) | reg(b1, b2) << 16 |		\
 		       reg_high(b3) << 8, op2, disp);		\
 	REG_SET_SEEN(b1);					\
 	REG_SET_SEEN(b2);					\
@@ -226,8 +231,8 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 #define EMIT6_PCREL_LABEL(op1, op2, b1, b2, label, mask)	\
 ({								\
 	int rel = (jit->labels[label] - jit->prg) >> 1;		\
-	_EMIT6(op1 | reg(b1, b2) << 16 | (rel & 0xffff),	\
-	       op2 | mask << 12);				\
+	_EMIT6((op1) | reg(b1, b2) << 16 | (rel & 0xffff),	\
+	       (op2) | (mask) << 12);				\
 	REG_SET_SEEN(b1);					\
 	REG_SET_SEEN(b2);					\
 })
@@ -235,68 +240,83 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 #define EMIT6_PCREL_IMM_LABEL(op1, op2, b1, imm, label, mask)	\
 ({								\
 	int rel = (jit->labels[label] - jit->prg) >> 1;		\
-	_EMIT6(op1 | (reg_high(b1) | mask) << 16 |		\
-		(rel & 0xffff), op2 | (imm & 0xff) << 8);	\
+	_EMIT6((op1) | (reg_high(b1) | (mask)) << 16 |		\
+		(rel & 0xffff), (op2) | ((imm) & 0xff) << 8);	\
 	REG_SET_SEEN(b1);					\
-	BUILD_BUG_ON(((unsigned long) imm) > 0xff);		\
+	BUILD_BUG_ON(((unsigned long) (imm)) > 0xff);		\
 })
 
 #define EMIT6_PCREL(op1, op2, b1, b2, i, off, mask)		\
 ({								\
 	/* Branch instruction needs 6 bytes */			\
-	int rel = (addrs[i + off + 1] - (addrs[i + 1] - 6)) / 2;\
-	_EMIT6(op1 | reg(b1, b2) << 16 | (rel & 0xffff), op2 | mask);	\
+	int rel = (addrs[(i) + (off) + 1] - (addrs[(i) + 1] - 6)) / 2;\
+	_EMIT6((op1) | reg(b1, b2) << 16 | (rel & 0xffff), (op2) | (mask));\
 	REG_SET_SEEN(b1);					\
 	REG_SET_SEEN(b2);					\
 })
 
 #define EMIT6_PCREL_RILB(op, b, target)				\
 ({								\
-	int rel = (target - jit->prg) / 2;			\
-	_EMIT6(op | reg_high(b) << 16 | rel >> 16, rel & 0xffff);	\
+	unsigned int rel = (int)((target) - jit->prg) / 2;	\
+	_EMIT6((op) | reg_high(b) << 16 | rel >> 16, rel & 0xffff);\
 	REG_SET_SEEN(b);					\
 })
 
 #define EMIT6_PCREL_RIL(op, target)				\
 ({								\
-	int rel = (target - jit->prg) / 2;			\
-	_EMIT6(op | rel >> 16, rel & 0xffff);			\
+	unsigned int rel = (int)((target) - jit->prg) / 2;	\
+	_EMIT6((op) | rel >> 16, rel & 0xffff);			\
+})
+
+#define EMIT6_PCREL_RILC(op, mask, target)			\
+({								\
+	EMIT6_PCREL_RIL((op) | (mask) << 20, (target));		\
 })
 
 #define _EMIT6_IMM(op, imm)					\
 ({								\
 	unsigned int __imm = (imm);				\
-	_EMIT6(op | (__imm >> 16), __imm & 0xffff);		\
+	_EMIT6((op) | (__imm >> 16), __imm & 0xffff);		\
 })
 
 #define EMIT6_IMM(op, b1, imm)					\
 ({								\
-	_EMIT6_IMM(op | reg_high(b1) << 16, imm);		\
+	_EMIT6_IMM((op) | reg_high(b1) << 16, imm);		\
 	REG_SET_SEEN(b1);					\
 })
 
-#define EMIT_CONST_U32(val)					\
+#define _EMIT_CONST_U32(val)					\
 ({								\
 	unsigned int ret;					\
-	ret = jit->lit - jit->base_ip;				\
-	jit->seen |= SEEN_LITERAL;				\
+	ret = jit->lit32;					\
 	if (jit->prg_buf)					\
-		*(u32 *) (jit->prg_buf + jit->lit) = (u32) val;	\
-	jit->lit += 4;						\
+		*(u32 *)(jit->prg_buf + jit->lit32) = (u32)(val);\
+	jit->lit32 += 4;					\
 	ret;							\
 })
 
-#define EMIT_CONST_U64(val)					\
+#define EMIT_CONST_U32(val)					\
 ({								\
-	unsigned int ret;					\
-	ret = jit->lit - jit->base_ip;				\
 	jit->seen |= SEEN_LITERAL;				\
+	_EMIT_CONST_U32(val) - jit->base_ip;			\
+})
+
+#define _EMIT_CONST_U64(val)					\
+({								\
+	unsigned int ret;					\
+	ret = jit->lit64;					\
 	if (jit->prg_buf)					\
-		*(u64 *) (jit->prg_buf + jit->lit) = (u64) val;	\
-	jit->lit += 8;						\
+		*(u64 *)(jit->prg_buf + jit->lit64) = (u64)(val);\
+	jit->lit64 += 8;					\
 	ret;							\
 })
 
+#define EMIT_CONST_U64(val)					\
+({								\
+	jit->seen |= SEEN_LITERAL;				\
+	_EMIT_CONST_U64(val) - jit->base_ip;			\
+})
+
 #define EMIT_ZERO(b1)						\
 ({								\
 	if (!fp->aux->verifier_zext) {				\
@@ -307,6 +327,67 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 })
 
 /*
+ * Return whether this is the first pass. The first pass is special, since we
+ * don't know any sizes yet, and thus must be conservative.
+ */
+static bool is_first_pass(struct bpf_jit *jit)
+{
+	return jit->size == 0;
+}
+
+/*
+ * Return whether this is the code generation pass. The code generation pass is
+ * special, since we should change as little as possible.
+ */
+static bool is_codegen_pass(struct bpf_jit *jit)
+{
+	return jit->prg_buf;
+}
+
+/*
+ * Return whether "rel" can be encoded as a short PC-relative offset
+ */
+static bool is_valid_rel(int rel)
+{
+	return rel >= -65536 && rel <= 65534;
+}
+
+/*
+ * Return whether "off" can be reached using a short PC-relative offset
+ */
+static bool can_use_rel(struct bpf_jit *jit, int off)
+{
+	return is_valid_rel(off - jit->prg);
+}
+
+/*
+ * Return whether given displacement can be encoded using
+ * Long-Displacement Facility
+ */
+static bool is_valid_ldisp(int disp)
+{
+	return disp >= -524288 && disp <= 524287;
+}
+
+/*
+ * Return whether the next 32-bit literal pool entry can be referenced using
+ * Long-Displacement Facility
+ */
+static bool can_use_ldisp_for_lit32(struct bpf_jit *jit)
+{
+	return is_valid_ldisp(jit->lit32 - jit->base_ip);
+}
+
+/*
+ * Return whether the next 64-bit literal pool entry can be referenced using
+ * Long-Displacement Facility
+ */
+static bool can_use_ldisp_for_lit64(struct bpf_jit *jit)
+{
+	return is_valid_ldisp(jit->lit64 - jit->base_ip);
+}
+
+/*
  * Fill whole space with illegal instructions
  */
 static void jit_fill_hole(void *area, unsigned int size)
@@ -383,9 +464,18 @@ static int get_end(struct bpf_jit *jit, int start)
  */
 static void save_restore_regs(struct bpf_jit *jit, int op, u32 stack_depth)
 {
-
+	const int last = 15, save_restore_size = 6;
 	int re = 6, rs;
 
+	if (is_first_pass(jit)) {
+		/*
+		 * We don't know yet which registers are used. Reserve space
+		 * conservatively.
+		 */
+		jit->prg += (last - re + 1) * save_restore_size;
+		return;
+	}
+
 	do {
 		rs = get_start(jit, re);
 		if (!rs)
@@ -396,7 +486,7 @@ static void save_restore_regs(struct bpf_jit *jit, int op, u32 stack_depth)
 		else
 			restore_regs(jit, rs, re, stack_depth);
 		re++;
-	} while (re <= 15);
+	} while (re <= last);
 }
 
 /*
@@ -420,21 +510,28 @@ static void bpf_jit_prologue(struct bpf_jit *jit, u32 stack_depth)
 	/* Save registers */
 	save_restore_regs(jit, REGS_SAVE, stack_depth);
 	/* Setup literal pool */
-	if (jit->seen & SEEN_LITERAL) {
-		/* basr %r13,0 */
-		EMIT2(0x0d00, REG_L, REG_0);
-		jit->base_ip = jit->prg;
+	if (is_first_pass(jit) || (jit->seen & SEEN_LITERAL)) {
+		if (!is_first_pass(jit) &&
+		    is_valid_ldisp(jit->size - (jit->prg + 2))) {
+			/* basr %l,0 */
+			EMIT2(0x0d00, REG_L, REG_0);
+			jit->base_ip = jit->prg;
+		} else {
+			/* larl %l,lit32_start */
+			EMIT6_PCREL_RILB(0xc0000000, REG_L, jit->lit32_start);
+			jit->base_ip = jit->lit32_start;
+		}
 	}
 	/* Setup stack and backchain */
-	if (jit->seen & SEEN_STACK) {
-		if (jit->seen & SEEN_FUNC)
+	if (is_first_pass(jit) || (jit->seen & SEEN_STACK)) {
+		if (is_first_pass(jit) || (jit->seen & SEEN_FUNC))
 			/* lgr %w1,%r15 (backchain) */
 			EMIT4(0xb9040000, REG_W1, REG_15);
 		/* la %bfp,STK_160_UNUSED(%r15) (BPF frame pointer) */
 		EMIT4_DISP(0x41000000, BPF_REG_FP, REG_15, STK_160_UNUSED);
 		/* aghi %r15,-STK_OFF */
 		EMIT4_IMM(0xa70b0000, REG_15, -(STK_OFF + stack_depth));
-		if (jit->seen & SEEN_FUNC)
+		if (is_first_pass(jit) || (jit->seen & SEEN_FUNC))
 			/* stg %w1,152(%r15) (backchain) */
 			EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0,
 				      REG_15, 152);
@@ -446,12 +543,6 @@ static void bpf_jit_prologue(struct bpf_jit *jit, u32 stack_depth)
  */
 static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth)
 {
-	/* Return 0 */
-	if (jit->seen & SEEN_RET0) {
-		jit->ret0_ip = jit->prg;
-		/* lghi %b0,0 */
-		EMIT4_IMM(0xa7090000, BPF_REG_0, 0);
-	}
 	jit->exit_ip = jit->prg;
 	/* Load exit code: lgr %r2,%b0 */
 	EMIT4(0xb9040000, REG_2, BPF_REG_0);
@@ -476,7 +567,7 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth)
 	_EMIT2(0x07fe);
 
 	if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable &&
-	    (jit->seen & SEEN_FUNC)) {
+	    (is_first_pass(jit) || (jit->seen & SEEN_FUNC))) {
 		jit->r1_thunk_ip = jit->prg;
 		/* Generate __s390_indirect_jump_r1 thunk */
 		if (test_facility(35)) {
@@ -506,16 +597,14 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 				 int i, bool extra_pass)
 {
 	struct bpf_insn *insn = &fp->insnsi[i];
-	int jmp_off, last, insn_count = 1;
 	u32 dst_reg = insn->dst_reg;
 	u32 src_reg = insn->src_reg;
+	int last, insn_count = 1;
 	u32 *addrs = jit->addrs;
 	s32 imm = insn->imm;
 	s16 off = insn->off;
 	unsigned int mask;
 
-	if (dst_reg == BPF_REG_AX || src_reg == BPF_REG_AX)
-		jit->seen |= SEEN_REG_AX;
 	switch (insn->code) {
 	/*
 	 * BPF_MOV
@@ -549,9 +638,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		u64 imm64;
 
 		imm64 = (u64)(u32) insn[0].imm | ((u64)(u32) insn[1].imm) << 32;
-		/* lg %dst,<d(imm)>(%l) */
-		EMIT6_DISP_LH(0xe3000000, 0x0004, dst_reg, REG_0, REG_L,
-			      EMIT_CONST_U64(imm64));
+		/* lgrl %dst,imm */
+		EMIT6_PCREL_RILB(0xc4080000, dst_reg, _EMIT_CONST_U64(imm64));
 		insn_count = 2;
 		break;
 	}
@@ -680,9 +768,18 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		EMIT4_IMM(0xa7080000, REG_W0, 0);
 		/* lr %w1,%dst */
 		EMIT2(0x1800, REG_W1, dst_reg);
-		/* dl %w0,<d(imm)>(%l) */
-		EMIT6_DISP_LH(0xe3000000, 0x0097, REG_W0, REG_0, REG_L,
-			      EMIT_CONST_U32(imm));
+		if (!is_first_pass(jit) && can_use_ldisp_for_lit32(jit)) {
+			/* dl %w0,<d(imm)>(%l) */
+			EMIT6_DISP_LH(0xe3000000, 0x0097, REG_W0, REG_0, REG_L,
+				      EMIT_CONST_U32(imm));
+		} else {
+			/* lgfrl %dst,imm */
+			EMIT6_PCREL_RILB(0xc40c0000, dst_reg,
+					 _EMIT_CONST_U32(imm));
+			jit->seen |= SEEN_LITERAL;
+			/* dlr %w0,%dst */
+			EMIT4(0xb9970000, REG_W0, dst_reg);
+		}
 		/* llgfr %dst,%rc */
 		EMIT4(0xb9160000, dst_reg, rc_reg);
 		if (insn_is_zext(&insn[1]))
@@ -704,9 +801,18 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		EMIT4_IMM(0xa7090000, REG_W0, 0);
 		/* lgr %w1,%dst */
 		EMIT4(0xb9040000, REG_W1, dst_reg);
-		/* dlg %w0,<d(imm)>(%l) */
-		EMIT6_DISP_LH(0xe3000000, 0x0087, REG_W0, REG_0, REG_L,
-			      EMIT_CONST_U64(imm));
+		if (!is_first_pass(jit) && can_use_ldisp_for_lit64(jit)) {
+			/* dlg %w0,<d(imm)>(%l) */
+			EMIT6_DISP_LH(0xe3000000, 0x0087, REG_W0, REG_0, REG_L,
+				      EMIT_CONST_U64(imm));
+		} else {
+			/* lgrl %dst,imm */
+			EMIT6_PCREL_RILB(0xc4080000, dst_reg,
+					 _EMIT_CONST_U64(imm));
+			jit->seen |= SEEN_LITERAL;
+			/* dlgr %w0,%dst */
+			EMIT4(0xb9870000, REG_W0, dst_reg);
+		}
 		/* lgr %dst,%rc */
 		EMIT4(0xb9040000, dst_reg, rc_reg);
 		break;
@@ -729,9 +835,19 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		EMIT_ZERO(dst_reg);
 		break;
 	case BPF_ALU64 | BPF_AND | BPF_K: /* dst = dst & imm */
-		/* ng %dst,<d(imm)>(%l) */
-		EMIT6_DISP_LH(0xe3000000, 0x0080, dst_reg, REG_0, REG_L,
-			      EMIT_CONST_U64(imm));
+		if (!is_first_pass(jit) && can_use_ldisp_for_lit64(jit)) {
+			/* ng %dst,<d(imm)>(%l) */
+			EMIT6_DISP_LH(0xe3000000, 0x0080,
+				      dst_reg, REG_0, REG_L,
+				      EMIT_CONST_U64(imm));
+		} else {
+			/* lgrl %w0,imm */
+			EMIT6_PCREL_RILB(0xc4080000, REG_W0,
+					 _EMIT_CONST_U64(imm));
+			jit->seen |= SEEN_LITERAL;
+			/* ngr %dst,%w0 */
+			EMIT4(0xb9800000, dst_reg, REG_W0);
+		}
 		break;
 	/*
 	 * BPF_OR
@@ -751,9 +867,19 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		EMIT_ZERO(dst_reg);
 		break;
 	case BPF_ALU64 | BPF_OR | BPF_K: /* dst = dst | imm */
-		/* og %dst,<d(imm)>(%l) */
-		EMIT6_DISP_LH(0xe3000000, 0x0081, dst_reg, REG_0, REG_L,
-			      EMIT_CONST_U64(imm));
+		if (!is_first_pass(jit) && can_use_ldisp_for_lit64(jit)) {
+			/* og %dst,<d(imm)>(%l) */
+			EMIT6_DISP_LH(0xe3000000, 0x0081,
+				      dst_reg, REG_0, REG_L,
+				      EMIT_CONST_U64(imm));
+		} else {
+			/* lgrl %w0,imm */
+			EMIT6_PCREL_RILB(0xc4080000, REG_W0,
+					 _EMIT_CONST_U64(imm));
+			jit->seen |= SEEN_LITERAL;
+			/* ogr %dst,%w0 */
+			EMIT4(0xb9810000, dst_reg, REG_W0);
+		}
 		break;
 	/*
 	 * BPF_XOR
@@ -775,9 +901,19 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		EMIT_ZERO(dst_reg);
 		break;
 	case BPF_ALU64 | BPF_XOR | BPF_K: /* dst = dst ^ imm */
-		/* xg %dst,<d(imm)>(%l) */
-		EMIT6_DISP_LH(0xe3000000, 0x0082, dst_reg, REG_0, REG_L,
-			      EMIT_CONST_U64(imm));
+		if (!is_first_pass(jit) && can_use_ldisp_for_lit64(jit)) {
+			/* xg %dst,<d(imm)>(%l) */
+			EMIT6_DISP_LH(0xe3000000, 0x0082,
+				      dst_reg, REG_0, REG_L,
+				      EMIT_CONST_U64(imm));
+		} else {
+			/* lgrl %w0,imm */
+			EMIT6_PCREL_RILB(0xc4080000, REG_W0,
+					 _EMIT_CONST_U64(imm));
+			jit->seen |= SEEN_LITERAL;
+			/* xgr %dst,%w0 */
+			EMIT4(0xb9820000, dst_reg, REG_W0);
+		}
 		break;
 	/*
 	 * BPF_LSH
@@ -1023,9 +1159,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 
 		REG_SET_SEEN(BPF_REG_5);
 		jit->seen |= SEEN_FUNC;
-		/* lg %w1,<d(imm)>(%l) */
-		EMIT6_DISP_LH(0xe3000000, 0x0004, REG_W1, REG_0, REG_L,
-			      EMIT_CONST_U64(func));
+		/* lgrl %w1,func */
+		EMIT6_PCREL_RILB(0xc4080000, REG_W1, _EMIT_CONST_U64(func));
 		if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable) {
 			/* brasl %r14,__s390_indirect_jump_r1 */
 			EMIT6_PCREL_RILB(0xc0050000, REG_14, jit->r1_thunk_ip);
@@ -1054,9 +1189,17 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		/* llgf %w1,map.max_entries(%b2) */
 		EMIT6_DISP_LH(0xe3000000, 0x0016, REG_W1, REG_0, BPF_REG_2,
 			      offsetof(struct bpf_array, map.max_entries));
-		/* clrj %b3,%w1,0xa,label0: if (u32)%b3 >= (u32)%w1 goto out */
-		EMIT6_PCREL_LABEL(0xec000000, 0x0077, BPF_REG_3,
-				  REG_W1, 0, 0xa);
+		/* if ((u32)%b3 >= (u32)%w1) goto out; */
+		if (!is_first_pass(jit) && can_use_rel(jit, jit->labels[0])) {
+			/* clrj %b3,%w1,0xa,label0 */
+			EMIT6_PCREL_LABEL(0xec000000, 0x0077, BPF_REG_3,
+					  REG_W1, 0, 0xa);
+		} else {
+			/* clr %b3,%w1 */
+			EMIT2(0x1500, BPF_REG_3, REG_W1);
+			/* brcl 0xa,label0 */
+			EMIT6_PCREL_RILC(0xc0040000, 0xa, jit->labels[0]);
+		}
 
 		/*
 		 * if (tail_call_cnt++ > MAX_TAIL_CALL_CNT)
@@ -1071,9 +1214,16 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		EMIT4_IMM(0xa7080000, REG_W0, 1);
 		/* laal %w1,%w0,off(%r15) */
 		EMIT6_DISP_LH(0xeb000000, 0x00fa, REG_W1, REG_W0, REG_15, off);
-		/* clij %w1,MAX_TAIL_CALL_CNT,0x2,label0 */
-		EMIT6_PCREL_IMM_LABEL(0xec000000, 0x007f, REG_W1,
-				      MAX_TAIL_CALL_CNT, 0, 0x2);
+		if (!is_first_pass(jit) && can_use_rel(jit, jit->labels[0])) {
+			/* clij %w1,MAX_TAIL_CALL_CNT,0x2,label0 */
+			EMIT6_PCREL_IMM_LABEL(0xec000000, 0x007f, REG_W1,
+					      MAX_TAIL_CALL_CNT, 0, 0x2);
+		} else {
+			/* clfi %w1,MAX_TAIL_CALL_CNT */
+			EMIT6_IMM(0xc20f0000, REG_W1, MAX_TAIL_CALL_CNT);
+			/* brcl 0x2,label0 */
+			EMIT6_PCREL_RILC(0xc0040000, 0x2, jit->labels[0]);
+		}
 
 		/*
 		 * prog = array->ptrs[index];
@@ -1085,11 +1235,16 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		EMIT4(0xb9160000, REG_1, BPF_REG_3);
 		/* sllg %r1,%r1,3: %r1 *= 8 */
 		EMIT6_DISP_LH(0xeb00