diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index f6a62ae44a65..25b3ee85066e 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -22,6 +22,7 @@
 #include <asm/cacheflush.h>
 #include <asm/hwcap.h>
 #include <asm/opcodes.h>
+#include <asm/system_info.h>
 
 #include "bpf_jit_32.h"
 
@@ -47,32 +48,73 @@
  * The callee saved registers depends on whether frame pointers are enabled.
  * With frame pointers (to be compliant with the ABI):
  *
- *                                high
- * original ARM_SP =>     +------------------+ \
- *                        |        pc        | |
- * current ARM_FP =>      +------------------+ } callee saved registers
- *                        |r4-r8,r10,fp,ip,lr| |
- *                        +------------------+ /
- *                                low
+ *                              high
+ * original ARM_SP =>     +--------------+ \
+ *                        |      pc      | |
+ * current ARM_FP =>      +--------------+ } callee saved registers
+ *                        |r4-r9,fp,ip,lr| |
+ *                        +--------------+ /
+ *                              low
  *
  * Without frame pointers:
  *
- *                                high
- * original ARM_SP =>     +------------------+
- *                        | r4-r8,r10,fp,lr  | callee saved registers
- * current ARM_FP =>      +------------------+
- *                                low
+ *                              high
+ * original ARM_SP =>     +--------------+
+ *                        |  r4-r9,fp,lr | callee saved registers
+ * current ARM_FP =>      +--------------+
+ *                              low
  *
  * When popping registers off the stack at the end of a BPF function, we
  * reference them via the current ARM_FP register.
  */
 #define CALLEE_MASK	(1 << ARM_R4 | 1 << ARM_R5 | 1 << ARM_R6 | \
-			 1 << ARM_R7 | 1 << ARM_R8 | 1 << ARM_R10 | \
+			 1 << ARM_R7 | 1 << ARM_R8 | 1 << ARM_R9 | \
 			 1 << ARM_FP)
 #define CALLEE_PUSH_MASK (CALLEE_MASK | 1 << ARM_LR)
 #define CALLEE_POP_MASK  (CALLEE_MASK | 1 << ARM_PC)
 
-#define STACK_OFFSET(k)	(k)
+enum {
+	/* Stack layout - these are offsets from (top of stack - 4) */
+	BPF_R2_HI,
+	BPF_R2_LO,
+	BPF_R3_HI,
+	BPF_R3_LO,
+	BPF_R4_HI,
+	BPF_R4_LO,
+	BPF_R5_HI,
+	BPF_R5_LO,
+	BPF_R7_HI,
+	BPF_R7_LO,
+	BPF_R8_HI,
+	BPF_R8_LO,
+	BPF_R9_HI,
+	BPF_R9_LO,
+	BPF_FP_HI,
+	BPF_FP_LO,
+	BPF_TC_HI,
+	BPF_TC_LO,
+	BPF_AX_HI,
+	BPF_AX_LO,
+	/* Stack space for BPF_REG_2, BPF_REG_3, BPF_REG_4,
+	 * BPF_REG_5, BPF_REG_7, BPF_REG_8, BPF_REG_9,
+	 * BPF_REG_FP and Tail call counts.
+	 */
+	BPF_JIT_SCRATCH_REGS,
+};
+
+/*
+ * Negative "register" values indicate the register is stored on the stack
+ * and are the offset from the top of the eBPF JIT scratch space.
+ */
+#define STACK_OFFSET(k)	(-4 - (k) * 4)
+#define SCRATCH_SIZE	(BPF_JIT_SCRATCH_REGS * 4)
+
+#ifdef CONFIG_FRAME_POINTER
+#define EBPF_SCRATCH_TO_ARM_FP(x) ((x) - 4 * hweight16(CALLEE_PUSH_MASK) - 4)
+#else
+#define EBPF_SCRATCH_TO_ARM_FP(x) (x)
+#endif
+
 #define TMP_REG_1	(MAX_BPF_JIT_REG + 0)	/* TEMP Register 1 */
 #define TMP_REG_2	(MAX_BPF_JIT_REG + 1)	/* TEMP Register 2 */
 #define TCALL_CNT	(MAX_BPF_JIT_REG + 2)	/* Tail Call Count */
@@ -94,35 +136,35 @@
  * scratch memory space and we have to build eBPF 64 bit register from those.
  *
  */
-static const u8 bpf2a32[][2] = {
+static const s8 bpf2a32[][2] = {
 	/* return value from in-kernel function, and exit value from eBPF */
 	[BPF_REG_0] = {ARM_R1, ARM_R0},
 	/* arguments from eBPF program to in-kernel function */
 	[BPF_REG_1] = {ARM_R3, ARM_R2},
 	/* Stored on stack scratch space */
-	[BPF_REG_2] = {STACK_OFFSET(0), STACK_OFFSET(4)},
-	[BPF_REG_3] = {STACK_OFFSET(8), STACK_OFFSET(12)},
-	[BPF_REG_4] = {STACK_OFFSET(16), STACK_OFFSET(20)},
-	[BPF_REG_5] = {STACK_OFFSET(24), STACK_OFFSET(28)},
+	[BPF_REG_2] = {STACK_OFFSET(BPF_R2_HI), STACK_OFFSET(BPF_R2_LO)},
+	[BPF_REG_3] = {STACK_OFFSET(BPF_R3_HI), STACK_OFFSET(BPF_R3_LO)},
+	[BPF_REG_4] = {STACK_OFFSET(BPF_R4_HI), STACK_OFFSET(BPF_R4_LO)},
+	[BPF_REG_5] = {STACK_OFFSET(BPF_R5_HI), STACK_OFFSET(BPF_R5_LO)},
 	/* callee saved registers that in-kernel function will preserve */
 	[BPF_REG_6] = {ARM_R5, ARM_R4},
 	/* Stored on stack scratch space */
-	[BPF_REG_7] = {STACK_OFFSET(32), STACK_OFFSET(36)},
-	[BPF_REG_8] = {STACK_OFFSET(40), STACK_OFFSET(44)},
-	[BPF_REG_9] = {STACK_OFFSET(48), STACK_OFFSET(52)},
+	[BPF_REG_7] = {STACK_OFFSET(BPF_R7_HI), STACK_OFFSET(BPF_R7_LO)},
+	[BPF_REG_8] = {STACK_OFFSET(BPF_R8_HI), STACK_OFFSET(BPF_R8_LO)},
+	[BPF_REG_9] = {STACK_OFFSET(BPF_R9_HI), STACK_OFFSET(BPF_R9_LO)},
 	/* Read only Frame Pointer to access Stack */
-	[BPF_REG_FP] = {STACK_OFFSET(56), STACK_OFFSET(60)},
+	[BPF_REG_FP] = {STACK_OFFSET(BPF_FP_HI), STACK_OFFSET(BPF_FP_LO)},
 	/* Temporary Register for internal BPF JIT, can be used
 	 * for constant blindings and others.
 	 */
 	[TMP_REG_1] = {ARM_R7, ARM_R6},
-	[TMP_REG_2] = {ARM_R10, ARM_R8},
+	[TMP_REG_2] = {ARM_R9, ARM_R8},
 	/* Tail call count. Stored on stack scratch space. */
-	[TCALL_CNT] = {STACK_OFFSET(64), STACK_OFFSET(68)},
+	[TCALL_CNT] = {STACK_OFFSET(BPF_TC_HI), STACK_OFFSET(BPF_TC_LO)},
 	/* temporary register for blinding constants.
 	 * Stored on stack scratch space.
 	 */
-	[BPF_REG_AX] = {STACK_OFFSET(72), STACK_OFFSET(76)},
+	[BPF_REG_AX] = {STACK_OFFSET(BPF_AX_HI), STACK_OFFSET(BPF_AX_LO)},
 };
 
 #define	dst_lo	dst[1]
@@ -151,6 +193,7 @@ struct jit_ctx {
 	unsigned int idx;
 	unsigned int prologue_bytes;
 	unsigned int epilogue_offset;
+	unsigned int cpu_architecture;
 	u32 flags;
 	u32 *offsets;
 	u32 *target;
@@ -195,10 +238,56 @@ static inline void emit(u32 inst, struct jit_ctx *ctx)
 	_emit(ARM_COND_AL, inst, ctx);
 }
 
+/*
+ * This is rather horrid, but necessary to convert an integer constant
+ * to an immediate operand for the opcodes, and be able to detect at
+ * build time whether the constant can't be converted (iow, usable in
+ * BUILD_BUG_ON()).
+ */
+#define imm12val(v, s) (rol32(v, (s)) | (s) << 7)
+#define const_imm8m(x)					\
+	({ int r;					\
+	   u32 v = (x);					\
+	   if (!(v & ~0x000000ff))			\
+		r = imm12val(v, 0);			\
+	   else if (!(v & ~0xc000003f))			\
+		r = imm12val(v, 2);			\
+	   else if (!(v & ~0xf000000f))			\
+		r = imm12val(v, 4);			\
+	   else if (!(v & ~0xfc000003))			\
+		r = imm12val(v, 6);			\
+	   else if (!(v & ~0xff000000))			\
+		r = imm12val(v, 8);			\
+	   else if (!(v & ~0x3fc00000))			\
+		r = imm12val(v, 10);			\
+	   else if (!(v & ~0x0ff00000))			\
+		r = imm12val(v, 12);			\
+	   else if (!(v & ~0x03fc0000))			\
+		r = imm12val(v, 14);			\
+	   else if (!(v & ~0x00ff0000))			\
+		r = imm12val(v, 16);			\
+	   else if (!(v & ~0x003fc000))			\
+		r = imm12val(v, 18);			\
+	   else if (!(v & ~0x000ff000))			\
+		r = imm12val(v, 20);			\
+	   else if (!(v & ~0x0003fc00))			\
+		r = imm12val(v, 22);			\
+	   else if (!(v & ~0x0000ff00))			\
+		r = imm12val(v, 24);			\
+	   else if (!(v & ~0x00003fc0))			\
+		r = imm12val(v, 26);			\
+	   else if (!(v & ~0x00000ff0))			\
+		r = imm12val(v, 28);			\
+	   else if (!(v & ~0x000003fc))			\
+		r = imm12val(v, 30);			\
+	   else						\
+		r = -1;					\
+	   r; })
+
 /*
  * Checks if immediate value can be converted to imm12(12 bits) value.
  */
-static int16_t imm8m(u32 x)
+static int imm8m(u32 x)
 {
 	u32 rot;
 
@@ -208,6 +297,38 @@ static int16_t imm8m(u32 x)
 	return -1;
 }
 
+#define imm8m(x) (__builtin_constant_p(x) ? const_imm8m(x) : imm8m(x))
+
+static u32 arm_bpf_ldst_imm12(u32 op, u8 rt, u8 rn, s16 imm12)
+{
+	op |= rt << 12 | rn << 16;
+	if (imm12 >= 0)
+		op |= ARM_INST_LDST__U;
+	else
+		imm12 = -imm12;
+	return op | (imm12 & ARM_INST_LDST__IMM12);
+}
+
+static u32 arm_bpf_ldst_imm8(u32 op, u8 rt, u8 rn, s16 imm8)
+{
+	op |= rt << 12 | rn << 16;
+	if (imm8 >= 0)
+		op |= ARM_INST_LDST__U;
+	else
+		imm8 = -imm8;
+	return op | (imm8 & 0xf0) << 4 | (imm8 & 0x0f);
+}
+
+#define ARM_LDR_I(rt, rn, off)	arm_bpf_ldst_imm12(ARM_INST_LDR_I, rt, rn, off)
+#define ARM_LDRB_I(rt, rn, off)	arm_bpf_ldst_imm12(ARM_INST_LDRB_I, rt, rn, off)
+#define ARM_LDRD_I(rt, rn, off)	arm_bpf_ldst_imm8(ARM_INST_LDRD_I, rt, rn, off)
+#define ARM_LDRH_I(rt, rn, off)	arm_bpf_ldst_imm8(ARM_INST_LDRH_I, rt, rn, off)
+
+#define ARM_STR_I(rt, rn, off)	arm_bpf_ldst_imm12(ARM_INST_STR_I, rt, rn, off)
+#define ARM_STRB_I(rt, rn, off)	arm_bpf_ldst_imm12(ARM_INST_STRB_I, rt, rn, off)
+#define ARM_STRD_I(rt, rn, off)	arm_bpf_ldst_imm8(ARM_INST_STRD_I, rt, rn, off)
+#define ARM_STRH_I(rt, rn, off)	arm_bpf_ldst_imm8(ARM_INST_STRH_I, rt, rn, off)
+
 /*
  * Initializes the JIT space with undefined instructions.
  */
@@ -227,19 +348,10 @@ static void jit_fill_hole(void *area, unsigned int size)
 #define STACK_ALIGNMENT	4
 #endif
 
-/* Stack space for BPF_REG_2, BPF_REG_3, BPF_REG_4,
- * BPF_REG_5, BPF_REG_7, BPF_REG_8, BPF_REG_9,
- * BPF_REG_FP and Tail call counts.
- */
-#define SCRATCH_SIZE 80
-
 /* total stack size used in JITed code */
 #define _STACK_SIZE	(ctx->prog->aux->stack_depth + SCRATCH_SIZE)
 #define STACK_SIZE	ALIGN(_STACK_SIZE, STACK_ALIGNMENT)
 
-/* Get the offset of eBPF REGISTERs stored on scratch space. */
-#define STACK_VAR(off) (STACK_SIZE - off)
-
 #if __LINUX_ARM_ARCH__ < 7
 
 static u16 imm_offset(u32 k, struct jit_ctx *ctx)
@@ -355,7 +467,7 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
 
 static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
 {
-	const u8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *tmp = bpf2a32[TMP_REG_1];
 
 #if __LINUX_ARM_ARCH__ == 7
 	if (elf_hwcap & HWCAP_IDIVA) {
@@ -402,44 +514,110 @@ static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
 		emit(ARM_MOV_R(ARM_R0, tmp[1]), ctx);
 }
 
-/* Checks whether BPF register is on scratch stack space or not. */
-static inline bool is_on_stack(u8 bpf_reg)
+/* Is the translated BPF register on stack? */
+static bool is_stacked(s8 reg)
 {
-	static u8 stack_regs[] = {BPF_REG_AX, BPF_REG_3, BPF_REG_4, BPF_REG_5,
-				BPF_REG_7, BPF_REG_8, BPF_REG_9, TCALL_CNT,
-				BPF_REG_2, BPF_REG_FP};
-	int i, reg_len = sizeof(stack_regs);
-
-	for (i = 0 ; i < reg_len ; i++) {
-		if (bpf_reg == stack_regs[i])
-			return true;
-	}
-	return false;
+	return reg < 0;
 }
 
-static inline void emit_a32_mov_i(const u8 dst, const u32 val,
-				  bool dstk, struct jit_ctx *ctx)
+/* If a BPF register is on the stack (stk is true), load it to the
+ * supplied temporary register and return the temporary register
+ * for subsequent operations, otherwise just use the CPU register.
+ */
+static s8 arm_bpf_get_reg32(s8 reg, s8 tmp, struct jit_ctx *ctx)
 {
-	const u8 *tmp = bpf2a32[TMP_REG_1];
+	if (is_stacked(reg)) {
+		emit(ARM_LDR_I(tmp, ARM_FP, EBPF_SCRATCH_TO_ARM_FP(reg)), ctx);
+		reg = tmp;
+	}
+	return reg;
+}
 
-	if (dstk) {
+static const s8 *arm_bpf_get_reg64(const s8 *reg, const s8 *tmp,
+				   struct jit_ctx *ctx)
+{
+	if (is_stacked(reg[1])) {
+		if (__LINUX_ARM_ARCH__ >= 6 ||
+		    ctx->cpu_architecture >= CPU_ARCH_ARMv5TE) {
+			emit(ARM_LDRD_I(tmp[1], ARM_FP,
+					EBPF_SCRATCH_TO_ARM_FP(reg[1])), ctx);
+		} else {
+			emit(ARM_LDR_I(tmp[1], ARM_FP,
+				       EBPF_SCRATCH_TO_ARM_FP(reg[1])), ctx);
+			emit(ARM_LDR_I(tmp[0], ARM_FP,
+				       EBPF_SCRATCH_TO_ARM_FP(reg[0])), ctx);
+		}
+		reg = tmp;
+	}
+	return reg;
+}
+
+/* If a BPF register is on the stack (stk is true), save the register
+ * back to the stack.  If the source register is not the same, then
+ * move it into the correct register.
+ */
+static void arm_bpf_put_reg32(s8 reg, s8 src, struct jit_ctx *ctx)
+{
+	if (is_stacked(reg))
+		emit(ARM_STR_I(src, ARM_FP, EBPF_SCRATCH_TO_ARM_FP(reg)), ctx);
+	else if (reg != src)
+		emit(ARM_MOV_R(reg, src), ctx);
+}
+
+static void arm_bpf_put_reg64(const s8 *reg, const s8 *src,
+			      struct jit_ctx *ctx)
+{
+	if (is_stacked(reg[1])) {
+		if (__LINUX_ARM_ARCH__ >= 6 ||
+		    ctx->cpu_architecture >= CPU_ARCH_ARMv5TE) {
+			emit(ARM_STRD_I(src[1], ARM_FP,
+				       EBPF_SCRATCH_TO_ARM_FP(reg[1])), ctx);
+		} else {
+			emit(ARM_STR_I(src[1], ARM_FP,
+				       EBPF_SCRATCH_TO_ARM_FP(reg[1])), ctx);
+			emit(ARM_STR_I(src[0], ARM_FP,
+				       EBPF_SCRATCH_TO_ARM_FP(reg[0])), ctx);
+		}
+	} else {
+		if (reg[1] != src[1])
+			emit(ARM_MOV_R(reg[1], src[1]), ctx);
+		if (reg[0] != src[0])
+			emit(ARM_MOV_R(reg[0], src[0]), ctx);
+	}
+}
+
+static inline void emit_a32_mov_i(const s8 dst, const u32 val,
+				  struct jit_ctx *ctx)
+{
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+
+	if (is_stacked(dst)) {
 		emit_mov_i(tmp[1], val, ctx);
-		emit(ARM_STR_I(tmp[1], ARM_SP, STACK_VAR(dst)), ctx);
+		arm_bpf_put_reg32(dst, tmp[1], ctx);
 	} else {
 		emit_mov_i(dst, val, ctx);
 	}
 }
 
+static void emit_a32_mov_i64(const s8 dst[], u64 val, struct jit_ctx *ctx)
+{
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *rd = is_stacked(dst_lo) ? tmp : dst;
+
+	emit_mov_i(rd[1], (u32)val, ctx);
+	emit_mov_i(rd[0], val >> 32, ctx);
+
+	arm_bpf_put_reg64(dst, rd, ctx);
+}
+
 /* Sign extended move */
-static inline void emit_a32_mov_i64(const bool is64, const u8 dst[],
-				  const u32 val, bool dstk,
-				  struct jit_ctx *ctx) {
-	u32 hi = 0;
+static inline void emit_a32_mov_se_i64(const bool is64, const s8 dst[],
+				       const u32 val, struct jit_ctx *ctx) {
+	u64 val64 = val;
 
 	if (is64 && (val & (1<<31)))
-		hi = (u32)~0;
-	emit_a32_mov_i(dst_lo, val, dstk, ctx);
-	emit_a32_mov_i(dst_hi, hi, dstk, ctx);
+		val64 |= 0xffffffff00000000ULL;
+	emit_a32_mov_i64(dst, val64, ctx);
 }
 
 static inline void emit_a32_add_r(const u8 dst, const u8 src,
@@ -521,75 +699,94 @@ static inline void emit_alu_r(const u8 dst, const u8 src, const bool is64,
 /* ALU operation (32 bit)
  * dst = dst (op) src
  */
-static inline void emit_a32_alu_r(const u8 dst, const u8 src,
-				  bool dstk, bool sstk,
+static inline void emit_a32_alu_r(const s8 dst, const s8 src,
 				  struct jit_ctx *ctx, const bool is64,
 				  const bool hi, const u8 op) {
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	u8 rn = sstk ? tmp[1] : src;
-
-	if (sstk)
-		emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src)), ctx);
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	s8 rn, rd;
 
+	rn = arm_bpf_get_reg32(src, tmp[1], ctx);
+	rd = arm_bpf_get_reg32(dst, tmp[0], ctx);
 	/* ALU operation */
-	if (dstk) {
-		emit(ARM_LDR_I(tmp[0], ARM_SP, STACK_VAR(dst)), ctx);
-		emit_alu_r(tmp[0], rn, is64, hi, op, ctx);
-		emit(ARM_STR_I(tmp[0], ARM_SP, STACK_VAR(dst)), ctx);
-	} else {
-		emit_alu_r(dst, rn, is64, hi, op, ctx);
-	}
+	emit_alu_r(rd, rn, is64, hi, op, ctx);
+	arm_bpf_put_reg32(dst, rd, ctx);
 }
 
 /* ALU operation (64 bit) */
-static inline void emit_a32_alu_r64(const bool is64, const u8 dst[],
-				  const u8 src[], bool dstk,
-				  bool sstk, struct jit_ctx *ctx,
+static inline void emit_a32_alu_r64(const bool is64, const s8 dst[],
+				  const s8 src[], struct jit_ctx *ctx,
 				  const u8 op) {
-	emit_a32_alu_r(dst_lo, src_lo, dstk, sstk, ctx, is64, false, op);
-	if (is64)
-		emit_a32_alu_r(dst_hi, src_hi, dstk, sstk, ctx, is64, true, op);
-	else
-		emit_a32_mov_i(dst_hi, 0, dstk, ctx);
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *rd;
+
+	rd = arm_bpf_get_reg64(dst, tmp, ctx);
+	if (is64) {
+		const s8 *rs;
+
+		rs = arm_bpf_get_reg64(src, tmp2, ctx);
+
+		/* ALU operation */
+		emit_alu_r(rd[1], rs[1], true, false, op, ctx);
+		emit_alu_r(rd[0], rs[0], true, true, op, ctx);
+	} else {
+		s8 rs;
+
+		rs = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
+
+		/* ALU operation */
+		emit_alu_r(rd[1], rs, true, false, op, ctx);
+		emit_a32_mov_i(rd[0], 0, ctx);
+	}
+
+	arm_bpf_put_reg64(dst, rd, ctx);
 }
 
-/* dst = imm (4 bytes)*/
-static inline void emit_a32_mov_r(const u8 dst, const u8 src,
-				  bool dstk, bool sstk,
+/* dst = src (4 bytes)*/
+static inline void emit_a32_mov_r(const s8 dst, const s8 src,
 				  struct jit_ctx *ctx) {
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	u8 rt = sstk ? tmp[0] : src;
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	s8 rt;
 
-	if (sstk)
-		emit(ARM_LDR_I(tmp[0], ARM_SP, STACK_VAR(src)), ctx);
-	if (dstk)
-		emit(ARM_STR_I(rt, ARM_SP, STACK_VAR(dst)), ctx);
-	else
-		emit(ARM_MOV_R(dst, rt), ctx);
+	rt = arm_bpf_get_reg32(src, tmp[0], ctx);
+	arm_bpf_put_reg32(dst, rt, ctx);
 }
 
 /* dst = src */
-static inline void emit_a32_mov_r64(const bool is64, const u8 dst[],
-				  const u8 src[], bool dstk,
-				  bool sstk, struct jit_ctx *ctx) {
-	emit_a32_mov_r(dst_lo, src_lo, dstk, sstk, ctx);
-	if (is64) {
-		/* complete 8 byte move */
-		emit_a32_mov_r(dst_hi, src_hi, dstk, sstk, ctx);
-	} else {
+static inline void emit_a32_mov_r64(const bool is64, const s8 dst[],
+				  const s8 src[],
+				  struct jit_ctx *ctx) {
+	if (!is64) {
+		emit_a32_mov_r(dst_lo, src_lo, ctx);
 		/* Zero out high 4 bytes */
-		emit_a32_mov_i(dst_hi, 0, dstk, ctx);
+		emit_a32_mov_i(dst_hi, 0, ctx);
+	} else if (__LINUX_ARM_ARCH__ < 6 &&
+		   ctx->cpu_architecture < CPU_ARCH_ARMv5TE) {
+		/* complete 8 byte move */
+		emit_a32_mov_r(dst_lo, src_lo, ctx);
+		emit_a32_mov_r(dst_hi, src_hi, ctx);
+	} else if (is_stacked(src_lo) && is_stacked(dst_lo)) {
+		const u8 *tmp = bpf2a32[TMP_REG_1];
+
+		emit(ARM_LDRD_I(tmp[1], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(src_lo)), ctx);
+		emit(ARM_STRD_I(tmp[1], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(dst_lo)), ctx);
+	} else if (is_stacked(src_lo)) {
+		emit(ARM_LDRD_I(dst[1], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(src_lo)), ctx);
+	} else if (is_stacked(dst_lo)) {
+		emit(ARM_STRD_I(src[1], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(dst_lo)), ctx);
+	} else {
+		emit(ARM_MOV_R(dst[0], src[0]), ctx);
+		emit(ARM_MOV_R(dst[1], src[1]), ctx);
 	}
 }
 
 /* Shift operations */
-static inline void emit_a32_alu_i(const u8 dst, const u32 val, bool dstk,
+static inline void emit_a32_alu_i(const s8 dst, const u32 val,
 				struct jit_ctx *ctx, const u8 op) {
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	u8 rd = dstk ? tmp[0] : dst;
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	s8 rd;
 
-	if (dstk)
-		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst)), ctx);
+	rd = arm_bpf_get_reg32(dst, tmp[0], ctx);
 
 	/* Do shift operation */
 	switch (op) {
@@ -604,303 +801,245 @@ static inline void emit_a32_alu_i(const u8 dst, const u32 val, bool dstk,
 		break;
 	}
 
-	if (dstk)
-		emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst)), ctx);
+	arm_bpf_put_reg32(dst, rd, ctx);
 }
 
 /* dst = ~dst (64 bit) */
-static inline void emit_a32_neg64(const u8 dst[], bool dstk,
+static inline void emit_a32_neg64(const s8 dst[],
 				struct jit_ctx *ctx){
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	u8 rd = dstk ? tmp[1] : dst[1];
-	u8 rm = dstk ? tmp[0] : dst[0];
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *rd;
 
 	/* Setup Operand */
-	if (dstk) {
-		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
+	rd = arm_bpf_get_reg64(dst, tmp, ctx);
 
 	/* Do Negate Operation */
-	emit(ARM_RSBS_I(rd, rd, 0), ctx);
-	emit(ARM_RSC_I(rm, rm, 0), ctx);
+	emit(ARM_RSBS_I(rd[1], rd[1], 0), ctx);
+	emit(ARM_RSC_I(rd[0], rd[0], 0), ctx);
 
-	if (dstk) {
-		emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
+	arm_bpf_put_reg64(dst, rd, ctx);
 }
 
 /* dst = dst << src */
-static inline void emit_a32_lsh_r64(const u8 dst[], const u8 src[], bool dstk,
-				    bool sstk, struct jit_ctx *ctx) {
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
+static inline void emit_a32_lsh_r64(const s8 dst[], const s8 src[],
+				    struct jit_ctx *ctx) {
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *rd;
+	s8 rt;
 
 	/* Setup Operands */
-	u8 rt = sstk ? tmp2[1] : src_lo;
-	u8 rd = dstk ? tmp[1] : dst_lo;
-	u8 rm = dstk ? tmp[0] : dst_hi;
-
-	if (sstk)
-		emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx);
-	if (dstk) {
-		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
+	rt = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
+	rd = arm_bpf_get_reg64(dst, tmp, ctx);
 
 	/* Do LSH operation */
 	emit(ARM_SUB_I(ARM_IP, rt, 32), ctx);
 	emit(ARM_RSB_I(tmp2[0], rt, 32), ctx);
-	emit(ARM_MOV_SR(ARM_LR, rm, SRTYPE_ASL, rt), ctx);
-	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd, SRTYPE_ASL, ARM_IP), ctx);
-	emit(ARM_ORR_SR(ARM_IP, ARM_LR, rd, SRTYPE_LSR, tmp2[0]), ctx);
-	emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_ASL, rt), ctx);
+	emit(ARM_MOV_SR(ARM_LR, rd[0], SRTYPE_ASL, rt), ctx);
+	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[1], SRTYPE_ASL, ARM_IP), ctx);
+	emit(ARM_ORR_SR(ARM_IP, ARM_LR, rd[1], SRTYPE_LSR, tmp2[0]), ctx);
+	emit(ARM_MOV_SR(ARM_LR, rd[1], SRTYPE_ASL, rt), ctx);
 
-	if (dstk) {
-		emit(ARM_STR_I(ARM_LR, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	} else {
-		emit(ARM_MOV_R(rd, ARM_LR), ctx);
-		emit(ARM_MOV_R(rm, ARM_IP), ctx);
-	}
+	arm_bpf_put_reg32(dst_lo, ARM_LR, ctx);
+	arm_bpf_put_reg32(dst_hi, ARM_IP, ctx);
 }
 
 /* dst = dst >> src (signed)*/
-static inline void emit_a32_arsh_r64(const u8 dst[], const u8 src[], bool dstk,
-				    bool sstk, struct jit_ctx *ctx) {
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
-	/* Setup Operands */
-	u8 rt = sstk ? tmp2[1] : src_lo;
-	u8 rd = dstk ? tmp[1] : dst_lo;
-	u8 rm = dstk ? tmp[0] : dst_hi;
+static inline void emit_a32_arsh_r64(const s8 dst[], const s8 src[],
+				     struct jit_ctx *ctx) {
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *rd;
+	s8 rt;
 
-	if (sstk)
-		emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx);
-	if (dstk) {
-		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
+	/* Setup Operands */
+	rt = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
+	rd = arm_bpf_get_reg64(dst, tmp, ctx);
 
 	/* Do the ARSH operation */
 	emit(ARM_RSB_I(ARM_IP, rt, 32), ctx);
 	emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx);
-	emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_LSR, rt), ctx);
-	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx);
+	emit(ARM_MOV_SR(ARM_LR, rd[1], SRTYPE_LSR, rt), ctx);
+	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[0], SRTYPE_ASL, ARM_IP), ctx);
 	_emit(ARM_COND_MI, ARM_B(0), ctx);
-	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASR, tmp2[0]), ctx);
-	emit(ARM_MOV_SR(ARM_IP, rm, SRTYPE_ASR, rt), ctx);
-	if (dstk) {
-		emit(ARM_STR_I(ARM_LR, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	} else {
-		emit(ARM_MOV_R(rd, ARM_LR), ctx);
-		emit(ARM_MOV_R(rm, ARM_IP), ctx);
-	}
+	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[0], SRTYPE_ASR, tmp2[0]), ctx);
+	emit(ARM_MOV_SR(ARM_IP, rd[0], SRTYPE_ASR, rt), ctx);
+
+	arm_bpf_put_reg32(dst_lo, ARM_LR, ctx);
+	arm_bpf_put_reg32(dst_hi, ARM_IP, ctx);
 }
 
 /* dst = dst >> src */
-static inline void emit_a32_rsh_r64(const u8 dst[], const u8 src[], bool dstk,
-				     bool sstk, struct jit_ctx *ctx) {
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
-	/* Setup Operands */
-	u8 rt = sstk ? tmp2[1] : src_lo;
-	u8 rd = dstk ? tmp[1] : dst_lo;
-	u8 rm = dstk ? tmp[0] : dst_hi;
+static inline void emit_a32_rsh_r64(const s8 dst[], const s8 src[],
+				    struct jit_ctx *ctx) {
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *rd;
+	s8 rt;
 
-	if (sstk)
-		emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx);
-	if (dstk) {
-		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
+	/* Setup Operands */
+	rt = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
+	rd = arm_bpf_get_reg64(dst, tmp, ctx);
 
 	/* Do RSH operation */
 	emit(ARM_RSB_I(ARM_IP, rt, 32), ctx);
 	emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx);
-	emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_LSR, rt), ctx);
-	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx);
-	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_LSR, tmp2[0]), ctx);
-	emit(ARM_MOV_SR(ARM_IP, rm, SRTYPE_LSR, rt), ctx);
-	if (dstk) {
-		emit(ARM_STR_I(ARM_LR, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	} else {
-		emit(ARM_MOV_R(rd, ARM_LR), ctx);
-		emit(ARM_MOV_R(rm, ARM_IP), ctx);
-	}
+	emit(ARM_MOV_SR(ARM_LR, rd[1], SRTYPE_LSR, rt), ctx);
+	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[0], SRTYPE_ASL, ARM_IP), ctx);
+	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[0], SRTYPE_LSR, tmp2[0]), ctx);
+	emit(ARM_MOV_SR(ARM_IP, rd[0], SRTYPE_LSR, rt), ctx);
+
+	arm_bpf_put_reg32(dst_lo, ARM_LR, ctx);
+	arm_bpf_put_reg32(dst_hi, ARM_IP, ctx);
 }
 
 /* dst = dst << val */
-static inline void emit_a32_lsh_i64(const u8 dst[], bool dstk,
-				     const u32 val, struct jit_ctx *ctx){
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
-	/* Setup operands */
-	u8 rd = dstk ? tmp[1] : dst_lo;
-	u8 rm = dstk ? tmp[0] : dst_hi;
+static inline void emit_a32_lsh_i64(const s8 dst[],
+				    const u32 val, struct jit_ctx *ctx){
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *rd;
 
-	if (dstk) {
-		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
+	/* Setup operands */
+	rd = arm_bpf_get_reg64(dst, tmp, ctx);
 
 	/* Do LSH operation */
 	if (val < 32) {
-		emit(ARM_MOV_SI(tmp2[0], rm, SRTYPE_ASL, val), ctx);
-		emit(ARM_ORR_SI(rm, tmp2[0], rd, SRTYPE_LSR, 32 - val), ctx);
-		emit(ARM_MOV_SI(rd, rd, SRTYPE_ASL, val), ctx);
+		emit(ARM_MOV_SI(tmp2[0], rd[0], SRTYPE_ASL, val), ctx);
+		emit(ARM_ORR_SI(rd[0], tmp2[0], rd[1], SRTYPE_LSR, 32 - val), ctx);
+		emit(ARM_MOV_SI(rd[1], rd[1], SRTYPE_ASL, val), ctx);
 	} else {
 		if (val == 32)
-			emit(ARM_MOV_R(rm, rd), ctx);
+			emit(ARM_MOV_R(rd[0], rd[1]), ctx);
 		else
-			emit(ARM_MOV_SI(rm, rd, SRTYPE_ASL, val - 32), ctx);
-		emit(ARM_EOR_R(rd, rd, rd), ctx);
+			emit(ARM_MOV_SI(rd[0], rd[1], SRTYPE_ASL, val - 32), ctx);
+		emit(ARM_EOR_R(rd[1], rd[1], rd[1]), ctx);
 	}
 
-	if (dstk) {
-		emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
+	arm_bpf_put_reg64(dst, rd, ctx);
 }
 
 /* dst = dst >> val */
-static inline void emit_a32_rsh_i64(const u8 dst[], bool dstk,
+static inline void emit_a32_rsh_i64(const s8 dst[],
 				    const u32 val, struct jit_ctx *ctx) {
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
-	/* Setup operands */
-	u8 rd = dstk ? tmp[1] : dst_lo;
-	u8 rm = dstk ? tmp[0] : dst_hi;
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *rd;
 
-	if (dstk) {
-		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
+	/* Setup operands */
+	rd = arm_bpf_get_reg64(dst, tmp, ctx);
 
 	/* Do LSR operation */
 	if (val < 32) {
-		emit(ARM_MOV_SI(tmp2[1], rd, SRTYPE_LSR, val), ctx);
-		emit(ARM_ORR_SI(rd, tmp2[1], rm, SRTYPE_ASL, 32 - val), ctx);
-		emit(ARM_MOV_SI(rm, rm, SRTYPE_LSR, val), ctx);
+		emit(ARM_MOV_SI(tmp2[1], rd[1], SRTYPE_LSR, val), ctx);
+		emit(ARM_ORR_SI(rd[1], tmp2[1], rd[0], SRTYPE_ASL, 32 - val), ctx);
+		emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_LSR, val), ctx);
 	} else if (val == 32) {
-		emit(ARM_MOV_R(rd, rm), ctx);
-		emit(ARM_MOV_I(rm, 0), ctx);
+		emit(ARM_MOV_R(rd[1], rd[0]), ctx);
+		emit(ARM_MOV_I(rd[0], 0), ctx);
 	} else {
-		emit(ARM_MOV_SI(rd, rm, SRTYPE_LSR, val - 32), ctx);
-		emit(ARM_MOV_I(rm, 0), ctx);
+		emit(ARM_MOV_SI(rd[1], rd[0], SRTYPE_LSR, val - 32), ctx);
+		emit(ARM_MOV_I(rd[0], 0), ctx);
 	}
 
-	if (dstk) {
-		emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
+	arm_bpf_put_reg64(dst, rd, ctx);
 }
 
 /* dst = dst >> val (signed) */
-static inline void emit_a32_arsh_i64(const u8 dst[], bool dstk,
+static inline void emit_a32_arsh_i64(const s8 dst[],
 				     const u32 val, struct jit_ctx *ctx){
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
-	 /* Setup operands */
-	u8 rd = dstk ? tmp[1] : dst_lo;
-	u8 rm = dstk ? tmp[0] : dst_hi;
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *rd;
 
-	if (dstk) {
-		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
+	/* Setup operands */
+	rd = arm_bpf_get_reg64(dst, tmp, ctx);
 
 	/* Do ARSH operation */
 	if (val < 32) {
-		emit(ARM_MOV_SI(tmp2[1], rd, SRTYPE_LSR, val), ctx);
-		emit(ARM_ORR_SI(rd, tmp2[1], rm, SRTYPE_ASL, 32 - val), ctx);
-		emit(ARM_MOV_SI(rm, rm, SRTYPE_ASR, val), ctx);
+		emit(ARM_MOV_SI(tmp2[1], rd[1], SRTYPE_LSR, val), ctx);
+		emit(ARM_ORR_SI(rd[1], tmp2[1], rd[0], SRTYPE_ASL, 32 - val), ctx);
+		emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_ASR, val), ctx);
 	} else if (val == 32) {
-		emit(ARM_MOV_R(rd, rm), ctx);
-		emit(ARM_MOV_SI(rm, rm, SRTYPE_ASR, 31), ctx);
+		emit(ARM_MOV_R(rd[1], rd[0]), ctx);
+		emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_ASR, 31), ctx);
 	} else {
-		emit(ARM_MOV_SI(rd, rm, SRTYPE_ASR, val - 32), ctx);
-		emit(ARM_MOV_SI(rm, rm, SRTYPE_ASR, 31), ctx);
+		emit(ARM_MOV_SI(rd[1], rd[0], SRTYPE_ASR, val - 32), ctx);
+		emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_ASR, 31), ctx);
 	}
 
-	if (dstk) {
-		emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
+	arm_bpf_put_reg64(dst, rd, ctx);
 }
 
-static inline void emit_a32_mul_r64(const u8 dst[], const u8 src[], bool dstk,
-				    bool sstk, struct jit_ctx *ctx) {
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
-	/* Setup operands for multiplication */
-	u8 rd = dstk ? tmp[1] : dst_lo;
-	u8 rm = dstk ? tmp[0] : dst_hi;
-	u8 rt = sstk ? tmp2[1] : src_lo;
-	u8 rn = sstk ? tmp2[0] : src_hi;
+static inline void emit_a32_mul_r64(const s8 dst[], const s8 src[],
+				    struct jit_ctx *ctx) {
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *rd, *rt;
 
-	if (dstk) {
-		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
-	if (sstk) {
-		emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx);
-		emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_hi)), ctx);
-	}
+	/* Setup operands for multiplication */
+	rd = arm_bpf_get_reg64(dst, tmp, ctx);
+	rt = arm_bpf_get_reg64(src, tmp2, ctx);
 
 	/* Do Multiplication */
-	emit(ARM_MUL(ARM_IP, rd, rn), ctx);
-	emit(ARM_MUL(ARM_LR, rm, rt), ctx);
+	emit(ARM_MUL(ARM_IP, rd[1], rt[0]), ctx);
+	emit(ARM_MUL(ARM_LR, rd[0], rt[1]), ctx);
 	emit(ARM_ADD_R(ARM_LR, ARM_IP, ARM_LR), ctx);
 
-	emit(ARM_UMULL(ARM_IP, rm, rd, rt), ctx);
-	emit(ARM_ADD_R(rm, ARM_LR, rm), ctx);
-	if (dstk) {
-		emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	} else {
-		emit(ARM_MOV_R(rd, ARM_IP), ctx);
-	}
+	emit(ARM_UMULL(ARM_IP, rd[0], rd[1], rt[1]), ctx);
+	emit(ARM_ADD_R(rd[0], ARM_LR, rd[0]), ctx);
+
+	arm_bpf_put_reg32(dst_lo, ARM_IP, ctx);
+	arm_bpf_put_reg32(dst_hi, rd[0], ctx);
 }
 
 /* *(size *)(dst + off) = src */
-static inline void emit_str_r(const u8 dst, const u8 src, bool dstk,
-			      const s32 off, struct jit_ctx *ctx, const u8 sz){
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	u8 rd = dstk ? tmp[1] : dst;
+static inline void emit_str_r(const s8 dst, const s8 src[],
+			      s32 off, struct jit_ctx *ctx, const u8 sz){
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	s32 off_max;
+	s8 rd;
 
-	if (dstk)
-		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst)), ctx);
-	if (off) {
-		emit_a32_mov_i(tmp[0], off, false, ctx);
-		emit(ARM_ADD_R(tmp[0], rd, tmp[0]), ctx);
+	rd = arm_bpf_get_reg32(dst, tmp[1], ctx);
+
+	if (sz == BPF_H)
+		off_max = 0xff;
+	else
+		off_max = 0xfff;
+
+	if (off < 0 || off > off_max) {
+		emit_a32_mov_i(tmp[0], off, ctx);
+		emit(ARM_ADD_R(tmp[0], tmp[0], rd), ctx);
 		rd = tmp[0];
+		off = 0;
 	}
 	switch (sz) {
-	case BPF_W:
-		/* Store a Word */
-		emit(ARM_STR_I(src, rd, 0), ctx);
+	case BPF_B:
+		/* Store a Byte */
+		emit(ARM_STRB_I(src_lo, rd, off), ctx);
 		break;
 	case BPF_H:
 		/* Store a HalfWord */
-		emit(ARM_STRH_I(src, rd, 0), ctx);
+		emit(ARM_STRH_I(src_lo, rd, off), ctx);
 		break;
-	case BPF_B:
-		/* Store a Byte */
-		emit(ARM_STRB_I(src, rd, 0), ctx);
+	case BPF_W:
+		/* Store a Word */
+		emit(ARM_STR_I(src_lo, rd, off), ctx);
+		break;
+	case BPF_DW:
+		/* Store a Double Word */
+		emit(ARM_STR_I(src_lo, rd, off), ctx);
+		emit(ARM_STR_I(src_hi, rd, off + 4), ctx);
 		break;
 	}
 }
 
 /* dst = *(size*)(src + off) */
-static inline void emit_ldx_r(const u8 dst[], const u8 src, bool dstk,
+static inline void emit_ldx_r(const s8 dst[], const s8 src,
 			      s32 off, struct jit_ctx *ctx, const u8 sz){
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	const u8 *rd = dstk ? tmp : dst;
-	u8 rm = src;
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *rd = is_stacked(dst_lo) ? tmp : dst;
+	s8 rm = src;
 	s32 off_max;
 
 	if (sz == BPF_H)
@@ -909,7 +1048,7 @@ static inline void emit_ldx_r(const u8 dst[], const u8 src, bool dstk,
 		off_max = 0xfff;
 
 	if (off < 0 || off > off_max) {
-		emit_a32_mov_i(tmp[0], off, false, ctx);
+		emit_a32_mov_i(tmp[0], off, ctx);
 		emit(ARM_ADD_R(tmp[0], tmp[0], src), ctx);
 		rm = tmp[0];
 		off = 0;
@@ -921,17 +1060,17 @@ static inline void emit_ldx_r(const u8 dst[], const u8 src, bool dstk,
 	case BPF_B:
 		/* Load a Byte */
 		emit(ARM_LDRB_I(rd[1], rm, off), ctx);
-		emit_a32_mov_i(dst[0], 0, dstk, ctx);
+		emit_a32_mov_i(rd[0], 0, ctx);
 		break;
 	case BPF_H:
 		/* Load a HalfWord */
 		emit(ARM_LDRH_I(rd[1], rm, off), ctx);
-		emit_a32_mov_i(dst[0], 0, dstk, ctx);
+		emit_a32_mov_i(rd[0], 0, ctx);
 		break;
 	case BPF_W:
 		/* Load a Word */
 		emit(ARM_LDR_I(rd[1], rm, off), ctx);
-		emit_a32_mov_i(dst[0], 0, dstk, ctx);
+		emit_a32_mov_i(rd[0], 0, ctx);
 		break;
 	case BPF_DW:
 		/* Load a Double Word */
@@ -939,10 +1078,7 @@ static inline void emit_ldx_r(const u8 dst[], const u8 src, bool dstk,
 		emit(ARM_LDR_I(rd[0], rm, off + 4), ctx);
 		break;
 	}
-	if (dstk)
-		emit(ARM_STR_I(rd[1], ARM_SP, STACK_VAR(dst[1])), ctx);
-	if (dstk && sz == BPF_DW)
-		emit(ARM_STR_I(rd[0], ARM_SP, STACK_VAR(dst[0])), ctx);
+	arm_bpf_put_reg64(dst, rd, ctx);
 }
 
 /* Arithmatic Operation */
@@ -981,64 +1117,66 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 {
 
 	/* bpf_tail_call(void *prog_ctx, struct bpf_array *array, u64 index) */
-	const u8 *r2 = bpf2a32[BPF_REG_2];
-	const u8 *r3 = bpf2a32[BPF_REG_3];
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
-	const u8 *tcc = bpf2a32[TCALL_CNT];
+	const s8 *r2 = bpf2a32[BPF_REG_2];
+	const s8 *r3 = bpf2a32[BPF_REG_3];
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *tcc = bpf2a32[TCALL_CNT];
+	const s8 *tc;
 	const int idx0 = ctx->idx;
 #define cur_offset (ctx->idx - idx0)
 #define jmp_offset (out_offset - (cur_offset) - 2)
-	u32 off, lo, hi;
+	u32 lo, hi;
+	s8 r_array, r_index;
+	int off;
 
 	/* if (index >= array->map.max_entries)
 	 *	goto out;
 	 */
+	BUILD_BUG_ON(offsetof(struct bpf_array, map.max_entries) >
+		     ARM_INST_LDST__IMM12);
 	off = offsetof(struct bpf_array, map.max_entries);
-	/* array->map.max_entries */
-	emit_a32_mov_i(tmp[1], off, false, ctx);
-	emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r2[1])), ctx);
-	emit(ARM_LDR_R(tmp[1], tmp2[1], tmp[1]), ctx);
+	r_array = arm_bpf_get_reg32(r2[1], tmp2[0], ctx);
 	/* index is 32-bit for arrays */
-	emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r3[1])), ctx);
+	r_index = arm_bpf_get_reg32(r3[1], tmp2[1], ctx);
+	/* array->map.max_entries */
+	emit(ARM_LDR_I(tmp[1], r_array, off), ctx);
 	/* index >= array->map.max_entries */
-	emit(ARM_CMP_R(tmp2[1], tmp[1]), ctx);
+	emit(ARM_CMP_R(r_index, tmp[1]), ctx);
 	_emit(ARM_COND_CS, ARM_B(jmp_offset), ctx);
 
+	/* tmp2[0] = array, tmp2[1] = index */
+
 	/* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
 	 *	goto out;
 	 * tail_call_cnt++;
 	 */
 	lo = (u32)MAX_TAIL_CALL_CNT;
 	hi = (u32)((u64)MAX_TAIL_CALL_CNT >> 32);
-	emit(ARM_LDR_I(tmp[1], ARM_SP, STACK_VAR(tcc[1])), ctx);
-	emit(ARM_LDR_I(tmp[0], ARM_SP, STACK_VAR(tcc[0])), ctx);
-	emit(ARM_CMP_I(tmp[0], hi), ctx);
-	_emit(ARM_COND_EQ, ARM_CMP_I(tmp[1], lo), ctx);
+	tc = arm_bpf_get_reg64(tcc, tmp, ctx);
+	emit(ARM_CMP_I(tc[0], hi), ctx);
+	_emit(ARM_COND_EQ, ARM_CMP_I(tc[1], lo), ctx);
 	_emit(ARM_COND_HI, ARM_B(jmp_offset), ctx);
-	emit(ARM_ADDS_I(tmp[1], tmp[1], 1), ctx);
-	emit(ARM_ADC_I(tmp[0], tmp[0], 0), ctx);
-	emit(ARM_STR_I(tmp[1], ARM_SP, STACK_VAR(tcc[1])), ctx);
-	emit(ARM_STR_I(tmp[0], ARM_SP, STACK_VAR(tcc[0])), ctx);
+	emit(ARM_ADDS_I(tc[1], tc[1], 1), ctx);
+	emit(ARM_ADC_I(tc[0], tc[0], 0), ctx);
+	arm_bpf_put_reg64(tcc, tmp, ctx);
 
 	/* prog = array->ptrs[index]
 	 * if (prog == NULL)
 	 *	goto out;
 	 */
-	off = offsetof(struct bpf_array, ptrs);
-	emit_a32_mov_i(tmp[1], off, false, ctx);
-	emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r2[1])), ctx);
-	emit(ARM_ADD_R(tmp[1], tmp2[1], tmp[1]), ctx);
-	emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r3[1])), ctx);
-	emit(ARM_MOV_SI(tmp[0], tmp2[1], SRTYPE_ASL, 2), ctx);
-	emit(ARM_LDR_R(tmp[1], tmp[1], tmp[0]), ctx);
+	BUILD_BUG_ON(imm8m(offsetof(struct bpf_array, ptrs)) < 0);
+	off = imm8m(offsetof(struct bpf_array, ptrs));
+	emit(ARM_ADD_I(tmp[1], r_array, off), ctx);
+	emit(ARM_LDR_R_SI(tmp[1], tmp[1], r_index, SRTYPE_ASL, 2), ctx);
 	emit(ARM_CMP_I(tmp[1], 0), ctx);
 	_emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx);
 
 	/* goto *(prog->bpf_func + prologue_size); */
+	BUILD_BUG_ON(offsetof(struct bpf_prog, bpf_func) >
+		     ARM_INST_LDST__IMM12);
 	off = offsetof(struct bpf_prog, bpf_func);
-	emit_a32_mov_i(tmp2[1], off, false, ctx);
-	emit(ARM_LDR_R(tmp[1], tmp[1], tmp2[1]), ctx);
+	emit(ARM_LDR_I(tmp[1], tmp[1], off), ctx);
 	emit(ARM_ADD_I(tmp[1], tmp[1], ctx->prologue_bytes), ctx);
 	emit_bx_r(tmp[1], ctx);
 
@@ -1059,7 +1197,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 static inline void emit_rev16(const u8 rd, const u8 rn, struct jit_ctx *ctx)
 {
 #if __LINUX_ARM_ARCH__ < 6
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
 
 	emit(ARM_AND_I(tmp2[1], rn, 0xff), ctx);
 	emit(ARM_MOV_SI(tmp2[0], rn, SRTYPE_LSR, 8), ctx);
@@ -1074,7 +1212,7 @@ static inline void emit_rev16(const u8 rd, const u8 rn, struct jit_ctx *ctx)
 static inline void emit_rev32(const u8 rd, const u8 rn, struct jit_ctx *ctx)
 {
 #if __LINUX_ARM_ARCH__ < 6
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
 
 	emit(ARM_AND_I(tmp2[1], rn, 0xff), ctx);
 	emit(ARM_MOV_SI(tmp2[0], rn, SRTYPE_LSR, 24), ctx);
@@ -1094,28 +1232,27 @@ static inline void emit_rev32(const u8 rd, const u8 rn, struct jit_ctx *ctx)
 }
 
 // push the scratch stack register on top of the stack
-static inline void emit_push_r64(const u8 src[], const u8 shift,
-		struct jit_ctx *ctx)
+static inline void emit_push_r64(const s8 src[], struct jit_ctx *ctx)
 {
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *rt;
 	u16 reg_set = 0;
 
-	emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(src[1]+shift)), ctx);
-	emit(ARM_LDR_I(tmp2[0], ARM_SP, STACK_VAR(src[0]+shift)), ctx);
+	rt = arm_bpf_get_reg64(src, tmp2, ctx);
 
-	reg_set = (1 << tmp2[1]) | (1 << tmp2[0]);
+	reg_set = (1 << rt[1]) | (1 << rt[0]);
 	emit(ARM_PUSH(reg_set), ctx);
 }
 
 static void build_prologue(struct jit_ctx *ctx)
 {
-	const u8 r0 = bpf2a32[BPF_REG_0][1];
-	const u8 r2 = bpf2a32[BPF_REG_1][1];
-	const u8 r3 = bpf2a32[BPF_REG_1][0];
-	const u8 r4 = bpf2a32[BPF_REG_6][1];
-	const u8 fplo = bpf2a32[BPF_REG_FP][1];
-	const u8 fphi = bpf2a32[BPF_REG_FP][0];
-	const u8 *tcc = bpf2a32[TCALL_CNT];
+	const s8 r0 = bpf2a32[BPF_REG_0][1];
+	const s8 r2 = bpf2a32[BPF_REG_1][1];
+	const s8 r3 = bpf2a32[BPF_REG_1][0];
+	const s8 r4 = bpf2a32[BPF_REG_6][1];
+	const s8 fplo = bpf2a32[BPF_REG_FP][1];
+	const s8 fphi = bpf2a32[BPF_REG_FP][0];
+	const s8 *tcc = bpf2a32[TCALL_CNT];
 
 	/* Save callee saved registers. */
 #ifdef CONFIG_FRAME_POINTER
@@ -1136,8 +1273,8 @@ static void build_prologue(struct jit_ctx *ctx)
 	emit(ARM_SUB_I(ARM_SP, ARM_SP, ctx->stack_size), ctx);
 
 	/* Set up BPF prog stack base register */
-	emit_a32_mov_r(fplo, ARM_IP, true, false, ctx);
-	emit_a32_mov_i(fphi, 0, true, ctx);
+	emit_a32_mov_r(fplo, ARM_IP, ctx);
+	emit_a32_mov_i(fphi, 0, ctx);
 
 	/* mov r4, 0 */
 	emit(ARM_MOV_I(r4, 0), ctx);
@@ -1146,8 +1283,8 @@ static void build_prologue(struct jit_ctx *ctx)
 	emit(ARM_MOV_R(r3, r4), ctx);
 	emit(ARM_MOV_R(r2, r0), ctx);
 	/* Initialize Tail Count */
-	emit(ARM_STR_I(r4, ARM_SP, STACK_VAR(tcc[0])), ctx);
-	emit(ARM_STR_I(r4, ARM_SP, STACK_VAR(tcc[1])), ctx);
+	emit(ARM_STR_I(r4, ARM_FP, EBPF_SCRATCH_TO_ARM_FP(tcc[0])), ctx);
+	emit(ARM_STR_I(r4, ARM_FP, EBPF_SCRATCH_TO_ARM_FP(tcc[1])), ctx);
 	/* end of prologue */
 }
 
@@ -1178,17 +1315,16 @@ static void build_epilogue(struct jit_ctx *ctx)
 static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 {
 	const u8 code = insn->code;
-	const u8 *dst = bpf2a32[insn->dst_reg];
-	const u8 *src = bpf2a32[insn->src_reg];
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *dst = bpf2a32[insn->dst_reg];
+	const s8 *src = bpf2a32[insn->src_reg];
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
 	const s16 off = insn->off;
 	const s32 imm = insn->imm;
 	const int i = insn - ctx->prog->insnsi;
 	const bool is64 = BPF_CLASS(code) == BPF_ALU64;
-	const bool dstk = is_on_stack(insn->dst_reg);
-	const bool sstk = is_on_stack(insn->src_reg);
-	u8 rd, rt, rm, rn;
+	const s8 *rd, *rs;
+	s8 rd_lo, rt, rm, rn;
 	s32 jmp_offset;
 
 #define check_imm(bits, imm) do {				\
@@ -1211,11 +1347,11 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_ALU64 | BPF_MOV | BPF_X:
 		switch (BPF_SRC(code)) {
 		case BPF_X:
-			emit_a32_mov_r64(is64, dst, src, dstk, sstk, ctx);
+			emit_a32_mov_r64(is64, dst, src, ctx);
 			break;
 		case BPF_K:
 			/* Sign-extend immediate value to destination reg */
-			emit_a32_mov_i64(is64, dst, imm, dstk, ctx);
+			emit_a32_mov_se_i64(is64, dst, imm, ctx);
 			break;
 		}
 		break;
@@ -1255,8 +1391,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_ALU64 | BPF_XOR | BPF_X:
 		switch (BPF_SRC(code)) {
 		case BPF_X:
-			emit_a32_alu_r64(is64, dst, src, dstk, sstk,
-					 ctx, BPF_OP(code));
+			emit_a32_alu_r64(is64, dst, src, ctx, BPF_OP(code));
 			break;
 		case BPF_K:
 			/* Move immediate value to the temporary register
@@ -1265,9 +1400,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			 * value into temporary reg and then it would be
 			 * safe to do the operation on it.
 			 */
-			emit_a32_mov_i64(is64, tmp2, imm, false, ctx);
-			emit_a32_alu_r64(is64, dst, tmp2, dstk, false,
-					 ctx, BPF_OP(code));
+			emit_a32_mov_se_i64(is64, tmp2, imm, ctx);
+			emit_a32_alu_r64(is64, dst, tmp2, ctx, BPF_OP(code));
 			break;
 		}
 		break;
@@ -1277,26 +1411,22 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_ALU | BPF_DIV | BPF_X:
 	case BPF_ALU | BPF_MOD | BPF_K:
 	case BPF_ALU | BPF_MOD | BPF_X:
-		rt = src_lo;
-		rd = dstk ? tmp2[1] : dst_lo;
-		if (dstk)
-			emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
+		rd_lo = arm_bpf_get_reg32(dst_lo, tmp2[1], ctx);
 		switch (BPF_SRC(code)) {
 		case BPF_X:
-			rt = sstk ? tmp2[0] : rt;
-			if (sstk)
-				emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)),
-				     ctx);
+			rt = arm_bpf_get_reg32(src_lo, tmp2[0], ctx);
 			break;
 		case BPF_K:
 			rt = tmp2[0];
-			emit_a32_mov_i(rt, imm, false, ctx);
+			emit_a32_mov_i(rt, imm, ctx);
+			break;
+		default:
+			rt = src_lo;
 			break;
 		}
-		emit_udivmod(rd, rd, rt, ctx, BPF_OP(code));
-		if (dstk)
-			emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit_a32_mov_i(dst_hi, 0, dstk, ctx);
+		emit_udivmod(rd_lo, rd_lo, rt, ctx, BPF_OP(code));
+		arm_bpf_put_reg32(dst_lo, rd_lo, ctx);
+		emit_a32_mov_i(dst_hi, 0, ctx);
 		break;
 	case BPF_ALU64 | BPF_DIV | BPF_K:
 	case BPF_ALU64 | BPF_DIV | BPF_X:
@@ -1310,54 +1440,54 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		if (unlikely(imm > 31))
 			return -EINVAL;
 		if (imm)
-			emit_a32_alu_i(dst_lo, imm, dstk, ctx, BPF_OP(code));
-		emit_a32_mov_i(dst_hi, 0, dstk, ctx);
+			emit_a32_alu_i(dst_lo, imm, ctx, BPF_OP(code));
+		emit_a32_mov_i(dst_hi, 0, ctx);
 		break;
 	/* dst = dst << imm */
 	case BPF_ALU64 | BPF_LSH | BPF_K:
 		if (unlikely(imm > 63))
 			return -EINVAL;
-		emit_a32_lsh_i64(dst, dstk, imm, ctx);
+		emit_a32_lsh_i64(dst, imm, ctx);
 		break;
 	/* dst = dst >> imm */
 	case BPF_ALU64 | BPF_RSH | BPF_K:
 		if (unlikely(imm > 63))
 			return -EINVAL;
-		emit_a32_rsh_i64(dst, dstk, imm, ctx);
+		emit_a32_rsh_i64(dst, imm, ctx);
 		break;
 	/* dst = dst << src */
 	case BPF_ALU64 | BPF_LSH | BPF_X:
-		emit_a32_lsh_r64(dst, src, dstk, sstk, ctx);
+		emit_a32_lsh_r64(dst, src, ctx);
 		break;
 	/* dst = dst >> src */
 	case BPF_ALU64 | BPF_RSH | BPF_X:
-		emit_a32_rsh_r64(dst, src, dstk, sstk, ctx);
+		emit_a32_rsh_r64(dst, src, ctx);
 		break;
 	/* dst = dst >> src (signed) */
 	case BPF_ALU64 | BPF_ARSH | BPF_X:
-		emit_a32_arsh_r64(dst, src, dstk, sstk, ctx);
+		emit_a32_arsh_r64(dst, src, ctx);
 		break;
 	/* dst = dst >> imm (signed) */
 	case BPF_ALU64 | BPF_ARSH | BPF_K:
 		if (unlikely(imm > 63))
 			return -EINVAL;
-		emit_a32_arsh_i64(dst, dstk, imm, ctx);
+		emit_a32_arsh_i64(dst, imm, ctx);
 		break;
 	/* dst = ~dst */
 	case BPF_ALU | BPF_NEG:
-		emit_a32_alu_i(dst_lo, 0, dstk, ctx, BPF_OP(code));
-		emit_a32_mov_i(dst_hi, 0, dstk, ctx);
+		emit_a32_alu_i(dst_lo, 0, ctx, BPF_OP(code));
+		emit_a32_mov_i(dst_hi, 0, ctx);
 		break;
 	/* dst = ~dst (64 bit) */
 	case BPF_ALU64 | BPF_NEG:
-		emit_a32_neg64(dst, dstk, ctx);
+		emit_a32_neg64(dst, ctx);
 		break;
 	/* dst = dst * src/imm */
 	case BPF_ALU64 | BPF_MUL | BPF_X:
 	case BPF_ALU64 | BPF_MUL | BPF_K:
 		switch (BPF_SRC(code)) {
 		case BPF_X:
-			emit_a32_mul_r64(dst, src, dstk, sstk, ctx);
+			emit_a32_mul_r64(dst, src, ctx);
 			break;
 		case BPF_K:
 			/* Move immediate value to the temporary register
@@ -1366,8 +1496,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			 * reg then it would be safe to do the operation
 			 * on it.
 			 */
-			emit_a32_mov_i64(is64, tmp2, imm, false, ctx);
-			emit_a32_mul_r64(dst, tmp2, dstk, false, ctx);
+			emit_a32_mov_se_i64(is64, tmp2, imm, ctx);
+			emit_a32_mul_r64(dst, tmp2, ctx);
 			break;
 		}
 		break;
@@ -1375,25 +1505,20 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	/* dst = htobe(dst) */
 	case BPF_ALU | BPF_END | BPF_FROM_LE:
 	case BPF_ALU | BPF_END | BPF_FROM_BE:
-		rd = dstk ? tmp[0] : dst_hi;
-		rt = dstk ? tmp[1] : dst_lo;
-		if (dstk) {
-			emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(dst_lo)), ctx);
-			emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_hi)), ctx);
-		}
+		rd = arm_bpf_get_reg64(dst, tmp, ctx);
 		if (BPF_SRC(code) == BPF_FROM_LE)
 			goto emit_bswap_uxt;
 		switch (imm) {
 		case 16:
-			emit_rev16(rt, rt, ctx);
+			emit_rev16(rd[1], rd[1], ctx);
 			goto emit_bswap_uxt;
 		case 32:
-			emit_rev32(rt, rt, ctx);
+			emit_rev32(rd[1], rd[1], ctx);
 			goto emit_bswap_uxt;
 		case 64:
-			emit_rev32(ARM_LR, rt, ctx);
-			emit_rev32(rt, rd, ctx);
-			emit(ARM_MOV_R(rd, ARM_LR), ctx);
+			emit_rev32(ARM_LR, rd[1], ctx);
+			emit_rev32(rd[1], rd[0], ctx);
+			emit(ARM_MOV_R(rd[0], ARM_LR), ctx);
 			break;
 		}
 		goto exit;
@@ -1402,36 +1527,30 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		case 16:
 			/* zero-extend 16 bits into 64 bits */
 #if __LINUX_ARM_ARCH__ < 6
-			emit_a32_mov_i(tmp2[1], 0xffff, false, ctx);
-			emit(ARM_AND_R(rt, rt, tmp2[1]), ctx);
+			emit_a32_mov_i(tmp2[1], 0xffff, ctx);
+			emit(ARM_AND_R(rd[1], rd[1], tmp2[1]), ctx);
 #else /* ARMv6+ */
-			emit(ARM_UXTH(rt, rt), ctx);
+			emit(ARM_UXTH(rd[1], rd[1]), ctx);
 #endif
-			emit(ARM_EOR_R(rd, rd, rd), ctx);
+			emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx);
 			break;
 		case 32:
 			/* zero-extend 32 bits into 64 bits */
-			emit(ARM_EOR_R(rd, rd, rd), ctx);
+			emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx);
 			break;
 		case 64:
 			/* nop */
 			break;
 		}
 exit:
-		if (dstk) {
-			emit(ARM_STR_I(rt, ARM_SP, STACK_VAR(dst_lo)), ctx);
-			emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_hi)), ctx);
-		}
+		arm_bpf_put_reg64(dst, rd, ctx);
 		break;
 	/* dst = imm64 */
 	case BPF_LD | BPF_IMM | BPF_DW:
 	{
-		const struct bpf_insn insn1 = insn[1];
-		u32 hi, lo = imm;
+		u64 val = (u32)imm | (u64)insn[1].imm << 32;
 
-		hi = insn1.imm;
-		emit_a32_mov_i(dst_lo, lo, dstk, ctx);
-		emit_a32_mov_i(dst_hi, hi, dstk, ctx);
+		emit_a32_mov_i64(dst, val, ctx);
 
 		return 1;
 	}
@@ -1440,10 +1559,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_LDX | BPF_MEM | BPF_H:
 	case BPF_LDX | BPF_MEM | BPF_B:
 	case BPF_LDX | BPF_MEM | BPF_DW:
-		rn = sstk ? tmp2[1] : src_lo;
-		if (sstk)
-			emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx);
-		emit_ldx_r(dst, rn, dstk, off, ctx, BPF_SIZE(code));
+		rn = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
+		emit_ldx_r(dst, rn, off, ctx, BPF_SIZE(code));
 		break;
 	/* ST: *(size *)(dst + off) = imm */
 	case BPF_ST | BPF_MEM | BPF_W:
@@ -1453,18 +1570,15 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		switch (BPF_SIZE(code)) {
 		case BPF_DW:
 			/* Sign-extend immediate value into temp reg */
-			emit_a32_mov_i64(true, tmp2, imm, false, ctx);
-			emit_str_r(dst_lo, tmp2[1], dstk, off, ctx, BPF_W);
-			emit_str_r(dst_lo, tmp2[0], dstk, off+4, ctx, BPF_W);
+			emit_a32_mov_se_i64(true, tmp2, imm, ctx);
 			break;
 		case BPF_W:
 		case BPF_H:
 		case BPF_B:
-			emit_a32_mov_i(tmp2[1], imm, false, ctx);
-			emit_str_r(dst_lo, tmp2[1], dstk, off, ctx,
-				   BPF_SIZE(code));
+			emit_a32_mov_i(tmp2[1], imm, ctx);
 			break;
 		}
+		emit_str_r(dst_lo, tmp2, off, ctx, BPF_SIZE(code));
 		break;
 	/* STX XADD: lock *(u32 *)(dst + off) += src */
 	case BPF_STX | BPF_XADD | BPF_W:
@@ -1476,25 +1590,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_STX | BPF_MEM | BPF_H:
 	case BPF_STX | BPF_MEM | BPF_B:
 	case BPF_STX | BPF_MEM | BPF_DW:
-	{
-		u8 sz = BPF_SIZE(code);
-
-		rn = sstk ? tmp2[1] : src_lo;
-		rm = sstk ? tmp2[0] : src_hi;
-		if (sstk) {
-			emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx);
-			emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(src_hi)), ctx);
-		}
-
-		/* Store the value */
-		if (BPF_SIZE(code) == BPF_DW) {
-			emit_str_r(dst_lo, rn, dstk, off, ctx, BPF_W);
-			emit_str_r(dst_lo, rm, dstk, off+4, ctx, BPF_W);
-		} else {
-			emit_str_r(dst_lo, rn, dstk, off, ctx, sz);
-		}
+		rs = arm_bpf_get_reg64(src, tmp2, ctx);
+		emit_str_r(dst_lo, rs, off, ctx, BPF_SIZE(code));
 		break;
-	}
 	/* PC += off if dst == src */
 	/* PC += off if dst > src */
 	/* PC += off if dst >= src */
@@ -1518,12 +1616,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_JMP | BPF_JSLT | BPF_X:
 	case BPF_JMP | BPF_JSLE | BPF_X:
 		/* Setup source registers */
-		rm = sstk ? tmp2[0] : src_hi;
-		rn = sstk ? tmp2[1] : src_lo;
-		if (sstk) {
-			emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx);
-			emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(src_hi)), ctx);
-		}
+		rm = arm_bpf_get_reg32(src_hi, tmp2[0], ctx);
+		rn = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
 		goto go_jmp;
 	/* PC += off if dst == imm */
 	/* PC += off if dst > imm */
@@ -1552,18 +1646,13 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		rm = tmp2[0];
 		rn = tmp2[1];
 		/* Sign-extend immediate value */
-		emit_a32_mov_i64(true, tmp2, imm, false, ctx);
+		emit_a32_mov_se_i64(true, tmp2, imm, ctx);
 go_jmp:
 		/* Setup destination register */
-		rd = dstk ? tmp[0] : dst_hi;
-		rt = dstk ? tmp[1] : dst_lo;
-		if (dstk) {
-			emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(dst_lo)), ctx);
-			emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_hi)), ctx);
-		}
+		rd = arm_bpf_get_reg64(dst, tmp, ctx);
 
 		/* Check for the condition */
-		emit_ar_r(rd, rt, rm, rn, ctx, BPF_OP(code));
+		emit_ar_r(rd[0], rd[1], rm, rn, ctx, BPF_OP(code));
 
 		/* Setup JUMP instruction */
 		jmp_offset = bpf2a32_offset(i+off, i, ctx);
@@ -1619,21 +1708,21 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	/* function call */
 	case BPF_JMP | BPF_CALL:
 	{
-		const u8 *r0 = bpf2a32[BPF_REG_0];
-		const u8 *r1 = bpf2a32[BPF_REG_1];
-		const u8 *r2 = bpf2a32[BPF_REG_2];
-		const u8 *r3 = bpf2a32[BPF_REG_3];
-		const u8 *r4 = bpf2a32[BPF_REG_4];
-		const u8 *r5 = bpf2a32[BPF_REG_5];
+		const s8 *r0 = bpf2a32[BPF_REG_0];
+		const s8 *r1 = bpf2a32[BPF_REG_1];
+		const s8 *r2 = bpf2a32[BPF_REG_2];
+		const s8 *r3 = bpf2a32[BPF_REG_3];
+		const s8 *r4 = bpf2a32[BPF_REG_4];
+		const s8 *r5 = bpf2a32[BPF_REG_5];
 		const u32 func = (u32)__bpf_call_base + (u32)imm;
 
-		emit_a32_mov_r64(true, r0, r1, false, false, ctx);
-		emit_a32_mov_r64(true, r1, r2, false, true, ctx);
-		emit_push_r64(r5, 0, ctx);
-		emit_push_r64(r4, 8, ctx);
-		emit_push_r64(r3, 16, ctx);
+		emit_a32_mov_r64(true, r0, r1, ctx);
+		emit_a32_mov_r64(true, r1, r2, ctx);
+		emit_push_r64(r5, ctx);
+		emit_push_r64(r4, ctx);
+		emit_push_r64(r3, ctx);
 
-		emit_a32_mov_i(tmp[1], func, false, ctx);
+		emit_a32_mov_i(tmp[1], func, ctx);
 		emit_blx_r(tmp[1], ctx);
 
 		emit(ARM_ADD_I(ARM_SP, ARM_SP, imm8m(24)), ctx); // callee clean
@@ -1745,6 +1834,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	memset(&ctx, 0, sizeof(ctx));
 	ctx.prog = prog;
+	ctx.cpu_architecture = cpu_architecture();
 
 	/* Not able to allocate memory for offsets[] , then
 	 * we must fall back to the interpreter
diff --git a/arch/arm/net/bpf_jit_32.h b/arch/arm/net/bpf_jit_32.h
index d5cf5f6208aa..f4e58bcdaa43 100644
--- a/arch/arm/net/bpf_jit_32.h
+++ b/arch/arm/net/bpf_jit_32.h
@@ -77,11 +77,14 @@
 #define ARM_INST_EOR_R		0x00200000
 #define ARM_INST_EOR_I		0x02200000
 
-#define ARM_INST_LDRB_I		0x05d00000
+#define ARM_INST_LDST__U	0x00800000
+#define ARM_INST_LDST__IMM12	0x00000fff
+#define ARM_INST_LDRB_I		0x05500000
 #define ARM_INST_LDRB_R		0x07d00000
-#define ARM_INST_LDRH_I		0x01d000b0
+#define ARM_INST_LDRD_I		0x014000d0
+#define ARM_INST_LDRH_I		0x015000b0
 #define ARM_INST_LDRH_R		0x019000b0
-#define ARM_INST_LDR_I		0x05900000
+#define ARM_INST_LDR_I		0x05100000
 #define ARM_INST_LDR_R		0x07900000
 
 #define ARM_INST_LDM		0x08900000
@@ -124,9 +127,10 @@
 #define ARM_INST_SBC_R		0x00c00000
 #define ARM_INST_SBCS_R		0x00d00000
 
-#define ARM_INST_STR_I		0x05800000
-#define ARM_INST_STRB_I		0x05c00000
-#define ARM_INST_STRH_I		0x01c000b0
+#define ARM_INST_STR_I		0x05000000
+#define ARM_INST_STRB_I		0x05400000
+#define ARM_INST_STRD_I		0x014000f0
+#define ARM_INST_STRH_I		0x014000b0
 
 #define ARM_INST_TST_R		0x01100000
 #define ARM_INST_TST_I		0x03100000
@@ -183,17 +187,18 @@
 #define ARM_EOR_R(rd, rn, rm)	_AL3_R(ARM_INST_EOR, rd, rn, rm)
 #define ARM_EOR_I(rd, rn, imm)	_AL3_I(ARM_INST_EOR, rd, rn, imm)
 
-#define ARM_LDR_I(rt, rn, off)	(ARM_INST_LDR_I | (rt) << 12 | (rn) << 16 \
-				 | ((off) & 0xfff))
-#define ARM_LDR_R(rt, rn, rm)	(ARM_INST_LDR_R | (rt) << 12 | (rn) << 16 \
+#define ARM_LDR_R(rt, rn, rm)	(ARM_INST_LDR_R | ARM_INST_LDST__U \
+				 | (rt) << 12 | (rn) << 16 \
 				 | (rm))
-#define ARM_LDRB_I(rt, rn, off)	(ARM_INST_LDRB_I | (rt) << 12 | (rn) << 16 \
-				 | (off))
-#define ARM_LDRB_R(rt, rn, rm)	(ARM_INST_LDRB_R | (rt) << 12 | (rn) << 16 \
+#define ARM_LDR_R_SI(rt, rn, rm, type, imm) \
+				(ARM_INST_LDR_R | ARM_INST_LDST__U \
+				 | (rt) << 12 | (rn) << 16 \
+				 | (imm) << 7 | (type) << 5 | (rm))
+#define ARM_LDRB_R(rt, rn, rm)	(ARM_INST_LDRB_R | ARM_INST_LDST__U \
+				 | (rt) << 12 | (rn) << 16 \
 				 | (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 \
+#define ARM_LDRH_R(rt, rn, rm)	(ARM_INST_LDRH_R | ARM_INST_LDST__U \
+				 | (rt) << 12 | (rn) << 16 \
 				 | (rm))
 
 #define ARM_LDM(rn, regs)	(ARM_INST_LDM | (rn) << 16 | (regs))
@@ -254,13 +259,6 @@
 #define ARM_SUBS_I(rd, rn, imm)	_AL3_I(ARM_INST_SUBS, rd, rn, imm)
 #define ARM_SBC_I(rd, rn, imm)	_AL3_I(ARM_INST_SBC, rd, rn, imm)
 
-#define ARM_STR_I(rt, rn, off)	(ARM_INST_STR_I | (rt) << 12 | (rn) << 16 \
-				 | ((off) & 0xfff))
-#define ARM_STRH_I(rt, rn, off)	(ARM_INST_STRH_I | (rt) << 12 | (rn) << 16 \
-				 | (((off) & 0xf0) << 4) | ((off) & 0xf))
-#define ARM_STRB_I(rt, rn, off)	(ARM_INST_STRB_I | (rt) << 12 | (rn) << 16 \
-				 | (((off) & 0xf0) << 4) | ((off) & 0xf))
-
 #define ARM_TST_R(rn, rm)	_AL3_R(ARM_INST_TST, 0, rn, rm)
 #define ARM_TST_I(rn, imm)	_AL3_I(ARM_INST_TST, 0, rn, imm)
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 1f0e872d0667..0584d07c8c33 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -219,7 +219,6 @@ int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 		rc = bnxt_xdp_set(bp, xdp->prog);
 		break;
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!bp->xdp_prog;
 		xdp->prog_id = bp->xdp_prog ? bp->xdp_prog->aux->id : 0;
 		rc = 0;
 		break;
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 135766c4296b..768f584f8392 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1848,7 +1848,6 @@ static int nicvf_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 	case XDP_SETUP_PROG:
 		return nicvf_xdp_setup(nic, xdp->prog);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!nic->xdp_prog;
 		xdp->prog_id = nic->xdp_prog ? nic->xdp_prog->aux->id : 0;
 		return 0;
 	default:
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 426b0ccb1fc6..51762428b40e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -11841,7 +11841,6 @@ static int i40e_xdp(struct net_device *dev,
 	case XDP_SETUP_PROG:
 		return i40e_xdp_setup(vsi, xdp->prog);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = i40e_enabled_xdp_vsi(vsi);
 		xdp->prog_id = vsi->xdp_prog ? vsi->xdp_prog->aux->id : 0;
 		return 0;
 	default:
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index bd6d9ea27b4b..5a6600f7b382 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -9992,7 +9992,6 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	case XDP_SETUP_PROG:
 		return ixgbe_xdp_setup(dev, xdp->prog);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!(adapter->xdp_prog);
 		xdp->prog_id = adapter->xdp_prog ?
 			adapter->xdp_prog->aux->id : 0;
 		return 0;
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 59416eddd840..d86446d202d5 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -4462,7 +4462,6 @@ static int ixgbevf_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	case XDP_SETUP_PROG:
 		return ixgbevf_xdp_setup(dev, xdp->prog);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!(adapter->xdp_prog);
 		xdp->prog_id = adapter->xdp_prog ?
 			       adapter->xdp_prog->aux->id : 0;
 		return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 65eb06e017e4..6785661d1a72 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2926,7 +2926,6 @@ static int mlx4_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 		return mlx4_xdp_set(dev, xdp->prog);
 	case XDP_QUERY_PROG:
 		xdp->prog_id = mlx4_xdp_query(dev);
-		xdp->prog_attached = !!xdp->prog_id;
 		return 0;
 	default:
 		return -EINVAL;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index c7791d036e9f..712b9766485f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4196,7 +4196,6 @@ static int mlx5e_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 		return mlx5e_xdp_set(dev, xdp->prog);
 	case XDP_QUERY_PROG:
 		xdp->prog_id = mlx5e_xdp_query(dev);
-		xdp->prog_attached = !!xdp->prog_id;
 		return 0;
 	default:
 		return -EINVAL;
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index 33111739b210..1d9e36835404 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -34,10 +34,11 @@
 #define pr_fmt(fmt)	"NFP net bpf: " fmt
 
 #include <linux/bug.h>
-#include <linux/kernel.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
+#include <linux/kernel.h>
 #include <linux/pkt_cls.h>
+#include <linux/reciprocal_div.h>
 #include <linux/unistd.h>
 
 #include "main.h"
@@ -415,6 +416,60 @@ emit_alu(struct nfp_prog *nfp_prog, swreg dst,
 		   reg.dst_lmextn, reg.src_lmextn);
 }
 
+static void
+__emit_mul(struct nfp_prog *nfp_prog, enum alu_dst_ab dst_ab, u16 areg,
+	   enum mul_type type, enum mul_step step, u16 breg, bool swap,
+	   bool wr_both, bool dst_lmextn, bool src_lmextn)
+{
+	u64 insn;
+
+	insn = OP_MUL_BASE |
+		FIELD_PREP(OP_MUL_A_SRC, areg) |
+		FIELD_PREP(OP_MUL_B_SRC, breg) |
+		FIELD_PREP(OP_MUL_STEP, step) |
+		FIELD_PREP(OP_MUL_DST_AB, dst_ab) |
+		FIELD_PREP(OP_MUL_SW, swap) |
+		FIELD_PREP(OP_MUL_TYPE, type) |
+		FIELD_PREP(OP_MUL_WR_AB, wr_both) |
+		FIELD_PREP(OP_MUL_SRC_LMEXTN, src_lmextn) |
+		FIELD_PREP(OP_MUL_DST_LMEXTN, dst_lmextn);
+
+	nfp_prog_push(nfp_prog, insn);
+}
+
+static void
+emit_mul(struct nfp_prog *nfp_prog, swreg lreg, enum mul_type type,
+	 enum mul_step step, swreg rreg)
+{
+	struct nfp_insn_ur_regs reg;
+	u16 areg;
+	int err;
+
+	if (type == MUL_TYPE_START && step != MUL_STEP_NONE) {
+		nfp_prog->error = -EINVAL;
+		return;
+	}
+
+	if (step == MUL_LAST || step == MUL_LAST_2) {
+		/* When type is step and step Number is LAST or LAST2, left
+		 * source is used as destination.
+		 */
+		err = swreg_to_unrestricted(lreg, reg_none(), rreg, &reg);
+		areg = reg.dst;
+	} else {
+		err = swreg_to_unrestricted(reg_none(), lreg, rreg, &reg);
+		areg = reg.areg;
+	}
+
+	if (err) {
+		nfp_prog->error = err;
+		return;
+	}
+
+	__emit_mul(nfp_prog, reg.dst_ab, areg, type, step, reg.breg, reg.swap,
+		   reg.wr_both, reg.dst_lmextn, reg.src_lmextn);
+}
+
 static void
 __emit_ld_field(struct nfp_prog *nfp_prog, enum shf_sc sc,
 		u8 areg, u8 bmask, u8 breg, u8 shift, bool imm8,
@@ -1380,6 +1435,133 @@ static void wrp_end32(struct nfp_prog *nfp_prog, swreg reg_in, u8 gpr_out)
 		      SHF_SC_R_ROT, 16);
 }
 
+static void
+wrp_mul_u32(struct nfp_prog *nfp_prog, swreg dst_hi, swreg dst_lo, swreg lreg,
+	    swreg rreg, bool gen_high_half)
+{
+	emit_mul(nfp_prog, lreg, MUL_TYPE_START, MUL_STEP_NONE, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_32x32, MUL_STEP_1, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_32x32, MUL_STEP_2, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_32x32, MUL_STEP_3, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_32x32, MUL_STEP_4, rreg);
+	emit_mul(nfp_prog, dst_lo, MUL_TYPE_STEP_32x32, MUL_LAST, reg_none());
+	if (gen_high_half)
+		emit_mul(nfp_prog, dst_hi, MUL_TYPE_STEP_32x32, MUL_LAST_2,
+			 reg_none());
+	else
+		wrp_immed(nfp_prog, dst_hi, 0);
+}
+
+static void
+wrp_mul_u16(struct nfp_prog *nfp_prog, swreg dst_hi, swreg dst_lo, swreg lreg,
+	    swreg rreg)
+{
+	emit_mul(nfp_prog, lreg, MUL_TYPE_START, MUL_STEP_NONE, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_16x16, MUL_STEP_1, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_16x16, MUL_STEP_2, rreg);
+	emit_mul(nfp_prog, dst_lo, MUL_TYPE_STEP_16x16, MUL_LAST, reg_none());
+}
+
+static int
+wrp_mul(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+	bool gen_high_half, bool ropnd_from_reg)
+{
+	swreg multiplier, multiplicand, dst_hi, dst_lo;
+	const struct bpf_insn *insn = &meta->insn;
+	u32 lopnd_max, ropnd_max;
+	u8 dst_reg;
+
+	dst_reg = insn->dst_reg;
+	multiplicand = reg_a(dst_reg * 2);
+	dst_hi = reg_both(dst_reg * 2 + 1);
+	dst_lo = reg_both(dst_reg * 2);
+	lopnd_max = meta->umax_dst;
+	if (ropnd_from_reg) {
+		multiplier = reg_b(insn->src_reg * 2);
+		ropnd_max = meta->umax_src;
+	} else {
+		u32 imm = insn->imm;
+
+		multiplier = ur_load_imm_any(nfp_prog, imm, imm_b(nfp_prog));
+		ropnd_max = imm;
+	}
+	if (lopnd_max > U16_MAX || ropnd_max > U16_MAX)
+		wrp_mul_u32(nfp_prog, dst_hi, dst_lo, multiplicand, multiplier,
+			    gen_high_half);
+	else
+		wrp_mul_u16(nfp_prog, dst_hi, dst_lo, multiplicand, multiplier);
+
+	return 0;
+}
+
+static int wrp_div_imm(struct nfp_prog *nfp_prog, u8 dst, u64 imm)
+{
+	swreg dst_both = reg_both(dst), dst_a = reg_a(dst), dst_b = reg_a(dst);
+	struct reciprocal_value_adv rvalue;
+	u8 pre_shift, exp;
+	swreg magic;
+
+	if (imm > U32_MAX) {
+		wrp_immed(nfp_prog, dst_both, 0);
+		return 0;
+	}
+
+	/* NOTE: because we are using "reciprocal_value_adv" which doesn't
+	 * support "divisor > (1u << 31)", we need to JIT separate NFP sequence
+	 * to handle such case which actually equals to the result of unsigned
+	 * comparison "dst >= imm" which could be calculated using the following
+	 * NFP sequence:
+	 *
+	 *  alu[--, dst, -, imm]
+	 *  immed[imm, 0]
+	 *  alu[dst, imm, +carry, 0]
+	 *
+	 */
+	if (imm > 1U << 31) {
+		swreg tmp_b = ur_load_imm_any(nfp_prog, imm, imm_b(nfp_prog));
+
+		emit_alu(nfp_prog, reg_none(), dst_a, ALU_OP_SUB, tmp_b);
+		wrp_immed(nfp_prog, imm_a(nfp_prog), 0);
+		emit_alu(nfp_prog, dst_both, imm_a(nfp_prog), ALU_OP_ADD_C,
+			 reg_imm(0));
+		return 0;
+	}
+
+	rvalue = reciprocal_value_adv(imm, 32);
+	exp = rvalue.exp;
+	if (rvalue.is_wide_m && !(imm & 1)) {
+		pre_shift = fls(imm & -imm) - 1;
+		rvalue = reciprocal_value_adv(imm >> pre_shift, 32 - pre_shift);
+	} else {
+		pre_shift = 0;
+	}
+	magic = ur_load_imm_any(nfp_prog, rvalue.m, imm_b(nfp_prog));
+	if (imm == 1U << exp) {
+		emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE, dst_b,
+			 SHF_SC_R_SHF, exp);
+	} else if (rvalue.is_wide_m) {
+		wrp_mul_u32(nfp_prog, imm_both(nfp_prog), reg_none(), dst_a,
+			    magic, true);
+		emit_alu(nfp_prog, dst_both, dst_a, ALU_OP_SUB,
+			 imm_b(nfp_prog));
+		emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE, dst_b,
+			 SHF_SC_R_SHF, 1);
+		emit_alu(nfp_prog, dst_both, dst_a, ALU_OP_ADD,
+			 imm_b(nfp_prog));
+		emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE, dst_b,
+			 SHF_SC_R_SHF, rvalue.sh - 1);
+	} else {
+		if (pre_shift)
+			emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE,
+				 dst_b, SHF_SC_R_SHF, pre_shift);
+		wrp_mul_u32(nfp_prog, dst_both, reg_none(), dst_a, magic, true);
+		emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE,
+			 dst_b, SHF_SC_R_SHF, rvalue.sh);
+	}
+
+	return 0;
+}
+
 static int adjust_head(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	swreg tmp = imm_a(nfp_prog), tmp_len = imm_b(nfp_prog);
@@ -1684,6 +1866,31 @@ static int sub_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return 0;
 }
 
+static int mul_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return wrp_mul(nfp_prog, meta, true, true);
+}
+
+static int mul_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return wrp_mul(nfp_prog, meta, true, false);
+}
+
+static int div_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+
+	return wrp_div_imm(nfp_prog, insn->dst_reg * 2, insn->imm);
+}
+
+static int div_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	/* NOTE: verifier hook has rejected cases for which verifier doesn't
+	 * know whether the source operand is constant or not.
+	 */
+	return wrp_div_imm(nfp_prog, meta->insn.dst_reg * 2, meta->umin_src);
+}
+
 static int neg_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
@@ -1772,8 +1979,8 @@ static int shl_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	u8 dst, src;
 
 	dst = insn->dst_reg * 2;
-	umin = meta->umin;
-	umax = meta->umax;
+	umin = meta->umin_src;
+	umax = meta->umax_src;
 	if (umin == umax)
 		return __shl_imm64(nfp_prog, dst, umin);
 
@@ -1881,8 +2088,8 @@ static int shr_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	u8 dst, src;
 
 	dst = insn->dst_reg * 2;
-	umin = meta->umin;
-	umax = meta->umax;
+	umin = meta->umin_src;
+	umax = meta->umax_src;
 	if (umin == umax)
 		return __shr_imm64(nfp_prog, dst, umin);
 
@@ -1995,8 +2202,8 @@ static int ashr_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	u8 dst, src;
 
 	dst = insn->dst_reg * 2;
-	umin = meta->umin;
-	umax = meta->umax;
+	umin = meta->umin_src;
+	umax = meta->umax_src;
 	if (umin == umax)
 		return __ashr_imm64(nfp_prog, dst, umin);
 
@@ -2097,6 +2304,26 @@ static int sub_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_SUB, !meta->insn.imm);
 }
 
+static int mul_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return wrp_mul(nfp_prog, meta, false, true);
+}
+
+static int mul_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return wrp_mul(nfp_prog, meta, false, false);
+}
+
+static int div_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return div_reg64(nfp_prog, meta);
+}
+
+static int div_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return div_imm64(nfp_prog, meta);
+}
+
 static int neg_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	u8 dst = meta->insn.dst_reg * 2;
@@ -2848,6 +3075,10 @@ static const instr_cb_t instr_cb[256] = {
 	[BPF_ALU64 | BPF_ADD | BPF_K] =	add_imm64,
 	[BPF_ALU64 | BPF_SUB | BPF_X] =	sub_reg64,
 	[BPF_ALU64 | BPF_SUB | BPF_K] =	sub_imm64,
+	[BPF_ALU64 | BPF_MUL | BPF_X] =	mul_reg64,
+	[BPF_ALU64 | BPF_MUL | BPF_K] =	mul_imm64,
+	[BPF_ALU64 | BPF_DIV | BPF_X] =	div_reg64,
+	[BPF_ALU64 | BPF_DIV | BPF_K] =	div_imm64,
 	[BPF_ALU64 | BPF_NEG] =		neg_reg64,
 	[BPF_ALU64 | BPF_LSH | BPF_X] =	shl_reg64,
 	[BPF_ALU64 | BPF_LSH | BPF_K] =	shl_imm64,
@@ -2867,6 +3098,10 @@ static const instr_cb_t instr_cb[256] = {
 	[BPF_ALU | BPF_ADD | BPF_K] =	add_imm,
 	[BPF_ALU | BPF_SUB | BPF_X] =	sub_reg,
 	[BPF_ALU | BPF_SUB | BPF_K] =	sub_imm,
+	[BPF_ALU | BPF_MUL | BPF_X] =	mul_reg,
+	[BPF_ALU | BPF_MUL | BPF_K] =	mul_imm,
+	[BPF_ALU | BPF_DIV | BPF_X] =	div_reg,
+	[BPF_ALU | BPF_DIV | BPF_K] =	div_imm,
 	[BPF_ALU | BPF_NEG] =		neg_reg,
 	[BPF_ALU | BPF_LSH | BPF_K] =	shl_imm,
 	[BPF_ALU | BPF_END | BPF_X] =	end_reg32,
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index 4dbf7cba6377..b95b94d008cf 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -66,26 +66,19 @@ nfp_bpf_xdp_offload(struct nfp_app *app, struct nfp_net *nn,
 		    struct bpf_prog *prog, struct netlink_ext_ack *extack)
 {
 	bool running, xdp_running;
-	int ret;
 
 	if (!nfp_net_ebpf_capable(nn))
 		return -EINVAL;
 
 	running = nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF;
-	xdp_running = running && nn->dp.bpf_offload_xdp;
+	xdp_running = running && nn->xdp_hw.prog;
 
 	if (!prog && !xdp_running)
 		return 0;
 	if (prog && running && !xdp_running)
 		return -EBUSY;
 
-	ret = nfp_net_bpf_offload(nn, prog, running, extack);
-	/* Stop offload if replace not possible */
-	if (ret)
-		return ret;
-
-	nn->dp.bpf_offload_xdp = !!prog;
-	return ret;
+	return nfp_net_bpf_offload(nn, prog, running, extack);
 }
 
 static const char *nfp_bpf_extra_cap(struct nfp_app *app, struct nfp_net *nn)
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index 654fe7823e5e..9845c1a2d4c2 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -263,8 +263,10 @@ struct nfp_bpf_reg_state {
  * @func_id: function id for call instructions
  * @arg1: arg1 for call instructions
  * @arg2: arg2 for call instructions
- * @umin: copy of core verifier umin_value.
- * @umax: copy of core verifier umax_value.
+ * @umin_src: copy of core verifier umin_value for src opearnd.
+ * @umax_src: copy of core verifier umax_value for src operand.
+ * @umin_dst: copy of core verifier umin_value for dst opearnd.
+ * @umax_dst: copy of core verifier umax_value for dst operand.
  * @off: index of first generated machine instruction (in nfp_prog.prog)
  * @n: eBPF instruction number
  * @flags: eBPF instruction extra optimization flags
@@ -300,12 +302,15 @@ struct nfp_insn_meta {
 			struct bpf_reg_state arg1;
 			struct nfp_bpf_reg_state arg2;
 		};
-		/* We are interested in range info for some operands,
-		 * for example, the shift amount.
+		/* We are interested in range info for operands of ALU
+		 * operations. For example, shift amount, multiplicand and
+		 * multiplier etc.
 		 */
 		struct {
-			u64 umin;
-			u64 umax;
+			u64 umin_src;
+			u64 umax_src;
+			u64 umin_dst;
+			u64 umax_dst;
 		};
 	};
 	unsigned int off;
@@ -339,6 +344,11 @@ static inline u8 mbpf_mode(const struct nfp_insn_meta *meta)
 	return BPF_MODE(meta->insn.code);
 }
 
+static inline bool is_mbpf_alu(const struct nfp_insn_meta *meta)
+{
+	return mbpf_class(meta) == BPF_ALU64 || mbpf_class(meta) == BPF_ALU;
+}
+
 static inline bool is_mbpf_load(const struct nfp_insn_meta *meta)
 {
 	return (meta->insn.code & ~BPF_SIZE_MASK) == (BPF_LDX | BPF_MEM);
@@ -384,23 +394,14 @@ static inline bool is_mbpf_xadd(const struct nfp_insn_meta *meta)
 	return (meta->insn.code & ~BPF_SIZE_MASK) == (BPF_STX | BPF_XADD);
 }
 
-static inline bool is_mbpf_indir_shift(const struct nfp_insn_meta *meta)
+static inline bool is_mbpf_mul(const struct nfp_insn_meta *meta)
 {
-	u8 code = meta->insn.code;
-	bool is_alu, is_shift;
-	u8 opclass, opcode;
+	return is_mbpf_alu(meta) && mbpf_op(meta) == BPF_MUL;
+}
 
-	opclass = BPF_CLASS(code);
-	is_alu = opclass == BPF_ALU64 || opclass == BPF_ALU;
-	if (!is_alu)
-		return false;
-
-	opcode = BPF_OP(code);
-	is_shift = opcode == BPF_LSH || opcode == BPF_RSH || opcode == BPF_ARSH;
-	if (!is_shift)
-		return false;
-
-	return BPF_SRC(code) == BPF_X;
+static inline bool is_mbpf_div(const struct nfp_insn_meta *meta)
+{
+	return is_mbpf_alu(meta) && mbpf_op(meta) == BPF_DIV;
 }
 
 /**
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index 7eae4c0266f8..78f44c4d95b4 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -190,8 +190,10 @@ nfp_prog_prepare(struct nfp_prog *nfp_prog, const struct bpf_insn *prog,
 
 		meta->insn = prog[i];
 		meta->n = i;
-		if (is_mbpf_indir_shift(meta))
-			meta->umin = U64_MAX;
+		if (is_mbpf_alu(meta)) {
+			meta->umin_src = U64_MAX;
+			meta->umin_dst = U64_MAX;
+		}
 
 		list_add_tail(&meta->l, &nfp_prog->insns);
 	}
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
index 4bfeba7b21b2..49ba0d645d36 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
@@ -516,6 +516,82 @@ nfp_bpf_check_xadd(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 	return nfp_bpf_check_ptr(nfp_prog, meta, env, meta->insn.dst_reg);
 }
 
+static int
+nfp_bpf_check_alu(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+		  struct bpf_verifier_env *env)
+{
+	const struct bpf_reg_state *sreg =
+		cur_regs(env) + meta->insn.src_reg;
+	const struct bpf_reg_state *dreg =
+		cur_regs(env) + meta->insn.dst_reg;
+
+	meta->umin_src = min(meta->umin_src, sreg->umin_value);
+	meta->umax_src = max(meta->umax_src, sreg->umax_value);
+	meta->umin_dst = min(meta->umin_dst, dreg->umin_value);
+	meta->umax_dst = max(meta->umax_dst, dreg->umax_value);
+
+	/* NFP supports u16 and u32 multiplication.
+	 *
+	 * For ALU64, if either operand is beyond u32's value range, we reject
+	 * it. One thing to note, if the source operand is BPF_K, then we need
+	 * to check "imm" field directly, and we'd reject it if it is negative.
+	 * Because for ALU64, "imm" (with s32 type) is expected to be sign
+	 * extended to s64 which NFP mul doesn't support.
+	 *
+	 * For ALU32, it is fine for "imm" be negative though, because the
+	 * result is 32-bits and there is no difference on the low halve of
+	 * the result for signed/unsigned mul, so we will get correct result.
+	 */
+	if (is_mbpf_mul(meta)) {
+		if (meta->umax_dst > U32_MAX) {
+			pr_vlog(env, "multiplier is not within u32 value range\n");
+			return -EINVAL;
+		}
+		if (mbpf_src(meta) == BPF_X && meta->umax_src > U32_MAX) {
+			pr_vlog(env, "multiplicand is not within u32 value range\n");
+			return -EINVAL;
+		}
+		if (mbpf_class(meta) == BPF_ALU64 &&
+		    mbpf_src(meta) == BPF_K && meta->insn.imm < 0) {
+			pr_vlog(env, "sign extended multiplicand won't be within u32 value range\n");
+			return -EINVAL;
+		}
+	}
+
+	/* NFP doesn't have divide instructions, we support divide by constant
+	 * through reciprocal multiplication. Given NFP support multiplication
+	 * no bigger than u32, we'd require divisor and dividend no bigger than
+	 * that as well.
+	 *
+	 * Also eBPF doesn't support signed divide and has enforced this on C
+	 * language level by failing compilation. However LLVM assembler hasn't
+	 * enforced this, so it is possible for negative constant to leak in as
+	 * a BPF_K operand through assembly code, we reject such cases as well.
+	 */
+	if (is_mbpf_div(meta)) {
+		if (meta->umax_dst > U32_MAX) {
+			pr_vlog(env, "dividend is not within u32 value range\n");
+			return -EINVAL;
+		}
+		if (mbpf_src(meta) == BPF_X) {
+			if (meta->umin_src != meta->umax_src) {
+				pr_vlog(env, "divisor is not constant\n");
+				return -EINVAL;
+			}
+			if (meta->umax_src > U32_MAX) {
+				pr_vlog(env, "divisor is not within u32 value range\n");
+				return -EINVAL;
+			}
+		}
+		if (mbpf_src(meta) == BPF_K && meta->insn.imm < 0) {
+			pr_vlog(env, "divide by negative constant is not supported\n");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 static int
 nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx)
 {
@@ -551,13 +627,8 @@ nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx)
 	if (is_mbpf_xadd(meta))
 		return nfp_bpf_check_xadd(nfp_prog, meta, env);
 
-	if (is_mbpf_indir_shift(meta)) {
-		const struct bpf_reg_state *sreg =
-			cur_regs(env) + meta->insn.src_reg;
-
-		meta->umin = min(meta->umin, sreg->umin_value);
-		meta->umax = max(meta->umax, sreg->umax_value);
-	}
+	if (is_mbpf_alu(meta))
+		return nfp_bpf_check_alu(nfp_prog, meta, env);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.h b/drivers/net/ethernet/netronome/nfp/nfp_asm.h
index f6677bc9875a..cdc4e065f6f5 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_asm.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.h
@@ -426,4 +426,32 @@ static inline u32 nfp_get_ind_csr_ctx_ptr_offs(u32 read_offset)
 	return (read_offset & ~NFP_IND_ME_CTX_PTR_BASE_MASK) | NFP_CSR_CTX_PTR;
 }
 
+enum mul_type {
+	MUL_TYPE_START		= 0x00,
+	MUL_TYPE_STEP_24x8	= 0x01,
+	MUL_TYPE_STEP_16x16	= 0x02,
+	MUL_TYPE_STEP_32x32	= 0x03,
+};
+
+enum mul_step {
+	MUL_STEP_1		= 0x00,
+	MUL_STEP_NONE		= MUL_STEP_1,
+	MUL_STEP_2		= 0x01,
+	MUL_STEP_3		= 0x02,
+	MUL_STEP_4		= 0x03,
+	MUL_LAST		= 0x04,
+	MUL_LAST_2		= 0x05,
+};
+
+#define OP_MUL_BASE		0x0f800000000ULL
+#define OP_MUL_A_SRC		0x000000003ffULL
+#define OP_MUL_B_SRC		0x000000ffc00ULL
+#define OP_MUL_STEP		0x00000700000ULL
+#define OP_MUL_DST_AB		0x00000800000ULL
+#define OP_MUL_SW		0x00040000000ULL
+#define OP_MUL_TYPE		0x00180000000ULL
+#define OP_MUL_WR_AB		0x20000000000ULL
+#define OP_MUL_SRC_LMEXTN	0x40000000000ULL
+#define OP_MUL_DST_LMEXTN	0x80000000000ULL
+
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index 2a71a9ffd095..8970ec981e11 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -485,7 +485,6 @@ struct nfp_stat_pair {
  * @dev:		Backpointer to struct device
  * @netdev:		Backpointer to net_device structure
  * @is_vf:		Is the driver attached to a VF?
- * @bpf_offload_xdp:	Offloaded BPF program is XDP
  * @chained_metadata_format:  Firemware will use new metadata format
  * @rx_dma_dir:		Mapping direction for RX buffers
  * @rx_dma_off:		Offset at which DMA packets (for XDP headroom)
@@ -510,7 +509,6 @@ struct nfp_net_dp {
 	struct net_device *netdev;
 
 	u8 is_vf:1;
-	u8 bpf_offload_xdp:1;
 	u8 chained_metadata_format:1;
 
 	u8 rx_dma_dir;
@@ -553,8 +551,8 @@ struct nfp_net_dp {
  * @rss_cfg:            RSS configuration
  * @rss_key:            RSS secret key
  * @rss_itbl:           RSS indirection table
- * @xdp_flags:		Flags with which XDP prog was loaded
- * @xdp_prog:		XDP prog (for ctrl path, both DRV and HW modes)
+ * @xdp:		Information about the driver XDP program
+ * @xdp_hw:		Information about the HW XDP program
  * @max_r_vecs:		Number of allocated interrupt vectors for RX/TX
  * @max_tx_rings:       Maximum number of TX rings supported by the Firmware
  * @max_rx_rings:       Maximum number of RX rings supported by the Firmware
@@ -610,8 +608,8 @@ struct nfp_net {
 	u8 rss_key[NFP_NET_CFG_RSS_KEY_SZ];
 	u8 rss_itbl[NFP_NET_CFG_RSS_ITBL_SZ];
 
-	u32 xdp_flags;
-	struct bpf_prog *xdp_prog;
+	struct xdp_attachment_info xdp;
+	struct xdp_attachment_info xdp_hw;
 
 	unsigned int max_tx_rings;
 	unsigned int max_rx_rings;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 7df5ca37bfb8..a712e83c3f0f 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1710,8 +1710,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 			}
 		}
 
-		if (xdp_prog && !(rxd->rxd.flags & PCIE_DESC_RX_BPF &&
-				  dp->bpf_offload_xdp) && !meta.portid) {
+		if (xdp_prog && !meta.portid) {
 			void *orig_data = rxbuf->frag + pkt_off;
 			unsigned int dma_off;
 			int act;
@@ -3393,14 +3392,18 @@ static void nfp_net_del_vxlan_port(struct net_device *netdev,
 		nfp_net_set_vxlan_port(nn, idx, 0);
 }
 
-static int
-nfp_net_xdp_setup_drv(struct nfp_net *nn, struct bpf_prog *prog,
-		      struct netlink_ext_ack *extack)
+static int nfp_net_xdp_setup_drv(struct nfp_net *nn, struct netdev_bpf *bpf)
 {
+	struct bpf_prog *prog = bpf->prog;
 	struct nfp_net_dp *dp;
+	int err;
+
+	if (!xdp_attachment_flags_ok(&nn->xdp, bpf))
+		return -EBUSY;
 
 	if (!prog == !nn->dp.xdp_prog) {
 		WRITE_ONCE(nn->dp.xdp_prog, prog);
+		xdp_attachment_setup(&nn->xdp, bpf);
 		return 0;
 	}
 
@@ -3414,38 +3417,26 @@ nfp_net_xdp_setup_drv(struct nfp_net *nn, struct bpf_prog *prog,
 	dp->rx_dma_off = prog ? XDP_PACKET_HEADROOM - nn->dp.rx_offset : 0;
 
 	/* We need RX reconfig to remap the buffers (BIDIR vs FROM_DEV) */
-	return nfp_net_ring_reconfig(nn, dp, extack);
-}
-
-static int
-nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog, u32 flags,
-		  struct netlink_ext_ack *extack)
-{
-	struct bpf_prog *drv_prog, *offload_prog;
-	int err;
-
-	if (nn->xdp_prog && (flags ^ nn->xdp_flags) & XDP_FLAGS_MODES)
-		return -EBUSY;
-
-	/* Load both when no flags set to allow easy activation of driver path
-	 * when program is replaced by one which can't be offloaded.
-	 */
-	drv_prog     = flags & XDP_FLAGS_HW_MODE  ? NULL : prog;
-	offload_prog = flags & XDP_FLAGS_DRV_MODE ? NULL : prog;
-
-	err = nfp_net_xdp_setup_drv(nn, drv_prog, extack);
+	err = nfp_net_ring_reconfig(nn, dp, bpf->extack);
 	if (err)
 		return err;
 
-	err = nfp_app_xdp_offload(nn->app, nn, offload_prog, extack);
-	if (err && flags & XDP_FLAGS_HW_MODE)
+	xdp_attachment_setup(&nn->xdp, bpf);
+	return 0;
+}
+
+static int nfp_net_xdp_setup_hw(struct nfp_net *nn, struct netdev_bpf *bpf)
+{
+	int err;
+
+	if (!xdp_attachment_flags_ok(&nn->xdp_hw, bpf))
+		return -EBUSY;
+
+	err = nfp_app_xdp_offload(nn->app, nn, bpf->prog, bpf->extack);
+	if (err)
 		return err;
 
-	if (nn->xdp_prog)
-		bpf_prog_put(nn->xdp_prog);
-	nn->xdp_prog = prog;
-	nn->xdp_flags = flags;
-
+	xdp_attachment_setup(&nn->xdp_hw, bpf);
 	return 0;
 }
 
@@ -3455,16 +3446,13 @@ static int nfp_net_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
+		return nfp_net_xdp_setup_drv(nn, xdp);
 	case XDP_SETUP_PROG_HW:
-		return nfp_net_xdp_setup(nn, xdp->prog, xdp->flags,
-					 xdp->extack);
+		return nfp_net_xdp_setup_hw(nn, xdp);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!nn->xdp_prog;
-		if (nn->dp.bpf_offload_xdp)
-			xdp->prog_attached = XDP_ATTACHED_HW;
-		xdp->prog_id = nn->xdp_prog ? nn->xdp_prog->aux->id : 0;
-		xdp->prog_flags = nn->xdp_prog ? nn->xdp_flags : 0;
-		return 0;
+		return xdp_attachment_query(&nn->xdp, xdp);
+	case XDP_QUERY_PROG_HW:
+		return xdp_attachment_query(&nn->xdp_hw, xdp);
 	default:
 		return nfp_app_bpf(nn->app, nn, xdp);
 	}
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index b823bfe2ea4d..f9a327c821eb 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -1116,7 +1116,6 @@ int qede_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	case XDP_SETUP_PROG:
 		return qede_xdp_set(edev, xdp->prog);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!edev->xdp_prog;
 		xdp->prog_id = edev->xdp_prog ? edev->xdp_prog->aux->id : 0;
 		return 0;
 	default:
diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index 75c25306d234..c36d2a768202 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -92,7 +92,7 @@ static const struct bpf_prog_offload_ops nsim_bpf_analyzer_ops = {
 
 static bool nsim_xdp_offload_active(struct netdevsim *ns)
 {
-	return ns->xdp_prog_mode == XDP_ATTACHED_HW;
+	return ns->xdp_hw.prog;
 }
 
 static void nsim_prog_set_loaded(struct bpf_prog *prog, bool loaded)
@@ -195,14 +195,14 @@ static int nsim_xdp_offload_prog(struct netdevsim *ns, struct netdev_bpf *bpf)
 	return nsim_bpf_offload(ns, bpf->prog, nsim_xdp_offload_active(ns));
 }
 
-static int nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf)
+static int
+nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf,
+		  struct xdp_attachment_info *xdp)
 {
 	int err;
 
-	if (ns->xdp_prog && (bpf->flags ^ ns->xdp_flags) & XDP_FLAGS_MODES) {
-		NSIM_EA(bpf->extack, "program loaded with different flags");
+	if (!xdp_attachment_flags_ok(xdp, bpf))
 		return -EBUSY;
-	}
 
 	if (bpf->command == XDP_SETUP_PROG && !ns->bpf_xdpdrv_accept) {
 		NSIM_EA(bpf->extack, "driver XDP disabled in DebugFS");
@@ -219,18 +219,7 @@ static int nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf)
 			return err;
 	}
 
-	if (ns->xdp_prog)
-		bpf_prog_put(ns->xdp_prog);
-
-	ns->xdp_prog = bpf->prog;
-	ns->xdp_flags = bpf->flags;
-
-	if (!bpf->prog)
-		ns->xdp_prog_mode = XDP_ATTACHED_NONE;
-	else if (bpf->command == XDP_SETUP_PROG)
-		ns->xdp_prog_mode = XDP_ATTACHED_DRV;
-	else
-		ns->xdp_prog_mode = XDP_ATTACHED_HW;
+	xdp_attachment_setup(xdp, bpf);
 
 	return 0;
 }
@@ -290,10 +279,6 @@ static int nsim_setup_prog_checks(struct netdevsim *ns, struct netdev_bpf *bpf)
 		NSIM_EA(bpf->extack, "MTU too large w/ XDP enabled");
 		return -EINVAL;
 	}
-	if (nsim_xdp_offload_active(ns)) {
-		NSIM_EA(bpf->extack, "xdp offload active, can't load drv prog");
-		return -EBUSY;
-	}
 	return 0;
 }
 
@@ -567,22 +552,21 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 		nsim_bpf_destroy_prog(bpf->offload.prog);
 		return 0;
 	case XDP_QUERY_PROG:
-		bpf->prog_attached = ns->xdp_prog_mode;
-		bpf->prog_id = ns->xdp_prog ? ns->xdp_prog->aux->id : 0;
-		bpf->prog_flags = ns->xdp_prog ? ns->xdp_flags : 0;
-		return 0;
+		return xdp_attachment_query(&ns->xdp, bpf);
+	case XDP_QUERY_PROG_HW:
+		return xdp_attachment_query(&ns->xdp_hw, bpf);
 	case XDP_SETUP_PROG:
 		err = nsim_setup_prog_checks(ns, bpf);
 		if (err)
 			return err;
 
-		return nsim_xdp_set_prog(ns, bpf);
+		return nsim_xdp_set_prog(ns, bpf, &ns->xdp);
 	case XDP_SETUP_PROG_HW:
 		err = nsim_setup_prog_hw_checks(ns, bpf);
 		if (err)
 			return err;
 
-		return nsim_xdp_set_prog(ns, bpf);
+		return nsim_xdp_set_prog(ns, bpf, &ns->xdp_hw);
 	case BPF_OFFLOAD_MAP_ALLOC:
 		if (!ns->bpf_map_accept)
 			return -EOPNOTSUPP;
@@ -637,6 +621,7 @@ void nsim_bpf_uninit(struct netdevsim *ns)
 {
 	WARN_ON(!list_empty(&ns->bpf_bound_progs));
 	WARN_ON(!list_empty(&ns->bpf_bound_maps));
-	WARN_ON(ns->xdp_prog);
+	WARN_ON(ns->xdp.prog);
+	WARN_ON(ns->xdp_hw.prog);
 	WARN_ON(ns->bpf_offloaded);
 }
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index b2f9d0df93b0..a7b179f0d954 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -228,8 +228,7 @@ static int nsim_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct netdevsim *ns = netdev_priv(dev);
 
-	if (ns->xdp_prog_mode == XDP_ATTACHED_DRV &&
-	    new_mtu > NSIM_XDP_MAX_MTU)
+	if (ns->xdp.prog && new_mtu > NSIM_XDP_MAX_MTU)
 		return -EBUSY;
 
 	dev->mtu = new_mtu;
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index d8a7cc995e88..0aeabbe81cc6 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -18,6 +18,7 @@
 #include <linux/list.h>
 #include <linux/netdevice.h>
 #include <linux/u64_stats_sync.h>
+#include <net/xdp.h>
 
 #define DRV_NAME	"netdevsim"
 
@@ -67,9 +68,8 @@ struct netdevsim {
 	struct bpf_prog	*bpf_offloaded;
 	u32 bpf_offloaded_id;
 
-	u32 xdp_flags;
-	int xdp_prog_mode;
-	struct bpf_prog	*xdp_prog;
+	struct xdp_attachment_info xdp;
+	struct xdp_attachment_info xdp_hw;
 
 	u32 prog_id_gen;
 
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 76f0f4131197..7b5748f86c9c 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1269,7 +1269,6 @@ static int tun_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 		return tun_xdp_set(dev, xdp->prog, xdp->extack);
 	case XDP_QUERY_PROG:
 		xdp->prog_id = tun_xdp_query(dev);
-		xdp->prog_attached = !!xdp->prog_id;
 		return 0;
 	default:
 		return -EINVAL;
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 53085c63277b..2ff08bc103a9 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2343,7 +2343,6 @@ static int virtnet_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 		return virtnet_xdp_set(dev, xdp->prog, xdp->extack);
 	case XDP_QUERY_PROG:
 		xdp->prog_id = virtnet_xdp_query(dev);
-		xdp->prog_attached = !!xdp->prog_id;
 		return 0;
 	default:
 		return -EINVAL;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2daf2fa6554f..4fa7f7a3f8b3 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -823,11 +823,8 @@ enum bpf_netdev_command {
 	 */
 	XDP_SETUP_PROG,
 	XDP_SETUP_PROG_HW,
-	/* Check if a bpf program is set on the device.  The callee should
-	 * set @prog_attached to one of XDP_ATTACHED_* values, note that "true"
-	 * is equivalent to XDP_ATTACHED_DRV.
-	 */
 	XDP_QUERY_PROG,
+	XDP_QUERY_PROG_HW,
 	/* BPF program for offload callbacks, invoked at program load time. */
 	BPF_OFFLOAD_VERIFIER_PREP,
 	BPF_OFFLOAD_TRANSLATE,
@@ -851,9 +848,8 @@ struct netdev_bpf {
 			struct bpf_prog *prog;
 			struct netlink_ext_ack *extack;
 		};
-		/* XDP_QUERY_PROG */
+		/* XDP_QUERY_PROG, XDP_QUERY_PROG_HW */
 		struct {
-			u8 prog_attached;
 			u32 prog_id;
 			/* flags with which program was installed */
 			u32 prog_flags;
@@ -3560,8 +3556,8 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf);
 int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		      int fd, u32 flags);
-void __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op,
-		     struct netdev_bpf *xdp);
+u32 __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op,
+		    enum bpf_netdev_command cmd);
 
 int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
diff --git a/include/linux/reciprocal_div.h b/include/linux/reciprocal_div.h
index e031e9f2f9d8..585ce89c0f33 100644
--- a/include/linux/reciprocal_div.h
+++ b/include/linux/reciprocal_div.h
@@ -25,6 +25,9 @@ struct reciprocal_value {
 	u8 sh1, sh2;
 };
 
+/* "reciprocal_value" and "reciprocal_divide" together implement the basic
+ * version of the algorithm described in Figure 4.1 of the paper.
+ */
 struct reciprocal_value reciprocal_value(u32 d);
 
 static inline u32 reciprocal_divide(u32 a, struct reciprocal_value R)
@@ -33,4 +36,69 @@ static inline u32 reciprocal_divide(u32 a, struct reciprocal_value R)
 	return (t + ((a - t) >> R.sh1)) >> R.sh2;
 }
 
+struct reciprocal_value_adv {
+	u32 m;
+	u8 sh, exp;
+	bool is_wide_m;
+};
+
+/* "reciprocal_value_adv" implements the advanced version of the algorithm
+ * described in Figure 4.2 of the paper except when "divisor > (1U << 31)" whose
+ * ceil(log2(d)) result will be 32 which then requires u128 divide on host. The
+ * exception case could be easily handled before calling "reciprocal_value_adv".
+ *
+ * The advanced version requires more complex calculation to get the reciprocal
+ * multiplier and other control variables, but then could reduce the required
+ * emulation operations.
+ *
+ * It makes no sense to use this advanced version for host divide emulation,
+ * those extra complexities for calculating multiplier etc could completely
+ * waive our saving on emulation operations.
+ *
+ * However, it makes sense to use it for JIT divide code generation for which
+ * we are willing to trade performance of JITed code with that of host. As shown
+ * by the following pseudo code, the required emulation operations could go down
+ * from 6 (the basic version) to 3 or 4.
+ *
+ * To use the result of "reciprocal_value_adv", suppose we want to calculate
+ * n/d, the pseudo C code will be:
+ *
+ *   struct reciprocal_value_adv rvalue;
+ *   u8 pre_shift, exp;
+ *
+ *   // handle exception case.
+ *   if (d >= (1U << 31)) {
+ *     result = n >= d;
+ *     return;
+ *   }
+ *
+ *   rvalue = reciprocal_value_adv(d, 32)
+ *   exp = rvalue.exp;
+ *   if (rvalue.is_wide_m && !(d & 1)) {
+ *     // floor(log2(d & (2^32 -d)))
+ *     pre_shift = fls(d & -d) - 1;
+ *     rvalue = reciprocal_value_adv(d >> pre_shift, 32 - pre_shift);
+ *   } else {
+ *     pre_shift = 0;
+ *   }
+ *
+ *   // code generation starts.
+ *   if (imm == 1U << exp) {
+ *     result = n >> exp;
+ *   } else if (rvalue.is_wide_m) {
+ *     // pre_shift must be zero when reached here.
+ *     t = (n * rvalue.m) >> 32;
+ *     result = n - t;
+ *     result >>= 1;
+ *     result += t;
+ *     result >>= rvalue.sh - 1;
+ *   } else {
+ *     if (pre_shift)
+ *       result = n >> pre_shift;
+ *     result = ((u64)result * rvalue.m) >> 32;
+ *     result >>= rvalue.sh;
+ *   }
+ */
+struct reciprocal_value_adv reciprocal_value_adv(u32 d, u8 prec);
+
 #endif /* _LINUX_RECIPROCAL_DIV_H */
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 2deea7166a34..fcb033f51d8c 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -144,4 +144,17 @@ xdp_data_meta_unsupported(const struct xdp_buff *xdp)
 	return unlikely(xdp->data_meta > xdp->data);
 }
 
+struct xdp_attachment_info {
+	struct bpf_prog *prog;
+	u32 flags;
+};
+
+struct netdev_bpf;
+int xdp_attachment_query(struct xdp_attachment_info *info,
+			 struct netdev_bpf *bpf);
+bool xdp_attachment_flags_ok(struct xdp_attachment_info *info,
+			     struct netdev_bpf *bpf);
+void xdp_attachment_setup(struct xdp_attachment_info *info,
+			  struct netdev_bpf *bpf);
+
 #endif /* __LINUX_NET_XDP_H__ */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index b7db3261c62d..870113916cac 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1826,7 +1826,7 @@ union bpf_attr {
  * 		A non-negative value equal to or less than *size* on success,
  * 		or a negative error in case of failure.
  *
- * int skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
+ * int bpf_skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
  * 	Description
  * 		This helper is similar to **bpf_skb_load_bytes**\ () in that
  * 		it provides an easy way to load *len* bytes from *offset*
@@ -1877,7 +1877,7 @@ union bpf_attr {
  *		* < 0 if any input argument is invalid
  *		*   0 on success (packet is forwarded, nexthop neighbor exists)
  *		* > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
- *		*     packet is not forwarded or needs assist from full stack
+ *		  packet is not forwarded or needs assist from full stack
  *
  * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
  *	Description
@@ -2033,7 +2033,6 @@ union bpf_attr {
  *		This helper is only available is the kernel was compiled with
  *		the **CONFIG_BPF_LIRC_MODE2** configuration option set to
  *		"**y**".
- *
  *	Return
  *		0
  *
@@ -2053,7 +2052,6 @@ union bpf_attr {
  *		This helper is only available is the kernel was compiled with
  *		the **CONFIG_BPF_LIRC_MODE2** configuration option set to
  *		"**y**".
- *
  *	Return
  *		0
  *
@@ -2557,6 +2555,9 @@ enum {
 					 * Arg1: old_state
 					 * Arg2: new_state
 					 */
+	BPF_SOCK_OPS_TCP_LISTEN_CB,	/* Called on listen(2), right after
+					 * socket transition to LISTEN state.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index cf01b6824244..8759cfb8aa2e 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -920,6 +920,7 @@ enum {
 	XDP_ATTACHED_DRV,
 	XDP_ATTACHED_SKB,
 	XDP_ATTACHED_HW,
+	XDP_ATTACHED_MULTI,
 };
 
 enum {
@@ -928,6 +929,9 @@ enum {
 	IFLA_XDP_ATTACHED,
 	IFLA_XDP_FLAGS,
 	IFLA_XDP_PROG_ID,
+	IFLA_XDP_DRV_PROG_ID,
+	IFLA_XDP_SKB_PROG_ID,
+	IFLA_XDP_HW_PROG_ID,
 	__IFLA_XDP_MAX,
 };
 
diff --git a/lib/reciprocal_div.c b/lib/reciprocal_div.c
index fcb4ce682c6f..bf043258fa00 100644
--- a/lib/reciprocal_div.c
+++ b/lib/reciprocal_div.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/bug.h>
 #include <linux/kernel.h>
 #include <asm/div64.h>
 #include <linux/reciprocal_div.h>
@@ -26,3 +27,43 @@ struct reciprocal_value reciprocal_value(u32 d)
 	return R;
 }
 EXPORT_SYMBOL(reciprocal_value);
+
+struct reciprocal_value_adv reciprocal_value_adv(u32 d, u8 prec)
+{
+	struct reciprocal_value_adv R;
+	u32 l, post_shift;
+	u64 mhigh, mlow;
+
+	/* ceil(log2(d)) */
+	l = fls(d - 1);
+	/* NOTE: mlow/mhigh could overflow u64 when l == 32. This case needs to
+	 * be handled before calling "reciprocal_value_adv", please see the
+	 * comment at include/linux/reciprocal_div.h.
+	 */
+	WARN(l == 32,
+	     "ceil(log2(0x%08x)) == 32, %s doesn't support such divisor",
+	     d, __func__);
+	post_shift = l;
+	mlow = 1ULL << (32 + l);
+	do_div(mlow, d);
+	mhigh = (1ULL << (32 + l)) + (1ULL << (32 + l - prec));
+	do_div(mhigh, d);
+
+	for (; post_shift > 0; post_shift--) {
+		u64 lo = mlow >> 1, hi = mhigh >> 1;
+
+		if (lo >= hi)
+			break;
+
+		mlow = lo;
+		mhigh = hi;
+	}
+
+	R.m = (u32)mhigh;
+	R.sh = post_shift;
+	R.exp = l;
+	R.is_wide_m = mhigh > U32_MAX;
+
+	return R;
+}
+EXPORT_SYMBOL(reciprocal_value_adv);
diff --git a/net/core/dev.c b/net/core/dev.c
index 14a748ee8cc9..0df1771a12f9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5042,7 +5042,6 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
 		break;
 
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!old;
 		xdp->prog_id = old ? old->aux->id : 0;
 		break;
 
@@ -7706,23 +7705,21 @@ int dev_change_proto_down(struct net_device *dev, bool proto_down)
 }
 EXPORT_SYMBOL(dev_change_proto_down);
 
-void __dev_xdp_query(struct net_device *dev, bpf_op_t bpf_op,
-		     struct netdev_bpf *xdp)
-{
-	memset(xdp, 0, sizeof(*xdp));
-	xdp->command = XDP_QUERY_PROG;
-
-	/* Query must always succeed. */
-	WARN_ON(bpf_op(dev, xdp) < 0);
-}
-
-static u8 __dev_xdp_attached(struct net_device *dev, bpf_op_t bpf_op)
+u32 __dev_xdp_query(struct net_device *dev, bpf_op_t bpf_op,
+		    enum bpf_netdev_command cmd)
 {
 	struct netdev_bpf xdp;
 
-	__dev_xdp_query(dev, bpf_op, &xdp);
+	if (!bpf_op)
+		return 0;
 
-	return xdp.prog_attached;
+	memset(&xdp, 0, sizeof(xdp));
+	xdp.command = cmd;
+
+	/* Query must always succeed. */
+	WARN_ON(bpf_op(dev, &xdp) < 0 && cmd == XDP_QUERY_PROG);
+
+	return xdp.prog_id;
 }
 
 static int dev_xdp_install(struct net_device *dev, bpf_op_t bpf_op,
@@ -7756,12 +7753,19 @@ static void dev_xdp_uninstall(struct net_device *dev)
 	if (!ndo_bpf)
 		return;
 
-	__dev_xdp_query(dev, ndo_bpf, &xdp);
-	if (xdp.prog_attached == XDP_ATTACHED_NONE)
-		return;
+	memset(&xdp, 0, sizeof(xdp));
+	xdp.command = XDP_QUERY_PROG;
+	WARN_ON(ndo_bpf(dev, &xdp));
+	if (xdp.prog_id)
+		WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags,
+					NULL));
 
-	/* Program removal should always succeed */
-	WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags, NULL));
+	/* Remove HW offload */
+	memset(&xdp, 0, sizeof(xdp));
+	xdp.command = XDP_QUERY_PROG_HW;
+	if (!ndo_bpf(dev, &xdp) && xdp.prog_id)
+		WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags,
+					NULL));
 }
 
 /**
@@ -7777,12 +7781,15 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		      int fd, u32 flags)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
+	enum bpf_netdev_command query;
 	struct bpf_prog *prog = NULL;
 	bpf_op_t bpf_op, bpf_chk;
 	int err;
 
 	ASSERT_RTNL();
 
+	query = flags & XDP_FLAGS_HW_MODE ? XDP_QUERY_PROG_HW : XDP_QUERY_PROG;
+
 	bpf_op = bpf_chk = ops->ndo_bpf;
 	if (!bpf_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE)))
 		return -EOPNOTSUPP;
@@ -7792,10 +7799,11 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		bpf_chk = generic_xdp_install;
 
 	if (fd >= 0) {
-		if (bpf_chk && __dev_xdp_attached(dev, bpf_chk))
+		if (__dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG) ||
+		    __dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG_HW))
 			return -EEXIST;
 		if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) &&
-		    __dev_xdp_attached(dev, bpf_op))
+		    __dev_xdp_query(dev, bpf_op, query))
 			return -EBUSY;
 
 		prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP,
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e3f743c141b3..e03258e954c8 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -964,7 +964,8 @@ static size_t rtnl_xdp_size(void)
 {
 	size_t xdp_size = nla_total_size(0) +	/* nest IFLA_XDP */
 			  nla_total_size(1) +	/* XDP_ATTACHED */
-			  nla_total_size(4);	/* XDP_PROG_ID */
+			  nla_total_size(4) +	/* XDP_PROG_ID (or 1st mode) */
+			  nla_total_size(4);	/* XDP_<mode>_PROG_ID */
 
 	return xdp_size;
 }
@@ -1353,27 +1354,51 @@ static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev)
 	return 0;
 }
 
-static u8 rtnl_xdp_attached_mode(struct net_device *dev, u32 *prog_id)
+static u32 rtnl_xdp_prog_skb(struct net_device *dev)
 {
-	const struct net_device_ops *ops = dev->netdev_ops;
 	const struct bpf_prog *generic_xdp_prog;
-	struct netdev_bpf xdp;
 
 	ASSERT_RTNL();
 
-	*prog_id = 0;
 	generic_xdp_prog = rtnl_dereference(dev->xdp_prog);
-	if (generic_xdp_prog) {
-		*prog_id = generic_xdp_prog->aux->id;
-		return XDP_ATTACHED_SKB;
-	}
-	if (!ops->ndo_bpf)
-		return XDP_ATTACHED_NONE;
+	if (!generic_xdp_prog)
+		return 0;
+	return generic_xdp_prog->aux->id;
+}
 
-	__dev_xdp_query(dev, ops->ndo_bpf, &xdp);
-	*prog_id = xdp.prog_id;
+static u32 rtnl_xdp_prog_drv(struct net_device *dev)
+{
+	return __dev_xdp_query(dev, dev->netdev_ops->ndo_bpf, XDP_QUERY_PROG);
+}
 
-	return xdp.prog_attached;
+static u32 rtnl_xdp_prog_hw(struct net_device *dev)
+{
+	return __dev_xdp_query(dev, dev->netdev_ops->ndo_bpf,
+			       XDP_QUERY_PROG_HW);
+}
+
+static int rtnl_xdp_report_one(struct sk_buff *skb, struct net_device *dev,
+			       u32 *prog_id, u8 *mode, u8 tgt_mode, u32 attr,
+			       u32 (*get_prog_id)(struct net_device *dev))
+{
+	u32 curr_id;
+	int err;
+
+	curr_id = get_prog_id(dev);
+	if (!curr_id)
+		return 0;
+
+	*prog_id = curr_id;
+	err = nla_put_u32(skb, attr, curr_id);
+	if (err)
+		return err;
+
+	if (*mode != XDP_ATTACHED_NONE)
+		*mode = XDP_ATTACHED_MULTI;
+	else
+		*mode = tgt_mode;
+
+	return 0;
 }
 
 static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev)
@@ -1381,17 +1406,29 @@ static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev)
 	struct nlattr *xdp;
 	u32 prog_id;
 	int err;
+	u8 mode;
 
 	xdp = nla_nest_start(skb, IFLA_XDP);
 	if (!xdp)
 		return -EMSGSIZE;
 
-	err = nla_put_u8(skb, IFLA_XDP_ATTACHED,
-			 rtnl_xdp_attached_mode(dev, &prog_id));
+	prog_id = 0;
+	mode = XDP_ATTACHED_NONE;
+	if (rtnl_xdp_report_one(skb, dev, &prog_id, &mode, XDP_ATTACHED_SKB,
+				IFLA_XDP_SKB_PROG_ID, rtnl_xdp_prog_skb))
+		goto err_cancel;
+	if (rtnl_xdp_report_one(skb, dev, &prog_id, &mode, XDP_ATTACHED_DRV,
+				IFLA_XDP_DRV_PROG_ID, rtnl_xdp_prog_drv))
+		goto err_cancel;
+	if (rtnl_xdp_report_one(skb, dev, &prog_id, &mode, XDP_ATTACHED_HW,
+				IFLA_XDP_HW_PROG_ID, rtnl_xdp_prog_hw))
+		goto err_cancel;
+
+	err = nla_put_u8(skb, IFLA_XDP_ATTACHED, mode);
 	if (err)
 		goto err_cancel;
 
-	if (prog_id) {
+	if (prog_id && mode != XDP_ATTACHED_MULTI) {
 		err = nla_put_u32(skb, IFLA_XDP_PROG_ID, prog_id);
 		if (err)
 			goto err_cancel;
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 31c58719b5a9..57285383ed00 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -3,8 +3,11 @@
  * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
  * Released under terms in GPL version 2.  See COPYING.
  */
+#include <linux/bpf.h>
+#include <linux/filter.h>
 #include <linux/types.h>
 #include <linux/mm.h>
+#include <linux/netdevice.h>
 #include <linux/slab.h>
 #include <linux/idr.h>
 #include <linux/rhashtable.h>
@@ -370,3 +373,34 @@ void xdp_return_buff(struct xdp_buff *xdp)
 	__xdp_return(xdp->data, &xdp->rxq->mem, true, xdp->handle);
 }
 EXPORT_SYMBOL_GPL(xdp_return_buff);
+
+int xdp_attachment_query(struct xdp_attachment_info *info,
+			 struct netdev_bpf *bpf)
+{
+	bpf->prog_id = info->prog ? info->prog->aux->id : 0;
+	bpf->prog_flags = info->prog ? info->flags : 0;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xdp_attachment_query);
+
+bool xdp_attachment_flags_ok(struct xdp_attachment_info *info,
+			     struct netdev_bpf *bpf)
+{
+	if (info->prog && (bpf->flags ^ info->flags) & XDP_FLAGS_MODES) {
+		NL_SET_ERR_MSG(bpf->extack,
+			       "program loaded with different flags");
+		return false;
+	}
+	return true;
+}
+EXPORT_SYMBOL_GPL(xdp_attachment_flags_ok);
+
+void xdp_attachment_setup(struct xdp_attachment_info *info,
+			  struct netdev_bpf *bpf)
+{
+	if (info->prog)
+		bpf_prog_put(info->prog);
+	info->prog = bpf->prog;
+	info->flags = bpf->flags;
+}
+EXPORT_SYMBOL_GPL(xdp_attachment_setup);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index c716be13d58c..f2a0a3bab6b5 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -229,6 +229,7 @@ int inet_listen(struct socket *sock, int backlog)
 		err = inet_csk_listen_start(sk, backlog);
 		if (err)
 			goto out;
+		tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_LISTEN_CB, 0, NULL);
 	}
 	sk->sk_max_ack_backlog = backlog;
 	err = 0;
diff --git a/samples/bpf/xdp_redirect_cpu_kern.c b/samples/bpf/xdp_redirect_cpu_kern.c
index 303e9e7161f3..8cb703671b04 100644
--- a/samples/bpf/xdp_redirect_cpu_kern.c
+++ b/samples/bpf/xdp_redirect_cpu_kern.c
@@ -134,7 +134,16 @@ bool parse_eth(struct ethhdr *eth, void *data_end,
 			return false;
 		eth_type = vlan_hdr->h_vlan_encapsulated_proto;
 	}
-	/* TODO: Handle double VLAN tagged packet */
+	/* Handle double VLAN tagged packet */
+	if (eth_type == htons(ETH_P_8021Q) || eth_type == htons(ETH_P_8021AD)) {
+		struct vlan_hdr *vlan_hdr;
+
+		vlan_hdr = (void *)eth + offset;
+		offset += sizeof(*vlan_hdr);
+		if ((void *)eth + offset > data_end)
+			return false;
+		eth_type = vlan_hdr->h_vlan_encapsulated_proto;
+	}
 
 	*eth_proto = ntohs(eth_type);
 	*l3_offset = offset;
diff --git a/tools/bpf/Makefile.helpers b/tools/bpf/Makefile.helpers
new file mode 100644
index 000000000000..c34fea77f39f
--- /dev/null
+++ b/tools/bpf/Makefile.helpers
@@ -0,0 +1,59 @@
+ifndef allow-override
+  include ../scripts/Makefile.include
+  include ../scripts/utilities.mak
+else
+  # Assume Makefile.helpers is being run from bpftool/Documentation
+  # subdirectory. Go up two more directories to fetch bpf.h header and
+  # associated script.
+  UP2DIR := ../../
+endif
+
+INSTALL ?= install
+RM ?= rm -f
+RMDIR ?= rmdir --ignore-fail-on-non-empty
+
+ifeq ($(V),1)
+  Q =
+else
+  Q = @
+endif
+
+prefix ?= /usr/local
+mandir ?= $(prefix)/man
+man7dir = $(mandir)/man7
+
+HELPERS_RST = bpf-helpers.rst
+MAN7_RST = $(HELPERS_RST)
+
+_DOC_MAN7 = $(patsubst %.rst,%.7,$(MAN7_RST))
+DOC_MAN7 = $(addprefix $(OUTPUT),$(_DOC_MAN7))
+
+helpers: man7
+man7: $(DOC_MAN7)
+
+RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null)
+
+$(OUTPUT)$(HELPERS_RST): $(UP2DIR)../../include/uapi/linux/bpf.h
+	$(QUIET_GEN)$(UP2DIR)../../scripts/bpf_helpers_doc.py --filename $< > $@
+
+$(OUTPUT)%.7: $(OUTPUT)%.rst
+ifndef RST2MAN_DEP
+	$(error "rst2man not found, but required to generate man pages")
+endif
+	$(QUIET_GEN)rst2man $< > $@
+
+helpers-clean:
+	$(call QUIET_CLEAN, eBPF_helpers-manpage)
+	$(Q)$(RM) $(DOC_MAN7) $(OUTPUT)$(HELPERS_RST)
+
+helpers-install: helpers
+	$(call QUIET_INSTALL, eBPF_helpers-manpage)
+	$(Q)$(INSTALL) -d -m 755 $(DESTDIR)$(man7dir)
+	$(Q)$(INSTALL) -m 644 $(DOC_MAN7) $(DESTDIR)$(man7dir)
+
+helpers-uninstall:
+	$(call QUIET_UNINST, eBPF_helpers-manpage)
+	$(Q)$(RM) $(addprefix $(DESTDIR)$(man7dir)/,$(_DOC_MAN7))
+	$(Q)$(RMDIR) $(DESTDIR)$(man7dir)
+
+.PHONY: helpers helpers-clean helpers-install helpers-uninstall
diff --git a/tools/bpf/bpftool/Documentation/Makefile b/tools/bpf/bpftool/Documentation/Makefile
index a9d47c1558bb..f7663a3e60c9 100644
--- a/tools/bpf/bpftool/Documentation/Makefile
+++ b/tools/bpf/bpftool/Documentation/Makefile
@@ -15,12 +15,15 @@ prefix ?= /usr/local
 mandir ?= $(prefix)/man
 man8dir = $(mandir)/man8
 
-MAN8_RST = $(wildcard *.rst)
+# Load targets for building eBPF helpers man page.
+include ../../Makefile.helpers
+
+MAN8_RST = $(filter-out $(HELPERS_RST),$(wildcard *.rst))
 
 _DOC_MAN8 = $(patsubst %.rst,%.8,$(MAN8_RST))
 DOC_MAN8 = $(addprefix $(OUTPUT),$(_DOC_MAN8))
 
-man: man8
+man: man8 helpers
 man8: $(DOC_MAN8)
 
 RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null)
@@ -31,16 +34,16 @@ ifndef RST2MAN_DEP
 endif
 	$(QUIET_GEN)rst2man $< > $@
 
-clean:
+clean: helpers-clean
 	$(call QUIET_CLEAN, Documentation)
 	$(Q)$(RM) $(DOC_MAN8)
 
-install: man
+install: man helpers-install
 	$(call QUIET_INSTALL, Documentation-man)
 	$(Q)$(INSTALL) -d -m 755 $(DESTDIR)$(man8dir)
 	$(Q)$(INSTALL) -m 644 $(DOC_MAN8) $(DESTDIR)$(man8dir)
 
-uninstall:
+uninstall: helpers-uninstall
 	$(call QUIET_UNINST, Documentation-man)
 	$(Q)$(RM) $(addprefix $(DESTDIR)$(man8dir)/,$(_DOC_MAN8))
 	$(Q)$(RMDIR) $(DESTDIR)$(man8dir)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
index 7b0e6d453e92..edbe81534c6d 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
@@ -15,12 +15,13 @@ SYNOPSIS
 	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-f** | **--bpffs** } }
 
 	*COMMANDS* :=
-	{ **show** | **list** | **attach** | **detach** | **help** }
+	{ **show** | **list** | **tree** | **attach** | **detach** | **help** }
 
 MAP COMMANDS
 =============
 
 |	**bpftool** **cgroup { show | list }** *CGROUP*
+|	**bpftool** **cgroup tree** [*CGROUP_ROOT*]
 |	**bpftool** **cgroup attach** *CGROUP* *ATTACH_TYPE* *PROG* [*ATTACH_FLAGS*]
 |	**bpftool** **cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG*
 |	**bpftool** **cgroup help**
@@ -39,6 +40,15 @@ DESCRIPTION
 		  Output will start with program ID followed by attach type,
 		  attach flags and program name.
 
+	**bpftool cgroup tree** [*CGROUP_ROOT*]
+		  Iterate over all cgroups in *CGROUP_ROOT* and list all
+		  attached programs. If *CGROUP_ROOT* is not specified,
+		  bpftool uses cgroup v2 mountpoint.
+
+		  The output is similar to the output of cgroup show/list
+		  commands: it starts with absolute cgroup path, followed by
+		  program ID, attach type, attach flags and program name.
+
 	**bpftool cgroup attach** *CGROUP* *ATTACH_TYPE* *PROG* [*ATTACH_FLAGS*]
 		  Attach program *PROG* to the cgroup *CGROUP* with attach type
 		  *ATTACH_TYPE* and optional *ATTACH_FLAGS*.
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 43d34a5c3ec5..64156a16d530 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -24,10 +24,20 @@ MAP COMMANDS
 |	**bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes** | **visual**}]
 |	**bpftool** **prog dump jited**  *PROG* [{**file** *FILE* | **opcodes**}]
 |	**bpftool** **prog pin** *PROG* *FILE*
-|	**bpftool** **prog load** *OBJ* *FILE*
+|	**bpftool** **prog load** *OBJ* *FILE* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
 |	**bpftool** **prog help**
 |
+|	*MAP* := { **id** *MAP_ID* | **pinned** *FILE* }
 |	*PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* }
+|	*TYPE* := {
+|		**socket** | **kprobe** | **kretprobe** | **classifier** | **action** |
+|		**tracepoint** | **raw_tracepoint** | **xdp** | **perf_event** | **cgroup/skb** |
+|		**cgroup/sock** | **cgroup/dev** | **lwt_in** | **lwt_out** | **lwt_xmit** |
+|		**lwt_seg6local** | **sockops** | **sk_skb** | **sk_msg** | **lirc_mode2** |
+|		**cgroup/bind4** | **cgroup/bind6** | **cgroup/post_bind4** | **cgroup/post_bind6** |
+|		**cgroup/connect4** | **cgroup/connect6** | **cgroup/sendmsg4** | **cgroup/sendmsg6**
+|	}
+
 
 DESCRIPTION
 ===========
@@ -64,8 +74,19 @@ DESCRIPTION
 
 		  Note: *FILE* must be located in *bpffs* mount.
 
-	**bpftool prog load** *OBJ* *FILE*
+	**bpftool prog load** *OBJ* *FILE* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
 		  Load bpf program from binary *OBJ* and pin as *FILE*.
+		  **type** is optional, if not specified program type will be
+		  inferred from section names.
+		  By default bpftool will create new maps as declared in the ELF
+		  object being loaded.  **map** parameter allows for the reuse
+		  of existing maps.  It can be specified multiple times, each
+		  time for a different map.  *IDX* refers to index of the map
+		  to be replaced in the ELF file counting from 0, while *NAME*
+		  allows to replace a map by name.  *MAP* specifies the map to
+		  use, referring to it by **id** or through a **pinned** file.
+		  If **dev** *NAME* is specified program will be loaded onto
+		  given networking device (offload).
 
 		  Note: *FILE* must be located in *bpffs* mount.
 
@@ -159,6 +180,14 @@ EXAMPLES
     mov    %rbx,0x0(%rbp)
     48 89 5d 00
 
+|
+| **# bpftool prog load xdp1_kern.o /sys/fs/bpf/xdp1 type xdp map name rxcnt id 7**
+| **# bpftool prog show pinned /sys/fs/bpf/xdp1**
+|   9: xdp  name xdp_prog1  tag 539ec6ce11b52f98  gpl
+|	loaded_at 2018-06-25T16:17:31-0700  uid 0
+|	xlated 488B  jited 336B  memlock 4096B  map_ids 7
+| **# rm /sys/fs/bpf/xdp1**
+|
 
 SEE ALSO
 ========
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 0911b00b25cc..6c4830e18879 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -52,7 +52,7 @@ INSTALL ?= install
 RM ?= rm -f
 
 FEATURE_USER = .bpftool
-FEATURE_TESTS = libbfd disassembler-four-args
+FEATURE_TESTS = libbfd disassembler-four-args reallocarray
 FEATURE_DISPLAY = libbfd disassembler-four-args
 
 check_feat := 1
@@ -75,6 +75,10 @@ ifeq ($(feature-disassembler-four-args), 1)
 CFLAGS += -DDISASM_FOUR_ARGS_SIGNATURE
 endif
 
+ifeq ($(feature-reallocarray), 0)
+CFLAGS += -DCOMPAT_NEED_REALLOCARRAY
+endif
+
 include $(wildcard $(OUTPUT)*.d)
 
 all: $(OUTPUT)bpftool
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index fffd76f4998b..598066c40191 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -99,6 +99,35 @@ _bpftool_get_prog_tags()
         command sed -n 's/.*"tag": "\(.*\)",$/\1/p' )" -- "$cur" ) )
 }
 
+_bpftool_get_obj_map_names()
+{
+    local obj
+
+    obj=$1
+
+    maps=$(objdump -j maps -t $obj 2>/dev/null | \
+        command awk '/g     . maps/ {print $NF}')
+
+    COMPREPLY+=( $( compgen -W "$maps" -- "$cur" ) )
+}
+
+_bpftool_get_obj_map_idxs()
+{
+    local obj
+
+    obj=$1
+
+    nmaps=$(objdump -j maps -t $obj 2>/dev/null | grep -c 'g     . maps')
+
+    COMPREPLY+=( $( compgen -W "$(seq 0 $((nmaps - 1)))" -- "$cur" ) )
+}
+
+_sysfs_get_netdevs()
+{
+    COMPREPLY+=( $( compgen -W "$( ls /sys/class/net 2>/dev/null )" -- \
+        "$cur" ) )
+}
+
 # For bpftool map update: retrieve type of the map to update.
 _bpftool_map_update_map_type()
 {
@@ -214,12 +243,14 @@ _bpftool()
     # Completion depends on object and command in use
     case $object in
         prog)
-            case $prev in
-                id)
-                    _bpftool_get_prog_ids
-                    return 0
-                    ;;
-            esac
+            if [[ $command != "load" ]]; then
+                case $prev in
+                    id)
+                        _bpftool_get_prog_ids
+                        return 0
+                        ;;
+                esac
+            fi
 
             local PROG_TYPE='id pinned tag'
             case $command in
@@ -262,8 +293,57 @@ _bpftool()
                     return 0
                     ;;
                 load)
-                    _filedir
-                    return 0
+                    local obj
+
+                    if [[ ${#words[@]} -lt 6 ]]; then
+                        _filedir
+                        return 0
+                    fi
+
+                    obj=${words[3]}
+
+                    if [[ ${words[-4]} == "map" ]]; then
+                        COMPREPLY=( $( compgen -W "id pinned" -- "$cur" ) )
+                        return 0
+                    fi
+                    if [[ ${words[-3]} == "map" ]]; then
+                        if [[ ${words[-2]} == "idx" ]]; then
+                            _bpftool_get_obj_map_idxs $obj
+                        elif [[ ${words[-2]} == "name" ]]; then
+                            _bpftool_get_obj_map_names $obj
+                        fi
+                        return 0
+                    fi
+                    if [[ ${words[-2]} == "map" ]]; then
+                        COMPREPLY=( $( compgen -W "idx name" -- "$cur" ) )
+                        return 0
+                    fi
+
+                    case $prev in
+                        type)
+                            COMPREPLY=( $( compgen -W "socket kprobe kretprobe classifier action tracepoint raw_tracepoint xdp perf_event cgroup/skb cgroup/sock cgroup/dev lwt_in lwt_out lwt_xmit lwt_seg6local sockops sk_skb sk_msg lirc_mode2 cgroup/bind4 cgroup/bind6 cgroup/connect4 cgroup/connect6 cgroup/sendmsg4 cgroup/sendmsg6 cgroup/post_bind4 cgroup/post_bind6" -- \
+                                                   "$cur" ) )
+                            return 0
+                            ;;
+                        id)
+                            _bpftool_get_map_ids
+                            return 0
+                            ;;
+                        pinned)
+                            _filedir
+                            return 0
+                            ;;
+                        dev)
+                            _sysfs_get_netdevs
+                            return 0
+                            ;;
+                        *)
+                            COMPREPLY=( $( compgen -W "map" -- "$cur" ) )
+                            _bpftool_once_attr 'type'
+                            _bpftool_once_attr 'dev'
+                            return 0
+                            ;;
+                    esac
                     ;;
                 *)
                     [[ $prev == $object ]] && \
@@ -414,6 +494,10 @@ _bpftool()
                     _filedir
                     return 0
                     ;;
+		tree)
+		    _filedir
+		    return 0
+		    ;;
                 attach|detach)
                     local ATTACH_TYPES='ingress egress sock_create sock_ops \
                         device bind4 bind6 post_bind4 post_bind6 connect4 \
@@ -455,7 +539,7 @@ _bpftool()
                 *)
                     [[ $prev == $object ]] && \
                         COMPREPLY=( $( compgen -W 'help attach detach \
-                            show list' -- "$cur" ) )
+                            show list tree' -- "$cur" ) )
                     ;;
             esac
             ;;
diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c
new file mode 100644
index 000000000000..55bc512a1831
--- /dev/null
+++ b/tools/bpf/bpftool/btf_dumper.c
@@ -0,0 +1,251 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 Facebook */
+
+#include <ctype.h>
+#include <stdio.h> /* for (FILE *) used by json_writer */
+#include <string.h>
+#include <asm/byteorder.h>
+#include <linux/bitops.h>
+#include <linux/btf.h>
+#include <linux/err.h>
+
+#include "btf.h"
+#include "json_writer.h"
+#include "main.h"
+
+#define BITS_PER_BYTE_MASK (BITS_PER_BYTE - 1)
+#define BITS_PER_BYTE_MASKED(bits) ((bits) & BITS_PER_BYTE_MASK)
+#define BITS_ROUNDDOWN_BYTES(bits) ((bits) >> 3)
+#define BITS_ROUNDUP_BYTES(bits) \
+	(BITS_ROUNDDOWN_BYTES(bits) + !!BITS_PER_BYTE_MASKED(bits))
+
+static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id,
+			      __u8 bit_offset, const void *data);
+
+static void btf_dumper_ptr(const void *data, json_writer_t *jw,
+			   bool is_plain_text)
+{
+	if (is_plain_text)
+		jsonw_printf(jw, "%p", *(unsigned long *)data);
+	else
+		jsonw_printf(jw, "%u", *(unsigned long *)data);
+}
+
+static int btf_dumper_modifier(const struct btf_dumper *d, __u32 type_id,
+			       const void *data)
+{
+	int actual_type_id;
+
+	actual_type_id = btf__resolve_type(d->btf, type_id);
+	if (actual_type_id < 0)
+		return actual_type_id;
+
+	return btf_dumper_do_type(d, actual_type_id, 0, data);
+}
+
+static void btf_dumper_enum(const void *data, json_writer_t *jw)
+{
+	jsonw_printf(jw, "%d", *(int *)data);
+}
+
+static int btf_dumper_array(const struct btf_dumper *d, __u32 type_id,
+			    const void *data)
+{
+	const struct btf_type *t = btf__type_by_id(d->btf, type_id);
+	struct btf_array *arr = (struct btf_array *)(t + 1);
+	long long elem_size;
+	int ret = 0;
+	__u32 i;
+
+	elem_size = btf__resolve_size(d->btf, arr->type);
+	if (elem_size < 0)
+		return elem_size;
+
+	jsonw_start_array(d->jw);
+	for (i = 0; i < arr->nelems; i++) {
+		ret = btf_dumper_do_type(d, arr->type, 0,
+					 data + i * elem_size);
+		if (ret)
+			break;
+	}
+
+	jsonw_end_array(d->jw);
+	return ret;
+}
+
+static void btf_dumper_int_bits(__u32 int_type, __u8 bit_offset,
+				const void *data, json_writer_t *jw,
+				bool is_plain_text)
+{
+	int left_shift_bits, right_shift_bits;
+	int nr_bits = BTF_INT_BITS(int_type);
+	int total_bits_offset;
+	int bytes_to_copy;
+	int bits_to_copy;
+	__u64 print_num;
+
+	total_bits_offset = bit_offset + BTF_INT_OFFSET(int_type);
+	data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
+	bit_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
+	bits_to_copy = bit_offset + nr_bits;
+	bytes_to_copy = BITS_ROUNDUP_BYTES(bits_to_copy);
+
+	print_num = 0;
+	memcpy(&print_num, data, bytes_to_copy);
+#if defined(__BIG_ENDIAN_BITFIELD)
+	left_shift_bits = bit_offset;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	left_shift_bits = 64 - bits_to_copy;
+#else
+#error neither big nor little endian
+#endif
+	right_shift_bits = 64 - nr_bits;
+
+	print_num <<= left_shift_bits;
+	print_num >>= right_shift_bits;
+	if (is_plain_text)
+		jsonw_printf(jw, "0x%llx", print_num);
+	else
+		jsonw_printf(jw, "%llu", print_num);
+}
+
+static int btf_dumper_int(const struct btf_type *t, __u8 bit_offset,
+			  const void *data, json_writer_t *jw,
+			  bool is_plain_text)
+{
+	__u32 *int_type;
+	__u32 nr_bits;
+
+	int_type = (__u32 *)(t + 1);
+	nr_bits = BTF_INT_BITS(*int_type);
+	/* if this is bit field */
+	if (bit_offset || BTF_INT_OFFSET(*int_type) ||
+	    BITS_PER_BYTE_MASKED(nr_bits)) {
+		btf_dumper_int_bits(*int_type, bit_offset, data, jw,
+				    is_plain_text);
+		return 0;
+	}
+
+	switch (BTF_INT_ENCODING(*int_type)) {
+	case 0:
+		if (BTF_INT_BITS(*int_type) == 64)
+			jsonw_printf(jw, "%lu", *(__u64 *)data);
+		else if (BTF_INT_BITS(*int_type) == 32)
+			jsonw_printf(jw, "%u", *(__u32 *)data);
+		else if (BTF_INT_BITS(*int_type) == 16)
+			jsonw_printf(jw, "%hu", *(__u16 *)data);
+		else if (BTF_INT_BITS(*int_type) == 8)
+			jsonw_printf(jw, "%hhu", *(__u8 *)data);
+		else
+			btf_dumper_int_bits(*int_type, bit_offset, data, jw,
+					    is_plain_text);
+		break;
+	case BTF_INT_SIGNED:
+		if (BTF_INT_BITS(*int_type) == 64)
+			jsonw_printf(jw, "%ld", *(long long *)data);
+		else if (BTF_INT_BITS(*int_type) == 32)
+			jsonw_printf(jw, "%d", *(int *)data);
+		else if (BTF_INT_BITS(*int_type) == 16)
+			jsonw_printf(jw, "%hd", *(short *)data);
+		else if (BTF_INT_BITS(*int_type) == 8)
+			jsonw_printf(jw, "%hhd", *(char *)data);
+		else
+			btf_dumper_int_bits(*int_type, bit_offset, data, jw,
+					    is_plain_text);
+		break;
+	case BTF_INT_CHAR:
+		if (isprint(*(char *)data))
+			jsonw_printf(jw, "\"%c\"", *(char *)data);
+		else
+			if (is_plain_text)
+				jsonw_printf(jw, "0x%hhx", *(char *)data);
+			else
+				jsonw_printf(jw, "\"\\u00%02hhx\"",
+					     *(char *)data);
+		break;
+	case BTF_INT_BOOL:
+		jsonw_bool(jw, *(int *)data);
+		break;
+	default:
+		/* shouldn't happen */
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int btf_dumper_struct(const struct btf_dumper *d, __u32 type_id,
+			     const void *data)
+{
+	const struct btf_type *t;
+	struct btf_member *m;
+	const void *data_off;
+	int ret = 0;
+	int i, vlen;
+
+	t = btf__type_by_id(d->btf, type_id);
+	if (!t)
+		return -EINVAL;
+
+	vlen = BTF_INFO_VLEN(t->info);
+	jsonw_start_object(d->jw);
+	m = (struct btf_member *)(t + 1);
+
+	for (i = 0; i < vlen; i++) {
+		data_off = data + BITS_ROUNDDOWN_BYTES(m[i].offset);
+		jsonw_name(d->jw, btf__name_by_offset(d->btf, m[i].name_off));
+		ret = btf_dumper_do_type(d, m[i].type,
+					 BITS_PER_BYTE_MASKED(m[i].offset),
+					 data_off);
+		if (ret)
+			break;
+	}
+
+	jsonw_end_object(d->jw);
+
+	return ret;
+}
+
+static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id,
+			      __u8 bit_offset, const void *data)
+{
+	const struct btf_type *t = btf__type_by_id(d->btf, type_id);
+
+	switch (BTF_INFO_KIND(t->info)) {
+	case BTF_KIND_INT:
+		return btf_dumper_int(t, bit_offset, data, d->jw,
+				     d->is_plain_text);
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION:
+		return btf_dumper_struct(d, type_id, data);
+	case BTF_KIND_ARRAY:
+		return btf_dumper_array(d, type_id, data);
+	case BTF_KIND_ENUM:
+		btf_dumper_enum(data, d->jw);
+		return 0;
+	case BTF_KIND_PTR:
+		btf_dumper_ptr(data, d->jw, d->is_plain_text);
+		return 0;
+	case BTF_KIND_UNKN:
+		jsonw_printf(d->jw, "(unknown)");
+		return 0;
+	case BTF_KIND_FWD:
+		/* map key or value can't be forward */
+		jsonw_printf(d->jw, "(fwd-kind-invalid)");
+		return -EINVAL;
+	case BTF_KIND_TYPEDEF:
+	case BTF_KIND_VOLATILE:
+	case BTF_KIND_CONST:
+	case BTF_KIND_RESTRICT:
+		return btf_dumper_modifier(d, type_id, data);
+	default:
+		jsonw_printf(d->jw, "(unsupported-kind");
+		return -EINVAL;
+	}
+}
+
+int btf_dumper_type(const struct btf_dumper *d, __u32 type_id,
+		    const void *data)
+{
+	return btf_dumper_do_type(d, type_id, 0, data);
+}
diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c
index 16bee011e16c..ee7a9765c6b3 100644
--- a/tools/bpf/bpftool/cgroup.c
+++ b/tools/bpf/bpftool/cgroup.c
@@ -2,7 +2,12 @@
 // Copyright (C) 2017 Facebook
 // Author: Roman Gushchin <guro@fb.com>
 
+#define _XOPEN_SOURCE 500
+#include <errno.h>
 #include <fcntl.h>
+#include <ftw.h>
+#include <mntent.h>
+#include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <sys/stat.h>
@@ -53,7 +58,8 @@ static enum bpf_attach_type parse_attach_type(const char *str)
 }
 
 static int show_bpf_prog(int id, const char *attach_type_str,
-			 const char *attach_flags_str)
+			 const char *attach_flags_str,
+			 int level)
 {
 	struct bpf_prog_info info = {};
 	__u32 info_len = sizeof(info);
@@ -78,7 +84,8 @@ static int show_bpf_prog(int id, const char *attach_type_str,
 		jsonw_string_field(json_wtr, "name", info.name);
 		jsonw_end_object(json_wtr);
 	} else {
-		printf("%-8u %-15s %-15s %-15s\n", info.id,
+		printf("%s%-8u %-15s %-15s %-15s\n", level ? "    " : "",
+		       info.id,
 		       attach_type_str,
 		       attach_flags_str,
 		       info.name);
@@ -88,7 +95,20 @@ static int show_bpf_prog(int id, const char *attach_type_str,
 	return 0;
 }
 
-static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type)
+static int count_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type)
+{
+	__u32 prog_cnt = 0;
+	int ret;
+
+	ret = bpf_prog_query(cgroup_fd, type, 0, NULL, NULL, &prog_cnt);
+	if (ret)
+		return -1;
+
+	return prog_cnt;
+}
+
+static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type,
+				   int level)
 {
 	__u32 prog_ids[1024] = {0};
 	char *attach_flags_str;
@@ -123,7 +143,7 @@ static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type)
 
 	for (iter = 0; iter < prog_cnt; iter++)
 		show_bpf_prog(prog_ids[iter], attach_type_strings[type],
-			      attach_flags_str);
+			      attach_flags_str, level);
 
 	return 0;
 }
@@ -161,7 +181,7 @@ static int do_show(int argc, char **argv)
 		 * If we were able to get the show for at least one
 		 * attach type, let's return 0.
 		 */
-		if (show_attached_bpf_progs(cgroup_fd, type) == 0)
+		if (show_attached_bpf_progs(cgroup_fd, type, 0) == 0)
 			ret = 0;
 	}
 
@@ -173,6 +193,143 @@ static int do_show(int argc, char **argv)
 	return ret;
 }
 
+/*
+ * To distinguish nftw() errors and do_show_tree_fn() errors
+ * and avoid duplicating error messages, let's return -2
+ * from do_show_tree_fn() in case of error.
+ */
+#define NFTW_ERR		-1
+#define SHOW_TREE_FN_ERR	-2
+static int do_show_tree_fn(const char *fpath, const struct stat *sb,
+			   int typeflag, struct FTW *ftw)
+{
+	enum bpf_attach_type type;
+	bool skip = true;
+	int cgroup_fd;
+
+	if (typeflag != FTW_D)
+		return 0;
+
+	cgroup_fd = open(fpath, O_RDONLY);
+	if (cgroup_fd < 0) {
+		p_err("can't open cgroup %s: %s", fpath, strerror(errno));
+		return SHOW_TREE_FN_ERR;
+	}
+
+	for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) {
+		int count = count_attached_bpf_progs(cgroup_fd, type);
+
+		if (count < 0 && errno != EINVAL) {
+			p_err("can't query bpf programs attached to %s: %s",
+			      fpath, strerror(errno));
+			close(cgroup_fd);
+			return SHOW_TREE_FN_ERR;
+		}
+		if (count > 0) {
+			skip = false;
+			break;
+		}
+	}
+
+	if (skip) {
+		close(cgroup_fd);
+		return 0;
+	}
+
+	if (json_output) {
+		jsonw_start_object(json_wtr);
+		jsonw_string_field(json_wtr, "cgroup", fpath);
+		jsonw_name(json_wtr, "programs");
+		jsonw_start_array(json_wtr);
+	} else {
+		printf("%s\n", fpath);
+	}
+
+	for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++)
+		show_attached_bpf_progs(cgroup_fd, type, ftw->level);
+
+	if (json_output) {
+		jsonw_end_array(json_wtr);
+		jsonw_end_object(json_wtr);
+	}
+
+	close(cgroup_fd);
+
+	return 0;
+}
+
+static char *find_cgroup_root(void)
+{
+	struct mntent *mnt;
+	FILE *f;
+
+	f = fopen("/proc/mounts", "r");
+	if (f == NULL)
+		return NULL;
+
+	while ((mnt = getmntent(f))) {
+		if (strcmp(mnt->mnt_type, "cgroup2") == 0) {
+			fclose(f);
+			return strdup(mnt->mnt_dir);
+		}
+	}
+
+	fclose(f);
+	return NULL;
+}
+
+static int do_show_tree(int argc, char **argv)
+{
+	char *cgroup_root;
+	int ret;
+
+	switch (argc) {
+	case 0:
+		cgroup_root = find_cgroup_root();
+		if (!cgroup_root) {
+			p_err("cgroup v2 isn't mounted");
+			return -1;
+		}
+		break;
+	case 1:
+		cgroup_root = argv[0];
+		break;
+	default:
+		p_err("too many parameters for cgroup tree");
+		return -1;
+	}
+
+
+	if (json_output)
+		jsonw_start_array(json_wtr);
+	else
+		printf("%s\n"
+		       "%-8s %-15s %-15s %-15s\n",
+		       "CgroupPath",
+		       "ID", "AttachType", "AttachFlags", "Name");
+
+	switch (nftw(cgroup_root, do_show_tree_fn, 1024, FTW_MOUNT)) {
+	case NFTW_ERR:
+		p_err("can't iterate over %s: %s", cgroup_root,
+		      strerror(errno));
+		ret = -1;
+		break;
+	case SHOW_TREE_FN_ERR:
+		ret = -1;
+		break;
+	default:
+		ret = 0;
+	}
+
+	if (json_output)
+		jsonw_end_array(json_wtr);
+
+	if (argc == 0)
+		free(cgroup_root);
+
+	return ret;
+}
+
 static int do_attach(int argc, char **argv)
 {
 	enum bpf_attach_type attach_type;
@@ -289,6 +446,7 @@ static int do_help(int argc, char **argv)
 
 	fprintf(stderr,
 		"Usage: %s %s { show | list } CGROUP\n"
+		"       %s %s tree [CGROUP_ROOT]\n"
 		"       %s %s attach CGROUP ATTACH_TYPE PROG [ATTACH_FLAGS]\n"
 		"       %s %s detach CGROUP ATTACH_TYPE PROG\n"
 		"       %s %s help\n"
@@ -298,6 +456,7 @@ static int do_help(int argc, char **argv)
 		"       " HELP_SPEC_PROGRAM "\n"
 		"       " HELP_SPEC_OPTIONS "\n"
 		"",
+		bin_name, argv[-2],
 		bin_name, argv[-2], bin_name, argv[-2],
 		bin_name, argv[-2], bin_name, argv[-2]);
 
@@ -307,6 +466,7 @@ static int do_help(int argc, char **argv)
 static const struct cmd cmds[] = {
 	{ "show",	do_show },
 	{ "list",	do_show },
+	{ "tree",       do_show_tree },
 	{ "attach",	do_attach },
 	{ "detach",	do_detach },
 	{ "help",	do_help },
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index d39f7ef01d23..238e734d75b3 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -42,6 +42,7 @@
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/hashtable.h>
+#include <tools/libc_compat.h>
 
 #include "json_writer.h"
 
@@ -50,6 +51,21 @@
 #define NEXT_ARG()	({ argc--; argv++; if (argc < 0) usage(); })
 #define NEXT_ARGP()	({ (*argc)--; (*argv)++; if (*argc < 0) usage(); })
 #define BAD_ARG()	({ p_err("what is '%s'?", *argv); -1; })
+#define GET_ARG()	({ argc--; *argv++; })
+#define REQ_ARGS(cnt)							\
+	({								\
+		int _cnt = (cnt);					\
+		bool _res;						\
+									\
+		if (argc < _cnt) {					\
+			p_err("'%s' needs at least %d arguments, %d found", \
+			      argv[-1], _cnt, argc);			\
+			_res = false;					\
+		} else {						\
+			_res = true;					\
+		}							\
+		_res;							\
+	})
 
 #define ERR_MAX_LEN	1024
 
@@ -59,6 +75,8 @@
 	"PROG := { id PROG_ID | pinned FILE | tag PROG_TAG }"
 #define HELP_SPEC_OPTIONS						\
 	"OPTIONS := { {-j|--json} [{-p|--pretty}] | {-f|--bpffs} }"
+#define HELP_SPEC_MAP							\
+	"MAP := { id MAP_ID | pinned FILE }"
 
 enum bpf_obj_type {
 	BPF_OBJ_UNKNOWN,
@@ -120,6 +138,7 @@ int do_cgroup(int argc, char **arg);
 int do_perf(int argc, char **arg);
 
 int prog_parse_fd(int *argc, char ***argv);
+int map_parse_fd(int *argc, char ***argv);
 int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len);
 
 void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
@@ -131,4 +150,19 @@ unsigned int get_page_size(void);
 unsigned int get_possible_cpus(void);
 const char *ifindex_to_bfd_name_ns(__u32 ifindex, __u64 ns_dev, __u64 ns_ino);
 
+struct btf_dumper {
+	const struct btf *btf;
+	json_writer_t *jw;
+	bool is_plain_text;
+};
+
+/* btf_dumper_type - print data along with type information
+ * @d: an instance containing context for dumping types
+ * @type_id: index in btf->types array. this points to the type to be dumped
+ * @data: pointer the actual data, i.e. the values to be printed
+ *
+ * Returns zero on success and negative error code otherwise
+ */
+int btf_dumper_type(const struct btf_dumper *d, __u32 type_id,
+		    const void *data);
 #endif
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 5989e1575ae4..9c8191845585 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -34,6 +34,7 @@
 #include <assert.h>
 #include <errno.h>
 #include <fcntl.h>
+#include <linux/err.h>
 #include <stdbool.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -44,6 +45,8 @@
 
 #include <bpf.h>
 
+#include "btf.h"
+#include "json_writer.h"
 #include "main.h"
 
 static const char * const map_type_name[] = {
@@ -93,7 +96,7 @@ static void *alloc_value(struct bpf_map_info *info)
 		return malloc(info->value_size);
 }
 
-static int map_parse_fd(int *argc, char ***argv)
+int map_parse_fd(int *argc, char ***argv)
 {
 	int fd;
 
@@ -148,8 +151,109 @@ int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len)
 	return fd;
 }
 
+static int do_dump_btf(const struct btf_dumper *d,
+		       struct bpf_map_info *map_info, void *key,
+		       void *value)
+{
+	int ret;
+
+	/* start of key-value pair */
+	jsonw_start_object(d->jw);
+
+	jsonw_name(d->jw, "key");
+
+	ret = btf_dumper_type(d, map_info->btf_key_type_id, key);
+	if (ret)
+		goto err_end_obj;
+
+	jsonw_name(d->jw, "value");
+
+	ret = btf_dumper_type(d, map_info->btf_value_type_id, value);
+
+err_end_obj:
+	/* end of key-value pair */
+	jsonw_end_object(d->jw);
+
+	return ret;
+}
+
+static int get_btf(struct bpf_map_info *map_info, struct btf **btf)
+{
+	struct bpf_btf_info btf_info = { 0 };
+	__u32 len = sizeof(btf_info);
+	__u32 last_size;
+	int btf_fd;
+	void *ptr;
+	int err;
+
+	err = 0;
+	*btf = NULL;
+	btf_fd = bpf_btf_get_fd_by_id(map_info->btf_id);
+	if (btf_fd < 0)
+		return 0;
+
+	/* we won't know btf_size until we call bpf_obj_get_info_by_fd(). so
+	 * let's start with a sane default - 4KiB here - and resize it only if
+	 * bpf_obj_get_info_by_fd() needs a bigger buffer.
+	 */
+	btf_info.btf_size = 4096;
+	last_size = btf_info.btf_size;
+	ptr = malloc(last_size);
+	if (!ptr) {
+		err = -ENOMEM;
+		goto exit_free;
+	}
+
+	bzero(ptr, last_size);
+	btf_info.btf = ptr_to_u64(ptr);
+	err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
+
+	if (!err && btf_info.btf_size > last_size) {
+		void *temp_ptr;
+
+		last_size = btf_info.btf_size;
+		temp_ptr = realloc(ptr, last_size);
+		if (!temp_ptr) {
+			err = -ENOMEM;
+			goto exit_free;
+		}
+		ptr = temp_ptr;
+		bzero(ptr, last_size);
+		btf_info.btf = ptr_to_u64(ptr);
+		err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
+	}
+
+	if (err || btf_info.btf_size > last_size) {
+		err = errno;
+		goto exit_free;
+	}
+
+	*btf = btf__new((__u8 *)btf_info.btf, btf_info.btf_size, NULL);
+	if (IS_ERR(*btf)) {
+		err = PTR_ERR(btf);
+		*btf = NULL;
+	}
+
+exit_free:
+	close(btf_fd);
+	free(ptr);
+
+	return err;
+}
+
+static json_writer_t *get_btf_writer(void)
+{
+	json_writer_t *jw = jsonw_new(stdout);
+
+	if (!jw)
+		return NULL;
+	jsonw_pretty(jw, true);
+
+	return jw;
+}
+
 static void print_entry_json(struct bpf_map_info *info, unsigned char *key,
-			     unsigned char *value)
+			     unsigned char *value, struct btf *btf)
 {
 	jsonw_start_object(json_wtr);
 
@@ -158,6 +262,16 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key,
 		print_hex_data_json(key, info->key_size);
 		jsonw_name(json_wtr, "value");
 		print_hex_data_json(value, info->value_size);
+		if (btf) {
+			struct btf_dumper d = {
+				.btf = btf,
+				.jw = json_wtr,
+				.is_plain_text = false,
+			};
+
+			jsonw_name(json_wtr, "formatted");
+			do_dump_btf(&d, info, key, value);
+		}
 	} else {
 		unsigned int i, n;
 
@@ -508,10 +622,12 @@ static int do_show(int argc, char **argv)
 
 static int do_dump(int argc, char **argv)
 {
+	struct bpf_map_info info = {};
 	void *key, *value, *prev_key;
 	unsigned int num_elems = 0;
-	struct bpf_map_info info = {};
 	__u32 len = sizeof(info);
+	json_writer_t *btf_wtr;
+	struct btf *btf = NULL;
 	int err;
 	int fd;
 
@@ -537,8 +653,27 @@ static int do_dump(int argc, char **argv)
 	}
 
 	prev_key = NULL;
+
+	err = get_btf(&info, &btf);
+	if (err) {
+		p_err("failed to get btf");
+		goto exit_free;
+	}
+
 	if (json_output)
 		jsonw_start_array(json_wtr);
+	else
+		if (btf) {
+			btf_wtr = get_btf_writer();
+			if (!btf_wtr) {
+				p_info("failed to create json writer for btf. falling back to plain output");
+				btf__free(btf);
+				btf = NULL;
+			} else {
+				jsonw_start_array(btf_wtr);
+			}
+		}
+
 	while (true) {
 		err = bpf_map_get_next_key(fd, prev_key, key);
 		if (err) {
@@ -549,9 +684,19 @@ static int do_dump(int argc, char **argv)
 
 		if (!bpf_map_lookup_elem(fd, key, value)) {
 			if (json_output)
-				print_entry_json(&info, key, value);
+				print_entry_json(&info, key, value, btf);
 			else
-				print_entry_plain(&info, key, value);
+				if (btf) {
+					struct btf_dumper d = {
+						.btf = btf,
+						.jw = btf_wtr,
+						.is_plain_text = true,
+					};
+
+					do_dump_btf(&d, &info, key, value);
+				} else {
+					print_entry_plain(&info, key, value);
+				}
 		} else {
 			if (json_output) {
 				jsonw_name(json_wtr, "key");
@@ -574,14 +719,19 @@ static int do_dump(int argc, char **argv)
 
 	if (json_output)
 		jsonw_end_array(json_wtr);
-	else
+	else if (btf) {
+		jsonw_end_array(btf_wtr);
+		jsonw_destroy(&btf_wtr);
+	} else {
 		printf("Found %u element%s\n", num_elems,
 		       num_elems != 1 ? "s" : "");
+	}
 
 exit_free:
 	free(key);
 	free(value);
 	close(fd);
+	btf__free(btf);
 
 	return err;
 }
@@ -637,6 +787,8 @@ static int do_lookup(int argc, char **argv)
 {
 	struct bpf_map_info info = {};
 	__u32 len = sizeof(info);
+	json_writer_t *btf_wtr;
+	struct btf *btf = NULL;
 	void *key, *value;
 	int err;
 	int fd;
@@ -661,27 +813,60 @@ static int do_lookup(int argc, char **argv)
 		goto exit_free;
 
 	err = bpf_map_lookup_elem(fd, key, value);
-	if (!err) {
-		if (json_output)
-			print_entry_json(&info, key, value);
-		else
-			print_entry_plain(&info, key, value);
-	} else if (errno == ENOENT) {
-		if (json_output) {
-			jsonw_null(json_wtr);
+	if (err) {
+		if (errno == ENOENT) {
+			if (json_output) {
+				jsonw_null(json_wtr);
+			} else {
+				printf("key:\n");
+				fprint_hex(stdout, key, info.key_size, " ");
+				printf("\n\nNot found\n");
+			}
 		} else {
-			printf("key:\n");
-			fprint_hex(stdout, key, info.key_size, " ");
-			printf("\n\nNot found\n");
+			p_err("lookup failed: %s", strerror(errno));
+		}
+
+		goto exit_free;
+	}
+
+	/* here means bpf_map_lookup_elem() succeeded */
+	err = get_btf(&info, &btf);
+	if (err) {
+		p_err("failed to get btf");
+		goto exit_free;
+	}
+
+	if (json_output) {
+		print_entry_json(&info, key, value, btf);
+	} else if (btf) {
+		/* if here json_wtr wouldn't have been initialised,
+		 * so let's create separate writer for btf
+		 */
+		btf_wtr = get_btf_writer();
+		if (!btf_wtr) {
+			p_info("failed to create json writer for btf. falling back to plain output");
+			btf__free(btf);
+			btf = NULL;
+			print_entry_plain(&info, key, value);
+		} else {
+			struct btf_dumper d = {
+				.btf = btf,
+				.jw = btf_wtr,
+				.is_plain_text = true,
+			};
+
+			do_dump_btf(&d, &info, key, value);
+			jsonw_destroy(&btf_wtr);
 		}
 	} else {
-		p_err("lookup failed: %s", strerror(errno));
+		print_entry_plain(&info, key, value);
 	}
 
 exit_free:
 	free(key);
 	free(value);
 	close(fd);
+	btf__free(btf);
 
 	return err;
 }
@@ -824,7 +1009,7 @@ static int do_help(int argc, char **argv)
 		"       %s %s event_pipe MAP [cpu N index M]\n"
 		"       %s %s help\n"
 		"\n"
-		"       MAP := { id MAP_ID | pinned FILE }\n"
+		"       " HELP_SPEC_MAP "\n"
 		"       DATA := { [hex] BYTES }\n"
 		"       " HELP_SPEC_PROGRAM "\n"
 		"       VALUE := { DATA | MAP | PROG }\n"
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index a740da99d477..dce960d22106 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -31,6 +31,7 @@
  * SOFTWARE.
  */
 
+#define _GNU_SOURCE
 #include <errno.h>
 #include <fcntl.h>
 #include <stdarg.h>
@@ -39,9 +40,12 @@
 #include <string.h>
 #include <time.h>
 #include <unistd.h>
+#include <net/if.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 
+#include <linux/err.h>
+
 #include <bpf.h>
 #include <libbpf.h>
 
@@ -679,31 +683,247 @@ static int do_pin(int argc, char **argv)
 	return err;
 }
 
+struct map_replace {
+	int idx;
+	int fd;
+	char *name;
+};
+
+int map_replace_compar(const void *p1, const void *p2)
+{
+	const struct map_replace *a = p1, *b = p2;
+
+	return a->idx - b->idx;
+}
+
 static int do_load(int argc, char **argv)
 {
+	enum bpf_attach_type expected_attach_type;
+	struct bpf_object_open_attr attr = {
+		.prog_type	= BPF_PROG_TYPE_UNSPEC,
+	};
+	struct map_replace *map_replace = NULL;
+	unsigned int old_map_fds = 0;
+	struct bpf_program *prog;
 	struct bpf_object *obj;
-	int prog_fd;
+	struct bpf_map *map;
+	const char *pinfile;
+	unsigned int i, j;
+	__u32 ifindex = 0;
+	int idx, err;
 
-	if (argc != 2)
-		usage();
-
-	if (bpf_prog_load(argv[0], BPF_PROG_TYPE_UNSPEC, &obj, &prog_fd)) {
-		p_err("failed to load program");
+	if (!REQ_ARGS(2))
 		return -1;
+	attr.file = GET_ARG();
+	pinfile = GET_ARG();
+
+	while (argc) {
+		if (is_prefix(*argv, "type")) {
+			char *type;
+
+			NEXT_ARG();
+
+			if (attr.prog_type != BPF_PROG_TYPE_UNSPEC) {
+				p_err("program type already specified");
+				goto err_free_reuse_maps;
+			}
+			if (!REQ_ARGS(1))
+				goto err_free_reuse_maps;
+
+			/* Put a '/' at the end of type to appease libbpf */
+			type = malloc(strlen(*argv) + 2);
+			if (!type) {
+				p_err("mem alloc failed");
+				goto err_free_reuse_maps;
+			}
+			*type = 0;
+			strcat(type, *argv);
+			strcat(type, "/");
+
+			err = libbpf_prog_type_by_name(type, &attr.prog_type,
+						       &expected_attach_type);
+			free(type);
+			if (err < 0) {
+				p_err("unknown program type '%s'", *argv);
+				goto err_free_reuse_maps;
+			}
+			NEXT_ARG();
+		} else if (is_prefix(*argv, "map")) {
+			char *endptr, *name;
+			int fd;
+
+			NEXT_ARG();
+
+			if (!REQ_ARGS(4))
+				goto err_free_reuse_maps;
+
+			if (is_prefix(*argv, "idx")) {
+				NEXT_ARG();
+
+				idx = strtoul(*argv, &endptr, 0);
+				if (*endptr) {
+					p_err("can't parse %s as IDX", *argv);
+					goto err_free_reuse_maps;
+				}
+				name = NULL;
+			} else if (is_prefix(*argv, "name")) {
+				NEXT_ARG();
+
+				name = *argv;
+				idx = -1;
+			} else {
+				p_err("expected 'idx' or 'name', got: '%s'?",
+				      *argv);
+				goto err_free_reuse_maps;
+			}
+			NEXT_ARG();
+
+			fd = map_parse_fd(&argc, &argv);
+			if (fd < 0)
+				goto err_free_reuse_maps;
+
+			map_replace = reallocarray(map_replace, old_map_fds + 1,
+						   sizeof(*map_replace));
+			if (!map_replace) {
+				p_err("mem alloc failed");
+				goto err_free_reuse_maps;
+			}
+			map_replace[old_map_fds].idx = idx;
+			map_replace[old_map_fds].name = name;
+			map_replace[old_map_fds].fd = fd;
+			old_map_fds++;
+		} else if (is_prefix(*argv, "dev")) {
+			NEXT_ARG();
+
+			if (ifindex) {
+				p_err("offload device already specified");
+				goto err_free_reuse_maps;
+			}
+			if (!REQ_ARGS(1))
+				goto err_free_reuse_maps;
+
+			ifindex = if_nametoindex(*argv);
+			if (!ifindex) {
+				p_err("unrecognized netdevice '%s': %s",
+				      *argv, strerror(errno));
+				goto err_free_reuse_maps;
+			}
+			NEXT_ARG();
+		} else {
+			p_err("expected no more arguments, 'type', 'map' or 'dev', got: '%s'?",
+			      *argv);
+			goto err_free_reuse_maps;
+		}
 	}
 
-	if (do_pin_fd(prog_fd, argv[1]))
+	obj = bpf_object__open_xattr(&attr);
+	if (IS_ERR_OR_NULL(obj)) {
+		p_err("failed to open object file");
+		goto err_free_reuse_maps;
+	}
+
+	prog = bpf_program__next(NULL, obj);
+	if (!prog) {
+		p_err("object file doesn't contain any bpf program");
+		goto err_close_obj;
+	}
+
+	bpf_program__set_ifindex(prog, ifindex);
+	if (attr.prog_type == BPF_PROG_TYPE_UNSPEC) {
+		const char *sec_name = bpf_program__title(prog, false);
+
+		err = libbpf_prog_type_by_name(sec_name, &attr.prog_type,
+					       &expected_attach_type);
+		if (err < 0) {
+			p_err("failed to guess program type based on section name %s\n",
+			      sec_name);
+			goto err_close_obj;
+		}
+	}
+	bpf_program__set_type(prog, attr.prog_type);
+	bpf_program__set_expected_attach_type(prog, expected_attach_type);
+
+	qsort(map_replace, old_map_fds, sizeof(*map_replace),
+	      map_replace_compar);
+
+	/* After the sort maps by name will be first on the list, because they
+	 * have idx == -1.  Resolve them.
+	 */
+	j = 0;
+	while (j < old_map_fds && map_replace[j].name) {
+		i = 0;
+		bpf_map__for_each(map, obj) {
+			if (!strcmp(bpf_map__name(map), map_replace[j].name)) {
+				map_replace[j].idx = i;
+				break;
+			}
+			i++;
+		}
+		if (map_replace[j].idx == -1) {
+			p_err("unable to find map '%s'", map_replace[j].name);
+			goto err_close_obj;
+		}
+		j++;
+	}
+	/* Resort if any names were resolved */
+	if (j)
+		qsort(map_replace, old_map_fds, sizeof(*map_replace),
+		      map_replace_compar);
+
+	/* Set ifindex and name reuse */
+	j = 0;
+	idx = 0;
+	bpf_map__for_each(map, obj) {
+		if (!bpf_map__is_offload_neutral(map))
+			bpf_map__set_ifindex(map, ifindex);
+
+		if (j < old_map_fds && idx == map_replace[j].idx) {
+			err = bpf_map__reuse_fd(map, map_replace[j++].fd);
+			if (err) {
+				p_err("unable to set up map reuse: %d", err);
+				goto err_close_obj;
+			}
+
+			/* Next reuse wants to apply to the same map */
+			if (j < old_map_fds && map_replace[j].idx == idx) {
+				p_err("replacement for map idx %d specified more than once",
+				      idx);
+				goto err_close_obj;
+			}
+		}
+
+		idx++;
+	}
+	if (j < old_map_fds) {
+		p_err("map idx '%d' not used", map_replace[j].idx);
+		goto err_close_obj;
+	}
+
+	err = bpf_object__load(obj);
+	if (err) {
+		p_err("failed to load object file");
+		goto err_close_obj;
+	}
+
+	if (do_pin_fd(bpf_program__fd(prog), pinfile))
 		goto err_close_obj;
 
 	if (json_output)
 		jsonw_null(json_wtr);
 
 	bpf_object__close(obj);
+	for (i = 0; i < old_map_fds; i++)
+		close(map_replace[i].fd);
+	free(map_replace);
 
 	return 0;
 
 err_close_obj:
 	bpf_object__close(obj);
+err_free_reuse_maps:
+	for (i = 0; i < old_map_fds; i++)
+		close(map_replace[i].fd);
+	free(map_replace);
 	return -1;
 }
 
@@ -719,10 +939,19 @@ static int do_help(int argc, char **argv)
 		"       %s %s dump xlated PROG [{ file FILE | opcodes | visual }]\n"
 		"       %s %s dump jited  PROG [{ file FILE | opcodes }]\n"
 		"       %s %s pin   PROG FILE\n"
-		"       %s %s load  OBJ  FILE\n"
+		"       %s %s load  OBJ  FILE [type TYPE] [dev NAME] \\\n"
+		"                         [map { idx IDX | name NAME } MAP]\n"
 		"       %s %s help\n"
 		"\n"
+		"       " HELP_SPEC_MAP "\n"
 		"       " HELP_SPEC_PROGRAM "\n"
+		"       TYPE := { socket | kprobe | kretprobe | classifier | action |\n"
+		"                 tracepoint | raw_tracepoint | xdp | perf_event | cgroup/skb |\n"
+		"                 cgroup/sock | cgroup/dev | lwt_in | lwt_out | lwt_xmit |\n"
+		"                 lwt_seg6local | sockops | sk_skb | sk_msg | lirc_mode2 |\n"
+		"                 cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n"
+		"                 cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n"
+		"                 cgroup/sendmsg4 | cgroup/sendmsg6 }\n"
 		"       " HELP_SPEC_OPTIONS "\n"
 		"",
 		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c
index b97f1da60dd1..3284759df98a 100644
--- a/tools/bpf/bpftool/xlated_dumper.c
+++ b/tools/bpf/bpftool/xlated_dumper.c
@@ -35,6 +35,7 @@
  * POSSIBILITY OF SUCH DAMAGE.
  */
 
+#define _GNU_SOURCE
 #include <stdarg.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -66,9 +67,8 @@ void kernel_syms_load(struct dump_data *dd)
 	while (!feof(fp)) {
 		if (!fgets(buff, sizeof(buff), fp))
 			break;
-		tmp = realloc(dd->sym_mapping,
-			      (dd->sym_count + 1) *
-			      sizeof(*dd->sym_mapping));
+		tmp = reallocarray(dd->sym_mapping, dd->sym_count + 1,
+				   sizeof(*dd->sym_mapping));
 		if (!tmp) {
 out:
 			free(dd->sym_mapping);
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 5b6dda3b1ca8..f216b2f5c3d7 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -57,6 +57,7 @@ FEATURE_TESTS_BASIC :=                  \
         libunwind-aarch64               \
         pthread-attr-setaffinity-np     \
         pthread-barrier     		\
+        reallocarray                    \
         stackprotector-all              \
         timerfd                         \
         libdw-dwarf-unwind              \
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index dac9563b5470..0516259be70f 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -14,6 +14,7 @@ FILES=                                          \
          test-libaudit.bin                      \
          test-libbfd.bin                        \
          test-disassembler-four-args.bin        \
+         test-reallocarray.bin			\
          test-liberty.bin                       \
          test-liberty-z.bin                     \
          test-cplus-demangle.bin                \
@@ -204,6 +205,9 @@ $(OUTPUT)test-libbfd.bin:
 $(OUTPUT)test-disassembler-four-args.bin:
 	$(BUILD) -DPACKAGE='"perf"' -lbfd -lopcodes
 
+$(OUTPUT)test-reallocarray.bin:
+	$(BUILD)
+
 $(OUTPUT)test-liberty.bin:
 	$(CC) $(CFLAGS) -Wall -Werror -o $@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty
 
diff --git a/tools/build/feature/test-reallocarray.c b/tools/build/feature/test-reallocarray.c
new file mode 100644
index 000000000000..8170de35150d
--- /dev/null
+++ b/tools/build/feature/test-reallocarray.c
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <stdlib.h>
+
+int main(void)
+{
+	return !!reallocarray(NULL, 1, 1);
+}
diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h
index 70fe61295733..0d35f18006a1 100644
--- a/tools/include/linux/compiler-gcc.h
+++ b/tools/include/linux/compiler-gcc.h
@@ -36,3 +36,7 @@
 #endif
 #define __printf(a, b)	__attribute__((format(printf, a, b)))
 #define __scanf(a, b)	__attribute__((format(scanf, a, b)))
+
+#if GCC_VERSION >= 50100
+#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
+#endif
diff --git a/tools/include/linux/overflow.h b/tools/include/linux/overflow.h
new file mode 100644
index 000000000000..8712ff70995f
--- /dev/null
+++ b/tools/include/linux/overflow.h
@@ -0,0 +1,278 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+#ifndef __LINUX_OVERFLOW_H
+#define __LINUX_OVERFLOW_H
+
+#include <linux/compiler.h>
+
+/*
+ * In the fallback code below, we need to compute the minimum and
+ * maximum values representable in a given type. These macros may also
+ * be useful elsewhere, so we provide them outside the
+ * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block.
+ *
+ * It would seem more obvious to do something like
+ *
+ * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0)
+ * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0)
+ *
+ * Unfortunately, the middle expressions, strictly speaking, have
+ * undefined behaviour, and at least some versions of gcc warn about
+ * the type_max expression (but not if -fsanitize=undefined is in
+ * effect; in that case, the warning is deferred to runtime...).
+ *
+ * The slightly excessive casting in type_min is to make sure the
+ * macros also produce sensible values for the exotic type _Bool. [The
+ * overflow checkers only almost work for _Bool, but that's
+ * a-feature-not-a-bug, since people shouldn't be doing arithmetic on
+ * _Bools. Besides, the gcc builtins don't allow _Bool* as third
+ * argument.]
+ *
+ * Idea stolen from
+ * https://mail-index.netbsd.org/tech-misc/2007/02/05/0000.html -
+ * credit to Christian Biere.
+ */
+#define is_signed_type(type)       (((type)(-1)) < (type)1)
+#define __type_half_max(type) ((type)1 << (8*sizeof(type) - 1 - is_signed_type(type)))
+#define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T)))
+#define type_min(T) ((T)((T)-type_max(T)-(T)1))
+
+
+#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW
+/*
+ * For simplicity and code hygiene, the fallback code below insists on
+ * a, b and *d having the same type (similar to the min() and max()
+ * macros), whereas gcc's type-generic overflow checkers accept
+ * different types. Hence we don't just make check_add_overflow an
+ * alias for __builtin_add_overflow, but add type checks similar to
+ * below.
+ */
+#define check_add_overflow(a, b, d) ({		\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	typeof(d) __d = (d);			\
+	(void) (&__a == &__b);			\
+	(void) (&__a == __d);			\
+	__builtin_add_overflow(__a, __b, __d);	\
+})
+
+#define check_sub_overflow(a, b, d) ({		\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	typeof(d) __d = (d);			\
+	(void) (&__a == &__b);			\
+	(void) (&__a == __d);			\
+	__builtin_sub_overflow(__a, __b, __d);	\
+})
+
+#define check_mul_overflow(a, b, d) ({		\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	typeof(d) __d = (d);			\
+	(void) (&__a == &__b);			\
+	(void) (&__a == __d);			\
+	__builtin_mul_overflow(__a, __b, __d);	\
+})
+
+#else
+
+
+/* Checking for unsigned overflow is relatively easy without causing UB. */
+#define __unsigned_add_overflow(a, b, d) ({	\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	typeof(d) __d = (d);			\
+	(void) (&__a == &__b);			\
+	(void) (&__a == __d);			\
+	*__d = __a + __b;			\
+	*__d < __a;				\
+})
+#define __unsigned_sub_overflow(a, b, d) ({	\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	typeof(d) __d = (d);			\
+	(void) (&__a == &__b);			\
+	(void) (&__a == __d);			\
+	*__d = __a - __b;			\
+	__a < __b;				\
+})
+/*
+ * If one of a or b is a compile-time constant, this avoids a division.
+ */
+#define __unsigned_mul_overflow(a, b, d) ({		\
+	typeof(a) __a = (a);				\
+	typeof(b) __b = (b);				\
+	typeof(d) __d = (d);				\
+	(void) (&__a == &__b);				\
+	(void) (&__a == __d);				\
+	*__d = __a * __b;				\
+	__builtin_constant_p(__b) ?			\
+	  __b > 0 && __a > type_max(typeof(__a)) / __b : \
+	  __a > 0 && __b > type_max(typeof(__b)) / __a;	 \
+})
+
+/*
+ * For signed types, detecting overflow is much harder, especially if
+ * we want to avoid UB. But the interface of these macros is such that
+ * we must provide a result in *d, and in fact we must produce the
+ * result promised by gcc's builtins, which is simply the possibly
+ * wrapped-around value. Fortunately, we can just formally do the
+ * operations in the widest relevant unsigned type (u64) and then
+ * truncate the result - gcc is smart enough to generate the same code
+ * with and without the (u64) casts.
+ */
+
+/*
+ * Adding two signed integers can overflow only if they have the same
+ * sign, and overflow has happened iff the result has the opposite
+ * sign.
+ */
+#define __signed_add_overflow(a, b, d) ({	\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	typeof(d) __d = (d);			\
+	(void) (&__a == &__b);			\
+	(void) (&__a == __d);			\
+	*__d = (u64)__a + (u64)__b;		\
+	(((~(__a ^ __b)) & (*__d ^ __a))	\
+		& type_min(typeof(__a))) != 0;	\
+})
+
+/*
+ * Subtraction is similar, except that overflow can now happen only
+ * when the signs are opposite. In this case, overflow has happened if
+ * the result has the opposite sign of a.
+ */
+#define __signed_sub_overflow(a, b, d) ({	\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	typeof(d) __d = (d);			\
+	(void) (&__a == &__b);			\
+	(void) (&__a == __d);			\
+	*__d = (u64)__a - (u64)__b;		\
+	((((__a ^ __b)) & (*__d ^ __a))		\
+		& type_min(typeof(__a))) != 0;	\
+})
+
+/*
+ * Signed multiplication is rather hard. gcc always follows C99, so
+ * division is truncated towards 0. This means that we can write the
+ * overflow check like this:
+ *
+ * (a > 0 && (b > MAX/a || b < MIN/a)) ||
+ * (a < -1 && (b > MIN/a || b < MAX/a) ||
+ * (a == -1 && b == MIN)
+ *
+ * The redundant casts of -1 are to silence an annoying -Wtype-limits
+ * (included in -Wextra) warning: When the type is u8 or u16, the
+ * __b_c_e in check_mul_overflow obviously selects
+ * __unsigned_mul_overflow, but unfortunately gcc still parses this
+ * code and warns about the limited range of __b.
+ */
+
+#define __signed_mul_overflow(a, b, d) ({				\
+	typeof(a) __a = (a);						\
+	typeof(b) __b = (b);						\
+	typeof(d) __d = (d);						\
+	typeof(a) __tmax = type_max(typeof(a));				\
+	typeof(a) __tmin = type_min(typeof(a));				\
+	(void) (&__a == &__b);						\
+	(void) (&__a == __d);						\
+	*__d = (u64)__a * (u64)__b;					\
+	(__b > 0   && (__a > __tmax/__b || __a < __tmin/__b)) ||	\
+	(__b < (typeof(__b))-1  && (__a > __tmin/__b || __a < __tmax/__b)) || \
+	(__b == (typeof(__b))-1 && __a == __tmin);			\
+})
+
+
+#define check_add_overflow(a, b, d)					\
+	__builtin_choose_expr(is_signed_type(typeof(a)),		\
+			__signed_add_overflow(a, b, d),			\
+			__unsigned_add_overflow(a, b, d))
+
+#define check_sub_overflow(a, b, d)					\
+	__builtin_choose_expr(is_signed_type(typeof(a)),		\
+			__signed_sub_overflow(a, b, d),			\
+			__unsigned_sub_overflow(a, b, d))
+
+#define check_mul_overflow(a, b, d)					\
+	__builtin_choose_expr(is_signed_type(typeof(a)),		\
+			__signed_mul_overflow(a, b, d),			\
+			__unsigned_mul_overflow(a, b, d))
+
+
+#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */
+
+/**
+ * array_size() - Calculate size of 2-dimensional array.
+ *
+ * @a: dimension one
+ * @b: dimension two
+ *
+ * Calculates size of 2-dimensional array: @a * @b.
+ *
+ * Returns: number of bytes needed to represent the array or SIZE_MAX on
+ * overflow.
+ */
+static inline __must_check size_t array_size(size_t a, size_t b)
+{
+	size_t bytes;
+
+	if (check_mul_overflow(a, b, &bytes))
+		return SIZE_MAX;
+
+	return bytes;
+}
+
+/**
+ * array3_size() - Calculate size of 3-dimensional array.
+ *
+ * @a: dimension one
+ * @b: dimension two
+ * @c: dimension three
+ *
+ * Calculates size of 3-dimensional array: @a * @b * @c.
+ *
+ * Returns: number of bytes needed to represent the array or SIZE_MAX on
+ * overflow.
+ */
+static inline __must_check size_t array3_size(size_t a, size_t b, size_t c)
+{
+	size_t bytes;
+
+	if (check_mul_overflow(a, b, &bytes))
+		return SIZE_MAX;
+	if (check_mul_overflow(bytes, c, &bytes))
+		return SIZE_MAX;
+
+	return bytes;
+}
+
+static inline __must_check size_t __ab_c_size(size_t n, size_t size, size_t c)
+{
+	size_t bytes;
+
+	if (check_mul_overflow(n, size, &bytes))
+		return SIZE_MAX;
+	if (check_add_overflow(bytes, c, &bytes))
+		return SIZE_MAX;
+
+	return bytes;
+}
+
+/**
+ * struct_size() - Calculate size of structure with trailing array.
+ * @p: Pointer to the structure.
+ * @member: Name of the array member.
+ * @n: Number of elements in the array.
+ *
+ * Calculates size of memory needed for structure @p followed by an
+ * array of @n @member elements.
+ *
+ * Return: number of bytes needed or SIZE_MAX on overflow.
+ */
+#define struct_size(p, member, n)					\
+	__ab_c_size(n,							\
+		    sizeof(*(p)->member) + __must_be_array((p)->member),\
+		    sizeof(*(p)))
+
+#endif /* __LINUX_OVERFLOW_H */
diff --git a/tools/include/tools/libc_compat.h b/tools/include/tools/libc_compat.h
new file mode 100644
index 000000000000..664ced8cb1b0
--- /dev/null
+++ b/tools/include/tools/libc_compat.h
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2018 Netronome Systems, Inc. */
+
+#ifndef __TOOLS_LIBC_COMPAT_H
+#define __TOOLS_LIBC_COMPAT_H
+
+#include <stdlib.h>
+#include <linux/overflow.h>
+
+#ifdef COMPAT_NEED_REALLOCARRAY
+static inline void *reallocarray(void *ptr, size_t nmemb, size_t size)
+{
+	size_t bytes;
+
+	if (unlikely(check_mul_overflow(nmemb, size, &bytes)))
+		return NULL;
+	return realloc(ptr, bytes);
+}
+#endif
+#endif
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 59b19b6a40d7..870113916cac 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1826,7 +1826,7 @@ union bpf_attr {
  * 		A non-negative value equal to or less than *size* on success,
  * 		or a negative error in case of failure.
  *
- * int skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
+ * int bpf_skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
  * 	Description
  * 		This helper is similar to **bpf_skb_load_bytes**\ () in that
  * 		it provides an easy way to load *len* bytes from *offset*
@@ -1857,7 +1857,8 @@ union bpf_attr {
  *		is resolved), the nexthop address is returned in ipv4_dst
  *		or ipv6_dst based on family, smac is set to mac address of
  *		egress device, dmac is set to nexthop mac address, rt_metric
- *		is set to metric from route (IPv4/IPv6 only).
+ *		is set to metric from route (IPv4/IPv6 only), and ifindex
+ *		is set to the device index of the nexthop from the FIB lookup.
  *
  *             *plen* argument is the size of the passed in struct.
  *             *flags* argument can be a combination of one or more of the
@@ -1873,9 +1874,10 @@ union bpf_attr {
  *             *ctx* is either **struct xdp_md** for XDP programs or
  *             **struct sk_buff** tc cls_act programs.
  *     Return
- *             Egress device index on success, 0 if packet needs to continue
- *             up the stack for further processing or a negative error in case
- *             of failure.
+ *		* < 0 if any input argument is invalid
+ *		*   0 on success (packet is forwarded, nexthop neighbor exists)
+ *		* > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
+ *		  packet is not forwarded or needs assist from full stack
  *
  * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
  *	Description
@@ -2031,7 +2033,6 @@ union bpf_attr {
  *		This helper is only available is the kernel was compiled with
  *		the **CONFIG_BPF_LIRC_MODE2** configuration option set to
  *		"**y**".
- *
  *	Return
  *		0
  *
@@ -2051,7 +2052,6 @@ union bpf_attr {
  *		This helper is only available is the kernel was compiled with
  *		the **CONFIG_BPF_LIRC_MODE2** configuration option set to
  *		"**y**".
- *
  *	Return
  *		0
  *
@@ -2555,6 +2555,9 @@ enum {
 					 * Arg1: old_state
 					 * Arg2: new_state
 					 */
+	BPF_SOCK_OPS_TCP_LISTEN_CB,	/* Called on listen(2), right after
+					 * socket transition to LISTEN state.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
@@ -2612,6 +2615,18 @@ struct bpf_raw_tracepoint_args {
 #define BPF_FIB_LOOKUP_DIRECT  BIT(0)
 #define BPF_FIB_LOOKUP_OUTPUT  BIT(1)
 
+enum {
+	BPF_FIB_LKUP_RET_SUCCESS,      /* lookup successful */
+	BPF_FIB_LKUP_RET_BLACKHOLE,    /* dest is blackholed; can be dropped */
+	BPF_FIB_LKUP_RET_UNREACHABLE,  /* dest is unreachable; can be dropped */
+	BPF_FIB_LKUP_RET_PROHIBIT,     /* dest not allowed; can be dropped */
+	BPF_FIB_LKUP_RET_NOT_FWDED,    /* packet is not forwarded */
+	BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */
+	BPF_FIB_LKUP_RET_UNSUPP_LWT,   /* fwd requires encapsulation */
+	BPF_FIB_LKUP_RET_NO_NEIGH,     /* no neighbor entry for nh */
+	BPF_FIB_LKUP_RET_FRAG_NEEDED,  /* fragmentation required to fwd */
+};
+
 struct bpf_fib_lookup {
 	/* input:  network family for lookup (AF_INET, AF_INET6)
 	 * output: network family of egress nexthop
@@ -2625,7 +2640,11 @@ struct bpf_fib_lookup {
 
 	/* total length of packet from network header - used for MTU check */
 	__u16	tot_len;
-	__u32	ifindex;  /* L3 device index for lookup */
+
+	/* input: L3 device index for lookup
+	 * output: device index from FIB lookup
+	 */
+	__u32	ifindex;
 
 	union {
 		/* inputs to lookup */
diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index 6070e655042d..13a861135127 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1 +1 @@
-libbpf-y := libbpf.o bpf.o nlattr.o btf.o
+libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 5390e7725e43..7a8e4c98ef1a 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -66,7 +66,7 @@ ifndef VERBOSE
 endif
 
 FEATURE_USER = .libbpf
-FEATURE_TESTS = libelf libelf-getphdrnum libelf-mmap bpf
+FEATURE_TESTS = libelf libelf-getphdrnum libelf-mmap bpf reallocarray
 FEATURE_DISPLAY = libelf bpf
 
 INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi -I$(srctree)/tools/perf
@@ -120,6 +120,10 @@ ifeq ($(feature-libelf-getphdrnum), 1)
   override CFLAGS += -DHAVE_ELF_GETPHDRNUM_SUPPORT
 endif
 
+ifeq ($(feature-reallocarray), 0)
+  override CFLAGS += -DCOMPAT_NEED_REALLOCARRAY
+endif
+
 # Append required CFLAGS
 override CFLAGS += $(EXTRA_WARNINGS)
 override CFLAGS += -Werror -Wall
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 8c54a4b6f187..03161be094b4 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -17,6 +17,11 @@
 
 #define BTF_MAX_NR_TYPES 65535
 
+#define IS_MODIFIER(k) (((k) == BTF_KIND_TYPEDEF) || \
+		((k) == BTF_KIND_VOLATILE) || \
+		((k) == BTF_KIND_CONST) || \
+		((k) == BTF_KIND_RESTRICT))
+
 static struct btf_type btf_void;
 
 struct btf {
@@ -33,14 +38,6 @@ struct btf {
 	int fd;
 };
 
-static const char *btf_name_by_offset(const struct btf *btf, uint32_t offset)
-{
-	if (offset < btf->hdr->str_len)
-		return &btf->strings[offset];
-	else
-		return NULL;
-}
-
 static int btf_add_type(struct btf *btf, struct btf_type *t)
 {
 	if (btf->types_size - btf->nr_types < 2) {
@@ -190,15 +187,6 @@ static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log)
 	return 0;
 }
 
-static const struct btf_type *btf_type_by_id(const struct btf *btf,
-					     uint32_t type_id)
-{
-	if (type_id > btf->nr_types)
-		return NULL;
-
-	return btf->types[type_id];
-}
-
 static bool btf_type_is_void(const struct btf_type *t)
 {
 	return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD;
@@ -234,7 +222,7 @@ int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id)
 	int64_t size = -1;
 	int i;
 
-	t = btf_type_by_id(btf, type_id);
+	t = btf__type_by_id(btf, type_id);
 	for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t);
 	     i++) {
 		size = btf_type_size(t);
@@ -259,7 +247,7 @@ int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id)
 			return -EINVAL;
 		}
 
-		t = btf_type_by_id(btf, type_id);
+		t = btf__type_by_id(btf, type_id);
 	}
 
 	if (size < 0)
@@ -271,6 +259,26 @@ int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id)
 	return nelems * size;
 }
 
+int btf__resolve_type(const struct btf *btf, __u32 type_id)
+{
+	const struct btf_type *t;
+	int depth = 0;
+
+	t = btf__type_by_id(btf, type_id);
+	while (depth < MAX_RESOLVE_DEPTH &&
+	       !btf_type_is_void_or_null(t) &&
+	       IS_MODIFIER(BTF_INFO_KIND(t->info))) {
+		type_id = t->type;
+		t = btf__type_by_id(btf, type_id);
+		depth++;
+	}
+
+	if (depth == MAX_RESOLVE_DEPTH || btf_type_is_void_or_null(t))
+		return -EINVAL;
+
+	return type_id;
+}
+
 int32_t btf__find_by_name(const struct btf *btf, const char *type_name)
 {
 	uint32_t i;
@@ -280,7 +288,7 @@ int32_t btf__find_by_name(const struct btf *btf, const char *type_name)
 
 	for (i = 1; i <= btf->nr_types; i++) {
 		const struct btf_type *t = btf->types[i];
-		const char *name = btf_name_by_offset(btf, t->name_off);
+		const char *name = btf__name_by_offset(btf, t->name_off);
 
 		if (name && !strcmp(type_name, name))
 			return i;
@@ -371,3 +379,20 @@ int btf__fd(const struct btf *btf)
 {
 	return btf->fd;
 }
+
+const char *btf__name_by_offset(const struct btf *btf, __u32 offset)
+{
+	if (offset < btf->hdr->str_len)
+		return &btf->strings[offset];
+	else
+		return NULL;
+}
+
+const struct btf_type *btf__type_by_id(const struct btf *btf,
+				       __u32 type_id)
+{
+	if (type_id > btf->nr_types)
+		return NULL;
+
+	return btf->types[type_id];
+}
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 74bb344035bb..24f361d99a5e 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -17,6 +17,9 @@ void btf__free(struct btf *btf);
 struct btf *btf__new(uint8_t *data, uint32_t size, btf_print_fn_t err_log);
 int32_t btf__find_by_name(const struct btf *btf, const char *type_name);
 int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id);
+int btf__resolve_type(const struct btf *btf, __u32 type_id);
 int btf__fd(const struct btf *btf);
+const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
+const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id);
 
 #endif
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 38ed3e92e393..955f8eafbf41 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -22,6 +22,7 @@
  * License along with this program; if not,  see <http://www.gnu.org/licenses>
  */
 
+#define _GNU_SOURCE
 #include <stdlib.h>
 #include <stdio.h>
 #include <stdarg.h>
@@ -41,6 +42,7 @@
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <sys/vfs.h>
+#include <tools/libc_compat.h>
 #include <libelf.h>
 #include <gelf.h>
 
@@ -95,54 +97,6 @@ void libbpf_set_print(libbpf_print_fn_t warn,
 
 #define STRERR_BUFSIZE  128
 
-#define ERRNO_OFFSET(e)		((e) - __LIBBPF_ERRNO__START)
-#define ERRCODE_OFFSET(c)	ERRNO_OFFSET(LIBBPF_ERRNO__##c)
-#define NR_ERRNO	(__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START)
-
-static const char *libbpf_strerror_table[NR_ERRNO] = {
-	[ERRCODE_OFFSET(LIBELF)]	= "Something wrong in libelf",
-	[ERRCODE_OFFSET(FORMAT)]	= "BPF object format invalid",
-	[ERRCODE_OFFSET(KVERSION)]	= "'version' section incorrect or lost",
-	[ERRCODE_OFFSET(ENDIAN)]	= "Endian mismatch",
-	[ERRCODE_OFFSET(INTERNAL)]	= "Internal error in libbpf",
-	[ERRCODE_OFFSET(RELOC)]		= "Relocation failed",
-	[ERRCODE_OFFSET(VERIFY)]	= "Kernel verifier blocks program loading",
-	[ERRCODE_OFFSET(PROG2BIG)]	= "Program too big",
-	[ERRCODE_OFFSET(KVER)]		= "Incorrect kernel version",
-	[ERRCODE_OFFSET(PROGTYPE)]	= "Kernel doesn't support this program type",
-	[ERRCODE_OFFSET(WRNGPID)]	= "Wrong pid in netlink message",
-	[ERRCODE_OFFSET(INVSEQ)]	= "Invalid netlink sequence",
-};
-
-int libbpf_strerror(int err, char *buf, size_t size)
-{
-	if (!buf || !size)
-		return -1;
-
-	err = err > 0 ? err : -err;
-
-	if (err < __LIBBPF_ERRNO__START) {
-		int ret;
-
-		ret = strerror_r(err, buf, size);
-		buf[size - 1] = '\0';
-		return ret;
-	}
-
-	if (err < __LIBBPF_ERRNO__END) {
-		const char *msg;
-
-		msg = libbpf_strerror_table[ERRNO_OFFSET(err)];
-		snprintf(buf, size, "%s", msg);
-		buf[size - 1] = '\0';
-		return 0;
-	}
-
-	snprintf(buf, size, "Unknown libbpf error %d", err);
-	buf[size - 1] = '\0';
-	return -1;
-}
-
 #define CHECK_ERR(action, err, out) do {	\
 	err = action;			\
 	if (err)			\
@@ -369,7 +323,7 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
 	progs = obj->programs;
 	nr_progs = obj->nr_programs;
 
-	progs = realloc(progs, sizeof(progs[0]) * (nr_progs + 1));
+	progs = reallocarray(progs, nr_progs + 1, sizeof(progs[0]));
 	if (!progs) {
 		/*
 		 * In this case the original obj->programs
@@ -870,8 +824,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 				continue;
 			}
 
-			reloc = realloc(reloc,
-					sizeof(*obj->efile.reloc) * nr_reloc);
+			reloc = reallocarray(reloc, nr_reloc,
+					     sizeof(*obj->efile.reloc));
 			if (!reloc) {
 				pr_warning("realloc failed\n");
 				err = -ENOMEM;
@@ -1081,6 +1035,53 @@ static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf)
 	return 0;
 }
 
+int bpf_map__reuse_fd(struct bpf_map *map, int fd)
+{
+	struct bpf_map_info info = {};
+	__u32 len = sizeof(info);
+	int new_fd, err;
+	char *new_name;
+
+	err = bpf_obj_get_info_by_fd(fd, &info, &len);
+	if (err)
+		return err;
+
+	new_name = strdup(info.name);
+	if (!new_name)
+		return -errno;
+
+	new_fd = open("/", O_RDONLY | O_CLOEXEC);
+	if (new_fd < 0)
+		goto err_free_new_name;
+
+	new_fd = dup3(fd, new_fd, O_CLOEXEC);
+	if (new_fd < 0)
+		goto err_close_new_fd;
+
+	err = zclose(map->fd);
+	if (err)
+		goto err_close_new_fd;
+	free(map->name);
+
+	map->fd = new_fd;
+	map->name = new_name;
+	map->def.type = info.type;
+	map->def.key_size = info.key_size;
+	map->def.value_size = info.value_size;
+	map->def.max_entries = info.max_entries;
+	map->def.map_flags = info.map_flags;
+	map->btf_key_type_id = info.btf_key_type_id;
+	map->btf_value_type_id = info.btf_value_type_id;
+
+	return 0;
+
+err_close_new_fd:
+	close(new_fd);
+err_free_new_name:
+	free(new_name);
+	return -errno;
+}
+
 static int
 bpf_object__create_maps(struct bpf_object *obj)
 {
@@ -1093,6 +1094,12 @@ bpf_object__create_maps(struct bpf_object *obj)
 		struct bpf_map_def *def = &map->def;
 		int *pfd = &map->fd;
 
+		if (map->fd >= 0) {
+			pr_debug("skip map create (preset) %s: fd=%d\n",
+				 map->name, map->fd);
+			continue;
+		}
+
 		create_attr.name = map->name;
 		create_attr.map_ifindex = map->map_ifindex;
 		create_attr.map_type = def->type;
@@ -1163,7 +1170,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
 			return -LIBBPF_ERRNO__RELOC;
 		}
 		new_cnt = prog->insns_cnt + text->insns_cnt;
-		new_insn = realloc(prog->insns, new_cnt * sizeof(*insn));
+		new_insn = reallocarray(prog->insns, new_cnt, sizeof(*insn));
 		if (!new_insn) {
 			pr_warning("oom in prog realloc\n");
 			return -ENOMEM;
@@ -1520,15 +1527,26 @@ __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz,
 	return ERR_PTR(err);
 }
 
-struct bpf_object *bpf_object__open(const char *path)
+struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr)
 {
 	/* param validation */
-	if (!path)
+	if (!attr->file)
 		return NULL;
 
-	pr_debug("loading %s\n", path);
+	pr_debug("loading %s\n", attr->file);
 
-	return __bpf_object__open(path, NULL, 0, true);
+	return __bpf_object__open(attr->file, NULL, 0,
+				  bpf_prog_type__needs_kver(attr->prog_type));
+}
+
+struct bpf_object *bpf_object__open(const char *path)
+{
+	struct bpf_object_open_attr attr = {
+		.file		= path,
+		.prog_type	= BPF_PROG_TYPE_UNSPEC,
+	};
+
+	return bpf_object__open_xattr(&attr);
 }
 
 struct bpf_object *bpf_object__open_buffer(void *obj_buf,
@@ -2081,23 +2099,31 @@ static const struct {
 #undef BPF_S_PROG_SEC
 #undef BPF_SA_PROG_SEC
 
-static int bpf_program__identify_section(struct bpf_program *prog)
+int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
+			     enum bpf_attach_type *expected_attach_type)
 {
 	int i;
 
-	if (!prog->section_name)
-		goto err;
+	if (!name)
+		return -EINVAL;
 
-	for (i = 0; i < ARRAY_SIZE(section_names); i++)
-		if (strncmp(prog->section_name, section_names[i].sec,
-			    section_names[i].len) == 0)
-			return i;
+	for (i = 0; i < ARRAY_SIZE(section_names); i++) {
+		if (strncmp(name, section_names[i].sec, section_names[i].len))
+			continue;
+		*prog_type = section_names[i].prog_type;
+		*expected_attach_type = section_names[i].expected_attach_type;
+		return 0;
+	}
+	return -EINVAL;
+}
 
-err:
-	pr_warning("failed to guess program type based on section name %s\n",
-		   prog->section_name);
-
-	return -1;
+static int
+bpf_program__identify_section(struct bpf_program *prog,
+			      enum bpf_prog_type *prog_type,
+			      enum bpf_attach_type *expected_attach_type)
+{
+	return libbpf_prog_type_by_name(prog->section_name, prog_type,
+					expected_attach_type);
 }
 
 int bpf_map__fd(struct bpf_map *map)
@@ -2146,6 +2172,11 @@ void *bpf_map__priv(struct bpf_map *map)
 	return map ? map->priv : ERR_PTR(-EINVAL);
 }
 
+bool bpf_map__is_offload_neutral(struct bpf_map *map)
+{
+	return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
+}
+
 void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
 {
 	map->map_ifindex = ifindex;
@@ -2225,12 +2256,15 @@ int bpf_prog_load(const char *file, enum bpf_prog_type type,
 int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 			struct bpf_object **pobj, int *prog_fd)
 {
+	struct bpf_object_open_attr open_attr = {
+		.file		= attr->file,
+		.prog_type	= attr->prog_type,
+	};
 	struct bpf_program *prog, *first_prog = NULL;
 	enum bpf_attach_type expected_attach_type;
 	enum bpf_prog_type prog_type;
 	struct bpf_object *obj;
 	struct bpf_map *map;
-	int section_idx;
 	int err;
 
 	if (!attr)
@@ -2238,8 +2272,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 	if (!attr->file)
 		return -EINVAL;
 
-	obj = __bpf_object__open(attr->file, NULL, 0,
-				 bpf_prog_type__needs_kver(attr->prog_type));
+	obj = bpf_object__open_xattr(&open_attr);
 	if (IS_ERR_OR_NULL(obj))
 		return -ENOENT;
 
@@ -2252,14 +2285,14 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 		prog->prog_ifindex = attr->ifindex;
 		expected_attach_type = attr->expected_attach_type;
 		if (prog_type == BPF_PROG_TYPE_UNSPEC) {
-			section_idx = bpf_program__identify_section(prog);
-			if (section_idx < 0) {
+			err = bpf_program__identify_section(prog, &prog_type,
+							    &expected_attach_type);
+			if (err < 0) {
+				pr_warning("failed to guess program type based on section name %s\n",
+					   prog->section_name);
 				bpf_object__close(obj);
 				return -EINVAL;
 			}
-			prog_type = section_names[section_idx].prog_type;
-			expected_attach_type =
-				section_names[section_idx].expected_attach_type;
 		}
 
 		bpf_program__set_type(prog, prog_type);
@@ -2271,7 +2304,8 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 	}
 
 	bpf_map__for_each(map, obj) {
-		map->map_ifindex = attr->ifindex;
+		if (!bpf_map__is_offload_neutral(map))
+			map->map_ifindex = attr->ifindex;
 	}
 
 	if (!first_prog) {
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 564f4be9bae0..1f8fc2060460 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -66,7 +66,13 @@ void libbpf_set_print(libbpf_print_fn_t warn,
 /* Hide internal to user */
 struct bpf_object;
 
+struct bpf_object_open_attr {
+	const char *file;
+	enum bpf_prog_type prog_type;
+};
+
 struct bpf_object *bpf_object__open(const char *path);
+struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr);
 struct bpf_object *bpf_object__open_buffer(void *obj_buf,
 					   size_t obj_buf_sz,
 					   const char *name);
@@ -92,6 +98,9 @@ int bpf_object__set_priv(struct bpf_object *obj, void *priv,
 			 bpf_object_clear_priv_t clear_priv);
 void *bpf_object__priv(struct bpf_object *prog);
 
+int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
+			     enum bpf_attach_type *expected_attach_type);
+
 /* Accessors of bpf_program */
 struct bpf_program;
 struct bpf_program *bpf_program__next(struct bpf_program *prog,
@@ -252,6 +261,8 @@ typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
 int bpf_map__set_priv(struct bpf_map *map, void *priv,
 		      bpf_map_clear_priv_t clear_priv);
 void *bpf_map__priv(struct bpf_map *map);
+int bpf_map__reuse_fd(struct bpf_map *map, int fd);
+bool bpf_map__is_offload_neutral(struct bpf_map *map);
 void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
 int bpf_map__pin(struct bpf_map *map, const char *path);
 
diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c
new file mode 100644
index 000000000000..d9ba851bd7f9
--- /dev/null
+++ b/tools/lib/bpf/libbpf_errno.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: LGPL-2.1
+
+/*
+ * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
+ * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
+ * Copyright (C) 2015 Huawei Inc.
+ * Copyright (C) 2017 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ */
+
+#include <stdio.h>
+#include <string.h>
+
+#include "libbpf.h"
+
+#define ERRNO_OFFSET(e)		((e) - __LIBBPF_ERRNO__START)
+#define ERRCODE_OFFSET(c)	ERRNO_OFFSET(LIBBPF_ERRNO__##c)
+#define NR_ERRNO	(__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START)
+
+static const char *libbpf_strerror_table[NR_ERRNO] = {
+	[ERRCODE_OFFSET(LIBELF)]	= "Something wrong in libelf",
+	[ERRCODE_OFFSET(FORMAT)]	= "BPF object format invalid",
+	[ERRCODE_OFFSET(KVERSION)]	= "'version' section incorrect or lost",
+	[ERRCODE_OFFSET(ENDIAN)]	= "Endian mismatch",
+	[ERRCODE_OFFSET(INTERNAL)]	= "Internal error in libbpf",
+	[ERRCODE_OFFSET(RELOC)]		= "Relocation failed",
+	[ERRCODE_OFFSET(VERIFY)]	= "Kernel verifier blocks program loading",
+	[ERRCODE_OFFSET(PROG2BIG)]	= "Program too big",
+	[ERRCODE_OFFSET(KVER)]		= "Incorrect kernel version",
+	[ERRCODE_OFFSET(PROGTYPE)]	= "Kernel doesn't support this program type",
+	[ERRCODE_OFFSET(WRNGPID)]	= "Wrong pid in netlink message",
+	[ERRCODE_OFFSET(INVSEQ)]	= "Invalid netlink sequence",
+};
+
+int libbpf_strerror(int err, char *buf, size_t size)
+{
+	if (!buf || !size)
+		return -1;
+
+	err = err > 0 ? err : -err;
+
+	if (err < __LIBBPF_ERRNO__START) {
+		int ret;
+
+		ret = strerror_r(err, buf, size);
+		buf[size - 1] = '\0';
+		return ret;
+	}
+
+	if (err < __LIBBPF_ERRNO__END) {
+		const char *msg;
+
+		msg = libbpf_strerror_table[ERRNO_OFFSET(err)];
+		snprintf(buf, size, "%s", msg);
+		buf[size - 1] = '\0';
+		return 0;
+	}
+
+	snprintf(buf, size, "Unknown libbpf error %d", err);
+	buf[size - 1] = '\0';
+	return -1;
+}
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 7a6214e9ae58..478bf1bcbbf5 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -61,6 +61,7 @@ $(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
 $(OUTPUT)/test_sock: cgroup_helpers.c
 $(OUTPUT)/test_sock_addr: cgroup_helpers.c
 $(OUTPUT)/test_sockmap: cgroup_helpers.c
+$(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c
 $(OUTPUT)/test_progs: trace_helpers.c
 $(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c
 
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index c87b4e052ce9..cf16948aad4a 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -118,7 +118,7 @@ static int join_cgroup_from_top(char *cgroup_path)
  *
  * On success, it returns 0, otherwise on failure it returns 1.
  */
-int join_cgroup(char *path)
+int join_cgroup(const char *path)
 {
 	char cgroup_path[PATH_MAX + 1];
 
@@ -158,7 +158,7 @@ void cleanup_cgroup_environment(void)
  * On success, it returns the file descriptor. On failure it returns 0.
  * If there is a failure, it prints the error to stderr.
  */
-int create_and_get_cgroup(char *path)
+int create_and_get_cgroup(const char *path)
 {
 	char cgroup_path[PATH_MAX + 1];
 	int fd;
@@ -186,7 +186,7 @@ int create_and_get_cgroup(char *path)
  * which is an invalid cgroup id.
  * If there is a failure, it prints the error to stderr.
  */
-unsigned long long get_cgroup_id(char *path)
+unsigned long long get_cgroup_id(const char *path)
 {
 	int dirfd, err, flags, mount_id, fhsize;
 	union {
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h
index 20a4a5dcd469..d64bb8957090 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.h
+++ b/tools/testing/selftests/bpf/cgroup_helpers.h
@@ -9,10 +9,10 @@
 	__FILE__, __LINE__, clean_errno(), ##__VA_ARGS__)
 
 
-int create_and_get_cgroup(char *path);
-int join_cgroup(char *path);
+int create_and_get_cgroup(const char *path);
+int join_cgroup(const char *path);
 int setup_cgroup_environment(void);
 void cleanup_cgroup_environment(void);
-unsigned long long get_cgroup_id(char *path);
+unsigned long long get_cgroup_id(const char *path);
 
 #endif
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index be800d0e7a84..b746227eaff2 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -339,6 +339,11 @@ class NetdevSim:
         self.dfs = DebugfsDir(self.dfs_dir)
         return self.dfs
 
+    def dfs_read(self, f):
+        path = os.path.join(self.dfs_dir, f)
+        _, data = cmd('cat %s' % (path))
+        return data.strip()
+
     def dfs_num_bound_progs(self):
         path = os.path.join(self.dfs_dir, "bpf_bound_progs")
         _, progs = cmd('ls %s' % (path))
@@ -547,11 +552,11 @@ def check_extack(output, reference, args):
     if skip_extack:
         return
     lines = output.split("\n")
-    comp = len(lines) >= 2 and lines[1] == reference
+    comp = len(lines) >= 2 and lines[1] == 'Error: ' + reference
     fail(not comp, "Missing or incorrect netlink extack message")
 
 def check_extack_nsim(output, reference, args):
-    check_extack(output, "Error: netdevsim: " + reference, args)
+    check_extack(output, "netdevsim: " + reference, args)
 
 def check_no_extack(res, needle):
     fail((res[1] + res[2]).count(needle) or (res[1] + res[2]).count("Warning:"),
@@ -654,7 +659,7 @@ try:
     ret, _, err = sim.cls_bpf_add_filter(obj, skip_sw=True,
                                          fail=False, include_stderr=True)
     fail(ret == 0, "TC filter loaded without enabling TC offloads")
-    check_extack(err, "Error: TC offload is disabled on net device.", args)
+    check_extack(err, "TC offload is disabled on net device.", args)
     sim.wait_for_flush()
 
     sim.set_ethtool_tc_offloads(True)
@@ -694,7 +699,7 @@ try:
                                          skip_sw=True,
                                          fail=False, include_stderr=True)
     fail(ret == 0, "Offloaded a filter to chain other than 0")
-    check_extack(err, "Error: Driver supports only offload of chain 0.", args)
+    check_extack(err, "Driver supports only offload of chain 0.", args)
     sim.tc_flush_filters()
 
     start_test("Test TC replace...")
@@ -814,24 +819,20 @@ try:
          "Device parameters reported for non-offloaded program")
 
     start_test("Test XDP prog replace with bad flags...")
-    ret, _, err = sim.set_xdp(obj, "offload", force=True,
+    ret, _, err = sim.set_xdp(obj, "generic", force=True,
                               fail=False, include_stderr=True)
     fail(ret == 0, "Replaced XDP program with a program in different mode")
-    check_extack_nsim(err, "program loaded with different flags.", args)
+    fail(err.count("File exists") != 1, "Replaced driver XDP with generic")
     ret, _, err = sim.set_xdp(obj, "", force=True,
                               fail=False, include_stderr=True)
     fail(ret == 0, "Replaced XDP program with a program in different mode")
-    check_extack_nsim(err, "program loaded with different flags.", args)
+    check_extack(err, "program loaded with different flags.", args)
 
     start_test("Test XDP prog remove with bad flags...")
-    ret, _, err = sim.unset_xdp("offload", force=True,
-                                fail=False, include_stderr=True)
-    fail(ret == 0, "Removed program with a bad mode mode")
-    check_extack_nsim(err, "program loaded with different flags.", args)
     ret, _, err = sim.unset_xdp("", force=True,
                                 fail=False, include_stderr=True)
-    fail(ret == 0, "Removed program with a bad mode mode")
-    check_extack_nsim(err, "program loaded with different flags.", args)
+    fail(ret == 0, "Removed program with a bad mode")
+    check_extack(err, "program loaded with different flags.", args)
 
     start_test("Test MTU restrictions...")
     ret, _ = sim.set_mtu(9000, fail=False)
@@ -891,6 +892,60 @@ try:
     rm(pin_file)
     bpftool_prog_list_wait(expected=0)
 
+    start_test("Test multi-attachment XDP - attach...")
+    sim.set_xdp(obj, "offload")
+    xdp = sim.ip_link_show(xdp=True)["xdp"]
+    offloaded = sim.dfs_read("bpf_offloaded_id")
+    fail("prog" not in xdp, "Base program not reported in single program mode")
+    fail(len(ipl["xdp"]["attached"]) != 1,
+         "Wrong attached program count with one program")
+
+    sim.set_xdp(obj, "")
+    two_xdps = sim.ip_link_show(xdp=True)["xdp"]
+    offloaded2 = sim.dfs_read("bpf_offloaded_id")
+
+    fail(two_xdps["mode"] != 4, "Bad mode reported with multiple programs")
+    fail("prog" in two_xdps, "Base program reported in multi program mode")
+    fail(xdp["attached"][0] not in two_xdps["attached"],
+         "Offload program not reported after driver activated")
+    fail(len(two_xdps["attached"]) != 2,
+         "Wrong attached program count with two programs")
+    fail(two_xdps["attached"][0]["prog"]["id"] ==
+         two_xdps["attached"][1]["prog"]["id"],
+         "offloaded and drv programs have the same id")
+    fail(offloaded != offloaded2,
+         "offload ID changed after loading driver program")
+
+    start_test("Test multi-attachment XDP - replace...")
+    ret, _, err = sim.set_xdp(obj, "offload", fail=False, include_stderr=True)
+    fail(err.count("busy") != 1, "Replaced one of programs without -force")
+
+    start_test("Test multi-attachment XDP - detach...")
+    ret, _, err = sim.unset_xdp("drv", force=True,
+                                fail=False, include_stderr=True)
+    fail(ret == 0, "Removed program with a bad mode")
+    check_extack(err, "program loaded with different flags.", args)
+
+    sim.unset_xdp("offload")
+    xdp = sim.ip_link_show(xdp=True)["xdp"]
+    offloaded = sim.dfs_read("bpf_offloaded_id")
+
+    fail(xdp["mode"] != 1, "Bad mode reported after multiple programs")
+    fail("prog" not in xdp,
+         "Base program not reported after multi program mode")
+    fail(xdp["attached"][0] not in two_xdps["attached"],
+         "Offload program not reported after driver activated")
+    fail(len(ipl["xdp"]["attached"]) != 1,
+         "Wrong attached program count with remaining programs")
+    fail(offloaded != "0", "offload ID reported with only driver program left")
+
+    start_test("Test multi-attachment XDP - device remove...")
+    sim.set_xdp(obj, "offload")
+    sim.remove()
+
+    sim = NetdevSim()
+    sim.set_ethtool_tc_offloads(True)
+
     start_test("Test mixing of TC and XDP...")
     sim.tc_add_ingress()
     sim.set_xdp(obj, "offload")
diff --git a/tools/testing/selftests/bpf/test_tcpbpf.h b/tools/testing/selftests/bpf/test_tcpbpf.h
index 2fe43289943c..7bcfa6207005 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf.h
+++ b/tools/testing/selftests/bpf/test_tcpbpf.h
@@ -12,5 +12,6 @@ struct tcpbpf_globals {
 	__u32 good_cb_test_rv;
 	__u64 bytes_received;
 	__u64 bytes_acked;
+	__u32 num_listen;
 };
 #endif
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
index 3e645ee41ed5..4b7fd540cea9 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf_kern.c
+++ b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
@@ -96,15 +96,22 @@ int bpf_testcb(struct bpf_sock_ops *skops)
 			if (!gp)
 				break;
 			g = *gp;
-			g.total_retrans = skops->total_retrans;
-			g.data_segs_in = skops->data_segs_in;
-			g.data_segs_out = skops->data_segs_out;
-			g.bytes_received = skops->bytes_received;
-			g.bytes_acked = skops->bytes_acked;
+			if (skops->args[0] == BPF_TCP_LISTEN) {
+				g.num_listen++;
+			} else {
+				g.total_retrans = skops->total_retrans;
+				g.data_segs_in = skops->data_segs_in;
+				g.data_segs_out = skops->data_segs_out;
+				g.bytes_received = skops->bytes_received;
+				g.bytes_acked = skops->bytes_acked;
+			}
 			bpf_map_update_elem(&global_map, &key, &g,
 					    BPF_ANY);
 		}
 		break;
+	case BPF_SOCK_OPS_TCP_LISTEN_CB:
+		bpf_sock_ops_cb_flags_set(skops, BPF_SOCK_OPS_STATE_CB_FLAG);
+		break;
 	default:
 		rv = -1;
 	}
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c
index 84ab5163c828..a275c2971376 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf_user.c
+++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c
@@ -1,27 +1,59 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <inttypes.h>
 #include <stdio.h>
 #include <stdlib.h>
-#include <stdio.h>
 #include <unistd.h>
 #include <errno.h>
-#include <signal.h>
 #include <string.h>
-#include <assert.h>
-#include <linux/perf_event.h>
-#include <linux/ptrace.h>
 #include <linux/bpf.h>
-#include <sys/ioctl.h>
-#include <sys/time.h>
 #include <sys/types.h>
-#include <sys/stat.h>
-#include <fcntl.h>
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
-#include "bpf_util.h"
+
 #include "bpf_rlimit.h"
-#include <linux/perf_event.h>
+#include "bpf_util.h"
+#include "cgroup_helpers.h"
+
 #include "test_tcpbpf.h"
 
+#define EXPECT_EQ(expected, actual, fmt)			\
+	do {							\
+		if ((expected) != (actual)) {			\
+			printf("  Value of: " #actual "\n"	\
+			       "    Actual: %" fmt "\n"		\
+			       "  Expected: %" fmt "\n",	\
+			       (actual), (expected));		\
+			goto err;				\
+		}						\
+	} while (0)
+
+int verify_result(const struct tcpbpf_globals *result)
+{
+	__u32 expected_events;
+
+	expected_events = ((1 << BPF_SOCK_OPS_TIMEOUT_INIT) |
+			   (1 << BPF_SOCK_OPS_RWND_INIT) |
+			   (1 << BPF_SOCK_OPS_TCP_CONNECT_CB) |
+			   (1 << BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB) |
+			   (1 << BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB) |
+			   (1 << BPF_SOCK_OPS_NEEDS_ECN) |
+			   (1 << BPF_SOCK_OPS_STATE_CB) |
+			   (1 << BPF_SOCK_OPS_TCP_LISTEN_CB));
+
+	EXPECT_EQ(expected_events, result->event_map, "#" PRIx32);
+	EXPECT_EQ(501ULL, result->bytes_received, "llu");
+	EXPECT_EQ(1002ULL, result->bytes_acked, "llu");
+	EXPECT_EQ(1, result->data_segs_in, PRIu32);
+	EXPECT_EQ(1, result->data_segs_out, PRIu32);
+	EXPECT_EQ(0x80, result->bad_cb_test_rv, PRIu32);
+	EXPECT_EQ(0, result->good_cb_test_rv, PRIu32);
+	EXPECT_EQ(1, result->num_listen, PRIu32);
+
+	return 0;
+err:
+	return -1;
+}
+
 static int bpf_find_map(const char *test, struct bpf_object *obj,
 			const char *name)
 {
@@ -35,42 +67,28 @@ static int bpf_find_map(const char *test, struct bpf_object *obj,
 	return bpf_map__fd(map);
 }
 
-#define SYSTEM(CMD)						\
-	do {							\
-		if (system(CMD)) {				\
-			printf("system(%s) FAILS!\n", CMD);	\
-		}						\
-	} while (0)
-
 int main(int argc, char **argv)
 {
 	const char *file = "test_tcpbpf_kern.o";
 	struct tcpbpf_globals g = {0};
-	int cg_fd, prog_fd, map_fd;
-	bool debug_flag = false;
+	const char *cg_path = "/foo";
 	int error = EXIT_FAILURE;
 	struct bpf_object *obj;
-	char cmd[100], *dir;
-	struct stat buffer;
+	int prog_fd, map_fd;
+	int cg_fd = -1;
 	__u32 key = 0;
-	int pid;
 	int rv;
 
-	if (argc > 1 && strcmp(argv[1], "-d") == 0)
-		debug_flag = true;
+	if (setup_cgroup_environment())
+		goto err;
 
-	dir = "/tmp/cgroupv2/foo";
+	cg_fd = create_and_get_cgroup(cg_path);
+	if (!cg_fd)
+		goto err;
 
-	if (stat(dir, &buffer) != 0) {
-		SYSTEM("mkdir -p /tmp/cgroupv2");
-		SYSTEM("mount -t cgroup2 none /tmp/cgroupv2");
-		SYSTEM("mkdir -p /tmp/cgroupv2/foo");
-	}
-	pid = (int) getpid();
-	sprintf(cmd, "echo %d >> /tmp/cgroupv2/foo/cgroup.procs", pid);
-	SYSTEM(cmd);
+	if (join_cgroup(cg_path))
+		goto err;
 
-	cg_fd = open(dir, O_DIRECTORY, O_RDONLY);
 	if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) {
 		printf("FAILED: load_bpf_file failed for: %s\n", file);
 		goto err;
@@ -83,7 +101,10 @@ int main(int argc, char **argv)
 		goto err;
 	}
 
-	SYSTEM("./tcp_server.py");
+	if (system("./tcp_server.py")) {
+		printf("FAILED: TCP server\n");
+		goto err;
+	}
 
 	map_fd = bpf_find_map(__func__, obj, "global_map");
 	if (map_fd < 0)
@@ -95,34 +116,16 @@ int main(int argc, char **argv)
 		goto err;
 	}
 
-	if (g.bytes_received != 501 || g.bytes_acked != 1002 ||
-	    g.data_segs_in != 1 || g.data_segs_out != 1 ||
-	    (g.event_map ^ 0x47e) != 0 || g.bad_cb_test_rv != 0x80 ||
-		g.good_cb_test_rv != 0) {
+	if (verify_result(&g)) {
 		printf("FAILED: Wrong stats\n");
-		if (debug_flag) {
-			printf("\n");
-			printf("bytes_received: %d (expecting 501)\n",
-			       (int)g.bytes_received);
-			printf("bytes_acked:    %d (expecting 1002)\n",
-			       (int)g.bytes_acked);
-			printf("data_segs_in:   %d (expecting 1)\n",
-			       g.data_segs_in);
-			printf("data_segs_out:  %d (expecting 1)\n",
-			       g.data_segs_out);
-			printf("event_map:      0x%x (at least 0x47e)\n",
-			       g.event_map);
-			printf("bad_cb_test_rv: 0x%x (expecting 0x80)\n",
-			       g.bad_cb_test_rv);
-			printf("good_cb_test_rv:0x%x (expecting 0)\n",
-			       g.good_cb_test_rv);
-		}
 		goto err;
 	}
+
 	printf("PASSED!\n");
 	error = 0;
 err:
 	bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS);
+	close(cg_fd);
+	cleanup_cgroup_environment();
 	return error;
-
 }