Merge branch 'move-ld_abs-to-native-BPF'

Daniel Borkmann says:

====================
This set simplifies BPF JITs significantly by moving ld_abs/ld_ind
to native BPF, for details see individual patches. Main rationale
is in patch 'implement ld_abs/ld_ind in native bpf'. Thanks!

v1 -> v2:
  - Added missing seen_lds_abs in LDX_MSH and use X = A
    initially due to being preserved on func call.
  - Added a large batch of cBPF tests into test_bpf.
  - Added x32 removal of LD_ABS/LD_IND, so all JITs are
    covered.
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

arch/arm/net/bpf_jit_32.c

@@ -1452,83 +1452,6 @@ exit:
 			emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx);
 		emit_ldx_r(dst, rn, dstk, off, ctx, BPF_SIZE(code));
 		break;
-	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */
-	case BPF_LD | BPF_ABS | BPF_W:
-	case BPF_LD | BPF_ABS | BPF_H:
-	case BPF_LD | BPF_ABS | BPF_B:
-	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + src + imm)) */
-	case BPF_LD | BPF_IND | BPF_W:
-	case BPF_LD | BPF_IND | BPF_H:
-	case BPF_LD | BPF_IND | BPF_B:
-	{
-		const u8 r4 = bpf2a32[BPF_REG_6][1]; /* r4 = ptr to sk_buff */
-		const u8 r0 = bpf2a32[BPF_REG_0][1]; /*r0: struct sk_buff *skb*/
-						     /* rtn value */
-		const u8 r1 = bpf2a32[BPF_REG_0][0]; /* r1: int k */
-		const u8 r2 = bpf2a32[BPF_REG_1][1]; /* r2: unsigned int size */
-		const u8 r3 = bpf2a32[BPF_REG_1][0]; /* r3: void *buffer */
-		const u8 r6 = bpf2a32[TMP_REG_1][1]; /* r6: void *(*func)(..) */
-		int size;
-
-		/* Setting up first argument */
-		emit(ARM_MOV_R(r0, r4), ctx);
-
-		/* Setting up second argument */
-		emit_a32_mov_i(r1, imm, false, ctx);
-		if (BPF_MODE(code) == BPF_IND)
-			emit_a32_alu_r(r1, src_lo, false, sstk, ctx,
-				       false, false, BPF_ADD);
-
-		/* Setting up third argument */
-		switch (BPF_SIZE(code)) {
-		case BPF_W:
-			size = 4;
-			break;
-		case BPF_H:
-			size = 2;
-			break;
-		case BPF_B:
-			size = 1;
-			break;
-		default:
-			return -EINVAL;
-		}
-		emit_a32_mov_i(r2, size, false, ctx);
-
-		/* Setting up fourth argument */
-		emit(ARM_ADD_I(r3, ARM_SP, imm8m(SKB_BUFFER)), ctx);
-
-		/* Setting up function pointer to call */
-		emit_a32_mov_i(r6, (unsigned int)bpf_load_pointer, false, ctx);
-		emit_blx_r(r6, ctx);
-
-		emit(ARM_EOR_R(r1, r1, r1), ctx);
-		/* Check if return address is NULL or not.
-		 * if NULL then jump to epilogue
-		 * else continue to load the value from retn address
-		 */
-		emit(ARM_CMP_I(r0, 0), ctx);
-		jmp_offset = epilogue_offset(ctx);
-		check_imm24(jmp_offset);
-		_emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx);
-
-		/* Load value from the address */
-		switch (BPF_SIZE(code)) {
-		case BPF_W:
-			emit(ARM_LDR_I(r0, r0, 0), ctx);
-			emit_rev32(r0, r0, ctx);
-			break;
-		case BPF_H:
-			emit(ARM_LDRH_I(r0, r0, 0), ctx);
-			emit_rev16(r0, r0, ctx);
-			break;
-		case BPF_B:
-			emit(ARM_LDRB_I(r0, r0, 0), ctx);
-			/* No need to reverse */
-			break;
-		}
-		break;
-	}
 	/* ST: *(size *)(dst + off) = imm */
 	case BPF_ST | BPF_MEM | BPF_W:
 	case BPF_ST | BPF_MEM | BPF_H:

arch/arm64/net/bpf_jit_comp.c

@@ -723,71 +723,6 @@ emit_cond_jmp:
 		emit(A64_CBNZ(0, tmp3, jmp_offset), ctx);
 		break;
 
-	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */
-	case BPF_LD | BPF_ABS | BPF_W:
-	case BPF_LD | BPF_ABS | BPF_H:
-	case BPF_LD | BPF_ABS | BPF_B:
-	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + src + imm)) */
-	case BPF_LD | BPF_IND | BPF_W:
-	case BPF_LD | BPF_IND | BPF_H:
-	case BPF_LD | BPF_IND | BPF_B:
-	{
-		const u8 r0 = bpf2a64[BPF_REG_0]; /* r0 = return value */
-		const u8 r6 = bpf2a64[BPF_REG_6]; /* r6 = pointer to sk_buff */
-		const u8 fp = bpf2a64[BPF_REG_FP];
-		const u8 r1 = bpf2a64[BPF_REG_1]; /* r1: struct sk_buff *skb */
-		const u8 r2 = bpf2a64[BPF_REG_2]; /* r2: int k */
-		const u8 r3 = bpf2a64[BPF_REG_3]; /* r3: unsigned int size */
-		const u8 r4 = bpf2a64[BPF_REG_4]; /* r4: void *buffer */
-		const u8 r5 = bpf2a64[BPF_REG_5]; /* r5: void *(*func)(...) */
-		int size;
-
-		emit(A64_MOV(1, r1, r6), ctx);
-		emit_a64_mov_i(0, r2, imm, ctx);
-		if (BPF_MODE(code) == BPF_IND)
-			emit(A64_ADD(0, r2, r2, src), ctx);
-		switch (BPF_SIZE(code)) {
-		case BPF_W:
-			size = 4;
-			break;
-		case BPF_H:
-			size = 2;
-			break;
-		case BPF_B:
-			size = 1;
-			break;
-		default:
-			return -EINVAL;
-		}
-		emit_a64_mov_i64(r3, size, ctx);
-		emit(A64_SUB_I(1, r4, fp, ctx->stack_size), ctx);
-		emit_a64_mov_i64(r5, (unsigned long)bpf_load_pointer, ctx);
-		emit(A64_BLR(r5), ctx);
-		emit(A64_MOV(1, r0, A64_R(0)), ctx);
-
-		jmp_offset = epilogue_offset(ctx);
-		check_imm19(jmp_offset);
-		emit(A64_CBZ(1, r0, jmp_offset), ctx);
-		emit(A64_MOV(1, r5, r0), ctx);
-		switch (BPF_SIZE(code)) {
-		case BPF_W:
-			emit(A64_LDR32(r0, r5, A64_ZR), ctx);
-#ifndef CONFIG_CPU_BIG_ENDIAN
-			emit(A64_REV32(0, r0, r0), ctx);
-#endif
-			break;
-		case BPF_H:
-			emit(A64_LDRH(r0, r5, A64_ZR), ctx);
-#ifndef CONFIG_CPU_BIG_ENDIAN
-			emit(A64_REV16(0, r0, r0), ctx);
-#endif
-			break;
-		case BPF_B:
-			emit(A64_LDRB(r0, r5, A64_ZR), ctx);
-			break;
-		}
-		break;
-	}
 	default:
 		pr_err_once("unknown opcode %02x\n", code);
 		return -EINVAL;

arch/mips/net/ebpf_jit.c

@@ -1267,110 +1267,6 @@ jeq_common:
 			return -EINVAL;
 		break;
 
-	case BPF_LD | BPF_B | BPF_ABS:
-	case BPF_LD | BPF_H | BPF_ABS:
-	case BPF_LD | BPF_W | BPF_ABS:
-	case BPF_LD | BPF_DW | BPF_ABS:
-		ctx->flags |= EBPF_SAVE_RA;
-
-		gen_imm_to_reg(insn, MIPS_R_A1, ctx);
-		emit_instr(ctx, addiu, MIPS_R_A2, MIPS_R_ZERO, size_to_len(insn));
-
-		if (insn->imm < 0) {
-			emit_const_to_reg(ctx, MIPS_R_T9, (u64)bpf_internal_load_pointer_neg_helper);
-		} else {
-			emit_const_to_reg(ctx, MIPS_R_T9, (u64)ool_skb_header_pointer);
-			emit_instr(ctx, daddiu, MIPS_R_A3, MIPS_R_SP, ctx->tmp_offset);
-		}
-		goto ld_skb_common;
-
-	case BPF_LD | BPF_B | BPF_IND:
-	case BPF_LD | BPF_H | BPF_IND:
-	case BPF_LD | BPF_W | BPF_IND:
-	case BPF_LD | BPF_DW | BPF_IND:
-		ctx->flags |= EBPF_SAVE_RA;
-		src = ebpf_to_mips_reg(ctx, insn, src_reg_no_fp);
-		if (src < 0)
-			return src;
-		ts = get_reg_val_type(ctx, this_idx, insn->src_reg);
-		if (ts == REG_32BIT_ZERO_EX) {
-			/* sign extend */
-			emit_instr(ctx, sll, MIPS_R_A1, src, 0);
-			src = MIPS_R_A1;
-		}
-		if (insn->imm >= S16_MIN && insn->imm <= S16_MAX) {
-			emit_instr(ctx, daddiu, MIPS_R_A1, src, insn->imm);
-		} else {
-			gen_imm_to_reg(insn, MIPS_R_AT, ctx);
-			emit_instr(ctx, daddu, MIPS_R_A1, MIPS_R_AT, src);
-		}
-		/* truncate to 32-bit int */
-		emit_instr(ctx, sll, MIPS_R_A1, MIPS_R_A1, 0);
-		emit_instr(ctx, daddiu, MIPS_R_A3, MIPS_R_SP, ctx->tmp_offset);
-		emit_instr(ctx, slt, MIPS_R_AT, MIPS_R_A1, MIPS_R_ZERO);
-
-		emit_const_to_reg(ctx, MIPS_R_T8, (u64)bpf_internal_load_pointer_neg_helper);
-		emit_const_to_reg(ctx, MIPS_R_T9, (u64)ool_skb_header_pointer);
-		emit_instr(ctx, addiu, MIPS_R_A2, MIPS_R_ZERO, size_to_len(insn));
-		emit_instr(ctx, movn, MIPS_R_T9, MIPS_R_T8, MIPS_R_AT);
-
-ld_skb_common:
-		emit_instr(ctx, jalr, MIPS_R_RA, MIPS_R_T9);
-		/* delay slot move */
-		emit_instr(ctx, daddu, MIPS_R_A0, MIPS_R_S0, MIPS_R_ZERO);
-
-		/* Check the error value */
-		b_off = b_imm(exit_idx, ctx);
-		if (is_bad_offset(b_off)) {
-			target = j_target(ctx, exit_idx);
-			if (target == (unsigned int)-1)
-				return -E2BIG;
-
-			if (!(ctx->offsets[this_idx] & OFFSETS_B_CONV)) {
-				ctx->offsets[this_idx] |= OFFSETS_B_CONV;
-				ctx->long_b_conversion = 1;
-			}
-			emit_instr(ctx, bne, MIPS_R_V0, MIPS_R_ZERO, 4 * 3);
-			emit_instr(ctx, nop);
-			emit_instr(ctx, j, target);
-			emit_instr(ctx, nop);
-		} else {
-			emit_instr(ctx, beq, MIPS_R_V0, MIPS_R_ZERO, b_off);
-			emit_instr(ctx, nop);
-		}
-
-#ifdef __BIG_ENDIAN
-		need_swap = false;
-#else
-		need_swap = true;
-#endif
-		dst = MIPS_R_V0;
-		switch (BPF_SIZE(insn->code)) {
-		case BPF_B:
-			emit_instr(ctx, lbu, dst, 0, MIPS_R_V0);
-			break;
-		case BPF_H:
-			emit_instr(ctx, lhu, dst, 0, MIPS_R_V0);
-			if (need_swap)
-				emit_instr(ctx, wsbh, dst, dst);
-			break;
-		case BPF_W:
-			emit_instr(ctx, lw, dst, 0, MIPS_R_V0);
-			if (need_swap) {
-				emit_instr(ctx, wsbh, dst, dst);
-				emit_instr(ctx, rotr, dst, dst, 16);
-			}
-			break;
-		case BPF_DW:
-			emit_instr(ctx, ld, dst, 0, MIPS_R_V0);
-			if (need_swap) {
-				emit_instr(ctx, dsbh, dst, dst);
-				emit_instr(ctx, dshd, dst, dst);
-			}
-			break;
-		}
-
-		break;
 	case BPF_ALU | BPF_END | BPF_FROM_BE:
 	case BPF_ALU | BPF_END | BPF_FROM_LE:
 		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);

arch/powerpc/net/Makefile

@@ -3,7 +3,7 @@
 # Arch-specific network modules
 #
 ifeq ($(CONFIG_PPC64),y)
-obj-$(CONFIG_BPF_JIT) += bpf_jit_asm64.o bpf_jit_comp64.o
+obj-$(CONFIG_BPF_JIT) += bpf_jit_comp64.o
 else
 obj-$(CONFIG_BPF_JIT) += bpf_jit_asm.o bpf_jit_comp.o
 endif

arch/powerpc/net/bpf_jit64.h

@@ -20,7 +20,7 @@
  * with our redzone usage.
  *
  *		[	prev sp		] <-------------
- *		[   nv gpr save area	] 8*8		|
+ *		[   nv gpr save area	] 6*8		|
  *		[    tail_call_cnt	] 8		|
  *		[    local_tmp_var	] 8		|
  * fp (r31) -->	[   ebpf stack space	] upto 512	|
@@ -28,8 +28,8 @@
  * sp (r1) --->	[    stack pointer	] --------------
  */
 
-/* for gpr non volatile registers BPG_REG_6 to 10, plus skb cache registers */
-#define BPF_PPC_STACK_SAVE	(8*8)
+/* for gpr non volatile registers BPG_REG_6 to 10 */
+#define BPF_PPC_STACK_SAVE	(6*8)
 /* for bpf JIT code internal usage */
 #define BPF_PPC_STACK_LOCALS	16
 /* stack frame excluding BPF stack, ensure this is quadword aligned */
@@ -39,10 +39,8 @@
 #ifndef __ASSEMBLY__
 
 /* BPF register usage */
-#define SKB_HLEN_REG	(MAX_BPF_JIT_REG + 0)
-#define SKB_DATA_REG	(MAX_BPF_JIT_REG + 1)
-#define TMP_REG_1	(MAX_BPF_JIT_REG + 2)
-#define TMP_REG_2	(MAX_BPF_JIT_REG + 3)
+#define TMP_REG_1	(MAX_BPF_JIT_REG + 0)
+#define TMP_REG_2	(MAX_BPF_JIT_REG + 1)
 
 /* BPF to ppc register mappings */
 static const int b2p[] = {
@@ -63,40 +61,23 @@ static const int b2p[] = {
 	[BPF_REG_FP] = 31,
 	/* eBPF jit internal registers */
 	[BPF_REG_AX] = 2,
-	[SKB_HLEN_REG] = 25,
-	[SKB_DATA_REG] = 26,
 	[TMP_REG_1] = 9,
 	[TMP_REG_2] = 10
 };
 
-/* PPC NVR range -- update this if we ever use NVRs below r24 */
-#define BPF_PPC_NVR_MIN		24
-
-/* Assembly helpers */
-#define DECLARE_LOAD_FUNC(func)	u64 func(u64 r3, u64 r4);			\
-				u64 func##_negative_offset(u64 r3, u64 r4);	\
-				u64 func##_positive_offset(u64 r3, u64 r4);
-
-DECLARE_LOAD_FUNC(sk_load_word);
-DECLARE_LOAD_FUNC(sk_load_half);
-DECLARE_LOAD_FUNC(sk_load_byte);
-
-#define CHOOSE_LOAD_FUNC(imm, func)						\
-			(imm < 0 ?						\
-			(imm >= SKF_LL_OFF ? func##_negative_offset : func) :	\
-			func##_positive_offset)
+/* PPC NVR range -- update this if we ever use NVRs below r27 */
+#define BPF_PPC_NVR_MIN		27
 
 #define SEEN_FUNC	0x1000 /* might call external helpers */
 #define SEEN_STACK	0x2000 /* uses BPF stack */
-#define SEEN_SKB	0x4000 /* uses sk_buff */
-#define SEEN_TAILCALL	0x8000 /* uses tail calls */
+#define SEEN_TAILCALL	0x4000 /* uses tail calls */
 
 struct codegen_context {
 	/*
 	 * This is used to track register usage as well
 	 * as calls to external helpers.
 	 * - register usage is tracked with corresponding
-	 *   bits (r3-r10 and r25-r31)
+	 *   bits (r3-r10 and r27-r31)
 	 * - rest of the bits can be used to track other
 	 *   things -- for now, we use bits 16 to 23
 	 *   encoded in SEEN_* macros above

arch/powerpc/net/bpf_jit_asm64.S

@@ -1,180 +0,0 @@
-/*
- * bpf_jit_asm64.S: Packet/header access helper functions
- * for PPC64 BPF compiler.
- *
- * Copyright 2016, Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
- * 		   IBM Corporation
- *
- * Based on bpf_jit_asm.S by Matt Evans
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-
-#include <asm/ppc_asm.h>
-#include <asm/ptrace.h>
-#include "bpf_jit64.h"
-
-/*
- * All of these routines are called directly from generated code,
- * with the below register usage:
- * r27		skb pointer (ctx)
- * r25		skb header length
- * r26		skb->data pointer
- * r4		offset
- *
- * Result is passed back in:
- * r8		data read in host endian format (accumulator)
- *
- * r9 is used as a temporary register
- */
-
-#define r_skb	r27
-#define r_hlen	r25
-#define r_data	r26
-#define r_off	r4
-#define r_val	r8
-#define r_tmp	r9
-
-_GLOBAL_TOC(sk_load_word)
-	cmpdi	r_off, 0
-	blt	bpf_slow_path_word_neg
-	b	sk_load_word_positive_offset
-
-_GLOBAL_TOC(sk_load_word_positive_offset)
-	/* Are we accessing past headlen? */
-	subi	r_tmp, r_hlen, 4
-	cmpd	r_tmp, r_off
-	blt	bpf_slow_path_word
-	/* Nope, just hitting the header.  cr0 here is eq or gt! */
-	LWZX_BE	r_val, r_data, r_off
-	blr	/* Return success, cr0 != LT */
-
-_GLOBAL_TOC(sk_load_half)
-	cmpdi	r_off, 0
-	blt	bpf_slow_path_half_neg
-	b	sk_load_half_positive_offset
-
-_GLOBAL_TOC(sk_load_half_positive_offset)
-	subi	r_tmp, r_hlen, 2
-	cmpd	r_tmp, r_off
-	blt	bpf_slow_path_half
-	LHZX_BE	r_val, r_data, r_off
-	blr
-
-_GLOBAL_TOC(sk_load_byte)
-	cmpdi	r_off, 0
-	blt	bpf_slow_path_byte_neg
-	b	sk_load_byte_positive_offset
-
-_GLOBAL_TOC(sk_load_byte_positive_offset)
-	cmpd	r_hlen, r_off
-	ble	bpf_slow_path_byte
-	lbzx	r_val, r_data, r_off
-	blr
-
-/*
- * Call out to skb_copy_bits:
- * Allocate a new stack frame here to remain ABI-compliant in
- * stashing LR.
- */
-#define bpf_slow_path_common(SIZE)					\
-	mflr	r0;							\
-	std	r0, PPC_LR_STKOFF(r1);					\
-	stdu	r1, -(STACK_FRAME_MIN_SIZE + BPF_PPC_STACK_LOCALS)(r1);	\
-	mr	r3, r_skb;						\
-	/* r4 = r_off as passed */					\
-	addi	r5, r1, STACK_FRAME_MIN_SIZE;				\
-	li	r6, SIZE;						\
-	bl	skb_copy_bits;						\
-	nop;								\
-	/* save r5 */							\
-	addi	r5, r1, STACK_FRAME_MIN_SIZE;				\
-	/* r3 = 0 on success */						\
-	addi	r1, r1, STACK_FRAME_MIN_SIZE + BPF_PPC_STACK_LOCALS;	\
-	ld	r0, PPC_LR_STKOFF(r1);					\
-	mtlr	r0;							\
-	cmpdi	r3, 0;							\
-	blt	bpf_error;	/* cr0 = LT */
-
-bpf_slow_path_word:
-	bpf_slow_path_common(4)
-	/* Data value is on stack, and cr0 != LT */
-	LWZX_BE	r_val, 0, r5
-	blr
-
-bpf_slow_path_half:
-	bpf_slow_path_common(2)
-	LHZX_BE	r_val, 0, r5
-	blr
-
-bpf_slow_path_byte:
-	bpf_slow_path_common(1)
-	lbzx	r_val, 0, r5
-	blr
-
-/*
- * Call out to bpf_internal_load_pointer_neg_helper
- */
-#define sk_negative_common(SIZE)				\
-	mflr	r0;						\
-	std	r0, PPC_LR_STKOFF(r1);				\
-	stdu	r1, -STACK_FRAME_MIN_SIZE(r1);			\
-	mr	r3, r_skb;					\
-	/* r4 = r_off, as passed */				\
-	li	r5, SIZE;					\
-	bl	bpf_internal_load_pointer_neg_helper;		\
-	nop;							\
-	addi	r1, r1, STACK_FRAME_MIN_SIZE;			\
-	ld	r0, PPC_LR_STKOFF(r1);				\
-	mtlr	r0;						\
-	/* R3 != 0 on success */				\
-	cmpldi	r3, 0;						\
-	beq	bpf_error_slow;	/* cr0 = EQ */
-
-bpf_slow_path_word_neg:
-	lis     r_tmp, -32	/* SKF_LL_OFF */
-	cmpd	r_off, r_tmp	/* addr < SKF_* */
-	blt	bpf_error	/* cr0 = LT */
-	b	sk_load_word_negative_offset
-
-_GLOBAL_TOC(sk_load_word_negative_offset)
-	sk_negative_common(4)
-	LWZX_BE	r_val, 0, r3
-	blr
-
-bpf_slow_path_half_neg:
-	lis     r_tmp, -32	/* SKF_LL_OFF */
-	cmpd	r_off, r_tmp	/* addr < SKF_* */
-	blt	bpf_error	/* cr0 = LT */
-	b	sk_load_half_negative_offset
-
-_GLOBAL_TOC(sk_load_half_negative_offset)
-	sk_negative_common(2)
-	LHZX_BE	r_val, 0, r3
-	blr
-
-bpf_slow_path_byte_neg:
-	lis     r_tmp, -32	/* SKF_LL_OFF */
-	cmpd	r_off, r_tmp	/* addr < SKF_* */
-	blt	bpf_error	/* cr0 = LT */
-	b	sk_load_byte_negative_offset
-
-_GLOBAL_TOC(sk_load_byte_negative_offset)
-	sk_negative_common(1)
-	lbzx	r_val, 0, r3
-	blr
-
-bpf_error_slow:
-	/* fabricate a cr0 = lt */
-	li	r_tmp, -1
-	cmpdi	r_tmp, 0
-bpf_error:
-	/*
-	 * Entered with cr0 = lt
-	 * Generated code will 'blt epilogue', returning 0.
-	 */
-	li	r_val, 0
-	blr

arch/powerpc/net/bpf_jit_comp64.c

@@ -59,7 +59,7 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx)
  *		[	prev sp		] <-------------
  *		[	  ...       	] 		|
  * sp (r1) --->	[    stack pointer	] --------------
- *		[   nv gpr save area	] 8*8
+ *		[   nv gpr save area	] 6*8
  *		[    tail_call_cnt	] 8
  *		[    local_tmp_var	] 8
  *		[   unused red zone	] 208 bytes protected
@@ -88,21 +88,6 @@ static int bpf_jit_stack_offsetof(struct codegen_context *ctx, int reg)
 	BUG();
 }
 
-static void bpf_jit_emit_skb_loads(u32 *image, struct codegen_context *ctx)
-{
-	/*
-	 * Load skb->len and skb->data_len
-	 * r3 points to skb
-	 */
-	PPC_LWZ(b2p[SKB_HLEN_REG], 3, offsetof(struct sk_buff, len));
-	PPC_LWZ(b2p[TMP_REG_1], 3, offsetof(struct sk_buff, data_len));
-	/* header_len = len - data_len */
-	PPC_SUB(b2p[SKB_HLEN_REG], b2p[SKB_HLEN_REG], b2p[TMP_REG_1]);
-
-	/* skb->data pointer */
-	PPC_BPF_LL(b2p[SKB_DATA_REG], 3, offsetof(struct sk_buff, data));
-}
-
 static void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
 {
 	int i;
@@ -145,18 +130,6 @@ static void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
 		if (bpf_is_seen_register(ctx, i))
 			PPC_BPF_STL(b2p[i], 1, bpf_jit_stack_offsetof(ctx, b2p[i]));
 
-	/*
-	 * Save additional non-volatile regs if we cache skb
-	 * Also, setup skb data
-	 */
-	if (ctx->seen & SEEN_SKB) {
-		PPC_BPF_STL(b2p[SKB_HLEN_REG], 1,
-				bpf_jit_stack_offsetof(ctx, b2p[SKB_HLEN_REG]));
-		PPC_BPF_STL(b2p[SKB_DATA_REG], 1,
-				bpf_jit_stack_offsetof(ctx, b2p[SKB_DATA_REG]));
-		bpf_jit_emit_skb_loads(image, ctx);
-	}
-
 	/* Setup frame pointer to point to the bpf stack area */
 	if (bpf_is_seen_register(ctx, BPF_REG_FP))
 		PPC_ADDI(b2p[BPF_REG_FP], 1,
@@ -172,14 +145,6 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx
 		if (bpf_is_seen_register(ctx, i))
 			PPC_BPF_LL(b2p[i], 1, bpf_jit_stack_offsetof(ctx, b2p[i]));
 
-	/* Restore non-volatile registers used for skb cache */
-	if (ctx->seen & SEEN_SKB) {
-		PPC_BPF_LL(b2p[SKB_HLEN_REG], 1,
-				bpf_jit_stack_offsetof(ctx, b2p[SKB_HLEN_REG]));
-		PPC_BPF_LL(b2p[SKB_DATA_REG], 1,
-				bpf_jit_stack_offsetof(ctx, b2p[SKB_DATA_REG]));
-	}
-
 	/* Tear down our stack frame */
 	if (bpf_has_stack_frame(ctx)) {
 		PPC_ADDI(1, 1, BPF_PPC_STACKFRAME + ctx->stack_size);
@@ -753,23 +718,10 @@ emit_clear:
 			ctx->seen |= SEEN_FUNC;
 			func = (u8 *) __bpf_call_base + imm;
 
-			/* Save skb pointer if we need to re-cache skb data */
-			if ((ctx->seen & SEEN_SKB) &&
-			    bpf_helper_changes_pkt_data(func))
-				PPC_BPF_STL(3, 1, bpf_jit_stack_local(ctx));
-
 			bpf_jit_emit_func_call(image, ctx, (u64)func);
 
 			/* move return value from r3 to BPF_REG_0 */
 			PPC_MR(b2p[BPF_REG_0], 3);
-
-			/* refresh skb cache */
-			if ((ctx->seen & SEEN_SKB) &&
-			    bpf_helper_changes_pkt_data(func)) {
-				/* reload skb pointer to r3 */
-				PPC_BPF_LL(3, 1, bpf_jit_stack_local(ctx));
-				bpf_jit_emit_skb_loads(image, ctx);
-			}
 			break;
 
 		/*
@@ -886,65 +838,6 @@ cond_branch:
 			PPC_BCC(true_cond, addrs[i + 1 + off]);
 			break;
 
-		/*
-		 * Loads from packet header/data
-		 * Assume 32-bit input value in imm and X (src_reg)
-		 */
-
-		/* Absolute loads */
-		case BPF_LD | BPF_W | BPF_ABS:
-			func = (u8 *)CHOOSE_LOAD_FUNC(imm, sk_load_word);
-			goto common_load_abs;
-		case BPF_LD | BPF_H | BPF_ABS:
-			func = (u8 *)CHOOSE_LOAD_FUNC(imm, sk_load_half);
-			goto common_load_abs;
-		case BPF_LD | BPF_B | BPF_ABS:
-			func = (u8 *)CHOOSE_LOAD_FUNC(imm, sk_load_byte);
-common_load_abs:
-			/*
-			 * Load from [imm]
-			 * Load into r4, which can just be passed onto
-			 *  skb load helpers as the second parameter
-			 */
-			PPC_LI32(4, imm);
-			goto common_load;
-
-		/* Indirect loads */
-		case BPF_LD | BPF_W | BPF_IND:
-			func = (u8 *)sk_load_word;
-			goto common_load_ind;
-		case BPF_LD | BPF_H | BPF_IND:
-			func = (u8 *)sk_load_half;
-			goto common_load_ind;
-		case BPF_LD | BPF_B | BPF_IND:
-			func = (u8 *)sk_load_byte;
-common_load_ind:
-			/*
-			 * Load from [src_reg + imm]
-			 * Treat src_reg as a 32-bit value
-			 */
-			PPC_EXTSW(4, src_reg);
-			if (imm) {
-				if (imm >= -32768 && imm < 32768)
-					PPC_ADDI(4, 4, IMM_L(imm));
-				else {
-					PPC_LI32(b2p[TMP_REG_1], imm);
-					PPC_ADD(4, 4, b2p[TMP_REG_1]);
-				}
-			}
-
-common_load:
-			ctx->seen |= SEEN_SKB;
-			ctx->seen |= SEEN_FUNC;
-			bpf_jit_emit_func_call(image, ctx, (u64)func);
-
-			/*
-			 * Helper returns 'lt' condition on error, and an
-			 * appropriate return value in BPF_REG_0
-			 */
-			PPC_BCC(COND_LT, exit_addr);
-			break;
-
 		/*
 		 * Tail call
 		 */

arch/s390/net/Makefile

@@ -2,4 +2,4 @@
 #
 # Arch-specific network modules
 #
-obj-$(CONFIG_BPF_JIT) += bpf_jit.o bpf_jit_comp.o
+obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o

arch/s390/net/bpf_jit.S

@@ -1,116 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * BPF Jit compiler for s390, help functions.
- *
- * Copyright IBM Corp. 2012,2015
- *
- * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
- *	      Michael Holzheu <holzheu@linux.vnet.ibm.com>
- */
-
-#include <linux/linkage.h>
-#include "bpf_jit.h"
-
-/*
- * Calling convention:
- * registers %r7-%r10, %r11,%r13, and %r15 are call saved
- *
- * Input (64 bit):
- *   %r3 (%b2) = offset into skb data
- *   %r6 (%b5) = return address
- *   %r7 (%b6) = skb pointer
- *   %r12      = skb data pointer
- *
- * Output:
- *   %r14= %b0 = return value (read skb value)
- *
- * Work registers: %r2,%r4,%r5,%r14
- *
- * skb_copy_bits takes 4 parameters:
- *   %r2 = skb pointer
- *   %r3 = offset into skb data
- *   %r4 = pointer to temp buffer
- *   %r5 = length to copy
- *   Return value in %r2: 0 = ok
- *
- * bpf_internal_load_pointer_neg_helper takes 3 parameters:
- *   %r2 = skb pointer
- *   %r3 = offset into data
- *   %r4 = length to copy
- *   Return value in %r2: Pointer to data
- */
-
-#define SKF_MAX_NEG_OFF	-0x200000	/* SKF_LL_OFF from filter.h */
-
-/*
- * Load SIZE bytes from SKB
- */
-#define sk_load_common(NAME, SIZE, LOAD)				\
-ENTRY(sk_load_##NAME);							\
-	ltgr	%r3,%r3;		/* Is offset negative? */	\
-	jl	sk_load_##NAME##_slow_neg;				\
-ENTRY(sk_load_##NAME##_pos);						\
-	aghi	%r3,SIZE;		/* Offset + SIZE */		\
-	clg	%r3,STK_OFF_HLEN(%r15);	/* Offset + SIZE > hlen? */	\
-	jh	sk_load_##NAME##_slow;					\
-	LOAD	%r14,-SIZE(%r3,%r12);	/* Get data from skb */		\
-	b	OFF_OK(%r6);		/* Return */			\
-									\
-sk_load_##NAME##_slow:;							\
-	lgr	%r2,%r7;		/* Arg1 = skb pointer */	\
-	aghi	%r3,-SIZE;		/* Arg2 = offset */		\
-	la	%r4,STK_OFF_TMP(%r15);	/* Arg3 = temp bufffer */	\
-	lghi	%r5,SIZE;		/* Arg4 = size */		\
-	brasl	%r14,skb_copy_bits;	/* Get data from skb */		\
-	LOAD	%r14,STK_OFF_TMP(%r15);	/* Load from temp bufffer */	\
-	ltgr	%r2,%r2;		/* Set cc to (%r2 != 0) */	\
-	br	%r6;			/* Return */
-
-sk_load_common(word, 4, llgf)	/* r14 = *(u32 *) (skb->data+offset) */
-sk_load_common(half, 2, llgh)	/* r14 = *(u16 *) (skb->data+offset) */
-
-/*
- * Load 1 byte from SKB (optimized version)
- */
-	/* r14 = *(u8 *) (skb->data+offset) */
-ENTRY(sk_load_byte)
-	ltgr	%r3,%r3			# Is offset negative?
-	jl	sk_load_byte_slow_neg
-ENTRY(sk_load_byte_pos)
-	clg	%r3,STK_OFF_HLEN(%r15)	# Offset >= hlen?
-	jnl	sk_load_byte_slow
-	llgc	%r14,0(%r3,%r12)	# Get byte from skb
-	b	OFF_OK(%r6)		# Return OK
-
-sk_load_byte_slow:
-	lgr	%r2,%r7			# Arg1 = skb pointer
-					# Arg2 = offset
-	la	%r4,STK_OFF_TMP(%r15)	# Arg3 = pointer to temp buffer
-	lghi	%r5,1			# Arg4 = size (1 byte)
-	brasl	%r14,skb_copy_bits	# Get data from skb
-	llgc	%r14,STK_OFF_TMP(%r15)	# Load result from temp buffer
-	ltgr	%r2,%r2			# Set cc to (%r2 != 0)
-	br	%r6			# Return cc
-
-#define sk_negative_common(NAME, SIZE, LOAD)				\
-sk_load_##NAME##_slow_neg:;						\
-	cgfi	%r3,SKF_MAX_NEG_OFF;					\
-	jl	bpf_error;						\
-	lgr	%r2,%r7;		/* Arg1 = skb pointer */	\
-					/* Arg2 = offset */		\
-	lghi	%r4,SIZE;		/* Arg3 = size */		\
-	brasl	%r14,bpf_internal_load_pointer_neg_helper;		\
-	ltgr	%r2,%r2;						\
-	jz	bpf_error;						\
-	LOAD	%r14,0(%r2);		/* Get data from pointer */	\
-	xr	%r3,%r3;		/* Set cc to zero */		\
-	br	%r6;			/* Return cc */
-
-sk_negative_common(word, 4, llgf)
-sk_negative_common(half, 2, llgh)
-sk_negative_common(byte, 1, llgc)
-
-bpf_error:
-# force a return 0 from jit handler
-	ltgr	%r15,%r15	# Set condition code
-	br	%r6

arch/s390/net/bpf_jit.h

@@ -16,9 +16,6 @@
 #include <linux/filter.h>
 #include <linux/types.h>
 
-extern u8 sk_load_word_pos[], sk_load_half_pos[], sk_load_byte_pos[];
-extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
-
 #endif /* __ASSEMBLY__ */
 
 /*
@@ -36,15 +33,6 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
  *	      |		      |     |
  *	      |   BPF stack   |     |
  *	      |		      |     |
- *	      +---------------+     |
- *	      | 8 byte skbp   |     |
- * R15+176 -> +---------------+     |
- *	      | 8 byte hlen   |     |
- * R15+168 -> +---------------+     |
- *	      | 4 byte align  |     |
- *	      +---------------+     |
- *	      | 4 byte temp   |     |
- *	      | for bpf_jit.S |     |
  * R15+160 -> +---------------+     |
  *	      | new backchain |     |
  * R15+152 -> +---------------+     |
@@ -57,17 +45,11 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
  * The stack size used by the BPF program ("BPF stack" above) is passed
  * via "aux->stack_depth".
  */
-#define STK_SPACE_ADD (8 + 8 + 4 + 4 + 160)
+#define STK_SPACE_ADD	(160)
 #define STK_160_UNUSED	(160 - 12 * 8)
 #define STK_OFF		(STK_SPACE_ADD - STK_160_UNUSED)
-#define STK_OFF_TMP	160	/* Offset of tmp buffer on stack */
-#define STK_OFF_HLEN	168	/* Offset of SKB header length on stack */
-#define STK_OFF_SKBP	176	/* Offset of SKB pointer on stack */
 
 #define STK_OFF_R6	(160 - 11 * 8)	/* Offset of r6 on stack */
 #define STK_OFF_TCCNT	(160 - 12 * 8)	/* Offset of tail_call_cnt on stack */
 
-/* Offset to skip condition code check */
-#define OFF_OK		4
-
 #endif /* __ARCH_S390_NET_BPF_JIT_H */

arch/s390/net/bpf_jit_comp.c

@@ -47,23 +47,21 @@ struct bpf_jit {
 
 #define BPF_SIZE_MAX	0xffff	/* Max size for program (16 bit branches) */
 
-#define SEEN_SKB	1	/* skb access */
-#define SEEN_MEM	2	/* use mem[] for temporary storage */
-#define SEEN_RET0	4	/* ret0_ip points to a valid return 0 */
-#define SEEN_LITERAL	8	/* code uses literals */
-#define SEEN_FUNC	16	/* calls C functions */
-#define SEEN_TAIL_CALL	32	/* code uses tail calls */
-#define SEEN_REG_AX	64	/* code uses constant blinding */
-#define SEEN_STACK	(SEEN_FUNC | SEEN_MEM | SEEN_SKB)
+#define SEEN_MEM	(1 << 0)	/* use mem[] for temporary storage */
+#define SEEN_RET0	(1 << 1)	/* ret0_ip points to a valid return 0 */
+#define SEEN_LITERAL	(1 << 2)	/* code uses literals */
+#define SEEN_FUNC	(1 << 3)	/* calls C functions */
+#define SEEN_TAIL_CALL	(1 << 4)	/* code uses tail calls */
+#define SEEN_REG_AX	(1 << 5)	/* code uses constant blinding */
+#define SEEN_STACK	(SEEN_FUNC | SEEN_MEM)
 
 /*
  * s390 registers
  */
 #define REG_W0		(MAX_BPF_JIT_REG + 0)	/* Work register 1 (even) */
 #define REG_W1		(MAX_BPF_JIT_REG + 1)	/* Work register 2 (odd) */
-#define REG_SKB_DATA	(MAX_BPF_JIT_REG + 2)	/* SKB data register */
-#define REG_L		(MAX_BPF_JIT_REG + 3)	/* Literal pool register */
-#define REG_15		(MAX_BPF_JIT_REG + 4)	/* Register 15 */
+#define REG_L		(MAX_BPF_JIT_REG + 2)	/* Literal pool register */
+#define REG_15		(MAX_BPF_JIT_REG + 3)	/* Register 15 */
 #define REG_0		REG_W0			/* Register 0 */
 #define REG_1		REG_W1			/* Register 1 */
 #define REG_2		BPF_REG_1		/* Register 2 */
@@ -88,10 +86,8 @@ static const int reg2hex[] = {
 	[BPF_REG_9]	= 10,
 	/* BPF stack pointer */
 	[BPF_REG_FP]	= 13,
-	/* Register for blinding (shared with REG_SKB_DATA) */
+	/* Register for blinding */
 	[BPF_REG_AX]	= 12,
-	/* SKB data pointer */
-	[REG_SKB_DATA]	= 12,
 	/* Work registers for s390x backend */
 	[REG_W0]	= 0,
 	[REG_W1]	= 1,
@@ -384,27 +380,6 @@ static void save_restore_regs(struct bpf_jit *jit, int op, u32 stack_depth)
 	} while (re <= 15);
 }
 
-/*
- * For SKB access %b1 contains the SKB pointer. For "bpf_jit.S"
- * we store the SKB header length on the stack and the SKB data
- * pointer in REG_SKB_DATA if BPF_REG_AX is not used.
- */
-static void emit_load_skb_data_hlen(struct bpf_jit *jit)
-{
-	/* Header length: llgf %w1,<len>(%b1) */
-	EMIT6_DISP_LH(0xe3000000, 0x0016, REG_W1, REG_0, BPF_REG_1,
-		      offsetof(struct sk_buff, len));
-	/* s %w1,<data_len>(%b1) */
-	EMIT4_DISP(0x5b000000, REG_W1, BPF_REG_1,
-		   offsetof(struct sk_buff, data_len));
-	/* stg %w1,ST_OFF_HLEN(%r0,%r15) */
-	EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15, STK_OFF_HLEN);
-	if (!(jit->seen & SEEN_REG_AX))
-		/* lg %skb_data,data_off(%b1) */
-		EMIT6_DISP_LH(0xe3000000, 0x0004, REG_SKB_DATA, REG_0,
-			      BPF_REG_1, offsetof(struct sk_buff, data));
-}
-
 /*
  * Emit function prologue
  *
@@ -445,12 +420,6 @@ static void bpf_jit_prologue(struct bpf_jit *jit, u32 stack_depth)
 			EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0,
 				      REG_15, 152);
 	}
-	if (jit->seen & SEEN_SKB) {
-		emit_load_skb_data_hlen(jit);
-		/* stg %b1,ST_OFF_SKBP(%r0,%r15) */
-		EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_1, REG_0, REG_15,
-			      STK_OFF_SKBP);
-	}
 }
 
 /*
@@ -483,12 +452,12 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 {
 	struct bpf_insn *insn = &fp->insnsi[i];
 	int jmp_off, last, insn_count = 1;
-	unsigned int func_addr, mask;
 	u32 dst_reg = insn->dst_reg;
 	u32 src_reg = insn->src_reg;
 	u32 *addrs = jit->addrs;
 	s32 imm = insn->imm;
 	s16 off = insn->off;
+	unsigned int mask;
 
 	if (dst_reg == BPF_REG_AX || src_reg == BPF_REG_AX)
 		jit->seen |= SEEN_REG_AX;
@@ -970,13 +939,6 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 		EMIT2(0x0d00, REG_14, REG_W1);
 		/* lgr %b0,%r2: load return value into %b0 */
 		EMIT4(0xb9040000, BPF_REG_0, REG_2);
-		if ((jit->seen & SEEN_SKB) &&
-		    bpf_helper_changes_pkt_data((void *)func)) {
-			/* lg %b1,ST_OFF_SKBP(%r15) */
-			EMIT6_DISP_LH(0xe3000000, 0x0004, BPF_REG_1, REG_0,
-				      REG_15, STK_OFF_SKBP);
-			emit_load_skb_data_hlen(jit);
-		}
 		break;
 	}
 	case BPF_JMP | BPF_TAIL_CALL:
@@ -1176,73 +1138,6 @@ branch_oc:
 		jmp_off = addrs[i + off + 1] - (addrs[i + 1] - 4);
 		EMIT4_PCREL(0xa7040000 | mask << 8, jmp_off);
 		break;
-	/*
-	 * BPF_LD
-	 */
-	case BPF_LD | BPF_ABS | BPF_B: /* b0 = *(u8 *) (skb->data+imm) */
-	case BPF_LD | BPF_IND | BPF_B: /* b0 = *(u8 *) (skb->data+imm+src) */
-		if ((BPF_MODE(insn->code) == BPF_ABS) && (imm >= 0))
-			func_addr = __pa(sk_load_byte_pos);
-		else
-			func_addr = __pa(sk_load_byte);
-		goto call_fn;
-	case BPF_LD | BPF_ABS | BPF_H: /* b0 = *(u16 *) (skb->data+imm) */
-	case BPF_LD | BPF_IND | BPF_H: /* b0 = *(u16 *) (skb->data+imm+src) */
-		if ((BPF_MODE(insn->code) == BPF_ABS) && (imm >= 0))
-			func_addr = __pa(sk_load_half_pos);
-		else
-			func_addr = __pa(sk_load_half);
-		goto call_fn;
-	case BPF_LD | BPF_ABS | BPF_W: /* b0 = *(u32 *) (skb->data+imm) */
-	case BPF_LD | BPF_IND | BPF_W: /* b0 = *(u32 *) (skb->data+imm+src) */
-		if ((BPF_MODE(insn->code) == BPF_ABS) && (imm >= 0))
-			func_addr = __pa(sk_load_word_pos);
-		else
-			func_addr = __pa(sk_load_word);
-		goto call_fn;
-call_fn:
-		jit->seen |= SEEN_SKB | SEEN_RET0 | SEEN_FUNC;
-		REG_SET_SEEN(REG_14); /* Return address of possible func call */
-
-		/*
-		 * Implicit input:
-		 *  BPF_REG_6	 (R7) : skb pointer
-		 *  REG_SKB_DATA (R12): skb data pointer (if no BPF_REG_AX)
-		 *
-		 * Calculated input:
-		 *  BPF_REG_2	 (R3) : offset of byte(s) to fetch in skb
-		 *  BPF_REG_5	 (R6) : return address
-		 *
-		 * Output:
-		 *  BPF_REG_0	 (R14): data read from skb
-		 *
-		 * Scratch registers (BPF_REG_1-5)
-		 */
-
-		/* Call function: llilf %w1,func_addr  */
-		EMIT6_IMM(0xc00f0000, REG_W1, func_addr);
-
-		/* Offset: lgfi %b2,imm */
-		EMIT6_IMM(0xc0010000, BPF_REG_2, imm);
-		if (BPF_MODE(insn->code) == BPF_IND)
-			/* agfr %b2,%src (%src is s32 here) */
-			EMIT4(0xb9180000, BPF_REG_2, src_reg);
-
-		/* Reload REG_SKB_DATA if BPF_REG_AX is used */
-		if (jit->seen & SEEN_REG_AX)
-			/* lg %skb_data,data_off(%b6) */
-			EMIT6_DISP_LH(0xe3000000, 0x0004, REG_SKB_DATA, REG_0,
-				      BPF_REG_6, offsetof(struct sk_buff, data));
-		/* basr %b5,%w1 (%b5 is call saved) */
-		EMIT2(0x0d00, BPF_REG_5, REG_W1);
-
-		/*
-		 * Note: For fast access we jump directly after the
-		 * jnz instruction from bpf_jit.S
-		 */
-		/* jnz <ret0> */
-		EMIT4_PCREL(0xa7740000, jit->ret0_ip - jit->prg);
-		break;
 	default: /* too complex, give up */
 		pr_err("Unknown opcode %02x\n", insn->code);
 		return -1;

arch/sparc/net/Makefile

@@ -1,4 +1,7 @@
 #
 # Arch-specific network modules
 #
-obj-$(CONFIG_BPF_JIT) += bpf_jit_asm_$(BITS).o bpf_jit_comp_$(BITS).o
+obj-$(CONFIG_BPF_JIT) += bpf_jit_comp_$(BITS).o
+ifeq ($(BITS),32)
+obj-$(CONFIG_BPF_JIT) += bpf_jit_asm_32.o
+endif

arch/sparc/net/bpf_jit_64.h

@@ -33,35 +33,6 @@
 #define I5		0x1d
 #define FP		0x1e
 #define I7		0x1f
-
-#define r_SKB		L0
-#define r_HEADLEN	L4
-#define r_SKB_DATA	L5
-#define r_TMP		G1
-#define r_TMP2		G3
-
-/* assembly code in arch/sparc/net/bpf_jit_asm_64.S */
-extern u32 bpf_jit_load_word[];
-extern u32 bpf_jit_load_half[];
-extern u32 bpf_jit_load_byte[];
-extern u32 bpf_jit_load_byte_msh[];
-extern u32 bpf_jit_load_word_positive_offset[];
-extern u32 bpf_jit_load_half_positive_offset[];
-extern u32 bpf_jit_load_byte_positive_offset[];
-extern u32 bpf_jit_load_byte_msh_positive_offset[];
-extern u32 bpf_jit_load_word_negative_offset[];
-extern u32 bpf_jit_load_half_negative_offset[];
-extern u32 bpf_jit_load_byte_negative_offset[];
-extern u32 bpf_jit_load_byte_msh_negative_offset[];
-
-#else
-#define r_RESULT	%o0
-#define r_SKB		%o0
-#define r_OFF		%o1
-#define r_HEADLEN	%l4
-#define r_SKB_DATA	%l5
-#define r_TMP		%g1
-#define r_TMP2		%g3
 #endif
 
 #endif /* _BPF_JIT_H */

arch/sparc/net/bpf_jit_asm_64.S

@@ -1,162 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#include <asm/ptrace.h>
-
-#include "bpf_jit_64.h"
-
-#define SAVE_SZ		176
-#define SCRATCH_OFF	STACK_BIAS + 128
-#define BE_PTR(label)	be,pn %xcc, label
-#define SIGN_EXTEND(reg)	sra reg, 0, reg
-
-#define SKF_MAX_NEG_OFF	(-0x200000) /* SKF_LL_OFF from filter.h */
-
-	.text
-	.globl	bpf_jit_load_word
-bpf_jit_load_word:
-	cmp	r_OFF, 0
-	bl	bpf_slow_path_word_neg
-	 nop
-	.globl	bpf_jit_load_word_positive_offset
-bpf_jit_load_word_positive_offset:
-	sub	r_HEADLEN, r_OFF, r_TMP
-	cmp	r_TMP, 3
-	ble	bpf_slow_path_word
-	 add	r_SKB_DATA, r_OFF, r_TMP
-	andcc	r_TMP, 3, %g0
-	bne	load_word_unaligned
-	 nop
-	retl
-	 ld	[r_TMP], r_RESULT
-load_word_unaligned:
-	ldub	[r_TMP + 0x0], r_OFF
-	ldub	[r_TMP + 0x1], r_TMP2
-	sll	r_OFF, 8, r_OFF
-	or	r_OFF, r_TMP2, r_OFF
-	ldub	[r_TMP + 0x2], r_TMP2
-	sll	r_OFF, 8, r_OFF
-	or	r_OFF, r_TMP2, r_OFF
-	ldub	[r_TMP + 0x3], r_TMP2
-	sll	r_OFF, 8, r_OFF
-	retl
-	 or	r_OFF, r_TMP2, r_RESULT
-
-	.globl	bpf_jit_load_half
-bpf_jit_load_half:
-	cmp	r_OFF, 0
-	bl	bpf_slow_path_half_neg
-	 nop
-	.globl	bpf_jit_load_half_positive_offset
-bpf_jit_load_half_positive_offset:
-	sub	r_HEADLEN, r_OFF, r_TMP
-	cmp	r_TMP, 1
-	ble	bpf_slow_path_half
-	 add	r_SKB_DATA, r_OFF, r_TMP
-	andcc	r_TMP, 1, %g0
-	bne	load_half_unaligned
-	 nop
-	retl
-	 lduh	[r_TMP], r_RESULT
-load_half_unaligned:
-	ldub	[r_TMP + 0x0], r_OFF
-	ldub	[r_TMP + 0x1], r_TMP2
-	sll	r_OFF, 8, r_OFF
-	retl
-	 or	r_OFF, r_TMP2, r_RESULT
-
-	.globl	bpf_jit_load_byte
-bpf_jit_load_byte:
-	cmp	r_OFF, 0
-	bl	bpf_slow_path_byte_neg
-	 nop
-	.globl	bpf_jit_load_byte_positive_offset
-bpf_jit_load_byte_positive_offset:
-	cmp	r_OFF, r_HEADLEN
-	bge	bpf_slow_path_byte
-	 nop
-	retl
-	 ldub	[r_SKB_DATA + r_OFF], r_RESULT
-
-#define bpf_slow_path_common(LEN)	\
-	save	%sp, -SAVE_SZ, %sp;	\
-	mov	%i0, %o0;		\
-	mov	%i1, %o1;		\
-	add	%fp, SCRATCH_OFF, %o2;	\
-	call	skb_copy_bits;		\
-	 mov	(LEN), %o3;		\
-	cmp	%o0, 0;			\
-	restore;
-
-bpf_slow_path_word:
-	bpf_slow_path_common(4)
-	bl	bpf_error
-	 ld	[%sp + SCRATCH_OFF], r_RESULT
-	retl
-	 nop
-bpf_slow_path_half:
-	bpf_slow_path_common(2)
-	bl	bpf_error
-	 lduh	[%sp + SCRATCH_OFF], r_RESULT
-	retl
-	 nop
-bpf_slow_path_byte:
-	bpf_slow_path_common(1)
-	bl	bpf_error
-	 ldub	[%sp + SCRATCH_OFF], r_RESULT
-	retl
-	 nop
-
-#define bpf_negative_common(LEN)			\
-	save	%sp, -SAVE_SZ, %sp;			\
-	mov	%i0, %o0;				\
-	mov	%i1, %o1;				\
-	SIGN_EXTEND(%o1);				\
-	call	bpf_internal_load_pointer_neg_helper;	\
-	 mov	(LEN), %o2;				\
-	mov	%o0, r_TMP;				\
-	cmp	%o0, 0;					\
-	BE_PTR(bpf_error);				\
-	 restore;
-
-bpf_slow_path_word_neg:
-	sethi	%hi(SKF_MAX_NEG_OFF), r_TMP
-	cmp	r_OFF, r_TMP
-	bl	bpf_error
-	 nop
-	.globl	bpf_jit_load_word_negative_offset
-bpf_jit_load_word_negative_offset:
-	bpf_negative_common(4)
-	andcc	r_TMP, 3, %g0
-	bne	load_word_unaligned
-	 nop
-	retl
-	 ld	[r_TMP], r_RESULT
-
-bpf_slow_path_half_neg:
-	sethi	%hi(SKF_MAX_NEG_OFF), r_TMP
-	cmp	r_OFF, r_TMP
-	bl	bpf_error
-	 nop
-	.globl	bpf_jit_load_half_negative_offset
-bpf_jit_load_half_negative_offset:
-	bpf_negative_common(2)
-	andcc	r_TMP, 1, %g0
-	bne	load_half_unaligned
-	 nop
-	retl
-	 lduh	[r_TMP], r_RESULT
-
-bpf_slow_path_byte_neg:
-	sethi	%hi(SKF_MAX_NEG_OFF), r_TMP
-	cmp	r_OFF, r_TMP
-	bl	bpf_error
-	 nop
-	.globl	bpf_jit_load_byte_negative_offset
-bpf_jit_load_byte_negative_offset:
-	bpf_negative_common(1)
-	retl
-	 ldub	[r_TMP], r_RESULT
-
-bpf_error:
-	/* Make the JIT program itself return zero. */
-	ret
-	restore	%g0, %g0, %o0

arch/sparc/net/bpf_jit_comp_64.c

@@ -48,10 +48,6 @@ static void bpf_flush_icache(void *start_, void *end_)
 	}
 }
 
-#define SEEN_DATAREF 1 /* might call external helpers */
-#define SEEN_XREG    2 /* ebx is used */
-#define SEEN_MEM     4 /* use mem[] for temporary storage */
-
 #define S13(X)		((X) & 0x1fff)
 #define S5(X)		((X) & 0x1f)
 #define IMMED		0x00002000
@@ -198,7 +194,6 @@ struct jit_ctx {
 	bool 			tmp_1_used;
 	bool 			tmp_2_used;
 	bool 			tmp_3_used;
-	bool			saw_ld_abs_ind;
 	bool			saw_frame_pointer;
 	bool			saw_call;
 	bool			saw_tail_call;
@@ -207,9 +202,7 @@ struct jit_ctx {
 
 #define TMP_REG_1	(MAX_BPF_JIT_REG + 0)
 #define TMP_REG_2	(MAX_BPF_JIT_REG + 1)
-#define SKB_HLEN_REG	(MAX_BPF_JIT_REG + 2)
-#define SKB_DATA_REG	(MAX_BPF_JIT_REG + 3)
-#define TMP_REG_3	(MAX_BPF_JIT_REG + 4)
+#define TMP_REG_3	(MAX_BPF_JIT_REG + 2)
 
 /* Map BPF registers to SPARC registers */
 static const int bpf2sparc[] = {
@@ -238,9 +231,6 @@ static const int bpf2sparc[] = {
 	[TMP_REG_1] = G1,
 	[TMP_REG_2] = G2,
 	[TMP_REG_3] = G3,
-
-	[SKB_HLEN_REG] = L4,
-	[SKB_DATA_REG] = L5,
 };
 
 static void emit(const u32 insn, struct jit_ctx *ctx)
@@ -800,25 +790,6 @@ static int emit_compare_and_branch(const u8 code, const u8 dst, u8 src,
 	return 0;
 }
 
-static void load_skb_regs(struct jit_ctx *ctx, u8 r_skb)
-{
-	const u8 r_headlen = bpf2sparc[SKB_HLEN_REG];
-	const u8 r_data = bpf2sparc[SKB_DATA_REG];
-	const u8 r_tmp = bpf2sparc[TMP_REG_1];
-	unsigned int off;
-
-	off = offsetof(struct sk_buff, len);
-	emit(LD32I | RS1(r_skb) | S13(off) | RD(r_headlen), ctx);
-
-	off = offsetof(struct sk_buff, data_len);
-	emit(LD32I | RS1(r_skb) | S13(off) | RD(r_tmp), ctx);
-
-	emit(SUB | RS1(r_headlen) | RS2(r_tmp) | RD(r_headlen), ctx);
-
-	off = offsetof(struct sk_buff, data);
-	emit(LDPTRI | RS1(r_skb) | S13(off) | RD(r_data), ctx);
-}
-
 /* Just skip the save instruction and the ctx register move.  */
 #define BPF_TAILCALL_PROLOGUE_SKIP	16
 #define BPF_TAILCALL_CNT_SP_OFF		(STACK_BIAS + 128)
@@ -857,9 +828,6 @@ static void build_prologue(struct jit_ctx *ctx)
 
 	emit_reg_move(I0, O0, ctx);
 	/* If you add anything here, adjust BPF_TAILCALL_PROLOGUE_SKIP above. */
-
-	if (ctx->saw_ld_abs_ind)
-		load_skb_regs(ctx, bpf2sparc[BPF_REG_1]);
 }
 
 static void build_epilogue(struct jit_ctx *ctx)
@@ -1225,16 +1193,11 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		u8 *func = ((u8 *)__bpf_call_base) + imm;
 
 		ctx->saw_call = true;
-		if (ctx->saw_ld_abs_ind && bpf_helper_changes_pkt_data(func))
-			emit_reg_move(bpf2sparc[BPF_REG_1], L7, ctx);
 
 		emit_call((u32 *)func, ctx);
 		emit_nop(ctx);
 
 		emit_reg_move(O0, bpf2sparc[BPF_REG_0], ctx);
-
-		if (ctx->saw_ld_abs_ind && bpf_helper_changes_pkt_data(func))
-			load_skb_regs(ctx, L7);
 		break;
 	}
 
@@ -1412,43 +1375,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		emit_nop(ctx);
 		break;
 	}
-#define CHOOSE_LOAD_FUNC(K, func) \
-		((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
-
-	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */
-	case BPF_LD | BPF_ABS | BPF_W:
-		func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_word);
-		goto common_load;
-	case BPF_LD | BPF_ABS | BPF_H:
-		func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_half);
-		goto common_load;
-	case BPF_LD | BPF_ABS | BPF_B:
-		func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_byte);
-		goto common_load;
-	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + src + imm)) */
-	case BPF_LD | BPF_IND | BPF_W:
-		func = bpf_jit_load_word;
-		goto common_load;
-	case BPF_LD | BPF_IND | BPF_H:
-		func = bpf_jit_load_half;
-		goto common_load;
-
-	case BPF_LD | BPF_IND | BPF_B:
-		func = bpf_jit_load_byte;
-	common_load:
-		ctx->saw_ld_abs_ind = true;
-
-		emit_reg_move(bpf2sparc[BPF_REG_6], O0, ctx);
-		emit_loadimm(imm, O1, ctx);
-
-		if (BPF_MODE(code) == BPF_IND)
-			emit_alu(ADD, src, O1, ctx);
-
-		emit_call(func, ctx);
-		emit_alu_K(SRA, O1, 0, ctx);
-
-		emit_reg_move(O0, bpf2sparc[BPF_REG_0], ctx);
-		break;
 
 	default:
 		pr_err_once("unknown opcode %02x\n", code);
@@ -1583,12 +1509,11 @@ skip_init_ctx:
 		build_epilogue(&ctx);
 
 		if (bpf_jit_enable > 1)
-			pr_info("Pass %d: shrink = %d, seen = [%c%c%c%c%c%c%c]\n", pass,
+			pr_info("Pass %d: shrink = %d, seen = [%c%c%c%c%c%c]\n", pass,
 				image_size - (ctx.idx * 4),
 				ctx.tmp_1_used ? '1' : ' ',
 				ctx.tmp_2_used ? '2' : ' ',
 				ctx.tmp_3_used ? '3' : ' ',
-				ctx.saw_ld_abs_ind ? 'L' : ' ',
 				ctx.saw_frame_pointer ? 'F' : ' ',
 				ctx.saw_call ? 'C' : ' ',
 				ctx.saw_tail_call ? 'T' : ' ');

arch/x86/net/Makefile

@@ -5,6 +5,5 @@
 ifeq ($(CONFIG_X86_32),y)
         obj-$(CONFIG_BPF_JIT) += bpf_jit_comp32.o
 else
-        OBJECT_FILES_NON_STANDARD_bpf_jit.o += y
-        obj-$(CONFIG_BPF_JIT) += bpf_jit.o bpf_jit_comp.o
+        obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o
 endif

arch/x86/net/bpf_jit.S

@@ -1,154 +0,0 @@
-/* bpf_jit.S : BPF JIT helper functions
- *
- * Copyright (C) 2011 Eric Dumazet (eric.dumazet@gmail.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-#include <linux/linkage.h>
-#include <asm/frame.h>
-
-/*
- * Calling convention :
- * rbx : skb pointer (callee saved)
- * esi : offset of byte(s) to fetch in skb (can be scratched)
- * r10 : copy of skb->data
- * r9d : hlen = skb->len - skb->data_len
- */
-#define SKBDATA	%r10
-#define SKF_MAX_NEG_OFF    $(-0x200000) /* SKF_LL_OFF from filter.h */
-
-#define FUNC(name) \
-	.globl name; \
-	.type name, @function; \
-	name:
-
-FUNC(sk_load_word)
-	test	%esi,%esi
-	js	bpf_slow_path_word_neg
-
-FUNC(sk_load_word_positive_offset)
-	mov	%r9d,%eax		# hlen
-	sub	%esi,%eax		# hlen - offset
-	cmp	$3,%eax
-	jle	bpf_slow_path_word
-	mov     (SKBDATA,%rsi),%eax
-	bswap   %eax  			/* ntohl() */
-	ret
-
-FUNC(sk_load_half)
-	test	%esi,%esi
-	js	bpf_slow_path_half_neg
-
-FUNC(sk_load_half_positive_offset)
-	mov	%r9d,%eax
-	sub	%esi,%eax		#	hlen - offset
-	cmp	$1,%eax
-	jle	bpf_slow_path_half
-	movzwl	(SKBDATA,%rsi),%eax
-	rol	$8,%ax			# ntohs()
-	ret
-
-FUNC(sk_load_byte)
-	test	%esi,%esi
-	js	bpf_slow_path_byte_neg
-
-FUNC(sk_load_byte_positive_offset)
-	cmp	%esi,%r9d   /* if (offset >= hlen) goto bpf_slow_path_byte */
-	jle	bpf_slow_path_byte
-	movzbl	(SKBDATA,%rsi),%eax
-	ret
-
-/* rsi contains offset and can be scratched */
-#define bpf_slow_path_common(LEN)		\
-	lea	32(%rbp), %rdx;\
-	FRAME_BEGIN;				\
-	mov	%rbx, %rdi; /* arg1 == skb */	\
-	push	%r9;				\
-	push	SKBDATA;			\
-/* rsi already has offset */			\
-	mov	$LEN,%ecx;	/* len */	\
-	call	skb_copy_bits;			\
-	test    %eax,%eax;			\
-	pop	SKBDATA;			\
-	pop	%r9;				\
-	FRAME_END
-
-
-bpf_slow_path_word:
-	bpf_slow_path_common(4)
-	js	bpf_error
-	mov	32(%rbp),%eax
-	bswap	%eax
-	ret
-
-bpf_slow_path_half:
-	bpf_slow_path_common(2)
-	js	bpf_error
-	mov	32(%rbp),%ax
-	rol	$8,%ax
-	movzwl	%ax,%eax
-	ret
-
-bpf_slow_path_byte:
-	bpf_slow_path_common(1)
-	js	bpf_error
-	movzbl	32(%rbp),%eax
-	ret
-
-#define sk_negative_common(SIZE)				\
-	FRAME_BEGIN;						\
-	mov	%rbx, %rdi; /* arg1 == skb */			\
-	push	%r9;						\
-	push	SKBDATA;					\
-/* rsi already has offset */					\
-	mov	$SIZE,%edx;	/* size */			\
-	call	bpf_internal_load_pointer_neg_helper;		\
-	test	%rax,%rax;					\
-	pop	SKBDATA;					\
-	pop	%r9;						\
-	FRAME_END;						\
-	jz	bpf_error
-
-bpf_slow_path_word_neg:
-	cmp	SKF_MAX_NEG_OFF, %esi	/* test range */
-	jl	bpf_error	/* offset lower -> error  */
-
-FUNC(sk_load_word_negative_offset)
-	sk_negative_common(4)
-	mov	(%rax), %eax
-	bswap	%eax
-	ret
-
-bpf_slow_path_half_neg:
-	cmp	SKF_MAX_NEG_OFF, %esi
-	jl	bpf_error
-
-FUNC(sk_load_half_negative_offset)
-	sk_negative_common(2)
-	mov	(%rax),%ax
-	rol	$8,%ax
-	movzwl	%ax,%eax
-	ret
-
-bpf_slow_path_byte_neg:
-	cmp	SKF_MAX_NEG_OFF, %esi
-	jl	bpf_error
-
-FUNC(sk_load_byte_negative_offset)
-	sk_negative_common(1)
-	movzbl	(%rax), %eax
-	ret
-
-bpf_error:
-# force a return 0 from jit handler
-	xor	%eax,%eax
-	mov	(%rbp),%rbx
-	mov	8(%rbp),%r13
-	mov	16(%rbp),%r14
-	mov	24(%rbp),%r15
-	add	$40, %rbp
-	leaveq
-	ret

arch/x86/net/bpf_jit_comp.c

@@ -17,15 +17,6 @@
 #include <asm/set_memory.h>
 #include <asm/nospec-branch.h>
 
-/*
- * Assembly code in arch/x86/net/bpf_jit.S
- */
-extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
-extern u8 sk_load_word_positive_offset[], sk_load_half_positive_offset[];
-extern u8 sk_load_byte_positive_offset[];
-extern u8 sk_load_word_negative_offset[], sk_load_half_negative_offset[];
-extern u8 sk_load_byte_negative_offset[];
-
 static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 {
 	if (len == 1)
@@ -107,9 +98,6 @@ static int bpf_size_to_x86_bytes(int bpf_size)
 #define X86_JLE 0x7E
 #define X86_JG  0x7F
 
-#define CHOOSE_LOAD_FUNC(K, func) \
-	((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
-
 /* Pick a register outside of BPF range for JIT internal work */
 #define AUX_REG (MAX_BPF_JIT_REG + 1)
 
@@ -120,8 +108,8 @@ static int bpf_size_to_x86_bytes(int bpf_size)
  * register in load/store instructions, it always needs an
  * extra byte of encoding and is callee saved.
  *
- * R9  caches skb->len - skb->data_len
- * R10 caches skb->data, and used for blinding (if enabled)
+ * Also x86-64 register R9 is unused. x86-64 register R10 is
+ * used for blinding (if enabled).
  */
 static const int reg2hex[] = {
 	[BPF_REG_0] = 0,  /* RAX */
@@ -196,19 +184,15 @@ static void jit_fill_hole(void *area, unsigned int size)
 
 struct jit_context {
 	int cleanup_addr; /* Epilogue code offset */
-	bool seen_ld_abs;
-	bool seen_ax_reg;
 };
 
 /* Maximum number of bytes emitted while JITing one eBPF insn */
 #define BPF_MAX_INSN_SIZE	128
 #define BPF_INSN_SAFETY		64
 
-#define AUX_STACK_SPACE \
-	(32 /* Space for RBX, R13, R14, R15 */ + \
-	  8 /* Space for skb_copy_bits() buffer */)
+#define AUX_STACK_SPACE		40 /* Space for RBX, R13, R14, R15, tailcnt */
 
-#define PROLOGUE_SIZE 37
+#define PROLOGUE_SIZE		37
 
 /*
  * Emit x86-64 prologue code for BPF program and check its size.
@@ -232,20 +216,8 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
 	/* sub rbp, AUX_STACK_SPACE */
 	EMIT4(0x48, 0x83, 0xED, AUX_STACK_SPACE);
 
-	/* All classic BPF filters use R6(rbx) save it */
-
 	/* mov qword ptr [rbp+0],rbx */
 	EMIT4(0x48, 0x89, 0x5D, 0);
-
-	/*
-	 * bpf_convert_filter() maps classic BPF register X to R7 and uses R8
-	 * as temporary, so all tcpdump filters need to spill/fill R7(R13) and
-	 * R8(R14). R9(R15) spill could be made conditional, but there is only
-	 * one 'bpf_error' return path out of helper functions inside bpf_jit.S
-	 * The overhead of extra spill is negligible for any filter other
-	 * than synthetic ones. Therefore not worth adding complexity.
-	 */
-
 	/* mov qword ptr [rbp+8],r13 */
 	EMIT4(0x4C, 0x89, 0x6D, 8);
 	/* mov qword ptr [rbp+16],r14 */
@@ -353,27 +325,6 @@ static void emit_bpf_tail_call(u8 **pprog)
 	*pprog = prog;
 }
 
-
-static void emit_load_skb_data_hlen(u8 **pprog)
-{
-	u8 *prog = *pprog;
-	int cnt = 0;
-
-	/*
-	 * r9d = skb->len - skb->data_len (headlen)
-	 * r10 = skb->data
-	 */
-	/* mov %r9d, off32(%rdi) */
-	EMIT3_off32(0x44, 0x8b, 0x8f, offsetof(struct sk_buff, len));
-
-	/* sub %r9d, off32(%rdi) */
-	EMIT3_off32(0x44, 0x2b, 0x8f, offsetof(struct sk_buff, data_len));
-
-	/* mov %r10, off32(%rdi) */
-	EMIT3_off32(0x4c, 0x8b, 0x97, offsetof(struct sk_buff, data));
-	*pprog = prog;
-}
-
 static void emit_mov_imm32(u8 **pprog, bool sign_propagate,
 			   u32 dst_reg, const u32 imm32)
 {
@@ -462,8 +413,6 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 {
 	struct bpf_insn *insn = bpf_prog->insnsi;
 	int insn_cnt = bpf_prog->len;
-	bool seen_ld_abs = ctx->seen_ld_abs | (oldproglen == 0);
-	bool seen_ax_reg = ctx->seen_ax_reg | (oldproglen == 0);
 	bool seen_exit = false;
 	u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
 	int i, cnt = 0;
@@ -473,9 +422,6 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 	emit_prologue(&prog, bpf_prog->aux->stack_depth,
 		      bpf_prog_was_classic(bpf_prog));
 
-	if (seen_ld_abs)
-		emit_load_skb_data_hlen(&prog);
-
 	for (i = 0; i < insn_cnt; i++, insn++) {
 		const s32 imm32 = insn->imm;
 		u32 dst_reg = insn->dst_reg;
@@ -483,13 +429,9 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		u8 b2 = 0, b3 = 0;
 		s64 jmp_offset;
 		u8 jmp_cond;
-		bool reload_skb_data;
 		int ilen;
 		u8 *func;
 
-		if (dst_reg == BPF_REG_AX || src_reg == BPF_REG_AX)
-			ctx->seen_ax_reg = seen_ax_reg = true;
-
 		switch (insn->code) {
 			/* ALU */
 		case BPF_ALU | BPF_ADD | BPF_X:
@@ -916,36 +858,12 @@ xadd:			if (is_imm8(insn->off))
 		case BPF_JMP | BPF_CALL:
 			func = (u8 *) __bpf_call_base + imm32;
 			jmp_offset = func - (image + addrs[i]);
-			if (seen_ld_abs) {
-				reload_skb_data = bpf_helper_changes_pkt_data(func);
-				if (reload_skb_data) {
-					EMIT1(0x57); /* push %rdi */
-					jmp_offset += 22; /* pop, mov, sub, mov */
-				} else {
-					EMIT2(0x41, 0x52); /* push %r10 */
-					EMIT2(0x41, 0x51); /* push %r9 */
-					/*
-					 * We need to adjust jmp offset, since
-					 * pop %r9, pop %r10 take 4 bytes after call insn
-					 */
-					jmp_offset += 4;
-				}
-			}
 			if (!imm32 || !is_simm32(jmp_offset)) {
 				pr_err("unsupported BPF func %d addr %p image %p\n",
 				       imm32, func, image);
 				return -EINVAL;
 			}
 			EMIT1_off32(0xE8, jmp_offset);
-			if (seen_ld_abs) {
-				if (reload_skb_data) {
-					EMIT1(0x5F); /* pop %rdi */
-					emit_load_skb_data_hlen(&prog);
-				} else {
-					EMIT2(0x41, 0x59); /* pop %r9 */
-					EMIT2(0x41, 0x5A); /* pop %r10 */
-				}
-			}
 			break;
 
 		case BPF_JMP | BPF_TAIL_CALL:
@@ -1080,60 +998,6 @@ emit_jmp:
 			}
 			break;
 
-		case BPF_LD | BPF_IND | BPF_W:
-			func = sk_load_word;
-			goto common_load;
-		case BPF_LD | BPF_ABS | BPF_W:
-			func = CHOOSE_LOAD_FUNC(imm32, sk_load_word);
-common_load:
-			ctx->seen_ld_abs = seen_ld_abs = true;
-			jmp_offset = func - (image + addrs[i]);
-			if (!func || !is_simm32(jmp_offset)) {
-				pr_err("unsupported BPF func %d addr %p image %p\n",
-				       imm32, func, image);
-				return -EINVAL;
-			}
-			if (BPF_MODE(insn->code) == BPF_ABS) {
-				/* mov %esi, imm32 */
-				EMIT1_off32(0xBE, imm32);
-			} else {
-				/* mov %rsi, src_reg */
-				EMIT_mov(BPF_REG_2, src_reg);
-				if (imm32) {
-					if (is_imm8(imm32))
-						/* add %esi, imm8 */
-						EMIT3(0x83, 0xC6, imm32);
-					else
-						/* add %esi, imm32 */
-						EMIT2_off32(0x81, 0xC6, imm32);
-				}
-			}
-			/*
-			 * skb pointer is in R6 (%rbx), it will be copied into
-			 * %rdi if skb_copy_bits() call is necessary.
-			 * sk_load_* helpers also use %r10 and %r9d.
-			 * See bpf_jit.S
-			 */
-			if (seen_ax_reg)
-				/* r10 = skb->data, mov %r10, off32(%rbx) */
-				EMIT3_off32(0x4c, 0x8b, 0x93,
-					    offsetof(struct sk_buff, data));
-			EMIT1_off32(0xE8, jmp_offset); /* call */
-			break;
-
-		case BPF_LD | BPF_IND | BPF_H:
-			func = sk_load_half;
-			goto common_load;
-		case BPF_LD | BPF_ABS | BPF_H:
-			func = CHOOSE_LOAD_FUNC(imm32, sk_load_half);
-			goto common_load;
-		case BPF_LD | BPF_IND | BPF_B:
-			func = sk_load_byte;
-			goto common_load;
-		case BPF_LD | BPF_ABS | BPF_B:
-			func = CHOOSE_LOAD_FUNC(imm32, sk_load_byte);
-			goto common_load;
-
 		case BPF_JMP | BPF_EXIT:
 			if (seen_exit) {
 				jmp_offset = ctx->cleanup_addr - addrs[i];

arch/x86/net/bpf_jit_comp32.c

@@ -175,19 +175,13 @@ static const u8 bpf2ia32[][2] = {
 #define SCRATCH_SIZE 96
 
 /* Total stack size used in JITed code */
-#define _STACK_SIZE \
-	(stack_depth + \
-	 + SCRATCH_SIZE + \
-	 + 4 /* Extra space for skb_copy_bits buffer */)
+#define _STACK_SIZE	(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) (off)
 
-/* Offset of skb_copy_bits buffer */
-#define SKB_BUFFER STACK_VAR(SCRATCH_SIZE)
-
 /* Encode 'dst_reg' register into IA32 opcode 'byte' */
 static u8 add_1reg(u8 byte, u32 dst_reg)
 {
@@ -2276,134 +2270,6 @@ emit_jmp:
 				return -EFAULT;
 			}
 			break;
-
-		case BPF_LD | BPF_ABS | BPF_W:
-		case BPF_LD | BPF_ABS | BPF_H:
-		case BPF_LD | BPF_ABS | BPF_B:
-		case BPF_LD | BPF_IND | BPF_W:
-		case BPF_LD | BPF_IND | BPF_H:
-		case BPF_LD | BPF_IND | BPF_B:
-		{
-			int size;
-			const u8 *r6 = bpf2ia32[BPF_REG_6];
-
-			/* Setting up first argument */
-			/* mov eax,dword ptr [ebp+off] */
-			EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX),
-			      STACK_VAR(r6[0]));
-
-			/* Setting up second argument */
-			if (BPF_MODE(code) == BPF_ABS) {
-				/* mov %edx, imm32 */
-				EMIT1_off32(0xBA, imm32);
-			} else {
-				if (sstk)
-					/* mov edx,dword ptr [ebp+off] */
-					EMIT3(0x8B, add_2reg(0x40, IA32_EBP,
-							     IA32_EDX),
-					      STACK_VAR(src_lo));
-				else
-					/* mov edx,src_lo */
-					EMIT2(0x8B, add_2reg(0xC0, src_lo,
-							     IA32_EDX));
-				if (imm32) {
-					if (is_imm8(imm32))
-						/* add %edx,imm8 */
-						EMIT3(0x83, 0xC2, imm32);
-					else
-						/* add %edx,imm32 */
-						EMIT2_off32(0x81, 0xC2, imm32);
-				}
-			}
-
-			/* Setting up third argument */
-			switch (BPF_SIZE(code)) {
-			case BPF_W:
-				size = 4;
-				break;
-			case BPF_H:
-				size = 2;
-				break;
-			case BPF_B:
-				size = 1;
-				break;
-			default:
-				return -EINVAL;
-			}
-			/* mov ecx,val */
-			EMIT2(0xB1, size);
-			/* movzx ecx,ecx */
-			EMIT3(0x0F, 0xB6, add_2reg(0xC0, IA32_ECX, IA32_ECX));
-
-			/* mov ebx,ebp */
-			EMIT2(0x8B, add_2reg(0xC0, IA32_EBP, IA32_EBX));
-			/* add %ebx,imm8 */
-			EMIT3(0x83, add_1reg(0xC0, IA32_EBX), SKB_BUFFER);
-			/* push ebx */
-			EMIT1(0x53);
-
-			/* Setting up function pointer to call */
-			/* mov ebx,imm32*/
-			EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EBX),
-				    (unsigned int)bpf_load_pointer);
-
-			EMIT2(0xFF, add_1reg(0xD0, IA32_EBX));
-			/* add %esp,4 */
-			EMIT3(0x83, add_1reg(0xC0, IA32_ESP), 4);
-			/* xor edx,edx */
-			EMIT2(0x33, add_2reg(0xC0, IA32_EDX, IA32_EDX));
-
-			/* mov dword ptr [ebp+off],eax */
-			EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EDX),
-			      STACK_VAR(r0[0]));
-			/* mov dword ptr [ebp+off],edx */
-			EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EDX),
-			      STACK_VAR(r0[1]));
-
-			/*
-			 * Check if return address is NULL or not.
-			 * If NULL then jump to epilogue else continue
-			 * to load the value from retn address
-			 */
-			EMIT3(0x83, add_1reg(0xF8, IA32_EAX), 0);
-			jmp_offset = ctx->cleanup_addr - addrs[i];
-
-			switch (BPF_SIZE(code)) {
-			case BPF_W:
-				jmp_offset += 7;
-				break;
-			case BPF_H:
-				jmp_offset += 10;
-				break;
-			case BPF_B:
-				jmp_offset += 6;
-				break;
-			}
-
-			EMIT2_off32(0x0F, IA32_JE + 0x10, jmp_offset);
-			/* Load value from the address */
-			switch (BPF_SIZE(code)) {
-			case BPF_W:
-				/* mov eax,[eax] */
-				EMIT2(0x8B, 0x0);
-				/* Emit 'bswap eax' */
-				EMIT2(0x0F, add_1reg(0xC8, IA32_EAX));
-				break;
-			case BPF_H:
-				EMIT3(0x0F, 0xB7, 0x0);
-				EMIT1(0x66);
-				EMIT3(0xC1, add_1reg(0xC8, IA32_EAX), 8);
-				break;
-			case BPF_B:
-				EMIT3(0x0F, 0xB6, 0x0);
-				break;
-			}
-
-			/* mov dword ptr [ebp+off],eax */
-			EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EAX),
-			      STACK_VAR(r0[0]));
-			break;
-		}
 		/* STX XADD: lock *(u32 *)(dst + off) += src */
 		case BPF_STX | BPF_XADD | BPF_W:
 		/* STX XADD: lock *(u64 *)(dst + off) += src */

include/linux/bpf.h

@@ -235,6 +235,8 @@ struct bpf_verifier_ops {
 				struct bpf_insn_access_aux *info);
 	int (*gen_prologue)(struct bpf_insn *insn, bool direct_write,
 			    const struct bpf_prog *prog);
+	int (*gen_ld_abs)(const struct bpf_insn *orig,
+			  struct bpf_insn *insn_buf);
 	u32 (*convert_ctx_access)(enum bpf_access_type type,
 				  const struct bpf_insn *src,
 				  struct bpf_insn *dst,
@@ -714,8 +716,6 @@ extern const struct bpf_func_proto bpf_ktime_get_ns_proto;
 extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto;
 extern const struct bpf_func_proto bpf_get_current_uid_gid_proto;
 extern const struct bpf_func_proto bpf_get_current_comm_proto;
-extern const struct bpf_func_proto bpf_skb_vlan_push_proto;
-extern const struct bpf_func_proto bpf_skb_vlan_pop_proto;
 extern const struct bpf_func_proto bpf_get_stackid_proto;
 extern const struct bpf_func_proto bpf_get_stack_proto;
 extern const struct bpf_func_proto bpf_sock_map_update_proto;

include/linux/filter.h

@@ -47,7 +47,9 @@ struct xdp_buff;
 /* Additional register mappings for converted user programs. */
 #define BPF_REG_A	BPF_REG_0
 #define BPF_REG_X	BPF_REG_7
-#define BPF_REG_TMP	BPF_REG_8
+#define BPF_REG_TMP	BPF_REG_2	/* scratch reg */
+#define BPF_REG_D	BPF_REG_8	/* data, callee-saved */
+#define BPF_REG_H	BPF_REG_9	/* hlen, callee-saved */
 
 /* Kernel hidden auxiliary/helper register for hardening step.
  * Only used by eBPF JITs. It's nothing more than a temporary

include/uapi/linux/bpf.h

@@ -1802,6 +1802,30 @@ union bpf_attr {
  * 	Return
  * 		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)
+ * 	Description
+ * 		This helper is similar to **bpf_skb_load_bytes**\ () in that
+ * 		it provides an easy way to load *len* bytes from *offset*
+ * 		from the packet associated to *skb*, into the buffer pointed
+ * 		by *to*. The difference to **bpf_skb_load_bytes**\ () is that
+ * 		a fifth argument *start_header* exists in order to select a
+ * 		base offset to start from. *start_header* can be one of:
+ *
+ * 		**BPF_HDR_START_MAC**
+ * 			Base offset to load data from is *skb*'s mac header.
+ * 		**BPF_HDR_START_NET**
+ * 			Base offset to load data from is *skb*'s network header.
+ *
+ * 		In general, "direct packet access" is the preferred method to
+ * 		access packet data, however, this helper is in particular useful
+ * 		in socket filters where *skb*\ **->data** does not always point
+ * 		to the start of the mac header and where "direct packet access"
+ * 		is not available.
+ *
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -1871,7 +1895,8 @@ union bpf_attr {
 	FN(bind),			\
 	FN(xdp_adjust_tail),		\
 	FN(skb_get_xfrm_state),		\
-	FN(get_stack),
+	FN(get_stack),			\
+	FN(skb_load_bytes_relative),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -1932,6 +1957,12 @@ enum bpf_adj_room_mode {
 	BPF_ADJ_ROOM_NET,
 };
 
+/* Mode for BPF_FUNC_skb_load_bytes_relative helper. */
+enum bpf_hdr_start_off {
+	BPF_HDR_START_MAC,
+	BPF_HDR_START_NET,
+};
+
 /* user accessible mirror of in-kernel sk_buff.
  * new fields can only be added to the end of this structure
  */

kernel/bpf/core.c

@@ -634,23 +634,6 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from,
 		*to++ = BPF_JMP_REG(from->code, from->dst_reg, BPF_REG_AX, off);
 		break;
 
-	case BPF_LD | BPF_ABS | BPF_W:
-	case BPF_LD | BPF_ABS | BPF_H:
-	case BPF_LD | BPF_ABS | BPF_B:
-		*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
-		*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
-		*to++ = BPF_LD_IND(from->code, BPF_REG_AX, 0);
-		break;
-
-	case BPF_LD | BPF_IND | BPF_W:
-	case BPF_LD | BPF_IND | BPF_H:
-	case BPF_LD | BPF_IND | BPF_B:
-		*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
-		*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
-		*to++ = BPF_ALU32_REG(BPF_ADD, BPF_REG_AX, from->src_reg);
-		*to++ = BPF_LD_IND(from->code, BPF_REG_AX, 0);
-		break;
-
 	case BPF_LD | BPF_IMM | BPF_DW:
 		*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[1].imm);
 		*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
@@ -891,14 +874,7 @@ EXPORT_SYMBOL_GPL(__bpf_call_base);
 	INSN_3(LDX, MEM, W),			\
 	INSN_3(LDX, MEM, DW),			\
 	/*   Immediate based. */		\
-	INSN_3(LD, IMM, DW),			\
-	/*   Misc (old cBPF carry-over). */	\
-	INSN_3(LD, ABS, B),			\
-	INSN_3(LD, ABS, H),			\
-	INSN_3(LD, ABS, W),			\
-	INSN_3(LD, IND, B),			\
-	INSN_3(LD, IND, H),			\
-	INSN_3(LD, IND, W)
+	INSN_3(LD, IMM, DW)
 
 bool bpf_opcode_in_insntable(u8 code)
 {
@@ -908,6 +884,13 @@ bool bpf_opcode_in_insntable(u8 code)
 		[0 ... 255] = false,
 		/* Now overwrite non-defaults ... */
 		BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL),
+		/* UAPI exposed, but rewritten opcodes. cBPF carry-over. */
+		[BPF_LD | BPF_ABS | BPF_B] = true,
+		[BPF_LD | BPF_ABS | BPF_H] = true,
+		[BPF_LD | BPF_ABS | BPF_W] = true,
+		[BPF_LD | BPF_IND | BPF_B] = true,
+		[BPF_LD | BPF_IND | BPF_H] = true,
+		[BPF_LD | BPF_IND | BPF_W] = true,
 	};
 #undef BPF_INSN_3_TBL
 #undef BPF_INSN_2_TBL
@@ -938,8 +921,6 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
 #undef BPF_INSN_3_LBL
 #undef BPF_INSN_2_LBL
 	u32 tail_call_cnt = 0;
-	void *ptr;
-	int off;
 
 #define CONT	 ({ insn++; goto select_insn; })
 #define CONT_JMP ({ insn++; goto select_insn; })
@@ -1266,67 +1247,6 @@ out:
 		atomic64_add((u64) SRC, (atomic64_t *)(unsigned long)
 			     (DST + insn->off));
 		CONT;
-	LD_ABS_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + imm32)) */
-		off = IMM;
-load_word:
-		/* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are only
-		 * appearing in the programs where ctx == skb
-		 * (see may_access_skb() in the verifier). All programs
-		 * keep 'ctx' in regs[BPF_REG_CTX] == BPF_R6,
-		 * bpf_convert_filter() saves it in BPF_R6, internal BPF
-		 * verifier will check that BPF_R6 == ctx.
-		 *
-		 * BPF_ABS and BPF_IND are wrappers of function calls,
-		 * so they scratch BPF_R1-BPF_R5 registers, preserve
-		 * BPF_R6-BPF_R9, and store return value into BPF_R0.
-		 *
-		 * Implicit input:
-		 *   ctx == skb == BPF_R6 == CTX
-		 *
-		 * Explicit input:
-		 *   SRC == any register
-		 *   IMM == 32-bit immediate
-		 *
-		 * Output:
-		 *   BPF_R0 - 8/16/32-bit skb data converted to cpu endianness
-		 */
-
-		ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 4, &tmp);
-		if (likely(ptr != NULL)) {
-			BPF_R0 = get_unaligned_be32(ptr);
-			CONT;
-		}
-
-		return 0;
-	LD_ABS_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + imm32)) */
-		off = IMM;
-load_half:
-		ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 2, &tmp);
-		if (likely(ptr != NULL)) {
-			BPF_R0 = get_unaligned_be16(ptr);
-			CONT;
-		}
-
-		return 0;
-	LD_ABS_B: /* BPF_R0 = *(u8 *) (skb->data + imm32) */
-		off = IMM;
-load_byte:
-		ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 1, &tmp);
-		if (likely(ptr != NULL)) {
-			BPF_R0 = *(u8 *)ptr;
-			CONT;
-		}
-
-		return 0;
-	LD_IND_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + src_reg + imm32)) */
-		off = IMM + SRC;
-		goto load_word;
-	LD_IND_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + src_reg + imm32)) */
-		off = IMM + SRC;
-		goto load_half;
-	LD_IND_B: /* BPF_R0 = *(u8 *) (skb->data + src_reg + imm32) */
-		off = IMM + SRC;
-		goto load_byte;
 
 	default_label:
 		/* If we ever reach this, we have a bug somewhere. Die hard here

kernel/bpf/verifier.c

@@ -3884,6 +3884,11 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 		return -EINVAL;
 	}
 
+	if (!env->ops->gen_ld_abs) {
+		verbose(env, "bpf verifier is misconfigured\n");
+		return -EINVAL;
+	}
+
 	if (env->subprog_cnt) {
 		/* when program has LD_ABS insn JITs and interpreter assume
 		 * that r1 == ctx == skb which is not the case for callees
@@ -5519,6 +5524,25 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 			continue;
 		}
 
+		if (BPF_CLASS(insn->code) == BPF_LD &&
+		    (BPF_MODE(insn->code) == BPF_ABS ||
+		     BPF_MODE(insn->code) == BPF_IND)) {
+			cnt = env->ops->gen_ld_abs(insn, insn_buf);
+			if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
+				verbose(env, "bpf verifier is misconfigured\n");
+				return -EINVAL;
+			}
+
+			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+			if (!new_prog)
+				return -ENOMEM;
+
+			delta    += cnt - 1;
+			env->prog = prog = new_prog;
+			insn      = new_prog->insnsi + i + delta;
+			continue;
+		}
+
 		if (insn->code != (BPF_JMP | BPF_CALL))
 			continue;
 		if (insn->src_reg == BPF_PSEUDO_CALL)

lib/test_bpf.c

@@ -386,116 +386,6 @@ static int bpf_fill_ld_abs_get_processor_id(struct bpf_test *self)
 	return 0;
 }
 
-#define PUSH_CNT 68
-/* test: {skb->data[0], vlan_push} x 68 + {skb->data[0], vlan_pop} x 68 */
-static int bpf_fill_ld_abs_vlan_push_pop(struct bpf_test *self)
-{
-	unsigned int len = BPF_MAXINSNS;
-	struct bpf_insn *insn;
-	int i = 0, j, k = 0;
-
-	insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL);
-	if (!insn)
-		return -ENOMEM;
-
-	insn[i++] = BPF_MOV64_REG(R6, R1);
-loop:
-	for (j = 0; j < PUSH_CNT; j++) {
-		insn[i++] = BPF_LD_ABS(BPF_B, 0);
-		insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0x34, len - i - 2);
-		i++;
-		insn[i++] = BPF_MOV64_REG(R1, R6);
-		insn[i++] = BPF_MOV64_IMM(R2, 1);
-		insn[i++] = BPF_MOV64_IMM(R3, 2);
-		insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-					 bpf_skb_vlan_push_proto.func - __bpf_call_base);
-		insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0, len - i - 2);
-		i++;
-	}
-
-	for (j = 0; j < PUSH_CNT; j++) {
-		insn[i++] = BPF_LD_ABS(BPF_B, 0);
-		insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0x34, len - i - 2);
-		i++;
-		insn[i++] = BPF_MOV64_REG(R1, R6);
-		insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-					 bpf_skb_vlan_pop_proto.func - __bpf_call_base);
-		insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0, len - i - 2);
-		i++;
-	}
-	if (++k < 5)
-		goto loop;
-
-	for (; i < len - 1; i++)
-		insn[i] = BPF_ALU32_IMM(BPF_MOV, R0, 0xbef);
-
-	insn[len - 1] = BPF_EXIT_INSN();
-
-	self->u.ptr.insns = insn;
-	self->u.ptr.len = len;
-
-	return 0;
-}
-
-static int bpf_fill_ld_abs_vlan_push_pop2(struct bpf_test *self)
-{
-	struct bpf_insn *insn;
-
-	insn = kmalloc_array(16, sizeof(*insn), GFP_KERNEL);
-	if (!insn)
-		return -ENOMEM;
-
-	/* Due to func address being non-const, we need to
-	 * assemble this here.
-	 */
-	insn[0] = BPF_MOV64_REG(R6, R1);
-	insn[1] = BPF_LD_ABS(BPF_B, 0);
-	insn[2] = BPF_LD_ABS(BPF_H, 0);
-	insn[3] = BPF_LD_ABS(BPF_W, 0);
-	insn[4] = BPF_MOV64_REG(R7, R6);
-	insn[5] = BPF_MOV64_IMM(R6, 0);
-	insn[6] = BPF_MOV64_REG(R1, R7);
-	insn[7] = BPF_MOV64_IMM(R2, 1);
-	insn[8] = BPF_MOV64_IMM(R3, 2);
-	insn[9] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-			       bpf_skb_vlan_push_proto.func - __bpf_call_base);
-	insn[10] = BPF_MOV64_REG(R6, R7);
-	insn[11] = BPF_LD_ABS(BPF_B, 0);
-	insn[12] = BPF_LD_ABS(BPF_H, 0);
-	insn[13] = BPF_LD_ABS(BPF_W, 0);
-	insn[14] = BPF_MOV64_IMM(R0, 42);
-	insn[15] = BPF_EXIT_INSN();
-
-	self->u.ptr.insns = insn;
-	self->u.ptr.len = 16;
-
-	return 0;
-}
-
-static int bpf_fill_jump_around_ld_abs(struct bpf_test *self)
-{
-	unsigned int len = BPF_MAXINSNS;
-	struct bpf_insn *insn;
-	int i = 0;
-
-	insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL);
-	if (!insn)
-		return -ENOMEM;
-
-	insn[i++] = BPF_MOV64_REG(R6, R1);
-	insn[i++] = BPF_LD_ABS(BPF_B, 0);
-	insn[i] = BPF_JMP_IMM(BPF_JEQ, R0, 10, len - i - 2);
-	i++;
-	while (i < len - 1)
-		insn[i++] = BPF_LD_ABS(BPF_B, 1);
-	insn[i] = BPF_EXIT_INSN();
-
-	self->u.ptr.insns = insn;
-	self->u.ptr.len = len;
-
-	return 0;
-}
-
 static int __bpf_fill_stxdw(struct bpf_test *self, int size)
 {
 	unsigned int len = BPF_MAXINSNS;
@@ -1987,40 +1877,6 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, -1 } }
 	},
-	{
-		"INT: DIV + ABS",
-		.u.insns_int = {
-			BPF_ALU64_REG(BPF_MOV, R6, R1),
-			BPF_LD_ABS(BPF_B, 3),
-			BPF_ALU64_IMM(BPF_MOV, R2, 2),
-			BPF_ALU32_REG(BPF_DIV, R0, R2),
-			BPF_ALU64_REG(BPF_MOV, R8, R0),
-			BPF_LD_ABS(BPF_B, 4),
-			BPF_ALU64_REG(BPF_ADD, R8, R0),
-			BPF_LD_IND(BPF_B, R8, -70),
-			BPF_EXIT_INSN(),
-		},
-		INTERNAL,
-		{ 10, 20, 30, 40, 50 },
-		{ { 4, 0 }, { 5, 10 } }
-	},
-	{
-		/* This one doesn't go through verifier, but is just raw insn
-		 * as opposed to cBPF tests from here. Thus div by 0 tests are
-		 * done in test_verifier in BPF kselftests.
-		 */
-		"INT: DIV by -1",
-		.u.insns_int = {
-			BPF_ALU64_REG(BPF_MOV, R6, R1),
-			BPF_ALU64_IMM(BPF_MOV, R7, -1),
-			BPF_LD_ABS(BPF_B, 3),
-			BPF_ALU32_REG(BPF_DIV, R0, R7),
-			BPF_EXIT_INSN(),
-		},
-		INTERNAL,
-		{ 10, 20, 30, 40, 50 },
-		{ { 3, 0 }, { 4, 0 } }
-	},
 	{
 		"check: missing ret",
 		.u.insns = {
@@ -2383,50 +2239,6 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 1 } }
 	},
-	{
-		"nmap reduced",
-		.u.insns_int = {
-			BPF_MOV64_REG(R6, R1),
-			BPF_LD_ABS(BPF_H, 12),
-			BPF_JMP_IMM(BPF_JNE, R0, 0x806, 28),
-			BPF_LD_ABS(BPF_H, 12),
-			BPF_JMP_IMM(BPF_JNE, R0, 0x806, 26),
-			BPF_MOV32_IMM(R0, 18),
-			BPF_STX_MEM(BPF_W, R10, R0, -64),
-			BPF_LDX_MEM(BPF_W, R7, R10, -64),
-			BPF_LD_IND(BPF_W, R7, 14),
-			BPF_STX_MEM(BPF_W, R10, R0, -60),
-			BPF_MOV32_IMM(R0, 280971478),
-			BPF_STX_MEM(BPF_W, R10, R0, -56),
-			BPF_LDX_MEM(BPF_W, R7, R10, -56),
-			BPF_LDX_MEM(BPF_W, R0, R10, -60),
-			BPF_ALU32_REG(BPF_SUB, R0, R7),
-			BPF_JMP_IMM(BPF_JNE, R0, 0, 15),
-			BPF_LD_ABS(BPF_H, 12),
-			BPF_JMP_IMM(BPF_JNE, R0, 0x806, 13),
-			BPF_MOV32_IMM(R0, 22),
-			BPF_STX_MEM(BPF_W, R10, R0, -56),
-			BPF_LDX_MEM(BPF_W, R7, R10, -56),
-			BPF_LD_IND(BPF_H, R7, 14),
-			BPF_STX_MEM(BPF_W, R10, R0, -52),
-			BPF_MOV32_IMM(R0, 17366),
-			BPF_STX_MEM(BPF_W, R10, R0, -48),
-			BPF_LDX_MEM(BPF_W, R7, R10, -48),
-			BPF_LDX_MEM(BPF_W, R0, R10, -52),
-			BPF_ALU32_REG(BPF_SUB, R0, R7),
-			BPF_JMP_IMM(BPF_JNE, R0, 0, 2),
-			BPF_MOV32_IMM(R0, 256),
-			BPF_EXIT_INSN(),
-			BPF_MOV32_IMM(R0, 0),
-			BPF_EXIT_INSN(),
-		},
-		INTERNAL,
-		{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0x06, 0, 0,
-		  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-		  0x10, 0xbf, 0x48, 0xd6, 0x43, 0xd6},
-		{ { 38, 256 } },
-		.stack_depth = 64,
-	},
 	/* BPF_ALU | BPF_MOV | BPF_X */
 	{
 		"ALU_MOV_X: dst = 2",
@@ -5485,22 +5297,6 @@ static struct bpf_test tests[] = {
 		{ { 1, 0xbee } },
 		.fill_helper = bpf_fill_ld_abs_get_processor_id,
 	},
-	{
-		"BPF_MAXINSNS: ld_abs+vlan_push/pop",
-		{ },
-		INTERNAL,
-		{ 0x34 },
-		{ { ETH_HLEN, 0xbef } },
-		.fill_helper = bpf_fill_ld_abs_vlan_push_pop,
-	},
-	{
-		"BPF_MAXINSNS: jump around ld_abs",
-		{ },
-		INTERNAL,
-		{ 10, 11 },
-		{ { 2, 10 } },
-		.fill_helper = bpf_fill_jump_around_ld_abs,
-	},
 	/*
 	 * LD_IND / LD_ABS on fragmented SKBs
 	 */
@@ -5682,6 +5478,53 @@ static struct bpf_test tests[] = {
 		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
 		{ {0x40, 0x05 } },
 	},
+	{
+		"LD_IND byte positive offset, all ff",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_B, 0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0xff, [0x3d] = 0xff,  [0x3e] = 0xff, [0x3f] = 0xff },
+		{ {0x40, 0xff } },
+	},
+	{
+		"LD_IND byte positive offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_B, 0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 }, },
+	},
+	{
+		"LD_IND byte negative offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_B, -0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 } },
+	},
+	{
+		"LD_IND byte negative offset, multiple calls",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3b),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_B, SKF_LL_OFF + 1),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_B, SKF_LL_OFF + 2),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_B, SKF_LL_OFF + 3),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_B, SKF_LL_OFF + 4),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0x82 }, },
+	},
 	{
 		"LD_IND halfword positive offset",
 		.u.insns = {
@@ -5730,6 +5573,39 @@ static struct bpf_test tests[] = {
 		},
 		{ {0x40, 0x66cc } },
 	},
+	{
+		"LD_IND halfword positive offset, all ff",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3d),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_H, 0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0xff, [0x3d] = 0xff,  [0x3e] = 0xff, [0x3f] = 0xff },
+		{ {0x40, 0xffff } },
+	},
+	{
+		"LD_IND halfword positive offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_H, 0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 }, },
+	},
+	{
+		"LD_IND halfword negative offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_H, -0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 } },
+	},
 	{
 		"LD_IND word positive offset",
 		.u.insns = {
@@ -5820,6 +5696,39 @@ static struct bpf_test tests[] = {
 		},
 		{ {0x40, 0x66cc77dd } },
 	},
+	{
+		"LD_IND word positive offset, all ff",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3b),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_W, 0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0xff, [0x3d] = 0xff,  [0x3e] = 0xff, [0x3f] = 0xff },
+		{ {0x40, 0xffffffff } },
+	},
+	{
+		"LD_IND word positive offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_W, 0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 }, },
+	},
+	{
+		"LD_IND word negative offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_W, -0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 } },
+	},
 	{
 		"LD_ABS byte",
 		.u.insns = {
@@ -5837,6 +5746,68 @@ static struct bpf_test tests[] = {
 		},
 		{ {0x40, 0xcc } },
 	},
+	{
+		"LD_ABS byte positive offset, all ff",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_B, 0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0xff, [0x3d] = 0xff,  [0x3e] = 0xff, [0x3f] = 0xff },
+		{ {0x40, 0xff } },
+	},
+	{
+		"LD_ABS byte positive offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_B, 0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 }, },
+	},
+	{
+		"LD_ABS byte negative offset, out of bounds load",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_B, -1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_EXPECTED_FAIL,
+		.expected_errcode = -EINVAL,
+	},
+	{
+		"LD_ABS byte negative offset, in bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0x82 }, },
+	},
+	{
+		"LD_ABS byte negative offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 }, },
+	},
+	{
+		"LD_ABS byte negative offset, multiple calls",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3c),
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3d),
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3e),
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0x82 }, },
+	},
 	{
 		"LD_ABS halfword",
 		.u.insns = {
@@ -5871,6 +5842,55 @@ static struct bpf_test tests[] = {
 		},
 		{ {0x40, 0x99ff } },
 	},
+	{
+		"LD_ABS halfword positive offset, all ff",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_H, 0x3e),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0xff, [0x3d] = 0xff,  [0x3e] = 0xff, [0x3f] = 0xff },
+		{ {0x40, 0xffff } },
+	},
+	{
+		"LD_ABS halfword positive offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_H, 0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 }, },
+	},
+	{
+		"LD_ABS halfword negative offset, out of bounds load",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_H, -1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_EXPECTED_FAIL,
+		.expected_errcode = -EINVAL,
+	},
+	{
+		"LD_ABS halfword negative offset, in bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_H, SKF_LL_OFF + 0x3e),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0x1982 }, },
+	},
+	{
+		"LD_ABS halfword negative offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_H, SKF_LL_OFF + 0x3e),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 }, },
+	},
 	{
 		"LD_ABS word",
 		.u.insns = {
@@ -5939,6 +5959,140 @@ static struct bpf_test tests[] = {
 		},
 		{ {0x40, 0x88ee99ff } },
 	},
+	{
+		"LD_ABS word positive offset, all ff",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_W, 0x3c),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0xff, [0x3d] = 0xff,  [0x3e] = 0xff, [0x3f] = 0xff },
+		{ {0x40, 0xffffffff } },
+	},
+	{
+		"LD_ABS word positive offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_W, 0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 }, },
+	},
+	{
+		"LD_ABS word negative offset, out of bounds load",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_W, -1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_EXPECTED_FAIL,
+		.expected_errcode = -EINVAL,
+	},
+	{
+		"LD_ABS word negative offset, in bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_W, SKF_LL_OFF + 0x3c),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0x25051982 }, },
+	},
+	{
+		"LD_ABS word negative offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_W, SKF_LL_OFF + 0x3c),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 }, },
+	},
+	{
+		"LDX_MSH standalone, preserved A",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa),
+			BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3c),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0xffeebbaa }, },
+	},
+	{
+		"LDX_MSH standalone, preserved A 2",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, 0x175e9d63),
+			BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3c),
+			BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3d),
+			BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3e),
+			BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0x175e9d63 }, },
+	},
+	{
+		"LDX_MSH standalone, test result 1",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa),
+			BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3c),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0x14 }, },
+	},
+	{
+		"LDX_MSH standalone, test result 2",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa),
+			BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3e),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0x24 }, },
+	},
+	{
+		"LDX_MSH standalone, negative offset",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa),
+			BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, -1),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0 }, },
+	},
+	{
+		"LDX_MSH standalone, negative offset 2",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa),
+			BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, SKF_LL_OFF + 0x3e),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0x24 }, },
+	},
+	{
+		"LDX_MSH standalone, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa),
+			BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x40),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0 }, },
+	},
 	/*
 	 * verify that the interpreter or JIT correctly sets A and X
 	 * to 0.
@@ -6127,14 +6281,6 @@ static struct bpf_test tests[] = {
 		{},
 		{ {0x1, 0x42 } },
 	},
-	{
-		"LD_ABS with helper changing skb data",
-		{ },
-		INTERNAL,
-		{ 0x34 },
-		{ { ETH_HLEN, 42 } },
-		.fill_helper = bpf_fill_ld_abs_vlan_push_pop2,
-	},
 	/* Checking interpreter vs JIT wrt signed extended imms. */
 	{
 		"JNE signed compare, test 1",

net/core/filter.c

@@ -113,12 +113,12 @@ int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap)
 }
 EXPORT_SYMBOL(sk_filter_trim_cap);
 
-BPF_CALL_1(__skb_get_pay_offset, struct sk_buff *, skb)
+BPF_CALL_1(bpf_skb_get_pay_offset, struct sk_buff *, skb)
 {
 	return skb_get_poff(skb);
 }
 
-BPF_CALL_3(__skb_get_nlattr, struct sk_buff *, skb, u32, a, u32, x)
+BPF_CALL_3(bpf_skb_get_nlattr, struct sk_buff *, skb, u32, a, u32, x)
 {
 	struct nlattr *nla;
 
@@ -138,7 +138,7 @@ BPF_CALL_3(__skb_get_nlattr, struct sk_buff *, skb, u32, a, u32, x)
 	return 0;
 }
 
-BPF_CALL_3(__skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x)
+BPF_CALL_3(bpf_skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x)
 {
 	struct nlattr *nla;
 
@@ -162,13 +162,94 @@ BPF_CALL_3(__skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x)
 	return 0;
 }
 
-BPF_CALL_0(__get_raw_cpu_id)
+BPF_CALL_4(bpf_skb_load_helper_8, const struct sk_buff *, skb, const void *,
+	   data, int, headlen, int, offset)
+{
+	u8 tmp, *ptr;
+	const int len = sizeof(tmp);
+
+	if (offset >= 0) {
+		if (headlen - offset >= len)
+			return *(u8 *)(data + offset);
+		if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
+			return tmp;
+	} else {
+		ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len);
+		if (likely(ptr))
+			return *(u8 *)ptr;
+	}
+
+	return -EFAULT;
+}
+
+BPF_CALL_2(bpf_skb_load_helper_8_no_cache, const struct sk_buff *, skb,
+	   int, offset)
+{
+	return ____bpf_skb_load_helper_8(skb, skb->data, skb->len - skb->data_len,
+					 offset);
+}
+
+BPF_CALL_4(bpf_skb_load_helper_16, const struct sk_buff *, skb, const void *,
+	   data, int, headlen, int, offset)
+{
+	u16 tmp, *ptr;
+	const int len = sizeof(tmp);
+
+	if (offset >= 0) {
+		if (headlen - offset >= len)
+			return get_unaligned_be16(data + offset);
+		if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
+			return be16_to_cpu(tmp);
+	} else {
+		ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len);
+		if (likely(ptr))
+			return get_unaligned_be16(ptr);
+	}
+
+	return -EFAULT;
+}
+
+BPF_CALL_2(bpf_skb_load_helper_16_no_cache, const struct sk_buff *, skb,
+	   int, offset)
+{
+	return ____bpf_skb_load_helper_16(skb, skb->data, skb->len - skb->data_len,
+					  offset);
+}
+
+BPF_CALL_4(bpf_skb_load_helper_32, const struct sk_buff *, skb, const void *,
+	   data, int, headlen, int, offset)
+{
+	u32 tmp, *ptr;
+	const int len = sizeof(tmp);
+
+	if (likely(offset >= 0)) {
+		if (headlen - offset >= len)
+			return get_unaligned_be32(data + offset);
+		if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp)))
+			return be32_to_cpu(tmp);
+	} else {
+		ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len);
+		if (likely(ptr))
+			return get_unaligned_be32(ptr);
+	}
+
+	return -EFAULT;
+}
+
+BPF_CALL_2(bpf_skb_load_helper_32_no_cache, const struct sk_buff *, skb,
+	   int, offset)
+{
+	return ____bpf_skb_load_helper_32(skb, skb->data, skb->len - skb->data_len,
+					  offset);
+}
+
+BPF_CALL_0(bpf_get_raw_cpu_id)
 {
 	return raw_smp_processor_id();
 }
 
 static const struct bpf_func_proto bpf_get_raw_smp_processor_id_proto = {
-	.func		= __get_raw_cpu_id,
+	.func		= bpf_get_raw_cpu_id,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 };
@@ -318,16 +399,16 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
 		/* Emit call(arg1=CTX, arg2=A, arg3=X) */
 		switch (fp->k) {
 		case SKF_AD_OFF + SKF_AD_PAY_OFFSET:
-			*insn = BPF_EMIT_CALL(__skb_get_pay_offset);
+			*insn = BPF_EMIT_CALL(bpf_skb_get_pay_offset);
 			break;
 		case SKF_AD_OFF + SKF_AD_NLATTR:
-			*insn = BPF_EMIT_CALL(__skb_get_nlattr);
+			*insn = BPF_EMIT_CALL(bpf_skb_get_nlattr);
 			break;
 		case SKF_AD_OFF + SKF_AD_NLATTR_NEST:
-			*insn = BPF_EMIT_CALL(__skb_get_nlattr_nest);
+			*insn = BPF_EMIT_CALL(bpf_skb_get_nlattr_nest);
 			break;
 		case SKF_AD_OFF + SKF_AD_CPU:
-			*insn = BPF_EMIT_CALL(__get_raw_cpu_id);
+			*insn = BPF_EMIT_CALL(bpf_get_raw_cpu_id);
 			break;
 		case SKF_AD_OFF + SKF_AD_RANDOM:
 			*insn = BPF_EMIT_CALL(bpf_user_rnd_u32);
@@ -354,26 +435,87 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
 	return true;
 }
 
+static bool convert_bpf_ld_abs(struct sock_filter *fp, struct bpf_insn **insnp)
+{
+	const bool unaligned_ok = IS_BUILTIN(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS);
+	int size = bpf_size_to_bytes(BPF_SIZE(fp->code));
+	bool endian = BPF_SIZE(fp->code) == BPF_H ||
+		      BPF_SIZE(fp->code) == BPF_W;
+	bool indirect = BPF_MODE(fp->code) == BPF_IND;
+	const int ip_align = NET_IP_ALIGN;
+	struct bpf_insn *insn = *insnp;
+	int offset = fp->k;
+
+	if (!indirect &&
+	    ((unaligned_ok && offset >= 0) ||
+	     (!unaligned_ok && offset >= 0 &&
+	      offset + ip_align >= 0 &&
+	      offset + ip_align % size == 0))) {
+		*insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H);
+		*insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset);
+		*insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP, size, 2 + endian);
+		*insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, BPF_REG_D,
+				      offset);
+		if (endian)
+			*insn++ = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, size * 8);
+		*insn++ = BPF_JMP_A(8);
+	}
+
+	*insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX);
+	*insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_D);
+	*insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_H);
+	if (!indirect) {
+		*insn++ = BPF_MOV64_IMM(BPF_REG_ARG4, offset);
+	} else {
+		*insn++ = BPF_MOV64_REG(BPF_REG_ARG4, BPF_REG_X);
+		if (fp->k)
+			*insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG4, offset);
+	}
+
+	switch (BPF_SIZE(fp->code)) {
+	case BPF_B:
+		*insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_8);
+		break;
+	case BPF_H:
+		*insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_16);
+		break;
+	case BPF_W:
+		*insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_32);
+		break;
+	default:
+		return false;
+	}
+
+	*insn++ = BPF_JMP_IMM(BPF_JSGE, BPF_REG_A, 0, 2);
+	*insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A);
+	*insn   = BPF_EXIT_INSN();
+
+	*insnp = insn;
+	return true;
+}
+
 /**
  *	bpf_convert_filter - convert filter program
  *	@prog: the user passed filter program
  *	@len: the length of the user passed filter program
  *	@new_prog: allocated 'struct bpf_prog' or NULL
  *	@new_len: pointer to store length of converted program
+ *	@seen_ld_abs: bool whether we've seen ld_abs/ind
  *
  * Remap 'sock_filter' style classic BPF (cBPF) instruction set to 'bpf_insn'
  * style extended BPF (eBPF).
  * Conversion workflow:
  *
  * 1) First pass for calculating the new program length:
- *   bpf_convert_filter(old_prog, old_len, NULL, &new_len)
+ *   bpf_convert_filter(old_prog, old_len, NULL, &new_len, &seen_ld_abs)
  *
  * 2) 2nd pass to remap in two passes: 1st pass finds new
  *    jump offsets, 2nd pass remapping:
- *   bpf_convert_filter(old_prog, old_len, new_prog, &new_len);
+ *   bpf_convert_filter(old_prog, old_len, new_prog, &new_len, &seen_ld_abs)
  */
 static int bpf_convert_filter(struct sock_filter *prog, int len,
-			      struct bpf_prog *new_prog, int *new_len)
+			      struct bpf_prog *new_prog, int *new_len,
+			      bool *seen_ld_abs)
 {
 	int new_flen = 0, pass = 0, target, i, stack_off;
 	struct bpf_insn *new_insn, *first_insn = NULL;
@@ -412,12 +554,27 @@ do_pass:
 		 * do this ourself. Initial CTX is present in BPF_REG_ARG1.
 		 */
 		*new_insn++ = BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1);
+		if (*seen_ld_abs) {
+			/* For packet access in classic BPF, cache skb->data
+			 * in callee-saved BPF R8 and skb->len - skb->data_len
+			 * (headlen) in BPF R9. Since classic BPF is read-only
+			 * on CTX, we only need to cache it once.
+			 */
+			*new_insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data),
+						  BPF_REG_D, BPF_REG_CTX,
+						  offsetof(struct sk_buff, data));
+			*new_insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_H, BPF_REG_CTX,
+						  offsetof(struct sk_buff, len));
+			*new_insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_TMP, BPF_REG_CTX,
+						  offsetof(struct sk_buff, data_len));
+			*new_insn++ = BPF_ALU32_REG(BPF_SUB, BPF_REG_H, BPF_REG_TMP);
+		}
 	} else {
 		new_insn += 3;
 	}
 
 	for (i = 0; i < len; fp++, i++) {
-		struct bpf_insn tmp_insns[6] = { };
+		struct bpf_insn tmp_insns[32] = { };
 		struct bpf_insn *insn = tmp_insns;
 
 		if (addrs)
@@ -460,6 +617,11 @@ do_pass:
 			    BPF_MODE(fp->code) == BPF_ABS &&
 			    convert_bpf_extensions(fp, &insn))
 				break;
+			if (BPF_CLASS(fp->code) == BPF_LD &&
+			    convert_bpf_ld_abs(fp, &insn)) {
+				*seen_ld_abs = true;
+				break;
+			}
 
 			if (fp->code == (BPF_ALU | BPF_DIV | BPF_X) ||
 			    fp->code == (BPF_ALU | BPF_MOD | BPF_X)) {
@@ -562,21 +724,31 @@ jmp_rest:
 			break;
 
 		/* ldxb 4 * ([14] & 0xf) is remaped into 6 insns. */
-		case BPF_LDX | BPF_MSH | BPF_B:
-			/* tmp = A */
-			*insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_A);
+		case BPF_LDX | BPF_MSH | BPF_B: {
+			struct sock_filter tmp = {
+				.code	= BPF_LD | BPF_ABS | BPF_B,
+				.k	= fp->k,
+			};
+
+			*seen_ld_abs = true;
+
+			/* X = A */
+			*insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A);
 			/* A = BPF_R0 = *(u8 *) (skb->data + K) */
-			*insn++ = BPF_LD_ABS(BPF_B, fp->k);
+			convert_bpf_ld_abs(&tmp, &insn);
+			insn++;
 			/* A &= 0xf */
 			*insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 0xf);
 			/* A <<= 2 */
 			*insn++ = BPF_ALU32_IMM(BPF_LSH, BPF_REG_A, 2);
+			/* tmp = X */
+			*insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_X);
 			/* X = A */
 			*insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A);
 			/* A = tmp */
 			*insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_TMP);
 			break;
-
+		}
 		/* RET_K is remaped into 2 insns. RET_A case doesn't need an
 		 * extra mov as BPF_REG_0 is already mapped into BPF_REG_A.
 		 */
@@ -658,6 +830,8 @@ jmp_rest:
 	if (!new_prog) {
 		/* Only calculating new length. */
 		*new_len = new_insn - first_insn;
+		if (*seen_ld_abs)
+			*new_len += 4; /* Prologue bits. */
 		return 0;
 	}
 
@@ -1019,6 +1193,7 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
 	struct sock_filter *old_prog;
 	struct bpf_prog *old_fp;
 	int err, new_len, old_len = fp->len;
+	bool seen_ld_abs = false;
 
 	/* We are free to overwrite insns et al right here as it
 	 * won't be used at this point in time anymore internally
@@ -1040,7 +1215,8 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
 	}
 
 	/* 1st pass: calculate the new program length. */
-	err = bpf_convert_filter(old_prog, old_len, NULL, &new_len);
+	err = bpf_convert_filter(old_prog, old_len, NULL, &new_len,
+				 &seen_ld_abs);
 	if (err)
 		goto out_err_free;
 
@@ -1059,7 +1235,8 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
 	fp->len = new_len;
 
 	/* 2nd pass: remap sock_filter insns into bpf_insn insns. */
-	err = bpf_convert_filter(old_prog, old_len, fp, &new_len);
+	err = bpf_convert_filter(old_prog, old_len, fp, &new_len,
+				 &seen_ld_abs);
 	if (err)
 		/* 2nd bpf_convert_filter() can fail only if it fails
 		 * to allocate memory, remapping must succeed. Note,
@@ -1507,6 +1684,47 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = {
 	.arg4_type	= ARG_CONST_SIZE,
 };
 
+BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb,
+	   u32, offset, void *, to, u32, len, u32, start_header)
+{
+	u8 *ptr;
+
+	if (unlikely(offset > 0xffff || len > skb_headlen(skb)))
+		goto err_clear;
+
+	switch (start_header) {
+	case BPF_HDR_START_MAC:
+		ptr = skb_mac_header(skb) + offset;
+		break;
+	case BPF_HDR_START_NET:
+		ptr = skb_network_header(skb) + offset;
+		break;
+	default:
+		goto err_clear;
+	}
+
+	if (likely(ptr >= skb_mac_header(skb) &&
+		   ptr + len <= skb_tail_pointer(skb))) {
+		memcpy(to, ptr, len);
+		return 0;
+	}
+
+err_clear:
+	memset(to, 0, len);
+	return -EFAULT;
+}
+
+static const struct bpf_func_proto bpf_skb_load_bytes_relative_proto = {
+	.func		= bpf_skb_load_bytes_relative,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg4_type	= ARG_CONST_SIZE,
+	.arg5_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_2(bpf_skb_pull_data, struct sk_buff *, skb, u32, len)
 {
 	/* Idea is the following: should the needed direct read/write
@@ -2181,7 +2399,7 @@ BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto,
 	return ret;
 }
 
-const struct bpf_func_proto bpf_skb_vlan_push_proto = {
+static const struct bpf_func_proto bpf_skb_vlan_push_proto = {
 	.func           = bpf_skb_vlan_push,
 	.gpl_only       = false,
 	.ret_type       = RET_INTEGER,
@@ -2189,7 +2407,6 @@ const struct bpf_func_proto bpf_skb_vlan_push_proto = {
 	.arg2_type      = ARG_ANYTHING,
 	.arg3_type      = ARG_ANYTHING,
 };
-EXPORT_SYMBOL_GPL(bpf_skb_vlan_push_proto);
 
 BPF_CALL_1(bpf_skb_vlan_pop, struct sk_buff *, skb)
 {
@@ -2203,13 +2420,12 @@ BPF_CALL_1(bpf_skb_vlan_pop, struct sk_buff *, skb)
 	return ret;
 }
 
-const struct bpf_func_proto bpf_skb_vlan_pop_proto = {
+static const struct bpf_func_proto bpf_skb_vlan_pop_proto = {
 	.func           = bpf_skb_vlan_pop,
 	.gpl_only       = false,
 	.ret_type       = RET_INTEGER,
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
-EXPORT_SYMBOL_GPL(bpf_skb_vlan_pop_proto);
 
 static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len)
 {
@@ -3886,6 +4102,8 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	switch (func_id) {
 	case BPF_FUNC_skb_load_bytes:
 		return &bpf_skb_load_bytes_proto;
+	case BPF_FUNC_skb_load_bytes_relative:
+		return &bpf_skb_load_bytes_relative_proto;
 	case BPF_FUNC_get_socket_cookie:
 		return &bpf_get_socket_cookie_proto;
 	case BPF_FUNC_get_socket_uid:
@@ -3903,6 +4121,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skb_store_bytes_proto;
 	case BPF_FUNC_skb_load_bytes:
 		return &bpf_skb_load_bytes_proto;
+	case BPF_FUNC_skb_load_bytes_relative:
+		return &bpf_skb_load_bytes_relative_proto;
 	case BPF_FUNC_skb_pull_data:
 		return &bpf_skb_pull_data_proto;
 	case BPF_FUNC_csum_diff:
@@ -4332,6 +4552,41 @@ static int bpf_unclone_prologue(struct bpf_insn *insn_buf, bool direct_write,
 	return insn - insn_buf;
 }
 
+static int bpf_gen_ld_abs(const struct bpf_insn *orig,
+			  struct bpf_insn *insn_buf)
+{
+	bool indirect = BPF_MODE(orig->code) == BPF_IND;
+	struct bpf_insn *insn = insn_buf;
+
+	/* We're guaranteed here that CTX is in R6. */
+	*insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_CTX);
+	if (!indirect) {
+		*insn++ = BPF_MOV64_IMM(BPF_REG_2, orig->imm);
+	} else {
+		*insn++ = BPF_MOV64_REG(BPF_REG_2, orig->src_reg);
+		if (orig->imm)
+			*insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, orig->imm);
+	}
+
+	switch (BPF_SIZE(orig->code)) {
+	case BPF_B:
+		*insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_8_no_cache);
+		break;
+	case BPF_H:
+		*insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_16_no_cache);
+		break;
+	case BPF_W:
+		*insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_32_no_cache);
+		break;
+	}
+
+	*insn++ = BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 2);
+	*insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_0, BPF_REG_0);
+	*insn++ = BPF_EXIT_INSN();
+
+	return insn - insn_buf;
+}
+
 static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write,
 			       const struct bpf_prog *prog)
 {
@@ -5601,6 +5856,7 @@ const struct bpf_verifier_ops sk_filter_verifier_ops = {
 	.get_func_proto		= sk_filter_func_proto,
 	.is_valid_access	= sk_filter_is_valid_access,
 	.convert_ctx_access	= bpf_convert_ctx_access,
+	.gen_ld_abs		= bpf_gen_ld_abs,
 };
 
 const struct bpf_prog_ops sk_filter_prog_ops = {
@@ -5612,6 +5868,7 @@ const struct bpf_verifier_ops tc_cls_act_verifier_ops = {
 	.is_valid_access	= tc_cls_act_is_valid_access,
 	.convert_ctx_access	= tc_cls_act_convert_ctx_access,
 	.gen_prologue		= tc_cls_act_prologue,
+	.gen_ld_abs		= bpf_gen_ld_abs,
 };
 
 const struct bpf_prog_ops tc_cls_act_prog_ops = {

tools/include/uapi/linux/bpf.h

@@ -1801,6 +1801,30 @@ union bpf_attr {
  * 	Return
  * 		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)
+ * 	Description
+ * 		This helper is similar to **bpf_skb_load_bytes**\ () in that
+ * 		it provides an easy way to load *len* bytes from *offset*
+ * 		from the packet associated to *skb*, into the buffer pointed
+ * 		by *to*. The difference to **bpf_skb_load_bytes**\ () is that
+ * 		a fifth argument *start_header* exists in order to select a
+ * 		base offset to start from. *start_header* can be one of:
+ *
+ * 		**BPF_HDR_START_MAC**
+ * 			Base offset to load data from is *skb*'s mac header.
+ * 		**BPF_HDR_START_NET**
+ * 			Base offset to load data from is *skb*'s network header.
+ *
+ * 		In general, "direct packet access" is the preferred method to
+ * 		access packet data, however, this helper is in particular useful
+ * 		in socket filters where *skb*\ **->data** does not always point
+ * 		to the start of the mac header and where "direct packet access"
+ * 		is not available.
+ *
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -1870,7 +1894,8 @@ union bpf_attr {
 	FN(bind),			\
 	FN(xdp_adjust_tail),		\
 	FN(skb_get_xfrm_state),		\
-	FN(get_stack),
+	FN(get_stack),			\
+	FN(skb_load_bytes_relative),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -1931,6 +1956,12 @@ enum bpf_adj_room_mode {
 	BPF_ADJ_ROOM_NET,
 };
 
+/* Mode for BPF_FUNC_skb_load_bytes_relative helper. */
+enum bpf_hdr_start_off {
+	BPF_HDR_START_MAC,
+	BPF_HDR_START_NET,
+};
+
 /* user accessible mirror of in-kernel sk_buff.
  * new fields can only be added to the end of this structure
  */

tools/testing/selftests/bpf/test_verifier.c

@@ -47,7 +47,7 @@
 # define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
 #endif
 
-#define MAX_INSNS	512
+#define MAX_INSNS	BPF_MAXINSNS
 #define MAX_FIXUPS	8
 #define MAX_NR_MAPS	4
 #define POINTER_VALUE	0xcafe4all
@@ -77,6 +77,8 @@ struct bpf_test {
 	} result, result_unpriv;
 	enum bpf_prog_type prog_type;
 	uint8_t flags;
+	__u8 data[TEST_DATA_LEN];
+	void (*fill_helper)(struct bpf_test *self);
 };
 
 /* Note we want this to be 64 bit aligned so that the end of our array is
@@ -94,6 +96,62 @@ struct other_val {
 	long long bar;
 };
 
+static void bpf_fill_ld_abs_vlan_push_pop(struct bpf_test *self)
+{
+	/* test: {skb->data[0], vlan_push} x 68 + {skb->data[0], vlan_pop} x 68 */
+#define PUSH_CNT 51
+	unsigned int len = BPF_MAXINSNS;
+	struct bpf_insn *insn = self->insns;
+	int i = 0, j, k = 0;
+
+	insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1);
+loop:
+	for (j = 0; j < PUSH_CNT; j++) {
+		insn[i++] = BPF_LD_ABS(BPF_B, 0);
+		insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x34, len - i - 2);
+		i++;
+		insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6);
+		insn[i++] = BPF_MOV64_IMM(BPF_REG_2, 1);
+		insn[i++] = BPF_MOV64_IMM(BPF_REG_3, 2);
+		insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+					 BPF_FUNC_skb_vlan_push),
+		insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 2);
+		i++;
+	}
+
+	for (j = 0; j < PUSH_CNT; j++) {
+		insn[i++] = BPF_LD_ABS(BPF_B, 0);
+		insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x34, len - i - 2);
+		i++;
+		insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6);
+		insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+					 BPF_FUNC_skb_vlan_pop),
+		insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 2);
+		i++;
+	}
+	if (++k < 5)
+		goto loop;
+
+	for (; i < len - 1; i++)
+		insn[i] = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, 0xbef);
+	insn[len - 1] = BPF_EXIT_INSN();
+}
+
+static void bpf_fill_jump_around_ld_abs(struct bpf_test *self)
+{
+	struct bpf_insn *insn = self->insns;
+	unsigned int len = BPF_MAXINSNS;
+	int i = 0;
+
+	insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1);
+	insn[i++] = BPF_LD_ABS(BPF_B, 0);
+	insn[i] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 10, len - i - 2);
+	i++;
+	while (i < len - 1)
+		insn[i++] = BPF_LD_ABS(BPF_B, 1);
+	insn[i] = BPF_EXIT_INSN();
+}
+
 static struct bpf_test tests[] = {
 	{
 		"add+sub+mul",
@@ -11725,6 +11783,197 @@ static struct bpf_test tests[] = {
 		.result = ACCEPT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
+	{
+		"ld_abs: invalid op 1",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_LD_ABS(BPF_DW, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = REJECT,
+		.errstr = "unknown opcode",
+	},
+	{
+		"ld_abs: invalid op 2",
+		.insns = {
+			BPF_MOV32_IMM(BPF_REG_0, 256),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_LD_IND(BPF_DW, BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = REJECT,
+		.errstr = "unknown opcode",
+	},
+	{
+		"ld_abs: nmap reduced",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_LD_ABS(BPF_H, 12),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x806, 28),
+			BPF_LD_ABS(BPF_H, 12),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x806, 26),
+			BPF_MOV32_IMM(BPF_REG_0, 18),
+			BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -64),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -64),
+			BPF_LD_IND(BPF_W, BPF_REG_7, 14),
+			BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -60),
+			BPF_MOV32_IMM(BPF_REG_0, 280971478),
+			BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -56),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -56),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -60),
+			BPF_ALU32_REG(BPF_SUB, BPF_REG_0, BPF_REG_7),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 15),
+			BPF_LD_ABS(BPF_H, 12),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x806, 13),
+			BPF_MOV32_IMM(BPF_REG_0, 22),
+			BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -56),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -56),
+			BPF_LD_IND(BPF_H, BPF_REG_7, 14),
+			BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -52),
+			BPF_MOV32_IMM(BPF_REG_0, 17366),
+			BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -48),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -48),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -52),
+			BPF_ALU32_REG(BPF_SUB, BPF_REG_0, BPF_REG_7),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+			BPF_MOV32_IMM(BPF_REG_0, 256),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.data = {
+			0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0x06, 0,
+			0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+			0x10, 0xbf, 0x48, 0xd6, 0x43, 0xd6,
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 256,
+	},
+	{
+		"ld_abs: div + abs, test 1",
+		.insns = {
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1),
+			BPF_LD_ABS(BPF_B, 3),
+			BPF_ALU64_IMM(BPF_MOV, BPF_REG_2, 2),
+			BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_8, BPF_REG_0),
+			BPF_LD_ABS(BPF_B, 4),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_8, BPF_REG_0),
+			BPF_LD_IND(BPF_B, BPF_REG_8, -70),
+			BPF_EXIT_INSN(),
+		},
+		.data = {
+			10, 20, 30, 40, 50,
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 10,
+	},
+	{
+		"ld_abs: div + abs, test 2",
+		.insns = {
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1),
+			BPF_LD_ABS(BPF_B, 3),
+			BPF_ALU64_IMM(BPF_MOV, BPF_REG_2, 2),
+			BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_8, BPF_REG_0),
+			BPF_LD_ABS(BPF_B, 128),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_8, BPF_REG_0),
+			BPF_LD_IND(BPF_B, BPF_REG_8, -70),
+			BPF_EXIT_INSN(),
+		},
+		.data = {
+			10, 20, 30, 40, 50,
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 0,
+	},
+	{
+		"ld_abs: div + abs, test 3",
+		.insns = {
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_MOV, BPF_REG_7, 0),
+			BPF_LD_ABS(BPF_B, 3),
+			BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_7),
+			BPF_EXIT_INSN(),
+		},
+		.data = {
+			10, 20, 30, 40, 50,
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 0,
+	},
+	{
+		"ld_abs: div + abs, test 4",
+		.insns = {
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_MOV, BPF_REG_7, 0),
+			BPF_LD_ABS(BPF_B, 256),
+			BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_7),
+			BPF_EXIT_INSN(),
+		},
+		.data = {
+			10, 20, 30, 40, 50,
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 0,
+	},
+	{
+		"ld_abs: vlan + abs, test 1",
+		.insns = { },
+		.data = {
+			0x34,
+		},
+		.fill_helper = bpf_fill_ld_abs_vlan_push_pop,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 0xbef,
+	},
+	{
+		"ld_abs: vlan + abs, test 2",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_LD_ABS(BPF_B, 0),
+			BPF_LD_ABS(BPF_H, 0),
+			BPF_LD_ABS(BPF_W, 0),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_6),
+			BPF_MOV64_IMM(BPF_REG_6, 0),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+			BPF_MOV64_IMM(BPF_REG_2, 1),
+			BPF_MOV64_IMM(BPF_REG_3, 2),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_skb_vlan_push),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_7),
+			BPF_LD_ABS(BPF_B, 0),
+			BPF_LD_ABS(BPF_H, 0),
+			BPF_LD_ABS(BPF_W, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 42),
+			BPF_EXIT_INSN(),
+		},
+		.data = {
+			0x34,
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 42,
+	},
+	{
+		"ld_abs: jump around ld_abs",
+		.insns = { },
+		.data = {
+			10, 11,
+		},
+		.fill_helper = bpf_fill_jump_around_ld_abs,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 10,
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
@@ -11828,7 +12077,7 @@ static int create_map_in_map(void)
 	return outer_map_fd;
 }
 
-static char bpf_vlog[32768];
+static char bpf_vlog[UINT_MAX >> 8];
 
 static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
 			  int *map_fds)
@@ -11839,6 +12088,9 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
 	int *fixup_prog = test->fixup_prog;
 	int *fixup_map_in_map = test->fixup_map_in_map;
 
+	if (test->fill_helper)
+		test->fill_helper(test);
+
 	/* Allocating HTs with 1 elem is fine here, since we only test
 	 * for verifier and not do a runtime lookup, so the only thing
 	 * that really matters is value size in this case.
@@ -11888,10 +12140,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 			   int *passes, int *errors)
 {
 	int fd_prog, expected_ret, reject_from_alignment;
+	int prog_len, prog_type = test->prog_type;
 	struct bpf_insn *prog = test->insns;
-	int prog_len = probe_filter_length(prog);
-	char data_in[TEST_DATA_LEN] = {};
-	int prog_type = test->prog_type;
 	int map_fds[MAX_NR_MAPS];
 	const char *expected_err;
 	uint32_t retval;
@@ -11901,6 +12151,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		map_fds[i] = -1;
 
 	do_test_fixup(test, prog, map_fds);
+	prog_len = probe_filter_length(prog);
 
 	fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
 				     prog, prog_len, test->flags & F_LOAD_WITH_STRICT_ALIGNMENT,
@@ -11940,8 +12191,9 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	}
 
 	if (fd_prog >= 0) {
-		err = bpf_prog_test_run(fd_prog, 1, data_in, sizeof(data_in),
-					NULL, NULL, &retval, NULL);
+		err = bpf_prog_test_run(fd_prog, 1, test->data,
+					sizeof(test->data), NULL, NULL,
+					&retval, NULL);
 		if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) {
 			printf("Unexpected bpf_prog_test_run error\n");
 			goto fail_log;