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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2018-01-26

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) A number of extensions to tcp-bpf, from Lawrence.
    - direct R or R/W access to many tcp_sock fields via bpf_sock_ops
    - passing up to 3 arguments to bpf_sock_ops functions
    - tcp_sock field bpf_sock_ops_cb_flags for controlling callbacks
    - optionally calling bpf_sock_ops program when RTO fires
    - optionally calling bpf_sock_ops program when packet is retransmitted
    - optionally calling bpf_sock_ops program when TCP state changes
    - access to tclass and sk_txhash
    - new selftest

2) div/mod exception handling, from Daniel.
    One of the ugly leftovers from the early eBPF days is that div/mod
    operations based on registers have a hard-coded src_reg == 0 test
    in the interpreter as well as in JIT code generators that would
    return from the BPF program with exit code 0. This was basically
    adopted from cBPF interpreter for historical reasons.
    There are multiple reasons why this is very suboptimal and prone
    to bugs. To name one: the return code mapping for such abnormal
    program exit of 0 does not always match with a suitable program
    type's exit code mapping. For example, '0' in tc means action 'ok'
    where the packet gets passed further up the stack, which is just
    undesirable for such cases (e.g. when implementing policy) and
    also does not match with other program types.
    After considering _four_ different ways to address the problem,
    we adapt the same behavior as on some major archs like ARMv8:
    X div 0 results in 0, and X mod 0 results in X. aarch64 and
    aarch32 ISA do not generate any traps or otherwise aborts
    of program execution for unsigned divides.
    Given the options, it seems the most suitable from
    all of them, also since major archs have similar schemes in
    place. Given this is all in the realm of undefined behavior,
    we still have the option to adapt if deemed necessary.

3) sockmap sample refactoring, from John.

4) lpm map get_next_key fixes, from Yonghong.

5) test cleanups, from Alexei and Prashant.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 4 insertions, 102 deletions

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 41e2feb0cf4f..b5030e1a41d8 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -363,15 +363,7 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
 static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
 {
 	const u8 *tmp = bpf2a32[TMP_REG_1];
-	s32 jmp_offset;
 
-	/* checks if divisor is zero or not. If it is, then
-	 * exit directly.
-	 */
-	emit(ARM_CMP_I(rn, 0), ctx);
-	_emit(ARM_COND_EQ, ARM_MOV_I(ARM_R0, 0), ctx);
-	jmp_offset = epilogue_offset(ctx);
-	_emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx);
 #if __LINUX_ARM_ARCH__ == 7
 	if (elf_hwcap & HWCAP_IDIVA) {
 		if (op == BPF_DIV)
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 0775d5ab8ee9..1d4f1da7c58f 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -390,18 +390,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_ALU64 | BPF_DIV | BPF_X:
 	case BPF_ALU | BPF_MOD | BPF_X:
 	case BPF_ALU64 | BPF_MOD | BPF_X:
-	{
-		const u8 r0 = bpf2a64[BPF_REG_0];
-
-		/* if (src == 0) return 0 */
-		jmp_offset = 3; /* skip ahead to else path */
-		check_imm19(jmp_offset);
-		emit(A64_CBNZ(is64, src, jmp_offset), ctx);
-		emit(A64_MOVZ(1, r0, 0, 0), ctx);
-		jmp_offset = epilogue_offset(ctx);
-		check_imm26(jmp_offset);
-		emit(A64_B(jmp_offset), ctx);
-		/* else */
 		switch (BPF_OP(code)) {
 		case BPF_DIV:
 			emit(A64_UDIV(is64, dst, dst, src), ctx);
@@ -413,7 +401,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			break;
 		}
 		break;
-	}
 	case BPF_ALU | BPF_LSH | BPF_X:
 	case BPF_ALU64 | BPF_LSH | BPF_X:
 		emit(A64_LSLV(is64, dst, dst, src), ctx);
diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c
index 4e347030ed2c..3e2798bfea4f 100644
--- a/arch/mips/net/ebpf_jit.c
+++ b/arch/mips/net/ebpf_jit.c
@@ -741,16 +741,11 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 		break;
 	case BPF_ALU | BPF_DIV | BPF_K: /* ALU_IMM */
 	case BPF_ALU | BPF_MOD | BPF_K: /* ALU_IMM */
+		if (insn->imm == 0)
+			return -EINVAL;
 		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
 		if (dst < 0)
 			return dst;
-		if (insn->imm == 0) { /* Div by zero */
-			b_off = b_imm(exit_idx, ctx);
-			if (is_bad_offset(b_off))
-				return -E2BIG;
-			emit_instr(ctx, beq, MIPS_R_ZERO, MIPS_R_ZERO, b_off);
-			emit_instr(ctx, addu, MIPS_R_V0, MIPS_R_ZERO, MIPS_R_ZERO);
-		}
 		td = get_reg_val_type(ctx, this_idx, insn->dst_reg);
 		if (td == REG_64BIT || td == REG_32BIT_ZERO_EX)
 			/* sign extend */
@@ -770,19 +765,13 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 		break;
 	case BPF_ALU64 | BPF_DIV | BPF_K: /* ALU_IMM */
 	case BPF_ALU64 | BPF_MOD | BPF_K: /* ALU_IMM */
+		if (insn->imm == 0)
+			return -EINVAL;
 		dst = ebpf_to_mips_reg(ctx, insn, dst_reg);
 		if (dst < 0)
 			return dst;
-		if (insn->imm == 0) { /* Div by zero */
-			b_off = b_imm(exit_idx, ctx);
-			if (is_bad_offset(b_off))
-				return -E2BIG;
-			emit_instr(ctx, beq, MIPS_R_ZERO, MIPS_R_ZERO, b_off);
-			emit_instr(ctx, addu, MIPS_R_V0, MIPS_R_ZERO, MIPS_R_ZERO);
-		}
 		if (get_reg_val_type(ctx, this_idx, insn->dst_reg) == REG_32BIT)
 			emit_instr(ctx, dinsu, dst, MIPS_R_ZERO, 32, 32);
-
 		if (insn->imm == 1) {
 			/* div by 1 is a nop, mod by 1 is zero */
 			if (bpf_op == BPF_MOD)
@@ -860,11 +849,6 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 			break;
 		case BPF_DIV:
 		case BPF_MOD:
-			b_off = b_imm(exit_idx, ctx);
-			if (is_bad_offset(b_off))
-				return -E2BIG;
-			emit_instr(ctx, beq, src, MIPS_R_ZERO, b_off);
-			emit_instr(ctx, movz, MIPS_R_V0, MIPS_R_ZERO, src);
 			emit_instr(ctx, ddivu, dst, src);
 			if (bpf_op == BPF_DIV)
 				emit_instr(ctx, mflo, dst);
@@ -943,11 +927,6 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 			break;
 		case BPF_DIV:
 		case BPF_MOD:
-			b_off = b_imm(exit_idx, ctx);
-			if (is_bad_offset(b_off))
-				return -E2BIG;
-			emit_instr(ctx, beq, src, MIPS_R_ZERO, b_off);
-			emit_instr(ctx, movz, MIPS_R_V0, MIPS_R_ZERO, src);
 			emit_instr(ctx, divu, dst, src);
 			if (bpf_op == BPF_DIV)
 				emit_instr(ctx, mflo, dst);
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 217a78e84865..0a34b0cec7b7 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -381,10 +381,6 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			goto bpf_alu32_trunc;
 		case BPF_ALU | BPF_DIV | BPF_X: /* (u32) dst /= (u32) src */
 		case BPF_ALU | BPF_MOD | BPF_X: /* (u32) dst %= (u32) src */
-			PPC_CMPWI(src_reg, 0);
-			PPC_BCC_SHORT(COND_NE, (ctx->idx * 4) + 12);
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_JMP(exit_addr);
 			if (BPF_OP(code) == BPF_MOD) {
 				PPC_DIVWU(b2p[TMP_REG_1], dst_reg, src_reg);
 				PPC_MULW(b2p[TMP_REG_1], src_reg,
@@ -395,10 +391,6 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			goto bpf_alu32_trunc;
 		case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */
 		case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */
-			PPC_CMPDI(src_reg, 0);
-			PPC_BCC_SHORT(COND_NE, (ctx->idx * 4) + 12);
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_JMP(exit_addr);
 			if (BPF_OP(code) == BPF_MOD) {
 				PPC_DIVD(b2p[TMP_REG_1], dst_reg, src_reg);
 				PPC_MULD(b2p[TMP_REG_1], src_reg,
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index e50188773ff3..78a19c93b380 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -610,11 +610,6 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 	{
 		int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0;
 
-		jit->seen |= SEEN_RET0;
-		/* ltr %src,%src (if src == 0 goto fail) */
-		EMIT2(0x1200, src_reg, src_reg);
-		/* jz <ret0> */
-		EMIT4_PCREL(0xa7840000, jit->ret0_ip - jit->prg);
 		/* lhi %w0,0 */
 		EMIT4_IMM(0xa7080000, REG_W0, 0);
 		/* lr %w1,%dst */
@@ -630,11 +625,6 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 	{
 		int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0;
 
-		jit->seen |= SEEN_RET0;
-		/* ltgr %src,%src (if src == 0 goto fail) */
-		EMIT4(0xb9020000, src_reg, src_reg);
-		/* jz <ret0> */
-		EMIT4_PCREL(0xa7840000, jit->ret0_ip - jit->prg);
 		/* lghi %w0,0 */
 		EMIT4_IMM(0xa7090000, REG_W0, 0);
 		/* lgr %w1,%dst */
diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c
index 50a24d7bd4c5..48a25869349b 100644
--- a/arch/sparc/net/bpf_jit_comp_64.c
+++ b/arch/sparc/net/bpf_jit_comp_64.c
@@ -967,31 +967,17 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		emit_alu(MULX, src, dst, ctx);
 		break;
 	case BPF_ALU | BPF_DIV | BPF_X:
-		emit_cmp(src, G0, ctx);
-		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
-		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
-
 		emit_write_y(G0, ctx);
 		emit_alu(DIV, src, dst, ctx);
 		break;
-
 	case BPF_ALU64 | BPF_DIV | BPF_X:
-		emit_cmp(src, G0, ctx);
-		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
-		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
-
 		emit_alu(UDIVX, src, dst, ctx);
 		break;
-
 	case BPF_ALU | BPF_MOD | BPF_X: {
 		const u8 tmp = bpf2sparc[TMP_REG_1];
 
 		ctx->tmp_1_used = true;
 
-		emit_cmp(src, G0, ctx);
-		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
-		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
-
 		emit_write_y(G0, ctx);
 		emit_alu3(DIV, dst, src, tmp, ctx);
 		emit_alu3(MULX, tmp, src, tmp, ctx);
@@ -1003,10 +989,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 
 		ctx->tmp_1_used = true;
 
-		emit_cmp(src, G0, ctx);
-		emit_branch(BE|ANNUL, ctx->idx, ctx->epilogue_offset, ctx);
-		emit_loadimm(0, bpf2sparc[BPF_REG_0], ctx);
-
 		emit_alu3(UDIVX, dst, src, tmp, ctx);
 		emit_alu3(MULX, tmp, src, tmp, ctx);
 		emit_alu3(SUB, dst, tmp, dst, ctx);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 5acee5139e28..4923d92f918d 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -568,26 +568,6 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			 */
 			EMIT2(0x31, 0xd2);
 
-			if (BPF_SRC(insn->code) == BPF_X) {
-				/* if (src_reg == 0) return 0 */
-
-				/* cmp r11, 0 */
-				EMIT4(0x49, 0x83, 0xFB, 0x00);
-
-				/* jne .+9 (skip over pop, pop, xor and jmp) */
-				EMIT2(X86_JNE, 1 + 1 + 2 + 5);
-				EMIT1(0x5A); /* pop rdx */
-				EMIT1(0x58); /* pop rax */
-				EMIT2(0x31, 0xc0); /* xor eax, eax */
-
-				/* jmp cleanup_addr
-				 * addrs[i] - 11, because there are 11 bytes
-				 * after this insn: div, mov, pop, pop, mov
-				 */
-				jmp_offset = ctx->cleanup_addr - (addrs[i] - 11);
-				EMIT1_off32(0xE9, jmp_offset);
-			}
-
 			if (BPF_CLASS(insn->code) == BPF_ALU64)
 				/* div r11 */
 				EMIT3(0x49, 0xF7, 0xF3);