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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2019-05-31

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

Lots of exciting new features in the first PR of this developement cycle!
The main changes are:

1) misc verifier improvements, from Alexei.

2) bpftool can now convert btf to valid C, from Andrii.

3) verifier can insert explicit ZEXT insn when requested by 32-bit JITs.
   This feature greatly improves BPF speed on 32-bit architectures. From Jiong.

4) cgroups will now auto-detach bpf programs. This fixes issue of thousands
   bpf programs got stuck in dying cgroups. From Roman.

5) new bpf_send_signal() helper, from Yonghong.

6) cgroup inet skb programs can signal CN to the stack, from Lawrence.

7) miscellaneous cleanups, from many developers.
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

Documentation/bpf/bpf_design_QA.rst

@@ -172,11 +172,31 @@ registers which makes BPF inefficient virtual machine for 32-bit
 CPU architectures and 32-bit HW accelerators. Can true 32-bit registers
 be added to BPF in the future?
 
-A: NO. The first thing to improve performance on 32-bit archs is to teach
-LLVM to generate code that uses 32-bit subregisters. Then second step
-is to teach verifier to mark operations where zero-ing upper bits
-is unnecessary. Then JITs can take advantage of those markings and
-drastically reduce size of generated code and improve performance.
+A: NO.
+
+But some optimizations on zero-ing the upper 32 bits for BPF registers are
+available, and can be leveraged to improve the performance of JITed BPF
+programs for 32-bit architectures.
+
+Starting with version 7, LLVM is able to generate instructions that operate
+on 32-bit subregisters, provided the option -mattr=+alu32 is passed for
+compiling a program. Furthermore, the verifier can now mark the
+instructions for which zero-ing the upper bits of the destination register
+is required, and insert an explicit zero-extension (zext) instruction
+(a mov32 variant). This means that for architectures without zext hardware
+support, the JIT back-ends do not need to clear the upper bits for
+subregisters written by alu32 instructions or narrow loads. Instead, the
+back-ends simply need to support code generation for that mov32 variant,
+and to overwrite bpf_jit_needs_zext() to make it return "true" (in order to
+enable zext insertion in the verifier).
+
+Note that it is possible for a JIT back-end to have partial hardware
+support for zext. In that case, if verifier zext insertion is enabled,
+it could lead to the insertion of unnecessary zext instructions. Such
+instructions could be removed by creating a simple peephole inside the JIT
+back-end: if one instruction has hardware support for zext and if the next
+instruction is an explicit zext, then the latter can be skipped when doing
+the code generation.
 
 Q: Does BPF have a stable ABI?
 ------------------------------

arch/arm/net/bpf_jit_32.c

@@ -736,7 +736,8 @@ static inline void emit_a32_alu_r64(const bool is64, const s8 dst[],
 
 		/* ALU operation */
 		emit_alu_r(rd[1], rs, true, false, op, ctx);
-		emit_a32_mov_i(rd[0], 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(rd[0], 0, ctx);
 	}
 
 	arm_bpf_put_reg64(dst, rd, ctx);
@@ -758,8 +759,9 @@ static inline void emit_a32_mov_r64(const bool is64, const s8 dst[],
 				  struct jit_ctx *ctx) {
 	if (!is64) {
 		emit_a32_mov_r(dst_lo, src_lo, ctx);
-		/* Zero out high 4 bytes */
-		emit_a32_mov_i(dst_hi, 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			/* Zero out high 4 bytes */
+			emit_a32_mov_i(dst_hi, 0, ctx);
 	} else if (__LINUX_ARM_ARCH__ < 6 &&
 		   ctx->cpu_architecture < CPU_ARCH_ARMv5TE) {
 		/* complete 8 byte move */
@@ -1060,17 +1062,20 @@ static inline void emit_ldx_r(const s8 dst[], const s8 src,
 	case BPF_B:
 		/* Load a Byte */
 		emit(ARM_LDRB_I(rd[1], rm, off), ctx);
-		emit_a32_mov_i(rd[0], 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(rd[0], 0, ctx);
 		break;
 	case BPF_H:
 		/* Load a HalfWord */
 		emit(ARM_LDRH_I(rd[1], rm, off), ctx);
-		emit_a32_mov_i(rd[0], 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(rd[0], 0, ctx);
 		break;
 	case BPF_W:
 		/* Load a Word */
 		emit(ARM_LDR_I(rd[1], rm, off), ctx);
-		emit_a32_mov_i(rd[0], 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(rd[0], 0, ctx);
 		break;
 	case BPF_DW:
 		/* Load a Double Word */
@@ -1359,6 +1364,11 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_ALU64 | BPF_MOV | BPF_X:
 		switch (BPF_SRC(code)) {
 		case BPF_X:
+			if (imm == 1) {
+				/* Special mov32 for zext */
+				emit_a32_mov_i(dst_hi, 0, ctx);
+				break;
+			}
 			emit_a32_mov_r64(is64, dst, src, ctx);
 			break;
 		case BPF_K:
@@ -1438,7 +1448,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		}
 		emit_udivmod(rd_lo, rd_lo, rt, ctx, BPF_OP(code));
 		arm_bpf_put_reg32(dst_lo, rd_lo, ctx);
-		emit_a32_mov_i(dst_hi, 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(dst_hi, 0, ctx);
 		break;
 	case BPF_ALU64 | BPF_DIV | BPF_K:
 	case BPF_ALU64 | BPF_DIV | BPF_X:
@@ -1453,7 +1464,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			return -EINVAL;
 		if (imm)
 			emit_a32_alu_i(dst_lo, imm, ctx, BPF_OP(code));
-		emit_a32_mov_i(dst_hi, 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(dst_hi, 0, ctx);
 		break;
 	/* dst = dst << imm */
 	case BPF_ALU64 | BPF_LSH | BPF_K:
@@ -1488,7 +1500,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	/* dst = ~dst */
 	case BPF_ALU | BPF_NEG:
 		emit_a32_alu_i(dst_lo, 0, ctx, BPF_OP(code));
-		emit_a32_mov_i(dst_hi, 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(dst_hi, 0, ctx);
 		break;
 	/* dst = ~dst (64 bit) */
 	case BPF_ALU64 | BPF_NEG:
@@ -1544,11 +1557,13 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 #else /* ARMv6+ */
 			emit(ARM_UXTH(rd[1], rd[1]), ctx);
 #endif
-			emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx);
+			if (!ctx->prog->aux->verifier_zext)
+				emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx);
 			break;
 		case 32:
 			/* zero-extend 32 bits into 64 bits */
-			emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx);
+			if (!ctx->prog->aux->verifier_zext)
+				emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx);
 			break;
 		case 64:
 			/* nop */
@@ -1838,6 +1853,11 @@ void bpf_jit_compile(struct bpf_prog *prog)
 	/* Nothing to do here. We support Internal BPF. */
 }
 
+bool bpf_jit_needs_zext(void)
+{
+	return true;
+}
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
 	struct bpf_prog *tmp, *orig_prog = prog;

arch/powerpc/net/bpf_jit_comp64.c

@@ -504,26 +504,35 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		case BPF_ALU | BPF_LSH | BPF_X: /* (u32) dst <<= (u32) src */
 			/* slw clears top 32 bits */
 			PPC_SLW(dst_reg, dst_reg, src_reg);
+			/* skip zero extension move, but set address map. */
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		case BPF_ALU64 | BPF_LSH | BPF_X: /* dst <<= src; */
 			PPC_SLD(dst_reg, dst_reg, src_reg);
 			break;
 		case BPF_ALU | BPF_LSH | BPF_K: /* (u32) dst <<== (u32) imm */
 			/* with imm 0, we still need to clear top 32 bits */
 			PPC_SLWI(dst_reg, dst_reg, imm);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		case BPF_ALU64 | BPF_LSH | BPF_K: /* dst <<== imm */
 			if (imm != 0)
 				PPC_SLDI(dst_reg, dst_reg, imm);
 			break;
 		case BPF_ALU | BPF_RSH | BPF_X: /* (u32) dst >>= (u32) src */
 			PPC_SRW(dst_reg, dst_reg, src_reg);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		case BPF_ALU64 | BPF_RSH | BPF_X: /* dst >>= src */
 			PPC_SRD(dst_reg, dst_reg, src_reg);
 			break;
 		case BPF_ALU | BPF_RSH | BPF_K: /* (u32) dst >>= (u32) imm */
 			PPC_SRWI(dst_reg, dst_reg, imm);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		case BPF_ALU64 | BPF_RSH | BPF_K: /* dst >>= imm */
 			if (imm != 0)
@@ -548,18 +557,25 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		 */
 		case BPF_ALU | BPF_MOV | BPF_X: /* (u32) dst = src */
 		case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */
+			if (imm == 1) {
+				/* special mov32 for zext */
+				PPC_RLWINM(dst_reg, dst_reg, 0, 0, 31);
+				break;
+			}
 			PPC_MR(dst_reg, src_reg);
 			goto bpf_alu32_trunc;
 		case BPF_ALU | BPF_MOV | BPF_K: /* (u32) dst = imm */
 		case BPF_ALU64 | BPF_MOV | BPF_K: /* dst = (s64) imm */
 			PPC_LI32(dst_reg, imm);
 			if (imm < 0)
 				goto bpf_alu32_trunc;
+			else if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 
 bpf_alu32_trunc:
 		/* Truncate to 32-bits */
-		if (BPF_CLASS(code) == BPF_ALU)
+		if (BPF_CLASS(code) == BPF_ALU && !fp->aux->verifier_zext)
 			PPC_RLWINM(dst_reg, dst_reg, 0, 0, 31);
 		break;
 
@@ -618,10 +634,13 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			case 16:
 				/* zero-extend 16 bits into 64 bits */
 				PPC_RLDICL(dst_reg, dst_reg, 0, 48);
+				if (insn_is_zext(&insn[i + 1]))
+					addrs[++i] = ctx->idx * 4;
 				break;
 			case 32:
-				/* zero-extend 32 bits into 64 bits */
-				PPC_RLDICL(dst_reg, dst_reg, 0, 32);
+				if (!fp->aux->verifier_zext)
+					/* zero-extend 32 bits into 64 bits */
+					PPC_RLDICL(dst_reg, dst_reg, 0, 32);
 				break;
 			case 64:
 				/* nop */
@@ -698,14 +717,20 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		/* dst = *(u8 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_B:
 			PPC_LBZ(dst_reg, src_reg, off);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		/* dst = *(u16 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_H:
 			PPC_LHZ(dst_reg, src_reg, off);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		/* dst = *(u32 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_W:
 			PPC_LWZ(dst_reg, src_reg, off);
+			if (insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
 			break;
 		/* dst = *(u64 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_DW:
@@ -1046,6 +1071,11 @@ struct powerpc64_jit_data {
 	struct codegen_context ctx;
 };
 
+bool bpf_jit_needs_zext(void)
+{
+	return true;
+}
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 {
 	u32 proglen;