Atomics for eBPF

.travis.yml

@@ -0,0 +1,33 @@
+sudo: required
+language: bash
+dist: bionic
+services:
+    - docker
+
+env:
+    global:
+        - PROJECT_NAME='libbpf'
+        - AUTHOR_EMAIL="$(git log -1 --pretty=\"%aE\")"
+        - REPO_ROOT="$TRAVIS_BUILD_DIR"
+        - CI_ROOT="$REPO_ROOT/travis-ci"
+        - VMTEST_ROOT="$CI_ROOT/vmtest"
+
+addons:
+    apt:
+        packages:
+            - qemu-kvm
+            - zstd
+            - binutils-dev
+            - elfutils
+            - libcap-dev
+            - libelf-dev
+            - libdw-dev
+            - python3-docutils
+
+jobs:
+    include:
+        - stage: Builds & Tests
+          name: Kernel LATEST + selftests
+          language: bash
+          env: KERNEL=LATEST
+          script:  $CI_ROOT/vmtest/run_vmtest.sh || travis_terminate 1

Documentation/networking/filter.rst

@@ -1006,13 +1006,13 @@ Size modifier is one of ...
 
 Mode modifier is one of::
 
-  BPF_IMM  0x00  /* used for 32-bit mov in classic BPF and 64-bit in eBPF */
-  BPF_ABS  0x20
-  BPF_IND  0x40
-  BPF_MEM  0x60
-  BPF_LEN  0x80  /* classic BPF only, reserved in eBPF */
-  BPF_MSH  0xa0  /* classic BPF only, reserved in eBPF */
-  BPF_XADD 0xc0  /* eBPF only, exclusive add */
+  BPF_IMM     0x00  /* used for 32-bit mov in classic BPF and 64-bit in eBPF */
+  BPF_ABS     0x20
+  BPF_IND     0x40
+  BPF_MEM     0x60
+  BPF_LEN     0x80  /* classic BPF only, reserved in eBPF */
+  BPF_MSH     0xa0  /* classic BPF only, reserved in eBPF */
+  BPF_ATOMIC  0xc0  /* eBPF only, atomic operations */
 
 eBPF has two non-generic instructions: (BPF_ABS | <size> | BPF_LD) and
 (BPF_IND | <size> | BPF_LD) which are used to access packet data.
@@ -1044,11 +1044,45 @@ Unlike classic BPF instruction set, eBPF has generic load/store operations::
     BPF_MEM | <size> | BPF_STX:  *(size *) (dst_reg + off) = src_reg
     BPF_MEM | <size> | BPF_ST:   *(size *) (dst_reg + off) = imm32
     BPF_MEM | <size> | BPF_LDX:  dst_reg = *(size *) (src_reg + off)
-    BPF_XADD | BPF_W  | BPF_STX: lock xadd *(u32 *)(dst_reg + off16) += src_reg
-    BPF_XADD | BPF_DW | BPF_STX: lock xadd *(u64 *)(dst_reg + off16) += src_reg
 
-Where size is one of: BPF_B or BPF_H or BPF_W or BPF_DW. Note that 1 and
-2 byte atomic increments are not supported.
+Where size is one of: BPF_B or BPF_H or BPF_W or BPF_DW.
+
+It also includes atomic operations, which use the immediate field for extra
+encoding.
+
+   .imm = BPF_ADD, .code = BPF_ATOMIC | BPF_W  | BPF_STX: lock xadd *(u32 *)(dst_reg + off16) += src_reg
+   .imm = BPF_ADD, .code = BPF_ATOMIC | BPF_DW | BPF_STX: lock xadd *(u64 *)(dst_reg + off16) += src_reg
+
+The basic atomic operations supported (from architecture v4 onwards) are:
+
+    BPF_ADD
+    BPF_AND
+    BPF_OR
+    BPF_XOR
+
+Each having equivalent semantics with the ``BPF_ADD`` example, that is: the
+memory location addresed by ``dst_reg + off`` is atomically modified, with
+``src_reg`` as the other operand. If the ``BPF_FETCH`` flag is set in the
+immediate, then these operations also overwrite ``src_reg`` with the
+value that was in memory before it was modified.
+
+The more special operations are:
+
+    BPF_XCHG
+
+This atomically exchanges ``src_reg`` with the value addressed by ``dst_reg +
+off``.
+
+    BPF_CMPXCHG
+
+This atomically compares the value addressed by ``dst_reg + off`` with
+``R0``. If they match it is replaced with ``src_reg``, The value that was there
+before is loaded back to ``R0``.
+
+Note that 1 and 2 byte atomic operations are not supported.
+
+You may encounter BPF_XADD - this is a legacy name for BPF_ATOMIC, referring to
+the exclusive-add operation encoded when the immediate field is zero.
 
 eBPF has one 16-byte instruction: BPF_LD | BPF_DW | BPF_IMM which consists
 of two consecutive ``struct bpf_insn`` 8-byte blocks and interpreted as single

arch/arm/net/bpf_jit_32.c

@@ -1620,10 +1620,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		}
 		emit_str_r(dst_lo, tmp2, off, ctx, BPF_SIZE(code));
 		break;
-	/* STX XADD: lock *(u32 *)(dst + off) += src */
-	case BPF_STX | BPF_XADD | BPF_W:
-	/* STX XADD: lock *(u64 *)(dst + off) += src */
-	case BPF_STX | BPF_XADD | BPF_DW:
+	/* Atomic ops */
+	case BPF_STX | BPF_ATOMIC | BPF_W:
+	case BPF_STX | BPF_ATOMIC | BPF_DW:
 		goto notyet;
 	/* STX: *(size *)(dst + off) = src */
 	case BPF_STX | BPF_MEM | BPF_W:

arch/arm64/net/bpf_jit_comp.c

@@ -875,10 +875,18 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 		}
 		break;
 
-	/* STX XADD: lock *(u32 *)(dst + off) += src */
-	case BPF_STX | BPF_XADD | BPF_W:
-	/* STX XADD: lock *(u64 *)(dst + off) += src */
-	case BPF_STX | BPF_XADD | BPF_DW:
+	case BPF_STX | BPF_ATOMIC | BPF_W:
+	case BPF_STX | BPF_ATOMIC | BPF_DW:
+		if (insn->imm != BPF_ADD) {
+			pr_err_once("unknown atomic op code %02x\n", insn->imm);
+			return -EINVAL;
+		}
+
+		/* STX XADD: lock *(u32 *)(dst + off) += src
+		 * and
+		 * STX XADD: lock *(u64 *)(dst + off) += src
+		 */
+
 		if (!off) {
 			reg = dst;
 		} else {

arch/mips/net/ebpf_jit.c

@@ -1423,8 +1423,8 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 	case BPF_STX | BPF_H | BPF_MEM:
 	case BPF_STX | BPF_W | BPF_MEM:
 	case BPF_STX | BPF_DW | BPF_MEM:
-	case BPF_STX | BPF_W | BPF_XADD:
-	case BPF_STX | BPF_DW | BPF_XADD:
+	case BPF_STX | BPF_W | BPF_ATOMIC:
+	case BPF_STX | BPF_DW | BPF_ATOMIC:
 		if (insn->dst_reg == BPF_REG_10) {
 			ctx->flags |= EBPF_SEEN_FP;
 			dst = MIPS_R_SP;
@@ -1438,7 +1438,12 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 		src = ebpf_to_mips_reg(ctx, insn, src_reg_no_fp);
 		if (src < 0)
 			return src;
-		if (BPF_MODE(insn->code) == BPF_XADD) {
+		if (BPF_MODE(insn->code) == BPF_ATOMIC) {
+			if (insn->imm != BPF_ADD) {
+				pr_err("ATOMIC OP %02x NOT HANDLED\n", insn->imm);
+				return -EINVAL;
+			}
+
 			/*
 			 * If mem_off does not fit within the 9 bit ll/sc
 			 * instruction immediate field, use a temp reg.

arch/powerpc/net/bpf_jit_comp64.c

@@ -683,10 +683,18 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			break;
 
 		/*
-		 * BPF_STX XADD (atomic_add)
+		 * BPF_STX ATOMIC (atomic ops)
 		 */
-		/* *(u32 *)(dst + off) += src */
-		case BPF_STX | BPF_XADD | BPF_W:
+		case BPF_STX | BPF_ATOMIC | BPF_W:
+			if (insn->imm != BPF_ADD) {
+				pr_err_ratelimited(
+					"eBPF filter atomic op code %02x (@%d) unsupported\n",
+					code, i);
+				return -ENOTSUPP;
+			}
+
+			/* *(u32 *)(dst + off) += src */
+
 			/* Get EA into TMP_REG_1 */
 			EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], dst_reg, off));
 			tmp_idx = ctx->idx * 4;
@@ -699,8 +707,15 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 			/* we're done if this succeeded */
 			PPC_BCC_SHORT(COND_NE, tmp_idx);
 			break;
-		/* *(u64 *)(dst + off) += src */
-		case BPF_STX | BPF_XADD | BPF_DW:
+		case BPF_STX | BPF_ATOMIC | BPF_DW:
+			if (insn->imm != BPF_ADD) {
+				pr_err_ratelimited(
+					"eBPF filter atomic op code %02x (@%d) unsupported\n",
+					code, i);
+				return -ENOTSUPP;
+			}
+			/* *(u64 *)(dst + off) += src */
+
 			EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], dst_reg, off));
 			tmp_idx = ctx->idx * 4;
 			EMIT(PPC_RAW_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0));

arch/riscv/net/bpf_jit_comp32.c

@@ -881,7 +881,7 @@ static int emit_store_r64(const s8 *dst, const s8 *src, s16 off,
 	const s8 *rd = bpf_get_reg64(dst, tmp1, ctx);
 	const s8 *rs = bpf_get_reg64(src, tmp2, ctx);
 
-	if (mode == BPF_XADD && size != BPF_W)
+	if (mode == BPF_ATOMIC && (size != BPF_W || imm != BPF_ADD))
 		return -1;
 
 	emit_imm(RV_REG_T0, off, ctx);
@@ -899,7 +899,7 @@ static int emit_store_r64(const s8 *dst, const s8 *src, s16 off,
 		case BPF_MEM:
 			emit(rv_sw(RV_REG_T0, 0, lo(rs)), ctx);
 			break;
-		case BPF_XADD:
+		case BPF_ATOMIC: /* .imm checked above - only BPF_ADD allowed */
 			emit(rv_amoadd_w(RV_REG_ZERO, lo(rs), RV_REG_T0, 0, 0),
 			     ctx);
 			break;
@@ -1260,7 +1260,6 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_STX | BPF_MEM | BPF_H:
 	case BPF_STX | BPF_MEM | BPF_W:
 	case BPF_STX | BPF_MEM | BPF_DW:
-	case BPF_STX | BPF_XADD | BPF_W:
 		if (BPF_CLASS(code) == BPF_ST) {
 			emit_imm32(tmp2, imm, ctx);
 			src = tmp2;
@@ -1271,8 +1270,21 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 			return -1;
 		break;
 
+	case BPF_STX | BPF_ATOMIC | BPF_W:
+		if (insn->imm != BPF_ADD) {
+			pr_info_once(
+				"bpf-jit: not supported: atomic operation %02x ***\n",
+				insn->imm);
+			return -EFAULT;
+		}
+
+		if (emit_store_r64(dst, src, off, ctx, BPF_SIZE(code),
+				   BPF_MODE(code)))
+			return -1;
+		break;
+
 	/* No hardware support for 8-byte atomics in RV32. */
-	case BPF_STX | BPF_XADD | BPF_DW:
+	case BPF_STX | BPF_ATOMIC | BPF_DW:
 		/* Fallthrough. */
 
 notsupported:

arch/riscv/net/bpf_jit_comp64.c

@@ -1027,10 +1027,18 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
 		emit_sd(RV_REG_T1, 0, rs, ctx);
 		break;
-	/* STX XADD: lock *(u32 *)(dst + off) += src */
-	case BPF_STX | BPF_XADD | BPF_W:
-	/* STX XADD: lock *(u64 *)(dst + off) += src */
-	case BPF_STX | BPF_XADD | BPF_DW:
+	case BPF_STX | BPF_ATOMIC | BPF_W:
+	case BPF_STX | BPF_ATOMIC | BPF_DW:
+		if (insn->imm != BPF_ADD) {
+			pr_err("bpf-jit: not supported: atomic operation %02x ***\n",
+			       insn->imm);
+			return -EINVAL;
+		}
+
+		/* atomic_add: lock *(u32 *)(dst + off) += src
+		 * atomic_add: lock *(u64 *)(dst + off) += src
+		 */
+
 		if (off) {
 			if (is_12b_int(off)) {
 				emit_addi(RV_REG_T1, rd, off, ctx);

arch/s390/net/bpf_jit_comp.c

@@ -1205,18 +1205,23 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 		jit->seen |= SEEN_MEM;
 		break;
 	/*
-	 * BPF_STX XADD (atomic_add)
+	 * BPF_ATOMIC
 	 */
-	case BPF_STX | BPF_XADD | BPF_W: /* *(u32 *)(dst + off) += src */
-		/* laal %w0,%src,off(%dst) */
-		EMIT6_DISP_LH(0xeb000000, 0x00fa, REG_W0, src_reg,
-			      dst_reg, off);
-		jit->seen |= SEEN_MEM;
-		break;
-	case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */
-		/* laalg %w0,%src,off(%dst) */
-		EMIT6_DISP_LH(0xeb000000, 0x00ea, REG_W0, src_reg,
-			      dst_reg, off);
+	case BPF_STX | BPF_ATOMIC | BPF_DW:
+	case BPF_STX | BPF_ATOMIC | BPF_W:
+		if (insn->imm != BPF_ADD) {
+			pr_err("Unknown atomic operation %02x\n", insn->imm);
+			return -1;
+		}
+
+		/* *(u32/u64 *)(dst + off) += src
+		 *
+		 * BFW_W:  laal  %w0,%src,off(%dst)
+		 * BPF_DW: laalg %w0,%src,off(%dst)
+		 */
+		EMIT6_DISP_LH(0xeb000000,
+			      BPF_SIZE(insn->code) == BPF_W ? 0x00fa : 0x00ea,
+			      REG_W0, src_reg, dst_reg, off);
 		jit->seen |= SEEN_MEM;
 		break;
 	/*

arch/sparc/net/bpf_jit_comp_64.c

@@ -1366,12 +1366,18 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		break;
 	}
 
-	/* STX XADD: lock *(u32 *)(dst + off) += src */
-	case BPF_STX | BPF_XADD | BPF_W: {
+	case BPF_STX | BPF_ATOMIC | BPF_W: {
 		const u8 tmp = bpf2sparc[TMP_REG_1];
 		const u8 tmp2 = bpf2sparc[TMP_REG_2];
 		const u8 tmp3 = bpf2sparc[TMP_REG_3];
 
+		if (insn->imm != BPF_ADD) {
+			pr_err_once("unknown atomic op %02x\n", insn->imm);
+			return -EINVAL;
+		}
+
+		/* lock *(u32 *)(dst + off) += src */
+
 		if (insn->dst_reg == BPF_REG_FP)
 			ctx->saw_frame_pointer = true;
 
@@ -1390,11 +1396,16 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		break;
 	}
 	/* STX XADD: lock *(u64 *)(dst + off) += src */
-	case BPF_STX | BPF_XADD | BPF_DW: {
+	case BPF_STX | BPF_ATOMIC | BPF_DW: {
 		const u8 tmp = bpf2sparc[TMP_REG_1];
 		const u8 tmp2 = bpf2sparc[TMP_REG_2];
 		const u8 tmp3 = bpf2sparc[TMP_REG_3];
 
+		if (insn->imm != BPF_ADD) {
+			pr_err_once("unknown atomic op %02x\n", insn->imm);
+			return -EINVAL;
+		}
+
 		if (insn->dst_reg == BPF_REG_FP)
 			ctx->saw_frame_pointer = true;