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

Daniel Borkmann says:

====================
pull-request: bpf-next 2021-01-16

1) Extend atomic operations to the BPF instruction set along with x86-64 JIT support,
   that is, atomic{,64}_{xchg,cmpxchg,fetch_{add,and,or,xor}}, from Brendan Jackman.

2) Add support for using kernel module global variables (__ksym externs in BPF
   programs) retrieved via module's BTF, from Andrii Nakryiko.

3) Generalize BPF stackmap's buildid retrieval and add support to have buildid
   stored in mmap2 event for perf, from Jiri Olsa.

4) Various fixes for cross-building BPF sefltests out-of-tree which then will
   unblock wider automated testing on ARM hardware, from Jean-Philippe Brucker.

5) Allow to retrieve SOL_SOCKET opts from sock_addr progs, from Daniel Borkmann.

6) Clean up driver's XDP buffer init and split into two helpers to init per-
   descriptor and non-changing fields during processing, from Lorenzo Bianconi.

7) Minor misc improvements to libbpf & bpftool, from Ian Rogers.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (41 commits)
  perf: Add build id data in mmap2 event
  bpf: Add size arg to build_id_parse function
  bpf: Move stack_map_get_build_id into lib
  bpf: Document new atomic instructions
  bpf: Add tests for new BPF atomic operations
  bpf: Add bitwise atomic instructions
  bpf: Pull out a macro for interpreting atomic ALU operations
  bpf: Add instructions for atomic_[cmp]xchg
  bpf: Add BPF_FETCH field / create atomic_fetch_add instruction
  bpf: Move BPF_STX reserved field check into BPF_STX verifier code
  bpf: Rename BPF_XADD and prepare to encode other atomics in .imm
  bpf: x86: Factor out a lookup table for some ALU opcodes
  bpf: x86: Factor out emission of REX byte
  bpf: x86: Factor out emission of ModR/M for *(reg + off)
  tools/bpftool: Add -Wall when building BPF programs
  bpf, libbpf: Avoid unused function warning on bpf_tail_call_static
  selftests/bpf: Install btf_dump test cases
  selftests/bpf: Fix installation of urandom_read
  selftests/bpf: Move generated test files to $(TEST_GEN_FILES)
  selftests/bpf: Fix out-of-tree build
  ...
====================

Link: https://lore.kernel.org/r/20210116012922.17823-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

10 files changed, 258 insertions, 104 deletions

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 0207b6ea6e8a..897634d0a67c 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -1620,10 +1620,9 @@ exit:
 		}
 		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:
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index ef9f1d5e989d..f7b194878a99 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -875,10 +875,18 @@ emit_cond_jmp:
 		}
 		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 {
diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c
index 561154cbcc40..939dd06764bc 100644
--- a/arch/mips/net/ebpf_jit.c
+++ b/arch/mips/net/ebpf_jit.c
@@ -1423,8 +1423,8 @@ jeq_common:
 	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 @@ jeq_common:
 		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.
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 022103c6a201..aaf1a887f653 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -683,10 +683,18 @@ emit_clear:
 			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 @@ emit_clear:
 			/* 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));
diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c
index 579575f9cdae..81de865f4c7c 100644
--- a/arch/riscv/net/bpf_jit_comp32.c
+++ b/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)
 		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: /* Only BPF_ADD supported */
 			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:
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 8a56b5293117..b44ff52f84a6 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -1027,10 +1027,18 @@ out_be:
 		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);
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 0a4182792876..f973e2ead197 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/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;
 	/*
diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c
index 3364e2a00989..4b8d3c65d266 100644
--- a/arch/sparc/net/bpf_jit_comp_64.c
+++ b/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;
 
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 796506dcfc42..1d4d50199293 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -205,6 +205,18 @@ static u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg)
 	return byte + reg2hex[dst_reg] + (reg2hex[src_reg] << 3);
 }
 
+/* Some 1-byte opcodes for binary ALU operations */
+static u8 simple_alu_opcodes[] = {
+	[BPF_ADD] = 0x01,
+	[BPF_SUB] = 0x29,
+	[BPF_AND] = 0x21,
+	[BPF_OR] = 0x09,
+	[BPF_XOR] = 0x31,
+	[BPF_LSH] = 0xE0,
+	[BPF_RSH] = 0xE8,
+	[BPF_ARSH] = 0xF8,
+};
+
 static void jit_fill_hole(void *area, unsigned int size)
 {
 	/* Fill whole space with INT3 instructions */
@@ -681,6 +693,42 @@ static void emit_mov_reg(u8 **pprog, bool is64, u32 dst_reg, u32 src_reg)
 	*pprog = prog;
 }
 
+/* Emit the suffix (ModR/M etc) for addressing *(ptr_reg + off) and val_reg */
+static void emit_insn_suffix(u8 **pprog, u32 ptr_reg, u32 val_reg, int off)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	if (is_imm8(off)) {
+		/* 1-byte signed displacement.
+		 *
+		 * If off == 0 we could skip this and save one extra byte, but
+		 * special case of x86 R13 which always needs an offset is not
+		 * worth the hassle
+		 */
+		EMIT2(add_2reg(0x40, ptr_reg, val_reg), off);
+	} else {
+		/* 4-byte signed displacement */
+		EMIT1_off32(add_2reg(0x80, ptr_reg, val_reg), off);
+	}
+	*pprog = prog;
+}
+
+/*
+ * Emit a REX byte if it will be necessary to address these registers
+ */
+static void maybe_emit_mod(u8 **pprog, u32 dst_reg, u32 src_reg, bool is64)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	if (is64)
+		EMIT1(add_2mod(0x48, dst_reg, src_reg));
+	else if (is_ereg(dst_reg) || is_ereg(src_reg))
+		EMIT1(add_2mod(0x40, dst_reg, src_reg));
+	*pprog = prog;
+}
+
 /* LDX: dst_reg = *(u8*)(src_reg + off) */
 static void emit_ldx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
 {
@@ -708,15 +756,7 @@ static void emit_ldx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
 		EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x8B);
 		break;
 	}
-	/*
-	 * If insn->off == 0 we can save one extra byte, but
-	 * special case of x86 R13 which always needs an offset
-	 * is not worth the hassle
-	 */
-	if (is_imm8(off))
-		EMIT2(add_2reg(0x40, src_reg, dst_reg), off);
-	else
-		EMIT1_off32(add_2reg(0x80, src_reg, dst_reg), off);
+	emit_insn_suffix(&prog, src_reg, dst_reg, off);
 	*pprog = prog;
 }
 
@@ -751,13 +791,53 @@ static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off)
 		EMIT2(add_2mod(0x48, dst_reg, src_reg), 0x89);
 		break;
 	}
-	if (is_imm8(off))
-		EMIT2(add_2reg(0x40, dst_reg, src_reg), off);
-	else
-		EMIT1_off32(add_2reg(0x80, dst_reg, src_reg), off);
+	emit_insn_suffix(&prog, dst_reg, src_reg, off);
 	*pprog = prog;
 }
 
+static int emit_atomic(u8 **pprog, u8 atomic_op,
+		       u32 dst_reg, u32 src_reg, s16 off, u8 bpf_size)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	EMIT1(0xF0); /* lock prefix */
+
+	maybe_emit_mod(&prog, dst_reg, src_reg, bpf_size == BPF_DW);
+
+	/* emit opcode */
+	switch (atomic_op) {
+	case BPF_ADD:
+	case BPF_SUB:
+	case BPF_AND:
+	case BPF_OR:
+	case BPF_XOR:
+		/* lock *(u32/u64*)(dst_reg + off) <op>= src_reg */
+		EMIT1(simple_alu_opcodes[atomic_op]);
+		break;
+	case BPF_ADD | BPF_FETCH:
+		/* src_reg = atomic_fetch_add(dst_reg + off, src_reg); */
+		EMIT2(0x0F, 0xC1);
+		break;
+	case BPF_XCHG:
+		/* src_reg = atomic_xchg(dst_reg + off, src_reg); */
+		EMIT1(0x87);
+		break;
+	case BPF_CMPXCHG:
+		/* r0 = atomic_cmpxchg(dst_reg + off, r0, src_reg); */
+		EMIT2(0x0F, 0xB1);
+		break;
+	default:
+		pr_err("bpf_jit: unknown atomic opcode %02x\n", atomic_op);
+		return -EFAULT;
+	}
+
+	emit_insn_suffix(&prog, dst_reg, src_reg, off);
+
+	*pprog = prog;
+	return 0;
+}
+
 static bool ex_handler_bpf(const struct exception_table_entry *x,
 			   struct pt_regs *regs, int trapnr,
 			   unsigned long error_code, unsigned long fault_addr)
@@ -802,6 +882,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 	int i, cnt = 0, excnt = 0;
 	int proglen = 0;
 	u8 *prog = temp;
+	int err;
 
 	detect_reg_usage(insn, insn_cnt, callee_regs_used,
 			 &tail_call_seen);
@@ -837,17 +918,9 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_ALU64 | BPF_AND | BPF_X:
 		case BPF_ALU64 | BPF_OR | BPF_X:
 		case BPF_ALU64 | BPF_XOR | BPF_X:
-			switch (BPF_OP(insn->code)) {
-			case BPF_ADD: b2 = 0x01; break;
-			case BPF_SUB: b2 = 0x29; break;
-			case BPF_AND: b2 = 0x21; break;
-			case BPF_OR: b2 = 0x09; break;
-			case BPF_XOR: b2 = 0x31; break;
-			}
-			if (BPF_CLASS(insn->code) == BPF_ALU64)
-				EMIT1(add_2mod(0x48, dst_reg, src_reg));
-			else if (is_ereg(dst_reg) || is_ereg(src_reg))
-				EMIT1(add_2mod(0x40, dst_reg, src_reg));
+			maybe_emit_mod(&prog, dst_reg, src_reg,
+				       BPF_CLASS(insn->code) == BPF_ALU64);
+			b2 = simple_alu_opcodes[BPF_OP(insn->code)];
 			EMIT2(b2, add_2reg(0xC0, dst_reg, src_reg));
 			break;
 
@@ -1027,12 +1100,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			else if (is_ereg(dst_reg))
 				EMIT1(add_1mod(0x40, dst_reg));
 
-			switch (BPF_OP(insn->code)) {
-			case BPF_LSH: b3 = 0xE0; break;
-			case BPF_RSH: b3 = 0xE8; break;
-			case BPF_ARSH: b3 = 0xF8; break;
-			}
-
+			b3 = simple_alu_opcodes[BPF_OP(insn->code)];
 			if (imm32 == 1)
 				EMIT2(0xD1, add_1reg(b3, dst_reg));
 			else
@@ -1066,11 +1134,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			else if (is_ereg(dst_reg))
 				EMIT1(add_1mod(0x40, dst_reg));
 
-			switch (BPF_OP(insn->code)) {
-			case BPF_LSH: b3 = 0xE0; break;
-			case BPF_RSH: b3 = 0xE8; break;
-			case BPF_ARSH: b3 = 0xF8; break;
-			}
+			b3 = simple_alu_opcodes[BPF_OP(insn->code)];
 			EMIT2(0xD3, add_1reg(b3, dst_reg));
 
 			if (src_reg != BPF_REG_4)
@@ -1230,21 +1294,56 @@ st:			if (is_imm8(insn->off))
 			}
 			break;
 
-			/* STX XADD: lock *(u32*)(dst_reg + off) += src_reg */
-		case BPF_STX | BPF_XADD | BPF_W:
-			/* Emit 'lock add dword ptr [rax + off], eax' */
-			if (is_ereg(dst_reg) || is_ereg(src_reg))
-				EMIT3(0xF0, add_2mod(0x40, dst_reg, src_reg), 0x01);
-			else
-				EMIT2(0xF0, 0x01);
-			goto xadd;
-		case BPF_STX | BPF_XADD | BPF_DW:
-			EMIT3(0xF0, add_2mod(0x48, dst_reg, src_reg), 0x01);
-xadd:			if (is_imm8(insn->off))
-				EMIT2(add_2reg(0x40, dst_reg, src_reg), insn->off);
-			else
-				EMIT1_off32(add_2reg(0x80, dst_reg, src_reg),
-					    insn->off);
+		case BPF_STX | BPF_ATOMIC | BPF_W:
+		case BPF_STX | BPF_ATOMIC | BPF_DW:
+			if (insn->imm == (BPF_AND | BPF_FETCH) ||
+			    insn->imm == (BPF_OR | BPF_FETCH) ||
+			    insn->imm == (BPF_XOR | BPF_FETCH)) {
+				u8 *branch_target;
+				bool is64 = BPF_SIZE(insn->code) == BPF_DW;
+
+				/*
+				 * Can't be implemented with a single x86 insn.
+				 * Need to do a CMPXCHG loop.
+				 */
+
+				/* Will need RAX as a CMPXCHG operand so save R0 */
+				emit_mov_reg(&prog, true, BPF_REG_AX, BPF_REG_0);
+				branch_target = prog;
+				/* Load old value */
+				emit_ldx(&prog, BPF_SIZE(insn->code),
+					 BPF_REG_0, dst_reg, insn->off);
+				/*
+				 * Perform the (commutative) operation locally,
+				 * put the result in the AUX_REG.
+				 */
+				emit_mov_reg(&prog, is64, AUX_REG, BPF_REG_0);
+				maybe_emit_mod(&prog, AUX_REG, src_reg, is64);
+				EMIT2(simple_alu_opcodes[BPF_OP(insn->imm)],
+				      add_2reg(0xC0, AUX_REG, src_reg));
+				/* Attempt to swap in new value */
+				err = emit_atomic(&prog, BPF_CMPXCHG,
+						  dst_reg, AUX_REG, insn->off,
+						  BPF_SIZE(insn->code));
+				if (WARN_ON(err))
+					return err;
+				/*
+				 * ZF tells us whether we won the race. If it's
+				 * cleared we need to try again.
+				 */
+				EMIT2(X86_JNE, -(prog - branch_target) - 2);
+				/* Return the pre-modification value */
+				emit_mov_reg(&prog, is64, src_reg, BPF_REG_0);
+				/* Restore R0 after clobbering RAX */
+				emit_mov_reg(&prog, true, BPF_REG_0, BPF_REG_AX);
+				break;
+
+			}
+
+			err = emit_atomic(&prog, insn->imm, dst_reg, src_reg,
+						  insn->off, BPF_SIZE(insn->code));
+			if (err)
+				return err;
 			break;
 
 			/* call */
@@ -1295,20 +1394,16 @@ xadd:			if (is_imm8(insn->off))
 		case BPF_JMP32 | BPF_JSGE | BPF_X:
 		case BPF_JMP32 | BPF_JSLE | BPF_X:
 			/* cmp dst_reg, src_reg */
-			if (BPF_CLASS(insn->code) == BPF_JMP)
-				EMIT1(add_2mod(0x48, dst_reg, src_reg));
-			else if (is_ereg(dst_reg) || is_ereg(src_reg))
-				EMIT1(add_2mod(0x40, dst_reg, src_reg));
+			maybe_emit_mod(&prog, dst_reg, src_reg,
+				       BPF_CLASS(insn->code) == BPF_JMP);
 			EMIT2(0x39, add_2reg(0xC0, dst_reg, src_reg));
 			goto emit_cond_jmp;
 
 		case BPF_JMP | BPF_JSET | BPF_X:
 		case BPF_JMP32 | BPF_JSET | BPF_X:
 			/* test dst_reg, src_reg */
-			if (BPF_CLASS(insn->code) == BPF_JMP)
-				EMIT1(add_2mod(0x48, dst_reg, src_reg));
-			else if (is_ereg(dst_reg) || is_ereg(src_reg))
-				EMIT1(add_2mod(0x40, dst_reg, src_reg));
+			maybe_emit_mod(&prog, dst_reg, src_reg,
+				       BPF_CLASS(insn->code) == BPF_JMP);
 			EMIT2(0x85, add_2reg(0xC0, dst_reg, src_reg));
 			goto emit_cond_jmp;
 
@@ -1344,10 +1439,8 @@ xadd:			if (is_imm8(insn->off))
 		case BPF_JMP32 | BPF_JSLE | BPF_K:
 			/* test dst_reg, dst_reg to save one extra byte */
 			if (imm32 == 0) {
-				if (BPF_CLASS(insn->code) == BPF_JMP)
-					EMIT1(add_2mod(0x48, dst_reg, dst_reg));
-				else if (is_ereg(dst_reg))
-					EMIT1(add_2mod(0x40, dst_reg, dst_reg));
+				maybe_emit_mod(&prog, dst_reg, dst_reg,
+					       BPF_CLASS(insn->code) == BPF_JMP);
 				EMIT2(0x85, add_2reg(0xC0, dst_reg, dst_reg));
 				goto emit_cond_jmp;
 			}
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index 96fde03aa987..d17b67c69f89 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -2243,10 +2243,8 @@ emit_jmp:
 				return -EFAULT;
 			}
 			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:
 			goto notyet;
 		case BPF_JMP | BPF_EXIT:
 			if (seen_exit) {