bpf, arm64: Support load-acquire and store-release instructions

Support BPF load-acquire (BPF_LOAD_ACQ) and store-release
(BPF_STORE_REL) instructions in the arm64 JIT compiler.  For example
(assuming little-endian):

  db 10 00 00 00 01 00 00  r0 = load_acquire((u64 *)(r1 + 0x0))
  95 00 00 00 00 00 00 00  exit

  opcode (0xdb): BPF_ATOMIC | BPF_DW | BPF_STX
  imm (0x00000100): BPF_LOAD_ACQ

The JIT compiler would emit an LDAR instruction for the above, e.g.:

  ldar  x7, [x0]

Similarly, consider the following 16-bit store-release:

  cb 21 00 00 10 01 00 00  store_release((u16 *)(r1 + 0x0), w2)
  95 00 00 00 00 00 00 00  exit

  opcode (0xcb): BPF_ATOMIC | BPF_H | BPF_STX
  imm (0x00000110): BPF_STORE_REL

An STLRH instruction would be emitted, e.g.:

  stlrh  w1, [x0]

For a complete mapping:

  load-acquire     8-bit  LDARB
 (BPF_LOAD_ACQ)   16-bit  LDARH
                  32-bit  LDAR (32-bit)
                  64-bit  LDAR (64-bit)
  store-release    8-bit  STLRB
 (BPF_STORE_REL)  16-bit  STLRH
                  32-bit  STLR (32-bit)
                  64-bit  STLR (64-bit)

Arena accesses are supported.
bpf_jit_supports_insn(..., /*in_arena=*/true) always returns true for
BPF_LOAD_ACQ and BPF_STORE_REL instructions, as they don't depend on
ARM64_HAS_LSE_ATOMICS.

Acked-by: Xu Kuohai <xukuohai@huawei.com>
Signed-off-by: Peilin Ye <yepeilin@google.com>
Link: https://lore.kernel.org/r/51664a1300710238ba2d4d95142b57a52c4f0cae.1741049567.git.yepeilin@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Author: peilin-ye

arch/arm64/net/bpf_jit.h

@@ -119,6 +119,26 @@
 	aarch64_insn_gen_load_store_ex(Rt, Rn, Rs, A64_SIZE(sf), \
 				       AARCH64_INSN_LDST_STORE_REL_EX)
 
+/* Load-acquire & store-release */
+#define A64_LDAR(Rt, Rn, size)  \
+	aarch64_insn_gen_load_acq_store_rel(Rt, Rn, AARCH64_INSN_SIZE_##size, \
+					    AARCH64_INSN_LDST_LOAD_ACQ)
+#define A64_STLR(Rt, Rn, size)  \
+	aarch64_insn_gen_load_acq_store_rel(Rt, Rn, AARCH64_INSN_SIZE_##size, \
+					    AARCH64_INSN_LDST_STORE_REL)
+
+/* Rt = [Rn] (load acquire) */
+#define A64_LDARB(Wt, Xn)	A64_LDAR(Wt, Xn, 8)
+#define A64_LDARH(Wt, Xn)	A64_LDAR(Wt, Xn, 16)
+#define A64_LDAR32(Wt, Xn)	A64_LDAR(Wt, Xn, 32)
+#define A64_LDAR64(Xt, Xn)	A64_LDAR(Xt, Xn, 64)
+
+/* [Rn] = Rt (store release) */
+#define A64_STLRB(Wt, Xn)	A64_STLR(Wt, Xn, 8)
+#define A64_STLRH(Wt, Xn)	A64_STLR(Wt, Xn, 16)
+#define A64_STLR32(Wt, Xn)	A64_STLR(Wt, Xn, 32)
+#define A64_STLR64(Xt, Xn)	A64_STLR(Xt, Xn, 64)
+
 /*
  * LSE atomics
  *

arch/arm64/net/bpf_jit_comp.c

@@ -647,6 +647,81 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	return 0;
 }
 
+static int emit_atomic_ld_st(const struct bpf_insn *insn, struct jit_ctx *ctx)
+{
+	const s32 imm = insn->imm;
+	const s16 off = insn->off;
+	const u8 code = insn->code;
+	const bool arena = BPF_MODE(code) == BPF_PROBE_ATOMIC;
+	const u8 arena_vm_base = bpf2a64[ARENA_VM_START];
+	const u8 dst = bpf2a64[insn->dst_reg];
+	const u8 src = bpf2a64[insn->src_reg];
+	const u8 tmp = bpf2a64[TMP_REG_1];
+	u8 reg;
+
+	switch (imm) {
+	case BPF_LOAD_ACQ:
+		reg = src;
+		break;
+	case BPF_STORE_REL:
+		reg = dst;
+		break;
+	default:
+		pr_err_once("unknown atomic load/store op code %02x\n", imm);
+		return -EINVAL;
+	}
+
+	if (off) {
+		emit_a64_add_i(1, tmp, reg, tmp, off, ctx);
+		reg = tmp;
+	}
+	if (arena) {
+		emit(A64_ADD(1, tmp, reg, arena_vm_base), ctx);
+		reg = tmp;
+	}
+
+	switch (imm) {
+	case BPF_LOAD_ACQ:
+		switch (BPF_SIZE(code)) {
+		case BPF_B:
+			emit(A64_LDARB(dst, reg), ctx);
+			break;
+		case BPF_H:
+			emit(A64_LDARH(dst, reg), ctx);
+			break;
+		case BPF_W:
+			emit(A64_LDAR32(dst, reg), ctx);
+			break;
+		case BPF_DW:
+			emit(A64_LDAR64(dst, reg), ctx);
+			break;
+		}
+		break;
+	case BPF_STORE_REL:
+		switch (BPF_SIZE(code)) {
+		case BPF_B:
+			emit(A64_STLRB(src, reg), ctx);
+			break;
+		case BPF_H:
+			emit(A64_STLRH(src, reg), ctx);
+			break;
+		case BPF_W:
+			emit(A64_STLR32(src, reg), ctx);
+			break;
+		case BPF_DW:
+			emit(A64_STLR64(src, reg), ctx);
+			break;
+		}
+		break;
+	default:
+		pr_err_once("unexpected atomic load/store op code %02x\n",
+			    imm);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 #ifdef CONFIG_ARM64_LSE_ATOMICS
 static int emit_lse_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx)
 {
@@ -1641,11 +1716,17 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 			return ret;
 		break;
 
+	case BPF_STX | BPF_ATOMIC | BPF_B:
+	case BPF_STX | BPF_ATOMIC | BPF_H:
 	case BPF_STX | BPF_ATOMIC | BPF_W:
 	case BPF_STX | BPF_ATOMIC | BPF_DW:
+	case BPF_STX | BPF_PROBE_ATOMIC | BPF_B:
+	case BPF_STX | BPF_PROBE_ATOMIC | BPF_H:
 	case BPF_STX | BPF_PROBE_ATOMIC | BPF_W:
 	case BPF_STX | BPF_PROBE_ATOMIC | BPF_DW:
-		if (cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
+		if (bpf_atomic_is_load_store(insn))
+			ret = emit_atomic_ld_st(insn, ctx);
+		else if (cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
 			ret = emit_lse_atomic(insn, ctx);
 		else
 			ret = emit_ll_sc_atomic(insn, ctx);
@@ -2667,13 +2748,10 @@ bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena)
 	if (!in_arena)
 		return true;
 	switch (insn->code) {
-	case BPF_STX | BPF_ATOMIC | BPF_B:
-	case BPF_STX | BPF_ATOMIC | BPF_H:
 	case BPF_STX | BPF_ATOMIC | BPF_W:
 	case BPF_STX | BPF_ATOMIC | BPF_DW:
-		if (bpf_atomic_is_load_store(insn))
-			return false;
-		if (!cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
+		if (!bpf_atomic_is_load_store(insn) &&
+		    !cpus_have_cap(ARM64_HAS_LSE_ATOMICS))
 			return false;
 	}
 	return true;