bpf, arm64: implement jiting of BPF_XADD

This work adds BPF_XADD for BPF_W/BPF_DW to the arm64 JIT and therefore
completes JITing of all BPF instructions, meaning we can thus also remove
the 'notyet' label and do not need to fall back to the interpreter when
BPF_XADD is used in a program!

This now also brings arm64 JIT in line with x86_64, s390x, ppc64, sparc64,
where all current eBPF features are supported.

BPF_W example from test_bpf:

  .u.insns_int = {
    BPF_ALU32_IMM(BPF_MOV, R0, 0x12),
    BPF_ST_MEM(BPF_W, R10, -40, 0x10),
    BPF_STX_XADD(BPF_W, R10, R0, -40),
    BPF_LDX_MEM(BPF_W, R0, R10, -40),
    BPF_EXIT_INSN(),
  },

  [...]
  00000020:  52800247  mov w7, #0x12 // #18
  00000024:  928004eb  mov x11, #0xffffffffffffffd8 // #-40
  00000028:  d280020a  mov x10, #0x10 // #16
  0000002c:  b82b6b2a  str w10, [x25,x11]
  // start of xadd mapping:
  00000030:  928004ea  mov x10, #0xffffffffffffffd8 // #-40
  00000034:  8b19014a  add x10, x10, x25
  00000038:  f9800151  prfm pstl1strm, [x10]
  0000003c:  885f7d4b  ldxr w11, [x10]
  00000040:  0b07016b  add w11, w11, w7
  00000044:  880b7d4b  stxr w11, w11, [x10]
  00000048:  35ffffab  cbnz w11, 0x0000003c
  // end of xadd mapping:
  [...]

BPF_DW example from test_bpf:

  .u.insns_int = {
    BPF_ALU32_IMM(BPF_MOV, R0, 0x12),
    BPF_ST_MEM(BPF_DW, R10, -40, 0x10),
    BPF_STX_XADD(BPF_DW, R10, R0, -40),
    BPF_LDX_MEM(BPF_DW, R0, R10, -40),
    BPF_EXIT_INSN(),
  },

  [...]
  00000020:  52800247  mov w7,  #0x12 // #18
  00000024:  928004eb  mov x11, #0xffffffffffffffd8 // #-40
  00000028:  d280020a  mov x10, #0x10 // #16
  0000002c:  f82b6b2a  str x10, [x25,x11]
  // start of xadd mapping:
  00000030:  928004ea  mov x10, #0xffffffffffffffd8 // #-40
  00000034:  8b19014a  add x10, x10, x25
  00000038:  f9800151  prfm pstl1strm, [x10]
  0000003c:  c85f7d4b  ldxr x11, [x10]
  00000040:  8b07016b  add x11, x11, x7
  00000044:  c80b7d4b  stxr w11, x11, [x10]
  00000048:  35ffffab  cbnz w11, 0x0000003c
  // end of xadd mapping:
  [...]

Tested on Cavium ThunderX ARMv8, test suite results after the patch:

  No JIT:   [ 3751.855362] test_bpf: Summary: 311 PASSED, 0 FAILED, [0/303 JIT'ed]
  With JIT: [ 3573.759527] test_bpf: Summary: 311 PASSED, 0 FAILED, [303/303 JIT'ed]

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 30 insertions, 5 deletions

diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h
index 7c16e547ccb2..b02a9268dfbf 100644
--- a/arch/arm64/net/bpf_jit.h
+++ b/arch/arm64/net/bpf_jit.h
@@ -83,6 +83,25 @@
 /* Rt = Rn[0]; Rt2 = Rn[8]; Rn += 16; */
 #define A64_POP(Rt, Rt2, Rn)  A64_LS_PAIR(Rt, Rt2, Rn, 16, LOAD, POST_INDEX)
 
+/* Load/store exclusive */
+#define A64_SIZE(sf) \
+	((sf) ? AARCH64_INSN_SIZE_64 : AARCH64_INSN_SIZE_32)
+#define A64_LSX(sf, Rt, Rn, Rs, type) \
+	aarch64_insn_gen_load_store_ex(Rt, Rn, Rs, A64_SIZE(sf), \
+				       AARCH64_INSN_LDST_##type)
+/* Rt = [Rn]; (atomic) */
+#define A64_LDXR(sf, Rt, Rn) \
+	A64_LSX(sf, Rt, Rn, A64_ZR, LOAD_EX)
+/* [Rn] = Rt; (atomic) Rs = [state] */
+#define A64_STXR(sf, Rt, Rn, Rs) \
+	A64_LSX(sf, Rt, Rn, Rs, STORE_EX)
+
+/* Prefetch */
+#define A64_PRFM(Rn, type, target, policy) \
+	aarch64_insn_gen_prefetch(Rn, AARCH64_INSN_PRFM_TYPE_##type, \
+				  AARCH64_INSN_PRFM_TARGET_##target, \
+				  AARCH64_INSN_PRFM_POLICY_##policy)
+
 /* Add/subtract (immediate) */
 #define A64_ADDSUB_IMM(sf, Rd, Rn, imm12, type) \
 	aarch64_insn_gen_add_sub_imm(Rd, Rn, imm12, \
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 304736870dca..4f2b35130f3c 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -321,6 +321,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	const s32 imm = insn->imm;
 	const int i = insn - ctx->prog->insnsi;
 	const bool is64 = BPF_CLASS(code) == BPF_ALU64;
+	const bool isdw = BPF_SIZE(code) == BPF_DW;
 	u8 jmp_cond;
 	s32 jmp_offset;
 
@@ -681,7 +682,16 @@ emit_cond_jmp:
 	case BPF_STX | BPF_XADD | BPF_W:
 	/* STX XADD: lock *(u64 *)(dst + off) += src */
 	case BPF_STX | BPF_XADD | BPF_DW:
-		goto notyet;
+		emit_a64_mov_i(1, tmp, off, ctx);
+		emit(A64_ADD(1, tmp, tmp, dst), ctx);
+		emit(A64_PRFM(tmp, PST, L1, STRM), ctx);
+		emit(A64_LDXR(isdw, tmp2, tmp), ctx);
+		emit(A64_ADD(isdw, tmp2, tmp2, src), ctx);
+		emit(A64_STXR(isdw, tmp2, tmp, tmp2), ctx);
+		jmp_offset = -3;
+		check_imm19(jmp_offset);
+		emit(A64_CBNZ(0, tmp2, jmp_offset), ctx);
+		break;
 
 	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */
 	case BPF_LD | BPF_ABS | BPF_W:
@@ -748,10 +758,6 @@ emit_cond_jmp:
 		}
 		break;
 	}
-notyet:
-		pr_info_once("*** NOT YET: opcode %02x ***\n", code);
-		return -EFAULT;
-
 	default:
 		pr_err_once("unknown opcode %02x\n", code);
 		return -EINVAL;