bpf, arm64: Optimize AND,OR,XOR,JSET BPF_K using arm64 logical immediates

The current code for BPF_{AND,OR,XOR,JSET} BPF_K loads the immediate to
a temporary register before use.

This patch changes the code to avoid using a temporary register
when the BPF immediate is encodable using an arm64 logical immediate
instruction. If the encoding fails (due to the immediate not being
encodable), it falls back to using a temporary register.

Example of generated code for BPF_ALU32_IMM(BPF_AND, R0, 0x80000001):

without optimization:

  24: mov  w10, #0x8000ffff
  28: movk w10, #0x1
  2c: and  w7, w7, w10

with optimization:

  24: and  w7, w7, #0x80000001

Since the encoding process is quite complex, the JIT reuses existing
functionality in arch/arm64/kernel/insn.c for encoding logical immediates
rather than duplicate it in the JIT.

Co-developed-by: Xi Wang <xi.wang@gmail.com>
Signed-off-by: Xi Wang <xi.wang@gmail.com>
Signed-off-by: Luke Nelson <luke.r.nels@gmail.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/20200508181547.24783-3-luke.r.nels@gmail.com
Signed-off-by: Will Deacon <will@kernel.org>

arch/arm64/net/bpf_jit.h

@@ -189,4 +189,18 @@
 /* Rn & Rm; set condition flags */
 #define A64_TST(sf, Rn, Rm) A64_ANDS(sf, A64_ZR, Rn, Rm)
 
+/* Logical (immediate) */
+#define A64_LOGIC_IMM(sf, Rd, Rn, imm, type) ({ \
+	u64 imm64 = (sf) ? (u64)imm : (u64)(u32)imm; \
+	aarch64_insn_gen_logical_immediate(AARCH64_INSN_LOGIC_##type, \
+		A64_VARIANT(sf), Rn, Rd, imm64); \
+})
+/* Rd = Rn OP imm */
+#define A64_AND_I(sf, Rd, Rn, imm) A64_LOGIC_IMM(sf, Rd, Rn, imm, AND)
+#define A64_ORR_I(sf, Rd, Rn, imm) A64_LOGIC_IMM(sf, Rd, Rn, imm, ORR)
+#define A64_EOR_I(sf, Rd, Rn, imm) A64_LOGIC_IMM(sf, Rd, Rn, imm, EOR)
+#define A64_ANDS_I(sf, Rd, Rn, imm) A64_LOGIC_IMM(sf, Rd, Rn, imm, AND_SETFLAGS)
+/* Rn & imm; set condition flags */
+#define A64_TST_I(sf, Rn, imm) A64_ANDS_I(sf, A64_ZR, Rn, imm)
+
 #endif /* _BPF_JIT_H */

arch/arm64/net/bpf_jit_comp.c

@@ -356,6 +356,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 	const bool isdw = BPF_SIZE(code) == BPF_DW;
 	u8 jmp_cond, reg;
 	s32 jmp_offset;
+	u32 a64_insn;
 
 #define check_imm(bits, imm) do {				\
 	if ((((imm) > 0) && ((imm) >> (bits))) ||		\
@@ -488,18 +489,33 @@ emit_bswap_uxt:
 		break;
 	case BPF_ALU | BPF_AND | BPF_K:
 	case BPF_ALU64 | BPF_AND | BPF_K:
-		emit_a64_mov_i(is64, tmp, imm, ctx);
-		emit(A64_AND(is64, dst, dst, tmp), ctx);
+		a64_insn = A64_AND_I(is64, dst, dst, imm);
+		if (a64_insn != AARCH64_BREAK_FAULT) {
+			emit(a64_insn, ctx);
+		} else {
+			emit_a64_mov_i(is64, tmp, imm, ctx);
+			emit(A64_AND(is64, dst, dst, tmp), ctx);
+		}
 		break;
 	case BPF_ALU | BPF_OR | BPF_K:
 	case BPF_ALU64 | BPF_OR | BPF_K:
-		emit_a64_mov_i(is64, tmp, imm, ctx);
-		emit(A64_ORR(is64, dst, dst, tmp), ctx);
+		a64_insn = A64_ORR_I(is64, dst, dst, imm);
+		if (a64_insn != AARCH64_BREAK_FAULT) {
+			emit(a64_insn, ctx);
+		} else {
+			emit_a64_mov_i(is64, tmp, imm, ctx);
+			emit(A64_ORR(is64, dst, dst, tmp), ctx);
+		}
 		break;
 	case BPF_ALU | BPF_XOR | BPF_K:
 	case BPF_ALU64 | BPF_XOR | BPF_K:
-		emit_a64_mov_i(is64, tmp, imm, ctx);
-		emit(A64_EOR(is64, dst, dst, tmp), ctx);
+		a64_insn = A64_EOR_I(is64, dst, dst, imm);
+		if (a64_insn != AARCH64_BREAK_FAULT) {
+			emit(a64_insn, ctx);
+		} else {
+			emit_a64_mov_i(is64, tmp, imm, ctx);
+			emit(A64_EOR(is64, dst, dst, tmp), ctx);
+		}
 		break;
 	case BPF_ALU | BPF_MUL | BPF_K:
 	case BPF_ALU64 | BPF_MUL | BPF_K:
@@ -628,8 +644,13 @@ emit_cond_jmp:
 		goto emit_cond_jmp;
 	case BPF_JMP | BPF_JSET | BPF_K:
 	case BPF_JMP32 | BPF_JSET | BPF_K:
-		emit_a64_mov_i(is64, tmp, imm, ctx);
-		emit(A64_TST(is64, dst, tmp), ctx);
+		a64_insn = A64_TST_I(is64, dst, imm);
+		if (a64_insn != AARCH64_BREAK_FAULT) {
+			emit(a64_insn, ctx);
+		} else {
+			emit_a64_mov_i(is64, tmp, imm, ctx);
+			emit(A64_TST(is64, dst, tmp), ctx);
+		}
 		goto emit_cond_jmp;
 	/* function call */
 	case BPF_JMP | BPF_CALL: