bpf, arm: Optimize ALU ARSH K using asr immediate instruction

This patch adds an optimization that uses the asr immediate instruction
for BPF_ALU BPF_ARSH BPF_K, rather than loading the immediate to
a temporary register. This is similar to existing code for handling
BPF_ALU BPF_{LSH,RSH} BPF_K. This optimization saves two instructions
and is more consistent with LSH and RSH.

Example of the code generated for BPF_ALU32_IMM(BPF_ARSH, BPF_REG_0, 5)
before the optimization:

2c: mov r8, #5
30: mov r9, #0
34: asr r0, r0, r8

and after optimization:

2c: asr r0, r0, #5

Tested on QEMU using lib/test_bpf and test_verifier.

Co-developed-by: Xi Wang <[e-mail]>
Signed-off-by: Xi Wang <[e-mail]>
Signed-off-by: Luke Nelson <[e-mail]>
Signed-off-by: Daniel Borkmann <[e-mail]>
Link: https://lore.kernel.org/bpf/[e-mail]

arch/arm/net/bpf_jit_32.c

···
 	case BPF_RSH:
 		emit(ARM_LSR_I(rd, rd, val), ctx);
 		break;
+	case BPF_ARSH:
+		emit(ARM_ASR_I(rd, rd, val), ctx);
+		break;
 	case BPF_NEG:
 		emit(ARM_RSB_I(rd, rd, val), ctx);
 		break;
···
 	case BPF_ALU | BPF_MUL | BPF_X:
 	case BPF_ALU | BPF_LSH | BPF_X:
 	case BPF_ALU | BPF_RSH | BPF_X:
-	case BPF_ALU | BPF_ARSH | BPF_K:
 	case BPF_ALU | BPF_ARSH | BPF_X:
 	case BPF_ALU64 | BPF_ADD | BPF_K:
 	case BPF_ALU64 | BPF_ADD | BPF_X:
···
 	case BPF_ALU64 | BPF_MOD | BPF_K:
 	case BPF_ALU64 | BPF_MOD | BPF_X:
 		goto notyet;
-	/* dst = dst >> imm */
 	/* dst = dst << imm */
-	case BPF_ALU | BPF_RSH | BPF_K:
+	/* dst = dst >> imm */
+	/* dst = dst >> imm (signed) */
 	case BPF_ALU | BPF_LSH | BPF_K:
+	case BPF_ALU | BPF_RSH | BPF_K:
+	case BPF_ALU | BPF_ARSH | BPF_K:
 		if (unlikely(imm > 31))
 			return -EINVAL;
 		if (imm)

arch/arm/net/bpf_jit_32.h

···
 #define ARM_INST_LSR_I		0x01a00020
 #define ARM_INST_LSR_R		0x01a00030
 
+#define ARM_INST_ASR_I		0x01a00040
+#define ARM_INST_ASR_R		0x01a00050
+
 #define ARM_INST_MOV_R		0x01a00000
 #define ARM_INST_MOVS_R		0x01b00000
 #define ARM_INST_MOV_I		0x03a00000