bpf/arm64: Fix BPF_ST into arena memory

The arm64 JIT supports BPF_ST with BPF_PROBE_MEM32 (arena) by using the
tmp2 register to hold the dst + arena_vm_base value and using tmp2 as the
new dst register. But this is broken because in case is_lsi_offset()
returns false the tmp2 will be clobbered by emit_a64_mov_i(1, tmp2, off,
ctx); and hence the emitted store instruction will be of the form:
	strb    w10, [x11, x11]
Fix this by using the third temporary register to hold the dst +
arena_vm_base.

Fixes: 339af57 ("bpf: Add arm64 JIT support for PROBE_MEM32 pseudo instructions.")
Signed-off-by: Puranjay Mohan <puranjay@kernel.org>
Link: https://lore.kernel.org/r/20251030121715.55214-1-puranjay@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Author: puranjaymohan

arch/arm64/net/bpf_jit_comp.c

@@ -1213,6 +1213,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 	u8 src = bpf2a64[insn->src_reg];
 	const u8 tmp = bpf2a64[TMP_REG_1];
 	const u8 tmp2 = bpf2a64[TMP_REG_2];
+	const u8 tmp3 = bpf2a64[TMP_REG_3];
 	const u8 fp = bpf2a64[BPF_REG_FP];
 	const u8 arena_vm_base = bpf2a64[ARENA_VM_START];
 	const u8 priv_sp = bpf2a64[PRIVATE_SP];
@@ -1757,8 +1758,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 	case BPF_ST | BPF_PROBE_MEM32 | BPF_W:
 	case BPF_ST | BPF_PROBE_MEM32 | BPF_DW:
 		if (BPF_MODE(insn->code) == BPF_PROBE_MEM32) {
-			emit(A64_ADD(1, tmp2, dst, arena_vm_base), ctx);
-			dst = tmp2;
+			emit(A64_ADD(1, tmp3, dst, arena_vm_base), ctx);
+			dst = tmp3;
 		}
 		if (dst == fp) {
 			dst_adj = ctx->priv_sp_used ? priv_sp : A64_SP;