libbpf: Usdt aarch64 arg parsing support

Parsing of USDT arguments is architecture-specific. On aarch64 it is
relatively easy since registers used are x[0-31] and sp. Format is
slightly different compared to x86_64. Possible forms are:

- "size@[reg[,offset]]" for dereferences, e.g. "-8@[sp,76]" and "-4@[sp]";
- "size@reg" for register values, e.g. "-4@x0";
- "size@value" for raw values, e.g. "-8@1".

Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/1649690496-1902-2-git-send-email-alan.maguire@oracle.com

tools/lib/bpf/usdt.c

@@ -1324,6 +1324,82 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 	return len;
 }
 
+#elif defined(__aarch64__)
+
+static int calc_pt_regs_off(const char *reg_name)
+{
+	int reg_num;
+
+	if (sscanf(reg_name, "x%d", &reg_num) == 1) {
+		if (reg_num >= 0 && reg_num < 31)
+			return offsetof(struct user_pt_regs, regs[reg_num]);
+	} else if (strcmp(reg_name, "sp") == 0) {
+		return offsetof(struct user_pt_regs, sp);
+	}
+	pr_warn("usdt: unrecognized register '%s'\n", reg_name);
+	return -ENOENT;
+}
+
+static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)
+{
+	char *reg_name = NULL;
+	int arg_sz, len, reg_off;
+	long off;
+
+	if (sscanf(arg_str, " %d @ \[ %m[a-z0-9], %ld ] %n", &arg_sz, &reg_name, &off, &len) == 3) {
+		/* Memory dereference case, e.g., -4@[sp, 96] */
+		arg->arg_type = USDT_ARG_REG_DEREF;
+		arg->val_off = off;
+		reg_off = calc_pt_regs_off(reg_name);
+		free(reg_name);
+		if (reg_off < 0)
+			return reg_off;
+		arg->reg_off = reg_off;
+	} else if (sscanf(arg_str, " %d @ \[ %m[a-z0-9] ] %n", &arg_sz, &reg_name, &len) == 2) {
+		/* Memory dereference case, e.g., -4@[sp] */
+		arg->arg_type = USDT_ARG_REG_DEREF;
+		arg->val_off = 0;
+		reg_off = calc_pt_regs_off(reg_name);
+		free(reg_name);
+		if (reg_off < 0)
+			return reg_off;
+		arg->reg_off = reg_off;
+	} else if (sscanf(arg_str, " %d @ %ld %n", &arg_sz, &off, &len) == 2) {
+		/* Constant value case, e.g., 4@5 */
+		arg->arg_type = USDT_ARG_CONST;
+		arg->val_off = off;
+		arg->reg_off = 0;
+	} else if (sscanf(arg_str, " %d @ %m[a-z0-9] %n", &arg_sz, &reg_name, &len) == 2) {
+		/* Register read case, e.g., -8@x4 */
+		arg->arg_type = USDT_ARG_REG;
+		arg->val_off = 0;
+		reg_off = calc_pt_regs_off(reg_name);
+		free(reg_name);
+		if (reg_off < 0)
+			return reg_off;
+		arg->reg_off = reg_off;
+	} else {
+		pr_warn("usdt: unrecognized arg #%d spec '%s'\n", arg_num, arg_str);
+		return -EINVAL;
+	}
+
+	arg->arg_signed = arg_sz < 0;
+	if (arg_sz < 0)
+		arg_sz = -arg_sz;
+
+	switch (arg_sz) {
+	case 1: case 2: case 4: case 8:
+		arg->arg_bitshift = 64 - arg_sz * 8;
+		break;
+	default:
+		pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n",
+			arg_num, arg_str, arg_sz);
+		return -EINVAL;
+	}
+
+	return len;
+}
+
 #else
 
 static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)