Re: [PATCH v1 2/5] firmware: Basic dmi-sysfs support

Overall, this looks great, just a few minor comments below:

On Thu, Feb 17, 2011 at 01:28:05PM -0800, Mike Waychison wrote:

+config DMI_SYSFS
+	tristate "DMI table support in sysfs"
+	depends on SYSFS && DMI
+	default X86

Huh?  Default should be 'N' for any new feature, unless it keeps your
machine from booting.

I think you want this option to depend on X86 though, right?

+	help
+	  Say Y or M here to enable the exporting of the raw DMI table
+	  data via sysfs.  This is useful for consuming the data without
+	  requiring any access to /dev/mem at all.  Tables are found
+	  under /sys/firmware/dmi when this option is enabled and
+	  loaded.

I just realized (due to other work I'm doing on a laptop) that we have a
bunch of entries today in /sys/class/dmi/id which is a pointer to the
dmi "device".

Now I think this really is different (these are the raw DMI tables), but
this doesn't have anything to do with that code, right?

+ *
+ * Copyright 2010 Google, Inc.

It's 2011 :)

+static int __init dmi_sysfs_init(void)
+{
+	int error = -ENOMEM;
+	int val;
+
+	/* Set up our directory */
+	dmi_kobj = kobject_create_and_add("dmi", firmware_kobj);
+	if (!dmi_kobj)
+		goto err;
+
+	dmi_kset = kset_create_and_add("entries", NULL, dmi_kobj);
+	if (!dmi_kset)
+		goto err;
+
+	val = 0;
+	error = dmi_walk(dmi_sysfs_register_handle, &val);
+	if (error)
+		goto err;
+	if (val) {
+		error = val;
+		goto err;
+	}
+
+	pr_info("dmi-sysfs: loaded.\n");

Is this really needed?  pr_dbg() instead please?

+
+	return 0;
+err:
+	cleanup_entry_list();
+	kset_unregister(dmi_kset);
+	kobject_put(dmi_kobj);
+	return error;
+}
+
+/* clean up everything. */
+static void __exit dmi_sysfs_exit(void)
+{
+	pr_info("dmi-sysfs: unloading.\n");
+	cleanup_entry_list();
+	kset_unregister(dmi_kset);
+	kobject_put(dmi_kobj);
+}
+
+module_init(dmi_sysfs_init);
+module_exit(dmi_sysfs_exit);
+
+MODULE_AUTHOR("Google, Inc.");

You don't want your name here?

thanks,

greg k-h