On Tuesday, August 06, 2013 11:12:51 AM Yasuaki Ishimatsu wrote: > (2013/08/06 9:15), Rafael J. Wysocki wrote: > > On Monday, August 05, 2013 05:19:56 PM Toshi Kani wrote: > >> On Mon, 2013-08-05 at 15:14 +0200, Rafael J. Wysocki wrote: > >> : > >>> Can you please test the appended patch? I tested it somewhat, but since the > >>> greatest number of physical nodes per ACPI device object I can get on my test > >>> machines is 2 (and even that after hacking the kernel somewhat), that was kind > >>> of unconclusive. > >>> > >>> Thanks, > >>> Rafael > >>> > >>> > >>> --- > >>> From: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx> > >>> Subject: ACPI: Drop physical_node_id_bitmap from struct acpi_device > >>> > >>> The physical_node_id_bitmap in struct acpi_device is only used for > >>> looking up the first currently unused phyiscal dependent node ID > >>> by acpi_bind_one(). It is not really necessary, however, because > >>> acpi_bind_one() walks the entire physical_node_list of the given > >>> device object for sanity checking anyway and if that list is always > >>> sorted by node_id, it is straightforward to find the first gap > >>> between the currently used node IDs and use that number as the ID > >>> of the new list node. > >>> > >>> This also removes the artificial limit of the maximum number of > >>> dependent physical devices per ACPI device object, which now depends > >>> only on the capacity of unsigend int. > >>> > >>> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx> > >> > >> I like the change. Much better :-) > >> > >> Acked-by: Toshi Kani <toshi.kani@xxxxxx> > > > > However, it introduces a bug in acpi_unbind_one(), because the size of the name > > array in there has to be increased too. Updated patch follows. > > > > Thanks, > > Rafael > > > > > > --- > > From: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx> > > Subject: ACPI: Drop physical_node_id_bitmap from struct acpi_device > > > > The physical_node_id_bitmap in struct acpi_device is only used for > > looking up the first currently unused dependent phyiscal node ID > > by acpi_bind_one(). It is not really necessary, however, because > > acpi_bind_one() walks the entire physical_node_list of the given > > device object for sanity checking anyway and if that list is always > > sorted by node_id, it is straightforward to find the first gap > > between the currently used node IDs and use that number as the ID > > of the new list node. > > > > This also removes the artificial limit of the maximum number of > > dependent physical devices per ACPI device object, which now depends > > only on the capacity of unsigend int. > > > > Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx> > > Reviewed-by: Yasuaki Ishimatsu <isimatu.yasuaki@xxxxxxxxxxxxxx> > Tested-by: Yasuaki Ishimatsu <isimatu.yasuaki@xxxxxxxxxxxxxx> > > I confirmed that I can add and remove a memory device correctly. Great, thanks for the confirmation! Rafael -- To unsubscribe from this list: send the line "unsubscribe linux-acpi" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
