Re: [PATCH v2 0/4] hw/pci: Convert rom_bar into OnOffAuto

2024-08-01 Thread Michael S. Tsirkin
On Thu, Aug 01, 2024 at 12:59:57PM +0200, Markus Armbruster wrote: > Akihiko Odaki writes: > > > On 2024/07/31 17:32, Markus Armbruster wrote: > >> Akihiko Odaki writes: > >> > >>> rom_bar is tristate but was defined as uint32_t so convert it into > >>> OnOffAuto to clarify that. For compatibil

Re: [PATCH v2 0/4] hw/pci: Convert rom_bar into OnOffAuto

2024-08-01 Thread Markus Armbruster
Akihiko Odaki writes: > On 2024/08/01 16:52, Michael S. Tsirkin wrote: >> On Thu, Aug 01, 2024 at 04:01:44PM +0900, Akihiko Odaki wrote: >>> rom_bar_set() and and underlying visit_type_str_preserving() are ugly, but >>> we can remove them once the deprecation period ends. On the other hand, if >>

Re: [PATCH v2 0/4] hw/pci: Convert rom_bar into OnOffAuto

2024-08-01 Thread Markus Armbruster
Akihiko Odaki writes: > On 2024/07/31 17:32, Markus Armbruster wrote: >> Akihiko Odaki writes: >> >>> rom_bar is tristate but was defined as uint32_t so convert it into >>> OnOffAuto to clarify that. For compatibility, a uint32 value set via >>> QOM will be converted into OnOffAuto. >>> >>> Sig

Re: [PATCH v2 0/4] hw/pci: Convert rom_bar into OnOffAuto

2024-08-01 Thread Akihiko Odaki
On 2024/08/01 16:52, Michael S. Tsirkin wrote: On Thu, Aug 01, 2024 at 04:01:44PM +0900, Akihiko Odaki wrote: rom_bar_set() and and underlying visit_type_str_preserving() are ugly, but we can remove them once the deprecation period ends. On the other hand, if we don't make this change, dev->opts

Re: [PATCH v2 0/4] hw/pci: Convert rom_bar into OnOffAuto

2024-08-01 Thread Michael S. Tsirkin
On Thu, Aug 01, 2024 at 04:01:44PM +0900, Akihiko Odaki wrote: > rom_bar_set() and and underlying visit_type_str_preserving() are ugly, but > we can remove them once the deprecation period ends. On the other hand, if > we don't make this change, dev->opts will keep floating around, and we will > ev

Re: [PATCH v2 0/4] hw/pci: Convert rom_bar into OnOffAuto

2024-08-01 Thread Akihiko Odaki
On 2024/07/31 17:32, Markus Armbruster wrote: Akihiko Odaki writes: rom_bar is tristate but was defined as uint32_t so convert it into OnOffAuto to clarify that. For compatibility, a uint32 value set via QOM will be converted into OnOffAuto. Signed-off-by: Akihiko Odaki I agree making prop

Re: [PATCH v2 0/4] hw/pci: Convert rom_bar into OnOffAuto

2024-07-31 Thread Michael S. Tsirkin
On Wed, Jul 31, 2024 at 10:32:19AM +0200, Markus Armbruster wrote: > Whether it would be worth your trouble and mine just to clean up > "rombar" seems highly dubious, though. Exactly. -- MST

Re: [PATCH v2 0/4] hw/pci: Convert rom_bar into OnOffAuto

2024-07-31 Thread Markus Armbruster
Akihiko Odaki writes: > rom_bar is tristate but was defined as uint32_t so convert it into > OnOffAuto to clarify that. For compatibility, a uint32 value set via > QOM will be converted into OnOffAuto. > > Signed-off-by: Akihiko Odaki I agree making property "rombar" an integer was a design mis

[PATCH v2 0/4] hw/pci: Convert rom_bar into OnOffAuto

2024-07-14 Thread Akihiko Odaki
rom_bar is tristate but was defined as uint32_t so convert it into OnOffAuto to clarify that. For compatibility, a uint32 value set via QOM will be converted into OnOffAuto. Signed-off-by: Akihiko Odaki --- Changes in v2: - Documented in docs/about/deprecated.rst (Daniel P. Berrangé) - Link to v1