Re: [PATCH v2 14/18] IOMMU: fold flush-all hook into "flush one"

2021-12-21 Thread Jan Beulich
On 16.12.2021 12:30, Rahul Singh wrote: >> On 24 Sep 2021, at 10:53 am, Jan Beulich wrote: >> >> Having a separate flush-all hook has always been puzzling me some. We >> will want to be able to force a full flush via accumulated flush flags >> from the map/unmap functions. Introduce a respective n

Re: [PATCH v2 14/18] IOMMU: fold flush-all hook into "flush one"

2021-12-17 Thread Julien Grall
On 24/09/2021 10:53, Jan Beulich wrote: Having a separate flush-all hook has always been puzzling me some. We will want to be able to force a full flush via accumulated flush flags from the map/unmap functions. Introduce a respective new flag and fold all flush handling to use the single remai

Re: [PATCH v2 14/18] IOMMU: fold flush-all hook into "flush one"

2021-12-16 Thread Rahul Singh
Hi Jan > On 24 Sep 2021, at 10:53 am, Jan Beulich wrote: > > Having a separate flush-all hook has always been puzzling me some. We > will want to be able to force a full flush via accumulated flush flags > from the map/unmap functions. Introduce a respective new flag and fold > all flush handlin

Re: [PATCH v2 14/18] IOMMU: fold flush-all hook into "flush one"

2021-12-16 Thread Oleksandr
On 16.12.21 10:49, Jan Beulich wrote: Hi Jan On 15.12.2021 16:28, Oleksandr wrote: On 24.09.21 12:53, Jan Beulich wrote: Having a separate flush-all hook has always been puzzling me some. We will want to be able to force a full flush via accumulated flush flags from the map/unmap functions

Re: [PATCH v2 14/18] IOMMU: fold flush-all hook into "flush one"

2021-12-16 Thread Jan Beulich
On 15.12.2021 16:28, Oleksandr wrote: > On 24.09.21 12:53, Jan Beulich wrote: >> Having a separate flush-all hook has always been puzzling me some. We >> will want to be able to force a full flush via accumulated flush flags >> from the map/unmap functions. Introduce a respective new flag and fold

Re: [PATCH v2 14/18] IOMMU: fold flush-all hook into "flush one"

2021-12-15 Thread Oleksandr
On 24.09.21 12:53, Jan Beulich wrote: Hi Jan Having a separate flush-all hook has always been puzzling me some. We will want to be able to force a full flush via accumulated flush flags from the map/unmap functions. Introduce a respective new flag and fold all flush handling to use the single

Re: [PATCH v2 14/18] IOMMU: fold flush-all hook into "flush one"

2021-12-14 Thread Roger Pau Monné
On Tue, Dec 14, 2021 at 10:06:37AM +0100, Jan Beulich wrote: > On 13.12.2021 16:04, Roger Pau Monné wrote: > > On Fri, Sep 24, 2021 at 11:53:59AM +0200, Jan Beulich wrote: > >> Having a separate flush-all hook has always been puzzling me some. We > >> will want to be able to force a full flush via

Re: [PATCH v2 14/18] IOMMU: fold flush-all hook into "flush one"

2021-12-14 Thread Jan Beulich
On 13.12.2021 16:04, Roger Pau Monné wrote: > On Fri, Sep 24, 2021 at 11:53:59AM +0200, Jan Beulich wrote: >> Having a separate flush-all hook has always been puzzling me some. We >> will want to be able to force a full flush via accumulated flush flags >> from the map/unmap functions. Introduce a

Re: [PATCH v2 14/18] IOMMU: fold flush-all hook into "flush one"

2021-12-13 Thread Roger Pau Monné
On Fri, Sep 24, 2021 at 11:53:59AM +0200, Jan Beulich wrote: > Having a separate flush-all hook has always been puzzling me some. We > will want to be able to force a full flush via accumulated flush flags > from the map/unmap functions. Introduce a respective new flag and fold > all flush handling

[PATCH v2 14/18] IOMMU: fold flush-all hook into "flush one"

2021-09-24 Thread Jan Beulich
Having a separate flush-all hook has always been puzzling me some. We will want to be able to force a full flush via accumulated flush flags from the map/unmap functions. Introduce a respective new flag and fold all flush handling to use the single remaining hook. Note that because of the respecti