On Wed, 2025-01-29 at 11:52 -0800, Matthew Brost wrote:
> Migration is implemented with range granularity, with VRAM backing
> being
> a VM private TTM BO (i.e., shares dma-resv with VM). The lifetime of
> the
> TTM BO is limited to when the SVM range is in VRAM (i.e., when a VRAM
> SVM range is mi
On Thu, Jan 30, 2025 at 07:51:49PM +0100, Thomas Hellström wrote:
> On Thu, 2025-01-30 at 09:31 -0800, Matthew Brost wrote:
> > On Thu, Jan 30, 2025 at 04:56:39PM +, Matthew Auld wrote:
> > > On 30/01/2025 16:32, Matthew Brost wrote:
> > > > On Thu, Jan 30, 2025 at 02:22:55PM +, Matthew Aul
On Thu, 2025-01-30 at 09:31 -0800, Matthew Brost wrote:
> On Thu, Jan 30, 2025 at 04:56:39PM +, Matthew Auld wrote:
> > On 30/01/2025 16:32, Matthew Brost wrote:
> > > On Thu, Jan 30, 2025 at 02:22:55PM +, Matthew Auld wrote:
> > > > On 29/01/2025 19:52, Matthew Brost wrote:
> > > > > Migra
On Thu, Jan 30, 2025 at 04:56:39PM +, Matthew Auld wrote:
> On 30/01/2025 16:32, Matthew Brost wrote:
> > On Thu, Jan 30, 2025 at 02:22:55PM +, Matthew Auld wrote:
> > > On 29/01/2025 19:52, Matthew Brost wrote:
> > > > Migration is implemented with range granularity, with VRAM backing bein
On 30/01/2025 16:32, Matthew Brost wrote:
On Thu, Jan 30, 2025 at 02:22:55PM +, Matthew Auld wrote:
On 29/01/2025 19:52, Matthew Brost wrote:
Migration is implemented with range granularity, with VRAM backing being
a VM private TTM BO (i.e., shares dma-resv with VM). The lifetime of the
TTM
On Thu, 2025-01-30 at 08:32 -0800, Matthew Brost wrote:
> On Thu, Jan 30, 2025 at 02:22:55PM +, Matthew Auld wrote:
> > On 29/01/2025 19:52, Matthew Brost wrote:
> > > Migration is implemented with range granularity, with VRAM
> > > backing being
> > > a VM private TTM BO (i.e., shares dma-resv
On Thu, Jan 30, 2025 at 02:22:55PM +, Matthew Auld wrote:
> On 29/01/2025 19:52, Matthew Brost wrote:
> > Migration is implemented with range granularity, with VRAM backing being
> > a VM private TTM BO (i.e., shares dma-resv with VM). The lifetime of the
> > TTM BO is limited to when the SVM r
On 29/01/2025 19:52, Matthew Brost wrote:
Migration is implemented with range granularity, with VRAM backing being
a VM private TTM BO (i.e., shares dma-resv with VM). The lifetime of the
TTM BO is limited to when the SVM range is in VRAM (i.e., when a VRAM
SVM range is migrated to SRAM, the TTM
