Re: Helping Wine use 64 bit Mesa OGL drivers for 32-bit Windows applications
On Oct 24, 2024, at 1:04 AM, Derek Lesho <dlesho(a)codeweavers.com> wrote:
In my last mail I responded to this approach all the way at the bottom, so it probably got lost: mremap on Linux as it exists now won't work as it only supports private anonymous mappings (in conjunction with MREMAP_DONTUNMAP), which GPU mappings are not.
This is seemingly not insurmountable: https://lore.kernel.org/linux-mm/20210303175235.3308220-1-bgeffon(a)google.c... ~Theodore
Wait, apparently this was fully merged in kernel 5.13? The man page is simply out of date. https://github.com/torvalds/linux/commit/a4609387859f0281951f5e476d9f76d7fb9... ~Theodore
On Oct 24, 2024, at 9:37 AM, tblodt(a)icloud.com wrote:
On Oct 24, 2024, at 1:04 AM, Derek Lesho <dlesho(a)codeweavers.com> wrote:
In my last mail I responded to this approach all the way at the bottom, so it probably got lost: mremap on Linux as it exists now won't work as it only supports private anonymous mappings (in conjunction with MREMAP_DONTUNMAP), which GPU mappings are not.
This is seemingly not insurmountable: https://lore.kernel.org/linux-mm/20210303175235.3308220-1-bgeffon(a)google.c...
~Theodore
Oh interesting, thanks for looking into this guys. As far as I understand it though, this is still not duplicating the mapping, but setting up a fault handler at the original address to manage access. I don't think we'd want this since when wine remaps the page/s hosting a given buffer it also forces all other resources mapped to the same page/s to go through this presumably slow fault handler. Am I missing something? Am 10/24/24 um 18:40 schrieb tblodt(a)icloud.com:
Wait, apparently this was fully merged in kernel 5.13? The man page is simply out of date. https://github.com/torvalds/linux/commit/a4609387859f0281951f5e476d9f76d7fb9...
~Theodore
On Oct 24, 2024, at 9:37 AM, tblodt(a)icloud.com wrote:
On Oct 24, 2024, at 1:04 AM, Derek Lesho <dlesho(a)codeweavers.com> wrote:
In my last mail I responded to this approach all the way at the bottom, so it probably got lost: mremap on Linux as it exists now won't work as it only supports private anonymous mappings (in conjunction with MREMAP_DONTUNMAP), which GPU mappings are not.
This is seemingly not insurmountable: https://lore.kernel.org/linux-mm/20210303175235.3308220-1-bgeffon(a)google.c...
~Theodore
participants (2)
-
Derek Lesho -
tblodt@icloud.com