Am 03.02.21 um 12:26 schrieb Daniel Vetter:
On Thu, Jan 28, 2021 at 02:16:02PM +0100, Christian König wrote:
TTM implements a rather extensive accounting of allocated memory.
There are two reasons for this:
1. It tries to block userspace allocating a huge number of very small
BOs without
On Thu, Jan 28, 2021 at 02:16:02PM +0100, Christian König wrote:
> TTM implements a rather extensive accounting of allocated memory.
>
> There are two reasons for this:
> 1. It tries to block userspace allocating a huge number of very small
>BOs without accounting for the kmalloced memory.
>
TTM implements a rather extensive accounting of allocated memory.
There are two reasons for this:
1. It tries to block userspace allocating a huge number of very small
BOs without accounting for the kmalloced memory.
2. Make sure we don't over allocate and run into an OOM situation
during
TTM implements a rather extensive accounting of allocated memory.
There are two reasons for this:
1. It tries to block userspace allocating a huge number of very small
BOs without accounting for the kmalloced memory.
2. Make sure we don't over allocate and run into an OOM situation
during
Hi Daniel,
just in case you read that when you come back from vacation.
I've tested this quite extensively and apart from the typo in the KFD in
patch #3 it looks pretty solid now.
E.g. no lockdep or KASAN splat when I use the debugfs stuff. Is this
sufficient?
Thanks,
Christian.
Am
TTM implements a rather extensive accounting of allocated memory.
There are two reasons for this:
1. It tries to block userspace allocating a huge number of very small
BOs without accounting for the kmalloced memory.
2. Make sure we don't over allocate and run into an OOM situation
during