Am Sonntag, dem 23.03.2025 um 17:51 +1100 schrieb Balbir Singh:
> On 3/22/25 23:23, Bert Karwatzki wrote:
> > The problem occurs in this part of ttm_tt_populate(), in the nokaslr case
> > the loop is entered and repeatedly run because ttm_dma32_pages allocated
>
/
Signed-off-by: Bert Karwatzki
---
drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 3 ++-
include/linux/ioport.h | 3 +++
kernel/resource.c| 31 ++--
3 files changed, 28 insertions(+), 9 deletions(-)
diff --git a/drivers/gpu/drm/amd
Am Mittwoch, dem 26.03.2025 um 15:58 -0700 schrieb Linus Torvalds:
> On Wed, 26 Mar 2025 at 15:00, Bert Karwatzki wrote:
> >
> > As Balbir Singh found out this memory comes from amdkfd
> > (kgd2kfd_init_zone_device()) with CONFIG_HSA_AMD_SVM=y. The memory ge
Am Dienstag, dem 25.03.2025 um 13:23 +0100 schrieb Christian König:
> Am 25.03.25 um 11:14 schrieb Bert Karwatzki:
> > My /proc/iomem contans two memory areas of 8G size which are
> > belonging to PCI :03:00.0, one of the is the BAR reported by dmesg
> > [ 0.312692] [
Am Mittwoch, dem 26.03.2025 um 12:50 +1100 schrieb Balbir Singh:
> On 3/26/25 10:43, Balbir Singh wrote:
> > On 3/26/25 10:21, Bert Karwatzki wrote:
> > > Am Mittwoch, dem 26.03.2025 um 09:45 +1100 schrieb Balbir Singh:
> > > >
> > > >
> > > &g
Am Mittwoch, dem 26.03.2025 um 21:36 +1100 schrieb Balbir Singh:
> On 3/26/25 21:10, Bert Karwatzki wrote:
> > Am Mittwoch, dem 26.03.2025 um 12:50 +1100 schrieb Balbir Singh:
> > > On 3/26/25 10:43, Balbir Singh wrote:
> > > > On 3/26/25 10:21, Bert Karwatzki wro
03:00.0: kfd_migrate: kgd2kfd_init_zone_device:
range.start = 0x3ffe ranges.end = 0x3fff
Bert Karwatzki
fe30403fff : :04:00.0
fe30404000-fe30404fff : :04:00.0
afe-aff : :03:00.0 This is the memory which shifts with
nokaslr
Bert Karwatzki
ases
(c) In the non-working case amdgpu_gtt_mgr_del() is called far more often then
in the working case:
Non-working case (cmdline: nokaslr) 834 calls to amdgpu_gtt_mgt_del()
Working case (cmdline: nokaslr amdgpu.vramlimit=512) 51 calls to
amdgpu_gtt_mgr_del()
Working case (cmdline: no additional arguments) 44 calls to amdgpu_gtt_mgr_del()
Bert Karwatzki
&amdgpu_bo_driver, adev->dev,
adev_to_drm(adev)->anon_inode->i_mapping,
adev_to_drm(adev)->vma_offset_manager,
adev->need_swiotlb,
false /* use_dma32 */);
if (r) {
DRM_ERROR("failed initializing buffer object driver(%d).\n", r);
return r;
}
Bert Karwatzki
D case ttm_global_swapout() is called
585 times leading to 54495 calls to ttm_bo_swapout_cb() while in the GOOD both
function are called 0 times.
Bert Karwatzki
Am Sonntag, dem 16.03.2025 um 14:09 +0100 schrieb Bert Karwatzki:
> This is related to the admgpu.gttsize. My laptop has the maximum amount
> of memory (64G) and usually gttsize is half of main memory size. I just
> tested with cmdline="nokaslr amdgpi.gttsize=2048" and the
GOOD
64000 GOOD
So for the discrete GPU increasing gttsize does no reproduce the bug.
Bert Karwatzki
Am Samstag, dem 15.03.2025 um 00:34 +1100 schrieb Balbir Singh:
> On 3/14/25 17:14, Balbir Singh wrote:
> > On 3/14/25 09:22, Bert Karwatzki wrote:
> > > Am Freitag, dem 14.03.2025 um 08:54 +1100 schrieb Balbir Singh:
> > > > On 3/14/25 05:12, Bert Karwatzki wrote
Am Freitag, dem 14.03.2025 um 08:54 +1100 schrieb Balbir Singh:
> On 3/14/25 05:12, Bert Karwatzki wrote:
> > Am Donnerstag, dem 13.03.2025 um 22:47 +1100 schrieb Balbir Singh:
> > >
> > >
> > > Anyway, I think the nokaslr result is interesting, it seems lik
_dm/amdgpu_dm.c | 52
+++-
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h | 2 ++
3 files changed, 53 insertions(+), 5 deletions(-)
Bert Karwatzki
radeon_atpx.
Fixes: https://gitlab.freedesktop.org/drm/amd/-/issues/2744
Signed-off-by: Bert Karwatzki
---
.../gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c | 40 +--
drivers/gpu/drm/radeon/radeon_atpx_handler.c | 30 +++---
2 files changed, 32 insertions(+), 38 deletions
> Regards,
> > Guchun
> >
> > -Original Message-
> > From: amd-gfx On Behalf Of
> > Bert Karwatzki
> > Sent: Friday, February 24, 2023 4:52 AM
> > To: amd-gfx@lists.freedesktop.org
> > Subject: Re: [PATCH] drm/amd: use drm_kms_helper_poll
> Regards,
> > Guchun
> >
> > -Original Message-
> > From: amd-gfx On Behalf Of
> > Bert Karwatzki
> > Sent: Friday, February 24, 2023 4:52 AM
> > To: amd-gfx@lists.freedesktop.org
> > Subject: Re: [PATCH] drm/amd: use drm_kms_helper_poll
Evolution seems to have garbled the first
patch.
>From 51cba3ae1e9f557cca8e37eb43b9b9310d0d504d Mon Sep 17 00:00:00 2001
From: Bert Karwatzki
Date: Thu, 16 Feb 2023 10:34:11 +0100
Subject: [PATCH] Use drm_kms_helper_poll_fini instead of
drm_kms_helper_poll_disable in amdgpu_device.c to avoi
rom 51cba3ae1e9f557cca8e37eb43b9b9310d0d504d Mon Sep 17 00:00:00 2001
From: Bert Karwatzki
Date: Thu, 16 Feb 2023 10:34:11 +0100
Subject: [PATCH] Use drm_kms_helper_poll_fini instead of
drm_kms_helper_poll_disable in amdgpu_device.c to avoid a warning from
__flush_work.
Signed-off-by: Bert Karwatzki
---
drivers/gpu/
Here is the fix for (send again to test if I can get it right with
Evolution)
Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2360
From 6e064c9565ef0da890f3fcb2a4f6a8cd44a12fdb Mon Sep 17 00:00:00 2001
From: Bert Karwatzki
Date: Thu, 2 Feb 2023 19:50:27 +0100
Subject: [PATCH] Fix memory
I hope I got it right this time:
Here is the fix for
Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2360
>From 6e064c9565ef0da890f3fcb2a4f6a8cd44a12fdb Mon Sep 17 00:00:00 2001
From: Bert Karwatzki
Date: Thu, 2 Feb 2023 19:50:27 +0100
Subject: [PATCH] Fix memory leak
r = amdgpu_sync_fence(&p->gang_leader->explicit_sync,
fence);
+ dma_fence_put(fence);
if (r)
return r;
}
Bert Karwatzki
tlab.freedesktop.org/drm/amd/-/issues/2291
Bert Karwatzki
tlab.freedesktop.org/drm/amd/-/issues/2291
Bert Karwatzki
issue by getting rid of the unneeded flag check
> during gart bind:
> https://patchwork.freedesktop.org/patch/469907/
>
> Thanks,
>
> Jon
>
> > -Original Message-
> > From: amd-gfx On Behalf Of
> > Bert
> > Karwatzki
> > Sent: January 19, 2
n 19, 2022 at 7:48 PM Bert Karwatzki
> wrote:
> >
> > Bisected the error and found the first bad commit to be
> > d015e9861e55928a78137a2c95897bc50637fc47 is the first bad commit
> > commit d015e9861e55928a78137a2c95897bc50637fc47
> > Author: Jonathan Kim
> >
+
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 4 ++
2 files changed, 82 insertions(+)
Am Donnerstag, dem 20.01.2022 um 00:22 +0100 schrieb Bert Karwatzki:
> Reverting commit 72f686438de13f121c52f58d7445570a33dfdc61 does not
> change the errors:
> [
he oth GPU in the
system (the integrated one at 08:00.0)
Am Mittwoch, dem 19.01.2022 um 23:40 +0100 schrieb Das, Nirmoy:
>
> On 1/19/2022 10:59 PM, Limonciello, Mario wrote:
> > [Public]
> >
> > > -Original Message-
> > > From: Bert Karwatzki
I just tested drm-staging-drm-next with HEAD
f1b2924ee6929cb431440e6f961f06eb65d52beb:
Going into suspend leads to a hang again:
This is probably caused by
[ 1.310551] trying to bind memory to uninitialized GART !
and/or
[ 3.976438] trying to bind memory to uninitialized GART !
Here's the complet
Am Mittwoch, dem 12.01.2022 um 02:08 + schrieb Limonciello, Mario:
> [AMD Official Use Only]
>
> > -Original Message-
> > From: Bert Karwatzki
> > Sent: Tuesday, January 11, 2022 19:12
> > To: amd-gfx@lists.freedesktop.org
> > Cc: Limonciel
Am Mittwoch, dem 12.01.2022 um 02:08 + schrieb Limonciello, Mario:
> [AMD Official Use Only]
>
> > -Original Message-
> > From: Bert Karwatzki
> > Sent: Tuesday, January 11, 2022 19:12
> > To: amd-gfx@lists.freedesktop.org
> > Cc: Limonciel
I just tested patch v5 applied to amd-staging-drm-next (with HEAD
26c981e27e698c251ef3241f73ac846e66ad7fc3) and suspend and resume work
fine. But as amd-staging-drm-next is still based on linux-5.13 I had to
replace the mediatek wlan driver by the version from linux-5.16.
34 matches
Mail list logo
