On 3/21/2024 12:28 PM, Ma, Jun wrote:
>
>
> On 3/20/2024 9:38 PM, Lazar, Lijo wrote:
>>
>>
>> On 3/20/2024 6:54 PM, Alex Deucher wrote:
>>> On Wed, Mar 20, 2024 at 6:17 AM Ma Jun wrote:
Because of the logic error, Arcturus and vega20 currently
use the AMDGPU_RUNPM_NONE for runt
On 3/21/2024 10:29 AM, Srinivasan Shanmugam wrote:
> Reducing the size of ucode_prefix to 25 in the amdgpu_vcn_early_init
> function. This would ensure that the total number of characters being
> written into fw_name does not exceed its size of 40.
>
> Fixes the below with gcc W=1:
> drivers/gp
On 3/21/2024 11:16 AM, Srinivasan Shanmugam wrote:
> The snprintf function is used to write a formatted string into fw_name.
> The format of the string is "amdgpu/%s_mes%s.bin", where %s is replaced
> by the string in ucode_prefix and the second %s is replaced by either
> "_2" or "1" depending o
From: Mario Limonciello
If the system hasn't entered GFXOFF when suspend starts it can cause
hangs accessing GC and RLC during the suspend stage.
Cc: # 6.1.y: 5095d5418193 ("drm/amd: Evict resources
during PM ops prepare() callback")
Cc: # 6.1.y: cb11ca3233aa ("drm/amd: Add concept of
runnin
From: Tvrtko Ursulin
Pipelined object migration will free up the old bo->resource, meaning
the tracepoint added in 94aeb4117343 ("drm/amdgpu: fix ftrace event
amdgpu_bo_move always move on same heap") will trigger an use after free
when it dereferences the cached old_mem.
Fix it by caching the m
On Wed, Mar 20, 2024 at 6:31 AM Christian König
wrote:
> Can you provide the full output of lspci -. As far as I can see that
> doesn't looks so invalid to me.
I've added the relevant pci probing debug output without assign-busses
and the lspci - for a boot with all devices visible.
htt
[AMD Official Use Only - General]
The series is Reviewed-by: Stanley.Yang
Regards,
Stanley
> -Original Message-
> From: amd-gfx On Behalf Of Tao
> Zhou
> Sent: Thursday, March 21, 2024 11:30 AM
> To: amd-gfx@lists.freedesktop.org
> Cc: Zhou1, Tao
> Subject: [PATCH 2/2] drm/amdgpu: simp
Am 20.03.24 um 20:44 schrieb Sunil Khatri:
Refractor devcoredump code into new files since its
functionality is expanded further and better to slit
and devcoredump to have its own file.
Signed-off-by: Sunil Khatri
Acked-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/Makefile
Am 20.03.24 um 18:12 schrieb Tvrtko Ursulin:
From: Tvrtko Ursulin
Pipelined object migration will free up the old bo->resource, meaning
the tracepoint added in 94aeb4117343 ("drm/amdgpu: fix ftrace event
amdgpu_bo_move always move on same heap") will trigger an use after free
when it dereferenc
Hi Christian,
On 21/03/2024 10:25, Christian König wrote:
Am 20.03.24 um 18:12 schrieb Tvrtko Ursulin:
From: Tvrtko Ursulin
Pipelined object migration will free up the old bo->resource, meaning
the tracepoint added in 94aeb4117343 ("drm/amdgpu: fix ftrace event
amdgpu_bo_move always move on
Le 20/03/2024 à 13:49, Christian König a écrit :
The majority of those where removed in the patch aed01a68047b
drm/amdgpu: Remove TTM resource->start visible VRAM condition v2
But this one was missed because it's working on the resource and not the
BO. Since we also no longer use a fake start
Downgrade to debug information when IBs are skipped. Also, use dev_* to
identify the device.
Signed-off-by: Lijo Lazar
---
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 7 +--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
b/drivers/gpu/drm
Am 21.03.24 um 13:36 schrieb Lijo Lazar:
Downgrade to debug information when IBs are skipped. Also, use dev_* to
identify the device.
Signed-off-by: Lijo Lazar
Reviewed-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 7 +--
1 file changed, 5 insertions(+), 2 deleti
This reverts drm/amdgpu: fix ftrace event amdgpu_bo_move always move
on same heap. The basic problem here is that after the move the old
location is simply not available any more.
Some fixes where suggested, but essentially we should call the move
notification before actually moving things because
[AMD Official Use Only - General]
Reviewed-by: Asad Kamal
Thanks & Regards
Asad
-Original Message-
From: Lazar, Lijo
Sent: Thursday, March 21, 2024 6:06 PM
To: amd-gfx@lists.freedesktop.org
Cc: Zhang, Hawking ; Deucher, Alexander
; Koenig, Christian ;
Kamal, Asad
Subject: [PATCH] dr
On Thu, Mar 21, 2024 at 2:52 AM Ma, Jun wrote:
>
>
>
> On 3/20/2024 9:24 PM, Alex Deucher wrote:
> > On Wed, Mar 20, 2024 at 6:17 AM Ma Jun wrote:
> >>
> >> Because of the logic error, Arcturus and vega20 currently
> >> use the AMDGPU_RUNPM_NONE for runtime pm even though they
> >> support BACO.
On 21/03/2024 12:43, Christian König wrote:
This reverts drm/amdgpu: fix ftrace event amdgpu_bo_move always move
on same heap. The basic problem here is that after the move the old
location is simply not available any more.
Some fixes where suggested, but essentially we should call the move
no
On 18/03/2024 16:24, Christian König wrote:
Am 18.03.24 um 16:22 schrieb Sharma, Shashank:
On 18/03/2024 16:01, Christian König wrote:
Am 18.03.24 um 15:44 schrieb Shashank Sharma:
The idea behind this patch is to delay the freeing of PT entry objects
until the TLB flush is done.
This patch
This patch adds a NULL check to fix this crash reported during the
freeing of root PT entry:
[ 06:55] BUG: unable to handle page fault for address: c9002d637aa0
[ +0.007689] #PF: supervisor write access in kernel mode
[ +0.005833] #PF: error_code(0x0002) - not-present page
[ +0.005732]
Am 21.03.24 um 15:12 schrieb Tvrtko Ursulin:
On 21/03/2024 12:43, Christian König wrote:
This reverts drm/amdgpu: fix ftrace event amdgpu_bo_move always move
on same heap. The basic problem here is that after the move the old
location is simply not available any more.
Some fixes where suggeste
[Public]
Ping for review.
Thanks,
Jon
> -Original Message-
> From: Kim, Jonathan
> Sent: Wednesday, March 13, 2024 10:21 AM
> To: amd-gfx@lists.freedesktop.org
> Cc: Kuehling, Felix ; Huang, JinHuiEric
> ; Kim, Jonathan ;
> Kim, Jonathan ; Zhang, Jesse(Jie)
>
> Subject: [PATCH] drm/am
tree/branch:
https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git master
branch HEAD: e7528c088874326d3060a46f572252be43755a86 Add linux-next specific
files for 20240321
Error/Warning reports:
https://lore.kernel.org/oe-kbuild-all/202403211931.wvl6ymav-...@intel.com
Error
On 2024-03-13 10:21, Jonathan Kim wrote:
Due to a CP interrupt bug, bad packet garbage exception codes are raised.
Do a range check so that the debugger and runtime do not receive garbage
codes.
Update the user api to guard exception code type checking as well.
Signed-off-by: Jonathan Kim
Tes
On 2024-03-20 18:52, Mukul Joshi wrote:
Destroy the high priority workqueue that handles interrupts
during KFD node cleanup.
Signed-off-by: Mukul Joshi
Reviewed-by: Felix Kuehling
---
drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/dri
when CONFIG_DEV_COREDUMP is not defined in that case
when amdgpu_coredump() is called it does not find it's
definition and the build fails.
This happens as the header is defined without the
CONFIG_DEV_COREDUMP ifdef and due to which header isn't
enabled.
Pulling the header out of such ifdef so in
Acked-by: Alex Deucher
On Thu, Mar 21, 2024 at 2:14 PM Sunil Khatri wrote:
>
> when CONFIG_DEV_COREDUMP is not defined in that case
> when amdgpu_coredump() is called it does not find it's
> definition and the build fails.
>
> This happens as the header is defined without the
> CONFIG_DEV_COREDU
On Thu, Mar 21, 2024 at 5:37 AM Mario Limonciello wrote:
>
> From: Mario Limonciello
>
> If the system hasn't entered GFXOFF when suspend starts it can cause
> hangs accessing GC and RLC during the suspend stage.
>
> Cc: # 6.1.y: 5095d5418193 ("drm/amd: Evict resources
> during PM ops prepare()
On Thu, Mar 21, 2024 at 8:52 AM Christian König
wrote:
>
> This reverts drm/amdgpu: fix ftrace event amdgpu_bo_move always move
> on same heap. The basic problem here is that after the move the old
> location is simply not available any more.
>
> Some fixes where suggested, but essentially we shou
On 2024-03-15 13:09, sunpeng...@amd.com wrote:
> From: Leo Li
>
> [Why]
>
> Compositors have different ways of assigning surfaces to DRM planes for
> render offloading. It may decide between various strategies: overlay,
> underlay, or a mix of both
>
> One way for compositors to implement th
On 2024-03-15 13:09, sunpeng...@amd.com wrote:
> From: Leo Li
>
> [Why]
>
> DCN is the display hardware for amdgpu. DRM planes are backed by DCN
> hardware pipes, which carry pixel data from one end (memory), to the
> other (output encoder).
>
> Each DCN pipe has the ability to blend in a cu
Hi Dave, Sima,
Fixes for 6.9. Fairly big because it's about 3 weeks of fixes.
The following changes since commit 119b225f01e4d3ce974cd3b4d982c76a380c796d:
Merge tag 'amd-drm-next-6.9-2024-03-08-1' of
https://gitlab.freedesktop.org/agd5f/linux into drm-next (2024-03-11 13:32:12
+1000)
are a
Align with FW changes.
Signed-off-by: Lang Yu
Reviewed-by: Veerabadhran Gopalakrishnan
---
drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.h | 20 +--
.../drm/amd/include/umsch_mm_4_0_api_def.h| 13 ++--
2 files changed, 21 insertions(+), 12 deletions(-)
diff --git a/dr
Share same codes with 4.0.5 and enable collaborate mode for VPE.
Signed-off-by: Lang Yu
Reviewed-by: Veerabadhran Gopalakrishnan
---
drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c | 12 ++--
drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c
The size of fw_name is increased to ensure that it can accommodate
the maximum possible size of the string being written into it.
Fixes the below with gcc W=1:
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c: In function ‘gfx_v9_0_early_init’:
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c:1255:52: warning: ‘%s’ dir
Reducing the size of ucode_prefix to 25 in the gfx_v11_0_init_microcode
function. This would ensure that the total number of characters being
written into fw_name does not exceed its size of 40.
Fixes the below with gcc W=1:
drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c: In function ‘gfx_v11_0_early_init
The total size of the fw_name buffer is 8 (for "amdgpu/") + 30 (for
ucode_prefix) + 5 (for "_pfp") + 5 (for "_wks") + 5 (for ".bin") = 53
characters.
Fixes the below with gcc W=1:
drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c: In function ‘gfx_v10_0_early_init’:
drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c:398
36 matches
Mail list logo
