On 2024-07-25 19:25, Philip Yang wrote:
Fixes the below if kernel config not enable HMM support
drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_queue.c:107:26: error:
implicit declaration of function 'svm_range_from_addr'
drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_queue.c:107:24: error:
assignment
On Fri, Jul 26, 2024 at 11:31 AM Jonathan Kim wrote:
>
> Support per-queue reset for GFX9. The recommendation is for the driver
> to target reset the HW queue via a SPI MMIO register write.
>
> Since this requires pipe and HW queue info and MEC FW is limited to
> doorbell reports of hung queues a
[Public]
> -Original Message-
> From: Alex Deucher
> Sent: Friday, July 26, 2024 2:57 PM
> To: Kim, Jonathan
> Cc: amd-gfx@lists.freedesktop.org; Kuehling, Felix
> ; Deucher, Alexander
>
> Subject: Re: [PATCH 2/2] drm/amdkfd: support the debugger during per-
> queue reset
>
> Caution: T
On 7/27/2024 12:13 AM, Alex Deucher wrote:
On Fri, Jul 26, 2024 at 1:16 PM Khatri, Sunil wrote:
On 7/26/2024 8:36 PM, Lazar, Lijo wrote:
On 7/26/2024 8:11 PM, Khatri, Sunil wrote:
On 7/26/2024 7:53 PM, Khatri, Sunil wrote:
On 7/26/2024 7:18 PM, Lazar, Lijo wrote:
On 7/26/2024 6:42 PM, Al
On Fri, Jul 26, 2024 at 11:40 AM Jonathan Kim wrote:
>
> In order to allow ROCm GDB to handle reset queues, raise an
> EC_QUEUE_RESET exception so that the debugger can subscribe and
> query this exception.
>
> Reset queues should still be considered suspendable with a status
> flag of KFD_DBG_QUE
On Fri, Jul 26, 2024 at 1:16 PM Khatri, Sunil wrote:
>
>
> On 7/26/2024 8:36 PM, Lazar, Lijo wrote:
> >
> > On 7/26/2024 8:11 PM, Khatri, Sunil wrote:
> >> On 7/26/2024 7:53 PM, Khatri, Sunil wrote:
> >>> On 7/26/2024 7:18 PM, Lazar, Lijo wrote:
> On 7/26/2024 6:42 PM, Alex Deucher wrote:
> >
On 7/26/2024 8:36 PM, Lazar, Lijo wrote:
On 7/26/2024 8:11 PM, Khatri, Sunil wrote:
On 7/26/2024 7:53 PM, Khatri, Sunil wrote:
On 7/26/2024 7:18 PM, Lazar, Lijo wrote:
On 7/26/2024 6:42 PM, Alex Deucher wrote:
On Fri, Jul 26, 2024 at 8:48 AM Sunil Khatri
wrote:
Problem:
IP dump right now
From: Xiaogang Chen
When app unmap vm ranges(munmap) kfd/svm starts drain pending page fault and
not handle any incoming pages fault of this process until a deferred work item
got executed by default system wq. The time period of "not handle page fault"
can be long and is unpredicable. That is ad
In order to allow ROCm GDB to handle reset queues, raise an
EC_QUEUE_RESET exception so that the debugger can subscribe and
query this exception.
Reset queues should still be considered suspendable with a status
flag of KFD_DBG_QUEUE_RESET_MASK.
However they should not be resumable since user spac
Support per-queue reset for GFX9. The recommendation is for the driver
to target reset the HW queue via a SPI MMIO register write.
Since this requires pipe and HW queue info and MEC FW is limited to
doorbell reports of hung queues after an unmap failure, scan the HW
queue slots defined by SET_RES
On Fri, Jul 26, 2024 at 9:50 AM Alex Deucher wrote:
>
> This adds allocation latency, but aligns better with user
> expectations. The latency should improve with the drm buddy
> clearing patches that Arun has been working on.
>
> Signed-off-by: Alex Deucher
> ---
> drivers/gpu/drm/amd/amdgpu/am
[Public]
Hi all,
This week this patchset was tested on the following systems:
* Lenovo ThinkBook T13s Gen4 with AMD Ryzen 5 6600U
* MSI Gaming X Trio RX 6800
* Gigabyte Gaming OC RX 7900 XTX
These systems were tested on the following display/connection types:
* eD
On 7/26/2024 8:11 PM, Khatri, Sunil wrote:
>
> On 7/26/2024 7:53 PM, Khatri, Sunil wrote:
>>
>> On 7/26/2024 7:18 PM, Lazar, Lijo wrote:
>>>
>>> On 7/26/2024 6:42 PM, Alex Deucher wrote:
On Fri, Jul 26, 2024 at 8:48 AM Sunil Khatri
wrote:
> Problem:
> IP dump right now is don
On 7/26/2024 7:53 PM, Khatri, Sunil wrote:
On 7/26/2024 7:18 PM, Lazar, Lijo wrote:
On 7/26/2024 6:42 PM, Alex Deucher wrote:
On Fri, Jul 26, 2024 at 8:48 AM Sunil Khatri
wrote:
Problem:
IP dump right now is done post suspend of
all IP's which for some IP's could change power
state and sof
Applied the series. Thanks!
Alex
On Fri, Jul 26, 2024 at 9:40 AM Thomas Weißschuh wrote:
>
> Instead of manually passing around 'struct edid *' and its size,
> use 'struct drm_edid', which encapsulates a validated combination of
> both.
>
> As the drm_edid_ can handle NULL gracefully, the expli
On 7/26/2024 7:18 PM, Lazar, Lijo wrote:
On 7/26/2024 6:42 PM, Alex Deucher wrote:
On Fri, Jul 26, 2024 at 8:48 AM Sunil Khatri wrote:
Problem:
IP dump right now is done post suspend of
all IP's which for some IP's could change power
state and software state too which we do not want
to refl
On Fri, Jul 26, 2024 at 09:55:50AM +0200, Christian König wrote:
> The current implementation of drm_sched_start uses a hardcoded
> -ECANCELED to dispose of a job when the parent/hw fence is NULL.
> This results in drm_sched_job_done being called with -ECANCELED for
> each job with a NULL parent in
Applied. Thanks!
On Fri, Jul 26, 2024 at 5:55 AM Jiapeng Chong
wrote:
>
> Use of macro ARRAY_SIZE to calculate array size minimizes
> the redundant code and improves code reusability.
>
> ./drivers/gpu/drm/amd/display/dc/spl/dc_spl_scl_easf_filters.c:1552:57-58:
> WARNING: Use ARRAY_SIZE.
> ./d
This commit adds a null check for 'stream_status' in the function
'planes_changed_for_existing_stream'. Previously, the code assumed
'stream_status' could be null, but did not handle the case where it was
actually null. This could lead to a null pointer dereference.
Reported by smatch:
drivers/gpu
On 7/24/2024 8:42 PM, Jani Nikula wrote:
On Tue, 23 Jul 2024, Arunpravin Paneer Selvam
wrote:
- Add a new start parameter in trim function to specify exact
address from where to start the trimming. This would help us
in situations like if drivers would like to do address alignment
On 7/26/2024 6:42 PM, Alex Deucher wrote:
> On Fri, Jul 26, 2024 at 8:48 AM Sunil Khatri wrote:
>>
>> Problem:
>> IP dump right now is done post suspend of
>> all IP's which for some IP's could change power
>> state and software state too which we do not want
>> to reflect in the dump as it mig
This adds allocation latency, but aligns better with user
expectations. The latency should improve with the drm buddy
clearing patches that Arun has been working on.
Signed-off-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 4
1 file changed, 4 insertions(+)
diff --git a/d
The kfdtest user queue validation cases don't cover those error
condition path, thanks for catching it.
This patch is
Reviewed-by: Philip Yang
On 2024-07-26 02:47, Srinivasan
Shanmugam wrote:
The fix involves setting 'err' to '-EINVAL' befo
On Fri, Jul 26, 2024 at 8:48 AM Sunil Khatri wrote:
>
> VCN dump is dependent on power state of the ip. Dump is
> valid if VCN was powered up at the time of ip dump.
>
> Signed-off-by: Sunil Khatri
Reviewed-by: Alex Deucher
> ---
> drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c | 28 +-
On Fri, Jul 26, 2024 at 8:48 AM Sunil Khatri wrote:
>
> Problem:
> IP dump right now is done post suspend of
> all IP's which for some IP's could change power
> state and software state too which we do not want
> to reflect in the dump as it might not be same at
> the time of hang.
>
> Solution:
>
On Thu, Jul 25, 2024 at 11:11 PM Feng, Kenneth wrote:
>
> [AMD Official Use Only - AMD Internal Distribution Only]
>
> Hi Alex,
> I know that G6 MCLK = 2*UCLK.
> May I know how did you get the data that effective_memory_clock =
> memory_controller_clock * 1?
I swear someone on the pplib team tol
On Fri, Jul 26, 2024 at 3:05 AM Christian König
wrote:
>
> Am 25.07.24 um 20:09 schrieb Nikita Zhandarovich:
> > Several cs track offsets (such as 'track->db_s_read_offset')
> > either are initialized with or plainly take big enough values that,
> > once shifted 8 bits left, may be hit with intege
Problem:
IP dump right now is done post suspend of
all IP's which for some IP's could change power
state and software state too which we do not want
to reflect in the dump as it might not be same at
the time of hang.
Solution:
IP should be dumped as close to the HW state when
the GPU was in hung s
VCN dump is dependent on power state of the ip. Dump is
valid if VCN was powered up at the time of ip dump.
Signed-off-by: Sunil Khatri
---
drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c | 28 +--
1 file changed, 18 insertions(+), 10 deletions(-)
diff --git a/drivers/gpu/drm/amd/
On Fri, Jul 26, 2024 at 09:55:50AM +0200, Christian König wrote:
> The current implementation of drm_sched_start uses a hardcoded
> -ECANCELED to dispose of a job when the parent/hw fence is NULL.
> This results in drm_sched_job_done being called with -ECANCELED for
> each job with a NULL parent in
The current implementation of drm_sched_start uses a hardcoded
-ECANCELED to dispose of a job when the parent/hw fence is NULL.
This results in drm_sched_job_done being called with -ECANCELED for
each job with a NULL parent in the pending list, making it difficult
to distinguish between recovery me
Several cs track offsets (such as 'track->db_s_read_offset')
either are initialized with or plainly take big enough values that,
once shifted 8 bits left, may be hit with integer overflow if the
resulting values end up going over u32 limit.
Some debug prints take this into account (see according d
Hello Chaitanya Dhere,
This is a semi-automatic email about new static checker warnings.
Commit 2563391e57b5 ("drm/amd/display: DML2.1 resynchronization")
from Jul 2, 2024, leads to the following Smatch complaint:
drivers/gpu/drm/amd/amdgpu/../display/dc/dml2/dml21/src/dml2_core/dml2_core_d
Hello Philip Yang,
Commit 629568d25fea ("drm/amdkfd: Validate queue cwsr area and eop
buffer size") from Jun 26, 2024 (linux-next), leads to the following
Smatch static checker warning:
drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_queue.c:265
kfd_queue_acquire_buffers()
warn: missing
Reviewed-by: Tom Chung
On 7/25/2024 10:54 AM, Srinivasan Shanmugam wrote:
This commit addresses a null pointer dereference issue in the
`dcn20_program_pipe` function. The issue could occur when
`pipe_ctx->plane_state` is null.
The fix adds a check to ensure `pipe_ctx->plane_state` is not null
Reviewed-by: Tom Chung
On 7/25/2024 10:54 AM, Srinivasan Shanmugam wrote:
This commit addresses a null pointer dereference issue in the
`commit_planes_for_stream` function at line 4140. The issue could occur
when `top_pipe_to_program` is null.
The fix adds a check to ensure `top_pipe_to_progra
I strongly suggest to revert that again. See my other mail.
Christian.
Am 25.07.24 um 22:59 schrieb Alex Deucher:
Applied. Thanks!
Alex
On Thu, Jul 25, 2024 at 2:20 PM Nikita Zhandarovich
wrote:
Several cs track offsets (such as 'track->db_s_read_offset')
either are initialized with or pla
Am 25.07.24 um 20:09 schrieb Nikita Zhandarovich:
Several cs track offsets (such as 'track->db_s_read_offset')
either are initialized with or plainly take big enough values that,
once shifted 8 bits left, may be hit with integer overflow if the
resulting values end up going over u32 limit.
Some
38 matches
Mail list logo
