[PATCH v1 2/2] drm/amdgpu: adding device coredump support

[Somalapuram, Amaranath]

On 5/20/2022 7:52 PM, Sharma, Shashank wrote:
>
>
> On 5/20/2022 3:49 PM, Somalapuram Amaranath wrote:
>> Added device coredump information:
>> - Kernel version
>> - Module
>> - Time
>> - VRAM status
>> - Guilty process name and PID
>> - GPU register dumps
>>
>> Signed-off-by: Somalapuram Amaranath <Amaranath.Somalapuram at amd.com>
>> ---
>>   drivers/gpu/drm/amd/amdgpu/amdgpu.h        |  3 ++
>>   drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 59 ++++++++++++++++++++++
>>   2 files changed, 62 insertions(+)
>>
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h 
>> b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
>> index c79d9992b113..f28d9c563f74 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
>> @@ -1044,6 +1044,9 @@ struct amdgpu_device {
>>       uint32_t                        *reset_dump_reg_list;
>>       uint32_t            *reset_dump_reg_value;
>>       int                             num_regs;
>> +    struct amdgpu_task_info         reset_context_task_info;
>> +    bool                            reset_context_vram_lost;
>
> How about drop the 'context' from name and just reset_task_info and 
> reset_vram_lost ?
OK.
>
>> +    struct timespec64 reset_time;
>>         struct amdgpu_reset_domain    *reset_domain;
>>   diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c 
>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> index 963c897a76e6..f9b710e741a7 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> @@ -32,6 +32,8 @@
>>   #include <linux/slab.h>
>>   #include <linux/iommu.h>
>>   #include <linux/pci.h>
>> +#include <linux/devcoredump.h>
>> +#include <generated/utsrelease.h>
>>     #include <drm/drm_atomic_helper.h>
>>   #include <drm/drm_probe_helper.h>
>> @@ -4733,6 +4735,55 @@ static int amdgpu_reset_reg_dumps(struct 
>> amdgpu_device *adev)
>>       return 0;
>>   }
>>   +#ifdef CONFIG_DEV_COREDUMP
>> +static ssize_t amdgpu_devcoredump_read(char *buffer, loff_t offset,
>> +        size_t count, void *data, size_t datalen)
>> +{
>> +    struct drm_printer p;
>> +    struct amdgpu_device *adev = data;
>> +    struct drm_print_iterator iter;
>> +    int i;
>> +
>
> A NULL check for 'buffer' here could prevent a segfault later.
>
Agreed.
>> +    iter.data = buffer;
>> +    iter.offset = 0;
>> +    iter.start = offset;
>> +    iter.remain = count;
>> +
>> +    p = drm_coredump_printer(&iter);
>> +
>> +    drm_printf(&p, "**** AMDGPU Device Coredump ****\n");
>> +    drm_printf(&p, "kernel: " UTS_RELEASE "\n");
>> +    drm_printf(&p, "module: " KBUILD_MODNAME "\n");
>> +    drm_printf(&p, "time: %lld.%09ld\n", adev->reset_time.tv_sec, 
>> adev->reset_time.tv_nsec);
>> +    if (adev->reset_context_task_info.pid)
>> +        drm_printf(&p, "process_name: %s PID: %d\n",
>> + adev->reset_context_task_info.process_name,
>> + adev->reset_context_task_info.pid);
> Please fix the alignment of print variables.
>
I will cross check this.
>> +
>> +    if (adev->reset_context_vram_lost)
>> +        drm_printf(&p, "VRAM is lost due to GPU reset!\n");
>> +    if (adev->num_regs) {
>> +        drm_printf(&p, "AMDGPU register dumps:\nOffset: Value:\n");
>> +
>> +        for (i = 0; i < adev->num_regs; i++)
>> +            drm_printf(&p, "0x%08x: 0x%08x\n",
>> +                    adev->reset_dump_reg_list[i],
>> +                    adev->reset_dump_reg_value[i]);
>> +    }
>> +
>> +    return count - iter.remain;
>> +}
>> +
>> +static void amdgpu_reset_capture_coredumpm(struct amdgpu_device *adev)
>> +{
>> +    struct drm_device *dev = adev_to_drm(adev);
>> +
>> +    ktime_get_ts64(&adev->reset_time);
>> +    dev_coredumpm(dev->dev, THIS_MODULE, adev, 0, GFP_KERNEL,
>> +            amdgpu_devcoredump_read, NULL);
> instead of registering NULL as free function, I would prefer you to 
> have a dummy no_op free function registered, which we can consume if 
> something changes.
you mean something like this (function without any code):
staticvoidamdgpu_devcoredump_free(void*data)
{
}
>> +}
>> +#endif
>> +
>>   int amdgpu_do_asic_reset(struct list_head *device_list_handle,
>>                struct amdgpu_reset_context *reset_context)
>>   {
>> @@ -4817,6 +4868,14 @@ int amdgpu_do_asic_reset(struct list_head 
>> *device_list_handle,
>>                       goto out;
>>                     vram_lost = amdgpu_device_check_vram_lost(tmp_adev);
>> +#ifdef CONFIG_DEV_COREDUMP
>> +                tmp_adev->reset_context_vram_lost = vram_lost;
>> +                tmp_adev->reset_context_task_info.pid = 0;
> why is the PID hardcoded to 0 ?
in case of reset context reset_context->job->vm  is null (possibility 
that reset can be non VM related).
If we don't set tmp_adev->reset_context_task_info.pid = 0, it will show 
previous reset valid PID.


Regards,
S.Amarnath
>> +                if (reset_context->job && reset_context->job->vm)
>> +                    tmp_adev->reset_context_task_info =
>> + reset_context->job->vm->task_info;
>> +                amdgpu_reset_capture_coredumpm(tmp_adev);
>> +#endif
>>                   if (vram_lost) {
>>                       DRM_INFO("VRAM is lost due to GPU reset!\n");
>>
> - Shashank
>                      amdgpu_inc_vram_lost(tmp_adev);
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/amd-gfx/attachments/20220524/35297869/attachment-0001.htm>