[PATCH 2/3] Revert "drm/xe: Move the coredump registration to the worker thread"

[Thomas Hellström]

On Wed, 2024-11-27 at 14:00 +0530, Himal Prasad Ghimiray wrote:
> This reverts commit e7c5f5ac82a9a763207eb30b194500fad48fbc88. The
> commit
> was accidentally and unintentionally pushed.
> 
> Cc: John Harrison <John.C.Harrison at Intel.com>
> Cc: Matthew Brost <matthew.brost at intel.com>
> Cc: Thomas Hellström <thomas.hellstrom at linux.intel.com>
> Cc: Rodrigo Vivi <rodrigo.vivi at intel.com>
> Signed-off-by: Himal Prasad Ghimiray
> <himal.prasad.ghimiray at intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom at linux.intel.com>



> ---
>  drivers/gpu/drm/xe/xe_devcoredump.c | 63 +++++++++++++--------------
> --
>  1 file changed, 29 insertions(+), 34 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c
> b/drivers/gpu/drm/xe/xe_devcoredump.c
> index 5d19a4e3d5af..f4c77f525819 100644
> --- a/drivers/gpu/drm/xe/xe_devcoredump.c
> +++ b/drivers/gpu/drm/xe/xe_devcoredump.c
> @@ -167,6 +167,31 @@ static void xe_devcoredump_snapshot_free(struct
> xe_devcoredump_snapshot *ss)
>  	ss->vm = NULL;
>  }
>  
> +static void xe_devcoredump_deferred_snap_work(struct work_struct
> *work)
> +{
> +	struct xe_devcoredump_snapshot *ss = container_of(work,
> typeof(*ss), work);
> +	struct xe_devcoredump *coredump = container_of(ss,
> typeof(*coredump), snapshot);
> +	unsigned int fw_ref;
> +
> +	/* keep going if fw fails as we still want to save the
> memory and SW data */
> +	fw_ref = xe_force_wake_get(gt_to_fw(ss->gt),
> XE_FORCEWAKE_ALL);
> +	if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL))
> +		xe_gt_info(ss->gt, "failed to get forcewake for
> coredump capture\n");
> +	xe_vm_snapshot_capture_delayed(ss->vm);
> +	xe_guc_exec_queue_snapshot_capture_delayed(ss->ge);
> +	xe_force_wake_put(gt_to_fw(ss->gt), fw_ref);
> +
> +	/* Calculate devcoredump size */
> +	ss->read.size = __xe_devcoredump_read(NULL, INT_MAX,
> coredump);
> +
> +	ss->read.buffer = kvmalloc(ss->read.size, GFP_USER);
> +	if (!ss->read.buffer)
> +		return;
> +
> +	__xe_devcoredump_read(ss->read.buffer, ss->read.size,
> coredump);
> +	xe_devcoredump_snapshot_free(ss);
> +}
> +
>  static ssize_t xe_devcoredump_read(char *buffer, loff_t offset,
>  				   size_t count, void *data, size_t
> datalen)
>  {
> @@ -215,40 +240,6 @@ static void xe_devcoredump_free(void *data)
>  		 "Xe device coredump has been deleted.\n");
>  }
>  
> -static void xe_devcoredump_deferred_snap_work(struct work_struct
> *work)
> -{
> -	struct xe_devcoredump_snapshot *ss = container_of(work,
> typeof(*ss), work);
> -	struct xe_devcoredump *coredump = container_of(ss,
> typeof(*coredump), snapshot);
> -	unsigned int fw_ref;
> -
> -	/*
> -	 * NB: Despite passing a GFP_ flags parameter here, more
> allocations are done
> -	 * internally using GFP_KERNEL expliictly. Hence this call
> must be in the worker
> -	 * thread and not in the initial capture call.
> -	 */
> -	dev_coredumpm_timeout(gt_to_xe(ss->gt)->drm.dev,
> THIS_MODULE, coredump, 0, GFP_KERNEL,
> -			      xe_devcoredump_read,
> xe_devcoredump_free,
> -			      XE_COREDUMP_TIMEOUT_JIFFIES);
> -
> -	/* keep going if fw fails as we still want to save the
> memory and SW data */
> -	fw_ref = xe_force_wake_get(gt_to_fw(ss->gt),
> XE_FORCEWAKE_ALL);
> -	if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL))
> -		xe_gt_info(ss->gt, "failed to get forcewake for
> coredump capture\n");
> -	xe_vm_snapshot_capture_delayed(ss->vm);
> -	xe_guc_exec_queue_snapshot_capture_delayed(ss->ge);
> -	xe_force_wake_put(gt_to_fw(ss->gt), fw_ref);
> -
> -	/* Calculate devcoredump size */
> -	ss->read.size = __xe_devcoredump_read(NULL, INT_MAX,
> coredump);
> -
> -	ss->read.buffer = kvmalloc(ss->read.size, GFP_USER);
> -	if (!ss->read.buffer)
> -		return;
> -
> -	__xe_devcoredump_read(ss->read.buffer, ss->read.size,
> coredump);
> -	xe_devcoredump_snapshot_free(ss);
> -}
> -
>  static void devcoredump_snapshot(struct xe_devcoredump *coredump,
>  				 struct xe_exec_queue *q,
>  				 struct xe_sched_job *job)
> @@ -337,6 +328,10 @@ void xe_devcoredump(struct xe_exec_queue *q,
> struct xe_sched_job *job, const cha
>  	drm_info(&xe->drm, "Xe device coredump has been created\n");
>  	drm_info(&xe->drm, "Check your
> /sys/class/drm/card%d/device/devcoredump/data\n",
>  		 xe->drm.primary->index);
> +
> +	dev_coredumpm_timeout(xe->drm.dev, THIS_MODULE, coredump, 0,
> GFP_KERNEL,
> +			      xe_devcoredump_read,
> xe_devcoredump_free,
> +			      XE_COREDUMP_TIMEOUT_JIFFIES);
>  }
>  
>  static void xe_driver_devcoredump_fini(void *arg)