[PATCH 2/2] drm/xe/pf: Expose access to the VF GGTT PTEs over debugfs

Matthew Brost matthew.brost at intel.com
Tue Nov 5 01:14:26 UTC 2024


On Sun, Nov 03, 2024 at 09:16:33PM +0100, Michal Wajdeczko wrote:
> For feature enabling and testing purposes, allow to capture and
> replace VF's GGTT PTEs data using debugfs blob file.
> 
> Signed-off-by: Michal Wajdeczko <michal.wajdeczko at intel.com>
> ---
>  drivers/gpu/drm/xe/xe_gt_sriov_pf_debugfs.c | 62 +++++++++++++++++++++
>  1 file changed, 62 insertions(+)
> 
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_debugfs.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_debugfs.c
> index 05df4ab3514b..69ba830d9e8d 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_debugfs.c
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_debugfs.c
> @@ -11,6 +11,7 @@
>  #include "xe_bo.h"
>  #include "xe_debugfs.h"
>  #include "xe_device.h"
> +#include "xe_ggtt.h"
>  #include "xe_gt.h"
>  #include "xe_gt_debugfs.h"
>  #include "xe_gt_sriov_pf_config.h"
> @@ -497,6 +498,64 @@ static const struct file_operations config_blob_ops = {
>  	.llseek		= default_llseek,
>  };
>  
> +/*
> + *      /sys/kernel/debug/dri/0/
> + *      ├── gt0
> + *      │   ├── vf1
> + *      │   │   ├── ggtt_raw
> + */
> +
> +static ssize_t ggtt_raw_read(struct file *file, char __user *buf,
> +			     size_t count, loff_t *pos)
> +{
> +	struct dentry *dent = file_dentry(file);
> +	struct dentry *parent = dent->d_parent;
> +	unsigned int vfid = extract_vfid(parent);
> +	struct xe_gt *gt = extract_gt(parent);
> +	struct xe_device *xe = gt_to_xe(gt);
> +	ssize_t ret;
> +
> +	xe_pm_runtime_get(xe);
> +	mutex_lock(xe_gt_sriov_pf_master_mutex(gt));

+ Thomas to confirm I'm making sense here.

So this relates to this patch [1] / Thomas comment [2].

You are adding memory allocations here under the
xe_gt_sriov_pf_master_mutex which renders [1] incomplete.

So you need to one of two things:

1. Never do any memory allocations under xe_gt_sriov_pf_master_mutex. If
you choose this option taint this mutex with reclaim when loading the
PF. It is then safe to xe_gt_sriov_pf_master_mutex in suspend / resume /
reset flows.

2. Remove xe_gt_sriov_pf_master_mutex from suspend / resume / reset
flows.

In addition to above, also never allocate memory in suspend / resume /
reset flows.

Not blocker here but just using this as an example to explain the
current SRIOV locking problems. Hope this helps.

Matt

[1] https://patchwork.freedesktop.org/patch/619024/?series=139801&rev=1
[2] https://lore.kernel.org/intel-xe/3e13401972fd49240f486fd7d47580e576794c78.camel@intel.com/

> +
> +	ret = xe_ggtt_node_read(gt->sriov.pf.vfs[vfid].config.ggtt_region,
> +				buf, count, pos);
> +
> +	mutex_unlock(xe_gt_sriov_pf_master_mutex(gt));
> +	xe_pm_runtime_put(xe);
> +
> +	return ret;
> +}
> +
> +static ssize_t ggtt_raw_write(struct file *file, const char __user *buf,
> +			      size_t count, loff_t *pos)
> +{
> +	struct dentry *dent = file_dentry(file);
> +	struct dentry *parent = dent->d_parent;
> +	unsigned int vfid = extract_vfid(parent);
> +	struct xe_gt *gt = extract_gt(parent);
> +	struct xe_device *xe = gt_to_xe(gt);
> +	ssize_t ret;
> +
> +	xe_pm_runtime_get(xe);
> +	mutex_lock(xe_gt_sriov_pf_master_mutex(gt));
> +
> +	ret = xe_ggtt_node_write(gt->sriov.pf.vfs[vfid].config.ggtt_region,
> +				 buf, count, pos);
> +
> +	mutex_unlock(xe_gt_sriov_pf_master_mutex(gt));
> +	xe_pm_runtime_put(xe);
> +
> +	return ret;
> +}
> +
> +static const struct file_operations ggtt_raw_ops = {
> +	.owner		= THIS_MODULE,
> +	.read		= ggtt_raw_read,
> +	.write		= ggtt_raw_write,
> +	.llseek		= default_llseek,
> +};
> +
>  /**
>   * xe_gt_sriov_pf_debugfs_register - Register SR-IOV PF specific entries in GT debugfs.
>   * @gt: the &xe_gt to register
> @@ -554,6 +613,9 @@ void xe_gt_sriov_pf_debugfs_register(struct xe_gt *gt, struct dentry *root)
>  			debugfs_create_file("config_blob",
>  					    IS_ENABLED(CONFIG_DRM_XE_DEBUG_SRIOV) ? 0600 : 0400,
>  					    vfdentry, NULL, &config_blob_ops);
> +			debugfs_create_file("ggtt_raw",
> +					    IS_ENABLED(CONFIG_DRM_XE_DEBUG_SRIOV) ? 0600 : 0400,
> +					    vfdentry, NULL, &ggtt_raw_ops);
>  		}
>  	}
>  }
> -- 
> 2.43.0
> 


More information about the Intel-xe mailing list