[PATCH v2 08/26] drm/xe/pf: Expose VF migration data size over debugfs

Michał Winiarski posted 26 patches 3 months, 2 weeks ago
There is a newer version of this series
[PATCH v2 08/26] drm/xe/pf: Expose VF migration data size over debugfs
Posted by Michał Winiarski 3 months, 2 weeks ago
The size is normally used to make a decision on when to stop the device
(mainly when it's in a pre_copy state).

Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
---
 drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c | 19 ++++++++++++
 drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.h |  2 ++
 drivers/gpu/drm/xe/xe_sriov_pf_debugfs.c      | 29 ++++++++++++++++++
 drivers/gpu/drm/xe/xe_sriov_pf_migration.c    | 30 +++++++++++++++++++
 drivers/gpu/drm/xe/xe_sriov_pf_migration.h    |  1 +
 5 files changed, 81 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c
index 8ba72165759b3..4e26feb9c267f 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c
@@ -395,6 +395,25 @@ ssize_t xe_gt_sriov_pf_migration_write_guc_state(struct xe_gt *gt, unsigned int
 }
 #endif /* CONFIG_DEBUG_FS */
 
+/**
+ * xe_gt_sriov_pf_migration_size() - Total size of migration data from all components within a GT.
+ * @gt: the &xe_gt
+ * @vfid: the VF identifier
+ *
+ * This function is for PF only.
+ *
+ * Return: total migration data size in bytes or a negative error code on failure.
+ */
+ssize_t xe_gt_sriov_pf_migration_size(struct xe_gt *gt, unsigned int vfid)
+{
+	ssize_t total = 0;
+
+	xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
+
+	/* Nothing to query yet - will be updated once per-GT migration data types are added */
+	return total;
+}
+
 /**
  * xe_gt_sriov_pf_migration_ring_empty() - Check if a migration ring is empty.
  * @gt: the &xe_gt
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.h b/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.h
index 1ed2248f0a17e..e2d41750f863c 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.h
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.h
@@ -15,6 +15,8 @@ int xe_gt_sriov_pf_migration_init(struct xe_gt *gt);
 int xe_gt_sriov_pf_migration_save_guc_state(struct xe_gt *gt, unsigned int vfid);
 int xe_gt_sriov_pf_migration_restore_guc_state(struct xe_gt *gt, unsigned int vfid);
 
+ssize_t xe_gt_sriov_pf_migration_size(struct xe_gt *gt, unsigned int vfid);
+
 bool xe_gt_sriov_pf_migration_ring_empty(struct xe_gt *gt, unsigned int vfid);
 bool xe_gt_sriov_pf_migration_ring_full(struct xe_gt *gt, unsigned int vfid);
 void xe_gt_sriov_pf_migration_ring_free(struct xe_gt *gt, unsigned int vfid);
diff --git a/drivers/gpu/drm/xe/xe_sriov_pf_debugfs.c b/drivers/gpu/drm/xe/xe_sriov_pf_debugfs.c
index a9a28aec22421..bc2d0b0342f22 100644
--- a/drivers/gpu/drm/xe/xe_sriov_pf_debugfs.c
+++ b/drivers/gpu/drm/xe/xe_sriov_pf_debugfs.c
@@ -14,6 +14,7 @@
 #include "xe_sriov_pf_control.h"
 #include "xe_sriov_pf_debugfs.h"
 #include "xe_sriov_pf_helpers.h"
+#include "xe_sriov_pf_migration.h"
 #include "xe_sriov_pf_provision.h"
 #include "xe_sriov_pf_service.h"
 #include "xe_sriov_printk.h"
@@ -254,6 +255,33 @@ static const struct file_operations data_vf_fops = {
 	.llseek		= default_llseek,
 };
 
+static ssize_t size_read(struct file *file, char __user *ubuf, size_t count, loff_t *ppos)
+{
+	struct dentry *dent = file_dentry(file)->d_parent;
+	struct xe_device *xe = extract_xe(dent);
+	unsigned int vfid = extract_vfid(dent);
+	char buf[21];
+	ssize_t ret;
+	int len;
+
+	xe_pm_runtime_get(xe);
+	ret = xe_sriov_pf_migration_size(xe, vfid);
+	xe_pm_runtime_put(xe);
+	if (ret < 0)
+		return ret;
+
+	len = scnprintf(buf, sizeof(buf), "%zd\n", ret);
+
+	return simple_read_from_buffer(ubuf, count, ppos, buf, len);
+}
+
+static const struct file_operations size_vf_fops = {
+	.owner		= THIS_MODULE,
+	.open		= simple_open,
+	.read		= size_read,
+	.llseek		= default_llseek,
+};
+
 static void pf_populate_vf(struct xe_device *xe, struct dentry *vfdent)
 {
 	debugfs_create_file("pause", 0200, vfdent, xe, &pause_vf_fops);
@@ -263,6 +291,7 @@ static void pf_populate_vf(struct xe_device *xe, struct dentry *vfdent)
 	debugfs_create_file("save", 0600, vfdent, xe, &save_vf_fops);
 	debugfs_create_file("restore", 0600, vfdent, xe, &restore_vf_fops);
 	debugfs_create_file("migration_data", 0600, vfdent, xe, &data_vf_fops);
+	debugfs_create_file("migration_size", 0400, vfdent, xe, &size_vf_fops);
 }
 
 static void pf_populate_with_tiles(struct xe_device *xe, struct dentry *dent, unsigned int vfid)
diff --git a/drivers/gpu/drm/xe/xe_sriov_pf_migration.c b/drivers/gpu/drm/xe/xe_sriov_pf_migration.c
index 0b4b237780102..88babec9c893e 100644
--- a/drivers/gpu/drm/xe/xe_sriov_pf_migration.c
+++ b/drivers/gpu/drm/xe/xe_sriov_pf_migration.c
@@ -242,3 +242,33 @@ int xe_sriov_pf_migration_restore_produce(struct xe_device *xe, unsigned int vfi
 
 	return xe_gt_sriov_pf_migration_restore_produce(gt, vfid, data);
 }
+
+/**
+ * xe_sriov_pf_migration_size() - Total size of migration data from all components within a device
+ * @xe: the &xe_device
+ * @vfid: the VF identifier (can't be 0)
+ *
+ * This function is for PF only.
+ *
+ * Return: total migration data size in bytes or a negative error code on failure.
+ */
+ssize_t xe_sriov_pf_migration_size(struct xe_device *xe, unsigned int vfid)
+{
+	size_t size = 0;
+	struct xe_gt *gt;
+	ssize_t ret;
+	u8 gt_id;
+
+	xe_assert(xe, IS_SRIOV_PF(xe));
+	xe_assert(xe, vfid);
+
+	for_each_gt(gt, xe, gt_id) {
+		ret = xe_gt_sriov_pf_migration_size(gt, vfid);
+		if (ret < 0)
+			return ret;
+
+		size += ret;
+	}
+
+	return size;
+}
diff --git a/drivers/gpu/drm/xe/xe_sriov_pf_migration.h b/drivers/gpu/drm/xe/xe_sriov_pf_migration.h
index df81a540c246a..16cb444c36aa6 100644
--- a/drivers/gpu/drm/xe/xe_sriov_pf_migration.h
+++ b/drivers/gpu/drm/xe/xe_sriov_pf_migration.h
@@ -18,6 +18,7 @@ int xe_sriov_pf_migration_restore_produce(struct xe_device *xe, unsigned int vfi
 					  struct xe_sriov_migration_data *data);
 struct xe_sriov_migration_data *
 xe_sriov_pf_migration_save_consume(struct xe_device *xe, unsigned int vfid);
+ssize_t xe_sriov_pf_migration_size(struct xe_device *xe, unsigned int vfid);
 wait_queue_head_t *xe_sriov_pf_migration_waitqueue(struct xe_device *xe, unsigned int vfid);
 
 #endif
-- 
2.50.1

Re: [PATCH v2 08/26] drm/xe/pf: Expose VF migration data size over debugfs
Posted by Michal Wajdeczko 3 months, 2 weeks ago

On 10/22/2025 12:41 AM, Michał Winiarski wrote:
> The size is normally used to make a decision on when to stop the device
> (mainly when it's in a pre_copy state).
> 
> Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c | 19 ++++++++++++
>  drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.h |  2 ++
>  drivers/gpu/drm/xe/xe_sriov_pf_debugfs.c      | 29 ++++++++++++++++++
>  drivers/gpu/drm/xe/xe_sriov_pf_migration.c    | 30 +++++++++++++++++++
>  drivers/gpu/drm/xe/xe_sriov_pf_migration.h    |  1 +
>  5 files changed, 81 insertions(+)
> 
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c
> index 8ba72165759b3..4e26feb9c267f 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c
> @@ -395,6 +395,25 @@ ssize_t xe_gt_sriov_pf_migration_write_guc_state(struct xe_gt *gt, unsigned int
>  }
>  #endif /* CONFIG_DEBUG_FS */
>  
> +/**
> + * xe_gt_sriov_pf_migration_size() - Total size of migration data from all components within a GT.
> + * @gt: the &xe_gt
> + * @vfid: the VF identifier
> + *
> + * This function is for PF only.
> + *
> + * Return: total migration data size in bytes or a negative error code on failure.
> + */
> +ssize_t xe_gt_sriov_pf_migration_size(struct xe_gt *gt, unsigned int vfid)
> +{
> +	ssize_t total = 0;
> +
> +	xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
> +
> +	/* Nothing to query yet - will be updated once per-GT migration data types are added */
> +	return total;
> +}
> +
>  /**
>   * xe_gt_sriov_pf_migration_ring_empty() - Check if a migration ring is empty.
>   * @gt: the &xe_gt
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.h b/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.h
> index 1ed2248f0a17e..e2d41750f863c 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.h
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.h
> @@ -15,6 +15,8 @@ int xe_gt_sriov_pf_migration_init(struct xe_gt *gt);
>  int xe_gt_sriov_pf_migration_save_guc_state(struct xe_gt *gt, unsigned int vfid);
>  int xe_gt_sriov_pf_migration_restore_guc_state(struct xe_gt *gt, unsigned int vfid);
>  
> +ssize_t xe_gt_sriov_pf_migration_size(struct xe_gt *gt, unsigned int vfid);
> +
>  bool xe_gt_sriov_pf_migration_ring_empty(struct xe_gt *gt, unsigned int vfid);
>  bool xe_gt_sriov_pf_migration_ring_full(struct xe_gt *gt, unsigned int vfid);
>  void xe_gt_sriov_pf_migration_ring_free(struct xe_gt *gt, unsigned int vfid);
> diff --git a/drivers/gpu/drm/xe/xe_sriov_pf_debugfs.c b/drivers/gpu/drm/xe/xe_sriov_pf_debugfs.c
> index a9a28aec22421..bc2d0b0342f22 100644
> --- a/drivers/gpu/drm/xe/xe_sriov_pf_debugfs.c
> +++ b/drivers/gpu/drm/xe/xe_sriov_pf_debugfs.c
> @@ -14,6 +14,7 @@
>  #include "xe_sriov_pf_control.h"
>  #include "xe_sriov_pf_debugfs.h"
>  #include "xe_sriov_pf_helpers.h"
> +#include "xe_sriov_pf_migration.h"
>  #include "xe_sriov_pf_provision.h"
>  #include "xe_sriov_pf_service.h"
>  #include "xe_sriov_printk.h"
> @@ -254,6 +255,33 @@ static const struct file_operations data_vf_fops = {
>  	.llseek		= default_llseek,
>  };
>  
> +static ssize_t size_read(struct file *file, char __user *ubuf, size_t count, loff_t *ppos)
> +{
> +	struct dentry *dent = file_dentry(file)->d_parent;
> +	struct xe_device *xe = extract_xe(dent);
> +	unsigned int vfid = extract_vfid(dent);
> +	char buf[21];
> +	ssize_t ret;
> +	int len;
> +
> +	xe_pm_runtime_get(xe);
> +	ret = xe_sriov_pf_migration_size(xe, vfid);
> +	xe_pm_runtime_put(xe);

IIRC during simple "cat migration_size" we might be called twice
to avoid that we can calc size in .open instead, see config_blob

but not a blocker, so

Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>

> +	if (ret < 0)
> +		return ret;
> +
> +	len = scnprintf(buf, sizeof(buf), "%zd\n", ret);
> +
> +	return simple_read_from_buffer(ubuf, count, ppos, buf, len);
> +}
> +
> +static const struct file_operations size_vf_fops = {
> +	.owner		= THIS_MODULE,
> +	.open		= simple_open,
> +	.read		= size_read,
> +	.llseek		= default_llseek,
> +};
> +
>  static void pf_populate_vf(struct xe_device *xe, struct dentry *vfdent)
>  {
>  	debugfs_create_file("pause", 0200, vfdent, xe, &pause_vf_fops);
> @@ -263,6 +291,7 @@ static void pf_populate_vf(struct xe_device *xe, struct dentry *vfdent)
>  	debugfs_create_file("save", 0600, vfdent, xe, &save_vf_fops);
>  	debugfs_create_file("restore", 0600, vfdent, xe, &restore_vf_fops);
>  	debugfs_create_file("migration_data", 0600, vfdent, xe, &data_vf_fops);
> +	debugfs_create_file("migration_size", 0400, vfdent, xe, &size_vf_fops);
>  }
>  
>  static void pf_populate_with_tiles(struct xe_device *xe, struct dentry *dent, unsigned int vfid)
> diff --git a/drivers/gpu/drm/xe/xe_sriov_pf_migration.c b/drivers/gpu/drm/xe/xe_sriov_pf_migration.c
> index 0b4b237780102..88babec9c893e 100644
> --- a/drivers/gpu/drm/xe/xe_sriov_pf_migration.c
> +++ b/drivers/gpu/drm/xe/xe_sriov_pf_migration.c
> @@ -242,3 +242,33 @@ int xe_sriov_pf_migration_restore_produce(struct xe_device *xe, unsigned int vfi
>  
>  	return xe_gt_sriov_pf_migration_restore_produce(gt, vfid, data);
>  }
> +
> +/**
> + * xe_sriov_pf_migration_size() - Total size of migration data from all components within a device
> + * @xe: the &xe_device
> + * @vfid: the VF identifier (can't be 0)
> + *
> + * This function is for PF only.
> + *
> + * Return: total migration data size in bytes or a negative error code on failure.
> + */
> +ssize_t xe_sriov_pf_migration_size(struct xe_device *xe, unsigned int vfid)
> +{
> +	size_t size = 0;
> +	struct xe_gt *gt;
> +	ssize_t ret;
> +	u8 gt_id;
> +
> +	xe_assert(xe, IS_SRIOV_PF(xe));
> +	xe_assert(xe, vfid);
> +
> +	for_each_gt(gt, xe, gt_id) {
> +		ret = xe_gt_sriov_pf_migration_size(gt, vfid);
> +		if (ret < 0)
> +			return ret;
> +
> +		size += ret;
> +	}
> +
> +	return size;
> +}
> diff --git a/drivers/gpu/drm/xe/xe_sriov_pf_migration.h b/drivers/gpu/drm/xe/xe_sriov_pf_migration.h
> index df81a540c246a..16cb444c36aa6 100644
> --- a/drivers/gpu/drm/xe/xe_sriov_pf_migration.h
> +++ b/drivers/gpu/drm/xe/xe_sriov_pf_migration.h
> @@ -18,6 +18,7 @@ int xe_sriov_pf_migration_restore_produce(struct xe_device *xe, unsigned int vfi
>  					  struct xe_sriov_migration_data *data);
>  struct xe_sriov_migration_data *
>  xe_sriov_pf_migration_save_consume(struct xe_device *xe, unsigned int vfid);
> +ssize_t xe_sriov_pf_migration_size(struct xe_device *xe, unsigned int vfid);
>  wait_queue_head_t *xe_sriov_pf_migration_waitqueue(struct xe_device *xe, unsigned int vfid);
>  
>  #endif