[PATCH v2 0/4] DRM RAS Fixes

[PATCH v2 0/4] DRM RAS Fixes

[Raag Jadav]

Detailed description in commit message.

v2: Use goto (Riana)
    Retain info as NULL on failure (Riana)

Raag Jadav (4):
  drm/ras: Cancel and free message on get counter failure
  drm/xe/drm_ras: Make counter allocation drm managed
  drm/xe/drm_ras: Add per node cleanup action
  drm/xe/hw_error: Use HW_ERR prefix in log

 drivers/gpu/drm/drm_ras.c        | 19 +++++-----
 drivers/gpu/drm/xe/xe_drm_ras.c  | 62 +++++++++++++-------------------
 drivers/gpu/drm/xe/xe_hw_error.c | 12 +++----
 3 files changed, 41 insertions(+), 52 deletions(-)

-- 
2.43.0

[PATCH v2 1/4] drm/ras: Cancel and free message on get counter failure

[Raag Jadav]

doit_reply_value() directly returns on get counter failure, which results
in stale sk_buff and genetlink header that aren't cleaned up. Fix it and
while at it, consolidate error handling using goto.

Fixes: c36218dc49f5 ("drm/ras: Introduce the DRM RAS infrastructure over generic netlink")
Signed-off-by: Raag Jadav <raag.jadav@intel.com>
---
v2: Use goto (Riana)
---
 drivers/gpu/drm/drm_ras.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/drm_ras.c b/drivers/gpu/drm/drm_ras.c
index d6eab29a1394..467a169026fc 100644
--- a/drivers/gpu/drm/drm_ras.c
+++ b/drivers/gpu/drm/drm_ras.c
@@ -201,25 +201,28 @@ static int doit_reply_value(struct genl_info *info, u32 node_id,
 
 	hdr = genlmsg_iput(msg, info);
 	if (!hdr) {
-		nlmsg_free(msg);
-		return -EMSGSIZE;
+		ret = -EMSGSIZE;
+		goto free_msg;
 	}
 
 	ret = get_node_error_counter(node_id, error_id,
 				     &error_name, &value);
 	if (ret)
-		return ret;
+		goto cancel_msg;
 
 	ret = msg_reply_value(msg, error_id, error_name, value);
-	if (ret) {
-		genlmsg_cancel(msg, hdr);
-		nlmsg_free(msg);
-		return ret;
-	}
+	if (ret)
+		goto cancel_msg;
 
 	genlmsg_end(msg, hdr);
 
 	return genlmsg_reply(msg, info);
+
+cancel_msg:
+	genlmsg_cancel(msg, hdr);
+free_msg:
+	nlmsg_free(msg);
+	return ret;
 }
 
 /**
-- 
2.43.0

[PATCH v2 2/4] drm/xe/drm_ras: Make counter allocation drm managed

[Raag Jadav]

cleanup_node_param() is not registered in case of counter allocation
failure, which results in stale memory of previous node that isn't
cleaned up on unwind. Fix this using drm managed allocation, which is
guaranteed to be cleaned up on unwind.

Fixes: b40db12b542f ("drm/xe/xe_drm_ras: Add support for XE DRM RAS")
Signed-off-by: Raag Jadav <raag.jadav@intel.com>
---
v2: Retain info as NULL on failure (Riana)
---
 drivers/gpu/drm/xe/xe_drm_ras.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_drm_ras.c b/drivers/gpu/drm/xe/xe_drm_ras.c
index c21c8b428de6..c1d5ac198a7c 100644
--- a/drivers/gpu/drm/xe/xe_drm_ras.c
+++ b/drivers/gpu/drm/xe/xe_drm_ras.c
@@ -80,7 +80,7 @@ static struct xe_drm_ras_counter *allocate_and_copy_counters(struct xe_device *x
 	struct xe_drm_ras_counter *counter;
 	int i;
 
-	counter = kcalloc(DRM_XE_RAS_ERR_COMP_MAX, sizeof(*counter), GFP_KERNEL);
+	counter = drmm_kcalloc(&xe->drm, DRM_XE_RAS_ERR_COMP_MAX, sizeof(*counter), GFP_KERNEL);
 	if (!counter)
 		return ERR_PTR(-ENOMEM);
 
@@ -135,7 +135,6 @@ static void cleanup_node_param(struct xe_drm_ras *ras, const enum drm_xe_ras_err
 {
 	struct drm_ras_node *node = &ras->node[severity];
 
-	kfree(ras->info[severity]);
 	ras->info[severity] = NULL;
 
 	kfree(node->device_name);
-- 
2.43.0

[PATCH v2 3/4] drm/xe/drm_ras: Add per node cleanup action

[Raag Jadav]

cleanup_node_param() is not registered for previous node in case of counter
allocation failure, which results in stale memory of previous node that
isn't cleaned up on unwind. Add per node cleanup action which guarantees
cleanup on unwind and also simplifies the cleanup logic.

Fixes: b40db12b542f ("drm/xe/xe_drm_ras: Add support for XE DRM RAS")
Signed-off-by: Raag Jadav <raag.jadav@intel.com>
---
 drivers/gpu/drm/xe/xe_drm_ras.c | 59 +++++++++++++--------------------
 1 file changed, 23 insertions(+), 36 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_drm_ras.c b/drivers/gpu/drm/xe/xe_drm_ras.c
index c1d5ac198a7c..b901976203fc 100644
--- a/drivers/gpu/drm/xe/xe_drm_ras.c
+++ b/drivers/gpu/drm/xe/xe_drm_ras.c
@@ -131,53 +131,46 @@ static int assign_node_params(struct xe_device *xe, struct drm_ras_node *node,
 	return 0;
 }
 
-static void cleanup_node_param(struct xe_drm_ras *ras, const enum drm_xe_ras_error_severity severity)
+static void cleanup_node_param(struct drm_ras_node *node)
 {
-	struct drm_ras_node *node = &ras->node[severity];
-
-	ras->info[severity] = NULL;
-
 	kfree(node->device_name);
 	node->device_name = NULL;
 }
 
+static void cleanup_node(struct drm_device *drm, void *node)
+{
+	drm_ras_node_unregister(node);
+	cleanup_node_param(node);
+}
+
 static int register_nodes(struct xe_device *xe)
 {
 	struct xe_drm_ras *ras = &xe->ras;
-	int i;
+	struct drm_ras_node *node;
+	int i, ret;
 
 	for_each_error_severity(i) {
-		struct drm_ras_node *node = &ras->node[i];
-		int ret;
+		node = &ras->node[i];
 
 		ret = assign_node_params(xe, node, i);
-		if (ret) {
-			cleanup_node_param(ras, i);
-			return ret;
-		}
+		if (ret)
+			break;
 
 		ret = drm_ras_node_register(node);
-		if (ret) {
-			cleanup_node_param(ras, i);
-			return ret;
-		}
-	}
-
-	return 0;
-}
-
-static void xe_drm_ras_unregister_nodes(struct drm_device *device, void *arg)
-{
-	struct xe_device *xe = arg;
-	struct xe_drm_ras *ras = &xe->ras;
-	int i;
+		if (ret)
+			break;
 
-	for_each_error_severity(i) {
-		struct drm_ras_node *node = &ras->node[i];
+		ret = drmm_add_action_or_reset(&xe->drm, cleanup_node, node);
+		if (ret)
+			break;
+	}
 
-		drm_ras_node_unregister(node);
-		cleanup_node_param(ras, i);
+	if (ret) {
+		cleanup_node_param(node);
+		ras->info[i] = NULL;
 	}
+
+	return ret;
 }
 
 /**
@@ -206,11 +199,5 @@ int xe_drm_ras_init(struct xe_device *xe)
 		return err;
 	}
 
-	err = drmm_add_action_or_reset(&xe->drm, xe_drm_ras_unregister_nodes, xe);
-	if (err) {
-		drm_err(&xe->drm, "Failed to add action for Xe DRM RAS (%pe)\n", ERR_PTR(err));
-		return err;
-	}
-
 	return 0;
 }
-- 
2.43.0

[PATCH v2 4/4] drm/xe/hw_error: Use HW_ERR prefix in log

[Raag Jadav]

Hardware errors should be logged with HW_ERR prefix. Make them
consistent with existing logs.

Fixes: 01aab7e1c9d4 ("drm/xe/xe_hw_error: Add support for PVC SoC errors")
Signed-off-by: Raag Jadav <raag.jadav@intel.com>
---
 drivers/gpu/drm/xe/xe_hw_error.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_hw_error.c b/drivers/gpu/drm/xe/xe_hw_error.c
index 5135e8e4093f..4b72959b2276 100644
--- a/drivers/gpu/drm/xe/xe_hw_error.c
+++ b/drivers/gpu/drm/xe/xe_hw_error.c
@@ -223,9 +223,9 @@ static void log_hw_error(struct xe_tile *tile, const char *name,
 	struct xe_device *xe = tile_to_xe(tile);
 
 	if (severity == DRM_XE_RAS_ERR_SEV_CORRECTABLE)
-		drm_warn(&xe->drm, "%s %s detected\n", name, severity_str);
+		drm_warn(&xe->drm, HW_ERR "%s %s detected\n", name, severity_str);
 	else
-		drm_err_ratelimited(&xe->drm, "%s %s detected\n", name, severity_str);
+		drm_err_ratelimited(&xe->drm, HW_ERR "%s %s detected\n", name, severity_str);
 }
 
 static void log_gt_err(struct xe_tile *tile, const char *name, int i, u32 err,
@@ -235,10 +235,10 @@ static void log_gt_err(struct xe_tile *tile, const char *name, int i, u32 err,
 	struct xe_device *xe = tile_to_xe(tile);
 
 	if (severity == DRM_XE_RAS_ERR_SEV_CORRECTABLE)
-		drm_warn(&xe->drm, "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n",
+		drm_warn(&xe->drm, HW_ERR "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n",
 			 name, severity_str, i, err);
 	else
-		drm_err_ratelimited(&xe->drm, "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n",
+		drm_err_ratelimited(&xe->drm, HW_ERR "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n",
 				    name, severity_str, i, err);
 }
 
@@ -255,9 +255,9 @@ static void log_soc_error(struct xe_tile *tile, const char * const *reg_info,
 
 	if (strcmp(name, "Undefined")) {
 		if (severity == DRM_XE_RAS_ERR_SEV_CORRECTABLE)
-			drm_warn(&xe->drm, "%s SOC %s detected", name, severity_str);
+			drm_warn(&xe->drm, HW_ERR "%s SOC %s detected", name, severity_str);
 		else
-			drm_err_ratelimited(&xe->drm, "%s SOC %s detected", name, severity_str);
+			drm_err_ratelimited(&xe->drm, HW_ERR "%s SOC %s detected", name, severity_str);
 		atomic_inc(&info[index].counter);
 	}
 }
-- 
2.43.0

Re: [PATCH v2 1/4] drm/ras: Cancel and free message on get counter failure

[Tauro, Riana]

On 5/23/2026 10:30 AM, Raag Jadav wrote:
> doit_reply_value() directly returns on get counter failure, which results
> in stale sk_buff and genetlink header that aren't cleaned up. Fix it and
> while at it, consolidate error handling using goto.
>
> Fixes: c36218dc49f5 ("drm/ras: Introduce the DRM RAS infrastructure over generic netlink")
> Signed-off-by: Raag Jadav <raag.jadav@intel.com>

Reviewed-by: Riana Tauro <riana.tauro@intel.com>

> ---
> v2: Use goto (Riana)
> ---
>   drivers/gpu/drm/drm_ras.c | 19 +++++++++++--------
>   1 file changed, 11 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/gpu/drm/drm_ras.c b/drivers/gpu/drm/drm_ras.c
> index d6eab29a1394..467a169026fc 100644
> --- a/drivers/gpu/drm/drm_ras.c
> +++ b/drivers/gpu/drm/drm_ras.c
> @@ -201,25 +201,28 @@ static int doit_reply_value(struct genl_info *info, u32 node_id,
>   
>   	hdr = genlmsg_iput(msg, info);
>   	if (!hdr) {
> -		nlmsg_free(msg);
> -		return -EMSGSIZE;
> +		ret = -EMSGSIZE;
> +		goto free_msg;
>   	}
>   
>   	ret = get_node_error_counter(node_id, error_id,
>   				     &error_name, &value);
>   	if (ret)
> -		return ret;
> +		goto cancel_msg;
>   
>   	ret = msg_reply_value(msg, error_id, error_name, value);
> -	if (ret) {
> -		genlmsg_cancel(msg, hdr);
> -		nlmsg_free(msg);
> -		return ret;
> -	}
> +	if (ret)
> +		goto cancel_msg;
>   
>   	genlmsg_end(msg, hdr);
>   
>   	return genlmsg_reply(msg, info);
> +
> +cancel_msg:
> +	genlmsg_cancel(msg, hdr);
> +free_msg:
> +	nlmsg_free(msg);
> +	return ret;
>   }
>   
>   /**

Re: [PATCH v2 3/4] drm/xe/drm_ras: Add per node cleanup action

[Tauro, Riana]

On 5/23/2026 10:30 AM, Raag Jadav wrote:
> cleanup_node_param() is not registered for previous node in case of counter
> allocation failure, which results in stale memory of previous node that
> isn't cleaned up on unwind. Add per node cleanup action which guarantees
> cleanup on unwind and also simplifies the cleanup logic.
>
> Fixes: b40db12b542f ("drm/xe/xe_drm_ras: Add support for XE DRM RAS")
> Signed-off-by: Raag Jadav <raag.jadav@intel.com>
> ---
>   drivers/gpu/drm/xe/xe_drm_ras.c | 59 +++++++++++++--------------------
>   1 file changed, 23 insertions(+), 36 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_drm_ras.c b/drivers/gpu/drm/xe/xe_drm_ras.c
> index c1d5ac198a7c..b901976203fc 100644
> --- a/drivers/gpu/drm/xe/xe_drm_ras.c
> +++ b/drivers/gpu/drm/xe/xe_drm_ras.c
> @@ -131,53 +131,46 @@ static int assign_node_params(struct xe_device *xe, struct drm_ras_node *node,
>   	return 0;
>   }
>   
> -static void cleanup_node_param(struct xe_drm_ras *ras, const enum drm_xe_ras_error_severity severity)
> +static void cleanup_node_param(struct drm_ras_node *node)
>   {
> -	struct drm_ras_node *node = &ras->node[severity];
> -
> -	ras->info[severity] = NULL;
> -
>   	kfree(node->device_name);
>   	node->device_name = NULL;
>   }
>   
> +static void cleanup_node(struct drm_device *drm, void *node)
> +{
> +	drm_ras_node_unregister(node);
> +	cleanup_node_param(node);
> +}
> +
>   static int register_nodes(struct xe_device *xe)
>   {
>   	struct xe_drm_ras *ras = &xe->ras;
> -	int i;
> +	struct drm_ras_node *node;
> +	int i, ret;
>   
>   	for_each_error_severity(i) {
> -		struct drm_ras_node *node = &ras->node[i];
> -		int ret;
> +		node = &ras->node[i];
>   
>   		ret = assign_node_params(xe, node, i);
> -		if (ret) {
> -			cleanup_node_param(ras, i);
> -			return ret;
> -		}
> +		if (ret)
> +			break;
>   
>   		ret = drm_ras_node_register(node);
> -		if (ret) {
> -			cleanup_node_param(ras, i);
> -			return ret;
> -		}
> -	}
> -
> -	return 0;
> -}
> -
> -static void xe_drm_ras_unregister_nodes(struct drm_device *device, void *arg)
> -{
> -	struct xe_device *xe = arg;
> -	struct xe_drm_ras *ras = &xe->ras;
> -	int i;
> +		if (ret)
> +			break;
>   
> -	for_each_error_severity(i) {
> -		struct drm_ras_node *node = &ras->node[i];
> +		ret = drmm_add_action_or_reset(&xe->drm, cleanup_node, node);
> +		if (ret)
> +			break;
On failure of drmm_add_action_or_reset , action is called. We don't need 
to cleanup_node_param again Thanks Riana
> +	}
>   
> -		drm_ras_node_unregister(node);
> -		cleanup_node_param(ras, i);
> +	if (ret) {
> +		cleanup_node_param(node);
> +		ras->info[i] = NULL;
>   	}
> +
> +	return ret;
>   }
>   
>   /**
> @@ -206,11 +199,5 @@ int xe_drm_ras_init(struct xe_device *xe)
>   		return err;
>   	}
>   
> -	err = drmm_add_action_or_reset(&xe->drm, xe_drm_ras_unregister_nodes, xe);
> -	if (err) {
> -		drm_err(&xe->drm, "Failed to add action for Xe DRM RAS (%pe)\n", ERR_PTR(err));
> -		return err;
> -	}
> -
>   	return 0;
>   }

Re: [PATCH v2 4/4] drm/xe/hw_error: Use HW_ERR prefix in log

[Tauro, Riana]

On 5/23/2026 10:30 AM, Raag Jadav wrote:
> Hardware errors should be logged with HW_ERR prefix. Make them
> consistent with existing logs.
>
> Fixes: 01aab7e1c9d4 ("drm/xe/xe_hw_error: Add support for PVC SoC errors")
> Signed-off-by: Raag Jadav <raag.jadav@intel.com>

LGTM

Reviewed-by: Riana Tauro <riana.tauro@intel.com>


> ---
>   drivers/gpu/drm/xe/xe_hw_error.c | 12 ++++++------
>   1 file changed, 6 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_hw_error.c b/drivers/gpu/drm/xe/xe_hw_error.c
> index 5135e8e4093f..4b72959b2276 100644
> --- a/drivers/gpu/drm/xe/xe_hw_error.c
> +++ b/drivers/gpu/drm/xe/xe_hw_error.c
> @@ -223,9 +223,9 @@ static void log_hw_error(struct xe_tile *tile, const char *name,
>   	struct xe_device *xe = tile_to_xe(tile);
>   
>   	if (severity == DRM_XE_RAS_ERR_SEV_CORRECTABLE)
> -		drm_warn(&xe->drm, "%s %s detected\n", name, severity_str);
> +		drm_warn(&xe->drm, HW_ERR "%s %s detected\n", name, severity_str);
>   	else
> -		drm_err_ratelimited(&xe->drm, "%s %s detected\n", name, severity_str);
> +		drm_err_ratelimited(&xe->drm, HW_ERR "%s %s detected\n", name, severity_str);
>   }
>   
>   static void log_gt_err(struct xe_tile *tile, const char *name, int i, u32 err,
> @@ -235,10 +235,10 @@ static void log_gt_err(struct xe_tile *tile, const char *name, int i, u32 err,
>   	struct xe_device *xe = tile_to_xe(tile);
>   
>   	if (severity == DRM_XE_RAS_ERR_SEV_CORRECTABLE)
> -		drm_warn(&xe->drm, "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n",
> +		drm_warn(&xe->drm, HW_ERR "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n",
>   			 name, severity_str, i, err);
>   	else
> -		drm_err_ratelimited(&xe->drm, "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n",
> +		drm_err_ratelimited(&xe->drm, HW_ERR "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n",
>   				    name, severity_str, i, err);
>   }
>   
> @@ -255,9 +255,9 @@ static void log_soc_error(struct xe_tile *tile, const char * const *reg_info,
>   
>   	if (strcmp(name, "Undefined")) {
>   		if (severity == DRM_XE_RAS_ERR_SEV_CORRECTABLE)
> -			drm_warn(&xe->drm, "%s SOC %s detected", name, severity_str);
> +			drm_warn(&xe->drm, HW_ERR "%s SOC %s detected", name, severity_str);
>   		else
> -			drm_err_ratelimited(&xe->drm, "%s SOC %s detected", name, severity_str);
> +			drm_err_ratelimited(&xe->drm, HW_ERR "%s SOC %s detected", name, severity_str);
>   		atomic_inc(&info[index].counter);
>   	}
>   }

Re: [PATCH v2 4/4] drm/xe/hw_error: Use HW_ERR prefix in log

[Michal Wajdeczko]

On 5/23/2026 7:00 AM, Raag Jadav wrote:
> Hardware errors should be logged with HW_ERR prefix. Make them
> consistent with existing logs.
> 
> Fixes: 01aab7e1c9d4 ("drm/xe/xe_hw_error: Add support for PVC SoC errors")
> Signed-off-by: Raag Jadav <raag.jadav@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_hw_error.c | 12 ++++++------
>  1 file changed, 6 insertions(+), 6 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_hw_error.c b/drivers/gpu/drm/xe/xe_hw_error.c
> index 5135e8e4093f..4b72959b2276 100644
> --- a/drivers/gpu/drm/xe/xe_hw_error.c
> +++ b/drivers/gpu/drm/xe/xe_hw_error.c
> @@ -223,9 +223,9 @@ static void log_hw_error(struct xe_tile *tile, const char *name,
>  	struct xe_device *xe = tile_to_xe(tile);
>  
>  	if (severity == DRM_XE_RAS_ERR_SEV_CORRECTABLE)
> -		drm_warn(&xe->drm, "%s %s detected\n", name, severity_str);
> +		drm_warn(&xe->drm, HW_ERR "%s %s detected\n", name, severity_str);

function is per-tile, so shouldn't we use tile-oriented logs instead?

		xe_tile_warn(tile, HW_ERR ...)

>  	else
> -		drm_err_ratelimited(&xe->drm, "%s %s detected\n", name, severity_str);
> +		drm_err_ratelimited(&xe->drm, HW_ERR "%s %s detected\n", name, severity_str);

		xe_tile_err_ratelimited(tile, HW_ERR ...)

>  }
>  
>  static void log_gt_err(struct xe_tile *tile, const char *name, int i, u32 err,
> @@ -235,10 +235,10 @@ static void log_gt_err(struct xe_tile *tile, const char *name, int i, u32 err,
>  	struct xe_device *xe = tile_to_xe(tile);
>  
>  	if (severity == DRM_XE_RAS_ERR_SEV_CORRECTABLE)
> -		drm_warn(&xe->drm, "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n",
> +		drm_warn(&xe->drm, HW_ERR "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n",
>  			 name, severity_str, i, err);
>  	else
> -		drm_err_ratelimited(&xe->drm, "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n",
> +		drm_err_ratelimited(&xe->drm, HW_ERR "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n",
>  				    name, severity_str, i, err);
>  }
>  
> @@ -255,9 +255,9 @@ static void log_soc_error(struct xe_tile *tile, const char * const *reg_info,
>  
>  	if (strcmp(name, "Undefined")) {
>  		if (severity == DRM_XE_RAS_ERR_SEV_CORRECTABLE)
> -			drm_warn(&xe->drm, "%s SOC %s detected", name, severity_str);
> +			drm_warn(&xe->drm, HW_ERR "%s SOC %s detected", name, severity_str);
>  		else
> -			drm_err_ratelimited(&xe->drm, "%s SOC %s detected", name, severity_str);
> +			drm_err_ratelimited(&xe->drm, HW_ERR "%s SOC %s detected", name, severity_str);
>  		atomic_inc(&info[index].counter);
>  	}
>  }

Re: [PATCH v2 4/4] drm/xe/hw_error: Use HW_ERR prefix in log

[Raag Jadav]

On Mon, Jun 01, 2026 at 01:13:12PM +0200, Michal Wajdeczko wrote:
> On 5/23/2026 7:00 AM, Raag Jadav wrote:
> > Hardware errors should be logged with HW_ERR prefix. Make them
> > consistent with existing logs.
> > 
> > Fixes: 01aab7e1c9d4 ("drm/xe/xe_hw_error: Add support for PVC SoC errors")
> > Signed-off-by: Raag Jadav <raag.jadav@intel.com>
> > ---
> >  drivers/gpu/drm/xe/xe_hw_error.c | 12 ++++++------
> >  1 file changed, 6 insertions(+), 6 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/xe/xe_hw_error.c b/drivers/gpu/drm/xe/xe_hw_error.c
> > index 5135e8e4093f..4b72959b2276 100644
> > --- a/drivers/gpu/drm/xe/xe_hw_error.c
> > +++ b/drivers/gpu/drm/xe/xe_hw_error.c
> > @@ -223,9 +223,9 @@ static void log_hw_error(struct xe_tile *tile, const char *name,
> >  	struct xe_device *xe = tile_to_xe(tile);
> >  
> >  	if (severity == DRM_XE_RAS_ERR_SEV_CORRECTABLE)
> > -		drm_warn(&xe->drm, "%s %s detected\n", name, severity_str);
> > +		drm_warn(&xe->drm, HW_ERR "%s %s detected\n", name, severity_str);
> 
> function is per-tile, so shouldn't we use tile-oriented logs instead?

Agree, but then it needs to be done file-wide which I'll pursue once
the fix lands and propageted.

Raag

> 		xe_tile_warn(tile, HW_ERR ...)
> 
> >  	else
> > -		drm_err_ratelimited(&xe->drm, "%s %s detected\n", name, severity_str);
> > +		drm_err_ratelimited(&xe->drm, HW_ERR "%s %s detected\n", name, severity_str);
> 
> 		xe_tile_err_ratelimited(tile, HW_ERR ...)
> 
> >  }
> >  
> >  static void log_gt_err(struct xe_tile *tile, const char *name, int i, u32 err,
> > @@ -235,10 +235,10 @@ static void log_gt_err(struct xe_tile *tile, const char *name, int i, u32 err,
> >  	struct xe_device *xe = tile_to_xe(tile);
> >  
> >  	if (severity == DRM_XE_RAS_ERR_SEV_CORRECTABLE)
> > -		drm_warn(&xe->drm, "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n",
> > +		drm_warn(&xe->drm, HW_ERR "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n",
> >  			 name, severity_str, i, err);
> >  	else
> > -		drm_err_ratelimited(&xe->drm, "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n",
> > +		drm_err_ratelimited(&xe->drm, HW_ERR "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n",
> >  				    name, severity_str, i, err);
> >  }
> >  
> > @@ -255,9 +255,9 @@ static void log_soc_error(struct xe_tile *tile, const char * const *reg_info,
> >  
> >  	if (strcmp(name, "Undefined")) {
> >  		if (severity == DRM_XE_RAS_ERR_SEV_CORRECTABLE)
> > -			drm_warn(&xe->drm, "%s SOC %s detected", name, severity_str);
> > +			drm_warn(&xe->drm, HW_ERR "%s SOC %s detected", name, severity_str);
> >  		else
> > -			drm_err_ratelimited(&xe->drm, "%s SOC %s detected", name, severity_str);
> > +			drm_err_ratelimited(&xe->drm, HW_ERR "%s SOC %s detected", name, severity_str);
> >  		atomic_inc(&info[index].counter);
> >  	}
> >  }
>