Merge tag 'drm-xe-fixes-2024-08-15' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-fixes

- Validate user fence during creation (Brost)
- Fix use after free when client stats are captured (Umesh)
- SRIOV fixes (Michal)
- Runtime PM fixes (Brost)

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/Zr4KWF5nM1YvnT8H@intel.com

Author: airlied

drivers/gpu/drm/xe/xe_device.c

@@ -87,9 +87,55 @@ static int xe_file_open(struct drm_device *dev, struct drm_file *file)
 	spin_unlock(&xe->clients.lock);
 
 	file->driver_priv = xef;
+	kref_init(&xef->refcount);
+
 	return 0;
 }
 
+static void xe_file_destroy(struct kref *ref)
+{
+	struct xe_file *xef = container_of(ref, struct xe_file, refcount);
+	struct xe_device *xe = xef->xe;
+
+	xa_destroy(&xef->exec_queue.xa);
+	mutex_destroy(&xef->exec_queue.lock);
+	xa_destroy(&xef->vm.xa);
+	mutex_destroy(&xef->vm.lock);
+
+	spin_lock(&xe->clients.lock);
+	xe->clients.count--;
+	spin_unlock(&xe->clients.lock);
+
+	xe_drm_client_put(xef->client);
+	kfree(xef);
+}
+
+/**
+ * xe_file_get() - Take a reference to the xe file object
+ * @xef: Pointer to the xe file
+ *
+ * Anyone with a pointer to xef must take a reference to the xe file
+ * object using this call.
+ *
+ * Return: xe file pointer
+ */
+struct xe_file *xe_file_get(struct xe_file *xef)
+{
+	kref_get(&xef->refcount);
+	return xef;
+}
+
+/**
+ * xe_file_put() - Drop a reference to the xe file object
+ * @xef: Pointer to the xe file
+ *
+ * Used to drop reference to the xef object
+ */
+void xe_file_put(struct xe_file *xef)
+{
+	kref_put(&xef->refcount, xe_file_destroy);
+}
+
 static void xe_file_close(struct drm_device *dev, struct drm_file *file)
 {
 	struct xe_device *xe = to_xe_device(dev);
@@ -98,6 +144,8 @@ static void xe_file_close(struct drm_device *dev, struct drm_file *file)
 	struct xe_exec_queue *q;
 	unsigned long idx;
 
+	xe_pm_runtime_get(xe);
+
 	/*
 	 * No need for exec_queue.lock here as there is no contention for it
 	 * when FD is closing as IOCTLs presumably can't be modifying the
@@ -108,21 +156,14 @@ static void xe_file_close(struct drm_device *dev, struct drm_file *file)
 		xe_exec_queue_kill(q);
 		xe_exec_queue_put(q);
 	}
-	xa_destroy(&xef->exec_queue.xa);
-	mutex_destroy(&xef->exec_queue.lock);
 	mutex_lock(&xef->vm.lock);
 	xa_for_each(&xef->vm.xa, idx, vm)
 		xe_vm_close_and_put(vm);
 	mutex_unlock(&xef->vm.lock);
-	xa_destroy(&xef->vm.xa);
-	mutex_destroy(&xef->vm.lock);
 
-	spin_lock(&xe->clients.lock);
-	xe->clients.count--;
-	spin_unlock(&xe->clients.lock);
+	xe_file_put(xef);
 
-	xe_drm_client_put(xef->client);
-	kfree(xef);
+	xe_pm_runtime_put(xe);
 }
 
 static const struct drm_ioctl_desc xe_ioctls[] = {

drivers/gpu/drm/xe/xe_device.h

@@ -170,4 +170,7 @@ static inline bool xe_device_wedged(struct xe_device *xe)
 
 void xe_device_declare_wedged(struct xe_device *xe);
 
+struct xe_file *xe_file_get(struct xe_file *xef);
+void xe_file_put(struct xe_file *xef);
+
 #endif

drivers/gpu/drm/xe/xe_device_types.h

@@ -566,6 +566,9 @@ struct xe_file {
 
 	/** @client: drm client */
 	struct xe_drm_client *client;
+
+	/** @refcount: ref count of this xe file */
+	struct kref refcount;
 };
 
 #endif

drivers/gpu/drm/xe/xe_drm_client.c

@@ -251,11 +251,8 @@ static void show_run_ticks(struct drm_printer *p, struct drm_file *file)
 
 	/* Accumulate all the exec queues from this client */
 	mutex_lock(&xef->exec_queue.lock);
-	xa_for_each(&xef->exec_queue.xa, i, q) {
+	xa_for_each(&xef->exec_queue.xa, i, q)
 		xe_exec_queue_update_run_ticks(q);
-		xef->run_ticks[q->class] += q->run_ticks - q->old_run_ticks;
-		q->old_run_ticks = q->run_ticks;
-	}
 	mutex_unlock(&xef->exec_queue.lock);
 
 	/* Get the total GPU cycles */

drivers/gpu/drm/xe/xe_exec_queue.c

@@ -37,6 +37,10 @@ static void __xe_exec_queue_free(struct xe_exec_queue *q)
 {
 	if (q->vm)
 		xe_vm_put(q->vm);
+
+	if (q->xef)
+		xe_file_put(q->xef);
+
 	kfree(q);
 }
 
@@ -649,6 +653,7 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data,
 		goto kill_exec_queue;
 
 	args->exec_queue_id = id;
+	q->xef = xe_file_get(xef);
 
 	return 0;
 
@@ -762,6 +767,7 @@ bool xe_exec_queue_is_idle(struct xe_exec_queue *q)
  */
 void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
 {
+	struct xe_file *xef;
 	struct xe_lrc *lrc;
 	u32 old_ts, new_ts;
 
@@ -773,6 +779,8 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
 	if (!q->vm || !q->vm->xef)
 		return;
 
+	xef = q->vm->xef;
+
 	/*
 	 * Only sample the first LRC. For parallel submission, all of them are
 	 * scheduled together and we compensate that below by multiplying by
@@ -783,7 +791,7 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
 	 */
 	lrc = q->lrc[0];
 	new_ts = xe_lrc_update_timestamp(lrc, &old_ts);
-	q->run_ticks += (new_ts - old_ts) * q->width;
+	xef->run_ticks[q->class] += (new_ts - old_ts) * q->width;
 }
 
 void xe_exec_queue_kill(struct xe_exec_queue *q)

drivers/gpu/drm/xe/xe_exec_queue_types.h

@@ -38,6 +38,9 @@ enum xe_exec_queue_priority {
  * a kernel object.
  */
 struct xe_exec_queue {
+	/** @xef: Back pointer to xe file if this is user created exec queue */
+	struct xe_file *xef;
+
 	/** @gt: graphics tile this exec queue can submit to */
 	struct xe_gt *gt;
 	/**
@@ -139,10 +142,6 @@ struct xe_exec_queue {
 	 * Protected by @vm's resv. Unused if @vm == NULL.
 	 */
 	u64 tlb_flush_seqno;
-	/** @old_run_ticks: prior hw engine class run time in ticks for this exec queue */
-	u64 old_run_ticks;
-	/** @run_ticks: hw engine class run time in ticks for this exec queue */
-	u64 run_ticks;
 	/** @lrc: logical ring context for this exec queue */
 	struct xe_lrc *lrc[];
 };

drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c

@@ -1927,6 +1927,7 @@ static int pf_validate_vf_config(struct xe_gt *gt, unsigned int vfid)
 {
 	struct xe_gt *primary_gt = gt_to_tile(gt)->primary_gt;
 	struct xe_device *xe = gt_to_xe(gt);
+	bool is_primary = !xe_gt_is_media_type(gt);
 	bool valid_ggtt, valid_ctxs, valid_dbs;
 	bool valid_any, valid_all;
 
@@ -1935,13 +1936,17 @@ static int pf_validate_vf_config(struct xe_gt *gt, unsigned int vfid)
 	valid_dbs = pf_get_vf_config_dbs(gt, vfid);
 
 	/* note that GuC doorbells are optional */
-	valid_any = valid_ggtt || valid_ctxs || valid_dbs;
-	valid_all = valid_ggtt && valid_ctxs;
+	valid_any = valid_ctxs || valid_dbs;
+	valid_all = valid_ctxs;
+
+	/* and GGTT/LMEM is configured on primary GT only */
+	valid_all = valid_all && valid_ggtt;
+	valid_any = valid_any || (valid_ggtt && is_primary);
 
 	if (IS_DGFX(xe)) {
 		bool valid_lmem = pf_get_vf_config_ggtt(primary_gt, vfid);
 
-		valid_any = valid_any || valid_lmem;
+		valid_any = valid_any || (valid_lmem && is_primary);
 		valid_all = valid_all && valid_lmem;
 	}
 

drivers/gpu/drm/xe/xe_gt_sriov_vf.c

@@ -850,7 +850,7 @@ static struct vf_runtime_reg *vf_lookup_reg(struct xe_gt *gt, u32 addr)
 
 	xe_gt_assert(gt, IS_SRIOV_VF(gt_to_xe(gt)));
 
-	return bsearch(&key, runtime->regs, runtime->regs_size, sizeof(key),
+	return bsearch(&key, runtime->regs, runtime->num_regs, sizeof(key),
 		       vf_runtime_reg_cmp);
 }