Merge tag 'drm-misc-fixes-2024-10-31' of https://gitlab.freedesktop.org/drm/misc/kernel into drm-fixes

Short summary of fixes pull:

ivpu:
- Fix firewall IRQ handling

panthor:
- Fix firmware initialization wrt page sizes
- Fix handling and reporting of dead job groups

sched:
- Guarantee forward progress via WC_MEM_RECLAIM

tests:
- Fix memory leak in drm_display_mode_from_cea_vic()

Signed-off-by: Dave Airlie <[email protected]>

From: Thomas Zimmermann <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

Author: airlied

drivers/accel/ivpu/ivpu_debugfs.c

@@ -108,6 +108,14 @@ static int reset_pending_show(struct seq_file *s, void *v)
 	return 0;
 }
 
+static int firewall_irq_counter_show(struct seq_file *s, void *v)
+{
+	struct ivpu_device *vdev = seq_to_ivpu(s);
+
+	seq_printf(s, "%d\n", atomic_read(&vdev->hw->firewall_irq_counter));
+	return 0;
+}
+
 static const struct drm_debugfs_info vdev_debugfs_list[] = {
 	{"bo_list", bo_list_show, 0},
 	{"fw_name", fw_name_show, 0},
@@ -116,6 +124,7 @@ static const struct drm_debugfs_info vdev_debugfs_list[] = {
 	{"last_bootmode", last_bootmode_show, 0},
 	{"reset_counter", reset_counter_show, 0},
 	{"reset_pending", reset_pending_show, 0},
+	{"firewall_irq_counter", firewall_irq_counter_show, 0},
 };
 
 static ssize_t

drivers/accel/ivpu/ivpu_hw.c

@@ -249,6 +249,7 @@ int ivpu_hw_init(struct ivpu_device *vdev)
 	platform_init(vdev);
 	wa_init(vdev);
 	timeouts_init(vdev);
+	atomic_set(&vdev->hw->firewall_irq_counter, 0);
 
 	return 0;
 }

drivers/accel/ivpu/ivpu_hw.h

@@ -52,6 +52,7 @@ struct ivpu_hw_info {
 	int dma_bits;
 	ktime_t d0i3_entry_host_ts;
 	u64 d0i3_entry_vpu_ts;
+	atomic_t firewall_irq_counter;
 };
 
 int ivpu_hw_init(struct ivpu_device *vdev);

drivers/accel/ivpu/ivpu_hw_ip.c

@@ -1062,7 +1062,10 @@ static void irq_wdt_mss_handler(struct ivpu_device *vdev)
 
 static void irq_noc_firewall_handler(struct ivpu_device *vdev)
 {
-	ivpu_pm_trigger_recovery(vdev, "NOC Firewall IRQ");
+	atomic_inc(&vdev->hw->firewall_irq_counter);
+
+	ivpu_dbg(vdev, IRQ, "NOC Firewall interrupt detected, counter %d\n",
+		 atomic_read(&vdev->hw->firewall_irq_counter));
 }
 
 /* Handler for IRQs from NPU core */

drivers/gpu/drm/panthor/panthor_fw.c

@@ -487,6 +487,7 @@ static int panthor_fw_load_section_entry(struct panthor_device *ptdev,
 					 struct panthor_fw_binary_iter *iter,
 					 u32 ehdr)
 {
+	ssize_t vm_pgsz = panthor_vm_page_size(ptdev->fw->vm);
 	struct panthor_fw_binary_section_entry_hdr hdr;
 	struct panthor_fw_section *section;
 	u32 section_size;
@@ -515,8 +516,7 @@ static int panthor_fw_load_section_entry(struct panthor_device *ptdev,
 		return -EINVAL;
 	}
 
-	if ((hdr.va.start & ~PAGE_MASK) != 0 ||
-	    (hdr.va.end & ~PAGE_MASK) != 0) {
+	if (!IS_ALIGNED(hdr.va.start, vm_pgsz) || !IS_ALIGNED(hdr.va.end, vm_pgsz)) {
 		drm_err(&ptdev->base, "Firmware corrupted, virtual addresses not page aligned: 0x%x-0x%x\n",
 			hdr.va.start, hdr.va.end);
 		return -EINVAL;

drivers/gpu/drm/panthor/panthor_gem.c

@@ -44,8 +44,7 @@ void panthor_kernel_bo_destroy(struct panthor_kernel_bo *bo)
 			to_panthor_bo(bo->obj)->exclusive_vm_root_gem != panthor_vm_root_gem(vm)))
 		goto out_free_bo;
 
-	ret = panthor_vm_unmap_range(vm, bo->va_node.start,
-				     panthor_kernel_bo_size(bo));
+	ret = panthor_vm_unmap_range(vm, bo->va_node.start, bo->va_node.size);
 	if (ret)
 		goto out_free_bo;
 
@@ -95,10 +94,16 @@ panthor_kernel_bo_create(struct panthor_device *ptdev, struct panthor_vm *vm,
 	}
 
 	bo = to_panthor_bo(&obj->base);
-	size = obj->base.size;
 	kbo->obj = &obj->base;
 	bo->flags = bo_flags;
 
+	/* The system and GPU MMU page size might differ, which becomes a
+	 * problem for FW sections that need to be mapped at explicit address
+	 * since our PAGE_SIZE alignment might cover a VA range that's
+	 * expected to be used for another section.
+	 * Make sure we never map more than we need.
+	 */
+	size = ALIGN(size, panthor_vm_page_size(vm));
 	ret = panthor_vm_alloc_va(vm, gpu_va, size, &kbo->va_node);
 	if (ret)
 		goto err_put_obj;

drivers/gpu/drm/panthor/panthor_mmu.c

@@ -826,6 +826,14 @@ void panthor_vm_idle(struct panthor_vm *vm)
 	mutex_unlock(&ptdev->mmu->as.slots_lock);
 }
 
+u32 panthor_vm_page_size(struct panthor_vm *vm)
+{
+	const struct io_pgtable *pgt = io_pgtable_ops_to_pgtable(vm->pgtbl_ops);
+	u32 pg_shift = ffs(pgt->cfg.pgsize_bitmap) - 1;
+
+	return 1u << pg_shift;
+}
+
 static void panthor_vm_stop(struct panthor_vm *vm)
 {
 	drm_sched_stop(&vm->sched, NULL);
@@ -1025,12 +1033,13 @@ int
 panthor_vm_alloc_va(struct panthor_vm *vm, u64 va, u64 size,
 		    struct drm_mm_node *va_node)
 {
+	ssize_t vm_pgsz = panthor_vm_page_size(vm);
 	int ret;
 
-	if (!size || (size & ~PAGE_MASK))
+	if (!size || !IS_ALIGNED(size, vm_pgsz))
 		return -EINVAL;
 
-	if (va != PANTHOR_VM_KERNEL_AUTO_VA && (va & ~PAGE_MASK))
+	if (va != PANTHOR_VM_KERNEL_AUTO_VA && !IS_ALIGNED(va, vm_pgsz))
 		return -EINVAL;
 
 	mutex_lock(&vm->mm_lock);
@@ -2366,11 +2375,12 @@ panthor_vm_bind_prepare_op_ctx(struct drm_file *file,
 			       const struct drm_panthor_vm_bind_op *op,
 			       struct panthor_vm_op_ctx *op_ctx)
 {
+	ssize_t vm_pgsz = panthor_vm_page_size(vm);
 	struct drm_gem_object *gem;
 	int ret;
 
 	/* Aligned on page size. */
-	if ((op->va | op->size) & ~PAGE_MASK)
+	if (!IS_ALIGNED(op->va | op->size, vm_pgsz))
 		return -EINVAL;
 
 	switch (op->flags & DRM_PANTHOR_VM_BIND_OP_TYPE_MASK) {

drivers/gpu/drm/panthor/panthor_mmu.h

@@ -30,6 +30,7 @@ panthor_vm_get_bo_for_va(struct panthor_vm *vm, u64 va, u64 *bo_offset);
 
 int panthor_vm_active(struct panthor_vm *vm);
 void panthor_vm_idle(struct panthor_vm *vm);
+u32 panthor_vm_page_size(struct panthor_vm *vm);
 int panthor_vm_as(struct panthor_vm *vm);
 int panthor_vm_flush_all(struct panthor_vm *vm);
 

drivers/gpu/drm/panthor/panthor_sched.c

@@ -589,10 +589,11 @@ struct panthor_group {
 	 * @timedout: True when a timeout occurred on any of the queues owned by
 	 * this group.
 	 *
-	 * Timeouts can be reported by drm_sched or by the FW. In any case, any
-	 * timeout situation is unrecoverable, and the group becomes useless.
-	 * We simply wait for all references to be dropped so we can release the
-	 * group object.
+	 * Timeouts can be reported by drm_sched or by the FW. If a reset is required,
+	 * and the group can't be suspended, this also leads to a timeout. In any case,
+	 * any timeout situation is unrecoverable, and the group becomes useless. We
+	 * simply wait for all references to be dropped so we can release the group
+	 * object.
 	 */
 	bool timedout;
 
@@ -2640,6 +2641,12 @@ void panthor_sched_suspend(struct panthor_device *ptdev)
 		csgs_upd_ctx_init(&upd_ctx);
 		while (slot_mask) {
 			u32 csg_id = ffs(slot_mask) - 1;
+			struct panthor_csg_slot *csg_slot = &sched->csg_slots[csg_id];
+
+			/* We consider group suspension failures as fatal and flag the
+			 * group as unusable by setting timedout=true.
+			 */
+			csg_slot->group->timedout = true;
 
 			csgs_upd_ctx_queue_reqs(ptdev, &upd_ctx, csg_id,
 						CSG_STATE_TERMINATE,
@@ -3409,6 +3416,11 @@ panthor_job_create(struct panthor_file *pfile,
 		goto err_put_job;
 	}
 
+	if (!group_can_run(job->group)) {
+		ret = -EINVAL;
+		goto err_put_job;
+	}
+
 	if (job->queue_idx >= job->group->queue_count ||
 	    !job->group->queues[job->queue_idx]) {
 		ret = -EINVAL;

drivers/gpu/drm/scheduler/sched_main.c

@@ -1276,10 +1276,11 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 		sched->own_submit_wq = false;
 	} else {
 #ifdef CONFIG_LOCKDEP
-		sched->submit_wq = alloc_ordered_workqueue_lockdep_map(name, 0,
+		sched->submit_wq = alloc_ordered_workqueue_lockdep_map(name,
+								       WQ_MEM_RECLAIM,
 								       &drm_sched_lockdep_map);
 #else
-		sched->submit_wq = alloc_ordered_workqueue(name, 0);
+		sched->submit_wq = alloc_ordered_workqueue(name, WQ_MEM_RECLAIM);
 #endif
 		if (!sched->submit_wq)
 			return -ENOMEM;