intel/ds: Fix crash when allocating more intel_ds_queues than u_vector was initialized

u_vector_add() don't keep the returned pointers valid.
After the initial size allocated in u_vector_init() is reached it will
allocate a bigger buffer and copy data from older buffer to the new
one and free the old buffer, making all the previous pointers returned
by u_vector_add() invalid and crashing the application when trying to
access it.

This is reproduced when running
dEQP-VK.synchronization.signal_order.timeline_semaphore.* in DG2 SKUs
that has 4 CCS engines, INTEL_COMPUTE_CLASS=1 is set and of course
perfetto build is enabled.

To fix this issue here I'm moving the storage/allocation of
struct intel_ds_queue to struct anv_queue/iris_batch and using
struct list_head to maintain a chain of intel_ds_queue of the
intel_ds_device.
This allows us to append or remove queues dynamically in future if
necessary.

Fixes: e760c5b37b ("anv: add perfetto source")
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20977>

src/intel/vulkan/anv_batch_chain.c

@@ -1341,14 +1341,14 @@ anv_queue_submit(struct vk_queue *vk_queue,
       return VK_SUCCESS;
    }
 
-   uint64_t start_ts = intel_ds_begin_submit(queue->ds);
+   uint64_t start_ts = intel_ds_begin_submit(&queue->ds);
 
    pthread_mutex_lock(&device->mutex);
    result = anv_queue_submit_locked(queue, submit);
    /* Take submission ID under lock */
    pthread_mutex_unlock(&device->mutex);
 
-   intel_ds_end_submit(queue->ds, start_ts);
+   intel_ds_end_submit(&queue->ds, start_ts);
 
    return result;
 }

src/intel/vulkan/anv_private.h

@@ -1055,7 +1055,7 @@ struct anv_queue {
    /** Synchronization object for debug purposes (DEBUG_SYNC) */
    struct vk_sync                           *sync;
 
-   struct intel_ds_queue *                   ds;
+   struct intel_ds_queue                     ds;
 };
 
 struct nir_xfb_info;

src/intel/vulkan/anv_utrace.c

@@ -114,7 +114,7 @@ anv_device_utrace_flush_cmd_buffers(struct anv_queue *queue,
    if (!flush)
       return vk_error(device, VK_ERROR_OUT_OF_HOST_MEMORY);
 
-   intel_ds_flush_data_init(&flush->ds, queue->ds, queue->ds->submission_id);
+   intel_ds_flush_data_init(&flush->ds, &queue->ds, queue->ds.submission_id);
 
    result = vk_sync_create(&device->vk, &device->physical->sync_syncobj_type,
                            0, 0, &flush->sync);
@@ -288,10 +288,9 @@ anv_device_utrace_init(struct anv_device *device)
    for (uint32_t q = 0; q < device->queue_count; q++) {
       struct anv_queue *queue = &device->queues[q];
 
-      queue->ds =
-         intel_ds_device_add_queue(&device->ds, "%s%u",
-                                   intel_engines_class_to_string(queue->family->engine_class),
-                                   queue->vk.index_in_family);
+      intel_ds_device_init_queue(&device->ds, &queue->ds, "%s%u",
+                                 intel_engines_class_to_string(queue->family->engine_class),
+                                 queue->vk.index_in_family);
    }
 }