drm/amdkfd: Fix user queue validation on Gfx7/8

To workaround queue full h/w issue on Gfx7/8, when application create
AQL queue, the ring buffer bo allocate size is queue_size/2 and
map queue_size ring buffer to GPU in 2 pieces using 2 attachments, each
attachment map size is queue_size/2, with same ring_bo backing memory.

For Gfx7/8, user queue buffer validation should use queue_size/2 to
verify ring_bo allocation and mapping size.

Fixes: 68e599db7a54 ("drm/amdkfd: Validate user queue buffers")
Suggested-by: Tomáš Trnka <trnka@scm.com>
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit e7a477735f1771b9a9346a5fbd09d7ff0641723a)
Cc: stable@vger.kernel.org

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
index 24396a2c77bd01eac1cc1210ba22e0c1b12d248b..4afff7094cafcdc64efcae179a599cbd23fa991a 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
@@ -233,6 +233,7 @@ void kfd_queue_buffer_put(struct amdgpu_bo **bo)
 int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_properties *properties)
 {
        struct kfd_topology_device *topo_dev;
+       u64 expected_queue_size;
        struct amdgpu_vm *vm;
        u32 total_cwsr_size;
        int err;
@@ -241,6 +242,15 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope
        if (!topo_dev)
                return -EINVAL;
 
+       /* AQL queues on GFX7 and GFX8 appear twice their actual size */
+       if (properties->type == KFD_QUEUE_TYPE_COMPUTE &&
+           properties->format == KFD_QUEUE_FORMAT_AQL &&
+           topo_dev->node_props.gfx_target_version >= 70000 &&
+           topo_dev->node_props.gfx_target_version < 90000)
+               expected_queue_size = properties->queue_size / 2;
+       else
+               expected_queue_size = properties->queue_size;
+
        vm = drm_priv_to_vm(pdd->drm_priv);
        err = amdgpu_bo_reserve(vm->root.bo, false);
        if (err)
@@ -255,7 +265,7 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope
                goto out_err_unreserve;
 
        err = kfd_queue_buffer_get(vm, (void *)properties->queue_address,
-                                  &properties->ring_bo, properties->queue_size);
+                                  &properties->ring_bo, expected_queue_size);
        if (err)
                goto out_err_unreserve;