drm/amdgpu/gfx12: set UNORD_DISPATCH in compute MQDs

This needs to be set to 1 to avoid a potential deadlock in
the GC 10.x and newer.  On GC 9.x and older, this needs
to be set to 0. This can lead to hangs in some mixed
graphics and compute workloads.

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3575
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 40318a2406bd426c6f4591269669c04e8eda571d)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
index 2c611b8..e45d23e 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
@@ -3005,7 +3005,7 @@ static int gfx_v12_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
                            (order_base_2(prop->queue_size / 4) - 1));
        tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, RPTR_BLOCK_SIZE,
                            (order_base_2(AMDGPU_GPU_PAGE_SIZE / 4) - 1));
-       tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 0);
+       tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 1);
        tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TUNNEL_DISPATCH, 0);
        tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1);
        tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, KMD_QUEUE, 1);

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c
index b7a08e7..d163d92 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c
@@ -187,6 +187,7 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
        m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
        m->cp_hqd_pq_control |=
                        ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
+       m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
        pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
 
        m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);