drm/amdgpu/gfx10: set UNORD_DISPATCH in compute MQDs

[ Upstream commit 03ff6d7238b77e5fb2b85dc5fe01d2db9eb893bd ]

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.  Updated firmware is also
required for AQL.

Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index d63cab294883b8b44caa908d5bafaeaf19750ef6..ecb622b7f9709c1a0f9e5307b3dad1da7f0f8f05 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -6589,7 +6589,7 @@ static int gfx_v10_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 #ifdef __BIG_ENDIAN
        tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, ENDIAN_SWAP, 1);
 #endif
-       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,
                            prop->allow_tunneling);
        tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1);

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
index 8b7fed91352696cf2b5cafab0680ad0737fa95ee..22cbfa1bdaddb9a764053421b16159391c1ba56d 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
@@ -170,6 +170,7 @@ 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);