14 files changed, 95 insertions, 64 deletions

diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c
index 57da14c15987..56e0a0e1b600 100644
--- a/drivers/dma-buf/dma-fence.c
+++ b/drivers/dma-buf/dma-fence.c
@@ -75,11 +75,6 @@ int dma_fence_signal_locked(struct dma_fence *fence)
         if (WARN_ON(!fence))
                 return -EINVAL;
 
-        if (!ktime_to_ns(fence->timestamp)) {
-                fence->timestamp = ktime_get();
-                smp_mb__before_atomic();
-        }
-
         if (test_and_set_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
                 ret = -EINVAL;
 
@@ -87,8 +82,11 @@ int dma_fence_signal_locked(struct dma_fence *fence)
                  * we might have raced with the unlocked dma_fence_signal,
                  * still run through all callbacks
                  */
-        } else
+        } else {
+                fence->timestamp = ktime_get();
+                set_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags);
                 trace_dma_fence_signaled(fence);
+        }
 
         list_for_each_entry_safe(cur, tmp, &fence->cb_list, node) {
                 list_del_init(&cur->node);
@@ -115,14 +113,11 @@ int dma_fence_signal(struct dma_fence *fence)
         if (!fence)
                 return -EINVAL;
 
-        if (!ktime_to_ns(fence->timestamp)) {
-                fence->timestamp = ktime_get();
-                smp_mb__before_atomic();
-        }
-
         if (test_and_set_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
                 return -EINVAL;
 
+        fence->timestamp = ktime_get();
+        set_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags);
         trace_dma_fence_signaled(fence);
 
         if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &fence->flags)) {
diff --git a/drivers/dma-buf/sync_debug.c b/drivers/dma-buf/sync_debug.c
index 82a6e7f6d37f..59a3b2f8ee91 100644
--- a/drivers/dma-buf/sync_debug.c
+++ b/drivers/dma-buf/sync_debug.c
@@ -84,7 +84,7 @@ static void sync_print_fence(struct seq_file *s,
                    show ? "_" : "",
                    sync_status_str(status));
 
-        if (status) {
+        if (test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags)) {
                 struct timespec64 ts64 =
                         ktime_to_timespec64(fence->timestamp);
 
diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c
index 545e2c5c4815..d7e219d2669d 100644
--- a/drivers/dma-buf/sync_file.c
+++ b/drivers/dma-buf/sync_file.c
@@ -391,7 +391,13 @@ static void sync_fill_fence_info(struct dma_fence *fence,
                 sizeof(info->driver_name));
 
         info->status = dma_fence_get_status(fence);
-        info->timestamp_ns = ktime_to_ns(fence->timestamp);
+        while (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags) &&
+               !test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags))
+                cpu_relax();
+        info->timestamp_ns =
+                test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags) ?
+                ktime_to_ns(fence->timestamp) :
+                ktime_set(0, 0);
 }
 
 static long sync_file_ioctl_fence_info(struct sync_file *sync_file,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 5f8ada1d872b..37971d9402e3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -101,7 +101,6 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
         if (adev->kfd) {
                 struct kgd2kfd_shared_resources gpu_resources = {
                         .compute_vmid_bitmap = 0xFF00,
-                        .num_mec = adev->gfx.mec.num_mec,
                         .num_pipe_per_mec = adev->gfx.mec.num_pipe_per_mec,
                         .num_queue_per_pipe = adev->gfx.mec.num_queue_per_pipe
                 };
@@ -122,7 +121,7 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 
                 /* According to linux/bitmap.h we shouldn't use bitmap_clear if
                  * nbits is not compile time constant */
-                last_valid_bit = adev->gfx.mec.num_mec
+                last_valid_bit = 1 /* only first MEC can have compute queues */
                                 * adev->gfx.mec.num_pipe_per_mec
                                 * adev->gfx.mec.num_queue_per_pipe;
                 for (i = last_valid_bit; i < KGD_MAX_QUEUES; ++i)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 88187bfc5ea3..3f95f7cb4019 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -226,10 +226,6 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 
         kfd->shared_resources = *gpu_resources;
 
-        /* We only use the first MEC */
-        if (kfd->shared_resources.num_mec > 1)
-                kfd->shared_resources.num_mec = 1;
-
         /* calculate max size of mqds needed for queues */
         size = max_num_of_queues_per_device *
                         kfd->device_info->mqd_size_aligned;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 955aa304ff48..602769ced3bd 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -77,13 +77,6 @@ static bool is_pipe_enabled(struct device_queue_manager *dqm, int mec, int pipe)
         return false;
 }
 
-unsigned int get_mec_num(struct device_queue_manager *dqm)
-{
-        BUG_ON(!dqm || !dqm->dev);
-
-        return dqm->dev->shared_resources.num_mec;
-}
-
 unsigned int get_queues_num(struct device_queue_manager *dqm)
 {
         BUG_ON(!dqm || !dqm->dev);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
index 66b9615bc3c1..faf820a06400 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -180,7 +180,6 @@ void device_queue_manager_init_cik(struct device_queue_manager_asic_ops *ops);
 void device_queue_manager_init_vi(struct device_queue_manager_asic_ops *ops);
 void program_sh_mem_settings(struct device_queue_manager *dqm,
                                         struct qcm_process_device *qpd);
-unsigned int get_mec_num(struct device_queue_manager *dqm);
 unsigned int get_queues_num(struct device_queue_manager *dqm);
 unsigned int get_queues_per_pipe(struct device_queue_manager *dqm);
 unsigned int get_pipes_per_mec(struct device_queue_manager *dqm);
diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index 91ef1484b3bb..36f376677a53 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -63,9 +63,6 @@ struct kgd2kfd_shared_resources {
         /* Bit n == 1 means VMID n is available for KFD. */
         unsigned int compute_vmid_bitmap;
 
-        /* number of mec available from the hardware */
-        uint32_t num_mec;
-
         /* number of pipes per mec */
         uint32_t num_pipe_per_mec;
 
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index bfd237c15e76..ae5f06895562 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -330,6 +330,13 @@ static bool drm_dp_sideband_msg_build(struct drm_dp_sideband_msg_rx *msg,
                         return false;