drm/amdgpu: Add KFD eviction fence

This fence is used by KFD to keep memory resident while user mode
queues are enabled. Trying to evict memory will trigger the
enable_signaling callback, which starts a KFD eviction, which
involves preempting user mode queues before signaling the fence.
There is one such fence per process.

v2:
* Grab a reference to mm_struct
* Dereference fence after NULL check
* Simplify fence release, no need to signal without anyone waiting
* Added signed-off-by Harish, who is the original author of this code

v3:
* update MAINTAINERS file
* change amd_kfd_ prefix to amdkfd_
* remove useless initialization of variable to NULL

v4:
* set amdkfd_fence_ops to be static
* Suggested by: Fengguang Wu <fengguang.wu@intel.com>

Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

1 files changed, 18 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 28c33d711bab..5fcb3488a595 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -46,6 +46,7 @@
 #include "amdgpu.h"
 #include "amdgpu_object.h"
 #include "amdgpu_trace.h"
+#include "amdgpu_amdkfd.h"
 #include "bif/bif_4_1_d.h"
 
 #define DRM_FILE_PAGE_OFFSET (0x100000000ULL >> PAGE_SHIFT)
@@ -1171,6 +1172,23 @@ static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo,
 {
         unsigned long num_pages = bo->mem.num_pages;
         struct drm_mm_node *node = bo->mem.mm_node;
+        struct reservation_object_list *flist;
+        struct dma_fence *f;
+        int i;
+
+        /* If bo is a KFD BO, check if the bo belongs to the current process.
+         * If true, then return false as any KFD process needs all its BOs to
+         * be resident to run successfully
+         */
+        flist = reservation_object_get_list(bo->resv);
+        if (flist) {
+                for (i = 0; i < flist->shared_count; ++i) {
+                        f = rcu_dereference_protected(flist->shared[i],
+                                reservation_object_held(bo->resv));
+                        if (amdkfd_fence_check_mm(f, current->mm))
+                                return false;
+                }
+        }
 
         switch (bo->mem.mem_type) {
         case TTM_PL_TT: