drm/amdgpu: guarantee bijective mapping of ring ids for LRU v3

Depending on usage patterns, the current LRU policy may create a
non-injective mapping between userspace ring ids and kernel rings.

This behaviour is undesired as apps that attempt to fill all HW blocks
would be unable to reach some of them.

This change forces the LRU policy to create bijective mappings only.

v2: compress ring_blacklist
v3: simplify amdgpu_ring_is_blacklisted() logic

Signed-off-by: Andres Rodriguez <andresx7@gmail.com>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

3 files changed, 42 insertions, 11 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
index 4073f072f6c4..9a14c27d99d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
@@ -124,10 +124,22 @@ static int amdgpu_lru_map(struct amdgpu_device *adev,
                           int user_ring,
                           struct amdgpu_ring **out_ring)
 {
-        int r;
+        int r, i, j;
         int ring_type = amdgpu_hw_ip_to_ring_type(mapper->hw_ip);
+        int ring_blacklist[AMDGPU_MAX_RINGS];
+        struct amdgpu_ring *ring;
 
-        r = amdgpu_ring_lru_get(adev, ring_type, out_ring);
+        /* 0 is a valid ring index, so initialize to -1 */
+        memset(ring_blacklist, 0xff, sizeof(ring_blacklist));
+
+        for (i = 0, j = 0; i < AMDGPU_MAX_RINGS; i++) {
+                ring = mapper->queue_map[i];
+                if (ring)
+                        ring_blacklist[j++] = ring->idx;
+        }
+
+        r = amdgpu_ring_lru_get(adev, ring_type, ring_blacklist,
+                                j, out_ring);
         if (r)
                 return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index f1076e3edf53..cef135ef7334 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -338,19 +338,34 @@ static void amdgpu_ring_lru_touch_locked(struct amdgpu_device *adev,
         list_move_tail(&ring->lru_list, &adev->ring_lru_list);
 }
 
+static bool amdgpu_ring_is_blacklisted(struct amdgpu_ring *ring,
+                                       int *blacklist, int num_blacklist)
+{
+        int i;
+
+        for (i = 0; i < num_blacklist; i++) {
+                if (ring->idx == blacklist[i])
+                        return true;
+        }
+
+        return false;
+}
+
 /**
  * amdgpu_ring_lru_get - get the least recently used ring for a HW IP block
  *
  * @adev: amdgpu_device pointer
  * @type: amdgpu_ring_type enum
+ * @blacklist: blacklisted ring ids array
+ * @num_blacklist: number of entries in @blacklist
  * @ring: output ring
  *
  * Retrieve the amdgpu_ring structure for the least recently used ring of
  * a specific IP block (all asics).
  * Returns 0 on success, error on failure.
  */
-int amdgpu_ring_lru_get(struct amdgpu_device *adev, int type,
-                        struct amdgpu_ring **ring)
+int amdgpu_ring_lru_get(struct amdgpu_device *adev, int type, int *blacklist,
+                        int num_blacklist, struct amdgpu_ring **ring)
 {
         struct amdgpu_ring *entry;
 
@@ -359,11 +374,15 @@ int amdgpu_ring_lru_get(struct amdgpu_device *adev, int type,
         *ring = NULL;
         spin_lock(&adev->ring_lru_list_lock);
         list_for_each_entry(entry, &adev->ring_lru_list, lru_list) {
-                if (entry->funcs->type == type) {
-                        *ring = entry;
-                        amdgpu_ring_lru_touch_locked(adev, *ring);
-                        break;
-                }
+                if (entry->funcs->type != type)
+                        continue;
+
+                if (amdgpu_ring_is_blacklisted(entry, blacklist, num_blacklist))
+                        continue;
+
+                *ring = entry;
+                amdgpu_ring_lru_touch_locked(adev, *ring);
+                break;
         }
         spin_unlock(&adev->ring_lru_list_lock);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index 577528a9af0b..a1dd9077c064 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -201,8 +201,8 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
                      unsigned ring_size, struct amdgpu_irq_src *irq_src,
                      unsigned irq_type);
 void amdgpu_ring_fini(struct amdgpu_ring *ring);
-int amdgpu_ring_lru_get(struct amdgpu_device *adev, int hw_ip,
-                        struct amdgpu_ring **ring);
+int amdgpu_ring_lru_get(struct amdgpu_device *adev, int type, int *blacklist,
+                        int num_blacklist, struct amdgpu_ring **ring);
 void amdgpu_ring_lru_touch(struct amdgpu_device *adev, struct amdgpu_ring *ring);
 static inline void amdgpu_ring_clear_ring(struct amdgpu_ring *ring)
 {