[PATCH 06/10] drm/ttm: fix busy memory to fail other user v10
Christian König
ckoenig.leichtzumerken at gmail.com
Tue May 28 16:25:53 UTC 2019
BOs on the LRU might be blocked during command submission
and cause OOM situations.
Avoid this by blocking for the first busy BO not locked by
the same ticket as the BO we are searching space for.
v10: completely start over with the patch since we didn't
handled a whole bunch of corner cases.
Signed-off-by: Christian König <christian.koenig at amd.com>
---
drivers/gpu/drm/ttm/ttm_bo.c | 77 ++++++++++++++++++++++++++++++------
1 file changed, 66 insertions(+), 11 deletions(-)
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 3bc31da1df67..98aa90056807 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -774,32 +774,72 @@ EXPORT_SYMBOL(ttm_bo_eviction_valuable);
* b. Otherwise, trylock it.
*/
static bool ttm_bo_evict_swapout_allowable(struct ttm_buffer_object *bo,
- struct ttm_operation_ctx *ctx, bool *locked)
+ struct ttm_operation_ctx *ctx, bool *locked, bool *busy)
{
bool ret = false;
- *locked = false;
if (bo->resv == ctx->resv) {
reservation_object_assert_held(bo->resv);
if (ctx->flags & TTM_OPT_FLAG_ALLOW_RES_EVICT
|| !list_empty(&bo->ddestroy))
ret = true;
+ *locked = false;
+ if (busy)
+ *busy = false;
} else {
- *locked = reservation_object_trylock(bo->resv);
- ret = *locked;
+ ret = reservation_object_trylock(bo->resv);
+ *locked = ret;
+ if (busy)
+ *busy = !ret;
}
return ret;
}
+/**
+ * ttm_mem_evict_wait_busy - wait for a busy BO to become available
+ *
+ * @busy_bo: BO which couldn't be locked with trylock
+ * @ctx: operation context
+ * @ticket: acquire ticket
+ *
+ * Try to lock a busy buffer object to avoid failing eviction.
+ */
+static int ttm_mem_evict_wait_busy(struct ttm_buffer_object *busy_bo,
+ struct ttm_operation_ctx *ctx,
+ struct ww_acquire_ctx *ticket)
+{
+ int r;
+
+ if (!busy_bo || !ticket)
+ return -EBUSY;
+
+ if (ctx->interruptible)
+ r = reservation_object_lock_interruptible(busy_bo->resv,
+ ticket);
+ else
+ r = reservation_object_lock(busy_bo->resv, ticket);
+
+ /*
+ * TODO: It would be better to keep the BO locked until allocation is at
+ * least tried one more time, but that would mean a much larger rework
+ * of TTM.
+ */
+ if (!r)
+ reservation_object_unlock(busy_bo->resv);
+
+ return r == -EDEADLK ? -EAGAIN : r;
+}
+
static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
uint32_t mem_type,
const struct ttm_place *place,
- struct ttm_operation_ctx *ctx)
+ struct ttm_operation_ctx *ctx,
+ struct ww_acquire_ctx *ticket)
{
+ struct ttm_buffer_object *bo = NULL, *busy_bo = NULL;
struct ttm_bo_global *glob = bdev->glob;
struct ttm_mem_type_manager *man = &bdev->man[mem_type];
- struct ttm_buffer_object *bo = NULL;
bool locked = false;
unsigned i;
int ret;
@@ -807,8 +847,15 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
spin_lock(&glob->lru_lock);
for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i) {
list_for_each_entry(bo, &man->lru[i], lru) {
- if (!ttm_bo_evict_swapout_allowable(bo, ctx, &locked))
+ bool busy;
+
+ if (!ttm_bo_evict_swapout_allowable(bo, ctx, &locked,
+ &busy)) {
+ if (busy && !busy_bo &&
+ bo->resv->lock.ctx != ticket)
+ busy_bo = bo;
continue;
+ }
if (place && !bdev->driver->eviction_valuable(bo,
place)) {
@@ -827,8 +874,13 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
}
if (!bo) {
+ if (busy_bo)
+ ttm_bo_get(busy_bo);
spin_unlock(&glob->lru_lock);
- return -EBUSY;
+ ret = ttm_mem_evict_wait_busy(busy_bo, ctx, ticket);
+ if (busy_bo)
+ ttm_bo_put(busy_bo);
+ return ret;
}
kref_get(&bo->list_kref);
@@ -914,7 +966,8 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo,
return ret;
if (mem->mm_node)
break;
- ret = ttm_mem_evict_first(bdev, mem->mem_type, place, ctx);
+ ret = ttm_mem_evict_first(bdev, mem->mem_type, place, ctx,
+ bo->resv->lock.ctx);
if (unlikely(ret != 0))
return ret;
} while (1);
@@ -1429,7 +1482,8 @@ static int ttm_bo_force_list_clean(struct ttm_bo_device *bdev,
for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i) {
while (!list_empty(&man->lru[i])) {
spin_unlock(&glob->lru_lock);
- ret = ttm_mem_evict_first(bdev, mem_type, NULL, &ctx);
+ ret = ttm_mem_evict_first(bdev, mem_type, NULL, &ctx,
+ NULL);
if (ret)
return ret;
spin_lock(&glob->lru_lock);
@@ -1800,7 +1854,8 @@ int ttm_bo_swapout(struct ttm_bo_global *glob, struct ttm_operation_ctx *ctx)
spin_lock(&glob->lru_lock);
for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i) {
list_for_each_entry(bo, &glob->swap_lru[i], swap) {
- if (ttm_bo_evict_swapout_allowable(bo, ctx, &locked)) {
+ if (ttm_bo_evict_swapout_allowable(bo, ctx, &locked,
+ NULL)) {
ret = 0;
break;
}
--
2.17.1
More information about the amd-gfx
mailing list