Merge tag 'v3.9-rc5' into wq/for-3.10

Writeback conversion to workqueue will be based on top of wq/for-3.10
branch to take advantage of custom attrs and NUMA support for unbound
workqueues.  Mainline currently contains two commits which result in
non-trivial merge conflicts with wq/for-3.10 and because
block/for-3.10/core is based on v3.9-rc3 which contains one of the
conflicting commits, we need a pre-merge-window merge anyway.  Let's
pull v3.9-rc5 into wq/for-3.10 so that the block tree doesn't suffer
from workqueue merge conflicts.

The two conflicts and their resolutions:

* e68035fb65 ("workqueue: convert to idr_alloc()") in mainline changes
  worker_pool_assign_id() to use idr_alloc() instead of the old idr
  interface.  worker_pool_assign_id() goes through multiple locking
  changes in wq/for-3.10 causing the following conflict.

  static int worker_pool_assign_id(struct worker_pool *pool)
  {
	  int ret;

  <<<<<<< HEAD
	  lockdep_assert_held(&wq_pool_mutex);

	  do {
		  if (!idr_pre_get(&worker_pool_idr, GFP_KERNEL))
			  return -ENOMEM;
		  ret = idr_get_new(&worker_pool_idr, pool, &pool->id);
	  } while (ret == -EAGAIN);
  =======
	  mutex_lock(&worker_pool_idr_mutex);
	  ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
	  if (ret >= 0)
		  pool->id = ret;
	  mutex_unlock(&worker_pool_idr_mutex);
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89

	  return ret < 0 ? ret : 0;
  }

  We want locking from the former and idr_alloc() usage from the
  latter, which can be combined to the following.

  static int worker_pool_assign_id(struct worker_pool *pool)
  {
	  int ret;

	  lockdep_assert_held(&wq_pool_mutex);

	  ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
	  if (ret >= 0) {
		  pool->id = ret;
		  return 0;
	  }
	  return ret;
   }

* eb2834285c ("workqueue: fix possible pool stall bug in
  wq_unbind_fn()") updated wq_unbind_fn() such that it has single
  larger for_each_std_worker_pool() loop instead of two separate loops
  with a schedule() call inbetween.  wq/for-3.10 renamed
  pool->assoc_mutex to pool->manager_mutex causing the following
  conflict (earlier function body and comments omitted for brevity).

  static void wq_unbind_fn(struct work_struct *work)
  {
  ...
		  spin_unlock_irq(&pool->lock);
  <<<<<<< HEAD
		  mutex_unlock(&pool->manager_mutex);
	  }
  =======
		  mutex_unlock(&pool->assoc_mutex);
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89

		  schedule();

  <<<<<<< HEAD
	  for_each_cpu_worker_pool(pool, cpu)
  =======
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89
		  atomic_set(&pool->nr_running, 0);

		  spin_lock_irq(&pool->lock);
		  wake_up_worker(pool);
		  spin_unlock_irq(&pool->lock);
	  }
  }

  The resolution is mostly trivial.  We want the control flow of the
  latter with the rename of the former.

  static void wq_unbind_fn(struct work_struct *work)
  {
  ...
		  spin_unlock_irq(&pool->lock);
		  mutex_unlock(&pool->manager_mutex);

		  schedule();

		  atomic_set(&pool->nr_running, 0);

		  spin_lock_irq(&pool->lock);
		  wake_up_worker(pool);
		  spin_unlock_irq(&pool->lock);
	  }
  }

Signed-off-by: Tejun Heo <tj@kernel.org>

1 files changed, 31 insertions, 14 deletions

diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index 5e396accd3d0..d87a17a819d0 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -862,17 +862,21 @@ static void check_unmap(struct dma_debug_entry *ref)
 	entry = bucket_find_exact(bucket, ref);
 
 	if (!entry) {
+		/* must drop lock before calling dma_mapping_error */
+		put_hash_bucket(bucket, &flags);
+
 		if (dma_mapping_error(ref->dev, ref->dev_addr)) {
 			err_printk(ref->dev, NULL,
-				   "DMA-API: device driver tries "
-				   "to free an invalid DMA memory address\n");
-			return;
+				   "DMA-API: device driver tries to free an "
+				   "invalid DMA memory address\n");
+		} else {
+			err_printk(ref->dev, NULL,
+				   "DMA-API: device driver tries to free DMA "
+				   "memory it has not allocated [device "
+				   "address=0x%016llx] [size=%llu bytes]\n",
+				   ref->dev_addr, ref->size);
 		}
-		err_printk(ref->dev, NULL, "DMA-API: device driver tries "
-			   "to free DMA memory it has not allocated "
-			   "[device address=0x%016llx] [size=%llu bytes]\n",
-			   ref->dev_addr, ref->size);
-		goto out;
+		return;
 	}
 
 	if (ref->size != entry->size) {
@@ -936,7 +940,6 @@ static void check_unmap(struct dma_debug_entry *ref)
 	hash_bucket_del(entry);
 	dma_entry_free(entry);
 
-out:
 	put_hash_bucket(bucket, &flags);
 }
 
@@ -1082,13 +1085,27 @@ void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 	ref.dev = dev;
 	ref.dev_addr = dma_addr;
 	bucket = get_hash_bucket(&ref, &flags);
-	entry = bucket_find_exact(bucket, &ref);
 
-	if (!entry)
-		goto out;
+	list_for_each_entry(entry, &bucket->list, list) {
+		if (!exact_match(&ref, entry))
+			continue;
+
+		/*
+		 * The same physical address can be mapped multiple
+		 * times. Without a hardware IOMMU this results in the
+		 * same device addresses being put into the dma-debug
+		 * hash multiple times too. This can result in false
+		 * positives being reported. Therefore we implement a
+		 * best-fit algorithm here which updates the first entry
+		 * from the hash which fits the reference value and is
+		 * not currently listed as being checked.
+		 */
+		if (entry->map_err_type == MAP_ERR_NOT_CHECKED) {
+			entry->map_err_type = MAP_ERR_CHECKED;
+			break;
+		}
+	}
 
-	entry->map_err_type = MAP_ERR_CHECKED;
-out:
 	put_hash_bucket(bucket, &flags);
 }
 EXPORT_SYMBOL(debug_dma_mapping_error);