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>

4 files changed, 66 insertions, 80 deletions

diff --git a/lib/bust_spinlocks.c b/lib/bust_spinlocks.c
index 9681d54b95d1..f8e0e5367398 100644
--- a/lib/bust_spinlocks.c
+++ b/lib/bust_spinlocks.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/printk.h>
 #include <linux/spinlock.h>
 #include <linux/tty.h>
 #include <linux/wait.h>
@@ -28,5 +29,3 @@ void __attribute__((weak)) bust_spinlocks(int yes)
 			wake_up_klogd();
 	}
 }
-
-
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);
diff --git a/lib/idr.c b/lib/idr.c
index 73f4d53c02f3..322e2816f2fb 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -106,8 +106,14 @@ static struct idr_layer *idr_layer_alloc(gfp_t gfp_mask, struct idr *layer_idr)
 	if (layer_idr)
 		return get_from_free_list(layer_idr);
 
-	/* try to allocate directly from kmem_cache */
-	new = kmem_cache_zalloc(idr_layer_cache, gfp_mask);
+	/*
+	 * Try to allocate directly from kmem_cache.  We want to try this
+	 * before preload buffer; otherwise, non-preloading idr_alloc()
+	 * users will end up taking advantage of preloading ones.  As the
+	 * following is allowed to fail for preloaded cases, suppress
+	 * warning this time.
+	 */
+	new = kmem_cache_zalloc(idr_layer_cache, gfp_mask | __GFP_NOWARN);
 	if (new)
 		return new;
 
@@ -115,18 +121,24 @@ static struct idr_layer *idr_layer_alloc(gfp_t gfp_mask, struct idr *layer_idr)
 	 * Try to fetch one from the per-cpu preload buffer if in process
 	 * context.  See idr_preload() for details.
 	 */
-	if (in_interrupt())
-		return NULL;
-
-	preempt_disable();
-	new = __this_cpu_read(idr_preload_head);
-	if (new) {
-		__this_cpu_write(idr_preload_head, new->ary[0]);
-		__this_cpu_dec(idr_preload_cnt);
-		new->ary[0] = NULL;
+	if (!in_interrupt()) {
+		preempt_disable();
+		new = __this_cpu_read(idr_preload_head);
+		if (new) {
+			__this_cpu_write(idr_preload_head, new->ary[0]);
+			__this_cpu_dec(idr_preload_cnt);
+			new->ary[0] = NULL;
+		}
+		preempt_enable();
+		if (new)
+			return new;
 	}
-	preempt_enable();
-	return new;
+
+	/*
+	 * Both failed.  Try kmem_cache again w/o adding __GFP_NOWARN so
+	 * that memory allocation failure warning is printed as intended.
+	 */
+	return kmem_cache_zalloc(idr_layer_cache, gfp_mask);
 }
 
 static void idr_layer_rcu_free(struct rcu_head *head)
@@ -184,20 +196,7 @@ static void idr_mark_full(struct idr_layer **pa, int id)
 	}
 }
 
-/**
- * idr_pre_get - reserve resources for idr allocation
- * @idp:	idr handle
- * @gfp_mask:	memory allocation flags
- *
- * This function should be called prior to calling the idr_get_new* functions.
- * It preallocates enough memory to satisfy the worst possible allocation. The
- * caller should pass in GFP_KERNEL if possible.  This of course requires that
- * no spinning locks be held.
- *
- * If the system is REALLY out of memory this function returns %0,
- * otherwise %1.
- */
-int idr_pre_get(struct idr *idp, gfp_t gfp_mask)
+int __idr_pre_get(struct idr *idp, gfp_t gfp_mask)
 {
 	while (idp->id_free_cnt < MAX_IDR_FREE) {
 		struct idr_layer *new;
@@ -208,13 +207,12 @@ int idr_pre_get(struct idr *idp, gfp_t gfp_mask)
 	}
 	return 1;
 }
-EXPORT_SYMBOL(idr_pre_get);
+EXPORT_SYMBOL(__idr_pre_get);
 
 /**
  * sub_alloc - try to allocate an id without growing the tree depth
  * @idp: idr handle
  * @starting_id: id to start search at
- * @id: pointer to the allocated handle
  * @pa: idr_layer[MAX_IDR_LEVEL] used as backtrack buffer
  * @gfp_mask: allocation mask for idr_layer_alloc()
  * @layer_idr: optional idr passed to idr_layer_alloc()
@@ -376,25 +374,7 @@ static void idr_fill_slot(struct idr *idr, void *ptr, int id,
 	idr_mark_full(pa, id);
 }
 
-/**
- * idr_get_new_above - allocate new idr entry above or equal to a start id
- * @idp: idr handle
- * @ptr: pointer you want associated with the id
- * @starting_id: id to start search at
- * @id: pointer to the allocated handle
- *
- * This is the allocate id function.  It should be called with any
- * required locks.
- *
- * If allocation from IDR's private freelist fails, idr_get_new_above() will
- * return %-EAGAIN.  The caller should retry the idr_pre_get() call to refill
- * IDR's preallocation and then retry the idr_get_new_above() call.
- *
- * If the idr is full idr_get_new_above() will return %-ENOSPC.
- *
- * @id returns a value in the range @starting_id ... %0x7fffffff
- */
-int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id)
+int __idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id)
 {
 	struct idr_layer *pa[MAX_IDR_LEVEL + 1];
 	int rv;
@@ -407,7 +387,7 @@ int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id)
 	*id = rv;
 	return 0;
 }
-EXPORT_SYMBOL(idr_get_new_above);
+EXPORT_SYMBOL(__idr_get_new_above);
 
 /**
  * idr_preload - preload for idr_alloc()
@@ -569,8 +549,7 @@ void idr_remove(struct idr *idp, int id)
 	struct idr_layer *p;
 	struct idr_layer *to_free;
 
-	/* see comment in idr_find_slowpath() */
-	if (WARN_ON_ONCE(id < 0))
+	if (id < 0)
 		return;
 
 	sub_remove(idp, (idp->layers - 1) * IDR_BITS, id);
@@ -667,15 +646,7 @@ void *idr_find_slowpath(struct idr *idp, int id)
 	int n;
 	struct idr_layer *p;
 
-	/*
-	 * If @id is negative, idr_find() used to ignore the sign bit and
-	 * performed lookup with the rest of bits, which is weird and can
-	 * lead to very obscure bugs.  We're now returning NULL for all
-	 * negative IDs but just in case somebody was depending on the sign
-	 * bit being ignored, let's trigger WARN_ON_ONCE() so that they can
-	 * be detected and fixed.  WARN_ON_ONCE() can later be removed.
-	 */
-	if (WARN_ON_ONCE(id < 0))
+	if (id < 0)
 		return NULL;
 
 	p = rcu_dereference_raw(idp->top);
@@ -824,8 +795,7 @@ void *idr_replace(struct idr *idp, void *ptr, int id)
 	int n;
 	struct idr_layer *p, *old_p;
 
-	/* see comment in idr_find_slowpath() */
-	if (WARN_ON_ONCE(id < 0))
+	if (id < 0)
 		return ERR_PTR(-EINVAL);
 
 	p = idp->top;
@@ -918,7 +888,7 @@ static void free_bitmap(struct ida *ida, struct ida_bitmap *bitmap)
 int ida_pre_get(struct ida *ida, gfp_t gfp_mask)
 {
 	/* allocate idr_layers */
-	if (!idr_pre_get(&ida->idr, gfp_mask))
+	if (!__idr_pre_get(&ida->idr, gfp_mask))
 		return 0;
 
 	/* allocate free_bitmap */
diff --git a/lib/xz/Kconfig b/lib/xz/Kconfig
index 82a04d7ba99e..08837db52d94 100644
--- a/lib/xz/Kconfig
+++ b/lib/xz/Kconfig
@@ -15,7 +15,7 @@ config XZ_DEC_X86
 
 config XZ_DEC_POWERPC
 	bool "PowerPC BCJ filter decoder"
-	default y if POWERPC
+	default y if PPC
 	select XZ_DEC_BCJ
 
 config XZ_DEC_IA64