Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block into for-3.18

This is to receive 0a30288da1 ("blk-mq, percpu_ref: implement a
kludge for SCSI blk-mq stall during probe") which implements
__percpu_ref_kill_expedited() to work around SCSI blk-mq stall.  The
commit reverted and patches to implement proper fix will be added.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@lst.de>

lib/Kconfig

@@ -51,6 +51,9 @@ config PERCPU_RWSEM
 config ARCH_USE_CMPXCHG_LOCKREF
 	bool
 
+config ARCH_HAS_FAST_MULTIPLIER
+	bool
+
 config CRC_CCITT
 	tristate "CRC-CCITT functions"
 	help

lib/Kconfig.debug

@@ -892,6 +892,10 @@ config DEBUG_WW_MUTEX_SLOWPATH
 	 the full mutex checks enabled with (CONFIG_PROVE_LOCKING) this
 	 will test all possible w/w mutex interface abuse with the
 	 exception of simply not acquiring all the required locks.
+	 Note that this feature can introduce significant overhead, so
+	 it really should not be enabled in a production or distro kernel,
+	 even a debug kernel.  If you are a driver writer, enable it.  If
+	 you are a distro, do not.
 
 config DEBUG_LOCK_ALLOC
 	bool "Lock debugging: detect incorrect freeing of live locks"
@@ -1032,8 +1036,13 @@ config TRACE_IRQFLAGS
 	  either tracing or lock debugging.
 
 config STACKTRACE
-	bool
+	bool "Stack backtrace support"
 	depends on STACKTRACE_SUPPORT
+	help
+	  This option causes the kernel to create a /proc/pid/stack for
+	  every process, showing its current stack trace.
+	  It is also used by various kernel debugging features that require
+	  stack trace generation.
 
 config DEBUG_KOBJECT
 	bool "kobject debugging"

lib/assoc_array.c

@@ -1723,11 +1723,13 @@ ascend_old_tree:
 		shortcut = assoc_array_ptr_to_shortcut(ptr);
 		slot = shortcut->parent_slot;
 		cursor = shortcut->back_pointer;
+		if (!cursor)
+			goto gc_complete;
 	} else {
 		slot = node->parent_slot;
 		cursor = ptr;
 	}
-	BUG_ON(!ptr);
+	BUG_ON(!cursor);
 	node = assoc_array_ptr_to_node(cursor);
 	slot++;
 	goto continue_node;
@@ -1735,7 +1737,7 @@ ascend_old_tree:
 gc_complete:
 	edit->set[0].to = new_root;
 	assoc_array_apply_edit(edit);
-	edit->array->nr_leaves_on_tree = nr_leaves_on_tree;
+	array->nr_leaves_on_tree = nr_leaves_on_tree;
 	return 0;
 
 enomem:

lib/hweight.c

@@ -11,7 +11,7 @@
 
 unsigned int __sw_hweight32(unsigned int w)
 {
-#ifdef ARCH_HAS_FAST_MULTIPLIER
+#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
 	w -= (w >> 1) & 0x55555555;
 	w =  (w & 0x33333333) + ((w >> 2) & 0x33333333);
 	w =  (w + (w >> 4)) & 0x0f0f0f0f;
@@ -49,7 +49,7 @@ unsigned long __sw_hweight64(__u64 w)
 	return __sw_hweight32((unsigned int)(w >> 32)) +
 	       __sw_hweight32((unsigned int)w);
 #elif BITS_PER_LONG == 64
-#ifdef ARCH_HAS_FAST_MULTIPLIER
+#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
 	w -= (w >> 1) & 0x5555555555555555ul;
 	w =  (w & 0x3333333333333333ul) + ((w >> 2) & 0x3333333333333333ul);
 	w =  (w + (w >> 4)) & 0x0f0f0f0f0f0f0f0ful;

lib/percpu-refcount.c

@@ -189,3 +189,19 @@ void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 	call_rcu_sched(&ref->rcu, percpu_ref_kill_rcu);
 }
 EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm);
+
+/*
+ * XXX: Temporary kludge to work around SCSI blk-mq stall.  Used only by
+ * block/blk-mq.c::blk_mq_freeze_queue().  Will be removed during v3.18
+ * devel cycle.  Do not use anywhere else.
+ */
+void __percpu_ref_kill_expedited(struct percpu_ref *ref)
+{
+	WARN_ONCE(ref->pcpu_count_ptr & PCPU_REF_DEAD,
+		  "percpu_ref_kill() called more than once on %pf!",
+		  ref->release);
+
+	ref->pcpu_count_ptr |= PCPU_REF_DEAD;
+	synchronize_sched_expedited();
+	percpu_ref_kill_rcu(&ref->rcu);
+}

lib/rhashtable.c

@@ -23,7 +23,6 @@
 #include <linux/hash.h>
 #include <linux/random.h>
 #include <linux/rhashtable.h>
-#include <linux/log2.h>
 
 #define HASH_DEFAULT_SIZE	64UL
 #define HASH_MIN_SIZE		4UL

lib/string.c

@@ -807,9 +807,9 @@ void *memchr_inv(const void *start, int c, size_t bytes)
 		return check_bytes8(start, value, bytes);
 
 	value64 = value;
-#if defined(ARCH_HAS_FAST_MULTIPLIER) && BITS_PER_LONG == 64
+#if defined(CONFIG_ARCH_HAS_FAST_MULTIPLIER) && BITS_PER_LONG == 64
 	value64 *= 0x0101010101010101;
-#elif defined(ARCH_HAS_FAST_MULTIPLIER)
+#elif defined(CONFIG_ARCH_HAS_FAST_MULTIPLIER)
 	value64 *= 0x01010101;
 	value64 |= value64 << 32;
 #else