Merge branch 'master' into queue

* master: (15791 commits)
  Linux 3.9-rc1
  btrfs/raid56: Add missing #include <linux/vmalloc.h>
  fix compat_sys_rt_sigprocmask()
  SUNRPC: One line comment fix
  ext4: enable quotas before orphan cleanup
  ext4: don't allow quota mount options when quota feature enabled
  ext4: fix a warning from sparse check for ext4_dir_llseek
  ext4: convert number of blocks to clusters properly
  ext4: fix possible memory leak in ext4_remount()
  jbd2: fix ERR_PTR dereference in jbd2__journal_start
  metag: Provide dma_get_sgtable()
  metag: prom.h: remove declaration of metag_dt_memblock_reserve()
  metag: copy devicetree to non-init memory
  metag: cleanup metag_ksyms.c includes
  metag: move mm/init.c exports out of metag_ksyms.c
  metag: move usercopy.c exports out of metag_ksyms.c
  metag: move setup.c exports out of metag_ksyms.c
  metag: move kick.c exports out of metag_ksyms.c
  metag: move traps.c exports out of metag_ksyms.c
  metag: move irq enable out of irqflags.h on SMP
  ...

Signed-off-by: Marcelo Tosatti <[email protected]>

Conflicts:
	arch/x86/kernel/kvmclock.c

1 files changed, 22 insertions, 13 deletions

diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 2b58905d3504..8afab27cdbc2 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -27,7 +27,7 @@ void delayed_work_timer_fn(unsigned long __data);
 enum {
 	WORK_STRUCT_PENDING_BIT	= 0,	/* work item is pending execution */
 	WORK_STRUCT_DELAYED_BIT	= 1,	/* work item is delayed */
-	WORK_STRUCT_CWQ_BIT	= 2,	/* data points to cwq */
+	WORK_STRUCT_PWQ_BIT	= 2,	/* data points to pwq */
 	WORK_STRUCT_LINKED_BIT	= 3,	/* next work is linked to this one */
 #ifdef CONFIG_DEBUG_OBJECTS_WORK
 	WORK_STRUCT_STATIC_BIT	= 4,	/* static initializer (debugobjects) */
@@ -40,7 +40,7 @@ enum {
 
 	WORK_STRUCT_PENDING	= 1 << WORK_STRUCT_PENDING_BIT,
 	WORK_STRUCT_DELAYED	= 1 << WORK_STRUCT_DELAYED_BIT,
-	WORK_STRUCT_CWQ		= 1 << WORK_STRUCT_CWQ_BIT,
+	WORK_STRUCT_PWQ		= 1 << WORK_STRUCT_PWQ_BIT,
 	WORK_STRUCT_LINKED	= 1 << WORK_STRUCT_LINKED_BIT,
 #ifdef CONFIG_DEBUG_OBJECTS_WORK
 	WORK_STRUCT_STATIC	= 1 << WORK_STRUCT_STATIC_BIT,
@@ -57,29 +57,36 @@ enum {
 
 	/* special cpu IDs */
 	WORK_CPU_UNBOUND	= NR_CPUS,
-	WORK_CPU_NONE		= NR_CPUS + 1,
-	WORK_CPU_LAST		= WORK_CPU_NONE,
+	WORK_CPU_END		= NR_CPUS + 1,
 
 	/*
-	 * Reserve 7 bits off of cwq pointer w/ debugobjects turned
-	 * off.  This makes cwqs aligned to 256 bytes and allows 15
-	 * workqueue flush colors.
+	 * Reserve 7 bits off of pwq pointer w/ debugobjects turned off.
+	 * This makes pwqs aligned to 256 bytes and allows 15 workqueue
+	 * flush colors.
 	 */
 	WORK_STRUCT_FLAG_BITS	= WORK_STRUCT_COLOR_SHIFT +
 				  WORK_STRUCT_COLOR_BITS,
 
-	/* data contains off-queue information when !WORK_STRUCT_CWQ */
+	/* data contains off-queue information when !WORK_STRUCT_PWQ */
 	WORK_OFFQ_FLAG_BASE	= WORK_STRUCT_FLAG_BITS,
 
 	WORK_OFFQ_CANCELING	= (1 << WORK_OFFQ_FLAG_BASE),
 
+	/*
+	 * When a work item is off queue, its high bits point to the last
+	 * pool it was on.  Cap at 31 bits and use the highest number to
+	 * indicate that no pool is associated.
+	 */
 	WORK_OFFQ_FLAG_BITS	= 1,
-	WORK_OFFQ_CPU_SHIFT	= WORK_OFFQ_FLAG_BASE + WORK_OFFQ_FLAG_BITS,
+	WORK_OFFQ_POOL_SHIFT	= WORK_OFFQ_FLAG_BASE + WORK_OFFQ_FLAG_BITS,
+	WORK_OFFQ_LEFT		= BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT,
+	WORK_OFFQ_POOL_BITS	= WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31,
+	WORK_OFFQ_POOL_NONE	= (1LU << WORK_OFFQ_POOL_BITS) - 1,
 
 	/* convenience constants */
 	WORK_STRUCT_FLAG_MASK	= (1UL << WORK_STRUCT_FLAG_BITS) - 1,
 	WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK,
-	WORK_STRUCT_NO_CPU	= (unsigned long)WORK_CPU_NONE << WORK_OFFQ_CPU_SHIFT,
+	WORK_STRUCT_NO_POOL	= (unsigned long)WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT,
 
 	/* bit mask for work_busy() return values */
 	WORK_BUSY_PENDING	= 1 << 0,
@@ -95,13 +102,16 @@ struct work_struct {
 #endif
 };
 
-#define WORK_DATA_INIT()	ATOMIC_LONG_INIT(WORK_STRUCT_NO_CPU)
+#define WORK_DATA_INIT()	ATOMIC_LONG_INIT(WORK_STRUCT_NO_POOL)
 #define WORK_DATA_STATIC_INIT()	\
-	ATOMIC_LONG_INIT(WORK_STRUCT_NO_CPU | WORK_STRUCT_STATIC)
+	ATOMIC_LONG_INIT(WORK_STRUCT_NO_POOL | WORK_STRUCT_STATIC)
 
 struct delayed_work {
 	struct work_struct work;
 	struct timer_list timer;
+
+	/* target workqueue and CPU ->timer uses to queue ->work */
+	struct workqueue_struct *wq;
 	int cpu;
 };
 
@@ -426,7 +436,6 @@ extern bool cancel_delayed_work_sync(struct delayed_work *dwork);
 extern void workqueue_set_max_active(struct workqueue_struct *wq,
 				     int max_active);
 extern bool workqueue_congested(unsigned int cpu, struct workqueue_struct *wq);
-extern unsigned int work_cpu(struct work_struct *work);
 extern unsigned int work_busy(struct work_struct *work);
 
 /*