Merge tag 'v3.9-rc3' into v4l_for_linus

Linux 3.9-rc3

* tag 'v3.9-rc3': (11231 commits)
  Linux 3.9-rc3
  perf,x86: fix link failure for non-Intel configs
  perf,x86: fix wrmsr_on_cpu() warning on suspend/resume
  Btrfs: fix warning of free_extent_map
  perf,x86: fix kernel crash with PEBS/BTS after suspend/resume
  ALSA: hda - Fix missing EAPD/GPIO setup for Cirrus codecs
  sound: sequencer: cap array index in seq_chn_common_event()
  mfd: twl4030-madc: Remove __exit_p annotation
  ALSA: hda/ca0132 - Remove extra setting of dsp_state.
  ALSA: hda/ca0132 - Check download state of DSP.
  ALSA: hda/ca0132 - Check if dspload_image succeeded.
  mm/fremap.c: fix possible oops on error path
  list: Fix double fetch of pointer in hlist_entry_safe()
  Btrfs: fix warning when creating snapshots
  Btrfs: return as soon as possible when edquot happens
  Btrfs: return EIO if we have extent tree corruption
  btrfs: use rcu_barrier() to wait for bdev puts at unmount
  Btrfs: remove btrfs_try_spin_lock
  Btrfs: get better concurrency for snapshot-aware defrag work
  hwmon: (pmbus/ltc2978) Fix temperature reporting
  ...

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);
 
 /*