30 files changed, 687 insertions, 141 deletions

diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index e531783e5d78..95ac82340c3b 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -313,6 +313,7 @@ unifdef-y += ptrace.h
 unifdef-y += qnx4_fs.h
 unifdef-y += quota.h
 unifdef-y += random.h
+unifdef-y += irqnr.h
 unifdef-y += reboot.h
 unifdef-y += reiserfs_fs.h
 unifdef-y += reiserfs_xattr.h
diff --git a/include/linux/aio.h b/include/linux/aio.h
index f6b8cf99b596..b16a957030f8 100644
--- a/include/linux/aio.h
+++ b/include/linux/aio.h
@@ -5,6 +5,7 @@
 #include <linux/workqueue.h>
 #include <linux/aio_abi.h>
 #include <linux/uio.h>
+#include <linux/rcupdate.h>
 
 #include <asm/atomic.h>
 
@@ -183,7 +184,7 @@ struct kioctx {
 
         /* This needs improving */
         unsigned long           user_id;
-        struct kioctx           *next;
+        struct hlist_node       list;
 
         wait_queue_head_t       wait;
 
@@ -199,6 +200,8 @@ struct kioctx {
         struct aio_ring_info    ring_info;
 
         struct delayed_work     wq;
+
+        struct rcu_head         rcu_head;
 };
 
 /* prototypes */
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 6a642098e5c3..18462c5b8fff 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -90,10 +90,11 @@ struct bio {
 
         unsigned int            bi_comp_cpu;    /* completion CPU */
 
+        atomic_t                bi_cnt;         /* pin count */
+
         struct bio_vec          *bi_io_vec;     /* the actual vec list */
 
         bio_end_io_t            *bi_end_io;
-        atomic_t                bi_cnt;         /* pin count */
 
         void                    *bi_private;
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
@@ -101,6 +102,13 @@ struct bio {
 #endif
 
         bio_destructor_t        *bi_destructor; /* destructor */
+
+        /*
+         * We can inline a number of vecs at the end of the bio, to avoid
+         * double allocations for a small number of bio_vecs. This member
+         * MUST obviously be kept at the very end of the bio.
+         */
+        struct bio_vec          bi_inline_vecs[0];
 };
 
 /*
@@ -117,6 +125,7 @@ struct bio {
 #define BIO_CPU_AFFINE  8       /* complete bio on same CPU as submitted */
 #define BIO_NULL_MAPPED 9       /* contains invalid user pages */
 #define BIO_FS_INTEGRITY 10     /* fs owns integrity data, not block layer */
+#define BIO_QUIET       11      /* Make BIO Quiet */
 #define bio_flagged(bio, flag)  ((bio)->bi_flags & (1 << (flag)))
 
 /*
@@ -211,6 +220,11 @@ static inline void *bio_data(struct bio *bio)
         return NULL;
 }
 
+static inline int bio_has_allocated_vec(struct bio *bio)
+{
+        return bio->bi_io_vec && bio->bi_io_vec != bio->bi_inline_vecs;
+}
+
 /*
  * will die
  */
@@ -332,7 +346,7 @@ struct bio_pair {
 extern struct bio_pair *bio_split(struct bio *bi, int first_sectors);
 extern void bio_pair_release(struct bio_pair *dbio);
 
-extern struct bio_set *bioset_create(int, int);
+extern struct bio_set *bioset_create(unsigned int, unsigned int);
 extern void bioset_free(struct bio_set *);
 
 extern struct bio *bio_alloc(gfp_t, int);
@@ -377,6 +391,7 @@ extern struct bio *bio_copy_user_iov(struct request_queue *,
 extern int bio_uncopy_user(struct bio *);
 void zero_fill_bio(struct bio *bio);
 extern struct bio_vec *bvec_alloc_bs(gfp_t, int, unsigned long *, struct bio_set *);
+extern void bvec_free_bs(struct bio_set *, struct bio_vec *, unsigned int);
 extern unsigned int bvec_nr_vecs(unsigned short idx);
 
 /*
@@ -395,13 +410,17 @@ static inline void bio_set_completion_cpu(struct bio *bio, unsigned int cpu)
  */
 #define BIO_POOL_SIZE 2
 #define BIOVEC_NR_POOLS 6
+#define BIOVEC_MAX_IDX  (BIOVEC_NR_POOLS - 1)
 
 struct bio_set {
+        struct kmem_cache *bio_slab;
+        unsigned int front_pad;
+
         mempool_t *bio_pool;
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
         mempool_t *bio_integrity_pool;
 #endif
-        mempool_t *bvec_pools[BIOVEC_NR_POOLS];
+        mempool_t *bvec_pool;
 };
 
 struct biovec_slab {
@@ -411,6 +430,7 @@ struct biovec_slab {
 };
 
 extern struct bio_set *fs_bio_set;
+extern struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] __read_mostly;
 
 /*
  * a small number of entries is fine, not going to be performance critical.
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 031a315c0509..7035cec583b6 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -26,7 +26,6 @@ struct scsi_ioctl_command;
 
 struct request_queue;
 struct elevator_queue;
-typedef struct elevator_queue elevator_t;
 struct request_pm_state;
 struct blk_trace;
 struct request;
@@ -313,7 +312,7 @@ struct request_queue
          */
         struct list_head        queue_head;
         struct request          *last_merge;
-        elevator_t              *elevator;
+        struct elevator_queue   *elevator;
 
         /*
          * the queue request freelist, one for reads and one for writes
@@ -449,6 +448,7 @@ struct request_queue
 #define QUEUE_FLAG_FAIL_IO     12       /* fake timeout */
 #define QUEUE_FLAG_STACKABLE   13       /* supports request stacking */
 #define QUEUE_FLAG_NONROT      14       /* non-rotational device (SSD) */
+#define QUEUE_FLAG_VIRT        QUEUE_FLAG_NONROT /* paravirt device */
 
 static inline int queue_is_locked(struct request_queue *q)
 {
@@ -522,22 +522,32 @@ enum {
          * TAG_FLUSH    : ordering by tag w/ pre and post flushes
          * TAG_FUA      : ordering by tag w/ pre flush and FUA write
          */
-        QUEUE_ORDERED_NONE      = 0x00,
-        QUEUE_ORDERED_DRAIN     = 0x01,
-        QUEUE_ORDERED_TAG       = 0x02,
-
-        QUEUE_ORDERED_PREFLUSH  = 0x10,
-        QUEUE_ORDERED_POSTFLUSH = 0x20,
-        QUEUE_ORDERED_FUA       = 0x40,
-
-        QUEUE_ORDERED_DRAIN_FLUSH = QUEUE_ORDERED_DRAIN |
-                        QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_POSTFLUSH,
-        QUEUE_ORDERED_DRAIN_FUA = QUEUE_ORDERED_DRAIN |
-                        QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_FUA,
-        QUEUE_ORDERED_TAG_FLUSH = QUEUE_ORDERED_TAG |
-                        QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_POSTFLUSH,
-        QUEUE_ORDERED_TAG_FUA   = QUEUE_ORDERED_TAG |
-                        QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_FUA,
+        QUEUE_ORDERED_BY_DRAIN          = 0x01,
+        QUEUE_ORDERED_BY_TAG            = 0x02,
+        QUEUE_ORDERED_DO_PREFLUSH       = 0x10,
+        QUEUE_ORDERED_DO_BAR            = 0x20,
+        QUEUE_ORDERED_DO_POSTFLUSH      = 0x40,
+        QUEUE_ORDERED_DO_FUA            = 0x80,
+
+        QUEUE_ORDERED_NONE              = 0x00,
+
+        QUEUE_ORDERED_DRAIN             = QUEUE_ORDERED_BY_DRAIN |
+                                          QUEUE_ORDERED_DO_BAR,
+        QUEUE_ORDERED_DRAIN_FLUSH       = QUEUE_ORDERED_DRAIN |
+                                          QUEUE_ORDERED_DO_PREFLUSH |
+                                          QUEUE_ORDERED_DO_POSTFLUSH,
+        QUEUE_ORDERED_DRAIN_FUA         = QUEUE_ORDERED_DRAIN |
+                                          QUEUE_ORDERED_DO_PREFLUSH |
+                                          QUEUE_ORDERED_DO_FUA,
+
+        QUEUE_ORDERED_TAG               = QUEUE_ORDERED_BY_TAG |
+                                          QUEUE_ORDERED_DO_BAR,
+        QUEUE_ORDERED_TAG_FLUSH         = QUEUE_ORDERED_TAG |
+                                          QUEUE_ORDERED_DO_PREFLUSH |
+                                          QUEUE_ORDERED_DO_POSTFLUSH,
+        QUEUE_ORDERED_TAG_FUA           = QUEUE_ORDERED_TAG |
+                                          QUEUE_ORDERED_DO_PREFLUSH |
+                                          QUEUE_ORDERED_DO_FUA,
 
         /*
          * Ordered operation sequence
@@ -585,7 +595,6 @@ enum {
 #define blk_fua_rq(rq)          ((rq)->cmd_flags & REQ_FUA)
 #define blk_discard_rq(rq)      ((rq)->cmd_flags & REQ_DISCARD)
 #define blk_bidi_rq(rq)         ((rq)->next_rq != NULL)
-#define blk_empty_barrier(rq)   (blk_barrier_rq(rq) && blk_fs_request(rq) && !(rq)->hard_nr_sectors)
 /* rq->queuelist of dequeued request must be list_empty() */
 #define blk_queued_rq(rq)       (!list_empty(&(rq)->queuelist))
 
@@ -855,10 +864,10 @@ extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *);
 extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
 extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
 extern int blk_queue_ordered(struct request_queue *, unsigned, prepare_flush_fn *);
-extern int blk_do_ordered(struct request_queue *, struct request **);
+extern bool blk_do_ordered(struct request_queue *, struct request **);
 extern unsigned blk_ordered_cur_seq(struct request_queue *);
 extern unsigned blk_ordered_req_seq(struct request *);
-extern void blk_ordered_complete_seq(struct request_queue *, unsigned, int);
+extern bool blk_ordered_complete_seq(struct request_queue *, unsigned, int);
 
 extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
 extern void blk_dump_rq_flags(struct request *, char *);
@@ -977,7 +986,6 @@ static inline void put_dev_sector(Sector p)
 
 struct work_struct;
 int kblockd_schedule_work(struct request_queue *q, struct work_struct *work);
-void kblockd_flush_work(struct work_struct *work);
 
 #define MODULE_ALIAS_BLOCKDEV(major,minor) \
         MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor))
diff --git a/include/linux/bottom_half.h b/include/linux/bottom_half.h
index 777dbf695d44..27b1bcffe408 100644
--- a/include/linux/bottom_half.h
+++ b/include/linux/bottom_half.h
@@ -2,7 +2,6 @@
 #define _LINUX_BH_H
 
 extern void local_bh_disable(void);
-extern void __local_bh_enable(void);
 extern void _local_bh_enable(void);
 extern void local_bh_enable(void);
 extern void local_bh_enable_ip(unsigned long ip);
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 3ce64b90118c..8605f8a74df9 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -35,6 +35,7 @@ enum bh_state_bits {
         BH_Ordered,     /* ordered write */
         BH_Eopnotsupp,  /* operation not supported (barrier) */
         BH_Unwritten,   /* Buffer is allocated on disk but not written */
+        BH_Quiet,       /* Buffer Error Prinks to be quiet */
 
         BH_PrivateStart,/* not a state bit, but the first bit available
                          * for private allocation by other entities
diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h
index 4aaa4afb1cb9..096476f1fb35 100644
--- a/include/linux/debug_locks.h
+++ b/include/linux/debug_locks.h
@@ -17,7 +17,7 @@ extern int debug_locks_off(void);
 ({                                                                      \
         int __ret = 0;                                                  \
                                                                         \
-        if (unlikely(c)) {                                              \
+        if (!oops_in_progress && unlikely(c)) {                         \
                 if (debug_locks_off() && !debug_locks_silent)           \
                         WARN_ON(1);                                     \
                 __ret = 1;                                              \
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 92f6f634e3e6..7a204256b155 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -28,7 +28,7 @@ typedef void (elevator_activate_req_fn) (struct request_queue *, struct request
 typedef void (elevator_deactivate_req_fn) (struct request_queue *, struct request *);
 
 typedef void *(elevator_init_fn) (struct request_queue *);
-typedef void (elevator_exit_fn) (elevator_t *);
+typedef void (elevator_exit_fn) (struct elevator_queue *);
 
 struct elevator_ops
 {
@@ -62,8 +62,8 @@ struct elevator_ops
 
 struct elv_fs_entry {
         struct attribute attr;
-        ssize_t (*show)(elevator_t *, char *);
-        ssize_t (*store)(elevator_t *, const char *, size_t);
+        ssize_t (*show)(struct elevator_queue *, char *);
+        ssize_t (*store)(struct elevator_queue *, const char *, size_t);
 };
 
 /*
@@ -130,7 +130,7 @@ extern ssize_t elv_iosched_show(struct request_queue *, char *);
 extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t);
 
 extern int elevator_init(struct request_queue *, char *);
-extern void elevator_exit(elevator_t *);
+extern void elevator_exit(struct elevator_queue *);
 extern int elv_rq_merge_ok(struct request *, struct bio *);
 
 /*
diff --git a/include/linux/futex.h b/include/linux/futex.h
index 586ab56a3ec3..3bf5bb5a34f9 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -25,7 +25,8 @@ union ktime;
 #define FUTEX_WAKE_BITSET       10
 
 #define FUTEX_PRIVATE_FLAG      128
-#define FUTEX_CMD_MASK          ~FUTEX_PRIVATE_FLAG
+#define FUTEX_CLOCK_REALTIME    256
+#define FUTEX_CMD_MASK          ~(FUTEX_PRIVATE_FLAG | FUTEX_CLOCK_REALTIME)
 
 #define FUTEX_WAIT_PRIVATE      (FUTEX_WAIT | FUTEX_PRIVATE_FLAG)
 #define FUTEX_WAKE_PRIVATE      (FUTEX_WAKE | FUTEX_PRIVATE_FLAG)
@@ -164,6 +165,8 @@ union futex_key {
         } both;
 };
 
+#define FUTEX_KEY_INIT (union futex_key) { .both = { .ptr = NULL } }
+
 #ifdef CONFIG_FUTEX
 extern void exit_robust_list(struct task_struct *curr);
 extern void exit_pi_state_list(struct task_struct *curr);
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 3df7742ce246..16948eaecae3 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -126,6 +126,7 @@ struct blk_scsi_cmd_filter {
 struct disk_part_tbl {
         struct rcu_head rcu_head;
         int len;
+        struct hd_struct *last_lookup;
         struct hd_struct *part[];
 };
 
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 89a56d79e4c6..f83288347dda 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -119,13 +119,17 @@ static inline void account_system_vtime(struct task_struct *tsk)
 }
 #endif
 
-#if defined(CONFIG_PREEMPT_RCU) && defined(CONFIG_NO_HZ)
+#if defined(CONFIG_NO_HZ) && !defined(CONFIG_CLASSIC_RCU)
 extern void rcu_irq_enter(void);
 extern void rcu_irq_exit(void);
+extern void rcu_nmi_enter(void);
+extern void rcu_nmi_exit(void);
 #else
 # define rcu_irq_enter() do { } while (0)
 # define rcu_irq_exit() do { } while (0)
-#endif /* CONFIG_PREEMPT_RCU */
+# define rcu_nmi_enter() do { } while (0)
+# define rcu_nmi_exit() do { } while (0)
+#endif /* #if defined(CONFIG_NO_HZ) && !defined(CONFIG_CLASSIC_RCU) */
 
 /*
  * It is safe to do non-atomic ops on ->hardirq_context,
@@ -135,7 +139,6 @@ extern void rcu_irq_exit(void);
  */
 #define __irq_enter()                                   \
         do {                                            \
-                rcu_irq_enter();                        \
                 account_system_vtime(current);          \
                 add_preempt_count(HARDIRQ_OFFSET);      \
                 trace_hardirq_enter();                  \
@@ -154,7 +157,6 @@ extern void irq_enter(void);
                 trace_hardirq_exit();                   \
                 account_system_vtime(current);          \
                 sub_preempt_count(HARDIRQ_OFFSET);      \
-                rcu_irq_exit();                         \
         } while (0)
 
 /*
@@ -166,11 +168,14 @@ extern void irq_exit(void);
         do {                                    \
                 ftrace_nmi_enter();             \
                 lockdep_off();                  \
+                rcu_nmi_enter();                \
                 __irq_enter();                  \
         } while (0)
+
 #define nmi_exit()                              \
         do {                                    \
                 __irq_exit();                   \
+                rcu_nmi_exit();                 \
                 lockdep_on();                   \
                 ftrace_nmi_exit();              \
         } while (0)
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 3eba43878dcb..bd37078c2d7d 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -43,26 +43,6 @@ enum hrtimer_restart {
 };
 
 /*
- * hrtimer callback modes:
- *
- *      HRTIMER_CB_SOFTIRQ:             Callback must run in softirq context
- *      HRTIMER_CB_IRQSAFE_PERCPU:      Callback must run in hardirq context
- *                                      Special mode for tick emulation and
- *                                      scheduler timer. Such timers are per
- *                                      cpu and not allowed to be migrated on
- *                                      cpu unplug.
- *      HRTIMER_CB_IRQSAFE_UNLOCKED:    Callback should run in hardirq context
- *                                      with timer->base lock unlocked
- *                                      used for timers which call wakeup to
- *                                      avoid lock order problems with rq->lock
- */
-enum hrtimer_cb_mode {
-        HRTIMER_CB_SOFTIRQ,
-        HRTIMER_CB_IRQSAFE_PERCPU,
-        HRTIMER_CB_IRQSAFE_UNLOCKED,
-};
-
-/*
  * Values to track state of the timer
  *
  * Possible states:
@@ -70,7 +50,6 @@ enum hrtimer_cb_mode {
  * 0x00         inactive
  * 0x01         enqueued into rbtree
  * 0x02         callback function running
- * 0x04         callback pending (high resolution mode)
  *
  * Special cases:
  * 0x03         callback function running and enqueued
@@ -92,8 +71,7 @@ enum hrtimer_cb_mode {
 #define HRTIMER_STATE_INACTIVE  0x00
 #define HRTIMER_STATE_ENQUEUED  0x01
 #define HRTIMER_STATE_CALLBACK  0x02
-#define HRTIMER_STATE_PENDING   0x04
-#define HRTIMER_STATE_MIGRATE   0x08
+#define HRTIMER_STATE_MIGRATE   0x04
 
 /**
  * struct hrtimer - the basic hrtimer structure
@@ -109,8 +87,6 @@ enum hrtimer_cb_mode {
  * @function:   timer expiry callback function
  * @base:       pointer to the timer base (per cpu and per clock)
  * @state:      state information (See bit values above)
- * @cb_mode:    high resolution timer feature to select the callback execution
- *               mode
  * @cb_entry:   list head to enqueue an expired timer into the callback list
  * @start_site: timer statistics field to store the site where the timer
  *              was started
@@ -129,7 +105,6 @@ struct hrtimer {
         struct hrtimer_clock_base       *base;
         unsigned long                   state;
         struct list_head                cb_entry;
-        enum hrtimer_cb_mode            cb_mode;
 #ifdef CONFIG_TIMER_STATS
         int                             start_pid;
         void                            *start_site;
@@ -188,15 +163,11 @@ struct hrtimer_clock_base {
  * @check_clocks:       Indictator, when set evaluate time source and clock
  *                      event devices whether high resolution mode can be
  *                      activated.
- * @cb_pending:         Expired timers are moved from the rbtree to this
- *                      list in the timer interrupt. The list is processed
- *                      in the softirq.
  * @nr_events:          Total number of timer interrupt events
  */
 struct hrtimer_cpu_base {
         spinlock_t                      lock;
         struct hrtimer_clock_base       clock_base[HRTIMER_MAX_CLOCK_BASES];
-        struct list_head                cb_pending;
 #ifdef CONFIG_HIGH_RES_TIMERS
         ktime_t                         expires_next;
         int                             hres_active;
@@ -404,8 +375,7 @@ static inline int hrtimer_active(const struct hrtimer *timer)
  */
 static inline int hrtimer_is_queued(struct hrtimer *timer)
 {
-        return timer->state &
-                (HRTIMER_STATE_ENQUEUED | HRTIMER_STATE_PENDING);
+        return timer->state & HRTIMER_STATE_ENQUEUED;
 }
 
 /*
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index f58a0cf8929a..be3c484b5242 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -14,6 +14,8 @@
 #include <linux/irqflags.h>
 #include <linux/smp.h>
 #include <linux/percpu.h>
+#include <linux/irqnr.h>
+
 #include <asm/atomic.h>
 #include <asm/ptrace.h>
 #include <asm/system.h>
@@ -251,9 +253,6 @@ enum
         BLOCK_SOFTIRQ,
         TASKLET_SOFTIRQ,
         SCHED_SOFTIRQ,
-#ifdef CONFIG_HIGH_RES_TIMERS
-        HRTIMER_SOFTIRQ,
-#endif
         RCU_SOFTIRQ,    /* Preferable RCU should always be the last softirq */
 
         NR_SOFTIRQS
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 3dddfa703ebd..98564dc64476 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -129,9 +129,14 @@ struct irq_chip {
         const char      *typename;
 };
 
+struct timer_rand_state;
+struct irq_2_iommu;
 /**
  * struct irq_desc - interrupt descriptor
  * @irq:                interrupt number for this descriptor
+ * @timer_rand_state:   pointer to timer rand state struct
+ * @kstat_irqs:         irq stats per cpu
+ * @irq_2_iommu:        iommu with this irq
  * @handle_irq:         highlevel irq-events handler [if NULL, __do_IRQ()]
  * @chip:               low level interrupt hardware access
  * @msi_desc:           MSI descriptor
@@ -143,8 +148,8 @@ struct irq_chip {
  * @depth:              disable-depth, for nested irq_disable() calls
  * @wake_depth:         enable depth, for multiple set_irq_wake() callers
  * @irq_count:          stats field to detect stalled irqs
- * @irqs_unhandled:     stats field for spurious unhandled interrupts
  * @last_unhandled:     aging timer for unhandled count
+ * @irqs_unhandled:     stats field for spurious unhandled interrupts
  * @lock:               locking for SMP
  * @affinity:           IRQ affinity on SMP
  * @cpu:                cpu index useful for balancing
@@ -154,6 +159,13 @@ struct irq_chip {
  */
 struct irq_desc {
         unsigned int            irq;
+#ifdef CONFIG_SPARSE_IRQ
+        struct timer_rand_state *timer_rand_state;
+        unsigned int            *kstat_irqs;
+# ifdef CONFIG_INTR_REMAP
+        struct irq_2_iommu      *irq_2_iommu;
+# endif
+#endif
         irq_flow_handler_t      handle_irq;
         struct irq_chip         *chip;
         struct msi_desc         *msi_desc;
@@ -165,8 +177,8 @@ struct irq_desc {
         unsigned int            depth;          /* nested irq disables */
         unsigned int            wake_depth;     /* nested wake enables */
         unsigned int            irq_count;      /* For detecting broken IRQs */
-        unsigned int            irqs_unhandled;
         unsigned long           last_unhandled; /* Aging timer for unhandled count */
+        unsigned int            irqs_unhandled;
         spinlock_t              lock;
 #ifdef CONFIG_SMP
         cpumask_t               affinity;
@@ -181,12 +193,51 @@ struct irq_desc {
         const char              *name;
 } ____cacheline_internodealigned_in_smp;
 
+extern void early_irq_init(void);
+extern void arch_early_irq_init(void);
+extern void arch_init_chip_data(struct irq_desc *desc, int cpu);
+extern void arch_init_copy_chip_data(struct irq_desc *old_desc,
+                                        struct irq_desc *desc, int cpu);
+extern void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc);
 
+#ifndef CONFIG_SPARSE_IRQ
 extern struct irq_desc irq_desc[NR_IRQS];
 
 static inline struct irq_desc *irq_to_desc(unsigned int irq)
 {
-        return (irq < nr_irqs) ? irq_desc + irq : NULL;
+        return (irq < NR_IRQS) ? irq_desc + irq : NULL;
+}
+static inline struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
+{
+        return irq_to_desc(irq);
+}
+
+#else
+
+extern struct irq_desc *irq_to_desc(unsigned int irq);
+extern struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu);
+extern struct irq_desc *move_irq_desc(struct irq_desc *old_desc, int cpu);
+
+# define for_each_irq_desc(irq, desc)           \
+        for (irq = 0, desc = irq_to_desc(irq); irq < nr_irqs; irq++, desc = irq_to_desc(irq))
+# define for_each_irq_desc_reverse(irq, desc)                          \
+        for (irq = nr_irqs - 1, desc = irq_to_desc(irq); irq >= 0; irq--, desc = irq_to_desc(irq))
+
+#define kstat_irqs_this_cpu(DESC) \
+        ((DESC)->kstat_irqs[smp_processor_id()])
+#define kstat_incr_irqs_this_cpu(irqno, DESC) \
+        ((DESC)->kstat_irqs[smp_processor_id()]++)
+
+#endif
+
+static inline struct irq_desc *
+irq_remap_to_desc(unsigned int irq, struct irq_desc *desc)
+{
+#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
+        return irq_to_desc(irq);
+#else
+        return desc;
+#endif
 }
 
 /*
@@ -380,6 +431,11 @@ extern int set_irq_msi(unsigned int irq, struct msi_desc *entry);
 #define get_irq_data(irq)       (irq_to_desc(irq)->handler_data)
 #define get_irq_msi(irq)        (irq_to_desc(irq)->msi_desc)
 
+#define get_irq_desc_chip(desc)         ((desc)->chip)
+#define get_irq_desc_chip_data(desc)    ((desc)->chip_data)
+#define get_irq_desc_data(desc)         ((desc)->handler_data)
+#define get_irq_desc_msi(desc)          ((desc)->msi_desc)
+
 #endif /* CONFIG_GENERIC_HARDIRQS */
 
 #endif /* !CONFIG_S390 */
diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h
index 452c280c8115..95d2b74641f5 100644
--- a/include/linux/irqnr.h
+++ b/include/linux/irqnr.h
@@ -1,24 +1,38 @@
 #ifndef _LINUX_IRQNR_H
 #define _LINUX_IRQNR_H
 
+/*
+ * Generic irq_desc iterators:
+ */
+#ifdef __KERNEL__
+
 #ifndef CONFIG_GENERIC_HARDIRQS
 #include <asm/irq.h>
 # define nr_irqs                NR_IRQS
 
 # define for_each_irq_desc(irq, desc)           \
         for (irq = 0; irq < nr_irqs; irq++)
+
+# define for_each_irq_desc_reverse(irq, desc)                          \
+        for (irq = nr_irqs - 1; irq >= 0; irq--)
 #else
+
 extern int nr_irqs;
 
+#ifndef CONFIG_SPARSE_IRQ
+
+struct irq_desc;
 # define for_each_irq_desc(irq, desc)           \
         for (irq = 0, desc = irq_desc; irq < nr_irqs; irq++, desc++)
-
-# define for_each_irq_desc_reverse(irq, desc)                           \
-        for (irq = nr_irqs - 1, desc = irq_desc + (nr_irqs - 1);        \
-             irq >= 0; irq--, desc--)
+# define for_each_irq_desc_reverse(irq, desc)                          \
+        for (irq = nr_irqs - 1, desc = irq_desc + (nr_irqs - 1);        \
+            irq >= 0; irq--, desc--)
+#endif
 #endif
 
-#define for_each_irq_nr(irq)                    \
-        for (irq = 0; irq < nr_irqs; irq++)
+#define for_each_irq_nr(irq)                   \
+       for (irq = 0; irq < nr_irqs; irq++)
+
+#endif /* __KERNEL__ */
 
 #endif
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 6002ae76785c..ca9ff6411dfa 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -141,6 +141,15 @@ extern int _cond_resched(void);
                 (__x < 0) ? -__x : __x;         \
         })
 
+#ifdef CONFIG_PROVE_LOCKING
+void might_fault(void);
+#else
+static inline void might_fault(void)
+{
+        might_sleep();
+}
+#endif
+
 extern struct atomic_notifier_head panic_notifier_list;
 extern long (*panic_blink)(long time);
 NORET_TYPE void panic(const char * fmt, ...)
@@ -188,6 +197,8 @@ extern unsigned long long memparse(const char *ptr, char **retptr);
 extern int core_kernel_text(unsigned long addr);
 extern int __kernel_text_address(unsigned long addr);
 extern int kernel_text_address(unsigned long addr);
+extern int func_ptr_is_kernel_text(void *ptr);
+
 struct pid;
 extern struct pid *session_of_pgrp(struct pid *pgrp);
 
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 4a145caeee07..4ee4b3d2316f 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -28,7 +28,9 @@ struct cpu_usage_stat {
 
 struct kernel_stat {
         struct cpu_usage_stat   cpustat;
-        unsigned int irqs[NR_IRQS];
+#ifndef CONFIG_SPARSE_IRQ
+       unsigned int irqs[NR_IRQS];
+#endif
 };
 
 DECLARE_PER_CPU(struct kernel_stat, kstat);
@@ -39,6 +41,10 @@ DECLARE_PER_CPU(struct kernel_stat, kstat);
 
 extern unsigned long long nr_context_switches(void);
 
+#ifndef CONFIG_SPARSE_IRQ
+#define kstat_irqs_this_cpu(irq) \
+        (kstat_this_cpu.irqs[irq])
+
 struct irq_desc;
 
 static inline void kstat_incr_irqs_this_cpu(unsigned int irq,
@@ -46,11 +52,17 @@ static inline void kstat_incr_irqs_this_cpu(unsigned int irq,
 {
         kstat_this_cpu.irqs[irq]++;
 }
+#endif
+
 
+#ifndef CONFIG_SPARSE_IRQ
 static inline unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
 {
        return kstat_cpu(cpu).irqs[irq];
 }
+#else
+extern unsigned int kstat_irqs_cpu(unsigned int irq, int cpu);
+#endif
 
 /*
  * Number of interrupts per specific IRQ source, since bootup
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 29aec6e10020..23bf02fb124f 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -73,6 +73,8 @@ struct lock_class_key {
         struct lockdep_subclass_key     subkeys[MAX_LOCKDEP_SUBCLASSES];
 };
 
+#define LOCKSTAT_POINTS         4
+
 /*
  * The lock-class itself:
  */
@@ -119,7 +121,8 @@ struct lock_class {
         int                             name_version;
 
 #ifdef CONFIG_LOCK_STAT
-        unsigned long                   contention_point[4];
+        unsigned long                   contention_point[LOCKSTAT_POINTS];
+        unsigned long                   contending_point[LOCKSTAT_POINTS];
 #endif
 };
 
@@ -144,6 +147,7 @@ enum bounce_type {
 
 struct lock_class_stats {
         unsigned long                   contention_point[4];
+        unsigned long                   contending_point[4];
         struct lock_time                read_waittime;
         struct lock_time                write_waittime;
         struct lock_time                read_holdtime;
@@ -165,6 +169,7 @@ struct lockdep_map {
         const char                      *name;
 #ifdef CONFIG_LOCK_STAT
         int                             cpu;
+        unsigned long                   ip;
 #endif
 };
 
@@ -309,8 +314,15 @@ extern void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 extern void lock_release(struct lockdep_map *lock, int nested,
                          unsigned long ip);
 
-extern void lock_set_subclass(struct lockdep_map *lock, unsigned int subclass,
-                              unsigned long ip);
+extern void lock_set_class(struct lockdep_map *lock, const char *name,
+                           struct lock_class_key *key, unsigned int subclass,
+                           unsigned long ip);
+
+static inline void lock_set_subclass(struct lockdep_map *lock,
+                unsigned int subclass, unsigned long ip)
+{
+        lock_set_class(lock, lock->name, lock->key, subclass, ip);
+}
 
 # define INIT_LOCKDEP                           .lockdep_recursion = 0,
 
@@ -328,6 +340,7 @@ static inline void lockdep_on(void)
 
 # define lock_acquire(l, s, t, r, c, n, i)      do { } while (0)
 # define lock_release(l, n, i)                  do { } while (0)
+# define lock_set_class(l, n, k, s, i)          do { } while (0)
 # define lock_set_subclass(l, s, i)             do { } while (0)
 # define lockdep_init()                         do { } while (0)
 # define lockdep_info()                         do { } while (0)
@@ -356,7 +369,7 @@ struct lock_class_key { };
 #ifdef CONFIG_LOCK_STAT
 
 extern void lock_contended(struct lockdep_map *lock, unsigned long ip);
-extern void lock_acquired(struct lockdep_map *lock);
+extern void lock_acquired(struct lockdep_map *lock, unsigned long ip);
 
 #define LOCK_CONTENDED(_lock, try, lock)                        \
 do {                                                            \
@@ -364,20 +377,20 @@ do {								\
                 lock_contended(&(_lock)->dep_map, _RET_IP_);    \
                 lock(_lock);                                    \
         }                                                       \
-        lock_acquired(&(_lock)->dep_map);                       \
+        lock_acquired(&(_lock)->dep_map, _RET_IP_);                     \
 } while (0)
 
 #else /* CONFIG_LOCK_STAT */
 
 #define lock_contended(lockdep_map, ip) do {} while (0)
-#define lock_acquired(lockdep_map) do {} while (0)
+#define lock_acquired(lockdep_map, ip) do {} while (0)
 
 #define LOCK_CONTENDED(_lock, try, lock) \
         lock(_lock)
 
 #endif /* CONFIG_LOCK_STAT */
 
-#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_GENERIC_HARDIRQS)
+#ifdef CONFIG_GENERIC_HARDIRQS
 extern void early_init_irq_lock_class(void);
 #else
 static inline void early_init_irq_lock_class(void)
@@ -481,4 +494,22 @@ static inline void print_irqtrace_events(struct task_struct *curr)
 # define lock_map_release(l)                    do { } while (0)
 #endif
 
+#ifdef CONFIG_PROVE_LOCKING
+# define might_lock(lock)                                               \
+do {                                                                    \
+        typecheck(struct lockdep_map *, &(lock)->dep_map);              \
+        lock_acquire(&(lock)->dep_map, 0, 0, 0, 2, NULL, _THIS_IP_);    \
+        lock_release(&(lock)->dep_map, 0, _THIS_IP_);                   \
+} while (0)
+# define might_lock_read(lock)                                          \
+do {                                                                    \
+        typecheck(struct lockdep_map *, &(lock)->dep_map);              \
+        lock_acquire(&(lock)->dep_map, 0, 0, 1, 2, NULL, _THIS_IP_);    \
+        lock_release(&(lock)->dep_map, 0, _THIS_IP_);                   \
+} while (0)
+#else
+# define might_lock(lock) do { } while (0)
+# define might_lock_read(lock) do { } while (0)
+#endif
+
 #endif /* __LINUX_LOCKDEP_H */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index fe825471d5aa..9cfc9b627fdd 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -232,8 +232,9 @@ struct mm_struct {
         struct core_state *core_state; /* coredumping support */
 
         /* aio bits */
-        rwlock_t                ioctx_list_lock;        /* aio lock */
-        struct kioctx           *ioctx_list;
+        spinlock_t              ioctx_lock;
+        struct hlist_head       ioctx_list;
+
 #ifdef CONFIG_MM_OWNER
         /*
          * "owner" points to a task that is regarded as the canonical
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 8f2939227207..d2b8a1e8ca11 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -10,8 +10,11 @@ struct msi_msg {
 };
 
 /* Helper functions */
+struct irq_desc;
 extern void mask_msi_irq(unsigned int irq);
 extern void unmask_msi_irq(unsigned int irq);
+extern void read_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg);
+extern void write_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg);
 extern void read_msi_msg(unsigned int irq, struct msi_msg *msg);
 extern void write_msi_msg(unsigned int irq, struct msi_msg *msg);
 
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index bc6da10ceee0..7a0e5c4f8072 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -144,6 +144,8 @@ extern int __must_check mutex_lock_killable(struct mutex *lock);
 /*
  * NOTE: mutex_trylock() follows the spin_trylock() convention,
  *       not the down_trylock() convention!
+ *
+ * Returns 1 if the mutex has been acquired successfully, and 0 on contention.
  */
 extern int mutex_trylock(struct mutex *lock);
 extern void mutex_unlock(struct mutex *lock);
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index a7c721355549..4f71bf4e628c 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -45,7 +45,11 @@ struct k_itimer {
         int it_requeue_pending;         /* waiting to requeue this timer */
 #define REQUEUE_PENDING 1
         int it_sigev_notify;            /* notify word of sigevent struct */
-        struct task_struct *it_process; /* process to send signal to */
+        struct signal_struct *it_signal;
+        union {
+                struct pid *it_pid;     /* pid of process to send signal to */
+                struct task_struct *it_process; /* for clock_nanosleep */
+        };
         struct sigqueue *sigq;          /* signal queue entry. */
         union {
                 struct {
diff --git a/include/linux/random.h b/include/linux/random.h
index 36f125c0c603..adbf3bd3c6b3 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -8,6 +8,7 @@
 #define _LINUX_RANDOM_H
 
 #include <linux/ioctl.h>
+#include <linux/irqnr.h>
 
 /* ioctl()'s for the random number generator */
 
@@ -44,6 +45,56 @@ struct rand_pool_info {
 
 extern void rand_initialize_irq(int irq);
 
+struct timer_rand_state;
+#ifndef CONFIG_SPARSE_IRQ
+
+extern struct timer_rand_state *irq_timer_state[];
+
+static inline struct timer_rand_state *get_timer_rand_state(unsigned int irq)
+{
+        if (irq >= nr_irqs)
+                return NULL;
+
+        return irq_timer_state[irq];
+}
+
+static inline void set_timer_rand_state(unsigned int irq, struct timer_rand_state *state)
+{
+        if (irq >= nr_irqs)
+                return;
+
+        irq_timer_state[irq] = state;
+}
+
+#else
+
+#include <linux/irq.h>
+static inline struct timer_rand_state *get_timer_rand_state(unsigned int irq)
+{
+        struct irq_desc *desc;
+
+        desc = irq_to_desc(irq);
+
+        if (!desc)
+                return NULL;
+
+        return desc->timer_rand_state;
+}
+
+static inline void set_timer_rand_state(unsigned int irq, struct timer_rand_state *state)
+{
+        struct irq_desc *desc;
+
+        desc = irq_to_desc(irq);
+
+        if (!desc)
+                return;
+
+        desc->timer_rand_state = state;
+}
+#endif
+
+
 extern void add_input_randomness(unsigned int type, unsigned int code,
                                  unsigned int value);
 extern void add_interrupt_randomness(int irq);
diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h
index 5f89b62e6983..301dda829e37 100644
--- a/include/linux/rcuclassic.h
+++ b/include/linux/rcuclassic.h
@@ -41,7 +41,7 @@
 #include <linux/seqlock.h>
 
 #ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-#define RCU_SECONDS_TILL_STALL_CHECK    ( 3 * HZ) /* for rcp->jiffies_stall */
+#define RCU_SECONDS_TILL_STALL_CHECK    (10 * HZ) /* for rcp->jiffies_stall */
 #define RCU_SECONDS_TILL_STALL_RECHECK  (30 * HZ) /* for rcp->jiffies_stall */
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 895dc9c1088c..1168fbcea8d4 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -52,11 +52,15 @@ struct rcu_head {
         void (*func)(struct rcu_head *head);
 };
 
-#ifdef CONFIG_CLASSIC_RCU
+#if defined(CONFIG_CLASSIC_RCU)
 #include <linux/rcuclassic.h>
-#else /* #ifdef CONFIG_CLASSIC_RCU */
+#elif defined(CONFIG_TREE_RCU)
+#include <linux/rcutree.h>
+#elif defined(CONFIG_PREEMPT_RCU)
 #include <linux/rcupreempt.h>
-#endif /* #else #ifdef CONFIG_CLASSIC_RCU */
+#else
+#error "Unknown RCU implementation specified to kernel configuration"
+#endif /* #else #if defined(CONFIG_CLASSIC_RCU) */
 
 #define RCU_HEAD_INIT   { .next = NULL, .func = NULL }
 #define RCU_HEAD(head) struct rcu_head head = RCU_HEAD_INIT
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
new file mode 100644
index 000000000000..d4368b7975c3
--- /dev/null
+++ b/include/linux/rcutree.h
@@ -0,0 +1,329 @@
+/*
+ * Read-Copy Update mechanism for mutual exclusion (tree-based version)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright IBM Corporation, 2008
+ *
+ * Author: Dipankar Sarma <dipankar@in.ibm.com>
+ *         Paul E. McKenney <paulmck@linux.vnet.ibm.com> Hierarchical algorithm
+ *
+ * Based on the original work by Paul McKenney <paulmck@us.ibm.com>
+ * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
+ *
+ * For detailed explanation of Read-Copy Update mechanism see -
+ *      Documentation/RCU
+ */
+
+#ifndef __LINUX_RCUTREE_H
+#define __LINUX_RCUTREE_H
+
+#include <linux/cache.h>
+#include <linux/spinlock.h>
+#include <linux/threads.h>
+#include <linux/percpu.h>
+#include <linux/cpumask.h>
+#include <linux/seqlock.h>
+
+/*
+ * Define shape of hierarchy based on NR_CPUS and CONFIG_RCU_FANOUT.
+ * In theory, it should be possible to add more levels straightforwardly.
+ * In practice, this has not been tested, so there is probably some
+ * bug somewhere.
+ */
+#define MAX_RCU_LVLS 3
+#define RCU_FANOUT            (CONFIG_RCU_FANOUT)
+#define RCU_FANOUT_SQ         (RCU_FANOUT * RCU_FANOUT)
+#define RCU_FANOUT_CUBE       (RCU_FANOUT_SQ * RCU_FANOUT)
+
+#if NR_CPUS <= RCU_FANOUT
+#  define NUM_RCU_LVLS        1
+#  define NUM_RCU_LVL_0       1
+#  define NUM_RCU_LVL_1       (NR_CPUS)
+#  define NUM_RCU_LVL_2       0
+#  define NUM_RCU_LVL_3       0
+#elif NR_CPUS <= RCU_FANOUT_SQ
+#  define NUM_RCU_LVLS        2
+#  define NUM_RCU_LVL_0       1
+#  define NUM_RCU_LVL_1       (((NR_CPUS) + RCU_FANOUT - 1) / RCU_FANOUT)
+#  define NUM_RCU_LVL_2       (NR_CPUS)
+#  define NUM_RCU_LVL_3       0
+#elif NR_CPUS <= RCU_FANOUT_CUBE
+#  define NUM_RCU_LVLS        3
+#  define NUM_RCU_LVL_0       1
+#  define NUM_RCU_LVL_1       (((NR_CPUS) + RCU_FANOUT_SQ - 1) / RCU_FANOUT_SQ)
+#  define NUM_RCU_LVL_2       (((NR_CPUS) + (RCU_FANOUT) - 1) / (RCU_FANOUT))
+#  define NUM_RCU_LVL_3       NR_CPUS
+#else
+# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
+#endif /* #if (NR_CPUS) <= RCU_FANOUT */
+
+#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3)
+#define NUM_RCU_NODES (RCU_SUM - NR_CPUS)
+
+/*
+ * Dynticks per-CPU state.
+ */
+struct rcu_dynticks {
+        int dynticks_nesting;   /* Track nesting level, sort of. */
+        int dynticks;           /* Even value for dynticks-idle, else odd. */
+        int dynticks_nmi;       /* Even value for either dynticks-idle or */
+                                /*  not in nmi handler, else odd.  So this */
+                                /*  remains even for nmi from irq handler. */
+};
+
+/*
+ * Definition for node within the RCU grace-period-detection hierarchy.
+ */
+struct rcu_node {
+        spinlock_t lock;
+        unsigned long qsmask;   /* CPUs or groups that need to switch in */
+                                /*  order for current grace period to proceed.*/
+        unsigned long qsmaskinit;
+                                /* Per-GP initialization for qsmask. */
+        unsigned long grpmask;  /* Mask to apply to parent qsmask. */
+        int     grplo;          /* lowest-numbered CPU or group here. */
+        int     grphi;          /* highest-numbered CPU or group here. */
+        u8      grpnum;         /* CPU/group number for next level up. */
+        u8      level;          /* root is at level 0. */
+        struct rcu_node *parent;
+} ____cacheline_internodealigned_in_smp;
+
+/* Index values for nxttail array in struct rcu_data. */
+#define RCU_DONE_TAIL           0       /* Also RCU_WAIT head. */
+#define RCU_WAIT_TAIL           1       /* Also RCU_NEXT_READY head. */
+#define RCU_NEXT_READY_TAIL     2       /* Also RCU_NEXT head. */
+#define RCU_NEXT_TAIL           3
+#define RCU_NEXT_SIZE           4
+
+/* Per-CPU data for read-copy update. */
+struct rcu_data {
+        /* 1) quiescent-state and grace-period handling : */
+        long            completed;      /* Track rsp->completed gp number */
+                                        /*  in order to detect GP end. */
+        long            gpnum;          /* Highest gp number that this CPU */
+                                        /*  is aware of having started. */
+        long            passed_quiesc_completed;
+                                        /* Value of completed at time of qs. */
+        bool            passed_quiesc;  /* User-mode/idle loop etc. */
+        bool            qs_pending;     /* Core waits for quiesc state. */
+        bool            beenonline;     /* CPU online at least once. */
+        struct rcu_node *mynode;        /* This CPU's leaf of hierarchy */
+        unsigned long grpmask;          /* Mask to apply to leaf qsmask. */
+
+        /* 2) batch handling */
+        /*
+         * If nxtlist is not NULL, it is partitioned as follows.
+         * Any of the partitions might be empty, in which case the
+         * pointer to that partition will be equal to the pointer for
+         * the following partition.  When the list is empty, all of
+         * the nxttail elements point to nxtlist, which is NULL.
+         *
+         * [*nxttail[RCU_NEXT_READY_TAIL], NULL = *nxttail[RCU_NEXT_TAIL]):
+         *      Entries that might have arrived after current GP ended
+         * [*nxttail[RCU_WAIT_TAIL], *nxttail[RCU_NEXT_READY_TAIL]):
+         *      Entries known to have arrived before current GP ended
+         * [*nxttail[RCU_DONE_TAIL], *nxttail[RCU_WAIT_TAIL]):
+         *      Entries that batch # <= ->completed - 1: waiting for current GP
+         * [nxtlist, *nxttail[RCU_DONE_TAIL]):
+         *      Entries that batch # <= ->completed
+         *      The grace period for these entries has completed, and
+         *      the other grace-period-completed entries may be moved
+         *      here temporarily in rcu_process_callbacks().
+         */
+        struct rcu_head *nxtlist;
+        struct rcu_head **nxttail[RCU_NEXT_SIZE];
+        long            qlen;           /* # of queued callbacks */
+        long            blimit;         /* Upper limit on a processed batch */
+
+#ifdef CONFIG_NO_HZ
+        /* 3) dynticks interface. */
+        struct rcu_dynticks *dynticks;  /* Shared per-CPU dynticks state. */
+        int dynticks_snap;              /* Per-GP tracking for dynticks. */
+        int dynticks_nmi_snap;          /* Per-GP tracking for dynticks_nmi. */
+#endif /* #ifdef CONFIG_NO_HZ */
+
+        /* 4) reasons this CPU needed to be kicked by force_quiescent_state */
+#ifdef CONFIG_NO_HZ
+        unsigned long dynticks_fqs;     /* Kicked due to dynticks idle. */
+#endif /* #ifdef CONFIG_NO_HZ */
+        unsigned long offline_fqs;      /* Kicked due to being offline. */
+        unsigned long resched_ipi;      /* Sent a resched IPI. */
+
+        /* 5) state to allow this CPU to force_quiescent_state on others */
+        long n_rcu_pending;             /* rcu_pending() calls since boot. */
+        long n_rcu_pending_force_qs;    /* when to force quiescent states. */
+
+        int cpu;
+};
+
+/* Values for signaled field in struct rcu_state. */
+#define RCU_GP_INIT             0       /* Grace period being initialized. */
+#define RCU_SAVE_DYNTICK        1       /* Need to scan dyntick state. */
+#define RCU_FORCE_QS            2       /* Need to force quiescent state. */
+#ifdef CONFIG_NO_HZ
+#define RCU_SIGNAL_INIT         RCU_SAVE_DYNTICK
+#else /* #ifdef CONFIG_NO_HZ */
+#define RCU_SIGNAL_INIT         RCU_FORCE_QS
+#endif /* #else #ifdef CONFIG_NO_HZ */
+
+#define RCU_JIFFIES_TILL_FORCE_QS        3      /* for rsp->jiffies_force_qs */
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+#define RCU_SECONDS_TILL_STALL_CHECK   (10 * HZ)  /* for rsp->jiffies_stall */
+#define RCU_SECONDS_TILL_STALL_RECHECK (30 * HZ)  /* for rsp->jiffies_stall */
+#define RCU_STALL_RAT_DELAY             2         /* Allow other CPUs time */
+                                                  /*  to take at least one */
+                                                  /*  scheduling clock irq */
+                                                  /*  before ratting on them. */
+
+#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+
+/*
+ * RCU global state, including node hierarchy.  This hierarchy is
+ * represented in "heap" form in a dense array.  The root (first level)
+ * of the hierarchy is in ->node[0] (referenced by ->level[0]), the second
+ * level in ->node[1] through ->node[m] (->node[1] referenced by ->level[1]),
+ * and the third level in ->node[m+1] and following (->node[m+1] referenced
+ * by ->level[2]).  The number of levels is determined by the number of
+ * CPUs and by CONFIG_RCU_FANOUT.  Small systems will have a "hierarchy"
+ * consisting of a single rcu_node.
+ */
+struct rcu_state {
+        struct rcu_node node[NUM_RCU_NODES];    /* Hierarchy. */
+        struct rcu_node *level[NUM_RCU_LVLS];   /* Hierarchy levels. */
+        u32 levelcnt[MAX_RCU_LVLS + 1];         /* # nodes in each level. */
+        u8 levelspread[NUM_RCU_LVLS];           /* kids/node in each level. */
+        struct rcu_data *rda[NR_CPUS];          /* array of rdp pointers. */
+
+        /* The following fields are guarded by the root rcu_node's lock. */
+
+        u8      signaled ____cacheline_internodealigned_in_smp;
+                                                /* Force QS state. */
+        long    gpnum;                          /* Current gp number. */
+        long    completed;                      /* # of last completed gp. */
+        spinlock_t onofflock;                   /* exclude on/offline and */
+                                                /*  starting new GP. */
+        spinlock_t fqslock;                     /* Only one task forcing */
+                                                /*  quiescent states. */
+        unsigned long jiffies_force_qs;         /* Time at which to invoke */
+                                                /*  force_quiescent_state(). */
+        unsigned long n_force_qs;               /* Number of calls to */
+                                                /*  force_quiescent_state(). */
+        unsigned long n_force_qs_lh;            /* ~Number of calls leaving */
+                                                /*  due to lock unavailable. */
+        unsigned long n_force_qs_ngp;           /* Number of calls leaving */
+                                                /*  due to no GP active. */
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+        unsigned long gp_start;                 /* Time at which GP started, */
+                                                /*  but in jiffies. */
+        unsigned long jiffies_stall;            /* Time at which to check */
+                                                /*  for CPU stalls. */
+#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+#ifdef CONFIG_NO_HZ
+        long dynticks_completed;                /* Value of completed @ snap. */
+#endif /* #ifdef CONFIG_NO_HZ */
+};
+
+extern struct rcu_state rcu_state;
+DECLARE_PER_CPU(struct rcu_data, rcu_data);
+
+extern struct rcu_state rcu_bh_state;
+DECLARE_PER_CPU(struct rcu_data, rcu_bh_data);
+
+/*
+ * Increment the quiescent state counter.
+ * The counter is a bit degenerated: We do not need to know
+ * how many quiescent states passed, just if there was at least
+ * one since the start of the grace period. Thus just a flag.
+ */
+static inline void rcu_qsctr_inc(int cpu)
+{
+        struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
+        rdp->passed_quiesc = 1;
+        rdp->passed_quiesc_completed = rdp->completed;
+}
+static inline void rcu_bh_qsctr_inc(int cpu)
+{
+        struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
+        rdp->passed_quiesc = 1;
+        rdp->passed_quiesc_completed = rdp->completed;
+}
+
+extern int rcu_pending(int cpu);
+extern int rcu_needs_cpu(int cpu);
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+extern struct lockdep_map rcu_lock_map;
+# define rcu_read_acquire()     \
+                        lock_acquire(&rcu_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_)
+# define rcu_read_release()     lock_release(&rcu_lock_map, 1, _THIS_IP_)
+#else
+# define rcu_read_acquire()     do { } while (0)
+# define rcu_read_release()     do { } while (0)
+#endif
+
+static inline void __rcu_read_lock(void)
+{
+        preempt_disable();
+        __acquire(RCU);
+        rcu_read_acquire();
+}
+static inline void __rcu_read_unlock(void)
+{
+        rcu_read_release();
+        __release(RCU);
+        preempt_enable();
+}
+static inline void __rcu_read_lock_bh(void)
+{
+        local_bh_disable();
+        __acquire(RCU_BH);
+        rcu_read_acquire();
+}
+static inline void __rcu_read_unlock_bh(void)
+{
+        rcu_read_release();
+        __release(RCU_BH);
+        local_bh_enable();
+}
+
+#define __synchronize_sched() synchronize_rcu()
+
+#define call_rcu_sched(head, func) call_rcu(head, func)
+
+static inline void rcu_init_sched(void)
+{
+}
+
+extern void __rcu_init(void);
+extern void rcu_check_callbacks(int cpu, int user);
+extern void rcu_restart_cpu(int cpu);
+
+extern long rcu_batches_completed(void);
+extern long rcu_batches_completed_bh(void);
+
+#ifdef CONFIG_NO_HZ
+void rcu_enter_nohz(void);
+void rcu_exit_nohz(void);
+#else /* CONFIG_NO_HZ */
+static inline void rcu_enter_nohz(void)
+{
+}
+static inline void rcu_exit_nohz(void)
+{
+}
+#endif /* CONFIG_NO_HZ */
+
+#endif /* __LINUX_RCUTREE_H */
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index b18ec5533e8c..325af1de0351 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -7,9 +7,31 @@ struct device;
 struct dma_attrs;
 struct scatterlist;
 
+/*
+ * Maximum allowable number of contiguous slabs to map,
+ * must be a power of 2.  What is the appropriate value ?
+ * The complexity of {map,unmap}_single is linearly dependent on this value.
+ */
+#define IO_TLB_SEGSIZE  128
+
+
+/*
+ * log of the size of each IO TLB slab.  The number of slabs is command line
+ * controllable.
+ */
+#define IO_TLB_SHIFT 11
+
 extern void
 swiotlb_init(void);
 
+extern void *swiotlb_alloc_boot(size_t bytes, unsigned long nslabs);
+extern void *swiotlb_alloc(unsigned order, unsigned long nslabs);
+
+extern dma_addr_t swiotlb_phys_to_bus(phys_addr_t address);
+extern phys_addr_t swiotlb_bus_to_phys(dma_addr_t address);
+
+extern int swiotlb_arch_range_needs_mapping(void *ptr, size_t size);
+
 extern void
 *swiotlb_alloc_coherent(struct device *hwdev, size_t size,
                         dma_addr_t *dma_handle, gfp_t flags);
diff --git a/include/linux/timex.h b/include/linux/timex.h
index 9007313b5b71..998a55d80acf 100644
--- a/include/linux/timex.h
+++ b/include/linux/timex.h
@@ -53,47 +53,11 @@
 #ifndef _LINUX_TIMEX_H
 #define _LINUX_TIMEX_H
 
-#include <linux/compiler.h>
 #include <linux/time.h>
 
-#include <asm/param.h>
-
 #define NTP_API         4       /* NTP API version */
 
 /*
- * SHIFT_KG and SHIFT_KF establish the damping of the PLL and are chosen
- * for a slightly underdamped convergence characteristic. SHIFT_KH
- * establishes the damping of the FLL and is chosen by wisdom and black
- * art.
- *
- * MAXTC establishes the maximum time constant of the PLL. With the
- * SHIFT_KG and SHIFT_KF values given and a time constant range from
- * zero to MAXTC, the PLL will converge in 15 minutes to 16 hours,
- * respectively.
- */
-#define SHIFT_PLL       4       /* PLL frequency factor (shift) */
-#define SHIFT_FLL       2       /* FLL frequency factor (shift) */
-#define MAXTC           10      /* maximum time constant (shift) */
-
-/*
- * SHIFT_USEC defines the scaling (shift) of the time_freq and
- * time_tolerance variables, which represent the current frequency
- * offset and maximum frequency tolerance.
- */
-#define SHIFT_USEC 16           /* frequency offset scale (shift) */
-#define PPM_SCALE (NSEC_PER_USEC << (NTP_SCALE_SHIFT - SHIFT_USEC))
-#define PPM_SCALE_INV_SHIFT 19
-#define PPM_SCALE_INV ((1ll << (PPM_SCALE_INV_SHIFT + NTP_SCALE_SHIFT)) / \
-                       PPM_SCALE + 1)
-
-#define MAXPHASE 500000000l     /* max phase error (ns) */
-#define MAXFREQ 500000          /* max frequency error (ns/s) */
-#define MAXFREQ_SCALED ((s64)MAXFREQ << NTP_SCALE_SHIFT)
-#define MINSEC 256              /* min interval between updates (s) */
-#define MAXSEC 2048             /* max interval between updates (s) */
-#define NTP_PHASE_LIMIT ((MAXPHASE / NSEC_PER_USEC) << 5) /* beyond max. dispersion */
-
-/*
  * syscall interface - used (mainly by NTP daemon)
  * to discipline kernel clock oscillator
  */
@@ -199,9 +163,46 @@ struct timex {
 #define TIME_BAD        TIME_ERROR /* bw compat */
 
 #ifdef __KERNEL__
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <linux/param.h>
+
 #include <asm/timex.h>
 
 /*
+ * SHIFT_KG and SHIFT_KF establish the damping of the PLL and are chosen
+ * for a slightly underdamped convergence characteristic. SHIFT_KH
+ * establishes the damping of the FLL and is chosen by wisdom and black
+ * art.
+ *
+ * MAXTC establishes the maximum time constant of the PLL. With the
+ * SHIFT_KG and SHIFT_KF values given and a time constant range from
+ * zero to MAXTC, the PLL will converge in 15 minutes to 16 hours,
+ * respectively.
+ */
+#define SHIFT_PLL       4       /* PLL frequency factor (shift) */
+#define SHIFT_FLL       2       /* FLL frequency factor (shift) */
+#define MAXTC           10      /* maximum time constant (shift) */
+
+/*
+ * SHIFT_USEC defines the scaling (shift) of the time_freq and
+ * time_tolerance variables, which represent the current frequency
+ * offset and maximum frequency tolerance.
+ */
+#define SHIFT_USEC 16           /* frequency offset scale (shift) */
+#define PPM_SCALE (NSEC_PER_USEC << (NTP_SCALE_SHIFT - SHIFT_USEC))
+#define PPM_SCALE_INV_SHIFT 19
+#define PPM_SCALE_INV ((1ll << (PPM_SCALE_INV_SHIFT + NTP_SCALE_SHIFT)) / \
+                       PPM_SCALE + 1)
+
+#define MAXPHASE 500000000l     /* max phase error (ns) */
+#define MAXFREQ 500000          /* max frequency error (ns/s) */
+#define MAXFREQ_SCALED ((s64)MAXFREQ << NTP_SCALE_SHIFT)
+#define MINSEC 256              /* min interval between updates (s) */
+#define MAXSEC 2048             /* max interval between updates (s) */
+#define NTP_PHASE_LIMIT ((MAXPHASE / NSEC_PER_USEC) << 5) /* beyond max. dispersion */
+
+/*
  * kernel variables
  * Note: maximum error = NTP synch distance = dispersion + delay / 2;
  * estimated error = NTP dispersion.
diff --git a/include/linux/types.h b/include/linux/types.h
index 1d98330b1f2c..121f349cb7ec 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -135,19 +135,14 @@ typedef		__s64		int64_t;
  *
  * Linux always considers sectors to be 512 bytes long independently
  * of the devices real block size.
+ *
+ * blkcnt_t is the type of the inode's block count.
  */
 #ifdef CONFIG_LBD
 typedef u64 sector_t;
-#else
-typedef unsigned long sector_t;
-#endif
-
-/*
- * The type of the inode's block count.
- */
-#ifdef CONFIG_LSF
 typedef u64 blkcnt_t;
 #else
+typedef unsigned long sector_t;
 typedef unsigned long blkcnt_t;
 #endif
 
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index fec6decfb983..6b58367d145e 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -78,7 +78,7 @@ static inline unsigned long __copy_from_user_nocache(void *to,
                                                         \
                 set_fs(KERNEL_DS);                      \
                 pagefault_disable();                    \
-                ret = __get_user(retval, (__force typeof(retval) __user *)(addr));              \
+                ret = __copy_from_user_inatomic(&(retval), (__force typeof(retval) __user *)(addr), sizeof(retval));            \
                 pagefault_enable();                     \
                 set_fs(old_fs);                         \
                 ret;                                    \