Merge branch 'linus' into x86/urgent

Merge reason: Merge upstream commits to avoid conflicts in upcoming patches. Signed-off-by: Ingo Molnar <mingo@elte.hu>
author: Ingo Molnar <mingo@elte.hu> 2011-03-18 05:38:53 -0400
committer: Ingo Molnar <mingo@elte.hu> 2011-03-18 05:39:00 -0400
commit: 8dd8997d2c56c9f248294805e129e1fc69444380 (patch)
tree: 3b030a04295fc031db98746c4074c2df1ed6a19f /include
parent: 1eda75c131ea42ec173323b6c34aeed78ae637c1 (diff)
parent: 016aa2ed1cc9cf704cf76d8df07751b6daa9750f (diff)
50 files changed, 930 insertions, 287 deletions
diff --git a/include/asm-generic/cputime.h b/include/asm-generic/cputime.h
index 2bcc5c7c22a6..61e03dd7939e 100644
--- a/include/asm-generic/cputime.h
+++ b/include/asm-generic/cputime.h
@@ -30,6 +30,9 @@ typedef u64 cputime64_t;
 #define cputime64_to_jiffies64(__ct)    (__ct)
 #define jiffies64_to_cputime64(__jif)   (__jif)
 #define cputime_to_cputime64(__ct)      ((u64) __ct)
+#define cputime64_gt(__a, __b)          ((__a) >  (__b))
+#define nsecs_to_cputime64(__ct)        nsecs_to_jiffies64(__ct)
 /*
diff --git a/include/asm-generic/fcntl.h b/include/asm-generic/fcntl.h
index 0fc16e3f0bfc..84793c7025e2 100644
--- a/include/asm-generic/fcntl.h
+++ b/include/asm-generic/fcntl.h
@@ -80,6 +80,10 @@
 #define O_SYNC          (__O_SYNC|O_DSYNC)
 #endif
+#ifndef O_PATH
+#define O_PATH          010000000
+#endif
 #ifndef O_NDELAY
 #define O_NDELAY        O_NONBLOCK
 #endif
diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h
index 3c2344f48136..01f227e14254 100644
--- a/include/asm-generic/futex.h
+++ b/include/asm-generic/futex.h
@@ -6,7 +6,7 @@
 #include <asm/errno.h>
 static inline int
-futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
        int op = (encoded_op >> 28) & 7;
        int cmp = (encoded_op >> 24) & 15;
@@ -16,7 +16,7 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
        if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
                oparg = 1 << oparg;
-        if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+        if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
                return -EFAULT;
        pagefault_disable();
@@ -48,7 +48,8 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 }
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+                              u32 oldval, u32 newval)
 {
        return -ENOSYS;
 }
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index b3bfabc258f3..c1a1216e29ce 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -11,6 +11,7 @@ extern char _sinittext[], _einittext[];
 extern char _end[];
 extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[];
 extern char __kprobes_text_start[], __kprobes_text_end[];
+extern char __entry_text_start[], __entry_text_end[];
 extern char __initdata_begin[], __initdata_end[];
 extern char __start_rodata[], __end_rodata[];
diff --git a/include/asm-generic/unistd.h b/include/asm-generic/unistd.h
index b969770196c2..57af0338d270 100644
--- a/include/asm-generic/unistd.h
+++ b/include/asm-generic/unistd.h
@@ -646,9 +646,13 @@ __SYSCALL(__NR_prlimit64, sys_prlimit64)
 __SYSCALL(__NR_fanotify_init, sys_fanotify_init)
 #define __NR_fanotify_mark 263
 __SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
+#define __NR_name_to_handle_at          264
+__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
+#define __NR_open_by_handle_at          265
+__SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at)
 #undef __NR_syscalls
-#define __NR_syscalls 264
+#define __NR_syscalls 266
 /*
 * All syscalls below here should go away really,
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index fe77e3395b40..906c3ceca9a2 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -424,6 +424,12 @@
                *(.kprobes.text)                                        \
                VMLINUX_SYMBOL(__kprobes_text_end) = .;
+#define ENTRY_TEXT                                                      \
+                ALIGN_FUNCTION();                                       \
+                VMLINUX_SYMBOL(__entry_text_start) = .;                 \
+                *(.entry.text)                                          \
+                VMLINUX_SYMBOL(__entry_text_end) = .;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 #define IRQENTRY_TEXT                                                   \
                ALIGN_FUNCTION();                                       \
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index ce104e33cd22..e654fa239916 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -474,7 +474,8 @@ struct cgroup_subsys {
                        struct cgroup *old_cgrp, struct task_struct *tsk,
                        bool threadgroup);
        void (*fork)(struct cgroup_subsys *ss, struct task_struct *task);
-        void (*exit)(struct cgroup_subsys *ss, struct task_struct *task);
+        void (*exit)(struct cgroup_subsys *ss, struct cgroup *cgrp,
+                        struct cgroup *old_cgrp, struct task_struct *task);
        int (*populate)(struct cgroup_subsys *ss,
                        struct cgroup *cgrp);
        void (*post_clone)(struct cgroup_subsys *ss, struct cgroup *cgrp);
@@ -626,6 +627,7 @@ bool css_is_ancestor(struct cgroup_subsys_state *cg,
 /* Get id and depth of css */
 unsigned short css_id(struct cgroup_subsys_state *css);
 unsigned short css_depth(struct cgroup_subsys_state *css);
+struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id);
 #else /* !CONFIG_CGROUPS */
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index ccefff02b6cb..cdbfcb8780ec 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -65,4 +65,8 @@ SUBSYS(net_cls)
 SUBSYS(blkio)
 #endif
+#ifdef CONFIG_CGROUP_PERF
+SUBSYS(perf)
+#endif
 /* */
diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h
index 597692f1fc8d..65970b811e22 100644
--- a/include/linux/debugobjects.h
+++ b/include/linux/debugobjects.h
@@ -34,7 +34,10 @@ struct debug_obj {
 /**
 * struct debug_obj_descr - object type specific debug description structure
+ *
 * @name:               name of the object typee
+ * @debug_hint:         function returning address, which have associated
+ *                      kernel symbol, to allow identify the object
 * @fixup_init:         fixup function, which is called when the init check
 *                      fails
 * @fixup_activate:     fixup function, which is called when the activate check
@@ -46,7 +49,7 @@ struct debug_obj {
 */
 struct debug_obj_descr {
        const char              *name;
+        void *(*debug_hint)     (void *addr);
        int (*fixup_init)       (void *addr, enum debug_obj_state state);
        int (*fixup_activate)   (void *addr, enum debug_obj_state state);
        int (*fixup_destroy)    (void *addr, enum debug_obj_state state);
diff --git a/include/linux/device.h b/include/linux/device.h
index 1bf5cf0b4513..ca5d25225aab 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -128,9 +128,7 @@ struct device_driver {
        bool suppress_bind_attrs;       /* disables bind/unbind via sysfs */
-#if defined(CONFIG_OF)
        const struct of_device_id       *of_match_table;
-#endif
        int (*probe) (struct device *dev);
        int (*remove) (struct device *dev);
@@ -441,9 +439,8 @@ struct device {
                                             override */
        /* arch specific additions */
        struct dev_archdata     archdata;
-#ifdef CONFIG_OF
-        struct device_node      *of_node;
+        struct device_node      *of_node; /* associated device tree node */
-#endif
        dev_t                   devt;   /* dev_t, creates the sysfs "dev" */
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 28028988c862..33a42f24b275 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -8,6 +8,9 @@ struct inode;
 struct super_block;
 struct vfsmount;
+/* limit the handle size to NFSv4 handle size now */
+#define MAX_HANDLE_SZ 128
 /*
 * The fileid_type identifies how the file within the filesystem is encoded.
 * In theory this is freely set and parsed by the filesystem, but we try to
@@ -121,8 +124,10 @@ struct fid {
 *    set, the encode_fh() should store sufficient information so that a good
 *    attempt can be made to find not only the file but also it's place in the
 *    filesystem.   This typically means storing a reference to de->d_parent in
- *    the filehandle fragment.  encode_fh() should return the number of bytes
+ *    the filehandle fragment.  encode_fh() should return the fileid_type on
- *    stored or a negative error code such as %-ENOSPC
+ *    success and on error returns 255 (if the space needed to encode fh is
+ *    greater than @max_len*4 bytes). On error @max_len contains the minimum
+ *    size(in 4 byte unit) needed to encode the file handle.
 *
 * fh_to_dentry:
 *    @fh_to_dentry is given a &struct super_block (@sb) and a file handle
diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h
index a562fa5fb4e3..f550f894ba15 100644
--- a/include/linux/fcntl.h
+++ b/include/linux/fcntl.h
@@ -46,6 +46,7 @@
                                           unlinking file.  */
 #define AT_SYMLINK_FOLLOW       0x400   /* Follow symbolic links.  */
 #define AT_NO_AUTOMOUNT         0x800   /* Suppress terminal automount traversal */
+#define AT_EMPTY_PATH           0x1000  /* Allow empty relative pathname */
 #ifdef __KERNEL__
diff --git a/include/linux/file.h b/include/linux/file.h
index e85baebf6279..21a79958541c 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -29,6 +29,8 @@ static inline void fput_light(struct file *file, int fput_needed)
 extern struct file *fget(unsigned int fd);
 extern struct file *fget_light(unsigned int fd, int *fput_needed);
+extern struct file *fget_raw(unsigned int fd);
+extern struct file *fget_raw_light(unsigned int fd, int *fput_needed);
 extern void set_close_on_exec(unsigned int fd, int flag);
 extern void put_filp(struct file *);
 extern int alloc_fd(unsigned start, unsigned flags);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e38b50a4b9d2..13df14e2c42e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -102,6 +102,9 @@ struct inodes_stat_t {
 /* File is huge (eg. /dev/kmem): treat loff_t as unsigned */
 #define FMODE_UNSIGNED_OFFSET   ((__force fmode_t)0x2000)
+/* File is opened with O_PATH; almost nothing can be done with it */
+#define FMODE_PATH              ((__force fmode_t)0x4000)
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY          ((__force fmode_t)0x1000000)
@@ -978,6 +981,13 @@ struct file {
 #endif
 };
+struct file_handle {
+        __u32 handle_bytes;
+        int handle_type;
+        /* file identifier */
+        unsigned char f_handle[0];
+};
 #define get_file(x)     atomic_long_inc(&(x)->f_count)
 #define fput_atomic(x)  atomic_long_add_unless(&(x)->f_count, -1, 1)
 #define file_count(x)   atomic_long_read(&(x)->f_count)
@@ -1401,6 +1411,7 @@ struct super_block {
        wait_queue_head_t       s_wait_unfrozen;
        char s_id[32];                          /* Informational name */
+        u8 s_uuid[16];                          /* UUID */
        void                    *s_fs_info;     /* Filesystem private info */
        fmode_t                 s_mode;
@@ -1874,6 +1885,8 @@ extern void drop_collected_mounts(struct vfsmount *);
 extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
                          struct vfsmount *);
 extern int vfs_statfs(struct path *, struct kstatfs *);
+extern int user_statfs(const char __user *, struct kstatfs *);
+extern int fd_statfs(int, struct kstatfs *);
 extern int statfs_by_dentry(struct dentry *, struct kstatfs *);
 extern int freeze_super(struct super_block *super);
 extern int thaw_super(struct super_block *super);
@@ -1990,6 +2003,8 @@ extern int do_fallocate(struct file *file, int mode, loff_t offset,
 extern long do_sys_open(int dfd, const char __user *filename, int flags,
                        int mode);
 extern struct file *filp_open(const char *, int, int);
+extern struct file *file_open_root(struct dentry *, struct vfsmount *,
+                                   const char *, int);
 extern struct file * dentry_open(struct dentry *, struct vfsmount *, int,
                                 const struct cred *);
 extern int filp_close(struct file *, fl_owner_t id);
@@ -2205,10 +2220,6 @@ extern struct file *create_read_pipe(struct file *f, int flags);
 extern struct file *create_write_pipe(int flags);
 extern void free_write_pipe(struct file *);
-extern struct file *do_filp_open(int dfd, const char *pathname,
-                int open_flag, int mode, int acc_mode);
-extern int may_open(struct path *, int, int);
 extern int kernel_read(struct file *, loff_t, char *, unsigned long);
 extern struct file * open_exec(const char *);
 
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index dcd6a7c3a435..ca29e03c1fac 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -428,6 +428,7 @@ extern void unregister_ftrace_graph(void);
 extern void ftrace_graph_init_task(struct task_struct *t);
 extern void ftrace_graph_exit_task(struct task_struct *t);
+extern void ftrace_graph_init_idle_task(struct task_struct *t, int cpu);
 static inline int task_curr_ret_stack(struct task_struct *t)
 {
@@ -451,6 +452,7 @@ static inline void unpause_graph_tracing(void)
 static inline void ftrace_graph_init_task(struct task_struct *t) { }
 static inline void ftrace_graph_exit_task(struct task_struct *t) { }
+static inline void ftrace_graph_init_idle_task(struct task_struct *t, int cpu) { }
 static inline int register_ftrace_graph(trace_func_graph_ret_t retfunc,
                          trace_func_graph_ent_t entryfunc)
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 47e3997f7b5c..22b32af1b5ec 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -37,7 +37,6 @@ struct trace_entry {
        unsigned char           flags;
        unsigned char           preempt_count;
        int                     pid;
-        int                     lock_depth;
 };
 #define FTRACE_MAX_EVENT                                                \
@@ -208,7 +207,6 @@ struct ftrace_event_call {
 #define PERF_MAX_TRACE_SIZE     2048
-#define MAX_FILTER_PRED         32
 #define MAX_FILTER_STR_VAL      256     /* Should handle KSYM_SYMBOL_LEN */
 extern void destroy_preds(struct ftrace_event_call *call);
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index f376ddc64c4d..62f500c724f9 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -54,11 +54,13 @@ enum hrtimer_restart {
 * 0x00         inactive
 * 0x01         enqueued into rbtree
 * 0x02         callback function running
+ * 0x04         timer is migrated to another cpu
 *
 * Special cases:
 * 0x03         callback function running and enqueued
 *              (was requeued on another CPU)
- * 0x09         timer was migrated on CPU hotunplug
+ * 0x05         timer was migrated on CPU hotunplug
+ *
 * The "callback function running and enqueued" status is only possible on
 * SMP. It happens for example when a posix timer expired and the callback
 * queued a signal. Between dropping the lock which protects the posix timer
@@ -67,8 +69,11 @@ enum hrtimer_restart {
 * as otherwise the timer could be removed before the softirq code finishes the
 * the handling of the timer.
 *
- * The HRTIMER_STATE_ENQUEUED bit is always or'ed to the current state to
+ * The HRTIMER_STATE_ENQUEUED bit is always or'ed to the current state
- * preserve the HRTIMER_STATE_CALLBACK bit in the above scenario.
+ * to preserve the HRTIMER_STATE_CALLBACK in the above scenario. This
+ * also affects HRTIMER_STATE_MIGRATE where the preservation is not
+ * necessary. HRTIMER_STATE_MIGRATE is cleared after the timer is
+ * enqueued on the new cpu.
 *
 * All state transitions are protected by cpu_base->lock.
 */
@@ -148,7 +153,12 @@ struct hrtimer_clock_base {
 #endif
 };
-#define HRTIMER_MAX_CLOCK_BASES 2
+enum  hrtimer_base_type {
+        HRTIMER_BASE_REALTIME,
+        HRTIMER_BASE_MONOTONIC,
+        HRTIMER_BASE_BOOTTIME,
+        HRTIMER_MAX_CLOCK_BASES,
+};
 /*
 * struct hrtimer_cpu_base - the per cpu clock bases
@@ -308,6 +318,7 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer)
 extern ktime_t ktime_get(void);
 extern ktime_t ktime_get_real(void);
+extern ktime_t ktime_get_boottime(void);
 DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
@@ -370,8 +381,9 @@ extern int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp);
 extern ktime_t hrtimer_get_next_event(void);
 /*
- * A timer is active, when it is enqueued into the rbtree or the callback
+ * A timer is active, when it is enqueued into the rbtree or the
- * function is running.
+ * callback function is running or it's in the state of being migrated
+ * to another cpu.
 */
 static inline int hrtimer_active(const struct hrtimer *timer)
 {
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 903576df88dc..06a8d9c7de98 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -258,9 +258,7 @@ struct i2c_board_info {
        unsigned short  addr;
        void            *platform_data;
        struct dev_archdata     *archdata;
-#ifdef CONFIG_OF
        struct device_node *of_node;
-#endif
        int             irq;
 };
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 55e0d4253e49..59b72ca1c5d1 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -14,6 +14,8 @@
 #include <linux/smp.h>
 #include <linux/percpu.h>
 #include <linux/hrtimer.h>
+#include <linux/kref.h>
+#include <linux/workqueue.h>
 #include <asm/atomic.h>
 #include <asm/ptrace.h>
@@ -55,7 +57,8 @@
 *                Used by threaded interrupts which need to keep the
 *                irq line disabled until the threaded handler has been run.
 * IRQF_NO_SUSPEND - Do not disable this IRQ during suspend
- *
+ * IRQF_FORCE_RESUME - Force enable it on resume even if IRQF_NO_SUSPEND is set
+ * IRQF_NO_THREAD - Interrupt cannot be threaded
 */
 #define IRQF_DISABLED           0x00000020
 #define IRQF_SAMPLE_RANDOM      0x00000040
@@ -67,22 +70,10 @@
 #define IRQF_IRQPOLL            0x00001000
 #define IRQF_ONESHOT            0x00002000
 #define IRQF_NO_SUSPEND         0x00004000
+#define IRQF_FORCE_RESUME       0x00008000
+#define IRQF_NO_THREAD          0x00010000
-#define IRQF_TIMER              (__IRQF_TIMER | IRQF_NO_SUSPEND)
+#define IRQF_TIMER              (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD)
-/*
- * Bits used by threaded handlers:
- * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run
- * IRQTF_DIED      - handler thread died
- * IRQTF_WARNED    - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed
- * IRQTF_AFFINITY  - irq thread is requested to adjust affinity
- */
-enum {
-        IRQTF_RUNTHREAD,
-        IRQTF_DIED,
-        IRQTF_WARNED,
-        IRQTF_AFFINITY,
-};
 /*
 * These values can be returned by request_any_context_irq() and
@@ -110,6 +101,7 @@ typedef irqreturn_t (*irq_handler_t)(int, void *);
 * @thread_fn:  interupt handler function for threaded interrupts
 * @thread:     thread pointer for threaded interrupts
 * @thread_flags:       flags related to @thread
+ * @thread_mask:        bitmask for keeping track of @thread activity
 */
 struct irqaction {
        irq_handler_t handler;
@@ -120,6 +112,7 @@ struct irqaction {
        irq_handler_t thread_fn;
        struct task_struct *thread;
        unsigned long thread_flags;
+        unsigned long thread_mask;
        const char *name;
        struct proc_dir_entry *dir;
 } ____cacheline_internodealigned_in_smp;
@@ -240,6 +233,35 @@ extern int irq_can_set_affinity(unsigned int irq);
 extern int irq_select_affinity(unsigned int irq);
 extern int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m);
+/**
+ * struct irq_affinity_notify - context for notification of IRQ affinity changes
+ * @irq:                Interrupt to which notification applies
+ * @kref:               Reference count, for internal use
+ * @work:               Work item, for internal use
+ * @notify:             Function to be called on change.  This will be
+ *                      called in process context.
+ * @release:            Function to be called on release.  This will be
+ *                      called in process context.  Once registered, the
+ *                      structure must only be freed when this function is
+ *                      called or later.
+ */
+struct irq_affinity_notify {
+        unsigned int irq;
+        struct kref kref;
+        struct work_struct work;
+        void (*notify)(struct irq_affinity_notify *, const cpumask_t *mask);
+        void (*release)(struct kref *ref);
+};
+extern int
+irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify);
+static inline void irq_run_affinity_notifiers(void)
+{
+        flush_scheduled_work();
+}
 #else /* CONFIG_SMP */
 static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m)
@@ -255,7 +277,7 @@ static inline int irq_can_set_affinity(unsigned int irq)
 static inline int irq_select_affinity(unsigned int irq)  { return 0; }
 static inline int irq_set_affinity_hint(unsigned int irq,
-                                        const struct cpumask *m)
+                                        const struct cpumask *m)
 {
        return -EINVAL;
 }
@@ -314,16 +336,24 @@ static inline void enable_irq_lockdep_irqrestore(unsigned int irq, unsigned long
 }
 /* IRQ wakeup (PM) control: */
-extern int set_irq_wake(unsigned int irq, unsigned int on);
+extern int irq_set_irq_wake(unsigned int irq, unsigned int on);
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+/* Please do not use: Use the replacement functions instead */
+static inline int set_irq_wake(unsigned int irq, unsigned int on)
+{
+        return irq_set_irq_wake(irq, on);
+}
+#endif
 static inline int enable_irq_wake(unsigned int irq)
 {
-        return set_irq_wake(irq, 1);
+        return irq_set_irq_wake(irq, 1);
 }
 static inline int disable_irq_wake(unsigned int irq)
 {
-        return set_irq_wake(irq, 0);
+        return irq_set_irq_wake(irq, 0);
 }
 #else /* !CONFIG_GENERIC_HARDIRQS */
@@ -353,6 +383,13 @@ static inline int disable_irq_wake(unsigned int irq)
 }
 #endif /* CONFIG_GENERIC_HARDIRQS */
+#ifdef CONFIG_IRQ_FORCED_THREADING
+extern bool force_irqthreads;
+#else
+#define force_irqthreads        (0)
+#endif
 #ifndef __ARCH_SET_SOFTIRQ_PENDING
 #define set_softirq_pending(x) (local_softirq_pending() = (x))
 #define or_softirq_pending(x)  (local_softirq_pending() |= (x))
@@ -426,6 +463,13 @@ extern void raise_softirq(unsigned int nr);
 */
 DECLARE_PER_CPU(struct list_head [NR_SOFTIRQS], softirq_work_list);
+DECLARE_PER_CPU(struct task_struct *, ksoftirqd);
+static inline struct task_struct *this_cpu_ksoftirqd(void)
+{
+        return this_cpu_read(ksoftirqd);
+}
 /* Try to send a softirq to a remote cpu.  If this cannot be done, the
 * work will be queued to the local cpu.
 */
@@ -645,6 +689,7 @@ static inline void init_irq_proc(void)
 struct seq_file;
 int show_interrupts(struct seq_file *p, void *v);
+int arch_show_interrupts(struct seq_file *p, int prec);
 extern int early_irq_init(void);
 extern int arch_probe_nr_irqs(void);
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 80fcb53057bc..1d3577f30d45 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -29,61 +29,104 @@
 #include <asm/irq_regs.h>
 struct irq_desc;
+struct irq_data;
 typedef void (*irq_flow_handler_t)(unsigned int irq,
                                            struct irq_desc *desc);
+typedef void (*irq_preflow_handler_t)(struct irq_data *data);
 /*
 * IRQ line status.
 *
- * Bits 0-7 are reserved for the IRQF_* bits in linux/interrupt.h
+ * Bits 0-7 are the same as the IRQF_* bits in linux/interrupt.h
+ *
+ * IRQ_TYPE_NONE                - default, unspecified type
+ * IRQ_TYPE_EDGE_RISING         - rising edge triggered
+ * IRQ_TYPE_EDGE_FALLING        - falling edge triggered
+ * IRQ_TYPE_EDGE_BOTH           - rising and falling edge triggered
+ * IRQ_TYPE_LEVEL_HIGH          - high level triggered
+ * IRQ_TYPE_LEVEL_LOW           - low level triggered
+ * IRQ_TYPE_LEVEL_MASK          - Mask to filter out the level bits
+ * IRQ_TYPE_SENSE_MASK          - Mask for all the above bits
+ * IRQ_TYPE_PROBE               - Special flag for probing in progress
+ *
+ * Bits which can be modified via irq_set/clear/modify_status_flags()
+ * IRQ_LEVEL                    - Interrupt is level type. Will be also
+ *                                updated in the code when the above trigger
+ *                                bits are modified via set_irq_type()
+ * IRQ_PER_CPU                  - Mark an interrupt PER_CPU. Will protect
+ *                                it from affinity setting
+ * IRQ_NOPROBE                  - Interrupt cannot be probed by autoprobing
+ * IRQ_NOREQUEST                - Interrupt cannot be requested via
+ *                                request_irq()
+ * IRQ_NOAUTOEN                 - Interrupt is not automatically enabled in
+ *                                request/setup_irq()
+ * IRQ_NO_BALANCING             - Interrupt cannot be balanced (affinity set)
+ * IRQ_MOVE_PCNTXT              - Interrupt can be migrated from process context
+ * IRQ_NESTED_TRHEAD            - Interrupt nests into another thread
+ *
+ * Deprecated bits. They are kept updated as long as
+ * CONFIG_GENERIC_HARDIRQS_NO_COMPAT is not set. Will go away soon. These bits
+ * are internal state of the core code and if you really need to acces
+ * them then talk to the genirq maintainer instead of hacking
+ * something weird.
 *
- * IRQ types
 */
-#define IRQ_TYPE_NONE           0x00000000      /* Default, unspecified type */
+enum {
-#define IRQ_TYPE_EDGE_RISING    0x00000001      /* Edge rising type */
+        IRQ_TYPE_NONE           = 0x00000000,
-#define IRQ_TYPE_EDGE_FALLING   0x00000002      /* Edge falling type */
+        IRQ_TYPE_EDGE_RISING    = 0x00000001,
-#define IRQ_TYPE_EDGE_BOTH (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING)
+        IRQ_TYPE_EDGE_FALLING   = 0x00000002,
-#define IRQ_TYPE_LEVEL_HIGH     0x00000004      /* Level high type */
+        IRQ_TYPE_EDGE_BOTH      = (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING),
-#define IRQ_TYPE_LEVEL_LOW      0x00000008      /* Level low type */
+        IRQ_TYPE_LEVEL_HIGH     = 0x00000004,
-#define IRQ_TYPE_SENSE_MASK     0x0000000f      /* Mask of the above */
+        IRQ_TYPE_LEVEL_LOW      = 0x00000008,
-#define IRQ_TYPE_PROBE          0x00000010      /* Probing in progress */
+        IRQ_TYPE_LEVEL_MASK     = (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH),
+        IRQ_TYPE_SENSE_MASK     = 0x0000000f,
-/* Internal flags */
-#define IRQ_INPROGRESS          0x00000100      /* IRQ handler active - do not enter! */
+        IRQ_TYPE_PROBE          = 0x00000010,
-#define IRQ_DISABLED            0x00000200      /* IRQ disabled - do not enter! */
-#define IRQ_PENDING             0x00000400      /* IRQ pending - replay on enable */
+        IRQ_LEVEL               = (1 <<  8),
-#define IRQ_REPLAY              0x00000800      /* IRQ has been replayed but not acked yet */
+        IRQ_PER_CPU             = (1 <<  9),
-#define IRQ_AUTODETECT          0x00001000      /* IRQ is being autodetected */
+        IRQ_NOPROBE             = (1 << 10),
-#define IRQ_WAITING             0x00002000      /* IRQ not yet seen - for autodetection */
+        IRQ_NOREQUEST           = (1 << 11),
-#define IRQ_LEVEL               0x00004000      /* IRQ level triggered */
+        IRQ_NOAUTOEN            = (1 << 12),
-#define IRQ_MASKED              0x00008000      /* IRQ masked - shouldn't be seen again */
+        IRQ_NO_BALANCING        = (1 << 13),
-#define IRQ_PER_CPU             0x00010000      /* IRQ is per CPU */
+        IRQ_MOVE_PCNTXT         = (1 << 14),
-#define IRQ_NOPROBE             0x00020000      /* IRQ is not valid for probing */
+        IRQ_NESTED_THREAD       = (1 << 15),
-#define IRQ_NOREQUEST           0x00040000      /* IRQ cannot be requested */
-#define IRQ_NOAUTOEN            0x00080000      /* IRQ will not be enabled on request irq */
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
-#define IRQ_WAKEUP              0x00100000      /* IRQ triggers system wakeup */
+        IRQ_INPROGRESS          = (1 << 16),
-#define IRQ_MOVE_PENDING        0x00200000      /* need to re-target IRQ destination */
+        IRQ_REPLAY              = (1 << 17),
-#define IRQ_NO_BALANCING        0x00400000      /* IRQ is excluded from balancing */
+        IRQ_WAITING             = (1 << 18),
-#define IRQ_SPURIOUS_DISABLED   0x00800000      /* IRQ was disabled by the spurious trap */
+        IRQ_DISABLED            = (1 << 19),
-#define IRQ_MOVE_PCNTXT         0x01000000      /* IRQ migration from process context */
+        IRQ_PENDING             = (1 << 20),
-#define IRQ_AFFINITY_SET        0x02000000      /* IRQ affinity was set from userspace*/
+        IRQ_MASKED              = (1 << 21),
-#define IRQ_SUSPENDED           0x04000000      /* IRQ has gone through suspend sequence */
+        IRQ_MOVE_PENDING        = (1 << 22),
-#define IRQ_ONESHOT             0x08000000      /* IRQ is not unmasked after hardirq */
+        IRQ_AFFINITY_SET        = (1 << 23),
-#define IRQ_NESTED_THREAD       0x10000000      /* IRQ is nested into another, no own handler thread */
+        IRQ_WAKEUP              = (1 << 24),
+#endif
+};
 #define IRQF_MODIFY_MASK        \
        (IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \
         IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \
-         IRQ_PER_CPU)
+         IRQ_PER_CPU | IRQ_NESTED_THREAD)
-#ifdef CONFIG_IRQ_PER_CPU
+#define IRQ_NO_BALANCING_MASK   (IRQ_PER_CPU | IRQ_NO_BALANCING)
-# define CHECK_IRQ_PER_CPU(var) ((var) & IRQ_PER_CPU)
-# define IRQ_NO_BALANCING_MASK  (IRQ_PER_CPU | IRQ_NO_BALANCING)
+static inline __deprecated bool CHECK_IRQ_PER_CPU(unsigned int status)
-#else
+{
-# define CHECK_IRQ_PER_CPU(var) 0
+        return status & IRQ_PER_CPU;
-# define IRQ_NO_BALANCING_MASK  IRQ_NO_BALANCING
+}
-#endif
+/*
+ * Return value for chip->irq_set_affinity()
+ *
+ * IRQ_SET_MASK_OK      - OK, core updates irq_data.affinity
+ * IRQ_SET_MASK_NOCPY   - OK, chip did update irq_data.affinity
+ */
+enum {
+        IRQ_SET_MASK_OK = 0,
+        IRQ_SET_MASK_OK_NOCOPY,
+};
 struct msi_desc;
@@ -91,6 +134,8 @@ struct msi_desc;
 * struct irq_data - per irq and irq chip data passed down to chip functions
 * @irq:                interrupt number
 * @node:               node index useful for balancing
+ * @state_use_accessor: status information for irq chip functions.
+ *                      Use accessor functions to deal with it
 * @chip:               low level interrupt hardware access
 * @handler_data:       per-IRQ data for the irq_chip methods
 * @chip_data:          platform-specific per-chip private data for the chip
@@ -105,6 +150,7 @@ struct msi_desc;
 struct irq_data {
        unsigned int            irq;
        unsigned int            node;
+        unsigned int            state_use_accessors;
        struct irq_chip         *chip;
        void                    *handler_data;
        void                    *chip_data;
@@ -114,6 +160,80 @@ struct irq_data {
 #endif
 };
+/*
+ * Bit masks for irq_data.state
+ *
+ * IRQD_TRIGGER_MASK            - Mask for the trigger type bits
+ * IRQD_SETAFFINITY_PENDING     - Affinity setting is pending
+ * IRQD_NO_BALANCING            - Balancing disabled for this IRQ
+ * IRQD_PER_CPU                 - Interrupt is per cpu
+ * IRQD_AFFINITY_SET            - Interrupt affinity was set
+ * IRQD_LEVEL                   - Interrupt is level triggered
+ * IRQD_WAKEUP_STATE            - Interrupt is configured for wakeup
+ *                                from suspend
+ * IRDQ_MOVE_PCNTXT             - Interrupt can be moved in process
+ *                                context
+ */
+enum {
+        IRQD_TRIGGER_MASK               = 0xf,
+        IRQD_SETAFFINITY_PENDING        = (1 <<  8),
+        IRQD_NO_BALANCING               = (1 << 10),
+        IRQD_PER_CPU                    = (1 << 11),
+        IRQD_AFFINITY_SET               = (1 << 12),
+        IRQD_LEVEL                      = (1 << 13),
+        IRQD_WAKEUP_STATE               = (1 << 14),
+        IRQD_MOVE_PCNTXT                = (1 << 15),
+};
+static inline bool irqd_is_setaffinity_pending(struct irq_data *d)
+{
+        return d->state_use_accessors & IRQD_SETAFFINITY_PENDING;
+}
+static inline bool irqd_is_per_cpu(struct irq_data *d)
+{
+        return d->state_use_accessors & IRQD_PER_CPU;
+}
+static inline bool irqd_can_balance(struct irq_data *d)
+{
+        return !(d->state_use_accessors & (IRQD_PER_CPU | IRQD_NO_BALANCING));
+}
+static inline bool irqd_affinity_was_set(struct irq_data *d)
+{
+        return d->state_use_accessors & IRQD_AFFINITY_SET;
+}
+static inline u32 irqd_get_trigger_type(struct irq_data *d)
+{
+        return d->state_use_accessors & IRQD_TRIGGER_MASK;
+}
+/*
+ * Must only be called inside irq_chip.irq_set_type() functions.
+ */
+static inline void irqd_set_trigger_type(struct irq_data *d, u32 type)
+{
+        d->state_use_accessors &= ~IRQD_TRIGGER_MASK;
+        d->state_use_accessors |= type & IRQD_TRIGGER_MASK;
+}
+static inline bool irqd_is_level_type(struct irq_data *d)
+{
+        return d->state_use_accessors & IRQD_LEVEL;
+}
+static inline bool irqd_is_wakeup_set(struct irq_data *d)
+{
+        return d->state_use_accessors & IRQD_WAKEUP_STATE;
+}
+static inline bool irqd_can_move_in_process_context(struct irq_data *d)
+{
+        return d->state_use_accessors & IRQD_MOVE_PCNTXT;
+}
 /**
 * struct irq_chip - hardware interrupt chip descriptor
 *
@@ -150,6 +270,7 @@ struct irq_data {
 * @irq_set_wake:       enable/disable power-management wake-on of an IRQ
 * @irq_bus_lock:       function to lock access to slow bus (i2c) chips
 * @irq_bus_sync_unlock:function to sync and unlock slow bus (i2c) chips
+ * @flags:              chip specific flags
 *
 * @release:            release function solely used by UML
 */
@@ -196,12 +317,27 @@ struct irq_chip {
        void            (*irq_bus_lock)(struct irq_data *data);
        void            (*irq_bus_sync_unlock)(struct irq_data *data);
+        unsigned long   flags;
        /* Currently used only by UML, might disappear one day.*/
 #ifdef CONFIG_IRQ_RELEASE_METHOD
        void            (*release)(unsigned int irq, void *dev_id);
 #endif
 };
+/*
+ * irq_chip specific flags
+ *
+ * IRQCHIP_SET_TYPE_MASKED:     Mask before calling chip.irq_set_type()
+ * IRQCHIP_EOI_IF_HANDLED:      Only issue irq_eoi() when irq was handled
+ * IRQCHIP_MASK_ON_SUSPEND:     Mask non wake irqs in the suspend path
+ */
+enum {
+        IRQCHIP_SET_TYPE_MASKED         = (1 <<  0),
+        IRQCHIP_EOI_IF_HANDLED          = (1 <<  1),
+        IRQCHIP_MASK_ON_SUSPEND         = (1 <<  2),
+};
 /* This include will go away once we isolated irq_desc usage to core code */
 #include <linux/irqdesc.h>
@@ -218,7 +354,7 @@ struct irq_chip {
 # define ARCH_IRQ_INIT_FLAGS    0
 #endif
-#define IRQ_DEFAULT_INIT_FLAGS  (IRQ_DISABLED | ARCH_IRQ_INIT_FLAGS)
+#define IRQ_DEFAULT_INIT_FLAGS  ARCH_IRQ_INIT_FLAGS
 struct irqaction;
 extern int setup_irq(unsigned int irq, struct irqaction *new);
@@ -229,9 +365,13 @@ extern void remove_irq(unsigned int irq, struct irqaction *act);
 #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ)
 void move_native_irq(int irq);
 void move_masked_irq(int irq);
+void irq_move_irq(struct irq_data *data);
+void irq_move_masked_irq(struct irq_data *data);
 #else
 static inline void move_native_irq(int irq) { }
 static inline void move_masked_irq(int irq) { }
+static inline void irq_move_irq(struct irq_data *data) { }
+static inline void irq_move_masked_irq(struct irq_data *data) { }
 #endif
 extern int no_irq_affinity;
@@ -267,23 +407,23 @@ extern struct irq_chip no_irq_chip;
 extern struct irq_chip dummy_irq_chip;
 extern void
-set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip,
+irq_set_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
-                         irq_flow_handler_t handle);
-extern void
-set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
                              irq_flow_handler_t handle, const char *name);
+static inline void irq_set_chip_and_handler(unsigned int irq, struct irq_chip *chip,
+                                            irq_flow_handler_t handle)
+{
+        irq_set_chip_and_handler_name(irq, chip, handle, NULL);
+}
 extern void
-__set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
+__irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
                  const char *name);
-/*
- * Set a highlevel flow handler for a given IRQ:
- */
 static inline void
-set_irq_handler(unsigned int irq, irq_flow_handler_t handle)
+irq_set_handler(unsigned int irq, irq_flow_handler_t handle)
 {
-        __set_irq_handler(irq, handle, 0, NULL);
+        __irq_set_handler(irq, handle, 0, NULL);
 }
 /*
@@ -292,14 +432,11 @@ set_irq_handler(unsigned int irq, irq_flow_handler_t handle)
 *  IRQ_NOREQUEST and IRQ_NOPROBE)
 */
 static inline void
-set_irq_chained_handler(unsigned int irq,
+irq_set_chained_handler(unsigned int irq, irq_flow_handler_t handle)
-                        irq_flow_handler_t handle)
 {
-        __set_irq_handler(irq, handle, 1, NULL);
+        __irq_set_handler(irq, handle, 1, NULL);
 }
-extern void set_irq_nested_thread(unsigned int irq, int nest);
 void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set);
 static inline void irq_set_status_flags(unsigned int irq, unsigned long set)
@@ -312,16 +449,24 @@ static inline void irq_clear_status_flags(unsigned int irq, unsigned long clr)
        irq_modify_status(irq, clr, 0);
 }
-static inline void set_irq_noprobe(unsigned int irq)
+static inline void irq_set_noprobe(unsigned int irq)
 {
        irq_modify_status(irq, 0, IRQ_NOPROBE);
 }
-static inline void set_irq_probe(unsigned int irq)
+static inline void irq_set_probe(unsigned int irq)
 {
        irq_modify_status(irq, IRQ_NOPROBE, 0);
 }
+static inline void irq_set_nested_thread(unsigned int irq, bool nest)
+{
+        if (nest)
+                irq_set_status_flags(irq, IRQ_NESTED_THREAD);
+        else
+                irq_clear_status_flags(irq, IRQ_NESTED_THREAD);
+}
 /* Handle dynamic irq creation and destruction */
 extern unsigned int create_irq_nr(unsigned int irq_want, int node);
 extern int create_irq(void);
@@ -338,14 +483,14 @@ static inline void dynamic_irq_init(unsigned int irq)
 }
 /* Set/get chip/data for an IRQ: */
-extern int set_irq_chip(unsigned int irq, struct irq_chip *chip);
+extern int irq_set_chip(unsigned int irq, struct irq_chip *chip);
-extern int set_irq_data(unsigned int irq, void *data);
+extern int irq_set_handler_data(unsigned int irq, void *data);
-extern int set_irq_chip_data(unsigned int irq, void *data);
+extern int irq_set_chip_data(unsigned int irq, void *data);
-extern int set_irq_type(unsigned int irq, unsigned int type);
+extern int irq_set_irq_type(unsigned int irq, unsigned int type);
-extern int set_irq_msi(unsigned int irq, struct msi_desc *entry);
+extern int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry);
 extern struct irq_data *irq_get_irq_data(unsigned int irq);
-static inline struct irq_chip *get_irq_chip(unsigned int irq)
+static inline struct irq_chip *irq_get_chip(unsigned int irq)
 {
        struct irq_data *d = irq_get_irq_data(irq);
        return d ? d->chip : NULL;
@@ -356,7 +501,7 @@ static inline struct irq_chip *irq_data_get_irq_chip(struct irq_data *d)
        return d->chip;
 }
-static inline void *get_irq_chip_data(unsigned int irq)
+static inline void *irq_get_chip_data(unsigned int irq)
 {
        struct irq_data *d = irq_get_irq_data(irq);
        return d ? d->chip_data : NULL;
@@ -367,18 +512,18 @@ static inline void *irq_data_get_irq_chip_data(struct irq_data *d)
        return d->chip_data;
 }
-static inline void *get_irq_data(unsigned int irq)
+static inline void *irq_get_handler_data(unsigned int irq)
 {
        struct irq_data *d = irq_get_irq_data(irq);
        return d ? d->handler_data : NULL;
 }
-static inline void *irq_data_get_irq_data(struct irq_data *d)
+static inline void *irq_data_get_irq_handler_data(struct irq_data *d)
 {
        return d->handler_data;
 }
-static inline struct msi_desc *get_irq_msi(unsigned int irq)
+static inline struct msi_desc *irq_get_msi_desc(unsigned int irq)
 {
        struct irq_data *d = irq_get_irq_data(irq);
        return d ? d->msi_desc : NULL;
@@ -389,6 +534,89 @@ static inline struct msi_desc *irq_data_get_msi(struct irq_data *d)
        return d->msi_desc;
 }
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+/* Please do not use: Use the replacement functions instead */
+static inline int set_irq_chip(unsigned int irq, struct irq_chip *chip)
+{
+        return irq_set_chip(irq, chip);
+}
+static inline int set_irq_data(unsigned int irq, void *data)
+{
+        return irq_set_handler_data(irq, data);
+}
+static inline int set_irq_chip_data(unsigned int irq, void *data)
+{
+        return irq_set_chip_data(irq, data);
+}
+static inline int set_irq_type(unsigned int irq, unsigned int type)
+{
+        return irq_set_irq_type(irq, type);
+}
+static inline int set_irq_msi(unsigned int irq, struct msi_desc *entry)
+{
+        return irq_set_msi_desc(irq, entry);
+}
+static inline struct irq_chip *get_irq_chip(unsigned int irq)
+{
+        return irq_get_chip(irq);
+}
+static inline void *get_irq_chip_data(unsigned int irq)
+{
+        return irq_get_chip_data(irq);
+}
+static inline void *get_irq_data(unsigned int irq)
+{
+        return irq_get_handler_data(irq);
+}
+static inline void *irq_data_get_irq_data(struct irq_data *d)
+{
+        return irq_data_get_irq_handler_data(d);
+}
+static inline struct msi_desc *get_irq_msi(unsigned int irq)
+{
+        return irq_get_msi_desc(irq);
+}
+static inline void set_irq_noprobe(unsigned int irq)
+{
+        irq_set_noprobe(irq);
+}
+static inline void set_irq_probe(unsigned int irq)
+{
+        irq_set_probe(irq);
+}
+static inline void set_irq_nested_thread(unsigned int irq, int nest)
+{
+        irq_set_nested_thread(irq, nest);
+}
+static inline void
+set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
+                              irq_flow_handler_t handle, const char *name)
+{
+        irq_set_chip_and_handler_name(irq, chip, handle, name);
+}
+static inline void
+set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip,
+                         irq_flow_handler_t handle)
+{
+        irq_set_chip_and_handler(irq, chip, handle);
+}
+static inline void
+__set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
+                  const char *name)
+{
+        __irq_set_handler(irq, handle, is_chained, name);
+}
+static inline void set_irq_handler(unsigned int irq, irq_flow_handler_t handle)
+{
+        irq_set_handler(irq, handle);
+}
+static inline void
+set_irq_chained_handler(unsigned int irq, irq_flow_handler_t handle)
+{
+        irq_set_chained_handler(irq, handle);
+}
+#endif
 int irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node);
 void irq_free_descs(unsigned int irq, unsigned int cnt);
 int irq_reserve_irqs(unsigned int from, unsigned int cnt);
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index c1a95b7b58de..00218371518b 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -8,6 +8,7 @@
 * For now it's included from <linux/irq.h>
 */
+struct irq_affinity_notify;
 struct proc_dir_entry;
 struct timer_rand_state;
 /**
@@ -18,13 +19,16 @@ struct timer_rand_state;
 * @handle_irq:         highlevel irq-events handler [if NULL, __do_IRQ()]
 * @action:             the irq action chain
 * @status:             status information
+ * @core_internal_state__do_not_mess_with_it: core internal status information
 * @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
 * @last_unhandled:     aging timer for unhandled count
 * @irqs_unhandled:     stats field for spurious unhandled interrupts
 * @lock:               locking for SMP
+ * @affinity_notify:    context for notification of affinity changes
 * @pending_mask:       pending rebalanced interrupts
+ * @threads_oneshot:    bitfield to handle shared oneshot threads
 * @threads_active:     number of irqaction threads currently running
 * @wait_for_threads:   wait queue for sync_irq to wait for threaded handlers
 * @dir:                /proc/irq/ procfs entry
@@ -45,6 +49,7 @@ struct irq_desc {
                struct {
                        unsigned int            irq;
                        unsigned int            node;
+                        unsigned int            pad_do_not_even_think_about_it;
                        struct irq_chip         *chip;
                        void                    *handler_data;
                        void                    *chip_data;
@@ -59,9 +64,16 @@ struct irq_desc {
        struct timer_rand_state *timer_rand_state;
        unsigned int __percpu   *kstat_irqs;
        irq_flow_handler_t      handle_irq;
+#ifdef CONFIG_IRQ_PREFLOW_FASTEOI
+        irq_preflow_handler_t   preflow_handler;
+#endif
        struct irqaction        *action;        /* IRQ action list */
+#ifdef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+        unsigned int            status_use_accessors;
+#else
        unsigned int            status;         /* IRQ status */
+#endif
+        unsigned int            core_internal_state__do_not_mess_with_it;
        unsigned int            depth;          /* nested irq disables */
        unsigned int            wake_depth;     /* nested wake enables */
        unsigned int            irq_count;      /* For detecting broken IRQs */
@@ -70,10 +82,12 @@ struct irq_desc {
        raw_spinlock_t          lock;
 #ifdef CONFIG_SMP
        const struct cpumask    *affinity_hint;
+        struct irq_affinity_notify *affinity_notify;
 #ifdef CONFIG_GENERIC_PENDING_IRQ
        cpumask_var_t           pending_mask;
 #endif
 #endif
+        unsigned long           threads_oneshot;
        atomic_t                threads_active;
        wait_queue_head_t       wait_for_threads;
 #ifdef CONFIG_PROC_FS
@@ -95,10 +109,51 @@ static inline struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
 #ifdef CONFIG_GENERIC_HARDIRQS
-#define get_irq_desc_chip(desc)         ((desc)->irq_data.chip)
+static inline struct irq_data *irq_desc_get_irq_data(struct irq_desc *desc)
-#define get_irq_desc_chip_data(desc)    ((desc)->irq_data.chip_data)
+{
-#define get_irq_desc_data(desc)         ((desc)->irq_data.handler_data)
+        return &desc->irq_data;
-#define get_irq_desc_msi(desc)          ((desc)->irq_data.msi_desc)
+}
+static inline struct irq_chip *irq_desc_get_chip(struct irq_desc *desc)
+{
+        return desc->irq_data.chip;
+}
+static inline void *irq_desc_get_chip_data(struct irq_desc *desc)
+{
+        return desc->irq_data.chip_data;
+}
+static inline void *irq_desc_get_handler_data(struct irq_desc *desc)
+{
+        return desc->irq_data.handler_data;
+}
+static inline struct msi_desc *irq_desc_get_msi_desc(struct irq_desc *desc)
+{
+        return desc->irq_data.msi_desc;
+}
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
+static inline struct irq_chip *get_irq_desc_chip(struct irq_desc *desc)
+{
+        return irq_desc_get_chip(desc);
+}
+static inline void *get_irq_desc_data(struct irq_desc *desc)
+{
+        return irq_desc_get_handler_data(desc);
+}
+static inline void *get_irq_desc_chip_data(struct irq_desc *desc)
+{
+        return irq_desc_get_chip_data(desc);
+}
+static inline struct msi_desc *get_irq_desc_msi(struct irq_desc *desc)
+{
+        return irq_desc_get_msi_desc(desc);
+}
+#endif
 /*
 * Architectures call this to let the generic IRQ layer
@@ -123,6 +178,7 @@ static inline int irq_has_action(unsigned int irq)
        return desc->action != NULL;
 }
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_COMPAT
 static inline int irq_balancing_disabled(unsigned int irq)
 {
        struct irq_desc *desc;
@@ -130,6 +186,7 @@ static inline int irq_balancing_disabled(unsigned int irq)
        desc = irq_to_desc(irq);
        return desc->status & IRQ_NO_BALANCING_MASK;
 }
+#endif
 /* caller has locked the irq_desc and both params are valid */
 static inline void __set_irq_handler_unlocked(int irq,
@@ -140,6 +197,17 @@ static inline void __set_irq_handler_unlocked(int irq,
        desc = irq_to_desc(irq);
        desc->handle_irq = handler;
 }
+#ifdef CONFIG_IRQ_PREFLOW_FASTEOI
+static inline void
+__irq_set_preflow_handler(unsigned int irq, irq_preflow_handler_t handler)
+{
+        struct irq_desc *desc;
+        desc = irq_to_desc(irq);
+        desc->preflow_handler = handler;
+}
+#endif
 #endif
 #endif
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index 6811f4bfc6e7..922aa313c9f9 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -307,6 +307,7 @@ extern clock_t jiffies_to_clock_t(long x);
 extern unsigned long clock_t_to_jiffies(unsigned long x);
 extern u64 jiffies_64_to_clock_t(u64 x);
 extern u64 nsec_to_clock_t(u64 x);
+extern u64 nsecs_to_jiffies64(u64 n);
 extern unsigned long nsecs_to_jiffies(u64 n);
 #define TIMESTAMP_SIZE  30
diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index ce0775aa64c3..7ff16f7d3ed4 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -64,7 +64,7 @@ struct kthread_work {
 };
 #define KTHREAD_WORKER_INIT(worker)     {                               \
-        .lock = SPIN_LOCK_UNLOCKED,                                     \
+        .lock = __SPIN_LOCK_UNLOCKED((worker).lock),                    \
        .work_list = LIST_HEAD_INIT((worker).work_list),                \
        }
diff --git a/include/linux/mm.h b/include/linux/mm.h
index f6385fc17ad4..679300c050f5 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1309,8 +1309,6 @@ int add_from_early_node_map(struct range *range, int az,
                                   int nr_range, int nid);
 u64 __init find_memory_core_early(int nid, u64 size, u64 align,
                                        u64 goal, u64 limit);
-void *__alloc_memory_core_early(int nodeid, u64 size, u64 align,
-                                 u64 goal, u64 limit);
 typedef int (*work_fn_t)(unsigned long, unsigned long, void *);
 extern void work_with_active_regions(int nid, work_fn_t work_fn, void *data);
 extern void sparse_memory_present_with_active_regions(int nid);
diff --git a/include/linux/namei.h b/include/linux/namei.h
index f276d4fa01fc..9c8603872c36 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -19,7 +19,6 @@ struct nameidata {
        struct path     path;
        struct qstr     last;
        struct path     root;
-        struct file     *file;
        struct inode    *inode; /* path.dentry.d_inode */
        unsigned int    flags;
        unsigned        seq;
@@ -63,6 +62,10 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
 #define LOOKUP_EXCL             0x0400
 #define LOOKUP_RENAME_TARGET    0x0800
+#define LOOKUP_JUMPED           0x1000
+#define LOOKUP_ROOT             0x2000
+#define LOOKUP_EMPTY            0x4000
 extern int user_path_at(int, const char __user *, unsigned, struct path *);
 #define user_path(name, path) user_path_at(AT_FDCWD, name, LOOKUP_FOLLOW, path)
@@ -72,7 +75,7 @@ extern int user_path_at(int, const char __user *, unsigned, struct path *);
 extern int kern_path(const char *, unsigned, struct path *);
-extern int path_lookup(const char *, unsigned, struct nameidata *);
+extern int kern_path_parent(const char *, struct nameidata *);
 extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
                           const char *, unsigned int, struct nameidata *);
diff --git a/include/linux/of.h b/include/linux/of.h
index cad7cf0ab278..266db1d0baa9 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -23,8 +23,6 @@
 #include <asm/byteorder.h>
-#ifdef CONFIG_OF
 typedef u32 phandle;
 typedef u32 ihandle;
@@ -65,11 +63,18 @@ struct device_node {
 #endif
 };
+#ifdef CONFIG_OF
 /* Pointer for first entry in chain of all nodes. */
 extern struct device_node *allnodes;
 extern struct device_node *of_chosen;
 extern rwlock_t devtree_lock;
+static inline bool of_have_populated_dt(void)
+{
+        return allnodes != NULL;
+}
 static inline bool of_node_is_root(const struct device_node *node)
 {
        return node && (node->parent == NULL);
@@ -222,5 +227,12 @@ extern void of_attach_node(struct device_node *);
 extern void of_detach_node(struct device_node *);
 #endif
+#else
+static inline bool of_have_populated_dt(void)
+{
+        return false;
+}
 #endif /* CONFIG_OF */
 #endif /* _LINUX_OF_H */
diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h
new file mode 100644
index 000000000000..85a27b650d76
--- /dev/null
+++ b/include/linux/of_pci.h
@@ -0,0 +1,9 @@
+#ifndef __OF_PCI_H
+#define __OF_PCI_H
+#include <linux/pci.h>
+struct pci_dev;
+struct of_irq;
+int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq);
+#endif
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index dda5b0a3ff60..614615b8d42b 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -225,8 +225,14 @@ struct perf_event_attr {
        };
        __u32                   bp_type;
-        __u64                   bp_addr;
+        union {
-        __u64                   bp_len;
+                __u64           bp_addr;
+                __u64           config1; /* extension of config */
+        };
+        union {
+                __u64           bp_len;
+                __u64           config2; /* extension of config1 */
+        };
 };
 /*
@@ -464,6 +470,7 @@ enum perf_callchain_context {
 #define PERF_FLAG_FD_NO_GROUP   (1U << 0)
 #define PERF_FLAG_FD_OUTPUT     (1U << 1)
+#define PERF_FLAG_PID_CGROUP    (1U << 2) /* pid=cgroup id, per-cpu mode only */
 #ifdef __KERNEL__
 /*
@@ -471,6 +478,7 @@ enum perf_callchain_context {
 */
 #ifdef CONFIG_PERF_EVENTS
+# include <linux/cgroup.h>
 # include <asm/perf_event.h>
 # include <asm/local64.h>
 #endif
@@ -539,6 +547,9 @@ struct hw_perf_event {
                        unsigned long   event_base;
                        int             idx;
                        int             last_cpu;
+                        unsigned int    extra_reg;
+                        u64             extra_config;
+                        int             extra_alloc;
                };
                struct { /* software */
                        struct hrtimer  hrtimer;
@@ -716,6 +727,22 @@ struct swevent_hlist {
 #define PERF_ATTACH_GROUP       0x02
 #define PERF_ATTACH_TASK        0x04
+#ifdef CONFIG_CGROUP_PERF
+/*
+ * perf_cgroup_info keeps track of time_enabled for a cgroup.
+ * This is a per-cpu dynamically allocated data structure.
+ */
+struct perf_cgroup_info {
+        u64 time;
+        u64 timestamp;
+};
+struct perf_cgroup {
+        struct cgroup_subsys_state css;
+        struct perf_cgroup_info *info;  /* timing info, one per cpu */
+};
+#endif
 /**
 * struct perf_event - performance event kernel representation:
 */
@@ -832,6 +859,11 @@ struct perf_event {
        struct event_filter             *filter;
 #endif
+#ifdef CONFIG_CGROUP_PERF
+        struct perf_cgroup              *cgrp; /* cgroup event is attach to */
+        int                             cgrp_defer_enabled;
+#endif
 #endif /* CONFIG_PERF_EVENTS */
 };
@@ -886,6 +918,7 @@ struct perf_event_context {
        u64                             generation;
        int                             pin_count;
        struct rcu_head                 rcu_head;
+        int                             nr_cgroups; /* cgroup events present */
 };
 /*
@@ -905,6 +938,9 @@ struct perf_cpu_context {
        struct list_head                rotation_list;
        int                             jiffies_interval;
        struct pmu                      *active_pmu;
+#ifdef CONFIG_CGROUP_PERF
+        struct perf_cgroup              *cgrp;
+#endif
 };
 struct perf_output_handle {
@@ -1040,11 +1076,11 @@ have_event:
        __perf_sw_event(event_id, nr, nmi, regs, addr);
 }
-extern atomic_t perf_task_events;
+extern atomic_t perf_sched_events;
 static inline void perf_event_task_sched_in(struct task_struct *task)
 {
-        COND_STMT(&perf_task_events, __perf_event_task_sched_in(task));
+        COND_STMT(&perf_sched_events, __perf_event_task_sched_in(task));
 }
 static inline
@@ -1052,7 +1088,7 @@ void perf_event_task_sched_out(struct task_struct *task, struct task_struct *nex
 {
        perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
-        COND_STMT(&perf_task_events, __perf_event_task_sched_out(task, next));
+        COND_STMT(&perf_sched_events, __perf_event_task_sched_out(task, next));
 }
 extern void perf_event_mmap(struct vm_area_struct *vma);
@@ -1083,6 +1119,10 @@ extern int sysctl_perf_event_paranoid;
 extern int sysctl_perf_event_mlock;
 extern int sysctl_perf_event_sample_rate;
+extern int perf_proc_update_handler(struct ctl_table *table, int write,
+                void __user *buffer, size_t *lenp,
+                loff_t *ppos);
 static inline bool perf_paranoid_tracepoint_raw(void)
 {
        return sysctl_perf_event_paranoid > -1;
diff --git a/include/linux/plist.h b/include/linux/plist.h
index 7254eda078e5..c9b9f322c8d8 100644
--- a/include/linux/plist.h
+++ b/include/linux/plist.h
@@ -31,15 +31,17 @@
 *
 * Simple ASCII art explanation:
 *
- * |HEAD          |
+ * pl:prio_list (only for plist_node)
- * |              |
+ * nl:node_list
- * |prio_list.prev|<------------------------------------|
+ *   HEAD|             NODE(S)
- * |prio_list.next|<->|pl|<->|pl|<--------------->|pl|<-|
+ *       |
- * |10            |   |10|   |21|   |21|   |21|   |40|   (prio)
+ *       ||------------------------------------|
- * |              |   |  |   |  |   |  |   |  |   |  |
+ *       ||->|pl|<->|pl|<--------------->|pl|<-|
- * |              |   |  |   |  |   |  |   |  |   |  |
+ *       |   |10|   |21|   |21|   |21|   |40|   (prio)
- * |node_list.next|<->|nl|<->|nl|<->|nl|<->|nl|<->|nl|<-|
+ *       |   |  |   |  |   |  |   |  |   |  |
- * |node_list.prev|<------------------------------------|
+ *       |   |  |   |  |   |  |   |  |   |  |
+ * |->|nl|<->|nl|<->|nl|<->|nl|<->|nl|<->|nl|<-|
+ * |-------------------------------------------|
 *
 * The nodes on the prio_list list are sorted by priority to simplify
 * the insertion of new nodes. There are no nodes with duplicate
@@ -78,7 +80,6 @@
 #include <linux/spinlock_types.h>
 struct plist_head {
-        struct list_head prio_list;
        struct list_head node_list;
 #ifdef CONFIG_DEBUG_PI_LIST
        raw_spinlock_t *rawlock;
@@ -88,7 +89,8 @@ struct plist_head {
 struct plist_node {
        int                     prio;
-        struct plist_head       plist;
+        struct list_head        prio_list;
+        struct list_head        node_list;
 };
 #ifdef CONFIG_DEBUG_PI_LIST
@@ -100,7 +102,6 @@ struct plist_node {
 #endif
 #define _PLIST_HEAD_INIT(head)                          \
-        .prio_list = LIST_HEAD_INIT((head).prio_list),  \
        .node_list = LIST_HEAD_INIT((head).node_list)
 /**
@@ -133,7 +134,8 @@ struct plist_node {
 #define PLIST_NODE_INIT(node, __prio)                   \
 {                                                       \
        .prio  = (__prio),                              \
-        .plist = { _PLIST_HEAD_INIT((node).plist) },    \
+        .prio_list = LIST_HEAD_INIT((node).prio_list),  \
+        .node_list = LIST_HEAD_INIT((node).node_list),  \
 }
 /**
@@ -144,7 +146,6 @@ struct plist_node {
 static inline void
 plist_head_init(struct plist_head *head, spinlock_t *lock)
 {
-        INIT_LIST_HEAD(&head->prio_list);
        INIT_LIST_HEAD(&head->node_list);
 #ifdef CONFIG_DEBUG_PI_LIST
        head->spinlock = lock;
@@ -160,7 +161,6 @@ plist_head_init(struct plist_head *head, spinlock_t *lock)
 static inline void
 plist_head_init_raw(struct plist_head *head, raw_spinlock_t *lock)
 {
-        INIT_LIST_HEAD(&head->prio_list);
        INIT_LIST_HEAD(&head->node_list);
 #ifdef CONFIG_DEBUG_PI_LIST
        head->rawlock = lock;
@@ -176,7 +176,8 @@ plist_head_init_raw(struct plist_head *head, raw_spinlock_t *lock)
 static inline void plist_node_init(struct plist_node *node, int prio)
 {
        node->prio = prio;
-        plist_head_init(&node->plist, NULL);
+        INIT_LIST_HEAD(&node->prio_list);
+        INIT_LIST_HEAD(&node->node_list);
 }
 extern void plist_add(struct plist_node *node, struct plist_head *head);
@@ -188,7 +189,7 @@ extern void plist_del(struct plist_node *node, struct plist_head *head);
 * @head:       the head for your list
 */
 #define plist_for_each(pos, head)       \
-         list_for_each_entry(pos, &(head)->node_list, plist.node_list)
+         list_for_each_entry(pos, &(head)->node_list, node_list)
 /**
 * plist_for_each_safe - iterate safely over a plist of given type
@@ -199,7 +200,7 @@ extern void plist_del(struct plist_node *node, struct plist_head *head);
 * Iterate over a plist of given type, safe against removal of list entry.
 */
 #define plist_for_each_safe(pos, n, head)       \
-         list_for_each_entry_safe(pos, n, &(head)->node_list, plist.node_list)
+         list_for_each_entry_safe(pos, n, &(head)->node_list, node_list)
 /**
 * plist_for_each_entry - iterate over list of given type
@@ -208,7 +209,7 @@ extern void plist_del(struct plist_node *node, struct plist_head *head);
 * @mem:        the name of the list_struct within the struct
 */
 #define plist_for_each_entry(pos, head, mem)    \
-         list_for_each_entry(pos, &(head)->node_list, mem.plist.node_list)
+         list_for_each_entry(pos, &(head)->node_list, mem.node_list)
 /**
 * plist_for_each_entry_safe - iterate safely over list of given type
@@ -220,7 +221,7 @@ extern void plist_del(struct plist_node *node, struct plist_head *head);
 * Iterate over list of given type, safe against removal of list entry.
 */
 #define plist_for_each_entry_safe(pos, n, head, m)      \
-        list_for_each_entry_safe(pos, n, &(head)->node_list, m.plist.node_list)
+        list_for_each_entry_safe(pos, n, &(head)->node_list, m.node_list)
 /**
 * plist_head_empty - return !0 if a plist_head is empty
@@ -237,7 +238,7 @@ static inline int plist_head_empty(const struct plist_head *head)
 */
 static inline int plist_node_empty(const struct plist_node *node)
 {
-        return plist_head_empty(&node->plist);
+        return list_empty(&node->node_list);
 }
 /* All functions below assume the plist_head is not empty. */
@@ -285,7 +286,7 @@ static inline int plist_node_empty(const struct plist_node *node)
 static inline struct plist_node *plist_first(const struct plist_head *head)
 {
        return list_entry(head->node_list.next,
-                          struct plist_node, plist.node_list);
+                          struct plist_node, node_list);
 }
 /**
@@ -297,7 +298,7 @@ static inline struct plist_node *plist_first(const struct plist_head *head)
 static inline struct plist_node *plist_last(const struct plist_head *head)
 {
        return list_entry(head->node_list.prev,
-                          struct plist_node, plist.node_list);
+                          struct plist_node, node_list);
 }
 #endif
diff --git a/include/linux/posix-clock.h b/include/linux/posix-clock.h
new file mode 100644
index 000000000000..369e19d3750b
--- /dev/null
+++ b/include/linux/posix-clock.h
@@ -0,0 +1,150 @@
+/*
+ * posix-clock.h - support for dynamic clock devices
+ *
+ * Copyright (C) 2010 OMICRON electronics GmbH
+ *
+ *  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., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+#ifndef _LINUX_POSIX_CLOCK_H_
+#define _LINUX_POSIX_CLOCK_H_
+#include <linux/cdev.h>
+#include <linux/fs.h>
+#include <linux/poll.h>
+#include <linux/posix-timers.h>
+struct posix_clock;
+/**
+ * struct posix_clock_operations - functional interface to the clock
+ *
+ * Every posix clock is represented by a character device. Drivers may
+ * optionally offer extended capabilities by implementing the
+ * character device methods. The character device file operations are
+ * first handled by the clock device layer, then passed on to the
+ * driver by calling these functions.
+ *
+ * @owner:          The clock driver should set to THIS_MODULE
+ * @clock_adjtime:  Adjust the clock
+ * @clock_gettime:  Read the current time
+ * @clock_getres:   Get the clock resolution
+ * @clock_settime:  Set the current time value
+ * @timer_create:   Create a new timer
+ * @timer_delete:   Remove a previously created timer
+ * @timer_gettime:  Get remaining time and interval of a timer
+ * @timer_setttime: Set a timer's initial expiration and interval
+ * @fasync:         Optional character device fasync method
+ * @mmap:           Optional character device mmap method
+ * @open:           Optional character device open method
+ * @release:        Optional character device release method
+ * @ioctl:          Optional character device ioctl method
+ * @read:           Optional character device read method
+ * @poll:           Optional character device poll method
+ */
+struct posix_clock_operations {
+        struct module *owner;
+        int  (*clock_adjtime)(struct posix_clock *pc, struct timex *tx);
+        int  (*clock_gettime)(struct posix_clock *pc, struct timespec *ts);
+        int  (*clock_getres) (struct posix_clock *pc, struct timespec *ts);
+        int  (*clock_settime)(struct posix_clock *pc,
+                              const struct timespec *ts);
+        int  (*timer_create) (struct posix_clock *pc, struct k_itimer *kit);
+        int  (*timer_delete) (struct posix_clock *pc, struct k_itimer *kit);
+        void (*timer_gettime)(struct posix_clock *pc,
+                              struct k_itimer *kit, struct itimerspec *tsp);
+        int  (*timer_settime)(struct posix_clock *pc,
+                              struct k_itimer *kit, int flags,
+                              struct itimerspec *tsp, struct itimerspec *old);
+        /*
+         * Optional character device methods:
+         */
+        int     (*fasync)  (struct posix_clock *pc,
+                            int fd, struct file *file, int on);
+        long    (*ioctl)   (struct posix_clock *pc,
+                            unsigned int cmd, unsigned long arg);
+        int     (*mmap)    (struct posix_clock *pc,
+                            struct vm_area_struct *vma);
+        int     (*open)    (struct posix_clock *pc, fmode_t f_mode);
+        uint    (*poll)    (struct posix_clock *pc,
+                            struct file *file, poll_table *wait);
+        int     (*release) (struct posix_clock *pc);
+        ssize_t (*read)    (struct posix_clock *pc,
+                            uint flags, char __user *buf, size_t cnt);
+};
+/**
+ * struct posix_clock - represents a dynamic posix clock
+ *
+ * @ops:     Functional interface to the clock
+ * @cdev:    Character device instance for this clock
+ * @kref:    Reference count.
+ * @mutex:   Protects the 'zombie' field from concurrent access.
+ * @zombie:  If 'zombie' is true, then the hardware has disappeared.
+ * @release: A function to free the structure when the reference count reaches
+ *           zero. May be NULL if structure is statically allocated.
+ *
+ * Drivers should embed their struct posix_clock within a private
+ * structure, obtaining a reference to it during callbacks using
+ * container_of().
+ */
+struct posix_clock {
+        struct posix_clock_operations ops;
+        struct cdev cdev;
+        struct kref kref;
+        struct mutex mutex;
+        bool zombie;
+        void (*release)(struct posix_clock *clk);
+};
+/**
+ * posix_clock_register() - register a new clock
+ * @clk:   Pointer to the clock. Caller must provide 'ops' and 'release'
+ * @devid: Allocated device id
+ *
+ * A clock driver calls this function to register itself with the
+ * clock device subsystem. If 'clk' points to dynamically allocated
+ * memory, then the caller must provide a 'release' function to free
+ * that memory.
+ *
+ * Returns zero on success, non-zero otherwise.
+ */
+int posix_clock_register(struct posix_clock *clk, dev_t devid);
+/**
+ * posix_clock_unregister() - unregister a clock
+ * @clk: Clock instance previously registered via posix_clock_register()
+ *
+ * A clock driver calls this function to remove itself from the clock
+ * device subsystem. The posix_clock itself will remain (in an
+ * inactive state) until its reference count drops to zero, at which
+ * point it will be deallocated with its 'release' method.
+ */
+void posix_clock_unregister(struct posix_clock *clk);
+#endif
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 3e23844a6990..d51243ae0726 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -4,6 +4,7 @@
 #include <linux/spinlock.h>
 #include <linux/list.h>
 #include <linux/sched.h>
+#include <linux/timex.h>
 union cpu_time_count {
        cputime_t cpu;
@@ -17,10 +18,21 @@ struct cpu_timer_list {
        int firing;
 };
+/*
+ * Bit fields within a clockid:
+ *
+ * The most significant 29 bits hold either a pid or a file descriptor.
+ *
+ * Bit 2 indicates whether a cpu clock refers to a thread or a process.
+ *
+ * Bits 1 and 0 give the type: PROF=0, VIRT=1, SCHED=2, or FD=3.
+ *
+ * A clockid is invalid if bits 2, 1, and 0 are all set.
+ */
 #define CPUCLOCK_PID(clock)             ((pid_t) ~((clock) >> 3))
 #define CPUCLOCK_PERTHREAD(clock) \
        (((clock) & (clockid_t) CPUCLOCK_PERTHREAD_MASK) != 0)
-#define CPUCLOCK_PID_MASK       7
 #define CPUCLOCK_PERTHREAD_MASK 4
 #define CPUCLOCK_WHICH(clock)   ((clock) & (clockid_t) CPUCLOCK_CLOCK_MASK)
 #define CPUCLOCK_CLOCK_MASK     3
@@ -28,12 +40,17 @@ struct cpu_timer_list {
 #define CPUCLOCK_VIRT           1
 #define CPUCLOCK_SCHED          2
 #define CPUCLOCK_MAX            3
+#define CLOCKFD                 CPUCLOCK_MAX
+#define CLOCKFD_MASK            (CPUCLOCK_PERTHREAD_MASK|CPUCLOCK_CLOCK_MASK)
 #define MAKE_PROCESS_CPUCLOCK(pid, clock) \
        ((~(clockid_t) (pid) << 3) | (clockid_t) (clock))
 #define MAKE_THREAD_CPUCLOCK(tid, clock) \
        MAKE_PROCESS_CPUCLOCK((tid), (clock) | CPUCLOCK_PERTHREAD_MASK)
+#define FD_TO_CLOCKID(fd)       ((~(clockid_t) (fd) << 3) | CLOCKFD)
+#define CLOCKID_TO_FD(clk)      ((unsigned int) ~((clk) >> 3))
 /* POSIX.1b interval timer structure. */
 struct k_itimer {
        struct list_head list;          /* free/ allocate list */
@@ -67,10 +84,11 @@ struct k_itimer {
 };
 struct k_clock {
-        int res;                /* in nanoseconds */
        int (*clock_getres) (const clockid_t which_clock, struct timespec *tp);
-        int (*clock_set) (const clockid_t which_clock, struct timespec * tp);
+        int (*clock_set) (const clockid_t which_clock,
+                          const struct timespec *tp);
        int (*clock_get) (const clockid_t which_clock, struct timespec * tp);
+        int (*clock_adj) (const clockid_t which_clock, struct timex *tx);
        int (*timer_create) (struct k_itimer *timer);
        int (*nsleep) (const clockid_t which_clock, int flags,
                       struct timespec *, struct timespec __user *);
@@ -84,28 +102,14 @@ struct k_clock {
                           struct itimerspec * cur_setting);
 };
-void register_posix_clock(const clockid_t clock_id, struct k_clock *new_clock);
+extern struct k_clock clock_posix_cpu;
+extern struct k_clock clock_posix_dynamic;
-/* error handlers for timer_create, nanosleep and settime */
+void posix_timers_register_clock(const clockid_t clock_id, struct k_clock *new_clock);
-int do_posix_clock_nonanosleep(const clockid_t, int flags, struct timespec *,
-                               struct timespec __user *);
-int do_posix_clock_nosettime(const clockid_t, struct timespec *tp);
 /* function to call to trigger timer event */
 int posix_timer_event(struct k_itimer *timr, int si_private);
-int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *ts);
-int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *ts);
-int posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *ts);
-int posix_cpu_timer_create(struct k_itimer *timer);
-int posix_cpu_nsleep(const clockid_t which_clock, int flags,
-                     struct timespec *rqtp, struct timespec __user *rmtp);
-long posix_cpu_nsleep_restart(struct restart_block *restart_block);
-int posix_cpu_timer_set(struct k_itimer *timer, int flags,
-                        struct itimerspec *new, struct itimerspec *old);
-int posix_cpu_timer_del(struct k_itimer *timer);
-void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp);
 void posix_cpu_timer_schedule(struct k_itimer *timer);
 void run_posix_cpu_timers(struct task_struct *task);
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 8d3a2486544d..ab38ac80b0f9 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -100,6 +100,8 @@ void ring_buffer_free(struct ring_buffer *buffer);
 int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size);
+void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val);
 struct ring_buffer_event *ring_buffer_lock_reserve(struct ring_buffer *buffer,
                                                   unsigned long length);
 int ring_buffer_unlock_commit(struct ring_buffer *buffer,
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index 89c3e5182991..2ca7e8a78060 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -133,7 +133,6 @@ extern struct class *rtc_class;
 * The (current) exceptions are mostly filesystem hooks:
 *   - the proc() hook for procfs
 *   - non-ioctl() chardev hooks:  open(), release(), read_callback()
- *   - periodic irq calls:  irq_set_state(), irq_set_freq()
 *
 * REVISIT those periodic irq calls *do* have ops_lock when they're
 * issued through ioctl() ...
@@ -148,11 +147,8 @@ struct rtc_class_ops {
        int (*set_alarm)(struct device *, struct rtc_wkalrm *);
        int (*proc)(struct device *, struct seq_file *);
        int (*set_mmss)(struct device *, unsigned long secs);
-        int (*irq_set_state)(struct device *, int enabled);
-        int (*irq_set_freq)(struct device *, int freq);
        int (*read_callback)(struct device *, int data);
        int (*alarm_irq_enable)(struct device *, unsigned int enabled);
-        int (*update_irq_enable)(struct device *, unsigned int enabled);
 };
 #define RTC_DEVICE_NAME_SIZE 20
@@ -227,6 +223,7 @@ extern void rtc_device_unregister(struct rtc_device *rtc);
 extern int rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm);
 extern int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm);
 extern int rtc_set_mmss(struct rtc_device *rtc, unsigned long secs);
+int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm);
 extern int rtc_read_alarm(struct rtc_device *rtc,
                        struct rtc_wkalrm *alrm);
 extern int rtc_set_alarm(struct rtc_device *rtc,
diff --git a/include/linux/rwlock_types.h b/include/linux/rwlock_types.h
index bd31808c7d8e..cc0072e93e36 100644
--- a/include/linux/rwlock_types.h
+++ b/include/linux/rwlock_types.h
@@ -43,14 +43,6 @@ typedef struct {
                                RW_DEP_MAP_INIT(lockname) }
 #endif
-/*
- * RW_LOCK_UNLOCKED defeat lockdep state tracking and is hence
- * deprecated.
- *
- * Please use DEFINE_RWLOCK() or __RW_LOCK_UNLOCKED() as appropriate.
- */
-#define RW_LOCK_UNLOCKED        __RW_LOCK_UNLOCKED(old_style_rw_init)
 #define DEFINE_RWLOCK(x)        rwlock_t x = __RW_LOCK_UNLOCKED(x)
 #endif /* __LINUX_RWLOCK_TYPES_H */
diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h
index bdfcc2527970..34701241b673 100644
--- a/include/linux/rwsem-spinlock.h
+++ b/include/linux/rwsem-spinlock.h
@@ -12,15 +12,7 @@
 #error "please don't include linux/rwsem-spinlock.h directly, use linux/rwsem.h instead"
 #endif
-#include <linux/spinlock.h>
-#include <linux/list.h>
 #ifdef __KERNEL__
-#include <linux/types.h>
-struct rwsem_waiter;
 /*
 * the rw-semaphore definition
 * - if activity is 0 then there are no active readers or writers
@@ -37,28 +29,7 @@ struct rw_semaphore {
 #endif
 };
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#define RWSEM_UNLOCKED_VALUE            0x00000000
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-#define __RWSEM_INITIALIZER(name) \
-{ 0, __SPIN_LOCK_UNLOCKED(name.wait_lock), LIST_HEAD_INIT((name).wait_list) \
-  __RWSEM_DEP_MAP_INIT(name) }
-#define DECLARE_RWSEM(name) \
-        struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
-                         struct lock_class_key *key);
-#define init_rwsem(sem)                                         \
-do {                                                            \
-        static struct lock_class_key __key;                     \
-                                                                \
-        __init_rwsem((sem), #sem, &__key);                      \
-} while (0)
 extern void __down_read(struct rw_semaphore *sem);
 extern int __down_read_trylock(struct rw_semaphore *sem);
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index efd348fe8ca7..a8afe9cd000c 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -11,6 +11,9 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
 #include <asm/system.h>
 #include <asm/atomic.h>
@@ -19,9 +22,57 @@ struct rw_semaphore;
 #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK
 #include <linux/rwsem-spinlock.h> /* use a generic implementation */
 #else
-#include <asm/rwsem.h> /* use an arch-specific implementation */
+/* All arch specific implementations share the same struct */
+struct rw_semaphore {
+        long                    count;
+        spinlock_t              wait_lock;
+        struct list_head        wait_list;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+        struct lockdep_map      dep_map;
+#endif
+};
+extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *);
+extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
+/* Include the arch specific part */
+#include <asm/rwsem.h>
+/* In all implementations count != 0 means locked */
+static inline int rwsem_is_locked(struct rw_semaphore *sem)
+{
+        return sem->count != 0;
+}
+#endif
+/* Common initializer macros and functions */
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
+#else
+# define __RWSEM_DEP_MAP_INIT(lockname)
 #endif
+#define __RWSEM_INITIALIZER(name) \
+        { RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED(name.wait_lock),   \
+          LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) }
+#define DECLARE_RWSEM(name) \
+        struct rw_semaphore name = __RWSEM_INITIALIZER(name)
+extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
+                         struct lock_class_key *key);
+#define init_rwsem(sem)                                         \
+do {                                                            \
+        static struct lock_class_key __key;                     \
+                                                                \
+        __init_rwsem((sem), #sem, &__key);                      \
+} while (0)
 /*
 * lock for reading
 */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 777d8a5ed06b..c15936fe998b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1058,6 +1058,7 @@ struct sched_class {
        void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
        void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
        void (*yield_task) (struct rq *rq);
+        bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt);
        void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
@@ -1084,12 +1085,10 @@ struct sched_class {
        void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
        void (*task_fork) (struct task_struct *p);
-        void (*switched_from) (struct rq *this_rq, struct task_struct *task,
+        void (*switched_from) (struct rq *this_rq, struct task_struct *task);
-                               int running);
+        void (*switched_to) (struct rq *this_rq, struct task_struct *task);
-        void (*switched_to) (struct rq *this_rq, struct task_struct *task,
-                             int running);
        void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
-                             int oldprio, int running);
+                             int oldprio);
        unsigned int (*get_rr_interval) (struct rq *rq,
                                         struct task_struct *task);
@@ -1715,7 +1714,6 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 /*
 * Per process flags
 */
-#define PF_KSOFTIRQD    0x00000001      /* I am ksoftirqd */
 #define PF_STARTING     0x00000002      /* being created */
 #define PF_EXITING      0x00000004      /* getting shut down */
 #define PF_EXITPIDONE   0x00000008      /* pi exit done on shut down */
@@ -1945,8 +1943,6 @@ int sched_rt_handler(struct ctl_table *table, int write,
                void __user *buffer, size_t *lenp,
                loff_t *ppos);
-extern unsigned int sysctl_sched_compat_yield;
 #ifdef CONFIG_SCHED_AUTOGROUP
 extern unsigned int sysctl_sched_autogroup_enabled;
@@ -1977,6 +1973,7 @@ static inline int rt_mutex_getprio(struct task_struct *p)
 # define rt_mutex_adjust_pi(p)          do { } while (0)
 #endif
+extern bool yield_to(struct task_struct *p, bool preempt);
 extern void set_user_nice(struct task_struct *p, long nice);
 extern int task_prio(const struct task_struct *p);
 extern int task_nice(const struct task_struct *p);
@@ -2049,7 +2046,7 @@ extern void release_uids(struct user_namespace *ns);
 #include <asm/current.h>
-extern void do_timer(unsigned long ticks);
+extern void xtime_update(unsigned long ticks);
 extern int wake_up_state(struct task_struct *tsk, unsigned int state);
 extern int wake_up_process(struct task_struct *tsk);
@@ -2578,13 +2575,6 @@ static inline void inc_syscw(struct task_struct *tsk)
 #define TASK_SIZE_OF(tsk)       TASK_SIZE
 #endif
-/*
- * Call the function if the target task is executing on a CPU right now:
- */
-extern void task_oncpu_function_call(struct task_struct *p,
-                                     void (*func) (void *info), void *info);
 #ifdef CONFIG_MM_OWNER
 extern void mm_update_next_owner(struct mm_struct *mm);
 extern void mm_init_owner(struct mm_struct *mm, struct task_struct *p);
diff --git a/include/linux/security.h b/include/linux/security.h
index b2b7f9749f5e..debbd97db7ab 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -53,7 +53,7 @@ struct audit_krule;
 */
 extern int cap_capable(struct task_struct *tsk, const struct cred *cred,
                       int cap, int audit);
-extern int cap_settime(struct timespec *ts, struct timezone *tz);
+extern int cap_settime(const struct timespec *ts, const struct timezone *tz);
 extern int cap_ptrace_access_check(struct task_struct *child, unsigned int mode);
 extern int cap_ptrace_traceme(struct task_struct *parent);
 extern int cap_capget(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted);
@@ -1387,7 +1387,7 @@ struct security_operations {
        int (*quotactl) (int cmds, int type, int id, struct super_block *sb);
        int (*quota_on) (struct dentry *dentry);
        int (*syslog) (int type);
-        int (*settime) (struct timespec *ts, struct timezone *tz);
+        int (*settime) (const struct timespec *ts, const struct timezone *tz);
        int (*vm_enough_memory) (struct mm_struct *mm, long pages);
        int (*bprm_set_creds) (struct linux_binprm *bprm);
@@ -1669,7 +1669,7 @@ int security_sysctl(struct ctl_table *table, int op);
 int security_quotactl(int cmds, int type, int id, struct super_block *sb);
 int security_quota_on(struct dentry *dentry);
 int security_syslog(int type);
-int security_settime(struct timespec *ts, struct timezone *tz);
+int security_settime(const struct timespec *ts, const struct timezone *tz);
 int security_vm_enough_memory(long pages);
 int security_vm_enough_memory_mm(struct mm_struct *mm, long pages);
 int security_vm_enough_memory_kern(long pages);
@@ -1904,7 +1904,8 @@ static inline int security_syslog(int type)
        return 0;
 }
-static inline int security_settime(struct timespec *ts, struct timezone *tz)
+static inline int security_settime(const struct timespec *ts,
+                                   const struct timezone *tz)
 {
        return cap_settime(ts, tz);
 }
diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h
index 851b7783720d..73548eb13a5d 100644
--- a/include/linux/spinlock_types.h
+++ b/include/linux/spinlock_types.h
@@ -81,14 +81,6 @@ typedef struct spinlock {
 #define __SPIN_LOCK_UNLOCKED(lockname) \
        (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname)
-/*
- * SPIN_LOCK_UNLOCKED defeats lockdep state tracking and is hence
- * deprecated.
- * Please use DEFINE_SPINLOCK() or __SPIN_LOCK_UNLOCKED() as
- * appropriate.
- */
-#define SPIN_LOCK_UNLOCKED      __SPIN_LOCK_UNLOCKED(old_style_spin_init)
 #define DEFINE_SPINLOCK(x)      spinlock_t x = __SPIN_LOCK_UNLOCKED(x)
 #include <linux/rwlock_types.h>
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 98664db1be47..1f5c18e6f4f1 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -62,6 +62,7 @@ struct robust_list_head;
 struct getcpu_cache;
 struct old_linux_dirent;
 struct perf_event_attr;
+struct file_handle;
 #include <linux/types.h>
 #include <linux/aio_abi.h>
@@ -132,11 +133,11 @@ extern struct trace_event_functions exit_syscall_print_funcs;
                .class                  = &event_class_syscall_enter,   \
                .event.funcs            = &enter_syscall_print_funcs,   \
                .data                   = (void *)&__syscall_meta_##sname,\
+                .flags                  = TRACE_EVENT_FL_CAP_ANY,       \
        };                                                              \
        static struct ftrace_event_call __used                          \
          __attribute__((section("_ftrace_events")))                    \
-         *__event_enter_##sname = &event_enter_##sname;                 \
+         *__event_enter_##sname = &event_enter_##sname;
-        __TRACE_EVENT_FLAGS(enter_##sname, TRACE_EVENT_FL_CAP_ANY)
 #define SYSCALL_TRACE_EXIT_EVENT(sname)                                 \
        static struct syscall_metadata __syscall_meta_##sname;          \
@@ -146,11 +147,11 @@ extern struct trace_event_functions exit_syscall_print_funcs;
                .class                  = &event_class_syscall_exit,    \
                .event.funcs            = &exit_syscall_print_funcs,    \
                .data                   = (void *)&__syscall_meta_##sname,\
+                .flags                  = TRACE_EVENT_FL_CAP_ANY,       \
        };                                                              \
        static struct ftrace_event_call __used                          \
          __attribute__((section("_ftrace_events")))                    \
-        *__event_exit_##sname = &event_exit_##sname;                    \
+        *__event_exit_##sname = &event_exit_##sname;
-        __TRACE_EVENT_FLAGS(exit_##sname, TRACE_EVENT_FL_CAP_ANY)
 #define SYSCALL_METADATA(sname, nb)                             \
        SYSCALL_TRACE_ENTER_EVENT(sname);                       \
@@ -158,6 +159,7 @@ extern struct trace_event_functions exit_syscall_print_funcs;
        static struct syscall_metadata __used                   \
          __syscall_meta_##sname = {                            \
                .name           = "sys"#sname,                  \
+                .syscall_nr     = -1,   /* Filled in at boot */ \
                .nb_args        = nb,                           \
                .types          = types_##sname,                \
                .args           = args_##sname,                 \
@@ -175,6 +177,7 @@ extern struct trace_event_functions exit_syscall_print_funcs;
        static struct syscall_metadata __used                   \
          __syscall_meta__##sname = {                           \
                .name           = "sys_"#sname,                 \
+                .syscall_nr     = -1,   /* Filled in at boot */ \
                .nb_args        = 0,                            \
                .enter_event    = &event_enter__##sname,        \
                .exit_event     = &event_exit__##sname,         \
@@ -313,6 +316,8 @@ asmlinkage long sys_clock_settime(clockid_t which_clock,
                                const struct timespec __user *tp);
 asmlinkage long sys_clock_gettime(clockid_t which_clock,
                                struct timespec __user *tp);
+asmlinkage long sys_clock_adjtime(clockid_t which_clock,
+                                struct timex __user *tx);
 asmlinkage long sys_clock_getres(clockid_t which_clock,
                                struct timespec __user *tp);
 asmlinkage long sys_clock_nanosleep(clockid_t which_clock, int flags,
@@ -832,5 +837,10 @@ asmlinkage long sys_mmap_pgoff(unsigned long addr, unsigned long len,
                        unsigned long prot, unsigned long flags,
                        unsigned long fd, unsigned long pgoff);
 asmlinkage long sys_old_mmap(struct mmap_arg_struct __user *arg);
+asmlinkage long sys_name_to_handle_at(int dfd, const char __user *name,
+                                      struct file_handle __user *handle,
+                                      int __user *mnt_id, int flag);
+asmlinkage long sys_open_by_handle_at(int mountdirfd,
+                                      struct file_handle __user *handle,
+                                      int flags);
 #endif
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index c90696544176..20fc303947d3 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -18,9 +18,6 @@ struct compat_timespec;
 struct restart_block {
        long (*fn)(struct restart_block *);
        union {
-                struct {
-                        unsigned long arg0, arg1, arg2, arg3;
-                };
                /* For futex_wait and futex_wait_requeue_pi */
                struct {
                        u32 __user *uaddr;
diff --git a/include/linux/time.h b/include/linux/time.h
index 1e6d3b59238d..454a26205787 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -113,8 +113,6 @@ static inline struct timespec timespec_sub(struct timespec lhs,
 #define timespec_valid(ts) \
        (((ts)->tv_sec >= 0) && (((unsigned long) (ts)->tv_nsec) < NSEC_PER_SEC))
-extern seqlock_t xtime_lock;
 extern void read_persistent_clock(struct timespec *ts);
 extern void read_boot_clock(struct timespec *ts);
 extern int update_persistent_clock(struct timespec now);
@@ -125,8 +123,9 @@ extern int timekeeping_suspended;
 unsigned long get_seconds(void);
 struct timespec current_kernel_time(void);
 struct timespec __current_kernel_time(void); /* does not take xtime_lock */
-struct timespec __get_wall_to_monotonic(void); /* does not take xtime_lock */
 struct timespec get_monotonic_coarse(void);
+void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
+                                struct timespec *wtom, struct timespec *sleep);
 #define CURRENT_TIME            (current_kernel_time())
 #define CURRENT_TIME_SEC        ((struct timespec) { get_seconds(), 0 })
@@ -147,8 +146,9 @@ static inline u32 arch_gettimeoffset(void) { return 0; }
 #endif
 extern void do_gettimeofday(struct timeval *tv);
-extern int do_settimeofday(struct timespec *tv);
+extern int do_settimeofday(const struct timespec *tv);
-extern int do_sys_settimeofday(struct timespec *tv, struct timezone *tz);
+extern int do_sys_settimeofday(const struct timespec *tv,
+                               const struct timezone *tz);
 #define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts)
 extern long do_utimes(int dfd, const char __user *filename, struct timespec *times, int flags);
 struct itimerval;
@@ -162,12 +162,13 @@ extern void getnstime_raw_and_real(struct timespec *ts_raw,
                struct timespec *ts_real);
 extern void getboottime(struct timespec *ts);
 extern void monotonic_to_bootbased(struct timespec *ts);
+extern void get_monotonic_boottime(struct timespec *ts);
 extern struct timespec timespec_trunc(struct timespec t, unsigned gran);
 extern int timekeeping_valid_for_hres(void);
 extern u64 timekeeping_max_deferment(void);
-extern void update_wall_time(void);
 extern void timekeeping_leap_insert(int leapsecond);
+extern int timekeeping_inject_offset(struct timespec *ts);
 struct tms;
 extern void do_sys_times(struct tms *);
@@ -292,6 +293,7 @@ struct itimerval {
 #define CLOCK_MONOTONIC_RAW             4
 #define CLOCK_REALTIME_COARSE           5
 #define CLOCK_MONOTONIC_COARSE          6
+#define CLOCK_BOOTTIME                  7
 /*
 * The IDs of various hardware clocks:
diff --git a/include/linux/timex.h b/include/linux/timex.h
index d23999f9499d..aa60fe7b6ed6 100644
--- a/include/linux/timex.h
+++ b/include/linux/timex.h
@@ -73,7 +73,7 @@ struct timex {
        long tolerance;         /* clock frequency tolerance (ppm)
                                 * (read only)
                                 */
-        struct timeval time;    /* (read only) */
+        struct timeval time;    /* (read only, except for ADJ_SETOFFSET) */
        long tick;              /* (modified) usecs between clock ticks */
        long ppsfreq;           /* pps frequency (scaled ppm) (ro) */
@@ -102,6 +102,7 @@ struct timex {
 #define ADJ_STATUS              0x0010  /* clock status */
 #define ADJ_TIMECONST           0x0020  /* pll time constant */
 #define ADJ_TAI                 0x0080  /* set TAI offset */
+#define ADJ_SETOFFSET           0x0100  /* add 'time' to current time */
 #define ADJ_MICRO               0x1000  /* select microsecond resolution */
 #define ADJ_NANO                0x2000  /* select nanosecond resolution */
 #define ADJ_TICK                0x4000  /* tick value */
diff --git a/include/trace/events/mce.h b/include/trace/events/mce.h
index 7eee77895cb3..4cbbcef6baa8 100644
--- a/include/trace/events/mce.h
+++ b/include/trace/events/mce.h
@@ -17,36 +17,36 @@ TRACE_EVENT(mce_record,
        TP_STRUCT__entry(
                __field(        u64,            mcgcap          )
                __field(        u64,            mcgstatus       )
-                __field(        u8,             bank            )
                __field(        u64,            status          )
                __field(        u64,            addr            )
                __field(        u64,            misc            )
                __field(        u64,            ip              )
-                __field(        u8,             cs              )
                __field(        u64,            tsc             )
                __field(        u64,            walltime        )
                __field(        u32,            cpu             )
                __field(        u32,            cpuid           )
                __field(        u32,            apicid          )
                __field(        u32,            socketid        )
+                __field(        u8,             cs              )
+                __field(        u8,             bank            )
                __field(        u8,             cpuvendor       )
        ),
        TP_fast_assign(
                __entry->mcgcap         = m->mcgcap;
                __entry->mcgstatus      = m->mcgstatus;
-                __entry->bank           = m->bank;
                __entry->status         = m->status;
                __entry->addr           = m->addr;
                __entry->misc           = m->misc;
                __entry->ip             = m->ip;
-                __entry->cs             = m->cs;
                __entry->tsc            = m->tsc;
                __entry->walltime       = m->time;
                __entry->cpu            = m->extcpu;
                __entry->cpuid          = m->cpuid;
                __entry->apicid         = m->apicid;
                __entry->socketid       = m->socketid;
+                __entry->cs             = m->cs;
+                __entry->bank           = m->bank;
                __entry->cpuvendor      = m->cpuvendor;
        ),
diff --git a/include/trace/events/module.h b/include/trace/events/module.h
index c6bae36547e5..21a546d27c0c 100644
--- a/include/trace/events/module.h
+++ b/include/trace/events/module.h
@@ -108,14 +108,14 @@ TRACE_EVENT(module_request,
        TP_ARGS(name, wait, ip),
        TP_STRUCT__entry(
-                __field(        bool,           wait            )
                __field(        unsigned long,  ip              )
+                __field(        bool,           wait            )
                __string(       name,           name            )
        ),
        TP_fast_assign(
-                __entry->wait   = wait;
                __entry->ip     = ip;
+                __entry->wait   = wait;
                __assign_str(name, name);
        ),
@@ -129,4 +129,3 @@ TRACE_EVENT(module_request,
 /* This part must be outside protection */
 #include <trace/define_trace.h>
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index f10293c41b1e..0c68ae22da22 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -19,14 +19,14 @@ TRACE_EVENT(kfree_skb,
        TP_STRUCT__entry(
                __field(        void *,         skbaddr         )
-                __field(        unsigned short, protocol        )
                __field(        void *,         location        )
+                __field(        unsigned short, protocol        )
        ),
        TP_fast_assign(
                __entry->skbaddr = skb;
-                __entry->protocol = ntohs(skb->protocol);
                __entry->location = location;
+                __entry->protocol = ntohs(skb->protocol);
        ),
        TP_printk("skbaddr=%p protocol=%u location=%p",
diff --git a/include/xen/events.h b/include/xen/events.h
index 00f53ddcc062..962da2ced5b4 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -75,11 +75,9 @@ int xen_allocate_pirq(unsigned gsi, int shareable, char *name);
 int xen_map_pirq_gsi(unsigned pirq, unsigned gsi, int shareable, char *name);
 #ifdef CONFIG_PCI_MSI
-/* Allocate an irq and a pirq to be used with MSIs. */
+int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc);
-#define XEN_ALLOC_PIRQ (1 << 0)
+int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
-#define XEN_ALLOC_IRQ  (1 << 1)
+                             int pirq, int vector, const char *name);
-void xen_allocate_pirq_msi(char *name, int *irq, int *pirq, int alloc_mask);
-int xen_create_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int type);
 #endif
 /* De-allocates the above mentioned physical interrupt. */
diff --git a/include/xen/interface/io/blkif.h b/include/xen/interface/io/blkif.h
index c2d1fa4dc1ee..61e523af3c46 100644
--- a/include/xen/interface/io/blkif.h
+++ b/include/xen/interface/io/blkif.h
@@ -51,11 +51,7 @@ typedef uint64_t blkif_sector_t;
 */
 #define BLKIF_MAX_SEGMENTS_PER_REQUEST 11
-struct blkif_request {
+struct blkif_request_rw {
-        uint8_t        operation;    /* BLKIF_OP_???                         */
-        uint8_t        nr_segments;  /* number of segments                   */
-        blkif_vdev_t   handle;       /* only for read/write requests         */
-        uint64_t       id;           /* private guest value, echoed in resp  */
        blkif_sector_t sector_number;/* start sector idx on disk (r/w only)  */
        struct blkif_request_segment {
                grant_ref_t gref;        /* reference to I/O buffer frame        */
@@ -65,6 +61,16 @@ struct blkif_request {
        } seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 };
+struct blkif_request {
+        uint8_t        operation;    /* BLKIF_OP_???                         */
+        uint8_t        nr_segments;  /* number of segments                   */
+        blkif_vdev_t   handle;       /* only for read/write requests         */
+        uint64_t       id;           /* private guest value, echoed in resp  */
+        union {
+                struct blkif_request_rw rw;
+        } u;
+};
 struct blkif_response {
        uint64_t        id;              /* copied from request */
        uint8_t         operation;       /* copied from request */
@@ -91,4 +97,25 @@ DEFINE_RING_TYPES(blkif, struct blkif_request, struct blkif_response);
 #define VDISK_REMOVABLE    0x2
 #define VDISK_READONLY     0x4
+/* Xen-defined major numbers for virtual disks, they look strangely
+ * familiar */
+#define XEN_IDE0_MAJOR  3
+#define XEN_IDE1_MAJOR  22
+#define XEN_SCSI_DISK0_MAJOR    8
+#define XEN_SCSI_DISK1_MAJOR    65
+#define XEN_SCSI_DISK2_MAJOR    66
+#define XEN_SCSI_DISK3_MAJOR    67
+#define XEN_SCSI_DISK4_MAJOR    68
+#define XEN_SCSI_DISK5_MAJOR    69
+#define XEN_SCSI_DISK6_MAJOR    70
+#define XEN_SCSI_DISK7_MAJOR    71
+#define XEN_SCSI_DISK8_MAJOR    128
+#define XEN_SCSI_DISK9_MAJOR    129
+#define XEN_SCSI_DISK10_MAJOR   130
+#define XEN_SCSI_DISK11_MAJOR   131
+#define XEN_SCSI_DISK12_MAJOR   132
+#define XEN_SCSI_DISK13_MAJOR   133
+#define XEN_SCSI_DISK14_MAJOR   134
+#define XEN_SCSI_DISK15_MAJOR   135
 #endif /* __XEN_PUBLIC_IO_BLKIF_H__ */
diff --git a/include/xen/interface/xen.h b/include/xen/interface/xen.h
index 2befa3e2f1bc..b33257bc7e83 100644
--- a/include/xen/interface/xen.h
+++ b/include/xen/interface/xen.h
@@ -30,7 +30,7 @@
 #define __HYPERVISOR_stack_switch          3
 #define __HYPERVISOR_set_callbacks         4
 #define __HYPERVISOR_fpu_taskswitch        5
-#define __HYPERVISOR_sched_op              6
+#define __HYPERVISOR_sched_op_compat       6
 #define __HYPERVISOR_dom0_op               7
 #define __HYPERVISOR_set_debugreg          8
 #define __HYPERVISOR_get_debugreg          9
@@ -52,7 +52,7 @@
 #define __HYPERVISOR_mmuext_op            26
 #define __HYPERVISOR_acm_op               27
 #define __HYPERVISOR_nmi_op               28
-#define __HYPERVISOR_sched_op_new         29
+#define __HYPERVISOR_sched_op             29
 #define __HYPERVISOR_callback_op          30
 #define __HYPERVISOR_xenoprof_op          31
 #define __HYPERVISOR_event_channel_op     32
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index 98b92154a264..03c85d7387fb 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -5,9 +5,9 @@
 DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu);
-void xen_pre_suspend(void);
+void xen_arch_pre_suspend(void);
-void xen_post_suspend(int suspend_cancelled);
+void xen_arch_post_suspend(int suspend_cancelled);
-void xen_hvm_post_suspend(int suspend_cancelled);
+void xen_arch_hvm_post_suspend(int suspend_cancelled);
 void xen_mm_pin_all(void);
 void xen_mm_unpin_all(void);
author	Ingo Molnar <mingo@elte.hu>	2011-03-18 05:38:53 -0400
committer	Ingo Molnar <mingo@elte.hu>	2011-03-18 05:39:00 -0400
commit	8dd8997d2c56c9f248294805e129e1fc69444380 (patch)
tree	3b030a04295fc031db98746c4074c2df1ed6a19f /include
parent	1eda75c131ea42ec173323b6c34aeed78ae637c1 (diff)
parent	016aa2ed1cc9cf704cf76d8df07751b6daa9750f (diff)