Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

Conflicts:
	drivers/power/wm97xx_battery.c

1 files changed, 148 insertions, 56 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4d075426988..97b10da0a3e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -38,6 +38,8 @@
 #define SCHED_BATCH		3
 /* SCHED_ISO: reserved but not implemented yet */
 #define SCHED_IDLE		5
+/* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */
+#define SCHED_RESET_ON_FORK     0x40000000
 
 #ifdef __KERNEL__
 
@@ -98,7 +100,7 @@ struct robust_list_head;
 struct bio;
 struct fs_struct;
 struct bts_context;
-struct perf_counter_context;
+struct perf_event_context;
 
 /*
  * List of flags we want to share for kernel threads,
@@ -138,6 +140,10 @@ extern int nr_processes(void);
 extern unsigned long nr_running(void);
 extern unsigned long nr_uninterruptible(void);
 extern unsigned long nr_iowait(void);
+extern unsigned long nr_iowait_cpu(void);
+extern unsigned long this_cpu_load(void);
+
+
 extern void calc_global_load(void);
 extern u64 cpu_nr_migrations(int cpu);
 
@@ -188,6 +194,7 @@ extern unsigned long long time_sync_thresh;
 /* in tsk->state again */
 #define TASK_DEAD		64
 #define TASK_WAKEKILL		128
+#define TASK_WAKING		256
 
 /* Convenience macros for the sake of set_task_state */
 #define TASK_KILLABLE		(TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
@@ -209,7 +216,7 @@ extern unsigned long long time_sync_thresh;
 			((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
 #define task_contributes_to_load(task)	\
 				((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
-				 (task->flags & PF_FROZEN) == 0)
+				 (task->flags & PF_FREEZING) == 0)
 
 #define __set_task_state(tsk, state_value)		\
 	do { (tsk)->state = (state_value); } while (0)
@@ -254,7 +261,7 @@ extern asmlinkage void schedule_tail(struct task_struct *prev);
 extern void init_idle(struct task_struct *idle, int cpu);
 extern void init_idle_bootup_task(struct task_struct *idle);
 
-extern int runqueue_is_locked(void);
+extern int runqueue_is_locked(int cpu);
 extern void task_rq_unlock_wait(struct task_struct *p);
 
 extern cpumask_var_t nohz_cpu_mask;
@@ -349,8 +356,20 @@ extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner);
 struct nsproxy;
 struct user_namespace;
 
-/* Maximum number of active map areas.. This is a random (large) number */
-#define DEFAULT_MAX_MAP_COUNT	65536
+/*
+ * Default maximum number of active map areas, this limits the number of vmas
+ * per mm struct. Users can overwrite this number by sysctl but there is a
+ * problem.
+ *
+ * When a program's coredump is generated as ELF format, a section is created
+ * per a vma. In ELF, the number of sections is represented in unsigned short.
+ * This means the number of sections should be smaller than 65535 at coredump.
+ * Because the kernel adds some informative sections to a image of program at
+ * generating coredump, we need some margin. The number of extra sections is
+ * 1-3 now and depends on arch. We use "5" as safe margin, here.
+ */
+#define MAPCOUNT_ELF_CORE_MARGIN	(5)
+#define DEFAULT_MAX_MAP_COUNT	(USHORT_MAX - MAPCOUNT_ELF_CORE_MARGIN)
 
 extern int sysctl_max_map_count;
 
@@ -419,7 +438,9 @@ extern int get_dumpable(struct mm_struct *mm);
 /* dumpable bits */
 #define MMF_DUMPABLE      0  /* core dump is permitted */
 #define MMF_DUMP_SECURELY 1  /* core file is readable only by root */
+
 #define MMF_DUMPABLE_BITS 2
+#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1)
 
 /* coredump filter bits */
 #define MMF_DUMP_ANON_PRIVATE	2
@@ -429,6 +450,7 @@ extern int get_dumpable(struct mm_struct *mm);
 #define MMF_DUMP_ELF_HEADERS	6
 #define MMF_DUMP_HUGETLB_PRIVATE 7
 #define MMF_DUMP_HUGETLB_SHARED  8
+
 #define MMF_DUMP_FILTER_SHIFT	MMF_DUMPABLE_BITS
 #define MMF_DUMP_FILTER_BITS	7
 #define MMF_DUMP_FILTER_MASK \
@@ -442,6 +464,10 @@ extern int get_dumpable(struct mm_struct *mm);
 #else
 # define MMF_DUMP_MASK_DEFAULT_ELF	0
 #endif
+					/* leave room for more dump flags */
+#define MMF_VM_MERGEABLE	16	/* KSM may merge identical pages */
+
+#define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK)
 
 struct sighand_struct {
 	atomic_t		count;
@@ -486,6 +512,15 @@ struct task_cputime {
 		.sum_exec_runtime = 0,				\
 	}
 
+/*
+ * Disable preemption until the scheduler is running.
+ * Reset by start_kernel()->sched_init()->init_idle().
+ *
+ * We include PREEMPT_ACTIVE to avoid cond_resched() from working
+ * before the scheduler is active -- see should_resched().
+ */
+#define INIT_PREEMPT_COUNT	(1 + PREEMPT_ACTIVE)
+
 /**
  * struct thread_group_cputimer - thread group interval timer counts
  * @cputime:		thread group interval timers.
@@ -608,6 +643,8 @@ struct signal_struct {
 	unsigned audit_tty;
 	struct tty_audit_buf *tty_audit_buf;
 #endif
+
+	int oom_adj;	/* OOM kill score adjustment (bit shift) */
 };
 
 /* Context switch must be unlocked if interrupts are to be enabled */
@@ -677,7 +714,7 @@ struct user_struct {
 #endif
 #endif
 
-#ifdef CONFIG_PERF_COUNTERS
+#ifdef CONFIG_PERF_EVENTS
 	atomic_long_t locked_vm;
 #endif
 };
@@ -775,18 +812,19 @@ enum cpu_idle_type {
 #define SCHED_LOAD_SCALE_FUZZ	SCHED_LOAD_SCALE
 
 #ifdef CONFIG_SMP
-#define SD_LOAD_BALANCE		1	/* Do load balancing on this domain. */
-#define SD_BALANCE_NEWIDLE	2	/* Balance when about to become idle */
-#define SD_BALANCE_EXEC		4	/* Balance on exec */
-#define SD_BALANCE_FORK		8	/* Balance on fork, clone */
-#define SD_WAKE_IDLE		16	/* Wake to idle CPU on task wakeup */
-#define SD_WAKE_AFFINE		32	/* Wake task to waking CPU */
-#define SD_WAKE_BALANCE		64	/* Perform balancing at task wakeup */
-#define SD_SHARE_CPUPOWER	128	/* Domain members share cpu power */
-#define SD_POWERSAVINGS_BALANCE	256	/* Balance for power savings */
-#define SD_SHARE_PKG_RESOURCES	512	/* Domain members share cpu pkg resources */
-#define SD_SERIALIZE		1024	/* Only a single load balancing instance */
-#define SD_WAKE_IDLE_FAR	2048	/* Gain latency sacrificing cache hit */
+#define SD_LOAD_BALANCE		0x0001	/* Do load balancing on this domain. */
+#define SD_BALANCE_NEWIDLE	0x0002	/* Balance when about to become idle */
+#define SD_BALANCE_EXEC		0x0004	/* Balance on exec */
+#define SD_BALANCE_FORK		0x0008	/* Balance on fork, clone */
+#define SD_BALANCE_WAKE		0x0010  /* Balance on wakeup */
+#define SD_WAKE_AFFINE		0x0020	/* Wake task to waking CPU */
+#define SD_PREFER_LOCAL		0x0040  /* Prefer to keep tasks local to this domain */
+#define SD_SHARE_CPUPOWER	0x0080	/* Domain members share cpu power */
+#define SD_POWERSAVINGS_BALANCE	0x0100	/* Balance for power savings */
+#define SD_SHARE_PKG_RESOURCES	0x0200	/* Domain members share cpu pkg resources */
+#define SD_SERIALIZE		0x0400	/* Only a single load balancing instance */
+
+#define SD_PREFER_SIBLING	0x1000	/* Prefer to place tasks in a sibling domain */
 
 enum powersavings_balance_level {
 	POWERSAVINGS_BALANCE_NONE = 0,  /* No power saving load balance */
@@ -806,7 +844,7 @@ static inline int sd_balance_for_mc_power(void)
 	if (sched_smt_power_savings)
 		return SD_POWERSAVINGS_BALANCE;
 
-	return 0;
+	return SD_PREFER_SIBLING;
 }
 
 static inline int sd_balance_for_package_power(void)
@@ -814,7 +852,7 @@ static inline int sd_balance_for_package_power(void)
 	if (sched_mc_power_savings | sched_smt_power_savings)
 		return SD_POWERSAVINGS_BALANCE;
 
-	return 0;
+	return SD_PREFER_SIBLING;
 }
 
 /*
@@ -836,15 +874,9 @@ struct sched_group {
 
 	/*
 	 * CPU power of this group, SCHED_LOAD_SCALE being max power for a
-	 * single CPU. This is read only (except for setup, hotplug CPU).
-	 * Note : Never change cpu_power without recompute its reciprocal
+	 * single CPU.
 	 */
-	unsigned int __cpu_power;
-	/*
-	 * reciprocal value of cpu_power to avoid expensive divides
-	 * (see include/linux/reciprocal_div.h)
-	 */
-	u32 reciprocal_cpu_power;
+	unsigned int cpu_power;
 
 	/*
 	 * The CPUs this group covers.
@@ -897,6 +929,7 @@ struct sched_domain {
 	unsigned int newidle_idx;
 	unsigned int wake_idx;
 	unsigned int forkexec_idx;
+	unsigned int smt_gain;
 	int flags;			/* See SD_* */
 	enum sched_domain_level level;
 
@@ -972,6 +1005,9 @@ static inline int test_sd_parent(struct sched_domain *sd, int flag)
 	return 0;
 }
 
+unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu);
+unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu);
+
 #else /* CONFIG_SMP */
 
 struct sched_domain_attr;
@@ -983,6 +1019,7 @@ partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
 }
 #endif	/* !CONFIG_SMP */
 
+
 struct io_context;			/* See blkdev.h */
 
 
@@ -1000,6 +1037,12 @@ struct uts_namespace;
 struct rq;
 struct sched_domain;
 
+/*
+ * wake flags
+ */
+#define WF_SYNC		0x01		/* waker goes to sleep after wakup */
+#define WF_FORK		0x02		/* child wakeup after fork */
+
 struct sched_class {
 	const struct sched_class *next;
 
@@ -1007,13 +1050,13 @@ struct sched_class {
 	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep);
 	void (*yield_task) (struct rq *rq);
 
-	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int sync);
+	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
 
 	struct task_struct * (*pick_next_task) (struct rq *rq);
 	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
 
 #ifdef CONFIG_SMP
-	int  (*select_task_rq)(struct task_struct *p, int sync);
+	int  (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
 
 	unsigned long (*load_balance) (struct rq *this_rq, int this_cpu,
 			struct rq *busiest, unsigned long max_load_move,
@@ -1024,7 +1067,6 @@ struct sched_class {
 			      struct rq *busiest, struct sched_domain *sd,
 			      enum cpu_idle_type idle);
 	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
-	int (*needs_post_schedule) (struct rq *this_rq);
 	void (*post_schedule) (struct rq *this_rq);
 	void (*task_wake_up) (struct rq *this_rq, struct task_struct *task);
 
@@ -1046,6 +1088,8 @@ struct sched_class {
 	void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
 			     int oldprio, int running);
 
+	unsigned int (*get_rr_interval) (struct task_struct *task);
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	void (*moved_group) (struct task_struct *p);
 #endif
@@ -1084,11 +1128,15 @@ struct sched_entity {
 	u64			start_runtime;
 	u64			avg_wakeup;
 
+	u64			avg_running;
+
 #ifdef CONFIG_SCHEDSTATS
 	u64			wait_start;
 	u64			wait_max;
 	u64			wait_count;
 	u64			wait_sum;
+	u64			iowait_count;
+	u64			iowait_sum;
 
 	u64			sleep_start;
 	u64			sleep_max;
@@ -1142,6 +1190,8 @@ struct sched_rt_entity {
 #endif
 };
 
+struct rcu_node;
+
 struct task_struct {
 	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
 	void *stack;
@@ -1184,10 +1234,12 @@ struct task_struct {
 	unsigned int policy;
 	cpumask_t cpus_allowed;
 
-#ifdef CONFIG_PREEMPT_RCU
+#ifdef CONFIG_TREE_PREEMPT_RCU
 	int rcu_read_lock_nesting;
-	int rcu_flipctr_idx;
-#endif /* #ifdef CONFIG_PREEMPT_RCU */
+	char rcu_read_unlock_special;
+	struct rcu_node *rcu_blocked_node;
+	struct list_head rcu_node_entry;
+#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
 	struct sched_info sched_info;
@@ -1208,11 +1260,19 @@ struct task_struct {
 	unsigned did_exec:1;
 	unsigned in_execve:1;	/* Tell the LSMs that the process is doing an
 				 * execve */
+	unsigned in_iowait:1;
+
+
+	/* Revert to default priority/policy when forking */
+	unsigned sched_reset_on_fork:1;
+
 	pid_t pid;
 	pid_t tgid;
 
+#ifdef CONFIG_CC_STACKPROTECTOR
 	/* Canary value for the -fstack-protector gcc feature */
 	unsigned long stack_canary;
+#endif
 
 	/* 
 	 * pointers to (original) parent process, youngest child, younger sibling,
@@ -1270,6 +1330,7 @@ struct task_struct {
 	struct mutex cred_guard_mutex;	/* guard against foreign influences on
 					 * credential calculations
 					 * (notably. ptrace) */
+	struct cred *replacement_session_keyring; /* for KEYCTL_SESSION_TO_PARENT */
 
 	char comm[TASK_COMM_LEN]; /* executable name excluding path
 				     - access with [gs]et_task_comm (which lock
@@ -1402,10 +1463,10 @@ struct task_struct {
 	struct list_head pi_state_list;
 	struct futex_pi_state *pi_state_cache;
 #endif
-#ifdef CONFIG_PERF_COUNTERS
-	struct perf_counter_context *perf_counter_ctxp;
-	struct mutex perf_counter_mutex;
-	struct list_head perf_counter_list;
+#ifdef CONFIG_PERF_EVENTS
+	struct perf_event_context *perf_event_ctxp;
+	struct mutex perf_event_mutex;
+	struct list_head perf_event_list;
 #endif
 #ifdef CONFIG_NUMA
 	struct mempolicy *mempolicy;	/* Protected by alloc_lock */
@@ -1659,11 +1720,12 @@ extern cputime_t task_gtime(struct task_struct *p);
 #define PF_MEMALLOC	0x00000800	/* Allocating memory */
 #define PF_FLUSHER	0x00001000	/* responsible for disk writeback */
 #define PF_USED_MATH	0x00002000	/* if unset the fpu must be initialized before use */
+#define PF_FREEZING	0x00004000	/* freeze in progress. do not account to load */
 #define PF_NOFREEZE	0x00008000	/* this thread should not be frozen */
 #define PF_FROZEN	0x00010000	/* frozen for system suspend */
 #define PF_FSTRANS	0x00020000	/* inside a filesystem transaction */
 #define PF_KSWAPD	0x00040000	/* I am kswapd */
-#define PF_SWAPOFF	0x00080000	/* I am in swapoff */
+#define PF_OOM_ORIGIN	0x00080000	/* Allocating much memory to others */
 #define PF_LESS_THROTTLE 0x00100000	/* Throttle me less: I clean memory */
 #define PF_KTHREAD	0x00200000	/* I am a kernel thread */
 #define PF_RANDOMIZE	0x00400000	/* randomize virtual address space */
@@ -1701,6 +1763,27 @@ extern cputime_t task_gtime(struct task_struct *p);
 #define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
 #define used_math() tsk_used_math(current)
 
+#ifdef CONFIG_TREE_PREEMPT_RCU
+
+#define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */
+#define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */
+
+static inline void rcu_copy_process(struct task_struct *p)
+{
+	p->rcu_read_lock_nesting = 0;
+	p->rcu_read_unlock_special = 0;
+	p->rcu_blocked_node = NULL;
+	INIT_LIST_HEAD(&p->rcu_node_entry);
+}
+
+#else
+
+static inline void rcu_copy_process(struct task_struct *p)
+{
+}
+
+#endif
+
 #ifdef CONFIG_SMP
 extern int set_cpus_allowed_ptr(struct task_struct *p,
 				const struct cpumask *new_mask);
@@ -1790,11 +1873,12 @@ extern unsigned int sysctl_sched_min_granularity;
 extern unsigned int sysctl_sched_wakeup_granularity;
 extern unsigned int sysctl_sched_shares_ratelimit;
 extern unsigned int sysctl_sched_shares_thresh;
-#ifdef CONFIG_SCHED_DEBUG
 extern unsigned int sysctl_sched_child_runs_first;
+#ifdef CONFIG_SCHED_DEBUG
 extern unsigned int sysctl_sched_features;
 extern unsigned int sysctl_sched_migration_cost;
 extern unsigned int sysctl_sched_nr_migrate;
+extern unsigned int sysctl_sched_time_avg;
 extern unsigned int sysctl_timer_migration;
 
 int sched_nr_latency_handler(struct ctl_table *table, int write,
@@ -2054,7 +2138,7 @@ static inline unsigned long wait_task_inactive(struct task_struct *p,
 #define for_each_process(p) \
 	for (p = &init_task ; (p = next_task(p)) != &init_task ; )
 
-extern bool is_single_threaded(struct task_struct *);
+extern bool current_is_single_threaded(void);
 
 /*
  * Careful: do_each_thread/while_each_thread is a double loop so
@@ -2258,23 +2342,31 @@ static inline int need_resched(void)
  * cond_resched_softirq() will enable bhs before scheduling.
  */
 extern int _cond_resched(void);
-#ifdef CONFIG_PREEMPT_BKL
-static inline int cond_resched(void)
-{
-	return 0;
-}
+
+#define cond_resched() ({			\
+	__might_sleep(__FILE__, __LINE__, 0);	\
+	_cond_resched();			\
+})
+
+extern int __cond_resched_lock(spinlock_t *lock);
+
+#ifdef CONFIG_PREEMPT
+#define PREEMPT_LOCK_OFFSET	PREEMPT_OFFSET
 #else
-static inline int cond_resched(void)
-{
-	return _cond_resched();
-}
+#define PREEMPT_LOCK_OFFSET	0
 #endif
-extern int cond_resched_lock(spinlock_t * lock);
-extern int cond_resched_softirq(void);
-static inline int cond_resched_bkl(void)
-{
-	return _cond_resched();
-}
+
+#define cond_resched_lock(lock) ({				\
+	__might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);	\
+	__cond_resched_lock(lock);				\
+})
+
+extern int __cond_resched_softirq(void);
+
+#define cond_resched_softirq() ({				\
+	__might_sleep(__FILE__, __LINE__, SOFTIRQ_OFFSET);	\
+	__cond_resched_softirq();				\
+})
 
 /*
  * Does a critical section need to be broken due to another