Merge commit 'v2.6.28-rc2' into x86/pci-ioapic-boot-irq-quirks

1 files changed, 145 insertions, 97 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1941d8b5cf11..8478f334d732 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -87,6 +87,7 @@ struct sched_param {
 #include <linux/task_io_accounting.h>
 #include <linux/kobject.h>
 #include <linux/latencytop.h>
+#include <linux/cred.h>
 
 #include <asm/processor.h>
 
@@ -286,19 +287,18 @@ extern void trap_init(void);
 extern void account_process_tick(struct task_struct *task, int user);
 extern void update_process_times(int user);
 extern void scheduler_tick(void);
-extern void hrtick_resched(void);
 
 extern void sched_show_task(struct task_struct *p);
 
 #ifdef CONFIG_DETECT_SOFTLOCKUP
 extern void softlockup_tick(void);
-extern void spawn_softlockup_task(void);
 extern void touch_softlockup_watchdog(void);
 extern void touch_all_softlockup_watchdogs(void);
-extern unsigned long  softlockup_thresh;
+extern unsigned int  softlockup_panic;
 extern unsigned long sysctl_hung_task_check_count;
 extern unsigned long sysctl_hung_task_timeout_secs;
 extern unsigned long sysctl_hung_task_warnings;
+extern int softlockup_thresh;
 #else
 static inline void softlockup_tick(void)
 {
@@ -351,7 +351,7 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
 extern void arch_unmap_area(struct mm_struct *, unsigned long);
 extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
 
-#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS
+#if USE_SPLIT_PTLOCKS
 /*
  * The mm counters are not protected by its page_table_lock,
  * so must be incremented atomically.
@@ -362,7 +362,7 @@ extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
 #define inc_mm_counter(mm, member) atomic_long_inc(&(mm)->_##member)
 #define dec_mm_counter(mm, member) atomic_long_dec(&(mm)->_##member)
 
-#else  /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
+#else  /* !USE_SPLIT_PTLOCKS */
 /*
  * The mm counters are protected by its page_table_lock,
  * so can be incremented directly.
@@ -373,7 +373,7 @@ extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
 #define inc_mm_counter(mm, member) (mm)->_##member++
 #define dec_mm_counter(mm, member) (mm)->_##member--
 
-#endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
+#endif /* !USE_SPLIT_PTLOCKS */
 
 #define get_mm_rss(mm)                                  \
         (get_mm_counter(mm, file_rss) + get_mm_counter(mm, anon_rss))
@@ -402,12 +402,21 @@ extern int get_dumpable(struct mm_struct *mm);
 #define MMF_DUMP_MAPPED_PRIVATE 4
 #define MMF_DUMP_MAPPED_SHARED  5
 #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    5
+#define MMF_DUMP_FILTER_BITS    7
 #define MMF_DUMP_FILTER_MASK \
         (((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT)
 #define MMF_DUMP_FILTER_DEFAULT \
-        ((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED))
+        ((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED) |\
+         (1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF)
+
+#ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS
+# define MMF_DUMP_MASK_DEFAULT_ELF      (1 << MMF_DUMP_ELF_HEADERS)
+#else
+# define MMF_DUMP_MASK_DEFAULT_ELF      0
+#endif
 
 struct sighand_struct {
         atomic_t                count;
@@ -424,6 +433,39 @@ struct pacct_struct {
         unsigned long           ac_minflt, ac_majflt;
 };
 
+/**
+ * struct task_cputime - collected CPU time counts
+ * @utime:              time spent in user mode, in &cputime_t units
+ * @stime:              time spent in kernel mode, in &cputime_t units
+ * @sum_exec_runtime:   total time spent on the CPU, in nanoseconds
+ *
+ * This structure groups together three kinds of CPU time that are
+ * tracked for threads and thread groups.  Most things considering
+ * CPU time want to group these counts together and treat all three
+ * of them in parallel.
+ */
+struct task_cputime {
+        cputime_t utime;
+        cputime_t stime;
+        unsigned long long sum_exec_runtime;
+};
+/* Alternate field names when used to cache expirations. */
+#define prof_exp        stime
+#define virt_exp        utime
+#define sched_exp       sum_exec_runtime
+
+/**
+ * struct thread_group_cputime - thread group interval timer counts
+ * @totals:             thread group interval timers; substructure for
+ *                      uniprocessor kernel, per-cpu for SMP kernel.
+ *
+ * This structure contains the version of task_cputime, above, that is
+ * used for thread group CPU clock calculations.
+ */
+struct thread_group_cputime {
+        struct task_cputime *totals;
+};
+
 /*
  * NOTE! "signal_struct" does not have it's own
  * locking, because a shared signal_struct always
@@ -450,8 +492,8 @@ struct signal_struct {
          * - everyone except group_exit_task is stopped during signal delivery
          *   of fatal signals, group_exit_task processes the signal.
          */
-        struct task_struct      *group_exit_task;
         int                     notify_count;
+        struct task_struct      *group_exit_task;
 
         /* thread group stop support, overloads group_exit_code too */
         int                     group_stop_count;
@@ -469,6 +511,17 @@ struct signal_struct {
         cputime_t it_prof_expires, it_virt_expires;
         cputime_t it_prof_incr, it_virt_incr;
 
+        /*
+         * Thread group totals for process CPU clocks.
+         * See thread_group_cputime(), et al, for details.
+         */
+        struct thread_group_cputime cputime;
+
+        /* Earliest-expiration cache. */
+        struct task_cputime cputime_expires;
+
+        struct list_head cpu_timers[3];
+
         /* job control IDs */
 
         /*
@@ -499,20 +552,13 @@ struct signal_struct {
          * Live threads maintain their own counters and add to these
          * in __exit_signal, except for the group leader.
          */
-        cputime_t utime, stime, cutime, cstime;
+        cputime_t cutime, cstime;
         cputime_t gtime;
         cputime_t cgtime;
         unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
         unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
         unsigned long inblock, oublock, cinblock, coublock;
-
-        /*
-         * Cumulative ns of scheduled CPU time for dead threads in the
-         * group, not including a zombie group leader.  (This only differs
-         * from jiffies_to_ns(utime + stime) if sched_clock uses something
-         * other than jiffies.)
-         */
-        unsigned long long sum_sched_runtime;
+        struct task_io_accounting ioac;
 
         /*
          * We don't bother to synchronize most readers of this at all,
@@ -525,8 +571,6 @@ struct signal_struct {
          */
         struct rlimit rlim[RLIM_NLIMITS];
 
-        struct list_head cpu_timers[3];
-
         /* keep the process-shared keyrings here so that they do the right
          * thing in threads created with CLONE_THREAD */
 #ifdef CONFIG_KEYS
@@ -636,10 +680,6 @@ struct sched_info {
 };
 #endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */
 
-#ifdef CONFIG_SCHEDSTATS
-extern const struct file_operations proc_schedstat_operations;
-#endif /* CONFIG_SCHEDSTATS */
-
 #ifdef CONFIG_TASK_DELAY_ACCT
 struct task_delay_info {
         spinlock_t      lock;
@@ -667,6 +707,10 @@ struct task_delay_info {
                                 /* io operations performed */
         u32 swapin_count;       /* total count of the number of swapin block */
                                 /* io operations performed */
+
+        struct timespec freepages_start, freepages_end;
+        u64 freepages_delay;    /* wait for memory reclaim */
+        u32 freepages_count;    /* total count of memory reclaim */
 };
 #endif  /* CONFIG_TASK_DELAY_ACCT */
 
@@ -818,13 +862,25 @@ struct sched_domain {
         unsigned int ttwu_move_affine;
         unsigned int ttwu_move_balance;
 #endif
+#ifdef CONFIG_SCHED_DEBUG
+        char *name;
+#endif
 };
 
 extern void partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
                                     struct sched_domain_attr *dattr_new);
 extern int arch_reinit_sched_domains(void);
 
-#endif  /* CONFIG_SMP */
+#else /* CONFIG_SMP */
+
+struct sched_domain_attr;
+
+static inline void
+partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
+                        struct sched_domain_attr *dattr_new)
+{
+}
+#endif  /* !CONFIG_SMP */
 
 struct io_context;                      /* See blkdev.h */
 #define NGROUPS_SMALL           32
@@ -882,7 +938,7 @@ struct sched_class {
         void (*yield_task) (struct rq *rq);
         int  (*select_task_rq)(struct task_struct *p, int sync);
 
-        void (*check_preempt_curr) (struct rq *rq, struct task_struct *p);
+        void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int sync);
 
         struct task_struct * (*pick_next_task) (struct rq *rq);
         void (*put_prev_task) (struct rq *rq, struct task_struct *p);
@@ -995,8 +1051,8 @@ struct sched_entity {
 
 struct sched_rt_entity {
         struct list_head run_list;
-        unsigned int time_slice;
         unsigned long timeout;
+        unsigned int time_slice;
         int nr_cpus_allowed;
 
         struct sched_rt_entity *back;
@@ -1119,8 +1175,7 @@ struct task_struct {
 /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
         unsigned long min_flt, maj_flt;
 
-        cputime_t it_prof_expires, it_virt_expires;
-        unsigned long long it_sched_expires;
+        struct task_cputime cputime_expires;
         struct list_head cpu_timers[3];
 
 /* process credentials */
@@ -1239,15 +1294,11 @@ struct task_struct {
 
         unsigned long ptrace_message;
         siginfo_t *last_siginfo; /* For ptrace use.  */
-#ifdef CONFIG_TASK_XACCT
-/* i/o counters(bytes read/written, #syscalls */
-        u64 rchar, wchar, syscr, syscw;
-#endif
         struct task_io_accounting ioac;
 #if defined(CONFIG_TASK_XACCT)
         u64 acct_rss_mem1;      /* accumulated rss usage */
         u64 acct_vm_mem1;       /* accumulated virtual memory usage */
-        cputime_t acct_stimexpd;/* stime since last update */
+        cputime_t acct_timexpd; /* stime + utime since last update */
 #endif
 #ifdef CONFIG_CPUSETS
         nodemask_t mems_allowed;
@@ -1290,6 +1341,12 @@ struct task_struct {
         int latency_record_count;
         struct latency_record latency_record[LT_SAVECOUNT];
 #endif
+        /*
+         * time slack values; these are used to round up poll() and
+         * select() etc timeout values. These are in nanoseconds.
+         */
+        unsigned long timer_slack_ns;
+        unsigned long default_timer_slack_ns;
 };
 
 /*
@@ -1464,6 +1521,10 @@ static inline void put_task_struct(struct task_struct *t)
                 __put_task_struct(t);
 }
 
+extern cputime_t task_utime(struct task_struct *p);
+extern cputime_t task_stime(struct task_struct *p);
+extern cputime_t task_gtime(struct task_struct *p);
+
 /*
  * Per process flags
  */
@@ -1486,7 +1547,7 @@ static inline void put_task_struct(struct task_struct *t)
 #define PF_KSWAPD       0x00040000      /* I am kswapd */
 #define PF_SWAPOFF      0x00080000      /* I am in swapoff */
 #define PF_LESS_THROTTLE 0x00100000     /* Throttle me less: I clean memory */
-#define PF_BORROWED_MM  0x00200000      /* I am a kthread doing use_mm */
+#define PF_KTHREAD      0x00200000      /* I am a kernel thread */
 #define PF_RANDOMIZE    0x00400000      /* randomize virtual address space */
 #define PF_SWAPWRITE    0x00800000      /* Allowed to write to swap */
 #define PF_SPREAD_PAGE  0x01000000      /* Spread page cache over cpuset */
@@ -1541,16 +1602,10 @@ static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
 
 extern unsigned long long sched_clock(void);
 
-#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-static inline void sched_clock_init(void)
-{
-}
-
-static inline u64 sched_clock_cpu(int cpu)
-{
-        return sched_clock();
-}
+extern void sched_clock_init(void);
+extern u64 sched_clock_cpu(int cpu);
 
+#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
 static inline void sched_clock_tick(void)
 {
 }
@@ -1562,28 +1617,11 @@ static inline void sched_clock_idle_sleep_event(void)
 static inline void sched_clock_idle_wakeup_event(u64 delta_ns)
 {
 }
-
-#ifdef CONFIG_NO_HZ
-static inline void sched_clock_tick_stop(int cpu)
-{
-}
-
-static inline void sched_clock_tick_start(int cpu)
-{
-}
-#endif
-
-#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
-extern void sched_clock_init(void);
-extern u64 sched_clock_cpu(int cpu);
+#else
 extern void sched_clock_tick(void);
 extern void sched_clock_idle_sleep_event(void);
 extern void sched_clock_idle_wakeup_event(u64 delta_ns);
-#ifdef CONFIG_NO_HZ
-extern void sched_clock_tick_stop(int cpu);
-extern void sched_clock_tick_start(int cpu);
 #endif
-#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
 
 /*
  * For kernel-internal use: high-speed (but slightly incorrect) per-cpu
@@ -1593,6 +1631,7 @@ extern unsigned long long cpu_clock(int cpu);
 
 extern unsigned long long
 task_sched_runtime(struct task_struct *task);
+extern unsigned long long thread_group_sched_runtime(struct task_struct *task);
 
 /* sched_exec is called by processes performing an exec */
 #ifdef CONFIG_SMP
@@ -1627,6 +1666,7 @@ 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_shares_ratelimit;
+extern unsigned int sysctl_sched_shares_thresh;
 
 int sched_nr_latency_handler(struct ctl_table *table, int write,
                 struct file *file, void __user *buffer, size_t *length,
@@ -1705,19 +1745,13 @@ extern struct pid_namespace init_pid_ns;
  *      finds a task by its pid in the specified namespace
  * find_task_by_vpid():
  *      finds a task by its virtual pid
- * find_task_by_pid():
- *      finds a task by its global pid
  *
- * see also find_pid() etc in include/linux/pid.h
+ * see also find_vpid() etc in include/linux/pid.h
  */
 
 extern struct task_struct *find_task_by_pid_type_ns(int type, int pid,
                 struct pid_namespace *ns);
 
-static inline struct task_struct *__deprecated find_task_by_pid(pid_t nr)
-{
-        return find_task_by_pid_type_ns(PIDTYPE_PID, nr, &init_pid_ns);
-}
 extern struct task_struct *find_task_by_vpid(pid_t nr);
 extern struct task_struct *find_task_by_pid_ns(pid_t nr,
                 struct pid_namespace *ns);
@@ -1785,12 +1819,11 @@ extern int kill_pid_info_as_uid(int, struct siginfo *, struct pid *, uid_t, uid_
 extern int kill_pgrp(struct pid *pid, int sig, int priv);
 extern int kill_pid(struct pid *pid, int sig, int priv);
 extern int kill_proc_info(int, struct siginfo *, pid_t);
-extern void do_notify_parent(struct task_struct *, int);
+extern int do_notify_parent(struct task_struct *, int);
 extern void force_sig(int, struct task_struct *);
 extern void force_sig_specific(int, struct task_struct *);
 extern int send_sig(int, struct task_struct *, int);
 extern void zap_other_threads(struct task_struct *p);
-extern int kill_proc(pid_t, int, int);
 extern struct sigqueue *sigqueue_alloc(void);
 extern void sigqueue_free(struct sigqueue *);
 extern int send_sigqueue(struct sigqueue *,  struct task_struct *, int group);
@@ -1872,9 +1905,13 @@ extern void set_task_comm(struct task_struct *tsk, char *from);
 extern char *get_task_comm(char *to, struct task_struct *tsk);
 
 #ifdef CONFIG_SMP
-extern void wait_task_inactive(struct task_struct * p);
+extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
 #else
-#define wait_task_inactive(p)   do { } while (0)
+static inline unsigned long wait_task_inactive(struct task_struct *p,
+                                               long match_state)
+{
+        return 1;
+}
 #endif
 
 #define next_task(p)    list_entry(rcu_dereference((p)->tasks.next), struct task_struct, tasks)
@@ -1973,6 +2010,13 @@ static inline unsigned long *end_of_stack(struct task_struct *p)
 
 #endif
 
+static inline int object_is_on_stack(void *obj)
+{
+        void *stack = task_stack_page(current);
+
+        return (obj >= stack) && (obj < (stack + THREAD_SIZE));
+}
+
 extern void thread_info_cache_init(void);
 
 /* set thread flags in other task's structures
@@ -2037,9 +2081,6 @@ static inline int signal_pending_state(long state, struct task_struct *p)
         if (!signal_pending(p))
                 return 0;
 
-        if (state & (__TASK_STOPPED | __TASK_TRACED))
-                return 0;
-
         return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p);
 }
 
@@ -2089,6 +2130,30 @@ static inline int spin_needbreak(spinlock_t *lock)
 }
 
 /*
+ * Thread group CPU time accounting.
+ */
+
+extern int thread_group_cputime_alloc(struct task_struct *);
+extern void thread_group_cputime(struct task_struct *, struct task_cputime *);
+
+static inline void thread_group_cputime_init(struct signal_struct *sig)
+{
+        sig->cputime.totals = NULL;
+}
+
+static inline int thread_group_cputime_clone_thread(struct task_struct *curr)
+{
+        if (curr->signal->cputime.totals)
+                return 0;
+        return thread_group_cputime_alloc(curr);
+}
+
+static inline void thread_group_cputime_free(struct signal_struct *sig)
+{
+        free_percpu(sig->cputime.totals);
+}
+
+/*
  * Reevaluate whether the task has signals pending delivery.
  * Wake the task if so.
  * This is required every time the blocked sigset_t changes.
@@ -2124,16 +2189,7 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
 
 #endif /* CONFIG_SMP */
 
-#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT
 extern void arch_pick_mmap_layout(struct mm_struct *mm);
-#else
-static inline void arch_pick_mmap_layout(struct mm_struct *mm)
-{
-        mm->mmap_base = TASK_UNMAPPED_BASE;
-        mm->get_unmapped_area = arch_get_unmapped_area;
-        mm->unmap_area = arch_unmap_area;
-}
-#endif
 
 #ifdef CONFIG_TRACING
 extern void
@@ -2181,22 +2237,22 @@ extern long sched_group_rt_period(struct task_group *tg);
 #ifdef CONFIG_TASK_XACCT
 static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
 {
-        tsk->rchar += amt;
+        tsk->ioac.rchar += amt;
 }
 
 static inline void add_wchar(struct task_struct *tsk, ssize_t amt)
 {
-        tsk->wchar += amt;
+        tsk->ioac.wchar += amt;
 }
 
 static inline void inc_syscr(struct task_struct *tsk)
 {
-        tsk->syscr++;
+        tsk->ioac.syscr++;
 }
 
 static inline void inc_syscw(struct task_struct *tsk)
 {
-        tsk->syscw++;
+        tsk->ioac.syscw++;
 }
 #else
 static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
@@ -2216,14 +2272,6 @@ static inline void inc_syscw(struct task_struct *tsk)
 }
 #endif
 
-#ifdef CONFIG_SMP
-void migration_init(void);
-#else
-static inline void migration_init(void)
-{
-}
-#endif
-
 #ifndef TASK_SIZE_OF
 #define TASK_SIZE_OF(tsk)       TASK_SIZE
 #endif