Merge commit 'v2.6.28-rc1' into sched/urgent

1 files changed, 88 insertions, 19 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index c05b45faef18..b483f39a7112 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -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
@@ -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 */
 
 	/*
@@ -499,7 +552,7 @@ 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;
@@ -508,14 +561,6 @@ struct signal_struct {
 	struct task_io_accounting ioac;
 
 	/*
-	 * 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;
-
-	/*
 	 * We don't bother to synchronize most readers of this at all,
 	 * because there is no reader checking a limit that actually needs
 	 * to get both rlim_cur and rlim_max atomically, and either one
@@ -526,8 +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
@@ -637,10 +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;
@@ -1138,8 +1177,7 @@ 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 */
@@ -1305,6 +1343,12 @@ 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;
 };
 
 /*
@@ -1589,6 +1633,7 @@ 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
@@ -2087,6 +2132,30 @@ 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.