Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

[karo-tx-linux.git] / include / linux / sched.h

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 7fa8c4d372e7d2eb547a7580932d1b7d661535a2..c115d617739d8e6f1f388c13069ad32cfca1bb3b 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -599,33 +599,42 @@ struct task_cputime_atomic {
                .sum_exec_runtime = ATOMIC64_INIT(0),           \
        }
 
-#ifdef CONFIG_PREEMPT_COUNT
-#define PREEMPT_DISABLED       (1 + PREEMPT_ENABLED)
-#else
-#define PREEMPT_DISABLED       PREEMPT_ENABLED
-#endif
+#define PREEMPT_DISABLED       (PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED)
 
 /*
- * Disable preemption until the scheduler is running.
- * Reset by start_kernel()->sched_init()->init_idle().
+ * Disable preemption until the scheduler is running -- use an unconditional
+ * value so that it also works on !PREEMPT_COUNT kernels.
+ *
+ * Reset by start_kernel()->sched_init()->init_idle()->init_idle_preempt_count().
+ */
+#define INIT_PREEMPT_COUNT     PREEMPT_OFFSET
+
+/*
+ * Initial preempt_count value; reflects the preempt_count schedule invariant
+ * which states that during context switches:
+ *
+ *    preempt_count() == 2*PREEMPT_DISABLE_OFFSET
  *
- * We include PREEMPT_ACTIVE to avoid cond_resched() from working
- * before the scheduler is active -- see should_resched().
+ * Note: PREEMPT_DISABLE_OFFSET is 0 for !PREEMPT_COUNT kernels.
+ * Note: See finish_task_switch().
  */
-#define INIT_PREEMPT_COUNT     (PREEMPT_DISABLED + PREEMPT_ACTIVE)
+#define FORK_PREEMPT_COUNT     (2*PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED)
 
 /**
  * struct thread_group_cputimer - thread group interval timer counts
  * @cputime_atomic:    atomic thread group interval timers.
- * @running:           non-zero when there are timers running and
- *                     @cputime receives updates.
+ * @running:           true when there are timers running and
+ *                     @cputime_atomic receives updates.
+ * @checking_timer:    true when a thread in the group is in the
+ *                     process of checking for thread group timers.
  *
  * This structure contains the version of task_cputime, above, that is
  * used for thread group CPU timer calculations.
  */
 struct thread_group_cputimer {
        struct task_cputime_atomic cputime_atomic;
-       int running;
+       bool running;
+       bool checking_timer;
 };
 
 #include <linux/rwsem.h>
@@ -762,6 +771,18 @@ struct signal_struct {
        unsigned audit_tty_log_passwd;
        struct tty_audit_buf *tty_audit_buf;
 #endif
+#ifdef CONFIG_CGROUPS
+       /*
+        * group_rwsem prevents new tasks from entering the threadgroup and
+        * member tasks from exiting,a more specifically, setting of
+        * PF_EXITING.  fork and exit paths are protected with this rwsem
+        * using threadgroup_change_begin/end().  Users which require
+        * threadgroup to remain stable should use threadgroup_[un]lock()
+        * which also takes care of exec path.  Currently, cgroup is the
+        * only user.
+        */
+       struct rw_semaphore group_rwsem;
+#endif
 
        oom_flags_t oom_flags;
        short oom_score_adj;            /* OOM kill score adjustment */
@@ -828,7 +849,7 @@ struct user_struct {
        struct hlist_node uidhash_node;
        kuid_t uid;
 
-#ifdef CONFIG_PERF_EVENTS
+#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL)
        atomic_long_t locked_vm;
 #endif
 };
@@ -1127,8 +1148,6 @@ struct sched_domain_topology_level {
 #endif
 };
 
-extern struct sched_domain_topology_level *sched_domain_topology;
-
 extern void set_sched_topology(struct sched_domain_topology_level *tl);
 extern void wake_up_if_idle(int cpu);
 
@@ -1177,10 +1196,10 @@ struct load_weight {
 
 /*
  * The load_avg/util_avg accumulates an infinite geometric series.
- * 1) load_avg factors the amount of time that a sched_entity is
- * runnable on a rq into its weight. For cfs_rq, it is the aggregated
- * such weights of all runnable and blocked sched_entities.
- * 2) util_avg factors frequency scaling into the amount of time
+ * 1) load_avg factors frequency scaling into the amount of time that a
+ * sched_entity is runnable on a rq into its weight. For cfs_rq, it is the
+ * aggregated such weights of all runnable and blocked sched_entities.
+ * 2) util_avg factors frequency and cpu scaling into the amount of time
  * that a sched_entity is running on a CPU, in the range [0..SCHED_LOAD_SCALE].
  * For cfs_rq, it is the aggregated such times of all runnable and
  * blocked sched_entities.