sched/core: Introduce 'struct sched_domain_shared'

[cascardo/linux.git] / include / linux / sched.h

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 553af29..8a878b9 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -448,6 +448,8 @@ static inline void io_schedule(void)
        io_schedule_timeout(MAX_SCHEDULE_TIMEOUT);
 }
 
+void __noreturn do_task_dead(void);
+
 struct nsproxy;
 struct user_namespace;
 
@@ -1022,7 +1024,8 @@ extern void wake_up_q(struct wake_q_head *head);
 #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_SHARE_CPUCAPACITY   0x0080  /* Domain members share cpu power */
+#define SD_ASYM_CPUCAPACITY    0x0040  /* Groups have different max cpu capacities */
+#define SD_SHARE_CPUCAPACITY   0x0080  /* Domain members share cpu capacity */
 #define SD_SHARE_POWERDOMAIN   0x0100  /* Domain members share power domain */
 #define SD_SHARE_PKG_RESOURCES 0x0200  /* Domain members share cpu pkg resources */
 #define SD_SERIALIZE           0x0400  /* Only a single load balancing instance */
@@ -1064,6 +1067,10 @@ extern int sched_domain_level_max;
 
 struct sched_group;
 
+struct sched_domain_shared {
+       atomic_t        ref;
+};
+
 struct sched_domain {
        /* These fields must be setup */
        struct sched_domain *parent;    /* top domain must be null terminated */
@@ -1132,6 +1139,7 @@ struct sched_domain {
                void *private;          /* used during construction */
                struct rcu_head rcu;    /* used during destruction */
        };
+       struct sched_domain_shared *shared;
 
        unsigned int span_weight;
        /*
@@ -1165,6 +1173,7 @@ typedef int (*sched_domain_flags_f)(void);
 
 struct sd_data {
        struct sched_domain **__percpu sd;
+       struct sched_domain_shared **__percpu sds;
        struct sched_group **__percpu sg;
        struct sched_group_capacity **__percpu sgc;
 };
@@ -1547,6 +1556,9 @@ struct task_struct {
        /* unserialized, strictly 'current' */
        unsigned in_execve:1; /* bit to tell LSMs we're in execve */
        unsigned in_iowait:1;
+#if !defined(TIF_RESTORE_SIGMASK)
+       unsigned restore_sigmask:1;
+#endif
 #ifdef CONFIG_MEMCG
        unsigned memcg_may_oom:1;
 #ifndef CONFIG_SLOB
@@ -2680,6 +2692,66 @@ extern void sigqueue_free(struct sigqueue *);
 extern int send_sigqueue(struct sigqueue *,  struct task_struct *, int group);
 extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
 
+#ifdef TIF_RESTORE_SIGMASK
+/*
+ * Legacy restore_sigmask accessors.  These are inefficient on
+ * SMP architectures because they require atomic operations.
+ */
+
+/**
+ * set_restore_sigmask() - make sure saved_sigmask processing gets done
+ *
+ * This sets TIF_RESTORE_SIGMASK and ensures that the arch signal code
+ * will run before returning to user mode, to process the flag.  For
+ * all callers, TIF_SIGPENDING is already set or it's no harm to set
+ * it.  TIF_RESTORE_SIGMASK need not be in the set of bits that the
+ * arch code will notice on return to user mode, in case those bits
+ * are scarce.  We set TIF_SIGPENDING here to ensure that the arch
+ * signal code always gets run when TIF_RESTORE_SIGMASK is set.
+ */
+static inline void set_restore_sigmask(void)
+{
+       set_thread_flag(TIF_RESTORE_SIGMASK);
+       WARN_ON(!test_thread_flag(TIF_SIGPENDING));
+}
+static inline void clear_restore_sigmask(void)
+{
+       clear_thread_flag(TIF_RESTORE_SIGMASK);
+}
+static inline bool test_restore_sigmask(void)
+{
+       return test_thread_flag(TIF_RESTORE_SIGMASK);
+}
+static inline bool test_and_clear_restore_sigmask(void)
+{
+       return test_and_clear_thread_flag(TIF_RESTORE_SIGMASK);
+}
+
+#else  /* TIF_RESTORE_SIGMASK */
+
+/* Higher-quality implementation, used if TIF_RESTORE_SIGMASK doesn't exist. */
+static inline void set_restore_sigmask(void)
+{
+       current->restore_sigmask = true;
+       WARN_ON(!test_thread_flag(TIF_SIGPENDING));
+}
+static inline void clear_restore_sigmask(void)
+{
+       current->restore_sigmask = false;
+}
+static inline bool test_restore_sigmask(void)
+{
+       return current->restore_sigmask;
+}
+static inline bool test_and_clear_restore_sigmask(void)
+{
+       if (!current->restore_sigmask)
+               return false;
+       current->restore_sigmask = false;
+       return true;
+}
+#endif
+
 static inline void restore_saved_sigmask(void)
 {
        if (test_and_clear_restore_sigmask())
@@ -3143,7 +3215,11 @@ static inline int signal_pending_state(long state, struct task_struct *p)
  * cond_resched_lock() will drop the spinlock before scheduling,
  * cond_resched_softirq() will enable bhs before scheduling.
  */
+#ifndef CONFIG_PREEMPT
 extern int _cond_resched(void);
+#else
+static inline int _cond_resched(void) { return 0; }
+#endif
 
 #define cond_resched() ({                      \
        ___might_sleep(__FILE__, __LINE__, 0);  \
@@ -3173,6 +3249,15 @@ static inline void cond_resched_rcu(void)
 #endif
 }
 
+static inline unsigned long get_preempt_disable_ip(struct task_struct *p)
+{
+#ifdef CONFIG_DEBUG_PREEMPT
+       return p->preempt_disable_ip;
+#else
+       return 0;
+#endif
+}
+
 /*
  * Does a critical section need to be broken due to another
  * task waiting?: (technically does not depend on CONFIG_PREEMPT,