1 files changed, 63 insertions, 55 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index b7b9501b41af..edad7a43edea 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -384,6 +384,7 @@ extern int proc_dowatchdog_thresh(struct ctl_table *table, int write,
                                   void __user *buffer,
                                   size_t *lenp, loff_t *ppos);
 extern unsigned int  softlockup_panic;
+extern unsigned int  hardlockup_panic;
 void lockup_detector_init(void);
 #else
 static inline void touch_softlockup_watchdog(void)
@@ -483,9 +484,11 @@ static inline 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_DAX_PRIVATE    9
+#define MMF_DUMP_DAX_SHARED     10
 
 #define MMF_DUMP_FILTER_SHIFT   MMF_DUMPABLE_BITS
-#define MMF_DUMP_FILTER_BITS    7
+#define MMF_DUMP_FILTER_BITS    9
 #define MMF_DUMP_FILTER_MASK \
         (((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT)
 #define MMF_DUMP_FILTER_DEFAULT \
@@ -599,33 +602,42 @@ 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.
  *
- * We include PREEMPT_ACTIVE to avoid cond_resched() from working
- * before the scheduler is active -- see should_resched().
+ * Reset by start_kernel()->sched_init()->init_idle()->init_idle_preempt_count().
  */
-#define INIT_PREEMPT_COUNT      (PREEMPT_DISABLED + PREEMPT_ACTIVE)
+#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
+ *
+ * Note: PREEMPT_DISABLE_OFFSET is 0 for !PREEMPT_COUNT kernels.
+ * Note: See finish_task_switch().
+ */
+#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>
@@ -762,18 +774,6 @@ 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 */
@@ -840,7 +840,7 @@ 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
 };
@@ -1139,8 +1139,6 @@ 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);
 
@@ -1189,10 +1187,10 @@ 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.
@@ -1342,10 +1340,12 @@ struct sched_dl_entity {
 
 union rcu_special {
         struct {
-                bool blocked;
-                bool need_qs;
-        } b;
-        short s;
+                u8 blocked;
+                u8 need_qs;
+                u8 exp_need_qs;
+                u8 pad; /* Otherwise the compiler can store garbage here. */
+        } b; /* Bits. */
+        u32 s; /* Set of bits. */
 };
 struct rcu_node;
 
@@ -1463,7 +1463,9 @@ struct task_struct {
         unsigned sched_reset_on_fork:1;
         unsigned sched_contributes_to_load:1;
         unsigned sched_migrated:1;
-
+#ifdef CONFIG_MEMCG
+        unsigned memcg_may_oom:1;
+#endif
 #ifdef CONFIG_MEMCG_KMEM
         unsigned memcg_kmem_skip_account:1;
 #endif
@@ -1570,9 +1572,7 @@ struct task_struct {
 
         unsigned long sas_ss_sp;
         size_t sas_ss_size;
-        int (*notifier)(void *priv);
-        void *notifier_data;
-        sigset_t *notifier_mask;
+
         struct callback_head *task_works;
 
         struct audit_context *audit_context;
@@ -1794,12 +1794,12 @@ struct task_struct {
         unsigned long trace_recursion;
 #endif /* CONFIG_TRACING */
 #ifdef CONFIG_MEMCG
-        struct memcg_oom_info {
-                struct mem_cgroup *memcg;
-                gfp_t gfp_mask;
-                int order;
-                unsigned int may_oom:1;
-        } memcg_oom;
+        struct mem_cgroup *memcg_in_oom;
+        gfp_t memcg_oom_gfp_mask;
+        int memcg_oom_order;
+
+        /* number of pages to reclaim on returning to userland */
+        unsigned int memcg_nr_pages_over_high;
 #endif
 #ifdef CONFIG_UPROBES
         struct uprobe_task *utask;
@@ -2464,21 +2464,29 @@ extern void ignore_signals(struct task_struct *);
 extern void flush_signal_handlers(struct task_struct *, int force_default);
 extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info);
 
-static inline int dequeue_signal_lock(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
+static inline int kernel_dequeue_signal(siginfo_t *info)
 {
-        unsigned long flags;
+        struct task_struct *tsk = current;
+        siginfo_t __info;
         int ret;
 
-        spin_lock_irqsave(&tsk->sighand->siglock, flags);
-        ret = dequeue_signal(tsk, mask, info);
-        spin_unlock_irqrestore(&tsk->sighand->siglock, flags);
+        spin_lock_irq(&tsk->sighand->siglock);
+        ret = dequeue_signal(tsk, &tsk->blocked, info ?: &__info);
+        spin_unlock_irq(&tsk->sighand->siglock);
 
         return ret;
 }
 
-extern void block_all_signals(int (*notifier)(void *priv), void *priv,
-                              sigset_t *mask);
-extern void unblock_all_signals(void);
+static inline void kernel_signal_stop(void)
+{
+        spin_lock_irq(&current->sighand->siglock);
+        if (current->jobctl & JOBCTL_STOP_DEQUEUED)
+                __set_current_state(TASK_STOPPED);
+        spin_unlock_irq(&current->sighand->siglock);
+
+        schedule();
+}
+
 extern void release_task(struct task_struct * p);
 extern int send_sig_info(int, struct siginfo *, struct task_struct *);
 extern int force_sigsegv(int, struct task_struct *);