These changes are the raw update to linux-4.4.6-rt14. Kernel sources

are taken from kernel.org, and rt patch from the rt wiki download page.

During the rebasing, the following patch collided:

Force tick interrupt and get rid of softirq magic(I70131fb85).

Collisions have been removed because its logic was found on the
source already.

Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>

1 files changed, 264 insertions, 203 deletions

diff --git a/kernel/include/linux/sched.h b/kernel/include/linux/sched.h
index 956658437..58c5ec8c3 100644
--- a/kernel/include/linux/sched.h
+++ b/kernel/include/linux/sched.h
@@ -25,7 +25,7 @@ struct sched_param {
 #include <linux/errno.h>
 #include <linux/nodemask.h>
 #include <linux/mm_types.h>
-#include <linux/preempt_mask.h>
+#include <linux/preempt.h>
 #include <asm/kmap_types.h>
 
 #include <asm/page.h>
@@ -59,6 +59,7 @@ struct sched_param {
 #include <linux/uidgid.h>
 #include <linux/gfp.h>
 #include <linux/magic.h>
+#include <linux/cgroup-defs.h>
 
 #include <asm/processor.h>
 
@@ -133,6 +134,7 @@ struct fs_struct;
 struct perf_event_context;
 struct blk_plug;
 struct filename;
+struct nameidata;
 
 #define VMACACHE_BITS 2
 #define VMACACHE_SIZE (1U << VMACACHE_BITS)
@@ -174,9 +176,12 @@ extern unsigned long nr_iowait_cpu(int cpu);
 extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load);
 
 extern void calc_global_load(unsigned long ticks);
-extern void update_cpu_load_nohz(void);
 
-extern unsigned long get_parent_ip(unsigned long addr);
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+extern void update_cpu_load_nohz(void);
+#else
+static inline void update_cpu_load_nohz(void) { }
+#endif
 
 extern void dump_cpu_task(int cpu);
 
@@ -186,8 +191,6 @@ struct task_group;
 #ifdef CONFIG_SCHED_DEBUG
 extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m);
 extern void proc_sched_set_task(struct task_struct *p);
-extern void
-print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
 #endif
 
 /*
@@ -214,9 +217,10 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
 #define TASK_WAKEKILL		128
 #define TASK_WAKING		256
 #define TASK_PARKED		512
-#define TASK_STATE_MAX		1024
+#define TASK_NOLOAD		1024
+#define TASK_STATE_MAX		2048
 
-#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWP"
+#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPN"
 
 extern char ___assert_task_state[1 - 2*!!(
 		sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)];
@@ -226,6 +230,8 @@ extern char ___assert_task_state[1 - 2*!!(
 #define TASK_STOPPED		(TASK_WAKEKILL | __TASK_STOPPED)
 #define TASK_TRACED		(TASK_WAKEKILL | __TASK_TRACED)
 
+#define TASK_IDLE		(TASK_UNINTERRUPTIBLE | TASK_NOLOAD)
+
 /* Convenience macros for the sake of wake_up */
 #define TASK_NORMAL		(TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)
 #define TASK_ALL		(TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED)
@@ -238,7 +244,8 @@ extern char ___assert_task_state[1 - 2*!!(
 #define task_is_stopped(task)	((task->state & __TASK_STOPPED) != 0)
 #define task_contributes_to_load(task)	\
 				((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
-				 (task->flags & PF_FROZEN) == 0)
+				 (task->flags & PF_FROZEN) == 0 && \
+				 (task->state & TASK_NOLOAD) == 0)
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 
@@ -250,7 +257,7 @@ extern char ___assert_task_state[1 - 2*!!(
 #define set_task_state(tsk, state_value)			\
 	do {							\
 		(tsk)->task_state_change = _THIS_IP_;		\
-		set_mb((tsk)->state, (state_value));		\
+		smp_store_mb((tsk)->state, (state_value));		\
 	} while (0)
 
 /*
@@ -272,7 +279,7 @@ extern char ___assert_task_state[1 - 2*!!(
 #define set_current_state(state_value)				\
 	do {							\
 		current->task_state_change = _THIS_IP_;		\
-		set_mb(current->state, (state_value));		\
+		smp_store_mb(current->state, (state_value));		\
 	} while (0)
 
 #else
@@ -280,7 +287,7 @@ extern char ___assert_task_state[1 - 2*!!(
 #define __set_task_state(tsk, state_value)		\
 	do { (tsk)->state = (state_value); } while (0)
 #define set_task_state(tsk, state_value)		\
-	set_mb((tsk)->state, (state_value))
+	smp_store_mb((tsk)->state, (state_value))
 
 /*
  * set_current_state() includes a barrier so that the write of current->state
@@ -296,7 +303,7 @@ extern char ___assert_task_state[1 - 2*!!(
 #define __set_current_state(state_value)		\
 	do { current->state = (state_value); } while (0)
 #define set_current_state(state_value)			\
-	set_mb(current->state, (state_value))
+	smp_store_mb(current->state, (state_value))
 
 #endif
 
@@ -338,14 +345,10 @@ extern int runqueue_is_locked(int cpu);
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
 extern void nohz_balance_enter_idle(int cpu);
 extern void set_cpu_sd_state_idle(void);
-extern int get_nohz_timer_target(int pinned);
+extern int get_nohz_timer_target(void);
 #else
 static inline void nohz_balance_enter_idle(int cpu) { }
 static inline void set_cpu_sd_state_idle(void) { }
-static inline int get_nohz_timer_target(int pinned)
-{
-	return smp_processor_id();
-}
 #endif
 
 /*
@@ -382,6 +385,7 @@ 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)
@@ -481,9 +485,11 @@ 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 \
@@ -528,39 +534,49 @@ struct cpu_itimer {
 };
 
 /**
- * struct cputime - snaphsot of system and user cputime
+ * struct prev_cputime - snaphsot of system and user cputime
  * @utime: time spent in user mode
  * @stime: time spent in system mode
+ * @lock: protects the above two fields
  *
- * Gathers a generic snapshot of user and system time.
+ * Stores previous user/system time values such that we can guarantee
+ * monotonicity.
  */
-struct cputime {
+struct prev_cputime {
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	cputime_t utime;
 	cputime_t stime;
+	raw_spinlock_t lock;
+#endif
 };
 
+static inline void prev_cputime_init(struct prev_cputime *prev)
+{
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+	prev->utime = prev->stime = 0;
+	raw_spin_lock_init(&prev->lock);
+#endif
+}
+
 /**
  * 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 is an extension of struct cputime that includes the total runtime
- * spent by the task from the scheduler point of view.
- *
- * As a result, 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.
+ * 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 prof_exp	stime
 #define sched_exp	sum_exec_runtime
 
 #define INIT_CPUTIME	\
@@ -570,35 +586,59 @@ struct task_cputime {
 		.sum_exec_runtime = 0,				\
 	}
 
-#ifdef CONFIG_PREEMPT_COUNT
-#define PREEMPT_DISABLED	(1 + PREEMPT_ENABLED)
-#else
-#define PREEMPT_DISABLED	PREEMPT_ENABLED
-#endif
+/*
+ * This is the atomic variant of task_cputime, which can be used for
+ * storing and updating task_cputime statistics without locking.
+ */
+struct task_cputime_atomic {
+	atomic64_t utime;
+	atomic64_t stime;
+	atomic64_t sum_exec_runtime;
+};
+
+#define INIT_CPUTIME_ATOMIC \
+	(struct task_cputime_atomic) {				\
+		.utime = ATOMIC64_INIT(0),			\
+		.stime = ATOMIC64_INIT(0),			\
+		.sum_exec_runtime = ATOMIC64_INIT(0),		\
+	}
+
+#define PREEMPT_DISABLED	(PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED)
+
+/*
+ * 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
 
 /*
- * Disable preemption until the scheduler is running.
- * Reset by start_kernel()->sched_init()->init_idle().
+ * 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:		thread group interval timers.
- * @running:		non-zero when there are timers running and
- * 			@cputime receives updates.
- * @lock:		lock for fields in this struct.
+ * @cputime_atomic:	atomic thread group interval timers.
+ * @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 cputime;
-	int running;
-	raw_spinlock_t lock;
+	struct task_cputime_atomic cputime_atomic;
+	bool running;
+	bool checking_timer;
 };
 
 #include <linux/rwsem.h>
@@ -698,9 +738,7 @@ struct signal_struct {
 	cputime_t utime, stime, cutime, cstime;
 	cputime_t gtime;
 	cputime_t cgtime;
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-	struct cputime prev_cputime;
-#endif
+	struct prev_cputime prev_cputime;
 	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
 	unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
 	unsigned long inblock, oublock, cinblock, coublock;
@@ -737,18 +775,6 @@ 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 */
@@ -805,6 +831,7 @@ struct user_struct {
 	unsigned long mq_bytes;	/* How many bytes can be allocated to mqueue? */
 #endif
 	unsigned long locked_shm; /* How many pages of mlocked shm ? */
+	unsigned long unix_inflight;	/* How many files in flight in unix sockets */
 
 #ifdef CONFIG_KEYS
 	struct key *uid_keyring;	/* UID specific keyring */
@@ -815,7 +842,7 @@ 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
 };
@@ -831,7 +858,7 @@ extern struct user_struct root_user;
 struct backing_dev_info;
 struct reclaim_state;
 
-#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
+#ifdef CONFIG_SCHED_INFO
 struct sched_info {
 	/* cumulative counters */
 	unsigned long pcount;	      /* # of times run on this cpu */
@@ -841,7 +868,7 @@ struct sched_info {
 	unsigned long long last_arrival,/* when we last ran on a cpu */
 			   last_queued;	/* when we were last queued to run */
 };
-#endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */
+#endif /* CONFIG_SCHED_INFO */
 
 #ifdef CONFIG_TASK_DELAY_ACCT
 struct task_delay_info {
@@ -943,8 +970,18 @@ struct wake_q_head {
 	struct wake_q_head name = { WAKE_Q_TAIL, &name.first }
 
 extern void wake_q_add(struct wake_q_head *head,
-		       struct task_struct *task);
-extern void wake_up_q(struct wake_q_head *head);
+			      struct task_struct *task);
+extern void __wake_up_q(struct wake_q_head *head, bool sleeper);
+
+static inline void wake_up_q(struct wake_q_head *head)
+{
+	__wake_up_q(head, false);
+}
+
+static inline void wake_up_q_sleeper(struct wake_q_head *head)
+{
+	__wake_up_q(head, true);
+}
 
 /*
  * sched-domains (multiprocessor balancing) declarations:
@@ -1114,8 +1151,6 @@ 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);
 
@@ -1162,29 +1197,24 @@ struct load_weight {
 	u32 inv_weight;
 };
 
+/*
+ * The load_avg/util_avg accumulates an infinite geometric series.
+ * 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.
+ * The 64 bit load_sum can:
+ * 1) for cfs_rq, afford 4353082796 (=2^64/47742/88761) entities with
+ * the highest weight (=88761) always runnable, we should not overflow
+ * 2) for entity, support any load.weight always runnable
+ */
 struct sched_avg {
-	u64 last_runnable_update;
-	s64 decay_count;
-	/*
-	 * utilization_avg_contrib describes the amount of time that a
-	 * sched_entity is running on a CPU. It is based on running_avg_sum
-	 * and is scaled in the range [0..SCHED_LOAD_SCALE].
-	 * load_avg_contrib described the amount of time that a sched_entity
-	 * is runnable on a rq. It is based on both runnable_avg_sum and the
-	 * weight of the task.
-	 */
-	unsigned long load_avg_contrib, utilization_avg_contrib;
-	/*
-	 * These sums represent an infinite geometric series and so are bound
-	 * above by 1024/(1-y).  Thus we only need a u32 to store them for all
-	 * choices of y < 1-2^(-32)*1024.
-	 * running_avg_sum reflects the time that the sched_entity is
-	 * effectively running on the CPU.
-	 * runnable_avg_sum represents the amount of time a sched_entity is on
-	 * a runqueue which includes the running time that is monitored by
-	 * running_avg_sum.
-	 */
-	u32 runnable_avg_sum, avg_period, running_avg_sum;
+	u64 last_update_time, load_sum;
+	u32 util_sum, period_contrib;
+	unsigned long load_avg, util_avg;
 };
 
 #ifdef CONFIG_SCHEDSTATS
@@ -1250,7 +1280,7 @@ struct sched_entity {
 #endif
 
 #ifdef CONFIG_SMP
-	/* Per-entity load-tracking */
+	/* Per entity load average tracking */
 	struct sched_avg	avg;
 #endif
 };
@@ -1322,10 +1352,12 @@ 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;
 
@@ -1336,6 +1368,25 @@ enum perf_event_task_context {
 	perf_nr_task_contexts,
 };
 
+/* Track pages that require TLB flushes */
+struct tlbflush_unmap_batch {
+	/*
+	 * Each bit set is a CPU that potentially has a TLB entry for one of
+	 * the PFNs being flushed. See set_tlb_ubc_flush_pending().
+	 */
+	struct cpumask cpumask;
+
+	/* True if any bit in cpumask is set */
+	bool flush_required;
+
+	/*
+	 * If true then the PTE was dirty when unmapped. The entry must be
+	 * flushed before IO is initiated or a stale TLB entry potentially
+	 * allows an update without redirtying the page.
+	 */
+	bool writable;
+};
+
 struct task_struct {
 	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
 	volatile long saved_state;	/* saved state for "spinlock sleepers" */
@@ -1347,9 +1398,9 @@ struct task_struct {
 #ifdef CONFIG_SMP
 	struct llist_node wake_entry;
 	int on_cpu;
-	struct task_struct *last_wakee;
-	unsigned long wakee_flips;
+	unsigned int wakee_flips;
 	unsigned long wakee_flip_decay_ts;
+	struct task_struct *last_wakee;
 
 	int wake_cpu;
 #endif
@@ -1388,8 +1439,6 @@ struct task_struct {
 	int rcu_read_lock_nesting;
 	union rcu_special rcu_read_unlock_special;
 	struct list_head rcu_node_entry;
-#endif /* #ifdef CONFIG_PREEMPT_RCU */
-#ifdef CONFIG_PREEMPT_RCU
 	struct rcu_node *rcu_blocked_node;
 #endif /* #ifdef CONFIG_PREEMPT_RCU */
 #ifdef CONFIG_TASKS_RCU
@@ -1399,7 +1448,7 @@ struct task_struct {
 	int rcu_tasks_idle_cpu;
 #endif /* #ifdef CONFIG_TASKS_RCU */
 
-#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
+#ifdef CONFIG_SCHED_INFO
 	struct sched_info sched_info;
 #endif
 
@@ -1410,9 +1459,6 @@ struct task_struct {
 #endif
 
 	struct mm_struct *mm, *active_mm;
-#ifdef CONFIG_COMPAT_BRK
-	unsigned brk_randomized:1;
-#endif
 	/* per-thread vma caching */
 	u32 vmacache_seqnum;
 	struct vm_area_struct *vmacache[VMACACHE_SIZE];
@@ -1423,22 +1469,29 @@ struct task_struct {
 	int exit_state;
 	int exit_code, exit_signal;
 	int pdeath_signal;  /*  The signal sent when the parent dies  */
-	unsigned int jobctl;	/* JOBCTL_*, siglock protected */
+	unsigned long jobctl;	/* JOBCTL_*, siglock protected */
 
 	/* Used for emulating ABI behavior of previous Linux versions */
 	unsigned int personality;
 
-	unsigned in_execve:1;	/* Tell the LSMs that the process is doing an
-				 * execve */
-	unsigned in_iowait:1;
-
-	/* Revert to default priority/policy when forking */
+	/* scheduler bits, serialized by scheduler locks */
 	unsigned sched_reset_on_fork:1;
 	unsigned sched_contributes_to_load:1;
+	unsigned sched_migrated:1;
+	unsigned :0; /* force alignment to the next boundary */
 
+	/* unserialized, strictly 'current' */
+	unsigned in_execve:1; /* bit to tell LSMs we're in execve */
+	unsigned in_iowait:1;
+#ifdef CONFIG_MEMCG
+	unsigned memcg_may_oom:1;
+#endif
 #ifdef CONFIG_MEMCG_KMEM
 	unsigned memcg_kmem_skip_account:1;
 #endif
+#ifdef CONFIG_COMPAT_BRK
+	unsigned brk_randomized:1;
+#endif
 
 	unsigned long atomic_flags; /* Flags needing atomic access. */
 
@@ -1484,9 +1537,7 @@ struct task_struct {
 
 	cputime_t utime, stime, utimescaled, stimescaled;
 	cputime_t gtime;
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-	struct cputime prev_cputime;
-#endif
+	struct prev_cputime prev_cputime;
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 	raw_spinlock_t vtime_lock;
 	seqcount_t vtime_seq;
@@ -1519,7 +1570,7 @@ struct task_struct {
 				       it with task_lock())
 				     - initialized normally by setup_new_exec */
 /* file system info */
-	int link_count, total_link_count;
+	struct nameidata *nameidata;
 #ifdef CONFIG_SYSVIPC
 /* ipc stuff */
 	struct sysv_sem sysvsem;
@@ -1529,8 +1580,6 @@ struct task_struct {
 /* hung task detection */
 	unsigned long last_switch_count;
 #endif
-/* CPU-specific state of this task */
-	struct thread_struct thread;
 /* filesystem information */
 	struct fs_struct *fs;
 /* open file information */
@@ -1552,9 +1601,7 @@ 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;
@@ -1713,6 +1760,10 @@ struct task_struct {
 	unsigned long numa_pages_migrated;
 #endif /* CONFIG_NUMA_BALANCING */
 
+#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+	struct tlbflush_unmap_batch tlb_ubc;
+#endif
+
 	struct rcu_head rcu;
 
 	/*
@@ -1778,12 +1829,12 @@ struct task_struct {
 #endif
 #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;
@@ -1806,9 +1857,26 @@ struct task_struct {
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 	unsigned long	task_state_change;
 #endif
+#ifdef CONFIG_PREEMPT_RT_FULL
+	int xmit_recursion;
+#endif
 	int pagefault_disabled;
+/* CPU-specific state of this task */
+	struct thread_struct thread;
+/*
+ * WARNING: on x86, 'thread_struct' contains a variable-sized
+ * structure.  It *MUST* be at the end of 'task_struct'.
+ *
+ * Do not put anything below here!
+ */
 };
 
+#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
+extern int arch_task_struct_size __read_mostly;
+#else
+# define arch_task_struct_size (sizeof(struct task_struct))
+#endif
+
 #define TNF_MIGRATED	0x01
 #define TNF_NO_GROUP	0x02
 #define TNF_SHARED	0x04
@@ -1980,7 +2048,8 @@ static inline int pid_alive(const struct task_struct *p)
 }
 
 /**
- * is_global_init - check if a task structure is init
+ * is_global_init - check if a task structure is init. Since init
+ * is free to have sub-threads we need to check tgid.
  * @tsk: Task structure to be checked.
  *
  * Check if a task structure is the first user space task the kernel created.
@@ -1989,7 +2058,7 @@ static inline int pid_alive(const struct task_struct *p)
  */
 static inline int is_global_init(struct task_struct *tsk)
 {
-	return tsk->pid == 1;
+	return task_tgid_nr(tsk) == 1;
 }
 
 extern struct pid *cad_pid;
@@ -2168,22 +2237,22 @@ TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab)
 #define JOBCTL_TRAPPING_BIT	21	/* switching to TRACED */
 #define JOBCTL_LISTENING_BIT	22	/* ptracer is listening for events */
 
-#define JOBCTL_STOP_DEQUEUED	(1 << JOBCTL_STOP_DEQUEUED_BIT)
-#define JOBCTL_STOP_PENDING	(1 << JOBCTL_STOP_PENDING_BIT)
-#define JOBCTL_STOP_CONSUME	(1 << JOBCTL_STOP_CONSUME_BIT)
-#define JOBCTL_TRAP_STOP	(1 << JOBCTL_TRAP_STOP_BIT)
-#define JOBCTL_TRAP_NOTIFY	(1 << JOBCTL_TRAP_NOTIFY_BIT)
-#define JOBCTL_TRAPPING		(1 << JOBCTL_TRAPPING_BIT)
-#define JOBCTL_LISTENING	(1 << JOBCTL_LISTENING_BIT)
+#define JOBCTL_STOP_DEQUEUED	(1UL << JOBCTL_STOP_DEQUEUED_BIT)
+#define JOBCTL_STOP_PENDING	(1UL << JOBCTL_STOP_PENDING_BIT)
+#define JOBCTL_STOP_CONSUME	(1UL << JOBCTL_STOP_CONSUME_BIT)
+#define JOBCTL_TRAP_STOP	(1UL << JOBCTL_TRAP_STOP_BIT)
+#define JOBCTL_TRAP_NOTIFY	(1UL << JOBCTL_TRAP_NOTIFY_BIT)
+#define JOBCTL_TRAPPING		(1UL << JOBCTL_TRAPPING_BIT)
+#define JOBCTL_LISTENING	(1UL << JOBCTL_LISTENING_BIT)
 
 #define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
 #define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
 
 extern bool task_set_jobctl_pending(struct task_struct *task,
-				    unsigned int mask);
+				    unsigned long mask);
 extern void task_clear_jobctl_trapping(struct task_struct *task);
 extern void task_clear_jobctl_pending(struct task_struct *task,
-				      unsigned int mask);
+				      unsigned long mask);
 
 static inline void rcu_copy_process(struct task_struct *p)
 {
@@ -2246,13 +2315,6 @@ static inline void calc_load_enter_idle(void) { }
 static inline void calc_load_exit_idle(void) { }
 #endif /* CONFIG_NO_HZ_COMMON */
 
-#ifndef CONFIG_CPUMASK_OFFSTACK
-static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
-{
-	return set_cpus_allowed_ptr(p, &new_mask);
-}
-#endif
-
 /*
  * Do not use outside of architecture code which knows its limitations.
  *
@@ -2464,26 +2526,33 @@ extern void sched_dead(struct task_struct *p);
 
 extern void proc_caches_init(void);
 extern void flush_signals(struct task_struct *);
-extern void __flush_signals(struct task_struct *);
 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 *);
@@ -2600,8 +2669,22 @@ extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode);
 /* Remove the current tasks stale references to the old mm_struct */
 extern void mm_release(struct task_struct *, struct mm_struct *);
 
+#ifdef CONFIG_HAVE_COPY_THREAD_TLS
+extern int copy_thread_tls(unsigned long, unsigned long, unsigned long,
+			struct task_struct *, unsigned long);
+#else
 extern int copy_thread(unsigned long, unsigned long, unsigned long,
 			struct task_struct *);
+
+/* Architectures that haven't opted into copy_thread_tls get the tls argument
+ * via pt_regs, so ignore the tls argument passed via C. */
+static inline int copy_thread_tls(
+		unsigned long clone_flags, unsigned long sp, unsigned long arg,
+		struct task_struct *p, unsigned long tls)
+{
+	return copy_thread(clone_flags, sp, arg, p);
+}
+#endif
 extern void flush_thread(void);
 extern void exit_thread(void);
 
@@ -2620,6 +2703,7 @@ extern int do_execveat(int, struct filename *,
 		       const char __user * const __user *,
 		       const char __user * const __user *,
 		       int);
+extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *, unsigned long);
 extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
 struct task_struct *fork_idle(int);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
@@ -2643,6 +2727,9 @@ static inline unsigned long wait_task_inactive(struct task_struct *p,
 }
 #endif
 
+#define tasklist_empty() \
+	list_empty(&init_task.tasks)
+
 #define next_task(p) \
 	list_entry_rcu((p)->tasks.next, struct task_struct, tasks)
 
@@ -2751,53 +2838,33 @@ static inline void unlock_task_sighand(struct task_struct *tsk,
 	spin_unlock_irqrestore(&tsk->sighand->siglock, *flags);
 }
 
-#ifdef CONFIG_CGROUPS
-static inline void threadgroup_change_begin(struct task_struct *tsk)
-{
-	down_read(&tsk->signal->group_rwsem);
-}
-static inline void threadgroup_change_end(struct task_struct *tsk)
-{
-	up_read(&tsk->signal->group_rwsem);
-}
-
 /**
- * threadgroup_lock - lock threadgroup
- * @tsk: member task of the threadgroup to lock
+ * threadgroup_change_begin - mark the beginning of changes to a threadgroup
+ * @tsk: task causing the changes
  *
- * Lock the threadgroup @tsk belongs to.  No new task is allowed to enter
- * and member tasks aren't allowed to exit (as indicated by PF_EXITING) or
- * change ->group_leader/pid.  This is useful for cases where the threadgroup
- * needs to stay stable across blockable operations.
- *
- * fork and exit paths explicitly call threadgroup_change_{begin|end}() for
- * synchronization.  While held, no new task will be added to threadgroup
- * and no existing live task will have its PF_EXITING set.
- *
- * de_thread() does threadgroup_change_{begin|end}() when a non-leader
- * sub-thread becomes a new leader.
+ * All operations which modify a threadgroup - a new thread joining the
+ * group, death of a member thread (the assertion of PF_EXITING) and
+ * exec(2) dethreading the process and replacing the leader - are wrapped
+ * by threadgroup_change_{begin|end}().  This is to provide a place which
+ * subsystems needing threadgroup stability can hook into for
+ * synchronization.
  */
-static inline void threadgroup_lock(struct task_struct *tsk)
+static inline void threadgroup_change_begin(struct task_struct *tsk)
 {
-	down_write(&tsk->signal->group_rwsem);
+	might_sleep();
+	cgroup_threadgroup_change_begin(tsk);
 }
 
 /**
- * threadgroup_unlock - unlock threadgroup
- * @tsk: member task of the threadgroup to unlock
+ * threadgroup_change_end - mark the end of changes to a threadgroup
+ * @tsk: task causing the changes
  *
- * Reverse threadgroup_lock().
+ * See threadgroup_change_begin().
  */
-static inline void threadgroup_unlock(struct task_struct *tsk)
+static inline void threadgroup_change_end(struct task_struct *tsk)
 {
-	up_write(&tsk->signal->group_rwsem);
+	cgroup_threadgroup_change_end(tsk);
 }
-#else
-static inline void threadgroup_change_begin(struct task_struct *tsk) {}
-static inline void threadgroup_change_end(struct task_struct *tsk) {}
-static inline void threadgroup_lock(struct task_struct *tsk) {}
-static inline void threadgroup_unlock(struct task_struct *tsk) {}
-#endif
 
 #ifndef __HAVE_THREAD_FUNCTIONS
 
@@ -3027,12 +3094,6 @@ extern int _cond_resched(void);
 
 extern int __cond_resched_lock(spinlock_t *lock);
 
-#if defined(CONFIG_PREEMPT_COUNT) && !defined(CONFIG_PREEMPT_RT_FULL)
-#define PREEMPT_LOCK_OFFSET	PREEMPT_OFFSET
-#else
-#define PREEMPT_LOCK_OFFSET	0
-#endif
-
 #define cond_resched_lock(lock) ({				\
 	___might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);\
 	__cond_resched_lock(lock);				\
@@ -3159,11 +3220,6 @@ static __always_inline bool need_resched(void)
 void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times);
 void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
 
-static inline void thread_group_cputime_init(struct signal_struct *sig)
-{
-	raw_spin_lock_init(&sig->cputimer.lock);
-}
-
 /*
  * Reevaluate whether the task has signals pending delivery.
  * Wake the task if so.
@@ -3226,14 +3282,19 @@ static inline int __migrate_disabled(struct task_struct *p)
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
 static inline const struct cpumask *tsk_cpus_allowed(struct task_struct *p)
 {
-#ifdef CONFIG_PREEMPT_RT_FULL
-	if (p->migrate_disable)
+	if (__migrate_disabled(p))
 		return cpumask_of(task_cpu(p));
-#endif
 
 	return &p->cpus_allowed;
 }
 
+static inline int tsk_nr_cpus_allowed(struct task_struct *p)
+{
+	if (__migrate_disabled(p))
+		return 1;
+	return p->nr_cpus_allowed;
+}
+
 extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
 extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
 
@@ -3297,13 +3358,13 @@ static inline void mm_update_next_owner(struct mm_struct *mm)
 static inline unsigned long task_rlimit(const struct task_struct *tsk,
 		unsigned int limit)
 {
-	return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_cur);
+	return READ_ONCE(tsk->signal->rlim[limit].rlim_cur);
 }
 
 static inline unsigned long task_rlimit_max(const struct task_struct *tsk,
 		unsigned int limit)
 {
-	return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_max);
+	return READ_ONCE(tsk->signal->rlim[limit].rlim_max);
 }
 
 static inline unsigned long rlimit(unsigned int limit)