Merge branch 'next' into for-linus

Prepare input updates for 5.12 merge window.

10 files changed, 262 insertions, 74 deletions

diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
index ecdc6542070f..dfd82eab2902 100644
--- a/include/linux/sched/coredump.h
+++ b/include/linux/sched/coredump.h
@@ -72,6 +72,7 @@ static inline int get_dumpable(struct mm_struct *mm)
 #define MMF_DISABLE_THP		24	/* disable THP for all VMAs */
 #define MMF_OOM_VICTIM		25	/* mm is the oom victim */
 #define MMF_OOM_REAP_QUEUED	26	/* mm was queued for oom_reaper */
+#define MMF_MULTIPROCESS	27	/* mm is shared between processes */
 #define MMF_DISABLE_THP_MASK	(1 << MMF_DISABLE_THP)
 
 #define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h
index 3ed5aa18593f..6205578ab6ee 100644
--- a/include/linux/sched/cpufreq.h
+++ b/include/linux/sched/cpufreq.h
@@ -28,6 +28,11 @@ static inline unsigned long map_util_freq(unsigned long util,
 {
 	return (freq + (freq >> 2)) * util / cap;
 }
+
+static inline unsigned long map_util_perf(unsigned long util)
+{
+	return util + (util >> 2);
+}
 #endif /* CONFIG_CPU_FREQ */
 
 #endif /* _LINUX_SCHED_CPUFREQ_H */
diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h
index 00c45a0e6abe..ae51f4529fc9 100644
--- a/include/linux/sched/debug.h
+++ b/include/linux/sched/debug.h
@@ -43,7 +43,7 @@ extern void proc_sched_set_task(struct task_struct *p);
 #endif
 
 /* Attach to any functions which should be ignored in wchan output. */
-#define __sched		__attribute__((__section__(".sched.text")))
+#define __sched		__section(".sched.text")
 
 /* Linker adds these: start and end of __sched functions */
 extern char __sched_text_start[], __sched_text_end[];
diff --git a/include/linux/sched/hotplug.h b/include/linux/sched/hotplug.h
index 9a62ffdd296f..412cdaba33eb 100644
--- a/include/linux/sched/hotplug.h
+++ b/include/linux/sched/hotplug.h
@@ -11,8 +11,10 @@ extern int sched_cpu_activate(unsigned int cpu);
 extern int sched_cpu_deactivate(unsigned int cpu);
 
 #ifdef CONFIG_HOTPLUG_CPU
+extern int sched_cpu_wait_empty(unsigned int cpu);
 extern int sched_cpu_dying(unsigned int cpu);
 #else
+# define sched_cpu_wait_empty	NULL
 # define sched_cpu_dying	NULL
 #endif
 
diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h
index d2b4204ba4d3..fa067de9f1a9 100644
--- a/include/linux/sched/jobctl.h
+++ b/include/linux/sched/jobctl.h
@@ -19,7 +19,6 @@ struct task_struct;
 #define JOBCTL_TRAPPING_BIT	21	/* switching to TRACED */
 #define JOBCTL_LISTENING_BIT	22	/* ptracer is listening for events */
 #define JOBCTL_TRAP_FREEZE_BIT	23	/* trap for cgroup freezer */
-#define JOBCTL_TASK_WORK_BIT	24	/* set by TWA_SIGNAL */
 
 #define JOBCTL_STOP_DEQUEUED	(1UL << JOBCTL_STOP_DEQUEUED_BIT)
 #define JOBCTL_STOP_PENDING	(1UL << JOBCTL_STOP_PENDING_BIT)
@@ -29,10 +28,9 @@ struct task_struct;
 #define JOBCTL_TRAPPING		(1UL << JOBCTL_TRAPPING_BIT)
 #define JOBCTL_LISTENING	(1UL << JOBCTL_LISTENING_BIT)
 #define JOBCTL_TRAP_FREEZE	(1UL << JOBCTL_TRAP_FREEZE_BIT)
-#define JOBCTL_TASK_WORK	(1UL << JOBCTL_TASK_WORK_BIT)
 
 #define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
-#define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK | JOBCTL_TASK_WORK)
+#define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
 
 extern bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask);
 extern void task_clear_jobctl_trapping(struct task_struct *task);
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index f889e332912f..1ae08b8462a4 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -49,31 +49,6 @@ static inline void mmdrop(struct mm_struct *mm)
 		__mmdrop(mm);
 }
 
-/*
- * This has to be called after a get_task_mm()/mmget_not_zero()
- * followed by taking the mmap_lock for writing before modifying the
- * vmas or anything the coredump pretends not to change from under it.
- *
- * It also has to be called when mmgrab() is used in the context of
- * the process, but then the mm_count refcount is transferred outside
- * the context of the process to run down_write() on that pinned mm.
- *
- * NOTE: find_extend_vma() called from GUP context is the only place
- * that can modify the "mm" (notably the vm_start/end) under mmap_lock
- * for reading and outside the context of the process, so it is also
- * the only case that holds the mmap_lock for reading that must call
- * this function. Generally if the mmap_lock is hold for reading
- * there's no need of this check after get_task_mm()/mmget_not_zero().
- *
- * This function can be obsoleted and the check can be removed, after
- * the coredump code will hold the mmap_lock for writing before
- * invoking the ->core_dump methods.
- */
-static inline bool mmget_still_valid(struct mm_struct *mm)
-{
-	return likely(!mm->core_state);
-}
-
 /**
  * mmget() - Pin the address space associated with a &struct mm_struct.
  * @mm: The address space to pin.
@@ -206,6 +181,22 @@ static inline void fs_reclaim_release(gfp_t gfp_mask) { }
 #endif
 
 /**
+ * might_alloc - Mark possible allocation sites
+ * @gfp_mask: gfp_t flags that would be used to allocate
+ *
+ * Similar to might_sleep() and other annotations, this can be used in functions
+ * that might allocate, but often don't. Compiles to nothing without
+ * CONFIG_LOCKDEP. Includes a conditional might_sleep() if @gfp allows blocking.
+ */
+static inline void might_alloc(gfp_t gfp_mask)
+{
+	fs_reclaim_acquire(gfp_mask);
+	fs_reclaim_release(gfp_mask);
+
+	might_sleep_if(gfpflags_allow_blocking(gfp_mask));
+}
+
+/**
  * memalloc_noio_save - Marks implicit GFP_NOIO allocation scope.
  *
  * This functions marks the beginning of the GFP_NOIO allocation scope.
@@ -304,39 +295,38 @@ static inline void memalloc_nocma_restore(unsigned int flags)
 #endif
 
 #ifdef CONFIG_MEMCG
+DECLARE_PER_CPU(struct mem_cgroup *, int_active_memcg);
 /**
- * memalloc_use_memcg - Starts the remote memcg charging scope.
+ * set_active_memcg - Starts the remote memcg charging scope.
  * @memcg: memcg to charge.
  *
  * This function marks the beginning of the remote memcg charging scope. All the
  * __GFP_ACCOUNT allocations till the end of the scope will be charged to the
  * given memcg.
  *
- * NOTE: This function is not nesting safe.
+ * NOTE: This function can nest. Users must save the return value and
+ * reset the previous value after their own charging scope is over.
  */
-static inline void memalloc_use_memcg(struct mem_cgroup *memcg)
+static inline struct mem_cgroup *
+set_active_memcg(struct mem_cgroup *memcg)
 {
-	WARN_ON_ONCE(current->active_memcg);
-	current->active_memcg = memcg;
-}
+	struct mem_cgroup *old;
+
+	if (in_interrupt()) {
+		old = this_cpu_read(int_active_memcg);
+		this_cpu_write(int_active_memcg, memcg);
+	} else {
+		old = current->active_memcg;
+		current->active_memcg = memcg;
+	}
 
-/**
- * memalloc_unuse_memcg - Ends the remote memcg charging scope.
- *
- * This function marks the end of the remote memcg charging scope started by
- * memalloc_use_memcg().
- */
-static inline void memalloc_unuse_memcg(void)
-{
-	current->active_memcg = NULL;
+	return old;
 }
 #else
-static inline void memalloc_use_memcg(struct mem_cgroup *memcg)
-{
-}
-
-static inline void memalloc_unuse_memcg(void)
+static inline struct mem_cgroup *
+set_active_memcg(struct mem_cgroup *memcg)
 {
+	return NULL;
 }
 #endif
 
@@ -348,10 +338,13 @@ enum {
 	MEMBARRIER_STATE_GLOBAL_EXPEDITED			= (1U << 3),
 	MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY	= (1U << 4),
 	MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE		= (1U << 5),
+	MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY		= (1U << 6),
+	MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ			= (1U << 7),
 };
 
 enum {
 	MEMBARRIER_FLAG_SYNC_CORE	= (1U << 0),
+	MEMBARRIER_FLAG_RSEQ		= (1U << 1),
 };
 
 #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS
@@ -370,6 +363,8 @@ static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
 
 extern void membarrier_exec_mmap(struct mm_struct *mm);
 
+extern void membarrier_update_current_mm(struct mm_struct *next_mm);
+
 #else
 #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS
 static inline void membarrier_arch_switch_mm(struct mm_struct *prev,
@@ -384,6 +379,9 @@ static inline void membarrier_exec_mmap(struct mm_struct *mm)
 static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
 {
 }
+static inline void membarrier_update_current_mm(struct mm_struct *next_mm)
+{
+}
 #endif
 
 #endif /* _LINUX_SCHED_MM_H */
diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h
new file mode 100644
index 000000000000..34b21e971d77
--- /dev/null
+++ b/include/linux/sched/sd_flags.h
@@ -0,0 +1,156 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * sched-domains (multiprocessor balancing) flag declarations.
+ */
+
+#ifndef SD_FLAG
+# error "Incorrect import of SD flags definitions"
+#endif
+
+/*
+ * Hierarchical metaflags
+ *
+ * SHARED_CHILD: These flags are meant to be set from the base domain upwards.
+ * If a domain has this flag set, all of its children should have it set. This
+ * is usually because the flag describes some shared resource (all CPUs in that
+ * domain share the same resource), or because they are tied to a scheduling
+ * behaviour that we want to disable at some point in the hierarchy for
+ * scalability reasons.
+ *
+ * In those cases it doesn't make sense to have the flag set for a domain but
+ * not have it in (some of) its children: sched domains ALWAYS span their child
+ * domains, so operations done with parent domains will cover CPUs in the lower
+ * child domains.
+ *
+ *
+ * SHARED_PARENT: These flags are meant to be set from the highest domain
+ * downwards. If a domain has this flag set, all of its parents should have it
+ * set. This is usually for topology properties that start to appear above a
+ * certain level (e.g. domain starts spanning CPUs outside of the base CPU's
+ * socket).
+ */
+#define SDF_SHARED_CHILD       0x1
+#define SDF_SHARED_PARENT      0x2
+
+/*
+ * Behavioural metaflags
+ *
+ * NEEDS_GROUPS: These flags are only relevant if the domain they are set on has
+ * more than one group. This is usually for balancing flags (load balancing
+ * involves equalizing a metric between groups), or for flags describing some
+ * shared resource (which would be shared between groups).
+ */
+#define SDF_NEEDS_GROUPS       0x4
+
+/*
+ * Balance when about to become idle
+ *
+ * SHARED_CHILD: Set from the base domain up to cpuset.sched_relax_domain_level.
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_BALANCE_NEWIDLE, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Balance on exec
+ *
+ * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level.
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_BALANCE_EXEC, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Balance on fork, clone
+ *
+ * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level.
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_BALANCE_FORK, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Balance on wakeup
+ *
+ * SHARED_CHILD: Set from the base domain up to cpuset.sched_relax_domain_level.
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_BALANCE_WAKE, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Consider waking task on waking CPU.
+ *
+ * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level.
+ */
+SD_FLAG(SD_WAKE_AFFINE, SDF_SHARED_CHILD)
+
+/*
+ * Domain members have different CPU capacities
+ *
+ * SHARED_PARENT: Set from the topmost domain down to the first domain where
+ *                asymmetry is detected.
+ * NEEDS_GROUPS: Per-CPU capacity is asymmetric between groups.
+ */
+SD_FLAG(SD_ASYM_CPUCAPACITY, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
+
+/*
+ * Domain members share CPU capacity (i.e. SMT)
+ *
+ * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share
+ *               CPU capacity.
+ * NEEDS_GROUPS: Capacity is shared between groups.
+ */
+SD_FLAG(SD_SHARE_CPUCAPACITY, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Domain members share CPU package resources (i.e. caches)
+ *
+ * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share
+ *               the same cache(s).
+ * NEEDS_GROUPS: Caches are shared between groups.
+ */
+SD_FLAG(SD_SHARE_PKG_RESOURCES, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Only a single load balancing instance
+ *
+ * SHARED_PARENT: Set for all NUMA levels above NODE. Could be set from a
+ *                different level upwards, but it doesn't change that if a
+ *                domain has this flag set, then all of its parents need to have
+ *                it too (otherwise the serialization doesn't make sense).
+ * NEEDS_GROUPS: No point in preserving domain if it has a single group.
+ */
+SD_FLAG(SD_SERIALIZE, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
+
+/*
+ * Place busy tasks earlier in the domain
+ *
+ * SHARED_CHILD: Usually set on the SMT level. Technically could be set further
+ *               up, but currently assumed to be set from the base domain
+ *               upwards (see update_top_cache_domain()).
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_ASYM_PACKING, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+
+/*
+ * Prefer to place tasks in a sibling domain
+ *
+ * Set up until domains start spanning NUMA nodes. Close to being a SHARED_CHILD
+ * flag, but cleared below domains with SD_ASYM_CPUCAPACITY.
+ *
+ * NEEDS_GROUPS: Load balancing flag.
+ */
+SD_FLAG(SD_PREFER_SIBLING, SDF_NEEDS_GROUPS)
+
+/*
+ * sched_groups of this level overlap
+ *
+ * SHARED_PARENT: Set for all NUMA levels above NODE.
+ * NEEDS_GROUPS: Overlaps can only exist with more than one group.
+ */
+SD_FLAG(SD_OVERLAP, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
+
+/*
+ * Cross-node balancing
+ *
+ * SHARED_PARENT: Set for all NUMA levels above NODE.
+ * NEEDS_GROUPS: No point in preserving domain if it has a single group.
+ */
+SD_FLAG(SD_NUMA, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 1bad18a1d8ba..3f6a0fcaa10c 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -228,12 +228,13 @@ struct signal_struct {
 					 * credential calculations
 					 * (notably. ptrace)
 					 * Deprecated do not use in new code.
-					 * Use exec_update_mutex instead.
-					 */
-	struct mutex exec_update_mutex;	/* Held while task_struct is being
-					 * updated during exec, and may have
-					 * inconsistent permissions.
+					 * Use exec_update_lock instead.
 					 */
+	struct rw_semaphore exec_update_lock;	/* Held while task_struct is
+						 * being updated during exec,
+						 * and may have inconsistent
+						 * permissions.
+						 */
 } __randomize_layout;
 
 /*
@@ -353,11 +354,23 @@ static inline int restart_syscall(void)
 	return -ERESTARTNOINTR;
 }
 
-static inline int signal_pending(struct task_struct *p)
+static inline int task_sigpending(struct task_struct *p)
 {
 	return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
 }
 
+static inline int signal_pending(struct task_struct *p)
+{
+	/*
+	 * TIF_NOTIFY_SIGNAL isn't really a signal, but it requires the same
+	 * behavior in terms of ensuring that we break out of wait loops
+	 * so that notify signal callbacks can be processed.
+	 */
+	if (unlikely(test_tsk_thread_flag(p, TIF_NOTIFY_SIGNAL)))
+		return 1;
+	return task_sigpending(p);
+}
+
 static inline int __fatal_signal_pending(struct task_struct *p)
 {
 	return unlikely(sigismember(&p->pending.signal, SIGKILL));
@@ -365,7 +378,7 @@ static inline int __fatal_signal_pending(struct task_struct *p)
 
 static inline int fatal_signal_pending(struct task_struct *p)
 {
-	return signal_pending(p) && __fatal_signal_pending(p);
+	return task_sigpending(p) && __fatal_signal_pending(p);
 }
 
 static inline int signal_pending_state(long state, struct task_struct *p)
@@ -502,7 +515,7 @@ extern int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize);
 static inline void restore_saved_sigmask_unless(bool interrupted)
 {
 	if (interrupted)
-		WARN_ON(!test_thread_flag(TIF_SIGPENDING));
+		WARN_ON(!signal_pending(current));
 	else
 		restore_saved_sigmask();
 }
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index a98965007eef..c0f71f2e7160 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -47,9 +47,7 @@ extern spinlock_t mmlist_lock;
 extern union thread_union init_thread_union;
 extern struct task_struct init_task;
 
-#ifdef CONFIG_PROVE_RCU
 extern int lockdep_tasklist_lock_is_held(void);
-#endif /* #ifdef CONFIG_PROVE_RCU */
 
 extern asmlinkage void schedule_tail(struct task_struct *prev);
 extern void init_idle(struct task_struct *idle, int cpu);
@@ -83,7 +81,7 @@ extern void do_group_exit(int);
 extern void exit_files(struct task_struct *);
 extern void exit_itimers(struct signal_struct *);
 
-extern long _do_fork(struct kernel_clone_args *kargs);
+extern pid_t kernel_clone(struct kernel_clone_args *kargs);
 struct task_struct *fork_idle(int);
 struct mm_struct *copy_init_mm(void);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 820511289857..8f0f778b7c91 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -11,20 +11,29 @@
  */
 #ifdef CONFIG_SMP
 
-#define SD_BALANCE_NEWIDLE	0x0001	/* Balance when about to become idle */
-#define SD_BALANCE_EXEC		0x0002	/* Balance on exec */
-#define SD_BALANCE_FORK		0x0004	/* Balance on fork, clone */
-#define SD_BALANCE_WAKE		0x0008  /* Balance on wakeup */
-#define SD_WAKE_AFFINE		0x0010	/* Wake task to waking CPU */
-#define SD_ASYM_CPUCAPACITY	0x0020  /* Domain members have different CPU capacities */
-#define SD_SHARE_CPUCAPACITY	0x0040	/* Domain members share CPU capacity */
-#define SD_SHARE_POWERDOMAIN	0x0080	/* Domain members share power domain */
-#define SD_SHARE_PKG_RESOURCES	0x0100	/* Domain members share CPU pkg resources */
-#define SD_SERIALIZE		0x0200	/* Only a single load balancing instance */
-#define SD_ASYM_PACKING		0x0400  /* Place busy groups earlier in the domain */
-#define SD_PREFER_SIBLING	0x0800	/* Prefer to place tasks in a sibling domain */
-#define SD_OVERLAP		0x1000	/* sched_domains of this level overlap */
-#define SD_NUMA			0x2000	/* cross-node balancing */
+/* Generate SD flag indexes */
+#define SD_FLAG(name, mflags) __##name,
+enum {
+	#include <linux/sched/sd_flags.h>
+	__SD_FLAG_CNT,
+};
+#undef SD_FLAG
+/* Generate SD flag bits */
+#define SD_FLAG(name, mflags) name = 1 << __##name,
+enum {
+	#include <linux/sched/sd_flags.h>
+};
+#undef SD_FLAG
+
+#ifdef CONFIG_SCHED_DEBUG
+
+struct sd_flag_debug {
+	unsigned int meta_flags;
+	char *name;
+};
+extern const struct sd_flag_debug sd_flag_debug[];
+
+#endif
 
 #ifdef CONFIG_SCHED_SMT
 static inline int cpu_smt_flags(void)
@@ -216,6 +225,14 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu)
 
 #endif	/* !CONFIG_SMP */
 
+#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
+extern void rebuild_sched_domains_energy(void);
+#else
+static inline void rebuild_sched_domains_energy(void)
+{
+}
+#endif
+
 #ifndef arch_scale_cpu_capacity
 /**
  * arch_scale_cpu_capacity - get the capacity scale factor of a given CPU.