Merge tag 'v5.8.5' into dev-5.8dev-5.8

This is the 5.8.5 stable release

Signed-off-by: Joel Stanley <joel@jms.id.au>

27 files changed, 337 insertions, 86 deletions

diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c
index c69071e334bf..1a04c168563d 100644
--- a/kernel/bpf/map_iter.c
+++ b/kernel/bpf/map_iter.c
@@ -6,7 +6,7 @@
 #include <linux/kernel.h>
 
 struct bpf_iter_seq_map_info {
-	u32 mid;
+	u32 map_id;
 };
 
 static void *bpf_map_seq_start(struct seq_file *seq, loff_t *pos)
@@ -14,27 +14,23 @@ static void *bpf_map_seq_start(struct seq_file *seq, loff_t *pos)
 	struct bpf_iter_seq_map_info *info = seq->private;
 	struct bpf_map *map;
 
-	map = bpf_map_get_curr_or_next(&info->mid);
+	map = bpf_map_get_curr_or_next(&info->map_id);
 	if (!map)
 		return NULL;
 
-	++*pos;
+	if (*pos == 0)
+		++*pos;
 	return map;
 }
 
 static void *bpf_map_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct bpf_iter_seq_map_info *info = seq->private;
-	struct bpf_map *map;
 
 	++*pos;
-	++info->mid;
+	++info->map_id;
 	bpf_map_put((struct bpf_map *)v);
-	map = bpf_map_get_curr_or_next(&info->mid);
-	if (!map)
-		return NULL;
-
-	return map;
+	return bpf_map_get_curr_or_next(&info->map_id);
 }
 
 struct bpf_iter__bpf_map {
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index 4dbf2b6035f8..a4a0fb4f94cc 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -50,7 +50,8 @@ static void *task_seq_start(struct seq_file *seq, loff_t *pos)
 	if (!task)
 		return NULL;
 
-	++*pos;
+	if (*pos == 0)
+		++*pos;
 	return task;
 }
 
@@ -176,10 +177,11 @@ again:
 		f = fcheck_files(curr_files, curr_fd);
 		if (!f)
 			continue;
+		if (!get_file_rcu(f))
+			continue;
 
 		/* set info->fd */
 		info->fd = curr_fd;
-		get_file(f);
 		rcu_read_unlock();
 		return f;
 	}
@@ -209,7 +211,8 @@ static void *task_file_seq_start(struct seq_file *seq, loff_t *pos)
 		return NULL;
 	}
 
-	++*pos;
+	if (*pos == 0)
+		++*pos;
 	info->task = task;
 	info->files = files;
 
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 5f8b0c52fd2e..661333c2893d 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -205,7 +205,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 		try_to_free_swap(old_page);
 	page_vma_mapped_walk_done(&pvmw);
 
-	if (vma->vm_flags & VM_LOCKED)
+	if ((vma->vm_flags & VM_LOCKED) && !PageCompound(old_page))
 		munlock_vma_page(old_page);
 	put_page(old_page);
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 2a9fec53e159..e68a8f993106 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -320,12 +320,16 @@ static bool irq_set_affinity_deactivated(struct irq_data *data,
 	struct irq_desc *desc = irq_data_to_desc(data);
 
 	/*
+	 * Handle irq chips which can handle affinity only in activated
+	 * state correctly
+	 *
 	 * If the interrupt is not yet activated, just store the affinity
 	 * mask and do not call the chip driver at all. On activation the
 	 * driver has to make sure anyway that the interrupt is in a
 	 * useable state so startup works.
 	 */
-	if (!IS_ENABLED(CONFIG_IRQ_DOMAIN_HIERARCHY) || irqd_is_activated(data))
+	if (!IS_ENABLED(CONFIG_IRQ_DOMAIN_HIERARCHY) ||
+	    irqd_is_activated(data) || !irqd_affinity_on_activate(data))
 		return false;
 
 	cpumask_copy(desc->irq_common_data.affinity, mask);
@@ -2731,8 +2735,10 @@ int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
 
 	do {
 		chip = irq_data_get_irq_chip(data);
-		if (WARN_ON_ONCE(!chip))
-			return -ENODEV;
+		if (WARN_ON_ONCE(!chip)) {
+			err = -ENODEV;
+			goto out_unlock;
+		}
 		if (chip->irq_set_irqchip_state)
 			break;
 #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
@@ -2745,6 +2751,7 @@ int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
 	if (data)
 		err = chip->irq_set_irqchip_state(data, which, val);
 
+out_unlock:
 	irq_put_desc_busunlock(desc, flags);
 	return err;
 }
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index 8f557fa1f4fe..c6c7e187ae74 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -185,14 +185,18 @@ void rearm_wake_irq(unsigned int irq)
 	unsigned long flags;
 	struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
 
-	if (!desc || !(desc->istate & IRQS_SUSPENDED) ||
-	    !irqd_is_wakeup_set(&desc->irq_data))
+	if (!desc)
 		return;
 
+	if (!(desc->istate & IRQS_SUSPENDED) ||
+	    !irqd_is_wakeup_set(&desc->irq_data))
+		goto unlock;
+
 	desc->istate &= ~IRQS_SUSPENDED;
 	irqd_set(&desc->irq_data, IRQD_WAKEUP_ARMED);
 	__enable_irq(desc);
 
+unlock:
 	irq_put_desc_busunlock(desc, flags);
 }
 
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 2e97febeef77..72af5d37e9ff 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1079,9 +1079,20 @@ static int disarm_kprobe_ftrace(struct kprobe *p)
 		ipmodify ? &kprobe_ipmodify_enabled : &kprobe_ftrace_enabled);
 }
 #else	/* !CONFIG_KPROBES_ON_FTRACE */
-#define prepare_kprobe(p)	arch_prepare_kprobe(p)
-#define arm_kprobe_ftrace(p)	(-ENODEV)
-#define disarm_kprobe_ftrace(p)	(-ENODEV)
+static inline int prepare_kprobe(struct kprobe *p)
+{
+	return arch_prepare_kprobe(p);
+}
+
+static inline int arm_kprobe_ftrace(struct kprobe *p)
+{
+	return -ENODEV;
+}
+
+static inline int disarm_kprobe_ftrace(struct kprobe *p)
+{
+	return -ENODEV;
+}
 #endif
 
 /* Arm a kprobe with text_mutex */
@@ -2113,6 +2124,13 @@ static void kill_kprobe(struct kprobe *p)
 	 * the original probed function (which will be freed soon) any more.
 	 */
 	arch_remove_kprobe(p);
+
+	/*
+	 * The module is going away. We should disarm the kprobe which
+	 * is using ftrace.
+	 */
+	if (kprobe_ftrace(p))
+		disarm_kprobe_ftrace(p);
 }
 
 /* Disable one kprobe */
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 132f84a5fde3..f481ab35de2f 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -1239,13 +1239,16 @@ void kthread_use_mm(struct mm_struct *mm)
 	WARN_ON_ONCE(tsk->mm);
 
 	task_lock(tsk);
+	/* Hold off tlb flush IPIs while switching mm's */
+	local_irq_disable();
 	active_mm = tsk->active_mm;
 	if (active_mm != mm) {
 		mmgrab(mm);
 		tsk->active_mm = mm;
 	}
 	tsk->mm = mm;
-	switch_mm(active_mm, mm, tsk);
+	switch_mm_irqs_off(active_mm, mm, tsk);
+	local_irq_enable();
 	task_unlock(tsk);
 #ifdef finish_arch_post_lock_switch
 	finish_arch_post_lock_switch();
@@ -1274,9 +1277,11 @@ void kthread_unuse_mm(struct mm_struct *mm)
 
 	task_lock(tsk);
 	sync_mm_rss(mm);
+	local_irq_disable();
 	tsk->mm = NULL;
 	/* active_mm is still 'mm' */
 	enter_lazy_tlb(mm, tsk);
+	local_irq_enable();
 	task_unlock(tsk);
 }
 EXPORT_SYMBOL_GPL(kthread_unuse_mm);
diff --git a/kernel/module.c b/kernel/module.c
index aa183c9ac0a2..08c46084d8cc 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1520,18 +1520,34 @@ struct module_sect_attrs {
 	struct module_sect_attr attrs[];
 };
 
+#define MODULE_SECT_READ_SIZE (3 /* "0x", "\n" */ + (BITS_PER_LONG / 4))
 static ssize_t module_sect_read(struct file *file, struct kobject *kobj,
 				struct bin_attribute *battr,
 				char *buf, loff_t pos, size_t count)
 {
 	struct module_sect_attr *sattr =
 		container_of(battr, struct module_sect_attr, battr);
+	char bounce[MODULE_SECT_READ_SIZE + 1];
+	size_t wrote;
 
 	if (pos != 0)
 		return -EINVAL;
 
-	return sprintf(buf, "0x%px\n",
-		       kallsyms_show_value(file->f_cred) ? (void *)sattr->address : NULL);
+	/*
+	 * Since we're a binary read handler, we must account for the
+	 * trailing NUL byte that sprintf will write: if "buf" is
+	 * too small to hold the NUL, or the NUL is exactly the last
+	 * byte, the read will look like it got truncated by one byte.
+	 * Since there is no way to ask sprintf nicely to not write
+	 * the NUL, we have to use a bounce buffer.
+	 */
+	wrote = scnprintf(bounce, sizeof(bounce), "0x%px\n",
+			 kallsyms_show_value(file->f_cred)
+				? (void *)sattr->address : NULL);
+	count = min(count, wrote);
+	memcpy(buf, bounce, count);
+
+	return count;
 }
 
 static void free_sect_attrs(struct module_sect_attrs *sect_attrs)
@@ -1580,7 +1596,7 @@ static void add_sect_attrs(struct module *mod, const struct load_info *info)
 			goto out;
 		sect_attrs->nsections++;
 		sattr->battr.read = module_sect_read;
-		sattr->battr.size = 3 /* "0x", "\n" */ + (BITS_PER_LONG / 4);
+		sattr->battr.size = MODULE_SECT_READ_SIZE;
 		sattr->battr.attr.mode = 0400;
 		*(gattr++) = &(sattr++)->battr;
 	}
diff --git a/kernel/pid.c b/kernel/pid.c
index f1496b757162..ee58530d1aca 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -42,6 +42,7 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/task.h>
 #include <linux/idr.h>
+#include <net/sock.h>
 
 struct pid init_struct_pid = {
 	.count		= REFCOUNT_INIT(1),
@@ -642,10 +643,12 @@ static int pidfd_getfd(struct pid *pid, int fd)
 	}
 
 	ret = get_unused_fd_flags(O_CLOEXEC);
-	if (ret < 0)
+	if (ret < 0) {
 		fput(file);
-	else
+	} else {
+		__receive_sock(file);
 		fd_install(ret, file);
+	}
 
 	return ret;
 }
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 6c6569e0586c..1e9e500ff790 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3105,7 +3105,7 @@ static void kfree_rcu_work(struct work_struct *work)
 static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp)
 {
 	struct kfree_rcu_cpu_work *krwp;
-	bool queued = false;
+	bool repeat = false;
 	int i;
 
 	lockdep_assert_held(&krcp->lock);
@@ -3143,11 +3143,14 @@ static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp)
 			 * been detached following each other, one by one.
 			 */
 			queue_rcu_work(system_wq, &krwp->rcu_work);
-			queued = true;
 		}
+
+		/* Repeat if any "free" corresponding channel is still busy. */
+		if (krcp->bhead || krcp->head)
+			repeat = true;
 	}
 
-	return queued;
+	return !repeat;
 }
 
 static inline void kfree_rcu_drain_unlock(struct kfree_rcu_cpu *krcp,
diff --git a/kernel/relay.c b/kernel/relay.c
index 72fe443ea78f..fb4e0c530c08 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -197,6 +197,7 @@ free_buf:
 static void relay_destroy_channel(struct kref *kref)
 {
 	struct rchan *chan = container_of(kref, struct rchan, kref);
+	free_percpu(chan->buf);
 	kfree(chan);
 }
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2142c6767682..f788cd61df21 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -794,6 +794,26 @@ unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE;
 /* All clamps are required to be less or equal than these values */
 static struct uclamp_se uclamp_default[UCLAMP_CNT];
 
+/*
+ * This static key is used to reduce the uclamp overhead in the fast path. It
+ * primarily disables the call to uclamp_rq_{inc, dec}() in
+ * enqueue/dequeue_task().
+ *
+ * This allows users to continue to enable uclamp in their kernel config with
+ * minimum uclamp overhead in the fast path.
+ *
+ * As soon as userspace modifies any of the uclamp knobs, the static key is
+ * enabled, since we have an actual users that make use of uclamp
+ * functionality.
+ *
+ * The knobs that would enable this static key are:
+ *
+ *   * A task modifying its uclamp value with sched_setattr().
+ *   * An admin modifying the sysctl_sched_uclamp_{min, max} via procfs.
+ *   * An admin modifying the cgroup cpu.uclamp.{min, max}
+ */
+DEFINE_STATIC_KEY_FALSE(sched_uclamp_used);
+
 /* Integer rounded range for each bucket */
 #define UCLAMP_BUCKET_DELTA DIV_ROUND_CLOSEST(SCHED_CAPACITY_SCALE, UCLAMP_BUCKETS)
 
@@ -990,10 +1010,38 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
 
 	lockdep_assert_held(&rq->lock);
 
+	/*
+	 * If sched_uclamp_used was enabled after task @p was enqueued,
+	 * we could end up with unbalanced call to uclamp_rq_dec_id().
+	 *
+	 * In this case the uc_se->active flag should be false since no uclamp
+	 * accounting was performed at enqueue time and we can just return
+	 * here.
+	 *
+	 * Need to be careful of the following enqeueue/dequeue ordering
+	 * problem too
+	 *
+	 *	enqueue(taskA)
+	 *	// sched_uclamp_used gets enabled
+	 *	enqueue(taskB)
+	 *	dequeue(taskA)
+	 *	// Must not decrement bukcet->tasks here
+	 *	dequeue(taskB)
+	 *
+	 * where we could end up with stale data in uc_se and
+	 * bucket[uc_se->bucket_id].
+	 *
+	 * The following check here eliminates the possibility of such race.
+	 */
+	if (unlikely(!uc_se->active))
+		return;
+
 	bucket = &uc_rq->bucket[uc_se->bucket_id];
+
 	SCHED_WARN_ON(!bucket->tasks);
 	if (likely(bucket->tasks))
 		bucket->tasks--;
+
 	uc_se->active = false;
 
 	/*
@@ -1021,6 +1069,15 @@ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
 {
 	enum uclamp_id clamp_id;
 
+	/*
+	 * Avoid any overhead until uclamp is actually used by the userspace.
+	 *
+	 * The condition is constructed such that a NOP is generated when
+	 * sched_uclamp_used is disabled.
+	 */
+	if (!static_branch_unlikely(&sched_uclamp_used))
+		return;
+
 	if (unlikely(!p->sched_class->uclamp_enabled))
 		return;
 
@@ -1036,6 +1093,15 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
 {
 	enum uclamp_id clamp_id;
 
+	/*
+	 * Avoid any overhead until uclamp is actually used by the userspace.
+	 *
+	 * The condition is constructed such that a NOP is generated when
+	 * sched_uclamp_used is disabled.
+	 */
+	if (!static_branch_unlikely(&sched_uclamp_used))
+		return;
+
 	if (unlikely(!p->sched_class->uclamp_enabled))
 		return;
 
@@ -1144,8 +1210,10 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 		update_root_tg = true;
 	}
 
-	if (update_root_tg)
+	if (update_root_tg) {
+		static_branch_enable(&sched_uclamp_used);
 		uclamp_update_root_tg();
+	}
 
 	/*
 	 * We update all RUNNABLE tasks only when task groups are in use.
@@ -1180,6 +1248,15 @@ static int uclamp_validate(struct task_struct *p,
 	if (upper_bound > SCHED_CAPACITY_SCALE)
 		return -EINVAL;
 
+	/*
+	 * We have valid uclamp attributes; make sure uclamp is enabled.
+	 *
+	 * We need to do that here, because enabling static branches is a
+	 * blocking operation which obviously cannot be done while holding
+	 * scheduler locks.
+	 */
+	static_branch_enable(&sched_uclamp_used);
+
 	return 0;
 }
 
@@ -1237,6 +1314,20 @@ static void uclamp_fork(struct task_struct *p)
 	}
 }
 
+static void __init init_uclamp_rq(struct rq *rq)
+{
+	enum uclamp_id clamp_id;
+	struct uclamp_rq *uc_rq = rq->uclamp;
+
+	for_each_clamp_id(clamp_id) {
+		uc_rq[clamp_id] = (struct uclamp_rq) {
+			.value = uclamp_none(clamp_id)
+		};
+	}
+
+	rq->uclamp_flags = 0;
+}
+
 static void __init init_uclamp(void)
 {
 	struct uclamp_se uc_max = {};
@@ -1245,11 +1336,8 @@ static void __init init_uclamp(void)
 
 	mutex_init(&uclamp_mutex);
 
-	for_each_possible_cpu(cpu) {
-		memset(&cpu_rq(cpu)->uclamp, 0,
-				sizeof(struct uclamp_rq)*UCLAMP_CNT);
-		cpu_rq(cpu)->uclamp_flags = 0;
-	}
+	for_each_possible_cpu(cpu)
+		init_uclamp_rq(cpu_rq(cpu));
 
 	for_each_clamp_id(clamp_id) {
 		uclamp_se_set(&init_task.uclamp_req[clamp_id],
@@ -7431,6 +7519,8 @@ static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf,
 	if (req.ret)
 		return req.ret;
 
+	static_branch_enable(&sched_uclamp_used);
+
 	mutex_lock(&uclamp_mutex);
 	rcu_read_lock();
 
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 7fbaee24c824..dc6835bc6490 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -210,7 +210,7 @@ unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs,
 	unsigned long dl_util, util, irq;
 	struct rq *rq = cpu_rq(cpu);
 
-	if (!IS_BUILTIN(CONFIG_UCLAMP_TASK) &&
+	if (!uclamp_is_used() &&
 	    type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) {
 		return max;
 	}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 04fa8dbcfa4d..6b3b59cc51d6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -10027,7 +10027,12 @@ static void kick_ilb(unsigned int flags)
 {
 	int ilb_cpu;
 
-	nohz.next_balance++;
+	/*
+	 * Increase nohz.next_balance only when if full ilb is triggered but
+	 * not if we only update stats.
+	 */
+	if (flags & NOHZ_BALANCE_KICK)
+		nohz.next_balance = jiffies+1;
 
 	ilb_cpu = find_new_ilb();
 
@@ -10348,6 +10353,14 @@ static bool _nohz_idle_balance(struct rq *this_rq, unsigned int flags,
 		}
 	}
 
+	/*
+	 * next_balance will be updated only when there is a need.
+	 * When the CPU is attached to null domain for ex, it will not be
+	 * updated.
+	 */
+	if (likely(update_next_balance))
+		nohz.next_balance = next_balance;
+
 	/* Newly idle CPU doesn't need an update */
 	if (idle != CPU_NEWLY_IDLE) {
 		update_blocked_averages(this_cpu);
@@ -10368,14 +10381,6 @@ abort:
 	if (has_blocked_load)
 		WRITE_ONCE(nohz.has_blocked, 1);
 
-	/*
-	 * next_balance will be updated only when there is a need.
-	 * When the CPU is attached to null domain for ex, it will not be
-	 * updated.
-	 */
-	if (likely(update_next_balance))
-		nohz.next_balance = next_balance;
-
 	return ret;
 }
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 877fb08eb1b0..c82857e2e288 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -862,6 +862,8 @@ struct uclamp_rq {
 	unsigned int value;
 	struct uclamp_bucket bucket[UCLAMP_BUCKETS];
 };
+
+DECLARE_STATIC_KEY_FALSE(sched_uclamp_used);
 #endif /* CONFIG_UCLAMP_TASK */
 
 /*
@@ -2349,12 +2351,35 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 #ifdef CONFIG_UCLAMP_TASK
 unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
 
+/**
+ * uclamp_rq_util_with - clamp @util with @rq and @p effective uclamp values.
+ * @rq:		The rq to clamp against. Must not be NULL.
+ * @util:	The util value to clamp.
+ * @p:		The task to clamp against. Can be NULL if you want to clamp
+ *		against @rq only.
+ *
+ * Clamps the passed @util to the max(@rq, @p) effective uclamp values.
+ *
+ * If sched_uclamp_used static key is disabled, then just return the util
+ * without any clamping since uclamp aggregation at the rq level in the fast
+ * path is disabled, rendering this operation a NOP.
+ *
+ * Use uclamp_eff_value() if you don't care about uclamp values at rq level. It
+ * will return the correct effective uclamp value of the task even if the
+ * static key is disabled.
+ */
 static __always_inline
 unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
 				  struct task_struct *p)
 {
-	unsigned long min_util = READ_ONCE(rq->uclamp[UCLAMP_MIN].value);
-	unsigned long max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value);
+	unsigned long min_util;
+	unsigned long max_util;
+
+	if (!static_branch_likely(&sched_uclamp_used))
+		return util;
+
+	min_util = READ_ONCE(rq->uclamp[UCLAMP_MIN].value);
+	max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value);
 
 	if (p) {
 		min_util = max(min_util, uclamp_eff_value(p, UCLAMP_MIN));
@@ -2371,6 +2396,19 @@ unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
 
 	return clamp(util, min_util, max_util);
 }
+
+/*
+ * When uclamp is compiled in, the aggregation at rq level is 'turned off'
+ * by default in the fast path and only gets turned on once userspace performs
+ * an operation that requires it.
+ *
+ * Returns true if userspace opted-in to use uclamp and aggregation at rq level
+ * hence is active.
+ */
+static inline bool uclamp_is_used(void)
+{
+	return static_branch_likely(&sched_uclamp_used);
+}
 #else /* CONFIG_UCLAMP_TASK */
 static inline
 unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
@@ -2378,6 +2416,11 @@ unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
 {
 	return util;
 }
+
+static inline bool uclamp_is_used(void)
+{
+	return false;
+}
 #endif /* CONFIG_UCLAMP_TASK */
 
 #ifdef arch_scale_freq_capacity
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index ba81187bb7af..9079d865a935 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1328,7 +1328,7 @@ sd_init(struct sched_domain_topology_level *tl,
 		sd_flags = (*tl->sd_flags)();
 	if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS,
 			"wrong sd_flags in topology description\n"))
-		sd_flags &= ~TOPOLOGY_SD_FLAGS;
+		sd_flags &= TOPOLOGY_SD_FLAGS;
 
 	/* Apply detected topology flags */
 	sd_flags |= dflags;
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index d653d8426de9..c461ba992513 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -42,6 +42,14 @@
 #include <linux/uaccess.h>
 #include <linux/anon_inodes.h>
 
+/*
+ * When SECCOMP_IOCTL_NOTIF_ID_VALID was first introduced, it had the
+ * wrong direction flag in the ioctl number. This is the broken one,
+ * which the kernel needs to keep supporting until all userspaces stop
+ * using the wrong command number.
+ */
+#define SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR	SECCOMP_IOR(2, __u64)
+
 enum notify_state {
 	SECCOMP_NOTIFY_INIT,
 	SECCOMP_NOTIFY_SENT,
@@ -1186,6 +1194,7 @@ static long seccomp_notify_ioctl(struct file *file, unsigned int cmd,
 		return seccomp_notify_recv(filter, buf);
 	case SECCOMP_IOCTL_NOTIF_SEND:
 		return seccomp_notify_send(filter, buf);
+	case SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR:
 	case SECCOMP_IOCTL_NOTIF_ID_VALID:
 		return seccomp_notify_id_valid(filter, buf);
 	default:
diff --git a/kernel/signal.c b/kernel/signal.c
index 6f16f7c5d375..42b67d2cea37 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2541,7 +2541,21 @@ bool get_signal(struct ksignal *ksig)
 
 relock:
 	spin_lock_irq(&sighand->siglock);
-	current->jobctl &= ~JOBCTL_TASK_WORK;
+	/*
+	 * Make sure we can safely read ->jobctl() in task_work add. As Oleg
+	 * states:
+	 *
+	 * It pairs with mb (implied by cmpxchg) before READ_ONCE. So we
+	 * roughly have
+	 *
+	 *	task_work_add:				get_signal:
+	 *	STORE(task->task_works, new_work);	STORE(task->jobctl);
+	 *	mb();					mb();
+	 *	LOAD(task->jobctl);			LOAD(task->task_works);
+	 *
+	 * and we can rely on STORE-MB-LOAD [ in task_work_add].
+	 */
+	smp_store_mb(current->jobctl, current->jobctl & ~JOBCTL_TASK_WORK);
 	if (unlikely(current->task_works)) {
 		spin_unlock_irq(&sighand->siglock);
 		task_work_run();
diff --git a/kernel/task_work.c b/kernel/task_work.c
index 5c0848ca1287..613b2d634af8 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -42,7 +42,13 @@ task_work_add(struct task_struct *task, struct callback_head *work, int notify)
 		set_notify_resume(task);
 		break;
 	case TWA_SIGNAL:
-		if (lock_task_sighand(task, &flags)) {
+		/*
+		 * Only grab the sighand lock if we don't already have some
+		 * task_work pending. This pairs with the smp_store_mb()
+		 * in get_signal(), see comment there.
+		 */
+		if (!(READ_ONCE(task->jobctl) & JOBCTL_TASK_WORK) &&
+		    lock_task_sighand(task, &flags)) {
 			task->jobctl |= JOBCTL_TASK_WORK;
 			signal_wake_up(task, 0);
 			unlock_task_sighand(task, &flags);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 3e2dc9b8858c..f0199a4ba1ad 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -351,16 +351,24 @@ void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit)
 EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_cpu);
 
 /*
- * Set a per-task tick dependency. Posix CPU timers need this in order to elapse
- * per task timers.
+ * Set a per-task tick dependency. RCU need this. Also posix CPU timers
+ * in order to elapse per task timers.
  */
 void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit)
 {
-	/*
-	 * We could optimize this with just kicking the target running the task
-	 * if that noise matters for nohz full users.
-	 */
-	tick_nohz_dep_set_all(&tsk->tick_dep_mask, bit);
+	if (!atomic_fetch_or(BIT(bit), &tsk->tick_dep_mask)) {
+		if (tsk == current) {
+			preempt_disable();
+			tick_nohz_full_kick();
+			preempt_enable();
+		} else {
+			/*
+			 * Some future tick_nohz_full_kick_task()
+			 * should optimize this.
+			 */
+			tick_nohz_full_kick_all();
+		}
+	}
 }
 EXPORT_SYMBOL_GPL(tick_nohz_dep_set_task);
 
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 5ef0484513ec..588e8e396019 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -522,10 +522,18 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (!bt->msg_data)
 		goto err;
 
-	ret = -ENOENT;
-
-	dir = debugfs_lookup(buts->name, blk_debugfs_root);
-	if (!dir)
+#ifdef CONFIG_BLK_DEBUG_FS
+	/*
+	 * When tracing whole make_request drivers (multiqueue) block devices,
+	 * reuse the existing debugfs directory created by the block layer on
+	 * init. For request-based block devices, all partitions block devices,
+	 * and scsi-generic block devices we create a temporary new debugfs
+	 * directory that will be removed once the trace ends.
+	 */
+	if (queue_is_mq(q) && bdev && bdev == bdev->bd_contains)
+		dir = q->debugfs_dir;
+	else
+#endif
 		bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root);
 
 	bt->dev = dev;
@@ -563,8 +571,6 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 
 	ret = 0;
 err:
-	if (dir && !bt->dir)
-		dput(dir);
 	if (ret)
 		blk_trace_free(bt);
 	return ret;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 1903b80db6eb..b5cb5be3ca6f 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -139,9 +139,6 @@ static inline void ftrace_ops_init(struct ftrace_ops *ops)
 #endif
 }
 
-#define FTRACE_PID_IGNORE	-1
-#define FTRACE_PID_TRACE	-2
-
 static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
 			    struct ftrace_ops *op, struct pt_regs *regs)
 {
@@ -6190,8 +6187,11 @@ static int referenced_filters(struct dyn_ftrace *rec)
 	int cnt = 0;
 
 	for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) {
-		if (ops_references_rec(ops, rec))
-		    cnt++;
+		if (ops_references_rec(ops, rec)) {
+			cnt++;
+			if (ops->flags & FTRACE_OPS_FL_SAVE_REGS)
+				rec->flags |= FTRACE_FL_REGS;
+		}
 	}
 
 	return cnt;
@@ -6370,8 +6370,8 @@ void ftrace_module_enable(struct module *mod)
 		if (ftrace_start_up)
 			cnt += referenced_filters(rec);
 
-		/* This clears FTRACE_FL_DISABLED */
-		rec->flags = cnt;
+		rec->flags &= ~FTRACE_FL_DISABLED;
+		rec->flags += cnt;
 
 		if (ftrace_start_up && cnt) {
 			int failed = __ftrace_replace_code(rec, 1);
@@ -6969,12 +6969,12 @@ void ftrace_pid_follow_fork(struct trace_array *tr, bool enable)
 	if (enable) {
 		register_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork,
 						  tr);
-		register_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit,
+		register_trace_sched_process_free(ftrace_pid_follow_sched_process_exit,
 						  tr);
 	} else {
 		unregister_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork,
 						    tr);
-		unregister_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit,
+		unregister_trace_sched_process_free(ftrace_pid_follow_sched_process_exit,
 						    tr);
 	}
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index bb62269724d5..6fc6da55b94e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -5887,7 +5887,7 @@ int tracing_set_tracer(struct trace_array *tr, const char *buf)
 	}
 
 	/* If trace pipe files are being read, we can't change the tracer */
-	if (tr->current_trace->ref) {
+	if (tr->trace_ref) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -6103,7 +6103,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 
 	nonseekable_open(inode, filp);
 
-	tr->current_trace->ref++;
+	tr->trace_ref++;
 out:
 	mutex_unlock(&trace_types_lock);
 	return ret;
@@ -6122,7 +6122,7 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
 
 	mutex_lock(&trace_types_lock);
 
-	tr->current_trace->ref--;
+	tr->trace_ref--;
 
 	if (iter->trace->pipe_close)
 		iter->trace->pipe_close(iter);
@@ -7424,7 +7424,7 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp)
 
 	filp->private_data = info;
 
-	tr->current_trace->ref++;
+	tr->trace_ref++;
 
 	mutex_unlock(&trace_types_lock);
 
@@ -7525,7 +7525,7 @@ static int tracing_buffers_release(struct inode *inode, struct file *file)
 
 	mutex_lock(&trace_types_lock);
 
-	iter->tr->current_trace->ref--;
+	iter->tr->trace_ref--;
 
 	__trace_array_put(iter->tr);
 
@@ -8733,7 +8733,7 @@ static int __remove_instance(struct trace_array *tr)
 	int i;
 
 	/* Reference counter for a newly created trace array = 1. */
-	if (tr->ref > 1 || (tr->current_trace && tr->current_trace->ref))
+	if (tr->ref > 1 || (tr->current_trace && tr->trace_ref))
 		return -EBUSY;
 
 	list_del(&tr->list);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 13db4000af3f..610d21355526 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -356,6 +356,7 @@ struct trace_array {
 	struct trace_event_file *trace_marker_file;
 	cpumask_var_t		tracing_cpumask; /* only trace on set CPUs */
 	int			ref;
+	int			trace_ref;
 #ifdef CONFIG_FUNCTION_TRACER
 	struct ftrace_ops	*ops;
 	struct trace_pid_list	__rcu *function_pids;
@@ -547,7 +548,6 @@ struct tracer {
 	struct tracer		*next;
 	struct tracer_flags	*flags;
 	int			enabled;
-	int			ref;
 	bool			print_max;
 	bool			allow_instances;
 #ifdef CONFIG_TRACER_MAX_TRACE
@@ -1103,6 +1103,10 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 extern struct list_head ftrace_pids;
 
 #ifdef CONFIG_FUNCTION_TRACER
+
+#define FTRACE_PID_IGNORE	-1
+#define FTRACE_PID_TRACE	-2
+
 struct ftrace_func_command {
 	struct list_head	list;
 	char			*name;
@@ -1114,7 +1118,8 @@ struct ftrace_func_command {
 extern bool ftrace_filter_param __initdata;
 static inline int ftrace_trace_task(struct trace_array *tr)
 {
-	return !this_cpu_read(tr->array_buffer.data->ftrace_ignore_pid);
+	return this_cpu_read(tr->array_buffer.data->ftrace_ignore_pid) !=
+		FTRACE_PID_IGNORE;
 }
 extern int ftrace_is_dead(void);
 int ftrace_create_function_files(struct trace_array *tr,
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index f6f55682d3e2..a85effb2373b 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -538,12 +538,12 @@ void trace_event_follow_fork(struct trace_array *tr, bool enable)
 	if (enable) {
 		register_trace_prio_sched_process_fork(event_filter_pid_sched_process_fork,
 						       tr, INT_MIN);
-		register_trace_prio_sched_process_exit(event_filter_pid_sched_process_exit,
+		register_trace_prio_sched_process_free(event_filter_pid_sched_process_exit,
 						       tr, INT_MAX);
 	} else {
 		unregister_trace_sched_process_fork(event_filter_pid_sched_process_fork,
 						    tr);
-		unregister_trace_sched_process_exit(event_filter_pid_sched_process_exit,
+		unregister_trace_sched_process_free(event_filter_pid_sched_process_exit,
 						    tr);
 	}
 }
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index e2be7bb7ef7e..17e1e49e5b93 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -283,6 +283,7 @@ static bool disable_migrate;
 static void move_to_next_cpu(void)
 {
 	struct cpumask *current_mask = &save_cpumask;
+	struct trace_array *tr = hwlat_trace;
 	int next_cpu;
 
 	if (disable_migrate)
@@ -296,7 +297,7 @@ static void move_to_next_cpu(void)
 		goto disable;
 
 	get_online_cpus();
-	cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask);
+	cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask);
 	next_cpu = cpumask_next(smp_processor_id(), current_mask);
 	put_online_cpus();
 
@@ -373,7 +374,7 @@ static int start_kthread(struct trace_array *tr)
 	/* Just pick the first CPU on first iteration */
 	current_mask = &save_cpumask;
 	get_online_cpus();
-	cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask);
+	cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask);
 	put_online_cpus();
 	next_cpu = cpumask_first(current_mask);
 
diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c
index f74020f6bd9d..0ef8f65bd2d7 100644
--- a/kernel/watch_queue.c
+++ b/kernel/watch_queue.c
@@ -393,6 +393,7 @@ static void free_watch(struct rcu_head *rcu)
 	struct watch *watch = container_of(rcu, struct watch, rcu);
 
 	put_watch_queue(rcu_access_pointer(watch->queue));
+	atomic_dec(&watch->cred->user->nr_watches);
 	put_cred(watch->cred);
 }
 
@@ -452,6 +453,13 @@ int add_watch_to_object(struct watch *watch, struct watch_list *wlist)
 	watch->cred = get_current_cred();
 	rcu_assign_pointer(watch->watch_list, wlist);
 
+	if (atomic_inc_return(&watch->cred->user->nr_watches) >
+	    task_rlimit(current, RLIMIT_NOFILE)) {
+		atomic_dec(&watch->cred->user->nr_watches);
+		put_cred(watch->cred);
+		return -EAGAIN;
+	}
+
 	spin_lock_bh(&wqueue->lock);
 	kref_get(&wqueue->usage);
 	kref_get(&watch->usage);