Backmerge tag 'v7.3-rc4' into drm-next

Linux 7.3-rc4

Requested by Philipp Stanner for
2ab510e63197360945f915dd5631a77c63ac6b27 would be needed as a groundlayer
for further patches that extend the locking in drm_sched

Signed-off-by: Dave Airlie <airlied@redhat.com>

36 files changed, 547 insertions, 234 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 2d532bf2c0c7..227d09704ca5 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -5303,10 +5303,13 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
 	if (it->flags & CSS_TASK_ITER_SKIPPED)
 		css_task_iter_advance(it);
 
-	if (it->task_pos) {
+	while (it->task_pos && !it->cur_task) {
 		it->cur_task = list_entry(it->task_pos, struct task_struct,
 					  cg_list);
-		get_task_struct(it->cur_task);
+		/* a task on dying_tasks with zero refcount is only valid for
+		 * RCU readers, not even interesting for
+		 * CSS_TASK_ITER_WITH_DEAD, find another one */
+		it->cur_task = tryget_task_struct(it->cur_task);
 		css_task_iter_advance(it);
 	}
 
diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
index 45bbae947f4b..4d0266893bcc 100644
--- a/kernel/dma/coherent.c
+++ b/kernel/dma/coherent.c
@@ -352,8 +352,7 @@ static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev)
 	    min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit))
 		dev_warn(dev, "reserved memory is beyond device's set DMA address range\n");
 
-	dma_assign_coherent_memory(dev, mem);
-	return 0;
+	return dma_assign_coherent_memory(dev, mem);
 }
 
 static void rmem_dma_device_release(struct reserved_mem *rmem,
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index ded7016a46a7..aa2f1c4588b9 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -1019,7 +1019,6 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size
 	int index = (tlb_addr - mem->start) >> IO_TLB_SHIFT;
 	phys_addr_t orig_addr = mem->slots[index].orig_addr;
 	size_t alloc_size = mem->slots[index].alloc_size;
-	unsigned long pfn = PFN_DOWN(orig_addr);
 	unsigned char *vaddr = mem->vaddr + tlb_addr - mem->start;
 	int tlb_offset;
 
@@ -1052,7 +1051,8 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size
 		size = alloc_size;
 	}
 
-	if (PageHighMem(pfn_to_page(pfn))) {
+	if (PhysHighMem(orig_addr)) {
+		unsigned long pfn = PFN_DOWN(orig_addr);
 		unsigned int offset = orig_addr & ~PAGE_MASK;
 		struct page *page;
 		unsigned int sz = 0;
diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c
index 2002c7aae435..59c861866941 100644
--- a/kernel/entry/syscall_user_dispatch.c
+++ b/kernel/entry/syscall_user_dispatch.c
@@ -178,7 +178,7 @@ int syscall_user_dispatch_set_config(struct task_struct *task, unsigned long siz
 					      (char __user *)(uintptr_t)cfg.selector);
 }
 
-#ifdef CONFIG_PROC_SYSCTL
+#ifdef CONFIG_SYSCTL
 static const struct ctl_table syscall_user_dispatch_sysctls[] = {
 	{
 		.procname	= "syscall_user_dispatch",
@@ -195,4 +195,4 @@ static int __init syscall_user_dispatch_sysctl_init(void)
 	return 0;
 }
 late_initcall(syscall_user_dispatch_sysctl_init);
-#endif /* CONFIG_PROC_SYSCTL */
+#endif /* CONFIG_SYSCTL */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 33210aff3ee6..db7b76d6b68a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3925,13 +3925,13 @@ static void perf_pmu_sched_task(struct task_struct *prev,
 				bool sched_in)
 {
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
-	struct perf_cpu_pmu_context *cpc;
+	struct perf_cpu_pmu_context *cpc, *cpc2;
 
 	/* cpuctx->task_ctx will be handled in perf_event_context_sched_in/out */
 	if (prev == next || cpuctx->task_ctx)
 		return;
 
-	list_for_each_entry(cpc, this_cpu_ptr(&sched_cb_list), sched_cb_entry)
+	list_for_each_entry_safe(cpc, cpc2, this_cpu_ptr(&sched_cb_list), sched_cb_entry)
 		__perf_pmu_sched_task(cpc, sched_in ? next : prev, sched_in);
 }
 
@@ -6350,6 +6350,9 @@ static DEFINE_MUTEX(perf_mediated_pmu_mutex);
 /* !exclude_guest event of PMU with PERF_PMU_CAP_MEDIATED_VPMU */
 static inline bool is_include_guest_event(struct perf_event *event)
 {
+	if (!event->pmu)
+		return false;
+
 	if ((event->pmu->capabilities & PERF_PMU_CAP_MEDIATED_VPMU) &&
 	    !event->attr.exclude_guest)
 		return true;
@@ -13002,6 +13005,7 @@ static void __pmu_detach_event(struct pmu *pmu, struct perf_event *event,
 	exclusive_event_destroy(event);
 	module_put(pmu->module);
 
+	mediated_pmu_unaccount_event(event);
 	event->pmu = NULL; /* force fault instead of UAF */
 }
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 97686af89501..424c44a42a4d 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -261,8 +261,11 @@ repeat:
 	pidfs_exit(p);
 	cgroup_task_release(p);
 
-	/* Retrieve @thread_pid before __unhash_process() may set it to NULL. */
-	thread_pid = task_pid(p);
+	/*
+	 * Pin @thread_pid before __unhash_process() clears it. The last
+	 * PIDTYPE detach can otherwise free it before proc_flush_pid().
+	 */
+	thread_pid = get_pid(task_pid(p));
 
 	write_lock_irq(&tasklist_lock);
 	ptrace_release_task(p);
@@ -291,20 +294,21 @@ repeat:
 	}
 
 	write_unlock_irq(&tasklist_lock);
-	/* @thread_pid can't go away until free_pids() below */
 	proc_flush_pid(thread_pid);
+	put_pid(thread_pid);
 	exit_cred_namespaces(p);
 	add_device_randomness(&p->se.sum_exec_runtime,
 			      sizeof(p->se.sum_exec_runtime));
 	free_pids(post.pids);
 	release_thread(p);
 	/*
-	 * This task was already removed from the process/thread/pid lists
-	 * and lock_task_sighand(p) can't succeed. Nobody else can touch
-	 * ->pending or, if group dead, signal->shared_pending. We can call
-	 * flush_sigqueue() lockless.
+	 * This task was already removed from the process/thread/pid lists and
+	 * lock_task_sighand(p) can't succeed. If it's the group leader then
+	 * flush tsk->signal->shared_pending. tsk->pending has been flushed
+	 * already in exit_signals(). Nothing else can touch
+	 * signal->shared_pending anymore, so flush_sigqueue() can be invoked
+	 * lockless.
 	 */
-	flush_sigqueue(&p->pending);
 	if (thread_group_leader(p))
 		flush_sigqueue(&p->signal->shared_pending);
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 416758c8a3d4..5ef413368912 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1996,9 +1996,9 @@ static bool need_futex_hash_allocate_default(u64 clone_flags)
 {
 	/*
 	 * Allocate a default futex hash for any sibling that will
-	 * share the parent's mm, except vfork.
+	 * share the parent's mm.
 	 */
-	return (clone_flags & (CLONE_VM | CLONE_VFORK)) == CLONE_VM;
+	return clone_flags & CLONE_VM;
 }
 
 /*
@@ -2133,6 +2133,11 @@ __latent_entropy struct task_struct *copy_process(
 	p = dup_task_struct(current, node);
 	if (!p)
 		goto fork_out;
+	/*
+	 * Must run before the first fallible op, so error paths never
+	 * free the parent's ret_stack.
+	 */
+	ftrace_graph_init_task(p);
 	retval = copy_exec_state(clone_flags, p);
 	if (retval)
 		goto bad_fork_free;
@@ -2159,8 +2164,6 @@ __latent_entropy struct task_struct *copy_process(
 	 */
 	p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? args->child_tid : NULL;
 
-	ftrace_graph_init_task(p);
-
 	rt_mutex_init_task(p);
 	raw_spin_lock_init(&p->blocked_lock);
 
diff --git a/kernel/nstree.c b/kernel/nstree.c
index 6d12e5900ac0..831f279d174a 100644
--- a/kernel/nstree.c
+++ b/kernel/nstree.c
@@ -533,19 +533,13 @@ DEFINE_FREE(ns_put, struct ns_common *, if (!IS_ERR_OR_NULL(_T)) ns_put(_T))
 static inline struct ns_common *__must_check legitimize_ns(const struct klistns *kls,
 							   struct ns_common *candidate)
 {
-	struct ns_common *ns __free(ns_put) = NULL;
-
 	if (!ns_requested(kls, candidate))
 		return NULL;
 
-	ns = ns_get_unless_inactive(candidate);
-	if (!ns)
-		return NULL;
-
-	if (!may_list_ns(kls, ns))
+	if (!may_list_ns(kls, candidate))
 		return NULL;
 
-	return no_free_ptr(ns);
+	return ns_get_unless_inactive(candidate);
 }
 
 static ssize_t do_listns_userns(struct klistns *kls)
diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c
index 4b03b019cd5e..d17704fe93ae 100644
--- a/kernel/printk/nbcon.c
+++ b/kernel/printk/nbcon.c
@@ -1382,7 +1382,7 @@ bool nbcon_kthread_create(struct console *con)
 		return true;
 
 	kt = kthread_run(nbcon_kthread_func, con, "pr/%s%d", con->name, con->index);
-	if (WARN_ON(IS_ERR(kt))) {
+	if (IS_ERR(kt)) {
 		con_printk(KERN_ERR, con, "failed to start printing thread\n");
 		return false;
 	}
@@ -1782,7 +1782,7 @@ bool nbcon_alloc(struct console *con)
 	}
 
 	rcuwait_init(&con->rcuwait);
-	init_irq_work(&con->irq_work, nbcon_irq_work);
+	con->irq_work = IRQ_WORK_INIT_LAZY(nbcon_irq_work);
 	atomic_long_set(&ACCESS_PRIVATE(con, nbcon_prev_seq), -1UL);
 	nbcon_state_set(con, &state);
 
@@ -1837,6 +1837,8 @@ void nbcon_free(struct console *con)
 	/* Synchronize the kthread stop. */
 	lockdep_assert_console_list_lock_held();
 
+	irq_work_sync(&con->irq_work);
+
 	if (printk_kthreads_running) {
 		nbcon_kthread_stop(con);
 
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 3fcdf4b4e2e5..6d3d18a50da7 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -3732,7 +3732,7 @@ static bool legacy_kthread_create(void)
 	lockdep_assert_console_list_lock_held();
 
 	kt = kthread_run(legacy_kthread_func, NULL, "pr/legacy");
-	if (WARN_ON(IS_ERR(kt))) {
+	if (IS_ERR(kt)) {
 		pr_err("failed to start legacy printing thread\n");
 		return false;
 	}
diff --git a/kernel/reboot.c b/kernel/reboot.c
index f070c5c1103a..d177d89fcc33 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -13,7 +13,9 @@
 #include <linux/kexec.h>
 #include <linux/kmod.h>
 #include <linux/kmsg_dump.h>
+#include <linux/rcupdate.h>
 #include <linux/reboot.h>
+#include <linux/sched/signal.h>
 #include <linux/suspend.h>
 #include <linux/syscalls.h>
 #include <linux/syscore_ops.h>
@@ -24,8 +26,7 @@
  */
 
 static int C_A_D = 1;
-struct pid *cad_pid;
-EXPORT_SYMBOL(cad_pid);
+struct pid __rcu *cad_pid;
 
 #if defined(CONFIG_ARM)
 #define DEFAULT_REBOOT_MODE		= REBOOT_HARD
@@ -1371,10 +1372,14 @@ static int proc_do_cad_pid(const struct ctl_table *table, int write, void *buffe
 {
 	struct ctl_table tmp_table = *table;
 	struct pid *new_pid;
+	struct pid *old_pid;
 	pid_t tmp_pid;
 	int r;
 
-	tmp_pid = pid_vnr(cad_pid);
+	rcu_read_lock();
+	tmp_pid = pid_vnr(rcu_dereference(cad_pid));
+	rcu_read_unlock();
+
 	tmp_table.data = &tmp_pid;
 
 	r = proc_dointvec(&tmp_table, write, buffer, lenp, ppos);
@@ -1385,7 +1390,13 @@ static int proc_do_cad_pid(const struct ctl_table *table, int write, void *buffe
 	if (!new_pid)
 		return -ESRCH;
 
-	put_pid(xchg(&cad_pid, new_pid));
+	old_pid = unrcu_pointer(xchg(&cad_pid, RCU_INITIALIZER(new_pid)));
+	/*
+	 * Wait for cad_pid readers before put_pid().  We cannot use
+	 * call_rcu() here because free_pid() already owns pid->rcu.
+	 */
+	synchronize_rcu();
+	put_pid(old_pid);
 	return 0;
 }
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b998ef6b87af..0b846a13c628 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3351,6 +3351,8 @@ void relax_compatible_cpus_allowed_ptr(struct task_struct *p)
 void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 {
 	unsigned int state = READ_ONCE(p->__state);
+	bool proxy_migrated = sched_proxy_exec() && p->is_blocked &&
+			      task_cpu(p) != p->wake_cpu;
 
 	/*
 	 * We should never call set_task_cpu() on a blocked task,
@@ -3386,7 +3388,12 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	 */
 	WARN_ON_ONCE(!cpu_online(new_cpu));
 
-	WARN_ON_ONCE(is_migration_disabled(p));
+	/*
+	 * Proxy execution can move a blocked task's scheduling context to any
+	 * CPU without moving its migration-disabled execution context. The
+	 * wakeup path will return the task to a CPU where it can execute.
+	 */
+	WARN_ON_ONCE(is_migration_disabled(p) && !proxy_migrated);
 
 	trace_sched_migrate_task(p, new_cpu);
 
@@ -5776,8 +5783,8 @@ void sched_tick(void)
 {
 	int cpu = smp_processor_id();
 	struct rq *rq = cpu_rq(cpu);
-	/* accounting goes to the donor task */
-	struct task_struct *donor;
+	/* scheduler accounting goes to the donor task */
+	struct task_struct *curr, *donor;
 	struct rq_flags rf;
 	unsigned long hw_pressure;
 	u64 resched_latency;
@@ -5788,6 +5795,7 @@ void sched_tick(void)
 	sched_clock_tick();
 
 	rq_lock(rq, &rf);
+	curr = rq->curr;
 	donor = rq->donor;
 
 	psi_account_irqtime(rq, donor, NULL);
@@ -5813,8 +5821,8 @@ void sched_tick(void)
 
 	perf_event_task_tick();
 
-	if (donor->flags & PF_WQ_WORKER)
-		wq_worker_tick(donor);
+	if (curr->flags & PF_WQ_WORKER)
+		wq_worker_tick(curr);
 
 	if (!scx_switched_all()) {
 		rq->idle_balance = idle_cpu(cpu);
diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index 51de1d8b72a1..3219f0da0fe4 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -2919,7 +2919,7 @@ static inline void maybe_queue_balance_callback(struct rq *rq)
 
 static enum scx_dsp_verdict dispatch_one(struct rq *rq, struct task_struct *prev)
 {
-	struct scx_sched *sch = scx_root_protected_live();
+	struct scx_sched *root_sch = scx_root_protected_live();
 	enum scx_dsp_verdict verdict;
 	s32 cpu = cpu_of(rq);
 
@@ -2928,7 +2928,7 @@ static enum scx_dsp_verdict dispatch_one(struct rq *rq, struct task_struct *prev
 
 	scx_process_sync_ecaps(rq, prev);
 
-	if ((sch->ops.flags & SCX_OPS_HAS_CPU_PREEMPT) &&
+	if ((root_sch->ops.flags & SCX_OPS_HAS_CPU_PREEMPT) &&
 	    unlikely(rq->scx.cpu_released)) {
 		/*
 		 * If the previous sched_class for the current CPU was not SCX,
@@ -2936,8 +2936,8 @@ static enum scx_dsp_verdict dispatch_one(struct rq *rq, struct task_struct *prev
 		 * core. This callback complements ->cpu_release(), which is
 		 * emitted in switch_class().
 		 */
-		if (sch->ops.cpu_acquire)
-			SCX_CALL_OP(sch, cpu_acquire, rq, cpu, NULL);
+		if (root_sch->ops.cpu_acquire)
+			SCX_CALL_OP(root_sch, cpu_acquire, rq, cpu, NULL);
 		rq->scx.cpu_released = false;
 	}
 
@@ -2955,7 +2955,7 @@ static enum scx_dsp_verdict dispatch_one(struct rq *rq, struct task_struct *prev
 		 * test.
 		 */
 		if ((prev->scx.flags & SCX_TASK_QUEUED) && prev->scx.slice &&
-		    !scx_bypassing(sch, cpu)) {
+		    !scx_bypassing(scx_task_sched(prev), cpu)) {
 			verdict = SCX_DSP_PREV;
 			goto has_tasks;
 		}
@@ -2967,20 +2967,25 @@ static enum scx_dsp_verdict dispatch_one(struct rq *rq, struct task_struct *prev
 		goto has_tasks;
 	}
 
-	verdict = scx_dispatch_sched(sch, rq, prev, false);
+	verdict = scx_dispatch_sched(root_sch, rq, prev, false);
 	if (verdict != SCX_DSP_NONE)
 		goto has_tasks;
 
 	/*
-	 * Didn't find another task to run. Keep running @prev unless
-	 * %SCX_OPS_ENQ_LAST is in effect.
+	 * Didn't find another task to run. Keep running @prev unless its own
+	 * scheduler set %SCX_OPS_ENQ_LAST and takes the enqueue instead, see
+	 * put_prev_task_scx(). Read the scheduler here as the dispatch above
+	 * may have dropped the rq lock while @prev changed class or scheduler.
 	 */
-	if ((prev->scx.flags & SCX_TASK_QUEUED) &&
-	    (!(sch->ops.flags & SCX_OPS_ENQ_LAST) || scx_bypassing(sch, cpu)) &&
-	    scx_task_can_stay_on_cpu(rq, prev)) {
-		__scx_add_event(sch, SCX_EV_DISPATCH_KEEP_LAST, 1);
-		verdict = SCX_DSP_PREV;
-		goto has_tasks;
+	if (prev->scx.flags & SCX_TASK_QUEUED) {
+		struct scx_sched *prev_sch = scx_task_sched(prev);
+
+		if ((!(prev_sch->ops.flags & SCX_OPS_ENQ_LAST) ||
+		     scx_bypassing(prev_sch, cpu)) && scx_task_can_stay_on_cpu(rq, prev)) {
+			__scx_add_event(prev_sch, SCX_EV_DISPATCH_KEEP_LAST, 1);
+			verdict = SCX_DSP_PREV;
+			goto has_tasks;
+		}
 	}
 	rq->scx.flags &= ~SCX_RQ_IN_DISPATCH;
 	return SCX_DSP_NONE;
@@ -3665,8 +3670,20 @@ static void handle_hotplug(struct rq *rq, bool online)
 		s16 *tbl = rcu_dereference_check(scx_cpu_to_cid_tbl,
 						 lockdep_is_cpus_held());
 
-		if (tbl)
+		if (tbl) {
+			struct scx_sched *pos;
+
 			cpu_or_cid = tbl[cpu];
+
+			guard(raw_spinlock_irqsave)(&scx_sched_lock);
+			list_for_each_entry(pos, &scx_sched_all, all) {
+				struct scx_cmask *mask = pos->online_cmask;
+
+				if (mask)
+					__assign_bit(cpu_or_cid, (unsigned long *)mask->bits,
+						     online);
+			}
+		}
 	}
 
 	if (online && SCX_HAS_OP(sch, cpu_online))
@@ -4766,7 +4783,8 @@ int scx_tg_online(struct task_group *tg)
 				{ .weight = tg->scx.weight,
 				  .bw_period_us = tg->scx.bw_period_us,
 				  .bw_quota_us = tg->scx.bw_quota_us,
-				  .bw_burst_us = tg->scx.bw_burst_us };
+				  .bw_burst_us = tg->scx.bw_burst_us,
+				  .sched_idle = tg->scx.idle };
 
 			ret = SCX_CALL_OP_RET(sch, cgroup_init,
 					      NULL, tg->css.cgroup, &args);
@@ -4932,7 +4950,8 @@ void scx_group_set_idle(struct task_group *tg, bool idle)
 	percpu_down_read(&scx_cgroup_ops_rwsem);
 	sch = scx_tg_knob_sched(tg);
 
-	if (scx_cgroup_enabled && sch && SCX_HAS_OP(sch, cgroup_set_idle))
+	if (scx_cgroup_enabled && sch && SCX_HAS_OP(sch, cgroup_set_idle) &&
+	    tg->scx.idle != idle)
 		SCX_CALL_OP(sch, cgroup_set_idle, NULL, tg_cgrp(tg), idle);
 
 	/* Update the task group's idle state */
@@ -5187,6 +5206,7 @@ static int scx_cgroup_init(struct scx_sched *sch)
 				.bw_period_us = tg->scx.bw_period_us,
 				.bw_quota_us = tg->scx.bw_quota_us,
 				.bw_burst_us = tg->scx.bw_burst_us,
+				.sched_idle = tg->scx.idle,
 			};
 
 			ret = SCX_CALL_OP_RET(sch, cgroup_init, NULL, css->cgroup, &args);
@@ -5272,12 +5292,17 @@ static void free_exit_info(struct scx_exit_info *ei);
 static const char *scx_exit_reason(enum scx_exit_kind kind);
 static bool scx_claim_exit(struct scx_sched *sch, enum scx_exit_kind kind);
 
-s32 scx_set_cmask_scratch_alloc(struct scx_sched *sch)
+s32 scx_alloc_kern_arena_objs(struct scx_sched *sch)
 {
 	size_t size = struct_size_t(struct scx_cmask, bits,
 				    SCX_CMASK_NR_WORDS(num_possible_cpus()));
+	struct scx_cmask *online;
+	struct scx_cmask_ref ref;
 	int cpu;
 
+	/* hotplug stays excluded until the online mask is published */
+	lockdep_assert_cpus_held();
+
 	if (!sch->is_cid_type || !sch->arena_pool)
 		return 0;
 
@@ -5293,15 +5318,28 @@ s32 scx_set_cmask_scratch_alloc(struct scx_sched *sch)
 			return -ENOMEM;
 		scx_cmask_init(*slot, 0, num_possible_cpus());
 	}
+
+	/* pack the online mask alongside the scratch masks */
+	online = scx_arena_alloc(sch, size);
+	if (!online)
+		return -ENOMEM;
+
+	scoped_guard(rcu) {
+		scx_cmask_ref_init_kern(sch, online, 0, num_possible_cpus(), &ref);
+		scx_cmask_ref_from_cpumask(&ref, cpu_active_mask);
+	}
+	sch->online_cmask = online;
+
 	return 0;
 }
 
-static void scx_set_cmask_scratch_free(struct scx_sched *sch)
+static void scx_free_kern_arena_objs(struct scx_sched *sch)
 {
 	size_t size = struct_size_t(struct scx_cmask, bits,
 				    SCX_CMASK_NR_WORDS(num_possible_cpus()));
 	int cpu;
 
+	scx_arena_free(sch, sch->online_cmask, size);
 	if (!sch->set_cmask_scratch)
 		return;
 
@@ -5388,7 +5426,7 @@ static void scx_sched_free_rcu_work(struct work_struct *work)
 
 	rhashtable_free_and_destroy(&sch->dsq_hash, NULL, NULL);
 	free_exit_info(sch->exit_info);
-	scx_set_cmask_scratch_free(sch);
+	scx_free_kern_arena_objs(sch);
 	scx_arena_pool_destroy(sch);
 	if (sch->arena_map)
 		bpf_map_put(sch->arena_map);
@@ -7508,22 +7546,24 @@ static void scx_root_enable_workfn(struct kthread_work *work)
 #ifdef CONFIG_EXT_SUB_SCHED
 	cgroup_get(cgrp);
 #endif
+	/*
+	 * Transition to ENABLING to arm the disable path. Allocation failure
+	 * still unwinds locally. Full disabling on failure applies only after
+	 * scx_alloc_and_add_sched() succeeds.
+	 */
+	WARN_ON_ONCE(scx_set_enable_state(SCX_ENABLING) != SCX_DISABLED);
+	WARN_ON_ONCE(scx_root);
+
 	sch = scx_alloc_and_add_sched(cmd, cgrp, NULL);
 	if (IS_ERR(sch)) {
 		ret = PTR_ERR(sch);
+		WARN_ON_ONCE(scx_set_enable_state(SCX_DISABLED) != SCX_ENABLING);
 		goto err_free_tid_hash;
 	}
 
 	if (sch->is_cid_type)
 		static_branch_enable(&__scx_is_cid_type);
 
-	/*
-	 * Transition to ENABLING and clear exit info to arm the disable path.
-	 * Failure triggers full disabling from here on.
-	 */
-	WARN_ON_ONCE(scx_set_enable_state(SCX_ENABLING) != SCX_DISABLED);
-	WARN_ON_ONCE(scx_root);
-
 	atomic_long_set(&scx_nr_rejected, 0);
 
 	for_each_possible_cpu(cpu) {
@@ -7591,7 +7631,7 @@ static void scx_root_enable_workfn(struct kthread_work *work)
 		goto err_disable;
 	}
 
-	ret = scx_set_cmask_scratch_alloc(sch);
+	ret = scx_alloc_kern_arena_objs(sch);
 	if (ret) {
 		cpus_read_unlock();
 		goto err_disable;
@@ -8946,10 +8986,17 @@ __bpf_kfunc void scx_bpf_dsq_insert_vtime(struct task_struct *p, u64 dsq_id,
 #ifdef CONFIG_EXT_SUB_SCHED
 	/*
 	 * Disallow if any sub-scheds are attached. There is no way to tell
-	 * which scheduler called us, just error out @p's scheduler.
+	 * which scheduler called us, so error out @p's scheduler -- read it
+	 * under RCU as @p's locks aren't necessarily held here. @p may be a
+	 * task past sched_ext_dead() or an idle task, in which case its
+	 * scheduler can't be determined and there is nothing obviously wrong
+	 * to report; just refuse the call.
 	 */
 	if (unlikely(!list_empty(&sch->children))) {
-		scx_error(scx_task_sched(p), "__scx_bpf_dsq_insert_vtime() must be used");
+		struct scx_sched *tsch = scx_task_sched_rcu(p);
+
+		if (tsch)
+			scx_error(tsch, "__scx_bpf_dsq_insert_vtime() must be used");
 		return;
 	}
 #endif
@@ -10321,7 +10368,8 @@ __bpf_kfunc u32 scx_bpf_nr_cids(void)
  * hotplug, which lets schedulers treat [0, nr_online_cids) as the online
  * range. Schedulers that prefer to handle hotplug without a restart should
  * install a custom mapping via scx_bpf_cid_override() and track onlining
- * through the ops.cid_online / ops.cid_offline callbacks.
+ * through the ops.cid_online / ops.cid_offline callbacks, starting from the
+ * mask scx_bpf_online_cmask() returns.
  */
 __bpf_kfunc u32 scx_bpf_nr_online_cids(void)
 {
@@ -10329,6 +10377,37 @@ __bpf_kfunc u32 scx_bpf_nr_online_cids(void)
 }
 
 /**
+ * scx_bpf_online_cmask - Return the online cid mask in the scheduler arena
+ * @aux: implicit BPF argument to access bpf_prog_aux hidden from BPF progs
+ *
+ * Return a kernel-maintained cmask covering [0, scx_bpf_nr_cids()), or NULL if
+ * the calling program is not associated with a live cid-form scheduler or the
+ * mask is not allocated yet, as in ops.init_cids(). Treat the mask as read-only
+ * even though arena memory stays writable by the BPF scheduler. The mask
+ * follows the SCX hotplug notifications: a cid's bit is updated before
+ * ops.cid_online/offline() runs for it. The pointer is valid from ops.init()
+ * through ops.exit(). Root ops.init() runs with hotplug excluded. Other
+ * contexts can observe concurrent updates.
+ */
+__bpf_kfunc const void *scx_bpf_online_cmask(const struct bpf_prog_aux *aux)
+{
+	struct scx_sched *sch;
+	struct scx_cmask *online;
+
+	guard(rcu)();
+
+	sch = scx_prog_sched(aux);
+	if (unlikely(!sch))
+		return NULL;
+	online = sch->online_cmask;
+	if (unlikely(!online))
+		return NULL;
+
+	/* BPF rebases by the low 32 bits, like __arena callback args */
+	return (void *)((unsigned long)online - sch->arena_kern_base);
+}
+
+/**
  * scx_bpf_this_cid - Return the cid of the CPU this program is running on
  *
  * cid-addressed equivalent of bpf_get_smp_processor_id() for scx programs.
@@ -10691,6 +10770,7 @@ BTF_ID_FLAGS(func, scx_bpf_nr_node_ids)
 BTF_ID_FLAGS(func, scx_bpf_nr_cpu_ids)
 BTF_ID_FLAGS(func, scx_bpf_nr_cids)
 BTF_ID_FLAGS(func, scx_bpf_nr_online_cids)
+BTF_ID_FLAGS(func, scx_bpf_online_cmask, KF_IMPLICIT_ARGS | KF_ARENA_RET)
 BTF_ID_FLAGS(func, scx_bpf_this_cid)
 BTF_ID_FLAGS(func, scx_bpf_get_possible_cpumask, KF_ACQUIRE)
 BTF_ID_FLAGS(func, scx_bpf_get_online_cpumask, KF_ACQUIRE)
diff --git a/kernel/sched/ext/idle.c b/kernel/sched/ext/idle.c
index d2973fb3af6d..aa9fb6de0ad6 100644
--- a/kernel/sched/ext/idle.c
+++ b/kernel/sched/ext/idle.c
@@ -1142,10 +1142,17 @@ __bpf_kfunc s32 scx_bpf_select_cpu_and(struct task_struct *p, s32 prev_cpu, u64
 #ifdef CONFIG_EXT_SUB_SCHED
 	/*
 	 * Disallow if any sub-scheds are attached. There is no way to tell
-	 * which scheduler called us, just error out @p's scheduler.
+	 * which scheduler called us, so error out @p's scheduler -- read it
+	 * under RCU as @p's locks aren't necessarily held here. @p may be a
+	 * task past sched_ext_dead() or an idle task, in which case its
+	 * scheduler can't be determined and there is nothing obviously wrong
+	 * to report; just refuse the call.
 	 */
 	if (unlikely(!list_empty(&sch->children))) {
-		scx_error(scx_task_sched(p), "__scx_bpf_select_cpu_and() must be used");
+		struct scx_sched *tsch = scx_task_sched_rcu(p);
+
+		if (tsch)
+			scx_error(tsch, "__scx_bpf_select_cpu_and() must be used");
 		return -EINVAL;
 	}
 #endif
diff --git a/kernel/sched/ext/internal.h b/kernel/sched/ext/internal.h
index 0967b99a4948..3464e0f113c1 100644
--- a/kernel/sched/ext/internal.h
+++ b/kernel/sched/ext/internal.h
@@ -259,6 +259,9 @@ struct scx_cgroup_init_args {
 	u64			bw_period_us;
 	u64			bw_quota_us;
 	u64			bw_burst_us;
+
+	/* whether the cgroup is configured SCHED_IDLE via cpu.idle */
+	bool			sched_idle;
 };
 
 enum scx_cpu_preempt_reason {
@@ -569,6 +572,12 @@ struct sched_ext_ops {
 	 *
 	 * Specify the %SCX_OPS_KEEP_BUILTIN_IDLE flag to keep the built-in idle
 	 * tracking.
+	 *
+	 * Only actual transitions are reported. A CPU that is claimed with an
+	 * idle pick and kicked but dispatches no task returns to idle without a
+	 * transition. A scheduler tracking idle CPUs itself must restore the
+	 * idle state from ops.dispatch() when it returns without the next task
+	 * to run.
 	 */
 	void (*update_idle)(s32 cpu, bool idle);
 
@@ -1552,6 +1561,7 @@ struct scx_sched {
 	 * and passes it to the callback's __arena argument.
 	 */
 	struct scx_cmask * __percpu *set_cmask_scratch;
+	struct scx_cmask *online_cmask;
 
 	DECLARE_BITMAP(has_op, SCX_OPI_END);
 
@@ -2078,7 +2088,7 @@ void scx_disable_and_exit_task(struct scx_sched *sch, struct task_struct *p);
 void scx_cgroup_lock(void);
 void scx_cgroup_unlock(void);
 #endif
-s32 scx_set_cmask_scratch_alloc(struct scx_sched *sch);
+s32 scx_alloc_kern_arena_objs(struct scx_sched *sch);
 void scx_disable_bypass_dsp(struct scx_sched *sch);
 void scx_bypass(struct scx_sched *sch, bool bypass);
 s32 scx_link_sched(struct scx_sched *sch);
diff --git a/kernel/sched/ext/sub.c b/kernel/sched/ext/sub.c
index 9e7040482bde..34e642a1a403 100644
--- a/kernel/sched/ext/sub.c
+++ b/kernel/sched/ext/sub.c
@@ -1361,6 +1361,7 @@ static s32 scx_cgroup_claim_subtree(struct scx_sched *sch)
 			.bw_period_us = tg->scx.bw_period_us,
 			.bw_quota_us = tg->scx.bw_quota_us,
 			.bw_burst_us = tg->scx.bw_burst_us,
+			.sched_idle = tg->scx.idle,
 		};
 
 		if (tg->scx.sched != parent ||
@@ -1464,6 +1465,7 @@ static void scx_cgroup_return_subtree(struct scx_sched *sch)
 			.bw_period_us = tg->scx.bw_period_us,
 			.bw_quota_us = tg->scx.bw_quota_us,
 			.bw_burst_us = tg->scx.bw_burst_us,
+			.sched_idle = tg->scx.idle,
 		};
 
 		/* the first pass must have transferred everything */
@@ -1803,6 +1805,12 @@ void scx_sub_enable_workfn(struct kthread_work *work)
 		goto err_disable;
 	}
 
+	scoped_guard(cpus_read_lock) {
+		ret = scx_alloc_kern_arena_objs(sch);
+		if (ret)
+			goto err_disable;
+	}
+
 	if (sch->ops.init) {
 		ret = SCX_CALL_OP_RET(sch, init, NULL);
 		if (ret) {
@@ -1813,10 +1821,6 @@ void scx_sub_enable_workfn(struct kthread_work *work)
 		sch->exit_info->flags |= SCX_EFLAG_INITIALIZED;
 	}
 
-	ret = scx_set_cmask_scratch_alloc(sch);
-	if (ret)
-		goto err_disable;
-
 	struct scx_sub_attach_args sub_attach_args = {
 		.ops = &sch->ops,
 		.cgroup_path = sch->cgrp_path,
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ade1eceb39b8..7455a83a6a99 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1032,6 +1032,13 @@ static inline void __max_slice_update(struct sched_entity *se, struct rb_node *n
 	}
 }
 
+static inline void min_vruntime_copy(struct sched_entity *new, struct sched_entity *old)
+{
+	new->min_vruntime = old->min_vruntime;
+	new->min_slice = old->min_slice;
+	new->max_slice = old->max_slice;
+}
+
 /*
  * se->min_vruntime = min(se->vruntime, {left,right}->min_vruntime)
  */
@@ -1059,8 +1066,9 @@ static inline bool min_vruntime_update(struct sched_entity *se, bool exit)
 	       se->max_slice == old_max_slice;
 }
 
-RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity,
-		     run_node, min_vruntime, min_vruntime_update);
+
+RB_DECLARE_CALLBACKS_MULTI(static, min_vruntime_cb, struct sched_entity,
+		     run_node, min_vruntime_copy, min_vruntime_update);
 
 /*
  * Enqueue an entity into the rb-tree:
@@ -1073,6 +1081,8 @@ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	sum_w_vruntime_add(cfs_rq, se);
 	se->min_vruntime = se->vruntime;
 	se->min_slice = se->slice;
+	se->max_slice = se->slice;
+
 	rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
 				__entity_less, &min_vruntime_cb);
 }
@@ -1404,7 +1414,6 @@ static s64 update_se(struct rq *rq, struct sched_entity *se)
 
 	se->exec_start = now;
 	if (entity_is_task(se)) {
-		struct task_struct *donor = task_of(se);
 		struct task_struct *running = rq->curr;
 		/*
 		 * If se is a task, we account the time against the running
@@ -1417,8 +1426,7 @@ static s64 update_se(struct rq *rq, struct sched_entity *se)
 		account_group_exec_runtime(running, delta_exec);
 		account_mm_sched(rq, running, delta_exec);
 
-		/* cgroup time is always accounted against the donor */
-		cgroup_account_cputime(donor, delta_exec);
+		cgroup_account_cputime(running, delta_exec);
 	} else {
 		/* If not task, account the time against donor se  */
 		se->sum_exec_runtime += delta_exec;
diff --git a/kernel/signal.c b/kernel/signal.c
index a5e15bf09d31..d31ebcb6ed4d 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -457,18 +457,42 @@ static void __sigqueue_free(struct sigqueue *q)
 	kmem_cache_free(sigqueue_cachep, q);
 }
 
-void flush_sigqueue(struct sigpending *queue)
+/*
+ * flush_sigqueue_list() can only be invoked without holding sighand::siglock in
+ * the following cases:
+ *
+ *  1) When flushing task::pending _after_ setting task::flags PF_EXITING
+ *
+ *     All functions which try to send a signal to @task will observe PF_EXITING
+ *     and drop the signal.
+ *
+ *  2) When flushing task::signal::shared_pending _after_ the last task in a
+ *     thread group was unhashed and task::sighand is NULL.
+ *
+ *     Nothing can queue a signal anymore because sighand is NULL.
+ */
+static void flush_sigqueue_list(struct list_head *head)
 {
-	struct sigqueue *q;
+	struct sigqueue *q, *tmp;
 
-	sigemptyset(&queue->signal);
-	while (!list_empty(&queue->list)) {
-		q = list_entry(queue->list.next, struct sigqueue , list);
+	list_for_each_entry_safe(q, tmp, head, list) {
 		list_del_init(&q->list);
 		__sigqueue_free(q);
 	}
 }
 
+void flush_sigqueue(struct sigpending *queue)
+{
+	sigemptyset(&queue->signal);
+	flush_sigqueue_list(&queue->list);
+}
+
+static void sigqueue_dequeue_pending(struct sigpending *queue, struct list_head *head)
+{
+	sigemptyset(&queue->signal);
+	list_splice_init(&queue->list, head);
+}
+
 /*
  * Flush all pending signals for this kthread.
  */
@@ -1019,6 +1043,21 @@ static inline bool legacy_queue(struct sigpending *signals, int sig)
 	return (sig < SIGRTMIN) && sigismember(&signals->signal, sig);
 }
 
+/*
+ * When PF_EXITING is set the task is on the way out and has t::pending
+ * flushed already. Prevent queueing of PIDTYPE_PID signals as they would
+ * be leaked.
+ */
+static inline bool task_can_queue_signal(struct task_struct *t, enum pid_type type)
+{
+	lockdep_assert_held(&t->sighand->siglock);
+
+	if (!(t->flags & PF_EXITING))
+		return true;
+
+	return type != PIDTYPE_PID;
+}
+
 static int __send_signal_locked(int sig, struct kernel_siginfo *info,
 				struct task_struct *t, enum pid_type type, bool force)
 {
@@ -1030,6 +1069,10 @@ static int __send_signal_locked(int sig, struct kernel_siginfo *info,
 	lockdep_assert_held(&t->sighand->siglock);
 
 	result = TRACE_SIGNAL_IGNORED;
+
+	if (!task_can_queue_signal(t, type))
+		goto ret;
+
 	if (!prepare_signal(sig, t, force))
 		goto ret;
 
@@ -1892,6 +1935,18 @@ int kill_pid(struct pid *pid, int sig, int priv)
 }
 EXPORT_SYMBOL(kill_pid);
 
+int kill_cad_pid(int sig, int priv)
+{
+	int ret;
+
+	rcu_read_lock();
+	ret = kill_pid(rcu_dereference(cad_pid), sig, priv);
+	rcu_read_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL(kill_cad_pid);
+
 #ifdef CONFIG_POSIX_TIMERS
 /*
  * These functions handle POSIX timer signals. POSIX timers use
@@ -1968,11 +2023,25 @@ static inline struct task_struct *posixtimer_get_target(struct k_itimer *tmr)
 	struct task_struct *t = pid_task(tmr->it_pid, tmr->it_pid_type);
 
 	if (t && tmr->it_pid_type != PIDTYPE_PID &&
-	    same_thread_group(t, current) && !current->exit_state)
+	    same_thread_group(t, current) && !(current->flags & PF_EXITING))
 		t = current;
 	return t;
 }
 
+/*
+ * Find the target task for the POSIX timer signal and prevent that a
+ * PIDTYPE_PID signal is queued on a task which has PF_EXITING set.
+ */
+static inline struct task_struct *posixtimer_get_unignore_target(struct k_itimer *tmr)
+{
+	struct task_struct *t = posixtimer_get_target(tmr);
+
+	if (t && task_can_queue_signal(t, tmr->it_pid_type))
+		return t;
+
+	return NULL;
+}
+
 void posixtimer_send_sigqueue(struct k_itimer *tmr)
 {
 	struct sigqueue *q = &tmr->sigq;
@@ -1990,6 +2059,9 @@ void posixtimer_send_sigqueue(struct k_itimer *tmr)
 	if (!likely(lock_task_sighand(t, &flags)))
 		return;
 
+	if (!task_can_queue_signal(t, tmr->it_pid_type))
+		goto unlock;
+
 	/*
 	 * Update @tmr::sigqueue_seq for posix timer signals with sighand
 	 * locked to prevent a race against dequeue_signal().
@@ -2081,6 +2153,7 @@ void posixtimer_send_sigqueue(struct k_itimer *tmr)
 	result = TRACE_SIGNAL_DELIVERED;
 out:
 	trace_signal_generate(sig, &q->info, t, tmr->it_pid_type != PIDTYPE_PID, result);
+unlock:
 	unlock_task_sighand(t, &flags);
 }
 
@@ -2136,7 +2209,7 @@ static void posixtimer_sig_unignore(struct task_struct *tsk, int sig)
 		 * has exited by now, drop the reference count.
 		 */
 		guard(rcu)();
-		target = posixtimer_get_target(tmr);
+		target = posixtimer_get_unignore_target(tmr);
 		if (target)
 			posixtimer_queue_sigqueue(&tmr->sigq, target, tmr->it_pid_type);
 		else
@@ -3120,42 +3193,36 @@ static void retarget_shared_pending(struct task_struct *tsk, sigset_t *which)
 
 void exit_signals(struct task_struct *tsk)
 {
+	LIST_HEAD(sigq_list);
 	int group_stop = 0;
-	sigset_t unblocked;
 
 	/*
 	 * @tsk is about to have PF_EXITING set - lock out users which
-	 * expect stable threadgroup.
+	 * expect a stable threadgroup.
 	 */
 	cgroup_threadgroup_change_begin(tsk);
 
-	if (thread_group_empty(tsk) || (tsk->signal->flags & SIGNAL_GROUP_EXIT)) {
+	scoped_guard(spinlock_irq, &tsk->sighand->siglock) {
 		tsk->flags |= PF_EXITING;
-		cgroup_threadgroup_change_end(tsk);
-		return;
-	}
 
-	spin_lock_irq(&tsk->sighand->siglock);
-	/*
-	 * From now this task is not visible for group-wide signals,
-	 * see wants_signal(), do_signal_stop().
-	 */
-	tsk->flags |= PF_EXITING;
+		sigqueue_dequeue_pending(&tsk->pending, &sigq_list);
 
-	cgroup_threadgroup_change_end(tsk);
+		if (task_sigpending(tsk) && !thread_group_empty(tsk) &&
+		    !(tsk->signal->flags & SIGNAL_GROUP_EXIT)) {
+			sigset_t unblocked = tsk->blocked;
 
-	if (!task_sigpending(tsk))
-		goto out;
+			signotset(&unblocked);
+			retarget_shared_pending(tsk, &unblocked);
 
-	unblocked = tsk->blocked;
-	signotset(&unblocked);
-	retarget_shared_pending(tsk, &unblocked);
+			if (unlikely(tsk->jobctl & JOBCTL_STOP_PENDING) &&
+			    task_participate_group_stop(tsk))
+				group_stop = CLD_STOPPED;
+		}
+	}
 
-	if (unlikely(tsk->jobctl & JOBCTL_STOP_PENDING) &&
-	    task_participate_group_stop(tsk))
-		group_stop = CLD_STOPPED;
-out:
-	spin_unlock_irq(&tsk->sighand->siglock);
+	cgroup_threadgroup_change_end(tsk);
+
+	flush_sigqueue_list(&sigq_list);
 
 	/*
 	 * If group stop has completed, deliver the notification.  This
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 0014d163f989..62ad7c000386 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -615,34 +615,41 @@ void clockevents_handle_noop(struct clock_event_device *dev)
 {
 }
 
-/**
- * clockevents_exchange_device - release and request clock devices
- * @old:	device to release (can be NULL)
- * @new:	device to request (can be NULL)
- *
- * Called from various tick functions with clockevents_lock held and
- * interrupts disabled.
- */
-void clockevents_exchange_device(struct clock_event_device *old,
-				 struct clock_event_device *new)
+void __clockevents_exchange_device(struct clock_event_device *old,
+				   struct clock_event_device *new)
 {
 	/*
 	 * Caller releases a clock event device. We queue it into the
 	 * released list and do a notify add later.
 	 */
 	if (old) {
-		module_put(old->owner);
 		clockevents_switch_state(old, CLOCK_EVT_STATE_DETACHED);
 		list_move(&old->list, &clockevents_released);
 	}
 
 	if (new) {
-		BUG_ON(!clockevent_state_detached(new));
+		WARN_ON(!clockevent_state_detached(new));
 		clockevents_shutdown(new);
 	}
 }
 
 /**
+ * clockevents_exchange_device - release and request clock devices
+ * @old:	device to release (can be NULL)
+ * @new:	device to request (can be NULL)
+ *
+ * Called from various tick functions with clockevents_lock held and
+ * interrupts disabled.
+ */
+void clockevents_exchange_device(struct clock_event_device *old,
+				 struct clock_event_device *new)
+{
+	__clockevents_exchange_device(old, new);
+	if (old)
+		module_put(old->owner);
+}
+
+/**
  * clockevents_suspend - suspend clock devices
  */
 void clockevents_suspend(void)
@@ -699,7 +706,7 @@ void tick_offline_cpu(unsigned int cpu)
 		if (cpumask_test_cpu(cpu, dev->cpumask) &&
 		    cpumask_weight(dev->cpumask) == 1 &&
 		    !tick_is_broadcast_device(dev)) {
-			BUG_ON(!clockevent_state_detached(dev));
+			WARN_ON(!clockevent_state_detached(dev));
 			list_del(&dev->list);
 		}
 	}
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 530d61257b9a..cbf1693c86b3 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1263,13 +1263,23 @@ remove_and_enqueue_same_base(struct hrtimer *timer, struct hrtimer_clock_base *b
 {
 	bool was_first = false;
 
+	/*
+	 * Updating the sort key while @timer is queued can temporarily
+	 * make the tree inconsistent. This is safe under cpu_base->lock:
+	 * no other queue operation can observe that state.
+	 * hrtimer_can_update_in_place() either confirms that the new expiry
+	 * fits between the neighbours or timerqueue_linked_del() removes the
+	 * timer without consulting the expiry.
+	 */
+	hrtimer_set_expires_range_ns(timer, expires, delta_ns);
+	expires = hrtimer_get_expires(timer);
+
 	/* Remove it from the timer queue if active */
 	if (timer->is_queued) {
 		was_first = !timerqueue_linked_prev(&timer->node);
 
 		/* Try to update in place to avoid the de/enqueue dance */
 		if (hrtimer_can_update_in_place(timer, base, expires)) {
-			hrtimer_set_expires_range_ns(timer, expires, delta_ns);
 			trace_hrtimer_start(timer, mode, true);
 			if (was_first)
 				base->expires_next = expires;
@@ -1280,9 +1290,6 @@ remove_and_enqueue_same_base(struct hrtimer *timer, struct hrtimer_clock_base *b
 		timerqueue_linked_del(&base->active, &timer->node);
 	}
 
-	/* Set the new expiry time */
-	hrtimer_set_expires_range_ns(timer, expires, delta_ns);
-
 	debug_activate(timer, mode, timer->is_queued);
 	base->cpu_base->active_bases |= 1 << base->index;
 
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 213ae1d6a014..80c354811538 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -136,6 +136,8 @@ static int sysctl_k2u_int_conv_userhz(bool *negp, ulong *u_ptr, const int *k_ptr
 
 static ulong sysctl_msecs_to_jiffies(const ulong val)
 {
+	if (val > jiffies_to_msecs(MAX_JIFFY_OFFSET))
+		return MAX_JIFFY_OFFSET;
 	return msecs_to_jiffies(val);
 }
 
@@ -181,7 +183,7 @@ static int do_proc_int_conv_ms_jiffies_minmax(bool *negp, ulong *u_ptr,
 					      int *k_ptr, int dir,
 					      const struct ctl_table *tbl)
 {
-	return proc_int_conv(negp, u_ptr, k_ptr, dir, tbl, false,
+	return proc_int_conv(negp, u_ptr, k_ptr, dir, tbl, true,
 			     sysctl_u2k_int_conv_ms, sysctl_k2u_int_conv_ms);
 }
 
@@ -195,10 +197,10 @@ static int sysctl_k2u_ulong_conv_ms(ulong *u_ptr, const ulong *k_ptr)
 	return proc_ulong_k2u_conv_kop(u_ptr, k_ptr, sysctl_jiffies_to_msecs);
 }
 
-static int do_proc_ulong_conv_ms_jiffies(bool *negp, ulong *u_ptr, ulong *k_ptr,
-					 int dir, const struct ctl_table *tbl)
+static int do_proc_ulong_conv_ms_jiffies_minmax(bool *negp, ulong *u_ptr, ulong *k_ptr,
+						int dir, const struct ctl_table *tbl)
 {
-	return proc_ulong_conv(u_ptr, k_ptr, dir, tbl, false,
+	return proc_ulong_conv(u_ptr, k_ptr, dir, tbl, true,
 			       sysctl_u2k_ulong_conv_ms, sysctl_k2u_ulong_conv_ms);
 }
 
@@ -229,8 +231,8 @@ static int do_proc_int_conv_ms_jiffies_minmax(bool *negp, ulong *u_ptr,
 	return -ENOSYS;
 }
 
-static int do_proc_ulong_conv_ms_jiffies(bool *negp, ulong *u_ptr, ulong *k_ptr,
-					 int dir, const struct ctl_table *tbl)
+static int do_proc_ulong_conv_ms_jiffies_minmax(bool *negp, ulong *u_ptr, ulong *k_ptr,
+						int dir, const struct ctl_table *tbl)
 {
 	return -ENOSYS;
 }
@@ -333,7 +335,7 @@ int proc_doulongvec_ms_jiffies_minmax(const struct ctl_table *table, int dir,
 				      void *buffer, size_t *lenp, loff_t *ppos)
 {
 	return proc_doulongvec_conv(table, dir, buffer, lenp, ppos,
-				    do_proc_ulong_conv_ms_jiffies);
+				    do_proc_ulong_conv_ms_jiffies_minmax);
 }
 EXPORT_SYMBOL(proc_doulongvec_ms_jiffies_minmax);
 
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index d73d31c7994f..0bf4fcd969c8 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -408,6 +408,7 @@ static int posix_cpu_timer_create(struct k_itimer *new_timer)
 
 	new_timer->kclock = &clock_posix_cpu;
 	timerqueue_init(&new_timer->it.cpu.node);
+	INIT_LIST_HEAD(&new_timer->it.cpu.elist);
 	new_timer->it.cpu.pid = get_pid(pid);
 	rcu_read_unlock();
 	return 0;
@@ -566,6 +567,24 @@ static struct task_struct *timer_lock_sighand(struct k_itimer *timer, unsigned l
 }
 
 /*
+ * If the timer is queued on the expiry list, then it cannot be dequeued because
+ * the firing list is not protected by sighand->lock. The delivery path is
+ * waiting for the timer lock. So go back, unlock and retry.
+ */
+static bool posix_cpu_timer_on_expiry_list(struct k_itimer *timer)
+{
+	if (list_empty(&timer->it.cpu.elist))
+		return false;
+
+	/*
+	 * Prevent signal delivery as there is no point in delivering a signal
+	 * which is made obsolete right away.
+	 */
+	timer->it.cpu.firing = false;
+	return true;
+}
+
+/*
  * Clean up a CPU-clock timer that is about to be destroyed.
  * This is called from timer deletion with the timer already locked.
  * If we return TIMER_RETRY, it's necessary to release the timer's lock
@@ -580,18 +599,10 @@ static int posix_cpu_timer_del(struct k_itimer *timer)
 	p = timer_lock_sighand(timer, &flags);
 
 	if (likely(p)) {
-		if (timer->it.cpu.firing) {
-			/*
-			 * Prevent signal delivery. The timer cannot be dequeued
-			 * because it is on the firing list which is not protected
-			 * by sighand->lock. The delivery path is waiting for
-			 * the timer lock. So go back, unlock and retry.
-			 */
-			timer->it.cpu.firing = false;
+		if (posix_cpu_timer_on_expiry_list(timer))
 			ret = TIMER_RETRY;
-		} else {
+		else
 			disarm_timer(timer, p);
-		}
 		unlock_task_sighand(p, &flags);
 	}
 
@@ -731,14 +742,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 	/* Retrieve the current expiry time before disarming the timer */
 	old_expires = cpu_timer_getexpires(ctmr);
 
-	if (unlikely(timer->it.cpu.firing)) {
-		/*
-		 * Prevent signal delivery. The timer cannot be dequeued
-		 * because it is on the firing list which is not protected
-		 * by sighand->lock. The delivery path is waiting for
-		 * the timer lock. So go back, unlock and retry.
-		 */
-		timer->it.cpu.firing = false;
+	if (posix_cpu_timer_on_expiry_list(timer)) {
 		ret = TIMER_RETRY;
 	} else {
 		cpu_timer_dequeue(ctmr);
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 115e0bf01276..bda3d2391a60 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -165,23 +165,31 @@ static bool tick_set_oneshot_wakeup_device(struct clock_event_device *newdev,
  */
 void tick_install_broadcast_device(struct clock_event_device *dev, int cpu)
 {
-	struct clock_event_device *cur = tick_broadcast_device.evtdev;
+	struct clock_event_device *cur;
 
-	if (tick_set_oneshot_wakeup_device(dev, cpu))
-		return;
+	scoped_guard(raw_spinlock_irqsave, &tick_broadcast_lock) {
 
-	if (!tick_check_broadcast_device(cur, dev))
-		return;
+		if (tick_set_oneshot_wakeup_device(dev, cpu))
+			return;
 
-	if (!try_module_get(dev->owner))
-		return;
+		cur = tick_broadcast_device.evtdev;
+		if (!tick_check_broadcast_device(cur, dev))
+			return;
 
-	clockevents_exchange_device(cur, dev);
+		if (!try_module_get(dev->owner))
+			return;
+
+		__clockevents_exchange_device(cur, dev);
+		if (cur)
+			cur->event_handler = clockevents_handle_noop;
+		WRITE_ONCE(tick_broadcast_device.evtdev, dev);
+		if (!cpumask_empty(tick_broadcast_mask))
+			tick_broadcast_start_periodic(dev);
+	}
+
+	/* Module release must be outside of the lock */
 	if (cur)
-		cur->event_handler = clockevents_handle_noop;
-	tick_broadcast_device.evtdev = dev;
-	if (!cpumask_empty(tick_broadcast_mask))
-		tick_broadcast_start_periodic(dev);
+		module_put(cur->owner);
 
 	if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT))
 		return;
@@ -1218,7 +1226,7 @@ int tick_broadcast_oneshot_active(void)
  */
 bool tick_broadcast_oneshot_available(void)
 {
-	struct clock_event_device *bc = tick_broadcast_device.evtdev;
+	struct clock_event_device *bc = READ_ONCE(tick_broadcast_device.evtdev);
 
 	return bc ? bc->features & CLOCK_EVT_FEAT_ONESHOT : false;
 }
@@ -1226,7 +1234,7 @@ bool tick_broadcast_oneshot_available(void)
 #else
 int __tick_broadcast_oneshot_control(enum tick_broadcast_state state)
 {
-	struct clock_event_device *bc = tick_broadcast_device.evtdev;
+	struct clock_event_device *bc = READ_ONCE(tick_broadcast_device.evtdev);
 
 	if (!bc || (bc->features & CLOCK_EVT_FEAT_HRTIMER))
 		return -EBUSY;
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 182974c4f21b..65680db95053 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -55,6 +55,8 @@ static inline void clockevent_set_state(struct clock_event_device *dev,
 }
 
 extern void clockevents_shutdown(struct clock_event_device *dev);
+extern void __clockevents_exchange_device(struct clock_event_device *old,
+					  struct clock_event_device *new);
 extern void clockevents_exchange_device(struct clock_event_device *old,
 					struct clock_event_device *new);
 extern void clockevents_switch_state(struct clock_event_device *dev,
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 40d373d65f9b..ed455b53513b 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -143,9 +143,6 @@ enum {
 #define FGRAPH_DATA_INDEX_MASK	GENMASK(FGRAPH_DATA_INDEX_BITS - 1, 0)
 #define FGRAPH_DATA_INDEX_SHIFT	(FGRAPH_DATA_SHIFT + FGRAPH_DATA_BITS)
 
-#define FGRAPH_MAX_INDEX	\
-	((FGRAPH_INDEX_SIZE << FGRAPH_DATA_BITS) + FGRAPH_RET_INDEX)
-
 #define FGRAPH_ARRAY_SIZE	FGRAPH_INDEX_BITS
 
 /*
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 53d5db60bfa5..673a54fdf392 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -6675,7 +6675,7 @@ int update_ftrace_direct_mod(struct ftrace_ops *ops, struct ftrace_hash *hash, b
 
 	/* Enable the tmp_ops to have the same functions as the hash object. */
 	ftrace_ops_init(&tmp_ops);
-	tmp_ops.func_hash->filter_hash = hash;
+	rcu_assign_pointer(tmp_ops.func_hash->filter_hash, hash);
 
 	err = register_ftrace_function_nolock(&tmp_ops);
 	if (err)
diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c
index 5a8bdf88999a..87a27f3aa4a6 100644
--- a/kernel/trace/rethook.c
+++ b/kernel/trace/rethook.c
@@ -171,7 +171,7 @@ struct rethook_node *rethook_try_get(struct rethook *rh)
 	 * This expects the caller will set up a rethook on a function entry.
 	 * When the function returns, the rethook will eventually be reclaimed
 	 * or released in the rethook_recycle() with call_rcu().
-	 * This means the caller must be run in the RCU-availabe context.
+	 * This means the caller must be run in the RCU-available context.
 	 */
 	if (unlikely(!rcu_is_watching()))
 		return NULL;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 9c03a555a6ba..04bb94c29f58 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -904,14 +904,13 @@ static void rb_wake_up_waiters(struct irq_work *work)
 		struct ring_buffer_per_cpu *cpu_buffer =
 			container_of(rbwork, struct ring_buffer_per_cpu, irq_work);
 
-		/* Called from interrupt context */
-		raw_spin_lock(&cpu_buffer->reader_lock);
-		rbwork->wakeup_full = false;
-		rbwork->full_waiters_pending = false;
+		scoped_guard(raw_spinlock_irqsave, &cpu_buffer->reader_lock) {
+			rbwork->wakeup_full = false;
+			rbwork->full_waiters_pending = false;
 
-		/* Waking up all waiters, they will reset the shortest full */
-		cpu_buffer->shortest_full = 0;
-		raw_spin_unlock(&cpu_buffer->reader_lock);
+			/* Waking up all waiters, they will reset the shortest full */
+			cpu_buffer->shortest_full = 0;
+		}
 
 		wake_up_all(&rbwork->full_waiters);
 	}
@@ -7384,7 +7383,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_read_page_data);
 
 /**
  * ring_buffer_read_page_size - get size of the read page.
- * @page:  the page to get the size from
+ * @rpage:  the page to get the size from
  *
  * Returns size of the page in bytes.
  */
@@ -7474,6 +7473,14 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
 
 	old_capacity = rb_subbuf_capacity(buffer);
 
+	/* The mmap fast path reads subbuf_order without buffer->mutex. */
+	for_each_buffer_cpu(buffer, cpu) {
+		if (!cpumask_test_cpu(cpu, buffer->cpumask))
+			continue;
+		if (atomic_read(&buffer->buffers[cpu]->resize_disabled))
+			return -EBUSY;
+	}
+
 	atomic_inc(&buffer->record_disabled);
 
 	/* Make sure all commits have finished */
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8658cad53cb5..e4a490d3d08c 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -7717,12 +7717,55 @@ trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt,
 	return cnt;
 }
 
+static bool tr_option_match(struct trace_array *tr, void *topt)
+{
+	for (int i = 0; i < tr->nr_topts; i++) {
+		struct trace_options *tr_topts = &tr->topts[i];
+
+		if (topt >= (void *)&tr_topts->topts[0] &&
+		    topt < (void *)&tr_topts->topts[tr_topts->nr_topts])
+			return true;
+	}
+	return false;
+}
+
+/*
+ * The topt is the address of a trace_array->topts[] element that holds the
+ * the tracer options descriptor. But since the trace_array reference has not
+ * been taken yet, it cannot be dereferenced as it could have been freed by
+ * a rmdir of the instance the trace_array represents.
+ *
+ * Search the list of trace_arrays and compare the topt to the address of
+ * the entire trace_array topts array for each trace_array in the list.
+ * If one is matched, then take the reference and return it. If not, the
+ * trace_array no longer exits.
+ */
+static int trace_array_tracer_options_get(void *topt)
+{
+	struct trace_array *tr;
+	int ret;
+
+	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	if (ret)
+		return ret;
+
+	if (tracing_disabled)
+		return -ENODEV;
+
+	guard(mutex)(&trace_types_lock);
+	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+		if (tr_option_match(tr, topt))
+			return __trace_array_get(tr);
+	}
+	return -ENODEV;
+}
+
 static int tracing_open_options(struct inode *inode, struct file *filp)
 {
 	struct trace_option_dentry *topt = inode->i_private;
 	int ret;
 
-	ret = tracing_check_open_get_tr(topt->tr);
+	ret = trace_array_tracer_options_get(topt);
 	if (ret)
 		return ret;
 
@@ -7984,6 +8027,7 @@ create_trace_option_files(struct trace_array *tr, struct tracer *tracer,
 	tr->topts = tr_topts;
 	tr->topts[tr->nr_topts].tracer = tracer;
 	tr->topts[tr->nr_topts].topts = topts;
+	tr->topts[tr->nr_topts].nr_topts = cnt;
 	tr->nr_topts++;
 
 	for (cnt = 0; opts[cnt].name; cnt++) {
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 5e76f94e7a80..3749485a7d85 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -227,6 +227,7 @@ struct array_buffer {
 struct trace_options {
 	struct tracer			*tracer;
 	struct trace_option_dentry	*topts;
+	int				nr_topts;
 };
 
 struct trace_pid_list *trace_pid_list_alloc(void);
@@ -1952,6 +1953,7 @@ struct event_trigger_data {
 
 struct enable_trigger_data {
 	struct trace_event_file		*file;
+	struct trace_event_call		*call;
 	bool				enable;
 	bool				hist;
 };
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 9dbc2441763b..30c0ddf90887 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1489,6 +1489,8 @@ int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set)
 	/* Put back the colon to allow this to be called again */
 	if (buf)
 		*(buf - 1) = ':';
+	if (mod)
+		*(mod - 5) = ':';
 
 	return ret;
 }
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 963e0d6b61fd..8af97fd4ee2d 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -169,7 +169,6 @@ struct hist_field {
 	struct hist_field		*operands[HIST_FIELD_OPERANDS_MAX];
 	struct hist_trigger_data	*hist_data;
 	enum hist_field_fn		fn_num;
-	unsigned int			ref;
 	unsigned int			size;
 	unsigned int			offset;
 	unsigned int                    is_signed;
@@ -1913,16 +1912,8 @@ out:
 	return field_op;
 }
 
-static void get_hist_field(struct hist_field *hist_field)
-{
-	hist_field->ref++;
-}
-
 static void __destroy_hist_field(struct hist_field *hist_field)
 {
-	if (--hist_field->ref > 1)
-		return;
-
 	kfree(hist_field->var.name);
 	kfree(hist_field->name);
 
@@ -1969,8 +1960,6 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
 	if (!hist_field)
 		return NULL;
 
-	hist_field->ref = 1;
-
 	hist_field->hist_data = hist_data;
 
 	if (flags & HIST_FIELD_FL_EXPR || flags & HIST_FIELD_FL_ALIAS)
@@ -2223,10 +2212,8 @@ static struct hist_field *create_var_ref(struct hist_trigger_data *hist_data,
 	for (i = 0; i < hist_data->n_var_refs; i++) {
 		ref_field = hist_data->var_refs[i];
 		if (ref_field->var.idx == var_field->var.idx &&
-		    ref_field->var.hist_data == var_field->hist_data) {
-			get_hist_field(ref_field);
+		    ref_field->var.hist_data == var_field->hist_data)
 			return ref_field;
-		}
 	}
 	/* Sanity check to avoid out-of-bound write on 'hist_data->var_refs' */
 	if (hist_data->n_var_refs >= TRACING_MAP_VARS_MAX)
@@ -2234,7 +2221,7 @@ static struct hist_field *create_var_ref(struct hist_trigger_data *hist_data,
 	ref_field = create_hist_field(var_field->hist_data, NULL, flags, NULL);
 	if (ref_field) {
 		if (init_var_ref(ref_field, var_field, system, event_name)) {
-			destroy_hist_field(ref_field, 0);
+			__destroy_hist_field(ref_field);
 			return NULL;
 		}
 
@@ -2330,6 +2317,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
 	struct ftrace_event_field *field = NULL;
 	char *field_name, *modifier, *str;
 	struct trace_array *tr = file->tr;
+	bool stack_modifier = false;
 
 	modifier = str = kstrdup(field_str, GFP_KERNEL);
 	if (!modifier)
@@ -2352,9 +2340,10 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
 			*flags |= HIST_FIELD_FL_EXECNAME;
 		else if (strcmp(modifier, "syscall") == 0)
 			*flags |= HIST_FIELD_FL_SYSCALL;
-		else if (strcmp(modifier, "stacktrace") == 0)
+		else if (strcmp(modifier, "stacktrace") == 0) {
 			*flags |= HIST_FIELD_FL_STACKTRACE;
-		else if (strcmp(modifier, "log2") == 0)
+			stack_modifier = true;
+		} else if (strcmp(modifier, "log2") == 0)
 			*flags |= HIST_FIELD_FL_LOG2;
 		else if (strcmp(modifier, "usecs") == 0)
 			*flags |= HIST_FIELD_FL_TIMESTAMP_USECS;
@@ -2415,6 +2404,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
 				*flags |= HIST_FIELD_FL_CPU;
 			} else if (field && field->filter_type == FILTER_STACKTRACE) {
 				*flags |= HIST_FIELD_FL_STACKTRACE;
+				field = NULL;
 			} else if (field && field->filter_type == FILTER_COMM) {
 				*flags |= HIST_FIELD_FL_COMM | HIST_FIELD_FL_STRING;
 			} else {
@@ -2425,6 +2415,12 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
 			}
 		}
 	}
+
+	if (stack_modifier &&
+	    (!field || field->filter_type != FILTER_STACKTRACE)) {
+		hist_err(tr, HIST_ERR_BAD_FIELD_MODIFIER, errpos(field_str));
+		field = ERR_PTR(-EINVAL);
+	}
  out:
 	kfree(str);
 
@@ -3276,7 +3272,6 @@ static struct hist_field *create_var(struct hist_trigger_data *hist_data,
 		goto out;
 	}
 
-	var->ref = 1;
 	var->flags = HIST_FIELD_FL_VAR;
 	var->var.idx = idx;
 	var->var.hist_data = var->hist_data = hist_data;
@@ -4313,8 +4308,7 @@ static int __create_val_field(struct hist_trigger_data *hist_data,
 			goto err;
 	} else {
 		/* Value */
-		if (hist_field->flags & (HIST_FIELD_FL_GRAPH | HIST_FIELD_FL_PERCENT |
-					 HIST_FIELD_FL_BUCKET | HIST_FIELD_FL_LOG2 |
+		if (hist_field->flags & (HIST_FIELD_FL_BUCKET | HIST_FIELD_FL_LOG2 |
 					 HIST_FIELD_FL_SYM | HIST_FIELD_FL_SYM_OFFSET |
 					 HIST_FIELD_FL_SYSCALL | HIST_FIELD_FL_STACKTRACE))
 			goto err;
@@ -4331,6 +4325,7 @@ static int __create_val_field(struct hist_trigger_data *hist_data,
 	return ret;
  err:
 	hist_err(file->tr, HIST_ERR_BAD_FIELD_MODIFIER, errpos(field_str));
+	destroy_hist_field(hist_field, 0);
 	return -EINVAL;
 }
 
@@ -5690,7 +5685,7 @@ static int print_entries(struct seq_file *m,
 {
 	struct tracing_map_sort_entry **sort_entries = NULL;
 	struct tracing_map *map = hist_data->map;
-	int i, j, n_entries;
+	int i, j, n_entries, ret;
 	struct hist_val_stat *stats = NULL;
 	u64 val;
 
@@ -5700,6 +5695,8 @@ static int print_entries(struct seq_file *m,
 	if (n_entries < 0)
 		return n_entries;
 
+	ret = n_entries;
+
 	/* Calculate the max and the total for each field if needed. */
 	for (j = 0; j < hist_data->n_vals; j++) {
 		if (!(hist_data->fields[j]->flags &
@@ -5708,7 +5705,7 @@ static int print_entries(struct seq_file *m,
 		if (!stats) {
 			stats = kzalloc_objs(*stats, hist_data->n_vals);
 			if (!stats) {
-				n_entries = -ENOMEM;
+				ret = -ENOMEM;
 				goto out;
 			}
 		}
@@ -5729,7 +5726,7 @@ static int print_entries(struct seq_file *m,
 out:
 	tracing_map_destroy_sort_entries(sort_entries, n_entries);
 
-	return n_entries;
+	return ret;
 }
 
 static void hist_trigger_show(struct seq_file *m,
@@ -6383,17 +6380,18 @@ static int event_hist_trigger_named_init(struct event_trigger_data *data)
 {
 	int ret;
 
-	data->ref++;
-
-	save_named_trigger(data->named_data->name, data);
-
 	ret = event_hist_trigger_init(data->named_data);
 	if (ret < 0) {
 		kfree(data->cmd_ops);
 		data->cmd_ops = &trigger_hist_cmd;
+		return ret;
 	}
 
-	return ret;
+	data->ref++;
+
+	save_named_trigger(data->named_data->name, data);
+
+	return 0;
 }
 
 static void event_hist_trigger_named_free(struct event_trigger_data *data)
@@ -6643,12 +6641,6 @@ static int hist_register_trigger(char *glob,
 		data->cmd_ops = cmd_ops;
 	}
 
-	if (data->cmd_ops->init) {
-		ret = data->cmd_ops->init(data);
-		if (ret < 0)
-			goto out;
-	}
-
 	if (hist_data->enable_timestamps) {
 		char *clock = hist_data->attrs->clock;
 
@@ -6661,6 +6653,15 @@ static int hist_register_trigger(char *glob,
 		tracing_set_filter_buffering(file->tr, true);
 	}
 
+	if (data->cmd_ops->init) {
+		ret = data->cmd_ops->init(data);
+		if (ret < 0) {
+			if (hist_data->enable_timestamps)
+				tracing_set_filter_buffering(file->tr, false);
+			goto out;
+		}
+	}
+
 	if (named_data) {
 		remove_hist_vars(hist_data);
 		destroy_hist_data(hist_data);
@@ -6678,11 +6679,12 @@ static int hist_trigger_enable(struct event_trigger_data *data,
 
 	update_cond_flag(file);
 
-	if (trace_event_trigger_enable_disable(file, 1) < 0) {
-		list_del_rcu(&data->list);
-		update_cond_flag(file);
+	/*
+	 * On failure the caller undoes the registration, and
+	 * hist_unregister_trigger() can only find the trigger here.
+	 */
+	if (trace_event_trigger_enable_disable(file, 1) < 0)
 		ret--;
-	}
 
 	return ret;
 }
@@ -6760,13 +6762,13 @@ static void hist_unregister_trigger(char *glob,
 		}
 	}
 
-	if (test && test->cmd_ops->free)
-		test->cmd_ops->free(test);
-
 	if (hist_data->enable_timestamps) {
 		if (!hist_data->remove || test)
 			tracing_set_filter_buffering(file->tr, false);
 	}
+
+	if (test && test->cmd_ops->free)
+		test->cmd_ops->free(test);
 }
 
 static bool hist_file_check_refs(struct trace_event_file *file)
@@ -6971,6 +6973,8 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
 	return ret;
  out_unreg:
 	event_trigger_unregister(cmd_ops, file, glob+1, trigger_data);
+	/* The unregister frees trigger_data, skip out_free */
+	goto out;
  out_free:
 	remove_hist_vars(hist_data);
 
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 149300cc5e8a..4d2fde996c0f 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -1728,7 +1728,8 @@ static void enable_trigger_private_data_free(struct event_trigger_data *data)
 {
 	struct enable_trigger_data *enable_data = data->private_data;
 
-	trace_event_put_ref(enable_data->file->event_call);
+	/* The file may already be freed here, only the call is kept alive */
+	trace_event_put_ref(enable_data->call);
 	kfree(enable_data);
 }
 
@@ -1801,6 +1802,7 @@ int event_enable_trigger_parse(struct event_command *cmd_ops,
 	enable_data->hist = hist;
 	enable_data->enable = enable;
 	enable_data->file = event_enable_file;
+	enable_data->call = event_enable_file->event_call;
 
 	trigger_data = trigger_data_alloc(cmd_ops, cmd, param, enable_data);
 	if (!trigger_data)
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index 93cda2f6f269..f658c3a77aa7 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -1122,10 +1122,9 @@ static void user_event_destroy_validators(struct user_event *user)
 	}
 }
 
-static void user_event_destroy_fields(struct user_event *user)
+static void user_event_destroy_fields(struct list_head *head)
 {
 	struct ftrace_event_field *field, *next;
-	struct list_head *head = &user->fields;
 
 	list_for_each_entry_safe(field, next, head, link) {
 		list_del(&field->link);
@@ -1502,17 +1501,32 @@ static int user_event_set_call_visible(struct user_event *user, bool visible)
 
 static int destroy_user_event(struct user_event *user)
 {
+	LIST_HEAD(fields);
 	int ret = 0;
 
 	lockdep_assert_held(&event_mutex);
 
-	/* Must destroy fields before call removal */
-	user_event_destroy_fields(user);
+	/*
+	 * Detach the fields before removing the call. Removing the event
+	 * frees the field list memory (trace_destroy_fields() is run on
+	 * successful removal and kmem_cache_free()s the fields), but the
+	 * fields here are allocated and owned by user_events. Destroy
+	 * them separately once removal has succeeded.
+	 */
+	list_splice_init(&user->fields, &fields);
 
 	ret = user_event_set_call_visible(user, false);
 
-	if (ret)
+	if (ret) {
+		/*
+		 * Removal failed and the event stays registered, recover
+		 * the fields so it is left in a consistent state.
+		 */
+		list_splice(&fields, &user->fields);
 		return ret;
+	}
+
+	user_event_destroy_fields(&fields);
 
 	dyn_event_remove(&user->devent);
 	hash_del(&user->node);
@@ -2212,7 +2226,7 @@ static int user_event_parse(struct user_event_group *group, char *name,
 put_user_lock:
 	mutex_unlock(&event_mutex);
 put_user:
-	user_event_destroy_fields(user);
+	user_event_destroy_fields(&user->fields);
 	user_event_destroy_validators(user);
 	kfree(user->call.print_fmt);
 
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index ff7cb1a76b95..c5befd0c5b9a 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -52,6 +52,7 @@ struct fgraph_data {
 	};
 	struct ftrace_graph_ret_entry	ret;
 	int				failed;
+	int				ent_size;
 	int				cpu;
 };
 
@@ -1274,6 +1275,7 @@ print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
 		if (s->full) {
 			data->failed = 1;
 			data->cpu = cpu;
+			data->ent_size = iter->ent_size;
 		} else
 			data->failed = 0;
 	}
@@ -1457,6 +1459,7 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 	if (data && data->failed) {
 		field = &data->ent.ent;
 		iter->cpu = data->cpu;
+		iter->ent_size = data->ent_size;
 		ret = print_graph_entry(field, s, iter, flags);
 		if (ret == TRACE_TYPE_HANDLED && iter->cpu != cpu) {
 			per_cpu_ptr(data->cpu_data, iter->cpu)->ignore = 1;
diff --git a/kernel/trace/trace_remote.c b/kernel/trace/trace_remote.c
index 75fa1ffc4c96..2d5bc423efca 100644
--- a/kernel/trace/trace_remote.c
+++ b/kernel/trace/trace_remote.c
@@ -980,9 +980,12 @@ int trace_remote_alloc_buffer(struct trace_buffer_desc *desc, size_t desc_size,
 			      const struct cpumask *cpumask)
 {
 	size_t min_desc_size = trace_buffer_desc_size(buffer_size, cpumask_weight(cpumask));
-	unsigned int nr_pages = max(DIV_ROUND_UP(buffer_size, PAGE_SIZE), 2UL) + 1;
 	struct ring_buffer_desc *rb_desc;
 	int cpu, ret = -ENOMEM;
+	unsigned int nr_pages;
+
+	if (min_desc_size == SIZE_MAX)
+		return -E2BIG;
 
 	if (desc_size < min_desc_size)
 		return -EINVAL;
@@ -991,6 +994,7 @@ int trace_remote_alloc_buffer(struct trace_buffer_desc *desc, size_t desc_size,
 	desc->struct_len = min_desc_size;
 
 	rb_desc = __first_ring_buffer_desc(desc);
+	nr_pages = __calc_nr_pages_ring_buffer_desc(buffer_size);
 
 	for_each_cpu(cpu, cpumask) {
 		unsigned int id;