Merging upstream version 6.1.85.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

21 files changed, 413 insertions, 215 deletions

diff --git a/kernel/bounds.c b/kernel/bounds.c
index b529182e8..c5a9fcd2d 100644
--- a/kernel/bounds.c
+++ b/kernel/bounds.c
@@ -19,7 +19,7 @@ int main(void)
 	DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS);
 	DEFINE(MAX_NR_ZONES, __MAX_NR_ZONES);
 #ifdef CONFIG_SMP
-	DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS));
+	DEFINE(NR_CPUS_BITS, bits_per(CONFIG_NR_CPUS));
 #endif
 	DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t));
 #ifdef CONFIG_LRU_GEN
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 76bf1de26..44abf88e1 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -857,7 +857,12 @@ static LIST_HEAD(pack_list);
  * CONFIG_MMU=n. Use PAGE_SIZE in these cases.
  */
 #ifdef PMD_SIZE
-#define BPF_PROG_PACK_SIZE (PMD_SIZE * num_possible_nodes())
+/* PMD_SIZE is really big for some archs. It doesn't make sense to
+ * reserve too much memory in one allocation. Hardcode BPF_PROG_PACK_SIZE to
+ * 2MiB * num_possible_nodes(). On most architectures PMD_SIZE will be
+ * greater than or equal to 2MB.
+ */
+#define BPF_PROG_PACK_SIZE (SZ_2M * num_possible_nodes())
 #else
 #define BPF_PROG_PACK_SIZE PAGE_SIZE
 #endif
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 050893704..806a7c1b3 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -306,6 +306,7 @@ static int cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames,
 static int cpu_map_kthread_run(void *data)
 {
 	struct bpf_cpu_map_entry *rcpu = data;
+	unsigned long last_qs = jiffies;
 
 	complete(&rcpu->kthread_running);
 	set_current_state(TASK_INTERRUPTIBLE);
@@ -331,10 +332,12 @@ static int cpu_map_kthread_run(void *data)
 			if (__ptr_ring_empty(rcpu->queue)) {
 				schedule();
 				sched = 1;
+				last_qs = jiffies;
 			} else {
 				__set_current_state(TASK_RUNNING);
 			}
 		} else {
+			rcu_softirq_qs_periodic(last_qs);
 			sched = cond_resched();
 		}
 
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index f9a87dcc5..e051cbb07 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -131,13 +131,14 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
 	bpf_map_init_from_attr(&dtab->map, attr);
 
 	if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
-		dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries);
-
-		if (!dtab->n_buckets) /* Overflow check */
+		/* hash table size must be power of 2; roundup_pow_of_two() can
+		 * overflow into UB on 32-bit arches, so check that first
+		 */
+		if (dtab->map.max_entries > 1UL << 31)
 			return -EINVAL;
-	}
 
-	if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
+		dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries);
+
 		dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets,
 							   dtab->map.numa_node);
 		if (!dtab->dev_index_head)
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 88c71de0a..0c74cc901 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -495,7 +495,13 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 							  num_possible_cpus());
 	}
 
-	/* hash table size must be power of 2 */
+	/* hash table size must be power of 2; roundup_pow_of_two() can overflow
+	 * into UB on 32-bit arches, so check that first
+	 */
+	err = -E2BIG;
+	if (htab->map.max_entries > 1UL << 31)
+		goto free_htab;
+
 	htab->n_buckets = roundup_pow_of_two(htab->map.max_entries);
 
 	htab->elem_size = sizeof(struct htab_elem) +
@@ -505,10 +511,8 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 	else
 		htab->elem_size += round_up(htab->map.value_size, 8);
 
-	err = -E2BIG;
-	/* prevent zero size kmalloc and check for u32 overflow */
-	if (htab->n_buckets == 0 ||
-	    htab->n_buckets > U32_MAX / sizeof(struct bucket))
+	/* check for u32 overflow */
+	if (htab->n_buckets > U32_MAX / sizeof(struct bucket))
 		goto free_htab;
 
 	err = -ENOMEM;
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 83f8f67e9..758510b46 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -328,7 +328,7 @@ static inline void __bpf_spin_lock_irqsave(struct bpf_spin_lock *lock)
 	__this_cpu_write(irqsave_flags, flags);
 }
 
-notrace BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock)
+NOTRACE_BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock)
 {
 	__bpf_spin_lock_irqsave(lock);
 	return 0;
@@ -350,7 +350,7 @@ static inline void __bpf_spin_unlock_irqrestore(struct bpf_spin_lock *lock)
 	local_irq_restore(flags);
 }
 
-notrace BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock)
+NOTRACE_BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock)
 {
 	__bpf_spin_unlock_irqrestore(lock);
 	return 0;
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index f86db3cf7..f0fd936ce 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -94,11 +94,14 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
 	} else if (value_size / 8 > sysctl_perf_event_max_stack)
 		return ERR_PTR(-EINVAL);
 
-	/* hash table size must be power of 2 */
-	n_buckets = roundup_pow_of_two(attr->max_entries);
-	if (!n_buckets)
+	/* hash table size must be power of 2; roundup_pow_of_two() can overflow
+	 * into UB on 32-bit arches, so check that first
+	 */
+	if (attr->max_entries > 1UL << 31)
 		return ERR_PTR(-E2BIG);
 
+	n_buckets = roundup_pow_of_two(attr->max_entries);
+
 	cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap);
 	smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr));
 	if (!smap)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1a29ac4db..27cc6e3db 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -4965,6 +4965,11 @@ static int check_stack_access_within_bounds(
 	err = check_stack_slot_within_bounds(min_off, state, type);
 	if (!err && max_off > 0)
 		err = -EINVAL; /* out of stack access into non-negative offsets */
+	if (!err && access_size < 0)
+		/* access_size should not be negative (or overflow an int); others checks
+		 * along the way should have prevented such an access.
+		 */
+		err = -EFAULT; /* invalid negative access size; integer overflow? */
 
 	if (err) {
 		if (tnum_is_const(reg->var_off)) {
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index ad6333c3f..db89ac94e 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -654,8 +654,7 @@ static int swiotlb_do_find_slots(struct device *dev, int area_index,
 	dma_addr_t tbl_dma_addr =
 		phys_to_dma_unencrypted(dev, mem->start) & boundary_mask;
 	unsigned long max_slots = get_max_slots(boundary_mask);
-	unsigned int iotlb_align_mask =
-		dma_get_min_align_mask(dev) & ~(IO_TLB_SIZE - 1);
+	unsigned int iotlb_align_mask = dma_get_min_align_mask(dev);
 	unsigned int nslots = nr_slots(alloc_size), stride;
 	unsigned int index, wrap, count = 0, i;
 	unsigned int offset = swiotlb_align_offset(dev, orig_addr);
@@ -667,6 +666,14 @@ static int swiotlb_do_find_slots(struct device *dev, int area_index,
 	BUG_ON(area_index >= mem->nareas);
 
 	/*
+	 * Ensure that the allocation is at least slot-aligned and update
+	 * 'iotlb_align_mask' to ignore bits that will be preserved when
+	 * offsetting into the allocation.
+	 */
+	alloc_align_mask |= (IO_TLB_SIZE - 1);
+	iotlb_align_mask &= ~alloc_align_mask;
+
+	/*
 	 * For mappings with an alignment requirement don't bother looping to
 	 * unaligned slots once we found an aligned one.  For allocations of
 	 * PAGE_SIZE or larger only look for page aligned allocations.
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index be61332c6..ccf2b1e1b 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -77,8 +77,14 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall,
 	/* Either of the above might have changed the syscall number */
 	syscall = syscall_get_nr(current, regs);
 
-	if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT))
+	if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT)) {
 		trace_sys_enter(regs, syscall);
+		/*
+		 * Probes or BPF hooks in the tracepoint may have changed the
+		 * system call number as well.
+		 */
+		syscall = syscall_get_nr(current, regs);
+	}
 
 	syscall_enter_audit(regs, syscall);
 
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 7a376e26d..554aba47a 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -2434,6 +2434,11 @@ static void do_free_init(struct work_struct *w)
 	}
 }
 
+void flush_module_init_free_work(void)
+{
+	flush_work(&init_free_wq);
+}
+
 #undef MODULE_PARAM_PREFIX
 #define MODULE_PARAM_PREFIX "module."
 /* Default value for module->async_probe_requested */
@@ -2524,8 +2529,8 @@ static noinline int do_init_module(struct module *mod)
 	 * Note that module_alloc() on most architectures creates W+X page
 	 * mappings which won't be cleaned up until do_free_init() runs.  Any
 	 * code such as mark_rodata_ro() which depends on those mappings to
-	 * be cleaned up needs to sync with the queued work - ie
-	 * rcu_barrier()
+	 * be cleaned up needs to sync with the queued work by invoking
+	 * flush_module_init_free_work().
 	 */
 	if (llist_add(&freeinit->node, &init_free_list))
 		schedule_work(&init_free_wq);
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index fa3bf161d..a718067de 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -192,6 +192,7 @@ static int __init mem_sleep_default_setup(char *str)
 		if (mem_sleep_labels[state] &&
 		    !strcmp(str, mem_sleep_labels[state])) {
 			mem_sleep_default = state;
+			mem_sleep_current = state;
 			break;
 		}
 
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index cc53fb77f..0ae06d504 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1797,10 +1797,23 @@ static bool console_waiter;
  */
 static void console_lock_spinning_enable(void)
 {
+	/*
+	 * Do not use spinning in panic(). The panic CPU wants to keep the lock.
+	 * Non-panic CPUs abandon the flush anyway.
+	 *
+	 * Just keep the lockdep annotation. The panic-CPU should avoid
+	 * taking console_owner_lock because it might cause a deadlock.
+	 * This looks like the easiest way how to prevent false lockdep
+	 * reports without handling races a lockless way.
+	 */
+	if (panic_in_progress())
+		goto lockdep;
+
 	raw_spin_lock(&console_owner_lock);
 	console_owner = current;
 	raw_spin_unlock(&console_owner_lock);
 
+lockdep:
 	/* The waiter may spin on us after setting console_owner */
 	spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_);
 }
@@ -1824,6 +1837,22 @@ static int console_lock_spinning_disable_and_check(void)
 {
 	int waiter;
 
+	/*
+	 * Ignore spinning waiters during panic() because they might get stopped
+	 * or blocked at any time,
+	 *
+	 * It is safe because nobody is allowed to start spinning during panic
+	 * in the first place. If there has been a waiter then non panic CPUs
+	 * might stay spinning. They would get stopped anyway. The panic context
+	 * will never start spinning and an interrupted spin on panic CPU will
+	 * never continue.
+	 */
+	if (panic_in_progress()) {
+		/* Keep lockdep happy. */
+		spin_release(&console_owner_dep_map, _THIS_IP_);
+		return 0;
+	}
+
 	raw_spin_lock(&console_owner_lock);
 	waiter = READ_ONCE(console_waiter);
 	console_owner = NULL;
@@ -1918,6 +1947,12 @@ static int console_trylock_spinning(void)
 	 */
 	mutex_acquire(&console_lock_dep_map, 0, 1, _THIS_IP_);
 
+	/*
+	 * Update @console_may_schedule for trylock because the previous
+	 * owner may have been schedulable.
+	 */
+	console_may_schedule = 0;
+
 	return 1;
 }
 
@@ -3016,6 +3051,21 @@ static int __init keep_bootcon_setup(char *str)
 
 early_param("keep_bootcon", keep_bootcon_setup);
 
+static int console_call_setup(struct console *newcon, char *options)
+{
+	int err;
+
+	if (!newcon->setup)
+		return 0;
+
+	/* Synchronize with possible boot console. */
+	console_lock();
+	err = newcon->setup(newcon, options);
+	console_unlock();
+
+	return err;
+}
+
 /*
  * This is called by register_console() to try to match
  * the newly registered console with any of the ones selected
@@ -3051,8 +3101,8 @@ static int try_enable_preferred_console(struct console *newcon,
 			if (_braille_register_console(newcon, c))
 				return 0;
 
-			if (newcon->setup &&
-			    (err = newcon->setup(newcon, c->options)) != 0)
+			err = console_call_setup(newcon, c->options);
+			if (err)
 				return err;
 		}
 		newcon->flags |= CON_ENABLED;
@@ -3078,7 +3128,7 @@ static void try_enable_default_console(struct console *newcon)
 	if (newcon->index < 0)
 		newcon->index = 0;
 
-	if (newcon->setup && newcon->setup(newcon, NULL) != 0)
+	if (console_call_setup(newcon, NULL) != 0)
 		return;
 
 	newcon->flags |= CON_ENABLED;
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 9d7464a90..61f9503a5 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -4465,13 +4465,16 @@ static void __init rcu_start_exp_gp_kworkers(void)
 	rcu_exp_gp_kworker = kthread_create_worker(0, gp_kworker_name);
 	if (IS_ERR_OR_NULL(rcu_exp_gp_kworker)) {
 		pr_err("Failed to create %s!\n", gp_kworker_name);
+		rcu_exp_gp_kworker = NULL;
 		return;
 	}
 
 	rcu_exp_par_gp_kworker = kthread_create_worker(0, par_gp_kworker_name);
 	if (IS_ERR_OR_NULL(rcu_exp_par_gp_kworker)) {
 		pr_err("Failed to create %s!\n", par_gp_kworker_name);
+		rcu_exp_par_gp_kworker = NULL;
 		kthread_destroy_worker(rcu_exp_gp_kworker);
+		rcu_exp_gp_kworker = NULL;
 		return;
 	}
 
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 6d2cbed96..75e8d9652 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -427,7 +427,12 @@ static void sync_rcu_exp_select_node_cpus(struct kthread_work *wp)
 	__sync_rcu_exp_select_node_cpus(rewp);
 }
 
-static inline bool rcu_gp_par_worker_started(void)
+static inline bool rcu_exp_worker_started(void)
+{
+	return !!READ_ONCE(rcu_exp_gp_kworker);
+}
+
+static inline bool rcu_exp_par_worker_started(void)
 {
 	return !!READ_ONCE(rcu_exp_par_gp_kworker);
 }
@@ -477,7 +482,12 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
 	__sync_rcu_exp_select_node_cpus(rewp);
 }
 
-static inline bool rcu_gp_par_worker_started(void)
+static inline bool rcu_exp_worker_started(void)
+{
+	return !!READ_ONCE(rcu_gp_wq);
+}
+
+static inline bool rcu_exp_par_worker_started(void)
 {
 	return !!READ_ONCE(rcu_par_gp_wq);
 }
@@ -540,7 +550,7 @@ static void sync_rcu_exp_select_cpus(void)
 		rnp->exp_need_flush = false;
 		if (!READ_ONCE(rnp->expmask))
 			continue; /* Avoid early boot non-existent wq. */
-		if (!rcu_gp_par_worker_started() ||
+		if (!rcu_exp_par_worker_started() ||
 		    rcu_scheduler_active != RCU_SCHEDULER_RUNNING ||
 		    rcu_is_last_leaf_node(rnp)) {
 			/* No worker started yet or last leaf, do direct call. */
@@ -910,7 +920,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp)
  */
 void synchronize_rcu_expedited(void)
 {
-	bool boottime = (rcu_scheduler_active == RCU_SCHEDULER_INIT);
+	bool use_worker;
 	unsigned long flags;
 	struct rcu_exp_work rew;
 	struct rcu_node *rnp;
@@ -921,6 +931,9 @@ void synchronize_rcu_expedited(void)
 			 lock_is_held(&rcu_sched_lock_map),
 			 "Illegal synchronize_rcu_expedited() in RCU read-side critical section");
 
+	use_worker = (rcu_scheduler_active != RCU_SCHEDULER_INIT) &&
+		      rcu_exp_worker_started();
+
 	/* Is the state is such that the call is a grace period? */
 	if (rcu_blocking_is_gp()) {
 		// Note well that this code runs with !PREEMPT && !SMP.
@@ -950,7 +963,7 @@ void synchronize_rcu_expedited(void)
 		return;  /* Someone else did our work for us. */
 
 	/* Ensure that load happens before action based on it. */
-	if (unlikely(boottime)) {
+	if (unlikely(!use_worker)) {
 		/* Direct call during scheduler init and early_initcalls(). */
 		rcu_exp_sel_wait_wake(s);
 	} else {
@@ -968,7 +981,7 @@ void synchronize_rcu_expedited(void)
 	/* Let the next expedited grace period start. */
 	mutex_unlock(&rcu_state.exp_mutex);
 
-	if (likely(!boottime))
+	if (likely(use_worker))
 		synchronize_rcu_expedited_destroy_work(&rew);
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 2558ab903..91c101ecf 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6656,7 +6656,7 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu
 		if (!available_idle_cpu(cpu)) {
 			idle = false;
 			if (*idle_cpu == -1) {
-				if (sched_idle_cpu(cpu) && cpumask_test_cpu(cpu, p->cpus_ptr)) {
+				if (sched_idle_cpu(cpu) && cpumask_test_cpu(cpu, cpus)) {
 					*idle_cpu = cpu;
 					break;
 				}
@@ -6664,7 +6664,7 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu
 			}
 			break;
 		}
-		if (*idle_cpu == -1 && cpumask_test_cpu(cpu, p->cpus_ptr))
+		if (*idle_cpu == -1 && cpumask_test_cpu(cpu, cpus))
 			*idle_cpu = cpu;
 	}
 
@@ -6678,13 +6678,19 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu
 /*
  * Scan the local SMT mask for idle CPUs.
  */
-static int select_idle_smt(struct task_struct *p, int target)
+static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	int cpu;
 
 	for_each_cpu_and(cpu, cpu_smt_mask(target), p->cpus_ptr) {
 		if (cpu == target)
 			continue;
+		/*
+		 * Check if the CPU is in the LLC scheduling domain of @target.
+		 * Due to isolcpus, there is no guarantee that all the siblings are in the domain.
+		 */
+		if (!cpumask_test_cpu(cpu, sched_domain_span(sd)))
+			continue;
 		if (available_idle_cpu(cpu) || sched_idle_cpu(cpu))
 			return cpu;
 	}
@@ -6708,7 +6714,7 @@ static inline int select_idle_core(struct task_struct *p, int core, struct cpuma
 	return __select_idle_cpu(core, p);
 }
 
-static inline int select_idle_smt(struct task_struct *p, int target)
+static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	return -1;
 }
@@ -6970,7 +6976,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 		has_idle_core = test_idle_cores(target);
 
 		if (!has_idle_core && cpus_share_cache(prev, target)) {
-			i = select_idle_smt(p, prev);
+			i = select_idle_smt(p, sd, prev);
 			if ((unsigned int)i < nr_cpumask_bits)
 				return i;
 		}
diff --git a/kernel/time/time_test.c b/kernel/time/time_test.c
index 831e8e779..f7c3de011 100644
--- a/kernel/time/time_test.c
+++ b/kernel/time/time_test.c
@@ -73,7 +73,7 @@ static void time64_to_tm_test_date_range(struct kunit *test)
 
 		days = div_s64(secs, 86400);
 
-		#define FAIL_MSG "%05ld/%02d/%02d (%2d) : %ld", \
+		#define FAIL_MSG "%05ld/%02d/%02d (%2d) : %lld", \
 			year, month, mdday, yday, days
 
 		KUNIT_ASSERT_EQ_MSG(test, year - 1900, result.tm_year, FAIL_MSG);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 221c8c404..b158cbef4 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1180,13 +1180,15 @@ static int adjust_historical_crosststamp(struct system_time_snapshot *history,
 }
 
 /*
- * cycle_between - true if test occurs chronologically between before and after
+ * timestamp_in_interval - true if ts is chronologically in [start, end]
+ *
+ * True if ts occurs chronologically at or after start, and before or at end.
  */
-static bool cycle_between(u64 before, u64 test, u64 after)
+static bool timestamp_in_interval(u64 start, u64 end, u64 ts)
 {
-	if (test > before && test < after)
+	if (ts >= start && ts <= end)
 		return true;
-	if (test < before && before > after)
+	if (start > end && (ts >= start || ts <= end))
 		return true;
 	return false;
 }
@@ -1246,7 +1248,7 @@ int get_device_system_crosststamp(int (*get_time_fn)
 		 */
 		now = tk_clock_read(&tk->tkr_mono);
 		interval_start = tk->tkr_mono.cycle_last;
-		if (!cycle_between(interval_start, cycles, now)) {
+		if (!timestamp_in_interval(interval_start, now, cycles)) {
 			clock_was_set_seq = tk->clock_was_set_seq;
 			cs_was_changed_seq = tk->cs_was_changed_seq;
 			cycles = interval_start;
@@ -1259,10 +1261,8 @@ int get_device_system_crosststamp(int (*get_time_fn)
 				      tk_core.timekeeper.offs_real);
 		base_raw = tk->tkr_raw.base;
 
-		nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono,
-						     system_counterval.cycles);
-		nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw,
-						    system_counterval.cycles);
+		nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, cycles);
+		nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, cycles);
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
 	xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real);
@@ -1277,13 +1277,13 @@ int get_device_system_crosststamp(int (*get_time_fn)
 		bool discontinuity;
 
 		/*
-		 * Check that the counter value occurs after the provided
+		 * Check that the counter value is not before the provided
 		 * history reference and that the history doesn't cross a
 		 * clocksource change
 		 */
 		if (!history_begin ||
-		    !cycle_between(history_begin->cycles,
-				   system_counterval.cycles, cycles) ||
+		    !timestamp_in_interval(history_begin->cycles,
+					   cycles, system_counterval.cycles) ||
 		    history_begin->cs_was_changed_seq != cs_was_changed_seq)
 			return -EINVAL;
 		partial_history_cycles = cycles - system_counterval.cycles;
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 717fcb9fb..594698974 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1083,7 +1083,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option
 		/*
 		 * We are trying to schedule the timer on the new base.
 		 * However we can't change timer's base while it is running,
-		 * otherwise del_timer_sync() can't detect that the timer's
+		 * otherwise timer_delete_sync() can't detect that the timer's
 		 * handler yet has not finished. This also guarantees that the
 		 * timer is serialized wrt itself.
 		 */
@@ -1121,14 +1121,16 @@ out_unlock:
 }
 
 /**
- * mod_timer_pending - modify a pending timer's timeout
- * @timer: the pending timer to be modified
- * @expires: new timeout in jiffies
+ * mod_timer_pending - Modify a pending timer's timeout
+ * @timer:	The pending timer to be modified
+ * @expires:	New absolute timeout in jiffies
  *
- * mod_timer_pending() is the same for pending timers as mod_timer(),
- * but will not re-activate and modify already deleted timers.
+ * mod_timer_pending() is the same for pending timers as mod_timer(), but
+ * will not activate inactive timers.
  *
- * It is useful for unserialized use of timers.
+ * Return:
+ * * %0 - The timer was inactive and not modified
+ * * %1 - The timer was active and requeued to expire at @expires
  */
 int mod_timer_pending(struct timer_list *timer, unsigned long expires)
 {
@@ -1137,24 +1139,27 @@ int mod_timer_pending(struct timer_list *timer, unsigned long expires)
 EXPORT_SYMBOL(mod_timer_pending);
 
 /**
- * mod_timer - modify a timer's timeout
- * @timer: the timer to be modified
- * @expires: new timeout in jiffies
- *
- * mod_timer() is a more efficient way to update the expire field of an
- * active timer (if the timer is inactive it will be activated)
+ * mod_timer - Modify a timer's timeout
+ * @timer:	The timer to be modified
+ * @expires:	New absolute timeout in jiffies
  *
  * mod_timer(timer, expires) is equivalent to:
  *
  *     del_timer(timer); timer->expires = expires; add_timer(timer);
  *
+ * mod_timer() is more efficient than the above open coded sequence. In
+ * case that the timer is inactive, the del_timer() part is a NOP. The
+ * timer is in any case activated with the new expiry time @expires.
+ *
  * Note that if there are multiple unserialized concurrent users of the
  * same timer, then mod_timer() is the only safe way to modify the timeout,
  * since add_timer() cannot modify an already running timer.
  *
- * The function returns whether it has modified a pending timer or not.
- * (ie. mod_timer() of an inactive timer returns 0, mod_timer() of an
- * active timer returns 1.)
+ * Return:
+ * * %0 - The timer was inactive and started
+ * * %1 - The timer was active and requeued to expire at @expires or
+ *	  the timer was active and not modified because @expires did
+ *	  not change the effective expiry time
  */
 int mod_timer(struct timer_list *timer, unsigned long expires)
 {
@@ -1165,11 +1170,18 @@ EXPORT_SYMBOL(mod_timer);
 /**
  * timer_reduce - Modify a timer's timeout if it would reduce the timeout
  * @timer:	The timer to be modified
- * @expires:	New timeout in jiffies
+ * @expires:	New absolute timeout in jiffies
  *
  * timer_reduce() is very similar to mod_timer(), except that it will only
- * modify a running timer if that would reduce the expiration time (it will
- * start a timer that isn't running).
+ * modify an enqueued timer if that would reduce the expiration time. If
+ * @timer is not enqueued it starts the timer.
+ *
+ * Return:
+ * * %0 - The timer was inactive and started
+ * * %1 - The timer was active and requeued to expire at @expires or
+ *	  the timer was active and not modified because @expires
+ *	  did not change the effective expiry time such that the
+ *	  timer would expire earlier than already scheduled
  */
 int timer_reduce(struct timer_list *timer, unsigned long expires)
 {
@@ -1178,18 +1190,21 @@ int timer_reduce(struct timer_list *timer, unsigned long expires)
 EXPORT_SYMBOL(timer_reduce);
 
 /**
- * add_timer - start a timer
- * @timer: the timer to be added
+ * add_timer - Start a timer
+ * @timer:	The timer to be started
  *
- * The kernel will do a ->function(@timer) callback from the
- * timer interrupt at the ->expires point in the future. The
- * current time is 'jiffies'.
+ * Start @timer to expire at @timer->expires in the future. @timer->expires
+ * is the absolute expiry time measured in 'jiffies'. When the timer expires
+ * timer->function(timer) will be invoked from soft interrupt context.
  *
- * The timer's ->expires, ->function fields must be set prior calling this
- * function.
+ * The @timer->expires and @timer->function fields must be set prior
+ * to calling this function.
  *
- * Timers with an ->expires field in the past will be executed in the next
- * timer tick.
+ * If @timer->expires is already in the past @timer will be queued to
+ * expire at the next timer tick.
+ *
+ * This can only operate on an inactive timer. Attempts to invoke this on
+ * an active timer are rejected with a warning.
  */
 void add_timer(struct timer_list *timer)
 {
@@ -1199,11 +1214,13 @@ void add_timer(struct timer_list *timer)
 EXPORT_SYMBOL(add_timer);
 
 /**
- * add_timer_on - start a timer on a particular CPU
- * @timer: the timer to be added
- * @cpu: the CPU to start it on
+ * add_timer_on - Start a timer on a particular CPU
+ * @timer:	The timer to be started
+ * @cpu:	The CPU to start it on
+ *
+ * Same as add_timer() except that it starts the timer on the given CPU.
  *
- * This is not very scalable on SMP. Double adds are not possible.
+ * See add_timer() for further details.
  */
 void add_timer_on(struct timer_list *timer, int cpu)
 {
@@ -1238,15 +1255,18 @@ void add_timer_on(struct timer_list *timer, int cpu)
 EXPORT_SYMBOL_GPL(add_timer_on);
 
 /**
- * del_timer - deactivate a timer.
- * @timer: the timer to be deactivated
- *
- * del_timer() deactivates a timer - this works on both active and inactive
- * timers.
- *
- * The function returns whether it has deactivated a pending timer or not.
- * (ie. del_timer() of an inactive timer returns 0, del_timer() of an
- * active timer returns 1.)
+ * del_timer - Deactivate a timer.
+ * @timer:	The timer to be deactivated
+ *
+ * The function only deactivates a pending timer, but contrary to
+ * timer_delete_sync() it does not take into account whether the timer's
+ * callback function is concurrently executed on a different CPU or not.
+ * It neither prevents rearming of the timer. If @timer can be rearmed
+ * concurrently then the return value of this function is meaningless.
+ *
+ * Return:
+ * * %0 - The timer was not pending
+ * * %1 - The timer was pending and deactivated
  */
 int del_timer(struct timer_list *timer)
 {
@@ -1268,10 +1288,19 @@ EXPORT_SYMBOL(del_timer);
 
 /**
  * try_to_del_timer_sync - Try to deactivate a timer
- * @timer: timer to delete
+ * @timer:	Timer to deactivate
+ *
+ * This function tries to deactivate a timer. On success the timer is not
+ * queued and the timer callback function is not running on any CPU.
+ *
+ * This function does not guarantee that the timer cannot be rearmed right
+ * after dropping the base lock. That needs to be prevented by the calling
+ * code if necessary.
  *
- * This function tries to deactivate a timer. Upon successful (ret >= 0)
- * exit the timer is not queued and the handler is not running on any CPU.
+ * Return:
+ * * %0  - The timer was not pending
+ * * %1  - The timer was pending and deactivated
+ * * %-1 - The timer callback function is running on a different CPU
  */
 int try_to_del_timer_sync(struct timer_list *timer)
 {
@@ -1365,25 +1394,20 @@ static inline void timer_sync_wait_running(struct timer_base *base) { }
 static inline void del_timer_wait_running(struct timer_list *timer) { }
 #endif
 
-#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
 /**
- * del_timer_sync - deactivate a timer and wait for the handler to finish.
- * @timer: the timer to be deactivated
- *
- * This function only differs from del_timer() on SMP: besides deactivating
- * the timer it also makes sure the handler has finished executing on other
- * CPUs.
+ * timer_delete_sync - Deactivate a timer and wait for the handler to finish.
+ * @timer:	The timer to be deactivated
  *
  * Synchronization rules: Callers must prevent restarting of the timer,
  * otherwise this function is meaningless. It must not be called from
  * interrupt contexts unless the timer is an irqsafe one. The caller must
- * not hold locks which would prevent completion of the timer's
- * handler. The timer's handler must not call add_timer_on(). Upon exit the
- * timer is not queued and the handler is not running on any CPU.
+ * not hold locks which would prevent completion of the timer's callback
+ * function. The timer's handler must not call add_timer_on(). Upon exit
+ * the timer is not queued and the handler is not running on any CPU.
  *
- * Note: For !irqsafe timers, you must not hold locks that are held in
- *   interrupt context while calling this function. Even if the lock has
- *   nothing to do with the timer in question.  Here's why::
+ * For !irqsafe timers, the caller must not hold locks that are held in
+ * interrupt context. Even if the lock has nothing to do with the timer in
+ * question.  Here's why::
  *
  *    CPU0                             CPU1
  *    ----                             ----
@@ -1393,16 +1417,23 @@ static inline void del_timer_wait_running(struct timer_list *timer) { }
  *    spin_lock_irq(somelock);
  *                                     <IRQ>
  *                                        spin_lock(somelock);
- *    del_timer_sync(mytimer);
+ *    timer_delete_sync(mytimer);
  *    while (base->running_timer == mytimer);
  *
- * Now del_timer_sync() will never return and never release somelock.
- * The interrupt on the other CPU is waiting to grab somelock but
- * it has interrupted the softirq that CPU0 is waiting to finish.
+ * Now timer_delete_sync() will never return and never release somelock.
+ * The interrupt on the other CPU is waiting to grab somelock but it has
+ * interrupted the softirq that CPU0 is waiting to finish.
+ *
+ * This function cannot guarantee that the timer is not rearmed again by
+ * some concurrent or preempting code, right after it dropped the base
+ * lock. If there is the possibility of a concurrent rearm then the return
+ * value of the function is meaningless.
  *
- * The function returns whether it has deactivated a pending timer or not.
+ * Return:
+ * * %0	- The timer was not pending
+ * * %1	- The timer was pending and deactivated
  */
-int del_timer_sync(struct timer_list *timer)
+int timer_delete_sync(struct timer_list *timer)
 {
 	int ret;
 
@@ -1442,8 +1473,7 @@ int del_timer_sync(struct timer_list *timer)
 
 	return ret;
 }
-EXPORT_SYMBOL(del_timer_sync);
-#endif
+EXPORT_SYMBOL(timer_delete_sync);
 
 static void call_timer_fn(struct timer_list *timer,
 			  void (*fn)(struct timer_list *),
@@ -1465,8 +1495,8 @@ static void call_timer_fn(struct timer_list *timer,
 #endif
 	/*
 	 * Couple the lock chain with the lock chain at
-	 * del_timer_sync() by acquiring the lock_map around the fn()
-	 * call here and in del_timer_sync().
+	 * timer_delete_sync() by acquiring the lock_map around the fn()
+	 * call here and in timer_delete_sync().
 	 */
 	lock_map_acquire(&lockdep_map);
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index e019a9278..431a922e5 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -414,7 +414,6 @@ struct rb_irq_work {
 	struct irq_work			work;
 	wait_queue_head_t		waiters;
 	wait_queue_head_t		full_waiters;
-	long				wait_index;
 	bool				waiters_pending;
 	bool				full_waiters_pending;
 	bool				wakeup_full;
@@ -908,8 +907,19 @@ static void rb_wake_up_waiters(struct irq_work *work)
 
 	wake_up_all(&rbwork->waiters);
 	if (rbwork->full_waiters_pending || rbwork->wakeup_full) {
+		/* Only cpu_buffer sets the above flags */
+		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;
+
+		/* Waking up all waiters, they will reset the shortest full */
+		cpu_buffer->shortest_full = 0;
+		raw_spin_unlock(&cpu_buffer->reader_lock);
+
 		wake_up_all(&rbwork->full_waiters);
 	}
 }
@@ -949,14 +959,95 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu)
 		rbwork = &cpu_buffer->irq_work;
 	}
 
-	rbwork->wait_index++;
-	/* make sure the waiters see the new index */
-	smp_wmb();
-
 	/* This can be called in any context */
 	irq_work_queue(&rbwork->work);
 }
 
+static bool rb_watermark_hit(struct trace_buffer *buffer, int cpu, int full)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	bool ret = false;
+
+	/* Reads of all CPUs always waits for any data */
+	if (cpu == RING_BUFFER_ALL_CPUS)
+		return !ring_buffer_empty(buffer);
+
+	cpu_buffer = buffer->buffers[cpu];
+
+	if (!ring_buffer_empty_cpu(buffer, cpu)) {
+		unsigned long flags;
+		bool pagebusy;
+
+		if (!full)
+			return true;
+
+		raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+		pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page;
+		ret = !pagebusy && full_hit(buffer, cpu, full);
+
+		if (!ret && (!cpu_buffer->shortest_full ||
+			     cpu_buffer->shortest_full > full)) {
+		    cpu_buffer->shortest_full = full;
+		}
+		raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	}
+	return ret;
+}
+
+static inline bool
+rb_wait_cond(struct rb_irq_work *rbwork, struct trace_buffer *buffer,
+	     int cpu, int full, ring_buffer_cond_fn cond, void *data)
+{
+	if (rb_watermark_hit(buffer, cpu, full))
+		return true;
+
+	if (cond(data))
+		return true;
+
+	/*
+	 * The events can happen in critical sections where
+	 * checking a work queue can cause deadlocks.
+	 * After adding a task to the queue, this flag is set
+	 * only to notify events to try to wake up the queue
+	 * using irq_work.
+	 *
+	 * We don't clear it even if the buffer is no longer
+	 * empty. The flag only causes the next event to run
+	 * irq_work to do the work queue wake up. The worse
+	 * that can happen if we race with !trace_empty() is that
+	 * an event will cause an irq_work to try to wake up
+	 * an empty queue.
+	 *
+	 * There's no reason to protect this flag either, as
+	 * the work queue and irq_work logic will do the necessary
+	 * synchronization for the wake ups. The only thing
+	 * that is necessary is that the wake up happens after
+	 * a task has been queued. It's OK for spurious wake ups.
+	 */
+	if (full)
+		rbwork->full_waiters_pending = true;
+	else
+		rbwork->waiters_pending = true;
+
+	return false;
+}
+
+/*
+ * The default wait condition for ring_buffer_wait() is to just to exit the
+ * wait loop the first time it is woken up.
+ */
+static bool rb_wait_once(void *data)
+{
+	long *once = data;
+
+	/* wait_event() actually calls this twice before scheduling*/
+	if (*once > 1)
+		return true;
+
+	(*once)++;
+	return false;
+}
+
 /**
  * ring_buffer_wait - wait for input to the ring buffer
  * @buffer: buffer to wait on
@@ -970,101 +1061,39 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu)
 int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
-	DEFINE_WAIT(wait);
-	struct rb_irq_work *work;
-	long wait_index;
+	struct wait_queue_head *waitq;
+	ring_buffer_cond_fn cond;
+	struct rb_irq_work *rbwork;
+	void *data;
+	long once = 0;
 	int ret = 0;
 
+	cond = rb_wait_once;
+	data = &once;
+
 	/*
 	 * Depending on what the caller is waiting for, either any
 	 * data in any cpu buffer, or a specific buffer, put the
 	 * caller on the appropriate wait queue.
 	 */
 	if (cpu == RING_BUFFER_ALL_CPUS) {
-		work = &buffer->irq_work;
+		rbwork = &buffer->irq_work;
 		/* Full only makes sense on per cpu reads */
 		full = 0;
 	} else {
 		if (!cpumask_test_cpu(cpu, buffer->cpumask))
 			return -ENODEV;
 		cpu_buffer = buffer->buffers[cpu];
-		work = &cpu_buffer->irq_work;
-	}
-
-	wait_index = READ_ONCE(work->wait_index);
-
-	while (true) {
-		if (full)
-			prepare_to_wait(&work->full_waiters, &wait, TASK_INTERRUPTIBLE);
-		else
-			prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE);
-
-		/*
-		 * The events can happen in critical sections where
-		 * checking a work queue can cause deadlocks.
-		 * After adding a task to the queue, this flag is set
-		 * only to notify events to try to wake up the queue
-		 * using irq_work.
-		 *
-		 * We don't clear it even if the buffer is no longer
-		 * empty. The flag only causes the next event to run
-		 * irq_work to do the work queue wake up. The worse
-		 * that can happen if we race with !trace_empty() is that
-		 * an event will cause an irq_work to try to wake up
-		 * an empty queue.
-		 *
-		 * There's no reason to protect this flag either, as
-		 * the work queue and irq_work logic will do the necessary
-		 * synchronization for the wake ups. The only thing
-		 * that is necessary is that the wake up happens after
-		 * a task has been queued. It's OK for spurious wake ups.
-		 */
-		if (full)
-			work->full_waiters_pending = true;
-		else
-			work->waiters_pending = true;
-
-		if (signal_pending(current)) {
-			ret = -EINTR;
-			break;
-		}
-
-		if (cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer))
-			break;
-
-		if (cpu != RING_BUFFER_ALL_CPUS &&
-		    !ring_buffer_empty_cpu(buffer, cpu)) {
-			unsigned long flags;
-			bool pagebusy;
-			bool done;
-
-			if (!full)
-				break;
-
-			raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
-			pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page;
-			done = !pagebusy && full_hit(buffer, cpu, full);
-
-			if (!cpu_buffer->shortest_full ||
-			    cpu_buffer->shortest_full > full)
-				cpu_buffer->shortest_full = full;
-			raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
-			if (done)
-				break;
-		}
-
-		schedule();
-
-		/* Make sure to see the new wait index */
-		smp_rmb();
-		if (wait_index != work->wait_index)
-			break;
+		rbwork = &cpu_buffer->irq_work;
 	}
 
 	if (full)
-		finish_wait(&work->full_waiters, &wait);
+		waitq = &rbwork->full_waiters;
 	else
-		finish_wait(&work->waiters, &wait);
+		waitq = &rbwork->waiters;
+
+	ret = wait_event_interruptible((*waitq),
+				rb_wait_cond(rbwork, buffer, cpu, full, cond, data));
 
 	return ret;
 }
@@ -1088,30 +1117,51 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
 			  struct file *filp, poll_table *poll_table, int full)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
-	struct rb_irq_work *work;
+	struct rb_irq_work *rbwork;
 
 	if (cpu == RING_BUFFER_ALL_CPUS) {
-		work = &buffer->irq_work;
+		rbwork = &buffer->irq_work;
 		full = 0;
 	} else {
 		if (!cpumask_test_cpu(cpu, buffer->cpumask))
 			return EPOLLERR;
 
 		cpu_buffer = buffer->buffers[cpu];
-		work = &cpu_buffer->irq_work;
+		rbwork = &cpu_buffer->irq_work;
 	}
 
 	if (full) {
-		poll_wait(filp, &work->full_waiters, poll_table);
-		work->full_waiters_pending = true;
+		unsigned long flags;
+
+		poll_wait(filp, &rbwork->full_waiters, poll_table);
+
+		raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 		if (!cpu_buffer->shortest_full ||
 		    cpu_buffer->shortest_full > full)
 			cpu_buffer->shortest_full = full;
-	} else {
-		poll_wait(filp, &work->waiters, poll_table);
-		work->waiters_pending = true;
+		raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+		if (full_hit(buffer, cpu, full))
+			return EPOLLIN | EPOLLRDNORM;
+		/*
+		 * Only allow full_waiters_pending update to be seen after
+		 * the shortest_full is set. If the writer sees the
+		 * full_waiters_pending flag set, it will compare the
+		 * amount in the ring buffer to shortest_full. If the amount
+		 * in the ring buffer is greater than the shortest_full
+		 * percent, it will call the irq_work handler to wake up
+		 * this list. The irq_handler will reset shortest_full
+		 * back to zero. That's done under the reader_lock, but
+		 * the below smp_mb() makes sure that the update to
+		 * full_waiters_pending doesn't leak up into the above.
+		 */
+		smp_mb();
+		rbwork->full_waiters_pending = true;
+		return 0;
 	}
 
+	poll_wait(filp, &rbwork->waiters, poll_table);
+	rbwork->waiters_pending = true;
+
 	/*
 	 * There's a tight race between setting the waiters_pending and
 	 * checking if the ring buffer is empty.  Once the waiters_pending bit
@@ -1127,9 +1177,6 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
 	 */
 	smp_mb();
 
-	if (full)
-		return full_hit(buffer, cpu, full) ? EPOLLIN | EPOLLRDNORM : 0;
-
 	if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
 	    (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))
 		return EPOLLIN | EPOLLRDNORM;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f667d6bdd..f2b00ea38 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -8278,6 +8278,20 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 	return size;
 }
 
+static int tracing_buffers_flush(struct file *file, fl_owner_t id)
+{
+	struct ftrace_buffer_info *info = file->private_data;
+	struct trace_iterator *iter = &info->iter;
+
+	iter->wait_index++;
+	/* Make sure the waiters see the new wait_index */
+	smp_wmb();
+
+	ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file);
+
+	return 0;
+}
+
 static int tracing_buffers_release(struct inode *inode, struct file *file)
 {
 	struct ftrace_buffer_info *info = file->private_data;
@@ -8289,12 +8303,6 @@ static int tracing_buffers_release(struct inode *inode, struct file *file)
 
 	__trace_array_put(iter->tr);
 
-	iter->wait_index++;
-	/* Make sure the waiters see the new wait_index */
-	smp_wmb();
-
-	ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file);
-
 	if (info->spare)
 		ring_buffer_free_read_page(iter->array_buffer->buffer,
 					   info->spare_cpu, info->spare);
@@ -8508,6 +8516,7 @@ static const struct file_operations tracing_buffers_fops = {
 	.read		= tracing_buffers_read,
 	.poll		= tracing_buffers_poll,
 	.release	= tracing_buffers_release,
+	.flush		= tracing_buffers_flush,
 	.splice_read	= tracing_buffers_splice_read,
 	.unlocked_ioctl = tracing_buffers_ioctl,
 	.llseek		= no_llseek,