Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

tools/lib/bpf/ringbuf.c
  927cbb478adf ("libbpf: Handle size overflow for ringbuf mmap")
  b486d19a0ab0 ("libbpf: checkpatch: Fixed code alignments in ringbuf.c")
https://lore.kernel.org/all/20221121122707.44d1446a@canb.auug.org.au/

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

22 files changed, 263 insertions, 115 deletions

diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index 37020078d1c1..b39a46e8fb08 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -74,7 +74,7 @@ bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner,
 				gfp_flags | __GFP_NOWARN);
 	if (selem) {
 		if (value)
-			memcpy(SDATA(selem)->data, value, smap->map.value_size);
+			copy_map_value(&smap->map, SDATA(selem)->data, value);
 		return selem;
 	}
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4ec3717003d5..7091bbf88ee7 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9030,7 +9030,7 @@ static void perf_event_bpf_emit_ksymbols(struct bpf_prog *prog,
 				PERF_RECORD_KSYMBOL_TYPE_BPF,
 				(u64)(unsigned long)subprog->bpf_func,
 				subprog->jited_len, unregister,
-				prog->aux->ksym.name);
+				subprog->aux->ksym.name);
 		}
 	}
 }
@@ -9273,6 +9273,19 @@ int perf_event_account_interrupt(struct perf_event *event)
 	return __perf_event_account_interrupt(event, 1);
 }
 
+static inline bool sample_is_allowed(struct perf_event *event, struct pt_regs *regs)
+{
+	/*
+	 * Due to interrupt latency (AKA "skid"), we may enter the
+	 * kernel before taking an overflow, even if the PMU is only
+	 * counting user events.
+	 */
+	if (event->attr.exclude_kernel && !user_mode(regs))
+		return false;
+
+	return true;
+}
+
 /*
  * Generic event overflow handling, sampling.
  */
@@ -9307,15 +9320,38 @@ static int __perf_event_overflow(struct perf_event *event,
 
 	if (event->attr.sigtrap) {
 		/*
-		 * Should not be able to return to user space without processing
-		 * pending_sigtrap (kernel events can overflow multiple times).
+		 * The desired behaviour of sigtrap vs invalid samples is a bit
+		 * tricky; on the one hand, one should not loose the SIGTRAP if
+		 * it is the first event, on the other hand, we should also not
+		 * trigger the WARN or override the data address.
 		 */
-		WARN_ON_ONCE(event->pending_sigtrap && event->attr.exclude_kernel);
+		bool valid_sample = sample_is_allowed(event, regs);
+		unsigned int pending_id = 1;
+
+		if (regs)
+			pending_id = hash32_ptr((void *)instruction_pointer(regs)) ?: 1;
 		if (!event->pending_sigtrap) {
-			event->pending_sigtrap = 1;
+			event->pending_sigtrap = pending_id;
 			local_inc(&event->ctx->nr_pending);
+		} else if (event->attr.exclude_kernel && valid_sample) {
+			/*
+			 * Should not be able to return to user space without
+			 * consuming pending_sigtrap; with exceptions:
+			 *
+			 *  1. Where !exclude_kernel, events can overflow again
+			 *     in the kernel without returning to user space.
+			 *
+			 *  2. Events that can overflow again before the IRQ-
+			 *     work without user space progress (e.g. hrtimer).
+			 *     To approximate progress (with false negatives),
+			 *     check 32-bit hash of the current IP.
+			 */
+			WARN_ON_ONCE(event->pending_sigtrap != pending_id);
 		}
-		event->pending_addr = data->addr;
+
+		event->pending_addr = 0;
+		if (valid_sample && (data->sample_flags & PERF_SAMPLE_ADDR))
+			event->pending_addr = data->addr;
 		irq_work_queue(&event->pending_irq);
 	}
 
diff --git a/kernel/gcov/clang.c b/kernel/gcov/clang.c
index cbb0bed958ab..7670a811a565 100644
--- a/kernel/gcov/clang.c
+++ b/kernel/gcov/clang.c
@@ -280,6 +280,8 @@ void gcov_info_add(struct gcov_info *dst, struct gcov_info *src)
 
 		for (i = 0; i < sfn_ptr->num_counters; i++)
 			dfn_ptr->counters[i] += sfn_ptr->counters[i];
+
+		sfn_ptr = list_next_entry(sfn_ptr, head);
 	}
 }
 
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index cd9f5a66a690..3050631e528d 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1766,7 +1766,13 @@ static int __unregister_kprobe_top(struct kprobe *p)
 				if ((list_p != p) && (list_p->post_handler))
 					goto noclean;
 			}
-			ap->post_handler = NULL;
+			/*
+			 * For the kprobe-on-ftrace case, we keep the
+			 * post_handler setting to identify this aggrprobe
+			 * armed with kprobe_ipmodify_ops.
+			 */
+			if (!kprobe_ftrace(ap))
+				ap->post_handler = NULL;
 		}
 noclean:
 		/*
diff --git a/kernel/rseq.c b/kernel/rseq.c
index bda8175f8f99..d38ab944105d 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -171,12 +171,27 @@ static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
 	return 0;
 }
 
+static bool rseq_warn_flags(const char *str, u32 flags)
+{
+	u32 test_flags;
+
+	if (!flags)
+		return false;
+	test_flags = flags & RSEQ_CS_NO_RESTART_FLAGS;
+	if (test_flags)
+		pr_warn_once("Deprecated flags (%u) in %s ABI structure", test_flags, str);
+	test_flags = flags & ~RSEQ_CS_NO_RESTART_FLAGS;
+	if (test_flags)
+		pr_warn_once("Unknown flags (%u) in %s ABI structure", test_flags, str);
+	return true;
+}
+
 static int rseq_need_restart(struct task_struct *t, u32 cs_flags)
 {
 	u32 flags, event_mask;
 	int ret;
 
-	if (WARN_ON_ONCE(cs_flags & RSEQ_CS_NO_RESTART_FLAGS) || cs_flags)
+	if (rseq_warn_flags("rseq_cs", cs_flags))
 		return -EINVAL;
 
 	/* Get thread flags. */
@@ -184,7 +199,7 @@ static int rseq_need_restart(struct task_struct *t, u32 cs_flags)
 	if (ret)
 		return ret;
 
-	if (WARN_ON_ONCE(flags & RSEQ_CS_NO_RESTART_FLAGS) || flags)
+	if (rseq_warn_flags("rseq", flags))
 		return -EINVAL;
 
 	/*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index cb2aa2b54c7a..daff72f00385 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4200,6 +4200,40 @@ out:
 	return success;
 }
 
+static bool __task_needs_rq_lock(struct task_struct *p)
+{
+	unsigned int state = READ_ONCE(p->__state);
+
+	/*
+	 * Since pi->lock blocks try_to_wake_up(), we don't need rq->lock when
+	 * the task is blocked. Make sure to check @state since ttwu() can drop
+	 * locks at the end, see ttwu_queue_wakelist().
+	 */
+	if (state == TASK_RUNNING || state == TASK_WAKING)
+		return true;
+
+	/*
+	 * Ensure we load p->on_rq after p->__state, otherwise it would be
+	 * possible to, falsely, observe p->on_rq == 0.
+	 *
+	 * See try_to_wake_up() for a longer comment.
+	 */
+	smp_rmb();
+	if (p->on_rq)
+		return true;
+
+#ifdef CONFIG_SMP
+	/*
+	 * Ensure the task has finished __schedule() and will not be referenced
+	 * anymore. Again, see try_to_wake_up() for a longer comment.
+	 */
+	smp_rmb();
+	smp_cond_load_acquire(&p->on_cpu, !VAL);
+#endif
+
+	return false;
+}
+
 /**
  * task_call_func - Invoke a function on task in fixed state
  * @p: Process for which the function is to be invoked, can be @current.
@@ -4217,28 +4251,12 @@ out:
 int task_call_func(struct task_struct *p, task_call_f func, void *arg)
 {
 	struct rq *rq = NULL;
-	unsigned int state;
 	struct rq_flags rf;
 	int ret;
 
 	raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
 
-	state = READ_ONCE(p->__state);
-
-	/*
-	 * Ensure we load p->on_rq after p->__state, otherwise it would be
-	 * possible to, falsely, observe p->on_rq == 0.
-	 *
-	 * See try_to_wake_up() for a longer comment.
-	 */
-	smp_rmb();
-
-	/*
-	 * Since pi->lock blocks try_to_wake_up(), we don't need rq->lock when
-	 * the task is blocked. Make sure to check @state since ttwu() can drop
-	 * locks at the end, see ttwu_queue_wakelist().
-	 */
-	if (state == TASK_RUNNING || state == TASK_WAKING || p->on_rq)
+	if (__task_needs_rq_lock(p))
 		rq = __task_rq_lock(p, &rf);
 
 	/*
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 9161d1136d01..1207c78f85c1 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -25,9 +25,6 @@ struct sugov_policy {
 	unsigned int		next_freq;
 	unsigned int		cached_raw_freq;
 
-	/* max CPU capacity, which is equal for all CPUs in freq. domain */
-	unsigned long		max;
-
 	/* The next fields are only needed if fast switch cannot be used: */
 	struct			irq_work irq_work;
 	struct			kthread_work work;
@@ -51,6 +48,7 @@ struct sugov_cpu {
 
 	unsigned long		util;
 	unsigned long		bw_dl;
+	unsigned long		max;
 
 	/* The field below is for single-CPU policies only: */
 #ifdef CONFIG_NO_HZ_COMMON
@@ -160,6 +158,7 @@ static void sugov_get_util(struct sugov_cpu *sg_cpu)
 {
 	struct rq *rq = cpu_rq(sg_cpu->cpu);
 
+	sg_cpu->max = arch_scale_cpu_capacity(sg_cpu->cpu);
 	sg_cpu->bw_dl = cpu_bw_dl(rq);
 	sg_cpu->util = effective_cpu_util(sg_cpu->cpu, cpu_util_cfs(sg_cpu->cpu),
 					  FREQUENCY_UTIL, NULL);
@@ -254,7 +253,6 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
  */
 static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time)
 {
-	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	unsigned long boost;
 
 	/* No boost currently required */
@@ -282,8 +280,7 @@ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time)
 	 * sg_cpu->util is already in capacity scale; convert iowait_boost
 	 * into the same scale so we can compare.
 	 */
-	boost = sg_cpu->iowait_boost * sg_policy->max;
-	boost >>= SCHED_CAPACITY_SHIFT;
+	boost = (sg_cpu->iowait_boost * sg_cpu->max) >> SCHED_CAPACITY_SHIFT;
 	boost = uclamp_rq_util_with(cpu_rq(sg_cpu->cpu), boost, NULL);
 	if (sg_cpu->util < boost)
 		sg_cpu->util = boost;
@@ -340,7 +337,7 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
 	if (!sugov_update_single_common(sg_cpu, time, flags))
 		return;
 
-	next_f = get_next_freq(sg_policy, sg_cpu->util, sg_policy->max);
+	next_f = get_next_freq(sg_policy, sg_cpu->util, sg_cpu->max);
 	/*
 	 * Do not reduce the frequency if the CPU has not been idle
 	 * recently, as the reduction is likely to be premature then.
@@ -376,7 +373,6 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
 				     unsigned int flags)
 {
 	struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
-	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	unsigned long prev_util = sg_cpu->util;
 
 	/*
@@ -403,8 +399,7 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
 		sg_cpu->util = prev_util;
 
 	cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
-				   map_util_perf(sg_cpu->util),
-				   sg_policy->max);
+				   map_util_perf(sg_cpu->util), sg_cpu->max);
 
 	sg_cpu->sg_policy->last_freq_update_time = time;
 }
@@ -413,19 +408,25 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
 {
 	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	struct cpufreq_policy *policy = sg_policy->policy;
-	unsigned long util = 0;
+	unsigned long util = 0, max = 1;
 	unsigned int j;
 
 	for_each_cpu(j, policy->cpus) {
 		struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
+		unsigned long j_util, j_max;
 
 		sugov_get_util(j_sg_cpu);
 		sugov_iowait_apply(j_sg_cpu, time);
+		j_util = j_sg_cpu->util;
+		j_max = j_sg_cpu->max;
 
-		util = max(j_sg_cpu->util, util);
+		if (j_util * max > j_max * util) {
+			util = j_util;
+			max = j_max;
+		}
 	}
 
-	return get_next_freq(sg_policy, util, sg_policy->max);
+	return get_next_freq(sg_policy, util, max);
 }
 
 static void
@@ -751,7 +752,7 @@ static int sugov_start(struct cpufreq_policy *policy)
 {
 	struct sugov_policy *sg_policy = policy->governor_data;
 	void (*uu)(struct update_util_data *data, u64 time, unsigned int flags);
-	unsigned int cpu = cpumask_first(policy->cpus);
+	unsigned int cpu;
 
 	sg_policy->freq_update_delay_ns	= sg_policy->tunables->rate_limit_us * NSEC_PER_USEC;
 	sg_policy->last_freq_update_time	= 0;
@@ -759,7 +760,6 @@ static int sugov_start(struct cpufreq_policy *policy)
 	sg_policy->work_in_progress		= false;
 	sg_policy->limits_changed		= false;
 	sg_policy->cached_raw_freq		= 0;
-	sg_policy->max				= arch_scale_cpu_capacity(cpu);
 
 	sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 705b990d264d..f2260bc65226 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1289,6 +1289,7 @@ static int ftrace_add_mod(struct trace_array *tr,
 	if (!ftrace_mod)
 		return -ENOMEM;
 
+	INIT_LIST_HEAD(&ftrace_mod->list);
 	ftrace_mod->func = kstrdup(func, GFP_KERNEL);
 	ftrace_mod->module = kstrdup(module, GFP_KERNEL);
 	ftrace_mod->enable = enable;
@@ -3190,7 +3191,7 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count)
 		/* if we can't allocate this size, try something smaller */
 		if (!order)
 			return -ENOMEM;
-		order >>= 1;
+		order--;
 		goto again;
 	}
 
@@ -7391,7 +7392,7 @@ void __init ftrace_init(void)
 	}
 
 	pr_info("ftrace: allocating %ld entries in %ld pages\n",
-		count, count / ENTRIES_PER_PAGE + 1);
+		count, DIV_ROUND_UP(count, ENTRIES_PER_PAGE));
 
 	ret = ftrace_process_locs(NULL,
 				  __start_mcount_loc,
diff --git a/kernel/trace/kprobe_event_gen_test.c b/kernel/trace/kprobe_event_gen_test.c
index d81f7c51025c..c736487fc0e4 100644
--- a/kernel/trace/kprobe_event_gen_test.c
+++ b/kernel/trace/kprobe_event_gen_test.c
@@ -73,6 +73,10 @@ static struct trace_event_file *gen_kretprobe_test;
 #define KPROBE_GEN_TEST_ARG3	NULL
 #endif
 
+static bool trace_event_file_is_valid(struct trace_event_file *input)
+{
+	return input && !IS_ERR(input);
+}
 
 /*
  * Test to make sure we can create a kprobe event, then add more
@@ -139,6 +143,8 @@ static int __init test_gen_kprobe_cmd(void)
 	kfree(buf);
 	return ret;
  delete:
+	if (trace_event_file_is_valid(gen_kprobe_test))
+		gen_kprobe_test = NULL;
 	/* We got an error after creating the event, delete it */
 	ret = kprobe_event_delete("gen_kprobe_test");
 	goto out;
@@ -202,6 +208,8 @@ static int __init test_gen_kretprobe_cmd(void)
 	kfree(buf);
 	return ret;
  delete:
+	if (trace_event_file_is_valid(gen_kretprobe_test))
+		gen_kretprobe_test = NULL;
 	/* We got an error after creating the event, delete it */
 	ret = kprobe_event_delete("gen_kretprobe_test");
 	goto out;
@@ -217,10 +225,12 @@ static int __init kprobe_event_gen_test_init(void)
 
 	ret = test_gen_kretprobe_cmd();
 	if (ret) {
-		WARN_ON(trace_array_set_clr_event(gen_kretprobe_test->tr,
-						  "kprobes",
-						  "gen_kretprobe_test", false));
-		trace_put_event_file(gen_kretprobe_test);
+		if (trace_event_file_is_valid(gen_kretprobe_test)) {
+			WARN_ON(trace_array_set_clr_event(gen_kretprobe_test->tr,
+							  "kprobes",
+							  "gen_kretprobe_test", false));
+			trace_put_event_file(gen_kretprobe_test);
+		}
 		WARN_ON(kprobe_event_delete("gen_kretprobe_test"));
 	}
 
@@ -229,24 +239,30 @@ static int __init kprobe_event_gen_test_init(void)
 
 static void __exit kprobe_event_gen_test_exit(void)
 {
-	/* Disable the event or you can't remove it */
-	WARN_ON(trace_array_set_clr_event(gen_kprobe_test->tr,
-					  "kprobes",
-					  "gen_kprobe_test", false));
+	if (trace_event_file_is_valid(gen_kprobe_test)) {
+		/* Disable the event or you can't remove it */
+		WARN_ON(trace_array_set_clr_event(gen_kprobe_test->tr,
+						  "kprobes",
+						  "gen_kprobe_test", false));
+
+		/* Now give the file and instance back */
+		trace_put_event_file(gen_kprobe_test);
+	}
 
-	/* Now give the file and instance back */
-	trace_put_event_file(gen_kprobe_test);
 
 	/* Now unregister and free the event */
 	WARN_ON(kprobe_event_delete("gen_kprobe_test"));
 
-	/* Disable the event or you can't remove it */
-	WARN_ON(trace_array_set_clr_event(gen_kretprobe_test->tr,
-					  "kprobes",
-					  "gen_kretprobe_test", false));
+	if (trace_event_file_is_valid(gen_kretprobe_test)) {
+		/* Disable the event or you can't remove it */
+		WARN_ON(trace_array_set_clr_event(gen_kretprobe_test->tr,
+						  "kprobes",
+						  "gen_kretprobe_test", false));
+
+		/* Now give the file and instance back */
+		trace_put_event_file(gen_kretprobe_test);
+	}
 
-	/* Now give the file and instance back */
-	trace_put_event_file(gen_kretprobe_test);
 
 	/* Now unregister and free the event */
 	WARN_ON(kprobe_event_delete("gen_kretprobe_test"));
diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c
index c69d82273ce7..32c3dfdb4d6a 100644
--- a/kernel/trace/rethook.c
+++ b/kernel/trace/rethook.c
@@ -83,8 +83,10 @@ struct rethook *rethook_alloc(void *data, rethook_handler_t handler)
 {
 	struct rethook *rh = kzalloc(sizeof(struct rethook), GFP_KERNEL);
 
-	if (!rh || !handler)
+	if (!rh || !handler) {
+		kfree(rh);
 		return NULL;
+	}
 
 	rh->data = data;
 	rh->handler = handler;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 9712083832f4..b21bf14bae9b 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -519,6 +519,7 @@ struct ring_buffer_per_cpu {
 	local_t				committing;
 	local_t				commits;
 	local_t				pages_touched;
+	local_t				pages_lost;
 	local_t				pages_read;
 	long				last_pages_touch;
 	size_t				shortest_full;
@@ -894,10 +895,18 @@ size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu)
 size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu)
 {
 	size_t read;
+	size_t lost;
 	size_t cnt;
 
 	read = local_read(&buffer->buffers[cpu]->pages_read);
+	lost = local_read(&buffer->buffers[cpu]->pages_lost);
 	cnt = local_read(&buffer->buffers[cpu]->pages_touched);
+
+	if (WARN_ON_ONCE(cnt < lost))
+		return 0;
+
+	cnt -= lost;
+
 	/* The reader can read an empty page, but not more than that */
 	if (cnt < read) {
 		WARN_ON_ONCE(read > cnt + 1);
@@ -907,6 +916,21 @@ size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu)
 	return cnt - read;
 }
 
+static __always_inline bool full_hit(struct trace_buffer *buffer, int cpu, int full)
+{
+	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+	size_t nr_pages;
+	size_t dirty;
+
+	nr_pages = cpu_buffer->nr_pages;
+	if (!nr_pages || !full)
+		return true;
+
+	dirty = ring_buffer_nr_dirty_pages(buffer, cpu);
+
+	return (dirty * 100) > (full * nr_pages);
+}
+
 /*
  * rb_wake_up_waiters - wake up tasks waiting for ring buffer input
  *
@@ -1046,22 +1070,20 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
 		    !ring_buffer_empty_cpu(buffer, cpu)) {
 			unsigned long flags;
 			bool pagebusy;
-			size_t nr_pages;
-			size_t dirty;
+			bool done;
 
 			if (!full)
 				break;
 
 			raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 			pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page;
-			nr_pages = cpu_buffer->nr_pages;
-			dirty = ring_buffer_nr_dirty_pages(buffer, cpu);
+			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 (!pagebusy &&
-			    (!nr_pages || (dirty * 100) > full * nr_pages))
+			if (done)
 				break;
 		}
 
@@ -1087,6 +1109,7 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
  * @cpu: the cpu buffer to wait on
  * @filp: the file descriptor
  * @poll_table: The poll descriptor
+ * @full: wait until the percentage of pages are available, if @cpu != RING_BUFFER_ALL_CPUS
  *
  * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon
  * as data is added to any of the @buffer's cpu buffers. Otherwise
@@ -1096,14 +1119,15 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
  * zero otherwise.
  */
 __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
-			  struct file *filp, poll_table *poll_table)
+			  struct file *filp, poll_table *poll_table, int full)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct rb_irq_work *work;
 
-	if (cpu == RING_BUFFER_ALL_CPUS)
+	if (cpu == RING_BUFFER_ALL_CPUS) {
 		work = &buffer->irq_work;
-	else {
+		full = 0;
+	} else {
 		if (!cpumask_test_cpu(cpu, buffer->cpumask))
 			return -EINVAL;
 
@@ -1111,8 +1135,14 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
 		work = &cpu_buffer->irq_work;
 	}
 
-	poll_wait(filp, &work->waiters, poll_table);
-	work->waiters_pending = true;
+	if (full) {
+		poll_wait(filp, &work->full_waiters, poll_table);
+		work->full_waiters_pending = true;
+	} else {
+		poll_wait(filp, &work->waiters, poll_table);
+		work->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
@@ -1128,6 +1158,9 @@ __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;
@@ -1769,9 +1802,9 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
 
 	free_buffer_page(cpu_buffer->reader_page);
 
-	rb_head_page_deactivate(cpu_buffer);
-
 	if (head) {
+		rb_head_page_deactivate(cpu_buffer);
+
 		list_for_each_entry_safe(bpage, tmp, head, list) {
 			list_del_init(&bpage->list);
 			free_buffer_page(bpage);
@@ -2007,6 +2040,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
 			 */
 			local_add(page_entries, &cpu_buffer->overrun);
 			local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes);
+			local_inc(&cpu_buffer->pages_lost);
 		}
 
 		/*
@@ -2491,6 +2525,7 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer,
 		 */
 		local_add(entries, &cpu_buffer->overrun);
 		local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes);
+		local_inc(&cpu_buffer->pages_lost);
 
 		/*
 		 * The entries will be zeroed out when we move the
@@ -3155,10 +3190,6 @@ static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
 static __always_inline void
 rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
 {
-	size_t nr_pages;
-	size_t dirty;
-	size_t full;
-
 	if (buffer->irq_work.waiters_pending) {
 		buffer->irq_work.waiters_pending = false;
 		/* irq_work_queue() supplies it's own memory barriers */
@@ -3182,10 +3213,7 @@ rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
 
 	cpu_buffer->last_pages_touch = local_read(&cpu_buffer->pages_touched);
 
-	full = cpu_buffer->shortest_full;
-	nr_pages = cpu_buffer->nr_pages;
-	dirty = ring_buffer_nr_dirty_pages(buffer, cpu_buffer->cpu);
-	if (full && nr_pages && (dirty * 100) <= full * nr_pages)
+	if (!full_hit(buffer, cpu_buffer->cpu, cpu_buffer->shortest_full))
 		return;
 
 	cpu_buffer->irq_work.wakeup_full = true;
@@ -5248,6 +5276,7 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 	local_set(&cpu_buffer->committing, 0);
 	local_set(&cpu_buffer->commits, 0);
 	local_set(&cpu_buffer->pages_touched, 0);
+	local_set(&cpu_buffer->pages_lost, 0);
 	local_set(&cpu_buffer->pages_read, 0);
 	cpu_buffer->last_pages_touch = 0;
 	cpu_buffer->shortest_full = 0;
diff --git a/kernel/trace/synth_event_gen_test.c b/kernel/trace/synth_event_gen_test.c
index 0b15e975d2c2..8d77526892f4 100644
--- a/kernel/trace/synth_event_gen_test.c
+++ b/kernel/trace/synth_event_gen_test.c
@@ -120,15 +120,13 @@ static int __init test_gen_synth_cmd(void)
 
 	/* Now generate a gen_synth_test event */
 	ret = synth_event_trace_array(gen_synth_test, vals, ARRAY_SIZE(vals));
- out:
+ free:
+	kfree(buf);
 	return ret;
  delete:
 	/* We got an error after creating the event, delete it */
 	synth_event_delete("gen_synth_test");
- free:
-	kfree(buf);
-
-	goto out;
+	goto free;
 }
 
 /*
@@ -227,15 +225,13 @@ static int __init test_empty_synth_event(void)
 
 	/* Now trace an empty_synth_test event */
 	ret = synth_event_trace_array(empty_synth_test, vals, ARRAY_SIZE(vals));
- out:
+ free:
+	kfree(buf);
 	return ret;
  delete:
 	/* We got an error after creating the event, delete it */
 	synth_event_delete("empty_synth_test");
- free:
-	kfree(buf);
-
-	goto out;
+	goto free;
 }
 
 static struct synth_field_desc create_synth_test_fields[] = {
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 47a44b055a1d..5cfc95a52bc3 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2180,10 +2180,12 @@ void tracing_reset_online_cpus(struct array_buffer *buf)
 }
 
 /* Must have trace_types_lock held */
-void tracing_reset_all_online_cpus(void)
+void tracing_reset_all_online_cpus_unlocked(void)
 {
 	struct trace_array *tr;
 
+	lockdep_assert_held(&trace_types_lock);
+
 	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
 		if (!tr->clear_trace)
 			continue;
@@ -2195,6 +2197,13 @@ void tracing_reset_all_online_cpus(void)
 	}
 }
 
+void tracing_reset_all_online_cpus(void)
+{
+	mutex_lock(&trace_types_lock);
+	tracing_reset_all_online_cpus_unlocked();
+	mutex_unlock(&trace_types_lock);
+}
+
 /*
  * The tgid_map array maps from pid to tgid; i.e. the value stored at index i
  * is the tgid last observed corresponding to pid=i.
@@ -6657,6 +6666,7 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
 	mutex_unlock(&trace_types_lock);
 
 	free_cpumask_var(iter->started);
+	kfree(iter->fmt);
 	mutex_destroy(&iter->mutex);
 	kfree(iter);
 
@@ -6681,7 +6691,7 @@ trace_poll(struct trace_iterator *iter, struct file *filp, poll_table *poll_tabl
 		return EPOLLIN | EPOLLRDNORM;
 	else
 		return ring_buffer_poll_wait(iter->array_buffer->buffer, iter->cpu_file,
-					     filp, poll_table);
+					     filp, poll_table, iter->tr->buffer_percent);
 }
 
 static __poll_t
@@ -7802,6 +7812,7 @@ static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr,
 						   int len)
 {
 	struct tracing_log_err *err;
+	char *cmd;
 
 	if (tr->n_err_log_entries < TRACING_LOG_ERRS_MAX) {
 		err = alloc_tracing_log_err(len);
@@ -7810,12 +7821,12 @@ static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr,
 
 		return err;
 	}
-
+	cmd = kzalloc(len, GFP_KERNEL);
+	if (!cmd)
+		return ERR_PTR(-ENOMEM);
 	err = list_first_entry(&tr->err_log, struct tracing_log_err, list);
 	kfree(err->cmd);
-	err->cmd = kzalloc(len, GFP_KERNEL);
-	if (!err->cmd)
-		return ERR_PTR(-ENOMEM);
+	err->cmd = cmd;
 	list_del(&err->list);
 
 	return err;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 54ee5711c729..d42e24507152 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -580,6 +580,7 @@ int tracing_is_enabled(void);
 void tracing_reset_online_cpus(struct array_buffer *buf);
 void tracing_reset_current(int cpu);
 void tracing_reset_all_online_cpus(void);
+void tracing_reset_all_online_cpus_unlocked(void);
 int tracing_open_generic(struct inode *inode, struct file *filp);
 int tracing_open_generic_tr(struct inode *inode, struct file *filp);
 bool tracing_is_disabled(void);
diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c
index 154996684fb5..4376887e0d8a 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -118,6 +118,7 @@ int dyn_event_release(const char *raw_command, struct dyn_event_operations *type
 		if (ret)
 			break;
 	}
+	tracing_reset_all_online_cpus();
 	mutex_unlock(&event_mutex);
 out:
 	argv_free(argv);
@@ -214,6 +215,7 @@ int dyn_events_release_all(struct dyn_event_operations *type)
 			break;
 	}
 out:
+	tracing_reset_all_online_cpus();
 	mutex_unlock(&event_mutex);
 
 	return ret;
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index 5dd0617e5df6..352b65e2b910 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -52,6 +52,7 @@ static void trace_event_probe_cleanup(struct trace_eprobe *ep)
 	kfree(ep->event_system);
 	if (ep->event)
 		trace_event_put_ref(ep->event);
+	kfree(ep->filter_str);
 	kfree(ep);
 }
 
@@ -563,6 +564,9 @@ static void eprobe_trigger_func(struct event_trigger_data *data,
 {
 	struct eprobe_data *edata = data->private_data;
 
+	if (unlikely(!rec))
+		return;
+
 	__eprobe_trace_func(edata, rec);
 }
 
@@ -642,7 +646,7 @@ new_eprobe_trigger(struct trace_eprobe *ep, struct trace_event_file *file)
 	INIT_LIST_HEAD(&trigger->list);
 
 	if (ep->filter_str) {
-		ret = create_event_filter(file->tr, file->event_call,
+		ret = create_event_filter(file->tr, ep->event,
 					ep->filter_str, false, &filter);
 		if (ret)
 			goto error;
@@ -900,7 +904,7 @@ static int trace_eprobe_tp_update_arg(struct trace_eprobe *ep, const char *argv[
 
 static int trace_eprobe_parse_filter(struct trace_eprobe *ep, int argc, const char *argv[])
 {
-	struct event_filter *dummy;
+	struct event_filter *dummy = NULL;
 	int i, ret, len = 0;
 	char *p;
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 0356cae0cf74..f71ea6e79b3c 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2880,7 +2880,10 @@ static int probe_remove_event_call(struct trace_event_call *call)
 		 * TRACE_REG_UNREGISTER.
 		 */
 		if (file->flags & EVENT_FILE_FL_ENABLED)
-			return -EBUSY;
+			goto busy;
+
+		if (file->flags & EVENT_FILE_FL_WAS_ENABLED)
+			tr->clear_trace = true;
 		/*
 		 * The do_for_each_event_file_safe() is
 		 * a double loop. After finding the call for this
@@ -2893,6 +2896,12 @@ static int probe_remove_event_call(struct trace_event_call *call)
 	__trace_remove_event_call(call);
 
 	return 0;
+ busy:
+	/* No need to clear the trace now */
+	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+		tr->clear_trace = false;
+	}
+	return -EBUSY;
 }
 
 /* Remove an event_call */
@@ -2972,7 +2981,7 @@ static void trace_module_remove_events(struct module *mod)
 	 * over from this module may be passed to the new module events and
 	 * unexpected results may occur.
 	 */
-	tracing_reset_all_online_cpus();
+	tracing_reset_all_online_cpus_unlocked();
 }
 
 static int trace_module_notify(struct notifier_block *self,
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 48465f7e97b4..1c82478e8dff 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -983,7 +983,7 @@ static struct hist_field *find_any_var_ref(struct hist_trigger_data *hist_data,
  * A trigger can define one or more variables.  If any one of them is
  * currently referenced by any other trigger, this function will
  * determine that.
-
+ *
  * Typically used to determine whether or not a trigger can be removed
  * - if there are any references to a trigger's variables, it cannot.
  *
@@ -3226,7 +3226,7 @@ static struct field_var *create_field_var(struct hist_trigger_data *hist_data,
  * events.  However, for convenience, users are allowed to directly
  * specify an event field in an action, which will be automatically
  * converted into a variable on their behalf.
-
+ *
  * This function creates a field variable with the name var_name on
  * the hist trigger currently being defined on the target event.  If
  * subsys_name and event_name are specified, this function simply
@@ -5143,6 +5143,9 @@ static void event_hist_trigger(struct event_trigger_data *data,
 	void *key = NULL;
 	unsigned int i;
 
+	if (unlikely(!rbe))
+		return;
+
 	memset(compound_key, 0, hist_data->key_size);
 
 	for_each_hist_key_field(i, hist_data) {
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index e310052dc83c..c3b582d19b62 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -828,10 +828,9 @@ static int register_synth_event(struct synth_event *event)
 	}
 
 	ret = set_synth_event_print_fmt(call);
-	if (ret < 0) {
+	/* unregister_trace_event() will be called inside */
+	if (ret < 0)
 		trace_remove_event_call(call);
-		goto err;
-	}
  out:
 	return ret;
  err:
@@ -1426,7 +1425,6 @@ int synth_event_delete(const char *event_name)
 	mutex_unlock(&event_mutex);
 
 	if (mod) {
-		mutex_lock(&trace_types_lock);
 		/*
 		 * It is safest to reset the ring buffer if the module
 		 * being unloaded registered any events that were
@@ -1438,7 +1436,6 @@ int synth_event_delete(const char *event_name)
 		 * occur.
 		 */
 		tracing_reset_all_online_cpus();
-		mutex_unlock(&trace_types_lock);
 	}
 
 	return ret;
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index ae78c2d53c8a..539b08ae7020 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -1100,8 +1100,10 @@ static int user_event_create(const char *raw_command)
 
 	group = current_user_event_group();
 
-	if (!group)
+	if (!group) {
+		kfree(name);
 		return -ENOENT;
+	}
 
 	mutex_lock(&group->reg_mutex);
 
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index 78d536d3ff3d..4300c5dc4e5d 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -917,7 +917,7 @@ void osnoise_trace_irq_entry(int id)
 void osnoise_trace_irq_exit(int id, const char *desc)
 {
 	struct osnoise_variables *osn_var = this_cpu_osn_var();
-	int duration;
+	s64 duration;
 
 	if (!osn_var->sampling)
 		return;
@@ -1048,7 +1048,7 @@ static void trace_softirq_entry_callback(void *data, unsigned int vec_nr)
 static void trace_softirq_exit_callback(void *data, unsigned int vec_nr)
 {
 	struct osnoise_variables *osn_var = this_cpu_osn_var();
-	int duration;
+	s64 duration;
 
 	if (!osn_var->sampling)
 		return;
@@ -1144,7 +1144,7 @@ thread_entry(struct osnoise_variables *osn_var, struct task_struct *t)
 static void
 thread_exit(struct osnoise_variables *osn_var, struct task_struct *t)
 {
-	int duration;
+	s64 duration;
 
 	if (!osn_var->sampling)
 		return;
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index b69e207012c9..942ddbdace4a 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -201,8 +201,6 @@ print_syscall_exit(struct trace_iterator *iter, int flags,
 	return trace_handle_return(s);
 }
 
-extern char *__bad_type_size(void);
-
 #define SYSCALL_FIELD(_type, _name) {					\
 	.type = #_type, .name = #_name,					\
 	.size = sizeof(_type), .align = __alignof__(_type),		\