25 files changed, 695 insertions, 224 deletions

diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 84b2d9dba79a..ece9870cab68 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -494,8 +494,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 	refcount_set(&kvalue->refcnt, 1);
 	bpf_map_inc(map);
 
-	set_memory_ro((long)st_map->image, 1);
-	set_memory_x((long)st_map->image, 1);
+	set_memory_rox((long)st_map->image, 1);
 	err = st_ops->reg(kdata);
 	if (likely(!err)) {
 		/* Pair with smp_load_acquire() during lookup_elem().
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 7f98dec6e90f..6cca66b39d01 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -868,8 +868,7 @@ static struct bpf_prog_pack *alloc_new_pack(bpf_jit_fill_hole_t bpf_fill_ill_ins
 	list_add_tail(&pack->list, &pack_list);
 
 	set_vm_flush_reset_perms(pack->ptr);
-	set_memory_ro((unsigned long)pack->ptr, BPF_PROG_PACK_SIZE / PAGE_SIZE);
-	set_memory_x((unsigned long)pack->ptr, BPF_PROG_PACK_SIZE / PAGE_SIZE);
+	set_memory_rox((unsigned long)pack->ptr, BPF_PROG_PACK_SIZE / PAGE_SIZE);
 	return pack;
 }
 
@@ -887,8 +886,7 @@ void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns)
 		if (ptr) {
 			bpf_fill_ill_insns(ptr, size);
 			set_vm_flush_reset_perms(ptr);
-			set_memory_ro((unsigned long)ptr, size / PAGE_SIZE);
-			set_memory_x((unsigned long)ptr, size / PAGE_SIZE);
+			set_memory_rox((unsigned long)ptr, size / PAGE_SIZE);
 		}
 		goto out;
 	}
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index d6395215b849..11f5ec0b8016 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -468,8 +468,7 @@ again:
 	if (err < 0)
 		goto out;
 
-	set_memory_ro((long)im->image, 1);
-	set_memory_x((long)im->image, 1);
+	set_memory_rox((long)im->image, 1);
 
 	WARN_ON(tr->cur_image && tr->selector == 0);
 	WARN_ON(!tr->cur_image && tr->selector);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e47914ac8732..eacc3702654d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7493,7 +7493,7 @@ static u64 perf_get_pgtable_size(struct mm_struct *mm, unsigned long addr)
 		return pud_leaf_size(pud);
 
 	pmdp = pmd_offset_lockless(pudp, pud, addr);
-	pmd = READ_ONCE(*pmdp);
+	pmd = pmdp_get_lockless(pmdp);
 	if (!pmd_present(pmd))
 		return 0;
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 7a08025d2c99..9f7fe3541897 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2607,11 +2607,6 @@ struct task_struct * __init fork_idle(int cpu)
 	return task;
 }
 
-struct mm_struct *copy_init_mm(void)
-{
-	return dup_mm(NULL, &init_mm);
-}
-
 /*
  * This is like kernel_clone(), but shaved down and tailored to just
  * creating io_uring workers. It returns a created task, or an error pointer.
@@ -3030,10 +3025,27 @@ static void sighand_ctor(void *data)
 	init_waitqueue_head(&sighand->signalfd_wqh);
 }
 
-void __init proc_caches_init(void)
+void __init mm_cache_init(void)
 {
 	unsigned int mm_size;
 
+	/*
+	 * The mm_cpumask is located at the end of mm_struct, and is
+	 * dynamically sized based on the maximum CPU number this system
+	 * can have, taking hotplug into account (nr_cpu_ids).
+	 */
+	mm_size = sizeof(struct mm_struct) + cpumask_size();
+
+	mm_cachep = kmem_cache_create_usercopy("mm_struct",
+			mm_size, ARCH_MIN_MMSTRUCT_ALIGN,
+			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
+			offsetof(struct mm_struct, saved_auxv),
+			sizeof_field(struct mm_struct, saved_auxv),
+			NULL);
+}
+
+void __init proc_caches_init(void)
+{
 	sighand_cachep = kmem_cache_create("sighand_cache",
 			sizeof(struct sighand_struct), 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU|
@@ -3051,19 +3063,6 @@ void __init proc_caches_init(void)
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
 			NULL);
 
-	/*
-	 * The mm_cpumask is located at the end of mm_struct, and is
-	 * dynamically sized based on the maximum CPU number this system
-	 * can have, taking hotplug into account (nr_cpu_ids).
-	 */
-	mm_size = sizeof(struct mm_struct) + cpumask_size();
-
-	mm_cachep = kmem_cache_create_usercopy("mm_struct",
-			mm_size, ARCH_MIN_MMSTRUCT_ALIGN,
-			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
-			offsetof(struct mm_struct, saved_auxv),
-			sizeof_field(struct mm_struct, saved_auxv),
-			NULL);
 	vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT);
 	mmap_init();
 	nsproxy_cache_init();
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index bd4d4dd626b4..955267bbc2be 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -165,7 +165,8 @@ static bool msi_ctrl_valid(struct device *dev, struct msi_ctrl *ctrl)
 	unsigned int hwsize;
 
 	if (WARN_ON_ONCE(ctrl->domid >= MSI_MAX_DEVICE_IRQDOMAINS ||
-			 !dev->msi.data->__domains[ctrl->domid].domain))
+			 (dev->msi.domain &&
+			  !dev->msi.data->__domains[ctrl->domid].domain)))
 		return false;
 
 	hwsize = msi_domain_get_hwsize(dev, ctrl->domid);
@@ -609,8 +610,8 @@ static unsigned int msi_domain_get_hwsize(struct device *dev, unsigned int domid
 		info = domain->host_data;
 		return info->hwsize;
 	}
-	/* No domain, no size... */
-	return 0;
+	/* No domain, default to MSI_XA_DOMAIN_SIZE */
+	return MSI_XA_DOMAIN_SIZE;
 }
 
 static inline void irq_chip_write_msi_msg(struct irq_data *data,
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 65dba9076f31..2df00b789b90 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -6,6 +6,7 @@
  * Copyright (C) 2004 Kay Sievers <kay.sievers@vrfy.org>
  */
 
+#include <asm/byteorder.h>
 #include <linux/kobject.h>
 #include <linux/string.h>
 #include <linux/sysfs.h>
@@ -20,6 +21,14 @@
 
 #include <linux/rcupdate.h>	/* rcu_expedited and rcu_normal */
 
+#if defined(__LITTLE_ENDIAN)
+#define CPU_BYTEORDER_STRING	"little"
+#elif defined(__BIG_ENDIAN)
+#define CPU_BYTEORDER_STRING	"big"
+#else
+#error Unknown byteorder
+#endif
+
 #define KERNEL_ATTR_RO(_name) \
 static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
 
@@ -34,6 +43,14 @@ static ssize_t uevent_seqnum_show(struct kobject *kobj,
 }
 KERNEL_ATTR_RO(uevent_seqnum);
 
+/* cpu byteorder */
+static ssize_t cpu_byteorder_show(struct kobject *kobj,
+				  struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%s\n", CPU_BYTEORDER_STRING);
+}
+KERNEL_ATTR_RO(cpu_byteorder);
+
 #ifdef CONFIG_UEVENT_HELPER
 /* uevent helper program, used during early boot */
 static ssize_t uevent_helper_show(struct kobject *kobj,
@@ -215,6 +232,7 @@ EXPORT_SYMBOL_GPL(kernel_kobj);
 static struct attribute * kernel_attrs[] = {
 	&fscaps_attr.attr,
 	&uevent_seqnum_attr.attr,
+	&cpu_byteorder_attr.attr,
 #ifdef CONFIG_UEVENT_HELPER
 	&uevent_helper_attr.attr,
 #endif
diff --git a/kernel/params.c b/kernel/params.c
index a06f80c56f19..14d66070757b 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -926,7 +926,7 @@ static const struct sysfs_ops module_sysfs_ops = {
 	.store = module_attr_store,
 };
 
-static int uevent_filter(struct kobject *kobj)
+static int uevent_filter(const struct kobject *kobj)
 {
 	const struct kobj_type *ktype = get_ktype(kobj);
 
diff --git a/kernel/resource.c b/kernel/resource.c
index 82ed54cd1f0d..ddbbacb9fb50 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -888,7 +888,7 @@ void insert_resource_expand_to_fit(struct resource *root, struct resource *new)
 		if (conflict->end > new->end)
 			new->end = conflict->end;
 
-		printk("Expanded resource %s due to conflict with %s\n", new->name, conflict->name);
+		pr_info("Expanded resource %s due to conflict with %s\n", new->name, conflict->name);
 	}
 	write_unlock(&resource_lock);
 }
@@ -1283,9 +1283,7 @@ void __release_region(struct resource *parent, resource_size_t start,
 
 	write_unlock(&resource_lock);
 
-	printk(KERN_WARNING "Trying to free nonexistent resource "
-		"<%016llx-%016llx>\n", (unsigned long long)start,
-		(unsigned long long)end);
+	pr_warn("Trying to free nonexistent resource <%pa-%pa>\n", &start, &end);
 }
 EXPORT_SYMBOL(__release_region);
 
@@ -1658,6 +1656,7 @@ __setup("reserve=", reserve_setup);
 int iomem_map_sanity_check(resource_size_t addr, unsigned long size)
 {
 	struct resource *p = &iomem_resource;
+	resource_size_t end = addr + size - 1;
 	int err = 0;
 	loff_t l;
 
@@ -1667,12 +1666,12 @@ int iomem_map_sanity_check(resource_size_t addr, unsigned long size)
 		 * We can probably skip the resources without
 		 * IORESOURCE_IO attribute?
 		 */
-		if (p->start >= addr + size)
+		if (p->start > end)
 			continue;
 		if (p->end < addr)
 			continue;
 		if (PFN_DOWN(p->start) <= PFN_DOWN(addr) &&
-		    PFN_DOWN(p->end) >= PFN_DOWN(addr + size - 1))
+		    PFN_DOWN(p->end) >= PFN_DOWN(end))
 			continue;
 		/*
 		 * if a resource is "BUSY", it's not a hardware resource
@@ -1683,10 +1682,8 @@ int iomem_map_sanity_check(resource_size_t addr, unsigned long size)
 		if (p->flags & IORESOURCE_BUSY)
 			continue;
 
-		printk(KERN_WARNING "resource sanity check: requesting [mem %#010llx-%#010llx], which spans more than %s %pR\n",
-		       (unsigned long long)addr,
-		       (unsigned long long)(addr + size - 1),
-		       p->name, p);
+		pr_warn("resource sanity check: requesting [mem %pa-%pa], which spans more than %s %pR\n",
+			&addr, &end, p->name, p);
 		err = -1;
 		break;
 	}
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 2c6611c13f99..e95c8fe478cd 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -375,6 +375,7 @@ config SCHED_TRACER
 config HWLAT_TRACER
 	bool "Tracer to detect hardware latencies (like SMIs)"
 	select GENERIC_TRACER
+	select TRACER_MAX_TRACE
 	help
 	 This tracer, when enabled will create one or more kernel threads,
 	 depending on what the cpumask file is set to, which each thread
@@ -410,6 +411,7 @@ config HWLAT_TRACER
 config OSNOISE_TRACER
 	bool "OS Noise tracer"
 	select GENERIC_TRACER
+	select TRACER_MAX_TRACE
 	help
 	  In the context of high-performance computing (HPC), the Operating
 	  System Noise (osnoise) refers to the interference experienced by an
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 8e842f68b9a5..442438b93fe9 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -163,7 +163,7 @@ static void ftrace_sync_ipi(void *data)
 static ftrace_func_t ftrace_ops_get_list_func(struct ftrace_ops *ops)
 {
 	/*
-	 * If this is a dynamic, RCU, or per CPU ops, or we force list func,
+	 * If this is a dynamic or RCU ops, or we force list func,
 	 * then it needs to call the list anyway.
 	 */
 	if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_RCU) ||
@@ -2762,6 +2762,19 @@ void __weak ftrace_arch_code_modify_post_process(void)
 {
 }
 
+static int update_ftrace_func(ftrace_func_t func)
+{
+	static ftrace_func_t save_func;
+
+	/* Avoid updating if it hasn't changed */
+	if (func == save_func)
+		return 0;
+
+	save_func = func;
+
+	return ftrace_update_ftrace_func(func);
+}
+
 void ftrace_modify_all_code(int command)
 {
 	int update = command & FTRACE_UPDATE_TRACE_FUNC;
@@ -2782,7 +2795,7 @@ void ftrace_modify_all_code(int command)
 	 * traced.
 	 */
 	if (update) {
-		err = ftrace_update_ftrace_func(ftrace_ops_list_func);
+		err = update_ftrace_func(ftrace_ops_list_func);
 		if (FTRACE_WARN_ON(err))
 			return;
 	}
@@ -2798,7 +2811,7 @@ void ftrace_modify_all_code(int command)
 		/* If irqs are disabled, we are in stop machine */
 		if (!irqs_disabled())
 			smp_call_function(ftrace_sync_ipi, NULL, 1);
-		err = ftrace_update_ftrace_func(ftrace_trace_function);
+		err = update_ftrace_func(ftrace_trace_function);
 		if (FTRACE_WARN_ON(err))
 			return;
 	}
@@ -3070,8 +3083,6 @@ out:
 	/*
 	 * Dynamic ops may be freed, we must make sure that all
 	 * callers are done before leaving this function.
-	 * The same goes for freeing the per_cpu data of the per_cpu
-	 * ops.
 	 */
 	if (ops->flags & FTRACE_OPS_FL_DYNAMIC) {
 		/*
@@ -4192,6 +4203,7 @@ match_records(struct ftrace_hash *hash, char *func, int len, char *mod)
 			}
 			found = 1;
 		}
+		cond_resched();
 	} while_for_each_ftrace_rec();
  out_unlock:
 	mutex_unlock(&ftrace_lock);
@@ -7518,8 +7530,6 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 		/*
 		 * Check the following for each ops before calling their func:
 		 *  if RCU flag is set, then rcu_is_watching() must be true
-		 *  if PER_CPU is set, then ftrace_function_local_disable()
-		 *                          must be false
 		 *  Otherwise test if the ip matches the ops filter
 		 *
 		 * If any of the above fails then the op->func() is not executed.
@@ -7569,8 +7579,8 @@ NOKPROBE_SYMBOL(arch_ftrace_ops_list_func);
 
 /*
  * If there's only one function registered but it does not support
- * recursion, needs RCU protection and/or requires per cpu handling, then
- * this function will be called by the mcount trampoline.
+ * recursion, needs RCU protection, then this function will be called
+ * by the mcount trampoline.
  */
 static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip,
 				   struct ftrace_ops *op, struct ftrace_regs *fregs)
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index b21bf14bae9b..c366a0a9ddba 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2062,8 +2062,10 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	struct list_head *pages = &cpu_buffer->new_pages;
 	int retries, success;
+	unsigned long flags;
 
-	raw_spin_lock_irq(&cpu_buffer->reader_lock);
+	/* Can be called at early boot up, where interrupts must not been enabled */
+	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 	/*
 	 * We are holding the reader lock, so the reader page won't be swapped
 	 * in the ring buffer. Now we are racing with the writer trying to
@@ -2120,7 +2122,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer)
 	 * tracing
 	 */
 	RB_WARN_ON(cpu_buffer, !success);
-	raw_spin_unlock_irq(&cpu_buffer->reader_lock);
+	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
 	/* free pages if they weren't inserted */
 	if (!success) {
@@ -2248,8 +2250,16 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 				rb_update_pages(cpu_buffer);
 				cpu_buffer->nr_pages_to_update = 0;
 			} else {
-				schedule_work_on(cpu,
-						&cpu_buffer->update_pages_work);
+				/* Run directly if possible. */
+				migrate_disable();
+				if (cpu != smp_processor_id()) {
+					migrate_enable();
+					schedule_work_on(cpu,
+							 &cpu_buffer->update_pages_work);
+				} else {
+					update_pages_handler(&cpu_buffer->update_pages_work);
+					migrate_enable();
+				}
 			}
 		}
 
@@ -2298,9 +2308,17 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 		if (!cpu_online(cpu_id))
 			rb_update_pages(cpu_buffer);
 		else {
-			schedule_work_on(cpu_id,
-					 &cpu_buffer->update_pages_work);
-			wait_for_completion(&cpu_buffer->update_done);
+			/* Run directly if possible. */
+			migrate_disable();
+			if (cpu_id == smp_processor_id()) {
+				rb_update_pages(cpu_buffer);
+				migrate_enable();
+			} else {
+				migrate_enable();
+				schedule_work_on(cpu_id,
+						 &cpu_buffer->update_pages_work);
+				wait_for_completion(&cpu_buffer->update_done);
+			}
 		}
 
 		cpu_buffer->nr_pages_to_update = 0;
@@ -3180,8 +3198,7 @@ static inline void rb_event_discard(struct ring_buffer_event *event)
 		event->time_delta = 1;
 }
 
-static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
-		      struct ring_buffer_event *event)
+static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	local_inc(&cpu_buffer->entries);
 	rb_end_commit(cpu_buffer);
@@ -3383,15 +3400,14 @@ void ring_buffer_nest_end(struct trace_buffer *buffer)
  *
  * Must be paired with ring_buffer_lock_reserve.
  */
-int ring_buffer_unlock_commit(struct trace_buffer *buffer,
-			      struct ring_buffer_event *event)
+int ring_buffer_unlock_commit(struct trace_buffer *buffer)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	int cpu = raw_smp_processor_id();
 
 	cpu_buffer = buffer->buffers[cpu];
 
-	rb_commit(cpu_buffer, event);
+	rb_commit(cpu_buffer);
 
 	rb_wakeups(buffer, cpu_buffer);
 
@@ -3977,7 +3993,7 @@ int ring_buffer_write(struct trace_buffer *buffer,
 
 	memcpy(body, data, length);
 
-	rb_commit(cpu_buffer, event);
+	rb_commit(cpu_buffer);
 
 	rb_wakeups(buffer, cpu_buffer);
 
@@ -5998,7 +6014,7 @@ static __init int rb_write_something(struct rb_test_data *data, bool nested)
 	}
 
  out:
-	ring_buffer_unlock_commit(data->buffer, event);
+	ring_buffer_unlock_commit(data->buffer);
 
 	return 0;
 }
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index 78e576575b79..aef34673d79d 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -258,7 +258,7 @@ static void ring_buffer_producer(void)
 				hit++;
 				entry = ring_buffer_event_data(event);
 				*entry = smp_processor_id();
-				ring_buffer_unlock_commit(buffer, event);
+				ring_buffer_unlock_commit(buffer);
 			}
 		}
 		end_time = ktime_get();
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 5cfc95a52bc3..6d7ef130f57e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -19,7 +19,6 @@
 #include <linux/kallsyms.h>
 #include <linux/security.h>
 #include <linux/seq_file.h>
-#include <linux/notifier.h>
 #include <linux/irqflags.h>
 #include <linux/debugfs.h>
 #include <linux/tracefs.h>
@@ -85,7 +84,7 @@ void __init disable_tracing_selftest(const char *reason)
 #endif
 
 /* Pipe tracepoints to printk */
-struct trace_iterator *tracepoint_print_iter;
+static struct trace_iterator *tracepoint_print_iter;
 int tracepoint_printk;
 static bool tracepoint_printk_stop_on_boot __initdata;
 static DEFINE_STATIC_KEY_FALSE(tracepoint_printk_key);
@@ -999,7 +998,7 @@ __buffer_unlock_commit(struct trace_buffer *buffer, struct ring_buffer_event *ev
 		/* ring_buffer_unlock_commit() enables preemption */
 		preempt_enable_notrace();
 	} else
-		ring_buffer_unlock_commit(buffer, event);
+		ring_buffer_unlock_commit(buffer);
 }
 
 /**
@@ -1421,6 +1420,7 @@ int tracing_snapshot_cond_disable(struct trace_array *tr)
 	return false;
 }
 EXPORT_SYMBOL_GPL(tracing_snapshot_cond_disable);
+#define free_snapshot(tr)	do { } while (0)
 #endif /* CONFIG_TRACER_SNAPSHOT */
 
 void tracer_tracing_off(struct trace_array *tr)
@@ -1692,6 +1692,8 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 }
 
 unsigned long __read_mostly	tracing_thresh;
+
+#ifdef CONFIG_TRACER_MAX_TRACE
 static const struct file_operations tracing_max_lat_fops;
 
 #ifdef LATENCY_FS_NOTIFY
@@ -1748,18 +1750,14 @@ void latency_fsnotify(struct trace_array *tr)
 	irq_work_queue(&tr->fsnotify_irqwork);
 }
 
-#elif defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)	\
-	|| defined(CONFIG_OSNOISE_TRACER)
+#else /* !LATENCY_FS_NOTIFY */
 
 #define trace_create_maxlat_file(tr, d_tracer)				\
 	trace_create_file("tracing_max_latency", TRACE_MODE_WRITE,	\
 			  d_tracer, &tr->max_latency, &tracing_max_lat_fops)
 
-#else
-#define trace_create_maxlat_file(tr, d_tracer)	 do { } while (0)
 #endif
 
-#ifdef CONFIG_TRACER_MAX_TRACE
 /*
  * Copy the new maximum trace into the separate maximum-trace
  * structure. (this way the maximum trace is permanently saved,
@@ -1834,14 +1832,15 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu,
 		ring_buffer_record_off(tr->max_buffer.buffer);
 
 #ifdef CONFIG_TRACER_SNAPSHOT
-	if (tr->cond_snapshot && !tr->cond_snapshot->update(tr, cond_data))
-		goto out_unlock;
+	if (tr->cond_snapshot && !tr->cond_snapshot->update(tr, cond_data)) {
+		arch_spin_unlock(&tr->max_lock);
+		return;
+	}
 #endif
 	swap(tr->array_buffer.buffer, tr->max_buffer.buffer);
 
 	__update_max_tr(tr, tsk, cpu);
 
- out_unlock:
 	arch_spin_unlock(&tr->max_lock);
 }
 
@@ -1888,6 +1887,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 	__update_max_tr(tr, tsk, cpu);
 	arch_spin_unlock(&tr->max_lock);
 }
+
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
 static int wait_on_pipe(struct trace_iterator *iter, int full)
@@ -5678,6 +5678,7 @@ static const char readme_msg[] =
 	"\t            [:size=#entries]\n"
 	"\t            [:pause][:continue][:clear]\n"
 	"\t            [:name=histname1]\n"
+	"\t            [:nohitcount]\n"
 	"\t            [:<handler>.<action>]\n"
 	"\t            [if <filter>]\n\n"
 	"\t    Note, special fields can be used as well:\n"
@@ -5724,7 +5725,9 @@ static const char readme_msg[] =
 	"\t            .syscall    display a syscall id as a syscall name\n"
 	"\t            .log2       display log2 value rather than raw number\n"
 	"\t            .buckets=size  display values in groups of size rather than raw number\n"
-	"\t            .usecs      display a common_timestamp in microseconds\n\n"
+	"\t            .usecs      display a common_timestamp in microseconds\n"
+	"\t            .percent    display a number of percentage value\n"
+	"\t            .graph      display a bar-graph of a value\n\n"
 	"\t    The 'pause' parameter can be used to pause an existing hist\n"
 	"\t    trigger or to start a hist trigger but not log any events\n"
 	"\t    until told to do so.  'continue' can be used to start or\n"
@@ -5732,6 +5735,8 @@ static const char readme_msg[] =
 	"\t    The 'clear' parameter will clear the contents of a running\n"
 	"\t    hist trigger and leave its current paused/active state\n"
 	"\t    unchanged.\n\n"
+	"\t    The 'nohitcount' (or NOHC) parameter will suppress display of\n"
+	"\t    raw hitcount in the histogram.\n\n"
 	"\t    The enable_hist and disable_hist triggers can be used to\n"
 	"\t    have one event conditionally start and stop another event's\n"
 	"\t    already-attached hist trigger.  The syntax is analogous to\n"
@@ -6572,7 +6577,7 @@ out:
 	return ret;
 }
 
-#if defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)
+#ifdef CONFIG_TRACER_MAX_TRACE
 
 static ssize_t
 tracing_max_lat_read(struct file *filp, char __user *ubuf,
@@ -6796,7 +6801,20 @@ waitagain:
 
 		ret = print_trace_line(iter);
 		if (ret == TRACE_TYPE_PARTIAL_LINE) {
-			/* don't print partial lines */
+			/*
+			 * If one print_trace_line() fills entire trace_seq in one shot,
+			 * trace_seq_to_user() will returns -EBUSY because save_len == 0,
+			 * In this case, we need to consume it, otherwise, loop will peek
+			 * this event next time, resulting in an infinite loop.
+			 */
+			if (save_len == 0) {
+				iter->seq.full = 0;
+				trace_seq_puts(&iter->seq, "[LINE TOO BIG]\n");
+				trace_consume(iter);
+				break;
+			}
+
+			/* In other cases, don't print partial lines */
 			iter->seq.seq.len = save_len;
 			break;
 		}
@@ -7587,7 +7605,7 @@ static const struct file_operations tracing_thresh_fops = {
 	.llseek		= generic_file_llseek,
 };
 
-#if defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)
+#ifdef CONFIG_TRACER_MAX_TRACE
 static const struct file_operations tracing_max_lat_fops = {
 	.open		= tracing_open_generic,
 	.read		= tracing_max_lat_read,
@@ -9601,7 +9619,9 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 
 	create_trace_options_dir(tr);
 
+#ifdef CONFIG_TRACER_MAX_TRACE
 	trace_create_maxlat_file(tr, d_tracer);
+#endif
 
 	if (ftrace_create_function_files(tr, d_tracer))
 		MEM_FAIL(1, "Could not allocate function filter files");
@@ -9855,41 +9875,41 @@ static __init int tracer_init_tracefs(void)
 
 fs_initcall(tracer_init_tracefs);
 
-static int trace_panic_handler(struct notifier_block *this,
-			       unsigned long event, void *unused)
-{
-	if (ftrace_dump_on_oops)
-		ftrace_dump(ftrace_dump_on_oops);
-	return NOTIFY_OK;
-}
+static int trace_die_panic_handler(struct notifier_block *self,
+				unsigned long ev, void *unused);
 
 static struct notifier_block trace_panic_notifier = {
-	.notifier_call  = trace_panic_handler,
-	.next           = NULL,
-	.priority       = 150   /* priority: INT_MAX >= x >= 0 */
+	.notifier_call = trace_die_panic_handler,
+	.priority = INT_MAX - 1,
 };
 
-static int trace_die_handler(struct notifier_block *self,
-			     unsigned long val,
-			     void *data)
-{
-	switch (val) {
-	case DIE_OOPS:
-		if (ftrace_dump_on_oops)
-			ftrace_dump(ftrace_dump_on_oops);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
 static struct notifier_block trace_die_notifier = {
-	.notifier_call = trace_die_handler,
-	.priority = 200
+	.notifier_call = trace_die_panic_handler,
+	.priority = INT_MAX - 1,
 };
 
 /*
+ * The idea is to execute the following die/panic callback early, in order
+ * to avoid showing irrelevant information in the trace (like other panic
+ * notifier functions); we are the 2nd to run, after hung_task/rcu_stall
+ * warnings get disabled (to prevent potential log flooding).
+ */
+static int trace_die_panic_handler(struct notifier_block *self,
+				unsigned long ev, void *unused)
+{
+	if (!ftrace_dump_on_oops)
+		return NOTIFY_DONE;
+
+	/* The die notifier requires DIE_OOPS to trigger */
+	if (self == &trace_die_notifier && ev != DIE_OOPS)
+		return NOTIFY_DONE;
+
+	ftrace_dump(ftrace_dump_on_oops);
+
+	return NOTIFY_DONE;
+}
+
+/*
  * printk is set to max of 1024, we really don't need it that big.
  * Nothing should be printing 1000 characters anyway.
  */
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index d42e24507152..e46a49269be2 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -308,8 +308,7 @@ struct trace_array {
 	struct array_buffer	max_buffer;
 	bool			allocated_snapshot;
 #endif
-#if defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER) \
-	|| defined(CONFIG_OSNOISE_TRACER)
+#ifdef CONFIG_TRACER_MAX_TRACE
 	unsigned long		max_latency;
 #ifdef CONFIG_FSNOTIFY
 	struct dentry		*d_max_latency;
@@ -615,7 +614,7 @@ void trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer,
 bool trace_is_tracepoint_string(const char *str);
 const char *trace_event_format(struct trace_iterator *iter, const char *fmt);
 void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
-			 va_list ap);
+			 va_list ap) __printf(2, 0);
 
 int trace_empty(struct trace_iterator *iter);
 
@@ -688,12 +687,11 @@ void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu,
 		   void *cond_data);
 void update_max_tr_single(struct trace_array *tr,
 			  struct task_struct *tsk, int cpu);
-#endif /* CONFIG_TRACER_MAX_TRACE */
 
-#if (defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER) \
-	|| defined(CONFIG_OSNOISE_TRACER)) && defined(CONFIG_FSNOTIFY)
+#ifdef CONFIG_FSNOTIFY
 #define LATENCY_FS_NOTIFY
 #endif
+#endif /* CONFIG_TRACER_MAX_TRACE */
 
 #ifdef LATENCY_FS_NOTIFY
 void latency_fsnotify(struct trace_array *tr);
@@ -1942,8 +1940,6 @@ static inline void tracer_hardirqs_on(unsigned long a0, unsigned long a1) { }
 static inline void tracer_hardirqs_off(unsigned long a0, unsigned long a1) { }
 #endif
 
-extern struct trace_iterator *tracepoint_print_iter;
-
 /*
  * Reset the state of the trace_iterator so that it can read consumed data.
  * Normally, the trace_iterator is used for reading the data when it is not
@@ -1956,17 +1952,30 @@ static __always_inline void trace_iterator_reset(struct trace_iterator *iter)
 }
 
 /* Check the name is good for event/group/fields */
-static inline bool is_good_name(const char *name)
+static inline bool __is_good_name(const char *name, bool hash_ok)
 {