Merge branch 'dynamic_sg' into rdma.git for-next

From Maor Gottlieb says:

====================
This series extends __sg_alloc_table_from_pages to allow chaining of new
pages to an already initialized SG table.

This allows for drivers to utilize the optimization of merging contiguous
pages without a need to pre allocate all the pages and hold them in a very
large temporary buffer prior to the call to SG table initialization.

The last patch changes the Infiniband core to use the new API. It removes
duplicate functionality from the code and benefits from the optimization
of allocating dynamic SG table from pages.

In huge pages system of 2MB page size, without this change, the SG table
would contain x512 SG entries.
====================

* branch 'dynamic_sg':
  RDMA/umem: Move to allocate SG table from pages
  lib/scatterlist: Add support in dynamic allocation of SG table from pages
  tools/testing/scatterlist: Show errors in human readable form
  tools/testing/scatterlist: Rejuvenate bit-rotten test

17 files changed, 130 insertions, 66 deletions

diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 78dfff6a501b..7df28a45c66b 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -1622,7 +1622,6 @@ struct bpf_iter_seq_hash_map_info {
 	struct bpf_map *map;
 	struct bpf_htab *htab;
 	void *percpu_value_buf; // non-zero means percpu hash
-	unsigned long flags;
 	u32 bucket_id;
 	u32 skip_elems;
 };
@@ -1632,7 +1631,6 @@ bpf_hash_map_seq_find_next(struct bpf_iter_seq_hash_map_info *info,
 			   struct htab_elem *prev_elem)
 {
 	const struct bpf_htab *htab = info->htab;
-	unsigned long flags = info->flags;
 	u32 skip_elems = info->skip_elems;
 	u32 bucket_id = info->bucket_id;
 	struct hlist_nulls_head *head;
@@ -1656,19 +1654,18 @@ bpf_hash_map_seq_find_next(struct bpf_iter_seq_hash_map_info *info,
 
 		/* not found, unlock and go to the next bucket */
 		b = &htab->buckets[bucket_id++];
-		htab_unlock_bucket(htab, b, flags);
+		rcu_read_unlock();
 		skip_elems = 0;
 	}
 
 	for (i = bucket_id; i < htab->n_buckets; i++) {
 		b = &htab->buckets[i];
-		flags = htab_lock_bucket(htab, b);
+		rcu_read_lock();
 
 		count = 0;
 		head = &b->head;
 		hlist_nulls_for_each_entry_rcu(elem, n, head, hash_node) {
 			if (count >= skip_elems) {
-				info->flags = flags;
 				info->bucket_id = i;
 				info->skip_elems = count;
 				return elem;
@@ -1676,7 +1673,7 @@ bpf_hash_map_seq_find_next(struct bpf_iter_seq_hash_map_info *info,
 			count++;
 		}
 
-		htab_unlock_bucket(htab, b, flags);
+		rcu_read_unlock();
 		skip_elems = 0;
 	}
 
@@ -1754,14 +1751,10 @@ static int bpf_hash_map_seq_show(struct seq_file *seq, void *v)
 
 static void bpf_hash_map_seq_stop(struct seq_file *seq, void *v)
 {
-	struct bpf_iter_seq_hash_map_info *info = seq->private;
-
 	if (!v)
 		(void)__bpf_hash_map_seq_show(seq, NULL);
 	else
-		htab_unlock_bucket(info->htab,
-				   &info->htab->buckets[info->bucket_id],
-				   info->flags);
+		rcu_read_unlock();
 }
 
 static int bpf_iter_init_hash_map(void *priv_data,
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index fb878ba3f22f..18f4969552ac 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -226,10 +226,12 @@ static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos)
 	else
 		prev_key = key;
 
+	rcu_read_lock();
 	if (map->ops->map_get_next_key(map, prev_key, key)) {
 		map_iter(m)->done = true;
-		return NULL;
+		key = NULL;
 	}
+	rcu_read_unlock();
 	return key;
 }
 
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 18683598edbc..6fdb6105e6d6 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -60,13 +60,15 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall,
 			return ret;
 	}
 
+	/* Either of the above might have changed the syscall number */
+	syscall = syscall_get_nr(current, regs);
+
 	if (unlikely(ti_work & _TIF_SYSCALL_TRACEPOINT))
 		trace_sys_enter(regs, syscall);
 
 	syscall_enter_audit(regs, syscall);
 
-	/* The above might have changed the syscall number */
-	return ret ? : syscall_get_nr(current, regs);
+	return ret ? : syscall;
 }
 
 static __always_inline long
diff --git a/kernel/fork.c b/kernel/fork.c
index 49677d668de4..da8d360fb032 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -589,7 +589,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 
 		mm->map_count++;
 		if (!(tmp->vm_flags & VM_WIPEONFORK))
-			retval = copy_page_range(mm, oldmm, mpnt);
+			retval = copy_page_range(mm, oldmm, mpnt, tmp);
 
 		if (tmp->vm_ops && tmp->vm_ops->open)
 			tmp->vm_ops->open(tmp);
@@ -1011,6 +1011,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	mm_pgtables_bytes_init(mm);
 	mm->map_count = 0;
 	mm->locked_vm = 0;
+	atomic_set(&mm->has_pinned, 0);
 	atomic64_set(&mm->pinned_vm, 0);
 	memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
 	spin_lock_init(&mm->page_table_lock);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 287b263c9cb9..e995541d277d 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2140,6 +2140,9 @@ static void kill_kprobe(struct kprobe *p)
 
 	lockdep_assert_held(&kprobe_mutex);
 
+	if (WARN_ON_ONCE(kprobe_gone(p)))
+		return;
+
 	p->flags |= KPROBE_FLAG_GONE;
 	if (kprobe_aggrprobe(p)) {
 		/*
@@ -2159,9 +2162,10 @@ static void kill_kprobe(struct kprobe *p)
 
 	/*
 	 * The module is going away. We should disarm the kprobe which
-	 * is using ftrace.
+	 * is using ftrace, because ftrace framework is still available at
+	 * MODULE_STATE_GOING notification.
 	 */
-	if (kprobe_ftrace(p))
+	if (kprobe_ftrace(p) && !kprobe_disabled(p) && !kprobes_all_disarmed)
 		disarm_kprobe_ftrace(p);
 }
 
@@ -2419,7 +2423,10 @@ static int kprobes_module_callback(struct notifier_block *nb,
 	mutex_lock(&kprobe_mutex);
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
-		hlist_for_each_entry(p, head, hlist)
+		hlist_for_each_entry(p, head, hlist) {
+			if (kprobe_gone(p))
+				continue;
+
 			if (within_module_init((unsigned long)p->addr, mod) ||
 			    (checkcore &&
 			     within_module_core((unsigned long)p->addr, mod))) {
@@ -2436,6 +2443,7 @@ static int kprobes_module_callback(struct notifier_block *nb,
 				 */
 				kill_kprobe(p);
 			}
+		}
 	}
 	if (val == MODULE_STATE_GOING)
 		remove_module_kprobe_blacklist(mod);
@@ -2452,6 +2460,28 @@ static struct notifier_block kprobe_module_nb = {
 extern unsigned long __start_kprobe_blacklist[];
 extern unsigned long __stop_kprobe_blacklist[];
 
+void kprobe_free_init_mem(void)
+{
+	void *start = (void *)(&__init_begin);
+	void *end = (void *)(&__init_end);
+	struct hlist_head *head;
+	struct kprobe *p;
+	int i;
+
+	mutex_lock(&kprobe_mutex);
+
+	/* Kill all kprobes on initmem */
+	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
+		head = &kprobe_table[i];
+		hlist_for_each_entry(p, head, hlist) {
+			if (start <= (void *)p->addr && (void *)p->addr < end)
+				kill_kprobe(p);
+		}
+	}
+
+	mutex_unlock(&kprobe_mutex);
+}
+
 static int __init init_kprobes(void)
 {
 	int i, err = 0;
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 54b74fabf40c..2facbbd146ec 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3969,13 +3969,18 @@ static int separate_irq_context(struct task_struct *curr,
 static int mark_lock(struct task_struct *curr, struct held_lock *this,
 			     enum lock_usage_bit new_bit)
 {
-	unsigned int new_mask = 1 << new_bit, ret = 1;
+	unsigned int old_mask, new_mask, ret = 1;
 
 	if (new_bit >= LOCK_USAGE_STATES) {
 		DEBUG_LOCKS_WARN_ON(1);
 		return 0;
 	}
 
+	if (new_bit == LOCK_USED && this->read)
+		new_bit = LOCK_USED_READ;
+
+	new_mask = 1 << new_bit;
+
 	/*
 	 * If already set then do not dirty the cacheline,
 	 * nor do any checks:
@@ -3988,13 +3993,22 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 	/*
 	 * Make sure we didn't race:
 	 */
-	if (unlikely(hlock_class(this)->usage_mask & new_mask)) {
-		graph_unlock();
-		return 1;
-	}
+	if (unlikely(hlock_class(this)->usage_mask & new_mask))
+		goto unlock;
 
+	old_mask = hlock_class(this)->usage_mask;
 	hlock_class(this)->usage_mask |= new_mask;
 
+	/*
+	 * Save one usage_traces[] entry and map both LOCK_USED and
+	 * LOCK_USED_READ onto the same entry.
+	 */
+	if (new_bit == LOCK_USED || new_bit == LOCK_USED_READ) {
+		if (old_mask & (LOCKF_USED | LOCKF_USED_READ))
+			goto unlock;
+		new_bit = LOCK_USED;
+	}
+
 	if (!(hlock_class(this)->usage_traces[new_bit] = save_trace()))
 		return 0;
 
@@ -4008,6 +4022,7 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 			return 0;
 	}
 
+unlock:
 	graph_unlock();
 
 	/*
@@ -4942,12 +4957,20 @@ static void verify_lock_unused(struct lockdep_map *lock, struct held_lock *hlock
 {
 #ifdef CONFIG_PROVE_LOCKING
 	struct lock_class *class = look_up_lock_class(lock, subclass);
+	unsigned long mask = LOCKF_USED;
 
 	/* if it doesn't have a class (yet), it certainly hasn't been used yet */
 	if (!class)
 		return;
 
-	if (!(class->usage_mask & LOCK_USED))
+	/*
+	 * READ locks only conflict with USED, such that if we only ever use
+	 * READ locks, there is no deadlock possible -- RCU.
+	 */
+	if (!hlock->read)
+		mask |= LOCKF_USED_READ;
+
+	if (!(class->usage_mask & mask))
 		return;
 
 	hlock->class_idx = class - lock_classes;
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index baca699b94e9..b0be1560ed17 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -19,6 +19,7 @@ enum lock_usage_bit {
 #include "lockdep_states.h"
 #undef LOCKDEP_STATE
 	LOCK_USED,
+	LOCK_USED_READ,
 	LOCK_USAGE_STATES
 };
 
@@ -40,6 +41,7 @@ enum {
 #include "lockdep_states.h"
 #undef LOCKDEP_STATE
 	__LOCKF(USED)
+	__LOCKF(USED_READ)
 };
 
 #define LOCKDEP_STATE(__STATE)	LOCKF_ENABLED_##__STATE |
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index 8bbafe3e5203..70a32a576f3f 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -45,7 +45,7 @@ EXPORT_SYMBOL_GPL(percpu_free_rwsem);
 
 static bool __percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
 {
-	__this_cpu_inc(*sem->read_count);
+	this_cpu_inc(*sem->read_count);
 
 	/*
 	 * Due to having preemption disabled the decrement happens on
@@ -71,7 +71,7 @@ static bool __percpu_down_read_trylock(struct percpu_rw_semaphore *sem)
 	if (likely(!atomic_read_acquire(&sem->block)))
 		return true;
 
-	__this_cpu_dec(*sem->read_count);
+	this_cpu_dec(*sem->read_count);
 
 	/* Prod writer to re-evaluate readers_active_check() */
 	rcuwait_wake_up(&sem->writer);
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 835e2df8590a..05d3e1375e4c 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -590,7 +590,7 @@ void exit_tasks_rcu_finish(void) __releases(&tasks_rcu_exit_srcu)
 }
 
 #else /* #ifdef CONFIG_TASKS_RCU */
-static void show_rcu_tasks_classic_gp_kthread(void) { }
+static inline void show_rcu_tasks_classic_gp_kthread(void) { }
 void exit_tasks_rcu_start(void) { }
 void exit_tasks_rcu_finish(void) { exit_tasks_rcu_finish_trace(current); }
 #endif /* #else #ifdef CONFIG_TASKS_RCU */
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 8ce77d9ac716..f78ee759af9c 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -673,6 +673,7 @@ void rcu_idle_enter(void)
 	lockdep_assert_irqs_disabled();
 	rcu_eqs_enter(false);
 }
+EXPORT_SYMBOL_GPL(rcu_idle_enter);
 
 #ifdef CONFIG_NO_HZ_FULL
 /**
@@ -886,6 +887,7 @@ void rcu_idle_exit(void)
 	rcu_eqs_exit(false);
 	local_irq_restore(flags);
 }
+EXPORT_SYMBOL_GPL(rcu_idle_exit);
 
 #ifdef CONFIG_NO_HZ_FULL
 /**
diff --git a/kernel/stackleak.c b/kernel/stackleak.c
index a8fc9ae1d03d..ce161a8e8d97 100644
--- a/kernel/stackleak.c
+++ b/kernel/stackleak.c
@@ -20,7 +20,7 @@
 static DEFINE_STATIC_KEY_FALSE(stack_erasing_bypass);
 
 int stack_erasing_sysctl(struct ctl_table *table, int write,
-			void __user *buffer, size_t *lenp, loff_t *ppos)
+			void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret = 0;
 	int state = !static_branch_unlikely(&stack_erasing_bypass);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 09e70ee2332e..afad085960b8 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2912,6 +2912,14 @@ static struct ctl_table vm_table[] = {
 		.proc_handler	= percpu_pagelist_fraction_sysctl_handler,
 		.extra1		= SYSCTL_ZERO,
 	},
+	{
+		.procname	= "page_lock_unfairness",
+		.data		= &sysctl_page_lock_unfairness,
+		.maxlen		= sizeof(sysctl_page_lock_unfairness),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+	},
 #ifdef CONFIG_MMU
 	{
 		.procname	= "max_map_count",
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 275441254bb5..541453927c82 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2782,6 +2782,7 @@ static void ftrace_remove_trampoline_from_kallsyms(struct ftrace_ops *ops)
 {
 	lockdep_assert_held(&ftrace_lock);
 	list_del_rcu(&ops->list);
+	synchronize_rcu();
 }
 
 /*
@@ -2862,6 +2863,8 @@ int ftrace_startup(struct ftrace_ops *ops, int command)
 		__unregister_ftrace_function(ops);
 		ftrace_start_up--;
 		ops->flags &= ~FTRACE_OPS_FL_ENABLED;
+		if (ops->flags & FTRACE_OPS_FL_DYNAMIC)
+			ftrace_trampoline_free(ops);
 		return ret;
 	}
 
@@ -6990,16 +6993,14 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip,
 {
 	int bit;
 
-	if ((op->flags & FTRACE_OPS_FL_RCU) && !rcu_is_watching())
-		return;
-
 	bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX);
 	if (bit < 0)
 		return;
 
 	preempt_disable_notrace();
 
-	op->func(ip, parent_ip, op, regs);
+	if (!(op->flags & FTRACE_OPS_FL_RCU) || rcu_is_watching())
+		op->func(ip, parent_ip, op, regs);
 
 	preempt_enable_notrace();
 	trace_clear_recursion(bit);
@@ -7531,8 +7532,7 @@ static bool is_permanent_ops_registered(void)
 
 int
 ftrace_enable_sysctl(struct ctl_table *table, int write,
-		     void __user *buffer, size_t *lenp,
-		     loff_t *ppos)
+		     void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret = -ENODEV;
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f40d850ebabc..d3e5de717df2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3546,13 +3546,15 @@ struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
 	if (iter->ent && iter->ent != iter->temp) {
 		if ((!iter->temp || iter->temp_size < iter->ent_size) &&
 		    !WARN_ON_ONCE(iter->temp == static_temp_buf)) {
-			kfree(iter->temp);
-			iter->temp = kmalloc(iter->ent_size, GFP_KERNEL);
-			if (!iter->temp)
+			void *temp;
+			temp = kmalloc(iter->ent_size, GFP_KERNEL);
+			if (!temp)
 				return NULL;
+			kfree(iter->temp);
+			iter->temp = temp;
+			iter->temp_size = iter->ent_size;
 		}
 		memcpy(iter->temp, iter->ent, iter->ent_size);
-		iter->temp_size = iter->ent_size;
 		iter->ent = iter->temp;
 	}
 	entry = __find_next_entry(iter, ent_cpu, NULL, ent_ts);
@@ -3782,14 +3784,14 @@ unsigned long trace_total_entries(struct trace_array *tr)
 
 static void print_lat_help_header(struct seq_file *m)
 {
-	seq_puts(m, "#                  _------=> CPU#            \n"
-		    "#                 / _-----=> irqs-off        \n"
-		    "#                | / _----=> need-resched    \n"
-		    "#                || / _---=> hardirq/softirq \n"
-		    "#                ||| / _--=> preempt-depth   \n"
-		    "#                |||| /     delay            \n"
-		    "#  cmd     pid   ||||| time  |   caller      \n"
-		    "#     \\   /      |||||  \\    |   /         \n");
+	seq_puts(m, "#                    _------=> CPU#            \n"
+		    "#                   / _-----=> irqs-off        \n"
+		    "#                  | / _----=> need-resched    \n"
+		    "#                  || / _---=> hardirq/softirq \n"
+		    "#                  ||| / _--=> preempt-depth   \n"
+		    "#                  |||| /     delay            \n"
+		    "#  cmd     pid     ||||| time  |   caller      \n"
+		    "#     \\   /        |||||  \\    |   /         \n");
 }
 
 static void print_event_info(struct array_buffer *buf, struct seq_file *m)
@@ -3810,26 +3812,26 @@ static void print_func_help_header(struct array_buffer *buf, struct seq_file *m,
 
 	print_event_info(buf, m);
 
-	seq_printf(m, "#           TASK-PID   %s  CPU#   TIMESTAMP  FUNCTION\n", tgid ? "TGID     " : "");
-	seq_printf(m, "#              | |     %s    |       |         |\n",	 tgid ? "  |      " : "");
+	seq_printf(m, "#           TASK-PID    %s CPU#     TIMESTAMP  FUNCTION\n", tgid ? "   TGID   " : "");
+	seq_printf(m, "#              | |      %s   |         |         |\n",      tgid ? "     |    " : "");
 }
 
 static void print_func_help_header_irq(struct array_buffer *buf, struct seq_file *m,
 				       unsigned int flags)
 {
 	bool tgid = flags & TRACE_ITER_RECORD_TGID;
-	const char *space = "          ";
-	int prec = tgid ? 10 : 2;
+	const char *space = "            ";
+	int prec = tgid ? 12 : 2;
 
 	print_event_info(buf, m);
 
-	seq_printf(m, "#                          %.*s  _-----=> irqs-off\n", prec, space);
-	seq_printf(m, "#                          %.*s / _----=> need-resched\n", prec, space);
-	seq_printf(m, "#                          %.*s| / _---=> hardirq/softirq\n", prec, space);
-	seq_printf(m, "#                          %.*s|| / _--=> preempt-depth\n", prec, space);
-	seq_printf(m, "#                          %.*s||| /     delay\n", prec, space);
-	seq_printf(m, "#           TASK-PID %.*sCPU#  ||||    TIMESTAMP  FUNCTION\n", prec, "   TGID   ");
-	seq_printf(m, "#              | |   %.*s  |   ||||       |         |\n", prec, "     |    ");
+	seq_printf(m, "#                            %.*s  _-----=> irqs-off\n", prec, space);
+	seq_printf(m, "#                            %.*s / _----=> need-resched\n", prec, space);
+	seq_printf(m, "#                            %.*s| / _---=> hardirq/softirq\n", prec, space);
+	seq_printf(m, "#                            %.*s|| / _--=> preempt-depth\n", prec, space);
+	seq_printf(m, "#                            %.*s||| /     delay\n", prec, space);
+	seq_printf(m, "#           TASK-PID  %.*s CPU#  ||||   TIMESTAMP  FUNCTION\n", prec, "     TGID   ");
+	seq_printf(m, "#              | |    %.*s   |   ||||      |         |\n", prec, "       |    ");
 }
 
 void
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 0b933546142e..1b2ef6490229 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -3865,7 +3865,6 @@ static int parse_var_defs(struct hist_trigger_data *hist_data)
 
 			s = kstrdup(field_str, GFP_KERNEL);
 			if (!s) {
-				kfree(hist_data->attrs->var_defs.name[n_vars]);
 				ret = -ENOMEM;
 				goto free;
 			}
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 4d1893564912..000e9dc224c6 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -497,7 +497,7 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
 
 	trace_find_cmdline(entry->pid, comm);
 
-	trace_seq_printf(s, "%8.8s-%-5d %3d",
+	trace_seq_printf(s, "%8.8s-%-7d %3d",
 			 comm, entry->pid, cpu);
 
 	return trace_print_lat_fmt(s, entry);
@@ -588,15 +588,15 @@ int trace_print_context(struct trace_iterator *iter)
 
 	trace_find_cmdline(entry->pid, comm);
 
-	trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid);
+	trace_seq_printf(s, "%16s-%-7d ", comm, entry->pid);
 
 	if (tr->trace_flags & TRACE_ITER_RECORD_TGID) {
 		unsigned int tgid = trace_find_tgid(entry->pid);
 
 		if (!tgid)
-			trace_seq_printf(s, "(-----) ");
+			trace_seq_printf(s, "(-------) ");
 		else
-			trace_seq_printf(s, "(%5d) ", tgid);
+			trace_seq_printf(s, "(%7d) ", tgid);
 	}
 
 	trace_seq_printf(s, "[%03d] ", iter->cpu);
@@ -636,7 +636,7 @@ int trace_print_lat_context(struct trace_iterator *iter)
 		trace_find_cmdline(entry->pid, comm);
 
 		trace_seq_printf(
-			s, "%16s %5d %3d %d %08x %08lx ",
+			s, "%16s %7d %3d %d %08x %08lx ",
 			comm, entry->pid, iter->cpu, entry->flags,
 			entry->preempt_count, iter->idx);
 	} else {
@@ -917,7 +917,7 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter,
 	S = task_index_to_char(field->prev_state);
 	trace_find_cmdline(field->next_pid, comm);
 	trace_seq_printf(&iter->seq,
-			 " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n",
+			 " %7d:%3d:%c %s [%03d] %7d:%3d:%c %s\n",
 			 field->prev_pid,
 			 field->prev_prio,
 			 S, delim,
diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c
index f10073e62603..f4938040c228 100644
--- a/kernel/trace/trace_preemptirq.c
+++ b/kernel/trace/trace_preemptirq.c
@@ -102,14 +102,14 @@ NOKPROBE_SYMBOL(trace_hardirqs_on_caller);
 
 __visible void trace_hardirqs_off_caller(unsigned long caller_addr)
 {
+	lockdep_hardirqs_off(CALLER_ADDR0);
+
 	if (!this_cpu_read(tracing_irq_cpu)) {
 		this_cpu_write(tracing_irq_cpu, 1);
 		tracer_hardirqs_off(CALLER_ADDR0, caller_addr);
 		if (!in_nmi())
 			trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr);
 	}
-
-	lockdep_hardirqs_off(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_off_caller);
 NOKPROBE_SYMBOL(trace_hardirqs_off_caller);