lkml.org 
[lkml]   [2021]   [Jun]   [17]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 1/3] locking/lockdep: unlikely bfs_error() inside
Date
From: Xiongwei Song <sxwjean@gmail.com>

The error from graph walk is small probability event, and there are some
bfs_error calls during lockdep detection, so unlikely bfs_error inside
can improve performance a little bit.

Suggested-by: Waiman Long <longman@redhat.com>
Signed-off-by: Xiongwei Song <sxwjean@gmail.com>
---
kernel/locking/lockdep.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 7641bd407239..a8a66a2a9bc1 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -1540,7 +1540,7 @@ enum bfs_result {
*/
static inline bool bfs_error(enum bfs_result res)
{
- return res < 0;
+ return unlikely(res < 0);
}

/*
@@ -2089,7 +2089,7 @@ check_path(struct held_lock *target, struct lock_list *src_entry,

ret = __bfs_forwards(src_entry, target, match, skip, target_entry);

- if (unlikely(bfs_error(ret)))
+ if (bfs_error(ret))
print_bfs_bug(ret);

return ret;
@@ -2936,7 +2936,7 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
* in the graph whose neighbours are to be checked.
*/
ret = check_noncircular(next, prev, trace);
- if (unlikely(bfs_error(ret) || ret == BFS_RMATCH))
+ if (bfs_error(ret) || unlikely(ret == BFS_RMATCH))
return 0;

if (!check_irq_usage(curr, prev, next))
--
2.30.2
\
 
 \ /
  Last update: 2021-06-17 16:30    [W:0.062 / U:0.676 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site