From: Waiman Long <longman@redhat.com>
To: Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@redhat.com>, Will Deacon <will.deacon@arm.com>,
Boqun Feng <boqun.feng@gmail.com>
Cc: linux-kernel@vger.kernel.org, Waiman Long <longman@redhat.com>
Subject: [PATCH 2/2] locking/lockdep: Optimize look_up_lock_class()
Date: Tue, 22 Feb 2022 19:20:53 -0500 [thread overview]
Message-ID: <20220223002053.486875-2-longman@redhat.com> (raw)
In-Reply-To: <20220223002053.486875-1-longman@redhat.com>
The lockdep_map structure has a built-in cache for the first two
subclasses. However, when lockdep_init_map_type() is called with a
subclass other than 0, it forces class_cache[0] to hold class for a
non-0 subclass. That messes up the utility of the cache as you never
know if class_cache[0] holds a class for subclass 0.
Use the 1-byte hole in the lockdep_map structure to hold the
subclass information in class_cache[0] so that we can reliably use the
class_cache[] information to get the class based on the given subclass
quicker in look_up_lock_class().
Signed-off-by: Waiman Long <longman@redhat.com>
---
include/linux/lockdep_types.h | 2 +-
kernel/locking/lockdep.c | 19 +++++++++++++++++--
2 files changed, 18 insertions(+), 3 deletions(-)
diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h
index 9c62d274b71e..2c2a19a0b645 100644
--- a/include/linux/lockdep_types.h
+++ b/include/linux/lockdep_types.h
@@ -176,7 +176,7 @@ struct lockdep_map {
u8 wait_type_outer; /* can be taken in this context */
u8 wait_type_inner; /* presents this context */
u8 lock_type;
- /* u8 hole; */
+ u8 cache0_subclass; /* class_cache[0] subclass */
#ifdef CONFIG_LOCK_STAT
int cpu;
unsigned long ip;
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 4a882f83aeb9..0b19d153ffa4 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -881,6 +881,18 @@ look_up_lock_class(const struct lockdep_map *lock, unsigned int subclass)
if (unlikely(!lock->key))
return NULL;
+ /*
+ * Use the class_cache[] to get the class information if available.
+ */
+ if (unlikely(lock->cache0_subclass)) {
+ if (subclass == lock->cache0_subclass)
+ return lock->class_cache[0];
+ } else if (likely(subclass < NR_LOCKDEP_CACHING_CLASSES)) {
+ class = lock->class_cache[subclass];
+ if (class)
+ return class;
+ }
+
/*
* NOTE: the class-key must be unique. For dynamic locks, a static
* lock_class_key variable is passed in through the mutex_init()
@@ -1335,10 +1347,12 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
graph_unlock();
out_set_class_cache:
- if (!subclass || force)
+ if (subclass && force) {
lock->class_cache[0] = class;
- else if (subclass < NR_LOCKDEP_CACHING_CLASSES)
+ lock->cache0_subclass = subclass;
+ } else if (subclass < NR_LOCKDEP_CACHING_CLASSES) {
lock->class_cache[subclass] = class;
+ }
/*
* Hash collision, did we smoke some? We found a class with a matching
@@ -4797,6 +4811,7 @@ void lockdep_init_map_type(struct lockdep_map *lock, const char *name,
lock->wait_type_outer = outer;
lock->wait_type_inner = inner;
lock->lock_type = lock_type;
+ lock->cache0_subclass = 0;
/*
* No key, no joy, we need to hash something.
--
2.27.0
prev parent reply other threads:[~2022-02-23 0:21 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-23 0:20 [PATCH 1/2] locking/lockdep: Remove obsolete generation counter comment in lock_class Waiman Long
2022-02-23 0:20 ` Waiman Long [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220223002053.486875-2-longman@redhat.com \
--to=longman@redhat.com \
--cc=boqun.feng@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=will.deacon@arm.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®