From: Andrii Nakryiko <andrii@kernel.org>
To: linux-trace-kernel@vger.kernel.org, rostedt@goodmis.org,
mhiramat@kernel.org, oleg@redhat.com
Cc: peterz@infradead.org, mingo@redhat.com, bpf@vger.kernel.org,
jolsa@kernel.org, paulmck@kernel.org, clm@meta.com,
Andrii Nakryiko <andrii@kernel.org>
Subject: [PATCH v2 09/12] uprobes: batch uprobes_treelock during registration
Date: Mon, 1 Jul 2024 15:39:32 -0700 [thread overview]
Message-ID: <20240701223935.3783951-10-andrii@kernel.org> (raw)
In-Reply-To: <20240701223935.3783951-1-andrii@kernel.org>
Now that we have a good separate of each registration step, take
uprobes_treelock just once for relevant registration step, and then
process all relevant uprobes in one go.
Even if writer lock introduces a relatively large delay (as might happen
with per-CPU RW semaphore), this will keep overall batch attachment
reasonably fast.
We teach put_uprobe(), though __put_uprobe() helper, to optionally take
or not uprobes_treelock, to accommodate this pattern.
With these changes we don't need insert_uprobe() operation that
unconditionally takes uprobes_treelock, so get rid of it, leaving only
lower-level __insert_uprobe() helper.
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
---
kernel/events/uprobes.c | 45 +++++++++++++++++++++--------------------
1 file changed, 23 insertions(+), 22 deletions(-)
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 128677ffe662..ced85284bbf4 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -665,7 +665,7 @@ static void uprobe_free_rcu(struct rcu_head *rcu)
kfree(uprobe);
}
-static void put_uprobe(struct uprobe *uprobe)
+static void __put_uprobe(struct uprobe *uprobe, bool tree_locked)
{
s64 v;
@@ -683,7 +683,8 @@ static void put_uprobe(struct uprobe *uprobe)
if (unlikely((u32)v == 0)) {
bool destroy;
- write_lock(&uprobes_treelock);
+ if (!tree_locked)
+ write_lock(&uprobes_treelock);
/*
* We might race with find_uprobe()->__get_uprobe() executed
* from inside read-locked uprobes_treelock, which can bump
@@ -706,7 +707,8 @@ static void put_uprobe(struct uprobe *uprobe)
destroy = atomic64_read(&uprobe->ref) == v;
if (destroy && uprobe_is_active(uprobe))
rb_erase(&uprobe->rb_node, &uprobes_tree);
- write_unlock(&uprobes_treelock);
+ if (!tree_locked)
+ write_unlock(&uprobes_treelock);
/*
* Beyond here we don't need RCU protection, we are either the
@@ -745,6 +747,11 @@ static void put_uprobe(struct uprobe *uprobe)
rcu_read_unlock_trace();
}
+static void put_uprobe(struct uprobe *uprobe)
+{
+ __put_uprobe(uprobe, false);
+}
+
static __always_inline
int uprobe_cmp(const struct inode *l_inode, const loff_t l_offset,
const struct uprobe *r)
@@ -844,21 +851,6 @@ static struct uprobe *__insert_uprobe(struct uprobe *uprobe)
return u;
}
-/*
- * Acquire uprobes_treelock and insert uprobe into uprobes_tree
- * (or reuse existing one, see __insert_uprobe() comments above).
- */
-static struct uprobe *insert_uprobe(struct uprobe *uprobe)
-{
- struct uprobe *u;
-
- write_lock(&uprobes_treelock);
- u = __insert_uprobe(uprobe);
- write_unlock(&uprobes_treelock);
-
- return u;
-}
-
static void
ref_ctr_mismatch_warn(struct uprobe *cur_uprobe, struct uprobe *uprobe)
{
@@ -1318,6 +1310,8 @@ int uprobe_register_batch(struct inode *inode, int cnt,
uc->uprobe = uprobe;
}
+ ret = 0;
+ write_lock(&uprobes_treelock);
for (i = 0; i < cnt; i++) {
struct uprobe *cur_uprobe;
@@ -1325,19 +1319,24 @@ int uprobe_register_batch(struct inode *inode, int cnt,
uprobe = uc->uprobe;
/* add to uprobes_tree, sorted on inode:offset */
- cur_uprobe = insert_uprobe(uprobe);
+ cur_uprobe = __insert_uprobe(uprobe);
/* a uprobe exists for this inode:offset combination */
if (cur_uprobe != uprobe) {
if (cur_uprobe->ref_ctr_offset != uprobe->ref_ctr_offset) {
ref_ctr_mismatch_warn(cur_uprobe, uprobe);
- put_uprobe(cur_uprobe);
+
+ __put_uprobe(cur_uprobe, true);
ret = -EINVAL;
- goto cleanup_uprobes;
+ goto unlock_treelock;
}
kfree(uprobe);
uc->uprobe = cur_uprobe;
}
}
+unlock_treelock:
+ write_unlock(&uprobes_treelock);
+ if (ret)
+ goto cleanup_uprobes;
for (i = 0; i < cnt; i++) {
uc = get_uprobe_consumer(i, ctx);
@@ -1367,13 +1366,15 @@ int uprobe_register_batch(struct inode *inode, int cnt,
}
cleanup_uprobes:
/* put all the successfully allocated/reused uprobes */
+ write_lock(&uprobes_treelock);
for (i = 0; i < cnt; i++) {
uc = get_uprobe_consumer(i, ctx);
if (uc->uprobe)
- put_uprobe(uc->uprobe);
+ __put_uprobe(uc->uprobe, true);
uc->uprobe = NULL;
}
+ write_unlock(&uprobes_treelock);
return ret;
}
--
2.43.0
next prev parent reply other threads:[~2024-07-01 22:40 UTC|newest]
Thread overview: 67+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-07-01 22:39 [PATCH v2 00/12] uprobes: add batched register/unregister APIs and per-CPU RW semaphore Andrii Nakryiko
2024-07-01 22:39 ` [PATCH v2 01/12] uprobes: update outdated comment Andrii Nakryiko
2024-07-03 11:38 ` Oleg Nesterov
2024-07-03 18:24 ` Andrii Nakryiko
2024-07-03 21:51 ` Andrii Nakryiko
2024-07-10 13:31 ` Oleg Nesterov
2024-07-10 15:14 ` Andrii Nakryiko
2024-07-01 22:39 ` [PATCH v2 02/12] uprobes: correct mmap_sem locking assumptions in uprobe_write_opcode() Andrii Nakryiko
2024-07-03 11:41 ` Oleg Nesterov
2024-07-03 13:15 ` Masami Hiramatsu
2024-07-03 18:25 ` Andrii Nakryiko
2024-07-03 21:47 ` Masami Hiramatsu
2024-07-01 22:39 ` [PATCH v2 03/12] uprobes: simplify error handling for alloc_uprobe() Andrii Nakryiko
2024-07-01 22:39 ` [PATCH v2 04/12] uprobes: revamp uprobe refcounting and lifetime management Andrii Nakryiko
2024-07-02 10:22 ` Peter Zijlstra
2024-07-02 17:54 ` Andrii Nakryiko
2024-07-03 13:36 ` Peter Zijlstra
2024-07-03 20:47 ` Andrii Nakryiko
2024-07-04 8:03 ` Peter Zijlstra
2024-07-04 8:45 ` Peter Zijlstra
2024-07-04 14:40 ` Masami Hiramatsu
2024-07-04 8:31 ` Peter Zijlstra
2024-07-05 15:37 ` Oleg Nesterov
2024-07-06 17:00 ` Jiri Olsa
2024-07-06 17:05 ` Jiri Olsa
2024-07-07 14:46 ` Oleg Nesterov
2024-07-08 17:47 ` Andrii Nakryiko
2024-07-09 18:47 ` Oleg Nesterov
2024-07-09 20:59 ` Andrii Nakryiko
2024-07-09 21:31 ` Oleg Nesterov
2024-07-09 21:45 ` Andrii Nakryiko
2024-07-08 17:47 ` Andrii Nakryiko
2024-07-01 22:39 ` [PATCH v2 05/12] uprobes: move offset and ref_ctr_offset into uprobe_consumer Andrii Nakryiko
2024-07-03 8:13 ` Peter Zijlstra
2024-07-03 10:13 ` Masami Hiramatsu
2024-07-03 18:23 ` Andrii Nakryiko
2024-07-07 12:48 ` Oleg Nesterov
2024-07-08 17:56 ` Andrii Nakryiko
2024-07-01 22:39 ` [PATCH v2 06/12] uprobes: add batch uprobe register/unregister APIs Andrii Nakryiko
2024-07-01 22:39 ` [PATCH v2 07/12] uprobes: inline alloc_uprobe() logic into __uprobe_register() Andrii Nakryiko
2024-07-01 22:39 ` [PATCH v2 08/12] uprobes: split uprobe allocation and uprobes_tree insertion steps Andrii Nakryiko
2024-07-01 22:39 ` Andrii Nakryiko [this message]
2024-07-01 22:39 ` [PATCH v2 10/12] uprobes: improve lock batching for uprobe_unregister_batch Andrii Nakryiko
2024-07-01 22:39 ` [PATCH v2 11/12] uprobes,bpf: switch to batch uprobe APIs for BPF multi-uprobes Andrii Nakryiko
2024-07-01 22:39 ` [PATCH v2 12/12] uprobes: switch uprobes_treelock to per-CPU RW semaphore Andrii Nakryiko
2024-07-02 10:23 ` [PATCH v2 00/12] uprobes: add batched register/unregister APIs and " Peter Zijlstra
2024-07-02 11:54 ` Peter Zijlstra
2024-07-02 12:01 ` Peter Zijlstra
2024-07-02 17:54 ` Andrii Nakryiko
2024-07-02 19:18 ` Peter Zijlstra
2024-07-02 23:56 ` Paul E. McKenney
2024-07-03 4:54 ` Andrii Nakryiko
2024-07-03 7:50 ` Peter Zijlstra
2024-07-03 14:08 ` Paul E. McKenney
2024-07-04 8:39 ` Peter Zijlstra
2024-07-04 15:13 ` Paul E. McKenney
2024-07-03 21:57 ` Steven Rostedt
2024-07-03 22:07 ` Paul E. McKenney
2024-07-03 4:47 ` Andrii Nakryiko
2024-07-03 8:07 ` Peter Zijlstra
2024-07-03 20:55 ` Andrii Nakryiko
2024-07-03 21:33 ` Andrii Nakryiko
2024-07-04 9:15 ` Peter Zijlstra
2024-07-04 13:56 ` Steven Rostedt
2024-07-04 15:44 ` Paul E. McKenney
2024-07-08 17:47 ` Andrii Nakryiko
2024-07-08 17:48 ` Andrii Nakryiko
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=20240701223935.3783951-10-andrii@kernel.org \
--to=andrii@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=clm@meta.com \
--cc=jolsa@kernel.org \
--cc=linux-trace-kernel@vger.kernel.org \
--cc=mhiramat@kernel.org \
--cc=mingo@redhat.com \
--cc=oleg@redhat.com \
--cc=paulmck@kernel.org \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
/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;
as well as URLs for NNTP newsgroup(s).