linux-trace-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
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 09/12] uprobes: batch uprobes_treelock during registration
Date: Mon, 24 Jun 2024 17:21:41 -0700	[thread overview]
Message-ID: <20240625002144.3485799-10-andrii@kernel.org> (raw)
In-Reply-To: <20240625002144.3485799-1-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 5e98e179d47d..416f408cbed9 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -657,7 +657,7 @@ static inline bool uprobe_is_active(struct uprobe *uprobe)
 	return !RB_EMPTY_NODE(&uprobe->rb_node);
 }
 
-static void put_uprobe(struct uprobe *uprobe)
+static void __put_uprobe(struct uprobe *uprobe, bool tree_locked)
 {
 	s64 v;
 
@@ -666,7 +666,8 @@ 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
@@ -689,7 +690,8 @@ 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);
 
 		/* uprobe got resurrected, pretend we never tried to free it */
 		if (!destroy)
@@ -718,6 +720,11 @@ static void put_uprobe(struct uprobe *uprobe)
 		(void)atomic64_cmpxchg(&uprobe->ref, v, v & ~(1ULL << 63));
 }
 
+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)
@@ -817,21 +824,6 @@ 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)
 {
@@ -1291,6 +1283,8 @@ 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;
 
@@ -1298,19 +1292,24 @@ 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);
@@ -1340,12 +1339,14 @@ int uprobe_register_batch(struct inode *inode, int cnt,
 	}
 cleanup_uprobes:
 	/* put all the successfully allocated/reused uprobes */
+	write_lock(&uprobes_treelock);
 	for (i = cnt - 1; i >= 0; i--) {
 		uc = get_uprobe_consumer(i, ctx);
 
-		put_uprobe(uc->uprobe);
+		__put_uprobe(uc->uprobe, true);
 		uc->uprobe = NULL;
 	}
+	write_unlock(&uprobes_treelock);
 	return ret;
 }
 
-- 
2.43.0


  parent reply	other threads:[~2024-06-25  0:22 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-06-25  0:21 [PATCH 00/12] uprobes: add batched register/unregister APIs and per-CPU RW semaphore Andrii Nakryiko
2024-06-25  0:21 ` [PATCH 01/12] uprobes: update outdated comment Andrii Nakryiko
2024-06-25  0:21 ` [PATCH 02/12] uprobes: grab write mmap lock in unapply_uprobe() Andrii Nakryiko
2024-06-25  1:29   ` Masami Hiramatsu
2024-06-25 14:49     ` Oleg Nesterov
2024-06-25 17:37       ` Andrii Nakryiko
2024-06-25 19:07         ` Oleg Nesterov
2024-06-26 16:38           ` Andrii Nakryiko
2024-06-25 10:50   ` Oleg Nesterov
2024-06-25  0:21 ` [PATCH 03/12] uprobes: simplify error handling for alloc_uprobe() Andrii Nakryiko
2024-06-25  0:21 ` [PATCH 04/12] uprobes: revamp uprobe refcounting and lifetime management Andrii Nakryiko
2024-06-25 14:44   ` Oleg Nesterov
2024-06-25 17:30     ` Andrii Nakryiko
2024-06-26  6:02   ` kernel test robot
2024-06-26 16:39     ` Andrii Nakryiko
2024-06-27  2:29   ` Masami Hiramatsu
2024-06-27 16:43     ` Andrii Nakryiko
2024-07-01 21:59       ` Andrii Nakryiko
2024-06-25  0:21 ` [PATCH 05/12] uprobes: move offset and ref_ctr_offset into uprobe_consumer Andrii Nakryiko
2024-06-27  3:06   ` Masami Hiramatsu
2024-06-25  0:21 ` [PATCH 06/12] uprobes: add batch uprobe register/unregister APIs Andrii Nakryiko
2024-06-26 11:27   ` Jiri Olsa
2024-06-26 16:44     ` Andrii Nakryiko
2024-06-27 13:04   ` Masami Hiramatsu
2024-06-27 16:47     ` Andrii Nakryiko
2024-06-28  6:28       ` Masami Hiramatsu
2024-06-28 16:34         ` Andrii Nakryiko
2024-06-29 23:30           ` Masami Hiramatsu
2024-07-01 17:55             ` Andrii Nakryiko
2024-07-01 22:15               ` Andrii Nakryiko
2024-07-02  1:01                 ` Masami Hiramatsu
2024-07-02  1:34                   ` Andrii Nakryiko
2024-07-02 15:19                     ` Masami Hiramatsu
2024-07-02 16:53                       ` Steven Rostedt
2024-07-02 21:23                         ` Andrii Nakryiko
2024-07-02 23:16                         ` Masami Hiramatsu
2024-06-25  0:21 ` [PATCH 07/12] uprobes: inline alloc_uprobe() logic into __uprobe_register() Andrii Nakryiko
2024-06-25  0:21 ` [PATCH 08/12] uprobes: split uprobe allocation and uprobes_tree insertion steps Andrii Nakryiko
2024-06-25  0:21 ` Andrii Nakryiko [this message]
2024-06-25  0:21 ` [PATCH 10/12] uprobes: improve lock batching for uprobe_unregister_batch Andrii Nakryiko
2024-06-25  0:21 ` [PATCH 11/12] uprobes,bpf: switch to batch uprobe APIs for BPF multi-uprobes Andrii Nakryiko
2024-06-25  0:21 ` [PATCH 12/12] uprobes: switch uprobes_treelock to per-CPU RW semaphore 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=20240625002144.3485799-10-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).