From: Andrii Nakryiko <andrii@kernel.org>
To: linux-trace-kernel@vger.kernel.org, peterz@infradead.org,
oleg@redhat.com
Cc: rostedt@goodmis.org, mhiramat@kernel.org, bpf@vger.kernel.org,
linux-kernel@vger.kernel.org, jolsa@kernel.org,
paulmck@kernel.org, willy@infradead.org, surenb@google.com,
akpm@linux-foundation.org, linux-mm@kvack.org,
Andrii Nakryiko <andrii@kernel.org>
Subject: [PATCH v5 5/8] perf/uprobe: split uprobe_unregister()
Date: Tue, 3 Sep 2024 10:46:00 -0700 [thread overview]
Message-ID: <20240903174603.3554182-6-andrii@kernel.org> (raw)
In-Reply-To: <20240903174603.3554182-1-andrii@kernel.org>
From: Peter Zijlstra <peterz@infradead.org>
With uprobe_unregister() having grown a synchronize_srcu(), it becomes
fairly slow to call. Esp. since both users of this API call it in a
loop.
Peel off the sync_srcu() and do it once, after the loop.
We also need to add uprobe_unregister_sync() into uprobe_register()'s
error handling path, as we need to be careful about returning to the
caller before we have a guarantee that partially attached consumer won't
be called anymore. This is an unlikely slow path and this should be
totally fine to be slow in the case of a failed attach.
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Co-developed-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
---
include/linux/uprobes.h | 8 +++++--
kernel/events/uprobes.c | 21 +++++++++++++------
kernel/trace/bpf_trace.c | 5 ++++-
kernel/trace/trace_uprobe.c | 6 +++++-
.../selftests/bpf/bpf_testmod/bpf_testmod.c | 3 ++-
5 files changed, 32 insertions(+), 11 deletions(-)
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 2785d1bedb74..968230d81798 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -116,7 +116,8 @@ extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs);
extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t);
extern struct uprobe *uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc);
extern int uprobe_apply(struct uprobe *uprobe, struct uprobe_consumer *uc, bool);
-extern void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc);
+extern void uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc);
+extern void uprobe_unregister_sync(void);
extern int uprobe_mmap(struct vm_area_struct *vma);
extern void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end);
extern void uprobe_start_dup_mmap(void);
@@ -165,7 +166,10 @@ uprobe_apply(struct uprobe* uprobe, struct uprobe_consumer *uc, bool add)
return -ENOSYS;
}
static inline void
-uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc)
+uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc)
+{
+}
+static inline void uprobe_unregister_sync(void)
{
}
static inline int uprobe_mmap(struct vm_area_struct *vma)
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 97e58d160647..e9b755ddf960 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1105,11 +1105,11 @@ register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new)
}
/**
- * uprobe_unregister - unregister an already registered probe.
+ * uprobe_unregister_nosync - unregister an already registered probe.
* @uprobe: uprobe to remove
* @uc: identify which probe if multiple probes are colocated.
*/
-void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc)
+void uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc)
{
int err;
@@ -1121,12 +1121,15 @@ void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc)
/* TODO : cant unregister? schedule a worker thread */
if (unlikely(err)) {
uprobe_warn(current, "unregister, leaking uprobe");
- goto out_sync;
+ return;
}
put_uprobe(uprobe);
+}
+EXPORT_SYMBOL_GPL(uprobe_unregister_nosync);
-out_sync:
+void uprobe_unregister_sync(void)
+{
/*
* Now that handler_chain() and handle_uretprobe_chain() iterate over
* uprobe->consumers list under RCU protection without holding
@@ -1138,7 +1141,7 @@ void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc)
*/
synchronize_srcu(&uprobes_srcu);
}
-EXPORT_SYMBOL_GPL(uprobe_unregister);
+EXPORT_SYMBOL_GPL(uprobe_unregister_sync);
/**
* uprobe_register - register a probe
@@ -1196,7 +1199,13 @@ struct uprobe *uprobe_register(struct inode *inode,
up_write(&uprobe->register_rwsem);
if (ret) {
- uprobe_unregister(uprobe, uc);
+ uprobe_unregister_nosync(uprobe, uc);
+ /*
+ * Registration might have partially succeeded, so we can have
+ * this consumer being called right at this time. We need to
+ * sync here. It's ok, it's unlikely slow path.
+ */
+ uprobe_unregister_sync();
return ERR_PTR(ret);
}
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 73c570b5988b..6b632710c98e 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -3184,7 +3184,10 @@ static void bpf_uprobe_unregister(struct bpf_uprobe *uprobes, u32 cnt)
u32 i;
for (i = 0; i < cnt; i++)
- uprobe_unregister(uprobes[i].uprobe, &uprobes[i].consumer);
+ uprobe_unregister_nosync(uprobes[i].uprobe, &uprobes[i].consumer);
+
+ if (cnt)
+ uprobe_unregister_sync();
}
static void bpf_uprobe_multi_link_release(struct bpf_link *link)
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 7eb79e0a5352..f7443e996b1b 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1097,6 +1097,7 @@ static int trace_uprobe_enable(struct trace_uprobe *tu, filter_func_t filter)
static void __probe_event_disable(struct trace_probe *tp)
{
struct trace_uprobe *tu;
+ bool sync = false;
tu = container_of(tp, struct trace_uprobe, tp);
WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter));
@@ -1105,9 +1106,12 @@ static void __probe_event_disable(struct trace_probe *tp)
if (!tu->uprobe)
continue;
- uprobe_unregister(tu->uprobe, &tu->consumer);
+ uprobe_unregister_nosync(tu->uprobe, &tu->consumer);
+ sync = true;
tu->uprobe = NULL;
}
+ if (sync)
+ uprobe_unregister_sync();
}
static int probe_event_enable(struct trace_event_call *call,
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index 3c0515a27842..1fc16657cf42 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -475,7 +475,8 @@ static void testmod_unregister_uprobe(void)
mutex_lock(&testmod_uprobe_mutex);
if (uprobe.uprobe) {
- uprobe_unregister(uprobe.uprobe, &uprobe.consumer);
+ uprobe_unregister_nosync(uprobe.uprobe, &uprobe.consumer);
+ uprobe_unregister_sync();
path_put(&uprobe.path);
uprobe.uprobe = NULL;
}
--
2.43.5
next prev parent reply other threads:[~2024-09-03 17:46 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-09-03 17:45 [PATCH v5 0/8] uprobes: RCU-protected hot path optimizations Andrii Nakryiko
2024-09-03 17:45 ` [PATCH v5 1/8] uprobes: revamp uprobe refcounting and lifetime management Andrii Nakryiko
2024-09-03 17:45 ` [PATCH v5 2/8] uprobes: protected uprobe lifetime with SRCU Andrii Nakryiko
2024-09-03 17:45 ` [PATCH v5 3/8] uprobes: get rid of enum uprobe_filter_ctx in uprobe filter callbacks Andrii Nakryiko
2024-09-03 17:45 ` [PATCH v5 4/8] uprobes: travers uprobe's consumer list locklessly under SRCU protection Andrii Nakryiko
2024-11-06 12:03 ` Breno Leitao
2024-11-06 16:25 ` Andrii Nakryiko
2024-11-07 11:35 ` Breno Leitao
2024-11-07 16:01 ` Andrii Nakryiko
2024-11-07 16:13 ` Paul E. McKenney
2024-09-03 17:46 ` Andrii Nakryiko [this message]
2024-09-03 17:46 ` [PATCH v5 6/8] rbtree: provide rb_find_rcu() / rb_find_add_rcu() Andrii Nakryiko
2024-09-03 17:46 ` [PATCH v5 7/8] uprobes: perform lockless SRCU-protected uprobes_tree lookup Andrii Nakryiko
2024-09-03 17:46 ` [PATCH v5 8/8] uprobes: switch to RCU Tasks Trace flavor for better performance 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=20240903174603.3554182-6-andrii@kernel.org \
--to=andrii@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=bpf@vger.kernel.org \
--cc=jolsa@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-trace-kernel@vger.kernel.org \
--cc=mhiramat@kernel.org \
--cc=oleg@redhat.com \
--cc=paulmck@kernel.org \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=surenb@google.com \
--cc=willy@infradead.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).