linux-kernel - [PATCH RFC bpf-next 7/7] bpf: implement "jmp" mode for trampoline

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20251114092450.172024-8-dongml2@chinatelecom.cn>
Date: Fri, 14 Nov 2025 17:24:50 +0800
From: Menglong Dong <menglong8.dong@...il.com>
To: ast@...nel.org,
	rostedt@...dmis.org
Cc: daniel@...earbox.net,
	john.fastabend@...il.com,
	andrii@...nel.org,
	martin.lau@...ux.dev,
	eddyz87@...il.com,
	song@...nel.org,
	yonghong.song@...ux.dev,
	kpsingh@...nel.org,
	sdf@...ichev.me,
	haoluo@...gle.com,
	jolsa@...nel.org,
	mhiramat@...nel.org,
	mark.rutland@....com,
	mathieu.desnoyers@...icios.com,
	bpf@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	linux-trace-kernel@...r.kernel.org
Subject: [PATCH RFC bpf-next 7/7] bpf: implement "jmp" mode for trampoline

Implement the "jmp" mode for the bpf trampoline. For the ftrace_managed
case, we need only to set the FTRACE_OPS_FL_JMP on the tr->fops if "jmp"
is needed.

For the bpf poke case, the new flag BPF_TRAMP_F_JMPED is introduced to
store and check if the trampoline is in the "jmp" mode.

Signed-off-by: Menglong Dong <dongml2@...natelecom.cn>
---
 include/linux/bpf.h     |  6 +++++
 kernel/bpf/trampoline.c | 53 ++++++++++++++++++++++++++++++++++-------
 2 files changed, 50 insertions(+), 9 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index aec7c65539f5..3598785ac8d1 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1201,6 +1201,12 @@ struct btf_func_model {
  */
 #define BPF_TRAMP_F_INDIRECT		BIT(8)
 
+/*
+ * Indicate that the trampoline is using "jmp" instead of "call". This flag
+ * is only used in the !ftrace_managed case.
+ */
+#define BPF_TRAMP_F_JMPED		BIT(9)
+
 /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50
  * bytes on x86.
  */
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 5949095e51c3..02a9f33d8f6c 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -175,15 +175,37 @@ static struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
 	return tr;
 }
 
-static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr)
+static int bpf_text_poke(struct bpf_trampoline *tr, void *old_addr,
+			 void *new_addr)
 {
+	enum bpf_text_poke_type new_t = BPF_MOD_CALL, old_t = BPF_MOD_CALL;
 	void *ip = tr->func.addr;
 	int ret;
 
+	if (bpf_trampoline_need_jmp(tr->flags))
+		new_t = BPF_MOD_JUMP;
+	if (tr->flags & BPF_TRAMP_F_JMPED)
+		old_t = BPF_MOD_JUMP;
+
+	ret = bpf_arch_text_poke_type(ip, old_t, new_t, old_addr, new_addr);
+	if (!ret) {
+		if (new_t == BPF_MOD_JUMP)
+			tr->flags |= BPF_TRAMP_F_JMPED;
+		else
+			tr->flags &= ~BPF_TRAMP_F_JMPED;
+	}
+
+	return ret;
+}
+
+static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr)
+{
+	int ret;
+
 	if (tr->func.ftrace_managed)
 		ret = unregister_ftrace_direct(tr->fops, (long)old_addr, false);
 	else
-		ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, NULL);
+		ret = bpf_text_poke(tr, old_addr, NULL);
 
 	return ret;
 }
@@ -191,7 +213,6 @@ static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr)
 static int modify_fentry(struct bpf_trampoline *tr, void *old_addr, void *new_addr,
 			 bool lock_direct_mutex)
 {
-	void *ip = tr->func.addr;
 	int ret;
 
 	if (tr->func.ftrace_managed) {
@@ -200,7 +221,7 @@ static int modify_fentry(struct bpf_trampoline *tr, void *old_addr, void *new_ad
 		else
 			ret = modify_ftrace_direct_nolock(tr->fops, (long)new_addr);
 	} else {
-		ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, new_addr);
+		ret = bpf_text_poke(tr, old_addr, new_addr);
 	}
 	return ret;
 }
@@ -223,7 +244,7 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr)
 		ftrace_set_filter_ip(tr->fops, (unsigned long)ip, 0, 1);
 		ret = register_ftrace_direct(tr->fops, (long)new_addr);
 	} else {
-		ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, NULL, new_addr);
+		ret = bpf_text_poke(tr, NULL, new_addr);
 	}
 
 	return ret;
@@ -415,7 +436,8 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
 	}
 
 	/* clear all bits except SHARE_IPMODIFY and TAIL_CALL_CTX */
-	tr->flags &= (BPF_TRAMP_F_SHARE_IPMODIFY | BPF_TRAMP_F_TAIL_CALL_CTX);
+	tr->flags &= (BPF_TRAMP_F_SHARE_IPMODIFY | BPF_TRAMP_F_TAIL_CALL_CTX |
+		      BPF_TRAMP_F_JMPED);
 
 	if (tlinks[BPF_TRAMP_FEXIT].nr_links ||
 	    tlinks[BPF_TRAMP_MODIFY_RETURN].nr_links) {
@@ -432,9 +454,17 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 again:
-	if ((tr->flags & BPF_TRAMP_F_SHARE_IPMODIFY) &&
-	    (tr->flags & BPF_TRAMP_F_CALL_ORIG))
-		tr->flags |= BPF_TRAMP_F_ORIG_STACK;
+	if (tr->flags & BPF_TRAMP_F_CALL_ORIG) {
+		if (tr->flags & BPF_TRAMP_F_SHARE_IPMODIFY) {
+			tr->flags |= BPF_TRAMP_F_ORIG_STACK;
+		} else if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_JMP)) {
+			/* Use "jmp" instead of "call" for the trampoline
+			 * in the origin call case, and we don't need to
+			 * skip the frame.
+			 */
+			tr->flags &= ~BPF_TRAMP_F_SKIP_FRAME;
+		}
+	}
 #endif
 
 	size = arch_bpf_trampoline_size(&tr->func.model, tr->flags,
@@ -465,6 +495,11 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
 	if (err)
 		goto out_free;
 
+	if (bpf_trampoline_need_jmp(tr->flags))
+		tr->fops->flags |= FTRACE_OPS_FL_JMP;
+	else
+		tr->fops->flags &= ~FTRACE_OPS_FL_JMP;
+
 	WARN_ON(tr->cur_image && total == 0);
 	if (tr->cur_image)
 		/* progs already running at this address */
-- 
2.51.2