From nobody Thu Dec 18 18:04:43 2025 Received: from SHSQR01.spreadtrum.com (unknown [222.66.158.135]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id DEF981C291 for ; Tue, 30 Apr 2024 07:15:36 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=222.66.158.135 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1714461340; cv=none; b=M7XAaDVqy+7xyeJcYdQTmLD/J30fqqyiCzCpH+qkUK/6SHI5Eia4e+LwkiWPiHsarHHLXRs1Eso487u+hGOSez3LzcxOb7fiVyePMvch3DzyHvQnwpFw01YcQxDyG/G3zTMOeelttGFdtpPwDkTa5GKxuRY7FFt5fTujdDyPmtk= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1714461340; c=relaxed/simple; bh=vpiLrtoA8Clxum6XMseE7kszP5lb19KSUPU8G9SIgN0=; h=From:To:CC:Subject:Date:Message-ID:References:In-Reply-To: Content-Type:MIME-Version; b=QU+QukAA3aYum6mnkKL8Roeez2xDvJEGVJuALj2SIKM5/qRN1uSg2FiPv9vheONQh1u3mwmRyrs2Q3v3hgQrTNIXgFf2bxfR2PTHAELBK2HOuA3+UEZTeRuMakkpvyxcwgVwl4JR3E1znE7mFpZGLWahzHHB43bAisJIvIALUNg= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=unisoc.com; spf=pass smtp.mailfrom=unisoc.com; arc=none smtp.client-ip=222.66.158.135 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=unisoc.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=unisoc.com Received: from dlp.unisoc.com ([10.29.3.86]) by SHSQR01.spreadtrum.com with ESMTP id 43U7FCBV023552; Tue, 30 Apr 2024 15:15:12 +0800 (+08) (envelope-from Zhiguo.Niu@unisoc.com) Received: from SHDLP.spreadtrum.com (bjmbx02.spreadtrum.com [10.0.64.8]) by dlp.unisoc.com (SkyGuard) with ESMTPS id 4VTBGJ2hWzz2P4QcL; Tue, 30 Apr 2024 15:12:08 +0800 (CST) Received: from BJMBX02.spreadtrum.com (10.0.64.8) by BJMBX02.spreadtrum.com (10.0.64.8) with Microsoft SMTP Server (TLS) id 15.0.1497.23; Tue, 30 Apr 2024 15:14:55 +0800 Received: from BJMBX02.spreadtrum.com ([fe80::c8c3:f3a0:9c9f:b0fb]) by BJMBX02.spreadtrum.com ([fe80::c8c3:f3a0:9c9f:b0fb%19]) with mapi id 15.00.1497.023; Tue, 30 Apr 2024 15:14:55 +0800 From: =?utf-8?B?54mb5b+X5Zu9IChaaGlndW8gTml1KQ==?= To: Carlos Llamas , Peter Zijlstra , Ingo Molnar , Will Deacon , Waiman Long , Boqun Feng , Bart Van Assche CC: "linux-kernel@vger.kernel.org" , "kernel-team@android.com" , "stable@vger.kernel.org" , =?utf-8?B?6Zer5a2m5paHIChYdWV3ZW4gWWFuKQ==?= , Ingo Molnar Subject: =?utf-8?B?562U5aSNOiBbUEFUQ0ggdjQgUkVTRU5EXSBsb2NrZGVwOiBmaXggZGVhZGxv?= =?utf-8?Q?ck_issue_between_lockdep_and_rcu?= Thread-Topic: [PATCH v4 RESEND] lockdep: fix deadlock issue between lockdep and rcu Thread-Index: AQHakRNq1uHIPB8QHkOifECnk9qXgbGAeTSg Date: Tue, 30 Apr 2024 07:14:54 +0000 Message-ID: References: <20240417220534.1370087-1-cmllamas@google.com> In-Reply-To: <20240417220534.1370087-1-cmllamas@google.com> Accept-Language: zh-CN, en-US Content-Language: zh-CN X-MS-Has-Attach: X-MS-TNEF-Correlator: x-ms-exchange-transport-fromentityheader: Hosted Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-MAIL: SHSQR01.spreadtrum.com 43U7FCBV023552 Ping..... Hi Carlos Llamas, If there is no maintainer help to merge this patch, we plan to upstream it = to google kernel.=20 How about your opinions? Thanks=20 Reviewed-by: Bart Van Assche Reviewed-by: Boqun Feng Reviewed-by: Carlos Llamas Reviewed-by: Waiman Long -----=E9=82=AE=E4=BB=B6=E5=8E=9F=E4=BB=B6----- =E5=8F=91=E4=BB=B6=E4=BA=BA: Carlos Llamas =20 =E5=8F=91=E9=80=81=E6=97=B6=E9=97=B4: 2024=E5=B9=B44=E6=9C=8818=E6=97=A5 6:= 06 =E6=94=B6=E4=BB=B6=E4=BA=BA: Peter Zijlstra ; Ingo Mo= lnar ; Will Deacon ; Waiman Long ; Boqun Feng ; Bart Van Assche =E6=8A=84=E9=80=81: linux-kernel@vger.kernel.org; kernel-team@android.com; = =E7=89=9B=E5=BF=97=E5=9B=BD (Zhiguo Niu) ; stable@vg= er.kernel.org; Carlos Llamas ; =E9=97=AB=E5=AD=A6=E6= =96=87 (Xuewen Yan) ; Ingo Molnar =E4=B8=BB=E9=A2=98: [PATCH v4 RESEND] lockdep: fix deadlock issue between l= ockdep and rcu =E6=B3=A8=E6=84=8F: =E8=BF=99=E5=B0=81=E9=82=AE=E4=BB=B6=E6=9D=A5=E8=87=AA= =E4=BA=8E=E5=A4=96=E9=83=A8=E3=80=82=E9=99=A4=E9=9D=9E=E4=BD=A0=E7=A1=AE=E5= =AE=9A=E9=82=AE=E4=BB=B6=E5=86=85=E5=AE=B9=E5=AE=89=E5=85=A8=EF=BC=8C=E5=90= =A6=E5=88=99=E4=B8=8D=E8=A6=81=E7=82=B9=E5=87=BB=E4=BB=BB=E4=BD=95=E9=93=BE= =E6=8E=A5=E5=92=8C=E9=99=84=E4=BB=B6=E3=80=82 CAUTION: This email originated from outside of the organization. Do not cli= ck links or open attachments unless you recognize the sender and know the c= ontent is safe. From: Zhiguo Niu There is a deadlock scenario between lockdep and rcu when rcu nocb feature = is enabled, just as following call stack: rcuop/x -000|queued_spin_lock_slowpath(lock =3D 0xFFFFFF817F2A8A80, val =3D ?) -001|queued_spin_lock(inline) // try to hold nocb_gp_lock=20 -001|do_raw_spin_lock(lock =3D 0xFFFFFF817F2A8A80) -002|__raw_spin_lock_irqsave(inline) -002|_raw_spin_lock_irqsave(lock =3D 0xFFFFFF817F2A8A80) -003|wake_nocb_gp_defer(inline) -003|__call_rcu_nocb_wake(rdp =3D 0xFFFFFF817F30B680) -004|__call_rcu_common(inline) -004|call_rcu(head =3D 0xFFFFFFC082EECC28, func =3D ?) -005|call_rcu_zapped(inline) -005|free_zapped_rcu(ch =3D ?)// hold graph lock -006|rcu_do_batch(rdp =3D 0xFFFFFF817F245680) -007|nocb_cb_wait(inline) -007|rcu_nocb_cb_kthread(arg =3D 0xFFFFFF817F245680) -008|kthread(_create =3D 0xFFFFFF80803122C0) -009|ret_from_fork(asm) rcuop/y -000|queued_spin_lock_slowpath(lock =3D 0xFFFFFFC08291BBC8, val =3D 0) -001|queued_spin_lock() -001|lockdep_lock() -001|graph_lock() // try to hold graph lock -002|lookup_chain_cache_add() -002|validate_chain() -003|lock_acquire -004|_raw_spin_lock_irqsave(lock =3D 0xFFFFFF817F211D80) -005|lock_timer_base(inline) -006|mod_timer(inline) -006|wake_nocb_gp_defer(inline)// hold nocb_gp_lock=20 -006|__call_rcu_nocb_wake(rdp =3D 0xFFFFFF817F2A8680) -007|__call_rcu_common(inline) -007|call_rcu(head =3D 0xFFFFFFC0822E0B58, func =3D ?) -008|call_rcu_hurry(inline) -008|rcu_sync_call(inline) -008|rcu_sync_func(rhp =3D 0xFFFFFFC0822E0B58) -009|rcu_do_batch(rdp =3D 0xFFFFFF817F266680) -010|nocb_cb_wait(inline) -010|rcu_nocb_cb_kthread(arg =3D 0xFFFFFF817F266680) -011|kthread(_create =3D 0xFFFFFF8080363740) -012|ret_from_fork(asm) rcuop/x and rcuop/y are rcu nocb threads with the same nocb gp thread. This patch release the graph lock before lockdep call_rcu. Fixes: a0b0fd53e1e6 ("locking/lockdep: Free lock classes that are no longer= in use") Cc: Cc: Boqun Feng Cc: Waiman Long Cc: Carlos Llamas Cc: Bart Van Assche Signed-off-by: Zhiguo Niu Signed-off-by: Xuewen Yan Reviewed-by: Boqun Feng Reviewed-by: Waiman Long Reviewed-by: Carlos Llamas Reviewed-by: Bart Van Assche --- kernel/locking/lockdep.c | 48 ++++++++++++++++++++++++++-------------- 1 file changed, 32 insertions(+), 16 deletions(-) diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 151b= d3de5936..3468d8230e5f 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -6184,25 +6184,27 @@ static struct pending_free *get_pending_free(void) = static void free_zapped_rcu(struct rcu_head *cb); /* - * Schedule an RCU callback if no RCU callback is pending. Must be called = with - * the graph lock held. - */ -static void call_rcu_zapped(struct pending_free *pf) +* See if we need to queue an RCU callback, must called with +* the lockdep lock held, returns false if either we don't have +* any pending free or the callback is already scheduled. +* Otherwise, a call_rcu() must follow this function call. +*/ +static bool prepare_call_rcu_zapped(struct pending_free *pf) { WARN_ON_ONCE(inside_selftest()); if (list_empty(&pf->zapped)) - return; + return false; if (delayed_free.scheduled) - return; + return false; delayed_free.scheduled =3D true; WARN_ON_ONCE(delayed_free.pf + delayed_free.index !=3D pf); delayed_free.index ^=3D 1; - call_rcu(&delayed_free.rcu_head, free_zapped_rcu); + return true; } /* The caller must hold the graph lock. May be called from RCU context. */= @@ -6228,6 +6230,7 @@ static void free_zapped_rcu(struct rcu_head *ch) { struct pending_free *pf; unsigned long flags; + bool need_callback; if (WARN_ON_ONCE(ch !=3D &delayed_free.rcu_head)) return; @@ -6239,14 +6242,18 @@ static void free_zapped_rcu(struct rcu_head *ch) pf =3D delayed_free.pf + (delayed_free.index ^ 1); __free_zapped_classes(pf); delayed_free.scheduled =3D false; + need_callback =3D + prepare_call_rcu_zapped(delayed_free.pf + delayed_free.inde= x); + lockdep_unlock(); + raw_local_irq_restore(flags); /* - * If there's anything on the open list, close and start a new call= back. - */ - call_rcu_zapped(delayed_free.pf + delayed_free.index); + * If there's pending free and its callback has not been scheduled, + * queue an RCU callback. + */ + if (need_callback) + call_rcu(&delayed_free.rcu_head, free_zapped_rcu); - lockdep_unlock(); - raw_local_irq_restore(flags); } /* @@ -6286,6 +6293,7 @@ static void lockdep_free_key_range_reg(void *start, u= nsigned long size) { struct pending_free *pf; unsigned long flags; + bool need_callback; init_data_structures_once(); @@ -6293,10 +6301,11 @@ static void lockdep_free_key_range_reg(void *start,= unsigned long size) lockdep_lock(); pf =3D get_pending_free(); __lockdep_free_key_range(pf, start, size); - call_rcu_zapped(pf); + need_callback =3D prepare_call_rcu_zapped(pf); lockdep_unlock(); raw_local_irq_restore(flags); - + if (need_callback) + call_rcu(&delayed_free.rcu_head, free_zapped_rcu); /* * Wait for any possible iterators from look_up_lock_class() to pass * before continuing to free the memory they refer to. @@ -6390,6 +6399,7 @@ static void lockdep_reset_lock_reg(struct lockdep_map= *lock) struct pending_free *pf; unsigned long flags; int locked; + bool need_callback =3D false; raw_local_irq_save(flags); locked =3D graph_lock(); @@ -6398,11 +6408,13 @@ static void lockdep_reset_lock_reg(struct lockdep_m= ap *lock) pf =3D get_pending_free(); __lockdep_reset_lock(pf, lock); - call_rcu_zapped(pf); + need_callback =3D prepare_call_rcu_zapped(pf); graph_unlock(); out_irq: raw_local_irq_restore(flags); + if (need_callback) + call_rcu(&delayed_free.rcu_head, free_zapped_rcu); } /* @@ -6446,6 +6458,7 @@ void lockdep_unregister_key(struct lock_class_key *ke= y) struct pending_free *pf; unsigned long flags; bool found =3D false; + bool need_callback =3D false; might_sleep(); @@ -6466,11 +6479,14 @@ void lockdep_unregister_key(struct lock_class_key *= key) if (found) { pf =3D get_pending_free(); __lockdep_free_key_range(pf, key, 1); - call_rcu_zapped(pf); + need_callback =3D prepare_call_rcu_zapped(pf); } lockdep_unlock(); raw_local_irq_restore(flags); + if (need_callback) + call_rcu(&delayed_free.rcu_head, free_zapped_rcu); + /* Wait until is_dynamic_key() has finished accessing k->hash_entry= . */ synchronize_rcu(); } -- 2.44.0.683.g7961c838ac-goog