Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753620AbbKXNEh (ORCPT ); Tue, 24 Nov 2015 08:04:37 -0500 Received: from mail.bmw-carit.de ([62.245.222.98]:46220 "EHLO linuxmail.bmw-carit.de" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751811AbbKXNDP (ORCPT ); Tue, 24 Nov 2015 08:03:15 -0500 From: Daniel Wagner To: linux-kernel@vger.kernel.org, linux-rt-users@vger.kernel.org Cc: Boqun Feng , Daniel Wagner , "Paul E. McKenney" , Peter Zijlstra , Thomas Gleixner , Marcelo Tosatti , Paolo Bonzini , Paul Gortmaker Subject: [PATCH tip v4 4/5] rcu: Do not call rcu_nocb_gp_cleanup() while holding rnp->lock Date: Tue, 24 Nov 2015 14:03:06 +0100 Message-Id: <1448370187-10075-5-git-send-email-daniel.wagner@bmw-carit.de> X-Mailer: git-send-email 2.4.3 In-Reply-To: <1448370187-10075-1-git-send-email-daniel.wagner@bmw-carit.de> References: <1448370187-10075-1-git-send-email-daniel.wagner@bmw-carit.de> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 7789 Lines: 193 rcu_nocb_gp_cleanup() is called while holding rnp->lock. Currently, this is okay because the wake_up_all() in rcu_nocb_gp_cleanup() will not enable the IRQs. lockdep is happy. By switching over using swait this is not true anymore. swake_up_all() enables the IRQs while processing the waiters. __do_softirq() can now run and will eventually call rcu_process_callbacks() which wants to grap nrp->lock. Let's move the rcu_nocb_gp_cleanup() call outside the lock before we switch over to swait. If we would hold the rnp->lock and use swait, lockdep reports following: ================================= [ INFO: inconsistent lock state ] 4.2.0-rc5-00025-g9a73ba0 #136 Not tainted --------------------------------- inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-W} usage. rcu_preempt/8 [HC0[0]:SC0[0]:HE1:SE1] takes: (rcu_node_1){+.?...}, at: [] rcu_gp_kthread+0xb97/0xeb0 {IN-SOFTIRQ-W} state was registered at: [] __lock_acquire+0xd5f/0x21e0 [] lock_acquire+0xdf/0x2b0 [] _raw_spin_lock_irqsave+0x59/0xa0 [] rcu_process_callbacks+0x141/0x3c0 [] __do_softirq+0x14d/0x670 [] irq_exit+0x104/0x110 [] smp_apic_timer_interrupt+0x46/0x60 [] apic_timer_interrupt+0x70/0x80 [] rq_attach_root+0xa6/0x100 [] cpu_attach_domain+0x16d/0x650 [] build_sched_domains+0x942/0xb00 [] sched_init_smp+0x509/0x5c1 [] kernel_init_freeable+0x172/0x28f [] kernel_init+0xe/0xe0 [] ret_from_fork+0x3f/0x70 irq event stamp: 76 hardirqs last enabled at (75): [] _raw_spin_unlock_irq+0x30/0x60 hardirqs last disabled at (76): [] _raw_spin_lock_irq+0x1f/0x90 softirqs last enabled at (0): [] copy_process.part.26+0x602/0x1cf0 softirqs last disabled at (0): [< (null)>] (null) other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(rcu_node_1); lock(rcu_node_1); *** DEADLOCK *** 1 lock held by rcu_preempt/8: #0: (rcu_node_1){+.?...}, at: [] rcu_gp_kthread+0xb97/0xeb0 stack backtrace: CPU: 0 PID: 8 Comm: rcu_preempt Not tainted 4.2.0-rc5-00025-g9a73ba0 #136 Hardware name: Dell Inc. PowerEdge R820/066N7P, BIOS 2.0.20 01/16/2014 0000000000000000 000000006d7e67d8 ffff881fb081fbd8 ffffffff818379e0 0000000000000000 ffff881fb0812a00 ffff881fb081fc38 ffffffff8110813b 0000000000000000 0000000000000001 ffff881f00000001 ffffffff8102fa4f Call Trace: [] dump_stack+0x4f/0x7b [] print_usage_bug+0x1db/0x1e0 [] ? save_stack_trace+0x2f/0x50 [] mark_lock+0x66d/0x6e0 [] ? check_usage_forwards+0x150/0x150 [] mark_held_locks+0x78/0xa0 [] ? _raw_spin_unlock_irq+0x30/0x60 [] trace_hardirqs_on_caller+0x168/0x220 [] trace_hardirqs_on+0xd/0x10 [] _raw_spin_unlock_irq+0x30/0x60 [] swake_up_all+0xb7/0xe0 [] rcu_gp_kthread+0xab1/0xeb0 [] ? trace_hardirqs_on_caller+0xff/0x220 [] ? _raw_spin_unlock_irq+0x41/0x60 [] ? rcu_barrier+0x20/0x20 [] kthread+0x104/0x120 [] ? _raw_spin_unlock_irq+0x30/0x60 [] ? kthread_create_on_node+0x260/0x260 [] ret_from_fork+0x3f/0x70 [] ? kthread_create_on_node+0x260/0x260 Signed-off-by: Daniel Wagner Cc: "Paul E. McKenney" Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org --- kernel/rcu/tree.c | 4 +++- kernel/rcu/tree.h | 3 ++- kernel/rcu/tree_plugin.h | 16 +++++++++++++--- 3 files changed, 18 insertions(+), 5 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 775d36c..952536d 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1568,7 +1568,6 @@ static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) int needmore; struct rcu_data *rdp = this_cpu_ptr(rsp->rda); - rcu_nocb_gp_cleanup(rsp, rnp); rnp->need_future_gp[c & 0x1] = 0; needmore = rnp->need_future_gp[(c + 1) & 0x1]; trace_rcu_future_gp(rnp, rdp, c, @@ -1972,6 +1971,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) int nocb = 0; struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(rsp); + struct swait_queue_head *sq; WRITE_ONCE(rsp->gp_activity, jiffies); raw_spin_lock_irq(&rnp->lock); @@ -2010,7 +2010,9 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) needgp = __note_gp_changes(rsp, rnp, rdp) || needgp; /* smp_mb() provided by prior unlock-lock pair. */ nocb += rcu_future_gp_cleanup(rsp, rnp); + sq = rcu_nocb_gp_get(rnp); raw_spin_unlock_irq(&rnp->lock); + rcu_nocb_gp_cleanup(sq); cond_resched_rcu_qs(); WRITE_ONCE(rsp->gp_activity, jiffies); rcu_gp_slow(rsp, gp_cleanup_delay); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 2e991f8..3dcf6368 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -608,7 +608,8 @@ static void zero_cpu_stall_ticks(struct rcu_data *rdp); static void increment_cpu_stall_ticks(void); static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu); static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq); -static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp); +static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp); +static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq); static void rcu_init_one_nocb(struct rcu_node *rnp); static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, bool lazy, unsigned long flags); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index b2bf396..db4f357 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -1777,9 +1777,9 @@ early_param("rcu_nocb_poll", parse_rcu_nocb_poll); * Wake up any no-CBs CPUs' kthreads that were waiting on the just-ended * grace period. */ -static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) +static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq) { - wake_up_all(&rnp->nocb_gp_wq[rnp->completed & 0x1]); + wake_up_all(sq); } /* @@ -1795,6 +1795,11 @@ static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq) rnp->need_future_gp[(rnp->completed + 1) & 0x1] += nrq; } +static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp) +{ + return &rnp->nocb_gp_wq[rnp->completed & 0x1]; +} + static void rcu_init_one_nocb(struct rcu_node *rnp) { init_waitqueue_head(&rnp->nocb_gp_wq[0]); @@ -2469,7 +2474,7 @@ static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu) return false; } -static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) +static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq) { } @@ -2477,6 +2482,11 @@ static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq) { } +static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp) +{ + return NULL; +} + static void rcu_init_one_nocb(struct rcu_node *rnp) { } -- 2.4.3 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/