Received-SPF: pass (google.com: domain of linux-wireless-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Message-Id: <20210309084241.988908275@linutronix.de>
Date:   Tue, 09 Mar 2021 09:42:10 +0100
From:   Thomas Gleixner <tglx@linutronix.de>
To:     LKML <linux-kernel@vger.kernel.org>
Cc:     Frederic Weisbecker <frederic@kernel.org>,
        Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
        "Ahmed S. Darwish" <a.darwish@linutronix.de>,
        Peter Zijlstra <peterz@infradead.org>,
        Denis Kirjanov <kda@linux-powerpc.org>,
        "David S. Miller" <davem@davemloft.net>,
        Jakub Kicinski <kuba@kernel.org>, netdev@vger.kernel.org,
        ath9k-devel@qca.qualcomm.com, Kalle Valo <kvalo@codeaurora.org>,
        linux-wireless@vger.kernel.org, Chas Williams <3chas3@gmail.com>,
        linux-atm-general@lists.sourceforge.net,
        "K. Y. Srinivasan" <kys@microsoft.com>,
        Haiyang Zhang <haiyangz@microsoft.com>,
        Stephen Hemminger <sthemmin@microsoft.com>,
        Wei Liu <wei.liu@kernel.org>,
        Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>,
        Rob Herring <robh@kernel.org>,
        Bjorn Helgaas <bhelgaas@google.com>,
        linux-hyperv@vger.kernel.org, linux-pci@vger.kernel.org,
        Stefan Richter <stefanr@s5r6.in-berlin.de>,
        linux1394-devel@lists.sourceforge.net
Subject: [patch 07/14] tasklets: Prevent tasklet_unlock_spin_wait() deadlock on RT
References: <20210309084203.995862150@linutronix.de>
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-transfer-encoding: 8-bit
Precedence: bulk

tasklet_unlock_spin_wait() spin waits for the TASKLET_STATE_SCHED bit in
the tasklet state to be cleared. This works on !RT nicely because the
corresponding execution can only happen on a different CPU.

On RT softirq processing is preemptible, therefore a task preempting the
softirq processing thread can spin forever.

Prevent this by invoking local_bh_disable()/enable() inside the loop. In
case that the softirq processing thread was preempted by the current task,
current will block on the local lock which yields the CPU to the preempted
softirq processing thread. If the tasklet is processed on a different CPU
then the local_bh_disable()/enable() pair is just a waste of processor
cycles.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 include/linux/interrupt.h |    2 +-
 kernel/softirq.c          |   28 +++++++++++++++++++++++++++-
 2 files changed, 28 insertions(+), 2 deletions(-)

--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -658,7 +658,7 @@ enum
 	TASKLET_STATE_RUN	/* Tasklet is running (SMP only) */
 };
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
 static inline int tasklet_trylock(struct tasklet_struct *t)
 {
 	return !test_and_set_bit(TASKLET_STATE_RUN, &(t)->state);
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -616,6 +616,32 @@ void tasklet_init(struct tasklet_struct
 }
 EXPORT_SYMBOL(tasklet_init);
 
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
+/*
+ * Do not use in new code. There is no real reason to invoke this from
+ * atomic contexts.
+ */
+void tasklet_unlock_spin_wait(struct tasklet_struct *t)
+{
+	while (test_bit(TASKLET_STATE_RUN, &(t)->state)) {
+		if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+			/*
+			 * Prevent a live lock when current preempted soft
+			 * interrupt processing or prevents ksoftirqd from
+			 * running. If the tasklet runs on a different CPU
+			 * then this has no effect other than doing the BH
+			 * disable/enable dance for nothing.
+			 */
+			local_bh_disable();
+			local_bh_enable();
+		} else {
+			cpu_relax();
+		}
+	}
+}
+EXPORT_SYMBOL(tasklet_unlock_spin_wait);
+#endif
+
 void tasklet_kill(struct tasklet_struct *t)
 {
 	if (in_interrupt())
@@ -629,7 +655,7 @@ void tasklet_kill(struct tasklet_struct
 }
 EXPORT_SYMBOL(tasklet_kill);
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
 void tasklet_unlock(struct tasklet_struct *t)
 {
 	smp_mb__before_atomic();