All of lore.kernel.org
 help / color / mirror / Atom feed
From: Steven Rostedt <rostedt@goodmis.org>
To: linux-kernel@vger.kernel.org,
	linux-rt-users <linux-rt-users@vger.kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>,
	Carsten Emde <C.Emde@osadl.org>,
	Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
	John Kacur <jkacur@redhat.com>,
	Paul Gortmaker <paul.gortmaker@windriver.com>,
	<stable-rt@vger.kernel.org>
Subject: [PATCH RT 03/20] net: move xmit_recursion to per-task variable on -RT
Date: Wed, 02 Mar 2016 10:37:01 -0500	[thread overview]
Message-ID: <20160302153714.582242097@goodmis.org> (raw)
In-Reply-To: 20160302153658.995489487@goodmis.org

[-- Attachment #1: 0003-net-move-xmit_recursion-to-per-task-variable-on-RT.patch --]
[-- Type: text/plain, Size: 3689 bytes --]

3.18.27-rt27-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

A softirq on -RT can be preempted. That means one task is in
__dev_queue_xmit(), gets preempted and another task may enter
__dev_queue_xmit() aw well. netperf together with a bridge device
will then trigger the `recursion alert` because each task increments
the xmit_recursion variable which is per-CPU.
A virtual device like br0 is required to trigger this warning.

This patch moves the counter to per task instead per-CPU so it counts
the recursion properly on -RT.

Cc: stable-rt@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/netdevice.h |  9 +++++++++
 include/linux/sched.h     |  1 +
 net/core/dev.c            | 41 ++++++++++++++++++++++++++++++++++++++---
 3 files changed, 48 insertions(+), 3 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ff0f50dcea4a..dab2603bcdba 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2130,11 +2130,20 @@ void netdev_freemem(struct net_device *dev);
 void synchronize_net(void);
 int init_dummy_netdev(struct net_device *dev);
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static inline int dev_recursion_level(void)
+{
+	return current->xmit_recursion;
+}
+
+#else
+
 DECLARE_PER_CPU(int, xmit_recursion);
 static inline int dev_recursion_level(void)
 {
 	return this_cpu_read(xmit_recursion);
 }
+#endif
 
 struct net_device *dev_get_by_index(struct net *net, int ifindex);
 struct net_device *__dev_get_by_index(struct net *net, int ifindex);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index bdc27dbffbe2..d05f52dcc0f4 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1523,6 +1523,7 @@ struct task_struct {
 	struct mutex_waiter *blocked_on;
 #endif
 #ifdef CONFIG_PREEMPT_RT_FULL
+	int xmit_recursion;
 	int pagefault_disabled;
 #endif
 #ifdef CONFIG_TRACE_IRQFLAGS
diff --git a/net/core/dev.c b/net/core/dev.c
index 39d2a0ba38ed..b89a1dd9f4d8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2861,9 +2861,44 @@ static void skb_update_prio(struct sk_buff *skb)
 #define skb_update_prio(skb)
 #endif
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+
+static inline int xmit_rec_read(void)
+{
+       return current->xmit_recursion;
+}
+
+static inline void xmit_rec_inc(void)
+{
+       current->xmit_recursion++;
+}
+
+static inline void xmit_rec_dec(void)
+{
+       current->xmit_recursion--;
+}
+
+#else
+
 DEFINE_PER_CPU(int, xmit_recursion);
 EXPORT_SYMBOL(xmit_recursion);
 
+static inline int xmit_rec_read(void)
+{
+	return __this_cpu_read(xmit_recursion);
+}
+
+static inline void xmit_rec_inc(void)
+{
+	__this_cpu_inc(xmit_recursion);
+}
+
+static inline int xmit_rec_dec(void)
+{
+	__this_cpu_dec(xmit_recursion);
+}
+#endif
+
 #define RECURSION_LIMIT 10
 
 /**
@@ -2965,7 +3000,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
 
 		if (txq->xmit_lock_owner != cpu) {
 
-			if (__this_cpu_read(xmit_recursion) > RECURSION_LIMIT)
+			if (xmit_rec_read() > RECURSION_LIMIT)
 				goto recursion_alert;
 
 			skb = validate_xmit_skb(skb, dev);
@@ -2975,9 +3010,9 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
 			HARD_TX_LOCK(dev, txq, cpu);
 
 			if (!netif_xmit_stopped(txq)) {
-				__this_cpu_inc(xmit_recursion);
+				xmit_rec_inc();
 				skb = dev_hard_start_xmit(skb, dev, txq, &rc);
-				__this_cpu_dec(xmit_recursion);
+				xmit_rec_dec();
 				if (dev_xmit_complete(rc)) {
 					HARD_TX_UNLOCK(dev, txq);
 					goto out;
-- 
2.7.0

  parent reply	other threads:[~2016-03-02 15:37 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-03-02 15:36 [PATCH RT 00/20] Linux 3.18.27-rt27-rc1 Steven Rostedt
2016-03-02 15:36 ` [PATCH RT 01/20] sched: reset tasks lockless wake-queues on fork() Steven Rostedt
2016-03-02 15:37 ` [PATCH RT 02/20] ptrace: dont open IRQs in ptrace_freeze_traced() too early Steven Rostedt
2016-03-02 15:37 ` Steven Rostedt [this message]
2016-03-02 15:37 ` [PATCH RT 04/20] preempt-lazy: Add the lazy-preemption check to preempt_schedule() Steven Rostedt
2016-03-02 15:37 ` [PATCH RT 05/20] softirq: split timer softirqs out of ksoftirqd Steven Rostedt
2016-03-02 15:37 ` [PATCH RT 06/20] net: provide a way to delegate processing a softirq to ksoftirqd Steven Rostedt
2016-03-02 15:37 ` [PATCH RT 07/20] latencyhist: disable jump-labels Steven Rostedt
2016-03-02 15:37 ` [PATCH RT 08/20] arm64: replace read_lock to rcu lock in call_step_hook Steven Rostedt
2016-03-02 15:37 ` [PATCH RT 09/20] kernel: migrate_disable() do fastpath in atomic & irqs-off Steven Rostedt
2016-03-02 15:37 ` [PATCH RT 10/20] kernel: softirq: unlock with irqs on Steven Rostedt
2016-03-02 15:37 ` [PATCH RT 11/20] kernel/stop_machine: partly revert "stop_machine: Use raw spinlocks" Steven Rostedt
2016-03-02 15:37 ` [PATCH RT 12/20] tick/broadcast: Make broadcast hrtimer irqsafe Steven Rostedt
2016-03-02 15:37 ` [PATCH RT 13/20] sched,rt: __always_inline preemptible_lazy() Steven Rostedt
2016-03-02 15:37 ` [PATCH RT 14/20] drm,radeon,i915: Use preempt_disable/enable_rt() where recommended Steven Rostedt
2016-03-02 15:37 ` [PATCH RT 15/20] drm,i915: Use local_lock/unlock_irq() in intel_pipe_update_start/end() Steven Rostedt
2016-03-02 15:37 ` [PATCH RT 16/20] trace: Use rcuidle version for preemptoff_hist trace point Steven Rostedt
2016-03-02 15:37 ` [PATCH RT 17/20] f2fs: Mutex cant be used by down_write_nest_lock() Steven Rostedt
2016-03-02 15:37   ` Steven Rostedt
2016-03-02 15:37 ` [PATCH RT 18/20] rcu/torture: Comment out rcu_bh ops on PREEMPT_RT_FULL Steven Rostedt
2016-03-02 15:37 ` [PATCH RT 19/20] kernel: sched: Fix preempt_disable_ip recodring for preempt_disable() Steven Rostedt
2016-03-02 15:37 ` [PATCH RT 20/20] Linux 3.18.27-rt27-rc1 Steven Rostedt

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=20160302153714.582242097@goodmis.org \
    --to=rostedt@goodmis.org \
    --cc=C.Emde@osadl.org \
    --cc=bigeasy@linutronix.de \
    --cc=jkacur@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rt-users@vger.kernel.org \
    --cc=paul.gortmaker@windriver.com \
    --cc=stable-rt@vger.kernel.org \
    --cc=tglx@linutronix.de \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.