From e15ffe4a7a13065eb2bafa7e262b169d2b2600c2 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 22 Feb 2012 12:03:30 +0100
Subject: seqlock: Prevent rt starvation

If a low prio writer gets preempted while holding the seqlock write
locked, a high prio reader spins forever on RT.

To prevent this let the reader grab the spinlock, so it blocks and
eventually boosts the writer. This way the writer can proceed and
endless spinning is prevented.

For seqcount writers we disable preemption over the update code
path. Thaanks to Al Viro for distangling some VFS code to make that
possible.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable-rt@vger.kernel.org
---
 include/linux/seqlock.h | 55 ++++++++++++++++++++++++++++++++++++++++---------
 include/net/neighbour.h |  2 +-
 2 files changed, 46 insertions(+), 11 deletions(-)

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 3e1f3f93dd18..a1dbf48d41f4 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -125,18 +125,30 @@ static inline int read_seqcount_retry(const seqcount_t *s, unsigned start)
  * Sequence counter only version assumes that callers are using their
  * own mutexing.
  */
-static inline void write_seqcount_begin(seqcount_t *s)
+static inline void __write_seqcount_begin(seqcount_t *s)
 {
 	s->sequence++;
 	smp_wmb();
 }
 
-static inline void write_seqcount_end(seqcount_t *s)
+static inline void write_seqcount_begin(seqcount_t *s)
+{
+	preempt_disable_rt();
+	__write_seqcount_begin(s);
+}
+
+static inline void __write_seqcount_end(seqcount_t *s)
 {
 	smp_wmb();
 	s->sequence++;
 }
 
+static inline void write_seqcount_end(seqcount_t *s)
+{
+	__write_seqcount_end(s);
+	preempt_enable_rt();
+}
+
 /**
  * write_seqcount_barrier - invalidate in-progress read-side seq operations
  * @s: pointer to seqcount_t
@@ -177,10 +189,33 @@ typedef struct {
 /*
  * Read side functions for starting and finalizing a read side section.
  */
+#ifndef CONFIG_PREEMPT_RT_FULL
 static inline unsigned read_seqbegin(const seqlock_t *sl)
 {
 	return read_seqcount_begin(&sl->seqcount);
 }
+#else
+/*
+ * Starvation safe read side for RT
+ */
+static inline unsigned read_seqbegin(seqlock_t *sl)
+{
+	unsigned ret;
+
+repeat:
+	ret = sl->seqcount.sequence;
+	if (unlikely(ret & 1)) {
+		/*
+		 * Take the lock and let the writer proceed (i.e. evtl
+		 * boost it), otherwise we could loop here forever.
+		 */
+		spin_lock(&sl->lock);
+		spin_unlock(&sl->lock);
+		goto repeat;
+	}
+	return ret;
+}
+#endif
 
 static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
 {
@@ -195,36 +230,36 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
 static inline void write_seqlock(seqlock_t *sl)
 {
 	spin_lock(&sl->lock);
-	write_seqcount_begin(&sl->seqcount);
+	__write_seqcount_begin(&sl->seqcount);
 }
 
 static inline void write_sequnlock(seqlock_t *sl)
 {
-	write_seqcount_end(&sl->seqcount);
+	__write_seqcount_end(&sl->seqcount);
 	spin_unlock(&sl->lock);
 }
 
 static inline void write_seqlock_bh(seqlock_t *sl)
 {
 	spin_lock_bh(&sl->lock);
-	write_seqcount_begin(&sl->seqcount);
+	__write_seqcount_begin(&sl->seqcount);
 }
 
 static inline void write_sequnlock_bh(seqlock_t *sl)
 {
-	write_seqcount_end(&sl->seqcount);
+	__write_seqcount_end(&sl->seqcount);
 	spin_unlock_bh(&sl->lock);
 }
 
 static inline void write_seqlock_irq(seqlock_t *sl)
 {
 	spin_lock_irq(&sl->lock);
-	write_seqcount_begin(&sl->seqcount);
+	__write_seqcount_begin(&sl->seqcount);
 }
 
 static inline void write_sequnlock_irq(seqlock_t *sl)
 {
-	write_seqcount_end(&sl->seqcount);
+	__write_seqcount_end(&sl->seqcount);
 	spin_unlock_irq(&sl->lock);
 }
 
@@ -233,7 +268,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
 	unsigned long flags;
 
 	spin_lock_irqsave(&sl->lock, flags);
-	write_seqcount_begin(&sl->seqcount);
+	__write_seqcount_begin(&sl->seqcount);
 	return flags;
 }
 
@@ -243,7 +278,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
 static inline void
 write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags)
 {
-	write_seqcount_end(&sl->seqcount);
+	__write_seqcount_end(&sl->seqcount);
 	spin_unlock_irqrestore(&sl->lock, flags);
 }
 
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 34c996f46181..8e626fa6ccde 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -394,7 +394,7 @@ struct neighbour_cb {
 
 #define NEIGH_CB(skb)	((struct neighbour_cb *)(skb)->cb)
 
-static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n,
+static inline void neigh_ha_snapshot(char *dst, struct neighbour *n,
 				     const struct net_device *dev)
 {
 	unsigned int seq;
-- 
cgit v1.2.3