From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 14 Sep 2016 17:36:35 +0200
Subject: net/Qdisc: use a seqlock instead seqcount
Git-repo: git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git
Git-commit: ab477791f151d454602bd7d3c57d654403f97759
Patch-mainline: Queued in subsystem maintainer repository
References: SLE Realtime Extension

The seqcount disables preemption on -RT while it is held which can't
remove. Also we don't want the reader to spin for ages if the writer is
scheduled out. The seqlock on the other hand will serialize / sleep on
the lock while writer is active.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Mike Galbraith <mgalbraith@suse.de>
---
 include/linux/seqlock.h    |    9 +++++++++
 include/net/gen_stats.h    |   11 ++++++-----
 include/net/net_seq_lock.h |   15 +++++++++++++++
 include/net/sch_generic.h  |   19 +++++++++++++++++--
 net/core/gen_estimator.c   |    6 +++---
 net/core/gen_stats.c       |   12 ++++++------
 net/sched/sch_api.c        |    2 +-
 net/sched/sch_generic.c    |   12 ++++++++++++
 8 files changed, 69 insertions(+), 17 deletions(-)
 create mode 100644 include/net/net_seq_lock.h

--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -481,6 +481,15 @@ static inline void write_seqlock(seqlock
 	__raw_write_seqcount_begin(&sl->seqcount);
 }
 
+static inline int try_write_seqlock(seqlock_t *sl)
+{
+	if (spin_trylock(&sl->lock)) {
+		__raw_write_seqcount_begin(&sl->seqcount);
+		return 1;
+	}
+	return 0;
+}
+
 static inline void write_sequnlock(seqlock_t *sl)
 {
 	__raw_write_seqcount_end(&sl->seqcount);
--- a/include/net/gen_stats.h
+++ b/include/net/gen_stats.h
@@ -5,6 +5,7 @@
 #include <linux/socket.h>
 #include <linux/rtnetlink.h>
 #include <linux/pkt_sched.h>
+#include <net/net_seq_lock.h>
 
 struct gnet_stats_basic_cpu {
 	struct gnet_stats_basic_packed bstats;
@@ -35,15 +36,15 @@ int gnet_stats_start_copy_compat(struct
 				 spinlock_t *lock, struct gnet_dump *d,
 				 int padattr);
 
-int gnet_stats_copy_basic(const seqcount_t *running,
+int gnet_stats_copy_basic(net_seqlock_t *running,
 			  struct gnet_dump *d,
 			  struct gnet_stats_basic_cpu __percpu *cpu,
 			  struct gnet_stats_basic_packed *b);
-void __gnet_stats_copy_basic(const seqcount_t *running,
+void __gnet_stats_copy_basic(net_seqlock_t *running,
 			     struct gnet_stats_basic_packed *bstats,
 			     struct gnet_stats_basic_cpu __percpu *cpu,
 			     struct gnet_stats_basic_packed *b);
-int gnet_stats_copy_basic_hw(const seqcount_t *running,
+int gnet_stats_copy_basic_hw(net_seqlock_t *running,
 			     struct gnet_dump *d,
 			     struct gnet_stats_basic_cpu __percpu *cpu,
 			     struct gnet_stats_basic_packed *b);
@@ -63,13 +64,13 @@ int gen_new_estimator(struct gnet_stats_
 		      struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 		      struct net_rate_estimator __rcu **rate_est,
 		      spinlock_t *lock,
-		      seqcount_t *running, struct nlattr *opt);
+		      net_seqlock_t *running, struct nlattr *opt);
 void gen_kill_estimator(struct net_rate_estimator __rcu **ptr);
 int gen_replace_estimator(struct gnet_stats_basic_packed *bstats,
 			  struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 			  struct net_rate_estimator __rcu **ptr,
 			  spinlock_t *lock,
-			  seqcount_t *running, struct nlattr *opt);
+			  net_seqlock_t *running, struct nlattr *opt);
 bool gen_estimator_active(struct net_rate_estimator __rcu **ptr);
 bool gen_estimator_read(struct net_rate_estimator __rcu **ptr,
 			struct gnet_stats_rate_est64 *sample);
--- /dev/null
+++ b/include/net/net_seq_lock.h
@@ -0,0 +1,15 @@
+#ifndef __NET_NET_SEQ_LOCK_H__
+#define __NET_NET_SEQ_LOCK_H__
+
+#ifdef CONFIG_PREEMPT_RT_BASE
+# define net_seqlock_t			seqlock_t
+# define net_seq_begin(__r)		read_seqbegin(__r)
+# define net_seq_retry(__r, __s)	read_seqretry(__r, __s)
+
+#else
+# define net_seqlock_t			seqcount_t
+# define net_seq_begin(__r)		read_seqcount_begin(__r)
+# define net_seq_retry(__r, __s)	read_seqcount_retry(__r, __s)
+#endif
+
+#endif
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -13,6 +13,7 @@
 #include <linux/workqueue.h>
 #include <net/gen_stats.h>
 #include <net/rtnetlink.h>
+#include <net/net_seq_lock.h>
 
 struct Qdisc_ops;
 struct qdisc_walker;
@@ -97,7 +98,7 @@ struct Qdisc {
 	struct sk_buff_head	gso_skb ____cacheline_aligned_in_smp;
 	struct qdisc_skb_head	q;
 	struct gnet_stats_basic_packed bstats;
-	seqcount_t		running;
+	net_seqlock_t		running;
 	struct gnet_stats_queue	qstats;
 	unsigned long		state;
 	struct Qdisc            *next_sched;
@@ -132,13 +133,22 @@ static inline struct Qdisc *qdisc_refcou
 
 static inline bool qdisc_is_running(struct Qdisc *qdisc)
 {
+#ifdef CONFIG_PREEMPT_RT_BASE
+	return spin_is_locked(&qdisc->running.lock) ? true : false;
+#else
 	if (qdisc->flags & TCQ_F_NOLOCK)
 		return spin_is_locked(&qdisc->seqlock);
 	return (raw_read_seqcount(&qdisc->running) & 1) ? true : false;
+#endif
 }
 
 static inline bool qdisc_run_begin(struct Qdisc *qdisc)
 {
+#ifdef CONFIG_PREEMPT_RT_BASE
+	if (try_write_seqlock(&qdisc->running))
+		return true;
+	return false;
+#else
 	if (qdisc->flags & TCQ_F_NOLOCK) {
 		if (!spin_trylock(&qdisc->seqlock))
 			return false;
@@ -151,13 +161,18 @@ static inline bool qdisc_run_begin(struc
 	raw_write_seqcount_begin(&qdisc->running);
 	seqcount_acquire(&qdisc->running.dep_map, 0, 1, _RET_IP_);
 	return true;
+#endif
 }
 
 static inline void qdisc_run_end(struct Qdisc *qdisc)
 {
+#ifdef CONFIG_PREEMPT_RT_BASE
+	write_sequnlock(&qdisc->running);
+#else
 	write_seqcount_end(&qdisc->running);
 	if (qdisc->flags & TCQ_F_NOLOCK)
 		spin_unlock(&qdisc->seqlock);
+#endif
 }
 
 static inline bool qdisc_may_bulk(const struct Qdisc *qdisc)
@@ -467,7 +482,7 @@ static inline spinlock_t *qdisc_root_sle
 	return qdisc_lock(root);
 }
 
-static inline seqcount_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc)
+static inline net_seqlock_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc)
 {
 	struct Qdisc *root = qdisc_root_sleeping(qdisc);
 
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -46,7 +46,7 @@
 struct net_rate_estimator {
 	struct gnet_stats_basic_packed	*bstats;
 	spinlock_t		*stats_lock;
-	seqcount_t		*running;
+	net_seqlock_t		*running;
 	struct gnet_stats_basic_cpu __percpu *cpu_bstats;
 	u8			ewma_log;
 	u8			intvl_log; /* period : (250ms << intvl_log) */
@@ -129,7 +129,7 @@ int gen_new_estimator(struct gnet_stats_
 		      struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 		      struct net_rate_estimator __rcu **rate_est,
 		      spinlock_t *lock,
-		      seqcount_t *running,
+		      net_seqlock_t *running,
 		      struct nlattr *opt)
 {
 	struct gnet_estimator *parm = nla_data(opt);
@@ -227,7 +227,7 @@ int gen_replace_estimator(struct gnet_st
 			  struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 			  struct net_rate_estimator __rcu **rate_est,
 			  spinlock_t *lock,
-			  seqcount_t *running, struct nlattr *opt)
+			  net_seqlock_t *running, struct nlattr *opt)
 {
 	return gen_new_estimator(bstats, cpu_bstats, rate_est,
 				 lock, running, opt);
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -142,7 +142,7 @@ __gnet_stats_copy_basic_cpu(struct gnet_
 }
 
 void
-__gnet_stats_copy_basic(const seqcount_t *running,
+__gnet_stats_copy_basic(net_seqlock_t *running,
 			struct gnet_stats_basic_packed *bstats,
 			struct gnet_stats_basic_cpu __percpu *cpu,
 			struct gnet_stats_basic_packed *b)
@@ -155,15 +155,15 @@ __gnet_stats_copy_basic(const seqcount_t
 	}
 	do {
 		if (running)
-			seq = read_seqcount_begin(running);
+			seq = net_seq_begin(running);
 		bstats->bytes = b->bytes;
 		bstats->packets = b->packets;
-	} while (running && read_seqcount_retry(running, seq));
+	} while (running && net_seq_retry(running, seq));
 }
 EXPORT_SYMBOL(__gnet_stats_copy_basic);
 
 static int
-___gnet_stats_copy_basic(const seqcount_t *running,
+___gnet_stats_copy_basic(net_seqlock_t *running,
 			 struct gnet_dump *d,
 			 struct gnet_stats_basic_cpu __percpu *cpu,
 			 struct gnet_stats_basic_packed *b,
@@ -204,7 +204,7 @@ ___gnet_stats_copy_basic(const seqcount_
  * if the room in the socket buffer was not sufficient.
  */
 int
-gnet_stats_copy_basic(const seqcount_t *running,
+gnet_stats_copy_basic(net_seqlock_t *running,
 		      struct gnet_dump *d,
 		      struct gnet_stats_basic_cpu __percpu *cpu,
 		      struct gnet_stats_basic_packed *b)
@@ -228,7 +228,7 @@ EXPORT_SYMBOL(gnet_stats_copy_basic);
  * if the room in the socket buffer was not sufficient.
  */
 int
-gnet_stats_copy_basic_hw(const seqcount_t *running,
+gnet_stats_copy_basic_hw(net_seqlock_t *running,
 			 struct gnet_dump *d,
 			 struct gnet_stats_basic_cpu __percpu *cpu,
 			 struct gnet_stats_basic_packed *b)
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1188,7 +1188,7 @@ static struct Qdisc *qdisc_create(struct
 		rcu_assign_pointer(sch->stab, stab);
 	}
 	if (tca[TCA_RATE]) {
-		seqcount_t *running;
+		net_seqlock_t *running;
 
 		err = -EOPNOTSUPP;
 		if (sch->flags & TCQ_F_MQROOT) {
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -567,7 +567,11 @@ struct Qdisc noop_qdisc = {
 	.ops		=	&noop_qdisc_ops,
 	.q.lock		=	__SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock),
 	.dev_queue	=	&noop_netdev_queue,
+#ifdef CONFIG_PREEMPT_RT_BASE
+	.running	=	__SEQLOCK_UNLOCKED(noop_qdisc.running),
+#else
 	.running	=	SEQCNT_ZERO(noop_qdisc.running),
+#endif
 	.busylock	=	__SPIN_LOCK_UNLOCKED(noop_qdisc.busylock),
 	.gso_skb = {
 		.next = (struct sk_buff *)&noop_qdisc.gso_skb,
@@ -881,9 +885,17 @@ struct Qdisc *qdisc_alloc(struct netdev_
 	lockdep_set_class(&sch->busylock,
 			  dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+	seqlock_init(&sch->running);
+	lockdep_set_class(&sch->running.seqcount,
+			  dev->qdisc_running_key ?: &qdisc_running_key);
+	lockdep_set_class(&sch->running.lock,
+			  dev->qdisc_running_key ?: &qdisc_running_key);
+#else
 	seqcount_init(&sch->running);
 	lockdep_set_class(&sch->running,
 			  dev->qdisc_running_key ?: &qdisc_running_key);
+#endif
 
 	sch->ops = ops;
 	sch->flags = ops->static_flags;