From: Sebastian Andrzej Siewior Date: Wed, 14 Sep 2016 17:36:35 +0200 Subject: [PATCH 201/354] net/Qdisc: use a seqlock instead seqcount Origin: https://git.kernel.org/cgit/linux/kernel/git/rt/linux-stable-rt.git/commit?id=d0f4cbf706e9a623aec379a6fec835c29d3feac7 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 --- include/linux/seqlock.h | 9 +++++++++ include/net/gen_stats.h | 9 +++++---- include/net/net_seq_lock.h | 15 +++++++++++++++ include/net/sch_generic.h | 19 +++++++++++++++++-- net/core/gen_estimator.c | 6 +++--- net/core/gen_stats.c | 8 ++++---- net/sched/sch_api.c | 2 +- net/sched/sch_generic.c | 12 ++++++++++++ 8 files changed, 66 insertions(+), 14 deletions(-) create mode 100644 include/net/net_seq_lock.h diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index a3768cfce914..31bc2cc99bf0 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -489,6 +489,15 @@ static inline void write_seqlock(seqlock_t *sl) __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); diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index 883bb9085f15..3b593cdeb9af 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -6,6 +6,7 @@ #include #include #include +#include struct gnet_stats_basic_cpu { struct gnet_stats_basic_packed bstats; @@ -36,11 +37,11 @@ int gnet_stats_start_copy_compat(struct sk_buff *skb, int type, 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); @@ -60,13 +61,13 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, 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); diff --git a/include/net/net_seq_lock.h b/include/net/net_seq_lock.h new file mode 100644 index 000000000000..a7034298a82a --- /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 diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 483303adf3df..038204c7b05e 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -100,7 +101,7 @@ 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; @@ -135,7 +136,11 @@ static inline bool qdisc_is_running(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) return spin_is_locked(&qdisc->seqlock); +#ifdef CONFIG_PREEMPT_RT_BASE + return spin_is_locked(&qdisc->running.lock) ? true : false; +#else return (raw_read_seqcount(&qdisc->running) & 1) ? true : false; +#endif } static inline bool qdisc_run_begin(struct Qdisc *qdisc) @@ -146,17 +151,27 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc) } else if (qdisc_is_running(qdisc)) { return false; } +#ifdef CONFIG_PREEMPT_RT_BASE + if (try_write_seqlock(&qdisc->running)) + return true; + return false; +#else /* Variant of write_seqcount_begin() telling lockdep a trylock * was attempted. */ 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); +#endif if (qdisc->flags & TCQ_F_NOLOCK) spin_unlock(&qdisc->seqlock); } @@ -475,7 +490,7 @@ static inline spinlock_t *qdisc_root_sleeping_lock(const struct Qdisc *qdisc) 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); diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 752744db11ff..7112e28b4130 100644 --- 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_basic_packed *bstats, 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); @@ -230,7 +230,7 @@ int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, 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); diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index e2fd8baec65f..8bab88738691 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -142,7 +142,7 @@ __gnet_stats_copy_basic_cpu(struct gnet_stats_basic_packed *bstats, } 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) @@ -155,10 +155,10 @@ __gnet_stats_copy_basic(const seqcount_t *running, } 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); @@ -176,7 +176,7 @@ EXPORT_SYMBOL(__gnet_stats_copy_basic); * 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) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index ab57c0ee9923..90d7c875eaf3 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1201,7 +1201,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev, 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) { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index a5262b2ba536..881467d3afb9 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -576,7 +576,11 @@ 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, @@ -877,9 +881,17 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, 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;