From 81c5bd0e861a32463f3d9408967fecf5f1a4ab09 Mon Sep 17 00:00:00 2001 From: meganz009 Date: Fri, 9 Jun 2023 11:43:18 +0800 Subject: [PATCH 1/3] debugobjects: Make RT aware commit 0afdb35f56928f5bde82e37d5a90197756bbbc21 upstream. Avoid filling the pool / allocating memory with irqs off(). Signed-off-by: Thomas Gleixner --- lib/debugobjects.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 14afeeb7d6ef..e28481c402ae 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -376,7 +376,10 @@ __debug_object_init(void *addr, struct debug_obj_descr *descr, int onstack) struct debug_obj *obj; unsigned long flags; - fill_pool(); +#ifdef CONFIG_PREEMPT_RT_FULL + if (preempt_count() == 0 && !irqs_disabled()) +#endif + fill_pool(); db = get_bucket((unsigned long) addr); -- Gitee From a70712694f34d518efd38254fa5c7f0d748ff651 Mon Sep 17 00:00:00 2001 From: meganz009 Date: Fri, 9 Jun 2023 11:43:36 +0800 Subject: [PATCH 2/3] seqlock: Prevent rt starvation commit 77d71203cae68a6d582b3c05f375bd68caea10e8 upstream. 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. Thanks to Al Viro for distangling some VFS code to make that possible. Nicholas Mc Guire: - spin_lock+unlock => spin_unlock_wait - __write_seqcount_begin => __raw_write_seqcount_begin Signed-off-by: Thomas Gleixner --- include/linux/seqlock.h | 57 ++++++++++++++++++++++++++++++++--------- include/net/neighbour.h | 6 ++--- 2 files changed, 48 insertions(+), 15 deletions(-) diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index bcf4cf26b8c8..689ed53016c7 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -221,20 +221,30 @@ static inline int read_seqcount_retry(const seqcount_t *s, unsigned start) return __read_seqcount_retry(s, start); } - - -static inline void raw_write_seqcount_begin(seqcount_t *s) +static inline void __raw_write_seqcount_begin(seqcount_t *s) { s->sequence++; smp_wmb(); } -static inline void raw_write_seqcount_end(seqcount_t *s) +static inline void raw_write_seqcount_begin(seqcount_t *s) +{ + preempt_disable_rt(); + __raw_write_seqcount_begin(s); +} + +static inline void __raw_write_seqcount_end(seqcount_t *s) { smp_wmb(); s->sequence++; } +static inline void raw_write_seqcount_end(seqcount_t *s) +{ + __raw_write_seqcount_end(s); + preempt_enable_rt(); +} + /** * raw_write_seqcount_barrier - do a seq write barrier * @s: pointer to seqcount_t @@ -428,10 +438,33 @@ 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 = READ_ONCE(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_unlock_wait(&sl->lock); + goto repeat; + } + smp_rmb(); + return ret; +} +#endif static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) { @@ -446,36 +479,36 @@ 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); + __raw_write_seqcount_begin(&sl->seqcount); } static inline void write_sequnlock(seqlock_t *sl) { - write_seqcount_end(&sl->seqcount); + __raw_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); + __raw_write_seqcount_begin(&sl->seqcount); } static inline void write_sequnlock_bh(seqlock_t *sl) { - write_seqcount_end(&sl->seqcount); + __raw_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); + __raw_write_seqcount_begin(&sl->seqcount); } static inline void write_sequnlock_irq(seqlock_t *sl) { - write_seqcount_end(&sl->seqcount); + __raw_write_seqcount_end(&sl->seqcount); spin_unlock_irq(&sl->lock); } @@ -484,7 +517,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl) unsigned long flags; spin_lock_irqsave(&sl->lock, flags); - write_seqcount_begin(&sl->seqcount); + __raw_write_seqcount_begin(&sl->seqcount); return flags; } @@ -494,7 +527,7 @@ 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); + __raw_write_seqcount_end(&sl->seqcount); spin_unlock_irqrestore(&sl->lock, flags); } diff --git a/include/net/neighbour.h b/include/net/neighbour.h index c84807c1c5bd..08d4700515da 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -451,7 +451,7 @@ static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb) } #endif -static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb) +static inline int neigh_hh_output(struct hh_cache *hh, struct sk_buff *skb) { unsigned int hh_alen = 0; unsigned int seq; @@ -493,7 +493,7 @@ static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb static inline int neigh_output(struct neighbour *n, struct sk_buff *skb) { - const struct hh_cache *hh = &n->hh; + struct hh_cache *hh = &n->hh; if ((n->nud_state & NUD_CONNECTED) && hh->hh_len) return neigh_hh_output(hh, skb); @@ -534,7 +534,7 @@ 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; -- Gitee From f293c98ff56ae9f1ed45f80ce5e871b362b828fb Mon Sep 17 00:00:00 2001 From: meganz009 Date: Fri, 9 Jun 2023 11:43:50 +0800 Subject: [PATCH 3/3] sunrpc: Make svc_xprt_do_enqueue() use get_cpu_light() commit 9d2425d84597125b000c785903c4afd36f00673c upstream. |BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:915 |in_atomic(): 1, irqs_disabled(): 0, pid: 3194, name: rpc.nfsd |Preemption disabled at:[] svc_xprt_received+0x4b/0xc0 [sunrpc] |CPU: 6 PID: 3194 Comm: rpc.nfsd Not tainted 3.18.7-rt1 #9 |Hardware name: MEDION MS-7848/MS-7848, BIOS M7848W08.404 11/06/2014 | ffff880409630000 ffff8800d9a33c78 ffffffff815bdeb5 0000000000000002 | 0000000000000000 ffff8800d9a33c98 ffffffff81073c86 ffff880408dd6008 | ffff880408dd6000 ffff8800d9a33cb8 ffffffff815c3d84 ffff88040b3ac000 |Call Trace: | [] dump_stack+0x4f/0x9e | [] __might_sleep+0xe6/0x150 | [] rt_spin_lock+0x24/0x50 | [] svc_xprt_do_enqueue+0x80/0x230 [sunrpc] | [] svc_xprt_received+0x4b/0xc0 [sunrpc] | [] svc_add_new_perm_xprt+0x6d/0x80 [sunrpc] | [] svc_addsock+0x143/0x200 [sunrpc] | [] write_ports+0x28c/0x340 [nfsd] | [] nfsctl_transaction_write+0x4c/0x80 [nfsd] | [] vfs_write+0xb3/0x1d0 | [] SyS_write+0x49/0xb0 | [] system_call_fastpath+0x16/0x1b Signed-off-by: Mike Galbraith Signed-off-by: Sebastian Andrzej Siewior --- net/sunrpc/svc_xprt.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 6cf0fd37cbf0..48c0a0b90946 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -393,7 +393,7 @@ void svc_xprt_do_enqueue(struct svc_xprt *xprt) if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags)) return; - cpu = get_cpu(); + cpu = get_cpu_light(); pool = svc_pool_for_cpu(xprt->xpt_server, cpu); atomic_long_inc(&pool->sp_stats.packets); @@ -417,7 +417,7 @@ void svc_xprt_do_enqueue(struct svc_xprt *xprt) rqstp = NULL; out_unlock: rcu_read_unlock(); - put_cpu(); + put_cpu_light(); trace_svc_xprt_do_enqueue(xprt, rqstp); } EXPORT_SYMBOL_GPL(svc_xprt_do_enqueue); -- Gitee