public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Tejun Heo <tj@kernel.org>
To: torvalds@linux-foundation.org, mingo@redhat.com,
	peterz@infradead.org, juri.lelli@redhat.com,
	vincent.guittot@linaro.org, dietmar.eggemann@arm.com,
	rostedt@goodmis.org, bsegall@google.com, mgorman@suse.de,
	bristot@redhat.com, vschneid@redhat.com, ast@kernel.org,
	daniel@iogearbox.net, andrii@kernel.org, martin.lau@kernel.org,
	joshdon@google.com, brho@google.com, pjt@google.com,
	derkling@google.com, haoluo@google.com, dvernet@meta.com,
	dschatzberg@meta.com, dskarlat@cs.cmu.edu, riel@surriel.com
Cc: linux-kernel@vger.kernel.org, bpf@vger.kernel.org,
	kernel-team@meta.com, Tejun Heo <tj@kernel.org>
Subject: [PATCH 01/31] rhashtable: Allow rhashtable to be used from irq-safe contexts
Date: Tue, 29 Nov 2022 22:22:43 -1000	[thread overview]
Message-ID: <20221130082313.3241517-2-tj@kernel.org> (raw)
In-Reply-To: <20221130082313.3241517-1-tj@kernel.org>

rhashtable currently only does bh-safe synchronization making it impossible
to use from irq-safe contexts. Switch it to use irq-safe synchronization to
remove the restriction.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: David Vernet <dvernet@meta.com>
Acked-by: Josh Don <joshdon@google.com>
Acked-by: Hao Luo <haoluo@google.com>
Acked-by: Barret Rhoden <brho@google.com>
---
 include/linux/rhashtable.h | 51 ++++++++++++++++++++++----------------
 lib/rhashtable.c           | 16 +++++++-----
 2 files changed, 39 insertions(+), 28 deletions(-)

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 68dab3e08aad..785fba3464f2 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -324,28 +324,31 @@ static inline struct rhash_lock_head __rcu **rht_bucket_insert(
  */
 
 static inline void rht_lock(struct bucket_table *tbl,
-			    struct rhash_lock_head __rcu **bkt)
+			    struct rhash_lock_head __rcu **bkt,
+			    unsigned long *flags)
 {
-	local_bh_disable();
+	local_irq_save(*flags);
 	bit_spin_lock(0, (unsigned long *)bkt);
 	lock_map_acquire(&tbl->dep_map);
 }
 
 static inline void rht_lock_nested(struct bucket_table *tbl,
 				   struct rhash_lock_head __rcu **bucket,
-				   unsigned int subclass)
+				   unsigned int subclass,
+				   unsigned long *flags)
 {
-	local_bh_disable();
+	local_irq_save(*flags);
 	bit_spin_lock(0, (unsigned long *)bucket);
 	lock_acquire_exclusive(&tbl->dep_map, subclass, 0, NULL, _THIS_IP_);
 }
 
 static inline void rht_unlock(struct bucket_table *tbl,
-			      struct rhash_lock_head __rcu **bkt)
+			      struct rhash_lock_head __rcu **bkt,
+			      unsigned long *flags)
 {
 	lock_map_release(&tbl->dep_map);
 	bit_spin_unlock(0, (unsigned long *)bkt);
-	local_bh_enable();
+	local_irq_restore(*flags);
 }
 
 static inline struct rhash_head *__rht_ptr(
@@ -393,7 +396,8 @@ static inline void rht_assign_locked(struct rhash_lock_head __rcu **bkt,
 
 static inline void rht_assign_unlock(struct bucket_table *tbl,
 				     struct rhash_lock_head __rcu **bkt,
-				     struct rhash_head *obj)
+				     struct rhash_head *obj,
+				     unsigned long *flags)
 {
 	if (rht_is_a_nulls(obj))
 		obj = NULL;
@@ -401,7 +405,7 @@ static inline void rht_assign_unlock(struct bucket_table *tbl,
 	rcu_assign_pointer(*bkt, (void *)obj);
 	preempt_enable();
 	__release(bitlock);
-	local_bh_enable();
+	local_irq_restore(*flags);
 }
 
 /**
@@ -706,6 +710,7 @@ static inline void *__rhashtable_insert_fast(
 	struct rhash_head __rcu **pprev;
 	struct bucket_table *tbl;
 	struct rhash_head *head;
+	unsigned long flags;
 	unsigned int hash;
 	int elasticity;
 	void *data;
@@ -720,11 +725,11 @@ static inline void *__rhashtable_insert_fast(
 	if (!bkt)
 		goto out;
 	pprev = NULL;
-	rht_lock(tbl, bkt);
+	rht_lock(tbl, bkt, &flags);
 
 	if (unlikely(rcu_access_pointer(tbl->future_tbl))) {
 slow_path:
-		rht_unlock(tbl, bkt);
+		rht_unlock(tbl, bkt, &flags);
 		rcu_read_unlock();
 		return rhashtable_insert_slow(ht, key, obj);
 	}
@@ -756,9 +761,9 @@ static inline void *__rhashtable_insert_fast(
 		RCU_INIT_POINTER(list->rhead.next, head);
 		if (pprev) {
 			rcu_assign_pointer(*pprev, obj);
-			rht_unlock(tbl, bkt);
+			rht_unlock(tbl, bkt, &flags);
 		} else
-			rht_assign_unlock(tbl, bkt, obj);
+			rht_assign_unlock(tbl, bkt, obj, &flags);
 		data = NULL;
 		goto out;
 	}
@@ -785,7 +790,7 @@ static inline void *__rhashtable_insert_fast(
 	}
 
 	atomic_inc(&ht->nelems);
-	rht_assign_unlock(tbl, bkt, obj);
+	rht_assign_unlock(tbl, bkt, obj, &flags);
 
 	if (rht_grow_above_75(ht, tbl))
 		schedule_work(&ht->run_work);
@@ -797,7 +802,7 @@ static inline void *__rhashtable_insert_fast(
 	return data;
 
 out_unlock:
-	rht_unlock(tbl, bkt);
+	rht_unlock(tbl, bkt, &flags);
 	goto out;
 }
 
@@ -991,6 +996,7 @@ static inline int __rhashtable_remove_fast_one(
 	struct rhash_lock_head __rcu **bkt;
 	struct rhash_head __rcu **pprev;
 	struct rhash_head *he;
+	unsigned long flags;
 	unsigned int hash;
 	int err = -ENOENT;
 
@@ -999,7 +1005,7 @@ static inline int __rhashtable_remove_fast_one(
 	if (!bkt)
 		return -ENOENT;
 	pprev = NULL;
-	rht_lock(tbl, bkt);
+	rht_lock(tbl, bkt, &flags);
 
 	rht_for_each_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) {
 		struct rhlist_head *list;
@@ -1043,14 +1049,14 @@ static inline int __rhashtable_remove_fast_one(
 
 		if (pprev) {
 			rcu_assign_pointer(*pprev, obj);
-			rht_unlock(tbl, bkt);
+			rht_unlock(tbl, bkt, &flags);
 		} else {
-			rht_assign_unlock(tbl, bkt, obj);
+			rht_assign_unlock(tbl, bkt, obj, &flags);
 		}
 		goto unlocked;
 	}
 
-	rht_unlock(tbl, bkt);
+	rht_unlock(tbl, bkt, &flags);
 unlocked:
 	if (err > 0) {
 		atomic_dec(&ht->nelems);
@@ -1143,6 +1149,7 @@ static inline int __rhashtable_replace_fast(
 	struct rhash_lock_head __rcu **bkt;
 	struct rhash_head __rcu **pprev;
 	struct rhash_head *he;
+	unsigned long flags;
 	unsigned int hash;
 	int err = -ENOENT;
 
@@ -1158,7 +1165,7 @@ static inline int __rhashtable_replace_fast(
 		return -ENOENT;
 
 	pprev = NULL;
-	rht_lock(tbl, bkt);
+	rht_lock(tbl, bkt, &flags);
 
 	rht_for_each_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) {
 		if (he != obj_old) {
@@ -1169,15 +1176,15 @@ static inline int __rhashtable_replace_fast(
 		rcu_assign_pointer(obj_new->next, obj_old->next);
 		if (pprev) {
 			rcu_assign_pointer(*pprev, obj_new);
-			rht_unlock(tbl, bkt);
+			rht_unlock(tbl, bkt, &flags);
 		} else {
-			rht_assign_unlock(tbl, bkt, obj_new);
+			rht_assign_unlock(tbl, bkt, obj_new, &flags);
 		}
 		err = 0;
 		goto unlocked;
 	}
 
-	rht_unlock(tbl, bkt);
+	rht_unlock(tbl, bkt, &flags);
 
 unlocked:
 	return err;
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index e12bbfb240b8..9781572b2f31 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -231,6 +231,7 @@ static int rhashtable_rehash_one(struct rhashtable *ht,
 	struct rhash_head *head, *next, *entry;
 	struct rhash_head __rcu **pprev = NULL;
 	unsigned int new_hash;
+	unsigned long flags;
 
 	if (new_tbl->nest)
 		goto out;
@@ -253,13 +254,14 @@ static int rhashtable_rehash_one(struct rhashtable *ht,
 
 	new_hash = head_hashfn(ht, new_tbl, entry);
 
-	rht_lock_nested(new_tbl, &new_tbl->buckets[new_hash], SINGLE_DEPTH_NESTING);
+	rht_lock_nested(new_tbl, &new_tbl->buckets[new_hash],
+			SINGLE_DEPTH_NESTING, &flags);
 
 	head = rht_ptr(new_tbl->buckets + new_hash, new_tbl, new_hash);
 
 	RCU_INIT_POINTER(entry->next, head);
 
-	rht_assign_unlock(new_tbl, &new_tbl->buckets[new_hash], entry);
+	rht_assign_unlock(new_tbl, &new_tbl->buckets[new_hash], entry, &flags);
 
 	if (pprev)
 		rcu_assign_pointer(*pprev, next);
@@ -276,18 +278,19 @@ static int rhashtable_rehash_chain(struct rhashtable *ht,
 {
 	struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
 	struct rhash_lock_head __rcu **bkt = rht_bucket_var(old_tbl, old_hash);
+	unsigned long flags;
 	int err;
 
 	if (!bkt)
 		return 0;
-	rht_lock(old_tbl, bkt);
+	rht_lock(old_tbl, bkt, &flags);
 
 	while (!(err = rhashtable_rehash_one(ht, bkt, old_hash)))
 		;
 
 	if (err == -ENOENT)
 		err = 0;
-	rht_unlock(old_tbl, bkt);
+	rht_unlock(old_tbl, bkt, &flags);
 
 	return err;
 }
@@ -590,6 +593,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key,
 	struct bucket_table *new_tbl;
 	struct bucket_table *tbl;
 	struct rhash_lock_head __rcu **bkt;
+	unsigned long flags;
 	unsigned int hash;
 	void *data;
 
@@ -607,7 +611,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key,
 			new_tbl = rht_dereference_rcu(tbl->future_tbl, ht);
 			data = ERR_PTR(-EAGAIN);
 		} else {
-			rht_lock(tbl, bkt);
+			rht_lock(tbl, bkt, &flags);
 			data = rhashtable_lookup_one(ht, bkt, tbl,
 						     hash, key, obj);
 			new_tbl = rhashtable_insert_one(ht, bkt, tbl,
@@ -615,7 +619,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key,
 			if (PTR_ERR(new_tbl) != -EEXIST)
 				data = ERR_CAST(new_tbl);
 
-			rht_unlock(tbl, bkt);
+			rht_unlock(tbl, bkt, &flags);
 		}
 	} while (!IS_ERR_OR_NULL(new_tbl));
 
-- 
2.38.1


  reply	other threads:[~2022-11-30  8:23 UTC|newest]

Thread overview: 92+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-11-30  8:22 [PATCHSET RFC] sched: Implement BPF extensible scheduler class Tejun Heo
2022-11-30  8:22 ` Tejun Heo [this message]
2022-11-30 16:35   ` [PATCH 01/31] rhashtable: Allow rhashtable to be used from irq-safe contexts Linus Torvalds
2022-11-30 17:00     ` Tejun Heo
2022-12-06 21:36   ` [PATCH v2 " Tejun Heo
2022-12-09 10:50     ` patchwork-bot+netdevbpf
2022-11-30  8:22 ` [PATCH 02/31] cgroup: Implement cgroup_show_cftypes() Tejun Heo
2022-11-30  8:22 ` [PATCH 03/31] BPF: Add @prog to bpf_struct_ops->check_member() Tejun Heo
2022-11-30  8:22 ` [PATCH 04/31] sched: Allow sched_cgroup_fork() to fail and introduce sched_cancel_fork() Tejun Heo
2022-12-12 11:13   ` Peter Zijlstra
2022-12-12 18:03     ` Tejun Heo
2022-12-12 20:07       ` Peter Zijlstra
2022-12-12 20:12         ` Tejun Heo
2022-11-30  8:22 ` [PATCH 05/31] sched: Add sched_class->reweight_task() Tejun Heo
2022-12-12 11:22   ` Peter Zijlstra
2022-12-12 17:34     ` Tejun Heo
2022-12-12 20:11       ` Peter Zijlstra
2022-12-12 20:15         ` Tejun Heo
2022-11-30  8:22 ` [PATCH 06/31] sched: Add sched_class->switching_to() and expose check_class_changing/changed() Tejun Heo
2022-12-12 11:28   ` Peter Zijlstra
2022-12-12 17:59     ` Tejun Heo
2022-11-30  8:22 ` [PATCH 07/31] sched: Factor out cgroup weight conversion functions Tejun Heo
2022-11-30  8:22 ` [PATCH 08/31] sched: Expose css_tg() and __setscheduler_prio() in kernel/sched/sched.h Tejun Heo
2022-12-12 11:49   ` Peter Zijlstra
2022-12-12 17:47     ` Tejun Heo
2022-11-30  8:22 ` [PATCH 09/31] sched: Enumerate CPU cgroup file types Tejun Heo
2022-11-30  8:22 ` [PATCH 10/31] sched: Add @reason to sched_class->rq_{on|off}line() Tejun Heo
2022-12-12 11:57   ` Peter Zijlstra
2022-12-12 18:06     ` Tejun Heo
2022-11-30  8:22 ` [PATCH 11/31] sched: Add @reason to sched_move_task() Tejun Heo
2022-12-12 12:00   ` Peter Zijlstra
2022-12-12 17:54     ` Tejun Heo
2022-11-30  8:22 ` [PATCH 12/31] sched: Add normal_policy() Tejun Heo
2022-11-30  8:22 ` [PATCH 13/31] sched_ext: Add boilerplate for extensible scheduler class Tejun Heo
2022-11-30  8:22 ` [PATCH 14/31] sched_ext: Implement BPF " Tejun Heo
2022-12-02 17:08   ` Barret Rhoden
2022-12-02 18:01     ` Tejun Heo
2022-12-06 21:42       ` Tejun Heo
2022-12-06 21:44   ` Tejun Heo
2022-12-11 22:33   ` Julia Lawall
2022-12-12  2:15     ` Tejun Heo
2022-12-12  6:03       ` Julia Lawall
2022-12-12  6:08         ` Tejun Heo
2022-12-12 12:31   ` Peter Zijlstra
2022-12-12 20:03     ` Tejun Heo
2022-12-12 12:53   ` Peter Zijlstra
2022-12-12 21:33     ` Tejun Heo
2022-12-13 10:55       ` Peter Zijlstra
2022-12-13 18:12         ` Tejun Heo
2022-12-13 18:40           ` Rik van Riel
2022-12-13 23:20             ` Josh Don
2022-12-13 10:57       ` Peter Zijlstra
2022-12-13 17:32         ` Tejun Heo
2022-11-30  8:22 ` [PATCH 15/31] sched_ext: [TEMPORARY] Add temporary workaround kfunc helpers Tejun Heo
2022-11-30  8:22 ` [PATCH 16/31] sched_ext: Add scx_example_dummy and scx_example_qmap example schedulers Tejun Heo
2022-11-30  8:22 ` [PATCH 17/31] sched_ext: Add sysrq-S which disables the BPF scheduler Tejun Heo
2022-11-30  8:23 ` [PATCH 18/31] sched_ext: Implement runnable task stall watchdog Tejun Heo
2022-11-30  8:23 ` [PATCH 19/31] sched_ext: Allow BPF schedulers to disallow specific tasks from joining SCHED_EXT Tejun Heo
2022-11-30  8:23 ` [PATCH 20/31] sched_ext: Allow BPF schedulers to switch all eligible tasks into sched_ext Tejun Heo
2022-11-30  8:23 ` [PATCH 21/31] sched_ext: Implement scx_bpf_kick_cpu() and task preemption support Tejun Heo
2022-11-30  8:23 ` [PATCH 22/31] sched_ext: Add task state tracking operations Tejun Heo
2022-11-30  8:23 ` [PATCH 23/31] sched_ext: Implement tickless support Tejun Heo
2022-11-30  8:23 ` [PATCH 24/31] sched_ext: Add cgroup support Tejun Heo
2022-11-30  8:23 ` [PATCH 25/31] sched_ext: Implement SCX_KICK_WAIT Tejun Heo
2022-11-30  8:23 ` [PATCH 26/31] sched_ext: Implement sched_ext_ops.cpu_acquire/release() Tejun Heo
2022-11-30  8:23 ` [PATCH 27/31] sched_ext: Implement sched_ext_ops.cpu_online/offline() Tejun Heo
2022-11-30  8:23 ` [PATCH 28/31] sched_ext: Add Documentation/scheduler/sched-ext.rst Tejun Heo
2022-12-12  4:01   ` Bagas Sanjaya
2022-12-12  6:28     ` Tejun Heo
2022-12-12 13:07       ` Bagas Sanjaya
2022-12-12 17:30         ` Tejun Heo
2022-12-12 12:39   ` Peter Zijlstra
2022-12-12 17:16     ` Tejun Heo
2022-11-30  8:23 ` [PATCH 29/31] sched_ext: Add a basic, userland vruntime scheduler Tejun Heo
2022-11-30  8:23 ` [PATCH 30/31] BPF: [TEMPORARY] Nerf BTF scalar value check Tejun Heo
2022-11-30  8:23 ` [PATCH 31/31] sched_ext: Add a rust userspace hybrid example scheduler Tejun Heo
2022-12-12 14:03   ` Peter Zijlstra
2022-12-12 21:05     ` Peter Oskolkov
2022-12-13 11:02       ` Peter Zijlstra
2022-12-13 18:24         ` Peter Oskolkov
2022-12-12 22:00     ` Tejun Heo
2022-12-12 22:18     ` Josh Don
2022-12-13 11:30       ` Peter Zijlstra
2022-12-13 20:33         ` Tejun Heo
2022-12-14  2:00         ` Josh Don
2022-12-12  9:37 ` [PATCHSET RFC] sched: Implement BPF extensible scheduler class Peter Zijlstra
2022-12-12 17:27   ` Tejun Heo
2022-12-12 10:14 ` Peter Zijlstra
2022-12-14  2:11   ` Josh Don
2022-12-14  8:55     ` Peter Zijlstra
2022-12-14 22:23       ` Tejun Heo
2022-12-14 23:20         ` Barret Rhoden

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=20221130082313.3241517-2-tj@kernel.org \
    --to=tj@kernel.org \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=brho@google.com \
    --cc=bristot@redhat.com \
    --cc=bsegall@google.com \
    --cc=daniel@iogearbox.net \
    --cc=derkling@google.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=dschatzberg@meta.com \
    --cc=dskarlat@cs.cmu.edu \
    --cc=dvernet@meta.com \
    --cc=haoluo@google.com \
    --cc=joshdon@google.com \
    --cc=juri.lelli@redhat.com \
    --cc=kernel-team@meta.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=martin.lau@kernel.org \
    --cc=mgorman@suse.de \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=pjt@google.com \
    --cc=riel@surriel.com \
    --cc=rostedt@goodmis.org \
    --cc=torvalds@linux-foundation.org \
    --cc=vincent.guittot@linaro.org \
    --cc=vschneid@redhat.com \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox