mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
* [PATCH batadv-next v3] batman-adv: tt: batch BH re-enable during TT hash walks
@ 2026-11-08  0:01 Ömer Mete Kaya
  2026-11-08  7:35 ` Sven Eckelmann
  0 siblings, 1 reply; 3+ messages in thread
From: Ömer Mete Kaya @ 2026-11-08  0:01 UTC (permalink / raw)
  To: sven, marek.lindner, sw, antonio
  Cc: b.a.t.m.a.n, netdev, linux-kernel, davem,
	syzbot+61b202fdc410840f0198, Ömer Mete Kaya

Each spin_unlock_bh() re-enables bottom halves and, when softirqs are
pending, processes them inline before returning. During a 1024-bucket
TT hash walk under network load, the purge worker can be repeatedly
interrupted by inline softirq processing at every bucket boundary.

Replace per-bucket spin_lock_bh()/spin_unlock_bh() with an outer
local_bh_disable(), inner spin_lock()/spin_unlock(), and periodic
re-enable points via batadv_hash_bh_resched(). The helper re-enables
BH and calls cond_resched() every BATADV_HASH_BH_BUDGET (64) buckets.
The total softirq work is unchanged, but BH state transitions drop
from 1024 to ~16 per walk, reducing how often the purge loop is
interrupted.

The cond_resched() provides a voluntary preemption point on
non-PREEMPT kernels. Functions called under a spinlock or from
non-sleepable contexts cannot yield; these use the outer
local_bh_disable()/local_bh_enable() conversion without
batadv_hash_bh_resched().

The five converted hash-walking functions are:

  batadv_tt_local_purge():
    Accepts a new @may_sleep parameter. From workqueue context
    (batadv_tt_purge), may_sleep=true allows periodic yielding.
    From batadv_tt_local_resize_to_mtu(), may_sleep=false because
    the caller holds tt.commit_lock.

  batadv_tt_global_del_orig():
    Called from multiple contexts including under spinlocks
    (batadv_purge_orig_ref). Cannot yield. Converts to outer
    local_bh_disable()/local_bh_enable() with inner spin_lock()/
    spin_unlock() but does not use batadv_hash_bh_resched().

  batadv_tt_global_purge():
    Called from workqueue context; yields every 64 buckets.

  batadv_tt_local_transition_new():
  batadv_tt_local_purge_pending_clients():
    Called under tt.commit_lock. Convert to outer local_bh_disable()/
    local_bh_enable() with inner spin_lock()/spin_unlock() but do
    not use batadv_hash_bh_resched().

On PREEMPT_RT, local_bh_disable() maps to migrate_disable() and
softirqs run in dedicated kthreads, so the batching has no effect
on softirq latency but the reduced BH transition overhead still
applies.

Reported-by: syzbot+61b202fdc410840f0198@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=61b202fdc410840f0198
Signed-off-by: Ömer Mete Kaya <omermetekaya0@gmail.com>
---
Changes in v3:
  - Remove batadv_hash_bh_resched() from batadv_tt_global_del_orig():
    called under spinlocks (e.g. batadv_purge_orig_ref).
    Convert to outer local_bh_disable()/local_bh_enable() with
    inner spin_lock()/spin_unlock() only, like the commit_lock paths.
  - Fix reverse christmas tree ordering in batadv_tt_global_purge()
  - Fix Closes: URL (remove backslash escaping)

 net/batman-adv/hash.h              | 30 +++++++++++++++++++
 net/batman-adv/translation-table.c | 48 ++++++++++++++++++++++--------
 2 files changed, 65 insertions(+), 13 deletions(-)

diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h
index 5d9a5ab..cf3ef70 100644
--- a/net/batman-adv/hash.h
+++ b/net/batman-adv/hash.h
@@ -10,10 +10,12 @@
 #include "main.h"

 #include <linux/atomic.h>
+#include <linux/bottom_half.h>
 #include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/lockdep.h>
 #include <linux/rculist.h>
+#include <linux/sched.h>
 #include <linux/spinlock.h>
 #include <linux/stddef.h>
 #include <linux/types.h>
@@ -167,4 +169,32 @@ static inline void *batadv_hash_remove(struct batadv_hashtable *hash,
 	return data_save;
 }

+/* work which can be done in a hash walk before BH gets re-enabled */
+#define BATADV_HASH_BH_BUDGET 64
+
+/**
+ * batadv_hash_bh_resched() - re-enable BH after the work budget is used up
+ * @buckets_done: buckets processed since BH was disabled, reset when BH is
+ *  re-enabled
+ *
+ * A walk over all buckets of a hash disables BH only once instead of
+ * re-enabling it after each bucket. Otherwise, pending softirqs would be
+ * processed inline after each bucket. When @buckets_done reached
+ * BATADV_HASH_BH_BUDGET, BH is re-enabled to run the pending softirqs and to
+ * give other tasks a chance to run.
+ *
+ * Must be called with BH disabled, without any spinlock held and from a
+ * context which is allowed to sleep.
+ */
+static inline void batadv_hash_bh_resched(u32 *buckets_done)
+{
+	if (*buckets_done < BATADV_HASH_BH_BUDGET)
+		return;
+
+	local_bh_enable();
+	cond_resched();
+	local_bh_disable();
+	*buckets_done = 0;
+}
+
 #endif /* _NET_BATMAN_ADV_HASH_H_ */
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index b9407ad..ebeb486 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -36,6 +36,7 @@
 #include <linux/overflow.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
+#include <linux/sched.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -1892,23 +1893,32 @@ static void batadv_tt_local_purge_list(struct batadv_priv *bat_priv,
  * @bat_priv: the bat priv with all the mesh interface information
  * @timeout: parameter deciding whether a given tt local entry is considered
  *  inactive or not
+ * @may_sleep: if true, periodically re-enable softirqs and yield the CPU.
+ *  Must be false when called with spinlocks held.
  */
 static void batadv_tt_local_purge(struct batadv_priv *bat_priv,
-				  int timeout)
+				  int timeout, bool may_sleep)
 {
 	spinlock_t *list_lock; /* protects write access to the hash lists */
 	struct batadv_hashtable *hash = bat_priv->tt.local_hash;
 	struct hlist_head *head;
+	u32 buckets_done = 0;
 	u32 i;

+	local_bh_disable();
 	for (i = 0; i < hash->size; i++) {
 		head = &hash->table[i];
 		list_lock = &hash->list_locks[i];

-		spin_lock_bh(list_lock);
+		spin_lock(list_lock);
 		batadv_tt_local_purge_list(bat_priv, head, timeout);
-		spin_unlock_bh(list_lock);
+		spin_unlock(list_lock);
+		buckets_done++;
+
+		if (may_sleep)
+			batadv_hash_bh_resched(&buckets_done);
 	}
+	local_bh_enable();
 }

 /**
@@ -2887,11 +2897,12 @@ void batadv_tt_global_del_orig(struct batadv_priv *bat_priv,
 	if (!hash)
 		return;

+	local_bh_disable();
 	for (i = 0; i < hash->size; i++) {
 		head = &hash->table[i];
 		list_lock = &hash->list_locks[i];

-		spin_lock_bh(list_lock);
+		spin_lock(list_lock);
 		hlist_for_each_entry_safe(tt_common_entry, safe,
 					  head, hash_entry) {
 			/* remove only matching entries */
@@ -2916,8 +2927,9 @@ void batadv_tt_global_del_orig(struct batadv_priv *bat_priv,
 				batadv_tt_global_entry_put(tt_global);
 			}
 		}
-		spin_unlock_bh(list_lock);
+		spin_unlock(list_lock);
 	}
+	local_bh_enable();
 	clear_bit(BATADV_ORIG_CAPA_HAS_TT, &orig_node->capa_initialized);
 }

@@ -2969,14 +2981,16 @@ static void batadv_tt_global_purge(struct batadv_priv *bat_priv)
 	struct batadv_tt_global_entry *tt_global;
 	struct hlist_node *node_tmp;
 	struct hlist_head *head;
+	u32 buckets_done = 0;
 	char *msg = NULL;
 	u32 i;

+	local_bh_disable();
 	for (i = 0; i < hash->size; i++) {
 		head = &hash->table[i];
 		list_lock = &hash->list_locks[i];

-		spin_lock_bh(list_lock);
+		spin_lock(list_lock);
 		hlist_for_each_entry_safe(tt_common, node_tmp, head,
 					  hash_entry) {
 			tt_global = container_of(tt_common,
@@ -2996,8 +3010,12 @@ static void batadv_tt_global_purge(struct batadv_priv *bat_priv)

 			batadv_tt_global_entry_put(tt_global);
 		}
-		spin_unlock_bh(list_lock);
+		spin_unlock(list_lock);
+		buckets_done++;
+
+		batadv_hash_bh_resched(&buckets_done);
 	}
+	local_bh_enable();
 }

 /**
@@ -4402,7 +4420,7 @@ static void batadv_tt_purge(struct work_struct *work)
 	priv_tt = container_of(delayed_work, struct batadv_priv_tt, work);
 	bat_priv = container_of(priv_tt, struct batadv_priv, tt);

-	batadv_tt_local_purge(bat_priv, BATADV_TT_LOCAL_TIMEOUT);
+	batadv_tt_local_purge(bat_priv, BATADV_TT_LOCAL_TIMEOUT, true);
 	batadv_tt_global_purge(bat_priv);
 	batadv_tt_req_purge(bat_priv);
 	batadv_tt_roam_purge(bat_priv);
@@ -4449,11 +4467,12 @@ static void batadv_tt_local_transition_new(struct batadv_priv *bat_priv)
 	if (!hash)
 		return;

+	local_bh_disable();
 	for (i = 0; i < hash->size; i++) {
 		head = &hash->table[i];
 		list_lock = &hash->list_locks[i];

-		spin_lock_bh(list_lock);
+		spin_lock(list_lock);
 		hlist_for_each_entry(tt_common_entry, head, hash_entry) {
 			bool cont = false;

@@ -4472,8 +4491,9 @@ static void batadv_tt_local_transition_new(struct batadv_priv *bat_priv)
 			batadv_tt_local_size_inc(bat_priv,
 						 tt_common_entry->key.vid);
 		}
-		spin_unlock_bh(list_lock);
+		spin_unlock(list_lock);
 	}
+	local_bh_enable();
 }

 /**
@@ -4497,11 +4517,12 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv)
 	if (!hash)
 		return;

+	local_bh_disable();
 	for (i = 0; i < hash->size; i++) {
 		head = &hash->table[i];
 		list_lock = &hash->list_locks[i];

-		spin_lock_bh(list_lock);
+		spin_lock(list_lock);
 		hlist_for_each_entry_safe(tt_common, node_tmp, head,
 					  hash_entry) {
 			bool cont = false;
@@ -4536,8 +4557,9 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv)

 			batadv_tt_local_entry_put(tt_local);
 		}
-		spin_unlock_bh(list_lock);
+		spin_unlock(list_lock);
 	}
+	local_bh_enable();
 }

 /**
@@ -4839,7 +4861,7 @@ void batadv_tt_local_resize_to_mtu(struct net_device *mesh_iface)
 		if (size_max >= table_size)
 			break;

-		batadv_tt_local_purge(bat_priv, timeout);
+		batadv_tt_local_purge(bat_priv, timeout, false);
 		batadv_tt_local_purge_pending_clients(bat_priv);

 		timeout /= 2;
--
2.56.0


^ permalink raw reply	[flat|nested] 3+ messages in thread
end of thread, other threads:[~2026-11-08  8:01 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2026-11-08  0:01 [PATCH batadv-next v3] batman-adv: tt: batch BH re-enable during TT hash walks Ömer Mete Kaya
2026-11-08  7:35 ` Sven Eckelmann
2026-11-08  8:01   ` [syzbot] [arm?] BUG: workqueue lockup in batadv_tt_purge syzbot

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®