This is a note to let you know that I've just added the patch titled
rxrpc: Fix locking issue
to the 5.15-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
rxrpc-fix-locking-issue.patch
and it can be found in the queue-5.15 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 6c69b2ec22827f6af9b763afbd7a393864949492
Author: David Howells <dhowells@xxxxxxxxxx>
Date: Sat May 21 08:45:28 2022 +0100
rxrpc: Fix locking issue
[ Upstream commit ad25f5cb39872ca14bcbe00816ae65c22fe04b89 ]
There's a locking issue with the per-netns list of calls in rxrpc. The
pieces of code that add and remove a call from the list use write_lock()
and the calls procfile uses read_lock() to access it. However, the timer
callback function may trigger a removal by trying to queue a call for
processing and finding that it's already queued - at which point it has a
spare refcount that it has to do something with. Unfortunately, if it puts
the call and this reduces the refcount to 0, the call will be removed from
the list. Unfortunately, since the _bh variants of the locking functions
aren't used, this can deadlock.
================================
WARNING: inconsistent lock state
5.18.0-rc3-build4+ #10 Not tainted
--------------------------------
inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
ksoftirqd/2/25 [HC0[0]:SC1[1]:HE1:SE0] takes:
ffff888107ac4038 (&rxnet->call_lock){+.?.}-{2:2}, at: rxrpc_put_call+0x103/0x14b
{SOFTIRQ-ON-W} state was registered at:
...
Possible unsafe locking scenario:
CPU0
----
lock(&rxnet->call_lock);
<Interrupt>
lock(&rxnet->call_lock);
*** DEADLOCK ***
1 lock held by ksoftirqd/2/25:
#0: ffff8881008ffdb0 ((&call->timer)){+.-.}-{0:0}, at: call_timer_fn+0x5/0x23d
Changes
=======
ver #2)
- Changed to using list_next_rcu() rather than rcu_dereference() directly.
Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
Signed-off-by: David Howells <dhowells@xxxxxxxxxx>
cc: Marc Dionne <marc.dionne@xxxxxxxxxxxx>
cc: linux-afs@xxxxxxxxxxxxxxxxxxx
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 4a2cda04d3e2..b17ee4c4f618 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -947,6 +947,38 @@ struct list_head *seq_list_next(void *v, struct list_head *head, loff_t *ppos)
}
EXPORT_SYMBOL(seq_list_next);
+struct list_head *seq_list_start_rcu(struct list_head *head, loff_t pos)
+{
+ struct list_head *lh;
+
+ list_for_each_rcu(lh, head)
+ if (pos-- == 0)
+ return lh;
+
+ return NULL;
+}
+EXPORT_SYMBOL(seq_list_start_rcu);
+
+struct list_head *seq_list_start_head_rcu(struct list_head *head, loff_t pos)
+{
+ if (!pos)
+ return head;
+
+ return seq_list_start_rcu(head, pos - 1);
+}
+EXPORT_SYMBOL(seq_list_start_head_rcu);
+
+struct list_head *seq_list_next_rcu(void *v, struct list_head *head,
+ loff_t *ppos)
+{
+ struct list_head *lh;
+
+ lh = list_next_rcu((struct list_head *)v);
+ ++*ppos;
+ return lh == head ? NULL : lh;
+}
+EXPORT_SYMBOL(seq_list_next_rcu);
+
/**
* seq_hlist_start - start an iteration of a hlist
* @head: the head of the hlist
diff --git a/include/linux/list.h b/include/linux/list.h
index a119dd1990d4..d206ae93c06d 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -577,6 +577,16 @@ static inline void list_splice_tail_init(struct list_head *list,
#define list_for_each(pos, head) \
for (pos = (head)->next; !list_is_head(pos, (head)); pos = pos->next)
+/**
+ * list_for_each_rcu - Iterate over a list in an RCU-safe fashion
+ * @pos: the &struct list_head to use as a loop cursor.
+ * @head: the head for your list.
+ */
+#define list_for_each_rcu(pos, head) \
+ for (pos = rcu_dereference((head)->next); \
+ !list_is_head(pos, (head)); \
+ pos = rcu_dereference(pos->next))
+
/**
* list_for_each_continue - continue iteration over a list
* @pos: the &struct list_head to use as a loop cursor.
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index 5733890df64f..0b429111f85e 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -261,6 +261,10 @@ extern struct list_head *seq_list_start_head(struct list_head *head,
extern struct list_head *seq_list_next(void *v, struct list_head *head,
loff_t *ppos);
+extern struct list_head *seq_list_start_rcu(struct list_head *head, loff_t pos);
+extern struct list_head *seq_list_start_head_rcu(struct list_head *head, loff_t pos);
+extern struct list_head *seq_list_next_rcu(void *v, struct list_head *head, loff_t *ppos);
+
/*
* Helpers for iteration over hlist_head-s in seq_files
*/
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index dce056adb78c..f2d593e27b64 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -68,7 +68,7 @@ struct rxrpc_net {
struct proc_dir_entry *proc_net; /* Subdir in /proc/net */
u32 epoch; /* Local epoch for detecting local-end reset */
struct list_head calls; /* List of calls active in this namespace */
- rwlock_t call_lock; /* Lock for ->calls */
+ spinlock_t call_lock; /* Lock for ->calls */
atomic_t nr_calls; /* Count of allocated calls */
atomic_t nr_conns;
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 1ae90fb97936..8b24ffbc72ef 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -140,9 +140,9 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
write_unlock(&rx->call_lock);
rxnet = call->rxnet;
- write_lock(&rxnet->call_lock);
- list_add_tail(&call->link, &rxnet->calls);
- write_unlock(&rxnet->call_lock);
+ spin_lock_bh(&rxnet->call_lock);
+ list_add_tail_rcu(&call->link, &rxnet->calls);
+ spin_unlock_bh(&rxnet->call_lock);
b->call_backlog[call_head] = call;
smp_store_release(&b->call_backlog_head, (call_head + 1) & (size - 1));
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 043508fd8d8a..25c9a2cbf048 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -337,9 +337,9 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
write_unlock(&rx->call_lock);
rxnet = call->rxnet;
- write_lock(&rxnet->call_lock);
- list_add_tail(&call->link, &rxnet->calls);
- write_unlock(&rxnet->call_lock);
+ spin_lock_bh(&rxnet->call_lock);
+ list_add_tail_rcu(&call->link, &rxnet->calls);
+ spin_unlock_bh(&rxnet->call_lock);
/* From this point on, the call is protected by its own lock. */
release_sock(&rx->sk);
@@ -631,9 +631,9 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op)
ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
if (!list_empty(&call->link)) {
- write_lock(&rxnet->call_lock);
+ spin_lock_bh(&rxnet->call_lock);
list_del_init(&call->link);
- write_unlock(&rxnet->call_lock);
+ spin_unlock_bh(&rxnet->call_lock);
}
rxrpc_cleanup_call(call);
@@ -705,7 +705,7 @@ void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet)
_enter("");
if (!list_empty(&rxnet->calls)) {
- write_lock(&rxnet->call_lock);
+ spin_lock_bh(&rxnet->call_lock);
while (!list_empty(&rxnet->calls)) {
call = list_entry(rxnet->calls.next,
@@ -720,12 +720,12 @@ void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet)
rxrpc_call_states[call->state],
call->flags, call->events);
- write_unlock(&rxnet->call_lock);
+ spin_unlock_bh(&rxnet->call_lock);
cond_resched();
- write_lock(&rxnet->call_lock);
+ spin_lock_bh(&rxnet->call_lock);
}
- write_unlock(&rxnet->call_lock);
+ spin_unlock_bh(&rxnet->call_lock);
}
atomic_dec(&rxnet->nr_calls);
diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c
index cc7e30733feb..e4d6d432515b 100644
--- a/net/rxrpc/net_ns.c
+++ b/net/rxrpc/net_ns.c
@@ -50,7 +50,7 @@ static __net_init int rxrpc_init_net(struct net *net)
rxnet->epoch |= RXRPC_RANDOM_EPOCH;
INIT_LIST_HEAD(&rxnet->calls);
- rwlock_init(&rxnet->call_lock);
+ spin_lock_init(&rxnet->call_lock);
atomic_set(&rxnet->nr_calls, 1);
atomic_set(&rxnet->nr_conns, 1);
diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index e2f990754f88..5a67955cc00f 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -26,29 +26,23 @@ static const char *const rxrpc_conn_states[RXRPC_CONN__NR_STATES] = {
*/
static void *rxrpc_call_seq_start(struct seq_file *seq, loff_t *_pos)
__acquires(rcu)
- __acquires(rxnet->call_lock)
{
struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
rcu_read_lock();
- read_lock(&rxnet->call_lock);
- return seq_list_start_head(&rxnet->calls, *_pos);
+ return seq_list_start_head_rcu(&rxnet->calls, *_pos);
}
static void *rxrpc_call_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
- return seq_list_next(v, &rxnet->calls, pos);
+ return seq_list_next_rcu(v, &rxnet->calls, pos);
}
static void rxrpc_call_seq_stop(struct seq_file *seq, void *v)
- __releases(rxnet->call_lock)
__releases(rcu)
{
- struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
-
- read_unlock(&rxnet->call_lock);
rcu_read_unlock();
}
