[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <20230711115848.2701559-1-pulehui@huaweicloud.com>
Date: Tue, 11 Jul 2023 19:58:48 +0800
From: Pu Lehui <pulehui@...weicloud.com>
To: bpf@...r.kernel.org, netdev@...r.kernel.org,
linux-kernel@...r.kernel.org
Cc: Alexei Starovoitov <ast@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>,
Andrii Nakryiko <andrii@...nel.org>,
"David S. Miller" <davem@...emloft.net>,
Jakub Kicinski <kuba@...nel.org>,
Jesper Dangaard Brouer <hawk@...nel.org>,
John Fastabend <john.fastabend@...il.com>,
Martin KaFai Lau <martin.lau@...ux.dev>,
Song Liu <song@...nel.org>, Yonghong Song <yhs@...com>,
KP Singh <kpsingh@...nel.org>,
Stanislav Fomichev <sdf@...gle.com>,
Hao Luo <haoluo@...gle.com>, Jiri Olsa <jolsa@...nel.org>,
Xu Kuohai <xukuohai@...wei.com>, Pu Lehui <pulehui@...wei.com>,
Pu Lehui <pulehui@...weicloud.com>
Subject: [PATCH bpf] bpf: cpumap: Fix memory leak in cpu_map_update_elem
From: Pu Lehui <pulehui@...wei.com>
Syzkaller reported a memory leak as follows:
BUG: memory leak
unreferenced object 0xff110001198ef748 (size 192):
comm "syz-executor.3", pid 17672, jiffies 4298118891 (age 9.906s)
hex dump (first 32 bytes):
00 00 00 00 4a 19 00 00 80 ad e3 e4 fe ff c0 00 ....J...........
00 b2 d3 0c 01 00 11 ff 28 f5 8e 19 01 00 11 ff ........(.......
backtrace:
[<ffffffffadd28087>] __cpu_map_entry_alloc+0xf7/0xb00
[<ffffffffadd28d8e>] cpu_map_update_elem+0x2fe/0x3d0
[<ffffffffadc6d0fd>] bpf_map_update_value.isra.0+0x2bd/0x520
[<ffffffffadc7349b>] map_update_elem+0x4cb/0x720
[<ffffffffadc7d983>] __se_sys_bpf+0x8c3/0xb90
[<ffffffffb029cc80>] do_syscall_64+0x30/0x40
[<ffffffffb0400099>] entry_SYSCALL_64_after_hwframe+0x61/0xc6
BUG: memory leak
unreferenced object 0xff110001198ef528 (size 192):
comm "syz-executor.3", pid 17672, jiffies 4298118891 (age 9.906s)
hex dump (first 32 bytes):
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
backtrace:
[<ffffffffadd281f0>] __cpu_map_entry_alloc+0x260/0xb00
[<ffffffffadd28d8e>] cpu_map_update_elem+0x2fe/0x3d0
[<ffffffffadc6d0fd>] bpf_map_update_value.isra.0+0x2bd/0x520
[<ffffffffadc7349b>] map_update_elem+0x4cb/0x720
[<ffffffffadc7d983>] __se_sys_bpf+0x8c3/0xb90
[<ffffffffb029cc80>] do_syscall_64+0x30/0x40
[<ffffffffb0400099>] entry_SYSCALL_64_after_hwframe+0x61/0xc6
BUG: memory leak
unreferenced object 0xff1100010fd93d68 (size 8):
comm "syz-executor.3", pid 17672, jiffies 4298118891 (age 9.906s)
hex dump (first 8 bytes):
00 00 00 00 00 00 00 00 ........
backtrace:
[<ffffffffade5db3e>] kvmalloc_node+0x11e/0x170
[<ffffffffadd28280>] __cpu_map_entry_alloc+0x2f0/0xb00
[<ffffffffadd28d8e>] cpu_map_update_elem+0x2fe/0x3d0
[<ffffffffadc6d0fd>] bpf_map_update_value.isra.0+0x2bd/0x520
[<ffffffffadc7349b>] map_update_elem+0x4cb/0x720
[<ffffffffadc7d983>] __se_sys_bpf+0x8c3/0xb90
[<ffffffffb029cc80>] do_syscall_64+0x30/0x40
[<ffffffffb0400099>] entry_SYSCALL_64_after_hwframe+0x61/0xc6
In the cpu_map_update_elem flow, when kthread_stop is called before
calling the threadfn of rcpu->kthread, since the KTHREAD_SHOULD_STOP bit
of kthread has been set by kthread_stop, the threadfn of rcpu->kthread
will never be executed, and rcpu->refcnt will never be 0, which will
lead to the allocated rcpu, rcpu->queue and rcpu->queue->queue cannot be
released.
Calling kthread_stop before executing kthread's threadfn will return
-EINTR. We can complete the release of memory resources in this state.
Fixes: 6710e1126934 ("bpf: introduce new bpf cpu map type BPF_MAP_TYPE_CPUMAP")
Signed-off-by: Pu Lehui <pulehui@...wei.com>
---
kernel/bpf/cpumap.c | 40 ++++++++++++++++++++++++----------------
1 file changed, 24 insertions(+), 16 deletions(-)
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 8a33e8747a0e..6ae02be7a48e 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -122,22 +122,6 @@ static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
atomic_inc(&rcpu->refcnt);
}
-/* called from workqueue, to workaround syscall using preempt_disable */
-static void cpu_map_kthread_stop(struct work_struct *work)
-{
- struct bpf_cpu_map_entry *rcpu;
-
- rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq);
-
- /* Wait for flush in __cpu_map_entry_free(), via full RCU barrier,
- * as it waits until all in-flight call_rcu() callbacks complete.
- */
- rcu_barrier();
-
- /* kthread_stop will wake_up_process and wait for it to complete */
- kthread_stop(rcpu->kthread);
-}
-
static void __cpu_map_ring_cleanup(struct ptr_ring *ring)
{
/* The tear-down procedure should have made sure that queue is
@@ -165,6 +149,30 @@ static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
}
}
+/* called from workqueue, to workaround syscall using preempt_disable */
+static void cpu_map_kthread_stop(struct work_struct *work)
+{
+ struct bpf_cpu_map_entry *rcpu;
+ int err;
+
+ rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq);
+
+ /* Wait for flush in __cpu_map_entry_free(), via full RCU barrier,
+ * as it waits until all in-flight call_rcu() callbacks complete.
+ */
+ rcu_barrier();
+
+ /* kthread_stop will wake_up_process and wait for it to complete */
+ err = kthread_stop(rcpu->kthread);
+ if (err) {
+ /* kthread_stop may be called before cpu_map_kthread_run
+ * is executed, so we need to release the memory related
+ * to rcpu.
+ */
+ put_cpu_map_entry(rcpu);
+ }
+}
+
static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu,
struct list_head *listp,
struct xdp_cpumap_stats *stats)
--
2.25.1
Powered by blists - more mailing lists