| Message ID | 166065637961.4008018.10420960640773607710.stgit@warthog.procyon.org.uk (mailing list archive) |
|---|---|
| State | Changes Requested |
| Delegated to: | Netdev Maintainers |
| Headers | show |
| Series | [net,v2] net: Fix suspicious RCU usage in bpf_sk_reuseport_detach() | expand |
Hi David,
I love your patch! Yet something to improve:
[auto build test ERROR on net/master]
url: https://github.com/intel-lab-lkp/linux/commits/David-Howells/net-Fix-suspicious-RCU-usage-in-bpf_sk_reuseport_detach/20220816-212744
base: https://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git ae806c7805571a9813e41bf6763dd08d0706f4ed
config: nios2-buildonly-randconfig-r001-20220815 (https://download.01.org/0day-ci/archive/20220817/202208171301.3cD4S3Ui-lkp@intel.com/config)
compiler: nios2-linux-gcc (GCC) 12.1.0
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# https://github.com/intel-lab-lkp/linux/commit/fe74fdc1e7fe8aa84006265deb7b55f40bcc8736
git remote add linux-review https://github.com/intel-lab-lkp/linux
git fetch --no-tags linux-review David-Howells/net-Fix-suspicious-RCU-usage-in-bpf_sk_reuseport_detach/20220816-212744
git checkout fe74fdc1e7fe8aa84006265deb7b55f40bcc8736
# save the config file
mkdir build_dir && cp config build_dir/.config
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-12.1.0 make.cross W=1 O=build_dir ARCH=nios2 SHELL=/bin/bash
If you fix the issue, kindly add following tag where applicable
Reported-by: kernel test robot <lkp@intel.com>
All errors (new ones prefixed by >>):
nios2-linux-ld: kernel/bpf/reuseport_array.o: in function `bpf_sk_reuseport_detach':
>> reuseport_array.c:(.text+0x368): undefined reference to `lockdep_is_held'
reuseport_array.c:(.text+0x368): relocation truncated to fit: R_NIOS2_CALL26 against `lockdep_is_held'
`adc3xxx_i2c_remove' referenced in section `.data' of sound/soc/codecs/tlv320adc3xxx.o: defined in discarded section `.exit.text' of sound/soc/codecs/tlv320adc3xxx.o
Hi David,
I love your patch! Yet something to improve:
[auto build test ERROR on net/master]
url: https://github.com/intel-lab-lkp/linux/commits/David-Howells/net-Fix-suspicious-RCU-usage-in-bpf_sk_reuseport_detach/20220816-212744
base: https://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git ae806c7805571a9813e41bf6763dd08d0706f4ed
config: x86_64-rhel-8.3-kvm (https://download.01.org/0day-ci/archive/20220817/202208171521.JiKYmnhP-lkp@intel.com/config)
compiler: gcc-11 (Debian 11.3.0-5) 11.3.0
reproduce (this is a W=1 build):
# https://github.com/intel-lab-lkp/linux/commit/fe74fdc1e7fe8aa84006265deb7b55f40bcc8736
git remote add linux-review https://github.com/intel-lab-lkp/linux
git fetch --no-tags linux-review David-Howells/net-Fix-suspicious-RCU-usage-in-bpf_sk_reuseport_detach/20220816-212744
git checkout fe74fdc1e7fe8aa84006265deb7b55f40bcc8736
# save the config file
mkdir build_dir && cp config build_dir/.config
make W=1 O=build_dir ARCH=x86_64 SHELL=/bin/bash
If you fix the issue, kindly add following tag where applicable
Reported-by: kernel test robot <lkp@intel.com>
All errors (new ones prefixed by >>):
ld: kernel/bpf/reuseport_array.o: in function `bpf_sk_reuseport_detach':
>> kernel/bpf/reuseport_array.c:28: undefined reference to `lockdep_is_held'
vim +28 kernel/bpf/reuseport_array.c
20
21 /* The caller must hold the reuseport_lock */
22 void bpf_sk_reuseport_detach(struct sock *sk)
23 {
24 struct sock __rcu **socks;
25
26 write_lock_bh(&sk->sk_callback_lock);
27 socks = __rcu_dereference_sk_user_data_with_flags_check(
> 28 sk, SK_USER_DATA_BPF, lockdep_is_held(&sk->sk_callback_lock));
29 if (socks) {
30 WRITE_ONCE(sk->sk_user_data, NULL);
31 /*
32 * Do not move this NULL assignment outside of
33 * sk->sk_callback_lock because there is
34 * a race with reuseport_array_free()
35 * which does not hold the reuseport_lock.
36 */
37 RCU_INIT_POINTER(*socks, NULL);
38 }
39 write_unlock_bh(&sk->sk_callback_lock);
40 }
41
diff --git a/include/net/sock.h b/include/net/sock.h index 05a1bbdf5805..6464da28e842 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -578,18 +578,22 @@ static inline bool sk_user_data_is_nocopy(const struct sock *sk) #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data))) /** - * __rcu_dereference_sk_user_data_with_flags - return the pointer + * __rcu_dereference_sk_user_data_with_flags_check - return the pointer * only if argument flags all has been set in sk_user_data. Otherwise * return NULL * * @sk: socket * @flags: flag bits + * @condition: Condition under which non-RCU access may take place + * + * The caller must be holding the RCU read lock */ static inline void * -__rcu_dereference_sk_user_data_with_flags(const struct sock *sk, - uintptr_t flags) +__rcu_dereference_sk_user_data_with_flags_check(const struct sock *sk, + uintptr_t flags, bool condition) { - uintptr_t sk_user_data = (uintptr_t)rcu_dereference(__sk_user_data(sk)); + uintptr_t sk_user_data = + (uintptr_t)rcu_dereference_check(__sk_user_data(sk), condition); WARN_ON_ONCE(flags & SK_USER_DATA_PTRMASK); @@ -598,6 +602,12 @@ __rcu_dereference_sk_user_data_with_flags(const struct sock *sk, return NULL; } +static inline void * +__rcu_dereference_sk_user_data_with_flags(const struct sock *sk, uintptr_t flags) +{ + return __rcu_dereference_sk_user_data_with_flags_check(sk, flags, false); +} + #define rcu_dereference_sk_user_data(sk) \ __rcu_dereference_sk_user_data_with_flags(sk, 0) #define __rcu_assign_sk_user_data_with_flags(sk, ptr, flags) \ diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c index 85fa9dbfa8bf..856c360a591d 100644 --- a/kernel/bpf/reuseport_array.c +++ b/kernel/bpf/reuseport_array.c @@ -24,7 +24,8 @@ void bpf_sk_reuseport_detach(struct sock *sk) struct sock __rcu **socks; write_lock_bh(&sk->sk_callback_lock); - socks = __rcu_dereference_sk_user_data_with_flags(sk, SK_USER_DATA_BPF); + socks = __rcu_dereference_sk_user_data_with_flags_check( + sk, SK_USER_DATA_BPF, lockdep_is_held(&sk->sk_callback_lock)); if (socks) { WRITE_ONCE(sk->sk_user_data, NULL); /*
bpf_sk_reuseport_detach() calls __rcu_dereference_sk_user_data_with_flags() to obtain the value of sk->sk_user_data, but that function is only usable if the RCU read lock is held, and neither that function nor any of its callers hold it. Fix this by adding a new helper, __rcu_dereference_sk_user_data_with_flags_check() that checks to see if sk->sk_callback_lock() is held and use that here instead. __rcu_dereference_sk_user_data_with_flags() then calls that, supplying false as condition indicating only the RCU read lock should be checked. Without this, the following warning can be occasionally observed: ============================= WARNING: suspicious RCU usage 6.0.0-rc1-build2+ #563 Not tainted ----------------------------- include/net/sock.h:592 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 5 locks held by locktest/29873: #0: ffff88812734b550 (&sb->s_type->i_mutex_key#9){+.+.}-{3:3}, at: __sock_release+0x77/0x121 #1: ffff88812f5621b0 (sk_lock-AF_INET){+.+.}-{0:0}, at: tcp_close+0x1c/0x70 #2: ffff88810312f5c8 (&h->lhash2[i].lock){+.+.}-{2:2}, at: inet_unhash+0x76/0x1c0 #3: ffffffff83768bb8 (reuseport_lock){+...}-{2:2}, at: reuseport_detach_sock+0x18/0xdd #4: ffff88812f562438 (clock-AF_INET){++..}-{2:2}, at: bpf_sk_reuseport_detach+0x24/0xa4 stack backtrace: CPU: 1 PID: 29873 Comm: locktest Not tainted 6.0.0-rc1-build2+ #563 Hardware name: ASUS All Series/H97-PLUS, BIOS 2306 10/09/2014 Call Trace: <TASK> dump_stack_lvl+0x4c/0x5f bpf_sk_reuseport_detach+0x6d/0xa4 reuseport_detach_sock+0x75/0xdd inet_unhash+0xa5/0x1c0 tcp_set_state+0x169/0x20f ? lockdep_sock_is_held+0x3a/0x3a ? __lock_release.isra.0+0x13e/0x220 ? reacquire_held_locks+0x1bb/0x1bb ? hlock_class+0x31/0x96 ? mark_lock+0x9e/0x1af __tcp_close+0x50/0x4b6 tcp_close+0x28/0x70 inet_release+0x8e/0xa7 __sock_release+0x95/0x121 sock_close+0x14/0x17 __fput+0x20f/0x36a task_work_run+0xa3/0xcc exit_to_user_mode_prepare+0x9c/0x14d syscall_exit_to_user_mode+0x18/0x44 entry_SYSCALL_64_after_hwframe+0x63/0xcd Changes ======= ver #2) - Changed to suggestion from Hawkins Jiawei to have a ..._check() function and make the original a special case of that. Fixes: cf8c1e967224 ("net: refactor bpf_sk_reuseport_detach()") Signed-off-by: David Howells <dhowells@redhat.com> cc: Hawkins Jiawei <yin31149@gmail.com> cc: Jakub Kicinski <kuba@kernel.org> cc: netdev@vger.kernel.org Link: https://lore.kernel.org/r/166064248071.3502205.10036394558814861778.stgit@warthog.procyon.org.uk # v1 --- include/net/sock.h | 18 ++++++++++++++---- kernel/bpf/reuseport_array.c | 3 ++- 2 files changed, 16 insertions(+), 5 deletions(-)