Revision 49054556289e8787501630b7c7a9d407da02e296 authored by Paolo Abeni on 29 September 2021, 09:59:17 UTC, committed by David S. Miller on 30 September 2021, 12:06:47 UTC
Syzkaller reported a false positive deadlock involving the nl socket lock and the subflow socket lock: MPTCP: kernel_bind error, err=-98 ============================================ WARNING: possible recursive locking detected 5.15.0-rc1-syzkaller #0 Not tainted -------------------------------------------- syz-executor998/6520 is trying to acquire lock: ffff8880795718a0 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x267/0x7b0 net/mptcp/protocol.c:2738 but task is already holding lock: ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1612 [inline] ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x23/0x7b0 net/mptcp/protocol.c:2720 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(k-sk_lock-AF_INET); lock(k-sk_lock-AF_INET); *** DEADLOCK *** May be due to missing lock nesting notation 3 locks held by syz-executor998/6520: #0: ffffffff8d176c50 (cb_lock){++++}-{3:3}, at: genl_rcv+0x15/0x40 net/netlink/genetlink.c:802 #1: ffffffff8d176d08 (genl_mutex){+.+.}-{3:3}, at: genl_lock net/netlink/genetlink.c:33 [inline] #1: ffffffff8d176d08 (genl_mutex){+.+.}-{3:3}, at: genl_rcv_msg+0x3e0/0x580 net/netlink/genetlink.c:790 #2: ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1612 [inline] #2: ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x23/0x7b0 net/mptcp/protocol.c:2720 stack backtrace: CPU: 1 PID: 6520 Comm: syz-executor998 Not tainted 5.15.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_deadlock_bug kernel/locking/lockdep.c:2944 [inline] check_deadlock kernel/locking/lockdep.c:2987 [inline] validate_chain kernel/locking/lockdep.c:3776 [inline] __lock_acquire.cold+0x149/0x3ab kernel/locking/lockdep.c:5015 lock_acquire kernel/locking/lockdep.c:5625 [inline] lock_acquire+0x1ab/0x510 kernel/locking/lockdep.c:5590 lock_sock_fast+0x36/0x100 net/core/sock.c:3229 mptcp_close+0x267/0x7b0 net/mptcp/protocol.c:2738 inet_release+0x12e/0x280 net/ipv4/af_inet.c:431 __sock_release net/socket.c:649 [inline] sock_release+0x87/0x1b0 net/socket.c:677 mptcp_pm_nl_create_listen_socket+0x238/0x2c0 net/mptcp/pm_netlink.c:900 mptcp_nl_cmd_add_addr+0x359/0x930 net/mptcp/pm_netlink.c:1170 genl_family_rcv_msg_doit+0x228/0x320 net/netlink/genetlink.c:731 genl_family_rcv_msg net/netlink/genetlink.c:775 [inline] genl_rcv_msg+0x328/0x580 net/netlink/genetlink.c:792 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2504 genl_rcv+0x24/0x40 net/netlink/genetlink.c:803 netlink_unicast_kernel net/netlink/af_netlink.c:1314 [inline] netlink_unicast+0x533/0x7d0 net/netlink/af_netlink.c:1340 netlink_sendmsg+0x86d/0xdb0 net/netlink/af_netlink.c:1929 sock_sendmsg_nosec net/socket.c:704 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:724 sock_no_sendpage+0x101/0x150 net/core/sock.c:2980 kernel_sendpage.part.0+0x1a0/0x340 net/socket.c:3504 kernel_sendpage net/socket.c:3501 [inline] sock_sendpage+0xe5/0x140 net/socket.c:1003 pipe_to_sendpage+0x2ad/0x380 fs/splice.c:364 splice_from_pipe_feed fs/splice.c:418 [inline] __splice_from_pipe+0x43e/0x8a0 fs/splice.c:562 splice_from_pipe fs/splice.c:597 [inline] generic_splice_sendpage+0xd4/0x140 fs/splice.c:746 do_splice_from fs/splice.c:767 [inline] direct_splice_actor+0x110/0x180 fs/splice.c:936 splice_direct_to_actor+0x34b/0x8c0 fs/splice.c:891 do_splice_direct+0x1b3/0x280 fs/splice.c:979 do_sendfile+0xae9/0x1240 fs/read_write.c:1249 __do_sys_sendfile64 fs/read_write.c:1314 [inline] __se_sys_sendfile64 fs/read_write.c:1300 [inline] __x64_sys_sendfile64+0x1cc/0x210 fs/read_write.c:1300 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f215cb69969 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 14 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffc96bb3868 EFLAGS: 00000246 ORIG_RAX: 0000000000000028 RAX: ffffffffffffffda RBX: 00007f215cbad072 RCX: 00007f215cb69969 RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000005 RBP: 0000000000000000 R08: 00007ffc96bb3a08 R09: 00007ffc96bb3a08 R10: 0000000100000002 R11: 0000000000000246 R12: 00007ffc96bb387c R13: 431bde82d7b634db R14: 0000000000000000 R15: 0000000000000000 the problem originates from uncorrect lock annotation in the mptcp code and is only visible since commit 2dcb96bacce3 ("net: core: Correct the sock::sk_lock.owned lockdep annotations"), but is present since the port-based endpoint support initial implementation. This patch addresses the issue introducing a nested variant of lock_sock_fast() and using it in the relevant code path. Fixes: 1729cf186d8a ("mptcp: create the listening socket for new port") Fixes: 2dcb96bacce3 ("net: core: Correct the sock::sk_lock.owned lockdep annotations") Suggested-by: Thomas Gleixner <tglx@linutronix.de> Reported-and-tested-by: syzbot+1dd53f7a89b299d59eaf@syzkaller.appspotmail.com Signed-off-by: Paolo Abeni <pabeni@redhat.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: David S. Miller <davem@davemloft.net>
1 parent d88fd1b
flex_proportions.c
// SPDX-License-Identifier: GPL-2.0
/*
* Floating proportions with flexible aging period
*
* Copyright (C) 2011, SUSE, Jan Kara <jack@suse.cz>
*
* The goal of this code is: Given different types of event, measure proportion
* of each type of event over time. The proportions are measured with
* exponentially decaying history to give smooth transitions. A formula
* expressing proportion of event of type 'j' is:
*
* p_{j} = (\Sum_{i>=0} x_{i,j}/2^{i+1})/(\Sum_{i>=0} x_i/2^{i+1})
*
* Where x_{i,j} is j's number of events in i-th last time period and x_i is
* total number of events in i-th last time period.
*
* Note that p_{j}'s are normalised, i.e.
*
* \Sum_{j} p_{j} = 1,
*
* This formula can be straightforwardly computed by maintaining denominator
* (let's call it 'd') and for each event type its numerator (let's call it
* 'n_j'). When an event of type 'j' happens, we simply need to do:
* n_j++; d++;
*
* When a new period is declared, we could do:
* d /= 2
* for each j
* n_j /= 2
*
* To avoid iteration over all event types, we instead shift numerator of event
* j lazily when someone asks for a proportion of event j or when event j
* occurs. This can bit trivially implemented by remembering last period in
* which something happened with proportion of type j.
*/
#include <linux/flex_proportions.h>
int fprop_global_init(struct fprop_global *p, gfp_t gfp)
{
int err;
p->period = 0;
/* Use 1 to avoid dealing with periods with 0 events... */
err = percpu_counter_init(&p->events, 1, gfp);
if (err)
return err;
seqcount_init(&p->sequence);
return 0;
}
void fprop_global_destroy(struct fprop_global *p)
{
percpu_counter_destroy(&p->events);
}
/*
* Declare @periods new periods. It is upto the caller to make sure period
* transitions cannot happen in parallel.
*
* The function returns true if the proportions are still defined and false
* if aging zeroed out all events. This can be used to detect whether declaring
* further periods has any effect.
*/
bool fprop_new_period(struct fprop_global *p, int periods)
{
s64 events;
unsigned long flags;
local_irq_save(flags);
events = percpu_counter_sum(&p->events);
/*
* Don't do anything if there are no events.
*/
if (events <= 1) {
local_irq_restore(flags);
return false;
}
write_seqcount_begin(&p->sequence);
if (periods < 64)
events -= events >> periods;
/* Use addition to avoid losing events happening between sum and set */
percpu_counter_add(&p->events, -events);
p->period += periods;
write_seqcount_end(&p->sequence);
local_irq_restore(flags);
return true;
}
/*
* ---- SINGLE ----
*/
int fprop_local_init_single(struct fprop_local_single *pl)
{
pl->events = 0;
pl->period = 0;
raw_spin_lock_init(&pl->lock);
return 0;
}
void fprop_local_destroy_single(struct fprop_local_single *pl)
{
}
static void fprop_reflect_period_single(struct fprop_global *p,
struct fprop_local_single *pl)
{
unsigned int period = p->period;
unsigned long flags;
/* Fast path - period didn't change */
if (pl->period == period)
return;
raw_spin_lock_irqsave(&pl->lock, flags);
/* Someone updated pl->period while we were spinning? */
if (pl->period >= period) {
raw_spin_unlock_irqrestore(&pl->lock, flags);
return;
}
/* Aging zeroed our fraction? */
if (period - pl->period < BITS_PER_LONG)
pl->events >>= period - pl->period;
else
pl->events = 0;
pl->period = period;
raw_spin_unlock_irqrestore(&pl->lock, flags);
}
/* Event of type pl happened */
void __fprop_inc_single(struct fprop_global *p, struct fprop_local_single *pl)
{
fprop_reflect_period_single(p, pl);
pl->events++;
percpu_counter_add(&p->events, 1);
}
/* Return fraction of events of type pl */
void fprop_fraction_single(struct fprop_global *p,
struct fprop_local_single *pl,
unsigned long *numerator, unsigned long *denominator)
{
unsigned int seq;
s64 num, den;
do {
seq = read_seqcount_begin(&p->sequence);
fprop_reflect_period_single(p, pl);
num = pl->events;
den = percpu_counter_read_positive(&p->events);
} while (read_seqcount_retry(&p->sequence, seq));
/*
* Make fraction <= 1 and denominator > 0 even in presence of percpu
* counter errors
*/
if (den <= num) {
if (num)
den = num;
else
den = 1;
}
*denominator = den;
*numerator = num;
}
/*
* ---- PERCPU ----
*/
#define PROP_BATCH (8*(1+ilog2(nr_cpu_ids)))
int fprop_local_init_percpu(struct fprop_local_percpu *pl, gfp_t gfp)
{
int err;
err = percpu_counter_init(&pl->events, 0, gfp);
if (err)
return err;
pl->period = 0;
raw_spin_lock_init(&pl->lock);
return 0;
}
void fprop_local_destroy_percpu(struct fprop_local_percpu *pl)
{
percpu_counter_destroy(&pl->events);
}
static void fprop_reflect_period_percpu(struct fprop_global *p,
struct fprop_local_percpu *pl)
{
unsigned int period = p->period;
unsigned long flags;
/* Fast path - period didn't change */
if (pl->period == period)
return;
raw_spin_lock_irqsave(&pl->lock, flags);
/* Someone updated pl->period while we were spinning? */
if (pl->period >= period) {
raw_spin_unlock_irqrestore(&pl->lock, flags);
return;
}
/* Aging zeroed our fraction? */
if (period - pl->period < BITS_PER_LONG) {
s64 val = percpu_counter_read(&pl->events);
if (val < (nr_cpu_ids * PROP_BATCH))
val = percpu_counter_sum(&pl->events);
percpu_counter_add_batch(&pl->events,
-val + (val >> (period-pl->period)), PROP_BATCH);
} else
percpu_counter_set(&pl->events, 0);
pl->period = period;
raw_spin_unlock_irqrestore(&pl->lock, flags);
}
/* Event of type pl happened */
void __fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl)
{
fprop_reflect_period_percpu(p, pl);
percpu_counter_add_batch(&pl->events, 1, PROP_BATCH);
percpu_counter_add(&p->events, 1);
}
void fprop_fraction_percpu(struct fprop_global *p,
struct fprop_local_percpu *pl,
unsigned long *numerator, unsigned long *denominator)
{
unsigned int seq;
s64 num, den;
do {
seq = read_seqcount_begin(&p->sequence);
fprop_reflect_period_percpu(p, pl);
num = percpu_counter_read_positive(&pl->events);
den = percpu_counter_read_positive(&p->events);
} while (read_seqcount_retry(&p->sequence, seq));
/*
* Make fraction <= 1 and denominator > 0 even in presence of percpu
* counter errors
*/
if (den <= num) {
if (num)
den = num;
else
den = 1;
}
*denominator = den;
*numerator = num;
}
/*
* Like __fprop_inc_percpu() except that event is counted only if the given
* type has fraction smaller than @max_frac/FPROP_FRAC_BASE
*/
void __fprop_inc_percpu_max(struct fprop_global *p,
struct fprop_local_percpu *pl, int max_frac)
{
if (unlikely(max_frac < FPROP_FRAC_BASE)) {
unsigned long numerator, denominator;
fprop_fraction_percpu(p, pl, &numerator, &denominator);
if (numerator >
(((u64)denominator) * max_frac) >> FPROP_FRAC_SHIFT)
return;
}
__fprop_inc_percpu(p, pl);
}
Computing file changes ...