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
bug.c
// SPDX-License-Identifier: GPL-2.0
/*
Generic support for BUG()
This respects the following config options:
CONFIG_BUG - emit BUG traps. Nothing happens without this.
CONFIG_GENERIC_BUG - enable this code.
CONFIG_GENERIC_BUG_RELATIVE_POINTERS - use 32-bit pointers relative to
the containing struct bug_entry for bug_addr and file.
CONFIG_DEBUG_BUGVERBOSE - emit full file+line information for each BUG
CONFIG_BUG and CONFIG_DEBUG_BUGVERBOSE are potentially user-settable
(though they're generally always on).
CONFIG_GENERIC_BUG is set by each architecture using this code.
To use this, your architecture must:
1. Set up the config options:
- Enable CONFIG_GENERIC_BUG if CONFIG_BUG
2. Implement BUG (and optionally BUG_ON, WARN, WARN_ON)
- Define HAVE_ARCH_BUG
- Implement BUG() to generate a faulting instruction
- NOTE: struct bug_entry does not have "file" or "line" entries
when CONFIG_DEBUG_BUGVERBOSE is not enabled, so you must generate
the values accordingly.
3. Implement the trap
- In the illegal instruction trap handler (typically), verify
that the fault was in kernel mode, and call report_bug()
- report_bug() will return whether it was a false alarm, a warning,
or an actual bug.
- You must implement the is_valid_bugaddr(bugaddr) callback which
returns true if the eip is a real kernel address, and it points
to the expected BUG trap instruction.
Jeremy Fitzhardinge <jeremy@goop.org> 2006
*/
#define pr_fmt(fmt) fmt
#include <linux/list.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/bug.h>
#include <linux/sched.h>
#include <linux/rculist.h>
#include <linux/ftrace.h>
extern struct bug_entry __start___bug_table[], __stop___bug_table[];
static inline unsigned long bug_addr(const struct bug_entry *bug)
{
#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
return bug->bug_addr;
#else
return (unsigned long)bug + bug->bug_addr_disp;
#endif
}
#ifdef CONFIG_MODULES
/* Updates are protected by module mutex */
static LIST_HEAD(module_bug_list);
static struct bug_entry *module_find_bug(unsigned long bugaddr)
{
struct module *mod;
struct bug_entry *bug = NULL;
rcu_read_lock_sched();
list_for_each_entry_rcu(mod, &module_bug_list, bug_list) {
unsigned i;
bug = mod->bug_table;
for (i = 0; i < mod->num_bugs; ++i, ++bug)
if (bugaddr == bug_addr(bug))
goto out;
}
bug = NULL;
out:
rcu_read_unlock_sched();
return bug;
}
void module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs,
struct module *mod)
{
char *secstrings;
unsigned int i;
mod->bug_table = NULL;
mod->num_bugs = 0;
/* Find the __bug_table section, if present */
secstrings = (char *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
for (i = 1; i < hdr->e_shnum; i++) {
if (strcmp(secstrings+sechdrs[i].sh_name, "__bug_table"))
continue;
mod->bug_table = (void *) sechdrs[i].sh_addr;
mod->num_bugs = sechdrs[i].sh_size / sizeof(struct bug_entry);
break;
}
/*
* Strictly speaking this should have a spinlock to protect against
* traversals, but since we only traverse on BUG()s, a spinlock
* could potentially lead to deadlock and thus be counter-productive.
* Thus, this uses RCU to safely manipulate the bug list, since BUG
* must run in non-interruptive state.
*/
list_add_rcu(&mod->bug_list, &module_bug_list);
}
void module_bug_cleanup(struct module *mod)
{
list_del_rcu(&mod->bug_list);
}
#else
static inline struct bug_entry *module_find_bug(unsigned long bugaddr)
{
return NULL;
}
#endif
void bug_get_file_line(struct bug_entry *bug, const char **file,
unsigned int *line)
{
#ifdef CONFIG_DEBUG_BUGVERBOSE
#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
*file = bug->file;
#else
*file = (const char *)bug + bug->file_disp;
#endif
*line = bug->line;
#else
*file = NULL;
*line = 0;
#endif
}
struct bug_entry *find_bug(unsigned long bugaddr)
{
struct bug_entry *bug;
for (bug = __start___bug_table; bug < __stop___bug_table; ++bug)
if (bugaddr == bug_addr(bug))
return bug;
return module_find_bug(bugaddr);
}
enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs)
{
struct bug_entry *bug;
const char *file;
unsigned line, warning, once, done;
if (!is_valid_bugaddr(bugaddr))
return BUG_TRAP_TYPE_NONE;
bug = find_bug(bugaddr);
if (!bug)
return BUG_TRAP_TYPE_NONE;
disable_trace_on_warning();
bug_get_file_line(bug, &file, &line);
warning = (bug->flags & BUGFLAG_WARNING) != 0;
once = (bug->flags & BUGFLAG_ONCE) != 0;
done = (bug->flags & BUGFLAG_DONE) != 0;
if (warning && once) {
if (done)
return BUG_TRAP_TYPE_WARN;
/*
* Since this is the only store, concurrency is not an issue.
*/
bug->flags |= BUGFLAG_DONE;
}
/*
* BUG() and WARN_ON() families don't print a custom debug message
* before triggering the exception handler, so we must add the
* "cut here" line now. WARN() issues its own "cut here" before the
* extra debugging message it writes before triggering the handler.
*/
if ((bug->flags & BUGFLAG_NO_CUT_HERE) == 0)
printk(KERN_DEFAULT CUT_HERE);
if (warning) {
/* this is a WARN_ON rather than BUG/BUG_ON */
__warn(file, line, (void *)bugaddr, BUG_GET_TAINT(bug), regs,
NULL);
return BUG_TRAP_TYPE_WARN;
}
if (file)
pr_crit("kernel BUG at %s:%u!\n", file, line);
else
pr_crit("Kernel BUG at %pB [verbose debug info unavailable]\n",
(void *)bugaddr);
return BUG_TRAP_TYPE_BUG;
}
static void clear_once_table(struct bug_entry *start, struct bug_entry *end)
{
struct bug_entry *bug;
for (bug = start; bug < end; bug++)
bug->flags &= ~BUGFLAG_DONE;
}
void generic_bug_clear_once(void)
{
#ifdef CONFIG_MODULES
struct module *mod;
rcu_read_lock_sched();
list_for_each_entry_rcu(mod, &module_bug_list, bug_list)
clear_once_table(mod->bug_table,
mod->bug_table + mod->num_bugs);
rcu_read_unlock_sched();
#endif
clear_once_table(__start___bug_table, __stop___bug_table);
}
Computing file changes ...