6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Matthieu Baerts (NGI0) matttbe@kernel.org
commit d38e26e36206ae3d544d496513212ae931d1da0a upstream.
Using the 'net' structure via 'current' is not recommended for different reasons.
First, if the goal is to use it to read or write per-netns data, this is inconsistent with how the "generic" sysctl entries are doing: directly by only using pointers set to the table entry, e.g. table->data. Linked to that, the per-netns data should always be obtained from the table linked to the netns it had been created for, which may not coincide with the reader's or writer's netns.
Another reason is that access to current->nsproxy->netns can oops if attempted when current->nsproxy had been dropped when the current task is exiting. This is what syzbot found, when using acct(2):
Oops: general protection fault, probably for non-canonical address 0xdffffc0000000005: 0000 [#1] PREEMPT SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000028-0x000000000000002f] CPU: 1 UID: 0 PID: 5924 Comm: syz-executor Not tainted 6.13.0-rc5-syzkaller-00004-gccb98ccef0e5 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024 RIP: 0010:proc_scheduler+0xc6/0x3c0 net/mptcp/ctrl.c:125 Code: 03 42 80 3c 38 00 0f 85 fe 02 00 00 4d 8b a4 24 08 09 00 00 48 b8 00 00 00 00 00 fc ff df 49 8d 7c 24 28 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 cc 02 00 00 4d 8b 7c 24 28 48 8d 84 24 c8 00 00 RSP: 0018:ffffc900034774e8 EFLAGS: 00010206
RAX: dffffc0000000000 RBX: 1ffff9200068ee9e RCX: ffffc90003477620 RDX: 0000000000000005 RSI: ffffffff8b08f91e RDI: 0000000000000028 RBP: 0000000000000001 R08: ffffc90003477710 R09: 0000000000000040 R10: 0000000000000040 R11: 00000000726f7475 R12: 0000000000000000 R13: ffffc90003477620 R14: ffffc90003477710 R15: dffffc0000000000 FS: 0000000000000000(0000) GS:ffff8880b8700000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fee3cd452d8 CR3: 000000007d116000 CR4: 00000000003526f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> proc_sys_call_handler+0x403/0x5d0 fs/proc/proc_sysctl.c:601 __kernel_write_iter+0x318/0xa80 fs/read_write.c:612 __kernel_write+0xf6/0x140 fs/read_write.c:632 do_acct_process+0xcb0/0x14a0 kernel/acct.c:539 acct_pin_kill+0x2d/0x100 kernel/acct.c:192 pin_kill+0x194/0x7c0 fs/fs_pin.c:44 mnt_pin_kill+0x61/0x1e0 fs/fs_pin.c:81 cleanup_mnt+0x3ac/0x450 fs/namespace.c:1366 task_work_run+0x14e/0x250 kernel/task_work.c:239 exit_task_work include/linux/task_work.h:43 [inline] do_exit+0xad8/0x2d70 kernel/exit.c:938 do_group_exit+0xd3/0x2a0 kernel/exit.c:1087 get_signal+0x2576/0x2610 kernel/signal.c:3017 arch_do_signal_or_restart+0x90/0x7e0 arch/x86/kernel/signal.c:337 exit_to_user_mode_loop kernel/entry/common.c:111 [inline] exit_to_user_mode_prepare include/linux/entry-common.h:329 [inline] __syscall_exit_to_user_mode_work kernel/entry/common.c:207 [inline] syscall_exit_to_user_mode+0x150/0x2a0 kernel/entry/common.c:218 do_syscall_64+0xda/0x250 arch/x86/entry/common.c:89 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7fee3cb87a6a Code: Unable to access opcode bytes at 0x7fee3cb87a40. RSP: 002b:00007fffcccac688 EFLAGS: 00000202 ORIG_RAX: 0000000000000037 RAX: 0000000000000000 RBX: 00007fffcccac710 RCX: 00007fee3cb87a6a RDX: 0000000000000041 RSI: 0000000000000000 RDI: 0000000000000003 RBP: 0000000000000003 R08: 00007fffcccac6ac R09: 00007fffcccacac7 R10: 00007fffcccac710 R11: 0000000000000202 R12: 00007fee3cd49500 R13: 00007fffcccac6ac R14: 0000000000000000 R15: 00007fee3cd4b000 </TASK> Modules linked in: ---[ end trace 0000000000000000 ]--- RIP: 0010:proc_scheduler+0xc6/0x3c0 net/mptcp/ctrl.c:125 Code: 03 42 80 3c 38 00 0f 85 fe 02 00 00 4d 8b a4 24 08 09 00 00 48 b8 00 00 00 00 00 fc ff df 49 8d 7c 24 28 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 cc 02 00 00 4d 8b 7c 24 28 48 8d 84 24 c8 00 00 RSP: 0018:ffffc900034774e8 EFLAGS: 00010206 RAX: dffffc0000000000 RBX: 1ffff9200068ee9e RCX: ffffc90003477620 RDX: 0000000000000005 RSI: ffffffff8b08f91e RDI: 0000000000000028 RBP: 0000000000000001 R08: ffffc90003477710 R09: 0000000000000040 R10: 0000000000000040 R11: 00000000726f7475 R12: 0000000000000000 R13: ffffc90003477620 R14: ffffc90003477710 R15: dffffc0000000000 FS: 0000000000000000(0000) GS:ffff8880b8700000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fee3cd452d8 CR3: 000000007d116000 CR4: 00000000003526f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 ---------------- Code disassembly (best guess), 1 bytes skipped: 0: 42 80 3c 38 00 cmpb $0x0,(%rax,%r15,1) 5: 0f 85 fe 02 00 00 jne 0x309 b: 4d 8b a4 24 08 09 00 mov 0x908(%r12),%r12 12: 00 13: 48 b8 00 00 00 00 00 movabs $0xdffffc0000000000,%rax 1a: fc ff df 1d: 49 8d 7c 24 28 lea 0x28(%r12),%rdi 22: 48 89 fa mov %rdi,%rdx 25: 48 c1 ea 03 shr $0x3,%rdx * 29: 80 3c 02 00 cmpb $0x0,(%rdx,%rax,1) <-- trapping instruction 2d: 0f 85 cc 02 00 00 jne 0x2ff 33: 4d 8b 7c 24 28 mov 0x28(%r12),%r15 38: 48 rex.W 39: 8d .byte 0x8d 3a: 84 24 c8 test %ah,(%rax,%rcx,8)
Here with 'net.mptcp.scheduler', the 'net' structure is not really needed, because the table->data already has a pointer to the current scheduler, the only thing needed from the per-netns data. Simply use 'data', instead of getting (most of the time) the same thing, but from a longer and indirect way.
Fixes: 6963c508fd7a ("mptcp: only allow set existing scheduler for net.mptcp.scheduler") Cc: stable@vger.kernel.org Reported-by: syzbot+e364f774c6f57f2c86d1@syzkaller.appspotmail.com Closes: https://lore.kernel.org/67769ecb.050a0220.3a8527.003f.GAE@google.com Suggested-by: Al Viro viro@zeniv.linux.org.uk Reviewed-by: Mat Martineau martineau@kernel.org Signed-off-by: Matthieu Baerts (NGI0) matttbe@kernel.org Link: https://patch.msgid.link/20250108-net-sysctl-current-nsproxy-v1-2-5df34b2083... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/mptcp/ctrl.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-)
--- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -87,16 +87,15 @@ static void mptcp_pernet_set_defaults(st }
#ifdef CONFIG_SYSCTL -static int mptcp_set_scheduler(const struct net *net, const char *name) +static int mptcp_set_scheduler(char *scheduler, const char *name) { - struct mptcp_pernet *pernet = mptcp_get_pernet(net); struct mptcp_sched_ops *sched; int ret = 0;
rcu_read_lock(); sched = mptcp_sched_find(name); if (sched) - strscpy(pernet->scheduler, name, MPTCP_SCHED_NAME_MAX); + strscpy(scheduler, name, MPTCP_SCHED_NAME_MAX); else ret = -ENOENT; rcu_read_unlock(); @@ -107,7 +106,7 @@ static int mptcp_set_scheduler(const str static int proc_scheduler(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { - const struct net *net = current->nsproxy->net_ns; + char (*scheduler)[MPTCP_SCHED_NAME_MAX] = ctl->data; char val[MPTCP_SCHED_NAME_MAX]; struct ctl_table tbl = { .data = val, @@ -115,11 +114,11 @@ static int proc_scheduler(struct ctl_tab }; int ret;
- strscpy(val, mptcp_get_scheduler(net), MPTCP_SCHED_NAME_MAX); + strscpy(val, *scheduler, MPTCP_SCHED_NAME_MAX);
ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) - ret = mptcp_set_scheduler(net, val); + ret = mptcp_set_scheduler(*scheduler, val);
return ret; }