From ee17e5d6201c66492a0e8053190fca2ed2b8457d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 12 Jan 2019 11:48:20 -0600 Subject: [PATCH 1/4] signal: Make siginmask safe when passed a signal of 0 Eric Biggers reported: > The following commit, which went into v4.20, introduced undefined behavior when > sys_rt_sigqueueinfo() is called with sig=0: > > commit 4ce5f9c9e7546915c559ffae594e6d73f918db00 > Author: Eric W. Biederman > Date: Tue Sep 25 12:59:31 2018 +0200 > > signal: Use a smaller struct siginfo in the kernel > > In sig_specific_sicodes(), used from known_siginfo_layout(), the expression > '1ULL << ((sig)-1)' is undefined as it evaluates to 1ULL << 4294967295. > > Reproducer: > > #include > #include > #include > > int main(void) > { > siginfo_t si = { .si_code = 1 }; > syscall(__NR_rt_sigqueueinfo, 0, 0, &si); > } > > UBSAN report for v5.0-rc1: > > UBSAN: Undefined behaviour in kernel/signal.c:2946:7 > shift exponent 4294967295 is too large for 64-bit type 'long unsigned int' > CPU: 2 PID: 346 Comm: syz_signal Not tainted 5.0.0-rc1 #25 > Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 > Call Trace: > __dump_stack lib/dump_stack.c:77 [inline] > dump_stack+0x70/0xa5 lib/dump_stack.c:113 > ubsan_epilogue+0xd/0x40 lib/ubsan.c:159 > __ubsan_handle_shift_out_of_bounds+0x12c/0x170 lib/ubsan.c:425 > known_siginfo_layout+0xae/0xe0 kernel/signal.c:2946 > post_copy_siginfo_from_user kernel/signal.c:3009 [inline] > __copy_siginfo_from_user+0x35/0x60 kernel/signal.c:3035 > __do_sys_rt_sigqueueinfo kernel/signal.c:3553 [inline] > __se_sys_rt_sigqueueinfo kernel/signal.c:3549 [inline] > __x64_sys_rt_sigqueueinfo+0x31/0x70 kernel/signal.c:3549 > do_syscall_64+0x4c/0x1b0 arch/x86/entry/common.c:290 > entry_SYSCALL_64_after_hwframe+0x49/0xbe > RIP: 0033:0x433639 > Code: c4 18 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 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 0f 83 7b 27 00 00 c3 66 2e 0f 1f 84 00 00 00 00 > RSP: 002b:00007fffcb289fc8 EFLAGS: 00000246 ORIG_RAX: 0000000000000081 > RAX: ffffffffffffffda RBX: 00000000004002e0 RCX: 0000000000433639 > RDX: 00007fffcb289fd0 RSI: 0000000000000000 RDI: 0000000000000000 > RBP: 00000000006b2018 R08: 000000000000004d R09: 0000000000000000 > R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000401560 > R13: 00000000004015f0 R14: 0000000000000000 R15: 0000000000000000 I have looked at the other callers of siginmask and they all appear to in locations where sig can not be zero. I have looked at the code generation of adding an extra test against zero and gcc was able with a simple decrement instruction to combine the two tests together. So the at most adding this test cost a single cpu cycle. In practice that decrement instruction was already present as part of the mask comparison, so the only change was when the instruction was executed. So given that it is cheap, and obviously correct to update siginmask to verify the signal is not zero. Fix this issue there to avoid any future problems. Reported-by: Eric Biggers Fixes: 4ce5f9c9e754 ("signal: Use a smaller struct siginfo in the kernel") Signed-off-by: "Eric W. Biederman" --- include/linux/signal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/signal.h b/include/linux/signal.h index cc7e2c1cd444..9702016734b1 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -392,7 +392,7 @@ extern bool unhandled_signal(struct task_struct *tsk, int sig); #endif #define siginmask(sig, mask) \ - ((sig) < SIGRTMIN && (rt_sigmask(sig) & (mask))) + ((sig) > 0 && (sig) < SIGRTMIN && (rt_sigmask(sig) & (mask))) #define SIG_KERNEL_ONLY_MASK (\ rt_sigmask(SIGKILL) | rt_sigmask(SIGSTOP)) From a692933a87691681e880feb708081681ff32400a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 5 Feb 2019 07:19:11 -0600 Subject: [PATCH 2/4] signal: Always attempt to allocate siginfo for SIGSTOP Since 2.5.34 the code has had the potential to not allocate siginfo for SIGSTOP signals. Except for ptrace this is perfectly fine as only ptrace can use PTRACE_PEEK_SIGINFO and see what the contents of the delivered siginfo are. Users of PTRACE_PEEK_SIGINFO that care about the contents siginfo for SIGSTOP are rare, but they do exist. A seccomp self test has cared and lldb cares. Jack Andersen writes: > The patch titled > `signal: Never allocate siginfo for SIGKILL or SIGSTOP` > created a regression for users of PTRACE_GETSIGINFO needing to > discern signals that were raised via the tgkill syscall. > > A notable user of this tgkill+ptrace combination is lldb while > debugging a multithreaded program. Without the ability to detect a > SIGSTOP originating from tgkill, lldb does not have a way to > synchronize on a per-thread basis and falls back to SIGSTOP-ing the > entire process. Everyone affected by this please note. The kernel can still fail to allocate a siginfo structure. The allocation is with GFP_KERNEL and is best effort only. If memory is tight when the signal allocation comes in this will fail to allocate a siginfo. So I strongly recommend looking at more robust solutions for synchronizing with a single thread such as PTRACE_INTERRUPT. Or if that does not work persuading your friendly local kernel developer to build the interface you need. Reported-by: Tycho Andersen Reported-by: Kees Cook Reported-by: Jack Andersen Acked-by: Linus Torvalds Reviewed-by: Christian Brauner Cc: stable@vger.kernel.org Fixes: f149b3155744 ("signal: Never allocate siginfo for SIGKILL or SIGSTOP") Fixes: 6dfc88977e42 ("[PATCH] shared thread signals") History Tree: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git Signed-off-by: "Eric W. Biederman" --- kernel/signal.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/kernel/signal.c b/kernel/signal.c index e1d7ad8e6ab1..9ca8e5278c8e 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1057,10 +1057,9 @@ static int __send_signal(int sig, struct kernel_siginfo *info, struct task_struc result = TRACE_SIGNAL_DELIVERED; /* - * Skip useless siginfo allocation for SIGKILL SIGSTOP, - * and kernel threads. + * Skip useless siginfo allocation for SIGKILL and kernel threads. */ - if (sig_kernel_only(sig) || (t->flags & PF_KTHREAD)) + if ((sig == SIGKILL) || (t->flags & PF_KTHREAD)) goto out_set; /* From 35634ffa1751b6efd8cf75010b509dcb0263e29b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 6 Feb 2019 18:39:40 -0600 Subject: [PATCH 3/4] signal: Always notice exiting tasks Recently syzkaller was able to create unkillablle processes by creating a timer that is delivered as a thread local signal on SIGHUP, and receiving SIGHUP SA_NODEFERER. Ultimately causing a loop failing to deliver SIGHUP but always trying. Upon examination it turns out part of the problem is actually most of the solution. Since 2.5 signal delivery has found all fatal signals, marked the signal group for death, and queued SIGKILL in every threads thread queue relying on signal->group_exit_code to preserve the information of which was the actual fatal signal. The conversion of all fatal signals to SIGKILL results in the synchronous signal heuristic in next_signal kicking in and preferring SIGHUP to SIGKILL. Which is especially problematic as all fatal signals have already been transformed into SIGKILL. Instead of dequeueing signals and depending upon SIGKILL to be the first signal dequeued, first test if the signal group has already been marked for death. This guarantees that nothing in the signal queue can prevent a process that needs to exit from exiting. Cc: stable@vger.kernel.org Tested-by: Dmitry Vyukov Reported-by: Dmitry Vyukov Ref: ebf5ebe31d2c ("[PATCH] signal-fixes-2.5.59-A4") History Tree: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git Signed-off-by: "Eric W. Biederman" --- kernel/signal.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/kernel/signal.c b/kernel/signal.c index 9ca8e5278c8e..5424cb0006bc 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2393,6 +2393,11 @@ relock: goto relock; } + /* Has this task already been marked for death? */ + ksig->info.si_signo = signr = SIGKILL; + if (signal_group_exit(signal)) + goto fatal; + for (;;) { struct k_sigaction *ka; @@ -2488,6 +2493,7 @@ relock: continue; } + fatal: spin_unlock_irq(&sighand->siglock); /* From 7146db3317c67b517258cb5e1b08af387da0618b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 6 Feb 2019 17:51:47 -0600 Subject: [PATCH 4/4] signal: Better detection of synchronous signals Recently syzkaller was able to create unkillablle processes by creating a timer that is delivered as a thread local signal on SIGHUP, and receiving SIGHUP SA_NODEFERER. Ultimately causing a loop failing to deliver SIGHUP but always trying. When the stack overflows delivery of SIGHUP fails and force_sigsegv is called. Unfortunately because SIGSEGV is numerically higher than SIGHUP next_signal tries again to deliver a SIGHUP. From a quality of implementation standpoint attempting to deliver the timer SIGHUP signal is wrong. We should attempt to deliver the synchronous SIGSEGV signal we just forced. We can make that happening in a fairly straight forward manner by instead of just looking at the signal number we also look at the si_code. In particular for exceptions (aka synchronous signals) the si_code is always greater than 0. That still has the potential to pick up a number of asynchronous signals as in a few cases the same si_codes that are used for synchronous signals are also used for asynchronous signals, and SI_KERNEL is also included in the list of possible si_codes. Still the heuristic is much better and timer signals are definitely excluded. Which is enough to prevent all known ways for someone sending a process signals fast enough to cause unexpected and arguably incorrect behavior. Cc: stable@vger.kernel.org Fixes: a27341cd5fcb ("Prioritize synchronous signals over 'normal' signals") Tested-by: Dmitry Vyukov Reported-by: Dmitry Vyukov Signed-off-by: "Eric W. Biederman" --- kernel/signal.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 51 insertions(+), 1 deletion(-) diff --git a/kernel/signal.c b/kernel/signal.c index 5424cb0006bc..99fa8ff06fd9 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -688,6 +688,48 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, kernel_siginfo_t *in } EXPORT_SYMBOL_GPL(dequeue_signal); +static int dequeue_synchronous_signal(kernel_siginfo_t *info) +{ + struct task_struct *tsk = current; + struct sigpending *pending = &tsk->pending; + struct sigqueue *q, *sync = NULL; + + /* + * Might a synchronous signal be in the queue? + */ + if (!((pending->signal.sig[0] & ~tsk->blocked.sig[0]) & SYNCHRONOUS_MASK)) + return 0; + + /* + * Return the first synchronous signal in the queue. + */ + list_for_each_entry(q, &pending->list, list) { + /* Synchronous signals have a postive si_code */ + if ((q->info.si_code > SI_USER) && + (sigmask(q->info.si_signo) & SYNCHRONOUS_MASK)) { + sync = q; + goto next; + } + } + return 0; +next: + /* + * Check if there is another siginfo for the same signal. + */ + list_for_each_entry_continue(q, &pending->list, list) { + if (q->info.si_signo == sync->info.si_signo) + goto still_pending; + } + + sigdelset(&pending->signal, sync->info.si_signo); + recalc_sigpending(); +still_pending: + list_del_init(&sync->list); + copy_siginfo(info, &sync->info); + __sigqueue_free(sync); + return info->si_signo; +} + /* * Tell a process that it has a new active signal.. * @@ -2411,7 +2453,15 @@ relock: goto relock; } - signr = dequeue_signal(current, ¤t->blocked, &ksig->info); + /* + * Signals generated by the execution of an instruction + * need to be delivered before any other pending signals + * so that the instruction pointer in the signal stack + * frame points to the faulting instruction. + */ + signr = dequeue_synchronous_signal(&ksig->info); + if (!signr) + signr = dequeue_signal(current, ¤t->blocked, &ksig->info); if (!signr) break; /* will return 0 */