Re: 5.11 regression: "ia64: add support for TIF_NOTIFY_SIGNAL" breaks ia64 boot

From: Jens Axboe
Date: Mon Feb 22 2021 - 19:44:55 EST

On 2/22/21 5:41 PM, Jens Axboe wrote:
> On 2/22/21 5:34 PM, Jens Axboe wrote:
>> On 2/22/21 4:53 PM, Sergei Trofimovich wrote:
>>> On Mon, 22 Feb 2021 16:34:50 -0700
>>> Jens Axboe <axboe@xxxxxxxxx> wrote:
>>>
>>>> On 2/22/21 4:05 PM, Sergei Trofimovich wrote:
>>>>> Hia Jens!
>>>>>
>>>>> Tried 5.11 on rx3600 box and noticed it has
>>>>> a problem handling init (5.10 booted fine):
>>>>>
>>>>> INIT: version 2.98 booting
>>>>>
>>>>> OpenRC 0.42.1 is starting up Gentoo Linux (ia64)
>>>>>
>>>>> mkdir `/run/openrc': Read-only file system
>>>>> mkdir `/run/openrc/starting': No such file or directory
>>>>> mkdir `/run/openrc/started': No such file or directory
>>>>> mkdir `/run/openrc/stopping': No such file or directory
>>>>> mkdir `/run/openrc/inactive': No such file or directory
>>>>> mkdir `/run/openrc/wasinactive': No such file or directory
>>>>> mkdir `/run/openrc/failed': No such file or directory
>>>>> mkdir `/run/openrc/hotplugged': No such file or directory
>>>>> mkdir `/run/openrc/daemons': No such file or directory
>>>>> mkdir `/run[ 14.595059] Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b
>>>>> [ 14.599059] ---[ end Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b ]---
>>>>>
>>>>> I suspect we build bad signal stack frame for userspace.
>>>>>
>>>>> With a bit of #define DEBUG_SIG 1 enabled the signals are SIGCHLD:
>>>>>
>>>>> [ 34.969771] SIG deliver (gendepends.sh:69): sig=17 sp=60000fffff6aeaa0 ip=a000000000040740 handler=000000004b4c59b6
>>>>> [ 34.969948] SIG deliver (init:1): sig=17 sp=60000fffff1ccc50 ip=a000000000040740 handler=000000004638b9e5
>>>>> [ 34.969948] SIG deliver (gendepends.sh:69): sig=17 sp=60000fffff6adf90 ip=a000000000040740 handler=000000004b4c59b6
>>>>> [ 34.973948] SIG deliver (init:1): sig=17 sp=60000fffff1cc140 ip=a000000000040740 handler=000000004638b9e5
>>>>> [ 34.973948] Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b
>>>>> [ 34.973948] SIG deliver (gendepends.sh:69): sig=17 sp=60000fffff6ad480 ip=a000000000040740 handler=000000004b4c59b6
>>>>> [ 34.973948] ---[ end Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b ]---
>>>>>
>>>>> Bisect points at:
>>>>>
>>>>> commit b269c229b0e89aedb7943c06673b56b6052cf5e5
>>>>> Author: Jens Axboe <axboe@xxxxxxxxx>
>>>>> Date: Fri Oct 9 14:49:43 2020 -0600
>>>>>
>>>>> ia64: add support for TIF_NOTIFY_SIGNAL
>>>>>
>>>>> Wire up TIF_NOTIFY_SIGNAL handling for ia64.
>>>>>
>>>>> Cc: linux-ia64@xxxxxxxxxxxxxxx
>>>>> [axboe: added fixes from Mike Rapoport <rppt@xxxxxxxxxx>]
>>>>> Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
>>>>>
>>>>> diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h
>>>>> index 64a1011f6812..51d20cb37706 100644
>>>>> --- a/arch/ia64/include/asm/thread_info.h
>>>>> +++ b/arch/ia64/include/asm/thread_info.h
>>>>> @@ -103,6 +103,7 @@ struct thread_info {
>>>>> #define TIF_SYSCALL_TRACE 2 /* syscall trace active */
>>>>> #define TIF_SYSCALL_AUDIT 3 /* syscall auditing active */
>>>>> #define TIF_SINGLESTEP 4 /* restore singlestep on return to user mode */
>>>>> +#define TIF_NOTIFY_SIGNAL 5 /* signal notification exist */
>>>>> #define TIF_NOTIFY_RESUME 6 /* resumption notification requested */
>>>>> #define TIF_MEMDIE 17 /* is terminating due to OOM killer */
>>>>> #define TIF_MCA_INIT 18 /* this task is processing MCA or INIT */
>>>>> @@ -115,6 +116,7 @@ struct thread_info {
>>>>> #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP)
>>>>> #define _TIF_SYSCALL_TRACEAUDIT (_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP)
>>>>> #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
>>>>> +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL)
>>>>> #define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
>>>>> #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
>>>>> #define _TIF_MCA_INIT (1 << TIF_MCA_INIT)
>>>>> @@ -124,7 +126,7 @@ struct thread_info {
>>>>>
>>>>> /* "work to do on user-return" bits */
>>>>> #define TIF_ALLWORK_MASK (_TIF_SIGPENDING|_TIF_NOTIFY_RESUME|_TIF_SYSCALL_AUDIT|\
>>>>> - _TIF_NEED_RESCHED|_TIF_SYSCALL_TRACE)
>>>>> + _TIF_NEED_RESCHED|_TIF_SYSCALL_TRACE|_TIF_NOTIFY_SIGNAL)
>>>>> /* like TIF_ALLWORK_BITS but sans TIF_SYSCALL_TRACE or TIF_SYSCALL_AUDIT */
>>>>> #define TIF_WORK_MASK (TIF_ALLWORK_MASK&~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT))
>>>>>
>>>>> diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
>>>>> index 6b61a703bcf5..8d4e1cab9190 100644
>>>>> --- a/arch/ia64/kernel/process.c
>>>>> +++ b/arch/ia64/kernel/process.c
>>>>> @@ -171,7 +171,8 @@ do_notify_resume_user(sigset_t *unused, struct sigscratch *scr, long in_syscall)
>>>>> }
>>>>>
>>>>> /* deal with pending signal delivery */
>>>>> - if (test_thread_flag(TIF_SIGPENDING)) {
>>>>> + if (test_thread_flag(TIF_SIGPENDING) ||
>>>>> + test_thread_flag(TIF_NOTIFY_SIGNAL)) {
>>>>> local_irq_enable(); /* force interrupt enable */
>>>>> ia64_do_signal(scr, in_syscall);
>>>>>
>>>>> which looks benign, but it enables a bit of conditional
>>>>> TIF_NOTIFY_SIGNAL handling I don't understand.
>>>>>
>>>>> Can you help me get what is the interaction between
>>>>> TIF_NOTIFY_SIGNAL and TIF_SIGPENDING for
>>>>> simple processes without io_uring use case?
>>>>>
>>>>> I wonder if it's ia64_do_signal()' generates a signal
>>>>> delivery when it should not.
>>>>
>>>> Can you test:
>>>>
>>>> https://marc.info/?l=linux-ia64&m=161187407609443&w=1
>>>>
>>>> with the addition mentioned here:
>>>
>>> Not enough:
>>>
>>> mkdir `/run/openrc': Read-only file system
>>> mkdir `/run/openrc/starting': No such file or directory
>>> mkdir `/run/openrc/started': No such file or directory
>>> mkdir `/run/openrc/stopping': No such file or directory
>>> mkdir `/run/openrc/inactive': No such file or directory
>>> mkdir `/run/openrc/wasinactive': No such file or directory
>>> mkdir `/run/openrc/failed': No such file or directory
>>> mkdir `/run/openrc/hotplugged': No such file or directory
>>> mkdir `/run/openrc/daemons': No such file or directory
>>> [ 14.554357] Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b
>>> [ 14.554357] ---[ end Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b ]---
>>> mkdir `/run/openrc/options': No such file or directory
>>> mkdir `/run/openrc/exclusive': No such file or directory
>>> mkdir `/run/openrc/scheduled': No such file or directory
>>> mkdir `/run/openrc/tmp': No such file or directory
>>>
>>>> https://marc.info/?l=linux-ia64&m=161187470709706&w=1
>>>>
>>>> if needed?
>>>
>>> Two patches above do fix the boot \o/ But have a lot of spam about
>>> 'signal 0' delivery to a bunch of processes:
>>>
>>> * Mounting /proc ...
>>> [ ok ]
>>> * Mounting /run ...
>>> * /run/openrc: creating directory
>>> * /run/lock: creating directory
>>> * /run/lock: correcting owner
>>> * Caching service dependencies ...
>>> [ ok ]
>>> * Mounting /sys ...
>>> [ ok ]
>>> * Mounting debug filesystem ...
>>> [ ok ]
>>> * Mounting efivarfs filesystem ...
>>> [ ok ]
>>> * sysfs: caught unknown signal 0
>>> * openrc: caught unknown signal 0
>>> * Mounting cgroup filesystem ...
>>
>> That's an improvement! Let me take a look at this tonight and see if I
>> can figure out what's going on. But yes, it's the ia64 signal delivery
>> being just different enough from the norm that it apparently triggers
>> some weirdness.
>
> Is this any better?

And if that one works, can you try this basic variant?


diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c
index e67b22fc3c60..c1b299760bf7 100644
--- a/arch/ia64/kernel/signal.c
+++ b/arch/ia64/kernel/signal.c
@@ -341,7 +341,8 @@ ia64_do_signal (struct sigscratch *scr, long in_syscall)
* need to push through a forced SIGSEGV.
*/
while (1) {
- get_signal(&ksig);
+ if (!get_signal(&ksig))
+ break;

/*
* get_signal() may have run a debugger (via notify_parent())

--
Jens Axboe