[ Upstream commit a382f8fee4 ]
These are indeed "should not happen" situations, but it turns out recent
changes made the 'task_is_stopped_or_trace()' case trigger (fix for that
exists, is pending more testing), and the BUG_ON() makes it
unnecessarily hard to actually debug for no good reason.
It's been that way for a long time, but let's make it clear: BUG_ON() is
not good for debugging, and should never be used in situations where you
could just say "this shouldn't happen, but we can continue".
Use WARN_ON_ONCE() instead to make sure it gets logged, and then just
continue running. Instead of making the system basically unusuable
because you crashed the machine while potentially holding some very core
locks (eg this function is commonly called while holding 'tasklist_lock'
for writing).
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 78ed93d72d ]
With SIGTRAP on perf events, we have encountered termination of
processes due to user space attempting to block delivery of SIGTRAP.
Consider this case:
<set up SIGTRAP on a perf event>
...
sigset_t s;
sigemptyset(&s);
sigaddset(&s, SIGTRAP | <and others>);
sigprocmask(SIG_BLOCK, &s, ...);
...
<perf event triggers>
When the perf event triggers, while SIGTRAP is blocked, force_sig_perf()
will force the signal, but revert back to the default handler, thus
terminating the task.
This makes sense for error conditions, but not so much for explicitly
requested monitoring. However, the expectation is still that signals
generated by perf events are synchronous, which will no longer be the
case if the signal is blocked and delivered later.
To give user space the ability to clearly distinguish synchronous from
asynchronous signals, introduce siginfo_t::si_perf_flags and
TRAP_PERF_FLAG_ASYNC (opted for flags in case more binary information is
required in future).
The resolution to the problem is then to (a) no longer force the signal
(avoiding the terminations), but (b) tell user space via si_perf_flags
if the signal was synchronous or not, so that such signals can be
handled differently (e.g. let user space decide to ignore or consider
the data imprecise).
The alternative of making the kernel ignore SIGTRAP on perf events if
the signal is blocked may work for some usecases, but likely causes
issues in others that then have to revert back to interception of
sigprocmask() (which we want to avoid). [ A concrete example: when using
breakpoint perf events to track data-flow, in a region of code where
signals are blocked, data-flow can no longer be tracked accurately.
When a relevant asynchronous signal is received after unblocking the
signal, the data-flow tracking logic needs to know its state is
imprecise. ]
Fixes: 97ba62b278 ("perf: Add support for SIGTRAP on perf events")
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Link: https://lore.kernel.org/r/20220404111204.935357-1-elver@google.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit e7f7c99ba9 ]
Recently while investigating a problem with rr and signals I noticed
that siglock is dropped in ptrace_signal and get_signal does not jump
to relock.
Looking farther to see if the problem is anywhere else I see that
do_signal_stop also returns if signal_group_exit is true. I believe
that test can now never be true, but it is a bit hard to trace
through and be certain.
Testing signal_group_exit is not expensive, so move the test for
signal_group_exit into the for loop inside of get_signal to ensure
the test is never skipped improperly.
This has been a potential problem since I added the test for
signal_group_exit was added.
Fixes: 35634ffa17 ("signal: Always notice exiting tasks")
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/875yssekcd.fsf_-_@email.froward.int.ebiederm.org
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit 5c72263ef2 upstream.
Fatal SIGSYS signals (i.e. seccomp RET_KILL_* syscall filter actions)
were not being delivered to ptraced pid namespace init processes. Make
sure the SIGNAL_UNKILLABLE doesn't get set for these cases.
Reported-by: Robert Święcki <robert@swiecki.net>
Suggested-by: "Eric W. Biederman" <ebiederm@xmission.com>
Fixes: 00b06da29c ("signal: Add SA_IMMUTABLE to ensure forced siganls do not get changed")
Cc: stable@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: "Eric W. Biederman" <ebiederm@xmission.com>
Link: https://lore.kernel.org/lkml/878rui8u4a.fsf@email.froward.int.ebiederm.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit fcb116bc43 upstream.
Recently to prevent issues with SECCOMP_RET_KILL and similar signals
being changed before they are delivered SA_IMMUTABLE was added.
Unfortunately this broke debuggers[1][2] which reasonably expect
to be able to trap synchronous SIGTRAP and SIGSEGV even when
the target process is not configured to handle those signals.
Add force_exit_sig and use it instead of force_fatal_sig where
historically the code has directly called do_exit. This has the
implementation benefits of going through the signal exit path
(including generating core dumps) without the danger of allowing
userspace to ignore or change these signals.
This avoids userspace regressions as older kernels exited with do_exit
which debuggers also can not intercept.
In the future is should be possible to improve the quality of
implementation of the kernel by changing some of these force_exit_sig
calls to force_fatal_sig. That can be done where it matters on
a case-by-case basis with careful analysis.
Reported-by: Kyle Huey <me@kylehuey.com>
Reported-by: kernel test robot <oliver.sang@intel.com>
[1] https://lkml.kernel.org/r/CAP045AoMY4xf8aC_4QU_-j7obuEPYgTcnQQP3Yxk=2X90jtpjw@mail.gmail.com
[2] https://lkml.kernel.org/r/20211117150258.GB5403@xsang-OptiPlex-9020
Fixes: 00b06da29c ("signal: Add SA_IMMUTABLE to ensure forced siganls do not get changed")
Fixes: a3616a3c02 ("signal/m68k: Use force_sigsegv(SIGSEGV) in fpsp040_die")
Fixes: 83a1f27ad7 ("signal/powerpc: On swapcontext failure force SIGSEGV")
Fixes: 9bc508cf07 ("signal/s390: Use force_sigsegv in default_trap_handler")
Fixes: 086ec444f8 ("signal/sparc32: In setup_rt_frame and setup_fram use force_fatal_sig")
Fixes: c317d306d5 ("signal/sparc32: Exit with a fatal signal when try_to_clear_window_buffer fails")
Fixes: 695dd0d634 ("signal/x86: In emulate_vsyscall force a signal instead of calling do_exit")
Fixes: 1fbd60df8a ("signal/vm86_32: Properly send SIGSEGV when the vm86 state cannot be saved.")
Fixes: 941edc5bf1 ("exit/syscall_user_dispatch: Send ordinary signals on failure")
Link: https://lkml.kernel.org/r/871r3dqfv8.fsf_-_@email.froward.int.ebiederm.org
Reviewed-by: Kees Cook <keescook@chromium.org>
Tested-by: Kees Cook <keescook@chromium.org>
Tested-by: Kyle Huey <khuey@kylehuey.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Thomas Backlund <tmb@iki.fi>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit e349d945fa upstream.
Recently to prevent issues with SECCOMP_RET_KILL and similar signals
being changed before they are delivered SA_IMMUTABLE was added.
Unfortunately this broke debuggers[1][2] which reasonably expect to be
able to trap synchronous SIGTRAP and SIGSEGV even when the target
process is not configured to handle those signals.
Update force_sig_to_task to support both the case when we can allow
the debugger to intercept and possibly ignore the signal and the case
when it is not safe to let userspace know about the signal until the
process has exited.
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Reported-by: Kyle Huey <me@kylehuey.com>
Reported-by: kernel test robot <oliver.sang@intel.com>
Cc: stable@vger.kernel.org
[1] https://lkml.kernel.org/r/CAP045AoMY4xf8aC_4QU_-j7obuEPYgTcnQQP3Yxk=2X90jtpjw@mail.gmail.com
[2] https://lkml.kernel.org/r/20211117150258.GB5403@xsang-OptiPlex-9020
Fixes: 00b06da29c ("signal: Add SA_IMMUTABLE to ensure forced siganls do not get changed")
Link: https://lkml.kernel.org/r/877dd5qfw5.fsf_-_@email.froward.int.ebiederm.org
Reviewed-by: Kees Cook <keescook@chromium.org>
Tested-by: Kees Cook <keescook@chromium.org>
Tested-by: Kyle Huey <khuey@kylehuey.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Thomas Backlund <tmb@iki.fi>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 26d5badbcc upstream.
Add a simple helper force_fatal_sig that causes a signal to be
delivered to a process as if the signal handler was set to SIG_DFL.
Reimplement force_sigsegv based upon this new helper. This fixes
force_sigsegv so that when it forces the default signal handler
to be used the code now forces the signal to be unblocked as well.
Reusing the tested logic in force_sig_info_to_task that was built for
force_sig_seccomp this makes the implementation trivial.
This is interesting both because it makes force_sigsegv simpler and
because there are a couple of buggy places in the kernel that call
do_exit(SIGILL) or do_exit(SIGSYS) because there is no straight
forward way today for those places to simply force the exit of a
process with the chosen signal. Creating force_fatal_sig allows
those places to be implemented with normal signal exits.
Link: https://lkml.kernel.org/r/20211020174406.17889-13-ebiederm@xmission.com
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Cc: Thomas Backlund <tmb@iki.fi>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 00b06da29c upstream.
As Andy pointed out that there are races between
force_sig_info_to_task and sigaction[1] when force_sig_info_task. As
Kees discovered[2] ptrace is also able to change these signals.
In the case of seeccomp killing a process with a signal it is a
security violation to allow the signal to be caught or manipulated.
Solve this problem by introducing a new flag SA_IMMUTABLE that
prevents sigaction and ptrace from modifying these forced signals.
This flag is carefully made kernel internal so that no new ABI is
introduced.
Longer term I think this can be solved by guaranteeing short circuit
delivery of signals in this case. Unfortunately reliable and
guaranteed short circuit delivery of these signals is still a ways off
from being implemented, tested, and merged. So I have implemented a much
simpler alternative for now.
[1] https://lkml.kernel.org/r/b5d52d25-7bde-4030-a7b1-7c6f8ab90660@www.fastmail.com
[2] https://lkml.kernel.org/r/202110281136.5CE65399A7@keescook
Cc: stable@vger.kernel.org
Fixes: 307d522f5e ("signal/seccomp: Refactor seccomp signal and coredump generation")
Tested-by: Andrea Righi <andrea.righi@canonical.com>
Tested-by: Kees Cook <keescook@chromium.org>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 7d613f9f72 upstream.
The existence of sigkill_pending is a little silly as it is
functionally a duplicate of fatal_signal_pending that is used in
exactly one place.
Checking for pending fatal signals and returning early in ptrace_stop
is actively harmful. It casues the ptrace_stop called by
ptrace_signal to return early before setting current->exit_code.
Later when ptrace_signal reads the signal number from
current->exit_code is undefined, making it unpredictable what will
happen.
Instead rely on the fact that schedule will not sleep if there is a
pending signal that can awaken a task.
Removing the explict sigkill_pending test fixes fixes ptrace_signal
when ptrace_stop does not stop because current->exit_code is always
set to to signr.
Cc: stable@vger.kernel.org
Fixes: 3d749b9e67 ("ptrace: simplify ptrace_stop()->sigkill_pending() path")
Fixes: 1a669c2f16 ("Add arch_ptrace_stop")
Link: https://lkml.kernel.org/r/87pmsyx29t.fsf@disp2133
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Pull ucounts fixes from Eric Biederman:
"There has been one very hard to track down bug in the ucount code that
we have been tracking since roughly v5.14 was released. Alex managed
to find a reliable reproducer a few days ago and then I was able to
instrument the code and figure out what the issue was.
It turns out the sigqueue_alloc single atomic operation optimization
did not play nicely with ucounts multiple level rlimits. It turned out
that either sigqueue_alloc or sigqueue_free could be operating on
multiple levels and trigger the conditions for the optimization on
more than one level at the same time.
To deal with that situation I have introduced inc_rlimit_get_ucounts
and dec_rlimit_put_ucounts that just focuses on the optimization and
the rlimit and ucount changes.
While looking into the big bug I found I couple of other little issues
so I am including those fixes here as well.
When I have time I would very much like to dig into process ownership
of the shared signal queue and see if we could pick a single owner for
the entire queue so that all of the rlimits can count to that owner.
That should entirely remove the need to call get_ucounts and
put_ucounts in sigqueue_alloc and sigqueue_free. It is difficult
because Linux unlike POSIX supports setuid that works on a single
thread"
* 'ucount-fixes-for-v5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
ucounts: Move get_ucounts from cred_alloc_blank to key_change_session_keyring
ucounts: Proper error handling in set_cred_ucounts
ucounts: Pair inc_rlimit_ucounts with dec_rlimit_ucoutns in commit_creds
ucounts: Fix signal ucount refcounting
In commit fda31c5029 ("signal: avoid double atomic counter
increments for user accounting") Linus made a clever optimization to
how rlimits and the struct user_struct. Unfortunately that
optimization does not work in the obvious way when moved to nested
rlimits. The problem is that the last decrement of the per user
namespace per user sigpending counter might also be the last decrement
of the sigpending counter in the parent user namespace as well. Which
means that simply freeing the leaf ucount in __free_sigqueue is not
enough.
Maintain the optimization and handle the tricky cases by introducing
inc_rlimit_get_ucounts and dec_rlimit_put_ucounts.
By moving the entire optimization into functions that perform all of
the work it becomes possible to ensure that every level is handled
properly.
The new function inc_rlimit_get_ucounts returns 0 on failure to
increment the ucount. This is different than inc_rlimit_ucounts which
increments the ucounts and returns LONG_MAX if the ucount counter has
exceeded it's maximum or it wrapped (to indicate the counter needs to
decremented).
I wish we had a single user to account all pending signals to across
all of the threads of a process so this complexity was not necessary
Cc: stable@vger.kernel.org
Fixes: d646969055 ("Reimplement RLIMIT_SIGPENDING on top of ucounts")
v1: https://lkml.kernel.org/r/87mtnavszx.fsf_-_@disp2133
Link: https://lkml.kernel.org/r/87fssytizw.fsf_-_@disp2133
Reviewed-by: Alexey Gladkov <legion@kernel.org>
Tested-by: Rune Kleveland <rune.kleveland@infomedia.dk>
Tested-by: Yu Zhao <yuzhao@google.com>
Tested-by: Jordan Glover <Golden_Miller83@protonmail.ch>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Merge misc updates from Andrew Morton:
"173 patches.
Subsystems affected by this series: ia64, ocfs2, block, and mm (debug,
pagecache, gup, swap, shmem, memcg, selftests, pagemap, mremap,
bootmem, sparsemem, vmalloc, kasan, pagealloc, memory-failure,
hugetlb, userfaultfd, vmscan, compaction, mempolicy, memblock,
oom-kill, migration, ksm, percpu, vmstat, and madvise)"
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (173 commits)
mm/madvise: add MADV_WILLNEED to process_madvise()
mm/vmstat: remove unneeded return value
mm/vmstat: simplify the array size calculation
mm/vmstat: correct some wrong comments
mm/percpu,c: remove obsolete comments of pcpu_chunk_populated()
selftests: vm: add COW time test for KSM pages
selftests: vm: add KSM merging time test
mm: KSM: fix data type
selftests: vm: add KSM merging across nodes test
selftests: vm: add KSM zero page merging test
selftests: vm: add KSM unmerge test
selftests: vm: add KSM merge test
mm/migrate: correct kernel-doc notation
mm: wire up syscall process_mrelease
mm: introduce process_mrelease system call
memblock: make memblock_find_in_range method private
mm/mempolicy.c: use in_task() in mempolicy_slab_node()
mm/mempolicy: unify the create() func for bind/interleave/prefer-many policies
mm/mempolicy: advertise new MPOL_PREFERRED_MANY
mm/hugetlb: add support for mempolicy MPOL_PREFERRED_MANY
...
When a user send a signal to any another processes it forces the kernel to
allocate memory for 'struct sigqueue' objects. The number of signals is
limited by RLIMIT_SIGPENDING resource limit, but even the default settings
allow each user to consume up to several megabytes of memory.
It makes sense to account for these allocations to restrict the host's
memory consumption from inside the memcg-limited container.
Link: https://lkml.kernel.org/r/e34e958c-e785-712e-a62a-2c7b66c646c7@virtuozzo.com
Signed-off-by: Vasily Averin <vvs@virtuozzo.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrei Vagin <avagin@gmail.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Borislav Petkov <bp@suse.de>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Dmitry Safonov <0x7f454c46@gmail.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "J. Bruce Fields" <bfields@fieldses.org>
Cc: Jeff Layton <jlayton@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jiri Slaby <jirislaby@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Serge Hallyn <serge@hallyn.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Yutian Yang <nglaive@gmail.com>
Cc: Zefan Li <lizefan.x@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull exit cleanups from Eric Biederman:
"In preparation of doing something about PTRACE_EVENT_EXIT I have
started cleaning up various pieces of code related to do_exit. Most of
that code I did not manage to get tested and reviewed before the merge
window opened but a handful of very useful cleanups are ready to be
merged.
The first change is simply the removal of the bdflush system call. The
code has now been disabled long enough that even the oldest userspace
working userspace setups anyone can find to test are fine with the
bdflush system call being removed.
Changing m68k fsp040_die to use force_sigsegv(SIGSEGV) instead of
calling do_exit directly is interesting only in that it is nearly the
most difficult of the incorrect uses of do_exit to remove.
The change to the seccomp code to simply send a signal instead of
calling do_coredump directly is a very nice little cleanup made
possible by realizing the existing signal sending helpers were missing
a little bit of functionality that is easy to provide"
* 'exit-cleanups-for-v5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
signal/seccomp: Dump core when there is only one live thread
signal/seccomp: Refactor seccomp signal and coredump generation
signal/m68k: Use force_sigsegv(SIGSEGV) in fpsp040_die
exit/bdflush: Remove the deprecated bdflush system call
Pull siginfo si_trapno updates from Eric Biederman:
"The full set of si_trapno changes was not appropriate as a fix for the
newly added SIGTRAP TRAP_PERF, and so I postponed the rest of the
related cleanups.
This is the rest of the cleanups for si_trapno that reduces it from
being a really weird arch special case that is expect to be always
present (but isn't) on the architectures that support it to being yet
another field in the _sigfault union of struct siginfo.
The changes have been reviewed and marinated in linux-next. With the
removal of this awkward special case new code (like SIGTRAP TRAP_PERF)
that works across architectures should be easier to write and
maintain"
* 'siginfo-si_trapno-for-v5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
signal: Rename SIL_PERF_EVENT SIL_FAULT_PERF_EVENT for consistency
signal: Verify the alignment and size of siginfo_t
signal: Remove the generic __ARCH_SI_TRAPNO support
signal/alpha: si_trapno is only used with SIGFPE and SIGTRAP TRAP_UNK
signal/sparc: si_trapno is only used with SIGILL ILL_ILLTRP
arm64: Add compile-time asserts for siginfo_t offsets
arm: Add compile-time asserts for siginfo_t offsets
sparc64: Add compile-time asserts for siginfo_t offsets
Factor out force_sig_seccomp from the seccomp signal generation and
place it in kernel/signal.c. The function force_sig_seccomp takes a
parameter force_coredump to indicate that the sigaction field should
be reset to SIGDFL so that a coredump will be generated when the
signal is delivered.
force_sig_seccomp is then used to replace both seccomp_send_sigsys
and seccomp_init_siginfo.
force_sig_info_to_task gains an extra parameter to force using
the default signal action.
With this change seccomp is no longer a special case and there
becomes exactly one place do_coredump is called from.
Further it no longer becomes necessary for __seccomp_filter
to call do_group_exit.
Acked-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/87r1gr6qc4.fsf_-_@disp2133
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Starting the process wide cputime counter needs to be done in the same
sighand locking sequence than actually arming the related timer otherwise
this races against concurrent timers setting/expiring in the same
threadgroup.
Detecting that the cputime counter is started without holding the sighand
lock is a first step toward debugging such situations.
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210726125513.271824-2-frederic@kernel.org
Now that __ARCH_SI_TRAPNO is no longer set by any architecture remove
all of the code it enabled from the kernel.
On alpha and sparc a more explict approach of using
send_sig_fault_trapno or force_sig_fault_trapno in the very limited
circumstances where si_trapno was set to a non-zero value.
The generic support that is being removed always set si_trapno on all
fault signals. With only SIGILL ILL_ILLTRAP on sparc and SIGFPE and
SIGTRAP TRAP_UNK on alpla providing si_trapno values asking all senders
of fault signals to provide an si_trapno value does not make sense.
Making si_trapno an ordinary extension of the fault siginfo layout has
enabled the architecture generic implementation of SIGTRAP TRAP_PERF,
and enables other faulting signals to grow architecture generic
senders as well.
v1: https://lkml.kernel.org/r/m18s4zs7nu.fsf_-_@fess.ebiederm.org
v2: https://lkml.kernel.org/r/20210505141101.11519-8-ebiederm@xmission.com
Link: https://lkml.kernel.org/r/87bl73xx6x.fsf_-_@disp2133
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
We must properly handle an errors when we increase the rlimit counter
and the ucounts reference counter. We have to this with RCU protection
to prevent possible use-after-free that could occur due to concurrent
put_cred_rcu().
The following reproducer triggers the problem:
$ cat testcase.sh
case "${STEP:-0}" in
0)
ulimit -Si 1
ulimit -Hi 1
STEP=1 unshare -rU "$0"
killall sleep
;;
1)
for i in 1 2 3 4 5; do unshare -rU sleep 5 & done
;;
esac
with the KASAN report being along the lines of
BUG: KASAN: use-after-free in put_ucounts+0x17/0xa0
Write of size 4 at addr ffff8880045f031c by task swapper/2/0
CPU: 2 PID: 0 Comm: swapper/2 Not tainted 5.13.0+ #19
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.14.0-alt4 04/01/2014
Call Trace:
<IRQ>
put_ucounts+0x17/0xa0
put_cred_rcu+0xd5/0x190
rcu_core+0x3bf/0xcb0
__do_softirq+0xe3/0x341
irq_exit_rcu+0xbe/0xe0
sysvec_apic_timer_interrupt+0x6a/0x90
</IRQ>
asm_sysvec_apic_timer_interrupt+0x12/0x20
default_idle_call+0x53/0x130
do_idle+0x311/0x3c0
cpu_startup_entry+0x14/0x20
secondary_startup_64_no_verify+0xc2/0xcb
Allocated by task 127:
kasan_save_stack+0x1b/0x40
__kasan_kmalloc+0x7c/0x90
alloc_ucounts+0x169/0x2b0
set_cred_ucounts+0xbb/0x170
ksys_unshare+0x24c/0x4e0
__x64_sys_unshare+0x16/0x20
do_syscall_64+0x37/0x70
entry_SYSCALL_64_after_hwframe+0x44/0xae
Freed by task 0:
kasan_save_stack+0x1b/0x40
kasan_set_track+0x1c/0x30
kasan_set_free_info+0x20/0x30
__kasan_slab_free+0xeb/0x120
kfree+0xaa/0x460
put_cred_rcu+0xd5/0x190
rcu_core+0x3bf/0xcb0
__do_softirq+0xe3/0x341
The buggy address belongs to the object at ffff8880045f0300
which belongs to the cache kmalloc-192 of size 192
The buggy address is located 28 bytes inside of
192-byte region [ffff8880045f0300, ffff8880045f03c0)
The buggy address belongs to the page:
page:000000008de0a388 refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff8880045f0000 pfn:0x45f0
flags: 0x100000000000200(slab|node=0|zone=1)
raw: 0100000000000200 ffffea00000f4640 0000000a0000000a ffff888001042a00
raw: ffff8880045f0000 000000008010000d 00000001ffffffff 0000000000000000
page dumped because: kasan: bad access detected
Memory state around the buggy address:
ffff8880045f0200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
ffff8880045f0280: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
>ffff8880045f0300: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
^
ffff8880045f0380: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
ffff8880045f0400: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================
Disabling lock debugging due to kernel taint
Fixes: d646969055 ("Reimplement RLIMIT_SIGPENDING on top of ucounts")
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Alexey Gladkov <legion@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Merge more updates from Andrew Morton:
"190 patches.
Subsystems affected by this patch series: mm (hugetlb, userfaultfd,
vmscan, kconfig, proc, z3fold, zbud, ras, mempolicy, memblock,
migration, thp, nommu, kconfig, madvise, memory-hotplug, zswap,
zsmalloc, zram, cleanups, kfence, and hmm), procfs, sysctl, misc,
core-kernel, lib, lz4, checkpatch, init, kprobes, nilfs2, hfs,
signals, exec, kcov, selftests, compress/decompress, and ipc"
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (190 commits)
ipc/util.c: use binary search for max_idx
ipc/sem.c: use READ_ONCE()/WRITE_ONCE() for use_global_lock
ipc: use kmalloc for msg_queue and shmid_kernel
ipc sem: use kvmalloc for sem_undo allocation
lib/decompressors: remove set but not used variabled 'level'
selftests/vm/pkeys: exercise x86 XSAVE init state
selftests/vm/pkeys: refill shadow register after implicit kernel write
selftests/vm/pkeys: handle negative sys_pkey_alloc() return code
selftests/vm/pkeys: fix alloc_random_pkey() to make it really, really random
kcov: add __no_sanitize_coverage to fix noinstr for all architectures
exec: remove checks in __register_bimfmt()
x86: signal: don't do sas_ss_reset() until we are certain that sigframe won't be abandoned
hfsplus: report create_date to kstat.btime
hfsplus: remove unnecessary oom message
nilfs2: remove redundant continue statement in a while-loop
kprobes: remove duplicated strong free_insn_page in x86 and s390
init: print out unknown kernel parameters
checkpatch: do not complain about positive return values starting with EPOLL
checkpatch: improve the indented label test
checkpatch: scripts/spdxcheck.py now requires python3
...
Currently we handle SS_AUTODISARM as soon as we have stored the altstack
settings into sigframe - that's the point when we have set the things up
for eventual sigreturn to restore the old settings. And if we manage to
set the sigframe up (we are not done with that yet), everything's fine.
However, in case of failure we end up with sigframe-to-be abandoned and
SIGSEGV force-delivered. And in that case we end up with inconsistent
rules - late failures have altstack reset, early ones do not.
It's trivial to get consistent behaviour - just handle SS_AUTODISARM once
we have set the sigframe up and are committed to entering the handler,
i.e. in signal_delivered().
Link: https://lore.kernel.org/lkml/20200404170604.GN23230@ZenIV.linux.org.uk/
Link: https://github.com/ClangBuiltLinux/linux/issues/876
Link: https://lkml.kernel.org/r/20210422230846.1756380-1-ndesaulniers@google.com
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Tested-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull user namespace rlimit handling update from Eric Biederman:
"This is the work mainly by Alexey Gladkov to limit rlimits to the
rlimits of the user that created a user namespace, and to allow users
to have stricter limits on the resources created within a user
namespace."
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
cred: add missing return error code when set_cred_ucounts() failed
ucounts: Silence warning in dec_rlimit_ucounts
ucounts: Set ucount_max to the largest positive value the type can hold
kselftests: Add test to check for rlimit changes in different user namespaces
Reimplement RLIMIT_MEMLOCK on top of ucounts
Reimplement RLIMIT_SIGPENDING on top of ucounts
Reimplement RLIMIT_MSGQUEUE on top of ucounts
Reimplement RLIMIT_NPROC on top of ucounts
Use atomic_t for ucounts reference counting
Add a reference to ucounts for each cred
Increase size of ucounts to atomic_long_t
- Changes to core scheduling facilities:
- Add "Core Scheduling" via CONFIG_SCHED_CORE=y, which enables
coordinated scheduling across SMT siblings. This is a much
requested feature for cloud computing platforms, to allow
the flexible utilization of SMT siblings, without exposing
untrusted domains to information leaks & side channels, plus
to ensure more deterministic computing performance on SMT
systems used by heterogenous workloads.
There's new prctls to set core scheduling groups, which
allows more flexible management of workloads that can share
siblings.
- Fix task->state access anti-patterns that may result in missed
wakeups and rename it to ->__state in the process to catch new
abuses.
- Load-balancing changes:
- Tweak newidle_balance for fair-sched, to improve
'memcache'-like workloads.
- "Age" (decay) average idle time, to better track & improve workloads
such as 'tbench'.
- Fix & improve energy-aware (EAS) balancing logic & metrics.
- Fix & improve the uclamp metrics.
- Fix task migration (taskset) corner case on !CONFIG_CPUSET.
- Fix RT and deadline utilization tracking across policy changes
- Introduce a "burstable" CFS controller via cgroups, which allows
bursty CPU-bound workloads to borrow a bit against their future
quota to improve overall latencies & batching. Can be tweaked
via /sys/fs/cgroup/cpu/<X>/cpu.cfs_burst_us.
- Rework assymetric topology/capacity detection & handling.
- Scheduler statistics & tooling:
- Disable delayacct by default, but add a sysctl to enable
it at runtime if tooling needs it. Use static keys and
other optimizations to make it more palatable.
- Use sched_clock() in delayacct, instead of ktime_get_ns().
- Misc cleanups and fixes.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
-----BEGIN PGP SIGNATURE-----
iQJFBAABCgAvFiEEBpT5eoXrXCwVQwEKEnMQ0APhK1gFAmDZcPoRHG1pbmdvQGtl
cm5lbC5vcmcACgkQEnMQ0APhK1g3yw//WfhIqy7Psa9d/MBMjQDRGbTuO4+w22Dj
vmWFU44Q4KJxQHWeIgUlrK+dzvYWvNmflUs2CUUOiDVzxFTHMIyBtL4qCBUbx4Ns
vKAcB9wsWZge2o3WzZqpProRhdoRaSKw8egUr2q7rACVBkckY7eGP/OjWxXU8BdA
b7D0LPWwuIBFfN4pFYeCDLn32Dqr9s6Chyj+ZecabdG7EE6Gu+f1diVcxy7JE/mc
4WWL0D1RqdgpGrBEuMJIxPYekdrZiuy4jtEbztz5gbTBteN1cj3BLfqn0Pc/e6rO
Vyuc5mXCAmzRVi18z6g6bsVl+IA/nrbErENB2OHOhOYtqiZxqGTd4GPWZszMyY17
5AsEO5+5pcaBsy4gyp09qURggBu9zhJnMVmOI3rIHZkmkhwzc6uUJlyhDCTiFWOz
3ZF3LjbZEyCKodMD8qMHbs3axIBpIfZqjzkvSKyFnvfXEGVytVse7NUuWtQ36u92
GnURxVeYY1TDVXvE1Y8owNKMxknKQ6YRlypP7Dtbeo/qG6hShp0xmS7qDLDi0ybZ
ZlK+bDECiVoDf3nvJo+8v5M82IJ3CBt4UYldeRJsa1YCK/FsbK8tp91fkEfnXVue
+U6LPX0AmMpXacR5HaZfb3uBIKRw/QMdP/7RFtBPhpV6jqCrEmuqHnpPQiEVtxwO
UmG7bt94Trk=
=3VDr
-----END PGP SIGNATURE-----
Merge tag 'sched-core-2021-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler udpates from Ingo Molnar:
- Changes to core scheduling facilities:
- Add "Core Scheduling" via CONFIG_SCHED_CORE=y, which enables
coordinated scheduling across SMT siblings. This is a much
requested feature for cloud computing platforms, to allow the
flexible utilization of SMT siblings, without exposing untrusted
domains to information leaks & side channels, plus to ensure more
deterministic computing performance on SMT systems used by
heterogenous workloads.
There are new prctls to set core scheduling groups, which allows
more flexible management of workloads that can share siblings.
- Fix task->state access anti-patterns that may result in missed
wakeups and rename it to ->__state in the process to catch new
abuses.
- Load-balancing changes:
- Tweak newidle_balance for fair-sched, to improve 'memcache'-like
workloads.
- "Age" (decay) average idle time, to better track & improve
workloads such as 'tbench'.
- Fix & improve energy-aware (EAS) balancing logic & metrics.
- Fix & improve the uclamp metrics.
- Fix task migration (taskset) corner case on !CONFIG_CPUSET.
- Fix RT and deadline utilization tracking across policy changes
- Introduce a "burstable" CFS controller via cgroups, which allows
bursty CPU-bound workloads to borrow a bit against their future
quota to improve overall latencies & batching. Can be tweaked via
/sys/fs/cgroup/cpu/<X>/cpu.cfs_burst_us.
- Rework assymetric topology/capacity detection & handling.
- Scheduler statistics & tooling:
- Disable delayacct by default, but add a sysctl to enable it at
runtime if tooling needs it. Use static keys and other
optimizations to make it more palatable.
- Use sched_clock() in delayacct, instead of ktime_get_ns().
- Misc cleanups and fixes.
* tag 'sched-core-2021-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (72 commits)
sched/doc: Update the CPU capacity asymmetry bits
sched/topology: Rework CPU capacity asymmetry detection
sched/core: Introduce SD_ASYM_CPUCAPACITY_FULL sched_domain flag
psi: Fix race between psi_trigger_create/destroy
sched/fair: Introduce the burstable CFS controller
sched/uclamp: Fix uclamp_tg_restrict()
sched/rt: Fix Deadline utilization tracking during policy change
sched/rt: Fix RT utilization tracking during policy change
sched: Change task_struct::state
sched,arch: Remove unused TASK_STATE offsets
sched,timer: Use __set_current_state()
sched: Add get_current_state()
sched,perf,kvm: Fix preemption condition
sched: Introduce task_is_running()
sched: Unbreak wakeups
sched/fair: Age the average idle time
sched/cpufreq: Consider reduced CPU capacity in energy calculation
sched/fair: Take thermal pressure into account while estimating energy
thermal/cpufreq_cooling: Update offline CPUs per-cpu thermal_pressure
sched/fair: Return early from update_tg_cfs_load() if delta == 0
...
This reverts commits 4bad58ebc8 (and
399f8dd9a8, which tried to fix it).
I do not believe these are correct, and I'm about to release 5.13, so am
reverting them out of an abundance of caution.
The locking is odd, and appears broken.
On the allocation side (in __sigqueue_alloc()), the locking is somewhat
straightforward: it depends on sighand->siglock. Since one caller
doesn't hold that lock, it further then tests 'sigqueue_flags' to avoid
the case with no locks held.
On the freeing side (in sigqueue_cache_or_free()), there is no locking
at all, and the logic instead depends on 'current' being a single
thread, and not able to race with itself.
To make things more exciting, there's also the data race between freeing
a signal and allocating one, which is handled by using WRITE_ONCE() and
READ_ONCE(), and being mutually exclusive wrt the initial state (ie
freeing will only free if the old state was NULL, while allocating will
obviously only use the value if it was non-NULL, so only one or the
other will actually act on the value).
However, while the free->alloc paths do seem mutually exclusive thanks
to just the data value dependency, it's not clear what the memory
ordering constraints are on it. Could writes from the previous
allocation possibly be delayed and seen by the new allocation later,
causing logical inconsistencies?
So it's all very exciting and unusual.
And in particular, it seems that the freeing side is incorrect in
depending on "current" being single-threaded. Yes, 'current' is a
single thread, but in the presense of asynchronous events even a single
thread can have data races.
And such asynchronous events can and do happen, with interrupts causing
signals to be flushed and thus free'd (for example - sending a
SIGCONT/SIGSTOP can happen from interrupt context, and can flush
previously queued process control signals).
So regardless of all the other questions about the memory ordering and
locking for this new cached allocation, the sigqueue_cache_or_free()
assumptions seem to be fundamentally incorrect.
It may be that people will show me the errors of my ways, and tell me
why this is all safe after all. We can reinstate it if so. But my
current belief is that the WRITE_ONCE() that sets the cached entry needs
to be a smp_store_release(), and the READ_ONCE() that finds a cached
entry needs to be a smp_load_acquire() to handle memory ordering
correctly.
And the sequence in sigqueue_cache_or_free() would need to either use a
lock or at least be interrupt-safe some way (perhaps by using something
like the percpu 'cmpxchg': it doesn't need to be SMP-safe, but like the
percpu operations it needs to be interrupt-safe).
Fixes: 399f8dd9a8 ("signal: Prevent sigqueue caching after task got released")
Fixes: 4bad58ebc8 ("signal: Allow tasks to cache one sigqueue struct")
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
syzbot reported a memory leak related to sigqueue caching.
The assumption that a task cannot cache a sigqueue after the signal handler
has been dropped and exit_task_sigqueue_cache() has been invoked turns out
to be wrong.
Such a task can still invoke release_task(other_task), which cleans up the
signals of 'other_task' and ends up in sigqueue_cache_or_free(), which in
turn will cache the signal because task->sigqueue_cache is NULL. That's
obviously bogus because nothing will free the cached signal of that task
anymore, so the cached item is leaked.
This happens when e.g. the last non-leader thread exits and reaps the
zombie leader.
Prevent this by setting tsk::sigqueue_cache to an error pointer value in
exit_task_sigqueue_cache() which forces any subsequent invocation of
sigqueue_cache_or_free() from that task to hand the sigqueue back to the
kmemcache.
Add comments to all relevant places.
Fixes: 4bad58ebc8 ("signal: Allow tasks to cache one sigqueue struct")
Reported-by: syzbot+0bac5fec63d4f399ba98@syzkaller.appspotmail.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/r/878s32g6j5.ffs@nanos.tec.linutronix.de
Replace a bunch of 'p->state == TASK_RUNNING' with a new helper:
task_is_running(p).
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Davidlohr Bueso <dave@stgolabs.net>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20210611082838.222401495@infradead.org
Pull siginfo fix from Eric Biederman:
"During the merge window an issue with si_perf and the siginfo ABI came
up. The alpha and sparc siginfo structure layout had changed with the
addition of SIGTRAP TRAP_PERF and the new field si_perf.
The reason only alpha and sparc were affected is that they are the
only architectures that use si_trapno.
Looking deeper it was discovered that si_trapno is used for only a few
select signals on alpha and sparc, and that none of the other
_sigfault fields past si_addr are used at all. Which means technically
no regression on alpha and sparc.
While the alignment concerns might be dismissed the abuse of si_errno
by SIGTRAP TRAP_PERF does have the potential to cause regressions in
existing userspace.
While we still have time before userspace starts using and depending
on the new definition siginfo for SIGTRAP TRAP_PERF this set of
changes cleans up siginfo_t.
- The si_trapno field is demoted from magic alpha and sparc status
and made an ordinary union member of the _sigfault member of
siginfo_t. Without moving it of course.
- si_perf is replaced with si_perf_data and si_perf_type ending the
abuse of si_errno.
- Unnecessary additions to signalfd_siginfo are removed"
* 'for-v5.13-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
signalfd: Remove SIL_PERF_EVENT fields from signalfd_siginfo
signal: Deliver all of the siginfo perf data in _perf
signal: Factor force_sig_perf out of perf_sigtrap
signal: Implement SIL_FAULT_TRAPNO
siginfo: Move si_trapno inside the union inside _si_fault
Now that si_trapno is part of the union in _si_fault and available on
all architectures, add SIL_FAULT_TRAPNO and update siginfo_layout to
return SIL_FAULT_TRAPNO when the code assumes si_trapno is valid.
There is room for future changes to reduce when si_trapno is valid but
this is all that is needed to make si_trapno and the other members of
the the union in _sigfault mutually exclusive.
Update the code that uses siginfo_layout to deal with SIL_FAULT_TRAPNO
and have the same code ignore si_trapno in in all other cases.
v1: https://lkml.kernel.org/r/m1o8dvs7s7.fsf_-_@fess.ebiederm.org
v2: https://lkml.kernel.org/r/20210505141101.11519-6-ebiederm@xmission.com
Link: https://lkml.kernel.org/r/20210517195748.8880-2-ebiederm@xmission.com
Reviewed-by: Marco Elver <elver@google.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
It turns out that linux uses si_trapno very sparingly, and as such it
can be considered extra information for a very narrow selection of
signals, rather than information that is present with every fault
reported in siginfo.
As such move si_trapno inside the union inside of _si_fault. This
results in no change in placement, and makes it eaiser
to extend _si_fault in the future as this reduces the number of
special cases. In particular with si_trapno included in the union it
is no longer a concern that the union must be pointer aligned on most
architectures because the union follows immediately after si_addr
which is a pointer.
This change results in a difference in siginfo field placement on
sparc and alpha for the fields si_addr_lsb, si_lower, si_upper,
si_pkey, and si_perf. These architectures do not implement the
signals that would use si_addr_lsb, si_lower, si_upper, si_pkey, and
si_perf. Further these architecture have not yet implemented the
userspace that would use si_perf.
The point of this change is in fact to correct these placement issues
before sparc or alpha grow userspace that cares. This change was
discussed[1] and the agreement is that this change is currently safe.
[1]: https://lkml.kernel.org/r/CAK8P3a0+uKYwL1NhY6Hvtieghba2hKYGD6hcKx5n8=4Gtt+pHA@mail.gmail.com
Acked-by: Marco Elver <elver@google.com>
v1: https://lkml.kernel.org/r/m1tunns7yf.fsf_-_@fess.ebiederm.org
v2: https://lkml.kernel.org/r/20210505141101.11519-5-ebiederm@xmission.com
Link: https://lkml.kernel.org/r/20210517195748.8880-1-ebiederm@xmission.com
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
The rlimit counter is tied to uid in the user_namespace. This allows
rlimit values to be specified in userns even if they are already
globally exceeded by the user. However, the value of the previous
user_namespaces cannot be exceeded.
Changelog
v11:
* Revert most of changes to fix performance issues.
v10:
* Fix memory leak on get_ucounts failure.
Signed-off-by: Alexey Gladkov <legion@kernel.org>
Link: https://lkml.kernel.org/r/df9d7764dddd50f28616b7840de74ec0f81711a8.1619094428.git.legion@kernel.org
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
- Clean up SCHED_DEBUG: move the decades old mess of sysctl, procfs and debugfs interfaces
to a unified debugfs interface.
- Signals: Allow caching one sigqueue object per task, to improve performance & latencies.
- Improve newidle_balance() irq-off latencies on systems with a large number of CPU cgroups.
- Improve energy-aware scheduling
- Improve the PELT metrics for certain workloads
- Reintroduce select_idle_smt() to improve load-balancing locality - but without the previous
regressions
- Add 'scheduler latency debugging': warn after long periods of pending need_resched. This
is an opt-in feature that requires the enabling of the LATENCY_WARN scheduler feature,
or the use of the resched_latency_warn_ms=xx boot parameter.
- CPU hotplug fixes for HP-rollback, and for the 'fail' interface. Fix remaining
balance_push() vs. hotplug holes/races
- PSI fixes, plus allow /proc/pressure/ files to be written by CAP_SYS_RESOURCE tasks as well
- Fix/improve various load-balancing corner cases vs. capacity margins
- Fix sched topology on systems with NUMA diameter of 3 or above
- Fix PF_KTHREAD vs to_kthread() race
- Minor rseq optimizations
- Misc cleanups, optimizations, fixes and smaller updates
Signed-off-by: Ingo Molnar <mingo@kernel.org>
-----BEGIN PGP SIGNATURE-----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=E7mz
-----END PGP SIGNATURE-----
Merge tag 'sched-core-2021-04-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar:
- Clean up SCHED_DEBUG: move the decades old mess of sysctl, procfs and
debugfs interfaces to a unified debugfs interface.
- Signals: Allow caching one sigqueue object per task, to improve
performance & latencies.
- Improve newidle_balance() irq-off latencies on systems with a large
number of CPU cgroups.
- Improve energy-aware scheduling
- Improve the PELT metrics for certain workloads
- Reintroduce select_idle_smt() to improve load-balancing locality -
but without the previous regressions
- Add 'scheduler latency debugging': warn after long periods of pending
need_resched. This is an opt-in feature that requires the enabling of
the LATENCY_WARN scheduler feature, or the use of the
resched_latency_warn_ms=xx boot parameter.
- CPU hotplug fixes for HP-rollback, and for the 'fail' interface. Fix
remaining balance_push() vs. hotplug holes/races
- PSI fixes, plus allow /proc/pressure/ files to be written by
CAP_SYS_RESOURCE tasks as well
- Fix/improve various load-balancing corner cases vs. capacity margins
- Fix sched topology on systems with NUMA diameter of 3 or above
- Fix PF_KTHREAD vs to_kthread() race
- Minor rseq optimizations
- Misc cleanups, optimizations, fixes and smaller updates
* tag 'sched-core-2021-04-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (61 commits)
cpumask/hotplug: Fix cpu_dying() state tracking
kthread: Fix PF_KTHREAD vs to_kthread() race
sched/debug: Fix cgroup_path[] serialization
sched,psi: Handle potential task count underflow bugs more gracefully
sched: Warn on long periods of pending need_resched
sched/fair: Move update_nohz_stats() to the CONFIG_NO_HZ_COMMON block to simplify the code & fix an unused function warning
sched/debug: Rename the sched_debug parameter to sched_verbose
sched,fair: Alternative sched_slice()
sched: Move /proc/sched_debug to debugfs
sched,debug: Convert sysctl sched_domains to debugfs
debugfs: Implement debugfs_create_str()
sched,preempt: Move preempt_dynamic to debug.c
sched: Move SCHED_DEBUG sysctl to debugfs
sched: Don't make LATENCYTOP select SCHED_DEBUG
sched: Remove sched_schedstats sysctl out from under SCHED_DEBUG
sched/numa: Allow runtime enabling/disabling of NUMA balance without SCHED_DEBUG
sched: Use cpu_dying() to fix balance_push vs hotplug-rollback
cpumask: Introduce DYING mask
cpumask: Make cpu_{online,possible,present,active}() inline
rseq: Optimise rseq_get_rseq_cs() and clear_rseq_cs()
...
- Improve Intel uncore PMU support:
- Parse uncore 'discovery tables' - a new hardware capability enumeration method
introduced on the latest Intel platforms. This table is in a well-defined PCI
namespace location and is read via MMIO. It is organized in an rbtree.
These uncore tables will allow the discovery of standard counter blocks, but
fancier counters still need to be enumerated explicitly.
- Add Alder Lake support
- Improve IIO stacks to PMON mapping support on Skylake servers
- Add Intel Alder Lake PMU support - which requires the introduction of 'hybrid' CPUs
and PMUs. Alder Lake is a mix of Golden Cove ('big') and Gracemont ('small' - Atom derived)
cores.
The CPU-side feature set is entirely symmetrical - but on the PMU side there's
core type dependent PMU functionality.
- Reduce data loss with CPU level hardware tracing on Intel PT / AUX profiling, by
fixing the AUX allocation watermark logic.
- Improve ring buffer allocation on NUMA systems
- Put 'struct perf_event' into their separate kmem_cache pool
- Add support for synchronous signals for select perf events. The immediate motivation
is to support low-overhead sampling-based race detection for user-space code. The
feature consists of the following main changes:
- Add thread-only event inheritance via perf_event_attr::inherit_thread, which limits
inheritance of events to CLONE_THREAD.
- Add the ability for events to not leak through exec(), via perf_event_attr::remove_on_exec.
- Allow the generation of SIGTRAP via perf_event_attr::sigtrap, extend siginfo with an u64
::si_perf, and add the breakpoint information to ::si_addr and ::si_perf if the event is
PERF_TYPE_BREAKPOINT.
The siginfo support is adequate for breakpoints right now - but the new field can be used
to introduce support for other types of metadata passed over siginfo as well.
- Misc fixes, cleanups and smaller updates.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
-----BEGIN PGP SIGNATURE-----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=NhQ7
-----END PGP SIGNATURE-----
Merge tag 'perf-core-2021-04-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf event updates from Ingo Molnar:
- Improve Intel uncore PMU support:
- Parse uncore 'discovery tables' - a new hardware capability
enumeration method introduced on the latest Intel platforms. This
table is in a well-defined PCI namespace location and is read via
MMIO. It is organized in an rbtree.
These uncore tables will allow the discovery of standard counter
blocks, but fancier counters still need to be enumerated
explicitly.
- Add Alder Lake support
- Improve IIO stacks to PMON mapping support on Skylake servers
- Add Intel Alder Lake PMU support - which requires the introduction of
'hybrid' CPUs and PMUs. Alder Lake is a mix of Golden Cove ('big')
and Gracemont ('small' - Atom derived) cores.
The CPU-side feature set is entirely symmetrical - but on the PMU
side there's core type dependent PMU functionality.
- Reduce data loss with CPU level hardware tracing on Intel PT / AUX
profiling, by fixing the AUX allocation watermark logic.
- Improve ring buffer allocation on NUMA systems
- Put 'struct perf_event' into their separate kmem_cache pool
- Add support for synchronous signals for select perf events. The
immediate motivation is to support low-overhead sampling-based race
detection for user-space code. The feature consists of the following
main changes:
- Add thread-only event inheritance via
perf_event_attr::inherit_thread, which limits inheritance of
events to CLONE_THREAD.
- Add the ability for events to not leak through exec(), via
perf_event_attr::remove_on_exec.
- Allow the generation of SIGTRAP via perf_event_attr::sigtrap,
extend siginfo with an u64 ::si_perf, and add the breakpoint
information to ::si_addr and ::si_perf if the event is
PERF_TYPE_BREAKPOINT.
The siginfo support is adequate for breakpoints right now - but the
new field can be used to introduce support for other types of
metadata passed over siginfo as well.
- Misc fixes, cleanups and smaller updates.
* tag 'perf-core-2021-04-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (53 commits)
signal, perf: Add missing TRAP_PERF case in siginfo_layout()
signal, perf: Fix siginfo_t by avoiding u64 on 32-bit architectures
perf/x86: Allow for 8<num_fixed_counters<16
perf/x86/rapl: Add support for Intel Alder Lake
perf/x86/cstate: Add Alder Lake CPU support
perf/x86/msr: Add Alder Lake CPU support
perf/x86/intel/uncore: Add Alder Lake support
perf: Extend PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE
perf/x86/intel: Add Alder Lake Hybrid support
perf/x86: Support filter_match callback
perf/x86/intel: Add attr_update for Hybrid PMUs
perf/x86: Add structures for the attributes of Hybrid PMUs
perf/x86: Register hybrid PMUs
perf/x86: Factor out x86_pmu_show_pmu_cap
perf/x86: Remove temporary pmu assignment in event_init
perf/x86/intel: Factor out intel_pmu_check_extra_regs
perf/x86/intel: Factor out intel_pmu_check_event_constraints
perf/x86/intel: Factor out intel_pmu_check_num_counters
perf/x86: Hybrid PMU support for extra_regs
perf/x86: Hybrid PMU support for event constraints
...
-----BEGIN PGP SIGNATURE-----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=ZMd+
-----END PGP SIGNATURE-----
Merge tag 'livepatching-for-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/livepatching/livepatching
Pull livepatching update from Petr Mladek:
- Use TIF_NOTIFY_SIGNAL infrastructure instead of the fake signal
* tag 'livepatching-for-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/livepatching/livepatching:
livepatch: Replace the fake signal sending with TIF_NOTIFY_SIGNAL infrastructure
Add the missing TRAP_PERF case in siginfo_layout() for interpreting the
layout correctly as SIL_PERF_EVENT instead of just SIL_FAULT. This
ensures the si_perf field is copied and not just the si_addr field.
This was caught and tested by running the perf_events/sigtrap_threads
kselftest as a 32-bit binary with a 64-bit kernel.
Fixes: fb6cc127e0 ("signal: Introduce TRAP_PERF si_code and si_perf to siginfo")
Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210422191823.79012-2-elver@google.com
Introduces the TRAP_PERF si_code, and associated siginfo_t field
si_perf. These will be used by the perf event subsystem to send signals
(if requested) to the task where an event occurred.
Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org> # m68k
Acked-by: Arnd Bergmann <arnd@arndb.de> # asm-generic
Link: https://lkml.kernel.org/r/20210408103605.1676875-6-elver@google.com
The idea for this originates from the real time tree to make signal
delivery for realtime applications more efficient. In quite some of these
application scenarios a control tasks signals workers to start their
computations. There is usually only one signal per worker on flight. This
works nicely as long as the kmem cache allocations do not hit the slow path
and cause latencies.
To cure this an optimistic caching was introduced (limited to RT tasks)
which allows a task to cache a single sigqueue in a pointer in task_struct
instead of handing it back to the kmem cache after consuming a signal. When
the next signal is sent to the task then the cached sigqueue is used
instead of allocating a new one. This solved the problem for this set of
application scenarios nicely.
The task cache is not preallocated so the first signal sent to a task goes
always to the cache allocator. The cached sigqueue stays around until the
task exits and is freed when task::sighand is dropped.
After posting this solution for mainline the discussion came up whether
this would be useful in general and should not be limited to realtime
tasks: https://lore.kernel.org/r/m11rcu7nbr.fsf@fess.ebiederm.org
One concern leading to the original limitation was to avoid a large amount
of pointlessly cached sigqueues in alive tasks. The other concern was
vs. RLIMIT_SIGPENDING as these cached sigqueues are not accounted for.
The accounting problem is real, but on the other hand slightly academic.
After gathering some statistics it turned out that after boot of a regular
distro install there are less than 10 sigqueues cached in ~1500 tasks.
In case of a 'mass fork and fire signal to child' scenario the extra 80
bytes of memory per task are well in the noise of the overall memory
consumption of the fork bomb.
If this should be limited then this would need an extra counter in struct
user, more atomic instructions and a seperate rlimit. Yet another tunable
which is mostly unused.
The caching is actually used. After boot and a full kernel compile on a
64CPU machine with make -j128 the number of 'allocations' looks like this:
From slab: 23996
From task cache: 52223
I.e. it reduces the number of slab cache operations by ~68%.
A typical pattern there is:
<...>-58490 __sigqueue_alloc: for 58488 from slab ffff8881132df460
<...>-58488 __sigqueue_free: cache ffff8881132df460
<...>-58488 __sigqueue_alloc: for 1149 from cache ffff8881103dc550
bash-1149 exit_task_sighand: free ffff8881132df460
bash-1149 __sigqueue_free: cache ffff8881103dc550
The interesting sequence is that the exiting task 58488 grabs the sigqueue
from bash's task cache to signal exit and bash sticks it back into it's own
cache. Lather, rinse and repeat.
The caching is probably not noticable for the general use case, but the
benefit for latency sensitive applications is clear. While kmem caches are
usually just serving from the fast path the slab merging (default) can
depending on the usage pattern of the merged slabs cause occasional slow
path allocations.
The time spared per cached entry is a few micro seconds per signal which is
not relevant for e.g. a kernel build, but for signal heavy workloads it's
measurable.
As there is no real downside of this caching mechanism making it
unconditionally available is preferred over more conditional code or new
magic tunables.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lkml.kernel.org/r/87sg4lbmxo.fsf@nanos.tec.linutronix.de
There is no point in having the conditional at the callsite.
Just hand in the allocation mode flag to __sigqueue_alloc() and use it to
initialize sigqueue::flags.
No functional change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210322092258.898677147@linutronix.de
Livepatch sends a fake signal to all remaining blocking tasks of a
running transition after a set period of time. It uses TIF_SIGPENDING
flag for the purpose. Commit 12db8b6900 ("entry: Add support for
TIF_NOTIFY_SIGNAL") added a generic infrastructure to achieve the same.
Replace our bespoke solution with the generic one.
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Acked-by: Joe Lawrence <joe.lawrence@redhat.com>
Signed-off-by: Miroslav Benes <mbenes@suse.cz>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
This reverts commit 4db4b1a0d1.
The IO threads allow and handle SIGSTOP now, so don't special case them
anymore in task_set_jobctl_pending().
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This reverts commit 6fb8f43ced.
The IO threads do allow signals now, including SIGSTOP, and we can allow
ptrace attach. Attaching won't reveal anything interesting for the IO
threads, but it will allow eg gdb to attach to a task with io_urings
and IO threads without complaining. And once attached, it will allow
the usual introspection into regular threads.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This reverts commit 5be28c8f85.
IO threads now take signals just fine, so there's no reason to limit them
specifically. Revert the change that prevented that from happening.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Right now we're never calling get_signal() from PF_IO_WORKER threads, but
in preparation for doing so, don't handle a fatal signal for them. The
workers have state they need to cleanup when exiting, so just return
instead of calling do_exit() on their behalf. The threads themselves will
detect a fatal signal and do proper shutdown.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Just like we don't allow normal signals to IO threads, don't deliver a
STOP to a task that has PF_IO_WORKER set. The IO threads don't take
signals in general, and have no means of flushing out a stop either.
Longer term, we may want to look into allowing stop of these threads,
as it relates to eg process freezing. For now, this prevents a spin
issue if a SIGSTOP is delivered to the parent task.
Reported-by: Stefan Metzmacher <metze@samba.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
They don't take signals individually, and even if they share signals with
the parent task, don't allow them to be delivered through the worker
thread. Linux does allow this kind of behavior for regular threads, but
it's really a compatability thing that we need not care about for the IO
threads.
Reported-by: Stefan Metzmacher <metze@samba.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Linus Torvalds
Marco Elver
Eric W. Biederman
Kees Cook
Vasily Averin
Frederic Weisbecker
Alexey Gladkov
Al Viro
Thomas Gleixner
Peter Zijlstra
Ingo Molnar
Miroslav Benes
Jens Axboe