commit dbb26055defd03d59f678cb5f2c992abe05b064a upstream.
David reported a futex/rtmutex state corruption. It's caused by the
following problem:
CPU0 CPU1 CPU2
l->owner=T1
rt_mutex_lock(l)
lock(l->wait_lock)
l->owner = T1 | HAS_WAITERS;
enqueue(T2)
boost()
unlock(l->wait_lock)
schedule()
rt_mutex_lock(l)
lock(l->wait_lock)
l->owner = T1 | HAS_WAITERS;
enqueue(T3)
boost()
unlock(l->wait_lock)
schedule()
signal(->T2) signal(->T3)
lock(l->wait_lock)
dequeue(T2)
deboost()
unlock(l->wait_lock)
lock(l->wait_lock)
dequeue(T3)
===> wait list is now empty
deboost()
unlock(l->wait_lock)
lock(l->wait_lock)
fixup_rt_mutex_waiters()
if (wait_list_empty(l)) {
owner = l->owner & ~HAS_WAITERS;
l->owner = owner
==> l->owner = T1
}
lock(l->wait_lock)
rt_mutex_unlock(l) fixup_rt_mutex_waiters()
if (wait_list_empty(l)) {
owner = l->owner & ~HAS_WAITERS;
cmpxchg(l->owner, T1, NULL)
===> Success (l->owner = NULL)
l->owner = owner
==> l->owner = T1
}
That means the problem is caused by fixup_rt_mutex_waiters() which does the
RMW to clear the waiters bit unconditionally when there are no waiters in
the rtmutexes rbtree.
This can be fatal: A concurrent unlock can release the rtmutex in the
fastpath because the waiters bit is not set. If the cmpxchg() gets in the
middle of the RMW operation then the previous owner, which just unlocked
the rtmutex is set as the owner again when the write takes place after the
successfull cmpxchg().
The solution is rather trivial: verify that the owner member of the rtmutex
has the waiters bit set before clearing it. This does not require a
cmpxchg() or other atomic operations because the waiters bit can only be
set and cleared with the rtmutex wait_lock held. It's also safe against the
fast path unlock attempt. The unlock attempt via cmpxchg() will either see
the bit set and take the slowpath or see the bit cleared and release it
atomically in the fastpath.
It's remarkable that the test program provided by David triggers on ARM64
and MIPS64 really quick, but it refuses to reproduce on x86-64, while the
problem exists there as well. That refusal might explain that this got not
discovered earlier despite the bug existing from day one of the rtmutex
implementation more than 10 years ago.
Thanks to David for meticulously instrumenting the code and providing the
information which allowed to decode this subtle problem.
Reported-by: David Daney <ddaney@caviumnetworks.com>
Tested-by: David Daney <david.daney@cavium.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Fixes: 23f78d4a03 ("[PATCH] pi-futex: rt mutex core")
Link: http://lkml.kernel.org/r/20161130210030.351136722@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 2c610022711675ee908b903d242f0b90e1db661f upstream.
While this prior commit:
54cf809b9512 ("locking,qspinlock: Fix spin_is_locked() and spin_unlock_wait()")
... fixes spin_is_locked() and spin_unlock_wait() for the usage
in ipc/sem and netfilter, it does not in fact work right for the
usage in task_work and futex.
So while the 2 locks crossed problem:
spin_lock(A) spin_lock(B)
if (!spin_is_locked(B)) spin_unlock_wait(A)
foo() foo();
... works with the smp_mb() injected by both spin_is_locked() and
spin_unlock_wait(), this is not sufficient for:
flag = 1;
smp_mb(); spin_lock()
spin_unlock_wait() if (!flag)
// add to lockless list
// iterate lockless list
... because in this scenario, the store from spin_lock() can be delayed
past the load of flag, uncrossing the variables and loosing the
guarantee.
This patch reworks spin_is_locked() and spin_unlock_wait() to work in
both cases by exploiting the observation that while the lock byte
store can be delayed, the contender must have registered itself
visibly in other state contained in the word.
It also allows for architectures to override both functions, as PPC
and ARM64 have an additional issue for which we currently have no
generic solution.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Giovanni Gherdovich <ggherdovich@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Pan Xinhui <xinhui.pan@linux.vnet.ibm.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Waiman Long <waiman.long@hpe.com>
Cc: Will Deacon <will.deacon@arm.com>
Fixes: 54cf809b9512 ("locking,qspinlock: Fix spin_is_locked() and spin_unlock_wait()")
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 920c720aa5aa3900a7f1689228fdfc2580a91e7e upstream.
Similar to commit b4b29f9485 ("locking/osq: Fix ordering of node
initialisation in osq_lock") the use of xchg_acquire() is
fundamentally broken with MCS like constructs.
Furthermore, it turns out we rely on the global transitivity of this
operation because the unlock path observes the pointer with a
READ_ONCE(), not an smp_load_acquire().
This is non-critical because the MCS code isn't actually used and
mostly serves as documentation, a stepping stone to the more complex
things we've build on top of the idea.
Reported-by: Andrea Parri <parri.andrea@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Fixes: 3552a07a9c ("locking/mcs: Use acquire/release semantics")
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The Cavium guys reported a soft lockup on their arm64 machine, caused by
commit c55a6ffa62 ("locking/osq: Relax atomic semantics"):
mutex_optimistic_spin+0x9c/0x1d0
__mutex_lock_slowpath+0x44/0x158
mutex_lock+0x54/0x58
kernfs_iop_permission+0x38/0x70
__inode_permission+0x88/0xd8
inode_permission+0x30/0x6c
link_path_walk+0x68/0x4d4
path_openat+0xb4/0x2bc
do_filp_open+0x74/0xd0
do_sys_open+0x14c/0x228
SyS_openat+0x3c/0x48
el0_svc_naked+0x24/0x28
This is because in osq_lock we initialise the node for the current CPU:
node->locked = 0;
node->next = NULL;
node->cpu = curr;
and then publish the current CPU in the lock tail:
old = atomic_xchg_acquire(&lock->tail, curr);
Once the update to lock->tail is visible to another CPU, the node is
then live and can be both read and updated by concurrent lockers.
Unfortunately, the ACQUIRE semantics of the xchg operation mean that
there is no guarantee the contents of the node will be visible before
lock tail is updated. This can lead to lock corruption when, for
example, a concurrent locker races to set the next field.
Fixes: c55a6ffa62 ("locking/osq: Relax atomic semantics"):
Reported-by: David Daney <ddaney@caviumnetworks.com>
Reported-by: Andrew Pinski <andrew.pinski@caviumnetworks.com>
Tested-by: Andrew Pinski <andrew.pinski@caviumnetworks.com>
Acked-by: Davidlohr Bueso <dave@stgolabs.net>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1449856001-21177-1-git-send-email-will.deacon@arm.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
__GFP_WAIT has been used to identify atomic context in callers that hold
spinlocks or are in interrupts. They are expected to be high priority and
have access one of two watermarks lower than "min" which can be referred
to as the "atomic reserve". __GFP_HIGH users get access to the first
lower watermark and can be called the "high priority reserve".
Over time, callers had a requirement to not block when fallback options
were available. Some have abused __GFP_WAIT leading to a situation where
an optimisitic allocation with a fallback option can access atomic
reserves.
This patch uses __GFP_ATOMIC to identify callers that are truely atomic,
cannot sleep and have no alternative. High priority users continue to use
__GFP_HIGH. __GFP_DIRECT_RECLAIM identifies callers that can sleep and
are willing to enter direct reclaim. __GFP_KSWAPD_RECLAIM to identify
callers that want to wake kswapd for background reclaim. __GFP_WAIT is
redefined as a caller that is willing to enter direct reclaim and wake
kswapd for background reclaim.
This patch then converts a number of sites
o __GFP_ATOMIC is used by callers that are high priority and have memory
pools for those requests. GFP_ATOMIC uses this flag.
o Callers that have a limited mempool to guarantee forward progress clear
__GFP_DIRECT_RECLAIM but keep __GFP_KSWAPD_RECLAIM. bio allocations fall
into this category where kswapd will still be woken but atomic reserves
are not used as there is a one-entry mempool to guarantee progress.
o Callers that are checking if they are non-blocking should use the
helper gfpflags_allow_blocking() where possible. This is because
checking for __GFP_WAIT as was done historically now can trigger false
positives. Some exceptions like dm-crypt.c exist where the code intent
is clearer if __GFP_DIRECT_RECLAIM is used instead of the helper due to
flag manipulations.
o Callers that built their own GFP flags instead of starting with GFP_KERNEL
and friends now also need to specify __GFP_KSWAPD_RECLAIM.
The first key hazard to watch out for is callers that removed __GFP_WAIT
and was depending on access to atomic reserves for inconspicuous reasons.
In some cases it may be appropriate for them to use __GFP_HIGH.
The second key hazard is callers that assembled their own combination of
GFP flags instead of starting with something like GFP_KERNEL. They may
now wish to specify __GFP_KSWAPD_RECLAIM. It's almost certainly harmless
if it's missed in most cases as other activity will wake kswapd.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Vitaly Wool <vitalywool@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull scheduler changes from Ingo Molnar:
"The main changes in this cycle were:
- sched/fair load tracking fixes and cleanups (Byungchul Park)
- Make load tracking frequency scale invariant (Dietmar Eggemann)
- sched/deadline updates (Juri Lelli)
- stop machine fixes, cleanups and enhancements for bugs triggered by
CPU hotplug stress testing (Oleg Nesterov)
- scheduler preemption code rework: remove PREEMPT_ACTIVE and related
cleanups (Peter Zijlstra)
- Rework the sched_info::run_delay code to fix races (Peter Zijlstra)
- Optimize per entity utilization tracking (Peter Zijlstra)
- ... misc other fixes, cleanups and smaller updates"
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (57 commits)
sched: Don't scan all-offline ->cpus_allowed twice if !CONFIG_CPUSETS
sched: Move cpu_active() tests from stop_two_cpus() into migrate_swap_stop()
sched: Start stopper early
stop_machine: Kill cpu_stop_threads->setup() and cpu_stop_unpark()
stop_machine: Kill smp_hotplug_thread->pre_unpark, introduce stop_machine_unpark()
stop_machine: Change cpu_stop_queue_two_works() to rely on stopper->enabled
stop_machine: Introduce __cpu_stop_queue_work() and cpu_stop_queue_two_works()
stop_machine: Ensure that a queued callback will be called before cpu_stop_park()
sched/x86: Fix typo in __switch_to() comments
sched/core: Remove a parameter in the migrate_task_rq() function
sched/core: Drop unlikely behind BUG_ON()
sched/core: Fix task and run queue sched_info::run_delay inconsistencies
sched/numa: Fix task_tick_fair() from disabling numa_balancing
sched/core: Add preempt_count invariant check
sched/core: More notrace annotations
sched/core: Kill PREEMPT_ACTIVE
sched/core, sched/x86: Kill thread_info::saved_preempt_count
sched/core: Simplify preempt_count tests
sched/core: Robustify preemption leak checks
sched/core: Stop setting PREEMPT_ACTIVE
...
Pull locking changes from Ingo Molnar:
"The main changes in this cycle were:
- More gradual enhancements to atomic ops: new atomic*_read_ctrl()
ops, synchronize atomic_{read,set}() ordering requirements between
architectures, add atomic_long_t bitops. (Peter Zijlstra)
- Add _{relaxed|acquire|release}() variants for inc/dec atomics and
use them in various locking primitives: mutex, rtmutex, mcs, rwsem.
This enables weakly ordered architectures (such as arm64) to make
use of more locking related optimizations. (Davidlohr Bueso)
- Implement atomic[64]_{inc,dec}_relaxed() on ARM. (Will Deacon)
- Futex kernel data cache footprint micro-optimization. (Rasmus
Villemoes)
- pvqspinlock runtime overhead micro-optimization. (Waiman Long)
- misc smaller fixlets"
* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
ARM, locking/atomics: Implement _relaxed variants of atomic[64]_{inc,dec}
locking/rwsem: Use acquire/release semantics
locking/mcs: Use acquire/release semantics
locking/rtmutex: Use acquire/release semantics
locking/mutex: Use acquire/release semantics
locking/asm-generic: Add _{relaxed|acquire|release}() variants for inc/dec atomics
atomic: Implement atomic_read_ctrl()
atomic, arch: Audit atomic_{read,set}()
atomic: Add atomic_long_t bitops
futex: Force hot variables into a single cache line
locking/pvqspinlock: Kick the PV CPU unconditionally when _Q_SLOW_VAL
locking/osq: Relax atomic semantics
locking/qrwlock: Rename ->lock to ->wait_lock
locking/Documentation/lockstat: Fix typo - lokcing -> locking
locking/atomics, cmpxchg: Privatize the inclusion of asm/cmpxchg.h
Pull RCU updates from Paul E. McKenney:
- Miscellaneous fixes. (Paul E. McKenney, Boqun Feng, Oleg Nesterov, Patrick Marlier)
- Improvements to expedited grace periods. (Paul E. McKenney)
- Performance improvements to and locktorture tests for percpu-rwsem.
(Oleg Nesterov, Paul E. McKenney)
- Torture-test changes. (Paul E. McKenney, Davidlohr Bueso)
- Documentation updates. (Paul E. McKenney)
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The locktorture module has a list of torture types, and specifying
a type not on this list is supposed to cleanly fail the module load.
Unfortunately, the "fail" happens without the "cleanly". This commit
therefore adds the needed clean-up after an incorrect torture_type.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Based on Peter Zijlstra's earlier patch.
Change percpu_down_read() to use __down_read(), this way we can
do rwsem_acquire_read() unconditionally at the start to make this
code more symmetric and clean.
Originally-From: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Currently down_write/up_write calls synchronize_sched_expedited()
twice, which is evil. Change this code to rely on rcu-sync primitives.
This avoids the _expedited "big hammer", and this can be faster in
the contended case or even in the case when a single thread does
down_write/up_write in a loop.
Of course, a single down_write() will take more time, but otoh it
will be much more friendly to the whole system.
To simplify the review this patch doesn't update the comments, fixed
by the next change.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
This is the temporary ugly hack which will be reverted later. We only
need it to ensure that the next patch will not break "change sb_writers
to use percpu_rw_semaphore" patches routed via the VFS tree.
The alloc_super()->destroy_super() error path assumes that it is safe
to call percpu_free_rwsem() after kzalloc() without percpu_init_rwsem(),
so let's not disappoint it.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
This commit exports percpu_down_read(), percpu_down_write(),
__percpu_init_rwsem(), percpu_up_read(), and percpu_up_write() to allow
locktorture to test them when built as a module.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Real time mutexes is one of the few general primitives
that we do not have in locktorture. Address this -- a few
considerations:
o To spice things up, enable competing thread(s) to become
rt, such that we can stress different prio boosting paths
in the rtmutex code. Introduce a ->task_boost callback,
only used by rtmutex-torturer. Tasks will boost/deboost
around every 50k (arbitrarily) lock/unlock operations.
o Hold times are similar to what we have for other locks:
only occasionally having longer hold times (per ~200k ops).
So we roughly do two full rt boost+deboosting ops with
short hold times.
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
