From c5b6ababd21ab6bb251e5a2b4db110e76fb00a26 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Mon, 12 May 2025 14:04:02 -0400 Subject: locking/mutex: implement mutex_trylock_nested Despite the fact that several lockdep-related checks are skipped when calling trylock* versions of the locking primitives, for example mutex_trylock, each time the mutex is acquired, a held_lock is still placed onto the lockdep stack by __lock_acquire() which is called regardless of whether the trylock* or regular locking API was used. This means that if the caller successfully acquires more than MAX_LOCK_DEPTH locks of the same class, even when using mutex_trylock, lockdep will still complain that the maximum depth of the held lock stack has been reached and disable itself. For example, the following error currently occurs in the ARM version of KVM, once the code tries to lock all vCPUs of a VM configured with more than MAX_LOCK_DEPTH vCPUs, a situation that can easily happen on modern systems, where having more than 48 CPUs is common, and it's also common to run VMs that have vCPU counts approaching that number: [ 328.171264] BUG: MAX_LOCK_DEPTH too low! [ 328.175227] turning off the locking correctness validator. [ 328.180726] Please attach the output of /proc/lock_stat to the bug report [ 328.187531] depth: 48 max: 48! [ 328.190678] 48 locks held by qemu-kvm/11664: [ 328.194957] #0: ffff800086de5ba0 (&kvm->lock){+.+.}-{3:3}, at: kvm_ioctl_create_device+0x174/0x5b0 [ 328.204048] #1: ffff0800e78800b8 (&vcpu->mutex){+.+.}-{3:3}, at: lock_all_vcpus+0x16c/0x2a0 [ 328.212521] #2: ffff07ffeee51e98 (&vcpu->mutex){+.+.}-{3:3}, at: lock_all_vcpus+0x16c/0x2a0 [ 328.220991] #3: ffff0800dc7d80b8 (&vcpu->mutex){+.+.}-{3:3}, at: lock_all_vcpus+0x16c/0x2a0 [ 328.229463] #4: ffff07ffe0c980b8 (&vcpu->mutex){+.+.}-{3:3}, at: lock_all_vcpus+0x16c/0x2a0 [ 328.237934] #5: ffff0800a3883c78 (&vcpu->mutex){+.+.}-{3:3}, at: lock_all_vcpus+0x16c/0x2a0 [ 328.246405] #6: ffff07fffbe480b8 (&vcpu->mutex){+.+.}-{3:3}, at: lock_all_vcpus+0x16c/0x2a0 Luckily, in all instances that require locking all vCPUs, the 'kvm->lock' is taken a priori, and that fact makes it possible to use the little known feature of lockdep, called a 'nest_lock', to avoid this warning and subsequent lockdep self-disablement. The action of 'nested lock' being provided to lockdep's lock_acquire(), causes the lockdep to detect that the top of the held lock stack contains a lock of the same class and then increment its reference counter instead of pushing a new held_lock item onto that stack. See __lock_acquire for more information. Signed-off-by: Maxim Levitsky Acked-by: Peter Zijlstra (Intel) Message-ID: <20250512180407.659015-2-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- kernel/locking/mutex.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'kernel/locking') diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 555e2b3a665a..c75a838d3bae 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -1062,6 +1062,7 @@ __ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock, #endif +#ifndef CONFIG_DEBUG_LOCK_ALLOC /** * mutex_trylock - try to acquire the mutex, without waiting * @lock: the mutex to be acquired @@ -1077,18 +1078,25 @@ __ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock, * mutex must be released by the same task that acquired it. */ int __sched mutex_trylock(struct mutex *lock) +{ + MUTEX_WARN_ON(lock->magic != lock); + return __mutex_trylock(lock); +} +EXPORT_SYMBOL(mutex_trylock); +#else +int __sched _mutex_trylock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock) { bool locked; MUTEX_WARN_ON(lock->magic != lock); - locked = __mutex_trylock(lock); if (locked) - mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); + mutex_acquire_nest(&lock->dep_map, 0, 1, nest_lock, _RET_IP_); return locked; } -EXPORT_SYMBOL(mutex_trylock); +EXPORT_SYMBOL(_mutex_trylock_nest_lock); +#endif #ifndef CONFIG_DEBUG_LOCK_ALLOC int __sched -- cgit v1.2.3 From fb49f07ba1d9d8c9bd8854878ae6b5b21ff9ac45 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Mon, 12 May 2025 14:04:03 -0400 Subject: locking/mutex: implement mutex_lock_killable_nest_lock KVM's SEV intra-host migration code needs to lock all vCPUs of the source and the target VM, before it proceeds with the migration. The number of vCPUs that belong to each VM is not bounded by anything except a self-imposed KVM limit of CONFIG_KVM_MAX_NR_VCPUS vCPUs which is significantly larger than the depth of lockdep's lock stack. Luckily, the locks in both of the cases mentioned above, are held under the 'kvm->lock' of each VM, which means that we can use the little known lockdep feature called a "nest_lock" to support this use case in a cleaner way, compared to the way it's currently done. Implement and expose 'mutex_lock_killable_nest_lock' for this purpose. Signed-off-by: Maxim Levitsky Acked-by: Peter Zijlstra (Intel) Message-ID: <20250512180407.659015-3-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- kernel/locking/mutex.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'kernel/locking') diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index c75a838d3bae..234923121ff0 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -808,11 +808,12 @@ _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest) EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock); int __sched -mutex_lock_killable_nested(struct mutex *lock, unsigned int subclass) +_mutex_lock_killable(struct mutex *lock, unsigned int subclass, + struct lockdep_map *nest) { - return __mutex_lock(lock, TASK_KILLABLE, subclass, NULL, _RET_IP_); + return __mutex_lock(lock, TASK_KILLABLE, subclass, nest, _RET_IP_); } -EXPORT_SYMBOL_GPL(mutex_lock_killable_nested); +EXPORT_SYMBOL_GPL(_mutex_lock_killable); int __sched mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass) -- cgit v1.2.3 From 438e22801b1958f86883812af70d402eda29c4f5 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Fri, 30 May 2025 03:45:13 -0400 Subject: rtmutex_api: provide correct extern functions Commit fb49f07ba1d9 ("locking/mutex: implement mutex_lock_killable_nest_lock") changed the set of functions that mutex.c defines when CONFIG_DEBUG_LOCK_ALLOC is set. - it removed the "extern" declaration of mutex_lock_killable_nested from include/linux/mutex.h, and replaced it with a macro since it could be treated as a special case of _mutex_lock_killable. It also removed a definition of the function in kernel/locking/mutex.c. - likewise, it replaced mutex_trylock() with the more generic mutex_trylock_nest_lock() and replaced mutex_trylock() with a macro. However, it left the old definitions in place in kernel/locking/rtmutex_api.c, which causes failures when building with CONFIG_RT_MUTEXES=y. Bring over the changes. Fixes: fb49f07ba1d9 ("locking/mutex: implement mutex_lock_killable_nest_lock") Reported-by: Randy Dunlap Tested-by: Randy Dunlap Cc: Peter Zijlstra Signed-off-by: Paolo Bonzini --- kernel/locking/rtmutex_api.c | 33 +++++++++++++++++++++------------ 1 file changed, 21 insertions(+), 12 deletions(-) (limited to 'kernel/locking') diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c index 191e4720e546..2d933528a0fa 100644 --- a/kernel/locking/rtmutex_api.c +++ b/kernel/locking/rtmutex_api.c @@ -544,12 +544,12 @@ int __sched mutex_lock_interruptible_nested(struct mutex *lock, } EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested); -int __sched mutex_lock_killable_nested(struct mutex *lock, - unsigned int subclass) +int __sched _mutex_lock_killable(struct mutex *lock, unsigned int subclass, + struct lockdep_map *nest_lock) { - return __mutex_lock_common(lock, TASK_KILLABLE, subclass, NULL, _RET_IP_); + return __mutex_lock_common(lock, TASK_KILLABLE, subclass, nest_lock, _RET_IP_); } -EXPORT_SYMBOL_GPL(mutex_lock_killable_nested); +EXPORT_SYMBOL_GPL(_mutex_lock_killable); void __sched mutex_lock_io_nested(struct mutex *lock, unsigned int subclass) { @@ -563,6 +563,21 @@ void __sched mutex_lock_io_nested(struct mutex *lock, unsigned int subclass) } EXPORT_SYMBOL_GPL(mutex_lock_io_nested); +int __sched _mutex_trylock_nest_lock(struct mutex *lock, + struct lockdep_map *nest_lock) +{ + int ret; + + if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES) && WARN_ON_ONCE(!in_task())) + return 0; + + ret = __rt_mutex_trylock(&lock->rtmutex); + if (ret) + mutex_acquire_nest(&lock->dep_map, 0, 1, nest_lock, _RET_IP_); + + return ret; +} +EXPORT_SYMBOL_GPL(_mutex_trylock_nest_lock); #else /* CONFIG_DEBUG_LOCK_ALLOC */ void __sched mutex_lock(struct mutex *lock) @@ -591,22 +606,16 @@ void __sched mutex_lock_io(struct mutex *lock) io_schedule_finish(token); } EXPORT_SYMBOL(mutex_lock_io); -#endif /* !CONFIG_DEBUG_LOCK_ALLOC */ int __sched mutex_trylock(struct mutex *lock) { - int ret; - if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES) && WARN_ON_ONCE(!in_task())) return 0; - ret = __rt_mutex_trylock(&lock->rtmutex); - if (ret) - mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); - - return ret; + return __rt_mutex_trylock(&lock->rtmutex); } EXPORT_SYMBOL(mutex_trylock); +#endif /* !CONFIG_DEBUG_LOCK_ALLOC */ void __sched mutex_unlock(struct mutex *lock) { -- cgit v1.2.3