From f49ef398f976ef3f7639a959d83210ec9cbf0910 Mon Sep 17 00:00:00 2001 From: Mogball Date: Fri, 24 May 2024 01:18:10 -0700 Subject: [PATCH] [mlir] Fix race condition introduced in ThreadLocalCache Okay, so an apparently not-so-rare crash could occur if the `perInstanceState` point got re-allocated to the same pointer as before. All the values have been destroyed, so the TLC is left with dangling pointers, but then the same `ValueT *` is pulled out of the TLC and dereferenced, leading to a crash. I suppose the purpose of the `weak_ptr` was that it would get reset to a default state when the `perInstanceState` shared pointer got destryoed (its reference count would only ever be 1, very briefly 2 when it gets aliased to a `ValueT *` but then assigned to a `weak_ptr`). Basically, there are circular references between TLC instances and `perInstanceState` instances and we have to ensure there are no dangling references. 1. Ensure the TLC entries are reset to a valid default state if the TLC (i.e. owning thread) lives longer than the `perInstanceState`. a. This is currently achieved by storing `weak_ptr` in the TLC. 2. If `perInstanceState` lives longer than the TLC, it cannot contain dangling references to entries in destroyed TLCs. a. This is not currently the case. 3. If both are being destroyed at the same time, we cannot race. a. The destructors are synchronized because the TLC destructor locks `weak_ptr` while it is destructing, preventing the owning `perInstanceState` of the entry from destructing. If `perInstanceState` got destructed first, the `weak_ptr` lock would fail. And 4. Ensure `get` in the common (initialized) case is as fast as possible (no atomics). We need to change the TLC to store a `ValueT **` so that it can be shared with entries owned by `perInstanceState` and written to null when they are destroyed. However, this is no longer something synchronized by an atomic, meaning that (2) becomes a problem. This is fine because when TLC destructs, we remove the entries from `perInstanceState` that could reference the TLC entries. Also, make the `ValueT **` a weak pointer so that destructors never write to invalid memory. This patch shows the same perf gain as before but hopefully without the bug. --- mlir/include/mlir/Support/ThreadLocalCache.h | 97 +++++++++++++++----- 1 file changed, 72 insertions(+), 25 deletions(-) diff --git a/mlir/include/mlir/Support/ThreadLocalCache.h b/mlir/include/mlir/Support/ThreadLocalCache.h index d19257bf6e25e..fe6c6fa3cf6bd 100644 --- a/mlir/include/mlir/Support/ThreadLocalCache.h +++ b/mlir/include/mlir/Support/ThreadLocalCache.h @@ -16,7 +16,6 @@ #include "mlir/Support/LLVM.h" #include "llvm/ADT/DenseMap.h" -#include "llvm/Support/ManagedStatic.h" #include "llvm/Support/Mutex.h" namespace mlir { @@ -25,28 +24,80 @@ namespace mlir { /// cache has very large lock contention. template class ThreadLocalCache { + struct PerInstanceState; + + /// The "observer" is owned by a thread-local cache instance. It is + /// constructed the first time a `ThreadLocalCache` instance is accessed by a + /// thread, unless `perInstanceState` happens to get re-allocated to the same + /// address as a previous one. This class is destructed the thread in which + /// the `thread_local` cache lives is destroyed. + /// + /// This class is called the "observer" because while values cached in + /// thread-local caches are owned by `PerInstanceState`, a reference is stored + /// via this class in the TLC. With a double pointer, it knows when the + /// referenced value has been destroyed. + struct Observer { + /// This is the double pointer, explicitly allocated because we need to keep + /// the address stable if the TLC map re-allocates. It is owned by the + /// observer and shared with the value owner. + std::shared_ptr ptr = std::make_shared(nullptr); + /// Because `Owner` living inside `PerInstanceState` contains a reference to + /// the double pointer, and livkewise this class contains a reference to the + /// value, we need to synchronize destruction of the TLC and the + /// `PerInstanceState` to avoid racing. This weak pointer is acquired during + /// TLC destruction if the `PerInstanceState` hasn't entered its destructor + /// yet, and prevents it from happening. + std::weak_ptr keepalive; + }; + + /// This struct owns the cache entries. It contains a reference back to the + /// reference inside the cache so that it can be written to null to indicate + /// that the cache entry is invalidated. It needs to do this because + /// `perInstanceState` could get re-allocated to the same pointer and we don't + /// remove entries from the TLC when it is deallocated. Thus, we have to reset + /// the TLC entries to a starting state in case the `ThreadLocalCache` lives + /// shorter than the threads. + struct Owner { + /// Save a pointer to the reference and write it to the newly created entry. + Owner(Observer &observer) + : value(std::make_unique()), ptrRef(observer.ptr) { + *observer.ptr = value.get(); + } + ~Owner() { + if (std::shared_ptr ptr = ptrRef.lock()) + *ptr = nullptr; + } + + Owner(Owner &&) = default; + Owner &operator=(Owner &&) = default; + + std::unique_ptr value; + std::weak_ptr ptrRef; + }; + // Keep a separate shared_ptr protected state that can be acquired atomically // instead of using shared_ptr's for each value. This avoids a problem // where the instance shared_ptr is locked() successfully, and then the // ThreadLocalCache gets destroyed before remove() can be called successfully. struct PerInstanceState { - /// Remove the given value entry. This is generally called when a thread - /// local cache is destructing. + /// Remove the given value entry. This is called when a thread local cache + /// is destructing but still contains references to values owned by the + /// `PerInstanceState`. Removal is required because it prevents writeback to + /// a pointer that was deallocated. void remove(ValueT *value) { // Erase the found value directly, because it is guaranteed to be in the // list. llvm::sys::SmartScopedLock threadInstanceLock(instanceMutex); - auto it = - llvm::find_if(instances, [&](std::unique_ptr &instance) { - return instance.get() == value; - }); + auto it = llvm::find_if(instances, [&](Owner &instance) { + return instance.value.get() == value; + }); assert(it != instances.end() && "expected value to exist in cache"); instances.erase(it); } /// Owning pointers to all of the values that have been constructed for this /// object in the static cache. - SmallVector, 1> instances; + SmallVector instances; /// A mutex used when a new thread instance has been added to the cache for /// this object. @@ -57,14 +108,14 @@ class ThreadLocalCache { /// instance of the non-static cache and a weak reference to an instance of /// ValueT. We use a weak reference here so that the object can be destroyed /// without needing to lock access to the cache itself. - struct CacheType - : public llvm::SmallDenseMap, ValueT *>> { + struct CacheType : public llvm::SmallDenseMap { ~CacheType() { - // Remove the values of this cache that haven't already expired. - for (auto &it : *this) - if (std::shared_ptr value = it.second.first.lock()) - it.first->remove(value.get()); + // Remove the values of this cache that haven't already expired. This is + // required because if we don't remove them, they will contain a reference + // back to the data here that is being destroyed. + for (auto &[instance, observer] : *this) + if (std::shared_ptr state = observer.keepalive.lock()) + state->remove(*observer.ptr); } /// Clear out any unused entries within the map. This method is not @@ -72,7 +123,7 @@ class ThreadLocalCache { void clearExpiredEntries() { for (auto it = this->begin(), e = this->end(); it != e;) { auto curIt = it++; - if (curIt->second.first.expired()) + if (!*curIt->second.ptr) this->erase(curIt); } } @@ -89,27 +140,23 @@ class ThreadLocalCache { ValueT &get() { // Check for an already existing instance for this thread. CacheType &staticCache = getStaticCache(); - std::pair, ValueT *> &threadInstance = - staticCache[perInstanceState.get()]; - if (ValueT *value = threadInstance.second) + Observer &threadInstance = staticCache[perInstanceState.get()]; + if (ValueT *value = *threadInstance.ptr) return *value; // Otherwise, create a new instance for this thread. { llvm::sys::SmartScopedLock threadInstanceLock( perInstanceState->instanceMutex); - threadInstance.second = - perInstanceState->instances.emplace_back(std::make_unique()) - .get(); + perInstanceState->instances.emplace_back(threadInstance); } - threadInstance.first = - std::shared_ptr(perInstanceState, threadInstance.second); + threadInstance.keepalive = perInstanceState; // Before returning the new instance, take the chance to clear out any used // entries in the static map. The cache is only cleared within the same // thread to remove the need to lock the cache itself. staticCache.clearExpiredEntries(); - return *threadInstance.second; + return **threadInstance.ptr; } ValueT &operator*() { return get(); } ValueT *operator->() { return &get(); }