From 899b32c988d36e4602cf675e02a780179731ae92 Mon Sep 17 00:00:00 2001 From: Mogball Date: Thu, 23 May 2024 20:32:13 -0700 Subject: [PATCH] [mlir] Optimize ThreadLocalCache by removing atomic bottleneck The ThreadLocalCache implementation is used by the MLIRContext (among other things) to try to manage thread contention in the StorageUniquers. There is a bunch of fancy shared pointer/weak pointer setups that basically keeps everything alive across threads at the right time, but a huge bottleneck is the `weak_ptr::lock` call inside the `::get` method. This is because the `lock` method has to hit the atomic refcount several times, and this is bottlenecking performance across many threads. However, all this is doing is checking whether the storage is initialized. Importantly, when the `PerThreadInstance` goes out of scope, it does not remove all of its associated entries from the thread-local hash map (it contains dangling `PerThreadInstance *` keys). The `weak_ptr` also allows the thread local cache to synchronize with the `PerThreadInstance`'s destruction: 1. if `ThreadLocalCache` destructs, the `weak_ptr`s that reference its contained values are immediately invalidated 2. if `CacheType` destructs within a thread, any entries still live are removed from the owning `PerThreadInstance`, and it locks the `weak_ptr` first to ensure it's kept alive long enough for the removal. This PR changes the TLC entries to contain a `shared_ptr` and a `weak_ptr`. It gives the `PerInstanceState` entries a `weak_ptr` on top of the `unique_ptr`. This enables `ThreadLocalCache::get` to check if the value is initialized by dereferencing the `shared_ptr` and check if the contained pointer is null. When `PerInstanceState` destructs, the values inside the TLC are written to nullptr. The TLC uses the `weak_ptr` to satisfy (2). (1) is no longer the case. When `ThreadLocalCache` begins destruction, the `weak_ptr` are invalidated, but not the `shared_ptr`. This is OK: because the overall object is being destroyed, `::get` cannot get called and because the `shared_ptr` finishes destruction before freeing the pointer, it cannot get reallocated to another `ThreadLocalCache` during destruction. I.e. the values inside the TLC associated with a `PerInstanceState` cannot be read during destruction. The most important thing is to make sure destruction of the TLC doesn't race with the destructor of `PerInstanceState`. Because `PerInstanceState` carries `weak_ptr` references into the TLC, we guarantee to not have any use-after-frees. --- mlir/include/mlir/Support/ThreadLocalCache.h | 98 +++++++++++++++----- 1 file changed, 76 insertions(+), 22 deletions(-) diff --git a/mlir/include/mlir/Support/ThreadLocalCache.h b/mlir/include/mlir/Support/ThreadLocalCache.h index 1be94ca14bcfac..87cc52cc56ac4f 100644 --- a/mlir/include/mlir/Support/ThreadLocalCache.h +++ b/mlir/include/mlir/Support/ThreadLocalCache.h @@ -25,28 +25,80 @@ 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. A `thread_local` instance of this class is + /// destructed when the thread in which it 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 the `Owner` instance that lives inside `PerInstanceState` + /// contains a reference to the double pointer, and likewise 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. @@ -57,13 +109,14 @@ 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> { + 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.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 @@ -71,7 +124,7 @@ class ThreadLocalCache { void clearExpiredEntries() { for (auto it = this->begin(), e = this->end(); it != e;) { auto curIt = it++; - if (curIt->second.expired()) + if (!*curIt->second.ptr) this->erase(curIt); } } @@ -88,22 +141,23 @@ class ThreadLocalCache { ValueT &get() { // Check for an already existing instance for this thread. CacheType &staticCache = getStaticCache(); - std::weak_ptr &threadInstance = staticCache[perInstanceState.get()]; - if (std::shared_ptr value = threadInstance.lock()) + 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); - perInstanceState->instances.push_back(std::make_unique()); - ValueT *instance = perInstanceState->instances.back().get(); - threadInstance = std::shared_ptr(perInstanceState, instance); + { + llvm::sys::SmartScopedLock threadInstanceLock( + perInstanceState->instanceMutex); + perInstanceState->instances.emplace_back(threadInstance); + } + 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 *instance; + return **threadInstance.ptr; } ValueT &operator*() { return get(); } ValueT *operator->() { return &get(); }