Change section memory manager to fix performance problem in long-running SectionMemoryManagers

src/codegen/memmgr.cpp

@@ -19,6 +19,7 @@
 #include "llvm/ExecutionEngine/RuntimeDyld.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/Memory.h"
+#include "llvm/Support/Process.h"
 
 #include "codegen/irgen/util.h"
 #include "codegen/unwinding.h"
@@ -49,9 +50,14 @@ public:
 private:
     void invalidateInstructionCache();
 
+    struct FreeMemBlock {
+        sys::MemoryBlock Free;
+        unsigned PendingPrefixIndex;
+    };
     struct MemoryGroup {
+        SmallVector<sys::MemoryBlock, 16> PendingMem;
         SmallVector<sys::MemoryBlock, 16> AllocatedMem;
-        SmallVector<sys::MemoryBlock, 16> FreeMem;
+        SmallVector<FreeMemBlock, 16> FreeMem;
         sys::MemoryBlock Near;
     };
 
@@ -91,21 +97,33 @@ uint8_t* PystonMemoryManager::allocateSection(MemoryGroup& MemGroup, uintptr_t S
     uintptr_t RequiredSize = Alignment * ((Size + Alignment - 1) / Alignment + 1);
     uintptr_t Addr = 0;
 
-    // Look in the list of free memory regions and use a block there if one
-    // is available.
-    for (int i = 0, e = MemGroup.FreeMem.size(); i != e; ++i) {
-        sys::MemoryBlock& MB = MemGroup.FreeMem[i];
-        if (MB.size() >= RequiredSize) {
-            Addr = (uintptr_t)MB.base();
-            uintptr_t EndOfBlock = Addr + MB.size();
+    // Note that all sections get allocated as read-write.  The permissions will
+    // be updated later based on memory group.
+    //
+    for (FreeMemBlock& FreeMB : MemGroup.FreeMem) {
+        if (FreeMB.Free.size() >= RequiredSize) {
+            Addr = (uintptr_t)FreeMB.Free.base();
+            uintptr_t EndOfBlock = Addr + FreeMB.Free.size();
             // Align the address.
             Addr = (Addr + Alignment - 1) & ~(uintptr_t)(Alignment - 1);
-            // Store cutted free memory block.
-            MemGroup.FreeMem[i] = sys::MemoryBlock((void*)(Addr + Size), EndOfBlock - Addr - Size);
+
+            if (FreeMB.PendingPrefixIndex == (unsigned)-1) {
+                // The part of the block we're giving out to the user is now pending
+                MemGroup.PendingMem.push_back(sys::MemoryBlock((void*)Addr, Size));
+
+                // Remember this pending block, such that future allocations can just
+                // modify it rather than creating a new one
+                FreeMB.PendingPrefixIndex = MemGroup.PendingMem.size() - 1;
+            } else {
+                sys::MemoryBlock& PendingMB = MemGroup.PendingMem[FreeMB.PendingPrefixIndex];
+                PendingMB = sys::MemoryBlock(PendingMB.base(), Addr + Size - (uintptr_t)PendingMB.base());
+            }
+
+            // Remember how much free space is now left in this block
+            FreeMB.Free = sys::MemoryBlock((void*)(Addr + Size), EndOfBlock - Addr - Size);
             return (uint8_t*)Addr;
         }
     }
-
     // No pre-allocated free block was large enough. Allocate a new memory region.
     // Note that all sections get allocated as read-write.  The permissions will
     // be updated later based on memory group.
@@ -120,7 +138,7 @@ uint8_t* PystonMemoryManager::allocateSection(MemoryGroup& MemGroup, uintptr_t S
                                                             sys::Memory::MF_READ | sys::Memory::MF_WRITE, ec);
     if (ec) {
         // FIXME: Add error propogation to the interface.
-        return NULL;
+        return nullptr;
     }
 
     std::string stat_name = "mem_section_" + std::string(SectionName);
@@ -136,13 +154,17 @@ uint8_t* PystonMemoryManager::allocateSection(MemoryGroup& MemGroup, uintptr_t S
     // Align the address.
     Addr = (Addr + Alignment - 1) & ~(uintptr_t)(Alignment - 1);
 
+    MemGroup.PendingMem.push_back(sys::MemoryBlock((void*)Addr, Size));
+
     // The allocateMappedMemory may allocate much more memory than we need. In
     // this case, we store the unused memory as a free memory block.
     unsigned FreeSize = EndOfBlock - Addr - Size;
-    if (FreeSize > 16)
-        MemGroup.FreeMem.push_back(sys::MemoryBlock((void*)(Addr + Size), FreeSize));
-
-    // Return aligned address
+    if (FreeSize > 16) {
+        FreeMemBlock FreeMB;
+        FreeMB.Free = sys::MemoryBlock((void*)(Addr + Size), FreeSize);
+        FreeMB.PendingPrefixIndex = (unsigned)-1;
+        MemGroup.FreeMem.push_back(FreeMB);
+    }
     return (uint8_t*)Addr;
 }
 
@@ -185,15 +207,47 @@ bool PystonMemoryManager::finalizeMemory(std::string* ErrMsg) {
     return false;
 }
 
+static sys::MemoryBlock trimBlockToPageSize(sys::MemoryBlock M) {
+    static const size_t PageSize = sys::Process::getPageSize();
+
+    size_t StartOverlap = (PageSize - ((uintptr_t)M.base() % PageSize)) % PageSize;
+
+    size_t TrimmedSize = M.size();
+    TrimmedSize -= StartOverlap;
+    TrimmedSize -= TrimmedSize % PageSize;
+
+    sys::MemoryBlock Trimmed((void*)((uintptr_t)M.base() + StartOverlap), TrimmedSize);
+
+    assert(((uintptr_t)Trimmed.base() % PageSize) == 0);
+    assert((Trimmed.size() % PageSize) == 0);
+    assert(M.base() <= Trimmed.base() && Trimmed.size() <= M.size());
+
+    return Trimmed;
+}
+
 llvm_error_code PystonMemoryManager::applyMemoryGroupPermissions(MemoryGroup& MemGroup, unsigned Permissions) {
 
-    for (int i = 0, e = MemGroup.AllocatedMem.size(); i != e; ++i) {
+    for (sys::MemoryBlock& MB : MemGroup.PendingMem) {
         llvm_error_code ec;
-        ec = sys::Memory::protectMappedMemory(MemGroup.AllocatedMem[i], Permissions);
+        ec = sys::Memory::protectMappedMemory(MB, Permissions);
         if (ec) {
             return ec;
         }
     }
+    MemGroup.PendingMem.clear();
+
+    // Now go through free blocks and trim any of them that don't span the entire
+    // page because one of the pending blocks may have overlapped it.
+    for (FreeMemBlock& FreeMB : MemGroup.FreeMem) {
+        FreeMB.Free = trimBlockToPageSize(FreeMB.Free);
+        // We cleared the PendingMem list, so all these pointers are now invalid
+        FreeMB.PendingPrefixIndex = (unsigned)-1;
+    }
+
+    // Remove all blocks which are now empty
+    MemGroup.FreeMem.erase(std::remove_if(MemGroup.FreeMem.begin(), MemGroup.FreeMem.end(), [](FreeMemBlock& FreeMB) {
+        return FreeMB.Free.size() == 0;
+    }), MemGroup.FreeMem.end());
 
 #if LLVMREV < 209952
     return llvm_error_code::success();
@@ -203,8 +257,8 @@ llvm_error_code PystonMemoryManager::applyMemoryGroupPermissions(MemoryGroup& Me
 }
 
 void PystonMemoryManager::invalidateInstructionCache() {
-    for (int i = 0, e = CodeMem.AllocatedMem.size(); i != e; ++i)
-        sys::Memory::InvalidateInstructionCache(CodeMem.AllocatedMem[i].base(), CodeMem.AllocatedMem[i].size());
+    for (sys::MemoryBlock& Block : CodeMem.PendingMem)
+        sys::Memory::InvalidateInstructionCache(Block.base(), Block.size());
 }
 
 uint64_t PystonMemoryManager::getSymbolAddress(const std::string& name) {
@@ -230,12 +284,10 @@ uint64_t PystonMemoryManager::getSymbolAddress(const std::string& name) {
 }
 
 PystonMemoryManager::~PystonMemoryManager() {
-    for (unsigned i = 0, e = CodeMem.AllocatedMem.size(); i != e; ++i)
-        sys::Memory::releaseMappedMemory(CodeMem.AllocatedMem[i]);
-    for (unsigned i = 0, e = RWDataMem.AllocatedMem.size(); i != e; ++i)
-        sys::Memory::releaseMappedMemory(RWDataMem.AllocatedMem[i]);
-    for (unsigned i = 0, e = RODataMem.AllocatedMem.size(); i != e; ++i)
-        sys::Memory::releaseMappedMemory(RODataMem.AllocatedMem[i]);
+    for (MemoryGroup* Group : { &CodeMem, &RWDataMem, &RODataMem }) {
+        for (sys::MemoryBlock& Block : Group->AllocatedMem)
+            sys::Memory::releaseMappedMemory(Block);
+    }
 }
 
 std::unique_ptr<llvm::RTDyldMemoryManager> createMemoryManager() {