Caching symbols on symbol resolution

This PR caches symbol resolutions. This can can significantly speed up the resolution process.
Fraunhofer-AISEC · Oct 16, 2023 · 5254d7a · 5254d7a
1 parent 54d3e3d
commit 5254d7a
Show file tree

Hide file tree

Showing 3 changed files with 78 additions and 24 deletions.
diff --git a/cpg-core/src/main/kotlin/de/fraunhofer/aisec/cpg/ScopeManager.kt b/cpg-core/src/main/kotlin/de/fraunhofer/aisec/cpg/ScopeManager.kt
@@ -34,6 +34,7 @@ import de.fraunhofer.aisec.cpg.graph.statements.*
 import de.fraunhofer.aisec.cpg.graph.statements.expressions.Block
 import de.fraunhofer.aisec.cpg.graph.statements.expressions.CallExpression
 import de.fraunhofer.aisec.cpg.graph.statements.expressions.Reference
+import de.fraunhofer.aisec.cpg.graph.statements.expressions.ReferenceTag
 import de.fraunhofer.aisec.cpg.graph.types.FunctionPointerType
 import de.fraunhofer.aisec.cpg.graph.types.IncompleteType
 import de.fraunhofer.aisec.cpg.graph.types.Type
@@ -74,6 +75,12 @@ class ScopeManager : ScopeProvider {
     /** Represents an alias with the name [to] for the particular name [from]. */
     data class Alias(var from: Name, var to: Name)
 
+    /**
+     * A cache map of unique tags (computed with [Reference.buildUniqueTag]) and their respective
+     * [ValueDeclaration]. This is used by [resolveReference] as a caching mechanism.
+     */
+    private val symbolTable = mutableMapOf<ReferenceTag, ValueDeclaration>()
+
     /**
      * In some languages, we can define aliases for names. An example is renaming package imports in
      * Go, e.g., to avoid name conflicts.
@@ -615,37 +622,56 @@ class ScopeManager : ScopeProvider {
      */
     @JvmOverloads
     fun resolveReference(ref: Reference, startScope: Scope? = currentScope): ValueDeclaration? {
+        // Retrieve a unique tag for the particular reference, based on the current scope
+        val tag = ref.buildUniqueTag(startScope)
+
+        // If we find a match in our symbol table, we can immediately return the declaration
+        var decl = symbolTable[tag]
+        if (decl != null) {
+            return decl
+        }
+
         val (scope, name) = extractScope(ref, startScope)
 
         // Try to resolve value declarations according to our criteria
-        return resolve<ValueDeclaration>(scope) {
-                if (it.name.lastPartsMatch(name)) {
-                    val helper = ref.resolutionHelper
-                    return@resolve when {
-                        // If the reference seems to point to a function (using a function pointer)
-                        // the entire signature is checked for equality
-                        helper?.type is FunctionPointerType && it is FunctionDeclaration -> {
-                            val fptrType = helper.type as FunctionPointerType
-                            // TODO(oxisto): Support multiple return values
-                            val returnType = it.returnTypes.firstOrNull() ?: IncompleteType()
-                            returnType == fptrType.returnType &&
-                                it.hasSignature(fptrType.parameters)
-                        }
-                        // If our language has first-class functions, we can safely return them as a
-                        // reference
-                        ref.language is HasFirstClassFunctions -> {
-                            true
-                        }
-                        // Otherwise, we are not looking for functions here
-                        else -> {
-                            it !is FunctionDeclaration
+        decl =
+            resolve<ValueDeclaration>(scope) {
+                    if (it.name.lastPartsMatch(name)) {
+                        val helper = ref.resolutionHelper
+                        return@resolve when {
+                            // If the reference seems to point to a function (using a function
+                            // pointer)
+                            // the entire signature is checked for equality
+                            helper?.type is FunctionPointerType && it is FunctionDeclaration -> {
+                                val fptrType = helper.type as FunctionPointerType
+                                // TODO(oxisto): Support multiple return values
+                                val returnType = it.returnTypes.firstOrNull() ?: IncompleteType()
+                                returnType == fptrType.returnType &&
+                                    it.hasSignature(fptrType.parameters)
+                            }
+                            // If our language has first-class functions, we can safely return them
+                            // as a
+                            // reference
+                            ref.language is HasFirstClassFunctions -> {
+                                true
+                            }
+                            // Otherwise, we are not looking for functions here
+                            else -> {
+                                it !is FunctionDeclaration
+                            }
                         }
                     }
+
+                    return@resolve false
                 }
+                .firstOrNull()
 
-                return@resolve false
-            }
-            .firstOrNull()
+        // Update the symbol cache, if we found a declaration for the tag
+        if (decl != null) {
+            symbolTable[tag] = decl
+        }
+
+        return decl
     }
 
     /**

diff --git a/cpg-core/src/main/kotlin/de/fraunhofer/aisec/cpg/graph/scopes/Scope.kt b/cpg-core/src/main/kotlin/de/fraunhofer/aisec/cpg/graph/scopes/Scope.kt
@@ -82,6 +82,22 @@ abstract class Scope(
         return this is LoopScope
     }
 
+    override fun equals(other: Any?): Boolean {
+        if (this === other) return true
+        if (javaClass != other?.javaClass) return false
+
+        other as Scope
+
+        if (astNode != other.astNode) return false
+        return name == other.name
+    }
+
+    override fun hashCode(): Int {
+        var result = astNode?.hashCode() ?: 0
+        result = 31 * result + (name?.hashCode() ?: 0)
+        return result
+    }
+
     /** Returns the [GlobalScope] of this scope by traversing its parents upwards. */
     val globalScope: Scope?
         get() {

diff --git a/cpg-core/src/main/kotlin/de/fraunhofer/aisec/cpg/graph/statements/expressions/Reference.kt b/cpg-core/src/main/kotlin/de/fraunhofer/aisec/cpg/graph/statements/expressions/Reference.kt
@@ -32,6 +32,7 @@ import de.fraunhofer.aisec.cpg.graph.declarations.Declaration
 import de.fraunhofer.aisec.cpg.graph.declarations.ValueDeclaration
 import de.fraunhofer.aisec.cpg.graph.declarations.VariableDeclaration
 import de.fraunhofer.aisec.cpg.graph.edge.Properties
+import de.fraunhofer.aisec.cpg.graph.scopes.Scope
 import de.fraunhofer.aisec.cpg.graph.types.HasType
 import de.fraunhofer.aisec.cpg.graph.types.Type
 import de.fraunhofer.aisec.cpg.passes.SymbolResolver
@@ -153,4 +154,15 @@ open class Reference : Expression(), HasType.TypeObserver {
             prev.registerTypeObserver(this)
         }
     }
+
+    /**
+     * This function builds a unique tag for the particular reference, based on the [startScope].
+     * Its purpose is to cache symbol resolutions, similar to LLVMs system of Unified Symbol
+     * Resolution (USR).
+     */
+    fun buildUniqueTag(startScope: Scope?): ReferenceTag {
+        return Objects.hash(this.name, startScope)
+    }
 }
+
+typealias ReferenceTag = Int