runtime: break out the debug.malloc codepaths into functions

This change breaks out the debug.malloc codepaths into dedicated
functions, both for making mallocgc easier to read, and to reduce the
function's size (currently all that code is inlined and really doesn't
need to be).

This is a microoptimization that on its own changes very little, but
together with other optimizations and a breaking up of the various
malloc paths will matter all together ("death by a thousand cuts").

Change-Id: I30b3ab4a1f349ba85b4a1b5b2c399abcdfe4844f
Reviewed-on: https://go-review.googlesource.com/c/go/+/617879
Reviewed-by: Keith Randall <khr@google.com>
Reviewed-by: Keith Randall <khr@golang.org>
Auto-Submit: Michael Knyszek <mknyszek@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>

src/runtime/malloc.go

@@ -1022,33 +1022,10 @@ func mallocgc(size uintptr, typ *_type, needzero bool) unsafe.Pointer {
 		size += computeRZlog(size)
 	}
 
+	// Pre-malloc debug hooks.
 	if debug.malloc {
-		if debug.sbrk != 0 {
+		if x := preMallocgcDebug(size, typ); x != nil {
-			align := uintptr(16)
+			return x
-			if typ != nil {
-				// TODO(austin): This should be just
-				//   align = uintptr(typ.align)
-				// but that's only 4 on 32-bit platforms,
-				// even if there's a uint64 field in typ (see #599).
-				// This causes 64-bit atomic accesses to panic.
-				// Hence, we use stricter alignment that matches
-				// the normal allocator better.
-				if size&7 == 0 {
-					align = 8
-				} else if size&3 == 0 {
-					align = 4
-				} else if size&1 == 0 {
-					align = 2
-				} else {
-					align = 1
-				}
-			}
-			return persistentalloc(size, align, &memstats.other_sys)
-		}
-
-		if inittrace.active && inittrace.id == getg().goid {
-			// Init functions are executed sequentially in a single goroutine.
-			inittrace.allocs += 1
 		}
 	}
 
@@ -1296,19 +1273,9 @@ func mallocgc(size uintptr, typ *_type, needzero bool) unsafe.Pointer {
 		}
 	}
 
+	// Post-malloc debug hooks.
 	if debug.malloc {
-		if inittrace.active && inittrace.id == getg().goid {
+		postMallocgcDebug(x, fullSize, typ)
-			// Init functions are executed sequentially in a single goroutine.
-			inittrace.bytes += uint64(fullSize)
-		}
-
-		if traceAllocFreeEnabled() {
-			trace := traceAcquire()
-			if trace.ok() {
-				trace.HeapObjectAlloc(uintptr(x), typ)
-				traceRelease(trace)
-			}
-		}
 	}
 
 	// Adjust our GC assist debt to account for internal fragmentation.
@@ -1343,6 +1310,51 @@ func mallocgc(size uintptr, typ *_type, needzero bool) unsafe.Pointer {
 	return x
 }
 
+func preMallocgcDebug(size uintptr, typ *_type) unsafe.Pointer {
+	if debug.sbrk != 0 {
+		align := uintptr(16)
+		if typ != nil {
+			// TODO(austin): This should be just
+			//   align = uintptr(typ.align)
+			// but that's only 4 on 32-bit platforms,
+			// even if there's a uint64 field in typ (see #599).
+			// This causes 64-bit atomic accesses to panic.
+			// Hence, we use stricter alignment that matches
+			// the normal allocator better.
+			if size&7 == 0 {
+				align = 8
+			} else if size&3 == 0 {
+				align = 4
+			} else if size&1 == 0 {
+				align = 2
+			} else {
+				align = 1
+			}
+		}
+		return persistentalloc(size, align, &memstats.other_sys)
+	}
+	if inittrace.active && inittrace.id == getg().goid {
+		// Init functions are executed sequentially in a single goroutine.
+		inittrace.allocs += 1
+	}
+	return nil
+}
+
+func postMallocgcDebug(x unsafe.Pointer, elemsize uintptr, typ *_type) {
+	if inittrace.active && inittrace.id == getg().goid {
+		// Init functions are executed sequentially in a single goroutine.
+		inittrace.bytes += uint64(elemsize)
+	}
+
+	if traceAllocFreeEnabled() {
+		trace := traceAcquire()
+		if trace.ok() {
+			trace.HeapObjectAlloc(uintptr(x), typ)
+			traceRelease(trace)
+		}
+	}
+}
+
 // deductAssistCredit reduces the current G's assist credit
 // by size bytes, and assists the GC if necessary.
 //