runtime: redo heap bitmap

[this is a retry of CL 407035 + its revert CL 422395. The content is unchanged]

Use just 1 bit per word to record the ptr/nonptr bitmap.
Use word-sized operations to manipulate the bitmap, so we can operate
on up to 64 ptr/nonptr bits at a time.

Use a separate bitmap, one bit per word of the ptr/nonptr bitmap,
to encode a no-more-pointers signal. Since we can check 64 ptr/nonptr
bits at once, knowing the exact last pointer location is not necessary.

As a followon CL, we should make the gcdata bitmap an array of
uintptr instead of an array of byte, so we can load 64 bits of it at once.
Similarly for the processing of gc programs.

Change-Id: Ica5eb622f5b87e647be64f471d67b02732ef8be6
Reviewed-on: https://go-review.googlesource.com/c/go/+/422634
Reviewed-by: Michael Knyszek <mknyszek@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@google.com>
Run-TryBot: Keith Randall <khr@golang.org>

1 files changed, 6 insertions, 4 deletions

diff --git a/src/runtime/malloc.go b/src/runtime/malloc.go
index b044e29d95..0219401c83 100644
--- a/src/runtime/malloc.go
+++ b/src/runtime/malloc.go
@@ -247,13 +247,15 @@ const (
 	// memory.
 	heapArenaBytes = 1 << logHeapArenaBytes
 
+	heapArenaWords = heapArenaBytes / goarch.PtrSize
+
 	// logHeapArenaBytes is log_2 of heapArenaBytes. For clarity,
 	// prefer using heapArenaBytes where possible (we need the
 	// constant to compute some other constants).
 	logHeapArenaBytes = (6+20)*(_64bit*(1-goos.IsWindows)*(1-goarch.IsWasm)*(1-goos.IsIos*goarch.IsArm64)) + (2+20)*(_64bit*goos.IsWindows) + (2+20)*(1-_64bit) + (2+20)*goarch.IsWasm + (2+20)*goos.IsIos*goarch.IsArm64
 
-	// heapArenaBitmapBytes is the size of each heap arena's bitmap.
-	heapArenaBitmapBytes = heapArenaBytes / (goarch.PtrSize * 8 / 2)
+	// heapArenaBitmapWords is the size of each heap arena's bitmap in uintptrs.
+	heapArenaBitmapWords = heapArenaWords / (8 * goarch.PtrSize)
 
 	pagesPerArena = heapArenaBytes / pageSize
 
@@ -353,10 +355,10 @@ func mallocinit() {
 		throw("bad TinySizeClass")
 	}
 
-	if heapArenaBitmapBytes&(heapArenaBitmapBytes-1) != 0 {
+	if heapArenaBitmapWords&(heapArenaBitmapWords-1) != 0 {
 		// heapBits expects modular arithmetic on bitmap
 		// addresses to work.
-		throw("heapArenaBitmapBytes not a power of 2")
+		throw("heapArenaBitmapWords not a power of 2")
 	}
 
 	// Check physPageSize.