cmd/compile: optimize make+copy pattern to avoid memclr

match:
 m = make([]T, x); copy(m, s)
for pointer free T and x==len(s) rewrite to:
 m = mallocgc(x*elemsize(T), nil, false); memmove(&m, &s, x*elemsize(T))
otherwise rewrite to:
 m = makeslicecopy([]T, x, s)

This avoids memclear and shading of pointers in the newly created slice
before the copy.

With this CL "s" is only be allowed to bev a variable and not a more
complex expression. This restriction could be lifted in future versions
of this optimization when it can be proven that "s" is not referencing "m".

Triggers 450 times during make.bash..
Reduces go binary size by ~8 kbyte.

name                           old time/op  new time/op  delta
MakeSliceCopy/mallocmove/Byte  71.1ns ± 1%  65.8ns ± 0%  -7.49%  (p=0.000 n=10+9)
MakeSliceCopy/mallocmove/Int   71.2ns ± 1%  66.0ns ± 0%  -7.27%  (p=0.000 n=10+8)
MakeSliceCopy/mallocmove/Ptr    104ns ± 4%    99ns ± 1%  -5.13%  (p=0.000 n=10+10)
MakeSliceCopy/makecopy/Byte    70.3ns ± 0%  68.0ns ± 0%  -3.22%  (p=0.000 n=10+9)
MakeSliceCopy/makecopy/Int     70.3ns ± 0%  68.5ns ± 1%  -2.59%  (p=0.000 n=9+10)
MakeSliceCopy/makecopy/Ptr      102ns ± 0%    99ns ± 1%  -2.97%  (p=0.000 n=9+9)
MakeSliceCopy/nilappend/Byte   75.4ns ± 0%  74.9ns ± 2%  -0.63%  (p=0.015 n=9+9)
MakeSliceCopy/nilappend/Int    75.6ns ± 0%  76.4ns ± 3%    ~     (p=0.245 n=9+10)
MakeSliceCopy/nilappend/Ptr     107ns ± 0%   108ns ± 1%  +0.93%  (p=0.005 n=9+10)

Fixes #26252

Change-Id: Iec553dd1fef6ded16197216a472351c8799a8e71
Reviewed-on: https://go-review.googlesource.com/c/go/+/146719
Reviewed-by: Keith Randall <khr@golang.org>
Run-TryBot: Martin Möhrmann <moehrmann@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>

1 files changed, 49 insertions, 0 deletions

diff --git a/src/runtime/slice.go b/src/runtime/slice.go
index 4ea4478601..d9949e7939 100644
--- a/src/runtime/slice.go
+++ b/src/runtime/slice.go
@@ -31,6 +31,55 @@ func panicmakeslicecap() {
 	panic(errorString("makeslice: cap out of range"))
 }
 
+// makeslicecopy allocates a slice of "tolen" elements of type "et",
+// then copies "fromlen" elements of type "et" into that new allocation from "from".
+func makeslicecopy(et *_type, tolen int, fromlen int, from unsafe.Pointer) unsafe.Pointer {
+	var tomem, copymem uintptr
+	if uintptr(tolen) > uintptr(fromlen) {
+		var overflow bool
+		tomem, overflow = math.MulUintptr(et.size, uintptr(tolen))
+		if overflow || tomem > maxAlloc || tolen < 0 {
+			panicmakeslicelen()
+		}
+		copymem = et.size * uintptr(fromlen)
+	} else {
+		// fromlen is a known good length providing and equal or greater than tolen,
+		// thereby making tolen a good slice length too as from and to slices have the
+		// same element width.
+		tomem = et.size * uintptr(tolen)
+		copymem = tomem
+	}
+
+	var to unsafe.Pointer
+	if et.ptrdata == 0 {
+		to = mallocgc(tomem, nil, false)
+		if copymem < tomem {
+			memclrNoHeapPointers(add(to, copymem), tomem-copymem)
+		}
+	} else {
+		// Note: can't use rawmem (which avoids zeroing of memory), because then GC can scan uninitialized memory.
+		to = mallocgc(tomem, et, true)
+		if writeBarrier.enabled {
+			// Only shade the pointers in old.array since we know the destination slice to
+			// only contains nil pointers because it has been cleared during alloc.
+			bulkBarrierPreWriteSrcOnly(uintptr(to), uintptr(from), copymem)
+		}
+	}
+
+	if raceenabled {
+		callerpc := getcallerpc()
+		pc := funcPC(makeslicecopy)
+		racereadrangepc(from, copymem, callerpc, pc)
+	}
+	if msanenabled {
+		msanread(from, copymem)
+	}
+
+	memmove(to, from, copymem)
+
+	return to
+}
+
 func makeslice(et *_type, len, cap int) unsafe.Pointer {
 	mem, overflow := math.MulUintptr(et.size, uintptr(cap))
 	if overflow || mem > maxAlloc || len < 0 || len > cap {