runtime: use uintptr where possible in malloc stats

linux/arm OMAP4 pandaboard

benchmark                 old ns/op    new ns/op    delta
BenchmarkBinaryTree17   68723297000  37026214000  -46.12%
BenchmarkFannkuch11     34962402000  35958435000   +2.85%
BenchmarkGobDecode        137298600    124182150   -9.55%
BenchmarkGobEncode         60717160     60006700   -1.17%
BenchmarkGzip            5647156000   5550873000   -1.70%
BenchmarkGunzip          1196350000   1198670000   +0.19%
BenchmarkJSONEncode       863012800    782898000   -9.28%
BenchmarkJSONDecode      3312989000   2781800000  -16.03%
BenchmarkMandelbrot200     45727540     45703120   -0.05%
BenchmarkParse             74781800     59990840  -19.78%
BenchmarkRevcomp          140043650    139462300   -0.42%
BenchmarkTemplate        6467682000   5832153000   -9.83%

benchmark                  old MB/s     new MB/s  speedup
BenchmarkGobDecode             5.59         6.18    1.11x
BenchmarkGobEncode            12.64        12.79    1.01x
BenchmarkGzip                  3.44         3.50    1.02x
BenchmarkGunzip               16.22        16.19    1.00x
BenchmarkJSONEncode            2.25         2.48    1.10x
BenchmarkJSONDecode            0.59         0.70    1.19x
BenchmarkParse                 0.77         0.97    1.26x
BenchmarkRevcomp              18.15        18.23    1.00x
BenchmarkTemplate              0.30         0.33    1.10x

darwin/386 core duo

benchmark                 old ns/op    new ns/op    delta
BenchmarkBinaryTree17   10591616577   9678245733   -8.62%
BenchmarkFannkuch11     10758473315  10749303846   -0.09%
BenchmarkGobDecode         34379785     34121250   -0.75%
BenchmarkGobEncode         23523721     23475750   -0.20%
BenchmarkGzip            2486191492   2446539568   -1.59%
BenchmarkGunzip           444179328    444250293   +0.02%
BenchmarkJSONEncode       221138507    219757826   -0.62%
BenchmarkJSONDecode      1056034428   1048975133   -0.67%
BenchmarkMandelbrot200     19862516     19868346   +0.03%
BenchmarkRevcomp         3742610872   3724821662   -0.48%
BenchmarkTemplate         960283112    944791517   -1.61%

benchmark                  old MB/s     new MB/s  speedup
BenchmarkGobDecode            22.33        22.49    1.01x
BenchmarkGobEncode            32.63        32.69    1.00x
BenchmarkGzip                  7.80         7.93    1.02x
BenchmarkGunzip               43.69        43.68    1.00x
BenchmarkJSONEncode            8.77         8.83    1.01x
BenchmarkJSONDecode            1.84         1.85    1.01x
BenchmarkRevcomp              67.91        68.24    1.00x
BenchmarkTemplate              2.02         2.05    1.01x

R=rsc, 0xe2.0x9a.0x9b, mirtchovski
CC=golang-dev, minux.ma
https://golang.org/cl/6297047

src/pkg/runtime/malloc.goc

@@ -72,6 +72,14 @@ runtime·mallocgc(uintptr size, uint32 flag, int32 dogc, int32 zeroed)
 		// setup for mark sweep
 		runtime·markspan(v, 0, 0, true);
 	}
+
+	if (sizeof(void*) == 4 && c->local_total_alloc >= (1<<30)) {
+		// purge cache stats to prevent overflow
+		runtime·lock(&runtime·mheap);
+		runtime·purgecachedstats(m);
+		runtime·unlock(&runtime·mheap);
+	}
+
 	if(!(flag & FlagNoGC))
 		runtime·markallocated(v, size, (flag&FlagNoPointers) != 0);
 
@@ -170,6 +178,13 @@ runtime·mlookup(void *v, byte **base, uintptr *size, MSpan **sp)
 	MSpan *s;
 
 	m->mcache->local_nlookup++;
+	if (sizeof(void*) == 4 && m->mcache->local_nlookup >= (1<<30)) {
+		// purge cache stats to prevent overflow
+		runtime·lock(&runtime·mheap);
+		runtime·purgecachedstats(m);
+		runtime·unlock(&runtime·mheap);
+	}
+
 	s = runtime·MHeap_LookupMaybe(&runtime·mheap, v);
 	if(sp)
 		*sp = s;

src/pkg/runtime/malloc.h

@@ -273,19 +273,19 @@ struct MCacheList
 struct MCache
 {
 	MCacheList list[NumSizeClasses];
-	uint64 size;
-	int64 local_cachealloc;	// bytes allocated (or freed) from cache since last lock of heap
-	int64 local_objects;	// objects allocated (or freed) from cache since last lock of heap
-	int64 local_alloc;	// bytes allocated (or freed) since last lock of heap
-	int64 local_total_alloc;	// bytes allocated (even if freed) since last lock of heap
-	int64 local_nmalloc;	// number of mallocs since last lock of heap
-	int64 local_nfree;	// number of frees since last lock of heap
-	int64 local_nlookup;	// number of pointer lookups since last lock of heap
+	uintptr size;
+	intptr local_cachealloc;	// bytes allocated (or freed) from cache since last lock of heap
+	intptr local_objects;	// objects allocated (or freed) from cache since last lock of heap
+	intptr local_alloc;	// bytes allocated (or freed) since last lock of heap
+	uintptr local_total_alloc;	// bytes allocated (even if freed) since last lock of heap
+	uintptr local_nmalloc;	// number of mallocs since last lock of heap
+	uintptr local_nfree;	// number of frees since last lock of heap
+	uintptr local_nlookup;	// number of pointer lookups since last lock of heap
 	int32 next_sample;	// trigger heap sample after allocating this many bytes
 	// Statistics about allocation size classes since last lock of heap
 	struct {
-		int64 nmalloc;
-		int64 nfree;
+		uintptr nmalloc;
+		uintptr nfree;
 	} local_by_size[NumSizeClasses];
 
 };