1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
|
// Copyright 2009 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package runtime
import (
"runtime/internal/atomic"
"unsafe"
)
// Per-thread (in Go, per-P) cache for small objects.
// This includes a small object cache and local allocation stats.
// No locking needed because it is per-thread (per-P).
//
// mcaches are allocated from non-GC'd memory, so any heap pointers
// must be specially handled.
//
//go:notinheap
type mcache struct {
// The following members are accessed on every malloc,
// so they are grouped here for better caching.
nextSample uintptr // trigger heap sample after allocating this many bytes
scanAlloc uintptr // bytes of scannable heap allocated
// Allocator cache for tiny objects w/o pointers.
// See "Tiny allocator" comment in malloc.go.
// tiny points to the beginning of the current tiny block, or
// nil if there is no current tiny block.
//
// tiny is a heap pointer. Since mcache is in non-GC'd memory,
// we handle it by clearing it in releaseAll during mark
// termination.
//
// tinyAllocs is the number of tiny allocations performed
// by the P that owns this mcache.
tiny uintptr
tinyoffset uintptr
tinyAllocs uintptr
// The rest is not accessed on every malloc.
alloc [numSpanClasses]*mspan // spans to allocate from, indexed by spanClass
// flushGen indicates the sweepgen during which this mcache
// was last flushed. If flushGen != mheap_.sweepgen, the spans
// in this mcache are stale and need to the flushed so they
// can be swept. This is done in acquirep.
flushGen uint32
}
// A gclink is a node in a linked list of blocks, like mlink,
// but it is opaque to the garbage collector.
// The GC does not trace the pointers during collection,
// and the compiler does not emit write barriers for assignments
// of gclinkptr values. Code should store references to gclinks
// as gclinkptr, not as *gclink.
type gclink struct {
next gclinkptr
}
// A gclinkptr is a pointer to a gclink, but it is opaque
// to the garbage collector.
type gclinkptr uintptr
// ptr returns the *gclink form of p.
// The result should be used for accessing fields, not stored
// in other data structures.
func (p gclinkptr) ptr() *gclink {
return (*gclink)(unsafe.Pointer(p))
}
// dummy mspan that contains no free objects.
var emptymspan mspan
func allocmcache() *mcache {
var c *mcache
systemstack(func() {
lock(&mheap_.lock)
c = (*mcache)(mheap_.cachealloc.alloc())
c.flushGen = mheap_.sweepgen
unlock(&mheap_.lock)
})
for i := range c.alloc {
c.alloc[i] = &emptymspan
}
c.nextSample = nextSample()
return c
}
// freemcache releases resources associated with this
// mcache and puts the object onto a free list.
//
// In some cases there is no way to simply release
// resources, such as statistics, so donate them to
// a different mcache (the recipient).
func freemcache(c *mcache) {
systemstack(func() {
c.releaseAll()
// NOTE(rsc,rlh): If gcworkbuffree comes back, we need to coordinate
// with the stealing of gcworkbufs during garbage collection to avoid
// a race where the workbuf is double-freed.
// gcworkbuffree(c.gcworkbuf)
lock(&mheap_.lock)
mheap_.cachealloc.free(unsafe.Pointer(c))
unlock(&mheap_.lock)
})
}
// getMCache is a convenience function which tries to obtain an mcache.
//
// Returns nil if we're not bootstrapping or we don't have a P. The caller's
// P must not change, so we must be in a non-preemptible state.
func getMCache() *mcache {
// Grab the mcache, since that's where stats live.
pp := getg().m.p.ptr()
var c *mcache
if pp == nil {
// We will be called without a P while bootstrapping,
// in which case we use mcache0, which is set in mallocinit.
// mcache0 is cleared when bootstrapping is complete,
// by procresize.
c = mcache0
} else {
c = pp.mcache
}
return c
}
// refill acquires a new span of span class spc for c. This span will
// have at least one free object. The current span in c must be full.
//
// Must run in a non-preemptible context since otherwise the owner of
// c could change.
func (c *mcache) refill(spc spanClass) {
// Return the current cached span to the central lists.
s := c.alloc[spc]
if uintptr(s.allocCount) != s.nelems {
throw("refill of span with free space remaining")
}
if s != &emptymspan {
// Mark this span as no longer cached.
if s.sweepgen != mheap_.sweepgen+3 {
throw("bad sweepgen in refill")
}
mheap_.central[spc].mcentral.uncacheSpan(s)
}
// Get a new cached span from the central lists.
s = mheap_.central[spc].mcentral.cacheSpan()
if s == nil {
throw("out of memory")
}
if uintptr(s.allocCount) == s.nelems {
throw("span has no free space")
}
// Indicate that this span is cached and prevent asynchronous
// sweeping in the next sweep phase.
s.sweepgen = mheap_.sweepgen + 3
// Assume all objects from this span will be allocated in the
// mcache. If it gets uncached, we'll adjust this.
stats := memstats.heapStats.acquire()
atomic.Xadduintptr(&stats.smallAllocCount[spc.sizeclass()], uintptr(s.nelems)-uintptr(s.allocCount))
memstats.heapStats.release()
// Update heap_live with the same assumption.
usedBytes := uintptr(s.allocCount) * s.elemsize
atomic.Xadd64(&memstats.heap_live, int64(s.npages*pageSize)-int64(usedBytes))
// Flush tinyAllocs.
if spc == tinySpanClass {
atomic.Xadd64(&memstats.tinyallocs, int64(c.tinyAllocs))
c.tinyAllocs = 0
}
// While we're here, flush scanAlloc, since we have to call
// revise anyway.
atomic.Xadd64(&memstats.heap_scan, int64(c.scanAlloc))
c.scanAlloc = 0
if trace.enabled {
// heap_live changed.
traceHeapAlloc()
}
if gcBlackenEnabled != 0 {
// heap_live and heap_scan changed.
gcController.revise()
}
c.alloc[spc] = s
}
// allocLarge allocates a span for a large object.
func (c *mcache) allocLarge(size uintptr, needzero bool, noscan bool) *mspan {
if size+_PageSize < size {
throw("out of memory")
}
npages := size >> _PageShift
if size&_PageMask != 0 {
npages++
}
// Deduct credit for this span allocation and sweep if
// necessary. mHeap_Alloc will also sweep npages, so this only
// pays the debt down to npage pages.
deductSweepCredit(npages*_PageSize, npages)
spc := makeSpanClass(0, noscan)
s := mheap_.alloc(npages, spc, needzero)
if s == nil {
throw("out of memory")
}
stats := memstats.heapStats.acquire()
atomic.Xadduintptr(&stats.largeAlloc, npages*pageSize)
atomic.Xadduintptr(&stats.largeAllocCount, 1)
memstats.heapStats.release()
// Update heap_live and revise pacing if needed.
atomic.Xadd64(&memstats.heap_live, int64(npages*pageSize))
if trace.enabled {
// Trace that a heap alloc occurred because heap_live changed.
traceHeapAlloc()
}
if gcBlackenEnabled != 0 {
gcController.revise()
}
// Put the large span in the mcentral swept list so that it's
// visible to the background sweeper.
mheap_.central[spc].mcentral.fullSwept(mheap_.sweepgen).push(s)
s.limit = s.base() + size
heapBitsForAddr(s.base()).initSpan(s)
return s
}
func (c *mcache) releaseAll() {
// Take this opportunity to flush scanAlloc.
atomic.Xadd64(&memstats.heap_scan, int64(c.scanAlloc))
c.scanAlloc = 0
sg := mheap_.sweepgen
for i := range c.alloc {
s := c.alloc[i]
if s != &emptymspan {
// Adjust nsmallalloc in case the span wasn't fully allocated.
n := uintptr(s.nelems) - uintptr(s.allocCount)
stats := memstats.heapStats.acquire()
atomic.Xadduintptr(&stats.smallAllocCount[spanClass(i).sizeclass()], -n)
memstats.heapStats.release()
if s.sweepgen != sg+1 {
// refill conservatively counted unallocated slots in heap_live.
// Undo this.
//
// If this span was cached before sweep, then
// heap_live was totally recomputed since
// caching this span, so we don't do this for
// stale spans.
atomic.Xadd64(&memstats.heap_live, -int64(n)*int64(s.elemsize))
}
// Release the span to the mcentral.
mheap_.central[i].mcentral.uncacheSpan(s)
c.alloc[i] = &emptymspan
}
}
// Clear tinyalloc pool.
c.tiny = 0
c.tinyoffset = 0
atomic.Xadd64(&memstats.tinyallocs, int64(c.tinyAllocs))
c.tinyAllocs = 0
// Updated heap_scan and possible heap_live.
if gcBlackenEnabled != 0 {
gcController.revise()
}
}
// prepareForSweep flushes c if the system has entered a new sweep phase
// since c was populated. This must happen between the sweep phase
// starting and the first allocation from c.
func (c *mcache) prepareForSweep() {
// Alternatively, instead of making sure we do this on every P
// between starting the world and allocating on that P, we
// could leave allocate-black on, allow allocation to continue
// as usual, use a ragged barrier at the beginning of sweep to
// ensure all cached spans are swept, and then disable
// allocate-black. However, with this approach it's difficult
// to avoid spilling mark bits into the *next* GC cycle.
sg := mheap_.sweepgen
if c.flushGen == sg {
return
} else if c.flushGen != sg-2 {
println("bad flushGen", c.flushGen, "in prepareForSweep; sweepgen", sg)
throw("bad flushGen")
}
c.releaseAll()
atomic.Store(&c.flushGen, mheap_.sweepgen) // Synchronizes with gcStart
}
|