[dev.simd] all: merge master (d70ad4e) into dev.simd

Conflicts:

- src/cmd/compile/internal/types2/stdlib_test.go
- src/go/types/stdlib_test.go

Merge List:

+ 2025-09-25 d70ad4e740 sync/atomic: correct Uintptr.Or return doc
+ 2025-09-25 d7abfe4f0d runtime: acquire/release C TSAN lock when calling cgo symbolizer/tracebacker
+ 2025-09-25 393d91aea0 cmd/fix: remove all functionality
+ 2025-09-25 6dceff8bad cmd/link: handle -w flag in external linking mode
+ 2025-09-25 76d088eb74 cmd/internal/obj/riscv: remove ACFLWSP/ACFSWSP and ACFLW/ACFSW
+ 2025-09-25 5225e9dc49 doc/next: document new image/jpeg DCT in release notes
+ 2025-09-25 81a83bba21 cmd: update x/tools@4df13e3
+ 2025-09-25 6b32c613ca go/types: make typeset return an iterator
+ 2025-09-25 fbba930271 image/jpeg: replace fdct.go and idct.go with new implementation in dct.go
+ 2025-09-25 92e093467f image/jpeg: correct and test reference slowFDCT and slowIDCT
+ 2025-09-25 27c7bbc51c image/jpeg: prepare for new FDCT/IDCT implementations
+ 2025-09-24 f15cd63ec4 cmd/compile: don't rely on loop info when there are irreducible loops
+ 2025-09-24 371c1d2fcb cmd/internal/obj/riscv: add support for vector unit-stride fault-only-first load instructions
+ 2025-09-23 411c250d64 runtime: add specialized malloc functions for sizes up to 512 bytes
+ 2025-09-23 d7a38adf4c runtime: eliminate global span queue [green tea]
+ 2025-09-23 7bc1935db5 cmd/compile/internal: support new(expr)
+ 2025-09-23 eb78f13c9f doc/go_spec.html: document new(expr)
+ 2025-09-23 74cc463f9e go/token: add TestRemovedFileFileReturnsNil test
+ 2025-09-23 902dc27ae9 go/token: clear cache after grabbing the mutex in RemoveFile
+ 2025-09-23 a13d085a5b cmd/cgo: don't hardcode section name in TestNumberOfExportedFunctions
+ 2025-09-23 61bf26a9ee cmd/link: fix Macho-O X86_64_RELOC_SUBTRACTOR in internal linking
+ 2025-09-23 4b787c8c2b reflect: remove stale comment in unpackEface
+ 2025-09-23 3df27cd21a cmd/compile: fix typo in comment
+ 2025-09-23 684e8d3363 reflect: allocate memory in TypeAssert[I] only when the assertion succeeds
+ 2025-09-23 a5866ebe40 cmd/compile: prevent shapifying of pointer shape type
+ 2025-09-23 a27261c42f go/types,types2: allow new(expr)
+ 2025-09-23 e93f439ac4 runtime/cgo: retry when CreateThread fails with ERROR_ACCESS_DENIED
+ 2025-09-23 69e74b0aac runtime: deduplicate pMask resize code
+ 2025-09-23 fde10c4ce7 runtime: split gcMarkWorkAvailable into two separate conditions
+ 2025-09-23 5d040df092 runtime: use scan kernels in scanSpan [green tea]
+ 2025-09-23 7e0251bf58 runtime: don't report non-blocked goroutines as "(durable)" in stacks
+ 2025-09-23 22ac328856 cmd/link: make -w behavior consistent on Windows

Change-Id: Id76b5a30a3b6f6669437f97e3320c9bca65a1e96

1 files changed, 36 insertions, 20 deletions

diff --git a/src/runtime/proc.go b/src/runtime/proc.go
index 05c60c4ba3..887063638b 100644
--- a/src/runtime/proc.go
+++ b/src/runtime/proc.go
@@ -3126,7 +3126,7 @@ func handoffp(pp *p) {
 		return
 	}
 	// if it has GC work, start it straight away
-	if gcBlackenEnabled != 0 && gcMarkWorkAvailable(pp) {
+	if gcBlackenEnabled != 0 && gcShouldScheduleWorker(pp) {
 		startm(pp, false, false)
 		return
 	}
@@ -3507,7 +3507,7 @@ top:
 	//
 	// If we're in the GC mark phase, can safely scan and blacken objects,
 	// and have work to do, run idle-time marking rather than give up the P.
-	if gcBlackenEnabled != 0 && gcMarkWorkAvailable(pp) && gcController.addIdleMarkWorker() {
+	if gcBlackenEnabled != 0 && gcShouldScheduleWorker(pp) && gcController.addIdleMarkWorker() {
 		node := (*gcBgMarkWorkerNode)(gcBgMarkWorkerPool.pop())
 		if node != nil {
 			pp.gcMarkWorkerMode = gcMarkWorkerIdleMode
@@ -3914,7 +3914,7 @@ func checkIdleGCNoP() (*p, *g) {
 	if atomic.Load(&gcBlackenEnabled) == 0 || !gcController.needIdleMarkWorker() {
 		return nil, nil
 	}
-	if !gcMarkWorkAvailable(nil) {
+	if !gcShouldScheduleWorker(nil) {
 		return nil, nil
 	}
 
@@ -5736,6 +5736,7 @@ func setcpuprofilerate(hz int32) {
 // previously destroyed p, and transitions it to status _Pgcstop.
 func (pp *p) init(id int32) {
 	pp.id = id
+	pp.gcw.id = id
 	pp.status = _Pgcstop
 	pp.sudogcache = pp.sudogbuf[:0]
 	pp.deferpool = pp.deferpoolbuf[:0]
@@ -5874,8 +5875,6 @@ func procresize(nprocs int32) *p {
 	}
 	sched.procresizetime = now
 
-	maskWords := (nprocs + 31) / 32
-
 	// Grow allp if necessary.
 	if nprocs > int32(len(allp)) {
 		// Synchronize with retake, which could be running
@@ -5891,19 +5890,9 @@ func procresize(nprocs int32) *p {
 			allp = nallp
 		}
 
-		if maskWords <= int32(cap(idlepMask)) {
-			idlepMask = idlepMask[:maskWords]
-			timerpMask = timerpMask[:maskWords]
-		} else {
-			nidlepMask := make([]uint32, maskWords)
-			// No need to copy beyond len, old Ps are irrelevant.
-			copy(nidlepMask, idlepMask)
-			idlepMask = nidlepMask
-
-			ntimerpMask := make([]uint32, maskWords)
-			copy(ntimerpMask, timerpMask)
-			timerpMask = ntimerpMask
-		}
+		idlepMask = idlepMask.resize(nprocs)
+		timerpMask = timerpMask.resize(nprocs)
+		work.spanqMask = work.spanqMask.resize(nprocs)
 		unlock(&allpLock)
 	}
 
@@ -5966,8 +5955,9 @@ func procresize(nprocs int32) *p {
 	if int32(len(allp)) != nprocs {
 		lock(&allpLock)
 		allp = allp[:nprocs]
-		idlepMask = idlepMask[:maskWords]
-		timerpMask = timerpMask[:maskWords]
+		idlepMask = idlepMask.resize(nprocs)
+		timerpMask = timerpMask.resize(nprocs)
+		work.spanqMask = work.spanqMask.resize(nprocs)
 		unlock(&allpLock)
 	}
 
@@ -6906,6 +6896,32 @@ func (p pMask) clear(id int32) {
 	atomic.And(&p[word], ^mask)
 }
 
+// any returns true if any bit in p is set.
+func (p pMask) any() bool {
+	for i := range p {
+		if atomic.Load(&p[i]) != 0 {
+			return true
+		}
+	}
+	return false
+}
+
+// resize resizes the pMask and returns a new one.
+//
+// The result may alias p, so callers are encouraged to
+// discard p. Not safe for concurrent use.
+func (p pMask) resize(nprocs int32) pMask {
+	maskWords := (nprocs + 31) / 32
+
+	if maskWords <= int32(cap(p)) {
+		return p[:maskWords]
+	}
+	newMask := make([]uint32, maskWords)
+	// No need to copy beyond len, old Ps are irrelevant.
+	copy(newMask, p)
+	return newMask
+}
+
 // pidleput puts p on the _Pidle list. now must be a relatively recent call
 // to nanotime or zero. Returns now or the current time if now was zero.
 //