runtime/cgo: store M for C-created thread in pthread key

In a C thread, it's necessary to acquire an extra M by using needm while invoking a Go function from C. But, needm and dropm are heavy costs due to the signal-related syscalls.
So, we change to not dropm while returning back to C, which means binding the extra M to the C thread until it exits, to avoid needm and dropm on each C to Go call.
Instead, we only dropm while the C thread exits, so the extra M won't leak.

When invoking a Go function from C:
Allocate a pthread variable using pthread_key_create, only once per shared object, and register a thread-exit-time destructor.
And store the g0 of the current m into the thread-specified value of the pthread key,  only once per C thread, so that the destructor will put the extra M back onto the extra M list while the C thread exits.

When returning back to C:
Skip dropm in cgocallback, when the pthread variable has been created, so that the extra M will be reused the next time invoke a Go function from C.

This is purely a performance optimization. The old version, in which needm & dropm happen on each cgo call, is still correct too, and we have to keep the old version on systems with cgo but without pthreads, like Windows.

This optimization is significant, and the specific value depends on the OS system and CPU, but in general, it can be considered as 10x faster, for a simple Go function call from a C thread.

For the newly added BenchmarkCGoInCThread, some benchmark results:
1. it's 28x faster, from 3395 ns/op to 121 ns/op, in darwin OS & Intel(R) Core(TM) i7-9750H CPU @ 2.60GHz
2. it's 6.5x faster, from 1495 ns/op to 230 ns/op, in Linux OS & Intel(R) Xeon(R) CPU E5-2630 0 @ 2.30GHz

Fixes #51676

Change-Id: I380702fe2f9b6b401b2d6f04b0aba990f4b9ee6c
GitHub-Last-Rev: 93dc64a
GitHub-Pull-Request: #51679
Reviewed-on: https://go-review.googlesource.com/c/go/+/392854
Reviewed-by: Ian Lance Taylor <[email protected]>
TryBot-Result: Gopher Robot <[email protected]>
Run-TryBot: thepudds <[email protected]>
Reviewed-by: Cherry Mui <[email protected]>

Author: doujiang24

misc/cgo/test/cgo_test.go

@@ -104,6 +104,7 @@ func TestThreadLock(t *testing.T)            { testThreadLockFunc(t) }
 func TestUnsignedInt(t *testing.T)           { testUnsignedInt(t) }
 func TestZeroArgCallback(t *testing.T)       { testZeroArgCallback(t) }
 
-func BenchmarkCgoCall(b *testing.B)     { benchCgoCall(b) }
-func BenchmarkGoString(b *testing.B)    { benchGoString(b) }
-func BenchmarkCGoCallback(b *testing.B) { benchCallback(b) }
+func BenchmarkCgoCall(b *testing.B)      { benchCgoCall(b) }
+func BenchmarkGoString(b *testing.B)     { benchGoString(b) }
+func BenchmarkCGoCallback(b *testing.B)  { benchCallback(b) }
+func BenchmarkCGoInCThread(b *testing.B) { benchCGoInCthread(b) }

misc/cgo/test/cthread_unix.c

@@ -32,3 +32,27 @@ doAdd(int max, int nthread)
 	for(i=0; i<nthread; i++)
 		pthread_join(thread_id[i], 0);		
 }
+
+static void*
+goDummyCallbackThread(void* p)
+{
+	int i, max;
+
+	max = *(int*)p;
+	for(i=0; i<max; i++)
+		goDummy();
+	return NULL;
+}
+
+int
+callGoInCThread(int max)
+{
+	pthread_t thread;
+
+	if (pthread_create(&thread, NULL, goDummyCallbackThread, (void*)(&max)) != 0)
+		return -1;
+	if (pthread_join(thread, NULL) != 0)
+		return -1;
+
+	return max;
+}

misc/cgo/test/cthread_windows.c

@@ -35,3 +35,25 @@ doAdd(int max, int nthread)
 		CloseHandle((HANDLE)thread_id[i]);
 	}
 }
+
+__stdcall
+static unsigned int
+goDummyCallbackThread(void* p)
+{
+	int i, max;
+
+	max = *(int*)p;
+	for(i=0; i<max; i++)
+		goDummy();
+	return 0;
+}
+
+int
+callGoInCThread(int max)
+{
+	uintptr_t thread_id;
+	thread_id = _beginthreadex(0, 0, goDummyCallbackThread, &max, 0, 0);
+	WaitForSingleObject((HANDLE)thread_id, INFINITE);
+	CloseHandle((HANDLE)thread_id);
+	return max;
+}

misc/cgo/test/testx.go

@@ -24,6 +24,7 @@ import (
 /*
 // threads
 extern void doAdd(int, int);
+extern int callGoInCThread(int);
 
 // issue 1328
 void IntoC(void);
@@ -146,6 +147,10 @@ func Add(x int) {
 	*p = 2
 }
 
+//export goDummy
+func goDummy() {
+}
+
 func testCthread(t *testing.T) {
 	if (runtime.GOOS == "darwin" || runtime.GOOS == "ios") && runtime.GOARCH == "arm64" {
 		t.Skip("the iOS exec wrapper is unable to properly handle the panic from Add")
@@ -159,6 +164,15 @@ func testCthread(t *testing.T) {
 	}
 }
 
+// Benchmark measuring overhead from C to Go in a C thread.
+// Create a new C thread and invoke Go function repeatedly in the new C thread.
+func benchCGoInCthread(b *testing.B) {
+	n := C.callGoInCThread(C.int(b.N))
+	if int(n) != b.N {
+		b.Fatal("unmatch loop times")
+	}
+}
+
 // issue 1328
 
 //export BackIntoGo

src/runtime/asm_386.s

@@ -689,7 +689,20 @@ nosave:
 TEXT ·cgocallback(SB),NOSPLIT,$12-12  // Frame size must match commented places below
 	NO_LOCAL_POINTERS
 
-	// If g is nil, Go did not create the current thread.
+	// Skip cgocallbackg, just dropm when fn is nil, and frame is the saved g.
+	// It is used to dropm while thread is exiting.
+	MOVL	fn+0(FP), AX
+	CMPL	AX, $0
+	JNE	loadg
+	// Restore the g from frame.
+	get_tls(CX)
+	MOVL	frame+4(FP), BX
+	MOVL	BX, g(CX)
+	JMP	dropm
+
+loadg:
+	// If g is nil, Go did not create the current thread,
+	// or if this thread never called into Go on pthread platforms.
 	// Call needm to obtain one for temporary use.
 	// In this case, we're running on the thread stack, so there's
 	// lots of space, but the linker doesn't know. Hide the call from
@@ -707,9 +720,9 @@ TEXT ·cgocallback(SB),NOSPLIT,$12-12  // Frame size must match commented places
 	MOVL	BP, savedm-4(SP) // saved copy of oldm
 	JMP	havem
 needm:
-	MOVL	$runtime·needm(SB), AX
+	MOVL	$runtime·needAndBindM(SB), AX
 	CALL	AX
-	MOVL	$0, savedm-4(SP) // dropm on return
+	MOVL	$0, savedm-4(SP)
 	get_tls(CX)
 	MOVL	g(CX), BP
 	MOVL	g_m(BP), BP
@@ -784,13 +797,29 @@ havem:
 	MOVL	0(SP), AX
 	MOVL	AX, (g_sched+gobuf_sp)(SI)
 
-	// If the m on entry was nil, we called needm above to borrow an m
-	// for the duration of the call. Since the call is over, return it with dropm.
+	// If the m on entry was nil, we called needm above to borrow an m,
+	// 1. for the duration of the call on non-pthread platforms,
+	// 2. or the duration of the C thread alive on pthread platforms.
+	// If the m on entry wasn't nil,
+	// 1. the thread might be a Go thread,
+	// 2. or it's wasn't the first call from a C thread on pthread platforms,
+	//    since the we skip dropm to resue the m in the first call.
 	MOVL	savedm-4(SP), DX
 	CMPL	DX, $0
-	JNE 3(PC)
+	JNE	droppedm
+
+	// Skip dropm to reuse it in the next call, when a pthread key has been created.
+	MOVL	_cgo_pthread_key_created(SB), DX
+	// It means cgo is disabled when _cgo_pthread_key_created is a nil pointer, need dropm.
+	CMPL	DX, $0
+	JEQ	dropm
+	CMPL	(DX), $0
+	JNE	droppedm
+
+dropm:
 	MOVL	$runtime·dropm(SB), AX
 	CALL	AX
+droppedm:
 
 	// Done!
 	RET

src/runtime/asm_amd64.s

@@ -915,7 +915,20 @@ GLOBL zeroTLS<>(SB),RODATA,$const_tlsSize
 TEXT ·cgocallback(SB),NOSPLIT,$24-24
 	NO_LOCAL_POINTERS
 
-	// If g is nil, Go did not create the current thread.
+	// Skip cgocallbackg, just dropm when fn is nil, and frame is the saved g.
+	// It is used to dropm while thread is exiting.
+	MOVQ	fn+0(FP), AX
+	CMPQ	AX, $0
+	JNE	loadg
+	// Restore the g from frame.
+	get_tls(CX)
+	MOVQ	frame+8(FP), BX
+	MOVQ	BX, g(CX)
+	JMP	dropm
+
+loadg:
+	// If g is nil, Go did not create the current thread,
+	// or if this thread never called into Go on pthread platforms.
 	// Call needm to obtain one m for temporary use.
 	// In this case, we're running on the thread stack, so there's
 	// lots of space, but the linker doesn't know. Hide the call from
@@ -953,9 +966,9 @@ needm:
 	// a bad value in there, in case needm tries to use it.
 	XORPS	X15, X15
 	XORQ    R14, R14
-	MOVQ	$runtime·needm<ABIInternal>(SB), AX
+	MOVQ	$runtime·needAndBindM<ABIInternal>(SB), AX
 	CALL	AX
-	MOVQ	$0, savedm-8(SP) // dropm on return
+	MOVQ	$0, savedm-8(SP)
 	get_tls(CX)
 	MOVQ	g(CX), BX
 	MOVQ	g_m(BX), BX
@@ -1044,11 +1057,26 @@ havem:
 	MOVQ	0(SP), AX
 	MOVQ	AX, (g_sched+gobuf_sp)(SI)
 
-	// If the m on entry was nil, we called needm above to borrow an m
-	// for the duration of the call. Since the call is over, return it with dropm.
+	// If the m on entry was nil, we called needm above to borrow an m,
+	// 1. for the duration of the call on non-pthread platforms,
+	// 2. or the duration of the C thread alive on pthread platforms.
+	// If the m on entry wasn't nil,
+	// 1. the thread might be a Go thread,
+	// 2. or it's wasn't the first call from a C thread on pthread platforms,
+	//    since the we skip dropm to resue the m in the first call.
 	MOVQ	savedm-8(SP), BX
 	CMPQ	BX, $0
 	JNE	done
+
+	// Skip dropm to reuse it in the next call, when a pthread key has been created.
+	MOVQ	_cgo_pthread_key_created(SB), AX
+	// It means cgo is disabled when _cgo_pthread_key_created is a nil pointer, need dropm.
+	CMPQ	AX, $0
+	JEQ	dropm
+	CMPQ	(AX), $0
+	JNE	done
+
+dropm:
 	MOVQ	$runtime·dropm(SB), AX
 	CALL	AX
 #ifdef GOOS_windows

src/runtime/asm_arm.s

@@ -630,6 +630,15 @@ nosave:
 TEXT	·cgocallback(SB),NOSPLIT,$12-12
 	NO_LOCAL_POINTERS
 
+	// Skip cgocallbackg, just dropm when fn is nil, and frame is the saved g.
+	// It is used to dropm while thread is exiting.
+	MOVW	fn+0(FP), R1
+	B.NE	loadg
+	// Restore the g from frame.
+	MOVW	frame+4(FP), g
+	B	dropm
+
+loadg:
 	// Load m and g from thread-local storage.
 #ifdef GOOS_openbsd
 	BL	runtime·load_g(SB)
@@ -639,7 +648,8 @@ TEXT	·cgocallback(SB),NOSPLIT,$12-12
 	BL.NE	runtime·load_g(SB)
 #endif
 
-	// If g is nil, Go did not create the current thread.
+	// If g is nil, Go did not create the current thread,
+	// or if this thread never called into Go on pthread platforms.
 	// Call needm to obtain one for temporary use.
 	// In this case, we're running on the thread stack, so there's
 	// lots of space, but the linker doesn't know. Hide the call from
@@ -653,7 +663,7 @@ TEXT	·cgocallback(SB),NOSPLIT,$12-12
 
 needm:
 	MOVW	g, savedm-4(SP) // g is zero, so is m.
-	MOVW	$runtime·needm(SB), R0
+	MOVW	$runtime·needAndBindM(SB), R0
 	BL	(R0)
 
 	// Set m->g0->sched.sp = SP, so that if a panic happens
@@ -724,14 +734,31 @@ havem:
 	MOVW	savedsp-12(SP), R4	// must match frame size
 	MOVW	R4, (g_sched+gobuf_sp)(g)
 
-	// If the m on entry was nil, we called needm above to borrow an m
-	// for the duration of the call. Since the call is over, return it with dropm.
+	// If the m on entry was nil, we called needm above to borrow an m,
+	// 1. for the duration of the call on non-pthread platforms,
+	// 2. or the duration of the C thread alive on pthread platforms.
+	// If the m on entry wasn't nil,
+	// 1. the thread might be a Go thread,
+	// 2. or it's wasn't the first call from a C thread on pthread platforms,
+	//    since the we skip dropm to resue the m in the first call.
 	MOVW	savedm-4(SP), R6
 	CMP	$0, R6
-	B.NE	3(PC)
+	B.NE	done
+
+	// Skip dropm to reuse it in the next call, when a pthread key has been created.
+	MOVW	_cgo_pthread_key_created(SB), R6
+	// It means cgo is disabled when _cgo_pthread_key_created is a nil pointer, need dropm.
+	CMP	$0, R6
+	B.EQ	dropm
+	MOVW	(R6), R6
+	CMP	$0, R6
+	B.NE	done
+
+dropm:
 	MOVW	$runtime·dropm(SB), R0
 	BL	(R0)
 
+done:
 	// Done!
 	RET
 

src/runtime/asm_arm64.s

@@ -1014,10 +1014,20 @@ nosave:
 TEXT ·cgocallback(SB),NOSPLIT,$24-24
 	NO_LOCAL_POINTERS
 
+	// Skip cgocallbackg, just dropm when fn is nil, and frame is the saved g.
+	// It is used to dropm while thread is exiting.
+	MOVD	fn+0(FP), R1
+	CBNZ	R1, loadg
+	// Restore the g from frame.
+	MOVD	frame+8(FP), g
+	B	dropm
+
+loadg:
 	// Load g from thread-local storage.
 	BL	runtime·load_g(SB)
 
-	// If g is nil, Go did not create the current thread.
+	// If g is nil, Go did not create the current thread,
+	// or if this thread never called into Go on pthread platforms.
 	// Call needm to obtain one for temporary use.
 	// In this case, we're running on the thread stack, so there's
 	// lots of space, but the linker doesn't know. Hide the call from
@@ -1030,7 +1040,7 @@ TEXT ·cgocallback(SB),NOSPLIT,$24-24
 
 needm:
 	MOVD	g, savedm-8(SP) // g is zero, so is m.
-	MOVD	$runtime·needm(SB), R0
+	MOVD	$runtime·needAndBindM(SB), R0
 	BL	(R0)
 
 	// Set m->g0->sched.sp = SP, so that if a panic happens
@@ -1111,10 +1121,24 @@ havem:
 	MOVD	savedsp-16(SP), R4
 	MOVD	R4, (g_sched+gobuf_sp)(g)
 
-	// If the m on entry was nil, we called needm above to borrow an m
-	// for the duration of the call. Since the call is over, return it with dropm.
+	// If the m on entry was nil, we called needm above to borrow an m,
+	// 1. for the duration of the call on non-pthread platforms,
+	// 2. or the duration of the C thread alive on pthread platforms.
+	// If the m on entry wasn't nil,
+	// 1. the thread might be a Go thread,
+	// 2. or it's wasn't the first call from a C thread on pthread platforms,
+	//    since the we skip dropm to resue the m in the first call.
 	MOVD	savedm-8(SP), R6
 	CBNZ	R6, droppedm
+
+	// Skip dropm to reuse it in the next call, when a pthread key has been created.
+	MOVD	_cgo_pthread_key_created(SB), R6
+	// It means cgo is disabled when _cgo_pthread_key_created is a nil pointer, need dropm.
+	CBZ	R6, dropm
+	MOVD	(R6), R6
+	CBNZ	R6, droppedm
+
+dropm:
 	MOVD	$runtime·dropm(SB), R0
 	BL	(R0)
 droppedm: