1
0
mirror of https://github.com/golang/go synced 2024-11-20 06:14:53 -07:00
go/src/pkg/runtime/sys_linux_amd64.s

394 lines
7.2 KiB
ArmAsm
Raw Normal View History

// 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.
//
// System calls and other sys.stuff for AMD64, Linux
//
#include "zasm_GOOS_GOARCH.h"
TEXT runtime·exit(SB),7,$0-8
MOVL 8(SP), DI
MOVL $231, AX // exitgroup - force all os threads to exit
SYSCALL
RET
TEXT runtime·exit1(SB),7,$0-8
MOVL 8(SP), DI
MOVL $60, AX // exit - exit the current os thread
SYSCALL
RET
TEXT runtime·open(SB),7,$0-16
MOVQ 8(SP), DI
MOVL 16(SP), SI
MOVL 20(SP), DX
MOVL $2, AX // syscall entry
SYSCALL
RET
runtime: improve Linux mutex The implementation is hybrid active/passive spin/blocking mutex. The design minimizes amount of context switches and futex calls. The idea is that all critical sections in runtime are intentially small, so pure blocking mutex behaves badly causing a lot of context switches, thread parking/unparking and kernel calls. Note that some synthetic benchmarks become somewhat slower, that's due to increased contention on other data structures, it should not affect programs that do any real work. On 2 x Intel E5620, 8 HT cores, 2.4GHz benchmark old ns/op new ns/op delta BenchmarkSelectContended 521.00 503.00 -3.45% BenchmarkSelectContended-2 661.00 320.00 -51.59% BenchmarkSelectContended-4 1139.00 629.00 -44.78% BenchmarkSelectContended-8 2870.00 878.00 -69.41% BenchmarkSelectContended-16 5276.00 818.00 -84.50% BenchmarkChanContended 112.00 103.00 -8.04% BenchmarkChanContended-2 631.00 174.00 -72.42% BenchmarkChanContended-4 682.00 272.00 -60.12% BenchmarkChanContended-8 1601.00 520.00 -67.52% BenchmarkChanContended-16 3100.00 372.00 -88.00% BenchmarkChanSync 253.00 239.00 -5.53% BenchmarkChanSync-2 5030.00 4648.00 -7.59% BenchmarkChanSync-4 4826.00 4694.00 -2.74% BenchmarkChanSync-8 4778.00 4713.00 -1.36% BenchmarkChanSync-16 5289.00 4710.00 -10.95% BenchmarkChanProdCons0 273.00 254.00 -6.96% BenchmarkChanProdCons0-2 599.00 400.00 -33.22% BenchmarkChanProdCons0-4 1168.00 659.00 -43.58% BenchmarkChanProdCons0-8 2831.00 1057.00 -62.66% BenchmarkChanProdCons0-16 4197.00 1037.00 -75.29% BenchmarkChanProdCons10 150.00 140.00 -6.67% BenchmarkChanProdCons10-2 607.00 268.00 -55.85% BenchmarkChanProdCons10-4 1137.00 404.00 -64.47% BenchmarkChanProdCons10-8 2115.00 828.00 -60.85% BenchmarkChanProdCons10-16 4283.00 855.00 -80.04% BenchmarkChanProdCons100 117.00 110.00 -5.98% BenchmarkChanProdCons100-2 558.00 218.00 -60.93% BenchmarkChanProdCons100-4 722.00 287.00 -60.25% BenchmarkChanProdCons100-8 1840.00 431.00 -76.58% BenchmarkChanProdCons100-16 3394.00 448.00 -86.80% BenchmarkChanProdConsWork0 2014.00 1996.00 -0.89% BenchmarkChanProdConsWork0-2 1207.00 1127.00 -6.63% BenchmarkChanProdConsWork0-4 1913.00 611.00 -68.06% BenchmarkChanProdConsWork0-8 3016.00 949.00 -68.53% BenchmarkChanProdConsWork0-16 4320.00 1154.00 -73.29% BenchmarkChanProdConsWork10 1906.00 1897.00 -0.47% BenchmarkChanProdConsWork10-2 1123.00 1033.00 -8.01% BenchmarkChanProdConsWork10-4 1076.00 571.00 -46.93% BenchmarkChanProdConsWork10-8 2748.00 1096.00 -60.12% BenchmarkChanProdConsWork10-16 4600.00 1105.00 -75.98% BenchmarkChanProdConsWork100 1884.00 1852.00 -1.70% BenchmarkChanProdConsWork100-2 1235.00 1146.00 -7.21% BenchmarkChanProdConsWork100-4 1217.00 619.00 -49.14% BenchmarkChanProdConsWork100-8 1534.00 509.00 -66.82% BenchmarkChanProdConsWork100-16 4126.00 918.00 -77.75% BenchmarkSyscall 34.40 33.30 -3.20% BenchmarkSyscall-2 160.00 121.00 -24.38% BenchmarkSyscall-4 131.00 136.00 +3.82% BenchmarkSyscall-8 139.00 131.00 -5.76% BenchmarkSyscall-16 161.00 168.00 +4.35% BenchmarkSyscallWork 950.00 950.00 +0.00% BenchmarkSyscallWork-2 481.00 480.00 -0.21% BenchmarkSyscallWork-4 268.00 270.00 +0.75% BenchmarkSyscallWork-8 156.00 169.00 +8.33% BenchmarkSyscallWork-16 188.00 184.00 -2.13% BenchmarkSemaSyntNonblock 36.40 35.60 -2.20% BenchmarkSemaSyntNonblock-2 81.40 45.10 -44.59% BenchmarkSemaSyntNonblock-4 126.00 108.00 -14.29% BenchmarkSemaSyntNonblock-8 112.00 112.00 +0.00% BenchmarkSemaSyntNonblock-16 110.00 112.00 +1.82% BenchmarkSemaSyntBlock 35.30 35.30 +0.00% BenchmarkSemaSyntBlock-2 118.00 124.00 +5.08% BenchmarkSemaSyntBlock-4 105.00 108.00 +2.86% BenchmarkSemaSyntBlock-8 101.00 111.00 +9.90% BenchmarkSemaSyntBlock-16 112.00 118.00 +5.36% BenchmarkSemaWorkNonblock 810.00 811.00 +0.12% BenchmarkSemaWorkNonblock-2 476.00 414.00 -13.03% BenchmarkSemaWorkNonblock-4 238.00 228.00 -4.20% BenchmarkSemaWorkNonblock-8 140.00 126.00 -10.00% BenchmarkSemaWorkNonblock-16 117.00 116.00 -0.85% BenchmarkSemaWorkBlock 810.00 811.00 +0.12% BenchmarkSemaWorkBlock-2 454.00 466.00 +2.64% BenchmarkSemaWorkBlock-4 243.00 241.00 -0.82% BenchmarkSemaWorkBlock-8 145.00 137.00 -5.52% BenchmarkSemaWorkBlock-16 132.00 123.00 -6.82% BenchmarkContendedSemaphore 123.00 102.00 -17.07% BenchmarkContendedSemaphore-2 34.80 34.90 +0.29% BenchmarkContendedSemaphore-4 34.70 34.80 +0.29% BenchmarkContendedSemaphore-8 34.70 34.70 +0.00% BenchmarkContendedSemaphore-16 34.80 34.70 -0.29% BenchmarkMutex 26.80 26.00 -2.99% BenchmarkMutex-2 108.00 45.20 -58.15% BenchmarkMutex-4 103.00 127.00 +23.30% BenchmarkMutex-8 109.00 147.00 +34.86% BenchmarkMutex-16 102.00 152.00 +49.02% BenchmarkMutexSlack 27.00 26.90 -0.37% BenchmarkMutexSlack-2 149.00 165.00 +10.74% BenchmarkMutexSlack-4 121.00 209.00 +72.73% BenchmarkMutexSlack-8 101.00 158.00 +56.44% BenchmarkMutexSlack-16 97.00 129.00 +32.99% BenchmarkMutexWork 792.00 794.00 +0.25% BenchmarkMutexWork-2 407.00 409.00 +0.49% BenchmarkMutexWork-4 220.00 209.00 -5.00% BenchmarkMutexWork-8 267.00 160.00 -40.07% BenchmarkMutexWork-16 315.00 300.00 -4.76% BenchmarkMutexWorkSlack 792.00 793.00 +0.13% BenchmarkMutexWorkSlack-2 406.00 404.00 -0.49% BenchmarkMutexWorkSlack-4 225.00 212.00 -5.78% BenchmarkMutexWorkSlack-8 268.00 136.00 -49.25% BenchmarkMutexWorkSlack-16 300.00 300.00 +0.00% BenchmarkRWMutexWrite100 27.10 27.00 -0.37% BenchmarkRWMutexWrite100-2 33.10 40.80 +23.26% BenchmarkRWMutexWrite100-4 113.00 88.10 -22.04% BenchmarkRWMutexWrite100-8 119.00 95.30 -19.92% BenchmarkRWMutexWrite100-16 148.00 109.00 -26.35% BenchmarkRWMutexWrite10 29.60 29.40 -0.68% BenchmarkRWMutexWrite10-2 111.00 61.40 -44.68% BenchmarkRWMutexWrite10-4 270.00 208.00 -22.96% BenchmarkRWMutexWrite10-8 204.00 185.00 -9.31% BenchmarkRWMutexWrite10-16 261.00 190.00 -27.20% BenchmarkRWMutexWorkWrite100 1040.00 1036.00 -0.38% BenchmarkRWMutexWorkWrite100-2 593.00 580.00 -2.19% BenchmarkRWMutexWorkWrite100-4 470.00 365.00 -22.34% BenchmarkRWMutexWorkWrite100-8 468.00 289.00 -38.25% BenchmarkRWMutexWorkWrite100-16 604.00 374.00 -38.08% BenchmarkRWMutexWorkWrite10 951.00 951.00 +0.00% BenchmarkRWMutexWorkWrite10-2 1001.00 928.00 -7.29% BenchmarkRWMutexWorkWrite10-4 1555.00 1006.00 -35.31% BenchmarkRWMutexWorkWrite10-8 2085.00 1171.00 -43.84% BenchmarkRWMutexWorkWrite10-16 2082.00 1614.00 -22.48% R=rsc, iant, msolo, fw, iant CC=golang-dev https://golang.org/cl/4711045
2011-07-29 10:44:06 -06:00
TEXT runtime·close(SB),7,$0-16
MOVL 8(SP), DI
MOVL $3, AX // syscall entry
SYSCALL
RET
TEXT runtime·write(SB),7,$0-24
MOVL 8(SP), DI
MOVQ 16(SP), SI
MOVL 24(SP), DX
MOVL $1, AX // syscall entry
SYSCALL
RET
runtime: improve Linux mutex The implementation is hybrid active/passive spin/blocking mutex. The design minimizes amount of context switches and futex calls. The idea is that all critical sections in runtime are intentially small, so pure blocking mutex behaves badly causing a lot of context switches, thread parking/unparking and kernel calls. Note that some synthetic benchmarks become somewhat slower, that's due to increased contention on other data structures, it should not affect programs that do any real work. On 2 x Intel E5620, 8 HT cores, 2.4GHz benchmark old ns/op new ns/op delta BenchmarkSelectContended 521.00 503.00 -3.45% BenchmarkSelectContended-2 661.00 320.00 -51.59% BenchmarkSelectContended-4 1139.00 629.00 -44.78% BenchmarkSelectContended-8 2870.00 878.00 -69.41% BenchmarkSelectContended-16 5276.00 818.00 -84.50% BenchmarkChanContended 112.00 103.00 -8.04% BenchmarkChanContended-2 631.00 174.00 -72.42% BenchmarkChanContended-4 682.00 272.00 -60.12% BenchmarkChanContended-8 1601.00 520.00 -67.52% BenchmarkChanContended-16 3100.00 372.00 -88.00% BenchmarkChanSync 253.00 239.00 -5.53% BenchmarkChanSync-2 5030.00 4648.00 -7.59% BenchmarkChanSync-4 4826.00 4694.00 -2.74% BenchmarkChanSync-8 4778.00 4713.00 -1.36% BenchmarkChanSync-16 5289.00 4710.00 -10.95% BenchmarkChanProdCons0 273.00 254.00 -6.96% BenchmarkChanProdCons0-2 599.00 400.00 -33.22% BenchmarkChanProdCons0-4 1168.00 659.00 -43.58% BenchmarkChanProdCons0-8 2831.00 1057.00 -62.66% BenchmarkChanProdCons0-16 4197.00 1037.00 -75.29% BenchmarkChanProdCons10 150.00 140.00 -6.67% BenchmarkChanProdCons10-2 607.00 268.00 -55.85% BenchmarkChanProdCons10-4 1137.00 404.00 -64.47% BenchmarkChanProdCons10-8 2115.00 828.00 -60.85% BenchmarkChanProdCons10-16 4283.00 855.00 -80.04% BenchmarkChanProdCons100 117.00 110.00 -5.98% BenchmarkChanProdCons100-2 558.00 218.00 -60.93% BenchmarkChanProdCons100-4 722.00 287.00 -60.25% BenchmarkChanProdCons100-8 1840.00 431.00 -76.58% BenchmarkChanProdCons100-16 3394.00 448.00 -86.80% BenchmarkChanProdConsWork0 2014.00 1996.00 -0.89% BenchmarkChanProdConsWork0-2 1207.00 1127.00 -6.63% BenchmarkChanProdConsWork0-4 1913.00 611.00 -68.06% BenchmarkChanProdConsWork0-8 3016.00 949.00 -68.53% BenchmarkChanProdConsWork0-16 4320.00 1154.00 -73.29% BenchmarkChanProdConsWork10 1906.00 1897.00 -0.47% BenchmarkChanProdConsWork10-2 1123.00 1033.00 -8.01% BenchmarkChanProdConsWork10-4 1076.00 571.00 -46.93% BenchmarkChanProdConsWork10-8 2748.00 1096.00 -60.12% BenchmarkChanProdConsWork10-16 4600.00 1105.00 -75.98% BenchmarkChanProdConsWork100 1884.00 1852.00 -1.70% BenchmarkChanProdConsWork100-2 1235.00 1146.00 -7.21% BenchmarkChanProdConsWork100-4 1217.00 619.00 -49.14% BenchmarkChanProdConsWork100-8 1534.00 509.00 -66.82% BenchmarkChanProdConsWork100-16 4126.00 918.00 -77.75% BenchmarkSyscall 34.40 33.30 -3.20% BenchmarkSyscall-2 160.00 121.00 -24.38% BenchmarkSyscall-4 131.00 136.00 +3.82% BenchmarkSyscall-8 139.00 131.00 -5.76% BenchmarkSyscall-16 161.00 168.00 +4.35% BenchmarkSyscallWork 950.00 950.00 +0.00% BenchmarkSyscallWork-2 481.00 480.00 -0.21% BenchmarkSyscallWork-4 268.00 270.00 +0.75% BenchmarkSyscallWork-8 156.00 169.00 +8.33% BenchmarkSyscallWork-16 188.00 184.00 -2.13% BenchmarkSemaSyntNonblock 36.40 35.60 -2.20% BenchmarkSemaSyntNonblock-2 81.40 45.10 -44.59% BenchmarkSemaSyntNonblock-4 126.00 108.00 -14.29% BenchmarkSemaSyntNonblock-8 112.00 112.00 +0.00% BenchmarkSemaSyntNonblock-16 110.00 112.00 +1.82% BenchmarkSemaSyntBlock 35.30 35.30 +0.00% BenchmarkSemaSyntBlock-2 118.00 124.00 +5.08% BenchmarkSemaSyntBlock-4 105.00 108.00 +2.86% BenchmarkSemaSyntBlock-8 101.00 111.00 +9.90% BenchmarkSemaSyntBlock-16 112.00 118.00 +5.36% BenchmarkSemaWorkNonblock 810.00 811.00 +0.12% BenchmarkSemaWorkNonblock-2 476.00 414.00 -13.03% BenchmarkSemaWorkNonblock-4 238.00 228.00 -4.20% BenchmarkSemaWorkNonblock-8 140.00 126.00 -10.00% BenchmarkSemaWorkNonblock-16 117.00 116.00 -0.85% BenchmarkSemaWorkBlock 810.00 811.00 +0.12% BenchmarkSemaWorkBlock-2 454.00 466.00 +2.64% BenchmarkSemaWorkBlock-4 243.00 241.00 -0.82% BenchmarkSemaWorkBlock-8 145.00 137.00 -5.52% BenchmarkSemaWorkBlock-16 132.00 123.00 -6.82% BenchmarkContendedSemaphore 123.00 102.00 -17.07% BenchmarkContendedSemaphore-2 34.80 34.90 +0.29% BenchmarkContendedSemaphore-4 34.70 34.80 +0.29% BenchmarkContendedSemaphore-8 34.70 34.70 +0.00% BenchmarkContendedSemaphore-16 34.80 34.70 -0.29% BenchmarkMutex 26.80 26.00 -2.99% BenchmarkMutex-2 108.00 45.20 -58.15% BenchmarkMutex-4 103.00 127.00 +23.30% BenchmarkMutex-8 109.00 147.00 +34.86% BenchmarkMutex-16 102.00 152.00 +49.02% BenchmarkMutexSlack 27.00 26.90 -0.37% BenchmarkMutexSlack-2 149.00 165.00 +10.74% BenchmarkMutexSlack-4 121.00 209.00 +72.73% BenchmarkMutexSlack-8 101.00 158.00 +56.44% BenchmarkMutexSlack-16 97.00 129.00 +32.99% BenchmarkMutexWork 792.00 794.00 +0.25% BenchmarkMutexWork-2 407.00 409.00 +0.49% BenchmarkMutexWork-4 220.00 209.00 -5.00% BenchmarkMutexWork-8 267.00 160.00 -40.07% BenchmarkMutexWork-16 315.00 300.00 -4.76% BenchmarkMutexWorkSlack 792.00 793.00 +0.13% BenchmarkMutexWorkSlack-2 406.00 404.00 -0.49% BenchmarkMutexWorkSlack-4 225.00 212.00 -5.78% BenchmarkMutexWorkSlack-8 268.00 136.00 -49.25% BenchmarkMutexWorkSlack-16 300.00 300.00 +0.00% BenchmarkRWMutexWrite100 27.10 27.00 -0.37% BenchmarkRWMutexWrite100-2 33.10 40.80 +23.26% BenchmarkRWMutexWrite100-4 113.00 88.10 -22.04% BenchmarkRWMutexWrite100-8 119.00 95.30 -19.92% BenchmarkRWMutexWrite100-16 148.00 109.00 -26.35% BenchmarkRWMutexWrite10 29.60 29.40 -0.68% BenchmarkRWMutexWrite10-2 111.00 61.40 -44.68% BenchmarkRWMutexWrite10-4 270.00 208.00 -22.96% BenchmarkRWMutexWrite10-8 204.00 185.00 -9.31% BenchmarkRWMutexWrite10-16 261.00 190.00 -27.20% BenchmarkRWMutexWorkWrite100 1040.00 1036.00 -0.38% BenchmarkRWMutexWorkWrite100-2 593.00 580.00 -2.19% BenchmarkRWMutexWorkWrite100-4 470.00 365.00 -22.34% BenchmarkRWMutexWorkWrite100-8 468.00 289.00 -38.25% BenchmarkRWMutexWorkWrite100-16 604.00 374.00 -38.08% BenchmarkRWMutexWorkWrite10 951.00 951.00 +0.00% BenchmarkRWMutexWorkWrite10-2 1001.00 928.00 -7.29% BenchmarkRWMutexWorkWrite10-4 1555.00 1006.00 -35.31% BenchmarkRWMutexWorkWrite10-8 2085.00 1171.00 -43.84% BenchmarkRWMutexWorkWrite10-16 2082.00 1614.00 -22.48% R=rsc, iant, msolo, fw, iant CC=golang-dev https://golang.org/cl/4711045
2011-07-29 10:44:06 -06:00
TEXT runtime·read(SB),7,$0-24
MOVL 8(SP), DI
MOVQ 16(SP), SI
MOVL 24(SP), DX
MOVL $0, AX // syscall entry
SYSCALL
RET
TEXT runtime·getrlimit(SB),7,$0-24
MOVL 8(SP), DI
MOVQ 16(SP), SI
MOVL $97, AX // syscall entry
SYSCALL
RET
TEXT runtime·usleep(SB),7,$16
MOVL $0, DX
MOVL usec+0(FP), AX
MOVL $1000000, CX
DIVL CX
MOVQ AX, 0(SP)
MOVQ DX, 8(SP)
// select(0, 0, 0, 0, &tv)
MOVL $0, DI
MOVL $0, SI
MOVL $0, DX
MOVL $0, R10
MOVQ SP, R8
MOVL $23, AX
SYSCALL
RET
TEXT runtime·raise(SB),7,$12
MOVL $186, AX // syscall - gettid
SYSCALL
MOVL AX, DI // arg 1 tid
MOVL sig+0(FP), SI // arg 2
MOVL $200, AX // syscall - tkill
SYSCALL
RET
TEXT runtime·setitimer(SB),7,$0-24
MOVL 8(SP), DI
MOVQ 16(SP), SI
MOVQ 24(SP), DX
MOVL $38, AX // syscall entry
SYSCALL
RET
TEXT runtime·mincore(SB),7,$0-24
MOVQ 8(SP), DI
MOVQ 16(SP), SI
MOVQ 24(SP), DX
MOVL $27, AX // syscall entry
SYSCALL
RET
// func now() (sec int64, nsec int32)
TEXT time·now(SB),7,$16
// Be careful. We're calling a function with gcc calling convention here.
// We're guaranteed 128 bytes on entry, and we've taken 16, and the
// call uses another 8.
// That leaves 104 for the gettime code to use. Hope that's enough!
MOVQ runtime·__vdso_clock_gettime_sym(SB), AX
CMPQ AX, $0
JEQ fallback_gtod
MOVL $0, DI // CLOCK_REALTIME
LEAQ 0(SP), SI
CALL AX
MOVQ 0(SP), AX // sec
MOVQ 8(SP), DX // nsec
MOVQ AX, sec+0(FP)
MOVL DX, nsec+8(FP)
RET
fallback_gtod:
LEAQ 0(SP), DI
MOVQ $0, SI
MOVQ runtime·__vdso_gettimeofday_sym(SB), AX
CALL AX
MOVQ 0(SP), AX // sec
MOVL 8(SP), DX // usec
IMULQ $1000, DX
MOVQ AX, sec+0(FP)
MOVL DX, nsec+8(FP)
RET
TEXT runtime·nanotime(SB),7,$16
// Duplicate time.now here to avoid using up precious stack space.
// See comment above in time.now.
MOVQ runtime·__vdso_clock_gettime_sym(SB), AX
CMPQ AX, $0
JEQ fallback_gtod_nt
MOVL $0, DI // CLOCK_REALTIME
LEAQ 0(SP), SI
CALL AX
MOVQ 0(SP), AX // sec
MOVQ 8(SP), DX // nsec
// sec is in AX, nsec in DX
// return nsec in AX
IMULQ $1000000000, AX
ADDQ DX, AX
RET
fallback_gtod_nt:
LEAQ 0(SP), DI
MOVQ $0, SI
MOVQ runtime·__vdso_gettimeofday_sym(SB), AX
CALL AX
MOVQ 0(SP), AX // sec
MOVL 8(SP), DX // usec
IMULQ $1000, DX
// sec is in AX, nsec in DX
// return nsec in AX
IMULQ $1000000000, AX
ADDQ DX, AX
RET
TEXT runtime·rtsigprocmask(SB),7,$0-32
MOVL 8(SP), DI
MOVQ 16(SP), SI
MOVQ 24(SP), DX
MOVL 32(SP), R10
MOVL $14, AX // syscall entry
SYSCALL
CMPQ AX, $0xfffffffffffff001
JLS 2(PC)
MOVL $0xf1, 0xf1 // crash
RET
TEXT runtime·rt_sigaction(SB),7,$0-32
MOVL 8(SP), DI
MOVQ 16(SP), SI
MOVQ 24(SP), DX
MOVQ 32(SP), R10
MOVL $13, AX // syscall entry
SYSCALL
RET
TEXT runtime·sigtramp(SB),7,$64
get_tls(BX)
// check that m exists
MOVQ m(BX), BP
CMPQ BP, $0
JNE 5(PC)
runtime: discard SIGPROF delivered to non-Go threads. Signal handlers are global resources but many language environments (Go, C++ at Google, etc) assume they have sole ownership of a particular handler. Signal handlers in mixed-language applications must therefore be robust against unexpected delivery of certain signals, such as SIGPROF. The default Go signal handler runtime·sigtramp assumes that it will never be called on a non-Go thread, but this assumption is violated by when linking in C++ code that spawns threads. Specifically, the handler asserts the thread has an associated "m" (Go scheduler). This CL is a very simple workaround: discard SIGPROF delivered to non-Go threads. runtime.badsignal(int32) now receives the signal number; if it returns without panicking (e.g. sig==SIGPROF) the signal is discarded. I don't think there is any really satisfactory solution to the problem of signal-based profiling in a mixed-language application. It's not only the issue of handler clobbering, but also that a C++ SIGPROF handler called in a Go thread can't unwind the Go stack (and vice versa). The best we can hope for is not crashing. Note: - I've ported this to all POSIX platforms, except ARM-linux which already ignores unexpected signals on m-less threads. - I've avoided tail-calling runtime.badsignal because AFAICT the 6a/6l don't support it. - I've avoided hoisting 'push sig' (common to both function calls) because it makes the code harder to read. - Fixed an (apparently incorrect?) docstring. R=iant, rsc, minux.ma CC=golang-dev https://golang.org/cl/6498057
2012-09-04 12:40:49 -06:00
MOVQ DI, 0(SP)
MOVQ $runtime·badsignal(SB), AX
CALL AX
runtime: discard SIGPROF delivered to non-Go threads. Signal handlers are global resources but many language environments (Go, C++ at Google, etc) assume they have sole ownership of a particular handler. Signal handlers in mixed-language applications must therefore be robust against unexpected delivery of certain signals, such as SIGPROF. The default Go signal handler runtime·sigtramp assumes that it will never be called on a non-Go thread, but this assumption is violated by when linking in C++ code that spawns threads. Specifically, the handler asserts the thread has an associated "m" (Go scheduler). This CL is a very simple workaround: discard SIGPROF delivered to non-Go threads. runtime.badsignal(int32) now receives the signal number; if it returns without panicking (e.g. sig==SIGPROF) the signal is discarded. I don't think there is any really satisfactory solution to the problem of signal-based profiling in a mixed-language application. It's not only the issue of handler clobbering, but also that a C++ SIGPROF handler called in a Go thread can't unwind the Go stack (and vice versa). The best we can hope for is not crashing. Note: - I've ported this to all POSIX platforms, except ARM-linux which already ignores unexpected signals on m-less threads. - I've avoided tail-calling runtime.badsignal because AFAICT the 6a/6l don't support it. - I've avoided hoisting 'push sig' (common to both function calls) because it makes the code harder to read. - Fixed an (apparently incorrect?) docstring. R=iant, rsc, minux.ma CC=golang-dev https://golang.org/cl/6498057
2012-09-04 12:40:49 -06:00
RET
// save g
MOVQ g(BX), R10
MOVQ R10, 40(SP)
// g = m->gsignal
MOVQ m_gsignal(BP), BP
MOVQ BP, g(BX)
MOVQ DI, 0(SP)
MOVQ SI, 8(SP)
MOVQ DX, 16(SP)
MOVQ R10, 24(SP)
CALL runtime·sighandler(SB)
// restore g
get_tls(BX)
MOVQ 40(SP), R10
MOVQ R10, g(BX)
RET
TEXT runtime·sigreturn(SB),7,$0
MOVL $15, AX // rt_sigreturn
SYSCALL
INT $3 // not reached
TEXT runtime·mmap(SB),7,$0
MOVQ 8(SP), DI
MOVQ $0, SI
MOVQ 16(SP), SI
MOVL 24(SP), DX
MOVL 28(SP), R10
MOVL 32(SP), R8
MOVL 36(SP), R9
MOVL $9, AX // mmap
SYSCALL
CMPQ AX, $0xfffffffffffff001
JLS 3(PC)
NOTQ AX
INCQ AX
RET
TEXT runtime·munmap(SB),7,$0
MOVQ 8(SP), DI
MOVQ 16(SP), SI
MOVQ $11, AX // munmap
SYSCALL
CMPQ AX, $0xfffffffffffff001
JLS 2(PC)
MOVL $0xf1, 0xf1 // crash
RET
TEXT runtime·madvise(SB),7,$0
MOVQ 8(SP), DI
MOVQ 16(SP), SI
MOVQ 24(SP), DX
MOVQ $28, AX // madvise
SYSCALL
// ignore failure - maybe pages are locked
RET
// int64 futex(int32 *uaddr, int32 op, int32 val,
// struct timespec *timeout, int32 *uaddr2, int32 val2);
TEXT runtime·futex(SB),7,$0
MOVQ 8(SP), DI
MOVL 16(SP), SI
MOVL 20(SP), DX
MOVQ 24(SP), R10
MOVQ 32(SP), R8
MOVL 40(SP), R9
MOVL $202, AX
SYSCALL
RET
// int64 clone(int32 flags, void *stack, M *mp, G *gp, void (*fn)(void));
TEXT runtime·clone(SB),7,$0
MOVL flags+8(SP), DI
MOVQ stack+16(SP), SI
// Copy mp, gp, fn off parent stack for use by child.
// Careful: Linux system call clobbers CX and R11.
MOVQ mm+24(SP), R8
MOVQ gg+32(SP), R9
MOVQ fn+40(SP), R12
MOVL $56, AX
SYSCALL
// In parent, return.
CMPQ AX, $0
JEQ 2(PC)
RET
// In child, on new stack.
MOVQ SI, SP
// Initialize m->procid to Linux tid
MOVL $186, AX // gettid
SYSCALL
MOVQ AX, m_procid(R8)
// Set FS to point at m->tls.
LEAQ m_tls(R8), DI
CALL runtime·settls(SB)
// In child, set up new stack
get_tls(CX)
MOVQ R8, m(CX)
MOVQ R9, g(CX)
CALL runtime·stackcheck(SB)
// Call fn
CALL R12
// It shouldn't return. If it does, exit
MOVL $111, DI
MOVL $60, AX
SYSCALL
JMP -3(PC) // keep exiting
TEXT runtime·sigaltstack(SB),7,$-8
MOVQ new+8(SP), DI
MOVQ old+16(SP), SI
MOVQ $131, AX
SYSCALL
CMPQ AX, $0xfffffffffffff001
JLS 2(PC)
MOVL $0xf1, 0xf1 // crash
RET
// set tls base to DI
TEXT runtime·settls(SB),7,$32
ADDQ $16, DI // ELF wants to use -16(FS), -8(FS)
MOVQ DI, SI
MOVQ $0x1002, DI // ARCH_SET_FS
MOVQ $158, AX // arch_prctl
SYSCALL
CMPQ AX, $0xfffffffffffff001
JLS 2(PC)
MOVL $0xf1, 0xf1 // crash
RET
runtime: improve Linux mutex The implementation is hybrid active/passive spin/blocking mutex. The design minimizes amount of context switches and futex calls. The idea is that all critical sections in runtime are intentially small, so pure blocking mutex behaves badly causing a lot of context switches, thread parking/unparking and kernel calls. Note that some synthetic benchmarks become somewhat slower, that's due to increased contention on other data structures, it should not affect programs that do any real work. On 2 x Intel E5620, 8 HT cores, 2.4GHz benchmark old ns/op new ns/op delta BenchmarkSelectContended 521.00 503.00 -3.45% BenchmarkSelectContended-2 661.00 320.00 -51.59% BenchmarkSelectContended-4 1139.00 629.00 -44.78% BenchmarkSelectContended-8 2870.00 878.00 -69.41% BenchmarkSelectContended-16 5276.00 818.00 -84.50% BenchmarkChanContended 112.00 103.00 -8.04% BenchmarkChanContended-2 631.00 174.00 -72.42% BenchmarkChanContended-4 682.00 272.00 -60.12% BenchmarkChanContended-8 1601.00 520.00 -67.52% BenchmarkChanContended-16 3100.00 372.00 -88.00% BenchmarkChanSync 253.00 239.00 -5.53% BenchmarkChanSync-2 5030.00 4648.00 -7.59% BenchmarkChanSync-4 4826.00 4694.00 -2.74% BenchmarkChanSync-8 4778.00 4713.00 -1.36% BenchmarkChanSync-16 5289.00 4710.00 -10.95% BenchmarkChanProdCons0 273.00 254.00 -6.96% BenchmarkChanProdCons0-2 599.00 400.00 -33.22% BenchmarkChanProdCons0-4 1168.00 659.00 -43.58% BenchmarkChanProdCons0-8 2831.00 1057.00 -62.66% BenchmarkChanProdCons0-16 4197.00 1037.00 -75.29% BenchmarkChanProdCons10 150.00 140.00 -6.67% BenchmarkChanProdCons10-2 607.00 268.00 -55.85% BenchmarkChanProdCons10-4 1137.00 404.00 -64.47% BenchmarkChanProdCons10-8 2115.00 828.00 -60.85% BenchmarkChanProdCons10-16 4283.00 855.00 -80.04% BenchmarkChanProdCons100 117.00 110.00 -5.98% BenchmarkChanProdCons100-2 558.00 218.00 -60.93% BenchmarkChanProdCons100-4 722.00 287.00 -60.25% BenchmarkChanProdCons100-8 1840.00 431.00 -76.58% BenchmarkChanProdCons100-16 3394.00 448.00 -86.80% BenchmarkChanProdConsWork0 2014.00 1996.00 -0.89% BenchmarkChanProdConsWork0-2 1207.00 1127.00 -6.63% BenchmarkChanProdConsWork0-4 1913.00 611.00 -68.06% BenchmarkChanProdConsWork0-8 3016.00 949.00 -68.53% BenchmarkChanProdConsWork0-16 4320.00 1154.00 -73.29% BenchmarkChanProdConsWork10 1906.00 1897.00 -0.47% BenchmarkChanProdConsWork10-2 1123.00 1033.00 -8.01% BenchmarkChanProdConsWork10-4 1076.00 571.00 -46.93% BenchmarkChanProdConsWork10-8 2748.00 1096.00 -60.12% BenchmarkChanProdConsWork10-16 4600.00 1105.00 -75.98% BenchmarkChanProdConsWork100 1884.00 1852.00 -1.70% BenchmarkChanProdConsWork100-2 1235.00 1146.00 -7.21% BenchmarkChanProdConsWork100-4 1217.00 619.00 -49.14% BenchmarkChanProdConsWork100-8 1534.00 509.00 -66.82% BenchmarkChanProdConsWork100-16 4126.00 918.00 -77.75% BenchmarkSyscall 34.40 33.30 -3.20% BenchmarkSyscall-2 160.00 121.00 -24.38% BenchmarkSyscall-4 131.00 136.00 +3.82% BenchmarkSyscall-8 139.00 131.00 -5.76% BenchmarkSyscall-16 161.00 168.00 +4.35% BenchmarkSyscallWork 950.00 950.00 +0.00% BenchmarkSyscallWork-2 481.00 480.00 -0.21% BenchmarkSyscallWork-4 268.00 270.00 +0.75% BenchmarkSyscallWork-8 156.00 169.00 +8.33% BenchmarkSyscallWork-16 188.00 184.00 -2.13% BenchmarkSemaSyntNonblock 36.40 35.60 -2.20% BenchmarkSemaSyntNonblock-2 81.40 45.10 -44.59% BenchmarkSemaSyntNonblock-4 126.00 108.00 -14.29% BenchmarkSemaSyntNonblock-8 112.00 112.00 +0.00% BenchmarkSemaSyntNonblock-16 110.00 112.00 +1.82% BenchmarkSemaSyntBlock 35.30 35.30 +0.00% BenchmarkSemaSyntBlock-2 118.00 124.00 +5.08% BenchmarkSemaSyntBlock-4 105.00 108.00 +2.86% BenchmarkSemaSyntBlock-8 101.00 111.00 +9.90% BenchmarkSemaSyntBlock-16 112.00 118.00 +5.36% BenchmarkSemaWorkNonblock 810.00 811.00 +0.12% BenchmarkSemaWorkNonblock-2 476.00 414.00 -13.03% BenchmarkSemaWorkNonblock-4 238.00 228.00 -4.20% BenchmarkSemaWorkNonblock-8 140.00 126.00 -10.00% BenchmarkSemaWorkNonblock-16 117.00 116.00 -0.85% BenchmarkSemaWorkBlock 810.00 811.00 +0.12% BenchmarkSemaWorkBlock-2 454.00 466.00 +2.64% BenchmarkSemaWorkBlock-4 243.00 241.00 -0.82% BenchmarkSemaWorkBlock-8 145.00 137.00 -5.52% BenchmarkSemaWorkBlock-16 132.00 123.00 -6.82% BenchmarkContendedSemaphore 123.00 102.00 -17.07% BenchmarkContendedSemaphore-2 34.80 34.90 +0.29% BenchmarkContendedSemaphore-4 34.70 34.80 +0.29% BenchmarkContendedSemaphore-8 34.70 34.70 +0.00% BenchmarkContendedSemaphore-16 34.80 34.70 -0.29% BenchmarkMutex 26.80 26.00 -2.99% BenchmarkMutex-2 108.00 45.20 -58.15% BenchmarkMutex-4 103.00 127.00 +23.30% BenchmarkMutex-8 109.00 147.00 +34.86% BenchmarkMutex-16 102.00 152.00 +49.02% BenchmarkMutexSlack 27.00 26.90 -0.37% BenchmarkMutexSlack-2 149.00 165.00 +10.74% BenchmarkMutexSlack-4 121.00 209.00 +72.73% BenchmarkMutexSlack-8 101.00 158.00 +56.44% BenchmarkMutexSlack-16 97.00 129.00 +32.99% BenchmarkMutexWork 792.00 794.00 +0.25% BenchmarkMutexWork-2 407.00 409.00 +0.49% BenchmarkMutexWork-4 220.00 209.00 -5.00% BenchmarkMutexWork-8 267.00 160.00 -40.07% BenchmarkMutexWork-16 315.00 300.00 -4.76% BenchmarkMutexWorkSlack 792.00 793.00 +0.13% BenchmarkMutexWorkSlack-2 406.00 404.00 -0.49% BenchmarkMutexWorkSlack-4 225.00 212.00 -5.78% BenchmarkMutexWorkSlack-8 268.00 136.00 -49.25% BenchmarkMutexWorkSlack-16 300.00 300.00 +0.00% BenchmarkRWMutexWrite100 27.10 27.00 -0.37% BenchmarkRWMutexWrite100-2 33.10 40.80 +23.26% BenchmarkRWMutexWrite100-4 113.00 88.10 -22.04% BenchmarkRWMutexWrite100-8 119.00 95.30 -19.92% BenchmarkRWMutexWrite100-16 148.00 109.00 -26.35% BenchmarkRWMutexWrite10 29.60 29.40 -0.68% BenchmarkRWMutexWrite10-2 111.00 61.40 -44.68% BenchmarkRWMutexWrite10-4 270.00 208.00 -22.96% BenchmarkRWMutexWrite10-8 204.00 185.00 -9.31% BenchmarkRWMutexWrite10-16 261.00 190.00 -27.20% BenchmarkRWMutexWorkWrite100 1040.00 1036.00 -0.38% BenchmarkRWMutexWorkWrite100-2 593.00 580.00 -2.19% BenchmarkRWMutexWorkWrite100-4 470.00 365.00 -22.34% BenchmarkRWMutexWorkWrite100-8 468.00 289.00 -38.25% BenchmarkRWMutexWorkWrite100-16 604.00 374.00 -38.08% BenchmarkRWMutexWorkWrite10 951.00 951.00 +0.00% BenchmarkRWMutexWorkWrite10-2 1001.00 928.00 -7.29% BenchmarkRWMutexWorkWrite10-4 1555.00 1006.00 -35.31% BenchmarkRWMutexWorkWrite10-8 2085.00 1171.00 -43.84% BenchmarkRWMutexWorkWrite10-16 2082.00 1614.00 -22.48% R=rsc, iant, msolo, fw, iant CC=golang-dev https://golang.org/cl/4711045
2011-07-29 10:44:06 -06:00
TEXT runtime·osyield(SB),7,$0
MOVL $24, AX
SYSCALL
RET
TEXT runtime·sched_getaffinity(SB),7,$0
MOVQ 8(SP), DI
MOVL 16(SP), SI
MOVQ 24(SP), DX
MOVL $204, AX // syscall entry
SYSCALL
RET
runtime: integrated network poller for linux vs tip: BenchmarkTCP4OneShot 172994 40485 -76.60% BenchmarkTCP4OneShot-2 96581 30028 -68.91% BenchmarkTCP4OneShot-4 52615 18454 -64.93% BenchmarkTCP4OneShot-8 26351 12289 -53.36% BenchmarkTCP4OneShot-16 12258 16093 +31.29% BenchmarkTCP4OneShot-32 13200 17045 +29.13% BenchmarkTCP4OneShotTimeout 124814 42932 -65.60% BenchmarkTCP4OneShotTimeout-2 99090 29040 -70.69% BenchmarkTCP4OneShotTimeout-4 51860 18455 -64.41% BenchmarkTCP4OneShotTimeout-8 26100 12073 -53.74% BenchmarkTCP4OneShotTimeout-16 12198 16654 +36.53% BenchmarkTCP4OneShotTimeout-32 13438 17143 +27.57% BenchmarkTCP4Persistent 115647 7782 -93.27% BenchmarkTCP4Persistent-2 58024 4808 -91.71% BenchmarkTCP4Persistent-4 24715 3674 -85.13% BenchmarkTCP4Persistent-8 16431 2407 -85.35% BenchmarkTCP4Persistent-16 2336 1875 -19.73% BenchmarkTCP4Persistent-32 1689 1637 -3.08% BenchmarkTCP4PersistentTimeout 79754 7859 -90.15% BenchmarkTCP4PersistentTimeout-2 57708 5952 -89.69% BenchmarkTCP4PersistentTimeout-4 26907 3823 -85.79% BenchmarkTCP4PersistentTimeout-8 15036 2567 -82.93% BenchmarkTCP4PersistentTimeout-16 2507 1903 -24.09% BenchmarkTCP4PersistentTimeout-32 1717 1627 -5.24% vs old scheduler: benchmark old ns/op new ns/op delta BenchmarkTCPOneShot 192244 40485 -78.94% BenchmarkTCPOneShot-2 63835 30028 -52.96% BenchmarkTCPOneShot-4 35443 18454 -47.93% BenchmarkTCPOneShot-8 22140 12289 -44.49% BenchmarkTCPOneShot-16 16930 16093 -4.94% BenchmarkTCPOneShot-32 16719 17045 +1.95% BenchmarkTCPOneShotTimeout 190495 42932 -77.46% BenchmarkTCPOneShotTimeout-2 64828 29040 -55.20% BenchmarkTCPOneShotTimeout-4 34591 18455 -46.65% BenchmarkTCPOneShotTimeout-8 21989 12073 -45.10% BenchmarkTCPOneShotTimeout-16 16848 16654 -1.15% BenchmarkTCPOneShotTimeout-32 16796 17143 +2.07% BenchmarkTCPPersistent 81670 7782 -90.47% BenchmarkTCPPersistent-2 26598 4808 -81.92% BenchmarkTCPPersistent-4 15633 3674 -76.50% BenchmarkTCPPersistent-8 18093 2407 -86.70% BenchmarkTCPPersistent-16 17472 1875 -89.27% BenchmarkTCPPersistent-32 7679 1637 -78.68% BenchmarkTCPPersistentTimeout 83186 7859 -90.55% BenchmarkTCPPersistentTimeout-2 26883 5952 -77.86% BenchmarkTCPPersistentTimeout-4 15776 3823 -75.77% BenchmarkTCPPersistentTimeout-8 18180 2567 -85.88% BenchmarkTCPPersistentTimeout-16 17454 1903 -89.10% BenchmarkTCPPersistentTimeout-32 7798 1627 -79.14% R=golang-dev, iant, bradfitz, dave, rsc CC=golang-dev https://golang.org/cl/7579044
2013-03-14 09:06:35 -06:00
// int32 runtime·epollcreate(int32 size);
TEXT runtime·epollcreate(SB),7,$0
MOVL 8(SP), DI
MOVL $213, AX // syscall entry
SYSCALL
RET
// int32 runtime·epollcreate1(int32 flags);
TEXT runtime·epollcreate1(SB),7,$0
MOVL 8(SP), DI
MOVL $291, AX // syscall entry
SYSCALL
RET
// int32 runtime·epollctl(int32 epfd, int32 op, int32 fd, EpollEvent *ev);
TEXT runtime·epollctl(SB),7,$0
MOVL 8(SP), DI
MOVL 12(SP), SI
MOVL 16(SP), DX
MOVQ 24(SP), R10
MOVL $233, AX // syscall entry
SYSCALL
RET
// int32 runtime·epollwait(int32 epfd, EpollEvent *ev, int32 nev, int32 timeout);
TEXT runtime·epollwait(SB),7,$0
MOVL 8(SP), DI
MOVQ 16(SP), SI
MOVL 24(SP), DX
MOVL 28(SP), R10
MOVL $232, AX // syscall entry
SYSCALL
RET
// void runtime·closeonexec(int32 fd);
TEXT runtime·closeonexec(SB),7,$0
MOVL 8(SP), DI // fd
MOVQ $2, SI // F_SETFD
MOVQ $1, DX // FD_CLOEXEC
MOVL $72, AX // fcntl
SYSCALL
RET