src/runtime/netpoll_epoll.go

// Copyright 2013 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.

//go:build linux

package runtime

import (
	"internal/runtime/atomic"
	"internal/runtime/syscall/linux"
	"unsafe"
)

var (
	epfd           int32         = -1 // epoll descriptor
	netpollEventFd uintptr            // eventfd for netpollBreak
	netpollWakeSig atomic.Uint32      // used to avoid duplicate calls of netpollBreak
)

// netpollPackData stores pd and its fdseq in the epoll data field of ev as
// a taggedPointer. A nil pd marks the netpollBreak eventfd: netpollopen always
// registers a non-nil *pollDesc, so netpollUnpackData can tell the two apart
// by the pointer alone, on any word size or endianness.
func netpollPackData(ev *linux.EpollEvent, pd *pollDesc, fdseq uintptr) {
	*(*taggedPointer)(unsafe.Pointer(&ev.Data)) = taggedPointerPack(unsafe.Pointer(pd), fdseq)
}

// netpollUnpackData returns the pollDesc and fdseq stored by netpollPackData.
// pd is nil for the netpollBreak eventfd.
func netpollUnpackData(ev *linux.EpollEvent) (pd *pollDesc, fdseq uintptr) {
	tp := *(*taggedPointer)(unsafe.Pointer(&ev.Data))
	return (*pollDesc)(tp.pointer()), tp.tag()
}

func netpollinit() {
	var errno uintptr
	epfd, errno = linux.EpollCreate1(linux.EPOLL_CLOEXEC)
	if errno != 0 {
		println("runtime: epollcreate failed with", errno)
		throw("runtime: netpollinit failed")
	}
	efd, errno := linux.Eventfd(0, linux.EFD_CLOEXEC|linux.EFD_NONBLOCK)
	if errno != 0 {
		println("runtime: eventfd failed with", errno)
		throw("runtime: eventfd failed")
	}
	ev := linux.EpollEvent{
		Events: linux.EPOLLIN,
	}
	netpollPackData(&ev, nil, 0)
	errno = linux.EpollCtl(epfd, linux.EPOLL_CTL_ADD, efd, &ev)
	if errno != 0 {
		println("runtime: epollctl failed with", errno)
		throw("runtime: epollctl failed")
	}
	netpollEventFd = uintptr(efd)
}

func netpollIsPollDescriptor(fd uintptr) bool {
	return fd == uintptr(epfd) || fd == netpollEventFd
}

func netpollopen(fd uintptr, pd *pollDesc) uintptr {
	var ev linux.EpollEvent
	ev.Events = linux.EPOLLIN | linux.EPOLLOUT | linux.EPOLLRDHUP | linux.EPOLLET
	netpollPackData(&ev, pd, pd.fdseq.Load())
	return linux.EpollCtl(epfd, linux.EPOLL_CTL_ADD, int32(fd), &ev)
}

func netpollclose(fd uintptr) uintptr {
	var ev linux.EpollEvent
	return linux.EpollCtl(epfd, linux.EPOLL_CTL_DEL, int32(fd), &ev)
}

func netpollarm(pd *pollDesc, mode int) {
	throw("runtime: unused")
}

// netpollBreak interrupts an epollwait.
func netpollBreak() {
	// Failing to cas indicates there is an in-flight wakeup, so we're done here.
	if !netpollWakeSig.CompareAndSwap(0, 1) {
		return
	}

	var one uint64 = 1
	oneSize := int32(unsafe.Sizeof(one))
	for {
		n := write(netpollEventFd, noescape(unsafe.Pointer(&one)), oneSize)
		if n == oneSize {
			break
		}
		if n == -_EINTR {
			continue
		}
		if n == -_EAGAIN {
			return
		}
		println("runtime: netpollBreak write failed with", -n)
		throw("runtime: netpollBreak write failed")
	}
}

// netpoll checks for ready network connections.
// Returns a list of goroutines that become runnable,
// and a delta to add to netpollWaiters.
// This must never return an empty list with a non-zero delta.
//
// delay < 0: blocks indefinitely
// delay == 0: does not block, just polls
// delay > 0: block for up to that many nanoseconds
func netpoll(delay int64) (gList, int32) {
	if epfd == -1 {
		return gList{}, 0
	}
	var waitms int32
	if delay < 0 {
		waitms = -1
	} else if delay == 0 {
		waitms = 0
	} else if delay < 1e6 {
		waitms = 1
	} else if delay < 1e15 {
		waitms = int32(delay / 1e6)
	} else {
		// An arbitrary cap on how long to wait for a timer.
		// 1e9 ms == ~11.5 days.
		waitms = 1e9
	}
	var events [128]linux.EpollEvent
retry:
	n, errno := linux.EpollWait(epfd, events[:], int32(len(events)), waitms)
	if errno != 0 {
		if errno != _EINTR {
			println("runtime: epollwait on fd", epfd, "failed with", errno)
			throw("runtime: netpoll failed")
		}
		// If a timed sleep was interrupted, just return to
		// recalculate how long we should sleep now.
		if waitms > 0 {
			return gList{}, 0
		}
		goto retry
	}
	var toRun gList
	delta := int32(0)
	for i := int32(0); i < n; i++ {
		ev := events[i]
		if ev.Events == 0 {
			continue
		}

		pd, tag := netpollUnpackData(&ev)
		// pd == nil denotes a netpollBreak eventfd.
		if pd == nil {
			if ev.Events != linux.EPOLLIN {
				println("runtime: netpoll: eventfd ready for", ev.Events)
				throw("runtime: netpoll: eventfd ready for something unexpected")
			}
			if delay != 0 {
				// netpollBreak could be picked up by a
				// nonblocking poll. Only read the 8-byte
				// integer if blocking.
				// Since EFD_SEMAPHORE was not specified,
				// the eventfd counter will be reset to 0.
				var one uint64
				read(int32(netpollEventFd), noescape(unsafe.Pointer(&one)), int32(unsafe.Sizeof(one)))
				netpollWakeSig.Store(0)
			}
			continue
		}

		var mode int32
		if ev.Events&(linux.EPOLLIN|linux.EPOLLRDHUP|linux.EPOLLHUP|linux.EPOLLERR) != 0 {
			mode += 'r'
		}
		if ev.Events&(linux.EPOLLOUT|linux.EPOLLHUP|linux.EPOLLERR) != 0 {
			mode += 'w'
		}
		if mode != 0 {
			if pd.fdseq.Load() == tag {
				pd.setEventErr(ev.Events == linux.EPOLLERR, tag)
				delta += netpollready(&toRun, pd, mode)
			}
		}
	}
	return toRun, delta
}