mirror of
https://github.com/hanzoai/visor.git
synced 2026-09-24 17:04:14 +00:00
Tianyu Zhou
fc1afc9de5
SlimVM is a lightweight VMX-based platform for gVisor that accelerates sentry system calls by eliminating unnecessary user/kernel context switches. In a traditional gVisor + KVM setup, every guest syscall triggers a full VM exit to userspace, then re-enters the kernel via a regular syscall: gr0 -> hr0 (vm_exit) -> hr3 (ioctl return) -> hr0 (re-invoke syscall) SlimVM eliminates this overhead. When the guest executes a VMCALL, the VM exits into VMX root mode where SlimVM directly invokes the host kernel's syscall handler, then immediately resumes the guest: gr0 -> hr0 (vmcall + direct function call) SlimVM requires a companion kernel module that provides the /dev/slimvm device interface. See https://github.com/antgroup/slimvm for the kernel module and full documentation. A sentry->host getpid microbenchmark (Xeon 6982P-C, host kernel 5.10.134) shows the effect: │ ns/op │ vs base │ base 82.5 1.0x slimvm 420.9 5.1x kvm 3566.1 43.2x slimvm is ~8.5x faster than the kvm platform on this path. See the issue for details. Updates: https://github.com/google/gvisor/issues/13330 Co-developed-by: Chenggang <[email protected]> Co-developed-by: Robin Luk <[email protected]> Co-developed-by: Tiwei Bie <[email protected]> Co-developed-by: Jianfeng Tan <[email protected]> Co-developed-by: liushi.ls <[email protected]> Co-developed-by: Yong He <[email protected]> Co-developed-by: Aaron Lu <[email protected]> Co-developed-by: chris.zn <[email protected]> Co-developed-by: Lai Jiangshan <[email protected]> Co-developed-by: Lingfu <[email protected]> Co-developed-by: Min Le <[email protected]> Co-developed-by: Quan Xu <[email protected]> Co-developed-by: Zhang Haoyu <[email protected]> Co-developed-by: Dawei Shen <[email protected]> Signed-off-by: Tianyu Zhou <[email protected]>
105 lines
2.9 KiB
Go
105 lines
2.9 KiB
Go
// Copyright 2026 The gVisor Authors.
|
|
//
|
|
// Licensed under the Apache License, Version 2.0 (the "License");
|
|
// you may not use this file except in compliance with the License.
|
|
// You may obtain a copy of the License at
|
|
//
|
|
// http://www.apache.org/licenses/LICENSE-2.0
|
|
//
|
|
// Unless required by applicable law or agreed to in writing, software
|
|
// distributed under the License is distributed on an "AS IS" BASIS,
|
|
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
// See the License for the specific language governing permissions and
|
|
// limitations under the License.
|
|
|
|
package slimvm
|
|
|
|
import (
|
|
"math"
|
|
"sync/atomic"
|
|
"syscall"
|
|
"unsafe"
|
|
|
|
"golang.org/x/sys/unix"
|
|
"gvisor.dev/gvisor/pkg/abi/linux"
|
|
"gvisor.dev/gvisor/pkg/hostsyscall"
|
|
)
|
|
|
|
//go:linkname entersyscall runtime.entersyscall
|
|
func entersyscall()
|
|
|
|
//go:linkname exitsyscall runtime.exitsyscall
|
|
func exitsyscall()
|
|
|
|
// atomicAddressSpace is an atomic address space pointer.
|
|
type atomicAddressSpace struct {
|
|
pointer unsafe.Pointer
|
|
}
|
|
|
|
// set sets the address space value.
|
|
//
|
|
//go:nosplit
|
|
func (a *atomicAddressSpace) set(as *addressSpace) {
|
|
atomic.StorePointer(&a.pointer, unsafe.Pointer(as))
|
|
}
|
|
|
|
// get gets the address space value.
|
|
//
|
|
// Note that this should be considered best-effort, and may have changed by the
|
|
// time this function returns.
|
|
//
|
|
//go:nosplit
|
|
func (a *atomicAddressSpace) get() *addressSpace {
|
|
return (*addressSpace)(atomic.LoadPointer(&a.pointer))
|
|
}
|
|
|
|
// notify notifies that the vCPU has transitioned modes.
|
|
//
|
|
// This may be called by a signal handler and therefore throws on error.
|
|
//
|
|
//go:nosplit
|
|
func (c *vCPU) notify() {
|
|
errno := hostsyscall.RawSyscallErrno6(
|
|
unix.SYS_FUTEX,
|
|
uintptr(unsafe.Pointer(&c.state)),
|
|
linux.FUTEX_WAKE,
|
|
math.MaxInt32, // Number of waiters.
|
|
0, 0, 0)
|
|
if errno != 0 {
|
|
throw("futex wake error")
|
|
}
|
|
}
|
|
|
|
// waitUntilNot waits for the vCPU to transition modes.
|
|
//
|
|
// The state should have been previously set to vCPUWaiter after performing an
|
|
// appropriate action to cause a transition (e.g. interrupt injection).
|
|
//
|
|
// This panics on error.
|
|
func (c *vCPU) waitUntilNot(state uint32) bool {
|
|
// Check transition mode before to issue a SYS_FUTEX.
|
|
if c.state.Load() != state {
|
|
return false
|
|
}
|
|
ts := linux.Timespec{Sec: 1}
|
|
_, _, errno := syscall.Syscall6(
|
|
syscall.SYS_FUTEX,
|
|
uintptr(unsafe.Pointer(&c.state)),
|
|
linux.FUTEX_WAIT,
|
|
uintptr(state),
|
|
uintptr(unsafe.Pointer(&ts)),
|
|
0, 0)
|
|
if errno != 0 && errno != syscall.EINTR && errno != syscall.EAGAIN && errno != syscall.ETIMEDOUT {
|
|
panic("futex wait error")
|
|
}
|
|
return errno == syscall.ETIMEDOUT
|
|
}
|
|
|
|
// createVCPU create VCPU in slimvm.
|
|
func (c *vCPU) createVCPU(memoryRegions []userMemoryRegion) (uintptr, unix.Errno) {
|
|
c.vmxConfig.memoryRegionNum = uint64(len(memoryRegions))
|
|
c.vmxConfig.memoryRegionAddr = uintptr(unsafe.Pointer(&memoryRegions[0]))
|
|
|
|
return hostsyscall.RawSyscall(unix.SYS_IOCTL, slimvmFD, _SLIMVM_CREATE_VCPU, uintptr(unsafe.Pointer(&c.vmxConfig)))
|
|
}
|