rust-vmm 学习
V0.1.0 feature
base knowledge:
Architecture of the Kernel-based Virtual Machine (KVM)
<Mastering KVM Virtualization>：第二章 KVM内部原理
Using the KVM API (org)
Example for a simple vmm (github, search pub fn test_vm())
kvm-ioctls (github)
run test:
cd vmm
FILE_LINE=`git grep -n "pub fn test_vm"` && echo ${FILE_LINE%:*}
cargo test test_vm
FILE_LINE=`git grep -n "pub fn test_vm"` && echo ${FILE_LINE%:*}
src/vm.rs:854
cargo test test_vm |grep "Running target/debug/deps/"
Finished dev [unoptimized + debuginfo] target(s) in 0.16s
Running target/debug/deps/vmm-5f7f458cb725298f
rust-gdb target/debug/deps/vmm-5f7f458cb725298f
(gdb) info functions test_vm
All functions matching regular expression "test_vm":
(gdb) help info
(gdb) info sources
(gdb) b src/vm.rs:854
No source file named src/vm.rs.
Make breakpoint pending on future shared library load? (y or [n]) n
(gdb) run --test test_vm
# note: Run with `RUST_BACKTRACE=1` environment variable to display a backtrace. RUST_BACKTRACE=1 cargo run vim ./cloud-hypervisor/src/main.rs
:ConqueGdbExe rust-gdb :ConqueGdb target/debug/cloud-hypervisor
(gdb) info functions main
All functions matching regular expression "main":
File cloud-hypervisor/src/main.rs:
static void cloud_hypervisor::main::h9d806d3576285a29(void);
(gdb) b cloud_hypervisor::main::h9d806d3576285a29
(gdb) run --kernel ./hypervisor-fw \ --disk ./clear-29160-kvm.img \ --cpus 4 \ --memory 512 \ --net "tap=,mac=,ip=,mask=" \ --rng (gdb) run target/debug/cloud-hypervisor \ --kernel ./linux-cloud-hypervisor/arch/x86/boot/compressed/vmlinux.bin \ --disk ./clear-29160-kvm.img \ --cmdline "console=ttyS0 reboot=k panic=1 nomodules i8042.noaux i8042.nomux i8042.nopnp i8042.dumbkbd root=/dev/vda3" \ --cpus 4 \ --memory 512 \ --net "tap=,mac=,ip=,mask=" \ --rng
Example: debug a Virtio devices(Rng)
sudo ~/.cargo/bin/rust-gdb cloud-hypervisor/target/debug/cloud-hypervisor
(gdb) i functions Rng::new
File vm-virtio/src/rng.rs:
struct Result<vm_virtio::rng::Rng, std::io::error::Error> vm_virtio::rng::Rng::new::h79792d122294607e(struct &str);
(gdb) b vm_virtio::rng::Rng::new::h79792d122294607e
Breakpoint 1 at 0x6330e4: file vm-virtio/src/rng.rs, line 156.
(gdb) r --kernel ./linux-cloud-hypervisor/arch/x86/boot/compressed/vmlinux.bin \
--disk ./clear-29160-kvm.img \
--cmdline "console=ttyS0 reboot=k panic=1 nomodules i8042.noaux i8042.nomux i8042.nopnp i8042.dumbkbd root=/dev/vda3" \
--cpus 4 \
--memory 512 \
--net "tap=,mac=,ip=,mask=" \
--rng
(gdb) bt
#0 vm_virtio::rng::Rng::new::h79792d122294607e (path="/dev/urandom") at vm-virtio/src/rng.rs:156
#1 0x0000555555ac81fa in vmm::vm::DeviceManager::new::hb95c517461758006 (memory=GuestMemoryMmap = {...}, allocator=0x7fffffff65e0, vm_fd=0x7fffffff59f0,
vm_cfg=0x7fffffff7a18, msi_capable=true, userspace_ioapic=true) at vmm/src/vm.rs:572
#2 0x0000555555acd235 in vmm::vm::Vm::new::h319ad49fd3f83723 (kvm=0x7fffffff731c, config=VmConfig = {...}) at vmm/src/vm.rs:905
#3 0x0000555555aafed1 in vmm::boot_kernel::hc06685bd1a4087c9 (config=VmConfig = {...}) at vmm/src/lib.rs:59
#4 0x00005555556d377b in cloud_hypervisor::main::hc6d3862453504aa4 () at src/main.rs:114
#5 0x00005555556d0110 in std::rt::lang_start::_$u7b$$u7b$closure$u7d$$u7d$::hb71d053f091b9e72 () at /rustc/91856ed52c58aa5ba66a015354d1cc69e9779bdf/src/libstd/rt.rs:64
#6 0x0000555555c36943 in {{closure}} () at src/libstd/rt.rs:49
#7 do_call<closure,i32> () at src/libstd/panicking.rs:297
#8 0x0000555555c3a0ca in __rust_maybe_catch_panic () at src/libpanic_unwind/lib.rs:87
#9 0x0000555555c3744d in try<i32,closure> () at src/libstd/panicking.rs:276
#10 catch_unwind<closure,i32> () at src/libstd/panic.rs:388
#11 lang_start_internal () at src/libstd/rt.rs:48
#12 0x00005555556d00e9 in std::rt::lang_start::hd3791e31e26e1c55 (main=0x5555556d2720 <cloud_hypervisor::main::hc6d3862453504aa4>, argc=14, argv=0x7fffffffe1a8)
at /rustc/91856ed52c58aa5ba66a015354d1cc69e9779bdf/src/libstd/rt.rs:64
#13 0x00005555556d3bca in main ()
(gdb) set print pretty on
(gdb) info functions Rng.*activate
(gdb) info functions Rng.*VirtioDevice.*activate
All functions matching regular expression "Rng.*VirtioDevice.*activate":
File vm-virtio/src/rng.rs:
struct Result<(), vm_virtio::ActivateError> _$LT$vm_virtio..rng..Rng$u20$as$u20$vm_virtio..device..VirtioDevice$GT$::activate::hdedcc2490e8a5155(struct Rng *,
struct GuestMemoryMmap, struct Arc<alloc::boxed::Box<Fn<(&vm_virtio::queue::Queue)>>>, struct Arc<core::sync::atomic::AtomicUsize>,
struct Vec<vm_virtio::queue::Queue>, struct Vec<vmm_sys_util::eventfd::EventFd>);
(gdb) b _$LT$vm_virtio..rng..Rng$u20$as$u20$vm_virtio..device..VirtioDevice$GT$::activate::hdedcc2490e8a5155
(gdb) b vm-virtio/src/rng.rs:236
(gdb) c
Thread 2 "cloud-hyperviso" hit Breakpoint 2, _$LT$vm_virtio..rng..Rng$u20$as$u20$vm_virtio..device..VirtioDevice$GT$::activate::hdedcc2490e8a5155 (self=0x555555f71f10,
mem=GuestMemoryMmap = {...}, interrupt_cb=Arc<alloc::boxed::Box<Fn<(&vm_virtio::queue::Queue)>>> = {...}, status=Arc<core::sync::atomic::AtomicUsize> = {...},
queues=Vec<vm_virtio::queue::Queue>(len: 1, cap: 1) = {...}, queue_evts=Vec<vmm_sys_util::eventfd::EventFd>(len: 1, cap: 1) = {...}) at vm-virtio/src/rng.rs:236
236 if queues.len() != NUM_QUEUES || queue_evts.len() != NUM_QUEUES {
(gdb) bt
#0 _$LT$vm_virtio..rng..Rng$u20$as$u20$vm_virtio..device..VirtioDevice$GT$::activate::hdedcc2490e8a5155 (self=0x555555f71f10, mem=GuestMemoryMmap = {...},
interrupt_cb=Arc<alloc::boxed::Box<Fn<(&vm_virtio::queue::Queue)>>> = {...}, status=Arc<core::sync::atomic::AtomicUsize> = {...},
queues=Vec<vm_virtio::queue::Queue>(len: 1, cap: 1) = {...}, queue_evts=Vec<vmm_sys_util::eventfd::EventFd>(len: 1, cap: 1) = {...}) at vm-virtio/src/rng.rs:236
#1 0x0000555555b84dc5 in _$LT$vm_virtio..transport..pci_device..VirtioPciDevice$u20$as$u20$pci..device..PciDevice$GT$::write_bar::h7ff0b55cec4a3130 (
self=0x555555f72170, offset=20, data=&[u8](len: 1) = {...}) at vm-virtio/src/transport/pci_device.rs:549
#2 0x0000555555b85692 in _$LT$vm_virtio..transport..pci_device..VirtioPciDevice$u20$as$u20$devices..bus..BusDevice$GT$::write::h32bdbeb4a3c402c0 (self=0x555555f72170,
offset=20, data=&[u8](len: 1) = {...}) at vm-virtio/src/transport/pci_device.rs:590
#3 0x0000555555be16ab in devices::bus::Bus::write::h23c30f9081f573b2 (self=0x7fffd6ec2788, addr=68717891604, data=&[u8](len: 1) = {...}) at devices/src/bus.rs:158
#4 0x0000555555ac561b in vmm::vm::Vcpu::run::h523fa30e0aaa7af6 (self=0x7fffd6ec2760) at vmm/src/vm.rs:363
#5 0x0000555555ae8eb3 in vmm::vm::Vm::start::_$u7b$$u7b$closure$u7d$$u7d$::h643431f00d7471fd () at vmm/src/vm.rs:1110
#6 0x0000555555ad9f12 in std::sys_common::backtrace::__rust_begin_short_backtrace::hd688e526ad581234 (f=...)
at /rustc/91856ed52c58aa5ba66a015354d1cc69e9779bdf/src/libstd/sys_common/backtrace.rs:135
#7 0x0000555555ad7931 in std::thread::Builder::spawn_unchecked::_$u7b$$u7b$closure$u7d$$u7d$::_$u7b$$u7b$closure$u7d$$u7d$::h8d7f8a62b8d1257c ()
at /rustc/91856ed52c58aa5ba66a015354d1cc69e9779bdf/src/libstd/thread/mod.rs:469
#8 0x0000555555af14a1 in _$LT$std..panic..AssertUnwindSafe$LT$F$GT$$u20$as$u20$core..ops..function..FnOnce$LT$$LP$$RP$$GT$$GT$::call_once::h1f5925e04de15538 (
self=..., _args=0) at /rustc/91856ed52c58aa5ba66a015354d1cc69e9779bdf/src/libstd/panic.rs:309
#9 0x0000555555b00eda in std::panicking::try::do_call::hebfb4f2c896f9302 (data=0x7fffd6ec2a40 "\020)\367UUU")
at /rustc/91856ed52c58aa5ba66a015354d1cc69e9779bdf/src/libstd/panicking.rs:297
#10 0x0000555555c3a0ca in __rust_maybe_catch_panic () at src/libpanic_unwind/lib.rs:87
#11 0x0000555555b00ca0 in std::panicking::try::h6da33e6171d79492 (f=...) at /rustc/91856ed52c58aa5ba66a015354d1cc69e9779bdf/src/libstd/panicking.rs:276
#12 0x0000555555af15d3 in std::panic::catch_unwind::h1660cc8af66e7984 (f=...) at /rustc/91856ed52c58aa5ba66a015354d1cc69e9779bdf/src/libstd/panic.rs:388
#13 0x0000555555ad7336 in std::thread::Builder::spawn_unchecked::_$u7b$$u7b$closure$u7d$$u7d$::h85cc8e716556c7d2 ()
at /rustc/91856ed52c58aa5ba66a015354d1cc69e9779bdf/src/libstd/thread/mod.rs:468
#14 0x0000555555ad7c7b in _$LT$F$u20$as$u20$alloc..boxed..FnBox$LT$A$GT$$GT$::call_box::h5eac52d3a365b1f5 (self=0x555555f72d70, args=0)
at /rustc/91856ed52c58aa5ba66a015354d1cc69e9779bdf/src/liballoc/boxed.rs:749
#15 0x0000555555c3985e in call_once<(),()> () at /rustc/91856ed52c58aa5ba66a015354d1cc69e9779bdf/src/liballoc/boxed.rs:759
#16 start_thread () at src/libstd/sys_common/thread.rs:14
#17 thread_start () at src/libstd/sys/unix/thread.rs:81
#18 0x00007ffff77b56ba in start_thread (arg=0x7fffd6ec4700) at pthread_create.c:333
#19 0x00007ffff72d541d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:109
set print pretty on
virtio (Github)
virtqueue的每个部分的内存对齐和大小要求如下表，其中Queue Size对应virtqueue中的最大buffer数，始终为2的n次幂，以特定于总线的方式指定：
Driver将sk_buffer填充进scatterlist table中(只是设置地址没有数据搬移)，然后通过计算得到GPA并将GPA写入Descriptor Table中，同时将Desc chain的head记录到Available Ring中，然后通过PIO的方式通知Device，Device发包并更新Used Ring。
VirtIO 代码分析（rust-vmm) cloud-hypervisor Latest commit f9036a1
Test_vm
vmm/src/vm.rs::test_vm是一个很好的入门例程。
VM创建过程:
1. src/main.rs 的main函数， 解析参数，然后boot_kernel (vmm/src/lib.rs).
2. 创建kvm (kvm_ioctls crate, 打开/dev/kvm得到fd),
3. vmm/src/vm.rs 创建Vm,
(kvm.create_vm() 得到vm的fd),
初始化guest的memory,
CPU的Vec，
DeviceManager::new 来创建设备, 各种设备，包括ＰＣＩ设备在此创建。
4. boot_kernel中，先load_kernel， 最后start (创建期望的个数的Vcpu，返回fd, 放在Vec<thread::JoinHandle<()>>中).
创建Ｖcpu时，会传入DeviceManager的各种信息：
io_bus = self.devices.io_bus.clone()
mmio_bus = self.devices.mmio_bus.clone()
ioapic = if let Some(ioapic) = &self.devices.ioapic {Some(ioapic.clone())}
io_bus和mmio_bus都是devices/src/bus.rs::Bus类型 ｛devices: BTreeMap<BusRange, Arc<Mutex<BusDevice>>>｝
然后在每个thread中, vcpu.run (ioctls/vcpu.rs pub fn run).
5. 最后，control_loop 通过epoll从stdin读入数据，发给ＶＭ的serial.
PCI设备创建过程（Rng为例）:
1. vmm/src/vm.rs: DeviceManager会调用Rng::new 生成virtio_rng_device
2. DeviceManager::add_virtio_pci_device将virtio_rng_device 生成一个VirtioPciDevice，并加入到pci_root(PciRoot::new)中
PciConfigIo::new(pci_root)
还会调用PciConfigIo::register_mapping 设置bus, 会将 (address, size), VirtioPciDevice插入到bus 的map中。
3. VirtioPciDevice::new 会设置
PCI configuration registers
virtio PCI common configuration
MSI-X config
PCI interrupts
virtio queues, 会Rng转化为queue，并设置queue_evts（EventFd::new), vm_fd.register_ioevent
Guest memory
Setting PCI BAR
PCI设备访问过程（Rng为例mmio为例）:
１. 每个VCPU线程vmm::vm::Vcpu::run会判断VCPU的退出情况。以MmioWrite为例
2. devices/src/bus.rs::write 会遍历找到对应的device 进行 write_bar
3. 调用device.activate， 即Rng::activate, 会在一个线程中调用RngEpollHandler::run
virtIO相关结构
1. struct Descriptor
/// A virtio descriptor constraints with C representive
struct Descriptor {
addr: u64,
len: u32,
flags: u16,
next: u16,
}
2. pub struct DescriptorChain
/// A virtio descriptor chain. 包含了Descriptor的４个字段
此外还包括申请的mmap,
desc_table的地址
desc table的索引
1 /// A virtio descriptor chain. 2 pub struct DescriptorChain<'a> { 3 mem: &'a GuestMemoryMmap, 4 desc_table: GuestAddress, 5 queue_size: u16, 6 ttl: u16, // used to prevent infinite chain cycles 7 8 /// Index into the descriptor table 9 pub index: u16, 10 11 /// Guest physical address of device specific data 12 pub addr: GuestAddress, 13 14 /// Length of device specific data 15 pub len: u32, 16 17 /// Includes next, write, and indirect bits 18 pub flags: u16, 19 20 /// Index into the descriptor table of the next descriptor if flags has 21 /// the next bit set 22 pub next: u16, 23 }
3. AvailIter
/// Consuming iterator over all available descriptor chain heads in the queue.
1 /// Consuming iterator over all available descriptor chain heads in the queue. 2 pub struct AvailIter<'a, 'b> { 3 mem: &'a GuestMemoryMmap, 4 desc_table: GuestAddress, 5 avail_ring: GuestAddress, 6 next_index: Wrapping<u16>, 7 last_index: Wrapping<u16>, 8 queue_size: u16, 9 next_avail: &'b mut Wrapping<u16>, 10 }
4. Queue
/// A virtio queue's parameters. 包含了desc_table, avail_ring, used_ring 和中断向量的索引。
1 /// A virtio queue's parameters. 2 pub struct Queue { 3 /// The maximal size in elements offered by the device 4 max_size: u16, 5 6 /// The queue size in elements the driver selected 7 pub size: u16, 8 9 /// Inidcates if the queue is finished with configuration 10 pub ready: bool, 11 12 /// Interrupt vector index of the queue 13 pub vector: u16, 14 15 /// Guest physical address of the descriptor table 16 pub desc_table: GuestAddress, 17 18 /// Guest physical address of the available ring 19 pub avail_ring: GuestAddress, 20 21 /// Guest physical address of the used ring 22 pub used_ring: GuestAddress, 23 24 next_avail: Wrapping<u16>, 25 next_used: Wrapping<u16>, 26 }
5. Rng
Rng 是不包括Queue字段的
VirtioPciDevice 的new时候，生成Queue, 还会生成bar的地址fn allocate_bars。
Queue传入的地址就是为VM申请的guest_memory
VirtioPciDevice::read_bar 和 VirtioPciDevice::write_bar （VirtioPciDevice被插入了bus中） 会调用common_config: VirtioPciCommonConfig的write 和read Queue的各个field.
PCI bar地址
1. vm new的时候，会初始化一个allocator = SystemAllocator::new.
2. 这个allocator会传给device_manager = DeviceManager::new .
3. DeviceManager new的时候，在add_virtio_pci_device的时候，会分配bars = virtio_pci_device.allocate_bars
4. 具体由vm-allocator/src/address.rs::AddressAllocator 的 AddressAllocator::allocate分配bar地址
5. SystemAllocator::allocate_mmio_addresses 会 Reserves a section of `size` bytes of MMIO address space.
PCI passtrough代码分析(从5372554开始支持VFIO)
REF:
vfio-mdev逻辑空间分析 (mdev设备也是基于VFIO)
地址空间的故事 （介绍了CCIX）
VFIO driver (VFIO的ORG文档， 内核及用户空间源码，内核 3.6)
VFIO简介 转自developerworks（很多不错的文章）
Cloud Phypervisor的实现
1. 5372554 实现了C语言的vfio-bindings
The default bindings are generated from the 5.0.0 Linux userspace API.
2. 2cec3aa 实现了VFIO API (用户态的调用这些API，操作VFIO, VFIO ——将 DMA 映射暴露给用户态 )
实现了 setup_dma_map， enable_msi, enable_msix, region_read, region_write
VFIO平台无关的接口层
- 向用户态提供访问硬件设备的接口
- 向用户态提供配置IOMMU的接
3. db5b476 实现了VFIO PCI device 的各种操作。VFIO实现层（PCI设备实现层）
allocate bar
write/read config register 会read/write region （write_config_register）
write/read bars 也会read/write region （write_bar）
allocate bar 时会 setup_dma_map
4. 20f0116 实现了MSI和MSI-X的设置
vfio: pci: Track MSI and MSI-X capabilities
5. c93d536 设置中断（需要研究一下原理）
vfio: pci: Build the KVM routes
VFIO实现层（PCI设备实现层）
6. b746dd7
7. 4d16ca8 实现了PCI passthroug (Doc)
vmm: Support direct device assignment
5ae3144 testcase
8. 927861c .. fa41ddd VFIO的bug fix.
REF:
https://wiki.qemu.org/Documentation/vhost-user-ovs-dpdk
linux下共享内存mmap和DMA(直接访问内存)的使用 (mmap 共享内存例子)
详解vhost-user协议及其在OVS DPDK、QEMU和virtio-net驱动中的实现
Vhost-user详解 (详细介绍了地址转换)
client.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <stddef.h>
#include <string.h>
#include <sys/types.h>
#include <errno.h>
#include <sys/un.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <sys/epoll.h>
#include <fcntl.h>
#define UNIXSTR_PATH "foo.socket"
#define OPEN_FILE "test"
int main(int argc, char *argv[])
{
int clifd;
struct sockaddr_un servaddr; //IPC
int ret;
struct msghdr msg;
struct iovec iov[1];
char buf[100];
union { //保证cmsghdr和msg_control对齐
struct cmsghdr cm;
char control[CMSG_SPACE(sizeof(int))];
} control_un;
struct cmsghdr *pcmsg;
int fd;
clifd = socket(AF_UNIX, SOCK_STREAM, 0) ;
if ( clifd < 0 ) {
printf ( "socket failed.\n" ) ;
return - 1 ;
}
fd = open(OPEN_FILE ,O_CREAT | O_RDWR, 0777);
if( fd < 0 ) {
printf("open test failed.\n");
return -1;
}
bzero (&servaddr, sizeof(servaddr));
servaddr.sun_family = AF_UNIX;
strcpy ( servaddr.sun_path, UNIXSTR_PATH);
ret = connect(clifd, (struct sockaddr*)&servaddr, sizeof(servaddr));
if(ret < 0) {
printf ( "connect failed.\n" ) ;
return 0;
}
//udp需要,tcp无视
msg.msg_name = NULL;
msg.msg_namelen = 0;
iov[0].iov_base = buf;
iov[0].iov_len = 100;
msg.msg_iov = iov;
msg.msg_iovlen = 1;
//设置缓冲区和长度
msg.msg_control = control_un.control;
msg.msg_controllen = sizeof(control_un.control);
//直接通过CMSG_FIRSTHDR取得附属数据
pcmsg = CMSG_FIRSTHDR(&msg);
pcmsg->cmsg_len = CMSG_LEN(sizeof(int));
pcmsg->cmsg_level = SOL_SOCKET;
pcmsg->cmsg_type = SCM_RIGHTS; //指明发送的是描述符
*((int*)CMSG_DATA(pcmsg)) == fd; //把描述符写入辅助数据
ret = sendmsg(clifd, &msg, 0); //send filedescriptor
printf ("ret = %d, filedescriptor = %d\n", ret, fd);
return 0 ;
}
gcc -o client client.c
server.c
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <stddef.h>
#include <string.h>
#include <sys/types.h>
#include <errno.h>
#include <sys/un.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <sys/epoll.h>
#include <fcntl.h>
#define UNIXSTR_PATH "foo.socket"
int main(int argc, char *argv[])
{
int clifd, listenfd;
struct sockaddr_un servaddr, cliaddr;
int ret;
socklen_t clilen;
struct msghdr msg;
struct iovec iov[1];
char buf [100];
char *testmsg = "test msg.\n";
union { //对齐
struct cmsghdr cm;
char control[CMSG_SPACE(sizeof(int))];
} control_un;
struct cmsghdr * pcmsg;
int recvfd;
listenfd = socket ( AF_UNIX , SOCK_STREAM , 0 ) ;
if(listenfd < 0) {
printf ( "socket failed.\n" ) ;
return -1;
}
unlink(UNIXSTR_PATH) ;
bzero (&servaddr, sizeof(servaddr));
servaddr.sun_family = AF_UNIX;
strcpy ( servaddr.sun_path , UNIXSTR_PATH ) ;
ret = bind ( listenfd, (struct sockaddr*)&servaddr, sizeof(servaddr));
if(ret < 0) {
printf ( "bind failed. errno = %d.\n" , errno ) ;
close(listenfd);
return - 1 ;
}
listen(listenfd, 5);
while(1) {
clilen = sizeof( cliaddr );
clifd = accept( listenfd, (struct sockaddr*)&cliaddr , &clilen);
if ( clifd < 0 ) {
printf ( "accept failed.\n" ) ;
continue ;
}
msg.msg_name = NULL;
msg.msg_namelen = 0;
//设置数据缓冲区
iov[0].iov_base = buf;
iov[0].iov_len = 100;
msg.msg_iov = iov;
msg.msg_iovlen = 1;
//设置辅助数据缓冲区和长度
msg.msg_control = control_un.control;
msg.msg_controllen = sizeof(control_un.control) ;
//接收
ret = recvmsg(clifd , &msg, 0);
if( ret <= 0 ) {
return ret;
}
//检查是否收到了辅助数据，以及长度
if((pcmsg = CMSG_FIRSTHDR(&msg) ) != NULL && ( pcmsg->cmsg_len == CMSG_LEN(sizeof(int)))) {
if ( pcmsg->cmsg_level != SOL_SOCKET ) {
printf("cmsg_leval is not SOL_SOCKET\n");
continue;
}
if ( pcmsg->cmsg_type != SCM_RIGHTS ) {
printf ( "cmsg_type is not SCM_RIGHTS" );
continue;
}
//这就是我们接收的描述符
recvfd = *((int*)CMSG_DATA(pcmsg));
printf ( "recv fd = %d\n", recvfd );
write ( recvfd, testmsg, strlen(testmsg) + 1);
}
}
return 0 ;
}
gcc -o server server.c
redhad有关虚拟化，kvm， vDPA, virtio/net, ceph存储的blog：
VMX(1) -- 简介，VMX(2) -- VMCS， VMX(3) -- VMXON Region，
丙部同学的 Virtio 基本概念和设备操作
1，前端填充好desc（addr/len），并更新vring->avail（ring[0]）
2，后端读取avail ring索引，找到desc(if ring[0]=2,then desctable[2] 记录的就是一个逻辑buffer的首个物理块的信息)，填充buffer数据；将buffer索引存在desc，将desc索引存放在used ring中
3，前端读取used ring索引，找到desc，获取buffer数据
